4047 files changed, 103952 insertions, 49867 deletions

diff --git a/Documentation/ABI/stable/sysfs-driver-usb-usbtmc b/Documentation/ABI/stable/sysfs-driver-usb-usbtmc
index 23a43b8207e6..2a7f9a00cb0a 100644
--- a/Documentation/ABI/stable/sysfs-driver-usb-usbtmc
+++ b/Documentation/ABI/stable/sysfs-driver-usb-usbtmc
@@ -55,7 +55,7 @@ What:		/sys/bus/usb/drivers/usbtmc/devices/*/auto_abort
 Date:		August 2008
 Contact:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 Description:
-		This file determines if the the transaction of the USB TMC
+		This file determines if the transaction of the USB TMC
 		device is to be automatically aborted if there is any error.
 		For more details about this, please see the document,
 		"Universal Serial Bus Test and Measurement Class Specification
diff --git a/Documentation/ABI/testing/debugfs-olpc b/Documentation/ABI/testing/debugfs-olpc
new file mode 100644
index 000000000000..bd76cc6d55f9
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-olpc
@@ -0,0 +1,16 @@
+What:		/sys/kernel/debug/olpc-ec/cmd
+Date:		Dec 2011
+KernelVersion:	3.4
+Contact:	devel@lists.laptop.org
+Description:
+
+A generic interface for executing OLPC Embedded Controller commands and
+reading their responses.
+
+To execute a command, write data with the format: CC:N A A A A
+CC is the (hex) command, N is the count of expected reply bytes, and A A A A
+are optional (hex) arguments.
+
+To read the response (if any), read from the generic node after executing
+a command. Hex reply bytes will be returned, *whether or not* they came from
+the immediately previous command.
diff --git a/Documentation/ABI/testing/sysfs-block-dm b/Documentation/ABI/testing/sysfs-block-dm
new file mode 100644
index 000000000000..87ca5691e29b
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-block-dm
@@ -0,0 +1,25 @@
+What:		/sys/block/dm-<num>/dm/name
+Date:		January 2009
+KernelVersion:	2.6.29
+Contact:	dm-devel@redhat.com
+Description:	Device-mapper device name.
+		Read-only string containing mapped device name.
+Users:		util-linux, device-mapper udev rules
+
+What:		/sys/block/dm-<num>/dm/uuid
+Date:		January 2009
+KernelVersion:	2.6.29
+Contact:	dm-devel@redhat.com
+Description:	Device-mapper device UUID.
+		Read-only string containing DM-UUID or empty string
+		if DM-UUID is not set.
+Users:		util-linux, device-mapper udev rules
+
+What:		/sys/block/dm-<num>/dm/suspended
+Date:		June 2009
+KernelVersion:	2.6.31
+Contact:	dm-devel@redhat.com
+Description:	Device-mapper device suspend state.
+		Contains the value 1 while the device is suspended.
+		Otherwise it contains 0. Read-only attribute.
+Users:		util-linux, device-mapper udev rules
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-format b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
new file mode 100644
index 000000000000..079afc71363d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
@@ -0,0 +1,14 @@
+Where:		/sys/bus/event_source/devices/<dev>/format
+Date:		January 2012
+Kernel Version: 3.3
+Contact:	Jiri Olsa <jolsa@redhat.com>
+Description:
+		Attribute group to describe the magic bits that go into
+		perf_event_attr::config[012] for a particular pmu.
+		Each attribute of this group defines the 'hardware' bitmask
+		we want to export, so that userspace can deal with sane
+		name/value pairs.
+
+		Example: 'config1:1,6-10,44'
+		Defines contents of attribute that occupies bits 1,6-10,44 of
+		perf_event_attr::config1.
diff --git a/Documentation/ABI/testing/sysfs-driver-samsung-laptop b/Documentation/ABI/testing/sysfs-driver-samsung-laptop
index e82e7c2b8f80..678819a3f8bf 100644
--- a/Documentation/ABI/testing/sysfs-driver-samsung-laptop
+++ b/Documentation/ABI/testing/sysfs-driver-samsung-laptop
@@ -17,3 +17,21 @@ Description:	Some Samsung laptops have different "performance levels"
 		Specifically, not all support the "overclock" option,
 		and it's still unknown if this value even changes
 		anything, other than making the user feel a bit better.
+
+What:		/sys/devices/platform/samsung/battery_life_extender
+Date:		December 1, 2011
+KernelVersion:	3.3
+Contact:	Corentin Chary <corentin.chary@gmail.com>
+Description:	Max battery charge level can be modified, battery cycle
+		life can be extended by reducing the max battery charge
+		level.
+		0 means normal battery mode (100% charge)
+		1 means battery life extender mode (80% charge)
+
+What:		/sys/devices/platform/samsung/usb_charge
+Date:		December 1, 2011
+KernelVersion:	3.3
+Contact:	Corentin Chary <corentin.chary@gmail.com>
+Description:	Use your USB ports to charge devices, even
+		when your laptop is powered off.
+		1 means enabled, 0 means disabled.
diff --git a/Documentation/ABI/testing/sysfs-firmware-acpi b/Documentation/ABI/testing/sysfs-firmware-acpi
index 4f9ba3c2fca7..dd930c8db41f 100644
--- a/Documentation/ABI/testing/sysfs-firmware-acpi
+++ b/Documentation/ABI/testing/sysfs-firmware-acpi
@@ -1,3 +1,23 @@
+What:		/sys/firmware/acpi/bgrt/
+Date:		January 2012
+Contact:	Matthew Garrett <mjg@redhat.com>
+Description:
+		The BGRT is an ACPI 5.0 feature that allows the OS
+		to obtain a copy of the firmware boot splash and
+		some associated metadata. This is intended to be used
+		by boot splash applications in order to interact with
+		the firmware boot splash in order to avoid jarring
+		transitions.
+
+		image: The image bitmap. Currently a 32-bit BMP.
+		status: 1 if the image is valid, 0 if firmware invalidated it.
+		type: 0 indicates image is in BMP format.
+		version: The version of the BGRT. Currently 1.
+		xoffset: The number of pixels between the left of the screen
+			 and the left edge of the image.
+		yoffset: The number of pixels between the top of the screen
+			 and the top edge of the image.
+
 What:		/sys/firmware/acpi/interrupts/
 Date:		February 2008
 Contact:	Len Brown <lenb@kernel.org>
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index 2b90d328b3ba..c58b236bbe04 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -793,6 +793,35 @@ own custom mode, or may have some other magic method for making indentation
 work correctly.
 
 
+		Chapter 19:  Inline assembly
+
+In architecture-specific code, you may need to use inline assembly to interface
+with CPU or platform functionality.  Don't hesitate to do so when necessary.
+However, don't use inline assembly gratuitously when C can do the job.  You can
+and should poke hardware from C when possible.
+
+Consider writing simple helper functions that wrap common bits of inline
+assembly, rather than repeatedly writing them with slight variations.  Remember
+that inline assembly can use C parameters.
+
+Large, non-trivial assembly functions should go in .S files, with corresponding
+C prototypes defined in C header files.  The C prototypes for assembly
+functions should use "asmlinkage".
+
+You may need to mark your asm statement as volatile, to prevent GCC from
+removing it if GCC doesn't notice any side effects.  You don't always need to
+do so, though, and doing so unnecessarily can limit optimization.
+
+When writing a single inline assembly statement containing multiple
+instructions, put each instruction on a separate line in a separate quoted
+string, and end each string except the last with \n\t to properly indent the
+next instruction in the assembly output:
+
+	asm ("magic %reg1, #42\n\t"
+	     "more_magic %reg2, %reg3"
+	     : /* outputs */ : /* inputs */ : /* clobbers */);
+
+
 
 		Appendix I: References
 
diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index b768cc0e402b..5c72eed89563 100644
--- a/Documentation/DMA-attributes.txt
+++ b/Documentation/DMA-attributes.txt
@@ -31,3 +31,21 @@ may be weakly ordered, that is that reads and writes may pass each other.
 Since it is optional for platforms to implement DMA_ATTR_WEAK_ORDERING,
 those that do not will simply ignore the attribute and exhibit default
 behavior.
+
+DMA_ATTR_WRITE_COMBINE
+----------------------
+
+DMA_ATTR_WRITE_COMBINE specifies that writes to the mapping may be
+buffered to improve performance.
+
+Since it is optional for platforms to implement DMA_ATTR_WRITE_COMBINE,
+those that do not will simply ignore the attribute and exhibit default
+behavior.
+
+DMA_ATTR_NON_CONSISTENT
+-----------------------
+
+DMA_ATTR_NON_CONSISTENT lets the platform to choose to return either
+consistent or non-consistent memory as it sees fit.  By using this API,
+you are guaranteeing to the platform that you have all the correct and
+necessary sync points for this memory in the driver.
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index 9c27e5125dd2..7514dbf0a679 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -446,4 +446,21 @@ X!Idrivers/video/console/fonts.c
 !Edrivers/i2c/i2c-core.c
   </chapter>
 
+  <chapter id="hsi">
+     <title>High Speed Synchronous Serial Interface (HSI)</title>
+
+     <para>
+	High Speed Synchronous Serial Interface (HSI) is a
+	serial interface mainly used for connecting application
+	engines (APE) with cellular modem engines (CMT) in cellular
+	handsets.
+
+	HSI provides multiplexing for up to 16 logical channels,
+	low-latency and full duplex communication.
+     </para>
+
+!Iinclude/linux/hsi/hsi.h
+!Edrivers/hsi/hsi.c
+  </chapter>
+
 </book>
diff --git a/Documentation/Makefile b/Documentation/Makefile
index 9b4bc5c76f33..30b656ece7aa 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -1,3 +1,3 @@
 obj-m := DocBook/ accounting/ auxdisplay/ connector/ \
 	filesystems/ filesystems/configfs/ ia64/ laptops/ networking/ \
-	pcmcia/ spi/ timers/ vm/ watchdog/src/
+	pcmcia/ spi/ timers/ watchdog/src/
diff --git a/Documentation/acpi/apei/einj.txt b/Documentation/acpi/apei/einj.txt
index e7cc36397217..e20b6daaced4 100644
--- a/Documentation/acpi/apei/einj.txt
+++ b/Documentation/acpi/apei/einj.txt
@@ -53,6 +53,14 @@ directory apei/einj. The following files are provided.
   This file is used to set the second error parameter value. Effect of
   parameter depends on error_type specified.
 
+- notrigger
+  The EINJ mechanism is a two step process. First inject the error, then
+  perform some actions to trigger it. Setting "notrigger" to 1 skips the
+  trigger phase, which *may* allow the user to cause the error in some other
+  context by a simple access to the cpu, memory location, or device that is
+  the target of the error injection. Whether this actually works depends
+  on what operations the BIOS actually includes in the trigger phase.
+
 BIOS versions based in the ACPI 4.0 specification have limited options
 to control where the errors are injected.  Your BIOS may support an
 extension (enabled with the param_extension=1 module parameter, or
diff --git a/Documentation/aoe/aoe.txt b/Documentation/aoe/aoe.txt
index b5aada9f20cc..5f5aa16047ff 100644
--- a/Documentation/aoe/aoe.txt
+++ b/Documentation/aoe/aoe.txt
@@ -35,7 +35,7 @@ CREATING DEVICE NODES
     sh Documentation/aoe/mkshelf.sh /dev/etherd 0
 
   There is also an autoload script that shows how to edit
-  /etc/modprobe.conf to ensure that the aoe module is loaded when
+  /etc/modprobe.d/aoe.conf to ensure that the aoe module is loaded when
   necessary.
 
 USING DEVICE NODES
diff --git a/Documentation/aoe/autoload.sh b/Documentation/aoe/autoload.sh
index 78dad1334c6f..815dff4691c9 100644
--- a/Documentation/aoe/autoload.sh
+++ b/Documentation/aoe/autoload.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 # set aoe to autoload by installing the
-# aliases in /etc/modprobe.conf
+# aliases in /etc/modprobe.d/
 
-f=/etc/modprobe.conf
+f=/etc/modprobe.d/aoe.conf
 
 if test ! -r $f || test ! -w $f; then
 	echo "cannot configure $f for module autoloading" 1>&2
diff --git a/Documentation/blockdev/floppy.txt b/Documentation/blockdev/floppy.txt
index 6ccab88705cb..470fe4b5e379 100644
--- a/Documentation/blockdev/floppy.txt
+++ b/Documentation/blockdev/floppy.txt
@@ -49,7 +49,7 @@ you can put:
 
  options floppy omnibook messages
 
-in /etc/modprobe.conf.
+in a configuration file in /etc/modprobe.d/.
 
 
  The floppy driver related options are:
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 5c51ed406d1d..cefd3d8bbd11 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -217,7 +217,7 @@ and name space for cpusets, with a minimum of additional kernel code.
 
 The cpus and mems files in the root (top_cpuset) cpuset are
 read-only.  The cpus file automatically tracks the value of
-cpu_online_map using a CPU hotplug notifier, and the mems file
+cpu_online_mask using a CPU hotplug notifier, and the mems file
 automatically tracks the value of node_states[N_HIGH_MEMORY]--i.e.,
 nodes with memory--using the cpuset_track_online_nodes() hook.
 
diff --git a/Documentation/clk.txt b/Documentation/clk.txt
new file mode 100644
index 000000000000..1943fae014fd
--- /dev/null
+++ b/Documentation/clk.txt
@@ -0,0 +1,233 @@
+		The Common Clk Framework
+		Mike Turquette <mturquette@ti.com>
+
+This document endeavours to explain the common clk framework details,
+and how to port a platform over to this framework.  It is not yet a
+detailed explanation of the clock api in include/linux/clk.h, but
+perhaps someday it will include that information.
+
+	Part 1 - introduction and interface split
+
+The common clk framework is an interface to control the clock nodes
+available on various devices today.  This may come in the form of clock
+gating, rate adjustment, muxing or other operations.  This framework is
+enabled with the CONFIG_COMMON_CLK option.
+
+The interface itself is divided into two halves, each shielded from the
+details of its counterpart.  First is the common definition of struct
+clk which unifies the framework-level accounting and infrastructure that
+has traditionally been duplicated across a variety of platforms.  Second
+is a common implementation of the clk.h api, defined in
+drivers/clk/clk.c.  Finally there is struct clk_ops, whose operations
+are invoked by the clk api implementation.
+
+The second half of the interface is comprised of the hardware-specific
+callbacks registered with struct clk_ops and the corresponding
+hardware-specific structures needed to model a particular clock.  For
+the remainder of this document any reference to a callback in struct
+clk_ops, such as .enable or .set_rate, implies the hardware-specific
+implementation of that code.  Likewise, references to struct clk_foo
+serve as a convenient shorthand for the implementation of the
+hardware-specific bits for the hypothetical "foo" hardware.
+
+Tying the two halves of this interface together is struct clk_hw, which
+is defined in struct clk_foo and pointed to within struct clk.  This
+allows easy for navigation between the two discrete halves of the common
+clock interface.
+
+	Part 2 - common data structures and api
+
+Below is the common struct clk definition from
+include/linux/clk-private.h, modified for brevity:
+
+	struct clk {
+		const char		*name;
+		const struct clk_ops	*ops;
+		struct clk_hw		*hw;
+		char			**parent_names;
+		struct clk		**parents;
+		struct clk		*parent;
+		struct hlist_head	children;
+		struct hlist_node	child_node;
+		...
+	};
+
+The members above make up the core of the clk tree topology.  The clk
+api itself defines several driver-facing functions which operate on
+struct clk.  That api is documented in include/linux/clk.h.
+
+Platforms and devices utilizing the common struct clk use the struct
+clk_ops pointer in struct clk to perform the hardware-specific parts of
+the operations defined in clk.h:
+
+	struct clk_ops {
+		int		(*prepare)(struct clk_hw *hw);
+		void		(*unprepare)(struct clk_hw *hw);
+		int		(*enable)(struct clk_hw *hw);
+		void		(*disable)(struct clk_hw *hw);
+		int		(*is_enabled)(struct clk_hw *hw);
+		unsigned long	(*recalc_rate)(struct clk_hw *hw,
+						unsigned long parent_rate);
+		long		(*round_rate)(struct clk_hw *hw, unsigned long,
+						unsigned long *);
+		int		(*set_parent)(struct clk_hw *hw, u8 index);
+		u8		(*get_parent)(struct clk_hw *hw);
+		int		(*set_rate)(struct clk_hw *hw, unsigned long);
+		void		(*init)(struct clk_hw *hw);
+	};
+
+	Part 3 - hardware clk implementations
+
+The strength of the common struct clk comes from its .ops and .hw pointers
+which abstract the details of struct clk from the hardware-specific bits, and
+vice versa.  To illustrate consider the simple gateable clk implementation in
+drivers/clk/clk-gate.c:
+
+struct clk_gate {
+	struct clk_hw	hw;
+	void __iomem    *reg;
+	u8              bit_idx;
+	...
+};
+
+struct clk_gate contains struct clk_hw hw as well as hardware-specific
+knowledge about which register and bit controls this clk's gating.
+Nothing about clock topology or accounting, such as enable_count or
+notifier_count, is needed here.  That is all handled by the common
+framework code and struct clk.
+
+Let's walk through enabling this clk from driver code:
+
+	struct clk *clk;
+	clk = clk_get(NULL, "my_gateable_clk");
+
+	clk_prepare(clk);
+	clk_enable(clk);
+
+The call graph for clk_enable is very simple:
+
+clk_enable(clk);
+	clk->ops->enable(clk->hw);
+	[resolves to...]
+		clk_gate_enable(hw);
+		[resolves struct clk gate with to_clk_gate(hw)]
+			clk_gate_set_bit(gate);
+
+And the definition of clk_gate_set_bit:
+
+static void clk_gate_set_bit(struct clk_gate *gate)
+{
+	u32 reg;
+
+	reg = __raw_readl(gate->reg);
+	reg |= BIT(gate->bit_idx);
+	writel(reg, gate->reg);
+}
+
+Note that to_clk_gate is defined as:
+
+#define to_clk_gate(_hw) container_of(_hw, struct clk_gate, clk)
+
+This pattern of abstraction is used for every clock hardware
+representation.
+
+	Part 4 - supporting your own clk hardware
+
+When implementing support for a new type of clock it only necessary to
+include the following header:
+
+#include <linux/clk-provider.h>
+
+include/linux/clk.h is included within that header and clk-private.h
+must never be included from the code which implements the operations for
+a clock.  More on that below in Part 5.
+
+To construct a clk hardware structure for your platform you must define
+the following:
+
+struct clk_foo {
+	struct clk_hw hw;
+	... hardware specific data goes here ...
+};
+
+To take advantage of your data you'll need to support valid operations
+for your clk:
+
+struct clk_ops clk_foo_ops {
+	.enable		= &clk_foo_enable;
+	.disable	= &clk_foo_disable;
+};
+
+Implement the above functions using container_of:
+
+#define to_clk_foo(_hw) container_of(_hw, struct clk_foo, hw)
+
+int clk_foo_enable(struct clk_hw *hw)
+{
+	struct clk_foo *foo;
+
+	foo = to_clk_foo(hw);
+
+	... perform magic on foo ...
+
+	return 0;
+};
+
+Below is a matrix detailing which clk_ops are mandatory based upon the
+hardware capbilities of that clock.  A cell marked as "y" means
+mandatory, a cell marked as "n" implies that either including that
+callback is invalid or otherwise uneccesary.  Empty cells are either
+optional or must be evaluated on a case-by-case basis.
+
+                           clock hardware characteristics
+	     -----------------------------------------------------------
+             | gate | change rate | single parent | multiplexer | root |
+             |------|-------------|---------------|-------------|------|
+.prepare     |      |             |               |             |      |
+.unprepare   |      |             |               |             |      |
+             |      |             |               |             |      |
+.enable      | y    |             |               |             |      |
+.disable     | y    |             |               |             |      |
+.is_enabled  | y    |             |               |             |      |
+             |      |             |               |             |      |
+.recalc_rate |      | y           |               |             |      |
+.round_rate  |      | y           |               |             |      |
+.set_rate    |      | y           |               |             |      |
+             |      |             |               |             |      |
+.set_parent  |      |             | n             | y           | n    |
+.get_parent  |      |             | n             | y           | n    |
+             |      |             |               |             |      |
+.init        |      |             |               |             |      |
+	     -----------------------------------------------------------
+
+Finally, register your clock at run-time with a hardware-specific
+registration function.  This function simply populates struct clk_foo's
+data and then passes the common struct clk parameters to the framework
+with a call to:
+
+clk_register(...)
+
+See the basic clock types in drivers/clk/clk-*.c for examples.
+
+	Part 5 - static initialization of clock data
+
+For platforms with many clocks (often numbering into the hundreds) it
+may be desirable to statically initialize some clock data.  This
+presents a problem since the definition of struct clk should be hidden
+from everyone except for the clock core in drivers/clk/clk.c.
+
+To get around this problem struct clk's definition is exposed in
+include/linux/clk-private.h along with some macros for more easily
+initializing instances of the basic clock types.  These clocks must
+still be initialized with the common clock framework via a call to
+__clk_init.
+
+clk-private.h must NEVER be included by code which implements struct
+clk_ops callbacks, nor must it be included by any logic which pokes
+around inside of struct clk at run-time.  To do so is a layering
+violation.
+
+To better enforce this policy, always follow this simple rule: any
+statically initialized clock data MUST be defined in a separate file
+from the logic that implements its ops.  Basically separate the logic
+from the data and all is well.
diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
index a20bfd415e41..66ef8f35613d 100644
--- a/Documentation/cpu-hotplug.txt
+++ b/Documentation/cpu-hotplug.txt
@@ -47,7 +47,7 @@ maxcpus=n    Restrict boot time cpus to n. Say if you have 4 cpus, using
              other cpus later online, read FAQ's for more info.
 
 additional_cpus=n (*)	Use this to limit hotpluggable cpus. This option sets
-  			cpu_possible_map = cpu_present_map + additional_cpus
+  			cpu_possible_mask = cpu_present_mask + additional_cpus
 
 cede_offline={"off","on"}  Use this option to disable/enable putting offlined
 		            processors to an extended H_CEDE state on
@@ -64,11 +64,11 @@ should only rely on this to count the # of cpus, but *MUST* not rely
 on the apicid values in those tables for disabled apics. In the event
 BIOS doesn't mark such hot-pluggable cpus as disabled entries, one could
 use this parameter "additional_cpus=x" to represent those cpus in the
-cpu_possible_map.
+cpu_possible_mask.
 
 possible_cpus=n		[s390,x86_64] use this to set hotpluggable cpus.
 			This option sets possible_cpus bits in
-			cpu_possible_map. Thus keeping the numbers of bits set
+			cpu_possible_mask. Thus keeping the numbers of bits set
 			constant even if the machine gets rebooted.
 
 CPU maps and such
@@ -76,7 +76,7 @@ CPU maps and such
 [More on cpumaps and primitive to manipulate, please check
 include/linux/cpumask.h that has more descriptive text.]
 
-cpu_possible_map: Bitmap of possible CPUs that can ever be available in the
+cpu_possible_mask: Bitmap of possible CPUs that can ever be available in the
 system. This is used to allocate some boot time memory for per_cpu variables
 that aren't designed to grow/shrink as CPUs are made available or removed.
 Once set during boot time discovery phase, the map is static, i.e no bits
@@ -84,13 +84,13 @@ are added or removed anytime.  Trimming it accurately for your system needs
 upfront can save some boot time memory. See below for how we use heuristics
 in x86_64 case to keep this under check.
 
-cpu_online_map: Bitmap of all CPUs currently online. Its set in __cpu_up()
+cpu_online_mask: Bitmap of all CPUs currently online. Its set in __cpu_up()
 after a cpu is available for kernel scheduling and ready to receive
 interrupts from devices. Its cleared when a cpu is brought down using
 __cpu_disable(), before which all OS services including interrupts are
 migrated to another target CPU.
 
-cpu_present_map: Bitmap of CPUs currently present in the system. Not all
+cpu_present_mask: Bitmap of CPUs currently present in the system. Not all
 of them may be online. When physical hotplug is processed by the relevant
 subsystem (e.g ACPI) can change and new bit either be added or removed
 from the map depending on the event is hot-add/hot-remove. There are currently
@@ -99,22 +99,22 @@ at which time hotplug is disabled.
 
 You really dont need to manipulate any of the system cpu maps. They should
 be read-only for most use. When setting up per-cpu resources almost always use
-cpu_possible_map/for_each_possible_cpu() to iterate.
+cpu_possible_mask/for_each_possible_cpu() to iterate.
 
 Never use anything other than cpumask_t to represent bitmap of CPUs.
 
 	#include <linux/cpumask.h>
 
-	for_each_possible_cpu     - Iterate over cpu_possible_map
-	for_each_online_cpu       - Iterate over cpu_online_map
-	for_each_present_cpu      - Iterate over cpu_present_map
+	for_each_possible_cpu     - Iterate over cpu_possible_mask
+	for_each_online_cpu       - Iterate over cpu_online_mask
+	for_each_present_cpu      - Iterate over cpu_present_mask
 	for_each_cpu_mask(x,mask) - Iterate over some random collection of cpu mask.
 
 	#include <linux/cpu.h>
 	get_online_cpus() and put_online_cpus():
 
 The above calls are used to inhibit cpu hotplug operations. While the
-cpu_hotplug.refcount is non zero, the cpu_online_map will not change.
+cpu_hotplug.refcount is non zero, the cpu_online_mask will not change.
 If you merely need to avoid cpus going away, you could also use
 preempt_disable() and preempt_enable() for those sections.
 Just remember the critical section cannot call any
diff --git a/Documentation/cpuidle/sysfs.txt b/Documentation/cpuidle/sysfs.txt
index 50d7b1642759..9d28a3406e74 100644
--- a/Documentation/cpuidle/sysfs.txt
+++ b/Documentation/cpuidle/sysfs.txt
@@ -36,6 +36,7 @@ drwxr-xr-x 2 root root 0 Feb  8 10:42 state3
 /sys/devices/system/cpu/cpu0/cpuidle/state0:
 total 0
 -r--r--r-- 1 root root 4096 Feb  8 10:42 desc
+-rw-r--r-- 1 root root 4096 Feb  8 10:42 disable
 -r--r--r-- 1 root root 4096 Feb  8 10:42 latency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 name
 -r--r--r-- 1 root root 4096 Feb  8 10:42 power
@@ -45,6 +46,7 @@ total 0
 /sys/devices/system/cpu/cpu0/cpuidle/state1:
 total 0
 -r--r--r-- 1 root root 4096 Feb  8 10:42 desc
+-rw-r--r-- 1 root root 4096 Feb  8 10:42 disable
 -r--r--r-- 1 root root 4096 Feb  8 10:42 latency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 name
 -r--r--r-- 1 root root 4096 Feb  8 10:42 power
@@ -54,6 +56,7 @@ total 0
 /sys/devices/system/cpu/cpu0/cpuidle/state2:
 total 0
 -r--r--r-- 1 root root 4096 Feb  8 10:42 desc
+-rw-r--r-- 1 root root 4096 Feb  8 10:42 disable
 -r--r--r-- 1 root root 4096 Feb  8 10:42 latency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 name
 -r--r--r-- 1 root root 4096 Feb  8 10:42 power
@@ -63,6 +66,7 @@ total 0
 /sys/devices/system/cpu/cpu0/cpuidle/state3:
 total 0
 -r--r--r-- 1 root root 4096 Feb  8 10:42 desc
+-rw-r--r-- 1 root root 4096 Feb  8 10:42 disable
 -r--r--r-- 1 root root 4096 Feb  8 10:42 latency
 -r--r--r-- 1 root root 4096 Feb  8 10:42 name
 -r--r--r-- 1 root root 4096 Feb  8 10:42 power
@@ -72,6 +76,7 @@ total 0
 
 
 * desc : Small description about the idle state (string)
+* disable : Option to disable this idle state (bool)
 * latency : Latency to exit out of this idle state (in microseconds)
 * name : Name of the idle state (string)
 * power : Power consumed while in this idle state (in milliwatts)
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 1ff044d87ca4..3370bc4d7b98 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -75,10 +75,12 @@ less sharing than average you'll need a larger-than-average metadata device.
 
 As a guide, we suggest you calculate the number of bytes to use in the
 metadata device as 48 * $data_dev_size / $data_block_size but round it up
-to 2MB if the answer is smaller.  The largest size supported is 16GB.
+to 2MB if the answer is smaller.  If you're creating large numbers of
+snapshots which are recording large amounts of change, you may find you
+need to increase this.
 
-If you're creating large numbers of snapshots which are recording large
-amounts of change, you may need find you need to increase this.
+The largest size supported is 16GB: If the device is larger,
+a warning will be issued and the excess space will not be used.
 
 Reloading a pool table
 ----------------------
@@ -167,6 +169,38 @@ ii) Using an internal snapshot.
 
     dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 1"
 
+External snapshots
+------------------
+
+You can use an external _read only_ device as an origin for a
+thinly-provisioned volume.  Any read to an unprovisioned area of the
+thin device will be passed through to the origin.  Writes trigger
+the allocation of new blocks as usual.
+
+One use case for this is VM hosts that want to run guests on
+thinly-provisioned volumes but have the base image on another device
+(possibly shared between many VMs).
+
+You must not write to the origin device if you use this technique!
+Of course, you may write to the thin device and take internal snapshots
+of the thin volume.
+
+i) Creating a snapshot of an external device
+
+  This is the same as creating a thin device.
+  You don't mention the origin at this stage.
+
+    dmsetup message /dev/mapper/pool 0 "create_thin 0"
+
+ii) Using a snapshot of an external device.
+
+  Append an extra parameter to the thin target specifying the origin:
+
+    dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 0 /dev/image"
+
+  N.B. All descendants (internal snapshots) of this snapshot require the
+  same extra origin parameter.
+
 Deactivation
 ------------
 
@@ -189,7 +223,13 @@ i) Constructor
 	      <low water mark (blocks)> [<number of feature args> [<arg>]*]
 
     Optional feature arguments:
-    - 'skip_block_zeroing': skips the zeroing of newly-provisioned blocks.
+
+      skip_block_zeroing: Skip the zeroing of newly-provisioned blocks.
+
+      ignore_discard: Disable discard support.
+
+      no_discard_passdown: Don't pass discards down to the underlying
+			   data device, but just remove the mapping.
 
     Data block size must be between 64KB (128 sectors) and 1GB
     (2097152 sectors) inclusive.
@@ -237,16 +277,6 @@ iii) Messages
 
 	Deletes a thin device.  Irreversible.
 
-    trim <dev id> <new size in sectors>
-
-	Delete mappings from the end of a thin device.  Irreversible.
-	You might want to use this if you're reducing the size of
-	your thinly-provisioned device.  In many cases, due to the
-	sharing of blocks between devices, it is not possible to
-	determine in advance how much space 'trim' will release.  (In
-	future a userspace tool might be able to perform this
-	calculation.)
-
     set_transaction_id <current id> <new id>
 
 	Userland volume managers, such as LVM, need a way to
@@ -262,7 +292,7 @@ iii) Messages
 
 i) Constructor
 
-    thin <pool dev> <dev id>
+    thin <pool dev> <dev id> [<external origin dev>]
 
     pool dev:
 	the thin-pool device, e.g. /dev/mapper/my_pool or 253:0
@@ -271,6 +301,11 @@ i) Constructor
 	the internal device identifier of the device to be
 	activated.
 
+    external origin dev:
+	an optional block device outside the pool to be treated as a
+	read-only snapshot origin: reads to unprovisioned areas of the
+	thin target will be mapped to this device.
+
 The pool doesn't store any size against the thin devices.  If you
 load a thin target that is smaller than you've been using previously,
 then you'll have no access to blocks mapped beyond the end.  If you
diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt
new file mode 100644
index 000000000000..32e48797a14f
--- /dev/null
+++ b/Documentation/device-mapper/verity.txt
@@ -0,0 +1,194 @@
+dm-verity
+==========
+
+Device-Mapper's "verity" target provides transparent integrity checking of
+block devices using a cryptographic digest provided by the kernel crypto API.
+This target is read-only.
+
+Construction Parameters
+=======================
+    <version> <dev> <hash_dev> <hash_start>
+    <data_block_size> <hash_block_size>
+    <num_data_blocks> <hash_start_block>
+    <algorithm> <digest> <salt>
+
+<version>
+    This is the version number of the on-disk format.
+
+    0 is the original format used in the Chromium OS.
+	The salt is appended when hashing, digests are stored continuously and
+	the rest of the block is padded with zeros.
+
+    1 is the current format that should be used for new devices.
+	The salt is prepended when hashing and each digest is
+	padded with zeros to the power of two.
+
+<dev>
+    This is the device containing the data the integrity of which needs to be
+    checked.  It may be specified as a path, like /dev/sdaX, or a device number,
+    <major>:<minor>.
+
+<hash_dev>
+    This is the device that that supplies the hash tree data.  It may be
+    specified similarly to the device path and may be the same device.  If the
+    same device is used, the hash_start should be outside of the dm-verity
+    configured device size.
+
+<data_block_size>
+    The block size on a data device.  Each block corresponds to one digest on
+    the hash device.
+
+<hash_block_size>
+    The size of a hash block.
+
+<num_data_blocks>
+    The number of data blocks on the data device.  Additional blocks are
+    inaccessible.  You can place hashes to the same partition as data, in this
+    case hashes are placed after <num_data_blocks>.
+
+<hash_start_block>
+    This is the offset, in <hash_block_size>-blocks, from the start of hash_dev
+    to the root block of the hash tree.
+
+<algorithm>
+    The cryptographic hash algorithm used for this device.  This should
+    be the name of the algorithm, like "sha1".
+
+<digest>
+    The hexadecimal encoding of the cryptographic hash of the root hash block
+    and the salt.  This hash should be trusted as there is no other authenticity
+    beyond this point.
+
+<salt>
+    The hexadecimal encoding of the salt value.
+
+Theory of operation
+===================
+
+dm-verity is meant to be setup as part of a verified boot path.  This
+may be anything ranging from a boot using tboot or trustedgrub to just
+booting from a known-good device (like a USB drive or CD).
+
+When a dm-verity device is configured, it is expected that the caller
+has been authenticated in some way (cryptographic signatures, etc).
+After instantiation, all hashes will be verified on-demand during
+disk access.  If they cannot be verified up to the root node of the
+tree, the root hash, then the I/O will fail.  This should identify
+tampering with any data on the device and the hash data.
+
+Cryptographic hashes are used to assert the integrity of the device on a
+per-block basis.  This allows for a lightweight hash computation on first read
+into the page cache.  Block hashes are stored linearly-aligned to the nearest
+block the size of a page.
+
+Hash Tree
+---------
+
+Each node in the tree is a cryptographic hash.  If it is a leaf node, the hash
+is of some block data on disk.  If it is an intermediary node, then the hash is
+of a number of child nodes.
+
+Each entry in the tree is a collection of neighboring nodes that fit in one
+block.  The number is determined based on block_size and the size of the
+selected cryptographic digest algorithm.  The hashes are linearly-ordered in
+this entry and any unaligned trailing space is ignored but included when
+calculating the parent node.
+
+The tree looks something like:
+
+alg = sha256, num_blocks = 32768, block_size = 4096
+
+                                 [   root    ]
+                                /    . . .    \
+                     [entry_0]                 [entry_1]
+                    /  . . .  \                 . . .   \
+         [entry_0_0]   . . .  [entry_0_127]    . . . .  [entry_1_127]
+           / ... \             /   . . .  \             /           \
+     blk_0 ... blk_127  blk_16256   blk_16383      blk_32640 . . . blk_32767
+
+
+On-disk format
+==============
+
+Below is the recommended on-disk format. The verity kernel code does not
+read the on-disk header. It only reads the hash blocks which directly
+follow the header. It is expected that a user-space tool will verify the
+integrity of the verity_header and then call dmsetup with the correct
+parameters. Alternatively, the header can be omitted and the dmsetup
+parameters can be passed via the kernel command-line in a rooted chain
+of trust where the command-line is verified.
+
+The on-disk format is especially useful in cases where the hash blocks
+are on a separate partition. The magic number allows easy identification
+of the partition contents. Alternatively, the hash blocks can be stored
+in the same partition as the data to be verified. In such a configuration
+the filesystem on the partition would be sized a little smaller than
+the full-partition, leaving room for the hash blocks.
+
+struct superblock {
+	uint8_t signature[8]
+		"verity\0\0";
+
+	uint8_t version;
+		1 - current format
+
+	uint8_t data_block_bits;
+		log2(data block size)
+
+	uint8_t hash_block_bits;
+		log2(hash block size)
+
+	uint8_t pad1[1];
+		zero padding
+
+	uint16_t salt_size;
+		big-endian salt size
+
+	uint8_t pad2[2];
+		zero padding
+
+	uint32_t data_blocks_hi;
+		big-endian high 32 bits of the 64-bit number of data blocks
+
+	uint32_t data_blocks_lo;
+		big-endian low 32 bits of the 64-bit number of data blocks
+
+	uint8_t algorithm[16];
+		cryptographic algorithm
+
+	uint8_t salt[384];
+		salt (the salt size is specified above)
+
+	uint8_t pad3[88];
+		zero padding to 512-byte boundary
+}
+
+Directly following the header (and with sector number padded to the next hash
+block boundary) are the hash blocks which are stored a depth at a time
+(starting from the root), sorted in order of increasing index.
+
+Status
+======
+V (for Valid) is returned if every check performed so far was valid.
+If any check failed, C (for Corruption) is returned.
+
+Example
+=======
+
+Setup a device:
+  dmsetup create vroot --table \
+    "0 2097152 "\
+    "verity 1 /dev/sda1 /dev/sda2 4096 4096 2097152 1 "\
+    "4392712ba01368efdf14b05c76f9e4df0d53664630b5d48632ed17a137f39076 "\
+    "1234000000000000000000000000000000000000000000000000000000000000"
+
+A command line tool veritysetup is available to compute or verify
+the hash tree or activate the kernel driver.  This is available from
+the LVM2 upstream repository and may be supplied as a package called
+device-mapper-verity-tools:
+    git://sources.redhat.com/git/lvm2
+    http://sourceware.org/git/?p=lvm2.git
+    http://sourceware.org/cgi-bin/cvsweb.cgi/LVM2/verity?cvsroot=lvm2
+
+veritysetup -a vroot /dev/sda1 /dev/sda2 \
+	4392712ba01368efdf14b05c76f9e4df0d53664630b5d48632ed17a137f39076
diff --git a/Documentation/devicetree/bindings/arm/atmel-at91.txt b/Documentation/devicetree/bindings/arm/atmel-at91.txt
index 1aeaf6f2a1ba..ecc81e368715 100644
--- a/Documentation/devicetree/bindings/arm/atmel-at91.txt
+++ b/Documentation/devicetree/bindings/arm/atmel-at91.txt
@@ -30,3 +30,63 @@ One interrupt per TC channel in a TC block:
 		reg = <0xfffdc000 0x100>;
 		interrupts = <26 4 27 4 28 4>;
 	};
+
+RSTC Reset Controller required properties:
+- compatible: Should be "atmel,<chip>-rstc".
+  <chip> can be "at91sam9260" or "at91sam9g45"
+- reg: Should contain registers location and length
+
+Example:
+
+	rstc@fffffd00 {
+		compatible = "atmel,at91sam9260-rstc";
+		reg = <0xfffffd00 0x10>;
+	};
+
+RAMC SDRAM/DDR Controller required properties:
+- compatible: Should be "atmel,at91sam9260-sdramc",
+			"atmel,at91sam9g45-ddramc",
+- reg: Should contain registers location and length
+  For at91sam9263 and at91sam9g45 you must specify 2 entries.
+
+Examples:
+
+	ramc0: ramc@ffffe800 {
+		compatible = "atmel,at91sam9g45-ddramc";
+		reg = <0xffffe800 0x200>;
+	};
+
+	ramc0: ramc@ffffe400 {
+		compatible = "atmel,at91sam9g45-ddramc";
+		reg = <0xffffe400 0x200
+		       0xffffe600 0x200>;
+	};
+
+SHDWC Shutdown Controller
+
+required properties:
+- compatible: Should be "atmel,<chip>-shdwc".
+  <chip> can be "at91sam9260", "at91sam9rl" or "at91sam9x5".
+- reg: Should contain registers location and length
+
+optional properties:
+- atmel,wakeup-mode: String, operation mode of the wakeup mode.
+  Supported values are: "none", "high", "low", "any".
+- atmel,wakeup-counter: Counter on Wake-up 0 (between 0x0 and 0xf).
+
+optional at91sam9260 properties:
+- atmel,wakeup-rtt-timer: boolean to enable Real-time Timer Wake-up.
+
+optional at91sam9rl properties:
+- atmel,wakeup-rtc-timer: boolean to enable Real-time Clock Wake-up.
+- atmel,wakeup-rtt-timer: boolean to enable Real-time Timer Wake-up.
+
+optional at91sam9x5 properties:
+- atmel,wakeup-rtc-timer: boolean to enable Real-time Clock Wake-up.
+
+Example:
+
+	rstc@fffffd00 {
+		compatible = "atmel,at91sam9260-rstc";
+		reg = <0xfffffd00 0x10>;
+	};
diff --git a/Documentation/devicetree/bindings/arm/atmel-pmc.txt b/Documentation/devicetree/bindings/arm/atmel-pmc.txt
new file mode 100644
index 000000000000..389bed5056e8
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/atmel-pmc.txt
@@ -0,0 +1,11 @@
+* Power Management Controller (PMC)
+
+Required properties:
+- compatible: Should be "atmel,at91rm9200-pmc"
+- reg: Should contain PMC registers location and length
+
+Examples:
+	pmc: pmc@fffffc00 {
+		compatible = "atmel,at91rm9200-pmc";
+		reg = <0xfffffc00 0x100>;
+	};
diff --git a/Documentation/devicetree/bindings/arm/spear.txt b/Documentation/devicetree/bindings/arm/spear.txt
new file mode 100644
index 000000000000..f8e54f092328
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/spear.txt
@@ -0,0 +1,8 @@
+ST SPEAr Platforms Device Tree Bindings
+---------------------------------------
+
+Boards with the ST SPEAr600 SoC shall have the following properties:
+
+Required root node property:
+
+compatible = "st,spear600";
diff --git a/Documentation/devicetree/bindings/gpio/gpio-omap.txt b/Documentation/devicetree/bindings/gpio/gpio-omap.txt
new file mode 100644
index 000000000000..bff51a2fee1e
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-omap.txt
@@ -0,0 +1,36 @@
+OMAP GPIO controller bindings
+
+Required properties:
+- compatible:
+  - "ti,omap2-gpio" for OMAP2 controllers
+  - "ti,omap3-gpio" for OMAP3 controllers
+  - "ti,omap4-gpio" for OMAP4 controllers
+- #gpio-cells : Should be two.
+  - first cell is the pin number
+  - second cell is used to specify optional parameters (unused)
+- gpio-controller : Marks the device node as a GPIO controller.
+- #interrupt-cells : Should be 2.
+- interrupt-controller: Mark the device node as an interrupt controller
+  The first cell is the GPIO number.
+  The second cell is used to specify flags:
+    bits[3:0] trigger type and level flags:
+      1 = low-to-high edge triggered.
+      2 = high-to-low edge triggered.
+      4 = active high level-sensitive.
+      8 = active low level-sensitive.
+
+OMAP specific properties:
+- ti,hwmods: Name of the hwmod associated to the GPIO:
+  "gpio<X>", <X> being the 1-based instance number from the HW spec
+
+
+Example:
+
+gpio4: gpio4 {
+    compatible = "ti,omap4-gpio";
+    ti,hwmods = "gpio4";
+    #gpio-cells = <2>;
+    gpio-controller;
+    #interrupt-cells = <2>;
+    interrupt-controller;
+};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-twl4030.txt b/Documentation/devicetree/bindings/gpio/gpio-twl4030.txt
new file mode 100644
index 000000000000..16695d9cf1e8
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-twl4030.txt
@@ -0,0 +1,23 @@
+twl4030 GPIO controller bindings
+
+Required properties:
+- compatible:
+  - "ti,twl4030-gpio" for twl4030 GPIO controller
+- #gpio-cells : Should be two.
+  - first cell is the pin number
+  - second cell is used to specify optional parameters (unused)
+- gpio-controller : Marks the device node as a GPIO controller.
+- #interrupt-cells : Should be 2.
+- interrupt-controller: Mark the device node as an interrupt controller
+  The first cell is the GPIO number.
+  The second cell is not used.
+
+Example:
+
+twl_gpio: gpio {
+    compatible = "ti,twl4030-gpio";
+    #gpio-cells = <2>;
+    gpio-controller;
+    #interrupt-cells = <2>;
+    interrupt-controller;
+};
diff --git a/Documentation/devicetree/bindings/gpio/gpio_i2c.txt b/Documentation/devicetree/bindings/gpio/gpio_i2c.txt
new file mode 100644
index 000000000000..4f8ec947c6bd
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio_i2c.txt
@@ -0,0 +1,32 @@
+Device-Tree bindings for i2c gpio driver
+
+Required properties:
+	- compatible = "i2c-gpio";
+	- gpios: sda and scl gpio
+
+
+Optional properties:
+	- i2c-gpio,sda-open-drain: sda as open drain
+	- i2c-gpio,scl-open-drain: scl as open drain
+	- i2c-gpio,scl-output-only: scl as output only
+	- i2c-gpio,delay-us: delay between GPIO operations (may depend on each platform)
+	- i2c-gpio,timeout-ms: timeout to get data
+
+Example nodes:
+
+i2c@0 {
+	compatible = "i2c-gpio";
+	gpios = <&pioA 23 0 /* sda */
+		 &pioA 24 0 /* scl */
+		>;
+	i2c-gpio,sda-open-drain;
+	i2c-gpio,scl-open-drain;
+	i2c-gpio,delay-us = <2>;	/* ~100 kHz */
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	rv3029c2@56 {
+		compatible = "rv3029c2";
+		reg = <0x56>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/gpio/sodaville.txt b/Documentation/devicetree/bindings/gpio/sodaville.txt
new file mode 100644
index 000000000000..563eff22b975
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/sodaville.txt
@@ -0,0 +1,48 @@
+GPIO controller on CE4100 / Sodaville SoCs
+==========================================
+
+The bindings for CE4100's GPIO controller match the generic description
+which is covered by the gpio.txt file in this folder.
+
+The only additional property is the intel,muxctl property which holds the
+value which is written into the MUXCNTL register.
+
+There is no compatible property for now because the driver is probed via
+PCI id (vendor 0x8086 device 0x2e67).
+
+The interrupt specifier consists of two cells encoded as follows:
+ - <1st cell>: The interrupt-number that identifies the interrupt source.
+ - <2nd cell>: The level-sense information, encoded as follows:
+		4 - active high level-sensitive
+		8 - active low level-sensitive
+
+Example of the GPIO device and one user:
+
+	pcigpio: gpio@b,1 {
+			/* two cells for GPIO and interrupt */
+			#gpio-cells = <2>;
+			#interrupt-cells = <2>;
+			compatible = "pci8086,2e67.2",
+					   "pci8086,2e67",
+					   "pciclassff0000",
+					   "pciclassff00";
+
+			reg = <0x15900 0x0 0x0 0x0 0x0>;
+			/* Interrupt line of the gpio device */
+			interrupts = <15 1>;
+			/* It is an interrupt and GPIO controller itself */
+			interrupt-controller;
+			gpio-controller;
+			intel,muxctl = <0>;
+	};
+
+	testuser@20 {
+			compatible = "example,testuser";
+			/* User the 11th GPIO line as an active high triggered
+			 * level interrupt
+			 */
+			interrupts = <11 8>;
+			interrupt-parent = <&pcigpio>;
+			/* Use this GPIO also with the gpio functions */
+			gpios = <&pcigpio 11 0>;
+	};
diff --git a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt
new file mode 100644
index 000000000000..dbd4368ab8cc
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt
@@ -0,0 +1,33 @@
+* TI Highspeed MMC host controller for OMAP
+
+The Highspeed MMC Host Controller on TI OMAP family
+provides an interface for MMC, SD, and SDIO types of memory cards.
+
+Required properties:
+- compatible:
+ Should be "ti,omap2-hsmmc", for OMAP2 controllers
+ Should be "ti,omap3-hsmmc", for OMAP3 controllers
+ Should be "ti,omap4-hsmmc", for OMAP4 controllers
+- ti,hwmods: Must be "mmc<n>", n is controller instance starting 1
+- reg : should contain hsmmc registers location and length
+
+Optional properties:
+ti,dual-volt: boolean, supports dual voltage cards
+<supply-name>-supply: phandle to the regulator device tree node
+"supply-name" examples are "vmmc", "vmmc_aux" etc
+ti,bus-width: Number of data lines, default assumed is 1 if the property is missing.
+cd-gpios: GPIOs for card detection
+wp-gpios: GPIOs for write protection
+ti,non-removable: non-removable slot (like eMMC)
+ti,needs-special-reset: Requires a special softreset sequence
+
+Example:
+	mmc1: mmc@0x4809c000 {
+		compatible = "ti,omap4-hsmmc";
+		reg = <0x4809c000 0x400>;
+		ti,hwmods = "mmc1";
+		ti,dual-volt;
+		ti,bus-width = <4>;
+		vmmc-supply = <&vmmc>; /* phandle to regulator node */
+		ti,non-removable;
+	};
diff --git a/Documentation/devicetree/bindings/mtd/arm-versatile.txt b/Documentation/devicetree/bindings/mtd/arm-versatile.txt
index 476845db94d0..beace4b89daa 100644
--- a/Documentation/devicetree/bindings/mtd/arm-versatile.txt
+++ b/Documentation/devicetree/bindings/mtd/arm-versatile.txt
@@ -4,5 +4,5 @@ Required properties:
 - compatible : must be "arm,versatile-flash";
 - bank-width : width in bytes of flash interface.
 
-Optional properties:
-- Subnode partition map from mtd flash binding
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
diff --git a/Documentation/devicetree/bindings/mtd/atmel-dataflash.txt b/Documentation/devicetree/bindings/mtd/atmel-dataflash.txt
index ef66ddd01da0..1889a4db5b7c 100644
--- a/Documentation/devicetree/bindings/mtd/atmel-dataflash.txt
+++ b/Documentation/devicetree/bindings/mtd/atmel-dataflash.txt
@@ -3,6 +3,9 @@
 Required properties:
 - compatible : "atmel,<model>", "atmel,<series>", "atmel,dataflash".
 
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
+
 Example:
 
 flash@1 {
diff --git a/Documentation/devicetree/bindings/mtd/atmel-nand.txt b/Documentation/devicetree/bindings/mtd/atmel-nand.txt
new file mode 100644
index 000000000000..a20069502f5a
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/atmel-nand.txt
@@ -0,0 +1,41 @@
+Atmel NAND flash
+
+Required properties:
+- compatible : "atmel,at91rm9200-nand".
+- reg : should specify localbus address and size used for the chip,
+	and if availlable the ECC.
+- atmel,nand-addr-offset : offset for the address latch.
+- atmel,nand-cmd-offset : offset for the command latch.
+- #address-cells, #size-cells : Must be present if the device has sub-nodes
+  representing partitions.
+
+- gpios : specifies the gpio pins to control the NAND device. detect is an
+  optional gpio and may be set to 0 if not present.
+
+Optional properties:
+- nand-ecc-mode : String, operation mode of the NAND ecc mode, soft by default.
+  Supported values are: "none", "soft", "hw", "hw_syndrome", "hw_oob_first",
+  "soft_bch".
+- nand-bus-width : 8 or 16 bus width if not present 8
+- nand-on-flash-bbt: boolean to enable on flash bbt option if not present false
+
+Examples:
+nand0: nand@40000000,0 {
+	compatible = "atmel,at91rm9200-nand";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	reg = <0x40000000 0x10000000
+	       0xffffe800 0x200
+	      >;
+	atmel,nand-addr-offset = <21>;	/* ale */
+	atmel,nand-cmd-offset = <22>;	/* cle */
+	nand-on-flash-bbt;
+	nand-ecc-mode = "soft";
+	gpios = <&pioC 13 0	/* rdy */
+		 &pioC 14 0 	/* nce */
+		 0		/* cd */
+		>;
+	partition@0 {
+		...
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt b/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt
index 00f1f546b32e..fce4894f5a98 100644
--- a/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt
@@ -19,6 +19,10 @@ Optional properties:
 	read registers (tR). Required if property "gpios" is not used
 	(R/B# pins not connected).
 
+Each flash chip described may optionally contain additional sub-nodes
+describing partitions of the address space. See partition.txt for more
+detail.
+
 Examples:
 
 upm@1,0 {
diff --git a/Documentation/devicetree/bindings/mtd/fsmc-nand.txt b/Documentation/devicetree/bindings/mtd/fsmc-nand.txt
new file mode 100644
index 000000000000..e2c663b354d2
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/fsmc-nand.txt
@@ -0,0 +1,33 @@
+* FSMC NAND
+
+Required properties:
+- compatible : "st,spear600-fsmc-nand"
+- reg : Address range of the mtd chip
+- reg-names: Should contain the reg names "fsmc_regs" and "nand_data"
+- st,ale-off : Chip specific offset to ALE
+- st,cle-off : Chip specific offset to CLE
+
+Optional properties:
+- bank-width : Width (in bytes) of the device.  If not present, the width
+  defaults to 1 byte
+- nand-skip-bbtscan: Indicates the the BBT scanning should be skipped
+
+Example:
+
+	fsmc: flash@d1800000 {
+		compatible = "st,spear600-fsmc-nand";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0xd1800000 0x1000	/* FSMC Register */
+		       0xd2000000 0x4000>;	/* NAND Base */
+		reg-names = "fsmc_regs", "nand_data";
+		st,ale-off = <0x20000>;
+		st,cle-off = <0x10000>;
+
+		bank-width = <1>;
+		nand-skip-bbtscan;
+
+		partition@0 {
+			...
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mtd/gpio-control-nand.txt b/Documentation/devicetree/bindings/mtd/gpio-control-nand.txt
index 719f4dc58df7..36ef07d3c90f 100644
--- a/Documentation/devicetree/bindings/mtd/gpio-control-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpio-control-nand.txt
@@ -25,6 +25,9 @@ Optional properties:
   GPIO state and before and after command byte writes, this register will be
   read to ensure that the GPIO accesses have completed.
 
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
+
 Examples:
 
 gpio-nand@1,0 {
diff --git a/Documentation/devicetree/bindings/mtd/mtd-physmap.txt b/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
index 80152cb567d9..a63c2bd7de2b 100644
--- a/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
+++ b/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
@@ -23,27 +23,8 @@ are defined:
  - vendor-id : Contains the flash chip's vendor id (1 byte).
  - device-id : Contains the flash chip's device id (1 byte).
 
-In addition to the information on the mtd bank itself, the
-device tree may optionally contain additional information
-describing partitions of the address space.  This can be
-used on platforms which have strong conventions about which
-portions of a flash are used for what purposes, but which don't
-use an on-flash partition table such as RedBoot.
-
-Each partition is represented as a sub-node of the mtd device.
-Each node's name represents the name of the corresponding
-partition of the mtd device.
-
-Flash partitions
- - reg : The partition's offset and size within the mtd bank.
- - label : (optional) The label / name for this partition.
-   If omitted, the label is taken from the node name (excluding
-   the unit address).
- - read-only : (optional) This parameter, if present, is a hint to
-   Linux that this partition should only be mounted
-   read-only.  This is usually used for flash partitions
-   containing early-boot firmware images or data which should not
-   be clobbered.
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt
new file mode 100644
index 000000000000..03855c8c492a
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/nand.txt
@@ -0,0 +1,7 @@
+* MTD generic binding
+
+- nand-ecc-mode : String, operation mode of the NAND ecc mode.
+  Supported values are: "none", "soft", "hw", "hw_syndrome", "hw_oob_first",
+  "soft_bch".
+- nand-bus-width : 8 or 16 bus width if not present 8
+- nand-on-flash-bbt: boolean to enable on flash bbt option if not present false
diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt
new file mode 100644
index 000000000000..f114ce1657c2
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/partition.txt
@@ -0,0 +1,38 @@
+Representing flash partitions in devicetree
+
+Partitions can be represented by sub-nodes of an mtd device. This can be used
+on platforms which have strong conventions about which portions of a flash are
+used for what purposes, but which don't use an on-flash partition table such
+as RedBoot.
+
+#address-cells & #size-cells must both be present in the mtd device and be
+equal to 1.
+
+Required properties:
+- reg : The partition's offset and size within the mtd bank.
+
+Optional properties:
+- label : The label / name for this partition.  If omitted, the label is taken
+  from the node name (excluding the unit address).
+- read-only : This parameter, if present, is a hint to Linux that this
+  partition should only be mounted read-only. This is usually used for flash
+  partitions containing early-boot firmware images or data which should not be
+  clobbered.
+
+Examples:
+
+
+flash@0 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	partition@0 {
+		label = "u-boot";
+		reg = <0x0000000 0x100000>;
+		read-only;
+	};
+
+	uimage@100000 {
+		reg = <0x0100000 0x200000>;
+	};
+];
diff --git a/Documentation/devicetree/bindings/mtd/spear_smi.txt b/Documentation/devicetree/bindings/mtd/spear_smi.txt
new file mode 100644
index 000000000000..7248aadd89e4
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/spear_smi.txt
@@ -0,0 +1,31 @@
+* SPEAr SMI
+
+Required properties:
+- compatible : "st,spear600-smi"
+- reg : Address range of the mtd chip
+- #address-cells, #size-cells : Must be present if the device has sub-nodes
+  representing partitions.
+- interrupt-parent: Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- interrupts: Should contain the STMMAC interrupts
+- clock-rate : Functional clock rate of SMI in Hz
+
+Optional properties:
+- st,smi-fast-mode : Flash supports read in fast mode
+
+Example:
+
+	smi: flash@fc000000 {
+		compatible = "st,spear600-smi";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0xfc000000 0x1000>;
+		interrupt-parent = <&vic1>;
+		interrupts = <12>;
+		clock-rate = <50000000>;	/* 50MHz */
+
+		flash@f8000000 {
+			st,smi-fast-mode;
+			...
+		};
+	};
diff --git a/Documentation/devicetree/bindings/power_supply/max17042_battery.txt b/Documentation/devicetree/bindings/power_supply/max17042_battery.txt
new file mode 100644
index 000000000000..5bc9b685cf8a
--- /dev/null
+++ b/Documentation/devicetree/bindings/power_supply/max17042_battery.txt
@@ -0,0 +1,18 @@
+max17042_battery
+~~~~~~~~~~~~~~~~
+
+Required properties :
+ - compatible : "maxim,max17042"
+
+Optional properties :
+ - maxim,rsns-microohm : Resistance of rsns resistor in micro Ohms
+                         (datasheet-recommended value is 10000).
+   Defining this property enables current-sense functionality.
+
+Example:
+
+	battery-charger@36 {
+		compatible = "maxim,max17042";
+		reg = <0x36>;
+		maxim,rsns-microohm = <10000>;
+	};
diff --git a/Documentation/devicetree/bindings/regulator/anatop-regulator.txt b/Documentation/devicetree/bindings/regulator/anatop-regulator.txt
new file mode 100644
index 000000000000..357758cb6e92
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/anatop-regulator.txt
@@ -0,0 +1,29 @@
+Anatop Voltage regulators
+
+Required properties:
+- compatible: Must be "fsl,anatop-regulator"
+- anatop-reg-offset: Anatop MFD register offset
+- anatop-vol-bit-shift: Bit shift for the register
+- anatop-vol-bit-width: Number of bits used in the register
+- anatop-min-bit-val: Minimum value of this register
+- anatop-min-voltage: Minimum voltage of this regulator
+- anatop-max-voltage: Maximum voltage of this regulator
+
+Any property defined as part of the core regulator
+binding, defined in regulator.txt, can also be used.
+
+Example:
+
+	regulator-vddpu {
+		compatible = "fsl,anatop-regulator";
+		regulator-name = "vddpu";
+		regulator-min-microvolt = <725000>;
+		regulator-max-microvolt = <1300000>;
+		regulator-always-on;
+		anatop-reg-offset = <0x140>;
+		anatop-vol-bit-shift = <9>;
+		anatop-vol-bit-width = <5>;
+		anatop-min-bit-val = <1>;
+		anatop-min-voltage = <725000>;
+		anatop-max-voltage = <1300000>;
+	};
diff --git a/Documentation/devicetree/bindings/usb/atmel-usb.txt b/Documentation/devicetree/bindings/usb/atmel-usb.txt
new file mode 100644
index 000000000000..60bd2150a3e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/atmel-usb.txt
@@ -0,0 +1,49 @@
+Atmel SOC USB controllers
+
+OHCI
+
+Required properties:
+ - compatible: Should be "atmel,at91rm9200-ohci" for USB controllers
+   used in host mode.
+ - num-ports: Number of ports.
+ - atmel,vbus-gpio: If present, specifies a gpio that needs to be
+   activated for the bus to be powered.
+ - atmel,oc-gpio: If present, specifies a gpio that needs to be
+   activated for the overcurrent detection.
+
+usb0: ohci@00500000 {
+	compatible = "atmel,at91rm9200-ohci", "usb-ohci";
+	reg = <0x00500000 0x100000>;
+	interrupts = <20 4>;
+	num-ports = <2>;
+};
+
+EHCI
+
+Required properties:
+ - compatible: Should be "atmel,at91sam9g45-ehci" for USB controllers
+   used in host mode.
+
+usb1: ehci@00800000 {
+	compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
+	reg = <0x00800000 0x100000>;
+	interrupts = <22 4>;
+};
+
+AT91 USB device controller
+
+Required properties:
+ - compatible: Should be "atmel,at91rm9200-udc"
+ - reg: Address and length of the register set for the device
+ - interrupts: Should contain macb interrupt
+
+Optional properties:
+ - atmel,vbus-gpio: If present, specifies a gpio that needs to be
+   activated for the bus to be powered.
+
+usb1: gadget@fffa4000 {
+	compatible = "atmel,at91rm9200-udc";
+	reg = <0xfffa4000 0x4000>;
+	interrupts = <10 4>;
+	atmel,vbus-gpio = <&pioC 5 0>;
+};
diff --git a/Documentation/devicetree/bindings/usb/tegra-usb.txt b/Documentation/devicetree/bindings/usb/tegra-usb.txt
index 035d63d5646d..007005ddbe12 100644
--- a/Documentation/devicetree/bindings/usb/tegra-usb.txt
+++ b/Documentation/devicetree/bindings/usb/tegra-usb.txt
@@ -11,3 +11,16 @@ Required properties :
  - phy_type : Should be one of "ulpi" or "utmi".
  - nvidia,vbus-gpio : If present, specifies a gpio that needs to be
    activated for the bus to be powered.
+
+Optional properties:
+  - dr_mode : dual role mode. Indicates the working mode for
+   nvidia,tegra20-ehci compatible controllers.  Can be "host", "peripheral",
+   or "otg".  Default to "host" if not defined for backward compatibility.
+      host means this is a host controller
+      peripheral means it is device controller
+      otg means it can operate as either ("on the go")
+  - nvidia,has-legacy-mode : boolean indicates whether this controller can
+    operate in legacy mode (as APX 2500 / 2600). In legacy mode some
+    registers are accessed through the APB_MISC base address instead of
+    the USB controller. Since this is a legacy issue it probably does not
+    warrant a compatible string of its own.
diff --git a/Documentation/devicetree/usage-model.txt b/Documentation/devicetree/usage-model.txt
new file mode 100644
index 000000000000..c5a80099b71c
--- /dev/null
+++ b/Documentation/devicetree/usage-model.txt
@@ -0,0 +1,412 @@
+Linux and the Device Tree
+-------------------------
+The Linux usage model for device tree data
+
+Author: Grant Likely <grant.likely@secretlab.ca>
+
+This article describes how Linux uses the device tree.  An overview of
+the device tree data format can be found on the device tree usage page
+at devicetree.org[1].
+
+[1] http://devicetree.org/Device_Tree_Usage
+
+The "Open Firmware Device Tree", or simply Device Tree (DT), is a data
+structure and language for describing hardware.  More specifically, it
+is a description of hardware that is readable by an operating system
+so that the operating system doesn't need to hard code details of the
+machine.
+
+Structurally, the DT is a tree, or acyclic graph with named nodes, and
+nodes may have an arbitrary number of named properties encapsulating
+arbitrary data.  A mechanism also exists to create arbitrary
+links from one node to another outside of the natural tree structure.
+
+Conceptually, a common set of usage conventions, called 'bindings',
+is defined for how data should appear in the tree to describe typical
+hardware characteristics including data busses, interrupt lines, GPIO
+connections, and peripheral devices.
+
+As much as possible, hardware is described using existing bindings to
+maximize use of existing support code, but since property and node
+names are simply text strings, it is easy to extend existing bindings
+or create new ones by defining new nodes and properties.  Be wary,
+however, of creating a new binding without first doing some homework
+about what already exists.  There are currently two different,
+incompatible, bindings for i2c busses that came about because the new
+binding was created without first investigating how i2c devices were
+already being enumerated in existing systems.
+
+1. History
+----------
+The DT was originally created by Open Firmware as part of the
+communication method for passing data from Open Firmware to a client
+program (like to an operating system).  An operating system used the
+Device Tree to discover the topology of the hardware at runtime, and
+thereby support a majority of available hardware without hard coded
+information (assuming drivers were available for all devices).
+
+Since Open Firmware is commonly used on PowerPC and SPARC platforms,
+the Linux support for those architectures has for a long time used the
+Device Tree.
+
+In 2005, when PowerPC Linux began a major cleanup and to merge 32-bit
+and 64-bit support, the decision was made to require DT support on all
+powerpc platforms, regardless of whether or not they used Open
+Firmware.  To do this, a DT representation called the Flattened Device
+Tree (FDT) was created which could be passed to the kernel as a binary
+blob without requiring a real Open Firmware implementation.  U-Boot,
+kexec, and other bootloaders were modified to support both passing a
+Device Tree Binary (dtb) and to modify a dtb at boot time.  DT was
+also added to the PowerPC boot wrapper (arch/powerpc/boot/*) so that
+a dtb could be wrapped up with the kernel image to support booting
+existing non-DT aware firmware.
+
+Some time later, FDT infrastructure was generalized to be usable by
+all architectures.  At the time of this writing, 6 mainlined
+architectures (arm, microblaze, mips, powerpc, sparc, and x86) and 1
+out of mainline (nios) have some level of DT support.
+
+2. Data Model
+-------------
+If you haven't already read the Device Tree Usage[1] page,
+then go read it now.  It's okay, I'll wait....
+
+2.1 High Level View
+-------------------
+The most important thing to understand is that the DT is simply a data
+structure that describes the hardware.  There is nothing magical about
+it, and it doesn't magically make all hardware configuration problems
+go away.  What it does do is provide a language for decoupling the
+hardware configuration from the board and device driver support in the
+Linux kernel (or any other operating system for that matter).  Using
+it allows board and device support to become data driven; to make
+setup decisions based on data passed into the kernel instead of on
+per-machine hard coded selections.
+
+Ideally, data driven platform setup should result in less code
+duplication and make it easier to support a wide range of hardware
+with a single kernel image.
+
+Linux uses DT data for three major purposes:
+1) platform identification,
+2) runtime configuration, and
+3) device population.
+
+2.2 Platform Identification
+---------------------------
+First and foremost, the kernel will use data in the DT to identify the
+specific machine.  In a perfect world, the specific platform shouldn't
+matter to the kernel because all platform details would be described
+perfectly by the device tree in a consistent and reliable manner.
+Hardware is not perfect though, and so the kernel must identify the
+machine during early boot so that it has the opportunity to run
+machine-specific fixups.
+
+In the majority of cases, the machine identity is irrelevant, and the
+kernel will instead select setup code based on the machine's core
+CPU or SoC.  On ARM for example, setup_arch() in
+arch/arm/kernel/setup.c will call setup_machine_fdt() in
+arch/arm/kernel/devicetree.c which searches through the machine_desc
+table and selects the machine_desc which best matches the device tree
+data.  It determines the best match by looking at the 'compatible'
+property in the root device tree node, and comparing it with the
+dt_compat list in struct machine_desc.
+
+The 'compatible' property contains a sorted list of strings starting
+with the exact name of the machine, followed by an optional list of
+boards it is compatible with sorted from most compatible to least.  For
+example, the root compatible properties for the TI BeagleBoard and its
+successor, the BeagleBoard xM board might look like:
+
+	compatible = "ti,omap3-beagleboard", "ti,omap3450", "ti,omap3";
+	compatible = "ti,omap3-beagleboard-xm", "ti,omap3450", "ti,omap3";
+
+Where "ti,omap3-beagleboard-xm" specifies the exact model, it also
+claims that it compatible with the OMAP 3450 SoC, and the omap3 family
+of SoCs in general.  You'll notice that the list is sorted from most
+specific (exact board) to least specific (SoC family).
+
+Astute readers might point out that the Beagle xM could also claim
+compatibility with the original Beagle board.  However, one should be
+cautioned about doing so at the board level since there is typically a
+high level of change from one board to another, even within the same
+product line, and it is hard to nail down exactly what is meant when one
+board claims to be compatible with another.  For the top level, it is
+better to err on the side of caution and not claim one board is
+compatible with another.  The notable exception would be when one
+board is a carrier for another, such as a CPU module attached to a
+carrier board.
+
+One more note on compatible values.  Any string used in a compatible
+property must be documented as to what it indicates.  Add
+documentation for compatible strings in Documentation/devicetree/bindings.
+
+Again on ARM, for each machine_desc, the kernel looks to see if
+any of the dt_compat list entries appear in the compatible property.
+If one does, then that machine_desc is a candidate for driving the
+machine.  After searching the entire table of machine_descs,
+setup_machine_fdt() returns the 'most compatible' machine_desc based
+on which entry in the compatible property each machine_desc matches
+against.  If no matching machine_desc is found, then it returns NULL.
+
+The reasoning behind this scheme is the observation that in the majority
+of cases, a single machine_desc can support a large number of boards
+if they all use the same SoC, or same family of SoCs.  However,
+invariably there will be some exceptions where a specific board will
+require special setup code that is not useful in the generic case.
+Special cases could be handled by explicitly checking for the
+troublesome board(s) in generic setup code, but doing so very quickly
+becomes ugly and/or unmaintainable if it is more than just a couple of
+cases.
+
+Instead, the compatible list allows a generic machine_desc to provide
+support for a wide common set of boards by specifying "less
+compatible" value in the dt_compat list.  In the example above,
+generic board support can claim compatibility with "ti,omap3" or
+"ti,omap3450".  If a bug was discovered on the original beagleboard
+that required special workaround code during early boot, then a new
+machine_desc could be added which implements the workarounds and only
+matches on "ti,omap3-beagleboard".
+
+PowerPC uses a slightly different scheme where it calls the .probe()
+hook from each machine_desc, and the first one returning TRUE is used.
+However, this approach does not take into account the priority of the
+compatible list, and probably should be avoided for new architecture
+support.
+
+2.3 Runtime configuration
+-------------------------
+In most cases, a DT will be the sole method of communicating data from
+firmware to the kernel, so also gets used to pass in runtime and
+configuration data like the kernel parameters string and the location
+of an initrd image.
+
+Most of this data is contained in the /chosen node, and when booting
+Linux it will look something like this:
+
+	chosen {
+		bootargs = "console=ttyS0,115200 loglevel=8";
+		initrd-start = <0xc8000000>;
+		initrd-end = <0xc8200000>;
+	};
+
+The bootargs property contains the kernel arguments, and the initrd-*
+properties define the address and size of an initrd blob.  The
+chosen node may also optionally contain an arbitrary number of
+additional properties for platform-specific configuration data.
+
+During early boot, the architecture setup code calls of_scan_flat_dt()
+several times with different helper callbacks to parse device tree
+data before paging is setup.  The of_scan_flat_dt() code scans through
+the device tree and uses the helpers to extract information required
+during early boot.  Typically the early_init_dt_scan_chosen() helper
+is used to parse the chosen node including kernel parameters,
+early_init_dt_scan_root() to initialize the DT address space model,
+and early_init_dt_scan_memory() to determine the size and
+location of usable RAM.
+
+On ARM, the function setup_machine_fdt() is responsible for early
+scanning of the device tree after selecting the correct machine_desc
+that supports the board.
+
+2.4 Device population
+---------------------
+After the board has been identified, and after the early configuration data
+has been parsed, then kernel initialization can proceed in the normal
+way.  At some point in this process, unflatten_device_tree() is called
+to convert the data into a more efficient runtime representation.
+This is also when machine-specific setup hooks will get called, like
+the machine_desc .init_early(), .init_irq() and .init_machine() hooks
+on ARM.  The remainder of this section uses examples from the ARM
+implementation, but all architectures will do pretty much the same
+thing when using a DT.
+
+As can be guessed by the names, .init_early() is used for any machine-
+specific setup that needs to be executed early in the boot process,
+and .init_irq() is used to set up interrupt handling.  Using a DT
+doesn't materially change the behaviour of either of these functions.
+If a DT is provided, then both .init_early() and .init_irq() are able
+to call any of the DT query functions (of_* in include/linux/of*.h) to
+get additional data about the platform.
+
+The most interesting hook in the DT context is .init_machine() which
+is primarily responsible for populating the Linux device model with
+data about the platform.  Historically this has been implemented on
+embedded platforms by defining a set of static clock structures,
+platform_devices, and other data in the board support .c file, and
+registering it en-masse in .init_machine().  When DT is used, then
+instead of hard coding static devices for each platform, the list of
+devices can be obtained by parsing the DT, and allocating device
+structures dynamically.
+
+The simplest case is when .init_machine() is only responsible for
+registering a block of platform_devices.  A platform_device is a concept
+used by Linux for memory or I/O mapped devices which cannot be detected
+by hardware, and for 'composite' or 'virtual' devices (more on those
+later).  While there is no 'platform device' terminology for the DT,
+platform devices roughly correspond to device nodes at the root of the
+tree and children of simple memory mapped bus nodes.
+
+About now is a good time to lay out an example.  Here is part of the
+device tree for the NVIDIA Tegra board.
+
+/{
+	compatible = "nvidia,harmony", "nvidia,tegra20";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&intc>;
+
+	chosen { };
+	aliases { };
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x40000000>;
+	};
+
+	soc {
+		compatible = "nvidia,tegra20-soc", "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		intc: interrupt-controller@50041000 {
+			compatible = "nvidia,tegra20-gic";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			reg = <0x50041000 0x1000>, < 0x50040100 0x0100 >;
+		};
+
+		serial@70006300 {
+			compatible = "nvidia,tegra20-uart";
+			reg = <0x70006300 0x100>;
+			interrupts = <122>;
+		};
+
+		i2s1: i2s@70002800 {
+			compatible = "nvidia,tegra20-i2s";
+			reg = <0x70002800 0x100>;
+			interrupts = <77>;
+			codec = <&wm8903>;
+		};
+
+		i2c@7000c000 {
+			compatible = "nvidia,tegra20-i2c";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x7000c000 0x100>;
+			interrupts = <70>;
+
+			wm8903: codec@1a {
+				compatible = "wlf,wm8903";
+				reg = <0x1a>;
+				interrupts = <347>;
+			};
+		};
+	};
+
+	sound {
+		compatible = "nvidia,harmony-sound";
+		i2s-controller = <&i2s1>;
+		i2s-codec = <&wm8903>;
+	};
+};
+
+At .machine_init() time, Tegra board support code will need to look at
+this DT and decide which nodes to create platform_devices for.
+However, looking at the tree, it is not immediately obvious what kind
+of device each node represents, or even if a node represents a device
+at all.  The /chosen, /aliases, and /memory nodes are informational
+nodes that don't describe devices (although arguably memory could be
+considered a device).  The children of the /soc node are memory mapped
+devices, but the codec@1a is an i2c device, and the sound node
+represents not a device, but rather how other devices are connected
+together to create the audio subsystem.  I know what each device is
+because I'm familiar with the board design, but how does the kernel
+know what to do with each node?
+
+The trick is that the kernel starts at the root of the tree and looks
+for nodes that have a 'compatible' property.  First, it is generally
+assumed that any node with a 'compatible' property represents a device
+of some kind, and second, it can be assumed that any node at the root
+of the tree is either directly attached to the processor bus, or is a
+miscellaneous system device that cannot be described any other way.
+For each of these nodes, Linux allocates and registers a
+platform_device, which in turn may get bound to a platform_driver.
+
+Why is using a platform_device for these nodes a safe assumption?
+Well, for the way that Linux models devices, just about all bus_types
+assume that its devices are children of a bus controller.  For
+example, each i2c_client is a child of an i2c_master.  Each spi_device
+is a child of an SPI bus.  Similarly for USB, PCI, MDIO, etc.  The
+same hierarchy is also found in the DT, where I2C device nodes only
+ever appear as children of an I2C bus node.  Ditto for SPI, MDIO, USB,
+etc.  The only devices which do not require a specific type of parent
+device are platform_devices (and amba_devices, but more on that
+later), which will happily live at the base of the Linux /sys/devices
+tree.  Therefore, if a DT node is at the root of the tree, then it
+really probably is best registered as a platform_device.
+
+Linux board support code calls of_platform_populate(NULL, NULL, NULL)
+to kick off discovery of devices at the root of the tree.  The
+parameters are all NULL because when starting from the root of the
+tree, there is no need to provide a starting node (the first NULL), a
+parent struct device (the last NULL), and we're not using a match
+table (yet).  For a board that only needs to register devices,
+.init_machine() can be completely empty except for the
+of_platform_populate() call.
+
+In the Tegra example, this accounts for the /soc and /sound nodes, but
+what about the children of the SoC node?  Shouldn't they be registered
+as platform devices too?  For Linux DT support, the generic behaviour
+is for child devices to be registered by the parent's device driver at
+driver .probe() time.  So, an i2c bus device driver will register a
+i2c_client for each child node, an SPI bus driver will register
+its spi_device children, and similarly for other bus_types.
+According to that model, a driver could be written that binds to the
+SoC node and simply registers platform_devices for each of its
+children.  The board support code would allocate and register an SoC
+device, a (theoretical) SoC device driver could bind to the SoC device,
+and register platform_devices for /soc/interrupt-controller, /soc/serial,
+/soc/i2s, and /soc/i2c in its .probe() hook.  Easy, right?
+
+Actually, it turns out that registering children of some
+platform_devices as more platform_devices is a common pattern, and the
+device tree support code reflects that and makes the above example
+simpler.  The second argument to of_platform_populate() is an
+of_device_id table, and any node that matches an entry in that table
+will also get its child nodes registered.  In the tegra case, the code
+can look something like this:
+
+static void __init harmony_init_machine(void)
+{
+	/* ... */
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
+
+"simple-bus" is defined in the ePAPR 1.0 specification as a property
+meaning a simple memory mapped bus, so the of_platform_populate() code
+could be written to just assume simple-bus compatible nodes will
+always be traversed.  However, we pass it in as an argument so that
+board support code can always override the default behaviour.
+
+[Need to add discussion of adding i2c/spi/etc child devices]
+
+Appendix A: AMBA devices
+------------------------
+
+ARM Primecells are a certain kind of device attached to the ARM AMBA
+bus which include some support for hardware detection and power
+management.  In Linux, struct amba_device and the amba_bus_type is
+used to represent Primecell devices.  However, the fiddly bit is that
+not all devices on an AMBA bus are Primecells, and for Linux it is
+typical for both amba_device and platform_device instances to be
+siblings of the same bus segment.
+
+When using the DT, this creates problems for of_platform_populate()
+because it must decide whether to register each node as either a
+platform_device or an amba_device.  This unfortunately complicates the
+device creation model a little bit, but the solution turns out not to
+be too invasive.  If a node is compatible with "arm,amba-primecell", then
+of_platform_populate() will register it as an amba_device instead of a
+platform_device.
diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt
index 225f96d88f55..3bbd5c51605a 100644
--- a/Documentation/dma-buf-sharing.txt
+++ b/Documentation/dma-buf-sharing.txt
@@ -32,8 +32,12 @@ The buffer-user
 *IMPORTANT*: [see https://lkml.org/lkml/2011/12/20/211 for more details]
 For this first version, A buffer shared using the dma_buf sharing API:
 - *may* be exported to user space using "mmap" *ONLY* by exporter, outside of
-   this framework.
-- may be used *ONLY* by importers that do not need CPU access to the buffer.
+  this framework.
+- with this new iteration of the dma-buf api cpu access from the kernel has been
+  enable, see below for the details.
+
+dma-buf operations for device dma only
+--------------------------------------
 
 The dma_buf buffer sharing API usage contains the following steps:
 
@@ -219,10 +223,120 @@ NOTES:
    If the exporter chooses not to allow an attach() operation once a
    map_dma_buf() API has been called, it simply returns an error.
 
-Miscellaneous notes:
+Kernel cpu access to a dma-buf buffer object
+--------------------------------------------
+
+The motivation to allow cpu access from the kernel to a dma-buf object from the
+importers side are:
+- fallback operations, e.g. if the devices is connected to a usb bus and the
+  kernel needs to shuffle the data around first before sending it away.
+- full transparency for existing users on the importer side, i.e. userspace
+  should not notice the difference between a normal object from that subsystem
+  and an imported one backed by a dma-buf. This is really important for drm
+  opengl drivers that expect to still use all the existing upload/download
+  paths.
+
+Access to a dma_buf from the kernel context involves three steps:
+
+1. Prepare access, which invalidate any necessary caches and make the object
+   available for cpu access.
+2. Access the object page-by-page with the dma_buf map apis
+3. Finish access, which will flush any necessary cpu caches and free reserved
+   resources.
+
+1. Prepare access
+
+   Before an importer can access a dma_buf object with the cpu from the kernel
+   context, it needs to notify the exporter of the access that is about to
+   happen.
+
+   Interface:
+      int dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
+				   size_t start, size_t len,
+				   enum dma_data_direction direction)
+
+   This allows the exporter to ensure that the memory is actually available for
+   cpu access - the exporter might need to allocate or swap-in and pin the
+   backing storage. The exporter also needs to ensure that cpu access is
+   coherent for the given range and access direction. The range and access
+   direction can be used by the exporter to optimize the cache flushing, i.e.
+   access outside of the range or with a different direction (read instead of
+   write) might return stale or even bogus data (e.g. when the exporter needs to
+   copy the data to temporary storage).
+
+   This step might fail, e.g. in oom conditions.
+
+2. Accessing the buffer
+
+   To support dma_buf objects residing in highmem cpu access is page-based using
+   an api similar to kmap. Accessing a dma_buf is done in aligned chunks of
+   PAGE_SIZE size. Before accessing a chunk it needs to be mapped, which returns
+   a pointer in kernel virtual address space. Afterwards the chunk needs to be
+   unmapped again. There is no limit on how often a given chunk can be mapped
+   and unmapped, i.e. the importer does not need to call begin_cpu_access again
+   before mapping the same chunk again.
+
+   Interfaces:
+      void *dma_buf_kmap(struct dma_buf *, unsigned long);
+      void dma_buf_kunmap(struct dma_buf *, unsigned long, void *);
+
+   There are also atomic variants of these interfaces. Like for kmap they
+   facilitate non-blocking fast-paths. Neither the importer nor the exporter (in
+   the callback) is allowed to block when using these.
+
+   Interfaces:
+      void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long);
+      void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *);
+
+   For importers all the restrictions of using kmap apply, like the limited
+   supply of kmap_atomic slots. Hence an importer shall only hold onto at most 2
+   atomic dma_buf kmaps at the same time (in any given process context).
+
+   dma_buf kmap calls outside of the range specified in begin_cpu_access are
+   undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on
+   the partial chunks at the beginning and end but may return stale or bogus
+   data outside of the range (in these partial chunks).
+
+   Note that these calls need to always succeed. The exporter needs to complete
+   any preparations that might fail in begin_cpu_access.
+
+3. Finish access
+
+   When the importer is done accessing the range specified in begin_cpu_access,
+   it needs to announce this to the exporter (to facilitate cache flushing and
+   unpinning of any pinned resources). The result of of any dma_buf kmap calls
+   after end_cpu_access is undefined.
+
+   Interface:
+      void dma_buf_end_cpu_access(struct dma_buf *dma_buf,
+				  size_t start, size_t len,
+				  enum dma_data_direction dir);
+
+
+Miscellaneous notes
+-------------------
+
 - Any exporters or users of the dma-buf buffer sharing framework must have
   a 'select DMA_SHARED_BUFFER' in their respective Kconfigs.
 
+- In order to avoid fd leaks on exec, the FD_CLOEXEC flag must be set
+  on the file descriptor.  This is not just a resource leak, but a
+  potential security hole.  It could give the newly exec'd application
+  access to buffers, via the leaked fd, to which it should otherwise
+  not be permitted access.
+
+  The problem with doing this via a separate fcntl() call, versus doing it
+  atomically when the fd is created, is that this is inherently racy in a
+  multi-threaded app[3].  The issue is made worse when it is library code
+  opening/creating the file descriptor, as the application may not even be
+  aware of the fd's.
+
+  To avoid this problem, userspace must have a way to request O_CLOEXEC
+  flag be set when the dma-buf fd is created.  So any API provided by
+  the exporting driver to create a dmabuf fd must provide a way to let
+  userspace control setting of O_CLOEXEC flag passed in to dma_buf_fd().
+
 References:
 [1] struct dma_buf_ops in include/linux/dma-buf.h
 [2] All interfaces mentioned above defined in include/linux/dma-buf.h
+[3] https://lwn.net/Articles/236486/
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 0c083c5c2faa..b4a898f43c37 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -158,7 +158,6 @@ logo_*.c
 logo_*_clut224.c
 logo_*_mono.c
 lxdialog
-mach
 mach-types
 mach-types.h
 machtypes.h
diff --git a/Documentation/fb/intel810.txt b/Documentation/fb/intel810.txt
index be3e7836abef..a8e9f5bca6f3 100644
--- a/Documentation/fb/intel810.txt
+++ b/Documentation/fb/intel810.txt
@@ -211,7 +211,7 @@ Using the same setup as described above, load the module like this:
 	modprobe i810fb vram=2 xres=1024 bpp=8 hsync1=30 hsync2=55 vsync1=50 \
 	         vsync2=85 accel=1 mtrr=1
 
-Or just add the following to /etc/modprobe.conf
+Or just add the following to a configuration file in /etc/modprobe.d/
 
 	options i810fb vram=2 xres=1024 bpp=16 hsync1=30 hsync2=55 vsync1=50 \
 	vsync2=85 accel=1 mtrr=1
diff --git a/Documentation/fb/intelfb.txt b/Documentation/fb/intelfb.txt
index dd9e944ea628..feac4e4d6968 100644
--- a/Documentation/fb/intelfb.txt
+++ b/Documentation/fb/intelfb.txt
@@ -120,7 +120,7 @@ Using the same setup as described above, load the module like this:
 
 	modprobe intelfb mode=800x600-32@75 vram=8 accel=1 hwcursor=1
 
-Or just add the following to /etc/modprobe.conf
+Or just add the following to a configuration file in /etc/modprobe.d/
 
 	options intelfb mode=800x600-32@75 vram=8 accel=1 hwcursor=1
 
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 0cad4803ffac..709e08e9a222 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,14 +6,6 @@ be removed from this file.
 
 ---------------------------
 
-What:	x86 floppy disable_hlt
-When:	2012
-Why:	ancient workaround of dubious utility clutters the
-	code used by everybody else.
-Who:	Len Brown <len.brown@intel.com>
-
----------------------------
-
 What:	CONFIG_APM_CPU_IDLE, and its ability to call APM BIOS in idle
 When:	2012
 Why:	This optional sub-feature of APM is of dubious reliability,
@@ -529,3 +521,13 @@ When:	3.5
 Why:	The old kmap_atomic() with two arguments is deprecated, we only
 	keep it for backward compatibility for few cycles and then drop it.
 Who:	Cong Wang <amwang@redhat.com>
+
+----------------------------
+
+What:	get_robust_list syscall
+When:	2013
+Why:	There appear to be no production users of the get_robust_list syscall,
+	and it runs the risk of leaking address locations, allowing the bypass
+	of ASLR. It was only ever intended for debugging, so it should be
+	removed.
+Who:	Kees Cook <keescook@chromium.org>
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 8c10bf375c73..1b7f9acbcbbe 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -144,9 +144,6 @@ journal_async_commit	Commit block can be written to disk without waiting
 			mount the device. This will enable 'journal_checksum'
 			internally.
 
-journal=update		Update the ext4 file system's journal to the current
-			format.
-
 journal_dev=devnum	When the external journal device's major/minor numbers
 			have changed, this option allows the user to specify
 			the new journal location.  The journal device is
@@ -356,11 +353,6 @@ nouid32			Disables 32-bit UIDs and GIDs.  This is for
 			interoperability  with  older kernels which only
 			store and expect 16-bit values.
 
-resize			Allows to resize filesystem to the end of the last
-			existing block group, further resize has to be done
-			with resize2fs either online, or offline. It can be
-			used only with conjunction with remount.
-
 block_validity		This options allows to enables/disables the in-kernel
 noblock_validity	facility for tracking filesystem metadata blocks
 			within internal data structures. This allows multi-
diff --git a/Documentation/filesystems/files.txt b/Documentation/filesystems/files.txt
index ac2facc50d2a..46dfc6b038c3 100644
--- a/Documentation/filesystems/files.txt
+++ b/Documentation/filesystems/files.txt
@@ -113,8 +113,8 @@ the fdtable structure -
 	if (fd >= 0) {
 		/* locate_fd() may have expanded fdtable, load the ptr */
 		fdt = files_fdtable(files);
-		FD_SET(fd, fdt->open_fds);
-		FD_CLR(fd, fdt->close_on_exec);
+		__set_open_fd(fd, fdt);
+		__clear_close_on_exec(fd, fdt);
 		spin_unlock(&files->file_lock);
 	.....
 
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index 792faa3c06cf..620a07844e8c 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -271,9 +271,26 @@ Some platforms may also use knowledge about what GPIOs are active for
 power management, such as by powering down unused chip sectors and, more
 easily, gating off unused clocks.
 
-Note that requesting a GPIO does NOT cause it to be configured in any
-way; it just marks that GPIO as in use.  Separate code must handle any
-pin setup (e.g. controlling which pin the GPIO uses, pullup/pulldown).
+For GPIOs that use pins known to the pinctrl subsystem, that subsystem should
+be informed of their use; a gpiolib driver's .request() operation may call
+pinctrl_request_gpio(), and a gpiolib driver's .free() operation may call
+pinctrl_free_gpio(). The pinctrl subsystem allows a pinctrl_request_gpio()
+to succeed concurrently with a pin or pingroup being "owned" by a device for
+pin multiplexing.
+
+Any programming of pin multiplexing hardware that is needed to route the
+GPIO signal to the appropriate pin should occur within a GPIO driver's
+.direction_input() or .direction_output() operations, and occur after any
+setup of an output GPIO's value. This allows a glitch-free migration from a
+pin's special function to GPIO. This is sometimes required when using a GPIO
+to implement a workaround on signals typically driven by a non-GPIO HW block.
+
+Some platforms allow some or all GPIO signals to be routed to different pins.
+Similarly, other aspects of the GPIO or pin may need to be configured, such as
+pullup/pulldown. Platform software should arrange that any such details are
+configured prior to gpio_request() being called for those GPIOs, e.g. using
+the pinctrl subsystem's mapping table, so that GPIO users need not be aware
+of these details.
 
 Also note that it's your responsibility to have stopped using a GPIO
 before you free it.
@@ -302,6 +319,8 @@ where 'flags' is currently defined to specify the following properties:
 
 	* GPIOF_INIT_LOW	- as output, set initial level to LOW
 	* GPIOF_INIT_HIGH	- as output, set initial level to HIGH
+	* GPIOF_OPEN_DRAIN	- gpio pin is open drain type.
+	* GPIOF_OPEN_SOURCE	- gpio pin is open source type.
 
 since GPIOF_INIT_* are only valid when configured as output, so group valid
 combinations as:
@@ -310,8 +329,19 @@ combinations as:
 	* GPIOF_OUT_INIT_LOW	- configured as output, initial level LOW
 	* GPIOF_OUT_INIT_HIGH	- configured as output, initial level HIGH
 
-In the future, these flags can be extended to support more properties such
-as open-drain status.
+When setting the flag as GPIOF_OPEN_DRAIN then it will assume that pins is
+open drain type. Such pins will not be driven to 1 in output mode. It is
+require to connect pull-up on such pins. By enabling this flag, gpio lib will
+make the direction to input when it is asked to set value of 1 in output mode
+to make the pin HIGH. The pin is make to LOW by driving value 0 in output mode.
+
+When setting the flag as GPIOF_OPEN_SOURCE then it will assume that pins is
+open source type. Such pins will not be driven to 0 in output mode. It is
+require to connect pull-down on such pin. By enabling this flag, gpio lib will
+make the direction to input when it is asked to set value of 0 in output mode
+to make the pin LOW. The pin is make to HIGH by driving value 1 in output mode.
+
+In the future, these flags can be extended to support more properties.
 
 Further more, to ease the claim/release of multiple GPIOs, 'struct gpio' is
 introduced to encapsulate all three fields as:
diff --git a/Documentation/hwmon/k10temp b/Documentation/hwmon/k10temp
index a10f73624ad3..90956b618025 100644
--- a/Documentation/hwmon/k10temp
+++ b/Documentation/hwmon/k10temp
@@ -11,7 +11,7 @@ Supported chips:
   Socket S1G2: Athlon (X2), Sempron (X2), Turion X2 (Ultra)
 * AMD Family 12h processors: "Llano" (E2/A4/A6/A8-Series)
 * AMD Family 14h processors: "Brazos" (C/E/G/Z-Series)
-* AMD Family 15h processors: "Bulldozer"
+* AMD Family 15h processors: "Bulldozer" (FX-Series), "Trinity"
 
   Prefix: 'k10temp'
   Addresses scanned: PCI space
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 2871fd500349..71f55bbcefc8 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -20,6 +20,7 @@ Supported adapters:
   * Intel Patsburg (PCH)
   * Intel DH89xxCC (PCH)
   * Intel Panther Point (PCH)
+  * Intel Lynx Point (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/i2c/busses/scx200_acb b/Documentation/i2c/busses/scx200_acb
index 7c07883d4dfc..ce83c871fe95 100644
--- a/Documentation/i2c/busses/scx200_acb
+++ b/Documentation/i2c/busses/scx200_acb
@@ -28,5 +28,5 @@ If the scx200_acb driver is built into the kernel, add the following
 parameter to your boot command line:
   scx200_acb.base=0x810,0x820
 If the scx200_acb driver is built as a module, add the following line to
-the file /etc/modprobe.conf instead:
+a configuration file in /etc/modprobe.d/ instead:
   options scx200_acb base=0x810,0x820
diff --git a/Documentation/ide/ide.txt b/Documentation/ide/ide.txt
index e77bebfa7b0d..7aca987c23d9 100644
--- a/Documentation/ide/ide.txt
+++ b/Documentation/ide/ide.txt
@@ -169,7 +169,7 @@ When using ide.c as a module in combination with kmod, add:
 
 	alias block-major-3 ide-probe
 
-to /etc/modprobe.conf.
+to a configuration file in /etc/modprobe.d/.
 
 When ide.c is used as a module, you can pass command line parameters to the
 driver using the "options=" keyword to insmod, while replacing any ',' with
diff --git a/Documentation/input/input.txt b/Documentation/input/input.txt
index b3d6787b4fb1..666c06c5ab0c 100644
--- a/Documentation/input/input.txt
+++ b/Documentation/input/input.txt
@@ -250,8 +250,8 @@ And so on up to event31.
 a USB keyboard works and is correctly connected to the kernel keyboard
 driver. 
 
-  Doing a cat /dev/input/mouse0 (c, 13, 32) will verify that a mouse
-is also emulated, characters should appear if you move it.
+  Doing a "cat /dev/input/mouse0" (c, 13, 32) will verify that a mouse
+is also emulated; characters should appear if you move it.
 
   You can test the joystick emulation with the 'jstest' utility,
 available in the joystick package (see Documentation/input/joystick.txt).
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 3b7488fc3373..e34b531dc316 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -225,6 +225,7 @@ Code  Seq#(hex)	Include File		Comments
 'j'	00-3F	linux/joystick.h
 'k'	00-0F	linux/spi/spidev.h	conflict!
 'k'	00-05	video/kyro.h		conflict!
+'k'	10-17	linux/hsi/hsi_char.h	HSI character device
 'l'	00-3F	linux/tcfs_fs.h		transparent cryptographic file system
 					<http://web.archive.org/web/*/http://mikonos.dia.unisa.it/tcfs>
 'l'	40-7F	linux/udf_fs_i.h	in development:
diff --git a/Documentation/isdn/README.gigaset b/Documentation/isdn/README.gigaset
index ef3343eaa002..7534c6039adc 100644
--- a/Documentation/isdn/README.gigaset
+++ b/Documentation/isdn/README.gigaset
@@ -97,8 +97,7 @@ GigaSet 307x Device Driver
 				   2.5.): 1=on (default), 0=off
 
      Depending on your distribution you may want to create a separate module
-     configuration file /etc/modprobe.d/gigaset for these, or add them to a
-     custom file like /etc/modprobe.conf.local.
+     configuration file like /etc/modprobe.d/gigaset.conf for these.
 
 2.2. Device nodes for user space programs
      ------------------------------------
@@ -212,8 +211,8 @@ GigaSet 307x Device Driver
 
         options ppp_async flag_time=0
 
-     to an appropriate module configuration file, like /etc/modprobe.d/gigaset
-     or /etc/modprobe.conf.local.
+     to an appropriate module configuration file, like
+     /etc/modprobe.d/gigaset.conf.
 
      Unimodem mode is needed for making some devices [e.g. SX100] work which
      do not support the regular Gigaset command set. If debug output (see
@@ -237,8 +236,8 @@ GigaSet 307x Device Driver
 	modprobe usb_gigaset startmode=0
      or by adding a line like
 	options usb_gigaset startmode=0
-     to an appropriate module configuration file, like /etc/modprobe.d/gigaset
-     or /etc/modprobe.conf.local.
+     to an appropriate module configuration file, like
+     /etc/modprobe.d/gigaset.conf
 
 2.6. Call-ID (CID) mode
      ------------------
@@ -310,7 +309,7 @@ GigaSet 307x Device Driver
 
            options isdn dialtimeout=15
 
-        to /etc/modprobe.d/gigaset, /etc/modprobe.conf.local or a similar file.
+        to /etc/modprobe.d/gigaset.conf or a similar file.
 
      Problem:
         The isdnlog program emits error messages or just doesn't work.
@@ -350,8 +349,7 @@ GigaSet 307x Device Driver
      The initial value can be set using the debug parameter when loading the
      module "gigaset", e.g. by adding a line
         options gigaset debug=0
-     to your module configuration file, eg. /etc/modprobe.d/gigaset or
-     /etc/modprobe.conf.local.
+     to your module configuration file, eg. /etc/modprobe.d/gigaset.conf
 
      Generated debugging information can be found
      - as output of the command
diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt
index c313d71324b4..9d5f2a90dca9 100644
--- a/Documentation/kbuild/kconfig.txt
+++ b/Documentation/kbuild/kconfig.txt
@@ -28,12 +28,10 @@ new (default) values, so you can use:
 
 	grep "(NEW)" conf.new
 
-to see the new config symbols or you can 'diff' the previous and
-new .config files to see the differences:
+to see the new config symbols or you can use diffconfig to see the
+differences between the previous and new .config files:
 
-	diff .config.old .config | less
-
-(Yes, we need something better here.)
+	scripts/diffconfig .config.old .config | less
 
 ______________________________________________________________________
 Environment variables for '*config'
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 58eac231fe69..c1601e5a8b71 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1699,6 +1699,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The default is to send the implementation identification
 			information.
 
+	nfsd.nfs4_disable_idmapping=
+			[NFSv4] When set to the default of '1', the NFSv4
+			server will return only numeric uids and gids to
+			clients using auth_sys, and will accept numeric uids
+			and gids from such clients.  This is intended to ease
+			migration from NFSv2/v3.
 
 	objlayoutdriver.osd_login_prog=
 			[NFS] [OBJLAYOUT] sets the pathname to the program which
@@ -1869,6 +1875,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			shutdown the other cpus.  Instead use the REBOOT_VECTOR
 			irq.
 
+	nomodule	Disable module load
+
 	nopat		[X86] Disable PAT (page attribute table extension of
 			pagetables) support.
 
diff --git a/Documentation/laptops/asus-laptop.txt b/Documentation/laptops/asus-laptop.txt
index 803e51f6768b..a1e04d679289 100644
--- a/Documentation/laptops/asus-laptop.txt
+++ b/Documentation/laptops/asus-laptop.txt
@@ -45,7 +45,7 @@ Status
 Usage
 -----
 
-  Try "modprobe asus_acpi". Check your dmesg (simply type dmesg). You should
+  Try "modprobe asus-laptop". Check your dmesg (simply type dmesg). You should
   see some lines like this :
 
       Asus Laptop Extras version 0.42
diff --git a/Documentation/laptops/sony-laptop.txt b/Documentation/laptops/sony-laptop.txt
index 2bd4e82e5d9f..0d5ac7f5287e 100644
--- a/Documentation/laptops/sony-laptop.txt
+++ b/Documentation/laptops/sony-laptop.txt
@@ -17,6 +17,11 @@ subsystem. See the logs of acpid or /proc/acpi/event and
 devices are created by the driver. Additionally, loading the driver with the
 debug option will report all events in the kernel log.
 
+The "scancodes" passed to the input system (that can be remapped with udev)
+are indexes to the table "sony_laptop_input_keycode_map" in the sony-laptop.c
+module.  For example the "FN/E" key combination (EJECTCD on some models)
+generates the scancode 20 (0x14).
+
 Backlight control:
 ------------------
 If your laptop model supports it, you will find sysfs files in the
diff --git a/Documentation/laptops/sonypi.txt b/Documentation/laptops/sonypi.txt
index 4857acfc50f1..606bdb9ce036 100644
--- a/Documentation/laptops/sonypi.txt
+++ b/Documentation/laptops/sonypi.txt
@@ -110,7 +110,7 @@ Module use:
 -----------
 
 In order to automatically load the sonypi module on use, you can put those
-lines in your /etc/modprobe.conf file:
+lines a configuration file in /etc/modprobe.d/:
 
 	alias char-major-10-250 sonypi
 	options sonypi minor=250
diff --git a/Documentation/mono.txt b/Documentation/mono.txt
index e8e1758e87da..d01ac6052194 100644
--- a/Documentation/mono.txt
+++ b/Documentation/mono.txt
@@ -38,11 +38,11 @@ if [ ! -e /proc/sys/fs/binfmt_misc/register ]; then
         /sbin/modprobe binfmt_misc
 	# Some distributions, like Fedora Core, perform
 	# the following command automatically when the
-	# binfmt_misc module is loaded into the kernel.
+	# binfmt_misc module is loaded into the kernel
+	# or during normal boot up (systemd-based systems).
 	# Thus, it is possible that the following line
-	# is not needed at all. Look at /etc/modprobe.conf
-	# to check whether this is applicable or not.
-        mount -t binfmt_misc none /proc/sys/fs/binfmt_misc
+	# is not needed at all.
+	mount -t binfmt_misc none /proc/sys/fs/binfmt_misc
 fi
 
 # Register support for .NET CLR binaries
diff --git a/Documentation/networking/baycom.txt b/Documentation/networking/baycom.txt
index 4e68849d5639..688f18fd4467 100644
--- a/Documentation/networking/baycom.txt
+++ b/Documentation/networking/baycom.txt
@@ -93,7 +93,7 @@ Every time a driver is inserted into the kernel, it has to know which
 modems it should access at which ports. This can be done with the setbaycom
 utility. If you are only using one modem, you can also configure the
 driver from the insmod command line (or by means of an option line in
-/etc/modprobe.conf).
+/etc/modprobe.d/*.conf).
 
 Examples:
   modprobe baycom_ser_fdx mode="ser12*" iobase=0x3f8 irq=4
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 080ad26690ae..bfea8a338901 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -173,9 +173,8 @@ bonding module at load time, or are specified via sysfs.
 
 	Module options may be given as command line arguments to the
 insmod or modprobe command, but are usually specified in either the
-/etc/modules.conf or /etc/modprobe.conf configuration file, or in a
-distro-specific configuration file (some of which are detailed in the next
-section).
+/etc/modrobe.d/*.conf configuration files, or in a distro-specific
+configuration file (some of which are detailed in the next section).
 
 	Details on bonding support for sysfs is provided in the
 "Configuring Bonding Manually via Sysfs" section, below.
@@ -1021,7 +1020,7 @@ ifcfg-bondX files.
 
 	Because the sysconfig scripts supply the bonding module
 options in the ifcfg-bondX file, it is not necessary to add them to
-the system /etc/modules.conf or /etc/modprobe.conf configuration file.
+the system /etc/modules.d/*.conf configuration files.
 
 3.2 Configuration with Initscripts Support
 ------------------------------------------
@@ -1098,15 +1097,13 @@ queried targets, e.g.,
 	arp_ip_target=+192.168.1.1 arp_ip_target=+192.168.1.2
 
 	is the proper syntax to specify multiple targets.  When specifying
-options via BONDING_OPTS, it is not necessary to edit /etc/modules.conf or
-/etc/modprobe.conf.
+options via BONDING_OPTS, it is not necessary to edit /etc/modprobe.d/*.conf.
 
 	For even older versions of initscripts that do not support
-BONDING_OPTS, it is necessary to edit /etc/modules.conf (or
-/etc/modprobe.conf, depending upon your distro) to load the bonding module
-with your desired options when the bond0 interface is brought up.  The
-following lines in /etc/modules.conf (or modprobe.conf) will load the
-bonding module, and select its options:
+BONDING_OPTS, it is necessary to edit /etc/modprobe.d/*.conf, depending upon
+your distro) to load the bonding module with your desired options when the
+bond0 interface is brought up.  The following lines in /etc/modprobe.d/*.conf
+will load the bonding module, and select its options:
 
 alias bond0 bonding
 options bond0 mode=balance-alb miimon=100
@@ -1152,7 +1149,7 @@ knowledge of bonding.  One such distro is SuSE Linux Enterprise Server
 version 8.
 
 	The general method for these systems is to place the bonding
-module parameters into /etc/modules.conf or /etc/modprobe.conf (as
+module parameters into a config file in /etc/modprobe.d/ (as
 appropriate for the installed distro), then add modprobe and/or
 ifenslave commands to the system's global init script.  The name of
 the global init script differs; for sysconfig, it is
@@ -1228,7 +1225,7 @@ network initialization scripts.
 specify a different name for each instance (the module loading system
 requires that every loaded module, even multiple instances of the same
 module, have a unique name).  This is accomplished by supplying multiple
-sets of bonding options in /etc/modprobe.conf, for example:
+sets of bonding options in /etc/modprobe.d/*.conf, for example:
 
 alias bond0 bonding
 options bond0 -o bond0 mode=balance-rr miimon=100
@@ -1793,8 +1790,8 @@ route additions may cause trouble.
 	On systems with network configuration scripts that do not
 associate physical devices directly with network interface names (so
 that the same physical device always has the same "ethX" name), it may
-be necessary to add some special logic to either /etc/modules.conf or
-/etc/modprobe.conf (depending upon which is installed on the system).
+be necessary to add some special logic to config files in
+/etc/modprobe.d/.
 
 	For example, given a modules.conf containing the following:
 
@@ -1821,20 +1818,15 @@ add above bonding e1000 tg3
 bonding is loaded.  This command is fully documented in the
 modules.conf manual page.
 
-	On systems utilizing modprobe.conf (or modprobe.conf.local),
-an equivalent problem can occur.  In this case, the following can be
-added to modprobe.conf (or modprobe.conf.local, as appropriate), as
-follows (all on one line; it has been split here for clarity):
+	On systems utilizing modprobe an equivalent problem can occur.
+In this case, the following can be added to config files in
+/etc/modprobe.d/ as:
 
-install bonding /sbin/modprobe tg3; /sbin/modprobe e1000;
-	/sbin/modprobe --ignore-install bonding
+softdep bonding pre: tg3 e1000
 
-	This will, when loading the bonding module, rather than
-performing the normal action, instead execute the provided command.
-This command loads the device drivers in the order needed, then calls
-modprobe with --ignore-install to cause the normal action to then take
-place.  Full documentation on this can be found in the modprobe.conf
-and modprobe manual pages.
+	This will load tg3 and e1000 modules before loading the bonding one.
+Full documentation on this can be found in the modprobe.d and modprobe
+manual pages.
 
 8.3. Painfully Slow Or No Failed Link Detection By Miimon
 ---------------------------------------------------------
diff --git a/Documentation/networking/dl2k.txt b/Documentation/networking/dl2k.txt
index 10e8490fa406..cba74f7a3abc 100644
--- a/Documentation/networking/dl2k.txt
+++ b/Documentation/networking/dl2k.txt
@@ -45,12 +45,13 @@ Now eth0 should active, you can test it by "ping" or get more information by
 "ifconfig". If tested ok, continue the next step.
 
 4. cp dl2k.ko /lib/modules/`uname -r`/kernel/drivers/net
-5. Add the following line to /etc/modprobe.conf:
+5. Add the following line to /etc/modprobe.d/dl2k.conf:
 	alias eth0 dl2k
-6. Run "netconfig" or "netconf" to create configuration script ifcfg-eth0
+6. Run depmod to updated module indexes.
+7. Run "netconfig" or "netconf" to create configuration script ifcfg-eth0
    located at /etc/sysconfig/network-scripts or create it manually.
    [see - Configuration Script Sample]
-7. Driver will automatically load and configure at next boot time.
+8. Driver will automatically load and configure at next boot time.
 
 Compiling the Driver
 ====================
@@ -154,8 +155,8 @@ Installing the Driver
   -----------------
   1. Copy dl2k.o to the network modules directory, typically
      /lib/modules/2.x.x-xx/net or /lib/modules/2.x.x/kernel/drivers/net.
-  2. Locate the boot module configuration file, most commonly modprobe.conf
-     or modules.conf (for 2.4) in the /etc directory. Add the following lines:
+  2. Locate the boot module configuration file, most commonly in the
+     /etc/modprobe.d/ directory. Add the following lines:
 
      alias ethx dl2k
      options dl2k <optional parameters>
diff --git a/Documentation/networking/driver.txt b/Documentation/networking/driver.txt
index 03283daa64fe..da59e2884130 100644
--- a/Documentation/networking/driver.txt
+++ b/Documentation/networking/driver.txt
@@ -2,16 +2,16 @@ Document about softnet driver issues
 
 Transmit path guidelines:
 
-1) The hard_start_xmit method must never return '1' under any
-   normal circumstances.  It is considered a hard error unless
+1) The ndo_start_xmit method must not return NETDEV_TX_BUSY under
+   any normal circumstances.  It is considered a hard error unless
    there is no way your device can tell ahead of time when it's
    transmit function will become busy.
 
    Instead it must maintain the queue properly.  For example,
    for a driver implementing scatter-gather this means:
 
-	static int drv_hard_start_xmit(struct sk_buff *skb,
-		   		       struct net_device *dev)
+	static netdev_tx_t drv_hard_start_xmit(struct sk_buff *skb,
+					       struct net_device *dev)
 	{
 		struct drv *dp = netdev_priv(dev);
 
@@ -23,7 +23,7 @@ Transmit path guidelines:
 			unlock_tx(dp);
 			printk(KERN_ERR PFX "%s: BUG! Tx Ring full when queue awake!\n",
 			       dev->name);
-			return 1;
+			return NETDEV_TX_BUSY;
 		}
 
 		... queue packet to card ...
@@ -35,6 +35,7 @@ Transmit path guidelines:
 		...
 		unlock_tx(dp);
 		...
+		return NETDEV_TX_OK;
 	}
 
    And then at the end of your TX reclamation event handling:
@@ -58,15 +59,12 @@ Transmit path guidelines:
             TX_BUFFS_AVAIL(dp) > 0)
 		netif_wake_queue(dp->dev);
 
-2) Do not forget to update netdev->trans_start to jiffies after
-   each new tx packet is given to the hardware.
-
-3) A hard_start_xmit method must not modify the shared parts of a
+2) An ndo_start_xmit method must not modify the shared parts of a
    cloned SKB.
 
-4) Do not forget that once you return 0 from your hard_start_xmit
-   method, it is your driver's responsibility to free up the SKB
-   and in some finite amount of time.
+3) Do not forget that once you return NETDEV_TX_OK from your
+   ndo_start_xmit method, it is your driver's responsibility to free
+   up the SKB and in some finite amount of time.
 
    For example, this means that it is not allowed for your TX
    mitigation scheme to let TX packets "hang out" in the TX
@@ -74,8 +72,9 @@ Transmit path guidelines:
    This error can deadlock sockets waiting for send buffer room
    to be freed up.
 
-   If you return 1 from the hard_start_xmit method, you must not keep
-   any reference to that SKB and you must not attempt to free it up.
+   If you return NETDEV_TX_BUSY from the ndo_start_xmit method, you
+   must not keep any reference to that SKB and you must not attempt
+   to free it up.
 
 Probing guidelines:
 
@@ -85,10 +84,10 @@ Probing guidelines:
 
 Close/stop guidelines:
 
-1) After the dev->stop routine has been called, the hardware must
+1) After the ndo_stop routine has been called, the hardware must
    not receive or transmit any data.  All in flight packets must
    be aborted. If necessary, poll or wait for completion of 
    any reset commands.
 
-2) The dev->stop routine will be called by unregister_netdevice
+2) The ndo_stop routine will be called by unregister_netdevice
    if device is still UP.
diff --git a/Documentation/networking/e100.txt b/Documentation/networking/e100.txt
index 162f323a7a1f..fcb6c71cdb69 100644
--- a/Documentation/networking/e100.txt
+++ b/Documentation/networking/e100.txt
@@ -94,8 +94,8 @@ Additional Configurations
 
   Configuring a network driver to load properly when the system is started is
   distribution dependent. Typically, the configuration process involves adding
-  an alias line to /etc/modules.conf or /etc/modprobe.conf as well as editing
-  other system startup scripts and/or configuration files.  Many popular Linux
+  an alias line to /etc/modprobe.d/*.conf as well as editing other system
+  startup scripts and/or configuration files.  Many popular Linux
   distributions ship with tools to make these changes for you. To learn the
   proper way to configure a network device for your system, refer to your
   distribution documentation.  If during this process you are asked for the
@@ -103,7 +103,7 @@ Additional Configurations
   PRO/100 Family of Adapters is e100.
 
   As an example, if you install the e100 driver for two PRO/100 adapters
-  (eth0 and eth1), add the following to modules.conf or modprobe.conf:
+  (eth0 and eth1), add the following to a configuraton file in /etc/modprobe.d/
 
        alias eth0 e100
        alias eth1 e100
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ad3e80e17b4f..bd80ba5847d2 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -604,15 +604,8 @@ IP Variables:
 ip_local_port_range - 2 INTEGERS
 	Defines the local port range that is used by TCP and UDP to
 	choose the local port. The first number is the first, the
-	second the last local port number. Default value depends on
-	amount of memory available on the system:
-	> 128Mb 32768-61000
-	< 128Mb 1024-4999 or even less.
-	This number defines number of active connections, which this
-	system can issue simultaneously to systems not supporting
-	TCP extensions (timestamps). With tcp_tw_recycle enabled
-	(i.e. by default) range 1024-4999 is enough to issue up to
-	2000 connections per second to systems supporting timestamps.
+	second the last local port number. The default values are
+	32768 and 61000 respectively.
 
 ip_local_reserved_ports - list of comma separated ranges
 	Specify the ports which are reserved for known third-party
diff --git a/Documentation/networking/ipv6.txt b/Documentation/networking/ipv6.txt
index 9fd7e21296c8..6cd74fa55358 100644
--- a/Documentation/networking/ipv6.txt
+++ b/Documentation/networking/ipv6.txt
@@ -2,9 +2,9 @@
 Options for the ipv6 module are supplied as parameters at load time.
 
 Module options may be given as command line arguments to the insmod
-or modprobe command, but are usually specified in either the
-/etc/modules.conf or /etc/modprobe.conf configuration file, or in a
-distro-specific configuration file.
+or modprobe command, but are usually specified in either
+/etc/modules.d/*.conf configuration files, or in a distro-specific
+configuration file.
 
 The available ipv6 module parameters are listed below.  If a parameter
 is not specified the default value is used.
diff --git a/Documentation/networking/ixgb.txt b/Documentation/networking/ixgb.txt
index e196f16df313..d75a1f9565bb 100644
--- a/Documentation/networking/ixgb.txt
+++ b/Documentation/networking/ixgb.txt
@@ -274,9 +274,9 @@ Additional Configurations
   -------------------------------------------------
   Configuring a network driver to load properly when the system is started is
   distribution dependent. Typically, the configuration process involves adding
-  an alias line to /etc/modprobe.conf as well as editing other system startup
-  scripts and/or configuration files.  Many popular Linux distributions ship
-  with tools to make these changes for you.  To learn the proper way to
+  an alias line to files in /etc/modprobe.d/ as well as editing other system
+  startup scripts and/or configuration files.  Many popular Linux distributions
+  ship with tools to make these changes for you.  To learn the proper way to
   configure a network device for your system, refer to your distribution
   documentation.  If during this process you are asked for the driver or module
   name, the name for the Linux Base Driver for the Intel 10GbE Family of
diff --git a/Documentation/networking/ltpc.txt b/Documentation/networking/ltpc.txt
index fe2a9129d959..0bf3220c715b 100644
--- a/Documentation/networking/ltpc.txt
+++ b/Documentation/networking/ltpc.txt
@@ -25,7 +25,7 @@ the driver will try to determine them itself.
 
 If you load the driver as a module, you can pass the parameters "io=",
 "irq=", and "dma=" on the command line with insmod or modprobe, or add
-them as options in /etc/modprobe.conf:
+them as options in a configuration file in /etc/modprobe.d/ directory:
 
  alias lt0 ltpc # autoload the module when the interface is configured
  options ltpc io=0x240 irq=9 dma=1
diff --git a/Documentation/networking/netdevices.txt b/Documentation/networking/netdevices.txt
index 89358341682a..c7ecc7080494 100644
--- a/Documentation/networking/netdevices.txt
+++ b/Documentation/networking/netdevices.txt
@@ -47,26 +47,25 @@ packets is preferred.
 
 struct net_device synchronization rules
 =======================================
-dev->open:
+ndo_open:
 	Synchronization: rtnl_lock() semaphore.
 	Context: process
 
-dev->stop:
+ndo_stop:
 	Synchronization: rtnl_lock() semaphore.
 	Context: process
-	Note1: netif_running() is guaranteed false
-	Note2: dev->poll() is guaranteed to be stopped
+	Note: netif_running() is guaranteed false
 
-dev->do_ioctl:
+ndo_do_ioctl:
 	Synchronization: rtnl_lock() semaphore.
 	Context: process
 
-dev->get_stats:
+ndo_get_stats:
 	Synchronization: dev_base_lock rwlock.
 	Context: nominally process, but don't sleep inside an rwlock
 
-dev->hard_start_xmit:
-	Synchronization: netif_tx_lock spinlock.
+ndo_start_xmit:
+	Synchronization: __netif_tx_lock spinlock.
 
 	When the driver sets NETIF_F_LLTX in dev->features this will be
 	called without holding netif_tx_lock. In this case the driver
@@ -87,20 +86,20 @@ dev->hard_start_xmit:
 	o NETDEV_TX_LOCKED Locking failed, please retry quickly.
 	  Only valid when NETIF_F_LLTX is set.
 
-dev->tx_timeout:
-	Synchronization: netif_tx_lock spinlock.
+ndo_tx_timeout:
+	Synchronization: netif_tx_lock spinlock; all TX queues frozen.
 	Context: BHs disabled
 	Notes: netif_queue_stopped() is guaranteed true
 
-dev->set_rx_mode:
-	Synchronization: netif_tx_lock spinlock.
+ndo_set_rx_mode:
+	Synchronization: netif_addr_lock spinlock.
 	Context: BHs disabled
 
 struct napi_struct synchronization rules
 ========================================
 napi->poll:
 	Synchronization: NAPI_STATE_SCHED bit in napi->state.  Device
-		driver's dev->close method will invoke napi_disable() on
+		driver's ndo_stop method will invoke napi_disable() on
 		all NAPI instances which will do a sleeping poll on the
 		NAPI_STATE_SCHED napi->state bit, waiting for all pending
 		NAPI activity to cease.
diff --git a/Documentation/networking/vortex.txt b/Documentation/networking/vortex.txt
index bd70976b8160..b4038ffb3bc5 100644
--- a/Documentation/networking/vortex.txt
+++ b/Documentation/networking/vortex.txt
@@ -67,8 +67,8 @@ Module parameters
 =================
 
 There are several parameters which may be provided to the driver when
-its module is loaded.  These are usually placed in /etc/modprobe.conf
-(/etc/modules.conf in 2.4).  Example:
+its module is loaded.  These are usually placed in /etc/modprobe.d/*.conf
+configuretion files.  Example:
 
 options 3c59x debug=3 rx_copybreak=300
 
@@ -425,7 +425,7 @@ steps you should take:
       1) Increase the debug level.  Usually this is done via:
 
          a) modprobe driver debug=7
-         b) In /etc/modprobe.conf (or /etc/modules.conf for 2.4):
+         b) In /etc/modprobe.d/driver.conf:
             options driver debug=7
 
       2) Recreate the problem with the higher debug level,
diff --git a/Documentation/parport.txt b/Documentation/parport.txt
index 93a7ceef398d..c208e4366c03 100644
--- a/Documentation/parport.txt
+++ b/Documentation/parport.txt
@@ -36,18 +36,17 @@ addresses should not be specified for supported PCI cards since they
 are automatically detected.
 
 
-KMod
-----
+modprobe
+--------
 
-If you use kmod, you will find it useful to edit /etc/modprobe.conf.
-Here is an example of the lines that need to be added:
+If you use modprobe , you will find it useful to add lines as below to a
+configuration file in /etc/modprobe.d/ directory:.
 
 	alias parport_lowlevel parport_pc
 	options parport_pc io=0x378,0x278 irq=7,auto
 
-KMod will then automatically load parport_pc (with the options
-"io=0x378,0x278 irq=7,auto") whenever a parallel port device driver
-(such as lp) is loaded.
+modprobe will load parport_pc (with the options "io=0x378,0x278 irq=7,auto")
+whenever a parallel port device driver (such as lp) is loaded.
 
 Note that these are example lines only!  You shouldn't in general need
 to specify any options to parport_pc in order to be able to use a
diff --git a/Documentation/s390/3270.txt b/Documentation/s390/3270.txt
index 7a5c73a7ed7f..7c715de99774 100644
--- a/Documentation/s390/3270.txt
+++ b/Documentation/s390/3270.txt
@@ -47,9 +47,9 @@ including the console 3270, changes subchannel identifier relative to
 one another.  ReIPL as soon as possible after running the configuration
 script and the resulting /tmp/mkdev3270.
 
-If you have chosen to make tub3270 a module, you add a line to
-/etc/modprobe.conf.  If you are working on a VM virtual machine, you
-can use DEF GRAF to define virtual 3270 devices.
+If you have chosen to make tub3270 a module, you add a line to a
+configuration file under /etc/modprobe.d/.  If you are working on a VM
+virtual machine, you can use DEF GRAF to define virtual 3270 devices.
 
 You may generate both 3270 and 3215 console support, or one or the
 other, or neither.  If you generate both, the console type under VM is
@@ -60,7 +60,7 @@ at boot time to a 3270 if it is a 3215.
 
 In brief, these are the steps:
 	1. Install the tub3270 patch
-	2. (If a module) add a line to /etc/modprobe.conf
+	2. (If a module) add a line to a file in /etc/modprobe.d/*.conf
 	3. (If VM) define devices with DEF GRAF
 	4. Reboot
 	5. Configure
@@ -84,13 +84,12 @@ Here are the installation steps in detail:
 		make modules_install
 
 	2. (Perform this step only if you have configured tub3270 as a
-	module.)  Add a line to /etc/modprobe.conf to automatically
-	load the driver when it's needed.  With this line added,
-	you will see login prompts appear on your 3270s as soon as
-	boot is complete (or with emulated 3270s, as soon as you dial
-	into your vm guest using the command "DIAL <vmguestname>").
-	Since the line-mode major number is 227, the line to add to
-	/etc/modprobe.conf should be:
+	module.)  Add a line to a file /etc/modprobe.d/*.conf to automatically
+	load the driver when it's needed.  With this line added, you will see
+	login prompts appear on your 3270s as soon as boot is complete (or
+	with emulated 3270s, as soon as you dial into your vm guest using the
+	command "DIAL <vmguestname>").  Since the line-mode major number is
+	227, the line to add should be:
 		alias char-major-227 tub3270
 
 	3. Define graphic devices to your vm guest machine, if you
diff --git a/Documentation/scsi/00-INDEX b/Documentation/scsi/00-INDEX
index b48ded55b555..b7dd6502bec5 100644
--- a/Documentation/scsi/00-INDEX
+++ b/Documentation/scsi/00-INDEX
@@ -94,3 +94,5 @@ sym53c8xx_2.txt
 	- info on second generation driver for sym53c8xx based adapters
 tmscsim.txt
 	- info on driver for AM53c974 based adapters
+ufs.txt
+	- info on Universal Flash Storage(UFS) and UFS host controller driver.
diff --git a/Documentation/scsi/aic79xx.txt b/Documentation/scsi/aic79xx.txt
index 64ac7093c872..e2d3273000d4 100644
--- a/Documentation/scsi/aic79xx.txt
+++ b/Documentation/scsi/aic79xx.txt
@@ -215,7 +215,7 @@ The following information is available in this file:
                  INCORRECTLY CAN RENDER YOUR SYSTEM INOPERABLE.
                  USE THEM WITH CAUTION. 
 
-   Edit the file "modprobe.conf" in the directory /etc and add/edit a
+   Put a .conf file in the /etc/modprobe.d/ directory and add/edit a
    line containing 'options aic79xx aic79xx=[command[,command...]]' where
    'command' is one or more of the following:
    -----------------------------------------------------------------
diff --git a/Documentation/scsi/aic7xxx.txt b/Documentation/scsi/aic7xxx.txt
index 18f8d1905e6a..7c5d0223d444 100644
--- a/Documentation/scsi/aic7xxx.txt
+++ b/Documentation/scsi/aic7xxx.txt
@@ -190,7 +190,7 @@ The following information is available in this file:
                  INCORRECTLY CAN RENDER YOUR SYSTEM INOPERABLE.
                  USE THEM WITH CAUTION. 
 
-   Edit the file "modprobe.conf" in the directory /etc and add/edit a
+   Put a .conf file in the /etc/modprobe.d directory and add/edit a
    line containing 'options aic7xxx aic7xxx=[command[,command...]]' where
    'command' is one or more of the following:
    -----------------------------------------------------------------
diff --git a/Documentation/scsi/osst.txt b/Documentation/scsi/osst.txt
index ad86c6d1e898..00c8ebb2fd18 100644
--- a/Documentation/scsi/osst.txt
+++ b/Documentation/scsi/osst.txt
@@ -66,7 +66,7 @@ recognized.
 If you want to have the module autoloaded on access to /dev/osst, you may
 add something like
 alias char-major-206 osst
-to your /etc/modprobe.conf (before 2.6: modules.conf).
+to a file under /etc/modprobe.d/ directory.
 
 You may find it convenient to create a symbolic link 
 ln -s nosst0 /dev/tape
diff --git a/Documentation/scsi/st.txt b/Documentation/scsi/st.txt
index 691ca292c24d..685bf3582abe 100644
--- a/Documentation/scsi/st.txt
+++ b/Documentation/scsi/st.txt
@@ -390,6 +390,10 @@ MTSETDRVBUFFER
 	     MT_ST_SYSV sets the SYSV semantics (mode)
 	     MT_ST_NOWAIT enables immediate mode (i.e., don't wait for
 	        the command to finish) for some commands (e.g., rewind)
+	     MT_ST_NOWAIT_EOF enables immediate filemark mode (i.e. when
+	        writing a filemark, don't wait for it to complete). Please
+		see the BASICS note about MTWEOFI with respect to the
+		possible dangers of writing immediate filemarks.
 	     MT_ST_SILI enables setting the SILI bit in SCSI commands when
 		reading in variable block mode to enhance performance when
 		reading blocks shorter than the byte count; set this only
diff --git a/Documentation/scsi/ufs.txt b/Documentation/scsi/ufs.txt
new file mode 100644
index 000000000000..41a6164592aa
--- /dev/null
+++ b/Documentation/scsi/ufs.txt
@@ -0,0 +1,133 @@
+                       Universal Flash Storage
+                       =======================
+
+
+Contents
+--------
+
+1. Overview
+2. UFS Architecture Overview
+  2.1 Application Layer
+  2.2 UFS Transport Protocol(UTP) layer
+  2.3 UFS Interconnect(UIC) Layer
+3. UFSHCD Overview
+  3.1 UFS controller initialization
+  3.2 UTP Transfer requests
+  3.3 UFS error handling
+  3.4 SCSI Error handling
+
+
+1. Overview
+-----------
+
+Universal Flash Storage(UFS) is a storage specification for flash devices.
+It is aimed to provide a universal storage interface for both
+embedded and removable flash memory based storage in mobile
+devices such as smart phones and tablet computers. The specification
+is defined by JEDEC Solid State Technology Association. UFS is based
+on MIPI M-PHY physical layer standard. UFS uses MIPI M-PHY as the
+physical layer and MIPI Unipro as the link layer.
+
+The main goals of UFS is to provide,
+ * Optimized performance:
+   For UFS version 1.0 and 1.1 the target performance is as follows,
+   Support for Gear1 is mandatory (rate A: 1248Mbps, rate B: 1457.6Mbps)
+   Support for Gear2 is optional (rate A: 2496Mbps, rate B: 2915.2Mbps)
+   Future version of the standard,
+   Gear3 (rate A: 4992Mbps, rate B: 5830.4Mbps)
+ * Low power consumption
+ * High random IOPs and low latency
+
+
+2. UFS Architecture Overview
+----------------------------
+
+UFS has a layered communication architecture which is based on SCSI
+SAM-5 architectural model.
+
+UFS communication architecture consists of following layers,
+
+2.1 Application Layer
+
+  The Application layer is composed of UFS command set layer(UCS),
+  Task Manager and Device manager. The UFS interface is designed to be
+  protocol agnostic, however SCSI has been selected as a baseline
+  protocol for versions 1.0 and 1.1 of UFS protocol  layer.
+  UFS supports subset of SCSI commands defined by SPC-4 and SBC-3.
+  * UCS: It handles SCSI commands supported by UFS specification.
+  * Task manager: It handles task management functions defined by the
+     UFS which are meant for command queue control.
+  * Device manager: It handles device level operations and device
+     configuration operations. Device level operations mainly involve
+     device power management operations and commands to Interconnect
+     layers. Device level configurations involve handling of query
+     requests which are used to modify and retrieve configuration
+     information of the device.
+
+2.2 UFS Transport Protocol(UTP) layer
+
+  UTP layer provides services for
+  the higher layers through Service Access Points. UTP defines 3
+  service access points for higher layers.
+  * UDM_SAP: Device manager service access point is exposed to device
+    manager for device level operations. These device level operations
+    are done through query requests.
+  * UTP_CMD_SAP: Command service access point is exposed to UFS command
+    set layer(UCS) to transport commands.
+  * UTP_TM_SAP: Task management service access point is exposed to task
+    manager to transport task management functions.
+  UTP transports messages through UFS protocol information unit(UPIU).
+
+2.3 UFS Interconnect(UIC) Layer
+
+  UIC is the lowest layer of UFS layered architecture. It handles
+  connection between UFS host and UFS device. UIC consists of
+  MIPI UniPro and MIPI M-PHY. UIC provides 2 service access points
+  to upper layer,
+  * UIC_SAP: To transport UPIU between UFS host and UFS device.
+  * UIO_SAP: To issue commands to Unipro layers.
+
+
+3. UFSHCD Overview
+------------------
+
+The UFS host controller driver is based on Linux SCSI Framework.
+UFSHCD is a low level device driver which acts as an interface between
+SCSI Midlayer and PCIe based UFS host controllers.
+
+The current UFSHCD implementation supports following functionality,
+
+3.1 UFS controller initialization
+
+  The initialization module brings UFS host controller to active state
+  and prepares the controller to transfer commands/response between
+  UFSHCD and UFS device.
+
+3.2 UTP Transfer requests
+
+  Transfer request handling module of UFSHCD receives SCSI commands
+  from SCSI Midlayer, forms UPIUs and issues the UPIUs to UFS Host
+  controller. Also, the module decodes, responses received from UFS
+  host controller in the form of UPIUs and intimates the SCSI Midlayer
+  of the status of the command.
+
+3.3 UFS error handling
+
+  Error handling module handles Host controller fatal errors,
+  Device fatal errors and UIC interconnect layer related errors.
+
+3.4 SCSI Error handling
+
+  This is done through UFSHCD SCSI error handling routines registered
+  with SCSI Midlayer. Examples of some of the error handling commands
+  issues by SCSI Midlayer are Abort task, Lun reset and host reset.
+  UFSHCD Routines to perform these tasks are registered with
+  SCSI Midlayer through .eh_abort_handler, .eh_device_reset_handler and
+  .eh_host_reset_handler.
+
+In this version of UFSHCD Query requests and power management
+functionality are not implemented.
+
+UFS Specifications can be found at,
+UFS - http://www.jedec.org/sites/default/files/docs/JESD220.pdf
+UFSHCI - http://www.jedec.org/sites/default/files/docs/JESD223.pdf
diff --git a/Documentation/serial/computone.txt b/Documentation/serial/computone.txt
index 39ddcdbeeb85..a6a1158ea2ba 100644
--- a/Documentation/serial/computone.txt
+++ b/Documentation/serial/computone.txt
@@ -49,7 +49,7 @@ Hardware - If you have an ISA card, find a free interrupt and io port.
 
 	Note the hardware address from the Computone ISA cards installed into
 		the system.  These are required for editing ip2.c or editing
-		/etc/modprobe.conf, or for specification on the modprobe
+		/etc/modprobe.d/*.conf, or for specification on the modprobe
 		command line.
 
 	Note that the /etc/modules.conf should be used for older (pre-2.6)
@@ -66,7 +66,7 @@ b) Run "make config" or "make menuconfig" or "make xconfig"
 c) Set address on ISA cards then:
    edit /usr/src/linux/drivers/char/ip2.c if needed 
 	or
-   edit /etc/modprobe.conf if needed (module).
+   edit config file in  /etc/modprobe.d/ if needed (module).
 	or both to match this setting.
 d) Run "make modules"
 e) Run "make modules_install"
@@ -153,11 +153,11 @@ the irqs are not specified the driver uses the default in ip2.c (which
 selects polled mode). If no base addresses are specified the defaults in 
 ip2.c are used. If you are autoloading the driver module with kerneld or
 kmod the base addresses and interrupt number must also be set in ip2.c
-and recompile or just insert and options line in /etc/modprobe.conf or both.
+and recompile or just insert and options line in /etc/modprobe.d/*.conf or both.
 The options line is equivalent to the command line and takes precedence over
 what is in ip2.c. 
 
-/etc/modprobe.conf sample:
+config sample to put /etc/modprobe.d/*.conf:
 	options ip2 io=1,0x328 irq=1,10
 	alias char-major-71 ip2
 	alias char-major-72 ip2
diff --git a/Documentation/serial/rocket.txt b/Documentation/serial/rocket.txt
index 1d8582990435..60b039891057 100644
--- a/Documentation/serial/rocket.txt
+++ b/Documentation/serial/rocket.txt
@@ -62,7 +62,7 @@ in the system log at /var/log/messages.
 
 If installed as a module, the module must be loaded.  This can be done
 manually by entering "modprobe rocket".  To have the module loaded automatically
-upon system boot, edit the /etc/modprobe.conf file and add the line
+upon system boot, edit a /etc/modprobe.d/*.conf file and add the line
 "alias char-major-46 rocket".
 
 In order to use the ports, their device names (nodes) must be created with mknod.
diff --git a/Documentation/serial/stallion.txt b/Documentation/serial/stallion.txt
index 5c4902d9a5be..55090914a9c5 100644
--- a/Documentation/serial/stallion.txt
+++ b/Documentation/serial/stallion.txt
@@ -139,8 +139,8 @@ secondary address 0x280 and IRQ 10.
 
 You will probably want to enter this module load and configuration information
 into your system startup scripts so that the drivers are loaded and configured
-on each system boot. Typically the start up script would be something like
-/etc/modprobe.conf.
+on each system boot. Typically configuration files are put in the
+/etc/modprobe.d/ directory.
 
 
 2.2 STATIC DRIVER CONFIGURATION:
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 6f75ba3b8a39..8c16d50f6cb6 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -2044,7 +2044,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
     Install the necessary firmware files in alsa-firmware package.
     When no hotplug fw loader is available, you need to load the
     firmware via vxloader utility in alsa-tools package.  To invoke
-    vxloader automatically, add the following to /etc/modprobe.conf
+    vxloader automatically, add the following to /etc/modprobe.d/alsa.conf
 
 	install snd-vx222 /sbin/modprobe --first-time -i snd-vx222 && /usr/bin/vxloader
 
@@ -2168,10 +2168,10 @@ corresponds to the card index of ALSA.  Usually, define this
 as the same card module.
 
 An example configuration for a single emu10k1 card is like below:
------ /etc/modprobe.conf
+----- /etc/modprobe.d/alsa.conf
 alias snd-card-0 snd-emu10k1
 alias sound-slot-0 snd-emu10k1
------ /etc/modprobe.conf
+----- /etc/modprobe.d/alsa.conf
 
 The available number of auto-loaded sound cards depends on the module
 option "cards_limit" of snd module.  As default it's set to 1.
@@ -2184,7 +2184,7 @@ cards is kept consistent.
 
 An example configuration for two sound cards is like below:
 
------ /etc/modprobe.conf
+----- /etc/modprobe.d/alsa.conf
 # ALSA portion
 options snd cards_limit=2
 alias snd-card-0 snd-interwave
@@ -2194,7 +2194,7 @@ options snd-ens1371 index=1
 # OSS/Free portion
 alias sound-slot-0 snd-interwave
 alias sound-slot-1 snd-ens1371
------ /etc/modprobe.conf
+----- /etc/modprobe.d/alsa.conf
 
 In this example, the interwave card is always loaded as the first card
 (index 0) and ens1371 as the second (index 1).
diff --git a/Documentation/sound/alsa/Audiophile-Usb.txt b/Documentation/sound/alsa/Audiophile-Usb.txt
index a4c53d8961e1..654dd3b694a8 100644
--- a/Documentation/sound/alsa/Audiophile-Usb.txt
+++ b/Documentation/sound/alsa/Audiophile-Usb.txt
@@ -232,7 +232,7 @@ The parameter can be given:
    # modprobe snd-usb-audio index=1 device_setup=0x09
 
  * Or while configuring the modules options in your modules configuration file
-   - For Fedora distributions, edit the /etc/modprobe.conf file:
+   (tipically a .conf file in /etc/modprobe.d/ directory:
        alias snd-card-1 snd-usb-audio
        options snd-usb-audio index=1 device_setup=0x09
 
@@ -253,7 +253,7 @@ CAUTION when initializing the device
    - first turn off the device
    - de-register the snd-usb-audio module (modprobe -r)
    - change the device_setup parameter by changing the device_setup
-     option in /etc/modprobe.conf 
+     option in /etc/modprobe.d/*.conf
    - turn on the device
  * A workaround for this last issue has been applied to kernel 2.6.23, but it may not
    be enough to ensure the 'stability' of the device initialization.
diff --git a/Documentation/sound/alsa/MIXART.txt b/Documentation/sound/alsa/MIXART.txt
index ef42c44fa1f2..4ee35b4fbe4a 100644
--- a/Documentation/sound/alsa/MIXART.txt
+++ b/Documentation/sound/alsa/MIXART.txt
@@ -76,9 +76,9 @@ FIRMWARE
  when CONFIG_FW_LOADER is set.  The mixartloader is necessary only
  for older versions or when you build the driver into kernel.]
  
-For loading the firmware automatically after the module is loaded, use
-the post-install command.  For example, add the following entry to
-/etc/modprobe.conf for miXart driver:
+For loading the firmware automatically after the module is loaded, use a
+install command.  For example, add the following entry to
+/etc/modprobe.d/mixart.conf for miXart driver:
 
 	install snd-mixart /sbin/modprobe --first-time -i snd-mixart && \
 			   /usr/bin/mixartloader
diff --git a/Documentation/sound/alsa/OSS-Emulation.txt b/Documentation/sound/alsa/OSS-Emulation.txt
index 022aaeb0e9dd..152ca2a3f1bd 100644
--- a/Documentation/sound/alsa/OSS-Emulation.txt
+++ b/Documentation/sound/alsa/OSS-Emulation.txt
@@ -19,7 +19,7 @@ the card number and the minor unit number.  Usually you don't have to
 define these aliases by yourself.
 
 Only necessary step for auto-loading of OSS modules is to define the
-card alias in /etc/modprobe.conf, such as
+card alias in /etc/modprobe.d/alsa.conf, such as
 
 	alias sound-slot-0 snd-emu10k1
 
diff --git a/Documentation/sound/oss/AudioExcelDSP16 b/Documentation/sound/oss/AudioExcelDSP16
index e0dc0641b480..ea8549faede9 100644
--- a/Documentation/sound/oss/AudioExcelDSP16
+++ b/Documentation/sound/oss/AudioExcelDSP16
@@ -41,7 +41,7 @@ mpu_base	I/O base address for activate MPU-401 mode
 		(0x300, 0x310, 0x320 or 0x330)
 mpu_irq		MPU-401 irq line (5, 7, 9, 10 or 0)
 
-The /etc/modprobe.conf will have lines like this:
+A configuration file in /etc/modprobe.d/ directory will have lines like this:
 
 options opl3 io=0x388
 options ad1848 io=0x530 irq=11 dma=3
@@ -51,11 +51,11 @@ Where the aedsp16 options are the options for this driver while opl3 and
 ad1848 are the corresponding options for the MSS and OPL3 modules.
 
 Loading MSS and OPL3 needs to pre load the aedsp16 module to set up correctly
-the sound card. Installation dependencies must be written in the modprobe.conf
-file:
+the sound card. Installation dependencies must be written in configuration
+files under /etc/modprobe.d/ directory:
 
-install ad1848 /sbin/modprobe aedsp16 && /sbin/modprobe -i ad1848
-install opl3 /sbin/modprobe aedsp16 && /sbin/modprobe -i opl3
+softdep ad1848 pre: aedsp16
+softdep opl3 pre: aedsp16
 
 Then you must load the sound modules stack in this order:
 sound -> aedsp16 -> [ ad1848, opl3 ]
diff --git a/Documentation/sound/oss/CMI8330 b/Documentation/sound/oss/CMI8330
index 9c439f1a6dba..8a5fd1611c6f 100644
--- a/Documentation/sound/oss/CMI8330
+++ b/Documentation/sound/oss/CMI8330
@@ -143,11 +143,10 @@ CONFIG_SOUND_MSS=m
 
 
 
-Alma Chao <elysian@ethereal.torsion.org> suggests the following /etc/modprobe.conf:
+Alma Chao <elysian@ethereal.torsion.org> suggests the following in
+a /etc/modprobe.d/*conf file:
 
 alias sound ad1848
 alias synth0 opl3
 options ad1848 io=0x530 irq=7 dma=0 soundpro=1
 options opl3 io=0x388
-
-	
diff --git a/Documentation/sound/oss/Introduction b/Documentation/sound/oss/Introduction
index 75d967ff9266..42da2d8fa372 100644
--- a/Documentation/sound/oss/Introduction
+++ b/Documentation/sound/oss/Introduction
@@ -167,8 +167,8 @@ in a file such as /root/soundon.sh.
 MODPROBE:
 =========
 
-If loading via modprobe, these common files are automatically loaded 
-when requested by modprobe.  For example, my /etc/modprobe.conf contains:
+If loading via modprobe, these common files are automatically loaded when
+requested by modprobe.  For example, my /etc/modprobe.d/oss.conf contains:
 
 alias sound sb 
 options sb io=0x240 irq=9 dma=3 dma16=5 mpu_io=0x300
@@ -228,7 +228,7 @@ http://www.opensound.com.  Before loading the commercial sound
 driver, you should do the following:
 
 1.  remove sound modules (detailed above)
-2.  remove the sound modules from /etc/modprobe.conf
+2.  remove the sound modules from /etc/modprobe.d/*.conf
 3.  move the sound modules from /lib/modules/<kernel>/misc
     (for example, I make a /lib/modules/<kernel>/misc/tmp
     directory and copy the sound module files to that 
@@ -265,7 +265,7 @@ twice, you need to do the following:
     sb.o could be copied (or symlinked) to sb1.o for the
     second SoundBlaster.
 
-2.  Make a second entry in /etc/modprobe.conf, for example,
+2.  Make a second entry in /etc/modprobe.d/*conf, for example,
     sound1 or sb1.  This second entry should refer to the
     new module names for example sb1, and should include
     the I/O, etc. for the second sound card.
@@ -369,7 +369,7 @@ There are several ways of configuring your sound:
 2)  On the command line when using insmod or in a bash script
     using command line calls to load sound.
 
-3)  In /etc/modprobe.conf when using modprobe.
+3)  In /etc/modprobe.d/*conf when using modprobe.
 
 4)  Via Red Hat's GPL'd /usr/sbin/sndconfig program (text based).
 
diff --git a/Documentation/sound/oss/Opti b/Documentation/sound/oss/Opti
index c15af3c07d46..4cd5d9ab3580 100644
--- a/Documentation/sound/oss/Opti
+++ b/Documentation/sound/oss/Opti
@@ -18,7 +18,7 @@ force the card into a mode in which it can be programmed.
 If you have another OS installed on your computer it is recommended
 that Linux and the other OS use the same resources.
 
-Also, it is recommended that resources specified in /etc/modprobe.conf
+Also, it is recommended that resources specified in /etc/modprobe.d/*.conf
 and resources specified in /etc/isapnp.conf agree.
 
 Compiling the sound driver
@@ -67,11 +67,7 @@ address is hard-coded into the driver.
 
 Using kmod and autoloading the sound driver
 -------------------------------------------
-Comment: as of linux-2.1.90 kmod is replacing kerneld.
-The config file '/etc/modprobe.conf' is used as before.
-
-This is the sound part of my /etc/modprobe.conf file.
-Following that I will explain each line.
+Config files in '/etc/modprobe.d/' are used as below:
 
 alias mixer0 mad16
 alias audio0 mad16
diff --git a/Documentation/sound/oss/PAS16 b/Documentation/sound/oss/PAS16
index 3dca4b75988e..5c27229eec8c 100644
--- a/Documentation/sound/oss/PAS16
+++ b/Documentation/sound/oss/PAS16
@@ -128,7 +128,7 @@ CONFIG_SOUND_YM3812
   You can then get OPL3 functionality by issuing the command:
   insmod opl3
   In addition, you must either add the following line to 
-  /etc/modprobe.conf:
+  /etc/modprobe.d/*.conf:
   options opl3 io=0x388
   or else add the following line to /etc/lilo.conf:
   opl3=0x388
@@ -158,5 +158,5 @@ following line would be appropriate:
 append="pas2=0x388,10,3,-1,0,-1,-1,-1 opl3=0x388"
 
 If sound is built totally modular, the above options may be 
-specified in /etc/modprobe.conf for pas2, sb and opl3
+specified in /etc/modprobe.d/*.conf for pas2, sb and opl3
 respectively. 
diff --git a/Documentation/sound/oss/README.modules b/Documentation/sound/oss/README.modules
index e691d74e1e5e..cdc039421a46 100644
--- a/Documentation/sound/oss/README.modules
+++ b/Documentation/sound/oss/README.modules
@@ -26,7 +26,7 @@ Note that it is no longer necessary or possible to configure sound in the
 drivers/sound dir. Now one simply configures and makes one's kernel and
 modules in the usual way.
 
- Then, add to your /etc/modprobe.conf something like:
+ Then, add to your /etc/modprobe.d/oss.conf something like:
 
 alias char-major-14-* sb
 install sb /sbin/modprobe -i sb && /sbin/modprobe adlib_card
@@ -36,7 +36,7 @@ options adlib_card io=0x388     # FM synthesizer
  Alternatively, if you have compiled in kernel level ISAPnP support:
 
 alias char-major-14 sb
-post-install sb /sbin/modprobe "-k" "adlib_card"
+softdep sb post: adlib_card
 options adlib_card io=0x388
 
   The effect of this is that the sound driver and all necessary bits and
@@ -66,12 +66,12 @@ args are expected.
  Note that at present there is no way to configure the io, irq and other
 parameters for the modular drivers as one does for the wired drivers.. One
 needs to pass the modules the necessary parameters as arguments, either
-with /etc/modprobe.conf or with command-line args to modprobe, e.g.
+with /etc/modprobe.d/*.conf or with command-line args to modprobe, e.g.
 
 modprobe sb io=0x220 irq=7 dma=1 dma16=5 mpu_io=0x330
 modprobe adlib_card io=0x388
 
- recommend using /etc/modprobe.conf.
+ recommend using /etc/modprobe.d/*.conf.
 
 Persistent DMA Buffers:
 
@@ -89,7 +89,7 @@ wasteful of RAM, but it guarantees that sound always works.
 
 To make the sound driver use persistent DMA buffers we need to pass the
 sound.o module a "dmabuf=1" command-line argument. This is normally done
-in /etc/modprobe.conf like so:
+in /etc/modprobe.d/*.conf files like so:
 
 options sound		dmabuf=1
 
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 312e3754e8c5..642f84495b29 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -241,9 +241,8 @@ command you are interested in.
 
 *  I have more questions, who can I ask?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-And I'll answer any questions about the registration system you got, also
-responding as soon as possible.
- -Crutcher
+Just ask them on the linux-kernel mailing list:
+	linux-kernel@vger.kernel.org
 
 *  Credits
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index 817df299ea07..4204eb01fd38 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -179,7 +179,8 @@ do:
 
 	modprobe usbcore autosuspend=5
 
-Equivalently, you could add to /etc/modprobe.conf a line saying:
+Equivalently, you could add to a configuration file in /etc/modprobe.d
+a line saying:
 
 	options usbcore autosuspend=5
 
diff --git a/Documentation/video4linux/CQcam.txt b/Documentation/video4linux/CQcam.txt
index 8977e7ce4dab..6e680fec1e9c 100644
--- a/Documentation/video4linux/CQcam.txt
+++ b/Documentation/video4linux/CQcam.txt
@@ -61,29 +61,19 @@ But that is my personal preference.
 2.2 Configuration
 
   The configuration requires module configuration and device
-configuration.  I like kmod or kerneld process with the
-/etc/modprobe.conf file so the modules can automatically load/unload as
-they are used.  The video devices could already exist, be generated
-using MAKEDEV, or need to be created.  The following sections detail
-these procedures.
+configuration.  The following sections detail these procedures.
 
 
 2.1 Module Configuration
 
   Using modules requires a bit of work to install and pass the
-parameters.  Understand that entries in /etc/modprobe.conf of:
+parameters.  Understand that entries in /etc/modprobe.d/*.conf of:
 
    alias parport_lowlevel parport_pc
    options parport_pc io=0x378 irq=none
    alias char-major-81 videodev
    alias char-major-81-0 c-qcam
 
-will cause the kmod/modprobe to do certain things.  If you are
-using kmod, then a request for a 'char-major-81-0' will cause
-the 'c-qcam' module to load.  If you have other video sources with
-modules, you might want to assign the different minor numbers to
-different modules.
-
 2.2 Device Configuration
 
   At this point, we need to ensure that the device files exist.
diff --git a/Documentation/video4linux/Zoran b/Documentation/video4linux/Zoran
index 9ed629d4874b..b5a911fd0602 100644
--- a/Documentation/video4linux/Zoran
+++ b/Documentation/video4linux/Zoran
@@ -255,7 +255,7 @@ Load zr36067.o. If it can't autodetect your card, use the card=X insmod
 option with X being the card number as given in the previous section.
 To have more than one card, use card=X1[,X2[,X3,[X4[..]]]]
 
-To automate this, add the following to your /etc/modprobe.conf:
+To automate this, add the following to your /etc/modprobe.d/zoran.conf:
 
 options zr36067 card=X1[,X2[,X3[,X4[..]]]]
 alias char-major-81-0 zr36067
diff --git a/Documentation/video4linux/bttv/Modules.conf b/Documentation/video4linux/bttv/Modules.conf
index 753f15956eb8..8f258faf18f1 100644
--- a/Documentation/video4linux/bttv/Modules.conf
+++ b/Documentation/video4linux/bttv/Modules.conf
@@ -1,4 +1,4 @@
-# For modern kernels (2.6 or above), this belongs in /etc/modprobe.conf
+# For modern kernels (2.6 or above), this belongs in /etc/modprobe.d/*.conf
 # For for 2.4 kernels or earlier, this belongs in /etc/modules.conf.
 
 # i2c
diff --git a/Documentation/video4linux/meye.txt b/Documentation/video4linux/meye.txt
index 34e2842c70ae..a051152ea99c 100644
--- a/Documentation/video4linux/meye.txt
+++ b/Documentation/video4linux/meye.txt
@@ -55,7 +55,7 @@ Module use:
 -----------
 
 In order to automatically load the meye module on use, you can put those lines
-in your /etc/modprobe.conf file:
+in your /etc/modprobe.d/meye.conf file:
 
 	alias char-major-81 videodev
 	alias char-major-81-0 meye
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index e1d94bf4056e..6386f8c0482e 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -95,7 +95,7 @@ described as 'basic' will be available.
 Capability: basic
 Architectures: all
 Type: system ioctl
-Parameters: none
+Parameters: machine type identifier (KVM_VM_*)
 Returns: a VM fd that can be used to control the new virtual machine.
 
 The new VM has no virtual cpus and no memory.  An mmap() of a VM fd
@@ -103,6 +103,11 @@ will access the virtual machine's physical address space; offset zero
 corresponds to guest physical address zero.  Use of mmap() on a VM fd
 is discouraged if userspace memory allocation (KVM_CAP_USER_MEMORY) is
 available.
+You most certainly want to use 0 as machine type.
+
+In order to create user controlled virtual machines on S390, check
+KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
+privileged user (CAP_SYS_ADMIN).
 
 4.3 KVM_GET_MSR_INDEX_LIST
 
@@ -213,6 +218,11 @@ allocation of vcpu ids.  For example, if userspace wants
 single-threaded guest vcpus, it should make all vcpu ids be a multiple
 of the number of vcpus per vcore.
 
+For virtual cpus that have been created with S390 user controlled virtual
+machines, the resulting vcpu fd can be memory mapped at page offset
+KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
+cpu's hardware control block.
+
 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
 
 Capability: basic
@@ -1159,6 +1169,14 @@ following flags are specified:
 
 /* Depends on KVM_CAP_IOMMU */
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
+/* The following two depend on KVM_CAP_PCI_2_3 */
+#define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
+#define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)
+
+If KVM_DEV_ASSIGN_PCI_2_3 is set, the kernel will manage legacy INTx interrupts
+via the PCI-2.3-compliant device-level mask, thus enable IRQ sharing with other
+assigned devices or host devices. KVM_DEV_ASSIGN_MASK_INTX specifies the
+guest's view on the INTx mask, see KVM_ASSIGN_SET_INTX_MASK for details.
 
 The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
 isolation of the device.  Usages not specifying this flag are deprecated.
@@ -1399,6 +1417,71 @@ The following flags are defined:
 If datamatch flag is set, the event will be signaled only if the written value
 to the registered address is equal to datamatch in struct kvm_ioeventfd.
 
+4.59 KVM_DIRTY_TLB
+
+Capability: KVM_CAP_SW_TLB
+Architectures: ppc
+Type: vcpu ioctl
+Parameters: struct kvm_dirty_tlb (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_dirty_tlb {
+	__u64 bitmap;
+	__u32 num_dirty;
+};
+
+This must be called whenever userspace has changed an entry in the shared
+TLB, prior to calling KVM_RUN on the associated vcpu.
+
+The "bitmap" field is the userspace address of an array.  This array
+consists of a number of bits, equal to the total number of TLB entries as
+determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
+nearest multiple of 64.
+
+Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
+array.
+
+The array is little-endian: the bit 0 is the least significant bit of the
+first byte, bit 8 is the least significant bit of the second byte, etc.
+This avoids any complications with differing word sizes.
+
+The "num_dirty" field is a performance hint for KVM to determine whether it
+should skip processing the bitmap and just invalidate everything.  It must
+be set to the number of set bits in the bitmap.
+
+4.60 KVM_ASSIGN_SET_INTX_MASK
+
+Capability: KVM_CAP_PCI_2_3
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_assigned_pci_dev (in)
+Returns: 0 on success, -1 on error
+
+Allows userspace to mask PCI INTx interrupts from the assigned device.  The
+kernel will not deliver INTx interrupts to the guest between setting and
+clearing of KVM_ASSIGN_SET_INTX_MASK via this interface.  This enables use of
+and emulation of PCI 2.3 INTx disable command register behavior.
+
+This may be used for both PCI 2.3 devices supporting INTx disable natively and
+older devices lacking this support. Userspace is responsible for emulating the
+read value of the INTx disable bit in the guest visible PCI command register.
+When modifying the INTx disable state, userspace should precede updating the
+physical device command register by calling this ioctl to inform the kernel of
+the new intended INTx mask state.
+
+Note that the kernel uses the device INTx disable bit to internally manage the
+device interrupt state for PCI 2.3 devices.  Reads of this register may
+therefore not match the expected value.  Writes should always use the guest
+intended INTx disable value rather than attempting to read-copy-update the
+current physical device state.  Races between user and kernel updates to the
+INTx disable bit are handled lazily in the kernel.  It's possible the device
+may generate unintended interrupts, but they will not be injected into the
+guest.
+
+See KVM_ASSIGN_DEV_IRQ for the data structure.  The target device is specified
+by assigned_dev_id.  In the flags field, only KVM_DEV_ASSIGN_MASK_INTX is
+evaluated.
+
 4.62 KVM_CREATE_SPAPR_TCE
 
 Capability: KVM_CAP_SPAPR_TCE
@@ -1491,6 +1574,101 @@ following algorithm:
 Some guests configure the LINT1 NMI input to cause a panic, aiding in
 debugging.
 
+4.65 KVM_S390_UCAS_MAP
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_ucas_mapping (in)
+Returns: 0 in case of success
+
+The parameter is defined like this:
+	struct kvm_s390_ucas_mapping {
+		__u64 user_addr;
+		__u64 vcpu_addr;
+		__u64 length;
+	};
+
+This ioctl maps the memory at "user_addr" with the length "length" to
+the vcpu's address space starting at "vcpu_addr". All parameters need to
+be alligned by 1 megabyte.
+
+4.66 KVM_S390_UCAS_UNMAP
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_ucas_mapping (in)
+Returns: 0 in case of success
+
+The parameter is defined like this:
+	struct kvm_s390_ucas_mapping {
+		__u64 user_addr;
+		__u64 vcpu_addr;
+		__u64 length;
+	};
+
+This ioctl unmaps the memory in the vcpu's address space starting at
+"vcpu_addr" with the length "length". The field "user_addr" is ignored.
+All parameters need to be alligned by 1 megabyte.
+
+4.67 KVM_S390_VCPU_FAULT
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: vcpu absolute address (in)
+Returns: 0 in case of success
+
+This call creates a page table entry on the virtual cpu's address space
+(for user controlled virtual machines) or the virtual machine's address
+space (for regular virtual machines). This only works for minor faults,
+thus it's recommended to access subject memory page via the user page
+table upfront. This is useful to handle validity intercepts for user
+controlled virtual machines to fault in the virtual cpu's lowcore pages
+prior to calling the KVM_RUN ioctl.
+
+4.68 KVM_SET_ONE_REG
+
+Capability: KVM_CAP_ONE_REG
+Architectures: all
+Type: vcpu ioctl
+Parameters: struct kvm_one_reg (in)
+Returns: 0 on success, negative value on failure
+
+struct kvm_one_reg {
+       __u64 id;
+       __u64 addr;
+};
+
+Using this ioctl, a single vcpu register can be set to a specific value
+defined by user space with the passed in struct kvm_one_reg, where id
+refers to the register identifier as described below and addr is a pointer
+to a variable with the respective size. There can be architecture agnostic
+and architecture specific registers. Each have their own range of operation
+and their own constants and width. To keep track of the implemented
+registers, find a list below:
+
+  Arch  |       Register        | Width (bits)
+        |                       |
+  PPC   | KVM_REG_PPC_HIOR      | 64
+
+4.69 KVM_GET_ONE_REG
+
+Capability: KVM_CAP_ONE_REG
+Architectures: all
+Type: vcpu ioctl
+Parameters: struct kvm_one_reg (in and out)
+Returns: 0 on success, negative value on failure
+
+This ioctl allows to receive the value of a single register implemented
+in a vcpu. The register to read is indicated by the "id" field of the
+kvm_one_reg struct passed in. On success, the register value can be found
+at the memory location pointed to by "addr".
+
+The list of registers accessible using this interface is identical to the
+list in 4.64.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
@@ -1651,6 +1829,20 @@ s390 specific.
 
 s390 specific.
 
+		/* KVM_EXIT_S390_UCONTROL */
+		struct {
+			__u64 trans_exc_code;
+			__u32 pgm_code;
+		} s390_ucontrol;
+
+s390 specific. A page fault has occurred for a user controlled virtual
+machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
+resolved by the kernel.
+The program code and the translation exception code that were placed
+in the cpu's lowcore are presented here as defined by the z Architecture
+Principles of Operation Book in the Chapter for Dynamic Address Translation
+(DAT)
+
 		/* KVM_EXIT_DCR */
 		struct {
 			__u32 dcrn;
@@ -1693,6 +1885,29 @@ developer registration required to access it).
 		/* Fix the size of the union. */
 		char padding[256];
 	};
+
+	/*
+	 * shared registers between kvm and userspace.
+	 * kvm_valid_regs specifies the register classes set by the host
+	 * kvm_dirty_regs specified the register classes dirtied by userspace
+	 * struct kvm_sync_regs is architecture specific, as well as the
+	 * bits for kvm_valid_regs and kvm_dirty_regs
+	 */
+	__u64 kvm_valid_regs;
+	__u64 kvm_dirty_regs;
+	union {
+		struct kvm_sync_regs regs;
+		char padding[1024];
+	} s;
+
+If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
+certain guest registers without having to call SET/GET_*REGS. Thus we can
+avoid some system call overhead if userspace has to handle the exit.
+Userspace can query the validity of the structure by checking
+kvm_valid_regs for specific bits. These bits are architecture specific
+and usually define the validity of a groups of registers. (e.g. one bit
+ for general purpose registers)
+
 };
 
 6. Capabilities that can be enabled
@@ -1741,3 +1956,45 @@ HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
 HTAB invisible to the guest.
 
 When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
+
+6.3 KVM_CAP_SW_TLB
+
+Architectures: ppc
+Parameters: args[0] is the address of a struct kvm_config_tlb
+Returns: 0 on success; -1 on error
+
+struct kvm_config_tlb {
+	__u64 params;
+	__u64 array;
+	__u32 mmu_type;
+	__u32 array_len;
+};
+
+Configures the virtual CPU's TLB array, establishing a shared memory area
+between userspace and KVM.  The "params" and "array" fields are userspace
+addresses of mmu-type-specific data structures.  The "array_len" field is an
+safety mechanism, and should be set to the size in bytes of the memory that
+userspace has reserved for the array.  It must be at least the size dictated
+by "mmu_type" and "params".
+
+While KVM_RUN is active, the shared region is under control of KVM.  Its
+contents are undefined, and any modification by userspace results in
+boundedly undefined behavior.
+
+On return from KVM_RUN, the shared region will reflect the current state of
+the guest's TLB.  If userspace makes any changes, it must call KVM_DIRTY_TLB
+to tell KVM which entries have been changed, prior to calling KVM_RUN again
+on this vcpu.
+
+For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+ - The "params" field is of type "struct kvm_book3e_206_tlb_params".
+ - The "array" field points to an array of type "struct
+   kvm_book3e_206_tlb_entry".
+ - The array consists of all entries in the first TLB, followed by all
+   entries in the second TLB.
+ - Within a TLB, entries are ordered first by increasing set number.  Within a
+   set, entries are ordered by way (increasing ESEL).
+ - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
+   where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
+ - The tsize field of mas1 shall be set to 4K on TLB0, even though the
+   hardware ignores this value for TLB0.
diff --git a/Documentation/virtual/kvm/ppc-pv.txt b/Documentation/virtual/kvm/ppc-pv.txt
index 2b7ce190cde4..6e7c37050930 100644
--- a/Documentation/virtual/kvm/ppc-pv.txt
+++ b/Documentation/virtual/kvm/ppc-pv.txt
@@ -81,28 +81,8 @@ additional registers to the magic page. If you add fields to the magic page,
 also define a new hypercall feature to indicate that the host can give you more
 registers. Only if the host supports the additional features, make use of them.
 
-The magic page has the following layout as described in
-arch/powerpc/include/asm/kvm_para.h:
-
-struct kvm_vcpu_arch_shared {
-	__u64 scratch1;
-	__u64 scratch2;
-	__u64 scratch3;
-	__u64 critical;		/* Guest may not get interrupts if == r1 */
-	__u64 sprg0;
-	__u64 sprg1;
-	__u64 sprg2;
-	__u64 sprg3;
-	__u64 srr0;
-	__u64 srr1;
-	__u64 dar;
-	__u64 msr;
-	__u32 dsisr;
-	__u32 int_pending;	/* Tells the guest if we have an interrupt */
-};
-
-Additions to the page must only occur at the end. Struct fields are always 32
-or 64 bit aligned, depending on them being 32 or 64 bit wide respectively.
+The magic page layout is described by struct kvm_vcpu_arch_shared
+in arch/powerpc/include/asm/kvm_para.h.
 
 Magic page features
 ===================
diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile
deleted file mode 100644
index 3fa4d0668864..000000000000
--- a/Documentation/vm/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# kbuild trick to avoid linker error. Can be omitted if a module is built.
-obj- := dummy.o
-
-# List of programs to build
-hostprogs-y := page-types hugepage-mmap hugepage-shm map_hugetlb
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
diff --git a/Documentation/watchdog/00-INDEX b/Documentation/watchdog/00-INDEX
deleted file mode 100644
index fc9082a1477a..000000000000
--- a/Documentation/watchdog/00-INDEX
+++ /dev/null
@@ -1,19 +0,0 @@
-00-INDEX
-	- this file.
-convert_drivers_to_kernel_api.txt
-	- how-to for converting old watchdog drivers to the new kernel API.
-hpwdt.txt
-	- information on the HP iLO2 NMI watchdog
-pcwd-watchdog.txt
-	- documentation for Berkshire Products PC Watchdog ISA cards.
-src/
-	- directory holding watchdog related example programs.
-watchdog-api.txt
-	- description of the Linux Watchdog driver API.
-watchdog-kernel-api.txt
-	- description of the Linux WatchDog Timer Driver Core kernel API.
-watchdog-parameters.txt
-	- information on driver parameters (for drivers other than
-	  the ones that have driver-specific files here)
-wdt.txt
-	- description of the Watchdog Timer Interfaces for Linux.
diff --git a/Documentation/watchdog/convert_drivers_to_kernel_api.txt b/Documentation/watchdog/convert_drivers_to_kernel_api.txt
index be8119bb15d2..271b8850dde7 100644
--- a/Documentation/watchdog/convert_drivers_to_kernel_api.txt
+++ b/Documentation/watchdog/convert_drivers_to_kernel_api.txt
@@ -59,6 +59,10 @@ Here is a overview of the functions and probably needed actions:
 	WDIOC_GETTIMEOUT:
 		No preparations needed
 
+	WDIOC_GETTIMELEFT:
+		It needs get_timeleft() callback to be defined. Otherwise it
+		will return EOPNOTSUPP
+
   Other IOCTLs can be served using the ioctl-callback. Note that this is mainly
   intended for porting old drivers; new drivers should not invent private IOCTLs.
   Private IOCTLs are processed first. When the callback returns with
diff --git a/Documentation/watchdog/watchdog-kernel-api.txt b/Documentation/watchdog/watchdog-kernel-api.txt
index 9e162465b0cf..227f6cd0e5fa 100644
--- a/Documentation/watchdog/watchdog-kernel-api.txt
+++ b/Documentation/watchdog/watchdog-kernel-api.txt
@@ -1,6 +1,6 @@
 The Linux WatchDog Timer Driver Core kernel API.
 ===============================================
-Last reviewed: 29-Nov-2011
+Last reviewed: 16-Mar-2012
 
 Wim Van Sebroeck <wim@iguana.be>
 
@@ -77,6 +77,7 @@ struct watchdog_ops {
 	int (*ping)(struct watchdog_device *);
 	unsigned int (*status)(struct watchdog_device *);
 	int (*set_timeout)(struct watchdog_device *, unsigned int);
+	unsigned int (*get_timeleft)(struct watchdog_device *);
 	long (*ioctl)(struct watchdog_device *, unsigned int, unsigned long);
 };
 
@@ -117,11 +118,13 @@ they are supported. These optional routines/operations are:
   status of the device is reported with watchdog WDIOF_* status flags/bits.
 * set_timeout: this routine checks and changes the timeout of the watchdog
   timer device. It returns 0 on success, -EINVAL for "parameter out of range"
-  and -EIO for "could not write value to the watchdog". On success the timeout
-  value of the watchdog_device will be changed to the value that was just used
-  to re-program the watchdog timer device.
+  and -EIO for "could not write value to the watchdog". On success this
+  routine should set the timeout value of the watchdog_device to the
+  achieved timeout value (which may be different from the requested one
+  because the watchdog does not necessarily has a 1 second resolution).
   (Note: the WDIOF_SETTIMEOUT needs to be set in the options field of the
   watchdog's info structure).
+* get_timeleft: this routines returns the time that's left before a reset.
 * ioctl: if this routine is present then it will be called first before we do
   our own internal ioctl call handling. This routine should return -ENOIOCTLCMD
   if a command is not supported. The parameters that are passed to the ioctl
diff --git a/MAINTAINERS b/MAINTAINERS
index 5ba74396af98..f7c39b88a503 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1939,7 +1939,7 @@ F:	drivers/connector/
 
 CONTROL GROUPS (CGROUPS)
 M:	Tejun Heo <tj@kernel.org>
-M:	Li Zefan <lizf@cn.fujitsu.com>
+M:	Li Zefan <lizefan@huawei.com>
 L:	containers@lists.linux-foundation.org
 L:	cgroups@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
@@ -2224,13 +2224,16 @@ W:	http://lanana.org/docs/device-list/index.html
 S:	Maintained
 
 DEVICE-MAPPER  (LVM)
-P:	Alasdair Kergon
+M:	Alasdair Kergon <agk@redhat.com>
+M:	dm-devel@redhat.com
 L:	dm-devel@redhat.com
 W:	http://sources.redhat.com/dm
 Q:	http://patchwork.kernel.org/project/dm-devel/list/
+T:	quilt http://people.redhat.com/agk/patches/linux/editing/
 S:	Maintained
 F:	Documentation/device-mapper/
 F:	drivers/md/dm*
+F:	drivers/md/persistent-data/
 F:	include/linux/device-mapper.h
 F:	include/linux/dm-*.h
 
@@ -4300,6 +4303,13 @@ W:	http://www.kernel.org/doc/man-pages
 L:	linux-man@vger.kernel.org
 S:	Maintained
 
+MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
+M:	Mirko Lindner <mlindner@marvell.com>
+M:	Stephen Hemminger <shemminger@vyatta.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/marvell/sk*
+
 MARVELL LIBERTAS WIRELESS DRIVER
 M:	Dan Williams <dcbw@redhat.com>
 L:	libertas-dev@lists.infradead.org
@@ -4330,12 +4340,6 @@ M:	Nicolas Pitre <nico@fluxnic.net>
 S:	Odd Fixes
 F:	drivers/mmc/host/mvsdio.*
 
-MARVELL YUKON / SYSKONNECT DRIVER
-M:	Mirko Lindner <mlindner@syskonnect.de>
-M:	Ralph Roesler <rroesler@syskonnect.de>
-W:	http://www.syskonnect.com
-S:	Supported
-
 MATROX FRAMEBUFFER DRIVER
 L:	linux-fbdev@vger.kernel.org
 S:	Orphan
@@ -5171,7 +5175,7 @@ F:	kernel/delayacct.c
 PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
 M:	Paul Mackerras <paulus@samba.org>
-M:	Ingo Molnar <mingo@elte.hu>
+M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Supported
@@ -5628,7 +5632,7 @@ M:	Ohad Ben-Cohen <ohad@wizery.com>
 S:	Maintained
 F:	drivers/remoteproc/
 F:	Documentation/remoteproc.txt
-F:	include/linux/remoteproc.txt
+F:	include/linux/remoteproc.h
 
 RFKILL
 M:	Johannes Berg <johannes@sipsolutions.net>
@@ -5762,6 +5766,12 @@ F:	drivers/media/common/saa7146*
 F:	drivers/media/video/*7146*
 F:	include/media/*7146*
 
+SAMSUNG LAPTOP DRIVER
+M:	Corentin Chary <corentincj@iksaif.net>
+L:	platform-driver-x86@vger.kernel.org
+S:	Maintained
+F:	drivers/platform/x86/samsung-laptop.c
+
 SAMSUNG AUDIO (ASoC) DRIVERS
 M:	Sangbeom Kim <sbkim73@samsung.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -5813,7 +5823,7 @@ S:	Maintained
 F:	drivers/watchdog/sc1200wdt.c
 
 SCHEDULER
-M:	Ingo Molnar <mingo@elte.hu>
+M:	Ingo Molnar <mingo@redhat.com>
 M:	Peter Zijlstra <peterz@infradead.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core
 S:	Maintained
@@ -6101,12 +6111,6 @@ W:	http://www.winischhofer.at/linuxsisusbvga.shtml
 S:	Maintained
 F:	drivers/usb/misc/sisusbvga/
 
-SKGE, SKY2 10/100/1000 GIGABIT ETHERNET DRIVERS
-M:	Stephen Hemminger <shemminger@vyatta.com>
-L:	netdev@vger.kernel.org
-S:	Maintained
-F:	drivers/net/ethernet/marvell/sk*
-
 SLAB ALLOCATOR
 M:	Christoph Lameter <cl@linux-foundation.org>
 M:	Pekka Enberg <penberg@kernel.org>
@@ -6272,6 +6276,15 @@ F:	drivers/tty/serial/sunsu.c
 F:	drivers/tty/serial/sunzilog.c
 F:	drivers/tty/serial/sunzilog.h
 
+SPARSE CHECKER
+M:	"Christopher Li" <sparse@chrisli.org>
+L:	linux-sparse@vger.kernel.org
+W:	https://sparse.wiki.kernel.org/
+T:	git git://git.kernel.org/pub/scm/devel/sparse/sparse.git
+T:	git git://git.kernel.org/pub/scm/devel/sparse/chrisl/sparse.git
+S:	Maintained
+F:	include/linux/compiler.h
+
 SPEAR PLATFORM SUPPORT
 M:	Viresh Kumar <viresh.kumar@st.com>
 L:	spear-devel@list.st.com
diff --git a/Makefile b/Makefile
index 1932984478c1..5e637c23974e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
-PATCHLEVEL = 3
+PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Saber-toothed Squirrel
 
 # *DOCUMENTATION*
@@ -1170,7 +1170,7 @@ MRPROPER_FILES += .config .config.old .version .old_version             \
 #
 clean: rm-dirs  := $(CLEAN_DIRS)
 clean: rm-files := $(CLEAN_FILES)
-clean-dirs      := $(addprefix _clean_, . $(vmlinux-alldirs) Documentation)
+clean-dirs      := $(addprefix _clean_, . $(vmlinux-alldirs) Documentation samples)
 
 PHONY += $(clean-dirs) clean archclean
 $(clean-dirs):
diff --git a/arch/Kconfig b/arch/Kconfig
index a6f14f622d13..684eb5af439d 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -213,4 +213,7 @@ config HAVE_CMPXCHG_LOCAL
 config HAVE_CMPXCHG_DOUBLE
 	bool
 
+config ARCH_WANT_OLD_COMPAT_IPC
+	bool
+
 source "kernel/gcov/Kconfig"
diff --git a/arch/alpha/boot/bootp.c b/arch/alpha/boot/bootp.c
index be61670d4096..2a542a506557 100644
--- a/arch/alpha/boot/bootp.c
+++ b/arch/alpha/boot/bootp.c
@@ -13,7 +13,6 @@
 #include <generated/utsrelease.h>
 #include <linux/mm.h>
 
-#include <asm/system.h>
 #include <asm/console.h>
 #include <asm/hwrpb.h>
 #include <asm/pgtable.h>
diff --git a/arch/alpha/boot/bootpz.c b/arch/alpha/boot/bootpz.c
index c98865f21423..d6ad191698da 100644
--- a/arch/alpha/boot/bootpz.c
+++ b/arch/alpha/boot/bootpz.c
@@ -15,7 +15,6 @@
 #include <generated/utsrelease.h>
 #include <linux/mm.h>
 
-#include <asm/system.h>
 #include <asm/console.h>
 #include <asm/hwrpb.h>
 #include <asm/pgtable.h>
diff --git a/arch/alpha/boot/head.S b/arch/alpha/boot/head.S
index f3d98089b3dc..b06812bcac83 100644
--- a/arch/alpha/boot/head.S
+++ b/arch/alpha/boot/head.S
@@ -4,7 +4,6 @@
  * initial bootloader stuff..
  */
 
-#include <asm/system.h>
 
 	.set noreorder
 	.globl	__start
diff --git a/arch/alpha/boot/main.c b/arch/alpha/boot/main.c
index ded57d9a80e1..3baf2d1e908d 100644
--- a/arch/alpha/boot/main.c
+++ b/arch/alpha/boot/main.c
@@ -11,7 +11,6 @@
 #include <generated/utsrelease.h>
 #include <linux/mm.h>
 
-#include <asm/system.h>
 #include <asm/console.h>
 #include <asm/hwrpb.h>
 #include <asm/pgtable.h>
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 640f909ddd41..f62251e82ffa 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -3,7 +3,6 @@
 
 #include <linux/types.h>
 #include <asm/barrier.h>
-#include <asm/system.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -169,6 +168,73 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 	return result;
 }
 
+/*
+ * Atomic exchange routines.
+ */
+
+#define __ASM__MB
+#define ____xchg(type, args...)		__xchg ## type ## _local(args)
+#define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
+#include <asm/xchg.h>
+
+#define xchg_local(ptr,x)						\
+  ({									\
+     __typeof__(*(ptr)) _x_ = (x);					\
+     (__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_,	\
+				       sizeof(*(ptr)));			\
+  })
+
+#define cmpxchg_local(ptr, o, n)					\
+  ({									\
+     __typeof__(*(ptr)) _o_ = (o);					\
+     __typeof__(*(ptr)) _n_ = (n);					\
+     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	\
+					  (unsigned long)_n_,		\
+					  sizeof(*(ptr)));		\
+  })
+
+#define cmpxchg64_local(ptr, o, n)					\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+  })
+
+#ifdef CONFIG_SMP
+#undef __ASM__MB
+#define __ASM__MB	"\tmb\n"
+#endif
+#undef ____xchg
+#undef ____cmpxchg
+#define ____xchg(type, args...)		__xchg ##type(args)
+#define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
+#include <asm/xchg.h>
+
+#define xchg(ptr,x)							\
+  ({									\
+     __typeof__(*(ptr)) _x_ = (x);					\
+     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_,		\
+				 sizeof(*(ptr)));			\
+  })
+
+#define cmpxchg(ptr, o, n)						\
+  ({									\
+     __typeof__(*(ptr)) _o_ = (o);					\
+     __typeof__(*(ptr)) _n_ = (n);					\
+     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		\
+				    (unsigned long)_n_,	sizeof(*(ptr)));\
+  })
+
+#define cmpxchg64(ptr, o, n)						\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg((ptr), (o), (n));					\
+  })
+
+#undef __ASM__MB
+#undef ____cmpxchg
+
+#define __HAVE_ARCH_CMPXCHG 1
+
 #define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
diff --git a/arch/alpha/include/asm/auxvec.h b/arch/alpha/include/asm/auxvec.h
index e96fe880e310..a3a579dfdb4d 100644
--- a/arch/alpha/include/asm/auxvec.h
+++ b/arch/alpha/include/asm/auxvec.h
@@ -21,4 +21,6 @@
 #define AT_L2_CACHESHAPE	36
 #define AT_L3_CACHESHAPE	37
 
+#define AT_VECTOR_SIZE_ARCH 4 /* entries in ARCH_DLINFO */
+
 #endif /* __ASM_ALPHA_AUXVEC_H */
diff --git a/arch/alpha/include/asm/core_lca.h b/arch/alpha/include/asm/core_lca.h
index f7cb4b460954..8ee6c516279c 100644
--- a/arch/alpha/include/asm/core_lca.h
+++ b/arch/alpha/include/asm/core_lca.h
@@ -1,8 +1,8 @@
 #ifndef __ALPHA_LCA__H__
 #define __ALPHA_LCA__H__
 
-#include <asm/system.h>
 #include <asm/compiler.h>
+#include <asm/mce.h>
 
 /*
  * Low Cost Alpha (LCA) definitions (these apply to 21066 and 21068,
diff --git a/arch/alpha/include/asm/core_mcpcia.h b/arch/alpha/include/asm/core_mcpcia.h
index 9f67a056b461..ad44bef29fba 100644
--- a/arch/alpha/include/asm/core_mcpcia.h
+++ b/arch/alpha/include/asm/core_mcpcia.h
@@ -7,6 +7,7 @@
 
 #include <linux/types.h>
 #include <asm/compiler.h>
+#include <asm/mce.h>
 
 /*
  * MCPCIA is the internal name for a core logic chipset which provides
diff --git a/arch/alpha/include/asm/core_t2.h b/arch/alpha/include/asm/core_t2.h
index 91b46801b290..ade9d92e68b4 100644
--- a/arch/alpha/include/asm/core_t2.h
+++ b/arch/alpha/include/asm/core_t2.h
@@ -7,7 +7,6 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <asm/compiler.h>
-#include <asm/system.h>
 
 /*
  * T2 is the internal name for the core logic chipset which provides
diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h
index 4567aca6fdd6..dfa32f061320 100644
--- a/arch/alpha/include/asm/dma-mapping.h
+++ b/arch/alpha/include/asm/dma-mapping.h
@@ -12,16 +12,22 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 
 #include <asm-generic/dma-mapping-common.h>
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t gfp)
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t gfp,
+				    struct dma_attrs *attrs)
 {
-	return get_dma_ops(dev)->alloc_coherent(dev, size, dma_handle, gfp);
+	return get_dma_ops(dev)->alloc(dev, size, dma_handle, gfp, attrs);
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
-	get_dma_ops(dev)->free_coherent(dev, size, vaddr, dma_handle);
+	get_dma_ops(dev)->free(dev, size, vaddr, dma_handle, attrs);
 }
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/alpha/include/asm/elf.h b/arch/alpha/include/asm/elf.h
index da5449e22175..968d9991f5ee 100644
--- a/arch/alpha/include/asm/elf.h
+++ b/arch/alpha/include/asm/elf.h
@@ -2,6 +2,7 @@
 #define __ASM_ALPHA_ELF_H
 
 #include <asm/auxvec.h>
+#include <asm/special_insns.h>
 
 /* Special values for the st_other field in the symbol table.  */
 
diff --git a/arch/alpha/include/asm/exec.h b/arch/alpha/include/asm/exec.h
new file mode 100644
index 000000000000..4a5a41f30779
--- /dev/null
+++ b/arch/alpha/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef __ALPHA_EXEC_H
+#define __ALPHA_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __ALPHA_EXEC_H */
diff --git a/arch/alpha/include/asm/fpu.h b/arch/alpha/include/asm/fpu.h
index ecb17a72acc3..db00f7885faa 100644
--- a/arch/alpha/include/asm/fpu.h
+++ b/arch/alpha/include/asm/fpu.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_ALPHA_FPU_H
 #define __ASM_ALPHA_FPU_H
 
+#include <asm/special_insns.h>
+
 /*
  * Alpha floating-point control register defines:
  */
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index 56ff96501350..7a3d38d5ed6b 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -6,7 +6,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <asm/compiler.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/machvec.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/include/asm/irqflags.h b/arch/alpha/include/asm/irqflags.h
index 299bbc7e9d71..ffb1726484af 100644
--- a/arch/alpha/include/asm/irqflags.h
+++ b/arch/alpha/include/asm/irqflags.h
@@ -1,7 +1,7 @@
 #ifndef __ALPHA_IRQFLAGS_H
 #define __ALPHA_IRQFLAGS_H
 
-#include <asm/system.h>
+#include <asm/pal.h>
 
 #define IPL_MIN		0
 #define IPL_SW0		1
diff --git a/arch/alpha/include/asm/mce.h b/arch/alpha/include/asm/mce.h
new file mode 100644
index 000000000000..660285b9aca8
--- /dev/null
+++ b/arch/alpha/include/asm/mce.h
@@ -0,0 +1,83 @@
+#ifndef __ALPHA_MCE_H
+#define __ALPHA_MCE_H
+
+/*
+ * This is the logout header that should be common to all platforms
+ * (assuming they are running OSF/1 PALcode, I guess).
+ */
+struct el_common {
+	unsigned int	size;		/* size in bytes of logout area */
+	unsigned int	sbz1	: 30;	/* should be zero */
+	unsigned int	err2	:  1;	/* second error */
+	unsigned int	retry	:  1;	/* retry flag */
+	unsigned int	proc_offset;	/* processor-specific offset */
+	unsigned int	sys_offset;	/* system-specific offset */
+	unsigned int	code;		/* machine check code */
+	unsigned int	frame_rev;	/* frame revision */
+};
+
+/* Machine Check Frame for uncorrectable errors (Large format)
+ *      --- This is used to log uncorrectable errors such as
+ *          double bit ECC errors.
+ *      --- These errors are detected by both processor and systems.
+ */
+struct el_common_EV5_uncorrectable_mcheck {
+        unsigned long   shadow[8];        /* Shadow reg. 8-14, 25           */
+        unsigned long   paltemp[24];      /* PAL TEMP REGS.                 */
+        unsigned long   exc_addr;         /* Address of excepting instruction*/
+        unsigned long   exc_sum;          /* Summary of arithmetic traps.   */
+        unsigned long   exc_mask;         /* Exception mask (from exc_sum). */
+        unsigned long   pal_base;         /* Base address for PALcode.      */
+        unsigned long   isr;              /* Interrupt Status Reg.          */
+        unsigned long   icsr;             /* CURRENT SETUP OF EV5 IBOX      */
+        unsigned long   ic_perr_stat;     /* I-CACHE Reg. <11> set Data parity
+                                                         <12> set TAG parity*/
+        unsigned long   dc_perr_stat;     /* D-CACHE error Reg. Bits set to 1:
+                                                     <2> Data error in bank 0
+                                                     <3> Data error in bank 1
+                                                     <4> Tag error in bank 0
+                                                     <5> Tag error in bank 1 */
+        unsigned long   va;               /* Effective VA of fault or miss. */
+        unsigned long   mm_stat;          /* Holds the reason for D-stream 
+                                             fault or D-cache parity errors */
+        unsigned long   sc_addr;          /* Address that was being accessed
+                                             when EV5 detected Secondary cache
+                                             failure.                 */
+        unsigned long   sc_stat;          /* Helps determine if the error was
+                                             TAG/Data parity(Secondary Cache)*/
+        unsigned long   bc_tag_addr;      /* Contents of EV5 BC_TAG_ADDR    */
+        unsigned long   ei_addr;          /* Physical address of any transfer
+                                             that is logged in EV5 EI_STAT */
+        unsigned long   fill_syndrome;    /* For correcting ECC errors.     */
+        unsigned long   ei_stat;          /* Helps identify reason of any 
+                                             processor uncorrectable error
+                                             at its external interface.     */
+        unsigned long   ld_lock;          /* Contents of EV5 LD_LOCK register*/
+};
+
+struct el_common_EV6_mcheck {
+	unsigned int FrameSize;		/* Bytes, including this field */
+	unsigned int FrameFlags;	/* <31> = Retry, <30> = Second Error */
+	unsigned int CpuOffset;		/* Offset to CPU-specific info */
+	unsigned int SystemOffset;	/* Offset to system-specific info */
+	unsigned int MCHK_Code;
+	unsigned int MCHK_Frame_Rev;
+	unsigned long I_STAT;		/* EV6 Internal Processor Registers */
+	unsigned long DC_STAT;		/* (See the 21264 Spec) */
+	unsigned long C_ADDR;
+	unsigned long DC1_SYNDROME;
+	unsigned long DC0_SYNDROME;
+	unsigned long C_STAT;
+	unsigned long C_STS;
+	unsigned long MM_STAT;
+	unsigned long EXC_ADDR;
+	unsigned long IER_CM;
+	unsigned long ISUM;
+	unsigned long RESERVED0;
+	unsigned long PAL_BASE;
+	unsigned long I_CTL;
+	unsigned long PCTX;
+};
+
+
+#endif /* __ALPHA_MCE_H */
diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h
index 86c08a02d239..4c51c05333c6 100644
--- a/arch/alpha/include/asm/mmu_context.h
+++ b/arch/alpha/include/asm/mmu_context.h
@@ -7,7 +7,6 @@
  * Copyright (C) 1996, Linus Torvalds
  */
 
-#include <asm/system.h>
 #include <asm/machvec.h>
 #include <asm/compiler.h>
 #include <asm-generic/mm_hooks.h>
diff --git a/arch/alpha/include/asm/pal.h b/arch/alpha/include/asm/pal.h
index 9b4ba0d6f00b..6699ee583429 100644
--- a/arch/alpha/include/asm/pal.h
+++ b/arch/alpha/include/asm/pal.h
@@ -48,4 +48,116 @@
 #define PAL_retsys	61
 #define PAL_rti		63
 
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+extern void halt(void) __attribute__((noreturn));
+#define __halt() __asm__ __volatile__ ("call_pal %0 #halt" : : "i" (PAL_halt))
+
+#define imb() \
+__asm__ __volatile__ ("call_pal %0 #imb" : : "i" (PAL_imb) : "memory")
+
+#define draina() \
+__asm__ __volatile__ ("call_pal %0 #draina" : : "i" (PAL_draina) : "memory")
+
+#define __CALL_PAL_R0(NAME, TYPE)				\
+extern inline TYPE NAME(void)					\
+{								\
+	register TYPE __r0 __asm__("$0");			\
+	__asm__ __volatile__(					\
+		"call_pal %1 # " #NAME				\
+		:"=r" (__r0)					\
+		:"i" (PAL_ ## NAME)				\
+		:"$1", "$16", "$22", "$23", "$24", "$25");	\
+	return __r0;						\
+}
+
+#define __CALL_PAL_W1(NAME, TYPE0)				\
+extern inline void NAME(TYPE0 arg0)				\
+{								\
+	register TYPE0 __r16 __asm__("$16") = arg0;		\
+	__asm__ __volatile__(					\
+		"call_pal %1 # "#NAME				\
+		: "=r"(__r16)					\
+		: "i"(PAL_ ## NAME), "0"(__r16)			\
+		: "$1", "$22", "$23", "$24", "$25");		\
+}
+
+#define __CALL_PAL_W2(NAME, TYPE0, TYPE1)			\
+extern inline void NAME(TYPE0 arg0, TYPE1 arg1)			\
+{								\
+	register TYPE0 __r16 __asm__("$16") = arg0;		\
+	register TYPE1 __r17 __asm__("$17") = arg1;		\
+	__asm__ __volatile__(					\
+		"call_pal %2 # "#NAME				\
+		: "=r"(__r16), "=r"(__r17)			\
+		: "i"(PAL_ ## NAME), "0"(__r16), "1"(__r17)	\
+		: "$1", "$22", "$23", "$24", "$25");		\
+}
+
+#define __CALL_PAL_RW1(NAME, RTYPE, TYPE0)			\
+extern inline RTYPE NAME(TYPE0 arg0)				\
+{								\
+	register RTYPE __r0 __asm__("$0");			\
+	register TYPE0 __r16 __asm__("$16") = arg0;		\
+	__asm__ __volatile__(					\
+		"call_pal %2 # "#NAME				\
+		: "=r"(__r16), "=r"(__r0)			\
+		: "i"(PAL_ ## NAME), "0"(__r16)			\
+		: "$1", "$22", "$23", "$24", "$25");		\
+	return __r0;						\
+}
+
+#define __CALL_PAL_RW2(NAME, RTYPE, TYPE0, TYPE1)		\
+extern inline RTYPE NAME(TYPE0 arg0, TYPE1 arg1)		\
+{								\
+	register RTYPE __r0 __asm__("$0");			\
+	register TYPE0 __r16 __asm__("$16") = arg0;		\
+	register TYPE1 __r17 __asm__("$17") = arg1;		\
+	__asm__ __volatile__(					\
+		"call_pal %3 # "#NAME				\
+		: "=r"(__r16), "=r"(__r17), "=r"(__r0)		\
+		: "i"(PAL_ ## NAME), "0"(__r16), "1"(__r17)	\
+		: "$1", "$22", "$23", "$24", "$25");		\
+	return __r0;						\
+}
+
+__CALL_PAL_W1(cflush, unsigned long);
+__CALL_PAL_R0(rdmces, unsigned long);
+__CALL_PAL_R0(rdps, unsigned long);
+__CALL_PAL_R0(rdusp, unsigned long);
+__CALL_PAL_RW1(swpipl, unsigned long, unsigned long);
+__CALL_PAL_R0(whami, unsigned long);
+__CALL_PAL_W2(wrent, void*, unsigned long);
+__CALL_PAL_W1(wripir, unsigned long);
+__CALL_PAL_W1(wrkgp, unsigned long);
+__CALL_PAL_W1(wrmces, unsigned long);
+__CALL_PAL_RW2(wrperfmon, unsigned long, unsigned long, unsigned long);
+__CALL_PAL_W1(wrusp, unsigned long);
+__CALL_PAL_W1(wrvptptr, unsigned long);
+
+/*
+ * TB routines..
+ */
+#define __tbi(nr,arg,arg1...)					\
+({								\
+	register unsigned long __r16 __asm__("$16") = (nr);	\
+	register unsigned long __r17 __asm__("$17"); arg;	\
+	__asm__ __volatile__(					\
+		"call_pal %3 #__tbi"				\
+		:"=r" (__r16),"=r" (__r17)			\
+		:"0" (__r16),"i" (PAL_tbi) ,##arg1		\
+		:"$0", "$1", "$22", "$23", "$24", "$25");	\
+})
+
+#define tbi(x,y)	__tbi(x,__r17=(y),"1" (__r17))
+#define tbisi(x)	__tbi(1,__r17=(x),"1" (__r17))
+#define tbisd(x)	__tbi(2,__r17=(x),"1" (__r17))
+#define tbis(x)		__tbi(3,__r17=(x),"1" (__r17))
+#define tbiap()		__tbi(-1, /* no second argument */)
+#define tbia()		__tbi(-2, /* no second argument */)
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
+
 #endif /* __ALPHA_PAL_H */
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index de98a732683d..81a4342d5a3f 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -15,6 +15,7 @@
 #include <asm/page.h>
 #include <asm/processor.h>	/* For TASK_SIZE */
 #include <asm/machvec.h>
+#include <asm/setup.h>
 
 struct mm_struct;
 struct vm_area_struct;
diff --git a/arch/alpha/include/asm/posix_types.h b/arch/alpha/include/asm/posix_types.h
index db167413300b..24779fc95994 100644
--- a/arch/alpha/include/asm/posix_types.h
+++ b/arch/alpha/include/asm/posix_types.h
@@ -8,116 +8,13 @@
  */
 
 typedef unsigned int	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef unsigned int	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef long long	__kernel_loff_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned long	__kernel_sigset_t;	/* at least 32 bits */
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_timer_t;
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
-
-typedef unsigned int	__kernel_old_dev_t;
-
-#ifdef __KERNEL__
-
-#ifndef __GNUC__
-
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-#define	__FD_ISSET(d, set)	(((set)->fds_bits[__FDELT(d)] & __FDMASK(d)) != 0)
-#define	__FD_ZERO(set)	\
-  ((void) memset ((void *) (set), 0, sizeof (__kernel_fd_set)))
-
-#else /* __GNUC__ */
-
-/* With GNU C, use inline functions instead so args are evaluated only once: */
+#define __kernel_ino_t __kernel_ino_t
 
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long fd, const __kernel_fd_set *p)
-{ 
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		      case 16:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			return;
-
-		      case 8:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			return;
-
-		      case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
+typedef unsigned int	__kernel_nlink_t;
+#define __kernel_nlink_t __kernel_nlink_t
 
-#endif /* __GNUC__ */
+typedef unsigned long	__kernel_sigset_t;	/* at least 32 bits */
 
-#endif /* __KERNEL__ */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ALPHA_POSIX_TYPES_H */
diff --git a/arch/alpha/include/asm/setup.h b/arch/alpha/include/asm/setup.h
index 2e023a4aa317..b50014b30909 100644
--- a/arch/alpha/include/asm/setup.h
+++ b/arch/alpha/include/asm/setup.h
@@ -3,4 +3,40 @@
 
 #define COMMAND_LINE_SIZE	256
 
+/*
+ * We leave one page for the initial stack page, and one page for
+ * the initial process structure. Also, the console eats 3 MB for
+ * the initial bootloader (one of which we can reclaim later).
+ */
+#define BOOT_PCB	0x20000000
+#define BOOT_ADDR	0x20000000
+/* Remove when official MILO sources have ELF support: */
+#define BOOT_SIZE	(16*1024)
+
+#ifdef CONFIG_ALPHA_LEGACY_START_ADDRESS
+#define KERNEL_START_PHYS	0x300000 /* Old bootloaders hardcoded this.  */
+#else
+#define KERNEL_START_PHYS	0x1000000 /* required: Wildfire/Titan/Marvel */
+#endif
+
+#define KERNEL_START	(PAGE_OFFSET+KERNEL_START_PHYS)
+#define SWAPPER_PGD	KERNEL_START
+#define INIT_STACK	(PAGE_OFFSET+KERNEL_START_PHYS+0x02000)
+#define EMPTY_PGT	(PAGE_OFFSET+KERNEL_START_PHYS+0x04000)
+#define EMPTY_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x08000)
+#define ZERO_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x0A000)
+
+#define START_ADDR	(PAGE_OFFSET+KERNEL_START_PHYS+0x10000)
+
+/*
+ * This is setup by the secondary bootstrap loader.  Because
+ * the zero page is zeroed out as soon as the vm system is
+ * initialized, we need to copy things out into a more permanent
+ * place.
+ */
+#define PARAM			ZERO_PGE
+#define COMMAND_LINE		((char*)(PARAM + 0x0000))
+#define INITRD_START		(*(unsigned long *) (PARAM+0x100))
+#define INITRD_SIZE		(*(unsigned long *) (PARAM+0x108))
+
 #endif
diff --git a/arch/alpha/include/asm/special_insns.h b/arch/alpha/include/asm/special_insns.h
new file mode 100644
index 000000000000..88d3452b21f0
--- /dev/null
+++ b/arch/alpha/include/asm/special_insns.h
@@ -0,0 +1,41 @@
+#ifndef __ALPHA_SPECIAL_INSNS_H
+#define __ALPHA_SPECIAL_INSNS_H
+
+enum implver_enum {
+	IMPLVER_EV4,
+	IMPLVER_EV5,
+	IMPLVER_EV6
+};
+
+#ifdef CONFIG_ALPHA_GENERIC
+#define implver()				\
+({ unsigned long __implver;			\
+   __asm__ ("implver %0" : "=r"(__implver));	\
+   (enum implver_enum) __implver; })
+#else
+/* Try to eliminate some dead code.  */
+#ifdef CONFIG_ALPHA_EV4
+#define implver() IMPLVER_EV4
+#endif
+#ifdef CONFIG_ALPHA_EV5
+#define implver() IMPLVER_EV5
+#endif
+#if defined(CONFIG_ALPHA_EV6)
+#define implver() IMPLVER_EV6
+#endif
+#endif
+
+enum amask_enum {
+	AMASK_BWX = (1UL << 0),
+	AMASK_FIX = (1UL << 1),
+	AMASK_CIX = (1UL << 2),
+	AMASK_MAX = (1UL << 8),
+	AMASK_PRECISE_TRAP = (1UL << 9),
+};
+
+#define amask(mask)						\
+({ unsigned long __amask, __input = (mask);			\
+   __asm__ ("amask %1,%0" : "=r"(__amask) : "rI"(__input));	\
+   __amask; })
+
+#endif /* __ALPHA_SPECIAL_INSNS_H */
diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h
index d0faca1e992d..3bba21e41b81 100644
--- a/arch/alpha/include/asm/spinlock.h
+++ b/arch/alpha/include/asm/spinlock.h
@@ -1,7 +1,6 @@
 #ifndef _ALPHA_SPINLOCK_H
 #define _ALPHA_SPINLOCK_H
 
-#include <asm/system.h>
 #include <linux/kernel.h>
 #include <asm/current.h>
 
diff --git a/arch/alpha/include/asm/switch_to.h b/arch/alpha/include/asm/switch_to.h
new file mode 100644
index 000000000000..44c0d4f2c0b2
--- /dev/null
+++ b/arch/alpha/include/asm/switch_to.h
@@ -0,0 +1,14 @@
+#ifndef __ALPHA_SWITCH_TO_H
+#define __ALPHA_SWITCH_TO_H
+
+
+struct task_struct;
+extern struct task_struct *alpha_switch_to(unsigned long, struct task_struct *);
+
+#define switch_to(P,N,L)						 \
+  do {									 \
+    (L) = alpha_switch_to(virt_to_phys(&task_thread_info(N)->pcb), (P)); \
+    check_mmu_context();						 \
+  } while (0)
+
+#endif /* __ALPHA_SWITCH_TO_H */
diff --git a/arch/alpha/include/asm/system.h b/arch/alpha/include/asm/system.h
deleted file mode 100644
index 9f78e6934637..000000000000
--- a/arch/alpha/include/asm/system.h
+++ /dev/null
@@ -1,354 +0,0 @@
-#ifndef __ALPHA_SYSTEM_H
-#define __ALPHA_SYSTEM_H
-
-#include <asm/pal.h>
-#include <asm/page.h>
-#include <asm/barrier.h>
-
-/*
- * System defines.. Note that this is included both from .c and .S
- * files, so it does only defines, not any C code.
- */
-
-/*
- * We leave one page for the initial stack page, and one page for
- * the initial process structure. Also, the console eats 3 MB for
- * the initial bootloader (one of which we can reclaim later).
- */
-#define BOOT_PCB	0x20000000
-#define BOOT_ADDR	0x20000000
-/* Remove when official MILO sources have ELF support: */
-#define BOOT_SIZE	(16*1024)
-
-#ifdef CONFIG_ALPHA_LEGACY_START_ADDRESS
-#define KERNEL_START_PHYS	0x300000 /* Old bootloaders hardcoded this.  */
-#else
-#define KERNEL_START_PHYS	0x1000000 /* required: Wildfire/Titan/Marvel */
-#endif
-
-#define KERNEL_START	(PAGE_OFFSET+KERNEL_START_PHYS)
-#define SWAPPER_PGD	KERNEL_START
-#define INIT_STACK	(PAGE_OFFSET+KERNEL_START_PHYS+0x02000)
-#define EMPTY_PGT	(PAGE_OFFSET+KERNEL_START_PHYS+0x04000)
-#define EMPTY_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x08000)
-#define ZERO_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x0A000)
-
-#define START_ADDR	(PAGE_OFFSET+KERNEL_START_PHYS+0x10000)
-
-/*
- * This is setup by the secondary bootstrap loader.  Because
- * the zero page is zeroed out as soon as the vm system is
- * initialized, we need to copy things out into a more permanent
- * place.
- */
-#define PARAM			ZERO_PGE
-#define COMMAND_LINE		((char*)(PARAM + 0x0000))
-#define INITRD_START		(*(unsigned long *) (PARAM+0x100))
-#define INITRD_SIZE		(*(unsigned long *) (PARAM+0x108))
-
-#ifndef __ASSEMBLY__
-#include <linux/kernel.h>
-#define AT_VECTOR_SIZE_ARCH 4 /* entries in ARCH_DLINFO */
-
-/*
- * This is the logout header that should be common to all platforms
- * (assuming they are running OSF/1 PALcode, I guess).
- */
-struct el_common {
-	unsigned int	size;		/* size in bytes of logout area */
-	unsigned int	sbz1	: 30;	/* should be zero */
-	unsigned int	err2	:  1;	/* second error */
-	unsigned int	retry	:  1;	/* retry flag */
-	unsigned int	proc_offset;	/* processor-specific offset */
-	unsigned int	sys_offset;	/* system-specific offset */
-	unsigned int	code;		/* machine check code */
-	unsigned int	frame_rev;	/* frame revision */
-};
-
-/* Machine Check Frame for uncorrectable errors (Large format)
- *      --- This is used to log uncorrectable errors such as
- *          double bit ECC errors.
- *      --- These errors are detected by both processor and systems.
- */
-struct el_common_EV5_uncorrectable_mcheck {
-        unsigned long   shadow[8];        /* Shadow reg. 8-14, 25           */
-        unsigned long   paltemp[24];      /* PAL TEMP REGS.                 */
-        unsigned long   exc_addr;         /* Address of excepting instruction*/
-        unsigned long   exc_sum;          /* Summary of arithmetic traps.   */
-        unsigned long   exc_mask;         /* Exception mask (from exc_sum). */
-        unsigned long   pal_base;         /* Base address for PALcode.      */
-        unsigned long   isr;              /* Interrupt Status Reg.          */
-        unsigned long   icsr;             /* CURRENT SETUP OF EV5 IBOX      */
-        unsigned long   ic_perr_stat;     /* I-CACHE Reg. <11> set Data parity
-                                                         <12> set TAG parity*/
-        unsigned long   dc_perr_stat;     /* D-CACHE error Reg. Bits set to 1:
-                                                     <2> Data error in bank 0
-                                                     <3> Data error in bank 1
-                                                     <4> Tag error in bank 0
-                                                     <5> Tag error in bank 1 */
-        unsigned long   va;               /* Effective VA of fault or miss. */
-        unsigned long   mm_stat;          /* Holds the reason for D-stream 
-                                             fault or D-cache parity errors */
-        unsigned long   sc_addr;          /* Address that was being accessed
-                                             when EV5 detected Secondary cache
-                                             failure.                 */
-        unsigned long   sc_stat;          /* Helps determine if the error was
-                                             TAG/Data parity(Secondary Cache)*/
-        unsigned long   bc_tag_addr;      /* Contents of EV5 BC_TAG_ADDR    */
-        unsigned long   ei_addr;          /* Physical address of any transfer
-                                             that is logged in EV5 EI_STAT */
-        unsigned long   fill_syndrome;    /* For correcting ECC errors.     */
-        unsigned long   ei_stat;          /* Helps identify reason of any 
-                                             processor uncorrectable error
-                                             at its external interface.     */
-        unsigned long   ld_lock;          /* Contents of EV5 LD_LOCK register*/
-};
-
-struct el_common_EV6_mcheck {
-	unsigned int FrameSize;		/* Bytes, including this field */
-	unsigned int FrameFlags;	/* <31> = Retry, <30> = Second Error */
-	unsigned int CpuOffset;		/* Offset to CPU-specific info */
-	unsigned int SystemOffset;	/* Offset to system-specific info */
-	unsigned int MCHK_Code;
-	unsigned int MCHK_Frame_Rev;
-	unsigned long I_STAT;		/* EV6 Internal Processor Registers */
-	unsigned long DC_STAT;		/* (See the 21264 Spec) */
-	unsigned long C_ADDR;
-	unsigned long DC1_SYNDROME;
-	unsigned long DC0_SYNDROME;
-	unsigned long C_STAT;
-	unsigned long C_STS;
-	unsigned long MM_STAT;
-	unsigned long EXC_ADDR;
-	unsigned long IER_CM;
-	unsigned long ISUM;
-	unsigned long RESERVED0;
-	unsigned long PAL_BASE;
-	unsigned long I_CTL;
-	unsigned long PCTX;
-};
-
-extern void halt(void) __attribute__((noreturn));
-#define __halt() __asm__ __volatile__ ("call_pal %0 #halt" : : "i" (PAL_halt))
-
-#define switch_to(P,N,L)						 \
-  do {									 \
-    (L) = alpha_switch_to(virt_to_phys(&task_thread_info(N)->pcb), (P)); \
-    check_mmu_context();						 \
-  } while (0)
-
-struct task_struct;
-extern struct task_struct *alpha_switch_to(unsigned long, struct task_struct*);
-
-#define imb() \
-__asm__ __volatile__ ("call_pal %0 #imb" : : "i" (PAL_imb) : "memory")
-
-#define draina() \
-__asm__ __volatile__ ("call_pal %0 #draina" : : "i" (PAL_draina) : "memory")
-
-enum implver_enum {
-	IMPLVER_EV4,
-	IMPLVER_EV5,
-	IMPLVER_EV6
-};
-
-#ifdef CONFIG_ALPHA_GENERIC
-#define implver()				\
-({ unsigned long __implver;			\
-   __asm__ ("implver %0" : "=r"(__implver));	\
-   (enum implver_enum) __implver; })
-#else
-/* Try to eliminate some dead code.  */
-#ifdef CONFIG_ALPHA_EV4
-#define implver() IMPLVER_EV4
-#endif
-#ifdef CONFIG_ALPHA_EV5
-#define implver() IMPLVER_EV5
-#endif
-#if defined(CONFIG_ALPHA_EV6)
-#define implver() IMPLVER_EV6
-#endif
-#endif
-
-enum amask_enum {
-	AMASK_BWX = (1UL << 0),
-	AMASK_FIX = (1UL << 1),
-	AMASK_CIX = (1UL << 2),
-	AMASK_MAX = (1UL << 8),
-	AMASK_PRECISE_TRAP = (1UL << 9),
-};
-
-#define amask(mask)						\
-({ unsigned long __amask, __input = (mask);			\
-   __asm__ ("amask %1,%0" : "=r"(__amask) : "rI"(__input));	\
-   __amask; })
-
-#define __CALL_PAL_R0(NAME, TYPE)				\
-extern inline TYPE NAME(void)					\
-{								\
-	register TYPE __r0 __asm__("$0");			\
-	__asm__ __volatile__(					\
-		"call_pal %1 # " #NAME				\
-		:"=r" (__r0)					\
-		:"i" (PAL_ ## NAME)				\
-		:"$1", "$16", "$22", "$23", "$24", "$25");	\
-	return __r0;						\
-}
-
-#define __CALL_PAL_W1(NAME, TYPE0)				\
-extern inline void NAME(TYPE0 arg0)				\
-{								\
-	register TYPE0 __r16 __asm__("$16") = arg0;		\
-	__asm__ __volatile__(					\
-		"call_pal %1 # "#NAME				\
-		: "=r"(__r16)					\
-		: "i"(PAL_ ## NAME), "0"(__r16)			\
-		: "$1", "$22", "$23", "$24", "$25");		\
-}
-
-#define __CALL_PAL_W2(NAME, TYPE0, TYPE1)			\
-extern inline void NAME(TYPE0 arg0, TYPE1 arg1)			\
-{								\
-	register TYPE0 __r16 __asm__("$16") = arg0;		\
-	register TYPE1 __r17 __asm__("$17") = arg1;		\
-	__asm__ __volatile__(					\
-		"call_pal %2 # "#NAME				\
-		: "=r"(__r16), "=r"(__r17)			\
-		: "i"(PAL_ ## NAME), "0"(__r16), "1"(__r17)	\
-		: "$1", "$22", "$23", "$24", "$25");		\
-}
-
-#define __CALL_PAL_RW1(NAME, RTYPE, TYPE0)			\
-extern inline RTYPE NAME(TYPE0 arg0)				\
-{								\
-	register RTYPE __r0 __asm__("$0");			\
-	register TYPE0 __r16 __asm__("$16") = arg0;		\
-	__asm__ __volatile__(					\
-		"call_pal %2 # "#NAME				\
-		: "=r"(__r16), "=r"(__r0)			\
-		: "i"(PAL_ ## NAME), "0"(__r16)			\
-		: "$1", "$22", "$23", "$24", "$25");		\
-	return __r0;						\
-}
-
-#define __CALL_PAL_RW2(NAME, RTYPE, TYPE0, TYPE1)		\
-extern inline RTYPE NAME(TYPE0 arg0, TYPE1 arg1)		\
-{								\
-	register RTYPE __r0 __asm__("$0");			\
-	register TYPE0 __r16 __asm__("$16") = arg0;		\
-	register TYPE1 __r17 __asm__("$17") = arg1;		\
-	__asm__ __volatile__(					\
-		"call_pal %3 # "#NAME				\
-		: "=r"(__r16), "=r"(__r17), "=r"(__r0)		\
-		: "i"(PAL_ ## NAME), "0"(__r16), "1"(__r17)	\
-		: "$1", "$22", "$23", "$24", "$25");		\
-	return __r0;						\
-}
-
-__CALL_PAL_W1(cflush, unsigned long);
-__CALL_PAL_R0(rdmces, unsigned long);
-__CALL_PAL_R0(rdps, unsigned long);
-__CALL_PAL_R0(rdusp, unsigned long);
-__CALL_PAL_RW1(swpipl, unsigned long, unsigned long);
-__CALL_PAL_R0(whami, unsigned long);
-__CALL_PAL_W2(wrent, void*, unsigned long);
-__CALL_PAL_W1(wripir, unsigned long);
-__CALL_PAL_W1(wrkgp, unsigned long);
-__CALL_PAL_W1(wrmces, unsigned long);
-__CALL_PAL_RW2(wrperfmon, unsigned long, unsigned long, unsigned long);
-__CALL_PAL_W1(wrusp, unsigned long);
-__CALL_PAL_W1(wrvptptr, unsigned long);
-
-/*
- * TB routines..
- */
-#define __tbi(nr,arg,arg1...)					\
-({								\
-	register unsigned long __r16 __asm__("$16") = (nr);	\
-	register unsigned long __r17 __asm__("$17"); arg;	\
-	__asm__ __volatile__(					\
-		"call_pal %3 #__tbi"				\
-		:"=r" (__r16),"=r" (__r17)			\
-		:"0" (__r16),"i" (PAL_tbi) ,##arg1		\
-		:"$0", "$1", "$22", "$23", "$24", "$25");	\
-})
-
-#define tbi(x,y)	__tbi(x,__r17=(y),"1" (__r17))
-#define tbisi(x)	__tbi(1,__r17=(x),"1" (__r17))
-#define tbisd(x)	__tbi(2,__r17=(x),"1" (__r17))
-#define tbis(x)		__tbi(3,__r17=(x),"1" (__r17))
-#define tbiap()		__tbi(-1, /* no second argument */)
-#define tbia()		__tbi(-2, /* no second argument */)
-
-/*
- * Atomic exchange routines.
- */
-
-#define __ASM__MB
-#define ____xchg(type, args...)		__xchg ## type ## _local(args)
-#define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
-#include <asm/xchg.h>
-
-#define xchg_local(ptr,x)						\
-  ({									\
-     __typeof__(*(ptr)) _x_ = (x);					\
-     (__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_,	\
-				       sizeof(*(ptr)));			\
-  })
-
-#define cmpxchg_local(ptr, o, n)					\
-  ({									\
-     __typeof__(*(ptr)) _o_ = (o);					\
-     __typeof__(*(ptr)) _n_ = (n);					\
-     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	\
-					  (unsigned long)_n_,		\
-					  sizeof(*(ptr)));		\
-  })
-
-#define cmpxchg64_local(ptr, o, n)					\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
-  })
-
-#ifdef CONFIG_SMP
-#undef __ASM__MB
-#define __ASM__MB	"\tmb\n"
-#endif
-#undef ____xchg
-#undef ____cmpxchg
-#define ____xchg(type, args...)		__xchg ##type(args)
-#define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
-#include <asm/xchg.h>
-
-#define xchg(ptr,x)							\
-  ({									\
-     __typeof__(*(ptr)) _x_ = (x);					\
-     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_,		\
-				 sizeof(*(ptr)));			\
-  })
-
-#define cmpxchg(ptr, o, n)						\
-  ({									\
-     __typeof__(*(ptr)) _o_ = (o);					\
-     __typeof__(*(ptr)) _n_ = (n);					\
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		\
-				    (unsigned long)_n_,	sizeof(*(ptr)));\
-  })
-
-#define cmpxchg64(ptr, o, n)						\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
-  })
-
-#undef __ASM__MB
-#undef ____cmpxchg
-
-#define __HAVE_ARCH_CMPXCHG 1
-
-#endif /* __ASSEMBLY__ */
-
-#define arch_align_stack(x) (x)
-
-#endif
diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h
index beba1b803e0d..1d1b436fbff2 100644
--- a/arch/alpha/include/asm/xchg.h
+++ b/arch/alpha/include/asm/xchg.h
@@ -1,4 +1,4 @@
-#ifndef __ALPHA_SYSTEM_H
+#ifndef _ALPHA_ATOMIC_H
 #error Do not include xchg.h directly!
 #else
 /*
diff --git a/arch/alpha/kernel/core_apecs.c b/arch/alpha/kernel/core_apecs.c
index ca46b2c24457..708c831efa76 100644
--- a/arch/alpha/kernel/core_apecs.c
+++ b/arch/alpha/kernel/core_apecs.c
@@ -21,6 +21,7 @@
 
 #include <asm/ptrace.h>
 #include <asm/smp.h>
+#include <asm/mce.h>
 
 #include "proto.h"
 #include "pci_impl.h"
diff --git a/arch/alpha/kernel/core_cia.c b/arch/alpha/kernel/core_cia.c
index 1d6ee6c985f9..c44339e176c1 100644
--- a/arch/alpha/kernel/core_cia.c
+++ b/arch/alpha/kernel/core_cia.c
@@ -23,6 +23,7 @@
 #include <linux/bootmem.h>
 
 #include <asm/ptrace.h>
+#include <asm/mce.h>
 
 #include "proto.h"
 #include "pci_impl.h"
diff --git a/arch/alpha/kernel/core_t2.c b/arch/alpha/kernel/core_t2.c
index 2f770e994289..3ada4f7b085d 100644
--- a/arch/alpha/kernel/core_t2.c
+++ b/arch/alpha/kernel/core_t2.c
@@ -21,6 +21,7 @@
 
 #include <asm/ptrace.h>
 #include <asm/delay.h>
+#include <asm/mce.h>
 
 #include "proto.h"
 #include "pci_impl.h"
diff --git a/arch/alpha/kernel/err_impl.h b/arch/alpha/kernel/err_impl.h
index 0c010ca4611e..ae529c416037 100644
--- a/arch/alpha/kernel/err_impl.h
+++ b/arch/alpha/kernel/err_impl.h
@@ -7,6 +7,8 @@
  * 	implementations.
  */
 
+#include <asm/mce.h>
+
 union el_timestamp;
 struct el_subpacket;
 struct ev7_lf_subpackets;
diff --git a/arch/alpha/kernel/head.S b/arch/alpha/kernel/head.S
index 4bdd1d2ff353..c352499ab9f8 100644
--- a/arch/alpha/kernel/head.S
+++ b/arch/alpha/kernel/head.S
@@ -8,14 +8,12 @@
  */
 
 #include <linux/init.h>
-#include <asm/system.h>
 #include <asm/asm-offsets.h>
+#include <asm/pal.h>
+#include <asm/setup.h>
 
 __HEAD
-.globl swapper_pg_dir
 .globl _stext
-swapper_pg_dir=SWAPPER_PGD
-
 	.set noreorder
 	.globl	__start
 	.ent	__start
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 381431a2d6d9..2872accd2215 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -26,7 +26,6 @@
 #include <linux/profile.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 
diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c
index 51b7fbd9e4c1..772ddfdb71a8 100644
--- a/arch/alpha/kernel/irq_alpha.c
+++ b/arch/alpha/kernel/irq_alpha.c
@@ -11,6 +11,7 @@
 #include <asm/machvec.h>
 #include <asm/dma.h>
 #include <asm/perf_event.h>
+#include <asm/mce.h>
 
 #include "proto.h"
 #include "irq_impl.h"
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 01e8715e26d9..49ee3193477a 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -40,7 +40,6 @@
 #include <asm/fpu.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/sysinfo.h>
 #include <asm/thread_info.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c
index 04eea4894ef3..df24b76f9246 100644
--- a/arch/alpha/kernel/pci-noop.c
+++ b/arch/alpha/kernel/pci-noop.c
@@ -108,7 +108,8 @@ sys_pciconfig_write(unsigned long bus, unsigned long dfn,
 }
 
 static void *alpha_noop_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t gfp)
+				       dma_addr_t *dma_handle, gfp_t gfp,
+				       struct dma_attrs *attrs)
 {
 	void *ret;
 
@@ -123,7 +124,8 @@ static void *alpha_noop_alloc_coherent(struct device *dev, size_t size,
 }
 
 static void alpha_noop_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_addr)
+				     void *cpu_addr, dma_addr_t dma_addr,
+				     struct dma_attrs *attrs)
 {
 	free_pages((unsigned long)cpu_addr, get_order(size));
 }
@@ -174,8 +176,8 @@ static int alpha_noop_set_mask(struct device *dev, u64 mask)
 }
 
 struct dma_map_ops alpha_noop_ops = {
-	.alloc_coherent		= alpha_noop_alloc_coherent,
-	.free_coherent		= alpha_noop_free_coherent,
+	.alloc			= alpha_noop_alloc_coherent,
+	.free			= alpha_noop_free_coherent,
 	.map_page		= alpha_noop_map_page,
 	.map_sg			= alpha_noop_map_sg,
 	.mapping_error		= alpha_noop_mapping_error,
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 43610804987d..cd634795aa9c 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -434,7 +434,8 @@ static void alpha_pci_unmap_page(struct device *dev, dma_addr_t dma_addr,
    else DMA_ADDRP is undefined.  */
 
 static void *alpha_pci_alloc_coherent(struct device *dev, size_t size,
-				      dma_addr_t *dma_addrp, gfp_t gfp)
+				      dma_addr_t *dma_addrp, gfp_t gfp,
+				      struct dma_attrs *attrs)
 {
 	struct pci_dev *pdev = alpha_gendev_to_pci(dev);
 	void *cpu_addr;
@@ -478,7 +479,8 @@ try_again:
    DMA_ADDR past this call are illegal.  */
 
 static void alpha_pci_free_coherent(struct device *dev, size_t size,
-				    void *cpu_addr, dma_addr_t dma_addr)
+				    void *cpu_addr, dma_addr_t dma_addr,
+				    struct dma_attrs *attrs)
 {
 	struct pci_dev *pdev = alpha_gendev_to_pci(dev);
 	pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
@@ -952,8 +954,8 @@ static int alpha_pci_set_mask(struct device *dev, u64 mask)
 }
 
 struct dma_map_ops alpha_pci_ops = {
-	.alloc_coherent		= alpha_pci_alloc_coherent,
-	.free_coherent		= alpha_pci_free_coherent,
+	.alloc			= alpha_pci_alloc_coherent,
+	.free			= alpha_pci_free_coherent,
 	.map_page		= alpha_pci_map_page,
 	.unmap_page		= alpha_pci_unmap_page,
 	.map_sg			= alpha_pci_map_sg,
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 89bbe5b41145..153d3fce3e8e 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -31,7 +31,6 @@
 
 #include <asm/reg.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c
index e2af5eb59bb4..54616f496aed 100644
--- a/arch/alpha/kernel/ptrace.c
+++ b/arch/alpha/kernel/ptrace.c
@@ -16,7 +16,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/fpu.h>
 
 #include "proto.h"
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index 32de56067e63..9e3107cc5ebb 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -55,7 +55,6 @@ static struct notifier_block alpha_panic_block = {
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/hwrpb.h>
 #include <asm/dma.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 6f7feb5db271..35f2ef44de12 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -120,12 +120,13 @@ SYSCALL_DEFINE5(rt_sigaction, int, sig, const struct sigaction __user *, act,
  */
 SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask)
 {
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
+	sigset_t blocked;
+
 	current->saved_sigmask = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -238,10 +239,7 @@ do_sigreturn(struct sigcontext __user *sc, struct pt_regs *regs,
 		goto give_sigsegv;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	if (restore_sigcontext(sc, regs, sw))
 		goto give_sigsegv;
@@ -276,10 +274,7 @@ do_rt_sigreturn(struct rt_sigframe __user *frame, struct pt_regs *regs,
 		goto give_sigsegv;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	if (restore_sigcontext(&frame->uc.uc_mcontext, regs, sw))
 		goto give_sigsegv;
@@ -501,14 +496,8 @@ handle_signal(int sig, struct k_sigaction *ka, siginfo_t *info,
 	else
 		ret = setup_frame(sig, ka, oldset, regs, sw);
 
-	if (ret == 0) {
-		spin_lock_irq(&current->sighand->siglock);
-		sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
-		if (!(ka->sa.sa_flags & SA_NODEFER)) 
-			sigaddset(&current->blocked,sig);
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-	}
+	if (ret == 0)
+		block_sigmask(ka, sig);
 
 	return ret;
 }
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 4087a569b43b..50d438db1f6b 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -450,7 +450,7 @@ setup_smp(void)
 		smp_num_probed = 1;
 	}
 
-	printk(KERN_INFO "SMP: %d CPUs probed -- cpu_present_map = %lx\n",
+	printk(KERN_INFO "SMP: %d CPUs probed -- cpu_present_mask = %lx\n",
 	       smp_num_probed, cpumask_bits(cpu_present_mask)[0]);
 }
 
diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c
index 8606d77e5163..118dc6af1805 100644
--- a/arch/alpha/kernel/sys_alcor.c
+++ b/arch/alpha/kernel/sys_alcor.c
@@ -18,7 +18,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c
index 1029619fb6c0..4c50f8f40cbb 100644
--- a/arch/alpha/kernel/sys_cabriolet.c
+++ b/arch/alpha/kernel/sys_cabriolet.c
@@ -18,7 +18,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 13f0717fc7fe..5bf401f7ea97 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -21,7 +21,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c
index 3c6c13cd8b19..ad40a425e841 100644
--- a/arch/alpha/kernel/sys_eb64p.c
+++ b/arch/alpha/kernel/sys_eb64p.c
@@ -17,7 +17,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c
index 35f480db7719..79d69d7f63f8 100644
--- a/arch/alpha/kernel/sys_eiger.c
+++ b/arch/alpha/kernel/sys_eiger.c
@@ -18,7 +18,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c
index 7f1a87f176e2..5a0af11b3a61 100644
--- a/arch/alpha/kernel/sys_jensen.c
+++ b/arch/alpha/kernel/sys_jensen.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 #define __EXTERN_INLINE inline
 #include <asm/io.h>
diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c
index fc8b12508611..14a4b6a7cf59 100644
--- a/arch/alpha/kernel/sys_marvel.c
+++ b/arch/alpha/kernel/sys_marvel.c
@@ -13,7 +13,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_miata.c b/arch/alpha/kernel/sys_miata.c
index 258da684670b..d5b9776a608d 100644
--- a/arch/alpha/kernel/sys_miata.c
+++ b/arch/alpha/kernel/sys_miata.c
@@ -17,7 +17,6 @@
 #include <linux/reboot.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c
index c0fd7284dec3..5e82dc1ad6f2 100644
--- a/arch/alpha/kernel/sys_mikasa.c
+++ b/arch/alpha/kernel/sys_mikasa.c
@@ -17,7 +17,7 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
+#include <asm/mce.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 4112200307c7..4d4c046f708d 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -35,7 +35,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c
index 21725283cdd7..063e594fd969 100644
--- a/arch/alpha/kernel/sys_noritake.c
+++ b/arch/alpha/kernel/sys_noritake.c
@@ -18,7 +18,7 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
+#include <asm/mce.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c
index a125d6bea7e1..dfd510ae5d8c 100644
--- a/arch/alpha/kernel/sys_rawhide.c
+++ b/arch/alpha/kernel/sys_rawhide.c
@@ -16,7 +16,6 @@
 #include <linux/init.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c
index 2581cbec6fc2..a3f485257170 100644
--- a/arch/alpha/kernel/sys_ruffian.c
+++ b/arch/alpha/kernel/sys_ruffian.c
@@ -18,7 +18,6 @@
 #include <linux/init.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c
index b172b27555a7..08ee737d4fba 100644
--- a/arch/alpha/kernel/sys_rx164.c
+++ b/arch/alpha/kernel/sys_rx164.c
@@ -17,7 +17,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c
index 98d1dbffe98f..8a0aa6d67b53 100644
--- a/arch/alpha/kernel/sys_sable.c
+++ b/arch/alpha/kernel/sys_sable.c
@@ -16,7 +16,6 @@
 #include <linux/init.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index 47bec1e97d1c..febd24eba7a6 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -20,7 +20,6 @@
 
 #include <asm/compiler.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_sx164.c b/arch/alpha/kernel/sys_sx164.c
index 73e1c317afcb..d063b360efed 100644
--- a/arch/alpha/kernel/sys_sx164.c
+++ b/arch/alpha/kernel/sys_sx164.c
@@ -17,7 +17,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
@@ -26,6 +25,7 @@
 #include <asm/core_cia.h>
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>
+#include <asm/special_insns.h>
 
 #include "proto.h"
 #include "irq_impl.h"
diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c
index 2ae99ad6975e..dd0f1eae3c68 100644
--- a/arch/alpha/kernel/sys_takara.c
+++ b/arch/alpha/kernel/sys_takara.c
@@ -16,7 +16,6 @@
 #include <linux/init.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c
index b8eafa053539..2533db280d9b 100644
--- a/arch/alpha/kernel/sys_titan.c
+++ b/arch/alpha/kernel/sys_titan.c
@@ -21,7 +21,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c
index 17c85a65e7b0..ee1874887776 100644
--- a/arch/alpha/kernel/sys_wildfire.c
+++ b/arch/alpha/kernel/sys_wildfire.c
@@ -15,7 +15,6 @@
 #include <linux/bitops.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 0414e021a91c..80d987c0e9aa 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -24,6 +24,7 @@
 #include <asm/sysinfo.h>
 #include <asm/hwrpb.h>
 #include <asm/mmu_context.h>
+#include <asm/special_insns.h>
 
 #include "proto.h"
 
diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index f937ad123852..647b84c15382 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -2,6 +2,7 @@
 #include <asm/thread_info.h>
 #include <asm/cache.h>
 #include <asm/page.h>
+#include <asm/setup.h>
 
 OUTPUT_FORMAT("elf64-alpha")
 OUTPUT_ARCH(alpha)
@@ -25,6 +26,7 @@ SECTIONS
 		*(.fixup)
 		*(.gnu.warning)
 	} :kernel
+	swapper_pg_dir = SWAPPER_PGD;
 	_etext = .;	/* End of text section */
 
 	NOTES :kernel :note
diff --git a/arch/alpha/lib/stacktrace.c b/arch/alpha/lib/stacktrace.c
index 6d432e42aedc..5e832161e6d2 100644
--- a/arch/alpha/lib/stacktrace.c
+++ b/arch/alpha/lib/stacktrace.c
@@ -1,5 +1,4 @@
 #include <linux/kernel.h>
-#include <asm/system.h>
 
 typedef unsigned int instr;
 
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index fadd5f882ff9..5eecab1a84ef 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -24,7 +24,6 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 69d0c5761e2f..1ad6ca74bed2 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -22,7 +22,6 @@
 #include <linux/vmalloc.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -31,6 +30,7 @@
 #include <asm/mmu_context.h>
 #include <asm/console.h>
 #include <asm/tlb.h>
+#include <asm/setup.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long);
 
diff --git a/arch/alpha/oprofile/common.c b/arch/alpha/oprofile/common.c
index bd8ac533a504..a0a5d27aa215 100644
--- a/arch/alpha/oprofile/common.c
+++ b/arch/alpha/oprofile/common.c
@@ -12,7 +12,6 @@
 #include <linux/smp.h>
 #include <linux/errno.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 #include "op_impl.h"
 
diff --git a/arch/alpha/oprofile/op_model_ev4.c b/arch/alpha/oprofile/op_model_ev4.c
index 80d764dbf22f..18aa9b4f94f1 100644
--- a/arch/alpha/oprofile/op_model_ev4.c
+++ b/arch/alpha/oprofile/op_model_ev4.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 #include "op_impl.h"
 
diff --git a/arch/alpha/oprofile/op_model_ev5.c b/arch/alpha/oprofile/op_model_ev5.c
index ceea6e1ad79a..c32f8a0ad925 100644
--- a/arch/alpha/oprofile/op_model_ev5.c
+++ b/arch/alpha/oprofile/op_model_ev5.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 #include "op_impl.h"
 
diff --git a/arch/alpha/oprofile/op_model_ev6.c b/arch/alpha/oprofile/op_model_ev6.c
index 0869f85f5748..1c84cc257fc7 100644
--- a/arch/alpha/oprofile/op_model_ev6.c
+++ b/arch/alpha/oprofile/op_model_ev6.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 #include "op_impl.h"
 
diff --git a/arch/alpha/oprofile/op_model_ev67.c b/arch/alpha/oprofile/op_model_ev67.c
index 5b9d178e0228..34a57a126553 100644
--- a/arch/alpha/oprofile/op_model_ev67.c
+++ b/arch/alpha/oprofile/op_model_ev67.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 #include "op_impl.h"
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 94422601ea5b..cf006d40342c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -9,6 +9,7 @@ config ARM
 	select SYS_SUPPORTS_APM_EMULATION
 	select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI)
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KGDB
 	select HAVE_KPROBES if !XIP_KERNEL
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
@@ -21,6 +22,7 @@ config ARM
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
+	select HAVE_KERNEL_XZ
 	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
@@ -28,10 +30,10 @@ config ARM
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select GENERIC_IRQ_SHOW
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select GENERIC_PCI_IOMAP
+	select HAVE_BPF_JIT if NET
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -52,9 +54,6 @@ config MIGHT_HAVE_PCI
 config SYS_SUPPORTS_APM_EMULATION
 	bool
 
-config HAVE_SCHED_CLOCK
-	bool
-
 config GENERIC_GPIO
 	bool
 
@@ -180,6 +179,9 @@ config ZONE_DMA
 config NEED_DMA_MAP_STATE
        def_bool y
 
+config ARCH_HAS_DMA_SET_COHERENT_MASK
+	bool
+
 config GENERIC_ISA_DMA
 	bool
 
@@ -217,6 +219,13 @@ config ARM_PATCH_PHYS_VIRT
 	  this feature (eg, building a kernel for a single machine) and
 	  you need to shrink the kernel to the minimal size.
 
+config NEED_MACH_IO_H
+	bool
+	help
+	  Select this when mach/io.h is required to provide special
+	  definitions for this platform.  The need for mach/io.h should
+	  be avoided when possible.
+
 config NEED_MACH_MEMORY_H
 	bool
 	help
@@ -268,7 +277,9 @@ config ARCH_INTEGRATOR
 	select GENERIC_CLOCKEVENTS
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_FPGA_IRQ
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
+	select SPARSE_IRQ
 	help
 	  Support for ARM's Integrator platform.
 
@@ -315,6 +326,7 @@ config ARCH_VEXPRESS
 	select HAVE_CLK
 	select HAVE_PATA_PLATFORM
 	select ICST
+	select NO_IOPORT
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_CLCD
 	help
@@ -326,6 +338,7 @@ config ARCH_AT91
 	select HAVE_CLK
 	select CLKDEV_LOOKUP
 	select IRQ_DOMAIN
+	select NEED_MACH_IO_H if PCCARD
 	help
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 processors.
@@ -354,6 +367,7 @@ config ARCH_HIGHBANK
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU
 	select HAVE_SMP
+	select SPARSE_IRQ
 	select USE_OF
 	help
 	  Support for the Calxeda Highbank SoC based boards.
@@ -404,6 +418,7 @@ config ARCH_EBSA110
 	select ISA
 	select NO_IOPORT
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  This is an evaluation board for the StrongARM processor available
@@ -430,6 +445,7 @@ config ARCH_FOOTBRIDGE
 	select FOOTBRIDGE
 	select GENERIC_CLOCKEVENTS
 	select HAVE_IDE
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  Support for systems based on the DC21285 companion chip
@@ -442,7 +458,6 @@ config ARCH_MXC
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
-	select HAVE_SCHED_CLOCK
 	select MULTI_IRQ_HANDLER
 	help
 	  Support for Freescale MXC/iMX-based family of processors
@@ -482,6 +497,7 @@ config ARCH_IOP13XX
 	select PCI
 	select ARCH_SUPPORTS_MSI
 	select VMSPLIT_1G
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	select NEED_RET_TO_USER
 	help
@@ -491,6 +507,7 @@ config ARCH_IOP32X
 	bool "IOP32x-based"
 	depends on MMU
 	select CPU_XSCALE
+	select NEED_MACH_IO_H
 	select NEED_RET_TO_USER
 	select PLAT_IOP
 	select PCI
@@ -503,6 +520,7 @@ config ARCH_IOP33X
 	bool "IOP33x-based"
 	depends on MMU
 	select CPU_XSCALE
+	select NEED_MACH_IO_H
 	select NEED_RET_TO_USER
 	select PLAT_IOP
 	select PCI
@@ -516,6 +534,7 @@ config ARCH_IXP23XX
 	select CPU_XSC3
  	select PCI
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  Support for Intel's IXP23xx (XScale) family of processors.
@@ -526,6 +545,7 @@ config ARCH_IXP2000
 	select CPU_XSCALE
 	select PCI
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  Support for Intel's IXP2400/2800 (XScale) family of processors.
@@ -533,12 +553,13 @@ config ARCH_IXP2000
 config ARCH_IXP4XX
 	bool "IXP4xx-based"
 	depends on MMU
+	select ARCH_HAS_DMA_SET_COHERENT_MASK
 	select CLKSRC_MMIO
 	select CPU_XSCALE
 	select GENERIC_GPIO
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select MIGHT_HAVE_PCI
+	select NEED_MACH_IO_H
 	select DMABOUNCE if PCI
 	help
 	  Support for Intel's IXP4XX (XScale) family of processors.
@@ -549,6 +570,7 @@ config ARCH_DOVE
 	select PCI
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
+	select NEED_MACH_IO_H
 	select PLAT_ORION
 	help
 	  Support for the Marvell Dove SoC 88AP510
@@ -559,6 +581,7 @@ config ARCH_KIRKWOOD
 	select PCI
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
+	select NEED_MACH_IO_H
 	select PLAT_ORION
 	help
 	  Support for the following Marvell Kirkwood series SoCs:
@@ -583,6 +606,7 @@ config ARCH_MV78XX0
 	select PCI
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
+	select NEED_MACH_IO_H
 	select PLAT_ORION
 	help
 	  Support for the following Marvell MV78xx0 series SoCs:
@@ -608,7 +632,6 @@ config ARCH_MMP
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
@@ -649,9 +672,9 @@ config ARCH_TEGRA
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
 	select HAVE_CLK
-	select HAVE_SCHED_CLOCK
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
+	select NEED_MACH_IO_H if PCI
 	select ARCH_HAS_CPUFREQ
 	help
 	  This enables support for NVIDIA Tegra based systems (Tegra APX,
@@ -666,7 +689,6 @@ config ARCH_PICOXCELL
 	select DW_APB_TIMER
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
-	select HAVE_SCHED_CLOCK
 	select HAVE_TCM
 	select NO_IOPORT
 	select SPARSE_IRQ
@@ -694,7 +716,6 @@ config ARCH_PXA
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
@@ -738,7 +759,6 @@ config ARCH_RPC
 	bool "RiscPC"
 	select ARCH_ACORN
 	select FIQ
-	select TIMER_ACORN
 	select ARCH_MAY_HAVE_PC_FDC
 	select HAVE_PATA_PLATFORM
 	select ISA_DMA_API
@@ -746,6 +766,7 @@ config ARCH_RPC
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_USES_GETTIMEOFFSET
 	select HAVE_IDE
+	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
 	help
 	  On the Acorn Risc-PC, Linux can support the internal IDE disk and
@@ -762,11 +783,11 @@ config ARCH_SA1100
 	select CPU_FREQ
 	select GENERIC_CLOCKEVENTS
 	select CLKDEV_LOOKUP
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_IDE
 	select NEED_MACH_MEMORY_H
+	select SPARSE_IRQ
 	help
 	  Support for StrongARM 11x0 based boards.
 
@@ -780,6 +801,7 @@ config ARCH_S3C24XX
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
+	select NEED_MACH_IO_H
 	help
 	  Samsung S3C2410, S3C2412, S3C2413, S3C2416, S3C2440, S3C2442, S3C2443
 	  and S3C2450 SoCs based systems, such as the Simtec Electronics BAST
@@ -818,7 +840,6 @@ config ARCH_S5P64X0
 	select CLKSRC_MMIO
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	help
@@ -849,7 +870,6 @@ config ARCH_S5PV210
 	select CLKSRC_MMIO
 	select ARCH_HAS_CPUFREQ
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
@@ -883,6 +903,7 @@ config ARCH_SHARK
 	select PCI
 	select ARCH_USES_GETTIMEOFFSET
 	select NEED_MACH_MEMORY_H
+	select NEED_MACH_IO_H
 	help
 	  Support for the StrongARM based Digital DNARD machine, also known
 	  as "Shark" (<http://www.shark-linux.de/shark.html>).
@@ -892,7 +913,6 @@ config ARCH_U300
 	depends on MMU
 	select CLKSRC_MMIO
 	select CPU_ARM926T
-	select HAVE_SCHED_CLOCK
 	select HAVE_TCM
 	select ARM_AMBA
 	select ARM_PATCH_PHYS_VIRT
@@ -951,7 +971,6 @@ config ARCH_OMAP
 	select ARCH_HAS_CPUFREQ
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	help
 	  Support for TI's OMAP platform (OMAP1/2/3/4).
@@ -1115,13 +1134,11 @@ config ARCH_ACORN
 config PLAT_IOP
 	bool
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 
 config PLAT_ORION
 	bool
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
-	select HAVE_SCHED_CLOCK
 
 config PLAT_PXA
 	bool
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 66ca8014ff3e..85348a09d655 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -292,6 +292,22 @@ choice
 		  Note that the system will appear to hang during boot if there
 		  is nothing connected to read from the DCC.
 
+	config DEBUG_SEMIHOSTING
+		bool "Kernel low-level debug output via semihosting I"
+		help
+		  Semihosting enables code running on an ARM target to use
+		  the I/O facilities on a host debugger/emulator through a
+		  simple SVC calls. The host debugger or emulator must have
+		  semihosting enabled for the special svc call to be trapped
+		  otherwise the kernel will crash.
+
+		  This is known to work with OpenOCD, as wellas
+		  ARM's Fast Models, or any other controlling environment
+		  that implements semihosting.
+
+		  For more details about semihosting, please see
+		  chapter 8 of DUI0203I_rvct_developer_guide.pdf from ARM Ltd.
+
 endchoice
 
 config EARLY_PRINTK
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 0106f75530c0..047a20780fc1 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -180,6 +180,7 @@ machine-$(CONFIG_ARCH_S5P64X0)		:= s5p64x0
 machine-$(CONFIG_ARCH_S5PC100)		:= s5pc100
 machine-$(CONFIG_ARCH_S5PV210)		:= s5pv210
 machine-$(CONFIG_ARCH_EXYNOS4)		:= exynos
+machine-$(CONFIG_ARCH_EXYNOS5)		:= exynos
 machine-$(CONFIG_ARCH_SA1100)		:= sa1100
 machine-$(CONFIG_ARCH_SHARK)		:= shark
 machine-$(CONFIG_ARCH_SHMOBILE) 	:= shmobile
@@ -252,6 +253,7 @@ core-$(CONFIG_VFP)		+= arch/arm/vfp/
 
 # If we have a machine-specific directory, then include it in the build.
 core-y				+= arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
+core-y				+= arch/arm/net/
 core-y				+= $(machdirs) $(platdirs)
 
 drivers-$(CONFIG_OPROFILE)      += arch/arm/oprofile/
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index fc871e719aae..c877087d2000 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -11,8 +11,6 @@
 # Copyright (C) 1995-2002 Russell King
 #
 
-MKIMAGE         := $(srctree)/scripts/mkuboot.sh
-
 ifneq ($(MACHINE),)
 include $(srctree)/$(MACHINE)/Makefile.boot
 endif
@@ -69,22 +67,19 @@ $(obj)/dtbs: $(addprefix $(obj)/, $(dtb-y))
 
 clean-files := *.dtb
 
-quiet_cmd_uimage = UIMAGE  $@
-      cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A arm -O linux -T kernel \
-		   -C none -a $(LOADADDR) -e $(STARTADDR) \
-		   -n 'Linux-$(KERNELRELEASE)' -d $< $@
-
-ifeq ($(CONFIG_ZBOOT_ROM),y)
-$(obj)/uImage: LOADADDR=$(CONFIG_ZBOOT_ROM_TEXT)
+ifneq ($(LOADADDR),)
+  UIMAGE_LOADADDR=$(LOADADDR)
 else
-$(obj)/uImage: LOADADDR=$(ZRELADDR)
+  ifeq ($(CONFIG_ZBOOT_ROM),y)
+    UIMAGE_LOADADDR=$(CONFIG_ZBOOT_ROM_TEXT)
+  else
+    UIMAGE_LOADADDR=$(ZRELADDR)
+  endif
 endif
 
-$(obj)/uImage: STARTADDR=$(LOADADDR)
-
 check_for_multiple_loadaddr = \
-if [ $(words $(LOADADDR)) -gt 1 ]; then \
-	echo 'multiple load addresses: $(LOADADDR)'; \
+if [ $(words $(UIMAGE_LOADADDR)) -gt 1 ]; then \
+	echo 'multiple load addresses: $(UIMAGE_LOADADDR)'; \
 	echo 'This is incompatible with uImages'; \
 	echo 'Specify LOADADDR on the commandline to build an uImage'; \
 	false; \
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index e0936a148516..d0d441c429ae 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -1,8 +1,10 @@
+ashldi3.S
 font.c
 lib1funcs.S
 piggy.gzip
 piggy.lzo
 piggy.lzma
+piggy.xzkern
 vmlinux
 vmlinux.lds
 
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index cf0a64ce4b83..bb267562e7ed 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -92,6 +92,7 @@ SEDFLAGS	= s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/
 suffix_$(CONFIG_KERNEL_GZIP) = gzip
 suffix_$(CONFIG_KERNEL_LZO)  = lzo
 suffix_$(CONFIG_KERNEL_LZMA) = lzma
+suffix_$(CONFIG_KERNEL_XZ)   = xzkern
 
 # Borrowed libfdt files for the ATAG compatibility mode
 
@@ -112,10 +113,12 @@ endif
 
 targets       := vmlinux vmlinux.lds \
 		 piggy.$(suffix_y) piggy.$(suffix_y).o \
-		 lib1funcs.o lib1funcs.S font.o font.c head.o misc.o $(OBJS)
+		 lib1funcs.o lib1funcs.S ashldi3.o ashldi3.S \
+		 font.o font.c head.o misc.o $(OBJS)
 
 # Make sure files are removed during clean
-extra-y       += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S $(libfdt) $(libfdt_hdrs)
+extra-y       += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern \
+		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs)
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
@@ -151,6 +154,12 @@ lib1funcs = $(obj)/lib1funcs.o
 $(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S
 	$(call cmd,shipped)
 
+# For __aeabi_llsl
+ashldi3 = $(obj)/ashldi3.o
+
+$(obj)/ashldi3.S: $(srctree)/arch/$(SRCARCH)/lib/ashldi3.S
+	$(call cmd,shipped)
+
 # We need to prevent any GOTOFF relocs being used with references
 # to symbols in the .bss section since we cannot relocate them
 # independently from the rest at run time.  This can be achieved by
@@ -172,7 +181,7 @@ if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \
 fi
 
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
-	 	$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE
+		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) FORCE
 	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)
diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c
index 07be5a2f8302..f41b38cafce8 100644
--- a/arch/arm/boot/compressed/decompress.c
+++ b/arch/arm/boot/compressed/decompress.c
@@ -44,6 +44,12 @@ extern void error(char *);
 #include "../../../../lib/decompress_unlzma.c"
 #endif
 
+#ifdef CONFIG_KERNEL_XZ
+#define memmove memmove
+#define memcpy memcpy
+#include "../../../../lib/decompress_unxz.c"
+#endif
+
 int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x))
 {
 	return decompress(input, len, NULL, NULL, output, NULL, error);
diff --git a/arch/arm/boot/compressed/piggy.xzkern.S b/arch/arm/boot/compressed/piggy.xzkern.S
new file mode 100644
index 000000000000..5703f300d027
--- /dev/null
+++ b/arch/arm/boot/compressed/piggy.xzkern.S
@@ -0,0 +1,6 @@
+	.section .piggydata,#alloc
+	.globl	input_data
+input_data:
+	.incbin	"arch/arm/boot/compressed/piggy.xzkern"
+	.globl	input_data_end
+input_data_end:
diff --git a/arch/arm/boot/dts/at91sam9g20.dtsi b/arch/arm/boot/dts/at91sam9g20.dtsi
index a100db03ec90..799ad1889b51 100644
--- a/arch/arm/boot/dts/at91sam9g20.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20.dtsi
@@ -35,7 +35,7 @@
 		};
 	};
 
-	memory@20000000 {
+	memory {
 		reg = <0x20000000 0x08000000>;
 	};
 
@@ -59,6 +59,26 @@
 				reg = <0xfffff000 0x200>;
 			};
 
+			ramc0: ramc@ffffea00 {
+				compatible = "atmel,at91sam9260-sdramc";
+				reg = <0xffffea00 0x200>;
+			};
+
+			pmc: pmc@fffffc00 {
+				compatible = "atmel,at91rm9200-pmc";
+				reg = <0xfffffc00 0x100>;
+			};
+
+			rstc@fffffd00 {
+				compatible = "atmel,at91sam9260-rstc";
+				reg = <0xfffffd00 0x10>;
+			};
+
+			shdwc@fffffd10 {
+				compatible = "atmel,at91sam9260-shdwc";
+				reg = <0xfffffd10 0x10>;
+			};
+
 			pit: timer@fffffd30 {
 				compatible = "atmel,at91sam9260-pit";
 				reg = <0xfffffd30 0xf>;
@@ -171,6 +191,49 @@
 				interrupts = <21 4>;
 				status = "disabled";
 			};
+
+			usb1: gadget@fffa4000 {
+				compatible = "atmel,at91rm9200-udc";
+				reg = <0xfffa4000 0x4000>;
+				interrupts = <10 4>;
+				status = "disabled";
+			};
+		};
+
+		nand0: nand@40000000 {
+			compatible = "atmel,at91rm9200-nand";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x40000000 0x10000000
+			       0xffffe800 0x200
+			      >;
+			atmel,nand-addr-offset = <21>;
+			atmel,nand-cmd-offset = <22>;
+			gpios = <&pioC 13 0
+				 &pioC 14 0
+				 0
+				>;
+			status = "disabled";
 		};
+
+		usb0: ohci@00500000 {
+			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
+			reg = <0x00500000 0x100000>;
+			interrupts = <20 4>;
+			status = "disabled";
+		};
+	};
+
+	i2c@0 {
+		compatible = "i2c-gpio";
+		gpios = <&pioA 23 0 /* sda */
+			 &pioA 24 0 /* scl */
+			>;
+		i2c-gpio,sda-open-drain;
+		i2c-gpio,scl-open-drain;
+		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9g25ek.dts b/arch/arm/boot/dts/at91sam9g25ek.dts
index e64eb932083b..7829a4d0cb22 100644
--- a/arch/arm/boot/dts/at91sam9g25ek.dts
+++ b/arch/arm/boot/dts/at91sam9g25ek.dts
@@ -15,7 +15,7 @@
 	compatible = "atmel,at91sam9g25ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9";
 
 	chosen {
-		bootargs = "128M console=ttyS0,115200 mtdparts=atmel_nand:8M(bootstrap/uboot/kernel)ro,-(rootfs) root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs";
+		bootargs = "128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs";
 	};
 
 	ahb {
@@ -33,5 +33,17 @@
 				status = "okay";
 			};
 		};
+
+		usb0: ohci@00600000 {
+			status = "okay";
+			num-ports = <2>;
+			atmel,vbus-gpio = <&pioD 19 1
+					   &pioD 20 1
+					  >;
+		};
+
+		usb1: ehci@00700000 {
+			status = "okay";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index f779667159b1..9e6eb6ecea0e 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -36,7 +36,7 @@
 		};
 	};
 
-	memory@70000000 {
+	memory {
 		reg = <0x70000000 0x10000000>;
 	};
 
@@ -60,6 +60,22 @@
 				reg = <0xfffff000 0x200>;
 			};
 
+			ramc0: ramc@ffffe400 {
+				compatible = "atmel,at91sam9g45-ddramc";
+				reg = <0xffffe400 0x200
+				       0xffffe600 0x200>;
+			};
+
+			pmc: pmc@fffffc00 {
+				compatible = "atmel,at91rm9200-pmc";
+				reg = <0xfffffc00 0x100>;
+			};
+
+			rstc@fffffd00 {
+				compatible = "atmel,at91sam9g45-rstc";
+				reg = <0xfffffd00 0x10>;
+			};
+
 			pit: timer@fffffd30 {
 				compatible = "atmel,at91sam9260-pit";
 				reg = <0xfffffd30 0xf>;
@@ -67,6 +83,11 @@
 			};
 
 
+			shdwc@fffffd10 {
+				compatible = "atmel,at91sam9rl-shdwc";
+				reg = <0xfffffd10 0x10>;
+			};
+
 			tcb0: timer@fff7c000 {
 				compatible = "atmel,at91rm9200-tcb";
 				reg = <0xfff7c000 0x100>;
@@ -180,5 +201,48 @@
 				status = "disabled";
 			};
 		};
+
+		nand0: nand@40000000 {
+			compatible = "atmel,at91rm9200-nand";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x40000000 0x10000000
+			       0xffffe200 0x200
+			      >;
+			atmel,nand-addr-offset = <21>;
+			atmel,nand-cmd-offset = <22>;
+			gpios = <&pioC 8 0
+				 &pioC 14 0
+				 0
+				>;
+			status = "disabled";
+		};
+
+		usb0: ohci@00700000 {
+			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
+			reg = <0x00700000 0x100000>;
+			interrupts = <22 4>;
+			status = "disabled";
+		};
+
+		usb1: ehci@00800000 {
+			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
+			reg = <0x00800000 0x100000>;
+			interrupts = <22 4>;
+			status = "disabled";
+		};
+	};
+
+	i2c@0 {
+		compatible = "i2c-gpio";
+		gpios = <&pioA 20 0 /* sda */
+			 &pioA 21 0 /* scl */
+			>;
+		i2c-gpio,sda-open-drain;
+		i2c-gpio,scl-open-drain;
+		i2c-gpio,delay-us = <5>;	/* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts
index 15e25f903cad..a3633bd13111 100644
--- a/arch/arm/boot/dts/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts
@@ -14,13 +14,24 @@
 	compatible = "atmel,at91sam9m10g45ek", "atmel,at91sam9g45", "atmel,at91sam9";
 
 	chosen {
-		bootargs = "mem=64M console=ttyS0,115200 mtdparts=atmel_nand:4M(bootstrap/uboot/kernel)ro,60M(rootfs),-(data) root=/dev/mtdblock1 rw rootfstype=jffs2";
+		bootargs = "mem=64M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
 	};
 
-	memory@70000000 {
+	memory {
 		reg = <0x70000000 0x4000000>;
 	};
 
+	clocks {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		main_clock: clock@0 {
+			compatible = "atmel,osc", "fixed-clock";
+			clock-frequency = <12000000>;
+		};
+	};
+
 	ahb {
 		apb {
 			dbgu: serial@ffffee00 {
@@ -36,6 +47,39 @@
 				status = "okay";
 			};
 		};
+
+		nand0: nand@40000000 {
+			nand-bus-width = <8>;
+			nand-ecc-mode = "soft";
+			nand-on-flash-bbt;
+			status = "okay";
+
+			boot@0 {
+				label = "bootstrap/uboot/kernel";
+				reg = <0x0 0x400000>;
+			};
+
+			rootfs@400000 {
+				label = "rootfs";
+				reg = <0x400000 0x3C00000>;
+			};
+
+			data@4000000 {
+				label = "data";
+				reg = <0x4000000 0xC000000>;
+			};
+		};
+
+		usb0: ohci@00700000 {
+			status = "okay";
+			num-ports = <2>;
+			atmel,vbus-gpio = <&pioD 1 1
+					   &pioD 3 1>;
+		};
+
+		usb1: ehci@00800000 {
+			status = "okay";
+		};
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index a02e636d8a57..70ab3a4e026f 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -34,7 +34,7 @@
 		};
 	};
 
-	memory@20000000 {
+	memory {
 		reg = <0x20000000 0x10000000>;
 	};
 
@@ -58,6 +58,26 @@
 				reg = <0xfffff000 0x200>;
 			};
 
+			ramc0: ramc@ffffe800 {
+				compatible = "atmel,at91sam9g45-ddramc";
+				reg = <0xffffe800 0x200>;
+			};
+
+			pmc: pmc@fffffc00 {
+				compatible = "atmel,at91rm9200-pmc";
+				reg = <0xfffffc00 0x100>;
+			};
+
+			rstc@fffffe00 {
+				compatible = "atmel,at91sam9g45-rstc";
+				reg = <0xfffffe00 0x10>;
+			};
+
+			shdwc@fffffe10 {
+				compatible = "atmel,at91sam9x5-shdwc";
+				reg = <0xfffffe10 0x10>;
+			};
+
 			pit: timer@fffffe30 {
 				compatible = "atmel,at91sam9260-pit";
 				reg = <0xfffffe30 0xf>;
@@ -172,5 +192,73 @@
 				status = "disabled";
 			};
 		};
+
+		nand0: nand@40000000 {
+			compatible = "atmel,at91rm9200-nand";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x40000000 0x10000000
+			      >;
+			atmel,nand-addr-offset = <21>;
+			atmel,nand-cmd-offset = <22>;
+			gpios = <&pioD 5 0
+				 &pioD 4 0
+				 0
+				>;
+			status = "disabled";
+		};
+
+		usb0: ohci@00600000 {
+			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
+			reg = <0x00600000 0x100000>;
+			interrupts = <22 4>;
+			status = "disabled";
+		};
+
+		usb1: ehci@00700000 {
+			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
+			reg = <0x00700000 0x100000>;
+			interrupts = <22 4>;
+			status = "disabled";
+		};
+	};
+
+	i2c@0 {
+		compatible = "i2c-gpio";
+		gpios = <&pioA 30 0 /* sda */
+			 &pioA 31 0 /* scl */
+			>;
+		i2c-gpio,sda-open-drain;
+		i2c-gpio,scl-open-drain;
+		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c@1 {
+		compatible = "i2c-gpio";
+		gpios = <&pioC 0 0 /* sda */
+			 &pioC 1 0 /* scl */
+			>;
+		i2c-gpio,sda-open-drain;
+		i2c-gpio,scl-open-drain;
+		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c@2 {
+		compatible = "i2c-gpio";
+		gpios = <&pioB 4 0 /* sda */
+			 &pioB 5 0 /* scl */
+			>;
+		i2c-gpio,sda-open-drain;
+		i2c-gpio,scl-open-drain;
+		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9x5cm.dtsi b/arch/arm/boot/dts/at91sam9x5cm.dtsi
index 64ae3e890259..31e7be23703d 100644
--- a/arch/arm/boot/dts/at91sam9x5cm.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5cm.dtsi
@@ -8,10 +8,55 @@
  */
 
 / {
-	memory@20000000 {
+	memory {
 		reg = <0x20000000 0x8000000>;
 	};
 
+	clocks {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		main_clock: clock@0 {
+			compatible = "atmel,osc", "fixed-clock";
+			clock-frequency = <12000000>;
+		};
+	};
+
+	ahb {
+		nand0: nand@40000000 {
+			nand-bus-width = <8>;
+			nand-ecc-mode = "soft";
+			nand-on-flash-bbt;
+			status = "okay";
+
+			at91bootstrap@0 {
+				label = "at91bootstrap";
+				reg = <0x0 0x40000>;
+			};
+
+			uboot@40000 {
+				label = "u-boot";
+				reg = <0x40000 0x80000>;
+			};
+
+			ubootenv@c0000 {
+				label = "U-Boot Env";
+				reg = <0xc0000 0x140000>;
+			};
+
+			kernel@200000 {
+				label = "kernel";
+				reg = <0x200000 0x600000>;
+			};
+
+			rootfs@800000 {
+				label = "rootfs";
+				reg = <0x800000 0x1f800000>;
+			};
+		};
+	};
+
 	leds {
 		compatible = "gpio-leds";
 
diff --git a/arch/arm/boot/dts/db8500.dtsi b/arch/arm/boot/dts/db8500.dtsi
new file mode 100644
index 000000000000..d73dce645667
--- /dev/null
+++ b/arch/arm/boot/dts/db8500.dtsi
@@ -0,0 +1,275 @@
+/*
+ * Copyright 2012 Linaro Ltd
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	soc-u9500 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "stericsson,db8500";
+		interrupt-parent = <&intc>;
+		ranges;
+
+		intc: interrupt-controller@a0411000 {
+			compatible = "arm,cortex-a9-gic";
+			#interrupt-cells = <3>;
+			#address-cells = <1>;
+			interrupt-controller;
+			interrupt-parent;
+			reg = <0xa0411000 0x1000>,
+			      <0xa0410100 0x100>;
+		};
+
+		L2: l2-cache {
+			compatible = "arm,pl310-cache";
+			reg = <0xa0412000 0x1000>;
+			interrupts = <0 13 4>;
+			cache-unified;
+			cache-level = <2>;
+		};
+
+		pmu {
+			compatible = "arm,cortex-a9-pmu";
+			interrupts = <0 7 0x4>;
+		};
+
+		timer@a0410600 {
+			compatible = "arm,cortex-a9-twd-timer";
+			reg = <0xa0410600 0x20>;
+			interrupts = <1 13 0x304>;
+		};
+
+		rtc@80154000 {
+			compatible = "stericsson,db8500-rtc";
+			reg = <0x80154000 0x1000>;
+			interrupts = <0 18 0x4>;
+		};
+
+		gpio0: gpio@8012e000 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0x8012e000 0x80>;
+			interrupts = <0 119 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		gpio1: gpio@8012e080 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0x8012e080 0x80>;
+			interrupts = <0 120 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		gpio2: gpio@8000e000 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0x8000e000 0x80>;
+			interrupts = <0 121 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		gpio3: gpio@8000e080 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0x8000e080 0x80>;
+			interrupts = <0 122 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		gpio4: gpio@8000e100 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0x8000e100 0x80>;
+			interrupts = <0 123 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		gpio5: gpio@8000e180 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0x8000e180 0x80>;
+			interrupts = <0 124 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		gpio6: gpio@8011e000 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0x8011e000 0x80>;
+			interrupts = <0 125 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		gpio7: gpio@8011e080 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0x8011e080 0x80>;
+			interrupts = <0 126 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		gpio8: gpio@a03fe000 {
+			compatible = "stericsson,db8500-gpio",
+				"stmicroelectronics,nomadik-gpio";
+			reg =  <0xa03fe000 0x80>;
+			interrupts = <0 127 0x4>;
+			supports-sleepmode;
+			gpio-controller;
+		};
+
+		usb@a03e0000 {
+			compatible = "stericsson,db8500-musb",
+				"mentor,musb";
+			reg = <0xa03e0000 0x10000>;
+			interrupts = <0 23 0x4>;
+		};
+
+		dma-controller@801C0000 {
+			compatible = "stericsson,db8500-dma40",
+					"stericsson,dma40";
+			reg = <0x801C0000 0x1000 0x40010000 0x800>;
+			interrupts = <0 25 0x4>;
+		};
+
+		prcmu@80157000 {
+			compatible = "stericsson,db8500-prcmu";
+			reg = <0x80157000 0x1000>;
+			interrupts = <46 47>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ab8500@5 {
+				compatible = "stericsson,ab8500";
+				reg = <5>; /* mailbox 5 is i2c */
+				interrupts = <0 40 0x4>;
+			};
+		};
+
+		i2c@80004000 {
+			compatible = "stericsson,db8500-i2c", "stmicroelectronics,nomadik-i2c";
+			reg = <0x80004000 0x1000>;
+			interrupts = <0 21 0x4>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c@80122000 {
+			compatible = "stericsson,db8500-i2c", "stmicroelectronics,nomadik-i2c";
+			reg = <0x80122000 0x1000>;
+			interrupts = <0 22 0x4>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c@80128000 {
+			compatible = "stericsson,db8500-i2c", "stmicroelectronics,nomadik-i2c";
+			reg = <0x80128000 0x1000>;
+			interrupts = <0 55 0x4>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c@80110000 {
+			compatible = "stericsson,db8500-i2c", "stmicroelectronics,nomadik-i2c";
+			reg = <0x80110000 0x1000>;
+			interrupts = <0 12 0x4>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c@8012a000 {
+			compatible = "stericsson,db8500-i2c", "stmicroelectronics,nomadik-i2c";
+			reg = <0x8012a000 0x1000>;
+			interrupts = <0 51 0x4>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		ssp@80002000 {
+			compatible = "arm,pl022", "arm,primecell";
+			reg = <80002000 0x1000>;
+			interrupts = <0 14 0x4>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+
+			// Add one of these for each child device
+			cs-gpios = <&gpio0 31 &gpio4 14 &gpio4 16 &gpio6 22 &gpio7 0>;
+
+		};
+
+		uart@80120000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x80120000 0x1000>;
+			interrupts = <0 11 0x4>;
+			status = "disabled";
+		};
+		uart@80121000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x80121000 0x1000>;
+			interrupts = <0 19 0x4>;
+			status = "disabled";
+		};
+		uart@80007000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x80007000 0x1000>;
+			interrupts = <0 26 0x4>;
+			status = "disabled";
+		};
+
+		sdi@80126000 {
+			compatible = "arm,pl18x", "arm,primecell";
+			reg = <0x80126000 0x1000>;
+			interrupts = <0 60 0x4>;
+			status = "disabled";
+		};
+		sdi@80118000 {
+			compatible = "arm,pl18x", "arm,primecell";
+			reg = <0x80118000 0x1000>;
+			interrupts = <0 50 0x4>;
+			status = "disabled";
+		};
+		sdi@80005000 {
+			compatible = "arm,pl18x", "arm,primecell";
+			reg = <0x80005000 0x1000>;
+			interrupts = <0 41 0x4>;
+			status = "disabled";
+		};
+		sdi@80119000 {
+			compatible = "arm,pl18x", "arm,primecell";
+			reg = <0x80119000 0x1000>;
+			interrupts = <0 59 0x4>;
+			status = "disabled";
+		};
+		sdi@80114000 {
+			compatible = "arm,pl18x", "arm,primecell";
+			reg = <0x80114000 0x1000>;
+			interrupts = <0 99 0x4>;
+			status = "disabled";
+		};
+		sdi@80008000 {
+			compatible = "arm,pl18x", "arm,primecell";
+			reg = <0x80114000 0x1000>;
+			interrupts = <0 100 0x4>;
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts
new file mode 100644
index 000000000000..399d17b231d2
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts
@@ -0,0 +1,26 @@
+/*
+ * SAMSUNG SMDK5250 board device tree source
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+/dts-v1/;
+/include/ "exynos5250.dtsi"
+
+/ {
+	model = "SAMSUNG SMDK5250 board based on EXYNOS5250";
+	compatible = "samsung,smdk5250", "samsung,exynos5250";
+
+	memory {
+		reg = <0x40000000 0x80000000>;
+	};
+
+	chosen {
+		bootargs = "root=/dev/ram0 rw ramdisk=8192 console=ttySAC1,115200";
+	};
+};
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
new file mode 100644
index 000000000000..dfc433599436
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -0,0 +1,413 @@
+/*
+ * SAMSUNG EXYNOS5250 SoC device tree source
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * SAMSUNG EXYNOS5250 SoC device nodes are listed in this file.
+ * EXYNOS5250 based board files can include this file and provide
+ * values for board specfic bindings.
+ *
+ * Note: This file does not include device nodes for all the controllers in
+ * EXYNOS5250 SoC. As device tree coverage for EXYNOS5250 increases,
+ * additional nodes can be added to this file.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "samsung,exynos5250";
+	interrupt-parent = <&gic>;
+
+	gic:interrupt-controller@10490000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		interrupt-controller;
+		reg = <0x10490000 0x1000>, <0x10480000 0x100>;
+	};
+
+	watchdog {
+		compatible = "samsung,s3c2410-wdt";
+		reg = <0x101D0000 0x100>;
+		interrupts = <0 42 0>;
+	};
+
+	rtc {
+		compatible = "samsung,s3c6410-rtc";
+		reg = <0x101E0000 0x100>;
+		interrupts = <0 43 0>, <0 44 0>;
+	};
+
+	sdhci@12200000 {
+		compatible = "samsung,exynos4210-sdhci";
+		reg = <0x12200000 0x100>;
+		interrupts = <0 75 0>;
+	};
+
+	sdhci@12210000 {
+		compatible = "samsung,exynos4210-sdhci";
+		reg = <0x12210000 0x100>;
+		interrupts = <0 76 0>;
+	};
+
+	sdhci@12220000 {
+		compatible = "samsung,exynos4210-sdhci";
+		reg = <0x12220000 0x100>;
+		interrupts = <0 77 0>;
+	};
+
+	sdhci@12230000 {
+		compatible = "samsung,exynos4210-sdhci";
+		reg = <0x12230000 0x100>;
+		interrupts = <0 78 0>;
+	};
+
+	serial@12C00000 {
+		compatible = "samsung,exynos4210-uart";
+		reg = <0x12C00000 0x100>;
+		interrupts = <0 51 0>;
+	};
+
+	serial@12C10000 {
+		compatible = "samsung,exynos4210-uart";
+		reg = <0x12C10000 0x100>;
+		interrupts = <0 52 0>;
+	};
+
+	serial@12C20000 {
+		compatible = "samsung,exynos4210-uart";
+		reg = <0x12C20000 0x100>;
+		interrupts = <0 53 0>;
+	};
+
+	serial@12C30000 {
+		compatible = "samsung,exynos4210-uart";
+		reg = <0x12C30000 0x100>;
+		interrupts = <0 54 0>;
+	};
+
+	i2c@12C60000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x12C60000 0x100>;
+		interrupts = <0 56 0>;
+	};
+
+	i2c@12C70000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x12C70000 0x100>;
+		interrupts = <0 57 0>;
+	};
+
+	i2c@12C80000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x12C80000 0x100>;
+		interrupts = <0 58 0>;
+	};
+
+	i2c@12C90000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x12C90000 0x100>;
+		interrupts = <0 59 0>;
+	};
+
+	i2c@12CA0000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x12CA0000 0x100>;
+		interrupts = <0 60 0>;
+	};
+
+	i2c@12CB0000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x12CB0000 0x100>;
+		interrupts = <0 61 0>;
+	};
+
+	i2c@12CC0000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x12CC0000 0x100>;
+		interrupts = <0 62 0>;
+	};
+
+	i2c@12CD0000 {
+		compatible = "samsung,s3c2440-i2c";
+		reg = <0x12CD0000 0x100>;
+		interrupts = <0 63 0>;
+	};
+
+	amba {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "arm,amba-bus";
+		interrupt-parent = <&gic>;
+		ranges;
+
+		pdma0: pdma@121A0000 {
+			compatible = "arm,pl330", "arm,primecell";
+			reg = <0x121A0000 0x1000>;
+			interrupts = <0 34 0>;
+		};
+
+		pdma1: pdma@121B0000 {
+			compatible = "arm,pl330", "arm,primecell";
+			reg = <0x121B0000 0x1000>;
+			interrupts = <0 35 0>;
+		};
+
+		mdma0: pdma@10800000 {
+			compatible = "arm,pl330", "arm,primecell";
+			reg = <0x10800000 0x1000>;
+			interrupts = <0 33 0>;
+		};
+
+		mdma1: pdma@11C10000 {
+			compatible = "arm,pl330", "arm,primecell";
+			reg = <0x11C10000 0x1000>;
+			interrupts = <0 124 0>;
+		};
+	};
+
+	gpio-controllers {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		gpio-controller;
+		ranges;
+
+		gpa0: gpio-controller@11400000 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400000 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpa1: gpio-controller@11400020 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400020 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpa2: gpio-controller@11400040 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400040 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpb0: gpio-controller@11400060 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400060 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpb1: gpio-controller@11400080 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400080 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpb2: gpio-controller@114000A0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x114000A0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpb3: gpio-controller@114000C0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x114000C0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpc0: gpio-controller@114000E0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x114000E0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpc1: gpio-controller@11400100 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400100 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpc2: gpio-controller@11400120 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400120 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpc3: gpio-controller@11400140 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400140 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpd0: gpio-controller@11400160 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400160 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpd1: gpio-controller@11400180 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400180 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpy0: gpio-controller@114001A0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x114001A0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpy1: gpio-controller@114001C0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x114001C0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpy2: gpio-controller@114001E0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x114001E0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpy3: gpio-controller@11400200 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400200 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpy4: gpio-controller@11400220 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400220 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpy5: gpio-controller@11400240 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400240 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpy6: gpio-controller@11400260 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400260 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpx0: gpio-controller@11400C00 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400C00 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpx1: gpio-controller@11400C20 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400C20 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpx2: gpio-controller@11400C40 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400C40 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpx3: gpio-controller@11400C60 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x11400C60 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpe0: gpio-controller@13400000 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x13400000 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpe1: gpio-controller@13400020 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x13400020 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpf0: gpio-controller@13400040 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x13400040 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpf1: gpio-controller@13400060 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x13400060 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpg0: gpio-controller@13400080 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x13400080 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpg1: gpio-controller@134000A0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x134000A0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpg2: gpio-controller@134000C0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x134000C0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gph0: gpio-controller@134000E0 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x134000E0 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gph1: gpio-controller@13400100 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x13400100 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpv0: gpio-controller@10D10000 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x10D10000 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpv1: gpio-controller@10D10020 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x10D10020 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpv2: gpio-controller@10D10040 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x10D10040 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpv3: gpio-controller@10D10060 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x10D10060 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpv4: gpio-controller@10D10080 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x10D10080 0x20>;
+			#gpio-cells = <4>;
+		};
+
+		gpz: gpio-controller@03860000 {
+			compatible = "samsung,exynos4-gpio";
+			reg = <0x03860000 0x20>;
+			#gpio-cells = <4>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-dreamplug.dts b/arch/arm/boot/dts/kirkwood-dreamplug.dts
index 8a5dff807b45..a5376b84227f 100644
--- a/arch/arm/boot/dts/kirkwood-dreamplug.dts
+++ b/arch/arm/boot/dts/kirkwood-dreamplug.dts
@@ -4,7 +4,7 @@
 
 / {
 	model = "Globalscale Technologies Dreamplug";
-	compatible = "globalscale,dreamplug-003-ds2001", "globalscale,dreamplug", "marvell,kirkwood-88f6281", "marvell,kirkwood";
+	compatible = "globalscale,dreamplug-003-ds2001", "globalscale,dreamplug", "mrvl,kirkwood-88f6281", "mrvl,kirkwood";
 
 	memory {
 		device_type = "memory";
@@ -15,11 +15,10 @@
 		bootargs = "console=ttyS0,115200n8 earlyprintk";
 	};
 
-	serial@f1012000 {
-		compatible = "ns16550a";
-		reg = <0xf1012000 0xff>;
-		reg-shift = <2>;
-		interrupts = <33>;
-		clock-frequency = <200000000>;
+	ocp@f1000000 {
+		serial@12000 {
+			clock-frequency = <200000000>;
+			status = "ok";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/kirkwood.dtsi b/arch/arm/boot/dts/kirkwood.dtsi
index 771c6bbeb29a..3474ef890945 100644
--- a/arch/arm/boot/dts/kirkwood.dtsi
+++ b/arch/arm/boot/dts/kirkwood.dtsi
@@ -1,6 +1,36 @@
 /include/ "skeleton.dtsi"
 
 / {
-	compatible = "marvell,kirkwood";
-};
+	compatible = "mrvl,kirkwood";
+
+	ocp@f1000000 {
+		compatible = "simple-bus";
+		ranges = <0 0xf1000000 0x1000000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		serial@12000 {
+			compatible = "ns16550a";
+			reg = <0x12000 0x100>;
+			reg-shift = <2>;
+			interrupts = <33>;
+			/* set clock-frequency in board dts */
+			status = "disabled";
+		};
 
+		serial@12100 {
+			compatible = "ns16550a";
+			reg = <0x12100 0x100>;
+			reg-shift = <2>;
+			interrupts = <34>;
+			/* set clock-frequency in board dts */
+			status = "disabled";
+		};
+
+		rtc@10300 {
+			compatible = "mrvl,kirkwood-rtc", "mrvl,orion-rtc";
+			reg = <0x10300 0x20>;
+			interrupts = <53>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/snowball.dts b/arch/arm/boot/dts/snowball.dts
new file mode 100644
index 000000000000..359c6d679156
--- /dev/null
+++ b/arch/arm/boot/dts/snowball.dts
@@ -0,0 +1,139 @@
+/*
+ * Copyright 2011 ST-Ericsson AB
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "db8500.dtsi"
+
+/ {
+	model = "Calao Systems Snowball platform with device tree";
+	compatible = "calaosystems,snowball-a9500";
+
+	memory {
+		reg = <0x00000000 0x20000000>;
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		button@1 {
+			debounce_interval = <50>;
+			wakeup = <1>;
+			linux,code = <2>;
+			label = "userpb";
+			gpios = <&gpio1 0>;
+		};
+		button@2 {
+			debounce_interval = <50>;
+			wakeup = <1>;
+			linux,code = <3>;
+			label = "userpb";
+			gpios = <&gpio4 23>;
+		};
+		button@3 {
+			debounce_interval = <50>;
+			wakeup = <1>;
+			linux,code = <4>;
+			label = "userpb";
+			gpios = <&gpio4 23>;
+		};
+		button@4 {
+			debounce_interval = <50>;
+			wakeup = <1>;
+			linux,code = <5>;
+			label = "userpb";
+			gpios = <&gpio5 1>;
+		};
+		button@5 {
+			debounce_interval = <50>;
+			wakeup = <1>;
+			linux,code = <6>;
+			label = "userpb";
+			gpios = <&gpio5 2>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		used-led {
+			label = "user_led";
+			gpios = <&gpio4 14>;
+		};
+	};
+
+	soc-u9500 {
+
+		external-bus@50000000 {
+			compatible = "simple-bus";
+			reg = <0x50000000 0x10000000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			ethernet@50000000 {
+				compatible = "smsc,9111";
+				reg = <0x50000000 0x10000>;
+				interrupts = <12>;
+				interrupt-parent = <&gpio4>;
+			};
+		};
+
+		sdi@80126000 {
+			status = "enabled";
+			cd-gpios = <&gpio6 26>;
+		};
+
+		sdi@80114000 {
+			status = "enabled";
+		};
+
+		uart@80120000 {
+			status = "okay";
+		};
+
+		uart@80121000 {
+			status = "okay";
+		};
+
+		uart@80007000 {
+			status = "okay";
+		};
+
+		i2c@80004000 {
+			tc3589x@42 {
+				//compatible = "tc3589x";
+				reg = <0x42>;
+				interrupts = <25>;
+				interrupt-parent = <&gpio6>;
+			};
+			tps61052@33 {
+				//compatible = "tps61052";
+				reg = <0x33>;
+			};
+		};
+
+		i2c@80128000 {
+			lp5521@0x33 {
+				// compatible = "lp5521";
+				reg = <0x33>;
+			};
+			lp5521@0x34 {
+				// compatible = "lp5521";
+				reg = <0x34>;
+			};
+			bh1780@0x29 {
+				// compatible = "rohm,bh1780gli";
+				reg = <0x33>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/spear600-evb.dts b/arch/arm/boot/dts/spear600-evb.dts
new file mode 100644
index 000000000000..636292e18c90
--- /dev/null
+++ b/arch/arm/boot/dts/spear600-evb.dts
@@ -0,0 +1,47 @@
+/*
+ * Copyright 2012 Stefan Roese <sr@denx.de>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "spear600.dtsi"
+
+/ {
+	model = "ST SPEAr600 Evaluation Board";
+	compatible = "st,spear600-evb", "st,spear600";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	memory {
+		device_type = "memory";
+		reg = <0 0x10000000>;
+	};
+
+	ahb {
+		gmac: ethernet@e0800000 {
+			phy-mode = "gmii";
+			status = "okay";
+		};
+
+		apb {
+			serial@d0000000 {
+				status = "okay";
+			};
+
+			serial@d0080000 {
+				status = "okay";
+			};
+
+			i2c@d0200000 {
+				clock-frequency = <400000>;
+				status = "okay";
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/spear600.dtsi b/arch/arm/boot/dts/spear600.dtsi
new file mode 100644
index 000000000000..ebe0885a2b98
--- /dev/null
+++ b/arch/arm/boot/dts/spear600.dtsi
@@ -0,0 +1,174 @@
+/*
+ * Copyright 2012 Stefan Roese <sr@denx.de>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "st,spear600";
+
+	cpus {
+		cpu@0 {
+			compatible = "arm,arm926ejs";
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0 0x40000000>;
+	};
+
+	ahb {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		ranges = <0xd0000000 0xd0000000 0x30000000>;
+
+		vic0: interrupt-controller@f1100000 {
+			compatible = "arm,pl190-vic";
+			interrupt-controller;
+			reg = <0xf1100000 0x1000>;
+			#interrupt-cells = <1>;
+		};
+
+		vic1: interrupt-controller@f1000000 {
+			compatible = "arm,pl190-vic";
+			interrupt-controller;
+			reg = <0xf1000000 0x1000>;
+			#interrupt-cells = <1>;
+		};
+
+		gmac: ethernet@e0800000 {
+			compatible = "st,spear600-gmac";
+			reg = <0xe0800000 0x8000>;
+			interrupt-parent = <&vic1>;
+			interrupts = <24 23>;
+			interrupt-names = "macirq", "eth_wake_irq";
+			status = "disabled";
+		};
+
+		fsmc: flash@d1800000 {
+			compatible = "st,spear600-fsmc-nand";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0xd1800000 0x1000	/* FSMC Register */
+			       0xd2000000 0x4000>;	/* NAND Base */
+			reg-names = "fsmc_regs", "nand_data";
+			st,ale-off = <0x20000>;
+			st,cle-off = <0x10000>;
+			status = "disabled";
+		};
+
+		smi: flash@fc000000 {
+			compatible = "st,spear600-smi";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0xfc000000 0x1000>;
+			interrupt-parent = <&vic1>;
+			interrupts = <12>;
+			status = "disabled";
+		};
+
+		ehci@e1800000 {
+			compatible = "st,spear600-ehci", "usb-ehci";
+			reg = <0xe1800000 0x1000>;
+			interrupt-parent = <&vic1>;
+			interrupts = <27>;
+			status = "disabled";
+		};
+
+		ehci@e2000000 {
+			compatible = "st,spear600-ehci", "usb-ehci";
+			reg = <0xe2000000 0x1000>;
+			interrupt-parent = <&vic1>;
+			interrupts = <29>;
+			status = "disabled";
+		};
+
+		ohci@e1900000 {
+			compatible = "st,spear600-ohci", "usb-ohci";
+			reg = <0xe1900000 0x1000>;
+			interrupt-parent = <&vic1>;
+			interrupts = <26>;
+			status = "disabled";
+		};
+
+		ohci@e2100000 {
+			compatible = "st,spear600-ohci", "usb-ohci";
+			reg = <0xe2100000 0x1000>;
+			interrupt-parent = <&vic1>;
+			interrupts = <28>;
+			status = "disabled";
+		};
+
+		apb {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "simple-bus";
+			ranges = <0xd0000000 0xd0000000 0x30000000>;
+
+			serial@d0000000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0xd0000000 0x1000>;
+				interrupt-parent = <&vic0>;
+				interrupts = <24>;
+				status = "disabled";
+			};
+
+			serial@d0080000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0xd0080000 0x1000>;
+				interrupt-parent = <&vic0>;
+				interrupts = <25>;
+				status = "disabled";
+			};
+
+			/* local/cpu GPIO */
+			gpio0: gpio@f0100000 {
+				#gpio-cells = <2>;
+				compatible = "arm,pl061", "arm,primecell";
+				gpio-controller;
+				reg = <0xf0100000 0x1000>;
+				interrupt-parent = <&vic0>;
+				interrupts = <18>;
+			};
+
+			/* basic GPIO */
+			gpio1: gpio@fc980000 {
+				#gpio-cells = <2>;
+				compatible = "arm,pl061", "arm,primecell";
+				gpio-controller;
+				reg = <0xfc980000 0x1000>;
+				interrupt-parent = <&vic1>;
+				interrupts = <19>;
+			};
+
+			/* appl GPIO */
+			gpio2: gpio@d8100000 {
+				#gpio-cells = <2>;
+				compatible = "arm,pl061", "arm,primecell";
+				gpio-controller;
+				reg = <0xd8100000 0x1000>;
+				interrupt-parent = <&vic1>;
+				interrupts = <4>;
+			};
+
+			i2c@d0200000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "snps,designware-i2c";
+				reg = <0xd0200000 0x1000>;
+				interrupt-parent = <&vic0>;
+				interrupts = <28>;
+				status = "disabled";
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/tegra-cardhu.dts b/arch/arm/boot/dts/tegra-cardhu.dts
index 73263501f581..ac3fb7558459 100644
--- a/arch/arm/boot/dts/tegra-cardhu.dts
+++ b/arch/arm/boot/dts/tegra-cardhu.dts
@@ -14,6 +14,22 @@
 		clock-frequency = < 408000000 >;
 	};
 
+	serial@70006040 {
+		status = "disable";
+	};
+
+	serial@70006200 {
+		status = "disable";
+	};
+
+	serial@70006300 {
+		status = "disable";
+	};
+
+	serial@70006400 {
+		status = "disable";
+	};
+
 	i2c@7000c000 {
 		clock-frequency = <100000>;
 	};
diff --git a/arch/arm/boot/dts/tegra-seaboard.dts b/arch/arm/boot/dts/tegra-seaboard.dts
index 876d5c92ce36..dbf1c5a171c2 100644
--- a/arch/arm/boot/dts/tegra-seaboard.dts
+++ b/arch/arm/boot/dts/tegra-seaboard.dts
@@ -112,6 +112,7 @@
 
 	usb@c5000000 {
 		nvidia,vbus-gpio = <&gpio 24 0>; /* PD0 */
+		dr_mode = "otg";
 	};
 
 	gpio-keys {
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index aff8a175aa40..108e894a8926 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -190,6 +190,7 @@
 		reg = <0xc5000000 0x4000>;
 		interrupts = < 0 20 0x04 >;
 		phy_type = "utmi";
+		nvidia,has-legacy-mode;
 	};
 
 	usb@c5004000 {
diff --git a/arch/arm/boot/dts/usb_a9g20-dab-mmx.dtsi b/arch/arm/boot/dts/usb_a9g20-dab-mmx.dtsi
new file mode 100644
index 000000000000..ad3eca17c436
--- /dev/null
+++ b/arch/arm/boot/dts/usb_a9g20-dab-mmx.dtsi
@@ -0,0 +1,96 @@
+/*
+ * calao-dab-mmx.dtsi - Device Tree Include file for Calao DAB-MMX Daughter Board
+ *
+ * Copyright (C) 2011 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
+ *
+ * Licensed under GPLv2.
+ */
+
+/ {
+	ahb {
+		apb {
+			usart1: serial@fffb4000 {
+				status = "okay";
+			};
+
+			usart3: serial@fffd0000 {
+				status = "okay";
+			};
+		};
+	};
+
+	i2c-gpio@0 {
+		status = "okay";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		user_led1 {
+			label = "user_led1";
+			gpios = <&pioB 20 1>;
+		};
+
+/*
+* led already used by mother board but active as high
+*		user_led2 {
+*			label = "user_led2";
+*			gpios = <&pioB 21 1>;
+*		};
+*/
+		user_led3 {
+			label = "user_led3";
+			gpios = <&pioB 22 1>;
+		};
+
+		user_led4 {
+			label = "user_led4";
+			gpios = <&pioB 23 1>;
+		};
+
+		red {
+			label = "red";
+			gpios = <&pioB 24 1>;
+		};
+
+		orange {
+			label = "orange";
+			gpios = <&pioB 30 1>;
+		};
+
+		green {
+			label = "green";
+			gpios = <&pioB 31 1>;
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		user_pb1 {
+			label = "user_pb1";
+			gpios = <&pioB 25 1>;
+			linux,code = <0x100>;
+		};
+
+		user_pb2 {
+			label = "user_pb2";
+			gpios = <&pioB 13 1>;
+			linux,code = <0x101>;
+		};
+
+		user_pb3 {
+			label = "user_pb3";
+			gpios = <&pioA 26 1>;
+			linux,code = <0x102>;
+		};
+
+		user_pb4 {
+			label = "user_pb4";
+			gpios = <&pioC 9 1>;
+			linux,code = <0x103>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/usb_a9g20.dts b/arch/arm/boot/dts/usb_a9g20.dts
index d74545a2a77c..7c2399c532e5 100644
--- a/arch/arm/boot/dts/usb_a9g20.dts
+++ b/arch/arm/boot/dts/usb_a9g20.dts
@@ -13,13 +13,24 @@
 	compatible = "calao,usb-a9g20", "atmel,at91sam9g20", "atmel,at91sam9";
 
 	chosen {
-		bootargs = "mem=64M console=ttyS0,115200 mtdparts=atmel_nand:128k(at91bootstrap),256k(barebox)ro,128k(bareboxenv),128k(bareboxenv2),4M(kernel),120M(rootfs),-(data) root=/dev/mtdblock5 rw rootfstype=ubifs";
+		bootargs = "mem=64M console=ttyS0,115200 root=/dev/mtdblock5 rw rootfstype=ubifs";
 	};
 
-	memory@20000000 {
+	memory {
 		reg = <0x20000000 0x4000000>;
 	};
 
+	clocks {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		main_clock: clock@0 {
+			compatible = "atmel,osc", "fixed-clock";
+			clock-frequency = <12000000>;
+		};
+	};
+
 	ahb {
 		apb {
 			dbgu: serial@fffff200 {
@@ -30,6 +41,58 @@
 				phy-mode = "rmii";
 				status = "okay";
 			};
+
+			usb1: gadget@fffa4000 {
+				atmel,vbus-gpio = <&pioC 5 0>;
+				status = "okay";
+			};
+		};
+
+		nand0: nand@40000000 {
+			nand-bus-width = <8>;
+			nand-ecc-mode = "soft";
+			nand-on-flash-bbt;
+			status = "okay";
+
+			at91bootstrap@0 {
+				label = "at91bootstrap";
+				reg = <0x0 0x20000>;
+			};
+
+			barebox@20000 {
+				label = "barebox";
+				reg = <0x20000 0x40000>;
+			};
+
+			bareboxenv@60000 {
+				label = "bareboxenv";
+				reg = <0x60000 0x20000>;
+			};
+
+			bareboxenv2@80000 {
+				label = "bareboxenv2";
+				reg = <0x80000 0x20000>;
+			};
+
+			kernel@a0000 {
+				label = "kernel";
+				reg = <0xa0000 0x400000>;
+			};
+
+			rootfs@4a0000 {
+				label = "rootfs";
+				reg = <0x4a0000 0x7800000>;
+			};
+
+			data@7ca0000 {
+				label = "data";
+				reg = <0x7ca0000 0x8360000>;
+			};
+		};
+
+		usb0: ohci@00500000 {
+			num-ports = <2>;
+			status = "okay";
 		};
 	};
 
@@ -55,4 +118,13 @@
 			gpio-key,wakeup;
 		};
 	};
+
+	i2c@0 {
+		status = "okay";
+
+		rv3029c2@56 {
+			compatible = "rv3029c2";
+			reg = <0x56>;
+		};
+	};
 };
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index 81a933eb0903..283fa1d804f4 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -24,9 +24,6 @@ config ARM_VIC_NR
 config ICST
 	bool
 
-config PL330
-	bool
-
 config SA1111
 	bool
 	select DMABOUNCE if !ARCH_PXA
@@ -35,9 +32,6 @@ config DMABOUNCE
 	bool
 	select ZONE_DMA
 
-config TIMER_ACORN
-	bool
-
 config SHARP_LOCOMO
 	bool
 
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 6ea9b6f3607a..215816f1775f 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -5,11 +5,9 @@
 obj-$(CONFIG_ARM_GIC)		+= gic.o
 obj-$(CONFIG_ARM_VIC)		+= vic.o
 obj-$(CONFIG_ICST)		+= icst.o
-obj-$(CONFIG_PL330)		+= pl330.o
 obj-$(CONFIG_SA1111)		+= sa1111.o
 obj-$(CONFIG_PCI_HOST_VIA82C505) += via82c505.o
 obj-$(CONFIG_DMABOUNCE)		+= dmabounce.o
-obj-$(CONFIG_TIMER_ACORN)	+= time-acorn.o
 obj-$(CONFIG_SHARP_LOCOMO)	+= locomo.o
 obj-$(CONFIG_SHARP_PARAM)	+= sharpsl_param.o
 obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index f0783be17352..aa5269984187 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -686,13 +686,12 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	 * For primary GICs, skip over SGIs.
 	 * For secondary GICs, skip over PPIs, too.
 	 */
-	hwirq_base = 32;
-	if (gic_nr == 0) {
-		if ((irq_start & 31) > 0) {
-			hwirq_base = 16;
-			if (irq_start != -1)
-				irq_start = (irq_start & ~31) + 16;
-		}
+	if (gic_nr == 0 && (irq_start & 31) > 0) {
+		hwirq_base = 16;
+		if (irq_start != -1)
+			irq_start = (irq_start & ~31) + 16;
+	} else {
+		hwirq_base = 32;
 	}
 
 	/*
diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c
deleted file mode 100644
index ff3ad2244824..000000000000
--- a/arch/arm/common/pl330.c
+++ /dev/null
@@ -1,1960 +0,0 @@
-/* linux/arch/arm/common/pl330.c
- *
- * Copyright (C) 2010 Samsung Electronics Co Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-
-#include <asm/hardware/pl330.h>
-
-/* Register and Bit field Definitions */
-#define DS		0x0
-#define DS_ST_STOP	0x0
-#define DS_ST_EXEC	0x1
-#define DS_ST_CMISS	0x2
-#define DS_ST_UPDTPC	0x3
-#define DS_ST_WFE	0x4
-#define DS_ST_ATBRR	0x5
-#define DS_ST_QBUSY	0x6
-#define DS_ST_WFP	0x7
-#define DS_ST_KILL	0x8
-#define DS_ST_CMPLT	0x9
-#define DS_ST_FLTCMP	0xe
-#define DS_ST_FAULT	0xf
-
-#define DPC		0x4
-#define INTEN		0x20
-#define ES		0x24
-#define INTSTATUS	0x28
-#define INTCLR		0x2c
-#define FSM		0x30
-#define FSC		0x34
-#define FTM		0x38
-
-#define _FTC		0x40
-#define FTC(n)		(_FTC + (n)*0x4)
-
-#define _CS		0x100
-#define CS(n)		(_CS + (n)*0x8)
-#define CS_CNS		(1 << 21)
-
-#define _CPC		0x104
-#define CPC(n)		(_CPC + (n)*0x8)
-
-#define _SA		0x400
-#define SA(n)		(_SA + (n)*0x20)
-
-#define _DA		0x404
-#define DA(n)		(_DA + (n)*0x20)
-
-#define _CC		0x408
-#define CC(n)		(_CC + (n)*0x20)
-
-#define CC_SRCINC	(1 << 0)
-#define CC_DSTINC	(1 << 14)
-#define CC_SRCPRI	(1 << 8)
-#define CC_DSTPRI	(1 << 22)
-#define CC_SRCNS	(1 << 9)
-#define CC_DSTNS	(1 << 23)
-#define CC_SRCIA	(1 << 10)
-#define CC_DSTIA	(1 << 24)
-#define CC_SRCBRSTLEN_SHFT	4
-#define CC_DSTBRSTLEN_SHFT	18
-#define CC_SRCBRSTSIZE_SHFT	1
-#define CC_DSTBRSTSIZE_SHFT	15
-#define CC_SRCCCTRL_SHFT	11
-#define CC_SRCCCTRL_MASK	0x7
-#define CC_DSTCCTRL_SHFT	25
-#define CC_DRCCCTRL_MASK	0x7
-#define CC_SWAP_SHFT	28
-
-#define _LC0		0x40c
-#define LC0(n)		(_LC0 + (n)*0x20)
-
-#define _LC1		0x410
-#define LC1(n)		(_LC1 + (n)*0x20)
-
-#define DBGSTATUS	0xd00
-#define DBG_BUSY	(1 << 0)
-
-#define DBGCMD		0xd04
-#define DBGINST0	0xd08
-#define DBGINST1	0xd0c
-
-#define CR0		0xe00
-#define CR1		0xe04
-#define CR2		0xe08
-#define CR3		0xe0c
-#define CR4		0xe10
-#define CRD		0xe14
-
-#define PERIPH_ID	0xfe0
-#define PCELL_ID	0xff0
-
-#define CR0_PERIPH_REQ_SET	(1 << 0)
-#define CR0_BOOT_EN_SET		(1 << 1)
-#define CR0_BOOT_MAN_NS		(1 << 2)
-#define CR0_NUM_CHANS_SHIFT	4
-#define CR0_NUM_CHANS_MASK	0x7
-#define CR0_NUM_PERIPH_SHIFT	12
-#define CR0_NUM_PERIPH_MASK	0x1f
-#define CR0_NUM_EVENTS_SHIFT	17
-#define CR0_NUM_EVENTS_MASK	0x1f
-
-#define CR1_ICACHE_LEN_SHIFT	0
-#define CR1_ICACHE_LEN_MASK	0x7
-#define CR1_NUM_ICACHELINES_SHIFT	4
-#define CR1_NUM_ICACHELINES_MASK	0xf
-
-#define CRD_DATA_WIDTH_SHIFT	0
-#define CRD_DATA_WIDTH_MASK	0x7
-#define CRD_WR_CAP_SHIFT	4
-#define CRD_WR_CAP_MASK		0x7
-#define CRD_WR_Q_DEP_SHIFT	8
-#define CRD_WR_Q_DEP_MASK	0xf
-#define CRD_RD_CAP_SHIFT	12
-#define CRD_RD_CAP_MASK		0x7
-#define CRD_RD_Q_DEP_SHIFT	16
-#define CRD_RD_Q_DEP_MASK	0xf
-#define CRD_DATA_BUFF_SHIFT	20
-#define CRD_DATA_BUFF_MASK	0x3ff
-
-#define	PART		0x330
-#define DESIGNER	0x41
-#define REVISION	0x0
-#define INTEG_CFG	0x0
-#define PERIPH_ID_VAL	((PART << 0) | (DESIGNER << 12))
-
-#define PCELL_ID_VAL	0xb105f00d
-
-#define PL330_STATE_STOPPED		(1 << 0)
-#define PL330_STATE_EXECUTING		(1 << 1)
-#define PL330_STATE_WFE			(1 << 2)
-#define PL330_STATE_FAULTING		(1 << 3)
-#define PL330_STATE_COMPLETING		(1 << 4)
-#define PL330_STATE_WFP			(1 << 5)
-#define PL330_STATE_KILLING		(1 << 6)
-#define PL330_STATE_FAULT_COMPLETING	(1 << 7)
-#define PL330_STATE_CACHEMISS		(1 << 8)
-#define PL330_STATE_UPDTPC		(1 << 9)
-#define PL330_STATE_ATBARRIER		(1 << 10)
-#define PL330_STATE_QUEUEBUSY		(1 << 11)
-#define PL330_STATE_INVALID		(1 << 15)
-
-#define PL330_STABLE_STATES (PL330_STATE_STOPPED | PL330_STATE_EXECUTING \
-				| PL330_STATE_WFE | PL330_STATE_FAULTING)
-
-#define CMD_DMAADDH	0x54
-#define CMD_DMAEND	0x00
-#define CMD_DMAFLUSHP	0x35
-#define CMD_DMAGO	0xa0
-#define CMD_DMALD	0x04
-#define CMD_DMALDP	0x25
-#define CMD_DMALP	0x20
-#define CMD_DMALPEND	0x28
-#define CMD_DMAKILL	0x01
-#define CMD_DMAMOV	0xbc
-#define CMD_DMANOP	0x18
-#define CMD_DMARMB	0x12
-#define CMD_DMASEV	0x34
-#define CMD_DMAST	0x08
-#define CMD_DMASTP	0x29
-#define CMD_DMASTZ	0x0c
-#define CMD_DMAWFE	0x36
-#define CMD_DMAWFP	0x30
-#define CMD_DMAWMB	0x13
-
-#define SZ_DMAADDH	3
-#define SZ_DMAEND	1
-#define SZ_DMAFLUSHP	2
-#define SZ_DMALD	1
-#define SZ_DMALDP	2
-#define SZ_DMALP	2
-#define SZ_DMALPEND	2
-#define SZ_DMAKILL	1
-#define SZ_DMAMOV	6
-#define SZ_DMANOP	1
-#define SZ_DMARMB	1
-#define SZ_DMASEV	2
-#define SZ_DMAST	1
-#define SZ_DMASTP	2
-#define SZ_DMASTZ	1
-#define SZ_DMAWFE	2
-#define SZ_DMAWFP	2
-#define SZ_DMAWMB	1
-#define SZ_DMAGO	6
-
-#define BRST_LEN(ccr)	((((ccr) >> CC_SRCBRSTLEN_SHFT) & 0xf) + 1)
-#define BRST_SIZE(ccr)	(1 << (((ccr) >> CC_SRCBRSTSIZE_SHFT) & 0x7))
-
-#define BYTE_TO_BURST(b, ccr)  ((b) / BRST_SIZE(ccr) / BRST_LEN(ccr))
-#define BURST_TO_BYTE(c, ccr)  ((c) * BRST_SIZE(ccr) * BRST_LEN(ccr))
-
-/*
- * With 256 bytes, we can do more than 2.5MB and 5MB xfers per req
- * at 1byte/burst for P<->M and M<->M respectively.
- * For typical scenario, at 1word/burst, 10MB and 20MB xfers per req
- * should be enough for P<->M and M<->M respectively.
- */
-#define MCODE_BUFF_PER_REQ	256
-
-/* If the _pl330_req is available to the client */
-#define IS_FREE(req)	(*((u8 *)((req)->mc_cpu)) == CMD_DMAEND)
-
-/* Use this _only_ to wait on transient states */
-#define UNTIL(t, s)	while (!(_state(t) & (s))) cpu_relax();
-
-#ifdef PL330_DEBUG_MCGEN
-static unsigned cmd_line;
-#define PL330_DBGCMD_DUMP(off, x...)	do { \
-						printk("%x:", cmd_line); \
-						printk(x); \
-						cmd_line += off; \
-					} while (0)
-#define PL330_DBGMC_START(addr)		(cmd_line = addr)
-#else
-#define PL330_DBGCMD_DUMP(off, x...)	do {} while (0)
-#define PL330_DBGMC_START(addr)		do {} while (0)
-#endif
-
-struct _xfer_spec {
-	u32 ccr;
-	struct pl330_req *r;
-	struct pl330_xfer *x;
-};
-
-enum dmamov_dst {
-	SAR = 0,
-	CCR,
-	DAR,
-};
-
-enum pl330_dst {
-	SRC = 0,
-	DST,
-};
-
-enum pl330_cond {
-	SINGLE,
-	BURST,
-	ALWAYS,
-};
-
-struct _pl330_req {
-	u32 mc_bus;
-	void *mc_cpu;
-	/* Number of bytes taken to setup MC for the req */
-	u32 mc_len;
-	struct pl330_req *r;
-	/* Hook to attach to DMAC's list of reqs with due callback */
-	struct list_head rqd;
-};
-
-/* ToBeDone for tasklet */
-struct _pl330_tbd {
-	bool reset_dmac;
-	bool reset_mngr;
-	u8 reset_chan;
-};
-
-/* A DMAC Thread */
-struct pl330_thread {
-	u8 id;
-	int ev;
-	/* If the channel is not yet acquired by any client */
-	bool free;
-	/* Parent DMAC */
-	struct pl330_dmac *dmac;
-	/* Only two at a time */
-	struct _pl330_req req[2];
-	/* Index of the last enqueued request */
-	unsigned lstenq;
-	/* Index of the last submitted request or -1 if the DMA is stopped */
-	int req_running;
-};
-
-enum pl330_dmac_state {
-	UNINIT,
-	INIT,
-	DYING,
-};
-
-/* A DMAC */
-struct pl330_dmac {
-	spinlock_t		lock;
-	/* Holds list of reqs with due callbacks */
-	struct list_head	req_done;
-	/* Pointer to platform specific stuff */
-	struct pl330_info	*pinfo;
-	/* Maximum possible events/irqs */
-	int			events[32];
-	/* BUS address of MicroCode buffer */
-	u32			mcode_bus;
-	/* CPU address of MicroCode buffer */
-	void			*mcode_cpu;
-	/* List of all Channel threads */
-	struct pl330_thread	*channels;
-	/* Pointer to the MANAGER thread */
-	struct pl330_thread	*manager;
-	/* To handle bad news in interrupt */
-	struct tasklet_struct	tasks;
-	struct _pl330_tbd	dmac_tbd;
-	/* State of DMAC operation */
-	enum pl330_dmac_state	state;
-};
-
-static inline void _callback(struct pl330_req *r, enum pl330_op_err err)
-{
-	if (r && r->xfer_cb)
-		r->xfer_cb(r->token, err);
-}
-
-static inline bool _queue_empty(struct pl330_thread *thrd)
-{
-	return (IS_FREE(&thrd->req[0]) && IS_FREE(&thrd->req[1]))
-		? true : false;
-}
-
-static inline bool _queue_full(struct pl330_thread *thrd)
-{
-	return (IS_FREE(&thrd->req[0]) || IS_FREE(&thrd->req[1]))
-		? false : true;
-}
-
-static inline bool is_manager(struct pl330_thread *thrd)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-
-	/* MANAGER is indexed at the end */
-	if (thrd->id == pl330->pinfo->pcfg.num_chan)
-		return true;
-	else
-		return false;
-}
-
-/* If manager of the thread is in Non-Secure mode */
-static inline bool _manager_ns(struct pl330_thread *thrd)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-
-	return (pl330->pinfo->pcfg.mode & DMAC_MODE_NS) ? true : false;
-}
-
-static inline u32 get_id(struct pl330_info *pi, u32 off)
-{
-	void __iomem *regs = pi->base;
-	u32 id = 0;
-
-	id |= (readb(regs + off + 0x0) << 0);
-	id |= (readb(regs + off + 0x4) << 8);
-	id |= (readb(regs + off + 0x8) << 16);
-	id |= (readb(regs + off + 0xc) << 24);
-
-	return id;
-}
-
-static inline u32 _emit_ADDH(unsigned dry_run, u8 buf[],
-		enum pl330_dst da, u16 val)
-{
-	if (dry_run)
-		return SZ_DMAADDH;
-
-	buf[0] = CMD_DMAADDH;
-	buf[0] |= (da << 1);
-	*((u16 *)&buf[1]) = val;
-
-	PL330_DBGCMD_DUMP(SZ_DMAADDH, "\tDMAADDH %s %u\n",
-		da == 1 ? "DA" : "SA", val);
-
-	return SZ_DMAADDH;
-}
-
-static inline u32 _emit_END(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMAEND;
-
-	buf[0] = CMD_DMAEND;
-
-	PL330_DBGCMD_DUMP(SZ_DMAEND, "\tDMAEND\n");
-
-	return SZ_DMAEND;
-}
-
-static inline u32 _emit_FLUSHP(unsigned dry_run, u8 buf[], u8 peri)
-{
-	if (dry_run)
-		return SZ_DMAFLUSHP;
-
-	buf[0] = CMD_DMAFLUSHP;
-
-	peri &= 0x1f;
-	peri <<= 3;
-	buf[1] = peri;
-
-	PL330_DBGCMD_DUMP(SZ_DMAFLUSHP, "\tDMAFLUSHP %u\n", peri >> 3);
-
-	return SZ_DMAFLUSHP;
-}
-
-static inline u32 _emit_LD(unsigned dry_run, u8 buf[],	enum pl330_cond cond)
-{
-	if (dry_run)
-		return SZ_DMALD;
-
-	buf[0] = CMD_DMALD;
-
-	if (cond == SINGLE)
-		buf[0] |= (0 << 1) | (1 << 0);
-	else if (cond == BURST)
-		buf[0] |= (1 << 1) | (1 << 0);
-
-	PL330_DBGCMD_DUMP(SZ_DMALD, "\tDMALD%c\n",
-		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'));
-
-	return SZ_DMALD;
-}
-
-static inline u32 _emit_LDP(unsigned dry_run, u8 buf[],
-		enum pl330_cond cond, u8 peri)
-{
-	if (dry_run)
-		return SZ_DMALDP;
-
-	buf[0] = CMD_DMALDP;
-
-	if (cond == BURST)
-		buf[0] |= (1 << 1);
-
-	peri &= 0x1f;
-	peri <<= 3;
-	buf[1] = peri;
-
-	PL330_DBGCMD_DUMP(SZ_DMALDP, "\tDMALDP%c %u\n",
-		cond == SINGLE ? 'S' : 'B', peri >> 3);
-
-	return SZ_DMALDP;
-}
-
-static inline u32 _emit_LP(unsigned dry_run, u8 buf[],
-		unsigned loop, u8 cnt)
-{
-	if (dry_run)
-		return SZ_DMALP;
-
-	buf[0] = CMD_DMALP;
-
-	if (loop)
-		buf[0] |= (1 << 1);
-
-	cnt--; /* DMAC increments by 1 internally */
-	buf[1] = cnt;
-
-	PL330_DBGCMD_DUMP(SZ_DMALP, "\tDMALP_%c %u\n", loop ? '1' : '0', cnt);
-
-	return SZ_DMALP;
-}
-
-struct _arg_LPEND {
-	enum pl330_cond cond;
-	bool forever;
-	unsigned loop;
-	u8 bjump;
-};
-
-static inline u32 _emit_LPEND(unsigned dry_run, u8 buf[],
-		const struct _arg_LPEND *arg)
-{
-	enum pl330_cond cond = arg->cond;
-	bool forever = arg->forever;
-	unsigned loop = arg->loop;
-	u8 bjump = arg->bjump;
-
-	if (dry_run)
-		return SZ_DMALPEND;
-
-	buf[0] = CMD_DMALPEND;
-
-	if (loop)
-		buf[0] |= (1 << 2);
-
-	if (!forever)
-		buf[0] |= (1 << 4);
-
-	if (cond == SINGLE)
-		buf[0] |= (0 << 1) | (1 << 0);
-	else if (cond == BURST)
-		buf[0] |= (1 << 1) | (1 << 0);
-
-	buf[1] = bjump;
-
-	PL330_DBGCMD_DUMP(SZ_DMALPEND, "\tDMALP%s%c_%c bjmpto_%x\n",
-			forever ? "FE" : "END",
-			cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'),
-			loop ? '1' : '0',
-			bjump);
-
-	return SZ_DMALPEND;
-}
-
-static inline u32 _emit_KILL(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMAKILL;
-
-	buf[0] = CMD_DMAKILL;
-
-	return SZ_DMAKILL;
-}
-
-static inline u32 _emit_MOV(unsigned dry_run, u8 buf[],
-		enum dmamov_dst dst, u32 val)
-{
-	if (dry_run)
-		return SZ_DMAMOV;
-
-	buf[0] = CMD_DMAMOV;
-	buf[1] = dst;
-	*((u32 *)&buf[2]) = val;
-
-	PL330_DBGCMD_DUMP(SZ_DMAMOV, "\tDMAMOV %s 0x%x\n",
-		dst == SAR ? "SAR" : (dst == DAR ? "DAR" : "CCR"), val);
-
-	return SZ_DMAMOV;
-}
-
-static inline u32 _emit_NOP(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMANOP;
-
-	buf[0] = CMD_DMANOP;
-
-	PL330_DBGCMD_DUMP(SZ_DMANOP, "\tDMANOP\n");
-
-	return SZ_DMANOP;
-}
-
-static inline u32 _emit_RMB(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMARMB;
-
-	buf[0] = CMD_DMARMB;
-
-	PL330_DBGCMD_DUMP(SZ_DMARMB, "\tDMARMB\n");
-
-	return SZ_DMARMB;
-}
-
-static inline u32 _emit_SEV(unsigned dry_run, u8 buf[], u8 ev)
-{
-	if (dry_run)
-		return SZ_DMASEV;
-
-	buf[0] = CMD_DMASEV;
-
-	ev &= 0x1f;
-	ev <<= 3;
-	buf[1] = ev;
-
-	PL330_DBGCMD_DUMP(SZ_DMASEV, "\tDMASEV %u\n", ev >> 3);
-
-	return SZ_DMASEV;
-}
-
-static inline u32 _emit_ST(unsigned dry_run, u8 buf[], enum pl330_cond cond)
-{
-	if (dry_run)
-		return SZ_DMAST;
-
-	buf[0] = CMD_DMAST;
-
-	if (cond == SINGLE)
-		buf[0] |= (0 << 1) | (1 << 0);
-	else if (cond == BURST)
-		buf[0] |= (1 << 1) | (1 << 0);
-
-	PL330_DBGCMD_DUMP(SZ_DMAST, "\tDMAST%c\n",
-		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'));
-
-	return SZ_DMAST;
-}
-
-static inline u32 _emit_STP(unsigned dry_run, u8 buf[],
-		enum pl330_cond cond, u8 peri)
-{
-	if (dry_run)
-		return SZ_DMASTP;
-
-	buf[0] = CMD_DMASTP;
-
-	if (cond == BURST)
-		buf[0] |= (1 << 1);
-
-	peri &= 0x1f;
-	peri <<= 3;
-	buf[1] = peri;
-
-	PL330_DBGCMD_DUMP(SZ_DMASTP, "\tDMASTP%c %u\n",
-		cond == SINGLE ? 'S' : 'B', peri >> 3);
-
-	return SZ_DMASTP;
-}
-
-static inline u32 _emit_STZ(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMASTZ;
-
-	buf[0] = CMD_DMASTZ;
-
-	PL330_DBGCMD_DUMP(SZ_DMASTZ, "\tDMASTZ\n");
-
-	return SZ_DMASTZ;
-}
-
-static inline u32 _emit_WFE(unsigned dry_run, u8 buf[], u8 ev,
-		unsigned invalidate)
-{
-	if (dry_run)
-		return SZ_DMAWFE;
-
-	buf[0] = CMD_DMAWFE;
-
-	ev &= 0x1f;
-	ev <<= 3;
-	buf[1] = ev;
-
-	if (invalidate)
-		buf[1] |= (1 << 1);
-
-	PL330_DBGCMD_DUMP(SZ_DMAWFE, "\tDMAWFE %u%s\n",
-		ev >> 3, invalidate ? ", I" : "");
-
-	return SZ_DMAWFE;
-}
-
-static inline u32 _emit_WFP(unsigned dry_run, u8 buf[],
-		enum pl330_cond cond, u8 peri)
-{
-	if (dry_run)
-		return SZ_DMAWFP;
-
-	buf[0] = CMD_DMAWFP;
-
-	if (cond == SINGLE)
-		buf[0] |= (0 << 1) | (0 << 0);
-	else if (cond == BURST)
-		buf[0] |= (1 << 1) | (0 << 0);
-	else
-		buf[0] |= (0 << 1) | (1 << 0);
-
-	peri &= 0x1f;
-	peri <<= 3;
-	buf[1] = peri;
-
-	PL330_DBGCMD_DUMP(SZ_DMAWFP, "\tDMAWFP%c %u\n",
-		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'P'), peri >> 3);
-
-	return SZ_DMAWFP;
-}
-
-static inline u32 _emit_WMB(unsigned dry_run, u8 buf[])
-{
-	if (dry_run)
-		return SZ_DMAWMB;
-
-	buf[0] = CMD_DMAWMB;
-
-	PL330_DBGCMD_DUMP(SZ_DMAWMB, "\tDMAWMB\n");
-
-	return SZ_DMAWMB;
-}
-
-struct _arg_GO {
-	u8 chan;
-	u32 addr;
-	unsigned ns;
-};
-
-static inline u32 _emit_GO(unsigned dry_run, u8 buf[],
-		const struct _arg_GO *arg)
-{
-	u8 chan = arg->chan;
-	u32 addr = arg->addr;
-	unsigned ns = arg->ns;
-
-	if (dry_run)
-		return SZ_DMAGO;
-
-	buf[0] = CMD_DMAGO;
-	buf[0] |= (ns << 1);
-
-	buf[1] = chan & 0x7;
-
-	*((u32 *)&buf[2]) = addr;
-
-	return SZ_DMAGO;
-}
-
-#define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t)
-
-/* Returns Time-Out */
-static bool _until_dmac_idle(struct pl330_thread *thrd)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	unsigned long loops = msecs_to_loops(5);
-
-	do {
-		/* Until Manager is Idle */
-		if (!(readl(regs + DBGSTATUS) & DBG_BUSY))
-			break;
-
-		cpu_relax();
-	} while (--loops);
-
-	if (!loops)
-		return true;
-
-	return false;
-}
-
-static inline void _execute_DBGINSN(struct pl330_thread *thrd,
-		u8 insn[], bool as_manager)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	u32 val;
-
-	val = (insn[0] << 16) | (insn[1] << 24);
-	if (!as_manager) {
-		val |= (1 << 0);
-		val |= (thrd->id << 8); /* Channel Number */
-	}
-	writel(val, regs + DBGINST0);
-
-	val = *((u32 *)&insn[2]);
-	writel(val, regs + DBGINST1);
-
-	/* If timed out due to halted state-machine */
-	if (_until_dmac_idle(thrd)) {
-		dev_err(thrd->dmac->pinfo->dev, "DMAC halted!\n");
-		return;
-	}
-
-	/* Get going */
-	writel(0, regs + DBGCMD);
-}
-
-/*
- * Mark a _pl330_req as free.
- * We do it by writing DMAEND as the first instruction
- * because no valid request is going to have DMAEND as
- * its first instruction to execute.
- */
-static void mark_free(struct pl330_thread *thrd, int idx)
-{
-	struct _pl330_req *req = &thrd->req[idx];
-
-	_emit_END(0, req->mc_cpu);
-	req->mc_len = 0;
-
-	thrd->req_running = -1;
-}
-
-static inline u32 _state(struct pl330_thread *thrd)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	u32 val;
-
-	if (is_manager(thrd))
-		val = readl(regs + DS) & 0xf;
-	else
-		val = readl(regs + CS(thrd->id)) & 0xf;
-
-	switch (val) {
-	case DS_ST_STOP:
-		return PL330_STATE_STOPPED;
-	case DS_ST_EXEC:
-		return PL330_STATE_EXECUTING;
-	case DS_ST_CMISS:
-		return PL330_STATE_CACHEMISS;
-	case DS_ST_UPDTPC:
-		return PL330_STATE_UPDTPC;
-	case DS_ST_WFE:
-		return PL330_STATE_WFE;
-	case DS_ST_FAULT:
-		return PL330_STATE_FAULTING;
-	case DS_ST_ATBRR:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_ATBARRIER;
-	case DS_ST_QBUSY:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_QUEUEBUSY;
-	case DS_ST_WFP:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_WFP;
-	case DS_ST_KILL:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_KILLING;
-	case DS_ST_CMPLT:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_COMPLETING;
-	case DS_ST_FLTCMP:
-		if (is_manager(thrd))
-			return PL330_STATE_INVALID;
-		else
-			return PL330_STATE_FAULT_COMPLETING;
-	default:
-		return PL330_STATE_INVALID;
-	}
-}
-
-static void _stop(struct pl330_thread *thrd)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	u8 insn[6] = {0, 0, 0, 0, 0, 0};
-
-	if (_state(thrd) == PL330_STATE_FAULT_COMPLETING)
-		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
-
-	/* Return if nothing needs to be done */
-	if (_state(thrd) == PL330_STATE_COMPLETING
-		  || _state(thrd) == PL330_STATE_KILLING
-		  || _state(thrd) == PL330_STATE_STOPPED)
-		return;
-
-	_emit_KILL(0, insn);
-
-	/* Stop generating interrupts for SEV */
-	writel(readl(regs + INTEN) & ~(1 << thrd->ev), regs + INTEN);
-
-	_execute_DBGINSN(thrd, insn, is_manager(thrd));
-}
-
-/* Start doing req 'idx' of thread 'thrd' */
-static bool _trigger(struct pl330_thread *thrd)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	struct _pl330_req *req;
-	struct pl330_req *r;
-	struct _arg_GO go;
-	unsigned ns;
-	u8 insn[6] = {0, 0, 0, 0, 0, 0};
-	int idx;
-
-	/* Return if already ACTIVE */
-	if (_state(thrd) != PL330_STATE_STOPPED)
-		return true;
-
-	idx = 1 - thrd->lstenq;
-	if (!IS_FREE(&thrd->req[idx]))
-		req = &thrd->req[idx];
-	else {
-		idx = thrd->lstenq;
-		if (!IS_FREE(&thrd->req[idx]))
-			req = &thrd->req[idx];
-		else
-			req = NULL;
-	}
-
-	/* Return if no request */
-	if (!req || !req->r)
-		return true;
-
-	r = req->r;
-
-	if (r->cfg)
-		ns = r->cfg->nonsecure ? 1 : 0;
-	else if (readl(regs + CS(thrd->id)) & CS_CNS)
-		ns = 1;
-	else
-		ns = 0;
-
-	/* See 'Abort Sources' point-4 at Page 2-25 */
-	if (_manager_ns(thrd) && !ns)
-		dev_info(thrd->dmac->pinfo->dev, "%s:%d Recipe for ABORT!\n",
-			__func__, __LINE__);
-
-	go.chan = thrd->id;
-	go.addr = req->mc_bus;
-	go.ns = ns;
-	_emit_GO(0, insn, &go);
-
-	/* Set to generate interrupts for SEV */
-	writel(readl(regs + INTEN) | (1 << thrd->ev), regs + INTEN);
-
-	/* Only manager can execute GO */
-	_execute_DBGINSN(thrd, insn, true);
-
-	thrd->req_running = idx;
-
-	return true;
-}
-
-static bool _start(struct pl330_thread *thrd)
-{
-	switch (_state(thrd)) {
-	case PL330_STATE_FAULT_COMPLETING:
-		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
-
-		if (_state(thrd) == PL330_STATE_KILLING)
-			UNTIL(thrd, PL330_STATE_STOPPED)
-
-	case PL330_STATE_FAULTING:
-		_stop(thrd);
-
-	case PL330_STATE_KILLING:
-	case PL330_STATE_COMPLETING:
-		UNTIL(thrd, PL330_STATE_STOPPED)
-
-	case PL330_STATE_STOPPED:
-		return _trigger(thrd);
-
-	case PL330_STATE_WFP:
-	case PL330_STATE_QUEUEBUSY:
-	case PL330_STATE_ATBARRIER:
-	case PL330_STATE_UPDTPC:
-	case PL330_STATE_CACHEMISS:
-	case PL330_STATE_EXECUTING:
-		return true;
-
-	case PL330_STATE_WFE: /* For RESUME, nothing yet */
-	default:
-		return false;
-	}
-}
-
-static inline int _ldst_memtomem(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
-{
-	int off = 0;
-
-	while (cyc--) {
-		off += _emit_LD(dry_run, &buf[off], ALWAYS);
-		off += _emit_RMB(dry_run, &buf[off]);
-		off += _emit_ST(dry_run, &buf[off], ALWAYS);
-		off += _emit_WMB(dry_run, &buf[off]);
-	}
-
-	return off;
-}
-
-static inline int _ldst_devtomem(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
-{
-	int off = 0;
-
-	while (cyc--) {
-		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri);
-		off += _emit_LDP(dry_run, &buf[off], SINGLE, pxs->r->peri);
-		off += _emit_ST(dry_run, &buf[off], ALWAYS);
-		off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri);
-	}
-
-	return off;
-}
-
-static inline int _ldst_memtodev(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
-{
-	int off = 0;
-
-	while (cyc--) {
-		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri);
-		off += _emit_LD(dry_run, &buf[off], ALWAYS);
-		off += _emit_STP(dry_run, &buf[off], SINGLE, pxs->r->peri);
-		off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri);
-	}
-
-	return off;
-}
-
-static int _bursts(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
-{
-	int off = 0;
-
-	switch (pxs->r->rqtype) {
-	case MEMTODEV:
-		off += _ldst_memtodev(dry_run, &buf[off], pxs, cyc);
-		break;
-	case DEVTOMEM:
-		off += _ldst_devtomem(dry_run, &buf[off], pxs, cyc);
-		break;
-	case MEMTOMEM:
-		off += _ldst_memtomem(dry_run, &buf[off], pxs, cyc);
-		break;
-	default:
-		off += 0x40000000; /* Scare off the Client */
-		break;
-	}
-
-	return off;
-}
-
-/* Returns bytes consumed and updates bursts */
-static inline int _loop(unsigned dry_run, u8 buf[],
-		unsigned long *bursts, const struct _xfer_spec *pxs)
-{
-	int cyc, cycmax, szlp, szlpend, szbrst, off;
-	unsigned lcnt0, lcnt1, ljmp0, ljmp1;
-	struct _arg_LPEND lpend;
-
-	/* Max iterations possible in DMALP is 256 */
-	if (*bursts >= 256*256) {
-		lcnt1 = 256;
-		lcnt0 = 256;
-		cyc = *bursts / lcnt1 / lcnt0;
-	} else if (*bursts > 256) {
-		lcnt1 = 256;
-		lcnt0 = *bursts / lcnt1;
-		cyc = 1;
-	} else {
-		lcnt1 = *bursts;
-		lcnt0 = 0;
-		cyc = 1;
-	}
-
-	szlp = _emit_LP(1, buf, 0, 0);
-	szbrst = _bursts(1, buf, pxs, 1);
-
-	lpend.cond = ALWAYS;
-	lpend.forever = false;
-	lpend.loop = 0;
-	lpend.bjump = 0;
-	szlpend = _emit_LPEND(1, buf, &lpend);
-
-	if (lcnt0) {
-		szlp *= 2;
-		szlpend *= 2;
-	}
-
-	/*
-	 * Max bursts that we can unroll due to limit on the
-	 * size of backward jump that can be encoded in DMALPEND
-	 * which is 8-bits and hence 255
-	 */
-	cycmax = (255 - (szlp + szlpend)) / szbrst;
-
-	cyc = (cycmax < cyc) ? cycmax : cyc;
-
-	off = 0;
-
-	if (lcnt0) {
-		off += _emit_LP(dry_run, &buf[off], 0, lcnt0);
-		ljmp0 = off;
-	}
-
-	off += _emit_LP(dry_run, &buf[off], 1, lcnt1);
-	ljmp1 = off;
-
-	off += _bursts(dry_run, &buf[off], pxs, cyc);
-
-	lpend.cond = ALWAYS;
-	lpend.forever = false;
-	lpend.loop = 1;
-	lpend.bjump = off - ljmp1;
-	off += _emit_LPEND(dry_run, &buf[off], &lpend);
-
-	if (lcnt0) {
-		lpend.cond = ALWAYS;
-		lpend.forever = false;
-		lpend.loop = 0;
-		lpend.bjump = off - ljmp0;
-		off += _emit_LPEND(dry_run, &buf[off], &lpend);
-	}
-
-	*bursts = lcnt1 * cyc;
-	if (lcnt0)
-		*bursts *= lcnt0;
-
-	return off;
-}
-
-static inline int _setup_loops(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs)
-{
-	struct pl330_xfer *x = pxs->x;
-	u32 ccr = pxs->ccr;
-	unsigned long c, bursts = BYTE_TO_BURST(x->bytes, ccr);
-	int off = 0;
-
-	while (bursts) {
-		c = bursts;
-		off += _loop(dry_run, &buf[off], &c, pxs);
-		bursts -= c;
-	}
-
-	return off;
-}
-
-static inline int _setup_xfer(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs)
-{
-	struct pl330_xfer *x = pxs->x;
-	int off = 0;
-
-	/* DMAMOV SAR, x->src_addr */
-	off += _emit_MOV(dry_run, &buf[off], SAR, x->src_addr);
-	/* DMAMOV DAR, x->dst_addr */
-	off += _emit_MOV(dry_run, &buf[off], DAR, x->dst_addr);
-
-	/* Setup Loop(s) */
-	off += _setup_loops(dry_run, &buf[off], pxs);
-
-	return off;
-}
-
-/*
- * A req is a sequence of one or more xfer units.
- * Returns the number of bytes taken to setup the MC for the req.
- */
-static int _setup_req(unsigned dry_run, struct pl330_thread *thrd,
-		unsigned index, struct _xfer_spec *pxs)
-{
-	struct _pl330_req *req = &thrd->req[index];
-	struct pl330_xfer *x;
-	u8 *buf = req->mc_cpu;
-	int off = 0;
-
-	PL330_DBGMC_START(req->mc_bus);
-
-	/* DMAMOV CCR, ccr */
-	off += _emit_MOV(dry_run, &buf[off], CCR, pxs->ccr);
-
-	x = pxs->r->x;
-	do {
-		/* Error if xfer length is not aligned at burst size */
-		if (x->bytes % (BRST_SIZE(pxs->ccr) * BRST_LEN(pxs->ccr)))
-			return -EINVAL;
-
-		pxs->x = x;
-		off += _setup_xfer(dry_run, &buf[off], pxs);
-
-		x = x->next;
-	} while (x);
-
-	/* DMASEV peripheral/event */
-	off += _emit_SEV(dry_run, &buf[off], thrd->ev);
-	/* DMAEND */
-	off += _emit_END(dry_run, &buf[off]);
-
-	return off;
-}
-
-static inline u32 _prepare_ccr(const struct pl330_reqcfg *rqc)
-{
-	u32 ccr = 0;
-
-	if (rqc->src_inc)
-		ccr |= CC_SRCINC;
-
-	if (rqc->dst_inc)
-		ccr |= CC_DSTINC;
-
-	/* We set same protection levels for Src and DST for now */
-	if (rqc->privileged)
-		ccr |= CC_SRCPRI | CC_DSTPRI;
-	if (rqc->nonsecure)
-		ccr |= CC_SRCNS | CC_DSTNS;
-	if (rqc->insnaccess)
-		ccr |= CC_SRCIA | CC_DSTIA;
-
-	ccr |= (((rqc->brst_len - 1) & 0xf) << CC_SRCBRSTLEN_SHFT);
-	ccr |= (((rqc->brst_len - 1) & 0xf) << CC_DSTBRSTLEN_SHFT);
-
-	ccr |= (rqc->brst_size << CC_SRCBRSTSIZE_SHFT);
-	ccr |= (rqc->brst_size << CC_DSTBRSTSIZE_SHFT);
-
-	ccr |= (rqc->scctl << CC_SRCCCTRL_SHFT);
-	ccr |= (rqc->dcctl << CC_DSTCCTRL_SHFT);
-
-	ccr |= (rqc->swap << CC_SWAP_SHFT);
-
-	return ccr;
-}
-
-static inline bool _is_valid(u32 ccr)
-{
-	enum pl330_dstcachectrl dcctl;
-	enum pl330_srccachectrl scctl;
-
-	dcctl = (ccr >> CC_DSTCCTRL_SHFT) & CC_DRCCCTRL_MASK;
-	scctl = (ccr >> CC_SRCCCTRL_SHFT) & CC_SRCCCTRL_MASK;
-
-	if (dcctl == DINVALID1 || dcctl == DINVALID2
-			|| scctl == SINVALID1 || scctl == SINVALID2)
-		return false;
-	else
-		return true;
-}
-
-/*
- * Submit a list of xfers after which the client wants notification.
- * Client is not notified after each xfer unit, just once after all
- * xfer units are done or some error occurs.
- */
-int pl330_submit_req(void *ch_id, struct pl330_req *r)
-{
-	struct pl330_thread *thrd = ch_id;
-	struct pl330_dmac *pl330;
-	struct pl330_info *pi;
-	struct _xfer_spec xs;
-	unsigned long flags;
-	void __iomem *regs;
-	unsigned idx;
-	u32 ccr;
-	int ret = 0;
-
-	/* No Req or Unacquired Channel or DMAC */
-	if (!r || !thrd || thrd->free)
-		return -EINVAL;
-
-	pl330 = thrd->dmac;
-	pi = pl330->pinfo;
-	regs = pi->base;
-
-	if (pl330->state == DYING
-		|| pl330->dmac_tbd.reset_chan & (1 << thrd->id)) {
-		dev_info(thrd->dmac->pinfo->dev, "%s:%d\n",
-			__func__, __LINE__);
-		return -EAGAIN;
-	}
-
-	/* If request for non-existing peripheral */
-	if (r->rqtype != MEMTOMEM && r->peri >= pi->pcfg.num_peri) {
-		dev_info(thrd->dmac->pinfo->dev,
-				"%s:%d Invalid peripheral(%u)!\n",
-				__func__, __LINE__, r->peri);
-		return -EINVAL;
-	}
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	if (_queue_full(thrd)) {
-		ret = -EAGAIN;
-		goto xfer_exit;
-	}
-
-	/* Prefer Secure Channel */
-	if (!_manager_ns(thrd))
-		r->cfg->nonsecure = 0;
-	else
-		r->cfg->nonsecure = 1;
-
-	/* Use last settings, if not provided */
-	if (r->cfg)
-		ccr = _prepare_ccr(r->cfg);
-	else
-		ccr = readl(regs + CC(thrd->id));
-
-	/* If this req doesn't have valid xfer settings */
-	if (!_is_valid(ccr)) {
-		ret = -EINVAL;
-		dev_info(thrd->dmac->pinfo->dev, "%s:%d Invalid CCR(%x)!\n",
-			__func__, __LINE__, ccr);
-		goto xfer_exit;
-	}
-
-	idx = IS_FREE(&thrd->req[0]) ? 0 : 1;
-
-	xs.ccr = ccr;
-	xs.r = r;
-
-	/* First dry run to check if req is acceptable */
-	ret = _setup_req(1, thrd, idx, &xs);
-	if (ret < 0)
-		goto xfer_exit;
-
-	if (ret > pi->mcbufsz / 2) {
-		dev_info(thrd->dmac->pinfo->dev,
-			"%s:%d Trying increasing mcbufsz\n",
-				__func__, __LINE__);
-		ret = -ENOMEM;
-		goto xfer_exit;
-	}
-
-	/* Hook the request */
-	thrd->lstenq = idx;
-	thrd->req[idx].mc_len = _setup_req(0, thrd, idx, &xs);
-	thrd->req[idx].r = r;
-
-	ret = 0;
-
-xfer_exit:
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
-	return ret;
-}
-EXPORT_SYMBOL(pl330_submit_req);
-
-static void pl330_dotask(unsigned long data)
-{
-	struct pl330_dmac *pl330 = (struct pl330_dmac *) data;
-	struct pl330_info *pi = pl330->pinfo;
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	/* The DMAC itself gone nuts */
-	if (pl330->dmac_tbd.reset_dmac) {
-		pl330->state = DYING;
-		/* Reset the manager too */
-		pl330->dmac_tbd.reset_mngr = true;
-		/* Clear the reset flag */
-		pl330->dmac_tbd.reset_dmac = false;
-	}
-
-	if (pl330->dmac_tbd.reset_mngr) {
-		_stop(pl330->manager);
-		/* Reset all channels */
-		pl330->dmac_tbd.reset_chan = (1 << pi->pcfg.num_chan) - 1;
-		/* Clear the reset flag */
-		pl330->dmac_tbd.reset_mngr = false;
-	}
-
-	for (i = 0; i < pi->pcfg.num_chan; i++) {
-
-		if (pl330->dmac_tbd.reset_chan & (1 << i)) {
-			struct pl330_thread *thrd = &pl330->channels[i];
-			void __iomem *regs = pi->base;
-			enum pl330_op_err err;
-
-			_stop(thrd);
-
-			if (readl(regs + FSC) & (1 << thrd->id))
-				err = PL330_ERR_FAIL;
-			else
-				err = PL330_ERR_ABORT;
-
-			spin_unlock_irqrestore(&pl330->lock, flags);
-
-			_callback(thrd->req[1 - thrd->lstenq].r, err);
-			_callback(thrd->req[thrd->lstenq].r, err);
-
-			spin_lock_irqsave(&pl330->lock, flags);
-
-			thrd->req[0].r = NULL;
-			thrd->req[1].r = NULL;
-			mark_free(thrd, 0);
-			mark_free(thrd, 1);
-
-			/* Clear the reset flag */
-			pl330->dmac_tbd.reset_chan &= ~(1 << i);
-		}
-	}
-
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
-	return;
-}
-
-/* Returns 1 if state was updated, 0 otherwise */
-int pl330_update(const struct pl330_info *pi)
-{
-	struct _pl330_req *rqdone;
-	struct pl330_dmac *pl330;
-	unsigned long flags;
-	void __iomem *regs;
-	u32 val;
-	int id, ev, ret = 0;
-
-	if (!pi || !pi->pl330_data)
-		return 0;
-
-	regs = pi->base;
-	pl330 = pi->pl330_data;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	val = readl(regs + FSM) & 0x1;
-	if (val)
-		pl330->dmac_tbd.reset_mngr = true;
-	else
-		pl330->dmac_tbd.reset_mngr = false;
-
-	val = readl(regs + FSC) & ((1 << pi->pcfg.num_chan) - 1);
-	pl330->dmac_tbd.reset_chan |= val;
-	if (val) {
-		int i = 0;
-		while (i < pi->pcfg.num_chan) {
-			if (val & (1 << i)) {
-				dev_info(pi->dev,
-					"Reset Channel-%d\t CS-%x FTC-%x\n",
-						i, readl(regs + CS(i)),
-						readl(regs + FTC(i)));
-				_stop(&pl330->channels[i]);
-			}
-			i++;
-		}
-	}
-
-	/* Check which event happened i.e, thread notified */
-	val = readl(regs + ES);
-	if (pi->pcfg.num_events < 32
-			&& val & ~((1 << pi->pcfg.num_events) - 1)) {
-		pl330->dmac_tbd.reset_dmac = true;
-		dev_err(pi->dev, "%s:%d Unexpected!\n", __func__, __LINE__);
-		ret = 1;
-		goto updt_exit;
-	}
-
-	for (ev = 0; ev < pi->pcfg.num_events; ev++) {
-		if (val & (1 << ev)) { /* Event occurred */
-			struct pl330_thread *thrd;
-			u32 inten = readl(regs + INTEN);
-			int active;
-
-			/* Clear the event */
-			if (inten & (1 << ev))
-				writel(1 << ev, regs + INTCLR);
-
-			ret = 1;
-
-			id = pl330->events[ev];
-
-			thrd = &pl330->channels[id];
-
-			active = thrd->req_running;
-			if (active == -1) /* Aborted */
-				continue;
-
-			rqdone = &thrd->req[active];
-			mark_free(thrd, active);
-
-			/* Get going again ASAP */
-			_start(thrd);
-
-			/* For now, just make a list of callbacks to be done */
-			list_add_tail(&rqdone->rqd, &pl330->req_done);
-		}
-	}
-
-	/* Now that we are in no hurry, do the callbacks */
-	while (!list_empty(&pl330->req_done)) {
-		struct pl330_req *r;
-
-		rqdone = container_of(pl330->req_done.next,
-					struct _pl330_req, rqd);
-
-		list_del_init(&rqdone->rqd);
-
-		/* Detach the req */
-		r = rqdone->r;
-		rqdone->r = NULL;
-
-		spin_unlock_irqrestore(&pl330->lock, flags);
-		_callback(r, PL330_ERR_NONE);
-		spin_lock_irqsave(&pl330->lock, flags);
-	}
-
-updt_exit:
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
-	if (pl330->dmac_tbd.reset_dmac
-			|| pl330->dmac_tbd.reset_mngr
-			|| pl330->dmac_tbd.reset_chan) {
-		ret = 1;
-		tasklet_schedule(&pl330->tasks);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(pl330_update);
-
-int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
-{
-	struct pl330_thread *thrd = ch_id;
-	struct pl330_dmac *pl330;
-	unsigned long flags;
-	int ret = 0, active;
-
-	if (!thrd || thrd->free || thrd->dmac->state == DYING)
-		return -EINVAL;
-
-	pl330 = thrd->dmac;
-	active = thrd->req_running;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	switch (op) {
-	case PL330_OP_FLUSH:
-		/* Make sure the channel is stopped */
-		_stop(thrd);
-
-		thrd->req[0].r = NULL;
-		thrd->req[1].r = NULL;
-		mark_free(thrd, 0);
-		mark_free(thrd, 1);
-		break;
-
-	case PL330_OP_ABORT:
-		/* Make sure the channel is stopped */
-		_stop(thrd);
-
-		/* ABORT is only for the active req */
-		if (active == -1)
-			break;
-
-		thrd->req[active].r = NULL;
-		mark_free(thrd, active);
-
-		/* Start the next */
-	case PL330_OP_START:
-		if ((active == -1) && !_start(thrd))
-			ret = -EIO;
-		break;
-
-	default:
-		ret = -EINVAL;
-	}
-
-	spin_unlock_irqrestore(&pl330->lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(pl330_chan_ctrl);
-
-int pl330_chan_status(void *ch_id, struct pl330_chanstatus *pstatus)
-{
-	struct pl330_thread *thrd = ch_id;
-	struct pl330_dmac *pl330;
-	struct pl330_info *pi;
-	void __iomem *regs;
-	int active;
-	u32 val;
-
-	if (!pstatus || !thrd || thrd->free)
-		return -EINVAL;
-
-	pl330 = thrd->dmac;
-	pi = pl330->pinfo;
-	regs = pi->base;
-
-	/* The client should remove the DMAC and add again */
-	if (pl330->state == DYING)
-		pstatus->dmac_halted = true;
-	else
-		pstatus->dmac_halted = false;
-
-	val = readl(regs + FSC);
-	if (val & (1 << thrd->id))
-		pstatus->faulting = true;
-	else
-		pstatus->faulting = false;
-
-	active = thrd->req_running;
-
-	if (active == -1) {
-		/* Indicate that the thread is not running */
-		pstatus->top_req = NULL;
-		pstatus->wait_req = NULL;
-	} else {
-		pstatus->top_req = thrd->req[active].r;
-		pstatus->wait_req = !IS_FREE(&thrd->req[1 - active])
-					? thrd->req[1 - active].r : NULL;
-	}
-
-	pstatus->src_addr = readl(regs + SA(thrd->id));
-	pstatus->dst_addr = readl(regs + DA(thrd->id));
-
-	return 0;
-}
-EXPORT_SYMBOL(pl330_chan_status);
-
-/* Reserve an event */
-static inline int _alloc_event(struct pl330_thread *thrd)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-	struct pl330_info *pi = pl330->pinfo;
-	int ev;
-
-	for (ev = 0; ev < pi->pcfg.num_events; ev++)
-		if (pl330->events[ev] == -1) {
-			pl330->events[ev] = thrd->id;
-			return ev;
-		}
-
-	return -1;
-}
-
-static bool _chan_ns(const struct pl330_info *pi, int i)
-{
-	return pi->pcfg.irq_ns & (1 << i);
-}
-
-/* Upon success, returns IdentityToken for the
- * allocated channel, NULL otherwise.
- */
-void *pl330_request_channel(const struct pl330_info *pi)
-{
-	struct pl330_thread *thrd = NULL;
-	struct pl330_dmac *pl330;
-	unsigned long flags;
-	int chans, i;
-
-	if (!pi || !pi->pl330_data)
-		return NULL;
-
-	pl330 = pi->pl330_data;
-
-	if (pl330->state == DYING)
-		return NULL;
-
-	chans = pi->pcfg.num_chan;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-
-	for (i = 0; i < chans; i++) {
-		thrd = &pl330->channels[i];
-		if ((thrd->free) && (!_manager_ns(thrd) ||
-					_chan_ns(pi, i))) {
-			thrd->ev = _alloc_event(thrd);
-			if (thrd->ev >= 0) {
-				thrd->free = false;
-				thrd->lstenq = 1;
-				thrd->req[0].r = NULL;
-				mark_free(thrd, 0);
-				thrd->req[1].r = NULL;
-				mark_free(thrd, 1);
-				break;
-			}
-		}
-		thrd = NULL;
-	}
-
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
-	return thrd;
-}
-EXPORT_SYMBOL(pl330_request_channel);
-
-/* Release an event */
-static inline void _free_event(struct pl330_thread *thrd, int ev)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-	struct pl330_info *pi = pl330->pinfo;
-
-	/* If the event is valid and was held by the thread */
-	if (ev >= 0 && ev < pi->pcfg.num_events
-			&& pl330->events[ev] == thrd->id)
-		pl330->events[ev] = -1;
-}
-
-void pl330_release_channel(void *ch_id)
-{
-	struct pl330_thread *thrd = ch_id;
-	struct pl330_dmac *pl330;
-	unsigned long flags;
-
-	if (!thrd || thrd->free)
-		return;
-
-	_stop(thrd);
-
-	_callback(thrd->req[1 - thrd->lstenq].r, PL330_ERR_ABORT);
-	_callback(thrd->req[thrd->lstenq].r, PL330_ERR_ABORT);
-
-	pl330 = thrd->dmac;
-
-	spin_lock_irqsave(&pl330->lock, flags);
-	_free_event(thrd, thrd->ev);
-	thrd->free = true;
-	spin_unlock_irqrestore(&pl330->lock, flags);
-}
-EXPORT_SYMBOL(pl330_release_channel);
-
-/* Initialize the structure for PL330 configuration, that can be used
- * by the client driver the make best use of the DMAC
- */
-static void read_dmac_config(struct pl330_info *pi)
-{
-	void __iomem *regs = pi->base;
-	u32 val;
-
-	val = readl(regs + CRD) >> CRD_DATA_WIDTH_SHIFT;
-	val &= CRD_DATA_WIDTH_MASK;
-	pi->pcfg.data_bus_width = 8 * (1 << val);
-
-	val = readl(regs + CRD) >> CRD_DATA_BUFF_SHIFT;
-	val &= CRD_DATA_BUFF_MASK;
-	pi->pcfg.data_buf_dep = val + 1;
-
-	val = readl(regs + CR0) >> CR0_NUM_CHANS_SHIFT;
-	val &= CR0_NUM_CHANS_MASK;
-	val += 1;
-	pi->pcfg.num_chan = val;
-
-	val = readl(regs + CR0);
-	if (val & CR0_PERIPH_REQ_SET) {
-		val = (val >> CR0_NUM_PERIPH_SHIFT) & CR0_NUM_PERIPH_MASK;
-		val += 1;
-		pi->pcfg.num_peri = val;
-		pi->pcfg.peri_ns = readl(regs + CR4);
-	} else {
-		pi->pcfg.num_peri = 0;
-	}
-
-	val = readl(regs + CR0);
-	if (val & CR0_BOOT_MAN_NS)
-		pi->pcfg.mode |= DMAC_MODE_NS;
-	else
-		pi->pcfg.mode &= ~DMAC_MODE_NS;
-
-	val = readl(regs + CR0) >> CR0_NUM_EVENTS_SHIFT;
-	val &= CR0_NUM_EVENTS_MASK;
-	val += 1;
-	pi->pcfg.num_events = val;
-
-	pi->pcfg.irq_ns = readl(regs + CR3);
-
-	pi->pcfg.periph_id = get_id(pi, PERIPH_ID);
-	pi->pcfg.pcell_id = get_id(pi, PCELL_ID);
-}
-
-static inline void _reset_thread(struct pl330_thread *thrd)
-{
-	struct pl330_dmac *pl330 = thrd->dmac;
-	struct pl330_info *pi = pl330->pinfo;
-
-	thrd->req[0].mc_cpu = pl330->mcode_cpu
-				+ (thrd->id * pi->mcbufsz);
-	thrd->req[0].mc_bus = pl330->mcode_bus
-				+ (thrd->id * pi->mcbufsz);
-	thrd->req[0].r = NULL;
-	mark_free(thrd, 0);
-
-	thrd->req[1].mc_cpu = thrd->req[0].mc_cpu
-				+ pi->mcbufsz / 2;
-	thrd->req[1].mc_bus = thrd->req[0].mc_bus
-				+ pi->mcbufsz / 2;
-	thrd->req[1].r = NULL;
-	mark_free(thrd, 1);
-}
-
-static int dmac_alloc_threads(struct pl330_dmac *pl330)
-{
-	struct pl330_info *pi = pl330->pinfo;
-	int chans = pi->pcfg.num_chan;
-	struct pl330_thread *thrd;
-	int i;
-
-	/* Allocate 1 Manager and 'chans' Channel threads */
-	pl330->channels = kzalloc((1 + chans) * sizeof(*thrd),
-					GFP_KERNEL);
-	if (!pl330->channels)
-		return -ENOMEM;
-
-	/* Init Channel threads */
-	for (i = 0; i < chans; i++) {
-		thrd = &pl330->channels[i];
-		thrd->id = i;
-		thrd->dmac = pl330;
-		_reset_thread(thrd);
-		thrd->free = true;
-	}
-
-	/* MANAGER is indexed at the end */
-	thrd = &pl330->channels[chans];
-	thrd->id = chans;
-	thrd->dmac = pl330;
-	thrd->free = false;
-	pl330->manager = thrd;
-
-	return 0;
-}
-
-static int dmac_alloc_resources(struct pl330_dmac *pl330)
-{
-	struct pl330_info *pi = pl330->pinfo;
-	int chans = pi->pcfg.num_chan;
-	int ret;
-
-	/*
-	 * Alloc MicroCode buffer for 'chans' Channel threads.
-	 * A channel's buffer offset is (Channel_Id * MCODE_BUFF_PERCHAN)
-	 */
-	pl330->mcode_cpu = dma_alloc_coherent(pi->dev,
-				chans * pi->mcbufsz,
-				&pl330->mcode_bus, GFP_KERNEL);
-	if (!pl330->mcode_cpu) {
-		dev_err(pi->dev, "%s:%d Can't allocate memory!\n",
-			__func__, __LINE__);
-		return -ENOMEM;
-	}
-
-	ret = dmac_alloc_threads(pl330);
-	if (ret) {
-		dev_err(pi->dev, "%s:%d Can't to create channels for DMAC!\n",
-			__func__, __LINE__);
-		dma_free_coherent(pi->dev,
-				chans * pi->mcbufsz,
-				pl330->mcode_cpu, pl330->mcode_bus);
-		return ret;
-	}
-
-	return 0;
-}
-
-int pl330_add(struct pl330_info *pi)
-{
-	struct pl330_dmac *pl330;
-	void __iomem *regs;
-	int i, ret;
-
-	if (!pi || !pi->dev)
-		return -EINVAL;
-
-	/* If already added */
-	if (pi->pl330_data)
-		return -EINVAL;
-
-	/*
-	 * If the SoC can perform reset on the DMAC, then do it
-	 * before reading its configuration.
-	 */
-	if (pi->dmac_reset)
-		pi->dmac_reset(pi);
-
-	regs = pi->base;
-
-	/* Check if we can handle this DMAC */
-	if ((get_id(pi, PERIPH_ID) & 0xfffff) != PERIPH_ID_VAL
-	   || get_id(pi, PCELL_ID) != PCELL_ID_VAL) {
-		dev_err(pi->dev, "PERIPH_ID 0x%x, PCELL_ID 0x%x !\n",
-			get_id(pi, PERIPH_ID), get_id(pi, PCELL_ID));
-		return -EINVAL;
-	}
-
-	/* Read the configuration of the DMAC */
-	read_dmac_config(pi);
-
-	if (pi->pcfg.num_events == 0) {
-		dev_err(pi->dev, "%s:%d Can't work without events!\n",
-			__func__, __LINE__);
-		return -EINVAL;
-	}
-
-	pl330 = kzalloc(sizeof(*pl330), GFP_KERNEL);
-	if (!pl330) {
-		dev_err(pi->dev, "%s:%d Can't allocate memory!\n",
-			__func__, __LINE__);
-		return -ENOMEM;
-	}
-
-	/* Assign the info structure and private data */
-	pl330->pinfo = pi;
-	pi->pl330_data = pl330;
-
-	spin_lock_init(&pl330->lock);
-
-	INIT_LIST_HEAD(&pl330->req_done);
-
-	/* Use default MC buffer size if not provided */
-	if (!pi->mcbufsz)
-		pi->mcbufsz = MCODE_BUFF_PER_REQ * 2;
-
-	/* Mark all events as free */
-	for (i = 0; i < pi->pcfg.num_events; i++)
-		pl330->events[i] = -1;
-
-	/* Allocate resources needed by the DMAC */
-	ret = dmac_alloc_resources(pl330);
-	if (ret) {
-		dev_err(pi->dev, "Unable to create channels for DMAC\n");
-		kfree(pl330);
-		return ret;
-	}
-
-	tasklet_init(&pl330->tasks, pl330_dotask, (unsigned long) pl330);
-
-	pl330->state = INIT;
-
-	return 0;
-}
-EXPORT_SYMBOL(pl330_add);
-
-static int dmac_free_threads(struct pl330_dmac *pl330)
-{
-	struct pl330_info *pi = pl330->pinfo;
-	int chans = pi->pcfg.num_chan;
-	struct pl330_thread *thrd;
-	int i;
-
-	/* Release Channel threads */
-	for (i = 0; i < chans; i++) {
-		thrd = &pl330->channels[i];
-		pl330_release_channel((void *)thrd);
-	}
-
-	/* Free memory */
-	kfree(pl330->channels);
-
-	return 0;
-}
-
-static void dmac_free_resources(struct pl330_dmac *pl330)
-{
-	struct pl330_info *pi = pl330->pinfo;
-	int chans = pi->pcfg.num_chan;
-
-	dmac_free_threads(pl330);
-
-	dma_free_coherent(pi->dev, chans * pi->mcbufsz,
-				pl330->mcode_cpu, pl330->mcode_bus);
-}
-
-void pl330_del(struct pl330_info *pi)
-{
-	struct pl330_dmac *pl330;
-
-	if (!pi || !pi->pl330_data)
-		return;
-
-	pl330 = pi->pl330_data;
-
-	pl330->state = UNINIT;
-
-	tasklet_kill(&pl330->tasks);
-
-	/* Free DMAC resources */
-	dmac_free_resources(pl330);
-
-	kfree(pl330);
-	pi->pl330_data = NULL;
-}
-EXPORT_SYMBOL(pl330_del);
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 61691cdbdcf2..9173d112ea01 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -16,6 +16,7 @@
  */
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -28,9 +29,8 @@
 #include <linux/io.h>
 
 #include <mach/hardware.h>
-#include <asm/mach-types.h>
-#include <asm/irq.h>
 #include <asm/mach/irq.h>
+#include <asm/mach-types.h>
 #include <asm/sizes.h>
 
 #include <asm/hardware/sa1111.h>
@@ -86,8 +86,10 @@
 #define IRQ_S1_CD_VALID		(52)
 #define IRQ_S0_BVD1_STSCHG	(53)
 #define IRQ_S1_BVD1_STSCHG	(54)
+#define SA1111_IRQ_NR		(55)
 
-extern void __init sa1110_mb_enable(void);
+extern void sa1110_mb_enable(void);
+extern void sa1110_mb_disable(void);
 
 /*
  * We keep the following data for the overall SA1111.  Note that the
@@ -104,6 +106,7 @@ struct sa1111 {
 	int		irq_base;	/* base for cascaded on-chip IRQs */
 	spinlock_t	lock;
 	void __iomem	*base;
+	struct sa1111_platform_data *pdata;
 #ifdef CONFIG_PM
 	void		*saved_state;
 #endif
@@ -118,6 +121,7 @@ static struct sa1111 *g_sa1111;
 struct sa1111_dev_info {
 	unsigned long	offset;
 	unsigned long	skpcr_mask;
+	bool		dma;
 	unsigned int	devid;
 	unsigned int	irq[6];
 };
@@ -126,6 +130,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 	{
 		.offset		= SA1111_USB,
 		.skpcr_mask	= SKPCR_UCLKEN,
+		.dma		= true,
 		.devid		= SA1111_DEVID_USB,
 		.irq = {
 			IRQ_USBPWR,
@@ -139,6 +144,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 	{
 		.offset		= 0x0600,
 		.skpcr_mask	= SKPCR_I2SCLKEN | SKPCR_L3CLKEN,
+		.dma		= true,
 		.devid		= SA1111_DEVID_SAC,
 		.irq = {
 			AUDXMTDMADONEA,
@@ -155,7 +161,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 	{
 		.offset		= SA1111_KBD,
 		.skpcr_mask	= SKPCR_PTCLKEN,
-		.devid		= SA1111_DEVID_PS2,
+		.devid		= SA1111_DEVID_PS2_KBD,
 		.irq = {
 			IRQ_TPRXINT,
 			IRQ_TPTXINT
@@ -164,7 +170,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 	{
 		.offset		= SA1111_MSE,
 		.skpcr_mask	= SKPCR_PMCLKEN,
-		.devid		= SA1111_DEVID_PS2,
+		.devid		= SA1111_DEVID_PS2_MSE,
 		.irq = {
 			IRQ_MSRXINT,
 			IRQ_MSTXINT
@@ -434,16 +440,28 @@ static struct irq_chip sa1111_high_chip = {
 	.irq_set_wake	= sa1111_wake_highirq,
 };
 
-static void sa1111_setup_irq(struct sa1111 *sachip)
+static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 {
 	void __iomem *irqbase = sachip->base + SA1111_INTC;
-	unsigned int irq;
+	unsigned i, irq;
+	int ret;
 
 	/*
 	 * We're guaranteed that this region hasn't been taken.
 	 */
 	request_mem_region(sachip->phys + SA1111_INTC, 512, "irq");
 
+	ret = irq_alloc_descs(-1, irq_base, SA1111_IRQ_NR, -1);
+	if (ret <= 0) {
+		dev_err(sachip->dev, "unable to allocate %u irqs: %d\n",
+			SA1111_IRQ_NR, ret);
+		if (ret == 0)
+			ret = -EINVAL;
+		return ret;
+	}
+
+	sachip->irq_base = ret;
+
 	/* disable all IRQs */
 	sa1111_writel(0, irqbase + SA1111_INTEN0);
 	sa1111_writel(0, irqbase + SA1111_INTEN1);
@@ -463,14 +481,16 @@ static void sa1111_setup_irq(struct sa1111 *sachip)
 	sa1111_writel(~0, irqbase + SA1111_INTSTATCLR0);
 	sa1111_writel(~0, irqbase + SA1111_INTSTATCLR1);
 
-	for (irq = IRQ_GPAIN0; irq <= SSPROR; irq++) {
+	for (i = IRQ_GPAIN0; i <= SSPROR; i++) {
+		irq = sachip->irq_base + i;
 		irq_set_chip_and_handler(irq, &sa1111_low_chip,
 					 handle_edge_irq);
 		irq_set_chip_data(irq, sachip);
 		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
 	}
 
-	for (irq = AUDXMTDMADONEA; irq <= IRQ_S1_BVD1_STSCHG; irq++) {
+	for (i = AUDXMTDMADONEA; i <= IRQ_S1_BVD1_STSCHG; i++) {
+		irq = sachip->irq_base + i;
 		irq_set_chip_and_handler(irq, &sa1111_high_chip,
 					 handle_edge_irq);
 		irq_set_chip_data(irq, sachip);
@@ -483,6 +503,11 @@ static void sa1111_setup_irq(struct sa1111 *sachip)
 	irq_set_irq_type(sachip->irq, IRQ_TYPE_EDGE_RISING);
 	irq_set_handler_data(sachip->irq, sachip);
 	irq_set_chained_handler(sachip->irq, sa1111_irq_handler);
+
+	dev_info(sachip->dev, "Providing IRQ%u-%u\n",
+		sachip->irq_base, sachip->irq_base + SA1111_IRQ_NR - 1);
+
+	return 0;
 }
 
 /*
@@ -581,41 +606,10 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac,
 }
 #endif
 
-#ifdef CONFIG_DMABOUNCE
-/*
- * According to the "Intel StrongARM SA-1111 Microprocessor Companion
- * Chip Specification Update" (June 2000), erratum #7, there is a
- * significant bug in the SA1111 SDRAM shared memory controller.  If
- * an access to a region of memory above 1MB relative to the bank base,
- * it is important that address bit 10 _NOT_ be asserted. Depending
- * on the configuration of the RAM, bit 10 may correspond to one
- * of several different (processor-relative) address bits.
- *
- * This routine only identifies whether or not a given DMA address
- * is susceptible to the bug.
- *
- * This should only get called for sa1111_device types due to the
- * way we configure our device dma_masks.
- */
-static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
-{
-	/*
-	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
-	 * User's Guide" mentions that jumpers R51 and R52 control the
-	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
-	 * SDRAM bank 1 on Neponset). The default configuration selects
-	 * Assabet, so any address in bank 1 is necessarily invalid.
-	 */
-	return (machine_is_assabet() || machine_is_pfs168()) &&
-		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000);
-}
-#endif
-
 static void sa1111_dev_release(struct device *_dev)
 {
 	struct sa1111_dev *dev = SA1111_DEV(_dev);
 
-	release_resource(&dev->res);
 	kfree(dev);
 }
 
@@ -624,67 +618,58 @@ sa1111_init_one_child(struct sa1111 *sachip, struct resource *parent,
 		      struct sa1111_dev_info *info)
 {
 	struct sa1111_dev *dev;
+	unsigned i;
 	int ret;
 
 	dev = kzalloc(sizeof(struct sa1111_dev), GFP_KERNEL);
 	if (!dev) {
 		ret = -ENOMEM;
-		goto out;
+		goto err_alloc;
 	}
 
+	device_initialize(&dev->dev);
 	dev_set_name(&dev->dev, "%4.4lx", info->offset);
 	dev->devid	 = info->devid;
 	dev->dev.parent  = sachip->dev;
 	dev->dev.bus     = &sa1111_bus_type;
 	dev->dev.release = sa1111_dev_release;
-	dev->dev.coherent_dma_mask = sachip->dev->coherent_dma_mask;
 	dev->res.start   = sachip->phys + info->offset;
 	dev->res.end     = dev->res.start + 511;
 	dev->res.name    = dev_name(&dev->dev);
 	dev->res.flags   = IORESOURCE_MEM;
 	dev->mapbase     = sachip->base + info->offset;
 	dev->skpcr_mask  = info->skpcr_mask;
-	memmove(dev->irq, info->irq, sizeof(dev->irq));
-
-	ret = request_resource(parent, &dev->res);
-	if (ret) {
-		printk("SA1111: failed to allocate resource for %s\n",
-			dev->res.name);
-		dev_set_name(&dev->dev, NULL);
-		kfree(dev);
-		goto out;
-	}
-
 
-	ret = device_register(&dev->dev);
-	if (ret) {
-		release_resource(&dev->res);
-		kfree(dev);
-		goto out;
-	}
+	for (i = 0; i < ARRAY_SIZE(info->irq); i++)
+		dev->irq[i] = sachip->irq_base + info->irq[i];
 
-#ifdef CONFIG_DMABOUNCE
 	/*
-	 * If the parent device has a DMA mask associated with it,
-	 * propagate it down to the children.
+	 * If the parent device has a DMA mask associated with it, and
+	 * this child supports DMA, propagate it down to the children.
 	 */
-	if (sachip->dev->dma_mask) {
+	if (info->dma && sachip->dev->dma_mask) {
 		dev->dma_mask = *sachip->dev->dma_mask;
 		dev->dev.dma_mask = &dev->dma_mask;
+		dev->dev.coherent_dma_mask = sachip->dev->coherent_dma_mask;
+	}
 
-		if (dev->dma_mask != 0xffffffffUL) {
-			ret = dmabounce_register_dev(&dev->dev, 1024, 4096,
-					sa1111_needs_bounce);
-			if (ret) {
-				dev_err(&dev->dev, "SA1111: Failed to register"
-					" with dmabounce\n");
-				device_unregister(&dev->dev);
-			}
-		}
+	ret = request_resource(parent, &dev->res);
+	if (ret) {
+		dev_err(sachip->dev, "failed to allocate resource for %s\n",
+			dev->res.name);
+		goto err_resource;
 	}
-#endif
 
-out:
+	ret = device_add(&dev->dev);
+	if (ret)
+		goto err_add;
+	return 0;
+
+ err_add:
+	release_resource(&dev->res);
+ err_resource:
+	put_device(&dev->dev);
+ err_alloc:
 	return ret;
 }
 
@@ -698,16 +683,21 @@ out:
  *	Returns:
  *	%-ENODEV	device not found.
  *	%-EBUSY		physical address already marked in-use.
+ *	%-EINVAL	no platform data passed
  *	%0		successful.
  */
 static int __devinit
 __sa1111_probe(struct device *me, struct resource *mem, int irq)
 {
+	struct sa1111_platform_data *pd = me->platform_data;
 	struct sa1111 *sachip;
 	unsigned long id;
 	unsigned int has_devs;
 	int i, ret = -ENODEV;
 
+	if (!pd)
+		return -EINVAL;
+
 	sachip = kzalloc(sizeof(struct sa1111), GFP_KERNEL);
 	if (!sachip)
 		return -ENOMEM;
@@ -727,6 +717,7 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	sachip->dev = me;
 	dev_set_drvdata(sachip->dev, sachip);
 
+	sachip->pdata = pd;
 	sachip->phys = mem->start;
 	sachip->irq = irq;
 
@@ -759,6 +750,16 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	 */
 	sa1111_wake(sachip);
 
+	/*
+	 * The interrupt controller must be initialised before any
+	 * other device to ensure that the interrupts are available.
+	 */
+	if (sachip->irq != NO_IRQ) {
+		ret = sa1111_setup_irq(sachip, pd->irq_base);
+		if (ret)
+			goto err_unmap;
+	}
+
 #ifdef CONFIG_ARCH_SA1100
 	{
 	unsigned int val;
@@ -789,24 +790,14 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	}
 #endif
 
-	/*
-	 * The interrupt controller must be initialised before any
-	 * other device to ensure that the interrupts are available.
-	 */
-	if (sachip->irq != NO_IRQ)
-		sa1111_setup_irq(sachip);
-
 	g_sa1111 = sachip;
 
 	has_devs = ~0;
-	if (machine_is_assabet() || machine_is_jornada720() ||
-	    machine_is_badge4())
-		has_devs &= ~(1 << 4);
-	else
-		has_devs &= ~(1 << 1);
+	if (pd)
+		has_devs &= ~pd->disable_devs;
 
 	for (i = 0; i < ARRAY_SIZE(sa1111_devices); i++)
-		if (has_devs & (1 << i))
+		if (sa1111_devices[i].devid & has_devs)
 			sa1111_init_one_child(sachip, mem, &sa1111_devices[i]);
 
 	return 0;
@@ -824,7 +815,10 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq)
 
 static int sa1111_remove_one(struct device *dev, void *data)
 {
-	device_unregister(dev);
+	struct sa1111_dev *sadev = SA1111_DEV(dev);
+	device_del(&sadev->dev);
+	release_resource(&sadev->res);
+	put_device(&sadev->dev);
 	return 0;
 }
 
@@ -846,6 +840,7 @@ static void __sa1111_remove(struct sa1111 *sachip)
 	if (sachip->irq != NO_IRQ) {
 		irq_set_chained_handler(sachip->irq, NULL);
 		irq_set_handler_data(sachip->irq, NULL);
+		irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
 
 		release_mem_region(sachip->phys + SA1111_INTC, 512);
 	}
@@ -904,6 +899,9 @@ static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
 	save->skpwm0   = sa1111_readl(base + SA1111_SKPWM0);
 	save->skpwm1   = sa1111_readl(base + SA1111_SKPWM1);
 
+	sa1111_writel(0, sachip->base + SA1111_SKPWM0);
+	sa1111_writel(0, sachip->base + SA1111_SKPWM1);
+
 	base = sachip->base + SA1111_INTC;
 	save->intpol0  = sa1111_readl(base + SA1111_INTPOL0);
 	save->intpol1  = sa1111_readl(base + SA1111_INTPOL1);
@@ -919,13 +917,15 @@ static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
 	 */
 	val = sa1111_readl(sachip->base + SA1111_SKCR);
 	sa1111_writel(val | SKCR_SLEEP, sachip->base + SA1111_SKCR);
-	sa1111_writel(0, sachip->base + SA1111_SKPWM0);
-	sa1111_writel(0, sachip->base + SA1111_SKPWM1);
 
 	clk_disable(sachip->clk);
 
 	spin_unlock_irqrestore(&sachip->lock, flags);
 
+#ifdef CONFIG_ARCH_SA1100
+	sa1110_mb_disable();
+#endif
+
 	return 0;
 }
 
@@ -966,6 +966,11 @@ static int sa1111_resume(struct platform_device *dev)
 	 */
 	sa1111_wake(sachip);
 
+#ifdef CONFIG_ARCH_SA1100
+	/* Enable the memory bus request/grant signals */
+	sa1110_mb_enable();
+#endif
+
 	/*
 	 * Only lock for write ops. Also, sa1111_wake must be called with
 	 * released spinlock!
@@ -1053,6 +1058,7 @@ static struct platform_driver sa1111_device_driver = {
 	.resume		= sa1111_resume,
 	.driver		= {
 		.name	= "sa1111",
+		.owner	= THIS_MODULE,
 	},
 };
 
@@ -1238,16 +1244,23 @@ EXPORT_SYMBOL(sa1111_set_sleep_io);
  *	sa1111_enable_device - enable an on-chip SA1111 function block
  *	@sadev: SA1111 function block device to enable
  */
-void sa1111_enable_device(struct sa1111_dev *sadev)
+int sa1111_enable_device(struct sa1111_dev *sadev)
 {
 	struct sa1111 *sachip = sa1111_chip_driver(sadev);
 	unsigned long flags;
 	unsigned int val;
+	int ret = 0;
 
-	spin_lock_irqsave(&sachip->lock, flags);
-	val = sa1111_readl(sachip->base + SA1111_SKPCR);
-	sa1111_writel(val | sadev->skpcr_mask, sachip->base + SA1111_SKPCR);
-	spin_unlock_irqrestore(&sachip->lock, flags);
+	if (sachip->pdata && sachip->pdata->enable)
+		ret = sachip->pdata->enable(sachip->pdata->data, sadev->devid);
+
+	if (ret == 0) {
+		spin_lock_irqsave(&sachip->lock, flags);
+		val = sa1111_readl(sachip->base + SA1111_SKPCR);
+		sa1111_writel(val | sadev->skpcr_mask, sachip->base + SA1111_SKPCR);
+		spin_unlock_irqrestore(&sachip->lock, flags);
+	}
+	return ret;
 }
 EXPORT_SYMBOL(sa1111_enable_device);
 
@@ -1265,6 +1278,9 @@ void sa1111_disable_device(struct sa1111_dev *sadev)
 	val = sa1111_readl(sachip->base + SA1111_SKPCR);
 	sa1111_writel(val & ~sadev->skpcr_mask, sachip->base + SA1111_SKPCR);
 	spin_unlock_irqrestore(&sachip->lock, flags);
+
+	if (sachip->pdata && sachip->pdata->disable)
+		sachip->pdata->disable(sachip->pdata->data, sadev->devid);
 }
 EXPORT_SYMBOL(sa1111_disable_device);
 
@@ -1279,7 +1295,7 @@ static int sa1111_match(struct device *_dev, struct device_driver *_drv)
 	struct sa1111_dev *dev = SA1111_DEV(_dev);
 	struct sa1111_driver *drv = SA1111_DRV(_drv);
 
-	return dev->devid == drv->devid;
+	return dev->devid & drv->devid;
 }
 
 static int sa1111_bus_suspend(struct device *dev, pm_message_t state)
@@ -1304,6 +1320,14 @@ static int sa1111_bus_resume(struct device *dev)
 	return ret;
 }
 
+static void sa1111_bus_shutdown(struct device *dev)
+{
+	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
+
+	if (drv && drv->shutdown)
+		drv->shutdown(SA1111_DEV(dev));
+}
+
 static int sa1111_bus_probe(struct device *dev)
 {
 	struct sa1111_dev *sadev = SA1111_DEV(dev);
@@ -1333,6 +1357,7 @@ struct bus_type sa1111_bus_type = {
 	.remove		= sa1111_bus_remove,
 	.suspend	= sa1111_bus_suspend,
 	.resume		= sa1111_bus_resume,
+	.shutdown	= sa1111_bus_shutdown,
 };
 EXPORT_SYMBOL(sa1111_bus_type);
 
@@ -1349,9 +1374,70 @@ void sa1111_driver_unregister(struct sa1111_driver *driver)
 }
 EXPORT_SYMBOL(sa1111_driver_unregister);
 
+#ifdef CONFIG_DMABOUNCE
+/*
+ * According to the "Intel StrongARM SA-1111 Microprocessor Companion
+ * Chip Specification Update" (June 2000), erratum #7, there is a
+ * significant bug in the SA1111 SDRAM shared memory controller.  If
+ * an access to a region of memory above 1MB relative to the bank base,
+ * it is important that address bit 10 _NOT_ be asserted. Depending
+ * on the configuration of the RAM, bit 10 may correspond to one
+ * of several different (processor-relative) address bits.
+ *
+ * This routine only identifies whether or not a given DMA address
+ * is susceptible to the bug.
+ *
+ * This should only get called for sa1111_device types due to the
+ * way we configure our device dma_masks.
+ */
+static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
+{
+	/*
+	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
+	 * User's Guide" mentions that jumpers R51 and R52 control the
+	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
+	 * SDRAM bank 1 on Neponset). The default configuration selects
+	 * Assabet, so any address in bank 1 is necessarily invalid.
+	 */
+	return (machine_is_assabet() || machine_is_pfs168()) &&
+		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000);
+}
+
+static int sa1111_notifier_call(struct notifier_block *n, unsigned long action,
+	void *data)
+{
+	struct sa1111_dev *dev = SA1111_DEV(data);
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		if (dev->dev.dma_mask && dev->dma_mask < 0xffffffffUL) {
+			int ret = dmabounce_register_dev(&dev->dev, 1024, 4096,
+					sa1111_needs_bounce);
+			if (ret)
+				dev_err(&dev->dev, "failed to register with dmabounce: %d\n", ret);
+		}
+		break;
+
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (dev->dev.dma_mask && dev->dma_mask < 0xffffffffUL)
+			dmabounce_unregister_dev(&dev->dev);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block sa1111_bus_notifier = {
+	.notifier_call = sa1111_notifier_call,
+};
+#endif
+
 static int __init sa1111_init(void)
 {
 	int ret = bus_register(&sa1111_bus_type);
+#ifdef CONFIG_DMABOUNCE
+	if (ret == 0)
+		bus_register_notifier(&sa1111_bus_type, &sa1111_bus_notifier);
+#endif
 	if (ret == 0)
 		platform_driver_register(&sa1111_device_driver);
 	return ret;
@@ -1360,6 +1446,9 @@ static int __init sa1111_init(void)
 static void __exit sa1111_exit(void)
 {
 	platform_driver_unregister(&sa1111_device_driver);
+#ifdef CONFIG_DMABOUNCE
+	bus_unregister_notifier(&sa1111_bus_type, &sa1111_bus_notifier);
+#endif
 	bus_unregister(&sa1111_bus_type);
 }
 
diff --git a/arch/arm/common/via82c505.c b/arch/arm/common/via82c505.c
index 67dd2affc57a..1171a5010aea 100644
--- a/arch/arm/common/via82c505.c
+++ b/arch/arm/common/via82c505.c
@@ -6,7 +6,6 @@
 #include <linux/ioport.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 
 #include <asm/mach/pci.h>
 
diff --git a/arch/arm/configs/at91sam9g20_defconfig b/arch/arm/configs/at91sam9g20_defconfig
index 9123568d9a8d..994d331b2319 100644
--- a/arch/arm/configs/at91sam9g20_defconfig
+++ b/arch/arm/configs/at91sam9g20_defconfig
@@ -74,6 +74,8 @@ CONFIG_LEGACY_PTY_COUNT=16
 CONFIG_SERIAL_ATMEL=y
 CONFIG_SERIAL_ATMEL_CONSOLE=y
 CONFIG_HW_RANDOM=y
+CONFIG_I2C=y
+CONFIG_I2C_GPIO=y
 CONFIG_SPI=y
 CONFIG_SPI_ATMEL=y
 CONFIG_SPI_SPIDEV=y
@@ -105,6 +107,7 @@ CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_RV3029C2=y
 CONFIG_RTC_DRV_AT91SAM9=y
 CONFIG_EXT2_FS=y
 CONFIG_MSDOS_FS=y
diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig
index 1103f62a1964..a8314c3ee84d 100644
--- a/arch/arm/configs/integrator_defconfig
+++ b/arch/arm/configs/integrator_defconfig
@@ -57,18 +57,24 @@ CONFIG_NETDEVICES=y
 CONFIG_NET_ETHERNET=y
 CONFIG_NET_PCI=y
 CONFIG_E100=y
+CONFIG_SMC91X=y
 # CONFIG_KEYBOARD_ATKBD is not set
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIAL_AMBA_PL010=y
 CONFIG_SERIAL_AMBA_PL010_CONSOLE=y
 CONFIG_FB=y
 CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_ARMCLCD=y
 CONFIG_FB_MATROX=y
 CONFIG_FB_MATROX_MILLENIUM=y
 CONFIG_FB_MATROX_MYSTIQUE=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_PL030=y
 CONFIG_EXT2_FS=y
+CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
@@ -78,5 +84,7 @@ CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
 CONFIG_NFSD_V3=y
 CONFIG_PARTITION_ADVANCED=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig
index 2d7b6e7b7271..889d73ac1ae1 100644
--- a/arch/arm/configs/u8500_defconfig
+++ b/arch/arm/configs/u8500_defconfig
@@ -13,6 +13,7 @@ CONFIG_UX500_SOC_DB8500=y
 CONFIG_MACH_HREFV60=y
 CONFIG_MACH_SNOWBALL=y
 CONFIG_MACH_U5500=y
+CONFIG_MACH_UX500_DT=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 23371b17b23e..03fb93621d0d 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -23,6 +23,8 @@
 #include <asm/ptrace.h>
 #include <asm/domain.h>
 
+#define IOMEM(x)	(x)
+
 /*
  * Endian independent macros for shifting bytes within registers.
  */
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 86976d034382..68374ba6a943 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -13,7 +13,9 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/system.h>
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)	{ (i) }
 
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
new file mode 100644
index 000000000000..05112380dc53
--- /dev/null
+++ b/arch/arm/include/asm/barrier.h
@@ -0,0 +1,69 @@
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+#include <asm/outercache.h>
+
+#define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
+
+#if __LINUX_ARM_ARCH__ >= 7 ||		\
+	(__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K))
+#define sev()	__asm__ __volatile__ ("sev" : : : "memory")
+#define wfe()	__asm__ __volatile__ ("wfe" : : : "memory")
+#define wfi()	__asm__ __volatile__ ("wfi" : : : "memory")
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 7
+#define isb() __asm__ __volatile__ ("isb" : : : "memory")
+#define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
+#define dmb() __asm__ __volatile__ ("dmb" : : : "memory")
+#elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
+#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+				    : : "r" (0) : "memory")
+#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
+				    : : "r" (0) : "memory")
+#elif defined(CONFIG_CPU_FA526)
+#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+				    : : "r" (0) : "memory")
+#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#else
+#define isb() __asm__ __volatile__ ("" : : : "memory")
+#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#endif
+
+#ifdef CONFIG_ARCH_HAS_BARRIERS
+#include <mach/barriers.h>
+#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
+#define mb()		do { dsb(); outer_sync(); } while (0)
+#define rmb()		dsb()
+#define wmb()		mb()
+#else
+#include <asm/memory.h>
+#define mb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
+#define rmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
+#define wmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
+#endif
+
+#ifndef CONFIG_SMP
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#else
+#define smp_mb()	dmb()
+#define smp_rmb()	dmb()
+#define smp_wmb()	dmb()
+#endif
+
+#define read_barrier_depends()		do { } while(0)
+#define smp_read_barrier_depends()	do { } while(0)
+
+#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index f7419ef9c8f9..e691ec91e4d3 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -24,7 +24,7 @@
 #endif
 
 #include <linux/compiler.h>
-#include <asm/system.h>
+#include <linux/irqflags.h>
 
 #define smp_mb__before_clear_bit()	smp_mb()
 #define smp_mb__after_clear_bit()	smp_mb()
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index fac79dceb736..7af5c6c3653a 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -1,6 +1,7 @@
 #ifndef _ASMARM_BUG_H
 #define _ASMARM_BUG_H
 
+#include <linux/linkage.h>
 
 #ifdef CONFIG_BUG
 
@@ -57,4 +58,33 @@ do {								\
 
 #include <asm-generic/bug.h>
 
+struct pt_regs;
+void die(const char *msg, struct pt_regs *regs, int err);
+
+struct siginfo;
+void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
+		unsigned long err, unsigned long trap);
+
+#ifdef CONFIG_ARM_LPAE
+#define FAULT_CODE_ALIGNMENT	33
+#define FAULT_CODE_DEBUG	34
+#else
+#define FAULT_CODE_ALIGNMENT	1
+#define FAULT_CODE_DEBUG	2
+#endif
+
+void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
+				       struct pt_regs *),
+		     int sig, int code, const char *name);
+
+void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int,
+				       struct pt_regs *),
+		     int sig, int code, const char *name);
+
+extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
+
+struct mm_struct;
+extern void show_pte(struct mm_struct *mm, unsigned long addr);
+extern void __show_regs(struct pt_regs *);
+
 #endif
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..d41d7cbf0ada
--- /dev/null
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -0,0 +1,295 @@
+#ifndef __ASM_ARM_CMPXCHG_H
+#define __ASM_ARM_CMPXCHG_H
+
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+
+#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
+/*
+ * On the StrongARM, "swp" is terminally broken since it bypasses the
+ * cache totally.  This means that the cache becomes inconsistent, and,
+ * since we use normal loads/stores as well, this is really bad.
+ * Typically, this causes oopsen in filp_close, but could have other,
+ * more disastrous effects.  There are two work-arounds:
+ *  1. Disable interrupts and emulate the atomic swap
+ *  2. Clean the cache, perform atomic swap, flush the cache
+ *
+ * We choose (1) since its the "easiest" to achieve here and is not
+ * dependent on the processor type.
+ *
+ * NOTE that this solution won't work on an SMP system, so explcitly
+ * forbid it here.
+ */
+#define swp_is_buggy
+#endif
+
+static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
+{
+	extern void __bad_xchg(volatile void *, int);
+	unsigned long ret;
+#ifdef swp_is_buggy
+	unsigned long flags;
+#endif
+#if __LINUX_ARM_ARCH__ >= 6
+	unsigned int tmp;
+#endif
+
+	smp_mb();
+
+	switch (size) {
+#if __LINUX_ARM_ARCH__ >= 6
+	case 1:
+		asm volatile("@	__xchg1\n"
+		"1:	ldrexb	%0, [%3]\n"
+		"	strexb	%1, %2, [%3]\n"
+		"	teq	%1, #0\n"
+		"	bne	1b"
+			: "=&r" (ret), "=&r" (tmp)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+	case 4:
+		asm volatile("@	__xchg4\n"
+		"1:	ldrex	%0, [%3]\n"
+		"	strex	%1, %2, [%3]\n"
+		"	teq	%1, #0\n"
+		"	bne	1b"
+			: "=&r" (ret), "=&r" (tmp)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+#elif defined(swp_is_buggy)
+#ifdef CONFIG_SMP
+#error SMP is not supported on this platform
+#endif
+	case 1:
+		raw_local_irq_save(flags);
+		ret = *(volatile unsigned char *)ptr;
+		*(volatile unsigned char *)ptr = x;
+		raw_local_irq_restore(flags);
+		break;
+
+	case 4:
+		raw_local_irq_save(flags);
+		ret = *(volatile unsigned long *)ptr;
+		*(volatile unsigned long *)ptr = x;
+		raw_local_irq_restore(flags);
+		break;
+#else
+	case 1:
+		asm volatile("@	__xchg1\n"
+		"	swpb	%0, %1, [%2]"
+			: "=&r" (ret)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+	case 4:
+		asm volatile("@	__xchg4\n"
+		"	swp	%0, %1, [%2]"
+			: "=&r" (ret)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+#endif
+	default:
+		__bad_xchg(ptr, size), ret = 0;
+		break;
+	}
+	smp_mb();
+
+	return ret;
+}
+
+#define xchg(ptr,x) \
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+#include <asm-generic/cmpxchg-local.h>
+
+#if __LINUX_ARM_ARCH__ < 6
+/* min ARCH < ARMv6 */
+
+#ifdef CONFIG_SMP
+#error "SMP is not supported on this platform"
+#endif
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#ifndef CONFIG_SMP
+#include <asm-generic/cmpxchg.h>
+#endif
+
+#else	/* min ARCH >= ARMv6 */
+
+extern void __bad_cmpxchg(volatile void *ptr, int size);
+
+/*
+ * cmpxchg only support 32-bits operands on ARMv6.
+ */
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	unsigned long oldval, res;
+
+	switch (size) {
+#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
+	case 1:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexb	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexbeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	case 2:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexh	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexheq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+#endif
+	case 4:
+		do {
+			asm volatile("@ __cmpxchg4\n"
+			"	ldrex	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	default:
+		__bad_cmpxchg(ptr, size);
+		oldval = 0;
+	}
+
+	return oldval;
+}
+
+static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
+					 unsigned long new, int size)
+{
+	unsigned long ret;
+
+	smp_mb();
+	ret = __cmpxchg(ptr, old, new, size);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
+					  (unsigned long)(o),		\
+					  (unsigned long)(n),		\
+					  sizeof(*(ptr))))
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+					    unsigned long old,
+					    unsigned long new, int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+#ifdef CONFIG_CPU_V6	/* min ARCH == ARMv6 */
+	case 1:
+	case 2:
+		ret = __cmpxchg_local_generic(ptr, old, new, size);
+		break;
+#endif
+	default:
+		ret = __cmpxchg(ptr, old, new, size);
+	}
+
+	return ret;
+}
+
+#define cmpxchg_local(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
+				       (unsigned long)(o),		\
+				       (unsigned long)(n),		\
+				       sizeof(*(ptr))))
+
+#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
+
+/*
+ * Note : ARMv7-M (currently unsupported by Linux) does not support
+ * ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should
+ * not be allowed to use __cmpxchg64.
+ */
+static inline unsigned long long __cmpxchg64(volatile void *ptr,
+					     unsigned long long old,
+					     unsigned long long new)
+{
+	register unsigned long long oldval asm("r0");
+	register unsigned long long __old asm("r2") = old;
+	register unsigned long long __new asm("r4") = new;
+	unsigned long res;
+
+	do {
+		asm volatile(
+		"	@ __cmpxchg8\n"
+		"	ldrexd	%1, %H1, [%2]\n"
+		"	mov	%0, #0\n"
+		"	teq	%1, %3\n"
+		"	teqeq	%H1, %H3\n"
+		"	strexdeq %0, %4, %H4, [%2]\n"
+			: "=&r" (res), "=&r" (oldval)
+			: "r" (ptr), "Ir" (__old), "r" (__new)
+			: "memory", "cc");
+	} while (res);
+
+	return oldval;
+}
+
+static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
+						unsigned long long old,
+						unsigned long long new)
+{
+	unsigned long long ret;
+
+	smp_mb();
+	ret = __cmpxchg64(ptr, old, new);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg64(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
+					    (unsigned long long)(o),	\
+					    (unsigned long long)(n)))
+
+#define cmpxchg64_local(ptr,o,n)					\
+	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+					 (unsigned long long)(o),	\
+					 (unsigned long long)(n)))
+
+#else /* min ARCH = ARMv6 */
+
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#endif
+
+#endif	/* __LINUX_ARM_ARCH__ >= 6 */
+
+#endif /* __ASM_ARM_CMPXCHG_H */
diff --git a/arch/arm/include/asm/compiler.h b/arch/arm/include/asm/compiler.h
new file mode 100644
index 000000000000..8155db2f7fa1
--- /dev/null
+++ b/arch/arm/include/asm/compiler.h
@@ -0,0 +1,15 @@
+#ifndef __ASM_ARM_COMPILER_H
+#define __ASM_ARM_COMPILER_H
+
+/*
+ * This is used to ensure the compiler did actually allocate the register we
+ * asked it for some inline assembly sequences.  Apparently we can't trust
+ * the compiler from one version to another so a bit of paranoia won't hurt.
+ * This string is meant to be concatenated with the inline asm string and
+ * will cause compilation to stop on mismatch.
+ * (for details, see gcc PR 15089)
+ */
+#define __asmeq(x, y)  ".ifnc " x "," y " ; .err ; .endif\n\t"
+
+
+#endif /* __ASM_ARM_COMPILER_H */
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
new file mode 100644
index 000000000000..5ef4d8015a60
--- /dev/null
+++ b/arch/arm/include/asm/cp15.h
@@ -0,0 +1,87 @@
+#ifndef __ASM_ARM_CP15_H
+#define __ASM_ARM_CP15_H
+
+#include <asm/barrier.h>
+
+/*
+ * CR1 bits (CP#15 CR1)
+ */
+#define CR_M	(1 << 0)	/* MMU enable				*/
+#define CR_A	(1 << 1)	/* Alignment abort enable		*/
+#define CR_C	(1 << 2)	/* Dcache enable			*/
+#define CR_W	(1 << 3)	/* Write buffer enable			*/
+#define CR_P	(1 << 4)	/* 32-bit exception handler		*/
+#define CR_D	(1 << 5)	/* 32-bit data address range		*/
+#define CR_L	(1 << 6)	/* Implementation defined		*/
+#define CR_B	(1 << 7)	/* Big endian				*/
+#define CR_S	(1 << 8)	/* System MMU protection		*/
+#define CR_R	(1 << 9)	/* ROM MMU protection			*/
+#define CR_F	(1 << 10)	/* Implementation defined		*/
+#define CR_Z	(1 << 11)	/* Implementation defined		*/
+#define CR_I	(1 << 12)	/* Icache enable			*/
+#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
+#define CR_RR	(1 << 14)	/* Round Robin cache replacement	*/
+#define CR_L4	(1 << 15)	/* LDR pc can set T bit			*/
+#define CR_DT	(1 << 16)
+#define CR_IT	(1 << 18)
+#define CR_ST	(1 << 19)
+#define CR_FI	(1 << 21)	/* Fast interrupt (lower latency mode)	*/
+#define CR_U	(1 << 22)	/* Unaligned access operation		*/
+#define CR_XP	(1 << 23)	/* Extended page tables			*/
+#define CR_VE	(1 << 24)	/* Vectored interrupts			*/
+#define CR_EE	(1 << 25)	/* Exception (Big) Endian		*/
+#define CR_TRE	(1 << 28)	/* TEX remap enable			*/
+#define CR_AFE	(1 << 29)	/* Access flag enable			*/
+#define CR_TE	(1 << 30)	/* Thumb exception enable		*/
+
+#ifndef __ASSEMBLY__
+
+#if __LINUX_ARM_ARCH__ >= 4
+#define vectors_high()	(cr_alignment & CR_V)
+#else
+#define vectors_high()	(0)
+#endif
+
+extern unsigned long cr_no_alignment;	/* defined in entry-armv.S */
+extern unsigned long cr_alignment;	/* defined in entry-armv.S */
+
+static inline unsigned int get_cr(void)
+{
+	unsigned int val;
+	asm("mrc p15, 0, %0, c1, c0, 0	@ get CR" : "=r" (val) : : "cc");
+	return val;
+}
+
+static inline void set_cr(unsigned int val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 0	@ set CR"
+	  : : "r" (val) : "cc");
+	isb();
+}
+
+#ifndef CONFIG_SMP
+extern void adjust_cr(unsigned long mask, unsigned long set);
+#endif
+
+#define CPACC_FULL(n)		(3 << (n * 2))
+#define CPACC_SVC(n)		(1 << (n * 2))
+#define CPACC_DISABLE(n)	(0 << (n * 2))
+
+static inline unsigned int get_copro_access(void)
+{
+	unsigned int val;
+	asm("mrc p15, 0, %0, c1, c0, 2 @ get copro access"
+	  : "=r" (val) : : "cc");
+	return val;
+}
+
+static inline void set_copro_access(unsigned int val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 2 @ set copro access"
+	  : : "r" (val) : "cc");
+	isb();
+}
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
new file mode 100644
index 000000000000..2fca60ab513a
--- /dev/null
+++ b/arch/arm/include/asm/cpuidle.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_CPUIDLE_H
+#define __ASM_ARM_CPUIDLE_H
+
+#ifdef CONFIG_CPU_IDLE
+extern int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index);
+#else
+static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index) { return -ENODEV; }
+#endif
+
+/* Common ARM WFI state */
+#define ARM_CPUIDLE_WFI_STATE_PWR(p) {\
+	.enter                  = arm_cpuidle_simple_enter,\
+	.exit_latency           = 1,\
+	.target_residency       = 1,\
+	.power_usage		= p,\
+	.flags                  = CPUIDLE_FLAG_TIME_VALID,\
+	.name                   = "WFI",\
+	.desc                   = "ARM WFI",\
+}
+
+/*
+ * in case power_specified == 1, give a default WFI power value needed
+ * by some governors
+ */
+#define ARM_CPUIDLE_WFI_STATE ARM_CPUIDLE_WFI_STATE_PWR(UINT_MAX)
+
+#endif
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index d3f0a9eee9f6..fe92ccf1d0b0 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -1,8 +1,8 @@
 #ifndef __ASM_ARM_DIV64
 #define __ASM_ARM_DIV64
 
-#include <asm/system.h>
 #include <linux/types.h>
+#include <asm/compiler.h>
 
 /*
  * The semantics of do_div() are:
diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index 69a5b0b6455c..5694a0d6576b 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -19,7 +19,6 @@
  * It should not be re-used except for that purpose.
  */
 #include <linux/spinlock.h>
-#include <asm/system.h>
 #include <asm/scatterlist.h>
 
 #include <mach/isa-dma.h>
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index b5dc173d336f..3d2220498abc 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -10,6 +10,10 @@
 #ifndef __ASM_PROC_DOMAIN_H
 #define __ASM_PROC_DOMAIN_H
 
+#ifndef __ASSEMBLY__
+#include <asm/barrier.h>
+#endif
+
 /*
  * Domain numbers
  *
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 0e9ce8d9686e..38050b1c4800 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -130,8 +130,4 @@ struct mm_struct;
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
-extern int vectors_user_mapping(void);
-#define arch_setup_additional_pages(bprm, uses_interp) vectors_user_mapping()
-#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
-
 #endif
diff --git a/arch/arm/include/asm/exec.h b/arch/arm/include/asm/exec.h
new file mode 100644
index 000000000000..7c4fbef72b3a
--- /dev/null
+++ b/arch/arm/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_ARM_EXEC_H
+#define __ASM_ARM_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __ASM_ARM_EXEC_H */
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 7df239bcdf27..c4c87bc12231 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -103,11 +103,11 @@
 #define L2X0_ADDR_FILTER_EN		1
 
 #ifndef __ASSEMBLY__
-extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask);
+extern void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask);
 #if defined(CONFIG_CACHE_L2X0) && defined(CONFIG_OF)
-extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask);
+extern int l2x0_of_init(u32 aux_val, u32 aux_mask);
 #else
-static inline int l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+static inline int l2x0_of_init(u32 aux_val, u32 aux_mask)
 {
 	return -ENODEV;
 }
diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h
index 077c32326c63..2ff2c75a4639 100644
--- a/arch/arm/include/asm/hardware/iop3xx.h
+++ b/arch/arm/include/asm/hardware/iop3xx.h
@@ -231,6 +231,9 @@ extern int iop3xx_get_init_atu(void);
 
 
 #ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
 void iop3xx_map_io(void);
 void iop_init_cp6_handler(void);
 void iop_init_time(unsigned long tickrate);
diff --git a/arch/arm/include/asm/hardware/iop_adma.h b/arch/arm/include/asm/hardware/iop_adma.h
index 59b8c3892f76..122f86d8c991 100644
--- a/arch/arm/include/asm/hardware/iop_adma.h
+++ b/arch/arm/include/asm/hardware/iop_adma.h
@@ -49,7 +49,6 @@ struct iop_adma_device {
 /**
  * struct iop_adma_chan - internal representation of an ADMA device
  * @pending: allows batching of hardware operations
- * @completed_cookie: identifier for the most recently completed operation
  * @lock: serializes enqueue/dequeue operations to the slot pool
  * @mmr_base: memory mapped register base
  * @chain: device chain view of the descriptors
@@ -62,7 +61,6 @@ struct iop_adma_device {
  */
 struct iop_adma_chan {
 	int pending;
-	dma_cookie_t completed_cookie;
 	spinlock_t lock; /* protects the descriptor slot pool */
 	void __iomem *mmr_base;
 	struct list_head chain;
diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h
index 43cab498bc27..73f84fa4f366 100644
--- a/arch/arm/include/asm/hardware/it8152.h
+++ b/arch/arm/include/asm/hardware/it8152.h
@@ -9,6 +9,9 @@
 
 #ifndef __ASM_HARDWARE_IT8152_H
 #define __ASM_HARDWARE_IT8152_H
+
+#include <mach/irqs.h>
+
 extern void __iomem *it8152_base_address;
 
 #define IT8152_IO_BASE			(it8152_base_address + 0x03e00000)
diff --git a/arch/arm/include/asm/hardware/pl330.h b/arch/arm/include/asm/hardware/pl330.h
deleted file mode 100644
index c1821385abfa..000000000000
--- a/arch/arm/include/asm/hardware/pl330.h
+++ /dev/null
@@ -1,217 +0,0 @@
-/* linux/include/asm/hardware/pl330.h
- *
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#ifndef __PL330_CORE_H
-#define __PL330_CORE_H
-
-#define PL330_MAX_CHAN		8
-#define PL330_MAX_IRQS		32
-#define PL330_MAX_PERI		32
-
-enum pl330_srccachectrl {
-	SCCTRL0 = 0, /* Noncacheable and nonbufferable */
-	SCCTRL1, /* Bufferable only */
-	SCCTRL2, /* Cacheable, but do not allocate */
-	SCCTRL3, /* Cacheable and bufferable, but do not allocate */
-	SINVALID1,
-	SINVALID2,
-	SCCTRL6, /* Cacheable write-through, allocate on reads only */
-	SCCTRL7, /* Cacheable write-back, allocate on reads only */
-};
-
-enum pl330_dstcachectrl {
-	DCCTRL0 = 0, /* Noncacheable and nonbufferable */
-	DCCTRL1, /* Bufferable only */
-	DCCTRL2, /* Cacheable, but do not allocate */
-	DCCTRL3, /* Cacheable and bufferable, but do not allocate */
-	DINVALID1,              /* AWCACHE = 0x1000 */
-	DINVALID2,
-	DCCTRL6, /* Cacheable write-through, allocate on writes only */
-	DCCTRL7, /* Cacheable write-back, allocate on writes only */
-};
-
-/* Populated by the PL330 core driver for DMA API driver's info */
-struct pl330_config {
-	u32	periph_id;
-	u32	pcell_id;
-#define DMAC_MODE_NS	(1 << 0)
-	unsigned int	mode;
-	unsigned int	data_bus_width:10; /* In number of bits */
-	unsigned int	data_buf_dep:10;
-	unsigned int	num_chan:4;
-	unsigned int	num_peri:6;
-	u32		peri_ns;
-	unsigned int	num_events:6;
-	u32		irq_ns;
-};
-
-/* Handle to the DMAC provided to the PL330 core */
-struct pl330_info {
-	/* Owning device */
-	struct device *dev;
-	/* Size of MicroCode buffers for each channel. */
-	unsigned mcbufsz;
-	/* ioremap'ed address of PL330 registers. */
-	void __iomem	*base;
-	/* Client can freely use it. */
-	void	*client_data;
-	/* PL330 core data, Client must not touch it. */
-	void	*pl330_data;
-	/* Populated by the PL330 core driver during pl330_add */
-	struct pl330_config	pcfg;
-	/*
-	 * If the DMAC has some reset mechanism, then the
-	 * client may want to provide pointer to the method.
-	 */
-	void (*dmac_reset)(struct pl330_info *pi);
-};
-
-enum pl330_byteswap {
-	SWAP_NO = 0,
-	SWAP_2,
-	SWAP_4,
-	SWAP_8,
-	SWAP_16,
-};
-
-/**
- * Request Configuration.
- * The PL330 core does not modify this and uses the last
- * working configuration if the request doesn't provide any.
- *
- * The Client may want to provide this info only for the
- * first request and a request with new settings.
- */
-struct pl330_reqcfg {
-	/* Address Incrementing */
-	unsigned dst_inc:1;
-	unsigned src_inc:1;
-
-	/*
-	 * For now, the SRC & DST protection levels
-	 * and burst size/length are assumed same.
-	 */
-	bool nonsecure;
-	bool privileged;
-	bool insnaccess;
-	unsigned brst_len:5;
-	unsigned brst_size:3; /* in power of 2 */
-
-	enum pl330_dstcachectrl dcctl;
-	enum pl330_srccachectrl scctl;
-	enum pl330_byteswap swap;
-};
-
-/*
- * One cycle of DMAC operation.
- * There may be more than one xfer in a request.
- */
-struct pl330_xfer {
-	u32 src_addr;
-	u32 dst_addr;
-	/* Size to xfer */
-	u32 bytes;
-	/*
-	 * Pointer to next xfer in the list.
-	 * The last xfer in the req must point to NULL.
-	 */
-	struct pl330_xfer *next;
-};
-
-/* The xfer callbacks are made with one of these arguments. */
-enum pl330_op_err {
-	/* The all xfers in the request were success. */
-	PL330_ERR_NONE,
-	/* If req aborted due to global error. */
-	PL330_ERR_ABORT,
-	/* If req failed due to problem with Channel. */
-	PL330_ERR_FAIL,
-};
-
-enum pl330_reqtype {
-	MEMTOMEM,
-	MEMTODEV,
-	DEVTOMEM,
-	DEVTODEV,
-};
-
-/* A request defining Scatter-Gather List ending with NULL xfer. */
-struct pl330_req {
-	enum pl330_reqtype rqtype;
-	/* Index of peripheral for the xfer. */
-	unsigned peri:5;
-	/* Unique token for this xfer, set by the client. */
-	void *token;
-	/* Callback to be called after xfer. */
-	void (*xfer_cb)(void *token, enum pl330_op_err err);
-	/* If NULL, req will be done at last set parameters. */
-	struct pl330_reqcfg *cfg;
-	/* Pointer to first xfer in the request. */
-	struct pl330_xfer *x;
-};
-
-/*
- * To know the status of the channel and DMAC, the client
- * provides a pointer to this structure. The PL330 core
- * fills it with current information.
- */
-struct pl330_chanstatus {
-	/*
-	 * If the DMAC engine halted due to some error,
-	 * the client should remove-add DMAC.
-	 */
-	bool dmac_halted;
-	/*
-	 * If channel is halted due to some error,
-	 * the client should ABORT/FLUSH and START the channel.
-	 */
-	bool faulting;
-	/* Location of last load */
-	u32 src_addr;
-	/* Location of last store */
-	u32 dst_addr;
-	/*
-	 * Pointer to the currently active req, NULL if channel is
-	 * inactive, even though the requests may be present.
-	 */
-	struct pl330_req *top_req;
-	/* Pointer to req waiting second in the queue if any. */
-	struct pl330_req *wait_req;
-};
-
-enum pl330_chan_op {
-	/* Start the channel */
-	PL330_OP_START,
-	/* Abort the active xfer */
-	PL330_OP_ABORT,
-	/* Stop xfer and flush queue */
-	PL330_OP_FLUSH,
-};
-
-extern int pl330_add(struct pl330_info *);
-extern void pl330_del(struct pl330_info *pi);
-extern int pl330_update(const struct pl330_info *pi);
-extern void pl330_release_channel(void *ch_id);
-extern void *pl330_request_channel(const struct pl330_info *pi);
-extern int pl330_chan_status(void *ch_id, struct pl330_chanstatus *pstatus);
-extern int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op);
-extern int pl330_submit_req(void *ch_id, struct pl330_req *r);
-
-#endif	/* __PL330_CORE_H */
diff --git a/arch/arm/include/asm/hardware/sa1111.h b/arch/arm/include/asm/hardware/sa1111.h
index 92ed254c175b..7c2bbc7f0be1 100644
--- a/arch/arm/include/asm/hardware/sa1111.h
+++ b/arch/arm/include/asm/hardware/sa1111.h
@@ -132,34 +132,10 @@
 #define SKPCR_DCLKEN	(1<<7)
 #define SKPCR_PWMCLKEN	(1<<8)
 
-/*
- * USB Host controller
- */
+/* USB Host controller */
 #define SA1111_USB		0x0400
 
 /*
- * Offsets from SA1111_USB_BASE
- */
-#define SA1111_USB_STATUS	0x0118
-#define SA1111_USB_RESET	0x011c
-#define SA1111_USB_IRQTEST	0x0120
-
-#define USB_RESET_FORCEIFRESET	(1 << 0)
-#define USB_RESET_FORCEHCRESET	(1 << 1)
-#define USB_RESET_CLKGENRESET	(1 << 2)
-#define USB_RESET_SIMSCALEDOWN	(1 << 3)
-#define USB_RESET_USBINTTEST	(1 << 4)
-#define USB_RESET_SLEEPSTBYEN	(1 << 5)
-#define USB_RESET_PWRSENSELOW	(1 << 6)
-#define USB_RESET_PWRCTRLLOW	(1 << 7)
-
-#define USB_STATUS_IRQHCIRMTWKUP  (1 <<  7)
-#define USB_STATUS_IRQHCIBUFFACC  (1 <<  8)
-#define USB_STATUS_NIRQHCIM       (1 <<  9)
-#define USB_STATUS_NHCIMFCLR      (1 << 10)
-#define USB_STATUS_USBPWRSENSE    (1 << 11)
-
-/*
  * Serial Audio Controller
  *
  * Registers
@@ -327,22 +303,6 @@
  *    PC_SSR		GPIO Block C Sleep State
  */
 
-#define _PA_DDR		_SA1111( 0x1000 )
-#define _PA_DRR		_SA1111( 0x1004 )
-#define _PA_DWR		_SA1111( 0x1004 )
-#define _PA_SDR		_SA1111( 0x1008 )
-#define _PA_SSR		_SA1111( 0x100c )
-#define _PB_DDR		_SA1111( 0x1010 )
-#define _PB_DRR		_SA1111( 0x1014 )
-#define _PB_DWR		_SA1111( 0x1014 )
-#define _PB_SDR		_SA1111( 0x1018 )
-#define _PB_SSR		_SA1111( 0x101c )
-#define _PC_DDR		_SA1111( 0x1020 )
-#define _PC_DRR		_SA1111( 0x1024 )
-#define _PC_DWR		_SA1111( 0x1024 )
-#define _PC_SDR		_SA1111( 0x1028 )
-#define _PC_SSR		_SA1111( 0x102c )
-
 #define SA1111_GPIO	0x1000
 
 #define SA1111_GPIO_PADDR	(0x000)
@@ -425,106 +385,30 @@
 #define SA1111_WAKEPOL0		0x0034
 #define SA1111_WAKEPOL1		0x0038
 
-/*
- * PS/2 Trackpad and Mouse Interfaces
- *
- * Registers
- *    PS2CR		Control Register
- *    PS2STAT		Status Register
- *    PS2DATA		Transmit/Receive Data register
- *    PS2CLKDIV		Clock Division Register
- *    PS2PRECNT		Clock Precount Register
- *    PS2TEST1		Test register 1
- *    PS2TEST2		Test register 2
- *    PS2TEST3		Test register 3
- *    PS2TEST4		Test register 4
- */
-
+/* PS/2 Trackpad and Mouse Interfaces */
 #define SA1111_KBD		0x0a00
 #define SA1111_MSE		0x0c00
 
-/*
- * These are offsets from the above bases.
- */
-#define SA1111_PS2CR		0x0000
-#define SA1111_PS2STAT		0x0004
-#define SA1111_PS2DATA		0x0008
-#define SA1111_PS2CLKDIV	0x000c
-#define SA1111_PS2PRECNT	0x0010
-
-#define PS2CR_ENA		0x08
-#define PS2CR_FKD		0x02
-#define PS2CR_FKC		0x01
-
-#define PS2STAT_STP		0x0100
-#define PS2STAT_TXE		0x0080
-#define PS2STAT_TXB		0x0040
-#define PS2STAT_RXF		0x0020
-#define PS2STAT_RXB		0x0010
-#define PS2STAT_ENA		0x0008
-#define PS2STAT_RXP		0x0004
-#define PS2STAT_KBD		0x0002
-#define PS2STAT_KBC		0x0001
+/* PCMCIA Interface */
+#define SA1111_PCMCIA		0x1600
 
-/*
- * PCMCIA Interface
- *
- * Registers
- *    PCSR	Status Register
- *    PCCR	Control Register
- *    PCSSR	Sleep State Register
- */
-
-#define SA1111_PCMCIA	0x1600
-
-/*
- * These are offsets from the above base.
- */
-#define SA1111_PCCR	0x0000
-#define SA1111_PCSSR	0x0004
-#define SA1111_PCSR	0x0008
-
-#define PCSR_S0_READY	(1<<0)
-#define PCSR_S1_READY	(1<<1)
-#define PCSR_S0_DETECT	(1<<2)
-#define PCSR_S1_DETECT	(1<<3)
-#define PCSR_S0_VS1	(1<<4)
-#define PCSR_S0_VS2	(1<<5)
-#define PCSR_S1_VS1	(1<<6)
-#define PCSR_S1_VS2	(1<<7)
-#define PCSR_S0_WP	(1<<8)
-#define PCSR_S1_WP	(1<<9)
-#define PCSR_S0_BVD1	(1<<10)
-#define PCSR_S0_BVD2	(1<<11)
-#define PCSR_S1_BVD1	(1<<12)
-#define PCSR_S1_BVD2	(1<<13)
-
-#define PCCR_S0_RST	(1<<0)
-#define PCCR_S1_RST	(1<<1)
-#define PCCR_S0_FLT	(1<<2)
-#define PCCR_S1_FLT	(1<<3)
-#define PCCR_S0_PWAITEN	(1<<4)
-#define PCCR_S1_PWAITEN	(1<<5)
-#define PCCR_S0_PSE	(1<<6)
-#define PCCR_S1_PSE	(1<<7)
-
-#define PCSSR_S0_SLEEP	(1<<0)
-#define PCSSR_S1_SLEEP	(1<<1)
 
 
 
 
 extern struct bus_type sa1111_bus_type;
 
-#define SA1111_DEVID_SBI	0
-#define SA1111_DEVID_SK		1
-#define SA1111_DEVID_USB	2
-#define SA1111_DEVID_SAC	3
-#define SA1111_DEVID_SSP	4
-#define SA1111_DEVID_PS2	5
-#define SA1111_DEVID_GPIO	6
-#define SA1111_DEVID_INT	7
-#define SA1111_DEVID_PCMCIA	8
+#define SA1111_DEVID_SBI	(1 << 0)
+#define SA1111_DEVID_SK		(1 << 1)
+#define SA1111_DEVID_USB	(1 << 2)
+#define SA1111_DEVID_SAC	(1 << 3)
+#define SA1111_DEVID_SSP	(1 << 4)
+#define SA1111_DEVID_PS2	(3 << 5)
+#define SA1111_DEVID_PS2_KBD	(1 << 5)
+#define SA1111_DEVID_PS2_MSE	(1 << 6)
+#define SA1111_DEVID_GPIO	(1 << 7)
+#define SA1111_DEVID_INT	(1 << 8)
+#define SA1111_DEVID_PCMCIA	(1 << 9)
 
 struct sa1111_dev {
 	struct device	dev;
@@ -548,6 +432,7 @@ struct sa1111_driver {
 	int (*remove)(struct sa1111_dev *);
 	int (*suspend)(struct sa1111_dev *, pm_message_t);
 	int (*resume)(struct sa1111_dev *);
+	void (*shutdown)(struct sa1111_dev *);
 };
 
 #define SA1111_DRV(_d)	container_of((_d), struct sa1111_driver, drv)
@@ -555,9 +440,10 @@ struct sa1111_driver {
 #define SA1111_DRIVER_NAME(_sadev) ((_sadev)->dev.driver->name)
 
 /*
- * These frob the SKPCR register.
+ * These frob the SKPCR register, and call platform specific
+ * enable/disable functions.
  */
-void sa1111_enable_device(struct sa1111_dev *);
+int sa1111_enable_device(struct sa1111_dev *);
 void sa1111_disable_device(struct sa1111_dev *);
 
 unsigned int sa1111_pll_clock(struct sa1111_dev *);
@@ -580,6 +466,10 @@ void sa1111_set_sleep_io(struct sa1111_dev *sadev, unsigned int bits, unsigned i
 
 struct sa1111_platform_data {
 	int	irq_base;	/* base for cascaded on-chip IRQs */
+	unsigned disable_devs;
+	void	*data;
+	int	(*enable)(void *, unsigned);
+	void	(*disable)(void *, unsigned);
 };
 
 #endif  /* _ASM_ARCH_SA1111 */
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 9275828feb3d..9af5563dd3eb 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -26,7 +26,6 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <asm/memory.h>
-#include <asm/system.h>
 #include <asm-generic/pci_iomap.h>
 
 /*
@@ -83,6 +82,11 @@ extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, uns
 extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
+extern void __arm_iounmap(volatile void __iomem *addr);
+
+extern void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+	unsigned int, void *);
+extern void (*arch_iounmap)(volatile void __iomem *);
 
 /*
  * Bad read/write accesses...
@@ -97,8 +101,11 @@ static inline void __iomem *__typesafe_io(unsigned long addr)
 	return (void __iomem *)addr;
 }
 
+#define IOMEM(x)	((void __force __iomem *)(x))
+
 /* IO barriers */
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+#include <asm/barrier.h>
 #define __iormb()		rmb()
 #define __iowmb()		wmb()
 #else
@@ -109,7 +116,11 @@ static inline void __iomem *__typesafe_io(unsigned long addr)
 /*
  * Now, pick up the machine-defined IO definitions
  */
+#ifdef CONFIG_NEED_MACH_IO_H
 #include <mach/io.h>
+#else
+#define __io(a)		__typesafe_io((a) & IO_SPACE_LIMIT)
+#endif
 
 /*
  * This is the limit of PC card/PCI/ISA IO space, which is by default
@@ -211,18 +222,18 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
  * Again, this are defined to perform little endian accesses.  See the
  * IO port primitives for more information.
  */
-#ifdef __mem_pci
-#define readb_relaxed(c) ({ u8  __r = __raw_readb(__mem_pci(c)); __r; })
+#ifndef readl
+#define readb_relaxed(c) ({ u8  __r = __raw_readb(c); __r; })
 #define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \
-					__raw_readw(__mem_pci(c))); __r; })
+					__raw_readw(c)); __r; })
 #define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \
-					__raw_readl(__mem_pci(c))); __r; })
+					__raw_readl(c)); __r; })
 
-#define writeb_relaxed(v,c)	((void)__raw_writeb(v,__mem_pci(c)))
+#define writeb_relaxed(v,c)	((void)__raw_writeb(v,c))
 #define writew_relaxed(v,c)	((void)__raw_writew((__force u16) \
-					cpu_to_le16(v),__mem_pci(c)))
+					cpu_to_le16(v),c))
 #define writel_relaxed(v,c)	((void)__raw_writel((__force u32) \
-					cpu_to_le32(v),__mem_pci(c)))
+					cpu_to_le32(v),c))
 
 #define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
 #define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
@@ -232,30 +243,19 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 #define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
 #define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
 
-#define readsb(p,d,l)		__raw_readsb(__mem_pci(p),d,l)
-#define readsw(p,d,l)		__raw_readsw(__mem_pci(p),d,l)
-#define readsl(p,d,l)		__raw_readsl(__mem_pci(p),d,l)
-
-#define writesb(p,d,l)		__raw_writesb(__mem_pci(p),d,l)
-#define writesw(p,d,l)		__raw_writesw(__mem_pci(p),d,l)
-#define writesl(p,d,l)		__raw_writesl(__mem_pci(p),d,l)
+#define readsb(p,d,l)		__raw_readsb(p,d,l)
+#define readsw(p,d,l)		__raw_readsw(p,d,l)
+#define readsl(p,d,l)		__raw_readsl(p,d,l)
 
-#define memset_io(c,v,l)	_memset_io(__mem_pci(c),(v),(l))
-#define memcpy_fromio(a,c,l)	_memcpy_fromio((a),__mem_pci(c),(l))
-#define memcpy_toio(c,a,l)	_memcpy_toio(__mem_pci(c),(a),(l))
+#define writesb(p,d,l)		__raw_writesb(p,d,l)
+#define writesw(p,d,l)		__raw_writesw(p,d,l)
+#define writesl(p,d,l)		__raw_writesl(p,d,l)
 
-#elif !defined(readb)
+#define memset_io(c,v,l)	_memset_io(c,(v),(l))
+#define memcpy_fromio(a,c,l)	_memcpy_fromio((a),c,(l))
+#define memcpy_toio(c,a,l)	_memcpy_toio(c,(a),(l))
 
-#define readb(c)			(__readwrite_bug("readb"),0)
-#define readw(c)			(__readwrite_bug("readw"),0)
-#define readl(c)			(__readwrite_bug("readl"),0)
-#define writeb(v,c)			__readwrite_bug("writeb")
-#define writew(v,c)			__readwrite_bug("writew")
-#define writel(v,c)			__readwrite_bug("writel")
-
-#define check_signature(io,sig,len)	(0)
-
-#endif	/* __mem_pci */
+#endif	/* readl */
 
 /*
  * ioremap and friends.
@@ -264,16 +264,11 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
  * Documentation/io-mapping.txt.
  *
  */
-#ifndef __arch_ioremap
-#define __arch_ioremap			__arm_ioremap
-#define __arch_iounmap			__iounmap
-#endif
-
-#define ioremap(cookie,size)		__arch_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arch_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cached(cookie,size)	__arch_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arch_ioremap((cookie), (size), MT_DEVICE_WC)
-#define iounmap				__arch_iounmap
+#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
+#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
+#define ioremap_cached(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
+#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
+#define iounmap				__arm_iounmap
 
 /*
  * io{read,write}{8,16,32} macros
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 5a526afb5f18..35c21c375d81 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -1,14 +1,18 @@
 #ifndef __ASM_ARM_IRQ_H
 #define __ASM_ARM_IRQ_H
 
+#define NR_IRQS_LEGACY	16
+
+#ifndef CONFIG_SPARSE_IRQ
 #include <mach/irqs.h>
+#else
+#define NR_IRQS NR_IRQS_LEGACY
+#endif
 
 #ifndef irq_canonicalize
 #define irq_canonicalize(i)	(i)
 #endif
 
-#define NR_IRQS_LEGACY	16
-
 /*
  * Use this value to indicate lack of interrupt
  * capability
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
new file mode 100644
index 000000000000..5c5ca2ea62b0
--- /dev/null
+++ b/arch/arm/include/asm/jump_label.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_ARM_JUMP_LABEL_H
+#define _ASM_ARM_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/system.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define JUMP_LABEL_NOP	"nop.w"
+#else
+#define JUMP_LABEL_NOP	"nop"
+#endif
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:\n\t"
+		 JUMP_LABEL_NOP "\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 : :  "i" (key) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+#endif /* __KERNEL__ */
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif
diff --git a/arch/arm/include/asm/mc146818rtc.h b/arch/arm/include/asm/mc146818rtc.h
index 6b884d2b0b69..e8567bb99dfc 100644
--- a/arch/arm/include/asm/mc146818rtc.h
+++ b/arch/arm/include/asm/mc146818rtc.h
@@ -5,7 +5,9 @@
 #define _ASM_MC146818RTC_H
 
 #include <linux/io.h>
-#include <mach/irqs.h>
+#include <linux/kernel.h>
+
+#define RTC_IRQ BUILD_BUG_ON(1)
 
 #ifndef RTC_PORT
 #define RTC_PORT(x)	(0x70 + (x))
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index a8997d71084e..fcb575747e5e 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -116,6 +116,8 @@
 #define MODULES_END		(END_MEM)
 #define MODULES_VADDR		(PHYS_OFFSET)
 
+#define XIP_VIRT_ADDR(physaddr)  (physaddr)
+
 #endif /* !CONFIG_MMU */
 
 /*
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index 14965658a923..b8e580a297e4 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -34,4 +34,11 @@ typedef struct {
 
 #endif
 
+/*
+ * switch_mm() may do a full cache flush over the context switch,
+ * so enable interrupts over the context switch to avoid high
+ * latency.
+ */
+#define __ARCH_WANT_INTERRUPTS_ON_CTXSW
+
 #endif
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 71605d9f8e42..a0b3cac0547c 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
+#include <asm-generic/mm_hooks.h>
 
 void __check_kvm_seq(struct mm_struct *mm);
 
@@ -133,32 +134,4 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 #define deactivate_mm(tsk,mm)	do { } while (0)
 #define activate_mm(prev,next)	switch_mm(prev, next, NULL)
 
-/*
- * We are inserting a "fake" vma for the user-accessible vector page so
- * gdb and friends can get to it through ptrace and /proc/<pid>/mem.
- * But we also want to remove it before the generic code gets to see it
- * during process exit or the unmapping of it would  cause total havoc.
- * (the macro is used as remove_vma() is static to mm/mmap.c)
- */
-#define arch_exit_mmap(mm) \
-do { \
-	struct vm_area_struct *high_vma = find_vma(mm, 0xffff0000); \
-	if (high_vma) { \
-		BUG_ON(high_vma->vm_next);  /* it should be last */ \
-		if (high_vma->vm_prev) \
-			high_vma->vm_prev->vm_next = NULL; \
-		else \
-			mm->mmap = NULL; \
-		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
-		mm->mmap_cache = NULL; \
-		mm->map_count--; \
-		remove_vma(high_vma); \
-	} \
-} while (0)
-
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
-{
-}
-
 #endif
diff --git a/arch/arm/include/asm/opcodes.h b/arch/arm/include/asm/opcodes.h
index c0efdd60966f..19c48deda70f 100644
--- a/arch/arm/include/asm/opcodes.h
+++ b/arch/arm/include/asm/opcodes.h
@@ -17,4 +17,63 @@ extern asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr);
 #define ARM_OPCODE_CONDTEST_PASS   1
 #define ARM_OPCODE_CONDTEST_UNCOND 2
 
+
+/*
+ * Opcode byteswap helpers
+ *
+ * These macros help with converting instructions between a canonical integer
+ * format and in-memory representation, in an endianness-agnostic manner.
+ *
+ * __mem_to_opcode_*() convert from in-memory representation to canonical form.
+ * __opcode_to_mem_*() convert from canonical form to in-memory representation.
+ *
+ *
+ * Canonical instruction representation:
+ *
+ *	ARM:		0xKKLLMMNN
+ *	Thumb 16-bit:	0x0000KKLL, where KK < 0xE8
+ *	Thumb 32-bit:	0xKKLLMMNN, where KK >= 0xE8
+ *
+ * There is no way to distinguish an ARM instruction in canonical representation
+ * from a Thumb instruction (just as these cannot be distinguished in memory).
+ * Where this distinction is important, it needs to be tracked separately.
+ *
+ * Note that values in the range 0x0000E800..0xE7FFFFFF intentionally do not
+ * represent any valid Thumb-2 instruction.  For this range,
+ * __opcode_is_thumb32() and __opcode_is_thumb16() will both be false.
+ */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/swab.h>
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define __opcode_to_mem_arm(x) swab32(x)
+#define __opcode_to_mem_thumb16(x) swab16(x)
+#define __opcode_to_mem_thumb32(x) swahb32(x)
+#else
+#define __opcode_to_mem_arm(x) ((u32)(x))
+#define __opcode_to_mem_thumb16(x) ((u16)(x))
+#define __opcode_to_mem_thumb32(x) swahw32(x)
+#endif
+
+#define __mem_to_opcode_arm(x) __opcode_to_mem_arm(x)
+#define __mem_to_opcode_thumb16(x) __opcode_to_mem_thumb16(x)
+#define __mem_to_opcode_thumb32(x) __opcode_to_mem_thumb32(x)
+
+/* Operations specific to Thumb opcodes */
+
+/* Instruction size checks: */
+#define __opcode_is_thumb32(x) ((u32)(x) >= 0xE8000000UL)
+#define __opcode_is_thumb16(x) ((u32)(x) < 0xE800UL)
+
+/* Operations to construct or split 32-bit Thumb instructions: */
+#define __opcode_thumb32_first(x) ((u16)((x) >> 16))
+#define __opcode_thumb32_second(x) ((u16)(x))
+#define __opcode_thumb32_compose(first, second) \
+	(((u32)(u16)(first) << 16) | (u32)(u16)(second))
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* __ASM_ARM_OPCODES_H */
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 97b440c25c58..5838361c48b3 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -151,6 +151,8 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
+#define __HAVE_ARCH_GATE_AREA 1
+
 #ifdef CONFIG_ARM_LPAE
 #include <asm/pgtable-3level-types.h>
 #else
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 7523340afb8a..00cbe10a50e3 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -22,6 +22,7 @@ enum arm_perf_pmu_ids {
 	ARM_PERF_PMU_ID_CA9,
 	ARM_PERF_PMU_ID_CA5,
 	ARM_PERF_PMU_ID_CA15,
+	ARM_PERF_PMU_ID_CA7,
 	ARM_NUM_PMU_IDS,
 };
 
diff --git a/arch/arm/include/asm/posix_types.h b/arch/arm/include/asm/posix_types.h
index 2446d23bfdbf..efdf99045d87 100644
--- a/arch/arm/include/asm/posix_types.h
+++ b/arch/arm/include/asm/posix_types.h
@@ -19,59 +19,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long		__kernel_ino_t;
 typedef unsigned short		__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short		__kernel_nlink_t;
-typedef long			__kernel_off_t;
-typedef int			__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short		__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short		__kernel_uid_t;
 typedef unsigned short		__kernel_gid_t;
-typedef unsigned int		__kernel_size_t;
-typedef int			__kernel_ssize_t;
-typedef int			__kernel_ptrdiff_t;
-typedef long			__kernel_time_t;
-typedef long			__kernel_suseconds_t;
-typedef long			__kernel_clock_t;
-typedef int			__kernel_timer_t;
-typedef int			__kernel_clockid_t;
-typedef int			__kernel_daddr_t;
-typedef char *			__kernel_caddr_t;
-typedef unsigned short		__kernel_uid16_t;
-typedef unsigned short		__kernel_gid16_t;
-typedef unsigned int		__kernel_uid32_t;
-typedef unsigned int		__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short		__kernel_old_uid_t;
-typedef unsigned short		__kernel_old_gid_t;
 typedef unsigned short		__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long		__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define __FD_SET(fd, fdsetp) \
-		(((fd_set *)(fdsetp))->fds_bits[(fd) >> 5] |= (1<<((fd) & 31)))
-
-#undef	__FD_CLR
-#define __FD_CLR(fd, fdsetp) \
-		(((fd_set *)(fdsetp))->fds_bits[(fd) >> 5] &= ~(1<<((fd) & 31)))
-
-#undef	__FD_ISSET
-#define __FD_ISSET(fd, fdsetp) \
-		((((fd_set *)(fdsetp))->fds_bits[(fd) >> 5] & (1<<((fd) & 31))) != 0)
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) \
-		(memset (fdsetp, 0, sizeof (*(fd_set *)(fdsetp))))
-
-#endif
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index cb8d638924fd..5ac8d3d3e025 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -22,7 +22,6 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
-#include <asm/system.h>
 
 #ifdef __KERNEL__
 #define STACK_TOP	((current->personality & ADDR_LIMIT_32BIT) ? \
@@ -56,7 +55,6 @@ struct thread_struct {
 #define start_thread(regs,pc,sp)					\
 ({									\
 	unsigned long *stack = (unsigned long *)sp;			\
-	set_fs(USER_DS);						\
 	memset(regs->uregs, 0, sizeof(regs->uregs));			\
 	if (current->personality & ADDR_LIMIT_32BIT)			\
 		regs->ARM_cpsr = USR_MODE;				\
@@ -90,6 +88,8 @@ unsigned long get_wchan(struct task_struct *p);
 #define cpu_relax()			barrier()
 #endif
 
+void cpu_idle_wait(void);
+
 /*
  * Create a new kernel thread
  */
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
index ee0363307918..aeae9c609df4 100644
--- a/arch/arm/include/asm/prom.h
+++ b/arch/arm/include/asm/prom.h
@@ -13,8 +13,6 @@
 
 #ifdef CONFIG_OF
 
-#include <asm/irq.h>
-
 extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
 extern void arm_dt_memblock_reserve(void);
 
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
new file mode 100644
index 000000000000..fa09e6b49bf1
--- /dev/null
+++ b/arch/arm/include/asm/switch_to.h
@@ -0,0 +1,18 @@
+#ifndef __ASM_ARM_SWITCH_TO_H
+#define __ASM_ARM_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+
+/*
+ * switch_to(prev, next) should switch from task `prev' to `next'
+ * `prev' will never be the same as `next'.  schedule() itself
+ * contains the memory barrier to tell GCC not to cache `current'.
+ */
+extern struct task_struct *__switch_to(struct task_struct *, struct thread_info *, struct thread_info *);
+
+#define switch_to(prev,next,last)					\
+do {									\
+	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
+} while (0)
+
+#endif /* __ASM_ARM_SWITCH_TO_H */
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 424aa458c487..74542c52f9be 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -1,544 +1,8 @@
-#ifndef __ASM_ARM_SYSTEM_H
-#define __ASM_ARM_SYSTEM_H
-
-#ifdef __KERNEL__
-
-#define CPU_ARCH_UNKNOWN	0
-#define CPU_ARCH_ARMv3		1
-#define CPU_ARCH_ARMv4		2
-#define CPU_ARCH_ARMv4T		3
-#define CPU_ARCH_ARMv5		4
-#define CPU_ARCH_ARMv5T		5
-#define CPU_ARCH_ARMv5TE	6
-#define CPU_ARCH_ARMv5TEJ	7
-#define CPU_ARCH_ARMv6		8
-#define CPU_ARCH_ARMv7		9
-
-/*
- * CR1 bits (CP#15 CR1)
- */
-#define CR_M	(1 << 0)	/* MMU enable				*/
-#define CR_A	(1 << 1)	/* Alignment abort enable		*/
-#define CR_C	(1 << 2)	/* Dcache enable			*/
-#define CR_W	(1 << 3)	/* Write buffer enable			*/
-#define CR_P	(1 << 4)	/* 32-bit exception handler		*/
-#define CR_D	(1 << 5)	/* 32-bit data address range		*/
-#define CR_L	(1 << 6)	/* Implementation defined		*/
-#define CR_B	(1 << 7)	/* Big endian				*/
-#define CR_S	(1 << 8)	/* System MMU protection		*/
-#define CR_R	(1 << 9)	/* ROM MMU protection			*/
-#define CR_F	(1 << 10)	/* Implementation defined		*/
-#define CR_Z	(1 << 11)	/* Implementation defined		*/
-#define CR_I	(1 << 12)	/* Icache enable			*/
-#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
-#define CR_RR	(1 << 14)	/* Round Robin cache replacement	*/
-#define CR_L4	(1 << 15)	/* LDR pc can set T bit			*/
-#define CR_DT	(1 << 16)
-#define CR_IT	(1 << 18)
-#define CR_ST	(1 << 19)
-#define CR_FI	(1 << 21)	/* Fast interrupt (lower latency mode)	*/
-#define CR_U	(1 << 22)	/* Unaligned access operation		*/
-#define CR_XP	(1 << 23)	/* Extended page tables			*/
-#define CR_VE	(1 << 24)	/* Vectored interrupts			*/
-#define CR_EE	(1 << 25)	/* Exception (Big) Endian		*/
-#define CR_TRE	(1 << 28)	/* TEX remap enable			*/
-#define CR_AFE	(1 << 29)	/* Access flag enable			*/
-#define CR_TE	(1 << 30)	/* Thumb exception enable		*/
-
-/*
- * This is used to ensure the compiler did actually allocate the register we
- * asked it for some inline assembly sequences.  Apparently we can't trust
- * the compiler from one version to another so a bit of paranoia won't hurt.
- * This string is meant to be concatenated with the inline asm string and
- * will cause compilation to stop on mismatch.
- * (for details, see gcc PR 15089)
- */
-#define __asmeq(x, y)  ".ifnc " x "," y " ; .err ; .endif\n\t"
-
-#ifndef __ASSEMBLY__
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <linux/irqflags.h>
-
-#include <asm/outercache.h>
-
-struct thread_info;
-struct task_struct;
-
-/* information about the system we're running on */
-extern unsigned int system_rev;
-extern unsigned int system_serial_low;
-extern unsigned int system_serial_high;
-extern unsigned int mem_fclk_21285;
-
-struct pt_regs;
-
-void die(const char *msg, struct pt_regs *regs, int err);
-
-struct siginfo;
-void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
-		unsigned long err, unsigned long trap);
-
-#ifdef CONFIG_ARM_LPAE
-#define FAULT_CODE_ALIGNMENT	33
-#define FAULT_CODE_DEBUG	34
-#else
-#define FAULT_CODE_ALIGNMENT	1
-#define FAULT_CODE_DEBUG	2
-#endif
-
-void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
-				       struct pt_regs *),
-		     int sig, int code, const char *name);
-
-void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int,
-				       struct pt_regs *),
-		     int sig, int code, const char *name);
-
-#define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
-
-struct mm_struct;
-extern void show_pte(struct mm_struct *mm, unsigned long addr);
-extern void __show_regs(struct pt_regs *);
-
-extern int __pure cpu_architecture(void);
-extern void cpu_init(void);
-
-void soft_restart(unsigned long);
-extern void (*arm_pm_restart)(char str, const char *cmd);
-extern void (*arm_pm_idle)(void);
-
-#define UDBG_UNDEFINED	(1 << 0)
-#define UDBG_SYSCALL	(1 << 1)
-#define UDBG_BADABORT	(1 << 2)
-#define UDBG_SEGV	(1 << 3)
-#define UDBG_BUS	(1 << 4)
-
-extern unsigned int user_debug;
-
-#if __LINUX_ARM_ARCH__ >= 4
-#define vectors_high()	(cr_alignment & CR_V)
-#else
-#define vectors_high()	(0)
-#endif
-
-#if __LINUX_ARM_ARCH__ >= 7 ||		\
-	(__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K))
-#define sev()	__asm__ __volatile__ ("sev" : : : "memory")
-#define wfe()	__asm__ __volatile__ ("wfe" : : : "memory")
-#define wfi()	__asm__ __volatile__ ("wfi" : : : "memory")
-#endif
-
-#if __LINUX_ARM_ARCH__ >= 7
-#define isb() __asm__ __volatile__ ("isb" : : : "memory")
-#define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
-#define dmb() __asm__ __volatile__ ("dmb" : : : "memory")
-#elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
-#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
-				    : : "r" (0) : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
-				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
-				    : : "r" (0) : "memory")
-#elif defined(CONFIG_CPU_FA526)
-#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
-				    : : "r" (0) : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
-				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
-#else
-#define isb() __asm__ __volatile__ ("" : : : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
-				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
-#endif
-
-#ifdef CONFIG_ARCH_HAS_BARRIERS
-#include <mach/barriers.h>
-#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
-#define mb()		do { dsb(); outer_sync(); } while (0)
-#define rmb()		dsb()
-#define wmb()		mb()
-#else
-#include <asm/memory.h>
-#define mb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
-#define rmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
-#define wmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
-#endif
-
-#ifndef CONFIG_SMP
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#else
-#define smp_mb()	dmb()
-#define smp_rmb()	dmb()
-#define smp_wmb()	dmb()
-#endif
-
-#define read_barrier_depends()		do { } while(0)
-#define smp_read_barrier_depends()	do { } while(0)
-
-#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
-#define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
-
-extern unsigned long cr_no_alignment;	/* defined in entry-armv.S */
-extern unsigned long cr_alignment;	/* defined in entry-armv.S */
-
-static inline unsigned int get_cr(void)
-{
-	unsigned int val;
-	asm("mrc p15, 0, %0, c1, c0, 0	@ get CR" : "=r" (val) : : "cc");
-	return val;
-}
-
-static inline void set_cr(unsigned int val)
-{
-	asm volatile("mcr p15, 0, %0, c1, c0, 0	@ set CR"
-	  : : "r" (val) : "cc");
-	isb();
-}
-
-#ifndef CONFIG_SMP
-extern void adjust_cr(unsigned long mask, unsigned long set);
-#endif
-
-#define CPACC_FULL(n)		(3 << (n * 2))
-#define CPACC_SVC(n)		(1 << (n * 2))
-#define CPACC_DISABLE(n)	(0 << (n * 2))
-
-static inline unsigned int get_copro_access(void)
-{
-	unsigned int val;
-	asm("mrc p15, 0, %0, c1, c0, 2 @ get copro access"
-	  : "=r" (val) : : "cc");
-	return val;
-}
-
-static inline void set_copro_access(unsigned int val)
-{
-	asm volatile("mcr p15, 0, %0, c1, c0, 2 @ set copro access"
-	  : : "r" (val) : "cc");
-	isb();
-}
-
-/*
- * switch_mm() may do a full cache flush over the context switch,
- * so enable interrupts over the context switch to avoid high
- * latency.
- */
-#define __ARCH_WANT_INTERRUPTS_ON_CTXSW
-
-/*
- * switch_to(prev, next) should switch from task `prev' to `next'
- * `prev' will never be the same as `next'.  schedule() itself
- * contains the memory barrier to tell GCC not to cache `current'.
- */
-extern struct task_struct *__switch_to(struct task_struct *, struct thread_info *, struct thread_info *);
-
-#define switch_to(prev,next,last)					\
-do {									\
-	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
-} while (0)
-
-#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
-/*
- * On the StrongARM, "swp" is terminally broken since it bypasses the
- * cache totally.  This means that the cache becomes inconsistent, and,
- * since we use normal loads/stores as well, this is really bad.
- * Typically, this causes oopsen in filp_close, but could have other,
- * more disastrous effects.  There are two work-arounds:
- *  1. Disable interrupts and emulate the atomic swap
- *  2. Clean the cache, perform atomic swap, flush the cache
- *
- * We choose (1) since its the "easiest" to achieve here and is not
- * dependent on the processor type.
- *
- * NOTE that this solution won't work on an SMP system, so explcitly
- * forbid it here.
- */
-#define swp_is_buggy
-#endif
-
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
-{
-	extern void __bad_xchg(volatile void *, int);
-	unsigned long ret;
-#ifdef swp_is_buggy
-	unsigned long flags;
-#endif
-#if __LINUX_ARM_ARCH__ >= 6
-	unsigned int tmp;
-#endif
-
-	smp_mb();
-
-	switch (size) {
-#if __LINUX_ARM_ARCH__ >= 6
-	case 1:
-		asm volatile("@	__xchg1\n"
-		"1:	ldrexb	%0, [%3]\n"
-		"	strexb	%1, %2, [%3]\n"
-		"	teq	%1, #0\n"
-		"	bne	1b"
-			: "=&r" (ret), "=&r" (tmp)
-			: "r" (x), "r" (ptr)
-			: "memory", "cc");
-		break;
-	case 4:
-		asm volatile("@	__xchg4\n"
-		"1:	ldrex	%0, [%3]\n"
-		"	strex	%1, %2, [%3]\n"
-		"	teq	%1, #0\n"
-		"	bne	1b"
-			: "=&r" (ret), "=&r" (tmp)
-			: "r" (x), "r" (ptr)
-			: "memory", "cc");
-		break;
-#elif defined(swp_is_buggy)
-#ifdef CONFIG_SMP
-#error SMP is not supported on this platform
-#endif
-	case 1:
-		raw_local_irq_save(flags);
-		ret = *(volatile unsigned char *)ptr;
-		*(volatile unsigned char *)ptr = x;
-		raw_local_irq_restore(flags);
-		break;
-
-	case 4:
-		raw_local_irq_save(flags);
-		ret = *(volatile unsigned long *)ptr;
-		*(volatile unsigned long *)ptr = x;
-		raw_local_irq_restore(flags);
-		break;
-#else
-	case 1:
-		asm volatile("@	__xchg1\n"
-		"	swpb	%0, %1, [%2]"
-			: "=&r" (ret)
-			: "r" (x), "r" (ptr)
-			: "memory", "cc");
-		break;
-	case 4:
-		asm volatile("@	__xchg4\n"
-		"	swp	%0, %1, [%2]"
-			: "=&r" (ret)
-			: "r" (x), "r" (ptr)
-			: "memory", "cc");
-		break;
-#endif
-	default:
-		__bad_xchg(ptr, size), ret = 0;
-		break;
-	}
-	smp_mb();
-
-	return ret;
-}
-
-extern void disable_hlt(void);
-extern void enable_hlt(void);
-
-void cpu_idle_wait(void);
-
-#include <asm-generic/cmpxchg-local.h>
-
-#if __LINUX_ARM_ARCH__ < 6
-/* min ARCH < ARMv6 */
-
-#ifdef CONFIG_SMP
-#error "SMP is not supported on this platform"
-#endif
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#ifndef CONFIG_SMP
-#include <asm-generic/cmpxchg.h>
-#endif
-
-#else	/* min ARCH >= ARMv6 */
-
-extern void __bad_cmpxchg(volatile void *ptr, int size);
-
-/*
- * cmpxchg only support 32-bits operands on ARMv6.
- */
-
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-				      unsigned long new, int size)
-{
-	unsigned long oldval, res;
-
-	switch (size) {
-#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
-	case 1:
-		do {
-			asm volatile("@ __cmpxchg1\n"
-			"	ldrexb	%1, [%2]\n"
-			"	mov	%0, #0\n"
-			"	teq	%1, %3\n"
-			"	strexbeq %0, %4, [%2]\n"
-				: "=&r" (res), "=&r" (oldval)
-				: "r" (ptr), "Ir" (old), "r" (new)
-				: "memory", "cc");
-		} while (res);
-		break;
-	case 2:
-		do {
-			asm volatile("@ __cmpxchg1\n"
-			"	ldrexh	%1, [%2]\n"
-			"	mov	%0, #0\n"
-			"	teq	%1, %3\n"
-			"	strexheq %0, %4, [%2]\n"
-				: "=&r" (res), "=&r" (oldval)
-				: "r" (ptr), "Ir" (old), "r" (new)
-				: "memory", "cc");
-		} while (res);
-		break;
-#endif
-	case 4:
-		do {
-			asm volatile("@ __cmpxchg4\n"
-			"	ldrex	%1, [%2]\n"
-			"	mov	%0, #0\n"
-			"	teq	%1, %3\n"
-			"	strexeq %0, %4, [%2]\n"
-				: "=&r" (res), "=&r" (oldval)
-				: "r" (ptr), "Ir" (old), "r" (new)
-				: "memory", "cc");
-		} while (res);
-		break;
-	default:
-		__bad_cmpxchg(ptr, size);
-		oldval = 0;
-	}
-
-	return oldval;
-}
-
-static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
-					 unsigned long new, int size)
-{
-	unsigned long ret;
-
-	smp_mb();
-	ret = __cmpxchg(ptr, old, new, size);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
-					  (unsigned long)(o),		\
-					  (unsigned long)(n),		\
-					  sizeof(*(ptr))))
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-					    unsigned long old,
-					    unsigned long new, int size)
-{
-	unsigned long ret;
-
-	switch (size) {
-#ifdef CONFIG_CPU_V6	/* min ARCH == ARMv6 */
-	case 1:
-	case 2:
-		ret = __cmpxchg_local_generic(ptr, old, new, size);
-		break;
-#endif
-	default:
-		ret = __cmpxchg(ptr, old, new, size);
-	}
-
-	return ret;
-}
-
-#define cmpxchg_local(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
-				       (unsigned long)(o),		\
-				       (unsigned long)(n),		\
-				       sizeof(*(ptr))))
-
-#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
-
-/*
- * Note : ARMv7-M (currently unsupported by Linux) does not support
- * ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should
- * not be allowed to use __cmpxchg64.
- */
-static inline unsigned long long __cmpxchg64(volatile void *ptr,
-					     unsigned long long old,
-					     unsigned long long new)
-{
-	register unsigned long long oldval asm("r0");
-	register unsigned long long __old asm("r2") = old;
-	register unsigned long long __new asm("r4") = new;
-	unsigned long res;
-
-	do {
-		asm volatile(
-		"	@ __cmpxchg8\n"
-		"	ldrexd	%1, %H1, [%2]\n"
-		"	mov	%0, #0\n"
-		"	teq	%1, %3\n"
-		"	teqeq	%H1, %H3\n"
-		"	strexdeq %0, %4, %H4, [%2]\n"
-			: "=&r" (res), "=&r" (oldval)
-			: "r" (ptr), "Ir" (__old), "r" (__new)
-			: "memory", "cc");
-	} while (res);
-
-	return oldval;
-}
-
-static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
-						unsigned long long old,
-						unsigned long long new)
-{
-	unsigned long long ret;
-
-	smp_mb();
-	ret = __cmpxchg64(ptr, old, new);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg64(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
-					    (unsigned long long)(o),	\
-					    (unsigned long long)(n)))
-
-#define cmpxchg64_local(ptr,o,n)					\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
-					 (unsigned long long)(o),	\
-					 (unsigned long long)(n)))
-
-#else /* min ARCH = ARMv6 */
-
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#endif
-
-#endif	/* __LINUX_ARM_ARCH__ >= 6 */
-
-#endif /* __ASSEMBLY__ */
-
-#define arch_align_stack(x) (x)
-
-#endif /* __KERNEL__ */
-
-#endif
+/* FILE TO BE DELETED. DO NOT ADD STUFF HERE! */
+#include <asm/barrier.h>
+#include <asm/compiler.h>
+#include <asm/cmpxchg.h>
+#include <asm/exec.h>
+#include <asm/switch_to.h>
+#include <asm/system_info.h>
+#include <asm/system_misc.h>
diff --git a/arch/arm/include/asm/system_info.h b/arch/arm/include/asm/system_info.h
new file mode 100644
index 000000000000..dfd386d0c022
--- /dev/null
+++ b/arch/arm/include/asm/system_info.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_ARM_SYSTEM_INFO_H
+#define __ASM_ARM_SYSTEM_INFO_H
+
+#define CPU_ARCH_UNKNOWN	0
+#define CPU_ARCH_ARMv3		1
+#define CPU_ARCH_ARMv4		2
+#define CPU_ARCH_ARMv4T		3
+#define CPU_ARCH_ARMv5		4
+#define CPU_ARCH_ARMv5T		5
+#define CPU_ARCH_ARMv5TE	6
+#define CPU_ARCH_ARMv5TEJ	7
+#define CPU_ARCH_ARMv6		8
+#define CPU_ARCH_ARMv7		9
+
+#ifndef __ASSEMBLY__
+
+/* information about the system we're running on */
+extern unsigned int system_rev;
+extern unsigned int system_serial_low;
+extern unsigned int system_serial_high;
+extern unsigned int mem_fclk_21285;
+
+extern int __pure cpu_architecture(void);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_ARM_SYSTEM_INFO_H */
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
new file mode 100644
index 000000000000..5a85f148b607
--- /dev/null
+++ b/arch/arm/include/asm/system_misc.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_SYSTEM_MISC_H
+#define __ASM_ARM_SYSTEM_MISC_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/irqflags.h>
+
+extern void cpu_init(void);
+
+void soft_restart(unsigned long);
+extern void (*arm_pm_restart)(char str, const char *cmd);
+extern void (*arm_pm_idle)(void);
+
+#define UDBG_UNDEFINED	(1 << 0)
+#define UDBG_SYSCALL	(1 << 1)
+#define UDBG_BADABORT	(1 << 2)
+#define UDBG_SEGV	(1 << 3)
+#define UDBG_BUS	(1 << 4)
+
+extern unsigned int user_debug;
+
+extern void disable_hlt(void);
+extern void enable_hlt(void);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_ARM_SYSTEM_MISC_H */
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 02b2f8203982..85fe61e73202 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -318,6 +318,21 @@ extern struct cpu_tlb_fns cpu_tlb;
 
 #define tlb_flag(f)	((always_tlb_flags & (f)) || (__tlb_flag & possible_tlb_flags & (f)))
 
+#define __tlb_op(f, insnarg, arg)					\
+	do {								\
+		if (always_tlb_flags & (f))				\
+			asm("mcr " insnarg				\
+			    : : "r" (arg) : "cc");			\
+		else if (possible_tlb_flags & (f))			\
+			asm("tst %1, %2\n\t"				\
+			    "mcrne " insnarg				\
+			    : : "r" (arg), "r" (__tlb_flag), "Ir" (f)	\
+			    : "cc");					\
+	} while (0)
+
+#define tlb_op(f, regs, arg)	__tlb_op(f, "p15, 0, %0, " regs, arg)
+#define tlb_l2_op(f, regs, arg)	__tlb_op(f, "p15, 1, %0, " regs, arg)
+
 static inline void local_flush_tlb_all(void)
 {
 	const int zero = 0;
@@ -326,16 +341,11 @@ static inline void local_flush_tlb_all(void)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (tlb_flag(TLB_V3_FULL))
-		asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_U_FULL | TLB_V6_U_FULL))
-		asm("mcr p15, 0, %0, c8, c7, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_D_FULL | TLB_V6_D_FULL))
-		asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_I_FULL | TLB_V6_I_FULL))
-		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V7_UIS_FULL))
-		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
+	tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
+	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
+	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
+	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
+	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
 
 	if (tlb_flag(TLB_BARRIER)) {
 		dsb();
@@ -352,29 +362,23 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
-		if (tlb_flag(TLB_V3_FULL))
-			asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_U_FULL))
-			asm("mcr p15, 0, %0, c8, c7, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_D_FULL))
-			asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_I_FULL))
-			asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
+	if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
+		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
+			tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
+			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
+			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
+			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
+		}
+		put_cpu();
 	}
-	put_cpu();
-
-	if (tlb_flag(TLB_V6_U_ASID))
-		asm("mcr p15, 0, %0, c8, c7, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V6_D_ASID))
-		asm("mcr p15, 0, %0, c8, c6, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V6_I_ASID))
-		asm("mcr p15, 0, %0, c8, c5, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V7_UIS_ASID))
+
+	tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid);
+	tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid);
+	tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid);
 #ifdef CONFIG_ARM_ERRATA_720789
-		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero);
 #else
-		asm("mcr p15, 0, %0, c8, c3, 2" : : "r" (asid) : "cc");
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid);
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
@@ -392,30 +396,23 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-		if (tlb_flag(TLB_V3_PAGE))
-			asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_U_PAGE))
-			asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_D_PAGE))
-			asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_I_PAGE))
-			asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
+	if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
+	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+		tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr);
+		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
+		tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr);
+		tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr);
 		if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
 			asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
 	}
 
-	if (tlb_flag(TLB_V6_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V6_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V6_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V7_UIS_PAGE))
+	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr);
+	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr);
+	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr);
 #ifdef CONFIG_ARM_ERRATA_720789
-		asm("mcr p15, 0, %0, c8, c3, 3" : : "r" (uaddr & PAGE_MASK) : "cc");
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK);
 #else
-		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (uaddr) : "cc");
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", uaddr);
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
@@ -432,25 +429,17 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (tlb_flag(TLB_V3_PAGE))
-		asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc");
+	tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr);
+	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
+	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
+	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
 	if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
 		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
 
-	if (tlb_flag(TLB_V6_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V6_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V6_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V7_UIS_PAGE))
-		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (kaddr) : "cc");
+	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr);
+	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr);
+	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr);
 
 	if (tlb_flag(TLB_BARRIER)) {
 		dsb();
@@ -475,13 +464,8 @@ static inline void flush_pmd_entry(void *pmd)
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_DCLEAN))
-		asm("mcr	p15, 0, %0, c7, c10, 1	@ flush_pmd"
-			: : "r" (pmd) : "cc");
-
-	if (tlb_flag(TLB_L2CLEAN_FR))
-		asm("mcr	p15, 1, %0, c15, c9, 1  @ L2 flush_pmd"
-			: : "r" (pmd) : "cc");
+	tlb_op(TLB_DCLEAN, "c7, c10, 1	@ flush_pmd", pmd);
+	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 
 	if (tlb_flag(TLB_WB))
 		dsb();
@@ -491,15 +475,11 @@ static inline void clean_pmd_entry(void *pmd)
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_DCLEAN))
-		asm("mcr	p15, 0, %0, c7, c10, 1	@ flush_pmd"
-			: : "r" (pmd) : "cc");
-
-	if (tlb_flag(TLB_L2CLEAN_FR))
-		asm("mcr	p15, 1, %0, c15, c9, 1  @ L2 flush_pmd"
-			: : "r" (pmd) : "cc");
+	tlb_op(TLB_DCLEAN, "c7, c10, 1	@ flush_pmd", pmd);
+	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 }
 
+#undef tlb_op
 #undef tlb_flag
 #undef always_tlb_flags
 #undef possible_tlb_flags
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 5b29a6673625..f555bb3664dc 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -46,7 +46,7 @@ static inline int in_exception_text(unsigned long ptr)
 	return in ? : __in_irqentry_text(ptr);
 }
 
-extern void __init early_trap_init(void);
+extern void __init early_trap_init(void *);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 extern void ptrace_break(struct task_struct *tsk, struct pt_regs *regs);
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 2958976d867b..71f6536d17ac 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -16,8 +16,8 @@
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/domain.h>
-#include <asm/system.h>
 #include <asm/unified.h>
+#include <asm/compiler.h>
 
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index f16d7652f34b..7b787d642af4 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -7,6 +7,8 @@ AFLAGS_head.o        := -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+CFLAGS_REMOVE_patch.o = -pg
 endif
 
 CFLAGS_REMOVE_return_address.o = -pg
@@ -14,30 +16,29 @@ CFLAGS_REMOVE_return_address.o = -pg
 # Object file lists.
 
 obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
-		   process.o ptrace.o return_address.o setup.o signal.o \
-		   sys_arm.o stacktrace.o time.o traps.o
+		   process.o ptrace.o return_address.o sched_clock.o \
+		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += compat.o
 
 obj-$(CONFIG_LEDS)		+= leds.o
 obj-$(CONFIG_OC_ETM)		+= etm.o
-
+obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
-obj-$(CONFIG_ARCH_ACORN)	+= ecard.o 
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
 obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
-obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
 obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
-obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o
+obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o patch.o
 ifdef CONFIG_THUMB2_KERNEL
 obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
 else
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 5b0bce61eb69..b57c75e0b01f 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -18,7 +18,6 @@
 #include <linux/io.h>
 
 #include <asm/checksum.h>
-#include <asm/system.h>
 #include <asm/ftrace.h>
 
 /*
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 632df9a66f8c..ede5f7741c42 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -299,7 +299,6 @@ static inline int pdev_bad_for_parity(struct pci_dev *dev)
  */
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	struct pci_sys_data *root = bus->sysdata;
 	struct pci_dev *dev;
 	u16 features = PCI_COMMAND_SERR | PCI_COMMAND_PARITY | PCI_COMMAND_FAST_BACK;
 
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
new file mode 100644
index 000000000000..89545f6c8403
--- /dev/null
+++ b/arch/arm/kernel/cpuidle.c
@@ -0,0 +1,21 @@
+/*
+ * Copyright 2012 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/cpuidle.h>
+#include <asm/proc-fns.h>
+
+int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index)
+{
+	cpu_do_idle();
+
+	return index;
+}
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 204e2160cfcc..c45522c36787 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -10,6 +10,7 @@
  *  32-bit debugging code
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 		.text
 
@@ -100,7 +101,7 @@
 
 #endif	/* CONFIG_CPU_V6 */
 
-#else
+#elif !defined(CONFIG_DEBUG_SEMIHOSTING)
 #include <mach/debug-macro.S>
 #endif	/* CONFIG_DEBUG_ICEDCC */
 
@@ -155,6 +156,8 @@ hexbuf:		.space 16
 
 		.ltorg
 
+#ifndef CONFIG_DEBUG_SEMIHOSTING
+
 ENTRY(printascii)
 		addruart_current r3, r1, r2
 		b	2f
@@ -177,3 +180,24 @@ ENTRY(printch)
 		mov	r0, #0
 		b	1b
 ENDPROC(printch)
+
+#else
+
+ENTRY(printascii)
+		mov	r1, r0
+		mov	r0, #0x04		@ SYS_WRITE0
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xab		)
+		mov	pc, lr
+ENDPROC(printascii)
+
+ENTRY(printch)
+		adr	r1, hexbuf
+		strb	r0, [r1]
+		mov	r0, #0x03		@ SYS_WRITEC
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xab		)
+		mov	pc, lr
+ENDPROC(printch)
+
+#endif
diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c
index ddba41d1fcf1..d0d1e83150c9 100644
--- a/arch/arm/kernel/elf.c
+++ b/arch/arm/kernel/elf.c
@@ -3,6 +3,7 @@
 #include <linux/personality.h>
 #include <linux/binfmts.h>
 #include <linux/elf.h>
+#include <asm/system_info.h>
 
 int elf_check_arch(const struct elf32_hdr *x)
 {
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 22f0ed324f37..7fd3ad048da9 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -15,6 +15,7 @@
  *  that causes it to save wrong values...  Be aware!
  */
 
+#include <asm/assembler.h>
 #include <asm/memory.h>
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
@@ -26,7 +27,7 @@
 #include <asm/unwind.h>
 #include <asm/unistd.h>
 #include <asm/tls.h>
-#include <asm/system.h>
+#include <asm/system_info.h>
 
 #include "entry-header.S"
 #include <asm/entry-macro-multi.S>
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 4c164ece5891..c32f8456aa09 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -42,9 +42,9 @@
 #include <linux/seq_file.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
 #include <asm/fiq.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 static unsigned long no_fiq_insn;
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index c0062ad1e847..df0bf0c8cb79 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -16,10 +16,13 @@
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
+#include <asm/opcodes.h>
 #include <asm/ftrace.h>
 
+#include "insn.h"
+
 #ifdef CONFIG_THUMB2_KERNEL
-#define	NOP		0xeb04f85d	/* pop.w {lr} */
+#define	NOP		0xf85deb04	/* pop.w {lr} */
 #else
 #define	NOP		0xe8bd4000	/* pop {lr} */
 #endif
@@ -60,76 +63,31 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
 }
 #endif
 
-#ifdef CONFIG_THUMB2_KERNEL
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
-				       bool link)
-{
-	unsigned long s, j1, j2, i1, i2, imm10, imm11;
-	unsigned long first, second;
-	long offset;
-
-	offset = (long)addr - (long)(pc + 4);
-	if (offset < -16777216 || offset > 16777214) {
-		WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	s	= (offset >> 24) & 0x1;
-	i1	= (offset >> 23) & 0x1;
-	i2	= (offset >> 22) & 0x1;
-	imm10	= (offset >> 12) & 0x3ff;
-	imm11	= (offset >>  1) & 0x7ff;
-
-	j1 = (!i1) ^ s;
-	j2 = (!i2) ^ s;
-
-	first = 0xf000 | (s << 10) | imm10;
-	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
-	if (link)
-		second |= 1 << 14;
-
-	return (second << 16) | first;
-}
-#else
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
-				       bool link)
-{
-	unsigned long opcode = 0xea000000;
-	long offset;
-
-	if (link)
-		opcode |= 1 << 24;
-
-	offset = (long)addr - (long)(pc + 8);
-	if (unlikely(offset < -33554432 || offset > 33554428)) {
-		/* Can't generate branches that far (from ARM ARM). Ftrace
-		 * doesn't generate branches outside of kernel text.
-		 */
-		WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	offset = (offset >> 2) & 0x00ffffff;
-
-	return opcode | offset;
-}
-#endif
-
 static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 {
-	return ftrace_gen_branch(pc, addr, true);
+	return arm_gen_branch_link(pc, addr);
 }
 
 static int ftrace_modify_code(unsigned long pc, unsigned long old,
-			      unsigned long new)
+			      unsigned long new, bool validate)
 {
 	unsigned long replaced;
 
-	if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		old = __opcode_to_mem_thumb32(old);
+		new = __opcode_to_mem_thumb32(new);
+	} else {
+		old = __opcode_to_mem_arm(old);
+		new = __opcode_to_mem_arm(new);
+	}
 
-	if (replaced != old)
-		return -EINVAL;
+	if (validate) {
+		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+			return -EFAULT;
+
+		if (replaced != old)
+			return -EINVAL;
+	}
 
 	if (probe_kernel_write((void *)pc, &new, MCOUNT_INSN_SIZE))
 		return -EPERM;
@@ -141,23 +99,21 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old,
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
-	unsigned long pc, old;
+	unsigned long pc;
 	unsigned long new;
 	int ret;
 
 	pc = (unsigned long)&ftrace_call;
-	memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE);
 	new = ftrace_call_replace(pc, (unsigned long)func);
 
-	ret = ftrace_modify_code(pc, old, new);
+	ret = ftrace_modify_code(pc, 0, new, false);
 
 #ifdef CONFIG_OLD_MCOUNT
 	if (!ret) {
 		pc = (unsigned long)&ftrace_call_old;
-		memcpy(&old, &ftrace_call_old, MCOUNT_INSN_SIZE);
 		new = ftrace_call_replace(pc, (unsigned long)func);
 
-		ret = ftrace_modify_code(pc, old, new);
+		ret = ftrace_modify_code(pc, 0, new, false);
 	}
 #endif
 
@@ -172,7 +128,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	old = ftrace_nop_replace(rec);
 	new = ftrace_call_replace(ip, adjust_address(rec, addr));
 
-	return ftrace_modify_code(rec->ip, old, new);
+	return ftrace_modify_code(rec->ip, old, new, true);
 }
 
 int ftrace_make_nop(struct module *mod,
@@ -185,7 +141,7 @@ int ftrace_make_nop(struct module *mod,
 
 	old = ftrace_call_replace(ip, adjust_address(rec, addr));
 	new = ftrace_nop_replace(rec);
-	ret = ftrace_modify_code(ip, old, new);
+	ret = ftrace_modify_code(ip, old, new, true);
 
 #ifdef CONFIG_OLD_MCOUNT
 	if (ret == -EINVAL && addr == MCOUNT_ADDR) {
@@ -193,7 +149,7 @@ int ftrace_make_nop(struct module *mod,
 
 		old = ftrace_call_replace(ip, adjust_address(rec, addr));
 		new = ftrace_nop_replace(rec);
-		ret = ftrace_modify_code(ip, old, new);
+		ret = ftrace_modify_code(ip, old, new, true);
 	}
 #endif
 
@@ -249,12 +205,12 @@ static int __ftrace_modify_caller(unsigned long *callsite,
 {
 	unsigned long caller_fn = (unsigned long) func;
 	unsigned long pc = (unsigned long) callsite;
-	unsigned long branch = ftrace_gen_branch(pc, caller_fn, false);
+	unsigned long branch = arm_gen_branch(pc, caller_fn);
 	unsigned long nop = 0xe1a00000;	/* mov r0, r0 */
 	unsigned long old = enable ? nop : branch;
 	unsigned long new = enable ? branch : nop;
 
-	return ftrace_modify_code(pc, old, new);
+	return ftrace_modify_code(pc, old, new, true);
 }
 
 static int ftrace_modify_graph_caller(bool enable)
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index d46f25968bec..278cfc144f44 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -17,8 +17,8 @@
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/cp15.h>
 #include <asm/thread_info.h>
-#include <asm/system.h>
 
 /*
  * Kernel startup entry point.
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 6d5791144066..3bf0c7f8b043 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -15,12 +15,12 @@
 #include <linux/init.h>
 
 #include <asm/assembler.h>
+#include <asm/cp15.h>
 #include <asm/domain.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
 #include <asm/memory.h>
 #include <asm/thread_info.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 
 #ifdef CONFIG_DEBUG_LL
@@ -265,7 +265,7 @@ __create_page_tables:
 	str	r6, [r3]
 
 #ifdef CONFIG_DEBUG_LL
-#ifndef CONFIG_DEBUG_ICEDCC
+#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING)
 	/*
 	 * Map in IO space for serial debugging.
 	 * This allows debug messages to be output
@@ -297,10 +297,10 @@ __create_page_tables:
 	cmp	r0, r6
 	blo	1b
 
-#else /* CONFIG_DEBUG_ICEDCC */
-	/* we don't need any serial debugging mappings for ICEDCC */
+#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */
+	/* we don't need any serial debugging mappings */
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
-#endif /* !CONFIG_DEBUG_ICEDCC */
+#endif
 
 #if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)
 	/*
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index d6a95ef9131d..ba386bd94107 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -34,7 +34,6 @@
 #include <asm/current.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/kdebug.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 /* Breakpoint currently in use for each BRP. */
diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c
new file mode 100644
index 000000000000..b760340b7014
--- /dev/null
+++ b/arch/arm/kernel/insn.c
@@ -0,0 +1,62 @@
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <asm/opcodes.h>
+
+static unsigned long
+__arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link)
+{
+	unsigned long s, j1, j2, i1, i2, imm10, imm11;
+	unsigned long first, second;
+	long offset;
+
+	offset = (long)addr - (long)(pc + 4);
+	if (offset < -16777216 || offset > 16777214) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	s	= (offset >> 24) & 0x1;
+	i1	= (offset >> 23) & 0x1;
+	i2	= (offset >> 22) & 0x1;
+	imm10	= (offset >> 12) & 0x3ff;
+	imm11	= (offset >>  1) & 0x7ff;
+
+	j1 = (!i1) ^ s;
+	j2 = (!i2) ^ s;
+
+	first = 0xf000 | (s << 10) | imm10;
+	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
+	if (link)
+		second |= 1 << 14;
+
+	return __opcode_thumb32_compose(first, second);
+}
+
+static unsigned long
+__arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link)
+{
+	unsigned long opcode = 0xea000000;
+	long offset;
+
+	if (link)
+		opcode |= 1 << 24;
+
+	offset = (long)addr - (long)(pc + 8);
+	if (unlikely(offset < -33554432 || offset > 33554428)) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	offset = (offset >> 2) & 0x00ffffff;
+
+	return opcode | offset;
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
+		return __arm_gen_branch_thumb2(pc, addr, link);
+	else
+		return __arm_gen_branch_arm(pc, addr, link);
+}
diff --git a/arch/arm/kernel/insn.h b/arch/arm/kernel/insn.h
new file mode 100644
index 000000000000..e96065da4dae
--- /dev/null
+++ b/arch/arm/kernel/insn.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_INSN_H
+#define __ASM_ARM_INSN_H
+
+static inline unsigned long
+arm_gen_nop(void)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+	return 0xf3af8000; /* nop.w */
+#else
+	return 0xe1a00000; /* mov r0, r0 */
+#endif
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link);
+
+static inline unsigned long
+arm_gen_branch(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, false);
+}
+
+static inline unsigned long
+arm_gen_branch_link(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, true);
+}
+
+#endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 3efd82cc95f0..71ccdbfed662 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -36,7 +36,6 @@
 #include <linux/proc_fs.h>
 
 #include <asm/exception.h>
-#include <asm/system.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
@@ -181,10 +180,7 @@ void migrate_irqs(void)
 	local_irq_save(flags);
 
 	for_each_irq_desc(i, desc) {
-		bool affinity_broken = false;
-
-		if (!desc)
-			continue;
+		bool affinity_broken;
 
 		raw_spin_lock(&desc->lock);
 		affinity_broken = migrate_one_irq(desc);
diff --git a/arch/arm/kernel/jump_label.c b/arch/arm/kernel/jump_label.c
new file mode 100644
index 000000000000..4ce4f789446d
--- /dev/null
+++ b/arch/arm/kernel/jump_label.c
@@ -0,0 +1,39 @@
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+
+#include "insn.h"
+#include "patch.h"
+
+#ifdef HAVE_JUMP_LABEL
+
+static void __arch_jump_label_transform(struct jump_entry *entry,
+					enum jump_label_type type,
+					bool is_static)
+{
+	void *addr = (void *)entry->code;
+	unsigned int insn;
+
+	if (type == JUMP_LABEL_ENABLE)
+		insn = arm_gen_branch(entry->code, entry->target);
+	else
+		insn = arm_gen_nop();
+
+	if (is_static)
+		__patch_text(addr, insn);
+	else
+		patch_text(addr, insn);
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, false);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, true);
+}
+
+#endif
diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c
index a5394fb4e4e0..18a76282970e 100644
--- a/arch/arm/kernel/kprobes-common.c
+++ b/arch/arm/kernel/kprobes-common.c
@@ -13,6 +13,7 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <asm/system_info.h>
 
 #include "kprobes.h"
 
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 129c1163248b..4dd41fc9e235 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -29,6 +29,7 @@
 #include <asm/cacheflush.h>
 
 #include "kprobes.h"
+#include "patch.h"
 
 #define MIN_STACK_SIZE(addr) 				\
 	min((unsigned long)MAX_STACK_SIZE,		\
@@ -103,57 +104,33 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	return 0;
 }
 
-#ifdef CONFIG_THUMB2_KERNEL
-
-/*
- * For a 32-bit Thumb breakpoint spanning two memory words we need to take
- * special precautions to insert the breakpoint atomically, especially on SMP
- * systems. This is achieved by calling this arming function using stop_machine.
- */
-static int __kprobes set_t32_breakpoint(void *addr)
-{
-	((u16 *)addr)[0] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION >> 16;
-	((u16 *)addr)[1] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION & 0xffff;
-	flush_insns(addr, 2*sizeof(u16));
-	return 0;
-}
-
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-	uintptr_t addr = (uintptr_t)p->addr & ~1; /* Remove any Thumb flag */
-
-	if (!is_wide_instruction(p->opcode)) {
-		*(u16 *)addr = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
-		flush_insns(addr, sizeof(u16));
-	} else if (addr & 2) {
-		/* A 32-bit instruction spanning two words needs special care */
-		stop_machine(set_t32_breakpoint, (void *)addr, &cpu_online_map);
+	unsigned int brkp;
+	void *addr;
+
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* Remove any Thumb flag */
+		addr = (void *)((uintptr_t)p->addr & ~1);
+
+		if (is_wide_instruction(p->opcode))
+			brkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
+		else
+			brkp = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
 	} else {
-		/* Word aligned 32-bit instruction can be written atomically */
-		u32 bkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
-#ifndef __ARMEB__ /* Swap halfwords for little-endian */
-		bkp = (bkp >> 16) | (bkp << 16);
-#endif
-		*(u32 *)addr = bkp;
-		flush_insns(addr, sizeof(u32));
-	}
-}
+		kprobe_opcode_t insn = p->opcode;
 
-#else /* !CONFIG_THUMB2_KERNEL */
+		addr = p->addr;
+		brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
 
-void __kprobes arch_arm_kprobe(struct kprobe *p)
-{
-	kprobe_opcode_t insn = p->opcode;
-	kprobe_opcode_t brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
-	if (insn >= 0xe0000000)
-		brkp |= 0xe0000000;  /* Unconditional instruction */
-	else
-		brkp |= insn & 0xf0000000;  /* Copy condition from insn */
-	*p->addr = brkp;
-	flush_insns(p->addr, sizeof(p->addr[0]));
-}
+		if (insn >= 0xe0000000)
+			brkp |= 0xe0000000;  /* Unconditional instruction */
+		else
+			brkp |= insn & 0xf0000000;  /* Copy condition from insn */
+	}
 
-#endif /* !CONFIG_THUMB2_KERNEL */
+	patch_text(addr, brkp);
+}
 
 /*
  * The actual disarming is done here on each CPU and synchronized using
@@ -166,31 +143,16 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
 int __kprobes __arch_disarm_kprobe(void *p)
 {
 	struct kprobe *kp = p;
-#ifdef CONFIG_THUMB2_KERNEL
-	u16 *addr = (u16 *)((uintptr_t)kp->addr & ~1);
-	kprobe_opcode_t insn = kp->opcode;
-	unsigned int len;
+	void *addr = (void *)((uintptr_t)kp->addr & ~1);
 
-	if (is_wide_instruction(insn)) {
-		((u16 *)addr)[0] = insn>>16;
-		((u16 *)addr)[1] = insn;
-		len = 2*sizeof(u16);
-	} else {
-		((u16 *)addr)[0] = insn;
-		len = sizeof(u16);
-	}
-	flush_insns(addr, len);
+	__patch_text(addr, kp->opcode);
 
-#else /* !CONFIG_THUMB2_KERNEL */
-	*kp->addr = kp->opcode;
-	flush_insns(kp->addr, sizeof(kp->addr[0]));
-#endif
 	return 0;
 }
 
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-	stop_machine(__arch_disarm_kprobe, p, &cpu_online_map);
+	stop_machine(__arch_disarm_kprobe, p, cpu_online_mask);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 764bd456d84f..dfcdb9f7c126 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -7,12 +7,13 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
-#include <asm/system.h>
+#include <asm/system_misc.h>
 
 extern const unsigned char relocate_new_kernel[];
 extern const unsigned int relocate_new_kernel_size;
@@ -53,6 +54,29 @@ void machine_crash_nonpanic_core(void *unused)
 		cpu_relax();
 }
 
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
+			chip->irq_eoi(&desc->irq_data);
+
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
+}
+
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	unsigned long msecs;
@@ -70,6 +94,7 @@ void machine_crash_shutdown(struct pt_regs *regs)
 		printk(KERN_WARNING "Non-crashing CPUs did not react to IPI\n");
 
 	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
 
 	printk(KERN_INFO "Loading crashdump kernel...\n");
 }
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
new file mode 100644
index 000000000000..07314af47733
--- /dev/null
+++ b/arch/arm/kernel/patch.c
@@ -0,0 +1,75 @@
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/stop_machine.h>
+
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include <asm/opcodes.h>
+
+#include "patch.h"
+
+struct patch {
+	void *addr;
+	unsigned int insn;
+};
+
+void __kprobes __patch_text(void *addr, unsigned int insn)
+{
+	bool thumb2 = IS_ENABLED(CONFIG_THUMB2_KERNEL);
+	int size;
+
+	if (thumb2 && __opcode_is_thumb16(insn)) {
+		*(u16 *)addr = __opcode_to_mem_thumb16(insn);
+		size = sizeof(u16);
+	} else if (thumb2 && ((uintptr_t)addr & 2)) {
+		u16 first = __opcode_thumb32_first(insn);
+		u16 second = __opcode_thumb32_second(insn);
+		u16 *addrh = addr;
+
+		addrh[0] = __opcode_to_mem_thumb16(first);
+		addrh[1] = __opcode_to_mem_thumb16(second);
+
+		size = sizeof(u32);
+	} else {
+		if (thumb2)
+			insn = __opcode_to_mem_thumb32(insn);
+		else
+			insn = __opcode_to_mem_arm(insn);
+
+		*(u32 *)addr = insn;
+		size = sizeof(u32);
+	}
+
+	flush_icache_range((uintptr_t)(addr),
+			   (uintptr_t)(addr) + size);
+}
+
+static int __kprobes patch_text_stop_machine(void *data)
+{
+	struct patch *patch = data;
+
+	__patch_text(patch->addr, patch->insn);
+
+	return 0;
+}
+
+void __kprobes patch_text(void *addr, unsigned int insn)
+{
+	struct patch patch = {
+		.addr = addr,
+		.insn = insn,
+	};
+
+	if (cache_ops_need_broadcast()) {
+		stop_machine(patch_text_stop_machine, &patch, cpu_online_mask);
+	} else {
+		bool straddles_word = IS_ENABLED(CONFIG_THUMB2_KERNEL)
+				      && __opcode_is_thumb32(insn)
+				      && ((uintptr_t)addr & 2);
+
+		if (straddles_word)
+			stop_machine(patch_text_stop_machine, &patch, NULL);
+		else
+			__patch_text(addr, insn);
+	}
+}
diff --git a/arch/arm/kernel/patch.h b/arch/arm/kernel/patch.h
new file mode 100644
index 000000000000..b4731f2dac38
--- /dev/null
+++ b/arch/arm/kernel/patch.h
@@ -0,0 +1,7 @@
+#ifndef _ARM_KERNEL_PATCH_H
+#define _ARM_KERNEL_PATCH_H
+
+void patch_text(void *addr, unsigned int insn);
+void __patch_text(void *addr, unsigned int insn);
+
+#endif
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 8a89d3b7626b..186c8cb982c5 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -738,6 +738,9 @@ init_hw_perf_events(void)
 		case 0xC0F0:	/* Cortex-A15 */
 			cpu_pmu = armv7_a15_pmu_init();
 			break;
+		case 0xC070:	/* Cortex-A7 */
+			cpu_pmu = armv7_a7_pmu_init();
+			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (0x69 == implementor) {
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4d7095af2ab3..00755d82e2f2 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -610,6 +610,130 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 };
 
 /*
+ * Cortex-A7 HW events mapping
+ */
+static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
  * Perf Events' indices
  */
 #define	ARMV7_IDX_CYCLE_COUNTER	0
@@ -1104,6 +1228,12 @@ static int armv7_a15_map_event(struct perf_event *event)
 				&armv7_a15_perf_cache_map, 0xFF);
 }
 
+static int armv7_a7_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a7_perf_map,
+				&armv7_a7_perf_cache_map, 0xFF);
+}
+
 static struct arm_pmu armv7pmu = {
 	.handle_irq		= armv7pmu_handle_irq,
 	.enable			= armv7pmu_enable_event,
@@ -1164,6 +1294,16 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void)
 	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
 	return &armv7pmu;
 }
+
+static struct arm_pmu *__init armv7_a7_pmu_init(void)
+{
+	armv7pmu.id		= ARM_PERF_PMU_ID_CA7;
+	armv7pmu.name		= "ARMv7 Cortex-A7";
+	armv7pmu.map_event	= armv7_a7_map_event;
+	armv7pmu.num_events	= armv7_read_num_pmnc_events();
+	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
+	return &armv7pmu;
+}
 #else
 static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
@@ -1184,4 +1324,9 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void)
 {
 	return NULL;
 }
+
+static struct arm_pmu *__init armv7_a7_pmu_init(void)
+{
+	return NULL;
+}
 #endif	/* CONFIG_CPU_V7 */
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index d3eca4524533..2b7b017a20cd 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -35,7 +35,6 @@
 #include <asm/cacheflush.h>
 #include <asm/leds.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/thread_notify.h>
 #include <asm/stacktrace.h>
 #include <asm/mach/time.h>
@@ -529,21 +528,39 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 #ifdef CONFIG_MMU
 /*
  * The vectors page is always readable from user space for the
- * atomic helpers and the signal restart code.  Let's declare a mapping
- * for it so it is visible through ptrace and /proc/<pid>/mem.
+ * atomic helpers and the signal restart code. Insert it into the
+ * gate_vma so that it is visible through ptrace and /proc/<pid>/mem.
  */
+static struct vm_area_struct gate_vma;
 
-int vectors_user_mapping(void)
+static int __init gate_vma_init(void)
 {
-	struct mm_struct *mm = current->mm;
-	return install_special_mapping(mm, 0xffff0000, PAGE_SIZE,
-				       VM_READ | VM_EXEC |
-				       VM_MAYREAD | VM_MAYEXEC | VM_RESERVED,
-				       NULL);
+	gate_vma.vm_start	= 0xffff0000;
+	gate_vma.vm_end		= 0xffff0000 + PAGE_SIZE;
+	gate_vma.vm_page_prot	= PAGE_READONLY_EXEC;
+	gate_vma.vm_flags	= VM_READ | VM_EXEC |
+				  VM_MAYREAD | VM_MAYEXEC;
+	return 0;
+}
+arch_initcall(gate_vma_init);
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+	return &gate_vma;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+	return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end);
+}
+
+int in_gate_area_no_mm(unsigned long addr)
+{
+	return in_gate_area(NULL, addr);
 }
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
-	return (vma->vm_start == 0xffff0000) ? "[vectors]" : NULL;
+	return (vma == &gate_vma) ? "[vectors]" : NULL;
 }
 #endif
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ede6443c34d9..80abafb9bf33 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -26,7 +26,6 @@
 #include <linux/audit.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 #define REG_PC	15
@@ -257,7 +256,7 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
 {
 	unsigned long tmp;
 
-	if (off & 3 || off >= sizeof(struct user))
+	if (off & 3)
 		return -EIO;
 
 	tmp = 0;
@@ -269,6 +268,8 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
 		tmp = tsk->mm->end_code;
 	else if (off < sizeof(struct pt_regs))
 		tmp = get_user_reg(tsk, off >> 2);
+	else if (off >= sizeof(struct user))
+		return -EIO;
 
 	return put_user(tmp, ret);
 }
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 5416c7c12528..27d186abbc06 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -10,6 +10,7 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/syscore_ops.h>
 #include <linux/timer.h>
 
 #include <asm/sched_clock.h>
@@ -164,3 +165,20 @@ void __init sched_clock_postinit(void)
 
 	sched_clock_poll(sched_clock_timer.data);
 }
+
+static int sched_clock_suspend(void)
+{
+	sched_clock_poll(sched_clock_timer.data);
+	return 0;
+}
+
+static struct syscore_ops sched_clock_ops = {
+	.suspend = sched_clock_suspend,
+};
+
+static int __init sched_clock_syscore_init(void)
+{
+	register_syscore_ops(&sched_clock_ops);
+	return 0;
+}
+device_initcall(sched_clock_syscore_init);
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index a255c39612ca..b91411371ae1 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -33,6 +33,7 @@
 #include <linux/sort.h>
 
 #include <asm/unified.h>
+#include <asm/cp15.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
@@ -44,12 +45,13 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/tlbflush.h>
-#include <asm/system.h>
 
 #include <asm/prom.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
+#include <asm/system_info.h>
+#include <asm/system_misc.h>
 #include <asm/traps.h>
 #include <asm/unwind.h>
 #include <asm/memblock.h>
@@ -974,7 +976,6 @@ void __init setup_arch(char **cmdline_p)
 	conswitchp = &dummy_con;
 #endif
 #endif
-	early_trap_init();
 
 	if (mdesc->init_early)
 		mdesc->init_early();
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 9e617bd4a146..7cb532fc8aa4 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -66,12 +66,13 @@ const unsigned long syscall_restart_code[2] = {
  */
 asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask)
 {
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
+	sigset_t blocked;
+
 	current->saved_sigmask = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -280,10 +281,7 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0) {
 		sigdelsetmask(&set, ~_BLOCKABLE);
-		spin_lock_irq(&current->sighand->siglock);
-		current->blocked = set;
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
+		set_current_blocked(&set);
 	}
 
 	__get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
@@ -636,13 +634,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka,
 	/*
 	 * Block the signal if we were successful.
 	 */
-	spin_lock_irq(&tsk->sighand->siglock);
-	sigorsets(&tsk->blocked, &tsk->blocked,
-		  &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&tsk->blocked, sig);
-	recalc_sigpending();
-	spin_unlock_irq(&tsk->sighand->siglock);
+	block_sigmask(ka, sig);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 1f268bda4552..987dcf33415c 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -4,7 +4,6 @@
 #include <asm/assembler.h>
 #include <asm/glue-cache.h>
 #include <asm/glue-proc.h>
-#include <asm/system.h>
 	.text
 
 /*
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 8f8cce2c46c4..addbbe8028c2 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -58,6 +58,8 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 };
 
+static DECLARE_COMPLETION(cpu_running);
+
 int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
@@ -98,20 +100,12 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	 */
 	ret = boot_secondary(cpu, idle);
 	if (ret == 0) {
-		unsigned long timeout;
-
 		/*
 		 * CPU was successfully started, wait for it
 		 * to come online or time out.
 		 */
-		timeout = jiffies + HZ;
-		while (time_before(jiffies, timeout)) {
-			if (cpu_online(cpu))
-				break;
-
-			udelay(10);
-			barrier();
-		}
+		wait_for_completion_timeout(&cpu_running,
+						 msecs_to_jiffies(1000));
 
 		if (!cpu_online(cpu)) {
 			pr_crit("CPU%u: failed to come online\n", cpu);
@@ -288,9 +282,10 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
-	 * before we continue.
+	 * before we continue - which happens after __cpu_up returns.
 	 */
 	set_cpu_online(cpu, true);
+	complete(&cpu_running);
 
 	/*
 	 * Setup the percpu timer for this CPU.
@@ -354,7 +349,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		 * re-initialize the map in platform_smp_prepare_cpus() if
 		 * present != possible (e.g. physical hotplug).
 		 */
-		init_cpu_present(&cpu_possible_map);
+		init_cpu_present(cpu_possible_mask);
 
 		/*
 		 * Initialise the SCU if there are more than one CPU
@@ -586,8 +581,9 @@ void smp_send_stop(void)
 	unsigned long timeout;
 
 	if (num_online_cpus() > 1) {
-		cpumask_t mask = cpu_online_map;
-		cpu_clear(smp_processor_id(), mask);
+		struct cpumask mask;
+		cpumask_copy(&mask, cpu_online_mask);
+		cpumask_clear_cpu(smp_processor_id(), &mask);
 
 		smp_cross_call(&mask, IPI_CPU_STOP);
 	}
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 7dcb35285be7..02c5d2ce23bf 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -13,18 +13,6 @@
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
 
-static void on_each_cpu_mask(void (*func)(void *), void *info, int wait,
-	const struct cpumask *mask)
-{
-	preempt_disable();
-
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(smp_processor_id(), mask))
-		func(info);
-
-	preempt_enable();
-}
-
 /**********************************************************************/
 
 /*
@@ -87,7 +75,7 @@ void flush_tlb_all(void)
 void flush_tlb_mm(struct mm_struct *mm)
 {
 	if (tlb_ops_need_broadcast())
-		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
+		on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
 	else
 		local_flush_tlb_mm(mm);
 }
@@ -98,7 +86,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		struct tlb_args ta;
 		ta.ta_vma = vma;
 		ta.ta_start = uaddr;
-		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page,
+					&ta, 1);
 	} else
 		local_flush_tlb_page(vma, uaddr);
 }
@@ -121,7 +110,8 @@ void flush_tlb_range(struct vm_area_struct *vma,
 		ta.ta_vma = vma;
 		ta.ta_start = start;
 		ta.ta_end = end;
-		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range,
+					&ta, 1);
 	} else
 		local_flush_tlb_range(vma, start, end);
 }
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 01ec453bb924..30ae6bb4a310 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -16,6 +16,7 @@
 #include <asm/cputype.h>
 #include <asm/mach/map.h>
 #include <asm/memory.h>
+#include <asm/system_info.h>
 #include "tcm.h"
 
 static struct gen_pool *tcm_pool;
diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c
index 9cb7aaca159f..aab899764053 100644
--- a/arch/arm/kernel/thumbee.c
+++ b/arch/arm/kernel/thumbee.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
+#include <asm/system_info.h>
 #include <asm/thread_notify.h>
 
 /*
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 8c57dd3680e9..fe31b22f18fd 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -25,8 +25,6 @@
 #include <linux/timer.h>
 #include <linux/irq.h>
 
-#include <linux/mc146818rtc.h>
-
 #include <asm/leds.h>
 #include <asm/thread_info.h>
 #include <asm/sched_clock.h>
@@ -149,8 +147,6 @@ void __init time_init(void)
 {
 	system_timer = machine_desc->timer;
 	system_timer->init();
-#ifdef CONFIG_HAVE_SCHED_CLOCK
 	sched_clock_postinit();
-#endif
 }
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index f84dfe67724f..778454750a6c 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -29,11 +29,11 @@
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/exception.h>
-#include <asm/system.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
 #include <asm/unwind.h>
 #include <asm/tls.h>
+#include <asm/system_misc.h>
 
 #include "signal.h"
 
@@ -227,6 +227,11 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 #else
 #define S_SMP ""
 #endif
+#ifdef CONFIG_THUMB2_KERNEL
+#define S_ISA " THUMB2"
+#else
+#define S_ISA " ARM"
+#endif
 
 static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs)
 {
@@ -234,8 +239,8 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt
 	static int die_counter;
 	int ret;
 
-	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n",
-	       str, err, ++die_counter);
+	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP
+	       S_ISA "\n", str, err, ++die_counter);
 
 	/* trap and error numbers are mostly meaningless on ARM */
 	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV);
@@ -784,18 +789,16 @@ static void __init kuser_get_tls_init(unsigned long vectors)
 		memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4);
 }
 
-void __init early_trap_init(void)
+void __init early_trap_init(void *vectors_base)
 {
-#if defined(CONFIG_CPU_USE_DOMAINS)
-	unsigned long vectors = CONFIG_VECTORS_BASE;
-#else
-	unsigned long vectors = (unsigned long)vectors_page;
-#endif
+	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	extern char __kuser_helper_start[], __kuser_helper_end[];
 	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
 
+	vectors_page = vectors_base;
+
 	/*
 	 * Copy the vectors, stubs and kuser helpers (in entry-armv.S)
 	 * into the vector page, mapped at 0xffff0000, and ensure these
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index e55cdcbd81fb..45db05d8d94c 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -20,9 +20,11 @@ config HAVE_AT91_USART5
 
 config AT91_SAM9_ALT_RESET
 	bool
+	default !ARCH_AT91X40
 
 config AT91_SAM9G45_RESET
 	bool
+	default !ARCH_AT91X40
 
 menu "Atmel AT91 System-on-Chip"
 
@@ -45,7 +47,6 @@ config ARCH_AT91SAM9260
 	select HAVE_AT91_USART4
 	select HAVE_AT91_USART5
 	select HAVE_NET_MACB
-	select AT91_SAM9_ALT_RESET
 
 config ARCH_AT91SAM9261
 	bool "AT91SAM9261"
@@ -53,7 +54,6 @@ config ARCH_AT91SAM9261
 	select GENERIC_CLOCKEVENTS
 	select HAVE_FB_ATMEL
 	select HAVE_AT91_DBGU0
-	select AT91_SAM9_ALT_RESET
 
 config ARCH_AT91SAM9G10
 	bool "AT91SAM9G10"
@@ -61,7 +61,6 @@ config ARCH_AT91SAM9G10
 	select GENERIC_CLOCKEVENTS
 	select HAVE_AT91_DBGU0
 	select HAVE_FB_ATMEL
-	select AT91_SAM9_ALT_RESET
 
 config ARCH_AT91SAM9263
 	bool "AT91SAM9263"
@@ -70,7 +69,6 @@ config ARCH_AT91SAM9263
 	select HAVE_FB_ATMEL
 	select HAVE_NET_MACB
 	select HAVE_AT91_DBGU1
-	select AT91_SAM9_ALT_RESET
 
 config ARCH_AT91SAM9RL
 	bool "AT91SAM9RL"
@@ -79,7 +77,6 @@ config ARCH_AT91SAM9RL
 	select HAVE_AT91_USART3
 	select HAVE_FB_ATMEL
 	select HAVE_AT91_DBGU0
-	select AT91_SAM9_ALT_RESET
 
 config ARCH_AT91SAM9G20
 	bool "AT91SAM9G20"
@@ -90,7 +87,6 @@ config ARCH_AT91SAM9G20
 	select HAVE_AT91_USART4
 	select HAVE_AT91_USART5
 	select HAVE_NET_MACB
-	select AT91_SAM9_ALT_RESET
 
 config ARCH_AT91SAM9G45
 	bool "AT91SAM9G45"
@@ -100,7 +96,6 @@ config ARCH_AT91SAM9G45
 	select HAVE_FB_ATMEL
 	select HAVE_NET_MACB
 	select HAVE_AT91_DBGU1
-	select AT91_SAM9G45_RESET
 
 config ARCH_AT91SAM9X5
 	bool "AT91SAM9x5 family"
@@ -109,7 +104,6 @@ config ARCH_AT91SAM9X5
 	select HAVE_FB_ATMEL
 	select HAVE_NET_MACB
 	select HAVE_AT91_DBGU0
-	select AT91_SAM9G45_RESET
 
 config ARCH_AT91X40
 	bool "AT91x40"
diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
index 0df1045311e4..364c19357e60 100644
--- a/arch/arm/mach-at91/at91rm9200.c
+++ b/arch/arm/mach-at91/at91rm9200.c
@@ -15,6 +15,7 @@
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/system_misc.h>
 #include <mach/at91rm9200.h>
 #include <mach/at91_pmc.h>
 #include <mach/at91_st.h>
diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c
index 14b5a9c9a514..46f774233298 100644
--- a/arch/arm/mach-at91/at91sam9260.c
+++ b/arch/arm/mach-at91/at91sam9260.c
@@ -16,6 +16,7 @@
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/system_misc.h>
 #include <mach/cpu.h>
 #include <mach/at91_dbgu.h>
 #include <mach/at91sam9260.h>
@@ -216,6 +217,7 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("t0_clk", "fffdc000.timer", &tc3_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "fffdc000.timer", &tc4_clk),
 	CLKDEV_CON_DEV_ID("t2_clk", "fffdc000.timer", &tc5_clk),
+	CLKDEV_CON_DEV_ID("hclk", "500000.ohci", &ohci_clk),
 	/* fake hclk clock */
 	CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &ohci_clk),
 	CLKDEV_CON_ID("pioA", &pioA_clk),
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 7e5651ee9f85..5652dde4bbe2 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -598,6 +598,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		else
 			cs_pin = spi1_standard_cs[devices[i].chip_select];
 
+		if (!gpio_is_valid(cs_pin))
+			continue;
+
 		if (devices[i].bus_num == 0)
 			enable_spi0 = 1;
 		else
diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c
index 684c5dfd92ac..7de81e6222f1 100644
--- a/arch/arm/mach-at91/at91sam9261.c
+++ b/arch/arm/mach-at91/at91sam9261.c
@@ -16,6 +16,7 @@
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/system_misc.h>
 #include <mach/cpu.h>
 #include <mach/at91sam9261.h>
 #include <mach/at91_pmc.h>
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 096da87dc00d..4db961a93085 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -415,6 +415,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		else
 			cs_pin = spi1_standard_cs[devices[i].chip_select];
 
+		if (!gpio_is_valid(cs_pin))
+			continue;
+
 		if (devices[i].bus_num == 0)
 			enable_spi0 = 1;
 		else
diff --git a/arch/arm/mach-at91/at91sam9263.c b/arch/arm/mach-at91/at91sam9263.c
index 0b4fa5a7f685..ef301be66575 100644
--- a/arch/arm/mach-at91/at91sam9263.c
+++ b/arch/arm/mach-at91/at91sam9263.c
@@ -16,6 +16,7 @@
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/system_misc.h>
 #include <mach/at91sam9263.h>
 #include <mach/at91_pmc.h>
 #include <mach/at91_rstc.h>
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index 53688c46f956..fe99206de880 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -72,7 +72,8 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data)
 	/* Enable VBus control for UHP ports */
 	for (i = 0; i < data->ports; i++) {
 		if (gpio_is_valid(data->vbus_pin[i]))
-			at91_set_gpio_output(data->vbus_pin[i], 0);
+			at91_set_gpio_output(data->vbus_pin[i],
+					     data->vbus_pin_active_low[i]);
 	}
 
 	/* Enable overcurrent notification */
@@ -671,6 +672,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		else
 			cs_pin = spi1_standard_cs[devices[i].chip_select];
 
+		if (!gpio_is_valid(cs_pin))
+			continue;
+
 		if (devices[i].bus_num == 0)
 			enable_spi0 = 1;
 		else
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index 0014573dfe17..d222f8333dab 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -16,6 +16,7 @@
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/system_misc.h>
 #include <mach/at91sam9g45.h>
 #include <mach/at91_pmc.h>
 #include <mach/cpu.h>
@@ -232,6 +233,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	/* more tc lookup table for DT entries */
 	CLKDEV_CON_DEV_ID("t0_clk", "fff7c000.timer", &tcb0_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "fffd4000.timer", &tcb0_clk),
+	CLKDEV_CON_DEV_ID("hclk", "700000.ohci", &uhphs_clk),
+	CLKDEV_CON_DEV_ID("ehci_clk", "800000.ehci", &uhphs_clk),
 	/* fake hclk clock */
 	CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &uhphs_clk),
 	CLKDEV_CON_ID("pioA", &pioA_clk),
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 4320b2096789..6b008aee1dff 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -127,12 +127,13 @@ void __init at91_add_device_usbh_ohci(struct at91_usbh_data *data)
 	/* Enable VBus control for UHP ports */
 	for (i = 0; i < data->ports; i++) {
 		if (gpio_is_valid(data->vbus_pin[i]))
-			at91_set_gpio_output(data->vbus_pin[i], 0);
+			at91_set_gpio_output(data->vbus_pin[i],
+					     data->vbus_pin_active_low[i]);
 	}
 
 	/* Enable overcurrent notification */
 	for (i = 0; i < data->ports; i++) {
-		if (data->overcurrent_pin[i])
+		if (gpio_is_valid(data->overcurrent_pin[i]))
 			at91_set_gpio_input(data->overcurrent_pin[i], 1);
 	}
 
@@ -188,7 +189,8 @@ void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data)
 	/* Enable VBus control for UHP ports */
 	for (i = 0; i < data->ports; i++) {
 		if (gpio_is_valid(data->vbus_pin[i]))
-			at91_set_gpio_output(data->vbus_pin[i], 0);
+			at91_set_gpio_output(data->vbus_pin[i],
+					     data->vbus_pin_active_low[i]);
 	}
 
 	usbh_ehci_data = *data;
@@ -437,7 +439,6 @@ void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *data)
 
 	/* DMA slave channel configuration */
 	atslave->dma_dev = &at_hdmac_device.dev;
-	atslave->reg_width = AT_DMA_SLAVE_WIDTH_32BIT;
 	atslave->cfg = ATC_FIFOCFG_HALFFIFO
 			| ATC_SRC_H2SEL_HW | ATC_DST_H2SEL_HW;
 	atslave->ctrla = ATC_SCSIZE_16 | ATC_DCSIZE_16;
@@ -786,6 +787,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		else
 			cs_pin = spi1_standard_cs[devices[i].chip_select];
 
+		if (!gpio_is_valid(cs_pin))
+			continue;
+
 		if (devices[i].bus_num == 0)
 			enable_spi0 = 1;
 		else
diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c
index 63d9372eb18e..d9f2774f385e 100644
--- a/arch/arm/mach-at91/at91sam9rl.c
+++ b/arch/arm/mach-at91/at91sam9rl.c
@@ -15,6 +15,7 @@
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/system_misc.h>
 #include <mach/cpu.h>
 #include <mach/at91_dbgu.h>
 #include <mach/at91sam9rl.h>
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index eda72e83037d..fe4ae22e8561 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -419,6 +419,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 		else
 			cs_pin = spi_standard_cs[devices[i].chip_select];
 
+		if (!gpio_is_valid(cs_pin))
+			continue;
+
 		/* enable chip-select pin */
 		at91_set_gpio_output(cs_pin, 1);
 
diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c
index a34d96afa746..13c8cae60462 100644
--- a/arch/arm/mach-at91/at91sam9x5.c
+++ b/arch/arm/mach-at91/at91sam9x5.c
@@ -131,7 +131,7 @@ static struct clk dma1_clk = {
 	.type		= CLK_TYPE_PERIPHERAL,
 };
 static struct clk uhphs_clk = {
-	.name		= "uhphs_clk",
+	.name		= "uhphs",
 	.pmc_mask	= 1 << AT91SAM9X5_ID_UHPHS,
 	.type		= CLK_TYPE_PERIPHERAL,
 };
@@ -223,6 +223,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("usart", "f8028000.serial", &usart3_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "f8008000.timer", &tcb0_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "f800c000.timer", &tcb0_clk),
+	CLKDEV_CON_DEV_ID("dma_clk", "ffffec00.dma-controller", &dma0_clk),
+	CLKDEV_CON_DEV_ID("dma_clk", "ffffee00.dma-controller", &dma1_clk),
 	CLKDEV_CON_ID("pioA", &pioAB_clk),
 	CLKDEV_CON_ID("pioB", &pioAB_clk),
 	CLKDEV_CON_ID("pioC", &pioCD_clk),
@@ -230,6 +232,9 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	/* additional fake clock for macb_hclk */
 	CLKDEV_CON_DEV_ID("hclk", "f802c000.ethernet", &macb0_clk),
 	CLKDEV_CON_DEV_ID("hclk", "f8030000.ethernet", &macb1_clk),
+	CLKDEV_CON_DEV_ID("hclk", "600000.ohci", &uhphs_clk),
+	CLKDEV_CON_DEV_ID("ohci_clk", "600000.ohci", &uhphs_clk),
+	CLKDEV_CON_DEV_ID("ehci_clk", "700000.ehci", &uhphs_clk),
 };
 
 /*
@@ -299,14 +304,8 @@ static void __init at91sam9x5_map_io(void)
 	at91_init_sram(0, AT91SAM9X5_SRAM_BASE, AT91SAM9X5_SRAM_SIZE);
 }
 
-static void __init at91sam9x5_ioremap_registers(void)
-{
-	at91_ioremap_ramc(0, AT91SAM9X5_BASE_DDRSDRC0, 512);
-}
-
 void __init at91sam9x5_initialize(void)
 {
-	arm_pm_restart = at91sam9g45_restart;
 	at91_extern_irq = (1 << AT91SAM9X5_ID_IRQ0);
 
 	/* Register GPIO subsystem (using DT) */
@@ -314,11 +313,6 @@ void __init at91sam9x5_initialize(void)
 }
 
 /* --------------------------------------------------------------------
- *  AT91SAM9x5 devices (temporary before modification of code)
- * -------------------------------------------------------------------- */
-void __init at91_add_device_nand(struct atmel_nand_data *data) {}
-
-/* --------------------------------------------------------------------
  *  Interrupt initialization
  * -------------------------------------------------------------------- */
 /*
@@ -362,7 +356,6 @@ static unsigned int at91sam9x5_default_irq_priority[NR_AIC_IRQS] __initdata = {
 struct at91_init_soc __initdata at91sam9x5_soc = {
 	.map_io = at91sam9x5_map_io,
 	.default_irq_priority = at91sam9x5_default_irq_priority,
-	.ioremap_registers = at91sam9x5_ioremap_registers,
 	.register_clocks = at91sam9x5_register_clocks,
 	.init = at91sam9x5_initialize,
 };
diff --git a/arch/arm/mach-at91/at91x40.c b/arch/arm/mach-at91/at91x40.c
index 5400a1d65035..d62fe090d814 100644
--- a/arch/arm/mach-at91/at91x40.c
+++ b/arch/arm/mach-at91/at91x40.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <asm/proc-fns.h>
+#include <asm/system_misc.h>
 #include <asm/mach/arch.h>
 #include <mach/at91x40.h>
 #include <mach/at91_st.h>
diff --git a/arch/arm/mach-at91/board-afeb-9260v1.c b/arch/arm/mach-at91/board-afeb-9260v1.c
index 3bb40694b02d..161efbaa1029 100644
--- a/arch/arm/mach-at91/board-afeb-9260v1.c
+++ b/arch/arm/mach-at91/board-afeb-9260v1.c
@@ -138,6 +138,7 @@ static struct atmel_nand_data __initdata afeb9260_nand_data = {
 	.rdy_pin	= AT91_PIN_PC13,
 	.enable_pin	= AT91_PIN_PC14,
 	.bus_width_16	= 0,
+	.ecc_mode	= NAND_ECC_SOFT,
 	.parts		= afeb9260_nand_partition,
 	.num_parts	= ARRAY_SIZE(afeb9260_nand_partition),
 	.det_pin	= -EINVAL,
diff --git a/arch/arm/mach-at91/board-cam60.c b/arch/arm/mach-at91/board-cam60.c
index 8510e9e54988..c6d44ee0c77e 100644
--- a/arch/arm/mach-at91/board-cam60.c
+++ b/arch/arm/mach-at91/board-cam60.c
@@ -140,6 +140,7 @@ static struct atmel_nand_data __initdata cam60_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PA9,
 	.enable_pin	= AT91_PIN_PA7,
+	.ecc_mode	= NAND_ECC_SOFT,
 	.parts		= cam60_nand_partition,
 	.num_parts	= ARRAY_SIZE(cam60_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-cpu9krea.c b/arch/arm/mach-at91/board-cpu9krea.c
index 989e1c5a9ca0..5f3680e7c883 100644
--- a/arch/arm/mach-at91/board-cpu9krea.c
+++ b/arch/arm/mach-at91/board-cpu9krea.c
@@ -117,6 +117,7 @@ static struct atmel_nand_data __initdata cpu9krea_nand_data = {
 	.enable_pin	= AT91_PIN_PC14,
 	.bus_width_16	= 0,
 	.det_pin	= -EINVAL,
+	.ecc_mode	= NAND_ECC_SOFT,
 };
 
 #ifdef CONFIG_MACH_CPU9260
diff --git a/arch/arm/mach-at91/board-dt.c b/arch/arm/mach-at91/board-dt.c
index 583b72472ad9..c18d4d307801 100644
--- a/arch/arm/mach-at91/board-dt.c
+++ b/arch/arm/mach-at91/board-dt.c
@@ -19,10 +19,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 
-#include <mach/hardware.h>
 #include <mach/board.h>
-#include <mach/system_rev.h>
-#include <mach/at91sam9_smc.h>
 
 #include <asm/setup.h>
 #include <asm/irq.h>
@@ -30,58 +27,9 @@
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
 
-#include "sam9_smc.h"
 #include "generic.h"
 
 
-static void __init ek_init_early(void)
-{
-	/* Initialize processor: 12.000 MHz crystal */
-	at91_initialize(12000000);
-}
-
-/* det_pin is not connected */
-static struct atmel_nand_data __initdata ek_nand_data = {
-	.ale		= 21,
-	.cle		= 22,
-	.det_pin	= -EINVAL,
-	.rdy_pin	= AT91_PIN_PC8,
-	.enable_pin	= AT91_PIN_PC14,
-};
-
-static struct sam9_smc_config __initdata ek_nand_smc_config = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 2,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 2,
-
-	.ncs_read_pulse		= 4,
-	.nrd_pulse		= 4,
-	.ncs_write_pulse	= 4,
-	.nwe_pulse		= 4,
-
-	.read_cycle		= 7,
-	.write_cycle		= 7,
-
-	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE,
-	.tdf_cycles		= 3,
-};
-
-static void __init ek_add_device_nand(void)
-{
-	ek_nand_data.bus_width_16 = board_have_nand_16bit();
-	/* setup bus-width (8 or 16) */
-	if (ek_nand_data.bus_width_16)
-		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
-	else
-		ek_nand_smc_config.mode |= AT91_SMC_DBW_8;
-
-	/* configure chip-select 3 (NAND) */
-	sam9_smc_configure(0, 3, &ek_nand_smc_config);
-
-	at91_add_device_nand(&ek_nand_data);
-}
-
 static const struct of_device_id irq_of_match[] __initconst = {
 
 	{ .compatible = "atmel,at91rm9200-aic", .data = at91_aic_of_init },
@@ -98,9 +46,6 @@ static void __init at91_dt_init_irq(void)
 static void __init at91_dt_device_init(void)
 {
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-
-	/* NAND */
-	ek_add_device_nand();
 }
 
 static const char *at91_dt_board_compat[] __initdata = {
@@ -114,7 +59,7 @@ DT_MACHINE_START(at91sam_dt, "Atmel AT91SAM (Device Tree)")
 	/* Maintainer: Atmel */
 	.timer		= &at91sam926x_timer,
 	.map_io		= at91_map_io,
-	.init_early	= ek_init_early,
+	.init_early	= at91_dt_initialize,
 	.init_irq	= at91_dt_init_irq,
 	.init_machine	= at91_dt_device_init,
 	.dt_compat	= at91_dt_board_compat,
diff --git a/arch/arm/mach-at91/board-kb9202.c b/arch/arm/mach-at91/board-kb9202.c
index bb9914582013..59b92aab9bcf 100644
--- a/arch/arm/mach-at91/board-kb9202.c
+++ b/arch/arm/mach-at91/board-kb9202.c
@@ -108,6 +108,7 @@ static struct atmel_nand_data __initdata kb9202_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PC29,
 	.enable_pin	= AT91_PIN_PC28,
+	.ecc_mode	= NAND_ECC_SOFT,
 	.parts		= kb9202_nand_partition,
 	.num_parts	= ARRAY_SIZE(kb9202_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-neocore926.c b/arch/arm/mach-at91/board-neocore926.c
index 3f8617c0e04e..57d5f6a4726a 100644
--- a/arch/arm/mach-at91/board-neocore926.c
+++ b/arch/arm/mach-at91/board-neocore926.c
@@ -190,6 +190,7 @@ static struct atmel_nand_data __initdata neocore926_nand_data = {
 	.rdy_pin		= AT91_PIN_PB19,
 	.rdy_pin_active_low	= 1,
 	.enable_pin		= AT91_PIN_PD15,
+	.ecc_mode		= NAND_ECC_SOFT,
 	.parts			= neocore926_nand_partition,
 	.num_parts		= ARRAY_SIZE(neocore926_nand_partition),
 	.det_pin		= -EINVAL,
diff --git a/arch/arm/mach-at91/board-qil-a9260.c b/arch/arm/mach-at91/board-qil-a9260.c
index e029d220cb84..b6ed5ed7081a 100644
--- a/arch/arm/mach-at91/board-qil-a9260.c
+++ b/arch/arm/mach-at91/board-qil-a9260.c
@@ -138,6 +138,8 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PC13,
 	.enable_pin	= AT91_PIN_PC14,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-rm9200dk.c b/arch/arm/mach-at91/board-rm9200dk.c
index 9083df04e7ed..01332aa538b2 100644
--- a/arch/arm/mach-at91/board-rm9200dk.c
+++ b/arch/arm/mach-at91/board-rm9200dk.c
@@ -150,6 +150,8 @@ static struct atmel_nand_data __initdata dk_nand_data = {
 	.det_pin	= AT91_PIN_PB1,
 	.rdy_pin	= AT91_PIN_PC2,
 	.enable_pin	= -EINVAL,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= dk_nand_partition,
 	.num_parts	= ARRAY_SIZE(dk_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-sam9-l9260.c b/arch/arm/mach-at91/board-sam9-l9260.c
index 84bce587735f..e8b116b6cba6 100644
--- a/arch/arm/mach-at91/board-sam9-l9260.c
+++ b/arch/arm/mach-at91/board-sam9-l9260.c
@@ -139,6 +139,7 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PC13,
 	.enable_pin	= AT91_PIN_PC14,
+	.ecc_mode	= NAND_ECC_SOFT,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-sam9260ek.c b/arch/arm/mach-at91/board-sam9260ek.c
index be8233bcabdc..d5aec55b0eb4 100644
--- a/arch/arm/mach-at91/board-sam9260ek.c
+++ b/arch/arm/mach-at91/board-sam9260ek.c
@@ -181,6 +181,8 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PC13,
 	.enable_pin	= AT91_PIN_PC14,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c
index 40895072a1a7..c3f994462864 100644
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@@ -187,6 +187,8 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PC15,
 	.enable_pin	= AT91_PIN_PC14,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index 29f66052fe63..2ffe50f3a9e9 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -74,6 +74,7 @@ static void __init ek_init_early(void)
 static struct at91_usbh_data __initdata ek_usbh_data = {
 	.ports		= 2,
 	.vbus_pin	= { AT91_PIN_PA24, AT91_PIN_PA21 },
+	.vbus_pin_active_low = {1, 1},
 	.overcurrent_pin= {-EINVAL, -EINVAL},
 };
 
@@ -187,6 +188,8 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PA22,
 	.enable_pin	= AT91_PIN_PD15,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-sam9g20ek.c b/arch/arm/mach-at91/board-sam9g20ek.c
index 843d6286c6f4..8923ec9f5831 100644
--- a/arch/arm/mach-at91/board-sam9g20ek.c
+++ b/arch/arm/mach-at91/board-sam9g20ek.c
@@ -166,6 +166,8 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PC13,
 	.enable_pin	= AT91_PIN_PC14,
 	.det_pin	= -EINVAL,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-sam9m10g45ek.c b/arch/arm/mach-at91/board-sam9m10g45ek.c
index 57497e2b8878..c88e908ddd82 100644
--- a/arch/arm/mach-at91/board-sam9m10g45ek.c
+++ b/arch/arm/mach-at91/board-sam9m10g45ek.c
@@ -71,6 +71,7 @@ static void __init ek_init_early(void)
 static struct at91_usbh_data __initdata ek_usbh_hs_data = {
 	.ports		= 2,
 	.vbus_pin	= {AT91_PIN_PD1, AT91_PIN_PD3},
+	.vbus_pin_active_low = {1, 1},
 	.overcurrent_pin= {-EINVAL, -EINVAL},
 };
 
@@ -148,6 +149,8 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PC8,
 	.enable_pin	= AT91_PIN_PC14,
 	.det_pin	= -EINVAL,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-sam9rlek.c b/arch/arm/mach-at91/board-sam9rlek.c
index c1366d0032bf..b109ce2ba864 100644
--- a/arch/arm/mach-at91/board-sam9rlek.c
+++ b/arch/arm/mach-at91/board-sam9rlek.c
@@ -94,6 +94,8 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PD17,
 	.enable_pin	= AT91_PIN_PB6,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-snapper9260.c b/arch/arm/mach-at91/board-snapper9260.c
index 3c2e3fcc310c..ebc9d01ce742 100644
--- a/arch/arm/mach-at91/board-snapper9260.c
+++ b/arch/arm/mach-at91/board-snapper9260.c
@@ -110,6 +110,7 @@ static struct atmel_nand_data __initdata snapper9260_nand_data = {
 	.bus_width_16	= 0,
 	.enable_pin	= -EINVAL,
 	.det_pin	= -EINVAL,
+	.ecc_mode	= NAND_ECC_SOFT,
 };
 
 static struct sam9_smc_config __initdata snapper9260_nand_smc_config = {
diff --git a/arch/arm/mach-at91/board-stamp9g20.c b/arch/arm/mach-at91/board-stamp9g20.c
index 72eb3b4d9ab6..7640049410a0 100644
--- a/arch/arm/mach-at91/board-stamp9g20.c
+++ b/arch/arm/mach-at91/board-stamp9g20.c
@@ -86,6 +86,7 @@ static struct atmel_nand_data __initdata nand_data = {
 	.enable_pin	= AT91_PIN_PC14,
 	.bus_width_16	= 0,
 	.det_pin	= -EINVAL,
+	.ecc_mode	= NAND_ECC_SOFT,
 };
 
 static struct sam9_smc_config __initdata nand_smc_config = {
diff --git a/arch/arm/mach-at91/board-usb-a926x.c b/arch/arm/mach-at91/board-usb-a926x.c
index 26c36fc2d1e5..b7483a3d0980 100644
--- a/arch/arm/mach-at91/board-usb-a926x.c
+++ b/arch/arm/mach-at91/board-usb-a926x.c
@@ -198,6 +198,8 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PA22,
 	.enable_pin	= AT91_PIN_PD15,
+	.ecc_mode	= NAND_ECC_SOFT,
+	.on_flash_bbt	= 1,
 	.parts		= ek_nand_partition,
 	.num_parts	= ARRAY_SIZE(ek_nand_partition),
 };
diff --git a/arch/arm/mach-at91/board-yl-9200.c b/arch/arm/mach-at91/board-yl-9200.c
index 52f460768f71..38dd279d30b2 100644
--- a/arch/arm/mach-at91/board-yl-9200.c
+++ b/arch/arm/mach-at91/board-yl-9200.c
@@ -182,6 +182,7 @@ static struct atmel_nand_data __initdata yl9200_nand_data = {
 	.det_pin	= -EINVAL,
 	.rdy_pin	= AT91_PIN_PC14,	/* R/!B (Sheet10) */
 	.enable_pin	= AT91_PIN_PC15,	/* !CE  (Sheet10) */
+	.ecc_mode	= NAND_ECC_SOFT,
 	.parts		= yl9200_nand_partition,
 	.num_parts	= ARRAY_SIZE(yl9200_nand_partition),
 };
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index be51ca7f694d..a0f4d7424cdc 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -23,6 +23,7 @@
 #include <linux/delay.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/of_address.h>
 
 #include <mach/hardware.h>
 #include <mach/at91_pmc.h>
@@ -671,16 +672,12 @@ static void __init at91_upll_usbfs_clock_init(unsigned long main_clock)
 	uhpck.rate_hz /= 1 + ((at91_pmc_read(AT91_PMC_USB) & AT91_PMC_OHCIUSBDIV) >> 8);
 }
 
-int __init at91_clock_init(unsigned long main_clock)
+static int __init at91_pmc_init(unsigned long main_clock)
 {
 	unsigned tmp, freq, mckr;
 	int i;
 	int pll_overclock = false;
 
-	at91_pmc_base = ioremap(AT91_PMC, 256);
-	if (!at91_pmc_base)
-		panic("Impossible to ioremap AT91_PMC 0x%x\n", AT91_PMC);
-
 	/*
 	 * When the bootloader initialized the main oscillator correctly,
 	 * there's no problem using the cycle counter.  But if it didn't,
@@ -802,6 +799,55 @@ int __init at91_clock_init(unsigned long main_clock)
 	return 0;
 }
 
+#if defined(CONFIG_OF)
+static struct of_device_id pmc_ids[] = {
+	{ .compatible = "atmel,at91rm9200-pmc" },
+	{ /*sentinel*/ }
+};
+
+static struct of_device_id osc_ids[] = {
+	{ .compatible = "atmel,osc" },
+	{ /*sentinel*/ }
+};
+
+int __init at91_dt_clock_init(void)
+{
+	struct device_node *np;
+	u32 main_clock = 0;
+
+	np = of_find_matching_node(NULL, pmc_ids);
+	if (!np)
+		panic("unable to find compatible pmc node in dtb\n");
+
+	at91_pmc_base = of_iomap(np, 0);
+	if (!at91_pmc_base)
+		panic("unable to map pmc cpu registers\n");
+
+	of_node_put(np);
+
+	/* retrieve the freqency of fixed clocks from device tree */
+	np = of_find_matching_node(NULL, osc_ids);
+	if (np) {
+		u32 rate;
+		if (!of_property_read_u32(np, "clock-frequency", &rate))
+			main_clock = rate;
+	}
+
+	of_node_put(np);
+
+	return at91_pmc_init(main_clock);
+}
+#endif
+
+int __init at91_clock_init(unsigned long main_clock)
+{
+	at91_pmc_base = ioremap(AT91_PMC, 256);
+	if (!at91_pmc_base)
+		panic("Impossible to ioremap AT91_PMC 0x%x\n", AT91_PMC);
+
+	return at91_pmc_init(main_clock);
+}
+
 /*
  * Several unused clocks may be active.  Turn them off.
  */
diff --git a/arch/arm/mach-at91/cpuidle.c b/arch/arm/mach-at91/cpuidle.c
index 555d956b3a57..ece1f9aefb47 100644
--- a/arch/arm/mach-at91/cpuidle.c
+++ b/arch/arm/mach-at91/cpuidle.c
@@ -17,9 +17,10 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/cpuidle.h>
-#include <asm/proc-fns.h>
 #include <linux/io.h>
 #include <linux/export.h>
+#include <asm/proc-fns.h>
+#include <asm/cpuidle.h>
 
 #include "pm.h"
 
@@ -27,61 +28,39 @@
 
 static DEFINE_PER_CPU(struct cpuidle_device, at91_cpuidle_device);
 
-static struct cpuidle_driver at91_idle_driver = {
-	.name =         "at91_idle",
-	.owner =        THIS_MODULE,
-};
-
 /* Actual code that puts the SoC in different idle states */
 static int at91_enter_idle(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			       int index)
 {
-	struct timeval before, after;
-	int idle_time;
-
-	local_irq_disable();
-	do_gettimeofday(&before);
-	if (index == 0)
-		/* Wait for interrupt state */
-		cpu_do_idle();
-	else if (index == 1)
-		at91_standby();
+	at91_standby();
 
-	do_gettimeofday(&after);
-	local_irq_enable();
-	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
-			(after.tv_usec - before.tv_usec);
-
-	dev->last_residency = idle_time;
 	return index;
 }
 
+static struct cpuidle_driver at91_idle_driver = {
+	.name			= "at91_idle",
+	.owner			= THIS_MODULE,
+	.en_core_tk_irqen	= 1,
+	.states[0]		= ARM_CPUIDLE_WFI_STATE,
+	.states[1]		= {
+		.enter			= at91_enter_idle,
+		.exit_latency		= 10,
+		.target_residency	= 100000,
+		.flags			= CPUIDLE_FLAG_TIME_VALID,
+		.name			= "RAM_SR",
+		.desc			= "WFI and DDR Self Refresh",
+	},
+	.state_count = AT91_MAX_STATES,
+};
+
 /* Initialize CPU idle by registering the idle states */
 static int at91_init_cpuidle(void)
 {
 	struct cpuidle_device *device;
-	struct cpuidle_driver *driver = &at91_idle_driver;
 
 	device = &per_cpu(at91_cpuidle_device, smp_processor_id());
 	device->state_count = AT91_MAX_STATES;
-	driver->state_count = AT91_MAX_STATES;
-
-	/* Wait for interrupt state */
-	driver->states[0].enter = at91_enter_idle;
-	driver->states[0].exit_latency = 1;
-	driver->states[0].target_residency = 10000;
-	driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(driver->states[0].name, "WFI");
-	strcpy(driver->states[0].desc, "Wait for interrupt");
-
-	/* Wait for interrupt and RAM self refresh state */
-	driver->states[1].enter = at91_enter_idle;
-	driver->states[1].exit_latency = 10;
-	driver->states[1].target_residency = 10000;
-	driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(driver->states[1].name, "RAM_SR");
-	strcpy(driver->states[1].desc, "WFI and RAM Self Refresh");
 
 	cpuidle_register_driver(&at91_idle_driver);
 
diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h
index 459f01a4a546..dd9b346c451d 100644
--- a/arch/arm/mach-at91/generic.h
+++ b/arch/arm/mach-at91/generic.h
@@ -20,6 +20,7 @@ extern void __init at91_init_sram(int bank, unsigned long base,
 extern void __init at91rm9200_set_type(int type);
 extern void __init at91_initialize(unsigned long main_clock);
 extern void __init at91x40_initialize(unsigned long main_clock);
+extern void __init at91_dt_initialize(void);
 
  /* Interrupts */
 extern void __init at91_init_irq_default(void);
@@ -52,6 +53,7 @@ extern void __init at91sam9rl_set_console_clock(int id);
 extern void __init at91sam9g45_set_console_clock(int id);
 #ifdef CONFIG_AT91_PMC_UNIT
 extern int __init at91_clock_init(unsigned long main_clock);
+extern int __init at91_dt_clock_init(void);
 #else
 static int inline at91_clock_init(unsigned long main_clock) { return 0; }
 #endif
diff --git a/arch/arm/mach-at91/include/mach/at91_shdwc.h b/arch/arm/mach-at91/include/mach/at91_shdwc.h
index 1d4fe822c77a..60478ea8bd46 100644
--- a/arch/arm/mach-at91/include/mach/at91_shdwc.h
+++ b/arch/arm/mach-at91/include/mach/at91_shdwc.h
@@ -36,9 +36,11 @@ extern void __iomem *at91_shdwc_base;
 #define			AT91_SHDW_WKMODE0_HIGH		1
 #define			AT91_SHDW_WKMODE0_LOW		2
 #define			AT91_SHDW_WKMODE0_ANYLEVEL	3
-#define		AT91_SHDW_CPTWK0	(0xf << 4)		/* Counter On Wake Up 0 */
+#define		AT91_SHDW_CPTWK0_MAX	0xf			/* Maximum Counter On Wake Up 0 */
+#define		AT91_SHDW_CPTWK0	(AT91_SHDW_CPTWK0_MAX << 4) /* Counter On Wake Up 0 */
 #define			AT91_SHDW_CPTWK0_(x)	((x) << 4)
 #define		AT91_SHDW_RTTWKEN	(1   << 16)		/* Real Time Timer Wake-up Enable */
+#define		AT91_SHDW_RTCWKEN	(1   << 17)		/* Real Time Clock Wake-up Enable */
 
 #define AT91_SHDW_SR		0x08			/* Shut Down Status Register */
 #define		AT91_SHDW_WAKEUP0	(1 <<  0)		/* Wake-up 0 Status */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9x5.h b/arch/arm/mach-at91/include/mach/at91sam9x5.h
index a297a77d88e2..88e43d534cdf 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9x5.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9x5.h
@@ -55,11 +55,6 @@
 #define AT91SAM9X5_BASE_USART2	0xf8024000
 
 /*
- * System Peripherals
- */
-#define AT91SAM9X5_BASE_DDRSDRC0	0xffffe800
-
-/*
  * Base addresses for early serial code (uncompress.h)
  */
 #define AT91_DBGU	AT91_BASE_DBGU0
diff --git a/arch/arm/mach-at91/include/mach/at_hdmac.h b/arch/arm/mach-at91/include/mach/at_hdmac.h
index 187cb58345c0..fff48d1a0f4e 100644
--- a/arch/arm/mach-at91/include/mach/at_hdmac.h
+++ b/arch/arm/mach-at91/include/mach/at_hdmac.h
@@ -24,18 +24,6 @@ struct at_dma_platform_data {
 };
 
 /**
- * enum at_dma_slave_width - DMA slave register access width.
- * @AT_DMA_SLAVE_WIDTH_8BIT: Do 8-bit slave register accesses
- * @AT_DMA_SLAVE_WIDTH_16BIT: Do 16-bit slave register accesses
- * @AT_DMA_SLAVE_WIDTH_32BIT: Do 32-bit slave register accesses
- */
-enum at_dma_slave_width {
-	AT_DMA_SLAVE_WIDTH_8BIT = 0,
-	AT_DMA_SLAVE_WIDTH_16BIT,
-	AT_DMA_SLAVE_WIDTH_32BIT,
-};
-
-/**
  * struct at_dma_slave - Controller-specific information about a slave
  * @dma_dev: required DMA master device
  * @tx_reg: physical address of data register used for
@@ -48,9 +36,6 @@ enum at_dma_slave_width {
  */
 struct at_dma_slave {
 	struct device		*dma_dev;
-	dma_addr_t		tx_reg;
-	dma_addr_t		rx_reg;
-	enum at_dma_slave_width	reg_width;
 	u32			cfg;
 	u32			ctrla;
 };
diff --git a/arch/arm/mach-at91/include/mach/board.h b/arch/arm/mach-at91/include/mach/board.h
index dc8d6d4f17cf..49a821192c65 100644
--- a/arch/arm/mach-at91/include/mach/board.h
+++ b/arch/arm/mach-at91/include/mach/board.h
@@ -41,6 +41,7 @@
 #include <sound/atmel-ac97c.h>
 #include <linux/serial.h>
 #include <linux/platform_data/macb.h>
+#include <linux/platform_data/atmel.h>
 
  /* USB Device */
 struct at91_udc_data {
@@ -85,33 +86,20 @@ extern void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *d
 extern void __init at91_add_device_eth(struct macb_platform_data *data);
 
  /* USB Host */
+#define AT91_MAX_USBH_PORTS	3
 struct at91_usbh_data {
-	u8		ports;		/* number of ports on root hub */
-	int		vbus_pin[2];	/* port power-control pin */
-	u8              vbus_pin_active_low[2];
+	int		vbus_pin[AT91_MAX_USBH_PORTS];	/* port power-control pin */
+	int             overcurrent_pin[AT91_MAX_USBH_PORTS];
+	u8		ports;				/* number of ports on root hub */
 	u8              overcurrent_supported;
-	int             overcurrent_pin[2];
-	u8              overcurrent_status[2];
-	u8              overcurrent_changed[2];
+	u8              vbus_pin_active_low[AT91_MAX_USBH_PORTS];
+	u8              overcurrent_status[AT91_MAX_USBH_PORTS];
+	u8              overcurrent_changed[AT91_MAX_USBH_PORTS];
 };
 extern void __init at91_add_device_usbh(struct at91_usbh_data *data);
 extern void __init at91_add_device_usbh_ohci(struct at91_usbh_data *data);
 extern void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data);
 
- /* NAND / SmartMedia */
-struct atmel_nand_data {
-	int		enable_pin;	/* chip enable */
-	int		det_pin;	/* card detect */
-	int		rdy_pin;	/* ready/busy */
-	u8              rdy_pin_active_low;     /* rdy_pin value is inverted */
-	u8		ale;		/* address line number connected to ALE */
-	u8		cle;		/* address line number connected to CLE */
-	u8		bus_width_16;	/* buswidth is 16 bit */
-	u8		correction_cap; /* PMECC correction capability */
-	u16		sector_size;    /* Sector size for PMECC */
-	struct mtd_partition *parts;
-	unsigned int	num_parts;
-};
 extern void __init at91_add_device_nand(struct atmel_nand_data *data);
 
  /* I2C*/
diff --git a/arch/arm/mach-at91/include/mach/io.h b/arch/arm/mach-at91/include/mach/io.h
index 4003001eca3d..2d9ca0455745 100644
--- a/arch/arm/mach-at91/include/mach/io.h
+++ b/arch/arm/mach-at91/include/mach/io.h
@@ -21,11 +21,7 @@
 #ifndef __ASM_ARCH_IO_H
 #define __ASM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT		0xFFFFFFFF
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
+#define __io(a)			__typesafe_io(a)
 
 #endif
diff --git a/arch/arm/mach-at91/include/mach/system_rev.h b/arch/arm/mach-at91/include/mach/system_rev.h
index ec164a4124c9..ef79a9aafc08 100644
--- a/arch/arm/mach-at91/include/mach/system_rev.h
+++ b/arch/arm/mach-at91/include/mach/system_rev.h
@@ -7,6 +7,8 @@
 #ifndef __ARCH_SYSTEM_REV_H__
 #define __ARCH_SYSTEM_REV_H__
 
+#include <asm/system_info.h>
+
 /*
  * board revision encoding
  * mach specific
diff --git a/arch/arm/mach-at91/include/mach/uncompress.h b/arch/arm/mach-at91/include/mach/uncompress.h
index 0234fd9d20d6..4218647c1fcd 100644
--- a/arch/arm/mach-at91/include/mach/uncompress.h
+++ b/arch/arm/mach-at91/include/mach/uncompress.h
@@ -23,6 +23,7 @@
 
 #include <linux/io.h>
 #include <linux/atmel_serial.h>
+#include <mach/hardware.h>
 
 #if defined(CONFIG_AT91_EARLY_DBGU0)
 #define UART_OFFSET AT91_BASE_DBGU0
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 6c9d5e69ac28..f630250c6b87 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -197,19 +197,6 @@ extern void at91_slow_clock(void __iomem *pmc, void __iomem *ramc0,
 extern u32 at91_slow_clock_sz;
 #endif
 
-void __iomem *at91_ramc_base[2];
-
-void __init at91_ioremap_ramc(int id, u32 addr, u32 size)
-{
-	if (id < 0 || id > 1) {
-		pr_emerg("Wrong RAM controller id (%d), cannot continue\n", id);
-		BUG();
-	}
-	at91_ramc_base[id] = ioremap(addr, size);
-	if (!at91_ramc_base[id])
-		panic("Impossible to ioremap ramc.%d 0x%x\n", id, addr);
-}
-
 static int at91_pm_enter(suspend_state_t state)
 {
 	at91_gpio_suspend();
diff --git a/arch/arm/mach-at91/setup.c b/arch/arm/mach-at91/setup.c
index 372396c2ecb6..97cc04dc8073 100644
--- a/arch/arm/mach-at91/setup.c
+++ b/arch/arm/mach-at91/setup.c
@@ -9,7 +9,9 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
+#include <linux/of_address.h>
 
+#include <asm/system_misc.h>
 #include <asm/mach/map.h>
 
 #include <mach/hardware.h>
@@ -51,6 +53,19 @@ void __init at91_init_interrupts(unsigned int *priority)
 	at91_gpio_irq_setup();
 }
 
+void __iomem *at91_ramc_base[2];
+
+void __init at91_ioremap_ramc(int id, u32 addr, u32 size)
+{
+	if (id < 0 || id > 1) {
+		pr_emerg("Wrong RAM controller id (%d), cannot continue\n", id);
+		BUG();
+	}
+	at91_ramc_base[id] = ioremap(addr, size);
+	if (!at91_ramc_base[id])
+		panic("Impossible to ioremap ramc.%d 0x%x\n", id, addr);
+}
+
 static struct map_desc sram_desc[2] __initdata;
 
 void __init at91_init_sram(int bank, unsigned long base, unsigned int length)
@@ -285,6 +300,150 @@ void __init at91_ioremap_matrix(u32 base_addr)
 		panic("Impossible to ioremap at91_matrix_base\n");
 }
 
+#if defined(CONFIG_OF)
+static struct of_device_id rstc_ids[] = {
+	{ .compatible = "atmel,at91sam9260-rstc", .data = at91sam9_alt_restart },
+	{ .compatible = "atmel,at91sam9g45-rstc", .data = at91sam9g45_restart },
+	{ /*sentinel*/ }
+};
+
+static void at91_dt_rstc(void)
+{
+	struct device_node *np;
+	const struct of_device_id *of_id;
+
+	np = of_find_matching_node(NULL, rstc_ids);
+	if (!np)
+		panic("unable to find compatible rstc node in dtb\n");
+
+	at91_rstc_base = of_iomap(np, 0);
+	if (!at91_rstc_base)
+		panic("unable to map rstc cpu registers\n");
+
+	of_id = of_match_node(rstc_ids, np);
+	if (!of_id)
+		panic("AT91: rtsc no restart function availlable\n");
+
+	arm_pm_restart = of_id->data;
+
+	of_node_put(np);
+}
+
+static struct of_device_id ramc_ids[] = {
+	{ .compatible = "atmel,at91sam9260-sdramc" },
+	{ .compatible = "atmel,at91sam9g45-ddramc" },
+	{ /*sentinel*/ }
+};
+
+static void at91_dt_ramc(void)
+{
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, ramc_ids);
+	if (!np)
+		panic("unable to find compatible ram conroller node in dtb\n");
+
+	at91_ramc_base[0] = of_iomap(np, 0);
+	if (!at91_ramc_base[0])
+		panic("unable to map ramc[0] cpu registers\n");
+	/* the controller may have 2 banks */
+	at91_ramc_base[1] = of_iomap(np, 1);
+
+	of_node_put(np);
+}
+
+static struct of_device_id shdwc_ids[] = {
+	{ .compatible = "atmel,at91sam9260-shdwc", },
+	{ .compatible = "atmel,at91sam9rl-shdwc", },
+	{ .compatible = "atmel,at91sam9x5-shdwc", },
+	{ /*sentinel*/ }
+};
+
+static const char *shdwc_wakeup_modes[] = {
+	[AT91_SHDW_WKMODE0_NONE]	= "none",
+	[AT91_SHDW_WKMODE0_HIGH]	= "high",
+	[AT91_SHDW_WKMODE0_LOW]		= "low",
+	[AT91_SHDW_WKMODE0_ANYLEVEL]	= "any",
+};
+
+const int at91_dtget_shdwc_wakeup_mode(struct device_node *np)
+{
+	const char *pm;
+	int err, i;
+
+	err = of_property_read_string(np, "atmel,wakeup-mode", &pm);
+	if (err < 0)
+		return AT91_SHDW_WKMODE0_ANYLEVEL;
+
+	for (i = 0; i < ARRAY_SIZE(shdwc_wakeup_modes); i++)
+		if (!strcasecmp(pm, shdwc_wakeup_modes[i]))
+			return i;
+
+	return -ENODEV;
+}
+
+static void at91_dt_shdwc(void)
+{
+	struct device_node *np;
+	int wakeup_mode;
+	u32 reg;
+	u32 mode = 0;
+
+	np = of_find_matching_node(NULL, shdwc_ids);
+	if (!np) {
+		pr_debug("AT91: unable to find compatible shutdown (shdwc) conroller node in dtb\n");
+		return;
+	}
+
+	at91_shdwc_base = of_iomap(np, 0);
+	if (!at91_shdwc_base)
+		panic("AT91: unable to map shdwc cpu registers\n");
+
+	wakeup_mode = at91_dtget_shdwc_wakeup_mode(np);
+	if (wakeup_mode < 0) {
+		pr_warn("AT91: shdwc unknown wakeup mode\n");
+		goto end;
+	}
+
+	if (!of_property_read_u32(np, "atmel,wakeup-counter", &reg)) {
+		if (reg > AT91_SHDW_CPTWK0_MAX) {
+			pr_warn("AT91: shdwc wakeup conter 0x%x > 0x%x reduce it to 0x%x\n",
+				reg, AT91_SHDW_CPTWK0_MAX, AT91_SHDW_CPTWK0_MAX);
+			reg = AT91_SHDW_CPTWK0_MAX;
+		}
+		mode |= AT91_SHDW_CPTWK0_(reg);
+	}
+
+	if (of_property_read_bool(np, "atmel,wakeup-rtc-timer"))
+			mode |= AT91_SHDW_RTCWKEN;
+
+	if (of_property_read_bool(np, "atmel,wakeup-rtt-timer"))
+			mode |= AT91_SHDW_RTTWKEN;
+
+	at91_shdwc_write(AT91_SHDW_MR, wakeup_mode | mode);
+
+end:
+	pm_power_off = at91sam9_poweroff;
+
+	of_node_put(np);
+}
+
+void __init at91_dt_initialize(void)
+{
+	at91_dt_rstc();
+	at91_dt_ramc();
+	at91_dt_shdwc();
+
+	/* Init clock subsystem */
+	at91_dt_clock_init();
+
+	/* Register the processor-specific clocks */
+	at91_boot_soc.register_clocks();
+
+	at91_boot_soc.init();
+}
+#endif
+
 void __init at91_initialize(unsigned long main_clock)
 {
 	at91_boot_soc.ioremap_registers();
diff --git a/arch/arm/mach-clps711x/common.c b/arch/arm/mach-clps711x/common.c
index 8736c1acc166..3c5b5bbf24e5 100644
--- a/arch/arm/mach-clps711x/common.c
+++ b/arch/arm/mach-clps711x/common.c
@@ -37,6 +37,7 @@
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 #include <asm/hardware/clps7111.h>
+#include <asm/system_misc.h>
 
 /*
  * This maps the generic CLPS711x registers
diff --git a/arch/arm/mach-clps711x/edb7211-mm.c b/arch/arm/mach-clps711x/edb7211-mm.c
index 0bea1454ae03..4372f06c9929 100644
--- a/arch/arm/mach-clps711x/edb7211-mm.c
+++ b/arch/arm/mach-clps711x/edb7211-mm.c
@@ -21,6 +21,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/bug.h>
 
 #include <mach/hardware.h>
 #include <asm/page.h>
diff --git a/arch/arm/mach-clps711x/include/mach/io.h b/arch/arm/mach-clps711x/include/mach/io.h
deleted file mode 100644
index 2e0b3ced8f07..000000000000
--- a/arch/arm/mach-clps711x/include/mach/io.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- *  arch/arm/mach-clps711x/include/mach/io.h
- *
- *  Copyright (C) 1999 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-/*
- * We don't support ins[lb]/outs[lb].  Make them fault.
- */
-#define __raw_readsb(p,d,l)	do { *(int *)0 = 0; } while (0)
-#define __raw_readsl(p,d,l)	do { *(int *)0 = 0; } while (0)
-#define __raw_writesb(p,d,l)	do { *(int *)0 = 0; } while (0)
-#define __raw_writesl(p,d,l)	do { *(int *)0 = 0; } while (0)
-
-#endif
diff --git a/arch/arm/mach-clps711x/include/mach/uncompress.h b/arch/arm/mach-clps711x/include/mach/uncompress.h
index 7164310dea7c..35ed731b9f16 100644
--- a/arch/arm/mach-clps711x/include/mach/uncompress.h
+++ b/arch/arm/mach-clps711x/include/mach/uncompress.h
@@ -17,7 +17,6 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#include <mach/io.h>
 #include <mach/hardware.h>
 #include <asm/hardware/clps7111.h>
 
diff --git a/arch/arm/mach-clps711x/p720t-leds.c b/arch/arm/mach-clps711x/p720t-leds.c
index 15121446efc8..dd9a6cdbeb02 100644
--- a/arch/arm/mach-clps711x/p720t-leds.c
+++ b/arch/arm/mach-clps711x/p720t-leds.c
@@ -25,7 +25,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 #include <asm/mach-types.h>
 
 #include <asm/hardware/clps7111.h>
diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
index 941a308e1253..031805b1428d 100644
--- a/arch/arm/mach-cns3xxx/core.c
+++ b/arch/arm/mach-cns3xxx/core.c
@@ -72,13 +72,13 @@ void __init cns3xxx_map_io(void)
 /* used by entry-macro.S */
 void __init cns3xxx_init_irq(void)
 {
-	gic_init(0, 29, __io(CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT),
-		 __io(CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT));
+	gic_init(0, 29, IOMEM(CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT),
+		 IOMEM(CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT));
 }
 
 void cns3xxx_power_off(void)
 {
-	u32 __iomem *pm_base = __io(CNS3XXX_PM_BASE_VIRT);
+	u32 __iomem *pm_base = IOMEM(CNS3XXX_PM_BASE_VIRT);
 	u32 clkctrl;
 
 	printk(KERN_INFO "powering system down...\n");
@@ -237,7 +237,7 @@ static void __init __cns3xxx_timer_init(unsigned int timer_irq)
 
 static void __init cns3xxx_timer_init(void)
 {
-	cns3xxx_tmr1 = __io(CNS3XXX_TIMER1_2_3_BASE_VIRT);
+	cns3xxx_tmr1 = IOMEM(CNS3XXX_TIMER1_2_3_BASE_VIRT);
 
 	__cns3xxx_timer_init(IRQ_CNS3XXX_TIMER0);
 }
diff --git a/arch/arm/mach-cns3xxx/devices.c b/arch/arm/mach-cns3xxx/devices.c
index 79d1fb02c23f..1e40c99b015f 100644
--- a/arch/arm/mach-cns3xxx/devices.c
+++ b/arch/arm/mach-cns3xxx/devices.c
@@ -98,7 +98,7 @@ static struct platform_device cns3xxx_sdhci_pdev = {
 
 void __init cns3xxx_sdhci_init(void)
 {
-	u32 __iomem *gpioa = __io(CNS3XXX_MISC_BASE_VIRT + 0x0014);
+	u32 __iomem *gpioa = IOMEM(CNS3XXX_MISC_BASE_VIRT + 0x0014);
 	u32 gpioa_pins = __raw_readl(gpioa);
 
 	/* MMC/SD pins share with GPIOA */
diff --git a/arch/arm/mach-cns3xxx/include/mach/io.h b/arch/arm/mach-cns3xxx/include/mach/io.h
deleted file mode 100644
index 33b6fc1ece7c..000000000000
--- a/arch/arm/mach-cns3xxx/include/mach/io.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Copyright 2008 Cavium Networks
- * Copyright 2003 ARM Limited
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- */
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-
-#endif
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index d5088900af6c..a70de24d1cbc 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -36,6 +36,7 @@
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
+#include <asm/system_info.h>
 
 #include <mach/cp_intc.h>
 #include <mach/da8xx.h>
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 864f676eccac..3683306e0245 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -613,6 +613,113 @@ static void __init evm_init_i2c(void)
 	i2c_register_board_info(1, i2c_info, ARRAY_SIZE(i2c_info));
 }
 
+#define VENC_STD_ALL	(V4L2_STD_NTSC | V4L2_STD_PAL)
+
+/* venc standard timings */
+static struct vpbe_enc_mode_info dm644xevm_enc_std_timing[] = {
+	{
+		.name		= "ntsc",
+		.timings_type	= VPBE_ENC_STD,
+		.timings	= {V4L2_STD_525_60},
+		.interlaced	= 1,
+		.xres		= 720,
+		.yres		= 480,
+		.aspect		= {11, 10},
+		.fps		= {30000, 1001},
+		.left_margin	= 0x79,
+		.upper_margin	= 0x10,
+	},
+	{
+		.name		= "pal",
+		.timings_type	= VPBE_ENC_STD,
+		.timings	= {V4L2_STD_625_50},
+		.interlaced	= 1,
+		.xres		= 720,
+		.yres		= 576,
+		.aspect		= {54, 59},
+		.fps		= {25, 1},
+		.left_margin	= 0x7e,
+		.upper_margin	= 0x16,
+	},
+};
+
+/* venc dv preset timings */
+static struct vpbe_enc_mode_info dm644xevm_enc_preset_timing[] = {
+	{
+		.name		= "480p59_94",
+		.timings_type	= VPBE_ENC_DV_PRESET,
+		.timings	= {V4L2_DV_480P59_94},
+		.interlaced	= 0,
+		.xres		= 720,
+		.yres		= 480,
+		.aspect		= {1, 1},
+		.fps		= {5994, 100},
+		.left_margin	= 0x80,
+		.upper_margin	= 0x20,
+	},
+	{
+		.name		= "576p50",
+		.timings_type	= VPBE_ENC_DV_PRESET,
+		.timings	= {V4L2_DV_576P50},
+		.interlaced	= 0,
+		.xres		= 720,
+		.yres		= 576,
+		.aspect		= {1, 1},
+		.fps		= {50, 1},
+		.left_margin	= 0x7e,
+		.upper_margin	= 0x30,
+	},
+};
+
+/*
+ * The outputs available from VPBE + encoders. Keep the order same
+ * as that of encoders. First those from venc followed by that from
+ * encoders. Index in the output refers to index on a particular encoder.
+ * Driver uses this index to pass it to encoder when it supports more
+ * than one output. Userspace applications use index of the array to
+ * set an output.
+ */
+static struct vpbe_output dm644xevm_vpbe_outputs[] = {
+	{
+		.output		= {
+			.index		= 0,
+			.name		= "Composite",
+			.type		= V4L2_OUTPUT_TYPE_ANALOG,
+			.std		= VENC_STD_ALL,
+			.capabilities	= V4L2_OUT_CAP_STD,
+		},
+		.subdev_name	= VPBE_VENC_SUBDEV_NAME,
+		.default_mode	= "ntsc",
+		.num_modes	= ARRAY_SIZE(dm644xevm_enc_std_timing),
+		.modes		= dm644xevm_enc_std_timing,
+	},
+	{
+		.output		= {
+			.index		= 1,
+			.name		= "Component",
+			.type		= V4L2_OUTPUT_TYPE_ANALOG,
+			.capabilities	= V4L2_OUT_CAP_PRESETS,
+		},
+		.subdev_name	= VPBE_VENC_SUBDEV_NAME,
+		.default_mode	= "480p59_94",
+		.num_modes	= ARRAY_SIZE(dm644xevm_enc_preset_timing),
+		.modes		= dm644xevm_enc_preset_timing,
+	},
+};
+
+static struct vpbe_config dm644xevm_display_cfg = {
+	.module_name	= "dm644x-vpbe-display",
+	.i2c_adapter_id	= 1,
+	.osd		= {
+		.module_name	= VPBE_OSD_SUBDEV_NAME,
+	},
+	.venc		= {
+		.module_name	= VPBE_VENC_SUBDEV_NAME,
+	},
+	.num_outputs	= ARRAY_SIZE(dm644xevm_vpbe_outputs),
+	.outputs	= dm644xevm_vpbe_outputs,
+};
+
 static struct platform_device *davinci_evm_devices[] __initdata = {
 	&davinci_fb_device,
 	&rtc_dev,
@@ -696,7 +803,7 @@ static __init void davinci_evm_init(void)
 	evm_init_i2c();
 
 	davinci_setup_mmc(0, &dm6446evm_mmc_config);
-	dm644x_init_video(&dm644xevm_capture_cfg);
+	dm644x_init_video(&dm644xevm_capture_cfg, &dm644xevm_display_cfg);
 
 	davinci_serial_init(&uart_config);
 	dm644x_init_asp(&dm644x_evm_snd_data);
diff --git a/arch/arm/mach-davinci/cpuidle.c b/arch/arm/mach-davinci/cpuidle.c
index a30c7c5a6d83..9107691adbdb 100644
--- a/arch/arm/mach-davinci/cpuidle.c
+++ b/arch/arm/mach-davinci/cpuidle.c
@@ -18,6 +18,7 @@
 #include <linux/io.h>
 #include <linux/export.h>
 #include <asm/proc-fns.h>
+#include <asm/cpuidle.h>
 
 #include <mach/cpuidle.h>
 #include <mach/ddr2.h>
@@ -30,12 +31,43 @@ struct davinci_ops {
 	u32 flags;
 };
 
+/* Actual code that puts the SoC in different idle states */
+static int davinci_enter_idle(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv,
+						int index)
+{
+	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
+	struct davinci_ops *ops = cpuidle_get_statedata(state_usage);
+
+	if (ops && ops->enter)
+		ops->enter(ops->flags);
+
+	index = cpuidle_wrap_enter(dev,	drv, index,
+				arm_cpuidle_simple_enter);
+
+	if (ops && ops->exit)
+		ops->exit(ops->flags);
+
+	return index;
+}
+
 /* fields in davinci_ops.flags */
 #define DAVINCI_CPUIDLE_FLAGS_DDR2_PWDN	BIT(0)
 
 static struct cpuidle_driver davinci_idle_driver = {
-	.name	= "cpuidle-davinci",
-	.owner	= THIS_MODULE,
+	.name			= "cpuidle-davinci",
+	.owner			= THIS_MODULE,
+	.en_core_tk_irqen	= 1,
+	.states[0]		= ARM_CPUIDLE_WFI_STATE,
+	.states[1]		= {
+		.enter			= davinci_enter_idle,
+		.exit_latency		= 10,
+		.target_residency	= 100000,
+		.flags			= CPUIDLE_FLAG_TIME_VALID,
+		.name			= "DDR SR",
+		.desc			= "WFI and DDR Self Refresh",
+	},
+	.state_count = DAVINCI_CPUIDLE_MAX_STATES,
 };
 
 static DEFINE_PER_CPU(struct cpuidle_device, davinci_cpuidle_device);
@@ -77,41 +109,10 @@ static struct davinci_ops davinci_states[DAVINCI_CPUIDLE_MAX_STATES] = {
 	},
 };
 
-/* Actual code that puts the SoC in different idle states */
-static int davinci_enter_idle(struct cpuidle_device *dev,
-				struct cpuidle_driver *drv,
-						int index)
-{
-	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
-	struct davinci_ops *ops = cpuidle_get_statedata(state_usage);
-	struct timeval before, after;
-	int idle_time;
-
-	local_irq_disable();
-	do_gettimeofday(&before);
-
-	if (ops && ops->enter)
-		ops->enter(ops->flags);
-	/* Wait for interrupt state */
-	cpu_do_idle();
-	if (ops && ops->exit)
-		ops->exit(ops->flags);
-
-	do_gettimeofday(&after);
-	local_irq_enable();
-	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
-			(after.tv_usec - before.tv_usec);
-
-	dev->last_residency = idle_time;
-
-	return index;
-}
-
 static int __init davinci_cpuidle_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct cpuidle_device *device;
-	struct cpuidle_driver *driver = &davinci_idle_driver;
 	struct davinci_cpuidle_config *pdata = pdev->dev.platform_data;
 
 	device = &per_cpu(davinci_cpuidle_device, smp_processor_id());
@@ -123,27 +124,11 @@ static int __init davinci_cpuidle_probe(struct platform_device *pdev)
 
 	ddr2_reg_base = pdata->ddr2_ctlr_base;
 
-	/* Wait for interrupt state */
-	driver->states[0].enter = davinci_enter_idle;
-	driver->states[0].exit_latency = 1;
-	driver->states[0].target_residency = 10000;
-	driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(driver->states[0].name, "WFI");
-	strcpy(driver->states[0].desc, "Wait for interrupt");
-
-	/* Wait for interrupt and DDR self refresh state */
-	driver->states[1].enter = davinci_enter_idle;
-	driver->states[1].exit_latency = 10;
-	driver->states[1].target_residency = 10000;
-	driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(driver->states[1].name, "DDR SR");
-	strcpy(driver->states[1].desc, "WFI and DDR Self Refresh");
 	if (pdata->ddr2_pdown)
 		davinci_states[1].flags |= DAVINCI_CPUIDLE_FLAGS_DDR2_PWDN;
 	cpuidle_set_statedata(&device->states_usage[1], &davinci_states[1]);
 
 	device->state_count = DAVINCI_CPUIDLE_MAX_STATES;
-	driver->state_count = DAVINCI_CPUIDLE_MAX_STATES;
 
 	ret = cpuidle_register_driver(&davinci_idle_driver);
 	if (ret) {
diff --git a/arch/arm/mach-davinci/davinci.h b/arch/arm/mach-davinci/davinci.h
index 9d708034b57f..3e519dad5bb9 100644
--- a/arch/arm/mach-davinci/davinci.h
+++ b/arch/arm/mach-davinci/davinci.h
@@ -29,9 +29,15 @@
 
 #include <media/davinci/vpfe_capture.h>
 #include <media/davinci/vpif_types.h>
+#include <media/davinci/vpss.h>
+#include <media/davinci/vpbe_types.h>
+#include <media/davinci/vpbe_venc.h>
+#include <media/davinci/vpbe.h>
+#include <media/davinci/vpbe_osd.h>
 
 #define DAVINCI_SYSTEM_MODULE_BASE	0x01c40000
 #define SYSMOD_VIDCLKCTL		0x38
+#define SYSMOD_VPSS_CLKCTL		0x44
 #define SYSMOD_VDD3P3VPWDN		0x48
 #define SYSMOD_VSCLKDIS			0x6c
 #define SYSMOD_PUPDCTL1			0x7c
@@ -83,7 +89,7 @@ void dm365_set_vpfe_config(struct vpfe_config *cfg);
 /* DM644x function declarations */
 void __init dm644x_init(void);
 void __init dm644x_init_asp(struct snd_platform_data *pdata);
-int __init dm644x_init_video(struct vpfe_config *);
+int __init dm644x_init_video(struct vpfe_config *, struct vpbe_config *);
 
 /* DM646x function declarations */
 void __init dm646x_init(void);
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index 23e81cafba8d..c8b866657fcb 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -627,7 +627,7 @@ static struct resource dm644x_vpfe_resources[] = {
 	},
 };
 
-static u64 vpfe_capture_dma_mask = DMA_BIT_MASK(32);
+static u64 dm644x_video_dma_mask = DMA_BIT_MASK(32);
 static struct resource dm644x_ccdc_resource[] = {
 	/* CCDC Base address */
 	{
@@ -643,7 +643,7 @@ static struct platform_device dm644x_ccdc_dev = {
 	.num_resources  = ARRAY_SIZE(dm644x_ccdc_resource),
 	.resource       = dm644x_ccdc_resource,
 	.dev = {
-		.dma_mask               = &vpfe_capture_dma_mask,
+		.dma_mask               = &dm644x_video_dma_mask,
 		.coherent_dma_mask      = DMA_BIT_MASK(32),
 	},
 };
@@ -654,7 +654,134 @@ static struct platform_device dm644x_vpfe_dev = {
 	.num_resources	= ARRAY_SIZE(dm644x_vpfe_resources),
 	.resource	= dm644x_vpfe_resources,
 	.dev = {
-		.dma_mask		= &vpfe_capture_dma_mask,
+		.dma_mask		= &dm644x_video_dma_mask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	},
+};
+
+#define DM644X_OSD_BASE		0x01c72600
+
+static struct resource dm644x_osd_resources[] = {
+	{
+		.start	= DM644X_OSD_BASE,
+		.end	= DM644X_OSD_BASE + 0x1ff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct osd_platform_data dm644x_osd_data = {
+	.vpbe_type     = VPBE_VERSION_1,
+};
+
+static struct platform_device dm644x_osd_dev = {
+	.name		= VPBE_OSD_SUBDEV_NAME,
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(dm644x_osd_resources),
+	.resource	= dm644x_osd_resources,
+	.dev		= {
+		.dma_mask		= &dm644x_video_dma_mask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+		.platform_data		= &dm644x_osd_data,
+	},
+};
+
+#define DM644X_VENC_BASE		0x01c72400
+
+static struct resource dm644x_venc_resources[] = {
+	{
+		.start	= DM644X_VENC_BASE,
+		.end	= DM644X_VENC_BASE + 0x17f,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+#define DM644X_VPSS_MUXSEL_PLL2_MODE          BIT(0)
+#define DM644X_VPSS_MUXSEL_VPBECLK_MODE       BIT(1)
+#define DM644X_VPSS_VENCLKEN                  BIT(3)
+#define DM644X_VPSS_DACCLKEN                  BIT(4)
+
+static int dm644x_venc_setup_clock(enum vpbe_enc_timings_type type,
+				   unsigned int mode)
+{
+	int ret = 0;
+	u32 v = DM644X_VPSS_VENCLKEN;
+
+	switch (type) {
+	case VPBE_ENC_STD:
+		v |= DM644X_VPSS_DACCLKEN;
+		writel(v, DAVINCI_SYSMOD_VIRT(SYSMOD_VPSS_CLKCTL));
+		break;
+	case VPBE_ENC_DV_PRESET:
+		switch (mode) {
+		case V4L2_DV_480P59_94:
+		case V4L2_DV_576P50:
+			v |= DM644X_VPSS_MUXSEL_PLL2_MODE |
+			     DM644X_VPSS_DACCLKEN;
+			writel(v, DAVINCI_SYSMOD_VIRT(SYSMOD_VPSS_CLKCTL));
+			break;
+		case V4L2_DV_720P60:
+		case V4L2_DV_1080I60:
+		case V4L2_DV_1080P30:
+			/*
+			 * For HD, use external clock source since
+			 * HD requires higher clock rate
+			 */
+			v |= DM644X_VPSS_MUXSEL_VPBECLK_MODE;
+			writel(v, DAVINCI_SYSMOD_VIRT(SYSMOD_VPSS_CLKCTL));
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+		}
+		break;
+	default:
+		ret  = -EINVAL;
+	}
+
+	return ret;
+}
+
+static struct resource dm644x_v4l2_disp_resources[] = {
+	{
+		.start	= IRQ_VENCINT,
+		.end	= IRQ_VENCINT,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device dm644x_vpbe_display = {
+	.name		= "vpbe-v4l2",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(dm644x_v4l2_disp_resources),
+	.resource	= dm644x_v4l2_disp_resources,
+	.dev		= {
+		.dma_mask		= &dm644x_video_dma_mask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	},
+};
+
+static struct venc_platform_data dm644x_venc_pdata = {
+	.venc_type	= VPBE_VERSION_1,
+	.setup_clock	= dm644x_venc_setup_clock,
+};
+
+static struct platform_device dm644x_venc_dev = {
+	.name		= VPBE_VENC_SUBDEV_NAME,
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(dm644x_venc_resources),
+	.resource	= dm644x_venc_resources,
+	.dev		= {
+		.dma_mask		= &dm644x_video_dma_mask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+		.platform_data		= &dm644x_venc_pdata,
+	},
+};
+
+static struct platform_device dm644x_vpbe_dev = {
+	.name		= "vpbe_controller",
+	.id		= -1,
+	.dev		= {
+		.dma_mask		= &dm644x_video_dma_mask,
 		.coherent_dma_mask	= DMA_BIT_MASK(32),
 	},
 };
@@ -786,17 +913,30 @@ void __init dm644x_init(void)
 	davinci_map_sysmod();
 }
 
-int __init dm644x_init_video(struct vpfe_config *vpfe_cfg)
+int __init dm644x_init_video(struct vpfe_config *vpfe_cfg,
+				struct vpbe_config *vpbe_cfg)
 {
-	dm644x_vpfe_dev.dev.platform_data = vpfe_cfg;
-
-	/* Add ccdc clock aliases */
-	clk_add_alias("master", dm644x_ccdc_dev.name, "vpss_master", NULL);
-	clk_add_alias("slave", dm644x_ccdc_dev.name, "vpss_slave", NULL);
-
-	platform_device_register(&dm644x_vpss_device);
-	platform_device_register(&dm644x_ccdc_dev);
-	platform_device_register(&dm644x_vpfe_dev);
+	if (vpfe_cfg || vpbe_cfg)
+		platform_device_register(&dm644x_vpss_device);
+
+	if (vpfe_cfg) {
+		dm644x_vpfe_dev.dev.platform_data = vpfe_cfg;
+		platform_device_register(&dm644x_ccdc_dev);
+		platform_device_register(&dm644x_vpfe_dev);
+		/* Add ccdc clock aliases */
+		clk_add_alias("master", dm644x_ccdc_dev.name,
+			      "vpss_master", NULL);
+		clk_add_alias("slave", dm644x_ccdc_dev.name,
+			      "vpss_slave", NULL);
+	}
+
+	if (vpbe_cfg) {
+		dm644x_vpbe_dev.dev.platform_data = vpbe_cfg;
+		platform_device_register(&dm644x_osd_dev);
+		platform_device_register(&dm644x_venc_dev);
+		platform_device_register(&dm644x_vpbe_dev);
+		platform_device_register(&dm644x_vpbe_display);
+	}
 
 	return 0;
 }
diff --git a/arch/arm/mach-davinci/include/mach/entry-macro.S b/arch/arm/mach-davinci/include/mach/entry-macro.S
index c1661d2feca9..768b3c060214 100644
--- a/arch/arm/mach-davinci/include/mach/entry-macro.S
+++ b/arch/arm/mach-davinci/include/mach/entry-macro.S
@@ -8,7 +8,6 @@
  * is licensed "as is" without any warranty of any kind, whether express
  * or implied.
  */
-#include <mach/io.h>
 #include <mach/irqs.h>
 
 		.macro  get_irqnr_preamble, base, tmp
diff --git a/arch/arm/mach-davinci/include/mach/hardware.h b/arch/arm/mach-davinci/include/mach/hardware.h
index 0209b1fc22a1..2184691ebc2f 100644
--- a/arch/arm/mach-davinci/include/mach/hardware.h
+++ b/arch/arm/mach-davinci/include/mach/hardware.h
@@ -30,10 +30,4 @@
 #define __IO_ADDRESS(x)			((x) + IO_OFFSET)
 #define IO_ADDRESS(pa)			IOMEM(__IO_ADDRESS(pa))
 
-#ifdef __ASSEMBLER__
-#define IOMEM(x)                	x
-#else
-#define IOMEM(x)                	((void __force __iomem *)(x))
-#endif
-
 #endif /* __ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-davinci/include/mach/io.h b/arch/arm/mach-davinci/include/mach/io.h
deleted file mode 100644
index b2267d1e1a71..000000000000
--- a/arch/arm/mach-davinci/include/mach/io.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * DaVinci IO address definitions
- *
- * Copied from include/asm/arm/arch-omap/io.h
- *
- * 2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-#ifndef __ASM_ARCH_IO_H
-#define __ASM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-#define __mem_isa(a)		(a)
-
-#endif /* __ASM_ARCH_IO_H */
diff --git a/arch/arm/mach-davinci/include/mach/uncompress.h b/arch/arm/mach-davinci/include/mach/uncompress.h
index 9dc7cf9664fe..da2fb2c2155a 100644
--- a/arch/arm/mach-davinci/include/mach/uncompress.h
+++ b/arch/arm/mach-davinci/include/mach/uncompress.h
@@ -25,6 +25,8 @@
 
 #include <mach/serial.h>
 
+#define IOMEM(x)	((void __force __iomem *)(x))
+
 u32 *uart;
 
 /* PORT_16C550A, in polled non-fifo mode */
diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c
index e1969ce904dc..75da315b6587 100644
--- a/arch/arm/mach-davinci/time.c
+++ b/arch/arm/mach-davinci/time.c
@@ -19,11 +19,14 @@
 #include <linux/err.h>
 #include <linux/platform_device.h>
 
-#include <mach/hardware.h>
+#include <asm/sched_clock.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
+
 #include <mach/cputype.h>
+#include <mach/hardware.h>
 #include <mach/time.h>
+
 #include "clock.h"
 
 static struct clock_event_device clockevent_davinci;
@@ -272,19 +275,9 @@ static cycle_t read_cycles(struct clocksource *cs)
 	return (cycles_t)timer32_read(t);
 }
 
-/*
- * Kernel assumes that sched_clock can be called early but may not have
- * things ready yet.
- */
-static cycle_t read_dummy(struct clocksource *cs)
-{
-	return 0;
-}
-
-
 static struct clocksource clocksource_davinci = {
 	.rating		= 300,
-	.read		= read_dummy,
+	.read		= read_cycles,
 	.mask		= CLOCKSOURCE_MASK(32),
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -292,12 +285,9 @@ static struct clocksource clocksource_davinci = {
 /*
  * Overwrite weak default sched_clock with something more precise
  */
-unsigned long long notrace sched_clock(void)
+static u32 notrace davinci_read_sched_clock(void)
 {
-	const cycle_t cyc = clocksource_davinci.read(&clocksource_davinci);
-
-	return clocksource_cyc2ns(cyc, clocksource_davinci.mult,
-				clocksource_davinci.shift);
+	return timer32_read(&timers[TID_CLOCKSOURCE]);
 }
 
 /*
@@ -397,12 +387,14 @@ static void __init davinci_timer_init(void)
 	davinci_clock_tick_rate = clk_get_rate(timer_clk);
 
 	/* setup clocksource */
-	clocksource_davinci.read = read_cycles;
 	clocksource_davinci.name = id_to_name[clocksource_id];
 	if (clocksource_register_hz(&clocksource_davinci,
 				    davinci_clock_tick_rate))
 		printk(err, clocksource_davinci.name);
 
+	setup_sched_clock(davinci_read_sched_clock, 32,
+			  davinci_clock_tick_rate);
+
 	/* setup clockevent */
 	clockevent_davinci.name = id_to_name[timers[TID_CLOCKEVENT].id];
 	clockevent_davinci.mult = div_sc(davinci_clock_tick_rate, NSEC_PER_SEC,
diff --git a/arch/arm/mach-dove/addr-map.c b/arch/arm/mach-dove/addr-map.c
index 98b8c83b09ab..2a06c0163418 100644
--- a/arch/arm/mach-dove/addr-map.c
+++ b/arch/arm/mach-dove/addr-map.c
@@ -14,6 +14,7 @@
 #include <linux/io.h>
 #include <asm/mach/arch.h>
 #include <asm/setup.h>
+#include <mach/dove.h>
 #include <plat/addr-map.h>
 #include "common.h"
 
diff --git a/arch/arm/mach-dove/include/mach/io.h b/arch/arm/mach-dove/include/mach/io.h
index eb4936ff90ad..29c8b85355a5 100644
--- a/arch/arm/mach-dove/include/mach/io.h
+++ b/arch/arm/mach-dove/include/mach/io.h
@@ -15,6 +15,5 @@
 
 #define __io(a)  	((void __iomem *)(((a) - DOVE_PCIE0_IO_BUS_BASE) + \
 						 DOVE_PCIE0_IO_VIRT_BASE))
-#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index 804c9122b7b3..6f8068692edf 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -22,7 +22,7 @@
 #include <asm/mach-types.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
+#include <asm/system_misc.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -30,10 +30,7 @@
 
 #include <asm/mach/time.h>
 
-#define IRQ_MASK		0xfe000000	/* read */
-#define IRQ_MSET		0xfe000000	/* write */
-#define IRQ_STAT		0xff000000	/* read */
-#define IRQ_MCLR		0xff000000	/* write */
+#include "core.h"
 
 static void ebsa110_mask_irq(struct irq_data *d)
 {
@@ -79,22 +76,22 @@ static struct map_desc ebsa110_io_desc[] __initdata = {
 	{	/* IRQ_STAT/IRQ_MCLR */
 		.virtual	= IRQ_STAT,
 		.pfn		= __phys_to_pfn(TRICK4_PHYS),
-		.length		= PGDIR_SIZE,
+		.length		= TRICK4_SIZE,
 		.type		= MT_DEVICE
 	}, {	/* IRQ_MASK/IRQ_MSET */
 		.virtual	= IRQ_MASK,
 		.pfn		= __phys_to_pfn(TRICK3_PHYS),
-		.length		= PGDIR_SIZE,
+		.length		= TRICK3_SIZE,
 		.type		= MT_DEVICE
 	}, {	/* SOFT_BASE */
 		.virtual	= SOFT_BASE,
 		.pfn		= __phys_to_pfn(TRICK1_PHYS),
-		.length		= PGDIR_SIZE,
+		.length		= TRICK1_SIZE,
 		.type		= MT_DEVICE
 	}, {	/* PIT_BASE */
 		.virtual	= PIT_BASE,
 		.pfn		= __phys_to_pfn(TRICK0_PHYS),
-		.length		= PGDIR_SIZE,
+		.length		= TRICK0_SIZE,
 		.type		= MT_DEVICE
 	},
 
@@ -119,6 +116,20 @@ static void __init ebsa110_map_io(void)
 	iotable_init(ebsa110_io_desc, ARRAY_SIZE(ebsa110_io_desc));
 }
 
+static void __iomem *ebsa110_ioremap_caller(unsigned long cookie, size_t size,
+					    unsigned int flags, void *caller)
+{
+	return (void __iomem *)cookie;
+}
+
+static void ebsa110_iounmap(volatile void __iomem *io_addr)
+{}
+
+static void __init ebsa110_init_early(void)
+{
+	arch_ioremap_caller = ebsa110_ioremap_caller;
+	arch_iounmap = ebsa110_iounmap;
+}
 
 #define PIT_CTRL		(PIT_BASE + 0x0d)
 #define PIT_T2			(PIT_BASE + 0x09)
@@ -315,6 +326,7 @@ MACHINE_START(EBSA110, "EBSA110")
 	.reserve_lp2	= 1,
 	.restart_mode	= 's',
 	.map_io		= ebsa110_map_io,
+	.init_early	= ebsa110_init_early,
 	.init_irq	= ebsa110_init_irq,
 	.timer		= &ebsa110_timer,
 	.restart	= ebsa110_restart,
diff --git a/arch/arm/mach-ebsa110/core.h b/arch/arm/mach-ebsa110/core.h
new file mode 100644
index 000000000000..c93c9e43012d
--- /dev/null
+++ b/arch/arm/mach-ebsa110/core.h
@@ -0,0 +1,41 @@
+/*
+ *  Copyright (C) 1996-2000 Russell King.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This file contains the core hardware definitions of the EBSA-110.
+ */
+#ifndef CORE_H
+#define CORE_H
+
+/* Physical addresses/sizes */
+#define ISAMEM_PHYS		0xe0000000
+#define ISAMEM_SIZE		0x10000000
+
+#define ISAIO_PHYS		0xf0000000
+#define ISAIO_SIZE		PGDIR_SIZE
+
+#define TRICK0_PHYS		0xf2000000
+#define TRICK0_SIZE		PGDIR_SIZE
+#define TRICK1_PHYS		0xf2400000
+#define TRICK1_SIZE		PGDIR_SIZE
+#define TRICK2_PHYS		0xf2800000
+#define TRICK3_PHYS		0xf2c00000
+#define TRICK3_SIZE		PGDIR_SIZE
+#define TRICK4_PHYS		0xf3000000
+#define TRICK4_SIZE		PGDIR_SIZE
+#define TRICK5_PHYS		0xf3400000
+#define TRICK6_PHYS		0xf3800000
+#define TRICK7_PHYS		0xf3c00000
+
+/* Virtual addresses */
+#define PIT_BASE		0xfc000000	/* trick 0 */
+#define SOFT_BASE		0xfd000000	/* trick 1 */
+#define IRQ_MASK		0xfe000000	/* trick 3 - read */
+#define IRQ_MSET		0xfe000000	/* trick 3 - write */
+#define IRQ_STAT		0xff000000	/* trick 4 - read */
+#define IRQ_MCLR		0xff000000	/* trick 4 - write */
+
+#endif
diff --git a/arch/arm/mach-ebsa110/include/mach/hardware.h b/arch/arm/mach-ebsa110/include/mach/hardware.h
index 4b2fb7743909..f4e5407bd004 100644
--- a/arch/arm/mach-ebsa110/include/mach/hardware.h
+++ b/arch/arm/mach-ebsa110/include/mach/hardware.h
@@ -12,48 +12,9 @@
 #ifndef __ASM_ARCH_HARDWARE_H
 #define __ASM_ARCH_HARDWARE_H
 
-/*
- * The EBSA110 has a weird "ISA IO" region:
- *
- * Region 0 (addr = 0xf0000000 + io << 2)
- * --------------------------------------------------------
- * Physical region	IO region
- * f0000fe0 - f0000ffc	3f8 - 3ff  ttyS0
- * f0000e60 - f0000e64	398 - 399
- * f0000de0 - f0000dfc	378 - 37f  lp0
- * f0000be0 - f0000bfc	2f8 - 2ff  ttyS1
- *
- * Region 1 (addr = 0xf0000000 + (io & ~1) << 1 + (io & 1))
- * --------------------------------------------------------
- * Physical region	IO region
- * f00014f1             a79        pnp write data
- * f00007c0 - f00007c1	3e0 - 3e1  pcmcia
- * f00004f1		279        pnp address
- * f0000440 - f000046c  220 - 236  eth0
- * f0000405		203        pnp read data
- */
-
-#define ISAMEM_PHYS		0xe0000000
-#define ISAMEM_SIZE		0x10000000
-
-#define ISAIO_PHYS		0xf0000000
-#define ISAIO_SIZE		PGDIR_SIZE
-
-#define TRICK0_PHYS		0xf2000000
-#define TRICK1_PHYS		0xf2400000
-#define TRICK2_PHYS		0xf2800000
-#define TRICK3_PHYS		0xf2c00000
-#define TRICK4_PHYS		0xf3000000
-#define TRICK5_PHYS		0xf3400000
-#define TRICK6_PHYS		0xf3800000
-#define TRICK7_PHYS		0xf3c00000
-
 #define ISAMEM_BASE		0xe0000000
 #define ISAIO_BASE		0xf0000000
 
-#define PIT_BASE		0xfc000000
-#define SOFT_BASE		0xfd000000
-
 /*
  * RAM definitions
  */
diff --git a/arch/arm/mach-ebsa110/include/mach/io.h b/arch/arm/mach-ebsa110/include/mach/io.h
index 44679db672fb..11bb0799424b 100644
--- a/arch/arm/mach-ebsa110/include/mach/io.h
+++ b/arch/arm/mach-ebsa110/include/mach/io.h
@@ -62,15 +62,6 @@ void __writel(u32 val, void __iomem *addr);
 #define writew(v,b)		__writew(v,b)
 #define writel(v,b)		__writel(v,b)
 
-static inline void __iomem *__arch_ioremap(unsigned long cookie, size_t size,
-					   unsigned int flags)
-{
-	return (void __iomem *)cookie;
-}
-
-#define __arch_ioremap		__arch_ioremap
-#define __arch_iounmap(cookie)	do { } while (0)
-
 extern void insb(unsigned int port, void *buf, int sz);
 extern void insw(unsigned int port, void *buf, int sz);
 extern void insl(unsigned int port, void *buf, int sz);
diff --git a/arch/arm/mach-ebsa110/io.c b/arch/arm/mach-ebsa110/io.c
index c52e3047a7eb..756cc377a73d 100644
--- a/arch/arm/mach-ebsa110/io.c
+++ b/arch/arm/mach-ebsa110/io.c
@@ -177,6 +177,26 @@ void writesl(void __iomem *addr, const void *data, int len)
 }
 EXPORT_SYMBOL(writesl);
 
+/*
+ * The EBSA110 has a weird "ISA IO" region:
+ *
+ * Region 0 (addr = 0xf0000000 + io << 2)
+ * --------------------------------------------------------
+ * Physical region	IO region
+ * f0000fe0 - f0000ffc	3f8 - 3ff  ttyS0
+ * f0000e60 - f0000e64	398 - 399
+ * f0000de0 - f0000dfc	378 - 37f  lp0
+ * f0000be0 - f0000bfc	2f8 - 2ff  ttyS1
+ *
+ * Region 1 (addr = 0xf0000000 + (io & ~1) << 1 + (io & 1))
+ * --------------------------------------------------------
+ * Physical region	IO region
+ * f00014f1             a79        pnp write data
+ * f00007c0 - f00007c1	3e0 - 3e1  pcmcia
+ * f00004f1		279        pnp address
+ * f0000440 - f000046c  220 - 236  eth0
+ * f0000405		203        pnp read data
+ */
 #define SUPERIO_PORT(p) \
 	(((p) >> 3) == (0x3f8 >> 3) || \
 	 ((p) >> 3) == (0x2f8 >> 3) || \
diff --git a/arch/arm/mach-ebsa110/leds.c b/arch/arm/mach-ebsa110/leds.c
index 6a6ea57c2a4e..99e14e362500 100644
--- a/arch/arm/mach-ebsa110/leds.c
+++ b/arch/arm/mach-ebsa110/leds.c
@@ -17,9 +17,10 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 #include <asm/mach-types.h>
 
+#include "core.h"
+
 static spinlock_t leds_lock;
 
 static void ebsa110_leds_event(led_event_t ledevt)
diff --git a/arch/arm/mach-ep93xx/include/mach/io.h b/arch/arm/mach-ep93xx/include/mach/io.h
deleted file mode 100644
index 594b77f21054..000000000000
--- a/arch/arm/mach-ep93xx/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-ep93xx/include/mach/io.h
- */
-
-#ifndef __ASM_MACH_IO_H
-#define __ASM_MACH_IO_H
-
-#define IO_SPACE_LIMIT		0xffffffff
-
-#define __io(p)			__typesafe_io(p)
-#define __mem_pci(p)		(p)
-
-/*
- * A typesafe __io() variation for variable initialisers
- */
-#ifdef __ASSEMBLER__
-#define IOMEM(p)		p
-#else
-#define IOMEM(p)		((void __iomem __force *)(p))
-#endif
-
-#endif /* __ASM_MACH_IO_H */
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 2bf7d6e23989..0491ceef1cda 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -11,18 +11,19 @@ if ARCH_EXYNOS
 
 menu "SAMSUNG EXYNOS SoCs Support"
 
-choice
-	prompt "EXYNOS System Type"
-	default ARCH_EXYNOS4
-
 config ARCH_EXYNOS4
 	bool "SAMSUNG EXYNOS4"
+	default y
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
 	help
 	  Samsung EXYNOS4 SoCs based systems
 
-endchoice
+config ARCH_EXYNOS5
+	bool "SAMSUNG EXYNOS5"
+	select HAVE_SMP
+	help
+	  Samsung EXYNOS5 (Cortex-A15) SoC based systems
 
 comment "EXYNOS SoCs"
 
@@ -56,6 +57,13 @@ config SOC_EXYNOS4412
 	help
 	  Enable EXYNOS4412 SoC support
 
+config SOC_EXYNOS5250
+	bool "SAMSUNG EXYNOS5250"
+	default y
+	depends on ARCH_EXYNOS5
+	help
+	  Enable EXYNOS5250 SoC support
+
 config EXYNOS4_MCT
 	bool
 	default y
@@ -356,7 +364,7 @@ config MACH_SMDK4412
 	  Machine support for Samsung SMDK4412
 endif
 
-comment "Flattened Device Tree based board for Exynos4 based SoC"
+comment "Flattened Device Tree based board for EXYNOS SoCs"
 
 config MACH_EXYNOS4_DT
 	bool "Samsung Exynos4 Machine using device tree"
@@ -370,6 +378,15 @@ config MACH_EXYNOS4_DT
 	  Note: This is under development and not all peripherals can be supported
 	  with this machine file.
 
+config MACH_EXYNOS5_DT
+	bool "SAMSUNG EXYNOS5 Machine using device tree"
+	select SOC_EXYNOS5250
+	select USE_OF
+	select ARM_AMBA
+	help
+	  Machine support for Samsung Exynos4 machine with device tree enabled.
+	  Select this if a fdt blob is available for the EXYNOS4 SoC based board.
+
 if ARCH_EXYNOS4
 
 comment "Configuration for HSMMC 8-bit bus width"
diff --git a/arch/arm/mach-exynos/Makefile b/arch/arm/mach-exynos/Makefile
index 9a4c09896509..8631840d1b5e 100644
--- a/arch/arm/mach-exynos/Makefile
+++ b/arch/arm/mach-exynos/Makefile
@@ -14,6 +14,7 @@ obj-				:=
 
 obj-$(CONFIG_ARCH_EXYNOS)	+= common.o
 obj-$(CONFIG_ARCH_EXYNOS4)	+= clock-exynos4.o
+obj-$(CONFIG_ARCH_EXYNOS5)	+= clock-exynos5.o
 obj-$(CONFIG_CPU_EXYNOS4210)	+= clock-exynos4210.o
 obj-$(CONFIG_SOC_EXYNOS4212)	+= clock-exynos4212.o
 
@@ -42,9 +43,11 @@ obj-$(CONFIG_MACH_SMDK4212)		+= mach-smdk4x12.o
 obj-$(CONFIG_MACH_SMDK4412)		+= mach-smdk4x12.o
 
 obj-$(CONFIG_MACH_EXYNOS4_DT)		+= mach-exynos4-dt.o
+obj-$(CONFIG_MACH_EXYNOS5_DT)		+= mach-exynos5-dt.o
 
 # device support
 
+obj-y					+= dev-uart.o
 obj-$(CONFIG_ARCH_EXYNOS4)		+= dev-audio.o
 obj-$(CONFIG_EXYNOS4_DEV_AHCI)		+= dev-ahci.o
 obj-$(CONFIG_EXYNOS4_DEV_SYSMMU)	+= dev-sysmmu.o
@@ -52,7 +55,7 @@ obj-$(CONFIG_EXYNOS4_DEV_DWMCI)		+= dev-dwmci.o
 obj-$(CONFIG_EXYNOS4_DEV_DMA)		+= dma.o
 obj-$(CONFIG_EXYNOS4_DEV_USB_OHCI)	+= dev-ohci.o
 
-obj-$(CONFIG_ARCH_EXYNOS4)		+= setup-i2c0.o
+obj-$(CONFIG_ARCH_EXYNOS)		+= setup-i2c0.o
 obj-$(CONFIG_EXYNOS4_SETUP_FIMC)	+= setup-fimc.o
 obj-$(CONFIG_EXYNOS4_SETUP_FIMD0)	+= setup-fimd0.o
 obj-$(CONFIG_EXYNOS4_SETUP_I2C1)	+= setup-i2c1.o
diff --git a/arch/arm/mach-exynos/clock-exynos4.c b/arch/arm/mach-exynos/clock-exynos4.c
index 200159dcb341..df54c2a92225 100644
--- a/arch/arm/mach-exynos/clock-exynos4.c
+++ b/arch/arm/mach-exynos/clock-exynos4.c
@@ -496,11 +496,6 @@ static struct clk exynos4_init_clocks_off[] = {
 		.enable		= exynos4_clk_ip_cam_ctrl,
 		.ctrlbit	= (1 << 3),
 	}, {
-		.name		= "fimd",
-		.devname	= "exynos4-fb.0",
-		.enable		= exynos4_clk_ip_lcd0_ctrl,
-		.ctrlbit	= (1 << 0),
-	}, {
 		.name		= "hsmmc",
 		.devname	= "s3c-sdhci.0",
 		.parent		= &exynos4_clk_aclk_133.clk,
@@ -796,6 +791,13 @@ static struct clk exynos4_clk_mdma1 = {
 	.ctrlbit	= ((1 << 8) | (1 << 5) | (1 << 2)),
 };
 
+static struct clk exynos4_clk_fimd0 = {
+	.name		= "fimd",
+	.devname	= "exynos4-fb.0",
+	.enable		= exynos4_clk_ip_lcd0_ctrl,
+	.ctrlbit	= (1 << 0),
+};
+
 struct clk *exynos4_clkset_group_list[] = {
 	[0] = &clk_ext_xtal_mux,
 	[1] = &clk_xusbxti,
@@ -1315,6 +1317,7 @@ static struct clk *exynos4_clk_cdev[] = {
 	&exynos4_clk_pdma0,
 	&exynos4_clk_pdma1,
 	&exynos4_clk_mdma1,
+	&exynos4_clk_fimd0,
 };
 
 static struct clksrc_clk *exynos4_clksrc_cdev[] = {
@@ -1341,6 +1344,7 @@ static struct clk_lookup exynos4_clk_lookup[] = {
 	CLKDEV_INIT("s3c-sdhci.1", "mmc_busclk.2", &exynos4_clk_sclk_mmc1.clk),
 	CLKDEV_INIT("s3c-sdhci.2", "mmc_busclk.2", &exynos4_clk_sclk_mmc2.clk),
 	CLKDEV_INIT("s3c-sdhci.3", "mmc_busclk.2", &exynos4_clk_sclk_mmc3.clk),
+	CLKDEV_INIT("exynos4-fb.0", "lcd", &exynos4_clk_fimd0),
 	CLKDEV_INIT("dma-pl330.0", "apb_pclk", &exynos4_clk_pdma0),
 	CLKDEV_INIT("dma-pl330.1", "apb_pclk", &exynos4_clk_pdma1),
 	CLKDEV_INIT("dma-pl330.2", "apb_pclk", &exynos4_clk_mdma1),
diff --git a/arch/arm/mach-exynos/clock-exynos5.c b/arch/arm/mach-exynos/clock-exynos5.c
new file mode 100644
index 000000000000..d013982d0f8e
--- /dev/null
+++ b/arch/arm/mach-exynos/clock-exynos5.c
@@ -0,0 +1,1247 @@
+/*
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Clock support for EXYNOS5 SoCs
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/syscore_ops.h>
+
+#include <plat/cpu-freq.h>
+#include <plat/clock.h>
+#include <plat/cpu.h>
+#include <plat/pll.h>
+#include <plat/s5p-clock.h>
+#include <plat/clock-clksrc.h>
+#include <plat/pm.h>
+
+#include <mach/map.h>
+#include <mach/regs-clock.h>
+#include <mach/sysmmu.h>
+
+#include "common.h"
+
+#ifdef CONFIG_PM_SLEEP
+static struct sleep_save exynos5_clock_save[] = {
+	/* will be implemented */
+};
+#endif
+
+static struct clk exynos5_clk_sclk_dptxphy = {
+	.name		= "sclk_dptx",
+};
+
+static struct clk exynos5_clk_sclk_hdmi24m = {
+	.name		= "sclk_hdmi24m",
+	.rate		= 24000000,
+};
+
+static struct clk exynos5_clk_sclk_hdmi27m = {
+	.name		= "sclk_hdmi27m",
+	.rate		= 27000000,
+};
+
+static struct clk exynos5_clk_sclk_hdmiphy = {
+	.name		= "sclk_hdmiphy",
+};
+
+static struct clk exynos5_clk_sclk_usbphy = {
+	.name		= "sclk_usbphy",
+	.rate		= 48000000,
+};
+
+static int exynos5_clksrc_mask_top_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKSRC_MASK_TOP, clk, enable);
+}
+
+static int exynos5_clksrc_mask_disp1_0_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKSRC_MASK_DISP1_0, clk, enable);
+}
+
+static int exynos5_clksrc_mask_fsys_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKSRC_MASK_FSYS, clk, enable);
+}
+
+static int exynos5_clksrc_mask_gscl_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKSRC_MASK_GSCL, clk, enable);
+}
+
+static int exynos5_clksrc_mask_peric0_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKSRC_MASK_PERIC0, clk, enable);
+}
+
+static int exynos5_clk_ip_core_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_IP_CORE, clk, enable);
+}
+
+static int exynos5_clk_ip_disp1_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_IP_DISP1, clk, enable);
+}
+
+static int exynos5_clk_ip_fsys_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_IP_FSYS, clk, enable);
+}
+
+static int exynos5_clk_block_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_BLOCK, clk, enable);
+}
+
+static int exynos5_clk_ip_gen_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_IP_GEN, clk, enable);
+}
+
+static int exynos5_clk_ip_gps_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_IP_GPS, clk, enable);
+}
+
+static int exynos5_clk_ip_mfc_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_IP_MFC, clk, enable);
+}
+
+static int exynos5_clk_ip_peric_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_IP_PERIC, clk, enable);
+}
+
+static int exynos5_clk_ip_peris_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(EXYNOS5_CLKGATE_IP_PERIS, clk, enable);
+}
+
+/* Core list of CMU_CPU side */
+
+static struct clksrc_clk exynos5_clk_mout_apll = {
+	.clk	= {
+		.name		= "mout_apll",
+	},
+	.sources = &clk_src_apll,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_CPU, .shift = 0, .size = 1 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_apll = {
+	.clk	= {
+		.name		= "sclk_apll",
+		.parent		= &exynos5_clk_mout_apll.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_CPU0, .shift = 24, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_mout_bpll = {
+	.clk	= {
+		.name		= "mout_bpll",
+	},
+	.sources = &clk_src_bpll,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_CDREX, .shift = 0, .size = 1 },
+};
+
+static struct clk *exynos5_clk_src_bpll_user_list[] = {
+	[0] = &clk_fin_mpll,
+	[1] = &exynos5_clk_mout_bpll.clk,
+};
+
+static struct clksrc_sources exynos5_clk_src_bpll_user = {
+	.sources	= exynos5_clk_src_bpll_user_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clk_src_bpll_user_list),
+};
+
+static struct clksrc_clk exynos5_clk_mout_bpll_user = {
+	.clk	= {
+		.name		= "mout_bpll_user",
+	},
+	.sources = &exynos5_clk_src_bpll_user,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP2, .shift = 24, .size = 1 },
+};
+
+static struct clksrc_clk exynos5_clk_mout_cpll = {
+	.clk	= {
+		.name		= "mout_cpll",
+	},
+	.sources = &clk_src_cpll,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP2, .shift = 8, .size = 1 },
+};
+
+static struct clksrc_clk exynos5_clk_mout_epll = {
+	.clk	= {
+		.name		= "mout_epll",
+	},
+	.sources = &clk_src_epll,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP2, .shift = 12, .size = 1 },
+};
+
+struct clksrc_clk exynos5_clk_mout_mpll = {
+	.clk = {
+		.name		= "mout_mpll",
+	},
+	.sources = &clk_src_mpll,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_CORE1, .shift = 8, .size = 1 },
+};
+
+static struct clk *exynos_clkset_vpllsrc_list[] = {
+	[0] = &clk_fin_vpll,
+	[1] = &exynos5_clk_sclk_hdmi27m,
+};
+
+static struct clksrc_sources exynos5_clkset_vpllsrc = {
+	.sources	= exynos_clkset_vpllsrc_list,
+	.nr_sources	= ARRAY_SIZE(exynos_clkset_vpllsrc_list),
+};
+
+static struct clksrc_clk exynos5_clk_vpllsrc = {
+	.clk	= {
+		.name		= "vpll_src",
+		.enable		= exynos5_clksrc_mask_top_ctrl,
+		.ctrlbit	= (1 << 0),
+	},
+	.sources = &exynos5_clkset_vpllsrc,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP2, .shift = 0, .size = 1 },
+};
+
+static struct clk *exynos5_clkset_sclk_vpll_list[] = {
+	[0] = &exynos5_clk_vpllsrc.clk,
+	[1] = &clk_fout_vpll,
+};
+
+static struct clksrc_sources exynos5_clkset_sclk_vpll = {
+	.sources	= exynos5_clkset_sclk_vpll_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clkset_sclk_vpll_list),
+};
+
+static struct clksrc_clk exynos5_clk_sclk_vpll = {
+	.clk	= {
+		.name		= "sclk_vpll",
+	},
+	.sources = &exynos5_clkset_sclk_vpll,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP2, .shift = 16, .size = 1 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_pixel = {
+	.clk	= {
+		.name		= "sclk_pixel",
+		.parent		= &exynos5_clk_sclk_vpll.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_DISP1_0, .shift = 28, .size = 4 },
+};
+
+static struct clk *exynos5_clkset_sclk_hdmi_list[] = {
+	[0] = &exynos5_clk_sclk_pixel.clk,
+	[1] = &exynos5_clk_sclk_hdmiphy,
+};
+
+static struct clksrc_sources exynos5_clkset_sclk_hdmi = {
+	.sources	= exynos5_clkset_sclk_hdmi_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clkset_sclk_hdmi_list),
+};
+
+static struct clksrc_clk exynos5_clk_sclk_hdmi = {
+	.clk	= {
+		.name		= "sclk_hdmi",
+		.enable		= exynos5_clksrc_mask_disp1_0_ctrl,
+		.ctrlbit	= (1 << 20),
+	},
+	.sources = &exynos5_clkset_sclk_hdmi,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_DISP1_0, .shift = 20, .size = 1 },
+};
+
+static struct clksrc_clk *exynos5_sclk_tv[] = {
+	&exynos5_clk_sclk_pixel,
+	&exynos5_clk_sclk_hdmi,
+};
+
+static struct clk *exynos5_clk_src_mpll_user_list[] = {
+	[0] = &clk_fin_mpll,
+	[1] = &exynos5_clk_mout_mpll.clk,
+};
+
+static struct clksrc_sources exynos5_clk_src_mpll_user = {
+	.sources	= exynos5_clk_src_mpll_user_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clk_src_mpll_user_list),
+};
+
+static struct clksrc_clk exynos5_clk_mout_mpll_user = {
+	.clk	= {
+		.name		= "mout_mpll_user",
+	},
+	.sources = &exynos5_clk_src_mpll_user,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP2, .shift = 20, .size = 1 },
+};
+
+static struct clk *exynos5_clkset_mout_cpu_list[] = {
+	[0] = &exynos5_clk_mout_apll.clk,
+	[1] = &exynos5_clk_mout_mpll.clk,
+};
+
+static struct clksrc_sources exynos5_clkset_mout_cpu = {
+	.sources	= exynos5_clkset_mout_cpu_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clkset_mout_cpu_list),
+};
+
+static struct clksrc_clk exynos5_clk_mout_cpu = {
+	.clk	= {
+		.name		= "mout_cpu",
+	},
+	.sources = &exynos5_clkset_mout_cpu,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_CPU, .shift = 16, .size = 1 },
+};
+
+static struct clksrc_clk exynos5_clk_dout_armclk = {
+	.clk	= {
+		.name		= "dout_armclk",
+		.parent		= &exynos5_clk_mout_cpu.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_CPU0, .shift = 0, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_dout_arm2clk = {
+	.clk	= {
+		.name		= "dout_arm2clk",
+		.parent		= &exynos5_clk_dout_armclk.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_CPU0, .shift = 28, .size = 3 },
+};
+
+static struct clk exynos5_clk_armclk = {
+	.name		= "armclk",
+	.parent		= &exynos5_clk_dout_arm2clk.clk,
+};
+
+/* Core list of CMU_CDREX side */
+
+static struct clk *exynos5_clkset_cdrex_list[] = {
+	[0] = &exynos5_clk_mout_mpll.clk,
+	[1] = &exynos5_clk_mout_bpll.clk,
+};
+
+static struct clksrc_sources exynos5_clkset_cdrex = {
+	.sources	= exynos5_clkset_cdrex_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clkset_cdrex_list),
+};
+
+static struct clksrc_clk exynos5_clk_cdrex = {
+	.clk	= {
+		.name		= "clk_cdrex",
+	},
+	.sources = &exynos5_clkset_cdrex,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_CDREX, .shift = 4, .size = 1 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_CDREX, .shift = 16, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_aclk_acp = {
+	.clk	= {
+		.name		= "aclk_acp",
+		.parent		= &exynos5_clk_mout_mpll.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_ACP, .shift = 0, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_pclk_acp = {
+	.clk	= {
+		.name		= "pclk_acp",
+		.parent		= &exynos5_clk_aclk_acp.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_ACP, .shift = 4, .size = 3 },
+};
+
+/* Core list of CMU_TOP side */
+
+struct clk *exynos5_clkset_aclk_top_list[] = {
+	[0] = &exynos5_clk_mout_mpll_user.clk,
+	[1] = &exynos5_clk_mout_bpll_user.clk,
+};
+
+struct clksrc_sources exynos5_clkset_aclk = {
+	.sources	= exynos5_clkset_aclk_top_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clkset_aclk_top_list),
+};
+
+static struct clksrc_clk exynos5_clk_aclk_400 = {
+	.clk	= {
+		.name		= "aclk_400",
+	},
+	.sources = &exynos5_clkset_aclk,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP0, .shift = 20, .size = 1 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_TOP0, .shift = 24, .size = 3 },
+};
+
+struct clk *exynos5_clkset_aclk_333_166_list[] = {
+	[0] = &exynos5_clk_mout_cpll.clk,
+	[1] = &exynos5_clk_mout_mpll_user.clk,
+};
+
+struct clksrc_sources exynos5_clkset_aclk_333_166 = {
+	.sources	= exynos5_clkset_aclk_333_166_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clkset_aclk_333_166_list),
+};
+
+static struct clksrc_clk exynos5_clk_aclk_333 = {
+	.clk	= {
+		.name		= "aclk_333",
+	},
+	.sources = &exynos5_clkset_aclk_333_166,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP0, .shift = 16, .size = 1 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_TOP0, .shift = 20, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_aclk_166 = {
+	.clk	= {
+		.name		= "aclk_166",
+	},
+	.sources = &exynos5_clkset_aclk_333_166,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP0, .shift = 8, .size = 1 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_TOP0, .shift = 8, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_aclk_266 = {
+	.clk	= {
+		.name		= "aclk_266",
+		.parent		= &exynos5_clk_mout_mpll_user.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_TOP0, .shift = 16, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_aclk_200 = {
+	.clk	= {
+		.name		= "aclk_200",
+	},
+	.sources = &exynos5_clkset_aclk,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_TOP0, .shift = 12, .size = 1 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_TOP0, .shift = 12, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_aclk_66_pre = {
+	.clk	= {
+		.name		= "aclk_66_pre",
+		.parent		= &exynos5_clk_mout_mpll_user.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_TOP1, .shift = 24, .size = 3 },
+};
+
+static struct clksrc_clk exynos5_clk_aclk_66 = {
+	.clk	= {
+		.name		= "aclk_66",
+		.parent		= &exynos5_clk_aclk_66_pre.clk,
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_TOP0, .shift = 0, .size = 3 },
+};
+
+static struct clk exynos5_init_clocks_off[] = {
+	{
+		.name		= "timers",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 24),
+	}, {
+		.name		= "rtc",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peris_ctrl,
+		.ctrlbit	= (1 << 20),
+	}, {
+		.name		= "hsmmc",
+		.devname	= "s3c-sdhci.0",
+		.parent		= &exynos5_clk_aclk_200.clk,
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 12),
+	}, {
+		.name		= "hsmmc",
+		.devname	= "s3c-sdhci.1",
+		.parent		= &exynos5_clk_aclk_200.clk,
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 13),
+	}, {
+		.name		= "hsmmc",
+		.devname	= "s3c-sdhci.2",
+		.parent		= &exynos5_clk_aclk_200.clk,
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 14),
+	}, {
+		.name		= "hsmmc",
+		.devname	= "s3c-sdhci.3",
+		.parent		= &exynos5_clk_aclk_200.clk,
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 15),
+	}, {
+		.name		= "dwmci",
+		.parent		= &exynos5_clk_aclk_200.clk,
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 16),
+	}, {
+		.name		= "sata",
+		.devname	= "ahci",
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 6),
+	}, {
+		.name		= "sata_phy",
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 24),
+	}, {
+		.name		= "sata_phy_i2c",
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 25),
+	}, {
+		.name		= "mfc",
+		.devname	= "s5p-mfc",
+		.enable		= exynos5_clk_ip_mfc_ctrl,
+		.ctrlbit	= (1 << 0),
+	}, {
+		.name		= "hdmi",
+		.devname	= "exynos4-hdmi",
+		.enable		= exynos5_clk_ip_disp1_ctrl,
+		.ctrlbit	= (1 << 6),
+	}, {
+		.name		= "mixer",
+		.devname	= "s5p-mixer",
+		.enable		= exynos5_clk_ip_disp1_ctrl,
+		.ctrlbit	= (1 << 5),
+	}, {
+		.name		= "jpeg",
+		.enable		= exynos5_clk_ip_gen_ctrl,
+		.ctrlbit	= (1 << 2),
+	}, {
+		.name		= "dsim0",
+		.enable		= exynos5_clk_ip_disp1_ctrl,
+		.ctrlbit	= (1 << 3),
+	}, {
+		.name		= "iis",
+		.devname	= "samsung-i2s.1",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 20),
+	}, {
+		.name		= "iis",
+		.devname	= "samsung-i2s.2",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 21),
+	}, {
+		.name		= "pcm",
+		.devname	= "samsung-pcm.1",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 22),
+	}, {
+		.name		= "pcm",
+		.devname	= "samsung-pcm.2",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 23),
+	}, {
+		.name		= "spdif",
+		.devname	= "samsung-spdif",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 26),
+	}, {
+		.name		= "ac97",
+		.devname	= "samsung-ac97",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 27),
+	}, {
+		.name		= "usbhost",
+		.enable		= exynos5_clk_ip_fsys_ctrl ,
+		.ctrlbit	= (1 << 18),
+	}, {
+		.name		= "usbotg",
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 7),
+	}, {
+		.name		= "gps",
+		.enable		= exynos5_clk_ip_gps_ctrl,
+		.ctrlbit	= ((1 << 3) | (1 << 2) | (1 << 0)),
+	}, {
+		.name		= "nfcon",
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 22),
+	}, {
+		.name		= "iop",
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= ((1 << 30) | (1 << 26) | (1 << 23)),
+	}, {
+		.name		= "core_iop",
+		.enable		= exynos5_clk_ip_core_ctrl,
+		.ctrlbit	= ((1 << 21) | (1 << 3)),
+	}, {
+		.name		= "mcu_iop",
+		.enable		= exynos5_clk_ip_fsys_ctrl,
+		.ctrlbit	= (1 << 0),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-i2c.0",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 6),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-i2c.1",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 7),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-i2c.2",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 8),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-i2c.3",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 9),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-i2c.4",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 10),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-i2c.5",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 11),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-i2c.6",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 12),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-i2c.7",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 13),
+	}, {
+		.name		= "i2c",
+		.devname	= "s3c2440-hdmiphy-i2c",
+		.parent		= &exynos5_clk_aclk_66.clk,
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 14),
+	}
+};
+
+static struct clk exynos5_init_clocks_on[] = {
+	{
+		.name		= "uart",
+		.devname	= "s5pv210-uart.0",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 0),
+	}, {
+		.name		= "uart",
+		.devname	= "s5pv210-uart.1",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 1),
+	}, {
+		.name		= "uart",
+		.devname	= "s5pv210-uart.2",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 2),
+	}, {
+		.name		= "uart",
+		.devname	= "s5pv210-uart.3",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 3),
+	}, {
+		.name		= "uart",
+		.devname	= "s5pv210-uart.4",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 4),
+	}, {
+		.name		= "uart",
+		.devname	= "s5pv210-uart.5",
+		.enable		= exynos5_clk_ip_peric_ctrl,
+		.ctrlbit	= (1 << 5),
+	}
+};
+
+static struct clk exynos5_clk_pdma0 = {
+	.name		= "dma",
+	.devname	= "dma-pl330.0",
+	.enable		= exynos5_clk_ip_fsys_ctrl,
+	.ctrlbit	= (1 << 1),
+};
+
+static struct clk exynos5_clk_pdma1 = {
+	.name		= "dma",
+	.devname	= "dma-pl330.1",
+	.enable		= exynos5_clk_ip_fsys_ctrl,
+	.ctrlbit	= (1 << 1),
+};
+
+static struct clk exynos5_clk_mdma1 = {
+	.name		= "dma",
+	.devname	= "dma-pl330.2",
+	.enable		= exynos5_clk_ip_gen_ctrl,
+	.ctrlbit	= (1 << 4),
+};
+
+struct clk *exynos5_clkset_group_list[] = {
+	[0] = &clk_ext_xtal_mux,
+	[1] = NULL,
+	[2] = &exynos5_clk_sclk_hdmi24m,
+	[3] = &exynos5_clk_sclk_dptxphy,
+	[4] = &exynos5_clk_sclk_usbphy,
+	[5] = &exynos5_clk_sclk_hdmiphy,
+	[6] = &exynos5_clk_mout_mpll_user.clk,
+	[7] = &exynos5_clk_mout_epll.clk,
+	[8] = &exynos5_clk_sclk_vpll.clk,
+	[9] = &exynos5_clk_mout_cpll.clk,
+};
+
+struct clksrc_sources exynos5_clkset_group = {
+	.sources	= exynos5_clkset_group_list,
+	.nr_sources	= ARRAY_SIZE(exynos5_clkset_group_list),
+};
+
+/* Possible clock sources for aclk_266_gscl_sub Mux */
+static struct clk *clk_src_gscl_266_list[] = {
+	[0] = &clk_ext_xtal_mux,
+	[1] = &exynos5_clk_aclk_266.clk,
+};
+
+static struct clksrc_sources clk_src_gscl_266 = {
+	.sources	= clk_src_gscl_266_list,
+	.nr_sources	= ARRAY_SIZE(clk_src_gscl_266_list),
+};
+
+static struct clksrc_clk exynos5_clk_dout_mmc0 = {
+	.clk		= {
+		.name		= "dout_mmc0",
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_FSYS, .shift = 0, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS1, .shift = 0, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_dout_mmc1 = {
+	.clk		= {
+		.name		= "dout_mmc1",
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_FSYS, .shift = 4, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS1, .shift = 16, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_dout_mmc2 = {
+	.clk		= {
+		.name		= "dout_mmc2",
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_FSYS, .shift = 8, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS2, .shift = 0, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_dout_mmc3 = {
+	.clk		= {
+		.name		= "dout_mmc3",
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_FSYS, .shift = 12, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS2, .shift = 16, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_dout_mmc4 = {
+	.clk		= {
+		.name		= "dout_mmc4",
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_FSYS, .shift = 16, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS3, .shift = 0, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_uart0 = {
+	.clk	= {
+		.name		= "uclk1",
+		.devname	= "exynos4210-uart.0",
+		.enable		= exynos5_clksrc_mask_peric0_ctrl,
+		.ctrlbit	= (1 << 0),
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_PERIC0, .shift = 0, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_PERIC0, .shift = 0, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_uart1 = {
+	.clk	= {
+		.name		= "uclk1",
+		.devname	= "exynos4210-uart.1",
+		.enable		= exynos5_clksrc_mask_peric0_ctrl,
+		.ctrlbit	= (1 << 4),
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_PERIC0, .shift = 4, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_PERIC0, .shift = 4, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_uart2 = {
+	.clk	= {
+		.name		= "uclk1",
+		.devname	= "exynos4210-uart.2",
+		.enable		= exynos5_clksrc_mask_peric0_ctrl,
+		.ctrlbit	= (1 << 8),
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_PERIC0, .shift = 8, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_PERIC0, .shift = 8, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_uart3 = {
+	.clk	= {
+		.name		= "uclk1",
+		.devname	= "exynos4210-uart.3",
+		.enable		= exynos5_clksrc_mask_peric0_ctrl,
+		.ctrlbit	= (1 << 12),
+	},
+	.sources = &exynos5_clkset_group,
+	.reg_src = { .reg = EXYNOS5_CLKSRC_PERIC0, .shift = 12, .size = 4 },
+	.reg_div = { .reg = EXYNOS5_CLKDIV_PERIC0, .shift = 12, .size = 4 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_mmc0 = {
+	.clk	= {
+		.name		= "sclk_mmc",
+		.devname	= "s3c-sdhci.0",
+		.parent		= &exynos5_clk_dout_mmc0.clk,
+		.enable		= exynos5_clksrc_mask_fsys_ctrl,
+		.ctrlbit	= (1 << 0),
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS1, .shift = 8, .size = 8 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_mmc1 = {
+	.clk	= {
+		.name		= "sclk_mmc",
+		.devname	= "s3c-sdhci.1",
+		.parent		= &exynos5_clk_dout_mmc1.clk,
+		.enable		= exynos5_clksrc_mask_fsys_ctrl,
+		.ctrlbit	= (1 << 4),
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS1, .shift = 24, .size = 8 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_mmc2 = {
+	.clk	= {
+		.name		= "sclk_mmc",
+		.devname	= "s3c-sdhci.2",
+		.parent		= &exynos5_clk_dout_mmc2.clk,
+		.enable		= exynos5_clksrc_mask_fsys_ctrl,
+		.ctrlbit	= (1 << 8),
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS2, .shift = 8, .size = 8 },
+};
+
+static struct clksrc_clk exynos5_clk_sclk_mmc3 = {
+	.clk	= {
+		.name		= "sclk_mmc",
+		.devname	= "s3c-sdhci.3",
+		.parent		= &exynos5_clk_dout_mmc3.clk,
+		.enable		= exynos5_clksrc_mask_fsys_ctrl,
+		.ctrlbit	= (1 << 12),
+	},
+	.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS2, .shift = 24, .size = 8 },
+};
+
+static struct clksrc_clk exynos5_clksrcs[] = {
+	{
+		.clk	= {
+			.name		= "sclk_dwmci",
+			.parent		= &exynos5_clk_dout_mmc4.clk,
+			.enable		= exynos5_clksrc_mask_fsys_ctrl,
+			.ctrlbit	= (1 << 16),
+		},
+		.reg_div = { .reg = EXYNOS5_CLKDIV_FSYS3, .shift = 8, .size = 8 },
+	}, {
+		.clk	= {
+			.name		= "sclk_fimd",
+			.devname	= "s3cfb.1",
+			.enable		= exynos5_clksrc_mask_disp1_0_ctrl,
+			.ctrlbit	= (1 << 0),
+		},
+		.sources = &exynos5_clkset_group,
+		.reg_src = { .reg = EXYNOS5_CLKSRC_DISP1_0, .shift = 0, .size = 4 },
+		.reg_div = { .reg = EXYNOS5_CLKDIV_DISP1_0, .shift = 0, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "aclk_266_gscl",
+		},
+		.sources = &clk_src_gscl_266,
+		.reg_src = { .reg = EXYNOS5_CLKSRC_TOP3, .shift = 8, .size = 1 },
+	}, {
+		.clk	= {
+			.name		= "sclk_g3d",
+			.devname	= "mali-t604.0",
+			.enable		= exynos5_clk_block_ctrl,
+			.ctrlbit	= (1 << 1),
+		},
+		.sources = &exynos5_clkset_aclk,
+		.reg_src = { .reg = EXYNOS5_CLKSRC_TOP0, .shift = 20, .size = 1 },
+		.reg_div = { .reg = EXYNOS5_CLKDIV_TOP0, .shift = 24, .size = 3 },
+	}, {
+		.clk	= {
+			.name		= "sclk_gscl_wrap",
+			.devname	= "s5p-mipi-csis.0",
+			.enable		= exynos5_clksrc_mask_gscl_ctrl,
+			.ctrlbit	= (1 << 24),
+		},
+		.sources = &exynos5_clkset_group,
+		.reg_src = { .reg = EXYNOS5_CLKSRC_GSCL, .shift = 24, .size = 4 },
+		.reg_div = { .reg = EXYNOS5_CLKDIV_GSCL, .shift = 24, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_gscl_wrap",
+			.devname	= "s5p-mipi-csis.1",
+			.enable		= exynos5_clksrc_mask_gscl_ctrl,
+			.ctrlbit	= (1 << 28),
+		},
+		.sources = &exynos5_clkset_group,
+		.reg_src = { .reg = EXYNOS5_CLKSRC_GSCL, .shift = 28, .size = 4 },
+		.reg_div = { .reg = EXYNOS5_CLKDIV_GSCL, .shift = 28, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_cam0",
+			.enable		= exynos5_clksrc_mask_gscl_ctrl,
+			.ctrlbit	= (1 << 16),
+		},
+		.sources = &exynos5_clkset_group,
+		.reg_src = { .reg = EXYNOS5_CLKSRC_GSCL, .shift = 16, .size = 4 },
+		.reg_div = { .reg = EXYNOS5_CLKDIV_GSCL, .shift = 16, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_cam1",
+			.enable		= exynos5_clksrc_mask_gscl_ctrl,
+			.ctrlbit	= (1 << 20),
+		},
+		.sources = &exynos5_clkset_group,
+		.reg_src = { .reg = EXYNOS5_CLKSRC_GSCL, .shift = 20, .size = 4 },
+		.reg_div = { .reg = EXYNOS5_CLKDIV_GSCL, .shift = 20, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_jpeg",
+			.parent		= &exynos5_clk_mout_cpll.clk,
+		},
+		.reg_div = { .reg = EXYNOS5_CLKDIV_GEN, .shift = 4, .size = 3 },
+	},
+};
+
+/* Clock initialization code */
+static struct clksrc_clk *exynos5_sysclks[] = {
+	&exynos5_clk_mout_apll,
+	&exynos5_clk_sclk_apll,
+	&exynos5_clk_mout_bpll,
+	&exynos5_clk_mout_bpll_user,
+	&exynos5_clk_mout_cpll,
+	&exynos5_clk_mout_epll,
+	&exynos5_clk_mout_mpll,
+	&exynos5_clk_mout_mpll_user,
+	&exynos5_clk_vpllsrc,
+	&exynos5_clk_sclk_vpll,
+	&exynos5_clk_mout_cpu,
+	&exynos5_clk_dout_armclk,
+	&exynos5_clk_dout_arm2clk,
+	&exynos5_clk_cdrex,
+	&exynos5_clk_aclk_400,
+	&exynos5_clk_aclk_333,
+	&exynos5_clk_aclk_266,
+	&exynos5_clk_aclk_200,
+	&exynos5_clk_aclk_166,
+	&exynos5_clk_aclk_66_pre,
+	&exynos5_clk_aclk_66,
+	&exynos5_clk_dout_mmc0,
+	&exynos5_clk_dout_mmc1,
+	&exynos5_clk_dout_mmc2,
+	&exynos5_clk_dout_mmc3,
+	&exynos5_clk_dout_mmc4,
+	&exynos5_clk_aclk_acp,
+	&exynos5_clk_pclk_acp,
+};
+
+static struct clk *exynos5_clk_cdev[] = {
+	&exynos5_clk_pdma0,
+	&exynos5_clk_pdma1,
+	&exynos5_clk_mdma1,
+};
+
+static struct clksrc_clk *exynos5_clksrc_cdev[] = {
+	&exynos5_clk_sclk_uart0,
+	&exynos5_clk_sclk_uart1,
+	&exynos5_clk_sclk_uart2,
+	&exynos5_clk_sclk_uart3,
+	&exynos5_clk_sclk_mmc0,
+	&exynos5_clk_sclk_mmc1,
+	&exynos5_clk_sclk_mmc2,
+	&exynos5_clk_sclk_mmc3,
+};
+
+static struct clk_lookup exynos5_clk_lookup[] = {
+	CLKDEV_INIT("exynos4210-uart.0", "clk_uart_baud0", &exynos5_clk_sclk_uart0.clk),
+	CLKDEV_INIT("exynos4210-uart.1", "clk_uart_baud0", &exynos5_clk_sclk_uart1.clk),
+	CLKDEV_INIT("exynos4210-uart.2", "clk_uart_baud0", &exynos5_clk_sclk_uart2.clk),
+	CLKDEV_INIT("exynos4210-uart.3", "clk_uart_baud0", &exynos5_clk_sclk_uart3.clk),
+	CLKDEV_INIT("s3c-sdhci.0", "mmc_busclk.2", &exynos5_clk_sclk_mmc0.clk),
+	CLKDEV_INIT("s3c-sdhci.1", "mmc_busclk.2", &exynos5_clk_sclk_mmc1.clk),
+	CLKDEV_INIT("s3c-sdhci.2", "mmc_busclk.2", &exynos5_clk_sclk_mmc2.clk),
+	CLKDEV_INIT("s3c-sdhci.3", "mmc_busclk.2", &exynos5_clk_sclk_mmc3.clk),
+	CLKDEV_INIT("dma-pl330.0", "apb_pclk", &exynos5_clk_pdma0),
+	CLKDEV_INIT("dma-pl330.1", "apb_pclk", &exynos5_clk_pdma1),
+	CLKDEV_INIT("dma-pl330.2", "apb_pclk", &exynos5_clk_mdma1),
+};
+
+static unsigned long exynos5_epll_get_rate(struct clk *clk)
+{
+	return clk->rate;
+}
+
+static struct clk *exynos5_clks[] __initdata = {
+	&exynos5_clk_sclk_hdmi27m,
+	&exynos5_clk_sclk_hdmiphy,
+	&clk_fout_bpll,
+	&clk_fout_cpll,
+	&exynos5_clk_armclk,
+};
+
+static u32 epll_div[][6] = {
+	{ 192000000, 0, 48, 3, 1, 0 },
+	{ 180000000, 0, 45, 3, 1, 0 },
+	{  73728000, 1, 73, 3, 3, 47710 },
+	{  67737600, 1, 90, 4, 3, 20762 },
+	{  49152000, 0, 49, 3, 3, 9961 },
+	{  45158400, 0, 45, 3, 3, 10381 },
+	{ 180633600, 0, 45, 3, 1, 10381 },
+};
+
+static int exynos5_epll_set_rate(struct clk *clk, unsigned long rate)
+{
+	unsigned int epll_con, epll_con_k;
+	unsigned int i;
+	unsigned int tmp;
+	unsigned int epll_rate;
+	unsigned int locktime;
+	unsigned int lockcnt;
+
+	/* Return if nothing changed */
+	if (clk->rate == rate)
+		return 0;
+
+	if (clk->parent)
+		epll_rate = clk_get_rate(clk->parent);
+	else
+		epll_rate = clk_ext_xtal_mux.rate;
+
+	if (epll_rate != 24000000) {
+		pr_err("Invalid Clock : recommended clock is 24MHz.\n");
+		return -EINVAL;
+	}
+
+	epll_con = __raw_readl(EXYNOS5_EPLL_CON0);
+	epll_con &= ~(0x1 << 27 | \
+			PLL46XX_MDIV_MASK << PLL46XX_MDIV_SHIFT |   \
+			PLL46XX_PDIV_MASK << PLL46XX_PDIV_SHIFT | \
+			PLL46XX_SDIV_MASK << PLL46XX_SDIV_SHIFT);
+
+	for (i = 0; i < ARRAY_SIZE(epll_div); i++) {
+		if (epll_div[i][0] == rate) {
+			epll_con_k = epll_div[i][5] << 0;
+			epll_con |= epll_div[i][1] << 27;
+			epll_con |= epll_div[i][2] << PLL46XX_MDIV_SHIFT;
+			epll_con |= epll_div[i][3] << PLL46XX_PDIV_SHIFT;
+			epll_con |= epll_div[i][4] << PLL46XX_SDIV_SHIFT;
+			break;
+		}
+	}
+
+	if (i == ARRAY_SIZE(epll_div)) {
+		printk(KERN_ERR "%s: Invalid Clock EPLL Frequency\n",
+				__func__);
+		return -EINVAL;
+	}
+
+	epll_rate /= 1000000;
+
+	/* 3000 max_cycls : specification data */
+	locktime = 3000 / epll_rate * epll_div[i][3];
+	lockcnt = locktime * 10000 / (10000 / epll_rate);
+
+	__raw_writel(lockcnt, EXYNOS5_EPLL_LOCK);
+
+	__raw_writel(epll_con, EXYNOS5_EPLL_CON0);
+	__raw_writel(epll_con_k, EXYNOS5_EPLL_CON1);
+
+	do {
+		tmp = __raw_readl(EXYNOS5_EPLL_CON0);
+	} while (!(tmp & 0x1 << EXYNOS5_EPLLCON0_LOCKED_SHIFT));
+
+	clk->rate = rate;
+
+	return 0;
+}
+
+static struct clk_ops exynos5_epll_ops = {
+	.get_rate = exynos5_epll_get_rate,
+	.set_rate = exynos5_epll_set_rate,
+};
+
+static int xtal_rate;
+
+static unsigned long exynos5_fout_apll_get_rate(struct clk *clk)
+{
+	return s5p_get_pll35xx(xtal_rate, __raw_readl(EXYNOS5_APLL_CON0));
+}
+
+static struct clk_ops exynos5_fout_apll_ops = {
+	.get_rate = exynos5_fout_apll_get_rate,
+};
+
+#ifdef CONFIG_PM
+static int exynos5_clock_suspend(void)
+{
+	s3c_pm_do_save(exynos5_clock_save, ARRAY_SIZE(exynos5_clock_save));
+
+	return 0;
+}
+
+static void exynos5_clock_resume(void)
+{
+	s3c_pm_do_restore_core(exynos5_clock_save, ARRAY_SIZE(exynos5_clock_save));
+}
+#else
+#define exynos5_clock_suspend NULL
+#define exynos5_clock_resume NULL
+#endif
+
+struct syscore_ops exynos5_clock_syscore_ops = {
+	.suspend	= exynos5_clock_suspend,
+	.resume		= exynos5_clock_resume,
+};
+
+void __init_or_cpufreq exynos5_setup_clocks(void)
+{
+	struct clk *xtal_clk;
+	unsigned long apll;
+	unsigned long bpll;
+	unsigned long cpll;
+	unsigned long mpll;
+	unsigned long epll;
+	unsigned long vpll;
+	unsigned long vpllsrc;
+	unsigned long xtal;
+	unsigned long armclk;
+	unsigned long mout_cdrex;
+	unsigned long aclk_400;
+	unsigned long aclk_333;
+	unsigned long aclk_266;
+	unsigned long aclk_200;
+	unsigned long aclk_166;
+	unsigned long aclk_66;
+	unsigned int ptr;
+
+	printk(KERN_DEBUG "%s: registering clocks\n", __func__);
+
+	xtal_clk = clk_get(NULL, "xtal");
+	BUG_ON(IS_ERR(xtal_clk));
+
+	xtal = clk_get_rate(xtal_clk);
+
+	xtal_rate = xtal;
+
+	clk_put(xtal_clk);
+
+	printk(KERN_DEBUG "%s: xtal is %ld\n", __func__, xtal);
+
+	apll = s5p_get_pll35xx(xtal, __raw_readl(EXYNOS5_APLL_CON0));
+	bpll = s5p_get_pll35xx(xtal, __raw_readl(EXYNOS5_BPLL_CON0));
+	cpll = s5p_get_pll35xx(xtal, __raw_readl(EXYNOS5_CPLL_CON0));
+	mpll = s5p_get_pll35xx(xtal, __raw_readl(EXYNOS5_MPLL_CON0));
+	epll = s5p_get_pll36xx(xtal, __raw_readl(EXYNOS5_EPLL_CON0),
+			__raw_readl(EXYNOS5_EPLL_CON1));
+
+	vpllsrc = clk_get_rate(&exynos5_clk_vpllsrc.clk);
+	vpll = s5p_get_pll36xx(vpllsrc, __raw_readl(EXYNOS5_VPLL_CON0),
+			__raw_readl(EXYNOS5_VPLL_CON1));
+
+	clk_fout_apll.ops = &exynos5_fout_apll_ops;
+	clk_fout_bpll.rate = bpll;
+	clk_fout_cpll.rate = cpll;
+	clk_fout_mpll.rate = mpll;
+	clk_fout_epll.rate = epll;
+	clk_fout_vpll.rate = vpll;
+
+	printk(KERN_INFO "EXYNOS5: PLL settings, A=%ld, B=%ld, C=%ld\n"
+			"M=%ld, E=%ld V=%ld",
+			apll, bpll, cpll, mpll, epll, vpll);
+
+	armclk = clk_get_rate(&exynos5_clk_armclk);
+	mout_cdrex = clk_get_rate(&exynos5_clk_cdrex.clk);
+
+	aclk_400 = clk_get_rate(&exynos5_clk_aclk_400.clk);
+	aclk_333 = clk_get_rate(&exynos5_clk_aclk_333.clk);
+	aclk_266 = clk_get_rate(&exynos5_clk_aclk_266.clk);
+	aclk_200 = clk_get_rate(&exynos5_clk_aclk_200.clk);
+	aclk_166 = clk_get_rate(&exynos5_clk_aclk_166.clk);
+	aclk_66 = clk_get_rate(&exynos5_clk_aclk_66.clk);
+
+	printk(KERN_INFO "EXYNOS5: ARMCLK=%ld, CDREX=%ld, ACLK400=%ld\n"
+			"ACLK333=%ld, ACLK266=%ld, ACLK200=%ld\n"
+			"ACLK166=%ld, ACLK66=%ld\n",
+			armclk, mout_cdrex, aclk_400,
+			aclk_333, aclk_266, aclk_200,
+			aclk_166, aclk_66);
+
+
+	clk_fout_epll.ops = &exynos5_epll_ops;
+
+	if (clk_set_parent(&exynos5_clk_mout_epll.clk, &clk_fout_epll))
+		printk(KERN_ERR "Unable to set parent %s of clock %s.\n",
+				clk_fout_epll.name, exynos5_clk_mout_epll.clk.name);
+
+	clk_set_rate(&exynos5_clk_sclk_apll.clk, 100000000);
+	clk_set_rate(&exynos5_clk_aclk_266.clk, 300000000);
+
+	clk_set_rate(&exynos5_clk_aclk_acp.clk, 267000000);
+	clk_set_rate(&exynos5_clk_pclk_acp.clk, 134000000);
+
+	for (ptr = 0; ptr < ARRAY_SIZE(exynos5_clksrcs); ptr++)
+		s3c_set_clksrc(&exynos5_clksrcs[ptr], true);
+}
+
+void __init exynos5_register_clocks(void)
+{
+	int ptr;
+
+	s3c24xx_register_clocks(exynos5_clks, ARRAY_SIZE(exynos5_clks));
+
+	for (ptr = 0; ptr < ARRAY_SIZE(exynos5_sysclks); ptr++)
+		s3c_register_clksrc(exynos5_sysclks[ptr], 1);
+
+	for (ptr = 0; ptr < ARRAY_SIZE(exynos5_sclk_tv); ptr++)
+		s3c_register_clksrc(exynos5_sclk_tv[ptr], 1);
+
+	for (ptr = 0; ptr < ARRAY_SIZE(exynos5_clksrc_cdev); ptr++)
+		s3c_register_clksrc(exynos5_clksrc_cdev[ptr], 1);
+
+	s3c_register_clksrc(exynos5_clksrcs, ARRAY_SIZE(exynos5_clksrcs));
+	s3c_register_clocks(exynos5_init_clocks_on, ARRAY_SIZE(exynos5_init_clocks_on));
+
+	s3c24xx_register_clocks(exynos5_clk_cdev, ARRAY_SIZE(exynos5_clk_cdev));
+	for (ptr = 0; ptr < ARRAY_SIZE(exynos5_clk_cdev); ptr++)
+		s3c_disable_clocks(exynos5_clk_cdev[ptr], 1);
+
+	s3c_register_clocks(exynos5_init_clocks_off, ARRAY_SIZE(exynos5_init_clocks_off));
+	s3c_disable_clocks(exynos5_init_clocks_off, ARRAY_SIZE(exynos5_init_clocks_off));
+	clkdev_add_table(exynos5_clk_lookup, ARRAY_SIZE(exynos5_clk_lookup));
+
+	register_syscore_ops(&exynos5_clock_syscore_ops);
+	s3c_pwmclk_init();
+}
diff --git a/arch/arm/mach-exynos/common.c b/arch/arm/mach-exynos/common.c
index 97ca2592ce83..8614aab47cc0 100644
--- a/arch/arm/mach-exynos/common.c
+++ b/arch/arm/mach-exynos/common.c
@@ -53,6 +53,14 @@
 static const char name_exynos4210[] = "EXYNOS4210";
 static const char name_exynos4212[] = "EXYNOS4212";
 static const char name_exynos4412[] = "EXYNOS4412";
+static const char name_exynos5250[] = "EXYNOS5250";
+
+static void exynos4_map_io(void);
+static void exynos5_map_io(void);
+static void exynos4_init_clocks(int xtal);
+static void exynos5_init_clocks(int xtal);
+static void exynos_init_uarts(struct s3c2410_uartcfg *cfg, int no);
+static int exynos_init(void);
 
 static struct cpu_table cpu_ids[] __initdata = {
 	{
@@ -60,7 +68,7 @@ static struct cpu_table cpu_ids[] __initdata = {
 		.idmask		= EXYNOS4_CPU_MASK,
 		.map_io		= exynos4_map_io,
 		.init_clocks	= exynos4_init_clocks,
-		.init_uarts	= exynos4_init_uarts,
+		.init_uarts	= exynos_init_uarts,
 		.init		= exynos_init,
 		.name		= name_exynos4210,
 	}, {
@@ -68,7 +76,7 @@ static struct cpu_table cpu_ids[] __initdata = {
 		.idmask		= EXYNOS4_CPU_MASK,
 		.map_io		= exynos4_map_io,
 		.init_clocks	= exynos4_init_clocks,
-		.init_uarts	= exynos4_init_uarts,
+		.init_uarts	= exynos_init_uarts,
 		.init		= exynos_init,
 		.name		= name_exynos4212,
 	}, {
@@ -76,9 +84,17 @@ static struct cpu_table cpu_ids[] __initdata = {
 		.idmask		= EXYNOS4_CPU_MASK,
 		.map_io		= exynos4_map_io,
 		.init_clocks	= exynos4_init_clocks,
-		.init_uarts	= exynos4_init_uarts,
+		.init_uarts	= exynos_init_uarts,
 		.init		= exynos_init,
 		.name		= name_exynos4412,
+	}, {
+		.idcode		= EXYNOS5250_SOC_ID,
+		.idmask		= EXYNOS5_SOC_MASK,
+		.map_io		= exynos5_map_io,
+		.init_clocks	= exynos5_init_clocks,
+		.init_uarts	= exynos_init_uarts,
+		.init		= exynos_init,
+		.name		= name_exynos5250,
 	},
 };
 
@@ -87,10 +103,14 @@ static struct cpu_table cpu_ids[] __initdata = {
 static struct map_desc exynos_iodesc[] __initdata = {
 	{
 		.virtual	= (unsigned long)S5P_VA_CHIPID,
-		.pfn		= __phys_to_pfn(EXYNOS4_PA_CHIPID),
+		.pfn		= __phys_to_pfn(EXYNOS_PA_CHIPID),
 		.length		= SZ_4K,
 		.type		= MT_DEVICE,
-	}, {
+	},
+};
+
+static struct map_desc exynos4_iodesc[] __initdata = {
+	{
 		.virtual	= (unsigned long)S3C_VA_SYS,
 		.pfn		= __phys_to_pfn(EXYNOS4_PA_SYSCON),
 		.length		= SZ_64K,
@@ -140,11 +160,7 @@ static struct map_desc exynos_iodesc[] __initdata = {
 		.pfn		= __phys_to_pfn(EXYNOS4_PA_UART),
 		.length		= SZ_512K,
 		.type		= MT_DEVICE,
-	},
-};
-
-static struct map_desc exynos4_iodesc[] __initdata = {
-	{
+	}, {
 		.virtual	= (unsigned long)S5P_VA_CMU,
 		.pfn		= __phys_to_pfn(EXYNOS4_PA_CMU),
 		.length		= SZ_128K,
@@ -160,21 +176,6 @@ static struct map_desc exynos4_iodesc[] __initdata = {
 		.length		= SZ_4K,
 		.type		= MT_DEVICE,
 	}, {
-		.virtual	= (unsigned long)S5P_VA_GPIO1,
-		.pfn		= __phys_to_pfn(EXYNOS4_PA_GPIO1),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)S5P_VA_GPIO2,
-		.pfn		= __phys_to_pfn(EXYNOS4_PA_GPIO2),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)S5P_VA_GPIO3,
-		.pfn		= __phys_to_pfn(EXYNOS4_PA_GPIO3),
-		.length		= SZ_256,
-		.type		= MT_DEVICE,
-	}, {
 		.virtual	= (unsigned long)S5P_VA_DMC0,
 		.pfn		= __phys_to_pfn(EXYNOS4_PA_DMC0),
 		.length		= SZ_64K,
@@ -210,11 +211,80 @@ static struct map_desc exynos4_iodesc1[] __initdata = {
 	},
 };
 
+static struct map_desc exynos5_iodesc[] __initdata = {
+	{
+		.virtual	= (unsigned long)S3C_VA_SYS,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_SYSCON),
+		.length		= SZ_64K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S3C_VA_TIMER,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_TIMER),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S3C_VA_WATCHDOG,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_WATCHDOG),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_SROMC,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_SROMC),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_SYSTIMER,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_SYSTIMER),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_SYSRAM,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_SYSRAM),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_CMU,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_CMU),
+		.length		= 144 * SZ_1K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_PMU,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_PMU),
+		.length		= SZ_64K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_COMBINER_BASE,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_COMBINER),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S3C_VA_UART,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_UART),
+		.length		= SZ_512K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_GIC_CPU,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_GIC_CPU),
+		.length		= SZ_64K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_GIC_DIST,
+		.pfn		= __phys_to_pfn(EXYNOS5_PA_GIC_DIST),
+		.length		= SZ_64K,
+		.type		= MT_DEVICE,
+	},
+};
+
 void exynos4_restart(char mode, const char *cmd)
 {
 	__raw_writel(0x1, S5P_SWRESET);
 }
 
+void exynos5_restart(char mode, const char *cmd)
+{
+	__raw_writel(0x1, EXYNOS_SWRESET);
+}
+
 /*
  * exynos_map_io
  *
@@ -234,7 +304,7 @@ void __init exynos_init_io(struct map_desc *mach_desc, int size)
 	s3c_init_cpu(samsung_cpu_id, cpu_ids, ARRAY_SIZE(cpu_ids));
 }
 
-void __init exynos4_map_io(void)
+static void __init exynos4_map_io(void)
 {
 	iotable_init(exynos4_iodesc, ARRAY_SIZE(exynos4_iodesc));
 
@@ -265,7 +335,22 @@ void __init exynos4_map_io(void)
 	s5p_hdmi_setname("exynos4-hdmi");
 }
 
-void __init exynos4_init_clocks(int xtal)
+static void __init exynos5_map_io(void)
+{
+	iotable_init(exynos5_iodesc, ARRAY_SIZE(exynos5_iodesc));
+
+	s3c_device_i2c0.resource[0].start = EXYNOS5_PA_IIC(0);
+	s3c_device_i2c0.resource[0].end   = EXYNOS5_PA_IIC(0) + SZ_4K - 1;
+	s3c_device_i2c0.resource[1].start = EXYNOS5_IRQ_IIC;
+	s3c_device_i2c0.resource[1].end   = EXYNOS5_IRQ_IIC;
+
+	/* The I2C bus controllers are directly compatible with s3c2440 */
+	s3c_i2c0_setname("s3c2440-i2c");
+	s3c_i2c1_setname("s3c2440-i2c");
+	s3c_i2c2_setname("s3c2440-i2c");
+}
+
+static void __init exynos4_init_clocks(int xtal)
 {
 	printk(KERN_DEBUG "%s: initializing clocks\n", __func__);
 
@@ -281,6 +366,17 @@ void __init exynos4_init_clocks(int xtal)
 	exynos4_setup_clocks();
 }
 
+static void __init exynos5_init_clocks(int xtal)
+{
+	printk(KERN_DEBUG "%s: initializing clocks\n", __func__);
+
+	s3c24xx_register_baseclocks(xtal);
+	s5p_register_clocks(xtal);
+
+	exynos5_register_clocks();
+	exynos5_setup_clocks();
+}
+
 #define COMBINER_ENABLE_SET	0x0
 #define COMBINER_ENABLE_CLEAR	0x4
 #define COMBINER_INT_STATUS	0xC
@@ -354,7 +450,14 @@ static struct irq_chip combiner_chip = {
 
 static void __init combiner_cascade_irq(unsigned int combiner_nr, unsigned int irq)
 {
-	if (combiner_nr >= MAX_COMBINER_NR)
+	unsigned int max_nr;
+
+	if (soc_is_exynos5250())
+		max_nr = EXYNOS5_MAX_COMBINER_NR;
+	else
+		max_nr = EXYNOS4_MAX_COMBINER_NR;
+
+	if (combiner_nr >= max_nr)
 		BUG();
 	if (irq_set_handler_data(irq, &combiner_data[combiner_nr]) != 0)
 		BUG();
@@ -365,8 +468,14 @@ static void __init combiner_init(unsigned int combiner_nr, void __iomem *base,
 			  unsigned int irq_start)
 {
 	unsigned int i;
+	unsigned int max_nr;
 
-	if (combiner_nr >= MAX_COMBINER_NR)
+	if (soc_is_exynos5250())
+		max_nr = EXYNOS5_MAX_COMBINER_NR;
+	else
+		max_nr = EXYNOS4_MAX_COMBINER_NR;
+
+	if (combiner_nr >= max_nr)
 		BUG();
 
 	combiner_data[combiner_nr].base = base;
@@ -409,7 +518,7 @@ void __init exynos4_init_irq(void)
 		of_irq_init(exynos4_dt_irq_match);
 #endif
 
-	for (irq = 0; irq < MAX_COMBINER_NR; irq++) {
+	for (irq = 0; irq < EXYNOS4_MAX_COMBINER_NR; irq++) {
 
 		combiner_init(irq, (void __iomem *)S5P_VA_COMBINER(irq),
 				COMBINER_IRQ(irq, 0));
@@ -424,25 +533,61 @@ void __init exynos4_init_irq(void)
 	s5p_init_irq(NULL, 0);
 }
 
+void __init exynos5_init_irq(void)
+{
+	int irq;
+
+	gic_init(0, IRQ_PPI(0), S5P_VA_GIC_DIST, S5P_VA_GIC_CPU);
+
+	for (irq = 0; irq < EXYNOS5_MAX_COMBINER_NR; irq++) {
+		combiner_init(irq, (void __iomem *)S5P_VA_COMBINER(irq),
+				COMBINER_IRQ(irq, 0));
+		combiner_cascade_irq(irq, IRQ_SPI(irq));
+	}
+
+	/*
+	 * The parameters of s5p_init_irq() are for VIC init.
+	 * Theses parameters should be NULL and 0 because EXYNOS4
+	 * uses GIC instead of VIC.
+	 */
+	s5p_init_irq(NULL, 0);
+}
+
 struct bus_type exynos4_subsys = {
 	.name		= "exynos4-core",
 	.dev_name	= "exynos4-core",
 };
 
+struct bus_type exynos5_subsys = {
+	.name		= "exynos5-core",
+	.dev_name	= "exynos5-core",
+};
+
 static struct device exynos4_dev = {
 	.bus	= &exynos4_subsys,
 };
 
-static int __init exynos4_core_init(void)
+static struct device exynos5_dev = {
+	.bus	= &exynos5_subsys,
+};
+
+static int __init exynos_core_init(void)
 {
-	return subsys_system_register(&exynos4_subsys, NULL);
+	if (soc_is_exynos5250())
+		return subsys_system_register(&exynos5_subsys, NULL);
+	else
+		return subsys_system_register(&exynos4_subsys, NULL);
 }
-core_initcall(exynos4_core_init);
+core_initcall(exynos_core_init);
 
 #ifdef CONFIG_CACHE_L2X0
 static int __init exynos4_l2x0_cache_init(void)
 {
 	int ret;
+
+	if (soc_is_exynos5250())
+		return 0;
+
 	ret = l2x0_of_init(L2_AUX_VAL, L2_AUX_MASK);
 	if (!ret) {
 		l2x0_regs_phys = virt_to_phys(&l2x0_saved_regs);
@@ -486,19 +631,47 @@ static int __init exynos4_l2x0_cache_init(void)
 	l2x0_init(S5P_VA_L2CC, L2_AUX_VAL, L2_AUX_MASK);
 	return 0;
 }
-
 early_initcall(exynos4_l2x0_cache_init);
 #endif
 
-int __init exynos_init(void)
+static int __init exynos5_l2_cache_init(void)
+{
+	unsigned int val;
+
+	if (!soc_is_exynos5250())
+		return 0;
+
+	asm volatile("mrc p15, 0, %0, c1, c0, 0\n"
+		     "bic %0, %0, #(1 << 2)\n"	/* cache disable */
+		     "mcr p15, 0, %0, c1, c0, 0\n"
+		     "mrc p15, 1, %0, c9, c0, 2\n"
+		     : "=r"(val));
+
+	val |= (1 << 9) | (1 << 5) | (2 << 6) | (2 << 0);
+
+	asm volatile("mcr p15, 1, %0, c9, c0, 2\n" : : "r"(val));
+	asm volatile("mrc p15, 0, %0, c1, c0, 0\n"
+		     "orr %0, %0, #(1 << 2)\n"	/* cache enable */
+		     "mcr p15, 0, %0, c1, c0, 0\n"
+		     : : "r"(val));
+
+	return 0;
+}
+early_initcall(exynos5_l2_cache_init);
+
+static int __init exynos_init(void)
 {
 	printk(KERN_INFO "EXYNOS: Initializing architecture\n");
-	return device_register(&exynos4_dev);
+
+	if (soc_is_exynos5250())
+		return device_register(&exynos5_dev);
+	else
+		return device_register(&exynos4_dev);
 }
 
 /* uart registration process */
 
-void __init exynos4_init_uarts(struct s3c2410_uartcfg *cfg, int no)
+static void __init exynos_init_uarts(struct s3c2410_uartcfg *cfg, int no)
 {
 	struct s3c2410_uartcfg *tcfg = cfg;
 	u32 ucnt;
@@ -506,69 +679,138 @@ void __init exynos4_init_uarts(struct s3c2410_uartcfg *cfg, int no)
 	for (ucnt = 0; ucnt < no; ucnt++, tcfg++)
 		tcfg->has_fracval = 1;
 
-	s3c24xx_init_uartdevs("exynos4210-uart", s5p_uart_resources, cfg, no);
+	if (soc_is_exynos5250())
+		s3c24xx_init_uartdevs("exynos4210-uart", exynos5_uart_resources, cfg, no);
+	else
+		s3c24xx_init_uartdevs("exynos4210-uart", exynos4_uart_resources, cfg, no);
 }
 
+static void __iomem *exynos_eint_base;
+
 static DEFINE_SPINLOCK(eint_lock);
 
 static unsigned int eint0_15_data[16];
 
-static unsigned int exynos4_get_irq_nr(unsigned int number)
+static inline int exynos4_irq_to_gpio(unsigned int irq)
 {
-	u32 ret = 0;
+	if (irq < IRQ_EINT(0))
+		return -EINVAL;
 
-	switch (number) {
-	case 0 ... 3:
-		ret = (number + IRQ_EINT0);
-		break;
-	case 4 ... 7:
-		ret = (number + (IRQ_EINT4 - 4));
-		break;
-	case 8 ... 15:
-		ret = (number + (IRQ_EINT8 - 8));
-		break;
-	default:
-		printk(KERN_ERR "number available : %d\n", number);
-	}
+	irq -= IRQ_EINT(0);
+	if (irq < 8)
+		return EXYNOS4_GPX0(irq);
+
+	irq -= 8;
+	if (irq < 8)
+		return EXYNOS4_GPX1(irq);
+
+	irq -= 8;
+	if (irq < 8)
+		return EXYNOS4_GPX2(irq);
+
+	irq -= 8;
+	if (irq < 8)
+		return EXYNOS4_GPX3(irq);
+
+	return -EINVAL;
+}
 
-	return ret;
+static inline int exynos5_irq_to_gpio(unsigned int irq)
+{
+	if (irq < IRQ_EINT(0))
+		return -EINVAL;
+
+	irq -= IRQ_EINT(0);
+	if (irq < 8)
+		return EXYNOS5_GPX0(irq);
+
+	irq -= 8;
+	if (irq < 8)
+		return EXYNOS5_GPX1(irq);
+
+	irq -= 8;
+	if (irq < 8)
+		return EXYNOS5_GPX2(irq);
+
+	irq -= 8;
+	if (irq < 8)
+		return EXYNOS5_GPX3(irq);
+
+	return -EINVAL;
 }
 
-static inline void exynos4_irq_eint_mask(struct irq_data *data)
+static unsigned int exynos4_eint0_15_src_int[16] = {
+	EXYNOS4_IRQ_EINT0,
+	EXYNOS4_IRQ_EINT1,
+	EXYNOS4_IRQ_EINT2,
+	EXYNOS4_IRQ_EINT3,
+	EXYNOS4_IRQ_EINT4,
+	EXYNOS4_IRQ_EINT5,
+	EXYNOS4_IRQ_EINT6,
+	EXYNOS4_IRQ_EINT7,
+	EXYNOS4_IRQ_EINT8,
+	EXYNOS4_IRQ_EINT9,
+	EXYNOS4_IRQ_EINT10,
+	EXYNOS4_IRQ_EINT11,
+	EXYNOS4_IRQ_EINT12,
+	EXYNOS4_IRQ_EINT13,
+	EXYNOS4_IRQ_EINT14,
+	EXYNOS4_IRQ_EINT15,
+};
+
+static unsigned int exynos5_eint0_15_src_int[16] = {
+	EXYNOS5_IRQ_EINT0,
+	EXYNOS5_IRQ_EINT1,
+	EXYNOS5_IRQ_EINT2,
+	EXYNOS5_IRQ_EINT3,
+	EXYNOS5_IRQ_EINT4,
+	EXYNOS5_IRQ_EINT5,
+	EXYNOS5_IRQ_EINT6,
+	EXYNOS5_IRQ_EINT7,
+	EXYNOS5_IRQ_EINT8,
+	EXYNOS5_IRQ_EINT9,
+	EXYNOS5_IRQ_EINT10,
+	EXYNOS5_IRQ_EINT11,
+	EXYNOS5_IRQ_EINT12,
+	EXYNOS5_IRQ_EINT13,
+	EXYNOS5_IRQ_EINT14,
+	EXYNOS5_IRQ_EINT15,
+};
+static inline void exynos_irq_eint_mask(struct irq_data *data)
 {
 	u32 mask;
 
 	spin_lock(&eint_lock);
-	mask = __raw_readl(S5P_EINT_MASK(EINT_REG_NR(data->irq)));
-	mask |= eint_irq_to_bit(data->irq);
-	__raw_writel(mask, S5P_EINT_MASK(EINT_REG_NR(data->irq)));
+	mask = __raw_readl(EINT_MASK(exynos_eint_base, data->irq));
+	mask |= EINT_OFFSET_BIT(data->irq);
+	__raw_writel(mask, EINT_MASK(exynos_eint_base, data->irq));
 	spin_unlock(&eint_lock);
 }
 
-static void exynos4_irq_eint_unmask(struct irq_data *data)
+static void exynos_irq_eint_unmask(struct irq_data *data)
 {
 	u32 mask;
 
 	spin_lock(&eint_lock);
-	mask = __raw_readl(S5P_EINT_MASK(EINT_REG_NR(data->irq)));
-	mask &= ~(eint_irq_to_bit(data->irq));
-	__raw_writel(mask, S5P_EINT_MASK(EINT_REG_NR(data->irq)));
+	mask = __raw_readl(EINT_MASK(exynos_eint_base, data->irq));
+	mask &= ~(EINT_OFFSET_BIT(data->irq));
+	__raw_writel(mask, EINT_MASK(exynos_eint_base, data->irq));
 	spin_unlock(&eint_lock);
 }
 
-static inline void exynos4_irq_eint_ack(struct irq_data *data)
+static inline void exynos_irq_eint_ack(struct irq_data *data)
 {
-	__raw_writel(eint_irq_to_bit(data->irq),
-		     S5P_EINT_PEND(EINT_REG_NR(data->irq)));
+	__raw_writel(EINT_OFFSET_BIT(data->irq),
+		     EINT_PEND(exynos_eint_base, data->irq));
 }
 
-static void exynos4_irq_eint_maskack(struct irq_data *data)
+static void exynos_irq_eint_maskack(struct irq_data *data)
 {
-	exynos4_irq_eint_mask(data);
-	exynos4_irq_eint_ack(data);
+	exynos_irq_eint_mask(data);
+	exynos_irq_eint_ack(data);
 }
 
-static int exynos4_irq_eint_set_type(struct irq_data *data, unsigned int type)
+static int exynos_irq_eint_set_type(struct irq_data *data, unsigned int type)
 {
 	int offs = EINT_OFFSET(data->irq);
 	int shift;
@@ -605,39 +847,27 @@ static int exynos4_irq_eint_set_type(struct irq_data *data, unsigned int type)
 	mask = 0x7 << shift;
 
 	spin_lock(&eint_lock);
-	ctrl = __raw_readl(S5P_EINT_CON(EINT_REG_NR(data->irq)));
+	ctrl = __raw_readl(EINT_CON(exynos_eint_base, data->irq));
 	ctrl &= ~mask;
 	ctrl |= newvalue << shift;
-	__raw_writel(ctrl, S5P_EINT_CON(EINT_REG_NR(data->irq)));
+	__raw_writel(ctrl, EINT_CON(exynos_eint_base, data->irq));
 	spin_unlock(&eint_lock);
 
-	switch (offs) {
-	case 0 ... 7:
-		s3c_gpio_cfgpin(EINT_GPIO_0(offs & 0x7), EINT_MODE);
-		break;
-	case 8 ... 15:
-		s3c_gpio_cfgpin(EINT_GPIO_1(offs & 0x7), EINT_MODE);
-		break;
-	case 16 ... 23:
-		s3c_gpio_cfgpin(EINT_GPIO_2(offs & 0x7), EINT_MODE);
-		break;
-	case 24 ... 31:
-		s3c_gpio_cfgpin(EINT_GPIO_3(offs & 0x7), EINT_MODE);
-		break;
-	default:
-		printk(KERN_ERR "No such irq number %d", offs);
-	}
+	if (soc_is_exynos5250())
+		s3c_gpio_cfgpin(exynos5_irq_to_gpio(data->irq), S3C_GPIO_SFN(0xf));
+	else
+		s3c_gpio_cfgpin(exynos4_irq_to_gpio(data->irq), S3C_GPIO_SFN(0xf));
 
 	return 0;
 }
 
-static struct irq_chip exynos4_irq_eint = {
-	.name		= "exynos4-eint",
-	.irq_mask	= exynos4_irq_eint_mask,
-	.irq_unmask	= exynos4_irq_eint_unmask,
-	.irq_mask_ack	= exynos4_irq_eint_maskack,
-	.irq_ack	= exynos4_irq_eint_ack,
-	.irq_set_type	= exynos4_irq_eint_set_type,
+static struct irq_chip exynos_irq_eint = {
+	.name		= "exynos-eint",
+	.irq_mask	= exynos_irq_eint_mask,
+	.irq_unmask	= exynos_irq_eint_unmask,
+	.irq_mask_ack	= exynos_irq_eint_maskack,
+	.irq_ack	= exynos_irq_eint_ack,
+	.irq_set_type	= exynos_irq_eint_set_type,
 #ifdef CONFIG_PM
 	.irq_set_wake	= s3c_irqext_wake,
 #endif
@@ -652,12 +882,12 @@ static struct irq_chip exynos4_irq_eint = {
  *
  * Each EINT pend/mask registers handle eight of them.
  */
-static inline void exynos4_irq_demux_eint(unsigned int start)
+static inline void exynos_irq_demux_eint(unsigned int start)
 {
 	unsigned int irq;
 
-	u32 status = __raw_readl(S5P_EINT_PEND(EINT_REG_NR(start)));
-	u32 mask = __raw_readl(S5P_EINT_MASK(EINT_REG_NR(start)));
+	u32 status = __raw_readl(EINT_PEND(exynos_eint_base, start));
+	u32 mask = __raw_readl(EINT_MASK(exynos_eint_base, start));
 
 	status &= ~mask;
 	status &= 0xff;
@@ -669,16 +899,16 @@ static inline void exynos4_irq_demux_eint(unsigned int start)
 	}
 }
 
-static void exynos4_irq_demux_eint16_31(unsigned int irq, struct irq_desc *desc)
+static void exynos_irq_demux_eint16_31(unsigned int irq, struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_get_chip(irq);
 	chained_irq_enter(chip, desc);
-	exynos4_irq_demux_eint(IRQ_EINT(16));
-	exynos4_irq_demux_eint(IRQ_EINT(24));
+	exynos_irq_demux_eint(IRQ_EINT(16));
+	exynos_irq_demux_eint(IRQ_EINT(24));
 	chained_irq_exit(chip, desc);
 }
 
-static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc)
+static void exynos_irq_eint0_15(unsigned int irq, struct irq_desc *desc)
 {
 	u32 *irq_data = irq_get_handler_data(irq);
 	struct irq_chip *chip = irq_get_chip(irq);
@@ -695,27 +925,44 @@ static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc)
 	chained_irq_exit(chip, desc);
 }
 
-static int __init exynos4_init_irq_eint(void)
+static int __init exynos_init_irq_eint(void)
 {
 	int irq;
 
+	if (soc_is_exynos5250())
+		exynos_eint_base = ioremap(EXYNOS5_PA_GPIO1, SZ_4K);
+	else
+		exynos_eint_base = ioremap(EXYNOS4_PA_GPIO2, SZ_4K);
+
+	if (exynos_eint_base == NULL) {
+		pr_err("unable to ioremap for EINT base address\n");
+		return -ENOMEM;
+	}
+
 	for (irq = 0 ; irq <= 31 ; irq++) {
-		irq_set_chip_and_handler(IRQ_EINT(irq), &exynos4_irq_eint,
+		irq_set_chip_and_handler(IRQ_EINT(irq), &exynos_irq_eint,
 					 handle_level_irq);
 		set_irq_flags(IRQ_EINT(irq), IRQF_VALID);
 	}
 
-	irq_set_chained_handler(IRQ_EINT16_31, exynos4_irq_demux_eint16_31);
+	irq_set_chained_handler(EXYNOS_IRQ_EINT16_31, exynos_irq_demux_eint16_31);
 
 	for (irq = 0 ; irq <= 15 ; irq++) {
 		eint0_15_data[irq] = IRQ_EINT(irq);
 
-		irq_set_handler_data(exynos4_get_irq_nr(irq),
-				     &eint0_15_data[irq]);
-		irq_set_chained_handler(exynos4_get_irq_nr(irq),
-					exynos4_irq_eint0_15);
+		if (soc_is_exynos5250()) {
+			irq_set_handler_data(exynos5_eint0_15_src_int[irq],
+					     &eint0_15_data[irq]);
+			irq_set_chained_handler(exynos5_eint0_15_src_int[irq],
+						exynos_irq_eint0_15);
+		} else {
+			irq_set_handler_data(exynos4_eint0_15_src_int[irq],
+					     &eint0_15_data[irq]);
+			irq_set_chained_handler(exynos4_eint0_15_src_int[irq],
+						exynos_irq_eint0_15);
+		}
 	}
 
 	return 0;
 }
-arch_initcall(exynos4_init_irq_eint);
+arch_initcall(exynos_init_irq_eint);
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index 8c1efe692c20..677b5467df18 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -12,39 +12,44 @@
 #ifndef __ARCH_ARM_MACH_EXYNOS_COMMON_H
 #define __ARCH_ARM_MACH_EXYNOS_COMMON_H
 
+extern struct sys_timer exynos4_timer;
+
 void exynos_init_io(struct map_desc *mach_desc, int size);
 void exynos4_init_irq(void);
+void exynos5_init_irq(void);
+void exynos4_restart(char mode, const char *cmd);
+void exynos5_restart(char mode, const char *cmd);
 
 #ifdef CONFIG_ARCH_EXYNOS4
 void exynos4_register_clocks(void);
 void exynos4_setup_clocks(void);
 
-void exynos4210_register_clocks(void);
-void exynos4212_register_clocks(void);
-
 #else
 #define exynos4_register_clocks()
 #define exynos4_setup_clocks()
+#endif
 
-#define exynos4210_register_clocks()
-#define exynos4212_register_clocks()
+#ifdef CONFIG_ARCH_EXYNOS5
+void exynos5_register_clocks(void);
+void exynos5_setup_clocks(void);
+
+#else
+#define exynos5_register_clocks()
+#define exynos5_setup_clocks()
 #endif
 
-void exynos4_restart(char mode, const char *cmd);
+#ifdef CONFIG_CPU_EXYNOS4210
+void exynos4210_register_clocks(void);
 
-extern struct sys_timer exynos4_timer;
+#else
+#define exynos4210_register_clocks()
+#endif
 
-#ifdef CONFIG_ARCH_EXYNOS
-extern  int exynos_init(void);
-extern void exynos4_map_io(void);
-extern void exynos4_init_clocks(int xtal);
-extern void exynos4_init_uarts(struct s3c2410_uartcfg *cfg, int no);
+#ifdef CONFIG_SOC_EXYNOS4212
+void exynos4212_register_clocks(void);
 
 #else
-#define exynos4_init_clocks NULL
-#define exynos4_init_uarts NULL
-#define exynos4_map_io NULL
-#define exynos_init NULL
+#define exynos4212_register_clocks()
 #endif
 
 #endif /* __ARCH_ARM_MACH_EXYNOS_COMMON_H */
diff --git a/arch/arm/mach-exynos/dev-ahci.c b/arch/arm/mach-exynos/dev-ahci.c
index f57a3de8e1d2..50ce5b0adcf1 100644
--- a/arch/arm/mach-exynos/dev-ahci.c
+++ b/arch/arm/mach-exynos/dev-ahci.c
@@ -242,8 +242,8 @@ static struct resource exynos4_ahci_resource[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= IRQ_SATA,
-		.end	= IRQ_SATA,
+		.start	= EXYNOS4_IRQ_SATA,
+		.end	= EXYNOS4_IRQ_SATA,
 		.flags	= IORESOURCE_IRQ,
 	},
 };
diff --git a/arch/arm/mach-exynos/dev-audio.c b/arch/arm/mach-exynos/dev-audio.c
index 5a9f9c2e53bf..7199e1ae79b4 100644
--- a/arch/arm/mach-exynos/dev-audio.c
+++ b/arch/arm/mach-exynos/dev-audio.c
@@ -304,8 +304,8 @@ static struct resource exynos4_ac97_resource[] = {
 		.flags	= IORESOURCE_DMA,
 	},
 	[4] = {
-		.start	= IRQ_AC97,
-		.end	= IRQ_AC97,
+		.start	= EXYNOS4_IRQ_AC97,
+		.end	= EXYNOS4_IRQ_AC97,
 		.flags	= IORESOURCE_IRQ,
 	},
 };
diff --git a/arch/arm/mach-exynos/dev-uart.c b/arch/arm/mach-exynos/dev-uart.c
new file mode 100644
index 000000000000..2e85c022fd16
--- /dev/null
+++ b/arch/arm/mach-exynos/dev-uart.c
@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Base EXYNOS UART resource and device definitions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/ioport.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/irq.h>
+#include <mach/hardware.h>
+#include <mach/map.h>
+
+#include <plat/devs.h>
+
+#define EXYNOS_UART_RESOURCE(_series, _nr)	\
+static struct resource exynos##_series##_uart##_nr##_resource[] = {	\
+	[0] = DEFINE_RES_MEM(EXYNOS##_series##_PA_UART##_nr, EXYNOS##_series##_SZ_UART),	\
+	[1] = DEFINE_RES_IRQ(EXYNOS##_series##_IRQ_UART##_nr),	\
+};
+
+EXYNOS_UART_RESOURCE(4, 0)
+EXYNOS_UART_RESOURCE(4, 1)
+EXYNOS_UART_RESOURCE(4, 2)
+EXYNOS_UART_RESOURCE(4, 3)
+
+struct s3c24xx_uart_resources exynos4_uart_resources[] __initdata = {
+	[0] = {
+		.resources	= exynos4_uart0_resource,
+		.nr_resources	= ARRAY_SIZE(exynos4_uart0_resource),
+	},
+	[1] = {
+		.resources	= exynos4_uart1_resource,
+		.nr_resources	= ARRAY_SIZE(exynos4_uart1_resource),
+	},
+	[2] = {
+		.resources	= exynos4_uart2_resource,
+		.nr_resources	= ARRAY_SIZE(exynos4_uart2_resource),
+	},
+	[3] = {
+		.resources	= exynos4_uart3_resource,
+		.nr_resources	= ARRAY_SIZE(exynos4_uart3_resource),
+	},
+};
+
+EXYNOS_UART_RESOURCE(5, 0)
+EXYNOS_UART_RESOURCE(5, 1)
+EXYNOS_UART_RESOURCE(5, 2)
+EXYNOS_UART_RESOURCE(5, 3)
+
+struct s3c24xx_uart_resources exynos5_uart_resources[] __initdata = {
+	[0] = {
+		.resources	= exynos5_uart0_resource,
+		.nr_resources	= ARRAY_SIZE(exynos5_uart0_resource),
+	},
+	[1] = {
+		.resources	= exynos5_uart1_resource,
+		.nr_resources	= ARRAY_SIZE(exynos5_uart0_resource),
+	},
+	[2] = {
+		.resources	= exynos5_uart2_resource,
+		.nr_resources	= ARRAY_SIZE(exynos5_uart2_resource),
+	},
+	[3] = {
+		.resources	= exynos5_uart3_resource,
+		.nr_resources	= ARRAY_SIZE(exynos5_uart3_resource),
+	},
+};
diff --git a/arch/arm/mach-exynos/dma.c b/arch/arm/mach-exynos/dma.c
index 13607c4328b3..69aaa4503205 100644
--- a/arch/arm/mach-exynos/dma.c
+++ b/arch/arm/mach-exynos/dma.c
@@ -35,8 +35,6 @@
 #include <mach/irqs.h>
 #include <mach/dma.h>
 
-static u64 dma_dmamask = DMA_BIT_MASK(32);
-
 static u8 exynos4210_pdma0_peri[] = {
 	DMACH_PCM0_RX,
 	DMACH_PCM0_TX,
@@ -108,7 +106,7 @@ static u8 exynos4212_pdma0_peri[] = {
 struct dma_pl330_platdata exynos4_pdma0_pdata;
 
 static AMBA_AHB_DEVICE(exynos4_pdma0, "dma-pl330.0", 0x00041330,
-	EXYNOS4_PA_PDMA0, {IRQ_PDMA0}, &exynos4_pdma0_pdata);
+	EXYNOS4_PA_PDMA0, {EXYNOS4_IRQ_PDMA0}, &exynos4_pdma0_pdata);
 
 static u8 exynos4210_pdma1_peri[] = {
 	DMACH_PCM0_RX,
@@ -174,7 +172,7 @@ static u8 exynos4212_pdma1_peri[] = {
 static struct dma_pl330_platdata exynos4_pdma1_pdata;
 
 static AMBA_AHB_DEVICE(exynos4_pdma1,  "dma-pl330.1", 0x00041330,
-	EXYNOS4_PA_PDMA1, {IRQ_PDMA1}, &exynos4_pdma1_pdata);
+	EXYNOS4_PA_PDMA1, {EXYNOS4_IRQ_PDMA1}, &exynos4_pdma1_pdata);
 
 static u8 mdma_peri[] = {
 	DMACH_MTOM_0,
@@ -193,7 +191,7 @@ static struct dma_pl330_platdata exynos4_mdma1_pdata = {
 };
 
 static AMBA_AHB_DEVICE(exynos4_mdma1,  "dma-pl330.2", 0x00041330,
-	EXYNOS4_PA_MDMA1, {IRQ_MDMA1}, &exynos4_mdma1_pdata);
+	EXYNOS4_PA_MDMA1, {EXYNOS4_IRQ_MDMA1}, &exynos4_mdma1_pdata);
 
 static int __init exynos4_dma_init(void)
 {
diff --git a/arch/arm/mach-exynos/hotplug.c b/arch/arm/mach-exynos/hotplug.c
index dd1ad55524c9..9c17a0a43858 100644
--- a/arch/arm/mach-exynos/hotplug.c
+++ b/arch/arm/mach-exynos/hotplug.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
 #include <asm/smp_plat.h>
 
 #include <mach/regs-pmu.h>
diff --git a/arch/arm/mach-exynos/include/mach/debug-macro.S b/arch/arm/mach-exynos/include/mach/debug-macro.S
index 6cacf16a67a6..e0c86ea475e7 100644
--- a/arch/arm/mach-exynos/include/mach/debug-macro.S
+++ b/arch/arm/mach-exynos/include/mach/debug-macro.S
@@ -21,8 +21,12 @@
 	 */
 
 	.macro addruart, rp, rv, tmp
-		ldr	\rp, = S3C_PA_UART
-		ldr	\rv, = S3C_VA_UART
+		mrc	p15, 0, \tmp, c0, c0, 0
+		and	\tmp, \tmp, #0xf0
+		teq	\tmp, #0xf0		@@ A15
+		ldreq	\rp, =EXYNOS5_PA_UART
+		movne	\rp, #EXYNOS4_PA_UART	@@ EXYNOS4
+		ldr	\rv, =S3C_VA_UART
 #if CONFIG_DEBUG_S3C_UART != 0
 		add	\rp, \rp, #(0x10000 * CONFIG_DEBUG_S3C_UART)
 		add	\rv, \rv, #(0x10000 * CONFIG_DEBUG_S3C_UART)
diff --git a/arch/arm/mach-exynos/include/mach/gpio.h b/arch/arm/mach-exynos/include/mach/gpio.h
index 80523ca9bb49..d7498afe036a 100644
--- a/arch/arm/mach-exynos/include/mach/gpio.h
+++ b/arch/arm/mach-exynos/include/mach/gpio.h
@@ -1,9 +1,8 @@
-/* linux/arch/arm/mach-exynos4/include/mach/gpio.h
- *
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
+/*
+ * Copyright (c) 2010-2012 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
- * EXYNOS4 - GPIO lib support
+ * EXYNOS - GPIO lib support
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -13,9 +12,13 @@
 #ifndef __ASM_ARCH_GPIO_H
 #define __ASM_ARCH_GPIO_H __FILE__
 
-/* Practically, GPIO banks up to GPZ are the configurable gpio banks */
+/* Macro for EXYNOS GPIO numbering */
+
+#define EXYNOS_GPIO_NEXT(__gpio) \
+	((__gpio##_START) + (__gpio##_NR) + CONFIG_S3C_GPIO_SPACE + 1)
+
+/* EXYNOS4 GPIO bank sizes */
 
-/* GPIO bank sizes */
 #define EXYNOS4_GPIO_A0_NR	(8)
 #define EXYNOS4_GPIO_A1_NR	(6)
 #define EXYNOS4_GPIO_B_NR	(8)
@@ -54,52 +57,50 @@
 #define EXYNOS4_GPIO_Y6_NR	(8)
 #define EXYNOS4_GPIO_Z_NR	(7)
 
-/* GPIO bank numbers */
-
-#define EXYNOS4_GPIO_NEXT(__gpio) \
-	((__gpio##_START) + (__gpio##_NR) + CONFIG_S3C_GPIO_SPACE + 1)
+/* EXYNOS4 GPIO bank numbers */
 
-enum s5p_gpio_number {
+enum exynos4_gpio_number {
 	EXYNOS4_GPIO_A0_START	= 0,
-	EXYNOS4_GPIO_A1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_A0),
-	EXYNOS4_GPIO_B_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_A1),
-	EXYNOS4_GPIO_C0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_B),
-	EXYNOS4_GPIO_C1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_C0),
-	EXYNOS4_GPIO_D0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_C1),
-	EXYNOS4_GPIO_D1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_D0),
-	EXYNOS4_GPIO_E0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_D1),
-	EXYNOS4_GPIO_E1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_E0),
-	EXYNOS4_GPIO_E2_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_E1),
-	EXYNOS4_GPIO_E3_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_E2),
-	EXYNOS4_GPIO_E4_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_E3),
-	EXYNOS4_GPIO_F0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_E4),
-	EXYNOS4_GPIO_F1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_F0),
-	EXYNOS4_GPIO_F2_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_F1),
-	EXYNOS4_GPIO_F3_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_F2),
-	EXYNOS4_GPIO_J0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_F3),
-	EXYNOS4_GPIO_J1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_J0),
-	EXYNOS4_GPIO_K0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_J1),
-	EXYNOS4_GPIO_K1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_K0),
-	EXYNOS4_GPIO_K2_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_K1),
-	EXYNOS4_GPIO_K3_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_K2),
-	EXYNOS4_GPIO_L0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_K3),
-	EXYNOS4_GPIO_L1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_L0),
-	EXYNOS4_GPIO_L2_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_L1),
-	EXYNOS4_GPIO_X0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_L2),
-	EXYNOS4_GPIO_X1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_X0),
-	EXYNOS4_GPIO_X2_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_X1),
-	EXYNOS4_GPIO_X3_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_X2),
-	EXYNOS4_GPIO_Y0_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_X3),
-	EXYNOS4_GPIO_Y1_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_Y0),
-	EXYNOS4_GPIO_Y2_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_Y1),
-	EXYNOS4_GPIO_Y3_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_Y2),
-	EXYNOS4_GPIO_Y4_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_Y3),
-	EXYNOS4_GPIO_Y5_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_Y4),
-	EXYNOS4_GPIO_Y6_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_Y5),
-	EXYNOS4_GPIO_Z_START	= EXYNOS4_GPIO_NEXT(EXYNOS4_GPIO_Y6),
+	EXYNOS4_GPIO_A1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_A0),
+	EXYNOS4_GPIO_B_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_A1),
+	EXYNOS4_GPIO_C0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_B),
+	EXYNOS4_GPIO_C1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_C0),
+	EXYNOS4_GPIO_D0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_C1),
+	EXYNOS4_GPIO_D1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_D0),
+	EXYNOS4_GPIO_E0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_D1),
+	EXYNOS4_GPIO_E1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_E0),
+	EXYNOS4_GPIO_E2_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_E1),
+	EXYNOS4_GPIO_E3_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_E2),
+	EXYNOS4_GPIO_E4_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_E3),
+	EXYNOS4_GPIO_F0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_E4),
+	EXYNOS4_GPIO_F1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_F0),
+	EXYNOS4_GPIO_F2_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_F1),
+	EXYNOS4_GPIO_F3_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_F2),
+	EXYNOS4_GPIO_J0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_F3),
+	EXYNOS4_GPIO_J1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_J0),
+	EXYNOS4_GPIO_K0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_J1),
+	EXYNOS4_GPIO_K1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_K0),
+	EXYNOS4_GPIO_K2_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_K1),
+	EXYNOS4_GPIO_K3_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_K2),
+	EXYNOS4_GPIO_L0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_K3),
+	EXYNOS4_GPIO_L1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_L0),
+	EXYNOS4_GPIO_L2_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_L1),
+	EXYNOS4_GPIO_X0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_L2),
+	EXYNOS4_GPIO_X1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_X0),
+	EXYNOS4_GPIO_X2_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_X1),
+	EXYNOS4_GPIO_X3_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_X2),
+	EXYNOS4_GPIO_Y0_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_X3),
+	EXYNOS4_GPIO_Y1_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_Y0),
+	EXYNOS4_GPIO_Y2_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_Y1),
+	EXYNOS4_GPIO_Y3_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_Y2),
+	EXYNOS4_GPIO_Y4_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_Y3),
+	EXYNOS4_GPIO_Y5_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_Y4),
+	EXYNOS4_GPIO_Y6_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_Y5),
+	EXYNOS4_GPIO_Z_START	= EXYNOS_GPIO_NEXT(EXYNOS4_GPIO_Y6),
 };
 
 /* EXYNOS4 GPIO number definitions */
+
 #define EXYNOS4_GPA0(_nr)	(EXYNOS4_GPIO_A0_START + (_nr))
 #define EXYNOS4_GPA1(_nr)	(EXYNOS4_GPIO_A1_START + (_nr))
 #define EXYNOS4_GPB(_nr)	(EXYNOS4_GPIO_B_START + (_nr))
@@ -139,11 +140,147 @@ enum s5p_gpio_number {
 #define EXYNOS4_GPZ(_nr)	(EXYNOS4_GPIO_Z_START + (_nr))
 
 /* the end of the EXYNOS4 specific gpios */
+
 #define EXYNOS4_GPIO_END	(EXYNOS4_GPZ(EXYNOS4_GPIO_Z_NR) + 1)
-#define S3C_GPIO_END		EXYNOS4_GPIO_END
 
-/* define the number of gpios we need to the one after the GPZ() range */
-#define ARCH_NR_GPIOS		(EXYNOS4_GPZ(EXYNOS4_GPIO_Z_NR) +	\
-				 CONFIG_SAMSUNG_GPIO_EXTRA + 1)
+/* EXYNOS5 GPIO bank sizes */
+
+#define EXYNOS5_GPIO_A0_NR	(8)
+#define EXYNOS5_GPIO_A1_NR	(6)
+#define EXYNOS5_GPIO_A2_NR	(8)
+#define EXYNOS5_GPIO_B0_NR	(5)
+#define EXYNOS5_GPIO_B1_NR	(5)
+#define EXYNOS5_GPIO_B2_NR	(4)
+#define EXYNOS5_GPIO_B3_NR	(4)
+#define EXYNOS5_GPIO_C0_NR	(7)
+#define EXYNOS5_GPIO_C1_NR	(7)
+#define EXYNOS5_GPIO_C2_NR	(7)
+#define EXYNOS5_GPIO_C3_NR	(7)
+#define EXYNOS5_GPIO_D0_NR	(8)
+#define EXYNOS5_GPIO_D1_NR	(8)
+#define EXYNOS5_GPIO_Y0_NR	(6)
+#define EXYNOS5_GPIO_Y1_NR	(4)
+#define EXYNOS5_GPIO_Y2_NR	(6)
+#define EXYNOS5_GPIO_Y3_NR	(8)
+#define EXYNOS5_GPIO_Y4_NR	(8)
+#define EXYNOS5_GPIO_Y5_NR	(8)
+#define EXYNOS5_GPIO_Y6_NR	(8)
+#define EXYNOS5_GPIO_X0_NR	(8)
+#define EXYNOS5_GPIO_X1_NR	(8)
+#define EXYNOS5_GPIO_X2_NR	(8)
+#define EXYNOS5_GPIO_X3_NR	(8)
+#define EXYNOS5_GPIO_E0_NR	(8)
+#define EXYNOS5_GPIO_E1_NR	(2)
+#define EXYNOS5_GPIO_F0_NR	(4)
+#define EXYNOS5_GPIO_F1_NR	(4)
+#define EXYNOS5_GPIO_G0_NR	(8)
+#define EXYNOS5_GPIO_G1_NR	(8)
+#define EXYNOS5_GPIO_G2_NR	(2)
+#define EXYNOS5_GPIO_H0_NR	(4)
+#define EXYNOS5_GPIO_H1_NR	(8)
+#define EXYNOS5_GPIO_V0_NR	(8)
+#define EXYNOS5_GPIO_V1_NR	(8)
+#define EXYNOS5_GPIO_V2_NR	(8)
+#define EXYNOS5_GPIO_V3_NR	(8)
+#define EXYNOS5_GPIO_V4_NR	(2)
+#define EXYNOS5_GPIO_Z_NR	(7)
+
+/* EXYNOS5 GPIO bank numbers */
+
+enum exynos5_gpio_number {
+	EXYNOS5_GPIO_A0_START		= 0,
+	EXYNOS5_GPIO_A1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_A0),
+	EXYNOS5_GPIO_A2_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_A1),
+	EXYNOS5_GPIO_B0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_A2),
+	EXYNOS5_GPIO_B1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_B0),
+	EXYNOS5_GPIO_B2_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_B1),
+	EXYNOS5_GPIO_B3_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_B2),
+	EXYNOS5_GPIO_C0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_B3),
+	EXYNOS5_GPIO_C1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_C0),
+	EXYNOS5_GPIO_C2_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_C1),
+	EXYNOS5_GPIO_C3_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_C2),
+	EXYNOS5_GPIO_D0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_C3),
+	EXYNOS5_GPIO_D1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_D0),
+	EXYNOS5_GPIO_Y0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_D1),
+	EXYNOS5_GPIO_Y1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_Y0),
+	EXYNOS5_GPIO_Y2_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_Y1),
+	EXYNOS5_GPIO_Y3_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_Y2),
+	EXYNOS5_GPIO_Y4_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_Y3),
+	EXYNOS5_GPIO_Y5_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_Y4),
+	EXYNOS5_GPIO_Y6_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_Y5),
+	EXYNOS5_GPIO_X0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_Y6),
+	EXYNOS5_GPIO_X1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_X0),
+	EXYNOS5_GPIO_X2_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_X1),
+	EXYNOS5_GPIO_X3_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_X2),
+	EXYNOS5_GPIO_E0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_X3),
+	EXYNOS5_GPIO_E1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_E0),
+	EXYNOS5_GPIO_F0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_E1),
+	EXYNOS5_GPIO_F1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_F0),
+	EXYNOS5_GPIO_G0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_F1),
+	EXYNOS5_GPIO_G1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_G0),
+	EXYNOS5_GPIO_G2_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_G1),
+	EXYNOS5_GPIO_H0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_G2),
+	EXYNOS5_GPIO_H1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_H0),
+	EXYNOS5_GPIO_V0_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_H1),
+	EXYNOS5_GPIO_V1_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_V0),
+	EXYNOS5_GPIO_V2_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_V1),
+	EXYNOS5_GPIO_V3_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_V2),
+	EXYNOS5_GPIO_V4_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_V3),
+	EXYNOS5_GPIO_Z_START		= EXYNOS_GPIO_NEXT(EXYNOS5_GPIO_V4),
+};
+
+/* EXYNOS5 GPIO number definitions */
+
+#define EXYNOS5_GPA0(_nr)	(EXYNOS5_GPIO_A0_START + (_nr))
+#define EXYNOS5_GPA1(_nr)	(EXYNOS5_GPIO_A1_START + (_nr))
+#define EXYNOS5_GPA2(_nr)	(EXYNOS5_GPIO_A2_START + (_nr))
+#define EXYNOS5_GPB0(_nr)	(EXYNOS5_GPIO_B0_START + (_nr))
+#define EXYNOS5_GPB1(_nr)	(EXYNOS5_GPIO_B1_START + (_nr))
+#define EXYNOS5_GPB2(_nr)	(EXYNOS5_GPIO_B2_START + (_nr))
+#define EXYNOS5_GPB3(_nr)	(EXYNOS5_GPIO_B3_START + (_nr))
+#define EXYNOS5_GPC0(_nr)	(EXYNOS5_GPIO_C0_START + (_nr))
+#define EXYNOS5_GPC1(_nr)	(EXYNOS5_GPIO_C1_START + (_nr))
+#define EXYNOS5_GPC2(_nr)	(EXYNOS5_GPIO_C2_START + (_nr))
+#define EXYNOS5_GPC3(_nr)	(EXYNOS5_GPIO_C3_START + (_nr))
+#define EXYNOS5_GPD0(_nr)	(EXYNOS5_GPIO_D0_START + (_nr))
+#define EXYNOS5_GPD1(_nr)	(EXYNOS5_GPIO_D1_START + (_nr))
+#define EXYNOS5_GPY0(_nr)	(EXYNOS5_GPIO_Y0_START + (_nr))
+#define EXYNOS5_GPY1(_nr)	(EXYNOS5_GPIO_Y1_START + (_nr))
+#define EXYNOS5_GPY2(_nr)	(EXYNOS5_GPIO_Y2_START + (_nr))
+#define EXYNOS5_GPY3(_nr)	(EXYNOS5_GPIO_Y3_START + (_nr))
+#define EXYNOS5_GPY4(_nr)	(EXYNOS5_GPIO_Y4_START + (_nr))
+#define EXYNOS5_GPY5(_nr)	(EXYNOS5_GPIO_Y5_START + (_nr))
+#define EXYNOS5_GPY6(_nr)	(EXYNOS5_GPIO_Y6_START + (_nr))
+#define EXYNOS5_GPX0(_nr)	(EXYNOS5_GPIO_X0_START + (_nr))
+#define EXYNOS5_GPX1(_nr)	(EXYNOS5_GPIO_X1_START + (_nr))
+#define EXYNOS5_GPX2(_nr)	(EXYNOS5_GPIO_X2_START + (_nr))
+#define EXYNOS5_GPX3(_nr)	(EXYNOS5_GPIO_X3_START + (_nr))
+#define EXYNOS5_GPE0(_nr)	(EXYNOS5_GPIO_E0_START + (_nr))
+#define EXYNOS5_GPE1(_nr)	(EXYNOS5_GPIO_E1_START + (_nr))
+#define EXYNOS5_GPF0(_nr)	(EXYNOS5_GPIO_F0_START + (_nr))
+#define EXYNOS5_GPF1(_nr)	(EXYNOS5_GPIO_F1_START + (_nr))
+#define EXYNOS5_GPG0(_nr)	(EXYNOS5_GPIO_G0_START + (_nr))
+#define EXYNOS5_GPG1(_nr)	(EXYNOS5_GPIO_G1_START + (_nr))
+#define EXYNOS5_GPG2(_nr)	(EXYNOS5_GPIO_G2_START + (_nr))
+#define EXYNOS5_GPH0(_nr)	(EXYNOS5_GPIO_H0_START + (_nr))
+#define EXYNOS5_GPH1(_nr)	(EXYNOS5_GPIO_H1_START + (_nr))
+#define EXYNOS5_GPV0(_nr)	(EXYNOS5_GPIO_V0_START + (_nr))
+#define EXYNOS5_GPV1(_nr)	(EXYNOS5_GPIO_V1_START + (_nr))
+#define EXYNOS5_GPV2(_nr)	(EXYNOS5_GPIO_V2_START + (_nr))
+#define EXYNOS5_GPV3(_nr)	(EXYNOS5_GPIO_V3_START + (_nr))
+#define EXYNOS5_GPV4(_nr)	(EXYNOS5_GPIO_V4_START + (_nr))
+#define EXYNOS5_GPZ(_nr)	(EXYNOS5_GPIO_Z_START + (_nr))
+
+/* the end of the EXYNOS5 specific gpios */
+
+#define EXYNOS5_GPIO_END	(EXYNOS5_GPZ(EXYNOS5_GPIO_Z_NR) + 1)
+
+/* actually, EXYNOS5_GPIO_END is bigger than EXYNOS4 */
+
+#define S3C_GPIO_END		(EXYNOS5_GPIO_END)
+
+/* define the number of gpios */
+
+#define ARCH_NR_GPIOS		(CONFIG_SAMSUNG_GPIO_EXTRA + S3C_GPIO_END)
 
 #endif /* __ASM_ARCH_GPIO_H */
diff --git a/arch/arm/mach-exynos/include/mach/io.h b/arch/arm/mach-exynos/include/mach/io.h
deleted file mode 100644
index d5478d247535..000000000000
--- a/arch/arm/mach-exynos/include/mach/io.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* linux/arch/arm/mach-exynos4/include/mach/io.h
- *
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Copyright 2008-2010 Ben Dooks <ben-linux@fluff.org>
- *
- * Based on arch/arm/mach-s5p6442/include/mach/io.h
- *
- * Default IO routines for EXYNOS4
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H __FILE__
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif /* __ASM_ARM_ARCH_IO_H */
diff --git a/arch/arm/mach-exynos/include/mach/irqs.h b/arch/arm/mach-exynos/include/mach/irqs.h
index 1d401c957835..9bee8535d9e0 100644
--- a/arch/arm/mach-exynos/include/mach/irqs.h
+++ b/arch/arm/mach-exynos/include/mach/irqs.h
@@ -1,9 +1,8 @@
-/* linux/arch/arm/mach-exynos4/include/mach/irqs.h
- *
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
+/*
+ * Copyright (c) 2010-2012 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
- * EXYNOS4 - IRQ definitions
+ * EXYNOS - IRQ definitions
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -17,160 +16,450 @@
 
 /* PPI: Private Peripheral Interrupt */
 
-#define IRQ_PPI(x)		(x+16)
-
-#define IRQ_MCT_LOCALTIMER	IRQ_PPI(12)
+#define IRQ_PPI(x)			(x + 16)
 
 /* SPI: Shared Peripheral Interrupt */
 
-#define IRQ_SPI(x)		(x+32)
-
-#define IRQ_EINT0		IRQ_SPI(16)
-#define IRQ_EINT1		IRQ_SPI(17)
-#define IRQ_EINT2		IRQ_SPI(18)
-#define IRQ_EINT3		IRQ_SPI(19)
-#define IRQ_EINT4		IRQ_SPI(20)
-#define IRQ_EINT5		IRQ_SPI(21)
-#define IRQ_EINT6		IRQ_SPI(22)
-#define IRQ_EINT7		IRQ_SPI(23)
-#define IRQ_EINT8		IRQ_SPI(24)
-#define IRQ_EINT9		IRQ_SPI(25)
-#define IRQ_EINT10		IRQ_SPI(26)
-#define IRQ_EINT11		IRQ_SPI(27)
-#define IRQ_EINT12		IRQ_SPI(28)
-#define IRQ_EINT13		IRQ_SPI(29)
-#define IRQ_EINT14		IRQ_SPI(30)
-#define IRQ_EINT15		IRQ_SPI(31)
-#define IRQ_EINT16_31		IRQ_SPI(32)
-
-#define IRQ_MDMA0		IRQ_SPI(33)
-#define IRQ_MDMA1		IRQ_SPI(34)
-#define IRQ_PDMA0		IRQ_SPI(35)
-#define IRQ_PDMA1		IRQ_SPI(36)
-#define IRQ_TIMER0_VIC		IRQ_SPI(37)
-#define IRQ_TIMER1_VIC		IRQ_SPI(38)
-#define IRQ_TIMER2_VIC		IRQ_SPI(39)
-#define IRQ_TIMER3_VIC		IRQ_SPI(40)
-#define IRQ_TIMER4_VIC		IRQ_SPI(41)
-#define IRQ_MCT_L0		IRQ_SPI(42)
-#define IRQ_WDT			IRQ_SPI(43)
-#define IRQ_RTC_ALARM		IRQ_SPI(44)
-#define IRQ_RTC_TIC		IRQ_SPI(45)
-#define IRQ_GPIO_XB		IRQ_SPI(46)
-#define IRQ_GPIO_XA		IRQ_SPI(47)
-#define IRQ_MCT_L1		IRQ_SPI(48)
-
-#define IRQ_UART0		IRQ_SPI(52)
-#define IRQ_UART1		IRQ_SPI(53)
-#define IRQ_UART2		IRQ_SPI(54)
-#define IRQ_UART3		IRQ_SPI(55)
-#define IRQ_UART4		IRQ_SPI(56)
-#define IRQ_MCT_G0		IRQ_SPI(57)
-#define IRQ_IIC			IRQ_SPI(58)
-#define IRQ_IIC1		IRQ_SPI(59)
-#define IRQ_IIC2		IRQ_SPI(60)
-#define IRQ_IIC3		IRQ_SPI(61)
-#define IRQ_IIC4		IRQ_SPI(62)
-#define IRQ_IIC5		IRQ_SPI(63)
-#define IRQ_IIC6		IRQ_SPI(64)
-#define IRQ_IIC7		IRQ_SPI(65)
-#define IRQ_SPI0		IRQ_SPI(66)
-#define IRQ_SPI1		IRQ_SPI(67)
-#define IRQ_SPI2		IRQ_SPI(68)
-
-#define IRQ_USB_HOST		IRQ_SPI(70)
-#define IRQ_USB_HSOTG		IRQ_SPI(71)
-#define IRQ_MODEM_IF		IRQ_SPI(72)
-#define IRQ_HSMMC0		IRQ_SPI(73)
-#define IRQ_HSMMC1		IRQ_SPI(74)
-#define IRQ_HSMMC2		IRQ_SPI(75)
-#define IRQ_HSMMC3		IRQ_SPI(76)
-#define IRQ_DWMCI		IRQ_SPI(77)
-
-#define IRQ_MIPI_CSIS0		IRQ_SPI(78)
-#define IRQ_MIPI_CSIS1		IRQ_SPI(80)
-
-#define IRQ_ONENAND_AUDI	IRQ_SPI(82)
-#define IRQ_ROTATOR		IRQ_SPI(83)
-#define IRQ_FIMC0		IRQ_SPI(84)
-#define IRQ_FIMC1		IRQ_SPI(85)
-#define IRQ_FIMC2		IRQ_SPI(86)
-#define IRQ_FIMC3		IRQ_SPI(87)
-#define IRQ_JPEG		IRQ_SPI(88)
-#define IRQ_2D			IRQ_SPI(89)
-#define IRQ_PCIE		IRQ_SPI(90)
-
-#define IRQ_MIXER		IRQ_SPI(91)
-#define IRQ_HDMI		IRQ_SPI(92)
-#define IRQ_IIC_HDMIPHY		IRQ_SPI(93)
-#define IRQ_MFC			IRQ_SPI(94)
-#define IRQ_SDO			IRQ_SPI(95)
-
-#define IRQ_AUDIO_SS		IRQ_SPI(96)
-#define IRQ_I2S0		IRQ_SPI(97)
-#define IRQ_I2S1		IRQ_SPI(98)
-#define IRQ_I2S2		IRQ_SPI(99)
-#define IRQ_AC97		IRQ_SPI(100)
-
-#define IRQ_SPDIF		IRQ_SPI(104)
-#define IRQ_ADC0		IRQ_SPI(105)
-#define IRQ_PEN0		IRQ_SPI(106)
-#define IRQ_ADC1		IRQ_SPI(107)
-#define IRQ_PEN1		IRQ_SPI(108)
-#define IRQ_KEYPAD		IRQ_SPI(109)
-#define IRQ_PMU			IRQ_SPI(110)
-#define IRQ_GPS			IRQ_SPI(111)
-#define IRQ_INTFEEDCTRL_SSS	IRQ_SPI(112)
-#define IRQ_SLIMBUS		IRQ_SPI(113)
-
-#define IRQ_TSI			IRQ_SPI(115)
-#define IRQ_SATA		IRQ_SPI(116)
-
-#define MAX_IRQ_IN_COMBINER	8
-#define COMBINER_GROUP(x)	((x) * MAX_IRQ_IN_COMBINER + IRQ_SPI(128))
-#define COMBINER_IRQ(x, y)	(COMBINER_GROUP(x) + y)
-
-#define IRQ_SYSMMU_MDMA0_0	COMBINER_IRQ(4, 0)
-#define IRQ_SYSMMU_SSS_0	COMBINER_IRQ(4, 1)
-#define IRQ_SYSMMU_FIMC0_0	COMBINER_IRQ(4, 2)
-#define IRQ_SYSMMU_FIMC1_0	COMBINER_IRQ(4, 3)
-#define IRQ_SYSMMU_FIMC2_0	COMBINER_IRQ(4, 4)
-#define IRQ_SYSMMU_FIMC3_0	COMBINER_IRQ(4, 5)
-#define IRQ_SYSMMU_JPEG_0	COMBINER_IRQ(4, 6)
-#define IRQ_SYSMMU_2D_0		COMBINER_IRQ(4, 7)
-
-#define IRQ_SYSMMU_ROTATOR_0	COMBINER_IRQ(5, 0)
-#define IRQ_SYSMMU_MDMA1_0	COMBINER_IRQ(5, 1)
-#define IRQ_SYSMMU_LCD0_M0_0	COMBINER_IRQ(5, 2)
-#define IRQ_SYSMMU_LCD1_M1_0	COMBINER_IRQ(5, 3)
-#define IRQ_SYSMMU_TV_M0_0	COMBINER_IRQ(5, 4)
-#define IRQ_SYSMMU_MFC_M0_0	COMBINER_IRQ(5, 5)
-#define IRQ_SYSMMU_MFC_M1_0	COMBINER_IRQ(5, 6)
-#define IRQ_SYSMMU_PCIE_0	COMBINER_IRQ(5, 7)
-
-#define IRQ_FIMD0_FIFO		COMBINER_IRQ(11, 0)
-#define IRQ_FIMD0_VSYNC		COMBINER_IRQ(11, 1)
-#define IRQ_FIMD0_SYSTEM	COMBINER_IRQ(11, 2)
-
-#define MAX_COMBINER_NR		16
-
-#define IRQ_ADC			IRQ_ADC0
-#define IRQ_TC			IRQ_PEN0
-
-#define S5P_IRQ_EINT_BASE	COMBINER_IRQ(MAX_COMBINER_NR, 0)
-
-#define S5P_EINT_BASE1		(S5P_IRQ_EINT_BASE + 0)
-#define S5P_EINT_BASE2		(S5P_IRQ_EINT_BASE + 16)
-
-/* optional GPIO interrupts */
-#define S5P_GPIOINT_BASE	(S5P_IRQ_EINT_BASE + 32)
-#define IRQ_GPIO1_NR_GROUPS	16
-#define IRQ_GPIO2_NR_GROUPS	9
-#define IRQ_GPIO_END		(S5P_GPIOINT_BASE + S5P_GPIOINT_COUNT)
-
-#define IRQ_TIMER_BASE		(IRQ_GPIO_END + 64)
+#define IRQ_SPI(x)			(x + 32)
+
+/* COMBINER */
+
+#define MAX_IRQ_IN_COMBINER		8
+#define COMBINER_GROUP(x)		((x) * MAX_IRQ_IN_COMBINER + IRQ_SPI(128))
+#define COMBINER_IRQ(x, y)		(COMBINER_GROUP(x) + y)
+
+/* For EXYNOS4 and EXYNOS5 */
+
+#define EXYNOS_IRQ_MCT_LOCALTIMER	IRQ_PPI(12)
+
+#define EXYNOS_IRQ_EINT16_31		IRQ_SPI(32)
+
+/* For EXYNOS4 SoCs */
+
+#define EXYNOS4_IRQ_EINT0		IRQ_SPI(16)
+#define EXYNOS4_IRQ_EINT1		IRQ_SPI(17)
+#define EXYNOS4_IRQ_EINT2		IRQ_SPI(18)
+#define EXYNOS4_IRQ_EINT3		IRQ_SPI(19)
+#define EXYNOS4_IRQ_EINT4		IRQ_SPI(20)
+#define EXYNOS4_IRQ_EINT5		IRQ_SPI(21)
+#define EXYNOS4_IRQ_EINT6		IRQ_SPI(22)
+#define EXYNOS4_IRQ_EINT7		IRQ_SPI(23)
+#define EXYNOS4_IRQ_EINT8		IRQ_SPI(24)
+#define EXYNOS4_IRQ_EINT9		IRQ_SPI(25)
+#define EXYNOS4_IRQ_EINT10		IRQ_SPI(26)
+#define EXYNOS4_IRQ_EINT11		IRQ_SPI(27)
+#define EXYNOS4_IRQ_EINT12		IRQ_SPI(28)
+#define EXYNOS4_IRQ_EINT13		IRQ_SPI(29)
+#define EXYNOS4_IRQ_EINT14		IRQ_SPI(30)
+#define EXYNOS4_IRQ_EINT15		IRQ_SPI(31)
+
+#define EXYNOS4_IRQ_MDMA0		IRQ_SPI(33)
+#define EXYNOS4_IRQ_MDMA1		IRQ_SPI(34)
+#define EXYNOS4_IRQ_PDMA0		IRQ_SPI(35)
+#define EXYNOS4_IRQ_PDMA1		IRQ_SPI(36)
+#define EXYNOS4_IRQ_TIMER0_VIC		IRQ_SPI(37)
+#define EXYNOS4_IRQ_TIMER1_VIC		IRQ_SPI(38)
+#define EXYNOS4_IRQ_TIMER2_VIC		IRQ_SPI(39)
+#define EXYNOS4_IRQ_TIMER3_VIC		IRQ_SPI(40)
+#define EXYNOS4_IRQ_TIMER4_VIC		IRQ_SPI(41)
+#define EXYNOS4_IRQ_MCT_L0		IRQ_SPI(42)
+#define EXYNOS4_IRQ_WDT			IRQ_SPI(43)
+#define EXYNOS4_IRQ_RTC_ALARM		IRQ_SPI(44)
+#define EXYNOS4_IRQ_RTC_TIC		IRQ_SPI(45)
+#define EXYNOS4_IRQ_GPIO_XB		IRQ_SPI(46)
+#define EXYNOS4_IRQ_GPIO_XA		IRQ_SPI(47)
+#define EXYNOS4_IRQ_MCT_L1		IRQ_SPI(48)
+
+#define EXYNOS4_IRQ_UART0		IRQ_SPI(52)
+#define EXYNOS4_IRQ_UART1		IRQ_SPI(53)
+#define EXYNOS4_IRQ_UART2		IRQ_SPI(54)
+#define EXYNOS4_IRQ_UART3		IRQ_SPI(55)
+#define EXYNOS4_IRQ_UART4		IRQ_SPI(56)
+#define EXYNOS4_IRQ_MCT_G0		IRQ_SPI(57)
+#define EXYNOS4_IRQ_IIC			IRQ_SPI(58)
+#define EXYNOS4_IRQ_IIC1		IRQ_SPI(59)
+#define EXYNOS4_IRQ_IIC2		IRQ_SPI(60)
+#define EXYNOS4_IRQ_IIC3		IRQ_SPI(61)
+#define EXYNOS4_IRQ_IIC4		IRQ_SPI(62)
+#define EXYNOS4_IRQ_IIC5		IRQ_SPI(63)
+#define EXYNOS4_IRQ_IIC6		IRQ_SPI(64)
+#define EXYNOS4_IRQ_IIC7		IRQ_SPI(65)
+#define EXYNOS4_IRQ_SPI0		IRQ_SPI(66)
+#define EXYNOS4_IRQ_SPI1		IRQ_SPI(67)
+#define EXYNOS4_IRQ_SPI2		IRQ_SPI(68)
+
+#define EXYNOS4_IRQ_USB_HOST		IRQ_SPI(70)
+#define EXYNOS4_IRQ_USB_HSOTG		IRQ_SPI(71)
+#define EXYNOS4_IRQ_MODEM_IF		IRQ_SPI(72)
+#define EXYNOS4_IRQ_HSMMC0		IRQ_SPI(73)
+#define EXYNOS4_IRQ_HSMMC1		IRQ_SPI(74)
+#define EXYNOS4_IRQ_HSMMC2		IRQ_SPI(75)
+#define EXYNOS4_IRQ_HSMMC3		IRQ_SPI(76)
+#define EXYNOS4_IRQ_DWMCI		IRQ_SPI(77)
+
+#define EXYNOS4_IRQ_MIPI_CSIS0		IRQ_SPI(78)
+#define EXYNOS4_IRQ_MIPI_CSIS1		IRQ_SPI(80)
+
+#define EXYNOS4_IRQ_ONENAND_AUDI	IRQ_SPI(82)
+#define EXYNOS4_IRQ_ROTATOR		IRQ_SPI(83)
+#define EXYNOS4_IRQ_FIMC0		IRQ_SPI(84)
+#define EXYNOS4_IRQ_FIMC1		IRQ_SPI(85)
+#define EXYNOS4_IRQ_FIMC2		IRQ_SPI(86)
+#define EXYNOS4_IRQ_FIMC3		IRQ_SPI(87)
+#define EXYNOS4_IRQ_JPEG		IRQ_SPI(88)
+#define EXYNOS4_IRQ_2D			IRQ_SPI(89)
+#define EXYNOS4_IRQ_PCIE		IRQ_SPI(90)
+
+#define EXYNOS4_IRQ_MIXER		IRQ_SPI(91)
+#define EXYNOS4_IRQ_HDMI		IRQ_SPI(92)
+#define EXYNOS4_IRQ_IIC_HDMIPHY		IRQ_SPI(93)
+#define EXYNOS4_IRQ_MFC			IRQ_SPI(94)
+#define EXYNOS4_IRQ_SDO			IRQ_SPI(95)
+
+#define EXYNOS4_IRQ_AUDIO_SS		IRQ_SPI(96)
+#define EXYNOS4_IRQ_I2S0		IRQ_SPI(97)
+#define EXYNOS4_IRQ_I2S1		IRQ_SPI(98)
+#define EXYNOS4_IRQ_I2S2		IRQ_SPI(99)
+#define EXYNOS4_IRQ_AC97		IRQ_SPI(100)
+
+#define EXYNOS4_IRQ_SPDIF		IRQ_SPI(104)
+#define EXYNOS4_IRQ_ADC0		IRQ_SPI(105)
+#define EXYNOS4_IRQ_PEN0		IRQ_SPI(106)
+#define EXYNOS4_IRQ_ADC1		IRQ_SPI(107)
+#define EXYNOS4_IRQ_PEN1		IRQ_SPI(108)
+#define EXYNOS4_IRQ_KEYPAD		IRQ_SPI(109)
+#define EXYNOS4_IRQ_PMU			IRQ_SPI(110)
+#define EXYNOS4_IRQ_GPS			IRQ_SPI(111)
+#define EXYNOS4_IRQ_INTFEEDCTRL_SSS	IRQ_SPI(112)
+#define EXYNOS4_IRQ_SLIMBUS		IRQ_SPI(113)
+
+#define EXYNOS4_IRQ_TSI			IRQ_SPI(115)
+#define EXYNOS4_IRQ_SATA		IRQ_SPI(116)
+
+#define EXYNOS4_IRQ_SYSMMU_MDMA0_0	COMBINER_IRQ(4, 0)
+#define EXYNOS4_IRQ_SYSMMU_SSS_0	COMBINER_IRQ(4, 1)
+#define EXYNOS4_IRQ_SYSMMU_FIMC0_0	COMBINER_IRQ(4, 2)
+#define EXYNOS4_IRQ_SYSMMU_FIMC1_0	COMBINER_IRQ(4, 3)
+#define EXYNOS4_IRQ_SYSMMU_FIMC2_0	COMBINER_IRQ(4, 4)
+#define EXYNOS4_IRQ_SYSMMU_FIMC3_0	COMBINER_IRQ(4, 5)
+#define EXYNOS4_IRQ_SYSMMU_JPEG_0	COMBINER_IRQ(4, 6)
+#define EXYNOS4_IRQ_SYSMMU_2D_0		COMBINER_IRQ(4, 7)
+
+#define EXYNOS4_IRQ_SYSMMU_ROTATOR_0	COMBINER_IRQ(5, 0)
+#define EXYNOS4_IRQ_SYSMMU_MDMA1_0	COMBINER_IRQ(5, 1)
+#define EXYNOS4_IRQ_SYSMMU_LCD0_M0_0	COMBINER_IRQ(5, 2)
+#define EXYNOS4_IRQ_SYSMMU_LCD1_M1_0	COMBINER_IRQ(5, 3)
+#define EXYNOS4_IRQ_SYSMMU_TV_M0_0	COMBINER_IRQ(5, 4)
+#define EXYNOS4_IRQ_SYSMMU_MFC_M0_0	COMBINER_IRQ(5, 5)
+#define EXYNOS4_IRQ_SYSMMU_MFC_M1_0	COMBINER_IRQ(5, 6)
+#define EXYNOS4_IRQ_SYSMMU_PCIE_0	COMBINER_IRQ(5, 7)
+
+#define EXYNOS4_IRQ_FIMD0_FIFO		COMBINER_IRQ(11, 0)
+#define EXYNOS4_IRQ_FIMD0_VSYNC		COMBINER_IRQ(11, 1)
+#define EXYNOS4_IRQ_FIMD0_SYSTEM	COMBINER_IRQ(11, 2)
+
+#define EXYNOS4_MAX_COMBINER_NR		16
+
+#define EXYNOS4_IRQ_GPIO1_NR_GROUPS	16
+#define EXYNOS4_IRQ_GPIO2_NR_GROUPS	9
+
+/*
+ * For Compatibility:
+ * the default is for EXYNOS4, and
+ * for exynos5, should be re-mapped at function
+ */
+
+#define IRQ_TIMER0_VIC			EXYNOS4_IRQ_TIMER0_VIC
+#define IRQ_TIMER1_VIC			EXYNOS4_IRQ_TIMER1_VIC
+#define IRQ_TIMER2_VIC			EXYNOS4_IRQ_TIMER2_VIC
+#define IRQ_TIMER3_VIC			EXYNOS4_IRQ_TIMER3_VIC
+#define IRQ_TIMER4_VIC			EXYNOS4_IRQ_TIMER4_VIC
+
+#define IRQ_WDT				EXYNOS4_IRQ_WDT
+#define IRQ_RTC_ALARM			EXYNOS4_IRQ_RTC_ALARM
+#define IRQ_RTC_TIC			EXYNOS4_IRQ_RTC_TIC
+#define IRQ_GPIO_XB			EXYNOS4_IRQ_GPIO_XB
+#define IRQ_GPIO_XA			EXYNOS4_IRQ_GPIO_XA
+
+#define IRQ_IIC				EXYNOS4_IRQ_IIC
+#define IRQ_IIC1			EXYNOS4_IRQ_IIC1
+#define IRQ_IIC3			EXYNOS4_IRQ_IIC3
+#define IRQ_IIC5			EXYNOS4_IRQ_IIC5
+#define IRQ_IIC6			EXYNOS4_IRQ_IIC6
+#define IRQ_IIC7			EXYNOS4_IRQ_IIC7
+
+#define IRQ_USB_HOST			EXYNOS4_IRQ_USB_HOST
+
+#define IRQ_HSMMC0			EXYNOS4_IRQ_HSMMC0
+#define IRQ_HSMMC1			EXYNOS4_IRQ_HSMMC1
+#define IRQ_HSMMC2			EXYNOS4_IRQ_HSMMC2
+#define IRQ_HSMMC3			EXYNOS4_IRQ_HSMMC3
+
+#define IRQ_MIPI_CSIS0			EXYNOS4_IRQ_MIPI_CSIS0
+
+#define IRQ_ONENAND_AUDI		EXYNOS4_IRQ_ONENAND_AUDI
+
+#define IRQ_FIMC0			EXYNOS4_IRQ_FIMC0
+#define IRQ_FIMC1			EXYNOS4_IRQ_FIMC1
+#define IRQ_FIMC2			EXYNOS4_IRQ_FIMC2
+#define IRQ_FIMC3			EXYNOS4_IRQ_FIMC3
+#define IRQ_JPEG			EXYNOS4_IRQ_JPEG
+#define IRQ_2D				EXYNOS4_IRQ_2D
+
+#define IRQ_MIXER			EXYNOS4_IRQ_MIXER
+#define IRQ_HDMI			EXYNOS4_IRQ_HDMI
+#define IRQ_IIC_HDMIPHY			EXYNOS4_IRQ_IIC_HDMIPHY
+#define IRQ_MFC				EXYNOS4_IRQ_MFC
+#define IRQ_SDO				EXYNOS4_IRQ_SDO
+
+#define IRQ_ADC				EXYNOS4_IRQ_ADC0
+#define IRQ_TC				EXYNOS4_IRQ_PEN0
+
+#define IRQ_KEYPAD			EXYNOS4_IRQ_KEYPAD
+#define IRQ_PMU				EXYNOS4_IRQ_PMU
+
+#define IRQ_SYSMMU_MDMA0_0		EXYNOS4_IRQ_SYSMMU_MDMA0_0
+#define IRQ_SYSMMU_SSS_0                EXYNOS4_IRQ_SYSMMU_SSS_0
+#define IRQ_SYSMMU_FIMC0_0              EXYNOS4_IRQ_SYSMMU_FIMC0_0
+#define IRQ_SYSMMU_FIMC1_0              EXYNOS4_IRQ_SYSMMU_FIMC1_0
+#define IRQ_SYSMMU_FIMC2_0              EXYNOS4_IRQ_SYSMMU_FIMC2_0
+#define IRQ_SYSMMU_FIMC3_0              EXYNOS4_IRQ_SYSMMU_FIMC3_0
+#define IRQ_SYSMMU_JPEG_0               EXYNOS4_IRQ_SYSMMU_JPEG_0
+#define IRQ_SYSMMU_2D_0                 EXYNOS4_IRQ_SYSMMU_2D_0
+
+#define IRQ_SYSMMU_ROTATOR_0            EXYNOS4_IRQ_SYSMMU_ROTATOR_0
+#define IRQ_SYSMMU_MDMA1_0              EXYNOS4_IRQ_SYSMMU_MDMA1_0
+#define IRQ_SYSMMU_LCD0_M0_0            EXYNOS4_IRQ_SYSMMU_LCD0_M0_0
+#define IRQ_SYSMMU_LCD1_M1_0            EXYNOS4_IRQ_SYSMMU_LCD1_M1_0
+#define IRQ_SYSMMU_TV_M0_0              EXYNOS4_IRQ_SYSMMU_TV_M0_0
+#define IRQ_SYSMMU_MFC_M0_0             EXYNOS4_IRQ_SYSMMU_MFC_M0_0
+#define IRQ_SYSMMU_MFC_M1_0             EXYNOS4_IRQ_SYSMMU_MFC_M1_0
+#define IRQ_SYSMMU_PCIE_0               EXYNOS4_IRQ_SYSMMU_PCIE_0
+
+#define IRQ_FIMD0_FIFO			EXYNOS4_IRQ_FIMD0_FIFO
+#define IRQ_FIMD0_VSYNC			EXYNOS4_IRQ_FIMD0_VSYNC
+#define IRQ_FIMD0_SYSTEM		EXYNOS4_IRQ_FIMD0_SYSTEM
+
+#define IRQ_GPIO1_NR_GROUPS		EXYNOS4_IRQ_GPIO1_NR_GROUPS
+#define IRQ_GPIO2_NR_GROUPS		EXYNOS4_IRQ_GPIO2_NR_GROUPS
+
+/* For EXYNOS5 SoCs */
+
+#define EXYNOS5_IRQ_MDMA0		IRQ_SPI(33)
+#define EXYNOS5_IRQ_PDMA0		IRQ_SPI(34)
+#define EXYNOS5_IRQ_PDMA1		IRQ_SPI(35)
+#define EXYNOS5_IRQ_TIMER0_VIC		IRQ_SPI(36)
+#define EXYNOS5_IRQ_TIMER1_VIC		IRQ_SPI(37)
+#define EXYNOS5_IRQ_TIMER2_VIC		IRQ_SPI(38)
+#define EXYNOS5_IRQ_TIMER3_VIC		IRQ_SPI(39)
+#define EXYNOS5_IRQ_TIMER4_VIC		IRQ_SPI(40)
+#define EXYNOS5_IRQ_RTIC		IRQ_SPI(41)
+#define EXYNOS5_IRQ_WDT			IRQ_SPI(42)
+#define EXYNOS5_IRQ_RTC_ALARM		IRQ_SPI(43)
+#define EXYNOS5_IRQ_RTC_TIC		IRQ_SPI(44)
+#define EXYNOS5_IRQ_GPIO_XB		IRQ_SPI(45)
+#define EXYNOS5_IRQ_GPIO_XA		IRQ_SPI(46)
+#define EXYNOS5_IRQ_GPIO		IRQ_SPI(47)
+#define EXYNOS5_IRQ_IEM_IEC		IRQ_SPI(48)
+#define EXYNOS5_IRQ_IEM_APC		IRQ_SPI(49)
+#define EXYNOS5_IRQ_GPIO_C2C		IRQ_SPI(50)
+#define EXYNOS5_IRQ_UART0		IRQ_SPI(51)
+#define EXYNOS5_IRQ_UART1		IRQ_SPI(52)
+#define EXYNOS5_IRQ_UART2		IRQ_SPI(53)
+#define EXYNOS5_IRQ_UART3		IRQ_SPI(54)
+#define EXYNOS5_IRQ_UART4		IRQ_SPI(55)
+#define EXYNOS5_IRQ_IIC			IRQ_SPI(56)
+#define EXYNOS5_IRQ_IIC1		IRQ_SPI(57)
+#define EXYNOS5_IRQ_IIC2		IRQ_SPI(58)
+#define EXYNOS5_IRQ_IIC3		IRQ_SPI(59)
+#define EXYNOS5_IRQ_IIC4		IRQ_SPI(60)
+#define EXYNOS5_IRQ_IIC5		IRQ_SPI(61)
+#define EXYNOS5_IRQ_IIC6		IRQ_SPI(62)
+#define EXYNOS5_IRQ_IIC7		IRQ_SPI(63)
+#define EXYNOS5_IRQ_IIC_HDMIPHY		IRQ_SPI(64)
+#define EXYNOS5_IRQ_TMU			IRQ_SPI(65)
+#define EXYNOS5_IRQ_FIQ_0		IRQ_SPI(66)
+#define EXYNOS5_IRQ_FIQ_1		IRQ_SPI(67)
+#define EXYNOS5_IRQ_SPI0		IRQ_SPI(68)
+#define EXYNOS5_IRQ_SPI1		IRQ_SPI(69)
+#define EXYNOS5_IRQ_SPI2		IRQ_SPI(70)
+#define EXYNOS5_IRQ_USB_HOST		IRQ_SPI(71)
+#define EXYNOS5_IRQ_USB3_DRD		IRQ_SPI(72)
+#define EXYNOS5_IRQ_MIPI_HSI		IRQ_SPI(73)
+#define EXYNOS5_IRQ_USB_HSOTG		IRQ_SPI(74)
+#define EXYNOS5_IRQ_HSMMC0		IRQ_SPI(75)
+#define EXYNOS5_IRQ_HSMMC1		IRQ_SPI(76)
+#define EXYNOS5_IRQ_HSMMC2		IRQ_SPI(77)
+#define EXYNOS5_IRQ_HSMMC3		IRQ_SPI(78)
+#define EXYNOS5_IRQ_MIPICSI0		IRQ_SPI(79)
+#define EXYNOS5_IRQ_MIPICSI1		IRQ_SPI(80)
+#define EXYNOS5_IRQ_EFNFCON_DMA_ABORT	IRQ_SPI(81)
+#define EXYNOS5_IRQ_MIPIDSI0		IRQ_SPI(82)
+#define EXYNOS5_IRQ_ROTATOR		IRQ_SPI(84)
+#define EXYNOS5_IRQ_GSC0		IRQ_SPI(85)
+#define EXYNOS5_IRQ_GSC1		IRQ_SPI(86)
+#define EXYNOS5_IRQ_GSC2		IRQ_SPI(87)
+#define EXYNOS5_IRQ_GSC3		IRQ_SPI(88)
+#define EXYNOS5_IRQ_JPEG		IRQ_SPI(89)
+#define EXYNOS5_IRQ_EFNFCON_DMA		IRQ_SPI(90)
+#define EXYNOS5_IRQ_2D			IRQ_SPI(91)
+#define EXYNOS5_IRQ_SFMC0		IRQ_SPI(92)
+#define EXYNOS5_IRQ_SFMC1		IRQ_SPI(93)
+#define EXYNOS5_IRQ_MIXER		IRQ_SPI(94)
+#define EXYNOS5_IRQ_HDMI		IRQ_SPI(95)
+#define EXYNOS5_IRQ_MFC			IRQ_SPI(96)
+#define EXYNOS5_IRQ_AUDIO_SS		IRQ_SPI(97)
+#define EXYNOS5_IRQ_I2S0		IRQ_SPI(98)
+#define EXYNOS5_IRQ_I2S1		IRQ_SPI(99)
+#define EXYNOS5_IRQ_I2S2		IRQ_SPI(100)
+#define EXYNOS5_IRQ_AC97		IRQ_SPI(101)
+#define EXYNOS5_IRQ_PCM0		IRQ_SPI(102)
+#define EXYNOS5_IRQ_PCM1		IRQ_SPI(103)
+#define EXYNOS5_IRQ_PCM2		IRQ_SPI(104)
+#define EXYNOS5_IRQ_SPDIF		IRQ_SPI(105)
+#define EXYNOS5_IRQ_ADC0		IRQ_SPI(106)
+
+#define EXYNOS5_IRQ_SATA_PHY		IRQ_SPI(108)
+#define EXYNOS5_IRQ_SATA_PMEMREQ	IRQ_SPI(109)
+#define EXYNOS5_IRQ_CAM_C		IRQ_SPI(110)
+#define EXYNOS5_IRQ_EAGLE_PMU		IRQ_SPI(111)
+#define EXYNOS5_IRQ_INTFEEDCTRL_SSS	IRQ_SPI(112)
+#define EXYNOS5_IRQ_DP1_INTP1		IRQ_SPI(113)
+#define EXYNOS5_IRQ_CEC			IRQ_SPI(114)
+#define EXYNOS5_IRQ_SATA		IRQ_SPI(115)
+#define EXYNOS5_IRQ_NFCON		IRQ_SPI(116)
+
+#define EXYNOS5_IRQ_MMC44		IRQ_SPI(123)
+#define EXYNOS5_IRQ_MDMA1		IRQ_SPI(124)
+#define EXYNOS5_IRQ_FIMC_LITE0		IRQ_SPI(125)
+#define EXYNOS5_IRQ_FIMC_LITE1		IRQ_SPI(126)
+#define EXYNOS5_IRQ_RP_TIMER		IRQ_SPI(127)
+
+#define EXYNOS5_IRQ_PMU			COMBINER_IRQ(1, 2)
+#define EXYNOS5_IRQ_PMU_CPU1		COMBINER_IRQ(1, 6)
+
+#define EXYNOS5_IRQ_SYSMMU_GSC0_0	COMBINER_IRQ(2, 0)
+#define EXYNOS5_IRQ_SYSMMU_GSC0_1	COMBINER_IRQ(2, 1)
+#define EXYNOS5_IRQ_SYSMMU_GSC1_0	COMBINER_IRQ(2, 2)
+#define EXYNOS5_IRQ_SYSMMU_GSC1_1	COMBINER_IRQ(2, 3)
+#define EXYNOS5_IRQ_SYSMMU_GSC2_0	COMBINER_IRQ(2, 4)
+#define EXYNOS5_IRQ_SYSMMU_GSC2_1	COMBINER_IRQ(2, 5)
+#define EXYNOS5_IRQ_SYSMMU_GSC3_0	COMBINER_IRQ(2, 6)
+#define EXYNOS5_IRQ_SYSMMU_GSC3_1	COMBINER_IRQ(2, 7)
+
+#define EXYNOS5_IRQ_SYSMMU_FIMD1_0	COMBINER_IRQ(3, 2)
+#define EXYNOS5_IRQ_SYSMMU_FIMD1_1	COMBINER_IRQ(3, 3)
+#define EXYNOS5_IRQ_SYSMMU_LITE0_0	COMBINER_IRQ(3, 4)
+#define EXYNOS5_IRQ_SYSMMU_LITE0_1	COMBINER_IRQ(3, 5)
+#define EXYNOS5_IRQ_SYSMMU_SCALERPISP_0	COMBINER_IRQ(3, 6)
+#define EXYNOS5_IRQ_SYSMMU_SCALERPISP_1	COMBINER_IRQ(3, 7)
+
+#define EXYNOS5_IRQ_SYSMMU_ROTATOR_0	COMBINER_IRQ(4, 0)
+#define EXYNOS5_IRQ_SYSMMU_ROTATOR_1	COMBINER_IRQ(4, 1)
+#define EXYNOS5_IRQ_SYSMMU_JPEG_0	COMBINER_IRQ(4, 2)
+#define EXYNOS5_IRQ_SYSMMU_JPEG_1	COMBINER_IRQ(4, 3)
+
+#define EXYNOS5_IRQ_SYSMMU_FD_0		COMBINER_IRQ(5, 0)
+#define EXYNOS5_IRQ_SYSMMU_FD_1		COMBINER_IRQ(5, 1)
+#define EXYNOS5_IRQ_SYSMMU_SCALERCISP_0	COMBINER_IRQ(5, 2)
+#define EXYNOS5_IRQ_SYSMMU_SCALERCISP_1	COMBINER_IRQ(5, 3)
+#define EXYNOS5_IRQ_SYSMMU_MCUISP_0	COMBINER_IRQ(5, 4)
+#define EXYNOS5_IRQ_SYSMMU_MCUISP_1	COMBINER_IRQ(5, 5)
+#define EXYNOS5_IRQ_SYSMMU_3DNR_0	COMBINER_IRQ(5, 6)
+#define EXYNOS5_IRQ_SYSMMU_3DNR_1	COMBINER_IRQ(5, 7)
+
+#define EXYNOS5_IRQ_SYSMMU_ARM_0	COMBINER_IRQ(6, 0)
+#define EXYNOS5_IRQ_SYSMMU_ARM_1	COMBINER_IRQ(6, 1)
+#define EXYNOS5_IRQ_SYSMMU_MFC_L_0	COMBINER_IRQ(6, 2)
+#define EXYNOS5_IRQ_SYSMMU_MFC_L_1	COMBINER_IRQ(6, 3)
+#define EXYNOS5_IRQ_SYSMMU_RTIC_0	COMBINER_IRQ(6, 4)
+#define EXYNOS5_IRQ_SYSMMU_RTIC_1	COMBINER_IRQ(6, 5)
+#define EXYNOS5_IRQ_SYSMMU_SSS_0	COMBINER_IRQ(6, 6)
+#define EXYNOS5_IRQ_SYSMMU_SSS_1	COMBINER_IRQ(6, 7)
+
+#define EXYNOS5_IRQ_SYSMMU_MDMA0_0	COMBINER_IRQ(7, 0)
+#define EXYNOS5_IRQ_SYSMMU_MDMA0_1	COMBINER_IRQ(7, 1)
+#define EXYNOS5_IRQ_SYSMMU_MDMA1_0	COMBINER_IRQ(7, 2)
+#define EXYNOS5_IRQ_SYSMMU_MDMA1_1	COMBINER_IRQ(7, 3)
+#define EXYNOS5_IRQ_SYSMMU_TV_0		COMBINER_IRQ(7, 4)
+#define EXYNOS5_IRQ_SYSMMU_TV_1		COMBINER_IRQ(7, 5)
+#define EXYNOS5_IRQ_SYSMMU_GPSX_0	COMBINER_IRQ(7, 6)
+#define EXYNOS5_IRQ_SYSMMU_GPSX_1	COMBINER_IRQ(7, 7)
+
+#define EXYNOS5_IRQ_SYSMMU_MFC_R_0	COMBINER_IRQ(8, 5)
+#define EXYNOS5_IRQ_SYSMMU_MFC_R_1	COMBINER_IRQ(8, 6)
+
+#define EXYNOS5_IRQ_SYSMMU_DIS1_0	COMBINER_IRQ(9, 4)
+#define EXYNOS5_IRQ_SYSMMU_DIS1_1	COMBINER_IRQ(9, 5)
+
+#define EXYNOS5_IRQ_DP			COMBINER_IRQ(10, 3)
+#define EXYNOS5_IRQ_SYSMMU_DIS0_0	COMBINER_IRQ(10, 4)
+#define EXYNOS5_IRQ_SYSMMU_DIS0_1	COMBINER_IRQ(10, 5)
+#define EXYNOS5_IRQ_SYSMMU_ISP_0	COMBINER_IRQ(10, 6)
+#define EXYNOS5_IRQ_SYSMMU_ISP_1	COMBINER_IRQ(10, 7)
+
+#define EXYNOS5_IRQ_SYSMMU_ODC_0	COMBINER_IRQ(11, 0)
+#define EXYNOS5_IRQ_SYSMMU_ODC_1	COMBINER_IRQ(11, 1)
+#define EXYNOS5_IRQ_SYSMMU_DRC_0	COMBINER_IRQ(11, 6)
+#define EXYNOS5_IRQ_SYSMMU_DRC_1	COMBINER_IRQ(11, 7)
+
+#define EXYNOS5_IRQ_FIMD1_FIFO		COMBINER_IRQ(18, 4)
+#define EXYNOS5_IRQ_FIMD1_VSYNC		COMBINER_IRQ(18, 5)
+#define EXYNOS5_IRQ_FIMD1_SYSTEM	COMBINER_IRQ(18, 6)
+
+#define EXYNOS5_IRQ_EINT0		COMBINER_IRQ(23, 0)
+#define EXYNOS5_IRQ_MCT_L0		COMBINER_IRQ(23, 1)
+#define EXYNOS5_IRQ_MCT_L1		COMBINER_IRQ(23, 2)
+#define EXYNOS5_IRQ_MCT_G0		COMBINER_IRQ(23, 3)
+#define EXYNOS5_IRQ_MCT_G1		COMBINER_IRQ(23, 4)
+#define EXYNOS5_IRQ_MCT_G2		COMBINER_IRQ(23, 5)
+#define EXYNOS5_IRQ_MCT_G3		COMBINER_IRQ(23, 6)
+
+#define EXYNOS5_IRQ_EINT1		COMBINER_IRQ(24, 0)
+#define EXYNOS5_IRQ_SYSMMU_LITE1_0	COMBINER_IRQ(24, 1)
+#define EXYNOS5_IRQ_SYSMMU_LITE1_1	COMBINER_IRQ(24, 2)
+#define EXYNOS5_IRQ_SYSMMU_2D_0		COMBINER_IRQ(24, 5)
+#define EXYNOS5_IRQ_SYSMMU_2D_1		COMBINER_IRQ(24, 6)
+
+#define EXYNOS5_IRQ_EINT2		COMBINER_IRQ(25, 0)
+#define EXYNOS5_IRQ_EINT3		COMBINER_IRQ(25, 1)
+
+#define EXYNOS5_IRQ_EINT4		COMBINER_IRQ(26, 0)
+#define EXYNOS5_IRQ_EINT5		COMBINER_IRQ(26, 1)
+
+#define EXYNOS5_IRQ_EINT6		COMBINER_IRQ(27, 0)
+#define EXYNOS5_IRQ_EINT7		COMBINER_IRQ(27, 1)
+
+#define EXYNOS5_IRQ_EINT8		COMBINER_IRQ(28, 0)
+#define EXYNOS5_IRQ_EINT9		COMBINER_IRQ(28, 1)
+
+#define EXYNOS5_IRQ_EINT10		COMBINER_IRQ(29, 0)
+#define EXYNOS5_IRQ_EINT11		COMBINER_IRQ(29, 1)
+
+#define EXYNOS5_IRQ_EINT12		COMBINER_IRQ(30, 0)
+#define EXYNOS5_IRQ_EINT13		COMBINER_IRQ(30, 1)
+
+#define EXYNOS5_IRQ_EINT14		COMBINER_IRQ(31, 0)
+#define EXYNOS5_IRQ_EINT15		COMBINER_IRQ(31, 1)
+
+#define EXYNOS5_MAX_COMBINER_NR		32
+
+#define EXYNOS5_IRQ_GPIO1_NR_GROUPS	13
+#define EXYNOS5_IRQ_GPIO2_NR_GROUPS	9
+#define EXYNOS5_IRQ_GPIO3_NR_GROUPS	5
+#define EXYNOS5_IRQ_GPIO4_NR_GROUPS	1
+
+#define MAX_COMBINER_NR			(EXYNOS4_MAX_COMBINER_NR > EXYNOS5_MAX_COMBINER_NR ? \
+					EXYNOS4_MAX_COMBINER_NR : EXYNOS5_MAX_COMBINER_NR)
+
+#define S5P_EINT_BASE1			COMBINER_IRQ(MAX_COMBINER_NR, 0)
+#define S5P_EINT_BASE2			(S5P_EINT_BASE1 + 16)
+#define S5P_GPIOINT_BASE		(S5P_EINT_BASE1 + 32)
+#define IRQ_GPIO_END			(S5P_GPIOINT_BASE + S5P_GPIOINT_COUNT)
+#define IRQ_TIMER_BASE			(IRQ_GPIO_END + 64)
 
 /* Set the default NR_IRQS */
-#define NR_IRQS			(IRQ_TIMER_BASE + IRQ_TIMER_COUNT)
+
+#define NR_IRQS				(IRQ_TIMER_BASE + IRQ_TIMER_COUNT)
 
 #endif /* __ASM_ARCH_IRQS_H */
diff --git a/arch/arm/mach-exynos/include/mach/map.h b/arch/arm/mach-exynos/include/mach/map.h
index 609127df9b02..024d38ff1718 100644
--- a/arch/arm/mach-exynos/include/mach/map.h
+++ b/arch/arm/mach-exynos/include/mach/map.h
@@ -25,6 +25,7 @@
 
 #define EXYNOS4_PA_SYSRAM0		0x02025000
 #define EXYNOS4_PA_SYSRAM1		0x02020000
+#define EXYNOS5_PA_SYSRAM		0x02020000
 
 #define EXYNOS4_PA_FIMC0		0x11800000
 #define EXYNOS4_PA_FIMC1		0x11810000
@@ -48,14 +49,23 @@
 #define EXYNOS4_PA_ONENAND		0x0C000000
 #define EXYNOS4_PA_ONENAND_DMA		0x0C600000
 
-#define EXYNOS4_PA_CHIPID		0x10000000
+#define EXYNOS_PA_CHIPID		0x10000000
 
 #define EXYNOS4_PA_SYSCON		0x10010000
+#define EXYNOS5_PA_SYSCON		0x10050100
+
 #define EXYNOS4_PA_PMU			0x10020000
+#define EXYNOS5_PA_PMU			0x10040000
+
 #define EXYNOS4_PA_CMU			0x10030000
+#define EXYNOS5_PA_CMU			0x10010000
 
 #define EXYNOS4_PA_SYSTIMER		0x10050000
+#define EXYNOS5_PA_SYSTIMER		0x101C0000
+
 #define EXYNOS4_PA_WATCHDOG		0x10060000
+#define EXYNOS5_PA_WATCHDOG		0x101D0000
+
 #define EXYNOS4_PA_RTC			0x10070000
 
 #define EXYNOS4_PA_KEYPAD		0x100A0000
@@ -64,9 +74,12 @@
 #define EXYNOS4_PA_DMC1			0x10410000
 
 #define EXYNOS4_PA_COMBINER		0x10440000
+#define EXYNOS5_PA_COMBINER		0x10440000
 
 #define EXYNOS4_PA_GIC_CPU		0x10480000
 #define EXYNOS4_PA_GIC_DIST		0x10490000
+#define EXYNOS5_PA_GIC_CPU		0x10480000
+#define EXYNOS5_PA_GIC_DIST		0x10490000
 
 #define EXYNOS4_PA_COREPERI		0x10500000
 #define EXYNOS4_PA_TWD			0x10500600
@@ -97,10 +110,13 @@
 #define EXYNOS4_PA_SPI1			0x13930000
 #define EXYNOS4_PA_SPI2			0x13940000
 
-
 #define EXYNOS4_PA_GPIO1		0x11400000
 #define EXYNOS4_PA_GPIO2		0x11000000
 #define EXYNOS4_PA_GPIO3		0x03860000
+#define EXYNOS5_PA_GPIO1		0x11400000
+#define EXYNOS5_PA_GPIO2		0x13400000
+#define EXYNOS5_PA_GPIO3		0x10D10000
+#define EXYNOS5_PA_GPIO4		0x03860000
 
 #define EXYNOS4_PA_MIPI_CSIS0		0x11880000
 #define EXYNOS4_PA_MIPI_CSIS1		0x11890000
@@ -115,6 +131,7 @@
 #define EXYNOS4_PA_SATAPHY_CTRL		0x126B0000
 
 #define EXYNOS4_PA_SROMC		0x12570000
+#define EXYNOS5_PA_SROMC		0x12250000
 
 #define EXYNOS4_PA_EHCI			0x12580000
 #define EXYNOS4_PA_OHCI			0x12590000
@@ -122,6 +139,7 @@
 #define EXYNOS4_PA_MFC			0x13400000
 
 #define EXYNOS4_PA_UART			0x13800000
+#define EXYNOS5_PA_UART			0x12C00000
 
 #define EXYNOS4_PA_VP			0x12C00000
 #define EXYNOS4_PA_MIXER		0x12C10000
@@ -130,6 +148,7 @@
 #define EXYNOS4_PA_IIC_HDMIPHY		0x138E0000
 
 #define EXYNOS4_PA_IIC(x)		(0x13860000 + ((x) * 0x10000))
+#define EXYNOS5_PA_IIC(x)		(0x12C60000 + ((x) * 0x10000))
 
 #define EXYNOS4_PA_ADC			0x13910000
 #define EXYNOS4_PA_ADC1			0x13911000
@@ -139,8 +158,10 @@
 #define EXYNOS4_PA_SPDIF		0x139B0000
 
 #define EXYNOS4_PA_TIMER		0x139D0000
+#define EXYNOS5_PA_TIMER		0x12DD0000
 
 #define EXYNOS4_PA_SDRAM		0x40000000
+#define EXYNOS5_PA_SDRAM		0x40000000
 
 /* Compatibiltiy Defines */
 
@@ -158,7 +179,6 @@
 #define S3C_PA_IIC7			EXYNOS4_PA_IIC(7)
 #define S3C_PA_RTC			EXYNOS4_PA_RTC
 #define S3C_PA_WDT			EXYNOS4_PA_WATCHDOG
-#define S3C_PA_UART			EXYNOS4_PA_UART
 #define S3C_PA_SPI0			EXYNOS4_PA_SPI0
 #define S3C_PA_SPI1			EXYNOS4_PA_SPI1
 #define S3C_PA_SPI2			EXYNOS4_PA_SPI2
@@ -189,15 +209,18 @@
 
 /* Compatibility UART */
 
-#define S3C_VA_UARTx(x)			(S3C_VA_UART + ((x) * S3C_UART_OFFSET))
+#define EXYNOS4_PA_UART0		0x13800000
+#define EXYNOS4_PA_UART1		0x13810000
+#define EXYNOS4_PA_UART2		0x13820000
+#define EXYNOS4_PA_UART3		0x13830000
+#define EXYNOS4_SZ_UART			SZ_256
 
-#define S5P_PA_UART(x)			(EXYNOS4_PA_UART + ((x) * S3C_UART_OFFSET))
-#define S5P_PA_UART0			S5P_PA_UART(0)
-#define S5P_PA_UART1			S5P_PA_UART(1)
-#define S5P_PA_UART2			S5P_PA_UART(2)
-#define S5P_PA_UART3			S5P_PA_UART(3)
-#define S5P_PA_UART4			S5P_PA_UART(4)
+#define EXYNOS5_PA_UART0		0x12C00000
+#define EXYNOS5_PA_UART1		0x12C10000
+#define EXYNOS5_PA_UART2		0x12C20000
+#define EXYNOS5_PA_UART3		0x12C30000
+#define EXYNOS5_SZ_UART			SZ_256
 
-#define S5P_SZ_UART			SZ_256
+#define S3C_VA_UARTx(x)			(S3C_VA_UART + ((x) * S3C_UART_OFFSET))
 
 #endif /* __ASM_ARCH_MAP_H */
diff --git a/arch/arm/mach-exynos/include/mach/regs-clock.h b/arch/arm/mach-exynos/include/mach/regs-clock.h
index 1e4abd64a547..e141c1fd68d8 100644
--- a/arch/arm/mach-exynos/include/mach/regs-clock.h
+++ b/arch/arm/mach-exynos/include/mach/regs-clock.h
@@ -253,6 +253,68 @@
 #define EXYNOS4_CLKDIV_CAM1_JPEG_SHIFT		(0)
 #define EXYNOS4_CLKDIV_CAM1_JPEG_MASK		(0xf << EXYNOS4_CLKDIV_CAM1_JPEG_SHIFT)
 
+/* For EXYNOS5250 */
+
+#define EXYNOS5_APLL_CON0			EXYNOS_CLKREG(0x00100)
+#define EXYNOS5_CLKSRC_CPU			EXYNOS_CLKREG(0x00200)
+#define EXYNOS5_CLKDIV_CPU0			EXYNOS_CLKREG(0x00500)
+#define EXYNOS5_MPLL_CON0			EXYNOS_CLKREG(0x04100)
+#define EXYNOS5_CLKSRC_CORE1			EXYNOS_CLKREG(0x04204)
+
+#define EXYNOS5_CLKGATE_IP_CORE			EXYNOS_CLKREG(0x04900)
+
+#define EXYNOS5_CLKDIV_ACP			EXYNOS_CLKREG(0x08500)
+
+#define EXYNOS5_CLKSRC_TOP2			EXYNOS_CLKREG(0x10218)
+#define EXYNOS5_EPLL_CON0			EXYNOS_CLKREG(0x10130)
+#define EXYNOS5_EPLL_CON1			EXYNOS_CLKREG(0x10134)
+#define EXYNOS5_VPLL_CON0			EXYNOS_CLKREG(0x10140)
+#define EXYNOS5_VPLL_CON1			EXYNOS_CLKREG(0x10144)
+#define EXYNOS5_CPLL_CON0			EXYNOS_CLKREG(0x10120)
+
+#define EXYNOS5_CLKSRC_TOP0			EXYNOS_CLKREG(0x10210)
+#define EXYNOS5_CLKSRC_TOP3			EXYNOS_CLKREG(0x1021C)
+#define EXYNOS5_CLKSRC_GSCL			EXYNOS_CLKREG(0x10220)
+#define EXYNOS5_CLKSRC_DISP1_0			EXYNOS_CLKREG(0x1022C)
+#define EXYNOS5_CLKSRC_FSYS			EXYNOS_CLKREG(0x10244)
+#define EXYNOS5_CLKSRC_PERIC0			EXYNOS_CLKREG(0x10250)
+
+#define EXYNOS5_CLKSRC_MASK_TOP			EXYNOS_CLKREG(0x10310)
+#define EXYNOS5_CLKSRC_MASK_GSCL		EXYNOS_CLKREG(0x10320)
+#define EXYNOS5_CLKSRC_MASK_DISP1_0		EXYNOS_CLKREG(0x1032C)
+#define EXYNOS5_CLKSRC_MASK_FSYS		EXYNOS_CLKREG(0x10340)
+#define EXYNOS5_CLKSRC_MASK_PERIC0		EXYNOS_CLKREG(0x10350)
+
+#define EXYNOS5_CLKDIV_TOP0			EXYNOS_CLKREG(0x10510)
+#define EXYNOS5_CLKDIV_TOP1			EXYNOS_CLKREG(0x10514)
+#define EXYNOS5_CLKDIV_GSCL			EXYNOS_CLKREG(0x10520)
+#define EXYNOS5_CLKDIV_DISP1_0			EXYNOS_CLKREG(0x1052C)
+#define EXYNOS5_CLKDIV_GEN			EXYNOS_CLKREG(0x1053C)
+#define EXYNOS5_CLKDIV_FSYS0			EXYNOS_CLKREG(0x10548)
+#define EXYNOS5_CLKDIV_FSYS1			EXYNOS_CLKREG(0x1054C)
+#define EXYNOS5_CLKDIV_FSYS2			EXYNOS_CLKREG(0x10550)
+#define EXYNOS5_CLKDIV_FSYS3			EXYNOS_CLKREG(0x10554)
+#define EXYNOS5_CLKDIV_PERIC0			EXYNOS_CLKREG(0x10558)
+
+#define EXYNOS5_CLKGATE_IP_ACP			EXYNOS_CLKREG(0x08800)
+#define EXYNOS5_CLKGATE_IP_GSCL			EXYNOS_CLKREG(0x10920)
+#define EXYNOS5_CLKGATE_IP_DISP1		EXYNOS_CLKREG(0x10928)
+#define EXYNOS5_CLKGATE_IP_MFC			EXYNOS_CLKREG(0x1092C)
+#define EXYNOS5_CLKGATE_IP_GEN			EXYNOS_CLKREG(0x10934)
+#define EXYNOS5_CLKGATE_IP_FSYS			EXYNOS_CLKREG(0x10944)
+#define EXYNOS5_CLKGATE_IP_GPS			EXYNOS_CLKREG(0x1094C)
+#define EXYNOS5_CLKGATE_IP_PERIC		EXYNOS_CLKREG(0x10950)
+#define EXYNOS5_CLKGATE_IP_PERIS		EXYNOS_CLKREG(0x10960)
+#define EXYNOS5_CLKGATE_BLOCK			EXYNOS_CLKREG(0x10980)
+
+#define EXYNOS5_BPLL_CON0			EXYNOS_CLKREG(0x20110)
+#define EXYNOS5_CLKSRC_CDREX			EXYNOS_CLKREG(0x20200)
+#define EXYNOS5_CLKDIV_CDREX			EXYNOS_CLKREG(0x20500)
+
+#define EXYNOS5_EPLL_LOCK			EXYNOS_CLKREG(0x10030)
+
+#define EXYNOS5_EPLLCON0_LOCKED_SHIFT		(29)
+
 /* Compatibility defines and inclusion */
 
 #include <mach/regs-pmu.h>
diff --git a/arch/arm/mach-exynos/include/mach/regs-gpio.h b/arch/arm/mach-exynos/include/mach/regs-gpio.h
index 1401b21663a5..e4b5b60dcb85 100644
--- a/arch/arm/mach-exynos/include/mach/regs-gpio.h
+++ b/arch/arm/mach-exynos/include/mach/regs-gpio.h
@@ -16,6 +16,15 @@
 #include <mach/map.h>
 #include <mach/irqs.h>
 
+#define EINT_REG_NR(x)			(EINT_OFFSET(x) >> 3)
+#define EINT_CON(b, x)			(b + 0xE00 + (EINT_REG_NR(x) * 4))
+#define EINT_FLTCON(b, x)		(b + 0xE80 + (EINT_REG_NR(x) * 4))
+#define EINT_MASK(b, x)			(b + 0xF00 + (EINT_REG_NR(x) * 4))
+#define EINT_PEND(b, x)			(b + 0xF40 + (EINT_REG_NR(x) * 4))
+
+#define EINT_OFFSET_BIT(x)		(1 << (EINT_OFFSET(x) & 0x7))
+
+/* compatibility for plat-s5p/irq-pm.c */
 #define EXYNOS4_EINT40CON		(S5P_VA_GPIO2 + 0xE00)
 #define S5P_EINT_CON(x)			(EXYNOS4_EINT40CON + ((x) * 0x4))
 
@@ -28,15 +37,4 @@
 #define EXYNOS4_EINT40PEND		(S5P_VA_GPIO2 + 0xF40)
 #define S5P_EINT_PEND(x)		(EXYNOS4_EINT40PEND + ((x) * 0x4))
 
-#define EINT_REG_NR(x)			(EINT_OFFSET(x) >> 3)
-
-#define eint_irq_to_bit(irq)		(1 << (EINT_OFFSET(irq) & 0x7))
-
-#define EINT_MODE			S3C_GPIO_SFN(0xf)
-
-#define EINT_GPIO_0(x)			EXYNOS4_GPX0(x)
-#define EINT_GPIO_1(x)			EXYNOS4_GPX1(x)
-#define EINT_GPIO_2(x)			EXYNOS4_GPX2(x)
-#define EINT_GPIO_3(x)			EXYNOS4_GPX3(x)
-
 #endif /* __ASM_ARCH_REGS_GPIO_H */
diff --git a/arch/arm/mach-exynos/include/mach/regs-pmu.h b/arch/arm/mach-exynos/include/mach/regs-pmu.h
index 4fff8e938fec..4c53f38b5a9e 100644
--- a/arch/arm/mach-exynos/include/mach/regs-pmu.h
+++ b/arch/arm/mach-exynos/include/mach/regs-pmu.h
@@ -31,6 +31,7 @@
 #define S5P_USE_STANDBYWFE_ISP_ARM		(1 << 26)
 
 #define S5P_SWRESET				S5P_PMUREG(0x0400)
+#define EXYNOS_SWRESET				S5P_PMUREG(0x0400)
 
 #define S5P_WAKEUP_STAT				S5P_PMUREG(0x0600)
 #define S5P_EINT_WAKEUP_MASK			S5P_PMUREG(0x0604)
diff --git a/arch/arm/mach-exynos/include/mach/uncompress.h b/arch/arm/mach-exynos/include/mach/uncompress.h
index 21d97bcd9acb..2979995d5a6a 100644
--- a/arch/arm/mach-exynos/include/mach/uncompress.h
+++ b/arch/arm/mach-exynos/include/mach/uncompress.h
@@ -1,9 +1,8 @@
-/* linux/arch/arm/mach-exynos4/include/mach/uncompress.h
- *
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
+/*
+ * Copyright (c) 2010-2012 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
- * EXYNOS4 - uncompress code
+ * EXYNOS - uncompress code
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -13,12 +12,35 @@
 #ifndef __ASM_ARCH_UNCOMPRESS_H
 #define __ASM_ARCH_UNCOMPRESS_H __FILE__
 
+#include <asm/mach-types.h>
+
 #include <mach/map.h>
+
+volatile u8 *uart_base;
+
 #include <plat/uncompress.h>
 
+static unsigned int __raw_readl(unsigned int ptr)
+{
+	return *((volatile unsigned int *)ptr);
+}
+
 static void arch_detect_cpu(void)
 {
-	/* we do not need to do any cpu detection here at the moment. */
+	u32 chip_id = __raw_readl(EXYNOS_PA_CHIPID);
+
+	/*
+	 * product_id is bits 31:12
+	 *    bits 23:20 describe the exynosX family
+	 *
+	 */
+	chip_id >>= 20;
+	chip_id &= 0xf;
+
+	if (chip_id == 0x5)
+		uart_base = (volatile u8 *)EXYNOS5_PA_UART + (S3C_UART_OFFSET * CONFIG_S3C_LOWLEVEL_UART_PORT);
+	else
+		uart_base = (volatile u8 *)EXYNOS4_PA_UART + (S3C_UART_OFFSET * CONFIG_S3C_LOWLEVEL_UART_PORT);
 
 	/*
 	 * For preventing FIFO overrun or infinite loop of UART console,
diff --git a/arch/arm/mach-exynos/mach-exynos4-dt.c b/arch/arm/mach-exynos/mach-exynos4-dt.c
index e6b02fdf1b09..8245f1c761d9 100644
--- a/arch/arm/mach-exynos/mach-exynos4-dt.c
+++ b/arch/arm/mach-exynos/mach-exynos4-dt.c
@@ -37,13 +37,13 @@
  * data from the device tree.
  */
 static const struct of_dev_auxdata exynos4210_auxdata_lookup[] __initconst = {
-	OF_DEV_AUXDATA("samsung,exynos4210-uart", S5P_PA_UART0,
+	OF_DEV_AUXDATA("samsung,exynos4210-uart", EXYNOS4_PA_UART0,
 				"exynos4210-uart.0", NULL),
-	OF_DEV_AUXDATA("samsung,exynos4210-uart", S5P_PA_UART1,
+	OF_DEV_AUXDATA("samsung,exynos4210-uart", EXYNOS4_PA_UART1,
 				"exynos4210-uart.1", NULL),
-	OF_DEV_AUXDATA("samsung,exynos4210-uart", S5P_PA_UART2,
+	OF_DEV_AUXDATA("samsung,exynos4210-uart", EXYNOS4_PA_UART2,
 				"exynos4210-uart.2", NULL),
-	OF_DEV_AUXDATA("samsung,exynos4210-uart", S5P_PA_UART3,
+	OF_DEV_AUXDATA("samsung,exynos4210-uart", EXYNOS4_PA_UART3,
 				"exynos4210-uart.3", NULL),
 	OF_DEV_AUXDATA("samsung,exynos4210-sdhci", EXYNOS4_PA_HSMMC(0),
 				"exynos4-sdhci.0", NULL),
diff --git a/arch/arm/mach-exynos/mach-exynos5-dt.c b/arch/arm/mach-exynos/mach-exynos5-dt.c
new file mode 100644
index 000000000000..0d26f50081ad
--- /dev/null
+++ b/arch/arm/mach-exynos/mach-exynos5-dt.c
@@ -0,0 +1,78 @@
+/*
+ * SAMSUNG EXYNOS5250 Flattened Device Tree enabled machine
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/of_platform.h>
+#include <linux/serial_core.h>
+
+#include <asm/mach/arch.h>
+#include <asm/hardware/gic.h>
+#include <mach/map.h>
+
+#include <plat/cpu.h>
+#include <plat/regs-serial.h>
+
+#include "common.h"
+
+/*
+ * The following lookup table is used to override device names when devices
+ * are registered from device tree. This is temporarily added to enable
+ * device tree support addition for the EXYNOS5 architecture.
+ *
+ * For drivers that require platform data to be provided from the machine
+ * file, a platform data pointer can also be supplied along with the
+ * devices names. Usually, the platform data elements that cannot be parsed
+ * from the device tree by the drivers (example: function pointers) are
+ * supplied. But it should be noted that this is a temporary mechanism and
+ * at some point, the drivers should be capable of parsing all the platform
+ * data from the device tree.
+ */
+static const struct of_dev_auxdata exynos5250_auxdata_lookup[] __initconst = {
+	OF_DEV_AUXDATA("samsung,exynos4210-uart", EXYNOS5_PA_UART0,
+				"exynos4210-uart.0", NULL),
+	OF_DEV_AUXDATA("samsung,exynos4210-uart", EXYNOS5_PA_UART1,
+				"exynos4210-uart.1", NULL),
+	OF_DEV_AUXDATA("samsung,exynos4210-uart", EXYNOS5_PA_UART2,
+				"exynos4210-uart.2", NULL),
+	OF_DEV_AUXDATA("samsung,exynos4210-uart", EXYNOS5_PA_UART3,
+				"exynos4210-uart.3", NULL),
+	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA0, "dma-pl330.0", NULL),
+	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA1, "dma-pl330.1", NULL),
+	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA1, "dma-pl330.2", NULL),
+	{},
+};
+
+static void __init exynos5250_dt_map_io(void)
+{
+	exynos_init_io(NULL, 0);
+	s3c24xx_init_clocks(24000000);
+}
+
+static void __init exynos5250_dt_machine_init(void)
+{
+	of_platform_populate(NULL, of_default_bus_match_table,
+				exynos5250_auxdata_lookup, NULL);
+}
+
+static char const *exynos5250_dt_compat[] __initdata = {
+	"samsung,exynos5250",
+	NULL
+};
+
+DT_MACHINE_START(EXYNOS5_DT, "SAMSUNG EXYNOS5 (Flattened Device Tree)")
+	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
+	.init_irq	= exynos5_init_irq,
+	.map_io		= exynos5250_dt_map_io,
+	.handle_irq	= gic_handle_irq,
+	.init_machine	= exynos5250_dt_machine_init,
+	.timer		= &exynos4_timer,
+	.dt_compat	= exynos5250_dt_compat,
+	.restart        = exynos5_restart,
+MACHINE_END
diff --git a/arch/arm/mach-exynos/mach-nuri.c b/arch/arm/mach-exynos/mach-nuri.c
index 82ea6fccfb34..b3982c867c9c 100644
--- a/arch/arm/mach-exynos/mach-nuri.c
+++ b/arch/arm/mach-exynos/mach-nuri.c
@@ -111,7 +111,7 @@ static struct s3c_sdhci_platdata nuri_hsmmc0_data __initdata = {
 	.max_width		= 8,
 	.host_caps		= (MMC_CAP_8_BIT_DATA | MMC_CAP_4_BIT_DATA |
 				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
-				MMC_CAP_DISABLE | MMC_CAP_ERASE),
+				MMC_CAP_ERASE),
 	.cd_type		= S3C_SDHCI_CD_PERMANENT,
 	.clk_type		= S3C_SDHCI_CLK_DIV_EXTERNAL,
 };
@@ -150,8 +150,7 @@ static struct platform_device emmc_fixed_voltage = {
 static struct s3c_sdhci_platdata nuri_hsmmc2_data __initdata = {
 	.max_width		= 4,
 	.host_caps		= MMC_CAP_4_BIT_DATA |
-				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
-				MMC_CAP_DISABLE,
+				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED,
 	.ext_cd_gpio		= EXYNOS4_GPX3(3),	/* XEINT_27 */
 	.ext_cd_gpio_invert	= 1,
 	.cd_type		= S3C_SDHCI_CD_GPIO,
diff --git a/arch/arm/mach-exynos/mach-universal_c210.c b/arch/arm/mach-exynos/mach-universal_c210.c
index 28658da9f423..6bb9dbdd73fd 100644
--- a/arch/arm/mach-exynos/mach-universal_c210.c
+++ b/arch/arm/mach-exynos/mach-universal_c210.c
@@ -745,8 +745,7 @@ static struct platform_device universal_gpio_keys = {
 static struct s3c_sdhci_platdata universal_hsmmc0_data __initdata = {
 	.max_width		= 8,
 	.host_caps		= (MMC_CAP_8_BIT_DATA | MMC_CAP_4_BIT_DATA |
-				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
-				MMC_CAP_DISABLE),
+				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED),
 	.cd_type		= S3C_SDHCI_CD_PERMANENT,
 	.clk_type		= S3C_SDHCI_CLK_DIV_EXTERNAL,
 };
@@ -784,8 +783,7 @@ static struct platform_device mmc0_fixed_voltage = {
 static struct s3c_sdhci_platdata universal_hsmmc2_data __initdata = {
 	.max_width		= 4,
 	.host_caps		= MMC_CAP_4_BIT_DATA |
-				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
-				MMC_CAP_DISABLE,
+				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED,
 	.ext_cd_gpio		= EXYNOS4_GPX3(4),      /* XEINT_28 */
 	.ext_cd_gpio_invert	= 1,
 	.cd_type		= S3C_SDHCI_CD_GPIO,
@@ -796,8 +794,7 @@ static struct s3c_sdhci_platdata universal_hsmmc2_data __initdata = {
 static struct s3c_sdhci_platdata universal_hsmmc3_data __initdata = {
 	.max_width		= 4,
 	.host_caps		= MMC_CAP_4_BIT_DATA |
-				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
-				MMC_CAP_DISABLE,
+				MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED,
 	.cd_type		= S3C_SDHCI_CD_EXTERNAL,
 };
 
diff --git a/arch/arm/mach-exynos/mct.c b/arch/arm/mach-exynos/mct.c
index e8a1caaf1902..897d9a9cf226 100644
--- a/arch/arm/mach-exynos/mct.c
+++ b/arch/arm/mach-exynos/mct.c
@@ -261,7 +261,10 @@ static void exynos4_clockevent_init(void)
 	mct_comp_device.cpumask = cpumask_of(0);
 	clockevents_register_device(&mct_comp_device);
 
-	setup_irq(IRQ_MCT_G0, &mct_comp_event_irq);
+	if (soc_is_exynos5250())
+		setup_irq(EXYNOS5_IRQ_MCT_G0, &mct_comp_event_irq);
+	else
+		setup_irq(EXYNOS4_IRQ_MCT_G0, &mct_comp_event_irq);
 }
 
 #ifdef CONFIG_LOCAL_TIMERS
@@ -412,16 +415,16 @@ static int __cpuinit exynos4_local_timer_setup(struct clock_event_device *evt)
 	if (mct_int_type == MCT_INT_SPI) {
 		if (cpu == 0) {
 			mct_tick0_event_irq.dev_id = mevt;
-			evt->irq = IRQ_MCT_L0;
-			setup_irq(IRQ_MCT_L0, &mct_tick0_event_irq);
+			evt->irq = EXYNOS4_IRQ_MCT_L0;
+			setup_irq(EXYNOS4_IRQ_MCT_L0, &mct_tick0_event_irq);
 		} else {
 			mct_tick1_event_irq.dev_id = mevt;
-			evt->irq = IRQ_MCT_L1;
-			setup_irq(IRQ_MCT_L1, &mct_tick1_event_irq);
-			irq_set_affinity(IRQ_MCT_L1, cpumask_of(1));
+			evt->irq = EXYNOS4_IRQ_MCT_L1;
+			setup_irq(EXYNOS4_IRQ_MCT_L1, &mct_tick1_event_irq);
+			irq_set_affinity(EXYNOS4_IRQ_MCT_L1, cpumask_of(1));
 		}
 	} else {
-		enable_percpu_irq(IRQ_MCT_LOCALTIMER, 0);
+		enable_percpu_irq(EXYNOS_IRQ_MCT_LOCALTIMER, 0);
 	}
 
 	return 0;
@@ -437,7 +440,7 @@ static void exynos4_local_timer_stop(struct clock_event_device *evt)
 		else
 			remove_irq(evt->irq, &mct_tick1_event_irq);
 	else
-		disable_percpu_irq(IRQ_MCT_LOCALTIMER);
+		disable_percpu_irq(EXYNOS_IRQ_MCT_LOCALTIMER);
 }
 
 static struct local_timer_ops exynos4_mct_tick_ops __cpuinitdata = {
@@ -457,11 +460,11 @@ static void __init exynos4_timer_resources(void)
 	if (mct_int_type == MCT_INT_PPI) {
 		int err;
 
-		err = request_percpu_irq(IRQ_MCT_LOCALTIMER,
+		err = request_percpu_irq(EXYNOS_IRQ_MCT_LOCALTIMER,
 					 exynos4_mct_tick_isr, "MCT",
 					 &percpu_mct_tick);
 		WARN(err, "MCT: can't request IRQ %d (%d)\n",
-		     IRQ_MCT_LOCALTIMER, err);
+		     EXYNOS_IRQ_MCT_LOCALTIMER, err);
 	}
 
 	local_timer_register(&exynos4_mct_tick_ops);
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 0f2035a1eb6e..36c3984aaa47 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -166,7 +166,10 @@ void __init smp_init_cpus(void)
 	void __iomem *scu_base = scu_base_addr();
 	unsigned int i, ncores;
 
-	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
+	if (soc_is_exynos5250())
+		ncores = 2;
+	else
+		ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
 	if (ncores > nr_cpu_ids) {
@@ -183,8 +186,8 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-
-	scu_enable(scu_base_addr());
+	if (!soc_is_exynos5250())
+		scu_enable(scu_base_addr());
 
 	/*
 	 * Write the address of secondary startup into the
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index 0b04af2b13cc..13b306808b42 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -183,6 +183,12 @@ static __init int exynos4_pm_init_power_domain(void)
 #ifdef CONFIG_S5P_DEV_CSIS1
 	exynos_pm_add_dev_to_genpd(&s5p_device_mipi_csis1, &exynos4_pd_cam);
 #endif
+#ifdef CONFIG_S5P_DEV_G2D
+	exynos_pm_add_dev_to_genpd(&s5p_device_g2d, &exynos4_pd_lcd0);
+#endif
+#ifdef CONFIG_S5P_DEV_JPEG
+	exynos_pm_add_dev_to_genpd(&s5p_device_jpeg, &exynos4_pd_cam);
+#endif
 	return 0;
 }
 arch_initcall(exynos4_pm_init_power_domain);
diff --git a/arch/arm/mach-exynos/setup-i2c0.c b/arch/arm/mach-exynos/setup-i2c0.c
index d395bd17c38b..b90d94c17f7c 100644
--- a/arch/arm/mach-exynos/setup-i2c0.c
+++ b/arch/arm/mach-exynos/setup-i2c0.c
@@ -1,7 +1,5 @@
 /*
- * linux/arch/arm/mach-exynos4/setup-i2c0.c
- *
- * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2009-2012 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
  * I2C0 GPIO configuration.
@@ -18,9 +16,14 @@ struct platform_device; /* don't need the contents */
 #include <linux/gpio.h>
 #include <plat/iic.h>
 #include <plat/gpio-cfg.h>
+#include <plat/cpu.h>
 
 void s3c_i2c0_cfg_gpio(struct platform_device *dev)
 {
+	if (soc_is_exynos5250())
+		/* will be implemented with gpio function */
+		return;
+
 	s3c_gpio_cfgall_range(EXYNOS4_GPD1(0), 2,
 			      S3C_GPIO_SFN(2), S3C_GPIO_PULL_UP);
 }
diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c
index 41978ee4f9d0..3e6aaa6361da 100644
--- a/arch/arm/mach-footbridge/common.c
+++ b/arch/arm/mach-footbridge/common.c
@@ -21,6 +21,7 @@
 #include <asm/irq.h>
 #include <asm/mach-types.h>
 #include <asm/setup.h>
+#include <asm/system_misc.h>
 #include <asm/hardware/dec21285.h>
 
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index 121ad1d4fa39..3b54196447c7 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -14,6 +14,7 @@
 
 #include <asm/hardware/dec21285.h>
 #include <asm/mach/time.h>
+#include <asm/system_info.h>
 
 #include "common.h"
 
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index 3194d3f73503..e17e11de4f5e 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -21,7 +21,6 @@
 #include <video/vga.h>
 
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/mach/pci.h>
 #include <asm/hardware/dec21285.h>
 
diff --git a/arch/arm/mach-footbridge/ebsa285-leds.c b/arch/arm/mach-footbridge/ebsa285-leds.c
index 4e10090cd87f..5bd266754b95 100644
--- a/arch/arm/mach-footbridge/ebsa285-leds.c
+++ b/arch/arm/mach-footbridge/ebsa285-leds.c
@@ -24,7 +24,6 @@
 #include <mach/hardware.h>
 #include <asm/leds.h>
 #include <asm/mach-types.h>
-#include <asm/system.h>
 
 #define LED_STATE_ENABLED	1
 #define LED_STATE_CLAIMED	2
diff --git a/arch/arm/mach-footbridge/include/mach/io.h b/arch/arm/mach-footbridge/include/mach/io.h
index 15a70396c27d..aba531eebbc6 100644
--- a/arch/arm/mach-footbridge/include/mach/io.h
+++ b/arch/arm/mach-footbridge/include/mach/io.h
@@ -27,18 +27,5 @@
  * Translation of various region addresses to virtual addresses
  */
 #define __io(a)			((void __iomem *)(PCIO_BASE + (a)))
-#if 1
-#define __mem_pci(a)		(a)
-#else
-
-static inline void __iomem *___mem_pci(void __iomem *p)
-{
-	unsigned long a = (unsigned long)p;
-	BUG_ON(a <= 0xc0000000 || a >= 0xe0000000);
-	return p;
-}
-
-#define __mem_pci(a)		___mem_pci(a)
-#endif
 
 #endif
diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c
index 80a1c5cc9071..cac9f67e7da7 100644
--- a/arch/arm/mach-footbridge/netwinder-hw.c
+++ b/arch/arm/mach-footbridge/netwinder-hw.c
@@ -17,6 +17,7 @@
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 #include <asm/setup.h>
+#include <asm/system_misc.h>
 
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-footbridge/netwinder-leds.c b/arch/arm/mach-footbridge/netwinder-leds.c
index e57102e871fc..5a2bd89cbdca 100644
--- a/arch/arm/mach-footbridge/netwinder-leds.c
+++ b/arch/arm/mach-footbridge/netwinder-leds.c
@@ -24,7 +24,6 @@
 #include <mach/hardware.h>
 #include <asm/leds.h>
 #include <asm/mach-types.h>
-#include <asm/system.h>
 
 #define LED_STATE_ENABLED	1
 #define LED_STATE_CLAIMED	2
diff --git a/arch/arm/mach-gemini/include/mach/io.h b/arch/arm/mach-gemini/include/mach/io.h
deleted file mode 100644
index c548056b98b2..000000000000
--- a/arch/arm/mach-gemini/include/mach/io.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- *  Copyright (C) 2001-2006 Storlink, Corp.
- *  Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#define IO_SPACE_LIMIT	0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif /* __MACH_IO_H */
diff --git a/arch/arm/mach-h720x/common.c b/arch/arm/mach-h720x/common.c
index e756d1ac00c2..aa1331e86bcf 100644
--- a/arch/arm/mach-h720x/common.c
+++ b/arch/arm/mach-h720x/common.c
@@ -24,6 +24,7 @@
 #include <asm/dma.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
+#include <asm/system_misc.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/map.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-h720x/include/mach/io.h b/arch/arm/mach-h720x/include/mach/io.h
deleted file mode 100644
index 2c8659c21a93..000000000000
--- a/arch/arm/mach-h720x/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-h720x/include/mach/io.h
- *
- * Copyright (C) 2000 Steve Hill (sjhill@cotw.com)
- *
- * Changelog:
- *
- *  09-19-2001	JJKIM
- *  		Created from arch/arm/mach-l7200/include/mach/io.h
- *
- *  03-27-2003  Robert Schwebel <r.schwebel@pengutronix.de>:
- *  		re-unified header files for h720x
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 808b055289b2..410a112bb52e 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -35,7 +35,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
-#include <mach/irqs.h>
 
 #include "core.h"
 #include "sysregs.h"
diff --git a/arch/arm/mach-highbank/include/mach/io.h b/arch/arm/mach-highbank/include/mach/io.h
deleted file mode 100644
index 70cfa3ba7697..000000000000
--- a/arch/arm/mach-highbank/include/mach/io.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#define __io(a)		({ (void)(a); __typesafe_io(0); })
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-highbank/include/mach/irqs.h b/arch/arm/mach-highbank/include/mach/irqs.h
deleted file mode 100644
index 9746aab14e9a..000000000000
--- a/arch/arm/mach-highbank/include/mach/irqs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __MACH_IRQS_H
-#define __MACH_IRQS_H
-
-#define NR_IRQS			192
-
-#endif
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 52359f80c42d..7561eca131b0 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -1,6 +1,3 @@
-config IMX_HAVE_DMA_V1
-	bool
-
 config HAVE_IMX_GPC
 	bool
 
@@ -38,7 +35,6 @@ config SOC_IMX1
 	bool
 	select ARCH_MX1
 	select CPU_ARM920T
-	select IMX_HAVE_DMA_V1
 	select IMX_HAVE_IOMUX_V1
 	select MXC_AVIC
 
@@ -46,7 +42,6 @@ config SOC_IMX21
 	bool
 	select MACH_MX21
 	select CPU_ARM926T
-	select IMX_HAVE_DMA_V1
 	select IMX_HAVE_IOMUX_V1
 	select MXC_AVIC
 
@@ -61,7 +56,6 @@ config SOC_IMX27
 	bool
 	select MACH_MX27
 	select CPU_ARM926T
-	select IMX_HAVE_DMA_V1
 	select IMX_HAVE_IOMUX_V1
 	select MXC_AVIC
 
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 35fc450fa263..ab939c5046c3 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -1,5 +1,3 @@
-obj-$(CONFIG_IMX_HAVE_DMA_V1) += dma-v1.o
-
 obj-$(CONFIG_SOC_IMX1) += clock-imx1.o mm-imx1.o
 obj-$(CONFIG_SOC_IMX21) += clock-imx21.o mm-imx21.o
 
diff --git a/arch/arm/mach-imx/clock-imx27.c b/arch/arm/mach-imx/clock-imx27.c
index b9a95ed75553..98e04f5a87dd 100644
--- a/arch/arm/mach-imx/clock-imx27.c
+++ b/arch/arm/mach-imx/clock-imx27.c
@@ -662,6 +662,7 @@ static struct clk_lookup lookups[] = {
 	_REGISTER_CLOCK(NULL, "dma", dma_clk)
 	_REGISTER_CLOCK(NULL, "rtic", rtic_clk)
 	_REGISTER_CLOCK(NULL, "brom", brom_clk)
+	_REGISTER_CLOCK(NULL, "emma", emma_clk)
 	_REGISTER_CLOCK("m2m-emmaprp.0", NULL, emma_clk)
 	_REGISTER_CLOCK(NULL, "slcdc", slcdc_clk)
 	_REGISTER_CLOCK("imx27-fec.0", NULL, fec_clk)
diff --git a/arch/arm/mach-imx/clock-imx35.c b/arch/arm/mach-imx/clock-imx35.c
index 1e279af656ad..e56c1a83eee3 100644
--- a/arch/arm/mach-imx/clock-imx35.c
+++ b/arch/arm/mach-imx/clock-imx35.c
@@ -483,7 +483,7 @@ static struct clk_lookup lookups[] = {
 	_REGISTER_CLOCK("imx2-wdt.0", NULL, wdog_clk)
 	_REGISTER_CLOCK(NULL, "max", max_clk)
 	_REGISTER_CLOCK(NULL, "audmux", audmux_clk)
-	_REGISTER_CLOCK(NULL, "csi", csi_clk)
+	_REGISTER_CLOCK("mx3-camera.0", NULL, csi_clk)
 	_REGISTER_CLOCK(NULL, "iim", iim_clk)
 	_REGISTER_CLOCK(NULL, "gpu2d", gpu2d_clk)
 	_REGISTER_CLOCK("mxc_nand.0", NULL, nfc_clk)
diff --git a/arch/arm/mach-imx/dma-v1.c b/arch/arm/mach-imx/dma-v1.c
deleted file mode 100644
index 42afc29a7da8..000000000000
--- a/arch/arm/mach-imx/dma-v1.c
+++ /dev/null
@@ -1,846 +0,0 @@
-/*
- *  linux/arch/arm/plat-mxc/dma-v1.c
- *
- *  i.MX DMA registration and IRQ dispatching
- *
- * Copyright 2006 Pavel Pisa <pisa@cmp.felk.cvut.cz>
- * Copyright 2008 Juergen Beisert, <kernel@pengutronix.de>
- * Copyright 2008 Sascha Hauer, <s.hauer@pengutronix.de>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/err.h>
-#include <linux/errno.h>
-#include <linux/clk.h>
-#include <linux/scatterlist.h>
-#include <linux/io.h>
-
-#include <asm/system.h>
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <mach/dma-v1.h>
-
-#define DMA_DCR     0x00		/* Control Register */
-#define DMA_DISR    0x04		/* Interrupt status Register */
-#define DMA_DIMR    0x08		/* Interrupt mask Register */
-#define DMA_DBTOSR  0x0c		/* Burst timeout status Register */
-#define DMA_DRTOSR  0x10		/* Request timeout Register */
-#define DMA_DSESR   0x14		/* Transfer Error Status Register */
-#define DMA_DBOSR   0x18		/* Buffer overflow status Register */
-#define DMA_DBTOCR  0x1c		/* Burst timeout control Register */
-#define DMA_WSRA    0x40		/* W-Size Register A */
-#define DMA_XSRA    0x44		/* X-Size Register A */
-#define DMA_YSRA    0x48		/* Y-Size Register A */
-#define DMA_WSRB    0x4c		/* W-Size Register B */
-#define DMA_XSRB    0x50		/* X-Size Register B */
-#define DMA_YSRB    0x54		/* Y-Size Register B */
-#define DMA_SAR(x)  (0x80 + ((x) << 6))	/* Source Address Registers */
-#define DMA_DAR(x)  (0x84 + ((x) << 6))	/* Destination Address Registers */
-#define DMA_CNTR(x) (0x88 + ((x) << 6))	/* Count Registers */
-#define DMA_CCR(x)  (0x8c + ((x) << 6))	/* Control Registers */
-#define DMA_RSSR(x) (0x90 + ((x) << 6))	/* Request source select Registers */
-#define DMA_BLR(x)  (0x94 + ((x) << 6))	/* Burst length Registers */
-#define DMA_RTOR(x) (0x98 + ((x) << 6))	/* Request timeout Registers */
-#define DMA_BUCR(x) (0x98 + ((x) << 6))	/* Bus Utilization Registers */
-#define DMA_CCNR(x) (0x9C + ((x) << 6))	/* Channel counter Registers */
-
-#define DCR_DRST           (1<<1)
-#define DCR_DEN            (1<<0)
-#define DBTOCR_EN          (1<<15)
-#define DBTOCR_CNT(x)      ((x) & 0x7fff)
-#define CNTR_CNT(x)        ((x) & 0xffffff)
-#define CCR_ACRPT          (1<<14)
-#define CCR_DMOD_LINEAR    (0x0 << 12)
-#define CCR_DMOD_2D        (0x1 << 12)
-#define CCR_DMOD_FIFO      (0x2 << 12)
-#define CCR_DMOD_EOBFIFO   (0x3 << 12)
-#define CCR_SMOD_LINEAR    (0x0 << 10)
-#define CCR_SMOD_2D        (0x1 << 10)
-#define CCR_SMOD_FIFO      (0x2 << 10)
-#define CCR_SMOD_EOBFIFO   (0x3 << 10)
-#define CCR_MDIR_DEC       (1<<9)
-#define CCR_MSEL_B         (1<<8)
-#define CCR_DSIZ_32        (0x0 << 6)
-#define CCR_DSIZ_8         (0x1 << 6)
-#define CCR_DSIZ_16        (0x2 << 6)
-#define CCR_SSIZ_32        (0x0 << 4)
-#define CCR_SSIZ_8         (0x1 << 4)
-#define CCR_SSIZ_16        (0x2 << 4)
-#define CCR_REN            (1<<3)
-#define CCR_RPT            (1<<2)
-#define CCR_FRC            (1<<1)
-#define CCR_CEN            (1<<0)
-#define RTOR_EN            (1<<15)
-#define RTOR_CLK           (1<<14)
-#define RTOR_PSC           (1<<13)
-
-/*
- * struct imx_dma_channel - i.MX specific DMA extension
- * @name: name specified by DMA client
- * @irq_handler: client callback for end of transfer
- * @err_handler: client callback for error condition
- * @data: clients context data for callbacks
- * @dma_mode: direction of the transfer %DMA_MODE_READ or %DMA_MODE_WRITE
- * @sg: pointer to the actual read/written chunk for scatter-gather emulation
- * @resbytes: total residual number of bytes to transfer
- *            (it can be lower or same as sum of SG mapped chunk sizes)
- * @sgcount: number of chunks to be read/written
- *
- * Structure is used for IMX DMA processing. It would be probably good
- * @struct dma_struct in the future for external interfacing and use
- * @struct imx_dma_channel only as extension to it.
- */
-
-struct imx_dma_channel {
-	const char *name;
-	void (*irq_handler) (int, void *);
-	void (*err_handler) (int, void *, int errcode);
-	void (*prog_handler) (int, void *, struct scatterlist *);
-	void *data;
-	unsigned int dma_mode;
-	struct scatterlist *sg;
-	unsigned int resbytes;
-	int dma_num;
-
-	int in_use;
-
-	u32 ccr_from_device;
-	u32 ccr_to_device;
-
-	struct timer_list watchdog;
-
-	int hw_chaining;
-};
-
-static void __iomem *imx_dmav1_baseaddr;
-
-static void imx_dmav1_writel(unsigned val, unsigned offset)
-{
-	__raw_writel(val, imx_dmav1_baseaddr + offset);
-}
-
-static unsigned imx_dmav1_readl(unsigned offset)
-{
-	return __raw_readl(imx_dmav1_baseaddr + offset);
-}
-
-static struct imx_dma_channel imx_dma_channels[IMX_DMA_CHANNELS];
-
-static struct clk *dma_clk;
-
-static int imx_dma_hw_chain(struct imx_dma_channel *imxdma)
-{
-	if (cpu_is_mx27())
-		return imxdma->hw_chaining;
-	else
-		return 0;
-}
-
-/*
- * imx_dma_sg_next - prepare next chunk for scatter-gather DMA emulation
- */
-static inline int imx_dma_sg_next(int channel, struct scatterlist *sg)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long now;
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT "%s: called for  not allocated channel %d\n",
-		       __func__, channel);
-		return 0;
-	}
-
-	now = min(imxdma->resbytes, sg->length);
-	if (imxdma->resbytes != IMX_DMA_LENGTH_LOOP)
-		imxdma->resbytes -= now;
-
-	if ((imxdma->dma_mode & DMA_MODE_MASK) == DMA_MODE_READ)
-		imx_dmav1_writel(sg->dma_address, DMA_DAR(channel));
-	else
-		imx_dmav1_writel(sg->dma_address, DMA_SAR(channel));
-
-	imx_dmav1_writel(now, DMA_CNTR(channel));
-
-	pr_debug("imxdma%d: next sg chunk dst 0x%08x, src 0x%08x, "
-		"size 0x%08x\n", channel,
-		 imx_dmav1_readl(DMA_DAR(channel)),
-		 imx_dmav1_readl(DMA_SAR(channel)),
-		 imx_dmav1_readl(DMA_CNTR(channel)));
-
-	return now;
-}
-
-/**
- * imx_dma_setup_single - setup i.MX DMA channel for linear memory to/from
- * device transfer
- *
- * @channel: i.MX DMA channel number
- * @dma_address: the DMA/physical memory address of the linear data block
- *		to transfer
- * @dma_length: length of the data block in bytes
- * @dev_addr: physical device port address
- * @dmamode: DMA transfer mode, %DMA_MODE_READ from the device to the memory
- *           or %DMA_MODE_WRITE from memory to the device
- *
- * Return value: if incorrect parameters are provided -%EINVAL.
- *		Zero indicates success.
- */
-int
-imx_dma_setup_single(int channel, dma_addr_t dma_address,
-		     unsigned int dma_length, unsigned int dev_addr,
-		     unsigned int dmamode)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-
-	imxdma->sg = NULL;
-	imxdma->dma_mode = dmamode;
-
-	if (!dma_address) {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_single null address\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	if (!dma_length) {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_single zero length\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	if ((dmamode & DMA_MODE_MASK) == DMA_MODE_READ) {
-		pr_debug("imxdma%d: %s dma_addressg=0x%08x dma_length=%d "
-			"dev_addr=0x%08x for read\n",
-			channel, __func__, (unsigned int)dma_address,
-			dma_length, dev_addr);
-
-		imx_dmav1_writel(dev_addr, DMA_SAR(channel));
-		imx_dmav1_writel(dma_address, DMA_DAR(channel));
-		imx_dmav1_writel(imxdma->ccr_from_device, DMA_CCR(channel));
-	} else if ((dmamode & DMA_MODE_MASK) == DMA_MODE_WRITE) {
-		pr_debug("imxdma%d: %s dma_addressg=0x%08x dma_length=%d "
-			"dev_addr=0x%08x for write\n",
-			channel, __func__, (unsigned int)dma_address,
-			dma_length, dev_addr);
-
-		imx_dmav1_writel(dma_address, DMA_SAR(channel));
-		imx_dmav1_writel(dev_addr, DMA_DAR(channel));
-		imx_dmav1_writel(imxdma->ccr_to_device,
-				DMA_CCR(channel));
-	} else {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_single bad dmamode\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	imx_dmav1_writel(dma_length, DMA_CNTR(channel));
-
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_setup_single);
-
-/**
- * imx_dma_setup_sg - setup i.MX DMA channel SG list to/from device transfer
- * @channel: i.MX DMA channel number
- * @sg: pointer to the scatter-gather list/vector
- * @sgcount: scatter-gather list hungs count
- * @dma_length: total length of the transfer request in bytes
- * @dev_addr: physical device port address
- * @dmamode: DMA transfer mode, %DMA_MODE_READ from the device to the memory
- *           or %DMA_MODE_WRITE from memory to the device
- *
- * The function sets up DMA channel state and registers to be ready for
- * transfer specified by provided parameters. The scatter-gather emulation
- * is set up according to the parameters.
- *
- * The full preparation of the transfer requires setup of more register
- * by the caller before imx_dma_enable() can be called.
- *
- * %BLR(channel) holds transfer burst length in bytes, 0 means 64 bytes
- *
- * %RSSR(channel) has to be set to the DMA request line source %DMA_REQ_xxx
- *
- * %CCR(channel) has to specify transfer parameters, the next settings is
- * typical for linear or simple scatter-gather transfers if %DMA_MODE_READ is
- * specified
- *
- * %CCR_DMOD_LINEAR | %CCR_DSIZ_32 | %CCR_SMOD_FIFO | %CCR_SSIZ_x
- *
- * The typical setup for %DMA_MODE_WRITE is specified by next options
- * combination
- *
- * %CCR_SMOD_LINEAR | %CCR_SSIZ_32 | %CCR_DMOD_FIFO | %CCR_DSIZ_x
- *
- * Be careful here and do not mistakenly mix source and target device
- * port sizes constants, they are really different:
- * %CCR_SSIZ_8, %CCR_SSIZ_16, %CCR_SSIZ_32,
- * %CCR_DSIZ_8, %CCR_DSIZ_16, %CCR_DSIZ_32
- *
- * Return value: if incorrect parameters are provided -%EINVAL.
- * Zero indicates success.
- */
-int
-imx_dma_setup_sg(int channel,
-		 struct scatterlist *sg, unsigned int sgcount,
-		 unsigned int dma_length, unsigned int dev_addr,
-		 unsigned int dmamode)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-
-	if (imxdma->in_use)
-		return -EBUSY;
-
-	imxdma->sg = sg;
-	imxdma->dma_mode = dmamode;
-	imxdma->resbytes = dma_length;
-
-	if (!sg || !sgcount) {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_sg empty sg list\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	if (!sg->length) {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_sg zero length\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	if ((dmamode & DMA_MODE_MASK) == DMA_MODE_READ) {
-		pr_debug("imxdma%d: %s sg=%p sgcount=%d total length=%d "
-			"dev_addr=0x%08x for read\n",
-			channel, __func__, sg, sgcount, dma_length, dev_addr);
-
-		imx_dmav1_writel(dev_addr, DMA_SAR(channel));
-		imx_dmav1_writel(imxdma->ccr_from_device, DMA_CCR(channel));
-	} else if ((dmamode & DMA_MODE_MASK) == DMA_MODE_WRITE) {
-		pr_debug("imxdma%d: %s sg=%p sgcount=%d total length=%d "
-			"dev_addr=0x%08x for write\n",
-			channel, __func__, sg, sgcount, dma_length, dev_addr);
-
-		imx_dmav1_writel(dev_addr, DMA_DAR(channel));
-		imx_dmav1_writel(imxdma->ccr_to_device, DMA_CCR(channel));
-	} else {
-		printk(KERN_ERR "imxdma%d: imx_dma_setup_sg bad dmamode\n",
-		       channel);
-		return -EINVAL;
-	}
-
-	imx_dma_sg_next(channel, sg);
-
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_setup_sg);
-
-int
-imx_dma_config_channel(int channel, unsigned int config_port,
-	unsigned int config_mem, unsigned int dmareq, int hw_chaining)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	u32 dreq = 0;
-
-	imxdma->hw_chaining = 0;
-
-	if (hw_chaining) {
-		imxdma->hw_chaining = 1;
-		if (!imx_dma_hw_chain(imxdma))
-			return -EINVAL;
-	}
-
-	if (dmareq)
-		dreq = CCR_REN;
-
-	imxdma->ccr_from_device = config_port | (config_mem << 2) | dreq;
-	imxdma->ccr_to_device = config_mem | (config_port << 2) | dreq;
-
-	imx_dmav1_writel(dmareq, DMA_RSSR(channel));
-
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_config_channel);
-
-void imx_dma_config_burstlen(int channel, unsigned int burstlen)
-{
-	imx_dmav1_writel(burstlen, DMA_BLR(channel));
-}
-EXPORT_SYMBOL(imx_dma_config_burstlen);
-
-/**
- * imx_dma_setup_handlers - setup i.MX DMA channel end and error notification
- * handlers
- * @channel: i.MX DMA channel number
- * @irq_handler: the pointer to the function called if the transfer
- *		ends successfully
- * @err_handler: the pointer to the function called if the premature
- *		end caused by error occurs
- * @data: user specified value to be passed to the handlers
- */
-int
-imx_dma_setup_handlers(int channel,
-		       void (*irq_handler) (int, void *),
-		       void (*err_handler) (int, void *, int),
-		       void *data)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT "%s: called for  not allocated channel %d\n",
-		       __func__, channel);
-		return -ENODEV;
-	}
-
-	local_irq_save(flags);
-	imx_dmav1_writel(1 << channel, DMA_DISR);
-	imxdma->irq_handler = irq_handler;
-	imxdma->err_handler = err_handler;
-	imxdma->data = data;
-	local_irq_restore(flags);
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_setup_handlers);
-
-/**
- * imx_dma_setup_progression_handler - setup i.MX DMA channel progression
- * handlers
- * @channel: i.MX DMA channel number
- * @prog_handler: the pointer to the function called if the transfer progresses
- */
-int
-imx_dma_setup_progression_handler(int channel,
-			void (*prog_handler) (int, void*, struct scatterlist*))
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT "%s: called for  not allocated channel %d\n",
-		       __func__, channel);
-		return -ENODEV;
-	}
-
-	local_irq_save(flags);
-	imxdma->prog_handler = prog_handler;
-	local_irq_restore(flags);
-	return 0;
-}
-EXPORT_SYMBOL(imx_dma_setup_progression_handler);
-
-/**
- * imx_dma_enable - function to start i.MX DMA channel operation
- * @channel: i.MX DMA channel number
- *
- * The channel has to be allocated by driver through imx_dma_request()
- * or imx_dma_request_by_prio() function.
- * The transfer parameters has to be set to the channel registers through
- * call of the imx_dma_setup_single() or imx_dma_setup_sg() function
- * and registers %BLR(channel), %RSSR(channel) and %CCR(channel) has to
- * be set prior this function call by the channel user.
- */
-void imx_dma_enable(int channel)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-
-	pr_debug("imxdma%d: imx_dma_enable\n", channel);
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT "%s: called for  not allocated channel %d\n",
-		       __func__, channel);
-		return;
-	}
-
-	if (imxdma->in_use)
-		return;
-
-	local_irq_save(flags);
-
-	imx_dmav1_writel(1 << channel, DMA_DISR);
-	imx_dmav1_writel(imx_dmav1_readl(DMA_DIMR) & ~(1 << channel), DMA_DIMR);
-	imx_dmav1_writel(imx_dmav1_readl(DMA_CCR(channel)) | CCR_CEN |
-		CCR_ACRPT, DMA_CCR(channel));
-
-	if ((cpu_is_mx21() || cpu_is_mx27()) &&
-			imxdma->sg && imx_dma_hw_chain(imxdma)) {
-		imxdma->sg = sg_next(imxdma->sg);
-		if (imxdma->sg) {
-			u32 tmp;
-			imx_dma_sg_next(channel, imxdma->sg);
-			tmp = imx_dmav1_readl(DMA_CCR(channel));
-			imx_dmav1_writel(tmp | CCR_RPT | CCR_ACRPT,
-				DMA_CCR(channel));
-		}
-	}
-	imxdma->in_use = 1;
-
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(imx_dma_enable);
-
-/**
- * imx_dma_disable - stop, finish i.MX DMA channel operatin
- * @channel: i.MX DMA channel number
- */
-void imx_dma_disable(int channel)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-
-	pr_debug("imxdma%d: imx_dma_disable\n", channel);
-
-	if (imx_dma_hw_chain(imxdma))
-		del_timer(&imxdma->watchdog);
-
-	local_irq_save(flags);
-	imx_dmav1_writel(imx_dmav1_readl(DMA_DIMR) | (1 << channel), DMA_DIMR);
-	imx_dmav1_writel(imx_dmav1_readl(DMA_CCR(channel)) & ~CCR_CEN,
-			DMA_CCR(channel));
-	imx_dmav1_writel(1 << channel, DMA_DISR);
-	imxdma->in_use = 0;
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(imx_dma_disable);
-
-static void imx_dma_watchdog(unsigned long chno)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[chno];
-
-	imx_dmav1_writel(0, DMA_CCR(chno));
-	imxdma->in_use = 0;
-	imxdma->sg = NULL;
-
-	if (imxdma->err_handler)
-		imxdma->err_handler(chno, imxdma->data, IMX_DMA_ERR_TIMEOUT);
-}
-
-static irqreturn_t dma_err_handler(int irq, void *dev_id)
-{
-	int i, disr;
-	struct imx_dma_channel *imxdma;
-	unsigned int err_mask;
-	int errcode;
-
-	disr = imx_dmav1_readl(DMA_DISR);
-
-	err_mask = imx_dmav1_readl(DMA_DBTOSR) |
-		   imx_dmav1_readl(DMA_DRTOSR) |
-		   imx_dmav1_readl(DMA_DSESR)  |
-		   imx_dmav1_readl(DMA_DBOSR);
-
-	if (!err_mask)
-		return IRQ_HANDLED;
-
-	imx_dmav1_writel(disr & err_mask, DMA_DISR);
-
-	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
-		if (!(err_mask & (1 << i)))
-			continue;
-		imxdma = &imx_dma_channels[i];
-		errcode = 0;
-
-		if (imx_dmav1_readl(DMA_DBTOSR) & (1 << i)) {
-			imx_dmav1_writel(1 << i, DMA_DBTOSR);
-			errcode |= IMX_DMA_ERR_BURST;
-		}
-		if (imx_dmav1_readl(DMA_DRTOSR) & (1 << i)) {
-			imx_dmav1_writel(1 << i, DMA_DRTOSR);
-			errcode |= IMX_DMA_ERR_REQUEST;
-		}
-		if (imx_dmav1_readl(DMA_DSESR) & (1 << i)) {
-			imx_dmav1_writel(1 << i, DMA_DSESR);
-			errcode |= IMX_DMA_ERR_TRANSFER;
-		}
-		if (imx_dmav1_readl(DMA_DBOSR) & (1 << i)) {
-			imx_dmav1_writel(1 << i, DMA_DBOSR);
-			errcode |= IMX_DMA_ERR_BUFFER;
-		}
-		if (imxdma->name && imxdma->err_handler) {
-			imxdma->err_handler(i, imxdma->data, errcode);
-			continue;
-		}
-
-		imx_dma_channels[i].sg = NULL;
-
-		printk(KERN_WARNING
-		       "DMA timeout on channel %d (%s) -%s%s%s%s\n",
-		       i, imxdma->name,
-		       errcode & IMX_DMA_ERR_BURST ?    " burst" : "",
-		       errcode & IMX_DMA_ERR_REQUEST ?  " request" : "",
-		       errcode & IMX_DMA_ERR_TRANSFER ? " transfer" : "",
-		       errcode & IMX_DMA_ERR_BUFFER ?   " buffer" : "");
-	}
-	return IRQ_HANDLED;
-}
-
-static void dma_irq_handle_channel(int chno)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[chno];
-
-	if (!imxdma->name) {
-		/*
-		 * IRQ for an unregistered DMA channel:
-		 * let's clear the interrupts and disable it.
-		 */
-		printk(KERN_WARNING
-		       "spurious IRQ for DMA channel %d\n", chno);
-		return;
-	}
-
-	if (imxdma->sg) {
-		u32 tmp;
-		struct scatterlist *current_sg = imxdma->sg;
-		imxdma->sg = sg_next(imxdma->sg);
-
-		if (imxdma->sg) {
-			imx_dma_sg_next(chno, imxdma->sg);
-
-			tmp = imx_dmav1_readl(DMA_CCR(chno));
-
-			if (imx_dma_hw_chain(imxdma)) {
-				/* FIXME: The timeout should probably be
-				 * configurable
-				 */
-				mod_timer(&imxdma->watchdog,
-					jiffies + msecs_to_jiffies(500));
-
-				tmp |= CCR_CEN | CCR_RPT | CCR_ACRPT;
-				imx_dmav1_writel(tmp, DMA_CCR(chno));
-			} else {
-				imx_dmav1_writel(tmp & ~CCR_CEN, DMA_CCR(chno));
-				tmp |= CCR_CEN;
-			}
-
-			imx_dmav1_writel(tmp, DMA_CCR(chno));
-
-			if (imxdma->prog_handler)
-				imxdma->prog_handler(chno, imxdma->data,
-						current_sg);
-
-			return;
-		}
-
-		if (imx_dma_hw_chain(imxdma)) {
-			del_timer(&imxdma->watchdog);
-			return;
-		}
-	}
-
-	imx_dmav1_writel(0, DMA_CCR(chno));
-	imxdma->in_use = 0;
-	if (imxdma->irq_handler)
-		imxdma->irq_handler(chno, imxdma->data);
-}
-
-static irqreturn_t dma_irq_handler(int irq, void *dev_id)
-{
-	int i, disr;
-
-	if (cpu_is_mx21() || cpu_is_mx27())
-		dma_err_handler(irq, dev_id);
-
-	disr = imx_dmav1_readl(DMA_DISR);
-
-	pr_debug("imxdma: dma_irq_handler called, disr=0x%08x\n",
-		     disr);
-
-	imx_dmav1_writel(disr, DMA_DISR);
-	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
-		if (disr & (1 << i))
-			dma_irq_handle_channel(i);
-	}
-
-	return IRQ_HANDLED;
-}
-
-/**
- * imx_dma_request - request/allocate specified channel number
- * @channel: i.MX DMA channel number
- * @name: the driver/caller own non-%NULL identification
- */
-int imx_dma_request(int channel, const char *name)
-{
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-	unsigned long flags;
-	int ret = 0;
-
-	/* basic sanity checks */
-	if (!name)
-		return -EINVAL;
-
-	if (channel >= IMX_DMA_CHANNELS) {
-		printk(KERN_CRIT "%s: called for  non-existed channel %d\n",
-		       __func__, channel);
-		return -EINVAL;
-	}
-
-	local_irq_save(flags);
-	if (imxdma->name) {
-		local_irq_restore(flags);
-		return -EBUSY;
-	}
-	memset(imxdma, 0, sizeof(*imxdma));
-	imxdma->name = name;
-	local_irq_restore(flags); /* request_irq() can block */
-
-	if (cpu_is_mx21() || cpu_is_mx27()) {
-		ret = request_irq(MX2x_INT_DMACH0 + channel,
-				dma_irq_handler, 0, "DMA", NULL);
-		if (ret) {
-			imxdma->name = NULL;
-			pr_crit("Can't register IRQ %d for DMA channel %d\n",
-					MX2x_INT_DMACH0 + channel, channel);
-			return ret;
-		}
-		init_timer(&imxdma->watchdog);
-		imxdma->watchdog.function = &imx_dma_watchdog;
-		imxdma->watchdog.data = channel;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(imx_dma_request);
-
-/**
- * imx_dma_free - release previously acquired channel
- * @channel: i.MX DMA channel number
- */
-void imx_dma_free(int channel)
-{
-	unsigned long flags;
-	struct imx_dma_channel *imxdma = &imx_dma_channels[channel];
-
-	if (!imxdma->name) {
-		printk(KERN_CRIT
-		       "%s: trying to free free channel %d\n",
-		       __func__, channel);
-		return;
-	}
-
-	local_irq_save(flags);
-	/* Disable interrupts */
-	imx_dma_disable(channel);
-	imxdma->name = NULL;
-
-	if (cpu_is_mx21() || cpu_is_mx27())
-		free_irq(MX2x_INT_DMACH0 + channel, NULL);
-
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(imx_dma_free);
-
-/**
- * imx_dma_request_by_prio - find and request some of free channels best
- * suiting requested priority
- * @channel: i.MX DMA channel number
- * @name: the driver/caller own non-%NULL identification
- *
- * This function tries to find a free channel in the specified priority group
- * if the priority cannot be achieved it tries to look for free channel
- * in the higher and then even lower priority groups.
- *
- * Return value: If there is no free channel to allocate, -%ENODEV is returned.
- *               On successful allocation channel is returned.
- */
-int imx_dma_request_by_prio(const char *name, enum imx_dma_prio prio)
-{
-	int i;
-	int best;
-
-	switch (prio) {
-	case (DMA_PRIO_HIGH):
-		best = 8;
-		break;
-	case (DMA_PRIO_MEDIUM):
-		best = 4;
-		break;
-	case (DMA_PRIO_LOW):
-	default:
-		best = 0;
-		break;
-	}
-
-	for (i = best; i < IMX_DMA_CHANNELS; i++)
-		if (!imx_dma_request(i, name))
-			return i;
-
-	for (i = best - 1; i >= 0; i--)
-		if (!imx_dma_request(i, name))
-			return i;
-
-	printk(KERN_ERR "%s: no free DMA channel found\n", __func__);
-
-	return -ENODEV;
-}
-EXPORT_SYMBOL(imx_dma_request_by_prio);
-
-static int __init imx_dma_init(void)
-{
-	int ret = 0;
-	int i;
-
-	if (cpu_is_mx1())
-		imx_dmav1_baseaddr = MX1_IO_ADDRESS(MX1_DMA_BASE_ADDR);
-	else if (cpu_is_mx21())
-		imx_dmav1_baseaddr = MX21_IO_ADDRESS(MX21_DMA_BASE_ADDR);
-	else if (cpu_is_mx27())
-		imx_dmav1_baseaddr = MX27_IO_ADDRESS(MX27_DMA_BASE_ADDR);
-	else
-		return 0;
-
-	dma_clk = clk_get(NULL, "dma");
-	if (IS_ERR(dma_clk))
-		return PTR_ERR(dma_clk);
-	clk_enable(dma_clk);
-
-	/* reset DMA module */
-	imx_dmav1_writel(DCR_DRST, DMA_DCR);
-
-	if (cpu_is_mx1()) {
-		ret = request_irq(MX1_DMA_INT, dma_irq_handler, 0, "DMA", NULL);
-		if (ret) {
-			pr_crit("Wow!  Can't register IRQ for DMA\n");
-			return ret;
-		}
-
-		ret = request_irq(MX1_DMA_ERR, dma_err_handler, 0, "DMA", NULL);
-		if (ret) {
-			pr_crit("Wow!  Can't register ERRIRQ for DMA\n");
-			free_irq(MX1_DMA_INT, NULL);
-			return ret;
-		}
-	}
-
-	/* enable DMA module */
-	imx_dmav1_writel(DCR_DEN, DMA_DCR);
-
-	/* clear all interrupts */
-	imx_dmav1_writel((1 << IMX_DMA_CHANNELS) - 1, DMA_DISR);
-
-	/* disable interrupts */
-	imx_dmav1_writel((1 << IMX_DMA_CHANNELS) - 1, DMA_DIMR);
-
-	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
-		imx_dma_channels[i].sg = NULL;
-		imx_dma_channels[i].dma_num = i;
-	}
-
-	return ret;
-}
-
-arch_initcall(imx_dma_init);
diff --git a/arch/arm/mach-imx/include/mach/dma-v1.h b/arch/arm/mach-imx/include/mach/dma-v1.h
deleted file mode 100644
index ac6fd713828a..000000000000
--- a/arch/arm/mach-imx/include/mach/dma-v1.h
+++ /dev/null
@@ -1,103 +0,0 @@
-/*
- *  linux/arch/arm/mach-imx/include/mach/dma-v1.h
- *
- *  i.MX DMA registration and IRQ dispatching
- *
- * Copyright 2006 Pavel Pisa <pisa@cmp.felk.cvut.cz>
- * Copyright 2008 Juergen Beisert, <kernel@pengutronix.de>
- * Copyright 2008 Sascha Hauer, <s.hauer@pengutronix.de>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef __MACH_DMA_V1_H__
-#define __MACH_DMA_V1_H__
-
-#define imx_has_dma_v1()	(cpu_is_mx1() || cpu_is_mx21() || cpu_is_mx27())
-
-#include <mach/dma.h>
-
-#define IMX_DMA_CHANNELS  16
-
-#define DMA_MODE_READ		0
-#define DMA_MODE_WRITE		1
-#define DMA_MODE_MASK		1
-
-#define MX1_DMA_REG(offset)	MX1_IO_ADDRESS(MX1_DMA_BASE_ADDR + (offset))
-
-/* DMA Interrupt Mask Register */
-#define MX1_DMA_DIMR		MX1_DMA_REG(0x08)
-
-/* Channel Control Register */
-#define MX1_DMA_CCR(x)		MX1_DMA_REG(0x8c + ((x) << 6))
-
-#define IMX_DMA_MEMSIZE_32	(0 << 4)
-#define IMX_DMA_MEMSIZE_8	(1 << 4)
-#define IMX_DMA_MEMSIZE_16	(2 << 4)
-#define IMX_DMA_TYPE_LINEAR	(0 << 10)
-#define IMX_DMA_TYPE_2D		(1 << 10)
-#define IMX_DMA_TYPE_FIFO	(2 << 10)
-
-#define IMX_DMA_ERR_BURST     (1 << 0)
-#define IMX_DMA_ERR_REQUEST   (1 << 1)
-#define IMX_DMA_ERR_TRANSFER  (1 << 2)
-#define IMX_DMA_ERR_BUFFER    (1 << 3)
-#define IMX_DMA_ERR_TIMEOUT   (1 << 4)
-
-int
-imx_dma_config_channel(int channel, unsigned int config_port,
-	unsigned int config_mem, unsigned int dmareq, int hw_chaining);
-
-void
-imx_dma_config_burstlen(int channel, unsigned int burstlen);
-
-int
-imx_dma_setup_single(int channel, dma_addr_t dma_address,
-		unsigned int dma_length, unsigned int dev_addr,
-		unsigned int dmamode);
-
-
-/*
- * Use this flag as the dma_length argument to imx_dma_setup_sg()
- * to create an endless running dma loop. The end of the scatterlist
- * must be linked to the beginning for this to work.
- */
-#define IMX_DMA_LENGTH_LOOP	((unsigned int)-1)
-
-int
-imx_dma_setup_sg(int channel, struct scatterlist *sg,
-		unsigned int sgcount, unsigned int dma_length,
-		unsigned int dev_addr, unsigned int dmamode);
-
-int
-imx_dma_setup_handlers(int channel,
-		void (*irq_handler) (int, void *),
-		void (*err_handler) (int, void *, int), void *data);
-
-int
-imx_dma_setup_progression_handler(int channel,
-		void (*prog_handler) (int, void*, struct scatterlist*));
-
-void imx_dma_enable(int channel);
-
-void imx_dma_disable(int channel);
-
-int imx_dma_request(int channel, const char *name);
-
-void imx_dma_free(int channel);
-
-int imx_dma_request_by_prio(const char *name, enum imx_dma_prio prio);
-
-#endif	/* __MACH_DMA_V1_H__ */
diff --git a/arch/arm/mach-imx/mach-armadillo5x0.c b/arch/arm/mach-imx/mach-armadillo5x0.c
index 27bc27e6ea41..c650145d1646 100644
--- a/arch/arm/mach-imx/mach-armadillo5x0.c
+++ b/arch/arm/mach-imx/mach-armadillo5x0.c
@@ -38,6 +38,8 @@
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
 #include <linux/delay.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@@ -479,6 +481,11 @@ static struct platform_device *devices[] __initdata = {
 	&armadillo5x0_smc911x_device,
 };
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
+
 /*
  * Perform board specific initializations
  */
@@ -489,6 +496,8 @@ static void __init armadillo5x0_init(void)
 	mxc_iomux_setup_multiple_pins(armadillo5x0_pins,
 			ARRAY_SIZE(armadillo5x0_pins), "armadillo5x0");
 
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 	imx_add_gpio_keys(&armadillo5x0_button_data);
 	imx31_add_imx_i2c1(NULL);
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 7696dfa2bdba..da6c1d9af768 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -26,6 +26,7 @@
 #include <asm/hardware/gic.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
+#include <asm/system_misc.h>
 #include <mach/common.h>
 #include <mach/hardware.h>
 
diff --git a/arch/arm/mach-imx/mach-kzm_arm11_01.c b/arch/arm/mach-imx/mach-kzm_arm11_01.c
index fc78e8071cd1..15a26e908260 100644
--- a/arch/arm/mach-imx/mach-kzm_arm11_01.c
+++ b/arch/arm/mach-imx/mach-kzm_arm11_01.c
@@ -24,6 +24,8 @@
 #include <linux/serial_8250.h>
 #include <linux/smsc911x.h>
 #include <linux/types.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
@@ -166,6 +168,11 @@ static struct platform_device kzm_smsc9118_device = {
 			  },
 };
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
+
 static int __init kzm_init_smsc9118(void)
 {
 	/*
@@ -175,6 +182,8 @@ static int __init kzm_init_smsc9118(void)
 	gpio_request(IOMUX_TO_GPIO(MX31_PIN_GPIO1_2), "smsc9118-int");
 	gpio_direction_input(IOMUX_TO_GPIO(MX31_PIN_GPIO1_2));
 
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	return platform_device_register(&kzm_smsc9118_device);
 }
 #else
diff --git a/arch/arm/mach-imx/mach-mx31lilly.c b/arch/arm/mach-imx/mach-mx31lilly.c
index 02401bbd6d53..83714b0cc290 100644
--- a/arch/arm/mach-imx/mach-mx31lilly.c
+++ b/arch/arm/mach-imx/mach-mx31lilly.c
@@ -34,6 +34,8 @@
 #include <linux/mfd/mc13783.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -242,6 +244,11 @@ static struct platform_device *devices[] __initdata = {
 static int mx31lilly_baseboard;
 core_param(mx31lilly_baseboard, mx31lilly_baseboard, int, 0444);
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
+
 static void __init mx31lilly_board_init(void)
 {
 	imx31_soc_init();
@@ -280,6 +287,8 @@ static void __init mx31lilly_board_init(void)
 	imx31_add_spi_imx1(&spi1_pdata);
 	spi_register_board_info(&mc13783_dev, 1);
 
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	/* USB */
diff --git a/arch/arm/mach-imx/mach-mx31lite.c b/arch/arm/mach-imx/mach-mx31lite.c
index ef80751712e7..0abef5f13df5 100644
--- a/arch/arm/mach-imx/mach-mx31lite.c
+++ b/arch/arm/mach-imx/mach-mx31lite.c
@@ -29,6 +29,8 @@
 #include <linux/usb/ulpi.h>
 #include <linux/mtd/physmap.h>
 #include <linux/delay.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -226,6 +228,11 @@ void __init mx31lite_map_io(void)
 static int mx31lite_baseboard;
 core_param(mx31lite_baseboard, mx31lite_baseboard, int, 0444);
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
+
 static void __init mx31lite_init(void)
 {
 	int ret;
@@ -259,6 +266,8 @@ static void __init mx31lite_init(void)
 	if (usbh2_pdata.otg)
 		imx31_add_mxc_ehci_hs(2, &usbh2_pdata);
 
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	/* SMSC9117 IRQ pin */
 	ret = gpio_request(IOMUX_TO_GPIO(MX31_PIN_SFS6), "sms9117-irq");
 	if (ret)
diff --git a/arch/arm/mach-imx/mach-mx35_3ds.c b/arch/arm/mach-imx/mach-mx35_3ds.c
index e14291d89e4f..6ae51c6b95b7 100644
--- a/arch/arm/mach-imx/mach-mx35_3ds.c
+++ b/arch/arm/mach-imx/mach-mx35_3ds.c
@@ -97,7 +97,7 @@ static struct i2c_board_info __initdata i2c_devices_3ds[] = {
 static int lcd_power_gpio = -ENXIO;
 
 static int mc9s08dz60_gpiochip_match(struct gpio_chip *chip,
-						     void *data)
+						     const void *data)
 {
 	return !strcmp(chip->label, data);
 }
diff --git a/arch/arm/mach-imx/mach-mx51_efikamx.c b/arch/arm/mach-imx/mach-mx51_efikamx.c
index 3a5ed2dd885a..586e9f822124 100644
--- a/arch/arm/mach-imx/mach-mx51_efikamx.c
+++ b/arch/arm/mach-imx/mach-mx51_efikamx.c
@@ -33,6 +33,7 @@
 #include <mach/iomux-mx51.h>
 
 #include <asm/setup.h>
+#include <asm/system_info.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-imx/mach-mx51_efikasb.c b/arch/arm/mach-imx/mach-mx51_efikasb.c
index ea5f65b0381a..24aded9e109f 100644
--- a/arch/arm/mach-imx/mach-mx51_efikasb.c
+++ b/arch/arm/mach-imx/mach-mx51_efikasb.c
@@ -36,6 +36,7 @@
 #include <mach/iomux-mx51.h>
 
 #include <asm/setup.h>
+#include <asm/system_info.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-imx/mach-mx53_ard.c b/arch/arm/mach-imx/mach-mx53_ard.c
index 753f4fc9ec04..05641980dc5e 100644
--- a/arch/arm/mach-imx/mach-mx53_ard.c
+++ b/arch/arm/mach-imx/mach-mx53_ard.c
@@ -23,6 +23,8 @@
 #include <linux/delay.h>
 #include <linux/gpio.h>
 #include <linux/smsc911x.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 
 #include <mach/common.h>
 #include <mach/hardware.h>
@@ -214,6 +216,11 @@ static int weim_cs_config(void)
 	return 0;
 }
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
+
 void __init imx53_ard_common_init(void)
 {
 	mxc_iomux_v3_setup_multiple_pads(mx53_ard_pads,
@@ -232,6 +239,7 @@ static void __init mx53_ard_board_init(void)
 
 	imx53_ard_common_init();
 	mx53_ard_io_init();
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	imx53_add_sdhci_esdhc_imx(0, &mx53_ard_sd1_data);
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index f8ca96c354f2..74127389e7ab 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -21,6 +21,7 @@
 #include <linux/err.h>
 
 #include <asm/pgtable.h>
+#include <asm/system_misc.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/mach/map.h>
 
@@ -61,8 +62,8 @@ static void imx3_idle(void)
 		: "=r" (reg));
 }
 
-static void __iomem *imx3_ioremap(unsigned long phys_addr, size_t size,
-				  unsigned int mtype)
+static void __iomem *imx3_ioremap_caller(unsigned long phys_addr, size_t size,
+					 unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
 		/*
@@ -75,7 +76,7 @@ static void __iomem *imx3_ioremap(unsigned long phys_addr, size_t size,
 			mtype = MT_DEVICE_NONSHARED;
 	}
 
-	return __arm_ioremap(phys_addr, size, mtype);
+	return __arm_ioremap_caller(phys_addr, size, mtype, caller);
 }
 
 void __init imx3_init_l2x0(void)
@@ -134,7 +135,7 @@ void __init imx31_init_early(void)
 {
 	mxc_set_cpu_type(MXC_CPU_MX31);
 	mxc_arch_reset_init(MX31_IO_ADDRESS(MX31_WDOG_BASE_ADDR));
-	imx_ioremap = imx3_ioremap;
+	arch_ioremap_caller = imx3_ioremap_caller;
 	arm_pm_idle = imx3_idle;
 }
 
@@ -208,7 +209,7 @@ void __init imx35_init_early(void)
 	mxc_iomux_v3_init(MX35_IO_ADDRESS(MX35_IOMUXC_BASE_ADDR));
 	mxc_arch_reset_init(MX35_IO_ADDRESS(MX35_WDOG_BASE_ADDR));
 	arm_pm_idle = imx3_idle;
-	imx_ioremap = imx3_ioremap;
+	arch_ioremap_caller = imx3_ioremap_caller;
 }
 
 void __init mx35_init_irq(void)
diff --git a/arch/arm/mach-imx/mm-imx5.c b/arch/arm/mach-imx/mm-imx5.c
index 51af9fa56944..05250aed61fb 100644
--- a/arch/arm/mach-imx/mm-imx5.c
+++ b/arch/arm/mach-imx/mm-imx5.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/clk.h>
 
+#include <asm/system_misc.h>
 #include <asm/mach/map.h>
 
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c
index 15b87f26ac96..eaf6c6366ffa 100644
--- a/arch/arm/mach-integrator/core.c
+++ b/arch/arm/mach-integrator/core.c
@@ -25,9 +25,9 @@
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
 #include <mach/cm.h>
-#include <asm/system.h>
+#include <mach/irqs.h>
+
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-integrator/include/mach/io.h b/arch/arm/mach-integrator/include/mach/io.h
index 37beed3fa3ed..8de70de3dd0a 100644
--- a/arch/arm/mach-integrator/include/mach/io.h
+++ b/arch/arm/mach-integrator/include/mach/io.h
@@ -29,6 +29,5 @@
 #define PCI_IO_VADDR            0xee000000
 
 #define __io(a)			((void __iomem *)(PCI_IO_VADDR + (a)))
-#define __mem_pci(a)		(a)
 
 #endif
diff --git a/arch/arm/mach-integrator/include/mach/irqs.h b/arch/arm/mach-integrator/include/mach/irqs.h
index 1fbe6d190222..a19a1a2fcf6b 100644
--- a/arch/arm/mach-integrator/include/mach/irqs.h
+++ b/arch/arm/mach-integrator/include/mach/irqs.h
@@ -78,5 +78,6 @@
 #define IRQ_SIC_CP_LMINT7		46
 #define IRQ_SIC_END			46
 
-#define NR_IRQS                         47
+#define NR_IRQS_INTEGRATOR_AP		34
+#define NR_IRQS_INTEGRATOR_CP		47
 
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 21a1d6cbef40..871f148ffd72 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -38,12 +38,13 @@
 #include <mach/hardware.h>
 #include <mach/platform.h>
 #include <asm/hardware/arm_timer.h>
-#include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/param.h>		/* HZ */
 #include <asm/mach-types.h>
+#include <asm/sched_clock.h>
 
 #include <mach/lm.h>
+#include <mach/irqs.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -325,6 +326,11 @@ static void __init ap_init(void)
 
 static unsigned long timer_reload;
 
+static u32 notrace integrator_read_sched_clock(void)
+{
+	return -readl((void __iomem *) TIMER2_VA_BASE + TIMER_VALUE);
+}
+
 static void integrator_clocksource_init(unsigned long inrate)
 {
 	void __iomem *base = (void __iomem *)TIMER2_VA_BASE;
@@ -341,6 +347,7 @@ static void integrator_clocksource_init(unsigned long inrate)
 
 	clocksource_mmio_init(base + TIMER_VALUE, "timer2",
 			rate, 200, 16, clocksource_mmio_readl_down);
+	setup_sched_clock(integrator_read_sched_clock, 16, rate);
 }
 
 static void __iomem * const clkevt_base = (void __iomem *)TIMER1_VA_BASE;
@@ -468,6 +475,7 @@ MACHINE_START(INTEGRATOR, "ARM-Integrator")
 	.atag_offset	= 0x100,
 	.reserve	= integrator_reserve,
 	.map_io		= ap_map_io,
+	.nr_irqs	= NR_IRQS_INTEGRATOR_AP,
 	.init_early	= integrator_init_early,
 	.init_irq	= ap_init_irq,
 	.timer		= &ap_timer,
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index be9ead4a3bcc..48a115a91d9d 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -26,7 +26,6 @@
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
 #include <asm/hardware/arm_timer.h>
@@ -34,6 +33,7 @@
 
 #include <mach/cm.h>
 #include <mach/lm.h>
+#include <mach/irqs.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -464,6 +464,7 @@ MACHINE_START(CINTEGRATOR, "ARM-IntegratorCP")
 	.atag_offset	= 0x100,
 	.reserve	= integrator_reserve,
 	.map_io		= intcp_map_io,
+	.nr_irqs	= NR_IRQS_INTEGRATOR_CP,
 	.init_early	= intcp_init_early,
 	.init_irq	= intcp_init_irq,
 	.timer		= &cp_timer,
diff --git a/arch/arm/mach-integrator/leds.c b/arch/arm/mach-integrator/leds.c
index 28be186adb89..466defa97842 100644
--- a/arch/arm/mach-integrator/leds.c
+++ b/arch/arm/mach-integrator/leds.c
@@ -29,7 +29,6 @@
 #include <mach/hardware.h>
 #include <mach/platform.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 #include <asm/mach-types.h>
 #include <mach/cm.h>
 
diff --git a/arch/arm/mach-integrator/pci.c b/arch/arm/mach-integrator/pci.c
index 520b6bf81bb1..f1ca9c122861 100644
--- a/arch/arm/mach-integrator/pci.c
+++ b/arch/arm/mach-integrator/pci.c
@@ -26,11 +26,11 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 
-#include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/mach/pci.h>
 #include <asm/mach-types.h>
 
+#include <mach/irqs.h>
+
 /* 
  * A small note about bridges and interrupts.  The DECchip 21050 (and
  * later) adheres to the PCI-PCI bridge specification.  This says that
diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index 015be770c1d8..67e6f9a9d1a0 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -30,9 +30,9 @@
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
+#include <mach/irqs.h>
+
 #include <asm/signal.h>
-#include <asm/system.h>
 #include <asm/mach/pci.h>
 #include <asm/irq_regs.h>
 
diff --git a/arch/arm/mach-iop13xx/include/mach/io.h b/arch/arm/mach-iop13xx/include/mach/io.h
index dffb234bb967..f13188518025 100644
--- a/arch/arm/mach-iop13xx/include/mach/io.h
+++ b/arch/arm/mach-iop13xx/include/mach/io.h
@@ -22,20 +22,7 @@
 #define IO_SPACE_LIMIT 0xffffffff
 
 #define __io(a) __iop13xx_io(a)
-#define __mem_pci(a) (a)
-#define __mem_isa(a) (a)
 
 extern void __iomem * __iop13xx_io(unsigned long io_addr);
-extern void __iomem *__iop13xx_ioremap(unsigned long cookie, size_t size,
-	unsigned int mtype);
-extern void __iop13xx_iounmap(void __iomem *addr);
-
-extern u32 iop13xx_atue_mem_base;
-extern u32 iop13xx_atux_mem_base;
-extern size_t iop13xx_atue_mem_size;
-extern size_t iop13xx_atux_mem_size;
-
-#define __arch_ioremap	__iop13xx_ioremap
-#define __arch_iounmap	__iop13xx_iounmap
 
 #endif
diff --git a/arch/arm/mach-iop13xx/include/mach/iop13xx.h b/arch/arm/mach-iop13xx/include/mach/iop13xx.h
index 07e9ff7adafb..e190dcd7d72d 100644
--- a/arch/arm/mach-iop13xx/include/mach/iop13xx.h
+++ b/arch/arm/mach-iop13xx/include/mach/iop13xx.h
@@ -5,6 +5,7 @@
 /* The ATU offsets can change based on the strapping */
 extern u32 iop13xx_atux_pmmr_offset;
 extern u32 iop13xx_atue_pmmr_offset;
+void iop13xx_init_early(void);
 void iop13xx_init_irq(void);
 void iop13xx_map_io(void);
 void iop13xx_platform_init(void);
diff --git a/arch/arm/mach-iop13xx/io.c b/arch/arm/mach-iop13xx/io.c
index 48642e66c566..3c364198db9c 100644
--- a/arch/arm/mach-iop13xx/io.c
+++ b/arch/arm/mach-iop13xx/io.c
@@ -21,6 +21,8 @@
 #include <linux/io.h>
 #include <mach/hardware.h>
 
+#include "pci.h"
+
 void * __iomem __iop13xx_io(unsigned long io_addr)
 {
 	void __iomem * io_virt;
@@ -40,8 +42,8 @@ void * __iomem __iop13xx_io(unsigned long io_addr)
 }
 EXPORT_SYMBOL(__iop13xx_io);
 
-void * __iomem __iop13xx_ioremap(unsigned long cookie, size_t size,
-	unsigned int mtype)
+static void __iomem *__iop13xx_ioremap_caller(unsigned long cookie,
+	size_t size, unsigned int mtype, void *caller)
 {
 	void __iomem * retval;
 
@@ -76,17 +78,14 @@ void * __iomem __iop13xx_ioremap(unsigned long cookie, size_t size,
 		break;
 	default:
 		retval = __arm_ioremap_caller(cookie, size, mtype,
-				__builtin_return_address(0));
+				caller);
 	}
 
 	return retval;
 }
-EXPORT_SYMBOL(__iop13xx_ioremap);
 
-void __iop13xx_iounmap(void __iomem *addr)
+static void __iop13xx_iounmap(volatile void __iomem *addr)
 {
-	extern void __iounmap(volatile void __iomem *addr);
-
 	if (iop13xx_atue_mem_base)
 		if (addr >= (void __iomem *) iop13xx_atue_mem_base &&
 	 	    addr < (void __iomem *) (iop13xx_atue_mem_base +
@@ -110,4 +109,9 @@ void __iop13xx_iounmap(void __iomem *addr)
 skip:
 	return;
 }
-EXPORT_SYMBOL(__iop13xx_iounmap);
+
+void __init iop13xx_init_early(void)
+{
+	arch_ioremap_caller = __iop13xx_ioremap_caller;
+	arch_iounmap = __iop13xx_iounmap;
+}
diff --git a/arch/arm/mach-iop13xx/iq81340mc.c b/arch/arm/mach-iop13xx/iq81340mc.c
index abaee8833588..5c96b73e6964 100644
--- a/arch/arm/mach-iop13xx/iq81340mc.c
+++ b/arch/arm/mach-iop13xx/iq81340mc.c
@@ -92,6 +92,7 @@ static struct sys_timer iq81340mc_timer = {
 MACHINE_START(IQ81340MC, "Intel IQ81340MC")
 	/* Maintainer: Dan Williams <dan.j.williams@intel.com> */
 	.atag_offset    = 0x100,
+	.init_early     = iop13xx_init_early,
 	.map_io         = iop13xx_map_io,
 	.init_irq       = iop13xx_init_irq,
 	.timer          = &iq81340mc_timer,
diff --git a/arch/arm/mach-iop13xx/iq81340sc.c b/arch/arm/mach-iop13xx/iq81340sc.c
index 690916a09dc6..aa4dd750135a 100644
--- a/arch/arm/mach-iop13xx/iq81340sc.c
+++ b/arch/arm/mach-iop13xx/iq81340sc.c
@@ -94,6 +94,7 @@ static struct sys_timer iq81340sc_timer = {
 MACHINE_START(IQ81340SC, "Intel IQ81340SC")
 	/* Maintainer: Dan Williams <dan.j.williams@intel.com> */
 	.atag_offset    = 0x100,
+	.init_early     = iop13xx_init_early,
 	.map_io         = iop13xx_map_io,
 	.init_irq       = iop13xx_init_irq,
 	.timer          = &iq81340sc_timer,
diff --git a/arch/arm/mach-iop13xx/pci.h b/arch/arm/mach-iop13xx/pci.h
new file mode 100644
index 000000000000..c70cf5b41e31
--- /dev/null
+++ b/arch/arm/mach-iop13xx/pci.h
@@ -0,0 +1,6 @@
+#include <linux/types.h>
+
+extern u32 iop13xx_atue_mem_base;
+extern u32 iop13xx_atux_mem_base;
+extern size_t iop13xx_atue_mem_size;
+extern size_t iop13xx_atux_mem_size;
diff --git a/arch/arm/mach-iop32x/include/mach/io.h b/arch/arm/mach-iop32x/include/mach/io.h
index 2d88264b9863..e2ada265bb8d 100644
--- a/arch/arm/mach-iop32x/include/mach/io.h
+++ b/arch/arm/mach-iop32x/include/mach/io.h
@@ -15,6 +15,5 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 #define __io(p)		((void __iomem *)IOP3XX_PCI_IO_PHYS_TO_VIRT(p))
-#define __mem_pci(a)		(a)
 
 #endif
diff --git a/arch/arm/mach-iop33x/include/mach/io.h b/arch/arm/mach-iop33x/include/mach/io.h
index a8a66fc8fbdb..f7c1b6595660 100644
--- a/arch/arm/mach-iop33x/include/mach/io.h
+++ b/arch/arm/mach-iop33x/include/mach/io.h
@@ -15,6 +15,5 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 #define __io(p)		((void __iomem *)IOP3XX_PCI_IO_PHYS_TO_VIRT(p))
-#define __mem_pci(a)		(a)
 
 #endif
diff --git a/arch/arm/mach-iop33x/uart.c b/arch/arm/mach-iop33x/uart.c
index cdae24e46eea..bbf54d794ce8 100644
--- a/arch/arm/mach-iop33x/uart.c
+++ b/arch/arm/mach-iop33x/uart.c
@@ -22,7 +22,6 @@
 #include <asm/page.h>
 #include <asm/mach/map.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/memory.h>
 #include <mach/hardware.h>
 #include <asm/hardware/iop3xx.h>
diff --git a/arch/arm/mach-ixp2000/core.c b/arch/arm/mach-ixp2000/core.c
index 81c45370a4e6..f214cdff01cb 100644
--- a/arch/arm/mach-ixp2000/core.c
+++ b/arch/arm/mach-ixp2000/core.c
@@ -32,7 +32,6 @@
 #include <asm/memory.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/pgtable.h>
 
diff --git a/arch/arm/mach-ixp2000/enp2611.c b/arch/arm/mach-ixp2000/enp2611.c
index e872d238cd0f..4867f408617c 100644
--- a/arch/arm/mach-ixp2000/enp2611.c
+++ b/arch/arm/mach-ixp2000/enp2611.c
@@ -36,7 +36,6 @@
 #include <asm/irq.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 
diff --git a/arch/arm/mach-ixp2000/include/mach/io.h b/arch/arm/mach-ixp2000/include/mach/io.h
index 859e584914d9..f6552d6f35ab 100644
--- a/arch/arm/mach-ixp2000/include/mach/io.h
+++ b/arch/arm/mach-ixp2000/include/mach/io.h
@@ -18,7 +18,6 @@
 #include <mach/hardware.h>
 
 #define IO_SPACE_LIMIT		0xffffffff
-#define __mem_pci(a)		(a)
 
 /*
  * The A? revisions of the IXP2000s assert byte lanes for PCI I/O
diff --git a/arch/arm/mach-ixp2000/ixdp2400.c b/arch/arm/mach-ixp2000/ixdp2400.c
index d519944653ad..915ad49e3b8f 100644
--- a/arch/arm/mach-ixp2000/ixdp2400.c
+++ b/arch/arm/mach-ixp2000/ixdp2400.c
@@ -29,7 +29,6 @@
 #include <asm/irq.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 
diff --git a/arch/arm/mach-ixp2000/ixdp2800.c b/arch/arm/mach-ixp2000/ixdp2800.c
index b415febd2025..a9f1819ea049 100644
--- a/arch/arm/mach-ixp2000/ixdp2800.c
+++ b/arch/arm/mach-ixp2000/ixdp2800.c
@@ -29,7 +29,6 @@
 #include <asm/irq.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 
diff --git a/arch/arm/mach-ixp2000/ixdp2x00.c b/arch/arm/mach-ixp2000/ixdp2x00.c
index dd9838299068..421e38dc0fac 100644
--- a/arch/arm/mach-ixp2000/ixdp2x00.c
+++ b/arch/arm/mach-ixp2000/ixdp2x00.c
@@ -30,7 +30,6 @@
 #include <asm/irq.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 
diff --git a/arch/arm/mach-ixp2000/ixdp2x01.c b/arch/arm/mach-ixp2000/ixdp2x01.c
index 7632beadabf6..5196c39cdba4 100644
--- a/arch/arm/mach-ixp2000/ixdp2x01.c
+++ b/arch/arm/mach-ixp2000/ixdp2x01.c
@@ -34,7 +34,6 @@
 #include <asm/irq.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 
diff --git a/arch/arm/mach-ixp2000/pci.c b/arch/arm/mach-ixp2000/pci.c
index 49c36f3cd602..9c02de932fac 100644
--- a/arch/arm/mach-ixp2000/pci.c
+++ b/arch/arm/mach-ixp2000/pci.c
@@ -26,7 +26,6 @@
 #include <linux/io.h>
 
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <mach/hardware.h>
 
 #include <asm/mach/pci.h>
diff --git a/arch/arm/mach-ixp23xx/core.c b/arch/arm/mach-ixp23xx/core.c
index 7c1495e4fe7a..d34542425990 100644
--- a/arch/arm/mach-ixp23xx/core.c
+++ b/arch/arm/mach-ixp23xx/core.c
@@ -34,9 +34,9 @@
 #include <asm/memory.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/pgtable.h>
+#include <asm/system_misc.h>
 
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-ixp23xx/espresso.c b/arch/arm/mach-ixp23xx/espresso.c
index 8f2487e1fc4e..d142d45dea12 100644
--- a/arch/arm/mach-ixp23xx/espresso.c
+++ b/arch/arm/mach-ixp23xx/espresso.c
@@ -32,7 +32,6 @@
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/pgtable.h>
 
diff --git a/arch/arm/mach-ixp23xx/include/mach/io.h b/arch/arm/mach-ixp23xx/include/mach/io.h
index 4ce4353b9f72..a7aceb55c130 100644
--- a/arch/arm/mach-ixp23xx/include/mach/io.h
+++ b/arch/arm/mach-ixp23xx/include/mach/io.h
@@ -18,6 +18,5 @@
 #define IO_SPACE_LIMIT 0xffffffff
 
 #define __io(p)		((void __iomem*)((p) + IXP23XX_PCI_IO_VIRT))
-#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-ixp23xx/ixdp2351.c b/arch/arm/mach-ixp23xx/ixdp2351.c
index 5d5dd3e8d069..b0e07db5ceaf 100644
--- a/arch/arm/mach-ixp23xx/ixdp2351.c
+++ b/arch/arm/mach-ixp23xx/ixdp2351.c
@@ -36,7 +36,6 @@
 #include <asm/memory.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/pgtable.h>
 
diff --git a/arch/arm/mach-ixp23xx/pci.c b/arch/arm/mach-ixp23xx/pci.c
index 3cbbd3208fa8..911f5a58e006 100644
--- a/arch/arm/mach-ixp23xx/pci.c
+++ b/arch/arm/mach-ixp23xx/pci.c
@@ -28,7 +28,6 @@
 
 #include <asm/irq.h>
 #include <asm/sizes.h>
-#include <asm/system.h>
 #include <asm/mach/pci.h>
 #include <mach/hardware.h>
 
diff --git a/arch/arm/mach-ixp23xx/roadrunner.c b/arch/arm/mach-ixp23xx/roadrunner.c
index 377283fc658c..eaaa3fa9fd05 100644
--- a/arch/arm/mach-ixp23xx/roadrunner.c
+++ b/arch/arm/mach-ixp23xx/roadrunner.c
@@ -36,7 +36,6 @@
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/pgtable.h>
 
diff --git a/arch/arm/mach-ixp4xx/avila-setup.c b/arch/arm/mach-ixp4xx/avila-setup.c
index a7277ad470a5..90e42e9982cb 100644
--- a/arch/arm/mach-ixp4xx/avila-setup.c
+++ b/arch/arm/mach-ixp4xx/avila-setup.c
@@ -165,6 +165,7 @@ static void __init avila_init(void)
 MACHINE_START(AVILA, "Gateworks Avila Network Platform")
 	/* Maintainer: Deepak Saxena <dsaxena@plexity.net> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -184,6 +185,7 @@ MACHINE_END
 MACHINE_START(LOFT, "Giant Shoulder Inc Loft board")
 	/* Maintainer: Tom Billman <kernel@giantshoulderinc.com> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c
index 8508882b13f0..d5719eb42591 100644
--- a/arch/arm/mach-ixp4xx/common-pci.c
+++ b/arch/arm/mach-ixp4xx/common-pci.c
@@ -32,7 +32,6 @@
 #include <asm/cputype.h>
 #include <asm/irq.h>
 #include <asm/sizes.h>
-#include <asm/system.h>
 #include <asm/mach/pci.h>
 #include <mach/hardware.h>
 
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index a6329a0a8ec4..ebbd7fc90eb4 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -31,11 +31,13 @@
 
 #include <mach/udc.h>
 #include <mach/hardware.h>
+#include <mach/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/irq.h>
 #include <asm/sched_clock.h>
+#include <asm/system_misc.h>
 
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
@@ -517,3 +519,35 @@ void ixp4xx_restart(char mode, const char *cmd)
 		*IXP4XX_OSWE = IXP4XX_WDT_RESET_ENABLE | IXP4XX_WDT_COUNT_ENABLE;
 	}
 }
+
+#ifdef CONFIG_IXP4XX_INDIRECT_PCI
+/*
+ * In the case of using indirect PCI, we simply return the actual PCI
+ * address and our read/write implementation use that to drive the
+ * access registers. If something outside of PCI is ioremap'd, we
+ * fallback to the default.
+ */
+
+static void __iomem *ixp4xx_ioremap_caller(unsigned long addr, size_t size,
+					   unsigned int mtype, void *caller)
+{
+	if (!is_pci_memory(addr))
+		return __arm_ioremap_caller(addr, size, mtype, caller);
+
+	return (void __iomem *)addr;
+}
+
+static void ixp4xx_iounmap(void __iomem *addr)
+{
+	if (!is_pci_memory((__force u32)addr))
+		__iounmap(addr);
+}
+
+void __init ixp4xx_init_early(void)
+{
+	arch_ioremap_caller = ixp4xx_ioremap_caller;
+	arch_iounmap = ixp4xx_iounmap;
+}
+#else
+void __init ixp4xx_init_early(void) {}
+#endif
diff --git a/arch/arm/mach-ixp4xx/coyote-setup.c b/arch/arm/mach-ixp4xx/coyote-setup.c
index a74f86ce8bcc..1b83110028d6 100644
--- a/arch/arm/mach-ixp4xx/coyote-setup.c
+++ b/arch/arm/mach-ixp4xx/coyote-setup.c
@@ -110,6 +110,7 @@ static void __init coyote_init(void)
 MACHINE_START(ADI_COYOTE, "ADI Engineering Coyote")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -129,6 +130,7 @@ MACHINE_END
 MACHINE_START(IXDPG425, "Intel IXDPG425")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c
index 67be177b336a..97a0af8f1955 100644
--- a/arch/arm/mach-ixp4xx/dsmg600-setup.c
+++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c
@@ -280,6 +280,7 @@ MACHINE_START(DSMG600, "D-Link DSM-G600 RevA")
 	/* Maintainer: www.nslu2-linux.org */
 	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &dsmg600_timer,
 	.init_machine	= dsmg600_init,
diff --git a/arch/arm/mach-ixp4xx/fsg-setup.c b/arch/arm/mach-ixp4xx/fsg-setup.c
index 6d5818285af8..9175a25a7511 100644
--- a/arch/arm/mach-ixp4xx/fsg-setup.c
+++ b/arch/arm/mach-ixp4xx/fsg-setup.c
@@ -270,6 +270,7 @@ static void __init fsg_init(void)
 MACHINE_START(FSG, "Freecom FSG-3")
 	/* Maintainer: www.nslu2-linux.org */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/gateway7001-setup.c b/arch/arm/mach-ixp4xx/gateway7001-setup.c
index 7ecf9b28f1c0..033c71758953 100644
--- a/arch/arm/mach-ixp4xx/gateway7001-setup.c
+++ b/arch/arm/mach-ixp4xx/gateway7001-setup.c
@@ -97,6 +97,7 @@ static void __init gateway7001_init(void)
 MACHINE_START(GATEWAY7001, "Gateway 7001 AP")
 	/* Maintainer: Imre Kaloz <kaloz@openwrt.org> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/goramo_mlr.c b/arch/arm/mach-ixp4xx/goramo_mlr.c
index c0e3d69a8aec..46bb924962ee 100644
--- a/arch/arm/mach-ixp4xx/goramo_mlr.c
+++ b/arch/arm/mach-ixp4xx/goramo_mlr.c
@@ -12,7 +12,6 @@
 #include <linux/pci.h>
 #include <linux/serial_8250.h>
 #include <asm/mach-types.h>
-#include <asm/system.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/pci.h>
@@ -497,6 +496,7 @@ subsys_initcall(gmlr_pci_init);
 MACHINE_START(GORAMO_MLR, "MultiLink")
 	/* Maintainer: Krzysztof Halasa */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/gtwx5715-setup.c b/arch/arm/mach-ixp4xx/gtwx5715-setup.c
index a23f89391458..18ebc6be7969 100644
--- a/arch/arm/mach-ixp4xx/gtwx5715-setup.c
+++ b/arch/arm/mach-ixp4xx/gtwx5715-setup.c
@@ -165,6 +165,7 @@ static void __init gtwx5715_init(void)
 MACHINE_START(GTWX5715, "Gemtek GTWX5715 (Linksys WRV54G)")
 	/* Maintainer: George Joseph */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/include/mach/hardware.h b/arch/arm/mach-ixp4xx/include/mach/hardware.h
index c30e7e923a73..034bb2a1b805 100644
--- a/arch/arm/mach-ixp4xx/include/mach/hardware.h
+++ b/arch/arm/mach-ixp4xx/include/mach/hardware.h
@@ -23,8 +23,6 @@
 #define PCIBIOS_MAX_MEM		0x4BFFFFFF
 #endif
 
-#define ARCH_HAS_DMA_SET_COHERENT_MASK
-
 /* Register locations and bits */
 #include "ixp4xx-regs.h"
 
diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h
index ffb9d6afb89f..5cf30d1b78d2 100644
--- a/arch/arm/mach-ixp4xx/include/mach/io.h
+++ b/arch/arm/mach-ixp4xx/include/mach/io.h
@@ -39,11 +39,7 @@ extern int ixp4xx_pci_write(u32 addr, u32 cmd, u32 data);
  *    but in some cases the performance hit is acceptable. In addition, you
  *    cannot mmap() PCI devices in this case.
  */
-#ifndef	CONFIG_IXP4XX_INDIRECT_PCI
-
-#define __mem_pci(a)		(a)
-
-#else
+#ifdef	CONFIG_IXP4XX_INDIRECT_PCI
 
 /*
  * In the case of using indirect PCI, we simply return the actual PCI
@@ -57,24 +53,6 @@ static inline int is_pci_memory(u32 addr)
 	return (addr >= PCIBIOS_MIN_MEM) && (addr <= 0x4FFFFFFF);
 }
 
-static inline void __iomem * __indirect_ioremap(unsigned long addr, size_t size,
-						unsigned int mtype)
-{
-	if (!is_pci_memory(addr))
-		return __arm_ioremap(addr, size, mtype);
-
-	return (void __iomem *)addr;
-}
-
-static inline void __indirect_iounmap(void __iomem *addr)
-{
-	if (!is_pci_memory((__force u32)addr))
-		__iounmap(addr);
-}
-
-#define __arch_ioremap			__indirect_ioremap
-#define __arch_iounmap			__indirect_iounmap
-
 #define writeb(v, p)			__indirect_writeb(v, p)
 #define writew(v, p)			__indirect_writew(v, p)
 #define writel(v, p)			__indirect_writel(v, p)
diff --git a/arch/arm/mach-ixp4xx/include/mach/platform.h b/arch/arm/mach-ixp4xx/include/mach/platform.h
index df9250bbf13d..b66bedc64de1 100644
--- a/arch/arm/mach-ixp4xx/include/mach/platform.h
+++ b/arch/arm/mach-ixp4xx/include/mach/platform.h
@@ -121,6 +121,7 @@ extern unsigned long ixp4xx_timer_freq;
  * Functions used by platform-level setup code
  */
 extern void ixp4xx_map_io(void);
+extern void ixp4xx_init_early(void);
 extern void ixp4xx_init_irq(void);
 extern void ixp4xx_sys_init(void);
 extern void ixp4xx_timer_init(void);
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index 8a38b39999f8..3d742aee1773 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -254,6 +254,7 @@ static void __init ixdp425_init(void)
 MACHINE_START(IXDP425, "Intel IXDP425 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -269,6 +270,7 @@ MACHINE_END
 MACHINE_START(IXDP465, "Intel IXDP465 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -283,6 +285,7 @@ MACHINE_END
 MACHINE_START(IXCDP1100, "Intel IXCDP1100 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
@@ -297,6 +300,7 @@ MACHINE_END
 MACHINE_START(KIXRP435, "Intel KIXRP435 Reference Platform")
 	/* Maintainer: MontaVista Software, Inc. */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
index 1010eb7b0083..33cb0955b6bf 100644
--- a/arch/arm/mach-ixp4xx/nas100d-setup.c
+++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
@@ -315,6 +315,7 @@ MACHINE_START(NAS100D, "Iomega NAS 100d")
 	/* Maintainer: www.nslu2-linux.org */
 	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
 	.init_machine	= nas100d_init,
diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c
index aa355c360d57..e2903faaebb3 100644
--- a/arch/arm/mach-ixp4xx/nslu2-setup.c
+++ b/arch/arm/mach-ixp4xx/nslu2-setup.c
@@ -301,6 +301,7 @@ MACHINE_START(NSLU2, "Linksys NSLU2")
 	/* Maintainer: www.nslu2-linux.org */
 	.atag_offset	= 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &nslu2_timer,
 	.init_machine	= nslu2_init,
diff --git a/arch/arm/mach-ixp4xx/omixp-setup.c b/arch/arm/mach-ixp4xx/omixp-setup.c
index 0940869fcfdd..158ddb79821d 100644
--- a/arch/arm/mach-ixp4xx/omixp-setup.c
+++ b/arch/arm/mach-ixp4xx/omixp-setup.c
@@ -243,6 +243,7 @@ static void __init omixp_init(void)
 MACHINE_START(DEVIXP, "Omicron DEVIXP")
 	.atag_offset    = 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
 	.init_machine	= omixp_init,
@@ -254,6 +255,7 @@ MACHINE_END
 MACHINE_START(MICCPT, "Omicron MICCPT")
 	.atag_offset    = 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
 	.init_machine	= omixp_init,
@@ -268,6 +270,7 @@ MACHINE_END
 MACHINE_START(MIC256, "Omicron MIC256")
 	.atag_offset    = 0x100,
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer          = &ixp4xx_timer,
 	.init_machine	= omixp_init,
diff --git a/arch/arm/mach-ixp4xx/vulcan-setup.c b/arch/arm/mach-ixp4xx/vulcan-setup.c
index 9dec20683291..2798f435aaf4 100644
--- a/arch/arm/mach-ixp4xx/vulcan-setup.c
+++ b/arch/arm/mach-ixp4xx/vulcan-setup.c
@@ -237,6 +237,7 @@ static void __init vulcan_init(void)
 MACHINE_START(ARCOM_VULCAN, "Arcom/Eurotech Vulcan")
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-ixp4xx/wg302v2-setup.c b/arch/arm/mach-ixp4xx/wg302v2-setup.c
index 5ac0f0a0fd8c..a785175b115b 100644
--- a/arch/arm/mach-ixp4xx/wg302v2-setup.c
+++ b/arch/arm/mach-ixp4xx/wg302v2-setup.c
@@ -98,6 +98,7 @@ static void __init wg302v2_init(void)
 MACHINE_START(WG302V2, "Netgear WG302 v2 / WAG302 v2")
 	/* Maintainer: Imre Kaloz <kaloz@openwrt.org> */
 	.map_io		= ixp4xx_map_io,
+	.init_early	= ixp4xx_init_early,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
 	.atag_offset	= 0x100,
diff --git a/arch/arm/mach-kirkwood/Makefile b/arch/arm/mach-kirkwood/Makefile
index acbc5e1db06f..e299a9576bf0 100644
--- a/arch/arm/mach-kirkwood/Makefile
+++ b/arch/arm/mach-kirkwood/Makefile
@@ -21,3 +21,4 @@ obj-$(CONFIG_MACH_T5325)		+= t5325-setup.o
 
 obj-$(CONFIG_CPU_IDLE)			+= cpuidle.o
 obj-$(CONFIG_ARCH_KIRKWOOD_DT)		+= board-dt.o
+obj-$(CONFIG_MACH_DREAMPLUG_DT)		+= board-dreamplug.o
diff --git a/arch/arm/mach-kirkwood/board-dreamplug.c b/arch/arm/mach-kirkwood/board-dreamplug.c
new file mode 100644
index 000000000000..985453994dd3
--- /dev/null
+++ b/arch/arm/mach-kirkwood/board-dreamplug.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright 2012 (C), Jason Cooper <jason@lakedaemon.net>
+ *
+ * arch/arm/mach-kirkwood/board-dreamplug.c
+ *
+ * Marvell DreamPlug Reference Board Init for drivers not converted to
+ * flattened device tree yet.
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/partitions.h>
+#include <linux/ata_platform.h>
+#include <linux/mv643xx_eth.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/gpio.h>
+#include <linux/leds.h>
+#include <linux/mtd/physmap.h>
+#include <linux/spi/flash.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/orion_spi.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <mach/kirkwood.h>
+#include <mach/bridge-regs.h>
+#include <plat/mvsdio.h>
+#include "common.h"
+#include "mpp.h"
+
+struct mtd_partition dreamplug_partitions[] = {
+	{
+		.name	= "u-boot",
+		.size	= SZ_512K,
+		.offset = 0,
+	},
+	{
+		.name	= "u-boot env",
+		.size	= SZ_64K,
+		.offset = SZ_512K + SZ_512K,
+	},
+	{
+		.name	= "dtb",
+		.size	= SZ_64K,
+		.offset = SZ_512K + SZ_512K + SZ_512K,
+	},
+};
+
+static const struct flash_platform_data dreamplug_spi_slave_data = {
+	.type		= "mx25l1606e",
+	.name		= "spi_flash",
+	.parts		= dreamplug_partitions,
+	.nr_parts	= ARRAY_SIZE(dreamplug_partitions),
+};
+
+static struct spi_board_info __initdata dreamplug_spi_slave_info[] = {
+	{
+		.modalias	= "m25p80",
+		.platform_data	= &dreamplug_spi_slave_data,
+		.irq		= -1,
+		.max_speed_hz	= 50000000,
+		.bus_num	= 0,
+		.chip_select	= 0,
+	},
+};
+
+static struct mv643xx_eth_platform_data dreamplug_ge00_data = {
+	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
+};
+
+static struct mv643xx_eth_platform_data dreamplug_ge01_data = {
+	.phy_addr	= MV643XX_ETH_PHY_ADDR(1),
+};
+
+static struct mv_sata_platform_data dreamplug_sata_data = {
+	.n_ports	= 1,
+};
+
+static struct mvsdio_platform_data dreamplug_mvsdio_data = {
+	/* unfortunately the CD signal has not been connected */
+};
+
+static struct gpio_led dreamplug_led_pins[] = {
+	{
+		.name			= "dreamplug:blue:bluetooth",
+		.gpio			= 47,
+		.active_low		= 1,
+	},
+	{
+		.name			= "dreamplug:green:wifi",
+		.gpio			= 48,
+		.active_low		= 1,
+	},
+	{
+		.name			= "dreamplug:green:wifi_ap",
+		.gpio			= 49,
+		.active_low		= 1,
+	},
+};
+
+static struct gpio_led_platform_data dreamplug_led_data = {
+	.leds		= dreamplug_led_pins,
+	.num_leds	= ARRAY_SIZE(dreamplug_led_pins),
+};
+
+static struct platform_device dreamplug_leds = {
+	.name	= "leds-gpio",
+	.id	= -1,
+	.dev	= {
+		.platform_data	= &dreamplug_led_data,
+	}
+};
+
+static unsigned int dreamplug_mpp_config[] __initdata = {
+	MPP0_SPI_SCn,
+	MPP1_SPI_MOSI,
+	MPP2_SPI_SCK,
+	MPP3_SPI_MISO,
+	MPP47_GPIO,	/* Bluetooth LED */
+	MPP48_GPIO,	/* Wifi LED */
+	MPP49_GPIO,	/* Wifi AP LED */
+	0
+};
+
+void __init dreamplug_init(void)
+{
+	/*
+	 * Basic setup. Needs to be called early.
+	 */
+	kirkwood_mpp_conf(dreamplug_mpp_config);
+
+	spi_register_board_info(dreamplug_spi_slave_info,
+				ARRAY_SIZE(dreamplug_spi_slave_info));
+	kirkwood_spi_init();
+
+	kirkwood_ehci_init();
+	kirkwood_ge00_init(&dreamplug_ge00_data);
+	kirkwood_ge01_init(&dreamplug_ge01_data);
+	kirkwood_sata_init(&dreamplug_sata_data);
+	kirkwood_sdio_init(&dreamplug_mvsdio_data);
+
+	platform_device_register(&dreamplug_leds);
+}
diff --git a/arch/arm/mach-kirkwood/board-dt.c b/arch/arm/mach-kirkwood/board-dt.c
index fbe6405602ed..1c672d9e6656 100644
--- a/arch/arm/mach-kirkwood/board-dt.c
+++ b/arch/arm/mach-kirkwood/board-dt.c
@@ -3,7 +3,7 @@
  *
  * arch/arm/mach-kirkwood/board-dt.c
  *
- * Marvell DreamPlug Reference Board Setup
+ * Flattened Device Tree board initialization
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2.  This program is licensed "as is" without any
@@ -12,150 +12,45 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/partitions.h>
-#include <linux/ata_platform.h>
-#include <linux/mv643xx_eth.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_fdt.h>
-#include <linux/of_irq.h>
 #include <linux/of_platform.h>
-#include <linux/gpio.h>
-#include <linux/leds.h>
-#include <linux/mtd/physmap.h>
-#include <linux/spi/flash.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/orion_spi.h>
-#include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <mach/kirkwood.h>
-#include <plat/mvsdio.h>
+#include <asm/mach/map.h>
+#include <mach/bridge-regs.h>
 #include "common.h"
-#include "mpp.h"
 
 static struct of_device_id kirkwood_dt_match_table[] __initdata = {
 	{ .compatible = "simple-bus", },
 	{ }
 };
 
-struct mtd_partition dreamplug_partitions[] = {
-	{
-		.name	= "u-boot",
-		.size	= SZ_512K,
-		.offset = 0,
-	},
-	{
-		.name	= "u-boot env",
-		.size	= SZ_64K,
-		.offset = SZ_512K + SZ_512K,
-	},
-	{
-		.name	= "dtb",
-		.size	= SZ_64K,
-		.offset = SZ_512K + SZ_512K + SZ_512K,
-	},
-};
-
-static const struct flash_platform_data dreamplug_spi_slave_data = {
-	.type		= "mx25l1606e",
-	.name		= "spi_flash",
-	.parts		= dreamplug_partitions,
-	.nr_parts	= ARRAY_SIZE(dreamplug_partitions),
-};
-
-static struct spi_board_info __initdata dreamplug_spi_slave_info[] = {
-	{
-		.modalias	= "m25p80",
-		.platform_data	= &dreamplug_spi_slave_data,
-		.irq		= -1,
-		.max_speed_hz	= 50000000,
-		.bus_num	= 0,
-		.chip_select	= 0,
-	},
-};
-
-static struct mv643xx_eth_platform_data dreamplug_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-static struct mv643xx_eth_platform_data dreamplug_ge01_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(1),
-};
-
-static struct mv_sata_platform_data dreamplug_sata_data = {
-	.n_ports	= 1,
-};
-
-static struct mvsdio_platform_data dreamplug_mvsdio_data = {
-	/* unfortunately the CD signal has not been connected */
-};
-
-static struct gpio_led dreamplug_led_pins[] = {
-	{
-		.name			= "dreamplug:blue:bluetooth",
-		.gpio			= 47,
-		.active_low		= 1,
-	},
-	{
-		.name			= "dreamplug:green:wifi",
-		.gpio			= 48,
-		.active_low		= 1,
-	},
-	{
-		.name			= "dreamplug:green:wifi_ap",
-		.gpio			= 49,
-		.active_low		= 1,
-	},
-};
-
-static struct gpio_led_platform_data dreamplug_led_data = {
-	.leds		= dreamplug_led_pins,
-	.num_leds	= ARRAY_SIZE(dreamplug_led_pins),
-};
-
-static struct platform_device dreamplug_leds = {
-	.name	= "leds-gpio",
-	.id	= -1,
-	.dev	= {
-		.platform_data	= &dreamplug_led_data,
-	}
-};
-
-static unsigned int dreamplug_mpp_config[] __initdata = {
-	MPP0_SPI_SCn,
-	MPP1_SPI_MOSI,
-	MPP2_SPI_SCK,
-	MPP3_SPI_MISO,
-	MPP47_GPIO,	/* Bluetooth LED */
-	MPP48_GPIO,	/* Wifi LED */
-	MPP49_GPIO,	/* Wifi AP LED */
-	0
-};
-
-static void __init dreamplug_init(void)
+static void __init kirkwood_dt_init(void)
 {
+	pr_info("Kirkwood: %s, TCLK=%d.\n", kirkwood_id(), kirkwood_tclk);
+
 	/*
-	 * Basic setup. Needs to be called early.
+	 * Disable propagation of mbus errors to the CPU local bus,
+	 * as this causes mbus errors (which can occur for example
+	 * for PCI aborts) to throw CPU aborts, which we're not set
+	 * up to deal with.
 	 */
-	kirkwood_mpp_conf(dreamplug_mpp_config);
+	writel(readl(CPU_CONFIG) & ~CPU_CONFIG_ERROR_PROP, CPU_CONFIG);
 
-	spi_register_board_info(dreamplug_spi_slave_info,
-				ARRAY_SIZE(dreamplug_spi_slave_info));
-	kirkwood_spi_init();
+	kirkwood_setup_cpu_mbus();
 
-	kirkwood_ehci_init();
-	kirkwood_ge00_init(&dreamplug_ge00_data);
-	kirkwood_ge01_init(&dreamplug_ge01_data);
-	kirkwood_sata_init(&dreamplug_sata_data);
-	kirkwood_sdio_init(&dreamplug_mvsdio_data);
+#ifdef CONFIG_CACHE_FEROCEON_L2
+	kirkwood_l2_init();
+#endif
 
-	platform_device_register(&dreamplug_leds);
-}
+	/* internal devices that every board has */
+	kirkwood_wdt_init();
+	kirkwood_xor0_init();
+	kirkwood_xor1_init();
+	kirkwood_crypto_init();
 
-static void __init kirkwood_dt_init(void)
-{
-	kirkwood_init();
+#ifdef CONFIG_KEXEC
+	kexec_reinit = kirkwood_enable_pcie;
+#endif
 
 	if (of_machine_is_compatible("globalscale,dreamplug"))
 		dreamplug_init();
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index 77d4852e19f2..a02cae881f2f 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -279,7 +279,7 @@ void __init kirkwood_crypto_init(void)
 /*****************************************************************************
  * XOR0
  ****************************************************************************/
-static void __init kirkwood_xor0_init(void)
+void __init kirkwood_xor0_init(void)
 {
 	kirkwood_clk_ctrl |= CGC_XOR0;
 
@@ -291,7 +291,7 @@ static void __init kirkwood_xor0_init(void)
 /*****************************************************************************
  * XOR1
  ****************************************************************************/
-static void __init kirkwood_xor1_init(void)
+void __init kirkwood_xor1_init(void)
 {
 	kirkwood_clk_ctrl |= CGC_XOR1;
 
@@ -303,7 +303,7 @@ static void __init kirkwood_xor1_init(void)
 /*****************************************************************************
  * Watchdog
  ****************************************************************************/
-static void __init kirkwood_wdt_init(void)
+void __init kirkwood_wdt_init(void)
 {
 	orion_wdt_init(kirkwood_tclk);
 }
@@ -392,7 +392,7 @@ void __init kirkwood_audio_init(void)
 /*
  * Identify device ID and revision.
  */
-static char * __init kirkwood_id(void)
+char * __init kirkwood_id(void)
 {
 	u32 dev, rev;
 
@@ -435,7 +435,7 @@ static char * __init kirkwood_id(void)
 	}
 }
 
-static void __init kirkwood_l2_init(void)
+void __init kirkwood_l2_init(void)
 {
 #ifdef CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH
 	writel(readl(L2_CONFIG_REG) | L2_WRITETHROUGH, L2_CONFIG_REG);
@@ -450,7 +450,6 @@ void __init kirkwood_init(void)
 {
 	printk(KERN_INFO "Kirkwood: %s, TCLK=%d.\n",
 		kirkwood_id(), kirkwood_tclk);
-	kirkwood_i2s_data.tclk = kirkwood_tclk;
 
 	/*
 	 * Disable propagation of mbus errors to the CPU local bus,
diff --git a/arch/arm/mach-kirkwood/common.h b/arch/arm/mach-kirkwood/common.h
index 9071a397136d..fa8e7689c436 100644
--- a/arch/arm/mach-kirkwood/common.h
+++ b/arch/arm/mach-kirkwood/common.h
@@ -51,6 +51,21 @@ void kirkwood_nand_init_rnb(struct mtd_partition *parts, int nr_parts, int (*dev
 void kirkwood_audio_init(void);
 void kirkwood_restart(char, const char *);
 
+/* board init functions for boards not fully converted to fdt */
+#ifdef CONFIG_MACH_DREAMPLUG_DT
+void dreamplug_init(void);
+#else
+static inline void dreamplug_init(void) {};
+#endif
+
+/* early init functions not converted to fdt yet */
+char *kirkwood_id(void);
+void kirkwood_l2_init(void);
+void kirkwood_wdt_init(void);
+void kirkwood_xor0_init(void);
+void kirkwood_xor1_init(void);
+void kirkwood_crypto_init(void);
+
 extern int kirkwood_tclk;
 extern struct sys_timer kirkwood_timer;
 
diff --git a/arch/arm/mach-kirkwood/cpuidle.c b/arch/arm/mach-kirkwood/cpuidle.c
index 7088180b018b..0f1710941878 100644
--- a/arch/arm/mach-kirkwood/cpuidle.c
+++ b/arch/arm/mach-kirkwood/cpuidle.c
@@ -20,77 +20,47 @@
 #include <linux/io.h>
 #include <linux/export.h>
 #include <asm/proc-fns.h>
+#include <asm/cpuidle.h>
 #include <mach/kirkwood.h>
 
 #define KIRKWOOD_MAX_STATES	2
 
-static struct cpuidle_driver kirkwood_idle_driver = {
-	.name =         "kirkwood_idle",
-	.owner =        THIS_MODULE,
-};
-
-static DEFINE_PER_CPU(struct cpuidle_device, kirkwood_cpuidle_device);
-
 /* Actual code that puts the SoC in different idle states */
 static int kirkwood_enter_idle(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv,
 			       int index)
 {
-	struct timeval before, after;
-	int idle_time;
-
-	local_irq_disable();
-	do_gettimeofday(&before);
-	if (index == 0)
-		/* Wait for interrupt state */
-		cpu_do_idle();
-	else if (index == 1) {
-		/*
-		 * Following write will put DDR in self refresh.
-		 * Note that we have 256 cycles before DDR puts it
-		 * self in self-refresh, so the wait-for-interrupt
-		 * call afterwards won't get the DDR from self refresh
-		 * mode.
-		 */
-		writel(0x7, DDR_OPERATION_BASE);
-		cpu_do_idle();
-	}
-	do_gettimeofday(&after);
-	local_irq_enable();
-	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
-			(after.tv_usec - before.tv_usec);
-
-	/* Update last residency */
-	dev->last_residency = idle_time;
+	writel(0x7, DDR_OPERATION_BASE);
+	cpu_do_idle();
 
 	return index;
 }
 
+static struct cpuidle_driver kirkwood_idle_driver = {
+	.name			= "kirkwood_idle",
+	.owner			= THIS_MODULE,
+	.en_core_tk_irqen	= 1,
+	.states[0]		= ARM_CPUIDLE_WFI_STATE,
+	.states[1]		= {
+		.enter			= kirkwood_enter_idle,
+		.exit_latency		= 10,
+		.target_residency	= 100000,
+		.flags			= CPUIDLE_FLAG_TIME_VALID,
+		.name			= "DDR SR",
+		.desc			= "WFI and DDR Self Refresh",
+	},
+	.state_count = KIRKWOOD_MAX_STATES,
+};
+
+static DEFINE_PER_CPU(struct cpuidle_device, kirkwood_cpuidle_device);
+
 /* Initialize CPU idle by registering the idle states */
 static int kirkwood_init_cpuidle(void)
 {
 	struct cpuidle_device *device;
-	struct cpuidle_driver *driver = &kirkwood_idle_driver;
 
 	device = &per_cpu(kirkwood_cpuidle_device, smp_processor_id());
 	device->state_count = KIRKWOOD_MAX_STATES;
-	driver->state_count = KIRKWOOD_MAX_STATES;
-
-	/* Wait for interrupt state */
-	driver->states[0].enter = kirkwood_enter_idle;
-	driver->states[0].exit_latency = 1;
-	driver->states[0].target_residency = 10000;
-	driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(driver->states[0].name, "WFI");
-	strcpy(driver->states[0].desc, "Wait for interrupt");
-
-	/* Wait for interrupt and DDR self refresh state */
-	driver->states[1].enter = kirkwood_enter_idle;
-	driver->states[1].exit_latency = 10;
-	driver->states[1].target_residency = 10000;
-	driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(driver->states[1].name, "DDR SR");
-	strcpy(driver->states[1].desc, "WFI and DDR Self Refresh");
 
 	cpuidle_register_driver(&kirkwood_idle_driver);
 	if (cpuidle_register_device(device)) {
diff --git a/arch/arm/mach-kirkwood/include/mach/io.h b/arch/arm/mach-kirkwood/include/mach/io.h
index 49dd0cb5e166..5d0ab61700d2 100644
--- a/arch/arm/mach-kirkwood/include/mach/io.h
+++ b/arch/arm/mach-kirkwood/include/mach/io.h
@@ -20,7 +20,5 @@ static inline void __iomem *__io(unsigned long addr)
 }
 
 #define __io(a)			__io(a)
-#define __mem_pci(a)		(a)
-
 
 #endif
diff --git a/arch/arm/mach-ks8695/include/mach/io.h b/arch/arm/mach-ks8695/include/mach/io.h
deleted file mode 100644
index a7a63ac3ba4e..000000000000
--- a/arch/arm/mach-ks8695/include/mach/io.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * arch/arm/mach-ks8695/include/mach/io.h
- *
- * Copyright (C) 2006 Andrew Victor
- *
- * This file is licensed under  the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __ASM_ARCH_IO_H
-#define __ASM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT		0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-ks8695/time.c b/arch/arm/mach-ks8695/time.c
index 37dfcd5bd2ad..ec783a3070ae 100644
--- a/arch/arm/mach-ks8695/time.c
+++ b/arch/arm/mach-ks8695/time.c
@@ -27,6 +27,7 @@
 #include <linux/io.h>
 
 #include <asm/mach/time.h>
+#include <asm/system_misc.h>
 
 #include <mach/regs-timer.h>
 #include <mach/regs-irq.h>
diff --git a/arch/arm/mach-lpc32xx/Kconfig b/arch/arm/mach-lpc32xx/Kconfig
index fde663508696..75946ac89ee9 100644
--- a/arch/arm/mach-lpc32xx/Kconfig
+++ b/arch/arm/mach-lpc32xx/Kconfig
@@ -29,5 +29,30 @@ config ARCH_LPC32XX_UART6_SELECT
 
 endmenu
 
+menu "LPC32XX chip components"
+
+config ARCH_LPC32XX_IRAM_FOR_NET
+	bool "Use IRAM for network buffers"
+	default y
+	help
+	  Say Y here to use the LPC internal fast IRAM (i.e. 256KB SRAM) as
+	  network buffer.  If the total combined required buffer sizes is
+	  larger than the size of IRAM, then SDRAM will be used instead.
+
+	  This can be enabled safely if the IRAM is not intended for other
+	  uses.
+
+config ARCH_LPC32XX_MII_SUPPORT
+	bool "Check to enable MII support or leave disabled for RMII support"
+	help
+	  Say Y here to enable MII support, or N for RMII support. Regardless of
+	  which support is selected, the ethernet interface driver needs to be
+	  selected in the device driver networking section.
+
+	  The PHY3250 reference board uses RMII, so users of this board should
+	  say N.
+
+endmenu
+
 endif
 
diff --git a/arch/arm/mach-lpc32xx/clock.c b/arch/arm/mach-lpc32xx/clock.c
index f55c772d1816..2fc24ca12054 100644
--- a/arch/arm/mach-lpc32xx/clock.c
+++ b/arch/arm/mach-lpc32xx/clock.c
@@ -87,6 +87,7 @@
 #include <linux/list.h>
 #include <linux/errno.h>
 #include <linux/device.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/amba/bus.h>
@@ -100,6 +101,8 @@
 
 static DEFINE_SPINLOCK(global_clkregs_lock);
 
+static int usb_pll_enable, usb_pll_valid;
+
 static struct clk clk_armpll;
 static struct clk clk_usbpll;
 
@@ -384,30 +387,62 @@ static u32 local_clk_usbpll_setup(struct clk_pll_setup *pHCLKPllSetup)
 static int local_usbpll_enable(struct clk *clk, int enable)
 {
 	u32 reg;
-	int ret = -ENODEV;
-	unsigned long timeout = jiffies + msecs_to_jiffies(10);
+	int ret = 0;
+	unsigned long timeout = jiffies + msecs_to_jiffies(20);
 
 	reg = __raw_readl(LPC32XX_CLKPWR_USB_CTRL);
 
-	if (enable == 0) {
-		reg &= ~(LPC32XX_CLKPWR_USBCTRL_CLK_EN1 |
-			LPC32XX_CLKPWR_USBCTRL_CLK_EN2);
-		__raw_writel(reg, LPC32XX_CLKPWR_USB_CTRL);
-	} else if (reg & LPC32XX_CLKPWR_USBCTRL_PLL_PWRUP) {
+	__raw_writel(reg & ~(LPC32XX_CLKPWR_USBCTRL_CLK_EN2 |
+		LPC32XX_CLKPWR_USBCTRL_PLL_PWRUP),
+		LPC32XX_CLKPWR_USB_CTRL);
+	__raw_writel(reg & ~LPC32XX_CLKPWR_USBCTRL_CLK_EN1,
+		LPC32XX_CLKPWR_USB_CTRL);
+
+	if (enable && usb_pll_valid && usb_pll_enable) {
+		ret = -ENODEV;
+		/*
+		 * If the PLL rate has been previously set, then the rate
+		 * in the PLL register is valid and can be enabled here.
+		 * Otherwise, it needs to be enabled as part of setrate.
+		 */
+
+		/*
+		 * Gate clock into PLL
+		 */
 		reg |= LPC32XX_CLKPWR_USBCTRL_CLK_EN1;
 		__raw_writel(reg, LPC32XX_CLKPWR_USB_CTRL);
 
-		/* Wait for PLL lock */
+		/*
+		 * Enable PLL
+		 */
+		reg |= LPC32XX_CLKPWR_USBCTRL_PLL_PWRUP;
+		__raw_writel(reg, LPC32XX_CLKPWR_USB_CTRL);
+
+		/*
+		 * Wait for PLL to lock
+		 */
 		while (time_before(jiffies, timeout) && (ret == -ENODEV)) {
 			reg = __raw_readl(LPC32XX_CLKPWR_USB_CTRL);
 			if (reg & LPC32XX_CLKPWR_USBCTRL_PLL_STS)
 				ret = 0;
+			else
+				udelay(10);
 		}
 
+		/*
+		 * Gate clock from PLL if PLL is locked
+		 */
 		if (ret == 0) {
-			reg |= LPC32XX_CLKPWR_USBCTRL_CLK_EN2;
-			__raw_writel(reg, LPC32XX_CLKPWR_USB_CTRL);
+			__raw_writel(reg | LPC32XX_CLKPWR_USBCTRL_CLK_EN2,
+				LPC32XX_CLKPWR_USB_CTRL);
+		} else {
+			__raw_writel(reg & ~(LPC32XX_CLKPWR_USBCTRL_CLK_EN1 |
+				LPC32XX_CLKPWR_USBCTRL_PLL_PWRUP),
+				LPC32XX_CLKPWR_USB_CTRL);
 		}
+	} else if ((enable == 0) && usb_pll_valid  && usb_pll_enable) {
+		usb_pll_valid = 0;
+		usb_pll_enable = 0;
 	}
 
 	return ret;
@@ -425,7 +460,7 @@ static unsigned long local_usbpll_round_rate(struct clk *clk,
 	 */
 	rate = rate * 1000;
 
-	clkin = clk->parent->rate;
+	clkin = clk->get_rate(clk);
 	usbdiv = (__raw_readl(LPC32XX_CLKPWR_USBCLK_PDIV) &
 		LPC32XX_CLKPWR_USBPDIV_PLL_MASK) + 1;
 	clkin = clkin / usbdiv;
@@ -439,7 +474,8 @@ static unsigned long local_usbpll_round_rate(struct clk *clk,
 
 static int local_usbpll_set_rate(struct clk *clk, unsigned long rate)
 {
-	u32 clkin, reg, usbdiv;
+	int ret = -ENODEV;
+	u32 clkin, usbdiv;
 	struct clk_pll_setup pllsetup;
 
 	/*
@@ -448,7 +484,7 @@ static int local_usbpll_set_rate(struct clk *clk, unsigned long rate)
 	 */
 	rate = rate * 1000;
 
-	clkin = clk->get_rate(clk);
+	clkin = clk->get_rate(clk->parent);
 	usbdiv = (__raw_readl(LPC32XX_CLKPWR_USBCLK_PDIV) &
 		LPC32XX_CLKPWR_USBPDIV_PLL_MASK) + 1;
 	clkin = clkin / usbdiv;
@@ -457,22 +493,25 @@ static int local_usbpll_set_rate(struct clk *clk, unsigned long rate)
 	if (local_clk_find_pll_cfg(clkin, rate, &pllsetup) == 0)
 		return -EINVAL;
 
+	/*
+	 * Disable PLL clocks during PLL change
+	 */
 	local_usbpll_enable(clk, 0);
-
-	reg = __raw_readl(LPC32XX_CLKPWR_USB_CTRL);
-	reg |= LPC32XX_CLKPWR_USBCTRL_CLK_EN1;
-	__raw_writel(reg, LPC32XX_CLKPWR_USB_CTRL);
-
-	pllsetup.analog_on = 1;
+	pllsetup.analog_on = 0;
 	local_clk_usbpll_setup(&pllsetup);
 
-	clk->rate = clk_check_pll_setup(clkin, &pllsetup);
+	/*
+	 * Start USB PLL and check PLL status
+	 */
+
+	usb_pll_valid = 1;
+	usb_pll_enable = 1;
 
-	reg = __raw_readl(LPC32XX_CLKPWR_USB_CTRL);
-	reg |= LPC32XX_CLKPWR_USBCTRL_CLK_EN2;
-	__raw_writel(reg, LPC32XX_CLKPWR_USB_CTRL);
+	ret = local_usbpll_enable(clk, 1);
+	if (ret >= 0)
+		clk->rate = clk_check_pll_setup(clkin, &pllsetup);
 
-	return 0;
+	return ret;
 }
 
 static struct clk clk_usbpll = {
@@ -1095,7 +1134,7 @@ static struct clk_lookup lookups[] = {
 	_REGISTER_CLOCK(NULL, "i2s1_ck", clk_i2s1)
 	_REGISTER_CLOCK("ts-lpc32xx", NULL, clk_tsc)
 	_REGISTER_CLOCK("dev:mmc0", NULL, clk_mmc)
-	_REGISTER_CLOCK("lpc-net.0", NULL, clk_net)
+	_REGISTER_CLOCK("lpc-eth.0", NULL, clk_net)
 	_REGISTER_CLOCK("dev:clcd", NULL, clk_lcd)
 	_REGISTER_CLOCK("lpc32xx_udc", "ck_usbd", clk_usbd)
 	_REGISTER_CLOCK("lpc32xx_rtc", NULL, clk_rtc)
diff --git a/arch/arm/mach-lpc32xx/common.c b/arch/arm/mach-lpc32xx/common.c
index 6c76bb36559b..bbbf063a74c2 100644
--- a/arch/arm/mach-lpc32xx/common.c
+++ b/arch/arm/mach-lpc32xx/common.c
@@ -160,6 +160,53 @@ struct platform_device lpc32xx_adc_device = {
 };
 
 /*
+ * USB support
+ */
+/* The dmamask must be set for OHCI to work */
+static u64 ohci_dmamask = ~(u32) 0;
+static struct resource ohci_resources[] = {
+	{
+		.start = IO_ADDRESS(LPC32XX_USB_BASE),
+		.end = IO_ADDRESS(LPC32XX_USB_BASE + 0x100 - 1),
+		.flags = IORESOURCE_MEM,
+	}, {
+		.start = IRQ_LPC32XX_USB_HOST,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+struct platform_device lpc32xx_ohci_device = {
+	.name = "usb-ohci",
+	.id = -1,
+	.dev = {
+		.dma_mask = &ohci_dmamask,
+		.coherent_dma_mask = 0xFFFFFFFF,
+	},
+	.num_resources = ARRAY_SIZE(ohci_resources),
+	.resource = ohci_resources,
+};
+
+/*
+ * Network Support
+ */
+static struct resource net_resources[] = {
+	[0] = DEFINE_RES_MEM(LPC32XX_ETHERNET_BASE, SZ_4K),
+	[1] = DEFINE_RES_MEM(LPC32XX_IRAM_BASE, SZ_128K),
+	[2] = DEFINE_RES_IRQ(IRQ_LPC32XX_ETHERNET),
+};
+
+static u64 lpc32xx_mac_dma_mask = 0xffffffffUL;
+struct platform_device lpc32xx_net_device = {
+	.name = "lpc-eth",
+	.id = 0,
+	.dev = {
+		.dma_mask = &lpc32xx_mac_dma_mask,
+		.coherent_dma_mask = 0xffffffffUL,
+	},
+	.num_resources = ARRAY_SIZE(net_resources),
+	.resource = net_resources,
+};
+
+/*
  * Returns the unique ID for the device
  */
 void lpc32xx_get_uid(u32 devid[4])
diff --git a/arch/arm/mach-lpc32xx/common.h b/arch/arm/mach-lpc32xx/common.h
index 68f2e46d98ad..68e45e8c9486 100644
--- a/arch/arm/mach-lpc32xx/common.h
+++ b/arch/arm/mach-lpc32xx/common.h
@@ -19,6 +19,7 @@
 #ifndef __LPC32XX_COMMON_H
 #define __LPC32XX_COMMON_H
 
+#include <mach/board.h>
 #include <linux/platform_device.h>
 
 /*
@@ -31,6 +32,8 @@ extern struct platform_device lpc32xx_i2c2_device;
 extern struct platform_device lpc32xx_tsc_device;
 extern struct platform_device lpc32xx_adc_device;
 extern struct platform_device lpc32xx_rtc_device;
+extern struct platform_device lpc32xx_ohci_device;
+extern struct platform_device lpc32xx_net_device;
 
 /*
  * Other arch specific structures and functions
@@ -67,7 +70,6 @@ extern u32 clk_get_pclk_div(void);
 extern void lpc32xx_get_uid(u32 devid[4]);
 
 extern u32 lpc32xx_return_iram_size(void);
-
 /*
  * Pointers used for sizing and copying suspend function data
  */
diff --git a/arch/arm/mach-lpc32xx/include/mach/io.h b/arch/arm/mach-lpc32xx/include/mach/board.h
index 9b59ab5cef89..52531ca7bd1d 100644
--- a/arch/arm/mach-lpc32xx/include/mach/io.h
+++ b/arch/arm/mach-lpc32xx/include/mach/board.h
@@ -1,5 +1,5 @@
 /*
- * arch/arm/mach-lpc32xx/include/mach/io.h
+ * arm/arch/mach-lpc32xx/include/mach/board.h
  *
  * Author: Kevin Wells <kevin.wells@nxp.com>
  *
@@ -16,12 +16,9 @@
  * GNU General Public License for more details.
  */
 
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
+#ifndef __ASM_ARCH_BOARD_H
+#define __ASM_ARCH_BOARD_H
 
-#define IO_SPACE_LIMIT	0xffffffff
+extern u32 lpc32xx_return_iram_size(void);
 
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
+#endif  /* __ASM_ARCH_BOARD_H */
diff --git a/arch/arm/mach-lpc32xx/irq.c b/arch/arm/mach-lpc32xx/irq.c
index c74de01ab5b6..d080cb1123dd 100644
--- a/arch/arm/mach-lpc32xx/irq.c
+++ b/arch/arm/mach-lpc32xx/irq.c
@@ -150,6 +150,10 @@ static const struct lpc32xx_event_info lpc32xx_events[NR_IRQS] = {
 		.event_group = &lpc32xx_event_int_regs,
 		.mask = LPC32XX_CLKPWR_INTSRC_KEY_BIT,
 	},
+	[IRQ_LPC32XX_ETHERNET] = {
+		.event_group = &lpc32xx_event_int_regs,
+		.mask = LPC32XX_CLKPWR_INTSRC_MAC_BIT,
+	},
 	[IRQ_LPC32XX_USB_OTG_ATX] = {
 		.event_group = &lpc32xx_event_int_regs,
 		.mask = LPC32XX_CLKPWR_INTSRC_USBATXINT_BIT,
diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c
index 0d79a3f8a5e0..7f7401ec7487 100644
--- a/arch/arm/mach-lpc32xx/phy3250.c
+++ b/arch/arm/mach-lpc32xx/phy3250.c
@@ -37,6 +37,7 @@
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
+#include <mach/board.h>
 #include <mach/gpio-lpc32xx.h>
 #include "common.h"
 
@@ -255,6 +256,8 @@ static struct platform_device *phy3250_devs[] __initdata = {
 	&lpc32xx_watchdog_device,
 	&lpc32xx_gpio_led_device,
 	&lpc32xx_adc_device,
+	&lpc32xx_ohci_device,
+	&lpc32xx_net_device,
 };
 
 static struct amba_device *amba_devs[] __initdata = {
diff --git a/arch/arm/mach-mmp/aspenite.c b/arch/arm/mach-mmp/aspenite.c
index 3588a5584153..bf5d8e195c3e 100644
--- a/arch/arm/mach-mmp/aspenite.c
+++ b/arch/arm/mach-mmp/aspenite.c
@@ -23,6 +23,7 @@
 #include <mach/addr-map.h>
 #include <mach/mfp-pxa168.h>
 #include <mach/pxa168.h>
+#include <mach/irqs.h>
 #include <video/pxa168fb.h>
 #include <linux/input.h>
 #include <plat/pxa27x_keypad.h>
@@ -239,7 +240,7 @@ static void __init common_init(void)
 
 MACHINE_START(ASPENITE, "PXA168-based Aspenite Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = common_init,
@@ -248,7 +249,7 @@ MACHINE_END
 
 MACHINE_START(ZYLONITE2, "PXA168-based Zylonite2 Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = common_init,
diff --git a/arch/arm/mach-mmp/avengers_lite.c b/arch/arm/mach-mmp/avengers_lite.c
index b148a9dc5a44..603542ae6fbd 100644
--- a/arch/arm/mach-mmp/avengers_lite.c
+++ b/arch/arm/mach-mmp/avengers_lite.c
@@ -43,6 +43,7 @@ static void __init avengers_lite_init(void)
 
 MACHINE_START(AVENGERS_LITE, "PXA168 Avengers lite Development Platform")
 	.map_io		= mmp_map_io,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = avengers_lite_init,
diff --git a/arch/arm/mach-mmp/brownstone.c b/arch/arm/mach-mmp/brownstone.c
index d839fe6421e6..5cb769cd26d9 100644
--- a/arch/arm/mach-mmp/brownstone.c
+++ b/arch/arm/mach-mmp/brownstone.c
@@ -28,7 +28,7 @@
 
 #include "common.h"
 
-#define BROWNSTONE_NR_IRQS	(IRQ_BOARD_START + 40)
+#define BROWNSTONE_NR_IRQS	(MMP_NR_IRQS + 40)
 
 #define GPIO_5V_ENABLE		(89)
 
@@ -158,7 +158,7 @@ static struct platform_device brownstone_v_5vp_device = {
 };
 
 static struct max8925_platform_data brownstone_max8925_info = {
-	.irq_base		= IRQ_BOARD_START,
+	.irq_base		= MMP_NR_IRQS,
 };
 
 static struct i2c_board_info brownstone_twsi1_info[] = {
diff --git a/arch/arm/mach-mmp/common.c b/arch/arm/mach-mmp/common.c
index 062b5b93c50e..9292b7966e3b 100644
--- a/arch/arm/mach-mmp/common.c
+++ b/arch/arm/mach-mmp/common.c
@@ -14,6 +14,7 @@
 
 #include <asm/page.h>
 #include <asm/mach/map.h>
+#include <asm/system_misc.h>
 #include <mach/addr-map.h>
 #include <mach/cputype.h>
 
diff --git a/arch/arm/mach-mmp/flint.c b/arch/arm/mach-mmp/flint.c
index 2ee8cd7829dd..8059cc0905c6 100644
--- a/arch/arm/mach-mmp/flint.c
+++ b/arch/arm/mach-mmp/flint.c
@@ -23,10 +23,11 @@
 #include <mach/addr-map.h>
 #include <mach/mfp-mmp2.h>
 #include <mach/mmp2.h>
+#include <mach/irqs.h>
 
 #include "common.h"
 
-#define FLINT_NR_IRQS	(IRQ_BOARD_START + 48)
+#define FLINT_NR_IRQS	(MMP_NR_IRQS + 48)
 
 static unsigned long flint_pin_config[] __initdata = {
 	/* UART1 */
diff --git a/arch/arm/mach-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c
index 87765467de63..f516e74ce0d5 100644
--- a/arch/arm/mach-mmp/gplugd.c
+++ b/arch/arm/mach-mmp/gplugd.c
@@ -191,7 +191,7 @@ static void __init gplugd_init(void)
 
 MACHINE_START(GPLUGD, "PXA168-based GuruPlug Display (gplugD) Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = gplugd_init,
diff --git a/arch/arm/mach-mmp/include/mach/addr-map.h b/arch/arm/mach-mmp/include/mach/addr-map.h
index 3e404acd6ff4..b1ece08174e8 100644
--- a/arch/arm/mach-mmp/include/mach/addr-map.h
+++ b/arch/arm/mach-mmp/include/mach/addr-map.h
@@ -11,12 +11,6 @@
 #ifndef __ASM_MACH_ADDR_MAP_H
 #define __ASM_MACH_ADDR_MAP_H
 
-#ifndef __ASSEMBLER__
-#define IOMEM(x)	((void __iomem *)(x))
-#else
-#define IOMEM(x)	(x)
-#endif
-
 /* APB - Application Subsystem Peripheral Bus
  *
  * NOTE: the DMA controller registers are actually on the AXI fabric #1
diff --git a/arch/arm/mach-mmp/include/mach/io.h b/arch/arm/mach-mmp/include/mach/io.h
deleted file mode 100644
index e7adf3d012c1..000000000000
--- a/arch/arm/mach-mmp/include/mach/io.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * linux/arch/arm/mach-mmp/include/mach/io.h
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_MACH_IO_H
-#define __ASM_MACH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif /* __ASM_MACH_IO_H */
diff --git a/arch/arm/mach-mmp/include/mach/irqs.h b/arch/arm/mach-mmp/include/mach/irqs.h
index 34635a0bbb59..d0e746626a3d 100644
--- a/arch/arm/mach-mmp/include/mach/irqs.h
+++ b/arch/arm/mach-mmp/include/mach/irqs.h
@@ -223,7 +223,6 @@
 #define MMP_GPIO_TO_IRQ(gpio)		(IRQ_GPIO_START + (gpio))
 
 #define IRQ_BOARD_START			(IRQ_GPIO_START + MMP_NR_BUILTIN_GPIO)
-
-#define NR_IRQS				(IRQ_BOARD_START)
+#define MMP_NR_IRQS			IRQ_BOARD_START
 
 #endif /* __ASM_MACH_IRQS_H */
diff --git a/arch/arm/mach-mmp/irq-mmp2.c b/arch/arm/mach-mmp/irq-mmp2.c
index d21c5441a3d0..7895d277421e 100644
--- a/arch/arm/mach-mmp/irq-mmp2.c
+++ b/arch/arm/mach-mmp/irq-mmp2.c
@@ -15,6 +15,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 
+#include <mach/irqs.h>
 #include <mach/regs-icu.h>
 #include <mach/mmp2.h>
 
diff --git a/arch/arm/mach-mmp/jasper.c b/arch/arm/mach-mmp/jasper.c
index 96cf5c8fe47d..ff73249884d0 100644
--- a/arch/arm/mach-mmp/jasper.c
+++ b/arch/arm/mach-mmp/jasper.c
@@ -19,6 +19,7 @@
 #include <linux/mfd/max8925.h>
 #include <linux/interrupt.h>
 
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <mach/addr-map.h>
@@ -27,7 +28,7 @@
 
 #include "common.h"
 
-#define JASPER_NR_IRQS		(IRQ_BOARD_START + 48)
+#define JASPER_NR_IRQS		(MMP_NR_IRQS + 48)
 
 static unsigned long jasper_pin_config[] __initdata = {
 	/* UART1 */
@@ -135,7 +136,7 @@ static struct max8925_power_pdata jasper_power_data = {
 static struct max8925_platform_data jasper_max8925_info = {
 	.backlight		= &jasper_backlight_data,
 	.power			= &jasper_power_data,
-	.irq_base		= IRQ_BOARD_START,
+	.irq_base		= MMP_NR_IRQS,
 };
 
 static struct i2c_board_info jasper_twsi1_info[] = {
diff --git a/arch/arm/mach-mmp/pxa168.c b/arch/arm/mach-mmp/pxa168.c
index f7d59c03fc67..b24d2c32cba9 100644
--- a/arch/arm/mach-mmp/pxa168.c
+++ b/arch/arm/mach-mmp/pxa168.c
@@ -16,6 +16,7 @@
 #include <linux/platform_device.h>
 
 #include <asm/mach/time.h>
+#include <asm/system_misc.h>
 #include <mach/addr-map.h>
 #include <mach/cputype.h>
 #include <mach/regs-apbc.h>
diff --git a/arch/arm/mach-mmp/tavorevb.c b/arch/arm/mach-mmp/tavorevb.c
index bc97170125bf..b28f9084dfff 100644
--- a/arch/arm/mach-mmp/tavorevb.c
+++ b/arch/arm/mach-mmp/tavorevb.c
@@ -101,6 +101,7 @@ static void __init tavorevb_init(void)
 
 MACHINE_START(TAVOREVB, "PXA910 Evaluation Board (aka TavorEVB)")
 	.map_io		= mmp_map_io,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa910_init_irq,
 	.timer          = &pxa910_timer,
 	.init_machine   = tavorevb_init,
diff --git a/arch/arm/mach-mmp/teton_bga.c b/arch/arm/mach-mmp/teton_bga.c
index 0523e422990e..42bef6674ecf 100644
--- a/arch/arm/mach-mmp/teton_bga.c
+++ b/arch/arm/mach-mmp/teton_bga.c
@@ -26,6 +26,7 @@
 #include <mach/mfp-pxa168.h>
 #include <mach/pxa168.h>
 #include <mach/teton_bga.h>
+#include <mach/irqs.h>
 
 #include "common.h"
 
@@ -83,7 +84,7 @@ static void __init teton_bga_init(void)
 
 MACHINE_START(TETON_BGA, "PXA168-based Teton BGA Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = teton_bga_init,
diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c
index e72c709da44f..3fc9ed21f97d 100644
--- a/arch/arm/mach-mmp/ttc_dkb.c
+++ b/arch/arm/mach-mmp/ttc_dkb.c
@@ -38,7 +38,7 @@
  * 16 board interrupts -- PCA9575 GPIO expander
  * 24 board interrupts -- 88PM860x PMIC
  */
-#define TTCDKB_NR_IRQS		(IRQ_BOARD_START + 16 + 16 + 24)
+#define TTCDKB_NR_IRQS		(MMP_NR_IRQS + 16 + 16 + 24)
 
 static unsigned long ttc_dkb_pin_config[] __initdata = {
 	/* UART2 */
@@ -131,7 +131,7 @@ static struct platform_device *ttc_dkb_devices[] = {
 static struct pca953x_platform_data max7312_data[] = {
 	{
 		.gpio_base	= TTCDKB_GPIO_EXT0(0),
-		.irq_base	= IRQ_BOARD_START,
+		.irq_base	= MMP_NR_IRQS,
 	},
 };
 
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index a60ab6d04ec5..3698a370d636 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -68,6 +68,11 @@ static struct platform_device *devices[] __initdata = {
 
 extern struct sys_timer msm_timer;
 
+static void __init halibut_init_early(void)
+{
+	arch_ioremap_caller = __msm_ioremap_caller;
+}
+
 static void __init halibut_init_irq(void)
 {
 	msm_init_irq();
@@ -96,6 +101,7 @@ MACHINE_START(HALIBUT, "Halibut Board (QCT SURF7200A)")
 	.atag_offset	= 0x100,
 	.fixup		= halibut_fixup,
 	.map_io		= halibut_map_io,
+	.init_early	= halibut_init_early,
 	.init_irq	= halibut_init_irq,
 	.init_machine	= halibut_init,
 	.timer		= &msm_timer,
diff --git a/arch/arm/mach-msm/board-sapphire.c b/arch/arm/mach-msm/board-sapphire.c
index 97b8191d9d38..4a8ea0d40b6f 100644
--- a/arch/arm/mach-msm/board-sapphire.c
+++ b/arch/arm/mach-msm/board-sapphire.c
@@ -27,7 +27,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/flash.h>
-#include <asm/system.h>
 #include <mach/system.h>
 #include <mach/vreg.h>
 #include <mach/board.h>
diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c
index 6b9b227c87c5..5414f76ec0a9 100644
--- a/arch/arm/mach-msm/board-trout.c
+++ b/arch/arm/mach-msm/board-trout.c
@@ -43,6 +43,11 @@ static struct platform_device *devices[] __initdata = {
 
 extern struct sys_timer msm_timer;
 
+static void __init trout_init_early(void)
+{
+	arch_ioremap_caller = __msm_ioremap_caller;
+}
+
 static void __init trout_init_irq(void)
 {
 	msm_init_irq();
@@ -96,6 +101,7 @@ MACHINE_START(TROUT, "HTC Dream")
 	.atag_offset	= 0x100,
 	.fixup		= trout_fixup,
 	.map_io		= trout_map_io,
+	.init_early	= trout_init_early,
 	.init_irq	= trout_init_irq,
 	.init_machine	= trout_init,
 	.timer		= &msm_timer,
diff --git a/arch/arm/mach-msm/include/mach/io.h b/arch/arm/mach-msm/include/mach/io.h
deleted file mode 100644
index dc1b928745e9..000000000000
--- a/arch/arm/mach-msm/include/mach/io.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* arch/arm/mach-msm/include/mach/io.h
- *
- * Copyright (C) 2007 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __arch_ioremap __msm_ioremap
-#define __arch_iounmap __iounmap
-
-void __iomem *__msm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype);
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)    (a)
-
-void msm_map_qsd8x50_io(void);
-void msm_map_msm7x30_io(void);
-void msm_map_msm8x60_io(void);
-void msm_map_msm8960_io(void);
-
-extern unsigned int msm_shared_ram_phys;
-
-#endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-7x00.h b/arch/arm/mach-msm/include/mach/msm_iomap-7x00.h
index 8af46123dab6..6c4046c21296 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-7x00.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-7x00.h
@@ -38,12 +38,6 @@
  *
  */
 
-#ifdef __ASSEMBLY__
-#define IOMEM(x)	x
-#else
-#define IOMEM(x)	((void __force __iomem *)(x))
-#endif
-
 #define MSM_VIC_BASE          IOMEM(0xE0000000)
 #define MSM_VIC_PHYS          0xC0000000
 #define MSM_VIC_SIZE          SZ_4K
@@ -111,5 +105,11 @@
 #define MSM_AD5_PHYS          0xAC000000
 #define MSM_AD5_SIZE          (SZ_1M*13)
 
+#ifndef __ASSEMBLY__
+
+extern void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+					  unsigned int mtype, void *caller);
+
+#endif
 
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-7x30.h b/arch/arm/mach-msm/include/mach/msm_iomap-7x30.h
index 198202c267c8..f944fe65a657 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-7x30.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-7x30.h
@@ -100,4 +100,8 @@
 #define MSM_HSUSB_PHYS        0xA3600000
 #define MSM_HSUSB_SIZE        SZ_1K
 
+#ifndef __ASSEMBLY__
+extern void msm_map_msm7x30_io(void);
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8960.h b/arch/arm/mach-msm/include/mach/msm_iomap-8960.h
index 800b55767e6b..a1752c0284fc 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-8960.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-8960.h
@@ -50,4 +50,8 @@
 #define MSM_DEBUG_UART_PHYS	0x16440000
 #endif
 
+#ifndef __ASSEMBLY__
+extern void msm_map_msm8960_io(void);
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8x50.h b/arch/arm/mach-msm/include/mach/msm_iomap-8x50.h
index 0faa894729b7..da77cc1d545d 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-8x50.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-8x50.h
@@ -122,4 +122,8 @@
 #define MSM_SDC4_PHYS          0xA0600000
 #define MSM_SDC4_SIZE          SZ_4K
 
+#ifndef __ASSEMBLY__
+extern void msm_map_qsd8x50_io(void);
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h b/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
index 54e12caa8d86..5aed57dc808c 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
@@ -67,4 +67,8 @@
 #define MSM_DEBUG_UART_PHYS	0x19C40000
 #endif
 
+#ifndef __ASSEMBLY__
+extern void msm_map_msm8x60_io(void);
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap.h b/arch/arm/mach-msm/include/mach/msm_iomap.h
index 90682f4599d3..00afdfb8c38f 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap.h
@@ -37,12 +37,6 @@
  *
  */
 
-#ifdef __ASSEMBLY__
-#define IOMEM(x)	x
-#else
-#define IOMEM(x)	((void __force __iomem *)(x))
-#endif
-
 #if defined(CONFIG_ARCH_MSM7X30)
 #include "msm_iomap-7x30.h"
 #elif defined(CONFIG_ARCH_QSD8X50)
diff --git a/arch/arm/mach-msm/include/mach/uncompress.h b/arch/arm/mach-msm/include/mach/uncompress.h
index 169a84007456..c14011fe832d 100644
--- a/arch/arm/mach-msm/include/mach/uncompress.h
+++ b/arch/arm/mach-msm/include/mach/uncompress.h
@@ -16,6 +16,7 @@
 #ifndef __ASM_ARCH_MSM_UNCOMPRESS_H
 #define __ASM_ARCH_MSM_UNCOMPRESS_H
 
+#include <asm/barrier.h>
 #include <asm/processor.h>
 #include <mach/msm_iomap.h>
 
diff --git a/arch/arm/mach-msm/io.c b/arch/arm/mach-msm/io.c
index 578b04e42deb..a1e7b1168850 100644
--- a/arch/arm/mach-msm/io.c
+++ b/arch/arm/mach-msm/io.c
@@ -172,8 +172,8 @@ void __init msm_map_msm7x30_io(void)
 }
 #endif /* CONFIG_ARCH_MSM7X30 */
 
-void __iomem *
-__msm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+				   unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
 		/* The peripherals in the 88000000 - D0000000 range
@@ -184,7 +184,5 @@ __msm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
 			mtype = MT_DEVICE_NONSHARED;
 	}
 
-	return __arm_ioremap_caller(phys_addr, size, mtype,
-		__builtin_return_address(0));
+	return __arm_ioremap_caller(phys_addr, size, mtype, caller);
 }
-EXPORT_SYMBOL(__msm_ioremap);
diff --git a/arch/arm/mach-msm/smd_debug.c b/arch/arm/mach-msm/smd_debug.c
index 0c56a5aaf588..c56df9e932ae 100644
--- a/arch/arm/mach-msm/smd_debug.c
+++ b/arch/arm/mach-msm/smd_debug.c
@@ -203,15 +203,9 @@ static ssize_t debug_read(struct file *file, char __user *buf,
 	return simple_read_from_buffer(buf, count, ppos, debug_buffer, bsize);
 }
 
-static int debug_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static const struct file_operations debug_ops = {
 	.read = debug_read,
-	.open = debug_open,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 75f4be40b3e5..812808254936 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -24,6 +24,7 @@
 #include <asm/mach/time.h>
 #include <asm/hardware/gic.h>
 #include <asm/localtimer.h>
+#include <asm/sched_clock.h>
 
 #include <mach/msm_iomap.h>
 #include <mach/cpu.h>
@@ -105,12 +106,12 @@ static union {
 
 static void __iomem *source_base;
 
-static cycle_t msm_read_timer_count(struct clocksource *cs)
+static notrace cycle_t msm_read_timer_count(struct clocksource *cs)
 {
 	return readl_relaxed(source_base + TIMER_COUNT_VAL);
 }
 
-static cycle_t msm_read_timer_count_shift(struct clocksource *cs)
+static notrace cycle_t msm_read_timer_count_shift(struct clocksource *cs)
 {
 	/*
 	 * Shift timer count down by a constant due to unreliable lower bits
@@ -166,6 +167,11 @@ static struct local_timer_ops msm_local_timer_ops __cpuinitdata = {
 };
 #endif /* CONFIG_LOCAL_TIMERS */
 
+static notrace u32 msm_sched_clock_read(void)
+{
+	return msm_clocksource.read(&msm_clocksource);
+}
+
 static void __init msm_timer_init(void)
 {
 	struct clock_event_device *ce = &msm_clockevent;
@@ -232,6 +238,8 @@ err:
 	res = clocksource_register_hz(cs, dgt_hz);
 	if (res)
 		pr_err("clocksource_register failed\n");
+	setup_sched_clock(msm_sched_clock_read,
+			cpu_is_msm7x01() ? 32 - MSM_DGT_SHIFT : 32, dgt_hz);
 }
 
 struct sys_timer msm_timer = {
diff --git a/arch/arm/mach-mv78xx0/include/mach/io.h b/arch/arm/mach-mv78xx0/include/mach/io.h
index 450e0e1ad092..c7d9d00d8fc1 100644
--- a/arch/arm/mach-mv78xx0/include/mach/io.h
+++ b/arch/arm/mach-mv78xx0/include/mach/io.h
@@ -20,7 +20,5 @@ static inline void __iomem *__io(unsigned long addr)
 }
 
 #define __io(a)			__io(a)
-#define __mem_pci(a)		(a)
-
 
 #endif
diff --git a/arch/arm/mach-mxs/include/mach/hardware.h b/arch/arm/mach-mxs/include/mach/hardware.h
index 53e89a09bf0d..4c0e8a64d8c7 100644
--- a/arch/arm/mach-mxs/include/mach/hardware.h
+++ b/arch/arm/mach-mxs/include/mach/hardware.h
@@ -20,10 +20,4 @@
 #ifndef __MACH_MXS_HARDWARE_H__
 #define __MACH_MXS_HARDWARE_H__
 
-#ifdef __ASSEMBLER__
-#define IOMEM(addr)	(addr)
-#else
-#define IOMEM(addr)	((void __force __iomem *)(addr))
-#endif
-
 #endif /* __MACH_MXS_HARDWARE_H__ */
diff --git a/arch/arm/mach-mxs/include/mach/io.h b/arch/arm/mach-mxs/include/mach/io.h
deleted file mode 100644
index 289b7227e072..000000000000
--- a/arch/arm/mach-mxs/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- *  Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- */
-
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __MACH_MXS_IO_H__
-#define __MACH_MXS_IO_H__
-
-/* Allow IO space to be anywhere in the memory */
-#define IO_SPACE_LIMIT 0xffffffff
-
-/* io address mapping macro */
-#define __io(a)		__typesafe_io(a)
-
-#define __mem_pci(a)	(a)
-
-#endif /* __MACH_MXS_IO_H__ */
diff --git a/arch/arm/mach-mxs/system.c b/arch/arm/mach-mxs/system.c
index 7aa5ac5d78bf..80ac1fca8a00 100644
--- a/arch/arm/mach-mxs/system.c
+++ b/arch/arm/mach-mxs/system.c
@@ -25,7 +25,7 @@
 #include <linux/module.h>
 
 #include <asm/proc-fns.h>
-#include <asm/system.h>
+#include <asm/system_misc.h>
 
 #include <mach/mxs.h>
 #include <mach/common.h>
diff --git a/arch/arm/mach-netx/generic.c b/arch/arm/mach-netx/generic.c
index 59e67979f197..aa627465d914 100644
--- a/arch/arm/mach-netx/generic.c
+++ b/arch/arm/mach-netx/generic.c
@@ -168,7 +168,7 @@ void __init netx_init_irq(void)
 {
 	int irq;
 
-	vic_init(__io(io_p2v(NETX_PA_VIC)), 0, ~0, 0);
+	vic_init(io_p2v(NETX_PA_VIC), 0, ~0, 0);
 
 	for (irq = NETX_IRQ_HIF_CHAINED(0); irq <= NETX_IRQ_HIF_LAST; irq++) {
 		irq_set_chip_and_handler(irq, &netx_hif_chip,
diff --git a/arch/arm/mach-netx/include/mach/hardware.h b/arch/arm/mach-netx/include/mach/hardware.h
index 517a2bd37842..b661af2f2145 100644
--- a/arch/arm/mach-netx/include/mach/hardware.h
+++ b/arch/arm/mach-netx/include/mach/hardware.h
@@ -33,7 +33,7 @@
 #define XMAC_MEM_SIZE 0x1000
 #define SRAM_MEM_SIZE 0x8000
 
-#define io_p2v(x) ((x) - NETX_IO_PHYS + NETX_IO_VIRT)
+#define io_p2v(x) IOMEM((x) - NETX_IO_PHYS + NETX_IO_VIRT)
 #define io_v2p(x) ((x) - NETX_IO_VIRT + NETX_IO_PHYS)
 
 #endif
diff --git a/arch/arm/mach-netx/include/mach/netx-regs.h b/arch/arm/mach-netx/include/mach/netx-regs.h
index 5a03e7ccb01a..fdde22b58ac3 100644
--- a/arch/arm/mach-netx/include/mach/netx-regs.h
+++ b/arch/arm/mach-netx/include/mach/netx-regs.h
@@ -115,7 +115,7 @@
  *********************************/
 
 /* Registers */
-#define NETX_SYSTEM_REG(ofs)            __io(NETX_VA_SYSTEM + (ofs))
+#define NETX_SYSTEM_REG(ofs)            IOMEM(NETX_VA_SYSTEM + (ofs))
 #define NETX_SYSTEM_BOO_SR          NETX_SYSTEM_REG(0x00)
 #define NETX_SYSTEM_IOC_CR          NETX_SYSTEM_REG(0x04)
 #define NETX_SYSTEM_IOC_MR          NETX_SYSTEM_REG(0x08)
@@ -185,7 +185,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_GPIO_REG(ofs)                     __io(NETX_VA_GPIO + (ofs))
+#define NETX_GPIO_REG(ofs)                     IOMEM(NETX_VA_GPIO + (ofs))
 #define NETX_GPIO_CFG(gpio)                NETX_GPIO_REG(0x0  + ((gpio)<<2))
 #define NETX_GPIO_THRESHOLD_CAPTURE(gpio)  NETX_GPIO_REG(0x40 + ((gpio)<<2))
 #define NETX_GPIO_COUNTER_CTRL(counter)    NETX_GPIO_REG(0x80 + ((counter)<<2))
@@ -230,7 +230,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_PIO_REG(ofs)        __io(NETX_VA_PIO + (ofs))
+#define NETX_PIO_REG(ofs)        IOMEM(NETX_VA_PIO + (ofs))
 #define NETX_PIO_INPIO       NETX_PIO_REG(0x0)
 #define NETX_PIO_OUTPIO      NETX_PIO_REG(0x4)
 #define NETX_PIO_OEPIO       NETX_PIO_REG(0x8)
@@ -240,7 +240,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_MIIMU           __io(NETX_VA_MIIMU)
+#define NETX_MIIMU           IOMEM(NETX_VA_MIIMU)
 
 /* Bits */
 #define MIIMU_SNRDY        (1<<0)
@@ -317,7 +317,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_PFIFO_REG(ofs)               __io(NETX_VA_PFIFO + (ofs))
+#define NETX_PFIFO_REG(ofs)               IOMEM(NETX_VA_PFIFO + (ofs))
 #define NETX_PFIFO_BASE(pfifo)        NETX_PFIFO_REG(0x00 + ((pfifo)<<2))
 #define NETX_PFIFO_BORDER_BASE(pfifo) NETX_PFIFO_REG(0x80 + ((pfifo)<<2))
 #define NETX_PFIFO_RESET              NETX_PFIFO_REG(0x100)
@@ -334,7 +334,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_MEMCR_REG(ofs)               __io(NETX_VA_MEMCR + (ofs))
+#define NETX_MEMCR_REG(ofs)               IOMEM(NETX_VA_MEMCR + (ofs))
 #define NETX_MEMCR_SRAM_CTRL(cs)      NETX_MEMCR_REG(0x0 + 4 * (cs)) /* SRAM for CS 0..2 */
 #define NETX_MEMCR_SDRAM_CFG_CTRL     NETX_MEMCR_REG(0x40)
 #define NETX_MEMCR_SDRAM_TIMING_CTRL  NETX_MEMCR_REG(0x44)
@@ -355,7 +355,7 @@
  *******************************/
 
 /* Registers */
-#define NETX_DPMAS_REG(ofs)               __io(NETX_VA_DPMAS + (ofs))
+#define NETX_DPMAS_REG(ofs)               IOMEM(NETX_VA_DPMAS + (ofs))
 #define NETX_DPMAS_SYS_STAT           NETX_DPMAS_REG(0x4d8)
 #define NETX_DPMAS_INT_STAT           NETX_DPMAS_REG(0x4e0)
 #define NETX_DPMAS_INT_EN             NETX_DPMAS_REG(0x4f0)
@@ -425,7 +425,7 @@
 /*******************************
  * I2C                         *
  *******************************/
-#define NETX_I2C_REG(ofs)	__io(NETX_VA_I2C, (ofs))
+#define NETX_I2C_REG(ofs)	IOMEM(NETX_VA_I2C, (ofs))
 #define NETX_I2C_CTRL	NETX_I2C_REG(0x0)
 #define NETX_I2C_DATA	NETX_I2C_REG(0x4)
 
diff --git a/arch/arm/mach-nomadik/include/mach/io.h b/arch/arm/mach-nomadik/include/mach/io.h
deleted file mode 100644
index 2e1eca1b8243..000000000000
--- a/arch/arm/mach-nomadik/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-nomadik/include/mach/io.h   (copied from mach-sa1100)
- *
- * Copyright (C) 1997-1999 Russell King
- *
- * Modifications:
- *  06-12-1997  RMK     Created.
- *  07-04-1999  RMK     Major cleanup
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)         __typesafe_io(a)
-#define __mem_pci(a)    (a)
-
-#endif
diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
index 399c4c49722f..a051cb8ae57f 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S
+++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
@@ -14,6 +14,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #include <plat/board-ams-delta.h>
 
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index c3068622fdcb..553a2e535764 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -245,8 +245,6 @@ static struct resource h2_smc91x_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(0),
-		.end	= OMAP_GPIO_IRQ(0),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
 	},
 };
@@ -359,11 +357,9 @@ static struct tps65010_board tps_board = {
 static struct i2c_board_info __initdata h2_i2c_board_info[] = {
 	{
 		I2C_BOARD_INFO("tps65010", 0x48),
-		.irq            = OMAP_GPIO_IRQ(58),
 		.platform_data	= &tps_board,
 	}, {
 		I2C_BOARD_INFO("isp1301_omap", 0x2d),
-		.irq		= OMAP_GPIO_IRQ(2),
 	},
 };
 
@@ -428,8 +424,12 @@ static void __init h2_init(void)
 	omap_cfg_reg(E19_1610_KBR4);
 	omap_cfg_reg(N19_1610_KBR5);
 
+	h2_smc91x_resources[1].start = gpio_to_irq(0);
+	h2_smc91x_resources[1].end = gpio_to_irq(0);
 	platform_add_devices(h2_devices, ARRAY_SIZE(h2_devices));
 	omap_serial_init();
+	h2_i2c_board_info[0].irq = gpio_to_irq(58);
+	h2_i2c_board_info[1].irq = gpio_to_irq(2);
 	omap_register_i2c_bus(1, 100, h2_i2c_board_info,
 			      ARRAY_SIZE(h2_i2c_board_info));
 	omap1_usb_init(&h2_usb_config);
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index 64b8584f64ce..4c19f4c06851 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -247,8 +247,6 @@ static struct resource smc91x_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(40),
-		.end	= OMAP_GPIO_IRQ(40),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
 	},
 };
@@ -338,7 +336,6 @@ static struct spi_board_info h3_spi_board_info[] __initdata = {
 		.modalias	= "tsc2101",
 		.bus_num	= 2,
 		.chip_select	= 0,
-		.irq		= OMAP_GPIO_IRQ(H3_TS_GPIO),
 		.max_speed_hz	= 16000000,
 		/* .platform_data	= &tsc_platform_data, */
 	},
@@ -374,11 +371,9 @@ static struct omap_lcd_config h3_lcd_config __initdata = {
 static struct i2c_board_info __initdata h3_i2c_board_info[] = {
        {
 		I2C_BOARD_INFO("tps65013", 0x48),
-               /* .irq         = OMAP_GPIO_IRQ(??), */
        },
 	{
 		I2C_BOARD_INFO("isp1301_omap", 0x2d),
-		.irq		= OMAP_GPIO_IRQ(14),
 	},
 };
 
@@ -420,10 +415,14 @@ static void __init h3_init(void)
 	omap_cfg_reg(E19_1610_KBR4);
 	omap_cfg_reg(N19_1610_KBR5);
 
+	smc91x_resources[1].start = gpio_to_irq(40);
+	smc91x_resources[1].end = gpio_to_irq(40);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
+	h3_spi_board_info[0].irq = gpio_to_irq(H3_TS_GPIO);
 	spi_register_board_info(h3_spi_board_info,
 				ARRAY_SIZE(h3_spi_board_info));
 	omap_serial_init();
+	h3_i2c_board_info[1].irq = gpio_to_irq(14);
 	omap_register_i2c_bus(1, 100, h3_i2c_board_info,
 			      ARRAY_SIZE(h3_i2c_board_info));
 	omap1_usb_init(&h3_usb_config);
diff --git a/arch/arm/mach-omap1/board-htcherald.c b/arch/arm/mach-omap1/board-htcherald.c
index 827d83a96af8..60c06ee23855 100644
--- a/arch/arm/mach-omap1/board-htcherald.c
+++ b/arch/arm/mach-omap1/board-htcherald.c
@@ -324,8 +324,6 @@ static struct platform_device gpio_leds_device = {
 
 static struct resource htcpld_resources[] = {
 	[0] = {
-		.start  = OMAP_GPIO_IRQ(HTCHERALD_GIRQ_BTNS),
-		.end    = OMAP_GPIO_IRQ(HTCHERALD_GIRQ_BTNS),
 		.flags  = IORESOURCE_IRQ,
 	},
 };
@@ -450,7 +448,6 @@ static struct spi_board_info __initdata htcherald_spi_board_info[] = {
 	{
 		.modalias		= "ads7846",
 		.platform_data		= &htcherald_ts_platform_data,
-		.irq			= OMAP_GPIO_IRQ(HTCHERALD_GPIO_TS),
 		.max_speed_hz		= 2500000,
 		.bus_num		= 2,
 		.chip_select		= 1,
@@ -576,6 +573,8 @@ static void __init htcherald_init(void)
 	printk(KERN_INFO "HTC Herald init.\n");
 
 	/* Do board initialization before we register all the devices */
+	htcpld_resources[0].start = gpio_to_irq(HTCHERALD_GIRQ_BTNS);
+	htcpld_resources[0].end = gpio_to_irq(HTCHERALD_GIRQ_BTNS);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	htcherald_disable_watchdog();
@@ -583,6 +582,7 @@ static void __init htcherald_init(void)
 	htcherald_usb_enable();
 	omap1_usb_init(&htcherald_usb_config);
 
+	htcherald_spi_board_info[0].irq = gpio_to_irq(HTCHERALD_GPIO_TS);
 	spi_register_board_info(htcherald_spi_board_info,
 		ARRAY_SIZE(htcherald_spi_board_info));
 
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index 61219182d16a..67d7fd57a692 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -248,8 +248,6 @@ static struct resource innovator1610_smc91x_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(0),
-		.end	= OMAP_GPIO_IRQ(0),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
 	},
 };
@@ -409,6 +407,8 @@ static void __init innovator_init(void)
 #endif
 #ifdef CONFIG_ARCH_OMAP16XX
 	if (!cpu_is_omap1510()) {
+		innovator1610_smc91x_resources[1].start = gpio_to_irq(0);
+		innovator1610_smc91x_resources[1].end = gpio_to_irq(0);
 		platform_add_devices(innovator1610_devices, ARRAY_SIZE(innovator1610_devices));
 	}
 #endif
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index fe95ec5f6f03..d21dcc2fbc5a 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -147,7 +147,6 @@ static struct spi_board_info nokia770_spi_board_info[] __initdata = {
 		.bus_num        = 2,
 		.chip_select    = 0,
 		.max_speed_hz   = 2500000,
-		.irq		= OMAP_GPIO_IRQ(15),
 		.platform_data	= &nokia770_ads7846_platform_data,
 	},
 };
@@ -237,6 +236,7 @@ static void __init omap_nokia770_init(void)
 	omap_writew((omap_readw(0xfffb5004) & ~2), 0xfffb5004);
 
 	platform_add_devices(nokia770_devices, ARRAY_SIZE(nokia770_devices));
+	nokia770_spi_board_info[1].irq = gpio_to_irq(15);
 	spi_register_board_info(nokia770_spi_board_info,
 				ARRAY_SIZE(nokia770_spi_board_info));
 	omap_serial_init();
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index 1fe347396f4d..a5f85dda3f69 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -129,8 +129,6 @@ static struct resource osk5912_smc91x_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(0),
-		.end	= OMAP_GPIO_IRQ(0),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE,
 	},
 };
@@ -147,8 +145,6 @@ static struct platform_device osk5912_smc91x_device = {
 
 static struct resource osk5912_cf_resources[] = {
 	[0] = {
-		.start	= OMAP_GPIO_IRQ(62),
-		.end	= OMAP_GPIO_IRQ(62),
 		.flags	= IORESOURCE_IRQ,
 	},
 };
@@ -240,7 +236,6 @@ static struct tps65010_board tps_board = {
 static struct i2c_board_info __initdata osk_i2c_board_info[] = {
 	{
 		I2C_BOARD_INFO("tps65010", 0x48),
-		.irq		= OMAP_GPIO_IRQ(OMAP_MPUIO(1)),
 		.platform_data	= &tps_board,
 
 	},
@@ -408,7 +403,6 @@ static struct spi_board_info __initdata mistral_boardinfo[] = { {
 	/* MicroWire (bus 2) CS0 has an ads7846e */
 	.modalias		= "ads7846",
 	.platform_data		= &mistral_ts_info,
-	.irq			= OMAP_GPIO_IRQ(4),
 	.max_speed_hz		= 120000 /* max sample rate at 3V */
 					* 26 /* command + data + overhead */,
 	.bus_num		= 2,
@@ -471,6 +465,7 @@ static void __init osk_mistral_init(void)
 	gpio_direction_input(4);
 	irq_set_irq_type(gpio_to_irq(4), IRQ_TYPE_EDGE_FALLING);
 
+	mistral_boardinfo[0].irq = gpio_to_irq(4);
 	spi_register_board_info(mistral_boardinfo,
 			ARRAY_SIZE(mistral_boardinfo));
 
@@ -542,6 +537,10 @@ static void __init osk_init(void)
 
 	osk_flash_resource.end = osk_flash_resource.start = omap_cs3_phys();
 	osk_flash_resource.end += SZ_32M - 1;
+	osk5912_smc91x_resources[1].start = gpio_to_irq(0);
+	osk5912_smc91x_resources[1].end = gpio_to_irq(0);
+	osk5912_cf_resources[0].start = gpio_to_irq(62);
+	osk5912_cf_resources[0].end = gpio_to_irq(62);
 	platform_add_devices(osk5912_devices, ARRAY_SIZE(osk5912_devices));
 
 	l = omap_readl(USB_TRANSCEIVER_CTRL);
@@ -556,6 +555,7 @@ static void __init osk_init(void)
 		gpio_direction_input(OMAP_MPUIO(1));
 
 	omap_serial_init();
+	osk_i2c_board_info[0].irq = gpio_to_irq(OMAP_MPUIO(1));
 	omap_register_i2c_bus(1, 400, osk_i2c_board_info,
 			      ARRAY_SIZE(osk_i2c_board_info));
 	osk_mistral_init();
diff --git a/arch/arm/mach-omap1/board-palmte.c b/arch/arm/mach-omap1/board-palmte.c
index 0863d8e2bdf1..a60e6c22f816 100644
--- a/arch/arm/mach-omap1/board-palmte.c
+++ b/arch/arm/mach-omap1/board-palmte.c
@@ -217,7 +217,6 @@ static struct spi_board_info palmte_spi_info[] __initdata = {
 		.modalias	= "tsc2102",
 		.bus_num	= 2,	/* uWire (officially) */
 		.chip_select	= 0,	/* As opposed to 3 */
-		.irq		= OMAP_GPIO_IRQ(PALMTE_PINTDAV_GPIO),
 		.max_speed_hz	= 8000000,
 	},
 };
@@ -251,6 +250,7 @@ static void __init omap_palmte_init(void)
 
 	platform_add_devices(palmte_devices, ARRAY_SIZE(palmte_devices));
 
+	palmte_spi_info[0].irq = gpio_to_irq(PALMTE_PINTDAV_GPIO);
 	spi_register_board_info(palmte_spi_info, ARRAY_SIZE(palmte_spi_info));
 	palmte_misc_gpio_setup();
 	omap_serial_init();
diff --git a/arch/arm/mach-omap1/board-palmtt.c b/arch/arm/mach-omap1/board-palmtt.c
index 4ff699c509c0..8d854878547b 100644
--- a/arch/arm/mach-omap1/board-palmtt.c
+++ b/arch/arm/mach-omap1/board-palmtt.c
@@ -257,7 +257,6 @@ static struct spi_board_info __initdata palmtt_boardinfo[] = {
 		/* MicroWire (bus 2) CS0 has an ads7846e */
 		.modalias	= "ads7846",
 		.platform_data	= &palmtt_ts_info,
-		.irq		= OMAP_GPIO_IRQ(6),
 		.max_speed_hz	= 120000	/* max sample rate at 3V */
 					* 26	/* command + data + overhead */,
 		.bus_num	= 2,
@@ -298,6 +297,7 @@ static void __init omap_palmtt_init(void)
 
 	platform_add_devices(palmtt_devices, ARRAY_SIZE(palmtt_devices));
 
+	palmtt_boardinfo[0].irq = gpio_to_irq(6);
 	spi_register_board_info(palmtt_boardinfo,ARRAY_SIZE(palmtt_boardinfo));
 	omap_serial_init();
 	omap1_usb_init(&palmtt_usb_config);
diff --git a/arch/arm/mach-omap1/board-palmz71.c b/arch/arm/mach-omap1/board-palmz71.c
index abcbbd339aeb..a2c5abcd7c84 100644
--- a/arch/arm/mach-omap1/board-palmz71.c
+++ b/arch/arm/mach-omap1/board-palmz71.c
@@ -224,7 +224,6 @@ static struct spi_board_info __initdata palmz71_boardinfo[] = { {
 	/* MicroWire (bus 2) CS0 has an ads7846e */
 	.modalias	= "ads7846",
 	.platform_data	= &palmz71_ts_info,
-	.irq		= OMAP_GPIO_IRQ(PALMZ71_PENIRQ_GPIO),
 	.max_speed_hz	= 120000	/* max sample rate at 3V */
 				* 26	/* command + data + overhead */,
 	.bus_num	= 2,
@@ -313,6 +312,7 @@ omap_palmz71_init(void)
 
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
+	palmz71_boardinfo[0].irq = gpio_to_irq(PALMZ71_PENIRQ_GPIO);
 	spi_register_board_info(palmz71_boardinfo,
 				ARRAY_SIZE(palmz71_boardinfo));
 	omap1_usb_init(&palmz71_usb_config);
diff --git a/arch/arm/mach-omap1/board-voiceblue.c b/arch/arm/mach-omap1/board-voiceblue.c
index 659d0f75de2c..37232d04233f 100644
--- a/arch/arm/mach-omap1/board-voiceblue.c
+++ b/arch/arm/mach-omap1/board-voiceblue.c
@@ -44,7 +44,6 @@
 static struct plat_serial8250_port voiceblue_ports[] = {
 	{
 		.mapbase	= (unsigned long)(OMAP_CS1_PHYS + 0x40000),
-		.irq		= OMAP_GPIO_IRQ(12),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
 		.iotype		= UPIO_MEM,
 		.regshift	= 1,
@@ -52,7 +51,6 @@ static struct plat_serial8250_port voiceblue_ports[] = {
 	},
 	{
 		.mapbase	= (unsigned long)(OMAP_CS1_PHYS + 0x50000),
-		.irq		= OMAP_GPIO_IRQ(13),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
 		.iotype		= UPIO_MEM,
 		.regshift	= 1,
@@ -60,7 +58,6 @@ static struct plat_serial8250_port voiceblue_ports[] = {
 	},
 	{
 		.mapbase	= (unsigned long)(OMAP_CS1_PHYS + 0x60000),
-		.irq		= OMAP_GPIO_IRQ(14),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
 		.iotype		= UPIO_MEM,
 		.regshift	= 1,
@@ -68,7 +65,6 @@ static struct plat_serial8250_port voiceblue_ports[] = {
 	},
 	{
 		.mapbase	= (unsigned long)(OMAP_CS1_PHYS + 0x70000),
-		.irq		= OMAP_GPIO_IRQ(15),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
 		.iotype		= UPIO_MEM,
 		.regshift	= 1,
@@ -80,9 +76,6 @@ static struct plat_serial8250_port voiceblue_ports[] = {
 static struct platform_device serial_device = {
 	.name			= "serial8250",
 	.id			= PLAT8250_DEV_PLATFORM1,
-	.dev			= {
-		.platform_data	= voiceblue_ports,
-	},
 };
 
 static int __init ext_uart_init(void)
@@ -90,6 +83,11 @@ static int __init ext_uart_init(void)
 	if (!machine_is_voiceblue())
 		return -ENODEV;
 
+	voiceblue_ports[0].irq = gpio_to_irq(12);
+	voiceblue_ports[1].irq = gpio_to_irq(13);
+	voiceblue_ports[2].irq = gpio_to_irq(14);
+	voiceblue_ports[3].irq = gpio_to_irq(15);
+	serial_device.dev.platform_data = voiceblue_ports;
 	return platform_device_register(&serial_device);
 }
 arch_initcall(ext_uart_init);
@@ -128,8 +126,6 @@ static struct resource voiceblue_smc91x_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(8),
-		.end	= OMAP_GPIO_IRQ(8),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE,
 	},
 };
@@ -275,6 +271,8 @@ static void __init voiceblue_init(void)
 	irq_set_irq_type(gpio_to_irq(14), IRQ_TYPE_EDGE_RISING);
 	irq_set_irq_type(gpio_to_irq(15), IRQ_TYPE_EDGE_RISING);
 
+	voiceblue_smc91x_resources[1].start = gpio_to_irq(8);
+	voiceblue_smc91x_resources[1].end = gpio_to_irq(8);
 	platform_add_devices(voiceblue_devices, ARRAY_SIZE(voiceblue_devices));
 	omap_board_config = voiceblue_config;
 	omap_board_config_size = ARRAY_SIZE(voiceblue_config);
diff --git a/arch/arm/mach-omap1/flash.c b/arch/arm/mach-omap1/flash.c
index f9bf78d4fdfb..401eb3c080c2 100644
--- a/arch/arm/mach-omap1/flash.c
+++ b/arch/arm/mach-omap1/flash.c
@@ -17,20 +17,12 @@
 
 void omap1_set_vpp(struct platform_device *pdev, int enable)
 {
-	static int count;
 	u32 l;
 
-	if (enable) {
-		if (count++ == 0) {
-			l = omap_readl(EMIFS_CONFIG);
-			l |= OMAP_EMIFS_CONFIG_WP;
-			omap_writel(l, EMIFS_CONFIG);
-		}
-	} else {
-		if (count && (--count == 0)) {
-			l = omap_readl(EMIFS_CONFIG);
-			l &= ~OMAP_EMIFS_CONFIG_WP;
-			omap_writel(l, EMIFS_CONFIG);
-		}
-	}
+	l = omap_readl(EMIFS_CONFIG);
+	if (enable)
+		l |= OMAP_EMIFS_CONFIG_WP;
+	else
+		l &= ~OMAP_EMIFS_CONFIG_WP;
+	omap_writel(l, EMIFS_CONFIG);
 }
diff --git a/arch/arm/mach-omap1/id.c b/arch/arm/mach-omap1/id.c
index f24c1e2c5044..2b28e1da14b0 100644
--- a/arch/arm/mach-omap1/id.c
+++ b/arch/arm/mach-omap1/id.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <asm/system_info.h>
 
 #include <plat/cpu.h>
 
diff --git a/arch/arm/mach-omap1/include/mach/entry-macro.S b/arch/arm/mach-omap1/include/mach/entry-macro.S
index fa0f32a686aa..88f08cab1717 100644
--- a/arch/arm/mach-omap1/include/mach/entry-macro.S
+++ b/arch/arm/mach-omap1/include/mach/entry-macro.S
@@ -11,7 +11,6 @@
  */
 
 #include <mach/hardware.h>
-#include <mach/io.h>
 #include <mach/irqs.h>
 
 #include "../../iomap.h"
diff --git a/arch/arm/mach-omap1/include/mach/io.h b/arch/arm/mach-omap1/include/mach/io.h
index 37b12e1fd022..ce4f8005b26f 100644
--- a/arch/arm/mach-omap1/include/mach/io.h
+++ b/arch/arm/mach-omap1/include/mach/io.h
@@ -41,6 +41,5 @@
  * drivers out there that might just work if we fake them...
  */
 #define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-omap1/iomap.h b/arch/arm/mach-omap1/iomap.h
index d68175761c3d..330c4716b028 100644
--- a/arch/arm/mach-omap1/iomap.h
+++ b/arch/arm/mach-omap1/iomap.h
@@ -22,12 +22,6 @@
  * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#ifdef __ASSEMBLER__
-#define IOMEM(x)		(x)
-#else
-#define IOMEM(x)		((void __force __iomem *)(x))
-#endif
-
 #define OMAP1_IO_OFFSET		0x01000000	/* Virtual IO = 0xfefb0000 */
 #define OMAP1_IO_ADDRESS(pa)	IOMEM((pa) - OMAP1_IO_OFFSET)
 
diff --git a/arch/arm/mach-omap1/leds-h2p2-debug.c b/arch/arm/mach-omap1/leds-h2p2-debug.c
index 4b818eb9f911..f6b14a14a957 100644
--- a/arch/arm/mach-omap1/leds-h2p2-debug.c
+++ b/arch/arm/mach-omap1/leds-h2p2-debug.c
@@ -17,7 +17,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 #include <asm/mach-types.h>
 
 #include <plat/fpga.h>
diff --git a/arch/arm/mach-omap1/leds-innovator.c b/arch/arm/mach-omap1/leds-innovator.c
index 9b99c2894623..3a066ee8d02c 100644
--- a/arch/arm/mach-omap1/leds-innovator.c
+++ b/arch/arm/mach-omap1/leds-innovator.c
@@ -5,7 +5,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #include "leds.h"
 
diff --git a/arch/arm/mach-omap1/leds-osk.c b/arch/arm/mach-omap1/leds-osk.c
index da09f4364979..936ed426b84f 100644
--- a/arch/arm/mach-omap1/leds-osk.c
+++ b/arch/arm/mach-omap1/leds-osk.c
@@ -8,7 +8,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #include "leds.h"
 
diff --git a/arch/arm/mach-omap1/mux.c b/arch/arm/mach-omap1/mux.c
index 5fdef7a34828..087dba0df47e 100644
--- a/arch/arm/mach-omap1/mux.c
+++ b/arch/arm/mach-omap1/mux.c
@@ -27,7 +27,6 @@
 #include <linux/io.h>
 #include <linux/spinlock.h>
 
-#include <asm/system.h>
 
 #include <plat/mux.h>
 
diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c
index 306beaca14c5..f66c32912b22 100644
--- a/arch/arm/mach-omap1/pm.c
+++ b/arch/arm/mach-omap1/pm.c
@@ -44,6 +44,7 @@
 #include <linux/io.h>
 #include <linux/atomic.h>
 
+#include <asm/system_misc.h>
 #include <asm/irq.h>
 #include <asm/mach/time.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-omap1/sleep.S b/arch/arm/mach-omap1/sleep.S
index 0779db150da7..0e628743bd03 100644
--- a/arch/arm/mach-omap1/sleep.S
+++ b/arch/arm/mach-omap1/sleep.S
@@ -36,8 +36,6 @@
 
 #include <asm/assembler.h>
 
-#include <mach/io.h>
-
 #include "iomap.h"
 #include "pm.h"
 
diff --git a/arch/arm/mach-omap1/sram.S b/arch/arm/mach-omap1/sram.S
index 2ce0b9ab20e5..00e9d9e9adf1 100644
--- a/arch/arm/mach-omap1/sram.S
+++ b/arch/arm/mach-omap1/sram.S
@@ -12,7 +12,6 @@
 
 #include <asm/assembler.h>
 
-#include <mach/io.h>
 #include <mach/hardware.h>
 
 #include "iomap.h"
diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c
index 2fae6a2740f1..4d8dd9a1b04c 100644
--- a/arch/arm/mach-omap1/time.c
+++ b/arch/arm/mach-omap1/time.c
@@ -44,7 +44,6 @@
 #include <linux/clockchips.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/leds.h>
 #include <asm/irq.h>
 #include <asm/sched_clock.h>
diff --git a/arch/arm/mach-omap1/timer32k.c b/arch/arm/mach-omap1/timer32k.c
index a2e6d0709df2..325b9a0aa4a0 100644
--- a/arch/arm/mach-omap1/timer32k.c
+++ b/arch/arm/mach-omap1/timer32k.c
@@ -46,7 +46,6 @@
 #include <linux/clockchips.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/leds.h>
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-omap2/board-2430sdp.c b/arch/arm/mach-omap2/board-2430sdp.c
index c8bda62900d8..e658f835d0de 100644
--- a/arch/arm/mach-omap2/board-2430sdp.c
+++ b/arch/arm/mach-omap2/board-2430sdp.c
@@ -230,12 +230,12 @@ static struct i2c_board_info __initdata sdp2430_i2c1_boardinfo[] = {
 	{
 		I2C_BOARD_INFO("isp1301_omap", 0x2D),
 		.flags = I2C_CLIENT_WAKE,
-		.irq = OMAP_GPIO_IRQ(78),
 	},
 };
 
 static int __init omap2430_i2c_init(void)
 {
+	sdp2430_i2c1_boardinfo[0].irq = gpio_to_irq(78);
 	omap_register_i2c_bus(1, 100, sdp2430_i2c1_boardinfo,
 			ARRAY_SIZE(sdp2430_i2c1_boardinfo));
 	omap_pmic_init(2, 100, "twl4030", INT_24XX_SYS_NIRQ,
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index 30768c2f53fd..a39fc4bbd2b8 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -490,21 +490,22 @@ static struct platform_device omap_vwlan_device = {
 
 static int omap4_twl6030_hsmmc_late_init(struct device *dev)
 {
-	int ret = 0;
+	int irq = 0;
 	struct platform_device *pdev = container_of(dev,
 				struct platform_device, dev);
 	struct omap_mmc_platform_data *pdata = dev->platform_data;
 
 	/* Setting MMC1 Card detect Irq */
 	if (pdev->id == 0) {
-		ret = twl6030_mmc_card_detect_config();
-		if (ret)
+		irq = twl6030_mmc_card_detect_config();
+		if (irq < 0) {
 			pr_err("Failed configuring MMC1 card detect\n");
-		pdata->slots[0].card_detect_irq = TWL6030_IRQ_BASE +
-						MMCDETECT_INTR_OFFSET;
+			return irq;
+		}
+		pdata->slots[0].card_detect_irq = irq;
 		pdata->slots[0].card_detect = twl6030_mmc_card_detect;
 	}
-	return ret;
+	return 0;
 }
 
 static __init void omap4_twl6030_hsmmc_set_late_init(struct device *dev)
@@ -906,7 +907,6 @@ static void __init omap4_sdp4430_wifi_mux_init(void)
 }
 
 static struct wl12xx_platform_data omap4_sdp4430_wlan_data __initdata = {
-	.irq = OMAP_GPIO_IRQ(GPIO_WIFI_IRQ),
 	.board_ref_clock = WL12XX_REFCLOCK_26,
 	.board_tcxo_clock = WL12XX_TCXOCLOCK_26,
 };
@@ -916,6 +916,7 @@ static void __init omap4_sdp4430_wifi_init(void)
 	int ret;
 
 	omap4_sdp4430_wifi_mux_init();
+	omap4_sdp4430_wlan_data.irq = gpio_to_irq(GPIO_WIFI_IRQ);
 	ret = wl12xx_set_platform_data(&omap4_sdp4430_wlan_data);
 	if (ret)
 		pr_err("Error setting wl12xx data: %d\n", ret);
diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c
index ac773829941f..768ece2e9c3b 100644
--- a/arch/arm/mach-omap2/board-apollon.c
+++ b/arch/arm/mach-omap2/board-apollon.c
@@ -136,8 +136,6 @@ static struct resource apollon_smc91x_resources[] = {
 		.flags  = IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= OMAP_GPIO_IRQ(APOLLON_ETHR_GPIO_IRQ),
-		.end	= OMAP_GPIO_IRQ(APOLLON_ETHR_GPIO_IRQ),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE,
 	},
 };
@@ -341,6 +339,8 @@ static void __init omap_apollon_init(void)
 	 * You have to mux them off in device drivers later on
 	 * if not needed.
 	 */
+	apollon_smc91x_resources[1].start = gpio_to_irq(APOLLON_ETHR_GPIO_IRQ);
+	apollon_smc91x_resources[1].end = gpio_to_irq(APOLLON_ETHR_GPIO_IRQ);
 	platform_add_devices(apollon_devices, ARRAY_SIZE(apollon_devices));
 	omap_serial_init();
 	omap_sdrc_init(NULL, NULL);
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index 41b0a2fe0b04..909a8b91b564 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -26,6 +26,7 @@
 
 #include <linux/i2c/at24.h>
 #include <linux/i2c/twl.h>
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/mmc/host.h>
 
@@ -81,8 +82,23 @@ static struct omap_smsc911x_platform_data sb_t35_smsc911x_cfg = {
 	.flags		= SMSC911X_USE_32BIT | SMSC911X_SAVE_MAC_ADDRESS,
 };
 
+static struct regulator_consumer_supply cm_t35_smsc911x_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
+
+static struct regulator_consumer_supply sb_t35_smsc911x_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.1"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.1"),
+};
+
 static void __init cm_t35_init_ethernet(void)
 {
+	regulator_register_fixed(0, cm_t35_smsc911x_supplies,
+				 ARRAY_SIZE(cm_t35_smsc911x_supplies));
+	regulator_register_fixed(1, sb_t35_smsc911x_supplies,
+				 ARRAY_SIZE(sb_t35_smsc911x_supplies));
+
 	gpmc_smsc911x_init(&cm_t35_smsc911x_cfg);
 	gpmc_smsc911x_init(&sb_t35_smsc911x_cfg);
 }
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index 11cd2a806093..a2010f07de31 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -411,7 +411,6 @@ static struct resource omap_dm9000_resources[] = {
 		.flags		= IORESOURCE_MEM,
 	},
 	[2] = {
-		.start		= OMAP_GPIO_IRQ(OMAP_DM9000_GPIO_IRQ),
 		.flags		= IORESOURCE_IRQ | IRQF_TRIGGER_LOW,
 	},
 };
@@ -639,6 +638,7 @@ static void __init devkit8000_init(void)
 
 	omap_hsmmc_init(mmc);
 	devkit8000_i2c_init();
+	omap_dm9000_resources[2].start = gpio_to_irq(OMAP_DM9000_GPIO_IRQ);
 	platform_add_devices(devkit8000_devices,
 			ARRAY_SIZE(devkit8000_devices));
 
diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c
index 54af800d143c..0bbbabe28fcc 100644
--- a/arch/arm/mach-omap2/board-h4.c
+++ b/arch/arm/mach-omap2/board-h4.c
@@ -348,7 +348,6 @@ static struct at24_platform_data m24c01 = {
 static struct i2c_board_info __initdata h4_i2c_board_info[] = {
 	{
 		I2C_BOARD_INFO("isp1301_omap", 0x2d),
-		.irq		= OMAP_GPIO_IRQ(125),
 	},
 	{	/* EEPROM on mainboard */
 		I2C_BOARD_INFO("24c01", 0x52),
@@ -377,6 +376,7 @@ static void __init omap_h4_init(void)
 	 */
 
 	board_mkp_init();
+	h4_i2c_board_info[0].irq = gpio_to_irq(125);
 	i2c_register_board_info(1, h4_i2c_board_info,
 			ARRAY_SIZE(h4_i2c_board_info));
 
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index e558800adfdf..930c0d380435 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -634,8 +634,14 @@ static void __init igep_wlan_bt_init(void)
 static inline void __init igep_wlan_bt_init(void) { }
 #endif
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
+
 static void __init igep_init(void)
 {
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 
 	/* Get IGEP2 hardware revision */
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index d50a562adfa0..1b6049567ab4 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -22,6 +22,7 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/spi/spi.h>
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/i2c/twl.h>
 #include <linux/io.h>
@@ -410,8 +411,14 @@ static struct mtd_partition ldp_nand_partitions[] = {
 
 };
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
+
 static void __init omap_ldp_init(void)
 {
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 	ldp_init_smsc911x();
 	omap_i2c_init();
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index a659e198892b..49df12735b41 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -114,15 +114,6 @@ static struct omap_smsc911x_platform_data smsc911x_cfg = {
 
 static inline void __init omap3evm_init_smsc911x(void)
 {
-	struct clk *l3ck;
-	unsigned int rate;
-
-	l3ck = clk_get(NULL, "l3_ck");
-	if (IS_ERR(l3ck))
-		rate = 100000000;
-	else
-		rate = clk_get_rate(l3ck);
-
 	/* Configure ethernet controller reset gpio */
 	if (cpu_is_omap3430()) {
 		if (get_omap3_evm_rev() == OMAP3EVM_BOARD_GEN_1)
@@ -487,7 +478,6 @@ static struct platform_device omap3evm_wlan_regulator = {
 };
 
 struct wl12xx_platform_data omap3evm_wlan_data __initdata = {
-	.irq = OMAP_GPIO_IRQ(OMAP3EVM_WLAN_IRQ_GPIO),
 	.board_ref_clock = WL12XX_REFCLOCK_38, /* 38.4 MHz */
 };
 #endif
@@ -623,6 +613,7 @@ static void __init omap3_evm_wl12xx_init(void)
 	int ret;
 
 	/* WL12xx WLAN Init */
+	omap3evm_wlan_data.irq = gpio_to_irq(OMAP3EVM_WLAN_IRQ_GPIO);
 	ret = wl12xx_set_platform_data(&omap3evm_wlan_data);
 	if (ret)
 		pr_err("error setting wl12xx data: %d\n", ret);
@@ -632,9 +623,15 @@ static void __init omap3_evm_wl12xx_init(void)
 #endif
 }
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
+
 static void __init omap3_evm_init(void)
 {
 	omap3_evm_get_revision();
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 
 	if (cpu_is_omap3630())
 		omap3_mux_init(omap36x_board_mux, OMAP_PACKAGE_CBB);
diff --git a/arch/arm/mach-omap2/board-omap3logic.c b/arch/arm/mach-omap2/board-omap3logic.c
index 4a7d8c8a75da..9b3c141ff51b 100644
--- a/arch/arm/mach-omap2/board-omap3logic.c
+++ b/arch/arm/mach-omap2/board-omap3logic.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 
 #include <linux/i2c/twl.h>
@@ -188,8 +189,14 @@ static struct omap_board_mux board_mux[] __initdata = {
 };
 #endif
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
+
 static void __init omap3logic_init(void)
 {
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 	omap3torpedo_fix_pbias_voltage();
 	omap3logic_i2c_init();
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index 641004380795..4dffc95bddd2 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -24,6 +24,7 @@
 #include <linux/input.h>
 #include <linux/gpio_keys.h>
 
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/i2c/twl.h>
 #include <linux/mmc/host.h>
@@ -72,15 +73,6 @@ static struct omap_smsc911x_platform_data smsc911x_cfg = {
 
 static inline void __init omap3stalker_init_eth(void)
 {
-	struct clk *l3ck;
-	unsigned int rate;
-
-	l3ck = clk_get(NULL, "l3_ck");
-	if (IS_ERR(l3ck))
-		rate = 100000000;
-	else
-		rate = clk_get_rate(l3ck);
-
 	omap_mux_init_gpio(19, OMAP_PIN_INPUT_PULLUP);
 	gpmc_smsc911x_init(&smsc911x_cfg);
 }
@@ -419,8 +411,14 @@ static struct omap_board_mux board_mux[] __initdata = {
 };
 #endif
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
+
 static void __init omap3_stalker_init(void)
 {
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CUS);
 	omap_board_config = omap3_stalker_config;
 	omap_board_config_size = ARRAY_SIZE(omap3_stalker_config);
diff --git a/arch/arm/mach-omap2/board-omap3touchbook.c b/arch/arm/mach-omap2/board-omap3touchbook.c
index 8842e04aef01..ae2251fa4a69 100644
--- a/arch/arm/mach-omap2/board-omap3touchbook.c
+++ b/arch/arm/mach-omap2/board-omap3touchbook.c
@@ -42,6 +42,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/flash.h>
+#include <asm/system_info.h>
 
 #include <plat/board.h>
 #include "common.h"
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index e9071a57c37b..d8c0e89f0126 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -231,14 +231,13 @@ static struct platform_device omap_vwlan_device = {
 };
 
 struct wl12xx_platform_data omap_panda_wlan_data  __initdata = {
-	.irq = OMAP_GPIO_IRQ(GPIO_WIFI_IRQ),
 	/* PANDA ref clock is 38.4 MHz */
 	.board_ref_clock = 2,
 };
 
 static int omap4_twl6030_hsmmc_late_init(struct device *dev)
 {
-	int ret = 0;
+	int irq = 0;
 	struct platform_device *pdev = container_of(dev,
 				struct platform_device, dev);
 	struct omap_mmc_platform_data *pdata = dev->platform_data;
@@ -249,14 +248,15 @@ static int omap4_twl6030_hsmmc_late_init(struct device *dev)
 	}
 	/* Setting MMC1 Card detect Irq */
 	if (pdev->id == 0) {
-		ret = twl6030_mmc_card_detect_config();
-		 if (ret)
+		irq = twl6030_mmc_card_detect_config();
+		if (irq < 0) {
 			dev_err(dev, "%s: Error card detect config(%d)\n",
-				__func__, ret);
-		 else
-			pdata->slots[0].card_detect = twl6030_mmc_card_detect;
+				__func__, irq);
+			return irq;
+		}
+		pdata->slots[0].card_detect = twl6030_mmc_card_detect;
 	}
-	return ret;
+	return 0;
 }
 
 static __init void omap4_twl6030_hsmmc_set_late_init(struct device *dev)
@@ -557,6 +557,7 @@ static void __init omap4_panda_init(void)
 		package = OMAP_PACKAGE_CBL;
 	omap4_mux_init(board_mux, NULL, package);
 
+	omap_panda_wlan_data.irq = gpio_to_irq(GPIO_WIFI_IRQ);
 	ret = wl12xx_set_platform_data(&omap_panda_wlan_data);
 	if (ret)
 		pr_err("error setting wl12xx data: %d\n", ret);
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index 668533e2a379..33aa3910b09e 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -498,10 +498,18 @@ static struct gpio overo_bt_gpios[] __initdata = {
 	{ OVERO_GPIO_BT_NRESET, GPIOF_OUT_INIT_HIGH,	"lcd bl enable" },
 };
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+	REGULATOR_SUPPLY("vddvario", "smsc911x.1"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.1"),
+};
+
 static void __init overo_init(void)
 {
 	int ret;
 
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 	omap_hsmmc_init(mmc);
 	overo_i2c_init();
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 16aebfb8a7ec..d87ee0612098 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -25,6 +25,7 @@
 #include <linux/gpio_keys.h>
 #include <linux/mmc/host.h>
 #include <linux/power/isp1704_charger.h>
+#include <asm/system_info.h>
 
 #include <plat/mcspi.h>
 #include <plat/board.h>
@@ -169,7 +170,6 @@ static struct spi_board_info rx51_peripherals_spi_board_info[] __initdata = {
 		.modalias		= "tsc2005",
 		.bus_num		= 1,
 		.chip_select		= 0,
-		.irq			= OMAP_GPIO_IRQ(RX51_TSC2005_IRQ_GPIO),
 		.max_speed_hz		= 6000000,
 		.controller_data	= &tsc2005_mcspi_config,
 		.platform_data		= &tsc2005_pdata,
@@ -1128,6 +1128,8 @@ static void __init rx51_init_tsc2005(void)
 	}
 
 	tsc2005_pdata.set_reset = rx51_tsc2005_set_reset;
+	rx51_peripherals_spi_board_info[RX51_SPI_TSC2005].irq =
+				gpio_to_irq(RX51_TSC2005_IRQ_GPIO);
 }
 
 void __init rx51_peripherals_init(void)
diff --git a/arch/arm/mach-omap2/board-zoom-debugboard.c b/arch/arm/mach-omap2/board-zoom-debugboard.c
index 369c2eb7715b..f64f44173061 100644
--- a/arch/arm/mach-omap2/board-zoom-debugboard.c
+++ b/arch/arm/mach-omap2/board-zoom-debugboard.c
@@ -14,6 +14,9 @@
 #include <linux/smsc911x.h>
 #include <linux/interrupt.h>
 
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
+
 #include <plat/gpmc.h>
 #include <plat/gpmc-smsc911x.h>
 
@@ -43,7 +46,6 @@ static inline void __init zoom_init_smsc911x(void)
 static struct plat_serial8250_port serial_platform_data[] = {
 	{
 		.mapbase	= ZOOM_UART_BASE,
-		.irq		= OMAP_GPIO_IRQ(102),
 		.flags		= UPF_BOOT_AUTOCONF|UPF_IOREMAP|UPF_SHARE_IRQ,
 		.irqflags	= IRQF_SHARED | IRQF_TRIGGER_RISING,
 		.iotype		= UPIO_MEM,
@@ -89,6 +91,8 @@ static inline void __init zoom_init_quaduart(void)
 	if (gpio_request_one(quart_gpio, GPIOF_IN, "TL16CP754C GPIO") < 0)
 		printk(KERN_ERR "Failed to request GPIO%d for TL16CP754C\n",
 								quart_gpio);
+
+	serial_platform_data[0].irq = gpio_to_irq(102);
 }
 
 static inline int omap_zoom_debugboard_detect(void)
@@ -116,11 +120,17 @@ static struct platform_device *zoom_devices[] __initdata = {
 	&zoom_debugboard_serial_device,
 };
 
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
+
 int __init zoom_debugboard_init(void)
 {
 	if (!omap_zoom_debugboard_detect())
 		return 0;
 
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	zoom_init_smsc911x();
 	zoom_init_quaduart();
 	return platform_add_devices(zoom_devices, ARRAY_SIZE(zoom_devices));
diff --git a/arch/arm/mach-omap2/board-zoom-peripherals.c b/arch/arm/mach-omap2/board-zoom-peripherals.c
index 3d39cdb2e250..b797cb279618 100644
--- a/arch/arm/mach-omap2/board-zoom-peripherals.c
+++ b/arch/arm/mach-omap2/board-zoom-peripherals.c
@@ -193,7 +193,6 @@ static struct platform_device omap_vwlan_device = {
 };
 
 static struct wl12xx_platform_data omap_zoom_wlan_data __initdata = {
-	.irq = OMAP_GPIO_IRQ(OMAP_ZOOM_WLAN_IRQ_GPIO),
 	/* ZOOM ref clock is 26 MHz */
 	.board_ref_clock = 1,
 };
@@ -297,7 +296,10 @@ static void enable_board_wakeup_source(void)
 
 void __init zoom_peripherals_init(void)
 {
-	int ret = wl12xx_set_platform_data(&omap_zoom_wlan_data);
+	int ret;
+
+	omap_zoom_wlan_data.irq = gpio_to_irq(OMAP_ZOOM_WLAN_IRQ_GPIO);
+	ret = wl12xx_set_platform_data(&omap_zoom_wlan_data);
 
 	if (ret)
 		pr_err("error setting wl12xx data: %d\n", ret);
diff --git a/arch/arm/mach-omap2/clock3xxx_data.c b/arch/arm/mach-omap2/clock3xxx_data.c
index 981b9f9111a4..f4a626f7c79e 100644
--- a/arch/arm/mach-omap2/clock3xxx_data.c
+++ b/arch/arm/mach-omap2/clock3xxx_data.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/clk.h>
 #include <linux/list.h>
+#include <linux/io.h>
 
 #include <plat/hardware.h>
 #include <plat/clkdev_omap.h>
@@ -746,7 +747,7 @@ static struct clk dpll4_m3_ck = {
 	.parent		= &dpll4_ck,
 	.init		= &omap2_init_clksel_parent,
 	.clksel_reg	= OMAP_CM_REGADDR(OMAP3430_DSS_MOD, CM_CLKSEL),
-	.clksel_mask	= OMAP3430_CLKSEL_TV_MASK,
+	.clksel_mask	= OMAP3630_CLKSEL_TV_MASK,
 	.clksel		= dpll4_clksel,
 	.clkdm_name	= "dpll4_clkdm",
 	.recalc		= &omap2_clksel_recalc,
@@ -831,7 +832,7 @@ static struct clk dpll4_m4_ck = {
 	.parent		= &dpll4_ck,
 	.init		= &omap2_init_clksel_parent,
 	.clksel_reg	= OMAP_CM_REGADDR(OMAP3430_DSS_MOD, CM_CLKSEL),
-	.clksel_mask	= OMAP3430_CLKSEL_DSS1_MASK,
+	.clksel_mask	= OMAP3630_CLKSEL_DSS1_MASK,
 	.clksel		= dpll4_clksel,
 	.clkdm_name	= "dpll4_clkdm",
 	.recalc		= &omap2_clksel_recalc,
@@ -858,7 +859,7 @@ static struct clk dpll4_m5_ck = {
 	.parent		= &dpll4_ck,
 	.init		= &omap2_init_clksel_parent,
 	.clksel_reg	= OMAP_CM_REGADDR(OMAP3430_CAM_MOD, CM_CLKSEL),
-	.clksel_mask	= OMAP3430_CLKSEL_CAM_MASK,
+	.clksel_mask	= OMAP3630_CLKSEL_CAM_MASK,
 	.clksel		= dpll4_clksel,
 	.clkdm_name	= "dpll4_clkdm",
 	.set_rate	= &omap2_clksel_set_rate,
@@ -885,7 +886,7 @@ static struct clk dpll4_m6_ck = {
 	.parent		= &dpll4_ck,
 	.init		= &omap2_init_clksel_parent,
 	.clksel_reg	= OMAP_CM_REGADDR(OMAP3430_EMU_MOD, CM_CLKSEL1),
-	.clksel_mask	= OMAP3430_DIV_DPLL4_MASK,
+	.clksel_mask	= OMAP3630_DIV_DPLL4_MASK,
 	.clksel		= dpll4_clksel,
 	.clkdm_name	= "dpll4_clkdm",
 	.recalc		= &omap2_clksel_recalc,
@@ -1393,6 +1394,7 @@ static struct clk cpefuse_fck = {
 	.name		= "cpefuse_fck",
 	.ops		= &clkops_omap2_dflt,
 	.parent		= &sys_ck,
+	.clkdm_name	= "core_l4_clkdm",
 	.enable_reg	= OMAP_CM_REGADDR(CORE_MOD, OMAP3430ES2_CM_FCLKEN3),
 	.enable_bit	= OMAP3430ES2_EN_CPEFUSE_SHIFT,
 	.recalc		= &followparent_recalc,
@@ -1402,6 +1404,7 @@ static struct clk ts_fck = {
 	.name		= "ts_fck",
 	.ops		= &clkops_omap2_dflt,
 	.parent		= &omap_32k_fck,
+	.clkdm_name	= "core_l4_clkdm",
 	.enable_reg	= OMAP_CM_REGADDR(CORE_MOD, OMAP3430ES2_CM_FCLKEN3),
 	.enable_bit	= OMAP3430ES2_EN_TS_SHIFT,
 	.recalc		= &followparent_recalc,
@@ -1411,6 +1414,7 @@ static struct clk usbtll_fck = {
 	.name		= "usbtll_fck",
 	.ops		= &clkops_omap2_dflt_wait,
 	.parent		= &dpll5_m2_ck,
+	.clkdm_name	= "core_l4_clkdm",
 	.enable_reg	= OMAP_CM_REGADDR(CORE_MOD, OMAP3430ES2_CM_FCLKEN3),
 	.enable_bit	= OMAP3430ES2_EN_USBTLL_SHIFT,
 	.recalc		= &followparent_recalc,
@@ -1616,6 +1620,7 @@ static struct clk fshostusb_fck = {
 	.name		= "fshostusb_fck",
 	.ops		= &clkops_omap2_dflt_wait,
 	.parent		= &core_48m_fck,
+	.clkdm_name	= "core_l4_clkdm",
 	.enable_reg	= OMAP_CM_REGADDR(CORE_MOD, CM_FCLKEN1),
 	.enable_bit	= OMAP3430ES1_EN_FSHOSTUSB_SHIFT,
 	.recalc		= &followparent_recalc,
@@ -2042,6 +2047,7 @@ static struct clk omapctrl_ick = {
 	.enable_reg	= OMAP_CM_REGADDR(CORE_MOD, CM_ICLKEN1),
 	.enable_bit	= OMAP3430_EN_OMAPCTRL_SHIFT,
 	.flags		= ENABLE_ON_INIT,
+	.clkdm_name	= "core_l4_clkdm",
 	.recalc		= &followparent_recalc,
 };
 
@@ -2093,6 +2099,7 @@ static struct clk usb_l4_ick = {
 	.clksel_reg	= OMAP_CM_REGADDR(CORE_MOD, CM_CLKSEL),
 	.clksel_mask	= OMAP3430ES1_CLKSEL_FSHOSTUSB_MASK,
 	.clksel		= usb_l4_clksel,
+	.clkdm_name	= "core_l4_clkdm",
 	.recalc		= &omap2_clksel_recalc,
 };
 
@@ -3466,8 +3473,8 @@ static struct omap_clk omap3xxx_clks[] = {
 	CLK(NULL,	"ipss_ick",	&ipss_ick,	CK_AM35XX),
 	CLK(NULL,	"rmii_ck",	&rmii_ck,	CK_AM35XX),
 	CLK(NULL,	"pclk_ck",	&pclk_ck,	CK_AM35XX),
-	CLK("davinci_emac",	"emac_clk",	&emac_ick,	CK_AM35XX),
-	CLK("davinci_emac",	"phy_clk",	&emac_fck,	CK_AM35XX),
+	CLK("davinci_emac",	NULL,	&emac_ick,	CK_AM35XX),
+	CLK("davinci_mdio.0",	NULL,	&emac_fck,	CK_AM35XX),
 	CLK("vpfe-capture",	"master",	&vpfe_ick,	CK_AM35XX),
 	CLK("vpfe-capture",	"slave",	&vpfe_fck,	CK_AM35XX),
 	CLK("musb-am35x",	"ick",		&hsotgusb_ick_am35xx,	CK_AM35XX),
diff --git a/arch/arm/mach-omap2/clock44xx_data.c b/arch/arm/mach-omap2/clock44xx_data.c
index 79b98f22f207..fa6ea65ad44b 100644
--- a/arch/arm/mach-omap2/clock44xx_data.c
+++ b/arch/arm/mach-omap2/clock44xx_data.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/clk.h>
+#include <linux/io.h>
 
 #include <plat/hardware.h>
 #include <plat/clkdev_omap.h>
@@ -956,8 +957,8 @@ static struct dpll_data dpll_usb_dd = {
 	.modes		= (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	.autoidle_reg	= OMAP4430_CM_AUTOIDLE_DPLL_USB,
 	.idlest_reg	= OMAP4430_CM_IDLEST_DPLL_USB,
-	.mult_mask	= OMAP4430_DPLL_MULT_MASK,
-	.div1_mask	= OMAP4430_DPLL_DIV_MASK,
+	.mult_mask	= OMAP4430_DPLL_MULT_USB_MASK,
+	.div1_mask	= OMAP4430_DPLL_DIV_0_7_MASK,
 	.enable_mask	= OMAP4430_DPLL_EN_MASK,
 	.autoidle_mask	= OMAP4430_AUTO_DPLL_MODE_MASK,
 	.idlest_mask	= OMAP4430_ST_DPLL_CLK_MASK,
@@ -977,6 +978,7 @@ static struct clk dpll_usb_ck = {
 	.recalc		= &omap3_dpll_recalc,
 	.round_rate	= &omap2_dpll_round_rate,
 	.set_rate	= &omap3_noncore_dpll_set_rate,
+	.clkdm_name	= "l3_init_clkdm",
 };
 
 static struct clk dpll_usb_clkdcoldo_ck = {
diff --git a/arch/arm/mach-omap2/clockdomains44xx_data.c b/arch/arm/mach-omap2/clockdomains44xx_data.c
index 9299ac291d28..bd7ed13515cc 100644
--- a/arch/arm/mach-omap2/clockdomains44xx_data.c
+++ b/arch/arm/mach-omap2/clockdomains44xx_data.c
@@ -390,7 +390,7 @@ static struct clockdomain emu_sys_44xx_clkdm = {
 	.prcm_partition	  = OMAP4430_PRM_PARTITION,
 	.cm_inst	  = OMAP4430_PRM_EMU_CM_INST,
 	.clkdm_offs	  = OMAP4430_PRM_EMU_CM_EMU_CDOFFS,
-	.flags		  = CLKDM_CAN_HWSUP,
+	.flags		  = CLKDM_CAN_ENABLE_AUTO | CLKDM_CAN_FORCE_WAKEUP,
 };
 
 static struct clockdomain l3_dma_44xx_clkdm = {
diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c
index 9498b0f5fbd0..1706ebcec08d 100644
--- a/arch/arm/mach-omap2/common-board-devices.c
+++ b/arch/arm/mach-omap2/common-board-devices.c
@@ -76,7 +76,7 @@ void __init omap_ads7846_init(int bus_num, int gpio_pendown, int gpio_debounce,
 	}
 
 	spi_bi->bus_num	= bus_num;
-	spi_bi->irq	= OMAP_GPIO_IRQ(gpio_pendown);
+	spi_bi->irq	= gpio_to_irq(gpio_pendown);
 
 	if (board_pdata) {
 		board_pdata->gpio_pendown = gpio_pendown;
diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c
index 464cffde58fe..535866489ce3 100644
--- a/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/arch/arm/mach-omap2/cpuidle34xx.c
@@ -87,29 +87,14 @@ static int _cpuidle_deny_idle(struct powerdomain *pwrdm,
 	return 0;
 }
 
-/**
- * omap3_enter_idle - Programs OMAP3 to enter the specified state
- * @dev: cpuidle device
- * @drv: cpuidle driver
- * @index: the index of state to be entered
- *
- * Called from the CPUidle framework to program the device to the
- * specified target state selected by the governor.
- */
-static int omap3_enter_idle(struct cpuidle_device *dev,
+static int __omap3_enter_idle(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv,
 				int index)
 {
 	struct omap3_idle_statedata *cx =
 			cpuidle_get_statedata(&dev->states_usage[index]);
-	struct timespec ts_preidle, ts_postidle, ts_idle;
 	u32 mpu_state = cx->mpu_state, core_state = cx->core_state;
-	int idle_time;
-
-	/* Used to keep track of the total time in idle */
-	getnstimeofday(&ts_preidle);
 
-	local_irq_disable();
 	local_fiq_disable();
 
 	pwrdm_set_next_pwrst(mpu_pd, mpu_state);
@@ -148,22 +133,29 @@ static int omap3_enter_idle(struct cpuidle_device *dev,
 	}
 
 return_sleep_time:
-	getnstimeofday(&ts_postidle);
-	ts_idle = timespec_sub(ts_postidle, ts_preidle);
 
-	local_irq_enable();
 	local_fiq_enable();
 
-	idle_time = ts_idle.tv_nsec / NSEC_PER_USEC + ts_idle.tv_sec * \
-								USEC_PER_SEC;
-
-	/* Update cpuidle counters */
-	dev->last_residency = idle_time;
-
 	return index;
 }
 
 /**
+ * omap3_enter_idle - Programs OMAP3 to enter the specified state
+ * @dev: cpuidle device
+ * @drv: cpuidle driver
+ * @index: the index of state to be entered
+ *
+ * Called from the CPUidle framework to program the device to the
+ * specified target state selected by the governor.
+ */
+static inline int omap3_enter_idle(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv,
+				int index)
+{
+	return cpuidle_wrap_enter(dev, drv, index, __omap3_enter_idle);
+}
+
+/**
  * next_valid_state - Find next valid C-state
  * @dev: cpuidle device
  * @drv: cpuidle driver
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 72e018b9b260..f386cbe9c889 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -62,15 +62,9 @@ static int omap4_enter_idle(struct cpuidle_device *dev,
 {
 	struct omap4_idle_statedata *cx =
 			cpuidle_get_statedata(&dev->states_usage[index]);
-	struct timespec ts_preidle, ts_postidle, ts_idle;
 	u32 cpu1_state;
-	int idle_time;
 	int cpu_id = smp_processor_id();
 
-	/* Used to keep track of the total time in idle */
-	getnstimeofday(&ts_preidle);
-
-	local_irq_disable();
 	local_fiq_disable();
 
 	/*
@@ -128,26 +122,17 @@ static int omap4_enter_idle(struct cpuidle_device *dev,
 	if (index > 0)
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id);
 
-	getnstimeofday(&ts_postidle);
-	ts_idle = timespec_sub(ts_postidle, ts_preidle);
-
-	local_irq_enable();
 	local_fiq_enable();
 
-	idle_time = ts_idle.tv_nsec / NSEC_PER_USEC + ts_idle.tv_sec * \
-								USEC_PER_SEC;
-
-	/* Update cpuidle counters */
-	dev->last_residency = idle_time;
-
 	return index;
 }
 
 DEFINE_PER_CPU(struct cpuidle_device, omap4_idle_dev);
 
 struct cpuidle_driver omap4_idle_driver = {
-	.name =		"omap4_idle",
-	.owner =	THIS_MODULE,
+	.name				= "omap4_idle",
+	.owner				= THIS_MODULE,
+	.en_core_tk_irqen		= 1,
 };
 
 static inline void _fill_cstate(struct cpuidle_driver *drv,
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 9706c648bc19..db5a88a36c63 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -99,7 +99,7 @@ static const struct omap_dss_hwmod_data omap4_dss_hwmod_data[] __initdata = {
 	{ "dss_hdmi", "omapdss_hdmi", -1 },
 };
 
-static void omap4_hdmi_mux_pads(enum omap_hdmi_flags flags)
+static void __init omap4_hdmi_mux_pads(enum omap_hdmi_flags flags)
 {
 	u32 reg;
 	u16 control_i2c_1;
@@ -125,7 +125,7 @@ static void omap4_hdmi_mux_pads(enum omap_hdmi_flags flags)
 	}
 }
 
-static int __init omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
+static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
 {
 	u32 enable_mask, enable_shift;
 	u32 pipd_mask, pipd_shift;
@@ -166,7 +166,7 @@ int __init omap_hdmi_init(enum omap_hdmi_flags flags)
 	return 0;
 }
 
-static int __init omap_dsi_enable_pads(int dsi_id, unsigned lane_mask)
+static int omap_dsi_enable_pads(int dsi_id, unsigned lane_mask)
 {
 	if (cpu_is_omap44xx())
 		return omap4_dsi_mux_pads(dsi_id, lane_mask);
@@ -174,7 +174,7 @@ static int __init omap_dsi_enable_pads(int dsi_id, unsigned lane_mask)
 	return 0;
 }
 
-static void __init omap_dsi_disable_pads(int dsi_id, unsigned lane_mask)
+static void omap_dsi_disable_pads(int dsi_id, unsigned lane_mask)
 {
 	if (cpu_is_omap44xx())
 		omap4_dsi_mux_pads(dsi_id, 0);
diff --git a/arch/arm/mach-omap2/gpmc-smsc911x.c b/arch/arm/mach-omap2/gpmc-smsc911x.c
index 5e5880d6d099..b6c77be3e8f7 100644
--- a/arch/arm/mach-omap2/gpmc-smsc911x.c
+++ b/arch/arm/mach-omap2/gpmc-smsc911x.c
@@ -19,15 +19,11 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/smsc911x.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
 
 #include <plat/board.h>
 #include <plat/gpmc.h>
 #include <plat/gpmc-smsc911x.h>
 
-static struct omap_smsc911x_platform_data *gpmc_cfg;
-
 static struct resource gpmc_smsc911x_resources[] = {
 	[0] = {
 		.flags		= IORESOURCE_MEM,
@@ -41,51 +37,6 @@ static struct smsc911x_platform_config gpmc_smsc911x_config = {
 	.phy_interface	= PHY_INTERFACE_MODE_MII,
 	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
 	.irq_type	= SMSC911X_IRQ_TYPE_OPEN_DRAIN,
-	.flags		= SMSC911X_USE_16BIT,
-};
-
-static struct regulator_consumer_supply gpmc_smsc911x_supply[] = {
-	REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
-	REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
-};
-
-/* Generic regulator definition to satisfy smsc911x */
-static struct regulator_init_data gpmc_smsc911x_reg_init_data = {
-	.constraints = {
-		.min_uV			= 3300000,
-		.max_uV			= 3300000,
-		.valid_modes_mask	= REGULATOR_MODE_NORMAL
-					| REGULATOR_MODE_STANDBY,
-		.valid_ops_mask		= REGULATOR_CHANGE_MODE
-					| REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(gpmc_smsc911x_supply),
-	.consumer_supplies	= gpmc_smsc911x_supply,
-};
-
-static struct fixed_voltage_config gpmc_smsc911x_fixed_reg_data = {
-	.supply_name		= "gpmc_smsc911x",
-	.microvolts		= 3300000,
-	.gpio			= -EINVAL,
-	.startup_delay		= 0,
-	.enable_high		= 0,
-	.enabled_at_boot	= 1,
-	.init_data		= &gpmc_smsc911x_reg_init_data,
-};
-
-/*
- * Platform device id of 42 is a temporary fix to avoid conflicts
- * with other reg-fixed-voltage devices. The real fix should
- * involve the driver core providing a way of dynamically
- * assigning a unique id on registration for platform devices
- * in the same name space.
- */
-static struct platform_device gpmc_smsc911x_regulator = {
-	.name		= "reg-fixed-voltage",
-	.id		= 42,
-	.dev = {
-		.platform_data	= &gpmc_smsc911x_fixed_reg_data,
-	},
 };
 
 /*
@@ -93,23 +44,12 @@ static struct platform_device gpmc_smsc911x_regulator = {
  * assume that pin multiplexing is done in the board-*.c file,
  * or in the bootloader.
  */
-void __init gpmc_smsc911x_init(struct omap_smsc911x_platform_data *board_data)
+void __init gpmc_smsc911x_init(struct omap_smsc911x_platform_data *gpmc_cfg)
 {
 	struct platform_device *pdev;
 	unsigned long cs_mem_base;
 	int ret;
 
-	gpmc_cfg = board_data;
-
-	if (!gpmc_cfg->id) {
-		ret = platform_device_register(&gpmc_smsc911x_regulator);
-		if (ret < 0) {
-			pr_err("Unable to register smsc911x regulators: %d\n",
-			       ret);
-			return;
-		}
-	}
-
 	if (gpmc_cs_request(gpmc_cfg->cs, SZ_16M, &cs_mem_base) < 0) {
 		pr_err("Failed to request GPMC mem region\n");
 		return;
@@ -139,8 +79,7 @@ void __init gpmc_smsc911x_init(struct omap_smsc911x_platform_data *board_data)
 		gpio_set_value(gpmc_cfg->gpio_reset, 1);
 	}
 
-	if (gpmc_cfg->flags)
-		gpmc_smsc911x_config.flags = gpmc_cfg->flags;
+	gpmc_smsc911x_config.flags = gpmc_cfg->flags ? : SMSC911X_USE_16BIT;
 
 	pdev = platform_device_register_resndata(NULL, "smsc911x", gpmc_cfg->id,
 		 gpmc_smsc911x_resources, ARRAY_SIZE(gpmc_smsc911x_resources),
diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index 8121720e942f..b0268eaffe13 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -316,6 +316,7 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 	mmc->slots[0].pm_caps = c->pm_caps;
 	mmc->slots[0].internal_clock = !c->ext_clock;
 	mmc->dma_mask = 0xffffffff;
+	mmc->max_freq = c->max_freq;
 	if (cpu_is_omap44xx())
 		mmc->reg_offset = OMAP4_MMC_REG_OFFSET;
 	else
@@ -505,6 +506,13 @@ static void __init omap_hsmmc_init_one(struct omap2_hsmmc_info *hsmmcinfo,
 	if (oh->dev_attr != NULL) {
 		mmc_dev_attr = oh->dev_attr;
 		mmc_data->controller_flags = mmc_dev_attr->flags;
+		/*
+		 * erratum 2.1.1.128 doesn't apply if board has
+		 * a transceiver is attached
+		 */
+		if (hsmmcinfo->transceiver)
+			mmc_data->controller_flags &=
+				~OMAP_HSMMC_BROKEN_MULTIBLOCK_READ;
 	}
 
 	pdev = platform_device_alloc(name, ctrl_nr - 1);
diff --git a/arch/arm/mach-omap2/hsmmc.h b/arch/arm/mach-omap2/hsmmc.h
index 07831cc3c171..7f2e790e0929 100644
--- a/arch/arm/mach-omap2/hsmmc.h
+++ b/arch/arm/mach-omap2/hsmmc.h
@@ -27,6 +27,8 @@ struct omap2_hsmmc_info {
 	char	*name;		/* or NULL for default */
 	struct platform_device *pdev;	/* mmc controller instance */
 	int	ocr_mask;	/* temporary HACK */
+	int	max_freq;	/* maximum clock, if constrained by external
+				 * circuitry, or 0 for default */
 	/* Remux (pad configuration) when powering on/off */
 	void (*remux)(struct device *dev, int slot, int power_on);
 	/* init some special card */
diff --git a/arch/arm/mach-omap2/include/mach/barriers.h b/arch/arm/mach-omap2/include/mach/barriers.h
index 4fa72c7cc7cd..1c582a8592b9 100644
--- a/arch/arm/mach-omap2/include/mach/barriers.h
+++ b/arch/arm/mach-omap2/include/mach/barriers.h
@@ -22,6 +22,8 @@
 #ifndef __MACH_BARRIERS_H
 #define __MACH_BARRIERS_H
 
+#include <asm/outercache.h>
+
 extern void omap_bus_sync(void);
 
 #define rmb()		dsb()
diff --git a/arch/arm/mach-omap2/include/mach/io.h b/arch/arm/mach-omap2/include/mach/io.h
deleted file mode 100644
index b8758c8a9394..000000000000
--- a/arch/arm/mach-omap2/include/mach/io.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * arch/arm/mach-omap2/include/mach/io.h
- *
- * IO definitions for TI OMAP processors and boards
- *
- * Copied from arch/arm/mach-sa1100/include/mach/io.h
- * Copyright (C) 1997-1999 Russell King
- *
- * Copyright (C) 2009 Texas Instruments
- * Added OMAP4 support - Santosh Shilimkar <santosh.shilimkar@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
- * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
- * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Modifications:
- *  06-12-1997	RMK	Created.
- *  07-04-1999	RMK	Major cleanup
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-omap2/iomap.h b/arch/arm/mach-omap2/iomap.h
index e6f958165296..0812b154f5b5 100644
--- a/arch/arm/mach-omap2/iomap.h
+++ b/arch/arm/mach-omap2/iomap.h
@@ -22,12 +22,6 @@
  * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#ifdef __ASSEMBLER__
-#define IOMEM(x)		(x)
-#else
-#define IOMEM(x)		((void __force __iomem *)(x))
-#endif
-
 #define OMAP2_L3_IO_OFFSET	0x90000000
 #define OMAP2_L3_IO_ADDRESS(pa)	IOMEM((pa) + OMAP2_L3_IO_OFFSET) /* L3 */
 
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index f26b2faa1694..65c33911341f 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -35,7 +35,6 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 
-#include <asm/system.h>
 
 #include <plat/omap_hwmod.h>
 
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index 63ab686834c1..13670aa84e58 100644
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -46,7 +46,6 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/smp_scu.h>
-#include <asm/system.h>
 #include <asm/pgalloc.h>
 #include <asm/suspend.h>
 #include <asm/hardware/cache-l2x0.h>
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index eba6cd3816f5..2c27fdb61e66 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1395,7 +1395,7 @@ static int _read_hardreset(struct omap_hwmod *oh, const char *name)
  */
 static int _ocp_softreset(struct omap_hwmod *oh)
 {
-	u32 v;
+	u32 v, softrst_mask;
 	int c = 0;
 	int ret = 0;
 
@@ -1427,11 +1427,13 @@ static int _ocp_softreset(struct omap_hwmod *oh)
 						    oh->class->sysc->syss_offs)
 				   & SYSS_RESETDONE_MASK),
 				  MAX_MODULE_SOFTRESET_WAIT, c);
-	else if (oh->class->sysc->sysc_flags & SYSC_HAS_RESET_STATUS)
+	else if (oh->class->sysc->sysc_flags & SYSC_HAS_RESET_STATUS) {
+		softrst_mask = (0x1 << oh->class->sysc->sysc_fields->srst_shift);
 		omap_test_timeout(!(omap_hwmod_read(oh,
 						     oh->class->sysc->sysc_offs)
-				   & SYSC_TYPE2_SOFTRESET_MASK),
+				   & softrst_mask),
 				  MAX_MODULE_SOFTRESET_WAIT, c);
+	}
 
 	if (c == MAX_MODULE_SOFTRESET_WAIT)
 		pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
@@ -1477,6 +1479,11 @@ static int _reset(struct omap_hwmod *oh)
 
 	ret = (oh->class->reset) ? oh->class->reset(oh) : _ocp_softreset(oh);
 
+	if (oh->class->sysc) {
+		_update_sysc_cache(oh);
+		_enable_sysc(oh);
+	}
+
 	return ret;
 }
 
@@ -1786,20 +1793,9 @@ static int _setup(struct omap_hwmod *oh, void *data)
 		return 0;
 	}
 
-	if (!(oh->flags & HWMOD_INIT_NO_RESET)) {
+	if (!(oh->flags & HWMOD_INIT_NO_RESET))
 		_reset(oh);
 
-		/*
-		 * OCP_SYSCONFIG bits need to be reprogrammed after a softreset.
-		 * The _enable() function should be split to
-		 * avoid the rewrite of the OCP_SYSCONFIG register.
-		 */
-		if (oh->class->sysc) {
-			_update_sysc_cache(oh);
-			_enable_sysc(oh);
-		}
-	}
-
 	postsetup_state = oh->_postsetup_state;
 	if (postsetup_state == _HWMOD_STATE_UNKNOWN)
 		postsetup_state = _HWMOD_STATE_ENABLED;
@@ -1907,20 +1903,10 @@ void omap_hwmod_write(u32 v, struct omap_hwmod *oh, u16 reg_offs)
  */
 int omap_hwmod_softreset(struct omap_hwmod *oh)
 {
-	u32 v;
-	int ret;
-
-	if (!oh || !(oh->_sysc_cache))
+	if (!oh)
 		return -EINVAL;
 
-	v = oh->_sysc_cache;
-	ret = _set_softreset(oh, &v);
-	if (ret)
-		goto error;
-	_write_sysconfig(v, oh);
-
-error:
-	return ret;
+	return _ocp_softreset(oh);
 }
 
 /**
@@ -2463,26 +2449,28 @@ int omap_hwmod_del_initiator_dep(struct omap_hwmod *oh,
  * @oh: struct omap_hwmod *
  *
  * Sets the module OCP socket ENAWAKEUP bit to allow the module to
- * send wakeups to the PRCM.  Eventually this should sets PRCM wakeup
- * registers to cause the PRCM to receive wakeup events from the
- * module.  Does not set any wakeup routing registers beyond this
- * point - if the module is to wake up any other module or subsystem,
- * that must be set separately.  Called by omap_device code.  Returns
- * -EINVAL on error or 0 upon success.
+ * send wakeups to the PRCM, and enable I/O ring wakeup events for
+ * this IP block if it has dynamic mux entries.  Eventually this
+ * should set PRCM wakeup registers to cause the PRCM to receive
+ * wakeup events from the module.  Does not set any wakeup routing
+ * registers beyond this point - if the module is to wake up any other
+ * module or subsystem, that must be set separately.  Called by
+ * omap_device code.  Returns -EINVAL on error or 0 upon success.
  */
 int omap_hwmod_enable_wakeup(struct omap_hwmod *oh)
 {
 	unsigned long flags;
 	u32 v;
 
-	if (!oh->class->sysc ||
-	    !(oh->class->sysc->sysc_flags & SYSC_HAS_ENAWAKEUP))
-		return -EINVAL;
-
 	spin_lock_irqsave(&oh->_lock, flags);
-	v = oh->_sysc_cache;
-	_enable_wakeup(oh, &v);
-	_write_sysconfig(v, oh);
+
+	if (oh->class->sysc &&
+	    (oh->class->sysc->sysc_flags & SYSC_HAS_ENAWAKEUP)) {
+		v = oh->_sysc_cache;
+		_enable_wakeup(oh, &v);
+		_write_sysconfig(v, oh);
+	}
+
 	_set_idle_ioring_wakeup(oh, true);
 	spin_unlock_irqrestore(&oh->_lock, flags);
 
@@ -2494,26 +2482,28 @@ int omap_hwmod_enable_wakeup(struct omap_hwmod *oh)
  * @oh: struct omap_hwmod *
  *
  * Clears the module OCP socket ENAWAKEUP bit to prevent the module
- * from sending wakeups to the PRCM.  Eventually this should clear
- * PRCM wakeup registers to cause the PRCM to ignore wakeup events
- * from the module.  Does not set any wakeup routing registers beyond
- * this point - if the module is to wake up any other module or
- * subsystem, that must be set separately.  Called by omap_device
- * code.  Returns -EINVAL on error or 0 upon success.
+ * from sending wakeups to the PRCM, and disable I/O ring wakeup
+ * events for this IP block if it has dynamic mux entries.  Eventually
+ * this should clear PRCM wakeup registers to cause the PRCM to ignore
+ * wakeup events from the module.  Does not set any wakeup routing
+ * registers beyond this point - if the module is to wake up any other
+ * module or subsystem, that must be set separately.  Called by
+ * omap_device code.  Returns -EINVAL on error or 0 upon success.
  */
 int omap_hwmod_disable_wakeup(struct omap_hwmod *oh)
 {
 	unsigned long flags;
 	u32 v;
 
-	if (!oh->class->sysc ||
-	    !(oh->class->sysc->sysc_flags & SYSC_HAS_ENAWAKEUP))
-		return -EINVAL;
-
 	spin_lock_irqsave(&oh->_lock, flags);
-	v = oh->_sysc_cache;
-	_disable_wakeup(oh, &v);
-	_write_sysconfig(v, oh);
+
+	if (oh->class->sysc &&
+	    (oh->class->sysc->sysc_flags & SYSC_HAS_ENAWAKEUP)) {
+		v = oh->_sysc_cache;
+		_disable_wakeup(oh, &v);
+		_write_sysconfig(v, oh);
+	}
+
 	_set_idle_ioring_wakeup(oh, false);
 	spin_unlock_irqrestore(&oh->_lock, flags);
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 08daa5e0eb5f..cc9bd106a854 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -2996,6 +2996,11 @@ static struct omap_hwmod_ocp_if *omap44xx_mcbsp1_slaves[] = {
 	&omap44xx_l4_abe__mcbsp1_dma,
 };
 
+static struct omap_hwmod_opt_clk mcbsp1_opt_clks[] = {
+	{ .role = "pad_fck", .clk = "pad_clks_ck" },
+	{ .role = "prcm_clk", .clk = "mcbsp1_sync_mux_ck" },
+};
+
 static struct omap_hwmod omap44xx_mcbsp1_hwmod = {
 	.name		= "mcbsp1",
 	.class		= &omap44xx_mcbsp_hwmod_class,
@@ -3012,6 +3017,8 @@ static struct omap_hwmod omap44xx_mcbsp1_hwmod = {
 	},
 	.slaves		= omap44xx_mcbsp1_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap44xx_mcbsp1_slaves),
+	.opt_clks	= mcbsp1_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mcbsp1_opt_clks),
 };
 
 /* mcbsp2 */
@@ -3071,6 +3078,11 @@ static struct omap_hwmod_ocp_if *omap44xx_mcbsp2_slaves[] = {
 	&omap44xx_l4_abe__mcbsp2_dma,
 };
 
+static struct omap_hwmod_opt_clk mcbsp2_opt_clks[] = {
+	{ .role = "pad_fck", .clk = "pad_clks_ck" },
+	{ .role = "prcm_clk", .clk = "mcbsp2_sync_mux_ck" },
+};
+
 static struct omap_hwmod omap44xx_mcbsp2_hwmod = {
 	.name		= "mcbsp2",
 	.class		= &omap44xx_mcbsp_hwmod_class,
@@ -3087,6 +3099,8 @@ static struct omap_hwmod omap44xx_mcbsp2_hwmod = {
 	},
 	.slaves		= omap44xx_mcbsp2_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap44xx_mcbsp2_slaves),
+	.opt_clks	= mcbsp2_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mcbsp2_opt_clks),
 };
 
 /* mcbsp3 */
@@ -3146,6 +3160,11 @@ static struct omap_hwmod_ocp_if *omap44xx_mcbsp3_slaves[] = {
 	&omap44xx_l4_abe__mcbsp3_dma,
 };
 
+static struct omap_hwmod_opt_clk mcbsp3_opt_clks[] = {
+	{ .role = "pad_fck", .clk = "pad_clks_ck" },
+	{ .role = "prcm_clk", .clk = "mcbsp3_sync_mux_ck" },
+};
+
 static struct omap_hwmod omap44xx_mcbsp3_hwmod = {
 	.name		= "mcbsp3",
 	.class		= &omap44xx_mcbsp_hwmod_class,
@@ -3162,6 +3181,8 @@ static struct omap_hwmod omap44xx_mcbsp3_hwmod = {
 	},
 	.slaves		= omap44xx_mcbsp3_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap44xx_mcbsp3_slaves),
+	.opt_clks	= mcbsp3_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mcbsp3_opt_clks),
 };
 
 /* mcbsp4 */
@@ -3200,6 +3221,11 @@ static struct omap_hwmod_ocp_if *omap44xx_mcbsp4_slaves[] = {
 	&omap44xx_l4_per__mcbsp4,
 };
 
+static struct omap_hwmod_opt_clk mcbsp4_opt_clks[] = {
+	{ .role = "pad_fck", .clk = "pad_clks_ck" },
+	{ .role = "prcm_clk", .clk = "mcbsp4_sync_mux_ck" },
+};
+
 static struct omap_hwmod omap44xx_mcbsp4_hwmod = {
 	.name		= "mcbsp4",
 	.class		= &omap44xx_mcbsp_hwmod_class,
@@ -3216,6 +3242,8 @@ static struct omap_hwmod omap44xx_mcbsp4_hwmod = {
 	},
 	.slaves		= omap44xx_mcbsp4_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap44xx_mcbsp4_slaves),
+	.opt_clks	= mcbsp4_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mcbsp4_opt_clks),
 };
 
 /*
diff --git a/arch/arm/mach-omap2/opp.c b/arch/arm/mach-omap2/opp.c
index 9262a6b47702..de6d46451746 100644
--- a/arch/arm/mach-omap2/opp.c
+++ b/arch/arm/mach-omap2/opp.c
@@ -64,10 +64,10 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def,
 		}
 		oh = omap_hwmod_lookup(opp_def->hwmod_name);
 		if (!oh || !oh->od) {
-			pr_warn("%s: no hwmod or odev for %s, [%d] "
+			pr_debug("%s: no hwmod or odev for %s, [%d] "
 				"cannot add OPPs.\n", __func__,
 				opp_def->hwmod_name, i);
-			return -EINVAL;
+			continue;
 		}
 		dev = &oh->od->pdev->dev;
 
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index a7bdec69a2b3..d0c1c9695996 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -17,6 +17,8 @@
 #include <linux/export.h>
 #include <linux/suspend.h>
 
+#include <asm/system_misc.h>
+
 #include <plat/omap-pm.h>
 #include <plat/omap_device.h>
 #include "common.h"
diff --git a/arch/arm/mach-omap2/pm24xx.c b/arch/arm/mach-omap2/pm24xx.c
index 5ca45ca76946..95442b69ae27 100644
--- a/arch/arm/mach-omap2/pm24xx.c
+++ b/arch/arm/mach-omap2/pm24xx.c
@@ -33,6 +33,7 @@
 #include <asm/mach/time.h>
 #include <asm/mach/irq.h>
 #include <asm/mach-types.h>
+#include <asm/system_misc.h>
 
 #include <plat/clock.h>
 #include <plat/sram.h>
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 027a537d72b2..703bd1099259 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -31,6 +31,7 @@
 #include <trace/events/power.h>
 
 #include <asm/suspend.h>
+#include <asm/system_misc.h>
 
 #include <plat/sram.h>
 #include "clockdomain.h"
@@ -152,8 +153,7 @@ static void omap3_save_secure_ram_context(void)
 		pwrdm_set_next_pwrst(mpu_pwrdm, mpu_next_state);
 		/* Following is for error tracking, it should not happen */
 		if (ret) {
-			printk(KERN_ERR "save_secure_sram() returns %08x\n",
-				ret);
+			pr_err("save_secure_sram() returns %08x\n", ret);
 			while (1)
 				;
 		}
@@ -288,7 +288,7 @@ void omap_sram_idle(void)
 		break;
 	default:
 		/* Invalid state */
-		printk(KERN_ERR "Invalid mpu state in sram_idle\n");
+		pr_err("Invalid mpu state in sram_idle\n");
 		return;
 	}
 
@@ -438,18 +438,17 @@ restore:
 	list_for_each_entry(pwrst, &pwrst_list, node) {
 		state = pwrdm_read_prev_pwrst(pwrst->pwrdm);
 		if (state > pwrst->next_state) {
-			printk(KERN_INFO "Powerdomain (%s) didn't enter "
-			       "target state %d\n",
+			pr_info("Powerdomain (%s) didn't enter "
+				"target state %d\n",
 			       pwrst->pwrdm->name, pwrst->next_state);
 			ret = -1;
 		}
 		omap_set_pwrdm_state(pwrst->pwrdm, pwrst->saved_state);
 	}
 	if (ret)
-		printk(KERN_ERR "Could not enter target state in pm_suspend\n");
+		pr_err("Could not enter target state in pm_suspend\n");
 	else
-		printk(KERN_INFO "Successfully put all powerdomains "
-		       "to target state\n");
+		pr_info("Successfully put all powerdomains to target state\n");
 
 	return ret;
 }
@@ -733,21 +732,22 @@ static int __init omap3_pm_init(void)
 
 	if (ret) {
 		pr_err("pm: Failed to request pm_io irq\n");
-		goto err1;
+		goto err2;
 	}
 
 	ret = pwrdm_for_each(pwrdms_setup, NULL);
 	if (ret) {
-		printk(KERN_ERR "Failed to setup powerdomains\n");
-		goto err2;
+		pr_err("Failed to setup powerdomains\n");
+		goto err3;
 	}
 
 	(void) clkdm_for_each(omap_pm_clkdms_setup, NULL);
 
 	mpu_pwrdm = pwrdm_lookup("mpu_pwrdm");
 	if (mpu_pwrdm == NULL) {
-		printk(KERN_ERR "Failed to get mpu_pwrdm\n");
-		goto err2;
+		pr_err("Failed to get mpu_pwrdm\n");
+		ret = -EINVAL;
+		goto err3;
 	}
 
 	neon_pwrdm = pwrdm_lookup("neon_pwrdm");
@@ -780,8 +780,8 @@ static int __init omap3_pm_init(void)
 		omap3_secure_ram_storage =
 			kmalloc(0x803F, GFP_KERNEL);
 		if (!omap3_secure_ram_storage)
-			printk(KERN_ERR "Memory allocation failed when"
-					"allocating for secure sram context\n");
+			pr_err("Memory allocation failed when "
+			       "allocating for secure sram context\n");
 
 		local_irq_disable();
 		local_fiq_disable();
@@ -795,14 +795,17 @@ static int __init omap3_pm_init(void)
 	}
 
 	omap3_save_scratchpad_contents();
-err1:
 	return ret;
-err2:
-	free_irq(INT_34XX_PRCM_MPU_IRQ, NULL);
+
+err3:
 	list_for_each_entry_safe(pwrst, tmp, &pwrst_list, node) {
 		list_del(&pwrst->node);
 		kfree(pwrst);
 	}
+	free_irq(omap_prcm_event_to_irq("io"), omap3_pm_init);
+err2:
+	free_irq(omap_prcm_event_to_irq("wkup"), NULL);
+err1:
 	return ret;
 }
 
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index 91e0b1c9b76c..885625352429 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -16,6 +16,7 @@
 #include <linux/list.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <asm/system_misc.h>
 
 #include "common.h"
 #include "clockdomain.h"
@@ -143,7 +144,7 @@ static void omap_default_idle(void)
 static int __init omap4_pm_init(void)
 {
 	int ret;
-	struct clockdomain *emif_clkdm, *mpuss_clkdm, *l3_1_clkdm;
+	struct clockdomain *emif_clkdm, *mpuss_clkdm, *l3_1_clkdm, *l4wkup;
 	struct clockdomain *ducati_clkdm, *l3_2_clkdm, *l4_per_clkdm;
 
 	if (!cpu_is_omap44xx())
@@ -167,14 +168,19 @@ static int __init omap4_pm_init(void)
 	 * MPUSS -> L4_PER/L3_* and DUCATI -> L3_* doesn't work as
 	 * expected. The hardware recommendation is to enable static
 	 * dependencies for these to avoid system lock ups or random crashes.
+	 * The L4 wakeup depedency is added to workaround the OCP sync hardware
+	 * BUG with 32K synctimer which lead to incorrect timer value read
+	 * from the 32K counter. The BUG applies for GPTIMER1 and WDT2 which
+	 * are part of L4 wakeup clockdomain.
 	 */
 	mpuss_clkdm = clkdm_lookup("mpuss_clkdm");
 	emif_clkdm = clkdm_lookup("l3_emif_clkdm");
 	l3_1_clkdm = clkdm_lookup("l3_1_clkdm");
 	l3_2_clkdm = clkdm_lookup("l3_2_clkdm");
 	l4_per_clkdm = clkdm_lookup("l4_per_clkdm");
+	l4wkup = clkdm_lookup("l4_wkup_clkdm");
 	ducati_clkdm = clkdm_lookup("ducati_clkdm");
-	if ((!mpuss_clkdm) || (!emif_clkdm) || (!l3_1_clkdm) ||
+	if ((!mpuss_clkdm) || (!emif_clkdm) || (!l3_1_clkdm) || (!l4wkup) ||
 		(!l3_2_clkdm) || (!ducati_clkdm) || (!l4_per_clkdm))
 		goto err2;
 
@@ -182,6 +188,7 @@ static int __init omap4_pm_init(void)
 	ret |= clkdm_add_wkdep(mpuss_clkdm, l3_1_clkdm);
 	ret |= clkdm_add_wkdep(mpuss_clkdm, l3_2_clkdm);
 	ret |= clkdm_add_wkdep(mpuss_clkdm, l4_per_clkdm);
+	ret |= clkdm_add_wkdep(mpuss_clkdm, l4wkup);
 	ret |= clkdm_add_wkdep(ducati_clkdm, l3_1_clkdm);
 	ret |= clkdm_add_wkdep(ducati_clkdm, l3_2_clkdm);
 	if (ret) {
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 8a18d1bd61c8..96ad3dbeac34 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -972,7 +972,13 @@ int pwrdm_wait_transition(struct powerdomain *pwrdm)
 
 int pwrdm_state_switch(struct powerdomain *pwrdm)
 {
-	return _pwrdm_state_switch(pwrdm, PWRDM_STATE_NOW);
+	int ret;
+
+	ret = pwrdm_wait_transition(pwrdm);
+	if (!ret)
+		ret = _pwrdm_state_switch(pwrdm, PWRDM_STATE_NOW);
+
+	return ret;
 }
 
 int pwrdm_clkdm_state_switch(struct clockdomain *clkdm)
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index eac623c7c3d8..f106d21ff581 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -147,8 +147,9 @@ static inline u32 _read_pending_irq_reg(u16 irqen_offs, u16 irqst_offs)
 	u32 mask, st;
 
 	/* XXX read mask from RAM? */
-	mask = omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST, irqen_offs);
-	st = omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST, irqst_offs);
+	mask = omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
+				       irqen_offs);
+	st = omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST, irqst_offs);
 
 	return mask & st;
 }
@@ -180,7 +181,7 @@ void omap44xx_prm_read_pending_irqs(unsigned long *events)
  */
 void omap44xx_prm_ocp_barrier(void)
 {
-	omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST,
+	omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
 				OMAP4_REVISION_PRM_OFFSET);
 }
 
@@ -198,19 +199,19 @@ void omap44xx_prm_ocp_barrier(void)
 void omap44xx_prm_save_and_clear_irqen(u32 *saved_mask)
 {
 	saved_mask[0] =
-		omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST,
+		omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
 					OMAP4_PRM_IRQSTATUS_MPU_OFFSET);
 	saved_mask[1] =
-		omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST,
+		omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
 					OMAP4_PRM_IRQSTATUS_MPU_2_OFFSET);
 
-	omap4_prm_write_inst_reg(0, OMAP4430_PRM_DEVICE_INST,
+	omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST,
 				 OMAP4_PRM_IRQENABLE_MPU_OFFSET);
-	omap4_prm_write_inst_reg(0, OMAP4430_PRM_DEVICE_INST,
+	omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST,
 				 OMAP4_PRM_IRQENABLE_MPU_2_OFFSET);
 
 	/* OCP barrier */
-	omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST,
+	omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
 				OMAP4_REVISION_PRM_OFFSET);
 }
 
@@ -226,9 +227,9 @@ void omap44xx_prm_save_and_clear_irqen(u32 *saved_mask)
  */
 void omap44xx_prm_restore_irqen(u32 *saved_mask)
 {
-	omap4_prm_write_inst_reg(saved_mask[0], OMAP4430_PRM_DEVICE_INST,
+	omap4_prm_write_inst_reg(saved_mask[0], OMAP4430_PRM_OCP_SOCKET_INST,
 				 OMAP4_PRM_IRQENABLE_MPU_OFFSET);
-	omap4_prm_write_inst_reg(saved_mask[1], OMAP4430_PRM_DEVICE_INST,
+	omap4_prm_write_inst_reg(saved_mask[1], OMAP4430_PRM_OCP_SOCKET_INST,
 				 OMAP4_PRM_IRQENABLE_MPU_2_OFFSET);
 }
 
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 873b51d494ea..d28f848897d6 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -290,7 +290,7 @@ int omap_prcm_register_chain_handler(struct omap_prcm_irq_setup *irq_setup)
 		goto err;
 	}
 
-	for (i = 0; i <= irq_setup->nr_regs; i++) {
+	for (i = 0; i < irq_setup->nr_regs; i++) {
 		gc = irq_alloc_generic_chip("PRCM", 1,
 			irq_setup->base_irq + i * 32, prm_base,
 			handle_level_irq);
diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S
index abd283400490..9f6b83d1b193 100644
--- a/arch/arm/mach-omap2/sleep44xx.S
+++ b/arch/arm/mach-omap2/sleep44xx.S
@@ -10,7 +10,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/system.h>
 #include <asm/smp_scu.h>
 #include <asm/memory.h>
 #include <asm/hardware/cache-l2x0.h>
diff --git a/arch/arm/mach-omap2/usb-host.c b/arch/arm/mach-omap2/usb-host.c
index f51348dafafd..dde8a11f47d5 100644
--- a/arch/arm/mach-omap2/usb-host.c
+++ b/arch/arm/mach-omap2/usb-host.c
@@ -54,7 +54,7 @@ static struct omap_device_pm_latency omap_uhhtll_latency[] = {
 /*
  * setup_ehci_io_mux - initialize IO pad mux for USBHOST
  */
-static void setup_ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
+static void __init setup_ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 {
 	switch (port_mode[0]) {
 	case OMAP_EHCI_PORT_MODE_PHY:
@@ -197,7 +197,8 @@ static void setup_ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 	return;
 }
 
-static void setup_4430ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
+static
+void __init setup_4430ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 {
 	switch (port_mode[0]) {
 	case OMAP_EHCI_PORT_MODE_PHY:
@@ -315,7 +316,7 @@ static void setup_4430ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 	}
 }
 
-static void setup_ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
+static void __init setup_ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 {
 	switch (port_mode[0]) {
 	case OMAP_OHCI_PORT_MODE_PHY_6PIN_DATSE0:
@@ -412,7 +413,8 @@ static void setup_ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 	}
 }
 
-static void setup_4430ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
+static
+void __init setup_4430ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 {
 	switch (port_mode[0]) {
 	case OMAP_OHCI_PORT_MODE_PHY_6PIN_DATSE0:
diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c
index 5dad38ec00ea..24481666d2cd 100644
--- a/arch/arm/mach-orion5x/common.c
+++ b/arch/arm/mach-orion5x/common.c
@@ -21,6 +21,7 @@
 #include <net/dsa.h>
 #include <asm/page.h>
 #include <asm/setup.h>
+#include <asm/system_misc.h>
 #include <asm/timex.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h
index d2513ac79ff5..2e6454c8d4ba 100644
--- a/arch/arm/mach-orion5x/common.h
+++ b/arch/arm/mach-orion5x/common.h
@@ -57,5 +57,14 @@ struct meminfo;
 struct tag;
 extern void __init tag_fixup_mem32(struct tag *, char **, struct meminfo *);
 
+/*****************************************************************************
+ * Helpers to access Orion registers
+ ****************************************************************************/
+/*
+ * These are not preempt-safe.  Locks, if needed, must be taken
+ * care of by the caller.
+ */
+#define orion5x_setbits(r, mask)	writel(readl(r) | (mask), (r))
+#define orion5x_clrbits(r, mask)	writel(readl(r) & ~(mask), (r))
 
 #endif
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index 91b0f4788597..c3ed15b8ea25 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -32,6 +32,7 @@
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/pci.h>
+#include <asm/system_info.h>
 #include <mach/orion5x.h>
 #include "common.h"
 #include "mpp.h"
diff --git a/arch/arm/mach-orion5x/include/mach/io.h b/arch/arm/mach-orion5x/include/mach/io.h
deleted file mode 100644
index e9d9afdc2659..000000000000
--- a/arch/arm/mach-orion5x/include/mach/io.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * arch/arm/mach-orion5x/include/mach/io.h
- *
- * Tzachi Perelstein <tzachi@marvell.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __ASM_ARCH_IO_H
-#define __ASM_ARCH_IO_H
-
-#include "orion5x.h"
-
-#define IO_SPACE_LIMIT		0xffffffff
-
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-
-
-/*****************************************************************************
- * Helpers to access Orion registers
- ****************************************************************************/
-/*
- * These are not preempt-safe.  Locks, if needed, must be taken
- * care of by the caller.
- */
-#define orion5x_setbits(r, mask)	writel(readl(r) | (mask), (r))
-#define orion5x_clrbits(r, mask)	writel(readl(r) & ~(mask), (r))
-
-
-#endif
diff --git a/arch/arm/mach-orion5x/ls-chl-setup.c b/arch/arm/mach-orion5x/ls-chl-setup.c
index 527213169db0..0c9e413b5805 100644
--- a/arch/arm/mach-orion5x/ls-chl-setup.c
+++ b/arch/arm/mach-orion5x/ls-chl-setup.c
@@ -22,7 +22,6 @@
 #include <linux/gpio.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <asm/system.h>
 #include <mach/orion5x.h>
 #include "common.h"
 #include "mpp.h"
diff --git a/arch/arm/mach-orion5x/ls_hgl-setup.c b/arch/arm/mach-orion5x/ls_hgl-setup.c
index 9a8697b97dd7..c1b5d8a58037 100644
--- a/arch/arm/mach-orion5x/ls_hgl-setup.c
+++ b/arch/arm/mach-orion5x/ls_hgl-setup.c
@@ -21,7 +21,6 @@
 #include <linux/gpio.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <asm/system.h>
 #include <mach/orion5x.h>
 #include "common.h"
 #include "mpp.h"
diff --git a/arch/arm/mach-orion5x/lsmini-setup.c b/arch/arm/mach-orion5x/lsmini-setup.c
index 09c73659f467..949eaa8f12e3 100644
--- a/arch/arm/mach-orion5x/lsmini-setup.c
+++ b/arch/arm/mach-orion5x/lsmini-setup.c
@@ -21,7 +21,6 @@
 #include <linux/gpio.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <asm/system.h>
 #include <mach/orion5x.h>
 #include "common.h"
 #include "mpp.h"
diff --git a/arch/arm/mach-orion5x/pci.c b/arch/arm/mach-orion5x/pci.c
index d6a91948e4dc..cb19e1661bb3 100644
--- a/arch/arm/mach-orion5x/pci.c
+++ b/arch/arm/mach-orion5x/pci.c
@@ -19,6 +19,7 @@
 #include <asm/mach/pci.h>
 #include <plat/pcie.h>
 #include <plat/addr-map.h>
+#include <mach/orion5x.h>
 #include "common.h"
 
 /*****************************************************************************
diff --git a/arch/arm/mach-orion5x/tsx09-common.c b/arch/arm/mach-orion5x/tsx09-common.c
index c9abb8fbfa70..7189827d641d 100644
--- a/arch/arm/mach-orion5x/tsx09-common.c
+++ b/arch/arm/mach-orion5x/tsx09-common.c
@@ -15,6 +15,7 @@
 #include <linux/mv643xx_eth.h>
 #include <linux/timex.h>
 #include <linux/serial_reg.h>
+#include <mach/orion5x.h>
 #include "tsx09-common.h"
 #include "common.h"
 
diff --git a/arch/arm/mach-picoxcell/include/mach/io.h b/arch/arm/mach-picoxcell/include/mach/io.h
deleted file mode 100644
index 7573ec7d10a3..000000000000
--- a/arch/arm/mach-picoxcell/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No ioports, but needed for driver compatibility. */
-#define __io(a)			__typesafe_io(a)
-/* No PCI possible on picoxcell. */
-#define __mem_pci(a)		(a)
-
-#endif /* __ASM_ARM_ARCH_IO_H */
diff --git a/arch/arm/mach-picoxcell/include/mach/irqs.h b/arch/arm/mach-picoxcell/include/mach/irqs.h
deleted file mode 100644
index 59eac1ee2820..000000000000
--- a/arch/arm/mach-picoxcell/include/mach/irqs.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef __MACH_IRQS_H
-#define __MACH_IRQS_H
-
-/* We dynamically allocate our irq_desc's. */
-#define NR_IRQS				0
-
-#endif /* __MACH_IRQS_H */
diff --git a/arch/arm/mach-pnx4008/core.c b/arch/arm/mach-pnx4008/core.c
index 4cfb40b2ec19..be4c92858509 100644
--- a/arch/arm/mach-pnx4008/core.c
+++ b/arch/arm/mach-pnx4008/core.c
@@ -32,7 +32,7 @@
 #include <asm/mach-types.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
+#include <asm/system_misc.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-pnx4008/dma.c b/arch/arm/mach-pnx4008/dma.c
index 7fa4bf2e2125..a4739e9fb2fb 100644
--- a/arch/arm/mach-pnx4008/dma.c
+++ b/arch/arm/mach-pnx4008/dma.c
@@ -24,7 +24,6 @@
 #include <linux/io.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <mach/dma.h>
 #include <asm/dma-mapping.h>
diff --git a/arch/arm/mach-pnx4008/include/mach/io.h b/arch/arm/mach-pnx4008/include/mach/io.h
deleted file mode 100644
index cbf0904540ea..000000000000
--- a/arch/arm/mach-pnx4008/include/mach/io.h
+++ /dev/null
@@ -1,21 +0,0 @@
-
-/*
- *  arch/arm/mach-pnx4008/include/mach/io.h
- *
- * Author: Dmitry Chigirev <chigirev@ru.mvista.com>
- *
- * 2005 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-pnx4008/irq.c b/arch/arm/mach-pnx4008/irq.c
index 7608c7a288cf..41e4201972d5 100644
--- a/arch/arm/mach-pnx4008/irq.c
+++ b/arch/arm/mach-pnx4008/irq.c
@@ -28,7 +28,6 @@
 #include <asm/setup.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-pnx4008/time.c b/arch/arm/mach-pnx4008/time.c
index 0c8aad4bb0dc..0cfe8af3d3be 100644
--- a/arch/arm/mach-pnx4008/time.c
+++ b/arch/arm/mach-pnx4008/time.c
@@ -24,7 +24,6 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/leds.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-prima2/include/mach/io.h b/arch/arm/mach-prima2/include/mach/io.h
deleted file mode 100644
index 6c31e9ec279e..000000000000
--- a/arch/arm/mach-prima2/include/mach/io.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * arch/arm/mach-prima2/include/mach/io.h
- *
- * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
- *
- * Licensed under GPLv2 or later.
- */
-
-#ifndef __MACH_PRIMA2_IO_H
-#define __MACH_PRIMA2_IO_H
-
-#define IO_SPACE_LIMIT ((resource_size_t)0)
-
-#define __mem_pci(a)            (a)
-
-#endif
diff --git a/arch/arm/mach-prima2/timer.c b/arch/arm/mach-prima2/timer.c
index b7a6091ce791..0d024b1e916d 100644
--- a/arch/arm/mach-prima2/timer.c
+++ b/arch/arm/mach-prima2/timer.c
@@ -18,6 +18,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <mach/map.h>
+#include <asm/sched_clock.h>
 #include <asm/mach/time.h>
 
 #define SIRFSOC_TIMER_COUNTER_LO	0x0000
@@ -165,21 +166,9 @@ static struct irqaction sirfsoc_timer_irq = {
 };
 
 /* Overwrite weak default sched_clock with more precise one */
-unsigned long long notrace sched_clock(void)
+static u32 notrace sirfsoc_read_sched_clock(void)
 {
-	static int is_mapped;
-
-	/*
-	 * sched_clock is called earlier than .init of sys_timer
-	 * if we map timer memory in .init of sys_timer, system
-	 * will panic due to illegal memory access
-	 */
-	if (!is_mapped) {
-		sirfsoc_of_timer_map();
-		is_mapped = 1;
-	}
-
-	return sirfsoc_timer_read(NULL) * (NSEC_PER_SEC / CLOCK_TICK_RATE);
+	return (u32)(sirfsoc_timer_read(NULL) & 0xffffffff);
 }
 
 static void __init sirfsoc_clockevent_init(void)
@@ -210,6 +199,8 @@ static void __init sirfsoc_timer_init(void)
 	BUG_ON(rate < CLOCK_TICK_RATE);
 	BUG_ON(rate % CLOCK_TICK_RATE);
 
+	sirfsoc_of_timer_map();
+
 	writel_relaxed(rate / CLOCK_TICK_RATE / 2 - 1, sirfsoc_timer_base + SIRFSOC_TIMER_DIV);
 	writel_relaxed(0, sirfsoc_timer_base + SIRFSOC_TIMER_COUNTER_LO);
 	writel_relaxed(0, sirfsoc_timer_base + SIRFSOC_TIMER_COUNTER_HI);
@@ -217,6 +208,8 @@ static void __init sirfsoc_timer_init(void)
 
 	BUG_ON(clocksource_register_hz(&sirfsoc_clocksource, CLOCK_TICK_RATE));
 
+	setup_sched_clock(sirfsoc_read_sched_clock, 32, CLOCK_TICK_RATE);
+
 	BUG_ON(setup_irq(sirfsoc_timer_irq.irq, &sirfsoc_timer_irq));
 
 	sirfsoc_clockevent_init();
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 61d3c72ded84..fe2d1f80ef50 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -108,10 +108,12 @@ config CSB726_CSB701
 
 config MACH_ARMCORE
 	bool "CompuLab CM-X255/CM-X270 modules"
+	select ARCH_HAS_DMA_SET_COHERENT_MASK if PCI
 	select PXA27x
 	select IWMMXT
 	select PXA25x
 	select MIGHT_HAVE_PCI
+	select NEED_MACH_IO_H if PCI
 
 config MACH_EM_X270
 	bool "CompuLab EM-x270 platform"
diff --git a/arch/arm/mach-pxa/capc7117.c b/arch/arm/mach-pxa/capc7117.c
index c91727d1fe09..9a8760b72913 100644
--- a/arch/arm/mach-pxa/capc7117.c
+++ b/arch/arm/mach-pxa/capc7117.c
@@ -150,6 +150,7 @@ MACHINE_START(CAPC7117,
 	      "Embedian CAPC-7117 evaluation kit based on the MXM-8x10 CoM")
 	.atag_offset = 0x100,
 	.map_io = pxa3xx_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa3xx_init_irq,
 	.handle_irq = pxa3xx_handle_irq,
 	.timer = &pxa_timer,
diff --git a/arch/arm/mach-pxa/clock-pxa2xx.c b/arch/arm/mach-pxa/clock-pxa2xx.c
index 1d5859d9a0e3..9ee2ad6a0a07 100644
--- a/arch/arm/mach-pxa/clock-pxa2xx.c
+++ b/arch/arm/mach-pxa/clock-pxa2xx.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/syscore_ops.h>
 
 #include <mach/pxa2xx-regs.h>
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 4b981b82d2a5..313274016277 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -44,6 +44,7 @@
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/setup.h>
+#include <asm/system_info.h>
 
 #include <mach/pxa300.h>
 #include <mach/pxa27x-udc.h>
@@ -713,7 +714,6 @@ struct da9030_battery_info cm_x300_battery_info = {
 
 static struct regulator_consumer_supply buck2_consumers[] = {
 	{
-		.dev = NULL,
 		.supply = "vcc_core",
 	},
 };
@@ -853,6 +853,7 @@ static void __init cm_x300_fixup(struct tag *tags, char **cmdline,
 MACHINE_START(CM_X300, "CM-X300 module")
 	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/colibri-pxa270.c b/arch/arm/mach-pxa/colibri-pxa270.c
index 29d5d541f602..b2f227d36125 100644
--- a/arch/arm/mach-pxa/colibri-pxa270.c
+++ b/arch/arm/mach-pxa/colibri-pxa270.c
@@ -310,6 +310,7 @@ MACHINE_START(COLIBRI, "Toradex Colibri PXA270")
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa270_init,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
@@ -320,6 +321,7 @@ MACHINE_START(INCOME, "Income s.r.o. SH-Dmaster PXA270 SBC")
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa270_income_init,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/colibri-pxa300.c b/arch/arm/mach-pxa/colibri-pxa300.c
index 0846d210cb05..bb6def8ec979 100644
--- a/arch/arm/mach-pxa/colibri-pxa300.c
+++ b/arch/arm/mach-pxa/colibri-pxa300.c
@@ -186,6 +186,7 @@ MACHINE_START(COLIBRI300, "Toradex Colibri PXA300")
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa300_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/colibri-pxa320.c b/arch/arm/mach-pxa/colibri-pxa320.c
index 6ad3359063af..d88e7b37f1da 100644
--- a/arch/arm/mach-pxa/colibri-pxa320.c
+++ b/arch/arm/mach-pxa/colibri-pxa320.c
@@ -256,6 +256,7 @@ MACHINE_START(COLIBRI320, "Toradex Colibri PXA320")
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa320_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/colibri-pxa3xx.c b/arch/arm/mach-pxa/colibri-pxa3xx.c
index 2b8ca0de8a3d..68cc75fac219 100644
--- a/arch/arm/mach-pxa/colibri-pxa3xx.c
+++ b/arch/arm/mach-pxa/colibri-pxa3xx.c
@@ -18,6 +18,7 @@
 #include <asm/mach-types.h>
 #include <mach/hardware.h>
 #include <asm/sizes.h>
+#include <asm/system_info.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <mach/pxa3xx-regs.h>
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 11f1e735966e..c1fe32db4755 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -40,7 +40,6 @@
 #include <asm/mach-types.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -730,6 +729,7 @@ static void __init fixup_corgi(struct tag *tags, char **cmdline,
 MACHINE_START(CORGI, "SHARP Corgi")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,
@@ -742,6 +742,7 @@ MACHINE_END
 MACHINE_START(SHEPHERD, "SHARP Shepherd")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,
@@ -754,6 +755,7 @@ MACHINE_END
 MACHINE_START(HUSKY, "SHARP Husky")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,
diff --git a/arch/arm/mach-pxa/corgi_pm.c b/arch/arm/mach-pxa/corgi_pm.c
index 39e265cfc86d..048c4299473c 100644
--- a/arch/arm/mach-pxa/corgi_pm.c
+++ b/arch/arm/mach-pxa/corgi_pm.c
@@ -19,6 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/apm-emulation.h>
+#include <linux/io.h>
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/cpufreq-pxa3xx.c b/arch/arm/mach-pxa/cpufreq-pxa3xx.c
index 88fbec05ec50..b85b4ab7aac6 100644
--- a/arch/arm/mach-pxa/cpufreq-pxa3xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa3xx.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/cpufreq.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 
 #include <mach/pxa3xx-regs.h>
 
diff --git a/arch/arm/mach-pxa/csb726.c b/arch/arm/mach-pxa/csb726.c
index fb5a51d834e5..67f0de37f46e 100644
--- a/arch/arm/mach-pxa/csb726.c
+++ b/arch/arm/mach-pxa/csb726.c
@@ -274,6 +274,7 @@ static void __init csb726_init(void)
 MACHINE_START(CSB726, "Cogent CSB726")
 	.atag_offset	= 0x100,
 	.map_io         = pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.init_machine   = csb726_init,
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 84f2d7015cfe..166eee5b8a70 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -12,6 +12,7 @@
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
 #include <mach/irda.h>
+#include <mach/irqs.h>
 #include <mach/ohci.h>
 #include <plat/pxa27x_keypad.h>
 #include <mach/camera.h>
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index d80c0ba9a095..16ec557b8e43 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -1083,19 +1083,19 @@ static void __init em_x270_userspace_consumers_init(void)
 }
 
 /* DA9030 related initializations */
-#define REGULATOR_CONSUMER(_name, _dev, _supply)			       \
+#define REGULATOR_CONSUMER(_name, _dev_name, _supply)		        \
 	static struct regulator_consumer_supply _name##_consumers[] = {	\
 		{							\
-			.dev = _dev,					\
+			.dev_name = _dev_name,				\
 			.supply = _supply,				\
 		},							\
 	}
 
-REGULATOR_CONSUMER(ldo3, &em_x270_gps_userspace_consumer.dev, "vcc gps");
+REGULATOR_CONSUMER(ldo3, "reg-userspace-consumer.0", "vcc gps");
 REGULATOR_CONSUMER(ldo5, NULL, "vcc cam");
-REGULATOR_CONSUMER(ldo10, &pxa_device_mci.dev, "vcc sdio");
+REGULATOR_CONSUMER(ldo10, "pxa2xx-mci", "vcc sdio");
 REGULATOR_CONSUMER(ldo12, NULL, "vcc usb");
-REGULATOR_CONSUMER(ldo19, &em_x270_gprs_userspace_consumer.dev, "vcc gprs");
+REGULATOR_CONSUMER(ldo19, "reg-userspace-consumer.1", "vcc gprs");
 REGULATOR_CONSUMER(buck2, NULL, "vcc_core");
 
 #define REGULATOR_INIT(_ldo, _min_uV, _max_uV, _ops_mask)		\
@@ -1301,6 +1301,7 @@ static void __init em_x270_init(void)
 MACHINE_START(EM_X270, "Compulab EM-X270")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
@@ -1311,6 +1312,7 @@ MACHINE_END
 MACHINE_START(EXEDA, "Compulab eXeda")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index 5432ecb15def..42254175fcf4 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -22,7 +22,6 @@
 #include <linux/init.h>
 
 #include <mach/hardware.h>
-#include <asm/system.h>
 #include <asm/mach/map.h>
 #include <asm/mach-types.h>
 
diff --git a/arch/arm/mach-pxa/gumstix.c b/arch/arm/mach-pxa/gumstix.c
index ac3b1cef4751..e529a35a44ce 100644
--- a/arch/arm/mach-pxa/gumstix.c
+++ b/arch/arm/mach-pxa/gumstix.c
@@ -235,6 +235,7 @@ static void __init gumstix_init(void)
 MACHINE_START(GUMSTIX, "Gumstix")
 	.atag_offset	= 0x100, /* match u-boot bi_boot_params */
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/h5000.c b/arch/arm/mach-pxa/h5000.c
index fde6b4c873c4..e7dec589f014 100644
--- a/arch/arm/mach-pxa/h5000.c
+++ b/arch/arm/mach-pxa/h5000.c
@@ -205,6 +205,7 @@ static void __init h5000_init(void)
 MACHINE_START(H5400, "HP iPAQ H5000")
 	.atag_offset = 0x100,
 	.map_io = pxa25x_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa25x_init_irq,
 	.handle_irq = pxa25x_handle_irq,
 	.timer = &pxa_timer,
diff --git a/arch/arm/mach-pxa/himalaya.c b/arch/arm/mach-pxa/himalaya.c
index 26d069a9f900..2962de898da9 100644
--- a/arch/arm/mach-pxa/himalaya.c
+++ b/arch/arm/mach-pxa/himalaya.c
@@ -160,6 +160,7 @@ static void __init himalaya_init(void)
 MACHINE_START(HIMALAYA, "HTC Himalaya")
 	.atag_offset = 0x100,
 	.map_io = pxa25x_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa25x_init_irq,
 	.handle_irq = pxa25x_handle_irq,
 	.init_machine = himalaya_init,
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index 3fa929d4a4f5..b83b95a29503 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -681,11 +681,9 @@ static struct platform_device power_supply = {
 
 static struct regulator_consumer_supply bq24022_consumers[] = {
 	{
-		.dev = &gpio_vbus.dev,
 		.supply = "vbus_draw",
 	},
 	{
-		.dev = &power_supply.dev,
 		.supply = "ac_draw",
 	},
 };
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index 67400192ed3b..1d02eabc9c65 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -193,6 +193,7 @@ static void __init icontrol_init(void)
 MACHINE_START(ICONTROL, "iControl/SafeTcam boards using Embedian MXM-8x10 CoM")
 	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index 8af1840e12cc..6ff466bd43e8 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -195,6 +195,7 @@ static void __init idp_map_io(void)
 MACHINE_START(PXA_IDP, "Vibren PXA255 IDP")
 	/* Maintainer: Vibren Technologies */
 	.map_io		= idp_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h
index 8184669dde28..56d92e5cad85 100644
--- a/arch/arm/mach-pxa/include/mach/hardware.h
+++ b/arch/arm/mach-pxa/include/mach/hardware.h
@@ -40,7 +40,6 @@
 #define io_p2v(x) IOMEM(0xf2000000 + ((x) & 0x01ffffff) + (((x) & 0x1c000000) >> 1))
 
 #ifndef __ASSEMBLY__
-# define IOMEM(x) ((void __iomem *)(x))
 # define __REG(x)	(*((volatile u32 __iomem *)io_p2v(x)))
 
 /* With indexed regs we don't want to feed the index through io_p2v()
@@ -52,7 +51,6 @@
 
 #else
 
-# define IOMEM(x)	x 
 # define __REG(x)	io_p2v(x)
 # define __PREG(x)	io_v2p(x)
 
@@ -337,8 +335,4 @@ extern unsigned int get_memclk_frequency_10khz(void);
 extern unsigned long get_clock_tick_rate(void);
 #endif
 
-#if defined(CONFIG_MACH_ARMCORE) && defined(CONFIG_PCI)
-#define ARCH_HAS_DMA_SET_COHERENT_MASK
-#endif
-
 #endif  /* _ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h
index fdca3be47d9b..cd78b7fe3567 100644
--- a/arch/arm/mach-pxa/include/mach/io.h
+++ b/arch/arm/mach-pxa/include/mach/io.h
@@ -6,8 +6,6 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT 0xffffffff
 
 /*
@@ -15,6 +13,5 @@
  * drivers out there that might just work if we fake them...
  */
 #define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/irqs.h b/arch/arm/mach-pxa/include/mach/irqs.h
index 32975adf3ca4..8765782dd955 100644
--- a/arch/arm/mach-pxa/include/mach/irqs.h
+++ b/arch/arm/mach-pxa/include/mach/irqs.h
@@ -100,7 +100,7 @@
  */
 #define IRQ_BOARD_START		(PXA_GPIO_IRQ_BASE + PXA_NR_BUILTIN_GPIO)
 
-#define NR_IRQS			(IRQ_BOARD_START)
+#define PXA_NR_IRQS		(IRQ_BOARD_START)
 
 #ifndef __ASSEMBLY__
 struct irq_data;
diff --git a/arch/arm/mach-pxa/include/mach/mainstone.h b/arch/arm/mach-pxa/include/mach/mainstone.h
index 4c2d11cd824d..1bfc4e822a41 100644
--- a/arch/arm/mach-pxa/include/mach/mainstone.h
+++ b/arch/arm/mach-pxa/include/mach/mainstone.h
@@ -13,6 +13,8 @@
 #ifndef ASM_ARCH_MAINSTONE_H
 #define ASM_ARCH_MAINSTONE_H
 
+#include <mach/irqs.h>
+
 #define MST_ETH_PHYS		PXA_CS4_PHYS
 
 #define MST_FPGA_PHYS		PXA_CS2_PHYS
diff --git a/arch/arm/mach-pxa/leds-idp.c b/arch/arm/mach-pxa/leds-idp.c
index 8b9c17142d5a..06b060025d11 100644
--- a/arch/arm/mach-pxa/leds-idp.c
+++ b/arch/arm/mach-pxa/leds-idp.c
@@ -16,7 +16,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #include <mach/pxa25x.h>
 #include <mach/idp.h>
diff --git a/arch/arm/mach-pxa/leds-lubbock.c b/arch/arm/mach-pxa/leds-lubbock.c
index e26d5efe1969..0bd85c884a7c 100644
--- a/arch/arm/mach-pxa/leds-lubbock.c
+++ b/arch/arm/mach-pxa/leds-lubbock.c
@@ -15,7 +15,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 #include <mach/pxa25x.h>
 #include <mach/lubbock.h>
 
diff --git a/arch/arm/mach-pxa/leds-mainstone.c b/arch/arm/mach-pxa/leds-mainstone.c
index db4af5eee8b2..4058ab340fe6 100644
--- a/arch/arm/mach-pxa/leds-mainstone.c
+++ b/arch/arm/mach-pxa/leds-mainstone.c
@@ -14,7 +14,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #include <mach/pxa27x.h>
 #include <mach/mainstone.h>
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index 6ebd276aebeb..6bb3f47b1f14 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -223,6 +223,7 @@ static struct resource sa1111_resources[] = {
 
 static struct sa1111_platform_data sa1111_info = {
 	.irq_base	= LUBBOCK_SA1111_IRQ_BASE,
+	.disable_devs	= SA1111_DEVID_SAC,
 };
 
 static struct platform_device sa1111_device = {
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index 5e26f3e93fdd..8de0651d7efb 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -34,6 +34,7 @@
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
+#include <asm/system_info.h>
 
 #include <mach/pxa27x.h>
 #include <mach/magician.h>
@@ -579,11 +580,9 @@ static struct platform_device power_supply = {
 
 static struct regulator_consumer_supply bq24022_consumers[] = {
 	{
-		.dev = &gpio_vbus.dev,
 		.supply = "vbus_draw",
 	},
 	{
-		.dev = &power_supply.dev,
 		.supply = "ac_draw",
 	},
 };
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c
index 29b62afc6f7c..b0a842887780 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/syscore_ops.h>
 
 #include <mach/pxa2xx-regs.h>
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index e80a3db735c2..061d57009cee 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -758,6 +758,7 @@ MACHINE_START(MIOA701, "MIO A701")
 	.atag_offset	= 0x100,
 	.restart_mode	= 's',
 	.map_io		= &pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= &pxa27x_init_irq,
 	.handle_irq	= &pxa27x_handle_irq,
 	.init_machine	= mioa701_machine_init,
diff --git a/arch/arm/mach-pxa/mp900.c b/arch/arm/mach-pxa/mp900.c
index 169bf8f97af0..152efbf093f6 100644
--- a/arch/arm/mach-pxa/mp900.c
+++ b/arch/arm/mach-pxa/mp900.c
@@ -95,6 +95,7 @@ MACHINE_START(NEC_MP900, "MobilePro900/C")
 	.atag_offset	= 0x220100,
 	.timer		= &pxa_timer,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= mp900c_init,
diff --git a/arch/arm/mach-pxa/palmld.c b/arch/arm/mach-pxa/palmld.c
index 1fa80f4f80c8..31e0433d83ba 100644
--- a/arch/arm/mach-pxa/palmld.c
+++ b/arch/arm/mach-pxa/palmld.c
@@ -344,6 +344,7 @@ static void __init palmld_init(void)
 MACHINE_START(PALMLD, "Palm LifeDrive")
 	.atag_offset	= 0x100,
 	.map_io		= palmld_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmt5.c b/arch/arm/mach-pxa/palmt5.c
index 5ba14316bd9c..0f6bd4fcfa3b 100644
--- a/arch/arm/mach-pxa/palmt5.c
+++ b/arch/arm/mach-pxa/palmt5.c
@@ -205,6 +205,7 @@ MACHINE_START(PALMT5, "Palm Tungsten|T5")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.reserve	= palmt5_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index 29b51b40f09d..e2d97eed07a7 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -539,6 +539,7 @@ static void __init palmtc_init(void)
 MACHINE_START(PALMTC, "Palm Tungsten|C")
 	.atag_offset 	= 0x100,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmte2.c b/arch/arm/mach-pxa/palmte2.c
index 5ebf49acb827..c054827c567f 100644
--- a/arch/arm/mach-pxa/palmte2.c
+++ b/arch/arm/mach-pxa/palmte2.c
@@ -358,6 +358,7 @@ static void __init palmte2_init(void)
 MACHINE_START(PALMTE2, "Palm Tungsten|E2")
 	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmtreo.c b/arch/arm/mach-pxa/palmtreo.c
index ec8249156c08..fbdebee39a53 100644
--- a/arch/arm/mach-pxa/palmtreo.c
+++ b/arch/arm/mach-pxa/palmtreo.c
@@ -448,6 +448,7 @@ MACHINE_START(TREO680, "Palm Treo 680")
 	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.reserve	= treo_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.timer          = &pxa_timer,
@@ -461,6 +462,7 @@ MACHINE_START(CENTRO, "Palm Centro 685")
 	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.reserve	= treo_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c
index 6170d76dfba8..9507605ed547 100644
--- a/arch/arm/mach-pxa/palmtx.c
+++ b/arch/arm/mach-pxa/palmtx.c
@@ -366,6 +366,7 @@ static void __init palmtx_init(void)
 MACHINE_START(PALMTX, "Palm T|X")
 	.atag_offset	= 0x100,
 	.map_io		= palmtx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index b2dff9d415eb..a97b59965bb9 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -401,6 +401,7 @@ static void __init palmz72_init(void)
 MACHINE_START(PALMZ72, "Palm Zire72")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 744baee12c0c..89d98c832189 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -34,7 +34,6 @@
 #include <asm/mach-types.h>
 #include <asm/irq.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-pxa/pxa2xx.c b/arch/arm/mach-pxa/pxa2xx.c
index 868270421b8c..f8ec85450c42 100644
--- a/arch/arm/mach-pxa/pxa2xx.c
+++ b/arch/arm/mach-pxa/pxa2xx.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
 #include <mach/pxa2xx-regs.h>
diff --git a/arch/arm/mach-pxa/pxa300.c b/arch/arm/mach-pxa/pxa300.c
index 40bb16501d86..17cbc0c7bdb8 100644
--- a/arch/arm/mach-pxa/pxa300.c
+++ b/arch/arm/mach-pxa/pxa300.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
+#include <linux/io.h>
 
 #include <mach/pxa300.h>
 
diff --git a/arch/arm/mach-pxa/pxa320.c b/arch/arm/mach-pxa/pxa320.c
index 8d614ecd8e99..6dc99d4f2dc6 100644
--- a/arch/arm/mach-pxa/pxa320.c
+++ b/arch/arm/mach-pxa/pxa320.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
+#include <linux/io.h>
 
 #include <mach/pxa320.h>
 
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 1570d457fea3..dffb7e813d98 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -31,6 +31,7 @@
 #include <mach/pm.h>
 #include <mach/dma.h>
 #include <mach/smemc.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 #include "devices.h"
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index 22818c7694a8..5905ed130e94 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -43,6 +43,8 @@
 #include <linux/regulator/consumer.h>
 #include <linux/delay.h>
 
+#include <asm/system_info.h>
+
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
@@ -1090,6 +1092,7 @@ MACHINE_START(RAUMFELD_RC, "Raumfeld Controller")
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_controller_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
@@ -1102,6 +1105,7 @@ MACHINE_START(RAUMFELD_CONNECTOR, "Raumfeld Connector")
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_connector_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
@@ -1114,6 +1118,7 @@ MACHINE_START(RAUMFELD_SPEAKER, "Raumfeld Speaker")
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_speaker_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/reset.c b/arch/arm/mach-pxa/reset.c
index c8497b00cdfe..b4528899ef08 100644
--- a/arch/arm/mach-pxa/reset.c
+++ b/arch/arm/mach-pxa/reset.c
@@ -9,6 +9,7 @@
 #include <linux/gpio.h>
 #include <linux/io.h>
 #include <asm/proc-fns.h>
+#include <asm/system_misc.h>
 
 #include <mach/regs-ost.h>
 #include <mach/reset.h>
diff --git a/arch/arm/mach-pxa/saar.c b/arch/arm/mach-pxa/saar.c
index 0fe354efb931..86c95a5d8533 100644
--- a/arch/arm/mach-pxa/saar.c
+++ b/arch/arm/mach-pxa/saar.c
@@ -598,6 +598,7 @@ MACHINE_START(SAAR, "PXA930 Handheld Platform (aka SAAR)")
 	/* Maintainer: Eric Miao <eric.miao@marvell.com> */
 	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa3xx_init_irq,
 	.handle_irq       = pxa3xx_handle_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c
index 30989baf7f2a..bdf4cb88ca0a 100644
--- a/arch/arm/mach-pxa/sharpsl_pm.c
+++ b/arch/arm/mach-pxa/sharpsl_pm.c
@@ -24,6 +24,7 @@
 #include <linux/leds.h>
 #include <linux/suspend.h>
 #include <linux/gpio.h>
+#include <linux/io.h>
 
 #include <asm/mach-types.h>
 #include <mach/pm.h>
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index abf355d0c92f..df2ab0fb2ace 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -984,6 +984,7 @@ MACHINE_START(SPITZ, "SHARP Spitz")
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,
@@ -997,6 +998,7 @@ MACHINE_START(BORZOI, "SHARP Borzoi")
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,
@@ -1010,6 +1012,7 @@ MACHINE_START(AKITA, "SHARP Akita")
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,
diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c
index b0656e158d90..4cd645e29b64 100644
--- a/arch/arm/mach-pxa/stargate2.c
+++ b/arch/arm/mach-pxa/stargate2.c
@@ -152,7 +152,7 @@ static struct platform_device sht15 = {
 
 static struct regulator_consumer_supply stargate2_sensor_3_con[] = {
 	{
-		.dev = &sht15.dev,
+		.dev_name = "sht15",
 		.supply = "vcc",
 	},
 };
@@ -1006,6 +1006,7 @@ static void __init stargate2_init(void)
 #ifdef CONFIG_MACH_INTELMOTE2
 MACHINE_START(INTELMOTE2, "IMOTE 2")
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/tavorevb.c b/arch/arm/mach-pxa/tavorevb.c
index 9fb38e80e076..736bfdc50ee6 100644
--- a/arch/arm/mach-pxa/tavorevb.c
+++ b/arch/arm/mach-pxa/tavorevb.c
@@ -491,6 +491,7 @@ MACHINE_START(TAVOREVB, "PXA930 Evaluation Board (aka TavorEVB)")
 	/* Maintainer: Eric Miao <eric.miao@marvell.com> */
 	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa3xx_init_irq,
 	.handle_irq       = pxa3xx_handle_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index b503049d6d26..3d6c9bd90de6 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -22,6 +22,7 @@
 #include <asm/mach/time.h>
 #include <asm/sched_clock.h>
 #include <mach/regs-ost.h>
+#include <mach/irqs.h>
 
 /*
  * This is PXA's sched_clock implementation. This has a resolution
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index 0f30af617d8f..2b6ac00b2cd9 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -558,6 +558,7 @@ MACHINE_START(TRIZEPS4, "Keith und Koep Trizeps IV module")
 	.atag_offset	= 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
@@ -569,6 +570,7 @@ MACHINE_START(TRIZEPS4WL, "Keith und Koep Trizeps IV-WL module")
 	.atag_offset	= 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 023d6ca789de..130379fb9d0f 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -57,6 +57,7 @@
 #include <asm/mach-types.h>
 #include <asm/irq.h>
 #include <asm/sizes.h>
+#include <asm/system_info.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -994,6 +995,7 @@ MACHINE_START(VIPER, "Arcom/Eurotech VIPER SBC")
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
 	.atag_offset	= 0x100,
 	.map_io		= viper_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= viper_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index 1f5cfa96f6d6..c57ab636ea9c 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -718,6 +718,7 @@ static void __init vpac270_init(void)
 MACHINE_START(VPAC270, "Voipac PXA270")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index 4bbe9a36fe74..4275713ccd10 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -182,6 +182,7 @@ MACHINE_START(XCEP, "Iskratel XCEP")
 	.atag_offset	= 0x100,
 	.init_machine	= xcep_init,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c
index b6476848b561..fa8619970841 100644
--- a/arch/arm/mach-pxa/z2.c
+++ b/arch/arm/mach-pxa/z2.c
@@ -721,6 +721,7 @@ static void __init z2_init(void)
 MACHINE_START(ZIPIT2, "Zipit Z2")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index a4dd1c347050..af3d4f7646d7 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -32,6 +32,7 @@
 
 #include <asm/mach-types.h>
 #include <asm/suspend.h>
+#include <asm/system_info.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index acd329afc3ac..45868bb43cbd 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -33,7 +33,6 @@
 #include <linux/clkdev.h>
 #include <linux/mtd/physmap.h>
 
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/leds.h>
diff --git a/arch/arm/mach-realview/hotplug.c b/arch/arm/mach-realview/hotplug.c
index eb55f05bef3a..57d9efba2956 100644
--- a/arch/arm/mach-realview/hotplug.c
+++ b/arch/arm/mach-realview/hotplug.c
@@ -13,6 +13,7 @@
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
 #include <asm/smp_plat.h>
 
 extern volatile int pen_release;
diff --git a/arch/arm/mach-realview/include/mach/hardware.h b/arch/arm/mach-realview/include/mach/hardware.h
index 8a638d15797f..281e71c97525 100644
--- a/arch/arm/mach-realview/include/mach/hardware.h
+++ b/arch/arm/mach-realview/include/mach/hardware.h
@@ -37,6 +37,6 @@
 #else
 #define IO_ADDRESS(x)		(x)
 #endif
-#define __io_address(n)		__io(IO_ADDRESS(n))
+#define __io_address(n)		IOMEM(IO_ADDRESS(n))
 
 #endif
diff --git a/arch/arm/mach-realview/include/mach/io.h b/arch/arm/mach-realview/include/mach/io.h
deleted file mode 100644
index f05bcdf605d8..000000000000
--- a/arch/arm/mach-realview/include/mach/io.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- *  arch/arm/mach-realview/include/mach/io.h
- *
- *  Copyright (C) 2003 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-rpc/Makefile b/arch/arm/mach-rpc/Makefile
index dfa405c0cfde..992e28b4ae9a 100644
--- a/arch/arm/mach-rpc/Makefile
+++ b/arch/arm/mach-rpc/Makefile
@@ -4,7 +4,7 @@
 
 # Object file lists.
 
-obj-y			:= dma.o fiq.o irq.o riscpc.o
+obj-y			:= dma.o ecard.o fiq.o irq.o riscpc.o time.o
 obj-m			:=
 obj-n			:=
 obj-			:=
diff --git a/arch/arm/kernel/ecard.c b/arch/arm/mach-rpc/ecard.c
index 1651d4950744..b91bc87b3dcf 100644
--- a/arch/arm/kernel/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -42,6 +42,7 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/kthread.h>
+#include <linux/irq.h>
 #include <linux/io.h>
 
 #include <asm/dma.h>
@@ -54,10 +55,6 @@
 
 #include "ecard.h"
 
-#ifndef CONFIG_ARCH_RPC
-#define HAVE_EXPMASK
-#endif
-
 struct ecard_request {
 	void		(*fn)(struct ecard_request *);
 	ecard_t		*ec;
@@ -77,9 +74,6 @@ struct expcard_blacklist {
 static ecard_t *cards;
 static ecard_t *slot_to_expcard[MAX_ECARDS];
 static unsigned int ectcr;
-#ifdef HAS_EXPMASK
-static unsigned int have_expmask;
-#endif
 
 /* List of descriptions of cards which don't have an extended
  * identification, or chunk directories containing a description.
@@ -391,22 +385,10 @@ int ecard_readchunk(struct in_chunk_dir *cd, ecard_t *ec, int id, int num)
 
 static void ecard_def_irq_enable(ecard_t *ec, int irqnr)
 {
-#ifdef HAS_EXPMASK
-	if (irqnr < 4 && have_expmask) {
-		have_expmask |= 1 << irqnr;
-		__raw_writeb(have_expmask, EXPMASK_ENABLE);
-	}
-#endif
 }
 
 static void ecard_def_irq_disable(ecard_t *ec, int irqnr)
 {
-#ifdef HAS_EXPMASK
-	if (irqnr < 4 && have_expmask) {
-		have_expmask &= ~(1 << irqnr);
-		__raw_writeb(have_expmask, EXPMASK_ENABLE);
-	}
-#endif
 }
 
 static int ecard_def_irq_pending(ecard_t *ec)
@@ -446,7 +428,7 @@ static expansioncard_ops_t ecard_default_ops = {
  */
 static void ecard_irq_unmask(struct irq_data *d)
 {
-	ecard_t *ec = slot_to_ecard(d->irq - 32);
+	ecard_t *ec = irq_data_get_irq_chip_data(d);
 
 	if (ec) {
 		if (!ec->ops)
@@ -462,7 +444,7 @@ static void ecard_irq_unmask(struct irq_data *d)
 
 static void ecard_irq_mask(struct irq_data *d)
 {
-	ecard_t *ec = slot_to_ecard(d->irq - 32);
+	ecard_t *ec = irq_data_get_irq_chip_data(d);
 
 	if (ec) {
 		if (!ec->ops)
@@ -579,7 +561,7 @@ ecard_irq_handler(unsigned int irq, struct irq_desc *desc)
 	for (ec = cards; ec; ec = ec->next) {
 		int pending;
 
-		if (!ec->claimed || ec->irq == NO_IRQ || ec->slot_no == 8)
+		if (!ec->claimed || !ec->irq || ec->slot_no == 8)
 			continue;
 
 		if (ec->ops && ec->ops->irqpending)
@@ -598,83 +580,6 @@ ecard_irq_handler(unsigned int irq, struct irq_desc *desc)
 		ecard_check_lockup(desc);
 }
 
-#ifdef HAS_EXPMASK
-static unsigned char priority_masks[] =
-{
-	0xf0, 0xf1, 0xf3, 0xf7, 0xff, 0xff, 0xff, 0xff
-};
-
-static unsigned char first_set[] =
-{
-	0x00, 0x00, 0x01, 0x00, 0x02, 0x00, 0x01, 0x00,
-	0x03, 0x00, 0x01, 0x00, 0x02, 0x00, 0x01, 0x00
-};
-
-static void
-ecard_irqexp_handler(unsigned int irq, struct irq_desc *desc)
-{
-	const unsigned int statusmask = 15;
-	unsigned int status;
-
-	status = __raw_readb(EXPMASK_STATUS) & statusmask;
-	if (status) {
-		unsigned int slot = first_set[status];
-		ecard_t *ec = slot_to_ecard(slot);
-
-		if (ec->claimed) {
-			/*
-			 * this ugly code is so that we can operate a
-			 * prioritorising system:
-			 *
-			 * Card 0 	highest priority
-			 * Card 1
-			 * Card 2
-			 * Card 3	lowest priority
-			 *
-			 * Serial cards should go in 0/1, ethernet/scsi in 2/3
-			 * otherwise you will lose serial data at high speeds!
-			 */
-			generic_handle_irq(ec->irq);
-		} else {
-			printk(KERN_WARNING "card%d: interrupt from unclaimed "
-			       "card???\n", slot);
-			have_expmask &= ~(1 << slot);
-			__raw_writeb(have_expmask, EXPMASK_ENABLE);
-		}
-	} else
-		printk(KERN_WARNING "Wild interrupt from backplane (masks)\n");
-}
-
-static int __init ecard_probeirqhw(void)
-{
-	ecard_t *ec;
-	int found;
-
-	__raw_writeb(0x00, EXPMASK_ENABLE);
-	__raw_writeb(0xff, EXPMASK_STATUS);
-	found = (__raw_readb(EXPMASK_STATUS) & 15) == 0;
-	__raw_writeb(0xff, EXPMASK_ENABLE);
-
-	if (found) {
-		printk(KERN_DEBUG "Expansion card interrupt "
-		       "management hardware found\n");
-
-		/* for each card present, set a bit to '1' */
-		have_expmask = 0x80000000;
-
-		for (ec = cards; ec; ec = ec->next)
-			have_expmask |= 1 << ec->slot_no;
-
-		__raw_writeb(have_expmask, EXPMASK_ENABLE);
-	}
-
-	return found;
-}
-#else
-#define ecard_irqexp_handler NULL
-#define ecard_probeirqhw() (0)
-#endif
-
 static void __iomem *__ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed)
 {
 	void __iomem *address = NULL;
@@ -806,8 +711,8 @@ static struct expansion_card *__init ecard_alloc_card(int type, int slot)
 
 	ec->slot_no = slot;
 	ec->easi = type == ECARD_EASI;
-	ec->irq = NO_IRQ;
-	ec->fiq = NO_IRQ;
+	ec->irq = 0;
+	ec->fiq = 0;
 	ec->dma = NO_DMA;
 	ec->ops = &ecard_default_ops;
 
@@ -978,8 +883,7 @@ EXPORT_SYMBOL(ecardm_iomap);
  * If bit 1 of the first byte of the card is set, then the
  * card does not exist.
  */
-static int __init
-ecard_probe(int slot, card_type_t type)
+static int __init ecard_probe(int slot, unsigned irq, card_type_t type)
 {
 	ecard_t **ecp;
 	ecard_t *ec;
@@ -1033,18 +937,18 @@ ecard_probe(int slot, card_type_t type)
 			break;
 		}
 
+	ec->irq = irq;
+
 	/*
 	 * hook the interrupt handlers
 	 */
 	if (slot < 8) {
-		ec->irq = 32 + slot;
 		irq_set_chip_and_handler(ec->irq, &ecard_chip,
 					 handle_level_irq);
+		irq_set_chip_data(ec->irq, ec);
 		set_irq_flags(ec->irq, IRQF_VALID);
 	}
 
-	if (slot == 8)
-		ec->irq = 11;
 #ifdef CONFIG_ARCH_RPC
 	/* On RiscPC, only first two slots have DMA capability */
 	if (slot < 2)
@@ -1074,28 +978,30 @@ ecard_probe(int slot, card_type_t type)
 static int __init ecard_init(void)
 {
 	struct task_struct *task;
-	int slot, irqhw;
+	int slot, irqbase;
+
+	irqbase = irq_alloc_descs(-1, 0, 8, -1);
+	if (irqbase < 0)
+		return irqbase;
 
 	task = kthread_run(ecard_task, NULL, "kecardd");
 	if (IS_ERR(task)) {
 		printk(KERN_ERR "Ecard: unable to create kernel thread: %ld\n",
 		       PTR_ERR(task));
+		irq_free_descs(irqbase, 8);
 		return PTR_ERR(task);
 	}
 
 	printk("Probing expansion cards\n");
 
 	for (slot = 0; slot < 8; slot ++) {
-		if (ecard_probe(slot, ECARD_EASI) == -ENODEV)
-			ecard_probe(slot, ECARD_IOC);
+		if (ecard_probe(slot, irqbase + slot, ECARD_EASI) == -ENODEV)
+			ecard_probe(slot, irqbase + slot, ECARD_IOC);
 	}
 
-	ecard_probe(8, ECARD_IOC);
-
-	irqhw = ecard_probeirqhw();
+	ecard_probe(8, 11, ECARD_IOC);
 
-	irq_set_chained_handler(IRQ_EXPANSIONCARD,
-				irqhw ? ecard_irqexp_handler : ecard_irq_handler);
+	irq_set_chained_handler(IRQ_EXPANSIONCARD, ecard_irq_handler);
 
 	ecard_proc_init();
 
diff --git a/arch/arm/kernel/ecard.h b/arch/arm/mach-rpc/ecard.h
index 4642d436be2a..4642d436be2a 100644
--- a/arch/arm/kernel/ecard.h
+++ b/arch/arm/mach-rpc/ecard.h
diff --git a/arch/arm/mach-rpc/include/mach/hardware.h b/arch/arm/mach-rpc/include/mach/hardware.h
index 050d63c74cc1..257166b21f3d 100644
--- a/arch/arm/mach-rpc/include/mach/hardware.h
+++ b/arch/arm/mach-rpc/include/mach/hardware.h
@@ -14,12 +14,6 @@
 
 #include <mach/memory.h>
 
-#ifndef __ASSEMBLY__
-#define IOMEM(x) ((void __iomem *)(unsigned long)(x))
-#else
-#define IOMEM(x) x
-#endif /* __ASSEMBLY__ */
-
 /*
  * What hardware must be present
  */
diff --git a/arch/arm/mach-rpc/include/mach/io.h b/arch/arm/mach-rpc/include/mach/io.h
index 695f4ed2e11b..707071a7ea4e 100644
--- a/arch/arm/mach-rpc/include/mach/io.h
+++ b/arch/arm/mach-rpc/include/mach/io.h
@@ -28,9 +28,4 @@
  */
 #define __io(a)		(PCIO_BASE + ((a) << 2))
 
-/*
- * 1:1 mapping for ioremapped regions.
- */
-#define __mem_pci(x)	(x)
-
 #endif
diff --git a/arch/arm/mach-rpc/include/mach/irqs.h b/arch/arm/mach-rpc/include/mach/irqs.h
index 3d2037496e38..6868e178274d 100644
--- a/arch/arm/mach-rpc/include/mach/irqs.h
+++ b/arch/arm/mach-rpc/include/mach/irqs.h
@@ -42,6 +42,4 @@
  */
 #define FIQ_START		64
 
-#define IRQ_TIMER		IRQ_TIMER0
-
 #define NR_IRQS			128
diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c
index 3d44a59fc0df..f3fa259ce01f 100644
--- a/arch/arm/mach-rpc/riscpc.c
+++ b/arch/arm/mach-rpc/riscpc.c
@@ -28,6 +28,7 @@
 #include <asm/page.h>
 #include <asm/domain.h>
 #include <asm/setup.h>
+#include <asm/system_misc.h>
 
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
@@ -98,15 +99,9 @@ static void __init rpc_map_io(void)
 }
 
 static struct resource acornfb_resources[] = {
-	{	/* VIDC */
-		.start		= 0x03400000,
-		.end		= 0x035fffff,
-		.flags		= IORESOURCE_MEM,
-	}, {
-		.start		= IRQ_VSYNCPULSE,
-		.end		= IRQ_VSYNCPULSE,
-		.flags		= IORESOURCE_IRQ,
-	},
+	/* VIDC */
+	DEFINE_RES_MEM(0x03400000, 0x00200000),
+	DEFINE_RES_IRQ(IRQ_VSYNCPULSE),
 };
 
 static struct platform_device acornfb_device = {
@@ -120,11 +115,7 @@ static struct platform_device acornfb_device = {
 };
 
 static struct resource iomd_resources[] = {
-	{
-		.start		= 0x03200000,
-		.end		= 0x0320ffff,
-		.flags		= IORESOURCE_MEM,
-	},
+	DEFINE_RES_MEM(0x03200000, 0x10000),
 };
 
 static struct platform_device iomd_device = {
@@ -134,18 +125,25 @@ static struct platform_device iomd_device = {
 	.resource		= iomd_resources,
 };
 
+static struct resource iomd_kart_resources[] = {
+	DEFINE_RES_IRQ(IRQ_KEYBOARDRX),
+	DEFINE_RES_IRQ(IRQ_KEYBOARDTX),
+};
+
 static struct platform_device kbd_device = {
 	.name			= "kart",
 	.id			= -1,
 	.dev			= {
 		.parent 	= &iomd_device.dev,
 	},
+	.num_resources		= ARRAY_SIZE(iomd_kart_resources),
+	.resource		= iomd_kart_resources,
 };
 
 static struct plat_serial8250_port serial_platform_data[] = {
 	{
 		.mapbase	= 0x03010fe0,
-		.irq		= 10,
+		.irq		= IRQ_SERIALPORT,
 		.uartclk	= 1843200,
 		.regshift	= 2,
 		.iotype		= UPIO_MEM,
@@ -167,21 +165,9 @@ static struct pata_platform_info pata_platform_data = {
 };
 
 static struct resource pata_resources[] = {
-	[0] = {
-		.start		= 0x030107c0,
-		.end		= 0x030107df,
-		.flags		= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start		= 0x03010fd8,
-		.end		= 0x03010fdb,
-		.flags		= IORESOURCE_MEM,
-	},
-	[2] = {
-		.start		= IRQ_HARDDISK,
-		.end		= IRQ_HARDDISK,
-		.flags		= IORESOURCE_IRQ,
-	},
+	DEFINE_RES_MEM(0x030107c0, 0x20),
+	DEFINE_RES_MEM(0x03010fd8, 0x04),
+	DEFINE_RES_IRQ(IRQ_HARDDISK),
 };
 
 static struct platform_device pata_device = {
diff --git a/arch/arm/common/time-acorn.c b/arch/arm/mach-rpc/time.c
index deeed561b168..581fca934bb3 100644
--- a/arch/arm/common/time-acorn.c
+++ b/arch/arm/mach-rpc/time.c
@@ -85,7 +85,7 @@ static struct irqaction ioc_timer_irq = {
 static void __init ioc_timer_init(void)
 {
 	ioctime_init();
-	setup_irq(IRQ_TIMER, &ioc_timer_irq);
+	setup_irq(IRQ_TIMER0, &ioc_timer_irq);
 }
 
 struct sys_timer ioc_timer = {
diff --git a/arch/arm/mach-s3c24xx/common.h b/arch/arm/mach-s3c24xx/common.h
new file mode 100644
index 000000000000..c2f596e7bc2d
--- /dev/null
+++ b/arch/arm/mach-s3c24xx/common.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Common Header for S3C24XX SoCs
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARCH_ARM_MACH_S3C24XX_COMMON_H
+#define __ARCH_ARM_MACH_S3C24XX_COMMON_H __FILE__
+
+void s3c2410_restart(char mode, const char *cmd);
+void s3c244x_restart(char mode, const char *cmd);
+
+#endif /* __ARCH_ARM_MACH_S3C24XX_COMMON_H */
diff --git a/arch/arm/mach-s3c24xx/include/mach/io.h b/arch/arm/mach-s3c24xx/include/mach/io.h
index 118749f37c4c..5dd1db4e2677 100644
--- a/arch/arm/mach-s3c24xx/include/mach/io.h
+++ b/arch/arm/mach-s3c24xx/include/mach/io.h
@@ -208,9 +208,4 @@ DECLARE_IO(int,l,"")
 #define outsw(p,d,l)	__raw_writesw(__ioaddr(p),d,l)
 #define outsl(p,d,l)	__raw_writesl(__ioaddr(p),d,l)
 
-/*
- * 1:1 mapping for ioremapped regions.
- */
-#define __mem_pci(x)	(x)
-
 #endif
diff --git a/arch/arm/mach-s3c24xx/s3c2410.c b/arch/arm/mach-s3c24xx/s3c2410.c
index 061b6bb1a557..a3c5cb086ee2 100644
--- a/arch/arm/mach-s3c24xx/s3c2410.c
+++ b/arch/arm/mach-s3c24xx/s3c2410.c
@@ -30,6 +30,7 @@
 
 #include <mach/hardware.h>
 #include <asm/irq.h>
+#include <asm/system_misc.h>
 
 #include <plat/cpu-freq.h>
 
diff --git a/arch/arm/mach-s3c24xx/s3c2412.c b/arch/arm/mach-s3c24xx/s3c2412.c
index c6eac9871093..d4bc7f960bbb 100644
--- a/arch/arm/mach-s3c24xx/s3c2412.c
+++ b/arch/arm/mach-s3c24xx/s3c2412.c
@@ -31,6 +31,7 @@
 #include <mach/hardware.h>
 #include <asm/proc-fns.h>
 #include <asm/irq.h>
+#include <asm/system_misc.h>
 
 #include <plat/cpu-freq.h>
 
diff --git a/arch/arm/mach-s3c24xx/s3c2416.c b/arch/arm/mach-s3c24xx/s3c2416.c
index 0e9a71c90ed7..7743fade50df 100644
--- a/arch/arm/mach-s3c24xx/s3c2416.c
+++ b/arch/arm/mach-s3c24xx/s3c2416.c
@@ -43,6 +43,7 @@
 #include <mach/hardware.h>
 #include <asm/proc-fns.h>
 #include <asm/irq.h>
+#include <asm/system_misc.h>
 
 #include <mach/regs-s3c2443-clock.h>
 
diff --git a/arch/arm/mach-s3c24xx/s3c2443.c b/arch/arm/mach-s3c24xx/s3c2443.c
index b7778a9dafaf..ab648ad8fa50 100644
--- a/arch/arm/mach-s3c24xx/s3c2443.c
+++ b/arch/arm/mach-s3c24xx/s3c2443.c
@@ -29,6 +29,7 @@
 
 #include <mach/hardware.h>
 #include <asm/irq.h>
+#include <asm/system_misc.h>
 
 #include <mach/regs-s3c2443-clock.h>
 
diff --git a/arch/arm/mach-s3c24xx/s3c244x.c b/arch/arm/mach-s3c24xx/s3c244x.c
index d15852f642b7..6f74118f60c6 100644
--- a/arch/arm/mach-s3c24xx/s3c244x.c
+++ b/arch/arm/mach-s3c24xx/s3c244x.c
@@ -23,6 +23,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 
+#include <asm/system_misc.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-s3c24xx/simtec-nor.c b/arch/arm/mach-s3c24xx/simtec-nor.c
index 2119ca6a73bc..b9d6d4f92c03 100644
--- a/arch/arm/mach-s3c24xx/simtec-nor.c
+++ b/arch/arm/mach-s3c24xx/simtec-nor.c
@@ -35,9 +35,7 @@
 static void simtec_nor_vpp(struct platform_device *pdev, int vpp)
 {
 	unsigned int val;
-	unsigned long flags;
 
-	local_irq_save(flags);
 	val = __raw_readb(BAST_VA_CTRL3);
 
 	printk(KERN_DEBUG "%s(%d)\n", __func__, vpp);
@@ -48,7 +46,6 @@ static void simtec_nor_vpp(struct platform_device *pdev, int vpp)
 		val &= ~BAST_CPLD_CTRL3_ROMWEN;
 
 	__raw_writeb(val, BAST_VA_CTRL3);
-	local_irq_restore(flags);
 }
 
 static struct physmap_flash_data simtec_nor_pdata = {
diff --git a/arch/arm/mach-s3c64xx/common.c b/arch/arm/mach-s3c64xx/common.c
index bee7dcd4df7c..b313380342a5 100644
--- a/arch/arm/mach-s3c64xx/common.c
+++ b/arch/arm/mach-s3c64xx/common.c
@@ -29,6 +29,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/hardware/vic.h>
+#include <asm/system_misc.h>
 
 #include <mach/map.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-s3c64xx/include/mach/io.h b/arch/arm/mach-s3c64xx/include/mach/io.h
deleted file mode 100644
index de5716dbbd65..000000000000
--- a/arch/arm/mach-s3c64xx/include/mach/io.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* arch/arm/mach-s3c64xxinclude/mach/io.h
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben-linux@fluff.org>
- *
- * Default IO routines for S3C64XX based
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410-module.c b/arch/arm/mach-s3c64xx/mach-crag6410-module.c
index b6a67728cc88..0ace108c3e3d 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410-module.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410-module.c
@@ -17,6 +17,8 @@
 #include <linux/mfd/wm831x/gpio.h>
 #include <linux/mfd/wm8994/pdata.h>
 
+#include <linux/regulator/machine.h>
+
 #include <sound/wm5100.h>
 #include <sound/wm8996.h>
 #include <sound/wm8962.h>
@@ -153,6 +155,14 @@ static const struct i2c_board_info wm1259_devs[] = {
 	},
 };
 
+static struct regulator_init_data wm8994_ldo1 = {
+	.supply_regulator = "WALLVDD",
+};
+
+static struct regulator_init_data wm8994_ldo2 = {
+	.supply_regulator = "WALLVDD",
+};
+
 static struct wm8994_pdata wm8994_pdata = {
 	.gpio_base = CODEC_GPIO_BASE,
 	.gpio_defaults = {
@@ -160,8 +170,8 @@ static struct wm8994_pdata wm8994_pdata = {
 	},
 	.irq_base = CODEC_IRQ_BASE,
 	.ldo = {
-		{ .supply = "WALLVDD" },
-		{ .supply = "WALLVDD" },
+		 { .init_data = &wm8994_ldo1, },
+		 { .init_data = &wm8994_ldo2, },
 	},
 };
 
diff --git a/arch/arm/mach-s5p64x0/common.c b/arch/arm/mach-s5p64x0/common.c
index 9143f8b19962..6e6a0a9d6778 100644
--- a/arch/arm/mach-s5p64x0/common.c
+++ b/arch/arm/mach-s5p64x0/common.c
@@ -27,6 +27,7 @@
 
 #include <asm/irq.h>
 #include <asm/proc-fns.h>
+#include <asm/system_misc.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-s5p64x0/include/mach/io.h b/arch/arm/mach-s5p64x0/include/mach/io.h
deleted file mode 100644
index a3e095c02fb5..000000000000
--- a/arch/arm/mach-s5p64x0/include/mach/io.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* linux/arch/arm/mach-s5p64x0/include/mach/io.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben-linux@fluff.org>
- *
- * Default IO routines for S5P64X0 based
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif
diff --git a/arch/arm/mach-s5pc100/common.c b/arch/arm/mach-s5pc100/common.c
index ff71e2d467c6..621908658861 100644
--- a/arch/arm/mach-s5pc100/common.c
+++ b/arch/arm/mach-s5pc100/common.c
@@ -27,6 +27,7 @@
 
 #include <asm/irq.h>
 #include <asm/proc-fns.h>
+#include <asm/system_misc.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-s5pc100/include/mach/io.h b/arch/arm/mach-s5pc100/include/mach/io.h
deleted file mode 100644
index 819acf5eaf89..000000000000
--- a/arch/arm/mach-s5pc100/include/mach/io.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* arch/arm/mach-s5pc100/include/mach/io.h
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben-linux@fluff.org>
- *
- * Default IO routines for S5PC100 systems
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif
diff --git a/arch/arm/mach-s5pv210/include/mach/io.h b/arch/arm/mach-s5pv210/include/mach/io.h
deleted file mode 100644
index 5ab9d560bc86..000000000000
--- a/arch/arm/mach-s5pv210/include/mach/io.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* linux/arch/arm/mach-s5pv210/include/mach/io.h
- *
- * Copyright 2008-2010 Ben Dooks <ben-linux@fluff.org>
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Based on arch/arm/mach-s5p6442/include/mach/io.h
- *
- * Default IO routines for S5PV210
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H __FILE__
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif /* __ASM_ARM_ARCH_IO_H */
diff --git a/arch/arm/mach-sa1100/Makefile b/arch/arm/mach-sa1100/Makefile
index ed7408d3216c..60b97ec01676 100644
--- a/arch/arm/mach-sa1100/Makefile
+++ b/arch/arm/mach-sa1100/Makefile
@@ -3,7 +3,7 @@
 #
 
 # Common support
-obj-y := clock.o generic.o irq.o dma.o time.o #nmi-oopser.o
+obj-y := clock.o generic.o irq.o time.o #nmi-oopser.o
 obj-m :=
 obj-n :=
 obj-  :=
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index 0c4b76ab4d8e..375d3f779a88 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -15,14 +15,16 @@
 #include <linux/errno.h>
 #include <linux/ioport.h>
 #include <linux/serial_core.h>
+#include <linux/mfd/ucb1x00.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
 
+#include <video/sa1100fb.h>
+
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
@@ -36,17 +38,18 @@
 #include <asm/mach/serial_sa1100.h>
 #include <mach/assabet.h>
 #include <mach/mcp.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 
 #define ASSABET_BCR_DB1110 \
-	(ASSABET_BCR_SPK_OFF    | ASSABET_BCR_QMUTE     | \
+	(ASSABET_BCR_SPK_OFF    | \
 	 ASSABET_BCR_LED_GREEN  | ASSABET_BCR_LED_RED   | \
 	 ASSABET_BCR_RS232EN    | ASSABET_BCR_LCD_12RGB | \
 	 ASSABET_BCR_IRDA_MD0)
 
 #define ASSABET_BCR_DB1111 \
-	(ASSABET_BCR_SPK_OFF    | ASSABET_BCR_QMUTE     | \
+	(ASSABET_BCR_SPK_OFF    | \
 	 ASSABET_BCR_LED_GREEN  | ASSABET_BCR_LED_RED   | \
 	 ASSABET_BCR_RS232EN    | ASSABET_BCR_LCD_12RGB | \
 	 ASSABET_BCR_CF_BUS_OFF | ASSABET_BCR_STEREO_LB | \
@@ -69,31 +72,10 @@ void ASSABET_BCR_frob(unsigned int mask, unsigned int val)
 
 EXPORT_SYMBOL(ASSABET_BCR_frob);
 
-static void assabet_backlight_power(int on)
-{
-#ifndef ASSABET_PAL_VIDEO
-	if (on)
-		ASSABET_BCR_set(ASSABET_BCR_LIGHT_ON);
-	else
-#endif
-		ASSABET_BCR_clear(ASSABET_BCR_LIGHT_ON);
-}
-
-/*
- * Turn on/off the backlight.  When turning the backlight on,
- * we wait 500us after turning it on so we don't cause the
- * supplies to droop when we enable the LCD controller (and
- * cause a hard reset.)
- */
-static void assabet_lcd_power(int on)
+static void assabet_ucb1x00_reset(enum ucb1x00_reset state)
 {
-#ifndef ASSABET_PAL_VIDEO
-	if (on) {
-		ASSABET_BCR_set(ASSABET_BCR_LCD_ON);
-		udelay(500);
-	} else
-#endif
-		ASSABET_BCR_clear(ASSABET_BCR_LCD_ON);
+	if (state == UCB_RST_PROBE)
+		ASSABET_BCR_set(ASSABET_BCR_CODEC_RST);
 }
 
 
@@ -152,15 +134,8 @@ static struct flash_platform_data assabet_flash_data = {
 };
 
 static struct resource assabet_flash_resources[] = {
-	{
-		.start	= SA1100_CS0_PHYS,
-		.end	= SA1100_CS0_PHYS + SZ_32M - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= SA1100_CS1_PHYS,
-		.end	= SA1100_CS1_PHYS + SZ_32M - 1,
-		.flags	= IORESOURCE_MEM,
-	}
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_32M),
+	DEFINE_RES_MEM(SA1100_CS1_PHYS, SZ_32M),
 };
 
 
@@ -199,18 +174,126 @@ static struct irda_platform_data assabet_irda_data = {
 	.set_speed	= assabet_irda_set_speed,
 };
 
+static struct ucb1x00_plat_data assabet_ucb1x00_data = {
+	.reset		= assabet_ucb1x00_reset,
+	.gpio_base	= -1,
+};
+
 static struct mcp_plat_data assabet_mcp_data = {
 	.mccr0		= MCCR0_ADM,
 	.sclk_rate	= 11981000,
+	.codec_pdata	= &assabet_ucb1x00_data,
+};
+
+static void assabet_lcd_set_visual(u32 visual)
+{
+	u_int is_true_color = visual == FB_VISUAL_TRUECOLOR;
+
+	if (machine_is_assabet()) {
+#if 1		// phase 4 or newer Assabet's
+		if (is_true_color)
+			ASSABET_BCR_set(ASSABET_BCR_LCD_12RGB);
+		else
+			ASSABET_BCR_clear(ASSABET_BCR_LCD_12RGB);
+#else
+		// older Assabet's
+		if (is_true_color)
+			ASSABET_BCR_clear(ASSABET_BCR_LCD_12RGB);
+		else
+			ASSABET_BCR_set(ASSABET_BCR_LCD_12RGB);
+#endif
+	}
+}
+
+#ifndef ASSABET_PAL_VIDEO
+static void assabet_lcd_backlight_power(int on)
+{
+	if (on)
+		ASSABET_BCR_set(ASSABET_BCR_LIGHT_ON);
+	else
+		ASSABET_BCR_clear(ASSABET_BCR_LIGHT_ON);
+}
+
+/*
+ * Turn on/off the backlight.  When turning the backlight on, we wait
+ * 500us after turning it on so we don't cause the supplies to droop
+ * when we enable the LCD controller (and cause a hard reset.)
+ */
+static void assabet_lcd_power(int on)
+{
+	if (on) {
+		ASSABET_BCR_set(ASSABET_BCR_LCD_ON);
+		udelay(500);
+	} else
+		ASSABET_BCR_clear(ASSABET_BCR_LCD_ON);
+}
+
+/*
+ * The assabet uses a sharp LQ039Q2DS54 LCD module.  It is actually
+ * takes an RGB666 signal, but we provide it with an RGB565 signal
+ * instead (def_rgb_16).
+ */
+static struct sa1100fb_mach_info lq039q2ds54_info = {
+	.pixclock	= 171521,	.bpp		= 16,
+	.xres		= 320,		.yres		= 240,
+
+	.hsync_len	= 5,		.vsync_len	= 1,
+	.left_margin	= 61,		.upper_margin	= 3,
+	.right_margin	= 9,		.lower_margin	= 0,
+
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+
+	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
+	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
+
+	.backlight_power = assabet_lcd_backlight_power,
+	.lcd_power = assabet_lcd_power,
+	.set_visual = assabet_lcd_set_visual,
+};
+#else
+static void assabet_pal_backlight_power(int on)
+{
+	ASSABET_BCR_clear(ASSABET_BCR_LIGHT_ON);
+}
+
+static void assabet_pal_power(int on)
+{
+	ASSABET_BCR_clear(ASSABET_BCR_LCD_ON);
+}
+
+static struct sa1100fb_mach_info pal_info = {
+	.pixclock	= 67797,	.bpp		= 16,
+	.xres		= 640,		.yres		= 512,
+
+	.hsync_len	= 64,		.vsync_len	= 6,
+	.left_margin	= 125,		.upper_margin	= 70,
+	.right_margin	= 115,		.lower_margin	= 36,
+
+	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
+	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(512),
+
+	.backlight_power = assabet_pal_backlight_power,
+	.lcd_power = assabet_pal_power,
+	.set_visual = assabet_lcd_set_visual,
 };
+#endif
+
+#ifdef CONFIG_ASSABET_NEPONSET
+static struct resource neponset_resources[] = {
+	DEFINE_RES_MEM(0x10000000, 0x08000000),
+	DEFINE_RES_MEM(0x18000000, 0x04000000),
+	DEFINE_RES_MEM(0x40000000, SZ_8K),
+	DEFINE_RES_IRQ(IRQ_GPIO25),
+};
+#endif
 
 static void __init assabet_init(void)
 {
 	/*
 	 * Ensure that the power supply is in "high power" mode.
 	 */
-	GPDR |= GPIO_GPIO16;
 	GPSR = GPIO_GPIO16;
+	GPDR |= GPIO_GPIO16;
 
 	/*
 	 * Ensure that these pins are set as outputs and are driving
@@ -218,8 +301,16 @@ static void __init assabet_init(void)
 	 * the WS latch in the CPLD, and we don't float causing
 	 * excessive power drain.  --rmk
 	 */
-	GPDR |= GPIO_SSP_TXD | GPIO_SSP_SCLK | GPIO_SSP_SFRM;
 	GPCR = GPIO_SSP_TXD | GPIO_SSP_SCLK | GPIO_SSP_SFRM;
+	GPDR |= GPIO_SSP_TXD | GPIO_SSP_SCLK | GPIO_SSP_SFRM;
+
+	/*
+	 * Also set GPIO27 as an output; this is used to clock UART3
+	 * via the FPGA and as otherwise has no pullups or pulldowns,
+	 * so stop it floating.
+	 */
+	GPCR = GPIO_GPIO27;
+	GPDR |= GPIO_GPIO27;
 
 	/*
 	 * Set up registers for sleep mode.
@@ -231,8 +322,7 @@ static void __init assabet_init(void)
 	PPDR |= PPC_TXD3 | PPC_TXD1;
 	PPSR |= PPC_TXD3 | PPC_TXD1;
 
-	sa1100fb_lcd_power = assabet_lcd_power;
-	sa1100fb_backlight_power = assabet_backlight_power;
+	sa11x0_ppc_configure_mcp();
 
 	if (machine_has_neponset()) {
 		/*
@@ -246,9 +336,17 @@ static void __init assabet_init(void)
 #ifndef CONFIG_ASSABET_NEPONSET
 		printk( "Warning: Neponset detected but full support "
 			"hasn't been configured in the kernel\n" );
+#else
+		platform_device_register_simple("neponset", 0,
+			neponset_resources, ARRAY_SIZE(neponset_resources));
 #endif
 	}
 
+#ifndef ASSABET_PAL_VIDEO
+	sa11x0_register_lcd(&lq039q2ds54_info);
+#else
+	sa11x0_register_lcd(&pal_video);
+#endif
 	sa11x0_register_mtd(&assabet_flash_data, assabet_flash_resources,
 			    ARRAY_SIZE(assabet_flash_resources));
 	sa11x0_register_irda(&assabet_irda_data);
@@ -412,21 +510,8 @@ static void __init assabet_map_io(void)
 	 */
 	Ser1SDCR0 |= SDCR0_SUS;
 
-	if (machine_has_neponset()) {
-#ifdef CONFIG_ASSABET_NEPONSET
-		extern void neponset_map_io(void);
-
-		/*
-		 * We map Neponset registers even if it isn't present since
-		 * many drivers will try to probe their stuff (and fail).
-		 * This is still more friendly than a kernel paging request
-		 * crash.
-		 */
-		neponset_map_io();
-#endif
-	} else {
+	if (!machine_has_neponset())
 		sa1100_register_uart_fns(&assabet_port_fns);
-	}
 
 	/*
 	 * When Neponset is attached, the first UART should be
@@ -449,6 +534,7 @@ MACHINE_START(ASSABET, "Intel-Assabet")
 	.atag_offset	= 0x100,
 	.fixup		= fixup_assabet,
 	.map_io		= assabet_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= assabet_init,
diff --git a/arch/arm/mach-sa1100/badge4.c b/arch/arm/mach-sa1100/badge4.c
index b07a2c024cb7..e0f0c030258c 100644
--- a/arch/arm/mach-sa1100/badge4.c
+++ b/arch/arm/mach-sa1100/badge4.c
@@ -39,20 +39,27 @@
 #include "generic.h"
 
 static struct resource sa1111_resources[] = {
-	[0] = {
-		.start		= BADGE4_SA1111_BASE,
-		.end		= BADGE4_SA1111_BASE + 0x00001fff,
-		.flags		= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start		= BADGE4_IRQ_GPIO_SA1111,
-		.end		= BADGE4_IRQ_GPIO_SA1111,
-		.flags		= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(BADGE4_SA1111_BASE, 0x2000),
+	[1] = DEFINE_RES_IRQ(BADGE4_IRQ_GPIO_SA1111),
 };
 
+static int badge4_sa1111_enable(void *data, unsigned devid)
+{
+	if (devid == SA1111_DEVID_USB)
+		badge4_set_5V(BADGE4_5V_USB, 1);
+	return 0;
+}
+
+static void badge4_sa1111_disable(void *data, unsigned devid)
+{
+	if (devid == SA1111_DEVID_USB)
+		badge4_set_5V(BADGE4_5V_USB, 0);
+}
+
 static struct sa1111_platform_data sa1111_info = {
-	.irq_base	= IRQ_BOARD_END,
+	.disable_devs	= SA1111_DEVID_PS2_MSE,
+	.enable		= badge4_sa1111_enable,
+	.disable	= badge4_sa1111_disable,
 };
 
 static u64 sa1111_dmamask = 0xffffffffUL;
@@ -121,11 +128,8 @@ static struct flash_platform_data badge4_flash_data = {
 	.nr_parts	= ARRAY_SIZE(badge4_partitions),
 };
 
-static struct resource badge4_flash_resource = {
-	.start		= SA1100_CS0_PHYS,
-	.end		= SA1100_CS0_PHYS + SZ_64M - 1,
-	.flags		= IORESOURCE_MEM,
-};
+static struct resource badge4_flash_resource =
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_64M);
 
 static int five_v_on __initdata = 0;
 
@@ -269,11 +273,6 @@ static struct map_desc badge4_io_desc[] __initdata = {
 		.pfn		= __phys_to_pfn(0x10000000),
 		.length		= 0x00100000,
 		.type		= MT_DEVICE
-	}, {	/* SA-1111      */
-		.virtual	= 0xf4000000,
-		.pfn		= __phys_to_pfn(0x48000000),
-		.length		= 0x00100000,
-		.type		= MT_DEVICE
 	}
 };
 
@@ -304,6 +303,7 @@ static void __init badge4_map_io(void)
 MACHINE_START(BADGE4, "Hewlett-Packard Laboratories BadgePAD 4")
 	.atag_offset	= 0x100,
 	.map_io		= badge4_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 #ifdef CONFIG_SA1111
diff --git a/arch/arm/mach-sa1100/cerf.c b/arch/arm/mach-sa1100/cerf.c
index 11bb6d0b9be3..4a61f60e0502 100644
--- a/arch/arm/mach-sa1100/cerf.c
+++ b/arch/arm/mach-sa1100/cerf.c
@@ -18,7 +18,6 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 
-#include <asm/irq.h>
 #include <mach/hardware.h>
 #include <asm/setup.h>
 
@@ -30,14 +29,11 @@
 
 #include <mach/cerf.h>
 #include <mach/mcp.h>
+#include <mach/irqs.h>
 #include "generic.h"
 
 static struct resource cerfuart2_resources[] = {
-	[0] = {
-		.start	= 0x80030000,
-		.end	= 0x8003ffff,
-		.flags	= IORESOURCE_MEM,
-	},
+	[0] = DEFINE_RES_MEM(0x80030000, SZ_64K),
 };
 
 static struct platform_device cerfuart2_device = {
@@ -87,11 +83,8 @@ static struct flash_platform_data cerf_flash_data = {
 	.nr_parts	= ARRAY_SIZE(cerf_partitions),
 };
 
-static struct resource cerf_flash_resource = {
-	.start		= SA1100_CS0_PHYS,
-	.end		= SA1100_CS0_PHYS + SZ_32M - 1,
-	.flags		= IORESOURCE_MEM,
-};
+static struct resource cerf_flash_resource =
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_32M);
 
 static void __init cerf_init_irq(void)
 {
@@ -128,6 +121,7 @@ static struct mcp_plat_data cerf_mcp_data = {
 
 static void __init cerf_init(void)
 {
+	sa11x0_ppc_configure_mcp();
 	platform_add_devices(cerf_devices, ARRAY_SIZE(cerf_devices));
 	sa11x0_register_mtd(&cerf_flash_data, &cerf_flash_resource, 1);
 	sa11x0_register_mcp(&cerf_mcp_data);
@@ -136,6 +130,7 @@ static void __init cerf_init(void)
 MACHINE_START(CERF, "Intrinsyc CerfBoard/CerfCube")
 	/* Maintainer: support@intrinsyc.com */
 	.map_io		= cerf_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= cerf_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= cerf_init,
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index fd5652118ed1..c7f418b0cde9 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -22,15 +22,17 @@
 #include <linux/tty.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
+#include <linux/mfd/ucb1x00.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/timer.h>
 #include <linux/gpio.h>
 #include <linux/pda_power.h>
 
+#include <video/sa1100fb.h>
+
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/irq.h>
 #include <asm/page.h>
 #include <asm/setup.h>
 #include <mach/collie.h>
@@ -44,15 +46,12 @@
 #include <asm/mach/sharpsl_param.h>
 #include <asm/hardware/locomo.h>
 #include <mach/mcp.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 
 static struct resource collie_scoop_resources[] = {
-	[0] = {
-		.start		= 0x40800000,
-		.end		= 0x40800fff,
-		.flags		= IORESOURCE_MEM,
-	},
+	[0] = DEFINE_RES_MEM(0x40800000, SZ_4K),
 };
 
 static struct scoop_config collie_scoop_setup = {
@@ -85,10 +84,14 @@ static struct scoop_pcmcia_config collie_pcmcia_config = {
 	.num_devs	= 1,
 };
 
+static struct ucb1x00_plat_data collie_ucb1x00_data = {
+	.gpio_base	= COLLIE_TC35143_GPIO_BASE,
+};
+
 static struct mcp_plat_data collie_mcp_data = {
 	.mccr0		= MCCR0_ADM | MCCR0_ExtClk,
 	.sclk_rate	= 9216000,
-	.gpio_base	= COLLIE_TC35143_GPIO_BASE,
+	.codec_pdata	= &collie_ucb1x00_data,
 };
 
 /*
@@ -221,16 +224,8 @@ device_initcall(collie_uart_init);
 
 
 static struct resource locomo_resources[] = {
-	[0] = {
-		.start		= 0x40000000,
-		.end		= 0x40001fff,
-		.flags		= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start		= IRQ_GPIO25,
-		.end		= IRQ_GPIO25,
-		.flags		= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(0x40000000, SZ_8K),
+	[1] = DEFINE_RES_IRQ(IRQ_GPIO25),
 };
 
 static struct locomo_platform_data locomo_info = {
@@ -303,11 +298,25 @@ static struct flash_platform_data collie_flash_data = {
 };
 
 static struct resource collie_flash_resources[] = {
-	{
-		.start	= SA1100_CS0_PHYS,
-		.end	= SA1100_CS0_PHYS + SZ_32M - 1,
-		.flags	= IORESOURCE_MEM,
-	}
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_32M),
+};
+
+static struct sa1100fb_mach_info collie_lcd_info = {
+	.pixclock	= 171521,	.bpp		= 16,
+	.xres		= 320,		.yres		= 240,
+
+	.hsync_len	= 5,		.vsync_len	= 1,
+	.left_margin	= 11,		.upper_margin	= 2,
+	.right_margin	= 30,		.lower_margin	= 0,
+
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+
+	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
+	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
+
+#ifdef CONFIG_BACKLIGHT_LOCOMO
+	.lcd_power	= locomolcd_power
+#endif
 };
 
 static void __init collie_init(void)
@@ -341,6 +350,10 @@ static void __init collie_init(void)
 
 	collie_power_resource[0].start = gpio_to_irq(COLLIE_GPIO_AC_IN);
 	collie_power_resource[0].end = gpio_to_irq(COLLIE_GPIO_AC_IN);
+
+	sa11x0_ppc_configure_mcp();
+
+
 	platform_scoop_config = &collie_pcmcia_config;
 
 	ret = platform_add_devices(devices, ARRAY_SIZE(devices));
@@ -348,6 +361,7 @@ static void __init collie_init(void)
 		printk(KERN_WARNING "collie: Unable to register LoCoMo device\n");
 	}
 
+	sa11x0_register_lcd(&collie_lcd_info);
 	sa11x0_register_mtd(&collie_flash_data, collie_flash_resources,
 			    ARRAY_SIZE(collie_flash_resources));
 	sa11x0_register_mcp(&collie_mcp_data);
@@ -383,6 +397,7 @@ static void __init collie_map_io(void)
 
 MACHINE_START(COLLIE, "Sharp-Collie")
 	.map_io		= collie_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= collie_init,
diff --git a/arch/arm/mach-sa1100/dma.c b/arch/arm/mach-sa1100/dma.c
deleted file mode 100644
index ad660350c296..000000000000
--- a/arch/arm/mach-sa1100/dma.c
+++ /dev/null
@@ -1,348 +0,0 @@
-/*
- * arch/arm/mach-sa1100/dma.c
- *
- * Support functions for the SA11x0 internal DMA channels.
- *
- * Copyright (C) 2000, 2001 by Nicolas Pitre
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/errno.h>
-
-#include <asm/system.h>
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <mach/dma.h>
-
-
-#undef DEBUG
-#ifdef DEBUG
-#define DPRINTK( s, arg... )  printk( "dma<%p>: " s, regs , ##arg )
-#else
-#define DPRINTK( x... )
-#endif
-
-
-typedef struct {
-	const char *device_id;		/* device name */
-	u_long device;			/* this channel device, 0  if unused*/
-	dma_callback_t callback;	/* to call when DMA completes */
-	void *data;			/* ... with private data ptr */
-} sa1100_dma_t;
-
-static sa1100_dma_t dma_chan[SA1100_DMA_CHANNELS];
-
-static DEFINE_SPINLOCK(dma_list_lock);
-
-
-static irqreturn_t dma_irq_handler(int irq, void *dev_id)
-{
-	dma_regs_t *dma_regs = dev_id;
-	sa1100_dma_t *dma = dma_chan + (((u_int)dma_regs >> 5) & 7);
-	int status = dma_regs->RdDCSR;
-
-	if (status & (DCSR_ERROR)) {
-		printk(KERN_CRIT "DMA on \"%s\" caused an error\n", dma->device_id);
-		dma_regs->ClrDCSR = DCSR_ERROR;
-	}
-
-	dma_regs->ClrDCSR = status & (DCSR_DONEA | DCSR_DONEB);
-	if (dma->callback) {
-		if (status & DCSR_DONEA)
-			dma->callback(dma->data);
-		if (status & DCSR_DONEB)
-			dma->callback(dma->data);
-	}
-	return IRQ_HANDLED;
-}
-
-
-/**
- *	sa1100_request_dma - allocate one of the SA11x0's DMA channels
- *	@device: The SA11x0 peripheral targeted by this request
- *	@device_id: An ascii name for the claiming device
- *	@callback: Function to be called when the DMA completes
- *	@data: A cookie passed back to the callback function
- *	@dma_regs: Pointer to the location of the allocated channel's identifier
- *
- * 	This function will search for a free DMA channel and returns the
- * 	address of the hardware registers for that channel as the channel
- * 	identifier. This identifier is written to the location pointed by
- * 	@dma_regs. The list of possible values for @device are listed into
- * 	arch/arm/mach-sa1100/include/mach/dma.h as a dma_device_t enum.
- *
- * 	Note that reading from a port and writing to the same port are
- * 	actually considered as two different streams requiring separate
- * 	DMA registrations.
- *
- * 	The @callback function is called from interrupt context when one
- * 	of the two possible DMA buffers in flight has terminated. That
- * 	function has to be small and efficient while posponing more complex
- * 	processing to a lower priority execution context.
- *
- * 	If no channels are available, or if the desired @device is already in
- * 	use by another DMA channel, then an error code is returned.  This
- * 	function must be called before any other DMA calls.
- **/
-
-int sa1100_request_dma (dma_device_t device, const char *device_id,
-			dma_callback_t callback, void *data,
-			dma_regs_t **dma_regs)
-{
-	sa1100_dma_t *dma = NULL;
-	dma_regs_t *regs;
-	int i, err;
-
-	*dma_regs = NULL;
-
-	err = 0;
-	spin_lock(&dma_list_lock);
-	for (i = 0; i < SA1100_DMA_CHANNELS; i++) {
-		if (dma_chan[i].device == device) {
-			err = -EBUSY;
-			break;
-		} else if (!dma_chan[i].device && !dma) {
-			dma = &dma_chan[i];
-		}
-	}
-	if (!err) {
-		if (dma)
-			dma->device = device;
-		else
-			err = -ENOSR;
-	}
-	spin_unlock(&dma_list_lock);
-	if (err)
-		return err;
-
-	i = dma - dma_chan;
-	regs = (dma_regs_t *)&DDAR(i);
-	err = request_irq(IRQ_DMA0 + i, dma_irq_handler, IRQF_DISABLED,
-			  device_id, regs);
-	if (err) {
-		printk(KERN_ERR
-		       "%s: unable to request IRQ %d for %s\n",
-		       __func__, IRQ_DMA0 + i, device_id);
-		dma->device = 0;
-		return err;
-	}
-
-	*dma_regs = regs;
-	dma->device_id = device_id;
-	dma->callback = callback;
-	dma->data = data;
-
-	regs->ClrDCSR =
-		(DCSR_DONEA | DCSR_DONEB | DCSR_STRTA | DCSR_STRTB |
-		 DCSR_IE | DCSR_ERROR | DCSR_RUN);
-	regs->DDAR = device;
-
-	return 0;
-}
-
-
-/**
- * 	sa1100_free_dma - free a SA11x0 DMA channel
- * 	@regs: identifier for the channel to free
- *
- * 	This clears all activities on a given DMA channel and releases it
- * 	for future requests.  The @regs identifier is provided by a
- * 	successful call to sa1100_request_dma().
- **/
-
-void sa1100_free_dma(dma_regs_t *regs)
-{
-	int i;
-
-	for (i = 0; i < SA1100_DMA_CHANNELS; i++)
-		if (regs == (dma_regs_t *)&DDAR(i))
-			break;
-	if (i >= SA1100_DMA_CHANNELS) {
-		printk(KERN_ERR "%s: bad DMA identifier\n", __func__);
-		return;
-	}
-
-	if (!dma_chan[i].device) {
-		printk(KERN_ERR "%s: Trying to free free DMA\n", __func__);
-		return;
-	}
-
-	regs->ClrDCSR =
-		(DCSR_DONEA | DCSR_DONEB | DCSR_STRTA | DCSR_STRTB |
-		 DCSR_IE | DCSR_ERROR | DCSR_RUN);
-	free_irq(IRQ_DMA0 + i, regs);
-	dma_chan[i].device = 0;
-}
-
-
-/**
- * 	sa1100_start_dma - submit a data buffer for DMA
- * 	@regs: identifier for the channel to use
- * 	@dma_ptr: buffer physical (or bus) start address
- * 	@size: buffer size
- *
- * 	This function hands the given data buffer to the hardware for DMA
- * 	access. If another buffer is already in flight then this buffer
- * 	will be queued so the DMA engine will switch to it automatically
- * 	when the previous one is done.  The DMA engine is actually toggling
- * 	between two buffers so at most 2 successful calls can be made before
- * 	one of them terminates and the callback function is called.
- *
- * 	The @regs identifier is provided by a successful call to
- * 	sa1100_request_dma().
- *
- * 	The @size must not be larger than %MAX_DMA_SIZE.  If a given buffer
- * 	is larger than that then it's the caller's responsibility to split
- * 	it into smaller chunks and submit them separately. If this is the
- * 	case then a @size of %CUT_DMA_SIZE is recommended to avoid ending
- * 	up with too small chunks. The callback function can be used to chain
- * 	submissions of buffer chunks.
- *
- * 	Error return values:
- * 	%-EOVERFLOW:	Given buffer size is too big.
- * 	%-EBUSY:	Both DMA buffers are already in use.
- * 	%-EAGAIN:	Both buffers were busy but one of them just completed
- * 			but the interrupt handler has to execute first.
- *
- * 	This function returs 0 on success.
- **/
-
-int sa1100_start_dma(dma_regs_t *regs, dma_addr_t dma_ptr, u_int size)
-{
-	unsigned long flags;
-	u_long status;
-	int ret;
-
-	if (dma_ptr & 3)
-		printk(KERN_WARNING "DMA: unaligned start address (0x%08lx)\n",
-		       (unsigned long)dma_ptr);
-
-	if (size > MAX_DMA_SIZE)
-		return -EOVERFLOW;
-
-	local_irq_save(flags);
-	status = regs->RdDCSR;
-
-	/* If both DMA buffers are started, there's nothing else we can do. */
-	if ((status & (DCSR_STRTA | DCSR_STRTB)) == (DCSR_STRTA | DCSR_STRTB)) {
-		DPRINTK("start: st %#x busy\n", status);
-		ret = -EBUSY;
-		goto out;
-	}
-
-	if (((status & DCSR_BIU) && (status & DCSR_STRTB)) ||
-	    (!(status & DCSR_BIU) && !(status & DCSR_STRTA))) {
-		if (status & DCSR_DONEA) {
-			/* give a chance for the interrupt to be processed */
-			ret = -EAGAIN;
-			goto out;
-		}
-		regs->DBSA = dma_ptr;
-		regs->DBTA = size;
-		regs->SetDCSR = DCSR_STRTA | DCSR_IE | DCSR_RUN;
-		DPRINTK("start a=%#x s=%d on A\n", dma_ptr, size);
-	} else {
-		if (status & DCSR_DONEB) {
-			/* give a chance for the interrupt to be processed */
-			ret = -EAGAIN;
-			goto out;
-		}
-		regs->DBSB = dma_ptr;
-		regs->DBTB = size;
-		regs->SetDCSR = DCSR_STRTB | DCSR_IE | DCSR_RUN;
-		DPRINTK("start a=%#x s=%d on B\n", dma_ptr, size);
-	}
-	ret = 0;
-
-out:
-	local_irq_restore(flags);
-	return ret;
-}
-
-
-/**
- * 	sa1100_get_dma_pos - return current DMA position
- * 	@regs: identifier for the channel to use
- *
- * 	This function returns the current physical (or bus) address for the
- * 	given DMA channel.  If the channel is running i.e. not in a stopped
- * 	state then the caller must disable interrupts prior calling this
- * 	function and process the returned value before re-enabling them to
- * 	prevent races with the completion interrupt handler and the callback
- * 	function. The validation of the returned value is the caller's
- * 	responsibility as well -- the hardware seems to return out of range
- * 	values when the DMA engine completes a buffer.
- *
- * 	The @regs identifier is provided by a successful call to
- * 	sa1100_request_dma().
- **/
-
-dma_addr_t sa1100_get_dma_pos(dma_regs_t *regs)
-{
-	int status;
-
-	/*
-	 * We must determine whether buffer A or B is active.
-	 * Two possibilities: either we are in the middle of
-	 * a buffer, or the DMA controller just switched to the
-	 * next toggle but the interrupt hasn't been serviced yet.
-	 * The former case is straight forward.  In the later case,
-	 * we'll do like if DMA is just at the end of the previous
-	 * toggle since all registers haven't been reset yet.
-	 * This goes around the edge case and since we're always
-	 * a little behind anyways it shouldn't make a big difference.
-	 * If DMA has been stopped prior calling this then the
-	 * position is exact.
-	 */
-	status = regs->RdDCSR;
-	if ((!(status & DCSR_BIU) &&  (status & DCSR_STRTA)) ||
-	    ( (status & DCSR_BIU) && !(status & DCSR_STRTB)))
-		return regs->DBSA;
-	else
-		return regs->DBSB;
-}
-
-
-/**
- * 	sa1100_reset_dma - reset a DMA channel
- * 	@regs: identifier for the channel to use
- *
- * 	This function resets and reconfigure the given DMA channel. This is
- * 	particularly useful after a sleep/wakeup event.
- *
- * 	The @regs identifier is provided by a successful call to
- * 	sa1100_request_dma().
- **/
-
-void sa1100_reset_dma(dma_regs_t *regs)
-{
-	int i;
-
-	for (i = 0; i < SA1100_DMA_CHANNELS; i++)
-		if (regs == (dma_regs_t *)&DDAR(i))
-			break;
-	if (i >= SA1100_DMA_CHANNELS) {
-		printk(KERN_ERR "%s: bad DMA identifier\n", __func__);
-		return;
-	}
-
-	regs->ClrDCSR =
-		(DCSR_DONEA | DCSR_DONEB | DCSR_STRTA | DCSR_STRTB |
-		 DCSR_IE | DCSR_ERROR | DCSR_RUN);
-	regs->DDAR = dma_chan[i].device;
-}
-
-
-EXPORT_SYMBOL(sa1100_request_dma);
-EXPORT_SYMBOL(sa1100_free_dma);
-EXPORT_SYMBOL(sa1100_start_dma);
-EXPORT_SYMBOL(sa1100_get_dma_pos);
-EXPORT_SYMBOL(sa1100_reset_dma);
-
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index 7c1ebf4a7920..7c524b4e415d 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -14,17 +14,22 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/pm.h>
 #include <linux/cpufreq.h>
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
 
+#include <video/sa1100fb.h>
+
 #include <asm/div64.h>
-#include <mach/hardware.h>
-#include <asm/system.h>
 #include <asm/mach/map.h>
 #include <asm/mach/flash.h>
 #include <asm/irq.h>
+#include <asm/system_misc.h>
+
+#include <mach/hardware.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 
@@ -149,16 +154,8 @@ static void sa11x0_register_device(struct platform_device *dev, void *data)
 
 
 static struct resource sa11x0udc_resources[] = {
-	[0] = {
-		.start	= __PREG(Ser0UDCCR),
-		.end	= __PREG(Ser0UDCCR) + 0xffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_Ser0UDC,
-		.end	= IRQ_Ser0UDC,
-		.flags	= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(__PREG(Ser0UDCCR), SZ_64K),
+	[1] = DEFINE_RES_IRQ(IRQ_Ser0UDC),
 };
 
 static u64 sa11x0udc_dma_mask = 0xffffffffUL;
@@ -175,16 +172,8 @@ static struct platform_device sa11x0udc_device = {
 };
 
 static struct resource sa11x0uart1_resources[] = {
-	[0] = {
-		.start	= __PREG(Ser1UTCR0),
-		.end	= __PREG(Ser1UTCR0) + 0xffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_Ser1UART,
-		.end	= IRQ_Ser1UART,
-		.flags	= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(__PREG(Ser1UTCR0), SZ_64K),
+	[1] = DEFINE_RES_IRQ(IRQ_Ser1UART),
 };
 
 static struct platform_device sa11x0uart1_device = {
@@ -195,16 +184,8 @@ static struct platform_device sa11x0uart1_device = {
 };
 
 static struct resource sa11x0uart3_resources[] = {
-	[0] = {
-		.start	= __PREG(Ser3UTCR0),
-		.end	= __PREG(Ser3UTCR0) + 0xffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_Ser3UART,
-		.end	= IRQ_Ser3UART,
-		.flags	= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(__PREG(Ser3UTCR0), SZ_64K),
+	[1] = DEFINE_RES_IRQ(IRQ_Ser3UART),
 };
 
 static struct platform_device sa11x0uart3_device = {
@@ -215,16 +196,9 @@ static struct platform_device sa11x0uart3_device = {
 };
 
 static struct resource sa11x0mcp_resources[] = {
-	[0] = {
-		.start	= __PREG(Ser4MCCR0),
-		.end	= __PREG(Ser4MCCR0) + 0xffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_Ser4MCP,
-		.end	= IRQ_Ser4MCP,
-		.flags	= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(__PREG(Ser4MCCR0), SZ_64K),
+	[1] = DEFINE_RES_MEM(__PREG(Ser4MCCR1), 4),
+	[2] = DEFINE_RES_IRQ(IRQ_Ser4MCP),
 };
 
 static u64 sa11x0mcp_dma_mask = 0xffffffffUL;
@@ -240,22 +214,24 @@ static struct platform_device sa11x0mcp_device = {
 	.resource	= sa11x0mcp_resources,
 };
 
+void __init sa11x0_ppc_configure_mcp(void)
+{
+	/* Setup the PPC unit for the MCP */
+	PPDR &= ~PPC_RXD4;
+	PPDR |= PPC_TXD4 | PPC_SCLK | PPC_SFRM;
+	PSDR |= PPC_RXD4;
+	PSDR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
+	PPSR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
+}
+
 void sa11x0_register_mcp(struct mcp_plat_data *data)
 {
 	sa11x0_register_device(&sa11x0mcp_device, data);
 }
 
 static struct resource sa11x0ssp_resources[] = {
-	[0] = {
-		.start	= 0x80070000,
-		.end	= 0x8007ffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_Ser4SSP,
-		.end	= IRQ_Ser4SSP,
-		.flags	= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(0x80070000, SZ_64K),
+	[1] = DEFINE_RES_IRQ(IRQ_Ser4SSP),
 };
 
 static u64 sa11x0ssp_dma_mask = 0xffffffffUL;
@@ -272,16 +248,8 @@ static struct platform_device sa11x0ssp_device = {
 };
 
 static struct resource sa11x0fb_resources[] = {
-	[0] = {
-		.start	= 0xb0100000,
-		.end	= 0xb010ffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_LCD,
-		.end	= IRQ_LCD,
-		.flags	= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(0xb0100000, SZ_64K),
+	[1] = DEFINE_RES_IRQ(IRQ_LCD),
 };
 
 static struct platform_device sa11x0fb_device = {
@@ -294,6 +262,11 @@ static struct platform_device sa11x0fb_device = {
 	.resource	= sa11x0fb_resources,
 };
 
+void sa11x0_register_lcd(struct sa1100fb_mach_info *inf)
+{
+	sa11x0_register_device(&sa11x0fb_device, inf);
+}
+
 static struct platform_device sa11x0pcmcia_device = {
 	.name		= "sa11x0-pcmcia",
 	.id		= -1,
@@ -314,23 +287,10 @@ void sa11x0_register_mtd(struct flash_platform_data *flash,
 }
 
 static struct resource sa11x0ir_resources[] = {
-	{
-		.start	= __PREG(Ser2UTCR0),
-		.end	= __PREG(Ser2UTCR0) + 0x24 - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= __PREG(Ser2HSCR0),
-		.end	= __PREG(Ser2HSCR0) + 0x1c - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= __PREG(Ser2HSCR2),
-		.end	= __PREG(Ser2HSCR2) + 0x04 - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= IRQ_Ser2ICP,
-		.end	= IRQ_Ser2ICP,
-		.flags	= IORESOURCE_IRQ,
-	}
+	DEFINE_RES_MEM(__PREG(Ser2UTCR0), 0x24),
+	DEFINE_RES_MEM(__PREG(Ser2HSCR0), 0x1c),
+	DEFINE_RES_MEM(__PREG(Ser2HSCR2), 0x04),
+	DEFINE_RES_IRQ(IRQ_Ser2ICP),
 };
 
 static struct platform_device sa11x0ir_device = {
@@ -358,14 +318,37 @@ static struct platform_device sa11x0rtc_device = {
 	.resource	= sa1100_rtc_resources,
 };
 
+static struct resource sa11x0dma_resources[] = {
+	DEFINE_RES_MEM(DMA_PHYS, DMA_SIZE),
+	DEFINE_RES_IRQ(IRQ_DMA0),
+	DEFINE_RES_IRQ(IRQ_DMA1),
+	DEFINE_RES_IRQ(IRQ_DMA2),
+	DEFINE_RES_IRQ(IRQ_DMA3),
+	DEFINE_RES_IRQ(IRQ_DMA4),
+	DEFINE_RES_IRQ(IRQ_DMA5),
+};
+
+static u64 sa11x0dma_dma_mask = DMA_BIT_MASK(32);
+
+static struct platform_device sa11x0dma_device = {
+	.name		= "sa11x0-dma",
+	.id		= -1,
+	.dev = {
+		.dma_mask = &sa11x0dma_dma_mask,
+		.coherent_dma_mask = 0xffffffff,
+	},
+	.num_resources	= ARRAY_SIZE(sa11x0dma_resources),
+	.resource	= sa11x0dma_resources,
+};
+
 static struct platform_device *sa11x0_devices[] __initdata = {
 	&sa11x0udc_device,
 	&sa11x0uart1_device,
 	&sa11x0uart3_device,
 	&sa11x0ssp_device,
 	&sa11x0pcmcia_device,
-	&sa11x0fb_device,
 	&sa11x0rtc_device,
+	&sa11x0dma_device,
 };
 
 static int __init sa1100_init(void)
@@ -376,12 +359,6 @@ static int __init sa1100_init(void)
 
 arch_initcall(sa1100_init);
 
-void (*sa1100fb_backlight_power)(int on);
-void (*sa1100fb_lcd_power)(int on);
-
-EXPORT_SYMBOL(sa1100fb_backlight_power);
-EXPORT_SYMBOL(sa1100fb_lcd_power);
-
 
 /*
  * Common I/O mapping:
@@ -436,7 +413,7 @@ void __init sa1100_map_io(void)
  * the MBGNT signal false to ensure the SA1111 doesn't own the
  * SDRAM bus.
  */
-void __init sa1110_mb_disable(void)
+void sa1110_mb_disable(void)
 {
 	unsigned long flags;
 
@@ -455,7 +432,7 @@ void __init sa1110_mb_disable(void)
  * If the system is going to use the SA-1111 DMA engines, set up
  * the memory bus request/grant pins.
  */
-void __devinit sa1110_mb_enable(void)
+void sa1110_mb_enable(void)
 {
 	unsigned long flags;
 
diff --git a/arch/arm/mach-sa1100/generic.h b/arch/arm/mach-sa1100/generic.h
index 33268cf6be36..9eb3b3cd5a63 100644
--- a/arch/arm/mach-sa1100/generic.h
+++ b/arch/arm/mach-sa1100/generic.h
@@ -16,9 +16,6 @@ extern void sa11x0_restart(char, const char *);
 	mi->bank[__nr].start = (__start), \
 	mi->bank[__nr].size = (__size)
 
-extern void (*sa1100fb_backlight_power)(int on);
-extern void (*sa1100fb_lcd_power)(int on);
-
 extern void sa1110_mb_enable(void);
 extern void sa1110_mb_disable(void);
 
@@ -39,4 +36,8 @@ struct irda_platform_data;
 void sa11x0_register_irda(struct irda_platform_data *irda);
 
 struct mcp_plat_data;
+void sa11x0_ppc_configure_mcp(void);
 void sa11x0_register_mcp(struct mcp_plat_data *data);
+
+struct sa1100fb_mach_info;
+void sa11x0_register_lcd(struct sa1100fb_mach_info *inf);
diff --git a/arch/arm/mach-sa1100/h3100.c b/arch/arm/mach-sa1100/h3100.c
index 1e6b3c105ba6..b2e8d0f418e0 100644
--- a/arch/arm/mach-sa1100/h3100.c
+++ b/arch/arm/mach-sa1100/h3100.c
@@ -14,11 +14,14 @@
 #include <linux/kernel.h>
 #include <linux/gpio.h>
 
+#include <video/sa1100fb.h>
+
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irda.h>
 
 #include <mach/h3xxx.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 
@@ -36,13 +39,28 @@ static void h3100_lcd_power(int enable)
 	}
 }
 
+static struct sa1100fb_mach_info h3100_lcd_info = {
+	.pixclock	= 406977, 	.bpp		= 4,
+	.xres		= 320,		.yres		= 240,
+
+	.hsync_len	= 26,		.vsync_len	= 41,
+	.left_margin	= 4,		.upper_margin	= 0,
+	.right_margin	= 4,		.lower_margin	= 0,
+
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+	.cmap_greyscale	= 1,
+	.cmap_inverse	= 1,
+
+	.lccr0		= LCCR0_Mono | LCCR0_4PixMono | LCCR0_Sngl | LCCR0_Pas,
+	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
+
+	.lcd_power = h3100_lcd_power,
+};
 
 static void __init h3100_map_io(void)
 {
 	h3xxx_map_io();
 
-	sa1100fb_lcd_power = h3100_lcd_power;
-
 	/* Older bootldrs put GPIO2-9 in alternate mode on the
 	   assumption that they are used for video */
 	GAFR &= ~0x000001fb;
@@ -80,12 +98,15 @@ static void __init h3100_mach_init(void)
 {
 	h3xxx_init_gpio(h3100_default_gpio, ARRAY_SIZE(h3100_default_gpio));
 	h3xxx_mach_init();
+
+	sa11x0_register_lcd(&h3100_lcd_info);
 	sa11x0_register_irda(&h3100_irda_data);
 }
 
 MACHINE_START(H3100, "Compaq iPAQ H3100")
 	.atag_offset	= 0x100,
 	.map_io		= h3100_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= h3100_mach_init,
diff --git a/arch/arm/mach-sa1100/h3600.c b/arch/arm/mach-sa1100/h3600.c
index 6b58e7460ecf..cb6659f294fe 100644
--- a/arch/arm/mach-sa1100/h3600.c
+++ b/arch/arm/mach-sa1100/h3600.c
@@ -14,11 +14,14 @@
 #include <linux/kernel.h>
 #include <linux/gpio.h>
 
+#include <video/sa1100fb.h>
+
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irda.h>
 
 #include <mach/h3xxx.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 
@@ -56,11 +59,35 @@ err2:	gpio_free(H3XXX_EGPIO_LCD_ON);
 err1:	return;
 }
 
+static const struct sa1100fb_rgb h3600_rgb_16 = {
+	.red	= { .offset = 12, .length = 4, },
+	.green	= { .offset = 7,  .length = 4, },
+	.blue	= { .offset = 1,  .length = 4, },
+	.transp	= { .offset = 0,  .length = 0, },
+};
+
+static struct sa1100fb_mach_info h3600_lcd_info = {
+	.pixclock	= 174757, 	.bpp		= 16,
+	.xres		= 320,		.yres		= 240,
+
+	.hsync_len	= 3,		.vsync_len	= 3,
+	.left_margin	= 12,		.upper_margin	= 10,
+	.right_margin	= 17,		.lower_margin	= 1,
+
+	.cmap_static	= 1,
+
+	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
+	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
+
+	.rgb[RGB_16] = &h3600_rgb_16,
+
+	.lcd_power = h3600_lcd_power,
+};
+
+
 static void __init h3600_map_io(void)
 {
 	h3xxx_map_io();
-
-	sa1100fb_lcd_power = h3600_lcd_power;
 }
 
 /*
@@ -121,12 +148,15 @@ static void __init h3600_mach_init(void)
 {
 	h3xxx_init_gpio(h3600_default_gpio, ARRAY_SIZE(h3600_default_gpio));
 	h3xxx_mach_init();
+
+	sa11x0_register_lcd(&h3600_lcd_info);
 	sa11x0_register_irda(&h3600_irda_data);
 }
 
 MACHINE_START(H3600, "Compaq iPAQ H3600")
 	.atag_offset	= 0x100,
 	.map_io		= h3600_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= h3600_mach_init,
diff --git a/arch/arm/mach-sa1100/h3xxx.c b/arch/arm/mach-sa1100/h3xxx.c
index b0784c974c2d..63150e1ffe9e 100644
--- a/arch/arm/mach-sa1100/h3xxx.c
+++ b/arch/arm/mach-sa1100/h3xxx.c
@@ -109,11 +109,8 @@ static struct flash_platform_data h3xxx_flash_data = {
 	.nr_parts	= ARRAY_SIZE(h3xxx_partitions),
 };
 
-static struct resource h3xxx_flash_resource = {
-	.start		= SA1100_CS0_PHYS,
-	.end		= SA1100_CS0_PHYS + SZ_32M - 1,
-	.flags		= IORESOURCE_MEM,
-};
+static struct resource h3xxx_flash_resource =
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_32M);
 
 
 /*
@@ -186,11 +183,7 @@ static struct sa1100_port_fns h3xxx_port_fns __initdata = {
  */
 
 static struct resource egpio_resources[] = {
-	[0] = {
-		.start	= H3600_EGPIO_PHYS,
-		.end	= H3600_EGPIO_PHYS + 0x4 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
+	[0] = DEFINE_RES_MEM(H3600_EGPIO_PHYS, 0x4),
 };
 
 static struct htc_egpio_chip egpio_chips[] = {
diff --git a/arch/arm/mach-sa1100/hackkit.c b/arch/arm/mach-sa1100/hackkit.c
index c01bb36db940..5535475bf583 100644
--- a/arch/arm/mach-sa1100/hackkit.c
+++ b/arch/arm/mach-sa1100/hackkit.c
@@ -22,12 +22,10 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 
-#include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/irq.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
@@ -35,6 +33,9 @@
 #include <asm/mach/irq.h>
 #include <asm/mach/serial_sa1100.h>
 
+#include <mach/hardware.h>
+#include <mach/irqs.h>
+
 #include "generic.h"
 
 /**********************************************************************
@@ -179,11 +180,8 @@ static struct flash_platform_data hackkit_flash_data = {
 	.nr_parts	= ARRAY_SIZE(hackkit_partitions),
 };
 
-static struct resource hackkit_flash_resource = {
-	.start		= SA1100_CS0_PHYS,
-	.end		= SA1100_CS0_PHYS + SZ_32M,
-	.flags		= IORESOURCE_MEM,
-};
+static struct resource hackkit_flash_resource =
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_32M);
 
 static void __init hackkit_init(void)
 {
@@ -197,6 +195,7 @@ static void __init hackkit_init(void)
 MACHINE_START(HACKKIT, "HackKit Cpu Board")
 	.atag_offset	= 0x100,
 	.map_io		= hackkit_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= hackkit_init,
diff --git a/arch/arm/mach-sa1100/include/mach/SA-1100.h b/arch/arm/mach-sa1100/include/mach/SA-1100.h
index bae8296f5dbf..3f2d1b60188c 100644
--- a/arch/arm/mach-sa1100/include/mach/SA-1100.h
+++ b/arch/arm/mach-sa1100/include/mach/SA-1100.h
@@ -1590,224 +1590,9 @@
 
 /*
  * Direct Memory Access (DMA) control registers
- *
- * Registers
- *    DDAR0     	Direct Memory Access (DMA) Device Address Register
- *              	channel 0 (read/write).
- *    DCSR0     	Direct Memory Access (DMA) Control and Status
- *              	Register channel 0 (read/write).
- *    DBSA0     	Direct Memory Access (DMA) Buffer Start address
- *              	register A channel 0 (read/write).
- *    DBTA0     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register A channel 0 (read/write).
- *    DBSB0     	Direct Memory Access (DMA) Buffer Start address
- *              	register B channel 0 (read/write).
- *    DBTB0     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register B channel 0 (read/write).
- *
- *    DDAR1     	Direct Memory Access (DMA) Device Address Register
- *              	channel 1 (read/write).
- *    DCSR1     	Direct Memory Access (DMA) Control and Status
- *              	Register channel 1 (read/write).
- *    DBSA1     	Direct Memory Access (DMA) Buffer Start address
- *              	register A channel 1 (read/write).
- *    DBTA1     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register A channel 1 (read/write).
- *    DBSB1     	Direct Memory Access (DMA) Buffer Start address
- *              	register B channel 1 (read/write).
- *    DBTB1     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register B channel 1 (read/write).
- *
- *    DDAR2     	Direct Memory Access (DMA) Device Address Register
- *              	channel 2 (read/write).
- *    DCSR2     	Direct Memory Access (DMA) Control and Status
- *              	Register channel 2 (read/write).
- *    DBSA2     	Direct Memory Access (DMA) Buffer Start address
- *              	register A channel 2 (read/write).
- *    DBTA2     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register A channel 2 (read/write).
- *    DBSB2     	Direct Memory Access (DMA) Buffer Start address
- *              	register B channel 2 (read/write).
- *    DBTB2     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register B channel 2 (read/write).
- *
- *    DDAR3     	Direct Memory Access (DMA) Device Address Register
- *              	channel 3 (read/write).
- *    DCSR3     	Direct Memory Access (DMA) Control and Status
- *              	Register channel 3 (read/write).
- *    DBSA3     	Direct Memory Access (DMA) Buffer Start address
- *              	register A channel 3 (read/write).
- *    DBTA3     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register A channel 3 (read/write).
- *    DBSB3     	Direct Memory Access (DMA) Buffer Start address
- *              	register B channel 3 (read/write).
- *    DBTB3     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register B channel 3 (read/write).
- *
- *    DDAR4     	Direct Memory Access (DMA) Device Address Register
- *              	channel 4 (read/write).
- *    DCSR4     	Direct Memory Access (DMA) Control and Status
- *              	Register channel 4 (read/write).
- *    DBSA4     	Direct Memory Access (DMA) Buffer Start address
- *              	register A channel 4 (read/write).
- *    DBTA4     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register A channel 4 (read/write).
- *    DBSB4     	Direct Memory Access (DMA) Buffer Start address
- *              	register B channel 4 (read/write).
- *    DBTB4     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register B channel 4 (read/write).
- *
- *    DDAR5     	Direct Memory Access (DMA) Device Address Register
- *              	channel 5 (read/write).
- *    DCSR5     	Direct Memory Access (DMA) Control and Status
- *              	Register channel 5 (read/write).
- *    DBSA5     	Direct Memory Access (DMA) Buffer Start address
- *              	register A channel 5 (read/write).
- *    DBTA5     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register A channel 5 (read/write).
- *    DBSB5     	Direct Memory Access (DMA) Buffer Start address
- *              	register B channel 5 (read/write).
- *    DBTB5     	Direct Memory Access (DMA) Buffer Transfer count
- *              	register B channel 5 (read/write).
  */
-
-#define DMASp   	0x00000020	/* DMA control reg. Space [byte]   */
-
-#define DDAR(Nb)	__REG(0xB0000000 + (Nb)*DMASp)  /* DMA Device Address Reg. channel [0..5] */
-#define SetDCSR(Nb)	__REG(0xB0000004 + (Nb)*DMASp)  /* Set DMA Control & Status Reg. channel [0..5] (write) */
-#define ClrDCSR(Nb)	__REG(0xB0000008 + (Nb)*DMASp)  /* Clear DMA Control & Status Reg. channel [0..5] (write) */
-#define RdDCSR(Nb)	__REG(0xB000000C + (Nb)*DMASp)  /* Read DMA Control & Status Reg. channel [0..5] (read) */
-#define DBSA(Nb)	__REG(0xB0000010 + (Nb)*DMASp)  /* DMA Buffer Start address reg. A channel [0..5] */
-#define DBTA(Nb)	__REG(0xB0000014 + (Nb)*DMASp)  /* DMA Buffer Transfer count reg. A channel [0..5] */
-#define DBSB(Nb)	__REG(0xB0000018 + (Nb)*DMASp)  /* DMA Buffer Start address reg. B channel [0..5] */
-#define DBTB(Nb)	__REG(0xB000001C + (Nb)*DMASp)  /* DMA Buffer Transfer count reg. B channel [0..5] */
-
-#define DDAR_RW 	0x00000001	/* device data Read/Write          */
-#define DDAR_DevWr	(DDAR_RW*0)	/*  Device data Write              */
-                	        	/*  (memory -> device)             */
-#define DDAR_DevRd	(DDAR_RW*1)	/*  Device data Read               */
-                	        	/*  (device -> memory)             */
-#define DDAR_E  	0x00000002	/* big/little Endian device        */
-#define DDAR_LtlEnd	(DDAR_E*0)	/*  Little Endian device           */
-#define DDAR_BigEnd	(DDAR_E*1)	/*  Big Endian device              */
-#define DDAR_BS 	0x00000004	/* device Burst Size               */
-#define DDAR_Brst4	(DDAR_BS*0)	/*  Burst-of-4 device              */
-#define DDAR_Brst8	(DDAR_BS*1)	/*  Burst-of-8 device              */
-#define DDAR_DW 	0x00000008	/* device Data Width               */
-#define DDAR_8BitDev	(DDAR_DW*0)	/*  8-Bit Device                   */
-#define DDAR_16BitDev	(DDAR_DW*1)	/*  16-Bit Device                  */
-#define DDAR_DS 	Fld (4, 4)	/* Device Select                   */
-#define DDAR_Ser0UDCTr	        	/*  Ser. port 0 UDC Transmit       */ \
-                	(0x0 << FShft (DDAR_DS))
-#define DDAR_Ser0UDCRc	        	/*  Ser. port 0 UDC Receive        */ \
-                	(0x1 << FShft (DDAR_DS))
-#define DDAR_Ser1SDLCTr	        	/*  Ser. port 1 SDLC Transmit      */ \
-                	(0x2 << FShft (DDAR_DS))
-#define DDAR_Ser1SDLCRc	        	/*  Ser. port 1 SDLC Receive       */ \
-                	(0x3 << FShft (DDAR_DS))
-#define DDAR_Ser1UARTTr	        	/*  Ser. port 1 UART Transmit      */ \
-                	(0x4 << FShft (DDAR_DS))
-#define DDAR_Ser1UARTRc	        	/*  Ser. port 1 UART Receive       */ \
-                	(0x5 << FShft (DDAR_DS))
-#define DDAR_Ser2ICPTr	        	/*  Ser. port 2 ICP Transmit       */ \
-                	(0x6 << FShft (DDAR_DS))
-#define DDAR_Ser2ICPRc	        	/*  Ser. port 2 ICP Receive        */ \
-                	(0x7 << FShft (DDAR_DS))
-#define DDAR_Ser3UARTTr	        	/*  Ser. port 3 UART Transmit      */ \
-                	(0x8 << FShft (DDAR_DS))
-#define DDAR_Ser3UARTRc	        	/*  Ser. port 3 UART Receive       */ \
-                	(0x9 << FShft (DDAR_DS))
-#define DDAR_Ser4MCP0Tr	        	/*  Ser. port 4 MCP 0 Transmit     */ \
-                	        	/*  (audio)                        */ \
-                	(0xA << FShft (DDAR_DS))
-#define DDAR_Ser4MCP0Rc	        	/*  Ser. port 4 MCP 0 Receive      */ \
-                	        	/*  (audio)                        */ \
-                	(0xB << FShft (DDAR_DS))
-#define DDAR_Ser4MCP1Tr	        	/*  Ser. port 4 MCP 1 Transmit     */ \
-                	        	/*  (telecom)                      */ \
-                	(0xC << FShft (DDAR_DS))
-#define DDAR_Ser4MCP1Rc	        	/*  Ser. port 4 MCP 1 Receive      */ \
-                	        	/*  (telecom)                      */ \
-                	(0xD << FShft (DDAR_DS))
-#define DDAR_Ser4SSPTr	        	/*  Ser. port 4 SSP Transmit       */ \
-                	(0xE << FShft (DDAR_DS))
-#define DDAR_Ser4SSPRc	        	/*  Ser. port 4 SSP Receive        */ \
-                	(0xF << FShft (DDAR_DS))
-#define DDAR_DA 	Fld (24, 8)	/* Device Address                  */
-#define DDAR_DevAdd(Add)        	/*  Device Address                 */ \
-                	(((Add) & 0xF0000000) | \
-                	 (((Add) & 0X003FFFFC) << (FShft (DDAR_DA) - 2)))
-#define DDAR_Ser0UDCWr	        	/* Ser. port 0 UDC Write           */ \
-                	(DDAR_DevWr + DDAR_Brst8 + DDAR_8BitDev + \
-                	 DDAR_Ser0UDCTr + DDAR_DevAdd (__PREG(Ser0UDCDR)))
-#define DDAR_Ser0UDCRd	        	/* Ser. port 0 UDC Read            */ \
-                	(DDAR_DevRd + DDAR_Brst8 + DDAR_8BitDev + \
-                	 DDAR_Ser0UDCRc + DDAR_DevAdd (__PREG(Ser0UDCDR)))
-#define DDAR_Ser1UARTWr	        	/* Ser. port 1 UART Write          */ \
-                	(DDAR_DevWr + DDAR_Brst4 + DDAR_8BitDev + \
-                	 DDAR_Ser1UARTTr + DDAR_DevAdd (__PREG(Ser1UTDR)))
-#define DDAR_Ser1UARTRd	        	/* Ser. port 1 UART Read           */ \
-                	(DDAR_DevRd + DDAR_Brst4 + DDAR_8BitDev + \
-                	 DDAR_Ser1UARTRc + DDAR_DevAdd (__PREG(Ser1UTDR)))
-#define DDAR_Ser1SDLCWr	        	/* Ser. port 1 SDLC Write          */ \
-                	(DDAR_DevWr + DDAR_Brst4 + DDAR_8BitDev + \
-                	 DDAR_Ser1SDLCTr + DDAR_DevAdd (__PREG(Ser1SDDR)))
-#define DDAR_Ser1SDLCRd	        	/* Ser. port 1 SDLC Read           */ \
-                	(DDAR_DevRd + DDAR_Brst4 + DDAR_8BitDev + \
-                	 DDAR_Ser1SDLCRc + DDAR_DevAdd (__PREG(Ser1SDDR)))
-#define DDAR_Ser2UARTWr	        	/* Ser. port 2 UART Write          */ \
-                	(DDAR_DevWr + DDAR_Brst4 + DDAR_8BitDev + \
-                	 DDAR_Ser2ICPTr + DDAR_DevAdd (__PREG(Ser2UTDR)))
-#define DDAR_Ser2UARTRd	        	/* Ser. port 2 UART Read           */ \
-                	(DDAR_DevRd + DDAR_Brst4 + DDAR_8BitDev + \
-                	 DDAR_Ser2ICPRc + DDAR_DevAdd (__PREG(Ser2UTDR)))
-#define DDAR_Ser2HSSPWr	        	/* Ser. port 2 HSSP Write          */ \
-                	(DDAR_DevWr + DDAR_Brst8 + DDAR_8BitDev + \
-                	 DDAR_Ser2ICPTr + DDAR_DevAdd (__PREG(Ser2HSDR)))
-#define DDAR_Ser2HSSPRd	        	/* Ser. port 2 HSSP Read           */ \
-                	(DDAR_DevRd + DDAR_Brst8 + DDAR_8BitDev + \
-                	 DDAR_Ser2ICPRc + DDAR_DevAdd (__PREG(Ser2HSDR)))
-#define DDAR_Ser3UARTWr	        	/* Ser. port 3 UART Write          */ \
-                	(DDAR_DevWr + DDAR_Brst4 + DDAR_8BitDev + \
-                	 DDAR_Ser3UARTTr + DDAR_DevAdd (__PREG(Ser3UTDR)))
-#define DDAR_Ser3UARTRd	        	/* Ser. port 3 UART Read           */ \
-                	(DDAR_DevRd + DDAR_Brst4 + DDAR_8BitDev + \
-                	 DDAR_Ser3UARTRc + DDAR_DevAdd (__PREG(Ser3UTDR)))
-#define DDAR_Ser4MCP0Wr	        	/* Ser. port 4 MCP 0 Write (audio) */ \
-                	(DDAR_DevWr + DDAR_Brst4 + DDAR_16BitDev + \
-                	 DDAR_Ser4MCP0Tr + DDAR_DevAdd (__PREG(Ser4MCDR0)))
-#define DDAR_Ser4MCP0Rd	        	/* Ser. port 4 MCP 0 Read (audio)  */ \
-                	(DDAR_DevRd + DDAR_Brst4 + DDAR_16BitDev + \
-                	 DDAR_Ser4MCP0Rc + DDAR_DevAdd (__PREG(Ser4MCDR0)))
-#define DDAR_Ser4MCP1Wr	        	/* Ser. port 4 MCP 1 Write         */ \
-                	        	/* (telecom)                       */ \
-                	(DDAR_DevWr + DDAR_Brst4 + DDAR_16BitDev + \
-                	 DDAR_Ser4MCP1Tr + DDAR_DevAdd (__PREG(Ser4MCDR1)))
-#define DDAR_Ser4MCP1Rd	        	/* Ser. port 4 MCP 1 Read          */ \
-                	        	/* (telecom)                       */ \
-                	(DDAR_DevRd + DDAR_Brst4 + DDAR_16BitDev + \
-                	 DDAR_Ser4MCP1Rc + DDAR_DevAdd (__PREG(Ser4MCDR1)))
-#define DDAR_Ser4SSPWr	        	/* Ser. port 4 SSP Write (16 bits) */ \
-                	(DDAR_DevWr + DDAR_Brst4 + DDAR_16BitDev + \
-                	 DDAR_Ser4SSPTr + DDAR_DevAdd (__PREG(Ser4SSDR)))
-#define DDAR_Ser4SSPRd	        	/* Ser. port 4 SSP Read (16 bits)  */ \
-                	(DDAR_DevRd + DDAR_Brst4 + DDAR_16BitDev + \
-                	 DDAR_Ser4SSPRc + DDAR_DevAdd (__PREG(Ser4SSDR)))
-
-#define DCSR_RUN	0x00000001	/* DMA running                     */
-#define DCSR_IE 	0x00000002	/* DMA Interrupt Enable            */
-#define DCSR_ERROR	0x00000004	/* DMA ERROR                       */
-#define DCSR_DONEA	0x00000008	/* DONE DMA transfer buffer A      */
-#define DCSR_STRTA	0x00000010	/* STaRTed DMA transfer buffer A   */
-#define DCSR_DONEB	0x00000020	/* DONE DMA transfer buffer B      */
-#define DCSR_STRTB	0x00000040	/* STaRTed DMA transfer buffer B   */
-#define DCSR_BIU	0x00000080	/* DMA Buffer In Use               */
-#define DCSR_BufA	(DCSR_BIU*0)	/*  DMA Buffer A in use            */
-#define DCSR_BufB	(DCSR_BIU*1)	/*  DMA Buffer B in use            */
-
-#define DBT_TC  	Fld (13, 0)	/* Transfer Count                  */
-#define DBTA_TCA	DBT_TC  	/* Transfer Count buffer A         */
-#define DBTB_TCB	DBT_TC  	/* Transfer Count buffer B         */
+#define DMA_SIZE	(6 * 0x20)
+#define DMA_PHYS	0xb0000000
 
 
 /*
@@ -1903,16 +1688,6 @@
 #define LCD_Int100_0A	0xF     	/* LCD Intensity = 100.0% =  1     */
                 	        	/* (Alternative)                   */
 
-#define LCCR0		__REG(0xB0100000)  /* LCD Control Reg. 0 */
-#define LCSR		__REG(0xB0100004)  /* LCD Status Reg. */
-#define DBAR1		__REG(0xB0100010)  /* LCD DMA Base Address Reg. channel 1 */
-#define DCAR1		__REG(0xB0100014)  /* LCD DMA Current Address Reg. channel 1 */
-#define DBAR2		__REG(0xB0100018)  /* LCD DMA Base Address Reg.  channel 2 */
-#define DCAR2		__REG(0xB010001C)  /* LCD DMA Current Address Reg. channel 2 */
-#define LCCR1		__REG(0xB0100020)  /* LCD Control Reg. 1 */
-#define LCCR2		__REG(0xB0100024)  /* LCD Control Reg. 2 */
-#define LCCR3		__REG(0xB0100028)  /* LCD Control Reg. 3 */
-
 #define LCCR0_LEN	0x00000001	/* LCD ENable                      */
 #define LCCR0_CMS	0x00000002	/* Color/Monochrome display Select */
 #define LCCR0_Color	(LCCR0_CMS*0)	/*  Color display                  */
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index 52acda7061b7..f33679d2d3ee 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -1,7 +1,7 @@
 /*
  * arch/arm/mach-sa1100/include/mach/collie.h
  *
- * This file contains the hardware specific definitions for Assabet
+ * This file contains the hardware specific definitions for Collie
  * Only include this file from SA1100-specific files.
  *
  * ChangeLog:
@@ -13,6 +13,7 @@
 #ifndef __ASM_ARCH_COLLIE_H
 #define __ASM_ARCH_COLLIE_H
 
+extern void locomolcd_power(int on);
 
 #define COLLIE_SCOOP_GPIO_BASE	(GPIO_MAX + 1)
 #define COLLIE_GPIO_CHARGE_ON	(COLLIE_SCOOP_GPIO_BASE + 0)
diff --git a/arch/arm/mach-sa1100/include/mach/dma.h b/arch/arm/mach-sa1100/include/mach/dma.h
deleted file mode 100644
index dda1b351310d..000000000000
--- a/arch/arm/mach-sa1100/include/mach/dma.h
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
- * arch/arm/mach-sa1100/include/mach/dma.h
- *
- * Generic SA1100 DMA support
- *
- * Copyright (C) 2000 Nicolas Pitre
- *
- */
-
-#ifndef __ASM_ARCH_DMA_H
-#define __ASM_ARCH_DMA_H
-
-#include "hardware.h"
-
-
-/*
- * The SA1100 has six internal DMA channels.
- */
-#define SA1100_DMA_CHANNELS	6
-
-/*
- * Maximum physical DMA buffer size
- */
-#define MAX_DMA_SIZE		0x1fff
-#define CUT_DMA_SIZE		0x1000
-
-/*
- * All possible SA1100 devices a DMA channel can be attached to.
- */
-typedef enum {
-	DMA_Ser0UDCWr  = DDAR_Ser0UDCWr,   /* Ser. port 0 UDC Write */
-	DMA_Ser0UDCRd  = DDAR_Ser0UDCRd,   /* Ser. port 0 UDC Read */
-	DMA_Ser1UARTWr = DDAR_Ser1UARTWr,  /* Ser. port 1 UART Write */
-	DMA_Ser1UARTRd = DDAR_Ser1UARTRd,  /* Ser. port 1 UART Read */
-	DMA_Ser1SDLCWr = DDAR_Ser1SDLCWr,  /* Ser. port 1 SDLC Write */
-	DMA_Ser1SDLCRd = DDAR_Ser1SDLCRd,  /* Ser. port 1 SDLC Read */
-	DMA_Ser2UARTWr = DDAR_Ser2UARTWr,  /* Ser. port 2 UART Write */
-	DMA_Ser2UARTRd = DDAR_Ser2UARTRd,  /* Ser. port 2 UART Read */
-	DMA_Ser2HSSPWr = DDAR_Ser2HSSPWr,  /* Ser. port 2 HSSP Write */
-	DMA_Ser2HSSPRd = DDAR_Ser2HSSPRd,  /* Ser. port 2 HSSP Read */
-	DMA_Ser3UARTWr = DDAR_Ser3UARTWr,  /* Ser. port 3 UART Write */
-	DMA_Ser3UARTRd = DDAR_Ser3UARTRd,  /* Ser. port 3 UART Read */
-	DMA_Ser4MCP0Wr = DDAR_Ser4MCP0Wr,  /* Ser. port 4 MCP 0 Write (audio) */
-	DMA_Ser4MCP0Rd = DDAR_Ser4MCP0Rd,  /* Ser. port 4 MCP 0 Read (audio) */
-	DMA_Ser4MCP1Wr = DDAR_Ser4MCP1Wr,  /* Ser. port 4 MCP 1 Write */
-	DMA_Ser4MCP1Rd = DDAR_Ser4MCP1Rd,  /* Ser. port 4 MCP 1 Read */
-	DMA_Ser4SSPWr  = DDAR_Ser4SSPWr,   /* Ser. port 4 SSP Write (16 bits) */
-	DMA_Ser4SSPRd  = DDAR_Ser4SSPRd    /* Ser. port 4 SSP Read (16 bits) */
-} dma_device_t;
-
-typedef struct {
-	volatile u_long DDAR;
-	volatile u_long SetDCSR;
-	volatile u_long ClrDCSR;
-	volatile u_long RdDCSR;
-	volatile dma_addr_t DBSA;
-	volatile u_long DBTA;
-	volatile dma_addr_t DBSB;
-	volatile u_long DBTB;
-} dma_regs_t;
-
-typedef void (*dma_callback_t)(void *data);
-
-/*
- * DMA function prototypes
- */
-
-extern int sa1100_request_dma( dma_device_t device, const char *device_id,
-			       dma_callback_t callback, void *data,
-			       dma_regs_t **regs );
-extern void sa1100_free_dma( dma_regs_t *regs );
-extern int sa1100_start_dma( dma_regs_t *regs, dma_addr_t dma_ptr, u_int size );
-extern dma_addr_t sa1100_get_dma_pos(dma_regs_t *regs);
-extern void sa1100_reset_dma(dma_regs_t *regs);
-
-/**
- * 	sa1100_stop_dma - stop DMA in progress
- * 	@regs: identifier for the channel to use
- *
- * 	This stops DMA without clearing buffer pointers. Unlike
- * 	sa1100_clear_dma() this allows subsequent use of sa1100_resume_dma()
- * 	or sa1100_get_dma_pos().
- *
- * 	The @regs identifier is provided by a successful call to
- * 	sa1100_request_dma().
- **/
-
-#define sa1100_stop_dma(regs)	((regs)->ClrDCSR = DCSR_IE|DCSR_RUN)
-
-/**
- * 	sa1100_resume_dma - resume DMA on a stopped channel
- * 	@regs: identifier for the channel to use
- *
- * 	This resumes DMA on a channel previously stopped with
- * 	sa1100_stop_dma().
- *
- * 	The @regs identifier is provided by a successful call to
- * 	sa1100_request_dma().
- **/
-
-#define sa1100_resume_dma(regs)	((regs)->SetDCSR = DCSR_IE|DCSR_RUN)
-
-/**
- * 	sa1100_clear_dma - clear DMA pointers
- * 	@regs: identifier for the channel to use
- *
- * 	This clear any DMA state so the DMA engine is ready to restart
- * 	with new buffers through sa1100_start_dma(). Any buffers in flight
- * 	are discarded.
- *
- * 	The @regs identifier is provided by a successful call to
- * 	sa1100_request_dma().
- **/
-
-#define sa1100_clear_dma(regs)	((regs)->ClrDCSR = DCSR_IE|DCSR_RUN|DCSR_STRTA|DCSR_STRTB)
-
-#endif /* _ASM_ARCH_DMA_H */
diff --git a/arch/arm/mach-sa1100/include/mach/io.h b/arch/arm/mach-sa1100/include/mach/io.h
deleted file mode 100644
index dfc27ff08344..000000000000
--- a/arch/arm/mach-sa1100/include/mach/io.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * arch/arm/mach-sa1100/include/mach/io.h
- *
- * Copyright (C) 1997-1999 Russell King
- *
- * Modifications:
- *  06-12-1997	RMK	Created.
- *  07-04-1999	RMK	Major cleanup
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/*
- * __io() is required to be an equivalent mapping to __mem_pci() for
- * SOC_COMMON to work.
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-sa1100/include/mach/irqs.h b/arch/arm/mach-sa1100/include/mach/irqs.h
index d18f21abef80..3790298b7142 100644
--- a/arch/arm/mach-sa1100/include/mach/irqs.h
+++ b/arch/arm/mach-sa1100/include/mach/irqs.h
@@ -71,22 +71,19 @@
 /*
  * Figure out the MAX IRQ number.
  *
- * If we have an SA1111, the max IRQ is S1_BVD1_STSCHG+1.
- * If we have an LoCoMo, the max IRQ is IRQ_BOARD_START + 4
- * Otherwise, we have the standard IRQs only.
+ * Neponset, SA1111 and UCB1x00 are sparse IRQ aware, so can dynamically
+ * allocate their IRQs above NR_IRQS.
+ *
+ * LoCoMo has 4 additional IRQs, but is not sparse IRQ aware, and so has
+ * to be included in the NR_IRQS calculation.
  */
-#ifdef CONFIG_SA1111
-#define NR_IRQS			(IRQ_BOARD_END + 55)
-#elif defined(CONFIG_SHARP_LOCOMO)
-#define NR_IRQS			(IRQ_BOARD_START + 4)
+#ifdef CONFIG_SHARP_LOCOMO
+#define NR_IRQS_LOCOMO		4
 #else
-#define NR_IRQS			(IRQ_BOARD_START)
+#define NR_IRQS_LOCOMO		0
 #endif
 
-/*
- * Board specific IRQs.  Define them here.
- * Do not surround them with ifdefs.
- */
-#define IRQ_NEPONSET_SMC9196	(IRQ_BOARD_START + 0)
-#define IRQ_NEPONSET_USAR	(IRQ_BOARD_START + 1)
-#define IRQ_NEPONSET_SA1111	(IRQ_BOARD_START + 2)
+#ifndef NR_IRQS
+#define NR_IRQS (IRQ_BOARD_START + NR_IRQS_LOCOMO)
+#endif
+#define SA1100_NR_IRQS (IRQ_BOARD_START + NR_IRQS_LOCOMO)
diff --git a/arch/arm/mach-sa1100/include/mach/mcp.h b/arch/arm/mach-sa1100/include/mach/mcp.h
index ed1a331508a7..4b2860ae3828 100644
--- a/arch/arm/mach-sa1100/include/mach/mcp.h
+++ b/arch/arm/mach-sa1100/include/mach/mcp.h
@@ -16,7 +16,7 @@ struct mcp_plat_data {
 	u32 mccr0;
 	u32 mccr1;
 	unsigned int sclk_rate;
-	int gpio_base;
+	void *codec_pdata;
 };
 
 #endif
diff --git a/arch/arm/mach-sa1100/include/mach/neponset.h b/arch/arm/mach-sa1100/include/mach/neponset.h
index ffe2bc45eed0..5516a52a329d 100644
--- a/arch/arm/mach-sa1100/include/mach/neponset.h
+++ b/arch/arm/mach-sa1100/include/mach/neponset.h
@@ -15,54 +15,6 @@
 /*
  * Neponset definitions: 
  */
-
-#define NEPONSET_CPLD_BASE      (0x10000000)
-#define Nep_p2v( x )            ((x) - NEPONSET_CPLD_BASE + 0xf3000000)
-#define Nep_v2p( x )            ((x) - 0xf3000000 + NEPONSET_CPLD_BASE)
-
-#define _IRR                    0x10000024      /* Interrupt Reason Register */
-#define _AUD_CTL                0x100000c0      /* Audio controls (RW)       */
-#define _MDM_CTL_0              0x100000b0      /* Modem control 0 (RW)      */
-#define _MDM_CTL_1              0x100000b4      /* Modem control 1 (RW)      */
-#define _NCR_0	                0x100000a0      /* Control Register (RW)     */
-#define _KP_X_OUT               0x10000090      /* Keypad row write (RW)     */
-#define _KP_Y_IN                0x10000080      /* Keypad column read (RO)   */
-#define _SWPK                   0x10000020      /* Switch pack (RO)          */
-#define _WHOAMI                 0x10000000      /* System ID Register (RO)   */
-
-#define _LEDS                   0x10000010      /* LEDs [31:0] (WO)          */
-
-#define IRR                     (*((volatile u_char *) Nep_p2v(_IRR)))
-#define AUD_CTL                 (*((volatile u_char *) Nep_p2v(_AUD_CTL)))
-#define MDM_CTL_0               (*((volatile u_char *) Nep_p2v(_MDM_CTL_0)))
-#define MDM_CTL_1               (*((volatile u_char *) Nep_p2v(_MDM_CTL_1)))
-#define NCR_0			(*((volatile u_char *) Nep_p2v(_NCR_0)))
-#define KP_X_OUT                (*((volatile u_char *) Nep_p2v(_KP_X_OUT)))
-#define KP_Y_IN                 (*((volatile u_char *) Nep_p2v(_KP_Y_IN)))
-#define SWPK                    (*((volatile u_char *) Nep_p2v(_SWPK)))
-#define WHOAMI                  (*((volatile u_char *) Nep_p2v(_WHOAMI)))
-
-#define LEDS                    (*((volatile Word   *) Nep_p2v(_LEDS)))
-
-#define IRR_ETHERNET		(1<<0)
-#define IRR_USAR		(1<<1)
-#define IRR_SA1111		(1<<2)
-
-#define AUD_SEL_1341            (1<<0)
-#define AUD_MUTE_1341           (1<<1)
-
-#define MDM_CTL0_RTS1		(1 << 0)
-#define MDM_CTL0_DTR1		(1 << 1)
-#define MDM_CTL0_RTS2		(1 << 2)
-#define MDM_CTL0_DTR2		(1 << 3)
-
-#define MDM_CTL1_CTS1		(1 << 0)
-#define MDM_CTL1_DSR1		(1 << 1)
-#define MDM_CTL1_DCD1		(1 << 2)
-#define MDM_CTL1_CTS2		(1 << 3)
-#define MDM_CTL1_DSR2		(1 << 4)
-#define MDM_CTL1_DCD2		(1 << 5)
-
 #define NCR_GP01_OFF		(1<<0)
 #define NCR_TP_PWR_EN		(1<<1)
 #define NCR_MS_PWR_EN		(1<<2)
@@ -71,4 +23,8 @@
 #define NCR_A0VPP		(1<<5)
 #define NCR_A1VPP		(1<<6)
 
+void neponset_ncr_frob(unsigned int, unsigned int);
+#define neponset_ncr_set(v)	neponset_ncr_frob(0, v)
+#define neponset_ncr_clear(v)	neponset_ncr_frob(v, 0)
+
 #endif
diff --git a/arch/arm/mach-sa1100/include/mach/shannon.h b/arch/arm/mach-sa1100/include/mach/shannon.h
index 019f857a7938..fff39e02b496 100644
--- a/arch/arm/mach-sa1100/include/mach/shannon.h
+++ b/arch/arm/mach-sa1100/include/mach/shannon.h
@@ -21,7 +21,7 @@
 #define SHANNON_GPIO_U3_RTS		GPIO_GPIO (19)	/* ?? */
 #define SHANNON_GPIO_U3_CTS		GPIO_GPIO (20)	/* ?? */
 #define SHANNON_GPIO_SENSE_12V		GPIO_GPIO (21)	/* Input, 12v flash unprotect detected */
-#define SHANNON_GPIO_DISP_EN		GPIO_GPIO (22)	/* out */
+#define SHANNON_GPIO_DISP_EN		22		/* out */
 /* XXX GPIO 23 unaccounted for */
 #define SHANNON_GPIO_EJECT_0		24		/* in */
 #define SHANNON_GPIO_EJECT_1		25		/* in */
diff --git a/arch/arm/mach-sa1100/irq.c b/arch/arm/mach-sa1100/irq.c
index dfbf824a69fa..516ccc25d7fd 100644
--- a/arch/arm/mach-sa1100/irq.c
+++ b/arch/arm/mach-sa1100/irq.c
@@ -17,6 +17,7 @@
 #include <linux/syscore_ops.h>
 
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <asm/mach/irq.h>
 
 #include "generic.h"
@@ -221,11 +222,8 @@ static struct irq_chip sa1100_normal_chip = {
 	.irq_set_wake	= sa1100_set_wake,
 };
 
-static struct resource irq_resource = {
-	.name	= "irqs",
-	.start	= 0x90050000,
-	.end	= 0x9005ffff,
-};
+static struct resource irq_resource =
+	DEFINE_RES_MEM_NAMED(0x90050000, SZ_64K, "irqs");
 
 static struct sa1100irq_state {
 	unsigned int	saved;
diff --git a/arch/arm/mach-sa1100/jornada720.c b/arch/arm/mach-sa1100/jornada720.c
index ee121d6f0480..ca7a7e834720 100644
--- a/arch/arm/mach-sa1100/jornada720.c
+++ b/arch/arm/mach-sa1100/jornada720.c
@@ -23,9 +23,7 @@
 #include <linux/mtd/partitions.h>
 #include <video/s1d13xxxfb.h>
 
-#include <mach/hardware.h>
 #include <asm/hardware/sa1111.h>
-#include <asm/irq.h>
 #include <asm/page.h>
 #include <asm/mach-types.h>
 #include <asm/setup.h>
@@ -34,6 +32,9 @@
 #include <asm/mach/map.h>
 #include <asm/mach/serial_sa1100.h>
 
+#include <mach/hardware.h>
+#include <mach/irqs.h>
+
 #include "generic.h"
 
 /*
@@ -46,7 +47,7 @@
 
 /* memory space (line 52 of HP's doc) */
 #define SA1111REGSTART	0x40000000
-#define SA1111REGLEN	0x00001fff
+#define SA1111REGLEN	0x00002000
 #define EPSONREGSTART	0x48000000
 #define EPSONREGLEN	0x00100000
 #define EPSONFBSTART	0x48200000
@@ -174,16 +175,8 @@ static struct s1d13xxxfb_pdata s1d13xxxfb_data = {
 };
 
 static struct resource s1d13xxxfb_resources[] = {
-	[0] = {
-		.start	= EPSONFBSTART,
-		.end	= EPSONFBSTART + EPSONFBLEN,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= EPSONREGSTART,
-		.end	= EPSONREGSTART + EPSONREGLEN,
-		.flags	= IORESOURCE_MEM,
-	}
+	[0] = DEFINE_RES_MEM(EPSONFBSTART, EPSONFBLEN),
+	[1] = DEFINE_RES_MEM(EPSONREGSTART, EPSONREGLEN),
 };
 
 static struct platform_device s1d13xxxfb_device = {
@@ -197,20 +190,12 @@ static struct platform_device s1d13xxxfb_device = {
 };
 
 static struct resource sa1111_resources[] = {
-	[0] = {
-		.start		= SA1111REGSTART,
-		.end		= SA1111REGSTART + SA1111REGLEN,
-		.flags		= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start		= IRQ_GPIO1,
-		.end		= IRQ_GPIO1,
-		.flags		= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(SA1111REGSTART, SA1111REGLEN),
+	[1] = DEFINE_RES_IRQ(IRQ_GPIO1),
 };
 
 static struct sa1111_platform_data sa1111_info = {
-	.irq_base	= IRQ_BOARD_END,
+	.disable_devs	= SA1111_DEVID_PS2_MSE,
 };
 
 static u64 sa1111_dmamask = 0xffffffffUL;
@@ -284,11 +269,6 @@ static struct map_desc jornada720_io_desc[] __initdata = {
 		.pfn		= __phys_to_pfn(EPSONFBSTART),
 		.length		= EPSONFBLEN,
 		.type		= MT_DEVICE
-	}, {	/* SA-1111 */
-		.virtual	= 0xf4000000,
-		.pfn		= __phys_to_pfn(SA1111REGSTART),
-		.length		= SA1111REGLEN,
-		.type		= MT_DEVICE
 	}
 };
 
@@ -352,11 +332,8 @@ static struct flash_platform_data jornada720_flash_data = {
 	.nr_parts	= ARRAY_SIZE(jornada720_partitions),
 };
 
-static struct resource jornada720_flash_resource = {
-	.start		= SA1100_CS0_PHYS,
-	.end		= SA1100_CS0_PHYS + SZ_32M - 1,
-	.flags		= IORESOURCE_MEM,
-};
+static struct resource jornada720_flash_resource =
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_32M);
 
 static void __init jornada720_mach_init(void)
 {
@@ -367,6 +344,7 @@ MACHINE_START(JORNADA720, "HP Jornada 720")
 	/* Maintainer: Kristoffer Ericson <Kristoffer.Ericson@gmail.com> */
 	.atag_offset	= 0x100,
 	.map_io		= jornada720_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= jornada720_mach_init,
diff --git a/arch/arm/mach-sa1100/lart.c b/arch/arm/mach-sa1100/lart.c
index af4e2761f3db..eb6534e0b0d0 100644
--- a/arch/arm/mach-sa1100/lart.c
+++ b/arch/arm/mach-sa1100/lart.c
@@ -6,6 +6,8 @@
 #include <linux/kernel.h>
 #include <linux/tty.h>
 
+#include <video/sa1100fb.h>
+
 #include <mach/hardware.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
@@ -15,6 +17,7 @@
 #include <asm/mach/map.h>
 #include <asm/mach/serial_sa1100.h>
 #include <mach/mcp.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 
@@ -26,8 +29,86 @@ static struct mcp_plat_data lart_mcp_data = {
 	.sclk_rate	= 11981000,
 };
 
+#ifdef LART_GREY_LCD
+static struct sa1100fb_mach_info lart_grey_info = {
+	.pixclock	= 150000,	.bpp		= 4,
+	.xres		= 320,		.yres		= 240,
+
+	.hsync_len	= 1,		.vsync_len	= 1,
+	.left_margin	= 4,		.upper_margin	= 0,
+	.right_margin	= 2,		.lower_margin	= 0,
+
+	.cmap_greyscale	= 1,
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+
+	.lccr0		= LCCR0_Mono | LCCR0_Sngl | LCCR0_Pas | LCCR0_4PixMono,
+	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(512),
+};
+#endif
+#ifdef LART_COLOR_LCD
+static struct sa1100fb_mach_info lart_color_info = {
+	.pixclock	= 150000,	.bpp		= 16,
+	.xres		= 320,		.yres		= 240,
+
+	.hsync_len	= 2,		.vsync_len	= 3,
+	.left_margin	= 69,		.upper_margin	= 14,
+	.right_margin	= 8,		.lower_margin	= 4,
+
+	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
+	.lccr3		= LCCR3_OutEnH | LCCR3_PixFlEdg | LCCR3_ACBsDiv(512),
+};
+#endif
+#ifdef LART_VIDEO_OUT
+static struct sa1100fb_mach_info lart_video_info = {
+	.pixclock	= 39721,	.bpp		= 16,
+	.xres		= 640,		.yres		= 480,
+
+	.hsync_len	= 95,		.vsync_len	= 2,
+	.left_margin	= 40,		.upper_margin	= 32,
+	.right_margin	= 24,		.lower_margin	= 11,
+
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+
+	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
+	.lccr3		= LCCR3_OutEnL | LCCR3_PixFlEdg | LCCR3_ACBsDiv(512),
+};
+#endif
+
+#ifdef LART_KIT01_LCD
+static struct sa1100fb_mach_info lart_kit01_info = {
+	.pixclock	= 63291,	.bpp		= 16,
+	.xres		= 640,		.yres		= 480,
+
+	.hsync_len	= 64,		.vsync_len	= 3,
+	.left_margin	= 122,		.upper_margin	= 45,
+	.right_margin	= 10,		.lower_margin	= 10,
+
+	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
+	.lccr3		= LCCR3_OutEnH | LCCR3_PixFlEdg
+};
+#endif
+
 static void __init lart_init(void)
 {
+	struct sa1100fb_mach_info *inf = NULL;
+
+#ifdef LART_GREY_LCD
+	inf = &lart_grey_info;
+#endif
+#ifdef LART_COLOR_LCD
+	inf = &lart_color_info;
+#endif
+#ifdef LART_VIDEO_OUT
+	inf = &lart_video_info;
+#endif
+#ifdef LART_KIT01_LCD
+	inf = &lart_kit01_info;
+#endif
+
+	if (inf)
+		sa11x0_register_lcd(inf);
+
+	sa11x0_ppc_configure_mcp();
 	sa11x0_register_mcp(&lart_mcp_data);
 }
 
@@ -63,6 +144,7 @@ static void __init lart_map_io(void)
 MACHINE_START(LART, "LART")
 	.atag_offset	= 0x100,
 	.map_io		= lart_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.init_machine	= lart_init,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/leds-assabet.c b/arch/arm/mach-sa1100/leds-assabet.c
index 64e9b4b11b54..3699176bca94 100644
--- a/arch/arm/mach-sa1100/leds-assabet.c
+++ b/arch/arm/mach-sa1100/leds-assabet.c
@@ -13,7 +13,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 #include <mach/assabet.h>
 
 #include "leds.h"
diff --git a/arch/arm/mach-sa1100/leds-badge4.c b/arch/arm/mach-sa1100/leds-badge4.c
index cf1e38458b81..f99fac3eedb6 100644
--- a/arch/arm/mach-sa1100/leds-badge4.c
+++ b/arch/arm/mach-sa1100/leds-badge4.c
@@ -14,7 +14,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #include "leds.h"
 
diff --git a/arch/arm/mach-sa1100/leds-cerf.c b/arch/arm/mach-sa1100/leds-cerf.c
index 259b48e0be89..040540fb7d8a 100644
--- a/arch/arm/mach-sa1100/leds-cerf.c
+++ b/arch/arm/mach-sa1100/leds-cerf.c
@@ -7,7 +7,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #include "leds.h"
 
diff --git a/arch/arm/mach-sa1100/leds-hackkit.c b/arch/arm/mach-sa1100/leds-hackkit.c
index 2bce137462e4..6a2352436e62 100644
--- a/arch/arm/mach-sa1100/leds-hackkit.c
+++ b/arch/arm/mach-sa1100/leds-hackkit.c
@@ -13,7 +13,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #include "leds.h"
 
diff --git a/arch/arm/mach-sa1100/leds-lart.c b/arch/arm/mach-sa1100/leds-lart.c
index 0505a1fdcdb2..a51830c60e53 100644
--- a/arch/arm/mach-sa1100/leds-lart.c
+++ b/arch/arm/mach-sa1100/leds-lart.c
@@ -13,7 +13,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #include "leds.h"
 
diff --git a/arch/arm/mach-sa1100/nanoengine.c b/arch/arm/mach-sa1100/nanoengine.c
index 85f6ee672225..8f6446b9f025 100644
--- a/arch/arm/mach-sa1100/nanoengine.c
+++ b/arch/arm/mach-sa1100/nanoengine.c
@@ -28,6 +28,7 @@
 
 #include <mach/hardware.h>
 #include <mach/nanoengine.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 
@@ -58,15 +59,8 @@ static struct flash_platform_data nanoengine_flash_data = {
 };
 
 static struct resource nanoengine_flash_resources[] = {
-	{
-		.start	= SA1100_CS0_PHYS,
-		.end	= SA1100_CS0_PHYS + SZ_32M - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= SA1100_CS1_PHYS,
-		.end	= SA1100_CS1_PHYS + SZ_32M - 1,
-		.flags	= IORESOURCE_MEM,
-	}
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_32M),
+	DEFINE_RES_MEM(SA1100_CS1_PHYS, SZ_32M),
 };
 
 static struct map_desc nanoengine_io_desc[] __initdata = {
@@ -114,6 +108,7 @@ static void __init nanoengine_init(void)
 MACHINE_START(NANOENGINE, "BSE nanoEngine")
 	.atag_offset	= 0x100,
 	.map_io		= nanoengine_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= nanoengine_init,
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index b4fa53a1427e..6c58f01b358a 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -1,89 +1,104 @@
 /*
  * linux/arch/arm/mach-sa1100/neponset.c
- *
  */
-#include <linux/kernel.h>
+#include <linux/err.h>
 #include <linux/init.h>
-#include <linux/tty.h>
 #include <linux/ioport.h>
-#include <linux/serial_core.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/serial_core.h>
+#include <linux/slab.h>
 
-#include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/irq.h>
 #include <asm/mach/map.h>
-#include <asm/mach/irq.h>
 #include <asm/mach/serial_sa1100.h>
-#include <mach/assabet.h>
-#include <mach/neponset.h>
 #include <asm/hardware/sa1111.h>
 #include <asm/sizes.h>
 
-/*
- * Install handler for Neponset IRQ.  Note that we have to loop here
- * since the ETHERNET and USAR IRQs are level based, and we need to
- * ensure that the IRQ signal is deasserted before returning.  This
- * is rather unfortunate.
- */
-static void
-neponset_irq_handler(unsigned int irq, struct irq_desc *desc)
-{
-	unsigned int irr;
-
-	while (1) {
-		/*
-		 * Acknowledge the parent IRQ.
-		 */
-		desc->irq_data.chip->irq_ack(&desc->irq_data);
-
-		/*
-		 * Read the interrupt reason register.  Let's have all
-		 * active IRQ bits high.  Note: there is a typo in the
-		 * Neponset user's guide for the SA1111 IRR level.
-		 */
-		irr = IRR ^ (IRR_ETHERNET | IRR_USAR);
-
-		if ((irr & (IRR_ETHERNET | IRR_USAR | IRR_SA1111)) == 0)
-			break;
-
-		/*
-		 * Since there is no individual mask, we have to
-		 * mask the parent IRQ.  This is safe, since we'll
-		 * recheck the register for any pending IRQs.
-		 */
-		if (irr & (IRR_ETHERNET | IRR_USAR)) {
-			desc->irq_data.chip->irq_mask(&desc->irq_data);
-
-			/*
-			 * Ack the interrupt now to prevent re-entering
-			 * this neponset handler.  Again, this is safe
-			 * since we'll check the IRR register prior to
-			 * leaving.
-			 */
-			desc->irq_data.chip->irq_ack(&desc->irq_data);
+#include <mach/hardware.h>
+#include <mach/assabet.h>
+#include <mach/neponset.h>
+#include <mach/irqs.h>
+
+#define NEP_IRQ_SMC91X	0
+#define NEP_IRQ_USAR	1
+#define NEP_IRQ_SA1111	2
+#define NEP_IRQ_NR	3
+
+#define WHOAMI		0x00
+#define LEDS		0x10
+#define SWPK		0x20
+#define IRR		0x24
+#define KP_Y_IN		0x80
+#define KP_X_OUT	0x90
+#define NCR_0		0xa0
+#define MDM_CTL_0	0xb0
+#define MDM_CTL_1	0xb4
+#define AUD_CTL		0xc0
+
+#define IRR_ETHERNET	(1 << 0)
+#define IRR_USAR	(1 << 1)
+#define IRR_SA1111	(1 << 2)
+
+#define MDM_CTL0_RTS1	(1 << 0)
+#define MDM_CTL0_DTR1	(1 << 1)
+#define MDM_CTL0_RTS2	(1 << 2)
+#define MDM_CTL0_DTR2	(1 << 3)
+
+#define MDM_CTL1_CTS1	(1 << 0)
+#define MDM_CTL1_DSR1	(1 << 1)
+#define MDM_CTL1_DCD1	(1 << 2)
+#define MDM_CTL1_CTS2	(1 << 3)
+#define MDM_CTL1_DSR2	(1 << 4)
+#define MDM_CTL1_DCD2	(1 << 5)
+
+#define AUD_SEL_1341	(1 << 0)
+#define AUD_MUTE_1341	(1 << 1)
 
-			if (irr & IRR_ETHERNET) {
-				generic_handle_irq(IRQ_NEPONSET_SMC9196);
-			}
+extern void sa1110_mb_disable(void);
 
-			if (irr & IRR_USAR) {
-				generic_handle_irq(IRQ_NEPONSET_USAR);
-			}
+struct neponset_drvdata {
+	void __iomem *base;
+	struct platform_device *sa1111;
+	struct platform_device *smc91x;
+	unsigned irq_base;
+#ifdef CONFIG_PM_SLEEP
+	u32 ncr0;
+	u32 mdm_ctl_0;
+#endif
+};
 
-			desc->irq_data.chip->irq_unmask(&desc->irq_data);
-		}
+static void __iomem *nep_base;
 
-		if (irr & IRR_SA1111) {
-			generic_handle_irq(IRQ_NEPONSET_SA1111);
-		}
+void neponset_ncr_frob(unsigned int mask, unsigned int val)
+{
+	void __iomem *base = nep_base;
+
+	if (base) {
+		unsigned long flags;
+		unsigned v;
+
+		local_irq_save(flags);
+		v = readb_relaxed(base + NCR_0);
+		writeb_relaxed((v & ~mask) | val, base + NCR_0);
+		local_irq_restore(flags);
+	} else {
+		WARN(1, "nep_base unset\n");
 	}
 }
 
 static void neponset_set_mctrl(struct uart_port *port, u_int mctrl)
 {
-	u_int mdm_ctl0 = MDM_CTL_0;
+	void __iomem *base = nep_base;
+	u_int mdm_ctl0;
 
+	if (!base)
+		return;
+
+	mdm_ctl0 = readb_relaxed(base + MDM_CTL_0);
 	if (port->mapbase == _Ser1UTCR0) {
 		if (mctrl & TIOCM_RTS)
 			mdm_ctl0 &= ~MDM_CTL0_RTS2;
@@ -106,14 +121,19 @@ static void neponset_set_mctrl(struct uart_port *port, u_int mctrl)
 			mdm_ctl0 |= MDM_CTL0_DTR1;
 	}
 
-	MDM_CTL_0 = mdm_ctl0;
+	writeb_relaxed(mdm_ctl0, base + MDM_CTL_0);
 }
 
 static u_int neponset_get_mctrl(struct uart_port *port)
 {
+	void __iomem *base = nep_base;
 	u_int ret = TIOCM_CD | TIOCM_CTS | TIOCM_DSR;
-	u_int mdm_ctl1 = MDM_CTL_1;
+	u_int mdm_ctl1;
+
+	if (!base)
+		return ret;
 
+	mdm_ctl1 = readb_relaxed(base + MDM_CTL_1);
 	if (port->mapbase == _Ser1UTCR0) {
 		if (mdm_ctl1 & MDM_CTL1_DCD2)
 			ret &= ~TIOCM_CD;
@@ -138,209 +158,278 @@ static struct sa1100_port_fns neponset_port_fns __devinitdata = {
 	.get_mctrl	= neponset_get_mctrl,
 };
 
-static int __devinit neponset_probe(struct platform_device *dev)
+/*
+ * Install handler for Neponset IRQ.  Note that we have to loop here
+ * since the ETHERNET and USAR IRQs are level based, and we need to
+ * ensure that the IRQ signal is deasserted before returning.  This
+ * is rather unfortunate.
+ */
+static void neponset_irq_handler(unsigned int irq, struct irq_desc *desc)
 {
-	sa1100_register_uart_fns(&neponset_port_fns);
+	struct neponset_drvdata *d = irq_desc_get_handler_data(desc);
+	unsigned int irr;
 
-	/*
-	 * Install handler for GPIO25.
-	 */
-	irq_set_irq_type(IRQ_GPIO25, IRQ_TYPE_EDGE_RISING);
-	irq_set_chained_handler(IRQ_GPIO25, neponset_irq_handler);
+	while (1) {
+		/*
+		 * Acknowledge the parent IRQ.
+		 */
+		desc->irq_data.chip->irq_ack(&desc->irq_data);
 
-	/*
-	 * We would set IRQ_GPIO25 to be a wake-up IRQ, but
-	 * unfortunately something on the Neponset activates
-	 * this IRQ on sleep (ethernet?)
-	 */
-#if 0
-	enable_irq_wake(IRQ_GPIO25);
-#endif
+		/*
+		 * Read the interrupt reason register.  Let's have all
+		 * active IRQ bits high.  Note: there is a typo in the
+		 * Neponset user's guide for the SA1111 IRR level.
+		 */
+		irr = readb_relaxed(d->base + IRR);
+		irr ^= IRR_ETHERNET | IRR_USAR;
 
-	/*
-	 * Setup other Neponset IRQs.  SA1111 will be done by the
-	 * generic SA1111 code.
-	 */
-	irq_set_handler(IRQ_NEPONSET_SMC9196, handle_simple_irq);
-	set_irq_flags(IRQ_NEPONSET_SMC9196, IRQF_VALID | IRQF_PROBE);
-	irq_set_handler(IRQ_NEPONSET_USAR, handle_simple_irq);
-	set_irq_flags(IRQ_NEPONSET_USAR, IRQF_VALID | IRQF_PROBE);
+		if ((irr & (IRR_ETHERNET | IRR_USAR | IRR_SA1111)) == 0)
+			break;
 
-	/*
-	 * Disable GPIO 0/1 drivers so the buttons work on the module.
-	 */
-	NCR_0 = NCR_GP01_OFF;
+		/*
+		 * Since there is no individual mask, we have to
+		 * mask the parent IRQ.  This is safe, since we'll
+		 * recheck the register for any pending IRQs.
+		 */
+		if (irr & (IRR_ETHERNET | IRR_USAR)) {
+			desc->irq_data.chip->irq_mask(&desc->irq_data);
 
-	return 0;
-}
+			/*
+			 * Ack the interrupt now to prevent re-entering
+			 * this neponset handler.  Again, this is safe
+			 * since we'll check the IRR register prior to
+			 * leaving.
+			 */
+			desc->irq_data.chip->irq_ack(&desc->irq_data);
 
-#ifdef CONFIG_PM
+			if (irr & IRR_ETHERNET)
+				generic_handle_irq(d->irq_base + NEP_IRQ_SMC91X);
 
-/*
- * LDM power management.
- */
-static unsigned int neponset_saved_state;
+			if (irr & IRR_USAR)
+				generic_handle_irq(d->irq_base + NEP_IRQ_USAR);
 
-static int neponset_suspend(struct platform_device *dev, pm_message_t state)
-{
-	/*
-	 * Save state.
-	 */
-	neponset_saved_state = NCR_0;
+			desc->irq_data.chip->irq_unmask(&desc->irq_data);
+		}
 
-	return 0;
+		if (irr & IRR_SA1111)
+			generic_handle_irq(d->irq_base + NEP_IRQ_SA1111);
+	}
 }
 
-static int neponset_resume(struct platform_device *dev)
+/* Yes, we really do not have any kind of masking or unmasking */
+static void nochip_noop(struct irq_data *irq)
 {
-	NCR_0 = neponset_saved_state;
-
-	return 0;
 }
 
-#else
-#define neponset_suspend NULL
-#define neponset_resume  NULL
-#endif
-
-static struct platform_driver neponset_device_driver = {
-	.probe		= neponset_probe,
-	.suspend	= neponset_suspend,
-	.resume		= neponset_resume,
-	.driver		= {
-		.name	= "neponset",
-	},
-};
-
-static struct resource neponset_resources[] = {
-	[0] = {
-		.start	= 0x10000000,
-		.end	= 0x17ffffff,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device neponset_device = {
-	.name		= "neponset",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(neponset_resources),
-	.resource	= neponset_resources,
-};
-
-static struct resource sa1111_resources[] = {
-	[0] = {
-		.start	= 0x40000000,
-		.end	= 0x40001fff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_NEPONSET_SA1111,
-		.end	= IRQ_NEPONSET_SA1111,
-		.flags	= IORESOURCE_IRQ,
-	},
+static struct irq_chip nochip = {
+	.name = "neponset",
+	.irq_ack = nochip_noop,
+	.irq_mask = nochip_noop,
+	.irq_unmask = nochip_noop,
 };
 
 static struct sa1111_platform_data sa1111_info = {
-	.irq_base	= IRQ_BOARD_END,
+	.disable_devs	= SA1111_DEVID_PS2_MSE,
 };
 
-static u64 sa1111_dmamask = 0xffffffffUL;
+static int __devinit neponset_probe(struct platform_device *dev)
+{
+	struct neponset_drvdata *d;
+	struct resource *nep_res, *sa1111_res, *smc91x_res;
+	struct resource sa1111_resources[] = {
+		DEFINE_RES_MEM(0x40000000, SZ_8K),
+		{ .flags = IORESOURCE_IRQ },
+	};
+	struct platform_device_info sa1111_devinfo = {
+		.parent = &dev->dev,
+		.name = "sa1111",
+		.id = 0,
+		.res = sa1111_resources,
+		.num_res = ARRAY_SIZE(sa1111_resources),
+		.data = &sa1111_info,
+		.size_data = sizeof(sa1111_info),
+		.dma_mask = 0xffffffffUL,
+	};
+	struct resource smc91x_resources[] = {
+		DEFINE_RES_MEM_NAMED(SA1100_CS3_PHYS,
+			0x02000000, "smc91x-regs"),
+		DEFINE_RES_MEM_NAMED(SA1100_CS3_PHYS + 0x02000000,
+			0x02000000, "smc91x-attrib"),
+		{ .flags = IORESOURCE_IRQ },
+	};
+	struct platform_device_info smc91x_devinfo = {
+		.parent = &dev->dev,
+		.name = "smc91x",
+		.id = 0,
+		.res = smc91x_resources,
+		.num_res = ARRAY_SIZE(smc91x_resources),
+	};
+	int ret, irq;
+
+	if (nep_base)
+		return -EBUSY;
+
+	irq = ret = platform_get_irq(dev, 0);
+	if (ret < 0)
+		goto err_alloc;
+
+	nep_res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	smc91x_res = platform_get_resource(dev, IORESOURCE_MEM, 1);
+	sa1111_res = platform_get_resource(dev, IORESOURCE_MEM, 2);
+	if (!nep_res || !smc91x_res || !sa1111_res) {
+		ret = -ENXIO;
+		goto err_alloc;
+	}
 
-static struct platform_device sa1111_device = {
-	.name		= "sa1111",
-	.id		= 0,
-	.dev		= {
-		.dma_mask = &sa1111_dmamask,
-		.coherent_dma_mask = 0xffffffff,
-		.platform_data = &sa1111_info,
-	},
-	.num_resources	= ARRAY_SIZE(sa1111_resources),
-	.resource	= sa1111_resources,
-};
+	d = kzalloc(sizeof(*d), GFP_KERNEL);
+	if (!d) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
 
-static struct resource smc91x_resources[] = {
-	[0] = {
-		.name	= "smc91x-regs",
-		.start	= SA1100_CS3_PHYS,
-		.end	= SA1100_CS3_PHYS + 0x01ffffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_NEPONSET_SMC9196,
-		.end	= IRQ_NEPONSET_SMC9196,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.name	= "smc91x-attrib",
-		.start	= SA1100_CS3_PHYS + 0x02000000,
-		.end	= SA1100_CS3_PHYS + 0x03ffffff,
-		.flags	= IORESOURCE_MEM,
-	},
-};
+	d->base = ioremap(nep_res->start, SZ_4K);
+	if (!d->base) {
+		ret = -ENOMEM;
+		goto err_ioremap;
+	}
 
-static struct platform_device smc91x_device = {
-	.name		= "smc91x",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(smc91x_resources),
-	.resource	= smc91x_resources,
-};
+	if (readb_relaxed(d->base + WHOAMI) != 0x11) {
+		dev_warn(&dev->dev, "Neponset board detected, but wrong ID: %02x\n",
+			 readb_relaxed(d->base + WHOAMI));
+		ret = -ENODEV;
+		goto err_id;
+	}
 
-static struct platform_device *devices[] __initdata = {
-	&neponset_device,
-	&sa1111_device,
-	&smc91x_device,
-};
+	ret = irq_alloc_descs(-1, IRQ_BOARD_START, NEP_IRQ_NR, -1);
+	if (ret <= 0) {
+		dev_err(&dev->dev, "unable to allocate %u irqs: %d\n",
+			NEP_IRQ_NR, ret);
+		if (ret == 0)
+			ret = -ENOMEM;
+		goto err_irq_alloc;
+	}
 
-extern void sa1110_mb_disable(void);
+	d->irq_base = ret;
 
-static int __init neponset_init(void)
-{
-	platform_driver_register(&neponset_device_driver);
+	irq_set_chip_and_handler(d->irq_base + NEP_IRQ_SMC91X, &nochip,
+		handle_simple_irq);
+	set_irq_flags(d->irq_base + NEP_IRQ_SMC91X, IRQF_VALID | IRQF_PROBE);
+	irq_set_chip_and_handler(d->irq_base + NEP_IRQ_USAR, &nochip,
+		handle_simple_irq);
+	set_irq_flags(d->irq_base + NEP_IRQ_USAR, IRQF_VALID | IRQF_PROBE);
+	irq_set_chip(d->irq_base + NEP_IRQ_SA1111, &nochip);
 
-	/*
-	 * The Neponset is only present on the Assabet machine type.
-	 */
-	if (!machine_is_assabet())
-		return -ENODEV;
+	irq_set_irq_type(irq, IRQ_TYPE_EDGE_RISING);
+	irq_set_handler_data(irq, d);
+	irq_set_chained_handler(irq, neponset_irq_handler);
 
 	/*
-	 * Ensure that the memory bus request/grant signals are setup,
-	 * and the grant is held in its inactive state, whether or not
-	 * we actually have a Neponset attached.
+	 * We would set IRQ_GPIO25 to be a wake-up IRQ, but unfortunately
+	 * something on the Neponset activates this IRQ on sleep (eth?)
 	 */
+#if 0
+	enable_irq_wake(irq);
+#endif
+
+	dev_info(&dev->dev, "Neponset daughter board, providing IRQ%u-%u\n",
+		 d->irq_base, d->irq_base + NEP_IRQ_NR - 1);
+	nep_base = d->base;
+
+	sa1100_register_uart_fns(&neponset_port_fns);
+
+	/* Ensure that the memory bus request/grant signals are setup */
 	sa1110_mb_disable();
 
-	if (!machine_has_neponset()) {
-		printk(KERN_DEBUG "Neponset expansion board not present\n");
-		return -ENODEV;
-	}
+	/* Disable GPIO 0/1 drivers so the buttons work on the Assabet */
+	writeb_relaxed(NCR_GP01_OFF, d->base + NCR_0);
 
-	if (WHOAMI != 0x11) {
-		printk(KERN_WARNING "Neponset board detected, but "
-			"wrong ID: %02x\n", WHOAMI);
-		return -ENODEV;
-	}
+	sa1111_resources[0].parent = sa1111_res;
+	sa1111_resources[1].start = d->irq_base + NEP_IRQ_SA1111;
+	sa1111_resources[1].end = d->irq_base + NEP_IRQ_SA1111;
+	d->sa1111 = platform_device_register_full(&sa1111_devinfo);
+
+	smc91x_resources[0].parent = smc91x_res;
+	smc91x_resources[1].parent = smc91x_res;
+	smc91x_resources[2].start = d->irq_base + NEP_IRQ_SMC91X;
+	smc91x_resources[2].end = d->irq_base + NEP_IRQ_SMC91X;
+	d->smc91x = platform_device_register_full(&smc91x_devinfo);
+
+	platform_set_drvdata(dev, d);
 
-	return platform_add_devices(devices, ARRAY_SIZE(devices));
+	return 0;
+
+ err_irq_alloc:
+ err_id:
+	iounmap(d->base);
+ err_ioremap:
+	kfree(d);
+ err_alloc:
+	return ret;
 }
 
-subsys_initcall(neponset_init);
+static int __devexit neponset_remove(struct platform_device *dev)
+{
+	struct neponset_drvdata *d = platform_get_drvdata(dev);
+	int irq = platform_get_irq(dev, 0);
+
+	if (!IS_ERR(d->sa1111))
+		platform_device_unregister(d->sa1111);
+	if (!IS_ERR(d->smc91x))
+		platform_device_unregister(d->smc91x);
+	irq_set_chained_handler(irq, NULL);
+	irq_free_descs(d->irq_base, NEP_IRQ_NR);
+	nep_base = NULL;
+	iounmap(d->base);
+	kfree(d);
 
-static struct map_desc neponset_io_desc[] __initdata = {
-	{	/* System Registers */
-		.virtual	=  0xf3000000,
-		.pfn		= __phys_to_pfn(0x10000000),
-		.length		= SZ_1M,
-		.type		= MT_DEVICE
-	}, {	/* SA-1111 */
-		.virtual	=  0xf4000000,
-		.pfn		= __phys_to_pfn(0x40000000),
-		.length		= SZ_1M,
-		.type		= MT_DEVICE
-	}
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int neponset_suspend(struct device *dev)
+{
+	struct neponset_drvdata *d = dev_get_drvdata(dev);
+
+	d->ncr0 = readb_relaxed(d->base + NCR_0);
+	d->mdm_ctl_0 = readb_relaxed(d->base + MDM_CTL_0);
+
+	return 0;
+}
+
+static int neponset_resume(struct device *dev)
+{
+	struct neponset_drvdata *d = dev_get_drvdata(dev);
+
+	writeb_relaxed(d->ncr0, d->base + NCR_0);
+	writeb_relaxed(d->mdm_ctl_0, d->base + MDM_CTL_0);
+
+	return 0;
+}
+
+static const struct dev_pm_ops neponset_pm_ops = {
+	.suspend_noirq = neponset_suspend,
+	.resume_noirq = neponset_resume,
+	.freeze_noirq = neponset_suspend,
+	.restore_noirq = neponset_resume,
+};
+#define PM_OPS &neponset_pm_ops
+#else
+#define PM_OPS NULL
+#endif
+
+static struct platform_driver neponset_device_driver = {
+	.probe		= neponset_probe,
+	.remove		= __devexit_p(neponset_remove),
+	.driver		= {
+		.name	= "neponset",
+		.owner	= THIS_MODULE,
+		.pm	= PM_OPS,
+	},
 };
 
-void __init neponset_map_io(void)
+static int __init neponset_init(void)
 {
-	iotable_init(neponset_io_desc, ARRAY_SIZE(neponset_io_desc));
+	return platform_driver_register(&neponset_device_driver);
 }
+
+subsys_initcall(neponset_init);
diff --git a/arch/arm/mach-sa1100/pci-nanoengine.c b/arch/arm/mach-sa1100/pci-nanoengine.c
index b466bca9c651..b49108b890a8 100644
--- a/arch/arm/mach-sa1100/pci-nanoengine.c
+++ b/arch/arm/mach-sa1100/pci-nanoengine.c
@@ -135,12 +135,8 @@ struct pci_bus * __init pci_nanoengine_scan_bus(int nr, struct pci_sys_data *sys
 				 &sys->resources);
 }
 
-static struct resource pci_io_ports = {
-	.name	= "PCI IO",
-	.start	= 0x400,
-	.end	= 0x7FF,
-	.flags	= IORESOURCE_IO,
-};
+static struct resource pci_io_ports =
+	DEFINE_RES_IO_NAMED(0x400, 0x400, "PCI IO");
 
 static struct resource pci_non_prefetchable_memory = {
 	.name	= "PCI non-prefetchable",
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index 9307df053533..1602575a0d5c 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -37,17 +37,9 @@
 #define IRQ_GPIO_ETH0_IRQ	IRQ_GPIO21
 
 static struct resource smc91x_resources[] = {
-	[0] = {
-		.start	= PLEB_ETH0_P,
-		.end	= PLEB_ETH0_P | 0x03ffffff,
-		.flags	= IORESOURCE_MEM,
-	},
+	[0] = DEFINE_RES_MEM(PLEB_ETH0_P, 0x04000000),
 #if 0 /* Autoprobe instead, to get rising/falling edge characteristic right */
-	[1] = {
-		.start	= IRQ_GPIO_ETH0_IRQ,
-		.end	= IRQ_GPIO_ETH0_IRQ,
-		.flags	= IORESOURCE_IRQ,
-	},
+	[1] = DEFINE_RES_IRQ(IRQ_GPIO_ETH0_IRQ),
 #endif
 };
 
@@ -70,16 +62,8 @@ static struct platform_device *devices[] __initdata = {
  * the two SA1100 lowest chip select outputs.
  */
 static struct resource pleb_flash_resources[] = {
-	[0] = {
-		.start = SA1100_CS0_PHYS,
-		.end   = SA1100_CS0_PHYS + SZ_8M - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = SA1100_CS1_PHYS,
-		.end   = SA1100_CS1_PHYS + SZ_8M - 1,
-		.flags = IORESOURCE_MEM,
-	}
+	[0] = DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_8M),
+	[1] = DEFINE_RES_MEM(SA1100_CS1_PHYS, SZ_8M),
 };
 
 
@@ -147,6 +131,7 @@ static void __init pleb_map_io(void)
 
 MACHINE_START(PLEB, "PLEB")
 	.map_io		= pleb_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine   = pleb_init,
diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c
index bf85b8b259d5..2fa499ec6afe 100644
--- a/arch/arm/mach-sa1100/pm.c
+++ b/arch/arm/mach-sa1100/pm.c
@@ -30,7 +30,6 @@
 #include <mach/hardware.h>
 #include <asm/memory.h>
 #include <asm/suspend.h>
-#include <asm/system.h>
 #include <asm/mach/time.h>
 
 extern int sa1100_finish_suspend(unsigned long);
diff --git a/arch/arm/mach-sa1100/shannon.c b/arch/arm/mach-sa1100/shannon.c
index 318b2b766a0b..ca8bf59b9047 100644
--- a/arch/arm/mach-sa1100/shannon.c
+++ b/arch/arm/mach-sa1100/shannon.c
@@ -9,6 +9,8 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 
+#include <video/sa1100fb.h>
+
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/setup.h>
@@ -19,6 +21,7 @@
 #include <asm/mach/serial_sa1100.h>
 #include <mach/mcp.h>
 #include <mach/shannon.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 
@@ -46,19 +49,32 @@ static struct flash_platform_data shannon_flash_data = {
 	.nr_parts	= ARRAY_SIZE(shannon_partitions),
 };
 
-static struct resource shannon_flash_resource = {
-	.start		= SA1100_CS0_PHYS,
-	.end		= SA1100_CS0_PHYS + SZ_4M - 1,
-	.flags		= IORESOURCE_MEM,
-};
+static struct resource shannon_flash_resource =
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_4M);
 
 static struct mcp_plat_data shannon_mcp_data = {
 	.mccr0		= MCCR0_ADM,
 	.sclk_rate	= 11981000,
 };
 
+static struct sa1100fb_mach_info shannon_lcd_info = {
+	.pixclock	= 152500,	.bpp		= 8,
+	.xres		= 640,		.yres		= 480,
+
+	.hsync_len	= 4,		.vsync_len	= 3,
+	.left_margin	= 2,		.upper_margin	= 0,
+	.right_margin	= 1,		.lower_margin	= 0,
+
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+
+	.lccr0		= LCCR0_Color | LCCR0_Dual | LCCR0_Pas,
+	.lccr3		= LCCR3_ACBsDiv(512),
+};
+
 static void __init shannon_init(void)
 {
+	sa11x0_ppc_configure_mcp();
+	sa11x0_register_lcd(&shannon_lcd_info);
 	sa11x0_register_mtd(&shannon_flash_data, &shannon_flash_resource, 1);
 	sa11x0_register_mcp(&shannon_mcp_data);
 }
@@ -84,6 +100,7 @@ static void __init shannon_map_io(void)
 MACHINE_START(SHANNON, "Shannon (AKA: Tuxscreen)")
 	.atag_offset	= 0x100,
 	.map_io		= shannon_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.init_machine	= shannon_init,
diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
index e17c04d6e324..3efae03cb3d7 100644
--- a/arch/arm/mach-sa1100/simpad.c
+++ b/arch/arm/mach-sa1100/simpad.c
@@ -7,15 +7,15 @@
 #include <linux/kernel.h>
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
-#include <linux/string.h> 
+#include <linux/string.h>
 #include <linux/pm.h>
 #include <linux/platform_device.h>
+#include <linux/mfd/ucb1x00.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
 
-#include <asm/irq.h>
 #include <mach/hardware.h>
 #include <asm/setup.h>
 
@@ -26,6 +26,7 @@
 #include <asm/mach/serial_sa1100.h>
 #include <mach/mcp.h>
 #include <mach/simpad.h>
+#include <mach/irqs.h>
 
 #include <linux/serial_core.h>
 #include <linux/ioport.h>
@@ -176,21 +177,18 @@ static struct flash_platform_data simpad_flash_data = {
 
 
 static struct resource simpad_flash_resources [] = {
-	{
-		.start     = SA1100_CS0_PHYS,
-		.end       = SA1100_CS0_PHYS + SZ_16M -1,
-		.flags     = IORESOURCE_MEM,
-	}, {
-		.start     = SA1100_CS1_PHYS,
-		.end       = SA1100_CS1_PHYS + SZ_16M -1,
-		.flags     = IORESOURCE_MEM,
-	}
+	DEFINE_RES_MEM(SA1100_CS0_PHYS, SZ_16M),
+	DEFINE_RES_MEM(SA1100_CS1_PHYS, SZ_16M),
+};
+
+static struct ucb1x00_plat_data simpad_ucb1x00_data = {
+	.gpio_base	= SIMPAD_UCB1X00_GPIO_BASE,
 };
 
 static struct mcp_plat_data simpad_mcp_data = {
 	.mccr0		= MCCR0_ADM,
 	.sclk_rate	= 11981000,
-	.gpio_base	= SIMPAD_UCB1X00_GPIO_BASE,
+	.codec_pdata	= &simpad_ucb1x00_data,
 };
 
 
@@ -376,6 +374,7 @@ static int __init simpad_init(void)
 
 	pm_power_off = simpad_power_off;
 
+	sa11x0_ppc_configure_mcp();
 	sa11x0_register_mtd(&simpad_flash_data, simpad_flash_resources,
 			      ARRAY_SIZE(simpad_flash_resources));
 	sa11x0_register_mcp(&simpad_mcp_data);
@@ -394,6 +393,7 @@ MACHINE_START(SIMPAD, "Simpad")
 	/* Maintainer: Holger Freyther */
 	.atag_offset	= 0x100,
 	.map_io		= simpad_map_io,
+	.nr_irqs	= SA1100_NR_IRQS,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
 	.restart	= sa11x0_restart,
diff --git a/arch/arm/mach-sa1100/sleep.S b/arch/arm/mach-sa1100/sleep.S
index e8223315b442..30cc6721665b 100644
--- a/arch/arm/mach-sa1100/sleep.S
+++ b/arch/arm/mach-sa1100/sleep.S
@@ -26,27 +26,36 @@
  *
  * Causes sa11x0 to enter sleep state
  *
+ * Must be aligned to a cacheline.
  */
-
+	.balign	32
 ENTRY(sa1100_finish_suspend)
 	@ disable clock switching
 	mcr	p15, 0, r1, c15, c2, 2
 
-        @ Adjust memory timing before lowering CPU clock
-	@ Clock speed adjustment without changing memory timing makes
-	@ CPU hang in some cases
-        ldr     r0, =MDREFR
-        ldr     r1, [r0]
-        orr     r1, r1, #MDREFR_K1DB2
-        str     r1, [r0]
+	ldr	r6, =MDREFR
+	ldr	r4, [r6]
+	orr     r4, r4, #MDREFR_K1DB2
+	ldr	r5, =PPCR
+
+	@ Pre-load __udelay into the I-cache
+	mov	r0, #1
+	bl	__udelay
+	mov	r0, r0
+
+	@ The following must all exist in a single cache line to
+	@ avoid accessing memory until this sequence is complete,
+	@ otherwise we occasionally hang.
+
+	@ Adjust memory timing before lowering CPU clock
+	str     r4, [r6]
 
 	@ delay 90us and set CPU PLL to lowest speed
 	@ fixes resume problem on high speed SA1110
 	mov	r0, #90
 	bl	__udelay
-	ldr	r0, =PPCR
 	mov	r1, #0
-	str	r1, [r0]
+	str	r1, [r5]
 	mov	r0, #90
 	bl	__udelay
 
@@ -85,12 +94,10 @@ ENTRY(sa1100_finish_suspend)
 	bic	r5, r5, #FMsk(MSC_RT)
 	bic	r5, r5, #FMsk(MSC_RT)<<16
 
-	ldr	r6, =MDREFR
-
 	ldr	r7, [r6]
-bic	r7, r7, #0x0000FF00
-bic	r7, r7, #0x000000F0
-orr	r8, r7, #MDREFR_SLFRSH
+	bic	r7, r7, #0x0000FF00
+	bic	r7, r7, #0x000000F0
+	orr	r8, r7, #MDREFR_SLFRSH
 
 	ldr	r9, =MDCNFG
 	ldr	r10, [r9]
diff --git a/arch/arm/mach-sa1100/ssp.c b/arch/arm/mach-sa1100/ssp.c
index b20ff93b84a5..e22fca9ad5ec 100644
--- a/arch/arm/mach-sa1100/ssp.c
+++ b/arch/arm/mach-sa1100/ssp.c
@@ -19,8 +19,8 @@
 #include <linux/init.h>
 #include <linux/io.h>
 
-#include <asm/irq.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <asm/hardware/ssp.h>
 
 #define TIMEOUT 100000
diff --git a/arch/arm/mach-sa1100/time.c b/arch/arm/mach-sa1100/time.c
index 69e33535dee6..6af26e8d55e6 100644
--- a/arch/arm/mach-sa1100/time.c
+++ b/arch/arm/mach-sa1100/time.c
@@ -18,6 +18,7 @@
 #include <asm/mach/time.h>
 #include <asm/sched_clock.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 
 static u32 notrace sa1100_read_sched_clock(void)
 {
diff --git a/arch/arm/mach-shark/core.c b/arch/arm/mach-shark/core.c
index 6a2a7f2c2557..2704bcd869cd 100644
--- a/arch/arm/mach-shark/core.c
+++ b/arch/arm/mach-shark/core.c
@@ -15,6 +15,7 @@
 #include <asm/mach-types.h>
 #include <asm/leds.h>
 #include <asm/param.h>
+#include <asm/system_misc.h>
 
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-shark/include/mach/io.h b/arch/arm/mach-shark/include/mach/io.h
index 9ccbcecc430b..1a45fc01ff1d 100644
--- a/arch/arm/mach-shark/include/mach/io.h
+++ b/arch/arm/mach-shark/include/mach/io.h
@@ -15,6 +15,4 @@
 
 #define __io(a)                 ((void __iomem *)(0xe0000000 + (a)))
 
-#define __mem_pci(addr) (addr)
-
 #endif
diff --git a/arch/arm/mach-shark/leds.c b/arch/arm/mach-shark/leds.c
index ccd49189bbd0..25609076921f 100644
--- a/arch/arm/mach-shark/leds.c
+++ b/arch/arm/mach-shark/leds.c
@@ -23,7 +23,6 @@
 #include <linux/io.h>
 
 #include <asm/leds.h>
-#include <asm/system.h>
 
 #define LED_STATE_ENABLED	1
 #define LED_STATE_CLAIMED	2
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 060e5644c49c..34560cab45d9 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -100,6 +100,10 @@ config MACH_MARZEN
 
 comment "SH-Mobile System Configuration"
 
+config CPU_HAS_INTEVT
+        bool
+	default y
+
 menu "Memory configuration"
 
 config MEMORY_START
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index f50d7c8b1221..cb224a344af0 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -43,6 +43,7 @@
 #include <video/sh_mipi_dsi.h>
 #include <sound/sh_fsi.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
@@ -584,7 +585,7 @@ static void __init ag5evm_init(void)
 
 #ifdef CONFIG_CACHE_L2X0
 	/* Shared attribute override enable, 64K*8way */
-	l2x0_init(__io(0xf0100000), 0x00460000, 0xc2000fff);
+	l2x0_init(IOMEM(0xf0100000), 0x00460000, 0xc2000fff);
 #endif
 	sh73a0_add_standard_devices();
 	platform_add_devices(ag5evm_devices, ARRAY_SIZE(ag5evm_devices));
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 262f8def5577..b56dde2732bb 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -1186,6 +1186,7 @@ static struct i2c_board_info i2c1_devices[] = {
 	},
 };
 
+
 #define GPIO_PORT9CR	0xE6051009
 #define GPIO_PORT10CR	0xE605100A
 #define USCCR1		0xE6058144
diff --git a/arch/arm/mach-shmobile/board-bonito.c b/arch/arm/mach-shmobile/board-bonito.c
index 8b2124da245d..81fd95f7f52a 100644
--- a/arch/arm/mach-shmobile/board-bonito.c
+++ b/arch/arm/mach-shmobile/board-bonito.c
@@ -35,6 +35,7 @@
 #include <asm/mach/time.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <mach/r8a7740.h>
+#include <mach/irqs.h>
 #include <video/sh_mobile_lcdc.h>
 
 /*
@@ -370,7 +371,7 @@ static void __init bonito_init(void)
 
 #ifdef CONFIG_CACHE_L2X0
 	/* Early BRESP enable, Shared attribute override enable, 32K*8way */
-	l2x0_init(__io(0xf0002000), 0x40440000, 0x82000fff);
+	l2x0_init(IOMEM(0xf0002000), 0x40440000, 0x82000fff);
 #endif
 
 	r8a7740_add_standard_devices();
diff --git a/arch/arm/mach-shmobile/board-g3evm.c b/arch/arm/mach-shmobile/board-g3evm.c
index b627e89037f5..39b6cf85ced6 100644
--- a/arch/arm/mach-shmobile/board-g3evm.c
+++ b/arch/arm/mach-shmobile/board-g3evm.c
@@ -33,6 +33,7 @@
 #include <linux/input.h>
 #include <linux/input/sh_keysc.h>
 #include <linux/dma-mapping.h>
+#include <mach/irqs.h>
 #include <mach/sh7367.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-shmobile/board-g4evm.c b/arch/arm/mach-shmobile/board-g4evm.c
index 46d757d2759d..0e5a39c670bc 100644
--- a/arch/arm/mach-shmobile/board-g4evm.c
+++ b/arch/arm/mach-shmobile/board-g4evm.c
@@ -34,6 +34,7 @@
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/gpio.h>
 #include <linux/dma-mapping.h>
+#include <mach/irqs.h>
 #include <mach/sh7377.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-shmobile/board-kota2.c b/arch/arm/mach-shmobile/board-kota2.c
index 61c067294660..200dcd42a3a0 100644
--- a/arch/arm/mach-shmobile/board-kota2.c
+++ b/arch/arm/mach-shmobile/board-kota2.c
@@ -39,6 +39,7 @@
 #include <linux/mfd/tmio.h>
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
@@ -507,7 +508,7 @@ static void __init kota2_init(void)
 
 #ifdef CONFIG_CACHE_L2X0
 	/* Early BRESP enable, Shared attribute override enable, 64K*8way */
-	l2x0_init(__io(0xf0100000), 0x40460000, 0x82000fff);
+	l2x0_init(IOMEM(0xf0100000), 0x40460000, 0x82000fff);
 #endif
 	sh73a0_add_standard_devices();
 	platform_add_devices(kota2_devices, ARRAY_SIZE(kota2_devices));
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index bd4253ba05b6..f49e28abe0ab 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -39,6 +39,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
+#include <linux/mtd/sh_flctl.h>
 #include <linux/pm_clock.h>
 #include <linux/smsc911x.h>
 #include <linux/sh_intc.h>
@@ -54,6 +55,7 @@
 #include <sound/sh_fsi.h>
 
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <mach/sh7372.h>
 
 #include <asm/mach/arch.h>
@@ -955,6 +957,50 @@ static struct platform_device fsi_ak4643_device = {
 	},
 };
 
+/* FLCTL */
+static struct mtd_partition nand_partition_info[] = {
+	{
+		.name	= "system",
+		.offset	= 0,
+		.size	= 128 * 1024 * 1024,
+	},
+	{
+		.name	= "userdata",
+		.offset	= MTDPART_OFS_APPEND,
+		.size	= 256 * 1024 * 1024,
+	},
+	{
+		.name	= "cache",
+		.offset	= MTDPART_OFS_APPEND,
+		.size	= 128 * 1024 * 1024,
+	},
+};
+
+static struct resource nand_flash_resources[] = {
+	[0] = {
+		.start	= 0xe6a30000,
+		.end	= 0xe6a3009b,
+		.flags	= IORESOURCE_MEM,
+	}
+};
+
+static struct sh_flctl_platform_data nand_flash_data = {
+	.parts		= nand_partition_info,
+	.nr_parts	= ARRAY_SIZE(nand_partition_info),
+	.flcmncr_val	= CLK_16B_12L_4H | TYPESEL_SET
+			| SHBUSSEL | SEL_16BIT | SNAND_E,
+	.use_holden	= 1,
+};
+
+static struct platform_device nand_flash_device = {
+	.name		= "sh_flctl",
+	.resource	= nand_flash_resources,
+	.num_resources	= ARRAY_SIZE(nand_flash_resources),
+	.dev		= {
+		.platform_data = &nand_flash_data,
+	},
+};
+
 /*
  * The card detect pin of the top SD/MMC slot (CN7) is active low and is
  * connected to GPIO A22 of SH7372 (GPIO_PORT41).
@@ -1258,6 +1304,7 @@ static struct platform_device *mackerel_devices[] __initdata = {
 	&fsi_device,
 	&fsi_ak4643_device,
 	&fsi_hdmi_device,
+	&nand_flash_device,
 	&sdhi0_device,
 #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
 	&sdhi1_device,
@@ -1327,15 +1374,6 @@ static struct i2c_board_info i2c1_devices[] = {
 	},
 };
 
-static void __init mackerel_map_io(void)
-{
-	sh7372_map_io();
-	/* DMA memory at 0xff200000 - 0xffdfffff. The default 2MB size isn't
-	 * enough to allocate the frame buffer memory.
-	 */
-	init_consistent_dma_size(12 << 20);
-}
-
 #define GPIO_PORT9CR	0xE6051009
 #define GPIO_PORT10CR	0xE605100A
 #define GPIO_PORT167CR	0xE60520A7
@@ -1496,6 +1534,30 @@ static void __init mackerel_init(void)
 	gpio_request(GPIO_FN_MMCCMD0, NULL);
 	gpio_request(GPIO_FN_MMCCLK0, NULL);
 
+	/* FLCTL */
+	gpio_request(GPIO_FN_D0_NAF0, NULL);
+	gpio_request(GPIO_FN_D1_NAF1, NULL);
+	gpio_request(GPIO_FN_D2_NAF2, NULL);
+	gpio_request(GPIO_FN_D3_NAF3, NULL);
+	gpio_request(GPIO_FN_D4_NAF4, NULL);
+	gpio_request(GPIO_FN_D5_NAF5, NULL);
+	gpio_request(GPIO_FN_D6_NAF6, NULL);
+	gpio_request(GPIO_FN_D7_NAF7, NULL);
+	gpio_request(GPIO_FN_D8_NAF8, NULL);
+	gpio_request(GPIO_FN_D9_NAF9, NULL);
+	gpio_request(GPIO_FN_D10_NAF10, NULL);
+	gpio_request(GPIO_FN_D11_NAF11, NULL);
+	gpio_request(GPIO_FN_D12_NAF12, NULL);
+	gpio_request(GPIO_FN_D13_NAF13, NULL);
+	gpio_request(GPIO_FN_D14_NAF14, NULL);
+	gpio_request(GPIO_FN_D15_NAF15, NULL);
+	gpio_request(GPIO_FN_FCE0, NULL);
+	gpio_request(GPIO_FN_WE0_FWE, NULL);
+	gpio_request(GPIO_FN_FRB, NULL);
+	gpio_request(GPIO_FN_A4_FOE, NULL);
+	gpio_request(GPIO_FN_A5_FCDE, NULL);
+	gpio_request(GPIO_FN_RD_FSC, NULL);
+
 	/* enable GPS module (GT-720F) */
 	gpio_request(GPIO_FN_SCIFA2_TXD1, NULL);
 	gpio_request(GPIO_FN_SCIFA2_RXD1, NULL);
@@ -1540,6 +1602,7 @@ static void __init mackerel_init(void)
 	sh7372_add_device_to_domain(&sh7372_a4mp, &fsi_device);
 	sh7372_add_device_to_domain(&sh7372_a3sp, &usbhs0_device);
 	sh7372_add_device_to_domain(&sh7372_a3sp, &usbhs1_device);
+	sh7372_add_device_to_domain(&sh7372_a3sp, &nand_flash_device);
 	sh7372_add_device_to_domain(&sh7372_a3sp, &sh_mmcif_device);
 	sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi0_device);
 #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
@@ -1555,7 +1618,7 @@ static void __init mackerel_init(void)
 }
 
 MACHINE_START(MACKEREL, "mackerel")
-	.map_io		= mackerel_map_io,
+	.map_io		= sh7372_map_io,
 	.init_early	= sh7372_add_early_devices,
 	.init_irq	= sh7372_init_irq,
 	.handle_irq	= shmobile_handle_irq_intc,
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index cbd5e4cd06d2..ef0e13bf0b3a 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -31,6 +31,7 @@
 #include <mach/hardware.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index de243e3c8392..94d1f88246d3 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -511,7 +511,7 @@ enum { MSTP001, MSTP000,
        MSTP223,
        MSTP218, MSTP217, MSTP216, MSTP214, MSTP208, MSTP207,
        MSTP206, MSTP205, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
-       MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
+	MSTP328, MSTP323, MSTP322, MSTP315, MSTP314, MSTP313, MSTP312,
        MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP407, MSTP406,
        MSTP405, MSTP404, MSTP403, MSTP400,
        MSTP_NR };
@@ -553,6 +553,7 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, 0), /* FSI2 */
 	[MSTP323] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 23, 0), /* IIC1 */
 	[MSTP322] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 22, 0), /* USB0 */
+	[MSTP315] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 15, 0), /* FLCTL*/
 	[MSTP314] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 14, 0), /* SDHI0 */
 	[MSTP313] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 13, 0), /* SDHI1 */
 	[MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMC */
@@ -653,6 +654,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("r8a66597_hcd.0", &mstp_clks[MSTP322]), /* USB0 */
 	CLKDEV_DEV_ID("r8a66597_udc.0", &mstp_clks[MSTP322]), /* USB0 */
 	CLKDEV_DEV_ID("renesas_usbhs.0", &mstp_clks[MSTP322]), /* USB0 */
+	CLKDEV_DEV_ID("sh_flctl.0", &mstp_clks[MSTP315]), /* FLCTL */
 	CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP314]), /* SDHI0 */
 	CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */
 	CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMC */
diff --git a/arch/arm/mach-shmobile/cpuidle.c b/arch/arm/mach-shmobile/cpuidle.c
index 1b2334277e85..7e6559105d40 100644
--- a/arch/arm/mach-shmobile/cpuidle.c
+++ b/arch/arm/mach-shmobile/cpuidle.c
@@ -13,7 +13,7 @@
 #include <linux/suspend.h>
 #include <linux/module.h>
 #include <linux/err.h>
-#include <asm/system.h>
+#include <asm/cpuidle.h>
 #include <asm/io.h>
 
 static void shmobile_enter_wfi(void)
@@ -29,37 +29,19 @@ static int shmobile_cpuidle_enter(struct cpuidle_device *dev,
 				  struct cpuidle_driver *drv,
 				  int index)
 {
-	ktime_t before, after;
-
-	before = ktime_get();
-
-	local_irq_disable();
-	local_fiq_disable();
-
 	shmobile_cpuidle_modes[index]();
 
-	local_irq_enable();
-	local_fiq_enable();
-
-	after = ktime_get();
-	dev->last_residency = ktime_to_ns(ktime_sub(after, before)) >> 10;
-
 	return index;
 }
 
 static struct cpuidle_device shmobile_cpuidle_dev;
 static struct cpuidle_driver shmobile_cpuidle_driver = {
-	.name =		"shmobile_cpuidle",
-	.owner =	THIS_MODULE,
-	.states[0] = {
-		.name = "C1",
-		.desc = "WFI",
-		.exit_latency = 1,
-		.target_residency = 1 * 2,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
-	},
-	.safe_state_index = 0, /* C1 */
-	.state_count = 1,
+	.name			= "shmobile_cpuidle",
+	.owner			= THIS_MODULE,
+	.en_core_tk_irqen	= 1,
+	.states[0]		= ARM_CPUIDLE_WFI_STATE,
+	.safe_state_index	= 0, /* C1 */
+	.state_count		= 1,
 };
 
 void (*shmobile_cpuidle_setup)(struct cpuidle_driver *drv);
diff --git a/arch/arm/mach-shmobile/include/mach/io.h b/arch/arm/mach-shmobile/include/mach/io.h
deleted file mode 100644
index 7339fe46cb7c..000000000000
--- a/arch/arm/mach-shmobile/include/mach/io.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_MACH_IO_H
-#define __ASM_MACH_IO_H
-
-#define IO_SPACE_LIMIT		0xffffffff
-
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
-
-#endif /* __ASM_MACH_IO_H */
diff --git a/arch/arm/mach-shmobile/include/mach/irqs.h b/arch/arm/mach-shmobile/include/mach/irqs.h
index dcb714f4d75a..4e686cc201fc 100644
--- a/arch/arm/mach-shmobile/include/mach/irqs.h
+++ b/arch/arm/mach-shmobile/include/mach/irqs.h
@@ -1,15 +1,11 @@
 #ifndef __ASM_MACH_IRQS_H
 #define __ASM_MACH_IRQS_H
 
-#define NR_IRQS         1024
+#include <linux/sh_intc.h>
 
 /* GIC */
 #define gic_spi(nr)		((nr) + 32)
 
-/* INTCA */
-#define evt2irq(evt)		(((evt) >> 5) - 16)
-#define irq2evt(irq)		(((irq) + 16) << 5)
-
 /* INTCS */
 #define INTCS_VECT_BASE		0x2200
 #define INTCS_VECT(n, vect)	INTC_VECT((n), INTCS_VECT_BASE + (vect))
diff --git a/arch/arm/mach-shmobile/include/mach/system.h b/arch/arm/mach-shmobile/include/mach/system.h
index 3bbcb3fa0775..540eaff08f34 100644
--- a/arch/arm/mach-shmobile/include/mach/system.h
+++ b/arch/arm/mach-shmobile/include/mach/system.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_ARCH_SYSTEM_H
 #define __ASM_ARCH_SYSTEM_H
 
+#include <asm/system_misc.h>
+
 static inline void arch_reset(char mode, const char *cmd)
 {
 	soft_restart(0);
diff --git a/arch/arm/mach-shmobile/intc-r8a7740.c b/arch/arm/mach-shmobile/intc-r8a7740.c
index 272c84c20c83..09c42afcb22d 100644
--- a/arch/arm/mach-shmobile/intc-r8a7740.c
+++ b/arch/arm/mach-shmobile/intc-r8a7740.c
@@ -25,6 +25,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-shmobile/intc-r8a7779.c b/arch/arm/mach-shmobile/intc-r8a7779.c
index 5d92fcde2bc3..550b23df4fd4 100644
--- a/arch/arm/mach-shmobile/intc-r8a7779.c
+++ b/arch/arm/mach-shmobile/intc-r8a7779.c
@@ -42,8 +42,8 @@ static int r8a7779_set_wake(struct irq_data *data, unsigned int on)
 
 void __init r8a7779_init_irq(void)
 {
-	void __iomem *gic_dist_base = __io(0xf0001000);
-	void __iomem *gic_cpu_base = __io(0xf0000100);
+	void __iomem *gic_dist_base = IOMEM(0xf0001000);
+	void __iomem *gic_cpu_base = IOMEM(0xf0000100);
 
 	/* use GIC to handle interrupts */
 	gic_init(0, 29, gic_dist_base, gic_cpu_base);
diff --git a/arch/arm/mach-shmobile/intc-sh7367.c b/arch/arm/mach-shmobile/intc-sh7367.c
index cfde9bfc3669..5bf776495b75 100644
--- a/arch/arm/mach-shmobile/intc-sh7367.c
+++ b/arch/arm/mach-shmobile/intc-sh7367.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-shmobile/intc-sh7372.c b/arch/arm/mach-shmobile/intc-sh7372.c
index 89afcaba99a1..6447e0af52d4 100644
--- a/arch/arm/mach-shmobile/intc-sh7372.c
+++ b/arch/arm/mach-shmobile/intc-sh7372.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-shmobile/intc-sh7377.c b/arch/arm/mach-shmobile/intc-sh7377.c
index 2af4e6e9bc5b..b84a460a3405 100644
--- a/arch/arm/mach-shmobile/intc-sh7377.c
+++ b/arch/arm/mach-shmobile/intc-sh7377.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c
index 9857595eaa79..ee447404c857 100644
--- a/arch/arm/mach-shmobile/intc-sh73a0.c
+++ b/arch/arm/mach-shmobile/intc-sh73a0.c
@@ -24,6 +24,7 @@
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <asm/hardware/gic.h>
 #include <asm/mach-types.h>
@@ -420,8 +421,8 @@ static irqreturn_t sh73a0_pint1_demux(int irq, void *dev_id)
 
 void __init sh73a0_init_irq(void)
 {
-	void __iomem *gic_dist_base = __io(0xf0001000);
-	void __iomem *gic_cpu_base = __io(0xf0000100);
+	void __iomem *gic_dist_base = IOMEM(0xf0001000);
+	void __iomem *gic_cpu_base = IOMEM(0xf0000100);
 	void __iomem *intevtsa = ioremap_nocache(0xffd20100, PAGE_SIZE);
 	int k, n;
 
diff --git a/arch/arm/mach-shmobile/pm-r8a7779.c b/arch/arm/mach-shmobile/pm-r8a7779.c
index c38ba7b43ef8..a18a4ae16d2b 100644
--- a/arch/arm/mach-shmobile/pm-r8a7779.c
+++ b/arch/arm/mach-shmobile/pm-r8a7779.c
@@ -18,7 +18,6 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/console.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <mach/common.h>
 #include <mach/r8a7779.h>
diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c
index fcf8b1761aef..a3bdb12acde9 100644
--- a/arch/arm/mach-shmobile/pm-sh7372.c
+++ b/arch/arm/mach-shmobile/pm-sh7372.c
@@ -21,7 +21,6 @@
 #include <linux/irq.h>
 #include <linux/bitrev.h>
 #include <linux/console.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/tlbflush.h>
 #include <asm/suspend.h>
diff --git a/arch/arm/mach-shmobile/setup-r8a7740.c b/arch/arm/mach-shmobile/setup-r8a7740.c
index 74e52341dd1b..14edb5cffa7f 100644
--- a/arch/arm/mach-shmobile/setup-r8a7740.c
+++ b/arch/arm/mach-shmobile/setup-r8a7740.c
@@ -26,6 +26,7 @@
 #include <linux/sh_timer.h>
 #include <mach/r8a7740.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c
index 6820d785493d..12c6f529ab89 100644
--- a/arch/arm/mach-shmobile/setup-r8a7779.c
+++ b/arch/arm/mach-shmobile/setup-r8a7779.c
@@ -29,6 +29,7 @@
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-shmobile/setup-sh7367.c b/arch/arm/mach-shmobile/setup-sh7367.c
index a51e1a1e6996..2e3074ab75b3 100644
--- a/arch/arm/mach-shmobile/setup-sh7367.c
+++ b/arch/arm/mach-shmobile/setup-sh7367.c
@@ -30,6 +30,7 @@
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c
index 5375325d7ca7..2fe8f83ca124 100644
--- a/arch/arm/mach-shmobile/setup-sh7372.c
+++ b/arch/arm/mach-shmobile/setup-sh7372.c
@@ -31,7 +31,9 @@
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <linux/pm_domain.h>
+#include <linux/dma-mapping.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh7372.h>
 #include <mach/common.h>
 #include <asm/mach/map.h>
@@ -54,6 +56,12 @@ static struct map_desc sh7372_io_desc[] __initdata = {
 void __init sh7372_map_io(void)
 {
 	iotable_init(sh7372_io_desc, ARRAY_SIZE(sh7372_io_desc));
+
+	/*
+	 * DMA memory at 0xff200000 - 0xffdfffff. The default 2MB size isn't
+	 * enough to allocate the frame buffer memory.
+	 */
+	init_consistent_dma_size(12 << 20);
 }
 
 /* SCIFA0 */
diff --git a/arch/arm/mach-shmobile/setup-sh7377.c b/arch/arm/mach-shmobile/setup-sh7377.c
index 9f146095098b..d576a6abbade 100644
--- a/arch/arm/mach-shmobile/setup-sh7377.c
+++ b/arch/arm/mach-shmobile/setup-sh7377.c
@@ -32,6 +32,7 @@
 #include <mach/hardware.h>
 #include <mach/common.h>
 #include <asm/mach/map.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index b6a0734a738e..5bebffc10455 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -31,6 +31,7 @@
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c
index 9bb7b8575a1f..b62e19d4c9af 100644
--- a/arch/arm/mach-shmobile/smp-r8a7779.c
+++ b/arch/arm/mach-shmobile/smp-r8a7779.c
@@ -30,7 +30,7 @@
 #include <asm/smp_twd.h>
 #include <asm/hardware/gic.h>
 
-#define AVECR 0xfe700040
+#define AVECR IOMEM(0xfe700040)
 
 static struct r8a7779_pm_ch r8a7779_ch_cpu1 = {
 	.chan_offs = 0x40, /* PWRSR0 .. PWRER0 */
@@ -138,7 +138,7 @@ void __init r8a7779_smp_prepare_cpus(void)
 	scu_enable(scu_base_addr());
 
 	/* Map the reset vector (in headsmp.S) */
-	__raw_writel(__pa(shmobile_secondary_vector), __io(AVECR));
+	__raw_writel(__pa(shmobile_secondary_vector), AVECR);
 
 	/* enable cache coherency on CPU0 */
 	modify_scu_cpu_psr(0, 3 << (cpu * 8));
diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c
index c0a9093ba3a8..14ad8b052f1a 100644
--- a/arch/arm/mach-shmobile/smp-sh73a0.c
+++ b/arch/arm/mach-shmobile/smp-sh73a0.c
@@ -28,11 +28,11 @@
 #include <asm/smp_twd.h>
 #include <asm/hardware/gic.h>
 
-#define WUPCR		0xe6151010
-#define SRESCR		0xe6151018
-#define PSTR		0xe6151040
-#define SBAR            0xe6180020
-#define APARMBAREA      0xe6f10020
+#define WUPCR		IOMEM(0xe6151010)
+#define SRESCR		IOMEM(0xe6151018)
+#define PSTR		IOMEM(0xe6151040)
+#define SBAR		IOMEM(0xe6180020)
+#define APARMBAREA	IOMEM(0xe6f10020)
 
 static void __iomem *scu_base_addr(void)
 {
@@ -78,10 +78,10 @@ int __cpuinit sh73a0_boot_secondary(unsigned int cpu)
 	/* enable cache coherency */
 	modify_scu_cpu_psr(0, 3 << (cpu * 8));
 
-	if (((__raw_readl(__io(PSTR)) >> (4 * cpu)) & 3) == 3)
-		__raw_writel(1 << cpu, __io(WUPCR));	/* wake up */
+	if (((__raw_readl(PSTR) >> (4 * cpu)) & 3) == 3)
+		__raw_writel(1 << cpu, WUPCR);	/* wake up */
 	else
-		__raw_writel(1 << cpu, __io(SRESCR));	/* reset */
+		__raw_writel(1 << cpu, SRESCR);	/* reset */
 
 	return 0;
 }
@@ -93,8 +93,8 @@ void __init sh73a0_smp_prepare_cpus(void)
 	scu_enable(scu_base_addr());
 
 	/* Map the reset vector (in headsmp.S) */
-	__raw_writel(0, __io(APARMBAREA));      /* 4k */
-	__raw_writel(__pa(shmobile_secondary_vector), __io(SBAR));
+	__raw_writel(0, APARMBAREA);      /* 4k */
+	__raw_writel(__pa(shmobile_secondary_vector), SBAR);
 
 	/* enable cache coherency on CPU0 */
 	modify_scu_cpu_psr(0, 3 << (cpu * 8));
diff --git a/arch/arm/mach-shmobile/suspend.c b/arch/arm/mach-shmobile/suspend.c
index c1febe13f709..4d1b86a49923 100644
--- a/arch/arm/mach-shmobile/suspend.c
+++ b/arch/arm/mach-shmobile/suspend.c
@@ -12,8 +12,8 @@
 #include <linux/suspend.h>
 #include <linux/module.h>
 #include <linux/err.h>
-#include <asm/system.h>
 #include <asm/io.h>
+#include <asm/system_misc.h>
 
 static int shmobile_suspend_default_enter(suspend_state_t suspend_state)
 {
diff --git a/arch/arm/mach-spear3xx/clock.c b/arch/arm/mach-spear3xx/clock.c
index f67860cd649f..6c4841f55223 100644
--- a/arch/arm/mach-spear3xx/clock.c
+++ b/arch/arm/mach-spear3xx/clock.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <asm/mach-types.h>
 #include <plat/clock.h>
diff --git a/arch/arm/mach-spear3xx/include/mach/io.h b/arch/arm/mach-spear3xx/include/mach/io.h
deleted file mode 100644
index 30cff8a1f6b5..000000000000
--- a/arch/arm/mach-spear3xx/include/mach/io.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * arch/arm/mach-spear3xx/include/mach/io.h
- *
- * IO definitions for SPEAr3xx machine family
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar<viresh.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#include <plat/io.h>
-
-#endif /* __MACH_IO_H */
diff --git a/arch/arm/mach-spear6xx/Kconfig b/arch/arm/mach-spear6xx/Kconfig
index ff4ae5ba00f1..fbe298bd1d92 100644
--- a/arch/arm/mach-spear6xx/Kconfig
+++ b/arch/arm/mach-spear6xx/Kconfig
@@ -5,11 +5,12 @@
 if ARCH_SPEAR6XX
 
 menu "SPEAr6xx Implementations"
-config BOARD_SPEAR600_EVB
-	bool "SPEAr600 Evaluation Board"
+config BOARD_SPEAR600_DT
+	bool "SPEAr600 generic board configured via device-tree"
 	select MACH_SPEAR600
+	select USE_OF
 	help
-	  Supports ST SPEAr600 Evaluation Board
+	  Supports ST SPEAr600 boards configured via the device-tree
 
 endmenu
 
diff --git a/arch/arm/mach-spear6xx/Makefile b/arch/arm/mach-spear6xx/Makefile
index cc1a4d82d459..76e5750552fc 100644
--- a/arch/arm/mach-spear6xx/Makefile
+++ b/arch/arm/mach-spear6xx/Makefile
@@ -4,9 +4,3 @@
 
 # common files
 obj-y	+= clock.o spear6xx.o
-
-# spear600 specific files
-obj-$(CONFIG_MACH_SPEAR600) += spear600.o
-
-# spear600 boards files
-obj-$(CONFIG_BOARD_SPEAR600_EVB) += spear600_evb.o
diff --git a/arch/arm/mach-spear6xx/clock.c b/arch/arm/mach-spear6xx/clock.c
index ac70e0d88fef..a86499a8a15f 100644
--- a/arch/arm/mach-spear6xx/clock.c
+++ b/arch/arm/mach-spear6xx/clock.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <plat/clock.h>
 #include <mach/misc_regs.h>
@@ -641,8 +642,8 @@ static struct clk_lookup spear_clk_lookups[] = {
 	{ .con_id = "gpt0_synth_clk",	.clk = &gpt0_synth_clk},
 	{ .con_id = "gpt2_synth_clk",	.clk = &gpt2_synth_clk},
 	{ .con_id = "gpt3_synth_clk",	.clk = &gpt3_synth_clk},
-	{ .dev_id = "uart0",		.clk = &uart0_clk},
-	{ .dev_id = "uart1",		.clk = &uart1_clk},
+	{ .dev_id = "d0000000.serial",	.clk = &uart0_clk},
+	{ .dev_id = "d0080000.serial",	.clk = &uart1_clk},
 	{ .dev_id = "firda",		.clk = &firda_clk},
 	{ .dev_id = "clcd",		.clk = &clcd_clk},
 	{ .dev_id = "gpt0",		.clk = &gpt0_clk},
@@ -655,20 +656,20 @@ static struct clk_lookup spear_clk_lookups[] = {
 	{ .con_id = "usbh.1_clk",	.clk = &usbh1_clk},
 	/* clock derived from ahb clk */
 	{ .con_id = "apb_clk",		.clk = &apb_clk},
-	{ .dev_id = "i2c_designware.0",	.clk = &i2c_clk},
+	{ .dev_id = "d0200000.i2c",	.clk = &i2c_clk},
 	{ .dev_id = "dma",		.clk = &dma_clk},
 	{ .dev_id = "jpeg",		.clk = &jpeg_clk},
 	{ .dev_id = "gmac",		.clk = &gmac_clk},
 	{ .dev_id = "smi",		.clk = &smi_clk},
-	{ .con_id = "fsmc",		.clk = &fsmc_clk},
+	{ .dev_id = "fsmc-nand",	.clk = &fsmc_clk},
 	/* clock derived from apb clk */
 	{ .dev_id = "adc",		.clk = &adc_clk},
 	{ .dev_id = "ssp-pl022.0",	.clk = &ssp0_clk},
 	{ .dev_id = "ssp-pl022.1",	.clk = &ssp1_clk},
 	{ .dev_id = "ssp-pl022.2",	.clk = &ssp2_clk},
-	{ .dev_id = "gpio0",		.clk = &gpio0_clk},
-	{ .dev_id = "gpio1",		.clk = &gpio1_clk},
-	{ .dev_id = "gpio2",		.clk = &gpio2_clk},
+	{ .dev_id = "f0100000.gpio",	.clk = &gpio0_clk},
+	{ .dev_id = "fc980000.gpio",	.clk = &gpio1_clk},
+	{ .dev_id = "d8100000.gpio",	.clk = &gpio2_clk},
 };
 
 void __init spear6xx_clk_init(void)
diff --git a/arch/arm/mach-spear6xx/include/mach/io.h b/arch/arm/mach-spear6xx/include/mach/io.h
deleted file mode 100644
index fb7c106cea94..000000000000
--- a/arch/arm/mach-spear6xx/include/mach/io.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * arch/arm/mach-spear6xx/include/mach/io.h
- *
- * IO definitions for SPEAr6xx machine family
- *
- * Copyright (C) 2009 ST Microelectronics
- * Rajeev Kumar Kumar<rajeev-dlh.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#include <plat/io.h>
-
-#endif	/* __MACH_IO_H */
-
diff --git a/arch/arm/mach-spear6xx/spear600.c b/arch/arm/mach-spear6xx/spear600.c
deleted file mode 100644
index d0e6eeae9b04..000000000000
--- a/arch/arm/mach-spear6xx/spear600.c
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * arch/arm/mach-spear6xx/spear600.c
- *
- * SPEAr600 machine source file
- *
- * Copyright (C) 2009 ST Microelectronics
- * Rajeev Kumar<rajeev-dlh.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/ptrace.h>
-#include <asm/irq.h>
-#include <mach/generic.h>
-#include <mach/hardware.h>
-
-/* Add spear600 specific devices here */
-
-void __init spear600_init(void)
-{
-	/* call spear6xx family common init function */
-	spear6xx_init();
-}
diff --git a/arch/arm/mach-spear6xx/spear600_evb.c b/arch/arm/mach-spear6xx/spear600_evb.c
deleted file mode 100644
index c6e4254741cc..000000000000
--- a/arch/arm/mach-spear6xx/spear600_evb.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * arch/arm/mach-spear6xx/spear600_evb.c
- *
- * SPEAr600 evaluation board source file
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar<viresh.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <asm/hardware/vic.h>
-#include <asm/mach/arch.h>
-#include <asm/mach-types.h>
-#include <mach/generic.h>
-#include <mach/hardware.h>
-
-static struct amba_device *amba_devs[] __initdata = {
-	&gpio_device[0],
-	&gpio_device[1],
-	&gpio_device[2],
-	&uart_device[0],
-	&uart_device[1],
-};
-
-static struct platform_device *plat_devs[] __initdata = {
-};
-
-static void __init spear600_evb_init(void)
-{
-	unsigned int i;
-
-	/* call spear600 machine init function */
-	spear600_init();
-
-	/* Add Platform Devices */
-	platform_add_devices(plat_devs, ARRAY_SIZE(plat_devs));
-
-	/* Add Amba Devices */
-	for (i = 0; i < ARRAY_SIZE(amba_devs); i++)
-		amba_device_register(amba_devs[i], &iomem_resource);
-}
-
-MACHINE_START(SPEAR600, "ST-SPEAR600-EVB")
-	.atag_offset	=	0x100,
-	.map_io		=	spear6xx_map_io,
-	.init_irq	=	spear6xx_init_irq,
-	.handle_irq	=	vic_handle_irq,
-	.timer		=	&spear6xx_timer,
-	.init_machine	=	spear600_evb_init,
-	.restart	=	spear_restart,
-MACHINE_END
diff --git a/arch/arm/mach-spear6xx/spear6xx.c b/arch/arm/mach-spear6xx/spear6xx.c
index b997b1b10ba0..2ed8b14c82c8 100644
--- a/arch/arm/mach-spear6xx/spear6xx.c
+++ b/arch/arm/mach-spear6xx/spear6xx.c
@@ -6,111 +6,21 @@
  * Copyright (C) 2009 ST Microelectronics
  * Rajeev Kumar<rajeev-dlh.kumar@st.com>
  *
+ * Copyright 2012 Stefan Roese <sr@denx.de>
+ *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
  */
 
-#include <linux/types.h>
-#include <linux/amba/pl061.h>
-#include <linux/ptrace.h>
-#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
 #include <asm/hardware/vic.h>
-#include <asm/irq.h>
 #include <asm/mach/arch.h>
 #include <mach/generic.h>
 #include <mach/hardware.h>
-#include <mach/irqs.h>
-
-/* Add spear6xx machines common devices here */
-/* uart device registration */
-struct amba_device uart_device[] = {
-	{
-		.dev = {
-			.init_name = "uart0",
-		},
-		.res = {
-			.start = SPEAR6XX_ICM1_UART0_BASE,
-			.end = SPEAR6XX_ICM1_UART0_BASE + SZ_4K - 1,
-			.flags = IORESOURCE_MEM,
-		},
-		.irq = {IRQ_UART_0},
-	}, {
-		.dev = {
-			.init_name = "uart1",
-		},
-		.res = {
-			.start = SPEAR6XX_ICM1_UART1_BASE,
-			.end = SPEAR6XX_ICM1_UART1_BASE + SZ_4K - 1,
-			.flags = IORESOURCE_MEM,
-		},
-		.irq = {IRQ_UART_1},
-	}
-};
-
-/* gpio device registration */
-static struct pl061_platform_data gpio_plat_data[] = {
-	{
-		.gpio_base	= 0,
-		.irq_base	= SPEAR_GPIO0_INT_BASE,
-	}, {
-		.gpio_base	= 8,
-		.irq_base	= SPEAR_GPIO1_INT_BASE,
-	}, {
-		.gpio_base	= 16,
-		.irq_base	= SPEAR_GPIO2_INT_BASE,
-	},
-};
-
-struct amba_device gpio_device[] = {
-	{
-		.dev = {
-			.init_name = "gpio0",
-			.platform_data = &gpio_plat_data[0],
-		},
-		.res = {
-			.start = SPEAR6XX_CPU_GPIO_BASE,
-			.end = SPEAR6XX_CPU_GPIO_BASE + SZ_4K - 1,
-			.flags = IORESOURCE_MEM,
-		},
-		.irq = {IRQ_LOCAL_GPIO},
-	}, {
-		.dev = {
-			.init_name = "gpio1",
-			.platform_data = &gpio_plat_data[1],
-		},
-		.res = {
-			.start = SPEAR6XX_ICM3_GPIO_BASE,
-			.end = SPEAR6XX_ICM3_GPIO_BASE + SZ_4K - 1,
-			.flags = IORESOURCE_MEM,
-		},
-		.irq = {IRQ_BASIC_GPIO},
-	}, {
-		.dev = {
-			.init_name = "gpio2",
-			.platform_data = &gpio_plat_data[2],
-		},
-		.res = {
-			.start = SPEAR6XX_ICM2_GPIO_BASE,
-			.end = SPEAR6XX_ICM2_GPIO_BASE + SZ_4K - 1,
-			.flags = IORESOURCE_MEM,
-		},
-		.irq = {IRQ_APPL_GPIO},
-	}
-};
-
-/* This will add devices, and do machine specific tasks */
-void __init spear6xx_init(void)
-{
-	/* nothing to do for now */
-}
-
-/* This will initialize vic */
-void __init spear6xx_init_irq(void)
-{
-	vic_init((void __iomem *)VA_SPEAR6XX_CPU_VIC_PRI_BASE, 0, ~0, 0);
-	vic_init((void __iomem *)VA_SPEAR6XX_CPU_VIC_SEC_BASE, 32, ~0, 0);
-}
 
 /* Following will create static virtual/physical mappings */
 static struct map_desc spear6xx_io_desc[] __initdata = {
@@ -181,3 +91,33 @@ static void __init spear6xx_timer_init(void)
 struct sys_timer spear6xx_timer = {
 	.init = spear6xx_timer_init,
 };
+
+static void __init spear600_dt_init(void)
+{
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
+
+static const char *spear600_dt_board_compat[] = {
+	"st,spear600",
+	NULL
+};
+
+static const struct of_device_id vic_of_match[] __initconst = {
+	{ .compatible = "arm,pl190-vic", .data = vic_of_init, },
+	{ /* Sentinel */ }
+};
+
+static void __init spear6xx_dt_init_irq(void)
+{
+	of_irq_init(vic_of_match);
+}
+
+DT_MACHINE_START(SPEAR600_DT, "ST SPEAr600 (Flattened Device Tree)")
+	.map_io		=	spear6xx_map_io,
+	.init_irq	=	spear6xx_dt_init_irq,
+	.handle_irq	=	vic_handle_irq,
+	.timer		=	&spear6xx_timer,
+	.init_machine	=	spear600_dt_init,
+	.restart	=	spear_restart,
+	.dt_compat	=	spear600_dt_board_compat,
+MACHINE_END
diff --git a/arch/arm/mach-tegra/Makefile b/arch/arm/mach-tegra/Makefile
index 1dd2726986cf..d87d968115ec 100644
--- a/arch/arm/mach-tegra/Makefile
+++ b/arch/arm/mach-tegra/Makefile
@@ -8,6 +8,7 @@ obj-y                                   += timer.o
 obj-y                                   += pinmux.o
 obj-y					+= fuse.o
 obj-y					+= pmc.o
+obj-y					+= flowctrl.o
 obj-$(CONFIG_CPU_IDLE)			+= cpuidle.o
 obj-$(CONFIG_CPU_IDLE)			+= sleep.o
 obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= powergate.o
@@ -18,6 +19,7 @@ obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= pinmux-tegra30-tables.o
 obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= board-dt-tegra30.o
 obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= tegra30_clocks.o
 obj-$(CONFIG_SMP)			+= platsmp.o headsmp.o
+obj-$(CONFIG_SMP)                       += reset.o
 obj-$(CONFIG_HOTPLUG_CPU)               += hotplug.o
 obj-$(CONFIG_TEGRA_SYSTEM_DMA)		+= dma.o apbio.o
 obj-$(CONFIG_CPU_FREQ)                  += cpu-tegra.o
diff --git a/arch/arm/mach-tegra/board-dt-tegra20.c b/arch/arm/mach-tegra/board-dt-tegra20.c
index e20b419d5983..0952494f481a 100644
--- a/arch/arm/mach-tegra/board-dt-tegra20.c
+++ b/arch/arm/mach-tegra/board-dt-tegra20.c
@@ -68,11 +68,11 @@ struct of_dev_auxdata tegra20_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("nvidia,tegra20-i2s", TEGRA_I2S2_BASE, "tegra-i2s.1", NULL),
 	OF_DEV_AUXDATA("nvidia,tegra20-das", TEGRA_APB_MISC_DAS_BASE, "tegra-das", NULL),
 	OF_DEV_AUXDATA("nvidia,tegra20-ehci", TEGRA_USB_BASE, "tegra-ehci.0",
-		       &tegra_ehci1_device.dev.platform_data),
+		       &tegra_ehci1_pdata),
 	OF_DEV_AUXDATA("nvidia,tegra20-ehci", TEGRA_USB2_BASE, "tegra-ehci.1",
-		       &tegra_ehci2_device.dev.platform_data),
+		       &tegra_ehci2_pdata),
 	OF_DEV_AUXDATA("nvidia,tegra20-ehci", TEGRA_USB3_BASE, "tegra-ehci.2",
-		       &tegra_ehci3_device.dev.platform_data),
+		       &tegra_ehci3_pdata),
 	{}
 };
 
diff --git a/arch/arm/mach-tegra/board-dt-tegra30.c b/arch/arm/mach-tegra/board-dt-tegra30.c
index 96f6c0d030bd..5f7c03e972f3 100644
--- a/arch/arm/mach-tegra/board-dt-tegra30.c
+++ b/arch/arm/mach-tegra/board-dt-tegra30.c
@@ -56,7 +56,7 @@ struct of_dev_auxdata tegra30_auxdata_lookup[] __initdata = {
 
 static __initdata struct tegra_clk_init_table tegra_dt_clk_init_table[] = {
 	/* name		parent		rate		enabled */
-	{ "uartd",	"pll_p",	408000000,	true },
+	{ "uarta",	"pll_p",	408000000,	true },
 	{ NULL,		NULL,		0,		0},
 };
 
diff --git a/arch/arm/mach-tegra/common.c b/arch/arm/mach-tegra/common.c
index 2f86fcca64a6..22df10fb9972 100644
--- a/arch/arm/mach-tegra/common.c
+++ b/arch/arm/mach-tegra/common.c
@@ -27,6 +27,7 @@
 #include <asm/hardware/gic.h>
 
 #include <mach/iomap.h>
+#include <mach/powergate.h>
 
 #include "board.h"
 #include "clock.h"
@@ -118,13 +119,16 @@ void __init tegra20_init_early(void)
 	tegra_clk_init_from_table(tegra20_clk_init_table);
 	tegra_init_cache(0x331, 0x441);
 	tegra_pmc_init();
+	tegra_powergate_init();
 }
 #endif
 #ifdef CONFIG_ARCH_TEGRA_3x_SOC
 void __init tegra30_init_early(void)
 {
+	tegra_init_fuse();
 	tegra30_init_clocks();
 	tegra_init_cache(0x441, 0x551);
 	tegra_pmc_init();
+	tegra_powergate_init();
 }
 #endif
diff --git a/arch/arm/mach-tegra/cpu-tegra.c b/arch/arm/mach-tegra/cpu-tegra.c
index bb5ce39b733b..7a065f0cf633 100644
--- a/arch/arm/mach-tegra/cpu-tegra.c
+++ b/arch/arm/mach-tegra/cpu-tegra.c
@@ -30,7 +30,6 @@
 #include <linux/io.h>
 #include <linux/suspend.h>
 
-#include <asm/system.h>
 
 #include <mach/clk.h>
 
diff --git a/arch/arm/mach-tegra/devices.c b/arch/arm/mach-tegra/devices.c
index 7a2a02dbd632..5f6b867e20b4 100644
--- a/arch/arm/mach-tegra/devices.c
+++ b/arch/arm/mach-tegra/devices.c
@@ -23,7 +23,6 @@
 #include <linux/fsl_devices.h>
 #include <linux/serial_8250.h>
 #include <linux/i2c-tegra.h>
-#include <linux/platform_data/tegra_usb.h>
 #include <asm/pmu.h>
 #include <mach/irqs.h>
 #include <mach/iomap.h>
@@ -446,18 +445,18 @@ static struct tegra_ulpi_config tegra_ehci2_ulpi_phy_config = {
 	.clk = "cdev2",
 };
 
-static struct tegra_ehci_platform_data tegra_ehci1_pdata = {
+struct tegra_ehci_platform_data tegra_ehci1_pdata = {
 	.operating_mode = TEGRA_USB_OTG,
 	.power_down_on_bus_suspend = 1,
 };
 
-static struct tegra_ehci_platform_data tegra_ehci2_pdata = {
+struct tegra_ehci_platform_data tegra_ehci2_pdata = {
 	.phy_config = &tegra_ehci2_ulpi_phy_config,
 	.operating_mode = TEGRA_USB_HOST,
 	.power_down_on_bus_suspend = 1,
 };
 
-static struct tegra_ehci_platform_data tegra_ehci3_pdata = {
+struct tegra_ehci_platform_data tegra_ehci3_pdata = {
 	.operating_mode = TEGRA_USB_HOST,
 	.power_down_on_bus_suspend = 1,
 };
diff --git a/arch/arm/mach-tegra/devices.h b/arch/arm/mach-tegra/devices.h
index 873ecb2f8ae6..ec455679b219 100644
--- a/arch/arm/mach-tegra/devices.h
+++ b/arch/arm/mach-tegra/devices.h
@@ -20,6 +20,11 @@
 #define __MACH_TEGRA_DEVICES_H
 
 #include <linux/platform_device.h>
+#include <linux/platform_data/tegra_usb.h>
+
+extern struct tegra_ehci_platform_data tegra_ehci1_pdata;
+extern struct tegra_ehci_platform_data tegra_ehci2_pdata;
+extern struct tegra_ehci_platform_data tegra_ehci3_pdata;
 
 extern struct platform_device tegra_gpio_device;
 extern struct platform_device tegra_pinmux_device;
diff --git a/arch/arm/mach-tegra/flowctrl.c b/arch/arm/mach-tegra/flowctrl.c
new file mode 100644
index 000000000000..fef66a7486ed
--- /dev/null
+++ b/arch/arm/mach-tegra/flowctrl.c
@@ -0,0 +1,62 @@
+/*
+ * arch/arm/mach-tegra/flowctrl.c
+ *
+ * functions and macros to control the flowcontroller
+ *
+ * Copyright (c) 2010-2012, NVIDIA Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+
+#include <mach/iomap.h>
+
+#include "flowctrl.h"
+
+u8 flowctrl_offset_halt_cpu[] = {
+	FLOW_CTRL_HALT_CPU0_EVENTS,
+	FLOW_CTRL_HALT_CPU1_EVENTS,
+	FLOW_CTRL_HALT_CPU1_EVENTS + 8,
+	FLOW_CTRL_HALT_CPU1_EVENTS + 16,
+};
+
+u8 flowctrl_offset_cpu_csr[] = {
+	FLOW_CTRL_CPU0_CSR,
+	FLOW_CTRL_CPU1_CSR,
+	FLOW_CTRL_CPU1_CSR + 8,
+	FLOW_CTRL_CPU1_CSR + 16,
+};
+
+static void flowctrl_update(u8 offset, u32 value)
+{
+	void __iomem *addr = IO_ADDRESS(TEGRA_FLOW_CTRL_BASE) + offset;
+
+	writel(value, addr);
+
+	/* ensure the update has reached the flow controller */
+	wmb();
+	readl_relaxed(addr);
+}
+
+void flowctrl_write_cpu_csr(unsigned int cpuid, u32 value)
+{
+	return flowctrl_update(flowctrl_offset_halt_cpu[cpuid], value);
+}
+
+void flowctrl_write_cpu_halt(unsigned int cpuid, u32 value)
+{
+	return flowctrl_update(flowctrl_offset_cpu_csr[cpuid], value);
+}
diff --git a/arch/arm/mach-tegra/flowctrl.h b/arch/arm/mach-tegra/flowctrl.h
index 74c6efbe52fa..19428173855e 100644
--- a/arch/arm/mach-tegra/flowctrl.h
+++ b/arch/arm/mach-tegra/flowctrl.h
@@ -34,4 +34,9 @@
 #define FLOW_CTRL_HALT_CPU1_EVENTS	0x14
 #define FLOW_CTRL_CPU1_CSR		0x18
 
+#ifndef __ASSEMBLY__
+void flowctrl_write_cpu_csr(unsigned int cpuid, u32 value);
+void flowctrl_write_cpu_halt(unsigned int cpuid, u32 value);
+#endif
+
 #endif
diff --git a/arch/arm/mach-tegra/fuse.c b/arch/arm/mach-tegra/fuse.c
index c1afb2738769..f946d129423c 100644
--- a/arch/arm/mach-tegra/fuse.c
+++ b/arch/arm/mach-tegra/fuse.c
@@ -34,6 +34,7 @@
 int tegra_sku_id;
 int tegra_cpu_process_id;
 int tegra_core_process_id;
+int tegra_chip_id;
 enum tegra_revision tegra_revision;
 
 /* The BCT to use at boot is specified by board straps that can be read
@@ -66,12 +67,9 @@ static inline bool get_spare_fuse(int bit)
 	return tegra_fuse_readl(FUSE_SPARE_BIT + bit * 4);
 }
 
-static enum tegra_revision tegra_get_revision(void)
+static enum tegra_revision tegra_get_revision(u32 id)
 {
-	void __iomem *chip_id = IO_ADDRESS(TEGRA_APB_MISC_BASE) + 0x804;
-	u32 id = readl(chip_id);
 	u32 minor_rev = (id >> 16) & 0xf;
-	u32 chipid = (id >> 8) & 0xff;
 
 	switch (minor_rev) {
 	case 1:
@@ -79,7 +77,8 @@ static enum tegra_revision tegra_get_revision(void)
 	case 2:
 		return TEGRA_REVISION_A02;
 	case 3:
-		if (chipid == 0x20 && (get_spare_fuse(18) || get_spare_fuse(19)))
+		if (tegra_chip_id == TEGRA20 &&
+			(get_spare_fuse(18) || get_spare_fuse(19)))
 			return TEGRA_REVISION_A03p;
 		else
 			return TEGRA_REVISION_A03;
@@ -92,6 +91,8 @@ static enum tegra_revision tegra_get_revision(void)
 
 void tegra_init_fuse(void)
 {
+	u32 id;
+
 	u32 reg = readl(IO_TO_VIRT(TEGRA_CLK_RESET_BASE + 0x48));
 	reg |= 1 << 28;
 	writel(reg, IO_TO_VIRT(TEGRA_CLK_RESET_BASE + 0x48));
@@ -108,10 +109,13 @@ void tegra_init_fuse(void)
 	reg = tegra_apb_readl(TEGRA_APB_MISC_BASE + STRAP_OPT);
 	tegra_bct_strapping = (reg & RAM_ID_MASK) >> RAM_CODE_SHIFT;
 
-	tegra_revision = tegra_get_revision();
+	id = readl_relaxed(IO_ADDRESS(TEGRA_APB_MISC_BASE) + 0x804);
+	tegra_chip_id = (id >> 8) & 0xff;
+
+	tegra_revision = tegra_get_revision(id);
 
 	pr_info("Tegra Revision: %s SKU: %d CPU Process: %d Core Process: %d\n",
-		tegra_revision_name[tegra_get_revision()],
+		tegra_revision_name[tegra_revision],
 		tegra_sku_id, tegra_cpu_process_id,
 		tegra_core_process_id);
 }
diff --git a/arch/arm/mach-tegra/fuse.h b/arch/arm/mach-tegra/fuse.h
index d65d2abf803b..d2107b2cb85a 100644
--- a/arch/arm/mach-tegra/fuse.h
+++ b/arch/arm/mach-tegra/fuse.h
@@ -35,9 +35,13 @@ enum tegra_revision {
 #define SKU_ID_AP25E	27
 #define SKU_ID_T25E	28
 
+#define TEGRA20		0x20
+#define TEGRA30		0x30
+
 extern int tegra_sku_id;
 extern int tegra_cpu_process_id;
 extern int tegra_core_process_id;
+extern int tegra_chip_id;
 extern enum tegra_revision tegra_revision;
 
 extern int tegra_bct_strapping;
diff --git a/arch/arm/mach-tegra/headsmp.S b/arch/arm/mach-tegra/headsmp.S
index b5349b2f13d2..fef9c2c51370 100644
--- a/arch/arm/mach-tegra/headsmp.S
+++ b/arch/arm/mach-tegra/headsmp.S
@@ -1,6 +1,23 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
+#include <asm/cache.h>
+
+#include <mach/iomap.h>
+
+#include "flowctrl.h"
+#include "reset.h"
+
+#define APB_MISC_GP_HIDREV	0x804
+#define PMC_SCRATCH41	0x140
+
+#define RESET_DATA(x)	((TEGRA_RESET_##x)*4)
+
+	.macro mov32, reg, val
+	movw	\reg, #:lower16:\val
+	movt	\reg, #:upper16:\val
+	.endm
+
         .section ".text.head", "ax"
 	__CPUINIT
 
@@ -47,15 +64,149 @@ ENTRY(v7_invalidate_l1)
         mov     pc, lr
 ENDPROC(v7_invalidate_l1)
 
+
 ENTRY(tegra_secondary_startup)
-	msr	cpsr_fsxc, #0xd3
         bl      v7_invalidate_l1
-	mrc	p15, 0, r0, c0, c0, 5
-        and	r0, r0, #15
-        ldr     r1, =0x6000f100
-        str     r0, [r1]
-1:      ldr     r2, [r1]
-        cmp     r0, r2
-        beq     1b
+	/* Enable coresight */
+	mov32	r0, 0xC5ACCE55
+	mcr	p14, 0, r0, c7, c12, 6
         b       secondary_startup
 ENDPROC(tegra_secondary_startup)
+
+	.align L1_CACHE_SHIFT
+ENTRY(__tegra_cpu_reset_handler_start)
+
+/*
+ * __tegra_cpu_reset_handler:
+ *
+ * Common handler for all CPU reset events.
+ *
+ * Register usage within the reset handler:
+ *
+ *      R7  = CPU present (to the OS) mask
+ *      R8  = CPU in LP1 state mask
+ *      R9  = CPU in LP2 state mask
+ *      R10 = CPU number
+ *      R11 = CPU mask
+ *      R12 = pointer to reset handler data
+ *
+ * NOTE: This code is copied to IRAM. All code and data accesses
+ *       must be position-independent.
+ */
+
+	.align L1_CACHE_SHIFT
+ENTRY(__tegra_cpu_reset_handler)
+
+	cpsid	aif, 0x13			@ SVC mode, interrupts disabled
+	mrc	p15, 0, r10, c0, c0, 5		@ MPIDR
+	and	r10, r10, #0x3			@ R10 = CPU number
+	mov	r11, #1
+	mov	r11, r11, lsl r10  		@ R11 = CPU mask
+	adr	r12, __tegra_cpu_reset_handler_data
+
+#ifdef CONFIG_SMP
+	/* Does the OS know about this CPU? */
+	ldr	r7, [r12, #RESET_DATA(MASK_PRESENT)]
+	tst	r7, r11 			@ if !present
+	bleq	__die				@ CPU not present (to OS)
+#endif
+
+#ifdef CONFIG_ARCH_TEGRA_2x_SOC
+	/* Are we on Tegra20? */
+	mov32	r6, TEGRA_APB_MISC_BASE
+	ldr	r0, [r6, #APB_MISC_GP_HIDREV]
+	and	r0, r0, #0xff00
+	cmp	r0, #(0x20 << 8)
+	bne	1f
+	/* If not CPU0, don't let CPU0 reset CPU1 now that CPU1 is coming up. */
+	mov32	r6, TEGRA_PMC_BASE
+	mov	r0, #0
+	cmp	r10, #0
+	strne	r0, [r6, #PMC_SCRATCH41]
+1:
+#endif
+
+#ifdef CONFIG_SMP
+	/*
+	 * Can only be secondary boot (initial or hotplug) but CPU 0
+	 * cannot be here.
+	 */
+	cmp	r10, #0
+	bleq	__die				@ CPU0 cannot be here
+	ldr	lr, [r12, #RESET_DATA(STARTUP_SECONDARY)]
+	cmp	lr, #0
+	bleq	__die				@ no secondary startup handler
+	bx	lr
+#endif
+
+/*
+ * We don't know why the CPU reset. Just kill it.
+ * The LR register will contain the address we died at + 4.
+ */
+
+__die:
+	sub	lr, lr, #4
+	mov32	r7, TEGRA_PMC_BASE
+	str	lr, [r7, #PMC_SCRATCH41]
+
+	mov32	r7, TEGRA_CLK_RESET_BASE
+
+	/* Are we on Tegra20? */
+	mov32	r6, TEGRA_APB_MISC_BASE
+	ldr	r0, [r6, #APB_MISC_GP_HIDREV]
+	and	r0, r0, #0xff00
+	cmp	r0, #(0x20 << 8)
+	bne	1f
+
+#ifdef CONFIG_ARCH_TEGRA_2x_SOC
+	mov32	r0, 0x1111
+	mov	r1, r0, lsl r10
+	str	r1, [r7, #0x340]		@ CLK_RST_CPU_CMPLX_SET
+#endif
+1:
+#ifdef CONFIG_ARCH_TEGRA_3x_SOC
+	mov32	r6, TEGRA_FLOW_CTRL_BASE
+
+	cmp	r10, #0
+	moveq	r1, #FLOW_CTRL_HALT_CPU0_EVENTS
+	moveq	r2, #FLOW_CTRL_CPU0_CSR
+	movne	r1, r10, lsl #3
+	addne	r2, r1, #(FLOW_CTRL_CPU1_CSR-8)
+	addne	r1, r1, #(FLOW_CTRL_HALT_CPU1_EVENTS-8)
+
+	/* Clear CPU "event" and "interrupt" flags and power gate
+	   it when halting but not before it is in the "WFI" state. */
+	ldr	r0, [r6, +r2]
+	orr	r0, r0, #FLOW_CTRL_CSR_INTR_FLAG | FLOW_CTRL_CSR_EVENT_FLAG
+	orr	r0, r0, #FLOW_CTRL_CSR_ENABLE
+	str	r0, [r6, +r2]
+
+	/* Unconditionally halt this CPU */
+	mov	r0, #FLOW_CTRL_WAITEVENT
+	str	r0, [r6, +r1]
+	ldr	r0, [r6, +r1]			@ memory barrier
+
+	dsb
+	isb
+	wfi					@ CPU should be power gated here
+
+	/* If the CPU didn't power gate above just kill it's clock. */
+
+	mov	r0, r11, lsl #8
+	str	r0, [r7, #348]			@ CLK_CPU_CMPLX_SET
+#endif
+
+	/* If the CPU still isn't dead, just spin here. */
+	b	.
+ENDPROC(__tegra_cpu_reset_handler)
+
+	.align L1_CACHE_SHIFT
+	.type	__tegra_cpu_reset_handler_data, %object
+	.globl	__tegra_cpu_reset_handler_data
+__tegra_cpu_reset_handler_data:
+	.rept	TEGRA_RESET_DATA_SIZE
+	.long	0
+	.endr
+	.align L1_CACHE_SHIFT
+
+ENTRY(__tegra_cpu_reset_handler_end)
diff --git a/arch/arm/mach-tegra/hotplug.c b/arch/arm/mach-tegra/hotplug.c
index f3294040d357..d8dc9ddd6d18 100644
--- a/arch/arm/mach-tegra/hotplug.c
+++ b/arch/arm/mach-tegra/hotplug.c
@@ -13,6 +13,7 @@
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
 
 static inline void cpu_enter_lowpower(void)
 {
diff --git a/arch/arm/mach-tegra/include/mach/debug-macro.S b/arch/arm/mach-tegra/include/mach/debug-macro.S
index 90069abd37bd..8ce0661b8a3d 100644
--- a/arch/arm/mach-tegra/include/mach/debug-macro.S
+++ b/arch/arm/mach-tegra/include/mach/debug-macro.S
@@ -26,7 +26,6 @@
 
 #include <linux/serial_reg.h>
 
-#include <mach/io.h>
 #include <mach/iomap.h>
 #include <mach/irammap.h>
 
diff --git a/arch/arm/mach-tegra/include/mach/io.h b/arch/arm/mach-tegra/include/mach/io.h
index f15defffb5d2..fe700f9ce7dc 100644
--- a/arch/arm/mach-tegra/include/mach/io.h
+++ b/arch/arm/mach-tegra/include/mach/io.h
@@ -23,56 +23,8 @@
 
 #define IO_SPACE_LIMIT 0xffff
 
-/* On TEGRA, many peripherals are very closely packed in
- * two 256MB io windows (that actually only use about 64KB
- * at the start of each).
- *
- * We will just map the first 1MB of each window (to minimize
- * pt entries needed) and provide a macro to transform physical
- * io addresses to an appropriate void __iomem *.
- *
- */
-
-#ifdef __ASSEMBLY__
-#define IOMEM(x)	(x)
-#else
-#define IOMEM(x)	((void __force __iomem *)(x))
-#endif
-
-#define IO_IRAM_PHYS	0x40000000
-#define IO_IRAM_VIRT	IOMEM(0xFE400000)
-#define IO_IRAM_SIZE	SZ_256K
-
-#define IO_CPU_PHYS     0x50040000
-#define IO_CPU_VIRT     IOMEM(0xFE000000)
-#define IO_CPU_SIZE	SZ_16K
-
-#define IO_PPSB_PHYS	0x60000000
-#define IO_PPSB_VIRT	IOMEM(0xFE200000)
-#define IO_PPSB_SIZE	SZ_1M
-
-#define IO_APB_PHYS	0x70000000
-#define IO_APB_VIRT	IOMEM(0xFE300000)
-#define IO_APB_SIZE	SZ_1M
-
-#define IO_TO_VIRT_BETWEEN(p, st, sz)	((p) >= (st) && (p) < ((st) + (sz)))
-#define IO_TO_VIRT_XLATE(p, pst, vst)	(((p) - (pst) + (vst)))
-
-#define IO_TO_VIRT(n) ( \
-	IO_TO_VIRT_BETWEEN((n), IO_PPSB_PHYS, IO_PPSB_SIZE) ?		\
-		IO_TO_VIRT_XLATE((n), IO_PPSB_PHYS, IO_PPSB_VIRT) :	\
-	IO_TO_VIRT_BETWEEN((n), IO_APB_PHYS, IO_APB_SIZE) ?		\
-		IO_TO_VIRT_XLATE((n), IO_APB_PHYS, IO_APB_VIRT) :	\
-	IO_TO_VIRT_BETWEEN((n), IO_CPU_PHYS, IO_CPU_SIZE) ?		\
-		IO_TO_VIRT_XLATE((n), IO_CPU_PHYS, IO_CPU_VIRT) :	\
-	IO_TO_VIRT_BETWEEN((n), IO_IRAM_PHYS, IO_IRAM_SIZE) ?		\
-		IO_TO_VIRT_XLATE((n), IO_IRAM_PHYS, IO_IRAM_VIRT) :	\
-	NULL)
-
 #ifndef __ASSEMBLER__
 
-#define IO_ADDRESS(n) (IO_TO_VIRT(n))
-
 #ifdef CONFIG_TEGRA_PCI
 extern void __iomem *tegra_pcie_io_base;
 
@@ -88,7 +40,6 @@ static inline void __iomem *__io(unsigned long addr)
 #endif
 
 #define __io(a)         __io(a)
-#define __mem_pci(a)    (a)
 
 #endif
 
diff --git a/arch/arm/mach-tegra/include/mach/iomap.h b/arch/arm/mach-tegra/include/mach/iomap.h
index 67644c905d8e..7e76da73121c 100644
--- a/arch/arm/mach-tegra/include/mach/iomap.h
+++ b/arch/arm/mach-tegra/include/mach/iomap.h
@@ -113,6 +113,9 @@
 #define TEGRA_AHB_GIZMO_BASE		0x6000C004
 #define TEGRA_AHB_GIZMO_SIZE		0x10C
 
+#define TEGRA_SB_BASE			0x6000C200
+#define TEGRA_SB_SIZE			256
+
 #define TEGRA_STATMON_BASE		0x6000C400
 #define TEGRA_STATMON_SIZE		SZ_1K
 
@@ -274,4 +277,46 @@
 # define TEGRA_DEBUG_UART_BASE TEGRA_UARTE_BASE
 #endif
 
+/* On TEGRA, many peripherals are very closely packed in
+ * two 256MB io windows (that actually only use about 64KB
+ * at the start of each).
+ *
+ * We will just map the first 1MB of each window (to minimize
+ * pt entries needed) and provide a macro to transform physical
+ * io addresses to an appropriate void __iomem *.
+ *
+ */
+
+#define IO_IRAM_PHYS	0x40000000
+#define IO_IRAM_VIRT	IOMEM(0xFE400000)
+#define IO_IRAM_SIZE	SZ_256K
+
+#define IO_CPU_PHYS     0x50040000
+#define IO_CPU_VIRT     IOMEM(0xFE000000)
+#define IO_CPU_SIZE	SZ_16K
+
+#define IO_PPSB_PHYS	0x60000000
+#define IO_PPSB_VIRT	IOMEM(0xFE200000)
+#define IO_PPSB_SIZE	SZ_1M
+
+#define IO_APB_PHYS	0x70000000
+#define IO_APB_VIRT	IOMEM(0xFE300000)
+#define IO_APB_SIZE	SZ_1M
+
+#define IO_TO_VIRT_BETWEEN(p, st, sz)	((p) >= (st) && (p) < ((st) + (sz)))
+#define IO_TO_VIRT_XLATE(p, pst, vst)	(((p) - (pst) + (vst)))
+
+#define IO_TO_VIRT(n) ( \
+	IO_TO_VIRT_BETWEEN((n), IO_PPSB_PHYS, IO_PPSB_SIZE) ?		\
+		IO_TO_VIRT_XLATE((n), IO_PPSB_PHYS, IO_PPSB_VIRT) :	\
+	IO_TO_VIRT_BETWEEN((n), IO_APB_PHYS, IO_APB_SIZE) ?		\
+		IO_TO_VIRT_XLATE((n), IO_APB_PHYS, IO_APB_VIRT) :	\
+	IO_TO_VIRT_BETWEEN((n), IO_CPU_PHYS, IO_CPU_SIZE) ?		\
+		IO_TO_VIRT_XLATE((n), IO_CPU_PHYS, IO_CPU_VIRT) :	\
+	IO_TO_VIRT_BETWEEN((n), IO_IRAM_PHYS, IO_IRAM_SIZE) ?		\
+		IO_TO_VIRT_XLATE((n), IO_IRAM_PHYS, IO_IRAM_VIRT) :	\
+	NULL)
+
+#define IO_ADDRESS(n) (IO_TO_VIRT(n))
+
 #endif
diff --git a/arch/arm/mach-tegra/include/mach/powergate.h b/arch/arm/mach-tegra/include/mach/powergate.h
index 39c396d2ddb0..4752b1a68f35 100644
--- a/arch/arm/mach-tegra/include/mach/powergate.h
+++ b/arch/arm/mach-tegra/include/mach/powergate.h
@@ -27,8 +27,21 @@
 #define TEGRA_POWERGATE_VDEC	4
 #define TEGRA_POWERGATE_L2	5
 #define TEGRA_POWERGATE_MPE	6
-#define TEGRA_NUM_POWERGATE	7
+#define TEGRA_POWERGATE_HEG	7
+#define TEGRA_POWERGATE_SATA	8
+#define TEGRA_POWERGATE_CPU1	9
+#define TEGRA_POWERGATE_CPU2	10
+#define TEGRA_POWERGATE_CPU3	11
+#define TEGRA_POWERGATE_CELP	12
+#define TEGRA_POWERGATE_3D1	13
 
+#define TEGRA_POWERGATE_CPU0	TEGRA_POWERGATE_CPU
+#define TEGRA_POWERGATE_3D0	TEGRA_POWERGATE_3D
+
+int  __init tegra_powergate_init(void);
+
+int tegra_cpu_powergate_id(int cpuid);
+int tegra_powergate_is_powered(int id);
 int tegra_powergate_power_on(int id);
 int tegra_powergate_power_off(int id);
 int tegra_powergate_remove_clamping(int id);
diff --git a/arch/arm/mach-tegra/io.c b/arch/arm/mach-tegra/io.c
index d23ee2db2827..58b4baf9c483 100644
--- a/arch/arm/mach-tegra/io.c
+++ b/arch/arm/mach-tegra/io.c
@@ -26,6 +26,7 @@
 
 #include <asm/page.h>
 #include <asm/mach/map.h>
+#include <mach/iomap.h>
 
 #include "board.h"
 
diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c
index 7d2b5d03c1df..1a208dbf682f 100644
--- a/arch/arm/mach-tegra/platsmp.c
+++ b/arch/arm/mach-tegra/platsmp.c
@@ -24,19 +24,31 @@
 #include <asm/mach-types.h>
 #include <asm/smp_scu.h>
 
+#include <mach/clk.h>
 #include <mach/iomap.h>
+#include <mach/powergate.h>
+
+#include "fuse.h"
+#include "flowctrl.h"
+#include "reset.h"
 
 extern void tegra_secondary_startup(void);
 
-static DEFINE_SPINLOCK(boot_lock);
 static void __iomem *scu_base = IO_ADDRESS(TEGRA_ARM_PERIF_BASE);
 
 #define EVP_CPU_RESET_VECTOR \
 	(IO_ADDRESS(TEGRA_EXCEPTION_VECTORS_BASE) + 0x100)
 #define CLK_RST_CONTROLLER_CLK_CPU_CMPLX \
 	(IO_ADDRESS(TEGRA_CLK_RESET_BASE) + 0x4c)
+#define CLK_RST_CONTROLLER_RST_CPU_CMPLX_SET \
+	(IO_ADDRESS(TEGRA_CLK_RESET_BASE) + 0x340)
 #define CLK_RST_CONTROLLER_RST_CPU_CMPLX_CLR \
 	(IO_ADDRESS(TEGRA_CLK_RESET_BASE) + 0x344)
+#define CLK_RST_CONTROLLER_CLK_CPU_CMPLX_CLR \
+	(IO_ADDRESS(TEGRA_CLK_RESET_BASE) + 0x34c)
+
+#define CPU_CLOCK(cpu)	(0x1<<(8+cpu))
+#define CPU_RESET(cpu)	(0x1111ul<<(cpu))
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
@@ -47,63 +59,106 @@ void __cpuinit platform_secondary_init(unsigned int cpu)
 	 */
 	gic_secondary_init(0);
 
-	/*
-	 * Synchronise with the boot thread.
-	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
 }
 
-int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+static int tegra20_power_up_cpu(unsigned int cpu)
 {
-	unsigned long old_boot_vector;
-	unsigned long boot_vector;
-	unsigned long timeout;
 	u32 reg;
 
-	/*
-	 * set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	spin_lock(&boot_lock);
+	/* Enable the CPU clock. */
+	reg = readl(CLK_RST_CONTROLLER_CLK_CPU_CMPLX);
+	writel(reg & ~CPU_CLOCK(cpu), CLK_RST_CONTROLLER_CLK_CPU_CMPLX);
+	barrier();
+	reg = readl(CLK_RST_CONTROLLER_CLK_CPU_CMPLX);
 
+	/* Clear flow controller CSR. */
+	flowctrl_write_cpu_csr(cpu, 0);
 
-	/* set the reset vector to point to the secondary_startup routine */
+	return 0;
+}
 
-	boot_vector = virt_to_phys(tegra_secondary_startup);
-	old_boot_vector = readl(EVP_CPU_RESET_VECTOR);
-	writel(boot_vector, EVP_CPU_RESET_VECTOR);
+static int tegra30_power_up_cpu(unsigned int cpu)
+{
+	u32 reg;
+	int ret, pwrgateid;
+	unsigned long timeout;
 
-	/* enable cpu clock on cpu1 */
-	reg = readl(CLK_RST_CONTROLLER_CLK_CPU_CMPLX);
-	writel(reg & ~(1<<9), CLK_RST_CONTROLLER_CLK_CPU_CMPLX);
+	pwrgateid = tegra_cpu_powergate_id(cpu);
+	if (pwrgateid < 0)
+		return pwrgateid;
+
+	/* If this is the first boot, toggle powergates directly. */
+	if (!tegra_powergate_is_powered(pwrgateid)) {
+		ret = tegra_powergate_power_on(pwrgateid);
+		if (ret)
+			return ret;
+
+		/* Wait for the power to come up. */
+		timeout = jiffies + 10*HZ;
+		while (tegra_powergate_is_powered(pwrgateid)) {
+			if (time_after(jiffies, timeout))
+				return -ETIMEDOUT;
+			udelay(10);
+		}
+	}
 
-	reg = (1<<13) | (1<<9) | (1<<5) | (1<<1);
-	writel(reg, CLK_RST_CONTROLLER_RST_CPU_CMPLX_CLR);
+	/* CPU partition is powered. Enable the CPU clock. */
+	writel(CPU_CLOCK(cpu), CLK_RST_CONTROLLER_CLK_CPU_CMPLX_CLR);
+	reg = readl(CLK_RST_CONTROLLER_CLK_CPU_CMPLX_CLR);
+	udelay(10);
 
-	smp_wmb();
-	flush_cache_all();
+	/* Remove I/O clamps. */
+	ret = tegra_powergate_remove_clamping(pwrgateid);
+	udelay(10);
 
-	/* unhalt the cpu */
-	writel(0, IO_ADDRESS(TEGRA_FLOW_CTRL_BASE) + 0x14);
+	/* Clear flow controller CSR. */
+	flowctrl_write_cpu_csr(cpu, 0);
 
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (readl(EVP_CPU_RESET_VECTOR) != boot_vector)
-			break;
-		udelay(10);
-	}
+	return 0;
+}
+
+int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	int status;
 
-	/* put the old boot vector back */
-	writel(old_boot_vector, EVP_CPU_RESET_VECTOR);
+	/*
+	 * Force the CPU into reset. The CPU must remain in reset when the
+	 * flow controller state is cleared (which will cause the flow
+	 * controller to stop driving reset if the CPU has been power-gated
+	 * via the flow controller). This will have no effect on first boot
+	 * of the CPU since it should already be in reset.
+	 */
+	writel(CPU_RESET(cpu), CLK_RST_CONTROLLER_RST_CPU_CMPLX_SET);
+	dmb();
 
 	/*
-	 * now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
+	 * Unhalt the CPU. If the flow controller was used to power-gate the
+	 * CPU this will cause the flow controller to stop driving reset.
+	 * The CPU will remain in reset because the clock and reset block
+	 * is now driving reset.
 	 */
-	spin_unlock(&boot_lock);
+	flowctrl_write_cpu_halt(cpu, 0);
+
+	switch (tegra_chip_id) {
+	case TEGRA20:
+		status = tegra20_power_up_cpu(cpu);
+		break;
+	case TEGRA30:
+		status = tegra30_power_up_cpu(cpu);
+		break;
+	default:
+		status = -EINVAL;
+		break;
+	}
 
-	return 0;
+	if (status)
+		goto done;
+
+	/* Take the CPU out of reset. */
+	writel(CPU_RESET(cpu), CLK_RST_CONTROLLER_RST_CPU_CMPLX_CLR);
+	wmb();
+done:
+	return status;
 }
 
 /*
@@ -128,6 +183,6 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-
+	tegra_cpu_reset_handler_init();
 	scu_enable(scu_base);
 }
diff --git a/arch/arm/mach-tegra/powergate.c b/arch/arm/mach-tegra/powergate.c
index 948306491a59..c238699ae86f 100644
--- a/arch/arm/mach-tegra/powergate.c
+++ b/arch/arm/mach-tegra/powergate.c
@@ -31,6 +31,8 @@
 #include <mach/iomap.h>
 #include <mach/powergate.h>
 
+#include "fuse.h"
+
 #define PWRGATE_TOGGLE		0x30
 #define  PWRGATE_TOGGLE_START	(1 << 8)
 
@@ -38,6 +40,16 @@
 
 #define PWRGATE_STATUS		0x38
 
+static int tegra_num_powerdomains;
+static int tegra_num_cpu_domains;
+static u8 *tegra_cpu_domains;
+static u8 tegra30_cpu_domains[] = {
+	TEGRA_POWERGATE_CPU0,
+	TEGRA_POWERGATE_CPU1,
+	TEGRA_POWERGATE_CPU2,
+	TEGRA_POWERGATE_CPU3,
+};
+
 static DEFINE_SPINLOCK(tegra_powergate_lock);
 
 static void __iomem *pmc = IO_ADDRESS(TEGRA_PMC_BASE);
@@ -75,7 +87,7 @@ static int tegra_powergate_set(int id, bool new_state)
 
 int tegra_powergate_power_on(int id)
 {
-	if (id < 0 || id >= TEGRA_NUM_POWERGATE)
+	if (id < 0 || id >= tegra_num_powerdomains)
 		return -EINVAL;
 
 	return tegra_powergate_set(id, true);
@@ -83,17 +95,18 @@ int tegra_powergate_power_on(int id)
 
 int tegra_powergate_power_off(int id)
 {
-	if (id < 0 || id >= TEGRA_NUM_POWERGATE)
+	if (id < 0 || id >= tegra_num_powerdomains)
 		return -EINVAL;
 
 	return tegra_powergate_set(id, false);
 }
 
-static bool tegra_powergate_is_powered(int id)
+int tegra_powergate_is_powered(int id)
 {
 	u32 status;
 
-	WARN_ON(id < 0 || id >= TEGRA_NUM_POWERGATE);
+	if (id < 0 || id >= tegra_num_powerdomains)
+		return -EINVAL;
 
 	status = pmc_read(PWRGATE_STATUS) & (1 << id);
 	return !!status;
@@ -103,7 +116,7 @@ int tegra_powergate_remove_clamping(int id)
 {
 	u32 mask;
 
-	if (id < 0 || id >= TEGRA_NUM_POWERGATE)
+	if (id < 0 || id >= tegra_num_powerdomains)
 		return -EINVAL;
 
 	/*
@@ -156,6 +169,34 @@ err_power:
 	return ret;
 }
 
+int tegra_cpu_powergate_id(int cpuid)
+{
+	if (cpuid > 0 && cpuid < tegra_num_cpu_domains)
+		return tegra_cpu_domains[cpuid];
+
+	return -EINVAL;
+}
+
+int __init tegra_powergate_init(void)
+{
+	switch (tegra_chip_id) {
+	case TEGRA20:
+		tegra_num_powerdomains = 7;
+		break;
+	case TEGRA30:
+		tegra_num_powerdomains = 14;
+		tegra_num_cpu_domains = 4;
+		tegra_cpu_domains = tegra30_cpu_domains;
+		break;
+	default:
+		/* Unknown Tegra variant. Disable powergating */
+		tegra_num_powerdomains = 0;
+		break;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_DEBUG_FS
 
 static const char * const powergate_name[] = {
@@ -175,7 +216,7 @@ static int powergate_show(struct seq_file *s, void *data)
 	seq_printf(s, " powergate powered\n");
 	seq_printf(s, "------------------\n");
 
-	for (i = 0; i < TEGRA_NUM_POWERGATE; i++)
+	for (i = 0; i < tegra_num_powerdomains; i++)
 		seq_printf(s, " %9s %7s\n", powergate_name[i],
 			tegra_powergate_is_powered(i) ? "yes" : "no");
 	return 0;
diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c
new file mode 100644
index 000000000000..4d6a2ee99c3b
--- /dev/null
+++ b/arch/arm/mach-tegra/reset.c
@@ -0,0 +1,84 @@
+/*
+ * arch/arm/mach-tegra/reset.c
+ *
+ * Copyright (C) 2011,2012 NVIDIA Corporation.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/cpumask.h>
+#include <linux/bitops.h>
+
+#include <asm/cacheflush.h>
+#include <asm/hardware/cache-l2x0.h>
+
+#include <mach/iomap.h>
+#include <mach/irammap.h>
+
+#include "reset.h"
+#include "fuse.h"
+
+#define TEGRA_IRAM_RESET_BASE (TEGRA_IRAM_BASE + \
+				TEGRA_IRAM_RESET_HANDLER_OFFSET)
+
+static bool is_enabled;
+
+static void tegra_cpu_reset_handler_enable(void)
+{
+	void __iomem *iram_base = IO_ADDRESS(TEGRA_IRAM_RESET_BASE);
+	void __iomem *evp_cpu_reset =
+		IO_ADDRESS(TEGRA_EXCEPTION_VECTORS_BASE + 0x100);
+	void __iomem *sb_ctrl = IO_ADDRESS(TEGRA_SB_BASE);
+	u32 reg;
+
+	BUG_ON(is_enabled);
+	BUG_ON(tegra_cpu_reset_handler_size > TEGRA_IRAM_RESET_HANDLER_SIZE);
+
+	memcpy(iram_base, (void *)__tegra_cpu_reset_handler_start,
+			tegra_cpu_reset_handler_size);
+
+	/*
+	 * NOTE: This must be the one and only write to the EVP CPU reset
+	 *       vector in the entire system.
+	 */
+	writel(TEGRA_IRAM_RESET_BASE + tegra_cpu_reset_handler_offset,
+			evp_cpu_reset);
+	wmb();
+	reg = readl(evp_cpu_reset);
+
+	/*
+	 * Prevent further modifications to the physical reset vector.
+	 *  NOTE: Has no effect on chips prior to Tegra30.
+	 */
+	if (tegra_chip_id != TEGRA20) {
+		reg = readl(sb_ctrl);
+		reg |= 2;
+		writel(reg, sb_ctrl);
+		wmb();
+	}
+
+	is_enabled = true;
+}
+
+void __init tegra_cpu_reset_handler_init(void)
+{
+
+#ifdef CONFIG_SMP
+	__tegra_cpu_reset_handler_data[TEGRA_RESET_MASK_PRESENT] =
+		*((u32 *)cpu_present_mask);
+	__tegra_cpu_reset_handler_data[TEGRA_RESET_STARTUP_SECONDARY] =
+		virt_to_phys((void *)tegra_secondary_startup);
+#endif
+
+	tegra_cpu_reset_handler_enable();
+}
diff --git a/arch/arm/mach-tegra/reset.h b/arch/arm/mach-tegra/reset.h
new file mode 100644
index 000000000000..de88bf851dd3
--- /dev/null
+++ b/arch/arm/mach-tegra/reset.h
@@ -0,0 +1,50 @@
+/*
+ * arch/arm/mach-tegra/reset.h
+ *
+ * CPU reset dispatcher.
+ *
+ * Copyright (c) 2011, NVIDIA Corporation.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __MACH_TEGRA_RESET_H
+#define __MACH_TEGRA_RESET_H
+
+#define TEGRA_RESET_MASK_PRESENT	0
+#define TEGRA_RESET_MASK_LP1		1
+#define TEGRA_RESET_MASK_LP2		2
+#define TEGRA_RESET_STARTUP_SECONDARY	3
+#define TEGRA_RESET_STARTUP_LP2		4
+#define TEGRA_RESET_STARTUP_LP1		5
+#define TEGRA_RESET_DATA_SIZE		6
+
+#ifndef __ASSEMBLY__
+
+extern unsigned long __tegra_cpu_reset_handler_data[TEGRA_RESET_DATA_SIZE];
+
+void __tegra_cpu_reset_handler_start(void);
+void __tegra_cpu_reset_handler(void);
+void __tegra_cpu_reset_handler_end(void);
+void tegra_secondary_startup(void);
+
+#define tegra_cpu_reset_handler_offset \
+		((u32)__tegra_cpu_reset_handler - \
+		 (u32)__tegra_cpu_reset_handler_start)
+
+#define tegra_cpu_reset_handler_size \
+		(__tegra_cpu_reset_handler_end - \
+		 __tegra_cpu_reset_handler_start)
+
+void __init tegra_cpu_reset_handler_init(void);
+
+#endif
+#endif
diff --git a/arch/arm/mach-tegra/sleep.S b/arch/arm/mach-tegra/sleep.S
index 8f9fde161c34..5b20197bae7f 100644
--- a/arch/arm/mach-tegra/sleep.S
+++ b/arch/arm/mach-tegra/sleep.S
@@ -23,7 +23,9 @@
  */
 
 #include <linux/linkage.h>
-#include <mach/io.h>
+
+#include <asm/assembler.h>
+
 #include <mach/iomap.h>
 
 #include "flowctrl.h"
diff --git a/arch/arm/mach-u300/core.c b/arch/arm/mach-u300/core.c
index 8b90c44d237f..1621ad07d284 100644
--- a/arch/arm/mach-u300/core.c
+++ b/arch/arm/mach-u300/core.c
@@ -1544,6 +1544,8 @@ static struct fsmc_nand_platform_data nand_platform_data = {
 	.nr_partitions = ARRAY_SIZE(u300_partitions),
 	.options = NAND_SKIP_BBTSCAN,
 	.width = FSMC_NAND_BW8,
+	.ale_off = PLAT_NAND_ALE,
+	.cle_off = PLAT_NAND_CLE,
 };
 
 static struct platform_device nand_device = {
diff --git a/arch/arm/mach-u300/include/mach/io.h b/arch/arm/mach-u300/include/mach/io.h
deleted file mode 100644
index 5d6b4c13b3a0..000000000000
--- a/arch/arm/mach-u300/include/mach/io.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- *
- * arch/arm/mach-u300/include/mach/io.h
- *
- *
- * Copyright (C) 2006-2009 ST-Ericsson AB
- * License terms: GNU General Public License (GPL) version 2
- * Dummy IO map for being able to use writew()/readw(),
- * writel()/readw() and similar accessor functions.
- * Author: Linus Walleij <linus.walleij@stericsson.com>
- */
-#ifndef __MACH_IO_H
-#define __MACH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-u300/include/mach/u300-regs.h b/arch/arm/mach-u300/include/mach/u300-regs.h
index 035fdc9dbdb0..65f87c523892 100644
--- a/arch/arm/mach-u300/include/mach/u300-regs.h
+++ b/arch/arm/mach-u300/include/mach/u300-regs.h
@@ -18,18 +18,17 @@
  * the defines are used for setting up the I/O memory mapping.
  */
 
-#ifdef __ASSEMBLER__
-#define IOMEM(a) (a)
-#else
-#define IOMEM(a) (void __iomem *) a
-#endif
-
 /* NAND Flash CS0 */
 #define U300_NAND_CS0_PHYS_BASE		0x80000000
 
 /* NFIF */
 #define U300_NAND_IF_PHYS_BASE		0x9f800000
 
+/* ALE, CLE offset for FSMC NAND */
+#define PLAT_NAND_CLE			(1 << 16)
+#define PLAT_NAND_ALE			(1 << 17)
+
+
 /* AHB Peripherals */
 #define U300_AHB_PER_PHYS_BASE		0xa0000000
 #define U300_AHB_PER_VIRT_BASE		0xff010000
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index 9ec635812349..880d02ec89d4 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -27,6 +27,7 @@ config MACH_MOP500
 	select UX500_SOC_DB8500
 	select I2C
 	select I2C_NOMADIK
+	select SOC_BUS
 	help
 	  Include support for the MOP500 development platform.
 
@@ -57,6 +58,12 @@ config UX500_AUTO_PLATFORM
 	  At least one platform needs to be selected in order to build
 	  a working kernel. If everything else is disabled, this
 	  automatically enables MACH_MOP500.
+
+config MACH_UX500_DT
+	bool "Generic U8500 support using device tree"
+	depends on MACH_MOP500
+	select USE_OF
+
 endmenu
 
 config UX500_DEBUG_UART
diff --git a/arch/arm/mach-ux500/Makefile.boot b/arch/arm/mach-ux500/Makefile.boot
index ff0a4b5b0a82..dd5cd00e2554 100644
--- a/arch/arm/mach-ux500/Makefile.boot
+++ b/arch/arm/mach-ux500/Makefile.boot
@@ -2,3 +2,4 @@
 params_phys-y	:= 0x00000100
 initrd_phys-y	:= 0x00800000
 
+dtb-$(CONFIG_MACH_SNOWBALL) += snowball.dtb
diff --git a/arch/arm/mach-ux500/board-mop500-sdi.c b/arch/arm/mach-ux500/board-mop500-sdi.c
index 1daead3e583e..920251cf834c 100644
--- a/arch/arm/mach-ux500/board-mop500-sdi.c
+++ b/arch/arm/mach-ux500/board-mop500-sdi.c
@@ -99,7 +99,7 @@ static struct mmci_platform_data mop500_sdi0_data = {
 #endif
 };
 
-static void sdi0_configure(void)
+static void sdi0_configure(struct device *parent)
 {
 	int ret;
 
@@ -118,15 +118,15 @@ static void sdi0_configure(void)
 	gpio_direction_output(sdi0_en, 1);
 
 	/* Add the device, force v2 to subrevision 1 */
-	db8500_add_sdi0(&mop500_sdi0_data, U8500_SDI_V2_PERIPHID);
+	db8500_add_sdi0(parent, &mop500_sdi0_data, U8500_SDI_V2_PERIPHID);
 }
 
-void mop500_sdi_tc35892_init(void)
+void mop500_sdi_tc35892_init(struct device *parent)
 {
 	mop500_sdi0_data.gpio_cd = GPIO_SDMMC_CD;
 	sdi0_en = GPIO_SDMMC_EN;
 	sdi0_vsel = GPIO_SDMMC_1V8_3V_SEL;
-	sdi0_configure();
+	sdi0_configure(parent);
 }
 
 /*
@@ -241,12 +241,13 @@ static struct mmci_platform_data mop500_sdi4_data = {
 #endif
 };
 
-void __init mop500_sdi_init(void)
+void __init mop500_sdi_init(struct device *parent)
 {
 	/* PoP:ed eMMC */
-	db8500_add_sdi2(&mop500_sdi2_data, U8500_SDI_V2_PERIPHID);
+	db8500_add_sdi2(parent, &mop500_sdi2_data, U8500_SDI_V2_PERIPHID);
 	/* On-board eMMC */
-	db8500_add_sdi4(&mop500_sdi4_data, U8500_SDI_V2_PERIPHID);
+	db8500_add_sdi4(parent, &mop500_sdi4_data, U8500_SDI_V2_PERIPHID);
+
 	/*
 	 * On boards with the TC35892 GPIO expander, sdi0 will finally
 	 * be added when the TC35892 initializes and calls
@@ -254,31 +255,31 @@ void __init mop500_sdi_init(void)
 	 */
 }
 
-void __init snowball_sdi_init(void)
+void __init snowball_sdi_init(struct device *parent)
 {
 	/* On Snowball MMC_CAP_SD_HIGHSPEED isn't supported (Hardware issue?) */
 	mop500_sdi0_data.capabilities &= ~MMC_CAP_SD_HIGHSPEED;
 	/* On-board eMMC */
-	db8500_add_sdi4(&mop500_sdi4_data, U8500_SDI_V2_PERIPHID);
+	db8500_add_sdi4(parent, &mop500_sdi4_data, U8500_SDI_V2_PERIPHID);
 	/* External Micro SD slot */
 	mop500_sdi0_data.gpio_cd = SNOWBALL_SDMMC_CD_GPIO;
 	mop500_sdi0_data.cd_invert = true;
 	sdi0_en = SNOWBALL_SDMMC_EN_GPIO;
 	sdi0_vsel = SNOWBALL_SDMMC_1V8_3V_GPIO;
-	sdi0_configure();
+	sdi0_configure(parent);
 }
 
-void __init hrefv60_sdi_init(void)
+void __init hrefv60_sdi_init(struct device *parent)
 {
 	/* PoP:ed eMMC */
-	db8500_add_sdi2(&mop500_sdi2_data, U8500_SDI_V2_PERIPHID);
+	db8500_add_sdi2(parent, &mop500_sdi2_data, U8500_SDI_V2_PERIPHID);
 	/* On-board eMMC */
-	db8500_add_sdi4(&mop500_sdi4_data, U8500_SDI_V2_PERIPHID);
+	db8500_add_sdi4(parent, &mop500_sdi4_data, U8500_SDI_V2_PERIPHID);
 	/* External Micro SD slot */
 	mop500_sdi0_data.gpio_cd = HREFV60_SDMMC_CD_GPIO;
 	sdi0_en = HREFV60_SDMMC_EN_GPIO;
 	sdi0_vsel = HREFV60_SDMMC_1V8_3V_GPIO;
-	sdi0_configure();
+	sdi0_configure(parent);
 	/* WLAN SDIO channel */
-	db8500_add_sdi1(&mop500_sdi1_data, U8500_SDI_V2_PERIPHID);
+	db8500_add_sdi1(parent, &mop500_sdi1_data, U8500_SDI_V2_PERIPHID);
 }
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index 6d672a556df8..77d03c1fbd04 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -30,6 +30,9 @@
 #include <linux/gpio_keys.h>
 #include <linux/delay.h>
 
+#include <linux/of.h>
+#include <linux/of_platform.h>
+
 #include <linux/leds.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -226,7 +229,12 @@ static struct tps6105x_platform_data mop500_tps61052_data = {
 
 static void mop500_tc35892_init(struct tc3589x *tc3589x, unsigned int base)
 {
-	mop500_sdi_tc35892_init();
+	struct device *parent = NULL;
+#if 0
+	/* FIXME: Is the sdi actually part of tc3589x? */
+	parent = tc3589x->dev;
+#endif
+	mop500_sdi_tc35892_init(parent);
 }
 
 static struct tc3589x_gpio_platform_data mop500_tc35892_gpio_data = {
@@ -353,12 +361,12 @@ U8500_I2C_CONTROLLER(1, 0xe, 1, 8, 100000, 200, I2C_FREQ_MODE_FAST);
 U8500_I2C_CONTROLLER(2,	0xe, 1, 8, 100000, 200, I2C_FREQ_MODE_FAST);
 U8500_I2C_CONTROLLER(3,	0xe, 1, 8, 100000, 200, I2C_FREQ_MODE_FAST);
 
-static void __init mop500_i2c_init(void)
+static void __init mop500_i2c_init(struct device *parent)
 {
-	db8500_add_i2c0(&u8500_i2c0_data);
-	db8500_add_i2c1(&u8500_i2c1_data);
-	db8500_add_i2c2(&u8500_i2c2_data);
-	db8500_add_i2c3(&u8500_i2c3_data);
+	db8500_add_i2c0(parent, &u8500_i2c0_data);
+	db8500_add_i2c1(parent, &u8500_i2c1_data);
+	db8500_add_i2c2(parent, &u8500_i2c2_data);
+	db8500_add_i2c3(parent, &u8500_i2c3_data);
 }
 
 static struct gpio_keys_button mop500_gpio_keys[] = {
@@ -435,7 +443,7 @@ static struct stedma40_chan_cfg ssp0_dma_cfg_tx = {
 };
 #endif
 
-static struct pl022_ssp_controller ssp0_platform_data = {
+static struct pl022_ssp_controller ssp0_plat = {
 	.bus_id = 0,
 #ifdef CONFIG_STE_DMA40
 	.enable_dma = 1,
@@ -451,9 +459,9 @@ static struct pl022_ssp_controller ssp0_platform_data = {
 	.num_chipselect = 5,
 };
 
-static void __init mop500_spi_init(void)
+static void __init mop500_spi_init(struct device *parent)
 {
-	db8500_add_ssp0(&ssp0_platform_data);
+	db8500_add_ssp0(parent, &ssp0_plat);
 }
 
 #ifdef CONFIG_STE_DMA40
@@ -587,11 +595,11 @@ static struct amba_pl011_data uart2_plat = {
 #endif
 };
 
-static void __init mop500_uart_init(void)
+static void __init mop500_uart_init(struct device *parent)
 {
-	db8500_add_uart0(&uart0_plat);
-	db8500_add_uart1(&uart1_plat);
-	db8500_add_uart2(&uart2_plat);
+	db8500_add_uart0(parent, &uart0_plat);
+	db8500_add_uart1(parent, &uart1_plat);
+	db8500_add_uart2(parent, &uart2_plat);
 }
 
 static struct platform_device *snowball_platform_devs[] __initdata = {
@@ -603,21 +611,27 @@ static struct platform_device *snowball_platform_devs[] __initdata = {
 
 static void __init mop500_init_machine(void)
 {
+	struct device *parent = NULL;
 	int i2c0_devs;
+	int i;
 
 	mop500_gpio_keys[0].gpio = GPIO_PROX_SENSOR;
 
-	u8500_init_devices();
+	parent = u8500_init_devices();
 
 	mop500_pins_init();
 
+	/* FIXME: parent of ab8500 should be prcmu */
+	for (i = 0; i < ARRAY_SIZE(mop500_platform_devs); i++)
+		mop500_platform_devs[i]->dev.parent = parent;
+
 	platform_add_devices(mop500_platform_devs,
 			ARRAY_SIZE(mop500_platform_devs));
 
-	mop500_i2c_init();
-	mop500_sdi_init();
-	mop500_spi_init();
-	mop500_uart_init();
+	mop500_i2c_init(parent);
+	mop500_sdi_init(parent);
+	mop500_spi_init(parent);
+	mop500_uart_init(parent);
 
 	i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
 
@@ -631,19 +645,24 @@ static void __init mop500_init_machine(void)
 
 static void __init snowball_init_machine(void)
 {
+	struct device *parent = NULL;
 	int i2c0_devs;
+	int i;
 
-	u8500_init_devices();
+	parent = u8500_init_devices();
 
 	snowball_pins_init();
 
+	for (i = 0; i < ARRAY_SIZE(snowball_platform_devs); i++)
+		snowball_platform_devs[i]->dev.parent = parent;
+
 	platform_add_devices(snowball_platform_devs,
 			ARRAY_SIZE(snowball_platform_devs));
 
-	mop500_i2c_init();
-	snowball_sdi_init();
-	mop500_spi_init();
-	mop500_uart_init();
+	mop500_i2c_init(parent);
+	snowball_sdi_init(parent);
+	mop500_spi_init(parent);
+	mop500_uart_init(parent);
 
 	i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
 	i2c_register_board_info(0, mop500_i2c0_devices, i2c0_devs);
@@ -656,7 +675,9 @@ static void __init snowball_init_machine(void)
 
 static void __init hrefv60_init_machine(void)
 {
+	struct device *parent = NULL;
 	int i2c0_devs;
+	int i;
 
 	/*
 	 * The HREFv60 board removed a GPIO expander and routed
@@ -665,17 +686,20 @@ static void __init hrefv60_init_machine(void)
 	 */
 	mop500_gpio_keys[0].gpio = HREFV60_PROX_SENSE_GPIO;
 
-	u8500_init_devices();
+	parent = u8500_init_devices();
 
 	hrefv60_pins_init();
 
+	for (i = 0; i < ARRAY_SIZE(mop500_platform_devs); i++)
+		mop500_platform_devs[i]->dev.parent = parent;
+
 	platform_add_devices(mop500_platform_devs,
 			ARRAY_SIZE(mop500_platform_devs));
 
-	mop500_i2c_init();
-	hrefv60_sdi_init();
-	mop500_spi_init();
-	mop500_uart_init();
+	mop500_i2c_init(parent);
+	hrefv60_sdi_init(parent);
+	mop500_spi_init(parent);
+	mop500_uart_init(parent);
 
 	i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
 
@@ -718,3 +742,94 @@ MACHINE_START(SNOWBALL, "Calao Systems Snowball platform")
 	.handle_irq	= gic_handle_irq,
 	.init_machine	= snowball_init_machine,
 MACHINE_END
+
+#ifdef CONFIG_MACH_UX500_DT
+
+struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = {
+	OF_DEV_AUXDATA("arm,pl011", 0x80120000, "uart0", &uart0_plat),
+	OF_DEV_AUXDATA("arm,pl011", 0x80121000, "uart1", &uart1_plat),
+	OF_DEV_AUXDATA("arm,pl011", 0x80007000, "uart2", &uart2_plat),
+	OF_DEV_AUXDATA("arm,pl022", 0x80002000, "ssp0",  &ssp0_plat),
+	{},
+};
+
+static const struct of_device_id u8500_soc_node[] = {
+	/* only create devices below soc node */
+	{ .compatible = "stericsson,db8500", },
+	{ },
+};
+
+static void __init u8500_init_machine(void)
+{
+	struct device *parent = NULL;
+	int i2c0_devs;
+	int i;
+
+	parent = u8500_init_devices();
+	i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
+
+	for (i = 0; i < ARRAY_SIZE(mop500_platform_devs); i++)
+		mop500_platform_devs[i]->dev.parent = parent;
+	for (i = 0; i < ARRAY_SIZE(snowball_platform_devs); i++)
+		snowball_platform_devs[i]->dev.parent = parent;
+
+	/* automatically probe child nodes of db8500 device */
+	of_platform_populate(NULL, u8500_soc_node, u8500_auxdata_lookup, parent);
+
+	if (of_machine_is_compatible("st-ericsson,mop500")) {
+		mop500_gpio_keys[0].gpio = GPIO_PROX_SENSOR;
+		mop500_pins_init();
+
+		platform_add_devices(mop500_platform_devs,
+				ARRAY_SIZE(mop500_platform_devs));
+
+		mop500_sdi_init(parent);
+	} else if (of_machine_is_compatible("calaosystems,snowball-a9500")) {
+		snowball_pins_init();
+		platform_add_devices(snowball_platform_devs,
+				ARRAY_SIZE(snowball_platform_devs));
+
+		snowball_sdi_init(parent);
+	} else if (of_machine_is_compatible("st-ericsson,hrefv60+")) {
+		/*
+		 * The HREFv60 board removed a GPIO expander and routed
+		 * all these GPIO pins to the internal GPIO controller
+		 * instead.
+		 */
+		mop500_gpio_keys[0].gpio = HREFV60_PROX_SENSE_GPIO;
+		i2c0_devs -= NUM_PRE_V60_I2C0_DEVICES;
+		hrefv60_pins_init();
+		platform_add_devices(mop500_platform_devs,
+				ARRAY_SIZE(mop500_platform_devs));
+
+		hrefv60_sdi_init(parent);
+	}
+	mop500_i2c_init(parent);
+
+	i2c_register_board_info(0, mop500_i2c0_devices, i2c0_devs);
+	i2c_register_board_info(2, mop500_i2c2_devices,
+				ARRAY_SIZE(mop500_i2c2_devices));
+
+	/* This board has full regulator constraints */
+	regulator_has_full_constraints();
+}
+
+static const char * u8500_dt_board_compat[] = {
+	"calaosystems,snowball-a9500",
+	"st-ericsson,hrefv60+",
+	"st-ericsson,u8500",
+	"st-ericsson,mop500",
+	NULL,
+};
+
+
+DT_MACHINE_START(U8500_DT, "ST-Ericsson U8500 platform (Device Tree Support)")
+	.map_io		= u8500_map_io,
+	.init_irq	= ux500_init_irq,
+	/* we re-use nomadik timer here */
+	.timer		= &ux500_timer,
+	.handle_irq	= gic_handle_irq,
+	.init_machine	= u8500_init_machine,
+	.dt_compat      = u8500_dt_board_compat,
+MACHINE_END
+#endif
diff --git a/arch/arm/mach-ux500/board-mop500.h b/arch/arm/mach-ux500/board-mop500.h
index 7ff6cbffc104..fdcfa8721bb4 100644
--- a/arch/arm/mach-ux500/board-mop500.h
+++ b/arch/arm/mach-ux500/board-mop500.h
@@ -75,10 +75,10 @@
 
 struct i2c_board_info;
 
-extern void mop500_sdi_init(void);
-extern void snowball_sdi_init(void);
-extern void hrefv60_sdi_init(void);
-extern void mop500_sdi_tc35892_init(void);
+extern void mop500_sdi_init(struct device *parent);
+extern void snowball_sdi_init(struct device *parent);
+extern void hrefv60_sdi_init(struct device *parent);
+extern void mop500_sdi_tc35892_init(struct device *parent);
 void __init mop500_u8500uib_init(void);
 void __init mop500_stuib_init(void);
 void __init mop500_pins_init(void);
diff --git a/arch/arm/mach-ux500/board-u5500-sdi.c b/arch/arm/mach-ux500/board-u5500-sdi.c
index 63c3f8058ffc..836112eedde7 100644
--- a/arch/arm/mach-ux500/board-u5500-sdi.c
+++ b/arch/arm/mach-ux500/board-u5500-sdi.c
@@ -66,9 +66,9 @@ static struct mmci_platform_data u5500_sdi0_data = {
 #endif
 };
 
-void __init u5500_sdi_init(void)
+void __init u5500_sdi_init(struct device *parent)
 {
 	nmk_config_pins(u5500_sdi_pins, ARRAY_SIZE(u5500_sdi_pins));
 
-	db5500_add_sdi0(&u5500_sdi0_data);
+	db5500_add_sdi0(parent, &u5500_sdi0_data);
 }
diff --git a/arch/arm/mach-ux500/board-u5500.c b/arch/arm/mach-ux500/board-u5500.c
index 9de9e9c4dbbb..0ff4be72a809 100644
--- a/arch/arm/mach-ux500/board-u5500.c
+++ b/arch/arm/mach-ux500/board-u5500.c
@@ -97,9 +97,9 @@ static struct i2c_board_info __initdata u5500_i2c2_devices[] = {
 	},
 };
 
-static void __init u5500_i2c_init(void)
+static void __init u5500_i2c_init(struct device *parent)
 {
-	db5500_add_i2c2(&u5500_i2c2_data);
+	db5500_add_i2c2(parent, &u5500_i2c2_data);
 	i2c_register_board_info(2, ARRAY_AND_SIZE(u5500_i2c2_devices));
 }
 
@@ -126,20 +126,27 @@ static struct platform_device *u5500_platform_devices[] __initdata = {
 	&ab5500_device,
 };
 
-static void __init u5500_uart_init(void)
+static void __init u5500_uart_init(struct device *parent)
 {
-	db5500_add_uart0(NULL);
-	db5500_add_uart1(NULL);
-	db5500_add_uart2(NULL);
+	db5500_add_uart0(parent, NULL);
+	db5500_add_uart1(parent, NULL);
+	db5500_add_uart2(parent, NULL);
 }
 
 static void __init u5500_init_machine(void)
 {
-	u5500_init_devices();
+	struct device *parent = NULL;
+	int i;
+
+	parent = u5500_init_devices();
 	nmk_config_pins(u5500_pins, ARRAY_SIZE(u5500_pins));
-	u5500_i2c_init();
-	u5500_sdi_init();
-	u5500_uart_init();
+
+	u5500_i2c_init(parent);
+	u5500_sdi_init(parent);
+	u5500_uart_init(parent);
+
+	for (i = 0; i < ARRAY_SIZE(u5500_platform_devices); i++)
+		u5500_platform_devices[i]->dev.parent = parent;
 
 	platform_add_devices(u5500_platform_devices,
 		ARRAY_SIZE(u5500_platform_devices));
diff --git a/arch/arm/mach-ux500/cache-l2x0.c b/arch/arm/mach-ux500/cache-l2x0.c
index da5569d83d58..77a75ed0df67 100644
--- a/arch/arm/mach-ux500/cache-l2x0.c
+++ b/arch/arm/mach-ux500/cache-l2x0.c
@@ -5,6 +5,8 @@
  */
 
 #include <linux/io.h>
+#include <linux/of.h>
+
 #include <asm/cacheflush.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <mach/hardware.h>
@@ -45,7 +47,10 @@ static int __init ux500_l2x0_init(void)
 	ux500_l2x0_unlock();
 
 	/* 64KB way size, 8 way associativity, force WA */
-	l2x0_init(l2x0_base, 0x3e060000, 0xc0000fff);
+	if (of_have_populated_dt())
+		l2x0_of_init(0x3e060000, 0xc0000fff);
+	else
+		l2x0_init(l2x0_base, 0x3e060000, 0xc0000fff);
 
 	/*
 	 * We can't disable l2 as we are in non secure mode, currently
diff --git a/arch/arm/mach-ux500/cpu-db5500.c b/arch/arm/mach-ux500/cpu-db5500.c
index 18aa5c05c69e..bca47f32082f 100644
--- a/arch/arm/mach-ux500/cpu-db5500.c
+++ b/arch/arm/mach-ux500/cpu-db5500.c
@@ -147,13 +147,13 @@ static resource_size_t __initdata db5500_gpio_base[] = {
 	U5500_GPIOBANK7_BASE,
 };
 
-static void __init db5500_add_gpios(void)
+static void __init db5500_add_gpios(struct device *parent)
 {
 	struct nmk_gpio_platform_data pdata = {
 		/* No custom data yet */
 	};
 
-	dbx500_add_gpios(ARRAY_AND_SIZE(db5500_gpio_base),
+	dbx500_add_gpios(parent, ARRAY_AND_SIZE(db5500_gpio_base),
 			 IRQ_DB5500_GPIO0, &pdata);
 }
 
@@ -212,14 +212,36 @@ static int usb_db5500_tx_dma_cfg[] = {
 	DB5500_DMA_DEV38_USB_OTG_OEP_8
 };
 
-void __init u5500_init_devices(void)
+static const char *db5500_read_soc_id(void)
 {
-	db5500_add_gpios();
+	return kasprintf(GFP_KERNEL, "u5500 currently unsupported\n");
+}
+
+static struct device * __init db5500_soc_device_init(void)
+{
+	const char *soc_id = db5500_read_soc_id();
+
+	return ux500_soc_device_init(soc_id);
+}
+
+struct device * __init u5500_init_devices(void)
+{
+	struct device *parent;
+	int i;
+
+	parent = db5500_soc_device_init();
+
+	db5500_add_gpios(parent);
 	db5500_pmu_init();
-	db5500_dma_init();
-	db5500_add_rtc();
-	db5500_add_usb(usb_db5500_rx_dma_cfg, usb_db5500_tx_dma_cfg);
+	db5500_dma_init(parent);
+	db5500_add_rtc(parent);
+	db5500_add_usb(parent, usb_db5500_rx_dma_cfg, usb_db5500_tx_dma_cfg);
+
+	for (i = 0; i < ARRAY_SIZE(db5500_platform_devs); i++)
+		db5500_platform_devs[i]->dev.parent = parent;
 
 	platform_add_devices(db5500_platform_devs,
 			     ARRAY_SIZE(db5500_platform_devs));
+
+	return parent;
 }
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 7176ee7491ab..9bd8163896cf 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -24,6 +24,7 @@
 #include <mach/setup.h>
 #include <mach/devices.h>
 #include <mach/usb.h>
+#include <mach/db8500-regs.h>
 
 #include "devices-db8500.h"
 #include "ste-dma40-db8500.h"
@@ -132,13 +133,13 @@ static resource_size_t __initdata db8500_gpio_base[] = {
 	U8500_GPIOBANK8_BASE,
 };
 
-static void __init db8500_add_gpios(void)
+static void __init db8500_add_gpios(struct device *parent)
 {
 	struct nmk_gpio_platform_data pdata = {
 		.supports_sleepmode = true,
 	};
 
-	dbx500_add_gpios(ARRAY_AND_SIZE(db8500_gpio_base),
+	dbx500_add_gpios(parent, ARRAY_AND_SIZE(db8500_gpio_base),
 			 IRQ_DB8500_GPIO0, &pdata);
 }
 
@@ -164,17 +165,44 @@ static int usb_db8500_tx_dma_cfg[] = {
 	DB8500_DMA_DEV39_USB_OTG_OEP_8
 };
 
+static const char *db8500_read_soc_id(void)
+{
+	void __iomem *uid = __io_address(U8500_BB_UID_BASE);
+
+	return kasprintf(GFP_KERNEL, "%08x%08x%08x%08x%08x",
+			 readl((u32 *)uid+1),
+			 readl((u32 *)uid+1), readl((u32 *)uid+2),
+			 readl((u32 *)uid+3), readl((u32 *)uid+4));
+}
+
+static struct device * __init db8500_soc_device_init(void)
+{
+	const char *soc_id = db8500_read_soc_id();
+
+	return ux500_soc_device_init(soc_id);
+}
+
 /*
  * This function is called from the board init
  */
-void __init u8500_init_devices(void)
+struct device * __init u8500_init_devices(void)
 {
-	db8500_add_rtc();
-	db8500_add_gpios();
-	db8500_add_usb(usb_db8500_rx_dma_cfg, usb_db8500_tx_dma_cfg);
+	struct device *parent;
+	int i;
+
+	parent = db8500_soc_device_init();
+
+	db8500_add_rtc(parent);
+	db8500_add_gpios(parent);
+	db8500_add_usb(parent, usb_db8500_rx_dma_cfg, usb_db8500_tx_dma_cfg);
+
+	platform_device_register_data(parent,
+		"cpufreq-u8500", -1, NULL, 0);
+
+	for (i = 0; i < ARRAY_SIZE(platform_devs); i++)
+		platform_devs[i]->dev.parent = parent;
 
-	platform_device_register_simple("cpufreq-u8500", -1, NULL, 0);
 	platform_add_devices(platform_devs, ARRAY_SIZE(platform_devs));
 
-	return ;
+	return parent;
 }
diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c
index 851308bf6424..d11f3892a27d 100644
--- a/arch/arm/mach-ux500/cpu.c
+++ b/arch/arm/mach-ux500/cpu.c
@@ -2,6 +2,7 @@
  * Copyright (C) ST-Ericsson SA 2010
  *
  * Author: Rabin Vincent <rabin.vincent@stericsson.com> for ST-Ericsson
+ * Author: Lee Jones <lee.jones@linaro.org> for ST-Ericsson
  * License terms: GNU General Public License (GPL) version 2
  */
 
@@ -11,6 +12,12 @@
 #include <linux/mfd/db8500-prcmu.h>
 #include <linux/mfd/db5500-prcmu.h>
 #include <linux/clksrc-dbx500-prcmu.h>
+#include <linux/sys_soc.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
 
 #include <asm/hardware/gic.h>
 #include <asm/mach/map.h>
@@ -23,6 +30,11 @@
 
 void __iomem *_PRCMU_BASE;
 
+static const struct of_device_id ux500_dt_irq_match[] = {
+	{ .compatible = "arm,cortex-a9-gic", .data = gic_of_init, },
+	{},
+};
+
 void __init ux500_init_irq(void)
 {
 	void __iomem *dist_base;
@@ -37,7 +49,12 @@ void __init ux500_init_irq(void)
 	} else
 		ux500_unknown_soc();
 
-	gic_init(0, 29, dist_base, cpu_base);
+#ifdef CONFIG_OF
+	if (of_have_populated_dt())
+		of_irq_init(ux500_dt_irq_match);
+	else
+#endif
+		gic_init(0, 29, dist_base, cpu_base);
 
 	/*
 	 * Init clocks here so that they are available for system timer
@@ -49,3 +66,73 @@ void __init ux500_init_irq(void)
 		db8500_prcmu_early_init();
 	clk_init();
 }
+
+static const char * __init ux500_get_machine(void)
+{
+	return kasprintf(GFP_KERNEL, "DB%4x", dbx500_partnumber());
+}
+
+static const char * __init ux500_get_family(void)
+{
+	return kasprintf(GFP_KERNEL, "ux500");
+}
+
+static const char * __init ux500_get_revision(void)
+{
+	unsigned int rev = dbx500_revision();
+
+	if (rev == 0x01)
+		return kasprintf(GFP_KERNEL, "%s", "ED");
+	else if (rev >= 0xA0)
+		return kasprintf(GFP_KERNEL, "%d.%d",
+				 (rev >> 4) - 0xA + 1, rev & 0xf);
+
+	return kasprintf(GFP_KERNEL, "%s", "Unknown");
+}
+
+static ssize_t ux500_get_process(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	if (dbx500_id.process == 0x00)
+		return sprintf(buf, "Standard\n");
+
+	return sprintf(buf, "%02xnm\n", dbx500_id.process);
+}
+
+static void __init soc_info_populate(struct soc_device_attribute *soc_dev_attr,
+				     const char *soc_id)
+{
+	soc_dev_attr->soc_id   = soc_id;
+	soc_dev_attr->machine  = ux500_get_machine();
+	soc_dev_attr->family   = ux500_get_family();
+	soc_dev_attr->revision = ux500_get_revision();
+}
+
+struct device_attribute ux500_soc_attr =
+	__ATTR(process,  S_IRUGO, ux500_get_process,  NULL);
+
+struct device * __init ux500_soc_device_init(const char *soc_id)
+{
+	struct device *parent;
+	struct soc_device *soc_dev;
+	struct soc_device_attribute *soc_dev_attr;
+
+	soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL);
+	if (!soc_dev_attr)
+		return ERR_PTR(-ENOMEM);
+
+	soc_info_populate(soc_dev_attr, soc_id);
+
+	soc_dev = soc_device_register(soc_dev_attr);
+	if (IS_ERR_OR_NULL(soc_dev)) {
+	        kfree(soc_dev_attr);
+		return NULL;
+	}
+
+	parent = soc_device_to_device(soc_dev);
+	if (!IS_ERR_OR_NULL(parent))
+		device_create_file(parent, &ux500_soc_attr);
+
+	return parent;
+}
diff --git a/arch/arm/mach-ux500/devices-common.c b/arch/arm/mach-ux500/devices-common.c
index 898a64517b09..c5312a4b49f5 100644
--- a/arch/arm/mach-ux500/devices-common.c
+++ b/arch/arm/mach-ux500/devices-common.c
@@ -20,8 +20,9 @@
 #include "devices-common.h"
 
 struct amba_device *
-dbx500_add_amba_device(const char *name, resource_size_t base,
-		       int irq, void *pdata, unsigned int periphid)
+dbx500_add_amba_device(struct device *parent, const char *name,
+		       resource_size_t base, int irq, void *pdata,
+		       unsigned int periphid)
 {
 	struct amba_device *dev;
 	int ret;
@@ -39,6 +40,8 @@ dbx500_add_amba_device(const char *name, resource_size_t base,
 
 	dev->dev.platform_data = pdata;
 
+	dev->dev.parent = parent;
+
 	ret = amba_device_add(dev, &iomem_resource);
 	if (ret) {
 		amba_device_put(dev);
@@ -49,60 +52,7 @@ dbx500_add_amba_device(const char *name, resource_size_t base,
 }
 
 static struct platform_device *
-dbx500_add_platform_device(const char *name, int id, void *pdata,
-			   struct resource *res, int resnum)
-{
-	struct platform_device *dev;
-	int ret;
-
-	dev = platform_device_alloc(name, id);
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
-
-	dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
-	dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
-
-	ret = platform_device_add_resources(dev, res, resnum);
-	if (ret)
-		goto out_free;
-
-	dev->dev.platform_data = pdata;
-
-	ret = platform_device_add(dev);
-	if (ret)
-		goto out_free;
-
-	return dev;
-
-out_free:
-	platform_device_put(dev);
-	return ERR_PTR(ret);
-}
-
-struct platform_device *
-dbx500_add_platform_device_4k1irq(const char *name, int id,
-				  resource_size_t base,
-				  int irq, void *pdata)
-{
-	struct resource resources[] = {
-		[0] = {
-			.start	= base,
-			.end	= base + SZ_4K - 1,
-			.flags	= IORESOURCE_MEM,
-		},
-		[1] = {
-			.start	= irq,
-			.end	= irq,
-			.flags	= IORESOURCE_IRQ,
-		}
-	};
-
-	return dbx500_add_platform_device(name, id, pdata, resources,
-					  ARRAY_SIZE(resources));
-}
-
-static struct platform_device *
-dbx500_add_gpio(int id, resource_size_t addr, int irq,
+dbx500_add_gpio(struct device *parent, int id, resource_size_t addr, int irq,
 		struct nmk_gpio_platform_data *pdata)
 {
 	struct resource resources[] = {
@@ -118,13 +68,18 @@ dbx500_add_gpio(int id, resource_size_t addr, int irq,
 		}
 	};
 
-	return platform_device_register_resndata(NULL, "gpio", id,
-				resources, ARRAY_SIZE(resources),
-				pdata, sizeof(*pdata));
+	return platform_device_register_resndata(
+		parent,
+		"gpio",
+		id,
+		resources,
+		ARRAY_SIZE(resources),
+		pdata,
+		sizeof(*pdata));
 }
 
-void dbx500_add_gpios(resource_size_t *base, int num, int irq,
-		      struct nmk_gpio_platform_data *pdata)
+void dbx500_add_gpios(struct device *parent, resource_size_t *base, int num,
+		      int irq, struct nmk_gpio_platform_data *pdata)
 {
 	int first = 0;
 	int i;
@@ -134,6 +89,6 @@ void dbx500_add_gpios(resource_size_t *base, int num, int irq,
 		pdata->first_irq = NOMADIK_GPIO_TO_IRQ(first);
 		pdata->num_gpio = 32;
 
-		dbx500_add_gpio(i, base[i], irq, pdata);
+		dbx500_add_gpio(parent, i, base[i], irq, pdata);
 	}
 }
diff --git a/arch/arm/mach-ux500/devices-common.h b/arch/arm/mach-ux500/devices-common.h
index 7825705033bf..39c74ec82add 100644
--- a/arch/arm/mach-ux500/devices-common.h
+++ b/arch/arm/mach-ux500/devices-common.h
@@ -8,80 +8,89 @@
 #ifndef __DEVICES_COMMON_H
 #define __DEVICES_COMMON_H
 
-extern struct amba_device *
-dbx500_add_amba_device(const char *name, resource_size_t base,
-		       int irq, void *pdata, unsigned int periphid);
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/sys_soc.h>
+#include <plat/i2c.h>
 
-extern struct platform_device *
-dbx500_add_platform_device_4k1irq(const char *name, int id,
-				  resource_size_t base,
-				  int irq, void *pdata);
+extern struct amba_device *
+dbx500_add_amba_device(struct device *parent, const char *name,
+		       resource_size_t base, int irq, void *pdata,
+		       unsigned int periphid);
 
 struct spi_master_cntlr;
 
 static inline struct amba_device *
-dbx500_add_msp_spi(const char *name, resource_size_t base, int irq,
+dbx500_add_msp_spi(struct device *parent, const char *name,
+		   resource_size_t base, int irq,
 		   struct spi_master_cntlr *pdata)
 {
-	return dbx500_add_amba_device(name, base, irq, pdata, 0);
+	return dbx500_add_amba_device(parent, name, base, irq,
+				      pdata, 0);
 }
 
 static inline struct amba_device *
-dbx500_add_spi(const char *name, resource_size_t base, int irq,
-	       struct spi_master_cntlr *pdata,
+dbx500_add_spi(struct device *parent, const char *name, resource_size_t base,
+	       int irq, struct spi_master_cntlr *pdata,
 	       u32 periphid)
 {
-	return dbx500_add_amba_device(name, base, irq, pdata, periphid);
+	return dbx500_add_amba_device(parent, name, base, irq,
+				      pdata, periphid);
 }
 
 struct mmci_platform_data;
 
 static inline struct amba_device *
-dbx500_add_sdi(const char *name, resource_size_t base, int irq,
-	       struct mmci_platform_data *pdata,
-	       u32 periphid)
+dbx500_add_sdi(struct device *parent, const char *name, resource_size_t base,
+	       int irq, struct mmci_platform_data *pdata, u32 periphid)
 {
-	return dbx500_add_amba_device(name, base, irq, pdata, periphid);
+	return dbx500_add_amba_device(parent, name, base, irq,
+				      pdata, periphid);
 }
 
 struct amba_pl011_data;
 
 static inline struct amba_device *
-dbx500_add_uart(const char *name, resource_size_t base, int irq,
-		struct amba_pl011_data *pdata)
+dbx500_add_uart(struct device *parent, const char *name, resource_size_t base,
+		int irq, struct amba_pl011_data *pdata)
 {
-	return dbx500_add_amba_device(name, base, irq, pdata, 0);
+	return dbx500_add_amba_device(parent, name, base, irq, pdata, 0);
 }
 
 struct nmk_i2c_controller;
 
 static inline struct platform_device *
-dbx500_add_i2c(int id, resource_size_t base, int irq,
-	       struct nmk_i2c_controller *pdata)
-{
-	return dbx500_add_platform_device_4k1irq("nmk-i2c", id, base, irq,
-						 pdata);
-}
-
-struct msp_i2s_platform_data;
-
-static inline struct platform_device *
-dbx500_add_msp_i2s(int id, resource_size_t base, int irq,
-		   struct msp_i2s_platform_data *pdata)
+dbx500_add_i2c(struct device *parent, int id, resource_size_t base, int irq,
+	       struct nmk_i2c_controller *data)
 {
-	return dbx500_add_platform_device_4k1irq("MSP_I2S", id, base, irq,
-						 pdata);
+	struct resource res[] = {
+		DEFINE_RES_MEM(base, SZ_4K),
+		DEFINE_RES_IRQ(irq),
+	};
+
+	struct platform_device_info pdevinfo = {
+		.parent = parent,
+		.name = "nmk-i2c",
+		.id = id,
+		.res = res,
+		.num_res = ARRAY_SIZE(res),
+		.data = data,
+		.size_data = sizeof(*data),
+		.dma_mask = DMA_BIT_MASK(32),
+	};
+
+	return platform_device_register_full(&pdevinfo);
 }
 
 static inline struct amba_device *
-dbx500_add_rtc(resource_size_t base, int irq)
+dbx500_add_rtc(struct device *parent, resource_size_t base, int irq)
 {
-	return dbx500_add_amba_device("rtc-pl031", base, irq, NULL, 0);
+	return dbx500_add_amba_device(parent, "rtc-pl031", base, irq, NULL, 0);
 }
 
 struct nmk_gpio_platform_data;
 
-void dbx500_add_gpios(resource_size_t *base, int num, int irq,
-		      struct nmk_gpio_platform_data *pdata);
+void dbx500_add_gpios(struct device *parent, resource_size_t *base, int num,
+		      int irq, struct nmk_gpio_platform_data *pdata);
 
 #endif
diff --git a/arch/arm/mach-ux500/devices-db5500.h b/arch/arm/mach-ux500/devices-db5500.h
index 0c4bccd02b90..e70955502c35 100644
--- a/arch/arm/mach-ux500/devices-db5500.h
+++ b/arch/arm/mach-ux500/devices-db5500.h
@@ -10,70 +10,90 @@
 
 #include "devices-common.h"
 
-#define db5500_add_i2c1(pdata) \
-	dbx500_add_i2c(1, U5500_I2C1_BASE, IRQ_DB5500_I2C1, pdata)
-#define db5500_add_i2c2(pdata) \
-	dbx500_add_i2c(2, U5500_I2C2_BASE, IRQ_DB5500_I2C2, pdata)
-#define db5500_add_i2c3(pdata) \
-	dbx500_add_i2c(3, U5500_I2C3_BASE, IRQ_DB5500_I2C3, pdata)
+#define db5500_add_i2c1(parent, pdata) \
+	dbx500_add_i2c(parent, 1, U5500_I2C1_BASE, IRQ_DB5500_I2C1, pdata)
+#define db5500_add_i2c2(parent, pdata) \
+	dbx500_add_i2c(parent, 2, U5500_I2C2_BASE, IRQ_DB5500_I2C2, pdata)
+#define db5500_add_i2c3(parent, pdata) \
+	dbx500_add_i2c(parent, 3, U5500_I2C3_BASE, IRQ_DB5500_I2C3, pdata)
 
-#define db5500_add_msp0_i2s(pdata) \
-	dbx500_add_msp_i2s(0, U5500_MSP0_BASE, IRQ_DB5500_MSP0, pdata)
-#define db5500_add_msp1_i2s(pdata) \
-	dbx500_add_msp_i2s(1, U5500_MSP1_BASE, IRQ_DB5500_MSP1, pdata)
-#define db5500_add_msp2_i2s(pdata) \
-	dbx500_add_msp_i2s(2, U5500_MSP2_BASE, IRQ_DB5500_MSP2, pdata)
+#define db5500_add_msp0_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp0", U5500_MSP0_BASE, \
+			   IRQ_DB5500_MSP0, pdata)
+#define db5500_add_msp1_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp1", U5500_MSP1_BASE, \
+			   IRQ_DB5500_MSP1, pdata)
+#define db5500_add_msp2_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp2", U5500_MSP2_BASE, \
+			   IRQ_DB5500_MSP2, pdata)
 
-#define db5500_add_msp0_spi(pdata) \
-	dbx500_add_msp_spi("msp0", U5500_MSP0_BASE, IRQ_DB5500_MSP0, pdata)
-#define db5500_add_msp1_spi(pdata) \
-	dbx500_add_msp_spi("msp1", U5500_MSP1_BASE, IRQ_DB5500_MSP1, pdata)
-#define db5500_add_msp2_spi(pdata) \
-	dbx500_add_msp_spi("msp2", U5500_MSP2_BASE, IRQ_DB5500_MSP2, pdata)
+#define db5500_add_msp0_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp0", U5500_MSP0_BASE, \
+			  IRQ_DB5500_MSP0, pdata)
+#define db5500_add_msp1_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp1", U5500_MSP1_BASE, \
+			  IRQ_DB5500_MSP1, pdata)
+#define db5500_add_msp2_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp2", U5500_MSP2_BASE, \
+			  IRQ_DB5500_MSP2, pdata)
 
-#define db5500_add_rtc() \
-	dbx500_add_rtc(U5500_RTC_BASE, IRQ_DB5500_RTC);
+#define db5500_add_rtc(parent) \
+	dbx500_add_rtc(parent, U5500_RTC_BASE, IRQ_DB5500_RTC);
 
-#define db5500_add_usb(rx_cfg, tx_cfg) \
-	ux500_add_usb(U5500_USBOTG_BASE, IRQ_DB5500_USBOTG, rx_cfg, tx_cfg)
+#define db5500_add_usb(parent, rx_cfg, tx_cfg) \
+	ux500_add_usb(parent, U5500_USBOTG_BASE, \
+		      IRQ_DB5500_USBOTG, rx_cfg, tx_cfg)
 
-#define db5500_add_sdi0(pdata) \
-	dbx500_add_sdi("sdi0", U5500_SDI0_BASE, IRQ_DB5500_SDMMC0, pdata, \
+#define db5500_add_sdi0(parent, pdata) \
+	dbx500_add_sdi(parent, "sdi0", U5500_SDI0_BASE, \
+		       IRQ_DB5500_SDMMC0, pdata,	\
 		       0x10480180)
-#define db5500_add_sdi1(pdata) \
-	dbx500_add_sdi("sdi1", U5500_SDI1_BASE, IRQ_DB5500_SDMMC1, pdata, \
+#define db5500_add_sdi1(parent, pdata) \
+	dbx500_add_sdi(parent, "sdi1", U5500_SDI1_BASE, \
+		       IRQ_DB5500_SDMMC1, pdata,	\
 		       0x10480180)
-#define db5500_add_sdi2(pdata) \
-	dbx500_add_sdi("sdi2", U5500_SDI2_BASE, IRQ_DB5500_SDMMC2, pdata \
+#define db5500_add_sdi2(parent, pdata) \
+	dbx500_add_sdi(parent, "sdi2", U5500_SDI2_BASE, \
+		       IRQ_DB5500_SDMMC2, pdata		\
 		       0x10480180)
-#define db5500_add_sdi3(pdata) \
-	dbx500_add_sdi("sdi3", U5500_SDI3_BASE, IRQ_DB5500_SDMMC3, pdata \
+#define db5500_add_sdi3(parent, pdata) \
+	dbx500_add_sdi(parent, "sdi3", U5500_SDI3_BASE, \
+		       IRQ_DB5500_SDMMC3, pdata		\
 		       0x10480180)
-#define db5500_add_sdi4(pdata) \
-	dbx500_add_sdi("sdi4", U5500_SDI4_BASE, IRQ_DB5500_SDMMC4, pdata \
+#define db5500_add_sdi4(parent, pdata) \
+	dbx500_add_sdi(parent, "sdi4", U5500_SDI4_BASE, \
+		       IRQ_DB5500_SDMMC4, pdata		\
 		       0x10480180)
 
 /* This one has a bad peripheral ID in the U5500 silicon */
-#define db5500_add_spi0(pdata) \
-	dbx500_add_spi("spi0", U5500_SPI0_BASE, IRQ_DB5500_SPI0, pdata, \
+#define db5500_add_spi0(parent, pdata) \
+	dbx500_add_spi(parent, "spi0", U5500_SPI0_BASE, \
+		       IRQ_DB5500_SPI0, pdata,		\
 		       0x10080023)
-#define db5500_add_spi1(pdata) \
-	dbx500_add_spi("spi1", U5500_SPI1_BASE, IRQ_DB5500_SPI1, pdata, \
+#define db5500_add_spi1(parent, pdata) \
+	dbx500_add_spi(parent, "spi1", U5500_SPI1_BASE, \
+		       IRQ_DB5500_SPI1, pdata,		\
 		       0x10080023)
-#define db5500_add_spi2(pdata) \
-	dbx500_add_spi("spi2", U5500_SPI2_BASE, IRQ_DB5500_SPI2, pdata \
+#define db5500_add_spi2(parent, pdata) \
+	dbx500_add_spi(parent, "spi2", U5500_SPI2_BASE, \
+		       IRQ_DB5500_SPI2, pdata		\
 		       0x10080023)
-#define db5500_add_spi3(pdata) \
-	dbx500_add_spi("spi3", U5500_SPI3_BASE, IRQ_DB5500_SPI3, pdata \
+#define db5500_add_spi3(parent, pdata) \
+	dbx500_add_spi(parent, "spi3", U5500_SPI3_BASE, \
+		       IRQ_DB5500_SPI3, pdata		\
 		       0x10080023)
 
-#define db5500_add_uart0(plat) \
-	dbx500_add_uart("uart0", U5500_UART0_BASE, IRQ_DB5500_UART0, plat)
-#define db5500_add_uart1(plat) \
-	dbx500_add_uart("uart1", U5500_UART1_BASE, IRQ_DB5500_UART1, plat)
-#define db5500_add_uart2(plat) \
-	dbx500_add_uart("uart2", U5500_UART2_BASE, IRQ_DB5500_UART2, plat)
-#define db5500_add_uart3(plat) \
-	dbx500_add_uart("uart3", U5500_UART3_BASE, IRQ_DB5500_UART3, plat)
+#define db5500_add_uart0(parent, plat) \
+	dbx500_add_uart(parent, "uart0", U5500_UART0_BASE, \
+			IRQ_DB5500_UART0, plat)
+#define db5500_add_uart1(parent, plat) \
+	dbx500_add_uart(parent, "uart1", U5500_UART1_BASE, \
+			IRQ_DB5500_UART1, plat)
+#define db5500_add_uart2(parent, plat) \
+	dbx500_add_uart(parent, "uart2", U5500_UART2_BASE, \
+			IRQ_DB5500_UART2, plat)
+#define db5500_add_uart3(parent, plat) \
+	dbx500_add_uart(parent, "uart3", U5500_UART3_BASE, \
+			IRQ_DB5500_UART3, plat)
 
 #endif
diff --git a/arch/arm/mach-ux500/devices-db8500.h b/arch/arm/mach-ux500/devices-db8500.h
index cbd4a9ae8109..9fd93e9da529 100644
--- a/arch/arm/mach-ux500/devices-db8500.h
+++ b/arch/arm/mach-ux500/devices-db8500.h
@@ -14,88 +14,114 @@ struct ske_keypad_platform_data;
 struct pl022_ssp_controller;
 
 static inline struct platform_device *
-db8500_add_ske_keypad(struct ske_keypad_platform_data *pdata)
+db8500_add_ske_keypad(struct device *parent,
+		      struct ske_keypad_platform_data *pdata,
+		      size_t size)
 {
-	return dbx500_add_platform_device_4k1irq("nmk-ske-keypad", -1,
-						 U8500_SKE_BASE,
-						 IRQ_DB8500_KB, pdata);
+	struct resource resources[] = {
+		DEFINE_RES_MEM(U8500_SKE_BASE, SZ_4K),
+		DEFINE_RES_IRQ(IRQ_DB8500_KB),
+	};
+
+	return platform_device_register_resndata(parent, "nmk-ske-keypad", -1,
+						 resources, 2, pdata, size);
 }
 
 static inline struct amba_device *
-db8500_add_ssp(const char *name, resource_size_t base, int irq,
-	       struct pl022_ssp_controller *pdata)
+db8500_add_ssp(struct device *parent, const char *name, resource_size_t base,
+	       int irq, struct pl022_ssp_controller *pdata)
 {
-	return dbx500_add_amba_device(name, base, irq, pdata, 0);
+	return dbx500_add_amba_device(parent, name, base, irq, pdata, 0);
 }
 
 
-#define db8500_add_i2c0(pdata) \
-	dbx500_add_i2c(0, U8500_I2C0_BASE, IRQ_DB8500_I2C0, pdata)
-#define db8500_add_i2c1(pdata) \
-	dbx500_add_i2c(1, U8500_I2C1_BASE, IRQ_DB8500_I2C1, pdata)
-#define db8500_add_i2c2(pdata) \
-	dbx500_add_i2c(2, U8500_I2C2_BASE, IRQ_DB8500_I2C2, pdata)
-#define db8500_add_i2c3(pdata) \
-	dbx500_add_i2c(3, U8500_I2C3_BASE, IRQ_DB8500_I2C3, pdata)
-#define db8500_add_i2c4(pdata) \
-	dbx500_add_i2c(4, U8500_I2C4_BASE, IRQ_DB8500_I2C4, pdata)
-
-#define db8500_add_msp0_i2s(pdata) \
-	dbx500_add_msp_i2s(0, U8500_MSP0_BASE, IRQ_DB8500_MSP0, pdata)
-#define db8500_add_msp1_i2s(pdata) \
-	dbx500_add_msp_i2s(1, U8500_MSP1_BASE, IRQ_DB8500_MSP1, pdata)
-#define db8500_add_msp2_i2s(pdata) \
-	dbx500_add_msp_i2s(2, U8500_MSP2_BASE, IRQ_DB8500_MSP2, pdata)
-#define db8500_add_msp3_i2s(pdata) \
-	dbx500_add_msp_i2s(3, U8500_MSP3_BASE, IRQ_DB8500_MSP1, pdata)
-
-#define db8500_add_msp0_spi(pdata) \
-	dbx500_add_msp_spi("msp0", U8500_MSP0_BASE, IRQ_DB8500_MSP0, pdata)
-#define db8500_add_msp1_spi(pdata) \
-	dbx500_add_msp_spi("msp1", U8500_MSP1_BASE, IRQ_DB8500_MSP1, pdata)
-#define db8500_add_msp2_spi(pdata) \
-	dbx500_add_msp_spi("msp2", U8500_MSP2_BASE, IRQ_DB8500_MSP2, pdata)
-#define db8500_add_msp3_spi(pdata) \
-	dbx500_add_msp_spi("msp3", U8500_MSP3_BASE, IRQ_DB8500_MSP1, pdata)
-
-#define db8500_add_rtc() \
-	dbx500_add_rtc(U8500_RTC_BASE, IRQ_DB8500_RTC);
-
-#define db8500_add_usb(rx_cfg, tx_cfg) \
-	ux500_add_usb(U8500_USBOTG_BASE, IRQ_DB8500_USBOTG, rx_cfg, tx_cfg)
-
-#define db8500_add_sdi0(pdata, pid) \
-	dbx500_add_sdi("sdi0", U8500_SDI0_BASE, IRQ_DB8500_SDMMC0, pdata, pid)
-#define db8500_add_sdi1(pdata, pid) \
-	dbx500_add_sdi("sdi1", U8500_SDI1_BASE, IRQ_DB8500_SDMMC1, pdata, pid)
-#define db8500_add_sdi2(pdata, pid) \
-	dbx500_add_sdi("sdi2", U8500_SDI2_BASE, IRQ_DB8500_SDMMC2, pdata, pid)
-#define db8500_add_sdi3(pdata, pid) \
-	dbx500_add_sdi("sdi3", U8500_SDI3_BASE, IRQ_DB8500_SDMMC3, pdata, pid)
-#define db8500_add_sdi4(pdata, pid) \
-	dbx500_add_sdi("sdi4", U8500_SDI4_BASE, IRQ_DB8500_SDMMC4, pdata, pid)
-#define db8500_add_sdi5(pdata, pid) \
-	dbx500_add_sdi("sdi5", U8500_SDI5_BASE, IRQ_DB8500_SDMMC5, pdata, pid)
-
-#define db8500_add_ssp0(pdata) \
-	db8500_add_ssp("ssp0", U8500_SSP0_BASE, IRQ_DB8500_SSP0, pdata)
-#define db8500_add_ssp1(pdata) \
-	db8500_add_ssp("ssp1", U8500_SSP1_BASE, IRQ_DB8500_SSP1, pdata)
-
-#define db8500_add_spi0(pdata) \
-	dbx500_add_spi("spi0", U8500_SPI0_BASE, IRQ_DB8500_SPI0, pdata, 0)
-#define db8500_add_spi1(pdata) \
-	dbx500_add_spi("spi1", U8500_SPI1_BASE, IRQ_DB8500_SPI1, pdata, 0)
-#define db8500_add_spi2(pdata) \
-	dbx500_add_spi("spi2", U8500_SPI2_BASE, IRQ_DB8500_SPI2, pdata, 0)
-#define db8500_add_spi3(pdata) \
-	dbx500_add_spi("spi3", U8500_SPI3_BASE, IRQ_DB8500_SPI3, pdata, 0)
-
-#define db8500_add_uart0(pdata) \
-	dbx500_add_uart("uart0", U8500_UART0_BASE, IRQ_DB8500_UART0, pdata)
-#define db8500_add_uart1(pdata) \
-	dbx500_add_uart("uart1", U8500_UART1_BASE, IRQ_DB8500_UART1, pdata)
-#define db8500_add_uart2(pdata) \
-	dbx500_add_uart("uart2", U8500_UART2_BASE, IRQ_DB8500_UART2, pdata)
+#define db8500_add_i2c0(parent, pdata) \
+	dbx500_add_i2c(parent, 0, U8500_I2C0_BASE, IRQ_DB8500_I2C0, pdata)
+#define db8500_add_i2c1(parent, pdata) \
+	dbx500_add_i2c(parent, 1, U8500_I2C1_BASE, IRQ_DB8500_I2C1, pdata)
+#define db8500_add_i2c2(parent, pdata) \
+	dbx500_add_i2c(parent, 2, U8500_I2C2_BASE, IRQ_DB8500_I2C2, pdata)
+#define db8500_add_i2c3(parent, pdata) \
+	dbx500_add_i2c(parent, 3, U8500_I2C3_BASE, IRQ_DB8500_I2C3, pdata)
+#define db8500_add_i2c4(parent, pdata) \
+	dbx500_add_i2c(parent, 4, U8500_I2C4_BASE, IRQ_DB8500_I2C4, pdata)
+
+#define db8500_add_msp0_i2s(parent, pdata) \
+	dbx500_add_msp_i2s(parent, 0, U8500_MSP0_BASE, IRQ_DB8500_MSP0, pdata)
+#define db8500_add_msp1_i2s(parent, pdata) \
+	dbx500_add_msp_i2s(parent, 1, U8500_MSP1_BASE, IRQ_DB8500_MSP1, pdata)
+#define db8500_add_msp2_i2s(parent, pdata) \
+	dbx500_add_msp_i2s(parent, 2, U8500_MSP2_BASE, IRQ_DB8500_MSP2, pdata)
+#define db8500_add_msp3_i2s(parent, pdata) \
+	dbx500_add_msp_i2s(parent, 3, U8500_MSP3_BASE, IRQ_DB8500_MSP1, pdata)
+
+#define db8500_add_msp0_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp0", U8500_MSP0_BASE, \
+			   IRQ_DB8500_MSP0, pdata)
+#define db8500_add_msp1_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp1", U8500_MSP1_BASE, \
+			   IRQ_DB8500_MSP1, pdata)
+#define db8500_add_msp2_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp2", U8500_MSP2_BASE, \
+			   IRQ_DB8500_MSP2, pdata)
+#define db8500_add_msp3_spi(parent, pdata) \
+	dbx500_add_msp_spi(parent, "msp3", U8500_MSP3_BASE, \
+			   IRQ_DB8500_MSP1, pdata)
+
+#define db8500_add_rtc(parent) \
+	dbx500_add_rtc(parent, U8500_RTC_BASE, IRQ_DB8500_RTC);
+
+#define db8500_add_usb(parent, rx_cfg, tx_cfg) \
+	ux500_add_usb(parent, U8500_USBOTG_BASE, \
+		      IRQ_DB8500_USBOTG, rx_cfg, tx_cfg)
+
+#define db8500_add_sdi0(parent, pdata, pid) \
+	dbx500_add_sdi(parent, "sdi0", U8500_SDI0_BASE, \
+		       IRQ_DB8500_SDMMC0, pdata, pid)
+#define db8500_add_sdi1(parent, pdata, pid) \
+	dbx500_add_sdi(parent, "sdi1", U8500_SDI1_BASE, \
+		       IRQ_DB8500_SDMMC1, pdata, pid)
+#define db8500_add_sdi2(parent, pdata, pid) \
+	dbx500_add_sdi(parent, "sdi2", U8500_SDI2_BASE, \
+		       IRQ_DB8500_SDMMC2, pdata, pid)
+#define db8500_add_sdi3(parent, pdata, pid) \
+	dbx500_add_sdi(parent, "sdi3", U8500_SDI3_BASE, \
+		       IRQ_DB8500_SDMMC3, pdata, pid)
+#define db8500_add_sdi4(parent, pdata, pid) \
+	dbx500_add_sdi(parent, "sdi4", U8500_SDI4_BASE, \
+		       IRQ_DB8500_SDMMC4, pdata, pid)
+#define db8500_add_sdi5(parent, pdata, pid) \
+	dbx500_add_sdi(parent, "sdi5", U8500_SDI5_BASE, \
+		       IRQ_DB8500_SDMMC5, pdata, pid)
+
+#define db8500_add_ssp0(parent, pdata) \
+	db8500_add_ssp(parent, "ssp0", U8500_SSP0_BASE, \
+		       IRQ_DB8500_SSP0, pdata)
+#define db8500_add_ssp1(parent, pdata) \
+	db8500_add_ssp(parent, "ssp1", U8500_SSP1_BASE, \
+		       IRQ_DB8500_SSP1, pdata)
+
+#define db8500_add_spi0(parent, pdata) \
+	dbx500_add_spi(parent, "spi0", U8500_SPI0_BASE, \
+		       IRQ_DB8500_SPI0, pdata, 0)
+#define db8500_add_spi1(parent, pdata) \
+	dbx500_add_spi(parent, "spi1", U8500_SPI1_BASE, \
+		       IRQ_DB8500_SPI1, pdata, 0)
+#define db8500_add_spi2(parent, pdata) \
+	dbx500_add_spi(parent, "spi2", U8500_SPI2_BASE, \
+		       IRQ_DB8500_SPI2, pdata, 0)
+#define db8500_add_spi3(parent, pdata) \
+	dbx500_add_spi(parent, "spi3", U8500_SPI3_BASE, \
+		       IRQ_DB8500_SPI3, pdata, 0)
+
+#define db8500_add_uart0(parent, pdata) \
+	dbx500_add_uart(parent, "uart0", U8500_UART0_BASE, \
+			IRQ_DB8500_UART0, pdata)
+#define db8500_add_uart1(parent, pdata) \
+	dbx500_add_uart(parent, "uart1", U8500_UART1_BASE, \
+			IRQ_DB8500_UART1, pdata)
+#define db8500_add_uart2(parent, pdata) \
+	dbx500_add_uart(parent, "uart2", U8500_UART2_BASE, \
+			IRQ_DB8500_UART2, pdata)
 
 #endif
diff --git a/arch/arm/mach-ux500/dma-db5500.c b/arch/arm/mach-ux500/dma-db5500.c
index 1cfab68ae417..41e9470fa0e6 100644
--- a/arch/arm/mach-ux500/dma-db5500.c
+++ b/arch/arm/mach-ux500/dma-db5500.c
@@ -125,10 +125,11 @@ static struct platform_device dma40_device = {
 	.resource	= dma40_resources
 };
 
-void __init db5500_dma_init(void)
+void __init db5500_dma_init(struct device *parent)
 {
 	int ret;
 
+	dma40_device.dev.parent = parent;
 	ret = platform_device_register(&dma40_device);
 	if (ret)
 		dev_err(&dma40_device.dev, "unable to register device: %d\n", ret);
diff --git a/arch/arm/mach-ux500/include/mach/db8500-regs.h b/arch/arm/mach-ux500/include/mach/db8500-regs.h
index 80e10f50282e..9ec20b96d8f2 100644
--- a/arch/arm/mach-ux500/include/mach/db8500-regs.h
+++ b/arch/arm/mach-ux500/include/mach/db8500-regs.h
@@ -161,4 +161,7 @@
 #define U8500_MODEM_BASE	0xe000000
 #define U8500_APE_BASE		0x6000000
 
+/* SoC identification number information */
+#define U8500_BB_UID_BASE      (U8500_BACKUPRAM1_BASE + 0xFC0)
+
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/hardware.h b/arch/arm/mach-ux500/include/mach/hardware.h
index d93d6dbef25b..f84698936d36 100644
--- a/arch/arm/mach-ux500/include/mach/hardware.h
+++ b/arch/arm/mach-ux500/include/mach/hardware.h
@@ -23,7 +23,7 @@
 	(((x) & 0x0fffffff) + (((x) >> 4) & 0x0f000000) + U8500_IO_VIRTUAL)
 
 /* typesafe io address */
-#define __io_address(n)		__io(IO_ADDRESS(n))
+#define __io_address(n)		IOMEM(IO_ADDRESS(n))
 /* Used by some plat-nomadik code */
 #define io_p2v(n)		__io_address(n)
 
diff --git a/arch/arm/mach-ux500/include/mach/io.h b/arch/arm/mach-ux500/include/mach/io.h
deleted file mode 100644
index 1cf3f44ce5b2..000000000000
--- a/arch/arm/mach-ux500/include/mach/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-u8500/include/mach/io.h
- *
- * Copyright (C) 1997-1999 Russell King
- *
- * Modifications:
- *  06-12-1997	RMK	Created.
- *  07-04-1999	RMK	Major cleanup
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
- */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h b/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h
index d2d4131435a6..7d34c52798b5 100644
--- a/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h
+++ b/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h
@@ -13,7 +13,7 @@
 
 #define MOP500_AB8500_IRQ_BASE		IRQ_BOARD_START
 #define MOP500_AB8500_IRQ_END		(MOP500_AB8500_IRQ_BASE \
-					 + AB8500_NR_IRQS)
+					 + AB8500_MAX_NR_IRQS)
 
 /* TC35892 */
 #define TC35892_NR_INTERNAL_IRQS	8
diff --git a/arch/arm/mach-ux500/include/mach/setup.h b/arch/arm/mach-ux500/include/mach/setup.h
index 93d403955eaa..3dc00ffa7bfa 100644
--- a/arch/arm/mach-ux500/include/mach/setup.h
+++ b/arch/arm/mach-ux500/include/mach/setup.h
@@ -18,14 +18,16 @@ void __init ux500_map_io(void);
 extern void __init u5500_map_io(void);
 extern void __init u8500_map_io(void);
 
-extern void __init u5500_init_devices(void);
-extern void __init u8500_init_devices(void);
+extern struct device * __init u5500_init_devices(void);
+extern struct device * __init u8500_init_devices(void);
 
 extern void __init ux500_init_irq(void);
 
-extern void __init u5500_sdi_init(void);
+extern void __init u5500_sdi_init(struct device *parent);
 
-extern void __init db5500_dma_init(void);
+extern void __init db5500_dma_init(struct device *parent);
+
+extern struct device *ux500_soc_device_init(const char *soc_id);
 
 struct amba_device;
 extern void __init amba_add_devices(struct amba_device *devs[], int num);
diff --git a/arch/arm/mach-ux500/include/mach/usb.h b/arch/arm/mach-ux500/include/mach/usb.h
index d3739d418813..4c1cc50a595a 100644
--- a/arch/arm/mach-ux500/include/mach/usb.h
+++ b/arch/arm/mach-ux500/include/mach/usb.h
@@ -20,6 +20,6 @@ struct ux500_musb_board_data {
 	bool (*dma_filter)(struct dma_chan *chan, void *filter_param);
 };
 
-void ux500_add_usb(resource_size_t base, int irq, int *dma_rx_cfg,
-	int *dma_tx_cfg);
+void ux500_add_usb(struct device *parent, resource_size_t base,
+		   int irq, int *dma_rx_cfg, int *dma_tx_cfg);
 #endif
diff --git a/arch/arm/mach-ux500/timer.c b/arch/arm/mach-ux500/timer.c
index e9d580702fbb..d37df98b5c32 100644
--- a/arch/arm/mach-ux500/timer.c
+++ b/arch/arm/mach-ux500/timer.c
@@ -7,6 +7,7 @@
 #include <linux/io.h>
 #include <linux/errno.h>
 #include <linux/clksrc-dbx500-prcmu.h>
+#include <linux/of.h>
 
 #include <asm/smp_twd.h>
 
@@ -30,9 +31,13 @@ static void __init ux500_twd_init(void)
 	twd_local_timer = cpu_is_u5500() ? &u5500_twd_local_timer :
 					   &u8500_twd_local_timer;
 
-	err = twd_local_timer_register(twd_local_timer);
-	if (err)
-		pr_err("twd_local_timer_register failed %d\n", err);
+	if (of_have_populated_dt())
+		twd_local_timer_of_register();
+	else {
+		err = twd_local_timer_register(twd_local_timer);
+		if (err)
+			pr_err("twd_local_timer_register failed %d\n", err);
+	}
 }
 #else
 #define ux500_twd_init()	do { } while(0)
diff --git a/arch/arm/mach-ux500/usb.c b/arch/arm/mach-ux500/usb.c
index 9f9e1c203061..a74af389bc63 100644
--- a/arch/arm/mach-ux500/usb.c
+++ b/arch/arm/mach-ux500/usb.c
@@ -7,6 +7,7 @@
 #include <linux/platform_device.h>
 #include <linux/usb/musb.h>
 #include <linux/dma-mapping.h>
+
 #include <plat/ste_dma40.h>
 #include <mach/hardware.h>
 #include <mach/usb.h>
@@ -140,8 +141,8 @@ static inline void ux500_usb_dma_update_tx_ch_config(int *dst_dev_type)
 		musb_dma_tx_ch[idx].dst_dev_type = dst_dev_type[idx];
 }
 
-void ux500_add_usb(resource_size_t base, int irq, int *dma_rx_cfg,
-	int *dma_tx_cfg)
+void ux500_add_usb(struct device *parent, resource_size_t base, int irq,
+		   int *dma_rx_cfg, int *dma_tx_cfg)
 {
 	ux500_musb_device.resource[0].start = base;
 	ux500_musb_device.resource[0].end = base + SZ_64K - 1;
@@ -151,5 +152,7 @@ void ux500_add_usb(resource_size_t base, int irq, int *dma_rx_cfg,
 	ux500_usb_dma_update_rx_ch_config(dma_rx_cfg);
 	ux500_usb_dma_update_tx_ch_config(dma_tx_cfg);
 
+	ux500_musb_device.dev.parent = parent;
+
 	platform_device_register(&ux500_musb_device);
 }
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index 0968772aedbe..6bbd74e950ab 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -36,7 +36,6 @@
 #include <linux/clkdev.h>
 #include <linux/mtd/physmap.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/leds.h>
 #include <asm/hardware/arm_timer.h>
diff --git a/arch/arm/mach-versatile/include/mach/io.h b/arch/arm/mach-versatile/include/mach/io.h
deleted file mode 100644
index f067c14c7182..000000000000
--- a/arch/arm/mach-versatile/include/mach/io.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- *  arch/arm/mach-versatile/include/mach/io.h
- *
- *  Copyright (C) 2003 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c
index 51733b022d04..d2268be8c34c 100644
--- a/arch/arm/mach-versatile/pci.c
+++ b/arch/arm/mach-versatile/pci.c
@@ -24,7 +24,6 @@
 
 #include <mach/hardware.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/mach/pci.h>
 
 /*
@@ -191,7 +190,7 @@ static struct resource pre_mem = {
 	.flags	= IORESOURCE_MEM | IORESOURCE_PREFETCH,
 };
 
-static int __init pci_versatile_setup_resources(struct list_head *resources)
+static int __init pci_versatile_setup_resources(struct pci_sys_data *sys)
 {
 	int ret = 0;
 
@@ -219,9 +218,9 @@ static int __init pci_versatile_setup_resources(struct list_head *resources)
 	 * the mem resource for this bus
 	 * the prefetch mem resource for this bus
 	 */
-	pci_add_resource_offset(resources, &io_mem, sys->io_offset);
-	pci_add_resource_offset(resources, &non_mem, sys->mem_offset);
-	pci_add_resource_offset(resources, &pre_mem, sys->mem_offset);
+	pci_add_resource_offset(&sys->resources, &io_mem, sys->io_offset);
+	pci_add_resource_offset(&sys->resources, &non_mem, sys->mem_offset);
+	pci_add_resource_offset(&sys->resources, &pre_mem, sys->mem_offset);
 
 	goto out;
 
@@ -250,7 +249,7 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys)
 
 	if (nr == 0) {
 		sys->mem_offset = 0;
-		ret = pci_versatile_setup_resources(&sys->resources);
+		ret = pci_versatile_setup_resources(sys);
 		if (ret < 0) {
 			printk("pci_versatile_setup: resources... oops?\n");
 			goto out;
diff --git a/arch/arm/mach-vexpress/hotplug.c b/arch/arm/mach-vexpress/hotplug.c
index 3034a4dab4a1..c504a72b94d6 100644
--- a/arch/arm/mach-vexpress/hotplug.c
+++ b/arch/arm/mach-vexpress/hotplug.c
@@ -14,7 +14,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
-#include <asm/system.h>
+#include <asm/cp15.h>
 
 extern volatile int pen_release;
 
diff --git a/arch/arm/mach-vexpress/include/mach/io.h b/arch/arm/mach-vexpress/include/mach/io.h
deleted file mode 100644
index 13522d86685e..000000000000
--- a/arch/arm/mach-vexpress/include/mach/io.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- *  arch/arm/mach-vexpress/include/mach/io.h
- *
- *  Copyright (C) 2003 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-vt8500/include/mach/io.h b/arch/arm/mach-vt8500/include/mach/io.h
deleted file mode 100644
index 46181eecf273..000000000000
--- a/arch/arm/mach-vt8500/include/mach/io.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- *  arch/arm/mach-vt8500/include/mach/io.h
- *
- *  Copyright (C) 2010 Alexey Charkov
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define __io(a)		__typesafe_io((a) + 0xf0000000)
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/mach-w90x900/cpu.c b/arch/arm/mach-w90x900/cpu.c
index 9a0661992909..9e4dd8b63c4a 100644
--- a/arch/arm/mach-w90x900/cpu.c
+++ b/arch/arm/mach-w90x900/cpu.c
@@ -28,6 +28,7 @@
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
 #include <asm/irq.h>
+#include <asm/system_misc.h>
 
 #include <mach/hardware.h>
 #include <mach/regs-serial.h>
diff --git a/arch/arm/mach-w90x900/dev.c b/arch/arm/mach-w90x900/dev.c
index db82568a998a..48f5b9fdfb7f 100644
--- a/arch/arm/mach-w90x900/dev.c
+++ b/arch/arm/mach-w90x900/dev.c
@@ -27,6 +27,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/flash.h>
 
+#include <asm/system_misc.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-w90x900/include/mach/io.h b/arch/arm/mach-w90x900/include/mach/io.h
deleted file mode 100644
index d96ab99df05b..000000000000
--- a/arch/arm/mach-w90x900/include/mach/io.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * arch/arm/mach-w90x900/include/mach/io.h
- *
- * Copyright (c) 2008 Nuvoton technology corporation
- * All rights reserved.
- *
- * Wan ZongShun <mcuos.com@gmail.com>
- *
- * Based on arch/arm/mach-s3c2410/include/mach/io.h
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#define IO_SPACE_LIMIT	0xffffffff
-
-/*
- * 1:1 mapping for ioremapped regions.
- */
-
-#define __mem_pci(a)	(a)
-#define __io(a)		__typesafe_io(a)
-
-#endif
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index caf14dc059e5..9107231aacc5 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -22,7 +22,8 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
+#include <asm/cp15.h>
+#include <asm/system_info.h>
 #include <asm/unaligned.h>
 
 #include "fault.h"
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index e0b0e7a4ec68..dd3d59122cc3 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
 #include <plat/cache-feroceon-l2.h>
 
 /*
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index b1e192ba8c24..a53fd2aaa2f4 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -30,13 +30,13 @@
 
 static void __iomem *l2x0_base;
 static DEFINE_RAW_SPINLOCK(l2x0_lock);
-static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
-static uint32_t l2x0_size;
+static u32 l2x0_way_mask;	/* Bitmask of active ways */
+static u32 l2x0_size;
 
 struct l2x0_regs l2x0_saved_regs;
 
 struct l2x0_of_data {
-	void (*setup)(const struct device_node *, __u32 *, __u32 *);
+	void (*setup)(const struct device_node *, u32 *, u32 *);
 	void (*save)(void);
 	void (*resume)(void);
 };
@@ -288,7 +288,7 @@ static void l2x0_disable(void)
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_unlock(__u32 cache_id)
+static void l2x0_unlock(u32 cache_id)
 {
 	int lockregs;
 	int i;
@@ -307,11 +307,11 @@ static void l2x0_unlock(__u32 cache_id)
 	}
 }
 
-void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
+void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 {
-	__u32 aux;
-	__u32 cache_id;
-	__u32 way_size = 0;
+	u32 aux;
+	u32 cache_id;
+	u32 way_size = 0;
 	int ways;
 	const char *type;
 
@@ -388,7 +388,7 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 
 #ifdef CONFIG_OF
 static void __init l2x0_of_setup(const struct device_node *np,
-				 __u32 *aux_val, __u32 *aux_mask)
+				 u32 *aux_val, u32 *aux_mask)
 {
 	u32 data[2] = { 0, 0 };
 	u32 tag = 0;
@@ -422,7 +422,7 @@ static void __init l2x0_of_setup(const struct device_node *np,
 }
 
 static void __init pl310_of_setup(const struct device_node *np,
-				  __u32 *aux_val, __u32 *aux_mask)
+				  u32 *aux_val, u32 *aux_mask)
 {
 	u32 data[3] = { 0, 0, 0 };
 	u32 tag[3] = { 0, 0, 0 };
@@ -548,7 +548,7 @@ static const struct of_device_id l2x0_ids[] __initconst = {
 	{}
 };
 
-int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 {
 	struct device_node *np;
 	struct l2x0_of_data *data;
diff --git a/arch/arm/mm/cache-tauros2.c b/arch/arm/mm/cache-tauros2.c
index 50868651890f..1fbca05fe906 100644
--- a/arch/arm/mm/cache-tauros2.c
+++ b/arch/arm/mm/cache-tauros2.c
@@ -16,6 +16,7 @@
 
 #include <linux/init.h>
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
 #include <asm/hardware/cache-tauros2.h>
 
 
diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c
index 5a32020471e3..6c3edeb66e74 100644
--- a/arch/arm/mm/cache-xsc3l2.c
+++ b/arch/arm/mm/cache-xsc3l2.c
@@ -18,7 +18,7 @@
  */
 #include <linux/init.h>
 #include <linux/highmem.h>
-#include <asm/system.h>
+#include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index ec8c3befb9c8..1267e64133b9 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -23,10 +23,6 @@
 
 #include "mm.h"
 
-/*
- * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
- * specific hacks for copying pages efficiently.
- */
 #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
 				  L_PTE_MT_MINICACHE)
 
@@ -78,10 +74,9 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from,
 
 	raw_spin_lock(&minicache_lock);
 
-	set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
-	flush_tlb_kernel_page(0xffff8000);
+	set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
 
-	mc_copy_user_page((void *)0xffff8000, kto);
+	mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
 
 	raw_spin_unlock(&minicache_lock);
 
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index 8b03a5814d00..b9bcc9d79176 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -24,9 +24,6 @@
 #error FIX ME
 #endif
 
-#define from_address	(0xffff8000)
-#define to_address	(0xffffc000)
-
 static DEFINE_RAW_SPINLOCK(v6_lock);
 
 /*
@@ -90,14 +87,11 @@ static void v6_copy_user_highpage_aliasing(struct page *to,
 	 */
 	raw_spin_lock(&v6_lock);
 
-	set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(page_to_pfn(from), PAGE_KERNEL), 0);
-	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(to), PAGE_KERNEL), 0);
-
-	kfrom = from_address + (offset << PAGE_SHIFT);
-	kto   = to_address + (offset << PAGE_SHIFT);
+	kfrom = COPYPAGE_V6_FROM + (offset << PAGE_SHIFT);
+	kto   = COPYPAGE_V6_TO + (offset << PAGE_SHIFT);
 
-	flush_tlb_kernel_page(kfrom);
-	flush_tlb_kernel_page(kto);
+	set_top_pte(kfrom, mk_pte(from, PAGE_KERNEL));
+	set_top_pte(kto, mk_pte(to, PAGE_KERNEL));
 
 	copy_page((void *)kto, (void *)kfrom);
 
@@ -111,8 +105,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to,
  */
 static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vaddr)
 {
-	unsigned int offset = CACHE_COLOUR(vaddr);
-	unsigned long to = to_address + (offset << PAGE_SHIFT);
+	unsigned long to = COPYPAGE_V6_TO + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 
 	/* FIXME: not highmem safe */
 	discard_old_kernel_data(page_address(page));
@@ -123,8 +116,7 @@ static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vad
 	 */
 	raw_spin_lock(&v6_lock);
 
-	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(page), PAGE_KERNEL), 0);
-	flush_tlb_kernel_page(to);
+	set_top_pte(to, mk_pte(page, PAGE_KERNEL));
 	clear_page((void *)to);
 
 	raw_spin_unlock(&v6_lock);
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 439d106ae638..0fb85025344d 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -23,12 +23,6 @@
 
 #include "mm.h"
 
-/*
- * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
- * specific hacks for copying pages efficiently.
- */
-#define COPYPAGE_MINICACHE	0xffff8000
-
 #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
 				  L_PTE_MT_MINICACHE)
 
@@ -100,8 +94,7 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
 
 	raw_spin_lock(&minicache_lock);
 
-	set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
-	flush_tlb_kernel_page(COPYPAGE_MINICACHE);
+	set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
 
 	mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1aa664a1999f..db23ae4aaaab 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -214,7 +214,8 @@ static int __init consistent_init(void)
 core_initcall(consistent_init);
 
 static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
+__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
+	const void *caller)
 {
 	struct arm_vmregion *c;
 	size_t align;
@@ -241,7 +242,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
 	 * Allocate a virtual address in the consistent mapping region.
 	 */
 	c = arm_vmregion_alloc(&consistent_head, align, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
+			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM), caller);
 	if (c) {
 		pte_t *pte;
 		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
@@ -320,14 +321,14 @@ static void __dma_free_remap(void *cpu_addr, size_t size)
 
 #else	/* !CONFIG_MMU */
 
-#define __dma_alloc_remap(page, size, gfp, prot)	page_address(page)
+#define __dma_alloc_remap(page, size, gfp, prot, c)	page_address(page)
 #define __dma_free_remap(addr, size)			do { } while (0)
 
 #endif	/* CONFIG_MMU */
 
 static void *
 __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
-	    pgprot_t prot)
+	    pgprot_t prot, const void *caller)
 {
 	struct page *page;
 	void *addr;
@@ -349,7 +350,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 		return NULL;
 
 	if (!arch_is_coherent())
-		addr = __dma_alloc_remap(page, size, gfp, prot);
+		addr = __dma_alloc_remap(page, size, gfp, prot, caller);
 	else
 		addr = page_address(page);
 
@@ -374,7 +375,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gf
 		return memory;
 
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_dmacoherent(pgprot_kernel));
+			   pgprot_dmacoherent(pgprot_kernel),
+			   __builtin_return_address(0));
 }
 EXPORT_SYMBOL(dma_alloc_coherent);
 
@@ -386,7 +388,8 @@ void *
 dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
 {
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_writecombine(pgprot_kernel));
+			   pgprot_writecombine(pgprot_kernel),
+			   __builtin_return_address(0));
 }
 EXPORT_SYMBOL(dma_alloc_writecombine);
 
@@ -723,6 +726,9 @@ EXPORT_SYMBOL(dma_set_mask);
 
 static int __init dma_debug_do_init(void)
 {
+#ifdef CONFIG_MMU
+	arm_vmregion_create_proc("dma-mappings", &consistent_head);
+#endif
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 	return 0;
 }
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index bb7eac381a8e..9055b5a84ec5 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -21,8 +21,9 @@
 #include <linux/perf_event.h>
 
 #include <asm/exception.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
+#include <asm/system_misc.h>
+#include <asm/system_info.h>
 #include <asm/tlbflush.h>
 
 #include "fault.h"
@@ -164,7 +165,8 @@ __do_user_fault(struct task_struct *tsk, unsigned long addr,
 	struct siginfo si;
 
 #ifdef CONFIG_DEBUG_USER
-	if (user_debug & UDBG_SEGV) {
+	if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
+	    ((user_debug & UDBG_BUS)  && (sig == SIGBUS))) {
 		printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
 		       tsk->comm, sig, addr, fsr);
 		show_pte(tsk->mm, addr);
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 1a8d4aa821be..77458548e031 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -16,22 +16,18 @@
 #include <asm/cachetype.h>
 #include <asm/highmem.h>
 #include <asm/smp_plat.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 
 #include "mm.h"
 
 #ifdef CONFIG_CPU_CACHE_VIPT
 
-#define ALIAS_FLUSH_START	0xffff4000
-
 static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
 {
-	unsigned long to = ALIAS_FLUSH_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
+	unsigned long to = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 	const int zero = 0;
 
-	set_pte_ext(TOP_PTE(to), pfn_pte(pfn, PAGE_KERNEL), 0);
-	flush_tlb_kernel_page(to);
+	set_top_pte(to, pfn_pte(pfn, PAGE_KERNEL));
 
 	asm(	"mcrr	p15, 0, %1, %0, c14\n"
 	"	mcr	p15, 0, %2, c7, c10, 4"
@@ -42,13 +38,12 @@ static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
 
 static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned long len)
 {
-	unsigned long colour = CACHE_COLOUR(vaddr);
+	unsigned long va = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 	unsigned long offset = vaddr & (PAGE_SIZE - 1);
 	unsigned long to;
 
-	set_pte_ext(TOP_PTE(ALIAS_FLUSH_START) + colour, pfn_pte(pfn, PAGE_KERNEL), 0);
-	to = ALIAS_FLUSH_START + (colour << PAGE_SHIFT) + offset;
-	flush_tlb_kernel_page(to);
+	set_top_pte(va, pfn_pte(pfn, PAGE_KERNEL));
+	to = va + offset;
 	flush_icache_range(to, to + len);
 }
 
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 5a21505d7550..21b9e1bf9b77 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -69,15 +69,14 @@ void *kmap_atomic(struct page *page)
 	 * With debugging enabled, kunmap_atomic forces that entry to 0.
 	 * Make sure it was indeed properly unmapped.
 	 */
-	BUG_ON(!pte_none(*(TOP_PTE(vaddr))));
+	BUG_ON(!pte_none(get_top_pte(vaddr)));
 #endif
-	set_pte_ext(TOP_PTE(vaddr), mk_pte(page, kmap_prot), 0);
 	/*
 	 * When debugging is off, kunmap_atomic leaves the previous mapping
-	 * in place, so this TLB flush ensures the TLB is updated with the
-	 * new mapping.
+	 * in place, so the contained TLB flush ensures the TLB is updated
+	 * with the new mapping.
 	 */
-	local_flush_tlb_kernel_page(vaddr);
+	set_top_pte(vaddr, mk_pte(page, kmap_prot));
 
 	return (void *)vaddr;
 }
@@ -96,8 +95,7 @@ void __kunmap_atomic(void *kvaddr)
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
 #ifdef CONFIG_DEBUG_HIGHMEM
 		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-		set_pte_ext(TOP_PTE(vaddr), __pte(0), 0);
-		local_flush_tlb_kernel_page(vaddr);
+		set_top_pte(vaddr, __pte(0));
 #else
 		(void) idx;  /* to kill a warning */
 #endif
@@ -121,10 +119,9 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(TOP_PTE(vaddr))));
+	BUG_ON(!pte_none(get_top_pte(vaddr)));
 #endif
-	set_pte_ext(TOP_PTE(vaddr), pfn_pte(pfn, kmap_prot), 0);
-	local_flush_tlb_kernel_page(vaddr);
+	set_top_pte(vaddr, pfn_pte(pfn, kmap_prot));
 
 	return (void *)vaddr;
 }
@@ -132,11 +129,9 @@ void *kmap_atomic_pfn(unsigned long pfn)
 struct page *kmap_atomic_to_page(const void *ptr)
 {
 	unsigned long vaddr = (unsigned long)ptr;
-	pte_t *pte;
 
 	if (vaddr < FIXADDR_START)
 		return virt_to_page(ptr);
 
-	pte = TOP_PTE(vaddr);
-	return pte_page(*pte);
+	return pte_page(get_top_pte(vaddr));
 }
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index feacf4c76712..ab88ed4f8e08 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -5,6 +5,7 @@
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/sections.h>
+#include <asm/system_info.h>
 
 pgd_t *idmap_pgd;
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 245a55a0a5bb..595079fa9d1d 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -658,7 +658,9 @@ void __init mem_init(void)
 #ifdef CONFIG_HIGHMEM
 			"    pkmap   : 0x%08lx - 0x%08lx   (%4ld MB)\n"
 #endif
+#ifdef CONFIG_MODULES
 			"    modules : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+#endif
 			"      .text : 0x%p" " - 0x%p" "   (%4d kB)\n"
 			"      .init : 0x%p" " - 0x%p" "   (%4d kB)\n"
 			"      .data : 0x%p" " - 0x%p" "   (%4d kB)\n"
@@ -677,7 +679,9 @@ void __init mem_init(void)
 			MLM(PKMAP_BASE, (PKMAP_BASE) + (LAST_PKMAP) *
 				(PAGE_SIZE)),
 #endif
+#ifdef CONFIG_MODULES
 			MLM(MODULES_VADDR, MODULES_END),
+#endif
 
 			MLK_ROUNDUP(_text, _etext),
 			MLK_ROUNDUP(__init_begin, __init_end),
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 80632e8d7538..4f55f5062ab7 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -26,12 +26,14 @@
 #include <linux/vmalloc.h>
 #include <linux/io.h>
 
+#include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/sizes.h>
+#include <asm/system_info.h>
 
 #include <asm/mach/map.h>
 #include "mm.h"
@@ -306,11 +308,15 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
+void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+				      unsigned int, void *) =
+	__arm_ioremap_caller;
+
 void __iomem *
 __arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
 {
-	return __arm_ioremap_caller(phys_addr, size, mtype,
-			__builtin_return_address(0));
+	return arch_ioremap_caller(phys_addr, size, mtype,
+		__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
@@ -369,4 +375,11 @@ void __iounmap(volatile void __iomem *io_addr)
 
 	vunmap(addr);
 }
-EXPORT_SYMBOL(__iounmap);
+
+void (*arch_iounmap)(volatile void __iomem *) = __iounmap;
+
+void __arm_iounmap(volatile void __iomem *io_addr)
+{
+	arch_iounmap(io_addr);
+}
+EXPORT_SYMBOL(__arm_iounmap);
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 70f6d3ea4834..27f4a619b35d 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -3,7 +3,31 @@
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
 
-#define TOP_PTE(x)	pte_offset_kernel(top_pmd, x)
+/*
+ * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
+ * specific hacks for copying pages efficiently, while 0xffff4000
+ * is reserved for VIPT aliasing flushing by generic code.
+ *
+ * Note that we don't allow VIPT aliasing caches with SMP.
+ */
+#define COPYPAGE_MINICACHE	0xffff8000
+#define COPYPAGE_V6_FROM	0xffff8000
+#define COPYPAGE_V6_TO		0xffffc000
+/* PFN alias flushing, for VIPT caches */
+#define FLUSH_ALIAS_START	0xffff4000
+
+static inline void set_top_pte(unsigned long va, pte_t pte)
+{
+	pte_t *ptep = pte_offset_kernel(top_pmd, va);
+	set_pte_ext(ptep, pte, 0);
+	local_flush_tlb_kernel_page(va);
+}
+
+static inline pte_t get_top_pte(unsigned long va)
+{
+	pte_t *ptep = pte_offset_kernel(top_pmd, va);
+	return *ptep;
+}
 
 static inline pmd_t *pmd_off_k(unsigned long virt)
 {
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 94c5a0c94f5e..b86f8933ff91 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -17,6 +17,7 @@
 #include <linux/fs.h>
 #include <linux/vmalloc.h>
 
+#include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/sections.h>
 #include <asm/cachetype.h>
@@ -25,6 +26,7 @@
 #include <asm/smp_plat.h>
 #include <asm/tlb.h>
 #include <asm/highmem.h>
+#include <asm/system_info.h>
 #include <asm/traps.h>
 
 #include <asm/mach/arch.h>
@@ -997,11 +999,14 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 {
 	struct map_desc map;
 	unsigned long addr;
+	void *vectors;
 
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors_page = early_alloc(PAGE_SIZE);
+	vectors = early_alloc(PAGE_SIZE);
+
+	early_trap_init(vectors);
 
 	for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -1041,7 +1046,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 * location (0xffff0000).  If we aren't using high-vectors, also
 	 * create a mapping at the low-vectors virtual address.
 	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors_page));
+	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
 	map.virtual = 0xffff0000;
 	map.length = PAGE_SIZE;
 	map.type = MT_HIGH_VECTORS;
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 4fc6794cca4b..6486d2f253cd 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -86,13 +86,17 @@ void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
+void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *);
+
 void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	return __arm_ioremap(phys_addr, size, mtype);
 }
 
-void __iounmap(volatile void __iomem *addr)
+void (*arch_iounmap)(volatile void __iomem *);
+
+void __arm_iounmap(volatile void __iomem *addr)
 {
 }
-EXPORT_SYMBOL(__iounmap);
+EXPORT_SYMBOL(__arm_iounmap);
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index a3e78ccabd65..0acb089d0f70 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -12,6 +12,7 @@
 #include <linux/highmem.h>
 #include <linux/slab.h>
 
+#include <asm/cp15.h>
 #include <asm/pgalloc.h>
 #include <asm/page.h>
 #include <asm/tlbflush.h>
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index 272558a133a3..d217e9795d74 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -22,7 +22,6 @@
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 #include "proc-macros.S"
 
diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c
index 036fdbfdd62f..a631016e1f8f 100644
--- a/arch/arm/mm/vmregion.c
+++ b/arch/arm/mm/vmregion.c
@@ -1,5 +1,8 @@
+#include <linux/fs.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 
 #include "vmregion.h"
@@ -36,7 +39,7 @@
 
 struct arm_vmregion *
 arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
-		   size_t size, gfp_t gfp)
+		   size_t size, gfp_t gfp, const void *caller)
 {
 	unsigned long start = head->vm_start, addr = head->vm_end;
 	unsigned long flags;
@@ -52,6 +55,8 @@ arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
 	if (!new)
 		goto out;
 
+	new->caller = caller;
+
 	spin_lock_irqsave(&head->vm_lock, flags);
 
 	addr = rounddown(addr - size, align);
@@ -129,3 +134,72 @@ void arm_vmregion_free(struct arm_vmregion_head *head, struct arm_vmregion *c)
 
 	kfree(c);
 }
+
+#ifdef CONFIG_PROC_FS
+static int arm_vmregion_show(struct seq_file *m, void *p)
+{
+	struct arm_vmregion *c = list_entry(p, struct arm_vmregion, vm_list);
+
+	seq_printf(m, "0x%08lx-0x%08lx %7lu", c->vm_start, c->vm_end,
+		c->vm_end - c->vm_start);
+	if (c->caller)
+		seq_printf(m, " %pS", (void *)c->caller);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void *arm_vmregion_start(struct seq_file *m, loff_t *pos)
+{
+	struct arm_vmregion_head *h = m->private;
+	spin_lock_irq(&h->vm_lock);
+	return seq_list_start(&h->vm_list, *pos);
+}
+
+static void *arm_vmregion_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct arm_vmregion_head *h = m->private;
+	return seq_list_next(p, &h->vm_list, pos);
+}
+
+static void arm_vmregion_stop(struct seq_file *m, void *p)
+{
+	struct arm_vmregion_head *h = m->private;
+	spin_unlock_irq(&h->vm_lock);
+}
+
+static const struct seq_operations arm_vmregion_ops = {
+	.start	= arm_vmregion_start,
+	.stop	= arm_vmregion_stop,
+	.next	= arm_vmregion_next,
+	.show	= arm_vmregion_show,
+};
+
+static int arm_vmregion_open(struct inode *inode, struct file *file)
+{
+	struct arm_vmregion_head *h = PDE(inode)->data;
+	int ret = seq_open(file, &arm_vmregion_ops);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = h;
+	}
+	return ret;
+}
+
+static const struct file_operations arm_vmregion_fops = {
+	.open	= arm_vmregion_open,
+	.read	= seq_read,
+	.llseek	= seq_lseek,
+	.release = seq_release,
+};
+
+int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
+{
+	proc_create_data(path, S_IRUSR, NULL, &arm_vmregion_fops, h);
+	return 0;
+}
+#else
+int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
+{
+	return 0;
+}
+#endif
diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h
index 15e9f044db9f..162be662c088 100644
--- a/arch/arm/mm/vmregion.h
+++ b/arch/arm/mm/vmregion.h
@@ -19,11 +19,14 @@ struct arm_vmregion {
 	unsigned long		vm_end;
 	struct page		*vm_pages;
 	int			vm_active;
+	const void		*caller;
 };
 
-struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t);
+struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t, const void *);
 struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *, unsigned long);
 struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *, unsigned long);
 void arm_vmregion_free(struct arm_vmregion_head *, struct arm_vmregion *);
 
+int arm_vmregion_create_proc(const char *, struct arm_vmregion_head *);
+
 #endif
diff --git a/arch/arm/net/Makefile b/arch/arm/net/Makefile
new file mode 100644
index 000000000000..c2c10841b6be
--- /dev/null
+++ b/arch/arm/net/Makefile
@@ -0,0 +1,3 @@
+# ARM-specific networking code
+
+obj-$(CONFIG_BPF_JIT) += bpf_jit_32.o
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
new file mode 100644
index 000000000000..62135849f48b
--- /dev/null
+++ b/arch/arm/net/bpf_jit_32.c
@@ -0,0 +1,915 @@
+/*
+ * Just-In-Time compiler for BPF filters on 32bit ARM
+ *
+ * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/filter.h>
+#include <linux/moduleloader.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <asm/cacheflush.h>
+#include <asm/hwcap.h>
+
+#include "bpf_jit_32.h"
+
+/*
+ * ABI:
+ *
+ * r0	scratch register
+ * r4	BPF register A
+ * r5	BPF register X
+ * r6	pointer to the skb
+ * r7	skb->data
+ * r8	skb_headlen(skb)
+ */
+
+#define r_scratch	ARM_R0
+/* r1-r3 are (also) used for the unaligned loads on the non-ARMv7 slowpath */
+#define r_off		ARM_R1
+#define r_A		ARM_R4
+#define r_X		ARM_R5
+#define r_skb		ARM_R6
+#define r_skb_data	ARM_R7
+#define r_skb_hl	ARM_R8
+
+#define SCRATCH_SP_OFFSET	0
+#define SCRATCH_OFF(k)		(SCRATCH_SP_OFFSET + (k))
+
+#define SEEN_MEM		((1 << BPF_MEMWORDS) - 1)
+#define SEEN_MEM_WORD(k)	(1 << (k))
+#define SEEN_X			(1 << BPF_MEMWORDS)
+#define SEEN_CALL		(1 << (BPF_MEMWORDS + 1))
+#define SEEN_SKB		(1 << (BPF_MEMWORDS + 2))
+#define SEEN_DATA		(1 << (BPF_MEMWORDS + 3))
+
+#define FLAG_NEED_X_RESET	(1 << 0)
+
+struct jit_ctx {
+	const struct sk_filter *skf;
+	unsigned idx;
+	unsigned prologue_bytes;
+	int ret0_fp_idx;
+	u32 seen;
+	u32 flags;
+	u32 *offsets;
+	u32 *target;
+#if __LINUX_ARM_ARCH__ < 7
+	u16 epilogue_bytes;
+	u16 imm_count;
+	u32 *imms;
+#endif
+};
+
+int bpf_jit_enable __read_mostly;
+
+static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
+{
+	u8 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 1);
+
+	return (u64)err << 32 | ret;
+}
+
+static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
+{
+	u16 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 2);
+
+	return (u64)err << 32 | ntohs(ret);
+}
+
+static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
+{
+	u32 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 4);
+
+	return (u64)err << 32 | ntohl(ret);
+}
+
+/*
+ * Wrapper that handles both OABI and EABI and assures Thumb2 interworking
+ * (where the assembly routines like __aeabi_uidiv could cause problems).
+ */
+static u32 jit_udiv(u32 dividend, u32 divisor)
+{
+	return dividend / divisor;
+}
+
+static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL)
+		ctx->target[ctx->idx] = inst | (cond << 28);
+
+	ctx->idx++;
+}
+
+/*
+ * Emit an instruction that will be executed unconditionally.
+ */
+static inline void emit(u32 inst, struct jit_ctx *ctx)
+{
+	_emit(ARM_COND_AL, inst, ctx);
+}
+
+static u16 saved_regs(struct jit_ctx *ctx)
+{
+	u16 ret = 0;
+
+	if ((ctx->skf->len > 1) ||
+	    (ctx->skf->insns[0].code == BPF_S_RET_A))
+		ret |= 1 << r_A;
+
+#ifdef CONFIG_FRAME_POINTER
+	ret |= (1 << ARM_FP) | (1 << ARM_IP) | (1 << ARM_LR) | (1 << ARM_PC);
+#else
+	if (ctx->seen & SEEN_CALL)
+		ret |= 1 << ARM_LR;
+#endif
+	if (ctx->seen & (SEEN_DATA | SEEN_SKB))
+		ret |= 1 << r_skb;
+	if (ctx->seen & SEEN_DATA)
+		ret |= (1 << r_skb_data) | (1 << r_skb_hl);
+	if (ctx->seen & SEEN_X)
+		ret |= 1 << r_X;
+
+	return ret;
+}
+
+static inline int mem_words_used(struct jit_ctx *ctx)
+{
+	/* yes, we do waste some stack space IF there are "holes" in the set" */
+	return fls(ctx->seen & SEEN_MEM);
+}
+
+static inline bool is_load_to_a(u16 inst)
+{
+	switch (inst) {
+	case BPF_S_LD_W_LEN:
+	case BPF_S_LD_W_ABS:
+	case BPF_S_LD_H_ABS:
+	case BPF_S_LD_B_ABS:
+	case BPF_S_ANC_CPU:
+	case BPF_S_ANC_IFINDEX:
+	case BPF_S_ANC_MARK:
+	case BPF_S_ANC_PROTOCOL:
+	case BPF_S_ANC_RXHASH:
+	case BPF_S_ANC_QUEUE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+	u16 reg_set = saved_regs(ctx);
+	u16 first_inst = ctx->skf->insns[0].code;
+	u16 off;
+
+#ifdef CONFIG_FRAME_POINTER
+	emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
+	emit(ARM_PUSH(reg_set), ctx);
+	emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
+#else
+	if (reg_set)
+		emit(ARM_PUSH(reg_set), ctx);
+#endif
+
+	if (ctx->seen & (SEEN_DATA | SEEN_SKB))
+		emit(ARM_MOV_R(r_skb, ARM_R0), ctx);
+
+	if (ctx->seen & SEEN_DATA) {
+		off = offsetof(struct sk_buff, data);
+		emit(ARM_LDR_I(r_skb_data, r_skb, off), ctx);
+		/* headlen = len - data_len */
+		off = offsetof(struct sk_buff, len);
+		emit(ARM_LDR_I(r_skb_hl, r_skb, off), ctx);
+		off = offsetof(struct sk_buff, data_len);
+		emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+		emit(ARM_SUB_R(r_skb_hl, r_skb_hl, r_scratch), ctx);
+	}
+
+	if (ctx->flags & FLAG_NEED_X_RESET)
+		emit(ARM_MOV_I(r_X, 0), ctx);
+
+	/* do not leak kernel data to userspace */
+	if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst)))
+		emit(ARM_MOV_I(r_A, 0), ctx);
+
+	/* stack space for the BPF_MEM words */
+	if (ctx->seen & SEEN_MEM)
+		emit(ARM_SUB_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	u16 reg_set = saved_regs(ctx);
+
+	if (ctx->seen & SEEN_MEM)
+		emit(ARM_ADD_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
+
+	reg_set &= ~(1 << ARM_LR);
+
+#ifdef CONFIG_FRAME_POINTER
+	/* the first instruction of the prologue was: mov ip, sp */
+	reg_set &= ~(1 << ARM_IP);
+	reg_set |= (1 << ARM_SP);
+	emit(ARM_LDM(ARM_SP, reg_set), ctx);
+#else
+	if (reg_set) {
+		if (ctx->seen & SEEN_CALL)
+			reg_set |= 1 << ARM_PC;
+		emit(ARM_POP(reg_set), ctx);
+	}
+
+	if (!(ctx->seen & SEEN_CALL))
+		emit(ARM_BX(ARM_LR), ctx);
+#endif
+}
+
+static int16_t imm8m(u32 x)
+{
+	u32 rot;
+
+	for (rot = 0; rot < 16; rot++)
+		if ((x & ~ror32(0xff, 2 * rot)) == 0)
+			return rol32(x, 2 * rot) | (rot << 8);
+
+	return -1;
+}
+
+#if __LINUX_ARM_ARCH__ < 7
+
+static u16 imm_offset(u32 k, struct jit_ctx *ctx)
+{
+	unsigned i = 0, offset;
+	u16 imm;
+
+	/* on the "fake" run we just count them (duplicates included) */
+	if (ctx->target == NULL) {
+		ctx->imm_count++;
+		return 0;
+	}
+
+	while ((i < ctx->imm_count) && ctx->imms[i]) {
+		if (ctx->imms[i] == k)
+			break;
+		i++;
+	}
+
+	if (ctx->imms[i] == 0)
+		ctx->imms[i] = k;
+
+	/* constants go just after the epilogue */
+	offset =  ctx->offsets[ctx->skf->len];
+	offset += ctx->prologue_bytes;
+	offset += ctx->epilogue_bytes;
+	offset += i * 4;
+
+	ctx->target[offset / 4] = k;
+
+	/* PC in ARM mode == address of the instruction + 8 */
+	imm = offset - (8 + ctx->idx * 4);
+
+	return imm;
+}
+
+#endif /* __LINUX_ARM_ARCH__ */
+
+/*
+ * Move an immediate that's not an imm8m to a core register.
+ */
+static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 7
+	emit(ARM_LDR_I(rd, ARM_PC, imm_offset(val, ctx)), ctx);
+#else
+	emit(ARM_MOVW(rd, val & 0xffff), ctx);
+	if (val > 0xffff)
+		emit(ARM_MOVT(rd, val >> 16), ctx);
+#endif
+}
+
+static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx)
+{
+	int imm12 = imm8m(val);
+
+	if (imm12 >= 0)
+		emit(ARM_MOV_I(rd, imm12), ctx);
+	else
+		emit_mov_i_no8m(rd, val, ctx);
+}
+
+#if __LINUX_ARM_ARCH__ < 6
+
+static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRB_I(ARM_R3, r_addr, 1), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 3), ctx);
+	_emit(cond, ARM_LSL_I(ARM_R3, ARM_R3, 16), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R0, r_addr, 2), ctx);
+	_emit(cond, ARM_ORR_S(ARM_R3, ARM_R3, ARM_R1, SRTYPE_LSL, 24), ctx);
+	_emit(cond, ARM_ORR_R(ARM_R3, ARM_R3, ARM_R2), ctx);
+	_emit(cond, ARM_ORR_S(r_res, ARM_R3, ARM_R0, SRTYPE_LSL, 8), ctx);
+}
+
+static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 1), ctx);
+	_emit(cond, ARM_ORR_S(r_res, ARM_R2, ARM_R1, SRTYPE_LSL, 8), ctx);
+}
+
+static inline void emit_swap16(u8 r_dst, u8 r_src, struct jit_ctx *ctx)
+{
+	emit(ARM_LSL_R(ARM_R1, r_src, 8), ctx);
+	emit(ARM_ORR_S(r_dst, ARM_R1, r_src, SRTYPE_LSL, 8), ctx);
+	emit(ARM_LSL_I(r_dst, r_dst, 8), ctx);
+	emit(ARM_LSL_R(r_dst, r_dst, 8), ctx);
+}
+
+#else  /* ARMv6+ */
+
+static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDR_I(r_res, r_addr, 0), ctx);
+#ifdef __LITTLE_ENDIAN
+	_emit(cond, ARM_REV(r_res, r_res), ctx);
+#endif
+}
+
+static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRH_I(r_res, r_addr, 0), ctx);
+#ifdef __LITTLE_ENDIAN
+	_emit(cond, ARM_REV16(r_res, r_res), ctx);
+#endif
+}
+
+static inline void emit_swap16(u8 r_dst __maybe_unused,
+			       u8 r_src __maybe_unused,
+			       struct jit_ctx *ctx __maybe_unused)
+{
+#ifdef __LITTLE_ENDIAN
+	emit(ARM_REV16(r_dst, r_src), ctx);
+#endif
+}
+
+#endif /* __LINUX_ARM_ARCH__ < 6 */
+
+
+/* Compute the immediate value for a PC-relative branch. */
+static inline u32 b_imm(unsigned tgt, struct jit_ctx *ctx)
+{
+	u32 imm;
+
+	if (ctx->target == NULL)
+		return 0;
+	/*
+	 * BPF allows only forward jumps and the offset of the target is
+	 * still the one computed during the first pass.
+	 */
+	imm  = ctx->offsets[tgt] + ctx->prologue_bytes - (ctx->idx * 4 + 8);
+
+	return imm >> 2;
+}
+
+#define OP_IMM3(op, r1, r2, imm_val, ctx)				\
+	do {								\
+		imm12 = imm8m(imm_val);					\
+		if (imm12 < 0) {					\
+			emit_mov_i_no8m(r_scratch, imm_val, ctx);	\
+			emit(op ## _R((r1), (r2), r_scratch), ctx);	\
+		} else {						\
+			emit(op ## _I((r1), (r2), imm12), ctx);		\
+		}							\
+	} while (0)
+
+static inline void emit_err_ret(u8 cond, struct jit_ctx *ctx)
+{
+	if (ctx->ret0_fp_idx >= 0) {
+		_emit(cond, ARM_B(b_imm(ctx->ret0_fp_idx, ctx)), ctx);
+		/* NOP to keep the size constant between passes */
+		emit(ARM_MOV_R(ARM_R0, ARM_R0), ctx);
+	} else {
+		_emit(cond, ARM_MOV_I(ARM_R0, 0), ctx);
+		_emit(cond, ARM_B(b_imm(ctx->skf->len, ctx)), ctx);
+	}
+}
+
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 5
+	emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+
+	if (elf_hwcap & HWCAP_THUMB)
+		emit(ARM_BX(tgt_reg), ctx);
+	else
+		emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+#else
+	emit(ARM_BLX_R(tgt_reg), ctx);
+#endif
+}
+
+static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ == 7
+	if (elf_hwcap & HWCAP_IDIVA) {
+		emit(ARM_UDIV(rd, rm, rn), ctx);
+		return;
+	}
+#endif
+	if (rm != ARM_R0)
+		emit(ARM_MOV_R(ARM_R0, rm), ctx);
+	if (rn != ARM_R1)
+		emit(ARM_MOV_R(ARM_R1, rn), ctx);
+
+	ctx->seen |= SEEN_CALL;
+	emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
+	emit_blx_r(ARM_R3, ctx);
+
+	if (rd != ARM_R0)
+		emit(ARM_MOV_R(rd, ARM_R0), ctx);
+}
+
+static inline void update_on_xread(struct jit_ctx *ctx)
+{
+	if (!(ctx->seen & SEEN_X))
+		ctx->flags |= FLAG_NEED_X_RESET;
+
+	ctx->seen |= SEEN_X;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+	void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w};
+	const struct sk_filter *prog = ctx->skf;
+	const struct sock_filter *inst;
+	unsigned i, load_order, off, condt;
+	int imm12;
+	u32 k;
+
+	for (i = 0; i < prog->len; i++) {
+		inst = &(prog->insns[i]);
+		/* K as an immediate value operand */
+		k = inst->k;
+
+		/* compute offsets only in the fake pass */
+		if (ctx->target == NULL)
+			ctx->offsets[i] = ctx->idx * 4;
+
+		switch (inst->code) {
+		case BPF_S_LD_IMM:
+			emit_mov_i(r_A, k, ctx);
+			break;
+		case BPF_S_LD_W_LEN:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+			emit(ARM_LDR_I(r_A, r_skb,
+				       offsetof(struct sk_buff, len)), ctx);
+			break;
+		case BPF_S_LD_MEM:
+			/* A = scratch[k] */
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_LD_W_ABS:
+			load_order = 2;
+			goto load;
+		case BPF_S_LD_H_ABS:
+			load_order = 1;
+			goto load;
+		case BPF_S_LD_B_ABS:
+			load_order = 0;
+load:
+			/* the interpreter will deal with the negative K */
+			if ((int)k < 0)
+				return -ENOTSUPP;
+			emit_mov_i(r_off, k, ctx);
+load_common:
+			ctx->seen |= SEEN_DATA | SEEN_CALL;
+
+			if (load_order > 0) {
+				emit(ARM_SUB_I(r_scratch, r_skb_hl,
+					       1 << load_order), ctx);
+				emit(ARM_CMP_R(r_scratch, r_off), ctx);
+				condt = ARM_COND_HS;
+			} else {
+				emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+				condt = ARM_COND_HI;
+			}
+
+			_emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
+			      ctx);
+
+			if (load_order == 0)
+				_emit(condt, ARM_LDRB_I(r_A, r_scratch, 0),
+				      ctx);
+			else if (load_order == 1)
+				emit_load_be16(condt, r_A, r_scratch, ctx);
+			else if (load_order == 2)
+				emit_load_be32(condt, r_A, r_scratch, ctx);
+
+			_emit(condt, ARM_B(b_imm(i + 1, ctx)), ctx);
+
+			/* the slowpath */
+			emit_mov_i(ARM_R3, (u32)load_func[load_order], ctx);
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			/* the offset is already in R1 */
+			emit_blx_r(ARM_R3, ctx);
+			/* check the result of skb_copy_bits */
+			emit(ARM_CMP_I(ARM_R1, 0), ctx);
+			emit_err_ret(ARM_COND_NE, ctx);
+			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+			break;
+		case BPF_S_LD_W_IND:
+			load_order = 2;
+			goto load_ind;
+		case BPF_S_LD_H_IND:
+			load_order = 1;
+			goto load_ind;
+		case BPF_S_LD_B_IND:
+			load_order = 0;
+load_ind:
+			OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
+			goto load_common;
+		case BPF_S_LDX_IMM:
+			ctx->seen |= SEEN_X;
+			emit_mov_i(r_X, k, ctx);
+			break;
+		case BPF_S_LDX_W_LEN:
+			ctx->seen |= SEEN_X | SEEN_SKB;
+			emit(ARM_LDR_I(r_X, r_skb,
+				       offsetof(struct sk_buff, len)), ctx);
+			break;
+		case BPF_S_LDX_MEM:
+			ctx->seen |= SEEN_X | SEEN_MEM_WORD(k);
+			emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_LDX_B_MSH:
+			/* x = ((*(frame + k)) & 0xf) << 2; */
+			ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
+			/* the interpreter should deal with the negative K */
+			if (k < 0)
+				return -1;
+			/* offset in r1: we might have to take the slow path */
+			emit_mov_i(r_off, k, ctx);
+			emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+
+			/* load in r0: common with the slowpath */
+			_emit(ARM_COND_HI, ARM_LDRB_R(ARM_R0, r_skb_data,
+						      ARM_R1), ctx);
+			/*
+			 * emit_mov_i() might generate one or two instructions,
+			 * the same holds for emit_blx_r()
+			 */
+			_emit(ARM_COND_HI, ARM_B(b_imm(i + 1, ctx) - 2), ctx);
+
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			/* r_off is r1 */
+			emit_mov_i(ARM_R3, (u32)jit_get_skb_b, ctx);
+			emit_blx_r(ARM_R3, ctx);
+			/* check the return value of skb_copy_bits */
+			emit(ARM_CMP_I(ARM_R1, 0), ctx);
+			emit_err_ret(ARM_COND_NE, ctx);
+
+			emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx);
+			emit(ARM_LSL_I(r_X, r_X, 2), ctx);
+			break;
+		case BPF_S_ST:
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_STX:
+			update_on_xread(ctx);
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_ALU_ADD_K:
+			/* A += K */
+			OP_IMM3(ARM_ADD, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_ADD_X:
+			update_on_xread(ctx);
+			emit(ARM_ADD_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_SUB_K:
+			/* A -= K */
+			OP_IMM3(ARM_SUB, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_SUB_X:
+			update_on_xread(ctx);
+			emit(ARM_SUB_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_MUL_K:
+			/* A *= K */
+			emit_mov_i(r_scratch, k, ctx);
+			emit(ARM_MUL(r_A, r_A, r_scratch), ctx);
+			break;
+		case BPF_S_ALU_MUL_X:
+			update_on_xread(ctx);
+			emit(ARM_MUL(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_DIV_K:
+			/* current k == reciprocal_value(userspace k) */
+			emit_mov_i(r_scratch, k, ctx);
+			/* A = top 32 bits of the product */
+			emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+			break;
+		case BPF_S_ALU_DIV_X:
+			update_on_xread(ctx);
+			emit(ARM_CMP_I(r_X, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+			emit_udiv(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_S_ALU_OR_K:
+			/* A |= K */
+			OP_IMM3(ARM_ORR, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_OR_X:
+			update_on_xread(ctx);
+			emit(ARM_ORR_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_AND_K:
+			/* A &= K */
+			OP_IMM3(ARM_AND, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_AND_X:
+			update_on_xread(ctx);
+			emit(ARM_AND_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_LSH_K:
+			if (unlikely(k > 31))
+				return -1;
+			emit(ARM_LSL_I(r_A, r_A, k), ctx);
+			break;
+		case BPF_S_ALU_LSH_X:
+			update_on_xread(ctx);
+			emit(ARM_LSL_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_RSH_K:
+			if (unlikely(k > 31))
+				return -1;
+			emit(ARM_LSR_I(r_A, r_A, k), ctx);
+			break;
+		case BPF_S_ALU_RSH_X:
+			update_on_xread(ctx);
+			emit(ARM_LSR_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_NEG:
+			/* A = -A */
+			emit(ARM_RSB_I(r_A, r_A, 0), ctx);
+			break;
+		case BPF_S_JMP_JA:
+			/* pc += K */
+			emit(ARM_B(b_imm(i + k + 1, ctx)), ctx);
+			break;
+		case BPF_S_JMP_JEQ_K:
+			/* pc += (A == K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_EQ;
+			goto cmp_imm;
+		case BPF_S_JMP_JGT_K:
+			/* pc += (A > K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_HI;
+			goto cmp_imm;
+		case BPF_S_JMP_JGE_K:
+			/* pc += (A >= K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_HS;
+cmp_imm:
+			imm12 = imm8m(k);
+			if (imm12 < 0) {
+				emit_mov_i_no8m(r_scratch, k, ctx);
+				emit(ARM_CMP_R(r_A, r_scratch), ctx);
+			} else {
+				emit(ARM_CMP_I(r_A, imm12), ctx);
+			}
+cond_jump:
+			if (inst->jt)
+				_emit(condt, ARM_B(b_imm(i + inst->jt + 1,
+						   ctx)), ctx);
+			if (inst->jf)
+				_emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1,
+							     ctx)), ctx);
+			break;
+		case BPF_S_JMP_JEQ_X:
+			/* pc += (A == X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_EQ;
+			goto cmp_x;
+		case BPF_S_JMP_JGT_X:
+			/* pc += (A > X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_HI;
+			goto cmp_x;
+		case BPF_S_JMP_JGE_X:
+			/* pc += (A >= X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_CS;
+cmp_x:
+			update_on_xread(ctx);
+			emit(ARM_CMP_R(r_A, r_X), ctx);
+			goto cond_jump;
+		case BPF_S_JMP_JSET_K:
+			/* pc += (A & K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_NE;
+			/* not set iff all zeroes iff Z==1 iff EQ */
+
+			imm12 = imm8m(k);
+			if (imm12 < 0) {
+				emit_mov_i_no8m(r_scratch, k, ctx);
+				emit(ARM_TST_R(r_A, r_scratch), ctx);
+			} else {
+				emit(ARM_TST_I(r_A, imm12), ctx);
+			}
+			goto cond_jump;
+		case BPF_S_JMP_JSET_X:
+			/* pc += (A & X) ? pc->jt : pc->jf */
+			update_on_xread(ctx);
+			condt  = ARM_COND_NE;
+			emit(ARM_TST_R(r_A, r_X), ctx);
+			goto cond_jump;
+		case BPF_S_RET_A:
+			emit(ARM_MOV_R(ARM_R0, r_A), ctx);
+			goto b_epilogue;
+		case BPF_S_RET_K:
+			if ((k == 0) && (ctx->ret0_fp_idx < 0))
+				ctx->ret0_fp_idx = i;
+			emit_mov_i(ARM_R0, k, ctx);
+b_epilogue:
+			if (i != ctx->skf->len - 1)
+				emit(ARM_B(b_imm(prog->len, ctx)), ctx);
+			break;
+		case BPF_S_MISC_TAX:
+			/* X = A */
+			ctx->seen |= SEEN_X;
+			emit(ARM_MOV_R(r_X, r_A), ctx);
+			break;
+		case BPF_S_MISC_TXA:
+			/* A = X */
+			update_on_xread(ctx);
+			emit(ARM_MOV_R(r_A, r_X), ctx);
+			break;
+		case BPF_S_ANC_PROTOCOL:
+			/* A = ntohs(skb->protocol) */
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  protocol) != 2);
+			off = offsetof(struct sk_buff, protocol);
+			emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx);
+			emit_swap16(r_A, r_scratch, ctx);
+			break;
+		case BPF_S_ANC_CPU:
+			/* r_scratch = current_thread_info() */
+			OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx);
+			/* A = current_thread_info()->cpu */
+			BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);
+			off = offsetof(struct thread_info, cpu);
+			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			break;
+		case BPF_S_ANC_IFINDEX:
+			/* A = skb->dev->ifindex */
+			ctx->seen |= SEEN_SKB;
+			off = offsetof(struct sk_buff, dev);
+			emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+
+			emit(ARM_CMP_I(r_scratch, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+
+			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+						  ifindex) != 4);
+			off = offsetof(struct net_device, ifindex);
+			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			break;
+		case BPF_S_ANC_MARK:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+			off = offsetof(struct sk_buff, mark);
+			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+			break;
+		case BPF_S_ANC_RXHASH:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
+			off = offsetof(struct sk_buff, rxhash);
+			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+			break;
+		case BPF_S_ANC_QUEUE:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  queue_mapping) != 2);
+			BUILD_BUG_ON(offsetof(struct sk_buff,
+					      queue_mapping) > 0xff);
+			off = offsetof(struct sk_buff, queue_mapping);
+			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	/* compute offsets only during the first pass */
+	if (ctx->target == NULL)
+		ctx->offsets[i] = ctx->idx * 4;
+
+	return 0;
+}
+
+
+void bpf_jit_compile(struct sk_filter *fp)
+{
+	struct jit_ctx ctx;
+	unsigned tmp_idx;
+	unsigned alloc_size;
+
+	if (!bpf_jit_enable)
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.skf		= fp;
+	ctx.ret0_fp_idx = -1;
+
+	ctx.offsets = kzalloc(GFP_KERNEL, 4 * (ctx.skf->len + 1));
+	if (ctx.offsets == NULL)
+		return;
+
+	/* fake pass to fill in the ctx->seen */
+	if (unlikely(build_body(&ctx)))
+		goto out;
+
+	tmp_idx = ctx.idx;
+	build_prologue(&ctx);
+	ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4;
+
+#if __LINUX_ARM_ARCH__ < 7
+	tmp_idx = ctx.idx;
+	build_epilogue(&ctx);
+	ctx.epilogue_bytes = (ctx.idx - tmp_idx) * 4;
+
+	ctx.idx += ctx.imm_count;
+	if (ctx.imm_count) {
+		ctx.imms = kzalloc(GFP_KERNEL, 4 * ctx.imm_count);
+		if (ctx.imms == NULL)
+			goto out;
+	}
+#else
+	/* there's nothing after the epilogue on ARMv7 */
+	build_epilogue(&ctx);
+#endif
+
+	alloc_size = 4 * ctx.idx;
+	ctx.target = module_alloc(max(sizeof(struct work_struct),
+				      alloc_size));
+	if (unlikely(ctx.target == NULL))
+		goto out;
+
+	ctx.idx = 0;
+	build_prologue(&ctx);
+	build_body(&ctx);
+	build_epilogue(&ctx);
+
+	flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
+
+#if __LINUX_ARM_ARCH__ < 7
+	if (ctx.imm_count)
+		kfree(ctx.imms);
+#endif
+
+	if (bpf_jit_enable > 1)
+		print_hex_dump(KERN_INFO, "BPF JIT code: ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, ctx.target,
+			       alloc_size, false);
+
+	fp->bpf_func = (void *)ctx.target;
+out:
+	kfree(ctx.offsets);
+	return;
+}
+
+static void bpf_jit_free_worker(struct work_struct *work)
+{
+	module_free(NULL, work);
+}
+
+void bpf_jit_free(struct sk_filter *fp)
+{
+	struct work_struct *work;
+
+	if (fp->bpf_func != sk_run_filter) {
+		work = (struct work_struct *)fp->bpf_func;
+
+		INIT_WORK(work, bpf_jit_free_worker);
+		schedule_work(work);
+	}
+}
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
new file mode 100644
index 000000000000..99ae5e3f46d2
--- /dev/null
+++ b/arch/arm/net/bpf_jit_32.h
@@ -0,0 +1,190 @@
+/*
+ * Just-In-Time compiler for BPF filters on 32bit ARM
+ *
+ * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+
+#ifndef PFILTER_OPCODES_ARM_H
+#define PFILTER_OPCODES_ARM_H
+
+#define ARM_R0	0
+#define ARM_R1	1
+#define ARM_R2	2
+#define ARM_R3	3
+#define ARM_R4	4
+#define ARM_R5	5
+#define ARM_R6	6
+#define ARM_R7	7
+#define ARM_R8	8
+#define ARM_R9	9
+#define ARM_R10	10
+#define ARM_FP	11
+#define ARM_IP	12
+#define ARM_SP	13
+#define ARM_LR	14
+#define ARM_PC	15
+
+#define ARM_COND_EQ		0x0
+#define ARM_COND_NE		0x1
+#define ARM_COND_CS		0x2
+#define ARM_COND_HS		ARM_COND_CS
+#define ARM_COND_CC		0x3
+#define ARM_COND_LO		ARM_COND_CC
+#define ARM_COND_MI		0x4
+#define ARM_COND_PL		0x5
+#define ARM_COND_VS		0x6
+#define ARM_COND_VC		0x7
+#define ARM_COND_HI		0x8
+#define ARM_COND_LS		0x9
+#define ARM_COND_GE		0xa
+#define ARM_COND_LT		0xb
+#define ARM_COND_GT		0xc
+#define ARM_COND_LE		0xd
+#define ARM_COND_AL		0xe
+
+/* register shift types */
+#define SRTYPE_LSL		0
+#define SRTYPE_LSR		1
+#define SRTYPE_ASR		2
+#define SRTYPE_ROR		3
+
+#define ARM_INST_ADD_R		0x00800000
+#define ARM_INST_ADD_I		0x02800000
+
+#define ARM_INST_AND_R		0x00000000
+#define ARM_INST_AND_I		0x02000000
+
+#define ARM_INST_BIC_R		0x01c00000
+#define ARM_INST_BIC_I		0x03c00000
+
+#define ARM_INST_B		0x0a000000
+#define ARM_INST_BX		0x012FFF10
+#define ARM_INST_BLX_R		0x012fff30
+
+#define ARM_INST_CMP_R		0x01500000
+#define ARM_INST_CMP_I		0x03500000
+
+#define ARM_INST_LDRB_I		0x05d00000
+#define ARM_INST_LDRB_R		0x07d00000
+#define ARM_INST_LDRH_I		0x01d000b0
+#define ARM_INST_LDR_I		0x05900000
+
+#define ARM_INST_LDM		0x08900000
+
+#define ARM_INST_LSL_I		0x01a00000
+#define ARM_INST_LSL_R		0x01a00010
+
+#define ARM_INST_LSR_I		0x01a00020
+#define ARM_INST_LSR_R		0x01a00030
+
+#define ARM_INST_MOV_R		0x01a00000
+#define ARM_INST_MOV_I		0x03a00000
+#define ARM_INST_MOVW		0x03000000
+#define ARM_INST_MOVT		0x03400000
+
+#define ARM_INST_MUL		0x00000090
+
+#define ARM_INST_POP		0x08bd0000
+#define ARM_INST_PUSH		0x092d0000
+
+#define ARM_INST_ORR_R		0x01800000
+#define ARM_INST_ORR_I		0x03800000
+
+#define ARM_INST_REV		0x06bf0f30
+#define ARM_INST_REV16		0x06bf0fb0
+
+#define ARM_INST_RSB_I		0x02600000
+
+#define ARM_INST_SUB_R		0x00400000
+#define ARM_INST_SUB_I		0x02400000
+
+#define ARM_INST_STR_I		0x05800000
+
+#define ARM_INST_TST_R		0x01100000
+#define ARM_INST_TST_I		0x03100000
+
+#define ARM_INST_UDIV		0x0730f010
+
+#define ARM_INST_UMULL		0x00800090
+
+/* register */
+#define _AL3_R(op, rd, rn, rm)	((op ## _R) | (rd) << 12 | (rn) << 16 | (rm))
+/* immediate */
+#define _AL3_I(op, rd, rn, imm)	((op ## _I) | (rd) << 12 | (rn) << 16 | (imm))
+
+#define ARM_ADD_R(rd, rn, rm)	_AL3_R(ARM_INST_ADD, rd, rn, rm)
+#define ARM_ADD_I(rd, rn, imm)	_AL3_I(ARM_INST_ADD, rd, rn, imm)
+
+#define ARM_AND_R(rd, rn, rm)	_AL3_R(ARM_INST_AND, rd, rn, rm)
+#define ARM_AND_I(rd, rn, imm)	_AL3_I(ARM_INST_AND, rd, rn, imm)
+
+#define ARM_BIC_R(rd, rn, rm)	_AL3_R(ARM_INST_BIC, rd, rn, rm)
+#define ARM_BIC_I(rd, rn, imm)	_AL3_I(ARM_INST_BIC, rd, rn, imm)
+
+#define ARM_B(imm24)		(ARM_INST_B | ((imm24) & 0xffffff))
+#define ARM_BX(rm)		(ARM_INST_BX | (rm))
+#define ARM_BLX_R(rm)		(ARM_INST_BLX_R | (rm))
+
+#define ARM_CMP_R(rn, rm)	_AL3_R(ARM_INST_CMP, 0, rn, rm)
+#define ARM_CMP_I(rn, imm)	_AL3_I(ARM_INST_CMP, 0, rn, imm)
+
+#define ARM_LDR_I(rt, rn, off)	(ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+#define ARM_LDRB_I(rt, rn, off)	(ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+#define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \
+				 | (rm))
+#define ARM_LDRH_I(rt, rn, off)	(ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
+				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
+
+#define ARM_LDM(rn, regs)	(ARM_INST_LDM | (rn) << 16 | (regs))
+
+#define ARM_LSL_R(rd, rn, rm)	(_AL3_R(ARM_INST_LSL, rd, 0, rn) | (rm) << 8)
+#define ARM_LSL_I(rd, rn, imm)	(_AL3_I(ARM_INST_LSL, rd, 0, rn) | (imm) << 7)
+
+#define ARM_LSR_R(rd, rn, rm)	(_AL3_R(ARM_INST_LSR, rd, 0, rn) | (rm) << 8)
+#define ARM_LSR_I(rd, rn, imm)	(_AL3_I(ARM_INST_LSR, rd, 0, rn) | (imm) << 7)
+
+#define ARM_MOV_R(rd, rm)	_AL3_R(ARM_INST_MOV, rd, 0, rm)
+#define ARM_MOV_I(rd, imm)	_AL3_I(ARM_INST_MOV, rd, 0, imm)
+
+#define ARM_MOVW(rd, imm)	\
+	(ARM_INST_MOVW | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
+
+#define ARM_MOVT(rd, imm)	\
+	(ARM_INST_MOVT | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
+
+#define ARM_MUL(rd, rm, rn)	(ARM_INST_MUL | (rd) << 16 | (rm) << 8 | (rn))
+
+#define ARM_POP(regs)		(ARM_INST_POP | (regs))
+#define ARM_PUSH(regs)		(ARM_INST_PUSH | (regs))
+
+#define ARM_ORR_R(rd, rn, rm)	_AL3_R(ARM_INST_ORR, rd, rn, rm)
+#define ARM_ORR_I(rd, rn, imm)	_AL3_I(ARM_INST_ORR, rd, rn, imm)
+#define ARM_ORR_S(rd, rn, rm, type, rs)	\
+	(ARM_ORR_R(rd, rn, rm) | (type) << 5 | (rs) << 7)
+
+#define ARM_REV(rd, rm)		(ARM_INST_REV | (rd) << 12 | (rm))
+#define ARM_REV16(rd, rm)	(ARM_INST_REV16 | (rd) << 12 | (rm))
+
+#define ARM_RSB_I(rd, rn, imm)	_AL3_I(ARM_INST_RSB, rd, rn, imm)
+
+#define ARM_SUB_R(rd, rn, rm)	_AL3_R(ARM_INST_SUB, rd, rn, rm)
+#define ARM_SUB_I(rd, rn, imm)	_AL3_I(ARM_INST_SUB, rd, rn, imm)
+
+#define ARM_STR_I(rt, rn, off)	(ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+
+#define ARM_TST_R(rn, rm)	_AL3_R(ARM_INST_TST, 0, rn, rm)
+#define ARM_TST_I(rn, imm)	_AL3_I(ARM_INST_TST, 0, rn, imm)
+
+#define ARM_UDIV(rd, rn, rm)	(ARM_INST_UDIV | (rd) << 16 | (rn) | (rm) << 8)
+
+#define ARM_UMULL(rd_lo, rd_hi, rn, rm)	(ARM_INST_UMULL | (rd_hi) << 16 \
+					 | (rd_lo) << 12 | (rm) << 8 | rn)
+
+#endif /* PFILTER_OPCODES_ARM_H */
diff --git a/arch/arm/nwfpe/fpa11.c b/arch/arm/nwfpe/fpa11.c
index cc60acde84d9..2782ebcc2ed3 100644
--- a/arch/arm/nwfpe/fpa11.c
+++ b/arch/arm/nwfpe/fpa11.c
@@ -28,7 +28,6 @@
 
 #include <linux/compiler.h>
 #include <linux/string.h>
-#include <asm/system.h>
 
 /* Reset the FPA11 chip.  Called to initialize and reset the emulator. */
 static void resetFPA11(void)
diff --git a/arch/arm/plat-iop/i2c.c b/arch/arm/plat-iop/i2c.c
index 4efe392859ee..88215ad031a2 100644
--- a/arch/arm/plat-iop/i2c.c
+++ b/arch/arm/plat-iop/i2c.c
@@ -23,7 +23,6 @@
 #include <asm/page.h>
 #include <asm/mach/map.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/memory.h>
 #include <mach/hardware.h>
 #include <asm/hardware/iop3xx.h>
diff --git a/arch/arm/plat-iop/pci.c b/arch/arm/plat-iop/pci.c
index 72768356447a..0da42058a20f 100644
--- a/arch/arm/plat-iop/pci.c
+++ b/arch/arm/plat-iop/pci.c
@@ -20,7 +20,6 @@
 #include <linux/io.h>
 #include <asm/irq.h>
 #include <asm/signal.h>
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/mach/pci.h>
 #include <asm/hardware/iop3xx.h>
diff --git a/arch/arm/plat-iop/restart.c b/arch/arm/plat-iop/restart.c
index 6a85a0c502e6..33fa699a4d28 100644
--- a/arch/arm/plat-iop/restart.c
+++ b/arch/arm/plat-iop/restart.c
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 #include <asm/hardware/iop3xx.h>
+#include <asm/system_misc.h>
 #include <mach/hardware.h>
 
 void iop3xx_restart(char mode, const char *cmd)
diff --git a/arch/arm/plat-mxc/3ds_debugboard.c b/arch/arm/plat-mxc/3ds_debugboard.c
index d1e31fa1b0c3..5cac2c540f4f 100644
--- a/arch/arm/plat-mxc/3ds_debugboard.c
+++ b/arch/arm/plat-mxc/3ds_debugboard.c
@@ -80,7 +80,7 @@ static struct smsc911x_platform_config smsc911x_config = {
 
 static struct platform_device smsc_lan9217_device = {
 	.name = "smsc911x",
-	.id = 0,
+	.id = -1,
 	.dev = {
 		.platform_data = &smsc911x_config,
 	},
diff --git a/arch/arm/plat-mxc/include/mach/hardware.h b/arch/arm/plat-mxc/include/mach/hardware.h
index a599f01f8b92..0630513554de 100644
--- a/arch/arm/plat-mxc/include/mach/hardware.h
+++ b/arch/arm/plat-mxc/include/mach/hardware.h
@@ -22,11 +22,8 @@
 
 #include <asm/sizes.h>
 
-#ifdef __ASSEMBLER__
-#define IOMEM(addr)	(addr)
-#else
-#define IOMEM(addr)	((void __force __iomem *)(addr))
-#endif
+#define addr_in_module(addr, mod) \
+	((unsigned long)(addr) - mod ## _BASE_ADDR < mod ## _SIZE)
 
 #define IMX_IO_P2V_MODULE(addr, module)					\
 	(((addr) - module ## _BASE_ADDR) < module ## _SIZE ?		\
diff --git a/arch/arm/plat-mxc/include/mach/io.h b/arch/arm/plat-mxc/include/mach/io.h
deleted file mode 100644
index 338300b18b00..000000000000
--- a/arch/arm/plat-mxc/include/mach/io.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- *  Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- */
-
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_ARCH_MXC_IO_H__
-#define __ASM_ARCH_MXC_IO_H__
-
-/* Allow IO space to be anywhere in the memory */
-#define IO_SPACE_LIMIT 0xffffffff
-
-#define __arch_ioremap __imx_ioremap
-#define __arch_iounmap __iounmap
-
-#define addr_in_module(addr, mod) \
-	((unsigned long)(addr) - mod ## _BASE_ADDR < mod ## _SIZE)
-
-extern void __iomem *(*imx_ioremap)(unsigned long, size_t, unsigned int);
-
-static inline void __iomem *
-__imx_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
-{
-	if (imx_ioremap != NULL)
-		return imx_ioremap(phys_addr, size, mtype);
-	else
-		return __arm_ioremap(phys_addr, size, mtype);
-}
-
-/* io address mapping macro */
-#define __io(a)		__typesafe_io(a)
-
-#define __mem_pci(a)	(a)
-
-#endif
diff --git a/arch/arm/plat-mxc/system.c b/arch/arm/plat-mxc/system.c
index f30dcacbbd0a..1996c3e3b8fe 100644
--- a/arch/arm/plat-mxc/system.c
+++ b/arch/arm/plat-mxc/system.c
@@ -25,8 +25,8 @@
 
 #include <mach/hardware.h>
 #include <mach/common.h>
+#include <asm/system_misc.h>
 #include <asm/proc-fns.h>
-#include <asm/system.h>
 #include <asm/mach-types.h>
 
 void __iomem *(*imx_ioremap)(unsigned long, size_t, unsigned int) = NULL;
diff --git a/arch/arm/plat-nomadik/Kconfig b/arch/arm/plat-nomadik/Kconfig
index bca4914b4b9d..4c48c8b60b54 100644
--- a/arch/arm/plat-nomadik/Kconfig
+++ b/arch/arm/plat-nomadik/Kconfig
@@ -23,7 +23,6 @@ config HAS_MTU
 config NOMADIK_MTU_SCHED_CLOCK
 	bool
 	depends on HAS_MTU
-	select HAVE_SCHED_CLOCK
 	help
 	  Use the Multi Timer Unit as the sched_clock.
 
diff --git a/arch/arm/plat-nomadik/include/plat/ste_dma40.h b/arch/arm/plat-nomadik/include/plat/ste_dma40.h
index fd0ee84c45d1..9ff93b065686 100644
--- a/arch/arm/plat-nomadik/include/plat/ste_dma40.h
+++ b/arch/arm/plat-nomadik/include/plat/ste_dma40.h
@@ -200,8 +200,7 @@ dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan,
 	sg.dma_address = addr;
 	sg.length = size;
 
-	return chan->device->device_prep_slave_sg(chan, &sg, 1,
-						  direction, flags);
+	return dmaengine_prep_slave_sg(chan, &sg, 1, direction, flags);
 }
 
 #else
diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig
index ce1e9b96ba1a..ad95c7a5d009 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -17,6 +17,7 @@ config ARCH_OMAP1
 	select IRQ_DOMAIN
 	select HAVE_IDE
 	select NEED_MACH_MEMORY_H
+	select NEED_MACH_IO_H if PCCARD
 	help
 	  "Systems based on omap7xx, omap15xx or omap16xx"
 
diff --git a/arch/arm/plat-omap/clock.c b/arch/arm/plat-omap/clock.c
index 56b6f8b7053e..8506cbb7fea4 100644
--- a/arch/arm/plat-omap/clock.c
+++ b/arch/arm/plat-omap/clock.c
@@ -441,6 +441,8 @@ static int __init clk_disable_unused(void)
 		return 0;
 
 	pr_info("clock: disabling unused clocks to save power\n");
+
+	spin_lock_irqsave(&clockfw_lock, flags);
 	list_for_each_entry(ck, &clocks, node) {
 		if (ck->ops == &clkops_null)
 			continue;
@@ -448,10 +450,9 @@ static int __init clk_disable_unused(void)
 		if (ck->usecount > 0 || !ck->enable_reg)
 			continue;
 
-		spin_lock_irqsave(&clockfw_lock, flags);
 		arch_clock->clk_disable_unused(ck);
-		spin_unlock_irqrestore(&clockfw_lock, flags);
 	}
+	spin_unlock_irqrestore(&clockfw_lock, flags);
 
 	return 0;
 }
diff --git a/arch/arm/plat-omap/debug-leds.c b/arch/arm/plat-omap/debug-leds.c
index 61a1ec2a6af4..39407cbe34c6 100644
--- a/arch/arm/plat-omap/debug-leds.c
+++ b/arch/arm/plat-omap/debug-leds.c
@@ -15,7 +15,6 @@
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
-#include <asm/system.h>
 #include <asm/mach-types.h>
 
 #include <plat/fpga.h>
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index 74300ae29b71..ecdb3da0dea9 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -36,7 +36,6 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <plat/dma.h>
 
diff --git a/arch/arm/plat-omap/include/plat/gpio.h b/arch/arm/plat-omap/include/plat/gpio.h
index cb75b657b04b..2f6e9924a814 100644
--- a/arch/arm/plat-omap/include/plat/gpio.h
+++ b/arch/arm/plat-omap/include/plat/gpio.h
@@ -158,10 +158,6 @@
 #define OMAP_MPUIO(nr)		(OMAP_MAX_GPIO_LINES + (nr))
 #define OMAP_GPIO_IS_MPUIO(nr)	((nr) >= OMAP_MAX_GPIO_LINES)
 
-#define OMAP_GPIO_IRQ(nr)	(OMAP_GPIO_IS_MPUIO(nr) ? \
-				 IH_MPUIO_BASE + ((nr) & 0x0f) : \
-				 IH_GPIO_BASE + (nr))
-
 struct omap_gpio_dev_attr {
 	int bank_width;		/* GPIO bank width */
 	bool dbck_flag;		/* dbck required or not - True for OMAP3&4 */
@@ -218,30 +214,14 @@ extern void omap_set_gpio_debounce(int gpio, int enable);
 extern void omap_set_gpio_debounce_time(int gpio, int enable);
 /*-------------------------------------------------------------------------*/
 
-/* Wrappers for "new style" GPIO calls, using the new infrastructure
+/*
+ * Wrappers for "new style" GPIO calls, using the new infrastructure
  * which lets us plug in FPGA, I2C, and other implementations.
- * *
+ *
  * The original OMAP-specific calls should eventually be removed.
  */
 
 #include <linux/errno.h>
 #include <asm-generic/gpio.h>
 
-static inline int irq_to_gpio(unsigned irq)
-{
-	int tmp;
-
-	/* omap1 SOC mpuio */
-	if (cpu_class_is_omap1() && (irq < (IH_MPUIO_BASE + 16)))
-		return (irq - IH_MPUIO_BASE) + OMAP_MAX_GPIO_LINES;
-
-	/* SOC gpio */
-	tmp = irq - IH_GPIO_BASE;
-	if (tmp < OMAP_MAX_GPIO_LINES)
-		return tmp;
-
-	/* we don't supply reverse mappings for non-SOC gpios */
-	return -EIO;
-}
-
 #endif
diff --git a/arch/arm/plat-omap/include/plat/hardware.h b/arch/arm/plat-omap/include/plat/hardware.h
index 537b05ae1f51..e897978371c2 100644
--- a/arch/arm/plat-omap/include/plat/hardware.h
+++ b/arch/arm/plat-omap/include/plat/hardware.h
@@ -43,12 +43,6 @@
 #endif
 #include <plat/serial.h>
 
-#ifdef __ASSEMBLER__
-#define IOMEM(x)		(x)
-#else
-#define IOMEM(x)		((void __force __iomem *)(x))
-#endif
-
 /*
  * ---------------------------------------------------------------------------
  * Common definitions for all OMAP processors
diff --git a/arch/arm/plat-omap/include/plat/mmc.h b/arch/arm/plat-omap/include/plat/mmc.h
index f75946c3293d..7a38750c0079 100644
--- a/arch/arm/plat-omap/include/plat/mmc.h
+++ b/arch/arm/plat-omap/include/plat/mmc.h
@@ -137,8 +137,6 @@ struct omap_mmc_platform_data {
 		int (*set_power)(struct device *dev, int slot,
 				 int power_on, int vdd);
 		int (*get_ro)(struct device *dev, int slot);
-		int (*set_sleep)(struct device *dev, int slot, int sleep,
-				 int vdd, int cardsleep);
 		void (*remux)(struct device *dev, int slot, int power_on);
 		/* Call back before enabling / disabling regulators */
 		void (*before_set_reg)(struct device *dev, int slot,
diff --git a/arch/arm/plat-omap/include/plat/omap_hwmod.h b/arch/arm/plat-omap/include/plat/omap_hwmod.h
index 9e8e63d52aab..8070145ccb98 100644
--- a/arch/arm/plat-omap/include/plat/omap_hwmod.h
+++ b/arch/arm/plat-omap/include/plat/omap_hwmod.h
@@ -47,17 +47,17 @@ extern struct omap_hwmod_sysc_fields omap_hwmod_sysc_type2;
  * with the original PRCM protocol defined for OMAP2420
  */
 #define SYSC_TYPE1_MIDLEMODE_SHIFT	12
-#define SYSC_TYPE1_MIDLEMODE_MASK	(0x3 << SYSC_MIDLEMODE_SHIFT)
+#define SYSC_TYPE1_MIDLEMODE_MASK	(0x3 << SYSC_TYPE1_MIDLEMODE_SHIFT)
 #define SYSC_TYPE1_CLOCKACTIVITY_SHIFT	8
-#define SYSC_TYPE1_CLOCKACTIVITY_MASK	(0x3 << SYSC_CLOCKACTIVITY_SHIFT)
+#define SYSC_TYPE1_CLOCKACTIVITY_MASK	(0x3 << SYSC_TYPE1_CLOCKACTIVITY_SHIFT)
 #define SYSC_TYPE1_SIDLEMODE_SHIFT	3
-#define SYSC_TYPE1_SIDLEMODE_MASK	(0x3 << SYSC_SIDLEMODE_SHIFT)
+#define SYSC_TYPE1_SIDLEMODE_MASK	(0x3 << SYSC_TYPE1_SIDLEMODE_SHIFT)
 #define SYSC_TYPE1_ENAWAKEUP_SHIFT	2
-#define SYSC_TYPE1_ENAWAKEUP_MASK	(1 << SYSC_ENAWAKEUP_SHIFT)
+#define SYSC_TYPE1_ENAWAKEUP_MASK	(1 << SYSC_TYPE1_ENAWAKEUP_SHIFT)
 #define SYSC_TYPE1_SOFTRESET_SHIFT	1
-#define SYSC_TYPE1_SOFTRESET_MASK	(1 << SYSC_SOFTRESET_SHIFT)
+#define SYSC_TYPE1_SOFTRESET_MASK	(1 << SYSC_TYPE1_SOFTRESET_SHIFT)
 #define SYSC_TYPE1_AUTOIDLE_SHIFT	0
-#define SYSC_TYPE1_AUTOIDLE_MASK	(1 << SYSC_AUTOIDLE_SHIFT)
+#define SYSC_TYPE1_AUTOIDLE_MASK	(1 << SYSC_TYPE1_AUTOIDLE_SHIFT)
 
 /*
  * OCP SYSCONFIG bit shifts/masks TYPE2. These are for IPs compliant
diff --git a/arch/arm/plat-omap/include/plat/sdrc.h b/arch/arm/plat-omap/include/plat/sdrc.h
index 925b12b500dc..9bb978ecd884 100644
--- a/arch/arm/plat-omap/include/plat/sdrc.h
+++ b/arch/arm/plat-omap/include/plat/sdrc.h
@@ -16,7 +16,6 @@
  * published by the Free Software Foundation.
  */
 
-#include <mach/io.h>
 
 /* SDRC register offsets - read/write with sdrc_{read,write}_reg() */
 
diff --git a/arch/arm/plat-omap/include/plat/usb.h b/arch/arm/plat-omap/include/plat/usb.h
index d0fc9f4dc155..762eeb0626c1 100644
--- a/arch/arm/plat-omap/include/plat/usb.h
+++ b/arch/arm/plat-omap/include/plat/usb.h
@@ -112,7 +112,6 @@ extern int omap4430_phy_suspend(struct device *dev, int suspend);
  */
 
 #define OMAP2_L4_IO_OFFSET	0xb2000000
-#define IOMEM(x)		((void __force __iomem *)(x))
 #define OMAP2_L4_IO_ADDRESS(pa)	IOMEM((pa) + OMAP2_L4_IO_OFFSET)
 
 static inline u8 omap_readb(u32 pa)
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 089899a7db72..74daf5ed1432 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -21,6 +21,7 @@
 #include <plat/orion_wdt.h>
 #include <plat/mv_xor.h>
 #include <plat/ehci-orion.h>
+#include <mach/bridge-regs.h>
 
 /* Fill in the resources structure and link it into the platform
    device structure. There is always a memory region, and nearly
@@ -568,13 +569,17 @@ void __init orion_spi_1_init(unsigned long mapbase,
  ****************************************************************************/
 static struct orion_wdt_platform_data orion_wdt_data;
 
+static struct resource orion_wdt_resource =
+		DEFINE_RES_MEM(TIMER_VIRT_BASE, 0x28);
+
 static struct platform_device orion_wdt_device = {
 	.name		= "orion_wdt",
 	.id		= -1,
 	.dev		= {
 		.platform_data	= &orion_wdt_data,
 	},
-	.num_resources	= 0,
+	.resource	= &orion_wdt_resource,
+	.num_resources	= 1,
 };
 
 void __init orion_wdt_init(unsigned long tclk)
diff --git a/arch/arm/plat-orion/include/plat/audio.h b/arch/arm/plat-orion/include/plat/audio.h
index 885f8abd927b..d6a55bd2e578 100644
--- a/arch/arm/plat-orion/include/plat/audio.h
+++ b/arch/arm/plat-orion/include/plat/audio.h
@@ -2,7 +2,6 @@
 #define __PLAT_AUDIO_H
 
 struct kirkwood_asoc_platform_data {
-	u32 tclk;
 	int burst;
 };
 #endif
diff --git a/arch/arm/plat-pxa/dma.c b/arch/arm/plat-pxa/dma.c
index 2d3c19d7c7b1..79ef102e3b2b 100644
--- a/arch/arm/plat-pxa/dma.c
+++ b/arch/arm/plat-pxa/dma.c
@@ -20,7 +20,6 @@
 #include <linux/errno.h>
 #include <linux/dma-mapping.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/memory.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/plat-s3c24xx/cpu.c b/arch/arm/plat-s3c24xx/cpu.c
index 32a09931350c..290942d9adda 100644
--- a/arch/arm/plat-s3c24xx/cpu.c
+++ b/arch/arm/plat-s3c24xx/cpu.c
@@ -35,6 +35,8 @@
 #include <mach/regs-clock.h>
 #include <asm/irq.h>
 #include <asm/cacheflush.h>
+#include <asm/system_info.h>
+#include <asm/system_misc.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index 2bab4c99a234..28f898f75380 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -27,7 +27,6 @@
 #include <linux/errno.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
 #include <mach/dma.h>
diff --git a/arch/arm/plat-s5p/Kconfig b/arch/arm/plat-s5p/Kconfig
index 7a308699f816..96bea3202304 100644
--- a/arch/arm/plat-s5p/Kconfig
+++ b/arch/arm/plat-s5p/Kconfig
@@ -9,8 +9,8 @@ config PLAT_S5P
 	bool
 	depends on (ARCH_S5P64X0 || ARCH_S5PC100 || ARCH_S5PV210 || ARCH_EXYNOS)
 	default y
-	select ARM_VIC if !ARCH_EXYNOS4
-	select ARM_GIC if ARCH_EXYNOS4
+	select ARM_VIC if !ARCH_EXYNOS
+	select ARM_GIC if ARCH_EXYNOS
 	select GIC_NON_BANKED if ARCH_EXYNOS4
 	select NO_IOPORT
 	select ARCH_REQUIRE_GPIOLIB
@@ -40,6 +40,10 @@ config S5P_HRT
 	help
 	  Use the High Resolution timer support
 
+config S5P_DEV_UART
+	def_bool y
+	depends on (ARCH_S5P64X0 || ARCH_S5PC100 || ARCH_S5PV210)
+
 config S5P_PM
 	bool
 	help
diff --git a/arch/arm/plat-s5p/Makefile b/arch/arm/plat-s5p/Makefile
index 30d8c3016e6b..4bd824136659 100644
--- a/arch/arm/plat-s5p/Makefile
+++ b/arch/arm/plat-s5p/Makefile
@@ -12,7 +12,6 @@ obj-				:=
 
 # Core files
 
-obj-y				+= dev-uart.o
 obj-y				+= clock.o
 obj-y				+= irq.o
 obj-$(CONFIG_S5P_EXT_INT)	+= irq-eint.o
@@ -23,5 +22,7 @@ obj-$(CONFIG_S5P_SLEEP)		+= sleep.o
 obj-$(CONFIG_S5P_HRT) 		+= s5p-time.o
 
 # devices
+
+obj-$(CONFIG_S5P_DEV_UART)	+= dev-uart.o
 obj-$(CONFIG_S5P_DEV_MFC)	+= dev-mfc.o
 obj-$(CONFIG_S5P_SETUP_MIPIPHY)	+= setup-mipiphy.o
diff --git a/arch/arm/plat-s5p/clock.c b/arch/arm/plat-s5p/clock.c
index 963edea7f7e7..f68a9bb11948 100644
--- a/arch/arm/plat-s5p/clock.c
+++ b/arch/arm/plat-s5p/clock.c
@@ -61,6 +61,20 @@ struct clk clk_fout_apll = {
 	.id		= -1,
 };
 
+/* BPLL clock output */
+
+struct clk clk_fout_bpll = {
+	.name		= "fout_bpll",
+	.id		= -1,
+};
+
+/* CPLL clock output */
+
+struct clk clk_fout_cpll = {
+	.name		= "fout_cpll",
+	.id		= -1,
+};
+
 /* MPLL clock output
  * No need .ctrlbit, this is always on
 */
@@ -101,6 +115,28 @@ struct clksrc_sources clk_src_apll = {
 	.nr_sources	= ARRAY_SIZE(clk_src_apll_list),
 };
 
+/* Possible clock sources for BPLL Mux */
+static struct clk *clk_src_bpll_list[] = {
+	[0] = &clk_fin_bpll,
+	[1] = &clk_fout_bpll,
+};
+
+struct clksrc_sources clk_src_bpll = {
+	.sources	= clk_src_bpll_list,
+	.nr_sources	= ARRAY_SIZE(clk_src_bpll_list),
+};
+
+/* Possible clock sources for CPLL Mux */
+static struct clk *clk_src_cpll_list[] = {
+	[0] = &clk_fin_cpll,
+	[1] = &clk_fout_cpll,
+};
+
+struct clksrc_sources clk_src_cpll = {
+	.sources	= clk_src_cpll_list,
+	.nr_sources	= ARRAY_SIZE(clk_src_cpll_list),
+};
+
 /* Possible clock sources for MPLL Mux */
 static struct clk *clk_src_mpll_list[] = {
 	[0] = &clk_fin_mpll,
diff --git a/arch/arm/plat-s5p/irq-pm.c b/arch/arm/plat-s5p/irq-pm.c
index 327acb3a4464..d1bfecae6c9f 100644
--- a/arch/arm/plat-s5p/irq-pm.c
+++ b/arch/arm/plat-s5p/irq-pm.c
@@ -39,19 +39,32 @@ unsigned long s3c_irqwake_eintallow	= 0xffffffffL;
 int s3c_irq_wake(struct irq_data *data, unsigned int state)
 {
 	unsigned long irqbit;
+	unsigned int irq_rtc_tic, irq_rtc_alarm;
+
+#ifdef CONFIG_ARCH_EXYNOS
+	if (soc_is_exynos5250()) {
+		irq_rtc_tic = EXYNOS5_IRQ_RTC_TIC;
+		irq_rtc_alarm = EXYNOS5_IRQ_RTC_ALARM;
+	} else {
+		irq_rtc_tic = EXYNOS4_IRQ_RTC_TIC;
+		irq_rtc_alarm = EXYNOS4_IRQ_RTC_ALARM;
+	}
+#else
+	irq_rtc_tic = IRQ_RTC_TIC;
+	irq_rtc_alarm = IRQ_RTC_ALARM;
+#endif
+
+	if (data->irq == irq_rtc_tic || data->irq == irq_rtc_alarm) {
+		irqbit = 1 << (data->irq + 1 - irq_rtc_alarm);
 
-	switch (data->irq) {
-	case IRQ_RTC_TIC:
-	case IRQ_RTC_ALARM:
-		irqbit = 1 << (data->irq + 1 - IRQ_RTC_ALARM);
 		if (!state)
 			s3c_irqwake_intmask |= irqbit;
 		else
 			s3c_irqwake_intmask &= ~irqbit;
-		break;
-	default:
+	} else {
 		return -ENOENT;
 	}
+
 	return 0;
 }
 
diff --git a/arch/arm/plat-samsung/cpu.c b/arch/arm/plat-samsung/cpu.c
index 81c06d44c11e..46b426e8aff5 100644
--- a/arch/arm/plat-samsung/cpu.c
+++ b/arch/arm/plat-samsung/cpu.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 
 #include <mach/map.h>
 #include <plat/cpu.h>
diff --git a/arch/arm/plat-samsung/dma-ops.c b/arch/arm/plat-samsung/dma-ops.c
index 301d9c319d0b..eb9f4f534006 100644
--- a/arch/arm/plat-samsung/dma-ops.c
+++ b/arch/arm/plat-samsung/dma-ops.c
@@ -79,11 +79,11 @@ static int samsung_dmadev_prepare(unsigned ch,
 			    info->len, offset_in_page(info->buf));
 		sg_dma_address(&sg) = info->buf;
 
-		desc = chan->device->device_prep_slave_sg(chan,
+		desc = dmaengine_prep_slave_sg(chan,
 			&sg, 1, info->direction, DMA_PREP_INTERRUPT);
 		break;
 	case DMA_CYCLIC:
-		desc = chan->device->device_prep_dma_cyclic(chan,
+		desc = dmaengine_prep_dma_cyclic(chan,
 			info->buf, info->len, info->period, info->direction);
 		break;
 	default:
diff --git a/arch/arm/plat-samsung/include/plat/cpu.h b/arch/arm/plat-samsung/include/plat/cpu.h
index 73cb3cfd0685..787ceaca0be8 100644
--- a/arch/arm/plat-samsung/include/plat/cpu.h
+++ b/arch/arm/plat-samsung/include/plat/cpu.h
@@ -42,6 +42,9 @@ extern unsigned long samsung_cpu_id;
 #define EXYNOS4412_CPU_ID	0xE4412200
 #define EXYNOS4_CPU_MASK	0xFFFE0000
 
+#define EXYNOS5250_SOC_ID	0x43520000
+#define EXYNOS5_SOC_MASK	0xFFFFF000
+
 #define IS_SAMSUNG_CPU(name, id, mask)		\
 static inline int is_samsung_##name(void)	\
 {						\
@@ -58,6 +61,7 @@ IS_SAMSUNG_CPU(s5pv210, S5PV210_CPU_ID, S5PV210_CPU_MASK)
 IS_SAMSUNG_CPU(exynos4210, EXYNOS4210_CPU_ID, EXYNOS4_CPU_MASK)
 IS_SAMSUNG_CPU(exynos4212, EXYNOS4212_CPU_ID, EXYNOS4_CPU_MASK)
 IS_SAMSUNG_CPU(exynos4412, EXYNOS4412_CPU_ID, EXYNOS4_CPU_MASK)
+IS_SAMSUNG_CPU(exynos5250, EXYNOS5250_SOC_ID, EXYNOS5_SOC_MASK)
 
 #if defined(CONFIG_CPU_S3C2410) || defined(CONFIG_CPU_S3C2412) || \
     defined(CONFIG_CPU_S3C2416) || defined(CONFIG_CPU_S3C2440) || \
@@ -120,6 +124,12 @@ IS_SAMSUNG_CPU(exynos4412, EXYNOS4412_CPU_ID, EXYNOS4_CPU_MASK)
 #define EXYNOS4210_REV_1_0	(0x10)
 #define EXYNOS4210_REV_1_1	(0x11)
 
+#if defined(CONFIG_SOC_EXYNOS5250)
+# define soc_is_exynos5250()	is_samsung_exynos5250()
+#else
+# define soc_is_exynos5250()	0
+#endif
+
 #define IODESC_ENT(x) { (unsigned long)S3C24XX_VA_##x, __phys_to_pfn(S3C24XX_PA_##x), S3C24XX_SZ_##x, MT_DEVICE }
 
 #ifndef MHZ
diff --git a/arch/arm/plat-samsung/include/plat/devs.h b/arch/arm/plat-samsung/include/plat/devs.h
index 5e7972de3ed5..2155d4af62a3 100644
--- a/arch/arm/plat-samsung/include/plat/devs.h
+++ b/arch/arm/plat-samsung/include/plat/devs.h
@@ -26,6 +26,8 @@ struct s3c24xx_uart_resources {
 extern struct s3c24xx_uart_resources s3c2410_uart_resources[];
 extern struct s3c24xx_uart_resources s3c64xx_uart_resources[];
 extern struct s3c24xx_uart_resources s5p_uart_resources[];
+extern struct s3c24xx_uart_resources exynos4_uart_resources[];
+extern struct s3c24xx_uart_resources exynos5_uart_resources[];
 
 extern struct platform_device *s3c24xx_uart_devs[];
 extern struct platform_device *s3c24xx_uart_src[];
diff --git a/arch/arm/plat-samsung/include/plat/s5p-clock.h b/arch/arm/plat-samsung/include/plat/s5p-clock.h
index 984bf9e7bc89..1de4b32f98e9 100644
--- a/arch/arm/plat-samsung/include/plat/s5p-clock.h
+++ b/arch/arm/plat-samsung/include/plat/s5p-clock.h
@@ -18,6 +18,8 @@
 #define GET_DIV(clk, field) ((((clk) & field##_MASK) >> field##_SHIFT) + 1)
 
 #define clk_fin_apll clk_ext_xtal_mux
+#define clk_fin_bpll clk_ext_xtal_mux
+#define clk_fin_cpll clk_ext_xtal_mux
 #define clk_fin_mpll clk_ext_xtal_mux
 #define clk_fin_epll clk_ext_xtal_mux
 #define clk_fin_dpll clk_ext_xtal_mux
@@ -29,6 +31,8 @@ extern struct clk clk_xusbxti;
 extern struct clk clk_48m;
 extern struct clk s5p_clk_27m;
 extern struct clk clk_fout_apll;
+extern struct clk clk_fout_bpll;
+extern struct clk clk_fout_cpll;
 extern struct clk clk_fout_mpll;
 extern struct clk clk_fout_epll;
 extern struct clk clk_fout_dpll;
@@ -37,6 +41,8 @@ extern struct clk clk_arm;
 extern struct clk clk_vpll;
 
 extern struct clksrc_sources clk_src_apll;
+extern struct clksrc_sources clk_src_bpll;
+extern struct clksrc_sources clk_src_cpll;
 extern struct clksrc_sources clk_src_mpll;
 extern struct clksrc_sources clk_src_epll;
 extern struct clksrc_sources clk_src_dpll;
diff --git a/arch/arm/plat-samsung/include/plat/uncompress.h b/arch/arm/plat-samsung/include/plat/uncompress.h
index ee48e12a1e72..7e068d182c3d 100644
--- a/arch/arm/plat-samsung/include/plat/uncompress.h
+++ b/arch/arm/plat-samsung/include/plat/uncompress.h
@@ -37,7 +37,9 @@ static void arch_detect_cpu(void);
 /* how many bytes we allow into the FIFO at a time in FIFO mode */
 #define FIFO_MAX	 (14)
 
+#ifdef S3C_PA_UART
 #define uart_base S3C_PA_UART + (S3C_UART_OFFSET * CONFIG_S3C_LOWLEVEL_UART_PORT)
+#endif
 
 static __inline__ void
 uart_wr(unsigned int reg, unsigned int val)
diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c
index 51583cd30164..f980cf3d2baa 100644
--- a/arch/arm/plat-samsung/irq-vic-timer.c
+++ b/arch/arm/plat-samsung/irq-vic-timer.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 
 #include <mach/map.h>
+#include <plat/cpu.h>
 #include <plat/irq-vic-timer.h>
 #include <plat/regs-timer.h>
 
@@ -57,6 +58,21 @@ void __init s3c_init_vic_timer_irq(unsigned int num, unsigned int timer_irq)
 	struct irq_chip_type *ct;
 	unsigned int i;
 
+#ifdef CONFIG_ARCH_EXYNOS
+	if (soc_is_exynos5250()) {
+		pirq[0] = EXYNOS5_IRQ_TIMER0_VIC;
+		pirq[1] = EXYNOS5_IRQ_TIMER1_VIC;
+		pirq[2] = EXYNOS5_IRQ_TIMER2_VIC;
+		pirq[3] = EXYNOS5_IRQ_TIMER3_VIC;
+		pirq[4] = EXYNOS5_IRQ_TIMER4_VIC;
+	} else {
+		pirq[0] = EXYNOS4_IRQ_TIMER0_VIC;
+		pirq[1] = EXYNOS4_IRQ_TIMER1_VIC;
+		pirq[2] = EXYNOS4_IRQ_TIMER2_VIC;
+		pirq[3] = EXYNOS4_IRQ_TIMER3_VIC;
+		pirq[4] = EXYNOS4_IRQ_TIMER4_VIC;
+	}
+#endif
 	s3c_tgc = irq_alloc_generic_chip("s3c-timer", 1, timer_irq,
 					 S3C64XX_TINT_CSTAT, handle_level_irq);
 
diff --git a/arch/arm/plat-samsung/time.c b/arch/arm/plat-samsung/time.c
index e3bb806bbafe..4dcb11c3d894 100644
--- a/arch/arm/plat-samsung/time.c
+++ b/arch/arm/plat-samsung/time.c
@@ -28,7 +28,6 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 
diff --git a/arch/arm/plat-spear/include/plat/hardware.h b/arch/arm/plat-spear/include/plat/hardware.h
index 66d677225d15..70187d763e26 100644
--- a/arch/arm/plat-spear/include/plat/hardware.h
+++ b/arch/arm/plat-spear/include/plat/hardware.h
@@ -14,10 +14,4 @@
 #ifndef __PLAT_HARDWARE_H
 #define __PLAT_HARDWARE_H
 
-#ifndef __ASSEMBLY__
-#define IOMEM(x)	((void __iomem __force *)(x))
-#else
-#define IOMEM(x)	(x)
-#endif
-
 #endif /* __PLAT_HARDWARE_H */
diff --git a/arch/arm/plat-spear/include/plat/io.h b/arch/arm/plat-spear/include/plat/io.h
deleted file mode 100644
index 4d4ba822b3eb..000000000000
--- a/arch/arm/plat-spear/include/plat/io.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/plat-spear/include/plat/io.h
- *
- * IO definitions for SPEAr platform
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar<viresh.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __PLAT_IO_H
-#define __PLAT_IO_H
-
-#define IO_SPACE_LIMIT		0xFFFFFFFF
-
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
-
-#endif /* __PLAT_IO_H */
diff --git a/arch/arm/plat-spear/include/plat/keyboard.h b/arch/arm/plat-spear/include/plat/keyboard.h
index c16cc31ecbed..0562f134621d 100644
--- a/arch/arm/plat-spear/include/plat/keyboard.h
+++ b/arch/arm/plat-spear/include/plat/keyboard.h
@@ -159,11 +159,4 @@ struct kbd_platform_data {
 	unsigned int mode;
 };
 
-/* This function is used to set platform data field of pdev->dev */
-static inline void
-kbd_set_plat_data(struct platform_device *pdev, struct kbd_platform_data *data)
-{
-	pdev->dev.platform_data = data;
-}
-
 #endif /* __PLAT_KEYBOARD_H */
diff --git a/arch/arm/plat-spear/restart.c b/arch/arm/plat-spear/restart.c
index 2b4e3d82957c..16f203e78d89 100644
--- a/arch/arm/plat-spear/restart.c
+++ b/arch/arm/plat-spear/restart.c
@@ -11,6 +11,7 @@
  * warranty of any kind, whether express or implied.
  */
 #include <linux/io.h>
+#include <asm/system_misc.h>
 #include <asm/hardware/sp810.h>
 #include <mach/hardware.h>
 #include <mach/generic.h>
diff --git a/arch/arm/plat-versatile/Kconfig b/arch/arm/plat-versatile/Kconfig
index 52353beb369d..043f7b02a9e7 100644
--- a/arch/arm/plat-versatile/Kconfig
+++ b/arch/arm/plat-versatile/Kconfig
@@ -11,7 +11,6 @@ config PLAT_VERSATILE_LEDS
 	depends on ARCH_REALVIEW || ARCH_VERSATILE
 
 config PLAT_VERSATILE_SCHED_CLOCK
-	def_bool y if !ARCH_INTEGRATOR_AP
-	select HAVE_SCHED_CLOCK
+	def_bool y
 
 endif
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 8f3ccddbdafd..858748eaa144 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -18,7 +18,9 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 
+#include <asm/cp15.h>
 #include <asm/cputype.h>
+#include <asm/system_info.h>
 #include <asm/thread_notify.h>
 #include <asm/vfp.h>
 
diff --git a/arch/avr32/boards/atngw100/setup.c b/arch/avr32/boards/atngw100/setup.c
index 7c756fb189f7..afeae8978a8d 100644
--- a/arch/avr32/boards/atngw100/setup.c
+++ b/arch/avr32/boards/atngw100/setup.c
@@ -97,6 +97,7 @@ static struct atmel_nand_data atngw100mkii_nand_data __initdata = {
 	.rdy_pin	= GPIO_PIN_PB(28),
 	.enable_pin	= GPIO_PIN_PE(23),
 	.bus_width_16	= true,
+	.ecc_mode	= NAND_ECC_SOFT,
 	.parts		= nand_partitions,
 	.num_parts	= ARRAY_SIZE(nand_partitions),
 };
diff --git a/arch/avr32/boards/atstk1000/atstk1002.c b/arch/avr32/boards/atstk1000/atstk1002.c
index c56ddac85d61..dc5263321480 100644
--- a/arch/avr32/boards/atstk1000/atstk1002.c
+++ b/arch/avr32/boards/atstk1000/atstk1002.c
@@ -95,6 +95,7 @@ static struct atmel_nand_data atstk1006_nand_data __initdata = {
 	.ale		= 22,
 	.rdy_pin	= GPIO_PIN_PB(30),
 	.enable_pin	= GPIO_PIN_PB(29),
+	.ecc_mode	= NAND_ECC_SOFT,
 	.parts		= nand_partitions,
 	.num_parts	= ARRAY_SIZE(num_partitions),
 };
diff --git a/arch/avr32/boot/images/Makefile b/arch/avr32/boot/images/Makefile
index 1848bf0d7f62..2a3b53978a3b 100644
--- a/arch/avr32/boot/images/Makefile
+++ b/arch/avr32/boot/images/Makefile
@@ -6,8 +6,6 @@
 # for more details.
 #
 
-MKIMAGE		:= $(srctree)/scripts/mkuboot.sh
-
 extra-y		:= vmlinux.bin vmlinux.gz
 
 OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note.gnu.build-id
@@ -17,10 +15,9 @@ $(obj)/vmlinux.bin: vmlinux FORCE
 $(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
 
-quiet_cmd_uimage = UIMAGE $@
-      cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A avr32 -O linux -T kernel	\
-		-C gzip -a $(CONFIG_LOAD_ADDRESS) -e $(CONFIG_ENTRY_ADDRESS)	\
-		-n 'Linux-$(KERNELRELEASE)' -d $< $@
+UIMAGE_LOADADDR = $(CONFIG_LOAD_ADDRESS)
+UIMAGE_ENTRYADDR = $(CONFIG_ENTRY_ADDRESS)
+UIMAGE_COMPRESSION = gzip
 
 targets += uImage uImage.srec
 $(obj)/uImage: $(obj)/vmlinux.gz
diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
index e0ac2631c87e..61407279208a 100644
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -15,7 +15,7 @@
 #define __ASM_AVR32_ATOMIC_H
 
 #include <linux/types.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)  { (i) }
 
diff --git a/arch/avr32/include/asm/barrier.h b/arch/avr32/include/asm/barrier.h
new file mode 100644
index 000000000000..0961275373db
--- /dev/null
+++ b/arch/avr32/include/asm/barrier.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2004-2006 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_AVR32_BARRIER_H
+#define __ASM_AVR32_BARRIER_H
+
+#define nop()			asm volatile("nop")
+
+#define mb()			asm volatile("" : : : "memory")
+#define rmb()			mb()
+#define wmb()			asm volatile("sync 0" : : : "memory")
+#define read_barrier_depends()  do { } while(0)
+#define set_mb(var, value)      do { var = value; mb(); } while(0)
+
+#ifdef CONFIG_SMP
+# error "The AVR32 port does not support SMP"
+#else
+# define smp_mb()		barrier()
+# define smp_rmb()		barrier()
+# define smp_wmb()		barrier()
+# define smp_read_barrier_depends() do { } while(0)
+#endif
+
+
+#endif /* __ASM_AVR32_BARRIER_H */
diff --git a/arch/avr32/include/asm/bitops.h b/arch/avr32/include/asm/bitops.h
index b70c19bab63a..ebe7ad3f490b 100644
--- a/arch/avr32/include/asm/bitops.h
+++ b/arch/avr32/include/asm/bitops.h
@@ -13,7 +13,6 @@
 #endif
 
 #include <asm/byteorder.h>
-#include <asm/system.h>
 
 /*
  * clear_bit() doesn't provide any barrier for the compiler
diff --git a/arch/avr32/include/asm/bug.h b/arch/avr32/include/asm/bug.h
index 2aa373cc61b5..85a92d099adb 100644
--- a/arch/avr32/include/asm/bug.h
+++ b/arch/avr32/include/asm/bug.h
@@ -70,4 +70,9 @@
 
 #include <asm-generic/bug.h>
 
+struct pt_regs;
+void die(const char *str, struct pt_regs *regs, long err);
+void _exception(long signr, struct pt_regs *regs, int code,
+		unsigned long addr);
+
 #endif /* __ASM_AVR32_BUG_H */
diff --git a/arch/avr32/include/asm/system.h b/arch/avr32/include/asm/cmpxchg.h
index 62d9ded01635..962a6aeab787 100644
--- a/arch/avr32/include/asm/system.h
+++ b/arch/avr32/include/asm/cmpxchg.h
@@ -1,76 +1,22 @@
 /*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc.
+ *
+ * But use these as seldom as possible since they are slower than
+ * regular operations.
+ *
  * Copyright (C) 2004-2006 Atmel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#ifndef __ASM_AVR32_SYSTEM_H
-#define __ASM_AVR32_SYSTEM_H
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <linux/types.h>
-
-#include <asm/ptrace.h>
-#include <asm/sysreg.h>
+#ifndef __ASM_AVR32_CMPXCHG_H
+#define __ASM_AVR32_CMPXCHG_H
 
 #define xchg(ptr,x) \
 	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
-#define nop() asm volatile("nop")
-
-#define mb()			asm volatile("" : : : "memory")
-#define rmb()			mb()
-#define wmb()			asm volatile("sync 0" : : : "memory")
-#define read_barrier_depends()  do { } while(0)
-#define set_mb(var, value)      do { var = value; mb(); } while(0)
-
-/*
- * Help PathFinder and other Nexus-compliant debuggers keep track of
- * the current PID by emitting an Ownership Trace Message each time we
- * switch task.
- */
-#ifdef CONFIG_OWNERSHIP_TRACE
-#include <asm/ocd.h>
-#define finish_arch_switch(prev)			\
-	do {						\
-		ocd_write(PID, prev->pid);		\
-		ocd_write(PID, current->pid);		\
-	} while(0)
-#endif
-
-/*
- * switch_to(prev, next, last) should switch from task `prev' to task
- * `next'. `prev' will never be the same as `next'.
- *
- * We just delegate everything to the __switch_to assembly function,
- * which is implemented in arch/avr32/kernel/switch_to.S
- *
- * mb() tells GCC not to cache `current' across this call.
- */
-struct cpu_context;
-struct task_struct;
-extern struct task_struct *__switch_to(struct task_struct *,
-				       struct cpu_context *,
-				       struct cpu_context *);
-#define switch_to(prev, next, last)					\
-	do {								\
-		last = __switch_to(prev, &prev->thread.cpu_context + 1,	\
-				   &next->thread.cpu_context);		\
-	} while (0)
-
-#ifdef CONFIG_SMP
-# error "The AVR32 port does not support SMP"
-#else
-# define smp_mb()		barrier()
-# define smp_rmb()		barrier()
-# define smp_wmb()		barrier()
-# define smp_read_barrier_depends() do { } while(0)
-#endif
-
-#include <linux/irqflags.h>
-
 extern void __xchg_called_with_bad_pointer(void);
 
 static inline unsigned long xchg_u32(u32 val, volatile u32 *m)
@@ -168,11 +114,4 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
 
-struct pt_regs;
-void die(const char *str, struct pt_regs *regs, long err);
-void _exception(long signr, struct pt_regs *regs, int code,
-		unsigned long addr);
-
-#define arch_align_stack(x)	(x)
-
-#endif /* __ASM_AVR32_SYSTEM_H */
+#endif /* __ASM_AVR32_CMPXCHG_H */
diff --git a/arch/avr32/include/asm/exec.h b/arch/avr32/include/asm/exec.h
new file mode 100644
index 000000000000..f467be8bf823
--- /dev/null
+++ b/arch/avr32/include/asm/exec.h
@@ -0,0 +1,13 @@
+/*
+ * Copyright (C) 2004-2006 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_AVR32_EXEC_H
+#define __ASM_AVR32_EXEC_H
+
+#define arch_align_stack(x)	(x)
+
+#endif /* __ASM_AVR32_EXEC_H */
diff --git a/arch/avr32/include/asm/posix_types.h b/arch/avr32/include/asm/posix_types.h
index fe0c0c014389..74667bfc88cc 100644
--- a/arch/avr32/include/asm/posix_types.h
+++ b/arch/avr32/include/asm/posix_types.h
@@ -14,112 +14,27 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long   __kernel_ino_t;
 typedef unsigned short  __kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short  __kernel_nlink_t;
-typedef long            __kernel_off_t;
-typedef int             __kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short  __kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned long	__kernel_size_t;
 typedef long		__kernel_ssize_t;
 typedef int             __kernel_ptrdiff_t;
-typedef long            __kernel_time_t;
-typedef long            __kernel_suseconds_t;
-typedef long            __kernel_clock_t;
-typedef int             __kernel_timer_t;
-typedef int             __kernel_clockid_t;
-typedef int             __kernel_daddr_t;
-typedef char *          __kernel_caddr_t;
-typedef unsigned short  __kernel_uid16_t;
-typedef unsigned short  __kernel_gid16_t;
-typedef unsigned int    __kernel_uid32_t;
-typedef unsigned int    __kernel_gid32_t;
+#define __kernel_size_t __kernel_size_t
 
 typedef unsigned short  __kernel_old_uid_t;
 typedef unsigned short  __kernel_old_gid_t;
-typedef unsigned short  __kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long       __kernel_loff_t;
-#endif
-
-typedef struct {
-    int     val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef  __FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-    unsigned long __tmp = __fd / __NFDBITS;
-    unsigned long __rem = __fd % __NFDBITS;
-    __fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef  __FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-    unsigned long __tmp = __fd / __NFDBITS;
-    unsigned long __rem = __fd % __NFDBITS;
-    __fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
+#define __kernel_old_uid_t __kernel_old_uid_t
 
+typedef unsigned short  __kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#undef  __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-    unsigned long __tmp = __fd / __NFDBITS;
-    unsigned long __rem = __fd % __NFDBITS;
-    return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef  __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-    unsigned long *__tmp = __p->fds_bits;
-    int __i;
-
-    if (__builtin_constant_p(__FDSET_LONGS)) {
-        switch (__FDSET_LONGS) {
-            case 16:
-                __tmp[ 0] = 0; __tmp[ 1] = 0;
-                __tmp[ 2] = 0; __tmp[ 3] = 0;
-                __tmp[ 4] = 0; __tmp[ 5] = 0;
-                __tmp[ 6] = 0; __tmp[ 7] = 0;
-                __tmp[ 8] = 0; __tmp[ 9] = 0;
-                __tmp[10] = 0; __tmp[11] = 0;
-                __tmp[12] = 0; __tmp[13] = 0;
-                __tmp[14] = 0; __tmp[15] = 0;
-                return;
-
-            case 8:
-                __tmp[ 0] = 0; __tmp[ 1] = 0;
-                __tmp[ 2] = 0; __tmp[ 3] = 0;
-                __tmp[ 4] = 0; __tmp[ 5] = 0;
-                __tmp[ 6] = 0; __tmp[ 7] = 0;
-                return;
-
-            case 4:
-                __tmp[ 0] = 0; __tmp[ 1] = 0;
-                __tmp[ 2] = 0; __tmp[ 3] = 0;
-                return;
-        }
-    }
-    __i = __FDSET_LONGS;
-    while (__i) {
-        __i--;
-        *__tmp = 0;
-        __tmp++;
-    }
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* __ASM_AVR32_POSIX_TYPES_H */
diff --git a/arch/avr32/include/asm/switch_to.h b/arch/avr32/include/asm/switch_to.h
new file mode 100644
index 000000000000..9a8e9d5208d4
--- /dev/null
+++ b/arch/avr32/include/asm/switch_to.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (C) 2004-2006 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_AVR32_SWITCH_TO_H
+#define __ASM_AVR32_SWITCH_TO_H
+
+/*
+ * Help PathFinder and other Nexus-compliant debuggers keep track of
+ * the current PID by emitting an Ownership Trace Message each time we
+ * switch task.
+ */
+#ifdef CONFIG_OWNERSHIP_TRACE
+#include <asm/ocd.h>
+#define finish_arch_switch(prev)			\
+	do {						\
+		ocd_write(PID, prev->pid);		\
+		ocd_write(PID, current->pid);		\
+	} while(0)
+#endif
+
+/*
+ * switch_to(prev, next, last) should switch from task `prev' to task
+ * `next'. `prev' will never be the same as `next'.
+ *
+ * We just delegate everything to the __switch_to assembly function,
+ * which is implemented in arch/avr32/kernel/switch_to.S
+ *
+ * mb() tells GCC not to cache `current' across this call.
+ */
+struct cpu_context;
+struct task_struct;
+extern struct task_struct *__switch_to(struct task_struct *,
+				       struct cpu_context *,
+				       struct cpu_context *);
+#define switch_to(prev, next, last)					\
+	do {								\
+		last = __switch_to(prev, &prev->thread.cpu_context + 1,	\
+				   &next->thread.cpu_context);		\
+	} while (0)
+
+
+#endif /* __ASM_AVR32_SWITCH_TO_H */
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 889c544688ca..0445c4fd67e3 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1351,7 +1351,6 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 		goto fail;
 
 	slave->sdata.dma_dev = &dw_dmac0_device.dev;
-	slave->sdata.reg_width = DW_DMA_SLAVE_WIDTH_32BIT;
 	slave->sdata.cfg_hi = (DWC_CFGH_SRC_PER(0)
 				| DWC_CFGH_DST_PER(1));
 	slave->sdata.cfg_lo &= ~(DWC_CFGL_HS_DST_POL
@@ -2046,27 +2045,19 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 	/* Check if DMA slave interface for capture should be configured. */
 	if (flags & AC97C_CAPTURE) {
 		rx_dws->dma_dev = &dw_dmac0_device.dev;
-		rx_dws->reg_width = DW_DMA_SLAVE_WIDTH_16BIT;
 		rx_dws->cfg_hi = DWC_CFGH_SRC_PER(3);
 		rx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 		rx_dws->src_master = 0;
 		rx_dws->dst_master = 1;
-		rx_dws->src_msize = DW_DMA_MSIZE_1;
-		rx_dws->dst_msize = DW_DMA_MSIZE_1;
-		rx_dws->fc = DW_DMA_FC_D_P2M;
 	}
 
 	/* Check if DMA slave interface for playback should be configured. */
 	if (flags & AC97C_PLAYBACK) {
 		tx_dws->dma_dev = &dw_dmac0_device.dev;
-		tx_dws->reg_width = DW_DMA_SLAVE_WIDTH_16BIT;
 		tx_dws->cfg_hi = DWC_CFGH_DST_PER(4);
 		tx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 		tx_dws->src_master = 0;
 		tx_dws->dst_master = 1;
-		tx_dws->src_msize = DW_DMA_MSIZE_1;
-		tx_dws->dst_msize = DW_DMA_MSIZE_1;
-		tx_dws->fc = DW_DMA_FC_D_M2P;
 	}
 
 	if (platform_device_add_data(pdev, data,
@@ -2136,14 +2127,10 @@ at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
 	dws = &data->dws;
 
 	dws->dma_dev = &dw_dmac0_device.dev;
-	dws->reg_width = DW_DMA_SLAVE_WIDTH_32BIT;
 	dws->cfg_hi = DWC_CFGH_DST_PER(2);
 	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 	dws->src_master = 0;
 	dws->dst_master = 1;
-	dws->src_msize = DW_DMA_MSIZE_1;
-	dws->dst_msize = DW_DMA_MSIZE_1;
-	dws->fc = DW_DMA_FC_D_M2P;
 
 	if (platform_device_add_data(pdev, data,
 				sizeof(struct atmel_abdac_pdata)))
diff --git a/arch/avr32/mach-at32ap/cpufreq.c b/arch/avr32/mach-at32ap/cpufreq.c
index 627743326253..18b765629a0c 100644
--- a/arch/avr32/mach-at32ap/cpufreq.c
+++ b/arch/avr32/mach-at32ap/cpufreq.c
@@ -19,7 +19,6 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/export.h>
-#include <asm/system.h>
 
 static struct clk *cpuclk;
 
diff --git a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
index a9b38967f703..4bba58561d5c 100644
--- a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
+++ b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
@@ -14,11 +14,4 @@ struct mci_dma_data {
 #define	slave_data_ptr(s)	(&(s)->sdata)
 #define find_slave_dev(s)	((s)->sdata.dma_dev)
 
-#define	setup_dma_addr(s, t, r)	do {		\
-	if (s) {				\
-		(s)->sdata.tx_reg = (t);	\
-		(s)->sdata.rx_reg = (r);	\
-	}					\
-} while (0)
-
 #endif /* __MACH_ATMEL_MCI_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h
index 67b111ce332d..70742ec997f8 100644
--- a/arch/avr32/mach-at32ap/include/mach/board.h
+++ b/arch/avr32/mach-at32ap/include/mach/board.h
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 #include <linux/serial.h>
 #include <linux/platform_data/macb.h>
+#include <linux/platform_data/atmel.h>
 
 #define GPIO_PIN_NONE	(-1)
 
@@ -116,18 +117,6 @@ struct platform_device *
 at32_add_device_cf(unsigned int id, unsigned int extint,
 		struct cf_platform_data *data);
 
-/* NAND / SmartMedia */
-struct atmel_nand_data {
-	int	enable_pin;	/* chip enable */
-	int	det_pin;	/* card detect */
-	int	rdy_pin;	/* ready/busy */
-	u8	rdy_pin_active_low;	/* rdy_pin value is inverted */
-	u8	ale;		/* address line number connected to ALE */
-	u8	cle;		/* address line number connected to CLE */
-	u8	bus_width_16;	/* buswidth is 16 bit */
-	struct mtd_partition *parts;
-	unsigned int	num_parts;
-};
 struct platform_device *
 at32_add_device_nand(unsigned int id, struct atmel_nand_data *data);
 
diff --git a/arch/avr32/oprofile/op_model_avr32.c b/arch/avr32/oprofile/op_model_avr32.c
index a3e9b3c4845a..f74b7809e089 100644
--- a/arch/avr32/oprofile/op_model_avr32.c
+++ b/arch/avr32/oprofile/op_model_avr32.c
@@ -17,7 +17,6 @@
 #include <linux/types.h>
 
 #include <asm/sysreg.h>
-#include <asm/system.h>
 
 #define AVR32_PERFCTR_IRQ_GROUP	0
 #define AVR32_PERFCTR_IRQ_LINE	1
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index c1269a1085e1..373a6902d8fa 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -823,7 +823,7 @@ config CACHELINE_ALIGNED_L1
 	bool "Locate cacheline_aligned data to L1 Data Memory"
 	default y if !BF54x
 	default n if BF54x
-	depends on !SMP && !BF531
+	depends on !SMP && !BF531 && !CRC32
 	help
 	  If enabled, cacheline_aligned data is linked
 	  into L1 data memory. (less latency)
diff --git a/arch/blackfin/boot/Makefile b/arch/blackfin/boot/Makefile
index 0a49279e3428..f7d27d50d02c 100644
--- a/arch/blackfin/boot/Makefile
+++ b/arch/blackfin/boot/Makefile
@@ -6,20 +6,17 @@
 # for more details.
 #
 
-MKIMAGE := $(srctree)/scripts/mkuboot.sh
-
 targets := vmImage vmImage.bin vmImage.bz2 vmImage.gz vmImage.lzma vmImage.lzo vmImage.xip
 extra-y += vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.xip
 
-UIMAGE_OPTS-y :=
-UIMAGE_OPTS-$(CONFIG_RAMKERNEL) += -a $(CONFIG_BOOT_LOAD)
-UIMAGE_OPTS-$(CONFIG_ROMKERNEL) += -a $(CONFIG_ROM_BASE) -x
-
-quiet_cmd_uimage = UIMAGE  $@
-      cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A $(ARCH) -O linux -T kernel \
-                   -C $(2) -n '$(CPU_REV)-$(KERNELRELEASE)' \
-                   -e $(shell $(NM) vmlinux | awk '$$NF == "__start" {print $$1}') \
-                   $(UIMAGE_OPTS-y) -d $< $@
+ifeq ($(CONFIG_RAMKERNEL),y)
+UIMAGE_LOADADDR = $(CONFIG_BOOT_LOAD)
+else # CONFIG_ROMKERNEL must be set
+UIMAGE_LOADADDR = $(CONFIG_ROM_BASE)
+endif
+UIMAGE_ENTRYADDR = $(shell $(NM) vmlinux | awk '$$NF == "__start" {print $$1}')
+UIMAGE_NAME = '$(CPU_REV)-$(KERNELRELEASE)'
+UIMAGE_OPTS-$(CONFIG_ROMKERNEL) += -x
 
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
diff --git a/arch/blackfin/configs/BF527-EZKIT_defconfig b/arch/blackfin/configs/BF527-EZKIT_defconfig
index 9ccc18a6b4df..90b175323644 100644
--- a/arch/blackfin/configs/BF527-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF527-EZKIT_defconfig
@@ -147,6 +147,7 @@ CONFIG_USB_OTG_BLACKLIST_HUB=y
 CONFIG_USB_MON=y
 CONFIG_USB_MUSB_HDRC=y
 CONFIG_USB_MUSB_BLACKFIN=y
+CONFIG_MUSB_PIO_ONLY=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_GADGET=y
 CONFIG_RTC_CLASS=y
diff --git a/arch/blackfin/include/asm/cmpxchg.h b/arch/blackfin/include/asm/cmpxchg.h
index ba2484f4cb2a..c05868cc61c1 100644
--- a/arch/blackfin/include/asm/cmpxchg.h
+++ b/arch/blackfin/include/asm/cmpxchg.h
@@ -122,7 +122,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
 			(unsigned long)(n), sizeof(*(ptr))))
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
 
-#include <asm-generic/cmpxchg.h>
+#define cmpxchg(ptr, o, n)	cmpxchg_local((ptr), (o), (n))
+#define cmpxchg64(ptr, o, n)	cmpxchg64_local((ptr), (o), (n))
 
 #endif /* !CONFIG_SMP */
 
diff --git a/arch/blackfin/include/asm/gpio.h b/arch/blackfin/include/asm/gpio.h
index 5a25856381ff..12d3571b5232 100644
--- a/arch/blackfin/include/asm/gpio.h
+++ b/arch/blackfin/include/asm/gpio.h
@@ -244,16 +244,26 @@ static inline int gpio_set_debounce(unsigned gpio, unsigned debounce)
 	return -EINVAL;
 }
 
-static inline int gpio_get_value(unsigned gpio)
+static inline int __gpio_get_value(unsigned gpio)
 {
 	return bfin_gpio_get_value(gpio);
 }
 
-static inline void gpio_set_value(unsigned gpio, int value)
+static inline void __gpio_set_value(unsigned gpio, int value)
 {
 	return bfin_gpio_set_value(gpio, value);
 }
 
+static inline int gpio_get_value(unsigned gpio)
+{
+	return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned gpio, int value)
+{
+	return __gpio_set_value(gpio, value);
+}
+
 static inline int gpio_to_irq(unsigned gpio)
 {
 	if (likely(gpio < MAX_BLACKFIN_GPIOS))
diff --git a/arch/blackfin/include/asm/system.h b/arch/blackfin/include/asm/system.h
deleted file mode 100644
index a7f40578587c..000000000000
--- a/arch/blackfin/include/asm/system.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* FILE TO BE DELETED. DO NOT ADD STUFF HERE! */
-#include <asm/barrier.h>
-#include <asm/cmpxchg.h>
-#include <asm/exec.h>
-#include <asm/switch_to.h>
diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c
index 2aa019368504..2ad747e909fb 100644
--- a/arch/blackfin/kernel/setup.c
+++ b/arch/blackfin/kernel/setup.c
@@ -550,6 +550,7 @@ static __init void memory_setup(void)
 {
 #ifdef CONFIG_MTD_UCLINUX
 	unsigned long mtd_phys = 0;
+	unsigned long n;
 #endif
 	unsigned long max_mem;
 
@@ -593,9 +594,9 @@ static __init void memory_setup(void)
 	mtd_size = PAGE_ALIGN(*((unsigned long *)(mtd_phys + 8)));
 
 # if defined(CONFIG_EXT2_FS) || defined(CONFIG_EXT3_FS)
-	if (*((unsigned short *)(mtd_phys + 0x438)) == EXT2_SUPER_MAGIC)
-		mtd_size =
-		    PAGE_ALIGN(*((unsigned long *)(mtd_phys + 0x404)) << 10);
+	n = ext2_image_size((void *)(mtd_phys + 0x400));
+	if (n)
+		mtd_size = PAGE_ALIGN(n * 1024);
 # endif
 
 # if defined(CONFIG_CRAMFS)
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 3c64b2894c13..1c3ccd416d50 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -11,7 +11,7 @@ config TMS320C6X
 	select HAVE_DMA_API_DEBUG
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_MEMBLOCK
-	select HAVE_SPARSE_IRQ
+	select SPARSE_IRQ
 	select IRQ_DOMAIN
 	select OF
 	select OF_EARLY_FLATTREE
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 13dcf78adf91..3af601e31e66 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -3,7 +3,6 @@ include include/asm-generic/Kbuild.asm
 generic-y += atomic.h
 generic-y += auxvec.h
 generic-y += bitsperlong.h
-generic-y += bug.h
 generic-y += bugs.h
 generic-y += cputime.h
 generic-y += current.h
diff --git a/arch/c6x/include/asm/barrier.h b/arch/c6x/include/asm/barrier.h
new file mode 100644
index 000000000000..538240e85909
--- /dev/null
+++ b/arch/c6x/include/asm/barrier.h
@@ -0,0 +1,27 @@
+/*
+ *  Port on Texas Instruments TMS320C6x architecture
+ *
+ *  Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated
+ *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+#ifndef _ASM_C6X_BARRIER_H
+#define _ASM_C6X_BARRIER_H
+
+#define nop()                    asm("NOP\n");
+
+#define mb()                     barrier()
+#define rmb()                    barrier()
+#define wmb()                    barrier()
+#define set_mb(var, value)       do { var = value;  mb(); } while (0)
+#define set_wmb(var, value)      do { var = value; wmb(); } while (0)
+
+#define smp_mb()	         barrier()
+#define smp_rmb()	         barrier()
+#define smp_wmb()	         barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+
+#endif /* _ASM_C6X_BARRIER_H */
diff --git a/arch/c6x/include/asm/bitops.h b/arch/c6x/include/asm/bitops.h
index 39ab7e874d96..0bec7e5036a8 100644
--- a/arch/c6x/include/asm/bitops.h
+++ b/arch/c6x/include/asm/bitops.h
@@ -15,7 +15,6 @@
 
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 /*
diff --git a/arch/c6x/include/asm/bug.h b/arch/c6x/include/asm/bug.h
new file mode 100644
index 000000000000..8d59933dd6fe
--- /dev/null
+++ b/arch/c6x/include/asm/bug.h
@@ -0,0 +1,23 @@
+/*
+ *  Port on Texas Instruments TMS320C6x architecture
+ *
+ *  Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated
+ *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+#ifndef _ASM_C6X_BUG_H
+#define _ASM_C6X_BUG_H
+
+#include <linux/linkage.h>
+#include <asm-generic/bug.h>
+
+struct pt_regs;
+
+extern void die(char *str, struct pt_regs *fp, int nr);
+extern asmlinkage int process_exception(struct pt_regs *regs);
+extern asmlinkage void enable_exception(void);
+
+#endif /* _ASM_C6X_BUG_H */
diff --git a/arch/c6x/include/asm/cmpxchg.h b/arch/c6x/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..b27c8cefb8c3
--- /dev/null
+++ b/arch/c6x/include/asm/cmpxchg.h
@@ -0,0 +1,68 @@
+/*
+ *  Port on Texas Instruments TMS320C6x architecture
+ *
+ *  Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated
+ *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+#ifndef _ASM_C6X_CMPXCHG_H
+#define _ASM_C6X_CMPXCHG_H
+
+#include <linux/irqflags.h>
+
+/*
+ * Misc. functions
+ */
+static inline unsigned int __xchg(unsigned int x, volatile void *ptr, int size)
+{
+	unsigned int tmp;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	switch (size) {
+	case 1:
+		tmp = 0;
+		tmp = *((unsigned char *) ptr);
+		*((unsigned char *) ptr) = (unsigned char) x;
+		break;
+	case 2:
+		tmp = 0;
+		tmp = *((unsigned short *) ptr);
+		*((unsigned short *) ptr) = x;
+		break;
+	case 4:
+		tmp = 0;
+		tmp = *((unsigned int *) ptr);
+		*((unsigned int *) ptr) = x;
+		break;
+	}
+	local_irq_restore(flags);
+	return tmp;
+}
+
+#define xchg(ptr, x) \
+	((__typeof__(*(ptr)))__xchg((unsigned int)(x), (void *) (ptr), \
+				    sizeof(*(ptr))))
+#define tas(ptr)    xchg((ptr), 1)
+
+
+#include <asm-generic/cmpxchg-local.h>
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)					\
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr),		\
+						     (unsigned long)(o), \
+						     (unsigned long)(n), \
+						     sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#include <asm-generic/cmpxchg.h>
+
+#endif /* _ASM_C6X_CMPXCHG_H */
diff --git a/arch/c6x/include/asm/exec.h b/arch/c6x/include/asm/exec.h
new file mode 100644
index 000000000000..0fea482cdc84
--- /dev/null
+++ b/arch/c6x/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_C6X_EXEC_H
+#define _ASM_C6X_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _ASM_C6X_EXEC_H */
diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h
index 77ecbded1f37..3ff7fab956ba 100644
--- a/arch/c6x/include/asm/processor.h
+++ b/arch/c6x/include/asm/processor.h
@@ -129,4 +129,13 @@ extern unsigned long get_wchan(struct task_struct *p);
 
 extern const struct seq_operations cpuinfo_op;
 
+/* Reset the board */
+#define HARD_RESET_NOW()
+
+extern unsigned int c6x_core_freq;
+
+
+extern void (*c6x_restart)(void);
+extern void (*c6x_halt)(void);
+
 #endif /* ASM_C6X_PROCESSOR_H */
diff --git a/arch/c6x/include/asm/setup.h b/arch/c6x/include/asm/setup.h
index 1808f279f82e..a01e31896fa9 100644
--- a/arch/c6x/include/asm/setup.h
+++ b/arch/c6x/include/asm/setup.h
@@ -27,6 +27,7 @@ extern unsigned int c6x_devstat;
 extern unsigned char c6x_fuse_mac[6];
 
 extern void machine_init(unsigned long dt_ptr);
+extern void time_init(void);
 
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_C6X_SETUP_H */
diff --git a/arch/c6x/include/asm/special_insns.h b/arch/c6x/include/asm/special_insns.h
new file mode 100644
index 000000000000..59672bca841d
--- /dev/null
+++ b/arch/c6x/include/asm/special_insns.h
@@ -0,0 +1,63 @@
+/*
+ *  Port on Texas Instruments TMS320C6x architecture
+ *
+ *  Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated
+ *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+#ifndef _ASM_C6X_SPECIAL_INSNS_H
+#define _ASM_C6X_SPECIAL_INSNS_H
+
+
+#define get_creg(reg) \
+	({ unsigned int __x; \
+	   asm volatile ("mvc .s2 " #reg ",%0\n" : "=b"(__x)); __x; })
+
+#define set_creg(reg, v) \
+	do { unsigned int __x = (unsigned int)(v); \
+		asm volatile ("mvc .s2 %0," #reg "\n" : : "b"(__x)); \
+	} while (0)
+
+#define or_creg(reg, n) \
+	do { unsigned __x, __n = (unsigned)(n);		  \
+		asm volatile ("mvc .s2 " #reg ",%0\n"	  \
+			      "or  .l2 %1,%0,%0\n"	  \
+			      "mvc .s2 %0," #reg "\n"	  \
+			      "nop\n"			  \
+			      : "=&b"(__x) : "b"(__n));	  \
+	} while (0)
+
+#define and_creg(reg, n) \
+	do { unsigned __x, __n = (unsigned)(n);		  \
+		asm volatile ("mvc .s2 " #reg ",%0\n"	  \
+			      "and .l2 %1,%0,%0\n"	  \
+			      "mvc .s2 %0," #reg "\n"	  \
+			      "nop\n"    \
+			      : "=&b"(__x) : "b"(__n));	  \
+	} while (0)
+
+#define get_coreid() (get_creg(DNUM) & 0xff)
+
+/* Set/get IST */
+#define set_ist(x)	set_creg(ISTP, x)
+#define get_ist()       get_creg(ISTP)
+
+/*
+ * Exception management
+ */
+#define disable_exception()
+#define get_except_type()        get_creg(EFR)
+#define ack_exception(type)      set_creg(ECR, 1 << (type))
+#define get_iexcept()            get_creg(IERR)
+#define set_iexcept(mask)        set_creg(IERR, (mask))
+
+#define _extu(x, s, e)							\
+	({      unsigned int __x;					\
+		asm volatile ("extu .S2 %3,%1,%2,%0\n" :		\
+			      "=b"(__x) : "n"(s), "n"(e), "b"(x));	\
+	       __x; })
+
+#endif /* _ASM_C6X_SPECIAL_INSNS_H */
diff --git a/arch/c6x/include/asm/switch_to.h b/arch/c6x/include/asm/switch_to.h
new file mode 100644
index 000000000000..af6c71fe75ec
--- /dev/null
+++ b/arch/c6x/include/asm/switch_to.h
@@ -0,0 +1,33 @@
+/*
+ *  Port on Texas Instruments TMS320C6x architecture
+ *
+ *  Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated
+ *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+#ifndef _ASM_C6X_SWITCH_TO_H
+#define _ASM_C6X_SWITCH_TO_H
+
+#include <linux/linkage.h>
+
+#define prepare_to_switch()    do { } while (0)
+
+struct task_struct;
+struct thread_struct;
+asmlinkage void *__switch_to(struct thread_struct *prev,
+			     struct thread_struct *next,
+			     struct task_struct *tsk);
+
+#define switch_to(prev, next, last)				\
+	do {							\
+		current->thread.wchan = (u_long) __builtin_return_address(0); \
+		(last) = __switch_to(&(prev)->thread,		\
+				     &(next)->thread, (prev));	\
+		mb();						\
+		current->thread.wchan = 0;			\
+	} while (0)
+
+#endif /* _ASM_C6X_SWITCH_TO_H */
diff --git a/arch/c6x/include/asm/system.h b/arch/c6x/include/asm/system.h
deleted file mode 100644
index e076dc0eacc8..000000000000
--- a/arch/c6x/include/asm/system.h
+++ /dev/null
@@ -1,168 +0,0 @@
-/*
- *  Port on Texas Instruments TMS320C6x architecture
- *
- *  Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated
- *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-#ifndef _ASM_C6X_SYSTEM_H
-#define _ASM_C6X_SYSTEM_H
-
-#include <linux/linkage.h>
-#include <linux/irqflags.h>
-
-#define prepare_to_switch()    do { } while (0)
-
-struct task_struct;
-struct thread_struct;
-asmlinkage void *__switch_to(struct thread_struct *prev,
-			     struct thread_struct *next,
-			     struct task_struct *tsk);
-
-#define switch_to(prev, next, last)				\
-	do {							\
-		current->thread.wchan = (u_long) __builtin_return_address(0); \
-		(last) = __switch_to(&(prev)->thread,		\
-				     &(next)->thread, (prev));	\
-		mb();						\
-		current->thread.wchan = 0;			\
-	} while (0)
-
-/* Reset the board */
-#define HARD_RESET_NOW()
-
-#define get_creg(reg) \
-	({ unsigned int __x; \
-	   asm volatile ("mvc .s2 " #reg ",%0\n" : "=b"(__x)); __x; })
-
-#define set_creg(reg, v) \
-	do { unsigned int __x = (unsigned int)(v); \
-		asm volatile ("mvc .s2 %0," #reg "\n" : : "b"(__x)); \
-	} while (0)
-
-#define or_creg(reg, n) \
-	do { unsigned __x, __n = (unsigned)(n);		  \
-		asm volatile ("mvc .s2 " #reg ",%0\n"	  \
-			      "or  .l2 %1,%0,%0\n"	  \
-			      "mvc .s2 %0," #reg "\n"	  \
-			      "nop\n"			  \
-			      : "=&b"(__x) : "b"(__n));	  \
-	} while (0)
-
-#define and_creg(reg, n) \
-	do { unsigned __x, __n = (unsigned)(n);		  \
-		asm volatile ("mvc .s2 " #reg ",%0\n"	  \
-			      "and .l2 %1,%0,%0\n"	  \
-			      "mvc .s2 %0," #reg "\n"	  \
-			      "nop\n"    \
-			      : "=&b"(__x) : "b"(__n));	  \
-	} while (0)
-
-#define get_coreid() (get_creg(DNUM) & 0xff)
-
-/* Set/get IST */
-#define set_ist(x)	set_creg(ISTP, x)
-#define get_ist()       get_creg(ISTP)
-
-/*
- * Exception management
- */
-asmlinkage void enable_exception(void);
-#define disable_exception()
-#define get_except_type()        get_creg(EFR)
-#define ack_exception(type)      set_creg(ECR, 1 << (type))
-#define get_iexcept()            get_creg(IERR)
-#define set_iexcept(mask)        set_creg(IERR, (mask))
-
-/*
- * Misc. functions
- */
-#define nop()                    asm("NOP\n");
-#define mb()                     barrier()
-#define rmb()                    barrier()
-#define wmb()                    barrier()
-#define set_mb(var, value)       do { var = value;  mb(); } while (0)
-#define set_wmb(var, value)      do { var = value; wmb(); } while (0)
-
-#define smp_mb()	         barrier()
-#define smp_rmb()	         barrier()
-#define smp_wmb()	         barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr)))__xchg((unsigned int)(x), (void *) (ptr), \
-				    sizeof(*(ptr))))
-#define tas(ptr)    xchg((ptr), 1)
-
-unsigned int _lmbd(unsigned int, unsigned int);
-unsigned int _bitr(unsigned int);
-
-struct __xchg_dummy { unsigned int a[100]; };
-#define __xg(x) ((volatile struct __xchg_dummy *)(x))
-
-static inline unsigned int __xchg(unsigned int x, volatile void *ptr, int size)
-{
-	unsigned int tmp;
-	unsigned long flags;
-
-	local_irq_save(flags);
-
-	switch (size) {
-	case 1:
-		tmp = 0;
-		tmp = *((unsigned char *) ptr);
-		*((unsigned char *) ptr) = (unsigned char) x;
-		break;
-	case 2:
-		tmp = 0;
-		tmp = *((unsigned short *) ptr);
-		*((unsigned short *) ptr) = x;
-		break;
-	case 4:
-		tmp = 0;
-		tmp = *((unsigned int *) ptr);
-		*((unsigned int *) ptr) = x;
-		break;
-	}
-	local_irq_restore(flags);
-	return tmp;
-}
-
-#include <asm-generic/cmpxchg-local.h>
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr),		\
-						     (unsigned long)(o), \
-						     (unsigned long)(n), \
-						     sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#include <asm-generic/cmpxchg.h>
-
-#define _extu(x, s, e)							\
-	({      unsigned int __x;					\
-		asm volatile ("extu .S2 %3,%1,%2,%0\n" :		\
-			      "=b"(__x) : "n"(s), "n"(e), "b"(x));	\
-	       __x; })
-
-
-extern unsigned int c6x_core_freq;
-
-struct pt_regs;
-
-extern void die(char *str, struct pt_regs *fp, int nr);
-extern asmlinkage int process_exception(struct pt_regs *regs);
-extern void time_init(void);
-extern void free_initmem(void);
-
-extern void (*c6x_restart)(void);
-extern void (*c6x_halt)(void);
-
-#endif /* _ASM_C6X_SYSTEM_H */
diff --git a/arch/c6x/kernel/irq.c b/arch/c6x/kernel/irq.c
index d77bcfdf0d8e..65b8ddf54b44 100644
--- a/arch/c6x/kernel/irq.c
+++ b/arch/c6x/kernel/irq.c
@@ -27,6 +27,7 @@
 #include <linux/kernel_stat.h>
 
 #include <asm/megamod-pic.h>
+#include <asm/special_insns.h>
 
 unsigned long irq_err_count;
 
diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c
index 0c07921747f4..ce46186600c5 100644
--- a/arch/c6x/kernel/setup.c
+++ b/arch/c6x/kernel/setup.c
@@ -34,6 +34,7 @@
 #include <asm/dscr.h>
 #include <asm/clock.h>
 #include <asm/soc.h>
+#include <asm/special_insns.h>
 
 static const char *c6x_soc_name;
 
diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c
index 304f675826e9..3b5a05099989 100644
--- a/arch/c6x/kernel/signal.c
+++ b/arch/c6x/kernel/signal.c
@@ -85,10 +85,7 @@ asmlinkage int do_rt_sigreturn(struct pt_regs *regs)
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
 		goto badframe;
@@ -279,15 +276,8 @@ static int handle_signal(int sig,
 
 	/* Set up the stack frame */
 	ret = setup_rt_frame(sig, ka, info, oldset, regs);
-	if (ret == 0) {
-		spin_lock_irq(&current->sighand->siglock);
-		sigorsets(&current->blocked, &current->blocked,
-			  &ka->sa.sa_mask);
-		if (!(ka->sa.sa_flags & SA_NODEFER))
-			sigaddset(&current->blocked, sig);
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-	}
+	if (ret == 0)
+		block_sigmask(ka, sig);
 
 	return ret;
 }
diff --git a/arch/c6x/kernel/soc.c b/arch/c6x/kernel/soc.c
index dd45bc39af0e..0748c94ebef6 100644
--- a/arch/c6x/kernel/soc.c
+++ b/arch/c6x/kernel/soc.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/etherdevice.h>
-#include <asm/system.h>
 #include <asm/setup.h>
 #include <asm/soc.h>
 
diff --git a/arch/c6x/kernel/time.c b/arch/c6x/kernel/time.c
index 4c9f136165f7..356ee84cad95 100644
--- a/arch/c6x/kernel/time.c
+++ b/arch/c6x/kernel/time.c
@@ -20,6 +20,7 @@
 #include <linux/timex.h>
 #include <linux/profile.h>
 
+#include <asm/special_insns.h>
 #include <asm/timer64.h>
 
 static u32 sched_clock_multiplier;
diff --git a/arch/c6x/kernel/traps.c b/arch/c6x/kernel/traps.c
index f50e3edd6dad..1be74e5b4788 100644
--- a/arch/c6x/kernel/traps.c
+++ b/arch/c6x/kernel/traps.c
@@ -14,6 +14,7 @@
 #include <linux/bug.h>
 
 #include <asm/soc.h>
+#include <asm/special_insns.h>
 #include <asm/traps.h>
 
 int (*c6x_nmi_handler)(struct pt_regs *regs);
diff --git a/arch/c6x/platforms/timer64.c b/arch/c6x/platforms/timer64.c
index 03c03c249191..3c73d74a4674 100644
--- a/arch/c6x/platforms/timer64.c
+++ b/arch/c6x/platforms/timer64.c
@@ -15,6 +15,7 @@
 #include <linux/of_address.h>
 #include <asm/soc.h>
 #include <asm/dscr.h>
+#include <asm/special_insns.h>
 #include <asm/timer64.h>
 
 struct timer_regs {
diff --git a/arch/cris/arch-v10/drivers/ds1302.c b/arch/cris/arch-v10/drivers/ds1302.c
index 3d655dcc65da..74f99c688c8d 100644
--- a/arch/cris/arch-v10/drivers/ds1302.c
+++ b/arch/cris/arch-v10/drivers/ds1302.c
@@ -24,7 +24,6 @@
 #include <linux/capability.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <arch/svinto.h>
 #include <asm/io.h>
 #include <asm/rtc.h>
diff --git a/arch/cris/arch-v10/drivers/gpio.c b/arch/cris/arch-v10/drivers/gpio.c
index a276f0811731..609d5510410e 100644
--- a/arch/cris/arch-v10/drivers/gpio.c
+++ b/arch/cris/arch-v10/drivers/gpio.c
@@ -24,7 +24,6 @@
 #include <asm/etraxgpio.h>
 #include <arch/svinto.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <arch/io_interface_mux.h>
 
diff --git a/arch/cris/arch-v10/drivers/i2c.c b/arch/cris/arch-v10/drivers/i2c.c
index c413539d4205..b3d1f9ed1b98 100644
--- a/arch/cris/arch-v10/drivers/i2c.c
+++ b/arch/cris/arch-v10/drivers/i2c.c
@@ -22,7 +22,6 @@
 
 #include <asm/etraxi2c.h>
 
-#include <asm/system.h>
 #include <arch/svinto.h>
 #include <asm/io.h>
 #include <asm/delay.h>
diff --git a/arch/cris/arch-v10/drivers/pcf8563.c b/arch/cris/arch-v10/drivers/pcf8563.c
index 1391b731ad1c..9da056860c92 100644
--- a/arch/cris/arch-v10/drivers/pcf8563.c
+++ b/arch/cris/arch-v10/drivers/pcf8563.c
@@ -29,7 +29,6 @@
 #include <linux/mutex.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/rtc.h>
 
diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c
index 466af40c5822..c4b71710fb0e 100644
--- a/arch/cris/arch-v10/drivers/sync_serial.c
+++ b/arch/cris/arch-v10/drivers/sync_serial.c
@@ -27,7 +27,6 @@
 #include <asm/io.h>
 #include <arch/svinto.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/sync_serial.h>
 #include <arch/io_interface_mux.h>
 
diff --git a/arch/cris/arch-v10/kernel/debugport.c b/arch/cris/arch-v10/kernel/debugport.c
index 99851ba8e5fa..f932c85fbde4 100644
--- a/arch/cris/arch-v10/kernel/debugport.c
+++ b/arch/cris/arch-v10/kernel/debugport.c
@@ -18,7 +18,6 @@
 #include <linux/major.h>
 #include <linux/delay.h>
 #include <linux/tty.h>
-#include <asm/system.h>
 #include <arch/svinto.h>
 #include <asm/io.h>             /* Get SIMCOUT. */
 
diff --git a/arch/cris/arch-v10/kernel/dma.c b/arch/cris/arch-v10/kernel/dma.c
index d31504b4a19e..5795047359b2 100644
--- a/arch/cris/arch-v10/kernel/dma.c
+++ b/arch/cris/arch-v10/kernel/dma.c
@@ -8,6 +8,7 @@
 
 #include <asm/dma.h>
 #include <arch/svinto.h>
+#include <arch/system.h>
 
 /* Macro to access ETRAX 100 registers */
 #define SETS(var, reg, field, val) var = (var & ~IO_MASK_(reg##_, field##_)) | \
diff --git a/arch/cris/arch-v10/kernel/io_interface_mux.c b/arch/cris/arch-v10/kernel/io_interface_mux.c
index 29f97e962795..ad64cd1c861a 100644
--- a/arch/cris/arch-v10/kernel/io_interface_mux.c
+++ b/arch/cris/arch-v10/kernel/io_interface_mux.c
@@ -14,6 +14,7 @@
 #include <arch/svinto.h>
 #include <asm/io.h>
 #include <arch/io_interface_mux.h>
+#include <arch/system.h>
 
 
 #define DBG(s)
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index 9a57db6907f5..bee8df43c201 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -16,6 +16,7 @@
 #include <linux/fs.h>
 #include <arch/svinto.h>
 #include <linux/init.h>
+#include <arch/system.h>
 
 #ifdef CONFIG_ETRAX_GPIO
 void etrax_gpio_wake_up_check(void); /* drivers/gpio.c */
diff --git a/arch/cris/arch-v10/kernel/ptrace.c b/arch/cris/arch-v10/kernel/ptrace.c
index 320065f3cbe5..bfddfb99401f 100644
--- a/arch/cris/arch-v10/kernel/ptrace.c
+++ b/arch/cris/arch-v10/kernel/ptrace.c
@@ -15,7 +15,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 
 /* 
diff --git a/arch/cris/arch-v10/kernel/setup.c b/arch/cris/arch-v10/kernel/setup.c
index de27b50b72a2..4f96d71b5154 100644
--- a/arch/cris/arch-v10/kernel/setup.c
+++ b/arch/cris/arch-v10/kernel/setup.c
@@ -14,6 +14,7 @@
 #include <linux/proc_fs.h>
 #include <linux/delay.h>
 #include <linux/param.h>
+#include <arch/system.h>
 
 #ifdef CONFIG_PROC_FS
 #define HAS_FPU		0x0001
diff --git a/arch/cris/arch-v10/kernel/signal.c b/arch/cris/arch-v10/kernel/signal.c
index e78fe49a9849..289c584ba499 100644
--- a/arch/cris/arch-v10/kernel/signal.c
+++ b/arch/cris/arch-v10/kernel/signal.c
@@ -27,6 +27,7 @@
 #include <asm/processor.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
+#include <arch/system.h>
 
 #define DEBUG_SIG 0
 
diff --git a/arch/cris/arch-v10/kernel/traps.c b/arch/cris/arch-v10/kernel/traps.c
index 8bebb96bbca1..7001beda716c 100644
--- a/arch/cris/arch-v10/kernel/traps.c
+++ b/arch/cris/arch-v10/kernel/traps.c
@@ -11,6 +11,7 @@
 #include <linux/ptrace.h>
 #include <asm/uaccess.h>
 #include <arch/sv_addr_ag.h>
+#include <arch/system.h>
 
 void
 show_registers(struct pt_regs *regs)
diff --git a/arch/cris/arch-v32/drivers/i2c.c b/arch/cris/arch-v32/drivers/i2c.c
index ddb23996f11a..3b2c82ce8147 100644
--- a/arch/cris/arch-v32/drivers/i2c.c
+++ b/arch/cris/arch-v32/drivers/i2c.c
@@ -36,7 +36,6 @@
 
 #include <asm/etraxi2c.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/delay.h>
 
diff --git a/arch/cris/arch-v32/drivers/mach-a3/gpio.c b/arch/cris/arch-v32/drivers/mach-a3/gpio.c
index c845831e2225..0b86deedacb9 100644
--- a/arch/cris/arch-v32/drivers/mach-a3/gpio.c
+++ b/arch/cris/arch-v32/drivers/mach-a3/gpio.c
@@ -31,7 +31,6 @@
 #include <hwregs/gio_defs.h>
 #include <hwregs/intr_vect_defs.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/pinmux.h>
 
diff --git a/arch/cris/arch-v32/drivers/mach-fs/gpio.c b/arch/cris/arch-v32/drivers/mach-fs/gpio.c
index ee90d2659be7..a2ac0917f1a6 100644
--- a/arch/cris/arch-v32/drivers/mach-fs/gpio.c
+++ b/arch/cris/arch-v32/drivers/mach-fs/gpio.c
@@ -30,7 +30,6 @@
 #include <hwregs/gio_defs.h>
 #include <hwregs/intr_vect_defs.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 
 #ifdef CONFIG_ETRAX_VIRTUAL_GPIO
diff --git a/arch/cris/arch-v32/kernel/debugport.c b/arch/cris/arch-v32/kernel/debugport.c
index 794b364d9f7d..610909b003f6 100644
--- a/arch/cris/arch-v32/kernel/debugport.c
+++ b/arch/cris/arch-v32/kernel/debugport.c
@@ -4,7 +4,6 @@
 
 #include <linux/console.h>
 #include <linux/init.h>
-#include <asm/system.h>
 #include <hwregs/reg_rdwr.h>
 #include <hwregs/reg_map.h>
 #include <hwregs/ser_defs.h>
diff --git a/arch/cris/arch-v32/kernel/fasttimer.c b/arch/cris/arch-v32/kernel/fasttimer.c
index 111caa1a2efb..ab1551ee43c5 100644
--- a/arch/cris/arch-v32/kernel/fasttimer.c
+++ b/arch/cris/arch-v32/kernel/fasttimer.c
@@ -17,7 +17,6 @@
 #include <linux/delay.h>
 
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include <hwregs/reg_map.h>
 #include <hwregs/reg_rdwr.h>
diff --git a/arch/cris/arch-v32/kernel/ptrace.c b/arch/cris/arch-v32/kernel/ptrace.c
index 511ece94a574..f7ad9e8637df 100644
--- a/arch/cris/arch-v32/kernel/ptrace.c
+++ b/arch/cris/arch-v32/kernel/ptrace.c
@@ -15,7 +15,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <arch/hwregs/supp_reg.h>
 
diff --git a/arch/cris/arch-v32/mach-a3/dma.c b/arch/cris/arch-v32/mach-a3/dma.c
index f35e4f65f4ef..47c64bf40eae 100644
--- a/arch/cris/arch-v32/mach-a3/dma.c
+++ b/arch/cris/arch-v32/mach-a3/dma.c
@@ -9,7 +9,6 @@
 #include <hwregs/clkgen_defs.h>
 #include <hwregs/strmux_defs.h>
 #include <linux/errno.h>
-#include <asm/system.h>
 #include <arbiter.h>
 
 static char used_dma_channels[MAX_DMA_CHANNELS];
diff --git a/arch/cris/arch-v32/mach-fs/dma.c b/arch/cris/arch-v32/mach-fs/dma.c
index 2d970d7505c9..fc6416a671ea 100644
--- a/arch/cris/arch-v32/mach-fs/dma.c
+++ b/arch/cris/arch-v32/mach-fs/dma.c
@@ -9,7 +9,6 @@
 #include <hwregs/config_defs.h>
 #include <hwregs/strmux_defs.h>
 #include <linux/errno.h>
-#include <asm/system.h>
 #include <mach/arbiter.h>
 
 static char used_dma_channels[MAX_DMA_CHANNELS];
diff --git a/arch/cris/include/arch-v10/arch/elf.h b/arch/cris/include/arch-v10/arch/elf.h
index 1c38ee728b17..1eb638aeddb4 100644
--- a/arch/cris/include/arch-v10/arch/elf.h
+++ b/arch/cris/include/arch-v10/arch/elf.h
@@ -1,6 +1,8 @@
 #ifndef __ASMCRIS_ARCH_ELF_H
 #define __ASMCRIS_ARCH_ELF_H
 
+#include <arch/system.h>
+
 #define ELF_MACH EF_CRIS_VARIANT_ANY_V0_V10
 
 /*
diff --git a/arch/cris/include/arch-v32/arch/elf.h b/arch/cris/include/arch-v32/arch/elf.h
index 1324e505a4d8..c46d58291166 100644
--- a/arch/cris/include/arch-v32/arch/elf.h
+++ b/arch/cris/include/arch-v32/arch/elf.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_CRIS_ELF_H
 #define _ASM_CRIS_ELF_H
 
+#include <arch/system.h>
+
 #define ELF_CORE_EFLAGS EF_CRIS_VARIANT_V32
 
 /*
diff --git a/arch/cris/include/arch-v32/arch/system.h b/arch/cris/include/arch-v32/arch/system.h
index 76cea99eaa60..db853fb3a458 100644
--- a/arch/cris/include/arch-v32/arch/system.h
+++ b/arch/cris/include/arch-v32/arch/system.h
@@ -34,14 +34,4 @@ static inline unsigned long rdsp(void)
 /* Write the user-mode stack pointer. */
 #define wrusp(usp) __asm__ __volatile__ ("move %0, $usp" : : "rm" (usp))
 
-#define nop() __asm__ __volatile__ ("nop");
-
-#define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long) (x),(ptr),sizeof(*(ptr))))
-
-#define tas(ptr) (xchg((ptr),1))
-
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((struct __xchg_dummy *)(x))
-
 #endif /* _ASM_CRIS_ARCH_SYSTEM_H */
diff --git a/arch/cris/include/asm/atomic.h b/arch/cris/include/asm/atomic.h
index bbf093814db2..1056a5dfe04f 100644
--- a/arch/cris/include/asm/atomic.h
+++ b/arch/cris/include/asm/atomic.h
@@ -5,7 +5,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 #include <arch/atomic.h>
 
 /*
diff --git a/arch/cris/include/asm/barrier.h b/arch/cris/include/asm/barrier.h
new file mode 100644
index 000000000000..198ad7fa6b25
--- /dev/null
+++ b/arch/cris/include/asm/barrier.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_CRIS_BARRIER_H
+#define __ASM_CRIS_BARRIER_H
+
+#define nop() __asm__ __volatile__ ("nop");
+
+#define barrier() __asm__ __volatile__("": : :"memory")
+#define mb() barrier()
+#define rmb() mb()
+#define wmb() mb()
+#define read_barrier_depends() do { } while(0)
+#define set_mb(var, value)  do { var = value; mb(); } while (0)
+
+#ifdef CONFIG_SMP
+#define smp_mb()        mb()
+#define smp_rmb()       rmb()
+#define smp_wmb()       wmb()
+#define smp_read_barrier_depends()     read_barrier_depends()
+#else
+#define smp_mb()        barrier()
+#define smp_rmb()       barrier()
+#define smp_wmb()       barrier()
+#define smp_read_barrier_depends()     do { } while(0)
+#endif
+
+#endif /* __ASM_CRIS_BARRIER_H */
diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h
index a78a2d70cd8b..184066ceb1f6 100644
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -19,7 +19,6 @@
 #endif
 
 #include <arch/bitops.h>
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <linux/compiler.h>
 
diff --git a/arch/cris/include/asm/system.h b/arch/cris/include/asm/cmpxchg.h
index ea10592f7d75..b756dac8aa3f 100644
--- a/arch/cris/include/asm/system.h
+++ b/arch/cris/include/asm/cmpxchg.h
@@ -1,44 +1,7 @@
-#ifndef __ASM_CRIS_SYSTEM_H
-#define __ASM_CRIS_SYSTEM_H
+#ifndef __ASM_CRIS_CMPXCHG__
+#define __ASM_CRIS_CMPXCHG__
 
 #include <linux/irqflags.h>
-#include <arch/system.h>
-
-/* the switch_to macro calls resume, an asm function in entry.S which does the actual
- * task switching.
- */
-
-extern struct task_struct *resume(struct task_struct *prev, struct task_struct *next, int);
-#define switch_to(prev,next,last) last = resume(prev,next, \
-					 (int)&((struct task_struct *)0)->thread)
-
-#define barrier() __asm__ __volatile__("": : :"memory")
-#define mb() barrier()
-#define rmb() mb()
-#define wmb() mb()
-#define read_barrier_depends() do { } while(0)
-#define set_mb(var, value)  do { var = value; mb(); } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()        mb()
-#define smp_rmb()       rmb()
-#define smp_wmb()       wmb()
-#define smp_read_barrier_depends()     read_barrier_depends()
-#else
-#define smp_mb()        barrier()
-#define smp_rmb()       barrier()
-#define smp_wmb()       barrier()
-#define smp_read_barrier_depends()     do { } while(0)
-#endif
-
-#define iret()
-
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-void disable_hlt(void);
-void enable_hlt(void);
 
 static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
 {
@@ -67,6 +30,11 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
   return x;
 }
 
+#define xchg(ptr,x) \
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+#define tas(ptr) (xchg((ptr),1))
+
 #include <asm-generic/cmpxchg-local.h>
 
 /*
@@ -82,8 +50,4 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 #include <asm-generic/cmpxchg.h>
 #endif
 
-#define arch_align_stack(x) (x)
-
-void default_idle(void);
-
-#endif
+#endif /* __ASM_CRIS_CMPXCHG__ */
diff --git a/arch/cris/include/asm/exec.h b/arch/cris/include/asm/exec.h
new file mode 100644
index 000000000000..9665dab7e25b
--- /dev/null
+++ b/arch/cris/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_CRIS_EXEC_H
+#define __ASM_CRIS_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __ASM_CRIS_EXEC_H */
diff --git a/arch/cris/include/asm/posix_types.h b/arch/cris/include/asm/posix_types.h
index ce3fb25a460b..72b3cd6eda0b 100644
--- a/arch/cris/include/asm/posix_types.h
+++ b/arch/cris/include/asm/posix_types.h
@@ -12,55 +12,25 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short  __kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
+#define __kernel_uid_t __kernel_uid_t
+
 typedef __SIZE_TYPE__	__kernel_size_t;
 typedef long		__kernel_ssize_t;
 typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long            __kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short  __kernel_uid16_t;
-typedef unsigned short  __kernel_gid16_t;
-typedef unsigned int    __kernel_uid32_t;
-typedef unsigned int    __kernel_gid32_t;
+#define __kernel_size_t __kernel_size_t
 
-typedef unsigned short  __kernel_old_uid_t;
-typedef unsigned short  __kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifdef __KERNEL__
-
-#undef	__FD_SET
-#define __FD_SET(fd,fdsetp) set_bit(fd, (void *)(fdsetp))
-
-#undef	__FD_CLR
-#define __FD_CLR(fd,fdsetp) clear_bit(fd, (void *)(fdsetp))
-
-#undef	__FD_ISSET
-#define __FD_ISSET(fd,fdsetp) test_bit(fd, (void *)(fdsetp))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) memset((void *)(fdsetp), 0, __FDSET_LONGS << 2)
-
-#endif /* __KERNEL__ */
+#define __kernel_old_dev_t __kernel_old_dev_t
 
 #endif /* __ARCH_CRIS_POSIX_TYPES_H */
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 3f7248f7a1c9..4210d72a6667 100644
--- a/arch/cris/include/asm/processor.h
+++ b/arch/cris/include/asm/processor.h
@@ -10,10 +10,10 @@
 #ifndef __ASM_CRIS_PROCESSOR_H
 #define __ASM_CRIS_PROCESSOR_H
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include <arch/processor.h>
+#include <arch/system.h>
 
 struct task_struct;
 
@@ -72,4 +72,13 @@ static inline void release_thread(struct task_struct *dead_task)
 
 #define cpu_relax()     barrier()
 
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+void disable_hlt(void);
+void enable_hlt(void);
+
+void default_idle(void);
+
 #endif /* __ASM_CRIS_PROCESSOR_H */
diff --git a/arch/cris/include/asm/switch_to.h b/arch/cris/include/asm/switch_to.h
new file mode 100644
index 000000000000..d842e1163ba1
--- /dev/null
+++ b/arch/cris/include/asm/switch_to.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_CRIS_SWITCH_TO_H
+#define __ASM_CRIS_SWITCH_TO_H
+
+/* the switch_to macro calls resume, an asm function in entry.S which does the actual
+ * task switching.
+ */
+
+extern struct task_struct *resume(struct task_struct *prev, struct task_struct *next, int);
+#define switch_to(prev,next,last) last = resume(prev,next, \
+					 (int)&((struct task_struct *)0)->thread)
+
+#endif /* __ASM_CRIS_SWITCH_TO_H */
diff --git a/arch/cris/kernel/irq.c b/arch/cris/kernel/irq.c
index 788eb2248916..d36836dbbc07 100644
--- a/arch/cris/kernel/irq.c
+++ b/arch/cris/kernel/irq.c
@@ -36,6 +36,7 @@
 #include <linux/spinlock.h>
 
 #include <asm/io.h>
+#include <arch/system.h>
 
 /* called by the assembler IRQ entry functions defined in irq.h
  * to dispatch the interrupts to registered handlers
diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c
index d8f50ff6fadd..891dad85e8bd 100644
--- a/arch/cris/kernel/process.c
+++ b/arch/cris/kernel/process.c
@@ -16,7 +16,6 @@
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/init_task.h>
diff --git a/arch/cris/kernel/ptrace.c b/arch/cris/kernel/ptrace.c
index 48b0f3912632..d114ad3da9b1 100644
--- a/arch/cris/kernel/ptrace.c
+++ b/arch/cris/kernel/ptrace.c
@@ -21,7 +21,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 
 
diff --git a/arch/cris/kernel/setup.c b/arch/cris/kernel/setup.c
index b712f4934c4b..32c3d248868e 100644
--- a/arch/cris/kernel/setup.c
+++ b/arch/cris/kernel/setup.c
@@ -20,6 +20,7 @@
 #include <linux/pfn.h>
 #include <linux/cpu.h>
 #include <asm/setup.h>
+#include <arch/system.h>
 
 /*
  * Setup options
diff --git a/arch/cris/kernel/traps.c b/arch/cris/kernel/traps.c
index 8da53f34c7a7..a11ad3229f8c 100644
--- a/arch/cris/kernel/traps.c
+++ b/arch/cris/kernel/traps.c
@@ -17,6 +17,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
+#include <arch/system.h>
 
 extern void arch_enable_nmi(void);
 extern void stop_watchdog(void);
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 9dcac8ec8fa0..b4760d86e1bb 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/wait.h>
 #include <asm/uaccess.h>
+#include <arch/system.h>
 
 extern int find_fixup_code(struct pt_regs *);
 extern void die_if_kernel(const char *, struct pt_regs *, long);
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 0d8a7d661740..b86329d0e316 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -16,7 +16,7 @@
 
 #include <linux/types.h>
 #include <asm/spr-regs.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 #ifdef CONFIG_SMP
 #error not SMP safe
@@ -181,61 +181,6 @@ static inline void atomic64_dec(atomic64_t *v)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_and_test(v)	(atomic64_inc_return((v)) == 0)
 
-/*****************************************************************************/
-/*
- * exchange value with memory
- */
-extern uint64_t __xchg_64(uint64_t i, volatile void *v);
-
-#ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
-
-#define xchg(ptr, x)								\
-({										\
-	__typeof__(ptr) __xg_ptr = (ptr);					\
-	__typeof__(*(ptr)) __xg_orig;						\
-										\
-	switch (sizeof(__xg_orig)) {						\
-	case 4:									\
-		asm volatile(							\
-			"swap%I0 %M0,%1"					\
-			: "+m"(*__xg_ptr), "=r"(__xg_orig)			\
-			: "1"(x)						\
-			: "memory"						\
-			);							\
-		break;								\
-										\
-	default:								\
-		__xg_orig = (__typeof__(__xg_orig))0;				\
-		asm volatile("break");						\
-		break;								\
-	}									\
-										\
-	__xg_orig;								\
-})
-
-#else
-
-extern uint32_t __xchg_32(uint32_t i, volatile void *v);
-
-#define xchg(ptr, x)										\
-({												\
-	__typeof__(ptr) __xg_ptr = (ptr);							\
-	__typeof__(*(ptr)) __xg_orig;								\
-												\
-	switch (sizeof(__xg_orig)) {								\
-	case 4: __xg_orig = (__typeof__(*(ptr))) __xchg_32((uint32_t) x, __xg_ptr);	break;	\
-	default:										\
-		__xg_orig = (__typeof__(__xg_orig))0;									\
-		asm volatile("break");								\
-		break;										\
-	}											\
-	__xg_orig;										\
-})
-
-#endif
-
-#define tas(ptr) (xchg((ptr), 1))
-
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&(v)->counter, old, new))
 #define atomic_xchg(v, new)		(xchg(&(v)->counter, new))
 #define atomic64_cmpxchg(v, old, new)	(__cmpxchg_64(old, new, &(v)->counter))
diff --git a/arch/frv/include/asm/barrier.h b/arch/frv/include/asm/barrier.h
new file mode 100644
index 000000000000..06776ad9f5e9
--- /dev/null
+++ b/arch/frv/include/asm/barrier.h
@@ -0,0 +1,29 @@
+/* FR-V CPU memory barrier definitions
+ *
+ * Copyright (C) 2003 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_BARRIER_H
+#define _ASM_BARRIER_H
+
+#define nop()			asm volatile ("nop"::)
+
+#define mb()			asm volatile ("membar" : : :"memory")
+#define rmb()			asm volatile ("membar" : : :"memory")
+#define wmb()			asm volatile ("membar" : : :"memory")
+#define read_barrier_depends()	do { } while (0)
+
+#define smp_mb()			barrier()
+#define smp_rmb()			barrier()
+#define smp_wmb()			barrier()
+#define smp_read_barrier_depends()	do {} while(0)
+#define set_mb(var, value) \
+	do { var = (value); barrier(); } while (0)
+
+#endif /* _ASM_BARRIER_H */
diff --git a/arch/frv/include/asm/bug.h b/arch/frv/include/asm/bug.h
index 2e054508a2f6..dd01bcf42ee6 100644
--- a/arch/frv/include/asm/bug.h
+++ b/arch/frv/include/asm/bug.h
@@ -51,4 +51,6 @@ do {						\
 
 #include <asm-generic/bug.h>
 
+extern void die_if_kernel(const char *, ...) __attribute__((format(printf, 1, 2)));
+
 #endif
diff --git a/arch/frv/include/asm/system.h b/arch/frv/include/asm/cmpxchg.h
index 6c10fd2c626d..5b04dd0aecab 100644
--- a/arch/frv/include/asm/system.h
+++ b/arch/frv/include/asm/cmpxchg.h
@@ -1,6 +1,9 @@
-/* system.h: FR-V CPU control definitions
+/* xchg and cmpxchg operation emulation for FR-V
  *
- * Copyright (C) 2003 Red Hat, Inc. All Rights Reserved.
+ * For an explanation of how atomic ops work in this arch, see:
+ *   Documentation/frv/atomic-ops.txt
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -8,54 +11,65 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
-
-#ifndef _ASM_SYSTEM_H
-#define _ASM_SYSTEM_H
+#ifndef _ASM_CMPXCHG_H
+#define _ASM_CMPXCHG_H
 
 #include <linux/types.h>
-#include <linux/linkage.h>
-#include <linux/kernel.h>
-
-struct thread_struct;
 
+/*****************************************************************************/
 /*
- * switch_to(prev, next) should switch from task `prev' to `next'
- * `prev' will never be the same as `next'.
- * The `mb' is to tell GCC not to cache `current' across this call.
+ * exchange value with memory
  */
-extern asmlinkage
-struct task_struct *__switch_to(struct thread_struct *prev_thread,
-				struct thread_struct *next_thread,
-				struct task_struct *prev);
-
-#define switch_to(prev, next, last)					\
-do {									\
-	(prev)->thread.sched_lr =					\
-		(unsigned long) __builtin_return_address(0);		\
-	(last) = __switch_to(&(prev)->thread, &(next)->thread, (prev));	\
-	mb();								\
-} while(0)
+extern uint64_t __xchg_64(uint64_t i, volatile void *v);
 
-/*
- * Force strict CPU ordering.
- */
-#define nop()			asm volatile ("nop"::)
-#define mb()			asm volatile ("membar" : : :"memory")
-#define rmb()			asm volatile ("membar" : : :"memory")
-#define wmb()			asm volatile ("membar" : : :"memory")
-#define read_barrier_depends()	do { } while (0)
+#ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
+
+#define xchg(ptr, x)								\
+({										\
+	__typeof__(ptr) __xg_ptr = (ptr);					\
+	__typeof__(*(ptr)) __xg_orig;						\
+										\
+	switch (sizeof(__xg_orig)) {						\
+	case 4:									\
+		asm volatile(							\
+			"swap%I0 %M0,%1"					\
+			: "+m"(*__xg_ptr), "=r"(__xg_orig)			\
+			: "1"(x)						\
+			: "memory"						\
+			);							\
+		break;								\
+										\
+	default:								\
+		__xg_orig = (__typeof__(__xg_orig))0;				\
+		asm volatile("break");						\
+		break;								\
+	}									\
+										\
+	__xg_orig;								\
+})
 
-#define smp_mb()			barrier()
-#define smp_rmb()			barrier()
-#define smp_wmb()			barrier()
-#define smp_read_barrier_depends()	do {} while(0)
-#define set_mb(var, value) \
-	do { var = (value); barrier(); } while (0)
+#else
 
-extern void die_if_kernel(const char *, ...) __attribute__((format(printf, 1, 2)));
-extern void free_initmem(void);
+extern uint32_t __xchg_32(uint32_t i, volatile void *v);
+
+#define xchg(ptr, x)										\
+({												\
+	__typeof__(ptr) __xg_ptr = (ptr);							\
+	__typeof__(*(ptr)) __xg_orig;								\
+												\
+	switch (sizeof(__xg_orig)) {								\
+	case 4: __xg_orig = (__typeof__(*(ptr))) __xchg_32((uint32_t) x, __xg_ptr);	break;	\
+	default:										\
+		__xg_orig = (__typeof__(__xg_orig))0;									\
+		asm volatile("break");								\
+		break;										\
+	}											\
+	__xg_orig;										\
+})
+
+#endif
 
-#define arch_align_stack(x) (x)
+#define tas(ptr) (xchg((ptr), 1))
 
 /*****************************************************************************/
 /*
@@ -155,4 +169,4 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 			(unsigned long)(n), sizeof(*(ptr))))
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
 
-#endif /* _ASM_SYSTEM_H */
+#endif /* _ASM_CMPXCHG_H */
diff --git a/arch/frv/include/asm/exec.h b/arch/frv/include/asm/exec.h
new file mode 100644
index 000000000000..65c91305d4a7
--- /dev/null
+++ b/arch/frv/include/asm/exec.h
@@ -0,0 +1,17 @@
+/* FR-V CPU executable handling
+ *
+ * Copyright (C) 2003 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_EXEC_H
+#define _ASM_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _ASM_EXEC_H */
diff --git a/arch/frv/include/asm/posix_types.h b/arch/frv/include/asm/posix_types.h
index a9f1f5be0632..3f34cb45fbb3 100644
--- a/arch/frv/include/asm/posix_types.h
+++ b/arch/frv/include/asm/posix_types.h
@@ -7,56 +7,23 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
-typedef unsigned short	__kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
+#define __kernel_uid_t __kernel_uid_t
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-
-#undef	__FD_CLR
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-
-#undef	__FD_ISSET
-#define	__FD_ISSET(d, set)	(!!((set)->fds_bits[__FDELT(d)] & __FDMASK(d)))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) (memset (fdsetp, 0, sizeof(*(fd_set *)fdsetp)))
+typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif
 
diff --git a/arch/frv/include/asm/switch_to.h b/arch/frv/include/asm/switch_to.h
new file mode 100644
index 000000000000..2cf0f6a7fbb1
--- /dev/null
+++ b/arch/frv/include/asm/switch_to.h
@@ -0,0 +1,35 @@
+/* FR-V CPU basic task switching
+ *
+ * Copyright (C) 2003 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_SWITCH_TO_H
+#define _ASM_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+
+/*
+ * switch_to(prev, next) should switch from task `prev' to `next'
+ * `prev' will never be the same as `next'.
+ * The `mb' is to tell GCC not to cache `current' across this call.
+ */
+extern asmlinkage
+struct task_struct *__switch_to(struct thread_struct *prev_thread,
+				struct thread_struct *next_thread,
+				struct task_struct *prev);
+
+#define switch_to(prev, next, last)					\
+do {									\
+	(prev)->thread.sched_lr =					\
+		(unsigned long) __builtin_return_address(0);		\
+	(last) = __switch_to(&(prev)->thread, &(next)->thread, (prev));	\
+	mb();								\
+} while(0)
+
+#endif /* _ASM_SWITCH_TO_H */
diff --git a/arch/frv/kernel/debug-stub.c b/arch/frv/kernel/debug-stub.c
index 2845139c8077..a0228f717ef2 100644
--- a/arch/frv/kernel/debug-stub.c
+++ b/arch/frv/kernel/debug-stub.c
@@ -17,7 +17,6 @@
 #include <linux/serial_reg.h>
 #include <linux/start_kernel.h>
 
-#include <asm/system.h>
 #include <asm/serial-regs.h>
 #include <asm/timer-regs.h>
 #include <asm/irc-regs.h>
diff --git a/arch/frv/kernel/gdb-io.c b/arch/frv/kernel/gdb-io.c
index 2ca641d199f8..0707d35079ba 100644
--- a/arch/frv/kernel/gdb-io.c
+++ b/arch/frv/kernel/gdb-io.c
@@ -19,7 +19,6 @@
 #include <linux/serial_reg.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/irc-regs.h>
 #include <asm/timer-regs.h>
 #include <asm/gdb-stub.h>
diff --git a/arch/frv/kernel/gdb-stub.c b/arch/frv/kernel/gdb-stub.c
index a6d5381c94fe..bbe78b0bffec 100644
--- a/arch/frv/kernel/gdb-stub.c
+++ b/arch/frv/kernel/gdb-stub.c
@@ -126,7 +126,6 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/gdb-stub.h>
 
 #define LEDS(x) do { /* *(u32*)0xe1200004 = ~(x); mb(); */ } while(0)
diff --git a/arch/frv/kernel/irq-mb93091.c b/arch/frv/kernel/irq-mb93091.c
index 9afc2ea400dc..2cc327a1ca44 100644
--- a/arch/frv/kernel/irq-mb93091.c
+++ b/arch/frv/kernel/irq-mb93091.c
@@ -20,7 +20,6 @@
 #include <linux/bitops.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/delay.h>
 #include <asm/irq.h>
 #include <asm/irc-regs.h>
diff --git a/arch/frv/kernel/irq-mb93093.c b/arch/frv/kernel/irq-mb93093.c
index 4d4ad09d3c91..95e4eb4f1f38 100644
--- a/arch/frv/kernel/irq-mb93093.c
+++ b/arch/frv/kernel/irq-mb93093.c
@@ -20,7 +20,6 @@
 #include <linux/bitops.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/delay.h>
 #include <asm/irq.h>
 #include <asm/irc-regs.h>
diff --git a/arch/frv/kernel/irq-mb93493.c b/arch/frv/kernel/irq-mb93493.c
index 4d034c7840c9..ba648da0932d 100644
--- a/arch/frv/kernel/irq-mb93493.c
+++ b/arch/frv/kernel/irq-mb93493.c
@@ -20,7 +20,6 @@
 #include <linux/bitops.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/delay.h>
 #include <asm/irq.h>
 #include <asm/irc-regs.h>
diff --git a/arch/frv/kernel/irq.c b/arch/frv/kernel/irq.c
index 3facbc28cbbc..2239346fa3db 100644
--- a/arch/frv/kernel/irq.c
+++ b/arch/frv/kernel/irq.c
@@ -28,7 +28,6 @@
 #include <linux/atomic.h>
 #include <asm/io.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/delay.h>
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 29cc49783787..d4de48bd5efe 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -28,7 +28,6 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
diff --git a/arch/frv/kernel/ptrace.c b/arch/frv/kernel/ptrace.c
index 9d68f7fac730..3987ff88dab0 100644
--- a/arch/frv/kernel/ptrace.c
+++ b/arch/frv/kernel/ptrace.c
@@ -26,7 +26,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/unistd.h>
 
diff --git a/arch/frv/kernel/traps.c b/arch/frv/kernel/traps.c
index 1d2dfe67d442..5cfd1420b091 100644
--- a/arch/frv/kernel/traps.c
+++ b/arch/frv/kernel/traps.c
@@ -23,7 +23,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/setup.h>
 #include <asm/fpu.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/siginfo.h>
diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c
index 41098a3803a2..4f8d8bcdc7de 100644
--- a/arch/frv/mb93090-mb00/pci-dma.c
+++ b/arch/frv/mb93090-mb00/pci-dma.c
@@ -13,6 +13,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/pci.h>
+#include <linux/export.h>
 #include <linux/highmem.h>
 #include <linux/scatterlist.h>
 #include <asm/io.h>
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index a325d57a83d5..331c1e2cfb67 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -20,7 +20,6 @@
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
 #include <asm/gdb-stub.h>
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index fbe5f0dbae06..a19effcccb34 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -33,7 +33,6 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/virtconvert.h>
 #include <asm/sections.h>
diff --git a/arch/frv/mm/kmap.c b/arch/frv/mm/kmap.c
index fb78be38ea02..e9217e605aa8 100644
--- a/arch/frv/mm/kmap.c
+++ b/arch/frv/mm/kmap.c
@@ -21,7 +21,6 @@
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #undef DEBUG
 
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index f5a38c1f5489..40901e353c21 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -2,6 +2,7 @@
 #define __ARCH_H8300_ATOMIC__
 
 #include <linux/types.h>
+#include <asm/cmpxchg.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -13,7 +14,6 @@
 #define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
-#include <asm/system.h>
 #include <linux/kernel.h>
 
 static __inline__ int atomic_add_return(int i, atomic_t *v)
@@ -102,8 +102,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
diff --git a/arch/h8300/include/asm/barrier.h b/arch/h8300/include/asm/barrier.h
new file mode 100644
index 000000000000..c7283c343c55
--- /dev/null
+++ b/arch/h8300/include/asm/barrier.h
@@ -0,0 +1,27 @@
+#ifndef _H8300_BARRIER_H
+#define _H8300_BARRIER_H
+
+#define nop()  asm volatile ("nop"::)
+
+/*
+ * Force strict CPU ordering.
+ * Not really required on H8...
+ */
+#define mb()   asm volatile (""   : : :"memory")
+#define rmb()  asm volatile (""   : : :"memory")
+#define wmb()  asm volatile (""   : : :"memory")
+#define set_mb(var, value) do { xchg(&var, value); } while (0)
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
+#define smp_read_barrier_depends()	read_barrier_depends()
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while(0)
+#endif
+
+#endif /* _H8300_BARRIER_H */
diff --git a/arch/h8300/include/asm/bitops.h b/arch/h8300/include/asm/bitops.h
index e856c1bb3415..eb34e0cd33d5 100644
--- a/arch/h8300/include/asm/bitops.h
+++ b/arch/h8300/include/asm/bitops.h
@@ -7,7 +7,6 @@
  */
 
 #include <linux/compiler.h>
-#include <asm/system.h>
 
 #ifdef __KERNEL__
 
diff --git a/arch/h8300/include/asm/bug.h b/arch/h8300/include/asm/bug.h
index 887c19773185..1e1be8119935 100644
--- a/arch/h8300/include/asm/bug.h
+++ b/arch/h8300/include/asm/bug.h
@@ -5,4 +5,8 @@
 #define is_valid_bugaddr(addr) (1)
 
 #include <asm-generic/bug.h>
+
+struct pt_regs;
+extern void die(const char *str, struct pt_regs *fp, unsigned long err);
+
 #endif
diff --git a/arch/h8300/include/asm/cmpxchg.h b/arch/h8300/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..cdb203ef681f
--- /dev/null
+++ b/arch/h8300/include/asm/cmpxchg.h
@@ -0,0 +1,60 @@
+#ifndef __ARCH_H8300_CMPXCHG__
+#define __ARCH_H8300_CMPXCHG__
+
+#include <linux/irqflags.h>
+
+#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((volatile struct __xchg_dummy *)(x))
+
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+  unsigned long tmp, flags;
+
+  local_irq_save(flags);
+
+  switch (size) {
+  case 1:
+    __asm__ __volatile__
+    ("mov.b %2,%0\n\t"
+     "mov.b %1,%2"
+    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
+    break;
+  case 2:
+    __asm__ __volatile__
+    ("mov.w %2,%0\n\t"
+     "mov.w %1,%2"
+    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
+    break;
+  case 4:
+    __asm__ __volatile__
+    ("mov.l %2,%0\n\t"
+     "mov.l %1,%2"
+    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
+    break;
+  default:
+    tmp = 0;	  
+  }
+  local_irq_restore(flags);
+  return tmp;
+}
+
+#include <asm-generic/cmpxchg-local.h>
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#ifndef CONFIG_SMP
+#include <asm-generic/cmpxchg.h>
+#endif
+
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+#endif /* __ARCH_H8300_CMPXCHG__ */
diff --git a/arch/h8300/include/asm/exec.h b/arch/h8300/include/asm/exec.h
new file mode 100644
index 000000000000..c01c45ccadf9
--- /dev/null
+++ b/arch/h8300/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef _H8300_EXEC_H
+#define _H8300_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _H8300_EXEC_H */
diff --git a/arch/h8300/include/asm/posix_types.h b/arch/h8300/include/asm/posix_types.h
index 6f833a16f694..bc4c34efb1ad 100644
--- a/arch/h8300/include/asm/posix_types.h
+++ b/arch/h8300/include/asm/posix_types.h
@@ -7,54 +7,23 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
 typedef unsigned short	__kernel_old_uid_t;
 typedef unsigned short	__kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-
-#undef	__FD_CLR
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-
-#undef	__FD_ISSET
-#define	__FD_ISSET(d, set)	(!!((set)->fds_bits[__FDELT(d)] & __FDMASK(d)))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) (memset (fdsetp, 0, sizeof(*(fd_set *)fdsetp)))
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h
index e834b6018897..61fabf1788c6 100644
--- a/arch/h8300/include/asm/processor.h
+++ b/arch/h8300/include/asm/processor.h
@@ -135,4 +135,9 @@ unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()    barrier()
 
+#define HARD_RESET_NOW() ({		\
+        local_irq_disable();		\
+        asm("jmp @@0");			\
+})
+
 #endif
diff --git a/arch/h8300/include/asm/switch_to.h b/arch/h8300/include/asm/switch_to.h
new file mode 100644
index 000000000000..cdd8731ce487
--- /dev/null
+++ b/arch/h8300/include/asm/switch_to.h
@@ -0,0 +1,50 @@
+#ifndef _H8300_SWITCH_TO_H
+#define _H8300_SWITCH_TO_H
+
+/*
+ * switch_to(n) should switch tasks to task ptr, first checking that
+ * ptr isn't the current task, in which case it does nothing.  This
+ * also clears the TS-flag if the task we switched to has used the
+ * math co-processor latest.
+ */
+/*
+ * switch_to() saves the extra registers, that are not saved
+ * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
+ * a0-a1. Some of these are used by schedule() and its predecessors
+ * and so we might get see unexpected behaviors when a task returns
+ * with unexpected register values.
+ *
+ * syscall stores these registers itself and none of them are used
+ * by syscall after the function in the syscall has been called.
+ *
+ * Beware that resume now expects *next to be in d1 and the offset of
+ * tss to be in a1. This saves a few instructions as we no longer have
+ * to push them onto the stack and read them back right after.
+ *
+ * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
+ *
+ * Changed 96/09/19 by Andreas Schwab
+ * pass prev in a0, next in a1, offset of tss in d1, and whether
+ * the mm structures are shared in d2 (to avoid atc flushing).
+ *
+ * H8/300 Porting 2002/09/04 Yoshinori Sato
+ */
+
+asmlinkage void resume(void);
+#define switch_to(prev,next,last) {                         \
+  void *_last;						    \
+  __asm__ __volatile__(					    \
+  			"mov.l	%1, er0\n\t"		    \
+			"mov.l	%2, er1\n\t"		    \
+                        "mov.l  %3, er2\n\t"                \
+			"jsr @_resume\n\t"                  \
+                        "mov.l  er2,%0\n\t"                 \
+		       : "=r" (_last)			    \
+		       : "r" (&(prev->thread)),		    \
+			 "r" (&(next->thread)),		    \
+                         "g" (prev)                         \
+		       : "cc", "er0", "er1", "er2", "er3"); \
+  (last) = _last; 					    \
+}
+
+#endif /* _H8300_SWITCH_TO_H */
diff --git a/arch/h8300/include/asm/system.h b/arch/h8300/include/asm/system.h
deleted file mode 100644
index 2c2382e50d93..000000000000
--- a/arch/h8300/include/asm/system.h
+++ /dev/null
@@ -1,140 +0,0 @@
-#ifndef _H8300_SYSTEM_H
-#define _H8300_SYSTEM_H
-
-#include <linux/linkage.h>
-#include <linux/irqflags.h>
-
-struct pt_regs;
-
-/*
- * switch_to(n) should switch tasks to task ptr, first checking that
- * ptr isn't the current task, in which case it does nothing.  This
- * also clears the TS-flag if the task we switched to has used the
- * math co-processor latest.
- */
-/*
- * switch_to() saves the extra registers, that are not saved
- * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
- * a0-a1. Some of these are used by schedule() and its predecessors
- * and so we might get see unexpected behaviors when a task returns
- * with unexpected register values.
- *
- * syscall stores these registers itself and none of them are used
- * by syscall after the function in the syscall has been called.
- *
- * Beware that resume now expects *next to be in d1 and the offset of
- * tss to be in a1. This saves a few instructions as we no longer have
- * to push them onto the stack and read them back right after.
- *
- * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
- *
- * Changed 96/09/19 by Andreas Schwab
- * pass prev in a0, next in a1, offset of tss in d1, and whether
- * the mm structures are shared in d2 (to avoid atc flushing).
- *
- * H8/300 Porting 2002/09/04 Yoshinori Sato
- */
-
-asmlinkage void resume(void);
-#define switch_to(prev,next,last) {                         \
-  void *_last;						    \
-  __asm__ __volatile__(					    \
-  			"mov.l	%1, er0\n\t"		    \
-			"mov.l	%2, er1\n\t"		    \
-                        "mov.l  %3, er2\n\t"                \
-			"jsr @_resume\n\t"                  \
-                        "mov.l  er2,%0\n\t"                 \
-		       : "=r" (_last)			    \
-		       : "r" (&(prev->thread)),		    \
-			 "r" (&(next->thread)),		    \
-                         "g" (prev)                         \
-		       : "cc", "er0", "er1", "er2", "er3"); \
-  (last) = _last; 					    \
-}
-
-#define iret() __asm__ __volatile__ ("rte": : :"memory", "sp", "cc")
-
-/*
- * Force strict CPU ordering.
- * Not really required on H8...
- */
-#define nop()  asm volatile ("nop"::)
-#define mb()   asm volatile (""   : : :"memory")
-#define rmb()  asm volatile (""   : : :"memory")
-#define wmb()  asm volatile (""   : : :"memory")
-#define set_mb(var, value) do { xchg(&var, value); } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
-#endif
-
-#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((volatile struct __xchg_dummy *)(x))
-
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
-  unsigned long tmp, flags;
-
-  local_irq_save(flags);
-
-  switch (size) {
-  case 1:
-    __asm__ __volatile__
-    ("mov.b %2,%0\n\t"
-     "mov.b %1,%2"
-    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  case 2:
-    __asm__ __volatile__
-    ("mov.w %2,%0\n\t"
-     "mov.w %1,%2"
-    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  case 4:
-    __asm__ __volatile__
-    ("mov.l %2,%0\n\t"
-     "mov.l %1,%2"
-    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  default:
-    tmp = 0;	  
-  }
-  local_irq_restore(flags);
-  return tmp;
-}
-
-#define HARD_RESET_NOW() ({		\
-        local_irq_disable();		\
-        asm("jmp @@0");			\
-})
-
-#include <asm-generic/cmpxchg-local.h>
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#ifndef CONFIG_SMP
-#include <asm-generic/cmpxchg.h>
-#endif
-
-#define arch_align_stack(x) (x)
-
-extern void die(const char *str, struct pt_regs *fp, unsigned long err);
-
-#endif /* _H8300_SYSTEM_H */
diff --git a/arch/h8300/kernel/irq.c b/arch/h8300/kernel/irq.c
index 1f67fed476af..2fa8ac7b79b5 100644
--- a/arch/h8300/kernel/irq.c
+++ b/arch/h8300/kernel/irq.c
@@ -16,7 +16,6 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/io.h>
 #include <asm/setup.h>
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 1a173b35f475..0e9c315be104 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -38,7 +38,6 @@
 #include <linux/slab.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c
index 497fa89b5df4..748cf6585aa4 100644
--- a/arch/h8300/kernel/ptrace.c
+++ b/arch/h8300/kernel/ptrace.c
@@ -27,7 +27,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/signal.h>
 
diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c
index dfa05bd908b6..7833aa3e7c7d 100644
--- a/arch/h8300/kernel/traps.c
+++ b/arch/h8300/kernel/traps.c
@@ -22,7 +22,6 @@
 #include <linux/module.h>
 #include <linux/bug.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/traps.h>
 #include <asm/page.h>
diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c
index 1d092abebf03..472535977006 100644
--- a/arch/h8300/mm/fault.c
+++ b/arch/h8300/mm/fault.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 
 /*
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
index 7cc3380f250c..973369c32a95 100644
--- a/arch/h8300/mm/init.c
+++ b/arch/h8300/mm/init.c
@@ -36,7 +36,6 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 
 #undef DEBUG
 
diff --git a/arch/h8300/mm/kmap.c b/arch/h8300/mm/kmap.c
index 944a502c2e56..f79edcdadf39 100644
--- a/arch/h8300/mm/kmap.c
+++ b/arch/h8300/mm/kmap.c
@@ -19,7 +19,6 @@
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #undef DEBUG
 
diff --git a/arch/h8300/mm/memory.c b/arch/h8300/mm/memory.c
index 5552ddfaab5e..06e364641392 100644
--- a/arch/h8300/mm/memory.c
+++ b/arch/h8300/mm/memory.c
@@ -26,7 +26,6 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/io.h>
 
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index e220f9053035..3e258043337b 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -23,6 +23,7 @@
 #define _ASM_ATOMIC_H
 
 #include <linux/types.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define atomic_set(v, i)	((v)->counter = (i))
diff --git a/arch/hexagon/include/asm/barrier.h b/arch/hexagon/include/asm/barrier.h
new file mode 100644
index 000000000000..a4ed6e26cb1d
--- /dev/null
+++ b/arch/hexagon/include/asm/barrier.h
@@ -0,0 +1,41 @@
+/*
+ * Memory barrier definitions for the Hexagon architecture
+ *
+ * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef _ASM_BARRIER_H
+#define _ASM_BARRIER_H
+
+#define rmb()				barrier()
+#define read_barrier_depends()		barrier()
+#define wmb()				barrier()
+#define mb()				barrier()
+#define smp_rmb()			barrier()
+#define smp_read_barrier_depends()	barrier()
+#define smp_wmb()			barrier()
+#define smp_mb()			barrier()
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
+/*  Set a value and use a memory barrier.  Used by the scheduler somewhere.  */
+#define set_mb(var, value) \
+	do { var = value; mb(); } while (0)
+
+#endif /* _ASM_BARRIER_H */
diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h
index d23461e080ff..4caa649ad78b 100644
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -24,7 +24,6 @@
 
 #include <linux/compiler.h>
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/atomic.h>
 
 #ifdef __KERNEL__
diff --git a/arch/hexagon/include/asm/system.h b/arch/hexagon/include/asm/cmpxchg.h
index 323ed1dd65e2..c5f9527e1df6 100644
--- a/arch/hexagon/include/asm/system.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -1,8 +1,9 @@
 /*
- * System level definitions for the Hexagon architecture
+ * xchg/cmpxchg operations for the Hexagon architecture
  *
  * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
  *
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 and
  * only version 2 as published by the Free Software Foundation.
@@ -18,37 +19,8 @@
  * 02110-1301, USA.
  */
 
-#ifndef _ASM_SYSTEM_H
-#define _ASM_SYSTEM_H
-
-#include <linux/linkage.h>
-#include <linux/irqflags.h>
-#include <asm/atomic.h>
-#include <asm/hexagon_vm.h>
-
-struct thread_struct;
-
-extern struct task_struct *__switch_to(struct task_struct *,
-	struct task_struct *,
-	struct task_struct *);
-
-#define switch_to(p, n, r) do {\
-	r = __switch_to((p), (n), (r));\
-} while (0)
-
-
-#define rmb()				barrier()
-#define read_barrier_depends()		barrier()
-#define wmb()				barrier()
-#define mb()				barrier()
-#define smp_rmb()			barrier()
-#define smp_read_barrier_depends()	barrier()
-#define smp_wmb()			barrier()
-#define smp_mb()			barrier()
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
+#ifndef _ASM_CMPXCHG_H
+#define _ASM_CMPXCHG_H
 
 /*
  * __xchg - atomically exchange a register and a memory location
@@ -87,10 +59,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
 #define xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), \
 	sizeof(*(ptr))))
 
-/*  Set a value and use a memory barrier.  Used by the scheduler somewhere.  */
-#define set_mb(var, value) \
-	do { var = value; mb(); } while (0)
-
 /*
  *  see rt-mutex-design.txt; cmpxchg supposedly checks if *ptr == A and swaps.
  *  looks just like atomic_cmpxchg on our arch currently with a bunch of
@@ -119,8 +87,4 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
 	__oldval;						\
 })
 
-/*  Should probably shoot for an 8-byte aligned stack pointer  */
-#define STACK_MASK (~7)
-#define arch_align_stack(x) (x & STACK_MASK)
-
-#endif
+#endif /* _ASM_CMPXCHG_H */
diff --git a/arch/hexagon/include/asm/dma-mapping.h b/arch/hexagon/include/asm/dma-mapping.h
index 448b224ba4ef..233ed3d2d25e 100644
--- a/arch/hexagon/include/asm/dma-mapping.h
+++ b/arch/hexagon/include/asm/dma-mapping.h
@@ -71,29 +71,35 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return (dma_addr == bad_dma_address);
 }
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
 {
 	void *ret;
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
-	ret = ops->alloc_coherent(dev, size, dma_handle, flag);
+	ret = ops->alloc(dev, size, dma_handle, flag, attrs);
 
 	debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
 
 	return ret;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
-	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+	dma_ops->free(dev, size, cpu_addr, dma_handle, attrs);
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
 }
diff --git a/arch/arm/mach-netx/include/mach/io.h b/arch/hexagon/include/asm/exec.h
index c3921cb3b6a6..350e6d497d44 100644
--- a/arch/arm/mach-netx/include/mach/io.h
+++ b/arch/hexagon/include/asm/exec.h
@@ -1,11 +1,11 @@
 /*
- *  arch/arm/mach-netx/include/mach/io.h
+ * Process execution related definitions for the Hexagon architecture
  *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
+ * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -14,15 +14,15 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
  */
 
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
+#ifndef _ASM_EXEC_H
+#define _ASM_EXEC_H
 
-#define IO_SPACE_LIMIT 0xffffffff
+/*  Should probably shoot for an 8-byte aligned stack pointer  */
+#define STACK_MASK (~7)
+#define arch_align_stack(x) (x & STACK_MASK)
 
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)            (a)
-
-#endif
+#endif /* _ASM_EXEC_H */
diff --git a/arch/hexagon/include/asm/switch_to.h b/arch/hexagon/include/asm/switch_to.h
new file mode 100644
index 000000000000..28ca0dfb6064
--- /dev/null
+++ b/arch/hexagon/include/asm/switch_to.h
@@ -0,0 +1,34 @@
+/*
+ * Task switching definitions for the Hexagon architecture
+ *
+ * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef _ASM_SWITCH_TO_H
+#define _ASM_SWITCH_TO_H
+
+struct thread_struct;
+
+extern struct task_struct *__switch_to(struct task_struct *,
+	struct task_struct *,
+	struct task_struct *);
+
+#define switch_to(p, n, r) do {\
+	r = __switch_to((p), (n), (r));\
+} while (0)
+
+#endif /* _ASM_SWITCH_TO_H */
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index e711ace62fdf..37302218ca4a 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -54,7 +54,8 @@ static struct gen_pool *coherent_pool;
 /* Allocates from a pool of uncached memory that was reserved at boot time */
 
 void *hexagon_dma_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_addr, gfp_t flag)
+				 dma_addr_t *dma_addr, gfp_t flag,
+				 struct dma_attrs *attrs)
 {
 	void *ret;
 
@@ -81,7 +82,7 @@ void *hexagon_dma_alloc_coherent(struct device *dev, size_t size,
 }
 
 static void hexagon_free_coherent(struct device *dev, size_t size, void *vaddr,
-				  dma_addr_t dma_addr)
+				  dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
 	gen_pool_free(coherent_pool, (unsigned long) vaddr, size);
 }
@@ -202,8 +203,8 @@ static void hexagon_sync_single_for_device(struct device *dev,
 }
 
 struct dma_map_ops hexagon_dma_ops = {
-	.alloc_coherent	= hexagon_dma_alloc_coherent,
-	.free_coherent	= hexagon_free_coherent,
+	.alloc		= hexagon_dma_alloc_coherent,
+	.free		= hexagon_free_coherent,
 	.map_sg		= hexagon_map_sg,
 	.map_page	= hexagon_map_page,
 	.sync_single_for_cpu = hexagon_sync_single_for_cpu,
diff --git a/arch/hexagon/kernel/ptrace.c b/arch/hexagon/kernel/ptrace.c
index bea3f08470fd..32342de1a79c 100644
--- a/arch/hexagon/kernel/ptrace.c
+++ b/arch/hexagon/kernel/ptrace.c
@@ -29,7 +29,6 @@
 #include <linux/regset.h>
 #include <linux/user.h>
 
-#include <asm/system.h>
 #include <asm/user.h>
 
 static int genregs_get(struct task_struct *target,
diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c
index 0123c63e9a3a..9b44a9e2d05a 100644
--- a/arch/hexagon/kernel/smp.c
+++ b/arch/hexagon/kernel/smp.c
@@ -29,14 +29,13 @@
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 
-#include <asm/system.h>  /*  xchg  */
 #include <asm/time.h>    /*  timer_interrupt  */
 #include <asm/hexagon_vm.h>
 
 #define BASE_IPI_IRQ 26
 
 /*
- * cpu_possible_map needs to be filled out prior to setup_per_cpu_areas
+ * cpu_possible_mask needs to be filled out prior to setup_per_cpu_areas
  * (which is prior to any of our smp_prepare_cpu crap), in order to set
  * up the...  per_cpu areas.
  */
@@ -209,7 +208,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	stack_start =  ((void *) thread) + THREAD_SIZE;
 	__vmstart(start_secondary, stack_start);
 
-	while (!cpu_isset(cpu, cpu_online_map))
+	while (!cpu_online(cpu))
 		barrier();
 
 	return 0;
@@ -230,7 +229,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 
 	/*  Right now, let's just fake it. */
 	for (i = 0; i < max_cpus; i++)
-		cpu_set(i, cpu_present_map);
+		set_cpu_present(i, true);
 
 	/*  Also need to register the interrupts for IPI  */
 	if (max_cpus > 1)
@@ -270,5 +269,5 @@ void smp_start_cpus(void)
 	int i;
 
 	for (i = 0; i < NR_CPUS; i++)
-		cpu_set(i, cpu_possible_map);
+		set_cpu_possible(i, true);
 }
diff --git a/arch/hexagon/kernel/vm_events.c b/arch/hexagon/kernel/vm_events.c
index 986a081e32ec..591fc1b68635 100644
--- a/arch/hexagon/kernel/vm_events.c
+++ b/arch/hexagon/kernel/vm_events.c
@@ -22,7 +22,6 @@
 #include <asm/registers.h>
 #include <linux/irq.h>
 #include <linux/hardirq.h>
-#include <asm/system.h>
 
 /*
  * show_regs - print pt_regs structure
diff --git a/arch/ia64/dig/setup.c b/arch/ia64/dig/setup.c
index 9196b330ff7f..98131e1db7a0 100644
--- a/arch/ia64/dig/setup.c
+++ b/arch/ia64/dig/setup.c
@@ -22,7 +22,7 @@
 
 #include <asm/io.h>
 #include <asm/machvec.h>
-#include <asm/system.h>
+#include <asm/setup.h>
 
 void __init
 dig_setup (char **cmdline_p)
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index f5f4ef149aac..bcda5b2d121a 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -43,7 +43,6 @@
 #include <asm/io.h>
 #include <asm/page.h>		/* PAGE_OFFSET */
 #include <asm/dma.h>
-#include <asm/system.h>		/* wmb() */
 
 #include <asm/acpi-ext.h>
 
@@ -1130,7 +1129,8 @@ void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
  * See Documentation/DMA-API-HOWTO.txt
  */
 static void *
-sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags)
+sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		   gfp_t flags, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 	void *addr;
@@ -1192,8 +1192,8 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp
  *
  * See Documentation/DMA-API-HOWTO.txt
  */
-static void sba_free_coherent (struct device *dev, size_t size, void *vaddr,
-			       dma_addr_t dma_handle)
+static void sba_free_coherent(struct device *dev, size_t size, void *vaddr,
+			      dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	sba_unmap_single_attrs(dev, dma_handle, size, 0, NULL);
 	free_pages((unsigned long) vaddr, get_order(size));
@@ -2213,8 +2213,8 @@ sba_page_override(char *str)
 __setup("sbapagesize=",sba_page_override);
 
 struct dma_map_ops sba_dma_ops = {
-	.alloc_coherent		= sba_alloc_coherent,
-	.free_coherent		= sba_free_coherent,
+	.alloc			= sba_alloc_coherent,
+	.free			= sba_free_coherent,
 	.map_page		= sba_map_page,
 	.unmap_page		= sba_unmap_page,
 	.map_sg			= sba_map_sg_attrs,
diff --git a/arch/ia64/hp/sim/boot/bootloader.c b/arch/ia64/hp/sim/boot/bootloader.c
index c5e9baafafe0..28f4b230b8cb 100644
--- a/arch/ia64/hp/sim/boot/bootloader.c
+++ b/arch/ia64/hp/sim/boot/bootloader.c
@@ -20,7 +20,6 @@ struct task_struct;	/* forward declaration for elf.h */
 #include <asm/pal.h>
 #include <asm/pgtable.h>
 #include <asm/sal.h>
-#include <asm/system.h>
 
 #include "ssc.h"
 
diff --git a/arch/ia64/hp/sim/boot/fw-emu.c b/arch/ia64/hp/sim/boot/fw-emu.c
index 0216e28300fa..271f412bda1a 100644
--- a/arch/ia64/hp/sim/boot/fw-emu.c
+++ b/arch/ia64/hp/sim/boot/fw-emu.c
@@ -13,6 +13,7 @@
 #include <asm/io.h>
 #include <asm/pal.h>
 #include <asm/sal.h>
+#include <asm/setup.h>
 
 #include "ssc.h"
 
diff --git a/arch/ia64/hp/sim/simeth.c b/arch/ia64/hp/sim/simeth.c
index a63218e1f6c9..c13064e422df 100644
--- a/arch/ia64/hp/sim/simeth.c
+++ b/arch/ia64/hp/sim/simeth.c
@@ -20,7 +20,6 @@
 #include <linux/skbuff.h>
 #include <linux/notifier.h>
 #include <linux/bitops.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/hpsim.h>
 
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index a06dfb13d518..301609c3fcec 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -32,7 +32,6 @@
 
 #include <linux/init.h>
 #include <linux/numa.h>
-#include <asm/system.h>
 #include <asm/numa.h>
 
 #define COMPILER_DEPENDENT_INT64	long
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 3fad89ee01cb..7d9116600a36 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -15,7 +15,6 @@
 #include <linux/types.h>
 
 #include <asm/intrinsics.h>
-#include <asm/system.h>
 
 
 #define ATOMIC_INIT(i)		((atomic_t) { (i) })
diff --git a/arch/ia64/include/asm/auxvec.h b/arch/ia64/include/asm/auxvec.h
index 23cebe5685b9..58277fc650ef 100644
--- a/arch/ia64/include/asm/auxvec.h
+++ b/arch/ia64/include/asm/auxvec.h
@@ -8,4 +8,6 @@
 #define AT_SYSINFO	32
 #define AT_SYSINFO_EHDR	33
 
+#define AT_VECTOR_SIZE_ARCH 2 /* entries in ARCH_DLINFO */
+
 #endif /* _ASM_IA64_AUXVEC_H */
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
new file mode 100644
index 000000000000..60576e06b6fb
--- /dev/null
+++ b/arch/ia64/include/asm/barrier.h
@@ -0,0 +1,68 @@
+/*
+ * Memory barrier definitions.  This is based on information published
+ * in the Processor Abstraction Layer and the System Abstraction Layer
+ * manual.
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ */
+#ifndef _ASM_IA64_BARRIER_H
+#define _ASM_IA64_BARRIER_H
+
+#include <linux/compiler.h>
+
+/*
+ * Macros to force memory ordering.  In these descriptions, "previous"
+ * and "subsequent" refer to program order; "visible" means that all
+ * architecturally visible effects of a memory access have occurred
+ * (at a minimum, this means the memory has been read or written).
+ *
+ *   wmb():	Guarantees that all preceding stores to memory-
+ *		like regions are visible before any subsequent
+ *		stores and that all following stores will be
+ *		visible only after all previous stores.
+ *   rmb():	Like wmb(), but for reads.
+ *   mb():	wmb()/rmb() combo, i.e., all previous memory
+ *		accesses are visible before all subsequent
+ *		accesses and vice versa.  This is also known as
+ *		a "fence."
+ *
+ * Note: "mb()" and its variants cannot be used as a fence to order
+ * accesses to memory mapped I/O registers.  For that, mf.a needs to
+ * be used.  However, we don't want to always use mf.a because (a)
+ * it's (presumably) much slower than mf and (b) mf.a is supported for
+ * sequential memory pages only.
+ */
+#define mb()	ia64_mf()
+#define rmb()	mb()
+#define wmb()	mb()
+#define read_barrier_depends()	do { } while(0)
+
+#ifdef CONFIG_SMP
+# define smp_mb()	mb()
+# define smp_rmb()	rmb()
+# define smp_wmb()	wmb()
+# define smp_read_barrier_depends()	read_barrier_depends()
+#else
+# define smp_mb()	barrier()
+# define smp_rmb()	barrier()
+# define smp_wmb()	barrier()
+# define smp_read_barrier_depends()	do { } while(0)
+#endif
+
+/*
+ * XXX check on this ---I suspect what Linus really wants here is
+ * acquire vs release semantics but we can't discuss this stuff with
+ * Linus just yet.  Grrr...
+ */
+#define set_mb(var, value)	do { (var) = (value); mb(); } while (0)
+
+/*
+ * The group barrier in front of the rsm & ssm are necessary to ensure
+ * that none of the previous instructions in the same group are
+ * affected by the rsm/ssm.
+ */
+
+#endif /* _ASM_IA64_BARRIER_H */
diff --git a/arch/ia64/include/asm/cmpxchg.h b/arch/ia64/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..4c96187e2049
--- /dev/null
+++ b/arch/ia64/include/asm/cmpxchg.h
@@ -0,0 +1 @@
+#include <asm/intrinsics.h>
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 4336d080b241..4f5e8148440d 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -23,23 +23,29 @@ extern void machvec_dma_sync_single(struct device *, dma_addr_t, size_t,
 extern void machvec_dma_sync_sg(struct device *, struct scatterlist *, int,
 				enum dma_data_direction);
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *daddr, gfp_t gfp)
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *daddr, gfp_t gfp,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = platform_dma_get_ops(dev);
 	void *caddr;
 
-	caddr = ops->alloc_coherent(dev, size, daddr, gfp);
+	caddr = ops->alloc(dev, size, daddr, gfp, attrs);
 	debug_dma_alloc_coherent(dev, size, *daddr, caddr);
 	return caddr;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *caddr, dma_addr_t daddr)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *caddr, dma_addr_t daddr,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = platform_dma_get_ops(dev);
 	debug_dma_free_coherent(dev, size, caddr, daddr);
-	ops->free_coherent(dev, size, caddr, daddr);
+	ops->free(dev, size, caddr, daddr, attrs);
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/ia64/include/asm/exec.h b/arch/ia64/include/asm/exec.h
new file mode 100644
index 000000000000..b26242490e36
--- /dev/null
+++ b/arch/ia64/include/asm/exec.h
@@ -0,0 +1,14 @@
+/*
+ * Process execution defines.
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ */
+#ifndef _ASM_IA64_EXEC_H
+#define _ASM_IA64_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _ASM_IA64_EXEC_H */
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index 8428525ddb22..0ab82cc2dc8f 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -4,7 +4,6 @@
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
-#include <asm/system.h>
 
 #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \
 do {									\
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index e5a6c3530c6c..2c26321c28c3 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -71,7 +71,6 @@ extern unsigned int num_io_spaces;
 #include <asm/intrinsics.h>
 #include <asm/machvec.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm-generic/iomap.h>
 
 /*
diff --git a/arch/ia64/include/asm/irqflags.h b/arch/ia64/include/asm/irqflags.h
index f82d6be2ecd2..2b68d856dc78 100644
--- a/arch/ia64/include/asm/irqflags.h
+++ b/arch/ia64/include/asm/irqflags.h
@@ -10,6 +10,8 @@
 #ifndef _ASM_IA64_IRQFLAGS_H
 #define _ASM_IA64_IRQFLAGS_H
 
+#include <asm/pal.h>
+
 #ifdef CONFIG_IA64_DEBUG_IRQ
 extern unsigned long last_cli_ip;
 static inline void arch_maybe_save_ip(unsigned long flags)
diff --git a/arch/ia64/include/asm/kexec.h b/arch/ia64/include/asm/kexec.h
index e1d58f819d78..aea2b81b03a3 100644
--- a/arch/ia64/include/asm/kexec.h
+++ b/arch/ia64/include/asm/kexec.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_IA64_KEXEC_H
 #define _ASM_IA64_KEXEC_H
 
+#include <asm/setup.h>
 
 /* Maximum physical address we can use pages from */
 #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h
index bc90c75adf67..b9f82c84f093 100644
--- a/arch/ia64/include/asm/kvm.h
+++ b/arch/ia64/include/asm/kvm.h
@@ -261,4 +261,8 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
 #endif
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 2689ee54a1c9..e35b3a84a40b 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -459,6 +459,9 @@ struct kvm_sal_data {
 	unsigned long boot_gp;
 };
 
+struct kvm_arch_memory_slot {
+};
+
 struct kvm_arch {
 	spinlock_t dirty_log_lock;
 
diff --git a/arch/ia64/include/asm/mca_asm.h b/arch/ia64/include/asm/mca_asm.h
index dd2a5b134390..13c1d4994d49 100644
--- a/arch/ia64/include/asm/mca_asm.h
+++ b/arch/ia64/include/asm/mca_asm.h
@@ -15,6 +15,8 @@
 #ifndef _ASM_IA64_MCA_ASM_H
 #define _ASM_IA64_MCA_ASM_H
 
+#include <asm/percpu.h>
+
 #define PSR_IC		13
 #define PSR_I		14
 #define	PSR_DT		17
diff --git a/arch/ia64/include/asm/page.h b/arch/ia64/include/asm/page.h
index 961a16f43e6b..f1e1b2e3cdb3 100644
--- a/arch/ia64/include/asm/page.h
+++ b/arch/ia64/include/asm/page.h
@@ -221,4 +221,14 @@ get_order (unsigned long size)
 					 (((current->personality & READ_IMPLIES_EXEC) != 0)	\
 					  ? VM_EXEC : 0))
 
+#define GATE_ADDR		RGN_BASE(RGN_GATE)
+
+/*
+ * 0xa000000000000000+2*PERCPU_PAGE_SIZE
+ * - 0xa000000000000000+3*PERCPU_PAGE_SIZE remain unmapped (guard page)
+ */
+#define KERNEL_START		 (GATE_ADDR+__IA64_UL_CONST(0x100000000))
+#define PERCPU_ADDR		(-PERCPU_PAGE_SIZE)
+#define LOAD_OFFSET		(KERNEL_START - KERNEL_TR_PAGE_SIZE)
+
 #endif /* _ASM_IA64_PAGE_H */
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index b22e5f5fa593..5e04b591e423 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -11,6 +11,14 @@
 #include <asm/scatterlist.h>
 #include <asm/hw_irq.h>
 
+struct pci_vector_struct {
+	__u16 segment;	/* PCI Segment number */
+	__u16 bus;	/* PCI Bus number */
+	__u32 pci_id;	/* ACPI split 16 bits device, 16 bits function (see section 6.1.1) */
+	__u8 pin;	/* PCI PIN (0 = A, 1 = B, 2 = C, 3 = D) */
+	__u32 irq;	/* IRQ assigned */
+};
+
 /*
  * Can be used to override the logic in pci_scan_bus for skipping already-configured bus
  * numbers - to be used for buggy BIOSes or architectures with incomplete PCI setup by the
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 1a97af31ef17..815810cbbedc 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -16,7 +16,6 @@
 #include <asm/mman.h>
 #include <asm/page.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/types.h>
 
 #define IA64_MAX_PHYS_BITS	50	/* max. number of physical address bits (architected) */
diff --git a/arch/ia64/include/asm/posix_types.h b/arch/ia64/include/asm/posix_types.h
index 17885567b731..7323ab9467eb 100644
--- a/arch/ia64/include/asm/posix_types.h
+++ b/arch/ia64/include/asm/posix_types.h
@@ -1,126 +1,11 @@
 #ifndef _ASM_IA64_POSIX_TYPES_H
 #define _ASM_IA64_POSIX_TYPES_H
 
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc.  Also, we cannot
- * assume GCC is being used.
- *
- * Based on <asm-alpha/posix_types.h>.
- *
- * Modified 1998-2000, 2003
- *	David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co
- */
-
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
 typedef unsigned int	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef long long	__kernel_loff_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned long	__kernel_sigset_t;	/* at least 32 bits */
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
-
-typedef unsigned int	__kernel_old_dev_t;
-
-# ifdef __KERNEL__
-
-#  ifndef __GNUC__
-
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-#define	__FD_ISSET(d, set)	(((set)->fds_bits[__FDELT(d)] & __FDMASK(d)) != 0)
-#define	__FD_ZERO(set)	\
-  ((void) memset ((void *) (set), 0, sizeof (__kernel_fd_set)))
+#define __kernel_nlink_t __kernel_nlink_t
 
-#  else /* !__GNUC__ */
-
-/* With GNU C, use inline functions instead so args are evaluated only once: */
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long fd, const __kernel_fd_set *p)
-{ 
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		      case 16:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			return;
-
-		      case 8:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			return;
+typedef unsigned long	__kernel_sigset_t;	/* at least 32 bits */
 
-		      case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
+#include <asm-generic/posix_types.h>
 
-#  endif /* !__GNUC__ */
-# endif /* __KERNEL__ */
 #endif /* _ASM_IA64_POSIX_TYPES_H */
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 691be0b95c1e..483f6c6a4238 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -19,6 +19,9 @@
 #include <asm/ptrace.h>
 #include <asm/ustack.h>
 
+#define __ARCH_WANT_UNLOCKED_CTXSW
+#define ARCH_HAS_PREFETCH_SWITCH_STACK
+
 #define IA64_NUM_PHYS_STACK_REG	96
 #define IA64_NUM_DBG_REGS	8
 
@@ -720,6 +723,11 @@ extern unsigned long boot_option_idle_override;
 enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_FORCE_MWAIT,
 			 IDLE_NOMWAIT, IDLE_POLL};
 
+void cpu_idle_wait(void);
+void default_idle(void);
+
+#define ia64_platform_is(x) (strcmp(x, platform_name) == 0)
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_IA64_PROCESSOR_H */
diff --git a/arch/ia64/include/asm/sal.h b/arch/ia64/include/asm/sal.h
index d19ddba4e327..e504f382115e 100644
--- a/arch/ia64/include/asm/sal.h
+++ b/arch/ia64/include/asm/sal.h
@@ -40,7 +40,6 @@
 #include <linux/efi.h>
 
 #include <asm/pal.h>
-#include <asm/system.h>
 #include <asm/fpu.h>
 
 extern spinlock_t sal_lock;
diff --git a/arch/ia64/include/asm/setup.h b/arch/ia64/include/asm/setup.h
index 4399a44355b3..8d56458310b3 100644
--- a/arch/ia64/include/asm/setup.h
+++ b/arch/ia64/include/asm/setup.h
@@ -3,4 +3,22 @@
 
 #define COMMAND_LINE_SIZE	2048
 
+extern struct ia64_boot_param {
+	__u64 command_line;		/* physical address of command line arguments */
+	__u64 efi_systab;		/* physical address of EFI system table */
+	__u64 efi_memmap;		/* physical address of EFI memory map */
+	__u64 efi_memmap_size;		/* size of EFI memory map */
+	__u64 efi_memdesc_size;		/* size of an EFI memory map descriptor */
+	__u32 efi_memdesc_version;	/* memory descriptor version */
+	struct {
+		__u16 num_cols;	/* number of columns on console output device */
+		__u16 num_rows;	/* number of rows on console output device */
+		__u16 orig_x;	/* cursor's x position */
+		__u16 orig_y;	/* cursor's y position */
+	} console_info;
+	__u64 fpswa;		/* physical address of the fpswa interface */
+	__u64 initrd_start;
+	__u64 initrd_size;
+} *ia64_boot_param;
+
 #endif
diff --git a/arch/ia64/include/asm/sn/pda.h b/arch/ia64/include/asm/sn/pda.h
index 1c5108d44d8b..22ae358c8d16 100644
--- a/arch/ia64/include/asm/sn/pda.h
+++ b/arch/ia64/include/asm/sn/pda.h
@@ -10,7 +10,6 @@
 
 #include <linux/cache.h>
 #include <asm/percpu.h>
-#include <asm/system.h>
 
 
 /*
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index b77768d35f93..54ff557d474e 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -15,7 +15,6 @@
 
 #include <linux/atomic.h>
 #include <asm/intrinsics.h>
-#include <asm/system.h>
 
 #define arch_spin_lock_init(x)			((x)->lock = 0)
 
diff --git a/arch/ia64/include/asm/switch_to.h b/arch/ia64/include/asm/switch_to.h
new file mode 100644
index 000000000000..cb2412fcd17f
--- /dev/null
+++ b/arch/ia64/include/asm/switch_to.h
@@ -0,0 +1,87 @@
+/*
+ * Low-level task switching. This is based on information published in
+ * the Processor Abstraction Layer and the System Abstraction Layer
+ * manual.
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ */
+#ifndef _ASM_IA64_SWITCH_TO_H
+#define _ASM_IA64_SWITCH_TO_H
+
+#include <linux/percpu.h>
+
+struct task_struct;
+
+/*
+ * Context switch from one thread to another.  If the two threads have
+ * different address spaces, schedule() has already taken care of
+ * switching to the new address space by calling switch_mm().
+ *
+ * Disabling access to the fph partition and the debug-register
+ * context switch MUST be done before calling ia64_switch_to() since a
+ * newly created thread returns directly to
+ * ia64_ret_from_syscall_clear_r8.
+ */
+extern struct task_struct *ia64_switch_to (void *next_task);
+
+extern void ia64_save_extra (struct task_struct *task);
+extern void ia64_load_extra (struct task_struct *task);
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct *next);
+# define IA64_ACCOUNT_ON_SWITCH(p,n) ia64_account_on_switch(p,n)
+#else
+# define IA64_ACCOUNT_ON_SWITCH(p,n)
+#endif
+
+#ifdef CONFIG_PERFMON
+  DECLARE_PER_CPU(unsigned long, pfm_syst_info);
+# define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
+#else
+# define PERFMON_IS_SYSWIDE() (0)
+#endif
+
+#define IA64_HAS_EXTRA_STATE(t)							\
+	((t)->thread.flags & (IA64_THREAD_DBG_VALID|IA64_THREAD_PM_VALID)	\
+	 || PERFMON_IS_SYSWIDE())
+
+#define __switch_to(prev,next,last) do {							 \
+	IA64_ACCOUNT_ON_SWITCH(prev, next);							 \
+	if (IA64_HAS_EXTRA_STATE(prev))								 \
+		ia64_save_extra(prev);								 \
+	if (IA64_HAS_EXTRA_STATE(next))								 \
+		ia64_load_extra(next);								 \
+	ia64_psr(task_pt_regs(next))->dfh = !ia64_is_local_fpu_owner(next);			 \
+	(last) = ia64_switch_to((next));							 \
+} while (0)
+
+#ifdef CONFIG_SMP
+/*
+ * In the SMP case, we save the fph state when context-switching away from a thread that
+ * modified fph.  This way, when the thread gets scheduled on another CPU, the CPU can
+ * pick up the state from task->thread.fph, avoiding the complication of having to fetch
+ * the latest fph state from another CPU.  In other words: eager save, lazy restore.
+ */
+# define switch_to(prev,next,last) do {						\
+	if (ia64_psr(task_pt_regs(prev))->mfh && ia64_is_local_fpu_owner(prev)) {				\
+		ia64_psr(task_pt_regs(prev))->mfh = 0;			\
+		(prev)->thread.flags |= IA64_THREAD_FPH_VALID;			\
+		__ia64_save_fpu((prev)->thread.fph);				\
+	}									\
+	__switch_to(prev, next, last);						\
+	/* "next" in old context is "current" in new context */			\
+	if (unlikely((current->thread.flags & IA64_THREAD_MIGRATION) &&	       \
+		     (task_cpu(current) !=				       \
+		      		      task_thread_info(current)->last_cpu))) { \
+		platform_migrate(current);				       \
+		task_thread_info(current)->last_cpu = task_cpu(current);       \
+	}								       \
+} while (0)
+#else
+# define switch_to(prev,next,last)	__switch_to(prev, next, last)
+#endif
+
+#endif /* _ASM_IA64_SWITCH_TO_H */
diff --git a/arch/ia64/include/asm/system.h b/arch/ia64/include/asm/system.h
deleted file mode 100644
index 6cca30705d50..000000000000
--- a/arch/ia64/include/asm/system.h
+++ /dev/null
@@ -1,203 +0,0 @@
-#ifndef _ASM_IA64_SYSTEM_H
-#define _ASM_IA64_SYSTEM_H
-
-/*
- * System defines. Note that this is included both from .c and .S
- * files, so it does only defines, not any C code.  This is based
- * on information published in the Processor Abstraction Layer
- * and the System Abstraction Layer manual.
- *
- * Copyright (C) 1998-2003 Hewlett-Packard Co
- *	David Mosberger-Tang <davidm@hpl.hp.com>
- * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
- * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
- */
-
-#include <asm/kregs.h>
-#include <asm/page.h>
-#include <asm/pal.h>
-#include <asm/percpu.h>
-
-#define GATE_ADDR		RGN_BASE(RGN_GATE)
-
-/*
- * 0xa000000000000000+2*PERCPU_PAGE_SIZE
- * - 0xa000000000000000+3*PERCPU_PAGE_SIZE remain unmapped (guard page)
- */
-#define KERNEL_START		 (GATE_ADDR+__IA64_UL_CONST(0x100000000))
-#define PERCPU_ADDR		(-PERCPU_PAGE_SIZE)
-#define LOAD_OFFSET		(KERNEL_START - KERNEL_TR_PAGE_SIZE)
-
-#ifndef __ASSEMBLY__
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-
-#define AT_VECTOR_SIZE_ARCH 2 /* entries in ARCH_DLINFO */
-
-struct pci_vector_struct {
-	__u16 segment;	/* PCI Segment number */
-	__u16 bus;	/* PCI Bus number */
-	__u32 pci_id;	/* ACPI split 16 bits device, 16 bits function (see section 6.1.1) */
-	__u8 pin;	/* PCI PIN (0 = A, 1 = B, 2 = C, 3 = D) */
-	__u32 irq;	/* IRQ assigned */
-};
-
-extern struct ia64_boot_param {
-	__u64 command_line;		/* physical address of command line arguments */
-	__u64 efi_systab;		/* physical address of EFI system table */
-	__u64 efi_memmap;		/* physical address of EFI memory map */
-	__u64 efi_memmap_size;		/* size of EFI memory map */
-	__u64 efi_memdesc_size;		/* size of an EFI memory map descriptor */
-	__u32 efi_memdesc_version;	/* memory descriptor version */
-	struct {
-		__u16 num_cols;	/* number of columns on console output device */
-		__u16 num_rows;	/* number of rows on console output device */
-		__u16 orig_x;	/* cursor's x position */
-		__u16 orig_y;	/* cursor's y position */
-	} console_info;
-	__u64 fpswa;		/* physical address of the fpswa interface */
-	__u64 initrd_start;
-	__u64 initrd_size;
-} *ia64_boot_param;
-
-/*
- * Macros to force memory ordering.  In these descriptions, "previous"
- * and "subsequent" refer to program order; "visible" means that all
- * architecturally visible effects of a memory access have occurred
- * (at a minimum, this means the memory has been read or written).
- *
- *   wmb():	Guarantees that all preceding stores to memory-
- *		like regions are visible before any subsequent
- *		stores and that all following stores will be
- *		visible only after all previous stores.
- *   rmb():	Like wmb(), but for reads.
- *   mb():	wmb()/rmb() combo, i.e., all previous memory
- *		accesses are visible before all subsequent
- *		accesses and vice versa.  This is also known as
- *		a "fence."
- *
- * Note: "mb()" and its variants cannot be used as a fence to order
- * accesses to memory mapped I/O registers.  For that, mf.a needs to
- * be used.  However, we don't want to always use mf.a because (a)
- * it's (presumably) much slower than mf and (b) mf.a is supported for
- * sequential memory pages only.
- */
-#define mb()	ia64_mf()
-#define rmb()	mb()
-#define wmb()	mb()
-#define read_barrier_depends()	do { } while(0)
-
-#ifdef CONFIG_SMP
-# define smp_mb()	mb()
-# define smp_rmb()	rmb()
-# define smp_wmb()	wmb()
-# define smp_read_barrier_depends()	read_barrier_depends()
-#else
-# define smp_mb()	barrier()
-# define smp_rmb()	barrier()
-# define smp_wmb()	barrier()
-# define smp_read_barrier_depends()	do { } while(0)
-#endif
-
-/*
- * XXX check on this ---I suspect what Linus really wants here is
- * acquire vs release semantics but we can't discuss this stuff with
- * Linus just yet.  Grrr...
- */
-#define set_mb(var, value)	do { (var) = (value); mb(); } while (0)
-
-/*
- * The group barrier in front of the rsm & ssm are necessary to ensure
- * that none of the previous instructions in the same group are
- * affected by the rsm/ssm.
- */
-
-#ifdef __KERNEL__
-
-/*
- * Context switch from one thread to another.  If the two threads have
- * different address spaces, schedule() has already taken care of
- * switching to the new address space by calling switch_mm().
- *
- * Disabling access to the fph partition and the debug-register
- * context switch MUST be done before calling ia64_switch_to() since a
- * newly created thread returns directly to
- * ia64_ret_from_syscall_clear_r8.
- */
-extern struct task_struct *ia64_switch_to (void *next_task);
-
-struct task_struct;
-
-extern void ia64_save_extra (struct task_struct *task);
-extern void ia64_load_extra (struct task_struct *task);
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct *next);
-# define IA64_ACCOUNT_ON_SWITCH(p,n) ia64_account_on_switch(p,n)
-#else
-# define IA64_ACCOUNT_ON_SWITCH(p,n)
-#endif
-
-#ifdef CONFIG_PERFMON
-  DECLARE_PER_CPU(unsigned long, pfm_syst_info);
-# define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
-#else
-# define PERFMON_IS_SYSWIDE() (0)
-#endif
-
-#define IA64_HAS_EXTRA_STATE(t)							\
-	((t)->thread.flags & (IA64_THREAD_DBG_VALID|IA64_THREAD_PM_VALID)	\
-	 || PERFMON_IS_SYSWIDE())
-
-#define __switch_to(prev,next,last) do {							 \
-	IA64_ACCOUNT_ON_SWITCH(prev, next);							 \
-	if (IA64_HAS_EXTRA_STATE(prev))								 \
-		ia64_save_extra(prev);								 \
-	if (IA64_HAS_EXTRA_STATE(next))								 \
-		ia64_load_extra(next);								 \
-	ia64_psr(task_pt_regs(next))->dfh = !ia64_is_local_fpu_owner(next);			 \
-	(last) = ia64_switch_to((next));							 \
-} while (0)
-
-#ifdef CONFIG_SMP
-/*
- * In the SMP case, we save the fph state when context-switching away from a thread that
- * modified fph.  This way, when the thread gets scheduled on another CPU, the CPU can
- * pick up the state from task->thread.fph, avoiding the complication of having to fetch
- * the latest fph state from another CPU.  In other words: eager save, lazy restore.
- */
-# define switch_to(prev,next,last) do {						\
-	if (ia64_psr(task_pt_regs(prev))->mfh && ia64_is_local_fpu_owner(prev)) {				\
-		ia64_psr(task_pt_regs(prev))->mfh = 0;			\
-		(prev)->thread.flags |= IA64_THREAD_FPH_VALID;			\
-		__ia64_save_fpu((prev)->thread.fph);				\
-	}									\
-	__switch_to(prev, next, last);						\
-	/* "next" in old context is "current" in new context */			\
-	if (unlikely((current->thread.flags & IA64_THREAD_MIGRATION) &&	       \
-		     (task_cpu(current) !=				       \
-		      		      task_thread_info(current)->last_cpu))) { \
-		platform_migrate(current);				       \
-		task_thread_info(current)->last_cpu = task_cpu(current);       \
-	}								       \
-} while (0)
-#else
-# define switch_to(prev,next,last)	__switch_to(prev, next, last)
-#endif
-
-#define __ARCH_WANT_UNLOCKED_CTXSW
-#define ARCH_HAS_PREFETCH_SWITCH_STACK
-#define ia64_platform_is(x) (strcmp(x, platform_name) == 0)
-
-void cpu_idle_wait(void);
-
-#define arch_align_stack(x) (x)
-
-void default_idle(void);
-
-#endif /* __KERNEL__ */
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_IA64_SYSTEM_H */
diff --git a/arch/ia64/include/asm/uv/uv.h b/arch/ia64/include/asm/uv/uv.h
index 61b5bdfd980e..8f6cbaa742e9 100644
--- a/arch/ia64/include/asm/uv/uv.h
+++ b/arch/ia64/include/asm/uv/uv.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_IA64_UV_UV_H
 #define _ASM_IA64_UV_UV_H
 
-#include <asm/system.h>
 #include <asm/sn/simulator.h>
 
 static inline int is_uv_system(void)
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 2d801bfe16ac..6f38b6120d96 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -50,7 +50,6 @@
 #include <asm/iosapic.h>
 #include <asm/machvec.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/numa.h>
 #include <asm/sal.h>
 #include <asm/cyclone.h>
@@ -840,11 +839,11 @@ static __init int setup_additional_cpus(char *s)
 early_param("additional_cpus", setup_additional_cpus);
 
 /*
- * cpu_possible_map should be static, it cannot change as CPUs
+ * cpu_possible_mask should be static, it cannot change as CPUs
  * are onlined, or offlined. The reason is per-cpu data-structures
  * are allocated by some modules at init time, and dont expect to
  * do this dynamically on cpu arrival/departure.
- * cpu_present_map on the other hand can change dynamically.
+ * cpu_present_mask on the other hand can change dynamically.
  * In case when cpu_hotplug is not compiled, then we resort to current
  * behaviour, which is cpu_possible == cpu_present.
  * - Ashok Raj
@@ -922,7 +921,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
 
 	acpi_map_cpu2node(handle, cpu, physid);
 
-	cpu_set(cpu, cpu_present_map);
+	set_cpu_present(cpu, true);
 	ia64_cpu_to_sapicid[cpu] = physid;
 
 	acpi_processor_set_pdc(handle);
@@ -941,7 +940,7 @@ EXPORT_SYMBOL(acpi_map_lsapic);
 int acpi_unmap_lsapic(int cpu)
 {
 	ia64_cpu_to_sapicid[cpu] = -1;
-	cpu_clear(cpu, cpu_present_map);
+	set_cpu_present(cpu, false);
 
 #ifdef CONFIG_ACPI_NUMA
 	/* NUMA specific cleanup's */
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index af5650169043..a48bd9a9927b 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -269,8 +269,8 @@ void foo(void)
 	BLANK();
 
 	/* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */
-	DEFINE(IA64_GTOD_LOCK_OFFSET,
-		offsetof (struct fsyscall_gtod_data_t, lock));
+	DEFINE(IA64_GTOD_SEQ_OFFSET,
+	       offsetof (struct fsyscall_gtod_data_t, seq));
 	DEFINE(IA64_GTOD_WALL_TIME_OFFSET,
 		offsetof (struct fsyscall_gtod_data_t, wall_time));
 	DEFINE(IA64_GTOD_MONO_TIME_OFFSET,
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index c38d22e5e902..d37bbd48637f 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -39,6 +39,7 @@
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/mca.h>
+#include <asm/setup.h>
 #include <asm/tlbflush.h>
 
 #define EFI_DEBUG	0
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index 331d42bda77a..cc26edac0ec6 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -21,7 +21,6 @@
 #include <asm/thread_info.h>
 #include <asm/sal.h>
 #include <asm/signal.h>
-#include <asm/system.h>
 #include <asm/unistd.h>
 
 #include "entry.h"
@@ -174,7 +173,7 @@ ENTRY(fsys_set_tid_address)
 	FSYS_RETURN
 END(fsys_set_tid_address)
 
-#if IA64_GTOD_LOCK_OFFSET !=0
+#if IA64_GTOD_SEQ_OFFSET !=0
 #error fsys_gettimeofday incompatible with changes to struct fsyscall_gtod_data_t
 #endif
 #if IA64_ITC_JITTER_OFFSET !=0
diff --git a/arch/ia64/kernel/fsyscall_gtod_data.h b/arch/ia64/kernel/fsyscall_gtod_data.h
index 57d2ee6c83e1..146b15b5fec3 100644
--- a/arch/ia64/kernel/fsyscall_gtod_data.h
+++ b/arch/ia64/kernel/fsyscall_gtod_data.h
@@ -6,7 +6,7 @@
  */
 
 struct fsyscall_gtod_data_t {
-	seqlock_t	lock;
+	seqcount_t	seq;
 	struct timespec	wall_time;
 	struct timespec monotonic_time;
 	cycle_t		clk_mask;
diff --git a/arch/ia64/kernel/gate.S b/arch/ia64/kernel/gate.S
index 245d3e1ec7e1..b5f8bdd8618e 100644
--- a/arch/ia64/kernel/gate.S
+++ b/arch/ia64/kernel/gate.S
@@ -11,8 +11,9 @@
 #include <asm/errno.h>
 #include <asm/asm-offsets.h>
 #include <asm/sigcontext.h>
-#include <asm/system.h>
 #include <asm/unistd.h>
+#include <asm/kregs.h>
+#include <asm/page.h>
 #include "paravirt_inst.h"
 
 /*
diff --git a/arch/ia64/kernel/gate.lds.S b/arch/ia64/kernel/gate.lds.S
index d32b0855110a..e518f7902af6 100644
--- a/arch/ia64/kernel/gate.lds.S
+++ b/arch/ia64/kernel/gate.lds.S
@@ -5,8 +5,7 @@
  * its layout.
  */
 
-
-#include <asm/system.h>
+#include <asm/page.h>
 #include "paravirt_patchlist.h"
 
 SECTIONS
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 17a9fba38930..629a250f7c19 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -30,7 +30,6 @@
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/mca_asm.h>
 #include <linux/init.h>
 #include <linux/linkage.h>
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index b0f9afebb146..ef4b5d877cf2 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -98,7 +98,6 @@
 #include <asm/machvec.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 #undef DEBUG_INTERRUPT_ROUTING
 
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 782c3a357f24..5c3e0888265a 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -39,7 +39,6 @@
 #include <asm/hw_irq.h>
 #include <asm/machvec.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 
 #ifdef CONFIG_PERFMON
@@ -118,7 +117,7 @@ static inline int find_unassigned_vector(cpumask_t domain)
 	cpumask_t mask;
 	int pos, vector;
 
-	cpus_and(mask, domain, cpu_online_map);
+	cpumask_and(&mask, &domain, cpu_online_mask);
 	if (cpus_empty(mask))
 		return -EINVAL;
 
@@ -141,7 +140,7 @@ static int __bind_irq_vector(int irq, int vector, cpumask_t domain)
 	BUG_ON((unsigned)irq >= NR_IRQS);
 	BUG_ON((unsigned)vector >= IA64_NUM_VECTORS);
 
-	cpus_and(mask, domain, cpu_online_map);
+	cpumask_and(&mask, &domain, cpu_online_mask);
 	if (cpus_empty(mask))
 		return -EINVAL;
 	if ((cfg->vector == vector) && cpus_equal(cfg->domain, domain))
@@ -179,7 +178,7 @@ static void __clear_irq_vector(int irq)
 	BUG_ON(cfg->vector == IRQ_VECTOR_UNASSIGNED);
 	vector = cfg->vector;
 	domain = cfg->domain;
-	cpus_and(mask, cfg->domain, cpu_online_map);
+	cpumask_and(&mask, &cfg->domain, cpu_online_mask);
 	for_each_cpu_mask(cpu, mask)
 		per_cpu(vector_irq, cpu)[vector] = -1;
 	cfg->vector = IRQ_VECTOR_UNASSIGNED;
@@ -322,7 +321,7 @@ void irq_complete_move(unsigned irq)
 	if (unlikely(cpu_isset(smp_processor_id(), cfg->old_domain)))
 		return;
 
-	cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+	cpumask_and(&cleanup_mask, &cfg->old_domain, cpu_online_mask);
 	cfg->move_cleanup_count = cpus_weight(cleanup_mask);
 	for_each_cpu_mask(i, cleanup_mask)
 		platform_send_ipi(i, IA64_IRQ_MOVE_VECTOR, IA64_IPI_DM_INT, 0);
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index d93e396bf599..fa25689fc453 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -54,7 +54,6 @@
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 #include <asm/errno.h>
diff --git a/arch/ia64/kernel/machvec.c b/arch/ia64/kernel/machvec.c
index d41a40ef80c0..f5a1e5246b3e 100644
--- a/arch/ia64/kernel/machvec.c
+++ b/arch/ia64/kernel/machvec.c
@@ -1,7 +1,6 @@
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
 #include <asm/machvec.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_IA64_GENERIC
 
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 8192009cb924..65bf9cd39044 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -92,7 +92,6 @@
 #include <asm/meminit.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/sal.h>
 #include <asm/mca.h>
 #include <asm/kexec.h>
@@ -1515,7 +1514,8 @@ static void
 ia64_mca_cmc_poll (unsigned long dummy)
 {
 	/* Trigger a CMC interrupt cascade  */
-	platform_send_ipi(first_cpu(cpu_online_map), IA64_CMCP_VECTOR, IA64_IPI_DM_INT, 0);
+	platform_send_ipi(cpumask_first(cpu_online_mask), IA64_CMCP_VECTOR,
+							IA64_IPI_DM_INT, 0);
 }
 
 /*
@@ -1591,7 +1591,8 @@ static void
 ia64_mca_cpe_poll (unsigned long dummy)
 {
 	/* Trigger a CPE interrupt cascade  */
-	platform_send_ipi(first_cpu(cpu_online_map), IA64_CPEP_VECTOR, IA64_IPI_DM_INT, 0);
+	platform_send_ipi(cpumask_first(cpu_online_mask), IA64_CPEP_VECTOR,
+							IA64_IPI_DM_INT, 0);
 }
 
 #endif /* CONFIG_ACPI */
diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c
index 09b4d6828c45..1c2e89406721 100644
--- a/arch/ia64/kernel/mca_drv.c
+++ b/arch/ia64/kernel/mca_drv.c
@@ -28,7 +28,6 @@
 #include <asm/machvec.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/sal.h>
 #include <asm/mca.h>
 
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 94e0db72d4a6..fb2f1e622877 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -57,7 +57,7 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 		return irq;
 
 	irq_set_msi_desc(irq, desc);
-	cpus_and(mask, irq_to_domain(irq), cpu_online_map);
+	cpumask_and(&mask, &(irq_to_domain(irq)), cpu_online_mask);
 	dest_phys_id = cpu_physical_id(first_cpu(mask));
 	vector = irq_to_vector(irq);
 
@@ -179,7 +179,7 @@ msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 	unsigned dest;
 	cpumask_t mask;
 
-	cpus_and(mask, irq_to_domain(irq), cpu_online_map);
+	cpumask_and(&mask, &(irq_to_domain(irq)), cpu_online_mask);
 	dest = cpu_physical_id(first_cpu(mask));
 
 	msg->address_hi = 0;
diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c
index 68a1311db806..1cf091793714 100644
--- a/arch/ia64/kernel/patch.c
+++ b/arch/ia64/kernel/patch.c
@@ -11,7 +11,6 @@
 #include <asm/patch.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/unistd.h>
 
 /*
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index eb1175720050..7cdc89b2483c 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/arch/ia64/kernel/pci-dma.c
@@ -12,7 +12,6 @@
 #include <asm/machvec.h>
 #include <linux/dma-mapping.h>
 
-#include <asm/system.h>
 
 #ifdef CONFIG_INTEL_IOMMU
 
diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c
index d9485d952ed0..939260aeac98 100644
--- a/arch/ia64/kernel/pci-swiotlb.c
+++ b/arch/ia64/kernel/pci-swiotlb.c
@@ -15,16 +15,24 @@ int swiotlb __read_mostly;
 EXPORT_SYMBOL(swiotlb);
 
 static void *ia64_swiotlb_alloc_coherent(struct device *dev, size_t size,
-					 dma_addr_t *dma_handle, gfp_t gfp)
+					 dma_addr_t *dma_handle, gfp_t gfp,
+					 struct dma_attrs *attrs)
 {
 	if (dev->coherent_dma_mask != DMA_BIT_MASK(64))
 		gfp |= GFP_DMA;
 	return swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
 }
 
+static void ia64_swiotlb_free_coherent(struct device *dev, size_t size,
+				       void *vaddr, dma_addr_t dma_addr,
+				       struct dma_attrs *attrs)
+{
+	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
+
 struct dma_map_ops swiotlb_dma_ops = {
-	.alloc_coherent = ia64_swiotlb_alloc_coherent,
-	.free_coherent = swiotlb_free_coherent,
+	.alloc = ia64_swiotlb_alloc_coherent,
+	.free = ia64_swiotlb_free_coherent,
 	.map_page = swiotlb_map_page,
 	.unmap_page = swiotlb_unmap_page,
 	.map_sg = swiotlb_map_sg_attrs,
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index b2c65e034f5d..9d0fd7d5bb82 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -49,7 +49,6 @@
 #include <asm/perfmon.h>
 #include <asm/processor.h>
 #include <asm/signal.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/delay.h>
 
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 9dc52b63fc87..ce74e143aea3 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -38,6 +38,7 @@
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/sal.h>
+#include <asm/switch_to.h>
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
 #include <asm/unwind.h>
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index dad91661ddf9..4265ff64219b 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -26,7 +26,6 @@
 #include <asm/processor.h>
 #include <asm/ptrace_offsets.h>
 #include <asm/rse.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/unwind.h>
 #ifdef CONFIG_PERFMON
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index cd57d7312de0..aaefd9b94f2f 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -59,7 +59,6 @@
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/unistd.h>
 #include <asm/hpsim.h>
@@ -486,7 +485,7 @@ mark_bsp_online (void)
 {
 #ifdef CONFIG_SMP
 	/* If we register an early console, allow CPU 0 to printk */
-	cpu_set(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), true);
 #endif
 }
 
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 0bd537b4ea6b..9fcd4e63048f 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -44,7 +44,6 @@
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/sal.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/unistd.h>
 #include <asm/mca.h>
@@ -77,7 +76,7 @@ stop_this_cpu(void)
 	/*
 	 * Remove this CPU:
 	 */
-	cpu_clear(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), false);
 	max_xtp();
 	local_irq_disable();
 	cpu_halt();
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 559097986672..796f6a5b966a 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -55,7 +55,6 @@
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/sal.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/unistd.h>
 #include <asm/sn/arch.h>
@@ -401,7 +400,7 @@ smp_callin (void)
 	/* Setup the per cpu irq handling data structures */
 	__setup_vector_irq(cpuid);
 	notify_cpu_starting(cpuid);
-	cpu_set(cpuid, cpu_online_map);
+	set_cpu_online(cpuid, true);
 	per_cpu(cpu_state, cpuid) = CPU_ONLINE;
 	spin_unlock(&vector_lock);
 	ipi_call_unlock_irq();
@@ -548,7 +547,7 @@ do_rest:
 	if (!cpu_isset(cpu, cpu_callin_map)) {
 		printk(KERN_ERR "Processor 0x%x/0x%x is stuck.\n", cpu, sapicid);
 		ia64_cpu_to_sapicid[cpu] = -1;
-		cpu_clear(cpu, cpu_online_map);  /* was set in smp_callin() */
+		set_cpu_online(cpu, false);  /* was set in smp_callin() */
 		return -EINVAL;
 	}
 	return 0;
@@ -578,8 +577,7 @@ smp_build_cpu_map (void)
 	}
 
 	ia64_cpu_to_sapicid[0] = boot_cpu_id;
-	cpus_clear(cpu_present_map);
-	set_cpu_present(0, true);
+	init_cpu_present(cpumask_of(0));
 	set_cpu_possible(0, true);
 	for (cpu = 1, i = 0; i < smp_boot_data.cpu_count; i++) {
 		sapicid = smp_boot_data.cpu_phys_id[i];
@@ -606,10 +604,6 @@ smp_prepare_cpus (unsigned int max_cpus)
 
 	smp_setup_percpu_timer();
 
-	/*
-	 * We have the boot CPU online for sure.
-	 */
-	cpu_set(0, cpu_online_map);
 	cpu_set(0, cpu_callin_map);
 
 	local_cpu_data->loops_per_jiffy = loops_per_jiffy;
@@ -633,7 +627,7 @@ smp_prepare_cpus (unsigned int max_cpus)
 
 void __devinit smp_prepare_boot_cpu(void)
 {
-	cpu_set(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), true);
 	cpu_set(smp_processor_id(), cpu_callin_map);
 	set_numa_node(cpu_to_node_map[smp_processor_id()]);
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
@@ -690,7 +684,7 @@ int migrate_platform_irqs(unsigned int cpu)
 			/*
 			 * Now re-target the CPEI to a different processor
 			 */
-			new_cpei_cpu = any_online_cpu(cpu_online_map);
+			new_cpei_cpu = cpumask_any(cpu_online_mask);
 			mask = cpumask_of(new_cpei_cpu);
 			set_cpei_target_cpu(new_cpei_cpu);
 			data = irq_get_irq_data(ia64_cpe_irq);
@@ -732,10 +726,10 @@ int __cpu_disable(void)
 			return -EBUSY;
 	}
 
-	cpu_clear(cpu, cpu_online_map);
+	set_cpu_online(cpu, false);
 
 	if (migrate_platform_irqs(cpu)) {
-		cpu_set(cpu, cpu_online_map);
+		set_cpu_online(cpu, true);
 		return -EBUSY;
 	}
 
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 43920de425f1..ecc904b33c5f 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -29,15 +29,12 @@
 #include <asm/ptrace.h>
 #include <asm/sal.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 
 #include "fsyscall_gtod_data.h"
 
 static cycle_t itc_get_cycles(struct clocksource *cs);
 
-struct fsyscall_gtod_data_t fsyscall_gtod_data = {
-	.lock = __SEQLOCK_UNLOCKED(fsyscall_gtod_data.lock),
-};
+struct fsyscall_gtod_data_t fsyscall_gtod_data;
 
 struct itc_jitter_data_t itc_jitter_data;
 
@@ -460,9 +457,7 @@ void update_vsyscall_tz(void)
 void update_vsyscall(struct timespec *wall, struct timespec *wtm,
 			struct clocksource *c, u32 mult)
 {
-        unsigned long flags;
-
-        write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags);
+	write_seqcount_begin(&fsyscall_gtod_data.seq);
 
         /* copy fsyscall clock data */
         fsyscall_gtod_data.clk_mask = c->mask;
@@ -485,6 +480,6 @@ void update_vsyscall(struct timespec *wall, struct timespec *wtm,
 		fsyscall_gtod_data.monotonic_time.tv_sec++;
 	}
 
-        write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags);
+	write_seqcount_end(&fsyscall_gtod_data.seq);
 }
 
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 9deb21dbf629..c64460b9c704 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -220,7 +220,8 @@ static ssize_t show_shared_cpu_map(struct cache_info *this_leaf, char *buf)
 	ssize_t	len;
 	cpumask_t shared_cpu_map;
 
-	cpus_and(shared_cpu_map, this_leaf->shared_cpu_map, cpu_online_map);
+	cpumask_and(&shared_cpu_map,
+				&this_leaf->shared_cpu_map, cpu_online_mask);
 	len = cpumask_scnprintf(buf, NR_CPUS+1, &shared_cpu_map);
 	len += sprintf(buf+len, "\n");
 	return len;
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index fd80e70018a9..bd42b76000d1 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -22,6 +22,7 @@
 #include <asm/intrinsics.h>
 #include <asm/processor.h>
 #include <asm/uaccess.h>
+#include <asm/setup.h>
 
 fpswa_interface_t *fpswa_interface;
 EXPORT_SYMBOL(fpswa_interface);
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index 6a867dc45c05..a96bcf83a735 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -23,7 +23,6 @@
 #include <linux/gfp.h>
 #include <asm/page.h>
 #include <asm/pal.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <linux/atomic.h>
 #include <asm/tlbflush.h>
diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c
index fed6afa2e8a9..8f66195999e7 100644
--- a/arch/ia64/kernel/unwind.c
+++ b/arch/ia64/kernel/unwind.c
@@ -41,7 +41,6 @@
 #include <asm/ptrace_offsets.h>
 #include <asm/rse.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "entry.h"
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 53c0ba004e9e..0ccb28fab27e 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -1,7 +1,6 @@
 
 #include <asm/cache.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 
 #include <asm-generic/vmlinux.lds.h>
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 405052002493..f5104b7c52cd 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -809,10 +809,13 @@ static void kvm_build_io_pmt(struct kvm *kvm)
 #define GUEST_PHYSICAL_RR4	0x2739
 #define VMM_INIT_RR		0x1660
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	BUG_ON(!kvm);
 
+	if (type)
+		return -EINVAL;
+
 	kvm->arch.is_sn2 = ia64_platform_is("sn2");
 
 	kvm->arch.metaphysical_rr0 = GUEST_PHYSICAL_RR0;
@@ -1169,6 +1172,11 @@ out:
 
 #define PALE_RESET_ENTRY    0x80000000ffffffb0UL
 
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
+{
+	return irqchip_in_kernel(vcpu->kcm) == (vcpu->arch.apic != NULL);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu *v;
@@ -1563,6 +1571,21 @@ out:
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		struct kvm_memory_slot *memslot,
 		struct kvm_memory_slot old,
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 20b359376128..02d29c2a132a 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -14,7 +14,6 @@
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 extern int die(char *, struct pt_regs *, long);
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 13df239dbed1..0eab454867a2 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -30,7 +30,6 @@
 #include <asm/pgalloc.h>
 #include <asm/sal.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/tlb.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
diff --git a/arch/ia64/oprofile/backtrace.c b/arch/ia64/oprofile/backtrace.c
index f7b798993cea..6a219a946050 100644
--- a/arch/ia64/oprofile/backtrace.c
+++ b/arch/ia64/oprofile/backtrace.c
@@ -14,7 +14,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 /*
  * For IA64 we need to perform a complex little dance to get both
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index d1ce3200147c..524df4295c90 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -24,7 +24,6 @@
 
 #include <asm/machvec.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/sal.h>
 #include <asm/smp.h>
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index 77db0b514fa4..f82e7b462b7b 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -33,9 +33,9 @@
 #include <asm/io.h>
 #include <asm/sal.h>
 #include <asm/machvec.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/vga.h>
+#include <asm/setup.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/pda.h>
diff --git a/arch/ia64/sn/kernel/sn2/prominfo_proc.c b/arch/ia64/sn/kernel/sn2/prominfo_proc.c
index e63328818643..20b88cb1881a 100644
--- a/arch/ia64/sn/kernel/sn2/prominfo_proc.c
+++ b/arch/ia64/sn/kernel/sn2/prominfo_proc.c
@@ -12,7 +12,6 @@
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/nodemask.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/sn/sn_sal.h>
 #include <asm/sn/sn_cpuid.h>
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index e884ba4e031d..68c845411624 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -26,7 +26,6 @@
 #include <asm/processor.h>
 #include <asm/irq.h>
 #include <asm/sal.h>
-#include <asm/system.h>
 #include <asm/delay.h>
 #include <asm/io.h>
 #include <asm/smp.h>
diff --git a/arch/ia64/sn/kernel/sn2/timer.c b/arch/ia64/sn/kernel/sn2/timer.c
index 0f8844e49363..abab8f99e913 100644
--- a/arch/ia64/sn/kernel/sn2/timer.c
+++ b/arch/ia64/sn/kernel/sn2/timer.c
@@ -14,7 +14,6 @@
 #include <linux/clocksource.h>
 
 #include <asm/hw_irq.h>
-#include <asm/system.h>
 #include <asm/timex.h>
 
 #include <asm/sn/leds.h>
diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c
index 2f406f509d44..14c1711238c0 100644
--- a/arch/ia64/sn/kernel/tiocx.c
+++ b/arch/ia64/sn/kernel/tiocx.c
@@ -14,7 +14,6 @@
 #include <linux/capability.h>
 #include <linux/device.h>
 #include <linux/delay.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/sn/sn_sal.h>
 #include <asm/sn/addrs.h>
diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
index a9d310de57da..3290d6e00c31 100644
--- a/arch/ia64/sn/pci/pci_dma.c
+++ b/arch/ia64/sn/pci/pci_dma.c
@@ -76,7 +76,8 @@ EXPORT_SYMBOL(sn_dma_set_mask);
  * more information.
  */
 static void *sn_dma_alloc_coherent(struct device *dev, size_t size,
-				   dma_addr_t * dma_handle, gfp_t flags)
+				   dma_addr_t * dma_handle, gfp_t flags,
+				   struct dma_attrs *attrs)
 {
 	void *cpuaddr;
 	unsigned long phys_addr;
@@ -137,7 +138,7 @@ static void *sn_dma_alloc_coherent(struct device *dev, size_t size,
  * any associated IOMMU mappings.
  */
 static void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-				 dma_addr_t dma_handle)
+				 dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
@@ -466,8 +467,8 @@ int sn_pci_legacy_write(struct pci_bus *bus, u16 port, u32 val, u8 size)
 }
 
 static struct dma_map_ops sn_dma_ops = {
-	.alloc_coherent		= sn_dma_alloc_coherent,
-	.free_coherent		= sn_dma_free_coherent,
+	.alloc			= sn_dma_alloc_coherent,
+	.free			= sn_dma_free_coherent,
 	.map_page		= sn_dma_map_page,
 	.unmap_page		= sn_dma_unmap_page,
 	.map_sg			= sn_dma_map_sg,
diff --git a/arch/ia64/xen/xensetup.S b/arch/ia64/xen/xensetup.S
index b820ed02ab9f..e29519ebe2d2 100644
--- a/arch/ia64/xen/xensetup.S
+++ b/arch/ia64/xen/xensetup.S
@@ -7,7 +7,6 @@
 #include <asm/processor.h>
 #include <asm/asmmacro.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/paravirt.h>
 #include <asm/xen/privop.h>
 #include <linux/elfnote.h>
diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h
index 1e7f29fb21f2..0d81697c326c 100644
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -11,7 +11,8 @@
 
 #include <linux/types.h>
 #include <asm/assembler.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
+#include <asm/dcache_clear.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
diff --git a/arch/m32r/include/asm/barrier.h b/arch/m32r/include/asm/barrier.h
new file mode 100644
index 000000000000..6976621efd3f
--- /dev/null
+++ b/arch/m32r/include/asm/barrier.h
@@ -0,0 +1,94 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001  Hiroyuki Kondo, Hirokazu Takata, and Hitoshi Yamamoto
+ * Copyright (C) 2004, 2006  Hirokazu Takata <takata at linux-m32r.org>
+ */
+#ifndef _ASM_M32R_BARRIER_H
+#define _ASM_M32R_BARRIER_H
+
+#define nop()  __asm__ __volatile__ ("nop" : : )
+
+/*
+ * Memory barrier.
+ *
+ * mb() prevents loads and stores being reordered across this point.
+ * rmb() prevents loads being reordered across this point.
+ * wmb() prevents stores being reordered across this point.
+ */
+#define mb()   barrier()
+#define rmb()  mb()
+#define wmb()  mb()
+
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier.  All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads.  This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies.  See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ *      CPU 0                           CPU 1
+ *
+ *      b = 2;
+ *      memory_barrier();
+ *      p = &b;                         q = p;
+ *                                      read_barrier_depends();
+ *                                      d = *q;
+ * </programlisting>
+ *
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends().  However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ *      CPU 0                           CPU 1
+ *
+ *      a = 2;
+ *      memory_barrier();
+ *      b = 3;                          y = b;
+ *                                      read_barrier_depends();
+ *                                      x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b".  Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
+ * in cases like this where there are no data dependencies.
+ **/
+
+#define read_barrier_depends()	do { } while (0)
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
+#define smp_read_barrier_depends()	read_barrier_depends()
+#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif
+
+#endif /* _ASM_M32R_BARRIER_H */
diff --git a/arch/m32r/include/asm/bitops.h b/arch/m32r/include/asm/bitops.h
index 6300f22cdbdb..d3dea9ac7d4e 100644
--- a/arch/m32r/include/asm/bitops.h
+++ b/arch/m32r/include/asm/bitops.h
@@ -16,9 +16,10 @@
 #endif
 
 #include <linux/compiler.h>
+#include <linux/irqflags.h>
 #include <asm/assembler.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
+#include <asm/dcache_clear.h>
 #include <asm/types.h>
 
 /*
diff --git a/arch/m32r/include/asm/cmpxchg.h b/arch/m32r/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..de651db20b43
--- /dev/null
+++ b/arch/m32r/include/asm/cmpxchg.h
@@ -0,0 +1,221 @@
+#ifndef _ASM_M32R_CMPXCHG_H
+#define _ASM_M32R_CMPXCHG_H
+
+/*
+ *  M32R version:
+ *    Copyright (C) 2001, 2002  Hitoshi Yamamoto
+ *    Copyright (C) 2004  Hirokazu Takata <takata at linux-m32r.org>
+ */
+
+#include <linux/irqflags.h>
+#include <asm/assembler.h>
+#include <asm/dcache_clear.h>
+
+extern void  __xchg_called_with_bad_pointer(void);
+
+static __always_inline unsigned long
+__xchg(unsigned long x, volatile void *ptr, int size)
+{
+	unsigned long flags;
+	unsigned long tmp = 0;
+
+	local_irq_save(flags);
+
+	switch (size) {
+#ifndef CONFIG_SMP
+	case 1:
+		__asm__ __volatile__ (
+			"ldb	%0, @%2 \n\t"
+			"stb	%1, @%2 \n\t"
+			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
+		break;
+	case 2:
+		__asm__ __volatile__ (
+			"ldh	%0, @%2 \n\t"
+			"sth	%1, @%2 \n\t"
+			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
+		break;
+	case 4:
+		__asm__ __volatile__ (
+			"ld	%0, @%2 \n\t"
+			"st	%1, @%2 \n\t"
+			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
+		break;
+#else  /* CONFIG_SMP */
+	case 4:
+		__asm__ __volatile__ (
+			DCACHE_CLEAR("%0", "r4", "%2")
+			"lock	%0, @%2;	\n\t"
+			"unlock	%1, @%2;	\n\t"
+			: "=&r" (tmp) : "r" (x), "r" (ptr)
+			: "memory"
+#ifdef CONFIG_CHIP_M32700_TS1
+			, "r4"
+#endif	/* CONFIG_CHIP_M32700_TS1 */
+		);
+		break;
+#endif  /* CONFIG_SMP */
+	default:
+		__xchg_called_with_bad_pointer();
+	}
+
+	local_irq_restore(flags);
+
+	return (tmp);
+}
+
+#define xchg(ptr, x)							\
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+
+static __always_inline unsigned long
+__xchg_local(unsigned long x, volatile void *ptr, int size)
+{
+	unsigned long flags;
+	unsigned long tmp = 0;
+
+	local_irq_save(flags);
+
+	switch (size) {
+	case 1:
+		__asm__ __volatile__ (
+			"ldb	%0, @%2 \n\t"
+			"stb	%1, @%2 \n\t"
+			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
+		break;
+	case 2:
+		__asm__ __volatile__ (
+			"ldh	%0, @%2 \n\t"
+			"sth	%1, @%2 \n\t"
+			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
+		break;
+	case 4:
+		__asm__ __volatile__ (
+			"ld	%0, @%2 \n\t"
+			"st	%1, @%2 \n\t"
+			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
+		break;
+	default:
+		__xchg_called_with_bad_pointer();
+	}
+
+	local_irq_restore(flags);
+
+	return (tmp);
+}
+
+#define xchg_local(ptr, x)						\
+	((__typeof__(*(ptr)))__xchg_local((unsigned long)(x), (ptr),	\
+			sizeof(*(ptr))))
+
+#define __HAVE_ARCH_CMPXCHG	1
+
+static inline unsigned long
+__cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new)
+{
+	unsigned long flags;
+	unsigned int retval;
+
+	local_irq_save(flags);
+	__asm__ __volatile__ (
+			DCACHE_CLEAR("%0", "r4", "%1")
+			M32R_LOCK" %0, @%1;	\n"
+		"	bne	%0, %2, 1f;	\n"
+			M32R_UNLOCK" %3, @%1;	\n"
+		"	bra	2f;		\n"
+                "       .fillinsn		\n"
+		"1:"
+			M32R_UNLOCK" %0, @%1;	\n"
+                "       .fillinsn		\n"
+		"2:"
+			: "=&r" (retval)
+			: "r" (p), "r" (old), "r" (new)
+			: "cbit", "memory"
+#ifdef CONFIG_CHIP_M32700_TS1
+			, "r4"
+#endif  /* CONFIG_CHIP_M32700_TS1 */
+		);
+	local_irq_restore(flags);
+
+	return retval;
+}
+
+static inline unsigned long
+__cmpxchg_local_u32(volatile unsigned int *p, unsigned int old,
+			unsigned int new)
+{
+	unsigned long flags;
+	unsigned int retval;
+
+	local_irq_save(flags);
+	__asm__ __volatile__ (
+			DCACHE_CLEAR("%0", "r4", "%1")
+			"ld %0, @%1;		\n"
+		"	bne	%0, %2, 1f;	\n"
+			"st %3, @%1;		\n"
+		"	bra	2f;		\n"
+		"       .fillinsn		\n"
+		"1:"
+			"st %0, @%1;		\n"
+		"       .fillinsn		\n"
+		"2:"
+			: "=&r" (retval)
+			: "r" (p), "r" (old), "r" (new)
+			: "cbit", "memory"
+#ifdef CONFIG_CHIP_M32700_TS1
+			, "r4"
+#endif  /* CONFIG_CHIP_M32700_TS1 */
+		);
+	local_irq_restore(flags);
+
+	return retval;
+}
+
+/* This function doesn't exist, so you'll get a linker error
+   if something tries to do an invalid cmpxchg().  */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32(ptr, old, new);
+#if 0	/* we don't have __cmpxchg_u64 */
+	case 8:
+		return __cmpxchg_u64(ptr, old, new);
+#endif /* 0 */
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						 \
+	((__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)(o),	 \
+			(unsigned long)(n), sizeof(*(ptr))))
+
+#include <asm-generic/cmpxchg-local.h>
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+				      unsigned long old,
+				      unsigned long new, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_local_u32(ptr, old, new);
+	default:
+		return __cmpxchg_local_generic(ptr, old, new, size);
+	}
+
+	return old;
+}
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	    \
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	    \
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#endif /* _ASM_M32R_CMPXCHG_H */
diff --git a/arch/m32r/include/asm/dcache_clear.h b/arch/m32r/include/asm/dcache_clear.h
new file mode 100644
index 000000000000..a0ae06c2e9e7
--- /dev/null
+++ b/arch/m32r/include/asm/dcache_clear.h
@@ -0,0 +1,29 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001  Hiroyuki Kondo, Hirokazu Takata, and Hitoshi Yamamoto
+ * Copyright (C) 2004, 2006  Hirokazu Takata <takata at linux-m32r.org>
+ */
+#ifndef _ASM_M32R_DCACHE_CLEAR_H
+#define _ASM_M32R_DCACHE_CLEAR_H
+
+#ifdef CONFIG_CHIP_M32700_TS1
+#define DCACHE_CLEAR(reg0, reg1, addr)				\
+	"seth	"reg1", #high(dcache_dummy);		\n\t"	\
+	"or3	"reg1", "reg1", #low(dcache_dummy);	\n\t"	\
+	"lock	"reg0", @"reg1";			\n\t"	\
+	"add3	"reg0", "addr", #0x1000;		\n\t"	\
+	"ld	"reg0", @"reg0";			\n\t"	\
+	"add3	"reg0", "addr", #0x2000;		\n\t"	\
+	"ld	"reg0", @"reg0";			\n\t"	\
+	"unlock	"reg0", @"reg1";			\n\t"
+	/* FIXME: This workaround code cannot handle kernel modules
+	 * correctly under SMP environment.
+	 */
+#else	/* CONFIG_CHIP_M32700_TS1 */
+#define DCACHE_CLEAR(reg0, reg1, addr)
+#endif	/* CONFIG_CHIP_M32700_TS1 */
+
+#endif /* _ASM_M32R_DCACHE_CLEAR_H */
diff --git a/arch/m32r/include/asm/exec.h b/arch/m32r/include/asm/exec.h
new file mode 100644
index 000000000000..c805dbd75b5d
--- /dev/null
+++ b/arch/m32r/include/asm/exec.h
@@ -0,0 +1,14 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001  Hiroyuki Kondo, Hirokazu Takata, and Hitoshi Yamamoto
+ * Copyright (C) 2004, 2006  Hirokazu Takata <takata at linux-m32r.org>
+ */
+#ifndef _ASM_M32R_EXEC_H
+#define _ASM_M32R_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _ASM_M32R_EXEC_H */
diff --git a/arch/m32r/include/asm/local.h b/arch/m32r/include/asm/local.h
index 734bca87018a..4045db3e4f65 100644
--- a/arch/m32r/include/asm/local.h
+++ b/arch/m32r/include/asm/local.h
@@ -12,7 +12,6 @@
 
 #include <linux/percpu.h>
 #include <asm/assembler.h>
-#include <asm/system.h>
 #include <asm/local.h>
 
 /*
diff --git a/arch/m32r/include/asm/posix_types.h b/arch/m32r/include/asm/posix_types.h
index b309c5858637..0195850e1f88 100644
--- a/arch/m32r/include/asm/posix_types.h
+++ b/arch/m32r/include/asm/posix_types.h
@@ -7,112 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef	__FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-
-#undef	__FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef	__FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif  /* _ASM_M32R_POSIX_TYPES_H */
diff --git a/arch/m32r/include/asm/spinlock.h b/arch/m32r/include/asm/spinlock.h
index b0ea2f26da3b..fa13694eaae3 100644
--- a/arch/m32r/include/asm/spinlock.h
+++ b/arch/m32r/include/asm/spinlock.h
@@ -11,6 +11,7 @@
 
 #include <linux/compiler.h>
 #include <linux/atomic.h>
+#include <asm/dcache_clear.h>
 #include <asm/page.h>
 
 /*
diff --git a/arch/m32r/include/asm/switch_to.h b/arch/m32r/include/asm/switch_to.h
new file mode 100644
index 000000000000..4b262f7a8fe9
--- /dev/null
+++ b/arch/m32r/include/asm/switch_to.h
@@ -0,0 +1,51 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001  Hiroyuki Kondo, Hirokazu Takata, and Hitoshi Yamamoto
+ * Copyright (C) 2004, 2006  Hirokazu Takata <takata at linux-m32r.org>
+ */
+#ifndef _ASM_M32R_SWITCH_TO_H
+#define _ASM_M32R_SWITCH_TO_H
+
+/*
+ * switch_to(prev, next) should switch from task `prev' to `next'
+ * `prev' will never be the same as `next'.
+ *
+ * `next' and `prev' should be struct task_struct, but it isn't always defined
+ */
+
+#if defined(CONFIG_FRAME_POINTER) || \
+	!defined(CONFIG_SCHED_OMIT_FRAME_POINTER)
+#define M32R_PUSH_FP "	push fp\n"
+#define M32R_POP_FP  "	pop  fp\n"
+#else
+#define M32R_PUSH_FP ""
+#define M32R_POP_FP  ""
+#endif
+
+#define switch_to(prev, next, last)  do { \
+	__asm__ __volatile__ ( \
+		"	seth	lr, #high(1f)				\n" \
+		"	or3	lr, lr, #low(1f)			\n" \
+		"	st	lr, @%4  ; store old LR			\n" \
+		"	ld	lr, @%5  ; load new LR			\n" \
+			M32R_PUSH_FP \
+		"	st	sp, @%2  ; store old SP			\n" \
+		"	ld	sp, @%3  ; load new SP			\n" \
+		"	push	%1  ; store `prev' on new stack		\n" \
+		"	jmp	lr					\n" \
+		"	.fillinsn					\n" \
+		"1:							\n" \
+		"	pop	%0  ; restore `__last' from new stack	\n" \
+			M32R_POP_FP \
+		: "=r" (last) \
+		: "0" (prev), \
+		  "r" (&(prev->thread.sp)), "r" (&(next->thread.sp)), \
+		  "r" (&(prev->thread.lr)), "r" (&(next->thread.lr)) \
+		: "memory", "lr" \
+	); \
+} while(0)
+
+#endif /* _ASM_M32R_SWITCH_TO_H */
diff --git a/arch/m32r/include/asm/system.h b/arch/m32r/include/asm/system.h
deleted file mode 100644
index 13c46794ccb1..000000000000
--- a/arch/m32r/include/asm/system.h
+++ /dev/null
@@ -1,367 +0,0 @@
-#ifndef _ASM_M32R_SYSTEM_H
-#define _ASM_M32R_SYSTEM_H
-
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001  Hiroyuki Kondo, Hirokazu Takata, and Hitoshi Yamamoto
- * Copyright (C) 2004, 2006  Hirokazu Takata <takata at linux-m32r.org>
- */
-
-#include <linux/compiler.h>
-#include <linux/irqflags.h>
-#include <asm/assembler.h>
-
-#ifdef __KERNEL__
-
-/*
- * switch_to(prev, next) should switch from task `prev' to `next'
- * `prev' will never be the same as `next'.
- *
- * `next' and `prev' should be struct task_struct, but it isn't always defined
- */
-
-#if defined(CONFIG_FRAME_POINTER) || \
-	!defined(CONFIG_SCHED_OMIT_FRAME_POINTER)
-#define M32R_PUSH_FP "	push fp\n"
-#define M32R_POP_FP  "	pop  fp\n"
-#else
-#define M32R_PUSH_FP ""
-#define M32R_POP_FP  ""
-#endif
-
-#define switch_to(prev, next, last)  do { \
-	__asm__ __volatile__ ( \
-		"	seth	lr, #high(1f)				\n" \
-		"	or3	lr, lr, #low(1f)			\n" \
-		"	st	lr, @%4  ; store old LR			\n" \
-		"	ld	lr, @%5  ; load new LR			\n" \
-			M32R_PUSH_FP \
-		"	st	sp, @%2  ; store old SP			\n" \
-		"	ld	sp, @%3  ; load new SP			\n" \
-		"	push	%1  ; store `prev' on new stack		\n" \
-		"	jmp	lr					\n" \
-		"	.fillinsn					\n" \
-		"1:							\n" \
-		"	pop	%0  ; restore `__last' from new stack	\n" \
-			M32R_POP_FP \
-		: "=r" (last) \
-		: "0" (prev), \
-		  "r" (&(prev->thread.sp)), "r" (&(next->thread.sp)), \
-		  "r" (&(prev->thread.lr)), "r" (&(next->thread.lr)) \
-		: "memory", "lr" \
-	); \
-} while(0)
-
-#define nop()	__asm__ __volatile__ ("nop" : : )
-
-#define xchg(ptr, x)							\
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-#define xchg_local(ptr, x)						\
-	((__typeof__(*(ptr)))__xchg_local((unsigned long)(x), (ptr),	\
-			sizeof(*(ptr))))
-
-extern void  __xchg_called_with_bad_pointer(void);
-
-#ifdef CONFIG_CHIP_M32700_TS1
-#define DCACHE_CLEAR(reg0, reg1, addr)				\
-	"seth	"reg1", #high(dcache_dummy);		\n\t"	\
-	"or3	"reg1", "reg1", #low(dcache_dummy);	\n\t"	\
-	"lock	"reg0", @"reg1";			\n\t"	\
-	"add3	"reg0", "addr", #0x1000;		\n\t"	\
-	"ld	"reg0", @"reg0";			\n\t"	\
-	"add3	"reg0", "addr", #0x2000;		\n\t"	\
-	"ld	"reg0", @"reg0";			\n\t"	\
-	"unlock	"reg0", @"reg1";			\n\t"
-	/* FIXME: This workaround code cannot handle kernel modules
-	 * correctly under SMP environment.
-	 */
-#else	/* CONFIG_CHIP_M32700_TS1 */
-#define DCACHE_CLEAR(reg0, reg1, addr)
-#endif	/* CONFIG_CHIP_M32700_TS1 */
-
-static __always_inline unsigned long
-__xchg(unsigned long x, volatile void *ptr, int size)
-{
-	unsigned long flags;
-	unsigned long tmp = 0;
-
-	local_irq_save(flags);
-
-	switch (size) {
-#ifndef CONFIG_SMP
-	case 1:
-		__asm__ __volatile__ (
-			"ldb	%0, @%2 \n\t"
-			"stb	%1, @%2 \n\t"
-			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
-		break;
-	case 2:
-		__asm__ __volatile__ (
-			"ldh	%0, @%2 \n\t"
-			"sth	%1, @%2 \n\t"
-			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
-		break;
-	case 4:
-		__asm__ __volatile__ (
-			"ld	%0, @%2 \n\t"
-			"st	%1, @%2 \n\t"
-			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
-		break;
-#else  /* CONFIG_SMP */
-	case 4:
-		__asm__ __volatile__ (
-			DCACHE_CLEAR("%0", "r4", "%2")
-			"lock	%0, @%2;	\n\t"
-			"unlock	%1, @%2;	\n\t"
-			: "=&r" (tmp) : "r" (x), "r" (ptr)
-			: "memory"
-#ifdef CONFIG_CHIP_M32700_TS1
-			, "r4"
-#endif	/* CONFIG_CHIP_M32700_TS1 */
-		);
-		break;
-#endif  /* CONFIG_SMP */
-	default:
-		__xchg_called_with_bad_pointer();
-	}
-
-	local_irq_restore(flags);
-
-	return (tmp);
-}
-
-static __always_inline unsigned long
-__xchg_local(unsigned long x, volatile void *ptr, int size)
-{
-	unsigned long flags;
-	unsigned long tmp = 0;
-
-	local_irq_save(flags);
-
-	switch (size) {
-	case 1:
-		__asm__ __volatile__ (
-			"ldb	%0, @%2 \n\t"
-			"stb	%1, @%2 \n\t"
-			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
-		break;
-	case 2:
-		__asm__ __volatile__ (
-			"ldh	%0, @%2 \n\t"
-			"sth	%1, @%2 \n\t"
-			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
-		break;
-	case 4:
-		__asm__ __volatile__ (
-			"ld	%0, @%2 \n\t"
-			"st	%1, @%2 \n\t"
-			: "=&r" (tmp) : "r" (x), "r" (ptr) : "memory");
-		break;
-	default:
-		__xchg_called_with_bad_pointer();
-	}
-
-	local_irq_restore(flags);
-
-	return (tmp);
-}
-
-#define __HAVE_ARCH_CMPXCHG	1
-
-static inline unsigned long
-__cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new)
-{
-	unsigned long flags;
-	unsigned int retval;
-
-	local_irq_save(flags);
-	__asm__ __volatile__ (
-			DCACHE_CLEAR("%0", "r4", "%1")
-			M32R_LOCK" %0, @%1;	\n"
-		"	bne	%0, %2, 1f;	\n"
-			M32R_UNLOCK" %3, @%1;	\n"
-		"	bra	2f;		\n"
-                "       .fillinsn		\n"
-		"1:"
-			M32R_UNLOCK" %0, @%1;	\n"
-                "       .fillinsn		\n"
-		"2:"
-			: "=&r" (retval)
-			: "r" (p), "r" (old), "r" (new)
-			: "cbit", "memory"
-#ifdef CONFIG_CHIP_M32700_TS1
-			, "r4"
-#endif  /* CONFIG_CHIP_M32700_TS1 */
-		);
-	local_irq_restore(flags);
-
-	return retval;
-}
-
-static inline unsigned long
-__cmpxchg_local_u32(volatile unsigned int *p, unsigned int old,
-			unsigned int new)
-{
-	unsigned long flags;
-	unsigned int retval;
-
-	local_irq_save(flags);
-	__asm__ __volatile__ (
-			DCACHE_CLEAR("%0", "r4", "%1")
-			"ld %0, @%1;		\n"
-		"	bne	%0, %2, 1f;	\n"
-			"st %3, @%1;		\n"
-		"	bra	2f;		\n"
-		"       .fillinsn		\n"
-		"1:"
-			"st %0, @%1;		\n"
-		"       .fillinsn		\n"
-		"2:"
-			: "=&r" (retval)
-			: "r" (p), "r" (old), "r" (new)
-			: "cbit", "memory"
-#ifdef CONFIG_CHIP_M32700_TS1
-			, "r4"
-#endif  /* CONFIG_CHIP_M32700_TS1 */
-		);
-	local_irq_restore(flags);
-
-	return retval;
-}
-
-/* This function doesn't exist, so you'll get a linker error
-   if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-static inline unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32(ptr, old, new);
-#if 0	/* we don't have __cmpxchg_u64 */
-	case 8:
-		return __cmpxchg_u64(ptr, old, new);
-#endif /* 0 */
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#define cmpxchg(ptr, o, n)						 \
-	((__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)(o),	 \
-			(unsigned long)(n), sizeof(*(ptr))))
-
-#include <asm-generic/cmpxchg-local.h>
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-				      unsigned long old,
-				      unsigned long new, int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_local_u32(ptr, old, new);
-	default:
-		return __cmpxchg_local_generic(ptr, old, new, size);
-	}
-
-	return old;
-}
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	    \
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	    \
-			(unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#endif  /* __KERNEL__ */
-
-/*
- * Memory barrier.
- *
- * mb() prevents loads and stores being reordered across this point.
- * rmb() prevents loads being reordered across this point.
- * wmb() prevents stores being reordered across this point.
- */
-#define mb()   barrier()
-#define rmb()  mb()
-#define wmb()  mb()
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *      CPU 0                           CPU 1
- *
- *      b = 2;
- *      memory_barrier();
- *      p = &b;                         q = p;
- *                                      read_barrier_depends();
- *                                      d = *q;
- * </programlisting>
- *
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *      CPU 0                           CPU 1
- *
- *      a = 2;
- *      memory_barrier();
- *      b = 3;                          y = b;
- *                                      read_barrier_depends();
- *                                      x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-#define arch_align_stack(x) (x)
-
-#endif /* _ASM_M32R_SYSTEM_H */
diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c
index 20743754f2b2..4c03361537aa 100644
--- a/arch/m32r/kernel/ptrace.c
+++ b/arch/m32r/kernel/ptrace.c
@@ -29,7 +29,6 @@
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
 
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index ee6a9199561c..3bcb207e5b6d 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -18,7 +18,6 @@
 #include <asm/page.h>
 #include <asm/processor.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/m32r/mm/fault-nommu.c b/arch/m32r/mm/fault-nommu.c
index 888aab1157ed..80f18cc6f547 100644
--- a/arch/m32r/mm/fault-nommu.c
+++ b/arch/m32r/mm/fault-nommu.c
@@ -22,7 +22,6 @@
 #include <linux/vt_kern.h>              /* For unblank_screen() */
 
 #include <asm/m32r.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 2c9aeb453847..3cdfa9c1d091 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -26,7 +26,6 @@
 #include <linux/module.h>
 
 #include <asm/m32r.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
diff --git a/arch/m32r/platforms/m32104ut/setup.c b/arch/m32r/platforms/m32104ut/setup.c
index 34671d32cefc..e2dd778aeac7 100644
--- a/arch/m32r/platforms/m32104ut/setup.c
+++ b/arch/m32r/platforms/m32104ut/setup.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/device.h>
 
-#include <asm/system.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 
diff --git a/arch/m32r/platforms/m32700ut/setup.c b/arch/m32r/platforms/m32700ut/setup.c
index 1053e1cb7401..9a4ba8a8589d 100644
--- a/arch/m32r/platforms/m32700ut/setup.c
+++ b/arch/m32r/platforms/m32700ut/setup.c
@@ -16,7 +16,6 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 
diff --git a/arch/m32r/platforms/mappi/setup.c b/arch/m32r/platforms/mappi/setup.c
index 35130ac3f8d1..767d2f4d6ded 100644
--- a/arch/m32r/platforms/mappi/setup.c
+++ b/arch/m32r/platforms/mappi/setup.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 
diff --git a/arch/m32r/platforms/mappi2/setup.c b/arch/m32r/platforms/mappi2/setup.c
index f3ed6b60a5f8..76d665abf51e 100644
--- a/arch/m32r/platforms/mappi2/setup.c
+++ b/arch/m32r/platforms/mappi2/setup.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 
diff --git a/arch/m32r/platforms/mappi3/setup.c b/arch/m32r/platforms/mappi3/setup.c
index 2408e356ad10..a3646d4b05bd 100644
--- a/arch/m32r/platforms/mappi3/setup.c
+++ b/arch/m32r/platforms/mappi3/setup.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 
diff --git a/arch/m32r/platforms/oaks32r/setup.c b/arch/m32r/platforms/oaks32r/setup.c
index 83b46b067a17..f8373c069524 100644
--- a/arch/m32r/platforms/oaks32r/setup.c
+++ b/arch/m32r/platforms/oaks32r/setup.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
-#include <asm/system.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 
diff --git a/arch/m32r/platforms/opsput/setup.c b/arch/m32r/platforms/opsput/setup.c
index 32660705f5fd..cd0170483e83 100644
--- a/arch/m32r/platforms/opsput/setup.c
+++ b/arch/m32r/platforms/opsput/setup.c
@@ -17,7 +17,6 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 
diff --git a/arch/m32r/platforms/usrv/setup.c b/arch/m32r/platforms/usrv/setup.c
index 0c7a1e8c77b0..dcde0ec777f6 100644
--- a/arch/m32r/platforms/usrv/setup.c
+++ b/arch/m32r/platforms/usrv/setup.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
-#include <asm/system.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 
diff --git a/arch/m68k/amiga/amisound.c b/arch/m68k/amiga/amisound.c
index 61e5c54625ae..2559eefc6aff 100644
--- a/arch/m68k/amiga/amisound.c
+++ b/arch/m68k/amiga/amisound.c
@@ -14,7 +14,6 @@
 #include <linux/string.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/amigahw.h>
 
 static unsigned short *snd_data;
diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index b95a451b1c3a..ee01b7a38e58 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -29,7 +29,6 @@
 
 #include <asm/bootinfo.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index 8d3eafab1ffe..0a30406b9442 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -9,7 +9,6 @@
 
 #include <asm/setup.h>
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/apollohw.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c
index 8048e1b7e552..783d8f02360d 100644
--- a/arch/m68k/atari/ataints.c
+++ b/arch/m68k/atari/ataints.c
@@ -42,7 +42,6 @@
 #include <linux/seq_file.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/traps.h>
 
 #include <asm/atarihw.h>
diff --git a/arch/m68k/atari/atasound.c b/arch/m68k/atari/atasound.c
index d266fe89c125..1c1181ebb947 100644
--- a/arch/m68k/atari/atasound.c
+++ b/arch/m68k/atari/atasound.c
@@ -25,7 +25,6 @@
 #include <linux/module.h>
 
 #include <asm/atarihw.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/pgtable.h>
 #include <asm/atariints.h>
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index c4ac15c4f065..d8eb32747ac5 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -39,7 +39,6 @@
 #include <asm/atarihw.h>
 #include <asm/atariints.h>
 #include <asm/atari_stram.h>
-#include <asm/system.h>
 #include <asm/machdep.h>
 #include <asm/hwtest.h>
 #include <asm/io.h>
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 81286476f740..0bf850a20ea2 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -28,7 +28,6 @@
 #include <linux/bcd.h>
 
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/bvme6000/rtc.c b/arch/m68k/bvme6000/rtc.c
index 1c4d4c7bf4d4..cf12a17dc289 100644
--- a/arch/m68k/bvme6000/rtc.c
+++ b/arch/m68k/bvme6000/rtc.c
@@ -21,7 +21,6 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/setup.h>
 
 /*
diff --git a/arch/m68k/hp300/time.c b/arch/m68k/hp300/time.c
index c87fe69b0728..29a71be9fa5b 100644
--- a/arch/m68k/hp300/time.c
+++ b/arch/m68k/hp300/time.c
@@ -15,7 +15,6 @@
 #include <asm/machdep.h>
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/blinken.h>
 
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 4eba796c00d4..f4e32de263a7 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -2,7 +2,8 @@
 #define __ARCH_M68K_ATOMIC__
 
 #include <linux/types.h>
-#include <asm/system.h>
+#include <linux/irqflags.h>
+#include <asm/cmpxchg.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h
new file mode 100644
index 000000000000..445ce22c23cb
--- /dev/null
+++ b/arch/m68k/include/asm/barrier.h
@@ -0,0 +1,20 @@
+#ifndef _M68K_BARRIER_H
+#define _M68K_BARRIER_H
+
+/*
+ * Force strict CPU ordering.
+ * Not really required on m68k...
+ */
+#define nop()		do { asm volatile ("nop"); barrier(); } while (0)
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#define read_barrier_depends()	((void)0)
+#define set_mb(var, value)	({ (var) = (value); wmb(); })
+
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	((void)0)
+
+#endif /* _M68K_BARRIER_H */
diff --git a/arch/m68k/include/asm/system.h b/arch/m68k/include/asm/cmpxchg.h
index 8dc68178716c..5c81d0eae5cf 100644
--- a/arch/m68k/include/asm/system.h
+++ b/arch/m68k/include/asm/cmpxchg.h
@@ -1,74 +1,13 @@
-#ifndef _M68K_SYSTEM_H
-#define _M68K_SYSTEM_H
+#ifndef __ARCH_M68K_CMPXCHG__
+#define __ARCH_M68K_CMPXCHG__
 
-#include <linux/linkage.h>
-#include <linux/kernel.h>
-#include <linux/bug.h>
 #include <linux/irqflags.h>
-#include <asm/segment.h>
-#include <asm/entry.h>
-
-#ifdef __KERNEL__
-
-/*
- * switch_to(n) should switch tasks to task ptr, first checking that
- * ptr isn't the current task, in which case it does nothing.  This
- * also clears the TS-flag if the task we switched to has used the
- * math co-processor latest.
- */
-/*
- * switch_to() saves the extra registers, that are not saved
- * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
- * a0-a1. Some of these are used by schedule() and its predecessors
- * and so we might get see unexpected behaviors when a task returns
- * with unexpected register values.
- *
- * syscall stores these registers itself and none of them are used
- * by syscall after the function in the syscall has been called.
- *
- * Beware that resume now expects *next to be in d1 and the offset of
- * tss to be in a1. This saves a few instructions as we no longer have
- * to push them onto the stack and read them back right after.
- *
- * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
- *
- * Changed 96/09/19 by Andreas Schwab
- * pass prev in a0, next in a1
- */
-asmlinkage void resume(void);
-#define switch_to(prev,next,last) do { \
-  register void *_prev __asm__ ("a0") = (prev); \
-  register void *_next __asm__ ("a1") = (next); \
-  register void *_last __asm__ ("d1"); \
-  __asm__ __volatile__("jbsr resume" \
-		       : "=a" (_prev), "=a" (_next), "=d" (_last) \
-		       : "0" (_prev), "1" (_next) \
-		       : "d0", "d2", "d3", "d4", "d5"); \
-  (last) = _last; \
-} while (0)
-
-
-/*
- * Force strict CPU ordering.
- * Not really required on m68k...
- */
-#define nop()		do { asm volatile ("nop"); barrier(); } while (0)
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define read_barrier_depends()	((void)0)
-#define set_mb(var, value)	({ (var) = (value); wmb(); })
-
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	((void)0)
-
-#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
 struct __xchg_dummy { unsigned long a[100]; };
 #define __xg(x) ((volatile struct __xchg_dummy *)(x))
 
+extern unsigned long __invalid_xchg_size(unsigned long, volatile void *, int);
+
 #ifndef CONFIG_RMW_INSNS
 static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
 {
@@ -93,7 +32,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 		x = tmp;
 		break;
 	default:
-		BUG();
+		tmp = __invalid_xchg_size(x, ptr, size);
+		break;
 	}
 
 	local_irq_restore(flags);
@@ -103,7 +43,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
 {
 	switch (size) {
-	    case 1:
+	case 1:
 		__asm__ __volatile__
 			("moveb %2,%0\n\t"
 			 "1:\n\t"
@@ -111,7 +51,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 			 "jne 1b"
 			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
 		break;
-	    case 2:
+	case 2:
 		__asm__ __volatile__
 			("movew %2,%0\n\t"
 			 "1:\n\t"
@@ -119,7 +59,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 			 "jne 1b"
 			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
 		break;
-	    case 4:
+	case 4:
 		__asm__ __volatile__
 			("movel %2,%0\n\t"
 			 "1:\n\t"
@@ -127,15 +67,23 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 			 "jne 1b"
 			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
 		break;
+	default:
+		x = __invalid_xchg_size(x, ptr, size);
+		break;
 	}
 	return x;
 }
 #endif
 
+#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
 #include <asm-generic/cmpxchg-local.h>
 
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
 
+extern unsigned long __invalid_cmpxchg_size(volatile void *,
+					    unsigned long, unsigned long, int);
+
 /*
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
  * store NEW in MEM.  Return the initial value in MEM.  Success is
@@ -163,6 +111,9 @@ static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
 				      : "=d" (old), "=m" (*(int *)p)
 				      : "d" (new), "0" (old), "m" (*(int *)p));
 		break;
+	default:
+		old = __invalid_cmpxchg_size(p, old, new, size);
+		break;
 	}
 	return old;
 }
@@ -187,8 +138,4 @@ static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
 
 #endif
 
-#define arch_align_stack(x) (x)
-
-#endif /* __KERNEL__ */
-
-#endif /* _M68K_SYSTEM_H */
+#endif /* __ARCH_M68K_CMPXCHG__ */
diff --git a/arch/m68k/include/asm/exec.h b/arch/m68k/include/asm/exec.h
new file mode 100644
index 000000000000..0499adf90230
--- /dev/null
+++ b/arch/m68k/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef _M68K_EXEC_H
+#define _M68K_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _M68K_EXEC_H */
diff --git a/arch/m68k/include/asm/posix_types.h b/arch/m68k/include/asm/posix_types.h
index 98d0970d9bad..6373093be72b 100644
--- a/arch/m68k/include/asm/posix_types.h
+++ b/arch/m68k/include/asm/posix_types.h
@@ -7,55 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
-typedef unsigned short	__kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
+#define __kernel_uid_t __kernel_uid_t
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-
-#undef	__FD_CLR
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-
-#undef	__FD_ISSET
-#define	__FD_ISSET(d, set)	(!!((set)->fds_bits[__FDELT(d)] & __FDMASK(d)))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp) (memset (fdsetp, 0, sizeof(*(fd_set *)fdsetp)))
+typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/m68k/include/asm/sun3xflop.h b/arch/m68k/include/asm/sun3xflop.h
index 32c45f84ac60..95231e2f9d64 100644
--- a/arch/m68k/include/asm/sun3xflop.h
+++ b/arch/m68k/include/asm/sun3xflop.h
@@ -11,7 +11,6 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/sun3x.h>
 
diff --git a/arch/m68k/include/asm/switch_to.h b/arch/m68k/include/asm/switch_to.h
new file mode 100644
index 000000000000..16fd6b634982
--- /dev/null
+++ b/arch/m68k/include/asm/switch_to.h
@@ -0,0 +1,41 @@
+#ifndef _M68K_SWITCH_TO_H
+#define _M68K_SWITCH_TO_H
+
+/*
+ * switch_to(n) should switch tasks to task ptr, first checking that
+ * ptr isn't the current task, in which case it does nothing.  This
+ * also clears the TS-flag if the task we switched to has used the
+ * math co-processor latest.
+ */
+/*
+ * switch_to() saves the extra registers, that are not saved
+ * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
+ * a0-a1. Some of these are used by schedule() and its predecessors
+ * and so we might get see unexpected behaviors when a task returns
+ * with unexpected register values.
+ *
+ * syscall stores these registers itself and none of them are used
+ * by syscall after the function in the syscall has been called.
+ *
+ * Beware that resume now expects *next to be in d1 and the offset of
+ * tss to be in a1. This saves a few instructions as we no longer have
+ * to push them onto the stack and read them back right after.
+ *
+ * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
+ *
+ * Changed 96/09/19 by Andreas Schwab
+ * pass prev in a0, next in a1
+ */
+asmlinkage void resume(void);
+#define switch_to(prev,next,last) do { \
+  register void *_prev __asm__ ("a0") = (prev); \
+  register void *_next __asm__ ("a1") = (next); \
+  register void *_last __asm__ ("d1"); \
+  __asm__ __volatile__("jbsr resume" \
+		       : "=a" (_prev), "=a" (_next), "=d" (_last) \
+		       : "0" (_prev), "1" (_next) \
+		       : "d0", "d2", "d3", "d4", "d5"); \
+  (last) = _last; \
+} while (0)
+
+#endif /* _M68K_SWITCH_TO_H */
diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c
index 74fefac00899..6b32b64bac35 100644
--- a/arch/m68k/kernel/ints.c
+++ b/arch/m68k/kernel/ints.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/traps.h>
 #include <asm/page.h>
diff --git a/arch/m68k/kernel/irq.c b/arch/m68k/kernel/irq.c
index c73988cfa90f..9ab4f550342e 100644
--- a/arch/m68k/kernel/irq.c
+++ b/arch/m68k/kernel/irq.c
@@ -15,7 +15,6 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/seq_file.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 asmlinkage void do_IRQ(int irq, struct pt_regs *regs)
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index c54ef927e483..c488e3cfab53 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -27,7 +27,6 @@
 #include <linux/mqueue.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/machdep.h>
 #include <asm/setup.h>
diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c
index 149a05f8b9ee..8b4a2222e658 100644
--- a/arch/m68k/kernel/ptrace.c
+++ b/arch/m68k/kernel/ptrace.c
@@ -23,7 +23,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 
 /*
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index daaa9187654c..388e5cc89599 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -32,7 +32,6 @@
 
 #include <asm/setup.h>
 #include <asm/fpu.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/traps.h>
 #include <asm/pgalloc.h>
diff --git a/arch/m68k/kernel/vectors.c b/arch/m68k/kernel/vectors.c
index 147b03fbc71e..322c977bb9ec 100644
--- a/arch/m68k/kernel/vectors.c
+++ b/arch/m68k/kernel/vectors.c
@@ -25,7 +25,6 @@
 
 #include <asm/setup.h>
 #include <asm/fpu.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 /* assembler routines */
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index f60ff5f59205..d9f62e0f46c0 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -30,7 +30,6 @@
 #include <asm/setup.h>
 #include <asm/bootinfo.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/pgtable.h>
@@ -981,6 +980,9 @@ int __init mac_platform_init(void)
 {
 	u8 *swim_base;
 
+	if (!MACH_IS_MAC)
+		return -ENODEV;
+
 	/*
 	 * Serial devices
 	 */
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index eb915551de69..5e085554ac7f 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -19,7 +19,6 @@
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/rtc.h>
-#include <asm/system.h>
 #include <asm/segment.h>
 #include <asm/setup.h>
 #include <asm/macintosh.h>
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 2db6099784ba..6b020a8461e7 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -13,7 +13,6 @@
 
 #include <asm/setup.h>
 #include <asm/traps.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 
diff --git a/arch/m68k/mm/init_mm.c b/arch/m68k/mm/init_mm.c
index 89f3b203814b..f77f258dce3a 100644
--- a/arch/m68k/mm/init_mm.c
+++ b/arch/m68k/mm/init_mm.c
@@ -23,7 +23,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
diff --git a/arch/m68k/mm/init_no.c b/arch/m68k/mm/init_no.c
index 1e33d39ca9a0..345ec0d83e3d 100644
--- a/arch/m68k/mm/init_no.c
+++ b/arch/m68k/mm/init_no.c
@@ -36,7 +36,6 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/machdep.h>
 
 /*
diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c
index 1cc2bed4c3dd..568cfad3ceb8 100644
--- a/arch/m68k/mm/kmap.c
+++ b/arch/m68k/mm/kmap.c
@@ -20,7 +20,6 @@
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #undef DEBUG
 
diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c
index a5dbb74fe1de..250b8b786f4f 100644
--- a/arch/m68k/mm/memory.c
+++ b/arch/m68k/mm/memory.c
@@ -17,7 +17,6 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/machdep.h>
 
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index 8b3db1c587fc..0dafa693515b 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -24,7 +24,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
-#include <asm/system.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
 #include <asm/dma.h>
diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c
index 1b902dbd4376..e0804060501e 100644
--- a/arch/m68k/mm/sun3mmu.c
+++ b/arch/m68k/mm/sun3mmu.c
@@ -21,7 +21,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
 
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 5de924ef42ed..a41c09149e23 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -26,7 +26,6 @@
 #include <linux/interrupt.h>
 
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index c3fb3bdd7ed9..b6d7d8a7a3dd 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -29,7 +29,6 @@
 #include <linux/module.h>
 
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c
index 39c79ebcd18a..6ef7a81a3b12 100644
--- a/arch/m68k/mvme16x/rtc.c
+++ b/arch/m68k/mvme16x/rtc.c
@@ -20,7 +20,6 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/setup.h>
 
 /*
diff --git a/arch/m68k/platform/68328/config.c b/arch/m68k/platform/68328/config.c
index 44b866544314..8c20e891e981 100644
--- a/arch/m68k/platform/68328/config.c
+++ b/arch/m68k/platform/68328/config.c
@@ -18,7 +18,6 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/rtc.h>
-#include <asm/system.h>
 #include <asm/machdep.h>
 #include <asm/MC68328.h>
 #if defined(CONFIG_PILOT) || defined(CONFIG_INIT_LCD)
diff --git a/arch/m68k/platform/68328/timers.c b/arch/m68k/platform/68328/timers.c
index b15ddef1ec76..c801c172b822 100644
--- a/arch/m68k/platform/68328/timers.c
+++ b/arch/m68k/platform/68328/timers.c
@@ -22,7 +22,6 @@
 #include <linux/clocksource.h>
 #include <linux/rtc.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/machdep.h>
 #include <asm/MC68VZ328.h>
diff --git a/arch/m68k/platform/68360/config.c b/arch/m68k/platform/68360/config.c
index 599a5949f320..255fc03913e9 100644
--- a/arch/m68k/platform/68360/config.c
+++ b/arch/m68k/platform/68360/config.c
@@ -18,7 +18,6 @@
 #include <linux/irq.h>
 
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/machdep.h>
 #include <asm/m68360.h>
diff --git a/arch/m68k/platform/68EZ328/config.c b/arch/m68k/platform/68EZ328/config.c
index dd2c53554341..4f158d551f02 100644
--- a/arch/m68k/platform/68EZ328/config.c
+++ b/arch/m68k/platform/68EZ328/config.c
@@ -16,7 +16,6 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/rtc.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/machdep.h>
 #include <asm/MC68EZ328.h>
diff --git a/arch/m68k/platform/68VZ328/config.c b/arch/m68k/platform/68VZ328/config.c
index 25ec673edc25..2ed8dc305e42 100644
--- a/arch/m68k/platform/68VZ328/config.c
+++ b/arch/m68k/platform/68VZ328/config.c
@@ -22,7 +22,6 @@
 #include <linux/irq.h>
 #include <linux/rtc.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/machdep.h>
 #include <asm/MC68VZ328.h>
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index be936480b964..8a1ce327c963 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -29,7 +29,6 @@
 #include <asm/io.h>
 #include <asm/rtc.h>
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
@@ -335,6 +334,9 @@ static __init int q40_add_kbd_device(void)
 {
 	struct platform_device *pdev;
 
+	if (!MACH_IS_Q40)
+		return -ENODEV;
+
 	pdev = platform_device_register_simple("q40kbd", -1, NULL, 0);
 	if (IS_ERR(pdev))
 		return PTR_ERR(pdev);
diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c
index 2b888491f29a..513f9bb17b9c 100644
--- a/arch/m68k/q40/q40ints.c
+++ b/arch/m68k/q40/q40ints.c
@@ -18,7 +18,6 @@
 #include <linux/irq.h>
 
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 #include <asm/q40_master.h>
diff --git a/arch/m68k/sun3/intersil.c b/arch/m68k/sun3/intersil.c
index 0116d208d300..94fe8016f1f0 100644
--- a/arch/m68k/sun3/intersil.c
+++ b/arch/m68k/sun3/intersil.c
@@ -14,7 +14,6 @@
 #include <linux/rtc.h>
 
 #include <asm/errno.h>
-#include <asm/system.h>
 #include <asm/rtc.h>
 #include <asm/intersil.h>
 
diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c
index 94f81ecfe3f8..8edc510a21be 100644
--- a/arch/m68k/sun3/mmu_emu.c
+++ b/arch/m68k/sun3/mmu_emu.c
@@ -17,7 +17,6 @@
 
 #include <asm/setup.h>
 #include <asm/traps.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
diff --git a/arch/m68k/sun3/prom/console.c b/arch/m68k/sun3/prom/console.c
index 2bcb6e4bfe54..e92364373b07 100644
--- a/arch/m68k/sun3/prom/console.c
+++ b/arch/m68k/sun3/prom/console.c
@@ -10,7 +10,6 @@
 #include <linux/sched.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/system.h>
 #include <linux/string.h>
 
 /* Non blocking get character from console input device, returns -1
diff --git a/arch/m68k/sun3x/config.c b/arch/m68k/sun3x/config.c
index fc599fad4a54..dd306c84d36d 100644
--- a/arch/m68k/sun3x/config.c
+++ b/arch/m68k/sun3x/config.c
@@ -12,7 +12,6 @@
 #include <linux/console.h>
 #include <linux/init.h>
 
-#include <asm/system.h>
 #include <asm/machdep.h>
 #include <asm/irq.h>
 #include <asm/sun3xprom.h>
diff --git a/arch/m68k/sun3x/time.c b/arch/m68k/sun3x/time.c
index 536a04aaf22f..1d0a72480409 100644
--- a/arch/m68k/sun3x/time.c
+++ b/arch/m68k/sun3x/time.c
@@ -15,7 +15,6 @@
 
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/sun3x.h>
 #include <asm/sun3ints.h>
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 11060fa87da3..ac22dc7f4cab 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -1,6 +1,7 @@
 config MICROBLAZE
 	def_bool y
 	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_FUNCTION_GRAPH_TRACER
@@ -28,6 +29,12 @@ config SWAP
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
+config ZONE_DMA
+	def_bool y
+
+config ARCH_POPULATES_NODE_MAP
+	def_bool y
+
 config RWSEM_XCHGADD_ALGORITHM
 	bool
 
@@ -153,20 +160,18 @@ config XILINX_UNCACHED_SHADOW
 	  The feature requires the design to define the RAM memory controller
 	  window to be twice as large as the actual physical memory.
 
-config HIGHMEM_START_BOOL
-	bool "Set high memory pool address"
-	depends on ADVANCED_OPTIONS && HIGHMEM
+config HIGHMEM
+	bool "High memory support"
+	depends on MMU
 	help
-	  This option allows you to set the base address of the kernel virtual
-	  area used to map high memory pages.  This can be useful in
-	  optimizing the layout of kernel virtual memory.
+	  The address space of Microblaze processors is only 4 Gigabytes large
+	  and it has to accommodate user address space, kernel address
+	  space as well as some memory mapped IO. That means that, if you
+	  have a large amount of physical memory and/or IO, not all of the
+	  memory can be "permanently mapped" by the kernel. The physical
+	  memory that is not permanently mapped is called "high memory".
 
-	  Say N here unless you know what you are doing.
-
-config HIGHMEM_START
-	hex "Virtual start address of high memory pool" if HIGHMEM_START_BOOL
-	depends on MMU
-	default "0xfe000000"
+	  If unsure, say n.
 
 config LOWMEM_SIZE_BOOL
 	bool "Set maximum low memory"
@@ -255,6 +260,10 @@ config MICROBLAZE_32K_PAGES
 
 endchoice
 
+config KERNEL_PAD
+	hex "Kernel PAD for unpacking" if ADVANCED_OPTIONS
+	default "0x80000" if MMU
+
 endmenu
 
 source "mm/Kconfig"
diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile
index 0c796cf81586..fa83ea497db7 100644
--- a/arch/microblaze/boot/Makefile
+++ b/arch/microblaze/boot/Makefile
@@ -2,13 +2,11 @@
 # arch/microblaze/boot/Makefile
 #
 
-MKIMAGE := $(srctree)/scripts/mkuboot.sh
-
 obj-y += linked_dtb.o
 
 targets := linux.bin linux.bin.gz simpleImage.%
 
-OBJCOPYFLAGS := -O binary
+OBJCOPYFLAGS := -R .note -R .comment -R .note.gnu.build-id -O binary
 
 # Ensure system.dtb exists
 $(obj)/linked_dtb.o: $(obj)/system.dtb
@@ -35,11 +33,9 @@ quiet_cmd_strip = STRIP   $@
 	cmd_strip = $(STRIP) -K microblaze_start -K _end -K __log_buf \
 				-K _fdt_start vmlinux -o $@
 
-quiet_cmd_uimage = UIMAGE  $@.ub
-	cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A microblaze -O linux -T kernel \
-		-C none -n 'Linux-$(KERNELRELEASE)' \
-		-a $(CONFIG_KERNEL_BASE_ADDR) -e $(CONFIG_KERNEL_BASE_ADDR) \
-		-d $@ $@.ub
+UIMAGE_IN = $@
+UIMAGE_OUT = $@.ub
+UIMAGE_LOADADDR = $(CONFIG_KERNEL_BASE_ADDR)
 
 $(obj)/simpleImage.%: vmlinux FORCE
 	$(call if_changed,cp,.unstrip)
diff --git a/arch/microblaze/include/asm/atomic.h b/arch/microblaze/include/asm/atomic.h
index 615f53992c65..472d8bf726df 100644
--- a/arch/microblaze/include/asm/atomic.h
+++ b/arch/microblaze/include/asm/atomic.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_MICROBLAZE_ATOMIC_H
 #define _ASM_MICROBLAZE_ATOMIC_H
 
+#include <asm/cmpxchg.h>
 #include <asm-generic/atomic.h>
 #include <asm-generic/atomic64.h>
 
diff --git a/arch/microblaze/include/asm/barrier.h b/arch/microblaze/include/asm/barrier.h
new file mode 100644
index 000000000000..df5be3e87044
--- /dev/null
+++ b/arch/microblaze/include/asm/barrier.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2006 Atmark Techno, Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef _ASM_MICROBLAZE_BARRIER_H
+#define _ASM_MICROBLAZE_BARRIER_H
+
+#define nop()                  asm volatile ("nop")
+
+#define smp_read_barrier_depends()	do {} while (0)
+#define read_barrier_depends()		do {} while (0)
+
+#define mb()			barrier()
+#define rmb()			mb()
+#define wmb()			mb()
+#define set_mb(var, value)	do { var = value; mb(); } while (0)
+#define set_wmb(var, value)	do { var = value; wmb(); } while (0)
+
+#define smp_mb()		mb()
+#define smp_rmb()		rmb()
+#define smp_wmb()		wmb()
+
+#endif /* _ASM_MICROBLAZE_BARRIER_H */
diff --git a/arch/microblaze/include/asm/cmpxchg.h b/arch/microblaze/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..538afc0ab9f3
--- /dev/null
+++ b/arch/microblaze/include/asm/cmpxchg.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_MICROBLAZE_CMPXCHG_H
+#define _ASM_MICROBLAZE_CMPXCHG_H
+
+#include <linux/irqflags.h>
+
+void __bad_xchg(volatile void *ptr, int size);
+
+static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
+								int size)
+{
+	unsigned long ret;
+	unsigned long flags;
+
+	switch (size) {
+	case 1:
+		local_irq_save(flags);
+		ret = *(volatile unsigned char *)ptr;
+		*(volatile unsigned char *)ptr = x;
+		local_irq_restore(flags);
+		break;
+
+	case 4:
+		local_irq_save(flags);
+		ret = *(volatile unsigned long *)ptr;
+		*(volatile unsigned long *)ptr = x;
+		local_irq_restore(flags);
+		break;
+	default:
+		__bad_xchg(ptr, size), ret = 0;
+		break;
+	}
+
+	return ret;
+}
+
+#define xchg(ptr, x) \
+	((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+
+#include <asm-generic/cmpxchg.h>
+#include <asm-generic/cmpxchg-local.h>
+
+#endif /* _ASM_MICROBLAZE_CMPXCHG_H */
diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h
index 3a3e5b886854..01d228286cb0 100644
--- a/arch/microblaze/include/asm/dma-mapping.h
+++ b/arch/microblaze/include/asm/dma-mapping.h
@@ -123,28 +123,34 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_handle, gfp_t flag)
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 	void *memory;
 
 	BUG_ON(!ops);
 
-	memory = ops->alloc_coherent(dev, size, dma_handle, flag);
+	memory = ops->alloc(dev, size, dma_handle, flag, attrs);
 
 	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
 	return memory;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d, s, c, h, NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!ops);
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	ops->free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
diff --git a/arch/microblaze/include/asm/exec.h b/arch/microblaze/include/asm/exec.h
new file mode 100644
index 000000000000..e750de1fe8fb
--- /dev/null
+++ b/arch/microblaze/include/asm/exec.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (C) 2006 Atmark Techno, Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef _ASM_MICROBLAZE_EXEC_H
+#define _ASM_MICROBLAZE_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _ASM_MICROBLAZE_EXEC_H */
diff --git a/arch/microblaze/include/asm/fixmap.h b/arch/microblaze/include/asm/fixmap.h
new file mode 100644
index 000000000000..f2b312e10b10
--- /dev/null
+++ b/arch/microblaze/include/asm/fixmap.h
@@ -0,0 +1,109 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Copyright 2008 Freescale Semiconductor Inc.
+ *   Port to powerpc added by Kumar Gala
+ *
+ * Copyright 2011 Michal Simek <monstr@monstr.eu>
+ * Copyright 2011 PetaLogix Qld Pty Ltd
+ *   Port to Microblaze
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/page.h>
+#ifdef CONFIG_HIGHMEM
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#endif
+
+#define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+enum fixed_addresses {
+	FIX_HOLE,
+#ifdef CONFIG_HIGHMEM
+	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * num_possible_cpus()) - 1,
+#endif
+	__end_of_fixed_addresses
+};
+
+extern void __set_fixmap(enum fixed_addresses idx,
+					phys_addr_t phys, pgprot_t flags);
+
+#define set_fixmap(idx, phys) \
+		__set_fixmap(idx, phys, PAGE_KERNEL)
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+		__set_fixmap(idx, phys, PAGE_KERNEL_CI)
+
+#define clear_fixmap(idx) \
+		__set_fixmap(idx, 0, __pgprot(0))
+
+#define __FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START		(FIXADDR_TOP - __FIXADDR_SIZE)
+
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without tranlation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
+{
+	/*
+	 * this branch gets completely eliminated after inlining,
+	 * except when someone tries to use fixaddr indices in an
+	 * illegal way. (such as mixing up address types or using
+	 * out-of-range indices).
+	 *
+	 * If it doesn't get removed, the linker will complain
+	 * loudly with a reasonably clear error message..
+	 */
+	if (idx >= __end_of_fixed_addresses)
+		__this_fixmap_does_not_exist();
+
+	return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+	return __virt_to_fix(vaddr);
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif
diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h
index b0526d2716fa..ff8cde159d9a 100644
--- a/arch/microblaze/include/asm/futex.h
+++ b/arch/microblaze/include/asm/futex.h
@@ -24,7 +24,7 @@
 			.word	1b,4b,2b,4b;				\
 			.previous;"					\
 	: "=&r" (oldval), "=&r" (ret)					\
-	: "b" (uaddr), "i" (-EFAULT), "r" (oparg)			\
+	: "r" (uaddr), "i" (-EFAULT), "r" (oparg)			\
 	);								\
 })
 
diff --git a/arch/microblaze/include/asm/highmem.h b/arch/microblaze/include/asm/highmem.h
new file mode 100644
index 000000000000..2446a73140ac
--- /dev/null
+++ b/arch/microblaze/include/asm/highmem.h
@@ -0,0 +1,96 @@
+/*
+ * highmem.h: virtual kernel memory mappings for high memory
+ *
+ * Used in CONFIG_HIGHMEM systems for memory pages which
+ * are not addressable by direct kernel virtual addresses.
+ *
+ * Copyright (C) 1999 Gerhard Wichert, Siemens AG
+ *		      Gerhard.Wichert@pdb.siemens.de
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * up to 16 Terabyte physical memory. With current x86 CPUs
+ * we now support up to 64 Gigabytes physical RAM.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef _ASM_HIGHMEM_H
+#define _ASM_HIGHMEM_H
+
+#ifdef __KERNEL__
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/uaccess.h>
+#include <asm/fixmap.h>
+
+extern pte_t *kmap_pte;
+extern pgprot_t kmap_prot;
+extern pte_t *pkmap_page_table;
+
+/*
+ * Right now we initialize only a single pte table. It can be extended
+ * easily, subsequent pte tables have to be allocated in one physical
+ * chunk of RAM.
+ */
+/*
+ * We use one full pte table with 4K pages. And with 16K/64K/256K pages pte
+ * table covers enough memory (32MB/512MB/2GB resp.), so that both FIXMAP
+ * and PKMAP can be placed in a single pte table. We use 512 pages for PKMAP
+ * in case of 16K/64K/256K page sizes.
+ */
+
+#define PKMAP_ORDER	PTE_SHIFT
+#define LAST_PKMAP	(1 << PKMAP_ORDER)
+
+#define PKMAP_BASE	((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1)) \
+								& PMD_MASK)
+
+#define LAST_PKMAP_MASK	(LAST_PKMAP - 1)
+#define PKMAP_NR(virt)  ((virt - PKMAP_BASE) >> PAGE_SHIFT)
+#define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
+
+extern void *kmap_high(struct page *page);
+extern void kunmap_high(struct page *page);
+extern void *kmap_atomic_prot(struct page *page, pgprot_t prot);
+extern void __kunmap_atomic(void *kvaddr);
+
+static inline void *kmap(struct page *page)
+{
+	might_sleep();
+	if (!PageHighMem(page))
+		return page_address(page);
+	return kmap_high(page);
+}
+
+static inline void kunmap(struct page *page)
+{
+	BUG_ON(in_interrupt());
+	if (!PageHighMem(page))
+		return;
+	kunmap_high(page);
+}
+
+static inline void *__kmap_atomic(struct page *page)
+{
+	return kmap_atomic_prot(page, kmap_prot);
+}
+
+static inline struct page *kmap_atomic_to_page(void *ptr)
+{
+	unsigned long idx, vaddr = (unsigned long) ptr;
+	pte_t *pte;
+
+	if (vaddr < FIXADDR_START)
+		return virt_to_page(ptr);
+
+	idx = virt_to_fix(vaddr);
+	pte = kmap_pte - (idx - FIX_KMAP_BEGIN);
+	return pte_page(*pte);
+}
+
+#define flush_cache_kmaps()	{ flush_icache(); flush_dcache(); }
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_HIGHMEM_H */
diff --git a/arch/microblaze/include/asm/mmu.h b/arch/microblaze/include/asm/mmu.h
index 8d6a654ceffb..1f9edddf7f4b 100644
--- a/arch/microblaze/include/asm/mmu.h
+++ b/arch/microblaze/include/asm/mmu.h
@@ -56,6 +56,12 @@ typedef struct _SEGREG {
 
 extern void _tlbie(unsigned long va);	/* invalidate a TLB entry */
 extern void _tlbia(void);		/* invalidate all TLB entries */
+
+/*
+ * tlb_skip size stores actual number skipped TLBs from TLB0 - every directy TLB
+ * mapping has to increase tlb_skip size.
+ */
+extern u32 tlb_skip;
 #   endif /* __ASSEMBLY__ */
 
 /*
@@ -69,6 +75,12 @@ extern void _tlbia(void);		/* invalidate all TLB entries */
 
 #  define MICROBLAZE_TLB_SIZE 64
 
+/* For cases when you want to skip some TLB entries */
+#  define MICROBLAZE_TLB_SKIP 0
+
+/* Use the last TLB for temporary access to LMB */
+#  define MICROBLAZE_LMB_TLB_ID 63
+
 /*
  * TLB entries are defined by a "high" tag portion and a "low" data
  * portion. The data portion is 32-bits.
diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h
index a25e6b5e2ad4..287c5485d286 100644
--- a/arch/microblaze/include/asm/page.h
+++ b/arch/microblaze/include/asm/page.h
@@ -135,8 +135,10 @@ extern unsigned long min_low_pfn;
 extern unsigned long max_pfn;
 
 extern unsigned long memory_start;
-extern unsigned long memory_end;
 extern unsigned long memory_size;
+extern unsigned long lowmem_size;
+
+extern unsigned long kernel_tlb;
 
 extern int page_is_ram(unsigned long pfn);
 
diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index 44dc67aa0277..3ef7b9cafeca 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -94,8 +94,7 @@ static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 /* Start and end of the vmalloc area. */
 /* Make sure to map the vmalloc area above the pinned kernel memory area
    of 32Mb.  */
-#define VMALLOC_START	(CONFIG_KERNEL_START + \
-				max(32 * 1024 * 1024UL, memory_size))
+#define VMALLOC_START	(CONFIG_KERNEL_START + CONFIG_LOWMEM_SIZE)
 #define VMALLOC_END	ioremap_bot
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 7283bfb2f7e4..bffb54527299 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -31,6 +31,8 @@ extern const struct seq_operations cpuinfo_op;
 /* Do necessary setup to start up a newly executed thread. */
 void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long usp);
 
+extern void ret_from_fork(void);
+
 # endif /* __ASSEMBLY__ */
 
 # ifndef CONFIG_MMU
@@ -125,7 +127,6 @@ struct thread_struct {
 	.pgdir = swapper_pg_dir, \
 }
 
-
 /* Free all resources held by a thread. */
 extern inline void release_thread(struct task_struct *dead_task)
 {
@@ -166,6 +167,14 @@ unsigned long get_wchan(struct task_struct *p);
 #  define STACK_TOP	TASK_SIZE
 #  define STACK_TOP_MAX	STACK_TOP
 
+void disable_hlt(void);
+void enable_hlt(void);
+void default_idle(void);
+
+#ifdef CONFIG_DEBUG_FS
+extern struct dentry *of_debugfs_root;
+#endif
+
 #  endif /* __ASSEMBLY__ */
 # endif /* CONFIG_MMU */
 #endif /* _ASM_MICROBLAZE_PROCESSOR_H */
diff --git a/arch/microblaze/include/asm/setup.h b/arch/microblaze/include/asm/setup.h
index 6c72ed7eba98..0061aa13a340 100644
--- a/arch/microblaze/include/asm/setup.h
+++ b/arch/microblaze/include/asm/setup.h
@@ -20,6 +20,8 @@ extern unsigned int boot_cpuid; /* move to smp.h */
 
 extern char cmd_line[COMMAND_LINE_SIZE];
 
+extern char *klimit;
+
 void early_printk(const char *fmt, ...);
 
 int setup_early_printk(char *opt);
@@ -39,13 +41,18 @@ extern void of_platform_reset_gpio_probe(void);
 void time_init(void);
 void init_IRQ(void);
 void machine_early_init(const char *cmdline, unsigned int ram,
-			unsigned int fdt, unsigned int msr);
+		unsigned int fdt, unsigned int msr, unsigned int tlb0,
+		unsigned int tlb1);
 
 void machine_restart(char *cmd);
 void machine_shutdown(void);
 void machine_halt(void);
 void machine_power_off(void);
 
+void free_init_pages(char *what, unsigned long begin, unsigned long end);
+extern void *alloc_maybe_bootmem(size_t size, gfp_t mask);
+extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
+
 #  endif/* __KERNEL__ */
 # endif /* __ASSEMBLY__ */
 #endif /* _ASM_MICROBLAZE_SETUP_H */
diff --git a/arch/microblaze/include/asm/switch_to.h b/arch/microblaze/include/asm/switch_to.h
new file mode 100644
index 000000000000..f45baa2c5e09
--- /dev/null
+++ b/arch/microblaze/include/asm/switch_to.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2006 Atmark Techno, Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef _ASM_MICROBLAZE_SWITCH_TO_H
+#define _ASM_MICROBLAZE_SWITCH_TO_H
+
+struct task_struct;
+struct thread_info;
+
+extern struct task_struct *_switch_to(struct thread_info *prev,
+					struct thread_info *next);
+
+#define switch_to(prev, next, last)					\
+	do {								\
+		(last) = _switch_to(task_thread_info(prev),		\
+					task_thread_info(next));	\
+	} while (0)
+
+#endif /* _ASM_MICROBLAZE_SWITCH_TO_H */
diff --git a/arch/microblaze/include/asm/system.h b/arch/microblaze/include/asm/system.h
deleted file mode 100644
index 5a433cbaafb3..000000000000
--- a/arch/microblaze/include/asm/system.h
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_SYSTEM_H
-#define _ASM_MICROBLAZE_SYSTEM_H
-
-#include <asm/registers.h>
-#include <asm/setup.h>
-#include <asm/irqflags.h>
-#include <asm/cache.h>
-
-#include <asm-generic/cmpxchg.h>
-#include <asm-generic/cmpxchg-local.h>
-
-struct task_struct;
-struct thread_info;
-
-extern struct task_struct *_switch_to(struct thread_info *prev,
-					struct thread_info *next);
-
-#define switch_to(prev, next, last)					\
-	do {								\
-		(last) = _switch_to(task_thread_info(prev),		\
-					task_thread_info(next));	\
-	} while (0)
-
-#define smp_read_barrier_depends()	do {} while (0)
-#define read_barrier_depends()		do {} while (0)
-
-#define nop()			asm volatile ("nop")
-#define mb()			barrier()
-#define rmb()			mb()
-#define wmb()			mb()
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
-#define set_wmb(var, value)	do { var = value; wmb(); } while (0)
-
-#define smp_mb()		mb()
-#define smp_rmb()		rmb()
-#define smp_wmb()		wmb()
-
-void __bad_xchg(volatile void *ptr, int size);
-
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
-								int size)
-{
-	unsigned long ret;
-	unsigned long flags;
-
-	switch (size) {
-	case 1:
-		local_irq_save(flags);
-		ret = *(volatile unsigned char *)ptr;
-		*(volatile unsigned char *)ptr = x;
-		local_irq_restore(flags);
-		break;
-
-	case 4:
-		local_irq_save(flags);
-		ret = *(volatile unsigned long *)ptr;
-		*(volatile unsigned long *)ptr = x;
-		local_irq_restore(flags);
-		break;
-	default:
-		__bad_xchg(ptr, size), ret = 0;
-		break;
-	}
-
-	return ret;
-}
-
-void disable_hlt(void);
-void enable_hlt(void);
-void default_idle(void);
-
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-
-void free_init_pages(char *what, unsigned long begin, unsigned long end);
-void free_initmem(void);
-extern char *klimit;
-extern void ret_from_fork(void);
-
-extern void *alloc_maybe_bootmem(size_t size, gfp_t mask);
-extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
-
-#ifdef CONFIG_DEBUG_FS
-extern struct dentry *of_debugfs_root;
-#endif
-
-#define arch_align_stack(x) (x)
-
-#endif /* _ASM_MICROBLAZE_SYSTEM_H */
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 072b0077abf9..ef25f7538d4a 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -80,7 +80,7 @@ extern unsigned long search_exception_table(unsigned long);
 static inline int ___range_ok(unsigned long addr, unsigned long size)
 {
 	return ((addr < memory_start) ||
-		((addr + size) > memory_end));
+		((addr + size - 1) > (memory_start + memory_size - 1)));
 }
 
 #define __range_ok(addr, size) \
diff --git a/arch/microblaze/kernel/cpu/cpuinfo.c b/arch/microblaze/kernel/cpu/cpuinfo.c
index 54194b28574a..eab6abf5652e 100644
--- a/arch/microblaze/kernel/cpu/cpuinfo.c
+++ b/arch/microblaze/kernel/cpu/cpuinfo.c
@@ -35,6 +35,8 @@ const struct cpu_ver_key cpu_ver_lookup[] = {
 	{"8.00.b", 0x13},
 	{"8.10.a", 0x14},
 	{"8.20.a", 0x15},
+	{"8.20.b", 0x16},
+	{"8.30.a", 0x17},
 	{NULL, 0},
 };
 
diff --git a/arch/microblaze/kernel/cpu/pvr.c b/arch/microblaze/kernel/cpu/pvr.c
index 488c1ed24e38..3a749d5e71fd 100644
--- a/arch/microblaze/kernel/cpu/pvr.c
+++ b/arch/microblaze/kernel/cpu/pvr.c
@@ -12,7 +12,6 @@
 
 #include <linux/kernel.h>
 #include <linux/compiler.h>
-#include <asm/system.h>
 #include <asm/exceptions.h>
 #include <asm/pvr.h>
 
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index 65a4af4cbbbe..a2bfa2ca5730 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -33,7 +33,8 @@ static unsigned long get_dma_direct_offset(struct device *dev)
 #define NOT_COHERENT_CACHE
 
 static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t flag)
+				       dma_addr_t *dma_handle, gfp_t flag,
+				       struct dma_attrs *attrs)
 {
 #ifdef NOT_COHERENT_CACHE
 	return consistent_alloc(flag, size, dma_handle);
@@ -57,7 +58,8 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 }
 
 static void dma_direct_free_coherent(struct device *dev, size_t size,
-			      void *vaddr, dma_addr_t dma_handle)
+				     void *vaddr, dma_addr_t dma_handle,
+				     struct dma_attrs *attrs)
 {
 #ifdef NOT_COHERENT_CACHE
 	consistent_free(size, vaddr);
@@ -176,8 +178,8 @@ dma_direct_sync_sg_for_device(struct device *dev,
 }
 
 struct dma_map_ops dma_direct_ops = {
-	.alloc_coherent	= dma_direct_alloc_coherent,
-	.free_coherent	= dma_direct_free_coherent,
+	.alloc		= dma_direct_alloc_coherent,
+	.free		= dma_direct_free_coherent,
 	.map_sg		= dma_direct_map_sg,
 	.unmap_sg	= dma_direct_unmap_sg,
 	.dma_supported	= dma_direct_dma_supported,
diff --git a/arch/microblaze/kernel/early_printk.c b/arch/microblaze/kernel/early_printk.c
index 8356e47631c4..aba1f9a97d5d 100644
--- a/arch/microblaze/kernel/early_printk.c
+++ b/arch/microblaze/kernel/early_printk.c
@@ -171,10 +171,26 @@ void __init remap_early_printk(void)
 {
 	if (!early_console_initialized || !early_console)
 		return;
-	printk(KERN_INFO "early_printk_console remaping from 0x%x to ",
+	printk(KERN_INFO "early_printk_console remapping from 0x%x to ",
 								base_addr);
 	base_addr = (u32) ioremap(base_addr, PAGE_SIZE);
 	printk(KERN_CONT "0x%x\n", base_addr);
+
+#ifdef CONFIG_MMU
+	/*
+	 * Early console is on the top of skipped TLB entries
+	 * decrease tlb_skip size ensure that hardcoded TLB entry will be
+	 * used by generic algorithm
+	 * FIXME check if early console mapping is on the top by rereading
+	 * TLB entry and compare baseaddr
+	 *  mts  rtlbx, (tlb_skip - 1)
+	 *  nop
+	 *  mfs  rX, rtlblo
+	 *  nop
+	 *  cmp rX, orig_base_addr
+	 */
+	tlb_skip -= 1;
+#endif
 }
 
 void __init disable_early_printk(void)
diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index 77320b8fc16a..98b17f9f904b 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -63,9 +63,7 @@ ENTRY(_start)
 real_start:
 #endif
 
-	mfs	r1, rmsr
-	andi	r1, r1, ~2
-	mts	rmsr, r1
+	mts	rmsr, r0
 /*
  * According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc'
  * if the msrclr instruction is not enabled. We use this to detect
@@ -73,6 +71,7 @@ real_start:
  * r8 == 0 - msr instructions are implemented
  * r8 != 0 - msr instructions are not implemented
  */
+	mfs	r1, rmsr
 	msrclr	r8, 0 /* clear nothing - just read msr for test */
 	cmpu	r8, r8, r1 /* r1 must contain msr reg content */
 
@@ -96,7 +95,7 @@ big_endian:
 _prepare_copy_fdt:
 	or	r11, r0, r0 /* incremment */
 	ori	r4, r0, TOPHYS(_fdt_start)
-	ori	r3, r0, (0x4000 - 4)
+	ori	r3, r0, (0x8000 - 4)
 _copy_fdt:
 	lw	r12, r7, r11 /* r12 = r7 + r11 */
 	sw	r12, r4, r11 /* addr[r4 + r11] = r12 */
@@ -150,6 +149,7 @@ _copy_bram:
 _invalidate:
 	mts	rtlbx, r3
 	mts	rtlbhi, r0			/* flush: ensure V is clear   */
+	mts	rtlblo, r0
 	bgtid	r3, _invalidate		/* loop for all entries       */
 	addik	r3, r3, -1
 	/* sync */
@@ -169,6 +169,53 @@ _invalidate:
 	addik	r3,r0, CONFIG_KERNEL_START /* Load the kernel virtual address */
 	tophys(r4,r3)			/* Load the kernel physical address */
 
+	/* start to do TLB calculation */
+	addik	r12, r0, _end
+	rsub	r12, r3, r12
+	addik	r12, r12, CONFIG_KERNEL_PAD /* that's the pad */
+
+	or r9, r0, r0 /* TLB0 = 0 */
+	or r10, r0, r0 /* TLB1 = 0 */
+
+	addik	r11, r12, -0x1000000
+	bgei	r11, GT16 /* size is greater than 16MB */
+	addik	r11, r12, -0x0800000
+	bgei	r11, GT8 /* size is greater than 8MB */
+	addik	r11, r12, -0x0400000
+	bgei	r11, GT4 /* size is greater than 4MB */
+	/* size is less than 4MB */
+	addik	r11, r12, -0x0200000
+	bgei	r11, GT2 /* size is greater than 2MB */
+	addik	r9, r0, 0x0100000 /* TLB0 must be 1MB */
+	addik	r11, r12, -0x0100000
+	bgei	r11, GT1 /* size is greater than 1MB */
+	/* TLB1 is 0 which is setup above */
+	bri tlb_end
+GT4: /* r11 contains the rest - will be either 1 or 4 */
+	ori r9, r0, 0x400000 /* TLB0 is 4MB */
+	bri TLB1
+GT16: /* TLB0 is 16MB */
+	addik	r9, r0, 0x1000000 /* means TLB0 is 16MB */
+TLB1:
+	/* must be used r2 because of substract if failed */
+	addik	r2, r11, -0x0400000
+	bgei	r2, GT20 /* size is greater than 16MB */
+	/* size is >16MB and <20MB */
+	addik	r11, r11, -0x0100000
+	bgei	r11, GT17 /* size is greater than 17MB */
+	/* kernel is >16MB and < 17MB */
+GT1:
+	addik	r10, r0, 0x0100000 /* means TLB1 is 1MB */
+	bri tlb_end
+GT2: /* TLB0 is 0 and TLB1 will be 4MB */
+GT17: /* TLB1 is 4MB - kernel size <20MB */
+	addik	r10, r0, 0x0400000 /* means TLB1 is 4MB */
+	bri tlb_end
+GT8: /* TLB0 is still zero that's why I can use only TLB1 */
+GT20: /* TLB1 is 16MB - kernel size >20MB */
+	addik	r10, r0, 0x1000000 /* means TLB1 is 16MB */
+tlb_end:
+
 	/*
 	 * Configure and load two entries into TLB slots 0 and 1.
 	 * In case we are pinning TLBs, these are reserved in by the
@@ -178,28 +225,81 @@ _invalidate:
 	andi	r4,r4,0xfffffc00	/* Mask off the real page number */
 	ori	r4,r4,(TLB_WR | TLB_EX)	/* Set the write and execute bits */
 
+	/*
+	 * TLB0 is always used - check if is not zero (r9 stores TLB0 value)
+	 * if is use TLB1 value and clear it (r10 stores TLB1 value)
+	 */
+	bnei	r9, tlb0_not_zero
+	add	r9, r10, r0
+	add	r10, r0, r0
+tlb0_not_zero:
+
+	/* look at the code below */
+	ori	r30, r0, 0x200
+	andi	r29, r9, 0x100000
+	bneid	r29, 1f
+	addik	r30, r30, 0x80
+	andi	r29, r9, 0x400000
+	bneid	r29, 1f
+	addik	r30, r30, 0x80
+	andi	r29, r9, 0x1000000
+	bneid	r29, 1f
+	addik	r30, r30, 0x80
+1:
 	andi	r3,r3,0xfffffc00	/* Mask off the effective page number */
-	ori	r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_16M))
+	ori	r3,r3,(TLB_VALID)
+	or	r3, r3, r30
 
-	mts     rtlbx,r0		/* TLB slow 0 */
+	/* Load tlb_skip size value which is index to first unused TLB entry */
+	lwi	r11, r0, TOPHYS(tlb_skip)
+	mts     rtlbx,r11		/* TLB slow 0 */
 
 	mts	rtlblo,r4		/* Load the data portion of the entry */
 	mts	rtlbhi,r3		/* Load the tag portion of the entry */
 
-	addik	r4, r4, 0x01000000	/* Map next 16 M entries */
-	addik	r3, r3, 0x01000000
+	/* Increase tlb_skip size */
+	addik	r11, r11, 1
+	swi	r11, r0, TOPHYS(tlb_skip)
+
+	/* TLB1 can be zeroes that's why we not setup it */
+	beqi	r10, jump_over2
+
+	/* look at the code below */
+	ori	r30, r0, 0x200
+	andi	r29, r10, 0x100000
+	bneid	r29, 1f
+	addik	r30, r30, 0x80
+	andi	r29, r10, 0x400000
+	bneid	r29, 1f
+	addik	r30, r30, 0x80
+	andi	r29, r10, 0x1000000
+	bneid	r29, 1f
+	addik	r30, r30, 0x80
+1:
+	addk	r4, r4, r9	/* previous addr + TLB0 size */
+	addk	r3, r3, r9
 
-	ori	r6,r0,1			/* TLB slot 1 */
-	mts     rtlbx,r6
+	andi	r3,r3,0xfffffc00	/* Mask off the effective page number */
+	ori	r3,r3,(TLB_VALID)
+	or	r3, r3, r30
+
+	lwi	r11, r0, TOPHYS(tlb_skip)
+	mts     rtlbx, r11		/* r11 is used from TLB0 */
 
 	mts	rtlblo,r4		/* Load the data portion of the entry */
 	mts	rtlbhi,r3		/* Load the tag portion of the entry */
 
+	/* Increase tlb_skip size */
+	addik	r11, r11, 1
+	swi	r11, r0, TOPHYS(tlb_skip)
+
+jump_over2:
 	/*
 	 * Load a TLB entry for LMB, since we need access to
 	 * the exception vectors, using a 4k real==virtual mapping.
 	 */
-	ori	r6,r0,3			/* TLB slot 3 */
+	/* Use temporary TLB_ID for LMB - clear this temporary mapping later */
+	ori	r6, r0, MICROBLAZE_LMB_TLB_ID
 	mts     rtlbx,r6
 
 	ori	r4,r0,(TLB_WR | TLB_EX)
@@ -238,8 +338,8 @@ start_here:
 	 * Please see $(ARCH)/mach-$(SUBARCH)/setup.c for
 	 * the function.
 	 */
-	addik	r9, r0, machine_early_init
-	brald	r15, r9
+	addik	r11, r0, machine_early_init
+	brald	r15, r11
 	nop
 
 #ifndef CONFIG_MMU
@@ -268,8 +368,7 @@ start_here:
 
 	/* Load up the kernel context */
 kernel_load_context:
-	# Keep entry 0 and 1 valid. Entry 3 mapped to LMB can go away.
-	ori	r5,r0,3
+	ori	r5, r0, MICROBLAZE_LMB_TLB_ID
 	mts     rtlbx,r5
 	nop
 	mts	rtlbhi,r0
diff --git a/arch/microblaze/kernel/hw_exception_handler.S b/arch/microblaze/kernel/hw_exception_handler.S
index e62be8379604..aa510f450ac6 100644
--- a/arch/microblaze/kernel/hw_exception_handler.S
+++ b/arch/microblaze/kernel/hw_exception_handler.S
@@ -820,19 +820,26 @@ ex_handler_done:
  *	Upon exit, we reload everything and RFI.
  * A common place to load the TLB.
  */
+.section .data
+.align 4
+.global tlb_skip
+	tlb_skip:
+		.long	MICROBLAZE_TLB_SKIP
 	tlb_index:
-		.long	1 /* MS: storing last used tlb index */
+		/* MS: storing last used tlb index */
+		.long	MICROBLAZE_TLB_SIZE/2
+.previous
 	finish_tlb_load:
 		/* MS: load the last used TLB index. */
 		lwi	r5, r0, TOPHYS(tlb_index)
 		addik	r5, r5, 1 /* MS: inc tlb_index -> use next one */
 
 /* MS: FIXME this is potential fault, because this is mask not count */
-		andi	r5, r5, (MICROBLAZE_TLB_SIZE-1)
+		andi	r5, r5, MICROBLAZE_TLB_SIZE - 1
 		ori	r6, r0, 1
 		cmp	r31, r5, r6
 		blti	r31, ex12
-		addik	r5, r6, 1
+		lwi	r5, r0, TOPHYS(tlb_skip)
 	ex12:
 		/* MS: save back current TLB index */
 		swi	r5, r0, TOPHYS(tlb_index)
diff --git a/arch/microblaze/kernel/intc.c b/arch/microblaze/kernel/intc.c
index ad120672cee5..6c54d4dcdec3 100644
--- a/arch/microblaze/kernel/intc.c
+++ b/arch/microblaze/kernel/intc.c
@@ -151,8 +151,8 @@ void __init init_IRQ(void)
 #ifdef CONFIG_SELFMOD_INTC
 	selfmod_function((int *) arr_func, intc_baseaddr);
 #endif
-	printk(KERN_INFO "XPS intc #0 at 0x%08x, num_irq=%d, edge=0x%x\n",
-		intc_baseaddr, nr_irq, intr_mask);
+	printk(KERN_INFO "%s #0 at 0x%08x, num_irq=%d, edge=0x%x\n",
+		intc->name, intc_baseaddr, nr_irq, intr_mask);
 
 	/*
 	 * Disable all external interrupts until they are
diff --git a/arch/microblaze/kernel/microblaze_ksyms.c b/arch/microblaze/kernel/microblaze_ksyms.c
index 49faeb429599..bb4907c828dc 100644
--- a/arch/microblaze/kernel/microblaze_ksyms.c
+++ b/arch/microblaze/kernel/microblaze_ksyms.c
@@ -18,7 +18,6 @@
 #include <asm/cacheflush.h>
 #include <linux/io.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
 
diff --git a/arch/microblaze/kernel/misc.S b/arch/microblaze/kernel/misc.S
index 206da3da361f..1dafddeb8a0b 100644
--- a/arch/microblaze/kernel/misc.S
+++ b/arch/microblaze/kernel/misc.S
@@ -29,16 +29,16 @@
 .type  _tlbia, @function
 .align 4;
 _tlbia:
-	addik	r12, r0, MICROBLAZE_TLB_SIZE - 1 /* flush all entries (63 - 3) */
+	lwi	r12, r0, tlb_skip;
 	/* isync */
 _tlbia_1:
 	mts	rtlbx, r12
 	nop
 	mts	rtlbhi, r0 /* flush: ensure V is clear */
 	nop
-	addik	r11, r12, -2
+	rsubi	r11, r12, MICROBLAZE_TLB_SIZE - 1
 	bneid	r11, _tlbia_1 /* loop for all entries */
-	addik	r12, r12, -1
+	addik	r12, r12, 1
 	/* sync */
 	rtsd	r15, 8
 	nop
@@ -75,7 +75,7 @@ early_console_reg_tlb_alloc:
 	 * Load a TLB entry for the UART, so that microblaze_progress() can use
 	 * the UARTs nice and early.  We use a 4k real==virtual mapping.
 	 */
-	ori	r4, r0, MICROBLAZE_TLB_SIZE - 1
+	lwi	r4, r0, tlb_skip
 	mts	rtlbx, r4 /* TLB slot 63 */
 
 	or	r4,r5,r0
@@ -89,6 +89,11 @@ early_console_reg_tlb_alloc:
 	nop
 	mts	rtlbhi,r5 /* Load the tag portion of the entry */
 	nop
+
+	lwi	r5, r0, tlb_skip
+	addik	r5, r5, 1
+	swi	r5, r0, tlb_skip
+
 	rtsd	r15, 8
 	nop
 
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 9155f7d92669..883b92789cdf 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -13,7 +13,6 @@
 #include <linux/pm.h>
 #include <linux/tick.h>
 #include <linux/bitops.h>
-#include <asm/system.h>
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h> /* for USER_DS macros */
 #include <asm/cacheflush.h>
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index 80d314e81901..4a764ccb9f26 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -36,7 +36,6 @@
 #include <asm/processor.h>
 #include <asm/irq.h>
 #include <linux/io.h>
-#include <asm/system.h>
 #include <asm/mmu.h>
 #include <asm/pgtable.h>
 #include <asm/sections.h>
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index 70e6d0b41ab4..16d8dfd9094b 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -30,7 +30,6 @@
 #include <asm/entry.h>
 #include <asm/cpuinfo.h>
 
-#include <asm/system.h>
 #include <asm/prom.h>
 #include <asm/pgtable.h>
 
@@ -95,8 +94,11 @@ inline unsigned get_romfs_len(unsigned *addr)
 }
 #endif	/* CONFIG_MTD_UCLINUX_EBSS */
 
+unsigned long kernel_tlb;
+
 void __init machine_early_init(const char *cmdline, unsigned int ram,
-		unsigned int fdt, unsigned int msr)
+		unsigned int fdt, unsigned int msr, unsigned int tlb0,
+		unsigned int tlb1)
 {
 	unsigned long *src, *dst;
 	unsigned int offset = 0;
@@ -143,6 +145,12 @@ void __init machine_early_init(const char *cmdline, unsigned int ram,
 	setup_early_printk(NULL);
 #endif
 
+	/* setup kernel_tlb after BSS cleaning
+	 * Maybe worth to move to asm code */
+	kernel_tlb = tlb0 + tlb1;
+	/* printk("TLB1 0x%08x, TLB0 0x%08x, tlb 0x%x\n", tlb0,
+							tlb1, kernel_tlb); */
+
 	printk("Ramdisk addr 0x%08x, ", ram);
 	if (fdt)
 		printk("FDT at 0x%08x\n", fdt);
@@ -197,6 +205,21 @@ static int microblaze_debugfs_init(void)
 	return of_debugfs_root == NULL;
 }
 arch_initcall(microblaze_debugfs_init);
+
+# ifdef CONFIG_MMU
+static int __init debugfs_tlb(void)
+{
+	struct dentry *d;
+
+	if (!of_debugfs_root)
+		return -ENODEV;
+
+	d = debugfs_create_u32("tlb_skip", S_IRUGO, of_debugfs_root, &tlb_skip);
+	if (!d)
+		return -ENOMEM;
+}
+device_initcall(debugfs_tlb);
+# endif
 #endif
 
 static int dflt_bus_notify(struct notifier_block *nb,
diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index 3cb0bf640135..522defa7d41f 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -27,7 +27,6 @@
 #include <asm/setup.h>
 #include <asm/prom.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <linux/cnt32_to_63.h>
 
 #ifdef CONFIG_SELFMOD_TIMER
@@ -79,7 +78,7 @@ static inline void microblaze_timer0_start_periodic(unsigned long load_val)
 	 * !PWMA - disable pwm
 	 * TINT - clear interrupt status
 	 * ENT- enable timer itself
-	 * EINT - enable interrupt
+	 * ENIT - enable interrupt
 	 * !LOAD - clear the bit to let go
 	 * ARHT - auto reload
 	 * !CAPT - no external trigger
@@ -274,8 +273,8 @@ void __init time_init(void)
 #ifdef CONFIG_SELFMOD_TIMER
 	selfmod_function((int *) arr_func, timer_baseaddr);
 #endif
-	printk(KERN_INFO "XPS timer #0 at 0x%08x, irq=%d\n",
-		timer_baseaddr, irq);
+	printk(KERN_INFO "%s #0 at 0x%08x, irq=%d\n",
+		timer->name, timer_baseaddr, irq);
 
 	/* If there is clock-frequency property than use it */
 	prop = of_get_property(timer, "clock-frequency", NULL);
diff --git a/arch/microblaze/kernel/traps.c b/arch/microblaze/kernel/traps.c
index ba034d421ec2..5541ac559593 100644
--- a/arch/microblaze/kernel/traps.c
+++ b/arch/microblaze/kernel/traps.c
@@ -15,7 +15,6 @@
 #include <linux/debug_locks.h>
 
 #include <asm/exceptions.h>
-#include <asm/system.h>
 #include <asm/unwind.h>
 
 void trap_init(void)
diff --git a/arch/microblaze/kernel/unwind.c b/arch/microblaze/kernel/unwind.c
index 9781a528cfc9..6be4ae3c3351 100644
--- a/arch/microblaze/kernel/unwind.c
+++ b/arch/microblaze/kernel/unwind.c
@@ -24,6 +24,7 @@
 #include <asm/sections.h>
 #include <asm/exceptions.h>
 #include <asm/unwind.h>
+#include <asm/switch_to.h>
 
 struct stack_trace;
 
diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S
index ac0e1a5d4782..109e9d86ade4 100644
--- a/arch/microblaze/kernel/vmlinux.lds.S
+++ b/arch/microblaze/kernel/vmlinux.lds.S
@@ -44,7 +44,7 @@ SECTIONS {
 	__fdt_blob : AT(ADDR(__fdt_blob) - LOAD_OFFSET) {
 		_fdt_start = . ;		/* place for fdt blob */
 		*(__fdt_blob) ;			/* Any link-placed DTB */
-	        . = _fdt_start + 0x4000;	/* Pad up to 16kbyte */
+	        . = _fdt_start + 0x8000;	/* Pad up to 32kbyte */
 		_fdt_end = . ;
 	}
 
diff --git a/arch/microblaze/lib/memcpy.c b/arch/microblaze/lib/memcpy.c
index 52746e718dfa..fe9c53fafdea 100644
--- a/arch/microblaze/lib/memcpy.c
+++ b/arch/microblaze/lib/memcpy.c
@@ -30,7 +30,6 @@
 #include <linux/module.h>
 
 #include <linux/string.h>
-#include <asm/system.h>
 
 #ifdef __HAVE_ARCH_MEMCPY
 #ifndef CONFIG_OPT_LIB_FUNCTION
diff --git a/arch/microblaze/lib/uaccess_old.S b/arch/microblaze/lib/uaccess_old.S
index f037266cdaf3..f085995ee848 100644
--- a/arch/microblaze/lib/uaccess_old.S
+++ b/arch/microblaze/lib/uaccess_old.S
@@ -122,22 +122,22 @@ __strnlen_user:
 15:	swi	r24, r5, 0x0018 + offset;	\
 16:	swi	r25, r5, 0x001C + offset;	\
 	.section __ex_table,"a";		\
-	.word	1b, 0f;				\
-	.word	2b, 0f;				\
-	.word	3b, 0f;				\
-	.word	4b, 0f;				\
-	.word	5b, 0f;				\
-	.word	6b, 0f;				\
-	.word	7b, 0f;				\
-	.word	8b, 0f;				\
-	.word	9b, 0f;				\
-	.word	10b, 0f;			\
-	.word	11b, 0f;			\
-	.word	12b, 0f;			\
-	.word	13b, 0f;			\
-	.word	14b, 0f;			\
-	.word	15b, 0f;			\
-	.word	16b, 0f;			\
+	.word	1b, 33f;			\
+	.word	2b, 33f;			\
+	.word	3b, 33f;			\
+	.word	4b, 33f;			\
+	.word	5b, 33f;			\
+	.word	6b, 33f;			\
+	.word	7b, 33f;			\
+	.word	8b, 33f;			\
+	.word	9b, 33f;			\
+	.word	10b, 33f;			\
+	.word	11b, 33f;			\
+	.word	12b, 33f;			\
+	.word	13b, 33f;			\
+	.word	14b, 33f;			\
+	.word	15b, 33f;			\
+	.word	16b, 33f;			\
 	.text
 
 #define COPY_80(offset)	\
@@ -190,14 +190,17 @@ w2:	sw	r4, r5, r3
 
 .align 4 /* Alignment is important to keep icache happy */
 page:	/* Create room on stack and save registers for storign values */
-	addik   r1, r1, -32
-	swi	r19, r1, 4
-	swi	r20, r1, 8
-	swi	r21, r1, 12
-	swi	r22, r1, 16
-	swi	r23, r1, 20
-	swi	r24, r1, 24
-	swi	r25, r1, 28
+	addik   r1, r1, -40
+	swi	r5, r1, 0
+	swi	r6, r1, 4
+	swi	r7, r1, 8
+	swi	r19, r1, 12
+	swi	r20, r1, 16
+	swi	r21, r1, 20
+	swi	r22, r1, 24
+	swi	r23, r1, 28
+	swi	r24, r1, 32
+	swi	r25, r1, 36
 loop:	/* r4, r19, r20, r21, r22, r23, r24, r25 are used for storing values */
 	/* Loop unrolling to get performance boost */
 	COPY_80(0x000);
@@ -205,21 +208,44 @@ loop:	/* r4, r19, r20, r21, r22, r23, r24, r25 are used for storing values */
 	COPY_80(0x100);
 	COPY_80(0x180);
 	/* copy loop */
-	addik	r6, r6, 0x200
-	addik	r7, r7, -0x200
-	bneid	r7, loop
-	addik	r5, r5, 0x200
+	addik   r6, r6, 0x200
+	addik   r7, r7, -0x200
+	bneid   r7, loop
+	addik   r5, r5, 0x200
+
 	/* Restore register content */
-	lwi	r19, r1, 4
-	lwi	r20, r1, 8
-	lwi	r21, r1, 12
-	lwi	r22, r1, 16
-	lwi	r23, r1, 20
-	lwi	r24, r1, 24
-	lwi	r25, r1, 28
-	addik   r1, r1, 32
+	lwi	r5, r1, 0
+	lwi	r6, r1, 4
+	lwi	r7, r1, 8
+	lwi	r19, r1, 12
+	lwi	r20, r1, 16
+	lwi	r21, r1, 20
+	lwi	r22, r1, 24
+	lwi	r23, r1, 28
+	lwi	r24, r1, 32
+	lwi	r25, r1, 36
+	addik   r1, r1, 40
 	/* return back */
+	addik	r3, r0, 0
+	rtsd	r15, 8
+	nop
+
+/* Fault case - return temp count */
+33:
 	addik	r3, r7, 0
+	/* Restore register content */
+	lwi	r5, r1, 0
+	lwi	r6, r1, 4
+	lwi	r7, r1, 8
+	lwi	r19, r1, 12
+	lwi	r20, r1, 16
+	lwi	r21, r1, 20
+	lwi	r22, r1, 24
+	lwi	r23, r1, 28
+	lwi	r24, r1, 32
+	lwi	r25, r1, 36
+	addik   r1, r1, 40
+	/* return back */
 	rtsd	r15, 8
 	nop
 
diff --git a/arch/microblaze/mm/Makefile b/arch/microblaze/mm/Makefile
index 09c49ed87235..7313bd8acbb7 100644
--- a/arch/microblaze/mm/Makefile
+++ b/arch/microblaze/mm/Makefile
@@ -5,3 +5,4 @@
 obj-y := consistent.o init.o
 
 obj-$(CONFIG_MMU) += pgtable.o mmu_context.o fault.o
+obj-$(CONFIG_HIGHMEM) += highmem.o
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index ae97d2ccdc22..c38a265846de 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -33,7 +33,6 @@
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <asm/exceptions.h>
 
diff --git a/arch/microblaze/mm/highmem.c b/arch/microblaze/mm/highmem.c
new file mode 100644
index 000000000000..7d78838e8bfa
--- /dev/null
+++ b/arch/microblaze/mm/highmem.c
@@ -0,0 +1,88 @@
+/*
+ * highmem.c: virtual kernel memory mappings for high memory
+ *
+ * PowerPC version, stolen from the i386 version.
+ *
+ * Used in CONFIG_HIGHMEM systems for memory pages which
+ * are not addressable by direct kernel virtual addresses.
+ *
+ * Copyright (C) 1999 Gerhard Wichert, Siemens AG
+ *		      Gerhard.Wichert@pdb.siemens.de
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * up to 16 Terrabyte physical memory. With current x86 CPUs
+ * we now support up to 64 Gigabytes physical RAM.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ *
+ * Reworked for PowerPC by various contributors. Moved from
+ * highmem.h by Benjamin Herrenschmidt (c) 2009 IBM Corp.
+ */
+
+#include <linux/highmem.h>
+#include <linux/module.h>
+
+/*
+ * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
+ * gives a more generic (and caching) interface. But kmap_atomic can
+ * be used in IRQ contexts, so in some (very limited) cases we need
+ * it.
+ */
+#include <asm/tlbflush.h>
+
+void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+{
+
+	unsigned long vaddr;
+	int idx, type;
+
+	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	pagefault_disable();
+	if (!PageHighMem(page))
+		return page_address(page);
+
+
+	type = kmap_atomic_idx_push();
+	idx = type + KM_TYPE_NR*smp_processor_id();
+	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+#ifdef CONFIG_DEBUG_HIGHMEM
+	BUG_ON(!pte_none(*(kmap_pte-idx)));
+#endif
+	set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot));
+	local_flush_tlb_page(NULL, vaddr);
+
+	return (void *) vaddr;
+}
+EXPORT_SYMBOL(kmap_atomic_prot);
+
+void __kunmap_atomic(void *kvaddr)
+{
+	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+	int type;
+
+	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
+		pagefault_enable();
+		return;
+	}
+
+	type = kmap_atomic_idx();
+#ifdef CONFIG_DEBUG_HIGHMEM
+	{
+		unsigned int idx;
+
+		idx = type + KM_TYPE_NR * smp_processor_id();
+		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
+
+		/*
+		 * force other mappings to Oops if they'll try to access
+		 * this pte without first remap it
+		 */
+		pte_clear(&init_mm, vaddr, kmap_pte-idx);
+		local_flush_tlb_page(NULL, vaddr);
+	}
+#endif
+	kmap_atomic_idx_pop();
+	pagefault_enable();
+}
+EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 565d193c7ebf..ce80823051ba 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -24,6 +24,7 @@
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
 #include <asm/tlb.h>
+#include <asm/fixmap.h>
 
 /* Use for MMU and noMMU because of PCI generic code */
 int mem_init_done;
@@ -44,9 +45,56 @@ char *klimit = _end;
  */
 unsigned long memory_start;
 EXPORT_SYMBOL(memory_start);
-unsigned long memory_end; /* due to mm/nommu.c */
 unsigned long memory_size;
 EXPORT_SYMBOL(memory_size);
+unsigned long lowmem_size;
+
+#ifdef CONFIG_HIGHMEM
+pte_t *kmap_pte;
+EXPORT_SYMBOL(kmap_pte);
+pgprot_t kmap_prot;
+EXPORT_SYMBOL(kmap_prot);
+
+static inline pte_t *virt_to_kpte(unsigned long vaddr)
+{
+	return pte_offset_kernel(pmd_offset(pgd_offset_k(vaddr),
+			vaddr), vaddr);
+}
+
+static void __init highmem_init(void)
+{
+	pr_debug("%x\n", (u32)PKMAP_BASE);
+	map_page(PKMAP_BASE, 0, 0);	/* XXX gross */
+	pkmap_page_table = virt_to_kpte(PKMAP_BASE);
+
+	kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
+	kmap_prot = PAGE_KERNEL;
+}
+
+static unsigned long highmem_setup(void)
+{
+	unsigned long pfn;
+	unsigned long reservedpages = 0;
+
+	for (pfn = max_low_pfn; pfn < max_pfn; ++pfn) {
+		struct page *page = pfn_to_page(pfn);
+
+		/* FIXME not sure about */
+		if (memblock_is_reserved(pfn << PAGE_SHIFT))
+			continue;
+		ClearPageReserved(page);
+		init_page_count(page);
+		__free_page(page);
+		totalhigh_pages++;
+		reservedpages++;
+	}
+	totalram_pages += totalhigh_pages;
+	printk(KERN_INFO "High memory: %luk\n",
+					totalhigh_pages << (PAGE_SHIFT-10));
+
+	return reservedpages;
+}
+#endif /* CONFIG_HIGHMEM */
 
 /*
  * paging_init() sets up the page tables - in fact we've already done this.
@@ -54,17 +102,28 @@ EXPORT_SYMBOL(memory_size);
 static void __init paging_init(void)
 {
 	unsigned long zones_size[MAX_NR_ZONES];
+#ifdef CONFIG_MMU
+	int idx;
+
+	/* Setup fixmaps */
+	for (idx = 0; idx < __end_of_fixed_addresses; idx++)
+		clear_fixmap(idx);
+#endif
 
 	/* Clean every zones */
 	memset(zones_size, 0, sizeof(zones_size));
 
-	/*
-	 * old: we can DMA to/from any address.put all page into ZONE_DMA
-	 * We use only ZONE_NORMAL
-	 */
-	zones_size[ZONE_NORMAL] = max_mapnr;
+#ifdef CONFIG_HIGHMEM
+	highmem_init();
 
-	free_area_init(zones_size);
+	zones_size[ZONE_DMA] = max_low_pfn;
+	zones_size[ZONE_HIGHMEM] = max_pfn;
+#else
+	zones_size[ZONE_DMA] = max_pfn;
+#endif
+
+	/* We don't have holes in memory map */
+	free_area_init_nodes(zones_size);
 }
 
 void __init setup_memory(void)
@@ -78,32 +137,31 @@ void __init setup_memory(void)
 	/* Find main memory where is the kernel */
 	for_each_memblock(memory, reg) {
 		memory_start = (u32)reg->base;
-		memory_end = (u32) reg->base + reg->size;
+		lowmem_size = reg->size;
 		if ((memory_start <= (u32)_text) &&
-					((u32)_text <= memory_end)) {
-			memory_size = memory_end - memory_start;
+			((u32)_text <= (memory_start + lowmem_size - 1))) {
+			memory_size = lowmem_size;
 			PAGE_OFFSET = memory_start;
-			printk(KERN_INFO "%s: Main mem: 0x%x-0x%x, "
+			printk(KERN_INFO "%s: Main mem: 0x%x, "
 				"size 0x%08x\n", __func__, (u32) memory_start,
-					(u32) memory_end, (u32) memory_size);
+					(u32) memory_size);
 			break;
 		}
 	}
 
-	if (!memory_start || !memory_end) {
-		panic("%s: Missing memory setting 0x%08x-0x%08x\n",
-			__func__, (u32) memory_start, (u32) memory_end);
+	if (!memory_start || !memory_size) {
+		panic("%s: Missing memory setting 0x%08x, size=0x%08x\n",
+			__func__, (u32) memory_start, (u32) memory_size);
 	}
 
 	/* reservation of region where is the kernel */
 	kernel_align_start = PAGE_DOWN((u32)_text);
 	/* ALIGN can be remove because _end in vmlinux.lds.S is align */
 	kernel_align_size = PAGE_UP((u32)klimit) - kernel_align_start;
-	memblock_reserve(kernel_align_start, kernel_align_size);
-	printk(KERN_INFO "%s: kernel addr=0x%08x-0x%08x size=0x%08x\n",
+	printk(KERN_INFO "%s: kernel addr:0x%08x-0x%08x size=0x%08x\n",
 		__func__, kernel_align_start, kernel_align_start
 			+ kernel_align_size, kernel_align_size);
-
+	memblock_reserve(kernel_align_start, kernel_align_size);
 #endif
 	/*
 	 * Kernel:
@@ -120,11 +178,13 @@ void __init setup_memory(void)
 	min_low_pfn = memory_start >> PAGE_SHIFT; /* minimum for allocation */
 	/* RAM is assumed contiguous */
 	num_physpages = max_mapnr = memory_size >> PAGE_SHIFT;
-	max_pfn = max_low_pfn = memory_end >> PAGE_SHIFT;
+	max_low_pfn = ((u64)memory_start + (u64)lowmem_size) >> PAGE_SHIFT;
+	max_pfn = ((u64)memory_start + (u64)memory_size) >> PAGE_SHIFT;
 
 	printk(KERN_INFO "%s: max_mapnr: %#lx\n", __func__, max_mapnr);
 	printk(KERN_INFO "%s: min_low_pfn: %#lx\n", __func__, min_low_pfn);
 	printk(KERN_INFO "%s: max_low_pfn: %#lx\n", __func__, max_low_pfn);
+	printk(KERN_INFO "%s: max_pfn: %#lx\n", __func__, max_pfn);
 
 	/*
 	 * Find an area to use for the bootmem bitmap.
@@ -137,15 +197,39 @@ void __init setup_memory(void)
 		PFN_UP(TOPHYS((u32)klimit)), min_low_pfn, max_low_pfn);
 	memblock_reserve(PFN_UP(TOPHYS((u32)klimit)) << PAGE_SHIFT, map_size);
 
+	/* Add active regions with valid PFNs */
+	for_each_memblock(memory, reg) {
+		unsigned long start_pfn, end_pfn;
+
+		start_pfn = memblock_region_memory_base_pfn(reg);
+		end_pfn = memblock_region_memory_end_pfn(reg);
+		memblock_set_node(start_pfn << PAGE_SHIFT,
+					(end_pfn - start_pfn) << PAGE_SHIFT, 0);
+	}
+
 	/* free bootmem is whole main memory */
-	free_bootmem(memory_start, memory_size);
+	free_bootmem_with_active_regions(0, max_low_pfn);
 
 	/* reserve allocate blocks */
 	for_each_memblock(reserved, reg) {
-		pr_debug("reserved - 0x%08x-0x%08x\n",
-			 (u32) reg->base, (u32) reg->size);
-		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+		unsigned long top = reg->base + reg->size - 1;
+
+		pr_debug("reserved - 0x%08x-0x%08x, %lx, %lx\n",
+			 (u32) reg->base, (u32) reg->size, top,
+						memory_start + lowmem_size - 1);
+
+		if (top <= (memory_start + lowmem_size - 1)) {
+			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+		} else if (reg->base < (memory_start + lowmem_size - 1)) {
+			unsigned long trunc_size = memory_start + lowmem_size -
+								reg->base;
+			reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
+		}
 	}
+
+	/* XXX need to clip this if using highmem? */
+	sparse_memory_present_with_active_regions(0);
+
 #ifdef CONFIG_MMU
 	init_bootmem_done = 1;
 #endif
@@ -190,13 +274,58 @@ void free_initmem(void)
 
 void __init mem_init(void)
 {
-	high_memory = (void *)__va(memory_end);
+	pg_data_t *pgdat;
+	unsigned long reservedpages = 0, codesize, initsize, datasize, bsssize;
+
+	high_memory = (void *)__va(memory_start + lowmem_size - 1);
+
 	/* this will put all memory onto the freelists */
 	totalram_pages += free_all_bootmem();
 
-	printk(KERN_INFO "Memory: %luk/%luk available\n",
-	       nr_free_pages() << (PAGE_SHIFT-10),
-	       num_physpages << (PAGE_SHIFT-10));
+	for_each_online_pgdat(pgdat) {
+		unsigned long i;
+		struct page *page;
+
+		for (i = 0; i < pgdat->node_spanned_pages; i++) {
+			if (!pfn_valid(pgdat->node_start_pfn + i))
+				continue;
+			page = pgdat_page_nr(pgdat, i);
+			if (PageReserved(page))
+				reservedpages++;
+		}
+	}
+
+#ifdef CONFIG_HIGHMEM
+	reservedpages -= highmem_setup();
+#endif
+
+	codesize = (unsigned long)&_sdata - (unsigned long)&_stext;
+	datasize = (unsigned long)&_edata - (unsigned long)&_sdata;
+	initsize = (unsigned long)&__init_end - (unsigned long)&__init_begin;
+	bsssize = (unsigned long)&__bss_stop - (unsigned long)&__bss_start;
+
+	pr_info("Memory: %luk/%luk available (%luk kernel code, "
+		"%luk reserved, %luk data, %luk bss, %luk init)\n",
+		nr_free_pages() << (PAGE_SHIFT-10),
+		num_physpages << (PAGE_SHIFT-10),
+		codesize >> 10,
+		reservedpages << (PAGE_SHIFT-10),
+		datasize >> 10,
+		bsssize >> 10,
+		initsize >> 10);
+
+#ifdef CONFIG_MMU
+	pr_info("Kernel virtual memory layout:\n");
+	pr_info("  * 0x%08lx..0x%08lx  : fixmap\n", FIXADDR_START, FIXADDR_TOP);
+#ifdef CONFIG_HIGHMEM
+	pr_info("  * 0x%08lx..0x%08lx  : highmem PTEs\n",
+		PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
+#endif /* CONFIG_HIGHMEM */
+	pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
+		ioremap_bot, ioremap_base);
+	pr_info("  * 0x%08lx..0x%08lx  : vmalloc & ioremap\n",
+		(unsigned long)VMALLOC_START, VMALLOC_END);
+#endif
 	mem_init_done = 1;
 }
 
@@ -226,7 +355,6 @@ static void mm_cmdline_setup(void)
 		maxmem = memparse(p, &p);
 		if (maxmem && memory_size > maxmem) {
 			memory_size = maxmem;
-			memory_end = memory_start + memory_size;
 			memblock.memory.regions[0].size = memory_size;
 		}
 	}
@@ -270,15 +398,26 @@ asmlinkage void __init mmu_init(void)
 		machine_restart(NULL);
 	}
 
-	if ((u32) memblock.memory.regions[0].size < 0x1000000) {
-		printk(KERN_EMERG "Memory must be greater than 16MB\n");
+	if ((u32) memblock.memory.regions[0].size < 0x400000) {
+		printk(KERN_EMERG "Memory must be greater than 4MB\n");
+		machine_restart(NULL);
+	}
+
+	if ((u32) memblock.memory.regions[0].size < kernel_tlb) {
+		printk(KERN_EMERG "Kernel size is greater than memory node\n");
 		machine_restart(NULL);
 	}
+
 	/* Find main memory where the kernel is */
 	memory_start = (u32) memblock.memory.regions[0].base;
-	memory_end = (u32) memblock.memory.regions[0].base +
-				(u32) memblock.memory.regions[0].size;
-	memory_size = memory_end - memory_start;
+	lowmem_size = memory_size = (u32) memblock.memory.regions[0].size;
+
+	if (lowmem_size > CONFIG_LOWMEM_SIZE) {
+		lowmem_size = CONFIG_LOWMEM_SIZE;
+#ifndef CONFIG_HIGHMEM
+		memory_size = lowmem_size;
+#endif
+	}
 
 	mm_cmdline_setup(); /* FIXME parse args from command line - not used */
 
@@ -305,15 +444,20 @@ asmlinkage void __init mmu_init(void)
 	/* Map in all of RAM starting at CONFIG_KERNEL_START */
 	mapin_ram();
 
-#ifdef CONFIG_HIGHMEM_START_BOOL
-	ioremap_base = CONFIG_HIGHMEM_START;
+	/* Extend vmalloc and ioremap area as big as possible */
+#ifdef CONFIG_HIGHMEM
+	ioremap_base = ioremap_bot = PKMAP_BASE;
 #else
-	ioremap_base = 0xfe000000UL;	/* for now, could be 0xfffff000 */
-#endif /* CONFIG_HIGHMEM_START_BOOL */
-	ioremap_bot = ioremap_base;
+	ioremap_base = ioremap_bot = FIXADDR_START;
+#endif
 
 	/* Initialize the context management stuff */
 	mmu_context_init();
+
+	/* Shortly after that, the entire linear mapping will be available */
+	/* This will also cause that unflatten device tree will be allocated
+	 * inside 768MB limit */
+	memblock_set_current_limit(memory_start + lowmem_size - 1);
 }
 
 /* This is only called until mem_init is done. */
@@ -324,11 +468,11 @@ void __init *early_get_page(void)
 		p = alloc_bootmem_pages(PAGE_SIZE);
 	} else {
 		/*
-		 * Mem start + 32MB -> here is limit
+		 * Mem start + kernel_tlb -> here is limit
 		 * because of mem mapping from head.S
 		 */
 		p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
-					memory_start + 0x2000000));
+					memory_start + kernel_tlb));
 	}
 	return p;
 }
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 59bf2335a4ce..d1c06d07fed8 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -37,6 +37,7 @@
 #include <linux/io.h>
 #include <asm/mmu.h>
 #include <asm/sections.h>
+#include <asm/fixmap.h>
 
 #define flush_HPTE(X, va, pg)	_tlbie(va)
 
@@ -44,11 +45,6 @@ unsigned long ioremap_base;
 unsigned long ioremap_bot;
 EXPORT_SYMBOL(ioremap_bot);
 
-/* The maximum lowmem defaults to 768Mb, but this can be configured to
- * another value.
- */
-#define MAX_LOW_MEM	CONFIG_LOWMEM_SIZE
-
 #ifndef CONFIG_SMP
 struct pgtable_cache_struct quicklists;
 #endif
@@ -80,7 +76,7 @@ static void __iomem *__ioremap(phys_addr_t addr, unsigned long size,
 		!(p >= virt_to_phys((unsigned long)&__bss_stop) &&
 		p < virt_to_phys((unsigned long)__bss_stop))) {
 		printk(KERN_WARNING "__ioremap(): phys addr "PTE_FMT
-			" is RAM lr %p\n", (unsigned long)p,
+			" is RAM lr %pf\n", (unsigned long)p,
 			__builtin_return_address(0));
 		return NULL;
 	}
@@ -171,7 +167,7 @@ void __init mapin_ram(void)
 
 	v = CONFIG_KERNEL_START;
 	p = memory_start;
-	for (s = 0; s < memory_size; s += PAGE_SIZE) {
+	for (s = 0; s < lowmem_size; s += PAGE_SIZE) {
 		f = _PAGE_PRESENT | _PAGE_ACCESSED |
 				_PAGE_SHARED | _PAGE_HWEXEC;
 		if ((char *) v < _stext || (char *) v >= _etext)
@@ -254,3 +250,13 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 	}
 	return pte;
 }
+
+void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags)
+{
+	unsigned long address = __fix_to_virt(idx);
+
+	if (idx >= __end_of_fixed_addresses)
+		BUG();
+
+	map_page(address, phys, pgprot_val(flags));
+}
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index edbbae17e820..ce30e2f91d77 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2457,6 +2457,7 @@ config MIPS32_COMPAT
 config COMPAT
 	bool
 	depends on MIPS32_COMPAT
+	select ARCH_WANT_OLD_COMPAT_IPC
 	default y
 
 config SYSVIPC_COMPAT
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index b6bb92c16a47..41dd00884975 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -157,7 +157,7 @@ static void octeon_dma_sync_sg_for_device(struct device *dev,
 }
 
 static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp)
+	dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	void *ret;
 
@@ -192,7 +192,7 @@ static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
 }
 
 static void octeon_dma_free_coherent(struct device *dev, size_t size,
-	void *vaddr, dma_addr_t dma_handle)
+	void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	int order = get_order(size);
 
@@ -240,8 +240,8 @@ EXPORT_SYMBOL(dma_to_phys);
 
 static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
 	.dma_map_ops = {
-		.alloc_coherent = octeon_dma_alloc_coherent,
-		.free_coherent = octeon_dma_free_coherent,
+		.alloc = octeon_dma_alloc_coherent,
+		.free = octeon_dma_free_coherent,
 		.map_page = octeon_dma_map_page,
 		.unmap_page = swiotlb_unmap_page,
 		.map_sg = octeon_dma_map_sg,
@@ -325,8 +325,8 @@ void __init plat_swiotlb_setup(void)
 #ifdef CONFIG_PCI
 static struct octeon_dma_map_ops _octeon_pci_dma_map_ops = {
 	.dma_map_ops = {
-		.alloc_coherent = octeon_dma_alloc_coherent,
-		.free_coherent = octeon_dma_free_coherent,
+		.alloc = octeon_dma_alloc_coherent,
+		.free = octeon_dma_free_coherent,
 		.map_page = octeon_dma_map_page,
 		.unmap_page = swiotlb_unmap_page,
 		.map_sg = octeon_dma_map_sg,
diff --git a/arch/mips/cavium-octeon/flash_setup.c b/arch/mips/cavium-octeon/flash_setup.c
index 0a430e06f5e5..e44a55bc7f0d 100644
--- a/arch/mips/cavium-octeon/flash_setup.c
+++ b/arch/mips/cavium-octeon/flash_setup.c
@@ -60,7 +60,7 @@ static int __init flash_init(void)
 		if (mymtd) {
 			mymtd->owner = THIS_MODULE;
 			mtd_device_parse_register(mymtd, part_probe_types,
-						  0, NULL, 0);
+						  NULL, NULL, 0);
 		} else {
 			pr_err("Failed to register MTD device for flash\n");
 		}
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 260b27367347..d3a9f012aa0a 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -24,7 +24,6 @@
 #include <asm/processor.h>
 #include <asm/reboot.h>
 #include <asm/smp-ops.h>
-#include <asm/system.h>
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
 #include <asm/bootinfo.h>
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index b1535fe409d4..97e7ce9b50ed 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -15,8 +15,8 @@
 #include <linux/module.h>
 
 #include <asm/mmu_context.h>
-#include <asm/system.h>
 #include <asm/time.h>
+#include <asm/setup.h>
 
 #include <asm/octeon/octeon.h>
 
@@ -78,7 +78,7 @@ static inline void octeon_send_ipi_mask(const struct cpumask *mask,
 }
 
 /**
- * Detect available CPUs, populate cpu_possible_map
+ * Detect available CPUs, populate cpu_possible_mask
  */
 static void octeon_smp_hotplug_setup(void)
 {
@@ -268,7 +268,7 @@ static int octeon_cpu_disable(void)
 
 	spin_lock(&smp_reserve_lock);
 
-	cpu_clear(cpu, cpu_online_map);
+	set_cpu_online(cpu, false);
 	cpu_clear(cpu, cpu_callin_map);
 	local_irq_disable();
 	fixup_irqs();
diff --git a/arch/mips/configs/db1300_defconfig b/arch/mips/configs/db1300_defconfig
index c38b190151c4..3590ab5d9791 100644
--- a/arch/mips/configs/db1300_defconfig
+++ b/arch/mips/configs/db1300_defconfig
@@ -133,7 +133,7 @@ CONFIG_BLK_DEV_BSG=y
 CONFIG_IOSCHED_NOOP=y
 CONFIG_DEFAULT_NOOP=y
 CONFIG_DEFAULT_IOSCHED="noop"
-CONFIG_INLINE_SPIN_UNLOCK=y
+# CONFIG_UNINLINE_SPIN_UNLOCK is not set
 CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
 CONFIG_INLINE_READ_UNLOCK=y
 CONFIG_INLINE_READ_UNLOCK_IRQ=y
diff --git a/arch/mips/dec/ecc-berr.c b/arch/mips/dec/ecc-berr.c
index 7abce661b90f..5abf4e894216 100644
--- a/arch/mips/dec/ecc-berr.c
+++ b/arch/mips/dec/ecc-berr.c
@@ -24,7 +24,6 @@
 #include <asm/irq_regs.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 #include <asm/dec/ecc.h>
diff --git a/arch/mips/dec/kn01-berr.c b/arch/mips/dec/kn01-berr.c
index 94d23b4a7dc3..44d8a87a8a68 100644
--- a/arch/mips/dec/kn01-berr.c
+++ b/arch/mips/dec/kn01-berr.c
@@ -22,7 +22,6 @@
 #include <asm/mipsregs.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
 
diff --git a/arch/mips/dec/kn02xa-berr.c b/arch/mips/dec/kn02xa-berr.c
index 07ca5405d48d..ebb73c51d821 100644
--- a/arch/mips/dec/kn02xa-berr.c
+++ b/arch/mips/dec/kn02xa-berr.c
@@ -21,7 +21,6 @@
 #include <asm/addrspace.h>
 #include <asm/irq_regs.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 #include <asm/dec/kn02ca.h>
diff --git a/arch/mips/dec/wbflush.c b/arch/mips/dec/wbflush.c
index 925c0525344b..43feddd5e19c 100644
--- a/arch/mips/dec/wbflush.c
+++ b/arch/mips/dec/wbflush.c
@@ -17,8 +17,8 @@
 #include <linux/init.h>
 
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/wbflush.h>
+#include <asm/barrier.h>
 
 static void wbflush_kn01(void);
 static void wbflush_kn210(void);
diff --git a/arch/mips/emma/markeins/irq.c b/arch/mips/emma/markeins/irq.c
index 7798887a1288..b5f08255d9c7 100644
--- a/arch/mips/emma/markeins/irq.c
+++ b/arch/mips/emma/markeins/irq.c
@@ -27,7 +27,6 @@
 #include <linux/delay.h>
 
 #include <asm/irq_cpu.h>
-#include <asm/system.h>
 #include <asm/mipsregs.h>
 #include <asm/addrspace.h>
 #include <asm/bootinfo.h>
diff --git a/arch/mips/fw/arc/misc.c b/arch/mips/fw/arc/misc.c
index 29627fbae7ad..7cf80ca2c1d2 100644
--- a/arch/mips/fw/arc/misc.c
+++ b/arch/mips/fw/arc/misc.c
@@ -17,7 +17,6 @@
 #include <asm/fw/arc/types.h>
 #include <asm/sgialib.h>
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 
 VOID
 ArcHalt(VOID)
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 1d93f81d57e7..3f4c5cb6433e 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -18,8 +18,8 @@
 #include <linux/types.h>
 #include <asm/barrier.h>
 #include <asm/cpu-features.h>
+#include <asm/cmpxchg.h>
 #include <asm/war.h>
-#include <asm/system.h>
 
 #define ATOMIC_INIT(i)    { (i) }
 
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index c0884f02d3a6..f7fdc24e972d 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -8,6 +8,8 @@
 #ifndef __ASM_BARRIER_H
 #define __ASM_BARRIER_H
 
+#include <asm/addrspace.h>
+
 /*
  * read_barrier_depends - Flush all pending reads that subsequents reads
  * depend on.
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index d8d1c2805ac7..285a41fa0b18 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -9,6 +9,130 @@
 #define __ASM_CMPXCHG_H
 
 #include <linux/irqflags.h>
+#include <asm/war.h>
+
+static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
+{
+	__u32 retval;
+
+	smp_mb__before_llsc();
+
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {
+		unsigned long dummy;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	ll	%0, %3			# xchg_u32	\n"
+		"	.set	mips0					\n"
+		"	move	%2, %z4					\n"
+		"	.set	mips3					\n"
+		"	sc	%2, %1					\n"
+		"	beqzl	%2, 1b					\n"
+		"	.set	mips0					\n"
+		: "=&r" (retval), "=m" (*m), "=&r" (dummy)
+		: "R" (*m), "Jr" (val)
+		: "memory");
+	} else if (kernel_uses_llsc) {
+		unsigned long dummy;
+
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	ll	%0, %3		# xchg_u32	\n"
+			"	.set	mips0				\n"
+			"	move	%2, %z4				\n"
+			"	.set	mips3				\n"
+			"	sc	%2, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (retval), "=m" (*m), "=&r" (dummy)
+			: "R" (*m), "Jr" (val)
+			: "memory");
+		} while (unlikely(!dummy));
+	} else {
+		unsigned long flags;
+
+		raw_local_irq_save(flags);
+		retval = *m;
+		*m = val;
+		raw_local_irq_restore(flags);	/* implies memory barrier  */
+	}
+
+	smp_llsc_mb();
+
+	return retval;
+}
+
+#ifdef CONFIG_64BIT
+static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
+{
+	__u64 retval;
+
+	smp_mb__before_llsc();
+
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {
+		unsigned long dummy;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	lld	%0, %3			# xchg_u64	\n"
+		"	move	%2, %z4					\n"
+		"	scd	%2, %1					\n"
+		"	beqzl	%2, 1b					\n"
+		"	.set	mips0					\n"
+		: "=&r" (retval), "=m" (*m), "=&r" (dummy)
+		: "R" (*m), "Jr" (val)
+		: "memory");
+	} else if (kernel_uses_llsc) {
+		unsigned long dummy;
+
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	lld	%0, %3		# xchg_u64	\n"
+			"	move	%2, %z4				\n"
+			"	scd	%2, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (retval), "=m" (*m), "=&r" (dummy)
+			: "R" (*m), "Jr" (val)
+			: "memory");
+		} while (unlikely(!dummy));
+	} else {
+		unsigned long flags;
+
+		raw_local_irq_save(flags);
+		retval = *m;
+		*m = val;
+		raw_local_irq_restore(flags);	/* implies memory barrier  */
+	}
+
+	smp_llsc_mb();
+
+	return retval;
+}
+#else
+extern __u64 __xchg_u64_unsupported_on_32bit_kernels(volatile __u64 * m, __u64 val);
+#define __xchg_u64 __xchg_u64_unsupported_on_32bit_kernels
+#endif
+
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+	switch (size) {
+	case 4:
+		return __xchg_u32(ptr, x);
+	case 8:
+		return __xchg_u64(ptr, x);
+	}
+
+	return x;
+}
+
+#define xchg(ptr, x)							\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) & ~0xc);				\
+									\
+	((__typeof__(*(ptr)))						\
+		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))));	\
+})
 
 #define __HAVE_ARCH_CMPXCHG 1
 
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 7aa37ddfca4b..be39a12901c6 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -57,25 +57,31 @@ dma_set_mask(struct device *dev, u64 mask)
 extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction);
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t gfp)
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t gfp,
+				    struct dma_attrs *attrs)
 {
 	void *ret;
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
-	ret = ops->alloc_coherent(dev, size, dma_handle, gfp);
+	ret = ops->alloc(dev, size, dma_handle, gfp, attrs);
 
 	debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
 
 	return ret;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
-	ops->free_coherent(dev, size, vaddr, dma_handle);
+	ops->free(dev, size, vaddr, dma_handle, attrs);
 
 	debug_dma_free_coherent(dev, size, vaddr, dma_handle);
 }
diff --git a/arch/mips/include/asm/dma.h b/arch/mips/include/asm/dma.h
index 2d47da62d5a7..f5097f65a8ab 100644
--- a/arch/mips/include/asm/dma.h
+++ b/arch/mips/include/asm/dma.h
@@ -15,7 +15,6 @@
 #include <asm/io.h>			/* need byte IO */
 #include <linux/spinlock.h>		/* And spinlocks */
 #include <linux/delay.h>
-#include <asm/system.h>
 
 
 #ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
diff --git a/arch/mips/include/asm/exec.h b/arch/mips/include/asm/exec.h
new file mode 100644
index 000000000000..c1f6afa4bc4f
--- /dev/null
+++ b/arch/mips/include/asm/exec.h
@@ -0,0 +1,17 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994, 95, 96, 97, 98, 99, 2003, 06 by Ralf Baechle
+ * Copyright (C) 1996 by Paul M. Antoine
+ * Copyright (C) 1999 Silicon Graphics
+ * Kevin D. Kissell, kevink@mips.org and Carsten Langgaard, carstenl@mips.com
+ * Copyright (C) 2000 MIPS Technologies, Inc.
+ */
+#ifndef _ASM_EXEC_H
+#define _ASM_EXEC_H
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif /* _ASM_EXEC_H */
diff --git a/arch/mips/include/asm/mach-au1x00/au1000_dma.h b/arch/mips/include/asm/mach-au1x00/au1000_dma.h
index 59f5b55b2200..ba4cf0e91c8b 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000_dma.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000_dma.h
@@ -33,7 +33,6 @@
 #include <linux/io.h>		/* need byte IO */
 #include <linux/spinlock.h>	/* And spinlocks */
 #include <linux/delay.h>
-#include <asm/system.h>
 
 #define NUM_AU1000_DMA_CHANNELS	8
 
diff --git a/arch/mips/include/asm/posix_types.h b/arch/mips/include/asm/posix_types.h
index c200102c8586..e0308dcca135 100644
--- a/arch/mips/include/asm/posix_types.h
+++ b/arch/mips/include/asm/posix_types.h
@@ -17,128 +17,21 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-#if (_MIPS_SZLONG == 32)
-typedef unsigned long	__kernel_nlink_t;
-#endif
 #if (_MIPS_SZLONG == 64)
 typedef unsigned int	__kernel_nlink_t;
+#define __kernel_nlink_t __kernel_nlink_t
 #endif
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-#if (_MIPS_SZLONG == 32)
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-#endif
-#if (_MIPS_SZLONG == 64)
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-#endif
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef long		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
 
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-typedef __kernel_uid_t	__kernel_old_uid_t;
-typedef __kernel_gid_t	__kernel_old_gid_t;
-typedef unsigned int	__kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long      __kernel_loff_t;
-#endif
+typedef long		__kernel_daddr_t;
+#define __kernel_daddr_t __kernel_daddr_t
 
-typedef struct {
 #if (_MIPS_SZLONG == 32)
+typedef struct {
 	long	val[2];
-#endif
-#if (_MIPS_SZLONG == 64)
-	int	val[2];
-#endif
 } __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+#endif
 
-#if defined(__KERNEL__)
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_POSIX_TYPES_H */
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index c104f1039a69..20e9dcf42b27 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -19,7 +19,6 @@
 #include <asm/cpu-info.h>
 #include <asm/mipsregs.h>
 #include <asm/prefetch.h>
-#include <asm/system.h>
 
 /*
  * Return current * instruction pointer ("program counter").
@@ -356,6 +355,12 @@ unsigned long get_wchan(struct task_struct *p);
 #define ARCH_HAS_PREFETCHW
 #define prefetchw(x) __builtin_prefetch((x), 1, 1)
 
+/*
+ * See Documentation/scheduler/sched-arch.txt; prevents deadlock on SMP
+ * systems.
+ */
+#define __ARCH_WANT_UNLOCKED_CTXSW
+
 #endif
 
 #endif /* _ASM_PROCESSOR_H */
diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h
index 50511aac04e9..6dce6d8d09ab 100644
--- a/arch/mips/include/asm/setup.h
+++ b/arch/mips/include/asm/setup.h
@@ -5,6 +5,17 @@
 
 #ifdef  __KERNEL__
 extern void setup_early_printk(void);
+
+extern void set_handler(unsigned long offset, void *addr, unsigned long len);
+extern void set_uncached_handler(unsigned long offset, void *addr, unsigned long len);
+
+typedef void (*vi_handler_t)(void);
+extern void *set_vi_handler(int n, vi_handler_t addr);
+
+extern void *set_except_vector(int n, void *addr);
+extern unsigned long ebase;
+extern void per_cpu_trap_init(void);
+
 #endif /* __KERNEL__ */
 
 #endif /* __SETUP_H */
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
new file mode 100644
index 000000000000..5d33621b5658
--- /dev/null
+++ b/arch/mips/include/asm/switch_to.h
@@ -0,0 +1,85 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994, 95, 96, 97, 98, 99, 2003, 06 by Ralf Baechle
+ * Copyright (C) 1996 by Paul M. Antoine
+ * Copyright (C) 1999 Silicon Graphics
+ * Kevin D. Kissell, kevink@mips.org and Carsten Langgaard, carstenl@mips.com
+ * Copyright (C) 2000 MIPS Technologies, Inc.
+ */
+#ifndef _ASM_SWITCH_TO_H
+#define _ASM_SWITCH_TO_H
+
+#include <asm/cpu-features.h>
+#include <asm/watch.h>
+#include <asm/dsp.h>
+
+struct task_struct;
+
+/*
+ * switch_to(n) should switch tasks to task nr n, first
+ * checking that n isn't the current task, in which case it does nothing.
+ */
+extern asmlinkage void *resume(void *last, void *next, void *next_ti);
+
+extern unsigned int ll_bit;
+extern struct task_struct *ll_task;
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+
+/*
+ * Handle the scheduler resume end of FPU affinity management.  We do this
+ * inline to try to keep the overhead down. If we have been forced to run on
+ * a "CPU" with an FPU because of a previous high level of FP computation,
+ * but did not actually use the FPU during the most recent time-slice (CU1
+ * isn't set), we undo the restriction on cpus_allowed.
+ *
+ * We're not calling set_cpus_allowed() here, because we have no need to
+ * force prompt migration - we're already switching the current CPU to a
+ * different thread.
+ */
+
+#define __mips_mt_fpaff_switch_to(prev)					\
+do {									\
+	struct thread_info *__prev_ti = task_thread_info(prev);		\
+									\
+	if (cpu_has_fpu &&						\
+	    test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) &&		\
+	    (!(KSTK_STATUS(prev) & ST0_CU1))) {				\
+		clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND);		\
+		prev->cpus_allowed = prev->thread.user_cpus_allowed;	\
+	}								\
+	next->thread.emulated_fp = 0;					\
+} while(0)
+
+#else
+#define __mips_mt_fpaff_switch_to(prev) do { (void) (prev); } while (0)
+#endif
+
+#define __clear_software_ll_bit()					\
+do {									\
+	if (!__builtin_constant_p(cpu_has_llsc) || !cpu_has_llsc)	\
+		ll_bit = 0;						\
+} while (0)
+
+#define switch_to(prev, next, last)					\
+do {									\
+	__mips_mt_fpaff_switch_to(prev);				\
+	if (cpu_has_dsp)						\
+		__save_dsp(prev);					\
+	__clear_software_ll_bit();					\
+	(last) = resume(prev, next, task_thread_info(next));		\
+} while (0)
+
+#define finish_arch_switch(prev)					\
+do {									\
+	if (cpu_has_dsp)						\
+		__restore_dsp(current);					\
+	if (cpu_has_userlocal)						\
+		write_c0_userlocal(current_thread_info()->tp_value);	\
+	__restore_watch();						\
+} while (0)
+
+#endif /* _ASM_SWITCH_TO_H */
diff --git a/arch/mips/include/asm/system.h b/arch/mips/include/asm/system.h
deleted file mode 100644
index 6018c80ce37a..000000000000
--- a/arch/mips/include/asm/system.h
+++ /dev/null
@@ -1,235 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1994, 95, 96, 97, 98, 99, 2003, 06 by Ralf Baechle
- * Copyright (C) 1996 by Paul M. Antoine
- * Copyright (C) 1999 Silicon Graphics
- * Kevin D. Kissell, kevink@mips.org and Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 2000 MIPS Technologies, Inc.
- */
-#ifndef _ASM_SYSTEM_H
-#define _ASM_SYSTEM_H
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/irqflags.h>
-
-#include <asm/addrspace.h>
-#include <asm/barrier.h>
-#include <asm/cmpxchg.h>
-#include <asm/cpu-features.h>
-#include <asm/dsp.h>
-#include <asm/watch.h>
-#include <asm/war.h>
-
-
-/*
- * switch_to(n) should switch tasks to task nr n, first
- * checking that n isn't the current task, in which case it does nothing.
- */
-extern asmlinkage void *resume(void *last, void *next, void *next_ti);
-
-struct task_struct;
-
-extern unsigned int ll_bit;
-extern struct task_struct *ll_task;
-
-#ifdef CONFIG_MIPS_MT_FPAFF
-
-/*
- * Handle the scheduler resume end of FPU affinity management.  We do this
- * inline to try to keep the overhead down. If we have been forced to run on
- * a "CPU" with an FPU because of a previous high level of FP computation,
- * but did not actually use the FPU during the most recent time-slice (CU1
- * isn't set), we undo the restriction on cpus_allowed.
- *
- * We're not calling set_cpus_allowed() here, because we have no need to
- * force prompt migration - we're already switching the current CPU to a
- * different thread.
- */
-
-#define __mips_mt_fpaff_switch_to(prev)					\
-do {									\
-	struct thread_info *__prev_ti = task_thread_info(prev);		\
-									\
-	if (cpu_has_fpu &&						\
-	    test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) &&		\
-	    (!(KSTK_STATUS(prev) & ST0_CU1))) {				\
-		clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND);		\
-		prev->cpus_allowed = prev->thread.user_cpus_allowed;	\
-	}								\
-	next->thread.emulated_fp = 0;					\
-} while(0)
-
-#else
-#define __mips_mt_fpaff_switch_to(prev) do { (void) (prev); } while (0)
-#endif
-
-#define __clear_software_ll_bit()					\
-do {									\
-	if (!__builtin_constant_p(cpu_has_llsc) || !cpu_has_llsc)	\
-		ll_bit = 0;						\
-} while (0)
-
-#define switch_to(prev, next, last)					\
-do {									\
-	__mips_mt_fpaff_switch_to(prev);				\
-	if (cpu_has_dsp)						\
-		__save_dsp(prev);					\
-	__clear_software_ll_bit();					\
-	(last) = resume(prev, next, task_thread_info(next));		\
-} while (0)
-
-#define finish_arch_switch(prev)					\
-do {									\
-	if (cpu_has_dsp)						\
-		__restore_dsp(current);					\
-	if (cpu_has_userlocal)						\
-		write_c0_userlocal(current_thread_info()->tp_value);	\
-	__restore_watch();						\
-} while (0)
-
-static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
-{
-	__u32 retval;
-
-	smp_mb__before_llsc();
-
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		unsigned long dummy;
-
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	ll	%0, %3			# xchg_u32	\n"
-		"	.set	mips0					\n"
-		"	move	%2, %z4					\n"
-		"	.set	mips3					\n"
-		"	sc	%2, %1					\n"
-		"	beqzl	%2, 1b					\n"
-		"	.set	mips0					\n"
-		: "=&r" (retval), "=m" (*m), "=&r" (dummy)
-		: "R" (*m), "Jr" (val)
-		: "memory");
-	} else if (kernel_uses_llsc) {
-		unsigned long dummy;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	mips3				\n"
-			"	ll	%0, %3		# xchg_u32	\n"
-			"	.set	mips0				\n"
-			"	move	%2, %z4				\n"
-			"	.set	mips3				\n"
-			"	sc	%2, %1				\n"
-			"	.set	mips0				\n"
-			: "=&r" (retval), "=m" (*m), "=&r" (dummy)
-			: "R" (*m), "Jr" (val)
-			: "memory");
-		} while (unlikely(!dummy));
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		retval = *m;
-		*m = val;
-		raw_local_irq_restore(flags);	/* implies memory barrier  */
-	}
-
-	smp_llsc_mb();
-
-	return retval;
-}
-
-#ifdef CONFIG_64BIT
-static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
-{
-	__u64 retval;
-
-	smp_mb__before_llsc();
-
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		unsigned long dummy;
-
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	lld	%0, %3			# xchg_u64	\n"
-		"	move	%2, %z4					\n"
-		"	scd	%2, %1					\n"
-		"	beqzl	%2, 1b					\n"
-		"	.set	mips0					\n"
-		: "=&r" (retval), "=m" (*m), "=&r" (dummy)
-		: "R" (*m), "Jr" (val)
-		: "memory");
-	} else if (kernel_uses_llsc) {
-		unsigned long dummy;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	mips3				\n"
-			"	lld	%0, %3		# xchg_u64	\n"
-			"	move	%2, %z4				\n"
-			"	scd	%2, %1				\n"
-			"	.set	mips0				\n"
-			: "=&r" (retval), "=m" (*m), "=&r" (dummy)
-			: "R" (*m), "Jr" (val)
-			: "memory");
-		} while (unlikely(!dummy));
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		retval = *m;
-		*m = val;
-		raw_local_irq_restore(flags);	/* implies memory barrier  */
-	}
-
-	smp_llsc_mb();
-
-	return retval;
-}
-#else
-extern __u64 __xchg_u64_unsupported_on_32bit_kernels(volatile __u64 * m, __u64 val);
-#define __xchg_u64 __xchg_u64_unsupported_on_32bit_kernels
-#endif
-
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
-	switch (size) {
-	case 4:
-		return __xchg_u32(ptr, x);
-	case 8:
-		return __xchg_u64(ptr, x);
-	}
-
-	return x;
-}
-
-#define xchg(ptr, x)							\
-({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) & ~0xc);				\
-									\
-	((__typeof__(*(ptr)))						\
-		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))));	\
-})
-
-extern void set_handler(unsigned long offset, void *addr, unsigned long len);
-extern void set_uncached_handler(unsigned long offset, void *addr, unsigned long len);
-
-typedef void (*vi_handler_t)(void);
-extern void *set_vi_handler(int n, vi_handler_t addr);
-
-extern void *set_except_vector(int n, void *addr);
-extern unsigned long ebase;
-extern void per_cpu_trap_init(void);
-
-/*
- * See include/asm-ia64/system.h; prevents deadlock on SMP
- * systems.
- */
-#define __ARCH_WANT_UNLOCKED_CTXSW
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-#endif /* _ASM_SYSTEM_H */
diff --git a/arch/mips/include/asm/txx9/jmr3927.h b/arch/mips/include/asm/txx9/jmr3927.h
index a409c446bf18..8808d7f82da0 100644
--- a/arch/mips/include/asm/txx9/jmr3927.h
+++ b/arch/mips/include/asm/txx9/jmr3927.h
@@ -12,7 +12,6 @@
 
 #include <asm/txx9/tx3927.h>
 #include <asm/addrspace.h>
-#include <asm/system.h>
 #include <asm/txx9irq.h>
 
 /* CS */
diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c
index f305ca14351b..d6a18644365a 100644
--- a/arch/mips/kernel/cpu-bugs64.c
+++ b/arch/mips/kernel/cpu-bugs64.c
@@ -16,7 +16,7 @@
 #include <asm/cpu.h>
 #include <asm/fpu.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
+#include <asm/setup.h>
 
 static char bug64hit[] __initdata =
 	"reliable operation impossible!\n%s";
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 0bab464b8e33..5099201fb7bc 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -22,7 +22,6 @@
 #include <asm/cpu.h>
 #include <asm/fpu.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/watch.h>
 #include <asm/elf.h>
 #include <asm/spram.h>
diff --git a/arch/mips/kernel/irq-rm7000.c b/arch/mips/kernel/irq-rm7000.c
index a8a8977d5887..b0662cf97ea8 100644
--- a/arch/mips/kernel/irq-rm7000.c
+++ b/arch/mips/kernel/irq-rm7000.c
@@ -16,7 +16,6 @@
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 
 static inline void unmask_rm7k_irq(struct irq_data *d)
 {
diff --git a/arch/mips/kernel/irq-rm9000.c b/arch/mips/kernel/irq-rm9000.c
index 38874a4b9255..1282b9ae81c4 100644
--- a/arch/mips/kernel/irq-rm9000.c
+++ b/arch/mips/kernel/irq-rm9000.c
@@ -17,7 +17,6 @@
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 
 static inline void unmask_rm9k_irq(struct irq_data *d)
 {
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 7f50318061b5..a5aa43d07c8e 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -23,7 +23,6 @@
 #include <linux/ftrace.h>
 
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #ifdef CONFIG_KGDB
diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c
index 191eb52228c4..972263bcf403 100644
--- a/arch/mips/kernel/irq_cpu.c
+++ b/arch/mips/kernel/irq_cpu.c
@@ -35,7 +35,6 @@
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
 #include <asm/mipsmtregs.h>
-#include <asm/system.h>
 
 static inline void unmask_mips_irq(struct irq_data *d)
 {
diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c
index 29811f043399..84d0639e4580 100644
--- a/arch/mips/kernel/kspd.c
+++ b/arch/mips/kernel/kspd.c
@@ -326,7 +326,7 @@ static void sp_cleanup(void)
 		i = j * __NFDBITS;
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->open_fds->fds_bits[j++];
+		set = fdt->open_fds[j++];
 		while (set) {
 			if (set & 1) {
 				struct file * file = xchg(&fdt->fd[i], NULL);
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 802e6160f37e..33f63bab478a 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -173,7 +173,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 	if (retval)
 		goto out_unlock;
 
-	cpus_and(mask, p->thread.user_cpus_allowed, cpu_possible_map);
+	cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask);
 
 out_unlock:
 	read_unlock(&tasklist_lock);
diff --git a/arch/mips/kernel/mips-mt.c b/arch/mips/kernel/mips-mt.c
index c23d11f6851d..7f3376b1c219 100644
--- a/arch/mips/kernel/mips-mt.c
+++ b/arch/mips/kernel/mips-mt.c
@@ -13,7 +13,6 @@
 #include <asm/cpu.h>
 #include <asm/processor.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
 #include <asm/mipsmtregs.h>
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index e309665b6c81..f8b2c592514d 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -25,7 +25,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	int i;
 
 #ifdef CONFIG_SMP
-	if (!cpu_isset(n, cpu_online_map))
+	if (!cpu_online(n))
 		return 0;
 #endif
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 61f1cb45a1d5..e9a5fd7277f4 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -32,7 +32,6 @@
 #include <asm/dsp.h>
 #include <asm/fpu.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/mipsregs.h>
 #include <asm/processor.h>
 #include <asm/uaccess.h>
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 7786b608d932..7c24c2973c6d 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -34,7 +34,6 @@
 #include <asm/mipsmtregs.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/bootinfo.h>
 #include <asm/reg.h>
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 32644b4a0714..a3b017815eff 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -32,7 +32,6 @@
 #include <asm/mipsmtregs.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/bootinfo.h>
 
diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index a9d801dec6b0..b8c18dcdd2c4 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -38,7 +38,6 @@
 #include <linux/atomic.h>
 #include <asm/cpu.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/vpe.h>
 #include <asm/rtlx.h>
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 058e964e7303..c504b212f8f3 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -31,7 +31,6 @@
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp-ops.h>
-#include <asm/system.h>
 #include <asm/prom.h>
 
 struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly;
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index f8524003676a..185ca00c4c84 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -34,6 +34,7 @@
 #include <asm/cpu-features.h>
 #include <asm/war.h>
 #include <asm/vdso.h>
+#include <asm/dsp.h>
 
 #include "signal-common.h"
 
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index aae986613795..06b5da392e24 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -29,10 +29,10 @@
 #include <asm/cacheflush.h>
 #include <asm/sim.h>
 #include <asm/ucontext.h>
-#include <asm/system.h>
 #include <asm/fpu.h>
 #include <asm/war.h>
 #include <asm/vdso.h>
+#include <asm/dsp.h>
 
 #include "signal-common.h"
 
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index ee24d814d5b9..ae29e894ab8d 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -35,7 +35,6 @@
 #include <asm/sim.h>
 #include <asm/uaccess.h>
 #include <asm/ucontext.h>
-#include <asm/system.h>
 #include <asm/fpu.h>
 #include <asm/cpu-features.h>
 #include <asm/war.h>
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index d5e950ab8527..3046e2986006 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -28,7 +28,6 @@
 #include <asm/time.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/bootinfo.h>
 #include <asm/pmon.h>
 #include <asm/cacheflush.h>
@@ -318,7 +317,7 @@ static int bmips_cpu_disable(void)
 
 	pr_info("SMP: CPU%d is offline\n", cpu);
 
-	cpu_clear(cpu, cpu_online_map);
+	set_cpu_online(cpu, false);
 	cpu_clear(cpu, cpu_callin_map);
 
 	local_flush_tlb_all();
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index fe3095160655..e7e03ecf5495 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -29,7 +29,6 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
 #include <asm/smp.h>
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index ce9e286f0a74..ff17868734cf 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -28,7 +28,6 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
 #include <asm/time.h>
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 32c1e954cd37..ba9376bf52a1 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -38,9 +38,9 @@
 #include <asm/cpu.h>
 #include <asm/processor.h>
 #include <asm/r4k-timer.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/time.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_MIPS_MT_SMTC
 #include <asm/mipsmtregs.h>
@@ -148,7 +148,7 @@ static void stop_this_cpu(void *dummy)
 	/*
 	 * Remove this CPU:
 	 */
-	cpu_clear(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), false);
 	for (;;) {
 		if (cpu_wait)
 			(*cpu_wait)();		/* Wait if available. */
@@ -174,7 +174,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	mp_ops->prepare_cpus(max_cpus);
 	set_cpu_sibling_map(0);
 #ifndef CONFIG_HOTPLUG_CPU
-	init_cpu_present(&cpu_possible_map);
+	init_cpu_present(cpu_possible_mask);
 #endif
 }
 
@@ -248,7 +248,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	while (!cpu_isset(cpu, cpu_callin_map))
 		udelay(100);
 
-	cpu_set(cpu, cpu_online_map);
+	set_cpu_online(cpu, true);
 
 	return 0;
 }
@@ -320,13 +320,12 @@ void flush_tlb_mm(struct mm_struct *mm)
 	if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) {
 		smp_on_other_tlbs(flush_tlb_mm_ipi, mm);
 	} else {
-		cpumask_t mask = cpu_online_map;
 		unsigned int cpu;
 
-		cpu_clear(smp_processor_id(), mask);
-		for_each_cpu_mask(cpu, mask)
-			if (cpu_context(cpu, mm))
+		for_each_online_cpu(cpu) {
+			if (cpu != smp_processor_id() && cpu_context(cpu, mm))
 				cpu_context(cpu, mm) = 0;
+		}
 	}
 	local_flush_tlb_mm(mm);
 
@@ -360,13 +359,12 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned l
 
 		smp_on_other_tlbs(flush_tlb_range_ipi, &fd);
 	} else {
-		cpumask_t mask = cpu_online_map;
 		unsigned int cpu;
 
-		cpu_clear(smp_processor_id(), mask);
-		for_each_cpu_mask(cpu, mask)
-			if (cpu_context(cpu, mm))
+		for_each_online_cpu(cpu) {
+			if (cpu != smp_processor_id() && cpu_context(cpu, mm))
 				cpu_context(cpu, mm) = 0;
+		}
 	}
 	local_flush_tlb_range(vma, start, end);
 	preempt_enable();
@@ -407,13 +405,12 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 
 		smp_on_other_tlbs(flush_tlb_page_ipi, &fd);
 	} else {
-		cpumask_t mask = cpu_online_map;
 		unsigned int cpu;
 
-		cpu_clear(smp_processor_id(), mask);
-		for_each_cpu_mask(cpu, mask)
-			if (cpu_context(cpu, vma->vm_mm))
+		for_each_online_cpu(cpu) {
+			if (cpu != smp_processor_id() && cpu_context(cpu, vma->vm_mm))
 				cpu_context(cpu, vma->vm_mm) = 0;
+		}
 	}
 	local_flush_tlb_page(vma, page);
 	preempt_enable();
diff --git a/arch/mips/kernel/smtc-proc.c b/arch/mips/kernel/smtc-proc.c
index 928a5a61e1a6..145771c0ed7a 100644
--- a/arch/mips/kernel/smtc-proc.c
+++ b/arch/mips/kernel/smtc-proc.c
@@ -11,7 +11,6 @@
 #include <asm/cpu.h>
 #include <asm/processor.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
 #include <asm/mipsregs.h>
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 0a42ff3ff6a1..f5dd38f1d015 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -31,7 +31,6 @@
 #include <asm/cpu.h>
 #include <asm/processor.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/hardirq.h>
 #include <asm/hazards.h>
 #include <asm/irq.h>
@@ -292,7 +291,7 @@ static void smtc_configure_tlb(void)
  * possibly leave some TCs/VPEs as "slave" processors.
  *
  * Use c0_MVPConf0 to find out how many TCs are available, setting up
- * cpu_possible_map and the logical/physical mappings.
+ * cpu_possible_mask and the logical/physical mappings.
  */
 
 int __init smtc_build_cpu_map(int start_cpu_slot)
diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c
index 1821d12a6410..6af08d896e20 100644
--- a/arch/mips/kernel/spram.c
+++ b/arch/mips/kernel/spram.c
@@ -15,7 +15,6 @@
 
 #include <asm/fpu.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/r4kcache.h>
 #include <asm/hazards.h>
 
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index d02765708ddb..b08220c82113 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -37,6 +37,7 @@
 #include <asm/shmparam.h>
 #include <asm/sysmips.h>
 #include <asm/uaccess.h>
+#include <asm/switch_to.h>
 
 /*
  * For historic reasons the pipe(2) syscall on MIPS has an unusual calling
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index d79ae5437b58..cfdaaa4cffc0 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -45,7 +45,6 @@
 #include <asm/pgtable.h>
 #include <asm/ptrace.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/tlbdebug.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index aedb8941caa5..9c58bdf58f23 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -85,7 +85,6 @@
 #include <asm/cop2.h>
 #include <asm/inst.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #define STR(x)  __STR(x)
 #define __STR(x)  #x
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index bfa12a4f97b9..f6f91523cb1c 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -49,7 +49,6 @@
 #include <asm/cpu.h>
 #include <asm/mips_mt.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/vpe.h>
 #include <asm/kspd.h>
 
diff --git a/arch/mips/lasat/reset.c b/arch/mips/lasat/reset.c
index b1e7a89fb730..e21f0b9a586e 100644
--- a/arch/mips/lasat/reset.c
+++ b/arch/mips/lasat/reset.c
@@ -21,7 +21,6 @@
 #include <linux/pm.h>
 
 #include <asm/reboot.h>
-#include <asm/system.h>
 #include <asm/lasat/lasat.h>
 
 #include "picvue.h"
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index 3c4a8c5ba7f2..384a3b0091ea 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -12,7 +12,6 @@
 #include <asm/uaccess.h>
 #include <asm/branch.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 
 #include <asm/fpu_emulator.h>
diff --git a/arch/mips/mipssim/sim_smtc.c b/arch/mips/mipssim/sim_smtc.c
index 915063991f6e..3c104abd8aa5 100644
--- a/arch/mips/mipssim/sim_smtc.c
+++ b/arch/mips/mipssim/sim_smtc.c
@@ -28,7 +28,6 @@
 #include <asm/cpu.h>
 #include <asm/processor.h>
 #include <asm/smtc.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/smtc_ipi.h>
 
diff --git a/arch/mips/mipssim/sim_time.c b/arch/mips/mipssim/sim_time.c
index 5492c42f7650..77bad3c04280 100644
--- a/arch/mips/mipssim/sim_time.c
+++ b/arch/mips/mipssim/sim_time.c
@@ -11,6 +11,7 @@
 #include <asm/hardirq.h>
 #include <asm/div64.h>
 #include <asm/cpu.h>
+#include <asm/setup.h>
 #include <asm/time.h>
 #include <asm/irq.h>
 #include <asm/mc146818-time.h>
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index cf7895db0739..47037ec5589b 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -21,7 +21,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/r4kcache.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/war.h>
 
@@ -81,9 +80,9 @@ static void octeon_flush_icache_all_cores(struct vm_area_struct *vma)
 	if (vma)
 		mask = *mm_cpumask(vma->vm_mm);
 	else
-		mask = cpu_online_map;
-	cpu_clear(cpu, mask);
-	for_each_cpu_mask(cpu, mask)
+		mask = *cpu_online_mask;
+	cpumask_clear_cpu(cpu, &mask);
+	for_each_cpu(cpu, &mask)
 		octeon_send_ipi_single(cpu, SMP_ICACHE_FLUSH);
 
 	preempt_enable();
diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c
index 0765583d0c92..031c4c2cdf2e 100644
--- a/arch/mips/mm/c-r3k.c
+++ b/arch/mips/mm/c-r3k.c
@@ -18,7 +18,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
-#include <asm/system.h>
 #include <asm/isadep.h>
 #include <asm/io.h>
 #include <asm/bootinfo.h>
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index c97087d12d07..bda8eb26ece7 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -29,7 +29,6 @@
 #include <asm/pgtable.h>
 #include <asm/r4kcache.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/war.h>
 #include <asm/cacheflush.h> /* for run_uncached() */
diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c
index a43c197ccf8c..87d23cada6d6 100644
--- a/arch/mips/mm/c-tx39.c
+++ b/arch/mips/mm/c-tx39.c
@@ -18,7 +18,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
-#include <asm/system.h>
 #include <asm/isadep.h>
 #include <asm/io.h>
 #include <asm/bootinfo.h>
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 46084912e588..3fab2046c8a4 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -98,7 +98,7 @@ void *dma_alloc_noncoherent(struct device *dev, size_t size,
 EXPORT_SYMBOL(dma_alloc_noncoherent);
 
 static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t * dma_handle, gfp_t gfp)
+	dma_addr_t * dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	void *ret;
 
@@ -132,7 +132,7 @@ void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
 EXPORT_SYMBOL(dma_free_noncoherent);
 
 static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-	dma_addr_t dma_handle)
+	dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	unsigned long addr = (unsigned long) vaddr;
 	int order = get_order(size);
@@ -323,8 +323,8 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 EXPORT_SYMBOL(dma_cache_sync);
 
 static struct dma_map_ops mips_default_dma_map_ops = {
-	.alloc_coherent = mips_dma_alloc_coherent,
-	.free_coherent = mips_dma_free_coherent,
+	.alloc = mips_dma_alloc_coherent,
+	.free = mips_dma_free_coherent,
 	.map_page = mips_dma_map_page,
 	.unmap_page = mips_dma_unmap_page,
 	.map_sg = mips_dma_map_sg,
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 69ebd586d7ff..c14f6dfed995 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -22,7 +22,6 @@
 
 #include <asm/branch.h>
 #include <asm/mmu_context.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/highmem.h>		/* For VMALLOC_END */
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index 36272f7d3744..cc0b626858b3 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -22,7 +22,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/prefetch.h>
-#include <asm/system.h>
 #include <asm/bootinfo.h>
 #include <asm/mipsregs.h>
 #include <asm/mmu_context.h>
diff --git a/arch/mips/mm/sc-ip22.c b/arch/mips/mm/sc-ip22.c
index a6bd11fba7bf..1eb708ef75ff 100644
--- a/arch/mips/mm/sc-ip22.c
+++ b/arch/mips/mm/sc-ip22.c
@@ -12,7 +12,6 @@
 #include <asm/bcache.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/bootinfo.h>
 #include <asm/sgi/ip22.h>
 #include <asm/sgi/mc.h>
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 9cca8de00545..93d937b4b1ba 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -11,7 +11,6 @@
 #include <asm/cacheops.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/r4kcache.h>
 
diff --git a/arch/mips/mm/sc-r5k.c b/arch/mips/mm/sc-r5k.c
index ae1e533a096e..8d90ff25b123 100644
--- a/arch/mips/mm/sc-r5k.c
+++ b/arch/mips/mm/sc-r5k.c
@@ -12,7 +12,6 @@
 #include <asm/cacheops.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/r4kcache.h>
 
diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c
index ed1fa460f84e..a63d1ed0827f 100644
--- a/arch/mips/mm/tlb-r3k.c
+++ b/arch/mips/mm/tlb-r3k.c
@@ -19,7 +19,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
-#include <asm/system.h>
 #include <asm/tlbmisc.h>
 #include <asm/isadep.h>
 #include <asm/io.h>
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 2dc625346c40..d2572cb232db 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -18,7 +18,6 @@
 #include <asm/bootinfo.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/tlbmisc.h>
 
 extern void build_tlb_refill_handler(void);
diff --git a/arch/mips/mm/tlb-r8k.c b/arch/mips/mm/tlb-r8k.c
index 3d95f76c106b..91c2499f806a 100644
--- a/arch/mips/mm/tlb-r8k.c
+++ b/arch/mips/mm/tlb-r8k.c
@@ -17,7 +17,6 @@
 #include <asm/bootinfo.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 
 extern void build_tlb_refill_handler(void);
 
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index e06370f58ef3..0bc485b3cd60 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -32,6 +32,7 @@
 #include <asm/pgtable.h>
 #include <asm/war.h>
 #include <asm/uasm.h>
+#include <asm/setup.h>
 
 /*
  * TLB load/store/modify handlers.
diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c
index 4b988b9a30d5..27a6cdb36e37 100644
--- a/arch/mips/mti-malta/malta-init.c
+++ b/arch/mips/mti-malta/malta-init.c
@@ -26,7 +26,6 @@
 #include <asm/bootinfo.h>
 #include <asm/gt64120.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 #include <asm/smp-ops.h>
 #include <asm/traps.h>
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index a588b5cef8d2..7b13a4caeea4 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -44,6 +44,7 @@
 #include <asm/msc01_ic.h>
 #include <asm/gic.h>
 #include <asm/gcmpregs.h>
+#include <asm/setup.h>
 
 int gcmp_present = -1;
 int gic_present;
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index f8ee945ee411..115f5bc06003 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -35,6 +35,7 @@
 #include <asm/irq.h>
 #include <asm/div64.h>
 #include <asm/cpu.h>
+#include <asm/setup.h>
 #include <asm/time.h>
 #include <asm/mc146818-time.h>
 #include <asm/msc01_ic.h>
diff --git a/arch/mips/netlogic/common/irq.c b/arch/mips/netlogic/common/irq.c
index 49a4f6cf71e5..e52bfcbce093 100644
--- a/arch/mips/netlogic/common/irq.c
+++ b/arch/mips/netlogic/common/irq.c
@@ -43,7 +43,6 @@
 
 #include <asm/errno.h>
 #include <asm/signal.h>
-#include <asm/system.h>
 #include <asm/ptrace.h>
 #include <asm/mipsregs.h>
 #include <asm/thread_info.h>
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index db17f49886c2..fab316de57e9 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -165,7 +165,7 @@ void __init nlm_smp_setup(void)
 	cpu_set(boot_cpu, phys_cpu_present_map);
 	__cpu_number_map[boot_cpu] = 0;
 	__cpu_logical_map[0] = boot_cpu;
-	cpu_set(0, cpu_possible_map);
+	set_cpu_possible(0, true);
 
 	num_cpus = 1;
 	for (i = 0; i < NR_CPUS; i++) {
@@ -177,14 +177,14 @@ void __init nlm_smp_setup(void)
 			cpu_set(i, phys_cpu_present_map);
 			__cpu_number_map[i] = num_cpus;
 			__cpu_logical_map[num_cpus] = i;
-			cpu_set(num_cpus, cpu_possible_map);
+			set_cpu_possible(num_cpus, true);
 			++num_cpus;
 		}
 	}
 
 	pr_info("Phys CPU present map: %lx, possible map %lx\n",
 		(unsigned long)phys_cpu_present_map.bits[0],
-		(unsigned long)cpu_possible_map.bits[0]);
+		(unsigned long)cpumask_bits(cpu_possible_mask)[0]);
 
 	pr_info("Detected %i Slave CPU(s)\n", num_cpus);
 	nlm_set_nmi_handler(nlm_boot_secondary_cpus);
diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c b/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c
index c4fa2d775d8b..2e6f7cab24c1 100644
--- a/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c
+++ b/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c
@@ -16,7 +16,6 @@
 #include <linux/irq.h>
 
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 
 #include <msp_cic_int.h>
 #include <msp_regs.h>
diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq_per.c b/arch/mips/pmc-sierra/msp71xx/msp_irq_per.c
index 98fd0099d964..598b6a66b970 100644
--- a/arch/mips/pmc-sierra/msp71xx/msp_irq_per.c
+++ b/arch/mips/pmc-sierra/msp71xx/msp_irq_per.c
@@ -16,7 +16,6 @@
 #include <linux/bitops.h>
 
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 
 #include <msp_cic_int.h>
 #include <msp_regs.h>
diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c b/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c
index 5bbcc47da6b9..83a1c5eae3f8 100644
--- a/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c
+++ b/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c
@@ -16,7 +16,6 @@
 #include <linux/bitops.h>
 
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 
 #include <msp_slp_int.h>
 #include <msp_regs.h>
diff --git a/arch/mips/pmc-sierra/yosemite/irq.c b/arch/mips/pmc-sierra/yosemite/irq.c
index 25bbbf428be9..6590812daa56 100644
--- a/arch/mips/pmc-sierra/yosemite/irq.c
+++ b/arch/mips/pmc-sierra/yosemite/irq.c
@@ -44,7 +44,6 @@
 #include <asm/irq.h>
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/titan_dep.h>
 
 /* Hypertransport specific */
diff --git a/arch/mips/pmc-sierra/yosemite/prom.c b/arch/mips/pmc-sierra/yosemite/prom.c
index dcc926e06fce..6a2754c4f106 100644
--- a/arch/mips/pmc-sierra/yosemite/prom.c
+++ b/arch/mips/pmc-sierra/yosemite/prom.c
@@ -20,7 +20,6 @@
 #include <asm/processor.h>
 #include <asm/reboot.h>
 #include <asm/smp-ops.h>
-#include <asm/system.h>
 #include <asm/bootinfo.h>
 #include <asm/pmon.h>
 
diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c
index 2608752898c0..b71fae231049 100644
--- a/arch/mips/pmc-sierra/yosemite/smp.c
+++ b/arch/mips/pmc-sierra/yosemite/smp.c
@@ -146,7 +146,7 @@ static void __cpuinit yos_boot_secondary(int cpu, struct task_struct *idle)
 }
 
 /*
- * Detect available CPUs, populate cpu_possible_map before smp_init
+ * Detect available CPUs, populate cpu_possible_mask before smp_init
  *
  * We don't want to start the secondary CPU yet nor do we have a nice probing
  * feature in PMON so we just assume presence of the secondary core.
@@ -155,10 +155,10 @@ static void __init yos_smp_setup(void)
 {
 	int i;
 
-	cpus_clear(cpu_possible_map);
+	init_cpu_possible(cpu_none_mask);
 
 	for (i = 0; i < 2; i++) {
-		cpu_set(i, cpu_possible_map);
+		set_cpu_possible(i, true);
 		__cpu_number_map[i]	= i;
 		__cpu_logical_map[i]	= i;
 	}
@@ -169,7 +169,7 @@ static void __init yos_prepare_cpus(unsigned int max_cpus)
 	/*
 	 * Be paranoid.  Enable the IPI only if we're really about to go SMP.
 	 */
-	if (cpus_weight(cpu_possible_map))
+	if (num_possible_cpus())
 		set_c0_status(STATUSF_IP5);
 }
 
diff --git a/arch/mips/pnx833x/common/interrupts.c b/arch/mips/pnx833x/common/interrupts.c
index adc171c8846f..a86d5d5fceb0 100644
--- a/arch/mips/pnx833x/common/interrupts.c
+++ b/arch/mips/pnx833x/common/interrupts.c
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <asm/mipsregs.h>
 #include <asm/irq_cpu.h>
+#include <asm/setup.h>
 #include <irq.h>
 #include <irq-mapping.h>
 #include <gpio.h>
diff --git a/arch/mips/powertv/asic/asic_int.c b/arch/mips/powertv/asic/asic_int.c
index 529c44a52d64..99d82e10000b 100644
--- a/arch/mips/powertv/asic/asic_int.c
+++ b/arch/mips/powertv/asic/asic_int.c
@@ -34,6 +34,7 @@
 #include <asm/irq_cpu.h>
 #include <linux/io.h>
 #include <asm/irq_regs.h>
+#include <asm/setup.h>
 #include <asm/mips-boards/generic.h>
 
 #include <asm/mach-powertv/asic_regs.h>
diff --git a/arch/mips/powertv/asic/irq_asic.c b/arch/mips/powertv/asic/irq_asic.c
index 7fb97fb0931e..fa9ae9584710 100644
--- a/arch/mips/powertv/asic/irq_asic.c
+++ b/arch/mips/powertv/asic/irq_asic.c
@@ -17,7 +17,6 @@
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 
 #include <asm/mach-powertv/asic_regs.h>
 
diff --git a/arch/mips/powertv/init.c b/arch/mips/powertv/init.c
index 83552288e802..1cf5abbef715 100644
--- a/arch/mips/powertv/init.c
+++ b/arch/mips/powertv/init.c
@@ -26,7 +26,6 @@
 
 #include <asm/bootinfo.h>
 #include <linux/io.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 
diff --git a/arch/mips/rb532/irq.c b/arch/mips/rb532/irq.c
index 7c6db74e3fad..f298430cff07 100644
--- a/arch/mips/rb532/irq.c
+++ b/arch/mips/rb532/irq.c
@@ -42,7 +42,6 @@
 #include <asm/bootinfo.h>
 #include <asm/time.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 
 #include <asm/mach-rc32434/irq.h>
 #include <asm/mach-rc32434/gpio.h>
diff --git a/arch/mips/sgi-ip22/ip22-berr.c b/arch/mips/sgi-ip22/ip22-berr.c
index 911d3999c0c7..3f6ccd53c15d 100644
--- a/arch/mips/sgi-ip22/ip22-berr.c
+++ b/arch/mips/sgi-ip22/ip22-berr.c
@@ -9,7 +9,6 @@
 #include <linux/sched.h>
 
 #include <asm/addrspace.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/branch.h>
 #include <asm/irq_regs.h>
diff --git a/arch/mips/sgi-ip22/ip22-reset.c b/arch/mips/sgi-ip22/ip22-reset.c
index 45b6694c2079..20363d29cb58 100644
--- a/arch/mips/sgi-ip22/ip22-reset.c
+++ b/arch/mips/sgi-ip22/ip22-reset.c
@@ -18,7 +18,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/reboot.h>
 #include <asm/sgialib.h>
 #include <asm/sgi/ioc.h>
diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index 88c684e05a3d..0626555fd1a3 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -11,7 +11,6 @@
 #include <linux/seq_file.h>
 
 #include <asm/addrspace.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/branch.h>
 #include <asm/irq_regs.h>
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 23642238c689..69a939ae65e4 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -27,7 +27,6 @@
 #include <asm/bootinfo.h>
 #include <asm/io.h>
 #include <asm/mipsregs.h>
-#include <asm/system.h>
 
 #include <asm/processor.h>
 #include <asm/pci/bridge.h>
diff --git a/arch/mips/sgi-ip27/ip27-reset.c b/arch/mips/sgi-ip27/ip27-reset.c
index c17076108d47..f347bc6b7954 100644
--- a/arch/mips/sgi-ip27/ip27-reset.c
+++ b/arch/mips/sgi-ip27/ip27-reset.c
@@ -19,7 +19,6 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/reboot.h>
-#include <asm/system.h>
 #include <asm/sgialib.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index c6851df9ab74..735b43bf8f82 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -76,7 +76,7 @@ static int do_cpumask(cnodeid_t cnode, nasid_t nasid, int highest)
 			/* Only let it join in if it's marked enabled */
 			if ((acpu->cpu_info.flags & KLINFO_ENABLE) &&
 			    (tot_cpus_found != NR_CPUS)) {
-				cpu_set(cpuid, cpu_possible_map);
+				set_cpu_possible(cpuid, true);
 				alloc_cpupda(cpuid, tot_cpus_found);
 				cpus_found++;
 				tot_cpus_found++;
diff --git a/arch/mips/sgi-ip32/ip32-irq.c b/arch/mips/sgi-ip32/ip32-irq.c
index a092860d5196..e7d5054de8c8 100644
--- a/arch/mips/sgi-ip32/ip32-irq.c
+++ b/arch/mips/sgi-ip32/ip32-irq.c
@@ -22,7 +22,6 @@
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
 #include <asm/signal.h>
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/ip32/crime.h>
 #include <asm/ip32/mace.h>
diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c
index 9b95d80ebc6e..1f823da4c77b 100644
--- a/arch/mips/sgi-ip32/ip32-reset.c
+++ b/arch/mips/sgi-ip32/ip32-reset.c
@@ -20,7 +20,6 @@
 #include <asm/addrspace.h>
 #include <asm/irq.h>
 #include <asm/reboot.h>
-#include <asm/system.h>
 #include <asm/wbflush.h>
 #include <asm/ip32/mace.h>
 #include <asm/ip32/crime.h>
diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c
index 09740d60e187..215713e1f3c4 100644
--- a/arch/mips/sibyte/bcm1480/irq.c
+++ b/arch/mips/sibyte/bcm1480/irq.c
@@ -27,7 +27,6 @@
 #include <asm/errno.h>
 #include <asm/irq_regs.h>
 #include <asm/signal.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <asm/sibyte/bcm1480_regs.h>
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index d667875be564..de88e22694a0 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -138,7 +138,7 @@ static void __cpuinit bcm1480_boot_secondary(int cpu, struct task_struct *idle)
 
 /*
  * Use CFE to find out how many CPUs are available, setting up
- * cpu_possible_map and the logical/physical mappings.
+ * cpu_possible_mask and the logical/physical mappings.
  * XXXKW will the boot CPU ever not be physical 0?
  *
  * Common setup before any secondaries are started
@@ -147,14 +147,13 @@ static void __init bcm1480_smp_setup(void)
 {
 	int i, num;
 
-	cpus_clear(cpu_possible_map);
-	cpu_set(0, cpu_possible_map);
+	init_cpu_possible(cpumask_of(0));
 	__cpu_number_map[0] = 0;
 	__cpu_logical_map[0] = 0;
 
 	for (i = 1, num = 0; i < NR_CPUS; i++) {
 		if (cfe_cpu_stop(i) == 0) {
-			cpu_set(i, cpu_possible_map);
+			set_cpu_possible(i, true);
 			__cpu_number_map[i] = ++num;
 			__cpu_logical_map[num] = i;
 		}
diff --git a/arch/mips/sibyte/common/sb_tbprof.c b/arch/mips/sibyte/common/sb_tbprof.c
index 48853ab5bcf0..e8c4538c5f61 100644
--- a/arch/mips/sibyte/common/sb_tbprof.c
+++ b/arch/mips/sibyte/common/sb_tbprof.c
@@ -53,7 +53,6 @@
 #define K_INT_PERF_CNT K_BCM1480_INT_PERF_CNT
 #endif
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #define SBPROF_TB_MAJOR 240
diff --git a/arch/mips/sibyte/sb1250/bus_watcher.c b/arch/mips/sibyte/sb1250/bus_watcher.c
index 45274bd3cd8b..86e6e54dd15d 100644
--- a/arch/mips/sibyte/sb1250/bus_watcher.c
+++ b/arch/mips/sibyte/sb1250/bus_watcher.c
@@ -30,7 +30,6 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/proc_fs.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <asm/sibyte/sb1250.h>
diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c
index 76ee045e2ce4..340aaf626659 100644
--- a/arch/mips/sibyte/sb1250/irq.c
+++ b/arch/mips/sibyte/sb1250/irq.c
@@ -26,7 +26,6 @@
 
 #include <asm/errno.h>
 #include <asm/signal.h>
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/io.h>
 
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index 38e7f6bd7922..285cfef4ebc0 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -126,7 +126,7 @@ static void __cpuinit sb1250_boot_secondary(int cpu, struct task_struct *idle)
 
 /*
  * Use CFE to find out how many CPUs are available, setting up
- * cpu_possible_map and the logical/physical mappings.
+ * cpu_possible_mask and the logical/physical mappings.
  * XXXKW will the boot CPU ever not be physical 0?
  *
  * Common setup before any secondaries are started
@@ -135,14 +135,13 @@ static void __init sb1250_smp_setup(void)
 {
 	int i, num;
 
-	cpus_clear(cpu_possible_map);
-	cpu_set(0, cpu_possible_map);
+	init_cpu_possible(cpumask_of(0));
 	__cpu_number_map[0] = 0;
 	__cpu_logical_map[0] = 0;
 
 	for (i = 1, num = 0; i < NR_CPUS; i++) {
 		if (cfe_cpu_stop(i) == 0) {
-			cpu_set(i, cpu_possible_map);
+			set_cpu_possible(i, true);
 			__cpu_number_map[i] = ++num;
 			__cpu_logical_map[num] = i;
 		}
diff --git a/arch/mips/sni/reset.c b/arch/mips/sni/reset.c
index 79f8d70f48c9..244f9427625b 100644
--- a/arch/mips/sni/reset.c
+++ b/arch/mips/sni/reset.c
@@ -5,7 +5,6 @@
  */
 #include <asm/io.h>
 #include <asm/reboot.h>
-#include <asm/system.h>
 #include <asm/sni.h>
 
 /*
diff --git a/arch/mips/vr41xx/common/irq.c b/arch/mips/vr41xx/common/irq.c
index fad2bef432cd..ae0e4ee6c617 100644
--- a/arch/mips/vr41xx/common/irq.c
+++ b/arch/mips/vr41xx/common/irq.c
@@ -22,7 +22,6 @@
 #include <linux/irq.h>
 
 #include <asm/irq_cpu.h>
-#include <asm/system.h>
 #include <asm/vr41xx/irq.h>
 
 typedef struct irq_cascade {
diff --git a/arch/mips/vr41xx/common/pmu.c b/arch/mips/vr41xx/common/pmu.c
index 692b4e85b7fc..9fbf5f0d1faf 100644
--- a/arch/mips/vr41xx/common/pmu.c
+++ b/arch/mips/vr41xx/common/pmu.c
@@ -30,7 +30,6 @@
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/reboot.h>
-#include <asm/system.h>
 
 #define PMU_TYPE1_BASE	0x0b0000a0UL
 #define PMU_TYPE1_SIZE	0x0eUL
diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h
index b9a8f8461262..975e1841ca64 100644
--- a/arch/mn10300/include/asm/atomic.h
+++ b/arch/mn10300/include/asm/atomic.h
@@ -12,112 +12,7 @@
 #define _ASM_ATOMIC_H
 
 #include <asm/irqflags.h>
-
-#ifndef __ASSEMBLY__
-
-#ifdef CONFIG_SMP
-#ifdef CONFIG_MN10300_HAS_ATOMIC_OPS_UNIT
-static inline
-unsigned long __xchg(volatile unsigned long *m, unsigned long val)
-{
-	unsigned long status;
-	unsigned long oldval;
-
-	asm volatile(
-		"1:	mov	%4,(_AAR,%3)	\n"
-		"	mov	(_ADR,%3),%1	\n"
-		"	mov	%5,(_ADR,%3)	\n"
-		"	mov	(_ADR,%3),%0	\n"	/* flush */
-		"	mov	(_ASR,%3),%0	\n"
-		"	or	%0,%0		\n"
-		"	bne	1b		\n"
-		: "=&r"(status), "=&r"(oldval), "=m"(*m)
-		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(m), "r"(val)
-		: "memory", "cc");
-
-	return oldval;
-}
-
-static inline unsigned long __cmpxchg(volatile unsigned long *m,
-				      unsigned long old, unsigned long new)
-{
-	unsigned long status;
-	unsigned long oldval;
-
-	asm volatile(
-		"1:	mov	%4,(_AAR,%3)	\n"
-		"	mov	(_ADR,%3),%1	\n"
-		"	cmp	%5,%1		\n"
-		"	bne	2f		\n"
-		"	mov	%6,(_ADR,%3)	\n"
-		"2:	mov	(_ADR,%3),%0	\n"	/* flush */
-		"	mov	(_ASR,%3),%0	\n"
-		"	or	%0,%0		\n"
-		"	bne	1b		\n"
-		: "=&r"(status), "=&r"(oldval), "=m"(*m)
-		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(m),
-		  "r"(old), "r"(new)
-		: "memory", "cc");
-
-	return oldval;
-}
-#else  /* CONFIG_MN10300_HAS_ATOMIC_OPS_UNIT */
-#error "No SMP atomic operation support!"
-#endif /* CONFIG_MN10300_HAS_ATOMIC_OPS_UNIT */
-
-#else  /* CONFIG_SMP */
-
-/*
- * Emulate xchg for non-SMP MN10300
- */
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((struct __xchg_dummy *)(x))
-
-static inline
-unsigned long __xchg(volatile unsigned long *m, unsigned long val)
-{
-	unsigned long oldval;
-	unsigned long flags;
-
-	flags = arch_local_cli_save();
-	oldval = *m;
-	*m = val;
-	arch_local_irq_restore(flags);
-	return oldval;
-}
-
-/*
- * Emulate cmpxchg for non-SMP MN10300
- */
-static inline unsigned long __cmpxchg(volatile unsigned long *m,
-				      unsigned long old, unsigned long new)
-{
-	unsigned long oldval;
-	unsigned long flags;
-
-	flags = arch_local_cli_save();
-	oldval = *m;
-	if (oldval == old)
-		*m = new;
-	arch_local_irq_restore(flags);
-	return oldval;
-}
-
-#endif /* CONFIG_SMP */
-
-#define xchg(ptr, v)						\
-	((__typeof__(*(ptr))) __xchg((unsigned long *)(ptr),	\
-				     (unsigned long)(v)))
-
-#define cmpxchg(ptr, o, n)					\
-	((__typeof__(*(ptr))) __cmpxchg((unsigned long *)(ptr), \
-					(unsigned long)(o),	\
-					(unsigned long)(n)))
-
-#define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
-#define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
-
-#endif /* !__ASSEMBLY__ */
+#include <asm/cmpxchg.h>
 
 #ifndef CONFIG_SMP
 #include <asm-generic/atomic.h>
@@ -269,6 +164,8 @@ static inline void atomic_dec(atomic_t *v)
 	c;							\
 })
 
+#define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
+#define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
 /**
  * atomic_clear_mask - Atomically clear bits in memory
diff --git a/arch/mn10300/include/asm/barrier.h b/arch/mn10300/include/asm/barrier.h
new file mode 100644
index 000000000000..2bd97a5c8af7
--- /dev/null
+++ b/arch/mn10300/include/asm/barrier.h
@@ -0,0 +1,37 @@
+/* MN10300 memory barrier definitions
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef _ASM_BARRIER_H
+#define _ASM_BARRIER_H
+
+#define nop()	asm volatile ("nop")
+
+#define mb()	asm volatile ("": : :"memory")
+#define rmb()	mb()
+#define wmb()	asm volatile ("": : :"memory")
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
+#define set_mb(var, value)  do { xchg(&var, value); } while (0)
+#else  /* CONFIG_SMP */
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define set_mb(var, value)  do { var = value;  mb(); } while (0)
+#endif /* CONFIG_SMP */
+
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+
+#define read_barrier_depends()		do {} while (0)
+#define smp_read_barrier_depends()	do {} while (0)
+
+#endif /* _ASM_BARRIER_H */
diff --git a/arch/mn10300/include/asm/cmpxchg.h b/arch/mn10300/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..97a4aaf387a6
--- /dev/null
+++ b/arch/mn10300/include/asm/cmpxchg.h
@@ -0,0 +1,115 @@
+/* MN10300 Atomic xchg/cmpxchg operations
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef _ASM_CMPXCHG_H
+#define _ASM_CMPXCHG_H
+
+#include <asm/irqflags.h>
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_MN10300_HAS_ATOMIC_OPS_UNIT
+static inline
+unsigned long __xchg(volatile unsigned long *m, unsigned long val)
+{
+	unsigned long status;
+	unsigned long oldval;
+
+	asm volatile(
+		"1:	mov	%4,(_AAR,%3)	\n"
+		"	mov	(_ADR,%3),%1	\n"
+		"	mov	%5,(_ADR,%3)	\n"
+		"	mov	(_ADR,%3),%0	\n"	/* flush */
+		"	mov	(_ASR,%3),%0	\n"
+		"	or	%0,%0		\n"
+		"	bne	1b		\n"
+		: "=&r"(status), "=&r"(oldval), "=m"(*m)
+		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(m), "r"(val)
+		: "memory", "cc");
+
+	return oldval;
+}
+
+static inline unsigned long __cmpxchg(volatile unsigned long *m,
+				      unsigned long old, unsigned long new)
+{
+	unsigned long status;
+	unsigned long oldval;
+
+	asm volatile(
+		"1:	mov	%4,(_AAR,%3)	\n"
+		"	mov	(_ADR,%3),%1	\n"
+		"	cmp	%5,%1		\n"
+		"	bne	2f		\n"
+		"	mov	%6,(_ADR,%3)	\n"
+		"2:	mov	(_ADR,%3),%0	\n"	/* flush */
+		"	mov	(_ASR,%3),%0	\n"
+		"	or	%0,%0		\n"
+		"	bne	1b		\n"
+		: "=&r"(status), "=&r"(oldval), "=m"(*m)
+		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(m),
+		  "r"(old), "r"(new)
+		: "memory", "cc");
+
+	return oldval;
+}
+#else  /* CONFIG_MN10300_HAS_ATOMIC_OPS_UNIT */
+#error "No SMP atomic operation support!"
+#endif /* CONFIG_MN10300_HAS_ATOMIC_OPS_UNIT */
+
+#else  /* CONFIG_SMP */
+
+/*
+ * Emulate xchg for non-SMP MN10300
+ */
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((struct __xchg_dummy *)(x))
+
+static inline
+unsigned long __xchg(volatile unsigned long *m, unsigned long val)
+{
+	unsigned long oldval;
+	unsigned long flags;
+
+	flags = arch_local_cli_save();
+	oldval = *m;
+	*m = val;
+	arch_local_irq_restore(flags);
+	return oldval;
+}
+
+/*
+ * Emulate cmpxchg for non-SMP MN10300
+ */
+static inline unsigned long __cmpxchg(volatile unsigned long *m,
+				      unsigned long old, unsigned long new)
+{
+	unsigned long oldval;
+	unsigned long flags;
+
+	flags = arch_local_cli_save();
+	oldval = *m;
+	if (oldval == old)
+		*m = new;
+	arch_local_irq_restore(flags);
+	return oldval;
+}
+
+#endif /* CONFIG_SMP */
+
+#define xchg(ptr, v)						\
+	((__typeof__(*(ptr))) __xchg((unsigned long *)(ptr),	\
+				     (unsigned long)(v)))
+
+#define cmpxchg(ptr, o, n)					\
+	((__typeof__(*(ptr))) __cmpxchg((unsigned long *)(ptr), \
+					(unsigned long)(o),	\
+					(unsigned long)(n)))
+
+#endif /* _ASM_CMPXCHG_H */
diff --git a/arch/mn10300/include/asm/dma.h b/arch/mn10300/include/asm/dma.h
index 098df2e617ab..10b77d4628c2 100644
--- a/arch/mn10300/include/asm/dma.h
+++ b/arch/mn10300/include/asm/dma.h
@@ -11,7 +11,6 @@
 #ifndef _ASM_DMA_H
 #define _ASM_DMA_H
 
-#include <asm/system.h>
 #include <linux/spinlock.h>
 #include <asm/io.h>
 #include <linux/delay.h>
diff --git a/arch/mn10300/include/asm/exec.h b/arch/mn10300/include/asm/exec.h
new file mode 100644
index 000000000000..c74e367f4b9d
--- /dev/null
+++ b/arch/mn10300/include/asm/exec.h
@@ -0,0 +1,16 @@
+/* MN10300 process execution definitions
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef _ASM_EXEC_H
+#define _ASM_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _ASM_EXEC_H */
diff --git a/arch/mn10300/include/asm/posix_types.h b/arch/mn10300/include/asm/posix_types.h
index 56ffbc158798..ab506181ec31 100644
--- a/arch/mn10300/include/asm/posix_types.h
+++ b/arch/mn10300/include/asm/posix_types.h
@@ -17,14 +17,19 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
+#define __kernel_uid_t __kernel_uid_t
+
 #if __GNUC__ == 4
 typedef unsigned int	__kernel_size_t;
 typedef signed int	__kernel_ssize_t;
@@ -33,105 +38,11 @@ typedef unsigned long	__kernel_size_t;
 typedef signed long	__kernel_ssize_t;
 #endif
 typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_size_t __kernel_size_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-#if defined(__KERNEL__) || defined(__USE_ALL)
-	int	val[2];
-#else /* !defined(__KERNEL__) && !defined(__USE_ALL) */
-	int	__val[2];
-#endif /* !defined(__KERNEL__) && !defined(__USE_ALL) */
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
-
-#undef	__FD_SET
-static inline void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef	__FD_CLR
-static inline void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-
-#undef	__FD_ISSET
-static inline int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef	__FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_POSIX_TYPES_H */
diff --git a/arch/mn10300/include/asm/switch_to.h b/arch/mn10300/include/asm/switch_to.h
new file mode 100644
index 000000000000..393d311735c8
--- /dev/null
+++ b/arch/mn10300/include/asm/switch_to.h
@@ -0,0 +1,49 @@
+/* MN10300 task switching definitions
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef _ASM_SWITCH_TO_H
+#define _ASM_SWITCH_TO_H
+
+#include <asm/barrier.h>
+
+struct task_struct;
+struct thread_struct;
+
+#if !defined(CONFIG_LAZY_SAVE_FPU)
+struct fpu_state_struct;
+extern asmlinkage void fpu_save(struct fpu_state_struct *);
+#define switch_fpu(prev, next)						\
+	do {								\
+		if ((prev)->thread.fpu_flags & THREAD_HAS_FPU) {	\
+			(prev)->thread.fpu_flags &= ~THREAD_HAS_FPU;	\
+			(prev)->thread.uregs->epsw &= ~EPSW_FE;		\
+			fpu_save(&(prev)->thread.fpu_state);		\
+		}							\
+	} while (0)
+#else
+#define switch_fpu(prev, next) do {} while (0)
+#endif
+
+/* context switching is now performed out-of-line in switch_to.S */
+extern asmlinkage
+struct task_struct *__switch_to(struct thread_struct *prev,
+				struct thread_struct *next,
+				struct task_struct *prev_task);
+
+#define switch_to(prev, next, last)					\
+do {									\
+	switch_fpu(prev, next);						\
+	current->thread.wchan = (u_long) __builtin_return_address(0);	\
+	(last) = __switch_to(&(prev)->thread, &(next)->thread, (prev));	\
+	mb();								\
+	current->thread.wchan = 0;					\
+} while (0)
+
+#endif /* _ASM_SWITCH_TO_H */
diff --git a/arch/mn10300/include/asm/system.h b/arch/mn10300/include/asm/system.h
deleted file mode 100644
index 94b4c5e1491b..000000000000
--- a/arch/mn10300/include/asm/system.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/* MN10300 System definitions
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-#ifndef _ASM_SYSTEM_H
-#define _ASM_SYSTEM_H
-
-#include <asm/cpu-regs.h>
-#include <asm/intctl-regs.h>
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-#include <linux/atomic.h>
-
-#if !defined(CONFIG_LAZY_SAVE_FPU)
-struct fpu_state_struct;
-extern asmlinkage void fpu_save(struct fpu_state_struct *);
-#define switch_fpu(prev, next)						\
-	do {								\
-		if ((prev)->thread.fpu_flags & THREAD_HAS_FPU) {	\
-			(prev)->thread.fpu_flags &= ~THREAD_HAS_FPU;	\
-			(prev)->thread.uregs->epsw &= ~EPSW_FE;		\
-			fpu_save(&(prev)->thread.fpu_state);		\
-		}							\
-	} while (0)
-#else
-#define switch_fpu(prev, next) do {} while (0)
-#endif
-
-struct task_struct;
-struct thread_struct;
-
-extern asmlinkage
-struct task_struct *__switch_to(struct thread_struct *prev,
-				struct thread_struct *next,
-				struct task_struct *prev_task);
-
-/* context switching is now performed out-of-line in switch_to.S */
-#define switch_to(prev, next, last)					\
-do {									\
-	switch_fpu(prev, next);						\
-	current->thread.wchan = (u_long) __builtin_return_address(0);	\
-	(last) = __switch_to(&(prev)->thread, &(next)->thread, (prev));	\
-	mb();								\
-	current->thread.wchan = 0;					\
-} while (0)
-
-#define arch_align_stack(x) (x)
-
-#define nop() asm volatile ("nop")
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- *
- * For now, "wmb()" doesn't actually do anything, as all
- * Intel CPU's follow what Intel calls a *Processor Order*,
- * in which all writes are seen in the program order even
- * outside the CPU.
- *
- * I expect future Intel CPU's to have a weaker ordering,
- * but I'd also expect them to finally get their act together
- * and add some real memory barriers if so.
- *
- * Some non intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-
-#define mb()	asm volatile ("": : :"memory")
-#define rmb()	mb()
-#define wmb()	asm volatile ("": : :"memory")
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define set_mb(var, value)  do { xchg(&var, value); } while (0)
-#else  /* CONFIG_SMP */
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define set_mb(var, value)  do { var = value;  mb(); } while (0)
-#endif /* CONFIG_SMP */
-
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-#endif /* !__ASSEMBLY__ */
-#endif /* __KERNEL__ */
-#endif /* _ASM_SYSTEM_H */
diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S
index 3e3620d9fc45..8e11f9f48999 100644
--- a/arch/mn10300/kernel/entry.S
+++ b/arch/mn10300/kernel/entry.S
@@ -15,7 +15,6 @@
 #include <linux/sys.h>
 #include <linux/linkage.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/irqflags.h>
 #include <asm/thread_info.h>
 #include <asm/intctl-regs.h>
diff --git a/arch/mn10300/kernel/fpu.c b/arch/mn10300/kernel/fpu.c
index bb5fa7df6c44..064fa194de2b 100644
--- a/arch/mn10300/kernel/fpu.c
+++ b/arch/mn10300/kernel/fpu.c
@@ -12,7 +12,6 @@
 #include <asm/fpu.h>
 #include <asm/elf.h>
 #include <asm/exceptions.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_LAZY_SAVE_FPU
 struct task_struct *fpu_state_owner;
diff --git a/arch/mn10300/kernel/gdb-io-serial.c b/arch/mn10300/kernel/gdb-io-serial.c
index f28dc99c6f72..df51242744cc 100644
--- a/arch/mn10300/kernel/gdb-io-serial.c
+++ b/arch/mn10300/kernel/gdb-io-serial.c
@@ -18,7 +18,6 @@
 #include <linux/nmi.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/gdb-stub.h>
 #include <asm/exceptions.h>
 #include <asm/serial-regs.h>
diff --git a/arch/mn10300/kernel/gdb-io-ttysm.c b/arch/mn10300/kernel/gdb-io-ttysm.c
index c859cacbb9c3..caae8cac9db1 100644
--- a/arch/mn10300/kernel/gdb-io-ttysm.c
+++ b/arch/mn10300/kernel/gdb-io-ttysm.c
@@ -17,7 +17,6 @@
 #include <linux/init.h>
 #include <linux/tty.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/gdb-stub.h>
 #include <asm/exceptions.h>
 #include <unit/clock.h>
diff --git a/arch/mn10300/kernel/gdb-stub.c b/arch/mn10300/kernel/gdb-stub.c
index 522eb8a9b60d..a128c57b586b 100644
--- a/arch/mn10300/kernel/gdb-stub.c
+++ b/arch/mn10300/kernel/gdb-stub.c
@@ -130,7 +130,6 @@
 #include <linux/bug.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/gdb-stub.h>
 #include <asm/exceptions.h>
 #include <asm/debugger.h>
diff --git a/arch/mn10300/kernel/mn10300-serial.c b/arch/mn10300/kernel/mn10300-serial.c
index 94901c56baf1..339cef4c8256 100644
--- a/arch/mn10300/kernel/mn10300-serial.c
+++ b/arch/mn10300/kernel/mn10300-serial.c
@@ -36,7 +36,6 @@ static const char serial_revdate[] = "2007-11-06";
 #include <linux/console.h>
 #include <linux/sysrq.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/bitops.h>
diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c
index a45f0c7549a6..db64a7166c09 100644
--- a/arch/mn10300/kernel/mn10300-watchdog.c
+++ b/arch/mn10300/kernel/mn10300-watchdog.c
@@ -18,7 +18,6 @@
 #include <linux/kernel_stat.h>
 #include <linux/nmi.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/intctl-regs.h>
 #include <asm/rtc-regs.h>
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index cac401d37f75..14707f25153b 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -27,7 +27,6 @@
 #include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
diff --git a/arch/mn10300/kernel/ptrace.c b/arch/mn10300/kernel/ptrace.c
index 5c0b07e61006..5bd58514e739 100644
--- a/arch/mn10300/kernel/ptrace.c
+++ b/arch/mn10300/kernel/ptrace.c
@@ -21,7 +21,6 @@
 #include <linux/tracehook.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/cacheflush.h>
 #include <asm/fpu.h>
diff --git a/arch/mn10300/kernel/setup.c b/arch/mn10300/kernel/setup.c
index 9e7a3209a3e1..33c3bd1e5c6d 100644
--- a/arch/mn10300/kernel/setup.c
+++ b/arch/mn10300/kernel/setup.c
@@ -26,7 +26,6 @@
 #include <asm/processor.h>
 #include <linux/console.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/setup.h>
 #include <asm/io.h>
 #include <asm/smp.h>
diff --git a/arch/mn10300/kernel/smp-low.S b/arch/mn10300/kernel/smp-low.S
index 72938cefc05e..71f1b2faaa0b 100644
--- a/arch/mn10300/kernel/smp-low.S
+++ b/arch/mn10300/kernel/smp-low.S
@@ -13,9 +13,9 @@
 #include <linux/sys.h>
 #include <linux/linkage.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/thread_info.h>
 #include <asm/cpu-regs.h>
+#include <asm/intctl-regs.h>
 #include <proc/smp-regs.h>
 #include <asm/asm-offsets.h>
 #include <asm/frame.inc>
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index 9242e9fcc564..910dddf65e44 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -25,7 +25,6 @@
 #include <linux/profile.h>
 #include <linux/smp.h>
 #include <asm/tlbflush.h>
-#include <asm/system.h>
 #include <asm/bitops.h>
 #include <asm/processor.h>
 #include <asm/bug.h>
diff --git a/arch/mn10300/kernel/traps.c b/arch/mn10300/kernel/traps.c
index 9220a75a7b43..94a9c6d53e1b 100644
--- a/arch/mn10300/kernel/traps.c
+++ b/arch/mn10300/kernel/traps.c
@@ -27,7 +27,6 @@
 #include <linux/bug.h>
 #include <linux/irq.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/mn10300/lib/bitops.c b/arch/mn10300/lib/bitops.c
index a66c6cdaf442..37309cdb7584 100644
--- a/arch/mn10300/lib/bitops.c
+++ b/arch/mn10300/lib/bitops.c
@@ -10,7 +10,6 @@
  */
 #include <linux/module.h>
 #include <asm/bitops.h>
-#include <asm/system.h>
 
 /*
  * try flipping a bit using BSET and BCLR
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 0945409a8022..90f346f7392d 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -24,7 +24,6 @@
 #include <linux/init.h>
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/hardirq.h>
diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c
index 13801824e3ee..e57e5bc23562 100644
--- a/arch/mn10300/mm/init.c
+++ b/arch/mn10300/mm/init.c
@@ -29,7 +29,6 @@
 #include <linux/gfp.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
diff --git a/arch/mn10300/mm/misalignment.c b/arch/mn10300/mm/misalignment.c
index f9bb8cb1c14a..b9920b1edd5a 100644
--- a/arch/mn10300/mm/misalignment.c
+++ b/arch/mn10300/mm/misalignment.c
@@ -23,7 +23,6 @@
 #include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c
index 450f7ba3f8f2..4ebf117c3285 100644
--- a/arch/mn10300/mm/pgtable.c
+++ b/arch/mn10300/mm/pgtable.c
@@ -21,7 +21,6 @@
 #include <linux/spinlock.h>
 #include <linux/quicklist.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
diff --git a/arch/mn10300/mm/tlb-smp.c b/arch/mn10300/mm/tlb-smp.c
index 9a777498a916..3e57faf04083 100644
--- a/arch/mn10300/mm/tlb-smp.c
+++ b/arch/mn10300/mm/tlb-smp.c
@@ -24,7 +24,6 @@
 #include <linux/profile.h>
 #include <linux/smp.h>
 #include <asm/tlbflush.h>
-#include <asm/system.h>
 #include <asm/bitops.h>
 #include <asm/processor.h>
 #include <asm/bug.h>
diff --git a/arch/mn10300/proc-mn2ws0050/proc-init.c b/arch/mn10300/proc-mn2ws0050/proc-init.c
index fe6e24906ffc..ee6d03dbc8d8 100644
--- a/arch/mn10300/proc-mn2ws0050/proc-init.c
+++ b/arch/mn10300/proc-mn2ws0050/proc-init.c
@@ -15,7 +15,6 @@
 #include <linux/interrupt.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 11162e6c878f..dcea5a0308ae 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -4,6 +4,7 @@ header-y += spr_defs.h
 
 generic-y += atomic.h
 generic-y += auxvec.h
+generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += bug.h
 generic-y += bugs.h
@@ -19,6 +20,7 @@ generic-y += div64.h
 generic-y += dma.h
 generic-y += emergency-restart.h
 generic-y += errno.h
+generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
@@ -55,6 +57,7 @@ generic-y += sockios.h
 generic-y += statfs.h
 generic-y += stat.h
 generic-y += string.h
+generic-y += switch_to.h
 generic-y += swab.h
 generic-y += termbits.h
 generic-y += termios.h
diff --git a/arch/openrisc/include/asm/system.h b/arch/openrisc/include/asm/system.h
deleted file mode 100644
index cf658882186b..000000000000
--- a/arch/openrisc/include/asm/system.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * OpenRISC Linux
- *
- * Linux architectural port borrowing liberally from similar works of
- * others.  All original copyrights apply as per the original source
- * declaration.
- *
- * OpenRISC implementation:
- * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
- * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
- * et al.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef __ASM_OPENRISC_SYSTEM_H
-#define __ASM_OPENRISC_SYSTEM_H
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <asm/spr.h>
-#include <asm-generic/system.h>
-
-/* We probably need this definition, but the generic system.h provides it
- * and it's not used on our arch anyway...
- */
-/*#define nop() __asm__ __volatile__ ("l.nop"::)*/
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-#endif /* __ASM_OPENRISC_SYSTEM_H */
diff --git a/arch/openrisc/kernel/idle.c b/arch/openrisc/kernel/idle.c
index e5fc78877830..7d618feb1b72 100644
--- a/arch/openrisc/kernel/idle.c
+++ b/arch/openrisc/kernel/idle.c
@@ -31,7 +31,6 @@
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index e4209af879ec..55210f37d1a3 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -38,7 +38,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/spr_defs.h>
diff --git a/arch/openrisc/kernel/prom.c b/arch/openrisc/kernel/prom.c
index 3d4478f6c942..5869e3fa5dd3 100644
--- a/arch/openrisc/kernel/prom.c
+++ b/arch/openrisc/kernel/prom.c
@@ -42,7 +42,6 @@
 #include <asm/processor.h>
 #include <asm/irq.h>
 #include <linux/io.h>
-#include <asm/system.h>
 #include <asm/mmu.h>
 #include <asm/pgtable.h>
 #include <asm/sections.h>
diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c
index 6deacb6b95a4..e71781d24b0e 100644
--- a/arch/openrisc/kernel/ptrace.c
+++ b/arch/openrisc/kernel/ptrace.c
@@ -33,7 +33,6 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 
 /*
  * Copy the thread state to a regset that can be interpreted by userspace.
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index bf5eba22ce9e..f4d5bedc3b4f 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -41,7 +41,6 @@
 #include <linux/of_platform.h>
 
 #include <asm/segment.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/types.h>
 #include <asm/setup.h>
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index a2ee12948f40..5cce396016d0 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -33,7 +33,6 @@
 #include <linux/kallsyms.h>
 #include <asm/uaccess.h>
 
-#include <asm/system.h>
 #include <asm/segment.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index 736f6b2f30af..79dea9740a3c 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -33,7 +33,6 @@
 #include <linux/pagemap.h>
 #include <linux/memblock.h>
 
-#include <asm/system.h>
 #include <asm/segment.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
diff --git a/arch/openrisc/mm/tlb.c b/arch/openrisc/mm/tlb.c
index 56b0b89624af..683bd4d31c7c 100644
--- a/arch/openrisc/mm/tlb.c
+++ b/arch/openrisc/mm/tlb.c
@@ -26,7 +26,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 
-#include <asm/system.h>
 #include <asm/segment.h>
 #include <asm/tlbflush.h>
 #include <asm/pgtable.h>
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 4054b31e0fa9..6c6defc24619 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -6,7 +6,7 @@
 #define _ASM_PARISC_ATOMIC_H_
 
 #include <linux/types.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -49,112 +49,6 @@ extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
 #  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
 #endif
 
-/* This should get optimized out since it's never called.
-** Or get a link error if xchg is used "wrong".
-*/
-extern void __xchg_called_with_bad_pointer(void);
-
-
-/* __xchg32/64 defined in arch/parisc/lib/bitops.c */
-extern unsigned long __xchg8(char, char *);
-extern unsigned long __xchg32(int, int *);
-#ifdef CONFIG_64BIT
-extern unsigned long __xchg64(unsigned long, unsigned long *);
-#endif
-
-/* optimizer better get rid of switch since size is a constant */
-static __inline__ unsigned long
-__xchg(unsigned long x, __volatile__ void * ptr, int size)
-{
-	switch(size) {
-#ifdef CONFIG_64BIT
-	case 8: return __xchg64(x,(unsigned long *) ptr);
-#endif
-	case 4: return __xchg32((int) x, (int *) ptr);
-	case 1: return __xchg8((char) x, (char *) ptr);
-	}
-	__xchg_called_with_bad_pointer();
-	return x;
-}
-
-
-/*
-** REVISIT - Abandoned use of LDCW in xchg() for now:
-** o need to test sizeof(*ptr) to avoid clearing adjacent bytes
-** o and while we are at it, could CONFIG_64BIT code use LDCD too?
-**
-**	if (__builtin_constant_p(x) && (x == NULL))
-**		if (((unsigned long)p & 0xf) == 0)
-**			return __ldcw(p);
-*/
-#define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-
-#define __HAVE_ARCH_CMPXCHG	1
-
-/* bug catcher for when unsupported size is used - won't link */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-/* __cmpxchg_u32/u64 defined in arch/parisc/lib/bitops.c */
-extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old, unsigned int new_);
-extern unsigned long __cmpxchg_u64(volatile unsigned long *ptr, unsigned long old, unsigned long new_);
-
-/* don't worry...optimizer will get rid of most of this */
-static __inline__ unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
-{
-	switch(size) {
-#ifdef CONFIG_64BIT
-	case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
-#endif
-	case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int) old, (unsigned int) new_);
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#define cmpxchg(ptr,o,n)						 \
-  ({									 \
-     __typeof__(*(ptr)) _o_ = (o);					 \
-     __typeof__(*(ptr)) _n_ = (n);					 \
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
-				    (unsigned long)_n_, sizeof(*(ptr))); \
-  })
-
-#include <asm-generic/cmpxchg-local.h>
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-				      unsigned long old,
-				      unsigned long new_, int size)
-{
-	switch (size) {
-#ifdef CONFIG_64BIT
-	case 8:	return __cmpxchg_u64((unsigned long *)ptr, old, new_);
-#endif
-	case 4:	return __cmpxchg_u32(ptr, old, new_);
-	default:
-		return __cmpxchg_local_generic(ptr, old, new_, size);
-	}
-}
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
-			(unsigned long)(n), sizeof(*(ptr))))
-#ifdef CONFIG_64BIT
-#define cmpxchg64_local(ptr, o, n)					\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
-  })
-#else
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-#endif
-
 /*
  * Note that we need not lock read accesses - aligned word writes/reads
  * are atomic, so a reader never sees inconsistent values.
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
new file mode 100644
index 000000000000..e77d834aa803
--- /dev/null
+++ b/arch/parisc/include/asm/barrier.h
@@ -0,0 +1,35 @@
+#ifndef __PARISC_BARRIER_H
+#define __PARISC_BARRIER_H
+
+/*
+** This is simply the barrier() macro from linux/kernel.h but when serial.c
+** uses tqueue.h uses smp_mb() defined using barrier(), linux/kernel.h
+** hasn't yet been included yet so it fails, thus repeating the macro here.
+**
+** PA-RISC architecture allows for weakly ordered memory accesses although
+** none of the processors use it. There is a strong ordered bit that is
+** set in the O-bit of the page directory entry. Operating systems that
+** can not tolerate out of order accesses should set this bit when mapping
+** pages. The O-bit of the PSW should also be set to 1 (I don't believe any
+** of the processor implemented the PSW O-bit). The PCX-W ERS states that
+** the TLB O-bit is not implemented so the page directory does not need to
+** have the O-bit set when mapping pages (section 3.1). This section also
+** states that the PSW Y, Z, G, and O bits are not implemented.
+** So it looks like nothing needs to be done for parisc-linux (yet).
+** (thanks to chada for the above comment -ggg)
+**
+** The __asm__ op below simple prevents gcc/ld from reordering
+** instructions across the mb() "call".
+*/
+#define mb()		__asm__ __volatile__("":::"memory")	/* barrier() */
+#define rmb()		mb()
+#define wmb()		mb()
+#define smp_mb()	mb()
+#define smp_rmb()	mb()
+#define smp_wmb()	mb()
+#define smp_read_barrier_depends()	do { } while(0)
+#define read_barrier_depends()		do { } while(0)
+
+#define set_mb(var, value)		do { var = value; mb(); } while (0)
+
+#endif /* __PARISC_BARRIER_H */
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..dbd13354ec41
--- /dev/null
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -0,0 +1,116 @@
+/*
+ * forked from parisc asm/atomic.h which was:
+ *	Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>
+ *	Copyright (C) 2006 Kyle McMartin <kyle@parisc-linux.org>
+ */
+
+#ifndef _ASM_PARISC_CMPXCHG_H_
+#define _ASM_PARISC_CMPXCHG_H_
+
+/* This should get optimized out since it's never called.
+** Or get a link error if xchg is used "wrong".
+*/
+extern void __xchg_called_with_bad_pointer(void);
+
+/* __xchg32/64 defined in arch/parisc/lib/bitops.c */
+extern unsigned long __xchg8(char, char *);
+extern unsigned long __xchg32(int, int *);
+#ifdef CONFIG_64BIT
+extern unsigned long __xchg64(unsigned long, unsigned long *);
+#endif
+
+/* optimizer better get rid of switch since size is a constant */
+static inline unsigned long
+__xchg(unsigned long x, __volatile__ void *ptr, int size)
+{
+	switch (size) {
+#ifdef CONFIG_64BIT
+	case 8: return __xchg64(x, (unsigned long *) ptr);
+#endif
+	case 4: return __xchg32((int) x, (int *) ptr);
+	case 1: return __xchg8((char) x, (char *) ptr);
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+
+/*
+** REVISIT - Abandoned use of LDCW in xchg() for now:
+** o need to test sizeof(*ptr) to avoid clearing adjacent bytes
+** o and while we are at it, could CONFIG_64BIT code use LDCD too?
+**
+**	if (__builtin_constant_p(x) && (x == NULL))
+**		if (((unsigned long)p & 0xf) == 0)
+**			return __ldcw(p);
+*/
+#define xchg(ptr, x) \
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+
+#define __HAVE_ARCH_CMPXCHG	1
+
+/* bug catcher for when unsupported size is used - won't link */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+/* __cmpxchg_u32/u64 defined in arch/parisc/lib/bitops.c */
+extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
+				   unsigned int new_);
+extern unsigned long __cmpxchg_u64(volatile unsigned long *ptr,
+				   unsigned long old, unsigned long new_);
+
+/* don't worry...optimizer will get rid of most of this */
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
+{
+	switch (size) {
+#ifdef CONFIG_64BIT
+	case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
+#endif
+	case 4: return __cmpxchg_u32((unsigned int *)ptr,
+				     (unsigned int)old, (unsigned int)new_);
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						 \
+({									 \
+	__typeof__(*(ptr)) _o_ = (o);					 \
+	__typeof__(*(ptr)) _n_ = (n);					 \
+	(__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,	 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+})
+
+#include <asm-generic/cmpxchg-local.h>
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+				      unsigned long old,
+				      unsigned long new_, int size)
+{
+	switch (size) {
+#ifdef CONFIG_64BIT
+	case 8:	return __cmpxchg_u64((unsigned long *)ptr, old, new_);
+#endif
+	case 4:	return __cmpxchg_u32(ptr, old, new_);
+	default:
+		return __cmpxchg_local_generic(ptr, old, new_, size);
+	}
+}
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)					\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
+			(unsigned long)(n), sizeof(*(ptr))))
+#ifdef CONFIG_64BIT
+#define cmpxchg64_local(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+})
+#else
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#endif
+
+#endif /* _ASM_PARISC_CMPXCHG_H_ */
diff --git a/arch/parisc/include/asm/delay.h b/arch/parisc/include/asm/delay.h
index 7a75e984674b..912ee7e6a579 100644
--- a/arch/parisc/include/asm/delay.h
+++ b/arch/parisc/include/asm/delay.h
@@ -1,7 +1,7 @@
 #ifndef _PARISC_DELAY_H
 #define _PARISC_DELAY_H
 
-#include <asm/system.h>    /* for mfctl() */
+#include <asm/special_insns.h>    /* for mfctl() */
 #include <asm/processor.h> /* for boot_cpu_data */
 
 
diff --git a/arch/parisc/include/asm/dma.h b/arch/parisc/include/asm/dma.h
index f7a18f968703..fd48ae2de950 100644
--- a/arch/parisc/include/asm/dma.h
+++ b/arch/parisc/include/asm/dma.h
@@ -9,7 +9,6 @@
 #define _ASM_DMA_H
 
 #include <asm/io.h>		/* need byte IO */
-#include <asm/system.h>	
 
 #define dma_outb	outb
 #define dma_inb		inb
diff --git a/arch/parisc/include/asm/exec.h b/arch/parisc/include/asm/exec.h
new file mode 100644
index 000000000000..6bb5af75b17a
--- /dev/null
+++ b/arch/parisc/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef __PARISC_EXEC_H
+#define __PARISC_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __PARISC_EXEC_H */
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index 2388bdb32832..49df14805a9b 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -8,6 +8,29 @@
 #include <asm/atomic.h>
 #include <asm/errno.h>
 
+/* The following has to match the LWS code in syscall.S.  We have
+   sixteen four-word locks. */
+
+static inline void
+_futex_spin_lock_irqsave(u32 __user *uaddr, unsigned long int *flags)
+{
+	extern u32 lws_lock_start[];
+	long index = ((long)uaddr & 0xf0) >> 2;
+	arch_spinlock_t *s = (arch_spinlock_t *)&lws_lock_start[index];
+	local_irq_save(*flags);
+	arch_spin_lock(s);
+}
+
+static inline void
+_futex_spin_unlock_irqrestore(u32 __user *uaddr, unsigned long int *flags)
+{
+	extern u32 lws_lock_start[];
+	long index = ((long)uaddr & 0xf0) >> 2;
+	arch_spinlock_t *s = (arch_spinlock_t *)&lws_lock_start[index];
+	arch_spin_unlock(s);
+	local_irq_restore(*flags);
+}
+
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
@@ -26,7 +49,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 
 	pagefault_disable();
 
-	_atomic_spin_lock_irqsave(uaddr, flags);
+	_futex_spin_lock_irqsave(uaddr, &flags);
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -71,7 +94,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	_atomic_spin_unlock_irqrestore(uaddr, flags);
+	_futex_spin_unlock_irqrestore(uaddr, &flags);
 
 	pagefault_enable();
 
@@ -113,7 +136,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	 * address. This should scale to a couple of CPUs.
 	 */
 
-	_atomic_spin_lock_irqsave(uaddr, flags);
+	_futex_spin_lock_irqsave(uaddr, &flags);
 
 	ret = get_user(val, uaddr);
 
@@ -122,7 +145,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 
 	*uval = val;
 
-	_atomic_spin_unlock_irqrestore(uaddr, flags);
+	_futex_spin_unlock_irqrestore(uaddr, &flags);
 
 	return ret;
 }
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
new file mode 100644
index 000000000000..d2d11b7055ba
--- /dev/null
+++ b/arch/parisc/include/asm/ldcw.h
@@ -0,0 +1,48 @@
+#ifndef __PARISC_LDCW_H
+#define __PARISC_LDCW_H
+
+#ifndef CONFIG_PA20
+/* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
+   and GCC only guarantees 8-byte alignment for stack locals, we can't
+   be assured of 16-byte alignment for atomic lock data even if we
+   specify "__attribute ((aligned(16)))" in the type declaration.  So,
+   we use a struct containing an array of four ints for the atomic lock
+   type and dynamically select the 16-byte aligned int from the array
+   for the semaphore.  */
+
+#define __PA_LDCW_ALIGNMENT	16
+#define __ldcw_align(a) ({					\
+	unsigned long __ret = (unsigned long) &(a)->lock[0];	\
+	__ret = (__ret + __PA_LDCW_ALIGNMENT - 1)		\
+		& ~(__PA_LDCW_ALIGNMENT - 1);			\
+	(volatile unsigned int *) __ret;			\
+})
+#define __LDCW	"ldcw"
+
+#else /*CONFIG_PA20*/
+/* From: "Jim Hull" <jim.hull of hp.com>
+   I've attached a summary of the change, but basically, for PA 2.0, as
+   long as the ",CO" (coherent operation) completer is specified, then the
+   16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
+   they only require "natural" alignment (4-byte for ldcw, 8-byte for
+   ldcd). */
+
+#define __PA_LDCW_ALIGNMENT	4
+#define __ldcw_align(a) (&(a)->slock)
+#define __LDCW	"ldcw,co"
+
+#endif /*!CONFIG_PA20*/
+
+/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.  */
+#define __ldcw(a) ({						\
+	unsigned __ret;						\
+	__asm__ __volatile__(__LDCW " 0(%2),%0"			\
+		: "=r" (__ret), "+m" (*(a)) : "r" (a));		\
+	__ret;							\
+})
+
+#ifdef CONFIG_SMP
+# define __lock_aligned __attribute__((__section__(".data..lock_aligned")))
+#endif
+
+#endif /* __PARISC_LDCW_H */
diff --git a/arch/parisc/include/asm/posix_types.h b/arch/parisc/include/asm/posix_types.h
index 00da29a340ba..5212b0357daf 100644
--- a/arch/parisc/include/asm/posix_types.h
+++ b/arch/parisc/include/asm/posix_types.h
@@ -6,123 +6,22 @@
  * be a little careful about namespace pollution etc.  Also, we cannot
  * assume GCC is being used.
  */
-typedef unsigned long		__kernel_ino_t;
+
 typedef unsigned short		__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short		__kernel_nlink_t;
-typedef long			__kernel_off_t;
-typedef int			__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short		__kernel_ipc_pid_t;
-typedef unsigned int		__kernel_uid_t;
-typedef unsigned int		__kernel_gid_t;
-typedef int			__kernel_suseconds_t;
-typedef long			__kernel_clock_t;
-typedef int			__kernel_timer_t;
-typedef int			__kernel_clockid_t;
-typedef int			__kernel_daddr_t;
-/* Note these change from narrow to wide kernels */
-#ifdef CONFIG_64BIT
-typedef unsigned long		__kernel_size_t;
-typedef long			__kernel_ssize_t;
-typedef long			__kernel_ptrdiff_t;
-#else
-typedef unsigned int		__kernel_size_t;
-typedef int			__kernel_ssize_t;
-typedef int			__kernel_ptrdiff_t;
-#endif
-typedef long			__kernel_time_t;
-typedef char *			__kernel_caddr_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
 
-typedef unsigned short		__kernel_uid16_t;
-typedef unsigned short		__kernel_gid16_t;
-typedef unsigned int		__kernel_uid32_t;
-typedef unsigned int		__kernel_gid32_t;
+typedef int			__kernel_suseconds_t;
+#define __kernel_suseconds_t __kernel_suseconds_t
 
-#ifdef __GNUC__
-typedef long long		__kernel_loff_t;
 typedef long long		__kernel_off64_t;
 typedef unsigned long long	__kernel_ino64_t;
-#endif
-
-typedef unsigned int		__kernel_old_dev_t;
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-/* compatibility stuff */
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-
-#if defined(__KERNEL__)
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{ 
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
 
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 7213ec9e594c..acdf4cad6125 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -16,7 +16,6 @@
 #include <asm/pdc.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
-#include <asm/system.h>
 #include <asm/percpu.h>
 
 #endif /* __ASSEMBLY__ */
@@ -169,6 +168,7 @@ struct thread_struct {
  * Return saved PC of a blocked thread.  This is used by ps mostly.
  */
 
+struct task_struct;
 unsigned long thread_saved_pc(struct task_struct *t);
 void show_trace(struct task_struct *task, unsigned long *stack);
 
diff --git a/arch/parisc/include/asm/psw.h b/arch/parisc/include/asm/psw.h
index 5a3e23c9ce63..ad69a35e9c0f 100644
--- a/arch/parisc/include/asm/psw.h
+++ b/arch/parisc/include/asm/psw.h
@@ -59,4 +59,45 @@
 #define USER_PSW_MASK (WIDE_PSW | PSW_T | PSW_N | PSW_X | PSW_B | PSW_V | PSW_CB)
 #define USER_PSW      (PSW_C | PSW_Q | PSW_P | PSW_D | PSW_I)
 
+#ifndef __ASSEMBLY__
+
+/* The program status word as bitfields.  */
+struct pa_psw {
+	unsigned int y:1;
+	unsigned int z:1;
+	unsigned int rv:2;
+	unsigned int w:1;
+	unsigned int e:1;
+	unsigned int s:1;
+	unsigned int t:1;
+
+	unsigned int h:1;
+	unsigned int l:1;
+	unsigned int n:1;
+	unsigned int x:1;
+	unsigned int b:1;
+	unsigned int c:1;
+	unsigned int v:1;
+	unsigned int m:1;
+
+	unsigned int cb:8;
+
+	unsigned int o:1;
+	unsigned int g:1;
+	unsigned int f:1;
+	unsigned int r:1;
+	unsigned int q:1;
+	unsigned int p:1;
+	unsigned int d:1;
+	unsigned int i:1;
+};
+
+#ifdef CONFIG_64BIT
+#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW + 4))
+#else
+#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW))
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
 #endif
diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h
new file mode 100644
index 000000000000..d306b75bc77f
--- /dev/null
+++ b/arch/parisc/include/asm/special_insns.h
@@ -0,0 +1,40 @@
+#ifndef __PARISC_SPECIAL_INSNS_H
+#define __PARISC_SPECIAL_INSNS_H
+
+#define mfctl(reg)	({		\
+	unsigned long cr;		\
+	__asm__ __volatile__(		\
+		"mfctl " #reg ",%0" :	\
+		 "=r" (cr)		\
+	);				\
+	cr;				\
+})
+
+#define mtctl(gr, cr) \
+	__asm__ __volatile__("mtctl %0,%1" \
+		: /* no outputs */ \
+		: "r" (gr), "i" (cr) : "memory")
+
+/* these are here to de-mystefy the calling code, and to provide hooks */
+/* which I needed for debugging EIEM problems -PB */
+#define get_eiem() mfctl(15)
+static inline void set_eiem(unsigned long val)
+{
+	mtctl(val, 15);
+}
+
+#define mfsp(reg)	({		\
+	unsigned long cr;		\
+	__asm__ __volatile__(		\
+		"mfsp " #reg ",%0" :	\
+		 "=r" (cr)		\
+	);				\
+	cr;				\
+})
+
+#define mtsp(gr, cr) \
+	__asm__ __volatile__("mtsp %0,%1" \
+		: /* no outputs */ \
+		: "r" (gr), "i" (cr) : "memory")
+
+#endif /* __PARISC_SPECIAL_INSNS_H */
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 74036f436a3b..804aa28ab1d6 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -1,7 +1,6 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/spinlock_types.h>
 
diff --git a/arch/parisc/include/asm/switch_to.h b/arch/parisc/include/asm/switch_to.h
new file mode 100644
index 000000000000..8ed8fea1e784
--- /dev/null
+++ b/arch/parisc/include/asm/switch_to.h
@@ -0,0 +1,12 @@
+#ifndef __PARISC_SWITCH_TO_H
+#define __PARISC_SWITCH_TO_H
+
+struct task_struct;
+
+extern struct task_struct *_switch_to(struct task_struct *, struct task_struct *);
+
+#define switch_to(prev, next, last) do {			\
+	(last) = _switch_to(prev, next);			\
+} while(0)
+
+#endif /* __PARISC_SWITCH_TO_H */
diff --git a/arch/parisc/include/asm/system.h b/arch/parisc/include/asm/system.h
deleted file mode 100644
index b19e63a8e848..000000000000
--- a/arch/parisc/include/asm/system.h
+++ /dev/null
@@ -1,165 +0,0 @@
-#ifndef __PARISC_SYSTEM_H
-#define __PARISC_SYSTEM_H
-
-#include <linux/irqflags.h>
-
-/* The program status word as bitfields.  */
-struct pa_psw {
-	unsigned int y:1;
-	unsigned int z:1;
-	unsigned int rv:2;
-	unsigned int w:1;
-	unsigned int e:1;
-	unsigned int s:1;
-	unsigned int t:1;
-
-	unsigned int h:1;
-	unsigned int l:1;
-	unsigned int n:1;
-	unsigned int x:1;
-	unsigned int b:1;
-	unsigned int c:1;
-	unsigned int v:1;
-	unsigned int m:1;
-
-	unsigned int cb:8;
-
-	unsigned int o:1;
-	unsigned int g:1;
-	unsigned int f:1;
-	unsigned int r:1;
-	unsigned int q:1;
-	unsigned int p:1;
-	unsigned int d:1;
-	unsigned int i:1;
-};
-
-#ifdef CONFIG_64BIT
-#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW + 4))
-#else
-#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW))
-#endif
-
-struct task_struct;
-
-extern struct task_struct *_switch_to(struct task_struct *, struct task_struct *);
-
-#define switch_to(prev, next, last) do {			\
-	(last) = _switch_to(prev, next);			\
-} while(0)
-
-#define mfctl(reg)	({		\
-	unsigned long cr;		\
-	__asm__ __volatile__(		\
-		"mfctl " #reg ",%0" :	\
-		 "=r" (cr)		\
-	);				\
-	cr;				\
-})
-
-#define mtctl(gr, cr) \
-	__asm__ __volatile__("mtctl %0,%1" \
-		: /* no outputs */ \
-		: "r" (gr), "i" (cr) : "memory")
-
-/* these are here to de-mystefy the calling code, and to provide hooks */
-/* which I needed for debugging EIEM problems -PB */
-#define get_eiem() mfctl(15)
-static inline void set_eiem(unsigned long val)
-{
-	mtctl(val, 15);
-}
-
-#define mfsp(reg)	({		\
-	unsigned long cr;		\
-	__asm__ __volatile__(		\
-		"mfsp " #reg ",%0" :	\
-		 "=r" (cr)		\
-	);				\
-	cr;				\
-})
-
-#define mtsp(gr, cr) \
-	__asm__ __volatile__("mtsp %0,%1" \
-		: /* no outputs */ \
-		: "r" (gr), "i" (cr) : "memory")
-
-
-/*
-** This is simply the barrier() macro from linux/kernel.h but when serial.c
-** uses tqueue.h uses smp_mb() defined using barrier(), linux/kernel.h
-** hasn't yet been included yet so it fails, thus repeating the macro here.
-**
-** PA-RISC architecture allows for weakly ordered memory accesses although
-** none of the processors use it. There is a strong ordered bit that is
-** set in the O-bit of the page directory entry. Operating systems that
-** can not tolerate out of order accesses should set this bit when mapping
-** pages. The O-bit of the PSW should also be set to 1 (I don't believe any
-** of the processor implemented the PSW O-bit). The PCX-W ERS states that
-** the TLB O-bit is not implemented so the page directory does not need to
-** have the O-bit set when mapping pages (section 3.1). This section also
-** states that the PSW Y, Z, G, and O bits are not implemented.
-** So it looks like nothing needs to be done for parisc-linux (yet).
-** (thanks to chada for the above comment -ggg)
-**
-** The __asm__ op below simple prevents gcc/ld from reordering
-** instructions across the mb() "call".
-*/
-#define mb()		__asm__ __volatile__("":::"memory")	/* barrier() */
-#define rmb()		mb()
-#define wmb()		mb()
-#define smp_mb()	mb()
-#define smp_rmb()	mb()
-#define smp_wmb()	mb()
-#define smp_read_barrier_depends()	do { } while(0)
-#define read_barrier_depends()		do { } while(0)
-
-#define set_mb(var, value)		do { var = value; mb(); } while (0)
-
-#ifndef CONFIG_PA20
-/* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
-   and GCC only guarantees 8-byte alignment for stack locals, we can't
-   be assured of 16-byte alignment for atomic lock data even if we
-   specify "__attribute ((aligned(16)))" in the type declaration.  So,
-   we use a struct containing an array of four ints for the atomic lock
-   type and dynamically select the 16-byte aligned int from the array
-   for the semaphore.  */
-
-#define __PA_LDCW_ALIGNMENT	16
-#define __ldcw_align(a) ({					\
-	unsigned long __ret = (unsigned long) &(a)->lock[0];	\
-	__ret = (__ret + __PA_LDCW_ALIGNMENT - 1)		\
-		& ~(__PA_LDCW_ALIGNMENT - 1);			\
-	(volatile unsigned int *) __ret;			\
-})
-#define __LDCW	"ldcw"
-
-#else /*CONFIG_PA20*/
-/* From: "Jim Hull" <jim.hull of hp.com>
-   I've attached a summary of the change, but basically, for PA 2.0, as
-   long as the ",CO" (coherent operation) completer is specified, then the
-   16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
-   they only require "natural" alignment (4-byte for ldcw, 8-byte for
-   ldcd). */
-
-#define __PA_LDCW_ALIGNMENT	4
-#define __ldcw_align(a) (&(a)->slock)
-#define __LDCW	"ldcw,co"
-
-#endif /*!CONFIG_PA20*/
-
-/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.  */
-#define __ldcw(a) ({						\
-	unsigned __ret;						\
-	__asm__ __volatile__(__LDCW " 0(%2),%0"			\
-		: "=r" (__ret), "+m" (*(a)) : "r" (a));		\
-	__ret;							\
-})
-
-#ifdef CONFIG_SMP
-# define __lock_aligned __attribute__((__section__(".data..lock_aligned")))
-#endif
-
-#define arch_align_stack(x) (x)
-
-#endif
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index 6d9c7c7973d0..83ae7dd4d99e 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -5,6 +5,7 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/processor.h>
+#include <asm/special_insns.h>
 
 struct thread_info {
 	struct task_struct *task;	/* main task structure */
diff --git a/arch/parisc/include/asm/timex.h b/arch/parisc/include/asm/timex.h
index 3b68d77273d9..2bd51f6d832b 100644
--- a/arch/parisc/include/asm/timex.h
+++ b/arch/parisc/include/asm/timex.h
@@ -6,7 +6,6 @@
 #ifndef _ASMPARISC_TIMEX_H
 #define _ASMPARISC_TIMEX_H
 
-#include <asm/system.h>
 
 #define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
 
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index ff4cf9dab8d2..9ac066086f03 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -5,7 +5,6 @@
  * User space memory access functions
  */
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm-generic/uaccess-unaligned.h>
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 83335f3da5fc..9d181890a7e3 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -22,7 +22,6 @@
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index 4896ed090585..f65fa480c905 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -67,7 +67,6 @@
 #include <asm/page.h>
 #include <asm/pdc.h>
 #include <asm/pdcpat.h>
-#include <asm/system.h>
 #include <asm/processor.h>	/* for boot_cpu_data */
 
 static DEFINE_SPINLOCK(pdc_lock);
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 74d544b1cd22..24644aca10cb 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -16,7 +16,6 @@
 #include <linux/types.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/superio.h>
 
 #define DEBUG_RESOURCES 0
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 2905b1f52d30..857c2f545470 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -22,7 +22,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/asm-offsets.h>
 
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 32d588488f04..0bb1d63907f8 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -32,7 +32,6 @@
 #include <linux/bitops.h>
 #include <linux/ftrace.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/current.h>
 #include <asm/delay.h>
@@ -291,8 +290,7 @@ smp_cpu_init(int cpunum)
 	mb();
 
 	/* Well, support 2.4 linux scheme as well. */
-	if (cpu_isset(cpunum, cpu_online_map))
-	{
+	if (cpu_online(cpunum))	{
 		extern void machine_halt(void); /* arch/parisc.../process.c */
 
 		printk(KERN_CRIT "CPU#%d already initialized!\n", cpunum);
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index f19e6604026a..45ba99f5080b 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -27,7 +27,6 @@
 #include <linux/bug.h>
 
 #include <asm/assembly.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c
index a8bffd8af77d..187118841af1 100644
--- a/arch/parisc/lib/bitops.c
+++ b/arch/parisc/lib/bitops.c
@@ -8,7 +8,6 @@
 
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
-#include <asm/system.h>
 #include <linux/atomic.h>
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d219ebecabf0..feab3bad6d0f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -133,7 +133,6 @@ config PPC
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select SPARSE_IRQ
 	select IRQ_PER_CPU
 	select IRQ_DOMAIN
@@ -154,6 +153,7 @@ config COMPAT
 	bool
 	default y if PPC64
 	select COMPAT_BINFMT_ELF
+	select ARCH_WANT_OLD_COMPAT_IPC
 
 config SYSVIPC_COMPAT
 	bool
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 72d55dbc6119..e5f26890a69e 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -114,16 +114,6 @@ config DEBUGGER
 	depends on KGDB || XMON
 	default y
 
-config VIRQ_DEBUG
-	bool "Expose hardware/virtual IRQ mapping via debugfs"
-	depends on DEBUG_FS
-	help
-	  This option will show the mapping relationship between hardware irq
-	  numbers and virtual irq numbers. The mapping is exposed via debugfs
-	  in the file powerpc/virq_mapping.
-
-	  If you don't know what this means you don't need it.
-
 config BDI_SWITCH
 	bool "Include BDI-2000 user context switcher"
 	depends on DEBUG_KERNEL && PPC32
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index 12da77ec0228..1c1aadc8c48f 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -27,7 +27,6 @@ zImage.bin.*
 zImage.chrp
 zImage.coff
 zImage.holly
-zImage.iseries
 zImage.*lds
 zImage.miboot
 zImage.pmac
diff --git a/arch/powerpc/boot/dts/p1020mbg-pc.dtsi b/arch/powerpc/boot/dts/p1020mbg-pc.dtsi
new file mode 100644
index 000000000000..a24699cfea9c
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020mbg-pc.dtsi
@@ -0,0 +1,151 @@
+/*
+ * P1020 MBG-PC Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&lbc {
+	nor@0,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "cfi-flash";
+		reg = <0x0 0x0 0x4000000>;
+		bank-width = <2>;
+		device-width = <1>;
+
+		partition@0 {
+			/* 128KB for DTB Image */
+			reg = <0x0 0x00020000>;
+			label = "NOR DTB Image";
+		};
+
+		partition@20000 {
+			/* 3.875 MB for Linux Kernel Image */
+			reg = <0x00020000 0x003e0000>;
+			label = "NOR Linux Kernel Image";
+		};
+
+		partition@400000 {
+			/* 58MB for Root file System */
+			reg = <0x00400000 0x03a00000>;
+			label = "NOR Root File System";
+		};
+
+		partition@3e00000 {
+			/* This location must not be altered  */
+			/* 1M for Vitesse 7385 Switch firmware */
+			reg = <0x3e00000 0x00100000>;
+			label = "NOR Vitesse-7385 Firmware";
+			read-only;
+		};
+
+		partition@3f00000 {
+			/* This location must not be altered  */
+			/* 512KB for u-boot Bootloader Image */
+			/* 512KB for u-boot Environment Variables */
+			reg = <0x03f00000 0x00100000>;
+			label = "NOR U-Boot Image";
+			read-only;
+		};
+	};
+
+	L2switch@2,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "vitesse-7385";
+		reg = <0x2 0x0 0x20000>;
+	};
+};
+
+&soc {
+	i2c@3000 {
+		rtc@68 {
+			compatible = "dallas,ds1339";
+			reg = <0x68>;
+		};
+	};
+
+	mdio@24000 {
+		phy0: ethernet-phy@0 {
+			interrupts = <3 1 0 0>;
+			reg = <0x0>;
+		};
+		phy1: ethernet-phy@1 {
+			interrupts = <2 1 0 0>;
+			reg = <0x1>;
+		};
+	};
+
+	mdio@25000 {
+		tbi1: tbi-phy@11 {
+			reg = <0x11>;
+			device_type = "tbi-phy";
+		};
+	};
+
+	mdio@26000 {
+		tbi2: tbi-phy@11 {
+			reg = <0x11>;
+			device_type = "tbi-phy";
+		};
+	};
+
+	enet0: ethernet@b0000 {
+		fixed-link = <1 1 1000 0 0>;
+		phy-connection-type = "rgmii-id";
+	};
+
+	enet1: ethernet@b1000 {
+		phy-handle = <&phy0>;
+		tbi-handle = <&tbi1>;
+		phy-connection-type = "sgmii";
+	};
+
+	enet2: ethernet@b2000 {
+		phy-handle = <&phy1>;
+		phy-connection-type = "rgmii-id";
+	};
+
+	usb@22000 {
+		phy_type = "ulpi";
+	};
+
+	/* USB2 is shared with localbus, so it must be disabled
+	   by default. We can't put 'status = "disabled";' here
+	   since U-Boot doesn't clear the status property when
+	   it enables USB2. OTOH, U-Boot does create a new node
+	   when there isn't any. So, just comment it out.
+	*/
+	usb@23000 {
+		status = "disabled";
+		phy_type = "ulpi";
+	};
+};
diff --git a/arch/powerpc/boot/dts/p1020mbg-pc_32b.dts b/arch/powerpc/boot/dts/p1020mbg-pc_32b.dts
new file mode 100644
index 000000000000..ab8f076eae90
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020mbg-pc_32b.dts
@@ -0,0 +1,89 @@
+/*
+ * P1020 MBG-PC Device Tree Source (32-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+	model = "fsl,P1020MBG-PC";
+	compatible = "fsl,P1020MBG-PC";
+
+	memory {
+		device_type = "memory";
+	};
+
+	lbc: localbus@ffe05000 {
+		reg = <0x0 0xffe05000 0x0 0x1000>;
+
+		/* NOR and L2 switch */
+		ranges = <0x0 0x0 0x0 0xec000000 0x04000000
+			  0x1 0x0 0x0 0xffa00000 0x00040000
+			  0x2 0x0 0x0 0xffb00000 0x00020000>;
+	};
+
+	soc: soc@ffe00000 {
+		ranges = <0x0 0x0 0xffe00000 0x100000>;
+	};
+
+	pci0: pcie@ffe09000 {
+		reg = <0x0 0xffe09000 0x0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0x0 0xa0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0x0 0xffc10000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci1: pcie@ffe0a000 {
+		reg = <0x0 0xffe0a000 0x0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0x0 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0x0 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
+
+/include/ "p1020mbg-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1020mbg-pc_36b.dts b/arch/powerpc/boot/dts/p1020mbg-pc_36b.dts
new file mode 100644
index 000000000000..9e9f401419b1
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020mbg-pc_36b.dts
@@ -0,0 +1,89 @@
+/*
+ * P1020 MBG-PC Device Tree Source (36-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+	model = "fsl,P1020MBG-PC";
+	compatible = "fsl,P1020MBG-PC";
+
+	memory {
+		device_type = "memory";
+	};
+
+	lbc: localbus@fffe05000 {
+		reg = <0xf 0xffe05000 0x0 0x1000>;
+
+		/* NOR and L2 switch */
+		ranges = <0x0 0x0 0xf 0xec000000 0x04000000
+			  0x1 0x0 0xf 0xffa00000 0x00040000
+			  0x2 0x0 0xf 0xffb00000 0x00020000>;
+	};
+
+	soc: soc@fffe00000 {
+		ranges = <0x0 0xf 0xffe00000 0x100000>;
+	};
+
+	pci0: pcie@fffe09000 {
+		reg = <0xf 0xffe09000 0x0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci1: pcie@fffe0a000 {
+		reg = <0xf 0xffe0a000 0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
+
+/include/ "p1020mbg-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1020utm-pc.dtsi b/arch/powerpc/boot/dts/p1020utm-pc.dtsi
new file mode 100644
index 000000000000..7ea85eabcc5c
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020utm-pc.dtsi
@@ -0,0 +1,140 @@
+/*
+ * P1020 UTM-PC Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&lbc {
+	nor@0,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "cfi-flash";
+		reg = <0x0 0x0 0x2000000>;
+		bank-width = <2>;
+		device-width = <1>;
+
+		partition@0 {
+			/* 256KB for DTB Image */
+			reg = <0x0 0x00040000>;
+			label = "NOR DTB Image";
+		};
+
+		partition@40000 {
+			/* 3.75 MB for Linux Kernel Image */
+			reg = <0x00040000 0x003c0000>;
+			label = "NOR Linux Kernel Image";
+		};
+
+		partition@400000 {
+			/* 27MB for Root file System */
+			reg = <0x00400000 0x01b00000>;
+			label = "NOR Root File System";
+		};
+
+		partition@1f00000 {
+			/* This location must not be altered  */
+			/* 512KB for u-boot Bootloader Image */
+			/* 512KB for u-boot Environment Variables */
+			reg = <0x01f00000 0x00100000>;
+			label = "NOR U-Boot Image";
+			read-only;
+		};
+	};
+};
+
+&soc {
+	i2c@3000 {
+		rtc@68 {
+			compatible = "dallas,ds1339";
+			reg = <0x68>;
+		};
+	};
+
+	mdio@24000 {
+		phy0: ethernet-phy@0 {
+			interrupts = <3 1 0 0>;
+			reg = <0x0>;
+		};
+		phy1: ethernet-phy@1 {
+			interrupts = <2 1 0 0>;
+			reg = <0x1>;
+		};
+		phy2: ethernet-phy@2 {
+			interrupts = <1 1 0 0>;
+			reg = <0x2>;
+		};
+	};
+
+	mdio@25000 {
+		tbi1: tbi-phy@11 {
+			reg = <0x11>;
+			device_type = "tbi-phy";
+		};
+	};
+
+	mdio@26000 {
+		tbi2: tbi-phy@11 {
+			reg = <0x11>;
+			device_type = "tbi-phy";
+		};
+	};
+
+	enet0: ethernet@b0000 {
+		phy-handle = <&phy2>;
+		phy-connection-type = "rgmii-id";
+	};
+
+	enet1: ethernet@b1000 {
+		phy-handle = <&phy0>;
+		tbi-handle = <&tbi1>;
+		phy-connection-type = "sgmii";
+	};
+
+	enet2: ethernet@b2000 {
+		phy-handle = <&phy1>;
+		phy-connection-type = "rgmii-id";
+	};
+
+	usb@22000 {
+		phy_type = "ulpi";
+	};
+
+	/* USB2 is shared with localbus, so it must be disabled
+	   by default. We can't put 'status = "disabled";' here
+	   since U-Boot doesn't clear the status property when
+	   it enables USB2. OTOH, U-Boot does create a new node
+	   when there isn't any. So, just comment it out.
+	*/
+	usb@23000 {
+		status = "disabled";
+		phy_type = "ulpi";
+	};
+};
diff --git a/arch/powerpc/boot/dts/p1020utm-pc_32b.dts b/arch/powerpc/boot/dts/p1020utm-pc_32b.dts
new file mode 100644
index 000000000000..4bfdd8971cdb
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020utm-pc_32b.dts
@@ -0,0 +1,89 @@
+/*
+ * P1020 UTM-PC Device Tree Source (32-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+	model = "fsl,P1020UTM-PC";
+	compatible = "fsl,P1020UTM-PC";
+
+	memory {
+		device_type = "memory";
+	};
+
+	lbc: localbus@ffe05000 {
+		reg = <0x0 0xffe05000 0x0 0x1000>;
+
+		/* NOR */
+		ranges = <0x0 0x0 0x0 0xec000000 0x02000000
+			  0x1 0x0 0x0 0xffa00000 0x00040000
+			  0x2 0x0 0x0 0xffb00000 0x00020000>;
+	};
+
+	soc: soc@ffe00000 {
+		ranges = <0x0 0x0 0xffe00000 0x100000>;
+	};
+
+	pci0: pcie@ffe09000 {
+		reg = <0x0 0xffe09000 0x0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0x0 0xa0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0x0 0xffc10000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci1: pcie@ffe0a000 {
+		reg = <0x0 0xffe0a000 0x0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0x0 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0x0 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
+
+/include/ "p1020utm-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1020utm-pc_36b.dts b/arch/powerpc/boot/dts/p1020utm-pc_36b.dts
new file mode 100644
index 000000000000..abec53557501
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020utm-pc_36b.dts
@@ -0,0 +1,89 @@
+/*
+ * P1020 UTM-PC Device Tree Source (36-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+	model = "fsl,P1020UTM-PC";
+	compatible = "fsl,P1020UTM-PC";
+
+	memory {
+		device_type = "memory";
+	};
+
+	lbc: localbus@fffe05000 {
+		reg = <0xf 0xffe05000 0x0 0x1000>;
+
+		/* NOR */
+		ranges = <0x0 0x0 0xf 0xec000000 0x02000000
+			  0x1 0x0 0xf 0xffa00000 0x00040000
+			  0x2 0x0 0xf 0xffb00000 0x00020000>;
+	};
+
+	soc: soc@fffe00000 {
+		ranges = <0x0 0xf 0xffe00000 0x100000>;
+	};
+
+	pci0: pcie@fffe09000 {
+		reg = <0xf 0xffe09000 0x0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci1: pcie@fffe0a000 {
+		reg = <0xf 0xffe0a000 0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
+
+/include/ "p1020utm-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p2041rdb.dts b/arch/powerpc/boot/dts/p2041rdb.dts
index 4f957db01230..285213976a7f 100644
--- a/arch/powerpc/boot/dts/p2041rdb.dts
+++ b/arch/powerpc/boot/dts/p2041rdb.dts
@@ -135,7 +135,6 @@
 		reg = <0xf 0xfe200000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-		fsl,msi = <&msi0>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -151,7 +150,6 @@
 		reg = <0xf 0xfe201000 0 0x1000>;
 		ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
 			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-		fsl,msi = <&msi1>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -167,7 +165,6 @@
 		reg = <0xf 0xfe202000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
-		fsl,msi = <&msi2>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/boot/dts/p3041ds.dts b/arch/powerpc/boot/dts/p3041ds.dts
index f469145abaeb..22a215e94162 100644
--- a/arch/powerpc/boot/dts/p3041ds.dts
+++ b/arch/powerpc/boot/dts/p3041ds.dts
@@ -173,7 +173,6 @@
 		reg = <0xf 0xfe200000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-		fsl,msi = <&msi0>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -189,7 +188,6 @@
 		reg = <0xf 0xfe201000 0 0x1000>;
 		ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
 			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-		fsl,msi = <&msi1>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -205,7 +203,6 @@
 		reg = <0xf 0xfe202000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
-		fsl,msi = <&msi2>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -221,7 +218,6 @@
 		reg = <0xf 0xfe203000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x60000000 0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>;
-		fsl,msi = <&msi2>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/boot/dts/p3060qds.dts b/arch/powerpc/boot/dts/p3060qds.dts
index 529042e4b9a2..9ae875c8a211 100644
--- a/arch/powerpc/boot/dts/p3060qds.dts
+++ b/arch/powerpc/boot/dts/p3060qds.dts
@@ -212,7 +212,6 @@
 		reg = <0xf 0xfe200000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-		fsl,msi = <&msi0>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -228,7 +227,6 @@
 		reg = <0xf 0xfe201000 0 0x1000>;
 		ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
 			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-		fsl,msi = <&msi1>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/boot/dts/p4080ds.dts b/arch/powerpc/boot/dts/p4080ds.dts
index 6d60e54e50a0..3e204609d02e 100644
--- a/arch/powerpc/boot/dts/p4080ds.dts
+++ b/arch/powerpc/boot/dts/p4080ds.dts
@@ -141,7 +141,6 @@
 		reg = <0xf 0xfe200000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-		fsl,msi = <&msi0>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -157,7 +156,6 @@
 		reg = <0xf 0xfe201000 0 0x1000>;
 		ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
 			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-		fsl,msi = <&msi1>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -173,7 +171,6 @@
 		reg = <0xf 0xfe202000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
-		fsl,msi = <&msi2>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/boot/dts/p5020ds.dts b/arch/powerpc/boot/dts/p5020ds.dts
index 1c250684c902..27c07ed6adc1 100644
--- a/arch/powerpc/boot/dts/p5020ds.dts
+++ b/arch/powerpc/boot/dts/p5020ds.dts
@@ -173,7 +173,6 @@
 		reg = <0xf 0xfe200000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-		fsl,msi = <&msi0>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -189,7 +188,6 @@
 		reg = <0xf 0xfe201000 0 0x1000>;
 		ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
 			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-		fsl,msi = <&msi1>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -205,7 +203,6 @@
 		reg = <0xf 0xfe202000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
-		fsl,msi = <&msi2>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
@@ -221,7 +218,6 @@
 		reg = <0xf 0xfe203000 0 0x1000>;
 		ranges = <0x02000000 0 0xe0000000 0xc 0x60000000 0 0x20000000
 			  0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>;
-		fsl,msi = <&msi2>;
 		pcie@0 {
 			ranges = <0x02000000 0 0xe0000000
 				  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023rds_defconfig
index c091aaf7685f..f4337bacd0e7 100644
--- a/arch/powerpc/configs/85xx/p1023rds_defconfig
+++ b/arch/powerpc/configs/85xx/p1023rds_defconfig
@@ -165,7 +165,7 @@ CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig
index acf7fb280464..f104ccde6b53 100644
--- a/arch/powerpc/configs/chroma_defconfig
+++ b/arch/powerpc/configs/chroma_defconfig
@@ -279,7 +279,7 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_PPC_EMULATED_STATS=y
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_PPC_EARLY_DEBUG=y
 CONFIG_KEYS_DEBUG_PROC_KEYS=y
 CONFIG_CRYPTO_NULL=m
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index f8aef205d222..91db656294e8 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -116,6 +116,7 @@ CONFIG_SERIAL_8250_RSA=y
 CONFIG_HW_RANDOM=y
 CONFIG_NVRAM=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
 CONFIG_SPI=y
 CONFIG_SPI_GPIO=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index 7ed8d4cf2719..6798343580f0 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -71,6 +71,8 @@ CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_MPC=y
 # CONFIG_HWMON is not set
 CONFIG_VIDEO_OUTPUT_CONTROL=y
 # CONFIG_HID_SUPPORT is not set
@@ -95,7 +97,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index 5fb0c8a94811..d6b6df5e8743 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -117,6 +117,7 @@ CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_QE=m
 CONFIG_NVRAM=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_CPM=m
 CONFIG_I2C_MPC=y
 CONFIG_SPI=y
@@ -214,7 +215,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index fb51bc90edd2..5b0e2926becd 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -119,6 +119,7 @@ CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_QE=m
 CONFIG_NVRAM=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_CPM=m
 CONFIG_I2C_MPC=y
 CONFIG_SPI=y
@@ -216,7 +217,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 1acf65026773..c1442a3758ae 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -457,7 +457,7 @@ CONFIG_CODE_PATCHING_SELFTEST=y
 CONFIG_FTR_FIXUP_SELFTEST=y
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_BOOTX_TEXT=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 30e7d0d20e49..6608232663cb 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -340,7 +340,7 @@ CONFIG_FTR_FIXUP_SELFTEST=y
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
-CONFIG_VIRQ_DEBUG=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 14174e838ad9..da29032ae38f 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -5,13 +5,9 @@
  * PowerPC atomic operations
  */
 
-#include <linux/types.h>
-
 #ifdef __KERNEL__
-#include <linux/compiler.h>
-#include <asm/synch.h>
-#include <asm/asm-compat.h>
-#include <asm/system.h>
+#include <linux/types.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)		{ (i) }
 
diff --git a/arch/powerpc/include/asm/auxvec.h b/arch/powerpc/include/asm/auxvec.h
index 19a099b62cd6..ce17d2c9eb4e 100644
--- a/arch/powerpc/include/asm/auxvec.h
+++ b/arch/powerpc/include/asm/auxvec.h
@@ -16,4 +16,6 @@
  */
 #define AT_SYSINFO_EHDR		33
 
+#define AT_VECTOR_SIZE_ARCH 6 /* entries in ARCH_DLINFO */
+
 #endif
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
new file mode 100644
index 000000000000..ae782254e731
--- /dev/null
+++ b/arch/powerpc/include/asm/barrier.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_BARRIER_H
+#define _ASM_POWERPC_BARRIER_H
+
+/*
+ * Memory barrier.
+ * The sync instruction guarantees that all memory accesses initiated
+ * by this processor have been performed (with respect to all other
+ * mechanisms that access memory).  The eieio instruction is a barrier
+ * providing an ordering (separately) for (a) cacheable stores and (b)
+ * loads and stores to non-cacheable memory (e.g. I/O devices).
+ *
+ * mb() prevents loads and stores being reordered across this point.
+ * rmb() prevents loads being reordered across this point.
+ * wmb() prevents stores being reordered across this point.
+ * read_barrier_depends() prevents data-dependent loads being reordered
+ *	across this point (nop on PPC).
+ *
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
+ *
+ * For the smp_ barriers, ordering is for cacheable memory operations
+ * only. We have to use the sync instruction for smp_mb(), since lwsync
+ * doesn't order loads with respect to previous stores.  Lwsync can be
+ * used for smp_rmb() and smp_wmb().
+ *
+ * However, on CPUs that don't support lwsync, lwsync actually maps to a
+ * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio.
+ */
+#define mb()   __asm__ __volatile__ ("sync" : : : "memory")
+#define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
+#define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
+#define read_barrier_depends()  do { } while(0)
+
+#define set_mb(var, value)	do { var = value; mb(); } while (0)
+
+#ifdef CONFIG_SMP
+
+#ifdef __SUBARCH_HAS_LWSYNC
+#    define SMPWMB      LWSYNC
+#else
+#    define SMPWMB      eieio
+#endif
+
+#define smp_mb()	mb()
+#define smp_rmb()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
+#define smp_read_barrier_depends()	read_barrier_depends()
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while(0)
+#endif /* CONFIG_SMP */
+
+/*
+ * This is a barrier which prevents following instructions from being
+ * started until the value of the argument x is known.  For example, if
+ * x is a variable loaded from memory, this prevents following
+ * instructions from being executed until the load has been performed.
+ */
+#define data_barrier(x)	\
+	asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
+
+#endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 065c590c991d..3eb53d741070 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -126,5 +126,16 @@
 
 #include <asm-generic/bug.h>
 
+#ifndef __ASSEMBLY__
+
+struct pt_regs;
+extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
+extern void bad_page_fault(struct pt_regs *, unsigned long, int);
+extern void _exception(int, struct pt_regs *, int, unsigned long);
+extern void die(const char *, struct pt_regs *, long);
+extern void print_backtrace(unsigned long *);
+
+#endif /* !__ASSEMBLY__ */
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_BUG_H */
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 4b509411ad8a..9e495c9a6a88 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -42,8 +42,24 @@ extern struct ppc64_caches ppc64_caches;
 #endif /* __powerpc64__ && ! __ASSEMBLY__ */
 
 #if !defined(__ASSEMBLY__)
+
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
+#ifdef CONFIG_6xx
+extern long _get_L2CR(void);
+extern long _get_L3CR(void);
+extern void _set_L2CR(unsigned long);
+extern void _set_L3CR(unsigned long);
+#else
+#define _get_L2CR()	0L
+#define _get_L3CR()	0L
+#define _set_L2CR(val)	do { } while(0)
+#define _set_L3CR(val)	do { } while(0)
 #endif
 
+extern void cacheable_memzero(void *p, unsigned int nb);
+extern void *cacheable_memcpy(void *, const void *, unsigned int);
+
+#endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_CACHE_H */
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..e245aab7f191
--- /dev/null
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -0,0 +1,309 @@
+#ifndef _ASM_POWERPC_CMPXCHG_H_
+#define _ASM_POWERPC_CMPXCHG_H_
+
+#ifdef __KERNEL__
+#include <linux/compiler.h>
+#include <asm/synch.h>
+#include <asm/asm-compat.h>
+
+/*
+ * Atomic exchange
+ *
+ * Changes the memory location '*ptr' to be val and returns
+ * the previous value stored there.
+ */
+static __always_inline unsigned long
+__xchg_u32(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+	PPC_RELEASE_BARRIER
+"1:	lwarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%3,0,%2 \n\
+	bne-	1b"
+	PPC_ACQUIRE_BARRIER
+	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+/*
+ * Atomic exchange
+ *
+ * Changes the memory location '*ptr' to be val and returns
+ * the previous value stored there.
+ */
+static __always_inline unsigned long
+__xchg_u32_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%3,0,%2 \n\
+	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+#ifdef CONFIG_PPC64
+static __always_inline unsigned long
+__xchg_u64(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+	PPC_RELEASE_BARRIER
+"1:	ldarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stdcx.	%3,0,%2 \n\
+	bne-	1b"
+	PPC_ACQUIRE_BARRIER
+	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u64_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stdcx.	%3,0,%2 \n\
+	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+#endif
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid xchg().
+ */
+extern void __xchg_called_with_bad_pointer(void);
+
+static __always_inline unsigned long
+__xchg(volatile void *ptr, unsigned long x, unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __xchg_u32(ptr, x);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __xchg_u64(ptr, x);
+#endif
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+
+static __always_inline unsigned long
+__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __xchg_u32_local(ptr, x);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __xchg_u64_local(ptr, x);
+#endif
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+#define xchg(ptr,x)							     \
+  ({									     \
+     __typeof__(*(ptr)) _x_ = (x);					     \
+     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \
+  })
+
+#define xchg_local(ptr,x)						     \
+  ({									     \
+     __typeof__(*(ptr)) _x_ = (x);					     \
+     (__typeof__(*(ptr))) __xchg_local((ptr),				     \
+     		(unsigned long)_x_, sizeof(*(ptr))); 			     \
+  })
+
+/*
+ * Compare and exchange - if *p == old, set it to new,
+ * and return the old value of *p.
+ */
+#define __HAVE_ARCH_CMPXCHG	1
+
+static __always_inline unsigned long
+__cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_RELEASE_BARRIER
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
+	cmpw	0,%0,%3\n\
+	bne-	2f\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%4,0,%2\n\
+	bne-	1b"
+	PPC_ACQUIRE_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
+	cmpw	0,%0,%3\n\
+	bne-	2f\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%4,0,%2\n\
+	bne-	1b"
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+#ifdef CONFIG_PPC64
+static __always_inline unsigned long
+__cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+	PPC_RELEASE_BARRIER
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
+	cmpd	0,%0,%3\n\
+	bne-	2f\n\
+	stdcx.	%4,0,%2\n\
+	bne-	1b"
+	PPC_ACQUIRE_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
+	cmpd	0,%0,%3\n\
+	bne-	2f\n\
+	stdcx.	%4,0,%2\n\
+	bne-	1b"
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+#endif
+
+/* This function doesn't exist, so you'll get a linker error
+   if something tries to do an invalid cmpxchg().  */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+static __always_inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
+	  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+static __always_inline unsigned long
+__cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
+	  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32_local(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_local(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+
+#define cmpxchg_local(ptr, o, n)					 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+#ifdef CONFIG_PPC64
+#define cmpxchg64(ptr, o, n)						\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg((ptr), (o), (n));					\
+  })
+#define cmpxchg64_local(ptr, o, n)					\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+  })
+#else
+#include <asm-generic/cmpxchg-local.h>
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_CMPXCHG_H_ */
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
new file mode 100644
index 000000000000..716d2f089eb6
--- /dev/null
+++ b/arch/powerpc/include/asm/debug.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_DEBUG_H
+#define _ASM_POWERPC_DEBUG_H
+
+struct pt_regs;
+
+extern struct dentry *powerpc_debugfs_root;
+
+#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
+
+extern int (*__debugger)(struct pt_regs *regs);
+extern int (*__debugger_ipi)(struct pt_regs *regs);
+extern int (*__debugger_bpt)(struct pt_regs *regs);
+extern int (*__debugger_sstep)(struct pt_regs *regs);
+extern int (*__debugger_iabr_match)(struct pt_regs *regs);
+extern int (*__debugger_dabr_match)(struct pt_regs *regs);
+extern int (*__debugger_fault_handler)(struct pt_regs *regs);
+
+#define DEBUGGER_BOILERPLATE(__NAME) \
+static inline int __NAME(struct pt_regs *regs) \
+{ \
+	if (unlikely(__ ## __NAME)) \
+		return __ ## __NAME(regs); \
+	return 0; \
+}
+
+DEBUGGER_BOILERPLATE(debugger)
+DEBUGGER_BOILERPLATE(debugger_ipi)
+DEBUGGER_BOILERPLATE(debugger_bpt)
+DEBUGGER_BOILERPLATE(debugger_sstep)
+DEBUGGER_BOILERPLATE(debugger_iabr_match)
+DEBUGGER_BOILERPLATE(debugger_dabr_match)
+DEBUGGER_BOILERPLATE(debugger_fault_handler)
+
+#else
+static inline int debugger(struct pt_regs *regs) { return 0; }
+static inline int debugger_ipi(struct pt_regs *regs) { return 0; }
+static inline int debugger_bpt(struct pt_regs *regs) { return 0; }
+static inline int debugger_sstep(struct pt_regs *regs) { return 0; }
+static inline int debugger_iabr_match(struct pt_regs *regs) { return 0; }
+static inline int debugger_dabr_match(struct pt_regs *regs) { return 0; }
+static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; }
+#endif
+
+extern int set_dabr(unsigned long dabr);
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+extern void do_send_trap(struct pt_regs *regs, unsigned long address,
+			 unsigned long error_code, int signal_code, int brkpt);
+#else
+extern void do_dabr(struct pt_regs *regs, unsigned long address,
+		    unsigned long error_code);
+#endif
+
+#endif /* _ASM_POWERPC_DEBUG_H */
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index dd70fac57ec8..62678e365ca0 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -22,9 +22,11 @@
 
 /* Some dma direct funcs must be visible for use in other dma_ops */
 extern void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag);
+				       dma_addr_t *dma_handle, gfp_t flag,
+				       struct dma_attrs *attrs);
 extern void dma_direct_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle);
+				     void *vaddr, dma_addr_t dma_handle,
+				     struct dma_attrs *attrs);
 
 
 #ifdef CONFIG_NOT_COHERENT_CACHE
@@ -130,23 +132,29 @@ static inline int dma_supported(struct device *dev, u64 mask)
 
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 	void *cpu_addr;
 
 	BUG_ON(!dma_ops);
 
-	cpu_addr = dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+	cpu_addr = dma_ops->alloc(dev, size, dma_handle, flag, attrs);
 
 	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
 
 	return cpu_addr;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
@@ -154,7 +162,7 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
 
-	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+	dma_ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/powerpc/include/asm/dma.h b/arch/powerpc/include/asm/dma.h
index adadb9943610..f6813e919bb2 100644
--- a/arch/powerpc/include/asm/dma.h
+++ b/arch/powerpc/include/asm/dma.h
@@ -24,7 +24,6 @@
 
 #include <asm/io.h>
 #include <linux/spinlock.h>
-#include <asm/system.h>
 
 #ifndef MAX_DMA_CHANNELS
 #define MAX_DMA_CHANNELS	8
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index f3b0c2cc9fea..976835d8f22e 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -134,10 +134,15 @@
  * whether they will be clobbered.
  *
  * Note that r11 can be used as an output parameter.
+ *
+ * The "memory" clobber is only necessary for hcalls where the Hypervisor
+ * will read or write guest memory. However, we add it to all hcalls because
+ * the impact is minimal, and we want to ensure that it's present for the
+ * hcalls that need it.
 */
 
 /* List of common clobbered registers.  Do not use this macro. */
-#define EV_HCALL_CLOBBERS "r0", "r12", "xer", "ctr", "lr", "cc"
+#define EV_HCALL_CLOBBERS "r0", "r12", "xer", "ctr", "lr", "cc", "memory"
 
 #define EV_HCALL_CLOBBERS8 EV_HCALL_CLOBBERS
 #define EV_HCALL_CLOBBERS7 EV_HCALL_CLOBBERS8, "r10"
diff --git a/arch/powerpc/include/asm/exec.h b/arch/powerpc/include/asm/exec.h
new file mode 100644
index 000000000000..8196e9c7d7e8
--- /dev/null
+++ b/arch/powerpc/include/asm/exec.h
@@ -0,0 +1,9 @@
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_EXEC_H
+#define _ASM_POWERPC_EXEC_H
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif /* _ASM_POWERPC_EXEC_H */
diff --git a/arch/powerpc/include/asm/fsl_guts.h b/arch/powerpc/include/asm/fsl_guts.h
index ce04530d2000..aa4c488589ce 100644
--- a/arch/powerpc/include/asm/fsl_guts.h
+++ b/arch/powerpc/include/asm/fsl_guts.h
@@ -16,15 +16,6 @@
 #define __ASM_POWERPC_FSL_GUTS_H__
 #ifdef __KERNEL__
 
-/*
- * These #ifdefs are safe because it's not possible to build a kernel that
- * runs on e500 and e600 cores.
- */
-
-#if !defined(CONFIG_PPC_85xx) && !defined(CONFIG_PPC_86xx)
-#error Only 85xx and 86xx SOCs are supported
-#endif
-
 /**
  * Global Utility Registers.
  *
@@ -36,11 +27,7 @@
  * different names.  In these cases, one name is chosen to avoid extraneous
  * #ifdefs.
  */
-#ifdef CONFIG_PPC_85xx
-struct ccsr_guts_85xx {
-#else
-struct ccsr_guts_86xx {
-#endif
+struct ccsr_guts {
 	__be32	porpllsr;	/* 0x.0000 - POR PLL Ratio Status Register */
 	__be32	porbmsr;	/* 0x.0004 - POR Boot Mode Status Register */
 	__be32	porimpscr;	/* 0x.0008 - POR I/O Impedance Status and Control Register */
@@ -77,11 +64,8 @@ struct ccsr_guts_86xx {
 	u8	res0a8[0xb0 - 0xa8];
 	__be32	rstcr;		/* 0x.00b0 - Reset Control Register */
 	u8	res0b4[0xc0 - 0xb4];
-#ifdef CONFIG_PPC_85xx
-	__be32  iovselsr;	/* 0x.00c0 - I/O voltage select status register */
-#else
-	__be32	elbcvselcr;	/* 0x.00c0 - eLBC Voltage Select Ctrl Reg */
-#endif
+	__be32  iovselsr;	/* 0x.00c0 - I/O voltage select status register
+					     Called 'elbcvselcr' on 86xx SOCs */
 	u8	res0c4[0x224 - 0xc4];
 	__be32  iodelay1;	/* 0x.0224 - IO delay control register 1 */
 	__be32  iodelay2;	/* 0x.0228 - IO delay control register 2 */
@@ -136,7 +120,7 @@ struct ccsr_guts_86xx {
  * ch: The channel on the DMA controller (0, 1, 2, or 3)
  * device: The device to set as the source (CCSR_GUTS_DMACR_DEV_xx)
  */
-static inline void guts_set_dmacr(struct ccsr_guts_86xx __iomem *guts,
+static inline void guts_set_dmacr(struct ccsr_guts __iomem *guts,
 	unsigned int co, unsigned int ch, unsigned int device)
 {
 	unsigned int shift = 16 + (8 * (1 - co) + 2 * (3 - ch));
@@ -172,7 +156,7 @@ static inline void guts_set_dmacr(struct ccsr_guts_86xx __iomem *guts,
  * ch: The channel on the DMA controller (0, 1, 2, or 3)
  * value: the new value for the bit (0 or 1)
  */
-static inline void guts_set_pmuxcr_dma(struct ccsr_guts_86xx __iomem *guts,
+static inline void guts_set_pmuxcr_dma(struct ccsr_guts __iomem *guts,
 	unsigned int co, unsigned int ch, unsigned int value)
 {
 	if ((ch == 0) || (ch == 3)) {
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 80fd4d2b4a62..be04330af751 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -35,7 +35,7 @@ struct arch_hw_breakpoint {
 
 #include <linux/kdebug.h>
 #include <asm/reg.h>
-#include <asm/system.h>
+#include <asm/debug.h>
 
 struct perf_event;
 struct pmu;
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index edfc9803ec91..957a83f43646 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -112,7 +112,6 @@ extern void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
 			     struct dma_attrs *attrs);
 
 extern void iommu_init_early_pSeries(void);
-extern void iommu_init_early_iSeries(void);
 extern void iommu_init_early_dart(void);
 extern void iommu_init_early_pasemi(void);
 
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index fe0b09dceb7d..cf417e510736 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -27,12 +27,6 @@ extern atomic_t ppc_n_lost_interrupts;
 /* This number is used when no interrupt has been assigned */
 #define NO_IRQ			(0)
 
-/* This is a special irq number to return from get_irq() to tell that
- * no interrupt happened _and_ ignore it (don't count it as bad). Some
- * platforms like iSeries rely on that.
- */
-#define NO_IRQ_IGNORE		((unsigned int)-1)
-
 /* Total number of virq in the platform */
 #define NR_IRQS		CONFIG_NR_IRQS
 
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index f7727d91ac6b..b921c3f48928 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -265,12 +265,9 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
-#define KVM_REG_MASK		0x001f
-#define KVM_REG_EXT_MASK	0xffe0
-#define KVM_REG_GPR		0x0000
-#define KVM_REG_FPR		0x0020
-#define KVM_REG_QPR		0x0040
-#define KVM_REG_FQPR		0x0060
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
 
 #define KVM_INTERRUPT_SET	-1U
 #define KVM_INTERRUPT_UNSET	-2U
@@ -292,4 +289,41 @@ struct kvm_allocate_rma {
 	__u64 rma_size;
 };
 
+struct kvm_book3e_206_tlb_entry {
+	__u32 mas8;
+	__u32 mas1;
+	__u64 mas2;
+	__u64 mas7_3;
+};
+
+struct kvm_book3e_206_tlb_params {
+	/*
+	 * For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+	 *
+	 * - The number of ways of TLB0 must be a power of two between 2 and
+	 *   16.
+	 * - TLB1 must be fully associative.
+	 * - The size of TLB0 must be a multiple of the number of ways, and
+	 *   the number of sets must be a power of two.
+	 * - The size of TLB1 may not exceed 64 entries.
+	 * - TLB0 supports 4 KiB pages.
+	 * - The page sizes supported by TLB1 are as indicated by
+	 *   TLB1CFG (if MMUCFG[MAVN] = 0) or TLB1PS (if MMUCFG[MAVN] = 1)
+	 *   as returned by KVM_GET_SREGS.
+	 * - TLB2 and TLB3 are reserved, and their entries in tlb_sizes[]
+	 *   and tlb_ways[] must be zero.
+	 *
+	 * tlb_ways[n] = tlb_sizes[n] means the array is fully associative.
+	 *
+	 * KVM will adjust TLBnCFG based on the sizes configured here,
+	 * though arrays greater than 2048 entries will have TLBnCFG[NENTRY]
+	 * set to zero.
+	 */
+	__u32 tlb_sizes[4];
+	__u32 tlb_ways[4];
+	__u32 reserved[8];
+};
+
+#define KVM_REG_PPC_HIOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 69c7377d2071..aa795ccef294 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -90,6 +90,8 @@ struct kvmppc_vcpu_book3s {
 #endif
 	int context_id[SID_CONTEXTS];
 
+	bool hior_explicit;		/* HIOR is set by ioctl, not PVR */
+
 	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
 	struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
 	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
@@ -119,6 +121,11 @@ extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
 extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
 extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
+extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run,
+			struct kvm_vcpu *vcpu, unsigned long addr,
+			unsigned long status);
+extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr,
+			unsigned long slb_v, unsigned long valid);
 
 extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
 extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu);
@@ -138,6 +145,21 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
 extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
+extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
+			unsigned long *rmap, long pte_index, int realmode);
+extern void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
+			unsigned long pte_index);
+void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
+			unsigned long pte_index);
+extern void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long addr,
+			unsigned long *nb_ret);
+extern void kvmppc_unpin_guest_page(struct kvm *kvm, void *addr);
+extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+			long pte_index, unsigned long pteh, unsigned long ptel);
+extern long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+			long pte_index, unsigned long pteh, unsigned long ptel);
+extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
+			struct kvm_memory_slot *memslot);
 
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);
@@ -183,7 +205,9 @@ static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
 	if ( num < 14 ) {
-		to_svcpu(vcpu)->gpr[num] = val;
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		svcpu->gpr[num] = val;
+		svcpu_put(svcpu);
 		to_book3s(vcpu)->shadow_vcpu->gpr[num] = val;
 	} else
 		vcpu->arch.gpr[num] = val;
@@ -191,80 +215,120 @@ static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
-	if ( num < 14 )
-		return to_svcpu(vcpu)->gpr[num];
-	else
+	if ( num < 14 ) {
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		ulong r = svcpu->gpr[num];
+		svcpu_put(svcpu);
+		return r;
+	} else
 		return vcpu->arch.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
-	to_svcpu(vcpu)->cr = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->cr = val;
+	svcpu_put(svcpu);
 	to_book3s(vcpu)->shadow_vcpu->cr = val;
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->cr;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
+	r = svcpu->cr;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
 {
-	to_svcpu(vcpu)->xer = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->xer = val;
 	to_book3s(vcpu)->shadow_vcpu->xer = val;
+	svcpu_put(svcpu);
 }
 
 static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->xer;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
+	r = svcpu->xer;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
 {
-	to_svcpu(vcpu)->ctr = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->ctr = val;
+	svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->ctr;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong r;
+	r = svcpu->ctr;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
 {
-	to_svcpu(vcpu)->lr = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->lr = val;
+	svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->lr;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong r;
+	r = svcpu->lr;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
 {
-	to_svcpu(vcpu)->pc = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->pc = val;
+	svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->pc;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong r;
+	r = svcpu->pc;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 {
 	ulong pc = kvmppc_get_pc(vcpu);
-	struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
 
 	/* Load the instruction manually if it failed to do so in the
 	 * exit path */
 	if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
 		kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
 
-	return svcpu->last_inst;
+	r = svcpu->last_inst;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->fault_dar;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong r;
+	r = svcpu->fault_dar;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/include/asm/kvm_book3s_32.h b/arch/powerpc/include/asm/kvm_book3s_32.h
index de604db135f5..38040ff82063 100644
--- a/arch/powerpc/include/asm/kvm_book3s_32.h
+++ b/arch/powerpc/include/asm/kvm_book3s_32.h
@@ -20,11 +20,15 @@
 #ifndef __ASM_KVM_BOOK3S_32_H__
 #define __ASM_KVM_BOOK3S_32_H__
 
-static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
+static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
 	return to_book3s(vcpu)->shadow_vcpu;
 }
 
+static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
+{
+}
+
 #define PTE_SIZE	12
 #define VSID_ALL	0
 #define SR_INVALID	0x00000001	/* VSID 1 should always be unused */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index d0ac94f98f9e..b0c08b142770 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -21,14 +21,56 @@
 #define __ASM_KVM_BOOK3S_64_H__
 
 #ifdef CONFIG_KVM_BOOK3S_PR
-static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
+static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
+	preempt_disable();
 	return &get_paca()->shadow_vcpu;
 }
+
+static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
+{
+	preempt_enable();
+}
 #endif
 
 #define SPAPR_TCE_SHIFT		12
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+/* For now use fixed-size 16MB page table */
+#define HPT_ORDER	24
+#define HPT_NPTEG	(1ul << (HPT_ORDER - 7))	/* 128B per pteg */
+#define HPT_NPTE	(HPT_NPTEG << 3)		/* 8 PTEs per PTEG */
+#define HPT_HASH_MASK	(HPT_NPTEG - 1)
+#endif
+
+#define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
+
+/*
+ * We use a lock bit in HPTE dword 0 to synchronize updates and
+ * accesses to each HPTE, and another bit to indicate non-present
+ * HPTEs.
+ */
+#define HPTE_V_HVLOCK	0x40UL
+#define HPTE_V_ABSENT	0x20UL
+
+static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits)
+{
+	unsigned long tmp, old;
+
+	asm volatile("	ldarx	%0,0,%2\n"
+		     "	and.	%1,%0,%3\n"
+		     "	bne	2f\n"
+		     "	ori	%0,%0,%4\n"
+		     "  stdcx.	%0,0,%2\n"
+		     "	beq+	2f\n"
+		     "	li	%1,%3\n"
+		     "2:	isync"
+		     : "=&r" (tmp), "=&r" (old)
+		     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
+		     : "cc", "memory");
+	return old == 0;
+}
+
 static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 					     unsigned long pte_index)
 {
@@ -62,4 +104,140 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	return rb;
 }
 
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+	/* only handle 4k, 64k and 16M pages for now */
+	if (!(h & HPTE_V_LARGE))
+		return 1ul << 12;		/* 4k page */
+	if ((l & 0xf000) == 0x1000 && cpu_has_feature(CPU_FTR_ARCH_206))
+		return 1ul << 16;		/* 64k page */
+	if ((l & 0xff000) == 0)
+		return 1ul << 24;		/* 16M page */
+	return 0;				/* error */
+}
+
+static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)
+{
+	return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
+}
+
+static inline int hpte_is_writable(unsigned long ptel)
+{
+	unsigned long pp = ptel & (HPTE_R_PP0 | HPTE_R_PP);
+
+	return pp != PP_RXRX && pp != PP_RXXX;
+}
+
+static inline unsigned long hpte_make_readonly(unsigned long ptel)
+{
+	if ((ptel & HPTE_R_PP0) || (ptel & HPTE_R_PP) == PP_RWXX)
+		ptel = (ptel & ~HPTE_R_PP) | PP_RXXX;
+	else
+		ptel |= PP_RXRX;
+	return ptel;
+}
+
+static inline int hpte_cache_flags_ok(unsigned long ptel, unsigned long io_type)
+{
+	unsigned int wimg = ptel & HPTE_R_WIMG;
+
+	/* Handle SAO */
+	if (wimg == (HPTE_R_W | HPTE_R_I | HPTE_R_M) &&
+	    cpu_has_feature(CPU_FTR_ARCH_206))
+		wimg = HPTE_R_M;
+
+	if (!io_type)
+		return wimg == HPTE_R_M;
+
+	return (wimg & (HPTE_R_W | HPTE_R_I)) == io_type;
+}
+
+/*
+ * Lock and read a linux PTE.  If it's present and writable, atomically
+ * set dirty and referenced bits and return the PTE, otherwise return 0.
+ */
+static inline pte_t kvmppc_read_update_linux_pte(pte_t *p, int writing)
+{
+	pte_t pte, tmp;
+
+	/* wait until _PAGE_BUSY is clear then set it atomically */
+	__asm__ __volatile__ (
+		"1:	ldarx	%0,0,%3\n"
+		"	andi.	%1,%0,%4\n"
+		"	bne-	1b\n"
+		"	ori	%1,%0,%4\n"
+		"	stdcx.	%1,0,%3\n"
+		"	bne-	1b"
+		: "=&r" (pte), "=&r" (tmp), "=m" (*p)
+		: "r" (p), "i" (_PAGE_BUSY)
+		: "cc");
+
+	if (pte_present(pte)) {
+		pte = pte_mkyoung(pte);
+		if (writing && pte_write(pte))
+			pte = pte_mkdirty(pte);
+	}
+
+	*p = pte;	/* clears _PAGE_BUSY */
+
+	return pte;
+}
+
+/* Return HPTE cache control bits corresponding to Linux pte bits */
+static inline unsigned long hpte_cache_bits(unsigned long pte_val)
+{
+#if _PAGE_NO_CACHE == HPTE_R_I && _PAGE_WRITETHRU == HPTE_R_W
+	return pte_val & (HPTE_R_W | HPTE_R_I);
+#else
+	return ((pte_val & _PAGE_NO_CACHE) ? HPTE_R_I : 0) +
+		((pte_val & _PAGE_WRITETHRU) ? HPTE_R_W : 0);
+#endif
+}
+
+static inline bool hpte_read_permission(unsigned long pp, unsigned long key)
+{
+	if (key)
+		return PP_RWRX <= pp && pp <= PP_RXRX;
+	return 1;
+}
+
+static inline bool hpte_write_permission(unsigned long pp, unsigned long key)
+{
+	if (key)
+		return pp == PP_RWRW;
+	return pp <= PP_RWRW;
+}
+
+static inline int hpte_get_skey_perm(unsigned long hpte_r, unsigned long amr)
+{
+	unsigned long skey;
+
+	skey = ((hpte_r & HPTE_R_KEY_HI) >> 57) |
+		((hpte_r & HPTE_R_KEY_LO) >> 9);
+	return (amr >> (62 - 2 * skey)) & 3;
+}
+
+static inline void lock_rmap(unsigned long *rmap)
+{
+	do {
+		while (test_bit(KVMPPC_RMAP_LOCK_BIT, rmap))
+			cpu_relax();
+	} while (test_and_set_bit_lock(KVMPPC_RMAP_LOCK_BIT, rmap));
+}
+
+static inline void unlock_rmap(unsigned long *rmap)
+{
+	__clear_bit_unlock(KVMPPC_RMAP_LOCK_BIT, rmap);
+}
+
+static inline bool slot_is_aligned(struct kvm_memory_slot *memslot,
+				   unsigned long pagesize)
+{
+	unsigned long mask = (pagesize >> PAGE_SHIFT) - 1;
+
+	if (pagesize <= PAGE_SIZE)
+		return 1;
+	return !(memslot->base_gfn & mask) && !(memslot->npages & mask);
+}
+
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h
index adbfca9dd100..8cd50a514271 100644
--- a/arch/powerpc/include/asm/kvm_e500.h
+++ b/arch/powerpc/include/asm/kvm_e500.h
@@ -22,46 +22,55 @@
 #define E500_PID_NUM   3
 #define E500_TLB_NUM   2
 
-struct tlbe{
-	u32 mas1;
-	u32 mas2;
-	u32 mas3;
-	u32 mas7;
-};
-
 #define E500_TLB_VALID 1
 #define E500_TLB_DIRTY 2
 
-struct tlbe_priv {
+struct tlbe_ref {
 	pfn_t pfn;
 	unsigned int flags; /* E500_TLB_* */
 };
 
+struct tlbe_priv {
+	struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
+};
+
 struct vcpu_id_table;
 
+struct kvmppc_e500_tlb_params {
+	int entries, ways, sets;
+};
+
 struct kvmppc_vcpu_e500 {
-	/* Unmodified copy of the guest's TLB. */
-	struct tlbe *gtlb_arch[E500_TLB_NUM];
+	/* Unmodified copy of the guest's TLB -- shared with host userspace. */
+	struct kvm_book3e_206_tlb_entry *gtlb_arch;
+
+	/* Starting entry number in gtlb_arch[] */
+	int gtlb_offset[E500_TLB_NUM];
 
 	/* KVM internal information associated with each guest TLB entry */
 	struct tlbe_priv *gtlb_priv[E500_TLB_NUM];
 
-	unsigned int gtlb_size[E500_TLB_NUM];
+	struct kvmppc_e500_tlb_params gtlb_params[E500_TLB_NUM];
+
 	unsigned int gtlb_nv[E500_TLB_NUM];
 
+	/*
+	 * information associated with each host TLB entry --
+	 * TLB1 only for now.  If/when guest TLB1 entries can be
+	 * mapped with host TLB0, this will be used for that too.
+	 *
+	 * We don't want to use this for guest TLB0 because then we'd
+	 * have the overhead of doing the translation again even if
+	 * the entry is still in the guest TLB (e.g. we swapped out
+	 * and back, and our host TLB entries got evicted).
+	 */
+	struct tlbe_ref *tlb_refs[E500_TLB_NUM];
+	unsigned int host_tlb1_nv;
+
 	u32 host_pid[E500_PID_NUM];
 	u32 pid[E500_PID_NUM];
 	u32 svr;
 
-	u32 mas0;
-	u32 mas1;
-	u32 mas2;
-	u32 mas3;
-	u32 mas4;
-	u32 mas5;
-	u32 mas6;
-	u32 mas7;
-
 	/* vcpu id table */
 	struct vcpu_id_table *idt;
 
@@ -73,6 +82,9 @@ struct kvmppc_vcpu_e500 {
 	u32 tlb1cfg;
 	u64 mcar;
 
+	struct page **shared_tlb_pages;
+	int num_shared_tlb_pages;
+
 	struct kvm_vcpu vcpu;
 };
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index bf8af5d5d5dc..52eb9c1f4fe0 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -32,17 +32,32 @@
 #include <linux/atomic.h>
 #include <asm/kvm_asm.h>
 #include <asm/processor.h>
+#include <asm/page.h>
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+#include <linux/mmu_notifier.h>
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+
+struct kvm;
+extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+extern int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
+extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
+
+#endif
+
 /* We don't currently support large pages. */
 #define KVM_HPAGE_GFN_SHIFT(x)	0
 #define KVM_NR_PAGE_SIZES	1
@@ -158,34 +173,72 @@ struct kvmppc_spapr_tce_table {
 	struct page *pages[0];
 };
 
-struct kvmppc_rma_info {
+struct kvmppc_linear_info {
 	void		*base_virt;
 	unsigned long	 base_pfn;
 	unsigned long	 npages;
 	struct list_head list;
-	atomic_t 	 use_count;
+	atomic_t	 use_count;
+	int		 type;
+};
+
+/*
+ * The reverse mapping array has one entry for each HPTE,
+ * which stores the guest's view of the second word of the HPTE
+ * (including the guest physical address of the mapping),
+ * plus forward and backward pointers in a doubly-linked ring
+ * of HPTEs that map the same host page.  The pointers in this
+ * ring are 32-bit HPTE indexes, to save space.
+ */
+struct revmap_entry {
+	unsigned long guest_rpte;
+	unsigned int forw, back;
+};
+
+/*
+ * We use the top bit of each memslot->rmap entry as a lock bit,
+ * and bit 32 as a present flag.  The bottom 32 bits are the
+ * index in the guest HPT of a HPTE that points to the page.
+ */
+#define KVMPPC_RMAP_LOCK_BIT	63
+#define KVMPPC_RMAP_RC_SHIFT	32
+#define KVMPPC_RMAP_REFERENCED	(HPTE_R_R << KVMPPC_RMAP_RC_SHIFT)
+#define KVMPPC_RMAP_CHANGED	(HPTE_R_C << KVMPPC_RMAP_RC_SHIFT)
+#define KVMPPC_RMAP_PRESENT	0x100000000ul
+#define KVMPPC_RMAP_INDEX	0xfffffffful
+
+/* Low-order bits in kvm->arch.slot_phys[][] */
+#define KVMPPC_PAGE_ORDER_MASK	0x1f
+#define KVMPPC_PAGE_NO_CACHE	HPTE_R_I	/* 0x20 */
+#define KVMPPC_PAGE_WRITETHRU	HPTE_R_W	/* 0x40 */
+#define KVMPPC_GOT_PAGE		0x80
+
+struct kvm_arch_memory_slot {
 };
 
 struct kvm_arch {
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	unsigned long hpt_virt;
-	unsigned long ram_npages;
-	unsigned long ram_psize;
-	unsigned long ram_porder;
-	struct kvmppc_pginfo *ram_pginfo;
+	struct revmap_entry *revmap;
 	unsigned int lpid;
 	unsigned int host_lpid;
 	unsigned long host_lpcr;
 	unsigned long sdr1;
 	unsigned long host_sdr1;
 	int tlbie_lock;
-	int n_rma_pages;
 	unsigned long lpcr;
 	unsigned long rmor;
-	struct kvmppc_rma_info *rma;
+	struct kvmppc_linear_info *rma;
+	unsigned long vrma_slb_v;
+	int rma_setup_done;
+	int using_mmu_notifiers;
 	struct list_head spapr_tce_tables;
+	spinlock_t slot_phys_lock;
+	unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
+	int slot_npages[KVM_MEM_SLOTS_NUM];
 	unsigned short last_vcpu[NR_CPUS];
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
+	struct kvmppc_linear_info *hpt_li;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
 
@@ -318,10 +371,6 @@ struct kvm_vcpu_arch {
 	u32 vrsave; /* also USPRG0 */
 	u32 mmucr;
 	ulong shadow_msr;
-	ulong sprg4;
-	ulong sprg5;
-	ulong sprg6;
-	ulong sprg7;
 	ulong csrr0;
 	ulong csrr1;
 	ulong dsrr0;
@@ -329,16 +378,14 @@ struct kvm_vcpu_arch {
 	ulong mcsrr0;
 	ulong mcsrr1;
 	ulong mcsr;
-	ulong esr;
 	u32 dec;
 	u32 decar;
 	u32 tbl;
 	u32 tbu;
 	u32 tcr;
-	u32 tsr;
+	ulong tsr; /* we need to perform set/clr_bits() which requires ulong */
 	u32 ivor[64];
 	ulong ivpr;
-	u32 pir;
 	u32 pvr;
 
 	u32 shadow_pid;
@@ -427,9 +474,14 @@ struct kvm_vcpu_arch {
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	struct kvm_vcpu_arch_shared shregs;
 
+	unsigned long pgfault_addr;
+	long pgfault_index;
+	unsigned long pgfault_hpte[2];
+
 	struct list_head run_list;
 	struct task_struct *run_task;
 	struct kvm_run *kvm_run;
+	pgd_t *pgdir;
 #endif
 };
 
@@ -438,4 +490,12 @@ struct kvm_vcpu_arch {
 #define KVMPPC_VCPU_BUSY_IN_HOST	1
 #define KVMPPC_VCPU_RUNNABLE		2
 
+/* Values for vcpu->arch.io_gpr */
+#define KVM_MMIO_REG_MASK	0x001f
+#define KVM_MMIO_REG_EXT_MASK	0xffe0
+#define KVM_MMIO_REG_GPR	0x0000
+#define KVM_MMIO_REG_FPR	0x0020
+#define KVM_MMIO_REG_QPR	0x0040
+#define KVM_MMIO_REG_FQPR	0x0060
+
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 50533f9adf40..7b754e743003 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -22,6 +22,16 @@
 
 #include <linux/types.h>
 
+/*
+ * Additions to this struct must only occur at the end, and should be
+ * accompanied by a KVM_MAGIC_FEAT flag to advertise that they are present
+ * (albeit not necessarily relevant to the current target hardware platform).
+ *
+ * Struct fields are always 32 or 64 bit aligned, depending on them being 32
+ * or 64 bit wide respectively.
+ *
+ * See Documentation/virtual/kvm/ppc-pv.txt
+ */
 struct kvm_vcpu_arch_shared {
 	__u64 scratch1;
 	__u64 scratch2;
@@ -33,11 +43,35 @@ struct kvm_vcpu_arch_shared {
 	__u64 sprg3;
 	__u64 srr0;
 	__u64 srr1;
-	__u64 dar;
+	__u64 dar;		/* dear on BookE */
 	__u64 msr;
 	__u32 dsisr;
 	__u32 int_pending;	/* Tells the guest if we have an interrupt */
 	__u32 sr[16];
+	__u32 mas0;
+	__u32 mas1;
+	__u64 mas7_3;
+	__u64 mas2;
+	__u32 mas4;
+	__u32 mas6;
+	__u32 esr;
+	__u32 pir;
+
+	/*
+	 * SPRG4-7 are user-readable, so we can only keep these consistent
+	 * between the shared area and the real registers when there's an
+	 * intervening exit to KVM.  This also applies to SPRG3 on some
+	 * chips.
+	 *
+	 * This suffices for access by guest userspace, since in PR-mode
+	 * KVM, an exit must occur when changing the guest's MSR[PR].
+	 * If the guest kernel writes to SPRG3-7 via the shared area, it
+	 * must also use the shared area for reading while in kernel space.
+	 */
+	__u64 sprg4;
+	__u64 sprg5;
+	__u64 sprg6;
+	__u64 sprg7;
 };
 
 #define KVM_SC_MAGIC_R0		0x4b564d21 /* "KVM!" */
@@ -47,7 +81,10 @@ struct kvm_vcpu_arch_shared {
 
 #define KVM_FEATURE_MAGIC_PAGE	1
 
-#define KVM_MAGIC_FEAT_SR	(1 << 0)
+#define KVM_MAGIC_FEAT_SR		(1 << 0)
+
+/* MASn, ESR, PIR, and high SPRGs */
+#define KVM_MAGIC_FEAT_MAS0_TO_SPRG7	(1 << 1)
 
 #ifdef __KERNEL__
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 46efd1a265c9..9d6dee0f7d48 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -66,6 +66,7 @@ extern int kvmppc_emulate_instruction(struct kvm_run *run,
 extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
 extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb);
+extern void kvmppc_decrementer_func(unsigned long data);
 extern int kvmppc_sanity_check(struct kvm_vcpu *vcpu);
 
 /* Core-specific hooks */
@@ -94,7 +95,7 @@ extern int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 extern void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 
-extern void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
 extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
@@ -120,15 +121,17 @@ extern long kvmppc_alloc_hpt(struct kvm *kvm);
 extern void kvmppc_free_hpt(struct kvm *kvm);
 extern long kvmppc_prepare_vrma(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
-extern void kvmppc_map_vrma(struct kvm *kvm,
-			    struct kvm_userspace_memory_region *mem);
+extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
+			struct kvm_memory_slot *memslot, unsigned long porder);
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce *args);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
-extern struct kvmppc_rma_info *kvm_alloc_rma(void);
-extern void kvm_release_rma(struct kvmppc_rma_info *ri);
+extern struct kvmppc_linear_info *kvm_alloc_rma(void);
+extern void kvm_release_rma(struct kvmppc_linear_info *ri);
+extern struct kvmppc_linear_info *kvm_alloc_hpt(void);
+extern void kvm_release_hpt(struct kvmppc_linear_info *li);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
@@ -175,6 +178,9 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
+
 void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
@@ -183,14 +189,19 @@ static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 	paca[cpu].kvm_hstate.xics_phys = addr;
 }
 
-extern void kvm_rma_init(void);
+extern void kvm_linear_init(void);
 
 #else
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {}
 
-static inline void kvm_rma_init(void)
+static inline void kvm_linear_init(void)
 {}
 #endif
 
+int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
+			      struct kvm_config_tlb *cfg);
+int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
+			     struct kvm_dirty_tlb *cfg);
+
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index bf37931d1ad6..42ce570812c1 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -99,9 +99,7 @@ struct machdep_calls {
 
 	void		(*init_IRQ)(void);
 
-	/* Return an irq, or NO_IRQ to indicate there are none pending.
-	 * If for some reason there is no irq, but the interrupt
-	 * shouldn't be counted as spurious, return NO_IRQ_IGNORE. */
+	/* Return an irq, or NO_IRQ to indicate there are none pending. */
 	unsigned int	(*get_irq)(void);
 
 	/* PCI stuff */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index f5f89cafebd0..cdb5421877e2 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -41,9 +41,10 @@
 /* MAS registers bit definitions */
 
 #define MAS0_TLBSEL(x)		(((x) << 28) & 0x30000000)
-#define MAS0_ESEL(x)		(((x) << 16) & 0x0FFF0000)
-#define MAS0_NV(x)		((x) & 0x00000FFF)
 #define MAS0_ESEL_MASK		0x0FFF0000
+#define MAS0_ESEL_SHIFT		16
+#define MAS0_ESEL(x)		(((x) << MAS0_ESEL_SHIFT) & MAS0_ESEL_MASK)
+#define MAS0_NV(x)		((x) & 0x00000FFF)
 #define MAS0_HES		0x00004000
 #define MAS0_WQ_ALLWAYS		0x00000000
 #define MAS0_WQ_COND		0x00001000
@@ -167,6 +168,7 @@
 #define TLBnCFG_MAXSIZE		0x000f0000	/* Maximum Page Size (v1.0) */
 #define TLBnCFG_MAXSIZE_SHIFT	16
 #define TLBnCFG_ASSOC		0xff000000	/* Associativity */
+#define TLBnCFG_ASSOC_SHIFT	24
 
 /* TLBnPS encoding */
 #define TLBnPS_4K		0x00000004
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 412ba493cb98..1c65a59881ea 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -108,11 +108,11 @@ extern char initial_stab[];
 #define HPTE_V_VRMA_MASK	ASM_CONST(0x4001ffffff000000)
 
 /* Values for PP (assumes Ks=0, Kp=1) */
-/* pp0 will always be 0 for linux     */
 #define PP_RWXX	0	/* Supervisor read/write, User none */
 #define PP_RWRX 1	/* Supervisor read/write, User read */
 #define PP_RWRW 2	/* Supervisor read/write, User read/write */
 #define PP_RXRX 3	/* Supervisor read,       User read */
+#define PP_RXXX	(HPTE_R_PP0 | 2)	/* Supervisor read, user none */
 
 #ifndef __ASSEMBLY__
 
@@ -267,7 +267,6 @@ extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
 extern void hpte_init_native(void);
 extern void hpte_init_lpar(void);
-extern void hpte_init_iSeries(void);
 extern void hpte_init_beat(void);
 extern void hpte_init_beat_v3(void);
 
@@ -325,9 +324,6 @@ extern void slb_set_size(u16 size);
  * WARNING - If you change these you must make sure the asm
  * implementations in slb_allocate (slb_low.S), do_stab_bolted
  * (head.S) and ASM_VSID_SCRAMBLE (below) are changed accordingly.
- *
- * You'll also need to change the precomputed VSID values in head.S
- * which are used by the iSeries firmware.
  */
 
 #define VSID_MULTIPLIER_256M	ASM_CONST(200730139)	/* 28-bit prime */
@@ -484,14 +480,6 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
 			     | (ea >> SID_SHIFT_1T), 1T);
 }
 
-/*
- * This is only used on legacy iSeries in lparmap.c,
- * hence the 256MB segment assumption.
- */
-#define VSID_SCRAMBLE(pvsid)	(((pvsid) * VSID_MULTIPLIER_256M) %	\
-				 VSID_MODULUS_256M)
-#define KERNEL_VSID(ea)		VSID_SCRAMBLE(GET_ESID(ea))
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_MMU_HASH64_H_ */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 5d487657322e..ac39e6a3b25a 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -155,14 +155,7 @@ struct pci_dn {
 
 	struct	pci_dev *pcidev;	/* back-pointer to the pci device */
 #ifdef CONFIG_EEH
-	int	class_code;		/* pci device class */
-	int	eeh_mode;		/* See eeh.h for possible EEH_MODEs */
-	int	eeh_config_addr;
-	int	eeh_pe_config_addr; /* new-style partition endpoint address */
-	int	eeh_check_count;	/* # times driver ignored error */
-	int	eeh_freeze_count;	/* # times this device froze up. */
-	int	eeh_false_positives;	/* # times this device reported #ff's */
-	u32	config_space[16];	/* saved PCI config space */
+	struct eeh_dev *edev;		/* eeh device */
 #endif
 #define IODA_INVALID_PE		(-1)
 #ifdef CONFIG_PPC_POWERNV
@@ -185,6 +178,13 @@ static inline int pci_device_from_OF_node(struct device_node *np,
 	return 0;
 }
 
+#if defined(CONFIG_EEH)
+static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn)
+{
+	return PCI_DN(dn)->edev;
+}
+#endif
+
 /** Find the bus corresponding to the indicated device node */
 extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn);
 
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 1a8093fa8f71..078019b5b353 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -47,6 +47,8 @@ struct power_pmu {
  */
 #define PPMU_LIMITED_PMC5_6	1	/* PMC5/6 have limited function */
 #define PPMU_ALT_SIPR		2	/* uses alternate posn for SIPR/HV */
+#define PPMU_NO_SIPR		4	/* no SIPR/HV in MMCRA at all */
+#define PPMU_NO_CONT_SAMPLING	8	/* no continuous sampling */
 
 /*
  * Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/posix_types.h b/arch/powerpc/include/asm/posix_types.h
index c4e396b540df..f1393252bbda 100644
--- a/arch/powerpc/include/asm/posix_types.h
+++ b/arch/powerpc/include/asm/posix_types.h
@@ -7,122 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef long		__kernel_suseconds_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-typedef unsigned int	__kernel_old_uid_t;
-typedef unsigned int	__kernel_old_gid_t;
-
 #ifdef __powerpc64__
-typedef unsigned long  	__kernel_nlink_t;
-typedef int             __kernel_ipc_pid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
 typedef unsigned long	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 #else
-typedef unsigned short	__kernel_nlink_t;
-typedef short		__kernel_ipc_pid_t;
 typedef unsigned int	__kernel_size_t;
 typedef int		__kernel_ssize_t;
-typedef unsigned int	__kernel_old_dev_t;
-#endif
-
-#ifdef __powerpc64__
-typedef long long	__kernel_loff_t;
-#else
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifndef __GNUC__
-
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-#define	__FD_ISSET(d, set)	(((set)->fds_bits[__FDELT(d)] & __FDMASK(d)) != 0)
-#define	__FD_ZERO(set)	\
-  ((void) memset ((void *) (set), 0, sizeof (__kernel_fd_set)))
-
-#else /* __GNUC__ */
-
-#if defined(__KERNEL__)
-/* With GNU C, use inline functions instead so args are evaluated only once: */
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long fd, __kernel_fd_set *p)
-{ 
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = (unsigned long *)p->fds_bits;
-	int i;
+typedef long		__kernel_ptrdiff_t;
+#define __kernel_size_t __kernel_size_t
 
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		      case 16:
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
+typedef unsigned short	__kernel_nlink_t;
+#define __kernel_nlink_t __kernel_nlink_t
 
-		      case 8:
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
+typedef short		__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+#endif
 
-		      case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
+#include <asm-generic/posix_types.h>
 
-#endif /* defined(__KERNEL__) */
-#endif /* __GNUC__ */
 #endif /* _ASM_POWERPC_POSIX_TYPES_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index e980faae4225..d81f99430fe7 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -45,6 +45,7 @@
 #define PPC_INST_MFSPR_DSCR_MASK	0xfc1fffff
 #define PPC_INST_MTSPR_DSCR		0x7c1103a6
 #define PPC_INST_MTSPR_DSCR_MASK	0xfc1fffff
+#define PPC_INST_SLBFEE			0x7c0007a7
 
 #define PPC_INST_STRING			0x7c00042a
 #define PPC_INST_STRING_MASK		0xfc0007fe
@@ -183,7 +184,8 @@
 					__PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
 #define PPC_ERATSX_DOT(t, a, w)	stringify_in_c(.long PPC_INST_ERATSX_DOT | \
 					__PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
-
+#define PPC_SLBFEE_DOT(t, b)	stringify_in_c(.long PPC_INST_SLBFEE | \
+					__PPC_RT(t) | __PPC_RB(b))
 
 /*
  * Define what the VSX XX1 form instructions will look like, then add
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index b585bff1a022..8e2d0371fe1e 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -385,6 +385,36 @@ static inline unsigned long get_clean_sp(struct pt_regs *regs, int is_32)
 extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
+extern int powersave_nap;	/* set if nap mode can be used in idle loop */
+void cpu_idle_wait(void);
+
+#ifdef CONFIG_PSERIES_IDLE
+extern void update_smt_snooze_delay(int snooze);
+extern int pseries_notify_cpuidle_add_cpu(int cpu);
+#else
+static inline void update_smt_snooze_delay(int snooze) {}
+static inline int pseries_notify_cpuidle_add_cpu(int cpu) { return 0; }
+#endif
+
+extern void flush_instruction_cache(void);
+extern void hard_reset_now(void);
+extern void poweroff_now(void);
+extern int fix_alignment(struct pt_regs *);
+extern void cvt_fd(float *from, double *to);
+extern void cvt_df(double *from, float *to);
+extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val);
+
+#ifdef CONFIG_PPC64
+/*
+ * We handle most unaligned accesses in hardware. On the other hand 
+ * unaligned DMA can be very expensive on some ppc64 IO chips (it does
+ * powers of 2 writes until it reaches sufficient alignment).
+ *
+ * Based on this we disable the IP header alignment in network drivers.
+ */
+#define NET_IP_ALIGN	0
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_PROCESSOR_H */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index b1a215eabef6..9d7f0fb69028 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -216,6 +216,7 @@
 #define   DSISR_ISSTORE		0x02000000	/* access was a store */
 #define   DSISR_DABRMATCH	0x00400000	/* hit data breakpoint */
 #define   DSISR_NOSEGMENT	0x00200000	/* STAB/SLB miss */
+#define   DSISR_KEYFAULT	0x00200000	/* Key fault */
 #define SPRN_TBRL	0x10C	/* Time Base Read Lower Register (user, R/O) */
 #define SPRN_TBRU	0x10D	/* Time Base Read Upper Register (user, R/O) */
 #define SPRN_TBWL	0x11C	/* Time Base Lower Register (super, R/W) */
@@ -237,6 +238,7 @@
 #define   LPCR_ISL	(1ul << (63-2))
 #define   LPCR_VC_SH	(63-2)
 #define   LPCR_DPFD_SH	(63-11)
+#define   LPCR_VRMASD	(0x1ful << (63-16))
 #define   LPCR_VRMA_L	(1ul << (63-12))
 #define   LPCR_VRMA_LP0	(1ul << (63-15))
 #define   LPCR_VRMA_LP1	(1ul << (63-16))
@@ -493,6 +495,9 @@
 #define SPRN_SPRG7	0x117	/* Special Purpose Register General 7 */
 #define SPRN_SRR0	0x01A	/* Save/Restore Register 0 */
 #define SPRN_SRR1	0x01B	/* Save/Restore Register 1 */
+#define   SRR1_ISI_NOPT		0x40000000 /* ISI: Not found in hash */
+#define   SRR1_ISI_N_OR_G	0x10000000 /* ISI: Access is no-exec or G */
+#define   SRR1_ISI_PROT		0x08000000 /* ISI: Other protection fault */
 #define   SRR1_WAKEMASK		0x00380000 /* reason for wakeup */
 #define   SRR1_WAKESYSERR	0x00300000 /* System error */
 #define   SRR1_WAKEEE		0x00200000 /* External interrupt */
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 8a97aa7289d3..b86faa9107da 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -15,6 +15,11 @@
 #ifndef __ASM_POWERPC_REG_BOOKE_H__
 #define __ASM_POWERPC_REG_BOOKE_H__
 
+#ifdef CONFIG_BOOKE_WDT
+extern u32 booke_wdt_enabled;
+extern u32 booke_wdt_period;
+#endif /* CONFIG_BOOKE_WDT */
+
 /* Machine State Register (MSR) Fields */
 #define MSR_GS		(1<<28) /* Guest state */
 #define MSR_UCLE	(1<<26)	/* User-mode cache lock enable */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 01c143bb77ae..557cff845dee 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -74,7 +74,6 @@ struct rtas_suspend_me_data {
 /* RTAS event classes */
 #define RTAS_INTERNAL_ERROR		0x80000000 /* set bit 0 */
 #define RTAS_EPOW_WARNING		0x40000000 /* set bit 1 */
-#define RTAS_POWERMGM_EVENTS		0x20000000 /* set bit 2 */
 #define RTAS_HOTPLUG_EVENTS		0x10000000 /* set bit 3 */
 #define RTAS_IO_EVENTS			0x08000000 /* set bit 4 */
 #define RTAS_EVENT_SCAN_ALL_EVENTS	0xffffffff
@@ -204,6 +203,39 @@ struct rtas_ext_event_log_v6 {
 					/* Variable length.		*/
 };
 
+/* pSeries event log format */
+
+/* Two bytes ASCII section IDs */
+#define PSERIES_ELOG_SECT_ID_PRIV_HDR		(('P' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_USER_HDR		(('U' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_PRIMARY_SRC	(('P' << 8) | 'S')
+#define PSERIES_ELOG_SECT_ID_EXTENDED_UH	(('E' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_FAILING_MTMS	(('M' << 8) | 'T')
+#define PSERIES_ELOG_SECT_ID_SECONDARY_SRC	(('S' << 8) | 'S')
+#define PSERIES_ELOG_SECT_ID_DUMP_LOCATOR	(('D' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_FW_ERROR		(('S' << 8) | 'W')
+#define PSERIES_ELOG_SECT_ID_IMPACT_PART_ID	(('L' << 8) | 'P')
+#define PSERIES_ELOG_SECT_ID_LOGIC_RESOURCE_ID	(('L' << 8) | 'R')
+#define PSERIES_ELOG_SECT_ID_HMC_ID		(('H' << 8) | 'M')
+#define PSERIES_ELOG_SECT_ID_EPOW		(('E' << 8) | 'P')
+#define PSERIES_ELOG_SECT_ID_IO_EVENT		(('I' << 8) | 'E')
+#define PSERIES_ELOG_SECT_ID_MANUFACT_INFO	(('M' << 8) | 'I')
+#define PSERIES_ELOG_SECT_ID_CALL_HOME		(('C' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_USER_DEF		(('U' << 8) | 'D')
+
+/* Vendor specific Platform Event Log Format, Version 6, section header */
+struct pseries_errorlog {
+	uint16_t id;			/* 0x00 2-byte ASCII section ID	*/
+	uint16_t length;		/* 0x02 Section length in bytes	*/
+	uint8_t version;		/* 0x04 Section version		*/
+	uint8_t subtype;		/* 0x05 Section subtype		*/
+	uint16_t creator_component;	/* 0x06 Creator component ID	*/
+	uint8_t data[];			/* 0x08 Start of section data	*/
+};
+
+struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
+					      uint16_t section_id);
+
 /*
  * This can be set by the rtas_flash module so that it can get called
  * as the absolutely last thing before the kernel terminates.
@@ -325,5 +357,7 @@ static inline int page_is_rtas_user_buf(unsigned long pfn)
 static inline int page_is_rtas_user_buf(unsigned long pfn) { return 0;}
 #endif
 
+extern int call_rtas(const char *, int, int, unsigned long *, ...);
+
 #endif /* __KERNEL__ */
 #endif /* _POWERPC_RTAS_H */
diff --git a/arch/powerpc/include/asm/runlatch.h b/arch/powerpc/include/asm/runlatch.h
new file mode 100644
index 000000000000..54e9b963876e
--- /dev/null
+++ b/arch/powerpc/include/asm/runlatch.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_RUNLATCH_H
+#define _ASM_POWERPC_RUNLATCH_H
+
+#ifdef CONFIG_PPC64
+
+extern void __ppc64_runlatch_on(void);
+extern void __ppc64_runlatch_off(void);
+
+/*
+ * We manually hard enable-disable, this is called
+ * in the idle loop and we don't want to mess up
+ * with soft-disable/enable & interrupt replay.
+ */
+#define ppc64_runlatch_off()					\
+	do {							\
+		if (cpu_has_feature(CPU_FTR_CTRL) &&		\
+		    test_thread_local_flags(_TLF_RUNLATCH)) {	\
+			unsigned long msr = mfmsr();		\
+			__hard_irq_disable();			\
+			__ppc64_runlatch_off();			\
+			if (msr & MSR_EE)			\
+				__hard_irq_enable();		\
+		}      						\
+	} while (0)
+
+#define ppc64_runlatch_on()					\
+	do {							\
+		if (cpu_has_feature(CPU_FTR_CTRL) &&		\
+		    !test_thread_local_flags(_TLF_RUNLATCH)) {	\
+			unsigned long msr = mfmsr();		\
+			__hard_irq_disable();			\
+			__ppc64_runlatch_on();			\
+			if (msr & MSR_EE)			\
+				__hard_irq_enable();		\
+		}      						\
+	} while (0)
+#else
+#define ppc64_runlatch_on()
+#define ppc64_runlatch_off()
+#endif /* CONFIG_PPC64 */
+
+#endif /* _ASM_POWERPC_RUNLATCH_H */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 186e0fb835bd..d084ce195fc3 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -5,6 +5,28 @@
 
 #ifndef __ASSEMBLY__
 extern void ppc_printk_progress(char *s, unsigned short hex);
-#endif
+
+extern unsigned int rtas_data;
+extern int mem_init_done;	/* set on boot once kmalloc can be called */
+extern int init_bootmem_done;	/* set once bootmem is available */
+extern phys_addr_t memory_limit;
+extern unsigned long klimit;
+extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
+
+extern void via_cuda_init(void);
+extern void read_rtc_time(void);
+extern void pmac_find_display(void);
+
+struct device_node;
+extern void note_scsi_host(struct device_node *, void *);
+
+/* Used in very early kernel initialization. */
+extern unsigned long reloc_offset(void);
+extern unsigned long add_reloc_offset(unsigned long);
+extern void reloc_got2(unsigned long);
+
+#define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
+
+#endif /* !__ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index adba970ce918..ebc24dc5b1a1 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -122,7 +122,6 @@ extern void smp_muxed_ipi_set_data(int cpu, unsigned long data);
 extern void smp_muxed_ipi_message_pass(int cpu, int msg);
 extern irqreturn_t smp_ipi_demux(void);
 
-void smp_init_iSeries(void);
 void smp_init_pSeries(void);
 void smp_init_cell(void);
 void smp_init_celleb(void);
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
new file mode 100644
index 000000000000..caf82d0a00de
--- /dev/null
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -0,0 +1,65 @@
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_SWITCH_TO_H
+#define _ASM_POWERPC_SWITCH_TO_H
+
+struct thread_struct;
+struct task_struct;
+struct pt_regs;
+
+extern struct task_struct *__switch_to(struct task_struct *,
+	struct task_struct *);
+#define switch_to(prev, next, last)	((last) = __switch_to((prev), (next)))
+
+struct thread_struct;
+extern struct task_struct *_switch(struct thread_struct *prev,
+				   struct thread_struct *next);
+
+extern void giveup_fpu(struct task_struct *);
+extern void disable_kernel_fp(void);
+extern void enable_kernel_fp(void);
+extern void flush_fp_to_thread(struct task_struct *);
+extern void enable_kernel_altivec(void);
+extern void giveup_altivec(struct task_struct *);
+extern void load_up_altivec(struct task_struct *);
+extern int emulate_altivec(struct pt_regs *);
+extern void __giveup_vsx(struct task_struct *);
+extern void giveup_vsx(struct task_struct *);
+extern void enable_kernel_spe(void);
+extern void giveup_spe(struct task_struct *);
+extern void load_up_spe(struct task_struct *);
+
+#ifndef CONFIG_SMP
+extern void discard_lazy_cpu_state(void);
+#else
+static inline void discard_lazy_cpu_state(void)
+{
+}
+#endif
+
+#ifdef CONFIG_ALTIVEC
+extern void flush_altivec_to_thread(struct task_struct *);
+#else
+static inline void flush_altivec_to_thread(struct task_struct *t)
+{
+}
+#endif
+
+#ifdef CONFIG_VSX
+extern void flush_vsx_to_thread(struct task_struct *);
+#else
+static inline void flush_vsx_to_thread(struct task_struct *t)
+{
+}
+#endif
+
+#ifdef CONFIG_SPE
+extern void flush_spe_to_thread(struct task_struct *);
+#else
+static inline void flush_spe_to_thread(struct task_struct *t)
+{
+}
+#endif
+
+#endif /* _ASM_POWERPC_SWITCH_TO_H */
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
deleted file mode 100644
index a02883d5af43..000000000000
--- a/arch/powerpc/include/asm/system.h
+++ /dev/null
@@ -1,592 +0,0 @@
-/*
- * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
- */
-#ifndef _ASM_POWERPC_SYSTEM_H
-#define _ASM_POWERPC_SYSTEM_H
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-#include <asm/hw_irq.h>
-
-/*
- * Memory barrier.
- * The sync instruction guarantees that all memory accesses initiated
- * by this processor have been performed (with respect to all other
- * mechanisms that access memory).  The eieio instruction is a barrier
- * providing an ordering (separately) for (a) cacheable stores and (b)
- * loads and stores to non-cacheable memory (e.g. I/O devices).
- *
- * mb() prevents loads and stores being reordered across this point.
- * rmb() prevents loads being reordered across this point.
- * wmb() prevents stores being reordered across this point.
- * read_barrier_depends() prevents data-dependent loads being reordered
- *	across this point (nop on PPC).
- *
- * *mb() variants without smp_ prefix must order all types of memory
- * operations with one another. sync is the only instruction sufficient
- * to do this.
- *
- * For the smp_ barriers, ordering is for cacheable memory operations
- * only. We have to use the sync instruction for smp_mb(), since lwsync
- * doesn't order loads with respect to previous stores.  Lwsync can be
- * used for smp_rmb() and smp_wmb().
- *
- * However, on CPUs that don't support lwsync, lwsync actually maps to a
- * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio.
- */
-#define mb()   __asm__ __volatile__ ("sync" : : : "memory")
-#define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
-#define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
-#define read_barrier_depends()  do { } while(0)
-
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
-
-#ifdef __KERNEL__
-#define AT_VECTOR_SIZE_ARCH 6 /* entries in ARCH_DLINFO */
-#ifdef CONFIG_SMP
-
-#ifdef __SUBARCH_HAS_LWSYNC
-#    define SMPWMB      LWSYNC
-#else
-#    define SMPWMB      eieio
-#endif
-
-#define smp_mb()	mb()
-#define smp_rmb()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
-#define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
-#endif /* CONFIG_SMP */
-
-/*
- * This is a barrier which prevents following instructions from being
- * started until the value of the argument x is known.  For example, if
- * x is a variable loaded from memory, this prevents following
- * instructions from being executed until the load has been performed.
- */
-#define data_barrier(x)	\
-	asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
-
-struct task_struct;
-struct pt_regs;
-
-#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
-
-extern int (*__debugger)(struct pt_regs *regs);
-extern int (*__debugger_ipi)(struct pt_regs *regs);
-extern int (*__debugger_bpt)(struct pt_regs *regs);
-extern int (*__debugger_sstep)(struct pt_regs *regs);
-extern int (*__debugger_iabr_match)(struct pt_regs *regs);
-extern int (*__debugger_dabr_match)(struct pt_regs *regs);
-extern int (*__debugger_fault_handler)(struct pt_regs *regs);
-
-#define DEBUGGER_BOILERPLATE(__NAME) \
-static inline int __NAME(struct pt_regs *regs) \
-{ \
-	if (unlikely(__ ## __NAME)) \
-		return __ ## __NAME(regs); \
-	return 0; \
-}
-
-DEBUGGER_BOILERPLATE(debugger)
-DEBUGGER_BOILERPLATE(debugger_ipi)
-DEBUGGER_BOILERPLATE(debugger_bpt)
-DEBUGGER_BOILERPLATE(debugger_sstep)
-DEBUGGER_BOILERPLATE(debugger_iabr_match)
-DEBUGGER_BOILERPLATE(debugger_dabr_match)
-DEBUGGER_BOILERPLATE(debugger_fault_handler)
-
-#else
-static inline int debugger(struct pt_regs *regs) { return 0; }
-static inline int debugger_ipi(struct pt_regs *regs) { return 0; }
-static inline int debugger_bpt(struct pt_regs *regs) { return 0; }
-static inline int debugger_sstep(struct pt_regs *regs) { return 0; }
-static inline int debugger_iabr_match(struct pt_regs *regs) { return 0; }
-static inline int debugger_dabr_match(struct pt_regs *regs) { return 0; }
-static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; }
-#endif
-
-extern int set_dabr(unsigned long dabr);
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-extern void do_send_trap(struct pt_regs *regs, unsigned long address,
-			 unsigned long error_code, int signal_code, int brkpt);
-#else
-extern void do_dabr(struct pt_regs *regs, unsigned long address,
-		    unsigned long error_code);
-#endif
-extern void print_backtrace(unsigned long *);
-extern void flush_instruction_cache(void);
-extern void hard_reset_now(void);
-extern void poweroff_now(void);
-
-#ifdef CONFIG_6xx
-extern long _get_L2CR(void);
-extern long _get_L3CR(void);
-extern void _set_L2CR(unsigned long);
-extern void _set_L3CR(unsigned long);
-#else
-#define _get_L2CR()	0L
-#define _get_L3CR()	0L
-#define _set_L2CR(val)	do { } while(0)
-#define _set_L3CR(val)	do { } while(0)
-#endif
-
-extern void via_cuda_init(void);
-extern void read_rtc_time(void);
-extern void pmac_find_display(void);
-extern void giveup_fpu(struct task_struct *);
-extern void disable_kernel_fp(void);
-extern void enable_kernel_fp(void);
-extern void flush_fp_to_thread(struct task_struct *);
-extern void enable_kernel_altivec(void);
-extern void giveup_altivec(struct task_struct *);
-extern void load_up_altivec(struct task_struct *);
-extern int emulate_altivec(struct pt_regs *);
-extern void __giveup_vsx(struct task_struct *);
-extern void giveup_vsx(struct task_struct *);
-extern void enable_kernel_spe(void);
-extern void giveup_spe(struct task_struct *);
-extern void load_up_spe(struct task_struct *);
-extern int fix_alignment(struct pt_regs *);
-extern void cvt_fd(float *from, double *to);
-extern void cvt_df(double *from, float *to);
-
-#ifndef CONFIG_SMP
-extern void discard_lazy_cpu_state(void);
-#else
-static inline void discard_lazy_cpu_state(void)
-{
-}
-#endif
-
-#ifdef CONFIG_ALTIVEC
-extern void flush_altivec_to_thread(struct task_struct *);
-#else
-static inline void flush_altivec_to_thread(struct task_struct *t)
-{
-}
-#endif
-
-#ifdef CONFIG_VSX
-extern void flush_vsx_to_thread(struct task_struct *);
-#else
-static inline void flush_vsx_to_thread(struct task_struct *t)
-{
-}
-#endif
-
-#ifdef CONFIG_SPE
-extern void flush_spe_to_thread(struct task_struct *);
-#else
-static inline void flush_spe_to_thread(struct task_struct *t)
-{
-}
-#endif
-
-extern int call_rtas(const char *, int, int, unsigned long *, ...);
-extern void cacheable_memzero(void *p, unsigned int nb);
-extern void *cacheable_memcpy(void *, const void *, unsigned int);
-extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
-extern void bad_page_fault(struct pt_regs *, unsigned long, int);
-extern void _exception(int, struct pt_regs *, int, unsigned long);
-extern void die(const char *, struct pt_regs *, long);
-extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val);
-
-#ifdef CONFIG_BOOKE_WDT
-extern u32 booke_wdt_enabled;
-extern u32 booke_wdt_period;
-#endif /* CONFIG_BOOKE_WDT */
-
-struct device_node;
-extern void note_scsi_host(struct device_node *, void *);
-
-extern struct task_struct *__switch_to(struct task_struct *,
-	struct task_struct *);
-#define switch_to(prev, next, last)	((last) = __switch_to((prev), (next)))
-
-struct thread_struct;
-extern struct task_struct *_switch(struct thread_struct *prev,
-				   struct thread_struct *next);
-
-extern unsigned int rtas_data;
-extern int mem_init_done;	/* set on boot once kmalloc can be called */
-extern int init_bootmem_done;	/* set once bootmem is available */
-extern phys_addr_t memory_limit;
-extern unsigned long klimit;
-extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
-
-extern int powersave_nap;	/* set if nap mode can be used in idle loop */
-void cpu_idle_wait(void);
-
-#ifdef CONFIG_PSERIES_IDLE
-extern void update_smt_snooze_delay(int snooze);
-extern int pseries_notify_cpuidle_add_cpu(int cpu);
-#else
-static inline void update_smt_snooze_delay(int snooze) {}
-static inline int pseries_notify_cpuidle_add_cpu(int cpu) { return 0; }
-#endif
-
-/*
- * Atomic exchange
- *
- * Changes the memory location '*ptr' to be val and returns
- * the previous value stored there.
- */
-static __always_inline unsigned long
-__xchg_u32(volatile void *p, unsigned long val)
-{
-	unsigned long prev;
-
-	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
-"1:	lwarx	%0,0,%2 \n"
-	PPC405_ERR77(0,%2)
-"	stwcx.	%3,0,%2 \n\
-	bne-	1b"
-	PPC_ACQUIRE_BARRIER
-	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
-	: "r" (p), "r" (val)
-	: "cc", "memory");
-
-	return prev;
-}
-
-/*
- * Atomic exchange
- *
- * Changes the memory location '*ptr' to be val and returns
- * the previous value stored there.
- */
-static __always_inline unsigned long
-__xchg_u32_local(volatile void *p, unsigned long val)
-{
-	unsigned long prev;
-
-	__asm__ __volatile__(
-"1:	lwarx	%0,0,%2 \n"
-	PPC405_ERR77(0,%2)
-"	stwcx.	%3,0,%2 \n\
-	bne-	1b"
-	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
-	: "r" (p), "r" (val)
-	: "cc", "memory");
-
-	return prev;
-}
-
-#ifdef CONFIG_PPC64
-static __always_inline unsigned long
-__xchg_u64(volatile void *p, unsigned long val)
-{
-	unsigned long prev;
-
-	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
-"1:	ldarx	%0,0,%2 \n"
-	PPC405_ERR77(0,%2)
-"	stdcx.	%3,0,%2 \n\
-	bne-	1b"
-	PPC_ACQUIRE_BARRIER
-	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
-	: "r" (p), "r" (val)
-	: "cc", "memory");
-
-	return prev;
-}
-
-static __always_inline unsigned long
-__xchg_u64_local(volatile void *p, unsigned long val)
-{
-	unsigned long prev;
-
-	__asm__ __volatile__(
-"1:	ldarx	%0,0,%2 \n"
-	PPC405_ERR77(0,%2)
-"	stdcx.	%3,0,%2 \n\
-	bne-	1b"
-	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
-	: "r" (p), "r" (val)
-	: "cc", "memory");
-
-	return prev;
-}
-#endif
-
-/*
- * This function doesn't exist, so you'll get a linker error
- * if something tries to do an invalid xchg().
- */
-extern void __xchg_called_with_bad_pointer(void);
-
-static __always_inline unsigned long
-__xchg(volatile void *ptr, unsigned long x, unsigned int size)
-{
-	switch (size) {
-	case 4:
-		return __xchg_u32(ptr, x);
-#ifdef CONFIG_PPC64
-	case 8:
-		return __xchg_u64(ptr, x);
-#endif
-	}
-	__xchg_called_with_bad_pointer();
-	return x;
-}
-
-static __always_inline unsigned long
-__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
-{
-	switch (size) {
-	case 4:
-		return __xchg_u32_local(ptr, x);
-#ifdef CONFIG_PPC64
-	case 8:
-		return __xchg_u64_local(ptr, x);
-#endif
-	}
-	__xchg_called_with_bad_pointer();
-	return x;
-}
-#define xchg(ptr,x)							     \
-  ({									     \
-     __typeof__(*(ptr)) _x_ = (x);					     \
-     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \
-  })
-
-#define xchg_local(ptr,x)						     \
-  ({									     \
-     __typeof__(*(ptr)) _x_ = (x);					     \
-     (__typeof__(*(ptr))) __xchg_local((ptr),				     \
-     		(unsigned long)_x_, sizeof(*(ptr))); 			     \
-  })
-
-/*
- * Compare and exchange - if *p == old, set it to new,
- * and return the old value of *p.
- */
-#define __HAVE_ARCH_CMPXCHG	1
-
-static __always_inline unsigned long
-__cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
-{
-	unsigned int prev;
-
-	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
-"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
-	cmpw	0,%0,%3\n\
-	bne-	2f\n"
-	PPC405_ERR77(0,%2)
-"	stwcx.	%4,0,%2\n\
-	bne-	1b"
-	PPC_ACQUIRE_BARRIER
-	"\n\
-2:"
-	: "=&r" (prev), "+m" (*p)
-	: "r" (p), "r" (old), "r" (new)
-	: "cc", "memory");
-
-	return prev;
-}
-
-static __always_inline unsigned long
-__cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
-			unsigned long new)
-{
-	unsigned int prev;
-
-	__asm__ __volatile__ (
-"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
-	cmpw	0,%0,%3\n\
-	bne-	2f\n"
-	PPC405_ERR77(0,%2)
-"	stwcx.	%4,0,%2\n\
-	bne-	1b"
-	"\n\
-2:"
-	: "=&r" (prev), "+m" (*p)
-	: "r" (p), "r" (old), "r" (new)
-	: "cc", "memory");
-
-	return prev;
-}
-
-#ifdef CONFIG_PPC64
-static __always_inline unsigned long
-__cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
-{
-	unsigned long prev;
-
-	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
-"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
-	cmpd	0,%0,%3\n\
-	bne-	2f\n\
-	stdcx.	%4,0,%2\n\
-	bne-	1b"
-	PPC_ACQUIRE_BARRIER
-	"\n\
-2:"
-	: "=&r" (prev), "+m" (*p)
-	: "r" (p), "r" (old), "r" (new)
-	: "cc", "memory");
-
-	return prev;
-}
-
-static __always_inline unsigned long
-__cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
-			unsigned long new)
-{
-	unsigned long prev;
-
-	__asm__ __volatile__ (
-"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
-	cmpd	0,%0,%3\n\
-	bne-	2f\n\
-	stdcx.	%4,0,%2\n\
-	bne-	1b"
-	"\n\
-2:"
-	: "=&r" (prev), "+m" (*p)
-	: "r" (p), "r" (old), "r" (new)
-	: "cc", "memory");
-
-	return prev;
-}
-#endif
-
-/* This function doesn't exist, so you'll get a linker error
-   if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-static __always_inline unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
-	  unsigned int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32(ptr, old, new);
-#ifdef CONFIG_PPC64
-	case 8:
-		return __cmpxchg_u64(ptr, old, new);
-#endif
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-static __always_inline unsigned long
-__cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
-	  unsigned int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32_local(ptr, old, new);
-#ifdef CONFIG_PPC64
-	case 8:
-		return __cmpxchg_u64_local(ptr, old, new);
-#endif
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#define cmpxchg(ptr, o, n)						 \
-  ({									 \
-     __typeof__(*(ptr)) _o_ = (o);					 \
-     __typeof__(*(ptr)) _n_ = (n);					 \
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
-				    (unsigned long)_n_, sizeof(*(ptr))); \
-  })
-
-
-#define cmpxchg_local(ptr, o, n)					 \
-  ({									 \
-     __typeof__(*(ptr)) _o_ = (o);					 \
-     __typeof__(*(ptr)) _n_ = (n);					 \
-     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	 \
-				    (unsigned long)_n_, sizeof(*(ptr))); \
-  })
-
-#ifdef CONFIG_PPC64
-/*
- * We handle most unaligned accesses in hardware. On the other hand 
- * unaligned DMA can be very expensive on some ppc64 IO chips (it does
- * powers of 2 writes until it reaches sufficient alignment).
- *
- * Based on this we disable the IP header alignment in network drivers.
- */
-#define NET_IP_ALIGN	0
-
-#define cmpxchg64(ptr, o, n)						\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
-  })
-#define cmpxchg64_local(ptr, o, n)					\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
-  })
-#else
-#include <asm-generic/cmpxchg-local.h>
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-#endif
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-/* Used in very early kernel initialization. */
-extern unsigned long reloc_offset(void);
-extern unsigned long add_reloc_offset(unsigned long);
-extern void reloc_got2(unsigned long);
-
-#define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
-
-extern struct dentry *powerpc_debugfs_root;
-
-#ifdef CONFIG_PPC64
-
-extern void __ppc64_runlatch_on(void);
-extern void __ppc64_runlatch_off(void);
-
-/*
- * We manually hard enable-disable, this is called
- * in the idle loop and we don't want to mess up
- * with soft-disable/enable & interrupt replay.
- */
-#define ppc64_runlatch_off()					\
-	do {							\
-		if (cpu_has_feature(CPU_FTR_CTRL) &&		\
-		    test_thread_local_flags(_TLF_RUNLATCH)) {	\
-			unsigned long msr = mfmsr();		\
-			__hard_irq_disable();			\
-			__ppc64_runlatch_off();			\
-			if (msr & MSR_EE)			\
-				__hard_irq_enable();		\
-		}      						\
-	} while (0)
-
-#define ppc64_runlatch_on()					\
-	do {							\
-		if (cpu_has_feature(CPU_FTR_CTRL) &&		\
-		    !test_thread_local_flags(_TLF_RUNLATCH)) {	\
-			unsigned long msr = mfmsr();		\
-			__hard_irq_disable();			\
-			__ppc64_runlatch_on();			\
-			if (msr & MSR_EE)			\
-				__hard_irq_enable();		\
-		}      						\
-	} while (0)
-#else
-#define ppc64_runlatch_on()
-#define ppc64_runlatch_off()
-#endif /* CONFIG_PPC64 */
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_SYSTEM_H */
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index 8338aef5a4d3..b3038817b8dc 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -44,7 +44,6 @@ extern void __init udbg_init_debug_lpar_hvsi(void);
 extern void __init udbg_init_pmac_realmode(void);
 extern void __init udbg_init_maple_realmode(void);
 extern void __init udbg_init_pas_realmode(void);
-extern void __init udbg_init_iseries(void);
 extern void __init udbg_init_rtas_panel(void);
 extern void __init udbg_init_rtas_console(void);
 extern void __init udbg_init_debug_beat(void);
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index 0a290a195946..6bfd5ffe1d4f 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -69,6 +69,7 @@ struct vio_dev {
 };
 
 struct vio_driver {
+	const char *name;
 	const struct vio_device_id *id_table;
 	int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
 	int (*remove)(struct vio_dev *dev);
@@ -76,10 +77,17 @@ struct vio_driver {
 	 * be loaded in a CMO environment if it uses DMA.
 	 */
 	unsigned long (*get_desired_dma)(struct vio_dev *dev);
+	const struct dev_pm_ops *pm;
 	struct device_driver driver;
 };
 
-extern int vio_register_driver(struct vio_driver *drv);
+extern int __vio_register_driver(struct vio_driver *drv, struct module *owner,
+				 const char *mod_name);
+/*
+ * vio_register_driver must be a macro so that KBUILD_MODNAME can be expanded
+ */
+#define vio_register_driver(driver)		\
+	__vio_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
 extern void vio_unregister_driver(struct vio_driver *drv);
 
 extern int vio_cmo_entitlement_update(size_t);
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 8184ee97e484..ee5b690a0bed 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -21,10 +21,10 @@
 #include <linux/mm.h>
 #include <asm/processor.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/cache.h>
 #include <asm/cputable.h>
 #include <asm/emulated_ops.h>
+#include <asm/switch_to.h>
 
 struct aligninfo {
 	unsigned char len;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index cc492e48ddfa..34b8afe94a50 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -412,16 +412,23 @@ int main(void)
 	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
 	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
 #endif
-	DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
-	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
-	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
-	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
+	DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
+	DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
+	DEFINE(VCPU_SHARED_SPRG6, offsetof(struct kvm_vcpu_arch_shared, sprg6));
+	DEFINE(VCPU_SHARED_SPRG7, offsetof(struct kvm_vcpu_arch_shared, sprg7));
 	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
 	DEFINE(VCPU_SHADOW_PID1, offsetof(struct kvm_vcpu, arch.shadow_pid1));
 	DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
 	DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
 	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
 
+	DEFINE(VCPU_SHARED_MAS0, offsetof(struct kvm_vcpu_arch_shared, mas0));
+	DEFINE(VCPU_SHARED_MAS1, offsetof(struct kvm_vcpu_arch_shared, mas1));
+	DEFINE(VCPU_SHARED_MAS2, offsetof(struct kvm_vcpu_arch_shared, mas2));
+	DEFINE(VCPU_SHARED_MAS7_3, offsetof(struct kvm_vcpu_arch_shared, mas7_3));
+	DEFINE(VCPU_SHARED_MAS4, offsetof(struct kvm_vcpu_arch_shared, mas4));
+	DEFINE(VCPU_SHARED_MAS6, offsetof(struct kvm_vcpu_arch_shared, mas6));
+
 	/* book3s */
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
@@ -434,6 +441,7 @@ int main(void)
 	DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu));
 	DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
 	DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
+	DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
 	DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
 	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
 #endif
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 138ae183c440..455faa389876 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -20,6 +20,7 @@
 #include <asm/cputable.h>
 #include <asm/prom.h>		/* for PTRRELOC on ARCH=ppc */
 #include <asm/mmu.h>
+#include <asm/setup.h>
 
 struct cpu_spec* cur_cpu_spec = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index abef75176c07..fdcd8f551aff 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -27,8 +27,8 @@
 #include <asm/kdump.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/setjmp.h>
+#include <asm/debug.h>
 
 /*
  * The primary CPU waits a while for all secondary CPUs to enter. This is to
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 3f6464b4d970..bcfdcd22c766 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -17,7 +17,8 @@
  * to the dma address (mapping) of the first page.
  */
 static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
-				      dma_addr_t *dma_handle, gfp_t flag)
+				      dma_addr_t *dma_handle, gfp_t flag,
+				      struct dma_attrs *attrs)
 {
 	return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
 				    dma_handle, dev->coherent_dma_mask, flag,
@@ -25,7 +26,8 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
 }
 
 static void dma_iommu_free_coherent(struct device *dev, size_t size,
-				    void *vaddr, dma_addr_t dma_handle)
+				    void *vaddr, dma_addr_t dma_handle,
+				    struct dma_attrs *attrs)
 {
 	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
 }
@@ -105,8 +107,8 @@ static u64 dma_iommu_get_required_mask(struct device *dev)
 }
 
 struct dma_map_ops dma_iommu_ops = {
-	.alloc_coherent		= dma_iommu_alloc_coherent,
-	.free_coherent		= dma_iommu_free_coherent,
+	.alloc			= dma_iommu_alloc_coherent,
+	.free			= dma_iommu_free_coherent,
 	.map_sg			= dma_iommu_map_sg,
 	.unmap_sg		= dma_iommu_unmap_sg,
 	.dma_supported		= dma_iommu_dma_supported,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 1ebc9189aada..4ab88dafb235 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -47,8 +47,8 @@ static u64 swiotlb_powerpc_get_required(struct device *dev)
  * for everything else.
  */
 struct dma_map_ops swiotlb_dma_ops = {
-	.alloc_coherent = dma_direct_alloc_coherent,
-	.free_coherent = dma_direct_free_coherent,
+	.alloc = dma_direct_alloc_coherent,
+	.free = dma_direct_free_coherent,
 	.map_sg = swiotlb_map_sg_attrs,
 	.unmap_sg = swiotlb_unmap_sg_attrs,
 	.dma_supported = swiotlb_dma_supported,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 7d0233c12ee3..b1ec983dcec8 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -26,7 +26,8 @@
 
 
 void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t flag)
+				dma_addr_t *dma_handle, gfp_t flag,
+				struct dma_attrs *attrs)
 {
 	void *ret;
 #ifdef CONFIG_NOT_COHERENT_CACHE
@@ -54,7 +55,8 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 }
 
 void dma_direct_free_coherent(struct device *dev, size_t size,
-			      void *vaddr, dma_addr_t dma_handle)
+			      void *vaddr, dma_addr_t dma_handle,
+			      struct dma_attrs *attrs)
 {
 #ifdef CONFIG_NOT_COHERENT_CACHE
 	__dma_free_coherent(size, vaddr);
@@ -150,8 +152,8 @@ static inline void dma_direct_sync_single(struct device *dev,
 #endif
 
 struct dma_map_ops dma_direct_ops = {
-	.alloc_coherent			= dma_direct_alloc_coherent,
-	.free_coherent			= dma_direct_free_coherent,
+	.alloc				= dma_direct_alloc_coherent,
+	.free				= dma_direct_free_coherent,
 	.map_sg				= dma_direct_map_sg,
 	.unmap_sg			= dma_direct_unmap_sg,
 	.dma_supported			= dma_direct_dma_supported,
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 2d0868a4e2f0..cb705fdbb458 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -101,14 +101,14 @@ data_access_not_stab:
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 #endif
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
-				 KVMTEST_PR, 0x300)
+				 KVMTEST, 0x300)
 
 	. = 0x380
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
 	HMT_MEDIUM
 	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_DAR
 #ifdef __DISABLED__
@@ -330,8 +330,8 @@ do_stab_bolted_pSeries:
 	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
 #endif /* CONFIG_POWER4_ONLY */
 
-	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x300)
-	KVM_HANDLER_PR_SKIP(PACA_EXSLB, EXC_STD, 0x380)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
+	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400)
 	KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index cfe7a38708c3..18bdf74fa164 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -40,6 +40,8 @@
 #include <asm/prom.h>
 #include <asm/rtas.h>
 #include <asm/fadump.h>
+#include <asm/debug.h>
+#include <asm/setup.h>
 
 static struct fw_dump fw_dump;
 static struct fadump_mem_struct fdm;
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 79bb282e6501..b01d14eeca8d 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -65,7 +65,8 @@ static struct of_device_id __initdata ibmebus_matches[] = {
 static void *ibmebus_alloc_coherent(struct device *dev,
 				    size_t size,
 				    dma_addr_t *dma_handle,
-				    gfp_t flag)
+				    gfp_t flag,
+				    struct dma_attrs *attrs)
 {
 	void *mem;
 
@@ -77,7 +78,8 @@ static void *ibmebus_alloc_coherent(struct device *dev,
 
 static void ibmebus_free_coherent(struct device *dev,
 				  size_t size, void *vaddr,
-				  dma_addr_t dma_handle)
+				  dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	kfree(vaddr);
 }
@@ -136,8 +138,8 @@ static u64 ibmebus_dma_get_required_mask(struct device *dev)
 }
 
 static struct dma_map_ops ibmebus_dma_ops = {
-	.alloc_coherent     = ibmebus_alloc_coherent,
-	.free_coherent      = ibmebus_free_coherent,
+	.alloc              = ibmebus_alloc_coherent,
+	.free               = ibmebus_free_coherent,
 	.map_sg             = ibmebus_map_sg,
 	.unmap_sg           = ibmebus_unmap_sg,
 	.dma_supported      = ibmebus_dma_supported,
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index e8e821146f38..6d2209ac0c44 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -26,11 +26,11 @@
 #include <linux/sysctl.h>
 #include <linux/tick.h>
 
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
+#include <asm/runlatch.h>
 #include <asm/smp.h>
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index a3d128e94cff..243dbabfe74d 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -57,7 +57,6 @@
 #include <linux/of_irq.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/irq.h>
@@ -67,6 +66,7 @@
 #include <asm/machdep.h>
 #include <asm/udbg.h>
 #include <asm/smp.h>
+#include <asm/debug.h>
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -208,8 +208,8 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 * we are checking the "new" CPU instead of the old one. This
 	 * is only a problem if an event happened on the "old" CPU.
 	 *
-	 * External interrupt events on non-iseries will have caused
-	 * interrupts to be hard-disabled, so there is no problem, we
+	 * External interrupt events will have caused interrupts to
+	 * be hard-disabled, so there is no problem, we
 	 * cannot have preempted.
 	 */
 	irq_happened = get_irq_happened();
@@ -445,9 +445,9 @@ void do_IRQ(struct pt_regs *regs)
 	may_hard_irq_enable();
 
 	/* And finally process it */
-	if (irq != NO_IRQ && irq != NO_IRQ_IGNORE)
+	if (irq != NO_IRQ)
 		handle_one_irq(irq);
-	else if (irq != NO_IRQ_IGNORE)
+	else
 		__get_cpu_var(irq_stat).spurious_irqs++;
 
 	irq_exit();
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 76a6e40a6f7c..782bd0a3c2f0 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -24,6 +24,7 @@
 #include <asm/current.h>
 #include <asm/processor.h>
 #include <asm/machdep.h>
+#include <asm/debug.h>
 
 /*
  * This table contains the mapping between PowerPC hardware trap types, and
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index bc47352deb1f..e88c64331819 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -35,7 +35,6 @@
 #include <asm/cacheflush.h>
 #include <asm/sstep.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 #define MSR_SINGLESTEP	(MSR_DE)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 2985338d0e10..62bdf2389669 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
  *
  * Authors:
  *     Alexander Graf <agraf@suse.de>
@@ -29,6 +30,7 @@
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
 #include <asm/disassemble.h>
+#include <asm/ppc-opcode.h>
 
 #define KVM_MAGIC_PAGE		(-4096L)
 #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
@@ -41,34 +43,30 @@
 #define KVM_INST_B		0x48000000
 #define KVM_INST_B_MASK		0x03ffffff
 #define KVM_INST_B_MAX		0x01ffffff
+#define KVM_INST_LI		0x38000000
 
 #define KVM_MASK_RT		0x03e00000
 #define KVM_RT_30		0x03c00000
 #define KVM_MASK_RB		0x0000f800
 #define KVM_INST_MFMSR		0x7c0000a6
-#define KVM_INST_MFSPR_SPRG0	0x7c1042a6
-#define KVM_INST_MFSPR_SPRG1	0x7c1142a6
-#define KVM_INST_MFSPR_SPRG2	0x7c1242a6
-#define KVM_INST_MFSPR_SPRG3	0x7c1342a6
-#define KVM_INST_MFSPR_SRR0	0x7c1a02a6
-#define KVM_INST_MFSPR_SRR1	0x7c1b02a6
-#define KVM_INST_MFSPR_DAR	0x7c1302a6
-#define KVM_INST_MFSPR_DSISR	0x7c1202a6
-
-#define KVM_INST_MTSPR_SPRG0	0x7c1043a6
-#define KVM_INST_MTSPR_SPRG1	0x7c1143a6
-#define KVM_INST_MTSPR_SPRG2	0x7c1243a6
-#define KVM_INST_MTSPR_SPRG3	0x7c1343a6
-#define KVM_INST_MTSPR_SRR0	0x7c1a03a6
-#define KVM_INST_MTSPR_SRR1	0x7c1b03a6
-#define KVM_INST_MTSPR_DAR	0x7c1303a6
-#define KVM_INST_MTSPR_DSISR	0x7c1203a6
+
+#define SPR_FROM		0
+#define SPR_TO			0x100
+
+#define KVM_INST_SPR(sprn, moveto) (0x7c0002a6 | \
+				    (((sprn) & 0x1f) << 16) | \
+				    (((sprn) & 0x3e0) << 6) | \
+				    (moveto))
+
+#define KVM_INST_MFSPR(sprn)	KVM_INST_SPR(sprn, SPR_FROM)
+#define KVM_INST_MTSPR(sprn)	KVM_INST_SPR(sprn, SPR_TO)
 
 #define KVM_INST_TLBSYNC	0x7c00046c
 #define KVM_INST_MTMSRD_L0	0x7c000164
 #define KVM_INST_MTMSRD_L1	0x7c010164
 #define KVM_INST_MTMSR		0x7c000124
 
+#define KVM_INST_WRTEE		0x7c000106
 #define KVM_INST_WRTEEI_0	0x7c000146
 #define KVM_INST_WRTEEI_1	0x7c008146
 
@@ -270,26 +268,27 @@ static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
 
 #ifdef CONFIG_BOOKE
 
-extern u32 kvm_emulate_wrteei_branch_offs;
-extern u32 kvm_emulate_wrteei_ee_offs;
-extern u32 kvm_emulate_wrteei_len;
-extern u32 kvm_emulate_wrteei[];
+extern u32 kvm_emulate_wrtee_branch_offs;
+extern u32 kvm_emulate_wrtee_reg_offs;
+extern u32 kvm_emulate_wrtee_orig_ins_offs;
+extern u32 kvm_emulate_wrtee_len;
+extern u32 kvm_emulate_wrtee[];
 
-static void kvm_patch_ins_wrteei(u32 *inst)
+static void kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one)
 {
 	u32 *p;
 	int distance_start;
 	int distance_end;
 	ulong next_inst;
 
-	p = kvm_alloc(kvm_emulate_wrteei_len * 4);
+	p = kvm_alloc(kvm_emulate_wrtee_len * 4);
 	if (!p)
 		return;
 
 	/* Find out where we are and put everything there */
 	distance_start = (ulong)p - (ulong)inst;
 	next_inst = ((ulong)inst + 4);
-	distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_branch_offs];
+	distance_end = next_inst - (ulong)&p[kvm_emulate_wrtee_branch_offs];
 
 	/* Make sure we only write valid b instructions */
 	if (distance_start > KVM_INST_B_MAX) {
@@ -298,10 +297,65 @@ static void kvm_patch_ins_wrteei(u32 *inst)
 	}
 
 	/* Modify the chunk to fit the invocation */
-	memcpy(p, kvm_emulate_wrteei, kvm_emulate_wrteei_len * 4);
-	p[kvm_emulate_wrteei_branch_offs] |= distance_end & KVM_INST_B_MASK;
-	p[kvm_emulate_wrteei_ee_offs] |= (*inst & MSR_EE);
-	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_len * 4);
+	memcpy(p, kvm_emulate_wrtee, kvm_emulate_wrtee_len * 4);
+	p[kvm_emulate_wrtee_branch_offs] |= distance_end & KVM_INST_B_MASK;
+
+	if (imm_one) {
+		p[kvm_emulate_wrtee_reg_offs] =
+			KVM_INST_LI | __PPC_RT(30) | MSR_EE;
+	} else {
+		/* Make clobbered registers work too */
+		switch (get_rt(rt)) {
+		case 30:
+			kvm_patch_ins_ll(&p[kvm_emulate_wrtee_reg_offs],
+					 magic_var(scratch2), KVM_RT_30);
+			break;
+		case 31:
+			kvm_patch_ins_ll(&p[kvm_emulate_wrtee_reg_offs],
+					 magic_var(scratch1), KVM_RT_30);
+			break;
+		default:
+			p[kvm_emulate_wrtee_reg_offs] |= rt;
+			break;
+		}
+	}
+
+	p[kvm_emulate_wrtee_orig_ins_offs] = *inst;
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrtee_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
+extern u32 kvm_emulate_wrteei_0_branch_offs;
+extern u32 kvm_emulate_wrteei_0_len;
+extern u32 kvm_emulate_wrteei_0[];
+
+static void kvm_patch_ins_wrteei_0(u32 *inst)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_wrteei_0_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_0_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	memcpy(p, kvm_emulate_wrteei_0, kvm_emulate_wrteei_0_len * 4);
+	p[kvm_emulate_wrteei_0_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_0_len * 4);
 
 	/* Patch the invocation */
 	kvm_patch_ins_b(inst, distance_start);
@@ -380,56 +434,191 @@ static void kvm_check_ins(u32 *inst, u32 features)
 	case KVM_INST_MFMSR:
 		kvm_patch_ins_ld(inst, magic_var(msr), inst_rt);
 		break;
-	case KVM_INST_MFSPR_SPRG0:
+	case KVM_INST_MFSPR(SPRN_SPRG0):
 		kvm_patch_ins_ld(inst, magic_var(sprg0), inst_rt);
 		break;
-	case KVM_INST_MFSPR_SPRG1:
+	case KVM_INST_MFSPR(SPRN_SPRG1):
 		kvm_patch_ins_ld(inst, magic_var(sprg1), inst_rt);
 		break;
-	case KVM_INST_MFSPR_SPRG2:
+	case KVM_INST_MFSPR(SPRN_SPRG2):
 		kvm_patch_ins_ld(inst, magic_var(sprg2), inst_rt);
 		break;
-	case KVM_INST_MFSPR_SPRG3:
+	case KVM_INST_MFSPR(SPRN_SPRG3):
 		kvm_patch_ins_ld(inst, magic_var(sprg3), inst_rt);
 		break;
-	case KVM_INST_MFSPR_SRR0:
+	case KVM_INST_MFSPR(SPRN_SRR0):
 		kvm_patch_ins_ld(inst, magic_var(srr0), inst_rt);
 		break;
-	case KVM_INST_MFSPR_SRR1:
+	case KVM_INST_MFSPR(SPRN_SRR1):
 		kvm_patch_ins_ld(inst, magic_var(srr1), inst_rt);
 		break;
-	case KVM_INST_MFSPR_DAR:
+#ifdef CONFIG_BOOKE
+	case KVM_INST_MFSPR(SPRN_DEAR):
+#else
+	case KVM_INST_MFSPR(SPRN_DAR):
+#endif
 		kvm_patch_ins_ld(inst, magic_var(dar), inst_rt);
 		break;
-	case KVM_INST_MFSPR_DSISR:
+	case KVM_INST_MFSPR(SPRN_DSISR):
 		kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt);
 		break;
 
+#ifdef CONFIG_PPC_BOOK3E_MMU
+	case KVM_INST_MFSPR(SPRN_MAS0):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_lwz(inst, magic_var(mas0), inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_MAS1):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_lwz(inst, magic_var(mas1), inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_MAS2):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_ld(inst, magic_var(mas2), inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_MAS3):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_lwz(inst, magic_var(mas7_3) + 4, inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_MAS4):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_lwz(inst, magic_var(mas4), inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_MAS6):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_lwz(inst, magic_var(mas6), inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_MAS7):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_lwz(inst, magic_var(mas7_3), inst_rt);
+		break;
+#endif /* CONFIG_PPC_BOOK3E_MMU */
+
+	case KVM_INST_MFSPR(SPRN_SPRG4):
+#ifdef CONFIG_BOOKE
+	case KVM_INST_MFSPR(SPRN_SPRG4R):
+#endif
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_ld(inst, magic_var(sprg4), inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_SPRG5):
+#ifdef CONFIG_BOOKE
+	case KVM_INST_MFSPR(SPRN_SPRG5R):
+#endif
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_ld(inst, magic_var(sprg5), inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_SPRG6):
+#ifdef CONFIG_BOOKE
+	case KVM_INST_MFSPR(SPRN_SPRG6R):
+#endif
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_ld(inst, magic_var(sprg6), inst_rt);
+		break;
+	case KVM_INST_MFSPR(SPRN_SPRG7):
+#ifdef CONFIG_BOOKE
+	case KVM_INST_MFSPR(SPRN_SPRG7R):
+#endif
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_ld(inst, magic_var(sprg7), inst_rt);
+		break;
+
+#ifdef CONFIG_BOOKE
+	case KVM_INST_MFSPR(SPRN_ESR):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_lwz(inst, magic_var(esr), inst_rt);
+		break;
+#endif
+
+	case KVM_INST_MFSPR(SPRN_PIR):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_lwz(inst, magic_var(pir), inst_rt);
+		break;
+
+
 	/* Stores */
-	case KVM_INST_MTSPR_SPRG0:
+	case KVM_INST_MTSPR(SPRN_SPRG0):
 		kvm_patch_ins_std(inst, magic_var(sprg0), inst_rt);
 		break;
-	case KVM_INST_MTSPR_SPRG1:
+	case KVM_INST_MTSPR(SPRN_SPRG1):
 		kvm_patch_ins_std(inst, magic_var(sprg1), inst_rt);
 		break;
-	case KVM_INST_MTSPR_SPRG2:
+	case KVM_INST_MTSPR(SPRN_SPRG2):
 		kvm_patch_ins_std(inst, magic_var(sprg2), inst_rt);
 		break;
-	case KVM_INST_MTSPR_SPRG3:
+	case KVM_INST_MTSPR(SPRN_SPRG3):
 		kvm_patch_ins_std(inst, magic_var(sprg3), inst_rt);
 		break;
-	case KVM_INST_MTSPR_SRR0:
+	case KVM_INST_MTSPR(SPRN_SRR0):
 		kvm_patch_ins_std(inst, magic_var(srr0), inst_rt);
 		break;
-	case KVM_INST_MTSPR_SRR1:
+	case KVM_INST_MTSPR(SPRN_SRR1):
 		kvm_patch_ins_std(inst, magic_var(srr1), inst_rt);
 		break;
-	case KVM_INST_MTSPR_DAR:
+#ifdef CONFIG_BOOKE
+	case KVM_INST_MTSPR(SPRN_DEAR):
+#else
+	case KVM_INST_MTSPR(SPRN_DAR):
+#endif
 		kvm_patch_ins_std(inst, magic_var(dar), inst_rt);
 		break;
-	case KVM_INST_MTSPR_DSISR:
+	case KVM_INST_MTSPR(SPRN_DSISR):
 		kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
 		break;
+#ifdef CONFIG_PPC_BOOK3E_MMU
+	case KVM_INST_MTSPR(SPRN_MAS0):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_stw(inst, magic_var(mas0), inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_MAS1):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_stw(inst, magic_var(mas1), inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_MAS2):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_std(inst, magic_var(mas2), inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_MAS3):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_stw(inst, magic_var(mas7_3) + 4, inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_MAS4):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_stw(inst, magic_var(mas4), inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_MAS6):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_stw(inst, magic_var(mas6), inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_MAS7):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_stw(inst, magic_var(mas7_3), inst_rt);
+		break;
+#endif /* CONFIG_PPC_BOOK3E_MMU */
+
+	case KVM_INST_MTSPR(SPRN_SPRG4):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_std(inst, magic_var(sprg4), inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_SPRG5):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_std(inst, magic_var(sprg5), inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_SPRG6):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_std(inst, magic_var(sprg6), inst_rt);
+		break;
+	case KVM_INST_MTSPR(SPRN_SPRG7):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_std(inst, magic_var(sprg7), inst_rt);
+		break;
+
+#ifdef CONFIG_BOOKE
+	case KVM_INST_MTSPR(SPRN_ESR):
+		if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+			kvm_patch_ins_stw(inst, magic_var(esr), inst_rt);
+		break;
+#endif
 
 	/* Nops */
 	case KVM_INST_TLBSYNC:
@@ -444,6 +633,11 @@ static void kvm_check_ins(u32 *inst, u32 features)
 	case KVM_INST_MTMSRD_L0:
 		kvm_patch_ins_mtmsr(inst, inst_rt);
 		break;
+#ifdef CONFIG_BOOKE
+	case KVM_INST_WRTEE:
+		kvm_patch_ins_wrtee(inst, inst_rt, 0);
+		break;
+#endif
 	}
 
 	switch (inst_no_rt & ~KVM_MASK_RB) {
@@ -461,13 +655,19 @@ static void kvm_check_ins(u32 *inst, u32 features)
 	switch (_inst) {
 #ifdef CONFIG_BOOKE
 	case KVM_INST_WRTEEI_0:
+		kvm_patch_ins_wrteei_0(inst);
+		break;
+
 	case KVM_INST_WRTEEI_1:
-		kvm_patch_ins_wrteei(inst);
+		kvm_patch_ins_wrtee(inst, 0, 1);
 		break;
 #endif
 	}
 }
 
+extern u32 kvm_template_start[];
+extern u32 kvm_template_end[];
+
 static void kvm_use_magic_page(void)
 {
 	u32 *p;
@@ -488,8 +688,23 @@ static void kvm_use_magic_page(void)
 	start = (void*)_stext;
 	end = (void*)_etext;
 
-	for (p = start; p < end; p++)
+	/*
+	 * Being interrupted in the middle of patching would
+	 * be bad for SPRG4-7, which KVM can't keep in sync
+	 * with emulated accesses because reads don't trap.
+	 */
+	local_irq_disable();
+
+	for (p = start; p < end; p++) {
+		/* Avoid patching the template code */
+		if (p >= kvm_template_start && p < kvm_template_end) {
+			p = kvm_template_end - 1;
+			continue;
+		}
 		kvm_check_ins(p, features);
+	}
+
+	local_irq_enable();
 
 	printk(KERN_INFO "KVM: Live patching for a fast VM %s\n",
 			 kvm_patching_worked ? "worked" : "failed");
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index f2b1b2523e61..e291cf3cf954 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -13,6 +13,7 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  *
  * Copyright SUSE Linux Products GmbH 2010
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
  *
  * Authors: Alexander Graf <agraf@suse.de>
  */
@@ -65,6 +66,9 @@ kvm_hypercall_start:
 	   shared->critical == r1 and r2 is always != r1 */		\
 	STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
 
+.global kvm_template_start
+kvm_template_start:
+
 .global kvm_emulate_mtmsrd
 kvm_emulate_mtmsrd:
 
@@ -167,6 +171,9 @@ maybe_stay_in_guest:
 kvm_emulate_mtmsr_reg2:
 	ori	r30, r0, 0
 
+	/* Put MSR into magic page because we don't call mtmsr */
+	STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
 	/* Check if we have to fetch an interrupt */
 	lwz	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
 	cmpwi	r31, 0
@@ -174,15 +181,10 @@ kvm_emulate_mtmsr_reg2:
 
 	/* Check if we may trigger an interrupt */
 	andi.	r31, r30, MSR_EE
-	beq	no_mtmsr
-
-	b	do_mtmsr
+	bne	do_mtmsr
 
 no_mtmsr:
 
-	/* Put MSR into magic page because we don't call mtmsr */
-	STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
-
 	SCRATCH_RESTORE
 
 	/* Go back to caller */
@@ -210,24 +212,80 @@ kvm_emulate_mtmsr_orig_ins_offs:
 kvm_emulate_mtmsr_len:
 	.long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
 
+/* also used for wrteei 1 */
+.global kvm_emulate_wrtee
+kvm_emulate_wrtee:
+
+	SCRATCH_SAVE
+
+	/* Fetch old MSR in r31 */
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	/* Insert new MSR[EE] */
+kvm_emulate_wrtee_reg:
+	ori	r30, r0, 0
+	rlwimi	r31, r30, 0, MSR_EE
+
+	/*
+	 * If MSR[EE] is now set, check for a pending interrupt.
+	 * We could skip this if MSR[EE] was already on, but that
+	 * should be rare, so don't bother.
+	 */
+	andi.	r30, r30, MSR_EE
+
+	/* Put MSR into magic page because we don't call wrtee */
+	STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	beq	no_wrtee
+
+	/* Check if we have to fetch an interrupt */
+	lwz	r30, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+	cmpwi	r30, 0
+	bne	do_wrtee
+
+no_wrtee:
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_wrtee_branch:
+	b	.
+
+do_wrtee:
+	SCRATCH_RESTORE
 
+	/* Just fire off the wrtee if it's critical */
+kvm_emulate_wrtee_orig_ins:
+	wrtee	r0
 
-.global kvm_emulate_wrteei
-kvm_emulate_wrteei:
+	b	kvm_emulate_wrtee_branch
 
+kvm_emulate_wrtee_end:
+
+.global kvm_emulate_wrtee_branch_offs
+kvm_emulate_wrtee_branch_offs:
+	.long (kvm_emulate_wrtee_branch - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_reg_offs
+kvm_emulate_wrtee_reg_offs:
+	.long (kvm_emulate_wrtee_reg - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_orig_ins_offs
+kvm_emulate_wrtee_orig_ins_offs:
+	.long (kvm_emulate_wrtee_orig_ins - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_len
+kvm_emulate_wrtee_len:
+	.long (kvm_emulate_wrtee_end - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrteei_0
+kvm_emulate_wrteei_0:
 	SCRATCH_SAVE
 
 	/* Fetch old MSR in r31 */
 	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
 
 	/* Remove MSR_EE from old MSR */
-	li	r30, 0
-	ori	r30, r30, MSR_EE
-	andc	r31, r31, r30
-
-	/* OR new MSR_EE onto the old MSR */
-kvm_emulate_wrteei_ee:
-	ori	r31, r31, 0
+	rlwinm	r31, r31, 0, ~MSR_EE
 
 	/* Write new MSR value back */
 	STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
@@ -235,22 +293,17 @@ kvm_emulate_wrteei_ee:
 	SCRATCH_RESTORE
 
 	/* Go back to caller */
-kvm_emulate_wrteei_branch:
+kvm_emulate_wrteei_0_branch:
 	b	.
-kvm_emulate_wrteei_end:
-
-.global kvm_emulate_wrteei_branch_offs
-kvm_emulate_wrteei_branch_offs:
-	.long (kvm_emulate_wrteei_branch - kvm_emulate_wrteei) / 4
+kvm_emulate_wrteei_0_end:
 
-.global kvm_emulate_wrteei_ee_offs
-kvm_emulate_wrteei_ee_offs:
-	.long (kvm_emulate_wrteei_ee - kvm_emulate_wrteei) / 4
-
-.global kvm_emulate_wrteei_len
-kvm_emulate_wrteei_len:
-	.long (kvm_emulate_wrteei_end - kvm_emulate_wrteei) / 4
+.global kvm_emulate_wrteei_0_branch_offs
+kvm_emulate_wrteei_0_branch_offs:
+	.long (kvm_emulate_wrteei_0_branch - kvm_emulate_wrteei_0) / 4
 
+.global kvm_emulate_wrteei_0_len
+kvm_emulate_wrteei_0_len:
+	.long (kvm_emulate_wrteei_0_end - kvm_emulate_wrteei_0) / 4
 
 .global kvm_emulate_mtsrin
 kvm_emulate_mtsrin:
@@ -300,3 +353,6 @@ kvm_emulate_mtsrin_orig_ins_offs:
 .global kvm_emulate_mtsrin_len
 kvm_emulate_mtsrin_len:
 	.long (kvm_emulate_mtsrin_end - kvm_emulate_mtsrin) / 4
+
+.global kvm_template_end
+kvm_template_end:
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index ac12bd80ad95..f5725bce9ed2 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -30,7 +30,6 @@
 #include <asm/hvcall.h>
 #include <asm/firmware.h>
 #include <asm/rtas.h>
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/prom.h>
 #include <asm/vdso_datapage.h>
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index d3114a71dd32..786a2700ec2d 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -26,7 +26,6 @@
 #include <linux/cuda.h>
 #include <linux/pmu.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/pci-bridge.h>
 #include <asm/irq.h>
 #include <asm/pmac_feature.h>
@@ -43,6 +42,7 @@
 #include <asm/signal.h>
 #include <asm/dcr.h>
 #include <asm/ftrace.h>
+#include <asm/switch_to.h>
 
 #ifdef CONFIG_PPC32
 extern void transfer_to_handler(void);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e40707032ac3..f88698c0f332 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -41,14 +41,16 @@
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/time.h>
+#include <asm/runlatch.h>
 #include <asm/syscalls.h>
+#include <asm/switch_to.h>
+#include <asm/debug.h>
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #endif
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 89e850af3dd6..f191bf02943a 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -41,7 +41,6 @@
 #include <asm/io.h>
 #include <asm/kdump.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/mmu.h>
 #include <asm/paca.h>
 #include <asm/pgtable.h>
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index e2d599048142..99860273211b 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -35,7 +35,6 @@
 #include <asm/irq.h>
 #include <asm/io.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/mmu.h>
 #include <asm/pgtable.h>
 #include <asm/pci.h>
@@ -447,7 +446,7 @@ static void __init __attribute__((noreturn)) prom_panic(const char *reason)
 	if (RELOC(of_platform) == PLATFORM_POWERMAC)
 		asm("trap\n");
 
-	/* ToDo: should put up an SRC here on p/iSeries */
+	/* ToDo: should put up an SRC here on pSeries */
 	call_prom("exit", 0, 0);
 
 	for (;;)			/* should never get here */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 5b43325402bc..8d8e028893be 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -36,7 +36,7 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
+#include <asm/switch_to.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c
index 69c4be917d07..469349d14a97 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace32.c
@@ -32,7 +32,7 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
+#include <asm/switch_to.h>
 
 /*
  * does not yet catch signals sent when the child dies.
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 9f843cdfee9e..fcec38241f79 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -33,7 +33,6 @@
 #include <asm/firmware.h>
 #include <asm/page.h>
 #include <asm/param.h>
-#include <asm/system.h>
 #include <asm/delay.h>
 #include <asm/uaccess.h>
 #include <asm/udbg.h>
@@ -868,6 +867,40 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 }
 #endif
 
+/**
+ * Find a specific pseries error log in an RTAS extended event log.
+ * @log: RTAS error/event log
+ * @section_id: two character section identifier
+ *
+ * Returns a pointer to the specified errorlog or NULL if not found.
+ */
+struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
+					      uint16_t section_id)
+{
+	struct rtas_ext_event_log_v6 *ext_log =
+		(struct rtas_ext_event_log_v6 *)log->buffer;
+	struct pseries_errorlog *sect;
+	unsigned char *p, *log_end;
+
+	/* Check that we understand the format */
+	if (log->extended_log_length < sizeof(struct rtas_ext_event_log_v6) ||
+	    ext_log->log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG ||
+	    ext_log->company_id != RTAS_V6EXT_COMPANY_ID_IBM)
+		return NULL;
+
+	log_end = log->buffer + log->extended_log_length;
+	p = ext_log->vendor_log;
+
+	while (p < log_end) {
+		sect = (struct pseries_errorlog *)p;
+		if (sect->id == section_id)
+			return sect;
+		p += sect->length;
+	}
+
+	return NULL;
+}
+
 asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 {
 	struct rtas_args args;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index b0ebdeab9494..afd4f051f3f2 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -51,7 +51,6 @@
 #include <asm/btext.h>
 #include <asm/nvram.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/rtas.h>
 #include <asm/iommu.h>
 #include <asm/serial.h>
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index ac7610815113..9825f29d1faf 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -30,7 +30,6 @@
 #include <asm/btext.h>
 #include <asm/machdep.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/pmac_feature.h>
 #include <asm/sections.h>
 #include <asm/nvram.h>
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 4cb8f1e9d044..389bd4f0cdb1 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -52,7 +52,6 @@
 #include <asm/btext.h>
 #include <asm/nvram.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/rtas.h>
 #include <asm/iommu.h>
 #include <asm/serial.h>
@@ -598,7 +597,7 @@ void __init setup_arch(char **cmdline_p)
 	/* Initialize the MMU context management stuff */
 	mmu_context_init();
 
-	kvm_rma_init();
+	kvm_linear_init();
 
 	ppc64_boot_msg(0x15, "Setup Done");
 }
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 7006b7f4267a..651c5963662b 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -15,6 +15,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
+#include <asm/debug.h>
 
 #include "signal.h"
 
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index e061ef5dd449..45eb998557f8 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -43,6 +43,7 @@
 #include <asm/syscalls.h>
 #include <asm/sigcontext.h>
 #include <asm/vdso.h>
+#include <asm/switch_to.h>
 #ifdef CONFIG_PPC64
 #include "ppc32.h"
 #include <asm/unistd.h>
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index a50b5ec281dc..2692efdb154e 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -33,6 +33,7 @@
 #include <asm/cacheflush.h>
 #include <asm/syscalls.h>
 #include <asm/vdso.h>
+#include <asm/switch_to.h>
 
 #include "signal.h"
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 46695febc09f..d9f94410fd7f 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -43,12 +43,12 @@
 #include <asm/machdep.h>
 #include <asm/cputhreads.h>
 #include <asm/cputable.h>
-#include <asm/system.h>
 #include <asm/mpic.h>
 #include <asm/vdso_datapage.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #endif
+#include <asm/debug.h>
 
 #ifdef DEBUG
 #include <asm/udbg.h>
diff --git a/arch/powerpc/kernel/softemu8xx.c b/arch/powerpc/kernel/softemu8xx.c
index af0e8290b4fc..29b2f81dd709 100644
--- a/arch/powerpc/kernel/softemu8xx.c
+++ b/arch/powerpc/kernel/softemu8xx.c
@@ -26,7 +26,6 @@
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 /* Eventually we may need a look-up table, but this works for now.
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index 641f9adc6205..eae33e10b65f 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -10,9 +10,9 @@
  */
 
 #include <linux/sched.h>
-#include <asm/system.h>
 #include <asm/current.h>
 #include <asm/mmu_context.h>
+#include <asm/switch_to.h>
 
 void save_processor_state(void)
 {
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 168e88480223..0e899e47c325 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -6,7 +6,6 @@
  * GPLv2
  */
 
-#include <asm/system.h>
 #include <asm/iommu.h>
 #include <linux/irq.h>
 #include <linux/sched.h>
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 4e5bf1edc0f2..81c570633ead 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -50,6 +50,7 @@
 #include <asm/mmu_context.h>
 #include <asm/ppc-pci.h>
 #include <asm/syscalls.h>
+#include <asm/switch_to.h>
 
 
 asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp,
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 0c683d376b1c..3529446c2abd 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -17,7 +17,6 @@
 #include <asm/machdep.h>
 #include <asm/smp.h>
 #include <asm/pmc.h>
-#include <asm/system.h>
 
 #include "cacheinfo.h"
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index a750409ccc4e..6aa0c663e247 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -39,7 +39,6 @@
 #include <asm/emulated_ops.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/machdep.h>
 #include <asm/rtas.h>
@@ -58,6 +57,8 @@
 #include <asm/ppc-opcode.h>
 #include <asm/rio.h>
 #include <asm/fadump.h>
+#include <asm/switch_to.h>
+#include <asm/debug.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 57fa2c0a531c..c39c1ca77f46 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -46,9 +46,6 @@ void __init udbg_early_init(void)
 #elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE)
 	/* Maple real mode debug */
 	udbg_init_maple_realmode();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_ISERIES)
-	/* For iSeries - hit Ctrl-x Ctrl-x to see the output */
-	udbg_init_iseries();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_BEAT)
 	udbg_init_debug_beat();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index d36ee1055f88..9eb5b9b536a7 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -24,7 +24,6 @@
 #include <linux/memblock.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
@@ -721,10 +720,10 @@ static int __init vdso_init(void)
 	vdso_data->version.minor = SYSTEMCFG_MINOR;
 	vdso_data->processor = mfspr(SPRN_PVR);
 	/*
-	 * Fake the old platform number for pSeries and iSeries and add
+	 * Fake the old platform number for pSeries and add
 	 * in LPAR bit if necessary
 	 */
-	vdso_data->platform = machine_is(iseries) ? 0x200 : 0x100;
+	vdso_data->platform = 0x100;
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		vdso_data->platform |= 1;
 	vdso_data->physicalMemorySize = memblock_phys_mem_size();
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index bca3fc427b45..a3a99901c8ec 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -482,7 +482,8 @@ static void vio_cmo_balance(struct work_struct *work)
 }
 
 static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
-                                          dma_addr_t *dma_handle, gfp_t flag)
+					  dma_addr_t *dma_handle, gfp_t flag,
+					  struct dma_attrs *attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 	void *ret;
@@ -492,7 +493,7 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
 		return NULL;
 	}
 
-	ret = dma_iommu_ops.alloc_coherent(dev, size, dma_handle, flag);
+	ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs);
 	if (unlikely(ret == NULL)) {
 		vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 		atomic_inc(&viodev->cmo.allocs_failed);
@@ -502,11 +503,12 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
 }
 
 static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
-                                        void *vaddr, dma_addr_t dma_handle)
+					void *vaddr, dma_addr_t dma_handle,
+					struct dma_attrs *attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 
-	dma_iommu_ops.free_coherent(dev, size, vaddr, dma_handle);
+	dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs);
 
 	vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 }
@@ -607,8 +609,8 @@ static u64 vio_dma_get_required_mask(struct device *dev)
 }
 
 struct dma_map_ops vio_dma_mapping_ops = {
-	.alloc_coherent    = vio_dma_iommu_alloc_coherent,
-	.free_coherent     = vio_dma_iommu_free_coherent,
+	.alloc             = vio_dma_iommu_alloc_coherent,
+	.free              = vio_dma_iommu_free_coherent,
 	.map_sg            = vio_dma_iommu_map_sg,
 	.unmap_sg          = vio_dma_iommu_unmap_sg,
 	.map_page          = vio_dma_iommu_map_page,
@@ -1159,17 +1161,21 @@ static int vio_bus_remove(struct device *dev)
  * vio_register_driver: - Register a new vio driver
  * @drv:	The vio_driver structure to be registered.
  */
-int vio_register_driver(struct vio_driver *viodrv)
+int __vio_register_driver(struct vio_driver *viodrv, struct module *owner,
+			  const char *mod_name)
 {
-	printk(KERN_DEBUG "%s: driver %s registering\n", __func__,
-		viodrv->driver.name);
+	pr_debug("%s: driver %s registering\n", __func__, viodrv->name);
 
 	/* fill in 'struct driver' fields */
+	viodrv->driver.name = viodrv->name;
+	viodrv->driver.pm = viodrv->pm;
 	viodrv->driver.bus = &vio_bus_type;
+	viodrv->driver.owner = owner;
+	viodrv->driver.mod_name = mod_name;
 
 	return driver_register(&viodrv->driver);
 }
-EXPORT_SYMBOL(vio_register_driver);
+EXPORT_SYMBOL(__vio_register_driver);
 
 /**
  * vio_unregister_driver - Remove registration of vio driver.
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 78133deb4b64..8f64709ae331 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -69,6 +69,7 @@ config KVM_BOOK3S_64
 config KVM_BOOK3S_64_HV
 	bool "KVM support for POWER7 and PPC970 using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
+	select MMU_NOTIFIER
 	---help---
 	  Support running unmodified book3s_64 guest kernels in
 	  virtual machines on POWER7 and PPC970 processors that have
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index e41ac6f7dcf1..7d54f4ed6d96 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -258,7 +258,7 @@ static bool clear_irqprio(struct kvm_vcpu *vcpu, unsigned int priority)
 	return true;
 }
 
-void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
+void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 {
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
 	unsigned long old_pending = vcpu->arch.pending_exceptions;
@@ -423,10 +423,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->sprg1 = vcpu->arch.shared->sprg1;
 	regs->sprg2 = vcpu->arch.shared->sprg2;
 	regs->sprg3 = vcpu->arch.shared->sprg3;
-	regs->sprg4 = vcpu->arch.sprg4;
-	regs->sprg5 = vcpu->arch.sprg5;
-	regs->sprg6 = vcpu->arch.sprg6;
-	regs->sprg7 = vcpu->arch.sprg7;
+	regs->sprg4 = vcpu->arch.shared->sprg4;
+	regs->sprg5 = vcpu->arch.shared->sprg5;
+	regs->sprg6 = vcpu->arch.shared->sprg6;
+	regs->sprg7 = vcpu->arch.shared->sprg7;
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
@@ -450,10 +450,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	vcpu->arch.shared->sprg1 = regs->sprg1;
 	vcpu->arch.shared->sprg2 = regs->sprg2;
 	vcpu->arch.shared->sprg3 = regs->sprg3;
-	vcpu->arch.sprg4 = regs->sprg4;
-	vcpu->arch.sprg5 = regs->sprg5;
-	vcpu->arch.sprg6 = regs->sprg6;
-	vcpu->arch.sprg7 = regs->sprg7;
+	vcpu->arch.shared->sprg4 = regs->sprg4;
+	vcpu->arch.shared->sprg5 = regs->sprg5;
+	vcpu->arch.shared->sprg6 = regs->sprg6;
+	vcpu->arch.shared->sprg7 = regs->sprg7;
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
@@ -477,41 +477,10 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-/*
- * Get (and clear) the dirty memory log for a memory slot.
- */
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
-				      struct kvm_dirty_log *log)
+void kvmppc_decrementer_func(unsigned long data)
 {
-	struct kvm_memory_slot *memslot;
-	struct kvm_vcpu *vcpu;
-	ulong ga, ga_end;
-	int is_dirty = 0;
-	int r;
-	unsigned long n;
-
-	mutex_lock(&kvm->slots_lock);
-
-	r = kvm_get_dirty_log(kvm, log, &is_dirty);
-	if (r)
-		goto out;
-
-	/* If nothing is dirty, don't bother messing with page tables. */
-	if (is_dirty) {
-		memslot = id_to_memslot(kvm->memslots, log->slot);
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
 
-		ga = memslot->base_gfn << PAGE_SHIFT;
-		ga_end = ga + (memslot->npages << PAGE_SHIFT);
-
-		kvm_for_each_vcpu(n, vcpu, kvm)
-			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
-
-		n = kvm_dirty_bitmap_bytes(memslot);
-		memset(memslot->dirty_bitmap, 0, n);
-	}
-
-	r = 0;
-out:
-	mutex_unlock(&kvm->slots_lock);
-	return r;
+	kvmppc_core_queue_dec(vcpu);
+	kvm_vcpu_kick(vcpu);
 }
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 9fecbfbce773..f922c29bb234 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -151,13 +151,15 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	bool primary = false;
 	bool evict = false;
 	struct hpte_cache *pte;
+	int r = 0;
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
 	if (is_error_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
 				 orig_pte->eaddr);
-		return -EINVAL;
+		r = -EINVAL;
+		goto out;
 	}
 	hpaddr <<= PAGE_SHIFT;
 
@@ -249,7 +251,8 @@ next_pteg:
 
 	kvmppc_mmu_hpte_cache_map(vcpu, pte);
 
-	return 0;
+out:
+	return r;
 }
 
 static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
@@ -297,12 +300,14 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 	u64 gvsid;
 	u32 sr;
 	struct kvmppc_sid_map *map;
-	struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	int r = 0;
 
 	if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
 		/* Invalidate an entry */
 		svcpu->sr[esid] = SR_INVALID;
-		return -ENOENT;
+		r = -ENOENT;
+		goto out;
 	}
 
 	map = find_sid_vsid(vcpu, gvsid);
@@ -315,17 +320,21 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 
 	dprintk_sr("MMU: mtsr %d, 0x%x\n", esid, sr);
 
-	return 0;
+out:
+	svcpu_put(svcpu);
+	return r;
 }
 
 void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 {
 	int i;
-	struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 
 	dprintk_sr("MMU: flushing all segments (%d)\n", ARRAY_SIZE(svcpu->sr));
 	for (i = 0; i < ARRAY_SIZE(svcpu->sr); i++)
 		svcpu->sr[i] = SR_INVALID;
+
+	svcpu_put(svcpu);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index fa2f08434ba5..6f87f39a1ac2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -88,12 +88,14 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	int vflags = 0;
 	int attempt = 0;
 	struct kvmppc_sid_map *map;
+	int r = 0;
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
 	if (is_error_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
-		return -EINVAL;
+		r = -EINVAL;
+		goto out;
 	}
 	hpaddr <<= PAGE_SHIFT;
 	hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
@@ -110,7 +112,8 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 		printk(KERN_ERR "KVM: Segment map for 0x%llx (0x%lx) failed\n",
 				vsid, orig_pte->eaddr);
 		WARN_ON(true);
-		return -EINVAL;
+		r = -EINVAL;
+		goto out;
 	}
 
 	vsid = map->host_vsid;
@@ -131,8 +134,10 @@ map_again:
 
 	/* In case we tried normal mapping already, let's nuke old entries */
 	if (attempt > 1)
-		if (ppc_md.hpte_remove(hpteg) < 0)
-			return -1;
+		if (ppc_md.hpte_remove(hpteg) < 0) {
+			r = -1;
+			goto out;
+		}
 
 	ret = ppc_md.hpte_insert(hpteg, va, hpaddr, rflags, vflags, MMU_PAGE_4K, MMU_SEGSIZE_256M);
 
@@ -162,7 +167,8 @@ map_again:
 		kvmppc_mmu_hpte_cache_map(vcpu, pte);
 	}
 
-	return 0;
+out:
+	return r;
 }
 
 static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
@@ -207,25 +213,30 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 
 static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
 {
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 	int i;
 	int max_slb_size = 64;
 	int found_inval = -1;
 	int r;
 
-	if (!to_svcpu(vcpu)->slb_max)
-		to_svcpu(vcpu)->slb_max = 1;
+	if (!svcpu->slb_max)
+		svcpu->slb_max = 1;
 
 	/* Are we overwriting? */
-	for (i = 1; i < to_svcpu(vcpu)->slb_max; i++) {
-		if (!(to_svcpu(vcpu)->slb[i].esid & SLB_ESID_V))
+	for (i = 1; i < svcpu->slb_max; i++) {
+		if (!(svcpu->slb[i].esid & SLB_ESID_V))
 			found_inval = i;
-		else if ((to_svcpu(vcpu)->slb[i].esid & ESID_MASK) == esid)
-			return i;
+		else if ((svcpu->slb[i].esid & ESID_MASK) == esid) {
+			r = i;
+			goto out;
+		}
 	}
 
 	/* Found a spare entry that was invalidated before */
-	if (found_inval > 0)
-		return found_inval;
+	if (found_inval > 0) {
+		r = found_inval;
+		goto out;
+	}
 
 	/* No spare invalid entry, so create one */
 
@@ -233,30 +244,35 @@ static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
 		max_slb_size = mmu_slb_size;
 
 	/* Overflowing -> purge */
-	if ((to_svcpu(vcpu)->slb_max) == max_slb_size)
+	if ((svcpu->slb_max) == max_slb_size)
 		kvmppc_mmu_flush_segments(vcpu);
 
-	r = to_svcpu(vcpu)->slb_max;
-	to_svcpu(vcpu)->slb_max++;
+	r = svcpu->slb_max;
+	svcpu->slb_max++;
 
+out:
+	svcpu_put(svcpu);
 	return r;
 }
 
 int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 {
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 	u64 esid = eaddr >> SID_SHIFT;
 	u64 slb_esid = (eaddr & ESID_MASK) | SLB_ESID_V;
 	u64 slb_vsid = SLB_VSID_USER;
 	u64 gvsid;
 	int slb_index;
 	struct kvmppc_sid_map *map;
+	int r = 0;
 
 	slb_index = kvmppc_mmu_next_segment(vcpu, eaddr & ESID_MASK);
 
 	if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
 		/* Invalidate an entry */
-		to_svcpu(vcpu)->slb[slb_index].esid = 0;
-		return -ENOENT;
+		svcpu->slb[slb_index].esid = 0;
+		r = -ENOENT;
+		goto out;
 	}
 
 	map = find_sid_vsid(vcpu, gvsid);
@@ -269,18 +285,22 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 	slb_vsid &= ~SLB_VSID_KP;
 	slb_esid |= slb_index;
 
-	to_svcpu(vcpu)->slb[slb_index].esid = slb_esid;
-	to_svcpu(vcpu)->slb[slb_index].vsid = slb_vsid;
+	svcpu->slb[slb_index].esid = slb_esid;
+	svcpu->slb[slb_index].vsid = slb_vsid;
 
 	trace_kvm_book3s_slbmte(slb_vsid, slb_esid);
 
-	return 0;
+out:
+	svcpu_put(svcpu);
+	return r;
 }
 
 void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 {
-	to_svcpu(vcpu)->slb_max = 1;
-	to_svcpu(vcpu)->slb[0].esid = 0;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->slb_max = 1;
+	svcpu->slb[0].esid = 0;
+	svcpu_put(svcpu);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index bc3a2ea94217..ddc485a529f2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -23,6 +23,7 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
+#include <linux/vmalloc.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -33,15 +34,6 @@
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER	24
-#define HPT_NPTEG	(1ul << (HPT_ORDER - 7))	/* 128B per pteg */
-#define HPT_HASH_MASK	(HPT_NPTEG - 1)
-
-/* Pages in the VRMA are 16MB pages */
-#define VRMA_PAGE_ORDER	24
-#define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
-
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970	63
 #define NR_LPIDS	(LPID_RSVD + 1)
@@ -51,21 +43,41 @@ long kvmppc_alloc_hpt(struct kvm *kvm)
 {
 	unsigned long hpt;
 	unsigned long lpid;
+	struct revmap_entry *rev;
+	struct kvmppc_linear_info *li;
+
+	/* Allocate guest's hashed page table */
+	li = kvm_alloc_hpt();
+	if (li) {
+		/* using preallocated memory */
+		hpt = (ulong)li->base_virt;
+		kvm->arch.hpt_li = li;
+	} else {
+		/* using dynamic memory */
+		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
+				       __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT);
+	}
 
-	hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|__GFP_NOWARN,
-			       HPT_ORDER - PAGE_SHIFT);
 	if (!hpt) {
 		pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
 		return -ENOMEM;
 	}
 	kvm->arch.hpt_virt = hpt;
 
+	/* Allocate reverse map array */
+	rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE);
+	if (!rev) {
+		pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n");
+		goto out_freehpt;
+	}
+	kvm->arch.revmap = rev;
+
+	/* Allocate the guest's logical partition ID */
 	do {
 		lpid = find_first_zero_bit(lpid_inuse, NR_LPIDS);
 		if (lpid >= NR_LPIDS) {
 			pr_err("kvm_alloc_hpt: No LPIDs free\n");
-			free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
-			return -ENOMEM;
+			goto out_freeboth;
 		}
 	} while (test_and_set_bit(lpid, lpid_inuse));
 
@@ -74,37 +86,64 @@ long kvmppc_alloc_hpt(struct kvm *kvm)
 
 	pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid);
 	return 0;
+
+ out_freeboth:
+	vfree(rev);
+ out_freehpt:
+	free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
+	return -ENOMEM;
 }
 
 void kvmppc_free_hpt(struct kvm *kvm)
 {
 	clear_bit(kvm->arch.lpid, lpid_inuse);
-	free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+	vfree(kvm->arch.revmap);
+	if (kvm->arch.hpt_li)
+		kvm_release_hpt(kvm->arch.hpt_li);
+	else
+		free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+}
+
+/* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
+static inline unsigned long hpte0_pgsize_encoding(unsigned long pgsize)
+{
+	return (pgsize > 0x1000) ? HPTE_V_LARGE : 0;
+}
+
+/* Bits in second HPTE dword for pagesize 4k, 64k or 16M */
+static inline unsigned long hpte1_pgsize_encoding(unsigned long pgsize)
+{
+	return (pgsize == 0x10000) ? 0x1000 : 0;
 }
 
-void kvmppc_map_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem)
+void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
+		     unsigned long porder)
 {
 	unsigned long i;
-	unsigned long npages = kvm->arch.ram_npages;
-	unsigned long pfn;
-	unsigned long *hpte;
-	unsigned long hash;
-	struct kvmppc_pginfo *pginfo = kvm->arch.ram_pginfo;
+	unsigned long npages;
+	unsigned long hp_v, hp_r;
+	unsigned long addr, hash;
+	unsigned long psize;
+	unsigned long hp0, hp1;
+	long ret;
 
-	if (!pginfo)
-		return;
+	psize = 1ul << porder;
+	npages = memslot->npages >> (porder - PAGE_SHIFT);
 
 	/* VRMA can't be > 1TB */
-	if (npages > 1ul << (40 - kvm->arch.ram_porder))
-		npages = 1ul << (40 - kvm->arch.ram_porder);
+	if (npages > 1ul << (40 - porder))
+		npages = 1ul << (40 - porder);
 	/* Can't use more than 1 HPTE per HPTEG */
 	if (npages > HPT_NPTEG)
 		npages = HPT_NPTEG;
 
+	hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
+		HPTE_V_BOLTED | hpte0_pgsize_encoding(psize);
+	hp1 = hpte1_pgsize_encoding(psize) |
+		HPTE_R_R | HPTE_R_C | HPTE_R_M | PP_RWXX;
+
 	for (i = 0; i < npages; ++i) {
-		pfn = pginfo[i].pfn;
-		if (!pfn)
-			break;
+		addr = i << porder;
 		/* can't use hpt_hash since va > 64 bits */
 		hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK;
 		/*
@@ -113,15 +152,15 @@ void kvmppc_map_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem)
 		 * at most one HPTE per HPTEG, we just assume entry 7
 		 * is available and use it.
 		 */
-		hpte = (unsigned long *) (kvm->arch.hpt_virt + (hash << 7));
-		hpte += 7 * 2;
-		/* HPTE low word - RPN, protection, etc. */
-		hpte[1] = (pfn << PAGE_SHIFT) | HPTE_R_R | HPTE_R_C |
-			HPTE_R_M | PP_RWXX;
-		wmb();
-		hpte[0] = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
-			(i << (VRMA_PAGE_ORDER - 16)) | HPTE_V_BOLTED |
-			HPTE_V_LARGE | HPTE_V_VALID;
+		hash = (hash << 3) + 7;
+		hp_v = hp0 | ((addr >> 16) & ~0x7fUL);
+		hp_r = hp1 | addr;
+		ret = kvmppc_virtmode_h_enter(vcpu, H_EXACT, hash, hp_v, hp_r);
+		if (ret != H_SUCCESS) {
+			pr_err("KVM: map_vrma at %lx failed, ret=%ld\n",
+			       addr, ret);
+			break;
+		}
 	}
 }
 
@@ -158,10 +197,814 @@ static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
 }
 
+/*
+ * This is called to get a reference to a guest page if there isn't
+ * one already in the kvm->arch.slot_phys[][] arrays.
+ */
+static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
+				  struct kvm_memory_slot *memslot,
+				  unsigned long psize)
+{
+	unsigned long start;
+	long np, err;
+	struct page *page, *hpage, *pages[1];
+	unsigned long s, pgsize;
+	unsigned long *physp;
+	unsigned int is_io, got, pgorder;
+	struct vm_area_struct *vma;
+	unsigned long pfn, i, npages;
+
+	physp = kvm->arch.slot_phys[memslot->id];
+	if (!physp)
+		return -EINVAL;
+	if (physp[gfn - memslot->base_gfn])
+		return 0;
+
+	is_io = 0;
+	got = 0;
+	page = NULL;
+	pgsize = psize;
+	err = -EINVAL;
+	start = gfn_to_hva_memslot(memslot, gfn);
+
+	/* Instantiate and get the page we want access to */
+	np = get_user_pages_fast(start, 1, 1, pages);
+	if (np != 1) {
+		/* Look up the vma for the page */
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma(current->mm, start);
+		if (!vma || vma->vm_start > start ||
+		    start + psize > vma->vm_end ||
+		    !(vma->vm_flags & VM_PFNMAP))
+			goto up_err;
+		is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
+		pfn = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+		/* check alignment of pfn vs. requested page size */
+		if (psize > PAGE_SIZE && (pfn & ((psize >> PAGE_SHIFT) - 1)))
+			goto up_err;
+		up_read(&current->mm->mmap_sem);
+
+	} else {
+		page = pages[0];
+		got = KVMPPC_GOT_PAGE;
+
+		/* See if this is a large page */
+		s = PAGE_SIZE;
+		if (PageHuge(page)) {
+			hpage = compound_head(page);
+			s <<= compound_order(hpage);
+			/* Get the whole large page if slot alignment is ok */
+			if (s > psize && slot_is_aligned(memslot, s) &&
+			    !(memslot->userspace_addr & (s - 1))) {
+				start &= ~(s - 1);
+				pgsize = s;
+				page = hpage;
+			}
+		}
+		if (s < psize)
+			goto out;
+		pfn = page_to_pfn(page);
+	}
+
+	npages = pgsize >> PAGE_SHIFT;
+	pgorder = __ilog2(npages);
+	physp += (gfn - memslot->base_gfn) & ~(npages - 1);
+	spin_lock(&kvm->arch.slot_phys_lock);
+	for (i = 0; i < npages; ++i) {
+		if (!physp[i]) {
+			physp[i] = ((pfn + i) << PAGE_SHIFT) +
+				got + is_io + pgorder;
+			got = 0;
+		}
+	}
+	spin_unlock(&kvm->arch.slot_phys_lock);
+	err = 0;
+
+ out:
+	if (got) {
+		if (PageHuge(page))
+			page = compound_head(page);
+		put_page(page);
+	}
+	return err;
+
+ up_err:
+	up_read(&current->mm->mmap_sem);
+	return err;
+}
+
+/*
+ * We come here on a H_ENTER call from the guest when we are not
+ * using mmu notifiers and we don't have the requested page pinned
+ * already.
+ */
+long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+			long pte_index, unsigned long pteh, unsigned long ptel)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long psize, gpa, gfn;
+	struct kvm_memory_slot *memslot;
+	long ret;
+
+	if (kvm->arch.using_mmu_notifiers)
+		goto do_insert;
+
+	psize = hpte_page_size(pteh, ptel);
+	if (!psize)
+		return H_PARAMETER;
+
+	pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
+
+	/* Find the memslot (if any) for this address */
+	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
+	gfn = gpa >> PAGE_SHIFT;
+	memslot = gfn_to_memslot(kvm, gfn);
+	if (memslot && !(memslot->flags & KVM_MEMSLOT_INVALID)) {
+		if (!slot_is_aligned(memslot, psize))
+			return H_PARAMETER;
+		if (kvmppc_get_guest_page(kvm, gfn, memslot, psize) < 0)
+			return H_PARAMETER;
+	}
+
+ do_insert:
+	/* Protect linux PTE lookup from page table destruction */
+	rcu_read_lock_sched();	/* this disables preemption too */
+	vcpu->arch.pgdir = current->mm->pgd;
+	ret = kvmppc_h_enter(vcpu, flags, pte_index, pteh, ptel);
+	rcu_read_unlock_sched();
+	if (ret == H_TOO_HARD) {
+		/* this can't happen */
+		pr_err("KVM: Oops, kvmppc_h_enter returned too hard!\n");
+		ret = H_RESOURCE;	/* or something */
+	}
+	return ret;
+
+}
+
+static struct kvmppc_slb *kvmppc_mmu_book3s_hv_find_slbe(struct kvm_vcpu *vcpu,
+							 gva_t eaddr)
+{
+	u64 mask;
+	int i;
+
+	for (i = 0; i < vcpu->arch.slb_nr; i++) {
+		if (!(vcpu->arch.slb[i].orige & SLB_ESID_V))
+			continue;
+
+		if (vcpu->arch.slb[i].origv & SLB_VSID_B_1T)
+			mask = ESID_MASK_1T;
+		else
+			mask = ESID_MASK;
+
+		if (((vcpu->arch.slb[i].orige ^ eaddr) & mask) == 0)
+			return &vcpu->arch.slb[i];
+	}
+	return NULL;
+}
+
+static unsigned long kvmppc_mmu_get_real_addr(unsigned long v, unsigned long r,
+			unsigned long ea)
+{
+	unsigned long ra_mask;
+
+	ra_mask = hpte_page_size(v, r) - 1;
+	return (r & HPTE_R_RPN & ~ra_mask) | (ea & ra_mask);
+}
+
 static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-				struct kvmppc_pte *gpte, bool data)
+			struct kvmppc_pte *gpte, bool data)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvmppc_slb *slbe;
+	unsigned long slb_v;
+	unsigned long pp, key;
+	unsigned long v, gr;
+	unsigned long *hptep;
+	int index;
+	int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
+
+	/* Get SLB entry */
+	if (virtmode) {
+		slbe = kvmppc_mmu_book3s_hv_find_slbe(vcpu, eaddr);
+		if (!slbe)
+			return -EINVAL;
+		slb_v = slbe->origv;
+	} else {
+		/* real mode access */
+		slb_v = vcpu->kvm->arch.vrma_slb_v;
+	}
+
+	/* Find the HPTE in the hash table */
+	index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
+					 HPTE_V_VALID | HPTE_V_ABSENT);
+	if (index < 0)
+		return -ENOENT;
+	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
+	v = hptep[0] & ~HPTE_V_HVLOCK;
+	gr = kvm->arch.revmap[index].guest_rpte;
+
+	/* Unlock the HPTE */
+	asm volatile("lwsync" : : : "memory");
+	hptep[0] = v;
+
+	gpte->eaddr = eaddr;
+	gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
+
+	/* Get PP bits and key for permission check */
+	pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
+	key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
+	key &= slb_v;
+
+	/* Calculate permissions */
+	gpte->may_read = hpte_read_permission(pp, key);
+	gpte->may_write = hpte_write_permission(pp, key);
+	gpte->may_execute = gpte->may_read && !(gr & (HPTE_R_N | HPTE_R_G));
+
+	/* Storage key permission check for POWER7 */
+	if (data && virtmode && cpu_has_feature(CPU_FTR_ARCH_206)) {
+		int amrfield = hpte_get_skey_perm(gr, vcpu->arch.amr);
+		if (amrfield & 1)
+			gpte->may_read = 0;
+		if (amrfield & 2)
+			gpte->may_write = 0;
+	}
+
+	/* Get the guest physical address */
+	gpte->raddr = kvmppc_mmu_get_real_addr(v, gr, eaddr);
+	return 0;
+}
+
+/*
+ * Quick test for whether an instruction is a load or a store.
+ * If the instruction is a load or a store, then this will indicate
+ * which it is, at least on server processors.  (Embedded processors
+ * have some external PID instructions that don't follow the rule
+ * embodied here.)  If the instruction isn't a load or store, then
+ * this doesn't return anything useful.
+ */
+static int instruction_is_store(unsigned int instr)
+{
+	unsigned int mask;
+
+	mask = 0x10000000;
+	if ((instr & 0xfc000000) == 0x7c000000)
+		mask = 0x100;		/* major opcode 31 */
+	return (instr & mask) != 0;
+}
+
+static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				  unsigned long gpa, int is_store)
+{
+	int ret;
+	u32 last_inst;
+	unsigned long srr0 = kvmppc_get_pc(vcpu);
+
+	/* We try to load the last instruction.  We don't let
+	 * emulate_instruction do it as it doesn't check what
+	 * kvmppc_ld returns.
+	 * If we fail, we just return to the guest and try executing it again.
+	 */
+	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) {
+		ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
+		if (ret != EMULATE_DONE || last_inst == KVM_INST_FETCH_FAILED)
+			return RESUME_GUEST;
+		vcpu->arch.last_inst = last_inst;
+	}
+
+	/*
+	 * WARNING: We do not know for sure whether the instruction we just
+	 * read from memory is the same that caused the fault in the first
+	 * place.  If the instruction we read is neither an load or a store,
+	 * then it can't access memory, so we don't need to worry about
+	 * enforcing access permissions.  So, assuming it is a load or
+	 * store, we just check that its direction (load or store) is
+	 * consistent with the original fault, since that's what we
+	 * checked the access permissions against.  If there is a mismatch
+	 * we just return and retry the instruction.
+	 */
+
+	if (instruction_is_store(vcpu->arch.last_inst) != !!is_store)
+		return RESUME_GUEST;
+
+	/*
+	 * Emulated accesses are emulated by looking at the hash for
+	 * translation once, then performing the access later. The
+	 * translation could be invalidated in the meantime in which
+	 * point performing the subsequent memory access on the old
+	 * physical address could possibly be a security hole for the
+	 * guest (but not the host).
+	 *
+	 * This is less of an issue for MMIO stores since they aren't
+	 * globally visible. It could be an issue for MMIO loads to
+	 * a certain extent but we'll ignore it for now.
+	 */
+
+	vcpu->arch.paddr_accessed = gpa;
+	return kvmppc_emulate_mmio(run, vcpu);
+}
+
+int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				unsigned long ea, unsigned long dsisr)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long *hptep, hpte[3], r;
+	unsigned long mmu_seq, psize, pte_size;
+	unsigned long gfn, hva, pfn;
+	struct kvm_memory_slot *memslot;
+	unsigned long *rmap;
+	struct revmap_entry *rev;
+	struct page *page, *pages[1];
+	long index, ret, npages;
+	unsigned long is_io;
+	unsigned int writing, write_ok;
+	struct vm_area_struct *vma;
+	unsigned long rcbits;
+
+	/*
+	 * Real-mode code has already searched the HPT and found the
+	 * entry we're interested in.  Lock the entry and check that
+	 * it hasn't changed.  If it has, just return and re-execute the
+	 * instruction.
+	 */
+	if (ea != vcpu->arch.pgfault_addr)
+		return RESUME_GUEST;
+	index = vcpu->arch.pgfault_index;
+	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
+	rev = &kvm->arch.revmap[index];
+	preempt_disable();
+	while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
+		cpu_relax();
+	hpte[0] = hptep[0] & ~HPTE_V_HVLOCK;
+	hpte[1] = hptep[1];
+	hpte[2] = r = rev->guest_rpte;
+	asm volatile("lwsync" : : : "memory");
+	hptep[0] = hpte[0];
+	preempt_enable();
+
+	if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
+	    hpte[1] != vcpu->arch.pgfault_hpte[1])
+		return RESUME_GUEST;
+
+	/* Translate the logical address and get the page */
+	psize = hpte_page_size(hpte[0], r);
+	gfn = hpte_rpn(r, psize);
+	memslot = gfn_to_memslot(kvm, gfn);
+
+	/* No memslot means it's an emulated MMIO region */
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+		unsigned long gpa = (gfn << PAGE_SHIFT) | (ea & (psize - 1));
+		return kvmppc_hv_emulate_mmio(run, vcpu, gpa,
+					      dsisr & DSISR_ISSTORE);
+	}
+
+	if (!kvm->arch.using_mmu_notifiers)
+		return -EFAULT;		/* should never get here */
+
+	/* used to check for invalidations in progress */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	is_io = 0;
+	pfn = 0;
+	page = NULL;
+	pte_size = PAGE_SIZE;
+	writing = (dsisr & DSISR_ISSTORE) != 0;
+	/* If writing != 0, then the HPTE must allow writing, if we get here */
+	write_ok = writing;
+	hva = gfn_to_hva_memslot(memslot, gfn);
+	npages = get_user_pages_fast(hva, 1, writing, pages);
+	if (npages < 1) {
+		/* Check if it's an I/O mapping */
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma(current->mm, hva);
+		if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end &&
+		    (vma->vm_flags & VM_PFNMAP)) {
+			pfn = vma->vm_pgoff +
+				((hva - vma->vm_start) >> PAGE_SHIFT);
+			pte_size = psize;
+			is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
+			write_ok = vma->vm_flags & VM_WRITE;
+		}
+		up_read(&current->mm->mmap_sem);
+		if (!pfn)
+			return -EFAULT;
+	} else {
+		page = pages[0];
+		if (PageHuge(page)) {
+			page = compound_head(page);
+			pte_size <<= compound_order(page);
+		}
+		/* if the guest wants write access, see if that is OK */
+		if (!writing && hpte_is_writable(r)) {
+			pte_t *ptep, pte;
+
+			/*
+			 * We need to protect against page table destruction
+			 * while looking up and updating the pte.
+			 */
+			rcu_read_lock_sched();
+			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
+							 hva, NULL);
+			if (ptep && pte_present(*ptep)) {
+				pte = kvmppc_read_update_linux_pte(ptep, 1);
+				if (pte_write(pte))
+					write_ok = 1;
+			}
+			rcu_read_unlock_sched();
+		}
+		pfn = page_to_pfn(page);
+	}
+
+	ret = -EFAULT;
+	if (psize > pte_size)
+		goto out_put;
+
+	/* Check WIMG vs. the actual page we're accessing */
+	if (!hpte_cache_flags_ok(r, is_io)) {
+		if (is_io)
+			return -EFAULT;
+		/*
+		 * Allow guest to map emulated device memory as
+		 * uncacheable, but actually make it cacheable.
+		 */
+		r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
+	}
+
+	/* Set the HPTE to point to pfn */
+	r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
+	if (hpte_is_writable(r) && !write_ok)
+		r = hpte_make_readonly(r);
+	ret = RESUME_GUEST;
+	preempt_disable();
+	while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
+		cpu_relax();
+	if ((hptep[0] & ~HPTE_V_HVLOCK) != hpte[0] || hptep[1] != hpte[1] ||
+	    rev->guest_rpte != hpte[2])
+		/* HPTE has been changed under us; let the guest retry */
+		goto out_unlock;
+	hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
+
+	rmap = &memslot->rmap[gfn - memslot->base_gfn];
+	lock_rmap(rmap);
+
+	/* Check if we might have been invalidated; let the guest retry if so */
+	ret = RESUME_GUEST;
+	if (mmu_notifier_retry(vcpu, mmu_seq)) {
+		unlock_rmap(rmap);
+		goto out_unlock;
+	}
+
+	/* Only set R/C in real HPTE if set in both *rmap and guest_rpte */
+	rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
+	r &= rcbits | ~(HPTE_R_R | HPTE_R_C);
+
+	if (hptep[0] & HPTE_V_VALID) {
+		/* HPTE was previously valid, so we need to invalidate it */
+		unlock_rmap(rmap);
+		hptep[0] |= HPTE_V_ABSENT;
+		kvmppc_invalidate_hpte(kvm, hptep, index);
+		/* don't lose previous R and C bits */
+		r |= hptep[1] & (HPTE_R_R | HPTE_R_C);
+	} else {
+		kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0);
+	}
+
+	hptep[1] = r;
+	eieio();
+	hptep[0] = hpte[0];
+	asm volatile("ptesync" : : : "memory");
+	preempt_enable();
+	if (page && hpte_is_writable(r))
+		SetPageDirty(page);
+
+ out_put:
+	if (page)
+		put_page(page);
+	return ret;
+
+ out_unlock:
+	hptep[0] &= ~HPTE_V_HVLOCK;
+	preempt_enable();
+	goto out_put;
+}
+
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+					 unsigned long gfn))
+{
+	int ret;
+	int retval = 0;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots) {
+		unsigned long start = memslot->userspace_addr;
+		unsigned long end;
+
+		end = start + (memslot->npages << PAGE_SHIFT);
+		if (hva >= start && hva < end) {
+			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+
+			ret = handler(kvm, &memslot->rmap[gfn_offset],
+				      memslot->base_gfn + gfn_offset);
+			retval |= ret;
+		}
+	}
+
+	return retval;
+}
+
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
+			   unsigned long gfn)
+{
+	struct revmap_entry *rev = kvm->arch.revmap;
+	unsigned long h, i, j;
+	unsigned long *hptep;
+	unsigned long ptel, psize, rcbits;
+
+	for (;;) {
+		lock_rmap(rmapp);
+		if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
+			unlock_rmap(rmapp);
+			break;
+		}
+
+		/*
+		 * To avoid an ABBA deadlock with the HPTE lock bit,
+		 * we can't spin on the HPTE lock while holding the
+		 * rmap chain lock.
+		 */
+		i = *rmapp & KVMPPC_RMAP_INDEX;
+		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
+			/* unlock rmap before spinning on the HPTE lock */
+			unlock_rmap(rmapp);
+			while (hptep[0] & HPTE_V_HVLOCK)
+				cpu_relax();
+			continue;
+		}
+		j = rev[i].forw;
+		if (j == i) {
+			/* chain is now empty */
+			*rmapp &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX);
+		} else {
+			/* remove i from chain */
+			h = rev[i].back;
+			rev[h].forw = j;
+			rev[j].back = h;
+			rev[i].forw = rev[i].back = i;
+			*rmapp = (*rmapp & ~KVMPPC_RMAP_INDEX) | j;
+		}
+
+		/* Now check and modify the HPTE */
+		ptel = rev[i].guest_rpte;
+		psize = hpte_page_size(hptep[0], ptel);
+		if ((hptep[0] & HPTE_V_VALID) &&
+		    hpte_rpn(ptel, psize) == gfn) {
+			hptep[0] |= HPTE_V_ABSENT;
+			kvmppc_invalidate_hpte(kvm, hptep, i);
+			/* Harvest R and C */
+			rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
+			*rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
+			rev[i].guest_rpte = ptel | rcbits;
+		}
+		unlock_rmap(rmapp);
+		hptep[0] &= ~HPTE_V_HVLOCK;
+	}
+	return 0;
+}
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	if (kvm->arch.using_mmu_notifiers)
+		kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+	return 0;
+}
+
+static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+			 unsigned long gfn)
+{
+	struct revmap_entry *rev = kvm->arch.revmap;
+	unsigned long head, i, j;
+	unsigned long *hptep;
+	int ret = 0;
+
+ retry:
+	lock_rmap(rmapp);
+	if (*rmapp & KVMPPC_RMAP_REFERENCED) {
+		*rmapp &= ~KVMPPC_RMAP_REFERENCED;
+		ret = 1;
+	}
+	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
+		unlock_rmap(rmapp);
+		return ret;
+	}
+
+	i = head = *rmapp & KVMPPC_RMAP_INDEX;
+	do {
+		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+		j = rev[i].forw;
+
+		/* If this HPTE isn't referenced, ignore it */
+		if (!(hptep[1] & HPTE_R_R))
+			continue;
+
+		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
+			/* unlock rmap before spinning on the HPTE lock */
+			unlock_rmap(rmapp);
+			while (hptep[0] & HPTE_V_HVLOCK)
+				cpu_relax();
+			goto retry;
+		}
+
+		/* Now check and modify the HPTE */
+		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_R)) {
+			kvmppc_clear_ref_hpte(kvm, hptep, i);
+			rev[i].guest_rpte |= HPTE_R_R;
+			ret = 1;
+		}
+		hptep[0] &= ~HPTE_V_HVLOCK;
+	} while ((i = j) != head);
+
+	unlock_rmap(rmapp);
+	return ret;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	if (!kvm->arch.using_mmu_notifiers)
+		return 0;
+	return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
+}
+
+static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+			      unsigned long gfn)
+{
+	struct revmap_entry *rev = kvm->arch.revmap;
+	unsigned long head, i, j;
+	unsigned long *hp;
+	int ret = 1;
+
+	if (*rmapp & KVMPPC_RMAP_REFERENCED)
+		return 1;
+
+	lock_rmap(rmapp);
+	if (*rmapp & KVMPPC_RMAP_REFERENCED)
+		goto out;
+
+	if (*rmapp & KVMPPC_RMAP_PRESENT) {
+		i = head = *rmapp & KVMPPC_RMAP_INDEX;
+		do {
+			hp = (unsigned long *)(kvm->arch.hpt_virt + (i << 4));
+			j = rev[i].forw;
+			if (hp[1] & HPTE_R_R)
+				goto out;
+		} while ((i = j) != head);
+	}
+	ret = 0;
+
+ out:
+	unlock_rmap(rmapp);
+	return ret;
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	if (!kvm->arch.using_mmu_notifiers)
+		return 0;
+	return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp);
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
-	return -ENOENT;
+	if (!kvm->arch.using_mmu_notifiers)
+		return;
+	kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+}
+
+static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
+{
+	struct revmap_entry *rev = kvm->arch.revmap;
+	unsigned long head, i, j;
+	unsigned long *hptep;
+	int ret = 0;
+
+ retry:
+	lock_rmap(rmapp);
+	if (*rmapp & KVMPPC_RMAP_CHANGED) {
+		*rmapp &= ~KVMPPC_RMAP_CHANGED;
+		ret = 1;
+	}
+	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
+		unlock_rmap(rmapp);
+		return ret;
+	}
+
+	i = head = *rmapp & KVMPPC_RMAP_INDEX;
+	do {
+		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+		j = rev[i].forw;
+
+		if (!(hptep[1] & HPTE_R_C))
+			continue;
+
+		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
+			/* unlock rmap before spinning on the HPTE lock */
+			unlock_rmap(rmapp);
+			while (hptep[0] & HPTE_V_HVLOCK)
+				cpu_relax();
+			goto retry;
+		}
+
+		/* Now check and modify the HPTE */
+		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_C)) {
+			/* need to make it temporarily absent to clear C */
+			hptep[0] |= HPTE_V_ABSENT;
+			kvmppc_invalidate_hpte(kvm, hptep, i);
+			hptep[1] &= ~HPTE_R_C;
+			eieio();
+			hptep[0] = (hptep[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
+			rev[i].guest_rpte |= HPTE_R_C;
+			ret = 1;
+		}
+		hptep[0] &= ~HPTE_V_HVLOCK;
+	} while ((i = j) != head);
+
+	unlock_rmap(rmapp);
+	return ret;
+}
+
+long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	unsigned long i;
+	unsigned long *rmapp, *map;
+
+	preempt_disable();
+	rmapp = memslot->rmap;
+	map = memslot->dirty_bitmap;
+	for (i = 0; i < memslot->npages; ++i) {
+		if (kvm_test_clear_dirty(kvm, rmapp))
+			__set_bit_le(i, map);
+		++rmapp;
+	}
+	preempt_enable();
+	return 0;
+}
+
+void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
+			    unsigned long *nb_ret)
+{
+	struct kvm_memory_slot *memslot;
+	unsigned long gfn = gpa >> PAGE_SHIFT;
+	struct page *page, *pages[1];
+	int npages;
+	unsigned long hva, psize, offset;
+	unsigned long pa;
+	unsigned long *physp;
+
+	memslot = gfn_to_memslot(kvm, gfn);
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+		return NULL;
+	if (!kvm->arch.using_mmu_notifiers) {
+		physp = kvm->arch.slot_phys[memslot->id];
+		if (!physp)
+			return NULL;
+		physp += gfn - memslot->base_gfn;
+		pa = *physp;
+		if (!pa) {
+			if (kvmppc_get_guest_page(kvm, gfn, memslot,
+						  PAGE_SIZE) < 0)
+				return NULL;
+			pa = *physp;
+		}
+		page = pfn_to_page(pa >> PAGE_SHIFT);
+	} else {
+		hva = gfn_to_hva_memslot(memslot, gfn);
+		npages = get_user_pages_fast(hva, 1, 1, pages);
+		if (npages < 1)
+			return NULL;
+		page = pages[0];
+	}
+	psize = PAGE_SIZE;
+	if (PageHuge(page)) {
+		page = compound_head(page);
+		psize <<= compound_order(page);
+	}
+	if (!kvm->arch.using_mmu_notifiers)
+		get_page(page);
+	offset = gpa & (psize - 1);
+	if (nb_ret)
+		*nb_ret = psize - offset;
+	return page_address(page) + offset;
+}
+
+void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
+{
+	struct page *page = virt_to_page(va);
+
+	page = compound_head(page);
+	put_page(page);
 }
 
 void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 0c9dc62532d0..135663a3e4fc 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -21,6 +21,7 @@
 #include <asm/disassemble.h>
 #include <asm/kvm_book3s.h>
 #include <asm/reg.h>
+#include <asm/switch_to.h>
 
 #define OP_19_XOP_RFID		18
 #define OP_19_XOP_RFI		50
@@ -230,9 +231,12 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 			r = kvmppc_st(vcpu, &addr, 32, zeros, true);
 			if ((r == -ENOENT) || (r == -EPERM)) {
+				struct kvmppc_book3s_shadow_vcpu *svcpu;
+
+				svcpu = svcpu_get(vcpu);
 				*advance = 0;
 				vcpu->arch.shared->dar = vaddr;
-				to_svcpu(vcpu)->fault_dar = vaddr;
+				svcpu->fault_dar = vaddr;
 
 				dsisr = DSISR_ISSTORE;
 				if (r == -ENOENT)
@@ -241,7 +245,8 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 					dsisr |= DSISR_PROTFAULT;
 
 				vcpu->arch.shared->dsisr = dsisr;
-				to_svcpu(vcpu)->fault_dsisr = dsisr;
+				svcpu->fault_dsisr = dsisr;
+				svcpu_put(svcpu);
 
 				kvmppc_book3s_queue_irqprio(vcpu,
 					BOOK3S_INTERRUPT_DATA_STORAGE);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a7267167a550..01294a5099dd 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -45,25 +45,18 @@
 #include <asm/cputhreads.h>
 #include <asm/page.h>
 #include <asm/hvcall.h>
+#include <asm/switch_to.h>
 #include <linux/gfp.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
-
-/*
- * For now, limit memory to 64GB and require it to be large pages.
- * This value is chosen because it makes the ram_pginfo array be
- * 64kB in size, which is about as large as we want to be trying
- * to allocate with kmalloc.
- */
-#define MAX_MEM_ORDER		36
-
-#define LARGE_PAGE_ORDER	24	/* 16MB pages */
+#include <linux/hugetlb.h>
 
 /* #define EXIT_DEBUG */
 /* #define EXIT_DEBUG_SIMPLE */
 /* #define EXIT_DEBUG_INT */
 
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
+static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu);
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
@@ -146,10 +139,10 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 				       unsigned long vcpuid, unsigned long vpa)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long pg_index, ra, len;
-	unsigned long pg_offset;
+	unsigned long len, nb;
 	void *va;
 	struct kvm_vcpu *tvcpu;
+	int err = H_PARAMETER;
 
 	tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
 	if (!tvcpu)
@@ -162,45 +155,41 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 	if (flags < 4) {
 		if (vpa & 0x7f)
 			return H_PARAMETER;
+		if (flags >= 2 && !tvcpu->arch.vpa)
+			return H_RESOURCE;
 		/* registering new area; convert logical addr to real */
-		pg_index = vpa >> kvm->arch.ram_porder;
-		pg_offset = vpa & (kvm->arch.ram_psize - 1);
-		if (pg_index >= kvm->arch.ram_npages)
+		va = kvmppc_pin_guest_page(kvm, vpa, &nb);
+		if (va == NULL)
 			return H_PARAMETER;
-		if (kvm->arch.ram_pginfo[pg_index].pfn == 0)
-			return H_PARAMETER;
-		ra = kvm->arch.ram_pginfo[pg_index].pfn << PAGE_SHIFT;
-		ra |= pg_offset;
-		va = __va(ra);
 		if (flags <= 1)
 			len = *(unsigned short *)(va + 4);
 		else
 			len = *(unsigned int *)(va + 4);
-		if (pg_offset + len > kvm->arch.ram_psize)
-			return H_PARAMETER;
+		if (len > nb)
+			goto out_unpin;
 		switch (flags) {
 		case 1:		/* register VPA */
 			if (len < 640)
-				return H_PARAMETER;
+				goto out_unpin;
+			if (tvcpu->arch.vpa)
+				kvmppc_unpin_guest_page(kvm, vcpu->arch.vpa);
 			tvcpu->arch.vpa = va;
 			init_vpa(vcpu, va);
 			break;
 		case 2:		/* register DTL */
 			if (len < 48)
-				return H_PARAMETER;
-			if (!tvcpu->arch.vpa)
-				return H_RESOURCE;
+				goto out_unpin;
 			len -= len % 48;
+			if (tvcpu->arch.dtl)
+				kvmppc_unpin_guest_page(kvm, vcpu->arch.dtl);
 			tvcpu->arch.dtl = va;
 			tvcpu->arch.dtl_end = va + len;
 			break;
 		case 3:		/* register SLB shadow buffer */
-			if (len < 8)
-				return H_PARAMETER;
-			if (!tvcpu->arch.vpa)
-				return H_RESOURCE;
-			tvcpu->arch.slb_shadow = va;
-			len = (len - 16) / 16;
+			if (len < 16)
+				goto out_unpin;
+			if (tvcpu->arch.slb_shadow)
+				kvmppc_unpin_guest_page(kvm, vcpu->arch.slb_shadow);
 			tvcpu->arch.slb_shadow = va;
 			break;
 		}
@@ -209,17 +198,30 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 		case 5:		/* unregister VPA */
 			if (tvcpu->arch.slb_shadow || tvcpu->arch.dtl)
 				return H_RESOURCE;
+			if (!tvcpu->arch.vpa)
+				break;
+			kvmppc_unpin_guest_page(kvm, tvcpu->arch.vpa);
 			tvcpu->arch.vpa = NULL;
 			break;
 		case 6:		/* unregister DTL */
+			if (!tvcpu->arch.dtl)
+				break;
+			kvmppc_unpin_guest_page(kvm, tvcpu->arch.dtl);
 			tvcpu->arch.dtl = NULL;
 			break;
 		case 7:		/* unregister SLB shadow buffer */
+			if (!tvcpu->arch.slb_shadow)
+				break;
+			kvmppc_unpin_guest_page(kvm, tvcpu->arch.slb_shadow);
 			tvcpu->arch.slb_shadow = NULL;
 			break;
 		}
 	}
 	return H_SUCCESS;
+
+ out_unpin:
+	kvmppc_unpin_guest_page(kvm, va);
+	return err;
 }
 
 int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
@@ -229,6 +231,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu *tvcpu;
 
 	switch (req) {
+	case H_ENTER:
+		ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4),
+					      kvmppc_get_gpr(vcpu, 5),
+					      kvmppc_get_gpr(vcpu, 6),
+					      kvmppc_get_gpr(vcpu, 7));
+		break;
 	case H_CEDE:
 		break;
 	case H_PROD:
@@ -318,20 +326,19 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 	}
 	/*
-	 * We get these next two if the guest does a bad real-mode access,
-	 * as we have enabled VRMA (virtualized real mode area) mode in the
-	 * LPCR.  We just generate an appropriate DSI/ISI to the guest.
+	 * We get these next two if the guest accesses a page which it thinks
+	 * it has mapped but which is not actually present, either because
+	 * it is for an emulated I/O device or because the corresonding
+	 * host page has been paged out.  Any other HDSI/HISI interrupts
+	 * have been handled already.
 	 */
 	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
-		vcpu->arch.shregs.dsisr = vcpu->arch.fault_dsisr;
-		vcpu->arch.shregs.dar = vcpu->arch.fault_dar;
-		kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, 0);
-		r = RESUME_GUEST;
+		r = kvmppc_book3s_hv_page_fault(run, vcpu,
+				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
 		break;
 	case BOOK3S_INTERRUPT_H_INST_STORAGE:
-		kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE,
-					0x08000000);
-		r = RESUME_GUEST;
+		r = kvmppc_book3s_hv_page_fault(run, vcpu,
+				kvmppc_get_pc(vcpu), 0);
 		break;
 	/*
 	 * This occurs if the guest executes an illegal instruction.
@@ -391,6 +398,42 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_PPC_HIOR:
+		r = put_user(0, (u64 __user *)reg->addr);
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_PPC_HIOR:
+	{
+		u64 hior;
+		/* Only allow this to be set to zero */
+		r = get_user(hior, (u64 __user *)reg->addr);
+		if (!r && (hior != 0))
+			r = -EINVAL;
+		break;
+	}
+	default:
+		break;
+	}
+
+	return r;
+}
+
 int kvmppc_core_check_processor_compat(void)
 {
 	if (cpu_has_feature(CPU_FTR_HVMODE))
@@ -410,7 +453,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 		goto out;
 
 	err = -ENOMEM;
-	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu)
 		goto out;
 
@@ -462,15 +505,21 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	return vcpu;
 
 free_vcpu:
-	kfree(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
 	return ERR_PTR(err);
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	if (vcpu->arch.dtl)
+		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.dtl);
+	if (vcpu->arch.slb_shadow)
+		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.slb_shadow);
+	if (vcpu->arch.vpa)
+		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.vpa);
 	kvm_vcpu_uninit(vcpu);
-	kfree(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
@@ -481,7 +530,7 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
 	if (now > vcpu->arch.dec_expires) {
 		/* decrementer has already gone negative */
 		kvmppc_core_queue_dec(vcpu);
-		kvmppc_core_deliver_interrupts(vcpu);
+		kvmppc_core_prepare_to_enter(vcpu);
 		return;
 	}
 	dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
@@ -796,7 +845,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 		list_for_each_entry_safe(v, vn, &vc->runnable_threads,
 					 arch.run_list) {
-			kvmppc_core_deliver_interrupts(v);
+			kvmppc_core_prepare_to_enter(v);
 			if (signal_pending(v->arch.run_task)) {
 				kvmppc_remove_runnable(vc, v);
 				v->stat.signal_exits++;
@@ -835,20 +884,26 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		return -EINVAL;
 	}
 
+	kvmppc_core_prepare_to_enter(vcpu);
+
 	/* No need to go into the guest when all we'll do is come back out */
 	if (signal_pending(current)) {
 		run->exit_reason = KVM_EXIT_INTR;
 		return -EINTR;
 	}
 
-	/* On PPC970, check that we have an RMA region */
-	if (!vcpu->kvm->arch.rma && cpu_has_feature(CPU_FTR_ARCH_201))
-		return -EPERM;
+	/* On the first time here, set up VRMA or RMA */
+	if (!vcpu->kvm->arch.rma_setup_done) {
+		r = kvmppc_hv_setup_rma(vcpu);
+		if (r)
+			return r;
+	}
 
 	flush_fp_to_thread(current);
 	flush_altivec_to_thread(current);
 	flush_vsx_to_thread(current);
 	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
+	vcpu->arch.pgdir = current->mm->pgd;
 
 	do {
 		r = kvmppc_run_vcpu(run, vcpu);
@@ -856,7 +911,7 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
 		    !(vcpu->arch.shregs.msr & MSR_PR)) {
 			r = kvmppc_pseries_do_hcall(vcpu);
-			kvmppc_core_deliver_interrupts(vcpu);
+			kvmppc_core_prepare_to_enter(vcpu);
 		}
 	} while (r == RESUME_GUEST);
 	return r;
@@ -1000,7 +1055,7 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct kvmppc_rma_info *ri = vma->vm_file->private_data;
+	struct kvmppc_linear_info *ri = vma->vm_file->private_data;
 	struct page *page;
 
 	if (vmf->pgoff >= ri->npages)
@@ -1025,7 +1080,7 @@ static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int kvm_rma_release(struct inode *inode, struct file *filp)
 {
-	struct kvmppc_rma_info *ri = filp->private_data;
+	struct kvmppc_linear_info *ri = filp->private_data;
 
 	kvm_release_rma(ri);
 	return 0;
@@ -1038,7 +1093,7 @@ static struct file_operations kvm_rma_fops = {
 
 long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 {
-	struct kvmppc_rma_info *ri;
+	struct kvmppc_linear_info *ri;
 	long fd;
 
 	ri = kvm_alloc_rma();
@@ -1053,89 +1108,189 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 	return fd;
 }
 
-static struct page *hva_to_page(unsigned long addr)
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
-	struct page *page[1];
-	int npages;
+	struct kvm_memory_slot *memslot;
+	int r;
+	unsigned long n;
 
-	might_sleep();
+	mutex_lock(&kvm->slots_lock);
 
-	npages = get_user_pages_fast(addr, 1, 1, page);
+	r = -EINVAL;
+	if (log->slot >= KVM_MEMORY_SLOTS)
+		goto out;
 
-	if (unlikely(npages != 1))
-		return 0;
+	memslot = id_to_memslot(kvm->memslots, log->slot);
+	r = -ENOENT;
+	if (!memslot->dirty_bitmap)
+		goto out;
+
+	n = kvm_dirty_bitmap_bytes(memslot);
+	memset(memslot->dirty_bitmap, 0, n);
+
+	r = kvmppc_hv_get_dirty_log(kvm, memslot);
+	if (r)
+		goto out;
 
-	return page[0];
+	r = -EFAULT;
+	if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
+		goto out;
+
+	r = 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
+static unsigned long slb_pgsize_encoding(unsigned long psize)
+{
+	unsigned long senc = 0;
+
+	if (psize > 0x1000) {
+		senc = SLB_VSID_L;
+		if (psize == 0x10000)
+			senc |= SLB_VSID_LP_01;
+	}
+	return senc;
 }
 
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem)
 {
-	unsigned long psize, porder;
-	unsigned long i, npages, totalpages;
-	unsigned long pg_ix;
-	struct kvmppc_pginfo *pginfo;
-	unsigned long hva;
-	struct kvmppc_rma_info *ri = NULL;
+	unsigned long npages;
+	unsigned long *phys;
+
+	/* Allocate a slot_phys array */
+	phys = kvm->arch.slot_phys[mem->slot];
+	if (!kvm->arch.using_mmu_notifiers && !phys) {
+		npages = mem->memory_size >> PAGE_SHIFT;
+		phys = vzalloc(npages * sizeof(unsigned long));
+		if (!phys)
+			return -ENOMEM;
+		kvm->arch.slot_phys[mem->slot] = phys;
+		kvm->arch.slot_npages[mem->slot] = npages;
+	}
+
+	return 0;
+}
+
+static void unpin_slot(struct kvm *kvm, int slot_id)
+{
+	unsigned long *physp;
+	unsigned long j, npages, pfn;
 	struct page *page;
 
-	/* For now, only allow 16MB pages */
-	porder = LARGE_PAGE_ORDER;
-	psize = 1ul << porder;
-	if ((mem->memory_size & (psize - 1)) ||
-	    (mem->guest_phys_addr & (psize - 1))) {
-		pr_err("bad memory_size=%llx @ %llx\n",
-		       mem->memory_size, mem->guest_phys_addr);
-		return -EINVAL;
+	physp = kvm->arch.slot_phys[slot_id];
+	npages = kvm->arch.slot_npages[slot_id];
+	if (physp) {
+		spin_lock(&kvm->arch.slot_phys_lock);
+		for (j = 0; j < npages; j++) {
+			if (!(physp[j] & KVMPPC_GOT_PAGE))
+				continue;
+			pfn = physp[j] >> PAGE_SHIFT;
+			page = pfn_to_page(pfn);
+			if (PageHuge(page))
+				page = compound_head(page);
+			SetPageDirty(page);
+			put_page(page);
+		}
+		kvm->arch.slot_phys[slot_id] = NULL;
+		spin_unlock(&kvm->arch.slot_phys_lock);
+		vfree(physp);
 	}
+}
 
-	npages = mem->memory_size >> porder;
-	totalpages = (mem->guest_phys_addr + mem->memory_size) >> porder;
+void kvmppc_core_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem)
+{
+}
 
-	/* More memory than we have space to track? */
-	if (totalpages > (1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER)))
-		return -EINVAL;
+static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
+{
+	int err = 0;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvmppc_linear_info *ri = NULL;
+	unsigned long hva;
+	struct kvm_memory_slot *memslot;
+	struct vm_area_struct *vma;
+	unsigned long lpcr, senc;
+	unsigned long psize, porder;
+	unsigned long rma_size;
+	unsigned long rmls;
+	unsigned long *physp;
+	unsigned long i, npages;
 
-	/* Do we already have an RMA registered? */
-	if (mem->guest_phys_addr == 0 && kvm->arch.rma)
-		return -EINVAL;
+	mutex_lock(&kvm->lock);
+	if (kvm->arch.rma_setup_done)
+		goto out;	/* another vcpu beat us to it */
 
-	if (totalpages > kvm->arch.ram_npages)
-		kvm->arch.ram_npages = totalpages;
+	/* Look up the memslot for guest physical address 0 */
+	memslot = gfn_to_memslot(kvm, 0);
+
+	/* We must have some memory at 0 by now */
+	err = -EINVAL;
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+		goto out;
+
+	/* Look up the VMA for the start of this memory slot */
+	hva = memslot->userspace_addr;
+	down_read(&current->mm->mmap_sem);
+	vma = find_vma(current->mm, hva);
+	if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO))
+		goto up_out;
+
+	psize = vma_kernel_pagesize(vma);
+	porder = __ilog2(psize);
 
 	/* Is this one of our preallocated RMAs? */
-	if (mem->guest_phys_addr == 0) {
-		struct vm_area_struct *vma;
-
-		down_read(&current->mm->mmap_sem);
-		vma = find_vma(current->mm, mem->userspace_addr);
-		if (vma && vma->vm_file &&
-		    vma->vm_file->f_op == &kvm_rma_fops &&
-		    mem->userspace_addr == vma->vm_start)
-			ri = vma->vm_file->private_data;
-		up_read(&current->mm->mmap_sem);
-		if (!ri && cpu_has_feature(CPU_FTR_ARCH_201)) {
-			pr_err("CPU requires an RMO\n");
-			return -EINVAL;
+	if (vma->vm_file && vma->vm_file->f_op == &kvm_rma_fops &&
+	    hva == vma->vm_start)
+		ri = vma->vm_file->private_data;
+
+	up_read(&current->mm->mmap_sem);
+
+	if (!ri) {
+		/* On POWER7, use VRMA; on PPC970, give up */
+		err = -EPERM;
+		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
+			pr_err("KVM: CPU requires an RMO\n");
+			goto out;
 		}
-	}
 
-	if (ri) {
-		unsigned long rma_size;
-		unsigned long lpcr;
-		long rmls;
+		/* We can handle 4k, 64k or 16M pages in the VRMA */
+		err = -EINVAL;
+		if (!(psize == 0x1000 || psize == 0x10000 ||
+		      psize == 0x1000000))
+			goto out;
+
+		/* Update VRMASD field in the LPCR */
+		senc = slb_pgsize_encoding(psize);
+		kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
+			(VRMA_VSID << SLB_VSID_SHIFT_1T);
+		lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
+		lpcr |= senc << (LPCR_VRMASD_SH - 4);
+		kvm->arch.lpcr = lpcr;
 
-		rma_size = ri->npages << PAGE_SHIFT;
-		if (rma_size > mem->memory_size)
-			rma_size = mem->memory_size;
+		/* Create HPTEs in the hash page table for the VRMA */
+		kvmppc_map_vrma(vcpu, memslot, porder);
+
+	} else {
+		/* Set up to use an RMO region */
+		rma_size = ri->npages;
+		if (rma_size > memslot->npages)
+			rma_size = memslot->npages;
+		rma_size <<= PAGE_SHIFT;
 		rmls = lpcr_rmls(rma_size);
+		err = -EINVAL;
 		if (rmls < 0) {
-			pr_err("Can't use RMA of 0x%lx bytes\n", rma_size);
-			return -EINVAL;
+			pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
+			goto out;
 		}
 		atomic_inc(&ri->use_count);
 		kvm->arch.rma = ri;
-		kvm->arch.n_rma_pages = rma_size >> porder;
 
 		/* Update LPCR and RMOR */
 		lpcr = kvm->arch.lpcr;
@@ -1155,53 +1310,35 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 			kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT;
 		}
 		kvm->arch.lpcr = lpcr;
-		pr_info("Using RMO at %lx size %lx (LPCR = %lx)\n",
+		pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
 			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
-	}
 
-	pg_ix = mem->guest_phys_addr >> porder;
-	pginfo = kvm->arch.ram_pginfo + pg_ix;
-	for (i = 0; i < npages; ++i, ++pg_ix) {
-		if (ri && pg_ix < kvm->arch.n_rma_pages) {
-			pginfo[i].pfn = ri->base_pfn +
-				(pg_ix << (porder - PAGE_SHIFT));
-			continue;
-		}
-		hva = mem->userspace_addr + (i << porder);
-		page = hva_to_page(hva);
-		if (!page) {
-			pr_err("oops, no pfn for hva %lx\n", hva);
-			goto err;
-		}
-		/* Check it's a 16MB page */
-		if (!PageHead(page) ||
-		    compound_order(page) != (LARGE_PAGE_ORDER - PAGE_SHIFT)) {
-			pr_err("page at %lx isn't 16MB (o=%d)\n",
-			       hva, compound_order(page));
-			goto err;
-		}
-		pginfo[i].pfn = page_to_pfn(page);
+		/* Initialize phys addrs of pages in RMO */
+		npages = ri->npages;
+		porder = __ilog2(npages);
+		physp = kvm->arch.slot_phys[memslot->id];
+		spin_lock(&kvm->arch.slot_phys_lock);
+		for (i = 0; i < npages; ++i)
+			physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) + porder;
+		spin_unlock(&kvm->arch.slot_phys_lock);
 	}
 
-	return 0;
-
- err:
-	return -EINVAL;
-}
+	/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
+	smp_wmb();
+	kvm->arch.rma_setup_done = 1;
+	err = 0;
+ out:
+	mutex_unlock(&kvm->lock);
+	return err;
 
-void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
-{
-	if (mem->guest_phys_addr == 0 && mem->memory_size != 0 &&
-	    !kvm->arch.rma)
-		kvmppc_map_vrma(kvm, mem);
+ up_out:
+	up_read(&current->mm->mmap_sem);
+	goto out;
 }
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
 	long r;
-	unsigned long npages = 1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER);
-	long err = -ENOMEM;
 	unsigned long lpcr;
 
 	/* Allocate hashed page table */
@@ -1211,19 +1348,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
 	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
 
-	kvm->arch.ram_pginfo = kzalloc(npages * sizeof(struct kvmppc_pginfo),
-				       GFP_KERNEL);
-	if (!kvm->arch.ram_pginfo) {
-		pr_err("kvmppc_core_init_vm: couldn't alloc %lu bytes\n",
-		       npages * sizeof(struct kvmppc_pginfo));
-		goto out_free;
-	}
-
-	kvm->arch.ram_npages = 0;
-	kvm->arch.ram_psize = 1ul << LARGE_PAGE_ORDER;
-	kvm->arch.ram_porder = LARGE_PAGE_ORDER;
 	kvm->arch.rma = NULL;
-	kvm->arch.n_rma_pages = 0;
 
 	kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
 
@@ -1241,30 +1366,25 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
 		lpcr &= LPCR_PECE | LPCR_LPES;
 		lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
-			LPCR_VPM0 | LPCR_VRMA_L;
+			LPCR_VPM0 | LPCR_VPM1;
+		kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
+			(VRMA_VSID << SLB_VSID_SHIFT_1T);
 	}
 	kvm->arch.lpcr = lpcr;
 
+	kvm->arch.using_mmu_notifiers = !!cpu_has_feature(CPU_FTR_ARCH_206);
+	spin_lock_init(&kvm->arch.slot_phys_lock);
 	return 0;
-
- out_free:
-	kvmppc_free_hpt(kvm);
-	return err;
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
-	struct kvmppc_pginfo *pginfo;
 	unsigned long i;
 
-	if (kvm->arch.ram_pginfo) {
-		pginfo = kvm->arch.ram_pginfo;
-		kvm->arch.ram_pginfo = NULL;
-		for (i = kvm->arch.n_rma_pages; i < kvm->arch.ram_npages; ++i)
-			if (pginfo[i].pfn)
-				put_page(pfn_to_page(pginfo[i].pfn));
-		kfree(pginfo);
-	}
+	if (!kvm->arch.using_mmu_notifiers)
+		for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
+			unpin_slot(kvm, i);
+
 	if (kvm->arch.rma) {
 		kvm_release_rma(kvm->arch.rma);
 		kvm->arch.rma = NULL;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index a795a13f4a70..bed1279aa6a8 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -18,6 +18,15 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
+#define KVM_LINEAR_RMA		0
+#define KVM_LINEAR_HPT		1
+
+static void __init kvm_linear_init_one(ulong size, int count, int type);
+static struct kvmppc_linear_info *kvm_alloc_linear(int type);
+static void kvm_release_linear(struct kvmppc_linear_info *ri);
+
+/*************** RMA *************/
+
 /*
  * This maintains a list of RMAs (real mode areas) for KVM guests to use.
  * Each RMA has to be physically contiguous and of a size that the
@@ -29,32 +38,6 @@
 static unsigned long kvm_rma_size = 64 << 20;	/* 64MB */
 static unsigned long kvm_rma_count;
 
-static int __init early_parse_rma_size(char *p)
-{
-	if (!p)
-		return 1;
-
-	kvm_rma_size = memparse(p, &p);
-
-	return 0;
-}
-early_param("kvm_rma_size", early_parse_rma_size);
-
-static int __init early_parse_rma_count(char *p)
-{
-	if (!p)
-		return 1;
-
-	kvm_rma_count = simple_strtoul(p, NULL, 0);
-
-	return 0;
-}
-early_param("kvm_rma_count", early_parse_rma_count);
-
-static struct kvmppc_rma_info *rma_info;
-static LIST_HEAD(free_rmas);
-static DEFINE_SPINLOCK(rma_lock);
-
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
 static inline int lpcr_rmls(unsigned long rma_size)
@@ -81,45 +64,106 @@ static inline int lpcr_rmls(unsigned long rma_size)
 	}
 }
 
+static int __init early_parse_rma_size(char *p)
+{
+	if (!p)
+		return 1;
+
+	kvm_rma_size = memparse(p, &p);
+
+	return 0;
+}
+early_param("kvm_rma_size", early_parse_rma_size);
+
+static int __init early_parse_rma_count(char *p)
+{
+	if (!p)
+		return 1;
+
+	kvm_rma_count = simple_strtoul(p, NULL, 0);
+
+	return 0;
+}
+early_param("kvm_rma_count", early_parse_rma_count);
+
+struct kvmppc_linear_info *kvm_alloc_rma(void)
+{
+	return kvm_alloc_linear(KVM_LINEAR_RMA);
+}
+EXPORT_SYMBOL_GPL(kvm_alloc_rma);
+
+void kvm_release_rma(struct kvmppc_linear_info *ri)
+{
+	kvm_release_linear(ri);
+}
+EXPORT_SYMBOL_GPL(kvm_release_rma);
+
+/*************** HPT *************/
+
 /*
- * Called at boot time while the bootmem allocator is active,
- * to allocate contiguous physical memory for the real memory
- * areas for guests.
+ * This maintains a list of big linear HPT tables that contain the GVA->HPA
+ * memory mappings. If we don't reserve those early on, we might not be able
+ * to get a big (usually 16MB) linear memory region from the kernel anymore.
  */
-void __init kvm_rma_init(void)
+
+static unsigned long kvm_hpt_count;
+
+static int __init early_parse_hpt_count(char *p)
+{
+	if (!p)
+		return 1;
+
+	kvm_hpt_count = simple_strtoul(p, NULL, 0);
+
+	return 0;
+}
+early_param("kvm_hpt_count", early_parse_hpt_count);
+
+struct kvmppc_linear_info *kvm_alloc_hpt(void)
+{
+	return kvm_alloc_linear(KVM_LINEAR_HPT);
+}
+EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
+
+void kvm_release_hpt(struct kvmppc_linear_info *li)
+{
+	kvm_release_linear(li);
+}
+EXPORT_SYMBOL_GPL(kvm_release_hpt);
+
+/*************** generic *************/
+
+static LIST_HEAD(free_linears);
+static DEFINE_SPINLOCK(linear_lock);
+
+static void __init kvm_linear_init_one(ulong size, int count, int type)
 {
 	unsigned long i;
 	unsigned long j, npages;
-	void *rma;
+	void *linear;
 	struct page *pg;
+	const char *typestr;
+	struct kvmppc_linear_info *linear_info;
 
-	/* Only do this on PPC970 in HV mode */
-	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
-	    !cpu_has_feature(CPU_FTR_ARCH_201))
-		return;
-
-	if (!kvm_rma_size || !kvm_rma_count)
+	if (!count)
 		return;
 
-	/* Check that the requested size is one supported in hardware */
-	if (lpcr_rmls(kvm_rma_size) < 0) {
-		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
-		return;
-	}
-
-	npages = kvm_rma_size >> PAGE_SHIFT;
-	rma_info = alloc_bootmem(kvm_rma_count * sizeof(struct kvmppc_rma_info));
-	for (i = 0; i < kvm_rma_count; ++i) {
-		rma = alloc_bootmem_align(kvm_rma_size, kvm_rma_size);
-		pr_info("Allocated KVM RMA at %p (%ld MB)\n", rma,
-			kvm_rma_size >> 20);
-		rma_info[i].base_virt = rma;
-		rma_info[i].base_pfn = __pa(rma) >> PAGE_SHIFT;
-		rma_info[i].npages = npages;
-		list_add_tail(&rma_info[i].list, &free_rmas);
-		atomic_set(&rma_info[i].use_count, 0);
-
-		pg = pfn_to_page(rma_info[i].base_pfn);
+	typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "HPT";
+
+	npages = size >> PAGE_SHIFT;
+	linear_info = alloc_bootmem(count * sizeof(struct kvmppc_linear_info));
+	for (i = 0; i < count; ++i) {
+		linear = alloc_bootmem_align(size, size);
+		pr_info("Allocated KVM %s at %p (%ld MB)\n", typestr, linear,
+			size >> 20);
+		linear_info[i].base_virt = linear;
+		linear_info[i].base_pfn = __pa(linear) >> PAGE_SHIFT;
+		linear_info[i].npages = npages;
+		linear_info[i].type = type;
+		list_add_tail(&linear_info[i].list, &free_linears);
+		atomic_set(&linear_info[i].use_count, 0);
+
+		pg = pfn_to_page(linear_info[i].base_pfn);
 		for (j = 0; j < npages; ++j) {
 			atomic_inc(&pg->_count);
 			++pg;
@@ -127,30 +171,59 @@ void __init kvm_rma_init(void)
 	}
 }
 
-struct kvmppc_rma_info *kvm_alloc_rma(void)
+static struct kvmppc_linear_info *kvm_alloc_linear(int type)
 {
-	struct kvmppc_rma_info *ri;
+	struct kvmppc_linear_info *ri;
 
 	ri = NULL;
-	spin_lock(&rma_lock);
-	if (!list_empty(&free_rmas)) {
-		ri = list_first_entry(&free_rmas, struct kvmppc_rma_info, list);
+	spin_lock(&linear_lock);
+	list_for_each_entry(ri, &free_linears, list) {
+		if (ri->type != type)
+			continue;
+
 		list_del(&ri->list);
 		atomic_inc(&ri->use_count);
+		break;
 	}
-	spin_unlock(&rma_lock);
+	spin_unlock(&linear_lock);
+	memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT);
 	return ri;
 }
-EXPORT_SYMBOL_GPL(kvm_alloc_rma);
 
-void kvm_release_rma(struct kvmppc_rma_info *ri)
+static void kvm_release_linear(struct kvmppc_linear_info *ri)
 {
 	if (atomic_dec_and_test(&ri->use_count)) {
-		spin_lock(&rma_lock);
-		list_add_tail(&ri->list, &free_rmas);
-		spin_unlock(&rma_lock);
+		spin_lock(&linear_lock);
+		list_add_tail(&ri->list, &free_linears);
+		spin_unlock(&linear_lock);
 
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_release_rma);
 
+/*
+ * Called at boot time while the bootmem allocator is active,
+ * to allocate contiguous physical memory for the hash page
+ * tables for guests.
+ */
+void __init kvm_linear_init(void)
+{
+	/* HPT */
+	kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT);
+
+	/* RMA */
+	/* Only do this on PPC970 in HV mode */
+	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
+	    !cpu_has_feature(CPU_FTR_ARCH_201))
+		return;
+
+	if (!kvm_rma_size || !kvm_rma_count)
+		return;
+
+	/* Check that the requested size is one supported in hardware */
+	if (lpcr_rmls(kvm_rma_size) < 0) {
+		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
+		return;
+	}
+
+	kvm_linear_init_one(kvm_rma_size, kvm_rma_count, KVM_LINEAR_RMA);
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index bacb0cfa3602..def880aea63a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -11,6 +11,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/hugetlb.h>
+#include <linux/module.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -20,95 +21,307 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER	24
-#define HPT_NPTEG	(1ul << (HPT_ORDER - 7))	/* 128B per pteg */
-#define HPT_HASH_MASK	(HPT_NPTEG - 1)
+/* Translate address of a vmalloc'd thing to a linear map address */
+static void *real_vmalloc_addr(void *x)
+{
+	unsigned long addr = (unsigned long) x;
+	pte_t *p;
 
-#define HPTE_V_HVLOCK	0x40UL
+	p = find_linux_pte(swapper_pg_dir, addr);
+	if (!p || !pte_present(*p))
+		return NULL;
+	/* assume we don't have huge pages in vmalloc space... */
+	addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
+	return __va(addr);
+}
 
-static inline long lock_hpte(unsigned long *hpte, unsigned long bits)
+/*
+ * Add this HPTE into the chain for the real page.
+ * Must be called with the chain locked; it unlocks the chain.
+ */
+void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
+			     unsigned long *rmap, long pte_index, int realmode)
 {
-	unsigned long tmp, old;
+	struct revmap_entry *head, *tail;
+	unsigned long i;
 
-	asm volatile("	ldarx	%0,0,%2\n"
-		     "	and.	%1,%0,%3\n"
-		     "	bne	2f\n"
-		     "	ori	%0,%0,%4\n"
-		     "  stdcx.	%0,0,%2\n"
-		     "	beq+	2f\n"
-		     "	li	%1,%3\n"
-		     "2:	isync"
-		     : "=&r" (tmp), "=&r" (old)
-		     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
-		     : "cc", "memory");
-	return old == 0;
+	if (*rmap & KVMPPC_RMAP_PRESENT) {
+		i = *rmap & KVMPPC_RMAP_INDEX;
+		head = &kvm->arch.revmap[i];
+		if (realmode)
+			head = real_vmalloc_addr(head);
+		tail = &kvm->arch.revmap[head->back];
+		if (realmode)
+			tail = real_vmalloc_addr(tail);
+		rev->forw = i;
+		rev->back = head->back;
+		tail->forw = pte_index;
+		head->back = pte_index;
+	} else {
+		rev->forw = rev->back = pte_index;
+		i = pte_index;
+	}
+	smp_wmb();
+	*rmap = i | KVMPPC_RMAP_REFERENCED | KVMPPC_RMAP_PRESENT; /* unlock */
+}
+EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
+
+/* Remove this HPTE from the chain for a real page */
+static void remove_revmap_chain(struct kvm *kvm, long pte_index,
+				struct revmap_entry *rev,
+				unsigned long hpte_v, unsigned long hpte_r)
+{
+	struct revmap_entry *next, *prev;
+	unsigned long gfn, ptel, head;
+	struct kvm_memory_slot *memslot;
+	unsigned long *rmap;
+	unsigned long rcbits;
+
+	rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
+	ptel = rev->guest_rpte |= rcbits;
+	gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
+	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+		return;
+
+	rmap = real_vmalloc_addr(&memslot->rmap[gfn - memslot->base_gfn]);
+	lock_rmap(rmap);
+
+	head = *rmap & KVMPPC_RMAP_INDEX;
+	next = real_vmalloc_addr(&kvm->arch.revmap[rev->forw]);
+	prev = real_vmalloc_addr(&kvm->arch.revmap[rev->back]);
+	next->back = rev->back;
+	prev->forw = rev->forw;
+	if (head == pte_index) {
+		head = rev->forw;
+		if (head == pte_index)
+			*rmap &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX);
+		else
+			*rmap = (*rmap & ~KVMPPC_RMAP_INDEX) | head;
+	}
+	*rmap |= rcbits << KVMPPC_RMAP_RC_SHIFT;
+	unlock_rmap(rmap);
+}
+
+static pte_t lookup_linux_pte(struct kvm_vcpu *vcpu, unsigned long hva,
+			      int writing, unsigned long *pte_sizep)
+{
+	pte_t *ptep;
+	unsigned long ps = *pte_sizep;
+	unsigned int shift;
+
+	ptep = find_linux_pte_or_hugepte(vcpu->arch.pgdir, hva, &shift);
+	if (!ptep)
+		return __pte(0);
+	if (shift)
+		*pte_sizep = 1ul << shift;
+	else
+		*pte_sizep = PAGE_SIZE;
+	if (ps > *pte_sizep)
+		return __pte(0);
+	if (!pte_present(*ptep))
+		return __pte(0);
+	return kvmppc_read_update_linux_pte(ptep, writing);
+}
+
+static inline void unlock_hpte(unsigned long *hpte, unsigned long hpte_v)
+{
+	asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
+	hpte[0] = hpte_v;
 }
 
 long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 		    long pte_index, unsigned long pteh, unsigned long ptel)
 {
-	unsigned long porder;
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long i, lpn, pa;
+	unsigned long i, pa, gpa, gfn, psize;
+	unsigned long slot_fn, hva;
 	unsigned long *hpte;
+	struct revmap_entry *rev;
+	unsigned long g_ptel = ptel;
+	struct kvm_memory_slot *memslot;
+	unsigned long *physp, pte_size;
+	unsigned long is_io;
+	unsigned long *rmap;
+	pte_t pte;
+	unsigned int writing;
+	unsigned long mmu_seq;
+	unsigned long rcbits;
+	bool realmode = vcpu->arch.vcore->vcore_state == VCORE_RUNNING;
 
-	/* only handle 4k, 64k and 16M pages for now */
-	porder = 12;
-	if (pteh & HPTE_V_LARGE) {
-		if (cpu_has_feature(CPU_FTR_ARCH_206) &&
-		    (ptel & 0xf000) == 0x1000) {
-			/* 64k page */
-			porder = 16;
-		} else if ((ptel & 0xff000) == 0) {
-			/* 16M page */
-			porder = 24;
-			/* lowest AVA bit must be 0 for 16M pages */
-			if (pteh & 0x80)
-				return H_PARAMETER;
-		} else
+	psize = hpte_page_size(pteh, ptel);
+	if (!psize)
+		return H_PARAMETER;
+	writing = hpte_is_writable(ptel);
+	pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
+
+	/* used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	/* Find the memslot (if any) for this address */
+	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
+	gfn = gpa >> PAGE_SHIFT;
+	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+	pa = 0;
+	is_io = ~0ul;
+	rmap = NULL;
+	if (!(memslot && !(memslot->flags & KVM_MEMSLOT_INVALID))) {
+		/* PPC970 can't do emulated MMIO */
+		if (!cpu_has_feature(CPU_FTR_ARCH_206))
 			return H_PARAMETER;
+		/* Emulated MMIO - mark this with key=31 */
+		pteh |= HPTE_V_ABSENT;
+		ptel |= HPTE_R_KEY_HI | HPTE_R_KEY_LO;
+		goto do_insert;
 	}
-	lpn = (ptel & HPTE_R_RPN) >> kvm->arch.ram_porder;
-	if (lpn >= kvm->arch.ram_npages || porder > kvm->arch.ram_porder)
-		return H_PARAMETER;
-	pa = kvm->arch.ram_pginfo[lpn].pfn << PAGE_SHIFT;
-	if (!pa)
+
+	/* Check if the requested page fits entirely in the memslot. */
+	if (!slot_is_aligned(memslot, psize))
 		return H_PARAMETER;
-	/* Check WIMG */
-	if ((ptel & HPTE_R_WIMG) != HPTE_R_M &&
-	    (ptel & HPTE_R_WIMG) != (HPTE_R_W | HPTE_R_I | HPTE_R_M))
+	slot_fn = gfn - memslot->base_gfn;
+	rmap = &memslot->rmap[slot_fn];
+
+	if (!kvm->arch.using_mmu_notifiers) {
+		physp = kvm->arch.slot_phys[memslot->id];
+		if (!physp)
+			return H_PARAMETER;
+		physp += slot_fn;
+		if (realmode)
+			physp = real_vmalloc_addr(physp);
+		pa = *physp;
+		if (!pa)
+			return H_TOO_HARD;
+		is_io = pa & (HPTE_R_I | HPTE_R_W);
+		pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
+		pa &= PAGE_MASK;
+	} else {
+		/* Translate to host virtual address */
+		hva = gfn_to_hva_memslot(memslot, gfn);
+
+		/* Look up the Linux PTE for the backing page */
+		pte_size = psize;
+		pte = lookup_linux_pte(vcpu, hva, writing, &pte_size);
+		if (pte_present(pte)) {
+			if (writing && !pte_write(pte))
+				/* make the actual HPTE be read-only */
+				ptel = hpte_make_readonly(ptel);
+			is_io = hpte_cache_bits(pte_val(pte));
+			pa = pte_pfn(pte) << PAGE_SHIFT;
+		}
+	}
+	if (pte_size < psize)
 		return H_PARAMETER;
-	pteh &= ~0x60UL;
-	ptel &= ~(HPTE_R_PP0 - kvm->arch.ram_psize);
+	if (pa && pte_size > psize)
+		pa |= gpa & (pte_size - 1);
+
+	ptel &= ~(HPTE_R_PP0 - psize);
 	ptel |= pa;
-	if (pte_index >= (HPT_NPTEG << 3))
+
+	if (pa)
+		pteh |= HPTE_V_VALID;
+	else
+		pteh |= HPTE_V_ABSENT;
+
+	/* Check WIMG */
+	if (is_io != ~0ul && !hpte_cache_flags_ok(ptel, is_io)) {
+		if (is_io)
+			return H_PARAMETER;
+		/*
+		 * Allow guest to map emulated device memory as
+		 * uncacheable, but actually make it cacheable.
+		 */
+		ptel &= ~(HPTE_R_W|HPTE_R_I|HPTE_R_G);
+		ptel |= HPTE_R_M;
+	}
+
+	/* Find and lock the HPTEG slot to use */
+ do_insert:
+	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
 	if (likely((flags & H_EXACT) == 0)) {
 		pte_index &= ~7UL;
 		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-		for (i = 0; ; ++i) {
-			if (i == 8)
-				return H_PTEG_FULL;
+		for (i = 0; i < 8; ++i) {
 			if ((*hpte & HPTE_V_VALID) == 0 &&
-			    lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
+			    try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
+					  HPTE_V_ABSENT))
 				break;
 			hpte += 2;
 		}
+		if (i == 8) {
+			/*
+			 * Since try_lock_hpte doesn't retry (not even stdcx.
+			 * failures), it could be that there is a free slot
+			 * but we transiently failed to lock it.  Try again,
+			 * actually locking each slot and checking it.
+			 */
+			hpte -= 16;
+			for (i = 0; i < 8; ++i) {
+				while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+					cpu_relax();
+				if (!(*hpte & (HPTE_V_VALID | HPTE_V_ABSENT)))
+					break;
+				*hpte &= ~HPTE_V_HVLOCK;
+				hpte += 2;
+			}
+			if (i == 8)
+				return H_PTEG_FULL;
+		}
+		pte_index += i;
 	} else {
-		i = 0;
 		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-		if (!lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
-			return H_PTEG_FULL;
+		if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
+				   HPTE_V_ABSENT)) {
+			/* Lock the slot and check again */
+			while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+				cpu_relax();
+			if (*hpte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
+				*hpte &= ~HPTE_V_HVLOCK;
+				return H_PTEG_FULL;
+			}
+		}
 	}
+
+	/* Save away the guest's idea of the second HPTE dword */
+	rev = &kvm->arch.revmap[pte_index];
+	if (realmode)
+		rev = real_vmalloc_addr(rev);
+	if (rev)
+		rev->guest_rpte = g_ptel;
+
+	/* Link HPTE into reverse-map chain */
+	if (pteh & HPTE_V_VALID) {
+		if (realmode)
+			rmap = real_vmalloc_addr(rmap);
+		lock_rmap(rmap);
+		/* Check for pending invalidations under the rmap chain lock */
+		if (kvm->arch.using_mmu_notifiers &&
+		    mmu_notifier_retry(vcpu, mmu_seq)) {
+			/* inval in progress, write a non-present HPTE */
+			pteh |= HPTE_V_ABSENT;
+			pteh &= ~HPTE_V_VALID;
+			unlock_rmap(rmap);
+		} else {
+			kvmppc_add_revmap_chain(kvm, rev, rmap, pte_index,
+						realmode);
+			/* Only set R/C in real HPTE if already set in *rmap */
+			rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
+			ptel &= rcbits | ~(HPTE_R_R | HPTE_R_C);
+		}
+	}
+
 	hpte[1] = ptel;
+
+	/* Write the first HPTE dword, unlocking the HPTE and making it valid */
 	eieio();
 	hpte[0] = pteh;
 	asm volatile("ptesync" : : : "memory");
-	atomic_inc(&kvm->arch.ram_pginfo[lpn].refcnt);
-	vcpu->arch.gpr[4] = pte_index + i;
+
+	vcpu->arch.gpr[4] = pte_index;
 	return H_SUCCESS;
 }
+EXPORT_SYMBOL_GPL(kvmppc_h_enter);
 
 #define LOCK_TOKEN	(*(u32 *)(&get_paca()->lock_token))
 
@@ -137,37 +350,46 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hpte;
 	unsigned long v, r, rb;
+	struct revmap_entry *rev;
 
-	if (pte_index >= (HPT_NPTEG << 3))
+	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
 	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-	while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
 		cpu_relax();
-	if ((hpte[0] & HPTE_V_VALID) == 0 ||
+	if ((hpte[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
 	    ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn) ||
 	    ((flags & H_ANDCOND) && (hpte[0] & avpn) != 0)) {
 		hpte[0] &= ~HPTE_V_HVLOCK;
 		return H_NOT_FOUND;
 	}
-	if (atomic_read(&kvm->online_vcpus) == 1)
-		flags |= H_LOCAL;
-	vcpu->arch.gpr[4] = v = hpte[0] & ~HPTE_V_HVLOCK;
-	vcpu->arch.gpr[5] = r = hpte[1];
-	rb = compute_tlbie_rb(v, r, pte_index);
-	hpte[0] = 0;
-	if (!(flags & H_LOCAL)) {
-		while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-			cpu_relax();
-		asm volatile("ptesync" : : : "memory");
-		asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-			     : : "r" (rb), "r" (kvm->arch.lpid));
-		asm volatile("ptesync" : : : "memory");
-		kvm->arch.tlbie_lock = 0;
-	} else {
-		asm volatile("ptesync" : : : "memory");
-		asm volatile("tlbiel %0" : : "r" (rb));
-		asm volatile("ptesync" : : : "memory");
+
+	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+	v = hpte[0] & ~HPTE_V_HVLOCK;
+	if (v & HPTE_V_VALID) {
+		hpte[0] &= ~HPTE_V_VALID;
+		rb = compute_tlbie_rb(v, hpte[1], pte_index);
+		if (!(flags & H_LOCAL) && atomic_read(&kvm->online_vcpus) > 1) {
+			while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+				cpu_relax();
+			asm volatile("ptesync" : : : "memory");
+			asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+				     : : "r" (rb), "r" (kvm->arch.lpid));
+			asm volatile("ptesync" : : : "memory");
+			kvm->arch.tlbie_lock = 0;
+		} else {
+			asm volatile("ptesync" : : : "memory");
+			asm volatile("tlbiel %0" : : "r" (rb));
+			asm volatile("ptesync" : : : "memory");
+		}
+		/* Read PTE low word after tlbie to get final R/C values */
+		remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
 	}
+	r = rev->guest_rpte;
+	unlock_hpte(hpte, 0);
+
+	vcpu->arch.gpr[4] = v;
+	vcpu->arch.gpr[5] = r;
 	return H_SUCCESS;
 }
 
@@ -175,78 +397,117 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long *args = &vcpu->arch.gpr[4];
-	unsigned long *hp, tlbrb[4];
-	long int i, found;
-	long int n_inval = 0;
-	unsigned long flags, req, pte_index;
+	unsigned long *hp, *hptes[4], tlbrb[4];
+	long int i, j, k, n, found, indexes[4];
+	unsigned long flags, req, pte_index, rcbits;
 	long int local = 0;
 	long int ret = H_SUCCESS;
+	struct revmap_entry *rev, *revs[4];
 
 	if (atomic_read(&kvm->online_vcpus) == 1)
 		local = 1;
-	for (i = 0; i < 4; ++i) {
-		pte_index = args[i * 2];
-		flags = pte_index >> 56;
-		pte_index &= ((1ul << 56) - 1);
-		req = flags >> 6;
-		flags &= 3;
-		if (req == 3)
-			break;
-		if (req != 1 || flags == 3 ||
-		    pte_index >= (HPT_NPTEG << 3)) {
-			/* parameter error */
-			args[i * 2] = ((0xa0 | flags) << 56) + pte_index;
-			ret = H_PARAMETER;
-			break;
-		}
-		hp = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-		while (!lock_hpte(hp, HPTE_V_HVLOCK))
-			cpu_relax();
-		found = 0;
-		if (hp[0] & HPTE_V_VALID) {
-			switch (flags & 3) {
-			case 0:		/* absolute */
-				found = 1;
+	for (i = 0; i < 4 && ret == H_SUCCESS; ) {
+		n = 0;
+		for (; i < 4; ++i) {
+			j = i * 2;
+			pte_index = args[j];
+			flags = pte_index >> 56;
+			pte_index &= ((1ul << 56) - 1);
+			req = flags >> 6;
+			flags &= 3;
+			if (req == 3) {		/* no more requests */
+				i = 4;
 				break;
-			case 1:		/* andcond */
-				if (!(hp[0] & args[i * 2 + 1]))
-					found = 1;
+			}
+			if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) {
+				/* parameter error */
+				args[j] = ((0xa0 | flags) << 56) + pte_index;
+				ret = H_PARAMETER;
 				break;
-			case 2:		/* AVPN */
-				if ((hp[0] & ~0x7fUL) == args[i * 2 + 1])
+			}
+			hp = (unsigned long *)
+				(kvm->arch.hpt_virt + (pte_index << 4));
+			/* to avoid deadlock, don't spin except for first */
+			if (!try_lock_hpte(hp, HPTE_V_HVLOCK)) {
+				if (n)
+					break;
+				while (!try_lock_hpte(hp, HPTE_V_HVLOCK))
+					cpu_relax();
+			}
+			found = 0;
+			if (hp[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) {
+				switch (flags & 3) {
+				case 0:		/* absolute */
 					found = 1;
-				break;
+					break;
+				case 1:		/* andcond */
+					if (!(hp[0] & args[j + 1]))
+						found = 1;
+					break;
+				case 2:		/* AVPN */
+					if ((hp[0] & ~0x7fUL) == args[j + 1])
+						found = 1;
+					break;
+				}
+			}
+			if (!found) {
+				hp[0] &= ~HPTE_V_HVLOCK;
+				args[j] = ((0x90 | flags) << 56) + pte_index;
+				continue;
 			}
+
+			args[j] = ((0x80 | flags) << 56) + pte_index;
+			rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+
+			if (!(hp[0] & HPTE_V_VALID)) {
+				/* insert R and C bits from PTE */
+				rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
+				args[j] |= rcbits << (56 - 5);
+				continue;
+			}
+
+			hp[0] &= ~HPTE_V_VALID;		/* leave it locked */
+			tlbrb[n] = compute_tlbie_rb(hp[0], hp[1], pte_index);
+			indexes[n] = j;
+			hptes[n] = hp;
+			revs[n] = rev;
+			++n;
+		}
+
+		if (!n)
+			break;
+
+		/* Now that we've collected a batch, do the tlbies */
+		if (!local) {
+			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+				cpu_relax();
+			asm volatile("ptesync" : : : "memory");
+			for (k = 0; k < n; ++k)
+				asm volatile(PPC_TLBIE(%1,%0) : :
+					     "r" (tlbrb[k]),
+					     "r" (kvm->arch.lpid));
+			asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+			kvm->arch.tlbie_lock = 0;
+		} else {
+			asm volatile("ptesync" : : : "memory");
+			for (k = 0; k < n; ++k)
+				asm volatile("tlbiel %0" : : "r" (tlbrb[k]));
+			asm volatile("ptesync" : : : "memory");
 		}
-		if (!found) {
-			hp[0] &= ~HPTE_V_HVLOCK;
-			args[i * 2] = ((0x90 | flags) << 56) + pte_index;
-			continue;
+
+		/* Read PTE low words after tlbie to get final R/C values */
+		for (k = 0; k < n; ++k) {
+			j = indexes[k];
+			pte_index = args[j] & ((1ul << 56) - 1);
+			hp = hptes[k];
+			rev = revs[k];
+			remove_revmap_chain(kvm, pte_index, rev, hp[0], hp[1]);
+			rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
+			args[j] |= rcbits << (56 - 5);
+			hp[0] = 0;
 		}
-		/* insert R and C bits from PTE */
-		flags |= (hp[1] >> 5) & 0x0c;
-		args[i * 2] = ((0x80 | flags) << 56) + pte_index;
-		tlbrb[n_inval++] = compute_tlbie_rb(hp[0], hp[1], pte_index);
-		hp[0] = 0;
-	}
-	if (n_inval == 0)
-		return ret;
-
-	if (!local) {
-		while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-			cpu_relax();
-		asm volatile("ptesync" : : : "memory");
-		for (i = 0; i < n_inval; ++i)
-			asm volatile(PPC_TLBIE(%1,%0)
-				     : : "r" (tlbrb[i]), "r" (kvm->arch.lpid));
-		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-		kvm->arch.tlbie_lock = 0;
-	} else {
-		asm volatile("ptesync" : : : "memory");
-		for (i = 0; i < n_inval; ++i)
-			asm volatile("tlbiel %0" : : "r" (tlbrb[i]));
-		asm volatile("ptesync" : : : "memory");
 	}
+
 	return ret;
 }
 
@@ -256,40 +517,55 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 {
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hpte;
-	unsigned long v, r, rb;
+	struct revmap_entry *rev;
+	unsigned long v, r, rb, mask, bits;
 
-	if (pte_index >= (HPT_NPTEG << 3))
+	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
+
 	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-	while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
 		cpu_relax();
-	if ((hpte[0] & HPTE_V_VALID) == 0 ||
+	if ((hpte[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
 	    ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn)) {
 		hpte[0] &= ~HPTE_V_HVLOCK;
 		return H_NOT_FOUND;
 	}
+
 	if (atomic_read(&kvm->online_vcpus) == 1)
 		flags |= H_LOCAL;
 	v = hpte[0];
-	r = hpte[1] & ~(HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
-			HPTE_R_KEY_HI | HPTE_R_KEY_LO);
-	r |= (flags << 55) & HPTE_R_PP0;
-	r |= (flags << 48) & HPTE_R_KEY_HI;
-	r |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
-	rb = compute_tlbie_rb(v, r, pte_index);
-	hpte[0] = v & ~HPTE_V_VALID;
-	if (!(flags & H_LOCAL)) {
-		while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-			cpu_relax();
-		asm volatile("ptesync" : : : "memory");
-		asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-			     : : "r" (rb), "r" (kvm->arch.lpid));
-		asm volatile("ptesync" : : : "memory");
-		kvm->arch.tlbie_lock = 0;
-	} else {
-		asm volatile("ptesync" : : : "memory");
-		asm volatile("tlbiel %0" : : "r" (rb));
-		asm volatile("ptesync" : : : "memory");
+	bits = (flags << 55) & HPTE_R_PP0;
+	bits |= (flags << 48) & HPTE_R_KEY_HI;
+	bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
+
+	/* Update guest view of 2nd HPTE dword */
+	mask = HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
+		HPTE_R_KEY_HI | HPTE_R_KEY_LO;
+	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+	if (rev) {
+		r = (rev->guest_rpte & ~mask) | bits;
+		rev->guest_rpte = r;
+	}
+	r = (hpte[1] & ~mask) | bits;
+
+	/* Update HPTE */
+	if (v & HPTE_V_VALID) {
+		rb = compute_tlbie_rb(v, r, pte_index);
+		hpte[0] = v & ~HPTE_V_VALID;
+		if (!(flags & H_LOCAL)) {
+			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+				cpu_relax();
+			asm volatile("ptesync" : : : "memory");
+			asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+				     : : "r" (rb), "r" (kvm->arch.lpid));
+			asm volatile("ptesync" : : : "memory");
+			kvm->arch.tlbie_lock = 0;
+		} else {
+			asm volatile("ptesync" : : : "memory");
+			asm volatile("tlbiel %0" : : "r" (rb));
+			asm volatile("ptesync" : : : "memory");
+		}
 	}
 	hpte[1] = r;
 	eieio();
@@ -298,40 +574,243 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	return H_SUCCESS;
 }
 
-static unsigned long reverse_xlate(struct kvm *kvm, unsigned long realaddr)
-{
-	long int i;
-	unsigned long offset, rpn;
-
-	offset = realaddr & (kvm->arch.ram_psize - 1);
-	rpn = (realaddr - offset) >> PAGE_SHIFT;
-	for (i = 0; i < kvm->arch.ram_npages; ++i)
-		if (rpn == kvm->arch.ram_pginfo[i].pfn)
-			return (i << PAGE_SHIFT) + offset;
-	return HPTE_R_RPN;	/* all 1s in the RPN field */
-}
-
 long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 		   unsigned long pte_index)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long *hpte, r;
+	unsigned long *hpte, v, r;
 	int i, n = 1;
+	struct revmap_entry *rev = NULL;
 
-	if (pte_index >= (HPT_NPTEG << 3))
+	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
 	if (flags & H_READ_4) {
 		pte_index &= ~3;
 		n = 4;
 	}
+	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
 	for (i = 0; i < n; ++i, ++pte_index) {
 		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+		v = hpte[0] & ~HPTE_V_HVLOCK;
 		r = hpte[1];
-		if ((flags & H_R_XLATE) && (hpte[0] & HPTE_V_VALID))
-			r = reverse_xlate(kvm, r & HPTE_R_RPN) |
-				(r & ~HPTE_R_RPN);
-		vcpu->arch.gpr[4 + i * 2] = hpte[0];
+		if (v & HPTE_V_ABSENT) {
+			v &= ~HPTE_V_ABSENT;
+			v |= HPTE_V_VALID;
+		}
+		if (v & HPTE_V_VALID)
+			r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
+		vcpu->arch.gpr[4 + i * 2] = v;
 		vcpu->arch.gpr[5 + i * 2] = r;
 	}
 	return H_SUCCESS;
 }
+
+void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
+			unsigned long pte_index)
+{
+	unsigned long rb;
+
+	hptep[0] &= ~HPTE_V_VALID;
+	rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
+	while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+		cpu_relax();
+	asm volatile("ptesync" : : : "memory");
+	asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+		     : : "r" (rb), "r" (kvm->arch.lpid));
+	asm volatile("ptesync" : : : "memory");
+	kvm->arch.tlbie_lock = 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
+
+void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
+			   unsigned long pte_index)
+{
+	unsigned long rb;
+	unsigned char rbyte;
+
+	rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
+	rbyte = (hptep[1] & ~HPTE_R_R) >> 8;
+	/* modify only the second-last byte, which contains the ref bit */
+	*((char *)hptep + 14) = rbyte;
+	while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+		cpu_relax();
+	asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+		     : : "r" (rb), "r" (kvm->arch.lpid));
+	asm volatile("ptesync" : : : "memory");
+	kvm->arch.tlbie_lock = 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_clear_ref_hpte);
+
+static int slb_base_page_shift[4] = {
+	24,	/* 16M */
+	16,	/* 64k */
+	34,	/* 16G */
+	20,	/* 1M, unsupported */
+};
+
+long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
+			      unsigned long valid)
+{
+	unsigned int i;
+	unsigned int pshift;
+	unsigned long somask;
+	unsigned long vsid, hash;
+	unsigned long avpn;
+	unsigned long *hpte;
+	unsigned long mask, val;
+	unsigned long v, r;
+
+	/* Get page shift, work out hash and AVPN etc. */
+	mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_SECONDARY;
+	val = 0;
+	pshift = 12;
+	if (slb_v & SLB_VSID_L) {
+		mask |= HPTE_V_LARGE;
+		val |= HPTE_V_LARGE;
+		pshift = slb_base_page_shift[(slb_v & SLB_VSID_LP) >> 4];
+	}
+	if (slb_v & SLB_VSID_B_1T) {
+		somask = (1UL << 40) - 1;
+		vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T;
+		vsid ^= vsid << 25;
+	} else {
+		somask = (1UL << 28) - 1;
+		vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT;
+	}
+	hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK;
+	avpn = slb_v & ~(somask >> 16);	/* also includes B */
+	avpn |= (eaddr & somask) >> 16;
+
+	if (pshift >= 24)
+		avpn &= ~((1UL << (pshift - 16)) - 1);
+	else
+		avpn &= ~0x7fUL;
+	val |= avpn;
+
+	for (;;) {
+		hpte = (unsigned long *)(kvm->arch.hpt_virt + (hash << 7));
+
+		for (i = 0; i < 16; i += 2) {
+			/* Read the PTE racily */
+			v = hpte[i] & ~HPTE_V_HVLOCK;
+
+			/* Check valid/absent, hash, segment size and AVPN */
+			if (!(v & valid) || (v & mask) != val)
+				continue;
+
+			/* Lock the PTE and read it under the lock */
+			while (!try_lock_hpte(&hpte[i], HPTE_V_HVLOCK))
+				cpu_relax();
+			v = hpte[i] & ~HPTE_V_HVLOCK;
+			r = hpte[i+1];
+
+			/*
+			 * Check the HPTE again, including large page size
+			 * Since we don't currently allow any MPSS (mixed
+			 * page-size segment) page sizes, it is sufficient
+			 * to check against the actual page size.
+			 */
+			if ((v & valid) && (v & mask) == val &&
+			    hpte_page_size(v, r) == (1ul << pshift))
+				/* Return with the HPTE still locked */
+				return (hash << 3) + (i >> 1);
+
+			/* Unlock and move on */
+			hpte[i] = v;
+		}
+
+		if (val & HPTE_V_SECONDARY)
+			break;
+		val |= HPTE_V_SECONDARY;
+		hash = hash ^ HPT_HASH_MASK;
+	}
+	return -1;
+}
+EXPORT_SYMBOL(kvmppc_hv_find_lock_hpte);
+
+/*
+ * Called in real mode to check whether an HPTE not found fault
+ * is due to accessing a paged-out page or an emulated MMIO page,
+ * or if a protection fault is due to accessing a page that the
+ * guest wanted read/write access to but which we made read-only.
+ * Returns a possibly modified status (DSISR) value if not
+ * (i.e. pass the interrupt to the guest),
+ * -1 to pass the fault up to host kernel mode code, -2 to do that
+ * and also load the instruction word (for MMIO emulation),
+ * or 0 if we should make the guest retry the access.
+ */
+long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
+			  unsigned long slb_v, unsigned int status, bool data)
+{
+	struct kvm *kvm = vcpu->kvm;
+	long int index;
+	unsigned long v, r, gr;
+	unsigned long *hpte;
+	unsigned long valid;
+	struct revmap_entry *rev;
+	unsigned long pp, key;
+
+	/* For protection fault, expect to find a valid HPTE */
+	valid = HPTE_V_VALID;
+	if (status & DSISR_NOHPTE)
+		valid |= HPTE_V_ABSENT;
+
+	index = kvmppc_hv_find_lock_hpte(kvm, addr, slb_v, valid);
+	if (index < 0) {
+		if (status & DSISR_NOHPTE)
+			return status;	/* there really was no HPTE */
+		return 0;		/* for prot fault, HPTE disappeared */
+	}
+	hpte = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
+	v = hpte[0] & ~HPTE_V_HVLOCK;
+	r = hpte[1];
+	rev = real_vmalloc_addr(&kvm->arch.revmap[index]);
+	gr = rev->guest_rpte;
+
+	unlock_hpte(hpte, v);
+
+	/* For not found, if the HPTE is valid by now, retry the instruction */
+	if ((status & DSISR_NOHPTE) && (v & HPTE_V_VALID))
+		return 0;
+
+	/* Check access permissions to the page */
+	pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
+	key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
+	status &= ~DSISR_NOHPTE;	/* DSISR_NOHPTE == SRR1_ISI_NOPT */
+	if (!data) {
+		if (gr & (HPTE_R_N | HPTE_R_G))
+			return status | SRR1_ISI_N_OR_G;
+		if (!hpte_read_permission(pp, slb_v & key))
+			return status | SRR1_ISI_PROT;
+	} else if (status & DSISR_ISSTORE) {
+		/* check write permission */
+		if (!hpte_write_permission(pp, slb_v & key))
+			return status | DSISR_PROTFAULT;
+	} else {
+		if (!hpte_read_permission(pp, slb_v & key))
+			return status | DSISR_PROTFAULT;
+	}
+
+	/* Check storage key, if applicable */
+	if (data && (vcpu->arch.shregs.msr & MSR_DR)) {
+		unsigned int perm = hpte_get_skey_perm(gr, vcpu->arch.amr);
+		if (status & DSISR_ISSTORE)
+			perm >>= 1;
+		if (perm & 1)
+			return status | DSISR_KEYFAULT;
+	}
+
+	/* Save HPTE info for virtual-mode handler */
+	vcpu->arch.pgfault_addr = addr;
+	vcpu->arch.pgfault_index = index;
+	vcpu->arch.pgfault_hpte[0] = v;
+	vcpu->arch.pgfault_hpte[1] = r;
+
+	/* Check the storage key to see if it is possibly emulated MMIO */
+	if (data && (vcpu->arch.shregs.msr & MSR_IR) &&
+	    (r & (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) ==
+	    (HPTE_R_KEY_HI | HPTE_R_KEY_LO))
+		return -2;	/* MMIO emulation - load instr word */
+
+	return -1;		/* send fault up to host kernel mode */
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 5c8b26183f50..b70bf22a3ff3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -601,6 +601,30 @@ kvmppc_interrupt:
 
 	stw	r12,VCPU_TRAP(r9)
 
+	/* Save HEIR (HV emulation assist reg) in last_inst
+	   if this is an HEI (HV emulation interrupt, e40) */
+	li	r3,KVM_INST_FETCH_FAILED
+BEGIN_FTR_SECTION
+	cmpwi	r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
+	bne	11f
+	mfspr	r3,SPRN_HEIR
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+11:	stw	r3,VCPU_LAST_INST(r9)
+
+	/* these are volatile across C function calls */
+	mfctr	r3
+	mfxer	r4
+	std	r3, VCPU_CTR(r9)
+	stw	r4, VCPU_XER(r9)
+
+BEGIN_FTR_SECTION
+	/* If this is a page table miss then see if it's theirs or ours */
+	cmpwi	r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
+	beq	kvmppc_hdsi
+	cmpwi	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
+	beq	kvmppc_hisi
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
 	/* See if this is a leftover HDEC interrupt */
 	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
 	bne	2f
@@ -608,7 +632,7 @@ kvmppc_interrupt:
 	cmpwi	r3,0
 	bge	ignore_hdec
 2:
-	/* See if this is something we can handle in real mode */
+	/* See if this is an hcall we can handle in real mode */
 	cmpwi	r12,BOOK3S_INTERRUPT_SYSCALL
 	beq	hcall_try_real_mode
 
@@ -624,6 +648,7 @@ BEGIN_FTR_SECTION
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
+nohpte_cont:
 hcall_real_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	/* Save DEC */
 	mfspr	r5,SPRN_DEC
@@ -632,36 +657,21 @@ hcall_real_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	add	r5,r5,r6
 	std	r5,VCPU_DEC_EXPIRES(r9)
 
-	/* Save HEIR (HV emulation assist reg) in last_inst
-	   if this is an HEI (HV emulation interrupt, e40) */
-	li	r3,-1
-BEGIN_FTR_SECTION
-	cmpwi	r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
-	bne	11f
-	mfspr	r3,SPRN_HEIR
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-11:	stw	r3,VCPU_LAST_INST(r9)
-
 	/* Save more register state  */
-	mfxer	r5
 	mfdar	r6
 	mfdsisr	r7
-	mfctr	r8
-
-	stw	r5, VCPU_XER(r9)
 	std	r6, VCPU_DAR(r9)
 	stw	r7, VCPU_DSISR(r9)
-	std	r8, VCPU_CTR(r9)
-	/* grab HDAR & HDSISR if HV data storage interrupt (HDSI) */
 BEGIN_FTR_SECTION
+	/* don't overwrite fault_dar/fault_dsisr if HDSI */
 	cmpwi	r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
 	beq	6f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-7:	std	r6, VCPU_FAULT_DAR(r9)
+	std	r6, VCPU_FAULT_DAR(r9)
 	stw	r7, VCPU_FAULT_DSISR(r9)
 
 	/* Save guest CTRL register, set runlatch to 1 */
-	mfspr	r6,SPRN_CTRLF
+6:	mfspr	r6,SPRN_CTRLF
 	stw	r6,VCPU_CTRL(r9)
 	andi.	r0,r6,1
 	bne	4f
@@ -1094,9 +1104,131 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mtspr	SPRN_HSRR1, r7
 	ba	0x500
 
-6:	mfspr	r6,SPRN_HDAR
-	mfspr	r7,SPRN_HDSISR
-	b	7b
+/*
+ * Check whether an HDSI is an HPTE not found fault or something else.
+ * If it is an HPTE not found fault that is due to the guest accessing
+ * a page that they have mapped but which we have paged out, then
+ * we continue on with the guest exit path.  In all other cases,
+ * reflect the HDSI to the guest as a DSI.
+ */
+kvmppc_hdsi:
+	mfspr	r4, SPRN_HDAR
+	mfspr	r6, SPRN_HDSISR
+	/* HPTE not found fault or protection fault? */
+	andis.	r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
+	beq	1f			/* if not, send it to the guest */
+	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
+	beq	3f
+	clrrdi	r0, r4, 28
+	PPC_SLBFEE_DOT(r5, r0)		/* if so, look up SLB */
+	bne	1f			/* if no SLB entry found */
+4:	std	r4, VCPU_FAULT_DAR(r9)
+	stw	r6, VCPU_FAULT_DSISR(r9)
+
+	/* Search the hash table. */
+	mr	r3, r9			/* vcpu pointer */
+	li	r7, 1			/* data fault */
+	bl	.kvmppc_hpte_hv_fault
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	ld	r10, VCPU_PC(r9)
+	ld	r11, VCPU_MSR(r9)
+	li	r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
+	cmpdi	r3, 0			/* retry the instruction */
+	beq	6f
+	cmpdi	r3, -1			/* handle in kernel mode */
+	beq	nohpte_cont
+	cmpdi	r3, -2			/* MMIO emulation; need instr word */
+	beq	2f
+
+	/* Synthesize a DSI for the guest */
+	ld	r4, VCPU_FAULT_DAR(r9)
+	mr	r6, r3
+1:	mtspr	SPRN_DAR, r4
+	mtspr	SPRN_DSISR, r6
+	mtspr	SPRN_SRR0, r10
+	mtspr	SPRN_SRR1, r11
+	li	r10, BOOK3S_INTERRUPT_DATA_STORAGE
+	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
+	rotldi	r11, r11, 63
+6:	ld	r7, VCPU_CTR(r9)
+	lwz	r8, VCPU_XER(r9)
+	mtctr	r7
+	mtxer	r8
+	mr	r4, r9
+	b	fast_guest_return
+
+3:	ld	r5, VCPU_KVM(r9)	/* not relocated, use VRMA */
+	ld	r5, KVM_VRMA_SLB_V(r5)
+	b	4b
+
+	/* If this is for emulated MMIO, load the instruction word */
+2:	li	r8, KVM_INST_FETCH_FAILED	/* In case lwz faults */
+
+	/* Set guest mode to 'jump over instruction' so if lwz faults
+	 * we'll just continue at the next IP. */
+	li	r0, KVM_GUEST_MODE_SKIP
+	stb	r0, HSTATE_IN_GUEST(r13)
+
+	/* Do the access with MSR:DR enabled */
+	mfmsr	r3
+	ori	r4, r3, MSR_DR		/* Enable paging for data */
+	mtmsrd	r4
+	lwz	r8, 0(r10)
+	mtmsrd	r3
+
+	/* Store the result */
+	stw	r8, VCPU_LAST_INST(r9)
+
+	/* Unset guest mode. */
+	li	r0, KVM_GUEST_MODE_NONE
+	stb	r0, HSTATE_IN_GUEST(r13)
+	b	nohpte_cont
+
+/*
+ * Similarly for an HISI, reflect it to the guest as an ISI unless
+ * it is an HPTE not found fault for a page that we have paged out.
+ */
+kvmppc_hisi:
+	andis.	r0, r11, SRR1_ISI_NOPT@h
+	beq	1f
+	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
+	beq	3f
+	clrrdi	r0, r10, 28
+	PPC_SLBFEE_DOT(r5, r0)		/* if so, look up SLB */
+	bne	1f			/* if no SLB entry found */
+4:
+	/* Search the hash table. */
+	mr	r3, r9			/* vcpu pointer */
+	mr	r4, r10
+	mr	r6, r11
+	li	r7, 0			/* instruction fault */
+	bl	.kvmppc_hpte_hv_fault
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	ld	r10, VCPU_PC(r9)
+	ld	r11, VCPU_MSR(r9)
+	li	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
+	cmpdi	r3, 0			/* retry the instruction */
+	beq	6f
+	cmpdi	r3, -1			/* handle in kernel mode */
+	beq	nohpte_cont
+
+	/* Synthesize an ISI for the guest */
+	mr	r11, r3
+1:	mtspr	SPRN_SRR0, r10
+	mtspr	SPRN_SRR1, r11
+	li	r10, BOOK3S_INTERRUPT_INST_STORAGE
+	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
+	rotldi	r11, r11, 63
+6:	ld	r7, VCPU_CTR(r9)
+	lwz	r8, VCPU_XER(r9)
+	mtctr	r7
+	mtxer	r8
+	mr	r4, r9
+	b	fast_guest_return
+
+3:	ld	r6, VCPU_KVM(r9)	/* not relocated, use VRMA */
+	ld	r5, KVM_VRMA_SLB_V(r6)
+	b	4b
 
 /*
  * Try to handle an hcall in real mode.
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index 7b0ee96c1bed..a59a25a13218 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -24,6 +24,7 @@
 #include <asm/kvm_fpu.h>
 #include <asm/reg.h>
 #include <asm/cacheflush.h>
+#include <asm/switch_to.h>
 #include <linux/vmalloc.h>
 
 /* #define DEBUG */
@@ -196,7 +197,8 @@ static int kvmppc_emulate_fpr_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_inject_pf(vcpu, addr, false);
 		goto done_load;
 	} else if (r == EMULATE_DO_MMIO) {
-		emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, len, 1);
+		emulated = kvmppc_handle_load(run, vcpu, KVM_MMIO_REG_FPR | rs,
+					      len, 1);
 		goto done_load;
 	}
 
@@ -286,11 +288,13 @@ static int kvmppc_emulate_psq_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_inject_pf(vcpu, addr, false);
 		goto done_load;
 	} else if ((r == EMULATE_DO_MMIO) && w) {
-		emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, 4, 1);
+		emulated = kvmppc_handle_load(run, vcpu, KVM_MMIO_REG_FPR | rs,
+					      4, 1);
 		vcpu->arch.qpr[rs] = tmp[1];
 		goto done_load;
 	} else if (r == EMULATE_DO_MMIO) {
-		emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FQPR | rs, 8, 1);
+		emulated = kvmppc_handle_load(run, vcpu, KVM_MMIO_REG_FQPR | rs,
+					      8, 1);
 		goto done_load;
 	}
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 220fcdf26978..642d88574b07 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -33,6 +33,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 #include <asm/mmu_context.h>
+#include <asm/switch_to.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
@@ -51,15 +52,19 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #define MSR_USER32 MSR_USER
 #define MSR_USER64 MSR_USER
 #define HW_PAGE_SIZE PAGE_SIZE
+#define __hard_irq_disable local_irq_disable
+#define __hard_irq_enable local_irq_enable
 #endif
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
-	memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb));
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
 	memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
 	       sizeof(get_paca()->shadow_vcpu));
-	to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max;
+	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+	svcpu_put(svcpu);
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_32
@@ -70,10 +75,12 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
-	memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb));
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
 	memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
 	       sizeof(get_paca()->shadow_vcpu));
-	to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max;
+	to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
+	svcpu_put(svcpu);
 #endif
 
 	kvmppc_giveup_ext(vcpu, MSR_FP);
@@ -151,14 +158,16 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 #ifdef CONFIG_PPC_BOOK3S_64
 	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
 		kvmppc_mmu_book3s_64_init(vcpu);
-		to_book3s(vcpu)->hior = 0xfff00000;
+		if (!to_book3s(vcpu)->hior_explicit)
+			to_book3s(vcpu)->hior = 0xfff00000;
 		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
 		vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	} else
 #endif
 	{
 		kvmppc_mmu_book3s_32_init(vcpu);
-		to_book3s(vcpu)->hior = 0;
+		if (!to_book3s(vcpu)->hior_explicit)
+			to_book3s(vcpu)->hior = 0;
 		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
 		vcpu->arch.cpu_type = KVM_CPU_3S_32;
 	}
@@ -308,19 +317,22 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	if (page_found == -ENOENT) {
 		/* Page not found in guest PTE entries */
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+		vcpu->arch.shared->dsisr = svcpu->fault_dsisr;
 		vcpu->arch.shared->msr |=
-			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+			(svcpu->shadow_srr1 & 0x00000000f8000000ULL);
+		svcpu_put(svcpu);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr =
-			to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
+		vcpu->arch.shared->dsisr = svcpu->fault_dsisr & ~DSISR_NOHPTE;
 		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
 		vcpu->arch.shared->msr |=
-			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+			svcpu->shadow_srr1 & 0x00000000f8000000ULL;
+		svcpu_put(svcpu);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
@@ -517,24 +529,29 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	run->ready_for_interrupt_injection = 1;
 
 	trace_kvm_book3s_exit(exit_nr, vcpu);
+	preempt_enable();
 	kvm_resched(vcpu);
 	switch (exit_nr) {
 	case BOOK3S_INTERRUPT_INST_STORAGE:
+	{
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		ulong shadow_srr1 = svcpu->shadow_srr1;
 		vcpu->stat.pf_instruc++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 		/* We set segments as unused segments when invalidating them. So
 		 * treat the respective fault as segment fault. */
-		if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT]
-		    == SR_INVALID) {
+		if (svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] == SR_INVALID) {
 			kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
 			r = RESUME_GUEST;
+			svcpu_put(svcpu);
 			break;
 		}
 #endif
+		svcpu_put(svcpu);
 
 		/* only care about PTEG not found errors, but leave NX alone */
-		if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) {
+		if (shadow_srr1 & 0x40000000) {
 			r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
 			vcpu->stat.sp_instruc++;
 		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
@@ -547,33 +564,37 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
 			r = RESUME_GUEST;
 		} else {
-			vcpu->arch.shared->msr |=
-				to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
+			vcpu->arch.shared->msr |= shadow_srr1 & 0x58000000;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			r = RESUME_GUEST;
 		}
 		break;
+	}
 	case BOOK3S_INTERRUPT_DATA_STORAGE:
 	{
 		ulong dar = kvmppc_get_fault_dar(vcpu);
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		u32 fault_dsisr = svcpu->fault_dsisr;
 		vcpu->stat.pf_storage++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 		/* We set segments as unused segments when invalidating them. So
 		 * treat the respective fault as segment fault. */
-		if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) {
+		if ((svcpu->sr[dar >> SID_SHIFT]) == SR_INVALID) {
 			kvmppc_mmu_map_segment(vcpu, dar);
 			r = RESUME_GUEST;
+			svcpu_put(svcpu);
 			break;
 		}
 #endif
+		svcpu_put(svcpu);
 
 		/* The only case we need to handle is missing shadow PTEs */
-		if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
+		if (fault_dsisr & DSISR_NOHPTE) {
 			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
 		} else {
 			vcpu->arch.shared->dar = dar;
-			vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+			vcpu->arch.shared->dsisr = fault_dsisr;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			r = RESUME_GUEST;
 		}
@@ -609,10 +630,13 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_PROGRAM:
 	{
 		enum emulation_result er;
+		struct kvmppc_book3s_shadow_vcpu *svcpu;
 		ulong flags;
 
 program_interrupt:
-		flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;
+		svcpu = svcpu_get(vcpu);
+		flags = svcpu->shadow_srr1 & 0x1f0000ull;
+		svcpu_put(svcpu);
 
 		if (vcpu->arch.shared->msr & MSR_PR) {
 #ifdef EXIT_DEBUG
@@ -740,20 +764,33 @@ program_interrupt:
 		r = RESUME_GUEST;
 		break;
 	default:
+	{
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		ulong shadow_srr1 = svcpu->shadow_srr1;
+		svcpu_put(svcpu);
 		/* Ugh - bork here! What did we get? */
 		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
-			exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1);
+			exit_nr, kvmppc_get_pc(vcpu), shadow_srr1);
 		r = RESUME_HOST;
 		BUG();
 		break;
 	}
-
+	}
 
 	if (!(r & RESUME_HOST)) {
 		/* To avoid clobbering exit_reason, only check for signals if
 		 * we aren't already exiting to userspace for some other
 		 * reason. */
+
+		/*
+		 * Interrupts could be timers for the guest which we have to
+		 * inject again, so let's postpone them until we're in the guest
+		 * and if we really did time things so badly, then we just exit
+		 * again due to a host external interrupt.
+		 */
+		__hard_irq_disable();
 		if (signal_pending(current)) {
+			__hard_irq_enable();
 #ifdef EXIT_DEBUG
 			printk(KERN_EMERG "KVM: Going back to host\n");
 #endif
@@ -761,10 +798,12 @@ program_interrupt:
 			run->exit_reason = KVM_EXIT_INTR;
 			r = -EINTR;
 		} else {
+			preempt_disable();
+
 			/* In case an interrupt came in that was triggered
 			 * from userspace (like DEC), we need to check what
 			 * to inject now! */
-			kvmppc_core_deliver_interrupts(vcpu);
+			kvmppc_core_prepare_to_enter(vcpu);
 		}
 	}
 
@@ -836,6 +875,38 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_PPC_HIOR:
+		r = put_user(to_book3s(vcpu)->hior, (u64 __user *)reg->addr);
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_PPC_HIOR:
+		r = get_user(to_book3s(vcpu)->hior, (u64 __user *)reg->addr);
+		if (!r)
+			to_book3s(vcpu)->hior_explicit = true;
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
 int kvmppc_core_check_processor_compat(void)
 {
 	return 0;
@@ -923,16 +994,31 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
 	ulong ext_msr;
 
+	preempt_disable();
+
 	/* Check if we can run the vcpu at all */
 	if (!vcpu->arch.sane) {
 		kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
+	kvmppc_core_prepare_to_enter(vcpu);
+
+	/*
+	 * Interrupts could be timers for the guest which we have to inject
+	 * again, so let's postpone them until we're in the guest and if we
+	 * really did time things so badly, then we just exit again due to
+	 * a host external interrupt.
+	 */
+	__hard_irq_disable();
+
 	/* No need to go into the guest when all we do is going out */
 	if (signal_pending(current)) {
+		__hard_irq_enable();
 		kvm_run->exit_reason = KVM_EXIT_INTR;
-		return -EINTR;
+		ret = -EINTR;
+		goto out;
 	}
 
 	/* Save FPU state in stack */
@@ -974,8 +1060,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	kvm_guest_exit();
 
-	local_irq_disable();
-
 	current->thread.regs->msr = ext_msr;
 
 	/* Make sure we save the guest FPU/Altivec/VSX state */
@@ -1002,9 +1086,50 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	current->thread.used_vsr = used_vsr;
 #endif
 
+out:
+	preempt_enable();
 	return ret;
 }
 
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+				      struct kvm_dirty_log *log)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm_vcpu *vcpu;
+	ulong ga, ga_end;
+	int is_dirty = 0;
+	int r;
+	unsigned long n;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = kvm_get_dirty_log(kvm, log, &is_dirty);
+	if (r)
+		goto out;
+
+	/* If nothing is dirty, don't bother messing with page tables. */
+	if (is_dirty) {
+		memslot = id_to_memslot(kvm->memslots, log->slot);
+
+		ga = memslot->base_gfn << PAGE_SHIFT;
+		ga_end = ga + (memslot->npages << PAGE_SHIFT);
+
+		kvm_for_each_vcpu(n, vcpu, kvm)
+			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
+
+		n = kvm_dirty_bitmap_bytes(memslot);
+		memset(memslot->dirty_bitmap, 0, n);
+	}
+
+	r = 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				      struct kvm_userspace_memory_region *mem)
 {
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index bb6c988f010a..ee9e1ee9c858 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -124,12 +124,6 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 	vcpu->arch.shared->msr = new_msr;
 
 	kvmppc_mmu_msr_notify(vcpu, old_msr);
-
-	if (vcpu->arch.shared->msr & MSR_WE) {
-		kvm_vcpu_block(vcpu);
-		kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
-	};
-
 	kvmppc_vcpu_sync_spe(vcpu);
 }
 
@@ -258,9 +252,11 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		allowed = vcpu->arch.shared->msr & MSR_ME;
 		msr_mask = 0;
 		break;
-	case BOOKE_IRQPRIO_EXTERNAL:
 	case BOOKE_IRQPRIO_DECREMENTER:
 	case BOOKE_IRQPRIO_FIT:
+		keep_irq = true;
+		/* fall through */
+	case BOOKE_IRQPRIO_EXTERNAL:
 		allowed = vcpu->arch.shared->msr & MSR_EE;
 		allowed = allowed && !crit;
 		msr_mask = MSR_CE|MSR_ME|MSR_DE;
@@ -276,7 +272,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		vcpu->arch.shared->srr1 = vcpu->arch.shared->msr;
 		vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
 		if (update_esr == true)
-			vcpu->arch.esr = vcpu->arch.queued_esr;
+			vcpu->arch.shared->esr = vcpu->arch.queued_esr;
 		if (update_dear == true)
 			vcpu->arch.shared->dar = vcpu->arch.queued_dear;
 		kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
@@ -288,13 +284,26 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	return allowed;
 }
 
-/* Check pending exceptions and deliver one, if possible. */
-void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
+static void update_timer_ints(struct kvm_vcpu *vcpu)
+{
+	if ((vcpu->arch.tcr & TCR_DIE) && (vcpu->arch.tsr & TSR_DIS))
+		kvmppc_core_queue_dec(vcpu);
+	else
+		kvmppc_core_dequeue_dec(vcpu);
+}
+
+static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
 {
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
-	unsigned long old_pending = vcpu->arch.pending_exceptions;
 	unsigned int priority;
 
+	if (vcpu->requests) {
+		if (kvm_check_request(KVM_REQ_PENDING_TIMER, vcpu)) {
+			smp_mb();
+			update_timer_ints(vcpu);
+		}
+	}
+
 	priority = __ffs(*pending);
 	while (priority <= BOOKE_IRQPRIO_MAX) {
 		if (kvmppc_booke_irqprio_deliver(vcpu, priority))
@@ -306,10 +315,24 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 	}
 
 	/* Tell the guest about our interrupt status */
-	if (*pending)
-		vcpu->arch.shared->int_pending = 1;
-	else if (old_pending)
-		vcpu->arch.shared->int_pending = 0;
+	vcpu->arch.shared->int_pending = !!*pending;
+}
+
+/* Check pending exceptions and deliver one, if possible. */
+void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(!irqs_disabled());
+
+	kvmppc_core_check_exceptions(vcpu);
+
+	if (vcpu->arch.shared->msr & MSR_WE) {
+		local_irq_enable();
+		kvm_vcpu_block(vcpu);
+		local_irq_disable();
+
+		kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
+		kvmppc_core_check_exceptions(vcpu);
+	};
 }
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
@@ -322,11 +345,21 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	}
 
 	local_irq_disable();
+
+	kvmppc_core_prepare_to_enter(vcpu);
+
+	if (signal_pending(current)) {
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		ret = -EINTR;
+		goto out;
+	}
+
 	kvm_guest_enter();
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 	kvm_guest_exit();
-	local_irq_enable();
 
+out:
+	local_irq_enable();
 	return ret;
 }
 
@@ -603,7 +636,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	local_irq_disable();
 
-	kvmppc_core_deliver_interrupts(vcpu);
+	kvmppc_core_prepare_to_enter(vcpu);
 
 	if (!(r & RESUME_HOST)) {
 		/* To avoid clobbering exit_reason, only check for signals if
@@ -628,6 +661,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	vcpu->arch.pc = 0;
 	vcpu->arch.shared->msr = 0;
 	vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
+	vcpu->arch.shared->pir = vcpu->vcpu_id;
 	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
 
 	vcpu->arch.shadow_pid = 1;
@@ -662,10 +696,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->sprg1 = vcpu->arch.shared->sprg1;
 	regs->sprg2 = vcpu->arch.shared->sprg2;
 	regs->sprg3 = vcpu->arch.shared->sprg3;
-	regs->sprg4 = vcpu->arch.sprg4;
-	regs->sprg5 = vcpu->arch.sprg5;
-	regs->sprg6 = vcpu->arch.sprg6;
-	regs->sprg7 = vcpu->arch.sprg7;
+	regs->sprg4 = vcpu->arch.shared->sprg4;
+	regs->sprg5 = vcpu->arch.shared->sprg5;
+	regs->sprg6 = vcpu->arch.shared->sprg6;
+	regs->sprg7 = vcpu->arch.shared->sprg7;
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
@@ -690,10 +724,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	vcpu->arch.shared->sprg1 = regs->sprg1;
 	vcpu->arch.shared->sprg2 = regs->sprg2;
 	vcpu->arch.shared->sprg3 = regs->sprg3;
-	vcpu->arch.sprg4 = regs->sprg4;
-	vcpu->arch.sprg5 = regs->sprg5;
-	vcpu->arch.sprg6 = regs->sprg6;
-	vcpu->arch.sprg7 = regs->sprg7;
+	vcpu->arch.shared->sprg4 = regs->sprg4;
+	vcpu->arch.shared->sprg5 = regs->sprg5;
+	vcpu->arch.shared->sprg6 = regs->sprg6;
+	vcpu->arch.shared->sprg7 = regs->sprg7;
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
@@ -711,7 +745,7 @@ static void get_sregs_base(struct kvm_vcpu *vcpu,
 	sregs->u.e.csrr0 = vcpu->arch.csrr0;
 	sregs->u.e.csrr1 = vcpu->arch.csrr1;
 	sregs->u.e.mcsr = vcpu->arch.mcsr;
-	sregs->u.e.esr = vcpu->arch.esr;
+	sregs->u.e.esr = vcpu->arch.shared->esr;
 	sregs->u.e.dear = vcpu->arch.shared->dar;
 	sregs->u.e.tsr = vcpu->arch.tsr;
 	sregs->u.e.tcr = vcpu->arch.tcr;
@@ -729,28 +763,19 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
 	vcpu->arch.csrr0 = sregs->u.e.csrr0;
 	vcpu->arch.csrr1 = sregs->u.e.csrr1;
 	vcpu->arch.mcsr = sregs->u.e.mcsr;
-	vcpu->arch.esr = sregs->u.e.esr;
+	vcpu->arch.shared->esr = sregs->u.e.esr;
 	vcpu->arch.shared->dar = sregs->u.e.dear;
 	vcpu->arch.vrsave = sregs->u.e.vrsave;
-	vcpu->arch.tcr = sregs->u.e.tcr;
+	kvmppc_set_tcr(vcpu, sregs->u.e.tcr);
 
-	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC)
+	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC) {
 		vcpu->arch.dec = sregs->u.e.dec;
-
-	kvmppc_emulate_dec(vcpu);
+		kvmppc_emulate_dec(vcpu);
+	}
 
 	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) {
-		/*
-		 * FIXME: existing KVM timer handling is incomplete.
-		 * TSR cannot be read by the guest, and its value in
-		 * vcpu->arch is always zero.  For now, just handle
-		 * the case where the caller is trying to inject a
-		 * decrementer interrupt.
-		 */
-
-		if ((sregs->u.e.tsr & TSR_DIS) &&
-		    (vcpu->arch.tcr & TCR_DIE))
-			kvmppc_core_queue_dec(vcpu);
+		vcpu->arch.tsr = sregs->u.e.tsr;
+		update_timer_ints(vcpu);
 	}
 
 	return 0;
@@ -761,7 +786,7 @@ static void get_sregs_arch206(struct kvm_vcpu *vcpu,
 {
 	sregs->u.e.features |= KVM_SREGS_E_ARCH206;
 
-	sregs->u.e.pir = 0;
+	sregs->u.e.pir = vcpu->vcpu_id;
 	sregs->u.e.mcsrr0 = vcpu->arch.mcsrr0;
 	sregs->u.e.mcsrr1 = vcpu->arch.mcsrr1;
 	sregs->u.e.decar = vcpu->arch.decar;
@@ -774,7 +799,7 @@ static int set_sregs_arch206(struct kvm_vcpu *vcpu,
 	if (!(sregs->u.e.features & KVM_SREGS_E_ARCH206))
 		return 0;
 
-	if (sregs->u.e.pir != 0)
+	if (sregs->u.e.pir != vcpu->vcpu_id)
 		return -EINVAL;
 
 	vcpu->arch.mcsrr0 = sregs->u.e.mcsrr0;
@@ -862,6 +887,16 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return kvmppc_core_set_sregs(vcpu, sregs);
 }
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	return -EINVAL;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	return -EINVAL;
+}
+
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -ENOTSUPP;
@@ -906,6 +941,33 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
 }
 
+void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
+{
+	vcpu->arch.tcr = new_tcr;
+	update_timer_ints(vcpu);
+}
+
+void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
+{
+	set_bits(tsr_bits, &vcpu->arch.tsr);
+	smp_wmb();
+	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	kvm_vcpu_kick(vcpu);
+}
+
+void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
+{
+	clear_bits(tsr_bits, &vcpu->arch.tsr);
+	update_timer_ints(vcpu);
+}
+
+void kvmppc_decrementer_func(unsigned long data)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+
+	kvmppc_set_tsr_bits(vcpu, TSR_DIS);
+}
+
 int __init kvmppc_booke_init(void)
 {
 	unsigned long ivor[16];
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 8e1fe33d64e5..2fe202705a3f 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -55,6 +55,10 @@ extern unsigned long kvmppc_booke_handlers;
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr);
 void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr);
 
+void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr);
+void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
+void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
+
 int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                             unsigned int inst, int *advance);
 int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt);
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 1260f5f24c0c..3e652da36534 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -13,6 +13,7 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  *
  * Copyright IBM Corp. 2008
+ * Copyright 2011 Freescale Semiconductor, Inc.
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
  */
@@ -107,7 +108,7 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_DEAR:
 		vcpu->arch.shared->dar = spr_val; break;
 	case SPRN_ESR:
-		vcpu->arch.esr = spr_val; break;
+		vcpu->arch.shared->esr = spr_val; break;
 	case SPRN_DBCR0:
 		vcpu->arch.dbcr0 = spr_val; break;
 	case SPRN_DBCR1:
@@ -115,23 +116,23 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_DBSR:
 		vcpu->arch.dbsr &= ~spr_val; break;
 	case SPRN_TSR:
-		vcpu->arch.tsr &= ~spr_val; break;
+		kvmppc_clr_tsr_bits(vcpu, spr_val);
+		break;
 	case SPRN_TCR:
-		vcpu->arch.tcr = spr_val;
-		kvmppc_emulate_dec(vcpu);
+		kvmppc_set_tcr(vcpu, spr_val);
 		break;
 
 	/* Note: SPRG4-7 are user-readable. These values are
 	 * loaded into the real SPRGs when resuming the
 	 * guest. */
 	case SPRN_SPRG4:
-		vcpu->arch.sprg4 = spr_val; break;
+		vcpu->arch.shared->sprg4 = spr_val; break;
 	case SPRN_SPRG5:
-		vcpu->arch.sprg5 = spr_val; break;
+		vcpu->arch.shared->sprg5 = spr_val; break;
 	case SPRN_SPRG6:
-		vcpu->arch.sprg6 = spr_val; break;
+		vcpu->arch.shared->sprg6 = spr_val; break;
 	case SPRN_SPRG7:
-		vcpu->arch.sprg7 = spr_val; break;
+		vcpu->arch.shared->sprg7 = spr_val; break;
 
 	case SPRN_IVPR:
 		vcpu->arch.ivpr = spr_val;
@@ -202,13 +203,17 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_DEAR:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar); break;
 	case SPRN_ESR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.esr); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->esr); break;
 	case SPRN_DBCR0:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr0); break;
 	case SPRN_DBCR1:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr1); break;
 	case SPRN_DBSR:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbsr); break;
+	case SPRN_TSR:
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tsr); break;
+	case SPRN_TCR:
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tcr); break;
 
 	case SPRN_IVOR0:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]);
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 42f2fb1f66e9..10d8ef602e5c 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -402,19 +402,25 @@ lightweight_exit:
 	/* Save vcpu pointer for the exception handlers. */
 	mtspr	SPRN_SPRG_WVCPU, r4
 
+	lwz	r5, VCPU_SHARED(r4)
+
 	/* Can't switch the stack pointer until after IVPR is switched,
 	 * because host interrupt handlers would get confused. */
 	lwz	r1, VCPU_GPR(r1)(r4)
 
-	/* Host interrupt handlers may have clobbered these guest-readable
-	 * SPRGs, so we need to reload them here with the guest's values. */
-	lwz	r3, VCPU_SPRG4(r4)
+	/*
+	 * Host interrupt handlers may have clobbered these
+	 * guest-readable SPRGs, or the guest kernel may have
+	 * written directly to the shared area, so we
+	 * need to reload them here with the guest's values.
+	 */
+	lwz	r3, VCPU_SHARED_SPRG4(r5)
 	mtspr	SPRN_SPRG4W, r3
-	lwz	r3, VCPU_SPRG5(r4)
+	lwz	r3, VCPU_SHARED_SPRG5(r5)
 	mtspr	SPRN_SPRG5W, r3
-	lwz	r3, VCPU_SPRG6(r4)
+	lwz	r3, VCPU_SHARED_SPRG6(r5)
 	mtspr	SPRN_SPRG6W, r3
-	lwz	r3, VCPU_SPRG7(r4)
+	lwz	r3, VCPU_SHARED_SPRG7(r5)
 	mtspr	SPRN_SPRG7W, r3
 
 #ifdef CONFIG_KVM_EXIT_TIMING
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 8c0d45a6faf7..ddcd896fa2ff 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -71,9 +71,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	vcpu->arch.pvr = mfspr(SPRN_PVR);
 	vcpu_e500->svr = mfspr(SPRN_SVR);
 
-	/* Since booke kvm only support one core, update all vcpus' PIR to 0 */
-	vcpu->vcpu_id = 0;
-
 	vcpu->arch.cpu_type = KVM_CPU_E500V2;
 
 	return 0;
@@ -118,12 +115,12 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
 	sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
 
-	sregs->u.e.mas0 = vcpu_e500->mas0;
-	sregs->u.e.mas1 = vcpu_e500->mas1;
-	sregs->u.e.mas2 = vcpu_e500->mas2;
-	sregs->u.e.mas7_3 = ((u64)vcpu_e500->mas7 << 32) | vcpu_e500->mas3;
-	sregs->u.e.mas4 = vcpu_e500->mas4;
-	sregs->u.e.mas6 = vcpu_e500->mas6;
+	sregs->u.e.mas0 = vcpu->arch.shared->mas0;
+	sregs->u.e.mas1 = vcpu->arch.shared->mas1;
+	sregs->u.e.mas2 = vcpu->arch.shared->mas2;
+	sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
+	sregs->u.e.mas4 = vcpu->arch.shared->mas4;
+	sregs->u.e.mas6 = vcpu->arch.shared->mas6;
 
 	sregs->u.e.mmucfg = mfspr(SPRN_MMUCFG);
 	sregs->u.e.tlbcfg[0] = vcpu_e500->tlb0cfg;
@@ -151,13 +148,12 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	}
 
 	if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
-		vcpu_e500->mas0 = sregs->u.e.mas0;
-		vcpu_e500->mas1 = sregs->u.e.mas1;
-		vcpu_e500->mas2 = sregs->u.e.mas2;
-		vcpu_e500->mas7 = sregs->u.e.mas7_3 >> 32;
-		vcpu_e500->mas3 = (u32)sregs->u.e.mas7_3;
-		vcpu_e500->mas4 = sregs->u.e.mas4;
-		vcpu_e500->mas6 = sregs->u.e.mas6;
+		vcpu->arch.shared->mas0 = sregs->u.e.mas0;
+		vcpu->arch.shared->mas1 = sregs->u.e.mas1;
+		vcpu->arch.shared->mas2 = sregs->u.e.mas2;
+		vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
+		vcpu->arch.shared->mas4 = sregs->u.e.mas4;
+		vcpu->arch.shared->mas6 = sregs->u.e.mas6;
 	}
 
 	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
@@ -233,6 +229,10 @@ static int __init kvmppc_e500_init(void)
 	unsigned long ivor[3];
 	unsigned long max_ivor = 0;
 
+	r = kvmppc_core_check_processor_compat();
+	if (r)
+		return r;
+
 	r = kvmppc_booke_init();
 	if (r)
 		return r;
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index d48ae396f41e..6d0b2bd54fb0 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -89,19 +89,23 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 			return EMULATE_FAIL;
 		vcpu_e500->pid[2] = spr_val; break;
 	case SPRN_MAS0:
-		vcpu_e500->mas0 = spr_val; break;
+		vcpu->arch.shared->mas0 = spr_val; break;
 	case SPRN_MAS1:
-		vcpu_e500->mas1 = spr_val; break;
+		vcpu->arch.shared->mas1 = spr_val; break;
 	case SPRN_MAS2:
-		vcpu_e500->mas2 = spr_val; break;
+		vcpu->arch.shared->mas2 = spr_val; break;
 	case SPRN_MAS3:
-		vcpu_e500->mas3 = spr_val; break;
+		vcpu->arch.shared->mas7_3 &= ~(u64)0xffffffff;
+		vcpu->arch.shared->mas7_3 |= spr_val;
+		break;
 	case SPRN_MAS4:
-		vcpu_e500->mas4 = spr_val; break;
+		vcpu->arch.shared->mas4 = spr_val; break;
 	case SPRN_MAS6:
-		vcpu_e500->mas6 = spr_val; break;
+		vcpu->arch.shared->mas6 = spr_val; break;
 	case SPRN_MAS7:
-		vcpu_e500->mas7 = spr_val; break;
+		vcpu->arch.shared->mas7_3 &= (u64)0xffffffff;
+		vcpu->arch.shared->mas7_3 |= (u64)spr_val << 32;
+		break;
 	case SPRN_L1CSR0:
 		vcpu_e500->l1csr0 = spr_val;
 		vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
@@ -143,6 +147,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
+	unsigned long val;
 
 	switch (sprn) {
 	case SPRN_PID:
@@ -152,20 +157,23 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_PID2:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[2]); break;
 	case SPRN_MAS0:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas0); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas0); break;
 	case SPRN_MAS1:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas1); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas1); break;
 	case SPRN_MAS2:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas2); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas2); break;
 	case SPRN_MAS3:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas3); break;
+		val = (u32)vcpu->arch.shared->mas7_3;
+		kvmppc_set_gpr(vcpu, rt, val);
+		break;
 	case SPRN_MAS4:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas4); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas4); break;
 	case SPRN_MAS6:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas6); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas6); break;
 	case SPRN_MAS7:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas7); break;
-
+		val = vcpu->arch.shared->mas7_3 >> 32;
+		kvmppc_set_gpr(vcpu, rt, val);
+		break;
 	case SPRN_TLB0CFG:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break;
 	case SPRN_TLB1CFG:
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 13c432ea2fa8..6e53e4164de1 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -12,12 +12,19 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/highmem.h>
+#include <linux/log2.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/rwsem.h>
+#include <linux/vmalloc.h>
+#include <linux/hugetlb.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_e500.h>
 
@@ -26,7 +33,7 @@
 #include "trace.h"
 #include "timing.h"
 
-#define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
+#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
 
 struct id {
 	unsigned long val;
@@ -63,7 +70,14 @@ static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
  * The valid range of shadow ID is [1..255] */
 static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
 
-static unsigned int tlb1_entry_num;
+static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
+
+static struct kvm_book3e_206_tlb_entry *get_entry(
+	struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
+{
+	int offset = vcpu_e500->gtlb_offset[tlbsel];
+	return &vcpu_e500->gtlb_arch[offset + entry];
+}
 
 /*
  * Allocate a free shadow id and setup a valid sid mapping in given entry.
@@ -116,13 +130,11 @@ static inline int local_sid_lookup(struct id *entry)
 	return -1;
 }
 
-/* Invalidate all id mappings on local core */
+/* Invalidate all id mappings on local core -- call with preempt disabled */
 static inline void local_sid_destroy_all(void)
 {
-	preempt_disable();
 	__get_cpu_var(pcpu_last_used_sid) = 0;
 	memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
-	preempt_enable();
 }
 
 static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
@@ -218,34 +230,13 @@ void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
 	preempt_enable();
 }
 
-void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct tlbe *tlbe;
-	int i, tlbsel;
-
-	printk("| %8s | %8s | %8s | %8s | %8s |\n",
-			"nr", "mas1", "mas2", "mas3", "mas7");
-
-	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
-		printk("Guest TLB%d:\n", tlbsel);
-		for (i = 0; i < vcpu_e500->gtlb_size[tlbsel]; i++) {
-			tlbe = &vcpu_e500->gtlb_arch[tlbsel][i];
-			if (tlbe->mas1 & MAS1_VALID)
-				printk(" G[%d][%3d] |  %08X | %08X | %08X | %08X |\n",
-					tlbsel, i, tlbe->mas1, tlbe->mas2,
-					tlbe->mas3, tlbe->mas7);
-		}
-	}
-}
-
-static inline unsigned int tlb0_get_next_victim(
+static inline unsigned int gtlb0_get_next_victim(
 		struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	unsigned int victim;
 
 	victim = vcpu_e500->gtlb_nv[0]++;
-	if (unlikely(vcpu_e500->gtlb_nv[0] >= KVM_E500_TLB0_WAY_NUM))
+	if (unlikely(vcpu_e500->gtlb_nv[0] >= vcpu_e500->gtlb_params[0].ways))
 		vcpu_e500->gtlb_nv[0] = 0;
 
 	return victim;
@@ -254,12 +245,12 @@ static inline unsigned int tlb0_get_next_victim(
 static inline unsigned int tlb1_max_shadow_size(void)
 {
 	/* reserve one entry for magic page */
-	return tlb1_entry_num - tlbcam_index - 1;
+	return host_tlb_params[1].entries - tlbcam_index - 1;
 }
 
-static inline int tlbe_is_writable(struct tlbe *tlbe)
+static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
 {
-	return tlbe->mas3 & (MAS3_SW|MAS3_UW);
+	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
 }
 
 static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
@@ -290,40 +281,66 @@ static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
 /*
  * writing shadow tlb entry to host TLB
  */
-static inline void __write_host_tlbe(struct tlbe *stlbe, uint32_t mas0)
+static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
+				     uint32_t mas0)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
 	mtspr(SPRN_MAS0, mas0);
 	mtspr(SPRN_MAS1, stlbe->mas1);
-	mtspr(SPRN_MAS2, stlbe->mas2);
-	mtspr(SPRN_MAS3, stlbe->mas3);
-	mtspr(SPRN_MAS7, stlbe->mas7);
+	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
+	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
+	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
 	asm volatile("isync; tlbwe" : : : "memory");
 	local_irq_restore(flags);
+
+	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
+	                              stlbe->mas2, stlbe->mas7_3);
+}
+
+/*
+ * Acquire a mas0 with victim hint, as if we just took a TLB miss.
+ *
+ * We don't care about the address we're searching for, other than that it's
+ * in the right set and is not present in the TLB.  Using a zero PID and a
+ * userspace address means we don't have to set and then restore MAS5, or
+ * calculate a proper MAS6 value.
+ */
+static u32 get_host_mas0(unsigned long eaddr)
+{
+	unsigned long flags;
+	u32 mas0;
+
+	local_irq_save(flags);
+	mtspr(SPRN_MAS6, 0);
+	asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET));
+	mas0 = mfspr(SPRN_MAS0);
+	local_irq_restore(flags);
+
+	return mas0;
 }
 
+/* sesel is for tlb1 only */
 static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
-		int tlbsel, int esel, struct tlbe *stlbe)
+		int tlbsel, int sesel, struct kvm_book3e_206_tlb_entry *stlbe)
 {
+	u32 mas0;
+
 	if (tlbsel == 0) {
-		__write_host_tlbe(stlbe,
-				  MAS0_TLBSEL(0) |
-				  MAS0_ESEL(esel & (KVM_E500_TLB0_WAY_NUM - 1)));
+		mas0 = get_host_mas0(stlbe->mas2);
+		__write_host_tlbe(stlbe, mas0);
 	} else {
 		__write_host_tlbe(stlbe,
 				  MAS0_TLBSEL(1) |
-				  MAS0_ESEL(to_htlb1_esel(esel)));
+				  MAS0_ESEL(to_htlb1_esel(sesel)));
 	}
-	trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
-			     stlbe->mas3, stlbe->mas7);
 }
 
 void kvmppc_map_magic(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct tlbe magic;
+	struct kvm_book3e_206_tlb_entry magic;
 	ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
 	unsigned int stid;
 	pfn_t pfn;
@@ -337,9 +354,9 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu)
 	magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) |
 		     MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 	magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M;
-	magic.mas3 = (pfn << PAGE_SHIFT) |
-		     MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
-	magic.mas7 = pfn >> (32 - PAGE_SHIFT);
+	magic.mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+		       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
+	magic.mas8 = 0;
 
 	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
 	preempt_enable();
@@ -357,10 +374,11 @@ void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
 {
 }
 
-static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
-					 int tlbsel, int esel)
+static void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500,
+				int tlbsel, int esel)
 {
-	struct tlbe *gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+	struct kvm_book3e_206_tlb_entry *gtlbe =
+		get_entry(vcpu_e500, tlbsel, esel);
 	struct vcpu_id_table *idt = vcpu_e500->idt;
 	unsigned int pr, tid, ts, pid;
 	u32 val, eaddr;
@@ -414,25 +432,57 @@ static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
 	preempt_enable();
 }
 
+static int tlb0_set_base(gva_t addr, int sets, int ways)
+{
+	int set_base;
+
+	set_base = (addr >> PAGE_SHIFT) & (sets - 1);
+	set_base *= ways;
+
+	return set_base;
+}
+
+static int gtlb0_set_base(struct kvmppc_vcpu_e500 *vcpu_e500, gva_t addr)
+{
+	return tlb0_set_base(addr, vcpu_e500->gtlb_params[0].sets,
+			     vcpu_e500->gtlb_params[0].ways);
+}
+
+static unsigned int get_tlb_esel(struct kvm_vcpu *vcpu, int tlbsel)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int esel = get_tlb_esel_bit(vcpu);
+
+	if (tlbsel == 0) {
+		esel &= vcpu_e500->gtlb_params[0].ways - 1;
+		esel += gtlb0_set_base(vcpu_e500, vcpu->arch.shared->mas2);
+	} else {
+		esel &= vcpu_e500->gtlb_params[tlbsel].entries - 1;
+	}
+
+	return esel;
+}
+
 /* Search the guest TLB for a matching entry. */
 static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
 		gva_t eaddr, int tlbsel, unsigned int pid, int as)
 {
-	int size = vcpu_e500->gtlb_size[tlbsel];
-	int set_base;
+	int size = vcpu_e500->gtlb_params[tlbsel].entries;
+	unsigned int set_base, offset;
 	int i;
 
 	if (tlbsel == 0) {
-		int mask = size / KVM_E500_TLB0_WAY_NUM - 1;
-		set_base = (eaddr >> PAGE_SHIFT) & mask;
-		set_base *= KVM_E500_TLB0_WAY_NUM;
-		size = KVM_E500_TLB0_WAY_NUM;
+		set_base = gtlb0_set_base(vcpu_e500, eaddr);
+		size = vcpu_e500->gtlb_params[0].ways;
 	} else {
 		set_base = 0;
 	}
 
+	offset = vcpu_e500->gtlb_offset[tlbsel];
+
 	for (i = 0; i < size; i++) {
-		struct tlbe *tlbe = &vcpu_e500->gtlb_arch[tlbsel][set_base + i];
+		struct kvm_book3e_206_tlb_entry *tlbe =
+			&vcpu_e500->gtlb_arch[offset + set_base + i];
 		unsigned int tid;
 
 		if (eaddr < get_tlb_eaddr(tlbe))
@@ -457,27 +507,55 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
 	return -1;
 }
 
-static inline void kvmppc_e500_priv_setup(struct tlbe_priv *priv,
-					  struct tlbe *gtlbe,
-					  pfn_t pfn)
+static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
+					 struct kvm_book3e_206_tlb_entry *gtlbe,
+					 pfn_t pfn)
 {
-	priv->pfn = pfn;
-	priv->flags = E500_TLB_VALID;
+	ref->pfn = pfn;
+	ref->flags = E500_TLB_VALID;
 
 	if (tlbe_is_writable(gtlbe))
-		priv->flags |= E500_TLB_DIRTY;
+		ref->flags |= E500_TLB_DIRTY;
 }
 
-static inline void kvmppc_e500_priv_release(struct tlbe_priv *priv)
+static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 {
-	if (priv->flags & E500_TLB_VALID) {
-		if (priv->flags & E500_TLB_DIRTY)
-			kvm_release_pfn_dirty(priv->pfn);
+	if (ref->flags & E500_TLB_VALID) {
+		if (ref->flags & E500_TLB_DIRTY)
+			kvm_release_pfn_dirty(ref->pfn);
 		else
-			kvm_release_pfn_clean(priv->pfn);
+			kvm_release_pfn_clean(ref->pfn);
+
+		ref->flags = 0;
+	}
+}
+
+static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int tlbsel = 0;
+	int i;
+
+	for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
+		struct tlbe_ref *ref =
+			&vcpu_e500->gtlb_priv[tlbsel][i].ref;
+		kvmppc_e500_ref_release(ref);
+	}
+}
+
+static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int stlbsel = 1;
+	int i;
+
+	kvmppc_e500_id_table_reset_all(vcpu_e500);
 
-		priv->flags = 0;
+	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
+		struct tlbe_ref *ref =
+			&vcpu_e500->tlb_refs[stlbsel][i];
+		kvmppc_e500_ref_release(ref);
 	}
+
+	clear_tlb_privs(vcpu_e500);
 }
 
 static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
@@ -488,59 +566,54 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 	int tlbsel;
 
 	/* since we only have two TLBs, only lower bit is used. */
-	tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
-	victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
-	pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
-	tsized = (vcpu_e500->mas4 >> 7) & 0x1f;
+	tlbsel = (vcpu->arch.shared->mas4 >> 28) & 0x1;
+	victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;
+	pidsel = (vcpu->arch.shared->mas4 >> 16) & 0xf;
+	tsized = (vcpu->arch.shared->mas4 >> 7) & 0x1f;
 
-	vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
+	vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
 		| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
-	vcpu_e500->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
+	vcpu->arch.shared->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
 		| MAS1_TID(vcpu_e500->pid[pidsel])
 		| MAS1_TSIZE(tsized);
-	vcpu_e500->mas2 = (eaddr & MAS2_EPN)
-		| (vcpu_e500->mas4 & MAS2_ATTRIB_MASK);
-	vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
-	vcpu_e500->mas6 = (vcpu_e500->mas6 & MAS6_SPID1)
+	vcpu->arch.shared->mas2 = (eaddr & MAS2_EPN)
+		| (vcpu->arch.shared->mas4 & MAS2_ATTRIB_MASK);
+	vcpu->arch.shared->mas7_3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
+	vcpu->arch.shared->mas6 = (vcpu->arch.shared->mas6 & MAS6_SPID1)
 		| (get_cur_pid(vcpu) << 16)
 		| (as ? MAS6_SAS : 0);
-	vcpu_e500->mas7 = 0;
 }
 
-static inline void kvmppc_e500_setup_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
-					   struct tlbe *gtlbe, int tsize,
-					   struct tlbe_priv *priv,
-					   u64 gvaddr, struct tlbe *stlbe)
+/* TID must be supplied by the caller */
+static inline void kvmppc_e500_setup_stlbe(
+	struct kvmppc_vcpu_e500 *vcpu_e500,
+	struct kvm_book3e_206_tlb_entry *gtlbe,
+	int tsize, struct tlbe_ref *ref, u64 gvaddr,
+	struct kvm_book3e_206_tlb_entry *stlbe)
 {
-	pfn_t pfn = priv->pfn;
-	unsigned int stid;
+	pfn_t pfn = ref->pfn;
 
-	stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe),
-				   get_tlb_tid(gtlbe),
-				   get_cur_pr(&vcpu_e500->vcpu), 0);
+	BUG_ON(!(ref->flags & E500_TLB_VALID));
 
 	/* Force TS=1 IPROT=0 for all guest mappings. */
-	stlbe->mas1 = MAS1_TSIZE(tsize)
-		| MAS1_TID(stid) | MAS1_TS | MAS1_VALID;
+	stlbe->mas1 = MAS1_TSIZE(tsize) | MAS1_TS | MAS1_VALID;
 	stlbe->mas2 = (gvaddr & MAS2_EPN)
 		| e500_shadow_mas2_attrib(gtlbe->mas2,
 				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
-	stlbe->mas3 = ((pfn << PAGE_SHIFT) & MAS3_RPN)
-		| e500_shadow_mas3_attrib(gtlbe->mas3,
+	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT)
+		| e500_shadow_mas3_attrib(gtlbe->mas7_3,
 				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
-	stlbe->mas7 = (pfn >> (32 - PAGE_SHIFT)) & MAS7_RPN;
 }
 
-
 static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-	u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, int tlbsel, int esel,
-	struct tlbe *stlbe)
+	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
+	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
+	struct tlbe_ref *ref)
 {
 	struct kvm_memory_slot *slot;
 	unsigned long pfn, hva;
 	int pfnmap = 0;
 	int tsize = BOOK3E_PAGESZ_4K;
-	struct tlbe_priv *priv;
 
 	/*
 	 * Translate guest physical to true physical, acquiring
@@ -621,12 +694,31 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 				pfn &= ~(tsize_pages - 1);
 				break;
 			}
+		} else if (vma && hva >= vma->vm_start &&
+			   (vma->vm_flags & VM_HUGETLB)) {
+			unsigned long psize = vma_kernel_pagesize(vma);
+
+			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
+				MAS1_TSIZE_SHIFT;
+
+			/*
+			 * Take the largest page size that satisfies both host
+			 * and guest mapping
+			 */
+			tsize = min(__ilog2(psize) - 10, tsize);
+
+			/*
+			 * e500 doesn't implement the lowest tsize bit,
+			 * or 1K pages.
+			 */
+			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
 		}
 
 		up_read(&current->mm->mmap_sem);
 	}
 
 	if (likely(!pfnmap)) {
+		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
 		pfn = gfn_to_pfn_memslot(vcpu_e500->vcpu.kvm, slot, gfn);
 		if (is_error_pfn(pfn)) {
 			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
@@ -634,45 +726,52 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 			kvm_release_pfn_clean(pfn);
 			return;
 		}
+
+		/* Align guest and physical address to page map boundaries */
+		pfn &= ~(tsize_pages - 1);
+		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
 	}
 
-	/* Drop old priv and setup new one. */
-	priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
-	kvmppc_e500_priv_release(priv);
-	kvmppc_e500_priv_setup(priv, gtlbe, pfn);
+	/* Drop old ref and setup new one. */
+	kvmppc_e500_ref_release(ref);
+	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
-	kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, priv, gvaddr, stlbe);
+	kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, ref, gvaddr, stlbe);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
-static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-				int esel, struct tlbe *stlbe)
+static void kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+				 int esel,
+				 struct kvm_book3e_206_tlb_entry *stlbe)
 {
-	struct tlbe *gtlbe;
+	struct kvm_book3e_206_tlb_entry *gtlbe;
+	struct tlbe_ref *ref;
 
-	gtlbe = &vcpu_e500->gtlb_arch[0][esel];
+	gtlbe = get_entry(vcpu_e500, 0, esel);
+	ref = &vcpu_e500->gtlb_priv[0][esel].ref;
 
 	kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
 			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
-			gtlbe, 0, esel, stlbe);
-
-	return esel;
+			gtlbe, 0, stlbe, ref);
 }
 
 /* Caller must ensure that the specified guest TLB entry is safe to insert into
  * the shadow TLB. */
 /* XXX for both one-one and one-to-many , for now use TLB1 */
 static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-		u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, struct tlbe *stlbe)
+		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
+		struct kvm_book3e_206_tlb_entry *stlbe)
 {
+	struct tlbe_ref *ref;
 	unsigned int victim;
 
-	victim = vcpu_e500->gtlb_nv[1]++;
+	victim = vcpu_e500->host_tlb1_nv++;
 
-	if (unlikely(vcpu_e500->gtlb_nv[1] >= tlb1_max_shadow_size()))
-		vcpu_e500->gtlb_nv[1] = 0;
+	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
+		vcpu_e500->host_tlb1_nv = 0;
 
-	kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, victim, stlbe);
+	ref = &vcpu_e500->tlb_refs[1][victim];
+	kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, ref);
 
 	return victim;
 }
@@ -689,7 +788,8 @@ static inline int kvmppc_e500_gtlbe_invalidate(
 				struct kvmppc_vcpu_e500 *vcpu_e500,
 				int tlbsel, int esel)
 {
-	struct tlbe *gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+	struct kvm_book3e_206_tlb_entry *gtlbe =
+		get_entry(vcpu_e500, tlbsel, esel);
 
 	if (unlikely(get_tlb_iprot(gtlbe)))
 		return -1;
@@ -704,10 +804,10 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
 	int esel;
 
 	if (value & MMUCSR0_TLB0FI)
-		for (esel = 0; esel < vcpu_e500->gtlb_size[0]; esel++)
+		for (esel = 0; esel < vcpu_e500->gtlb_params[0].entries; esel++)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 0, esel);
 	if (value & MMUCSR0_TLB1FI)
-		for (esel = 0; esel < vcpu_e500->gtlb_size[1]; esel++)
+		for (esel = 0; esel < vcpu_e500->gtlb_params[1].entries; esel++)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);
 
 	/* Invalidate all vcpu id mappings */
@@ -732,7 +832,8 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
 
 	if (ia) {
 		/* invalidate all entries */
-		for (esel = 0; esel < vcpu_e500->gtlb_size[tlbsel]; esel++)
+		for (esel = 0; esel < vcpu_e500->gtlb_params[tlbsel].entries;
+		     esel++)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
 	} else {
 		ea &= 0xfffff000;
@@ -752,18 +853,17 @@ int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int tlbsel, esel;
-	struct tlbe *gtlbe;
+	struct kvm_book3e_206_tlb_entry *gtlbe;
 
-	tlbsel = get_tlb_tlbsel(vcpu_e500);
-	esel = get_tlb_esel(vcpu_e500, tlbsel);
+	tlbsel = get_tlb_tlbsel(vcpu);
+	esel = get_tlb_esel(vcpu, tlbsel);
 
-	gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
-	vcpu_e500->mas0 &= ~MAS0_NV(~0);
-	vcpu_e500->mas0 |= MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
-	vcpu_e500->mas1 = gtlbe->mas1;
-	vcpu_e500->mas2 = gtlbe->mas2;
-	vcpu_e500->mas3 = gtlbe->mas3;
-	vcpu_e500->mas7 = gtlbe->mas7;
+	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
+	vcpu->arch.shared->mas0 &= ~MAS0_NV(~0);
+	vcpu->arch.shared->mas0 |= MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
+	vcpu->arch.shared->mas1 = gtlbe->mas1;
+	vcpu->arch.shared->mas2 = gtlbe->mas2;
+	vcpu->arch.shared->mas7_3 = gtlbe->mas7_3;
 
 	return EMULATE_DONE;
 }
@@ -771,10 +871,10 @@ int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
 int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	int as = !!get_cur_sas(vcpu_e500);
-	unsigned int pid = get_cur_spid(vcpu_e500);
+	int as = !!get_cur_sas(vcpu);
+	unsigned int pid = get_cur_spid(vcpu);
 	int esel, tlbsel;
-	struct tlbe *gtlbe = NULL;
+	struct kvm_book3e_206_tlb_entry *gtlbe = NULL;
 	gva_t ea;
 
 	ea = kvmppc_get_gpr(vcpu, rb);
@@ -782,70 +882,90 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
 	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
 		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
 		if (esel >= 0) {
-			gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+			gtlbe = get_entry(vcpu_e500, tlbsel, esel);
 			break;
 		}
 	}
 
 	if (gtlbe) {
-		vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel)
+		esel &= vcpu_e500->gtlb_params[tlbsel].ways - 1;
+
+		vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel)
 			| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
-		vcpu_e500->mas1 = gtlbe->mas1;
-		vcpu_e500->mas2 = gtlbe->mas2;
-		vcpu_e500->mas3 = gtlbe->mas3;
-		vcpu_e500->mas7 = gtlbe->mas7;
+		vcpu->arch.shared->mas1 = gtlbe->mas1;
+		vcpu->arch.shared->mas2 = gtlbe->mas2;
+		vcpu->arch.shared->mas7_3 = gtlbe->mas7_3;
 	} else {
 		int victim;
 
 		/* since we only have two TLBs, only lower bit is used. */
-		tlbsel = vcpu_e500->mas4 >> 28 & 0x1;
-		victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
+		tlbsel = vcpu->arch.shared->mas4 >> 28 & 0x1;
+		victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;
 
-		vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
+		vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel)
+			| MAS0_ESEL(victim)
 			| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
-		vcpu_e500->mas1 = (vcpu_e500->mas6 & MAS6_SPID0)
-			| (vcpu_e500->mas6 & (MAS6_SAS ? MAS1_TS : 0))
-			| (vcpu_e500->mas4 & MAS4_TSIZED(~0));
-		vcpu_e500->mas2 &= MAS2_EPN;
-		vcpu_e500->mas2 |= vcpu_e500->mas4 & MAS2_ATTRIB_MASK;
-		vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
-		vcpu_e500->mas7 = 0;
+		vcpu->arch.shared->mas1 =
+			  (vcpu->arch.shared->mas6 & MAS6_SPID0)
+			| (vcpu->arch.shared->mas6 & (MAS6_SAS ? MAS1_TS : 0))
+			| (vcpu->arch.shared->mas4 & MAS4_TSIZED(~0));
+		vcpu->arch.shared->mas2 &= MAS2_EPN;
+		vcpu->arch.shared->mas2 |= vcpu->arch.shared->mas4 &
+					   MAS2_ATTRIB_MASK;
+		vcpu->arch.shared->mas7_3 &= MAS3_U0 | MAS3_U1 |
+					     MAS3_U2 | MAS3_U3;
 	}
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBSX_EXITS);
 	return EMULATE_DONE;
 }
 
+/* sesel is for tlb1 only */
+static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+			struct kvm_book3e_206_tlb_entry *gtlbe,
+			struct kvm_book3e_206_tlb_entry *stlbe,
+			int stlbsel, int sesel)
+{
+	int stid;
+
+	preempt_disable();
+	stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe),
+				   get_tlb_tid(gtlbe),
+				   get_cur_pr(&vcpu_e500->vcpu), 0);
+
+	stlbe->mas1 |= MAS1_TID(stid);
+	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
+	preempt_enable();
+}
+
 int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct tlbe *gtlbe;
+	struct kvm_book3e_206_tlb_entry *gtlbe;
 	int tlbsel, esel;
 
-	tlbsel = get_tlb_tlbsel(vcpu_e500);
-	esel = get_tlb_esel(vcpu_e500, tlbsel);
+	tlbsel = get_tlb_tlbsel(vcpu);
+	esel = get_tlb_esel(vcpu, tlbsel);
 
-	gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
 
 	if (get_tlb_v(gtlbe))
-		kvmppc_e500_stlbe_invalidate(vcpu_e500, tlbsel, esel);
+		inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
 
-	gtlbe->mas1 = vcpu_e500->mas1;
-	gtlbe->mas2 = vcpu_e500->mas2;
-	gtlbe->mas3 = vcpu_e500->mas3;
-	gtlbe->mas7 = vcpu_e500->mas7;
+	gtlbe->mas1 = vcpu->arch.shared->mas1;
+	gtlbe->mas2 = vcpu->arch.shared->mas2;
+	gtlbe->mas7_3 = vcpu->arch.shared->mas7_3;
 
-	trace_kvm_gtlb_write(vcpu_e500->mas0, gtlbe->mas1, gtlbe->mas2,
-			     gtlbe->mas3, gtlbe->mas7);
+	trace_kvm_booke206_gtlb_write(vcpu->arch.shared->mas0, gtlbe->mas1,
+	                              gtlbe->mas2, gtlbe->mas7_3);
 
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
-		struct tlbe stlbe;
+		struct kvm_book3e_206_tlb_entry stlbe;
 		int stlbsel, sesel;
 		u64 eaddr;
 		u64 raddr;
 
-		preempt_disable();
 		switch (tlbsel) {
 		case 0:
 			/* TLB0 */
@@ -853,7 +973,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 			gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 
 			stlbsel = 0;
-			sesel = kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
+			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
+			sesel = 0; /* unused */
 
 			break;
 
@@ -874,8 +995,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 		default:
 			BUG();
 		}
-		write_host_tlbe(vcpu_e500, stlbsel, sesel, &stlbe);
-		preempt_enable();
+
+		write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
 	}
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
@@ -914,9 +1035,11 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
 			gva_t eaddr)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct tlbe *gtlbe =
-		&vcpu_e500->gtlb_arch[tlbsel_of(index)][esel_of(index)];
-	u64 pgmask = get_tlb_bytes(gtlbe) - 1;
+	struct kvm_book3e_206_tlb_entry *gtlbe;
+	u64 pgmask;
+
+	gtlbe = get_entry(vcpu_e500, tlbsel_of(index), esel_of(index));
+	pgmask = get_tlb_bytes(gtlbe) - 1;
 
 	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
 }
@@ -930,22 +1053,21 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	struct tlbe_priv *priv;
-	struct tlbe *gtlbe, stlbe;
+	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
 	int tlbsel = tlbsel_of(index);
 	int esel = esel_of(index);
 	int stlbsel, sesel;
 
-	gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
 
-	preempt_disable();
 	switch (tlbsel) {
 	case 0:
 		stlbsel = 0;
-		sesel = esel;
-		priv = &vcpu_e500->gtlb_priv[stlbsel][sesel];
+		sesel = 0; /* unused */
+		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
 		kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, BOOK3E_PAGESZ_4K,
-					priv, eaddr, &stlbe);
+					&priv->ref, eaddr, &stlbe);
 		break;
 
 	case 1: {
@@ -962,8 +1084,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 		break;
 	}
 
-	write_host_tlbe(vcpu_e500, stlbsel, sesel, &stlbe);
-	preempt_enable();
+	write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
 }
 
 int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
@@ -993,85 +1114,279 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
 
 void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-	struct tlbe *tlbe;
+	struct kvm_book3e_206_tlb_entry *tlbe;
 
 	/* Insert large initial mapping for guest. */
-	tlbe = &vcpu_e500->gtlb_arch[1][0];
+	tlbe = get_entry(vcpu_e500, 1, 0);
 	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
 	tlbe->mas2 = 0;
-	tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
-	tlbe->mas7 = 0;
+	tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
 
 	/* 4K map for serial output. Used by kernel wrapper. */
-	tlbe = &vcpu_e500->gtlb_arch[1][1];
+	tlbe = get_entry(vcpu_e500, 1, 1);
 	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
-	tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
-	tlbe->mas7 = 0;
+	tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+}
+
+static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int i;
+
+	clear_tlb_refs(vcpu_e500);
+	kfree(vcpu_e500->gtlb_priv[0]);
+	kfree(vcpu_e500->gtlb_priv[1]);
+
+	if (vcpu_e500->shared_tlb_pages) {
+		vfree((void *)(round_down((uintptr_t)vcpu_e500->gtlb_arch,
+					  PAGE_SIZE)));
+
+		for (i = 0; i < vcpu_e500->num_shared_tlb_pages; i++) {
+			set_page_dirty_lock(vcpu_e500->shared_tlb_pages[i]);
+			put_page(vcpu_e500->shared_tlb_pages[i]);
+		}
+
+		vcpu_e500->num_shared_tlb_pages = 0;
+		vcpu_e500->shared_tlb_pages = NULL;
+	} else {
+		kfree(vcpu_e500->gtlb_arch);
+	}
+
+	vcpu_e500->gtlb_arch = NULL;
+}
+
+int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
+			      struct kvm_config_tlb *cfg)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct kvm_book3e_206_tlb_params params;
+	char *virt;
+	struct page **pages;
+	struct tlbe_priv *privs[2] = {};
+	size_t array_len;
+	u32 sets;
+	int num_pages, ret, i;
+
+	if (cfg->mmu_type != KVM_MMU_FSL_BOOKE_NOHV)
+		return -EINVAL;
+
+	if (copy_from_user(&params, (void __user *)(uintptr_t)cfg->params,
+			   sizeof(params)))
+		return -EFAULT;
+
+	if (params.tlb_sizes[1] > 64)
+		return -EINVAL;
+	if (params.tlb_ways[1] != params.tlb_sizes[1])
+		return -EINVAL;
+	if (params.tlb_sizes[2] != 0 || params.tlb_sizes[3] != 0)
+		return -EINVAL;
+	if (params.tlb_ways[2] != 0 || params.tlb_ways[3] != 0)
+		return -EINVAL;
+
+	if (!is_power_of_2(params.tlb_ways[0]))
+		return -EINVAL;
+
+	sets = params.tlb_sizes[0] >> ilog2(params.tlb_ways[0]);
+	if (!is_power_of_2(sets))
+		return -EINVAL;
+
+	array_len = params.tlb_sizes[0] + params.tlb_sizes[1];
+	array_len *= sizeof(struct kvm_book3e_206_tlb_entry);
+
+	if (cfg->array_len < array_len)
+		return -EINVAL;
+
+	num_pages = DIV_ROUND_UP(cfg->array + array_len - 1, PAGE_SIZE) -
+		    cfg->array / PAGE_SIZE;
+	pages = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	ret = get_user_pages_fast(cfg->array, num_pages, 1, pages);
+	if (ret < 0)
+		goto err_pages;
+
+	if (ret != num_pages) {
+		num_pages = ret;
+		ret = -EFAULT;
+		goto err_put_page;
+	}
+
+	virt = vmap(pages, num_pages, VM_MAP, PAGE_KERNEL);
+	if (!virt)
+		goto err_put_page;
+
+	privs[0] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[0],
+			   GFP_KERNEL);
+	privs[1] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[1],
+			   GFP_KERNEL);
+
+	if (!privs[0] || !privs[1])
+		goto err_put_page;
+
+	free_gtlb(vcpu_e500);
+
+	vcpu_e500->gtlb_priv[0] = privs[0];
+	vcpu_e500->gtlb_priv[1] = privs[1];
+
+	vcpu_e500->gtlb_arch = (struct kvm_book3e_206_tlb_entry *)
+		(virt + (cfg->array & (PAGE_SIZE - 1)));
+
+	vcpu_e500->gtlb_params[0].entries = params.tlb_sizes[0];
+	vcpu_e500->gtlb_params[1].entries = params.tlb_sizes[1];
+
+	vcpu_e500->gtlb_offset[0] = 0;
+	vcpu_e500->gtlb_offset[1] = params.tlb_sizes[0];
+
+	vcpu_e500->tlb0cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+	if (params.tlb_sizes[0] <= 2048)
+		vcpu_e500->tlb0cfg |= params.tlb_sizes[0];
+	vcpu_e500->tlb0cfg |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;
+
+	vcpu_e500->tlb1cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+	vcpu_e500->tlb1cfg |= params.tlb_sizes[1];
+	vcpu_e500->tlb1cfg |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;
+
+	vcpu_e500->shared_tlb_pages = pages;
+	vcpu_e500->num_shared_tlb_pages = num_pages;
+
+	vcpu_e500->gtlb_params[0].ways = params.tlb_ways[0];
+	vcpu_e500->gtlb_params[0].sets = sets;
+
+	vcpu_e500->gtlb_params[1].ways = params.tlb_sizes[1];
+	vcpu_e500->gtlb_params[1].sets = 1;
+
+	return 0;
+
+err_put_page:
+	kfree(privs[0]);
+	kfree(privs[1]);
+
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+
+err_pages:
+	kfree(pages);
+	return ret;
+}
+
+int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
+			     struct kvm_dirty_tlb *dirty)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	clear_tlb_refs(vcpu_e500);
+	return 0;
 }
 
 int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-	tlb1_entry_num = mfspr(SPRN_TLB1CFG) & 0xFFF;
-
-	vcpu_e500->gtlb_size[0] = KVM_E500_TLB0_SIZE;
-	vcpu_e500->gtlb_arch[0] =
-		kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
-	if (vcpu_e500->gtlb_arch[0] == NULL)
-		goto err_out;
-
-	vcpu_e500->gtlb_size[1] = KVM_E500_TLB1_SIZE;
-	vcpu_e500->gtlb_arch[1] =
-		kzalloc(sizeof(struct tlbe) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
-	if (vcpu_e500->gtlb_arch[1] == NULL)
-		goto err_out_guest0;
-
-	vcpu_e500->gtlb_priv[0] = (struct tlbe_priv *)
-		kzalloc(sizeof(struct tlbe_priv) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
-	if (vcpu_e500->gtlb_priv[0] == NULL)
-		goto err_out_guest1;
-	vcpu_e500->gtlb_priv[1] = (struct tlbe_priv *)
-		kzalloc(sizeof(struct tlbe_priv) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
-
-	if (vcpu_e500->gtlb_priv[1] == NULL)
-		goto err_out_priv0;
+	int entry_size = sizeof(struct kvm_book3e_206_tlb_entry);
+	int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE;
+
+	host_tlb_params[0].entries = mfspr(SPRN_TLB0CFG) & TLBnCFG_N_ENTRY;
+	host_tlb_params[1].entries = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+	/*
+	 * This should never happen on real e500 hardware, but is
+	 * architecturally possible -- e.g. in some weird nested
+	 * virtualization case.
+	 */
+	if (host_tlb_params[0].entries == 0 ||
+	    host_tlb_params[1].entries == 0) {
+		pr_err("%s: need to know host tlb size\n", __func__);
+		return -ENODEV;
+	}
+
+	host_tlb_params[0].ways = (mfspr(SPRN_TLB0CFG) & TLBnCFG_ASSOC) >>
+				  TLBnCFG_ASSOC_SHIFT;
+	host_tlb_params[1].ways = host_tlb_params[1].entries;
+
+	if (!is_power_of_2(host_tlb_params[0].entries) ||
+	    !is_power_of_2(host_tlb_params[0].ways) ||
+	    host_tlb_params[0].entries < host_tlb_params[0].ways ||
+	    host_tlb_params[0].ways == 0) {
+		pr_err("%s: bad tlb0 host config: %u entries %u ways\n",
+		       __func__, host_tlb_params[0].entries,
+		       host_tlb_params[0].ways);
+		return -ENODEV;
+	}
+
+	host_tlb_params[0].sets =
+		host_tlb_params[0].entries / host_tlb_params[0].ways;
+	host_tlb_params[1].sets = 1;
+
+	vcpu_e500->gtlb_params[0].entries = KVM_E500_TLB0_SIZE;
+	vcpu_e500->gtlb_params[1].entries = KVM_E500_TLB1_SIZE;
+
+	vcpu_e500->gtlb_params[0].ways = KVM_E500_TLB0_WAY_NUM;
+	vcpu_e500->gtlb_params[0].sets =
+		KVM_E500_TLB0_SIZE / KVM_E500_TLB0_WAY_NUM;
+
+	vcpu_e500->gtlb_params[1].ways = KVM_E500_TLB1_SIZE;
+	vcpu_e500->gtlb_params[1].sets = 1;
+
+	vcpu_e500->gtlb_arch = kmalloc(entries * entry_size, GFP_KERNEL);
+	if (!vcpu_e500->gtlb_arch)
+		return -ENOMEM;
+
+	vcpu_e500->gtlb_offset[0] = 0;
+	vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE;
+
+	vcpu_e500->tlb_refs[0] =
+		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
+			GFP_KERNEL);
+	if (!vcpu_e500->tlb_refs[0])
+		goto err;
+
+	vcpu_e500->tlb_refs[1] =
+		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
+			GFP_KERNEL);
+	if (!vcpu_e500->tlb_refs[1])
+		goto err;
+
+	vcpu_e500->gtlb_priv[0] = kzalloc(sizeof(struct tlbe_ref) *
+					  vcpu_e500->gtlb_params[0].entries,
+					  GFP_KERNEL);
+	if (!vcpu_e500->gtlb_priv[0])
+		goto err;
+
+	vcpu_e500->gtlb_priv[1] = kzalloc(sizeof(struct tlbe_ref) *
+					  vcpu_e500->gtlb_params[1].entries,
+					  GFP_KERNEL);
+	if (!vcpu_e500->gtlb_priv[1])
+		goto err;
 
 	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
-		goto err_out_priv1;
+		goto err;
 
 	/* Init TLB configuration register */
-	vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) & ~0xfffUL;
-	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_size[0];
-	vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) & ~0xfffUL;
-	vcpu_e500->tlb1cfg |= vcpu_e500->gtlb_size[1];
+	vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) &
+			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[0].entries;
+	vcpu_e500->tlb0cfg |=
+		vcpu_e500->gtlb_params[0].ways << TLBnCFG_ASSOC_SHIFT;
+
+	vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) &
+			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[1].entries;
+	vcpu_e500->tlb0cfg |=
+		vcpu_e500->gtlb_params[1].ways << TLBnCFG_ASSOC_SHIFT;
 
 	return 0;
 
-err_out_priv1:
-	kfree(vcpu_e500->gtlb_priv[1]);
-err_out_priv0:
-	kfree(vcpu_e500->gtlb_priv[0]);
-err_out_guest1:
-	kfree(vcpu_e500->gtlb_arch[1]);
-err_out_guest0:
-	kfree(vcpu_e500->gtlb_arch[0]);
-err_out:
+err:
+	free_gtlb(vcpu_e500);
+	kfree(vcpu_e500->tlb_refs[0]);
+	kfree(vcpu_e500->tlb_refs[1]);
 	return -1;
 }
 
 void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-	int stlbsel, i;
-
-	/* release all privs */
-	for (stlbsel = 0; stlbsel < 2; stlbsel++)
-		for (i = 0; i < vcpu_e500->gtlb_size[stlbsel]; i++) {
-			struct tlbe_priv *priv =
-				&vcpu_e500->gtlb_priv[stlbsel][i];
-			kvmppc_e500_priv_release(priv);
-		}
-
+	free_gtlb(vcpu_e500);
 	kvmppc_e500_id_table_free(vcpu_e500);
-	kfree(vcpu_e500->gtlb_arch[1]);
-	kfree(vcpu_e500->gtlb_arch[0]);
+
+	kfree(vcpu_e500->tlb_refs[0]);
+	kfree(vcpu_e500->tlb_refs[1]);
 }
diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h
index 59b88e99a235..5c6d2d7bf058 100644
--- a/arch/powerpc/kvm/e500_tlb.h
+++ b/arch/powerpc/kvm/e500_tlb.h
@@ -20,13 +20,9 @@
 #include <asm/tlb.h>
 #include <asm/kvm_e500.h>
 
-#define KVM_E500_TLB0_WAY_SIZE_BIT	7	/* Fixed */
-#define KVM_E500_TLB0_WAY_SIZE		(1UL << KVM_E500_TLB0_WAY_SIZE_BIT)
-#define KVM_E500_TLB0_WAY_SIZE_MASK	(KVM_E500_TLB0_WAY_SIZE - 1)
-
-#define KVM_E500_TLB0_WAY_NUM_BIT	1	/* No greater than 7 */
-#define KVM_E500_TLB0_WAY_NUM		(1UL << KVM_E500_TLB0_WAY_NUM_BIT)
-#define KVM_E500_TLB0_WAY_NUM_MASK	(KVM_E500_TLB0_WAY_NUM - 1)
+/* This geometry is the legacy default -- can be overridden by userspace */
+#define KVM_E500_TLB0_WAY_SIZE		128
+#define KVM_E500_TLB0_WAY_NUM		2
 
 #define KVM_E500_TLB0_SIZE  (KVM_E500_TLB0_WAY_SIZE * KVM_E500_TLB0_WAY_NUM)
 #define KVM_E500_TLB1_SIZE  16
@@ -58,50 +54,54 @@ extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
 extern void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *);
 
 /* TLB helper functions */
-static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_size(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 7) & 0x1f;
 }
 
-static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
+static inline gva_t get_tlb_eaddr(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return tlbe->mas2 & 0xfffff000;
 }
 
-static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
+static inline u64 get_tlb_bytes(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	unsigned int pgsize = get_tlb_size(tlbe);
 	return 1ULL << 10 << pgsize;
 }
 
-static inline gva_t get_tlb_end(const struct tlbe *tlbe)
+static inline gva_t get_tlb_end(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	u64 bytes = get_tlb_bytes(tlbe);
 	return get_tlb_eaddr(tlbe) + bytes - 1;
 }
 
-static inline u64 get_tlb_raddr(const struct tlbe *tlbe)
+static inline u64 get_tlb_raddr(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
-	u64 rpn = tlbe->mas7;
-	return (rpn << 32) | (tlbe->mas3 & 0xfffff000);
+	return tlbe->mas7_3 & ~0xfffULL;
 }
 
-static inline unsigned int get_tlb_tid(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_tid(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 16) & 0xff;
 }
 
-static inline unsigned int get_tlb_ts(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_ts(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 12) & 0x1;
 }
 
-static inline unsigned int get_tlb_v(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_v(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 31) & 0x1;
 }
 
-static inline unsigned int get_tlb_iprot(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_iprot(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 30) & 0x1;
 }
@@ -121,59 +121,37 @@ static inline unsigned int get_cur_pr(struct kvm_vcpu *vcpu)
 	return !!(vcpu->arch.shared->msr & MSR_PR);
 }
 
-static inline unsigned int get_cur_spid(
-		const struct kvmppc_vcpu_e500 *vcpu_e500)
+static inline unsigned int get_cur_spid(const struct kvm_vcpu *vcpu)
 {
-	return (vcpu_e500->mas6 >> 16) & 0xff;
+	return (vcpu->arch.shared->mas6 >> 16) & 0xff;
 }
 
-static inline unsigned int get_cur_sas(
-		const struct kvmppc_vcpu_e500 *vcpu_e500)
+static inline unsigned int get_cur_sas(const struct kvm_vcpu *vcpu)
 {
-	return vcpu_e500->mas6 & 0x1;
+	return vcpu->arch.shared->mas6 & 0x1;
 }
 
-static inline unsigned int get_tlb_tlbsel(
-		const struct kvmppc_vcpu_e500 *vcpu_e500)
+static inline unsigned int get_tlb_tlbsel(const struct kvm_vcpu *vcpu)
 {
 	/*
 	 * Manual says that tlbsel has 2 bits wide.
 	 * Since we only have two TLBs, only lower bit is used.
 	 */
-	return (vcpu_e500->mas0 >> 28) & 0x1;
-}
-
-static inline unsigned int get_tlb_nv_bit(
-		const struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	return vcpu_e500->mas0 & 0xfff;
+	return (vcpu->arch.shared->mas0 >> 28) & 0x1;
 }
 
-static inline unsigned int get_tlb_esel_bit(
-		const struct kvmppc_vcpu_e500 *vcpu_e500)
+static inline unsigned int get_tlb_nv_bit(const struct kvm_vcpu *vcpu)
 {
-	return (vcpu_e500->mas0 >> 16) & 0xfff;
+	return vcpu->arch.shared->mas0 & 0xfff;
 }
 
-static inline unsigned int get_tlb_esel(
-		const struct kvmppc_vcpu_e500 *vcpu_e500,
-		int tlbsel)
+static inline unsigned int get_tlb_esel_bit(const struct kvm_vcpu *vcpu)
 {
-	unsigned int esel = get_tlb_esel_bit(vcpu_e500);
-
-	if (tlbsel == 0) {
-		esel &= KVM_E500_TLB0_WAY_NUM_MASK;
-		esel |= ((vcpu_e500->mas2 >> 12) & KVM_E500_TLB0_WAY_SIZE_MASK)
-				<< KVM_E500_TLB0_WAY_NUM_BIT;
-	} else {
-		esel &= KVM_E500_TLB1_SIZE - 1;
-	}
-
-	return esel;
+	return (vcpu->arch.shared->mas0 >> 16) & 0xfff;
 }
 
 static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
-			const struct tlbe *tlbe)
+			const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	gpa_t gpa;
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 141dce3c6810..968f40101883 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -13,6 +13,7 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  *
  * Copyright IBM Corp. 2007
+ * Copyright 2011 Freescale Semiconductor, Inc.
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
  */
@@ -69,54 +70,55 @@
 #define OP_STH  44
 #define OP_STHU 45
 
-#ifdef CONFIG_PPC_BOOK3S
-static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
-{
-	return 1;
-}
-#else
-static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.tcr & TCR_DIE;
-}
-#endif
-
 void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 {
 	unsigned long dec_nsec;
+	unsigned long long dec_time;
 
 	pr_debug("mtDEC: %x\n", vcpu->arch.dec);
+	hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+
 #ifdef CONFIG_PPC_BOOK3S
 	/* mtdec lowers the interrupt line when positive. */
 	kvmppc_core_dequeue_dec(vcpu);
 
 	/* POWER4+ triggers a dec interrupt if the value is < 0 */
 	if (vcpu->arch.dec & 0x80000000) {
-		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
 		kvmppc_core_queue_dec(vcpu);
 		return;
 	}
 #endif
-	if (kvmppc_dec_enabled(vcpu)) {
-		/* The decrementer ticks at the same rate as the timebase, so
-		 * that's how we convert the guest DEC value to the number of
-		 * host ticks. */
-
-		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
-		dec_nsec = vcpu->arch.dec;
-		dec_nsec *= 1000;
-		dec_nsec /= tb_ticks_per_usec;
-		hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
-			      HRTIMER_MODE_REL);
-		vcpu->arch.dec_jiffies = get_tb();
-	} else {
-		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
-	}
+
+#ifdef CONFIG_BOOKE
+	/* On BOOKE, DEC = 0 is as good as decrementer not enabled */
+	if (vcpu->arch.dec == 0)
+		return;
+#endif
+
+	/*
+	 * The decrementer ticks at the same rate as the timebase, so
+	 * that's how we convert the guest DEC value to the number of
+	 * host ticks.
+	 */
+
+	dec_time = vcpu->arch.dec;
+	dec_time *= 1000;
+	do_div(dec_time, tb_ticks_per_usec);
+	dec_nsec = do_div(dec_time, NSEC_PER_SEC);
+	hrtimer_start(&vcpu->arch.dec_timer,
+		ktime_set(dec_time, dec_nsec), HRTIMER_MODE_REL);
+	vcpu->arch.dec_jiffies = get_tb();
 }
 
 u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb)
 {
 	u64 jd = tb - vcpu->arch.dec_jiffies;
+
+#ifdef CONFIG_BOOKE
+	if (vcpu->arch.dec < jd)
+		return 0;
+#endif
+
 	return vcpu->arch.dec - jd;
 }
 
@@ -159,7 +161,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	case OP_TRAP_64:
 		kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP);
 #else
-		kvmppc_core_queue_program(vcpu, vcpu->arch.esr | ESR_PTR);
+		kvmppc_core_queue_program(vcpu,
+					  vcpu->arch.shared->esr | ESR_PTR);
 #endif
 		advance = 0;
 		break;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 607fbdf24b84..00d7e345b3fe 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -39,7 +39,8 @@
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
 	return !(v->arch.shared->msr & MSR_WE) ||
-	       !!(v->arch.pending_exceptions);
+	       !!(v->arch.pending_exceptions) ||
+	       v->requests;
 }
 
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
@@ -66,7 +67,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 		vcpu->arch.magic_page_pa = param1;
 		vcpu->arch.magic_page_ea = param2;
 
-		r2 = KVM_MAGIC_FEAT_SR;
+		r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;
 
 		r = HC_EV_SUCCESS;
 		break;
@@ -171,8 +172,11 @@ void kvm_arch_check_processor_compat(void *rtn)
 	*(int *)rtn = kvmppc_core_check_processor_compat();
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+	if (type)
+		return -EINVAL;
+
 	return kvmppc_core_init_vm(kvm);
 }
 
@@ -208,17 +212,22 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_BOOKE_SREGS:
 #else
 	case KVM_CAP_PPC_SEGSTATE:
+	case KVM_CAP_PPC_HIOR:
 	case KVM_CAP_PPC_PAPR:
 #endif
 	case KVM_CAP_PPC_UNSET_IRQ:
 	case KVM_CAP_PPC_IRQ_LEVEL:
 	case KVM_CAP_ENABLE_CAP:
+	case KVM_CAP_ONE_REG:
 		r = 1;
 		break;
 #ifndef CONFIG_KVM_BOOK3S_64_HV
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
+#ifdef CONFIG_KVM_E500
+	case KVM_CAP_SW_TLB:
+#endif
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -238,7 +247,26 @@ int kvm_dev_ioctl_check_extension(long ext)
 		if (cpu_has_feature(CPU_FTR_ARCH_201))
 			r = 2;
 		break;
+	case KVM_CAP_SYNC_MMU:
+		r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
+		break;
 #endif
+	case KVM_CAP_NR_VCPUS:
+		/*
+		 * Recommending a number of CPUs is somewhat arbitrary; we
+		 * return the number of present CPUs for -HV (since a host
+		 * will have secondary threads "offline"), and for other KVM
+		 * implementations just count online CPUs.
+		 */
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+		r = num_present_cpus();
+#else
+		r = num_online_cpus();
+#endif
+		break;
+	case KVM_CAP_MAX_VCPUS:
+		r = KVM_MAX_VCPUS;
+		break;
 	default:
 		r = 0;
 		break;
@@ -253,6 +281,16 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                    struct kvm_memory_slot *memslot,
                                    struct kvm_memory_slot old,
@@ -279,9 +317,10 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	struct kvm_vcpu *vcpu;
 	vcpu = kvmppc_core_vcpu_create(kvm, id);
-	vcpu->arch.wqp = &vcpu->wq;
-	if (!IS_ERR(vcpu))
+	if (!IS_ERR(vcpu)) {
+		vcpu->arch.wqp = &vcpu->wq;
 		kvmppc_create_vcpu_debugfs(vcpu, id);
+	}
 	return vcpu;
 }
 
@@ -305,18 +344,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvmppc_core_pending_dec(vcpu);
 }
 
-static void kvmppc_decrementer_func(unsigned long data)
-{
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
-
-	kvmppc_core_queue_dec(vcpu);
-
-	if (waitqueue_active(vcpu->arch.wqp)) {
-		wake_up_interruptible(vcpu->arch.wqp);
-		vcpu->stat.halt_wakeup++;
-	}
-}
-
 /*
  * low level hrtimer wake routine. Because this runs in hardirq context
  * we schedule a tasklet to do the real work.
@@ -431,20 +458,20 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 
 	kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
 
-	switch (vcpu->arch.io_gpr & KVM_REG_EXT_MASK) {
-	case KVM_REG_GPR:
+	switch (vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) {
+	case KVM_MMIO_REG_GPR:
 		kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
 		break;
-	case KVM_REG_FPR:
-		vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+	case KVM_MMIO_REG_FPR:
+		vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
 		break;
 #ifdef CONFIG_PPC_BOOK3S
-	case KVM_REG_QPR:
-		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+	case KVM_MMIO_REG_QPR:
+		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
 		break;
-	case KVM_REG_FQPR:
-		vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
-		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+	case KVM_MMIO_REG_FQPR:
+		vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
+		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
 		break;
 #endif
 	default:
@@ -553,8 +580,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		vcpu->arch.hcall_needed = 0;
 	}
 
-	kvmppc_core_deliver_interrupts(vcpu);
-
 	r = kvmppc_vcpu_run(run, vcpu);
 
 	if (vcpu->sigset_active)
@@ -563,6 +588,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return r;
 }
 
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+	int me;
+	int cpu = vcpu->cpu;
+
+	me = get_cpu();
+	if (waitqueue_active(vcpu->arch.wqp)) {
+		wake_up_interruptible(vcpu->arch.wqp);
+		vcpu->stat.halt_wakeup++;
+	} else if (cpu != me && cpu != -1) {
+		smp_send_reschedule(vcpu->cpu);
+	}
+	put_cpu();
+}
+
 int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 {
 	if (irq->irq == KVM_INTERRUPT_UNSET) {
@@ -571,13 +611,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 	}
 
 	kvmppc_core_queue_external(vcpu, irq);
-
-	if (waitqueue_active(vcpu->arch.wqp)) {
-		wake_up_interruptible(vcpu->arch.wqp);
-		vcpu->stat.halt_wakeup++;
-	} else if (vcpu->cpu != -1) {
-		smp_send_reschedule(vcpu->cpu);
-	}
+	kvm_vcpu_kick(vcpu);
 
 	return 0;
 }
@@ -599,6 +633,19 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		r = 0;
 		vcpu->arch.papr_enabled = true;
 		break;
+#ifdef CONFIG_KVM_E500
+	case KVM_CAP_SW_TLB: {
+		struct kvm_config_tlb cfg;
+		void __user *user_ptr = (void __user *)(uintptr_t)cap->args[0];
+
+		r = -EFAULT;
+		if (copy_from_user(&cfg, user_ptr, sizeof(cfg)))
+			break;
+
+		r = kvm_vcpu_ioctl_config_tlb(vcpu, &cfg);
+		break;
+	}
+#endif
 	default:
 		r = -EINVAL;
 		break;
@@ -648,6 +695,32 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
 		break;
 	}
+
+	case KVM_SET_ONE_REG:
+	case KVM_GET_ONE_REG:
+	{
+		struct kvm_one_reg reg;
+		r = -EFAULT;
+		if (copy_from_user(&reg, argp, sizeof(reg)))
+			goto out;
+		if (ioctl == KVM_SET_ONE_REG)
+			r = kvm_vcpu_ioctl_set_one_reg(vcpu, &reg);
+		else
+			r = kvm_vcpu_ioctl_get_one_reg(vcpu, &reg);
+		break;
+	}
+
+#ifdef CONFIG_KVM_E500
+	case KVM_DIRTY_TLB: {
+		struct kvm_dirty_tlb dirty;
+		r = -EFAULT;
+		if (copy_from_user(&dirty, argp, sizeof(dirty)))
+			goto out;
+		r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
+		break;
+	}
+#endif
+
 	default:
 		r = -EINVAL;
 	}
@@ -656,6 +729,11 @@ out:
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
 static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
 {
 	u32 inst_lis = 0x3c000000;
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index b135d3d397db..877186b7b1c3 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -118,11 +118,14 @@ TRACE_EVENT(kvm_book3s_exit,
 	),
 
 	TP_fast_assign(
+		struct kvmppc_book3s_shadow_vcpu *svcpu;
 		__entry->exit_nr	= exit_nr;
 		__entry->pc		= kvmppc_get_pc(vcpu);
 		__entry->dar		= kvmppc_get_fault_dar(vcpu);
 		__entry->msr		= vcpu->arch.shared->msr;
-		__entry->srr1		= to_svcpu(vcpu)->shadow_srr1;
+		svcpu = svcpu_get(vcpu);
+		__entry->srr1		= svcpu->shadow_srr1;
+		svcpu_put(svcpu);
 	),
 
 	TP_printk("exit=0x%x | pc=0x%lx | msr=0x%lx | dar=0x%lx | srr1=0x%lx",
@@ -337,6 +340,63 @@ TRACE_EVENT(kvm_book3s_slbmte,
 
 #endif /* CONFIG_PPC_BOOK3S */
 
+
+/*************************************************************************
+ *                         Book3E trace points                           *
+ *************************************************************************/
+
+#ifdef CONFIG_BOOKE
+
+TRACE_EVENT(kvm_booke206_stlb_write,
+	TP_PROTO(__u32 mas0, __u32 mas8, __u32 mas1, __u64 mas2, __u64 mas7_3),
+	TP_ARGS(mas0, mas8, mas1, mas2, mas7_3),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	mas0		)
+		__field(	__u32,	mas8		)
+		__field(	__u32,	mas1		)
+		__field(	__u64,	mas2		)
+		__field(	__u64,	mas7_3		)
+	),
+
+	TP_fast_assign(
+		__entry->mas0		= mas0;
+		__entry->mas8		= mas8;
+		__entry->mas1		= mas1;
+		__entry->mas2		= mas2;
+		__entry->mas7_3		= mas7_3;
+	),
+
+	TP_printk("mas0=%x mas8=%x mas1=%x mas2=%llx mas7_3=%llx",
+		__entry->mas0, __entry->mas8, __entry->mas1,
+		__entry->mas2, __entry->mas7_3)
+);
+
+TRACE_EVENT(kvm_booke206_gtlb_write,
+	TP_PROTO(__u32 mas0, __u32 mas1, __u64 mas2, __u64 mas7_3),
+	TP_ARGS(mas0, mas1, mas2, mas7_3),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	mas0		)
+		__field(	__u32,	mas1		)
+		__field(	__u64,	mas2		)
+		__field(	__u64,	mas7_3		)
+	),
+
+	TP_fast_assign(
+		__entry->mas0		= mas0;
+		__entry->mas1		= mas1;
+		__entry->mas2		= mas2;
+		__entry->mas7_3		= mas7_3;
+	),
+
+	TP_printk("mas0=%x mas1=%x mas2=%llx mas7_3=%llx",
+		__entry->mas0, __entry->mas1,
+		__entry->mas2, __entry->mas7_3)
+);
+
+#endif
+
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
index 13b676c20d12..da22c84a8fed 100644
--- a/arch/powerpc/lib/alloc.c
+++ b/arch/powerpc/lib/alloc.c
@@ -3,8 +3,8 @@
 #include <linux/slab.h>
 #include <linux/bootmem.h>
 #include <linux/string.h>
+#include <asm/setup.h>
 
-#include <asm/system.h>
 
 void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask)
 {
diff --git a/arch/powerpc/lib/copyuser_power7_vmx.c b/arch/powerpc/lib/copyuser_power7_vmx.c
index 6e1efadac48b..bf2654f2b68e 100644
--- a/arch/powerpc/lib/copyuser_power7_vmx.c
+++ b/arch/powerpc/lib/copyuser_power7_vmx.c
@@ -20,6 +20,7 @@
  */
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
+#include <asm/switch_to.h>
 
 int enter_vmx_copy(void)
 {
diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
index 388b95e1a009..2c9441ee6bb8 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/44x_mmu.c
@@ -27,7 +27,6 @@
 #include <linux/memblock.h>
 
 #include <asm/mmu.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 19f2f9498b27..08ffcf52a856 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -38,10 +38,10 @@
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
+#include <asm/debug.h>
 #include <mm/mmu_decl.h>
 
 #include "icswx.h"
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 3e8c37a4e395..377e5cbedbbb 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -40,7 +40,6 @@
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/types.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/machdep.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 57c7465e656e..fb05b123218f 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
+#include <linux/export.h>
 #include <linux/of_fdt.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>
@@ -103,6 +104,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 		*shift = hugepd_shift(*hpdp);
 	return hugepte_offset(hpdp, ea, pdshift);
 }
+EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
@@ -310,7 +312,8 @@ void __init reserve_hugetlb_gpages(void)
 	int i;
 
 	strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE);
-	parse_args("hugetlb gpages", cmdline, NULL, 0, &do_gpage_early_setup);
+	parse_args("hugetlb gpages", cmdline, NULL, 0, 0, 0,
+			&do_gpage_early_setup);
 
 	/*
 	 * Walk gpage list in reverse, allocating larger page sizes first.
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 6157be2a7049..01e2db97a210 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -45,7 +45,6 @@
 #include <asm/btext.h>
 #include <asm/tlb.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/hugetlb.h>
 
 #include "mmu_decl.h"
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index e94b57fb79a0..620b7acd2fdf 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -61,7 +61,6 @@
 #include <asm/mmzone.h>
 #include <asm/cputable.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/iommu.h>
 #include <asm/abs_addr.h>
 #include <asm/vdso.h>
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 3feefc3842a8..b6edbb3b4a54 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -24,11 +24,11 @@
 #include <linux/node.h>
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/smp.h>
 #include <asm/firmware.h>
 #include <asm/paca.h>
 #include <asm/hvcall.h>
+#include <asm/setup.h>
 
 static int numa_enabled = 1;
 
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 0907f92ce309..6c856fb8c15b 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -33,6 +33,7 @@
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
 #include <asm/io.h>
+#include <asm/setup.h>
 
 #include "mmu_decl.h"
 
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index ad36ede469cc..249a0631c4db 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -51,7 +51,6 @@
 #include <asm/processor.h>
 #include <asm/cputable.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/abs_addr.h>
 #include <asm/firmware.h>
 
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
index 6f01624f317f..4f51025f5b00 100644
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -18,7 +18,6 @@
 #include <linux/smp.h>
 #include <linux/errno.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/pmc.h>
 #include <asm/cputable.h>
 #include <asm/oprofile_impl.h>
diff --git a/arch/powerpc/oprofile/op_model_7450.c b/arch/powerpc/oprofile/op_model_7450.c
index f8d36f940e88..ff617246d128 100644
--- a/arch/powerpc/oprofile/op_model_7450.c
+++ b/arch/powerpc/oprofile/op_model_7450.c
@@ -19,7 +19,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
 #include <asm/page.h>
diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c
index cb515cff745c..b9589c19ccda 100644
--- a/arch/powerpc/oprofile/op_model_cell.c
+++ b/arch/powerpc/oprofile/op_model_cell.c
@@ -34,7 +34,6 @@
 #include <asm/ptrace.h>
 #include <asm/reg.h>
 #include <asm/rtas.h>
-#include <asm/system.h>
 #include <asm/cell-regs.h>
 
 #include "../platforms/cell/interrupt.h"
diff --git a/arch/powerpc/oprofile/op_model_fsl_emb.c b/arch/powerpc/oprofile/op_model_fsl_emb.c
index d4e6507277b5..ccc1daa33aed 100644
--- a/arch/powerpc/oprofile/op_model_fsl_emb.c
+++ b/arch/powerpc/oprofile/op_model_fsl_emb.c
@@ -17,7 +17,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
 #include <asm/reg_fsl_emb.h>
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index e6bec74be131..95ae77dec3f6 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -14,7 +14,6 @@
 #include <linux/smp.h>
 #include <asm/firmware.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
 #include <asm/rtas.h>
diff --git a/arch/powerpc/oprofile/op_model_rs64.c b/arch/powerpc/oprofile/op_model_rs64.c
index a20afe45d936..9b801b8c8c5a 100644
--- a/arch/powerpc/oprofile/op_model_rs64.c
+++ b/arch/powerpc/oprofile/op_model_rs64.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
 #include <asm/oprofile_impl.h>
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index c2e27ede07ec..02aee03e713c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -116,14 +116,45 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 		*addrp = mfspr(SPRN_SDAR);
 }
 
+static inline u32 perf_flags_from_msr(struct pt_regs *regs)
+{
+	if (regs->msr & MSR_PR)
+		return PERF_RECORD_MISC_USER;
+	if ((regs->msr & MSR_HV) && freeze_events_kernel != MMCR0_FCHV)
+		return PERF_RECORD_MISC_HYPERVISOR;
+	return PERF_RECORD_MISC_KERNEL;
+}
+
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
 	unsigned long mmcra = regs->dsisr;
 	unsigned long sihv = MMCRA_SIHV;
 	unsigned long sipr = MMCRA_SIPR;
 
+	/* Not a PMU interrupt: Make up flags from regs->msr */
 	if (TRAP(regs) != 0xf00)
-		return 0;	/* not a PMU interrupt */
+		return perf_flags_from_msr(regs);
+
+	/*
+	 * If we don't support continuous sampling and this
+	 * is not a marked event, same deal
+	 */
+	if ((ppmu->flags & PPMU_NO_CONT_SAMPLING) &&
+	    !(mmcra & MMCRA_SAMPLE_ENABLE))
+		return perf_flags_from_msr(regs);
+
+	/*
+	 * If we don't have flags in MMCRA, rather than using
+	 * the MSR, we intuit the flags from the address in
+	 * SIAR which should give slightly more reliable
+	 * results
+	 */
+	if (ppmu->flags & PPMU_NO_SIPR) {
+		unsigned long siar = mfspr(SPRN_SIAR);
+		if (siar >= PAGE_OFFSET)
+			return PERF_RECORD_MISC_KERNEL;
+		return PERF_RECORD_MISC_USER;
+	}
 
 	if (ppmu->flags & PPMU_ALT_SIPR) {
 		sihv = POWER6_MMCRA_SIHV;
@@ -1299,13 +1330,18 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  */
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	unsigned long ip;
+	unsigned long mmcra = regs->dsisr;
 
+	/* Not a PMU interrupt */
 	if (TRAP(regs) != 0xf00)
-		return regs->nip;	/* not a PMU interrupt */
+		return regs->nip;
+
+	/* Processor doesn't support sampling non marked events */
+	if ((ppmu->flags & PPMU_NO_CONT_SAMPLING) &&
+	    !(mmcra & MMCRA_SAMPLE_ENABLE))
+		return regs->nip;
 
-	ip = mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
-	return ip;
+	return mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
 }
 
 static bool pmc_overflow(unsigned long val)
diff --git a/arch/powerpc/perf/power4-pmu.c b/arch/powerpc/perf/power4-pmu.c
index b4f1dda4d089..9103a1de864d 100644
--- a/arch/powerpc/perf/power4-pmu.c
+++ b/arch/powerpc/perf/power4-pmu.c
@@ -607,6 +607,7 @@ static struct power_pmu power4_pmu = {
 	.n_generic		= ARRAY_SIZE(p4_generic_events),
 	.generic_events		= p4_generic_events,
 	.cache_events		= &power4_cache_events,
+	.flags			= PPMU_NO_SIPR | PPMU_NO_CONT_SAMPLING,
 };
 
 static int __init init_power4_pmu(void)
diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c
index 111eb25bb0b6..20139ceeacf6 100644
--- a/arch/powerpc/perf/ppc970-pmu.c
+++ b/arch/powerpc/perf/ppc970-pmu.c
@@ -487,6 +487,7 @@ static struct power_pmu ppc970_pmu = {
 	.n_generic		= ARRAY_SIZE(ppc970_generic_events),
 	.generic_events		= ppc970_generic_events,
 	.cache_events		= &ppc970_cache_events,
+	.flags			= PPMU_NO_SIPR | PPMU_NO_CONT_SAMPLING,
 };
 
 static int __init init_ppc970_pmu(void)
diff --git a/arch/powerpc/platforms/52xx/lite5200_pm.c b/arch/powerpc/platforms/52xx/lite5200_pm.c
index eda0fc2a3914..870b70f5d1bd 100644
--- a/arch/powerpc/platforms/52xx/lite5200_pm.c
+++ b/arch/powerpc/platforms/52xx/lite5200_pm.c
@@ -3,6 +3,7 @@
 #include <asm/io.h>
 #include <asm/time.h>
 #include <asm/mpc52xx.h>
+#include <asm/switch_to.h>
 
 /* defined in lite5200_sleep.S and only used here */
 extern void lite5200_low_power(void __iomem *sram, void __iomem *mbar);
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pci.c b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
index bfb11e01133e..e2d401ad8fbb 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pci.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
@@ -93,7 +93,7 @@ struct mpc52xx_pci {
 };
 
 /* MPC5200 device tree match tables */
-const struct of_device_id mpc52xx_pci_ids[] __initdata = {
+const struct of_device_id mpc52xx_pci_ids[] __initconst = {
 	{ .type = "pci", .compatible = "fsl,mpc5200-pci", },
 	{ .type = "pci", .compatible = "mpc5200-pci", },
 	{}
diff --git a/arch/powerpc/platforms/82xx/pq2.c b/arch/powerpc/platforms/82xx/pq2.c
index d111b024eafd..fb94d10e5a4d 100644
--- a/arch/powerpc/platforms/82xx/pq2.c
+++ b/arch/powerpc/platforms/82xx/pq2.c
@@ -17,7 +17,6 @@
 #include <asm/cpm2.h>
 #include <asm/io.h>
 #include <asm/pci-bridge.h>
-#include <asm/system.h>
 
 #include <platforms/82xx/pq2.h>
 
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index 65eb792a0d00..a266ba876863 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -27,7 +27,6 @@
 #include <linux/of_platform.h>
 #include <linux/of_device.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/time.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c
index e36bc611dd6e..d440435e055c 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c
@@ -26,7 +26,6 @@
 #include <linux/of_platform.h>
 #include <linux/of_device.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/time.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c
index 39849dd1b5bb..a494fa57bdf9 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_itx.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c
@@ -25,7 +25,6 @@
 #include <linux/root_dev.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/time.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/83xx/mpc834x_mds.c b/arch/powerpc/platforms/83xx/mpc834x_mds.c
index 5828d8e97c37..553e793a4a93 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_mds.c
@@ -25,7 +25,6 @@
 #include <linux/root_dev.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/time.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c
index ad8e4bcd7d55..1b1f6c8a1a12 100644
--- a/arch/powerpc/platforms/83xx/mpc836x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c
@@ -33,7 +33,6 @@
 #include <linux/of_platform.h>
 #include <linux/of_device.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/time.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/83xx/sbc834x.c b/arch/powerpc/platforms/83xx/sbc834x.c
index 8a81d7640b1f..26cb3e934722 100644
--- a/arch/powerpc/platforms/83xx/sbc834x.c
+++ b/arch/powerpc/platforms/83xx/sbc834x.c
@@ -27,7 +27,6 @@
 #include <linux/root_dev.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/time.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index edf66870d978..1a046715e461 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -27,6 +27,7 @@
 #include <asm/io.h>
 #include <asm/time.h>
 #include <asm/mpc6xx.h>
+#include <asm/switch_to.h>
 
 #include <sysdev/fsl_soc.h>
 
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c
index df69e99e511c..dd3617c531d7 100644
--- a/arch/powerpc/platforms/85xx/corenet_ds.c
+++ b/arch/powerpc/platforms/85xx/corenet_ds.c
@@ -18,7 +18,6 @@
 #include <linux/interrupt.h>
 #include <linux/memblock.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index d50056f424f6..18014629416d 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -24,7 +24,6 @@
 #include <linux/of_platform.h>
 #include <linux/memblock.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c
index 60120e55da41..3dc1bda3ddc3 100644
--- a/arch/powerpc/platforms/85xx/ksi8560.c
+++ b/arch/powerpc/platforms/85xx/ksi8560.c
@@ -20,7 +20,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index f58872688d8f..585bd22b1406 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -19,7 +19,6 @@
 #include <linux/of_platform.h>
 #include <linux/memblock.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
index d19f675cb369..29ee8fcd75a2 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
@@ -19,7 +19,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index ab5f0bf19454..11156fb53d83 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -27,7 +27,6 @@
 #include <linux/fsl_devices.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <linux/atomic.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index 6e23e3e34bd9..1fd91e9e0ffb 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -22,7 +22,6 @@
 #include <linux/of_platform.h>
 #include <linux/memblock.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index f33662b46b8d..9a6f04406e0d 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -35,7 +35,6 @@
 #include <linux/phy.h>
 #include <linux/memblock.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/time.h>
 #include <asm/io.h>
@@ -271,7 +270,7 @@ static void __init mpc85xx_mds_qe_init(void)
 
 	if (machine_is(p1021_mds)) {
 
-		struct ccsr_guts_85xx __iomem *guts;
+		struct ccsr_guts __iomem *guts;
 
 		np = of_find_node_by_name(NULL, "global-utilities");
 		if (np) {
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index db214cd4c822..313fce4f5574 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -18,7 +18,6 @@
 #include <linux/interrupt.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
@@ -128,7 +127,7 @@ static void __init mpc85xx_rdb_setup_arch(void)
 #if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE)
 	if (machine_is(p1025_rdb)) {
 
-		struct ccsr_guts_85xx __iomem *guts;
+		struct ccsr_guts __iomem *guts;
 
 		np = of_find_node_by_name(NULL, "global-utilities");
 		if (np) {
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index d8bd6563d9ca..dbaf44354f0d 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 0fe88e39945e..e74b7cde9aee 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -150,7 +150,7 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 {
 	struct device_node *guts_node;
 	struct device_node *indirect_node = NULL;
-	struct ccsr_guts_85xx __iomem *guts;
+	struct ccsr_guts __iomem *guts;
 	u8 __iomem *lbc_lcs0_ba = NULL;
 	u8 __iomem *lbc_lcs1_ba = NULL;
 	u8 b;
@@ -269,7 +269,7 @@ exit:
 void p1022ds_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
-	struct ccsr_guts_85xx __iomem *guts;
+	struct ccsr_guts __iomem *guts;
 	unsigned long freq;
 	u64 temp;
 	u32 pxclk;
diff --git a/arch/powerpc/platforms/85xx/p1023_rds.c b/arch/powerpc/platforms/85xx/p1023_rds.c
index 6b07398e4369..2990e8b13dc9 100644
--- a/arch/powerpc/platforms/85xx/p1023_rds.c
+++ b/arch/powerpc/platforms/85xx/p1023_rds.c
@@ -22,7 +22,6 @@
 #include <linux/of_platform.h>
 #include <linux/of_device.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/p2041_rdb.c b/arch/powerpc/platforms/85xx/p2041_rdb.c
index eda6ed5683e1..6541fa2630c0 100644
--- a/arch/powerpc/platforms/85xx/p2041_rdb.c
+++ b/arch/powerpc/platforms/85xx/p2041_rdb.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/phy.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/p3041_ds.c b/arch/powerpc/platforms/85xx/p3041_ds.c
index 96d99a374dcf..f238efa75891 100644
--- a/arch/powerpc/platforms/85xx/p3041_ds.c
+++ b/arch/powerpc/platforms/85xx/p3041_ds.c
@@ -18,7 +18,6 @@
 #include <linux/interrupt.h>
 #include <linux/phy.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/p4080_ds.c b/arch/powerpc/platforms/85xx/p4080_ds.c
index d1b21d7663e3..c92417dc6574 100644
--- a/arch/powerpc/platforms/85xx/p4080_ds.c
+++ b/arch/powerpc/platforms/85xx/p4080_ds.c
@@ -17,7 +17,6 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/p5020_ds.c b/arch/powerpc/platforms/85xx/p5020_ds.c
index e8cba5004fd8..17bef15a85ed 100644
--- a/arch/powerpc/platforms/85xx/p5020_ds.c
+++ b/arch/powerpc/platforms/85xx/p5020_ds.c
@@ -18,7 +18,6 @@
 #include <linux/interrupt.h>
 #include <linux/phy.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c
index 1677b8a22677..cd3a66bdb54b 100644
--- a/arch/powerpc/platforms/85xx/sbc8548.c
+++ b/arch/powerpc/platforms/85xx/sbc8548.c
@@ -30,7 +30,6 @@
 #include <linux/fsl_devices.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <linux/atomic.h>
diff --git a/arch/powerpc/platforms/85xx/sbc8560.c b/arch/powerpc/platforms/85xx/sbc8560.c
index 3c3bbcc27566..b1be632ede43 100644
--- a/arch/powerpc/platforms/85xx/sbc8560.c
+++ b/arch/powerpc/platforms/85xx/sbc8560.c
@@ -21,7 +21,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c
index b71919217756..b9c6daa07b66 100644
--- a/arch/powerpc/platforms/85xx/socrates.c
+++ b/arch/powerpc/platforms/85xx/socrates.c
@@ -29,7 +29,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c
index 27ca3a7b04ab..e0508002b086 100644
--- a/arch/powerpc/platforms/85xx/stx_gp3.c
+++ b/arch/powerpc/platforms/85xx/stx_gp3.c
@@ -28,7 +28,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index d7504cefe016..4d786c25d3e5 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -26,7 +26,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 503c21596c63..41c687550ea7 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -21,7 +21,6 @@
 #include <linux/interrupt.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index ed58b6cfd60c..1fca663f1b25 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -24,7 +24,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 710db69bd523..14e0e576bcbd 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -24,7 +24,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index 4a13d2f4ac20..1638f43599f0 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -24,7 +24,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index 13fa9a6403e6..62cd3c555bfb 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -25,7 +25,6 @@
 #include <linux/seq_file.h>
 #include <linux/of.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
@@ -226,7 +225,7 @@ void mpc8610hpcd_set_monitor_port(enum fsl_diu_monitor_port port)
 void mpc8610hpcd_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
-	struct ccsr_guts_86xx __iomem *guts;
+	struct ccsr_guts __iomem *guts;
 	unsigned long freq;
 	u64 temp;
 	u32 pxclk;
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 569262ca499a..3755e61d7ecf 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -21,7 +21,6 @@
 #include <linux/of_platform.h>
 #include <linux/memblock.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c
index 22cc3571ae19..9982f57c98b9 100644
--- a/arch/powerpc/platforms/86xx/pic.c
+++ b/arch/powerpc/platforms/86xx/pic.c
@@ -12,7 +12,6 @@
 #include <linux/interrupt.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/mpic.h>
 #include <asm/i8259.h>
 
diff --git a/arch/powerpc/platforms/86xx/sbc8641d.c b/arch/powerpc/platforms/86xx/sbc8641d.c
index 51c8f331b671..e7007d0d949e 100644
--- a/arch/powerpc/platforms/86xx/sbc8641d.c
+++ b/arch/powerpc/platforms/86xx/sbc8641d.c
@@ -21,7 +21,6 @@
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/8xx/mpc86xads_setup.c b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
index caaec29796b7..866feff83c91 100644
--- a/arch/powerpc/platforms/8xx/mpc86xads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
@@ -19,7 +19,6 @@
 
 #include <asm/io.h>
 #include <asm/machdep.h>
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/8xx_immap.h>
 #include <asm/cpm1.h>
diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
index 45ed6cdc1310..5d98398c2f5e 100644
--- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
@@ -32,7 +32,6 @@
 #include <asm/machdep.h>
 #include <asm/page.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/mpc8xx.h>
 #include <asm/8xx_immap.h>
diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
index 528e00ddef31..8d21ab70e06c 100644
--- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
@@ -35,7 +35,6 @@
 #include <asm/machdep.h>
 #include <asm/page.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/mpc8xx.h>
 #include <asm/8xx_immap.h>
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 2516c1cf8467..943c9d39aa16 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -95,7 +95,6 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group,
 	unsigned long lpar_rc;
 	u64 hpte_v, hpte_r, slot;
 
-	/* same as iseries */
 	if (vflags & HPTE_V_SECONDARY)
 		return -1;
 
@@ -319,7 +318,6 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
 	unsigned long lpar_rc;
 	u64 hpte_v, hpte_r, slot;
 
-	/* same as iseries */
 	if (vflags & HPTE_V_SECONDARY)
 		return -1;
 
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index ae9fc7bc17d6..b9f509a34c01 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -564,7 +564,8 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev)
 /* A coherent allocation implies strong ordering */
 
 static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
-				      dma_addr_t *dma_handle, gfp_t flag)
+				      dma_addr_t *dma_handle, gfp_t flag,
+				      struct dma_attrs *attrs)
 {
 	if (iommu_fixed_is_weak)
 		return iommu_alloc_coherent(dev, cell_get_iommu_table(dev),
@@ -572,18 +573,19 @@ static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
 					    device_to_mask(dev), flag,
 					    dev_to_node(dev));
 	else
-		return dma_direct_ops.alloc_coherent(dev, size, dma_handle,
-						     flag);
+		return dma_direct_ops.alloc(dev, size, dma_handle, flag,
+					    attrs);
 }
 
 static void dma_fixed_free_coherent(struct device *dev, size_t size,
-				    void *vaddr, dma_addr_t dma_handle)
+				    void *vaddr, dma_addr_t dma_handle,
+				    struct dma_attrs *attrs)
 {
 	if (iommu_fixed_is_weak)
 		iommu_free_coherent(cell_get_iommu_table(dev), size, vaddr,
 				    dma_handle);
 	else
-		dma_direct_ops.free_coherent(dev, size, vaddr, dma_handle);
+		dma_direct_ops.free(dev, size, vaddr, dma_handle, attrs);
 }
 
 static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page,
@@ -642,8 +644,8 @@ static int dma_fixed_dma_supported(struct device *dev, u64 mask)
 static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask);
 
 struct dma_map_ops dma_iommu_fixed_ops = {
-	.alloc_coherent = dma_fixed_alloc_coherent,
-	.free_coherent  = dma_fixed_free_coherent,
+	.alloc          = dma_fixed_alloc_coherent,
+	.free           = dma_fixed_free_coherent,
 	.map_sg         = dma_fixed_map_sg,
 	.unmap_sg       = dma_fixed_unmap_sg,
 	.dma_supported  = dma_fixed_dma_supported,
diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c
index 7f9b6742f8b6..6e3409d590ac 100644
--- a/arch/powerpc/platforms/cell/qpace_setup.c
+++ b/arch/powerpc/platforms/cell/qpace_setup.c
@@ -61,7 +61,7 @@ static void qpace_progress(char *s, unsigned short hex)
 	printk("*** %04x : %s\n", hex, s ? s : "");
 }
 
-static const struct of_device_id qpace_bus_ids[] __initdata = {
+static const struct of_device_id qpace_bus_ids[] __initconst = {
 	{ .type = "soc", },
 	{ .compatible = "soc", },
 	{ .type = "spider", },
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index fa3e294fd343..4ab087671185 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -140,7 +140,7 @@ static int __devinit cell_setup_phb(struct pci_controller *phb)
 	return 0;
 }
 
-static const struct of_device_id cell_bus_ids[] __initdata = {
+static const struct of_device_id cell_bus_ids[] __initconst = {
 	{ .type = "soc", },
 	{ .compatible = "soc", },
 	{ .type = "spider", },
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index 4a255cf8cd17..49a65e2dfc71 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -38,7 +38,6 @@
 #include <asm/machdep.h>
 #include <asm/cputable.h>
 #include <asm/firmware.h>
-#include <asm/system.h>
 #include <asm/rtas.h>
 #include <asm/cputhreads.h>
 
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 03c5fce2a5b3..c2c5b078ba80 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -122,7 +122,7 @@ static struct spu_context *coredump_next_context(int *fd)
 	struct spu_context *ctx = NULL;
 
 	for (; *fd < fdt->max_fds; (*fd)++) {
-		if (!FD_ISSET(*fd, fdt->open_fds))
+		if (!fd_is_open(*fd, fdt))
 			continue;
 
 		file = fcheck(*fd);
diff --git a/arch/powerpc/platforms/embedded6xx/c2k.c b/arch/powerpc/platforms/embedded6xx/c2k.c
index 8cab5731850f..ebd3963fdf91 100644
--- a/arch/powerpc/platforms/embedded6xx/c2k.c
+++ b/arch/powerpc/platforms/embedded6xx/c2k.c
@@ -23,7 +23,6 @@
 
 #include <asm/machdep.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/time.h>
 
 #include <mm/mmu_decl.h>
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index ab51b21b4bd7..8c305c7c8977 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -28,7 +28,6 @@
 #include <linux/of_platform.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index 74ccce36baed..beeaf4a173e1 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -32,7 +32,6 @@
 #include <linux/tty.h>
 #include <linux/serial_core.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/platforms/embedded6xx/prpmc2800.c b/arch/powerpc/platforms/embedded6xx/prpmc2800.c
index 670035f49a69..d455f08bea53 100644
--- a/arch/powerpc/platforms/embedded6xx/prpmc2800.c
+++ b/arch/powerpc/platforms/embedded6xx/prpmc2800.c
@@ -17,7 +17,6 @@
 
 #include <asm/machdep.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/time.h>
 
 #include <mm/mmu_decl.h>
diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c
index e0ed3c71d69b..c458b60d14c4 100644
--- a/arch/powerpc/platforms/embedded6xx/storcenter.c
+++ b/arch/powerpc/platforms/embedded6xx/storcenter.c
@@ -16,7 +16,6 @@
 #include <linux/initrd.h>
 #include <linux/of_platform.h>
 
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/prom.h>
 #include <asm/mpic.h>
diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c
index 8b0c2082a783..64fde058e545 100644
--- a/arch/powerpc/platforms/fsl_uli1575.c
+++ b/arch/powerpc/platforms/fsl_uli1575.c
@@ -15,7 +15,6 @@
 #include <linux/interrupt.h>
 #include <linux/mc146818rtc.h>
 
-#include <asm/system.h>
 #include <asm/pci-bridge.h>
 
 #define ULI_PIRQA	0x08
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 3b7545a51aa9..cb1b0b35a0c6 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -47,7 +47,6 @@
 #include <asm/processor.h>
 #include <asm/sections.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/maple/time.c b/arch/powerpc/platforms/maple/time.c
index eac569dee27c..b4a369dac3a8 100644
--- a/arch/powerpc/platforms/maple/time.c
+++ b/arch/powerpc/platforms/maple/time.c
@@ -27,7 +27,6 @@
 
 #include <asm/sections.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index e777ad471a48..2ed9212d7d59 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -32,13 +32,13 @@
 #include <linux/gfp.h>
 
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/iommu.h>
 #include <asm/machdep.h>
 #include <asm/mpic.h>
 #include <asm/smp.h>
 #include <asm/time.h>
 #include <asm/mmu.h>
+#include <asm/debug.h>
 
 #include <pcmcia/ss.h>
 #include <pcmcia/cistpl.h>
diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c
index 84d7fd9bcc69..3e91ef538114 100644
--- a/arch/powerpc/platforms/powermac/bootx_init.c
+++ b/arch/powerpc/platforms/powermac/bootx_init.c
@@ -19,6 +19,7 @@
 #include <asm/bootx.h>
 #include <asm/btext.h>
 #include <asm/io.h>
+#include <asm/setup.h>
 
 #undef DEBUG
 #define SET_BOOT_BAT
diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c
index 1fc386a23f18..64171198535c 100644
--- a/arch/powerpc/platforms/powermac/cpufreq_32.c
+++ b/arch/powerpc/platforms/powermac/cpufreq_32.c
@@ -33,9 +33,9 @@
 #include <asm/sections.h>
 #include <asm/cputable.h>
 #include <asm/time.h>
-#include <asm/system.h>
 #include <asm/mpic.h>
 #include <asm/keylargo.h>
+#include <asm/switch_to.h>
 
 /* WARNING !!! This will cause calibrate_delay() to be called,
  * but this is an __init function ! So you MUST go edit
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index da18b26dcc6f..014d06e6d46b 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -23,7 +23,6 @@
 #include <linux/spinlock.h>
 #include <asm/sections.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/nvram.h>
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 970ea1de4298..141f8899a633 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -57,7 +57,6 @@
 #include <asm/reg.h>
 #include <asm/sections.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c
index 11c9fce43b5b..8680bb69795d 100644
--- a/arch/powerpc/platforms/powermac/time.c
+++ b/arch/powerpc/platforms/powermac/time.c
@@ -26,7 +26,6 @@
 
 #include <asm/sections.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 17210c526c52..3ef46254c35b 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -25,7 +25,6 @@
 #include <asm/machdep.h>
 #include <asm/cputable.h>
 #include <asm/firmware.h>
-#include <asm/system.h>
 #include <asm/rtas.h>
 #include <asm/vdso_datapage.h>
 #include <asm/cputhreads.h>
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index 8bd6ba542691..de2aea421707 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -29,6 +29,7 @@
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/lv1call.h>
+#include <asm/setup.h>
 
 #include "platform.h"
 
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 880eb9ce22c5..5606fe36faf2 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -515,7 +515,8 @@ core_initcall(ps3_system_bus_init);
  * to the dma address (mapping) of the first page.
  */
 static void * ps3_alloc_coherent(struct device *_dev, size_t size,
-				      dma_addr_t *dma_handle, gfp_t flag)
+				 dma_addr_t *dma_handle, gfp_t flag,
+				 struct dma_attrs *attrs)
 {
 	int result;
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
@@ -552,7 +553,7 @@ clean_none:
 }
 
 static void ps3_free_coherent(struct device *_dev, size_t size, void *vaddr,
-	dma_addr_t dma_handle)
+			      dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 
@@ -701,8 +702,8 @@ static u64 ps3_dma_get_required_mask(struct device *_dev)
 }
 
 static struct dma_map_ops ps3_sb_dma_ops = {
-	.alloc_coherent = ps3_alloc_coherent,
-	.free_coherent = ps3_free_coherent,
+	.alloc = ps3_alloc_coherent,
+	.free = ps3_free_coherent,
 	.map_sg = ps3_sb_map_sg,
 	.unmap_sg = ps3_sb_unmap_sg,
 	.dma_supported = ps3_dma_supported,
@@ -712,8 +713,8 @@ static struct dma_map_ops ps3_sb_dma_ops = {
 };
 
 static struct dma_map_ops ps3_ioc0_dma_ops = {
-	.alloc_coherent = ps3_alloc_coherent,
-	.free_coherent = ps3_free_coherent,
+	.alloc = ps3_alloc_coherent,
+	.free = ps3_free_coherent,
 	.map_sg = ps3_ioc0_map_sg,
 	.unmap_sg = ps3_ioc0_unmap_sg,
 	.dma_supported = ps3_dma_supported,
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 0e8656370063..a7648543c59e 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -25,10 +25,10 @@
 #include <linux/debugfs.h>
 #include <linux/spinlock.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/firmware.h>
 #include <asm/lppaca.h>
+#include <asm/debug.h>
 
 #include "plpar_wrappers.h"
 
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 8011088392d3..309d38ef7322 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -984,7 +984,8 @@ int __exit eeh_ops_unregister(const char *name)
  */
 void __init eeh_init(void)
 {
-	struct device_node *phb, *np;
+	struct pci_controller *hose, *tmp;
+	struct device_node *phb;
 	int ret;
 
 	/* call platform initialization function */
@@ -1000,19 +1001,9 @@ void __init eeh_init(void)
 
 	raw_spin_lock_init(&confirm_error_lock);
 
-	np = of_find_node_by_path("/rtas");
-	if (np == NULL)
-		return;
-
-	/* Enable EEH for all adapters.  Note that eeh requires buid's */
-	for (phb = of_find_node_by_name(NULL, "pci"); phb;
-	     phb = of_find_node_by_name(phb, "pci")) {
-		unsigned long buid;
-
-		buid = get_phb_buid(phb);
-		if (buid == 0 || !of_node_to_eeh_dev(phb))
-			continue;
-
+	/* Enable EEH for all adapters */
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		phb = hose->dn;
 		traverse_pci_devices(phb, eeh_early_enable, NULL);
 	}
 
diff --git a/arch/powerpc/platforms/pseries/eeh_dev.c b/arch/powerpc/platforms/pseries/eeh_dev.c
index f3aed7dcae95..c4507d095900 100644
--- a/arch/powerpc/platforms/pseries/eeh_dev.c
+++ b/arch/powerpc/platforms/pseries/eeh_dev.c
@@ -62,7 +62,7 @@ void * __devinit eeh_dev_init(struct device_node *dn, void *data)
 	}
 
 	/* Associate EEH device with OF node */
-	dn->edev  = edev;
+	PCI_DN(dn)->edev = edev;
 	edev->dn  = dn;
 	edev->phb = phb;
 
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index 4a4752565856..4cb375c0f8d1 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -59,8 +59,7 @@ static int eeh_event_handler(void * dummy)
 	struct eeh_event *event;
 	struct eeh_dev *edev;
 
-	daemonize("eehd");
-	set_current_state(TASK_INTERRUPTIBLE);
+	set_task_comm(current, "eehd");
 
 	spin_lock_irqsave(&eeh_eventlist_lock, flags);
 	event = NULL;
@@ -83,6 +82,7 @@ static int eeh_event_handler(void * dummy)
 	printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
 	       eeh_pci_name(edev->pdev));
 
+	set_current_state(TASK_INTERRUPTIBLE);	/* Don't add to load average */
 	edev = handle_eeh_events(event);
 
 	eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index c986d08d0807..64c97d8ac0c5 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -23,7 +23,6 @@
 #include <linux/delay.h>
 #include <linux/sched.h>	/* for idle_task_exit */
 #include <linux/cpu.h>
-#include <asm/system.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
 #include <asm/firmware.h>
diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c
index 1a709bc48ce1..ef9d9d84c7d5 100644
--- a/arch/powerpc/platforms/pseries/io_event_irq.c
+++ b/arch/powerpc/platforms/pseries/io_event_irq.c
@@ -63,73 +63,9 @@ EXPORT_SYMBOL_GPL(pseries_ioei_notifier_list);
 
 static int ioei_check_exception_token;
 
-/* pSeries event log format */
-
-/* Two bytes ASCII section IDs */
-#define PSERIES_ELOG_SECT_ID_PRIV_HDR		(('P' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_USER_HDR		(('U' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_PRIMARY_SRC	(('P' << 8) | 'S')
-#define PSERIES_ELOG_SECT_ID_EXTENDED_UH	(('E' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_FAILING_MTMS	(('M' << 8) | 'T')
-#define PSERIES_ELOG_SECT_ID_SECONDARY_SRC	(('S' << 8) | 'S')
-#define PSERIES_ELOG_SECT_ID_DUMP_LOCATOR	(('D' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_FW_ERROR		(('S' << 8) | 'W')
-#define PSERIES_ELOG_SECT_ID_IMPACT_PART_ID	(('L' << 8) | 'P')
-#define PSERIES_ELOG_SECT_ID_LOGIC_RESOURCE_ID	(('L' << 8) | 'R')
-#define PSERIES_ELOG_SECT_ID_HMC_ID		(('H' << 8) | 'M')
-#define PSERIES_ELOG_SECT_ID_EPOW		(('E' << 8) | 'P')
-#define PSERIES_ELOG_SECT_ID_IO_EVENT		(('I' << 8) | 'E')
-#define PSERIES_ELOG_SECT_ID_MANUFACT_INFO	(('M' << 8) | 'I')
-#define PSERIES_ELOG_SECT_ID_CALL_HOME		(('C' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_USER_DEF		(('U' << 8) | 'D')
-
-/* Vendor specific Platform Event Log Format, Version 6, section header */
-struct pseries_elog_section {
-	uint16_t id;			/* 0x00 2-byte ASCII section ID	*/
-	uint16_t length;		/* 0x02 Section length in bytes	*/
-	uint8_t version;		/* 0x04 Section version		*/
-	uint8_t subtype;		/* 0x05 Section subtype		*/
-	uint16_t creator_component;	/* 0x06 Creator component ID	*/
-	uint8_t data[];			/* 0x08 Start of section data	*/
-};
-
 static char ioei_rtas_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned;
 
 /**
- * Find data portion of a specific section in RTAS extended event log.
- * @elog: RTAS error/event log.
- * @sect_id: secsion ID.
- *
- * Return:
- *	pointer to the section data of the specified section
- *	NULL if not found
- */
-static struct pseries_elog_section *find_xelog_section(struct rtas_error_log *elog,
-						       uint16_t sect_id)
-{
-	struct rtas_ext_event_log_v6 *xelog =
-		(struct rtas_ext_event_log_v6 *) elog->buffer;
-	struct pseries_elog_section *sect;
-	unsigned char *p, *log_end;
-
-	/* Check that we understand the format */
-	if (elog->extended_log_length < sizeof(struct rtas_ext_event_log_v6) ||
-	    xelog->log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG ||
-	    xelog->company_id != RTAS_V6EXT_COMPANY_ID_IBM)
-		return NULL;
-
-	log_end = elog->buffer + elog->extended_log_length;
-	p = xelog->vendor_log;
-	while (p < log_end) {
-		sect = (struct pseries_elog_section *)p;
-		if (sect->id == sect_id)
-			return sect;
-		p += sect->length;
-	}
-	return NULL;
-}
-
-/**
  * Find the data portion of an IO Event section from event log.
  * @elog: RTAS error/event log.
  *
@@ -138,7 +74,7 @@ static struct pseries_elog_section *find_xelog_section(struct rtas_error_log *el
  */
 static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog)
 {
-	struct pseries_elog_section *sect;
+	struct pseries_errorlog *sect;
 
 	/* We should only ever get called for io-event interrupts, but if
 	 * we do get called for another type then something went wrong so
@@ -152,7 +88,7 @@ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog)
 		return NULL;
 	}
 
-	sect = find_xelog_section(elog, PSERIES_ELOG_SECT_ID_IO_EVENT);
+	sect = get_pseries_errorlog(elog, PSERIES_ELOG_SECT_ID_IO_EVENT);
 	if (unlikely(!sect)) {
 		printk_once(KERN_WARNING "io_event_irq: RTAS extended event "
 			    "log does not contain an IO Event section. "
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index c442f2b1980f..0915b1ad66ce 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -809,8 +809,7 @@ machine_arch_initcall(pseries, find_existing_ddw_windows);
 static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 			struct ddw_query_response *query)
 {
-	struct device_node *dn;
-	struct pci_dn *pcidn;
+	struct eeh_dev *edev;
 	u32 cfg_addr;
 	u64 buid;
 	int ret;
@@ -821,12 +820,12 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	 * Retrieve them from the pci device, not the node with the
 	 * dma-window property
 	 */
-	dn = pci_device_to_OF_node(dev);
-	pcidn = PCI_DN(dn);
-	cfg_addr = pcidn->eeh_config_addr;
-	if (pcidn->eeh_pe_config_addr)
-		cfg_addr = pcidn->eeh_pe_config_addr;
-	buid = pcidn->phb->buid;
+	edev = pci_dev_to_eeh_dev(dev);
+	cfg_addr = edev->config_addr;
+	if (edev->pe_config_addr)
+		cfg_addr = edev->pe_config_addr;
+	buid = edev->phb->buid;
+
 	ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
 		  cfg_addr, BUID_HI(buid), BUID_LO(buid));
 	dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x"
@@ -839,8 +838,7 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 			struct ddw_create_response *create, int page_shift,
 			int window_shift)
 {
-	struct device_node *dn;
-	struct pci_dn *pcidn;
+	struct eeh_dev *edev;
 	u32 cfg_addr;
 	u64 buid;
 	int ret;
@@ -851,12 +849,11 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	 * Retrieve them from the pci device, not the node with the
 	 * dma-window property
 	 */
-	dn = pci_device_to_OF_node(dev);
-	pcidn = PCI_DN(dn);
-	cfg_addr = pcidn->eeh_config_addr;
-	if (pcidn->eeh_pe_config_addr)
-		cfg_addr = pcidn->eeh_pe_config_addr;
-	buid = pcidn->phb->buid;
+	edev = pci_dev_to_eeh_dev(dev);
+	cfg_addr = edev->config_addr;
+	if (edev->pe_config_addr)
+		cfg_addr = edev->pe_config_addr;
+	buid = edev->phb->buid;
 
 	do {
 		/* extra outputs are LIOBN and dma-addr (hi, lo) */
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
index a12e95af6933..41a34bc4a9a2 100644
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -14,9 +14,9 @@
 
 #include <asm/paca.h>
 #include <asm/reg.h>
-#include <asm/system.h>
 #include <asm/machdep.h>
 #include <asm/firmware.h>
+#include <asm/runlatch.h>
 
 #include "plpar_wrappers.h"
 #include "pseries.h"
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 086d2ae4e06a..c4dfccd3a3d9 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -16,37 +16,15 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-/* Change Activity:
- * 2001/09/21 : engebret : Created with minimal EPOW and HW exception support.
- * End Change Activity
- */
-
-#include <linux/errno.h>
-#include <linux/threads.h>
-#include <linux/kernel_stat.h>
-#include <linux/signal.h>
 #include <linux/sched.h>
-#include <linux/ioport.h>
 #include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/init.h>
-#include <linux/delay.h>
 #include <linux/irq.h>
-#include <linux/random.h>
-#include <linux/sysrq.h>
-#include <linux/bitops.h>
-
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/pgtable.h>
-#include <asm/irq.h>
-#include <asm/cache.h>
-#include <asm/prom.h>
-#include <asm/ptrace.h>
+#include <linux/of.h>
+#include <linux/fs.h>
+#include <linux/reboot.h>
+
 #include <asm/machdep.h>
 #include <asm/rtas.h>
-#include <asm/udbg.h>
 #include <asm/firmware.h>
 
 #include "pseries.h"
@@ -57,7 +35,6 @@ static DEFINE_SPINLOCK(ras_log_buf_lock);
 static char global_mce_data_buf[RTAS_ERROR_LOG_MAX];
 static DEFINE_PER_CPU(__u64, mce_data_buf);
 
-static int ras_get_sensor_state_token;
 static int ras_check_exception_token;
 
 #define EPOW_SENSOR_TOKEN	9
@@ -75,7 +52,6 @@ static int __init init_ras_IRQ(void)
 {
 	struct device_node *np;
 
-	ras_get_sensor_state_token = rtas_token("get-sensor-state");
 	ras_check_exception_token = rtas_token("check-exception");
 
 	/* Internal Errors */
@@ -95,26 +71,126 @@ static int __init init_ras_IRQ(void)
 
 	return 0;
 }
-__initcall(init_ras_IRQ);
+subsys_initcall(init_ras_IRQ);
 
-/*
- * Handle power subsystem events (EPOW).
- *
- * Presently we just log the event has occurred.  This should be fixed
- * to examine the type of power failure and take appropriate action where
- * the time horizon permits something useful to be done.
- */
+#define EPOW_SHUTDOWN_NORMAL				1
+#define EPOW_SHUTDOWN_ON_UPS				2
+#define EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS	3
+#define EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH	4
+
+static void handle_system_shutdown(char event_modifier)
+{
+	switch (event_modifier) {
+	case EPOW_SHUTDOWN_NORMAL:
+		pr_emerg("Firmware initiated power off");
+		orderly_poweroff(1);
+		break;
+
+	case EPOW_SHUTDOWN_ON_UPS:
+		pr_emerg("Loss of power reported by firmware, system is "
+			"running on UPS/battery");
+		break;
+
+	case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS:
+		pr_emerg("Loss of system critical functions reported by "
+			"firmware");
+		pr_emerg("Check RTAS error log for details");
+		orderly_poweroff(1);
+		break;
+
+	case EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH:
+		pr_emerg("Ambient temperature too high reported by firmware");
+		pr_emerg("Check RTAS error log for details");
+		orderly_poweroff(1);
+		break;
+
+	default:
+		pr_err("Unknown power/cooling shutdown event (modifier %d)",
+			event_modifier);
+	}
+}
+
+struct epow_errorlog {
+	unsigned char sensor_value;
+	unsigned char event_modifier;
+	unsigned char extended_modifier;
+	unsigned char reserved;
+	unsigned char platform_reason;
+};
+
+#define EPOW_RESET			0
+#define EPOW_WARN_COOLING		1
+#define EPOW_WARN_POWER			2
+#define EPOW_SYSTEM_SHUTDOWN		3
+#define EPOW_SYSTEM_HALT		4
+#define EPOW_MAIN_ENCLOSURE		5
+#define EPOW_POWER_OFF			7
+
+void rtas_parse_epow_errlog(struct rtas_error_log *log)
+{
+	struct pseries_errorlog *pseries_log;
+	struct epow_errorlog *epow_log;
+	char action_code;
+	char modifier;
+
+	pseries_log = get_pseries_errorlog(log, PSERIES_ELOG_SECT_ID_EPOW);
+	if (pseries_log == NULL)
+		return;
+
+	epow_log = (struct epow_errorlog *)pseries_log->data;
+	action_code = epow_log->sensor_value & 0xF;	/* bottom 4 bits */
+	modifier = epow_log->event_modifier & 0xF;	/* bottom 4 bits */
+
+	switch (action_code) {
+	case EPOW_RESET:
+		pr_err("Non critical power or cooling issue cleared");
+		break;
+
+	case EPOW_WARN_COOLING:
+		pr_err("Non critical cooling issue reported by firmware");
+		pr_err("Check RTAS error log for details");
+		break;
+
+	case EPOW_WARN_POWER:
+		pr_err("Non critical power issue reported by firmware");
+		pr_err("Check RTAS error log for details");
+		break;
+
+	case EPOW_SYSTEM_SHUTDOWN:
+		handle_system_shutdown(epow_log->event_modifier);
+		break;
+
+	case EPOW_SYSTEM_HALT:
+		pr_emerg("Firmware initiated power off");
+		orderly_poweroff(1);
+		break;
+
+	case EPOW_MAIN_ENCLOSURE:
+	case EPOW_POWER_OFF:
+		pr_emerg("Critical power/cooling issue reported by firmware");
+		pr_emerg("Check RTAS error log for details");
+		pr_emerg("Immediate power off");
+		emergency_sync();
+		kernel_power_off();
+		break;
+
+	default:
+		pr_err("Unknown power/cooling event (action code %d)",
+			action_code);
+	}
+}
+
+/* Handle environmental and power warning (EPOW) interrupts. */
 static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 {
-	int status = 0xdeadbeef;
-	int state = 0;
+	int status;
+	int state;
 	int critical;
 
-	status = rtas_call(ras_get_sensor_state_token, 2, 2, &state,
-			   EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX);
+	status = rtas_get_sensor(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX, &state);
 
 	if (state > 3)
-		critical = 1;  /* Time Critical */
+		critical = 1;		/* Time Critical */
 	else
 		critical = 0;
 
@@ -123,18 +199,14 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 	status = rtas_call(ras_check_exception_token, 6, 1, NULL,
 			   RTAS_VECTOR_EXTERNAL_INTERRUPT,
 			   virq_to_hw(irq),
-			   RTAS_EPOW_WARNING | RTAS_POWERMGM_EVENTS,
+			   RTAS_EPOW_WARNING,
 			   critical, __pa(&ras_log_buf),
 				rtas_get_error_log_max());
 
-	udbg_printf("EPOW <0x%lx 0x%x 0x%x>\n",
-		    *((unsigned long *)&ras_log_buf), status, state);
-	printk(KERN_WARNING "EPOW <0x%lx 0x%x 0x%x>\n",
-	       *((unsigned long *)&ras_log_buf), status, state);
-
-	/* format and print the extended information */
 	log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, 0);
 
+	rtas_parse_epow_errlog((struct rtas_error_log *)ras_log_buf);
+
 	spin_unlock(&ras_log_buf_lock);
 	return IRQ_HANDLED;
 }
@@ -150,7 +222,7 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 {
 	struct rtas_error_log *rtas_elog;
-	int status = 0xdeadbeef;
+	int status;
 	int fatal;
 
 	spin_lock(&ras_log_buf_lock);
@@ -158,7 +230,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 	status = rtas_call(ras_check_exception_token, 6, 1, NULL,
 			   RTAS_VECTOR_EXTERNAL_INTERRUPT,
 			   virq_to_hw(irq),
-			   RTAS_INTERNAL_ERROR, 1 /*Time Critical */,
+			   RTAS_INTERNAL_ERROR, 1 /* Time Critical */,
 			   __pa(&ras_log_buf),
 				rtas_get_error_log_max());
 
@@ -173,24 +245,13 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 	log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, fatal);
 
 	if (fatal) {
-		udbg_printf("Fatal HW Error <0x%lx 0x%x>\n",
-			    *((unsigned long *)&ras_log_buf), status);
-		printk(KERN_EMERG "Error: Fatal hardware error <0x%lx 0x%x>\n",
-		       *((unsigned long *)&ras_log_buf), status);
-
-#ifndef DEBUG_RTAS_POWER_OFF
-		/* Don't actually power off when debugging so we can test
-		 * without actually failing while injecting errors.
-		 * Error data will not be logged to syslog.
-		 */
-		ppc_md.power_off();
-#endif
+		pr_emerg("Fatal hardware error reported by firmware");
+		pr_emerg("Check RTAS error log for details");
+		pr_emerg("Immediate power off");
+		emergency_sync();
+		kernel_power_off();
 	} else {
-		udbg_printf("Recoverable HW Error <0x%lx 0x%x>\n",
-			    *((unsigned long *)&ras_log_buf), status);
-		printk(KERN_WARNING
-		       "Warning: Recoverable hardware error <0x%lx 0x%x>\n",
-		       *((unsigned long *)&ras_log_buf), status);
+		pr_err("Recoverable hardware error reported by firmware");
 	}
 
 	spin_unlock(&ras_log_buf_lock);
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index eadba9521a35..e16bb8d48550 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -37,7 +37,6 @@
 #include <asm/machdep.h>
 #include <asm/cputable.h>
 #include <asm/firmware.h>
-#include <asm/system.h>
 #include <asm/rtas.h>
 #include <asm/pSeries_reconfig.h>
 #include <asm/mpic.h>
diff --git a/arch/powerpc/platforms/wsp/chroma.c b/arch/powerpc/platforms/wsp/chroma.c
index ca6fa26f6e63..8ef53bc2e70e 100644
--- a/arch/powerpc/platforms/wsp/chroma.c
+++ b/arch/powerpc/platforms/wsp/chroma.c
@@ -17,7 +17,6 @@
 #include <linux/time.h>
 
 #include <asm/machdep.h>
-#include <asm/system.h>
 #include <asm/udbg.h>
 
 #include "ics.h"
diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c
index 0c1ae06d0be1..508ec8282b96 100644
--- a/arch/powerpc/platforms/wsp/psr2.c
+++ b/arch/powerpc/platforms/wsp/psr2.c
@@ -17,7 +17,6 @@
 #include <linux/time.h>
 
 #include <asm/machdep.h>
-#include <asm/system.h>
 #include <asm/udbg.h>
 
 #include "ics.h"
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
index 763014cd1e62..1526551f9fe6 100644
--- a/arch/powerpc/platforms/wsp/wsp_pci.c
+++ b/arch/powerpc/platforms/wsp/wsp_pci.c
@@ -27,6 +27,7 @@
 #include <asm/ppc-pci.h>
 #include <asm/iommu.h>
 #include <asm/io-workarounds.h>
+#include <asm/debug.h>
 
 #include "wsp.h"
 #include "wsp_pci.h"
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index bf6c7cc0a6af..4dd534194ae8 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -26,7 +26,6 @@
 
 #include <asm/udbg.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/rheap.h>
 #include <asm/cpm.h>
 
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index e8f385fbf549..c449dbd1c938 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -31,7 +31,6 @@
 #include <linux/fs_enet_pd.h>
 #include <linux/fs_uart_pd.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 5287e95cec3a..0968b66b4cf9 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/bitmap.h>
 #include <asm/msi_bitmap.h>
+#include <asm/setup.h>
 
 int msi_bitmap_alloc_hwirqs(struct msi_bitmap *bmp, int num)
 {
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index ceb09cbd2329..818e763f8265 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006 Freescale Semicondutor, Inc. All rights reserved.
+ * Copyright (C) 2006-2010 Freescale Semicondutor, Inc. All rights reserved.
  *
  * Authors: 	Shlomi Gridish <gridish@freescale.com>
  * 		Li Yang <leoli@freescale.com>
@@ -266,7 +266,19 @@ EXPORT_SYMBOL(qe_clock_source);
 static void qe_snums_init(void)
 {
 	int i;
-	static const u8 snum_init[] = {
+	static const u8 snum_init_76[] = {
+		0x04, 0x05, 0x0C, 0x0D, 0x14, 0x15, 0x1C, 0x1D,
+		0x24, 0x25, 0x2C, 0x2D, 0x34, 0x35, 0x88, 0x89,
+		0x98, 0x99, 0xA8, 0xA9, 0xB8, 0xB9, 0xC8, 0xC9,
+		0xD8, 0xD9, 0xE8, 0xE9, 0x44, 0x45, 0x4C, 0x4D,
+		0x54, 0x55, 0x5C, 0x5D, 0x64, 0x65, 0x6C, 0x6D,
+		0x74, 0x75, 0x7C, 0x7D, 0x84, 0x85, 0x8C, 0x8D,
+		0x94, 0x95, 0x9C, 0x9D, 0xA4, 0xA5, 0xAC, 0xAD,
+		0xB4, 0xB5, 0xBC, 0xBD, 0xC4, 0xC5, 0xCC, 0xCD,
+		0xD4, 0xD5, 0xDC, 0xDD, 0xE4, 0xE5, 0xEC, 0xED,
+		0xF4, 0xF5, 0xFC, 0xFD,
+	};
+	static const u8 snum_init_46[] = {
 		0x04, 0x05, 0x0C, 0x0D, 0x14, 0x15, 0x1C, 0x1D,
 		0x24, 0x25, 0x2C, 0x2D, 0x34, 0x35, 0x88, 0x89,
 		0x98, 0x99, 0xA8, 0xA9, 0xB8, 0xB9, 0xC8, 0xC9,
@@ -274,9 +286,15 @@ static void qe_snums_init(void)
 		0x28, 0x29, 0x38, 0x39, 0x48, 0x49, 0x58, 0x59,
 		0x68, 0x69, 0x78, 0x79, 0x80, 0x81,
 	};
+	static const u8 *snum_init;
 
 	qe_num_of_snum = qe_get_num_of_snums();
 
+	if (qe_num_of_snum == 76)
+		snum_init = snum_init_76;
+	else
+		snum_init = snum_init_46;
+
 	for (i = 0; i < qe_num_of_snum; i++) {
 		snums[i].num = snum_init[i];
 		snums[i].state = QE_SNUM_STATE_FREE;
diff --git a/arch/powerpc/sysdev/tsi108_dev.c b/arch/powerpc/sysdev/tsi108_dev.c
index 2370e1c63379..1fd0717ade02 100644
--- a/arch/powerpc/sysdev/tsi108_dev.c
+++ b/arch/powerpc/sysdev/tsi108_dev.c
@@ -22,7 +22,6 @@
 #include <linux/of_net.h>
 #include <asm/tsi108.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 68a9cbbab450..0f3ab06d2222 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -41,6 +41,7 @@
 #include <asm/spu_priv1.h>
 #include <asm/setjmp.h>
 #include <asm/reg.h>
+#include <asm/debug.h>
 
 #ifdef CONFIG_PPC64
 #include <asm/hvcall.h>
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 6d99a5fcc090..2b7c0fbe578e 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -64,6 +64,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 config S390
 	def_bool y
 	select USE_GENERIC_SMP_HELPERS if SMP
+	select GENERIC_CPU_DEVICES if !SMP
 	select HAVE_SYSCALL_WRAPPERS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
@@ -218,6 +219,7 @@ config COMPAT
 	prompt "Kernel support for 31 bit emulation"
 	depends on 64BIT
 	select COMPAT_BINFMT_ELF
+	select ARCH_WANT_OLD_COMPAT_IPC
 	help
 	  Select this option if you want to enable your system kernel to
 	  handle system-calls from ELF binaries for 31 bit ESA.  This option
diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h
index ffd1ac255f19..9178db6db0a5 100644
--- a/arch/s390/crypto/crypt_s390.h
+++ b/arch/s390/crypto/crypt_s390.h
@@ -17,6 +17,7 @@
 #define _CRYPTO_ARCH_S390_CRYPT_S390_H
 
 #include <asm/errno.h>
+#include <asm/facility.h>
 
 #define CRYPT_S390_OP_MASK 0xFF00
 #define CRYPT_S390_FUNC_MASK 0x00FF
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 8517d2ae3b5c..748347baecb8 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,7 +15,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)  { (i) }
 
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
new file mode 100644
index 000000000000..451273ad4d34
--- /dev/null
+++ b/arch/s390/include/asm/barrier.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * This is very similar to the ppc eieio/sync instruction in that is
+ * does a checkpoint syncronisation & makes sure that 
+ * all memory ops have completed wrt other CPU's ( see 7-15 POP  DJB ).
+ */
+
+#define eieio()	asm volatile("bcr 15,0" : : : "memory")
+#define SYNC_OTHER_CORES(x)   eieio()
+#define mb()    eieio()
+#define rmb()   eieio()
+#define wmb()   eieio()
+#define read_barrier_depends() do { } while(0)
+#define smp_mb()       mb()
+#define smp_rmb()      rmb()
+#define smp_wmb()      wmb()
+#define smp_read_barrier_depends()    read_barrier_depends()
+#define smp_mb__before_clear_bit()     smp_mb()
+#define smp_mb__after_clear_bit()      smp_mb()
+
+#define set_mb(var, value)      do { var = value; mb(); } while (0)
+
+#endif /* __ASM_BARRIER_H */
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
new file mode 100644
index 000000000000..a3afecdae145
--- /dev/null
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -0,0 +1,97 @@
+/*
+ * CPU-measurement facilities
+ *
+ *  Copyright IBM Corp. 2012
+ *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *	       Jan Glauber <jang@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#ifndef _ASM_S390_CPU_MF_H
+#define _ASM_S390_CPU_MF_H
+
+#include <asm/facility.h>
+
+#define CPU_MF_INT_SF_IAE	(1 << 31)	/* invalid entry address */
+#define CPU_MF_INT_SF_ISE	(1 << 30)	/* incorrect SDBT entry */
+#define CPU_MF_INT_SF_PRA	(1 << 29)	/* program request alert */
+#define CPU_MF_INT_SF_SACA	(1 << 23)	/* sampler auth. change alert */
+#define CPU_MF_INT_SF_LSDA	(1 << 22)	/* loss of sample data alert */
+#define CPU_MF_INT_CF_CACA	(1 <<  7)	/* counter auth. change alert */
+#define CPU_MF_INT_CF_LCDA	(1 <<  6)	/* loss of counter data alert */
+
+#define CPU_MF_INT_CF_MASK	(CPU_MF_INT_CF_CACA|CPU_MF_INT_CF_LCDA)
+#define CPU_MF_INT_SF_MASK	(CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE|	\
+				 CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA|	\
+				 CPU_MF_INT_SF_LSDA)
+
+/* CPU measurement facility support */
+static inline int cpum_cf_avail(void)
+{
+	return MACHINE_HAS_SPP && test_facility(67);
+}
+
+static inline int cpum_sf_avail(void)
+{
+	return MACHINE_HAS_SPP && test_facility(68);
+}
+
+
+struct cpumf_ctr_info {
+	u16   cfvn;
+	u16   auth_ctl;
+	u16   enable_ctl;
+	u16   act_ctl;
+	u16   max_cpu;
+	u16   csvn;
+	u16   max_cg;
+	u16   reserved1;
+	u32   reserved2[12];
+} __packed;
+
+/* Query counter information */
+static inline int qctri(struct cpumf_ctr_info *info)
+{
+	int rc = -EINVAL;
+
+	asm volatile (
+		"0:	.insn	s,0xb28e0000,%1\n"
+		"1:	lhi	%0,0\n"
+		"2:\n"
+		EX_TABLE(1b, 2b)
+		: "+d" (rc), "=Q" (*info));
+	return rc;
+}
+
+/* Load CPU-counter-set controls */
+static inline int lcctl(u64 ctl)
+{
+	int cc;
+
+	asm volatile (
+		"	.insn	s,0xb2840000,%1\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (cc) : "m" (ctl) : "cc");
+	return cc;
+}
+
+/* Extract CPU counter */
+static inline int ecctr(u64 ctr, u64 *val)
+{
+	register u64 content asm("4") = 0;
+	int cc;
+
+	asm volatile (
+		"	.insn	rre,0xb2e40000,%0,%2\n"
+		"	ipm	%1\n"
+		"	srl	%1,28\n"
+		: "=d" (content), "=d" (cc) : "d" (ctr) : "cc");
+	if (!cc)
+		*val = content;
+	return cc;
+}
+
+#endif /* _ASM_S390_CPU_MF_H */
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
new file mode 100644
index 000000000000..ecde9417d669
--- /dev/null
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_CTL_REG_H
+#define __ASM_CTL_REG_H
+
+#ifdef __s390x__
+
+#define __ctl_load(array, low, high) ({				\
+	typedef struct { char _[sizeof(array)]; } addrtype;	\
+	asm volatile(						\
+		"	lctlg	%1,%2,%0\n"			\
+		: : "Q" (*(addrtype *)(&array)),		\
+		    "i" (low), "i" (high));			\
+	})
+
+#define __ctl_store(array, low, high) ({			\
+	typedef struct { char _[sizeof(array)]; } addrtype;	\
+	asm volatile(						\
+		"	stctg	%1,%2,%0\n"			\
+		: "=Q" (*(addrtype *)(&array))			\
+		: "i" (low), "i" (high));			\
+	})
+
+#else /* __s390x__ */
+
+#define __ctl_load(array, low, high) ({				\
+	typedef struct { char _[sizeof(array)]; } addrtype;	\
+	asm volatile(						\
+		"	lctl	%1,%2,%0\n"			\
+		: : "Q" (*(addrtype *)(&array)),		\
+		    "i" (low), "i" (high));			\
+})
+
+#define __ctl_store(array, low, high) ({			\
+	typedef struct { char _[sizeof(array)]; } addrtype;	\
+	asm volatile(						\
+		"	stctl	%1,%2,%0\n"			\
+		: "=Q" (*(addrtype *)(&array))			\
+		: "i" (low), "i" (high));			\
+	})
+
+#endif /* __s390x__ */
+
+#define __ctl_set_bit(cr, bit) ({	\
+	unsigned long __dummy;		\
+	__ctl_store(__dummy, cr, cr);	\
+	__dummy |= 1UL << (bit);	\
+	__ctl_load(__dummy, cr, cr);	\
+})
+
+#define __ctl_clear_bit(cr, bit) ({	\
+	unsigned long __dummy;		\
+	__ctl_store(__dummy, cr, cr);	\
+	__dummy &= ~(1UL << (bit));	\
+	__ctl_load(__dummy, cr, cr);	\
+})
+
+#ifdef CONFIG_SMP
+
+extern void smp_ctl_set_bit(int cr, int bit);
+extern void smp_ctl_clear_bit(int cr, int bit);
+#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
+#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
+
+#else
+
+#define ctl_set_bit(cr, bit) __ctl_set_bit(cr, bit)
+#define ctl_clear_bit(cr, bit) __ctl_clear_bit(cr, bit)
+
+#endif /* CONFIG_SMP */
+
+#endif /* __ASM_CTL_REG_H */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 547f1a6a35d4..c4ee39f7a4d6 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -129,7 +129,6 @@ typedef s390_fp_regs compat_elf_fpregset_t;
 typedef s390_compat_regs compat_elf_gregset_t;
 
 #include <linux/sched.h>	/* for task_struct */
-#include <asm/system.h>		/* for save_access_regs */
 #include <asm/mmu_context.h>
 
 #include <asm/vdso.h>
diff --git a/arch/s390/include/asm/exec.h b/arch/s390/include/asm/exec.h
new file mode 100644
index 000000000000..c4a93d6327fa
--- /dev/null
+++ b/arch/s390/include/asm/exec.h
@@ -0,0 +1,12 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_EXEC_H
+#define __ASM_EXEC_H
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif /* __ASM_EXEC_H */
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
new file mode 100644
index 000000000000..1e5b27edc0c9
--- /dev/null
+++ b/arch/s390/include/asm/facility.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_FACILITY_H
+#define __ASM_FACILITY_H
+
+#include <linux/string.h>
+#include <linux/preempt.h>
+#include <asm/lowcore.h>
+
+#define MAX_FACILITY_BIT (256*8)	/* stfle_fac_list has 256 bytes */
+
+/*
+ * The test_facility function uses the bit odering where the MSB is bit 0.
+ * That makes it easier to query facility bits with the bit number as
+ * documented in the Principles of Operation.
+ */
+static inline int test_facility(unsigned long nr)
+{
+	unsigned char *ptr;
+
+	if (nr >= MAX_FACILITY_BIT)
+		return 0;
+	ptr = (unsigned char *) &S390_lowcore.stfle_fac_list + (nr >> 3);
+	return (*ptr & (0x80 >> (nr & 7))) != 0;
+}
+
+/**
+ * stfle - Store facility list extended
+ * @stfle_fac_list: array where facility list can be stored
+ * @size: size of passed in array in double words
+ */
+static inline void stfle(u64 *stfle_fac_list, int size)
+{
+	unsigned long nr;
+
+	preempt_disable();
+	S390_lowcore.stfl_fac_list = 0;
+	asm volatile(
+		"	.insn s,0xb2b10000,0(0)\n" /* stfl */
+		"0:\n"
+		EX_TABLE(0b, 0b)
+		: "=m" (S390_lowcore.stfl_fac_list));
+	nr = 4; /* bytes stored by stfl */
+	memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
+	if (S390_lowcore.stfl_fac_list & 0x01000000) {
+		/* More facility bits available with stfle */
+		register unsigned long reg0 asm("0") = size - 1;
+
+		asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
+			     : "+d" (reg0)
+			     : "a" (stfle_fac_list)
+			     : "memory", "cc");
+		nr = (reg0 + 1) * 8; /* # bytes stored by stfle */
+	}
+	memset((char *) stfle_fac_list + nr, 0, size * 8 - nr);
+	preempt_enable();
+}
+
+#endif /* __ASM_FACILITY_H */
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index acee1806f61e..5289cacd4861 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -45,5 +45,7 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler);
 int unregister_external_interrupt(u16 code, ext_int_handler_t handler);
 void service_subclass_irq_register(void);
 void service_subclass_irq_unregister(void);
+void measurement_alert_subclass_register(void);
+void measurement_alert_subclass_unregister(void);
 
 #endif /* _ASM_IRQ_H */
diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index 82b32a100c7d..96076676e224 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -41,4 +41,15 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+#define KVM_SYNC_PREFIX (1UL << 0)
+#define KVM_SYNC_GPRS   (1UL << 1)
+#define KVM_SYNC_ACRS   (1UL << 2)
+#define KVM_SYNC_CRS    (1UL << 3)
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+	__u64 prefix;	/* prefix register */
+	__u64 gprs[16];	/* general purpose registers */
+	__u32 acrs[16];	/* access registers */
+	__u64 crs[16];	/* control registers */
+};
 #endif
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index b0c235cb6ad5..7343872890a2 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -220,18 +220,17 @@ struct kvm_s390_float_interrupt {
 	struct list_head list;
 	atomic_t active;
 	int next_rr_cpu;
-	unsigned long idle_mask [(64 + sizeof(long) - 1) / sizeof(long)];
-	struct kvm_s390_local_interrupt *local_int[64];
+	unsigned long idle_mask[(KVM_MAX_VCPUS + sizeof(long) - 1)
+				/ sizeof(long)];
+	struct kvm_s390_local_interrupt *local_int[KVM_MAX_VCPUS];
 };
 
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
-	unsigned long	  guest_gprs[16];
 	s390_fp_regs      host_fpregs;
 	unsigned int      host_acrs[NUM_ACRS];
 	s390_fp_regs      guest_fpregs;
-	unsigned int      guest_acrs[NUM_ACRS];
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct tasklet_struct tasklet;
@@ -246,6 +245,9 @@ struct kvm_vm_stat {
 	u32 remote_tlb_flush;
 };
 
+struct kvm_arch_memory_slot {
+};
+
 struct kvm_arch{
 	struct sca_block *sca;
 	debug_info_t *dbf;
@@ -253,5 +255,5 @@ struct kvm_arch{
 	struct gmap *gmap;
 };
 
-extern int sie64a(struct kvm_s390_sie_block *, unsigned long *);
+extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 #endif
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 4506791adcd5..6340178748bf 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -1,6 +1,8 @@
 #ifndef __MMU_H
 #define __MMU_H
 
+#include <linux/errno.h>
+
 typedef struct {
 	atomic_t attach_count;
 	unsigned int flush_mm;
@@ -21,4 +23,18 @@ typedef struct {
 	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),    \
 	.context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list),
 
+static inline int tprot(unsigned long addr)
+{
+	int rc = -EFAULT;
+
+	asm volatile(
+		"	tprot	0(%1),0\n"
+		"0:	ipm	%0\n"
+		"	srl	%0,28\n"
+		"1:\n"
+		EX_TABLE(0b,1b)
+		: "+d" (rc) : "a" (addr) : "cc");
+	return rc;
+}
+
 #endif
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 5682f160ff82..5d09e405c54d 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -12,6 +12,7 @@
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
+#include <asm/ctl_reg.h>
 #include <asm-generic/mm_hooks.h>
 
 static inline int init_new_context(struct task_struct *tsk,
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 4eb444edbe49..7941968e12b4 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -1,8 +1,16 @@
 /*
  * Performance event support - s390 specific definitions.
  *
- * Copyright 2009 Martin Schwidefsky, IBM Corporation.
+ * Copyright IBM Corp. 2009, 2012
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *	      Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 
-/* Empty, just to avoid compiling error */
+#include <asm/cpu_mf.h>
 
+/* CPU-measurement counter facility */
+#define PERF_CPUM_CF_MAX_CTR		160
+
+/* Per-CPU flags for PMU states */
+#define PMU_F_RESERVED			0x1000
+#define PMU_F_ENABLED			0x2000
diff --git a/arch/s390/include/asm/posix_types.h b/arch/s390/include/asm/posix_types.h
index 8cc113f92523..edf8527ff08d 100644
--- a/arch/s390/include/asm/posix_types.h
+++ b/arch/s390/include/asm/posix_types.h
@@ -3,7 +3,6 @@
  *
  *  S390 version
  *
- *  Derived from "include/asm-i386/posix_types.h"
  */
 
 #ifndef __ARCH_S390_POSIX_TYPES_H
@@ -15,22 +14,11 @@
  * assume GCC is being used.
  */
 
-typedef long            __kernel_off_t;
-typedef int             __kernel_pid_t;
 typedef unsigned long   __kernel_size_t;
-typedef long            __kernel_time_t;
-typedef long            __kernel_suseconds_t;
-typedef long            __kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int             __kernel_daddr_t;
-typedef char *          __kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
+#define __kernel_size_t __kernel_size_t
 
-#ifdef __GNUC__
-typedef long long       __kernel_loff_t;
-#endif
+typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
 #ifndef __s390x__
 
@@ -42,11 +30,6 @@ typedef unsigned short  __kernel_uid_t;
 typedef unsigned short  __kernel_gid_t;
 typedef int             __kernel_ssize_t;
 typedef int             __kernel_ptrdiff_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
-typedef unsigned short	__kernel_old_dev_t;
 
 #else /* __s390x__ */
 
@@ -59,49 +42,16 @@ typedef unsigned int    __kernel_gid_t;
 typedef long            __kernel_ssize_t;
 typedef long            __kernel_ptrdiff_t;
 typedef unsigned long   __kernel_sigset_t;      /* at least 32 bits */
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
-typedef unsigned short __kernel_old_dev_t;
 
 #endif /* __s390x__ */
 
-typedef struct {
-        int     val[2];
-} __kernel_fsid_t;
-
-
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, const __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (fdsetp->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-#undef  __FD_ZERO
-#define __FD_ZERO(fdsetp) \
-	((void) memset ((void *) (fdsetp), 0, sizeof (__kernel_fd_set)))
+#define __kernel_ino_t  __kernel_ino_t
+#define __kernel_mode_t __kernel_mode_t
+#define __kernel_nlink_t __kernel_nlink_t
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+#define __kernel_uid_t __kernel_uid_t
+#define __kernel_gid_t __kernel_gid_t
 
-#endif     /* __KERNEL__ */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index d25843a6a915..d499b30ea487 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -14,6 +14,7 @@
 #define __ASM_S390_PROCESSOR_H
 
 #include <linux/linkage.h>
+#include <linux/irqflags.h>
 #include <asm/cpu.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -156,6 +157,14 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_EIP(tsk)	(task_pt_regs(tsk)->psw.addr)
 #define KSTK_ESP(tsk)	(task_pt_regs(tsk)->gprs[15])
 
+static inline unsigned short stap(void)
+{
+	unsigned short cpu_address;
+
+	asm volatile("stap %0" : "=m" (cpu_address));
+	return cpu_address;
+}
+
 /*
  * Give up the time slice of the virtual PU.
  */
@@ -304,6 +313,21 @@ static inline void __noreturn disabled_wait(unsigned long code)
 }
 
 /*
+ * Use to set psw mask except for the first byte which
+ * won't be changed by this function.
+ */
+static inline void
+__set_psw_mask(unsigned long mask)
+{
+	__load_psw_mask(mask | (arch_local_save_flags() & ~(-1UL >> 8)));
+}
+
+#define local_mcck_enable() \
+	__set_psw_mask(psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK)
+#define local_mcck_disable() \
+	__set_psw_mask(psw_kernel_bits | PSW_MASK_DAT)
+
+/*
  * Basic Machine Check/Program Check Handler.
  */
 
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 097183c70407..b21e46e5d4b8 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -140,6 +140,20 @@ extern char vmpoff_cmd[];
 #define NSS_NAME_SIZE	8
 extern char kernel_nss_name[];
 
+#ifdef CONFIG_PFAULT
+extern int pfault_init(void);
+extern void pfault_fini(void);
+#else /* CONFIG_PFAULT */
+#define pfault_init()		({-1;})
+#define pfault_fini()		do { } while (0)
+#endif /* CONFIG_PFAULT */
+
+extern void cmma_init(void);
+
+extern void (*_machine_restart)(char *command);
+extern void (*_machine_halt)(void);
+extern void (*_machine_power_off)(void);
+
 #else /* __ASSEMBLY__ */
 
 #ifndef __s390x__
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 797f78729680..c77c6de6f6c0 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -9,7 +9,7 @@
 
 #ifdef CONFIG_SMP
 
-#include <asm/system.h>
+#include <asm/lowcore.h>
 
 #define raw_smp_processor_id()	(S390_lowcore.cpu_nr)
 
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
new file mode 100644
index 000000000000..f223068b7822
--- /dev/null
+++ b/arch/s390/include/asm/switch_to.h
@@ -0,0 +1,100 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_SWITCH_TO_H
+#define __ASM_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+
+extern struct task_struct *__switch_to(void *, void *);
+extern void update_per_regs(struct task_struct *task);
+
+static inline void save_fp_regs(s390_fp_regs *fpregs)
+{
+	asm volatile(
+		"	std	0,%O0+8(%R0)\n"
+		"	std	2,%O0+24(%R0)\n"
+		"	std	4,%O0+40(%R0)\n"
+		"	std	6,%O0+56(%R0)"
+		: "=Q" (*fpregs) : "Q" (*fpregs));
+	if (!MACHINE_HAS_IEEE)
+		return;
+	asm volatile(
+		"	stfpc	%0\n"
+		"	std	1,%O0+16(%R0)\n"
+		"	std	3,%O0+32(%R0)\n"
+		"	std	5,%O0+48(%R0)\n"
+		"	std	7,%O0+64(%R0)\n"
+		"	std	8,%O0+72(%R0)\n"
+		"	std	9,%O0+80(%R0)\n"
+		"	std	10,%O0+88(%R0)\n"
+		"	std	11,%O0+96(%R0)\n"
+		"	std	12,%O0+104(%R0)\n"
+		"	std	13,%O0+112(%R0)\n"
+		"	std	14,%O0+120(%R0)\n"
+		"	std	15,%O0+128(%R0)\n"
+		: "=Q" (*fpregs) : "Q" (*fpregs));
+}
+
+static inline void restore_fp_regs(s390_fp_regs *fpregs)
+{
+	asm volatile(
+		"	ld	0,%O0+8(%R0)\n"
+		"	ld	2,%O0+24(%R0)\n"
+		"	ld	4,%O0+40(%R0)\n"
+		"	ld	6,%O0+56(%R0)"
+		: : "Q" (*fpregs));
+	if (!MACHINE_HAS_IEEE)
+		return;
+	asm volatile(
+		"	lfpc	%0\n"
+		"	ld	1,%O0+16(%R0)\n"
+		"	ld	3,%O0+32(%R0)\n"
+		"	ld	5,%O0+48(%R0)\n"
+		"	ld	7,%O0+64(%R0)\n"
+		"	ld	8,%O0+72(%R0)\n"
+		"	ld	9,%O0+80(%R0)\n"
+		"	ld	10,%O0+88(%R0)\n"
+		"	ld	11,%O0+96(%R0)\n"
+		"	ld	12,%O0+104(%R0)\n"
+		"	ld	13,%O0+112(%R0)\n"
+		"	ld	14,%O0+120(%R0)\n"
+		"	ld	15,%O0+128(%R0)\n"
+		: : "Q" (*fpregs));
+}
+
+static inline void save_access_regs(unsigned int *acrs)
+{
+	asm volatile("stam 0,15,%0" : "=Q" (*acrs));
+}
+
+static inline void restore_access_regs(unsigned int *acrs)
+{
+	asm volatile("lam 0,15,%0" : : "Q" (*acrs));
+}
+
+#define switch_to(prev,next,last) do {					\
+	if (prev->mm) {							\
+		save_fp_regs(&prev->thread.fp_regs);			\
+		save_access_regs(&prev->thread.acrs[0]);		\
+	}								\
+	if (next->mm) {							\
+		restore_fp_regs(&next->thread.fp_regs);			\
+		restore_access_regs(&next->thread.acrs[0]);		\
+		update_per_regs(next);					\
+	}								\
+	prev = __switch_to(prev,next);					\
+} while (0)
+
+extern void account_vtime(struct task_struct *, struct task_struct *);
+extern void account_tick_vtime(struct task_struct *);
+
+#define finish_arch_switch(prev) do {					     \
+	set_fs(current->thread.mm_segment);				     \
+	account_vtime(prev, current);					     \
+} while (0)
+
+#endif /* __ASM_SWITCH_TO_H */
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
deleted file mode 100644
index 2e0bb7f0f9b2..000000000000
--- a/arch/s390/include/asm/system.h
+++ /dev/null
@@ -1,315 +0,0 @@
-/*
- * Copyright IBM Corp. 1999, 2009
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-
-#ifndef __ASM_SYSTEM_H
-#define __ASM_SYSTEM_H
-
-#include <linux/preempt.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <asm/types.h>
-#include <asm/ptrace.h>
-#include <asm/setup.h>
-#include <asm/processor.h>
-#include <asm/lowcore.h>
-#include <asm/cmpxchg.h>
-
-#ifdef __KERNEL__
-
-struct task_struct;
-
-extern struct task_struct *__switch_to(void *, void *);
-extern void update_per_regs(struct task_struct *task);
-
-static inline void save_fp_regs(s390_fp_regs *fpregs)
-{
-	asm volatile(
-		"	std	0,%O0+8(%R0)\n"
-		"	std	2,%O0+24(%R0)\n"
-		"	std	4,%O0+40(%R0)\n"
-		"	std	6,%O0+56(%R0)"
-		: "=Q" (*fpregs) : "Q" (*fpregs));
-	if (!MACHINE_HAS_IEEE)
-		return;
-	asm volatile(
-		"	stfpc	%0\n"
-		"	std	1,%O0+16(%R0)\n"
-		"	std	3,%O0+32(%R0)\n"
-		"	std	5,%O0+48(%R0)\n"
-		"	std	7,%O0+64(%R0)\n"
-		"	std	8,%O0+72(%R0)\n"
-		"	std	9,%O0+80(%R0)\n"
-		"	std	10,%O0+88(%R0)\n"
-		"	std	11,%O0+96(%R0)\n"
-		"	std	12,%O0+104(%R0)\n"
-		"	std	13,%O0+112(%R0)\n"
-		"	std	14,%O0+120(%R0)\n"
-		"	std	15,%O0+128(%R0)\n"
-		: "=Q" (*fpregs) : "Q" (*fpregs));
-}
-
-static inline void restore_fp_regs(s390_fp_regs *fpregs)
-{
-	asm volatile(
-		"	ld	0,%O0+8(%R0)\n"
-		"	ld	2,%O0+24(%R0)\n"
-		"	ld	4,%O0+40(%R0)\n"
-		"	ld	6,%O0+56(%R0)"
-		: : "Q" (*fpregs));
-	if (!MACHINE_HAS_IEEE)
-		return;
-	asm volatile(
-		"	lfpc	%0\n"
-		"	ld	1,%O0+16(%R0)\n"
-		"	ld	3,%O0+32(%R0)\n"
-		"	ld	5,%O0+48(%R0)\n"
-		"	ld	7,%O0+64(%R0)\n"
-		"	ld	8,%O0+72(%R0)\n"
-		"	ld	9,%O0+80(%R0)\n"
-		"	ld	10,%O0+88(%R0)\n"
-		"	ld	11,%O0+96(%R0)\n"
-		"	ld	12,%O0+104(%R0)\n"
-		"	ld	13,%O0+112(%R0)\n"
-		"	ld	14,%O0+120(%R0)\n"
-		"	ld	15,%O0+128(%R0)\n"
-		: : "Q" (*fpregs));
-}
-
-static inline void save_access_regs(unsigned int *acrs)
-{
-	asm volatile("stam 0,15,%0" : "=Q" (*acrs));
-}
-
-static inline void restore_access_regs(unsigned int *acrs)
-{
-	asm volatile("lam 0,15,%0" : : "Q" (*acrs));
-}
-
-#define switch_to(prev,next,last) do {					\
-	if (prev->mm) {							\
-		save_fp_regs(&prev->thread.fp_regs);			\
-		save_access_regs(&prev->thread.acrs[0]);		\
-	}								\
-	if (next->mm) {							\
-		restore_fp_regs(&next->thread.fp_regs);			\
-		restore_access_regs(&next->thread.acrs[0]);		\
-		update_per_regs(next);					\
-	}								\
-	prev = __switch_to(prev,next);					\
-} while (0)
-
-extern void account_vtime(struct task_struct *, struct task_struct *);
-extern void account_tick_vtime(struct task_struct *);
-
-#ifdef CONFIG_PFAULT
-extern int pfault_init(void);
-extern void pfault_fini(void);
-#else /* CONFIG_PFAULT */
-#define pfault_init()		({-1;})
-#define pfault_fini()		do { } while (0)
-#endif /* CONFIG_PFAULT */
-
-extern void cmma_init(void);
-extern int memcpy_real(void *, void *, size_t);
-extern void copy_to_absolute_zero(void *dest, void *src, size_t count);
-extern int copy_to_user_real(void __user *dest, void *src, size_t count);
-extern int copy_from_user_real(void *dest, void __user *src, size_t count);
-
-#define finish_arch_switch(prev) do {					     \
-	set_fs(current->thread.mm_segment);				     \
-	account_vtime(prev, current);					     \
-} while (0)
-
-#define nop() asm volatile("nop")
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- *
- * This is very similar to the ppc eieio/sync instruction in that is
- * does a checkpoint syncronisation & makes sure that 
- * all memory ops have completed wrt other CPU's ( see 7-15 POP  DJB ).
- */
-
-#define eieio()	asm volatile("bcr 15,0" : : : "memory")
-#define SYNC_OTHER_CORES(x)   eieio()
-#define mb()    eieio()
-#define rmb()   eieio()
-#define wmb()   eieio()
-#define read_barrier_depends() do { } while(0)
-#define smp_mb()       mb()
-#define smp_rmb()      rmb()
-#define smp_wmb()      wmb()
-#define smp_read_barrier_depends()    read_barrier_depends()
-#define smp_mb__before_clear_bit()     smp_mb()
-#define smp_mb__after_clear_bit()      smp_mb()
-
-
-#define set_mb(var, value)      do { var = value; mb(); } while (0)
-
-#ifdef __s390x__
-
-#define __ctl_load(array, low, high) ({				\
-	typedef struct { char _[sizeof(array)]; } addrtype;	\
-	asm volatile(						\
-		"	lctlg	%1,%2,%0\n"			\
-		: : "Q" (*(addrtype *)(&array)),		\
-		    "i" (low), "i" (high));			\
-	})
-
-#define __ctl_store(array, low, high) ({			\
-	typedef struct { char _[sizeof(array)]; } addrtype;	\
-	asm volatile(						\
-		"	stctg	%1,%2,%0\n"			\
-		: "=Q" (*(addrtype *)(&array))			\
-		: "i" (low), "i" (high));			\
-	})
-
-#else /* __s390x__ */
-
-#define __ctl_load(array, low, high) ({				\
-	typedef struct { char _[sizeof(array)]; } addrtype;	\
-	asm volatile(						\
-		"	lctl	%1,%2,%0\n"			\
-		: : "Q" (*(addrtype *)(&array)),		\
-		    "i" (low), "i" (high));			\
-})
-
-#define __ctl_store(array, low, high) ({			\
-	typedef struct { char _[sizeof(array)]; } addrtype;	\
-	asm volatile(						\
-		"	stctl	%1,%2,%0\n"			\
-		: "=Q" (*(addrtype *)(&array))			\
-		: "i" (low), "i" (high));			\
-	})
-
-#endif /* __s390x__ */
-
-#define __ctl_set_bit(cr, bit) ({	\
-	unsigned long __dummy;		\
-	__ctl_store(__dummy, cr, cr);	\
-	__dummy |= 1UL << (bit);	\
-	__ctl_load(__dummy, cr, cr);	\
-})
-
-#define __ctl_clear_bit(cr, bit) ({	\
-	unsigned long __dummy;		\
-	__ctl_store(__dummy, cr, cr);	\
-	__dummy &= ~(1UL << (bit));	\
-	__ctl_load(__dummy, cr, cr);	\
-})
-
-/*
- * Use to set psw mask except for the first byte which
- * won't be changed by this function.
- */
-static inline void
-__set_psw_mask(unsigned long mask)
-{
-	__load_psw_mask(mask | (arch_local_save_flags() & ~(-1UL >> 8)));
-}
-
-#define local_mcck_enable() \
-	__set_psw_mask(psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK)
-#define local_mcck_disable() \
-	__set_psw_mask(psw_kernel_bits | PSW_MASK_DAT)
-
-#ifdef CONFIG_SMP
-
-extern void smp_ctl_set_bit(int cr, int bit);
-extern void smp_ctl_clear_bit(int cr, int bit);
-#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
-#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
-
-#else
-
-#define ctl_set_bit(cr, bit) __ctl_set_bit(cr, bit)
-#define ctl_clear_bit(cr, bit) __ctl_clear_bit(cr, bit)
-
-#endif /* CONFIG_SMP */
-
-#define MAX_FACILITY_BIT (256*8)	/* stfle_fac_list has 256 bytes */
-
-/*
- * The test_facility function uses the bit odering where the MSB is bit 0.
- * That makes it easier to query facility bits with the bit number as
- * documented in the Principles of Operation.
- */
-static inline int test_facility(unsigned long nr)
-{
-	unsigned char *ptr;
-
-	if (nr >= MAX_FACILITY_BIT)
-		return 0;
-	ptr = (unsigned char *) &S390_lowcore.stfle_fac_list + (nr >> 3);
-	return (*ptr & (0x80 >> (nr & 7))) != 0;
-}
-
-/**
- * stfle - Store facility list extended
- * @stfle_fac_list: array where facility list can be stored
- * @size: size of passed in array in double words
- */
-static inline void stfle(u64 *stfle_fac_list, int size)
-{
-	unsigned long nr;
-
-	preempt_disable();
-	S390_lowcore.stfl_fac_list = 0;
-	asm volatile(
-		"	.insn s,0xb2b10000,0(0)\n" /* stfl */
-		"0:\n"
-		EX_TABLE(0b, 0b)
-		: "=m" (S390_lowcore.stfl_fac_list));
-	nr = 4; /* bytes stored by stfl */
-	memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
-	if (S390_lowcore.stfl_fac_list & 0x01000000) {
-		/* More facility bits available with stfle */
-		register unsigned long reg0 asm("0") = size - 1;
-
-		asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
-			     : "+d" (reg0)
-			     : "a" (stfle_fac_list)
-			     : "memory", "cc");
-		nr = (reg0 + 1) * 8; /* # bytes stored by stfle */
-	}
-	memset((char *) stfle_fac_list + nr, 0, size * 8 - nr);
-	preempt_enable();
-}
-
-static inline unsigned short stap(void)
-{
-	unsigned short cpu_address;
-
-	asm volatile("stap %0" : "=m" (cpu_address));
-	return cpu_address;
-}
-
-extern void (*_machine_restart)(char *command);
-extern void (*_machine_halt)(void);
-extern void (*_machine_power_off)(void);
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-static inline int tprot(unsigned long addr)
-{
-	int rc = -EFAULT;
-
-	asm volatile(
-		"	tprot	0(%1),0\n"
-		"0:	ipm	%0\n"
-		"	srl	%0,28\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (rc) : "a" (addr) : "cc");
-	return rc;
-}
-
-#endif /* __KERNEL__ */
-
-#endif
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 2b23885e81e9..8f2cada4f7c9 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -16,6 +16,7 @@
  */
 #include <linux/sched.h>
 #include <linux/errno.h>
+#include <asm/ctl_reg.h>
 
 #define VERIFY_READ     0
 #define VERIFY_WRITE    1
@@ -375,4 +376,9 @@ clear_user(void __user *to, unsigned long n)
 	return n;
 }
 
+extern int memcpy_real(void *, void *, size_t);
+extern void copy_to_absolute_zero(void *dest, void *src, size_t count);
+extern int copy_to_user_real(void __user *dest, void *src, size_t count);
+extern int copy_from_user_real(void *dest, void __user *src, size_t count);
+
 #endif /* __S390_UACCESS_H */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 16b0b433f1f4..884b18afc864 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)  += ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o
 
 # Kexec part
 S390_KEXEC_OBJS := machine_kexec.o crash.o
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index ed8c913db79e..83e6edf5cf17 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -12,7 +12,6 @@
 #include <asm/timer.h>
 #include <asm/vdso.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 
 /*
  * Make sure that the compiler is new enough. We want a compiler that
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 53a82c8d50e9..28040fd5e8a2 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -27,6 +27,7 @@
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 #include <asm/lowcore.h>
+#include <asm/switch_to.h>
 #include "compat_linux.h"
 #include "compat_ptrace.h"
 #include "entry.h"
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index 3e8b8816f309..e3dd886e1b32 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -18,7 +18,6 @@
 #include <linux/string.h>
 #include <asm/ebcdic.h>
 #include <asm/cpcmd.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 static DEFINE_SPINLOCK(cpcmd_lock);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index e2f847599c8e..3221c6fca8bb 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -24,7 +24,6 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 578eb4e6d157..9475e682727f 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -29,7 +29,7 @@
 #include <asm/sysinfo.h>
 #include <asm/cpcmd.h>
 #include <asm/sclp.h>
-#include <asm/system.h>
+#include <asm/facility.h>
 #include "entry.h"
 
 /*
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 2429ecd68872..1c2cdd59ccd0 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -255,3 +255,26 @@ void service_subclass_irq_unregister(void)
 	spin_unlock(&sc_irq_lock);
 }
 EXPORT_SYMBOL(service_subclass_irq_unregister);
+
+static DEFINE_SPINLOCK(ma_subclass_lock);
+static int ma_subclass_refcount;
+
+void measurement_alert_subclass_register(void)
+{
+	spin_lock(&ma_subclass_lock);
+	if (!ma_subclass_refcount)
+		ctl_set_bit(0, 5);
+	ma_subclass_refcount++;
+	spin_unlock(&ma_subclass_lock);
+}
+EXPORT_SYMBOL(measurement_alert_subclass_register);
+
+void measurement_alert_subclass_unregister(void)
+{
+	spin_lock(&ma_subclass_lock);
+	ma_subclass_refcount--;
+	if (!ma_subclass_refcount)
+		ctl_clear_bit(0, 5);
+	spin_unlock(&ma_subclass_lock);
+}
+EXPORT_SYMBOL(measurement_alert_subclass_unregister);
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
index 8431b92ca3ae..87f080b17af1 100644
--- a/arch/s390/kernel/lgr.c
+++ b/arch/s390/kernel/lgr.c
@@ -8,9 +8,9 @@
 #include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
+#include <asm/facility.h>
 #include <asm/sysinfo.h>
 #include <asm/ebcdic.h>
-#include <asm/system.h>
 #include <asm/debug.h>
 #include <asm/ipl.h>
 
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 0f8cdf1268d0..bdad47d54478 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -19,7 +19,6 @@
 #include <asm/setup.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
-#include <asm/system.h>
 #include <asm/smp.h>
 #include <asm/reset.h>
 #include <asm/ipl.h>
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index bbe522672e06..e8d6c214d498 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <asm/checksum.h>
 #include <asm/lowcore.h>
-#include <asm/system.h>
 #include <asm/os_info.h>
 
 /*
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
new file mode 100644
index 000000000000..46405086479c
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -0,0 +1,690 @@
+/*
+ * Performance event support for s390x - CPU-measurement Counter Facility
+ *
+ *  Copyright IBM Corp. 2012
+ *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#define KMSG_COMPONENT	"cpum_cf"
+#define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <asm/ctl_reg.h>
+#include <asm/irq.h>
+#include <asm/cpu_mf.h>
+
+/* CPU-measurement counter facility supports these CPU counter sets:
+ * For CPU counter sets:
+ *    Basic counter set:	     0-31
+ *    Problem-state counter set:    32-63
+ *    Crypto-activity counter set:  64-127
+ *    Extented counter set:	   128-159
+ */
+enum cpumf_ctr_set {
+	/* CPU counter sets */
+	CPUMF_CTR_SET_BASIC   = 0,
+	CPUMF_CTR_SET_USER    = 1,
+	CPUMF_CTR_SET_CRYPTO  = 2,
+	CPUMF_CTR_SET_EXT     = 3,
+
+	/* Maximum number of counter sets */
+	CPUMF_CTR_SET_MAX,
+};
+
+#define CPUMF_LCCTL_ENABLE_SHIFT    16
+#define CPUMF_LCCTL_ACTCTL_SHIFT     0
+static const u64 cpumf_state_ctl[CPUMF_CTR_SET_MAX] = {
+	[CPUMF_CTR_SET_BASIC]	= 0x02,
+	[CPUMF_CTR_SET_USER]	= 0x04,
+	[CPUMF_CTR_SET_CRYPTO]	= 0x08,
+	[CPUMF_CTR_SET_EXT]	= 0x01,
+};
+
+static void ctr_set_enable(u64 *state, int ctr_set)
+{
+	*state |= cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT;
+}
+static void ctr_set_disable(u64 *state, int ctr_set)
+{
+	*state &= ~(cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT);
+}
+static void ctr_set_start(u64 *state, int ctr_set)
+{
+	*state |= cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT;
+}
+static void ctr_set_stop(u64 *state, int ctr_set)
+{
+	*state &= ~(cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT);
+}
+
+/* Local CPUMF event structure */
+struct cpu_hw_events {
+	struct cpumf_ctr_info	info;
+	atomic_t		ctr_set[CPUMF_CTR_SET_MAX];
+	u64			state, tx_state;
+	unsigned int		flags;
+};
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
+	.ctr_set = {
+		[CPUMF_CTR_SET_BASIC]  = ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_USER]   = ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_CRYPTO] = ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_EXT]    = ATOMIC_INIT(0),
+	},
+	.state = 0,
+	.flags = 0,
+};
+
+static int get_counter_set(u64 event)
+{
+	int set = -1;
+
+	if (event < 32)
+		set = CPUMF_CTR_SET_BASIC;
+	else if (event < 64)
+		set = CPUMF_CTR_SET_USER;
+	else if (event < 128)
+		set = CPUMF_CTR_SET_CRYPTO;
+	else if (event < 160)
+		set = CPUMF_CTR_SET_EXT;
+
+	return set;
+}
+
+static int validate_event(const struct hw_perf_event *hwc)
+{
+	switch (hwc->config_base) {
+	case CPUMF_CTR_SET_BASIC:
+	case CPUMF_CTR_SET_USER:
+	case CPUMF_CTR_SET_CRYPTO:
+	case CPUMF_CTR_SET_EXT:
+		/* check for reserved counters */
+		if ((hwc->config >=  6 && hwc->config <=  31) ||
+		    (hwc->config >= 38 && hwc->config <=  63) ||
+		    (hwc->config >= 80 && hwc->config <= 127))
+			return -EOPNOTSUPP;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int validate_ctr_version(const struct hw_perf_event *hwc)
+{
+	struct cpu_hw_events *cpuhw;
+	int err = 0;
+
+	cpuhw = &get_cpu_var(cpu_hw_events);
+
+	/* check required version for counter sets */
+	switch (hwc->config_base) {
+	case CPUMF_CTR_SET_BASIC:
+	case CPUMF_CTR_SET_USER:
+		if (cpuhw->info.cfvn < 1)
+			err = -EOPNOTSUPP;
+		break;
+	case CPUMF_CTR_SET_CRYPTO:
+	case CPUMF_CTR_SET_EXT:
+		if (cpuhw->info.csvn < 1)
+			err = -EOPNOTSUPP;
+		break;
+	}
+
+	put_cpu_var(cpu_hw_events);
+	return err;
+}
+
+static int validate_ctr_auth(const struct hw_perf_event *hwc)
+{
+	struct cpu_hw_events *cpuhw;
+	u64 ctrs_state;
+	int err = 0;
+
+	cpuhw = &get_cpu_var(cpu_hw_events);
+
+	/* check authorization for cpu counter sets */
+	ctrs_state = cpumf_state_ctl[hwc->config_base];
+	if (!(ctrs_state & cpuhw->info.auth_ctl))
+		err = -EPERM;
+
+	put_cpu_var(cpu_hw_events);
+	return err;
+}
+
+/*
+ * Change the CPUMF state to active.
+ * Enable and activate the CPU-counter sets according
+ * to the per-cpu control state.
+ */
+static void cpumf_pmu_enable(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	int err;
+
+	if (cpuhw->flags & PMU_F_ENABLED)
+		return;
+
+	err = lcctl(cpuhw->state);
+	if (err) {
+		pr_err("Enabling the performance measuring unit "
+		       "failed with rc=%lx\n", err);
+		return;
+	}
+
+	cpuhw->flags |= PMU_F_ENABLED;
+}
+
+/*
+ * Change the CPUMF state to inactive.
+ * Disable and enable (inactive) the CPU-counter sets according
+ * to the per-cpu control state.
+ */
+static void cpumf_pmu_disable(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	int err;
+	u64 inactive;
+
+	if (!(cpuhw->flags & PMU_F_ENABLED))
+		return;
+
+	inactive = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1);
+	err = lcctl(inactive);
+	if (err) {
+		pr_err("Disabling the performance measuring unit "
+		       "failed with rc=%lx\n", err);
+		return;
+	}
+
+	cpuhw->flags &= ~PMU_F_ENABLED;
+}
+
+
+/* Number of perf events counting hardware events */
+static atomic_t num_events = ATOMIC_INIT(0);
+/* Used to avoid races in calling reserve/release_cpumf_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+/* CPU-measurement alerts for the counter facility */
+static void cpumf_measurement_alert(struct ext_code ext_code,
+				    unsigned int alert, unsigned long unused)
+{
+	struct cpu_hw_events *cpuhw;
+
+	if (!(alert & CPU_MF_INT_CF_MASK))
+		return;
+
+	kstat_cpu(smp_processor_id()).irqs[EXTINT_CPM]++;
+	cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	/* Measurement alerts are shared and might happen when the PMU
+	 * is not reserved.  Ignore these alerts in this case. */
+	if (!(cpuhw->flags & PMU_F_RESERVED))
+		return;
+
+	/* counter authorization change alert */
+	if (alert & CPU_MF_INT_CF_CACA)
+		qctri(&cpuhw->info);
+
+	/* loss of counter data alert */
+	if (alert & CPU_MF_INT_CF_LCDA)
+		pr_err("CPU[%i] Counter data was lost\n", smp_processor_id());
+}
+
+#define PMC_INIT      0
+#define PMC_RELEASE   1
+static void setup_pmc_cpu(void *flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	switch (*((int *) flags)) {
+	case PMC_INIT:
+		memset(&cpuhw->info, 0, sizeof(cpuhw->info));
+		qctri(&cpuhw->info);
+		cpuhw->flags |= PMU_F_RESERVED;
+		break;
+
+	case PMC_RELEASE:
+		cpuhw->flags &= ~PMU_F_RESERVED;
+		break;
+	}
+
+	/* Disable CPU counter sets */
+	lcctl(0);
+}
+
+/* Initialize the CPU-measurement facility */
+static int reserve_pmc_hardware(void)
+{
+	int flags = PMC_INIT;
+
+	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	measurement_alert_subclass_register();
+
+	return 0;
+}
+
+/* Release the CPU-measurement facility */
+static void release_pmc_hardware(void)
+{
+	int flags = PMC_RELEASE;
+
+	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	measurement_alert_subclass_unregister();
+}
+
+/* Release the PMU if event is the last perf event */
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+	if (!atomic_add_unless(&num_events, -1, 1)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_dec_return(&num_events) == 0)
+			release_pmc_hardware();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
+/* CPUMF <-> perf event mappings for kernel+userspace (basic set) */
+static const int cpumf_generic_events_basic[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = 0,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = 1,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = -1,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = -1,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = -1,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = -1,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
+};
+/* CPUMF <-> perf event mappings for userspace (problem-state set) */
+static const int cpumf_generic_events_user[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = 32,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = 33,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = -1,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = -1,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = -1,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = -1,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
+};
+
+static int __hw_perf_event_init(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	struct hw_perf_event *hwc = &event->hw;
+	int err;
+	u64 ev;
+
+	switch (attr->type) {
+	case PERF_TYPE_RAW:
+		/* Raw events are used to access counters directly,
+		 * hence do not permit excludes */
+		if (attr->exclude_kernel || attr->exclude_user ||
+		    attr->exclude_hv)
+			return -EOPNOTSUPP;
+		ev = attr->config;
+		break;
+
+	case PERF_TYPE_HARDWARE:
+		ev = attr->config;
+		/* Count user space (problem-state) only */
+		if (!attr->exclude_user && attr->exclude_kernel) {
+			if (ev >= ARRAY_SIZE(cpumf_generic_events_user))
+				return -EOPNOTSUPP;
+			ev = cpumf_generic_events_user[ev];
+
+		/* No support for kernel space counters only */
+		} else if (!attr->exclude_kernel && attr->exclude_user) {
+			return -EOPNOTSUPP;
+
+		/* Count user and kernel space */
+		} else {
+			if (ev >= ARRAY_SIZE(cpumf_generic_events_basic))
+				return -EOPNOTSUPP;
+			ev = cpumf_generic_events_basic[ev];
+		}
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
+	if (ev == -1)
+		return -ENOENT;
+
+	if (ev >= PERF_CPUM_CF_MAX_CTR)
+		return -EINVAL;
+
+	/* The CPU measurement counter facility does not have any interrupts
+	 * to do sampling.  Sampling must be provided by external means,
+	 * for example, by timers.
+	 */
+	if (hwc->sample_period)
+		return -EINVAL;
+
+	/* Use the hardware perf event structure to store the counter number
+	 * in 'config' member and the counter set to which the counter belongs
+	 * in the 'config_base'.  The counter set (config_base) is then used
+	 * to enable/disable the counters.
+	 */
+	hwc->config = ev;
+	hwc->config_base = get_counter_set(ev);
+
+	/* Validate the counter that is assigned to this event.
+	 * Because the counter facility can use numerous counters at the
+	 * same time without constraints, it is not necessary to explicity
+	 * validate event groups (event->group_leader != event).
+	 */
+	err = validate_event(hwc);
+	if (err)
+		return err;
+
+	/* Initialize for using the CPU-measurement counter facility */
+	if (!atomic_inc_not_zero(&num_events)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&num_events) == 0 && reserve_pmc_hardware())
+			err = -EBUSY;
+		else
+			atomic_inc(&num_events);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+	event->destroy = hw_perf_event_destroy;
+
+	/* Finally, validate version and authorization of the counter set */
+	err = validate_ctr_auth(hwc);
+	if (!err)
+		err = validate_ctr_version(hwc);
+
+	return err;
+}
+
+static int cpumf_pmu_event_init(struct perf_event *event)
+{
+	int err;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+	case PERF_TYPE_RAW:
+		err = __hw_perf_event_init(event);
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	if (unlikely(err) && event->destroy)
+		event->destroy(event);
+
+	return err;
+}
+
+static int hw_perf_event_reset(struct perf_event *event)
+{
+	u64 prev, new;
+	int err;
+
+	do {
+		prev = local64_read(&event->hw.prev_count);
+		err = ecctr(event->hw.config, &new);
+		if (err) {
+			if (err != 3)
+				break;
+			/* The counter is not (yet) available. This
+			 * might happen if the counter set to which
+			 * this counter belongs is in the disabled
+			 * state.
+			 */
+			new = 0;
+		}
+	} while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev);
+
+	return err;
+}
+
+static int hw_perf_event_update(struct perf_event *event)
+{
+	u64 prev, new, delta;
+	int err;
+
+	do {
+		prev = local64_read(&event->hw.prev_count);
+		err = ecctr(event->hw.config, &new);
+		if (err)
+			goto out;
+	} while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev);
+
+	delta = (prev <= new) ? new - prev
+			      : (-1ULL - prev) + new + 1;	 /* overflow */
+	local64_add(delta, &event->count);
+out:
+	return err;
+}
+
+static void cpumf_pmu_read(struct perf_event *event)
+{
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
+	hw_perf_event_update(event);
+}
+
+static void cpumf_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	if (WARN_ON_ONCE(hwc->config == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
+
+	/* (Re-)enable and activate the counter set */
+	ctr_set_enable(&cpuhw->state, hwc->config_base);
+	ctr_set_start(&cpuhw->state, hwc->config_base);
+
+	/* The counter set to which this counter belongs can be already active.
+	 * Because all counters in a set are active, the event->hw.prev_count
+	 * needs to be synchronized.  At this point, the counter set can be in
+	 * the inactive or disabled state.
+	 */
+	hw_perf_event_reset(event);
+
+	/* increment refcount for this counter set */
+	atomic_inc(&cpuhw->ctr_set[hwc->config_base]);
+}
+
+static void cpumf_pmu_stop(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		/* Decrement reference count for this counter set and if this
+		 * is the last used counter in the set, clear activation
+		 * control and set the counter set state to inactive.
+		 */
+		if (!atomic_dec_return(&cpuhw->ctr_set[hwc->config_base]))
+			ctr_set_stop(&cpuhw->state, hwc->config_base);
+		event->hw.state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		hw_perf_event_update(event);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
+
+static int cpumf_pmu_add(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	/* Check authorization for the counter set to which this
+	 * counter belongs.
+	 * For group events transaction, the authorization check is
+	 * done in cpumf_pmu_commit_txn().
+	 */
+	if (!(cpuhw->flags & PERF_EVENT_TXN))
+		if (validate_ctr_auth(&event->hw))
+			return -EPERM;
+
+	ctr_set_enable(&cpuhw->state, event->hw.config_base);
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		cpumf_pmu_start(event, PERF_EF_RELOAD);
+
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static void cpumf_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	cpumf_pmu_stop(event, PERF_EF_UPDATE);
+
+	/* Check if any counter in the counter set is still used.  If not used,
+	 * change the counter set to the disabled state.  This also clears the
+	 * content of all counters in the set.
+	 *
+	 * When a new perf event has been added but not yet started, this can
+	 * clear enable control and resets all counters in a set.  Therefore,
+	 * cpumf_pmu_start() always has to reenable a counter set.
+	 */
+	if (!atomic_read(&cpuhw->ctr_set[event->hw.config_base]))
+		ctr_set_disable(&cpuhw->state, event->hw.config_base);
+
+	perf_event_update_userpage(event);
+}
+
+/*
+ * Start group events scheduling transaction.
+ * Set flags to perform a single test at commit time.
+ */
+static void cpumf_pmu_start_txn(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	perf_pmu_disable(pmu);
+	cpuhw->flags |= PERF_EVENT_TXN;
+	cpuhw->tx_state = cpuhw->state;
+}
+
+/*
+ * Stop and cancel a group events scheduling tranctions.
+ * Assumes cpumf_pmu_del() is called for each successful added
+ * cpumf_pmu_add() during the transaction.
+ */
+static void cpumf_pmu_cancel_txn(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	WARN_ON(cpuhw->tx_state != cpuhw->state);
+
+	cpuhw->flags &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
+}
+
+/*
+ * Commit the group events scheduling transaction.  On success, the
+ * transaction is closed.   On error, the transaction is kept open
+ * until cpumf_pmu_cancel_txn() is called.
+ */
+static int cpumf_pmu_commit_txn(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	u64 state;
+
+	/* check if the updated state can be scheduled */
+	state = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1);
+	state >>= CPUMF_LCCTL_ENABLE_SHIFT;
+	if ((state & cpuhw->info.auth_ctl) != state)
+		return -EPERM;
+
+	cpuhw->flags &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
+	return 0;
+}
+
+/* Performance monitoring unit for s390x */
+static struct pmu cpumf_pmu = {
+	.pmu_enable   = cpumf_pmu_enable,
+	.pmu_disable  = cpumf_pmu_disable,
+	.event_init   = cpumf_pmu_event_init,
+	.add	      = cpumf_pmu_add,
+	.del	      = cpumf_pmu_del,
+	.start	      = cpumf_pmu_start,
+	.stop	      = cpumf_pmu_stop,
+	.read	      = cpumf_pmu_read,
+	.start_txn    = cpumf_pmu_start_txn,
+	.commit_txn   = cpumf_pmu_commit_txn,
+	.cancel_txn   = cpumf_pmu_cancel_txn,
+};
+
+static int __cpuinit cpumf_pmu_notifier(struct notifier_block *self,
+					unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long) hcpu;
+	int flags;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		flags = PMC_INIT;
+		smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1);
+		break;
+	case CPU_DOWN_PREPARE:
+		flags = PMC_RELEASE;
+		smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int __init cpumf_pmu_init(void)
+{
+	int rc;
+
+	if (!cpum_cf_avail())
+		return -ENODEV;
+
+	/* clear bit 15 of cr0 to unauthorize problem-state to
+	 * extract measurement counters */
+	ctl_clear_bit(0, 48);
+
+	/* register handler for measurement-alert interruptions */
+	rc = register_external_interrupt(0x1407, cpumf_measurement_alert);
+	if (rc) {
+		pr_err("Registering for CPU-measurement alerts "
+		       "failed with rc=%i\n", rc);
+		goto out;
+	}
+
+	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+	if (rc) {
+		pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
+		unregister_external_interrupt(0x1407, cpumf_measurement_alert);
+		goto out;
+	}
+	perf_cpu_notifier(cpumf_pmu_notifier);
+out:
+	return rc;
+}
+early_initcall(cpumf_pmu_init);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
new file mode 100644
index 000000000000..f58f37f66824
--- /dev/null
+++ b/arch/s390/kernel/perf_event.c
@@ -0,0 +1,124 @@
+/*
+ * Performance event support for s390x
+ *
+ *  Copyright IBM Corp. 2012
+ *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#define KMSG_COMPONENT	"perf"
+#define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/export.h>
+#include <asm/irq.h>
+#include <asm/cpu_mf.h>
+#include <asm/lowcore.h>
+#include <asm/processor.h>
+
+const char *perf_pmu_name(void)
+{
+	if (cpum_cf_avail() || cpum_sf_avail())
+		return "CPU-measurement facilities (CPUMF)";
+	return "pmu";
+}
+EXPORT_SYMBOL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	int num = 0;
+
+	if (cpum_cf_avail())
+		num += PERF_CPUM_CF_MAX_CTR;
+
+	return num;
+}
+EXPORT_SYMBOL(perf_num_counters);
+
+void perf_event_print_debug(void)
+{
+	struct cpumf_ctr_info cf_info;
+	unsigned long flags;
+	int cpu;
+
+	if (!cpum_cf_avail())
+		return;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+	memset(&cf_info, 0, sizeof(cf_info));
+	if (!qctri(&cf_info)) {
+		pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n",
+			cpu, cf_info.cfvn, cf_info.csvn,
+			cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl);
+		print_hex_dump_bytes("CPUMF Query: ", DUMP_PREFIX_OFFSET,
+				     &cf_info, sizeof(cf_info));
+	}
+
+	local_irq_restore(flags);
+}
+
+/* See also arch/s390/kernel/traps.c */
+static unsigned long __store_trace(struct perf_callchain_entry *entry,
+				   unsigned long sp,
+				   unsigned long low, unsigned long high)
+{
+	struct stack_frame *sf;
+	struct pt_regs *regs;
+
+	while (1) {
+		sp = sp & PSW_ADDR_INSN;
+		if (sp < low || sp > high - sizeof(*sf))
+			return sp;
+		sf = (struct stack_frame *) sp;
+		perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN);
+		/* Follow the backchain. */
+		while (1) {
+			low = sp;
+			sp = sf->back_chain & PSW_ADDR_INSN;
+			if (!sp)
+				break;
+			if (sp <= low || sp > high - sizeof(*sf))
+				return sp;
+			sf = (struct stack_frame *) sp;
+			perf_callchain_store(entry,
+					     sf->gprs[8] & PSW_ADDR_INSN);
+		}
+		/* Zero backchain detected, check for interrupt frame. */
+		sp = (unsigned long) (sf + 1);
+		if (sp <= low || sp > high - sizeof(*regs))
+			return sp;
+		regs = (struct pt_regs *) sp;
+		perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN);
+		low = sp;
+		sp = regs->gprs[15];
+	}
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+			   struct pt_regs *regs)
+{
+	unsigned long head;
+	struct stack_frame *head_sf;
+
+	if (user_mode(regs))
+		return;
+
+	head = regs->gprs[15];
+	head_sf = (struct stack_frame *) head;
+
+	if (!head_sf || !head_sf->back_chain)
+		return;
+
+	head = head_sf->back_chain;
+	head = __store_trace(entry, head, S390_lowcore.async_stack - ASYNC_SIZE,
+			     S390_lowcore.async_stack);
+
+	__store_trace(entry, head, S390_lowcore.thread_info,
+		      S390_lowcore.thread_info + THREAD_SIZE);
+}
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 3732e4c09cbe..60055cefdd04 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -23,13 +23,13 @@
 #include <linux/kprobes.h>
 #include <linux/random.h>
 #include <linux/module.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/irq.h>
 #include <asm/timer.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 61f95489d70c..02f300fbf070 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -26,9 +26,9 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 38e751278bf7..06264ae8ccd9 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -50,7 +50,7 @@
 
 #include <asm/ipl.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
+#include <asm/facility.h>
 #include <asm/smp.h>
 #include <asm/mmu_context.h>
 #include <asm/cpcmd.h>
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index f29f5ef400e5..f7582b27f600 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -30,6 +30,7 @@
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 #include <asm/lowcore.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index a8bf9994b086..1f77227669e8 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -32,6 +32,8 @@
 #include <linux/slab.h>
 #include <linux/crash_dump.h>
 #include <asm/asm-offsets.h>
+#include <asm/switch_to.h>
+#include <asm/facility.h>
 #include <asm/ipl.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index 47df775c844d..aa1494d0e380 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -9,7 +9,7 @@
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/mm.h>
-#include <asm/system.h>
+#include <asm/ctl_reg.h>
 
 /*
  * References to section boundaries
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index cd6ebe12c481..77cdf4234ebc 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -33,7 +33,6 @@
 #include <linux/kprobes.h>
 #include <linux/bug.h>
 #include <linux/utsname.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 9c80138206b0..ea5590fdca3b 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -25,12 +25,12 @@
 #include <linux/compat.h>
 #include <asm/asm-offsets.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/sections.h>
 #include <asm/vdso.h>
+#include <asm/facility.h>
 
 #if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
 extern char vdso32_start, vdso32_end;
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index a21634173a66..78eb9847008f 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -34,6 +34,15 @@ config KVM
 
 	  If unsure, say N.
 
+config KVM_S390_UCONTROL
+	bool "Userspace controlled virtual machines"
+	depends on KVM
+	---help---
+	  Allow CAP_SYS_ADMIN users to create KVM virtual machines that are
+	  controlled by userspace.
+
+	  If unsure, say N.
+
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/vhost/Kconfig
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 8943e82cd4d9..a353f0ea45c2 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -20,8 +20,8 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
 	unsigned long start, end;
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
 
-	start = vcpu->arch.guest_gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
-	end = vcpu->arch.guest_gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
+	start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
+	end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
 
 	if (start & ~PAGE_MASK || end & ~PAGE_MASK || start > end
 	    || start < 2 * PAGE_SIZE)
@@ -56,7 +56,7 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 {
 	unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
-	unsigned long subcode = vcpu->arch.guest_gprs[reg] & 0xffff;
+	unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
 
 	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
 	switch (subcode) {
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 02434543eabb..361456577c6f 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -36,7 +36,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -75,7 +75,7 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -133,13 +133,6 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 
 	vcpu->stat.exit_stop_request++;
 	spin_lock_bh(&vcpu->arch.local_int.lock);
-	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
-		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
-		rc = kvm_s390_vcpu_store_status(vcpu,
-						  KVM_S390_STORE_STATUS_NOADDR);
-		if (rc >= 0)
-			rc = -EOPNOTSUPP;
-	}
 
 	if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP;
@@ -155,7 +148,18 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 		rc = -EOPNOTSUPP;
 	}
 
-	spin_unlock_bh(&vcpu->arch.local_int.lock);
+	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
+		/* store status must be called unlocked. Since local_int.lock
+		 * only protects local_int.* and not guest memory we can give
+		 * up the lock here */
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
+		rc = kvm_s390_vcpu_store_status(vcpu,
+						KVM_S390_STORE_STATUS_NOADDR);
+		if (rc >= 0)
+			rc = -EOPNOTSUPP;
+	} else
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
 	return rc;
 }
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index f0647ce6da21..2d9f9a72bb81 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -236,8 +236,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
 			   inti->prefix.address);
 		vcpu->stat.deliver_prefix_signal++;
-		vcpu->arch.sie_block->prefix = inti->prefix.address;
-		vcpu->arch.sie_block->ihcpu = 0xffff;
+		kvm_s390_set_prefix(vcpu, inti->prefix.address);
 		break;
 
 	case KVM_S390_RESTART:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d1c445732451..217ce44395a4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -27,7 +27,7 @@
 #include <asm/lowcore.h>
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
-#include <asm/system.h>
+#include <asm/switch_to.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -129,6 +129,10 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_S390_PSW:
 	case KVM_CAP_S390_GMAP:
 	case KVM_CAP_SYNC_MMU:
+#ifdef CONFIG_KVM_S390_UCONTROL
+	case KVM_CAP_S390_UCONTROL:
+#endif
+	case KVM_CAP_SYNC_REGS:
 		r = 1;
 		break;
 	default:
@@ -171,11 +175,22 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	return r;
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	int rc;
 	char debug_name[16];
 
+	rc = -EINVAL;
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (type & ~KVM_VM_S390_UCONTROL)
+		goto out_err;
+	if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN)))
+		goto out_err;
+#else
+	if (type)
+		goto out_err;
+#endif
+
 	rc = s390_enable_sie();
 	if (rc)
 		goto out_err;
@@ -198,10 +213,13 @@ int kvm_arch_init_vm(struct kvm *kvm)
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
 	VM_EVENT(kvm, 3, "%s", "vm created");
 
-	kvm->arch.gmap = gmap_alloc(current->mm);
-	if (!kvm->arch.gmap)
-		goto out_nogmap;
-
+	if (type & KVM_VM_S390_UCONTROL) {
+		kvm->arch.gmap = NULL;
+	} else {
+		kvm->arch.gmap = gmap_alloc(current->mm);
+		if (!kvm->arch.gmap)
+			goto out_nogmap;
+	}
 	return 0;
 out_nogmap:
 	debug_unregister(kvm->arch.dbf);
@@ -214,11 +232,18 @@ out_err:
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
-	clear_bit(63 - vcpu->vcpu_id, (unsigned long *) &vcpu->kvm->arch.sca->mcn);
-	if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
-		(__u64) vcpu->arch.sie_block)
-		vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+	if (!kvm_is_ucontrol(vcpu->kvm)) {
+		clear_bit(63 - vcpu->vcpu_id,
+			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
+		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
+		    (__u64) vcpu->arch.sie_block)
+			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+	}
 	smp_mb();
+
+	if (kvm_is_ucontrol(vcpu->kvm))
+		gmap_free(vcpu->arch.gmap);
+
 	free_page((unsigned long)(vcpu->arch.sie_block));
 	kvm_vcpu_uninit(vcpu);
 	kfree(vcpu);
@@ -249,13 +274,25 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_vcpus(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
-	gmap_free(kvm->arch.gmap);
+	if (!kvm_is_ucontrol(kvm))
+		gmap_free(kvm->arch.gmap);
 }
 
 /* Section: vcpu related */
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		vcpu->arch.gmap = gmap_alloc(current->mm);
+		if (!vcpu->arch.gmap)
+			return -ENOMEM;
+		return 0;
+	}
+
 	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
+				    KVM_SYNC_GPRS |
+				    KVM_SYNC_ACRS |
+				    KVM_SYNC_CRS;
 	return 0;
 }
 
@@ -270,7 +307,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	save_access_regs(vcpu->arch.host_acrs);
 	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
-	restore_access_regs(vcpu->arch.guest_acrs);
+	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);
 	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 }
@@ -280,7 +317,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
-	save_access_regs(vcpu->arch.guest_acrs);
+	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_fp_regs(&vcpu->arch.host_fpregs);
 	restore_access_regs(vcpu->arch.host_acrs);
 }
@@ -290,8 +327,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	/* this equals initial cpu reset in pop, but we don't switch to ESA */
 	vcpu->arch.sie_block->gpsw.mask = 0UL;
 	vcpu->arch.sie_block->gpsw.addr = 0UL;
-	vcpu->arch.sie_block->prefix    = 0UL;
-	vcpu->arch.sie_block->ihcpu     = 0xffff;
+	kvm_s390_set_prefix(vcpu, 0);
 	vcpu->arch.sie_block->cputm     = 0UL;
 	vcpu->arch.sie_block->ckc       = 0UL;
 	vcpu->arch.sie_block->todpr     = 0;
@@ -342,12 +378,19 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 		goto out_free_cpu;
 
 	vcpu->arch.sie_block->icpua = id;
-	BUG_ON(!kvm->arch.sca);
-	if (!kvm->arch.sca->cpu[id].sda)
-		kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
-	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
-	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
-	set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
+	if (!kvm_is_ucontrol(kvm)) {
+		if (!kvm->arch.sca) {
+			WARN_ON_ONCE(1);
+			goto out_free_cpu;
+		}
+		if (!kvm->arch.sca->cpu[id].sda)
+			kvm->arch.sca->cpu[id].sda =
+				(__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh =
+			(__u32)(((__u64)kvm->arch.sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
+		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
+	}
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
@@ -388,29 +431,29 @@ static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
-	memcpy(&vcpu->arch.guest_gprs, &regs->gprs, sizeof(regs->gprs));
+	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
-	memcpy(&regs->gprs, &vcpu->arch.guest_gprs, sizeof(regs->gprs));
+	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs));
+	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
 	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
-	restore_access_regs(vcpu->arch.guest_acrs);
+	restore_access_regs(vcpu->run->s.regs.acrs);
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	memcpy(&sregs->acrs, &vcpu->arch.guest_acrs, sizeof(sregs->acrs));
+	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
 	memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
 	return 0;
 }
@@ -418,7 +461,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
-	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
+	vcpu->arch.guest_fpregs.fpc = fpu->fpc & FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	return 0;
 }
@@ -467,9 +510,11 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return -EINVAL; /* not implemented yet */
 }
 
-static void __vcpu_run(struct kvm_vcpu *vcpu)
+static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
-	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
+	int rc;
+
+	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
 
 	if (need_resched())
 		schedule();
@@ -477,7 +522,8 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	if (test_thread_flag(TIF_MCCK_PENDING))
 		s390_handle_mcck();
 
-	kvm_s390_deliver_pending_interrupts(vcpu);
+	if (!kvm_is_ucontrol(vcpu->kvm))
+		kvm_s390_deliver_pending_interrupts(vcpu);
 
 	vcpu->arch.sie_block->icptcode = 0;
 	local_irq_disable();
@@ -485,9 +531,15 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
-	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
-		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
-		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
+	if (rc) {
+		if (kvm_is_ucontrol(vcpu->kvm)) {
+			rc = SIE_INTERCEPT_UCONTROL;
+		} else {
+			VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+			kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+			rc = 0;
+		}
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
@@ -495,7 +547,8 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	kvm_guest_exit();
 	local_irq_enable();
 
-	memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	return rc;
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -516,6 +569,7 @@ rerun_vcpu:
 	case KVM_EXIT_UNKNOWN:
 	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
+	case KVM_EXIT_S390_UCONTROL:
 		break;
 	default:
 		BUG();
@@ -523,12 +577,26 @@ rerun_vcpu:
 
 	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
 	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) {
+		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_PREFIX;
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	}
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
+		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_CRS;
+		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	}
 
 	might_fault();
 
 	do {
-		__vcpu_run(vcpu);
-		rc = kvm_handle_sie_intercept(vcpu);
+		rc = __vcpu_run(vcpu);
+		if (rc)
+			break;
+		if (kvm_is_ucontrol(vcpu->kvm))
+			rc = -EOPNOTSUPP;
+		else
+			rc = kvm_handle_sie_intercept(vcpu);
 	} while (!signal_pending(current) && !rc);
 
 	if (rc == SIE_INTERCEPT_RERUNVCPU)
@@ -539,6 +607,16 @@ rerun_vcpu:
 		rc = -EINTR;
 	}
 
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (rc == SIE_INTERCEPT_UCONTROL) {
+		kvm_run->exit_reason = KVM_EXIT_S390_UCONTROL;
+		kvm_run->s390_ucontrol.trans_exc_code =
+			current->thread.gmap_addr;
+		kvm_run->s390_ucontrol.pgm_code = 0x10;
+		rc = 0;
+	}
+#endif
+
 	if (rc == -EOPNOTSUPP) {
 		/* intercept cannot be handled in-kernel, prepare kvm-run */
 		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
@@ -556,6 +634,8 @@ rerun_vcpu:
 
 	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
 	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
+	kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix;
+	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
@@ -602,7 +682,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
-			vcpu->arch.guest_gprs, 128, prefix))
+			vcpu->run->s.regs.gprs, 128, prefix))
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
@@ -631,7 +711,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
-			&vcpu->arch.guest_acrs, 64, prefix))
+			&vcpu->run->s.regs.acrs, 64, prefix))
 		return -EFAULT;
 
 	if (__guestcopy(vcpu,
@@ -673,12 +753,77 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_S390_INITIAL_RESET:
 		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
 		break;
+#ifdef CONFIG_KVM_S390_UCONTROL
+	case KVM_S390_UCAS_MAP: {
+		struct kvm_s390_ucas_mapping ucasmap;
+
+		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
+			r = -EFAULT;
+			break;
+		}
+
+		if (!kvm_is_ucontrol(vcpu->kvm)) {
+			r = -EINVAL;
+			break;
+		}
+
+		r = gmap_map_segment(vcpu->arch.gmap, ucasmap.user_addr,
+				     ucasmap.vcpu_addr, ucasmap.length);
+		break;
+	}
+	case KVM_S390_UCAS_UNMAP: {
+		struct kvm_s390_ucas_mapping ucasmap;
+
+		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
+			r = -EFAULT;
+			break;
+		}
+
+		if (!kvm_is_ucontrol(vcpu->kvm)) {
+			r = -EINVAL;
+			break;
+		}
+
+		r = gmap_unmap_segment(vcpu->arch.gmap, ucasmap.vcpu_addr,
+			ucasmap.length);
+		break;
+	}
+#endif
+	case KVM_S390_VCPU_FAULT: {
+		r = gmap_fault(arg, vcpu->arch.gmap);
+		if (!IS_ERR_VALUE(r))
+			r = 0;
+		break;
+	}
 	default:
-		r = -EINVAL;
+		r = -ENOTTY;
 	}
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if ((vmf->pgoff == KVM_S390_SIE_PAGE_OFFSET)
+		 && (kvm_is_ucontrol(vcpu->kvm))) {
+		vmf->page = virt_to_page(vcpu->arch.sie_block);
+		get_page(vmf->page);
+		return 0;
+	}
+#endif
+	return VM_FAULT_SIGBUS;
+}
+
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 99b0b7597115..ff28f9d1c9eb 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -26,6 +26,7 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
 /* negativ values are error codes, positive values for internal conditions */
 #define SIE_INTERCEPT_RERUNVCPU		(1<<0)
+#define SIE_INTERCEPT_UCONTROL		(1<<1)
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
 
 #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
@@ -47,6 +48,23 @@ static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
 	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
 }
 
+static inline int kvm_is_ucontrol(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (kvm->arch.gmap)
+		return 0;
+	return 1;
+#else
+	return 0;
+#endif
+}
+
+static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
+{
+	vcpu->arch.sie_block->prefix = prefix & 0x7fffe000u;
+	vcpu->arch.sie_block->ihcpu  = 0xffff;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d02638959922..e5a45dbd26ac 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -33,7 +33,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -56,8 +56,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	vcpu->arch.sie_block->prefix = address;
-	vcpu->arch.sie_block->ihcpu = 0xffff;
+	kvm_s390_set_prefix(vcpu, address);
 
 	VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
 out:
@@ -74,7 +73,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stpx++;
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -106,7 +105,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stap++;
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 1) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -181,7 +180,7 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stidp++;
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	if (operand2 & 7) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -232,9 +231,9 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 
 static int handle_stsi(struct kvm_vcpu *vcpu)
 {
-	int fc = (vcpu->arch.guest_gprs[0] & 0xf0000000) >> 28;
-	int sel1 = vcpu->arch.guest_gprs[0] & 0xff;
-	int sel2 = vcpu->arch.guest_gprs[1] & 0xffff;
+	int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28;
+	int sel1 = vcpu->run->s.regs.gprs[0] & 0xff;
+	int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff;
 	int base2 = vcpu->arch.sie_block->ipb >> 28;
 	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
@@ -245,14 +244,14 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	if (operand2 & 0xfff && fc > 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	switch (fc) {
 	case 0:
-		vcpu->arch.guest_gprs[0] = 3 << 28;
+		vcpu->run->s.regs.gprs[0] = 3 << 28;
 		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
 		return 0;
 	case 1: /* same handling for 1 and 2 */
@@ -281,7 +280,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	}
 	free_page(mem);
 	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.guest_gprs[0] = 0;
+	vcpu->run->s.regs.gprs[0] = 0;
 	return 0;
 out_mem:
 	free_page(mem);
@@ -333,8 +332,8 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
 	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
 	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
-	u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
-	u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
+	u64 address1 = disp1 + base1 ? vcpu->run->s.regs.gprs[base1] : 0;
+	u64 address2 = disp2 + base2 ? vcpu->run->s.regs.gprs[base2] : 0;
 	struct vm_area_struct *vma;
 	unsigned long user_address;
 
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 0a7941d74bc6..0ad4cf238391 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -48,7 +48,7 @@
 
 
 static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
-			unsigned long *reg)
+			u64 *reg)
 {
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	int rc;
@@ -160,12 +160,15 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	inti->type = KVM_S390_SIGP_STOP;
 
 	spin_lock_bh(&li->lock);
+	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED))
+		goto out;
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
 	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
 	li->action_bits |= action;
 	if (waitqueue_active(&li->wq))
 		wake_up_interruptible(&li->wq);
+out:
 	spin_unlock_bh(&li->lock);
 
 	return 0; /* order accepted */
@@ -220,7 +223,7 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 }
 
 static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
-			     unsigned long *reg)
+			     u64 *reg)
 {
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li = NULL;
@@ -278,7 +281,7 @@ out_fi:
 }
 
 static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
-				unsigned long *reg)
+				u64 *reg)
 {
 	int rc;
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
@@ -309,6 +312,34 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
 	return rc;
 }
 
+static int __sigp_restart(struct kvm_vcpu *vcpu, u16 cpu_addr)
+{
+	int rc = 0;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return 3; /* not operational */
+
+	spin_lock(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = 3; /* not operational */
+		goto out;
+	}
+
+	spin_lock_bh(&li->lock);
+	if (li->action_bits & ACTION_STOP_ON_STOP)
+		rc = 2; /* busy */
+	else
+		VCPU_EVENT(vcpu, 4, "sigp restart %x to handle userspace",
+			cpu_addr);
+	spin_unlock_bh(&li->lock);
+out:
+	spin_unlock(&fi->lock);
+	return rc;
+}
+
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
 	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
@@ -316,7 +347,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	int base2 = vcpu->arch.sie_block->ipb >> 28;
 	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u32 parameter;
-	u16 cpu_addr = vcpu->arch.guest_gprs[r3];
+	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
 	u8 order_code;
 	int rc;
 
@@ -327,18 +358,18 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 
 	order_code = disp2;
 	if (base2)
-		order_code += vcpu->arch.guest_gprs[base2];
+		order_code += vcpu->run->s.regs.gprs[base2];
 
 	if (r1 % 2)
-		parameter = vcpu->arch.guest_gprs[r1];
+		parameter = vcpu->run->s.regs.gprs[r1];
 	else
-		parameter = vcpu->arch.guest_gprs[r1 + 1];
+		parameter = vcpu->run->s.regs.gprs[r1 + 1];
 
 	switch (order_code) {
 	case SIGP_SENSE:
 		vcpu->stat.instruction_sigp_sense++;
 		rc = __sigp_sense(vcpu, cpu_addr,
-				  &vcpu->arch.guest_gprs[r1]);
+				  &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_EXTERNAL_CALL:
 		vcpu->stat.instruction_sigp_external_call++;
@@ -354,7 +385,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		break;
 	case SIGP_STOP_STORE_STATUS:
 		vcpu->stat.instruction_sigp_stop++;
-		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP);
+		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP |
+						 ACTION_STOP_ON_STOP);
 		break;
 	case SIGP_SET_ARCH:
 		vcpu->stat.instruction_sigp_arch++;
@@ -363,15 +395,18 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	case SIGP_SET_PREFIX:
 		vcpu->stat.instruction_sigp_prefix++;
 		rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
-				       &vcpu->arch.guest_gprs[r1]);
+				       &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_SENSE_RUNNING:
 		vcpu->stat.instruction_sigp_sense_running++;
 		rc = __sigp_sense_running(vcpu, cpu_addr,
-					  &vcpu->arch.guest_gprs[r1]);
+					  &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_RESTART:
 		vcpu->stat.instruction_sigp_restart++;
+		rc = __sigp_restart(vcpu, cpu_addr);
+		if (rc == 2) /* busy */
+			break;
 		/* user space must know about restart */
 	default:
 		return -EOPNOTSUPP;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index b17c42df61c9..46ef3fd0663b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -32,10 +32,10 @@
 #include <linux/uaccess.h>
 #include <linux/hugetlb.h>
 #include <asm/asm-offsets.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
+#include <asm/facility.h>
 #include "../kernel/entry.h"
 
 #ifndef CONFIG_64BIT
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 50236610de83..2bea0605856e 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -29,7 +29,6 @@
 #include <linux/export.h>
 #include <linux/gfp.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -38,6 +37,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
+#include <asm/ctl_reg.h>
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
 
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 1cb8427bedfb..7bb15fcca75e 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -12,7 +12,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/gfp.h>
-#include <asm/system.h>
+#include <asm/ctl_reg.h>
 
 /*
  * This function writes to kernel memory bypassing DAT and possible
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index a0155c02e324..2857c48486ea 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -100,7 +100,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
-EXPORT_SYMBOL_GPL(arch_pick_mmap_layout);
 
 #else
 
@@ -175,6 +174,5 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
-EXPORT_SYMBOL_GPL(arch_pick_mmap_layout);
 
 #endif
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 51b0738e13d1..373adf69b01c 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -18,7 +18,6 @@
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index 12bea05a0fc1..c6646de07bf4 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -18,7 +18,8 @@
 #include <linux/oom.h>
 #include <linux/oprofile.h>
 
-#include <asm/lowcore.h>
+#include <asm/facility.h>
+#include <asm/cpu_mf.h>
 #include <asm/irq.h>
 
 #include "hwsampler.h"
@@ -30,12 +31,6 @@
 #define ALERT_REQ_MASK   0x4000000000000000ul
 #define BUFFER_FULL_MASK 0x8000000000000000ul
 
-#define EI_IEA      (1 << 31)	/* invalid entry address              */
-#define EI_ISE      (1 << 30)	/* incorrect SDBT entry               */
-#define EI_PRA      (1 << 29)	/* program request alert              */
-#define EI_SACA     (1 << 23)	/* sampler authorization change alert */
-#define EI_LSDA     (1 << 22)	/* loss of sample data alert          */
-
 DECLARE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
 
 struct hws_execute_parms {
@@ -232,9 +227,20 @@ static inline unsigned long *trailer_entry_ptr(unsigned long v)
 	return (unsigned long *) ret;
 }
 
-/* prototypes for external interrupt handler and worker */
 static void hws_ext_handler(struct ext_code ext_code,
-			    unsigned int param32, unsigned long param64);
+			    unsigned int param32, unsigned long param64)
+{
+	struct hws_cpu_buffer *cb = &__get_cpu_var(sampler_cpu_buffer);
+
+	if (!(param32 & CPU_MF_INT_SF_MASK))
+		return;
+
+	kstat_cpu(smp_processor_id()).irqs[EXTINT_CPM]++;
+	atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
+
+	if (hws_wq)
+		queue_work(hws_wq, &cb->worker);
+}
 
 static void worker(struct work_struct *work);
 
@@ -673,18 +679,6 @@ int hwsampler_activate(unsigned int cpu)
 	return rc;
 }
 
-static void hws_ext_handler(struct ext_code ext_code,
-			    unsigned int param32, unsigned long param64)
-{
-	struct hws_cpu_buffer *cb;
-
-	kstat_cpu(smp_processor_id()).irqs[EXTINT_CPM]++;
-	cb = &__get_cpu_var(sampler_cpu_buffer);
-	atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
-	if (hws_wq)
-		queue_work(hws_wq, &cb->worker);
-}
-
 static int check_qsi_on_setup(void)
 {
 	int rc;
@@ -760,23 +754,23 @@ static int worker_check_error(unsigned int cpu, int ext_params)
 	if (!sdbt || !*sdbt)
 		return -EINVAL;
 
-	if (ext_params & EI_PRA)
+	if (ext_params & CPU_MF_INT_SF_PRA)
 		cb->req_alert++;
 
-	if (ext_params & EI_LSDA)
+	if (ext_params & CPU_MF_INT_SF_LSDA)
 		cb->loss_of_sample_data++;
 
-	if (ext_params & EI_IEA) {
+	if (ext_params & CPU_MF_INT_SF_IAE) {
 		cb->invalid_entry_address++;
 		rc = -EINVAL;
 	}
 
-	if (ext_params & EI_ISE) {
+	if (ext_params & CPU_MF_INT_SF_ISE) {
 		cb->incorrect_sdbt_entry++;
 		rc = -EINVAL;
 	}
 
-	if (ext_params & EI_SACA) {
+	if (ext_params & CPU_MF_INT_SF_SACA) {
 		cb->sample_auth_change_alert++;
 		rc = -EINVAL;
 	}
@@ -1009,7 +1003,7 @@ int hwsampler_deallocate(void)
 	if (hws_state != HWS_STOPPED)
 		goto deallocate_exit;
 
-	ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
+	measurement_alert_subclass_unregister();
 	deallocate_sdbt();
 
 	hws_state = HWS_DEALLOCATED;
@@ -1123,7 +1117,7 @@ int hwsampler_shutdown(void)
 		mutex_lock(&hws_sem);
 
 		if (hws_state == HWS_STOPPED) {
-			ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
+			measurement_alert_subclass_unregister();
 			deallocate_sdbt();
 		}
 		if (hws_wq) {
@@ -1198,7 +1192,7 @@ start_all_exit:
 	hws_oom = 1;
 	hws_flush_all = 0;
 	/* now let them in, 1407 CPUMF external interrupts */
-	ctl_set_bit(0, 5); /* set CR0 bit 58 */
+	measurement_alert_subclass_register();
 
 	return 0;
 }
diff --git a/arch/score/include/asm/atomic.h b/arch/score/include/asm/atomic.h
index 84eb8ddf9f3f..edf33dbded1e 100644
--- a/arch/score/include/asm/atomic.h
+++ b/arch/score/include/asm/atomic.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_SCORE_ATOMIC_H
 #define _ASM_SCORE_ATOMIC_H
 
+#include <asm/cmpxchg.h>
 #include <asm-generic/atomic.h>
 
 #endif /* _ASM_SCORE_ATOMIC_H */
diff --git a/arch/score/include/asm/barrier.h b/arch/score/include/asm/barrier.h
new file mode 100644
index 000000000000..0eacb6471e6d
--- /dev/null
+++ b/arch/score/include/asm/barrier.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_SCORE_BARRIER_H
+#define _ASM_SCORE_BARRIER_H
+
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+
+#define read_barrier_depends()		do {} while (0)
+#define smp_read_barrier_depends()	do {} while (0)
+
+#define set_mb(var, value) 		do {var = value; wmb(); } while (0)
+
+#endif /* _ASM_SCORE_BARRIER_H */
diff --git a/arch/score/include/asm/bitops.h b/arch/score/include/asm/bitops.h
index 2763b050fca8..a304096b1894 100644
--- a/arch/score/include/asm/bitops.h
+++ b/arch/score/include/asm/bitops.h
@@ -2,7 +2,6 @@
 #define _ASM_SCORE_BITOPS_H
 
 #include <asm/byteorder.h> /* swab32 */
-#include <asm/system.h> /* save_flags */
 
 /*
  * clear_bit() doesn't provide any barrier for the compiler.
diff --git a/arch/score/include/asm/bug.h b/arch/score/include/asm/bug.h
index bb76a330bcf1..fd7164af1f04 100644
--- a/arch/score/include/asm/bug.h
+++ b/arch/score/include/asm/bug.h
@@ -3,4 +3,15 @@
 
 #include <asm-generic/bug.h>
 
+struct pt_regs;
+extern void __die(const char *, struct pt_regs *, const char *,
+	const char *, unsigned long) __attribute__((noreturn));
+extern void __die_if_kernel(const char *, struct pt_regs *, const char *,
+	const char *, unsigned long);
+
+#define die(msg, regs)							\
+	__die(msg, regs, __FILE__ ":", __func__, __LINE__)
+#define die_if_kernel(msg, regs)					\
+	__die_if_kernel(msg, regs, __FILE__ ":", __func__, __LINE__)
+
 #endif /* _ASM_SCORE_BUG_H */
diff --git a/arch/score/include/asm/cmpxchg.h b/arch/score/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..f384839c3ee5
--- /dev/null
+++ b/arch/score/include/asm/cmpxchg.h
@@ -0,0 +1,49 @@
+#ifndef _ASM_SCORE_CMPXCHG_H
+#define _ASM_SCORE_CMPXCHG_H
+
+#include <linux/irqflags.h>
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((struct __xchg_dummy *)(x))
+
+static inline
+unsigned long __xchg(volatile unsigned long *m, unsigned long val)
+{
+	unsigned long retval;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	retval = *m;
+	*m = val;
+	local_irq_restore(flags);
+	return retval;
+}
+
+#define xchg(ptr, v)						\
+	((__typeof__(*(ptr))) __xchg((unsigned long *)(ptr),	\
+					(unsigned long)(v)))
+
+static inline unsigned long __cmpxchg(volatile unsigned long *m,
+				unsigned long old, unsigned long new)
+{
+	unsigned long retval;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	retval = *m;
+	if (retval == old)
+		*m = new;
+	local_irq_restore(flags);
+	return retval;
+}
+
+#define cmpxchg(ptr, o, n)					\
+	((__typeof__(*(ptr))) __cmpxchg((unsigned long *)(ptr),	\
+					(unsigned long)(o),	\
+					(unsigned long)(n)))
+
+#define __HAVE_ARCH_CMPXCHG	1
+
+#include <asm-generic/cmpxchg-local.h>
+
+#endif /* _ASM_SCORE_CMPXCHG_H */
diff --git a/arch/score/include/asm/exec.h b/arch/score/include/asm/exec.h
new file mode 100644
index 000000000000..f9f3cd59c860
--- /dev/null
+++ b/arch/score/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_SCORE_EXEC_H
+#define _ASM_SCORE_EXEC_H
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif /* _ASM_SCORE_EXEC_H */
diff --git a/arch/score/include/asm/switch_to.h b/arch/score/include/asm/switch_to.h
new file mode 100644
index 000000000000..031756b59ece
--- /dev/null
+++ b/arch/score/include/asm/switch_to.h
@@ -0,0 +1,13 @@
+#ifndef _ASM_SCORE_SWITCH_TO_H
+#define _ASM_SCORE_SWITCH_TO_H
+
+extern void *resume(void *last, void *next, void *next_ti);
+
+#define switch_to(prev, next, last)				\
+do {								\
+	(last) = resume(prev, next, task_thread_info(next));	\
+} while (0)
+
+#define finish_arch_switch(prev)	do {} while (0)
+
+#endif /* _ASM_SCORE_SWITCH_TO_H */
diff --git a/arch/score/include/asm/system.h b/arch/score/include/asm/system.h
deleted file mode 100644
index 589d5c7e171c..000000000000
--- a/arch/score/include/asm/system.h
+++ /dev/null
@@ -1,90 +0,0 @@
-#ifndef _ASM_SCORE_SYSTEM_H
-#define _ASM_SCORE_SYSTEM_H
-
-#include <linux/types.h>
-#include <linux/irqflags.h>
-
-struct pt_regs;
-struct task_struct;
-
-extern void *resume(void *last, void *next, void *next_ti);
-
-#define switch_to(prev, next, last)				\
-do {								\
-	(last) = resume(prev, next, task_thread_info(next));	\
-} while (0)
-
-#define finish_arch_switch(prev)	do {} while (0)
-
-typedef void (*vi_handler_t)(void);
-extern unsigned long arch_align_stack(unsigned long sp);
-
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-#define set_mb(var, value) 		do {var = value; wmb(); } while (0)
-
-#define __HAVE_ARCH_CMPXCHG	1
-
-#include <asm-generic/cmpxchg-local.h>
-
-#ifndef __ASSEMBLY__
-
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((struct __xchg_dummy *)(x))
-
-static inline
-unsigned long __xchg(volatile unsigned long *m, unsigned long val)
-{
-	unsigned long retval;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	retval = *m;
-	*m = val;
-	local_irq_restore(flags);
-	return retval;
-}
-
-#define xchg(ptr, v)						\
-	((__typeof__(*(ptr))) __xchg((unsigned long *)(ptr),	\
-					(unsigned long)(v)))
-
-static inline unsigned long __cmpxchg(volatile unsigned long *m,
-				unsigned long old, unsigned long new)
-{
-	unsigned long retval;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	retval = *m;
-	if (retval == old)
-		*m = new;
-	local_irq_restore(flags);
-	return retval;
-}
-
-#define cmpxchg(ptr, o, n)					\
-	((__typeof__(*(ptr))) __cmpxchg((unsigned long *)(ptr),	\
-					(unsigned long)(o),	\
-					(unsigned long)(n)))
-
-extern void __die(const char *, struct pt_regs *, const char *,
-	const char *, unsigned long) __attribute__((noreturn));
-extern void __die_if_kernel(const char *, struct pt_regs *, const char *,
-	const char *, unsigned long);
-
-#define die(msg, regs)							\
-	__die(msg, regs, __FILE__ ":", __func__, __LINE__)
-#define die_if_kernel(msg, regs)					\
-	__die_if_kernel(msg, regs, __FILE__ ":", __func__, __LINE__)
-
-#endif /* !__ASSEMBLY__ */
-#endif /* _ASM_SCORE_SYSTEM_H */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 713fb58ca507..ff9e033ce626 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -5,6 +5,7 @@ config SUPERH
 	select HAVE_IDE if HAS_IOPORT
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
+	select ARCH_DISCARD_MEMBLOCK
 	select HAVE_OPROFILE
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_ARCH_TRACEHOOK
@@ -22,7 +23,7 @@ config SUPERH
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
+	select MAY_HAVE_SPARSE_IRQ
 	select IRQ_FORCED_THREADING
 	select RTC_LIB
 	select GENERIC_ATOMIC64
@@ -161,6 +162,9 @@ config NO_IOPORT
 config IO_TRAPPED
 	bool
 
+config SWAP_IO_SPACE
+	bool
+
 config DMA_COHERENT
 	bool
 
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index e5ac12b2ce65..d12fe9ddf3da 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -522,11 +522,18 @@ static void sdhi0_set_pwr(struct platform_device *pdev, int state)
 	gpio_set_value(GPIO_PTB6, state);
 }
 
+static int sdhi0_get_cd(struct platform_device *pdev)
+{
+	return !gpio_get_value(GPIO_PTY7);
+}
+
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
 	.set_pwr	= sdhi0_set_pwr,
-	.tmio_caps      = MMC_CAP_SDIO_IRQ | MMC_CAP_POWER_OFF_CARD,
+	.tmio_caps      = MMC_CAP_SDIO_IRQ | MMC_CAP_POWER_OFF_CARD |
+			  MMC_CAP_NEEDS_POLL,
+	.get_cd		= sdhi0_get_cd,
 };
 
 static struct resource sdhi0_resources[] = {
@@ -559,11 +566,18 @@ static void sdhi1_set_pwr(struct platform_device *pdev, int state)
 	gpio_set_value(GPIO_PTB7, state);
 }
 
+static int sdhi1_get_cd(struct platform_device *pdev)
+{
+	return !gpio_get_value(GPIO_PTW7);
+}
+
 static struct sh_mobile_sdhi_info sdhi1_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI1_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI1_RX,
-	.tmio_caps      = MMC_CAP_SDIO_IRQ | MMC_CAP_POWER_OFF_CARD,
+	.tmio_caps      = MMC_CAP_SDIO_IRQ | MMC_CAP_POWER_OFF_CARD |
+			  MMC_CAP_NEEDS_POLL,
 	.set_pwr	= sdhi1_set_pwr,
+	.get_cd		= sdhi1_get_cd,
 };
 
 static struct resource sdhi1_resources[] = {
@@ -1001,6 +1015,7 @@ extern char ecovec24_sdram_leave_end;
 static int __init arch_setup(void)
 {
 	struct clk *clk;
+	bool cn12_enabled = false;
 
 	/* register board specific self-refresh code */
 	sh_mobile_register_self_refresh(SUSP_SH_STANDBY | SUSP_SH_SF |
@@ -1201,9 +1216,13 @@ static int __init arch_setup(void)
 	gpio_direction_input(GPIO_PTR5);
 	gpio_direction_input(GPIO_PTR6);
 
+	/* SD-card slot CN11 */
+	/* Card-detect, used on CN11, either with SDHI0 or with SPI */
+	gpio_request(GPIO_PTY7, NULL);
+	gpio_direction_input(GPIO_PTY7);
+
 #if defined(CONFIG_MMC_SDHI) || defined(CONFIG_MMC_SDHI_MODULE)
 	/* enable SDHI0 on CN11 (needs DS2.4 set to ON) */
-	gpio_request(GPIO_FN_SDHI0CD,  NULL);
 	gpio_request(GPIO_FN_SDHI0WP,  NULL);
 	gpio_request(GPIO_FN_SDHI0CMD, NULL);
 	gpio_request(GPIO_FN_SDHI0CLK, NULL);
@@ -1213,23 +1232,6 @@ static int __init arch_setup(void)
 	gpio_request(GPIO_FN_SDHI0D0,  NULL);
 	gpio_request(GPIO_PTB6, NULL);
 	gpio_direction_output(GPIO_PTB6, 0);
-
-#if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
-	/* enable SDHI1 on CN12 (needs DS2.6,7 set to ON,OFF) */
-	gpio_request(GPIO_FN_SDHI1CD,  NULL);
-	gpio_request(GPIO_FN_SDHI1WP,  NULL);
-	gpio_request(GPIO_FN_SDHI1CMD, NULL);
-	gpio_request(GPIO_FN_SDHI1CLK, NULL);
-	gpio_request(GPIO_FN_SDHI1D3,  NULL);
-	gpio_request(GPIO_FN_SDHI1D2,  NULL);
-	gpio_request(GPIO_FN_SDHI1D1,  NULL);
-	gpio_request(GPIO_FN_SDHI1D0,  NULL);
-	gpio_request(GPIO_PTB7, NULL);
-	gpio_direction_output(GPIO_PTB7, 0);
-
-	/* I/O buffer drive ability is high for SDHI1 */
-	__raw_writew((__raw_readw(IODRIVEA) & ~0x3000) | 0x2000 , IODRIVEA);
-#endif /* CONFIG_MMC_SH_MMCIF */
 #else
 	/* enable MSIOF0 on CN11 (needs DS2.4 set to OFF) */
 	gpio_request(GPIO_FN_MSIOF0_TXD, NULL);
@@ -1241,12 +1243,51 @@ static int __init arch_setup(void)
 	gpio_direction_output(GPIO_PTB6, 0); /* disable power by default */
 	gpio_request(GPIO_PTY6, NULL); /* write protect */
 	gpio_direction_input(GPIO_PTY6);
-	gpio_request(GPIO_PTY7, NULL); /* card detect */
-	gpio_direction_input(GPIO_PTY7);
 
 	spi_register_board_info(spi_bus, ARRAY_SIZE(spi_bus));
 #endif
 
+	/* MMC/SD-card slot CN12 */
+#if defined(CONFIG_MMC_SH_MMCIF) || defined(CONFIG_MMC_SH_MMCIF_MODULE)
+	/* enable MMCIF (needs DS2.6,7 set to OFF,ON) */
+	gpio_request(GPIO_FN_MMC_D7, NULL);
+	gpio_request(GPIO_FN_MMC_D6, NULL);
+	gpio_request(GPIO_FN_MMC_D5, NULL);
+	gpio_request(GPIO_FN_MMC_D4, NULL);
+	gpio_request(GPIO_FN_MMC_D3, NULL);
+	gpio_request(GPIO_FN_MMC_D2, NULL);
+	gpio_request(GPIO_FN_MMC_D1, NULL);
+	gpio_request(GPIO_FN_MMC_D0, NULL);
+	gpio_request(GPIO_FN_MMC_CLK, NULL);
+	gpio_request(GPIO_FN_MMC_CMD, NULL);
+	gpio_request(GPIO_PTB7, NULL);
+	gpio_direction_output(GPIO_PTB7, 0);
+
+	cn12_enabled = true;
+#elif defined(CONFIG_MMC_SDHI) || defined(CONFIG_MMC_SDHI_MODULE)
+	/* enable SDHI1 on CN12 (needs DS2.6,7 set to ON,OFF) */
+	gpio_request(GPIO_FN_SDHI1WP,  NULL);
+	gpio_request(GPIO_FN_SDHI1CMD, NULL);
+	gpio_request(GPIO_FN_SDHI1CLK, NULL);
+	gpio_request(GPIO_FN_SDHI1D3,  NULL);
+	gpio_request(GPIO_FN_SDHI1D2,  NULL);
+	gpio_request(GPIO_FN_SDHI1D1,  NULL);
+	gpio_request(GPIO_FN_SDHI1D0,  NULL);
+	gpio_request(GPIO_PTB7, NULL);
+	gpio_direction_output(GPIO_PTB7, 0);
+
+	/* Card-detect, used on CN12 with SDHI1 */
+	gpio_request(GPIO_PTW7, NULL);
+	gpio_direction_input(GPIO_PTW7);
+
+	cn12_enabled = true;
+#endif
+
+	if (cn12_enabled)
+		/* I/O buffer drive ability is high for CN12 */
+		__raw_writew((__raw_readw(IODRIVEA) & ~0x3000) | 0x2000,
+			     IODRIVEA);
+
 	/* enable Video */
 	gpio_request(GPIO_PTU2, NULL);
 	gpio_direction_output(GPIO_PTU2, 1);
@@ -1305,25 +1346,6 @@ static int __init arch_setup(void)
 	gpio_request(GPIO_PTU5, NULL);
 	gpio_direction_output(GPIO_PTU5, 0);
 
-#if defined(CONFIG_MMC_SH_MMCIF) || defined(CONFIG_MMC_SH_MMCIF_MODULE)
-	/* enable MMCIF (needs DS2.6,7 set to OFF,ON) */
-	gpio_request(GPIO_FN_MMC_D7, NULL);
-	gpio_request(GPIO_FN_MMC_D6, NULL);
-	gpio_request(GPIO_FN_MMC_D5, NULL);
-	gpio_request(GPIO_FN_MMC_D4, NULL);
-	gpio_request(GPIO_FN_MMC_D3, NULL);
-	gpio_request(GPIO_FN_MMC_D2, NULL);
-	gpio_request(GPIO_FN_MMC_D1, NULL);
-	gpio_request(GPIO_FN_MMC_D0, NULL);
-	gpio_request(GPIO_FN_MMC_CLK, NULL);
-	gpio_request(GPIO_FN_MMC_CMD, NULL);
-	gpio_request(GPIO_PTB7, NULL);
-	gpio_direction_output(GPIO_PTB7, 0);
-
-	/* I/O buffer drive ability is high for MMCIF */
-	__raw_writew((__raw_readw(IODRIVEA) & ~0x3000) | 0x2000 , IODRIVEA);
-#endif
-
 	/* enable I2C device */
 	i2c_register_board_info(0, i2c0_devices,
 				ARRAY_SIZE(i2c0_devices));
diff --git a/arch/sh/boards/mach-microdev/irq.c b/arch/sh/boards/mach-microdev/irq.c
index 4fb00369f0e2..9a8aff339619 100644
--- a/arch/sh/boards/mach-microdev/irq.c
+++ b/arch/sh/boards/mach-microdev/irq.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <mach/microdev.h>
 
diff --git a/arch/sh/boot/Makefile b/arch/sh/boot/Makefile
index e4ea31a62c55..58592dfa5cb6 100644
--- a/arch/sh/boot/Makefile
+++ b/arch/sh/boot/Makefile
@@ -8,8 +8,6 @@
 # Copyright (C) 1999 Stuart Menefy
 #
 
-MKIMAGE := $(srctree)/scripts/mkuboot.sh
-
 #
 # Assign safe dummy values if these variables are not defined,
 # in order to suppress error message.
@@ -61,10 +59,8 @@ KERNEL_ENTRY	:= $(shell /bin/bash -c 'printf "0x%08x" \
 			$(KERNEL_MEMORY) + \
 			$(CONFIG_ZERO_PAGE_OFFSET) + $(CONFIG_ENTRY_OFFSET)]')
 
-quiet_cmd_uimage = UIMAGE  $@
-      cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A sh -O linux -T kernel \
-		   -C $(2) -a $(KERNEL_LOAD) -e $(KERNEL_ENTRY) \
-		   -n 'Linux-$(KERNELRELEASE)' -d $< $@
+UIMAGE_LOADADDR = $(KERNEL_LOAD)
+UIMAGE_ENTRYADDR = $(KERNEL_ENTRY)
 
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
diff --git a/arch/sh/drivers/dma/dma-g2.c b/arch/sh/drivers/dma/dma-g2.c
index be9ca7ca0ce4..e1ab6eb3c04b 100644
--- a/arch/sh/drivers/dma/dma-g2.c
+++ b/arch/sh/drivers/dma/dma-g2.c
@@ -181,14 +181,14 @@ static int __init g2_dma_init(void)
 
 	ret = register_dmac(&g2_dma_info);
 	if (unlikely(ret != 0))
-		free_irq(HW_EVENT_G2_DMA, 0);
+		free_irq(HW_EVENT_G2_DMA, &g2_dma_info);
 
 	return ret;
 }
 
 static void __exit g2_dma_exit(void)
 {
-	free_irq(HW_EVENT_G2_DMA, 0);
+	free_irq(HW_EVENT_G2_DMA, &g2_dma_info);
 	unregister_dmac(&g2_dma_info);
 }
 
diff --git a/arch/sh/drivers/dma/dmabrg.c b/arch/sh/drivers/dma/dmabrg.c
index 3d66a32ce610..c0dd904483c7 100644
--- a/arch/sh/drivers/dma/dmabrg.c
+++ b/arch/sh/drivers/dma/dmabrg.c
@@ -189,8 +189,8 @@ static int __init dmabrg_init(void)
 	if (ret == 0)
 		return ret;
 
-	free_irq(DMABRGI1, 0);
-out1:	free_irq(DMABRGI0, 0);
+	free_irq(DMABRGI1, NULL);
+out1:	free_irq(DMABRGI0, NULL);
 out0:	kfree(dmabrg_handlers);
 	return ret;
 }
diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c
index fb8f14990743..5a6dab6e27d9 100644
--- a/arch/sh/drivers/pci/pci-sh7780.c
+++ b/arch/sh/drivers/pci/pci-sh7780.c
@@ -21,6 +21,13 @@
 #include <asm/mmu.h>
 #include <asm/sizes.h>
 
+#if defined(CONFIG_CPU_BIG_ENDIAN)
+# define PCICR_ENDIANNESS SH4_PCICR_BSWP
+#else
+# define PCICR_ENDIANNESS 0
+#endif
+
+
 static struct resource sh7785_pci_resources[] = {
 	{
 		.name	= "PCI IO",
@@ -254,7 +261,7 @@ static int __init sh7780_pci_init(void)
 	__raw_writel(PCIECR_ENBL, PCIECR);
 
 	/* Reset */
-	__raw_writel(SH4_PCICR_PREFIX | SH4_PCICR_PRST,
+	__raw_writel(SH4_PCICR_PREFIX | SH4_PCICR_PRST | PCICR_ENDIANNESS,
 		     chan->reg_base + SH4_PCICR);
 
 	/*
@@ -290,7 +297,8 @@ static int __init sh7780_pci_init(void)
 	 * Now throw it in to register initialization mode and
 	 * start the real work.
 	 */
-	__raw_writel(SH4_PCICR_PREFIX, chan->reg_base + SH4_PCICR);
+	__raw_writel(SH4_PCICR_PREFIX | PCICR_ENDIANNESS,
+		     chan->reg_base + SH4_PCICR);
 
 	memphys = __pa(memory_start);
 	memsize = roundup_pow_of_two(memory_end - memory_start);
@@ -380,7 +388,8 @@ static int __init sh7780_pci_init(void)
 	 * Initialization mode complete, release the control register and
 	 * enable round robin mode to stop device overruns/starvation.
 	 */
-	__raw_writel(SH4_PCICR_PREFIX | SH4_PCICR_CFIN | SH4_PCICR_FTO,
+	__raw_writel(SH4_PCICR_PREFIX | SH4_PCICR_CFIN | SH4_PCICR_FTO |
+		     PCICR_ENDIANNESS,
 		     chan->reg_base + SH4_PCICR);
 
 	ret = register_pci_controller(chan);
diff --git a/arch/sh/include/asm/atomic-irq.h b/arch/sh/include/asm/atomic-irq.h
index 467d9415a32e..9f7c56609e53 100644
--- a/arch/sh/include/asm/atomic-irq.h
+++ b/arch/sh/include/asm/atomic-irq.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_SH_ATOMIC_IRQ_H
 #define __ASM_SH_ATOMIC_IRQ_H
 
+#include <linux/irqflags.h>
+
 /*
  * To get proper branch prediction for the main line, we must branch
  * forward to code at the end of this object's .text section, then
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index 63a27dbc952e..37f2f4a55231 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -9,7 +9,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)	( (atomic_t) { (i) } )
 
diff --git a/arch/sh/include/asm/auxvec.h b/arch/sh/include/asm/auxvec.h
index 483effd65e00..8bcc51af9367 100644
--- a/arch/sh/include/asm/auxvec.h
+++ b/arch/sh/include/asm/auxvec.h
@@ -33,4 +33,6 @@
 #define AT_L1D_CACHESHAPE	35
 #define AT_L2_CACHESHAPE	36
 
+#define AT_VECTOR_SIZE_ARCH 5 /* entries in ARCH_DLINFO */
+
 #endif /* __ASM_SH_AUXVEC_H */
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
new file mode 100644
index 000000000000..72c103dae300
--- /dev/null
+++ b/arch/sh/include/asm/barrier.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (C) 1999, 2000  Niibe Yutaka  &  Kaz Kojima
+ * Copyright (C) 2002 Paul Mundt
+ */
+#ifndef __ASM_SH_BARRIER_H
+#define __ASM_SH_BARRIER_H
+
+#if defined(CONFIG_CPU_SH4A) || defined(CONFIG_CPU_SH5)
+#include <asm/cache_insns.h>
+#endif
+
+/*
+ * A brief note on ctrl_barrier(), the control register write barrier.
+ *
+ * Legacy SH cores typically require a sequence of 8 nops after
+ * modification of a control register in order for the changes to take
+ * effect. On newer cores (like the sh4a and sh5) this is accomplished
+ * with icbi.
+ *
+ * Also note that on sh4a in the icbi case we can forego a synco for the
+ * write barrier, as it's not necessary for control registers.
+ *
+ * Historically we have only done this type of barrier for the MMUCR, but
+ * it's also necessary for the CCR, so we make it generic here instead.
+ */
+#if defined(CONFIG_CPU_SH4A) || defined(CONFIG_CPU_SH5)
+#define mb()		__asm__ __volatile__ ("synco": : :"memory")
+#define rmb()		mb()
+#define wmb()		__asm__ __volatile__ ("synco": : :"memory")
+#define ctrl_barrier()	__icbi(PAGE_OFFSET)
+#define read_barrier_depends()	do { } while(0)
+#else
+#define mb()		__asm__ __volatile__ ("": : :"memory")
+#define rmb()		mb()
+#define wmb()		__asm__ __volatile__ ("": : :"memory")
+#define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
+#define read_barrier_depends()	do { } while(0)
+#endif
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
+#define smp_read_barrier_depends()	read_barrier_depends()
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while(0)
+#endif
+
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+
+#endif /* __ASM_SH_BARRIER_H */
diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h
index 90fa3e48b4d6..ea8706d94f08 100644
--- a/arch/sh/include/asm/bitops.h
+++ b/arch/sh/include/asm/bitops.h
@@ -7,7 +7,6 @@
 #error only <linux/bitops.h> can be included directly
 #endif
 
-#include <asm/system.h>
 /* For __swab32 */
 #include <asm/byteorder.h>
 
diff --git a/arch/sh/include/asm/bl_bit.h b/arch/sh/include/asm/bl_bit.h
new file mode 100644
index 000000000000..45e6b9fc37a0
--- /dev/null
+++ b/arch/sh/include/asm/bl_bit.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_SH_BL_BIT_H
+#define __ASM_SH_BL_BIT_H
+
+#ifdef CONFIG_SUPERH32
+# include "bl_bit_32.h"
+#else
+# include "bl_bit_64.h"
+#endif
+
+#endif /* __ASM_SH_BL_BIT_H */
diff --git a/arch/sh/include/asm/bl_bit_32.h b/arch/sh/include/asm/bl_bit_32.h
new file mode 100644
index 000000000000..fd21eee62149
--- /dev/null
+++ b/arch/sh/include/asm/bl_bit_32.h
@@ -0,0 +1,33 @@
+#ifndef __ASM_SH_BL_BIT_32_H
+#define __ASM_SH_BL_BIT_32_H
+
+static inline void set_bl_bit(void)
+{
+	unsigned long __dummy0, __dummy1;
+
+	__asm__ __volatile__ (
+		"stc	sr, %0\n\t"
+		"or	%2, %0\n\t"
+		"and	%3, %0\n\t"
+		"ldc	%0, sr\n\t"
+		: "=&r" (__dummy0), "=r" (__dummy1)
+		: "r" (0x10000000), "r" (0xffffff0f)
+		: "memory"
+	);
+}
+
+static inline void clear_bl_bit(void)
+{
+	unsigned long __dummy0, __dummy1;
+
+	__asm__ __volatile__ (
+		"stc	sr, %0\n\t"
+		"and	%2, %0\n\t"
+		"ldc	%0, sr\n\t"
+		: "=&r" (__dummy0), "=r" (__dummy1)
+		: "1" (~0x10000000)
+		: "memory"
+	);
+}
+
+#endif /* __ASM_SH_BL_BIT_32_H */
diff --git a/arch/sh/include/asm/bl_bit_64.h b/arch/sh/include/asm/bl_bit_64.h
new file mode 100644
index 000000000000..6cc8711af435
--- /dev/null
+++ b/arch/sh/include/asm/bl_bit_64.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_BL_BIT_64_H
+#define __ASM_SH_BL_BIT_64_H
+
+#include <asm/processor.h>
+
+#define SR_BL_LL	0x0000000010000000LL
+
+static inline void set_bl_bit(void)
+{
+	unsigned long long __dummy0, __dummy1 = SR_BL_LL;
+
+	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
+			     "or	%0, %1, %0\n\t"
+			     "putcon	%0, " __SR "\n\t"
+			     : "=&r" (__dummy0)
+			     : "r" (__dummy1));
+
+}
+
+static inline void clear_bl_bit(void)
+{
+	unsigned long long __dummy0, __dummy1 = ~SR_BL_LL;
+
+	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
+			     "and	%0, %1, %0\n\t"
+			     "putcon	%0, " __SR "\n\t"
+			     : "=&r" (__dummy0)
+			     : "r" (__dummy1));
+}
+
+#endif /* __ASM_SH_BL_BIT_64_H */
diff --git a/arch/sh/include/asm/bug.h b/arch/sh/include/asm/bug.h
index 6323f864d111..2b87d86bfc41 100644
--- a/arch/sh/include/asm/bug.h
+++ b/arch/sh/include/asm/bug.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_SH_BUG_H
 #define __ASM_SH_BUG_H
 
+#include <linux/linkage.h>
+
 #define TRAPA_BUG_OPCODE	0xc33e	/* trapa #0x3e */
 #define BUGFLAG_UNWINDER	(1 << 1)
 
@@ -107,4 +109,7 @@ do {							\
 
 #include <asm-generic/bug.h>
 
+struct pt_regs;
+extern void die(const char *str, struct pt_regs *regs, long err) __attribute__ ((noreturn));
+
 #endif /* __ASM_SH_BUG_H */
diff --git a/arch/sh/include/asm/cache_insns.h b/arch/sh/include/asm/cache_insns.h
new file mode 100644
index 000000000000..d25fbe53090d
--- /dev/null
+++ b/arch/sh/include/asm/cache_insns.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_SH_CACHE_INSNS_H
+#define __ASM_SH_CACHE_INSNS_H
+
+
+#ifdef CONFIG_SUPERH32
+# include "cache_insns_32.h"
+#else
+# include "cache_insns_64.h"
+#endif
+
+#endif /* __ASM_SH_CACHE_INSNS_H */
diff --git a/arch/sh/include/asm/cache_insns_32.h b/arch/sh/include/asm/cache_insns_32.h
new file mode 100644
index 000000000000..b92fe5416092
--- /dev/null
+++ b/arch/sh/include/asm/cache_insns_32.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SH_CACHE_INSNS_32_H
+#define __ASM_SH_CACHE_INSNS_32_H
+
+#include <linux/types.h>
+
+#if defined(CONFIG_CPU_SH4A)
+#define __icbi(addr)	__asm__ __volatile__ ( "icbi @%0\n\t" : : "r" (addr))
+#else
+#define __icbi(addr)	mb()
+#endif
+
+#define __ocbp(addr)	__asm__ __volatile__ ( "ocbp @%0\n\t" : : "r" (addr))
+#define __ocbi(addr)	__asm__ __volatile__ ( "ocbi @%0\n\t" : : "r" (addr))
+#define __ocbwb(addr)	__asm__ __volatile__ ( "ocbwb @%0\n\t" : : "r" (addr))
+
+static inline reg_size_t register_align(void *val)
+{
+	return (unsigned long)(signed long)val;
+}
+
+#endif /* __ASM_SH_CACHE_INSNS_32_H */
diff --git a/arch/sh/include/asm/cache_insns_64.h b/arch/sh/include/asm/cache_insns_64.h
new file mode 100644
index 000000000000..70b6357eaf1a
--- /dev/null
+++ b/arch/sh/include/asm/cache_insns_64.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_CACHE_INSNS_64_H
+#define __ASM_SH_CACHE_INSNS_64_H
+
+#define __icbi(addr)	__asm__ __volatile__ ( "icbi %0, 0\n\t" : : "r" (addr))
+#define __ocbp(addr)	__asm__ __volatile__ ( "ocbp %0, 0\n\t" : : "r" (addr))
+#define __ocbi(addr)	__asm__ __volatile__ ( "ocbi %0, 0\n\t" : : "r" (addr))
+#define __ocbwb(addr)	__asm__ __volatile__ ( "ocbwb %0, 0\n\t" : : "r" (addr))
+
+static inline reg_size_t register_align(void *val)
+{
+	return (unsigned long long)(signed long long)(signed long)val;
+}
+
+#endif /* __ASM_SH_CACHE_INSNS_64_H */
diff --git a/arch/sh/include/asm/cmpxchg-irq.h b/arch/sh/include/asm/cmpxchg-irq.h
index 43049ec0554b..bd11f630414a 100644
--- a/arch/sh/include/asm/cmpxchg-irq.h
+++ b/arch/sh/include/asm/cmpxchg-irq.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_SH_CMPXCHG_IRQ_H
 #define __ASM_SH_CMPXCHG_IRQ_H
 
+#include <linux/irqflags.h>
+
 static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
 {
 	unsigned long flags, retval;
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..f6bd1406b897
--- /dev/null
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -0,0 +1,70 @@
+#ifndef __ASM_SH_CMPXCHG_H
+#define __ASM_SH_CMPXCHG_H
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#if defined(CONFIG_GUSA_RB)
+#include <asm/cmpxchg-grb.h>
+#elif defined(CONFIG_CPU_SH4A)
+#include <asm/cmpxchg-llsc.h>
+#else
+#include <asm/cmpxchg-irq.h>
+#endif
+
+extern void __xchg_called_with_bad_pointer(void);
+
+#define __xchg(ptr, x, size)				\
+({							\
+	unsigned long __xchg__res;			\
+	volatile void *__xchg_ptr = (ptr);		\
+	switch (size) {					\
+	case 4:						\
+		__xchg__res = xchg_u32(__xchg_ptr, x);	\
+		break;					\
+	case 1:						\
+		__xchg__res = xchg_u8(__xchg_ptr, x);	\
+		break;					\
+	default:					\
+		__xchg_called_with_bad_pointer();	\
+		__xchg__res = x;			\
+		break;					\
+	}						\
+							\
+	__xchg__res;					\
+})
+
+#define xchg(ptr,x)	\
+	((__typeof__(*(ptr)))__xchg((ptr),(unsigned long)(x), sizeof(*(ptr))))
+
+/* This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg(). */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
+		unsigned long new, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32(ptr, old, new);
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr,o,n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+#endif /* __ASM_SH_CMPXCHG_H */
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
index 1a73c3e759a7..8bd965e00a15 100644
--- a/arch/sh/include/asm/dma-mapping.h
+++ b/arch/sh/include/asm/dma-mapping.h
@@ -52,25 +52,31 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return dma_addr == 0;
 }
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t gfp)
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t gfp,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
 		return memory;
-	if (!ops->alloc_coherent)
+	if (!ops->alloc)
 		return NULL;
 
-	memory = ops->alloc_coherent(dev, size, dma_handle, gfp);
+	memory = ops->alloc(dev, size, dma_handle, gfp, attrs);
 	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
 
 	return memory;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
@@ -78,14 +84,16 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 		return;
 
 	debug_dma_free_coherent(dev, size, vaddr, dma_handle);
-	if (ops->free_coherent)
-		ops->free_coherent(dev, size, vaddr, dma_handle);
+	if (ops->free)
+		ops->free(dev, size, vaddr, dma_handle, attrs);
 }
 
 /* arch/sh/mm/consistent.c */
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag);
+					dma_addr_t *dma_addr, gfp_t flag,
+					struct dma_attrs *attrs);
 extern void dma_generic_free_coherent(struct device *dev, size_t size,
-				      void *vaddr, dma_addr_t dma_handle);
+				      void *vaddr, dma_addr_t dma_handle,
+				      struct dma_attrs *attrs);
 
 #endif /* __ASM_SH_DMA_MAPPING_H */
diff --git a/arch/sh/include/asm/exec.h b/arch/sh/include/asm/exec.h
new file mode 100644
index 000000000000..69486a9497f7
--- /dev/null
+++ b/arch/sh/include/asm/exec.h
@@ -0,0 +1,10 @@
+/*
+ * Copyright (C) 1999, 2000  Niibe Yutaka  &  Kaz Kojima
+ * Copyright (C) 2002 Paul Mundt
+ */
+#ifndef __ASM_SH_EXEC_H
+#define __ASM_SH_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __ASM_SH_EXEC_H */
diff --git a/arch/sh/include/asm/futex-irq.h b/arch/sh/include/asm/futex-irq.h
index 6cb9f193a95e..63d33129ea23 100644
--- a/arch/sh/include/asm/futex-irq.h
+++ b/arch/sh/include/asm/futex-irq.h
@@ -1,7 +1,6 @@
 #ifndef __ASM_SH_FUTEX_IRQ_H
 #define __ASM_SH_FUTEX_IRQ_H
 
-#include <asm/system.h>
 
 static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr,
 					   int *oldval)
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 28c5aa58bb45..ec464a6b95fe 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -14,7 +14,6 @@
  */
 #include <linux/errno.h>
 #include <asm/cache.h>
-#include <asm/system.h>
 #include <asm/addrspace.h>
 #include <asm/machvec.h>
 #include <asm/pgtable.h>
@@ -24,6 +23,7 @@
 #define __IO_PREFIX     generic
 #include <asm/io_generic.h>
 #include <asm/io_trapped.h>
+#include <mach/mangle-port.h>
 
 #define __raw_writeb(v,a)	(__chk_io_ptr(a), *(volatile u8  __force *)(a) = (v))
 #define __raw_writew(v,a)	(__chk_io_ptr(a), *(volatile u16 __force *)(a) = (v))
@@ -35,21 +35,15 @@
 #define __raw_readl(a)		(__chk_io_ptr(a), *(volatile u32 __force *)(a))
 #define __raw_readq(a)		(__chk_io_ptr(a), *(volatile u64 __force *)(a))
 
-#define readb_relaxed(c)	({ u8  __v = __raw_readb(c); __v; })
-#define readw_relaxed(c)	({ u16 __v = le16_to_cpu((__force __le16) \
-					__raw_readw(c)); __v; })
-#define readl_relaxed(c)	({ u32 __v = le32_to_cpu((__force __le32) \
-					__raw_readl(c)); __v; })
-#define readq_relaxed(c)	({ u64 __v = le64_to_cpu((__force __le64) \
-					__raw_readq(c)); __v; })
-
-#define writeb_relaxed(v,c)	((void)__raw_writeb(v,c))
-#define writew_relaxed(v,c)	((void)__raw_writew((__force u16) \
-					cpu_to_le16(v),c))
-#define writel_relaxed(v,c)	((void)__raw_writel((__force u32) \
-					cpu_to_le32(v),c))
-#define writeq_relaxed(v,c)	((void)__raw_writeq((__force u64) \
-					cpu_to_le64(v),c))
+#define readb_relaxed(c)	({ u8  __v = ioswabb(__raw_readb(c)); __v; })
+#define readw_relaxed(c)	({ u16 __v = ioswabw(__raw_readw(c)); __v; })
+#define readl_relaxed(c)	({ u32 __v = ioswabl(__raw_readl(c)); __v; })
+#define readq_relaxed(c)	({ u64 __v = ioswabq(__raw_readq(c)); __v; })
+
+#define writeb_relaxed(v,c)	((void)__raw_writeb((__force  u8)ioswabb(v),c))
+#define writew_relaxed(v,c)	((void)__raw_writew((__force u16)ioswabw(v),c))
+#define writel_relaxed(v,c)	((void)__raw_writel((__force u32)ioswabl(v),c))
+#define writeq_relaxed(v,c)	((void)__raw_writeq((__force u64)ioswabq(v),c))
 
 #define readb(a)		({ u8  r_ = readb_relaxed(a); rmb(); r_; })
 #define readw(a)		({ u16 r_ = readw_relaxed(a); rmb(); r_; })
diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h
index 45d08b6a5ef7..2a62017eb275 100644
--- a/arch/sh/include/asm/irq.h
+++ b/arch/sh/include/asm/irq.h
@@ -21,17 +21,6 @@
 #define NO_IRQ_IGNORE		((unsigned int)-1)
 
 /*
- * Convert back and forth between INTEVT and IRQ values.
- */
-#ifdef CONFIG_CPU_HAS_INTEVT
-#define evt2irq(evt)		(((evt) >> 5) - 16)
-#define irq2evt(irq)		(((irq) + 16) << 5)
-#else
-#define evt2irq(evt)		(evt)
-#define irq2evt(irq)		(irq)
-#endif
-
-/*
  * Simple Mask Register Support
  */
 extern void make_maskreg_irq(unsigned int irq);
diff --git a/arch/sh/include/asm/posix_types_32.h b/arch/sh/include/asm/posix_types_32.h
index 6a9ceaaf1aea..abda58467ece 100644
--- a/arch/sh/include/asm/posix_types_32.h
+++ b/arch/sh/include/asm/posix_types_32.h
@@ -12,11 +12,6 @@ typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
 #define __kernel_gid_t __kernel_gid_t
 
-typedef unsigned int	__kernel_uid32_t;
-#define __kernel_uid32_t __kernel_uid32_t
-typedef unsigned int	__kernel_gid32_t;
-#define __kernel_gid32_t __kernel_gid32_t
-
 typedef unsigned short	__kernel_old_uid_t;
 #define __kernel_old_uid_t __kernel_old_uid_t
 typedef unsigned short	__kernel_old_gid_t;
diff --git a/arch/sh/include/asm/posix_types_64.h b/arch/sh/include/asm/posix_types_64.h
index 8cd11485c06b..fcda07b4a616 100644
--- a/arch/sh/include/asm/posix_types_64.h
+++ b/arch/sh/include/asm/posix_types_64.h
@@ -17,10 +17,6 @@ typedef int		__kernel_ssize_t;
 #define __kernel_ssize_t __kernel_ssize_t
 typedef int		__kernel_ptrdiff_t;
 #define __kernel_ptrdiff_t __kernel_ptrdiff_t
-typedef unsigned int	__kernel_uid32_t;
-#define __kernel_uid32_t __kernel_uid32_t
-typedef unsigned int	__kernel_gid32_t;
-#define __kernel_gid32_t __kernel_gid32_t
 
 typedef unsigned short	__kernel_old_uid_t;
 #define __kernel_old_uid_t __kernel_old_uid_t
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 9c7bdfcaebbd..a229c393826a 100644
--- a/arch/sh/include/asm/processor.h
+++ b/arch/sh/include/asm/processor.h
@@ -101,6 +101,10 @@ extern struct sh_cpuinfo cpu_data[];
 #define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
 #define cpu_relax()	barrier()
 
+void default_idle(void);
+void cpu_idle_wait(void);
+void stop_this_cpu(void *);
+
 /* Forward decl */
 struct seq_operations;
 struct task_struct;
@@ -161,6 +165,17 @@ int vsyscall_init(void);
 #define vsyscall_init() do { } while (0)
 #endif
 
+/*
+ * SH-2A has both 16 and 32-bit opcodes, do lame encoding checks.
+ */
+#ifdef CONFIG_CPU_SH2A
+extern unsigned int instruction_size(unsigned int insn);
+#elif defined(CONFIG_SUPERH32)
+#define instruction_size(insn)	(2)
+#else
+#define instruction_size(insn)	(4)
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #ifdef CONFIG_SUPERH32
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index 2d3679b2447f..c7b7e1ed194a 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -37,7 +37,6 @@
 #include <linux/thread_info.h>
 #include <asm/addrspace.h>
 #include <asm/page.h>
-#include <asm/system.h>
 
 #define user_mode(regs)			(((regs)->sr & 0x40000000)==0)
 #define kernel_stack_pointer(_regs)	((unsigned long)(_regs)->regs[15])
diff --git a/arch/sh/include/asm/setup.h b/arch/sh/include/asm/setup.h
index 01fa17a3d759..465a22df8fd0 100644
--- a/arch/sh/include/asm/setup.h
+++ b/arch/sh/include/asm/setup.h
@@ -20,6 +20,7 @@
 
 void sh_mv_setup(void);
 void check_for_initrd(void);
+void per_cpu_trap_init(void);
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/sh/include/asm/switch_to.h b/arch/sh/include/asm/switch_to.h
new file mode 100644
index 000000000000..62b1941813e3
--- /dev/null
+++ b/arch/sh/include/asm/switch_to.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_SWITCH_TO_H
+#define __ASM_SH_SWITCH_TO_H
+
+#ifdef CONFIG_SUPERH32
+# include "switch_to_32.h"
+#else
+# include "switch_to_64.h"
+#endif
+
+#endif /* __ASM_SH_SWITCH_TO_H */
diff --git a/arch/sh/include/asm/system_32.h b/arch/sh/include/asm/switch_to_32.h
index a4ad1cd9bc4d..0c065513e7ac 100644
--- a/arch/sh/include/asm/system_32.h
+++ b/arch/sh/include/asm/switch_to_32.h
@@ -1,8 +1,5 @@
-#ifndef __ASM_SH_SYSTEM_32_H
-#define __ASM_SH_SYSTEM_32_H
-
-#include <linux/types.h>
-#include <asm/mmu.h>
+#ifndef __ASM_SH_SWITCH_TO_32_H
+#define __ASM_SH_SWITCH_TO_32_H
 
 #ifdef CONFIG_SH_DSP
 
@@ -32,7 +29,6 @@ do {									\
 		: : "r" (__ts2));					\
 } while (0)
 
-
 #define __save_dsp(tsk)							\
 do {									\
 	register u32 *__ts2 __asm__ ("r2") =				\
@@ -64,16 +60,6 @@ do {									\
 #define __restore_dsp(tsk)	do { } while (0)
 #endif
 
-#if defined(CONFIG_CPU_SH4A)
-#define __icbi(addr)	__asm__ __volatile__ ( "icbi @%0\n\t" : : "r" (addr))
-#else
-#define __icbi(addr)	mb()
-#endif
-
-#define __ocbp(addr)	__asm__ __volatile__ ( "ocbp @%0\n\t" : : "r" (addr))
-#define __ocbi(addr)	__asm__ __volatile__ ( "ocbi @%0\n\t" : : "r" (addr))
-#define __ocbwb(addr)	__asm__ __volatile__ ( "ocbwb @%0\n\t" : : "r" (addr))
-
 struct task_struct *__switch_to(struct task_struct *prev,
 				struct task_struct *next);
 
@@ -145,92 +131,4 @@ do {								\
 		__restore_dsp(prev);				\
 } while (0)
 
-#ifdef CONFIG_CPU_HAS_SR_RB
-#define lookup_exception_vector()	\
-({					\
-	unsigned long _vec;		\
-					\
-	__asm__ __volatile__ (		\
-		"stc r2_bank, %0\n\t"	\
-		: "=r" (_vec)		\
-	);				\
-					\
-	_vec;				\
-})
-#else
-#define lookup_exception_vector()	\
-({					\
-	unsigned long _vec;		\
-	__asm__ __volatile__ (		\
-		"mov r4, %0\n\t"	\
-		: "=r" (_vec)		\
-	);				\
-					\
-	_vec;				\
-})
-#endif
-
-static inline reg_size_t register_align(void *val)
-{
-	return (unsigned long)(signed long)val;
-}
-
-int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
-			    struct mem_access *ma, int, unsigned long address);
-
-static inline void trigger_address_error(void)
-{
-	__asm__ __volatile__ (
-		"ldc %0, sr\n\t"
-		"mov.l @%1, %0"
-		:
-		: "r" (0x10000000), "r" (0x80000001)
-	);
-}
-
-asmlinkage void do_address_error(struct pt_regs *regs,
-				 unsigned long writeaccess,
-				 unsigned long address);
-asmlinkage void do_divide_error(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs);
-asmlinkage void do_reserved_inst(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs);
-asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs);
-asmlinkage void do_exception_error(unsigned long r4, unsigned long r5,
-				   unsigned long r6, unsigned long r7,
-				   struct pt_regs __regs);
-
-static inline void set_bl_bit(void)
-{
-	unsigned long __dummy0, __dummy1;
-
-	__asm__ __volatile__ (
-		"stc	sr, %0\n\t"
-		"or	%2, %0\n\t"
-		"and	%3, %0\n\t"
-		"ldc	%0, sr\n\t"
-		: "=&r" (__dummy0), "=r" (__dummy1)
-		: "r" (0x10000000), "r" (0xffffff0f)
-		: "memory"
-	);
-}
-
-static inline void clear_bl_bit(void)
-{
-	unsigned long __dummy0, __dummy1;
-
-	__asm__ __volatile__ (
-		"stc	sr, %0\n\t"
-		"and	%2, %0\n\t"
-		"ldc	%0, sr\n\t"
-		: "=&r" (__dummy0), "=r" (__dummy1)
-		: "1" (~0x10000000)
-		: "memory"
-	);
-}
-
-#endif /* __ASM_SH_SYSTEM_32_H */
+#endif /* __ASM_SH_SWITCH_TO_32_H */
diff --git a/arch/sh/include/asm/switch_to_64.h b/arch/sh/include/asm/switch_to_64.h
new file mode 100644
index 000000000000..ba3129d6bc21
--- /dev/null
+++ b/arch/sh/include/asm/switch_to_64.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_SWITCH_TO_64_H
+#define __ASM_SH_SWITCH_TO_64_H
+
+struct thread_struct;
+struct task_struct;
+
+/*
+ *	switch_to() should switch tasks to task nr n, first
+ */
+struct task_struct *sh64_switch_to(struct task_struct *prev,
+				   struct thread_struct *prev_thread,
+				   struct task_struct *next,
+				   struct thread_struct *next_thread);
+
+#define switch_to(prev,next,last)				\
+do {								\
+	if (last_task_used_math != next) {			\
+		struct pt_regs *regs = next->thread.uregs;	\
+		if (regs) regs->sr |= SR_FD;			\
+	}							\
+	last = sh64_switch_to(prev, &prev->thread, next,	\
+			      &next->thread);			\
+} while (0)
+
+
+#endif /* __ASM_SH_SWITCH_TO_64_H */
diff --git a/arch/sh/include/asm/system.h b/arch/sh/include/asm/system.h
deleted file mode 100644
index 10c8b1823a18..000000000000
--- a/arch/sh/include/asm/system.h
+++ /dev/null
@@ -1,184 +0,0 @@
-#ifndef __ASM_SH_SYSTEM_H
-#define __ASM_SH_SYSTEM_H
-
-/*
- * Copyright (C) 1999, 2000  Niibe Yutaka  &  Kaz Kojima
- * Copyright (C) 2002 Paul Mundt
- */
-
-#include <linux/irqflags.h>
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <asm/types.h>
-#include <asm/uncached.h>
-
-#define AT_VECTOR_SIZE_ARCH 5 /* entries in ARCH_DLINFO */
-
-/*
- * A brief note on ctrl_barrier(), the control register write barrier.
- *
- * Legacy SH cores typically require a sequence of 8 nops after
- * modification of a control register in order for the changes to take
- * effect. On newer cores (like the sh4a and sh5) this is accomplished
- * with icbi.
- *
- * Also note that on sh4a in the icbi case we can forego a synco for the
- * write barrier, as it's not necessary for control registers.
- *
- * Historically we have only done this type of barrier for the MMUCR, but
- * it's also necessary for the CCR, so we make it generic here instead.
- */
-#if defined(CONFIG_CPU_SH4A) || defined(CONFIG_CPU_SH5)
-#define mb()		__asm__ __volatile__ ("synco": : :"memory")
-#define rmb()		mb()
-#define wmb()		__asm__ __volatile__ ("synco": : :"memory")
-#define ctrl_barrier()	__icbi(PAGE_OFFSET)
-#define read_barrier_depends()	do { } while(0)
-#else
-#define mb()		__asm__ __volatile__ ("": : :"memory")
-#define rmb()		mb()
-#define wmb()		__asm__ __volatile__ ("": : :"memory")
-#define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
-#define read_barrier_depends()	do { } while(0)
-#endif
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
-#endif
-
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-
-#ifdef CONFIG_GUSA_RB
-#include <asm/cmpxchg-grb.h>
-#elif defined(CONFIG_CPU_SH4A)
-#include <asm/cmpxchg-llsc.h>
-#else
-#include <asm/cmpxchg-irq.h>
-#endif
-
-extern void __xchg_called_with_bad_pointer(void);
-
-#define __xchg(ptr, x, size)				\
-({							\
-	unsigned long __xchg__res;			\
-	volatile void *__xchg_ptr = (ptr);		\
-	switch (size) {					\
-	case 4:						\
-		__xchg__res = xchg_u32(__xchg_ptr, x);	\
-		break;					\
-	case 1:						\
-		__xchg__res = xchg_u8(__xchg_ptr, x);	\
-		break;					\
-	default:					\
-		__xchg_called_with_bad_pointer();	\
-		__xchg__res = x;			\
-		break;					\
-	}						\
-							\
-	__xchg__res;					\
-})
-
-#define xchg(ptr,x)	\
-	((__typeof__(*(ptr)))__xchg((ptr),(unsigned long)(x), sizeof(*(ptr))))
-
-/* This function doesn't exist, so you'll get a linker error
- * if something tries to do an invalid cmpxchg(). */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-#define __HAVE_ARCH_CMPXCHG 1
-
-static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
-		unsigned long new, int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32(ptr, old, new);
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#define cmpxchg(ptr,o,n)						 \
-  ({									 \
-     __typeof__(*(ptr)) _o_ = (o);					 \
-     __typeof__(*(ptr)) _n_ = (n);					 \
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
-				    (unsigned long)_n_, sizeof(*(ptr))); \
-  })
-
-struct pt_regs;
-
-extern void die(const char *str, struct pt_regs *regs, long err) __attribute__ ((noreturn));
-void free_initmem(void);
-void free_initrd_mem(unsigned long start, unsigned long end);
-
-extern void *set_exception_table_vec(unsigned int vec, void *handler);
-
-static inline void *set_exception_table_evt(unsigned int evt, void *handler)
-{
-	return set_exception_table_vec(evt >> 5, handler);
-}
-
-/*
- * SH-2A has both 16 and 32-bit opcodes, do lame encoding checks.
- */
-#ifdef CONFIG_CPU_SH2A
-extern unsigned int instruction_size(unsigned int insn);
-#elif defined(CONFIG_SUPERH32)
-#define instruction_size(insn)	(2)
-#else
-#define instruction_size(insn)	(4)
-#endif
-
-void per_cpu_trap_init(void);
-void default_idle(void);
-void cpu_idle_wait(void);
-void stop_this_cpu(void *);
-
-#ifdef CONFIG_SUPERH32
-#define BUILD_TRAP_HANDLER(name)					\
-asmlinkage void name##_trap_handler(unsigned long r4, unsigned long r5,	\
-				    unsigned long r6, unsigned long r7,	\
-				    struct pt_regs __regs)
-
-#define TRAP_HANDLER_DECL				\
-	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);	\
-	unsigned int vec = regs->tra;			\
-	(void)vec;
-#else
-#define BUILD_TRAP_HANDLER(name)	\
-asmlinkage void name##_trap_handler(unsigned int vec, struct pt_regs *regs)
-#define TRAP_HANDLER_DECL
-#endif
-
-BUILD_TRAP_HANDLER(address_error);
-BUILD_TRAP_HANDLER(debug);
-BUILD_TRAP_HANDLER(bug);
-BUILD_TRAP_HANDLER(breakpoint);
-BUILD_TRAP_HANDLER(singlestep);
-BUILD_TRAP_HANDLER(fpu_error);
-BUILD_TRAP_HANDLER(fpu_state_restore);
-BUILD_TRAP_HANDLER(nmi);
-
-#define arch_align_stack(x) (x)
-
-struct mem_access {
-	unsigned long (*from)(void *dst, const void __user *src, unsigned long cnt);
-	unsigned long (*to)(void __user *dst, const void *src, unsigned long cnt);
-};
-
-#ifdef CONFIG_SUPERH32
-# include "system_32.h"
-#else
-# include "system_64.h"
-#endif
-
-#endif
diff --git a/arch/sh/include/asm/system_64.h b/arch/sh/include/asm/system_64.h
deleted file mode 100644
index 8593bc8d1a4e..000000000000
--- a/arch/sh/include/asm/system_64.h
+++ /dev/null
@@ -1,79 +0,0 @@
-#ifndef __ASM_SH_SYSTEM_64_H
-#define __ASM_SH_SYSTEM_64_H
-
-/*
- * include/asm-sh/system_64.h
- *
- * Copyright (C) 2000, 2001  Paolo Alberelli
- * Copyright (C) 2003  Paul Mundt
- * Copyright (C) 2004  Richard Curnow
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <cpu/registers.h>
-#include <asm/processor.h>
-
-/*
- *	switch_to() should switch tasks to task nr n, first
- */
-struct thread_struct;
-struct task_struct *sh64_switch_to(struct task_struct *prev,
-				   struct thread_struct *prev_thread,
-				   struct task_struct *next,
-				   struct thread_struct *next_thread);
-
-#define switch_to(prev,next,last)				\
-do {								\
-	if (last_task_used_math != next) {			\
-		struct pt_regs *regs = next->thread.uregs;	\
-		if (regs) regs->sr |= SR_FD;			\
-	}							\
-	last = sh64_switch_to(prev, &prev->thread, next,	\
-			      &next->thread);			\
-} while (0)
-
-#define __icbi(addr)	__asm__ __volatile__ ( "icbi %0, 0\n\t" : : "r" (addr))
-#define __ocbp(addr)	__asm__ __volatile__ ( "ocbp %0, 0\n\t" : : "r" (addr))
-#define __ocbi(addr)	__asm__ __volatile__ ( "ocbi %0, 0\n\t" : : "r" (addr))
-#define __ocbwb(addr)	__asm__ __volatile__ ( "ocbwb %0, 0\n\t" : : "r" (addr))
-
-static inline reg_size_t register_align(void *val)
-{
-	return (unsigned long long)(signed long long)(signed long)val;
-}
-
-extern void phys_stext(void);
-
-static inline void trigger_address_error(void)
-{
-	phys_stext();
-}
-
-#define SR_BL_LL	0x0000000010000000LL
-
-static inline void set_bl_bit(void)
-{
-	unsigned long long __dummy0, __dummy1 = SR_BL_LL;
-
-	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
-			     "or	%0, %1, %0\n\t"
-			     "putcon	%0, " __SR "\n\t"
-			     : "=&r" (__dummy0)
-			     : "r" (__dummy1));
-
-}
-
-static inline void clear_bl_bit(void)
-{
-	unsigned long long __dummy0, __dummy1 = ~SR_BL_LL;
-
-	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
-			     "and	%0, %1, %0\n\t"
-			     "putcon	%0, " __SR "\n\t"
-			     : "=&r" (__dummy0)
-			     : "r" (__dummy1));
-}
-
-#endif /* __ASM_SH_SYSTEM_64_H */
diff --git a/arch/sh/include/asm/traps.h b/arch/sh/include/asm/traps.h
new file mode 100644
index 000000000000..afd9df8d0641
--- /dev/null
+++ b/arch/sh/include/asm/traps.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SH_TRAPS_H
+#define __ASM_SH_TRAPS_H
+
+#include <linux/compiler.h>
+
+#ifdef CONFIG_SUPERH32
+# include "traps_32.h"
+#else
+# include "traps_64.h"
+#endif
+
+BUILD_TRAP_HANDLER(address_error);
+BUILD_TRAP_HANDLER(debug);
+BUILD_TRAP_HANDLER(bug);
+BUILD_TRAP_HANDLER(breakpoint);
+BUILD_TRAP_HANDLER(singlestep);
+BUILD_TRAP_HANDLER(fpu_error);
+BUILD_TRAP_HANDLER(fpu_state_restore);
+BUILD_TRAP_HANDLER(nmi);
+
+#endif /* __ASM_SH_TRAPS_H */
diff --git a/arch/sh/include/asm/traps_32.h b/arch/sh/include/asm/traps_32.h
new file mode 100644
index 000000000000..cfd55ff9dff2
--- /dev/null
+++ b/arch/sh/include/asm/traps_32.h
@@ -0,0 +1,68 @@
+#ifndef __ASM_SH_TRAPS_32_H
+#define __ASM_SH_TRAPS_32_H
+
+#include <linux/types.h>
+#include <asm/mmu.h>
+
+#ifdef CONFIG_CPU_HAS_SR_RB
+#define lookup_exception_vector()	\
+({					\
+	unsigned long _vec;		\
+					\
+	__asm__ __volatile__ (		\
+		"stc r2_bank, %0\n\t"	\
+		: "=r" (_vec)		\
+	);				\
+					\
+	_vec;				\
+})
+#else
+#define lookup_exception_vector()	\
+({					\
+	unsigned long _vec;		\
+	__asm__ __volatile__ (		\
+		"mov r4, %0\n\t"	\
+		: "=r" (_vec)		\
+	);				\
+					\
+	_vec;				\
+})
+#endif
+
+static inline void trigger_address_error(void)
+{
+	__asm__ __volatile__ (
+		"ldc %0, sr\n\t"
+		"mov.l @%1, %0"
+		:
+		: "r" (0x10000000), "r" (0x80000001)
+	);
+}
+
+asmlinkage void do_address_error(struct pt_regs *regs,
+				 unsigned long writeaccess,
+				 unsigned long address);
+asmlinkage void do_divide_error(unsigned long r4, unsigned long r5,
+				unsigned long r6, unsigned long r7,
+				struct pt_regs __regs);
+asmlinkage void do_reserved_inst(unsigned long r4, unsigned long r5,
+				unsigned long r6, unsigned long r7,
+				struct pt_regs __regs);
+asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5,
+				unsigned long r6, unsigned long r7,
+				struct pt_regs __regs);
+asmlinkage void do_exception_error(unsigned long r4, unsigned long r5,
+				   unsigned long r6, unsigned long r7,
+				   struct pt_regs __regs);
+
+#define BUILD_TRAP_HANDLER(name)					\
+asmlinkage void name##_trap_handler(unsigned long r4, unsigned long r5,	\
+				    unsigned long r6, unsigned long r7,	\
+				    struct pt_regs __regs)
+
+#define TRAP_HANDLER_DECL				\
+	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);	\
+	unsigned int vec = regs->tra;			\
+	(void)vec;
+
+#endif /* __ASM_SH_TRAPS_32_H */
diff --git a/arch/sh/include/asm/traps_64.h b/arch/sh/include/asm/traps_64.h
new file mode 100644
index 000000000000..c52d7f9a06c1
--- /dev/null
+++ b/arch/sh/include/asm/traps_64.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_TRAPS_64_H
+#define __ASM_SH_TRAPS_64_H
+
+extern void phys_stext(void);
+
+static inline void trigger_address_error(void)
+{
+	phys_stext();
+}
+
+#define BUILD_TRAP_HANDLER(name)	\
+asmlinkage void name##_trap_handler(unsigned int vec, struct pt_regs *regs)
+#define TRAP_HANDLER_DECL
+
+#endif /* __ASM_SH_TRAPS_64_H */
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index 075848f43b6a..050f221fa898 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -254,5 +254,19 @@ int fixup_exception(struct pt_regs *regs);
 unsigned long search_exception_table(unsigned long addr);
 const struct exception_table_entry *search_exception_tables(unsigned long addr);
 
+extern void *set_exception_table_vec(unsigned int vec, void *handler);
+
+static inline void *set_exception_table_evt(unsigned int evt, void *handler)
+{
+	return set_exception_table_vec(evt >> 5, handler);
+}
+
+struct mem_access {
+	unsigned long (*from)(void *dst, const void __user *src, unsigned long cnt);
+	unsigned long (*to)(void __user *dst, const void *src, unsigned long cnt);
+};
+
+int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
+			    struct mem_access *ma, int, unsigned long address);
 
 #endif /* __ASM_SH_UACCESS_H */
diff --git a/arch/sh/include/asm/unistd.h b/arch/sh/include/asm/unistd.h
index 65be656ead7d..a42a5610a36a 100644
--- a/arch/sh/include/asm/unistd.h
+++ b/arch/sh/include/asm/unistd.h
@@ -1,9 +1,46 @@
 #ifdef __KERNEL__
 # ifdef CONFIG_SUPERH32
+
 #  include "unistd_32.h"
+#  define __ARCH_WANT_SYS_RT_SIGSUSPEND
+
 # else
 #  include "unistd_64.h"
 # endif
+
+# define __ARCH_WANT_IPC_PARSE_VERSION
+# define __ARCH_WANT_OLD_READDIR
+# define __ARCH_WANT_OLD_STAT
+# define __ARCH_WANT_STAT64
+# define __ARCH_WANT_SYS_ALARM
+# define __ARCH_WANT_SYS_GETHOSTNAME
+# define __ARCH_WANT_SYS_IPC
+# define __ARCH_WANT_SYS_PAUSE
+# define __ARCH_WANT_SYS_SGETMASK
+# define __ARCH_WANT_SYS_SIGNAL
+# define __ARCH_WANT_SYS_TIME
+# define __ARCH_WANT_SYS_UTIME
+# define __ARCH_WANT_SYS_WAITPID
+# define __ARCH_WANT_SYS_SOCKETCALL
+# define __ARCH_WANT_SYS_FADVISE64
+# define __ARCH_WANT_SYS_GETPGRP
+# define __ARCH_WANT_SYS_LLSEEK
+# define __ARCH_WANT_SYS_NICE
+# define __ARCH_WANT_SYS_OLD_GETRLIMIT
+# define __ARCH_WANT_SYS_OLD_UNAME
+# define __ARCH_WANT_SYS_OLDUMOUNT
+# define __ARCH_WANT_SYS_SIGPENDING
+# define __ARCH_WANT_SYS_SIGPROCMASK
+# define __ARCH_WANT_SYS_RT_SIGACTION
+
+/*
+ * "Conditional" syscalls
+ *
+ * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
+ * but it doesn't work on all toolchains, so we just do it by hand
+ */
+# define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+
 #else
 # ifdef __SH5__
 #  include "unistd_64.h"
diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h
index 152b8627a184..72fd1e061006 100644
--- a/arch/sh/include/asm/unistd_32.h
+++ b/arch/sh/include/asm/unistd_32.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_SH_UNISTD_H
-#define __ASM_SH_UNISTD_H
+#ifndef __ASM_SH_UNISTD_32_H
+#define __ASM_SH_UNISTD_32_H
 
 /*
  * Copyright (C) 1999  Niibe Yutaka
@@ -26,7 +26,7 @@
 #define __NR_mknod		 14
 #define __NR_chmod		 15
 #define __NR_lchown		 16
-#define __NR_break		 17
+				 /* 17 was sys_break */
 #define __NR_oldstat		 18
 #define __NR_lseek		 19
 #define __NR_getpid		 20
@@ -40,11 +40,11 @@
 #define __NR_oldfstat		 28
 #define __NR_pause		 29
 #define __NR_utime		 30
-#define __NR_stty		 31
-#define __NR_gtty		 32
+				 /* 31 was sys_stty */
+				 /* 32 was sys_gtty */
 #define __NR_access		 33
 #define __NR_nice		 34
-#define __NR_ftime		 35
+				 /* 35 was sys_ftime */
 #define __NR_sync		 36
 #define __NR_kill		 37
 #define __NR_rename		 38
@@ -53,7 +53,7 @@
 #define __NR_dup		 41
 #define __NR_pipe		 42
 #define __NR_times		 43
-#define __NR_prof		 44
+				 /* 44 was sys_prof */
 #define __NR_brk		 45
 #define __NR_setgid		 46
 #define __NR_getgid		 47
@@ -62,13 +62,13 @@
 #define __NR_getegid		 50
 #define __NR_acct		 51
 #define __NR_umount2		 52
-#define __NR_lock		 53
+				 /* 53 was sys_lock */
 #define __NR_ioctl		 54
 #define __NR_fcntl		 55
-#define __NR_mpx		 56
+				 /* 56 was sys_mpx */
 #define __NR_setpgid		 57
-#define __NR_ulimit		 58
-#define __NR_oldolduname	 59
+				 /* 58 was sys_ulimit */
+				 /* 59 was sys_olduname */
 #define __NR_umask		 60
 #define __NR_chroot		 61
 #define __NR_ustat		 62
@@ -91,7 +91,7 @@
 #define __NR_settimeofday	 79
 #define __NR_getgroups		 80
 #define __NR_setgroups		 81
-#define __NR_select		 82
+				 /* 82 was sys_oldselect */
 #define __NR_symlink		 83
 #define __NR_oldlstat		 84
 #define __NR_readlink		 85
@@ -107,10 +107,10 @@
 #define __NR_fchown		 95
 #define __NR_getpriority	 96
 #define __NR_setpriority	 97
-#define __NR_profil		 98
+				 /* 98 was sys_profil */
 #define __NR_statfs		 99
 #define __NR_fstatfs		100
-#define __NR_ioperm		101
+				/* 101 was sys_ioperm */
 #define __NR_socketcall		102
 #define __NR_syslog		103
 #define __NR_setitimer		104
@@ -119,10 +119,10 @@
 #define __NR_lstat		107
 #define __NR_fstat		108
 #define __NR_olduname		109
-#define __NR_iopl		110
+				/* 110 was sys_iopl */
 #define __NR_vhangup		111
-#define __NR_idle		112
-#define __NR_vm86old		113
+				/* 112 was sys_idle */
+				/* 113 was sys_vm86old */
 #define __NR_wait4		114
 #define __NR_swapoff		115
 #define __NR_sysinfo		116
@@ -136,17 +136,17 @@
 #define __NR_adjtimex		124
 #define __NR_mprotect		125
 #define __NR_sigprocmask	126
-#define __NR_create_module	127
+				/* 127 was sys_create_module */
 #define __NR_init_module	128
 #define __NR_delete_module	129
-#define __NR_get_kernel_syms	130
+				/* 130 was sys_get_kernel_syms */
 #define __NR_quotactl		131
 #define __NR_getpgid		132
 #define __NR_fchdir		133
 #define __NR_bdflush		134
 #define __NR_sysfs		135
 #define __NR_personality	136
-#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
+				/* 137 was sys_afs_syscall */
 #define __NR_setfsuid		138
 #define __NR_setfsgid		139
 #define __NR__llseek		140
@@ -175,8 +175,8 @@
 #define __NR_mremap		163
 #define __NR_setresuid		164
 #define __NR_getresuid		165
-#define __NR_vm86		166
-#define __NR_query_module	167
+				/* 166 was sys_vm86 */
+				/* 167 was sys_query_module */
 #define __NR_poll		168
 #define __NR_nfsservctl		169
 #define __NR_setresgid		170
@@ -197,8 +197,8 @@
 #define __NR_capset		185
 #define __NR_sigaltstack	186
 #define __NR_sendfile		187
-#define __NR_streams1		188	/* some people actually want it */
-#define __NR_streams2		189	/* some people actually want it */
+				/* 188 reserved for sys_getpmsg */
+				/* 189 reserved for sys_putpmsg */
 #define __NR_vfork		190
 #define __NR_ugetrlimit		191	/* SuS compliant getrlimit */
 #define __NR_mmap2		192
@@ -231,7 +231,8 @@
 #define __NR_madvise		219
 #define __NR_getdents64		220
 #define __NR_fcntl64		221
-/* 223 is unused */
+				/* 222 is reserved for tux */
+				/* 223 is unused */
 #define __NR_gettid		224
 #define __NR_readahead		225
 #define __NR_setxattr		226
@@ -251,15 +252,15 @@
 #define __NR_futex		240
 #define __NR_sched_setaffinity	241
 #define __NR_sched_getaffinity	242
-#define __NR_set_thread_area	243
-#define __NR_get_thread_area	244
+				/* 243 is reserved for set_thread_area */
+				/* 244 is reserved for get_thread_area */
 #define __NR_io_setup		245
 #define __NR_io_destroy		246
 #define __NR_io_getevents	247
 #define __NR_io_submit		248
 #define __NR_io_cancel		249
 #define __NR_fadvise64		250
-
+				/* 251 is unused */
 #define __NR_exit_group		252
 #define __NR_lookup_dcookie	253
 #define __NR_epoll_create	254
@@ -281,7 +282,7 @@
 #define __NR_tgkill		270
 #define __NR_utimes		271
 #define __NR_fadvise64_64	272
-#define __NR_vserver		273
+				/* 273 is reserved for vserver */
 #define __NR_mbind              274
 #define __NR_get_mempolicy      275
 #define __NR_set_mempolicy      276
@@ -301,7 +302,7 @@
 #define __NR_inotify_init	290
 #define __NR_inotify_add_watch	291
 #define __NR_inotify_rm_watch	292
-/* 293 is unused */
+				/* 293 is unused */
 #define __NR_migrate_pages	294
 #define __NR_openat		295
 #define __NR_mkdirat		296
@@ -380,43 +381,4 @@
 
 #define NR_syscalls 367
 
-#ifdef __KERNEL__
-
-#define __ARCH_WANT_IPC_PARSE_VERSION
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_OLD_STAT
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_IPC
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLD_UNAME
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGACTION
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#ifndef cond_syscall
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-#endif
-
-#endif /* __KERNEL__ */
-#endif /* __ASM_SH_UNISTD_H */
+#endif /* __ASM_SH_UNISTD_32_H */
diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h
index c330c23db5a0..a28edc329692 100644
--- a/arch/sh/include/asm/unistd_64.h
+++ b/arch/sh/include/asm/unistd_64.h
@@ -31,7 +31,7 @@
 #define __NR_mknod		 14
 #define __NR_chmod		 15
 #define __NR_lchown		 16
-#define __NR_break		 17
+				 /* 17 was sys_break */
 #define __NR_oldstat		 18
 #define __NR_lseek		 19
 #define __NR_getpid		 20
@@ -45,11 +45,11 @@
 #define __NR_oldfstat		 28
 #define __NR_pause		 29
 #define __NR_utime		 30
-#define __NR_stty		 31
-#define __NR_gtty		 32
+				 /* 31 was sys_stty */
+				 /* 32 was sys_gtty */
 #define __NR_access		 33
 #define __NR_nice		 34
-#define __NR_ftime		 35
+				 /* 35 was sys_ftime */
 #define __NR_sync		 36
 #define __NR_kill		 37
 #define __NR_rename		 38
@@ -58,7 +58,7 @@
 #define __NR_dup		 41
 #define __NR_pipe		 42
 #define __NR_times		 43
-#define __NR_prof		 44
+				 /* 44 was sys_prof */
 #define __NR_brk		 45
 #define __NR_setgid		 46
 #define __NR_getgid		 47
@@ -67,13 +67,13 @@
 #define __NR_getegid		 50
 #define __NR_acct		 51
 #define __NR_umount2		 52
-#define __NR_lock		 53
+				 /* 53 was sys_lock */
 #define __NR_ioctl		 54
 #define __NR_fcntl		 55
-#define __NR_mpx		 56
+				 /* 56 was sys_mpx */
 #define __NR_setpgid		 57
-#define __NR_ulimit		 58
-#define __NR_oldolduname	 59
+				 /* 58 was sys_ulimit */
+				 /* 59 was sys_olduname */
 #define __NR_umask		 60
 #define __NR_chroot		 61
 #define __NR_ustat		 62
@@ -96,7 +96,7 @@
 #define __NR_settimeofday	 79
 #define __NR_getgroups		 80
 #define __NR_setgroups		 81
-#define __NR_select		 82
+				 /* 82 was sys_select */
 #define __NR_symlink		 83
 #define __NR_oldlstat		 84
 #define __NR_readlink		 85
@@ -112,10 +112,10 @@
 #define __NR_fchown		 95
 #define __NR_getpriority	 96
 #define __NR_setpriority	 97
-#define __NR_profil		 98
+				 /* 98 was sys_profil */
 #define __NR_statfs		 99
 #define __NR_fstatfs		100
-#define __NR_ioperm		101
+				/* 101 was sys_ioperm */
 #define __NR_socketcall		102	/* old implementation of socket systemcall */
 #define __NR_syslog		103
 #define __NR_setitimer		104
@@ -124,10 +124,10 @@
 #define __NR_lstat		107
 #define __NR_fstat		108
 #define __NR_olduname		109
-#define __NR_iopl		110
+				/* 110 was sys_iopl */
 #define __NR_vhangup		111
-#define __NR_idle		112
-#define __NR_vm86old		113
+				/* 112 was sys_idle */
+				/* 113 was sys_vm86old */
 #define __NR_wait4		114
 #define __NR_swapoff		115
 #define __NR_sysinfo		116
@@ -141,17 +141,17 @@
 #define __NR_adjtimex		124
 #define __NR_mprotect		125
 #define __NR_sigprocmask	126
-#define __NR_create_module	127
+				/* 127 was sys_create_module */
 #define __NR_init_module	128
 #define __NR_delete_module	129
-#define __NR_get_kernel_syms	130
+				/* 130 was sys_get_kernel_syms */
 #define __NR_quotactl		131
 #define __NR_getpgid		132
 #define __NR_fchdir		133
 #define __NR_bdflush		134
 #define __NR_sysfs		135
 #define __NR_personality	136
-#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
+				/* 137 was sys_afs_syscall */
 #define __NR_setfsuid		138
 #define __NR_setfsgid		139
 #define __NR__llseek		140
@@ -180,8 +180,8 @@
 #define __NR_mremap		163
 #define __NR_setresuid		164
 #define __NR_getresuid		165
-#define __NR_vm86		166
-#define __NR_query_module	167
+				/* 166 was sys_vm86 */
+				/* 167 was sys_query_module */
 #define __NR_poll		168
 #define __NR_nfsservctl		169
 #define __NR_setresgid		170
@@ -202,8 +202,8 @@
 #define __NR_capset		185
 #define __NR_sigaltstack	186
 #define __NR_sendfile		187
-#define __NR_streams1		188	/* some people actually want it */
-#define __NR_streams2		189	/* some people actually want it */
+				/* 188 reserved for getpmsg */
+				/* 189 reserved for putpmsg */
 #define __NR_vfork		190
 #define __NR_ugetrlimit		191	/* SuS compliant getrlimit */
 #define __NR_mmap2		192
@@ -262,16 +262,15 @@
 #define __NR_msgrcv		241
 #define __NR_msgget		242
 #define __NR_msgctl		243
-#if 0
-#define __NR_shmatcall		244
-#endif
+#define __NR_shmat		244
 #define __NR_shmdt		245
 #define __NR_shmget		246
 #define __NR_shmctl		247
 
 #define __NR_getdents64		248
 #define __NR_fcntl64		249
-/* 223 is unused */
+				/* 250 is reserved for tux */
+				/* 251 is unused */
 #define __NR_gettid		252
 #define __NR_readahead		253
 #define __NR_setxattr		254
@@ -291,14 +290,15 @@
 #define __NR_futex		268
 #define __NR_sched_setaffinity	269
 #define __NR_sched_getaffinity	270
-#define __NR_set_thread_area	271
-#define __NR_get_thread_area	272
+				/* 271 is reserved for set_thread_area */
+				/* 272 is reserved for get_thread_area */
 #define __NR_io_setup		273
 #define __NR_io_destroy		274
 #define __NR_io_getevents	275
 #define __NR_io_submit		276
 #define __NR_io_cancel		277
 #define __NR_fadvise64		278
+				/* 279 is unused */
 #define __NR_exit_group		280
 
 #define __NR_lookup_dcookie	281
@@ -321,17 +321,17 @@
 #define __NR_tgkill		298
 #define __NR_utimes		299
 #define __NR_fadvise64_64	300
-#define __NR_vserver		301
-#define __NR_mbind              302
-#define __NR_get_mempolicy      303
-#define __NR_set_mempolicy      304
+				/* 301 is reserved for vserver */
+				/* 302 is reserved for mbind */
+				/* 303 is reserved for get_mempolicy */
+				/* 304 is reserved for set_mempolicy */
 #define __NR_mq_open            305
 #define __NR_mq_unlink          (__NR_mq_open+1)
 #define __NR_mq_timedsend       (__NR_mq_open+2)
 #define __NR_mq_timedreceive    (__NR_mq_open+3)
 #define __NR_mq_notify          (__NR_mq_open+4)
 #define __NR_mq_getsetattr      (__NR_mq_open+5)
-#define __NR_kexec_load		311
+				/* 311 is reserved for kexec */
 #define __NR_waitid		312
 #define __NR_add_key		313
 #define __NR_request_key	314
@@ -341,7 +341,7 @@
 #define __NR_inotify_init	318
 #define __NR_inotify_add_watch	319
 #define __NR_inotify_rm_watch	320
-/* 321 is unused */
+				/* 321 is unused */
 #define __NR_migrate_pages	322
 #define __NR_openat		323
 #define __NR_mkdirat		324
@@ -399,44 +399,6 @@
 #define __NR_process_vm_readv	376
 #define __NR_process_vm_writev	377
 
-#ifdef __KERNEL__
-
 #define NR_syscalls 378
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_OLD_STAT
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_IPC
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLD_UNAME
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGACTION
-
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#ifndef cond_syscall
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-#endif
-
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_UNISTD_64_H */
diff --git a/arch/sh/include/cpu-sh4/cpu/dma-register.h b/arch/sh/include/cpu-sh4/cpu/dma-register.h
index 18fa80aba15e..02788b6a03b7 100644
--- a/arch/sh/include/cpu-sh4/cpu/dma-register.h
+++ b/arch/sh/include/cpu-sh4/cpu/dma-register.h
@@ -16,45 +16,29 @@
 
 #define DMAOR_INIT	DMAOR_DME
 
-#if defined(CONFIG_CPU_SUBTYPE_SH7343) || \
-	defined(CONFIG_CPU_SUBTYPE_SH7730)
+#if defined(CONFIG_CPU_SUBTYPE_SH7343)
 #define CHCR_TS_LOW_MASK	0x00000018
 #define CHCR_TS_LOW_SHIFT	3
 #define CHCR_TS_HIGH_MASK	0
 #define CHCR_TS_HIGH_SHIFT	0
 #elif defined(CONFIG_CPU_SUBTYPE_SH7722) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7723) || \
 	defined(CONFIG_CPU_SUBTYPE_SH7724) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7730) || \
 	defined(CONFIG_CPU_SUBTYPE_SH7786)
 #define CHCR_TS_LOW_MASK	0x00000018
 #define CHCR_TS_LOW_SHIFT	3
 #define CHCR_TS_HIGH_MASK	0x00300000
 #define CHCR_TS_HIGH_SHIFT	(20 - 2)	/* 2 bits for shifted low TS */
-#elif defined(CONFIG_CPU_SUBTYPE_SH7763) || \
-	defined(CONFIG_CPU_SUBTYPE_SH7764)
-#define CHCR_TS_LOW_MASK	0x00000018
-#define CHCR_TS_LOW_SHIFT	3
-#define CHCR_TS_HIGH_MASK	0
-#define CHCR_TS_HIGH_SHIFT	0
-#elif defined(CONFIG_CPU_SUBTYPE_SH7723)
-#define CHCR_TS_LOW_MASK	0x00000018
-#define CHCR_TS_LOW_SHIFT	3
-#define CHCR_TS_HIGH_MASK	0
-#define CHCR_TS_HIGH_SHIFT	0
-#elif defined(CONFIG_CPU_SUBTYPE_SH7757)
+#elif defined(CONFIG_CPU_SUBTYPE_SH7757) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7763) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7764) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7780) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7785)
 #define CHCR_TS_LOW_MASK	0x00000018
 #define CHCR_TS_LOW_SHIFT	3
 #define CHCR_TS_HIGH_MASK	0x00100000
 #define CHCR_TS_HIGH_SHIFT	(20 - 2)	/* 2 bits for shifted low TS */
-#elif defined(CONFIG_CPU_SUBTYPE_SH7780)
-#define CHCR_TS_LOW_MASK	0x00000018
-#define CHCR_TS_LOW_SHIFT	3
-#define CHCR_TS_HIGH_MASK	0
-#define CHCR_TS_HIGH_SHIFT	0
-#else /* SH7785 */
-#define CHCR_TS_LOW_MASK	0x00000018
-#define CHCR_TS_LOW_SHIFT	3
-#define CHCR_TS_HIGH_MASK	0
-#define CHCR_TS_HIGH_SHIFT	0
 #endif
 
 /* Transmit sizes and respective CHCR register values */
diff --git a/arch/sh/include/mach-common/mach/mangle-port.h b/arch/sh/include/mach-common/mach/mangle-port.h
new file mode 100644
index 000000000000..4ca1769a0f12
--- /dev/null
+++ b/arch/sh/include/mach-common/mach/mangle-port.h
@@ -0,0 +1,49 @@
+/*
+ * SH version cribbed from the MIPS copy:
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2003, 2004 Ralf Baechle
+ */
+#ifndef __MACH_COMMON_MANGLE_PORT_H
+#define __MACH_COMMON_MANGLE_PORT_H
+
+/*
+ * Sane hardware offers swapping of PCI/ISA I/O space accesses in hardware;
+ * less sane hardware forces software to fiddle with this...
+ *
+ * Regardless, if the host bus endianness mismatches that of PCI/ISA, then
+ * you can't have the numerical value of data and byte addresses within
+ * multibyte quantities both preserved at the same time.  Hence two
+ * variations of functions: non-prefixed ones that preserve the value
+ * and prefixed ones that preserve byte addresses.  The latters are
+ * typically used for moving raw data between a peripheral and memory (cf.
+ * string I/O functions), hence the "__mem_" prefix.
+ */
+#if defined(CONFIG_SWAP_IO_SPACE)
+
+# define ioswabb(x)		(x)
+# define __mem_ioswabb(x)	(x)
+# define ioswabw(x)		le16_to_cpu(x)
+# define __mem_ioswabw(x)	(x)
+# define ioswabl(x)		le32_to_cpu(x)
+# define __mem_ioswabl(x)	(x)
+# define ioswabq(x)		le64_to_cpu(x)
+# define __mem_ioswabq(x)	(x)
+
+#else
+
+# define ioswabb(x)		(x)
+# define __mem_ioswabb(x)	(x)
+# define ioswabw(x)		(x)
+# define __mem_ioswabw(x)	cpu_to_le16(x)
+# define ioswabl(x)		(x)
+# define __mem_ioswabl(x)	cpu_to_le32(x)
+# define ioswabq(x)		(x)
+# define __mem_ioswabq(x)	cpu_to_le32(x)
+
+#endif
+
+#endif /* __MACH_COMMON_MANGLE_PORT_H */
diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c
index fac742e514ee..61a07dafcd46 100644
--- a/arch/sh/kernel/cpu/init.c
+++ b/arch/sh/kernel/cpu/init.c
@@ -18,13 +18,13 @@
 #include <asm/processor.h>
 #include <asm/uaccess.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 #include <asm/cache.h>
 #include <asm/elf.h>
 #include <asm/io.h>
 #include <asm/smp.h>
 #include <asm/sh_bios.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_SH_FPU
 #define cpu_has_fpu	1
diff --git a/arch/sh/kernel/cpu/irq/imask.c b/arch/sh/kernel/cpu/irq/imask.c
index 39b6a24c159d..e7f1745bd121 100644
--- a/arch/sh/kernel/cpu/irq/imask.c
+++ b/arch/sh/kernel/cpu/irq/imask.c
@@ -19,7 +19,6 @@
 #include <linux/cache.h>
 #include <linux/irq.h>
 #include <linux/bitmap.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 
 /* Bitmap of IRQ masked */
diff --git a/arch/sh/kernel/cpu/sh2a/opcode_helper.c b/arch/sh/kernel/cpu/sh2a/opcode_helper.c
index 9704b7926d8b..72aa61c81e48 100644
--- a/arch/sh/kernel/cpu/sh2a/opcode_helper.c
+++ b/arch/sh/kernel/cpu/sh2a/opcode_helper.c
@@ -10,7 +10,6 @@
  * for more details.
  */
 #include <linux/kernel.h>
-#include <asm/system.h>
 
 /*
  * Instructions on SH are generally fixed at 16-bits, however, SH-2A
diff --git a/arch/sh/kernel/cpu/sh4/fpu.c b/arch/sh/kernel/cpu/sh4/fpu.c
index 447482d7f65e..e74cd6c0f10d 100644
--- a/arch/sh/kernel/cpu/sh4/fpu.c
+++ b/arch/sh/kernel/cpu/sh4/fpu.c
@@ -15,7 +15,6 @@
 #include <linux/io.h>
 #include <cpu/fpu.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/fpu.h>
 
 /* The PR (precision) bit in the FP Status Register must be clear when
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
index 2875e8be4f72..c8836cffa216 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
@@ -680,6 +680,25 @@ static struct platform_device spi1_device = {
 	.resource	= spi1_resources,
 };
 
+static struct resource rspi_resources[] = {
+	{
+		.start	= 0xfe480000,
+		.end	= 0xfe4800ff,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.start	= 220,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device rspi_device = {
+	.name	= "rspi",
+	.id	= 2,
+	.num_resources	= ARRAY_SIZE(rspi_resources),
+	.resource	= rspi_resources,
+};
+
 static struct resource usb_ehci_resources[] = {
 	[0] = {
 		.start	= 0xfe4f1000,
@@ -740,6 +759,7 @@ static struct platform_device *sh7757_devices[] __initdata = {
 	&dma3_device,
 	&spi0_device,
 	&spi1_device,
+	&rspi_device,
 	&usb_ehci_device,
 	&usb_ohci_device,
 };
diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c
index 6d62eb40e750..1ddc876d3b26 100644
--- a/arch/sh/kernel/cpu/shmobile/cpuidle.c
+++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c
@@ -29,7 +29,6 @@ static int cpuidle_sleep_enter(struct cpuidle_device *dev,
 				int index)
 {
 	unsigned long allowed_mode = SUSP_SH_SLEEP;
-	ktime_t before, after;
 	int requested_state = index;
 	int allowed_state;
 	int k;
@@ -47,19 +46,16 @@ static int cpuidle_sleep_enter(struct cpuidle_device *dev,
 	 */
 	k = min_t(int, allowed_state, requested_state);
 
-	before = ktime_get();
 	sh_mobile_call_standby(cpuidle_mode[k]);
-	after = ktime_get();
-
-	dev->last_residency = (int)ktime_to_ns(ktime_sub(after, before)) >> 10;
 
 	return k;
 }
 
 static struct cpuidle_device cpuidle_dev;
 static struct cpuidle_driver cpuidle_driver = {
-	.name =		"sh_idle",
-	.owner =	THIS_MODULE,
+	.name			= "sh_idle",
+	.owner			= THIS_MODULE,
+	.en_core_tk_irqen	= 1,
 };
 
 void sh_mobile_setup_cpuidle(void)
diff --git a/arch/sh/kernel/cpufreq.c b/arch/sh/kernel/cpufreq.c
index 0fffacea6ed9..e68b45b6f3f9 100644
--- a/arch/sh/kernel/cpufreq.c
+++ b/arch/sh/kernel/cpufreq.c
@@ -3,7 +3,7 @@
  *
  * cpufreq driver for the SuperH processors.
  *
- * Copyright (C) 2002 - 2007 Paul Mundt
+ * Copyright (C) 2002 - 2012 Paul Mundt
  * Copyright (C) 2002 M. R. Brown
  *
  * Clock framework bits from arch/avr32/mach-at32ap/cpufreq.c
@@ -14,6 +14,8 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
+#define pr_fmt(fmt) "cpufreq: " fmt
+
 #include <linux/types.h>
 #include <linux/cpufreq.h>
 #include <linux/kernel.h>
@@ -21,15 +23,18 @@
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/cpumask.h>
+#include <linux/cpu.h>
 #include <linux/smp.h>
 #include <linux/sched.h>	/* set_cpus_allowed() */
 #include <linux/clk.h>
+#include <linux/percpu.h>
+#include <linux/sh_clk.h>
 
-static struct clk *cpuclk;
+static DEFINE_PER_CPU(struct clk, sh_cpuclk);
 
 static unsigned int sh_cpufreq_get(unsigned int cpu)
 {
-	return (clk_get_rate(cpuclk) + 500) / 1000;
+	return (clk_get_rate(&per_cpu(sh_cpuclk, cpu)) + 500) / 1000;
 }
 
 /*
@@ -40,8 +45,10 @@ static int sh_cpufreq_target(struct cpufreq_policy *policy,
 			     unsigned int relation)
 {
 	unsigned int cpu = policy->cpu;
+	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
 	cpumask_t cpus_allowed;
 	struct cpufreq_freqs freqs;
+	struct device *dev;
 	long freq;
 
 	if (!cpu_online(cpu))
@@ -52,13 +59,15 @@ static int sh_cpufreq_target(struct cpufreq_policy *policy,
 
 	BUG_ON(smp_processor_id() != cpu);
 
+	dev = get_cpu_device(cpu);
+
 	/* Convert target_freq from kHz to Hz */
 	freq = clk_round_rate(cpuclk, target_freq * 1000);
 
 	if (freq < (policy->min * 1000) || freq > (policy->max * 1000))
 		return -EINVAL;
 
-	pr_debug("cpufreq: requested frequency %u Hz\n", target_freq * 1000);
+	dev_dbg(dev, "requested frequency %u Hz\n", target_freq * 1000);
 
 	freqs.cpu	= cpu;
 	freqs.old	= sh_cpufreq_get(cpu);
@@ -70,78 +79,112 @@ static int sh_cpufreq_target(struct cpufreq_policy *policy,
 	clk_set_rate(cpuclk, freq);
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
-	pr_debug("cpufreq: set frequency %lu Hz\n", freq);
+	dev_dbg(dev, "set frequency %lu Hz\n", freq);
+
+	return 0;
+}
+
+static int sh_cpufreq_verify(struct cpufreq_policy *policy)
+{
+	struct clk *cpuclk = &per_cpu(sh_cpuclk, policy->cpu);
+	struct cpufreq_frequency_table *freq_table;
+
+	freq_table = cpuclk->nr_freqs ? cpuclk->freq_table : NULL;
+	if (freq_table)
+		return cpufreq_frequency_table_verify(policy, freq_table);
+
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+				     policy->cpuinfo.max_freq);
+
+	policy->min = (clk_round_rate(cpuclk, 1) + 500) / 1000;
+	policy->max = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
+
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+				     policy->cpuinfo.max_freq);
 
 	return 0;
 }
 
 static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	if (!cpu_online(policy->cpu))
+	unsigned int cpu = policy->cpu;
+	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
+	struct cpufreq_frequency_table *freq_table;
+	struct device *dev;
+
+	if (!cpu_online(cpu))
 		return -ENODEV;
 
-	cpuclk = clk_get(NULL, "cpu_clk");
+	dev = get_cpu_device(cpu);
+
+	cpuclk = clk_get(dev, "cpu_clk");
 	if (IS_ERR(cpuclk)) {
-		printk(KERN_ERR "cpufreq: couldn't get CPU#%d clk\n",
-		       policy->cpu);
+		dev_err(dev, "couldn't get CPU clk\n");
 		return PTR_ERR(cpuclk);
 	}
 
-	/* cpuinfo and default policy values */
-	policy->cpuinfo.min_freq = (clk_round_rate(cpuclk, 1) + 500) / 1000;
-	policy->cpuinfo.max_freq = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
-	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
+	policy->cur = policy->min = policy->max = sh_cpufreq_get(cpu);
 
-	policy->cur		= sh_cpufreq_get(policy->cpu);
-	policy->min		= policy->cpuinfo.min_freq;
-	policy->max		= policy->cpuinfo.max_freq;
+	freq_table = cpuclk->nr_freqs ? cpuclk->freq_table : NULL;
+	if (freq_table) {
+		int result;
 
-	/*
-	 * Catch the cases where the clock framework hasn't been wired up
-	 * properly to support scaling.
-	 */
-	if (unlikely(policy->min == policy->max)) {
-		printk(KERN_ERR "cpufreq: clock framework rate rounding "
-		       "not supported on CPU#%d.\n", policy->cpu);
+		result = cpufreq_frequency_table_cpuinfo(policy, freq_table);
+		if (!result)
+			cpufreq_frequency_table_get_attr(freq_table, cpu);
+	} else {
+		dev_notice(dev, "no frequency table found, falling back "
+			   "to rate rounding.\n");
 
-		clk_put(cpuclk);
-		return -EINVAL;
+		policy->cpuinfo.min_freq =
+			(clk_round_rate(cpuclk, 1) + 500) / 1000;
+		policy->cpuinfo.max_freq =
+			(clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
 	}
 
-	printk(KERN_INFO "cpufreq: CPU#%d Frequencies - Minimum %u.%03u MHz, "
+	policy->min = policy->cpuinfo.min_freq;
+	policy->max = policy->cpuinfo.max_freq;
+
+	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
+
+	dev_info(dev, "CPU Frequencies - Minimum %u.%03u MHz, "
 	       "Maximum %u.%03u MHz.\n",
-	       policy->cpu, policy->min / 1000, policy->min % 1000,
+	       policy->min / 1000, policy->min % 1000,
 	       policy->max / 1000, policy->max % 1000);
 
 	return 0;
 }
 
-static int sh_cpufreq_verify(struct cpufreq_policy *policy)
+static int sh_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				     policy->cpuinfo.max_freq);
-	return 0;
-}
+	unsigned int cpu = policy->cpu;
+	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
 
-static int sh_cpufreq_exit(struct cpufreq_policy *policy)
-{
+	cpufreq_frequency_table_put_attr(cpu);
 	clk_put(cpuclk);
+
 	return 0;
 }
 
+static struct freq_attr *sh_freq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
 static struct cpufreq_driver sh_cpufreq_driver = {
 	.owner		= THIS_MODULE,
 	.name		= "sh",
-	.init		= sh_cpufreq_cpu_init,
-	.verify		= sh_cpufreq_verify,
-	.target		= sh_cpufreq_target,
 	.get		= sh_cpufreq_get,
-	.exit		= sh_cpufreq_exit,
+	.target		= sh_cpufreq_target,
+	.verify		= sh_cpufreq_verify,
+	.init		= sh_cpufreq_cpu_init,
+	.exit		= sh_cpufreq_cpu_exit,
+	.attr		= sh_freq_attr,
 };
 
 static int __init sh_cpufreq_module_init(void)
 {
-	printk(KERN_INFO "cpufreq: SuperH CPU frequency driver.\n");
+	pr_notice("SuperH CPU frequency driver.\n");
 	return cpufreq_register_driver(&sh_cpufreq_driver);
 }
 
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
index 3c55b87f8b63..5b0bfcda6d0b 100644
--- a/arch/sh/kernel/dma-nommu.c
+++ b/arch/sh/kernel/dma-nommu.c
@@ -63,8 +63,8 @@ static void nommu_sync_sg(struct device *dev, struct scatterlist *sg,
 #endif
 
 struct dma_map_ops nommu_dma_ops = {
-	.alloc_coherent		= dma_generic_alloc_coherent,
-	.free_coherent		= dma_generic_free_coherent,
+	.alloc			= dma_generic_alloc_coherent,
+	.free			= dma_generic_free_coherent,
 	.map_page		= nommu_map_page,
 	.map_sg			= nommu_map_sg,
 #ifdef CONFIG_DMA_NONCOHERENT
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index efae6ab3d54c..f9173766ec4b 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -22,6 +22,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/mmu_context.h>
 #include <asm/ptrace.h>
+#include <asm/traps.h>
 
 /*
  * Stores the breakpoints currently in use on each breakpoint address
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 7e4892826563..64852ecc6881 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -18,9 +18,9 @@
 #include <linux/smp.h>
 #include <linux/cpuidle.h>
 #include <asm/pgalloc.h>
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/smp.h>
+#include <asm/bl_bit.h>
 
 void (*pm_idle)(void);
 
diff --git a/arch/sh/kernel/io_trapped.c b/arch/sh/kernel/io_trapped.c
index 0f62f4672754..c0a9761f2f8a 100644
--- a/arch/sh/kernel/io_trapped.c
+++ b/arch/sh/kernel/io_trapped.c
@@ -15,7 +15,6 @@
 #include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 7ec665178125..f72e3a951588 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -24,7 +24,6 @@
 #include <linux/prefetch.h>
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
-#include <asm/system.h>
 #include <asm/fpu.h>
 #include <asm/syscalls.h>
 
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index cbd4e4bb9fc5..4264583eabac 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -30,6 +30,7 @@
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 #include <asm/fpu.h>
+#include <asm/switch_to.h>
 
 struct task_struct *last_task_used_math = NULL;
 
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index a3e651563763..9698671444e6 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -28,7 +28,6 @@
 #include <linux/hw_breakpoint.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
diff --git a/arch/sh/kernel/ptrace_64.c b/arch/sh/kernel/ptrace_64.c
index 3d0080b5c976..bc81e07dc098 100644
--- a/arch/sh/kernel/ptrace_64.c
+++ b/arch/sh/kernel/ptrace_64.c
@@ -34,11 +34,11 @@
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 #include <asm/fpu.h>
+#include <asm/traps.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
diff --git a/arch/sh/kernel/reboot.c b/arch/sh/kernel/reboot.c
index ca6a5ca64015..04afe5b20663 100644
--- a/arch/sh/kernel/reboot.c
+++ b/arch/sh/kernel/reboot.c
@@ -8,8 +8,8 @@
 #endif
 #include <asm/addrspace.h>
 #include <asm/reboot.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
+#include <asm/traps.h>
 
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index a7a55ed43a59..5901fba3176e 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -25,7 +25,6 @@
 #include <linux/freezer.h>
 #include <linux/io.h>
 #include <linux/tracehook.h>
-#include <asm/system.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -58,12 +57,13 @@ sys_sigsuspend(old_sigset_t mask,
 	       unsigned long r5, unsigned long r6, unsigned long r7,
 	       struct pt_regs __regs)
 {
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
+	sigset_t blocked;
+
 	current->saved_sigmask = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -240,11 +240,7 @@ asmlinkage int sys_sigreturn(unsigned long r4, unsigned long r5,
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	if (restore_sigcontext(regs, &frame->sc, &r0))
 		goto badframe;
@@ -274,10 +270,7 @@ asmlinkage int sys_rt_sigreturn(unsigned long r4, unsigned long r5,
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &r0))
 		goto badframe;
@@ -548,17 +541,8 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info,
 	else
 		ret = setup_frame(sig, ka, oldset, regs);
 
-	if (ka->sa.sa_flags & SA_ONESHOT)
-		ka->sa.sa_handler = SIG_DFL;
-
-	if (ret == 0) {
-		spin_lock_irq(&current->sighand->siglock);
-		sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
-		if (!(ka->sa.sa_flags & SA_NODEFER))
-			sigaddset(&current->blocked,sig);
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-	}
+	if (ret == 0)
+		block_sigmask(ka, sig);
 
 	return ret;
 }
diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c
index 6b5603fe274b..3c9a6f7dcdce 100644
--- a/arch/sh/kernel/signal_64.c
+++ b/arch/sh/kernel/signal_64.c
@@ -159,14 +159,13 @@ sys_sigsuspend(old_sigset_t mask,
 	       unsigned long r6, unsigned long r7,
 	       struct pt_regs * regs)
 {
-	sigset_t saveset;
+	sigset_t saveset, blocked;
 
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
 	saveset = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
 
 	REF_REG_RET = -EINTR;
 	while (1) {
@@ -198,11 +197,8 @@ sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize,
 	if (copy_from_user(&newset, unewset, sizeof(newset)))
 		return -EFAULT;
 	sigdelsetmask(&newset, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
 	saveset = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	REF_REG_RET = -EINTR;
 	while (1) {
@@ -408,11 +404,7 @@ asmlinkage int sys_sigreturn(unsigned long r2, unsigned long r3,
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	if (restore_sigcontext(regs, &frame->sc, &ret))
 		goto badframe;
@@ -445,10 +437,7 @@ asmlinkage int sys_rt_sigreturn(unsigned long r2, unsigned long r3,
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ret))
 		goto badframe;
@@ -734,17 +723,8 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 	else
 		ret = setup_frame(sig, ka, oldset, regs);
 
-	if (ka->sa.sa_flags & SA_ONESHOT)
-		ka->sa.sa_handler = SIG_DFL;
-
-	if (ret == 0) {
-		spin_lock_irq(&current->sighand->siglock);
-		sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
-		if (!(ka->sa.sa_flags & SA_NODEFER))
-			sigaddset(&current->blocked,sig);
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-	}
+	if (ret == 0)
+		block_sigmask(ka, sig);
 
 	return ret;
 }
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index f624174bf239..a17a14d32340 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -23,7 +23,6 @@
 #include <linux/sched.h>
 #include <linux/atomic.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/smp.h>
 #include <asm/cacheflush.h>
diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S
index ee56a9b1a981..4b68f0f79761 100644
--- a/arch/sh/kernel/syscalls_32.S
+++ b/arch/sh/kernel/syscalls_32.S
@@ -204,8 +204,8 @@ ENTRY(sys_call_table)
 	.long sys_capset           /* 185 */
 	.long sys_sigaltstack
 	.long sys_sendfile
-	.long sys_ni_syscall	/* streams1 */
-	.long sys_ni_syscall	/* streams2 */
+	.long sys_ni_syscall	/* getpmsg */
+	.long sys_ni_syscall	/* putpmsg */
 	.long sys_vfork            /* 190 */
 	.long sys_getrlimit
 	.long sys_mmap2
@@ -259,8 +259,8 @@ ENTRY(sys_call_table)
 	.long sys_futex		/* 240 */
 	.long sys_sched_setaffinity
 	.long sys_sched_getaffinity
-	.long sys_ni_syscall
-	.long sys_ni_syscall
+	.long sys_ni_syscall	/* reserved for set_thread_area */
+	.long sys_ni_syscall	/* reserved for get_thread_area */
 	.long sys_io_setup	/* 245 */
 	.long sys_io_destroy
 	.long sys_io_getevents
diff --git a/arch/sh/kernel/syscalls_64.S b/arch/sh/kernel/syscalls_64.S
index 9af7de26fb71..0956345b36ef 100644
--- a/arch/sh/kernel/syscalls_64.S
+++ b/arch/sh/kernel/syscalls_64.S
@@ -208,8 +208,8 @@ sys_call_table:
 	.long sys_capset		/* 185 */
 	.long sys_sigaltstack
 	.long sys_sendfile
-	.long sys_ni_syscall	/* streams1 */
-	.long sys_ni_syscall	/* streams2 */
+	.long sys_ni_syscall	/* getpmsg */
+	.long sys_ni_syscall	/* putpmsg */
 	.long sys_vfork			/* 190 */
 	.long sys_getrlimit
 	.long sys_mmap2
@@ -296,8 +296,8 @@ sys_call_table:
 	.long sys_futex
 	.long sys_sched_setaffinity
 	.long sys_sched_getaffinity	/* 270 */
-	.long sys_ni_syscall
-	.long sys_ni_syscall
+	.long sys_ni_syscall		/* reserved for set_thread_area */
+	.long sys_ni_syscall		/* reserved for get_thread_area */
 	.long sys_io_setup
 	.long sys_io_destroy
 	.long sys_io_getevents		/* 275 */
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index 0830c2a9f712..a87e58a9e38f 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -7,7 +7,7 @@
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
 #include <asm/unwinder.h>
-#include <asm/system.h>
+#include <asm/traps.h>
 
 #ifdef CONFIG_GENERIC_BUG
 static void handle_BUG(struct pt_regs *regs)
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 7bbef95c9d1b..a37175deb73f 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -27,10 +27,11 @@
 #include <linux/sysfs.h>
 #include <linux/uaccess.h>
 #include <linux/perf_event.h>
-#include <asm/system.h>
 #include <asm/alignment.h>
 #include <asm/fpu.h>
 #include <asm/kprobes.h>
+#include <asm/traps.h>
+#include <asm/bl_bit.h>
 
 #ifdef CONFIG_CPU_SH2
 # define TRAP_RESERVED_INST	4
diff --git a/arch/sh/kernel/traps_64.c b/arch/sh/kernel/traps_64.c
index cd3a40483299..6c0486094e48 100644
--- a/arch/sh/kernel/traps_64.c
+++ b/arch/sh/kernel/traps_64.c
@@ -25,7 +25,6 @@
 #include <linux/sysctl.h>
 #include <linux/module.h>
 #include <linux/perf_event.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c
index 977195210653..b876780c1e1c 100644
--- a/arch/sh/math-emu/math.c
+++ b/arch/sh/math-emu/math.c
@@ -14,7 +14,6 @@
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/processor.h>
 #include <asm/io.h>
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index f251b5f27652..b81d9dbf9fef 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -33,7 +33,8 @@ static int __init dma_init(void)
 fs_initcall(dma_init);
 
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_handle, gfp_t gfp)
+				 dma_addr_t *dma_handle, gfp_t gfp,
+				 struct dma_attrs *attrs)
 {
 	void *ret, *ret_nocache;
 	int order = get_order(size);
@@ -64,7 +65,8 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 }
 
 void dma_generic_free_coherent(struct device *dev, size_t size,
-			       void *vaddr, dma_addr_t dma_handle)
+			       void *vaddr, dma_addr_t dma_handle,
+			       struct dma_attrs *attrs)
 {
 	int order = get_order(size);
 	unsigned long pfn = dma_handle >> PAGE_SHIFT;
diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c
index 7bebd044f2a1..324eef93c900 100644
--- a/arch/sh/mm/fault_32.c
+++ b/arch/sh/mm/fault_32.c
@@ -17,9 +17,9 @@
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
 #include <asm/io_trapped.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
+#include <asm/traps.h>
 
 static inline int notify_page_fault(struct pt_regs *regs, int trap)
 {
diff --git a/arch/sh/mm/fault_64.c b/arch/sh/mm/fault_64.c
index 2b356cec2489..44a341029e7b 100644
--- a/arch/sh/mm/fault_64.c
+++ b/arch/sh/mm/fault_64.c
@@ -33,7 +33,6 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
-#include <asm/system.h>
 #include <asm/tlb.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
diff --git a/arch/sh/mm/flush-sh4.c b/arch/sh/mm/flush-sh4.c
index cef402678f42..75a17f5bfa14 100644
--- a/arch/sh/mm/flush-sh4.c
+++ b/arch/sh/mm/flush-sh4.c
@@ -1,6 +1,7 @@
 #include <linux/mm.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
+#include <asm/traps.h>
 
 /*
  * Write back the dirty D-caches, but not invalidate them.
diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c
index fad52f1f6812..7160c9fd6fe3 100644
--- a/arch/sh/mm/pmb.c
+++ b/arch/sh/mm/pmb.c
@@ -25,7 +25,6 @@
 #include <linux/vmalloc.h>
 #include <asm/cacheflush.h>
 #include <asm/sizes.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
diff --git a/arch/sh/mm/tlb-pteaex.c b/arch/sh/mm/tlb-pteaex.c
index b71db6af8060..4db21adfe5de 100644
--- a/arch/sh/mm/tlb-pteaex.c
+++ b/arch/sh/mm/tlb-pteaex.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/io.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/sh/mm/tlb-sh3.c b/arch/sh/mm/tlb-sh3.c
index 7a940dbfc2e9..6554fb439f0e 100644
--- a/arch/sh/mm/tlb-sh3.c
+++ b/arch/sh/mm/tlb-sh3.c
@@ -20,7 +20,6 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
diff --git a/arch/sh/mm/tlb-sh4.c b/arch/sh/mm/tlb-sh4.c
index cfdf7930d294..d42dd7e443d5 100644
--- a/arch/sh/mm/tlb-sh4.c
+++ b/arch/sh/mm/tlb-sh4.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/io.h>
-#include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/sh/mm/tlbflush_64.c b/arch/sh/mm/tlbflush_64.c
index e3430e093d43..11c5a18f10ed 100644
--- a/arch/sh/mm/tlbflush_64.c
+++ b/arch/sh/mm/tlbflush_64.c
@@ -22,7 +22,6 @@
 #include <linux/smp.h>
 #include <linux/perf_event.h>
 #include <linux/interrupt.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/tlb.h>
 #include <asm/uaccess.h>
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 1666de84d477..6c0683d3fcba 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -577,6 +577,7 @@ config COMPAT
 	depends on SPARC64
 	default y
 	select COMPAT_BINFMT_ELF
+	select ARCH_WANT_OLD_COMPAT_IPC
 
 config SYSVIPC_COMPAT
 	bool
diff --git a/arch/sparc/boot/Makefile b/arch/sparc/boot/Makefile
index 9205416b1e67..d56d199c1aa8 100644
--- a/arch/sparc/boot/Makefile
+++ b/arch/sparc/boot/Makefile
@@ -5,7 +5,6 @@
 
 ROOT_IMG	:= /usr/src/root.img
 ELFTOAOUT	:= elftoaout
-MKIMAGE 	:= $(srctree)/scripts/mkuboot.sh
 
 hostprogs-y	:= piggyback btfixupprep
 targets		:= tftpboot.img btfix.o btfix.S image zImage vmlinux.aout
@@ -92,11 +91,9 @@ $(obj)/image.bin: $(obj)/image FORCE
 $(obj)/image.gz: $(obj)/image.bin
 	$(call if_changed,gzip)
 
-quiet_cmd_uimage = UIMAGE  $@
-      cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A sparc -O linux -T kernel \
-               -C gzip -a $(CONFIG_UBOOT_LOAD_ADDR) \
-	       -e $(CONFIG_UBOOT_ENTRY_ADDR) -n 'Linux-$(KERNELRELEASE)' \
-               -d $< $@
+UIMAGE_LOADADDR = $(CONFIG_UBOOT_LOAD_ADDR)
+UIMAGE_ENTRYADDR = $(CONFIG_UBOOT_ENTRY_ADDR)
+UIMAGE_COMPRESSION = gzip
 
 quiet_cmd_uimage.o = UIMAGE.O $@
       cmd_uimage.o = $(LD) -Tdata $(CONFIG_UBOOT_FLASH_ADDR) \
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 9dd0a769fa18..905832aa9e9e 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -13,9 +13,9 @@
 
 #include <linux/types.h>
 
+#include <asm/cmpxchg.h>
 #include <asm-generic/atomic64.h>
 
-#include <asm/system.h>
 
 #define ATOMIC_INIT(i)  { (i) }
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 9f421df46aec..ce35a1cf1a20 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -8,7 +8,7 @@
 #define __ARCH_SPARC64_ATOMIC__
 
 #include <linux/types.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -85,7 +85,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
diff --git a/arch/sparc/include/asm/auxio_32.h b/arch/sparc/include/asm/auxio_32.h
index e03e088be95f..3a319775ae37 100644
--- a/arch/sparc/include/asm/auxio_32.h
+++ b/arch/sparc/include/asm/auxio_32.h
@@ -6,7 +6,6 @@
 #ifndef _SPARC_AUXIO_H
 #define _SPARC_AUXIO_H
 
-#include <asm/system.h>
 #include <asm/vaddrs.h>
 
 /* This register is an unsigned char in IO space.  It does two things.
diff --git a/arch/sparc/include/asm/barrier.h b/arch/sparc/include/asm/barrier.h
new file mode 100644
index 000000000000..b25f02a029e0
--- /dev/null
+++ b/arch/sparc/include/asm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef ___ASM_SPARC_BARRIER_H
+#define ___ASM_SPARC_BARRIER_H
+#if defined(__sparc__) && defined(__arch64__)
+#include <asm/barrier_64.h>
+#else
+#include <asm/barrier_32.h>
+#endif
+#endif
diff --git a/arch/sparc/include/asm/barrier_32.h b/arch/sparc/include/asm/barrier_32.h
new file mode 100644
index 000000000000..c1b76654ee76
--- /dev/null
+++ b/arch/sparc/include/asm/barrier_32.h
@@ -0,0 +1,15 @@
+#ifndef __SPARC_BARRIER_H
+#define __SPARC_BARRIER_H
+
+/* XXX Change this if we ever use a PSO mode kernel. */
+#define mb()	__asm__ __volatile__ ("" : : : "memory")
+#define rmb()	mb()
+#define wmb()	mb()
+#define read_barrier_depends()	do { } while(0)
+#define set_mb(__var, __value)  do { __var = __value; mb(); } while(0)
+#define smp_mb()	__asm__ __volatile__("":::"memory")
+#define smp_rmb()	__asm__ __volatile__("":::"memory")
+#define smp_wmb()	__asm__ __volatile__("":::"memory")
+#define smp_read_barrier_depends()	do { } while(0)
+
+#endif /* !(__SPARC_BARRIER_H) */
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
new file mode 100644
index 000000000000..95d45986f908
--- /dev/null
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -0,0 +1,56 @@
+#ifndef __SPARC64_BARRIER_H
+#define __SPARC64_BARRIER_H
+
+/* These are here in an effort to more fully work around Spitfire Errata
+ * #51.  Essentially, if a memory barrier occurs soon after a mispredicted
+ * branch, the chip can stop executing instructions until a trap occurs.
+ * Therefore, if interrupts are disabled, the chip can hang forever.
+ *
+ * It used to be believed that the memory barrier had to be right in the
+ * delay slot, but a case has been traced recently wherein the memory barrier
+ * was one instruction after the branch delay slot and the chip still hung.
+ * The offending sequence was the following in sym_wakeup_done() of the
+ * sym53c8xx_2 driver:
+ *
+ *	call	sym_ccb_from_dsa, 0
+ *	 movge	%icc, 0, %l0
+ *	brz,pn	%o0, .LL1303
+ *	 mov	%o0, %l2
+ *	membar	#LoadLoad
+ *
+ * The branch has to be mispredicted for the bug to occur.  Therefore, we put
+ * the memory barrier explicitly into a "branch always, predicted taken"
+ * delay slot to avoid the problem case.
+ */
+#define membar_safe(type) \
+do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
+			     " membar	" type "\n" \
+			     "1:\n" \
+			     : : : "memory"); \
+} while (0)
+
+/* The kernel always executes in TSO memory model these days,
+ * and furthermore most sparc64 chips implement more stringent
+ * memory ordering than required by the specifications.
+ */
+#define mb()	membar_safe("#StoreLoad")
+#define rmb()	__asm__ __volatile__("":::"memory")
+#define wmb()	__asm__ __volatile__("":::"memory")
+
+#define read_barrier_depends()		do { } while(0)
+#define set_mb(__var, __value) \
+	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
+#else
+#define smp_mb()	__asm__ __volatile__("":::"memory")
+#define smp_rmb()	__asm__ __volatile__("":::"memory")
+#define smp_wmb()	__asm__ __volatile__("":::"memory")
+#endif
+
+#define smp_read_barrier_depends()	do { } while(0)
+
+#endif /* !(__SPARC64_BARRIER_H) */
diff --git a/arch/sparc/include/asm/bug.h b/arch/sparc/include/asm/bug.h
index 8a59e5a8c217..6bd9f43cb5a5 100644
--- a/arch/sparc/include/asm/bug.h
+++ b/arch/sparc/include/asm/bug.h
@@ -19,4 +19,7 @@ extern void do_BUG(const char *file, int line);
 
 #include <asm-generic/bug.h>
 
+struct pt_regs;
+extern void die_if_kernel(char *str, struct pt_regs *regs) __attribute__ ((noreturn));
+
 #endif
diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h
index 2e468773f250..68431b47a22a 100644
--- a/arch/sparc/include/asm/cacheflush_32.h
+++ b/arch/sparc/include/asm/cacheflush_32.h
@@ -83,4 +83,13 @@ extern void sparc_flush_page_to_ram(struct page *page);
 #define flush_cache_vmap(start, end)		flush_cache_all()
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
+/* When a context switch happens we must flush all user windows so that
+ * the windows of the current process are flushed onto its stack. This
+ * way the windows are all clean for the next process and the stack
+ * frames are up to date.
+ */
+extern void flush_user_windows(void);
+extern void kill_user_windows(void);
+extern void flushw_all(void);
+
 #endif /* _SPARC_CACHEFLUSH_H */
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index b95384033e89..2efea2ff88b7 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -9,6 +9,16 @@
 
 /* Cache flush operations. */
 
+
+#define flushi(addr)	__asm__ __volatile__ ("flush %0" : : "r" (addr) : "memory")
+#define flushw_all()	__asm__ __volatile__("flushw")
+
+extern void __flushw_user(void);
+#define flushw_user() __flushw_user()
+
+#define flush_user_windows flushw_user
+#define flush_register_windows flushw_all
+
 /* These are the same regardless of whether this is an SMP kernel or not. */
 #define flush_cache_mm(__mm) \
 	do { if ((__mm) == current->mm) flushw_user(); } while(0)
diff --git a/arch/sparc/include/asm/cmpxchg.h b/arch/sparc/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..9355893efa52
--- /dev/null
+++ b/arch/sparc/include/asm/cmpxchg.h
@@ -0,0 +1,8 @@
+#ifndef ___ASM_SPARC_CMPXCHG_H
+#define ___ASM_SPARC_CMPXCHG_H
+#if defined(__sparc__) && defined(__arch64__)
+#include <asm/cmpxchg_64.h>
+#else
+#include <asm/cmpxchg_32.h>
+#endif
+#endif
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
new file mode 100644
index 000000000000..c786b0a92b51
--- /dev/null
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -0,0 +1,112 @@
+/* 32-bit atomic xchg() and cmpxchg() definitions.
+ *
+ * Copyright (C) 1996 David S. Miller (davem@davemloft.net)
+ * Copyright (C) 2000 Anton Blanchard (anton@linuxcare.com.au)
+ * Copyright (C) 2007 Kyle McMartin (kyle@parisc-linux.org)
+ *
+ * Additions by Keith M Wesolowski (wesolows@foobazco.org) based
+ * on asm-parisc/atomic.h Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>.
+ */
+
+#ifndef __ARCH_SPARC_CMPXCHG__
+#define __ARCH_SPARC_CMPXCHG__
+
+#include <asm/btfixup.h>
+
+/* This has special calling conventions */
+#ifndef CONFIG_SMP
+BTFIXUPDEF_CALL(void, ___xchg32, void)
+#endif
+
+static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val)
+{
+#ifdef CONFIG_SMP
+	__asm__ __volatile__("swap [%2], %0"
+			     : "=&r" (val)
+			     : "0" (val), "r" (m)
+			     : "memory");
+	return val;
+#else
+	register unsigned long *ptr asm("g1");
+	register unsigned long ret asm("g2");
+
+	ptr = (unsigned long *) m;
+	ret = val;
+
+	/* Note: this is magic and the nop there is
+	   really needed. */
+	__asm__ __volatile__(
+	"mov	%%o7, %%g4\n\t"
+	"call	___f____xchg32\n\t"
+	" nop\n\t"
+	: "=&r" (ret)
+	: "0" (ret), "r" (ptr)
+	: "g3", "g4", "g7", "memory", "cc");
+
+	return ret;
+#endif
+}
+
+extern void __xchg_called_with_bad_pointer(void);
+
+static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
+{
+	switch (size) {
+	case 4:
+		return xchg_u32(ptr, x);
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+
+#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+/* Emulate cmpxchg() the same way we emulate atomics,
+ * by hashing the object address and indexing into an array
+ * of spinlocks to get a bit of performance...
+ *
+ * See arch/sparc/lib/atomic32.c for implementation.
+ *
+ * Cribbed from <asm-parisc/atomic.h>
+ */
+#define __HAVE_ARCH_CMPXCHG	1
+
+/* bug catcher for when unsupported size is used - won't link */
+extern void __cmpxchg_called_with_bad_pointer(void);
+/* we only need to support cmpxchg of a u32 on sparc */
+extern unsigned long __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
+
+/* don't worry...optimizer will get rid of most of this */
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32((u32 *)ptr, (u32)old, (u32)new_);
+	default:
+		__cmpxchg_called_with_bad_pointer();
+		break;
+	}
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,	\
+			(unsigned long)_n_, sizeof(*(ptr)));		\
+})
+
+#include <asm-generic/cmpxchg-local.h>
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#endif /* __ARCH_SPARC_CMPXCHG__ */
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
new file mode 100644
index 000000000000..b30eb37294c5
--- /dev/null
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -0,0 +1,145 @@
+/* 64-bit atomic xchg() and cmpxchg() definitions.
+ *
+ * Copyright (C) 1996, 1997, 2000 David S. Miller (davem@redhat.com)
+ */
+
+#ifndef __ARCH_SPARC64_CMPXCHG__
+#define __ARCH_SPARC64_CMPXCHG__
+
+static inline unsigned long xchg32(__volatile__ unsigned int *m, unsigned int val)
+{
+	unsigned long tmp1, tmp2;
+
+	__asm__ __volatile__(
+"	mov		%0, %1\n"
+"1:	lduw		[%4], %2\n"
+"	cas		[%4], %2, %0\n"
+"	cmp		%2, %0\n"
+"	bne,a,pn	%%icc, 1b\n"
+"	 mov		%1, %0\n"
+	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
+	: "0" (val), "r" (m)
+	: "cc", "memory");
+	return val;
+}
+
+static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long val)
+{
+	unsigned long tmp1, tmp2;
+
+	__asm__ __volatile__(
+"	mov		%0, %1\n"
+"1:	ldx		[%4], %2\n"
+"	casx		[%4], %2, %0\n"
+"	cmp		%2, %0\n"
+"	bne,a,pn	%%xcc, 1b\n"
+"	 mov		%1, %0\n"
+	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
+	: "0" (val), "r" (m)
+	: "cc", "memory");
+	return val;
+}
+
+#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+extern void __xchg_called_with_bad_pointer(void);
+
+static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
+				       int size)
+{
+	switch (size) {
+	case 4:
+		return xchg32(ptr, x);
+	case 8:
+		return xchg64(ptr, x);
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#include <asm-generic/cmpxchg-local.h>
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long
+__cmpxchg_u32(volatile int *m, int old, int new)
+{
+	__asm__ __volatile__("cas [%2], %3, %0"
+			     : "=&r" (new)
+			     : "0" (new), "r" (m), "r" (old)
+			     : "memory");
+
+	return new;
+}
+
+static inline unsigned long
+__cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new)
+{
+	__asm__ __volatile__("casx [%2], %3, %0"
+			     : "=&r" (new)
+			     : "0" (new), "r" (m), "r" (old)
+			     : "memory");
+
+	return new;
+}
+
+/* This function doesn't exist, so you'll get a linker error
+   if something tries to do an invalid cmpxchg().  */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
+{
+	switch (size) {
+		case 4:
+			return __cmpxchg_u32(ptr, old, new);
+		case 8:
+			return __cmpxchg_u64(ptr, old, new);
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr,o,n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+				      unsigned long old,
+				      unsigned long new, int size)
+{
+	switch (size) {
+	case 4:
+	case 8:	return __cmpxchg(ptr, old, new, size);
+	default:
+		return __cmpxchg_local_generic(ptr, old, new, size);
+	}
+
+	return old;
+}
+
+#define cmpxchg_local(ptr, o, n)				  	\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n)					\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+  })
+
+#endif /* __ARCH_SPARC64_CMPXCHG__ */
diff --git a/arch/sparc/include/asm/cpu_type.h b/arch/sparc/include/asm/cpu_type.h
new file mode 100644
index 000000000000..4ca184d95d82
--- /dev/null
+++ b/arch/sparc/include/asm/cpu_type.h
@@ -0,0 +1,34 @@
+#ifndef __ASM_CPU_TYPE_H
+#define __ASM_CPU_TYPE_H
+
+/*
+ * Sparc (general) CPU types
+ */
+enum sparc_cpu {
+  sun4        = 0x00,
+  sun4c       = 0x01,
+  sun4m       = 0x02,
+  sun4d       = 0x03,
+  sun4e       = 0x04,
+  sun4u       = 0x05, /* V8 ploos ploos */
+  sun_unknown = 0x06,
+  ap1000      = 0x07, /* almost a sun4m */
+  sparc_leon  = 0x08, /* Leon SoC */
+};
+
+#ifdef CONFIG_SPARC32
+extern enum sparc_cpu sparc_cpu_model;
+
+#define ARCH_SUN4C (sparc_cpu_model==sun4c)
+
+#define SUN4M_NCPUS            4              /* Architectural limit of sun4m. */
+
+#else
+
+#define sparc_cpu_model sun4u
+
+/* This cannot ever be a sun4c :) That's just history. */
+#define ARCH_SUN4C 0
+#endif
+
+#endif /* __ASM_CPU_TYPE_H */
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 8c0e4f7bb204..48a7c65731d2 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -26,24 +26,30 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 
 #include <asm-generic/dma-mapping-common.h>
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 	void *cpu_addr;
 
-	cpu_addr = ops->alloc_coherent(dev, size, dma_handle, flag);
+	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
 	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
 	return cpu_addr;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	ops->free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/sparc/include/asm/exec.h b/arch/sparc/include/asm/exec.h
new file mode 100644
index 000000000000..2e085881e0d1
--- /dev/null
+++ b/arch/sparc/include/asm/exec.h
@@ -0,0 +1,6 @@
+#ifndef __SPARC_EXEC_H
+#define __SPARC_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __SPARC_EXEC_H */
diff --git a/arch/sparc/include/asm/floppy_32.h b/arch/sparc/include/asm/floppy_32.h
index 7440915e86d8..698d9559fead 100644
--- a/arch/sparc/include/asm/floppy_32.h
+++ b/arch/sparc/include/asm/floppy_32.h
@@ -11,7 +11,6 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/idprom.h>
 #include <asm/machines.h>
 #include <asm/oplib.h>
diff --git a/arch/sparc/include/asm/futex_64.h b/arch/sparc/include/asm/futex_64.h
index 444e7bea23bc..4e899b0dabf7 100644
--- a/arch/sparc/include/asm/futex_64.h
+++ b/arch/sparc/include/asm/futex_64.h
@@ -4,7 +4,6 @@
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
-#include <asm/system.h>
 
 #define __futex_cas_op(insn, ret, oldval, uaddr, oparg)	\
 	__asm__ __volatile__(				\
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index 2006e5d359df..c1acbd891cbc 100644
--- a/arch/sparc/include/asm/io_32.h
+++ b/arch/sparc/include/asm/io_32.h
@@ -6,7 +6,6 @@
 #include <linux/ioport.h>  /* struct resource */
 
 #include <asm/page.h>      /* IO address mapping routines need this */
-#include <asm/system.h>
 #include <asm-generic/pci_iomap.h>
 
 #define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 9481e5a6fa90..09b0b88aeb2a 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -6,7 +6,6 @@
 #include <linux/types.h>
 
 #include <asm/page.h>      /* IO address mapping routines need this */
-#include <asm/system.h>
 #include <asm/asi.h>
 #include <asm-generic/pci_iomap.h>
 
diff --git a/arch/sparc/include/asm/irqflags_32.h b/arch/sparc/include/asm/irqflags_32.h
index 14848909e0de..e414c06615c1 100644
--- a/arch/sparc/include/asm/irqflags_32.h
+++ b/arch/sparc/include/asm/irqflags_32.h
@@ -13,6 +13,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
+#include <asm/psr.h>
 
 extern void arch_local_irq_restore(unsigned long);
 extern unsigned long arch_local_irq_save(void);
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index 666a73fef28d..a97fd085cebe 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -6,7 +6,6 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/spinlock.h>
-#include <asm/system.h>
 #include <asm/spitfire.h>
 #include <asm-generic/mm_hooks.h>
 
diff --git a/arch/sparc/include/asm/ns87303.h b/arch/sparc/include/asm/ns87303.h
index af755483e17d..6b947ee0f6aa 100644
--- a/arch/sparc/include/asm/ns87303.h
+++ b/arch/sparc/include/asm/ns87303.h
@@ -79,7 +79,6 @@
 
 #include <linux/spinlock.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 extern spinlock_t ns87303_lock;
diff --git a/arch/sparc/include/asm/perfctr.h b/arch/sparc/include/asm/perfctr.h
index 8d8720a8770d..3332d2cba6c1 100644
--- a/arch/sparc/include/asm/perfctr.h
+++ b/arch/sparc/include/asm/perfctr.h
@@ -168,6 +168,29 @@ struct vcounter_struct {
   unsigned long long vcnt1;
 };
 
+#else /* !(__KERNEL__) */
+
+#ifndef CONFIG_SPARC32
+
+/* Performance counter register access. */
+#define read_pcr(__p)  __asm__ __volatile__("rd	%%pcr, %0" : "=r" (__p))
+#define write_pcr(__p) __asm__ __volatile__("wr	%0, 0x0, %%pcr" : : "r" (__p))
+#define read_pic(__p)  __asm__ __volatile__("rd %%pic, %0" : "=r" (__p))
+
+/* Blackbird errata workaround.  See commentary in
+ * arch/sparc64/kernel/smp.c:smp_percpu_timer_interrupt()
+ * for more information.
+ */
+#define write_pic(__p)  					\
+	__asm__ __volatile__("ba,pt	%%xcc, 99f\n\t"		\
+			     " nop\n\t"				\
+			     ".align	64\n"			\
+			  "99:wr	%0, 0x0, %%pic\n\t"	\
+			     "rd	%%pic, %%g0" : : "r" (__p))
+#define reset_pic()	write_pic(0)
+
+#endif /* !CONFIG_SPARC32 */
+
 #endif /* !(__KERNEL__) */
 
 #endif /* !(PERF_COUNTER_API) */
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index a790cc657476..3d7101860e68 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -21,7 +21,7 @@
 #include <asm/vac-ops.h>
 #include <asm/oplib.h>
 #include <asm/btfixup.h>
-#include <asm/system.h>
+#include <asm/cpu_type.h>
 
 
 struct vm_area_struct;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 38ebb2c60137..76e4a52aa85e 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -12,17 +12,16 @@
  * the SpitFire page tables.
  */
 
-#include <asm-generic/pgtable-nopud.h>
-
 #include <linux/compiler.h>
 #include <linux/const.h>
 #include <asm/types.h>
 #include <asm/spitfire.h>
 #include <asm/asi.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/processor.h>
 
+#include <asm-generic/pgtable-nopud.h>
+
 /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
  * The page copy blockops can use 0x6000000 to 0x8000000.
  * The TSB is mapped in the 0x8000000 to 0xa000000 range.
diff --git a/arch/sparc/include/asm/posix_types.h b/arch/sparc/include/asm/posix_types.h
index dbfc1a34b3a2..3070f25ae90a 100644
--- a/arch/sparc/include/asm/posix_types.h
+++ b/arch/sparc/include/asm/posix_types.h
@@ -9,35 +9,16 @@
 
 #if defined(__sparc__) && defined(__arch64__)
 /* sparc 64 bit */
-typedef unsigned long          __kernel_size_t;
-typedef long                   __kernel_ssize_t;
-typedef long                   __kernel_ptrdiff_t;
-typedef long                   __kernel_time_t;
-typedef long                   __kernel_clock_t;
-typedef int                    __kernel_pid_t;
-typedef int                    __kernel_ipc_pid_t;
-typedef unsigned int           __kernel_uid_t;
-typedef unsigned int           __kernel_gid_t;
-typedef unsigned long          __kernel_ino_t;
-typedef unsigned int           __kernel_mode_t;
 typedef unsigned int           __kernel_nlink_t;
-typedef int                    __kernel_daddr_t;
-typedef long                   __kernel_off_t;
-typedef char *                 __kernel_caddr_t;
-typedef unsigned short	       __kernel_uid16_t;
-typedef unsigned short	       __kernel_gid16_t;
-typedef int                    __kernel_clockid_t;
-typedef int                    __kernel_timer_t;
+#define __kernel_nlink_t __kernel_nlink_t
 
 typedef unsigned short 	       __kernel_old_uid_t;
 typedef unsigned short         __kernel_old_gid_t;
-typedef __kernel_uid_t	       __kernel_uid32_t;
-typedef __kernel_gid_t	       __kernel_gid32_t;
-
-typedef unsigned int	       __kernel_old_dev_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
 
 /* Note this piece of asymmetry from the v9 ABI.  */
 typedef int		       __kernel_suseconds_t;
+#define __kernel_suseconds_t __kernel_suseconds_t
 
 #else
 /* sparc 32 bit */
@@ -45,109 +26,29 @@ typedef int		       __kernel_suseconds_t;
 typedef unsigned int           __kernel_size_t;
 typedef int                    __kernel_ssize_t;
 typedef long int               __kernel_ptrdiff_t;
-typedef long                   __kernel_time_t;
-typedef long		       __kernel_suseconds_t;
-typedef long                   __kernel_clock_t;
-typedef int                    __kernel_pid_t;
+#define __kernel_size_t __kernel_size_t
+
 typedef unsigned short         __kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short         __kernel_uid_t;
 typedef unsigned short         __kernel_gid_t;
-typedef unsigned long          __kernel_ino_t;
+#define __kernel_uid_t __kernel_uid_t
+
 typedef unsigned short         __kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef short                  __kernel_nlink_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef long                   __kernel_daddr_t;
-typedef long                   __kernel_off_t;
-typedef char *                 __kernel_caddr_t;
-typedef unsigned short	       __kernel_uid16_t;
-typedef unsigned short	       __kernel_gid16_t;
-typedef unsigned int	       __kernel_uid32_t;
-typedef unsigned int	       __kernel_gid32_t;
-typedef unsigned short	       __kernel_old_uid_t;
-typedef unsigned short	       __kernel_old_gid_t;
+#define __kernel_daddr_t __kernel_daddr_t
+
 typedef unsigned short	       __kernel_old_dev_t;
-typedef int                    __kernel_clockid_t;
-typedef int                    __kernel_timer_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
 #endif /* defined(__sparc__) && defined(__arch64__) */
 
-#ifdef __GNUC__
-typedef long long              __kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant cases (8 or 32 longs,
- * for 256 and 1024-bit fd_sets respectively)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-			case 32:
-			  tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			  tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			  tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			  tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			  tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
-			  tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
-			  tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
-			  tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
-			  return;
-			case 16:
-			  tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			  tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			  tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			  tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			  return;
-			case 8:
-			  tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			  tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			  return;
-			case 4:
-			  tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			  return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
+#include <asm-generic/posix_types.h>
 
-#endif /* __KERNEL__ */
 #endif /* __SPARC_POSIX_TYPES_H */
diff --git a/arch/sparc/include/asm/processor.h b/arch/sparc/include/asm/processor.h
index 9da9646bf6c6..2fe99e66e760 100644
--- a/arch/sparc/include/asm/processor.h
+++ b/arch/sparc/include/asm/processor.h
@@ -5,4 +5,7 @@
 #else
 #include <asm/processor_32.h>
 #endif
+
+#define nop() 		__asm__ __volatile__ ("nop")
+
 #endif
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 59fcebb8f440..e713db249931 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -18,6 +18,9 @@
 #include <asm/ptrace.h>
 #include <asm/page.h>
 
+/* Don't hold the runqueue lock over context switch */
+#define __ARCH_WANT_UNLOCKED_CTXSW
+
 /* The sparc has no problems with write protection */
 #define wp_works_ok 1
 #define wp_works_ok__is_a_macro /* for versions in ksyms.c */
diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h
index c00c3b5c2806..fd9c3f21cbf0 100644
--- a/arch/sparc/include/asm/ptrace.h
+++ b/arch/sparc/include/asm/ptrace.h
@@ -98,6 +98,8 @@ struct sparc_trapf {
  */
 #ifndef __ASSEMBLY__
 
+#include <linux/types.h>
+
 struct pt_regs {
 	unsigned long psr;
 	unsigned long pc;
@@ -163,7 +165,7 @@ struct sparc_stackf {
 #ifdef __KERNEL__
 
 #include <linux/threads.h>
-#include <asm/system.h>
+#include <asm/switch_to.h>
 
 static inline int pt_regs_trap_type(struct pt_regs *regs)
 {
@@ -239,8 +241,7 @@ extern unsigned long profile_pc(struct pt_regs *);
 #ifndef __ASSEMBLY__
 
 #ifdef __KERNEL__
-
-#include <asm/system.h>
+#include <asm/switch_to.h>
 
 static inline bool pt_regs_is_syscall(struct pt_regs *regs)
 {
diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h
index 64718ba26434..00497abec996 100644
--- a/arch/sparc/include/asm/setup.h
+++ b/arch/sparc/include/asm/setup.h
@@ -13,14 +13,30 @@
 
 #ifdef __KERNEL__
 
+extern char reboot_command[];
+
 #ifdef CONFIG_SPARC32
 /* The CPU that was used for booting
  * Only sun4d + leon may have boot_cpu_id != 0
  */
 extern unsigned char boot_cpu_id;
 extern unsigned char boot_cpu_id4;
+
+extern unsigned long empty_bad_page;
+extern unsigned long empty_bad_page_table;
+extern unsigned long empty_zero_page;
+
+extern int serial_console;
+static inline int con_is_present(void)
+{
+	return serial_console ? 0 : 1;
+}
 #endif
 
+extern void sun_do_break(void);
+extern int stop_a_enabled;
+extern int scons_pwroff;
+
 #endif /* __KERNEL__ */
 
 #endif /* _SPARC_SETUP_H */
diff --git a/arch/sparc/include/asm/switch_to.h b/arch/sparc/include/asm/switch_to.h
new file mode 100644
index 000000000000..2dc4fa5c6f8c
--- /dev/null
+++ b/arch/sparc/include/asm/switch_to.h
@@ -0,0 +1,8 @@
+#ifndef ___ASM_SPARC_SWITCH_TO_H
+#define ___ASM_SPARC_SWITCH_TO_H
+#if defined(__sparc__) && defined(__arch64__)
+#include <asm/switch_to_64.h>
+#else
+#include <asm/switch_to_32.h>
+#endif
+#endif
diff --git a/arch/sparc/include/asm/switch_to_32.h b/arch/sparc/include/asm/switch_to_32.h
new file mode 100644
index 000000000000..e32e82b76eed
--- /dev/null
+++ b/arch/sparc/include/asm/switch_to_32.h
@@ -0,0 +1,106 @@
+#ifndef __SPARC_SWITCH_TO_H
+#define __SPARC_SWITCH_TO_H
+
+#include <asm/smp.h>
+
+extern struct thread_info *current_set[NR_CPUS];
+
+/*
+ * Flush windows so that the VM switch which follows
+ * would not pull the stack from under us.
+ *
+ * SWITCH_ENTER and SWITH_DO_LAZY_FPU do not work yet (e.g. SMP does not work)
+ * XXX WTF is the above comment? Found in late teen 2.4.x.
+ */
+#ifdef CONFIG_SMP
+#define SWITCH_ENTER(prv) \
+	do {			\
+	if (test_tsk_thread_flag(prv, TIF_USEDFPU)) { \
+		put_psr(get_psr() | PSR_EF); \
+		fpsave(&(prv)->thread.float_regs[0], &(prv)->thread.fsr, \
+		       &(prv)->thread.fpqueue[0], &(prv)->thread.fpqdepth); \
+		clear_tsk_thread_flag(prv, TIF_USEDFPU); \
+		(prv)->thread.kregs->psr &= ~PSR_EF; \
+	} \
+	} while(0)
+
+#define SWITCH_DO_LAZY_FPU(next)	/* */
+#else
+#define SWITCH_ENTER(prv)		/* */
+#define SWITCH_DO_LAZY_FPU(nxt)	\
+	do {			\
+	if (last_task_used_math != (nxt))		\
+		(nxt)->thread.kregs->psr&=~PSR_EF;	\
+	} while(0)
+#endif
+
+#define prepare_arch_switch(next) do { \
+	__asm__ __volatile__( \
+	".globl\tflush_patch_switch\nflush_patch_switch:\n\t" \
+	"save %sp, -0x40, %sp; save %sp, -0x40, %sp; save %sp, -0x40, %sp\n\t" \
+	"save %sp, -0x40, %sp; save %sp, -0x40, %sp; save %sp, -0x40, %sp\n\t" \
+	"save %sp, -0x40, %sp\n\t" \
+	"restore; restore; restore; restore; restore; restore; restore"); \
+} while(0)
+
+	/* Much care has gone into this code, do not touch it.
+	 *
+	 * We need to loadup regs l0/l1 for the newly forked child
+	 * case because the trap return path relies on those registers
+	 * holding certain values, gcc is told that they are clobbered.
+	 * Gcc needs registers for 3 values in and 1 value out, so we
+	 * clobber every non-fixed-usage register besides l2/l3/o4/o5.  -DaveM
+	 *
+	 * Hey Dave, that do not touch sign is too much of an incentive
+	 * - Anton & Pete
+	 */
+#define switch_to(prev, next, last) do {						\
+	SWITCH_ENTER(prev);								\
+	SWITCH_DO_LAZY_FPU(next);							\
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next->active_mm));		\
+	__asm__ __volatile__(								\
+	"sethi	%%hi(here - 0x8), %%o7\n\t"						\
+	"mov	%%g6, %%g3\n\t"								\
+	"or	%%o7, %%lo(here - 0x8), %%o7\n\t"					\
+	"rd	%%psr, %%g4\n\t"							\
+	"std	%%sp, [%%g6 + %4]\n\t"							\
+	"rd	%%wim, %%g5\n\t"							\
+	"wr	%%g4, 0x20, %%psr\n\t"							\
+	"nop\n\t"									\
+	"std	%%g4, [%%g6 + %3]\n\t"							\
+	"ldd	[%2 + %3], %%g4\n\t"							\
+	"mov	%2, %%g6\n\t"								\
+	".globl	patchme_store_new_current\n"						\
+"patchme_store_new_current:\n\t"							\
+	"st	%2, [%1]\n\t"								\
+	"wr	%%g4, 0x20, %%psr\n\t"							\
+	"nop\n\t"									\
+	"nop\n\t"									\
+	"nop\n\t"	/* LEON needs all 3 nops: load to %sp depends on CWP. */		\
+	"ldd	[%%g6 + %4], %%sp\n\t"							\
+	"wr	%%g5, 0x0, %%wim\n\t"							\
+	"ldd	[%%sp + 0x00], %%l0\n\t"						\
+	"ldd	[%%sp + 0x38], %%i6\n\t"						\
+	"wr	%%g4, 0x0, %%psr\n\t"							\
+	"nop\n\t"									\
+	"nop\n\t"									\
+	"jmpl	%%o7 + 0x8, %%g0\n\t"							\
+	" ld	[%%g3 + %5], %0\n\t"							\
+	"here:\n"									\
+        : "=&r" (last)									\
+        : "r" (&(current_set[hard_smp_processor_id()])),	\
+	  "r" (task_thread_info(next)),				\
+	  "i" (TI_KPSR),					\
+	  "i" (TI_KSP),						\
+	  "i" (TI_TASK)						\
+	:       "g1", "g2", "g3", "g4", "g5",       "g7",	\
+	  "l0", "l1",       "l3", "l4", "l5", "l6", "l7",	\
+	  "i0", "i1", "i2", "i3", "i4", "i5",			\
+	  "o0", "o1", "o2", "o3",                   "o7");	\
+	} while(0)
+
+extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
+		   void *fpqueue, unsigned long *fpqdepth);
+extern void synchronize_user_stack(void);
+
+#endif /* __SPARC_SWITCH_TO_H */
diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h
new file mode 100644
index 000000000000..7923c4a2be38
--- /dev/null
+++ b/arch/sparc/include/asm/switch_to_64.h
@@ -0,0 +1,72 @@
+#ifndef __SPARC64_SWITCH_TO_64_H
+#define __SPARC64_SWITCH_TO_64_H
+
+#include <asm/visasm.h>
+
+#define prepare_arch_switch(next)		\
+do {						\
+	flushw_all();				\
+} while (0)
+
+	/* See what happens when you design the chip correctly?
+	 *
+	 * We tell gcc we clobber all non-fixed-usage registers except
+	 * for l0/l1.  It will use one for 'next' and the other to hold
+	 * the output value of 'last'.  'next' is not referenced again
+	 * past the invocation of switch_to in the scheduler, so we need
+	 * not preserve it's value.  Hairy, but it lets us remove 2 loads
+	 * and 2 stores in this critical code path.  -DaveM
+	 */
+#define switch_to(prev, next, last)					\
+do {	flush_tlb_pending();						\
+	save_and_clear_fpu();						\
+	/* If you are tempted to conditionalize the following */	\
+	/* so that ASI is only written if it changes, think again. */	\
+	__asm__ __volatile__("wr %%g0, %0, %%asi"			\
+	: : "r" (__thread_flag_byte_ptr(task_thread_info(next))[TI_FLAG_BYTE_CURRENT_DS]));\
+	trap_block[current_thread_info()->cpu].thread =			\
+		task_thread_info(next);					\
+	__asm__ __volatile__(						\
+	"mov	%%g4, %%g7\n\t"						\
+	"stx	%%i6, [%%sp + 2047 + 0x70]\n\t"				\
+	"stx	%%i7, [%%sp + 2047 + 0x78]\n\t"				\
+	"rdpr	%%wstate, %%o5\n\t"					\
+	"stx	%%o6, [%%g6 + %6]\n\t"					\
+	"stb	%%o5, [%%g6 + %5]\n\t"					\
+	"rdpr	%%cwp, %%o5\n\t"					\
+	"stb	%%o5, [%%g6 + %8]\n\t"					\
+	"wrpr	%%g0, 15, %%pil\n\t"					\
+	"mov	%4, %%g6\n\t"						\
+	"ldub	[%4 + %8], %%g1\n\t"					\
+	"wrpr	%%g1, %%cwp\n\t"					\
+	"ldx	[%%g6 + %6], %%o6\n\t"					\
+	"ldub	[%%g6 + %5], %%o5\n\t"					\
+	"ldub	[%%g6 + %7], %%o7\n\t"					\
+	"wrpr	%%o5, 0x0, %%wstate\n\t"				\
+	"ldx	[%%sp + 2047 + 0x70], %%i6\n\t"				\
+	"ldx	[%%sp + 2047 + 0x78], %%i7\n\t"				\
+	"ldx	[%%g6 + %9], %%g4\n\t"					\
+	"wrpr	%%g0, 14, %%pil\n\t"					\
+	"brz,pt %%o7, switch_to_pc\n\t"					\
+	" mov	%%g7, %0\n\t"						\
+	"sethi	%%hi(ret_from_syscall), %%g1\n\t"			\
+	"jmpl	%%g1 + %%lo(ret_from_syscall), %%g0\n\t"		\
+	" nop\n\t"							\
+	".globl switch_to_pc\n\t"					\
+	"switch_to_pc:\n\t"						\
+	: "=&r" (last), "=r" (current), "=r" (current_thread_info_reg),	\
+	  "=r" (__local_per_cpu_offset)					\
+	: "0" (task_thread_info(next)),					\
+	  "i" (TI_WSTATE), "i" (TI_KSP), "i" (TI_NEW_CHILD),            \
+	  "i" (TI_CWP), "i" (TI_TASK)					\
+	: "cc",								\
+	        "g1", "g2", "g3",                   "g7",		\
+	        "l1", "l2", "l3", "l4", "l5", "l6", "l7",		\
+	  "i0", "i1", "i2", "i3", "i4", "i5",				\
+	  "o0", "o1", "o2", "o3", "o4", "o5",       "o7");		\
+} while(0)
+
+extern void synchronize_user_stack(void);
+extern void fault_in_user_windows(void);
+
+#endif /* __SPARC64_SWITCH_TO_64_H */
diff --git a/arch/sparc/include/asm/system.h b/arch/sparc/include/asm/system.h
deleted file mode 100644
index 7944a7cfc996..000000000000
--- a/arch/sparc/include/asm/system.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef ___ASM_SPARC_SYSTEM_H
-#define ___ASM_SPARC_SYSTEM_H
-#if defined(__sparc__) && defined(__arch64__)
-#include <asm/system_64.h>
-#else
-#include <asm/system_32.h>
-#endif
-#endif
diff --git a/arch/sparc/include/asm/system_32.h b/arch/sparc/include/asm/system_32.h
deleted file mode 100644
index aba16092a81b..000000000000
--- a/arch/sparc/include/asm/system_32.h
+++ /dev/null
@@ -1,284 +0,0 @@
-#ifndef __SPARC_SYSTEM_H
-#define __SPARC_SYSTEM_H
-
-#include <linux/kernel.h>
-#include <linux/threads.h>	/* NR_CPUS */
-#include <linux/thread_info.h>
-
-#include <asm/page.h>
-#include <asm/psr.h>
-#include <asm/ptrace.h>
-#include <asm/btfixup.h>
-#include <asm/smp.h>
-
-#ifndef __ASSEMBLY__
-
-#include <linux/irqflags.h>
-
-/*
- * Sparc (general) CPU types
- */
-enum sparc_cpu {
-  sun4        = 0x00,
-  sun4c       = 0x01,
-  sun4m       = 0x02,
-  sun4d       = 0x03,
-  sun4e       = 0x04,
-  sun4u       = 0x05, /* V8 ploos ploos */
-  sun_unknown = 0x06,
-  ap1000      = 0x07, /* almost a sun4m */
-  sparc_leon  = 0x08, /* Leon SoC */
-};
-
-/* Really, userland should not be looking at any of this... */
-#ifdef __KERNEL__
-
-extern enum sparc_cpu sparc_cpu_model;
-
-#define ARCH_SUN4C (sparc_cpu_model==sun4c)
-
-#define SUN4M_NCPUS            4              /* Architectural limit of sun4m. */
-
-extern char reboot_command[];
-
-extern struct thread_info *current_set[NR_CPUS];
-
-extern unsigned long empty_bad_page;
-extern unsigned long empty_bad_page_table;
-extern unsigned long empty_zero_page;
-
-extern void sun_do_break(void);
-extern int serial_console;
-extern int stop_a_enabled;
-extern int scons_pwroff;
-
-static inline int con_is_present(void)
-{
-	return serial_console ? 0 : 1;
-}
-
-/* When a context switch happens we must flush all user windows so that
- * the windows of the current process are flushed onto its stack. This
- * way the windows are all clean for the next process and the stack
- * frames are up to date.
- */
-extern void flush_user_windows(void);
-extern void kill_user_windows(void);
-extern void synchronize_user_stack(void);
-extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
-		   void *fpqueue, unsigned long *fpqdepth);
-
-#ifdef CONFIG_SMP
-#define SWITCH_ENTER(prv) \
-	do {			\
-	if (test_tsk_thread_flag(prv, TIF_USEDFPU)) { \
-		put_psr(get_psr() | PSR_EF); \
-		fpsave(&(prv)->thread.float_regs[0], &(prv)->thread.fsr, \
-		       &(prv)->thread.fpqueue[0], &(prv)->thread.fpqdepth); \
-		clear_tsk_thread_flag(prv, TIF_USEDFPU); \
-		(prv)->thread.kregs->psr &= ~PSR_EF; \
-	} \
-	} while(0)
-
-#define SWITCH_DO_LAZY_FPU(next)	/* */
-#else
-#define SWITCH_ENTER(prv)		/* */
-#define SWITCH_DO_LAZY_FPU(nxt)	\
-	do {			\
-	if (last_task_used_math != (nxt))		\
-		(nxt)->thread.kregs->psr&=~PSR_EF;	\
-	} while(0)
-#endif
-
-extern void flushw_all(void);
-
-/*
- * Flush windows so that the VM switch which follows
- * would not pull the stack from under us.
- *
- * SWITCH_ENTER and SWITH_DO_LAZY_FPU do not work yet (e.g. SMP does not work)
- * XXX WTF is the above comment? Found in late teen 2.4.x.
- */
-#define prepare_arch_switch(next) do { \
-	__asm__ __volatile__( \
-	".globl\tflush_patch_switch\nflush_patch_switch:\n\t" \
-	"save %sp, -0x40, %sp; save %sp, -0x40, %sp; save %sp, -0x40, %sp\n\t" \
-	"save %sp, -0x40, %sp; save %sp, -0x40, %sp; save %sp, -0x40, %sp\n\t" \
-	"save %sp, -0x40, %sp\n\t" \
-	"restore; restore; restore; restore; restore; restore; restore"); \
-} while(0)
-
-	/* Much care has gone into this code, do not touch it.
-	 *
-	 * We need to loadup regs l0/l1 for the newly forked child
-	 * case because the trap return path relies on those registers
-	 * holding certain values, gcc is told that they are clobbered.
-	 * Gcc needs registers for 3 values in and 1 value out, so we
-	 * clobber every non-fixed-usage register besides l2/l3/o4/o5.  -DaveM
-	 *
-	 * Hey Dave, that do not touch sign is too much of an incentive
-	 * - Anton & Pete
-	 */
-#define switch_to(prev, next, last) do {						\
-	SWITCH_ENTER(prev);								\
-	SWITCH_DO_LAZY_FPU(next);							\
-	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next->active_mm));		\
-	__asm__ __volatile__(								\
-	"sethi	%%hi(here - 0x8), %%o7\n\t"						\
-	"mov	%%g6, %%g3\n\t"								\
-	"or	%%o7, %%lo(here - 0x8), %%o7\n\t"					\
-	"rd	%%psr, %%g4\n\t"							\
-	"std	%%sp, [%%g6 + %4]\n\t"							\
-	"rd	%%wim, %%g5\n\t"							\
-	"wr	%%g4, 0x20, %%psr\n\t"							\
-	"nop\n\t"									\
-	"std	%%g4, [%%g6 + %3]\n\t"							\
-	"ldd	[%2 + %3], %%g4\n\t"							\
-	"mov	%2, %%g6\n\t"								\
-	".globl	patchme_store_new_current\n"						\
-"patchme_store_new_current:\n\t"							\
-	"st	%2, [%1]\n\t"								\
-	"wr	%%g4, 0x20, %%psr\n\t"							\
-	"nop\n\t"									\
-	"nop\n\t"									\
-	"nop\n\t"	/* LEON needs all 3 nops: load to %sp depends on CWP. */		\
-	"ldd	[%%g6 + %4], %%sp\n\t"							\
-	"wr	%%g5, 0x0, %%wim\n\t"							\
-	"ldd	[%%sp + 0x00], %%l0\n\t"						\
-	"ldd	[%%sp + 0x38], %%i6\n\t"						\
-	"wr	%%g4, 0x0, %%psr\n\t"							\
-	"nop\n\t"									\
-	"nop\n\t"									\
-	"jmpl	%%o7 + 0x8, %%g0\n\t"							\
-	" ld	[%%g3 + %5], %0\n\t"							\
-	"here:\n"									\
-        : "=&r" (last)									\
-        : "r" (&(current_set[hard_smp_processor_id()])),	\
-	  "r" (task_thread_info(next)),				\
-	  "i" (TI_KPSR),					\
-	  "i" (TI_KSP),						\
-	  "i" (TI_TASK)						\
-	:       "g1", "g2", "g3", "g4", "g5",       "g7",	\
-	  "l0", "l1",       "l3", "l4", "l5", "l6", "l7",	\
-	  "i0", "i1", "i2", "i3", "i4", "i5",			\
-	  "o0", "o1", "o2", "o3",                   "o7");	\
-	} while(0)
-
-/* XXX Change this if we ever use a PSO mode kernel. */
-#define mb()	__asm__ __volatile__ ("" : : : "memory")
-#define rmb()	mb()
-#define wmb()	mb()
-#define read_barrier_depends()	do { } while(0)
-#define set_mb(__var, __value)  do { __var = __value; mb(); } while(0)
-#define smp_mb()	__asm__ __volatile__("":::"memory")
-#define smp_rmb()	__asm__ __volatile__("":::"memory")
-#define smp_wmb()	__asm__ __volatile__("":::"memory")
-#define smp_read_barrier_depends()	do { } while(0)
-
-#define nop() __asm__ __volatile__ ("nop")
-
-/* This has special calling conventions */
-#ifndef CONFIG_SMP
-BTFIXUPDEF_CALL(void, ___xchg32, void)
-#endif
-
-static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val)
-{
-#ifdef CONFIG_SMP
-	__asm__ __volatile__("swap [%2], %0"
-			     : "=&r" (val)
-			     : "0" (val), "r" (m)
-			     : "memory");
-	return val;
-#else
-	register unsigned long *ptr asm("g1");
-	register unsigned long ret asm("g2");
-
-	ptr = (unsigned long *) m;
-	ret = val;
-
-	/* Note: this is magic and the nop there is
-	   really needed. */
-	__asm__ __volatile__(
-	"mov	%%o7, %%g4\n\t"
-	"call	___f____xchg32\n\t"
-	" nop\n\t"
-	: "=&r" (ret)
-	: "0" (ret), "r" (ptr)
-	: "g3", "g4", "g7", "memory", "cc");
-
-	return ret;
-#endif
-}
-
-#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-extern void __xchg_called_with_bad_pointer(void);
-
-static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
-{
-	switch (size) {
-	case 4:
-		return xchg_u32(ptr, x);
-	}
-	__xchg_called_with_bad_pointer();
-	return x;
-}
-
-/* Emulate cmpxchg() the same way we emulate atomics,
- * by hashing the object address and indexing into an array
- * of spinlocks to get a bit of performance...
- *
- * See arch/sparc/lib/atomic32.c for implementation.
- *
- * Cribbed from <asm-parisc/atomic.h>
- */
-#define __HAVE_ARCH_CMPXCHG	1
-
-/* bug catcher for when unsupported size is used - won't link */
-extern void __cmpxchg_called_with_bad_pointer(void);
-/* we only need to support cmpxchg of a u32 on sparc */
-extern unsigned long __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
-
-/* don't worry...optimizer will get rid of most of this */
-static inline unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32((u32 *)ptr, (u32)old, (u32)new_);
-	default:
-		__cmpxchg_called_with_bad_pointer();
-		break;
-	}
-	return old;
-}
-
-#define cmpxchg(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) _o_ = (o);					\
-	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,	\
-			(unsigned long)_n_, sizeof(*(ptr)));		\
-})
-
-#include <asm-generic/cmpxchg-local.h>
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-extern void die_if_kernel(char *str, struct pt_regs *regs) __attribute__ ((noreturn));
-
-#endif /* __KERNEL__ */
-
-#endif /* __ASSEMBLY__ */
-
-#define arch_align_stack(x) (x)
-
-#endif /* !(__SPARC_SYSTEM_H) */
diff --git a/arch/sparc/include/asm/system_64.h b/arch/sparc/include/asm/system_64.h
deleted file mode 100644
index 10bcabce97b2..000000000000
--- a/arch/sparc/include/asm/system_64.h
+++ /dev/null
@@ -1,331 +0,0 @@
-#ifndef __SPARC64_SYSTEM_H
-#define __SPARC64_SYSTEM_H
-
-#include <asm/ptrace.h>
-#include <asm/processor.h>
-#include <asm/visasm.h>
-
-#ifndef __ASSEMBLY__
-
-#include <linux/irqflags.h>
-#include <asm-generic/cmpxchg-local.h>
-
-/*
- * Sparc (general) CPU types
- */
-enum sparc_cpu {
-  sun4        = 0x00,
-  sun4c       = 0x01,
-  sun4m       = 0x02,
-  sun4d       = 0x03,
-  sun4e       = 0x04,
-  sun4u       = 0x05, /* V8 ploos ploos */
-  sun_unknown = 0x06,
-  ap1000      = 0x07, /* almost a sun4m */
-};
-
-#define sparc_cpu_model sun4u
-
-/* This cannot ever be a sun4c :) That's just history. */
-#define ARCH_SUN4C 0
-
-extern char reboot_command[];
-
-/* These are here in an effort to more fully work around Spitfire Errata
- * #51.  Essentially, if a memory barrier occurs soon after a mispredicted
- * branch, the chip can stop executing instructions until a trap occurs.
- * Therefore, if interrupts are disabled, the chip can hang forever.
- *
- * It used to be believed that the memory barrier had to be right in the
- * delay slot, but a case has been traced recently wherein the memory barrier
- * was one instruction after the branch delay slot and the chip still hung.
- * The offending sequence was the following in sym_wakeup_done() of the
- * sym53c8xx_2 driver:
- *
- *	call	sym_ccb_from_dsa, 0
- *	 movge	%icc, 0, %l0
- *	brz,pn	%o0, .LL1303
- *	 mov	%o0, %l2
- *	membar	#LoadLoad
- *
- * The branch has to be mispredicted for the bug to occur.  Therefore, we put
- * the memory barrier explicitly into a "branch always, predicted taken"
- * delay slot to avoid the problem case.
- */
-#define membar_safe(type) \
-do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
-			     " membar	" type "\n" \
-			     "1:\n" \
-			     : : : "memory"); \
-} while (0)
-
-/* The kernel always executes in TSO memory model these days,
- * and furthermore most sparc64 chips implement more stringent
- * memory ordering than required by the specifications.
- */
-#define mb()	membar_safe("#StoreLoad")
-#define rmb()	__asm__ __volatile__("":::"memory")
-#define wmb()	__asm__ __volatile__("":::"memory")
-
-#endif
-
-#define nop() 		__asm__ __volatile__ ("nop")
-
-#define read_barrier_depends()		do { } while(0)
-#define set_mb(__var, __value) \
-	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#else
-#define smp_mb()	__asm__ __volatile__("":::"memory")
-#define smp_rmb()	__asm__ __volatile__("":::"memory")
-#define smp_wmb()	__asm__ __volatile__("":::"memory")
-#endif
-
-#define smp_read_barrier_depends()	do { } while(0)
-
-#define flushi(addr)	__asm__ __volatile__ ("flush %0" : : "r" (addr) : "memory")
-
-#define flushw_all()	__asm__ __volatile__("flushw")
-
-/* Performance counter register access. */
-#define read_pcr(__p)  __asm__ __volatile__("rd	%%pcr, %0" : "=r" (__p))
-#define write_pcr(__p) __asm__ __volatile__("wr	%0, 0x0, %%pcr" : : "r" (__p))
-#define read_pic(__p)  __asm__ __volatile__("rd %%pic, %0" : "=r" (__p))
-
-/* Blackbird errata workaround.  See commentary in
- * arch/sparc64/kernel/smp.c:smp_percpu_timer_interrupt()
- * for more information.
- */
-#define write_pic(__p)  					\
-	__asm__ __volatile__("ba,pt	%%xcc, 99f\n\t"		\
-			     " nop\n\t"				\
-			     ".align	64\n"			\
-			  "99:wr	%0, 0x0, %%pic\n\t"	\
-			     "rd	%%pic, %%g0" : : "r" (__p))
-#define reset_pic()	write_pic(0)
-
-#ifndef __ASSEMBLY__
-
-extern void sun_do_break(void);
-extern int stop_a_enabled;
-extern int scons_pwroff;
-
-extern void fault_in_user_windows(void);
-extern void synchronize_user_stack(void);
-
-extern void __flushw_user(void);
-#define flushw_user() __flushw_user()
-
-#define flush_user_windows flushw_user
-#define flush_register_windows flushw_all
-
-/* Don't hold the runqueue lock over context switch */
-#define __ARCH_WANT_UNLOCKED_CTXSW
-#define prepare_arch_switch(next)		\
-do {						\
-	flushw_all();				\
-} while (0)
-
-	/* See what happens when you design the chip correctly?
-	 *
-	 * We tell gcc we clobber all non-fixed-usage registers except
-	 * for l0/l1.  It will use one for 'next' and the other to hold
-	 * the output value of 'last'.  'next' is not referenced again
-	 * past the invocation of switch_to in the scheduler, so we need
-	 * not preserve it's value.  Hairy, but it lets us remove 2 loads
-	 * and 2 stores in this critical code path.  -DaveM
-	 */
-#define switch_to(prev, next, last)					\
-do {	flush_tlb_pending();						\
-	save_and_clear_fpu();						\
-	/* If you are tempted to conditionalize the following */	\
-	/* so that ASI is only written if it changes, think again. */	\
-	__asm__ __volatile__("wr %%g0, %0, %%asi"			\
-	: : "r" (__thread_flag_byte_ptr(task_thread_info(next))[TI_FLAG_BYTE_CURRENT_DS]));\
-	trap_block[current_thread_info()->cpu].thread =			\
-		task_thread_info(next);					\
-	__asm__ __volatile__(						\
-	"mov	%%g4, %%g7\n\t"						\
-	"stx	%%i6, [%%sp + 2047 + 0x70]\n\t"				\
-	"stx	%%i7, [%%sp + 2047 + 0x78]\n\t"				\
-	"rdpr	%%wstate, %%o5\n\t"					\
-	"stx	%%o6, [%%g6 + %6]\n\t"					\
-	"stb	%%o5, [%%g6 + %5]\n\t"					\
-	"rdpr	%%cwp, %%o5\n\t"					\
-	"stb	%%o5, [%%g6 + %8]\n\t"					\
-	"wrpr	%%g0, 15, %%pil\n\t"					\
-	"mov	%4, %%g6\n\t"						\
-	"ldub	[%4 + %8], %%g1\n\t"					\
-	"wrpr	%%g1, %%cwp\n\t"					\
-	"ldx	[%%g6 + %6], %%o6\n\t"					\
-	"ldub	[%%g6 + %5], %%o5\n\t"					\
-	"ldub	[%%g6 + %7], %%o7\n\t"					\
-	"wrpr	%%o5, 0x0, %%wstate\n\t"				\
-	"ldx	[%%sp + 2047 + 0x70], %%i6\n\t"				\
-	"ldx	[%%sp + 2047 + 0x78], %%i7\n\t"				\
-	"ldx	[%%g6 + %9], %%g4\n\t"					\
-	"wrpr	%%g0, 14, %%pil\n\t"					\
-	"brz,pt %%o7, switch_to_pc\n\t"					\
-	" mov	%%g7, %0\n\t"						\
-	"sethi	%%hi(ret_from_syscall), %%g1\n\t"			\
-	"jmpl	%%g1 + %%lo(ret_from_syscall), %%g0\n\t"		\
-	" nop\n\t"							\
-	".globl switch_to_pc\n\t"					\
-	"switch_to_pc:\n\t"						\
-	: "=&r" (last), "=r" (current), "=r" (current_thread_info_reg),	\
-	  "=r" (__local_per_cpu_offset)					\
-	: "0" (task_thread_info(next)),					\
-	  "i" (TI_WSTATE), "i" (TI_KSP), "i" (TI_NEW_CHILD),            \
-	  "i" (TI_CWP), "i" (TI_TASK)					\
-	: "cc",								\
-	        "g1", "g2", "g3",                   "g7",		\
-	        "l1", "l2", "l3", "l4", "l5", "l6", "l7",		\
-	  "i0", "i1", "i2", "i3", "i4", "i5",				\
-	  "o0", "o1", "o2", "o3", "o4", "o5",       "o7");		\
-} while(0)
-
-static inline unsigned long xchg32(__volatile__ unsigned int *m, unsigned int val)
-{
-	unsigned long tmp1, tmp2;
-
-	__asm__ __volatile__(
-"	mov		%0, %1\n"
-"1:	lduw		[%4], %2\n"
-"	cas		[%4], %2, %0\n"
-"	cmp		%2, %0\n"
-"	bne,a,pn	%%icc, 1b\n"
-"	 mov		%1, %0\n"
-	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
-	: "0" (val), "r" (m)
-	: "cc", "memory");
-	return val;
-}
-
-static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long val)
-{
-	unsigned long tmp1, tmp2;
-
-	__asm__ __volatile__(
-"	mov		%0, %1\n"
-"1:	ldx		[%4], %2\n"
-"	casx		[%4], %2, %0\n"
-"	cmp		%2, %0\n"
-"	bne,a,pn	%%xcc, 1b\n"
-"	 mov		%1, %0\n"
-	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
-	: "0" (val), "r" (m)
-	: "cc", "memory");
-	return val;
-}
-
-#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-extern void __xchg_called_with_bad_pointer(void);
-
-static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
-				       int size)
-{
-	switch (size) {
-	case 4:
-		return xchg32(ptr, x);
-	case 8:
-		return xchg64(ptr, x);
-	}
-	__xchg_called_with_bad_pointer();
-	return x;
-}
-
-extern void die_if_kernel(char *str, struct pt_regs *regs) __attribute__ ((noreturn));
-
-/*
- * Atomic compare and exchange.  Compare OLD with MEM, if identical,
- * store NEW in MEM.  Return the initial value in MEM.  Success is
- * indicated by comparing RETURN with OLD.
- */
-
-#define __HAVE_ARCH_CMPXCHG 1
-
-static inline unsigned long
-__cmpxchg_u32(volatile int *m, int old, int new)
-{
-	__asm__ __volatile__("cas [%2], %3, %0"
-			     : "=&r" (new)
-			     : "0" (new), "r" (m), "r" (old)
-			     : "memory");
-
-	return new;
-}
-
-static inline unsigned long
-__cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new)
-{
-	__asm__ __volatile__("casx [%2], %3, %0"
-			     : "=&r" (new)
-			     : "0" (new), "r" (m), "r" (old)
-			     : "memory");
-
-	return new;
-}
-
-/* This function doesn't exist, so you'll get a linker error
-   if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-static inline unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
-{
-	switch (size) {
-		case 4:
-			return __cmpxchg_u32(ptr, old, new);
-		case 8:
-			return __cmpxchg_u64(ptr, old, new);
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#define cmpxchg(ptr,o,n)						 \
-  ({									 \
-     __typeof__(*(ptr)) _o_ = (o);					 \
-     __typeof__(*(ptr)) _n_ = (n);					 \
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
-				    (unsigned long)_n_, sizeof(*(ptr))); \
-  })
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-				      unsigned long old,
-				      unsigned long new, int size)
-{
-	switch (size) {
-	case 4:
-	case 8:	return __cmpxchg(ptr, old, new, size);
-	default:
-		return __cmpxchg_local_generic(ptr, old, new, size);
-	}
-
-	return old;
-}
-
-#define cmpxchg_local(ptr, o, n)				  	\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
-			(unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n)					\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
-  })
-
-#endif /* !(__ASSEMBLY__) */
-
-#define arch_align_stack(x) (x)
-
-#endif /* !(__SPARC64_SYSTEM_H) */
diff --git a/arch/sparc/include/asm/timer_32.h b/arch/sparc/include/asm/timer_32.h
index 2ec030ef3810..1a91e11dd104 100644
--- a/arch/sparc/include/asm/timer_32.h
+++ b/arch/sparc/include/asm/timer_32.h
@@ -8,12 +8,13 @@
 #ifndef _SPARC_TIMER_H
 #define _SPARC_TIMER_H
 
-#include <asm/system.h>  /* For SUN4M_NCPUS */
+#include <asm/cpu_type.h>  /* For SUN4M_NCPUS */
 #include <asm/btfixup.h>
 
 extern __volatile__ unsigned int *master_l10_counter;
 
 /* FIXME: Make do_[gs]ettimeofday btfixup calls */
+struct timespec;
 BTFIXUPDEF_CALL(int, bus_do_settimeofday, struct timespec *tv)
 #define bus_do_settimeofday(tv) BTFIXUP_CALL(bus_do_settimeofday)(tv)
 
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index 3e1449f07798..a1091afb8831 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -11,7 +11,6 @@
 #include <linux/string.h>
 #include <linux/thread_info.h>
 #include <asm/asi.h>
-#include <asm/system.h>
 #include <asm/spitfire.h>
 #include <asm-generic/uaccess-unaligned.h>
 #endif
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 9d83d3bcb494..432afa838861 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -284,6 +284,7 @@ struct vio_dev {
 };
 
 struct vio_driver {
+	const char			*name;
 	struct list_head		node;
 	const struct vio_device_id	*id_table;
 	int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
@@ -371,7 +372,13 @@ do {	if (vio->debug & VIO_DEBUG_##TYPE) \
 		       vio->vdev->channel_id, ## a); \
 } while (0)
 
-extern int vio_register_driver(struct vio_driver *drv);
+extern int __vio_register_driver(struct vio_driver *drv, struct module *owner,
+				 const char *mod_name);
+/*
+ * vio_register_driver must be a macro so that KBUILD_MODNAME can be expanded
+ */
+#define vio_register_driver(driver)		\
+	__vio_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
 extern void vio_unregister_driver(struct vio_driver *drv);
 
 static inline struct vio_driver *to_vio_driver(struct device_driver *drv)
diff --git a/arch/sparc/kernel/auxio_32.c b/arch/sparc/kernel/auxio_32.c
index f7ea8f032719..56d0f52c3e62 100644
--- a/arch/sparc/kernel/auxio_32.c
+++ b/arch/sparc/kernel/auxio_32.c
@@ -13,6 +13,7 @@
 #include <asm/io.h>
 #include <asm/auxio.h>
 #include <asm/string.h>		/* memset(), Linux has no bzero() */
+#include <asm/cpu_type.h>
 
 /* Probe and map in the Auxiliary I/O register */
 
diff --git a/arch/sparc/kernel/devices.c b/arch/sparc/kernel/devices.c
index 113c052c3043..6b2f56a6f8af 100644
--- a/arch/sparc/kernel/devices.c
+++ b/arch/sparc/kernel/devices.c
@@ -17,8 +17,8 @@
 #include <asm/oplib.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
-#include <asm/system.h>
 #include <asm/cpudata.h>
+#include <asm/cpu_type.h>
 
 extern void clock_stop_probe(void); /* tadpole.c */
 extern void sun4c_probe_memerr_reg(void);
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 381edcd5bc29..fea13c7b1aee 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1244,10 +1244,7 @@ static struct vio_driver ds_driver = {
 	.id_table	= ds_match,
 	.probe		= ds_probe,
 	.remove		= ds_remove,
-	.driver		= {
-		.name	= "ds",
-		.owner	= THIS_MODULE,
-	}
+	.name		= "ds",
 };
 
 static int __init ds_init(void)
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 4643d68713fa..070ed141aac7 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -280,7 +280,8 @@ static inline void iommu_free_ctx(struct iommu *iommu, int ctx)
 }
 
 static void *dma_4u_alloc_coherent(struct device *dev, size_t size,
-				   dma_addr_t *dma_addrp, gfp_t gfp)
+				   dma_addr_t *dma_addrp, gfp_t gfp,
+				   struct dma_attrs *attrs)
 {
 	unsigned long flags, order, first_page;
 	struct iommu *iommu;
@@ -330,7 +331,8 @@ static void *dma_4u_alloc_coherent(struct device *dev, size_t size,
 }
 
 static void dma_4u_free_coherent(struct device *dev, size_t size,
-				 void *cpu, dma_addr_t dvma)
+				 void *cpu, dma_addr_t dvma,
+				 struct dma_attrs *attrs)
 {
 	struct iommu *iommu;
 	unsigned long flags, order, npages;
@@ -825,8 +827,8 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 }
 
 static struct dma_map_ops sun4u_dma_ops = {
-	.alloc_coherent		= dma_4u_alloc_coherent,
-	.free_coherent		= dma_4u_free_coherent,
+	.alloc			= dma_4u_alloc_coherent,
+	.free			= dma_4u_free_coherent,
 	.map_page		= dma_4u_map_page,
 	.unmap_page		= dma_4u_unmap_page,
 	.map_sg			= dma_4u_map_sg,
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index d0479e2163fa..21bd73943f7f 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -261,7 +261,8 @@ EXPORT_SYMBOL(sbus_set_sbus64);
  * CPU may access them without any explicit flushing.
  */
 static void *sbus_alloc_coherent(struct device *dev, size_t len,
-				 dma_addr_t *dma_addrp, gfp_t gfp)
+				 dma_addr_t *dma_addrp, gfp_t gfp,
+				 struct dma_attrs *attrs)
 {
 	struct platform_device *op = to_platform_device(dev);
 	unsigned long len_total = PAGE_ALIGN(len);
@@ -315,7 +316,7 @@ err_nopages:
 }
 
 static void sbus_free_coherent(struct device *dev, size_t n, void *p,
-			       dma_addr_t ba)
+			       dma_addr_t ba, struct dma_attrs *attrs)
 {
 	struct resource *res;
 	struct page *pgv;
@@ -407,8 +408,8 @@ static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 }
 
 struct dma_map_ops sbus_dma_ops = {
-	.alloc_coherent		= sbus_alloc_coherent,
-	.free_coherent		= sbus_free_coherent,
+	.alloc			= sbus_alloc_coherent,
+	.free			= sbus_free_coherent,
 	.map_page		= sbus_map_page,
 	.unmap_page		= sbus_unmap_page,
 	.map_sg			= sbus_map_sg,
@@ -436,7 +437,8 @@ arch_initcall(sparc_register_ioport);
  * hwdev should be valid struct pci_dev pointer for PCI devices.
  */
 static void *pci32_alloc_coherent(struct device *dev, size_t len,
-				  dma_addr_t *pba, gfp_t gfp)
+				  dma_addr_t *pba, gfp_t gfp,
+				  struct dma_attrs *attrs)
 {
 	unsigned long len_total = PAGE_ALIGN(len);
 	void *va;
@@ -489,7 +491,7 @@ err_nopages:
  * past this call are illegal.
  */
 static void pci32_free_coherent(struct device *dev, size_t n, void *p,
-				dma_addr_t ba)
+				dma_addr_t ba, struct dma_attrs *attrs)
 {
 	struct resource *res;
 
@@ -645,8 +647,8 @@ static void pci32_sync_sg_for_device(struct device *device, struct scatterlist *
 }
 
 struct dma_map_ops pci32_dma_ops = {
-	.alloc_coherent		= pci32_alloc_coherent,
-	.free_coherent		= pci32_free_coherent,
+	.alloc			= pci32_alloc_coherent,
+	.free			= pci32_free_coherent,
 	.map_page		= pci32_map_page,
 	.unmap_page		= pci32_unmap_page,
 	.map_sg			= pci32_map_sg,
diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h
index 42851122bbd9..5a021dd2f854 100644
--- a/arch/sparc/kernel/irq.h
+++ b/arch/sparc/kernel/irq.h
@@ -1,6 +1,7 @@
 #include <linux/platform_device.h>
 
 #include <asm/btfixup.h>
+#include <asm/cpu_type.h>
 
 struct irq_bucket {
         struct irq_bucket *next;
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index d45b710ea7e4..dff2c3d7d370 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -26,7 +26,6 @@
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/io.h>
 #include <asm/iommu.h>
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
index 971fd435a281..48565c11e82a 100644
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -6,6 +6,8 @@
 #include <linux/jump_label.h>
 #include <linux/memory.h>
 
+#include <asm/cacheflush.h>
+
 #ifdef HAVE_JUMP_LABEL
 
 void arch_jump_label_transform(struct jump_entry *entry,
diff --git a/arch/sparc/kernel/kgdb_32.c b/arch/sparc/kernel/kgdb_32.c
index 539243b236fa..2e424a576a36 100644
--- a/arch/sparc/kernel/kgdb_32.c
+++ b/arch/sparc/kernel/kgdb_32.c
@@ -9,6 +9,7 @@
 #include <asm/kdebug.h>
 #include <asm/ptrace.h>
 #include <asm/irq.h>
+#include <asm/cacheflush.h>
 
 extern unsigned long trapbase;
 
diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c
index 768290a6c028..c8759550799f 100644
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@@ -7,6 +7,7 @@
 #include <linux/kdebug.h>
 #include <linux/ftrace.h>
 
+#include <asm/cacheflush.h>
 #include <asm/kdebug.h>
 #include <asm/ptrace.h>
 #include <asm/irq.h>
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index a19c8a063683..35e43673c453 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -104,11 +104,11 @@ static int irq_choose_cpu(const struct cpumask *affinity)
 {
 	cpumask_t mask;
 
-	cpus_and(mask, cpu_online_map, *affinity);
-	if (cpus_equal(mask, cpu_online_map) || cpus_empty(mask))
+	cpumask_and(&mask, cpu_online_mask, affinity);
+	if (cpumask_equal(&mask, cpu_online_mask) || cpumask_empty(&mask))
 		return boot_cpu_id;
 	else
-		return first_cpu(mask);
+		return cpumask_first(&mask);
 }
 #else
 #define irq_choose_cpu(affinity) boot_cpu_id
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index e5519870c3d9..276359e1ff56 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -16,6 +16,7 @@
 
 #include <asm/processor.h>
 #include <asm/spitfire.h>
+#include <asm/cacheflush.h>
 
 #include "entry.h"
 
diff --git a/arch/sparc/kernel/muldiv.c b/arch/sparc/kernel/muldiv.c
index 6ce1021d487c..f7db516b07d8 100644
--- a/arch/sparc/kernel/muldiv.c
+++ b/arch/sparc/kernel/muldiv.c
@@ -14,7 +14,6 @@
 #include <linux/mm.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "kernel.h"
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index c76fe0b5bd94..eb1c1f010a47 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -22,6 +22,7 @@
 #include <asm/perf_event.h>
 #include <asm/ptrace.h>
 #include <asm/pcr.h>
+#include <asm/perfctr.h>
 
 #include "kstack.h"
 
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index af5755d20fbe..7661e84a05a0 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -128,7 +128,8 @@ static inline long iommu_batch_end(void)
 }
 
 static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
-				   dma_addr_t *dma_addrp, gfp_t gfp)
+				   dma_addr_t *dma_addrp, gfp_t gfp,
+				   struct dma_attrs *attrs)
 {
 	unsigned long flags, order, first_page, npages, n;
 	struct iommu *iommu;
@@ -198,7 +199,7 @@ range_alloc_fail:
 }
 
 static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
-				 dma_addr_t dvma)
+				 dma_addr_t dvma, struct dma_attrs *attrs)
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
@@ -527,8 +528,8 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 }
 
 static struct dma_map_ops sun4v_dma_ops = {
-	.alloc_coherent			= dma_4v_alloc_coherent,
-	.free_coherent			= dma_4v_free_coherent,
+	.alloc				= dma_4v_alloc_coherent,
+	.free				= dma_4v_free_coherent,
 	.map_page			= dma_4v_map_page,
 	.unmap_page			= dma_4v_unmap_page,
 	.map_sg				= dma_4v_map_sg,
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index a24072a49270..0ce0dd2332aa 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -14,6 +14,7 @@
 #include <asm/pcr.h>
 #include <asm/nmi.h>
 #include <asm/spitfire.h>
+#include <asm/perfctr.h>
 
 /* This code is shared between various users of the performance
  * counters.  Users will be oprofile, pseudo-NMI watchdog, and the
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 8e16a4a21582..28559ce5eeb5 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -25,6 +25,8 @@
 #include <linux/atomic.h>
 #include <asm/nmi.h>
 #include <asm/pcr.h>
+#include <asm/perfctr.h>
+#include <asm/cacheflush.h>
 
 #include "kernel.h"
 #include "kstack.h"
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 935fdbcd88c2..efa07542e85f 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -28,7 +28,6 @@
 #include <asm/auxio.h>
 #include <asm/oplib.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
@@ -38,6 +37,7 @@
 #include <asm/elf.h>
 #include <asm/prom.h>
 #include <asm/unistd.h>
+#include <asm/setup.h>
 
 /* 
  * Power management idle function 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 06b5b5fc20c7..aff0c72fac09 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -32,7 +32,6 @@
 #include <linux/nmi.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index 27b9e93d0121..896ba7c5cd8e 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -23,8 +23,8 @@
 #include <linux/tracehook.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
+#include <asm/cacheflush.h>
 
 /* #define ALLOW_INIT_TRACING */
 
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 9388844cd88c..6f97c0767995 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -29,7 +29,6 @@
 
 #include <asm/asi.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/psrcompat.h>
 #include <asm/visasm.h>
diff --git a/arch/sparc/kernel/reboot.c b/arch/sparc/kernel/reboot.c
index 006a42dd2007..eba7d918162a 100644
--- a/arch/sparc/kernel/reboot.c
+++ b/arch/sparc/kernel/reboot.c
@@ -7,9 +7,9 @@
 #include <linux/export.h>
 #include <linux/pm.h>
 
-#include <asm/system.h>
 #include <asm/oplib.h>
 #include <asm/prom.h>
+#include <asm/setup.h>
 
 /* sysctl - toggle power-off restriction for serial console
  * systems in machine_power_off()
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index ffb883ddd0f0..d444468b27f6 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -33,7 +33,6 @@
 #include <linux/kdebug.h>
 #include <linux/export.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/oplib.h>
@@ -46,6 +45,7 @@
 #include <asm/machines.h>
 #include <asm/cpudata.h>
 #include <asm/setup.h>
+#include <asm/cacheflush.h>
 
 #include "kernel.h"
 
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index a854a1c240ff..1414d16712b2 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -31,7 +31,6 @@
 #include <linux/initrd.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/oplib.h>
@@ -49,6 +48,7 @@
 #include <asm/btext.h>
 #include <asm/elf.h>
 #include <asm/mdesc.h>
+#include <asm/cacheflush.h>
 
 #ifdef CONFIG_IP_PNP
 #include <net/ipconfig.h>
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index c8f5b50db89c..948700fb9036 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -28,6 +28,7 @@
 #include <asm/fpumacro.h>
 #include <asm/visasm.h>
 #include <asm/compat_signal.h>
+#include <asm/switch_to.h>
 
 #include "sigutil.h"
 
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 7bb71b6fbd20..1e750e415d7a 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -25,6 +25,7 @@
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>	/* flush_sig_insns */
+#include <asm/switch_to.h>
 
 #include "sigutil.h"
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index d8a67e60be80..48b0f57b65f7 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -31,6 +31,8 @@
 #include <asm/uctx.h>
 #include <asm/siginfo.h>
 #include <asm/visasm.h>
+#include <asm/switch_to.h>
+#include <asm/cacheflush.h>
 
 #include "entry.h"
 #include "systbls.h"
diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c
index 35c7897b009a..0f6eebe71e6c 100644
--- a/arch/sparc/kernel/sigutil_32.c
+++ b/arch/sparc/kernel/sigutil_32.c
@@ -7,6 +7,7 @@
 #include <asm/sigcontext.h>
 #include <asm/fpumacro.h>
 #include <asm/ptrace.h>
+#include <asm/switch_to.h>
 
 #include "sigutil.h"
 
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
index b19570d41a39..387834a9c56a 100644
--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -7,6 +7,7 @@
 #include <asm/sigcontext.h>
 #include <asm/fpumacro.h>
 #include <asm/ptrace.h>
+#include <asm/switch_to.h>
 
 #include "sigutil.h"
 
diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c
index 12ff09824cd9..9f5e24ddcc70 100644
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -10,12 +10,12 @@
 #include <linux/init.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/cpudata.h>
 #include <asm/uaccess.h>
 #include <asm/spitfire.h>
 #include <asm/oplib.h>
 #include <asm/hypervisor.h>
+#include <asm/cacheflush.h>
 
 struct poll {
 	int fd;
diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c
index 133387980b56..540b2fec09f0 100644
--- a/arch/sparc/kernel/sun4d_smp.c
+++ b/arch/sparc/kernel/sun4d_smp.c
@@ -14,6 +14,7 @@
 #include <asm/sbi.h>
 #include <asm/mmu.h>
 #include <asm/tlbflush.h>
+#include <asm/switch_to.h>
 #include <asm/cacheflush.h>
 
 #include "kernel.h"
diff --git a/arch/sparc/kernel/sun4m_smp.c b/arch/sparc/kernel/sun4m_smp.c
index 594768686525..02db9a0412ce 100644
--- a/arch/sparc/kernel/sun4m_smp.c
+++ b/arch/sparc/kernel/sun4m_smp.c
@@ -10,6 +10,7 @@
 #include <linux/cpu.h>
 
 #include <asm/cacheflush.h>
+#include <asm/switch_to.h>
 #include <asm/tlbflush.h>
 
 #include "irq.h"
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index 1060e0672a4b..7d0c088e8aba 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -37,7 +37,6 @@
 #include <asm/oplib.h>
 #include <asm/timex.h>
 #include <asm/timer.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/io.h>
 #include <asm/idprom.h>
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index 591f20ca9e48..d2de21333146 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -17,7 +17,6 @@
 #include <linux/export.h>
 
 #include <asm/delay.h>
-#include <asm/system.h>
 #include <asm/ptrace.h>
 #include <asm/oplib.h>
 #include <asm/page.h>
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 0cbdaa41cd1e..c72fdf55e1c1 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -22,7 +22,6 @@
 
 #include <asm/smp.h>
 #include <asm/delay.h>
-#include <asm/system.h>
 #include <asm/ptrace.h>
 #include <asm/oplib.h>
 #include <asm/page.h>
@@ -41,6 +40,7 @@
 #include <asm/head.h>
 #include <asm/prom.h>
 #include <asm/memctrl.h>
+#include <asm/cacheflush.h>
 
 #include "entry.h"
 #include "kstack.h"
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 4d043a1b2492..c0ec89786193 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -12,7 +12,6 @@
 #include <linux/mm.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/smp.h>
 #include <linux/perf_event.h>
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 76e4ac1a13e1..dae85bc2eda5 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -16,7 +16,6 @@
 #include <asm/ptrace.h>
 #include <asm/pstate.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/smp.h>
 #include <linux/bitops.h>
@@ -24,6 +23,7 @@
 #include <linux/ratelimit.h>
 #include <linux/bitops.h>
 #include <asm/fpumacro.h>
+#include <asm/cacheflush.h>
 
 enum direction {
 	load,    /* ld, ldd, ldh, ldsh */
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index f67e28ef598c..5cffdc55f075 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -119,13 +119,17 @@ static struct bus_type vio_bus_type = {
 	.remove		= vio_device_remove,
 };
 
-int vio_register_driver(struct vio_driver *viodrv)
+int __vio_register_driver(struct vio_driver *viodrv, struct module *owner,
+			const char *mod_name)
 {
 	viodrv->driver.bus = &vio_bus_type;
+	viodrv->driver.name = viodrv->name;
+	viodrv->driver.owner = owner;
+	viodrv->driver.mod_name = mod_name;
 
 	return driver_register(&viodrv->driver);
 }
-EXPORT_SYMBOL(vio_register_driver);
+EXPORT_SYMBOL(__vio_register_driver);
 
 void vio_unregister_driver(struct vio_driver *viodrv)
 {
diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c
index 73370674ccff..08e074b7eb6a 100644
--- a/arch/sparc/kernel/visemul.c
+++ b/arch/sparc/kernel/visemul.c
@@ -9,9 +9,9 @@
 
 #include <asm/ptrace.h>
 #include <asm/pstate.h>
-#include <asm/system.h>
 #include <asm/fpumacro.h>
 #include <asm/uaccess.h>
+#include <asm/cacheflush.h>
 
 /* OPF field of various VIS instructions.  */
 
diff --git a/arch/sparc/math-emu/math_64.c b/arch/sparc/math-emu/math_64.c
index e575bd2fe381..2bbe2f28ad23 100644
--- a/arch/sparc/math-emu/math_64.c
+++ b/arch/sparc/math-emu/math_64.c
@@ -16,6 +16,7 @@
 #include <asm/fpumacro.h>
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
+#include <asm/cacheflush.h>
 
 #include "sfp-util_64.h"
 #include <math-emu/soft-fp.h>
diff --git a/arch/sparc/mm/btfixup.c b/arch/sparc/mm/btfixup.c
index 8a7f81743c12..09d6af22db2d 100644
--- a/arch/sparc/mm/btfixup.c
+++ b/arch/sparc/mm/btfixup.c
@@ -12,7 +12,6 @@
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/oplib.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 
 #define BTFIXUP_OPTIMIZE_NOP
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 8023fd7e77b5..7705c6731e28 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -22,7 +22,6 @@
 #include <linux/interrupt.h>
 #include <linux/kdebug.h>
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/memreg.h>
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index 7b00de61c5f1..c5f9021b1a01 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -27,7 +27,6 @@
 #include <linux/gfp.h>
 
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/vac-ops.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index b3f5e7dfea51..21faaeea85de 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -28,7 +28,6 @@
 #include <linux/gfp.h>
 
 #include <asm/head.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h
index 77d1b313e344..3e1ac8b96cae 100644
--- a/arch/sparc/mm/init_64.h
+++ b/arch/sparc/mm/init_64.h
@@ -36,8 +36,6 @@ extern unsigned long kern_locked_tte_data;
 
 extern void prom_world(int enter);
 
-extern void free_initmem(void);
-
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #define VMEMMAP_CHUNK_SHIFT	22
 #define VMEMMAP_CHUNK		(1UL << VMEMMAP_CHUNK_SHIFT)
diff --git a/arch/sparc/mm/loadmmu.c b/arch/sparc/mm/loadmmu.c
index 82ec8f666036..c5bf2a6c3858 100644
--- a/arch/sparc/mm/loadmmu.c
+++ b/arch/sparc/mm/loadmmu.c
@@ -11,7 +11,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 536412d8f416..c52add79b83d 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -6,7 +6,6 @@
 #include <linux/kernel.h>
 #include <linux/preempt.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
diff --git a/arch/sparc/prom/console_32.c b/arch/sparc/prom/console_32.c
index a00f47b16c10..1cfb50f4cb9c 100644
--- a/arch/sparc/prom/console_32.c
+++ b/arch/sparc/prom/console_32.c
@@ -11,7 +11,6 @@
 #include <linux/sched.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/system.h>
 #include <linux/string.h>
 
 extern void restore_current(void);
diff --git a/arch/sparc/prom/console_64.c b/arch/sparc/prom/console_64.c
index 9de6c8cfe04a..f95edcc54fd5 100644
--- a/arch/sparc/prom/console_64.c
+++ b/arch/sparc/prom/console_64.c
@@ -10,7 +10,6 @@
 #include <linux/sched.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/system.h>
 #include <linux/string.h>
 
 static int __prom_console_write_buf(const char *buf, int len)
diff --git a/arch/sparc/prom/misc_32.c b/arch/sparc/prom/misc_32.c
index 677b6a10fbde..8dc0b6b271e8 100644
--- a/arch/sparc/prom/misc_32.c
+++ b/arch/sparc/prom/misc_32.c
@@ -13,7 +13,6 @@
 #include <asm/openprom.h>
 #include <asm/oplib.h>
 #include <asm/auxio.h>
-#include <asm/system.h>
 
 extern void restore_current(void);
 
diff --git a/arch/sparc/prom/misc_64.c b/arch/sparc/prom/misc_64.c
index e4f31d4d3715..f178b9dcc7b7 100644
--- a/arch/sparc/prom/misc_64.c
+++ b/arch/sparc/prom/misc_64.c
@@ -15,7 +15,6 @@
 
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/system.h>
 #include <asm/ldc.h>
 
 static int prom_service_exists(const char *service_name)
diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c
index d9850c2b9bf2..04a4540509dd 100644
--- a/arch/sparc/prom/p1275.c
+++ b/arch/sparc/prom/p1275.c
@@ -13,7 +13,6 @@
 
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/system.h>
 #include <asm/spitfire.h>
 #include <asm/pstate.h>
 #include <asm/ldc.h>
diff --git a/arch/sparc/prom/ranges.c b/arch/sparc/prom/ranges.c
index 0857aa9e839d..ad143c13bdc0 100644
--- a/arch/sparc/prom/ranges.c
+++ b/arch/sparc/prom/ranges.c
@@ -11,7 +11,6 @@
 #include <asm/openprom.h>
 #include <asm/oplib.h>
 #include <asm/types.h>
-#include <asm/system.h>
 
 static struct linux_prom_ranges promlib_obio_ranges[PROMREG_MAX];
 static int num_obio_ranges;
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index 921dbeb8a70c..bb696da5d7cd 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -20,7 +20,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/compiler.h>
-#include <asm/system.h>
+#include <linux/types.h>
 
 #define ATOMIC_INIT(i)	{ (i) }
 
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index c03349e0ca9f..466dc4a39a4f 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -17,6 +17,7 @@
 #ifndef _ASM_TILE_ATOMIC_32_H
 #define _ASM_TILE_ATOMIC_32_H
 
+#include <asm/barrier.h>
 #include <arch/chip.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index 27fe667fddfe..f4500c688ffa 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -19,6 +19,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <arch/spr_def.h>
 
 /* First, the 32-bit atomic ops that are "real" on our 64-bit platform. */
diff --git a/arch/tile/include/asm/system.h b/arch/tile/include/asm/barrier.h
index 23d1842f4839..990a217a0b72 100644
--- a/arch/tile/include/asm/system.h
+++ b/arch/tile/include/asm/barrier.h
@@ -12,20 +12,15 @@
  *   more details.
  */
 
-#ifndef _ASM_TILE_SYSTEM_H
-#define _ASM_TILE_SYSTEM_H
+#ifndef _ASM_TILE_BARRIER_H
+#define _ASM_TILE_BARRIER_H
 
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
-#include <linux/irqflags.h>
-
-/* NOTE: we can't include <linux/ptrace.h> due to #include dependencies. */
-#include <asm/ptrace.h>
-
 #include <arch/chip.h>
-#include <arch/sim_def.h>
 #include <arch/spr_def.h>
+#include <asm/timex.h>
 
 /*
  * read_barrier_depends - Flush all pending reads that subsequents reads
@@ -78,17 +73,10 @@
  * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
  * in cases like this where there are no data dependencies.
  */
-
 #define read_barrier_depends()	do { } while (0)
 
 #define __sync()	__insn_mf()
 
-#if CHIP_HAS_SPLIT_CYCLE()
-#define get_cycles_low() __insn_mfspr(SPR_CYCLE_LOW)
-#else
-#define get_cycles_low() __insn_mfspr(SPR_CYCLE)   /* just get all 64 bits */
-#endif
-
 #if !CHIP_HAS_MF_WAITS_FOR_VICTIMS()
 #include <hv/syscall_public.h>
 /*
@@ -156,106 +144,5 @@ mb_incoherent(void)
 #define set_mb(var, value) \
 	do { var = value; mb(); } while (0)
 
-/*
- * Pause the DMA engine and static network before task switching.
- */
-#define prepare_arch_switch(next) _prepare_arch_switch(next)
-void _prepare_arch_switch(struct task_struct *next);
-
-
-/*
- * switch_to(n) should switch tasks to task nr n, first
- * checking that n isn't the current task, in which case it does nothing.
- * The number of callee-saved registers saved on the kernel stack
- * is defined here for use in copy_thread() and must agree with __switch_to().
- */
-#endif /* !__ASSEMBLY__ */
-#define CALLEE_SAVED_FIRST_REG 30
-#define CALLEE_SAVED_REGS_COUNT 24   /* r30 to r52, plus an empty to align */
-#ifndef __ASSEMBLY__
-struct task_struct;
-#define switch_to(prev, next, last) ((last) = _switch_to((prev), (next)))
-extern struct task_struct *_switch_to(struct task_struct *prev,
-				      struct task_struct *next);
-
-/* Helper function for _switch_to(). */
-extern struct task_struct *__switch_to(struct task_struct *prev,
-				       struct task_struct *next,
-				       unsigned long new_system_save_k_0);
-
-/* Address that switched-away from tasks are at. */
-extern unsigned long get_switch_to_pc(void);
-
-/*
- * On SMP systems, when the scheduler does migration-cost autodetection,
- * it needs a way to flush as much of the CPU's caches as possible:
- *
- * TODO: fill this in!
- */
-static inline void sched_cacheflush(void)
-{
-}
-
-#define arch_align_stack(x) (x)
-
-/*
- * Is the kernel doing fixups of unaligned accesses?  If <0, no kernel
- * intervention occurs and SIGBUS is delivered with no data address
- * info.  If 0, the kernel single-steps the instruction to discover
- * the data address to provide with the SIGBUS.  If 1, the kernel does
- * a fixup.
- */
-extern int unaligned_fixup;
-
-/* Is the kernel printing on each unaligned fixup? */
-extern int unaligned_printk;
-
-/* Number of unaligned fixups performed */
-extern unsigned int unaligned_fixup_count;
-
-/* Init-time routine to do tile-specific per-cpu setup. */
-void setup_cpu(int boot);
-
-/* User-level DMA management functions */
-void grant_dma_mpls(void);
-void restrict_dma_mpls(void);
-
-#ifdef CONFIG_HARDWALL
-/* User-level network management functions */
-void reset_network_state(void);
-void grant_network_mpls(void);
-void restrict_network_mpls(void);
-int hardwall_deactivate(struct task_struct *task);
-
-/* Hook hardwall code into changes in affinity. */
-#define arch_set_cpus_allowed(p, new_mask) do { \
-	if (p->thread.hardwall && !cpumask_equal(&p->cpus_allowed, new_mask)) \
-		hardwall_deactivate(p); \
-} while (0)
-#endif
-
-/*
- * Kernel threads can check to see if they need to migrate their
- * stack whenever they return from a context switch; for user
- * threads, we defer until they are returning to user-space.
- */
-#define finish_arch_switch(prev) do {                                     \
-	if (unlikely((prev)->state == TASK_DEAD))                         \
-		__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_EXIT |       \
-			((prev)->pid << _SIM_CONTROL_OPERATOR_BITS));     \
-	__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_SWITCH |             \
-		(current->pid << _SIM_CONTROL_OPERATOR_BITS));            \
-	if (current->mm == NULL && !kstack_hash &&                        \
-	    current_thread_info()->homecache_cpu != smp_processor_id())   \
-		homecache_migrate_kthread();                              \
-} while (0)
-
-/* Support function for forking a new task. */
-void ret_from_fork(void);
-
-/* Called from ret_from_fork() when a new process starts up. */
-struct task_struct *sim_notify_fork(struct task_struct *prev);
-
 #endif /* !__ASSEMBLY__ */
-
-#endif /* _ASM_TILE_SYSTEM_H */
+#endif /* _ASM_TILE_BARRIER_H */
diff --git a/arch/tile/include/asm/bitops_32.h b/arch/tile/include/asm/bitops_32.h
index 571b118bfd9b..ddc4c1efde43 100644
--- a/arch/tile/include/asm/bitops_32.h
+++ b/arch/tile/include/asm/bitops_32.h
@@ -17,7 +17,6 @@
 
 #include <linux/compiler.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 
 /* Tile-specific routines to support <asm/bitops.h>. */
 unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask);
diff --git a/arch/tile/include/asm/bitops_64.h b/arch/tile/include/asm/bitops_64.h
index e9c8e381ee0e..58d021a9834f 100644
--- a/arch/tile/include/asm/bitops_64.h
+++ b/arch/tile/include/asm/bitops_64.h
@@ -17,7 +17,6 @@
 
 #include <linux/compiler.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 
 /* See <asm/bitops.h> for API comments. */
 
diff --git a/arch/tile/include/asm/cacheflush.h b/arch/tile/include/asm/cacheflush.h
index e925f4bb498f..0fc63c488edf 100644
--- a/arch/tile/include/asm/cacheflush.h
+++ b/arch/tile/include/asm/cacheflush.h
@@ -20,7 +20,6 @@
 /* Keep includes the same across arches.  */
 #include <linux/mm.h>
 #include <linux/cache.h>
-#include <asm/system.h>
 #include <arch/icache.h>
 
 /* Caches are physically-indexed and so don't need special treatment */
@@ -152,4 +151,14 @@ static inline void finv_buffer_local(void *buffer, size_t size)
  */
 void finv_buffer_remote(void *buffer, size_t size, int hfh);
 
+/*
+ * On SMP systems, when the scheduler does migration-cost autodetection,
+ * it needs a way to flush as much of the CPU's caches as possible:
+ *
+ * TODO: fill this in!
+ */
+static inline void sched_cacheflush(void)
+{
+}
+
 #endif /* _ASM_TILE_CACHEFLUSH_H */
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index bf95f55b82b0..4b4b28969a65 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -242,17 +242,6 @@ long compat_sys_fallocate(int fd, int mode,
 long compat_sys_sched_rr_get_interval(compat_pid_t pid,
 				      struct compat_timespec __user *interval);
 
-/* Versions of compat functions that differ from generic Linux. */
-struct compat_msgbuf;
-long tile_compat_sys_msgsnd(int msqid,
-			    struct compat_msgbuf __user *msgp,
-			    size_t msgsz, int msgflg);
-long tile_compat_sys_msgrcv(int msqid,
-			    struct compat_msgbuf __user *msgp,
-			    size_t msgsz, long msgtyp, int msgflg);
-long tile_compat_sys_ptrace(compat_long_t request, compat_long_t pid,
-			    compat_long_t addr, compat_long_t data);
-
 /* Tilera Linux syscalls that don't have "compat" versions. */
 #define compat_sys_flush_cache sys_flush_cache
 
diff --git a/arch/tile/include/asm/exec.h b/arch/tile/include/asm/exec.h
new file mode 100644
index 000000000000..a714e1950867
--- /dev/null
+++ b/arch/tile/include/asm/exec.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef _ASM_TILE_EXEC_H
+#define _ASM_TILE_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _ASM_TILE_EXEC_H */
diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h
index 1a20b7ef8ea2..67490910774d 100644
--- a/arch/tile/include/asm/pgtable.h
+++ b/arch/tile/include/asm/pgtable.h
@@ -29,7 +29,6 @@
 #include <linux/spinlock.h>
 #include <asm/processor.h>
 #include <asm/fixmap.h>
-#include <asm/system.h>
 
 struct mm_struct;
 struct vm_area_struct;
diff --git a/arch/tile/include/asm/setup.h b/arch/tile/include/asm/setup.h
index 7caf0f36b030..e58613e0752f 100644
--- a/arch/tile/include/asm/setup.h
+++ b/arch/tile/include/asm/setup.h
@@ -31,6 +31,28 @@ void early_panic(const char *fmt, ...);
 void warn_early_printk(void);
 void __init disable_early_printk(void);
 
+/* Init-time routine to do tile-specific per-cpu setup. */
+void setup_cpu(int boot);
+
+/* User-level DMA management functions */
+void grant_dma_mpls(void);
+void restrict_dma_mpls(void);
+
+#ifdef CONFIG_HARDWALL
+/* User-level network management functions */
+void reset_network_state(void);
+void grant_network_mpls(void);
+void restrict_network_mpls(void);
+struct task_struct;
+int hardwall_deactivate(struct task_struct *task);
+
+/* Hook hardwall code into changes in affinity. */
+#define arch_set_cpus_allowed(p, new_mask) do { \
+	if (p->thread.hardwall && !cpumask_equal(&p->cpus_allowed, new_mask)) \
+		hardwall_deactivate(p); \
+} while (0)
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_TILE_SETUP_H */
diff --git a/arch/tile/include/asm/smp.h b/arch/tile/include/asm/smp.h
index 532124ae4b12..1aa759aeb5b3 100644
--- a/arch/tile/include/asm/smp.h
+++ b/arch/tile/include/asm/smp.h
@@ -43,10 +43,6 @@ void evaluate_message(int tag);
 /* Boot a secondary cpu */
 void online_secondary(void);
 
-/* Call a function on a specified set of CPUs (may include this one). */
-extern void on_each_cpu_mask(const struct cpumask *mask,
-			     void (*func)(void *), void *info, bool wait);
-
 /* Topology of the supervisor tile grid, and coordinates of boot processor */
 extern HV_Topology smp_topology;
 
@@ -91,9 +87,6 @@ void print_disabled_cpus(void);
 
 #else /* !CONFIG_SMP */
 
-#define on_each_cpu_mask(mask, func, info, wait)		\
-  do { if (cpumask_test_cpu(0, (mask))) func(info); } while (0)
-
 #define smp_master_cpu		0
 #define smp_height		1
 #define smp_width		1
diff --git a/arch/tile/include/asm/spinlock_32.h b/arch/tile/include/asm/spinlock_32.h
index a5e4208d34f9..c0a77b38d39a 100644
--- a/arch/tile/include/asm/spinlock_32.h
+++ b/arch/tile/include/asm/spinlock_32.h
@@ -19,7 +19,6 @@
 
 #include <linux/atomic.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <linux/compiler.h>
 
 /*
diff --git a/arch/tile/include/asm/switch_to.h b/arch/tile/include/asm/switch_to.h
new file mode 100644
index 000000000000..1d48c5fee8b7
--- /dev/null
+++ b/arch/tile/include/asm/switch_to.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef _ASM_TILE_SWITCH_TO_H
+#define _ASM_TILE_SWITCH_TO_H
+
+#include <arch/sim_def.h>
+
+/*
+ * switch_to(n) should switch tasks to task nr n, first
+ * checking that n isn't the current task, in which case it does nothing.
+ * The number of callee-saved registers saved on the kernel stack
+ * is defined here for use in copy_thread() and must agree with __switch_to().
+ */
+#define CALLEE_SAVED_FIRST_REG 30
+#define CALLEE_SAVED_REGS_COUNT 24   /* r30 to r52, plus an empty to align */
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+/*
+ * Pause the DMA engine and static network before task switching.
+ */
+#define prepare_arch_switch(next) _prepare_arch_switch(next)
+void _prepare_arch_switch(struct task_struct *next);
+
+struct task_struct;
+#define switch_to(prev, next, last) ((last) = _switch_to((prev), (next)))
+extern struct task_struct *_switch_to(struct task_struct *prev,
+				      struct task_struct *next);
+
+/* Helper function for _switch_to(). */
+extern struct task_struct *__switch_to(struct task_struct *prev,
+				       struct task_struct *next,
+				       unsigned long new_system_save_k_0);
+
+/* Address that switched-away from tasks are at. */
+extern unsigned long get_switch_to_pc(void);
+
+/*
+ * Kernel threads can check to see if they need to migrate their
+ * stack whenever they return from a context switch; for user
+ * threads, we defer until they are returning to user-space.
+ */
+#define finish_arch_switch(prev) do {                                     \
+	if (unlikely((prev)->state == TASK_DEAD))                         \
+		__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_EXIT |       \
+			((prev)->pid << _SIM_CONTROL_OPERATOR_BITS));     \
+	__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_SWITCH |             \
+		(current->pid << _SIM_CONTROL_OPERATOR_BITS));            \
+	if (current->mm == NULL && !kstack_hash &&                        \
+	    current_thread_info()->homecache_cpu != smp_processor_id())   \
+		homecache_migrate_kthread();                              \
+} while (0)
+
+/* Support function for forking a new task. */
+void ret_from_fork(void);
+
+/* Called from ret_from_fork() when a new process starts up. */
+struct task_struct *sim_notify_fork(struct task_struct *prev);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_TILE_SWITCH_TO_H */
diff --git a/arch/tile/include/asm/timex.h b/arch/tile/include/asm/timex.h
index 29921f0b86da..dc987d53e2a9 100644
--- a/arch/tile/include/asm/timex.h
+++ b/arch/tile/include/asm/timex.h
@@ -29,11 +29,13 @@ typedef unsigned long long cycles_t;
 
 #if CHIP_HAS_SPLIT_CYCLE()
 cycles_t get_cycles(void);
+#define get_cycles_low() __insn_mfspr(SPR_CYCLE_LOW)
 #else
 static inline cycles_t get_cycles(void)
 {
 	return __insn_mfspr(SPR_CYCLE);
 }
+#define get_cycles_low() __insn_mfspr(SPR_CYCLE)   /* just get all 64 bits */
 #endif
 
 cycles_t get_clock_rate(void);
diff --git a/arch/tile/include/asm/unaligned.h b/arch/tile/include/asm/unaligned.h
index 137e2de5b102..37dfbe598872 100644
--- a/arch/tile/include/asm/unaligned.h
+++ b/arch/tile/include/asm/unaligned.h
@@ -21,4 +21,19 @@
 #define get_unaligned	__get_unaligned_le
 #define put_unaligned	__put_unaligned_le
 
+/*
+ * Is the kernel doing fixups of unaligned accesses?  If <0, no kernel
+ * intervention occurs and SIGBUS is delivered with no data address
+ * info.  If 0, the kernel single-steps the instruction to discover
+ * the data address to provide with the SIGBUS.  If 1, the kernel does
+ * a fixup.
+ */
+extern int unaligned_fixup;
+
+/* Is the kernel printing on each unaligned fixup? */
+extern int unaligned_printk;
+
+/* Number of unaligned fixups performed */
+extern unsigned int unaligned_fixup_count;
+
 #endif /* _ASM_TILE_UNALIGNED_H */
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index bf5e9d70266c..d67459b9ac2a 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -16,7 +16,6 @@
 #define __SYSCALL_COMPAT
 
 #include <linux/compat.h>
-#include <linux/msg.h>
 #include <linux/syscalls.h>
 #include <linux/kdev_t.h>
 #include <linux/fs.h>
@@ -95,52 +94,10 @@ long compat_sys_sched_rr_get_interval(compat_pid_t pid,
 	return ret;
 }
 
-/*
- * The usual compat_sys_msgsnd() and _msgrcv() seem to be assuming
- * some different calling convention than our normal 32-bit tile code.
- */
-
-/* Already defined in ipc/compat.c, but we need it here. */
-struct compat_msgbuf {
-	compat_long_t mtype;
-	char mtext[1];
-};
-
-long tile_compat_sys_msgsnd(int msqid,
-			    struct compat_msgbuf __user *msgp,
-			    size_t msgsz, int msgflg)
-{
-	compat_long_t mtype;
-
-	if (get_user(mtype, &msgp->mtype))
-		return -EFAULT;
-	return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg);
-}
-
-long tile_compat_sys_msgrcv(int msqid,
-			    struct compat_msgbuf __user *msgp,
-			    size_t msgsz, long msgtyp, int msgflg)
-{
-	long err, mtype;
-
-	err =  do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg);
-	if (err < 0)
-		goto out;
-
-	if (put_user(mtype, &msgp->mtype))
-		err = -EFAULT;
- out:
-	return err;
-}
-
 /* Provide the compat syscall number to call mapping. */
 #undef __SYSCALL
 #define __SYSCALL(nr, call) [nr] = (call),
 
-/* The generic versions of these don't work for Tile. */
-#define compat_sys_msgrcv tile_compat_sys_msgrcv
-#define compat_sys_msgsnd tile_compat_sys_msgsnd
-
 /* See comments in sys.c */
 #define compat_sys_fadvise64_64 sys32_fadvise64_64
 #define compat_sys_readahead sys32_readahead
diff --git a/arch/tile/kernel/early_printk.c b/arch/tile/kernel/early_printk.c
index 493a0e66d916..afb9c9a0d887 100644
--- a/arch/tile/kernel/early_printk.c
+++ b/arch/tile/kernel/early_printk.c
@@ -16,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include <linux/irqflags.h>
 #include <asm/setup.h>
 #include <hv/hypervisor.h>
 
diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c
index 62d820833c68..7a9327046404 100644
--- a/arch/tile/kernel/proc.c
+++ b/arch/tile/kernel/proc.c
@@ -23,6 +23,7 @@
 #include <linux/sysctl.h>
 #include <linux/hardirq.h>
 #include <linux/mman.h>
+#include <asm/unaligned.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 6ae495ef2b99..30caecac94dc 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -27,16 +27,17 @@
 #include <linux/kernel.h>
 #include <linux/tracehook.h>
 #include <linux/signal.h>
-#include <asm/system.h>
 #include <asm/stack.h>
 #include <asm/homecache.h>
 #include <asm/syscalls.h>
 #include <asm/traps.h>
+#include <asm/setup.h>
 #ifdef CONFIG_HARDWALL
 #include <asm/hardwall.h>
 #endif
 #include <arch/chip.h>
 #include <arch/abi.h>
+#include <arch/sim_def.h>
 
 
 /*
diff --git a/arch/tile/kernel/regs_32.S b/arch/tile/kernel/regs_32.S
index caa13101c264..c12280c2d904 100644
--- a/arch/tile/kernel/regs_32.S
+++ b/arch/tile/kernel/regs_32.S
@@ -13,11 +13,11 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/system.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
 #include <arch/spr_def.h>
 #include <asm/processor.h>
+#include <asm/switch_to.h>
 
 /*
  * See <asm/system.h>; called with prev and next task_struct pointers.
diff --git a/arch/tile/kernel/regs_64.S b/arch/tile/kernel/regs_64.S
index f748c1e85285..0829fd01fa30 100644
--- a/arch/tile/kernel/regs_64.S
+++ b/arch/tile/kernel/regs_64.S
@@ -13,11 +13,11 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/system.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
 #include <arch/spr_def.h>
 #include <asm/processor.h>
+#include <asm/switch_to.h>
 
 /*
  * See <asm/system.h>; called with prev and next task_struct pointers.
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 5f85d8b34dbb..92a94f4920ad 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1100,7 +1100,7 @@ EXPORT_SYMBOL(hash_for_home_map);
 
 /*
  * cpu_cacheable_map lists all the cpus whose caches the hypervisor can
- * flush on our behalf.  It is set to cpu_possible_map OR'ed with
+ * flush on our behalf.  It is set to cpu_possible_mask OR'ed with
  * hash_for_home_map, and it is what should be passed to
  * hv_flush_remote() to flush all caches.  Note that if there are
  * dedicated hypervisor driver tiles that have authorized use of their
@@ -1186,7 +1186,7 @@ static void __init setup_cpu_maps(void)
 			      sizeof(cpu_lotar_map));
 	if (rc < 0) {
 		pr_err("warning: no HV_INQ_TILES_LOTAR; using AVAIL\n");
-		cpu_lotar_map = cpu_possible_map;
+		cpu_lotar_map = *cpu_possible_mask;
 	}
 
 #if CHIP_HAS_CBOX_HOME_MAP()
@@ -1196,9 +1196,9 @@ static void __init setup_cpu_maps(void)
 			      sizeof(hash_for_home_map));
 	if (rc < 0)
 		early_panic("hv_inquire_tiles(HFH_CACHE) failed: rc %d\n", rc);
-	cpumask_or(&cpu_cacheable_map, &cpu_possible_map, &hash_for_home_map);
+	cpumask_or(&cpu_cacheable_map, cpu_possible_mask, &hash_for_home_map);
 #else
-	cpu_cacheable_map = cpu_possible_map;
+	cpu_cacheable_map = *cpu_possible_mask;
 #endif
 }
 
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index b7a879504086..bc1eb586e24d 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -25,6 +25,7 @@
 #include <linux/types.h>
 #include <linux/err.h>
 #include <asm/cacheflush.h>
+#include <asm/unaligned.h>
 #include <arch/abi.h>
 #include <arch/opcode.h>
 
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index c52224d5ed45..a44e103c5a63 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -87,25 +87,6 @@ void send_IPI_allbutself(int tag)
 	send_IPI_many(&mask, tag);
 }
 
-
-/*
- * Provide smp_call_function_mask, but also run function locally
- * if specified in the mask.
- */
-void on_each_cpu_mask(const struct cpumask *mask, void (*func)(void *),
-		      void *info, bool wait)
-{
-	int cpu = get_cpu();
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(cpu, mask)) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-	}
-	put_cpu();
-}
-
-
 /*
  * Functions related to starting/stopping cpus.
  */
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 4f47b8a356df..2bb6602a1ee7 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -21,6 +21,7 @@
 #include <linux/ptrace.h>
 #include <asm/stack.h>
 #include <asm/traps.h>
+#include <asm/setup.h>
 
 #include <arch/interrupts.h>
 #include <arch/spr_def.h>
diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c
index 1a00fb64fc88..758b6038c2b7 100644
--- a/arch/tile/mm/elf.c
+++ b/arch/tile/mm/elf.c
@@ -21,6 +21,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
+#include <arch/sim_def.h>
 
 /* Notify a running simulator, if any, that an exec just occurred. */
 static void sim_notify_exec(const char *binary_name)
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index c1eaaa1fcc20..cba30e9547b4 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -35,7 +35,6 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
 #include <asm/traps.h>
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index 7309988c9794..830c4908ea76 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -38,7 +38,6 @@
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/dma.h>
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index de7d8e21e01d..87303693a072 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -27,7 +27,6 @@
 #include <linux/vmalloc.h>
 #include <linux/smp.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index b37ae706af3e..20a49ba93cb9 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -9,6 +9,7 @@ config UML
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
+	select GENERIC_IO
 
 config MMU
 	bool
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 28688e6d96d7..55c0661e2b5d 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -28,6 +28,7 @@ ifeq ($(SUBARCH),i386)
 endif
 ifeq ($(SUBARCH),x86_64)
         HEADER_ARCH := x86
+	KBUILD_CFLAGS += -mcmodel=large
 endif
 
 HOST_DIR := arch/$(HEADER_ARCH)
@@ -50,7 +51,7 @@ KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/um
 #
 # These apply to USER_CFLAGS to.
 
-KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ -DSUBARCH=\"$(SUBARCH)\" \
+KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ \
 	$(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap	\
 	-Din6addr_loopback=kernel_in6addr_loopback \
 	-Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr
@@ -99,7 +100,7 @@ KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig
 
 archheaders:
 	$(Q)$(MAKE) -C '$(srctree)' KBUILD_SRC= \
-		ARCH=$(SUBARCH) O='$(objtree)' archheaders
+		ARCH=$(HEADER_ARCH) O='$(objtree)' archheaders
 
 archprepare: include/generated/user_constants.h
 
diff --git a/arch/um/defconfig b/arch/um/defconfig
index 761f5e1a657e..fdc97e2c3d73 100644
--- a/arch/um/defconfig
+++ b/arch/um/defconfig
@@ -1,10 +1,8 @@
 #
-# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.24
-# Thu Feb  7 11:48:55 2008
+# Automatically generated file; DO NOT EDIT.
+# User Mode Linux/i386 3.3.0 Kernel Configuration
 #
 CONFIG_DEFCONFIG_LIST="arch/$ARCH/defconfig"
-CONFIG_GENERIC_HARDIRQS=y
 CONFIG_UML=y
 CONFIG_MMU=y
 CONFIG_NO_IOMEM=y
@@ -20,12 +18,10 @@ CONFIG_HZ=100
 #
 # UML-specific options
 #
-# CONFIG_STATIC_LINK is not set
 
 #
 # Host processor type and features
 #
-# CONFIG_M386 is not set
 # CONFIG_M486 is not set
 # CONFIG_M586 is not set
 # CONFIG_M586TSC is not set
@@ -41,17 +37,17 @@ CONFIG_M686=y
 # CONFIG_MCRUSOE is not set
 # CONFIG_MEFFICEON is not set
 # CONFIG_MWINCHIPC6 is not set
-# CONFIG_MWINCHIP2 is not set
 # CONFIG_MWINCHIP3D is not set
+# CONFIG_MELAN is not set
 # CONFIG_MGEODEGX1 is not set
 # CONFIG_MGEODE_LX is not set
 # CONFIG_MCYRIXIII is not set
 # CONFIG_MVIAC3_2 is not set
 # CONFIG_MVIAC7 is not set
-# CONFIG_MPSC is not set
 # CONFIG_MCORE2 is not set
-# CONFIG_GENERIC_CPU is not set
+# CONFIG_MATOM is not set
 # CONFIG_X86_GENERIC is not set
+CONFIG_X86_INTERNODE_CACHE_SHIFT=5
 CONFIG_X86_CMPXCHG=y
 CONFIG_X86_L1_CACHE_SHIFT=5
 CONFIG_X86_XADD=y
@@ -60,47 +56,59 @@ CONFIG_X86_WP_WORKS_OK=y
 CONFIG_X86_INVLPG=y
 CONFIG_X86_BSWAP=y
 CONFIG_X86_POPAD_OK=y
-CONFIG_X86_GOOD_APIC=y
 CONFIG_X86_USE_PPRO_CHECKSUM=y
 CONFIG_X86_TSC=y
+CONFIG_X86_CMPXCHG64=y
 CONFIG_X86_CMOV=y
-CONFIG_X86_MINIMUM_CPU_FAMILY=4
-CONFIG_X86_DEBUGCTLMSR=y
+CONFIG_X86_MINIMUM_CPU_FAMILY=5
+CONFIG_CPU_SUP_INTEL=y
+CONFIG_CPU_SUP_CYRIX_32=y
+CONFIG_CPU_SUP_AMD=y
+CONFIG_CPU_SUP_CENTAUR=y
+CONFIG_CPU_SUP_TRANSMETA_32=y
+CONFIG_CPU_SUP_UMC_32=y
 CONFIG_UML_X86=y
-CONFIG_X86_32=y
-CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 # CONFIG_64BIT is not set
-CONFIG_SEMAPHORE_SLEEPERS=y
+CONFIG_X86_32=y
+# CONFIG_X86_64 is not set
+# CONFIG_RWSEM_XCHGADD_ALGORITHM is not set
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
 # CONFIG_3_LEVEL_PGTABLES is not set
 CONFIG_ARCH_HAS_SC_SIGNALS=y
 CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA=y
 CONFIG_GENERIC_HWEIGHT=y
+# CONFIG_STATIC_LINK is not set
 CONFIG_SELECT_MEMORY_MODEL=y
 CONFIG_FLATMEM_MANUAL=y
-# CONFIG_DISCONTIGMEM_MANUAL is not set
-# CONFIG_SPARSEMEM_MANUAL is not set
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
-# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
-# CONFIG_RESOURCES_64BIT is not set
+# CONFIG_COMPACTION is not set
+# CONFIG_PHYS_ADDR_T_64BIT is not set
 CONFIG_ZONE_DMA_FLAG=0
 CONFIG_VIRT_TO_BUS=y
+# CONFIG_KSM is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
+CONFIG_NEED_PER_CPU_KM=y
+# CONFIG_CLEANCACHE is not set
 CONFIG_TICK_ONESHOT=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 CONFIG_LD_SCRIPT_DYN=y
 CONFIG_BINFMT_ELF=y
+CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
+CONFIG_HAVE_AOUT=y
 # CONFIG_BINFMT_AOUT is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HOSTFS=y
 # CONFIG_HPPFS is not set
 CONFIG_MCONSOLE=y
 CONFIG_MAGIC_SYSRQ=y
-# CONFIG_HIGHMEM is not set
 CONFIG_KERNEL_STACK_ORDER=0
+# CONFIG_MMAPPER is not set
+CONFIG_NO_DMA=y
 
 #
 # General setup
@@ -108,99 +116,169 @@ CONFIG_KERNEL_STACK_ORDER=0
 CONFIG_EXPERIMENTAL=y
 CONFIG_BROKEN_ON_SMP=y
 CONFIG_INIT_ENV_ARG_LIMIT=128
+CONFIG_CROSS_COMPILE=""
 CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
+CONFIG_DEFAULT_HOSTNAME="(none)"
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
+# CONFIG_FHANDLE is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_USER_NS is not set
-# CONFIG_PID_NS is not set
 # CONFIG_AUDIT is not set
+CONFIG_HAVE_GENERIC_HARDIRQS=y
+
+#
+# IRQ subsystem
+#
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_SHOW=y
+
+#
+# RCU Subsystem
+#
+CONFIG_TINY_RCU=y
+# CONFIG_PREEMPT_RCU is not set
+# CONFIG_RCU_TRACE is not set
+# CONFIG_TREE_RCU_TRACE is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CGROUPS is not set
+CONFIG_CGROUPS=y
+# CONFIG_CGROUP_DEBUG is not set
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CPUSETS=y
+CONFIG_PROC_PID_CPUSET=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+# CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED is not set
+# CONFIG_CGROUP_MEM_RES_CTLR_KMEM is not set
+CONFIG_CGROUP_SCHED=y
 CONFIG_FAIR_GROUP_SCHED=y
-CONFIG_FAIR_USER_SCHED=y
-# CONFIG_FAIR_CGROUP_SCHED is not set
+# CONFIG_CFS_BANDWIDTH is not set
+# CONFIG_RT_GROUP_SCHED is not set
+CONFIG_BLK_CGROUP=m
+# CONFIG_DEBUG_BLK_CGROUP is not set
+# CONFIG_CHECKPOINT_RESTORE is not set
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+# CONFIG_USER_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_NET_NS=y
+# CONFIG_SCHED_AUTOGROUP is not set
+CONFIG_MM_OWNER=y
 CONFIG_SYSFS_DEPRECATED=y
+# CONFIG_SYSFS_DEPRECATED_V2 is not set
 # CONFIG_RELAY is not set
 # CONFIG_BLK_DEV_INITRD is not set
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
 # CONFIG_EXPERT is not set
 CONFIG_UID16=y
-CONFIG_SYSCTL_SYSCALL=y
+# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
-CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
-CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
 CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
+CONFIG_AIO=y
+# CONFIG_EMBEDDED is not set
+
+#
+# Kernel Performance Events And Counters
+#
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_COMPAT_BRK=y
 CONFIG_SLAB=y
 # CONFIG_SLUB is not set
-# CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
-# CONFIG_MARKERS is not set
-# CONFIG_HAVE_OPROFILE is not set
-# CONFIG_HAVE_KPROBES is not set
-CONFIG_PROC_PAGE_MONITOR=y
+
+#
+# GCOV-based kernel profiling
+#
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
-# CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
 CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_FORCE_UNLOAD is not set
 # CONFIG_MODVERSIONS is not set
 # CONFIG_MODULE_SRCVERSION_ALL is not set
-CONFIG_KMOD=y
 CONFIG_BLOCK=y
-# CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
-# CONFIG_LSF is not set
+CONFIG_LBDAF=y
 # CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_BSGLIB is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
 
 #
 # IO Schedulers
 #
 CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
 CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
-CONFIG_DEFAULT_AS=y
-# CONFIG_DEFAULT_DEADLINE is not set
+CONFIG_IOSCHED_CFQ=m
+# CONFIG_CFQ_GROUP_IOSCHED is not set
+CONFIG_DEFAULT_DEADLINE=y
 # CONFIG_DEFAULT_CFQ is not set
 # CONFIG_DEFAULT_NOOP is not set
-CONFIG_DEFAULT_IOSCHED="anticipatory"
-CONFIG_CLASSIC_RCU=y
-# CONFIG_PREEMPT_RCU is not set
-CONFIG_BLK_DEV=y
-CONFIG_BLK_DEV_UBD=y
-# CONFIG_BLK_DEV_UBD_SYNC is not set
-CONFIG_BLK_DEV_COW_COMMON=y
-CONFIG_BLK_DEV_LOOP=m
-# CONFIG_BLK_DEV_CRYPTOLOOP is not set
-CONFIG_BLK_DEV_NBD=m
-# CONFIG_BLK_DEV_RAM is not set
-# CONFIG_ATA_OVER_ETH is not set
+CONFIG_DEFAULT_IOSCHED="deadline"
+# CONFIG_INLINE_SPIN_TRYLOCK is not set
+# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set
+# CONFIG_INLINE_SPIN_LOCK is not set
+# CONFIG_INLINE_SPIN_LOCK_BH is not set
+# CONFIG_INLINE_SPIN_LOCK_IRQ is not set
+# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set
+CONFIG_INLINE_SPIN_UNLOCK=y
+# CONFIG_INLINE_SPIN_UNLOCK_BH is not set
+CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
+# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set
+# CONFIG_INLINE_READ_TRYLOCK is not set
+# CONFIG_INLINE_READ_LOCK is not set
+# CONFIG_INLINE_READ_LOCK_BH is not set
+# CONFIG_INLINE_READ_LOCK_IRQ is not set
+# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set
+CONFIG_INLINE_READ_UNLOCK=y
+# CONFIG_INLINE_READ_UNLOCK_BH is not set
+CONFIG_INLINE_READ_UNLOCK_IRQ=y
+# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set
+# CONFIG_INLINE_WRITE_TRYLOCK is not set
+# CONFIG_INLINE_WRITE_LOCK is not set
+# CONFIG_INLINE_WRITE_LOCK_BH is not set
+# CONFIG_INLINE_WRITE_LOCK_IRQ is not set
+# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set
+CONFIG_INLINE_WRITE_UNLOCK=y
+# CONFIG_INLINE_WRITE_UNLOCK_BH is not set
+CONFIG_INLINE_WRITE_UNLOCK_IRQ=y
+# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set
+# CONFIG_MUTEX_SPIN_ON_OWNER is not set
+CONFIG_FREEZER=y
 
 #
-# Character Devices
+# UML Character Devices
 #
 CONFIG_STDERR_CONSOLE=y
 CONFIG_STDIO_CONSOLE=y
@@ -214,40 +292,191 @@ CONFIG_XTERM_CHAN=y
 CONFIG_CON_ZERO_CHAN="fd:0,fd:1"
 CONFIG_CON_CHAN="xterm"
 CONFIG_SSL_CHAN="pts"
-CONFIG_UNIX98_PTYS=y
-CONFIG_LEGACY_PTYS=y
-# CONFIG_RAW_DRIVER is not set
-CONFIG_LEGACY_PTY_COUNT=32
-# CONFIG_WATCHDOG is not set
 CONFIG_UML_SOUND=m
 CONFIG_SOUND=m
+CONFIG_SOUND_OSS_CORE=y
 CONFIG_HOSTAUDIO=m
-# CONFIG_HW_RANDOM is not set
-CONFIG_UML_RANDOM=y
-# CONFIG_MMAPPER is not set
+
+#
+# Device Drivers
+#
 
 #
 # Generic Driver Options
 #
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
-# CONFIG_FW_LOADER is not set
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
 # CONFIG_DEBUG_DRIVER is not set
 # CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
+CONFIG_GENERIC_CPU_DEVICES=y
+# CONFIG_DMA_SHARED_BUFFER is not set
+# CONFIG_CONNECTOR is not set
+# CONFIG_MTD is not set
+CONFIG_BLK_DEV=y
+CONFIG_BLK_DEV_UBD=y
+# CONFIG_BLK_DEV_UBD_SYNC is not set
+CONFIG_BLK_DEV_COW_COMMON=y
+CONFIG_BLK_DEV_LOOP=m
+CONFIG_BLK_DEV_LOOP_MIN_COUNT=8
+# CONFIG_BLK_DEV_CRYPTOLOOP is not set
+
+#
+# DRBD disabled because PROC_FS, INET or CONNECTOR not selected
+#
+CONFIG_BLK_DEV_NBD=m
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_ATA_OVER_ETH is not set
+# CONFIG_BLK_DEV_RBD is not set
+
+#
+# Misc devices
+#
+# CONFIG_ENCLOSURE_SERVICES is not set
+# CONFIG_C2PORT is not set
+
+#
+# EEPROM support
+#
+# CONFIG_EEPROM_93CX6 is not set
+
+#
+# Texas Instruments shared transport line discipline
+#
+
+#
+# Altera FPGA firmware download module
+#
+
+#
+# SCSI device support
+#
+CONFIG_SCSI_MOD=y
+# CONFIG_RAID_ATTRS is not set
+# CONFIG_SCSI is not set
+# CONFIG_SCSI_DMA is not set
+# CONFIG_SCSI_NETLINK is not set
+# CONFIG_MD is not set
+CONFIG_NETDEVICES=y
+CONFIG_NET_CORE=y
+# CONFIG_BONDING is not set
+CONFIG_DUMMY=m
+# CONFIG_EQUALIZER is not set
+# CONFIG_MII is not set
+# CONFIG_NET_TEAM is not set
+# CONFIG_MACVLAN is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+CONFIG_TUN=m
+# CONFIG_VETH is not set
+
+#
+# CAIF transport drivers
+#
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_CHELSIO=y
+CONFIG_NET_VENDOR_INTEL=y
+CONFIG_NET_VENDOR_I825XX=y
+CONFIG_NET_VENDOR_MARVELL=y
+CONFIG_NET_VENDOR_NATSEMI=y
+CONFIG_NET_VENDOR_8390=y
+# CONFIG_PHYLIB is not set
+CONFIG_PPP=m
+# CONFIG_PPP_BSDCOMP is not set
+# CONFIG_PPP_DEFLATE is not set
+# CONFIG_PPP_FILTER is not set
+# CONFIG_PPP_MPPE is not set
+# CONFIG_PPP_MULTILINK is not set
+# CONFIG_PPPOE is not set
+# CONFIG_PPP_ASYNC is not set
+# CONFIG_PPP_SYNC_TTY is not set
+CONFIG_SLIP=m
+CONFIG_SLHC=m
+# CONFIG_SLIP_COMPRESSED is not set
+# CONFIG_SLIP_SMART is not set
+# CONFIG_SLIP_MODE_SLIP6 is not set
+CONFIG_WLAN=y
+# CONFIG_HOSTAP is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
+# CONFIG_WAN is not set
+
+#
+# Character devices
+#
+CONFIG_UNIX98_PTYS=y
+# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=32
+# CONFIG_N_GSM is not set
+# CONFIG_TRACE_SINK is not set
+CONFIG_DEVKMEM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_UML_RANDOM=y
+# CONFIG_R3964 is not set
+# CONFIG_NSC_GPIO is not set
+# CONFIG_RAW_DRIVER is not set
+
+#
+# PPS support
+#
+# CONFIG_PPS is not set
+
+#
+# PPS generators support
+#
+
+#
+# PTP clock support
+#
+
+#
+# Enable Device Drivers -> PPS to see the PTP clock options.
+#
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_THERMAL is not set
+# CONFIG_WATCHDOG is not set
+# CONFIG_REGULATOR is not set
+CONFIG_SOUND_OSS_CORE_PRECLAIM=y
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_AUXDISPLAY is not set
+# CONFIG_UIO is not set
+
+#
+# Virtio drivers
+#
+# CONFIG_VIRTIO_BALLOON is not set
+
+#
+# Microsoft Hyper-V guest support
+#
+# CONFIG_STAGING is not set
 
 #
-# Networking
+# Hardware Spinlock drivers
 #
+CONFIG_IOMMU_SUPPORT=y
+# CONFIG_VIRT_DRIVERS is not set
+# CONFIG_PM_DEVFREQ is not set
 CONFIG_NET=y
 
 #
 # Networking options
 #
 CONFIG_PACKET=y
-CONFIG_PACKET_MMAP=y
 CONFIG_UNIX=y
+# CONFIG_UNIX_DIAG is not set
 CONFIG_XFRM=y
 # CONFIG_XFRM_USER is not set
 # CONFIG_XFRM_SUB_POLICY is not set
@@ -257,10 +486,9 @@ CONFIG_XFRM=y
 CONFIG_INET=y
 # CONFIG_IP_MULTICAST is not set
 # CONFIG_IP_ADVANCED_ROUTER is not set
-CONFIG_IP_FIB_HASH=y
 # CONFIG_IP_PNP is not set
 # CONFIG_NET_IPIP is not set
-# CONFIG_NET_IPGRE is not set
+# CONFIG_NET_IPGRE_DEMUX is not set
 # CONFIG_ARPD is not set
 # CONFIG_SYN_COOKIES is not set
 # CONFIG_INET_AH is not set
@@ -274,20 +502,23 @@ CONFIG_INET_XFRM_MODE_BEET=y
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
+# CONFIG_INET_UDP_DIAG is not set
 # CONFIG_TCP_CONG_ADVANCED is not set
 CONFIG_TCP_CONG_CUBIC=y
 CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_TCP_MD5SIG is not set
 # CONFIG_IPV6 is not set
-# CONFIG_INET6_XFRM_TUNNEL is not set
-# CONFIG_INET6_TUNNEL is not set
 # CONFIG_NETWORK_SECMARK is not set
+# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
 # CONFIG_NETFILTER is not set
 # CONFIG_IP_DCCP is not set
 # CONFIG_IP_SCTP is not set
+# CONFIG_RDS is not set
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
+# CONFIG_L2TP is not set
 # CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
 # CONFIG_LLC2 is not set
@@ -297,7 +528,14 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
+# CONFIG_PHONET is not set
+# CONFIG_IEEE802154 is not set
 # CONFIG_NET_SCHED is not set
+# CONFIG_DCB is not set
+# CONFIG_BATMAN_ADV is not set
+# CONFIG_OPENVSWITCH is not set
+# CONFIG_NETPRIO_CGROUP is not set
+CONFIG_BQL=y
 
 #
 # Network testing
@@ -308,16 +546,19 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
+CONFIG_WIRELESS=y
+# CONFIG_CFG80211 is not set
+# CONFIG_LIB80211 is not set
 
 #
-# Wireless
+# CFG80211 needs to be enabled for MAC80211
 #
-# CONFIG_CFG80211 is not set
-# CONFIG_WIRELESS_EXT is not set
-# CONFIG_MAC80211 is not set
-# CONFIG_IEEE80211 is not set
+# CONFIG_WIMAX is not set
 # CONFIG_RFKILL is not set
 # CONFIG_NET_9P is not set
+# CONFIG_CAIF is not set
+# CONFIG_CEPH_LIB is not set
+# CONFIG_NFC is not set
 
 #
 # UML Network Devices
@@ -331,76 +572,51 @@ CONFIG_UML_NET_DAEMON=y
 CONFIG_UML_NET_MCAST=y
 # CONFIG_UML_NET_PCAP is not set
 CONFIG_UML_NET_SLIRP=y
-CONFIG_NETDEVICES=y
-# CONFIG_NETDEVICES_MULTIQUEUE is not set
-CONFIG_DUMMY=m
-# CONFIG_BONDING is not set
-# CONFIG_MACVLAN is not set
-# CONFIG_EQUALIZER is not set
-CONFIG_TUN=m
-# CONFIG_VETH is not set
-
-#
-# Wireless LAN
-#
-# CONFIG_WLAN_PRE80211 is not set
-# CONFIG_WLAN_80211 is not set
-# CONFIG_WAN is not set
-CONFIG_PPP=m
-# CONFIG_PPP_MULTILINK is not set
-# CONFIG_PPP_FILTER is not set
-# CONFIG_PPP_ASYNC is not set
-# CONFIG_PPP_SYNC_TTY is not set
-# CONFIG_PPP_DEFLATE is not set
-# CONFIG_PPP_BSDCOMP is not set
-# CONFIG_PPP_MPPE is not set
-# CONFIG_PPPOE is not set
-# CONFIG_PPPOL2TP is not set
-CONFIG_SLIP=m
-# CONFIG_SLIP_COMPRESSED is not set
-CONFIG_SLHC=m
-# CONFIG_SLIP_SMART is not set
-# CONFIG_SLIP_MODE_SLIP6 is not set
-# CONFIG_NETCONSOLE is not set
-# CONFIG_NETPOLL is not set
-# CONFIG_NET_POLL_CONTROLLER is not set
-# CONFIG_CONNECTOR is not set
 
 #
 # File systems
 #
-CONFIG_EXT2_FS=y
-# CONFIG_EXT2_FS_XATTR is not set
-# CONFIG_EXT2_FS_XIP is not set
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
-# CONFIG_EXT4DEV_FS is not set
-CONFIG_JBD=y
+# CONFIG_EXT2_FS is not set
+# CONFIG_EXT3_FS is not set
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_USE_FOR_EXT23=y
+CONFIG_EXT4_FS_XATTR=y
+# CONFIG_EXT4_FS_POSIX_ACL is not set
+# CONFIG_EXT4_FS_SECURITY is not set
+# CONFIG_EXT4_DEBUG is not set
+CONFIG_JBD2=y
+CONFIG_FS_MBCACHE=y
 CONFIG_REISERFS_FS=y
 # CONFIG_REISERFS_CHECK is not set
 # CONFIG_REISERFS_PROC_INFO is not set
 # CONFIG_REISERFS_FS_XATTR is not set
 # CONFIG_JFS_FS is not set
-# CONFIG_FS_POSIX_ACL is not set
 # CONFIG_XFS_FS is not set
 # CONFIG_GFS2_FS is not set
-# CONFIG_OCFS2_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
-CONFIG_INOTIFY=y
+# CONFIG_BTRFS_FS is not set
+# CONFIG_NILFS2_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+CONFIG_FILE_LOCKING=y
+CONFIG_FSNOTIFY=y
+CONFIG_DNOTIFY=y
 CONFIG_INOTIFY_USER=y
+# CONFIG_FANOTIFY is not set
 CONFIG_QUOTA=y
 # CONFIG_QUOTA_NETLINK_INTERFACE is not set
 CONFIG_PRINT_QUOTA_WARNING=y
+# CONFIG_QUOTA_DEBUG is not set
 # CONFIG_QFMT_V1 is not set
 # CONFIG_QFMT_V2 is not set
 CONFIG_QUOTACTL=y
-CONFIG_DNOTIFY=y
-CONFIG_AUTOFS_FS=m
 CONFIG_AUTOFS4_FS=m
 # CONFIG_FUSE_FS is not set
 
 #
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
 # CD-ROM/DVD Filesystems
 #
 CONFIG_ISO9660_FS=m
@@ -421,15 +637,14 @@ CONFIG_JOLIET=y
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 # CONFIG_TMPFS_POSIX_ACL is not set
+# CONFIG_TMPFS_XATTR is not set
 # CONFIG_HUGETLB_PAGE is not set
 # CONFIG_CONFIGFS_FS is not set
-
-#
-# Miscellaneous filesystems
-#
+CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ADFS_FS is not set
 # CONFIG_AFFS_FS is not set
 # CONFIG_HFS_FS is not set
@@ -437,26 +652,26 @@ CONFIG_TMPFS=y
 # CONFIG_BEFS_FS is not set
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
+# CONFIG_LOGFS is not set
 # CONFIG_CRAMFS is not set
+# CONFIG_SQUASHFS is not set
 # CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_PSTORE is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
-# CONFIG_SMB_FS is not set
+# CONFIG_CEPH_FS is not set
 # CONFIG_CIFS is not set
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_AFS_FS is not set
-
-#
-# Partition Types
-#
-# CONFIG_PARTITION_ADVANCED is not set
-CONFIG_MSDOS_PARTITION=y
 CONFIG_NLS=y
 CONFIG_NLS_DEFAULT="iso8859-1"
 # CONFIG_NLS_CODEPAGE_437 is not set
@@ -497,119 +712,191 @@ CONFIG_NLS_DEFAULT="iso8859-1"
 # CONFIG_NLS_KOI8_R is not set
 # CONFIG_NLS_KOI8_U is not set
 # CONFIG_NLS_UTF8 is not set
-# CONFIG_DLM is not set
 
 #
 # Security options
 #
 # CONFIG_KEYS is not set
+# CONFIG_SECURITY_DMESG_RESTRICT is not set
 # CONFIG_SECURITY is not set
-# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+# CONFIG_SECURITYFS is not set
+CONFIG_DEFAULT_SECURITY_DAC=y
+CONFIG_DEFAULT_SECURITY=""
 CONFIG_CRYPTO=y
-# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_FIPS is not set
+CONFIG_CRYPTO_ALGAPI=m
+CONFIG_CRYPTO_ALGAPI2=m
+CONFIG_CRYPTO_RNG=m
+CONFIG_CRYPTO_RNG2=m
 # CONFIG_CRYPTO_MANAGER is not set
+# CONFIG_CRYPTO_MANAGER2 is not set
+# CONFIG_CRYPTO_USER is not set
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+# CONFIG_CRYPTO_CBC is not set
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+# CONFIG_CRYPTO_ECB is not set
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
 # CONFIG_CRYPTO_HMAC is not set
 # CONFIG_CRYPTO_XCBC is not set
-# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_VMAC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_GHASH is not set
 # CONFIG_CRYPTO_MD4 is not set
 # CONFIG_CRYPTO_MD5 is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
 # CONFIG_CRYPTO_SHA1 is not set
 # CONFIG_CRYPTO_SHA256 is not set
 # CONFIG_CRYPTO_SHA512 is not set
-# CONFIG_CRYPTO_WP512 is not set
 # CONFIG_CRYPTO_TGR192 is not set
-# CONFIG_CRYPTO_GF128MUL is not set
-# CONFIG_CRYPTO_ECB is not set
-# CONFIG_CRYPTO_CBC is not set
-# CONFIG_CRYPTO_PCBC is not set
-# CONFIG_CRYPTO_LRW is not set
-# CONFIG_CRYPTO_XTS is not set
-# CONFIG_CRYPTO_CTR is not set
-# CONFIG_CRYPTO_GCM is not set
-# CONFIG_CRYPTO_CCM is not set
-# CONFIG_CRYPTO_CRYPTD is not set
-# CONFIG_CRYPTO_DES is not set
-# CONFIG_CRYPTO_FCRYPT is not set
-# CONFIG_CRYPTO_BLOWFISH is not set
-# CONFIG_CRYPTO_TWOFISH is not set
-# CONFIG_CRYPTO_TWOFISH_586 is not set
-# CONFIG_CRYPTO_SERPENT is not set
-# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=m
 # CONFIG_CRYPTO_AES_586 is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
 # CONFIG_CRYPTO_CAST5 is not set
 # CONFIG_CRYPTO_CAST6 is not set
-# CONFIG_CRYPTO_TEA is not set
-# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_DES is not set
+# CONFIG_CRYPTO_FCRYPT is not set
 # CONFIG_CRYPTO_KHAZAD is not set
-# CONFIG_CRYPTO_ANUBIS is not set
-# CONFIG_CRYPTO_SEED is not set
 # CONFIG_CRYPTO_SALSA20 is not set
 # CONFIG_CRYPTO_SALSA20_586 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+# CONFIG_CRYPTO_TWOFISH_586 is not set
+
+#
+# Compression
+#
 # CONFIG_CRYPTO_DEFLATE is not set
-# CONFIG_CRYPTO_MICHAEL_MIC is not set
-# CONFIG_CRYPTO_CRC32C is not set
-# CONFIG_CRYPTO_CAMELLIA is not set
-# CONFIG_CRYPTO_TEST is not set
-# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_ZLIB is not set
 # CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
+CONFIG_CRYPTO_ANSI_CPRNG=m
+# CONFIG_CRYPTO_USER_API_HASH is not set
+# CONFIG_CRYPTO_USER_API_SKCIPHER is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
 #
-CONFIG_BITREVERSE=m
+CONFIG_BITREVERSE=y
+CONFIG_GENERIC_FIND_FIRST_BIT=y
+CONFIG_GENERIC_IO=y
 # CONFIG_CRC_CCITT is not set
-# CONFIG_CRC16 is not set
+CONFIG_CRC16=y
+# CONFIG_CRC_T10DIF is not set
 # CONFIG_CRC_ITU_T is not set
-CONFIG_CRC32=m
+CONFIG_CRC32=y
 # CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
-CONFIG_PLIST=y
-
-#
-# SCSI device support
-#
-# CONFIG_RAID_ATTRS is not set
-# CONFIG_SCSI is not set
-# CONFIG_SCSI_DMA is not set
-# CONFIG_SCSI_NETLINK is not set
-# CONFIG_MD is not set
-# CONFIG_INPUT is not set
+# CONFIG_CRC8 is not set
+# CONFIG_XZ_DEC is not set
+# CONFIG_XZ_DEC_BCJ is not set
+CONFIG_DQL=y
+CONFIG_NLATTR=y
+# CONFIG_AVERAGE is not set
+# CONFIG_CORDIC is not set
 
 #
 # Kernel hacking
 #
 # CONFIG_PRINTK_TIME is not set
+CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4
 CONFIG_ENABLE_WARN_DEPRECATED=y
 CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=1024
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_UNUSED_SYMBOLS is not set
 # CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_SECTION_MISMATCH is not set
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
-CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_LOCKUP_DETECTOR is not set
+# CONFIG_HARDLOCKUP_DETECTOR is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
+# CONFIG_DEBUG_OBJECTS is not set
 # CONFIG_DEBUG_SLAB is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
 # CONFIG_DEBUG_MUTEXES is not set
-# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
+# CONFIG_SPARSE_RCU_POINTER is not set
+# CONFIG_DEBUG_ATOMIC_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+# CONFIG_DEBUG_STACK_USAGE is not set
 # CONFIG_DEBUG_KOBJECT is not set
 CONFIG_DEBUG_BUGVERBOSE=y
 CONFIG_DEBUG_INFO=y
+# CONFIG_DEBUG_INFO_REDUCED is not set
 # CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
+CONFIG_DEBUG_MEMORY_INIT=y
 # CONFIG_DEBUG_LIST is not set
+# CONFIG_TEST_LIST_SORT is not set
 # CONFIG_DEBUG_SG is not set
+# CONFIG_DEBUG_NOTIFIERS is not set
+# CONFIG_DEBUG_CREDENTIALS is not set
 CONFIG_FRAME_POINTER=y
-CONFIG_FORCED_INLINING=y
 # CONFIG_BOOT_PRINTK_DELAY is not set
 # CONFIG_RCU_TORTURE_TEST is not set
 # CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
 # CONFIG_FAULT_INJECTION is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_ATOMIC64_SELFTEST is not set
 # CONFIG_SAMPLES is not set
+# CONFIG_TEST_KSTRTOX is not set
 # CONFIG_GPROF is not set
 # CONFIG_GCOV is not set
-# CONFIG_DEBUG_STACK_USAGE is not set
+CONFIG_EARLY_PRINTK=y
diff --git a/arch/um/drivers/chan.h b/arch/um/drivers/chan.h
index 8df0fd9024dc..02b5a76e98d9 100644
--- a/arch/um/drivers/chan.h
+++ b/arch/um/drivers/chan.h
@@ -27,24 +27,24 @@ struct chan {
 	void *data;
 };
 
-extern void chan_interrupt(struct list_head *chans, struct delayed_work *task,
+extern void chan_interrupt(struct line *line,
 			   struct tty_struct *tty, int irq);
 extern int parse_chan_pair(char *str, struct line *line, int device,
 			   const struct chan_opts *opts, char **error_out);
-extern int write_chan(struct list_head *chans, const char *buf, int len,
+extern int write_chan(struct chan *chan, const char *buf, int len,
 			     int write_irq);
-extern int console_write_chan(struct list_head *chans, const char *buf, 
+extern int console_write_chan(struct chan *chan, const char *buf, 
 			      int len);
 extern int console_open_chan(struct line *line, struct console *co);
-extern void deactivate_chan(struct list_head *chans, int irq);
-extern void reactivate_chan(struct list_head *chans, int irq);
-extern void chan_enable_winch(struct list_head *chans, struct tty_struct *tty);
+extern void deactivate_chan(struct chan *chan, int irq);
+extern void reactivate_chan(struct chan *chan, int irq);
+extern void chan_enable_winch(struct chan *chan, struct tty_struct *tty);
 extern int enable_chan(struct line *line);
-extern void close_chan(struct list_head *chans, int delay_free_irq);
-extern int chan_window_size(struct list_head *chans, 
+extern void close_chan(struct line *line);
+extern int chan_window_size(struct line *line, 
 			     unsigned short *rows_out, 
 			     unsigned short *cols_out);
-extern int chan_config_string(struct list_head *chans, char *str, int size,
+extern int chan_config_string(struct line *line, char *str, int size,
 			      char **error_out);
 
 #endif
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index 420e2c800799..ca4c7ebfd0aa 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -140,18 +140,18 @@ static int open_chan(struct list_head *chans)
 	return err;
 }
 
-void chan_enable_winch(struct list_head *chans, struct tty_struct *tty)
+void chan_enable_winch(struct chan *chan, struct tty_struct *tty)
 {
-	struct list_head *ele;
-	struct chan *chan;
+	if (chan && chan->primary && chan->ops->winch)
+		register_winch(chan->fd, tty);
+}
 
-	list_for_each(ele, chans) {
-		chan = list_entry(ele, struct chan, list);
-		if (chan->primary && chan->output && chan->ops->winch) {
-			register_winch(chan->fd, tty);
-			return;
-		}
-	}
+static void line_timer_cb(struct work_struct *work)
+{
+	struct line *line = container_of(work, struct line, task.work);
+
+	if (!line->throttled)
+		chan_interrupt(line, line->tty, line->driver->read_irq);
 }
 
 int enable_chan(struct line *line)
@@ -160,6 +160,8 @@ int enable_chan(struct line *line)
 	struct chan *chan;
 	int err;
 
+	INIT_DELAYED_WORK(&line->task, line_timer_cb);
+
 	list_for_each(ele, &line->chan_list) {
 		chan = list_entry(ele, struct chan, list);
 		err = open_one_chan(chan);
@@ -183,7 +185,7 @@ int enable_chan(struct line *line)
 	return 0;
 
  out_close:
-	close_chan(&line->chan_list, 0);
+	close_chan(line);
 	return err;
 }
 
@@ -244,7 +246,7 @@ static void close_one_chan(struct chan *chan, int delay_free_irq)
 	chan->fd = -1;
 }
 
-void close_chan(struct list_head *chans, int delay_free_irq)
+void close_chan(struct line *line)
 {
 	struct chan *chan;
 
@@ -253,77 +255,50 @@ void close_chan(struct list_head *chans, int delay_free_irq)
 	 * state.  Then, the first one opened will have the original state,
 	 * so it must be the last closed.
 	 */
-	list_for_each_entry_reverse(chan, chans, list) {
-		close_one_chan(chan, delay_free_irq);
+	list_for_each_entry_reverse(chan, &line->chan_list, list) {
+		close_one_chan(chan, 0);
 	}
 }
 
-void deactivate_chan(struct list_head *chans, int irq)
+void deactivate_chan(struct chan *chan, int irq)
 {
-	struct list_head *ele;
-
-	struct chan *chan;
-	list_for_each(ele, chans) {
-		chan = list_entry(ele, struct chan, list);
-
-		if (chan->enabled && chan->input)
-			deactivate_fd(chan->fd, irq);
-	}
+	if (chan && chan->enabled)
+		deactivate_fd(chan->fd, irq);
 }
 
-void reactivate_chan(struct list_head *chans, int irq)
+void reactivate_chan(struct chan *chan, int irq)
 {
-	struct list_head *ele;
-	struct chan *chan;
-
-	list_for_each(ele, chans) {
-		chan = list_entry(ele, struct chan, list);
-
-		if (chan->enabled && chan->input)
-			reactivate_fd(chan->fd, irq);
-	}
+	if (chan && chan->enabled)
+		reactivate_fd(chan->fd, irq);
 }
 
-int write_chan(struct list_head *chans, const char *buf, int len,
+int write_chan(struct chan *chan, const char *buf, int len,
 	       int write_irq)
 {
-	struct list_head *ele;
-	struct chan *chan = NULL;
 	int n, ret = 0;
 
-	if (len == 0)
+	if (len == 0 || !chan || !chan->ops->write)
 		return 0;
 
-	list_for_each(ele, chans) {
-		chan = list_entry(ele, struct chan, list);
-		if (!chan->output || (chan->ops->write == NULL))
-			continue;
-
-		n = chan->ops->write(chan->fd, buf, len, chan->data);
-		if (chan->primary) {
-			ret = n;
-			if ((ret == -EAGAIN) || ((ret >= 0) && (ret < len)))
-				reactivate_fd(chan->fd, write_irq);
-		}
+	n = chan->ops->write(chan->fd, buf, len, chan->data);
+	if (chan->primary) {
+		ret = n;
+		if ((ret == -EAGAIN) || ((ret >= 0) && (ret < len)))
+			reactivate_fd(chan->fd, write_irq);
 	}
 	return ret;
 }
 
-int console_write_chan(struct list_head *chans, const char *buf, int len)
+int console_write_chan(struct chan *chan, const char *buf, int len)
 {
-	struct list_head *ele;
-	struct chan *chan;
 	int n, ret = 0;
 
-	list_for_each(ele, chans) {
-		chan = list_entry(ele, struct chan, list);
-		if (!chan->output || (chan->ops->console_write == NULL))
-			continue;
+	if (!chan || !chan->ops->console_write)
+		return 0;
 
-		n = chan->ops->console_write(chan->fd, buf, len);
-		if (chan->primary)
-			ret = n;
-	}
+	n = chan->ops->console_write(chan->fd, buf, len);
+	if (chan->primary)
+		ret = n;
 	return ret;
 }
 
@@ -340,20 +315,24 @@ int console_open_chan(struct line *line, struct console *co)
 	return 0;
 }
 
-int chan_window_size(struct list_head *chans, unsigned short *rows_out,
+int chan_window_size(struct line *line, unsigned short *rows_out,
 		      unsigned short *cols_out)
 {
-	struct list_head *ele;
 	struct chan *chan;
 
-	list_for_each(ele, chans) {
-		chan = list_entry(ele, struct chan, list);
-		if (chan->primary) {
-			if (chan->ops->window_size == NULL)
-				return 0;
-			return chan->ops->window_size(chan->fd, chan->data,
-						      rows_out, cols_out);
-		}
+	chan = line->chan_in;
+	if (chan && chan->primary) {
+		if (chan->ops->window_size == NULL)
+			return 0;
+		return chan->ops->window_size(chan->fd, chan->data,
+					      rows_out, cols_out);
+	}
+	chan = line->chan_out;
+	if (chan && chan->primary) {
+		if (chan->ops->window_size == NULL)
+			return 0;
+		return chan->ops->window_size(chan->fd, chan->data,
+					      rows_out, cols_out);
 	}
 	return 0;
 }
@@ -429,21 +408,15 @@ static int chan_pair_config_string(struct chan *in, struct chan *out,
 	return n;
 }
 
-int chan_config_string(struct list_head *chans, char *str, int size,
+int chan_config_string(struct line *line, char *str, int size,
 		       char **error_out)
 {
-	struct list_head *ele;
-	struct chan *chan, *in = NULL, *out = NULL;
+	struct chan *in = line->chan_in, *out = line->chan_out;
 
-	list_for_each(ele, chans) {
-		chan = list_entry(ele, struct chan, list);
-		if (!chan->primary)
-			continue;
-		if (chan->input)
-			in = chan;
-		if (chan->output)
-			out = chan;
-	}
+	if (in && !in->primary)
+		in = NULL;
+	if (out && !out->primary)
+		out = NULL;
 
 	return chan_pair_config_string(in, out, str, size, error_out);
 }
@@ -547,10 +520,14 @@ int parse_chan_pair(char *str, struct line *line, int device,
 	char *in, *out;
 
 	if (!list_empty(chans)) {
+		line->chan_in = line->chan_out = NULL;
 		free_chan(chans);
 		INIT_LIST_HEAD(chans);
 	}
 
+	if (!str)
+		return 0;
+
 	out = strchr(str, ',');
 	if (out != NULL) {
 		in = str;
@@ -562,6 +539,7 @@ int parse_chan_pair(char *str, struct line *line, int device,
 
 		new->input = 1;
 		list_add(&new->list, chans);
+		line->chan_in = new;
 
 		new = parse_chan(line, out, device, opts, error_out);
 		if (new == NULL)
@@ -569,6 +547,7 @@ int parse_chan_pair(char *str, struct line *line, int device,
 
 		list_add(&new->list, chans);
 		new->output = 1;
+		line->chan_out = new;
 	}
 	else {
 		new = parse_chan(line, str, device, opts, error_out);
@@ -578,43 +557,42 @@ int parse_chan_pair(char *str, struct line *line, int device,
 		list_add(&new->list, chans);
 		new->input = 1;
 		new->output = 1;
+		line->chan_in = line->chan_out = new;
 	}
 	return 0;
 }
 
-void chan_interrupt(struct list_head *chans, struct delayed_work *task,
-		    struct tty_struct *tty, int irq)
+void chan_interrupt(struct line *line, struct tty_struct *tty, int irq)
 {
-	struct list_head *ele, *next;
-	struct chan *chan;
+	struct chan *chan = line->chan_in;
 	int err;
 	char c;
 
-	list_for_each_safe(ele, next, chans) {
-		chan = list_entry(ele, struct chan, list);
-		if (!chan->input || (chan->ops->read == NULL))
-			continue;
-		do {
-			if (tty && !tty_buffer_request_room(tty, 1)) {
-				schedule_delayed_work(task, 1);
-				goto out;
-			}
-			err = chan->ops->read(chan->fd, &c, chan->data);
-			if (err > 0)
-				tty_receive_char(tty, c);
-		} while (err > 0);
-
-		if (err == 0)
-			reactivate_fd(chan->fd, irq);
-		if (err == -EIO) {
-			if (chan->primary) {
-				if (tty != NULL)
-					tty_hangup(tty);
-				close_chan(chans, 1);
-				return;
-			}
-			else close_one_chan(chan, 1);
+	if (!chan || !chan->ops->read)
+		goto out;
+
+	do {
+		if (tty && !tty_buffer_request_room(tty, 1)) {
+			schedule_delayed_work(&line->task, 1);
+			goto out;
 		}
+		err = chan->ops->read(chan->fd, &c, chan->data);
+		if (err > 0)
+			tty_receive_char(tty, c);
+	} while (err > 0);
+
+	if (err == 0)
+		reactivate_fd(chan->fd, irq);
+	if (err == -EIO) {
+		if (chan->primary) {
+			if (tty != NULL)
+				tty_hangup(tty);
+			if (line->chan_out != chan)
+				close_one_chan(line->chan_out, 1);
+		}
+		close_one_chan(chan, 1);
+		if (chan->primary)
+			return;
 	}
  out:
 	if (tty)
diff --git a/arch/um/drivers/chan_user.h b/arch/um/drivers/chan_user.h
index 9b9ced85b703..6257b7a6e1af 100644
--- a/arch/um/drivers/chan_user.h
+++ b/arch/um/drivers/chan_user.h
@@ -14,8 +14,6 @@ struct chan_opts {
 	const int raw;
 };
 
-enum chan_init_pri { INIT_STATIC, INIT_ALL, INIT_ONE };
-
 struct chan_ops {
 	char *type;
 	void *(*init)(char *, int, const struct chan_opts *);
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index c1cf2206b84b..4ab0d9c0911c 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -21,19 +21,10 @@ static irqreturn_t line_interrupt(int irq, void *data)
 	struct line *line = chan->line;
 
 	if (line)
-		chan_interrupt(&line->chan_list, &line->task, line->tty, irq);
+		chan_interrupt(line, line->tty, irq);
 	return IRQ_HANDLED;
 }
 
-static void line_timer_cb(struct work_struct *work)
-{
-	struct line *line = container_of(work, struct line, task.work);
-
-	if (!line->throttled)
-		chan_interrupt(&line->chan_list, &line->task, line->tty,
-			       line->driver->read_irq);
-}
-
 /*
  * Returns the free space inside the ring buffer of this line.
  *
@@ -145,7 +136,7 @@ static int flush_buffer(struct line *line)
 		/* line->buffer + LINE_BUFSIZE is the end of the buffer! */
 		count = line->buffer + LINE_BUFSIZE - line->head;
 
-		n = write_chan(&line->chan_list, line->head, count,
+		n = write_chan(line->chan_out, line->head, count,
 			       line->driver->write_irq);
 		if (n < 0)
 			return n;
@@ -162,7 +153,7 @@ static int flush_buffer(struct line *line)
 	}
 
 	count = line->tail - line->head;
-	n = write_chan(&line->chan_list, line->head, count,
+	n = write_chan(line->chan_out, line->head, count,
 		       line->driver->write_irq);
 
 	if (n < 0)
@@ -206,7 +197,7 @@ int line_write(struct tty_struct *tty, const unsigned char *buf, int len)
 	if (line->head != line->tail)
 		ret = buffer_data(line, buf, len);
 	else {
-		n = write_chan(&line->chan_list, buf, len,
+		n = write_chan(line->chan_out, buf, len,
 			       line->driver->write_irq);
 		if (n < 0) {
 			ret = n;
@@ -318,7 +309,7 @@ void line_throttle(struct tty_struct *tty)
 {
 	struct line *line = tty->driver_data;
 
-	deactivate_chan(&line->chan_list, line->driver->read_irq);
+	deactivate_chan(line->chan_in, line->driver->read_irq);
 	line->throttled = 1;
 }
 
@@ -327,8 +318,7 @@ void line_unthrottle(struct tty_struct *tty)
 	struct line *line = tty->driver_data;
 
 	line->throttled = 0;
-	chan_interrupt(&line->chan_list, &line->task, tty,
-		       line->driver->read_irq);
+	chan_interrupt(line, tty, line->driver->read_irq);
 
 	/*
 	 * Maybe there is enough stuff pending that calling the interrupt
@@ -336,7 +326,7 @@ void line_unthrottle(struct tty_struct *tty)
 	 * again and we shouldn't turn the interrupt back on.
 	 */
 	if (!line->throttled)
-		reactivate_chan(&line->chan_list, line->driver->read_irq);
+		reactivate_chan(line->chan_in, line->driver->read_irq);
 }
 
 static irqreturn_t line_write_interrupt(int irq, void *data)
@@ -347,13 +337,14 @@ static irqreturn_t line_write_interrupt(int irq, void *data)
 	int err;
 
 	/*
-	 * Interrupts are disabled here because we registered the interrupt with
-	 * IRQF_DISABLED (see line_setup_irq).
+	 * Interrupts are disabled here because genirq keep irqs disabled when
+	 * calling the action handler.
 	 */
 
 	spin_lock(&line->lock);
 	err = flush_buffer(line);
 	if (err == 0) {
+		spin_unlock(&line->lock);
 		return IRQ_NONE;
 	} else if (err < 0) {
 		line->head = line->buffer;
@@ -371,7 +362,7 @@ static irqreturn_t line_write_interrupt(int irq, void *data)
 int line_setup_irq(int fd, int input, int output, struct line *line, void *data)
 {
 	const struct line_driver *driver = line->driver;
-	int err = 0, flags = IRQF_DISABLED | IRQF_SHARED | IRQF_SAMPLE_RANDOM;
+	int err = 0, flags = IRQF_SHARED | IRQF_SAMPLE_RANDOM;
 
 	if (input)
 		err = um_request_irq(driver->read_irq, fd, IRQ_READ,
@@ -383,7 +374,6 @@ int line_setup_irq(int fd, int input, int output, struct line *line, void *data)
 		err = um_request_irq(driver->write_irq, fd, IRQ_WRITE,
 					line_write_interrupt, flags,
 					driver->write_irq_name, data);
-	line->have_irq = 1;
 	return err;
 }
 
@@ -409,7 +399,7 @@ int line_open(struct line *lines, struct tty_struct *tty)
 	struct line *line = &lines[tty->index];
 	int err = -ENODEV;
 
-	spin_lock(&line->count_lock);
+	mutex_lock(&line->count_lock);
 	if (!line->valid)
 		goto out_unlock;
 
@@ -421,25 +411,19 @@ int line_open(struct line *lines, struct tty_struct *tty)
 	tty->driver_data = line;
 	line->tty = tty;
 
-	spin_unlock(&line->count_lock);
 	err = enable_chan(line);
 	if (err) /* line_close() will be called by our caller */
-		return err;
-
-	INIT_DELAYED_WORK(&line->task, line_timer_cb);
+		goto out_unlock;
 
 	if (!line->sigio) {
-		chan_enable_winch(&line->chan_list, tty);
+		chan_enable_winch(line->chan_out, tty);
 		line->sigio = 1;
 	}
 
-	chan_window_size(&line->chan_list, &tty->winsize.ws_row,
+	chan_window_size(line, &tty->winsize.ws_row,
 			 &tty->winsize.ws_col);
-
-	return 0;
-
 out_unlock:
-	spin_unlock(&line->count_lock);
+	mutex_unlock(&line->count_lock);
 	return err;
 }
 
@@ -459,7 +443,7 @@ void line_close(struct tty_struct *tty, struct file * filp)
 	/* We ignore the error anyway! */
 	flush_buffer(line);
 
-	spin_lock(&line->count_lock);
+	mutex_lock(&line->count_lock);
 	BUG_ON(!line->valid);
 
 	if (--line->count)
@@ -468,17 +452,13 @@ void line_close(struct tty_struct *tty, struct file * filp)
 	line->tty = NULL;
 	tty->driver_data = NULL;
 
-	spin_unlock(&line->count_lock);
-
 	if (line->sigio) {
 		unregister_winch(tty);
 		line->sigio = 0;
 	}
 
-	return;
-
 out_unlock:
-	spin_unlock(&line->count_lock);
+	mutex_unlock(&line->count_lock);
 }
 
 void close_lines(struct line *lines, int nlines)
@@ -486,34 +466,60 @@ void close_lines(struct line *lines, int nlines)
 	int i;
 
 	for(i = 0; i < nlines; i++)
-		close_chan(&lines[i].chan_list, 0);
+		close_chan(&lines[i]);
 }
 
-static int setup_one_line(struct line *lines, int n, char *init, int init_prio,
-			  char **error_out)
+int setup_one_line(struct line *lines, int n, char *init,
+		   const struct chan_opts *opts, char **error_out)
 {
 	struct line *line = &lines[n];
+	struct tty_driver *driver = line->driver->driver;
 	int err = -EINVAL;
 
-	spin_lock(&line->count_lock);
+	mutex_lock(&line->count_lock);
 
 	if (line->count) {
 		*error_out = "Device is already open";
 		goto out;
 	}
 
-	if (line->init_pri <= init_prio) {
-		line->init_pri = init_prio;
-		if (!strcmp(init, "none"))
+	if (!strcmp(init, "none")) {
+		if (line->valid) {
+			line->valid = 0;
+			kfree(line->init_str);
+			tty_unregister_device(driver, n);
+			parse_chan_pair(NULL, line, n, opts, error_out);
+			err = 0;
+		}
+	} else {
+		char *new = kstrdup(init, GFP_KERNEL);
+		if (!new) {
+			*error_out = "Failed to allocate memory";
+			return -ENOMEM;
+		}
+		if (line->valid) {
+			tty_unregister_device(driver, n);
+			kfree(line->init_str);
+		}
+		line->init_str = new;
+		line->valid = 1;
+		err = parse_chan_pair(new, line, n, opts, error_out);
+		if (!err) {
+			struct device *d = tty_register_device(driver, n, NULL);
+			if (IS_ERR(d)) {
+				*error_out = "Failed to register device";
+				err = PTR_ERR(d);
+				parse_chan_pair(NULL, line, n, opts, error_out);
+			}
+		}
+		if (err) {
+			line->init_str = NULL;
 			line->valid = 0;
-		else {
-			line->init_str = init;
-			line->valid = 1;
+			kfree(new);
 		}
 	}
-	err = 0;
 out:
-	spin_unlock(&line->count_lock);
+	mutex_unlock(&line->count_lock);
 	return err;
 }
 
@@ -524,54 +530,43 @@ out:
  * @error_out is an error string in the case of failure;
  */
 
-int line_setup(struct line *lines, unsigned int num, char *init,
-	       char **error_out)
+int line_setup(char **conf, unsigned int num, char **def,
+	       char *init, char *name)
 {
-	int i, n, err;
-	char *end;
+	char *error;
 
 	if (*init == '=') {
 		/*
 		 * We said con=/ssl= instead of con#=, so we are configuring all
 		 * consoles at once.
 		 */
-		n = -1;
-	}
-	else {
-		n = simple_strtoul(init, &end, 0);
+		*def = init + 1;
+	} else {
+		char *end;
+		unsigned n = simple_strtoul(init, &end, 0);
+
 		if (*end != '=') {
-			*error_out = "Couldn't parse device number";
-			return -EINVAL;
+			error = "Couldn't parse device number";
+			goto out;
 		}
-		init = end;
-	}
-	init++;
-
-	if (n >= (signed int) num) {
-		*error_out = "Device number out of range";
-		return -EINVAL;
-	}
-	else if (n >= 0) {
-		err = setup_one_line(lines, n, init, INIT_ONE, error_out);
-		if (err)
-			return err;
-	}
-	else {
-		for(i = 0; i < num; i++) {
-			err = setup_one_line(lines, i, init, INIT_ALL,
-					     error_out);
-			if (err)
-				return err;
+		if (n >= num) {
+			error = "Device number out of range";
+			goto out;
 		}
+		conf[n] = end + 1;
 	}
-	return n == -1 ? num : n;
+	return 0;
+
+out:
+	printk(KERN_ERR "Failed to set up %s with "
+	       "configuration string \"%s\" : %s\n", name, init, error);
+	return -EINVAL;
 }
 
 int line_config(struct line *lines, unsigned int num, char *str,
 		const struct chan_opts *opts, char **error_out)
 {
-	struct line *line;
-	char *new;
+	char *end;
 	int n;
 
 	if (*str == '=') {
@@ -579,17 +574,17 @@ int line_config(struct line *lines, unsigned int num, char *str,
 		return -EINVAL;
 	}
 
-	new = kstrdup(str, GFP_KERNEL);
-	if (new == NULL) {
-		*error_out = "Failed to allocate memory";
-		return -ENOMEM;
+	n = simple_strtoul(str, &end, 0);
+	if (*end++ != '=') {
+		*error_out = "Couldn't parse device number";
+		return -EINVAL;
+	}
+	if (n >= num) {
+		*error_out = "Device number out of range";
+		return -EINVAL;
 	}
-	n = line_setup(lines, num, new, error_out);
-	if (n < 0)
-		return n;
 
-	line = &lines[n];
-	return parse_chan_pair(line->init_str, line, n, opts, error_out);
+	return setup_one_line(lines, n, end, opts, error_out);
 }
 
 int line_get_config(char *name, struct line *lines, unsigned int num, char *str,
@@ -612,13 +607,13 @@ int line_get_config(char *name, struct line *lines, unsigned int num, char *str,
 
 	line = &lines[dev];
 
-	spin_lock(&line->count_lock);
+	mutex_lock(&line->count_lock);
 	if (!line->valid)
 		CONFIG_CHUNK(str, size, n, "none", 1);
 	else if (line->tty == NULL)
 		CONFIG_CHUNK(str, size, n, line->init_str, 1);
-	else n = chan_config_string(&line->chan_list, str, size, error_out);
-	spin_unlock(&line->count_lock);
+	else n = chan_config_string(line, str, size, error_out);
+	mutex_unlock(&line->count_lock);
 
 	return n;
 }
@@ -640,25 +635,23 @@ int line_id(char **str, int *start_out, int *end_out)
 
 int line_remove(struct line *lines, unsigned int num, int n, char **error_out)
 {
-	int err;
-	char config[sizeof("conxxxx=none\0")];
-
-	sprintf(config, "%d=none", n);
-	err = line_setup(lines, num, config, error_out);
-	if (err >= 0)
-		err = 0;
-	return err;
+	if (n >= num) {
+		*error_out = "Device number out of range";
+		return -EINVAL;
+	}
+	return setup_one_line(lines, n, "none", NULL, error_out);
 }
 
-struct tty_driver *register_lines(struct line_driver *line_driver,
-				  const struct tty_operations *ops,
-				  struct line *lines, int nlines)
+int register_lines(struct line_driver *line_driver,
+		   const struct tty_operations *ops,
+		   struct line *lines, int nlines)
 {
-	int i;
 	struct tty_driver *driver = alloc_tty_driver(nlines);
+	int err;
+	int i;
 
 	if (!driver)
-		return NULL;
+		return -ENOMEM;
 
 	driver->driver_name = line_driver->name;
 	driver->name = line_driver->device_name;
@@ -666,54 +659,33 @@ struct tty_driver *register_lines(struct line_driver *line_driver,
 	driver->minor_start = line_driver->minor_start;
 	driver->type = line_driver->type;
 	driver->subtype = line_driver->subtype;
-	driver->flags = TTY_DRIVER_REAL_RAW;
+	driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV;
 	driver->init_termios = tty_std_termios;
+	
+	for (i = 0; i < nlines; i++) {
+		spin_lock_init(&lines[i].lock);
+		mutex_init(&lines[i].count_lock);
+		lines[i].driver = line_driver;
+		INIT_LIST_HEAD(&lines[i].chan_list);
+	}
 	tty_set_operations(driver, ops);
 
-	if (tty_register_driver(driver)) {
+	err = tty_register_driver(driver);
+	if (err) {
 		printk(KERN_ERR "register_lines : can't register %s driver\n",
 		       line_driver->name);
 		put_tty_driver(driver);
-		return NULL;
-	}
-
-	for(i = 0; i < nlines; i++) {
-		if (!lines[i].valid)
-			tty_unregister_device(driver, i);
+		return err;
 	}
 
+	line_driver->driver = driver;
 	mconsole_register_dev(&line_driver->mc);
-	return driver;
+	return 0;
 }
 
 static DEFINE_SPINLOCK(winch_handler_lock);
 static LIST_HEAD(winch_handlers);
 
-void lines_init(struct line *lines, int nlines, struct chan_opts *opts)
-{
-	struct line *line;
-	char *error;
-	int i;
-
-	for(i = 0; i < nlines; i++) {
-		line = &lines[i];
-		INIT_LIST_HEAD(&line->chan_list);
-
-		if (line->init_str == NULL)
-			continue;
-
-		line->init_str = kstrdup(line->init_str, GFP_KERNEL);
-		if (line->init_str == NULL)
-			printk(KERN_ERR "lines_init - kstrdup returned NULL\n");
-
-		if (parse_chan_pair(line->init_str, line, i, opts, &error)) {
-			printk(KERN_ERR "parse_chan_pair failed for "
-			       "device %d : %s\n", i, error);
-			line->valid = 0;
-		}
-	}
-}
-
 struct winch {
 	struct list_head list;
 	int fd;
@@ -777,7 +749,7 @@ static irqreturn_t winch_interrupt(int irq, void *data)
 	if (tty != NULL) {
 		line = tty->driver_data;
 		if (line != NULL) {
-			chan_window_size(&line->chan_list, &tty->winsize.ws_row,
+			chan_window_size(line, &tty->winsize.ws_row,
 					 &tty->winsize.ws_col);
 			kill_pgrp(tty->pgrp, SIGWINCH, 1);
 		}
@@ -807,7 +779,7 @@ void register_winch_irq(int fd, int tty_fd, int pid, struct tty_struct *tty,
 				   .stack	= stack });
 
 	if (um_request_irq(WINCH_IRQ, fd, IRQ_READ, winch_interrupt,
-			   IRQF_DISABLED | IRQF_SHARED | IRQF_SAMPLE_RANDOM,
+			   IRQF_SHARED | IRQF_SAMPLE_RANDOM,
 			   "winch", winch) < 0) {
 		printk(KERN_ERR "register_winch_irq - failed to register "
 		       "IRQ\n");
diff --git a/arch/um/drivers/line.h b/arch/um/drivers/line.h
index 63df3ca02ac2..0a1834719dba 100644
--- a/arch/um/drivers/line.h
+++ b/arch/um/drivers/line.h
@@ -15,7 +15,7 @@
 #include "chan_user.h"
 #include "mconsole_kern.h"
 
-/* There's only one modifiable field in this - .mc.list */
+/* There's only two modifiable fields in this - .mc.list and .driver */
 struct line_driver {
 	const char *name;
 	const char *device_name;
@@ -28,17 +28,18 @@ struct line_driver {
 	const int write_irq;
 	const char *write_irq_name;
 	struct mc_device mc;
+	struct tty_driver *driver;
 };
 
 struct line {
 	struct tty_struct *tty;
-	spinlock_t count_lock;
+	struct mutex count_lock;
 	unsigned long count;
 	int valid;
 
 	char *init_str;
-	int init_pri;
 	struct list_head chan_list;
+	struct chan *chan_in, *chan_out;
 
 	/*This lock is actually, mostly, local to*/
 	spinlock_t lock;
@@ -55,21 +56,12 @@ struct line {
 	int sigio;
 	struct delayed_work task;
 	const struct line_driver *driver;
-	int have_irq;
 };
 
-#define LINE_INIT(str, d) \
-	{ .count_lock =	__SPIN_LOCK_UNLOCKED((str).count_lock), \
-	  .init_str =	str,	\
-	  .init_pri =	INIT_STATIC, \
-	  .valid =	1, \
-	  .lock =	__SPIN_LOCK_UNLOCKED((str).lock), \
-	  .driver =	d }
-
 extern void line_close(struct tty_struct *tty, struct file * filp);
 extern int line_open(struct line *lines, struct tty_struct *tty);
-extern int line_setup(struct line *lines, unsigned int sizeof_lines,
-		      char *init, char **error_out);
+extern int line_setup(char **conf, unsigned nlines, char **def,
+		      char *init, char *name);
 extern int line_write(struct tty_struct *tty, const unsigned char *buf,
 		      int len);
 extern int line_put_char(struct tty_struct *tty, unsigned char ch);
@@ -87,10 +79,11 @@ extern char *add_xterm_umid(char *base);
 extern int line_setup_irq(int fd, int input, int output, struct line *line,
 			  void *data);
 extern void line_close_chan(struct line *line);
-extern struct tty_driver *register_lines(struct line_driver *line_driver,
-					 const struct tty_operations *driver,
-					 struct line *lines, int nlines);
-extern void lines_init(struct line *lines, int nlines, struct chan_opts *opts);
+extern int register_lines(struct line_driver *line_driver,
+			  const struct tty_operations *driver,
+			  struct line *lines, int nlines);
+extern int setup_one_line(struct line *lines, int n, char *init,
+			  const struct chan_opts *opts, char **error_out);
 extern void close_lines(struct line *lines, int nlines);
 
 extern int line_config(struct line *lines, unsigned int sizeof_lines,
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index c70e047eed72..e672bd6d43e3 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -773,7 +773,7 @@ static int __init mconsole_init(void)
 	register_reboot_notifier(&reboot_notifier);
 
 	err = um_request_irq(MCONSOLE_IRQ, sock, IRQ_READ, mconsole_interrupt,
-			     IRQF_DISABLED | IRQF_SHARED | IRQF_SAMPLE_RANDOM,
+			     IRQF_SHARED | IRQF_SAMPLE_RANDOM,
 			     "mconsole", (void *)sock);
 	if (err) {
 		printk(KERN_ERR "Failed to get IRQ for management console\n");
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index d2996183e584..95f4416e6d9f 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -161,7 +161,7 @@ static int uml_net_open(struct net_device *dev)
 	}
 
 	err = um_request_irq(dev->irq, lp->fd, IRQ_READ, uml_net_interrupt,
-			     IRQF_DISABLED | IRQF_SHARED, dev->name, dev);
+			     IRQF_SHARED, dev->name, dev);
 	if (err != 0) {
 		printk(KERN_ERR "uml_net_open: failed to get irq(%d)\n", err);
 		err = -ENETUNREACH;
diff --git a/arch/um/drivers/port_kern.c b/arch/um/drivers/port_kern.c
index a11573be0961..e31680e662a4 100644
--- a/arch/um/drivers/port_kern.c
+++ b/arch/um/drivers/port_kern.c
@@ -100,7 +100,7 @@ static int port_accept(struct port_list *port)
 		  .port 	= port });
 
 	if (um_request_irq(TELNETD_IRQ, socket[0], IRQ_READ, pipe_interrupt,
-			  IRQF_DISABLED | IRQF_SHARED | IRQF_SAMPLE_RANDOM,
+			  IRQF_SHARED | IRQF_SAMPLE_RANDOM,
 			  "telnetd", conn)) {
 		printk(KERN_ERR "port_accept : failed to get IRQ for "
 		       "telnetd\n");
@@ -184,7 +184,7 @@ void *port_data(int port_num)
 	}
 
 	if (um_request_irq(ACCEPT_IRQ, fd, IRQ_READ, port_interrupt,
-			  IRQF_DISABLED | IRQF_SHARED | IRQF_SAMPLE_RANDOM,
+			  IRQF_SHARED | IRQF_SAMPLE_RANDOM,
 			  "port", port)) {
 		printk(KERN_ERR "Failed to get IRQ for port %d\n", port_num);
 		goto out_close;
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index 981085a93f30..b25296e6218a 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -131,7 +131,7 @@ static int __init rng_init (void)
 	random_fd = err;
 
 	err = um_request_irq(RANDOM_IRQ, random_fd, IRQ_READ, random_interrupt,
-			     IRQF_DISABLED | IRQF_SAMPLE_RANDOM, "random",
+			     IRQF_SAMPLE_RANDOM, "random",
 			     NULL);
 	if (err)
 		goto err_out_cleanup_hw;
diff --git a/arch/um/drivers/ssl.c b/arch/um/drivers/ssl.c
index 9d8c20af6f80..e09801a1327b 100644
--- a/arch/um/drivers/ssl.c
+++ b/arch/um/drivers/ssl.c
@@ -20,12 +20,6 @@
 
 static const int ssl_version = 1;
 
-/* Referenced only by tty_driver below - presumably it's locked correctly
- * by the tty driver.
- */
-
-static struct tty_driver *ssl_driver;
-
 #define NR_PORTS 64
 
 static void ssl_announce(char *dev_name, int dev)
@@ -71,8 +65,9 @@ static struct line_driver driver = {
 /* The array is initialized by line_init, at initcall time.  The
  * elements are locked individually as needed.
  */
-static struct line serial_lines[NR_PORTS] =
-	{ [0 ... NR_PORTS - 1] = LINE_INIT(CONFIG_SSL_CHAN, &driver) };
+static char *conf[NR_PORTS];
+static char *def_conf = CONFIG_SSL_CHAN;
+static struct line serial_lines[NR_PORTS];
 
 static int ssl_config(char *str, char **error_out)
 {
@@ -156,14 +151,14 @@ static void ssl_console_write(struct console *c, const char *string,
 	unsigned long flags;
 
 	spin_lock_irqsave(&line->lock, flags);
-	console_write_chan(&line->chan_list, string, len);
+	console_write_chan(line->chan_out, string, len);
 	spin_unlock_irqrestore(&line->lock, flags);
 }
 
 static struct tty_driver *ssl_console_device(struct console *c, int *index)
 {
 	*index = c->index;
-	return ssl_driver;
+	return driver.driver;
 }
 
 static int ssl_console_setup(struct console *co, char *options)
@@ -186,17 +181,30 @@ static struct console ssl_cons = {
 static int ssl_init(void)
 {
 	char *new_title;
+	int err;
+	int i;
 
 	printk(KERN_INFO "Initializing software serial port version %d\n",
 	       ssl_version);
-	ssl_driver = register_lines(&driver, &ssl_ops, serial_lines,
+
+	err = register_lines(&driver, &ssl_ops, serial_lines,
 				    ARRAY_SIZE(serial_lines));
+	if (err)
+		return err;
 
 	new_title = add_xterm_umid(opts.xterm_title);
 	if (new_title != NULL)
 		opts.xterm_title = new_title;
 
-	lines_init(serial_lines, ARRAY_SIZE(serial_lines), &opts);
+	for (i = 0; i < NR_PORTS; i++) {
+		char *error;
+		char *s = conf[i];
+		if (!s)
+			s = def_conf;
+		if (setup_one_line(serial_lines, i, s, &opts, &error))
+			printk(KERN_ERR "setup_one_line failed for "
+			       "device %d : %s\n", i, error);
+	}
 
 	ssl_init_done = 1;
 	register_console(&ssl_cons);
@@ -214,14 +222,7 @@ __uml_exitcall(ssl_exit);
 
 static int ssl_chan_setup(char *str)
 {
-	char *error;
-	int ret;
-
-	ret = line_setup(serial_lines, ARRAY_SIZE(serial_lines), str, &error);
-	if(ret < 0)
-		printk(KERN_ERR "Failed to set up serial line with "
-		       "configuration string \"%s\" : %s\n", str, error);
-
+	line_setup(conf, NR_PORTS, &def_conf, str, "serial line");
 	return 1;
 }
 
diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c
index 088776f01908..7663541c372e 100644
--- a/arch/um/drivers/stdio_console.c
+++ b/arch/um/drivers/stdio_console.c
@@ -27,12 +27,6 @@
 
 #define MAX_TTYS (16)
 
-/* Referenced only by tty_driver below - presumably it's locked correctly
- * by the tty driver.
- */
-
-static struct tty_driver *console_driver;
-
 static void stdio_announce(char *dev_name, int dev)
 {
 	printk(KERN_INFO "Virtual console %d assigned device '%s'\n", dev,
@@ -76,9 +70,9 @@ static struct line_driver driver = {
 /* The array is initialized by line_init, at initcall time.  The
  * elements are locked individually as needed.
  */
-static struct line vts[MAX_TTYS] = { LINE_INIT(CONFIG_CON_ZERO_CHAN, &driver),
-				     [ 1 ... MAX_TTYS - 1 ] =
-				     LINE_INIT(CONFIG_CON_CHAN, &driver) };
+static char *vt_conf[MAX_TTYS];
+static char *def_conf;
+static struct line vts[MAX_TTYS];
 
 static int con_config(char *str, char **error_out)
 {
@@ -130,14 +124,14 @@ static void uml_console_write(struct console *console, const char *string,
 	unsigned long flags;
 
 	spin_lock_irqsave(&line->lock, flags);
-	console_write_chan(&line->chan_list, string, len);
+	console_write_chan(line->chan_out, string, len);
 	spin_unlock_irqrestore(&line->lock, flags);
 }
 
 static struct tty_driver *uml_console_device(struct console *c, int *index)
 {
 	*index = c->index;
-	return console_driver;
+	return driver.driver;
 }
 
 static int uml_console_setup(struct console *co, char *options)
@@ -160,18 +154,31 @@ static struct console stdiocons = {
 static int stdio_init(void)
 {
 	char *new_title;
+	int err;
+	int i;
 
-	console_driver = register_lines(&driver, &console_ops, vts,
+	err = register_lines(&driver, &console_ops, vts,
 					ARRAY_SIZE(vts));
-	if (console_driver == NULL)
-		return -1;
+	if (err)
+		return err;
+
 	printk(KERN_INFO "Initialized stdio console driver\n");
 
 	new_title = add_xterm_umid(opts.xterm_title);
 	if(new_title != NULL)
 		opts.xterm_title = new_title;
 
-	lines_init(vts, ARRAY_SIZE(vts), &opts);
+	for (i = 0; i < MAX_TTYS; i++) {
+		char *error;
+		char *s = vt_conf[i];
+		if (!s)
+			s = def_conf;
+		if (!s)
+			s = i ? CONFIG_CON_CHAN : CONFIG_CON_ZERO_CHAN;
+		if (setup_one_line(vts, i, s, &opts, &error))
+			printk(KERN_ERR "setup_one_line failed for "
+			       "device %d : %s\n", i, error);
+	}
 
 	con_init_done = 1;
 	register_console(&stdiocons);
@@ -189,14 +196,7 @@ __uml_exitcall(console_exit);
 
 static int console_chan_setup(char *str)
 {
-	char *error;
-	int ret;
-
-	ret = line_setup(vts, ARRAY_SIZE(vts), str, &error);
-	if(ret < 0)
-		printk(KERN_ERR "Failed to set up console with "
-		       "configuration string \"%s\" : %s\n", str, error);
-
+	line_setup(vt_conf, MAX_TTYS, &def_conf, str, "console");
 	return 1;
 }
 __setup("con", console_chan_setup);
diff --git a/arch/um/drivers/ubd_user.h b/arch/um/drivers/ubd.h
index 3845051f1b10..3845051f1b10 100644
--- a/arch/um/drivers/ubd_user.h
+++ b/arch/um/drivers/ubd.h
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 944453a3ec99..20505cafa299 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -19,40 +19,26 @@
 
 #define UBD_SHIFT 4
 
-#include "linux/kernel.h"
-#include "linux/module.h"
-#include "linux/blkdev.h"
-#include "linux/ata.h"
-#include "linux/hdreg.h"
-#include "linux/init.h"
-#include "linux/cdrom.h"
-#include "linux/proc_fs.h"
-#include "linux/seq_file.h"
-#include "linux/ctype.h"
-#include "linux/capability.h"
-#include "linux/mm.h"
-#include "linux/slab.h"
-#include "linux/vmalloc.h"
-#include "linux/mutex.h"
-#include "linux/blkpg.h"
-#include "linux/genhd.h"
-#include "linux/spinlock.h"
-#include "linux/platform_device.h"
-#include "linux/scatterlist.h"
-#include "asm/segment.h"
-#include "asm/uaccess.h"
-#include "asm/irq.h"
-#include "asm/types.h"
-#include "asm/tlbflush.h"
-#include "mem_user.h"
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/ata.h>
+#include <linux/hdreg.h>
+#include <linux/cdrom.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/ctype.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <asm/tlbflush.h>
 #include "kern_util.h"
 #include "mconsole_kern.h"
 #include "init.h"
-#include "irq_user.h"
 #include "irq_kern.h"
-#include "ubd_user.h"
+#include "ubd.h"
 #include "os.h"
-#include "mem.h"
 #include "cow.h"
 
 enum ubd_req { UBD_READ, UBD_WRITE };
@@ -1115,7 +1101,7 @@ static int __init ubd_driver_init(void){
 		return 0;
 	}
 	err = um_request_irq(UBD_IRQ, thread_fd, IRQ_READ, ubd_intr,
-			     IRQF_DISABLED, "ubd", ubd_devs);
+			     0, "ubd", ubd_devs);
 	if(err != 0)
 		printk(KERN_ERR "um_request_irq failed - errno = %d\n", -err);
 	return 0;
diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c
index 007b94d97726..ffe02c431dea 100644
--- a/arch/um/drivers/ubd_user.c
+++ b/arch/um/drivers/ubd_user.c
@@ -15,14 +15,12 @@
 #include <sys/socket.h>
 #include <sys/mman.h>
 #include <sys/param.h>
-#include "asm/types.h"
-#include "ubd_user.h"
-#include "os.h"
-#include "cow.h"
-
 #include <endian.h>
 #include <byteswap.h>
 
+#include "ubd.h"
+#include "os.h"
+
 void ignore_sigwinch_sig(void)
 {
 	signal(SIGWINCH, SIG_IGN);
diff --git a/arch/um/drivers/xterm_kern.c b/arch/um/drivers/xterm_kern.c
index b646bccef37a..8bd130f0bda3 100644
--- a/arch/um/drivers/xterm_kern.c
+++ b/arch/um/drivers/xterm_kern.c
@@ -50,7 +50,7 @@ int xterm_fd(int socket, int *pid_out)
 	init_completion(&data->ready);
 
 	err = um_request_irq(XTERM_IRQ, socket, IRQ_READ, xterm_interrupt,
-			     IRQF_DISABLED | IRQF_SHARED | IRQF_SAMPLE_RANDOM,
+			     IRQF_SHARED | IRQF_SAMPLE_RANDOM,
 			     "xterm", data);
 	if (err) {
 		printk(KERN_ERR "xterm_fd : failed to get IRQ for xterm, "
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 451f4517b334..8419f5cf2ac7 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,3 +1,3 @@
 generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
 generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
-generic-y += ftrace.h
+generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h
diff --git a/arch/um/include/asm/asm-offsets.h b/arch/um/include/asm/asm-offsets.h
deleted file mode 100644
index d370ee36a182..000000000000
--- a/arch/um/include/asm/asm-offsets.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <generated/asm-offsets.h>
diff --git a/arch/um/include/asm/auxvec.h b/arch/um/include/asm/auxvec.h
deleted file mode 100644
index 1e5e1c2fc9b1..000000000000
--- a/arch/um/include/asm/auxvec.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __UM_AUXVEC_H
-#define __UM_AUXVEC_H
-
-#endif
diff --git a/arch/um/include/asm/current.h b/arch/um/include/asm/current.h
deleted file mode 100644
index c2191d9aa03d..000000000000
--- a/arch/um/include/asm/current.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_CURRENT_H
-#define __UM_CURRENT_H
-
-#include "linux/thread_info.h"
-
-#define current (current_thread_info()->task)
-
-#endif
diff --git a/arch/um/include/asm/delay.h b/arch/um/include/asm/delay.h
deleted file mode 100644
index 8a5576d8eda5..000000000000
--- a/arch/um/include/asm/delay.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef __UM_DELAY_H
-#define __UM_DELAY_H
-
-/* Undefined on purpose */
-extern void __bad_udelay(void);
-extern void __bad_ndelay(void);
-
-extern void __udelay(unsigned long usecs);
-extern void __ndelay(unsigned long usecs);
-extern void __delay(unsigned long loops);
-
-#define udelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \
-	__bad_udelay() : __udelay(n))
-
-#define ndelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \
-	__bad_ndelay() : __ndelay(n))
-
-#endif
diff --git a/arch/um/include/asm/fixmap.h b/arch/um/include/asm/fixmap.h
index 69c0252345f1..21a423bae5e8 100644
--- a/arch/um/include/asm/fixmap.h
+++ b/arch/um/include/asm/fixmap.h
@@ -2,7 +2,6 @@
 #define __UM_FIXMAP_H
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/kmap_types.h>
 #include <asm/archparam.h>
 #include <asm/page.h>
diff --git a/arch/um/include/asm/io.h b/arch/um/include/asm/io.h
deleted file mode 100644
index 44e8b8c772ae..000000000000
--- a/arch/um/include/asm/io.h
+++ /dev/null
@@ -1,57 +0,0 @@
-#ifndef __UM_IO_H
-#define __UM_IO_H
-
-#include "asm/page.h"
-
-#define IO_SPACE_LIMIT 0xdeadbeef /* Sure hope nothing uses this */
-
-static inline int inb(unsigned long i) { return(0); }
-static inline void outb(char c, unsigned long i) { }
-
-/*
- * Change virtual addresses to physical addresses and vv.
- * These are pretty trivial
- */
-static inline unsigned long virt_to_phys(volatile void * address)
-{
-	return __pa((void *) address);
-}
-
-static inline void * phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
-static inline void writeb(unsigned char b, volatile void __iomem *addr)
-{
-	*(volatile unsigned char __force *) addr = b;
-}
-static inline void writew(unsigned short b, volatile void __iomem *addr)
-{
-	*(volatile unsigned short __force *) addr = b;
-}
-static inline void writel(unsigned int b, volatile void __iomem *addr)
-{
-	*(volatile unsigned int __force *) addr = b;
-}
-static inline void writeq(unsigned int b, volatile void __iomem *addr)
-{
-	*(volatile unsigned long long __force *) addr = b;
-}
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
-#define __raw_writeq writeq
-
-#endif
diff --git a/arch/um/include/asm/mutex.h b/arch/um/include/asm/mutex.h
deleted file mode 100644
index 458c1f7fbc18..000000000000
--- a/arch/um/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
diff --git a/arch/um/include/asm/param.h b/arch/um/include/asm/param.h
deleted file mode 100644
index e44f4e60d16d..000000000000
--- a/arch/um/include/asm/param.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef _UM_PARAM_H
-#define _UM_PARAM_H
-
-#define EXEC_PAGESIZE   4096
-
-#ifndef NOGROUP
-#define NOGROUP         (-1)
-#endif
-
-#define MAXHOSTNAMELEN  64      /* max length of hostname */
-
-#ifdef __KERNEL__
-#define HZ CONFIG_HZ
-#define USER_HZ	100	   /* .. some user interfaces are in "ticks" */
-#define CLOCKS_PER_SEC (USER_HZ)  /* frequency at which times() counts */
-#else
-#define HZ 100
-#endif
-
-#endif
diff --git a/arch/um/include/asm/pci.h b/arch/um/include/asm/pci.h
deleted file mode 100644
index b44cf59ede1e..000000000000
--- a/arch/um/include/asm/pci.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_PCI_H
-#define __UM_PCI_H
-
-#define PCI_DMA_BUS_IS_PHYS     (1)
-
-#endif
diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h
index 32c8ce4e1515..bf90b2aa2002 100644
--- a/arch/um/include/asm/pgalloc.h
+++ b/arch/um/include/asm/pgalloc.h
@@ -8,8 +8,7 @@
 #ifndef __UM_PGALLOC_H
 #define __UM_PGALLOC_H
 
-#include "linux/mm.h"
-#include "asm/fixmap.h"
+#include <linux/mm.h>
 
 #define pmd_populate_kernel(mm, pmd, pte) \
 	set_pmd(pmd, __pmd(_PAGE_TABLE + (unsigned long) __pa(pte)))
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index 41474fb5eee7..6a3f9845743e 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -69,6 +69,8 @@ extern unsigned long end_iomem;
 #define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
 #define PAGE_KERNEL_EXEC	__pgprot(__PAGE_KERNEL_EXEC)
 
+#define io_remap_pfn_range	remap_pfn_range
+
 /*
  * The i386 can't do page protection for execute, and considers that the same
  * are read.
diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h
index f605d3c4844c..e786a6a3ec5e 100644
--- a/arch/um/include/asm/ptrace-generic.h
+++ b/arch/um/include/asm/ptrace-generic.h
@@ -9,7 +9,6 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/ptrace-abi.h>
-#include <asm/user.h>
 #include "sysdep/ptrace.h"
 
 struct pt_regs {
diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h
index d7fe563aa7e7..40db8f71deae 100644
--- a/arch/um/include/shared/common-offsets.h
+++ b/arch/um/include/shared/common-offsets.h
@@ -2,8 +2,6 @@
 
 DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
 
-OFFSET(HOST_TASK_PID, task_struct, pid);
-
 DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE);
 DEFINE(UM_KERN_PAGE_MASK, PAGE_MASK);
 DEFINE(UM_KERN_PAGE_SHIFT, PAGE_SHIFT);
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index 0f1483852460..00965d06d2ca 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -48,7 +48,7 @@ extern void do_uml_exitcalls(void);
  * GFP_ATOMIC.
  */
 extern int __cant_sleep(void);
-extern void *get_current(void);
+extern int get_current_pid(void);
 extern int copy_from_user_proc(void *to, void *from, int size);
 extern int cpu(void);
 extern char *uml_strdup(const char *string);
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index bc494741b1f3..492bc4c1b62b 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -3,7 +3,7 @@
 # Licensed under the GPL
 #
 
-CPPFLAGS_vmlinux.lds := -U$(SUBARCH) -DSTART=$(LDS_START) \
+CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START) \
                         -DELF_ARCH=$(LDS_ELF_ARCH)        \
                         -DELF_FORMAT=$(LDS_ELF_FORMAT)
 extra-y := vmlinux.lds
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 69f24905abdc..f386d04a84a5 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -126,9 +126,9 @@ void exit_thread(void)
 {
 }
 
-void *get_current(void)
+int get_current_pid(void)
 {
-	return current;
+	return task_pid_nr(current);
 }
 
 /*
diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c
index 2b272b63b514..2a1639255763 100644
--- a/arch/um/kernel/sigio.c
+++ b/arch/um/kernel/sigio.c
@@ -25,7 +25,7 @@ int write_sigio_irq(int fd)
 	int err;
 
 	err = um_request_irq(SIGIO_WRITE_IRQ, fd, IRQ_READ, sigio_interrupt,
-			     IRQF_DISABLED|IRQF_SAMPLE_RANDOM, "write sigio",
+			     IRQF_SAMPLE_RANDOM, "write sigio",
 			     NULL);
 	if (err) {
 		printk(KERN_ERR "write_sigio_irq : um_request_irq failed, "
diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c
index 2e9852c0d487..0a9e57e7446b 100644
--- a/arch/um/kernel/skas/process.c
+++ b/arch/um/kernel/skas/process.c
@@ -41,7 +41,7 @@ static int __init start_kernel_proc(void *unused)
 	cpu_tasks[0].pid = pid;
 	cpu_tasks[0].task = current;
 #ifdef CONFIG_SMP
-	cpu_online_map = cpumask_of_cpu(0);
+	init_cpu_online(get_cpu_mask(0));
 #endif
 	start_kernel();
 	return 0;
diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index 155206a66908..6f588e160fb0 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -76,7 +76,7 @@ static int idle_proc(void *cpup)
 		cpu_relax();
 
 	notify_cpu_starting(cpu);
-	cpu_set(cpu, cpu_online_map);
+	set_cpu_online(cpu, true);
 	default_idle();
 	return 0;
 }
@@ -110,8 +110,7 @@ void smp_prepare_cpus(unsigned int maxcpus)
 	for (i = 0; i < ncpus; ++i)
 		set_cpu_possible(i, true);
 
-	cpu_clear(me, cpu_online_map);
-	cpu_set(me, cpu_online_map);
+	set_cpu_online(me, true);
 	cpu_set(me, cpu_callin_map);
 
 	err = os_pipe(cpu_data[me].ipi_pipe, 1, 1);
@@ -138,13 +137,13 @@ void smp_prepare_cpus(unsigned int maxcpus)
 
 void smp_prepare_boot_cpu(void)
 {
-	cpu_set(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), true);
 }
 
 int __cpu_up(unsigned int cpu)
 {
 	cpu_set(cpu, smp_commenced_mask);
-	while (!cpu_isset(cpu, cpu_online_map))
+	while (!cpu_online(cpu))
 		mb();
 	return 0;
 }
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index 82a6e22f1f35..d1a23fb3190d 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -82,7 +82,7 @@ static void __init setup_itimer(void)
 {
 	int err;
 
-	err = request_irq(TIMER_IRQ, um_timer, IRQF_DISABLED, "timer", NULL);
+	err = request_irq(TIMER_IRQ, um_timer, 0, "timer", NULL);
 	if (err != 0)
 		printk(KERN_ERR "register_timer : request_irq failed - "
 		       "errno = %d\n", -err);
diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile
index dd764101e488..08ff5094fcdd 100644
--- a/arch/um/os-Linux/Makefile
+++ b/arch/um/os-Linux/Makefile
@@ -13,8 +13,6 @@ USER_OBJS := $(user-objs-y) aio.o elf_aux.o execvp.o file.o helper.o irq.o \
 	main.o mem.o process.o registers.o sigio.o signal.o start_up.o time.o \
 	tty.o umid.o util.o
 
-CFLAGS_user_syms.o += -DSUBARCH_$(SUBARCH)
-
 HAVE_AIO_ABI := $(shell [ -r /usr/include/linux/aio_abi.h ] && \
 	echo -DHAVE_AIO_ABI )
 CFLAGS_aio.o += $(HAVE_AIO_ABI)
diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c
index 45ffe46871e0..73926fa3f96b 100644
--- a/arch/um/os-Linux/user_syms.c
+++ b/arch/um/os-Linux/user_syms.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL(readdir64);
 extern void truncate64(void) __attribute__((weak));
 EXPORT_SYMBOL(truncate64);
 
-#ifdef SUBARCH_i386
+#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA
 EXPORT_SYMBOL(vsyscall_ehdr);
 EXPORT_SYMBOL(vsyscall_end);
 #endif
diff --git a/arch/um/scripts/Makefile.rules b/arch/um/scripts/Makefile.rules
index 2eb2843b0634..d50270d26b42 100644
--- a/arch/um/scripts/Makefile.rules
+++ b/arch/um/scripts/Makefile.rules
@@ -9,8 +9,6 @@ USER_OBJS := $(foreach file,$(USER_OBJS),$(obj)/$(file))
 
 $(USER_OBJS:.o=.%): \
 	c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include user.h $(CFLAGS_$(basetarget).o)
-$(USER_OBJS) : CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ \
-	-Dunix -D__unix__ -D__$(SUBARCH)__ $(CF)
 
 # These are like USER_OBJS but filter USER_CFLAGS through unprofile instead of
 # using it directly.
@@ -18,8 +16,9 @@ UNPROFILE_OBJS := $(foreach file,$(UNPROFILE_OBJS),$(obj)/$(file))
 
 $(UNPROFILE_OBJS:.o=.%): \
 	c_flags = -Wp,-MD,$(depfile) $(call unprofile,$(USER_CFLAGS)) $(CFLAGS_$(basetarget).o)
-$(UNPROFILE_OBJS) : CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ \
-	-Dunix -D__unix__ -D__$(SUBARCH)__ $(CF)
+
+$(USER_OBJS) $(UNPROFILE_OBJS): \
+	CHECKFLAGS := $(patsubst $(NOSTDINC_FLAGS),,$(CHECKFLAGS))
 
 # The stubs can't try to call mcount or update basic block data
 define unprofile
diff --git a/arch/unicore32/boot/Makefile b/arch/unicore32/boot/Makefile
index 79e5f88845d9..ec7fb70b412b 100644
--- a/arch/unicore32/boot/Makefile
+++ b/arch/unicore32/boot/Makefile
@@ -11,8 +11,6 @@
 # Copyright (C) 2001~2010 GUAN Xue-tao
 #
 
-MKIMAGE := $(srctree)/scripts/mkuboot.sh
-
 targets := Image zImage uImage
 
 $(obj)/Image: vmlinux FORCE
@@ -26,14 +24,8 @@ $(obj)/zImage: $(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
 	@echo '  Kernel: $@ is ready'
 
-quiet_cmd_uimage = UIMAGE  $@
-      cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A unicore -O linux -T kernel \
-		   -C none -a $(LOADADDR) -e $(STARTADDR) \
-		   -n 'Linux-$(KERNELRELEASE)' -d $< $@
-
-$(obj)/uImage: LOADADDR=0x0
-
-$(obj)/uImage: STARTADDR=$(LOADADDR)
+UIMAGE_ARCH = unicore
+UIMAGE_LOADADDR = 0x0
 
 $(obj)/uImage: $(obj)/zImage FORCE
 	$(call if_changed,uimage)
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index ca113d6999c5..34b789b71115 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -3,7 +3,6 @@ include include/asm-generic/Kbuild.asm
 generic-y += atomic.h
 generic-y += auxvec.h
 generic-y += bitsperlong.h
-generic-y += bug.h
 generic-y += bugs.h
 generic-y += cputime.h
 generic-y += current.h
diff --git a/arch/unicore32/include/asm/barrier.h b/arch/unicore32/include/asm/barrier.h
new file mode 100644
index 000000000000..a6620e5336b6
--- /dev/null
+++ b/arch/unicore32/include/asm/barrier.h
@@ -0,0 +1,28 @@
+/*
+ * Memory barrier implementations for PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2012 GUAN Xue-tao
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __UNICORE_BARRIER_H__
+#define __UNICORE_BARRIER_H__
+
+#define isb() __asm__ __volatile__ ("" : : : "memory")
+#define dsb() __asm__ __volatile__ ("" : : : "memory")
+#define dmb() __asm__ __volatile__ ("" : : : "memory")
+
+#define mb()				barrier()
+#define rmb()				barrier()
+#define wmb()				barrier()
+#define smp_mb()			barrier()
+#define smp_rmb()			barrier()
+#define smp_wmb()			barrier()
+#define read_barrier_depends()		do { } while (0)
+#define smp_read_barrier_depends()	do { } while (0)
+
+#define set_mb(var, value)		do { var = value; smp_mb(); } while (0)
+
+#endif /* __UNICORE_BARRIER_H__ */
diff --git a/arch/unicore32/include/asm/bug.h b/arch/unicore32/include/asm/bug.h
new file mode 100644
index 000000000000..b1ff8cadb086
--- /dev/null
+++ b/arch/unicore32/include/asm/bug.h
@@ -0,0 +1,27 @@
+/*
+ * Bug handling for PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2012 GUAN Xue-tao
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __UNICORE_BUG_H__
+#define __UNICORE_BUG_H__
+
+#include <asm-generic/bug.h>
+
+struct pt_regs;
+struct siginfo;
+
+extern void die(const char *msg, struct pt_regs *regs, int err);
+extern void uc32_notify_die(const char *str, struct pt_regs *regs,
+		struct siginfo *info, unsigned long err, unsigned long trap);
+
+extern asmlinkage void __backtrace(void);
+extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
+
+extern void __show_regs(struct pt_regs *);
+
+#endif /* __UNICORE_BUG_H__ */
diff --git a/arch/unicore32/include/asm/cmpxchg.h b/arch/unicore32/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..df4d5acfd19f
--- /dev/null
+++ b/arch/unicore32/include/asm/cmpxchg.h
@@ -0,0 +1,61 @@
+/*
+ * Atomics xchg/cmpxchg for PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2012 GUAN Xue-tao
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __UNICORE_CMPXCHG_H__
+#define __UNICORE_CMPXCHG_H__
+
+/*
+ * Generate a link failure on undefined symbol if the pointer points to a value
+ * of unsupported size.
+ */
+extern void __xchg_bad_pointer(void);
+
+static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
+		int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+	case 1:
+		asm volatile("swapb	%0, %1, [%2]"
+			: "=&r" (ret)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+	case 4:
+		asm volatile("swapw	%0, %1, [%2]"
+			: "=&r" (ret)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+	default:
+		ret = __xchg_bad_pointer();
+	}
+
+	return ret;
+}
+
+#define xchg(ptr, x) \
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+
+#include <asm-generic/cmpxchg-local.h>
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)					\
+		((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr),	\
+		(unsigned long)(o), (unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n)					\
+		__cmpxchg64_local_generic((ptr), (o), (n))
+
+#include <asm-generic/cmpxchg.h>
+
+#endif /* __UNICORE_CMPXCHG_H__ */
diff --git a/arch/unicore32/include/asm/dma-mapping.h b/arch/unicore32/include/asm/dma-mapping.h
index 9258e592f414..366460a81796 100644
--- a/arch/unicore32/include/asm/dma-mapping.h
+++ b/arch/unicore32/include/asm/dma-mapping.h
@@ -82,20 +82,26 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 	return 0;
 }
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+	return dma_ops->alloc(dev, size, dma_handle, flag, attrs);
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+	dma_ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/unicore32/include/asm/exec.h b/arch/unicore32/include/asm/exec.h
new file mode 100644
index 000000000000..06d1f0f57888
--- /dev/null
+++ b/arch/unicore32/include/asm/exec.h
@@ -0,0 +1,15 @@
+/*
+ * Process execution bits for PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2012 GUAN Xue-tao
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __UNICORE_EXEC_H__
+#define __UNICORE_EXEC_H__
+
+#define arch_align_stack(x)		(x)
+
+#endif /* __UNICORE_EXEC_H__ */
diff --git a/arch/unicore32/include/asm/hwdef-copro.h b/arch/unicore32/include/asm/hwdef-copro.h
new file mode 100644
index 000000000000..a3292f039a68
--- /dev/null
+++ b/arch/unicore32/include/asm/hwdef-copro.h
@@ -0,0 +1,48 @@
+/*
+ * Co-processor register definitions for PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2012 GUAN Xue-tao
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __UNICORE_HWDEF_COPRO_H__
+#define __UNICORE_HWDEF_COPRO_H__
+
+/*
+ * Control Register bits (CP#0 CR1)
+ */
+#define CR_M	(1 << 0)	/* MMU enable				*/
+#define CR_A	(1 << 1)	/* Alignment abort enable		*/
+#define CR_D	(1 << 2)	/* Dcache enable			*/
+#define CR_I	(1 << 3)	/* Icache enable			*/
+#define CR_B	(1 << 4)	/* Dcache write mechanism: write back	*/
+#define CR_T	(1 << 5)	/* Burst enable				*/
+#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
+
+#ifndef __ASSEMBLY__
+
+#define vectors_high()		(cr_alignment & CR_V)
+
+extern unsigned long cr_no_alignment;	/* defined in entry.S */
+extern unsigned long cr_alignment;	/* defined in entry.S */
+
+static inline unsigned int get_cr(void)
+{
+	unsigned int val;
+	asm("movc %0, p0.c1, #0" : "=r" (val) : : "cc");
+	return val;
+}
+
+static inline void set_cr(unsigned int val)
+{
+	asm volatile("movc p0.c1, %0, #0" : : "r" (val) : "cc");
+	isb();
+}
+
+extern void adjust_cr(unsigned long mask, unsigned long set);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __UNICORE_HWDEF_COPRO_H__ */
diff --git a/arch/unicore32/include/asm/io.h b/arch/unicore32/include/asm/io.h
index adddf6d64077..39decb6e6f57 100644
--- a/arch/unicore32/include/asm/io.h
+++ b/arch/unicore32/include/asm/io.h
@@ -16,7 +16,6 @@
 
 #include <asm/byteorder.h>
 #include <asm/memory.h>
-#include <asm/system.h>
 
 #define PCI_IOBASE	PKUNITY_PCILIO_BASE
 #include <asm-generic/io.h>
diff --git a/arch/unicore32/include/asm/switch_to.h b/arch/unicore32/include/asm/switch_to.h
new file mode 100644
index 000000000000..39572d2bd692
--- /dev/null
+++ b/arch/unicore32/include/asm/switch_to.h
@@ -0,0 +1,30 @@
+/*
+ * Task switching for PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2012 GUAN Xue-tao
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __UNICORE_SWITCH_TO_H__
+#define __UNICORE_SWITCH_TO_H__
+
+struct task_struct;
+struct thread_info;
+
+/*
+ * switch_to(prev, next) should switch from task `prev' to `next'
+ * `prev' will never be the same as `next'.  schedule() itself
+ * contains the memory barrier to tell GCC not to cache `current'.
+ */
+extern struct task_struct *__switch_to(struct task_struct *,
+		struct thread_info *, struct thread_info *);
+
+#define switch_to(prev, next, last)					\
+	do {								\
+		last = __switch_to(prev, task_thread_info(prev),	\
+					task_thread_info(next));	\
+	} while (0)
+
+#endif /* __UNICORE_SWITCH_TO_H__ */
diff --git a/arch/unicore32/include/asm/system.h b/arch/unicore32/include/asm/system.h
deleted file mode 100644
index 246b71c17fda..000000000000
--- a/arch/unicore32/include/asm/system.h
+++ /dev/null
@@ -1,161 +0,0 @@
-/*
- * linux/arch/unicore32/include/asm/system.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __UNICORE_SYSTEM_H__
-#define __UNICORE_SYSTEM_H__
-
-#ifdef __KERNEL__
-
-/*
- * CR1 bits (CP#0 CR1)
- */
-#define CR_M	(1 << 0)	/* MMU enable				*/
-#define CR_A	(1 << 1)	/* Alignment abort enable		*/
-#define CR_D	(1 << 2)	/* Dcache enable			*/
-#define CR_I	(1 << 3)	/* Icache enable			*/
-#define CR_B	(1 << 4)	/* Dcache write mechanism: write back	*/
-#define CR_T	(1 << 5)	/* Burst enable				*/
-#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
-
-#ifndef __ASSEMBLY__
-
-#include <linux/linkage.h>
-#include <linux/irqflags.h>
-
-struct thread_info;
-struct task_struct;
-
-struct pt_regs;
-
-void die(const char *msg, struct pt_regs *regs, int err);
-
-struct siginfo;
-void uc32_notify_die(const char *str, struct pt_regs *regs,
-		struct siginfo *info, unsigned long err, unsigned long trap);
-
-void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
-				       struct pt_regs *),
-		     int sig, int code, const char *name);
-
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-
-extern asmlinkage void __backtrace(void);
-extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
-
-struct mm_struct;
-extern void show_pte(struct mm_struct *mm, unsigned long addr);
-extern void __show_regs(struct pt_regs *);
-
-extern int cpu_architecture(void);
-extern void cpu_init(void);
-
-#define vectors_high()	(cr_alignment & CR_V)
-
-#define isb() __asm__ __volatile__ ("" : : : "memory")
-#define dsb() __asm__ __volatile__ ("" : : : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
-
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define read_barrier_depends()		do { } while (0)
-#define smp_read_barrier_depends()	do { } while (0)
-
-#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
-#define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
-
-extern unsigned long cr_no_alignment;	/* defined in entry-unicore.S */
-extern unsigned long cr_alignment;	/* defined in entry-unicore.S */
-
-static inline unsigned int get_cr(void)
-{
-	unsigned int val;
-	asm("movc %0, p0.c1, #0" : "=r" (val) : : "cc");
-	return val;
-}
-
-static inline void set_cr(unsigned int val)
-{
-	asm volatile("movc p0.c1, %0, #0	@set CR"
-	  : : "r" (val) : "cc");
-	isb();
-}
-
-extern void adjust_cr(unsigned long mask, unsigned long set);
-
-/*
- * switch_to(prev, next) should switch from task `prev' to `next'
- * `prev' will never be the same as `next'.  schedule() itself
- * contains the memory barrier to tell GCC not to cache `current'.
- */
-extern struct task_struct *__switch_to(struct task_struct *,
-		struct thread_info *, struct thread_info *);
-extern void panic(const char *fmt, ...);
-
-#define switch_to(prev, next, last)					\
-do {									\
-	last = __switch_to(prev,					\
-		task_thread_info(prev), task_thread_info(next));	\
-} while (0)
-
-static inline unsigned long
-__xchg(unsigned long x, volatile void *ptr, int size)
-{
-	unsigned long ret;
-
-	switch (size) {
-	case 1:
-		asm volatile("@	__xchg1\n"
-		"	swapb	%0, %1, [%2]"
-			: "=&r" (ret)
-			: "r" (x), "r" (ptr)
-			: "memory", "cc");
-		break;
-	case 4:
-		asm volatile("@	__xchg4\n"
-		"	swapw	%0, %1, [%2]"
-			: "=&r" (ret)
-			: "r" (x), "r" (ptr)
-			: "memory", "cc");
-		break;
-	default:
-		panic("xchg: bad data size: ptr 0x%p, size %d\n",
-			ptr, size);
-	}
-
-	return ret;
-}
-
-#include <asm-generic/cmpxchg-local.h>
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)					\
-		((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr),	\
-		(unsigned long)(o), (unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n)					\
-		__cmpxchg64_local_generic((ptr), (o), (n))
-
-#include <asm-generic/cmpxchg.h>
-
-#endif /* __ASSEMBLY__ */
-
-#define arch_align_stack(x) (x)
-
-#endif /* __KERNEL__ */
-
-#endif
diff --git a/arch/unicore32/include/asm/uaccess.h b/arch/unicore32/include/asm/uaccess.h
index 2acda503a6d9..897e11ad8124 100644
--- a/arch/unicore32/include/asm/uaccess.h
+++ b/arch/unicore32/include/asm/uaccess.h
@@ -16,7 +16,6 @@
 #include <linux/errno.h>
 
 #include <asm/memory.h>
-#include <asm/system.h>
 
 #define __copy_from_user	__copy_from_user
 #define __copy_to_user		__copy_to_user
diff --git a/arch/unicore32/kernel/dma.c b/arch/unicore32/kernel/dma.c
index ae441bc3122c..ed2d4d78d9c4 100644
--- a/arch/unicore32/kernel/dma.c
+++ b/arch/unicore32/kernel/dma.c
@@ -18,7 +18,6 @@
 #include <linux/errno.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
 #include <mach/dma.h>
diff --git a/arch/unicore32/kernel/head.S b/arch/unicore32/kernel/head.S
index 8caf322e110d..e8f0b98c02ee 100644
--- a/arch/unicore32/kernel/head.S
+++ b/arch/unicore32/kernel/head.S
@@ -17,7 +17,7 @@
 #include <generated/asm-offsets.h>
 #include <asm/memory.h>
 #include <asm/thread_info.h>
-#include <asm/system.h>
+#include <asm/hwdef-copro.h>
 #include <asm/pgtable-hwdef.h>
 
 #if (PHYS_OFFSET & 0x003fffff)
diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c
index 7d0f0b7983a0..d75ef8b6cb56 100644
--- a/arch/unicore32/kernel/hibernate.c
+++ b/arch/unicore32/kernel/hibernate.c
@@ -15,7 +15,6 @@
 #include <linux/suspend.h>
 #include <linux/bootmem.h>
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
diff --git a/arch/unicore32/kernel/irq.c b/arch/unicore32/kernel/irq.c
index d4efa7d679ff..0be5ccd7ccd2 100644
--- a/arch/unicore32/kernel/irq.c
+++ b/arch/unicore32/kernel/irq.c
@@ -26,7 +26,6 @@
 #include <linux/syscore_ops.h>
 #include <linux/gpio.h>
 
-#include <asm/system.h>
 #include <mach/hardware.h>
 
 #include "setup.h"
diff --git a/arch/unicore32/kernel/ksyms.c b/arch/unicore32/kernel/ksyms.c
index d98bd812cae1..d285d71cbe35 100644
--- a/arch/unicore32/kernel/ksyms.c
+++ b/arch/unicore32/kernel/ksyms.c
@@ -20,7 +20,6 @@
 #include <linux/io.h>
 
 #include <asm/checksum.h>
-#include <asm/system.h>
 
 #include "ksyms.h"
 
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 432b4291f37b..b6f0458c3143 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -34,7 +34,6 @@
 
 #include <asm/cacheflush.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/stacktrace.h>
 
 #include "setup.h"
diff --git a/arch/unicore32/kernel/setup.h b/arch/unicore32/kernel/setup.h
index dcd1306eb5c6..f23955028a18 100644
--- a/arch/unicore32/kernel/setup.h
+++ b/arch/unicore32/kernel/setup.h
@@ -12,8 +12,11 @@
 #ifndef __UNICORE_KERNEL_SETUP_H__
 #define __UNICORE_KERNEL_SETUP_H__
 
+#include <asm/hwdef-copro.h>
+
 extern void paging_init(void);
 extern void puv3_core_init(void);
+extern void cpu_init(void);
 
 extern void puv3_ps2_init(void);
 extern void pci_puv3_preinit(void);
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
index b9a26465e728..2054f0d4db13 100644
--- a/arch/unicore32/kernel/traps.c
+++ b/arch/unicore32/kernel/traps.c
@@ -26,7 +26,6 @@
 #include <linux/unistd.h>
 
 #include <asm/cacheflush.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 #include "setup.h"
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
index 28f576d733ee..de7dc5fdd58b 100644
--- a/arch/unicore32/mm/alignment.c
+++ b/arch/unicore32/mm/alignment.c
@@ -24,6 +24,8 @@
 #include <asm/tlbflush.h>
 #include <asm/unaligned.h>
 
+#include "mm.h"
+
 #define CODING_BITS(i)	(i & 0xe0000120)
 
 #define LDST_P_BIT(i)	(i & (1 << 28))	/* Preindex             */
diff --git a/arch/unicore32/mm/dma-swiotlb.c b/arch/unicore32/mm/dma-swiotlb.c
index bfa9fbb2bbb1..16c08b2143a7 100644
--- a/arch/unicore32/mm/dma-swiotlb.c
+++ b/arch/unicore32/mm/dma-swiotlb.c
@@ -17,9 +17,23 @@
 
 #include <asm/dma.h>
 
+static void *unicore_swiotlb_alloc_coherent(struct device *dev, size_t size,
+					    dma_addr_t *dma_handle, gfp_t flags,
+					    struct dma_attrs *attrs)
+{
+	return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+}
+
+static void unicore_swiotlb_free_coherent(struct device *dev, size_t size,
+					  void *vaddr, dma_addr_t dma_addr,
+					  struct dma_attrs *attrs)
+{
+	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
+
 struct dma_map_ops swiotlb_dma_map_ops = {
-	.alloc_coherent = swiotlb_alloc_coherent,
-	.free_coherent = swiotlb_free_coherent,
+	.alloc = unicore_swiotlb_alloc_coherent,
+	.free = unicore_swiotlb_free_coherent,
 	.map_sg = swiotlb_map_sg_attrs,
 	.unmap_sg = swiotlb_unmap_sg_attrs,
 	.dma_supported = swiotlb_dma_supported,
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 283aa4b50b7a..2eeb9c04cab0 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -20,7 +20,6 @@
 #include <linux/sched.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
diff --git a/arch/unicore32/mm/flush.c b/arch/unicore32/mm/flush.c
index 93478cc8b26d..6d4c096ffa2a 100644
--- a/arch/unicore32/mm/flush.c
+++ b/arch/unicore32/mm/flush.c
@@ -14,7 +14,6 @@
 #include <linux/pagemap.h>
 
 #include <asm/cacheflush.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 
 void flush_cache_mm(struct mm_struct *mm)
diff --git a/arch/unicore32/mm/mm.h b/arch/unicore32/mm/mm.h
index 3296bca0f1f7..05c7f532eee2 100644
--- a/arch/unicore32/mm/mm.h
+++ b/arch/unicore32/mm/mm.h
@@ -9,6 +9,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <asm/hwdef-copro.h>
+
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
 extern int sysctl_overcommit_memory;
@@ -34,6 +36,9 @@ struct mem_type {
 const struct mem_type *get_mem_type(unsigned int type);
 
 extern void __flush_dcache_page(struct address_space *, struct page *);
+extern void hook_fault_code(int nr, int (*fn)
+		(unsigned long, unsigned int, struct pt_regs *),
+		int sig, int code, const char *name);
 
 void __init bootmem_init(void);
 void uc32_mm_memblock_reserve(void);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 901952355969..1d14cc6b79ad 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -69,7 +69,6 @@ config X86
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_TEXT_POKE_SMP
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select SPARSE_IRQ
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_IRQ_PROBE
@@ -2125,6 +2124,13 @@ config NET5501
 	---help---
 	  This option enables system support for the Soekris Engineering net5501.
 
+config GEOS
+	bool "Traverse Technologies GEOS System Support (LEDS, GPIO, etc)"
+	select GPIOLIB
+	depends on DMI
+	---help---
+	  This option enables system support for the Traverse Technologies GEOS.
+
 endif # X86_32
 
 config AMD_NB
@@ -2157,9 +2163,9 @@ config IA32_EMULATION
 	depends on X86_64
 	select COMPAT_BINFMT_ELF
 	---help---
-	  Include code to run 32-bit programs under a 64-bit kernel. You should
-	  likely turn this on, unless you're 100% sure that you don't have any
-	  32-bit programs left.
+	  Include code to run legacy 32-bit programs under a
+	  64-bit kernel. You should likely turn this on, unless you're
+	  100% sure that you don't have any 32-bit programs left.
 
 config IA32_AOUT
 	tristate "IA32 a.out support"
@@ -2167,9 +2173,23 @@ config IA32_AOUT
 	---help---
 	  Support old a.out binaries in the 32bit emulation.
 
+config X86_X32
+	bool "x32 ABI for 64-bit mode (EXPERIMENTAL)"
+	depends on X86_64 && IA32_EMULATION && EXPERIMENTAL
+	---help---
+	  Include code to run binaries for the x32 native 32-bit ABI
+	  for 64-bit processors.  An x32 process gets access to the
+	  full 64-bit register file and wide data path while leaving
+	  pointers at 32 bits for smaller memory footprint.
+
+	  You will need a recent binutils (2.22 or later) with
+	  elf32_x86_64 support enabled to compile a kernel with this
+	  option set.
+
 config COMPAT
 	def_bool y
-	depends on IA32_EMULATION
+	depends on IA32_EMULATION || X86_X32
+	select ARCH_WANT_OLD_COMPAT_IPC
 
 config COMPAT_FOR_U64_ALIGNMENT
 	def_bool COMPAT
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 209ba1294592..41a7237606a3 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -82,6 +82,22 @@ ifdef CONFIG_CC_STACKPROTECTOR
         endif
 endif
 
+ifdef CONFIG_X86_X32
+	x32_ld_ok := $(call try-run,\
+			/bin/echo -e '1: .quad 1b' | \
+			$(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" - && \
+			$(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMPO" && \
+			$(LD) -m elf32_x86_64 "$$TMPO" -o "$$TMP",y,n)
+        ifeq ($(x32_ld_ok),y)
+                CONFIG_X86_X32_ABI := y
+                KBUILD_AFLAGS += -DCONFIG_X86_X32_ABI
+                KBUILD_CFLAGS += -DCONFIG_X86_X32_ABI
+        else
+                $(warning CONFIG_X86_X32 enabled but no binutils support)
+        endif
+endif
+export CONFIG_X86_X32_ABI
+
 # Don't unroll struct assignments with kmemcheck enabled
 ifeq ($(CONFIG_KMEMCHECK),y)
 	KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
@@ -113,6 +129,7 @@ KBUILD_CFLAGS += -Wno-sign-compare
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 # prevent gcc from generating any FP code by mistake
 KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
+KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 36ddec6a41c9..4be406abeefd 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -8,15 +8,11 @@ ELF_ARCH		:= i386
 ELF_FORMAT 		:= elf32-i386
 CHECKFLAGS	+= -D__i386__
 
-ifeq ("$(origin SUBARCH)", "command line")
-ifneq ("$(shell uname -m | sed -e s/i.86/i386/)", "$(SUBARCH)")
 KBUILD_CFLAGS		+= $(call cc-option,-m32)
 KBUILD_AFLAGS		+= $(call cc-option,-m32)
 LINK-y			+= $(call cc-option,-m32)
 
 export LDFLAGS
-endif
-endif
 
 # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y.
 include $(srctree)/arch/x86/Makefile_32.cpu
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 2bf18059fbea..119db67dcb03 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -15,23 +15,28 @@ CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
 CONFIG_CGROUP_SCHED=y
-CONFIG_UTS_NS=y
-CONFIG_IPC_NS=y
-CONFIG_USER_NS=y
-CONFIG_PID_NS=y
-CONFIG_NET_NS=y
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_SGI_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
-CONFIG_SPARSE_IRQ=y
 CONFIG_X86_GENERIC=y
 CONFIG_HPET_TIMER=y
 CONFIG_SCHED_SMT=y
@@ -51,14 +56,12 @@ CONFIG_HZ_1000=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 # CONFIG_COMPAT_VDSO is not set
-CONFIG_PM=y
+CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
 CONFIG_PM_TRACE_RTC=y
-CONFIG_HIBERNATION=y
 CONFIG_ACPI_PROCFS=y
 CONFIG_ACPI_DOCK=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_DEBUG=y
 # CONFIG_CPU_FREQ_STAT is not set
 CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
@@ -69,7 +72,6 @@ CONFIG_PCI_MSI=y
 CONFIG_PCCARD=y
 CONFIG_YENTA=y
 CONFIG_HOTPLUG_PCI=y
-CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
 CONFIG_BINFMT_MISC=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -120,7 +122,6 @@ CONFIG_NF_CONNTRACK_IPV4=y
 CONFIG_IP_NF_IPTABLES=y
 CONFIG_IP_NF_FILTER=y
 CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_LOG=y
 CONFIG_IP_NF_TARGET_ULOG=y
 CONFIG_NF_NAT=y
 CONFIG_IP_NF_TARGET_MASQUERADE=y
@@ -128,7 +129,6 @@ CONFIG_IP_NF_MANGLE=y
 CONFIG_NF_CONNTRACK_IPV6=y
 CONFIG_IP6_NF_IPTABLES=y
 CONFIG_IP6_NF_MATCH_IPV6HEADER=y
-CONFIG_IP6_NF_TARGET_LOG=y
 CONFIG_IP6_NF_FILTER=y
 CONFIG_IP6_NF_TARGET_REJECT=y
 CONFIG_IP6_NF_MANGLE=y
@@ -169,25 +169,20 @@ CONFIG_DM_ZERO=y
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_NET_VENDOR_3COM=y
+CONFIG_NETCONSOLE=y
+CONFIG_BNX2=y
+CONFIG_TIGON3=y
 CONFIG_NET_TULIP=y
-CONFIG_NET_PCI=y
-CONFIG_FORCEDETH=y
 CONFIG_E100=y
+CONFIG_E1000=y
+CONFIG_E1000E=y
+CONFIG_SKY2=y
 CONFIG_NE2K_PCI=y
+CONFIG_FORCEDETH=y
 CONFIG_8139TOO=y
 # CONFIG_8139TOO_PIO is not set
-CONFIG_E1000=y
-CONFIG_E1000E=y
 CONFIG_R8169=y
-CONFIG_SKY2=y
-CONFIG_TIGON3=y
-CONFIG_BNX2=y
-CONFIG_TR=y
-CONFIG_NET_PCMCIA=y
 CONFIG_FDDI=y
-CONFIG_NETCONSOLE=y
 CONFIG_INPUT_POLLDEV=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
@@ -196,6 +191,7 @@ CONFIG_INPUT_TABLET=y
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_INPUT_MISC=y
 CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_NONSTANDARD=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
@@ -205,7 +201,6 @@ CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
-# CONFIG_LEGACY_PTYS is not set
 CONFIG_HW_RANDOM=y
 CONFIG_NVRAM=y
 CONFIG_HPET=y
@@ -220,7 +215,6 @@ CONFIG_DRM_I915=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
@@ -283,7 +277,6 @@ CONFIG_ZISOFS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_NFS_FS=y
@@ -291,18 +284,6 @@ CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
@@ -317,13 +298,12 @@ CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_DEBUG_STACK_USAGE=y
 # CONFIG_DEBUG_RODATA_TEST is not set
 CONFIG_DEBUG_NX_TEST=m
 CONFIG_DEBUG_BOOT_PARAMS=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 058a35b8286c..76eb2903809f 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,4 +1,3 @@
-CONFIG_64BIT=y
 CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SYSVIPC=y
@@ -16,26 +15,29 @@ CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
 CONFIG_CGROUP_SCHED=y
-CONFIG_UTS_NS=y
-CONFIG_IPC_NS=y
-CONFIG_USER_NS=y
-CONFIG_PID_NS=y
-CONFIG_NET_NS=y
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_SGI_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
-CONFIG_SPARSE_IRQ=y
 CONFIG_CALGARY_IOMMU=y
-CONFIG_AMD_IOMMU=y
-CONFIG_AMD_IOMMU_STATS=y
 CONFIG_NR_CPUS=64
 CONFIG_SCHED_SMT=y
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -53,27 +55,22 @@ CONFIG_HZ_1000=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 # CONFIG_COMPAT_VDSO is not set
-CONFIG_PM=y
+CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
 CONFIG_PM_TRACE_RTC=y
-CONFIG_HIBERNATION=y
 CONFIG_ACPI_PROCFS=y
 CONFIG_ACPI_DOCK=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_DEBUG=y
 # CONFIG_CPU_FREQ_STAT is not set
 CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_X86_ACPI_CPUFREQ=y
 CONFIG_PCI_MMCONFIG=y
-CONFIG_INTEL_IOMMU=y
-# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCCARD=y
 CONFIG_YENTA=y
 CONFIG_HOTPLUG_PCI=y
-CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
 CONFIG_BINFMT_MISC=y
 CONFIG_IA32_EMULATION=y
 CONFIG_NET=y
@@ -125,7 +122,6 @@ CONFIG_NF_CONNTRACK_IPV4=y
 CONFIG_IP_NF_IPTABLES=y
 CONFIG_IP_NF_FILTER=y
 CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_LOG=y
 CONFIG_IP_NF_TARGET_ULOG=y
 CONFIG_NF_NAT=y
 CONFIG_IP_NF_TARGET_MASQUERADE=y
@@ -133,7 +129,6 @@ CONFIG_IP_NF_MANGLE=y
 CONFIG_NF_CONNTRACK_IPV6=y
 CONFIG_IP6_NF_IPTABLES=y
 CONFIG_IP6_NF_MATCH_IPV6HEADER=y
-CONFIG_IP6_NF_TARGET_LOG=y
 CONFIG_IP6_NF_FILTER=y
 CONFIG_IP6_NF_TARGET_REJECT=y
 CONFIG_IP6_NF_MANGLE=y
@@ -172,20 +167,15 @@ CONFIG_DM_ZERO=y
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_NET_VENDOR_3COM=y
+CONFIG_NETCONSOLE=y
+CONFIG_TIGON3=y
 CONFIG_NET_TULIP=y
-CONFIG_NET_PCI=y
-CONFIG_FORCEDETH=y
 CONFIG_E100=y
-CONFIG_8139TOO=y
 CONFIG_E1000=y
 CONFIG_SKY2=y
-CONFIG_TIGON3=y
-CONFIG_TR=y
-CONFIG_NET_PCMCIA=y
+CONFIG_FORCEDETH=y
+CONFIG_8139TOO=y
 CONFIG_FDDI=y
-CONFIG_NETCONSOLE=y
 CONFIG_INPUT_POLLDEV=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
@@ -194,6 +184,7 @@ CONFIG_INPUT_TABLET=y
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_INPUT_MISC=y
 CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_NONSTANDARD=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
@@ -203,7 +194,6 @@ CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
-# CONFIG_LEGACY_PTYS is not set
 CONFIG_HW_RANDOM=y
 # CONFIG_HW_RANDOM_INTEL is not set
 # CONFIG_HW_RANDOM_AMD is not set
@@ -221,7 +211,6 @@ CONFIG_DRM_I915_KMS=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
@@ -268,6 +257,10 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
 CONFIG_DMADEVICES=y
 CONFIG_EEEPC_LAPTOP=y
+CONFIG_AMD_IOMMU=y
+CONFIG_AMD_IOMMU_STATS=y
+CONFIG_INTEL_IOMMU=y
+# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
 CONFIG_EFI_VARS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
@@ -284,7 +277,6 @@ CONFIG_ZISOFS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_NFS_FS=y
@@ -292,18 +284,6 @@ CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
@@ -317,13 +297,12 @@ CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_DEBUG_STACK_USAGE=y
 # CONFIG_DEBUG_RODATA_TEST is not set
 CONFIG_DEBUG_NX_TEST=m
 CONFIG_DEBUG_BOOT_PARAMS=y
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 4c2e59a420b9..d511d951a052 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -26,7 +26,6 @@
 #include <linux/init.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 5563ba1cf513..a69245ba27e3 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -12,10 +12,8 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
-#include <linux/signal.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
-#include <linux/ptrace.h>
 #include <linux/unistd.h>
 #include <linux/stddef.h>
 #include <linux/personality.h>
@@ -32,20 +30,15 @@
 #include <asm/proto.h>
 #include <asm/vdso.h>
 #include <asm/sigframe.h>
+#include <asm/sighandling.h>
 #include <asm/sys_ia32.h>
 
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
-#define FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
-			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
-			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
-			 X86_EFLAGS_CF)
-
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+#define FIX_EFLAGS	__FIX_EFLAGS
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 {
 	int err = 0;
+	bool ia32 = is_ia32_task();
 
 	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
 		return -EFAULT;
@@ -75,8 +68,13 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 			case __SI_FAULT >> 16:
 				break;
 			case __SI_CHLD >> 16:
-				put_user_ex(from->si_utime, &to->si_utime);
-				put_user_ex(from->si_stime, &to->si_stime);
+				if (ia32) {
+					put_user_ex(from->si_utime, &to->si_utime);
+					put_user_ex(from->si_stime, &to->si_stime);
+				} else {
+					put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
+					put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
+				}
 				put_user_ex(from->si_status, &to->si_status);
 				/* FALL THROUGH */
 			default:
@@ -348,7 +346,7 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
 		put_user_ex(regs->dx, &sc->dx);
 		put_user_ex(regs->cx, &sc->cx);
 		put_user_ex(regs->ax, &sc->ax);
-		put_user_ex(current->thread.trap_no, &sc->trapno);
+		put_user_ex(current->thread.trap_nr, &sc->trapno);
 		put_user_ex(current->thread.error_code, &sc->err);
 		put_user_ex(regs->ip, &sc->ip);
 		put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index f6f5c53dc903..aec2202a596c 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -287,46 +287,6 @@ asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act,
 	return ret;
 }
 
-asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
-				     compat_sigset_t __user *oset,
-				     unsigned int sigsetsize)
-{
-	sigset_t s;
-	compat_sigset_t s32;
-	int ret;
-	mm_segment_t old_fs = get_fs();
-
-	if (set) {
-		if (copy_from_user(&s32, set, sizeof(compat_sigset_t)))
-			return -EFAULT;
-		switch (_NSIG_WORDS) {
-		case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32);
-		case 3: s.sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32);
-		case 2: s.sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32);
-		case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32);
-		}
-	}
-	set_fs(KERNEL_DS);
-	ret = sys_rt_sigprocmask(how,
-				 set ? (sigset_t __user *)&s : NULL,
-				 oset ? (sigset_t __user *)&s : NULL,
-				 sigsetsize);
-	set_fs(old_fs);
-	if (ret)
-		return ret;
-	if (oset) {
-		switch (_NSIG_WORDS) {
-		case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3];
-		case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2];
-		case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1];
-		case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0];
-		}
-		if (copy_to_user(oset, &s32, sizeof(compat_sigset_t)))
-			return -EFAULT;
-	}
-	return 0;
-}
-
 asmlinkage long sys32_alarm(unsigned int seconds)
 {
 	return alarm_setitimer(seconds);
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index b57e6a43a37a..f9c0d3ba9e84 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -14,6 +14,7 @@ header-y += msr.h
 header-y += mtrr.h
 header-y += posix_types_32.h
 header-y += posix_types_64.h
+header-y += posix_types_x32.h
 header-y += prctl.h
 header-y += processor-flags.h
 header-y += ptrace-abi.h
@@ -24,3 +25,4 @@ header-y += vsyscall.h
 
 genhdr-y += unistd_32.h
 genhdr-y += unistd_64.h
+genhdr-y += unistd_x32.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a9371c91718c..d85410171260 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -11,7 +11,6 @@
 #include <linux/atomic.h>
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
-#include <asm/system.h>
 #include <asm/msr.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
@@ -535,7 +534,7 @@ static inline unsigned int read_apic_id(void)
 
 static inline int default_apic_id_valid(int apicid)
 {
-	return x2apic_mode || (apicid < 255);
+	return (apicid < 255);
 }
 
 extern void default_setup_apic_routing(void);
diff --git a/arch/x86/include/asm/auxvec.h b/arch/x86/include/asm/auxvec.h
index 1316b4c35425..77203ac352de 100644
--- a/arch/x86/include/asm/auxvec.h
+++ b/arch/x86/include/asm/auxvec.h
@@ -9,4 +9,11 @@
 #endif
 #define AT_SYSINFO_EHDR		33
 
+/* entries in ARCH_DLINFO: */
+#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
+# define AT_VECTOR_SIZE_ARCH 2
+#else /* else it's non-compat x86-64 */
+# define AT_VECTOR_SIZE_ARCH 1
+#endif
+
 #endif /* _ASM_X86_AUXVEC_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
new file mode 100644
index 000000000000..c6cd358a1eec
--- /dev/null
+++ b/arch/x86/include/asm/barrier.h
@@ -0,0 +1,116 @@
+#ifndef _ASM_X86_BARRIER_H
+#define _ASM_X86_BARRIER_H
+
+#include <asm/alternative.h>
+#include <asm/nops.h>
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#ifdef CONFIG_X86_32
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#else
+#define mb() 	asm volatile("mfence":::"memory")
+#define rmb()	asm volatile("lfence":::"memory")
+#define wmb()	asm volatile("sfence" ::: "memory")
+#endif
+
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier.  All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads.  This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies.  See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	b = 2;
+ *	memory_barrier();
+ *	p = &b;				q = p;
+ *					read_barrier_depends();
+ *					d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends().  However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	a = 2;
+ *	memory_barrier();
+ *	b = 3;				y = b;
+ *					read_barrier_depends();
+ *					x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b".  Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
+ * in cases like this where there are no data dependencies.
+ **/
+
+#define read_barrier_depends()	do { } while (0)
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+# define smp_rmb()	rmb()
+#else
+# define smp_rmb()	barrier()
+#endif
+#ifdef CONFIG_X86_OOSTORE
+# define smp_wmb() 	wmb()
+#else
+# define smp_wmb()	barrier()
+#endif
+#define smp_read_barrier_depends()	read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static __always_inline void rdtsc_barrier(void)
+{
+	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index f654d1bb17fb..11e1152222d0 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -36,4 +36,8 @@ do {								\
 #endif /* !CONFIG_BUG */
 
 #include <asm-generic/bug.h>
+
+
+extern void show_regs_common(void);
+
 #endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 4e12668711e5..9863ee3747da 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -3,6 +3,7 @@
 
 /* Caches aren't brain-dead on the intel. */
 #include <asm-generic/cacheflush.h>
+#include <asm/special_insns.h>
 
 #ifdef CONFIG_X86_PAT
 /*
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 30d737ef2a42..d6805798d6fc 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -6,7 +6,9 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <asm/processor.h>
 #include <asm/user32.h>
+#include <asm/unistd.h>
 
 #define COMPAT_USER_HZ		100
 #define COMPAT_UTS_MACHINE	"i686\0\0"
@@ -186,7 +188,20 @@ struct compat_shmid64_ds {
 /*
  * The type of struct elf_prstatus.pr_reg in compatible core dumps.
  */
+#ifdef CONFIG_X86_X32_ABI
+typedef struct user_regs_struct compat_elf_gregset_t;
+
+#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216)
+#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296)
+#define SET_PR_FPVALID(S,V) \
+  do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \
+  while (0)
+
+#define COMPAT_USE_64BIT_TIME \
+	(!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT))
+#else
 typedef struct user_regs_struct32 compat_elf_gregset_t;
+#endif
 
 /*
  * A pointer passed in from user mode. This should not
@@ -208,13 +223,30 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	return (void __user *)regs->sp - len;
+	compat_uptr_t sp;
+
+	if (test_thread_flag(TIF_IA32)) {
+		sp = task_pt_regs(current)->sp;
+	} else {
+		/* -128 for the x32 ABI redzone */
+		sp = percpu_read(old_rsp) - 128;
+	}
+
+	return (void __user *)round_down(sp - len, 16);
+}
+
+static inline bool is_x32_task(void)
+{
+#ifdef CONFIG_X86_X32_ABI
+	if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)
+		return true;
+#endif
+	return false;
 }
 
-static inline int is_compat_task(void)
+static inline bool is_compat_task(void)
 {
-	return current_thread_info()->status & TS_COMPAT;
+	return is_ia32_task() || is_x32_task();
 }
 
 #endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ed3065fd6314..4b4331d71935 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -59,7 +59,8 @@ extern int dma_supported(struct device *hwdev, u64 mask);
 extern int dma_set_mask(struct device *dev, u64 mask);
 
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag);
+					dma_addr_t *dma_addr, gfp_t flag,
+					struct dma_attrs *attrs);
 
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
@@ -111,9 +112,11 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
        return gfp;
 }
 
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
 static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp)
+dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 	void *memory;
@@ -129,18 +132,21 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (!is_device_dma_capable(dev))
 		return NULL;
 
-	if (!ops->alloc_coherent)
+	if (!ops->alloc)
 		return NULL;
 
-	memory = ops->alloc_coherent(dev, size, dma_handle,
-				     dma_alloc_coherent_gfp_flags(dev, gfp));
+	memory = ops->alloc(dev, size, dma_handle,
+			    dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
 	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
 
 	return memory;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t bus)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t bus,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
@@ -150,8 +156,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 		return;
 
 	debug_dma_free_coherent(dev, size, vaddr, bus);
-	if (ops->free_coherent)
-		ops->free_coherent(dev, size, vaddr, bus);
+	if (ops->free)
+		ops->free(dev, size, vaddr, bus, attrs);
 }
 
 #endif
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 5f962df30d0f..5939f44fe0c0 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -84,7 +84,6 @@ extern unsigned int vdso_enabled;
 	(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
 
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_X86_32
 #include <asm/desc.h>
@@ -156,7 +155,12 @@ do {						\
 #define elf_check_arch(x)			\
 	((x)->e_machine == EM_X86_64)
 
-#define compat_elf_check_arch(x)	elf_check_arch_ia32(x)
+#define compat_elf_check_arch(x)		\
+	(elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+
+#if __USER32_DS != __USER_DS
+# error "The following code assumes __USER32_DS == __USER_DS"
+#endif
 
 static inline void elf_common_init(struct thread_struct *t,
 				   struct pt_regs *regs, const u16 ds)
@@ -179,8 +183,9 @@ static inline void elf_common_init(struct thread_struct *t,
 void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
 #define compat_start_thread start_thread_ia32
 
-void set_personality_ia32(void);
-#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32()
+void set_personality_ia32(bool);
+#define COMPAT_SET_PERSONALITY(ex)			\
+	set_personality_ia32((ex).e_machine == EM_X86_64)
 
 #define COMPAT_ELF_PLATFORM			("i686")
 
@@ -287,7 +292,7 @@ do {									\
 #define VDSO_HIGH_BASE		0xffffe000U /* CONFIG_COMPAT_VDSO address */
 
 /* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
+#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
 
 #define ARCH_DLINFO							\
 do {									\
@@ -296,9 +301,20 @@ do {									\
 			    (unsigned long)current->mm->context.vdso);	\
 } while (0)
 
+#define ARCH_DLINFO_X32							\
+do {									\
+	if (vdso_enabled)						\
+		NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
+			    (unsigned long)current->mm->context.vdso);	\
+} while (0)
+
 #define AT_SYSINFO		32
 
-#define COMPAT_ARCH_DLINFO	ARCH_DLINFO_IA32(sysctl_vsyscall32)
+#define COMPAT_ARCH_DLINFO						\
+if (test_thread_flag(TIF_X32))						\
+	ARCH_DLINFO_X32;						\
+else									\
+	ARCH_DLINFO_IA32(sysctl_vsyscall32)
 
 #define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
 
@@ -314,6 +330,8 @@ struct linux_binprm;
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int uses_interp);
+extern int x32_setup_additional_pages(struct linux_binprm *bprm,
+				      int uses_interp);
 
 extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
 #define compat_arch_setup_additional_pages	syscall32_setup_pages
@@ -330,7 +348,7 @@ static inline int mmap_is_ia32(void)
 	return 1;
 #endif
 #ifdef CONFIG_IA32_EMULATION
-	if (test_thread_flag(TIF_IA32))
+	if (test_thread_flag(TIF_ADDR32))
 		return 1;
 #endif
 	return 0;
diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h
new file mode 100644
index 000000000000..54c2e1db274a
--- /dev/null
+++ b/arch/x86/include/asm/exec.h
@@ -0,0 +1 @@
+/* define arch_align_stack() here */
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index d09bb03653f0..71ecbcba1a4e 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -9,7 +9,6 @@
 #include <asm/asm.h>
 #include <asm/errno.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg)	\
 	asm volatile("1:\t" insn "\n"				\
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 7ce0798b1b26..257d9cca214f 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -14,7 +14,6 @@
 
 #include <linux/sched.h>
 #include <linux/hardirq.h>
-#include <asm/system.h>
 
 struct pt_regs;
 struct user_i387_struct;
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 1f7e62517284..ee52760549f0 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -43,6 +43,15 @@ struct ucontext_ia32 {
 	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
 };
 
+struct ucontext_x32 {
+	unsigned int	  uc_flags;
+	unsigned int 	  uc_link;
+	stack_ia32_t	  uc_stack;
+	unsigned int	  uc__pad0;     /* needed for alignment */
+	struct sigcontext uc_mcontext;  /* the 64-bit sigcontext type */
+	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
+};
+
 /* This matches struct stat64 in glibc2.2, hence the absolutely
  * insane amounts of padding around dev_t's.
  */
@@ -116,6 +125,15 @@ typedef struct compat_siginfo {
 			compat_clock_t _stime;
 		} _sigchld;
 
+		/* SIGCHLD (x32 version) */
+		struct {
+			unsigned int _pid;	/* which child */
+			unsigned int _uid;	/* sender's uid */
+			int _status;		/* exit code */
+			compat_s64 _utime;
+			compat_s64 _stime;
+		} _sigchld_x32;
+
 		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 		struct {
 			unsigned int _addr;	/* faulting insn/memory ref. */
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index f49253d75710..c5d1785373ed 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -14,6 +14,7 @@ void exit_idle(void);
 #else /* !CONFIG_X86_64 */
 static inline void enter_idle(void) { }
 static inline void exit_idle(void) { }
+static inline void __exit_idle(void) { }
 #endif /* CONFIG_X86_64 */
 
 void amd_e400_remove_cpu(int cpu);
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 690d1cc9a877..2c4943de5150 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -21,6 +21,15 @@
 #define IO_APIC_REDIR_LEVEL_TRIGGER	(1 << 15)
 #define IO_APIC_REDIR_MASKED		(1 << 16)
 
+struct io_apic_ops {
+	void		(*init)  (void);
+	unsigned int	(*read)  (unsigned int apic, unsigned int reg);
+	void		(*write) (unsigned int apic, unsigned int reg, unsigned int value);
+	void		(*modify)(unsigned int apic, unsigned int reg, unsigned int value);
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *);
+
 /*
  * The structure of the IO-APIC:
  */
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 4d8dcbdfc120..e7d1c194d272 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -321,4 +321,8 @@ struct kvm_xcrs {
 	__u64 padding[16];
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 7b9cfc4878af..c222e1a1b12a 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -176,6 +176,7 @@ struct x86_emulate_ops {
 	void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
 	ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr);
 	int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val);
+	void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val);
 	int (*cpl)(struct x86_emulate_ctxt *ctxt);
 	int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
 	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
@@ -388,7 +389,7 @@ bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_INTERCEPTED 2
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
-			 u16 tss_selector, int reason,
+			 u16 tss_selector, int idt_index, int reason,
 			 bool has_error_code, u32 error_code);
 int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq);
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 52d6640a5ca1..e216ba066e79 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -29,7 +29,7 @@
 #include <asm/msr-index.h>
 
 #define KVM_MAX_VCPUS 254
-#define KVM_SOFT_MAX_VCPUS 64
+#define KVM_SOFT_MAX_VCPUS 160
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
@@ -181,13 +181,6 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
-#define NR_PTE_CHAIN_ENTRIES 5
-
-struct kvm_pte_chain {
-	u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
-	struct hlist_node link;
-};
-
 /*
  * kvm_mmu_page_role, below, is defined as:
  *
@@ -427,12 +420,16 @@ struct kvm_vcpu_arch {
 
 	u64 last_guest_tsc;
 	u64 last_kernel_ns;
-	u64 last_tsc_nsec;
-	u64 last_tsc_write;
-	u32 virtual_tsc_khz;
+	u64 last_host_tsc;
+	u64 tsc_offset_adjustment;
+	u64 this_tsc_nsec;
+	u64 this_tsc_write;
+	u8  this_tsc_generation;
 	bool tsc_catchup;
-	u32  tsc_catchup_mult;
-	s8   tsc_catchup_shift;
+	bool tsc_always_catchup;
+	s8 virtual_tsc_shift;
+	u32 virtual_tsc_mult;
+	u32 virtual_tsc_khz;
 
 	atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
 	unsigned nmi_pending; /* NMI queued after currently running handler */
@@ -478,6 +475,21 @@ struct kvm_vcpu_arch {
 		u32 id;
 		bool send_user_only;
 	} apf;
+
+	/* OSVW MSRs (AMD only) */
+	struct {
+		u64 length;
+		u64 status;
+	} osvw;
+};
+
+struct kvm_lpage_info {
+	unsigned long rmap_pde;
+	int write_count;
+};
+
+struct kvm_arch_memory_slot {
+	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
 };
 
 struct kvm_arch {
@@ -511,8 +523,12 @@ struct kvm_arch {
 	s64 kvmclock_offset;
 	raw_spinlock_t tsc_write_lock;
 	u64 last_tsc_nsec;
-	u64 last_tsc_offset;
 	u64 last_tsc_write;
+	u32 last_tsc_khz;
+	u64 cur_tsc_nsec;
+	u64 cur_tsc_write;
+	u64 cur_tsc_offset;
+	u8  cur_tsc_generation;
 
 	struct kvm_xen_hvm_config xen_hvm_config;
 
@@ -644,7 +660,7 @@ struct kvm_x86_ops {
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
-	void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment);
+	void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host);
 
 	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
@@ -652,7 +668,7 @@ struct kvm_x86_ops {
 
 	bool (*has_wbinvd_exit)(void);
 
-	void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz);
+	void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale);
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
 	u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc);
@@ -674,6 +690,17 @@ struct kvm_arch_async_pf {
 
 extern struct kvm_x86_ops *kvm_x86_ops;
 
+static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
+					   s64 adjustment)
+{
+	kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, false);
+}
+
+static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
+{
+	kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, true);
+}
+
 int kvm_mmu_module_init(void);
 void kvm_mmu_module_exit(void);
 
@@ -741,8 +768,8 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
 
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
-		    bool has_error_code, u32 error_code);
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
+		    int reason, bool has_error_code, u32 error_code);
 
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 9cdae5d47e8f..c8bed0da434a 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -3,7 +3,6 @@
 
 #include <linux/percpu.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/asm.h>
 
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index 0e8e85bb7c51..d354fb781c57 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -5,7 +5,6 @@
 #define _ASM_X86_MC146818RTC_H
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <linux/mc146818rtc.h>
 
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index 4365ffdb461f..7e3f17f92c66 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -29,18 +29,18 @@
 
 #define	MTRR_IOCTL_BASE	'M'
 
-struct mtrr_sentry {
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int type;     /*  Type of region   */
-};
-
 /* Warning: this structure has a different order from i386
    on x86-64. The 32bit emulation code takes care of that.
    But you need to use this for 64bit, otherwise your X server
    will break. */
 
 #ifdef __i386__
+struct mtrr_sentry {
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int type;     /*  Type of region   */
+};
+
 struct mtrr_gentry {
     unsigned int regnum;   /*  Register number  */
     unsigned long base;    /*  Base address     */
@@ -50,12 +50,20 @@ struct mtrr_gentry {
 
 #else /* __i386__ */
 
+struct mtrr_sentry {
+	__u64 base;		/*  Base address     */
+	__u32 size;		/*  Size of region   */
+	__u32 type;		/*  Type of region   */
+};
+
 struct mtrr_gentry {
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int regnum;   /*  Register number  */
-    unsigned int type;     /*  Type of region   */
+	__u64 base;		/*  Base address     */
+	__u32 size;		/*  Size of region   */
+	__u32 regnum;		/*  Register number  */
+	__u32 type;		/*  Type of region   */
+	__u32 _pad;		/*  Unused	     */
 };
+
 #endif /* !__i386__ */
 
 struct mtrr_var_range {
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index bce688d54c12..e21fdd10479f 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -55,7 +55,6 @@ extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 
 extern void initmem_init(void);
-extern void free_initmem(void);
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index e8fb2c7a5f4f..2291895b1836 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -23,6 +23,7 @@
 #define ARCH_PERFMON_EVENTSEL_USR			(1ULL << 16)
 #define ARCH_PERFMON_EVENTSEL_OS			(1ULL << 17)
 #define ARCH_PERFMON_EVENTSEL_EDGE			(1ULL << 18)
+#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL		(1ULL << 19)
 #define ARCH_PERFMON_EVENTSEL_INT			(1ULL << 20)
 #define ARCH_PERFMON_EVENTSEL_ANY			(1ULL << 21)
 #define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h
index bb7133dc155d..3427b7798dbc 100644
--- a/arch/x86/include/asm/posix_types.h
+++ b/arch/x86/include/asm/posix_types.h
@@ -7,7 +7,9 @@
 #else
 # ifdef __i386__
 #  include "posix_types_32.h"
-# else
+# elif defined(__LP64__)
 #  include "posix_types_64.h"
+# else
+#  include "posix_types_x32.h"
 # endif
 #endif
diff --git a/arch/x86/include/asm/posix_types_32.h b/arch/x86/include/asm/posix_types_32.h
index f7d9adf82e53..99f262e04b91 100644
--- a/arch/x86/include/asm/posix_types_32.h
+++ b/arch/x86/include/asm/posix_types_32.h
@@ -7,79 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define __FD_SET(fd,fdsetp)					\
-	asm volatile("btsl %1,%0":				\
-		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
-		     : "r" ((int)(fd)))
-
-#undef	__FD_CLR
-#define __FD_CLR(fd,fdsetp)					\
-	asm volatile("btrl %1,%0":				\
-		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
-		     : "r" ((int) (fd)))
-
-#undef	__FD_ISSET
-#define __FD_ISSET(fd,fdsetp)					\
-	(__extension__						\
-	 ({							\
-	 unsigned char __result;				\
-	 asm volatile("btl %1,%2 ; setb %0"			\
-		      : "=q" (__result)				\
-		      : "r" ((int)(fd)),			\
-			"m" (*(__kernel_fd_set *)(fdsetp)));	\
-	 __result;						\
-}))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp)					\
-do {								\
-	int __d0, __d1;						\
-	asm volatile("cld ; rep ; stosl"			\
-		     : "=m" (*(__kernel_fd_set *)(fdsetp)),	\
-		       "=&c" (__d0), "=&D" (__d1)		\
-		     : "a" (0), "1" (__FDSET_LONGS),		\
-		       "2" ((__kernel_fd_set *)(fdsetp))	\
-		     : "memory");				\
-} while (0)
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_X86_POSIX_TYPES_32_H */
diff --git a/arch/x86/include/asm/posix_types_64.h b/arch/x86/include/asm/posix_types_64.h
index eb8d2d92b63e..cba0c1ead162 100644
--- a/arch/x86/include/asm/posix_types_64.h
+++ b/arch/x86/include/asm/posix_types_64.h
@@ -7,113 +7,13 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef unsigned long	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
 typedef unsigned short __kernel_old_uid_t;
 typedef unsigned short __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
 
 typedef unsigned long	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant cases (8 or 32 longs,
- * for 256 and 1024-bit fd_sets respectively)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 32:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
-			tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
-			tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
-			tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
-			return;
-		case 16:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			return;
-		case 8:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			return;
-		case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_X86_POSIX_TYPES_64_H */
diff --git a/arch/x86/include/asm/posix_types_x32.h b/arch/x86/include/asm/posix_types_x32.h
new file mode 100644
index 000000000000..85f9bdafa93c
--- /dev/null
+++ b/arch/x86/include/asm/posix_types_x32.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_X86_POSIX_TYPES_X32_H
+#define _ASM_X86_POSIX_TYPES_X32_H
+
+/*
+ * This file is only used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.  Also, we cannot
+ * assume GCC is being used.
+ *
+ * These types should generally match the ones used by the 64-bit kernel,
+ *
+ */
+
+typedef long long __kernel_long_t;
+typedef unsigned long long __kernel_ulong_t;
+#define __kernel_long_t __kernel_long_t
+
+#include <asm/posix_types_64.h>
+
+#endif /* _ASM_X86_POSIX_TYPES_X32_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5533b30cac07..4fa7dcceb6c0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -14,13 +14,13 @@ struct mm_struct;
 #include <asm/sigcontext.h>
 #include <asm/current.h>
 #include <asm/cpufeature.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 #include <asm/percpu.h>
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
+#include <asm/special_insns.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -29,6 +29,15 @@ struct mm_struct;
 #include <linux/math64.h>
 #include <linux/init.h>
 #include <linux/err.h>
+#include <linux/irqflags.h>
+
+/*
+ * We handle most unaligned accesses in hardware.  On the other hand
+ * unaligned DMA can be quite expensive on some Nehalem processors.
+ *
+ * Based on this we disable the IP header alignment in network drivers.
+ */
+#define NET_IP_ALIGN	0
 
 #define HBP_NUM 4
 /*
@@ -454,7 +463,7 @@ struct thread_struct {
 	unsigned long           ptrace_dr7;
 	/* Fault info: */
 	unsigned long		cr2;
-	unsigned long		trap_no;
+	unsigned long		trap_nr;
 	unsigned long		error_code;
 	/* floating point and extended processor state */
 	struct fpu		fpu;
@@ -864,9 +873,9 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
 					0xc0000000 : 0xFFFFe000)
 
-#define TASK_SIZE		(test_thread_flag(TIF_IA32) ? \
+#define TASK_SIZE		(test_thread_flag(TIF_ADDR32) ? \
 					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_IA32)) ? \
+#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
 					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
 
 #define STACK_TOP		TASK_SIZE
@@ -888,6 +897,12 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
+
+/*
+ * User space RSP while inside the SYSCALL fast path
+ */
+DECLARE_PER_CPU(unsigned long, old_rsp);
+
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
@@ -959,4 +974,14 @@ extern bool cpu_has_amd_erratum(const int *);
 #define cpu_has_amd_erratum(x)	(false)
 #endif /* CONFIG_CPU_SUP_AMD */
 
+void cpu_idle_wait(void);
+
+extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+
+void default_idle(void);
+bool set_pm_idle_to_default(void);
+
+void stop_this_cpu(void *dummy);
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 35664547125b..dcfde52979c3 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -145,7 +145,6 @@ extern unsigned long
 convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 			 int error_code, int si_code);
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 
 extern long syscall_trace_enter(struct pt_regs *);
 extern void syscall_trace_leave(struct pt_regs *);
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 5e641715c3fe..165466233ab0 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -212,7 +212,61 @@
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
 extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
-#endif
-#endif
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg, value)						\
+do {									\
+	unsigned short __val = (value);					\
+									\
+	asm volatile("						\n"	\
+		     "1:	movl %k0,%%" #seg "		\n"	\
+									\
+		     ".section .fixup,\"ax\"			\n"	\
+		     "2:	xorl %k0,%k0			\n"	\
+		     "		jmp 1b				\n"	\
+		     ".previous					\n"	\
+									\
+		     _ASM_EXTABLE(1b, 2b)				\
+									\
+		     : "+r" (__val) : : "memory");			\
+} while (0)
+
+/*
+ * Save a segment register away
+ */
+#define savesegment(seg, value)				\
+	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
+
+/*
+ * x86_32 user gs accessors.
+ */
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_32_LAZY_GS
+#define get_user_gs(regs)	(u16)({unsigned long v; savesegment(gs, v); v;})
+#define set_user_gs(regs, v)	loadsegment(gs, (unsigned long)(v))
+#define task_user_gs(tsk)	((tsk)->thread.gs)
+#define lazy_save_gs(v)		savesegment(gs, (v))
+#define lazy_load_gs(v)		loadsegment(gs, (v))
+#else	/* X86_32_LAZY_GS */
+#define get_user_gs(regs)	(u16)((regs)->gs)
+#define set_user_gs(regs, v)	do { (regs)->gs = (v); } while (0)
+#define task_user_gs(tsk)	(task_pt_regs(tsk)->gs)
+#define lazy_save_gs(v)		do { } while (0)
+#define lazy_load_gs(v)		do { } while (0)
+#endif	/* X86_32_LAZY_GS */
+#endif	/* X86_32 */
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+	unsigned long __limit;
+	asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
+	return __limit + 1;
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SEGMENT_H */
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 04459d25e66e..4a085383af27 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -230,34 +230,37 @@ struct sigcontext {
  * User-space might still rely on the old definition:
  */
 struct sigcontext {
-	unsigned long r8;
-	unsigned long r9;
-	unsigned long r10;
-	unsigned long r11;
-	unsigned long r12;
-	unsigned long r13;
-	unsigned long r14;
-	unsigned long r15;
-	unsigned long rdi;
-	unsigned long rsi;
-	unsigned long rbp;
-	unsigned long rbx;
-	unsigned long rdx;
-	unsigned long rax;
-	unsigned long rcx;
-	unsigned long rsp;
-	unsigned long rip;
-	unsigned long eflags;		/* RFLAGS */
-	unsigned short cs;
-	unsigned short gs;
-	unsigned short fs;
-	unsigned short __pad0;
-	unsigned long err;
-	unsigned long trapno;
-	unsigned long oldmask;
-	unsigned long cr2;
+	__u64 r8;
+	__u64 r9;
+	__u64 r10;
+	__u64 r11;
+	__u64 r12;
+	__u64 r13;
+	__u64 r14;
+	__u64 r15;
+	__u64 rdi;
+	__u64 rsi;
+	__u64 rbp;
+	__u64 rbx;
+	__u64 rdx;
+	__u64 rax;
+	__u64 rcx;
+	__u64 rsp;
+	__u64 rip;
+	__u64 eflags;		/* RFLAGS */
+	__u16 cs;
+	__u16 gs;
+	__u16 fs;
+	__u16 __pad0;
+	__u64 err;
+	__u64 trapno;
+	__u64 oldmask;
+	__u64 cr2;
 	struct _fpstate __user *fpstate;	/* zero when no FPU context */
-	unsigned long reserved1[8];
+#ifndef __LP64__
+	__u32 __fpstate_pad;
+#endif
+	__u64 reserved1[8];
 };
 #endif /* !__KERNEL__ */
 
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 4e0fe26d27d3..7c7c27c97daa 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -59,12 +59,25 @@ struct rt_sigframe_ia32 {
 #endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */
 
 #ifdef CONFIG_X86_64
+
 struct rt_sigframe {
 	char __user *pretcode;
 	struct ucontext uc;
 	struct siginfo info;
 	/* fp state follows here */
 };
+
+#ifdef CONFIG_X86_X32_ABI
+
+struct rt_sigframe_x32 {
+	u64 pretcode;
+	struct ucontext_x32 uc;
+	compat_siginfo_t info;
+	/* fp state follows here */
+};
+
+#endif /* CONFIG_X86_X32_ABI */
+
 #endif /* CONFIG_X86_64 */
 
 #endif /* _ASM_X86_SIGFRAME_H */
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
new file mode 100644
index 000000000000..ada93b3b8c66
--- /dev/null
+++ b/arch/x86/include/asm/sighandling.h
@@ -0,0 +1,24 @@
+#ifndef _ASM_X86_SIGHANDLING_H
+#define _ASM_X86_SIGHANDLING_H
+
+#include <linux/compiler.h>
+#include <linux/ptrace.h>
+#include <linux/signal.h>
+
+#include <asm/processor-flags.h>
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+#define __FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
+			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
+			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
+			 X86_EFLAGS_CF)
+
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
+		       unsigned long *pax);
+int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+		     struct pt_regs *regs, unsigned long mask);
+
+#endif /* _ASM_X86_SIGHANDLING_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
new file mode 100644
index 000000000000..41fc93a2e225
--- /dev/null
+++ b/arch/x86/include/asm/special_insns.h
@@ -0,0 +1,199 @@
+#ifndef _ASM_X86_SPECIAL_INSNS_H
+#define _ASM_X86_SPECIAL_INSNS_H
+
+
+#ifdef __KERNEL__
+
+static inline void native_clts(void)
+{
+	asm volatile("clts");
+}
+
+/*
+ * Volatile isn't enough to prevent the compiler from reordering the
+ * read/write functions for the control registers and messing everything up.
+ * A memory clobber would solve the problem, but would prevent reordering of
+ * all loads stores around it, which can hurt performance. Solution is to
+ * use a variable and mimic reads and writes to it to enforce serialization
+ */
+static unsigned long __force_order;
+
+static inline unsigned long native_read_cr0(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr0(unsigned long val)
+{
+	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr2(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr2(unsigned long val)
+{
+	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr3(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr3(unsigned long val)
+{
+	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr4(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline unsigned long native_read_cr4_safe(void)
+{
+	unsigned long val;
+	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
+	 * exists, so it will never fail. */
+#ifdef CONFIG_X86_32
+	asm volatile("1: mov %%cr4, %0\n"
+		     "2:\n"
+		     _ASM_EXTABLE(1b, 2b)
+		     : "=r" (val), "=m" (__force_order) : "0" (0));
+#else
+	val = native_read_cr4();
+#endif
+	return val;
+}
+
+static inline void native_write_cr4(unsigned long val)
+{
+	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
+}
+
+#ifdef CONFIG_X86_64
+static inline unsigned long native_read_cr8(void)
+{
+	unsigned long cr8;
+	asm volatile("movq %%cr8,%0" : "=r" (cr8));
+	return cr8;
+}
+
+static inline void native_write_cr8(unsigned long val)
+{
+	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
+}
+#endif
+
+static inline void native_wbinvd(void)
+{
+	asm volatile("wbinvd": : :"memory");
+}
+
+extern void native_load_gs_index(unsigned);
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+
+static inline unsigned long read_cr0(void)
+{
+	return native_read_cr0();
+}
+
+static inline void write_cr0(unsigned long x)
+{
+	native_write_cr0(x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+	return native_read_cr2();
+}
+
+static inline void write_cr2(unsigned long x)
+{
+	native_write_cr2(x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+	return native_read_cr3();
+}
+
+static inline void write_cr3(unsigned long x)
+{
+	native_write_cr3(x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+	return native_read_cr4();
+}
+
+static inline unsigned long read_cr4_safe(void)
+{
+	return native_read_cr4_safe();
+}
+
+static inline void write_cr4(unsigned long x)
+{
+	native_write_cr4(x);
+}
+
+static inline void wbinvd(void)
+{
+	native_wbinvd();
+}
+
+#ifdef CONFIG_X86_64
+
+static inline unsigned long read_cr8(void)
+{
+	return native_read_cr8();
+}
+
+static inline void write_cr8(unsigned long x)
+{
+	native_write_cr8(x);
+}
+
+static inline void load_gs_index(unsigned selector)
+{
+	native_load_gs_index(selector);
+}
+
+#endif
+
+/* Clear the 'TS' bit */
+static inline void clts(void)
+{
+	native_clts();
+}
+
+#endif/* CONFIG_PARAVIRT */
+
+#define stts() write_cr0(read_cr0() | X86_CR0_TS)
+
+static inline void clflush(volatile void *__p)
+{
+	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
+}
+
+#define nop() asm volatile ("nop")
+
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 157517763565..b5d9533d2c38 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -38,7 +38,6 @@
 #include <asm/tsc.h>
 #include <asm/processor.h>
 #include <asm/percpu.h>
-#include <asm/system.h>
 #include <asm/desc.h>
 #include <linux/random.h>
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
new file mode 100644
index 000000000000..4ec45b3abba1
--- /dev/null
+++ b/arch/x86/include/asm/switch_to.h
@@ -0,0 +1,129 @@
+#ifndef _ASM_X86_SWITCH_TO_H
+#define _ASM_X86_SWITCH_TO_H
+
+struct task_struct; /* one of the stranger aspects of C forward declarations */
+struct task_struct *__switch_to(struct task_struct *prev,
+				struct task_struct *next);
+struct tss_struct;
+void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
+		      struct tss_struct *tss);
+
+#ifdef CONFIG_X86_32
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary							\
+	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
+	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
+#define __switch_canary_oparam						\
+	, [stack_canary] "=m" (stack_canary.canary)
+#define __switch_canary_iparam						\
+	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else	/* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif	/* CC_STACKPROTECTOR */
+
+/*
+ * Saving eflags is important. It switches not only IOPL between tasks,
+ * it also protects other tasks from NT leaking through sysenter etc.
+ */
+#define switch_to(prev, next, last)					\
+do {									\
+	/*								\
+	 * Context-switching clobbers all registers, so we clobber	\
+	 * them explicitly, via unused output variables.		\
+	 * (EAX and EBP is not listed because EBP is saved/restored	\
+	 * explicitly for wchan access and EAX is the return value of	\
+	 * __switch_to())						\
+	 */								\
+	unsigned long ebx, ecx, edx, esi, edi;				\
+									\
+	asm volatile("pushfl\n\t"		/* save    flags */	\
+		     "pushl %%ebp\n\t"		/* save    EBP   */	\
+		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
+		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
+		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
+		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
+		     __switch_canary					\
+		     "jmp __switch_to\n"	/* regparm call  */	\
+		     "1:\t"						\
+		     "popl %%ebp\n\t"		/* restore EBP   */	\
+		     "popfl\n"			/* restore flags */	\
+									\
+		     /* output parameters */				\
+		     : [prev_sp] "=m" (prev->thread.sp),		\
+		       [prev_ip] "=m" (prev->thread.ip),		\
+		       "=a" (last),					\
+									\
+		       /* clobbered output registers: */		\
+		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
+		       "=S" (esi), "=D" (edi)				\
+		       							\
+		       __switch_canary_oparam				\
+									\
+		       /* input parameters: */				\
+		     : [next_sp]  "m" (next->thread.sp),		\
+		       [next_ip]  "m" (next->thread.ip),		\
+		       							\
+		       /* regparm parameters for __switch_to(): */	\
+		       [prev]     "a" (prev),				\
+		       [next]     "d" (next)				\
+									\
+		       __switch_canary_iparam				\
+									\
+		     : /* reloaded segment registers */			\
+			"memory");					\
+} while (0)
+
+#else /* CONFIG_X86_32 */
+
+/* frame pointer must be last for get_wchan */
+#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+
+#define __EXTRA_CLOBBER  \
+	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
+	  "r12", "r13", "r14", "r15"
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary							  \
+	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
+	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
+#define __switch_canary_oparam						  \
+	, [gs_canary] "=m" (irq_stack_union.stack_canary)
+#define __switch_canary_iparam						  \
+	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else	/* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif	/* CC_STACKPROTECTOR */
+
+/* Save restore flags to clear handle leaking NT */
+#define switch_to(prev, next, last) \
+	asm volatile(SAVE_CONTEXT					  \
+	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
+	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
+	     "call __switch_to\n\t"					  \
+	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
+	     __switch_canary						  \
+	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
+	     "movq %%rax,%%rdi\n\t" 					  \
+	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"		  \
+	     "jnz   ret_from_fork\n\t"					  \
+	     RESTORE_CONTEXT						  \
+	     : "=a" (last)					  	  \
+	       __switch_canary_oparam					  \
+	     : [next] "S" (next), [prev] "D" (prev),			  \
+	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
+	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
+	       [_tif_fork] "i" (_TIF_FORK),			  	  \
+	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
+	       [current_task] "m" (current_task)			  \
+	       __switch_canary_iparam					  \
+	     : "memory", "cc" __EXTRA_CLOBBER)
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index cb238526a9f1..3fda9db48819 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -10,6 +10,8 @@
 #ifndef _ASM_X86_SYS_IA32_H
 #define _ASM_X86_SYS_IA32_H
 
+#ifdef CONFIG_COMPAT
+
 #include <linux/compiler.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
@@ -36,8 +38,6 @@ asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *,
 				   struct sigaction32 __user *, unsigned int);
 asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *,
 				struct old_sigaction32 __user *);
-asmlinkage long sys32_rt_sigprocmask(int, compat_sigset_t __user *,
-				     compat_sigset_t __user *, unsigned int);
 asmlinkage long sys32_alarm(unsigned int);
 
 asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int);
@@ -83,4 +83,7 @@ asmlinkage long sys32_ipc(u32, int, int, int, compat_uptr_t, u32);
 
 asmlinkage long sys32_fanotify_mark(int, unsigned int, u32, u32, int,
 				    const char __user *);
+
+#endif /* CONFIG_COMPAT */
+
 #endif /* _ASM_X86_SYS_IA32_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d962e5652a73..386b78686c4d 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 #include <asm/asm-offsets.h>	/* For NR_syscalls */
+#include <asm/unistd.h>
 
 extern const unsigned long sys_call_table[];
 
@@ -26,13 +27,13 @@ extern const unsigned long sys_call_table[];
  */
 static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
-	return regs->orig_ax;
+	return regs->orig_ax & __SYSCALL_MASK;
 }
 
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
-	regs->ax = regs->orig_ax;
+	regs->ax = regs->orig_ax & __SYSCALL_MASK;
 }
 
 static inline long syscall_get_error(struct task_struct *task,
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
deleted file mode 100644
index 2d2f01ce6dcb..000000000000
--- a/arch/x86/include/asm/system.h
+++ /dev/null
@@ -1,523 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H
-#define _ASM_X86_SYSTEM_H
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
-# define AT_VECTOR_SIZE_ARCH 2
-#else /* else it's non-compat x86-64 */
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-struct task_struct; /* one of the stranger aspects of C forward declarations */
-struct task_struct *__switch_to(struct task_struct *prev,
-				struct task_struct *next);
-struct tss_struct;
-void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
-		      struct tss_struct *tss);
-extern void show_regs_common(void);
-
-#ifdef CONFIG_X86_32
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary							\
-	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
-	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
-#define __switch_canary_oparam						\
-	, [stack_canary] "=m" (stack_canary.canary)
-#define __switch_canary_iparam						\
-	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else	/* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif	/* CC_STACKPROTECTOR */
-
-/*
- * Saving eflags is important. It switches not only IOPL between tasks,
- * it also protects other tasks from NT leaking through sysenter etc.
- */
-#define switch_to(prev, next, last)					\
-do {									\
-	/*								\
-	 * Context-switching clobbers all registers, so we clobber	\
-	 * them explicitly, via unused output variables.		\
-	 * (EAX and EBP is not listed because EBP is saved/restored	\
-	 * explicitly for wchan access and EAX is the return value of	\
-	 * __switch_to())						\
-	 */								\
-	unsigned long ebx, ecx, edx, esi, edi;				\
-									\
-	asm volatile("pushfl\n\t"		/* save    flags */	\
-		     "pushl %%ebp\n\t"		/* save    EBP   */	\
-		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
-		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
-		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
-		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
-		     __switch_canary					\
-		     "jmp __switch_to\n"	/* regparm call  */	\
-		     "1:\t"						\
-		     "popl %%ebp\n\t"		/* restore EBP   */	\
-		     "popfl\n"			/* restore flags */	\
-									\
-		     /* output parameters */				\
-		     : [prev_sp] "=m" (prev->thread.sp),		\
-		       [prev_ip] "=m" (prev->thread.ip),		\
-		       "=a" (last),					\
-									\
-		       /* clobbered output registers: */		\
-		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
-		       "=S" (esi), "=D" (edi)				\
-		       							\
-		       __switch_canary_oparam				\
-									\
-		       /* input parameters: */				\
-		     : [next_sp]  "m" (next->thread.sp),		\
-		       [next_ip]  "m" (next->thread.ip),		\
-		       							\
-		       /* regparm parameters for __switch_to(): */	\
-		       [prev]     "a" (prev),				\
-		       [next]     "d" (next)				\
-									\
-		       __switch_canary_iparam				\
-									\
-		     : /* reloaded segment registers */			\
-			"memory");					\
-} while (0)
-
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-#else
-
-/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
-
-#define __EXTRA_CLOBBER  \
-	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15"
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary							  \
-	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
-	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
-#define __switch_canary_oparam						  \
-	, [gs_canary] "=m" (irq_stack_union.stack_canary)
-#define __switch_canary_iparam						  \
-	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else	/* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif	/* CC_STACKPROTECTOR */
-
-/* Save restore flags to clear handle leaking NT */
-#define switch_to(prev, next, last) \
-	asm volatile(SAVE_CONTEXT					  \
-	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
-	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
-	     "call __switch_to\n\t"					  \
-	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
-	     __switch_canary						  \
-	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
-	     "movq %%rax,%%rdi\n\t" 					  \
-	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"		  \
-	     "jnz   ret_from_fork\n\t"					  \
-	     RESTORE_CONTEXT						  \
-	     : "=a" (last)					  	  \
-	       __switch_canary_oparam					  \
-	     : [next] "S" (next), [prev] "D" (prev),			  \
-	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
-	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
-	       [_tif_fork] "i" (_TIF_FORK),			  	  \
-	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [current_task] "m" (current_task)			  \
-	       __switch_canary_iparam					  \
-	     : "memory", "cc" __EXTRA_CLOBBER)
-#endif
-
-#ifdef __KERNEL__
-
-extern void native_load_gs_index(unsigned);
-
-/*
- * Load a segment. Fall back on loading the zero
- * segment if something goes wrong..
- */
-#define loadsegment(seg, value)						\
-do {									\
-	unsigned short __val = (value);					\
-									\
-	asm volatile("						\n"	\
-		     "1:	movl %k0,%%" #seg "		\n"	\
-									\
-		     ".section .fixup,\"ax\"			\n"	\
-		     "2:	xorl %k0,%k0			\n"	\
-		     "		jmp 1b				\n"	\
-		     ".previous					\n"	\
-									\
-		     _ASM_EXTABLE(1b, 2b)				\
-									\
-		     : "+r" (__val) : : "memory");			\
-} while (0)
-
-/*
- * Save a segment register away
- */
-#define savesegment(seg, value)				\
-	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
-
-/*
- * x86_32 user gs accessors.
- */
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_X86_32_LAZY_GS
-#define get_user_gs(regs)	(u16)({unsigned long v; savesegment(gs, v); v;})
-#define set_user_gs(regs, v)	loadsegment(gs, (unsigned long)(v))
-#define task_user_gs(tsk)	((tsk)->thread.gs)
-#define lazy_save_gs(v)		savesegment(gs, (v))
-#define lazy_load_gs(v)		loadsegment(gs, (v))
-#else	/* X86_32_LAZY_GS */
-#define get_user_gs(regs)	(u16)((regs)->gs)
-#define set_user_gs(regs, v)	do { (regs)->gs = (v); } while (0)
-#define task_user_gs(tsk)	(task_pt_regs(tsk)->gs)
-#define lazy_save_gs(v)		do { } while (0)
-#define lazy_load_gs(v)		do { } while (0)
-#endif	/* X86_32_LAZY_GS */
-#endif	/* X86_32 */
-
-static inline unsigned long get_limit(unsigned long segment)
-{
-	unsigned long __limit;
-	asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
-	return __limit + 1;
-}
-
-static inline void native_clts(void)
-{
-	asm volatile("clts");
-}
-
-/*
- * Volatile isn't enough to prevent the compiler from reordering the
- * read/write functions for the control registers and messing everything up.
- * A memory clobber would solve the problem, but would prevent reordering of
- * all loads stores around it, which can hurt performance. Solution is to
- * use a variable and mimic reads and writes to it to enforce serialization
- */
-static unsigned long __force_order;
-
-static inline unsigned long native_read_cr0(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr0(unsigned long val)
-{
-	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr2(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr2(unsigned long val)
-{
-	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr3(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr3(unsigned long val)
-{
-	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr4(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline unsigned long native_read_cr4_safe(void)
-{
-	unsigned long val;
-	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
-	 * exists, so it will never fail. */
-#ifdef CONFIG_X86_32
-	asm volatile("1: mov %%cr4, %0\n"
-		     "2:\n"
-		     _ASM_EXTABLE(1b, 2b)
-		     : "=r" (val), "=m" (__force_order) : "0" (0));
-#else
-	val = native_read_cr4();
-#endif
-	return val;
-}
-
-static inline void native_write_cr4(unsigned long val)
-{
-	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
-}
-
-#ifdef CONFIG_X86_64
-static inline unsigned long native_read_cr8(void)
-{
-	unsigned long cr8;
-	asm volatile("movq %%cr8,%0" : "=r" (cr8));
-	return cr8;
-}
-
-static inline void native_write_cr8(unsigned long val)
-{
-	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-#endif
-
-static inline void native_wbinvd(void)
-{
-	asm volatile("wbinvd": : :"memory");
-}
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-
-static inline unsigned long read_cr0(void)
-{
-	return native_read_cr0();
-}
-
-static inline void write_cr0(unsigned long x)
-{
-	native_write_cr0(x);
-}
-
-static inline unsigned long read_cr2(void)
-{
-	return native_read_cr2();
-}
-
-static inline void write_cr2(unsigned long x)
-{
-	native_write_cr2(x);
-}
-
-static inline unsigned long read_cr3(void)
-{
-	return native_read_cr3();
-}
-
-static inline void write_cr3(unsigned long x)
-{
-	native_write_cr3(x);
-}
-
-static inline unsigned long read_cr4(void)
-{
-	return native_read_cr4();
-}
-
-static inline unsigned long read_cr4_safe(void)
-{
-	return native_read_cr4_safe();
-}
-
-static inline void write_cr4(unsigned long x)
-{
-	native_write_cr4(x);
-}
-
-static inline void wbinvd(void)
-{
-	native_wbinvd();
-}
-
-#ifdef CONFIG_X86_64
-
-static inline unsigned long read_cr8(void)
-{
-	return native_read_cr8();
-}
-
-static inline void write_cr8(unsigned long x)
-{
-	native_write_cr8(x);
-}
-
-static inline void load_gs_index(unsigned selector)
-{
-	native_load_gs_index(selector);
-}
-
-#endif
-
-/* Clear the 'TS' bit */
-static inline void clts(void)
-{
-	native_clts();
-}
-
-#endif/* CONFIG_PARAVIRT */
-
-#define stts() write_cr0(read_cr0() | X86_CR0_TS)
-
-#endif /* __KERNEL__ */
-
-static inline void clflush(volatile void *__p)
-{
-	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
-}
-
-#define nop() asm volatile ("nop")
-
-void disable_hlt(void);
-void enable_hlt(void);
-
-void cpu_idle_wait(void);
-
-extern unsigned long arch_align_stack(unsigned long sp);
-extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
-
-void default_idle(void);
-bool set_pm_idle_to_default(void);
-
-void stop_this_cpu(void *dummy);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
-#define wmb()	asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb()	rmb()
-#else
-# define smp_rmb()	barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static __always_inline void rdtsc_barrier(void)
-{
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-/*
- * We handle most unaligned accesses in hardware.  On the other hand
- * unaligned DMA can be quite expensive on some Nehalem processors.
- *
- * Based on this we disable the IP header alignment in network drivers.
- */
-#define NET_IP_ALIGN	0
-#endif /* _ASM_X86_SYSTEM_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index cfd8144d5527..ad6df8ccd715 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -86,7 +86,7 @@ struct thread_info {
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
-#define TIF_IA32		17	/* 32bit process */
+#define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_FORK		18	/* ret_from_fork */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_DEBUG		21	/* uses debug registers */
@@ -95,6 +95,8 @@ struct thread_info {
 #define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
+#define TIF_ADDR32		29	/* 32-bit address space on 64 bits */
+#define TIF_X32			30	/* 32-bit native x86-64 binary */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -116,6 +118,8 @@ struct thread_info {
 #define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_ADDR32		(1 << TIF_ADDR32)
+#define _TIF_X32		(1 << TIF_X32)
 
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY	\
@@ -262,6 +266,18 @@ static inline void set_restore_sigmask(void)
 	ti->status |= TS_RESTORE_SIGMASK;
 	set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
 }
+
+static inline bool is_ia32_task(void)
+{
+#ifdef CONFIG_X86_32
+	return true;
+#endif
+#ifdef CONFIG_IA32_EMULATION
+	if (current_thread_info()->status & TS_COMPAT)
+		return true;
+#endif
+	return false;
+}
 #endif	/* !__ASSEMBLY__ */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 169be8938b96..c0e108e08079 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -5,7 +5,7 @@
 #include <linux/sched.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
+#include <asm/special_insns.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 0012d0902c5f..88eae2aec619 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -89,4 +89,29 @@ asmlinkage void smp_thermal_interrupt(void);
 asmlinkage void mce_threshold_interrupt(void);
 #endif
 
+/* Interrupts/Exceptions */
+enum {
+	X86_TRAP_DE = 0,	/*  0, Divide-by-zero */
+	X86_TRAP_DB,		/*  1, Debug */
+	X86_TRAP_NMI,		/*  2, Non-maskable Interrupt */
+	X86_TRAP_BP,		/*  3, Breakpoint */
+	X86_TRAP_OF,		/*  4, Overflow */
+	X86_TRAP_BR,		/*  5, Bound Range Exceeded */
+	X86_TRAP_UD,		/*  6, Invalid Opcode */
+	X86_TRAP_NM,		/*  7, Device Not Available */
+	X86_TRAP_DF,		/*  8, Double Fault */
+	X86_TRAP_OLD_MF,	/*  9, Coprocessor Segment Overrun */
+	X86_TRAP_TS,		/* 10, Invalid TSS */
+	X86_TRAP_NP,		/* 11, Segment Not Present */
+	X86_TRAP_SS,		/* 12, Stack Segment Fault */
+	X86_TRAP_GP,		/* 13, General Protection Fault */
+	X86_TRAP_PF,		/* 14, Page Fault */
+	X86_TRAP_SPURIOUS,	/* 15, Spurious Interrupt */
+	X86_TRAP_MF,		/* 16, x87 Floating-Point Exception */
+	X86_TRAP_AC,		/* 17, Alignment Check */
+	X86_TRAP_MC,		/* 18, Machine Check */
+	X86_TRAP_XF,		/* 19, SIMD Floating-Point Exception */
+	X86_TRAP_IRET = 32,	/* 32, IRET Exception */
+};
+
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 15d99153a96d..c91e8b9d588b 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -61,7 +61,7 @@ extern void check_tsc_sync_source(int cpu);
 extern void check_tsc_sync_target(void);
 
 extern int notsc_setup(char *);
-extern void save_sched_clock_state(void);
-extern void restore_sched_clock_state(void);
+extern void tsc_save_sched_clock_state(void);
+extern void tsc_restore_sched_clock_state(void);
 
 #endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 21f77b89e47a..37cdc9d99bb1 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -1,7 +1,17 @@
 #ifndef _ASM_X86_UNISTD_H
 #define _ASM_X86_UNISTD_H 1
 
+/* x32 syscall flag bit */
+#define __X32_SYSCALL_BIT	0x40000000
+
 #ifdef __KERNEL__
+
+# ifdef CONFIG_X86_X32_ABI
+#  define __SYSCALL_MASK (~(__X32_SYSCALL_BIT))
+# else
+#  define __SYSCALL_MASK (~0)
+# endif
+
 # ifdef CONFIG_X86_32
 
 #  include <asm/unistd_32.h>
@@ -14,6 +24,7 @@
 # else
 
 #  include <asm/unistd_64.h>
+#  include <asm/unistd_64_x32.h>
 #  define __ARCH_WANT_COMPAT_SYS_TIME
 
 # endif
@@ -52,8 +63,10 @@
 #else
 # ifdef __i386__
 #  include <asm/unistd_32.h>
-# else
+# elif defined(__LP64__)
 #  include <asm/unistd_64.h>
+# else
+#  include <asm/unistd_x32.h>
 # endif
 #endif
 
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 815285bcaceb..8b38be2de9e1 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -5,13 +5,8 @@
 #include <linux/clocksource.h>
 
 struct vsyscall_gtod_data {
-	seqlock_t	lock;
+	seqcount_t	seq;
 
-	/* open coded 'struct timespec' */
-	time_t		wall_time_sec;
-	u32		wall_time_nsec;
-
-	struct timezone sys_tz;
 	struct { /* extract of a clocksource struct */
 		int vclock_mode;
 		cycle_t	cycle_last;
@@ -19,8 +14,16 @@ struct vsyscall_gtod_data {
 		u32	mult;
 		u32	shift;
 	} clock;
-	struct timespec wall_to_monotonic;
+
+	/* open coded 'struct timespec' */
+	time_t		wall_time_sec;
+	u32		wall_time_nsec;
+	u32		monotonic_time_nsec;
+	time_t		monotonic_time_sec;
+
+	struct timezone sys_tz;
 	struct timespec wall_time_coarse;
+	struct timespec monotonic_time_coarse;
 };
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index e0f9aa16358b..5da71c27cc59 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -16,7 +16,6 @@
 #define _ASM_X86_VIRTEX_H
 
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #include <asm/vmx.h>
 #include <asm/svm.h>
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..6fe6767b7124
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,46 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+	return mask*0x0001020304050608ul >> 56;
+}
+
+#else	/* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+#endif
+
+#define REPEAT_BYTE(x)	((~0ul / 0xff) * (x))
+
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+	return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h
index 6bf5b8e478c0..92e54abf89e0 100644
--- a/arch/x86/include/asm/x2apic.h
+++ b/arch/x86/include/asm/x2apic.h
@@ -18,6 +18,11 @@ static const struct cpumask *x2apic_target_cpus(void)
 	return cpu_online_mask;
 }
 
+static int x2apic_apic_id_valid(int apicid)
+{
+	return 1;
+}
+
 static int x2apic_apic_id_registered(void)
 {
 	return 1;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 517d4767ffdd..baaca8defec8 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -145,9 +145,11 @@ struct x86_init_ops {
 /**
  * struct x86_cpuinit_ops - platform specific cpu hotplug setups
  * @setup_percpu_clockev:	set up the per cpu clock event device
+ * @early_percpu_clock_init:	early init of the per cpu clock event device
  */
 struct x86_cpuinit_ops {
 	void (*setup_percpu_clockev)(void);
+	void (*early_percpu_clock_init)(void);
 	void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
 };
 
@@ -160,6 +162,8 @@ struct x86_cpuinit_ops {
  * @is_untracked_pat_range	exclude from PAT logic
  * @nmi_init			enable NMI on cpus
  * @i8042_detect		pre-detect if i8042 controller exists
+ * @save_sched_clock_state:	save state for sched_clock() on suspend
+ * @restore_sched_clock_state:	restore state for sched_clock() on resume
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
@@ -171,6 +175,8 @@ struct x86_platform_ops {
 	void (*nmi_init)(void);
 	unsigned char (*get_nmi_reason)(void);
 	int (*i8042_detect)(void);
+	void (*save_sched_clock_state)(void);
+	void (*restore_sched_clock_state)(void);
 };
 
 struct pci_dev;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 406ed77216d0..a415b1f44365 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -239,7 +239,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 	 * to not preallocating memory for all NR_CPUS
 	 * when we use CPU hotplug.
 	 */
-	if (!cpu_has_x2apic && (apic_id >= 0xff) && enabled)
+	if (!apic->apic_id_valid(apic_id) && enabled)
 		printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
 	else
 		acpi_register_lapic(apic_id, enabled);
@@ -642,6 +642,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
 	kfree(buffer.pointer);
 	buffer.length = ACPI_ALLOCATE_BUFFER;
 	buffer.pointer = NULL;
+	lapic = NULL;
 
 	if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL))
 		goto out;
@@ -650,7 +651,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
 		goto free_tmp_map;
 
 	cpumask_copy(tmp_map, cpu_present_mask);
-	acpi_register_lapic(physid, lapic->lapic_flags & ACPI_MADT_ENABLED);
+	acpi_register_lapic(physid, ACPI_MADT_ENABLED);
 
 	/*
 	 * If mp_register_lapic successfully generates a new logical cpu
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index f50e7fb2a201..d2b7f27781bc 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -14,6 +14,7 @@
 #include <acpi/processor.h>
 #include <asm/acpi.h>
 #include <asm/mwait.h>
+#include <asm/special_insns.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b1e7c7f7a0af..e66311200cbd 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -477,7 +477,7 @@ error:
 /* allocate and map a coherent mapping */
 static void *
 gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
-		    gfp_t flag)
+		    gfp_t flag, struct dma_attrs *attrs)
 {
 	dma_addr_t paddr;
 	unsigned long align_mask;
@@ -500,7 +500,8 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 		}
 		__free_pages(page, get_order(size));
 	} else
-		return dma_generic_alloc_coherent(dev, size, dma_addr, flag);
+		return dma_generic_alloc_coherent(dev, size, dma_addr, flag,
+						  attrs);
 
 	return NULL;
 }
@@ -508,7 +509,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 /* free a coherent mapping */
 static void
 gart_free_coherent(struct device *dev, size_t size, void *vaddr,
-		   dma_addr_t dma_addr)
+		   dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL);
 	free_pages((unsigned long)vaddr, get_order(size));
@@ -700,8 +701,8 @@ static struct dma_map_ops gart_dma_ops = {
 	.unmap_sg			= gart_unmap_sg,
 	.map_page			= gart_map_page,
 	.unmap_page			= gart_unmap_page,
-	.alloc_coherent			= gart_alloc_coherent,
-	.free_coherent			= gart_free_coherent,
+	.alloc				= gart_alloc_coherent,
+	.free				= gart_free_coherent,
 	.mapping_error			= gart_mapping_error,
 };
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2eec05b6d1b8..11544d8f1e97 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -383,20 +383,25 @@ static inline int eilvt_entry_is_changeable(unsigned int old, unsigned int new)
 
 static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 {
-	unsigned int rsvd;			/* 0: uninitialized */
+	unsigned int rsvd, vector;
 
 	if (offset >= APIC_EILVT_NR_MAX)
 		return ~0;
 
-	rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED;
+	rsvd = atomic_read(&eilvt_offsets[offset]);
 	do {
-		if (rsvd &&
-		    !eilvt_entry_is_changeable(rsvd, new))
+		vector = rsvd & ~APIC_EILVT_MASKED;	/* 0: unassigned */
+		if (vector && !eilvt_entry_is_changeable(vector, new))
 			/* may not change if vectors are different */
 			return rsvd;
 		rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
 	} while (rsvd != new);
 
+	rsvd &= ~APIC_EILVT_MASKED;
+	if (rsvd && rsvd != vector)
+		pr_info("LVT offset %d assigned for vector 0x%02x\n",
+			offset, rsvd);
+
 	return new;
 }
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index d9ea5f331ac5..899803e03214 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -229,11 +229,10 @@ static int __init numachip_system_init(void)
 }
 early_initcall(numachip_system_init);
 
-static int __cpuinit numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (!strncmp(oem_id, "NUMASC", 6)) {
 		numachip_system = 1;
-		setup_force_cpu_cap(X86_FEATURE_X2APIC);
 		return 1;
 	}
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 6d10a66fc5a9..e88300d8e80a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -64,9 +64,28 @@
 #include <asm/apic.h>
 
 #define __apicdebuginit(type) static type __init
+
 #define for_each_irq_pin(entry, head) \
 	for (entry = head; entry; entry = entry->next)
 
+static void		__init __ioapic_init_mappings(void);
+
+static unsigned int	__io_apic_read  (unsigned int apic, unsigned int reg);
+static void		__io_apic_write (unsigned int apic, unsigned int reg, unsigned int val);
+static void		__io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
+
+static struct io_apic_ops io_apic_ops = {
+	.init	= __ioapic_init_mappings,
+	.read	= __io_apic_read,
+	.write	= __io_apic_write,
+	.modify = __io_apic_modify,
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *ops)
+{
+	io_apic_ops = *ops;
+}
+
 /*
  *      Is the SiS APIC rmw bug present ?
  *      -1 = don't know, 0 = no, 1 = yes
@@ -294,6 +313,22 @@ static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
 	irq_free_desc(at);
 }
 
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+	return io_apic_ops.read(apic, reg);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+	io_apic_ops.write(apic, reg, value);
+}
+
+static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+{
+	io_apic_ops.modify(apic, reg, value);
+}
+
+
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -314,16 +349,17 @@ static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
 	writel(vector, &io_apic->eoi);
 }
 
-static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+static unsigned int __io_apic_read(unsigned int apic, unsigned int reg)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 	writel(reg, &io_apic->index);
 	return readl(&io_apic->data);
 }
 
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
+
 	writel(reg, &io_apic->index);
 	writel(value, &io_apic->data);
 }
@@ -334,7 +370,7 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i
  *
  * Older SiS APIC requires we rewrite the index register
  */
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 
@@ -377,6 +413,7 @@ static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin)
 
 	eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
 	eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
+
 	return eu.entry;
 }
 
@@ -384,9 +421,11 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
 {
 	union entry_union eu;
 	unsigned long flags;
+
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	eu.entry = __ioapic_read_entry(apic, pin);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+
 	return eu.entry;
 }
 
@@ -396,8 +435,7 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
  * the interrupt, and we need to make sure the entry is fully populated
  * before that happens.
  */
-static void
-__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	union entry_union eu = {{0, 0}};
 
@@ -409,6 +447,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	unsigned long flags;
+
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	__ioapic_write_entry(apic, pin, e);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -435,8 +474,7 @@ static void ioapic_mask_entry(int apic, int pin)
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static int
-__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list **last, *entry;
 
@@ -521,6 +559,7 @@ static void io_apic_sync(struct irq_pin_list *entry)
 	 * a dummy read from the IO-APIC
 	 */
 	struct io_apic __iomem *io_apic;
+
 	io_apic = io_apic_base(entry->apic);
 	readl(&io_apic->data);
 }
@@ -2512,21 +2551,73 @@ static void ack_apic_edge(struct irq_data *data)
 
 atomic_t irq_mis_count;
 
-static void ack_apic_level(struct irq_data *data)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	int i, do_unmask_irq = 0, irq = data->irq;
-	unsigned long v;
-
-	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
+static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+{
 	/* If we are moving the irq we need to mask it */
 	if (unlikely(irqd_is_setaffinity_pending(data))) {
-		do_unmask_irq = 1;
 		mask_ioapic(cfg);
+		return true;
 	}
+	return false;
+}
+
+static inline void ioapic_irqd_unmask(struct irq_data *data,
+				      struct irq_cfg *cfg, bool masked)
+{
+	if (unlikely(masked)) {
+		/* Only migrate the irq if the ack has been received.
+		 *
+		 * On rare occasions the broadcast level triggered ack gets
+		 * delayed going to ioapics, and if we reprogram the
+		 * vector while Remote IRR is still set the irq will never
+		 * fire again.
+		 *
+		 * To prevent this scenario we read the Remote IRR bit
+		 * of the ioapic.  This has two effects.
+		 * - On any sane system the read of the ioapic will
+		 *   flush writes (and acks) going to the ioapic from
+		 *   this cpu.
+		 * - We get to see if the ACK has actually been delivered.
+		 *
+		 * Based on failed experiments of reprogramming the
+		 * ioapic entry from outside of irq context starting
+		 * with masking the ioapic entry and then polling until
+		 * Remote IRR was clear before reprogramming the
+		 * ioapic I don't trust the Remote IRR bit to be
+		 * completey accurate.
+		 *
+		 * However there appears to be no other way to plug
+		 * this race, so if the Remote IRR bit is not
+		 * accurate and is causing problems then it is a hardware bug
+		 * and you can go talk to the chipset vendor about it.
+		 */
+		if (!io_apic_level_ack_pending(cfg))
+			irq_move_masked_irq(data);
+		unmask_ioapic(cfg);
+	}
+}
+#else
+static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+{
+	return false;
+}
+static inline void ioapic_irqd_unmask(struct irq_data *data,
+				      struct irq_cfg *cfg, bool masked)
+{
+}
 #endif
 
+static void ack_apic_level(struct irq_data *data)
+{
+	struct irq_cfg *cfg = data->chip_data;
+	int i, irq = data->irq;
+	unsigned long v;
+	bool masked;
+
+	irq_complete_move(cfg);
+	masked = ioapic_irqd_mask(data, cfg);
+
 	/*
 	 * It appears there is an erratum which affects at least version 0x11
 	 * of I/O APIC (that's the 82093AA and cores integrated into various
@@ -2581,38 +2672,7 @@ static void ack_apic_level(struct irq_data *data)
 		eoi_ioapic_irq(irq, cfg);
 	}
 
-	/* Now we can move and renable the irq */
-	if (unlikely(do_unmask_irq)) {
-		/* Only migrate the irq if the ack has been received.
-		 *
-		 * On rare occasions the broadcast level triggered ack gets
-		 * delayed going to ioapics, and if we reprogram the
-		 * vector while Remote IRR is still set the irq will never
-		 * fire again.
-		 *
-		 * To prevent this scenario we read the Remote IRR bit
-		 * of the ioapic.  This has two effects.
-		 * - On any sane system the read of the ioapic will
-		 *   flush writes (and acks) going to the ioapic from
-		 *   this cpu.
-		 * - We get to see if the ACK has actually been delivered.
-		 *
-		 * Based on failed experiments of reprogramming the
-		 * ioapic entry from outside of irq context starting
-		 * with masking the ioapic entry and then polling until
-		 * Remote IRR was clear before reprogramming the
-		 * ioapic I don't trust the Remote IRR bit to be
-		 * completey accurate.
-		 *
-		 * However there appears to be no other way to plug
-		 * this race, so if the Remote IRR bit is not
-		 * accurate and is causing problems then it is a hardware bug
-		 * and you can go talk to the chipset vendor about it.
-		 */
-		if (!io_apic_level_ack_pending(cfg))
-			irq_move_masked_irq(data);
-		unmask_ioapic(cfg);
-	}
+	ioapic_irqd_unmask(data, cfg, masked);
 }
 
 #ifdef CONFIG_IRQ_REMAP
@@ -3873,6 +3933,11 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics)
 
 void __init ioapic_and_gsi_init(void)
 {
+	io_apic_ops.init();
+}
+
+static void __init __ioapic_init_mappings(void)
+{
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
 	struct resource *ioapic_res;
 	int i;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 9193713060a9..48f3103b3c93 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -213,7 +213,7 @@ static struct apic apic_x2apic_cluster = {
 	.name				= "cluster x2apic",
 	.probe				= x2apic_cluster_probe,
 	.acpi_madt_oem_check		= x2apic_acpi_madt_oem_check,
-	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_valid			= x2apic_apic_id_valid,
 	.apic_id_registered		= x2apic_apic_id_registered,
 
 	.irq_delivery_mode		= dest_LowestPrio,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index bcd1db6eaca9..8a778db45e3a 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -119,7 +119,7 @@ static struct apic apic_x2apic_phys = {
 	.name				= "physical x2apic",
 	.probe				= x2apic_phys_probe,
 	.acpi_madt_oem_check		= x2apic_acpi_madt_oem_check,
-	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_valid			= x2apic_apic_id_valid,
 	.apic_id_registered		= x2apic_apic_id_registered,
 
 	.irq_delivery_mode		= dest_Fixed,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index fc4771425852..87bfa69e216e 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -266,6 +266,11 @@ static void uv_send_IPI_all(int vector)
 	uv_send_IPI_mask(cpu_online_mask, vector);
 }
 
+static int uv_apic_id_valid(int apicid)
+{
+	return 1;
+}
+
 static int uv_apic_id_registered(void)
 {
 	return 1;
@@ -351,7 +356,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
 	.name				= "UV large system",
 	.probe				= uv_probe,
 	.acpi_madt_oem_check		= uv_acpi_madt_oem_check,
-	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_valid			= uv_apic_id_valid,
 	.apic_id_registered		= uv_apic_id_registered,
 
 	.irq_delivery_mode		= dest_Fixed,
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5d56931a15b3..459e78cbf61e 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -231,7 +231,6 @@
 #include <linux/syscore_ops.h>
 #include <linux/i8253.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/olpc.h>
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 834e897b1e25..1b4754f82ba7 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -1,6 +1,12 @@
 #include <asm/ia32.h>
 
 #define __SYSCALL_64(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) [nr] = 1,
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
 static char syscalls_64[] = {
 #include <asm/syscalls_64.h>
 };
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e49477444fff..67e258362a3d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -999,7 +999,7 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
 	else
 		printk(KERN_CONT "\n");
 
-	__print_cpu_msr();
+	print_cpu_msr(c);
 }
 
 void __cpuinit print_cpu_msr(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 5c0e6533d9bc..2d5454cd2c4f 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -9,7 +9,6 @@
 #include <linux/smp.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 67bb17a37a0a..47a1870279aa 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -25,7 +25,6 @@
 #include <linux/cpu.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/idle.h>
 #include <asm/mce.h>
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 54060f565974..2d7998fb628c 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -8,7 +8,6 @@
 #include <linux/init.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 97b26356e9ee..75772ae6c65f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -12,7 +12,6 @@
 #include <asm/processor-flags.h>
 #include <asm/cpufeature.h>
 #include <asm/tlbflush.h>
-#include <asm/system.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 #include <asm/pat.h>
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 79289632cb27..a041e094b8b9 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -167,6 +167,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 {
 	int err = 0;
 	mtrr_type type;
+	unsigned long base;
 	unsigned long size;
 	struct mtrr_sentry sentry;
 	struct mtrr_gentry gentry;
@@ -267,14 +268,14 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 #endif
 		if (gentry.regnum >= num_var_ranges)
 			return -EINVAL;
-		mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+		mtrr_if->get(gentry.regnum, &base, &size, &type);
 
 		/* Hide entries that go above 4GB */
-		if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
+		if (base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
 		    || size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)))
 			gentry.base = gentry.size = gentry.type = 0;
 		else {
-			gentry.base <<= PAGE_SHIFT;
+			gentry.base = base << PAGE_SHIFT;
 			gentry.size = size << PAGE_SHIFT;
 			gentry.type = type;
 		}
@@ -321,11 +322,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 #endif
 		if (gentry.regnum >= num_var_ranges)
 			return -EINVAL;
-		mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+		mtrr_if->get(gentry.regnum, &base, &size, &type);
 		/* Hide entries that would overflow */
 		if (size != (__typeof__(gentry.size))size)
 			gentry.base = gentry.size = gentry.type = 0;
 		else {
+			gentry.base = base;
 			gentry.size = size;
 			gentry.type = type;
 		}
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index fa2900c0e398..bb8e03407e18 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -29,7 +29,6 @@
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
-#include <asm/compat.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
 #include <asm/timer.h>
@@ -1314,6 +1313,11 @@ static void __init pmu_check_apic(void)
 	pr_info("no hardware sampling interrupt available.\n");
 }
 
+static struct attribute_group x86_pmu_format_group = {
+	.name = "format",
+	.attrs = NULL,
+};
+
 static int __init init_hw_perf_events(void)
 {
 	struct x86_pmu_quirk *quirk;
@@ -1388,6 +1392,7 @@ static int __init init_hw_perf_events(void)
 	}
 
 	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
@@ -1616,6 +1621,9 @@ static int x86_pmu_event_idx(struct perf_event *event)
 {
 	int idx = event->hw.idx;
 
+	if (!x86_pmu.attr_rdpmc)
+		return 0;
+
 	if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
 		idx -= X86_PMC_IDX_FIXED;
 		idx |= 1 << 30;
@@ -1668,6 +1676,7 @@ static struct attribute_group x86_pmu_attr_group = {
 
 static const struct attribute_group *x86_pmu_attr_groups[] = {
 	&x86_pmu_attr_group,
+	&x86_pmu_format_group,
 	NULL,
 };
 
@@ -1699,14 +1708,19 @@ static struct pmu pmu = {
 	.flush_branch_stack	= x86_pmu_flush_branch_stack,
 };
 
-void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
+	userpg->cap_usr_time = 0;
+	userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+	userpg->pmc_width = x86_pmu.cntval_bits;
+
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		return;
 
 	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 		return;
 
+	userpg->cap_usr_time = 1;
 	userpg->time_mult = this_cpu_read(cyc2ns);
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
@@ -1748,6 +1762,9 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 }
 
 #ifdef CONFIG_COMPAT
+
+#include <asm/compat.h>
+
 static inline int
 perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8484e77c211e..6638aaf54493 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -339,6 +339,7 @@ struct x86_pmu {
 	 * sysfs attrs
 	 */
 	int		attr_rdpmc;
+	struct attribute **format_attrs;
 
 	/*
 	 * CPU Hotplug hooks
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index dd002faff7a6..95e7fe1c5f0b 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -404,6 +404,21 @@ static void amd_pmu_cpu_dead(int cpu)
 	}
 }
 
+PMU_FORMAT_ATTR(event,	"config:0-7,32-35");
+PMU_FORMAT_ATTR(umask,	"config:8-15"	);
+PMU_FORMAT_ATTR(edge,	"config:18"	);
+PMU_FORMAT_ATTR(inv,	"config:23"	);
+PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
+
+static struct attribute *amd_format_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -426,6 +441,8 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.get_event_constraints	= amd_get_event_constraints,
 	.put_event_constraints	= amd_put_event_constraints,
 
+	.format_attrs		= amd_format_attr,
+
 	.cpu_prepare		= amd_pmu_cpu_prepare,
 	.cpu_starting		= amd_pmu_cpu_starting,
 	.cpu_dead		= amd_pmu_cpu_dead,
@@ -596,6 +613,7 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
 	.cpu_dead		= amd_pmu_cpu_dead,
 #endif
 	.cpu_starting		= amd_pmu_cpu_starting,
+	.format_attrs		= amd_format_attr,
 };
 
 __init int amd_pmu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 6a84e7f28f05..26b3e2fef104 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1431,6 +1431,24 @@ static void core_pmu_enable_all(int added)
 	}
 }
 
+PMU_FORMAT_ATTR(event,	"config:0-7"	);
+PMU_FORMAT_ATTR(umask,	"config:8-15"	);
+PMU_FORMAT_ATTR(edge,	"config:18"	);
+PMU_FORMAT_ATTR(pc,	"config:19"	);
+PMU_FORMAT_ATTR(any,	"config:21"	); /* v3 + */
+PMU_FORMAT_ATTR(inv,	"config:23"	);
+PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
+
+static struct attribute *intel_arch_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_pc.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -1455,6 +1473,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.put_event_constraints	= intel_put_event_constraints,
 	.event_constraints	= intel_core_event_constraints,
 	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
 };
 
 struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1553,6 +1572,21 @@ static void intel_pmu_flush_branch_stack(void)
 		intel_pmu_lbr_reset();
 }
 
+PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
+
+static struct attribute *intel_arch3_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_pc.attr,
+	&format_attr_any.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+
+	&format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
+	NULL,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -1576,6 +1610,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
 
+	.format_attrs		= intel_arch3_formats_attr,
+
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ef484d9d0a25..a2dfacfd7103 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1271,6 +1271,17 @@ done:
 	return num ? -EINVAL : 0;
 }
 
+PMU_FORMAT_ATTR(cccr, "config:0-31" );
+PMU_FORMAT_ATTR(escr, "config:32-62");
+PMU_FORMAT_ATTR(ht,   "config:63"   );
+
+static struct attribute *intel_p4_formats_attr[] = {
+	&format_attr_cccr.attr,
+	&format_attr_escr.attr,
+	&format_attr_ht.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu p4_pmu = {
 	.name			= "Netburst P4/Xeon",
 	.handle_irq		= p4_pmu_handle_irq,
@@ -1305,6 +1316,8 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 * the former idea is taken from OProfile code
 	 */
 	.perfctr_second_write	= 1,
+
+	.format_attrs		= intel_p4_formats_attr,
 };
 
 __init int p4_pmu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index c7181befecde..32bcfc7dd230 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -87,6 +87,23 @@ static void p6_pmu_enable_event(struct perf_event *event)
 	(void)checking_wrmsrl(hwc->config_base, val);
 }
 
+PMU_FORMAT_ATTR(event,	"config:0-7"	);
+PMU_FORMAT_ATTR(umask,	"config:8-15"	);
+PMU_FORMAT_ATTR(edge,	"config:18"	);
+PMU_FORMAT_ATTR(pc,	"config:19"	);
+PMU_FORMAT_ATTR(inv,	"config:23"	);
+PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
+
+static struct attribute *intel_p6_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_pc.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu p6_pmu = {
 	.name			= "p6",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -115,6 +132,8 @@ static __initconst const struct x86_pmu p6_pmu = {
 	.cntval_mask		= (1ULL << 32) - 1,
 	.get_event_constraints	= x86_get_event_constraints,
 	.event_constraints	= p6_event_constraints,
+
+	.format_attrs		= intel_p6_formats_attr,
 };
 
 __init int p6_pmu_init(void)
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index a524353d93f2..39472dd2323f 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -43,7 +43,6 @@
 
 #include <asm/processor.h>
 #include <asm/msr.h>
-#include <asm/system.h>
 
 static struct class *cpuid_class;
 
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 4025fe4f928f..1b81839b6c88 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -37,13 +37,16 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
 			const struct stacktrace_ops *ops,
 			struct thread_info *tinfo, int *graph)
 {
-	struct task_struct *task = tinfo->task;
+	struct task_struct *task;
 	unsigned long ret_addr;
-	int index = task->curr_ret_stack;
+	int index;
 
 	if (addr != (unsigned long)return_to_handler)
 		return;
 
+	task = tinfo->task;
+	index = task->curr_ret_stack;
+
 	if (!task->ret_stack || index < *graph)
 		return;
 
@@ -265,7 +268,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 #endif
 	printk("\n");
 	if (notify_die(DIE_OOPS, str, regs, err,
-			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+			current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
 		return 1;
 
 	show_registers(regs);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 734ebd1d3caa..cdc79b5cfcd9 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -481,7 +481,12 @@ GLOBAL(system_call_after_swapgs)
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	jnz tracesys
 system_call_fastpath:
+#if __SYSCALL_MASK == ~0
 	cmpq $__NR_syscall_max,%rax
+#else
+	andl $__SYSCALL_MASK,%eax
+	cmpl $__NR_syscall_max,%eax
+#endif
 	ja badsys
 	movq %r10,%rcx
 	call *sys_call_table(,%rax,8)  # XXX:	 rip relative
@@ -595,7 +600,12 @@ tracesys:
 	 */
 	LOAD_ARGS ARGOFFSET, 1
 	RESTORE_REST
+#if __SYSCALL_MASK == ~0
 	cmpq $__NR_syscall_max,%rax
+#else
+	andl $__SYSCALL_MASK,%eax
+	cmpl $__NR_syscall_max,%eax
+#endif
 	ja   int_ret_from_sys_call	/* RAX(%rsp) set to -ENOSYS above */
 	movq %r10,%rcx	/* fixup for C */
 	call *sys_call_table(,%rax,8)
@@ -735,6 +745,40 @@ ENTRY(stub_rt_sigreturn)
 	CFI_ENDPROC
 END(stub_rt_sigreturn)
 
+#ifdef CONFIG_X86_X32_ABI
+	PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx
+
+ENTRY(stub_x32_rt_sigreturn)
+	CFI_STARTPROC
+	addq $8, %rsp
+	PARTIAL_FRAME 0
+	SAVE_REST
+	movq %rsp,%rdi
+	FIXUP_TOP_OF_STACK %r11
+	call sys32_x32_rt_sigreturn
+	movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
+	RESTORE_REST
+	jmp int_ret_from_sys_call
+	CFI_ENDPROC
+END(stub_x32_rt_sigreturn)
+
+ENTRY(stub_x32_execve)
+	CFI_STARTPROC
+	addq $8, %rsp
+	PARTIAL_FRAME 0
+	SAVE_REST
+	FIXUP_TOP_OF_STACK %r11
+	movq %rsp, %rcx
+	call sys32_execve
+	RESTORE_TOP_OF_STACK %r11
+	movq %rax,RAX(%rsp)
+	RESTORE_REST
+	jmp int_ret_from_sys_call
+	CFI_ENDPROC
+END(stub_x32_execve)
+
+#endif
+
 /*
  * Build the entry stubs and pointer table with some assembler magic.
  * We pack 7 stubs into a single 32-byte chunk, which will fit in a
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 610485223bdb..36d1853e91af 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -15,7 +15,6 @@
 #include <linux/delay.h>
 
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/timer.h>
 #include <asm/hw_irq.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7943e0c21bde..3dafc6003b7c 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -282,8 +282,13 @@ void fixup_irqs(void)
 		else if (!(warned++))
 			set_affinity = 0;
 
+		/*
+		 * We unmask if the irq was not marked masked by the
+		 * core code. That respects the lazy irq disable
+		 * behaviour.
+		 */
 		if (!irqd_can_move_in_process_context(data) &&
-		    !irqd_irq_disabled(data) && chip->irq_unmask)
+		    !irqd_irq_masked(data) && chip->irq_unmask)
 			chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 43e2b1cff0a7..252981afd6c4 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -16,7 +16,6 @@
 #include <linux/delay.h>
 
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/timer.h>
 #include <asm/hw_irq.h>
 #include <asm/pgtable.h>
@@ -61,7 +60,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id)
 	outb(0, 0xF0);
 	if (ignore_fpu_irq || !boot_cpu_data.hard_math)
 		return IRQ_NONE;
-	math_error(get_irq_regs(), 0, 16);
+	math_error(get_irq_regs(), 0, X86_TRAP_MF);
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 90fcf62854bb..1d5d31ea686b 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -68,16 +68,9 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
 	return count;
 }
 
-static int setup_data_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-
-	return 0;
-}
-
 static const struct file_operations fops_setup_data = {
 	.read		= setup_data_read,
-	.open		= setup_data_open,
+	.open		= simple_open,
 	.llseek		= default_llseek,
 };
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index fdc37b3d0ce3..8bfb6146f753 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -43,10 +43,11 @@
 #include <linux/smp.h>
 #include <linux/nmi.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/uaccess.h>
+#include <linux/memory.h>
 
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
-#include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/nmi.h>
 
@@ -742,6 +743,64 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+	int err;
+	char opc[BREAK_INSTR_SIZE];
+
+	bpt->type = BP_BREAKPOINT;
+	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+				BREAK_INSTR_SIZE);
+	if (err)
+		return err;
+	err = probe_kernel_write((char *)bpt->bpt_addr,
+				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
+#ifdef CONFIG_DEBUG_RODATA
+	if (!err)
+		return err;
+	/*
+	 * It is safe to call text_poke() because normal kernel execution
+	 * is stopped on all cores, so long as the text_mutex is not locked.
+	 */
+	if (mutex_is_locked(&text_mutex))
+		return -EBUSY;
+	text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+		  BREAK_INSTR_SIZE);
+	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+	if (err)
+		return err;
+	if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
+		return -EINVAL;
+	bpt->type = BP_POKE_BREAKPOINT;
+#endif /* CONFIG_DEBUG_RODATA */
+	return err;
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+#ifdef CONFIG_DEBUG_RODATA
+	int err;
+	char opc[BREAK_INSTR_SIZE];
+
+	if (bpt->type != BP_POKE_BREAKPOINT)
+		goto knl_write;
+	/*
+	 * It is safe to call text_poke() because normal kernel execution
+	 * is stopped on all cores, so long as the text_mutex is not locked.
+	 */
+	if (mutex_is_locked(&text_mutex))
+		goto knl_write;
+	text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
+	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+	if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
+		goto knl_write;
+	return err;
+knl_write:
+#endif /* CONFIG_DEBUG_RODATA */
+	return probe_kernel_write((char *)bpt->bpt_addr,
+				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
+}
+
 struct kgdb_arch arch_kgdb_ops = {
 	/* Breakpoint instruction: */
 	.gdb_bpt_instr		= { 0xcc },
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 44842d756b29..f8492da65bfc 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -136,6 +136,15 @@ int kvm_register_clock(char *txt)
 	return ret;
 }
 
+static void kvm_save_sched_clock_state(void)
+{
+}
+
+static void kvm_restore_sched_clock_state(void)
+{
+	kvm_register_clock("primary cpu clock, resume");
+}
+
 #ifdef CONFIG_X86_LOCAL_APIC
 static void __cpuinit kvm_setup_secondary_clock(void)
 {
@@ -144,8 +153,6 @@ static void __cpuinit kvm_setup_secondary_clock(void)
 	 * we shouldn't fail.
 	 */
 	WARN_ON(kvm_register_clock("secondary cpu clock"));
-	/* ok, done with our trickery, call native */
-	setup_secondary_APIC_clock();
 }
 #endif
 
@@ -194,9 +201,11 @@ void __init kvmclock_init(void)
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-	x86_cpuinit.setup_percpu_clockev =
+	x86_cpuinit.early_percpu_clock_init =
 		kvm_setup_secondary_clock;
 #endif
+	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
+	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
 	machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
 	machine_ops.crash_shutdown  = kvm_crash_shutdown;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ea697263b373..ebc987398923 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -15,7 +15,6 @@
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 #include <asm/ldt.h>
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index a3fa43ba5d3b..5b19e4d78b00 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -23,7 +23,6 @@
 #include <asm/apic.h>
 #include <asm/cpufeature.h>
 #include <asm/desc.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 #include <asm/debugreg.h>
 
diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c
index 177183cbb6ae..7eb1e2b97827 100644
--- a/arch/x86/kernel/mca_32.c
+++ b/arch/x86/kernel/mca_32.c
@@ -43,7 +43,6 @@
 #include <linux/mca.h>
 #include <linux/kprobes.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <linux/proc_fs.h>
 #include <linux/mman.h>
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 925179f871de..f21fd94ac897 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -26,7 +26,6 @@
 #include <linux/gfp.h>
 #include <linux/jump_label.h>
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 96356762a51d..eb113693f043 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -40,7 +40,6 @@
 
 #include <asm/processor.h>
 #include <asm/msr.h>
-#include <asm/system.h>
 
 static struct class *msr_class;
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9c57c02e54f6..ab137605e694 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -38,6 +38,7 @@
 #include <asm/apic.h>
 #include <asm/tlbflush.h>
 #include <asm/timer.h>
+#include <asm/special_insns.h>
 
 /* nop stub */
 void _paravirt_nop(void)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 726494b58345..d0b2fb9ccbb1 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -42,7 +42,6 @@
 #include <asm/calgary.h>
 #include <asm/tce.h>
 #include <asm/pci-direct.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/rio.h>
 #include <asm/bios_ebda.h>
@@ -431,7 +430,7 @@ static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr,
 }
 
 static void* calgary_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t flag)
+	dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs)
 {
 	void *ret = NULL;
 	dma_addr_t mapping;
@@ -464,7 +463,8 @@ error:
 }
 
 static void calgary_free_coherent(struct device *dev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle)
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	unsigned int npages;
 	struct iommu_table *tbl = find_iommu_table(dev);
@@ -477,8 +477,8 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 }
 
 static struct dma_map_ops calgary_dma_ops = {
-	.alloc_coherent = calgary_alloc_coherent,
-	.free_coherent = calgary_free_coherent,
+	.alloc = calgary_alloc_coherent,
+	.free = calgary_free_coherent,
 	.map_sg = calgary_map_sg,
 	.unmap_sg = calgary_unmap_sg,
 	.map_page = calgary_map_page,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 28e5e06fcba4..3003250ac51d 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -96,7 +96,8 @@ void __init pci_iommu_alloc(void)
 	}
 }
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_addr, gfp_t flag)
+				 dma_addr_t *dma_addr, gfp_t flag,
+				 struct dma_attrs *attrs)
 {
 	unsigned long dma_mask;
 	struct page *page;
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 3af4af810c07..f96050685b46 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -75,7 +75,7 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 }
 
 static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
-				dma_addr_t dma_addr)
+				dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
 	free_pages((unsigned long)vaddr, get_order(size));
 }
@@ -96,8 +96,8 @@ static void nommu_sync_sg_for_device(struct device *dev,
 }
 
 struct dma_map_ops nommu_dma_ops = {
-	.alloc_coherent		= dma_generic_alloc_coherent,
-	.free_coherent		= nommu_free_coherent,
+	.alloc			= dma_generic_alloc_coherent,
+	.free			= nommu_free_coherent,
 	.map_sg			= nommu_map_sg,
 	.map_page		= nommu_map_page,
 	.sync_single_for_device = nommu_sync_single_for_device,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 8f972cbddef0..6c483ba98b9c 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -15,21 +15,30 @@
 int swiotlb __read_mostly;
 
 static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-					dma_addr_t *dma_handle, gfp_t flags)
+					dma_addr_t *dma_handle, gfp_t flags,
+					struct dma_attrs *attrs)
 {
 	void *vaddr;
 
-	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags);
+	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
+					   attrs);
 	if (vaddr)
 		return vaddr;
 
 	return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
 }
 
+static void x86_swiotlb_free_coherent(struct device *dev, size_t size,
+				      void *vaddr, dma_addr_t dma_addr,
+				      struct dma_attrs *attrs)
+{
+	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
+
 static struct dma_map_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
-	.alloc_coherent = x86_swiotlb_alloc_coherent,
-	.free_coherent = swiotlb_free_coherent,
+	.alloc = x86_swiotlb_alloc_coherent,
+	.free = x86_swiotlb_free_coherent,
 	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 14baf78d5a1f..1d92a5ab6e8b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -12,10 +12,12 @@
 #include <linux/user-return-notifier.h>
 #include <linux/dmi.h>
 #include <linux/utsname.h>
+#include <linux/stackprotector.h>
+#include <linux/tick.h>
+#include <linux/cpuidle.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
 #include <asm/cpu.h>
-#include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/syscalls.h>
 #include <asm/idle.h>
@@ -23,6 +25,24 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/debugreg.h>
+#include <asm/nmi.h>
+
+#ifdef CONFIG_X86_64
+static DEFINE_PER_CPU(unsigned char, is_idle);
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+	atomic_notifier_chain_register(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+	atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
+#endif
 
 struct kmem_cache *task_xstate_cachep;
 EXPORT_SYMBOL_GPL(task_xstate_cachep);
@@ -342,36 +362,105 @@ void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
 #endif
 
-#ifdef CONFIG_X86_32
-/*
- * This halt magic was a workaround for ancient floppy DMA
- * wreckage. It should be safe to remove.
- */
-static int hlt_counter;
-void disable_hlt(void)
+static inline int hlt_use_halt(void)
 {
-	hlt_counter++;
+	return 1;
 }
-EXPORT_SYMBOL(disable_hlt);
 
-void enable_hlt(void)
+#ifndef CONFIG_SMP
+static inline void play_dead(void)
 {
-	hlt_counter--;
+	BUG();
 }
-EXPORT_SYMBOL(enable_hlt);
+#endif
 
-static inline int hlt_use_halt(void)
+#ifdef CONFIG_X86_64
+void enter_idle(void)
 {
-	return (!hlt_counter && boot_cpu_data.hlt_works_ok);
+	percpu_write(is_idle, 1);
+	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
 }
-#else
-static inline int hlt_use_halt(void)
+
+static void __exit_idle(void)
 {
-	return 1;
+	if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
+		return;
+	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
+}
+
+/* Called from interrupts to signify idle end */
+void exit_idle(void)
+{
+	/* idle loop has pid 0 */
+	if (current->pid)
+		return;
+	__exit_idle();
 }
 #endif
 
 /*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+ * low exit latency (ie sit in a loop waiting for
+ * somebody to say that they'd like to reschedule)
+ */
+void cpu_idle(void)
+{
+	/*
+	 * If we're the non-boot CPU, nothing set the stack canary up
+	 * for us.  CPU0 already has it initialized but no harm in
+	 * doing it again.  This is a good place for updating it, as
+	 * we wont ever return from this function (so the invalid
+	 * canaries already on the stack wont ever trigger).
+	 */
+	boot_init_stack_canary();
+	current_thread_info()->status |= TS_POLLING;
+
+	while (1) {
+		tick_nohz_idle_enter();
+
+		while (!need_resched()) {
+			rmb();
+
+			if (cpu_is_offline(smp_processor_id()))
+				play_dead();
+
+			/*
+			 * Idle routines should keep interrupts disabled
+			 * from here on, until they go to idle.
+			 * Otherwise, idle callbacks can misfire.
+			 */
+			local_touch_nmi();
+			local_irq_disable();
+
+			enter_idle();
+
+			/* Don't trace irqs off for idle */
+			stop_critical_timings();
+
+			/* enter_idle() needs rcu for notifiers */
+			rcu_idle_enter();
+
+			if (cpuidle_idle_call())
+				pm_idle();
+
+			rcu_idle_exit();
+			start_critical_timings();
+
+			/* In many cases the interrupt that ended idle
+			   has already called exit_idle. But some idle
+			   loops can be woken up without interrupt. */
+			__exit_idle();
+		}
+
+		tick_nohz_idle_exit();
+		preempt_enable_no_resched();
+		schedule();
+		preempt_disable();
+	}
+}
+
+/*
  * We use this if we don't have any better
  * idle routine..
  */
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 9d7d4842bfaf..ae6847303e26 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -9,7 +9,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -31,17 +30,14 @@
 #include <linux/kallsyms.h>
 #include <linux/ptrace.h>
 #include <linux/personality.h>
-#include <linux/tick.h>
 #include <linux/percpu.h>
 #include <linux/prctl.h>
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/kdebug.h>
-#include <linux/cpuidle.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
@@ -58,7 +54,7 @@
 #include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
-#include <asm/nmi.h>
+#include <asm/switch_to.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
@@ -70,60 +66,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return ((unsigned long *)tsk->thread.sp)[3];
 }
 
-#ifndef CONFIG_SMP
-static inline void play_dead(void)
-{
-	BUG();
-}
-#endif
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * If we're the non-boot CPU, nothing set the stack canary up
-	 * for us.  CPU0 already has it initialized but no harm in
-	 * doing it again.  This is a good place for updating it, as
-	 * we wont ever return from this function (so the invalid
-	 * canaries already on the stack wont ever trigger).
-	 */
-	boot_init_stack_canary();
-
-	current_thread_info()->status |= TS_POLLING;
-
-	/* endless idle loop with no priority at all */
-	while (1) {
-		tick_nohz_idle_enter();
-		rcu_idle_enter();
-		while (!need_resched()) {
-
-			check_pgt_cache();
-			rmb();
-
-			if (cpu_is_offline(cpu))
-				play_dead();
-
-			local_touch_nmi();
-			local_irq_disable();
-			/* Don't trace irqs off for idle */
-			stop_critical_timings();
-			if (cpuidle_idle_call())
-				pm_idle();
-			start_critical_timings();
-		}
-		rcu_idle_exit();
-		tick_nohz_idle_exit();
-		schedule_preempt_disabled();
-	}
-}
-
 void __show_regs(struct pt_regs *regs, int all)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 292da13fc5aa..733ca39f367e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -14,7 +14,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -32,15 +31,12 @@
 #include <linux/notifier.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
-#include <linux/tick.h>
 #include <linux/prctl.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/ftrace.h>
-#include <linux/cpuidle.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
@@ -52,114 +48,11 @@
 #include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
-#include <asm/nmi.h>
+#include <asm/switch_to.h>
 
 asmlinkage extern void ret_from_fork(void);
 
 DEFINE_PER_CPU(unsigned long, old_rsp);
-static DEFINE_PER_CPU(unsigned char, is_idle);
-
-static ATOMIC_NOTIFIER_HEAD(idle_notifier);
-
-void idle_notifier_register(struct notifier_block *n)
-{
-	atomic_notifier_chain_register(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_register);
-
-void idle_notifier_unregister(struct notifier_block *n)
-{
-	atomic_notifier_chain_unregister(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_unregister);
-
-void enter_idle(void)
-{
-	percpu_write(is_idle, 1);
-	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
-}
-
-static void __exit_idle(void)
-{
-	if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
-		return;
-	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
-}
-
-/* Called from interrupts to signify idle end */
-void exit_idle(void)
-{
-	/* idle loop has pid 0 */
-	if (current->pid)
-		return;
-	__exit_idle();
-}
-
-#ifndef CONFIG_SMP
-static inline void play_dead(void)
-{
-	BUG();
-}
-#endif
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
-	current_thread_info()->status |= TS_POLLING;
-
-	/*
-	 * If we're the non-boot CPU, nothing set the stack canary up
-	 * for us.  CPU0 already has it initialized but no harm in
-	 * doing it again.  This is a good place for updating it, as
-	 * we wont ever return from this function (so the invalid
-	 * canaries already on the stack wont ever trigger).
-	 */
-	boot_init_stack_canary();
-
-	/* endless idle loop with no priority at all */
-	while (1) {
-		tick_nohz_idle_enter();
-		while (!need_resched()) {
-
-			rmb();
-
-			if (cpu_is_offline(smp_processor_id()))
-				play_dead();
-			/*
-			 * Idle routines should keep interrupts disabled
-			 * from here on, until they go to idle.
-			 * Otherwise, idle callbacks can misfire.
-			 */
-			local_touch_nmi();
-			local_irq_disable();
-			enter_idle();
-			/* Don't trace irqs off for idle */
-			stop_critical_timings();
-
-			/* enter_idle() needs rcu for notifiers */
-			rcu_idle_enter();
-
-			if (cpuidle_idle_call())
-				pm_idle();
-
-			rcu_idle_exit();
-			start_critical_timings();
-
-			/* In many cases the interrupt that ended idle
-			   has already called exit_idle. But some idle
-			   loops can be woken up without interrupt. */
-			__exit_idle();
-		}
-
-		tick_nohz_idle_exit();
-		schedule_preempt_disabled();
-	}
-}
 
 /* Prints also some state that isn't saved in the pt_regs */
 void __show_regs(struct pt_regs *regs, int all)
@@ -365,7 +258,9 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
 {
 	start_thread_common(regs, new_ip, new_sp,
-			    __USER32_CS, __USER32_DS, __USER32_DS);
+			    test_thread_flag(TIF_X32)
+			    ? __USER_CS : __USER32_CS,
+			    __USER_DS, __USER_DS);
 }
 #endif
 
@@ -488,6 +383,8 @@ void set_personality_64bit(void)
 
 	/* Make sure to be in 64bit mode */
 	clear_thread_flag(TIF_IA32);
+	clear_thread_flag(TIF_ADDR32);
+	clear_thread_flag(TIF_X32);
 
 	/* Ensure the corresponding mm is not marked. */
 	if (current->mm)
@@ -500,20 +397,31 @@ void set_personality_64bit(void)
 	current->personality &= ~READ_IMPLIES_EXEC;
 }
 
-void set_personality_ia32(void)
+void set_personality_ia32(bool x32)
 {
 	/* inherit personality from parent */
 
 	/* Make sure to be in 32bit mode */
-	set_thread_flag(TIF_IA32);
-	current->personality |= force_personality32;
+	set_thread_flag(TIF_ADDR32);
 
 	/* Mark the associated mm as containing 32-bit tasks. */
 	if (current->mm)
 		current->mm->context.ia32_compat = 1;
 
-	/* Prepare the first "return" to user space */
-	current_thread_info()->status |= TS_COMPAT;
+	if (x32) {
+		clear_thread_flag(TIF_IA32);
+		set_thread_flag(TIF_X32);
+		current->personality &= ~READ_IMPLIES_EXEC;
+		/* is_compat_task() uses the presence of the x32
+		   syscall bit flag to determine compat status */
+		current_thread_info()->status &= ~TS_COMPAT;
+	} else {
+		set_thread_flag(TIF_IA32);
+		clear_thread_flag(TIF_X32);
+		current->personality |= force_personality32;
+		/* Prepare the first "return" to user space */
+		current_thread_info()->status |= TS_COMPAT;
+	}
 }
 
 unsigned long get_wchan(struct task_struct *p)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 78f05e438be5..685845cf16e0 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -24,7 +24,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
@@ -34,6 +33,7 @@
 #include <asm/prctl.h>
 #include <asm/proto.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/traps.h>
 
 #include "tls.h"
 
@@ -1131,6 +1131,100 @@ static int genregs32_set(struct task_struct *target,
 	return ret;
 }
 
+#ifdef CONFIG_X86_X32_ABI
+static long x32_arch_ptrace(struct task_struct *child,
+			    compat_long_t request, compat_ulong_t caddr,
+			    compat_ulong_t cdata)
+{
+	unsigned long addr = caddr;
+	unsigned long data = cdata;
+	void __user *datap = compat_ptr(data);
+	int ret;
+
+	switch (request) {
+	/* Read 32bits at location addr in the USER area.  Only allow
+	   to return the lower 32bits of segment and debug registers.  */
+	case PTRACE_PEEKUSR: {
+		u32 tmp;
+
+		ret = -EIO;
+		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+		    addr < offsetof(struct user_regs_struct, cs))
+			break;
+
+		tmp = 0;  /* Default return condition */
+		if (addr < sizeof(struct user_regs_struct))
+			tmp = getreg(child, addr);
+		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+			 addr <= offsetof(struct user, u_debugreg[7])) {
+			addr -= offsetof(struct user, u_debugreg[0]);
+			tmp = ptrace_get_debugreg(child, addr / sizeof(data));
+		}
+		ret = put_user(tmp, (__u32 __user *)datap);
+		break;
+	}
+
+	/* Write the word at location addr in the USER area.  Only allow
+	   to update segment and debug registers with the upper 32bits
+	   zero-extended. */
+	case PTRACE_POKEUSR:
+		ret = -EIO;
+		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+		    addr < offsetof(struct user_regs_struct, cs))
+			break;
+
+		if (addr < sizeof(struct user_regs_struct))
+			ret = putreg(child, addr, data);
+		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+			 addr <= offsetof(struct user, u_debugreg[7])) {
+			addr -= offsetof(struct user, u_debugreg[0]);
+			ret = ptrace_set_debugreg(child,
+						  addr / sizeof(data), data);
+		}
+		break;
+
+	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
+		return copy_regset_to_user(child,
+					   task_user_regset_view(current),
+					   REGSET_GENERAL,
+					   0, sizeof(struct user_regs_struct),
+					   datap);
+
+	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
+		return copy_regset_from_user(child,
+					     task_user_regset_view(current),
+					     REGSET_GENERAL,
+					     0, sizeof(struct user_regs_struct),
+					     datap);
+
+	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
+		return copy_regset_to_user(child,
+					   task_user_regset_view(current),
+					   REGSET_FP,
+					   0, sizeof(struct user_i387_struct),
+					   datap);
+
+	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
+		return copy_regset_from_user(child,
+					     task_user_regset_view(current),
+					     REGSET_FP,
+					     0, sizeof(struct user_i387_struct),
+					     datap);
+
+		/* normal 64bit interface to access TLS data.
+		   Works just like arch_prctl, except that the arguments
+		   are reversed. */
+	case PTRACE_ARCH_PRCTL:
+		return do_arch_prctl(child, data, addr);
+
+	default:
+		return compat_ptrace_request(child, request, addr, data);
+	}
+
+	return ret;
+}
+#endif
+
 long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			compat_ulong_t caddr, compat_ulong_t cdata)
 {
@@ -1140,6 +1234,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 	int ret;
 	__u32 val;
 
+#ifdef CONFIG_X86_X32_ABI
+	if (!is_ia32_task())
+		return x32_arch_ptrace(child, request, caddr, cdata);
+#endif
+
 	switch (request) {
 	case PTRACE_PEEKUSR:
 		ret = getreg32(child, addr, &val);
@@ -1327,7 +1426,7 @@ static void fill_sigtrap_info(struct task_struct *tsk,
 				int error_code, int si_code,
 				struct siginfo *info)
 {
-	tsk->thread.trap_no = 1;
+	tsk->thread.trap_nr = X86_TRAP_DB;
 	tsk->thread.error_code = error_code;
 
 	memset(info, 0, sizeof(*info));
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 88638883176a..1a2901562059 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -90,7 +90,6 @@
 #include <asm/processor.h>
 #include <asm/bugs.h>
 
-#include <asm/system.h>
 #include <asm/vsyscall.h>
 #include <asm/cpu.h>
 #include <asm/desc.h>
@@ -509,15 +508,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 
 #ifdef CONFIG_KEXEC
 
-static inline unsigned long long get_total_mem(void)
-{
-	unsigned long long total;
-
-	total = max_pfn - min_low_pfn;
-
-	return total << PAGE_SHIFT;
-}
-
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
@@ -536,7 +526,7 @@ static void __init reserve_crashkernel(void)
 	unsigned long long crash_size, crash_base;
 	int ret;
 
-	total_mem = get_total_mem();
+	total_mem = memblock_phys_mem_size();
 
 	ret = parse_crashkernel(boot_command_line, total_mem,
 			&crash_size, &crash_base);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 25edcfc9ba5b..115eac431483 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -10,10 +10,8 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
-#include <linux/signal.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
-#include <linux/ptrace.h>
 #include <linux/tracehook.h>
 #include <linux/unistd.h>
 #include <linux/stddef.h>
@@ -27,10 +25,12 @@
 #include <asm/fpu-internal.h>
 #include <asm/vdso.h>
 #include <asm/mce.h>
+#include <asm/sighandling.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/proto.h>
 #include <asm/ia32_unistd.h>
+#include <asm/sys_ia32.h>
 #endif /* CONFIG_X86_64 */
 
 #include <asm/syscall.h>
@@ -38,13 +38,6 @@
 
 #include <asm/sigframe.h>
 
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
-#define __FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
-			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
-			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
-			 X86_EFLAGS_CF)
-
 #ifdef CONFIG_X86_32
 # define FIX_EFLAGS	(__FIX_EFLAGS | X86_EFLAGS_RF)
 #else
@@ -69,9 +62,8 @@
 	regs->seg = GET_SEG(seg) | 3;			\
 } while (0)
 
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
-		   unsigned long *pax)
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
+		       unsigned long *pax)
 {
 	void __user *buf;
 	unsigned int tmpflags;
@@ -126,9 +118,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	return err;
 }
 
-static int
-setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
-		 struct pt_regs *regs, unsigned long mask)
+int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+		     struct pt_regs *regs, unsigned long mask)
 {
 	int err = 0;
 
@@ -160,7 +151,7 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 		put_user_ex(regs->r15, &sc->r15);
 #endif /* CONFIG_X86_64 */
 
-		put_user_ex(current->thread.trap_no, &sc->trapno);
+		put_user_ex(current->thread.trap_nr, &sc->trapno);
 		put_user_ex(current->thread.error_code, &sc->err);
 		put_user_ex(regs->ip, &sc->ip);
 #ifdef CONFIG_X86_32
@@ -643,6 +634,16 @@ static int signr_convert(int sig)
 #define is_ia32	0
 #endif /* CONFIG_IA32_EMULATION */
 
+#ifdef CONFIG_X86_X32_ABI
+#define is_x32	test_thread_flag(TIF_X32)
+
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+			      siginfo_t *info, compat_sigset_t *set,
+			      struct pt_regs *regs);
+#else /* !CONFIG_X86_X32_ABI */
+#define is_x32	0
+#endif /* CONFIG_X86_X32_ABI */
+
 int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		sigset_t *set, struct pt_regs *regs);
 int ia32_setup_frame(int sig, struct k_sigaction *ka,
@@ -667,8 +668,14 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 			ret = ia32_setup_rt_frame(usig, ka, info, set, regs);
 		else
 			ret = ia32_setup_frame(usig, ka, set, regs);
-	} else
+#ifdef CONFIG_X86_X32_ABI
+	} else if (is_x32) {
+		ret = x32_setup_rt_frame(usig, ka, info,
+					 (compat_sigset_t *)set, regs);
+#endif
+	} else {
 		ret = __setup_rt_frame(sig, ka, info, set, regs);
+	}
 
 	if (ret) {
 		force_sigsegv(sig, current);
@@ -851,3 +858,102 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 
 	force_sig(SIGSEGV, me);
 }
+
+#ifdef CONFIG_X86_X32_ABI
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+			      siginfo_t *info, compat_sigset_t *set,
+			      struct pt_regs *regs)
+{
+	struct rt_sigframe_x32 __user *frame;
+	void __user *restorer;
+	int err = 0;
+	void __user *fpstate = NULL;
+
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+		return -EFAULT;
+
+	if (ka->sa.sa_flags & SA_SIGINFO) {
+		if (copy_siginfo_to_user32(&frame->info, info))
+			return -EFAULT;
+	}
+
+	put_user_try {
+		/* Create the ucontext.  */
+		if (cpu_has_xsave)
+			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+		else
+			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(0, &frame->uc.uc_link);
+		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+		put_user_ex(sas_ss_flags(regs->sp),
+			    &frame->uc.uc_stack.ss_flags);
+		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		put_user_ex(0, &frame->uc.uc__pad0);
+		err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+					regs, set->sig[0]);
+		err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+		if (ka->sa.sa_flags & SA_RESTORER) {
+			restorer = ka->sa.sa_restorer;
+		} else {
+			/* could use a vstub here */
+			restorer = NULL;
+			err |= -EFAULT;
+		}
+		put_user_ex(restorer, &frame->pretcode);
+	} put_user_catch(err);
+
+	if (err)
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	regs->sp = (unsigned long) frame;
+	regs->ip = (unsigned long) ka->sa.sa_handler;
+
+	/* We use the x32 calling convention here... */
+	regs->di = sig;
+	regs->si = (unsigned long) &frame->info;
+	regs->dx = (unsigned long) &frame->uc;
+
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+
+	regs->cs = __USER_CS;
+	regs->ss = __USER_DS;
+
+	return 0;
+}
+
+asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
+{
+	struct rt_sigframe_x32 __user *frame;
+	sigset_t set;
+	unsigned long ax;
+	struct pt_regs tregs;
+
+	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
+
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	sigdelsetmask(&set, ~_BLOCKABLE);
+	set_current_blocked(&set);
+
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+		goto badframe;
+
+	tregs = *regs;
+	if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
+		goto badframe;
+
+	return ax;
+
+badframe:
+	signal_fault(regs, frame, "x32 rt_sigreturn");
+	return 0;
+}
+#endif
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e578a79a3093..6e1e406038c2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -50,6 +50,7 @@
 #include <linux/tboot.h>
 #include <linux/stackprotector.h>
 #include <linux/gfp.h>
+#include <linux/cpuidle.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -219,14 +220,9 @@ static void __cpuinit smp_callin(void)
 	 * Update loops_per_jiffy in cpu_data. Previous call to
 	 * smp_store_cpu_info() stored a value that is close but not as
 	 * accurate as the value just calculated.
-	 *
-	 * Need to enable IRQs because it can take longer and then
-	 * the NMI watchdog might kill us.
 	 */
-	local_irq_enable();
 	calibrate_delay();
 	cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
-	local_irq_disable();
 	pr_debug("Stack at about %p\n", &cpuid);
 
 	/*
@@ -255,6 +251,7 @@ notrace static void __cpuinit start_secondary(void *unused)
 	 * most necessary things.
 	 */
 	cpu_init();
+	x86_cpuinit.early_percpu_clock_init();
 	preempt_disable();
 	smp_callin();
 
@@ -1408,7 +1405,8 @@ void native_play_dead(void)
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
 	mwait_play_dead();	/* Only returns on failure */
-	hlt_play_dead();
+	if (cpuidle_play_dead())
+		hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index ef59642ff1bf..b4d3c3927dd8 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -98,7 +98,7 @@ out:
 static void find_start_end(unsigned long flags, unsigned long *begin,
 			   unsigned long *end)
 {
-	if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) {
+	if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) {
 		unsigned long new_begin;
 		/* This is usually used needed to map code in small
 		   model, so it needs to be in the first 31bit. Limit
@@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
-	if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32))
+	if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32))
 	    && len <= mm->cached_hole_size) {
 		mm->cached_hole_size = 0;
 		mm->free_area_cache = begin;
@@ -205,7 +205,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		return addr;
 
 	/* for MAP_32BIT mappings we force the legact mmap base */
-	if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT))
+	if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT))
 		goto bottomup;
 
 	/* requesting a specific address */
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index 7ac7943be02c..5c7f8c20da74 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -5,6 +5,14 @@
 #include <linux/cache.h>
 #include <asm/asm-offsets.h>
 
+#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
+
 #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index e2410e27f97e..6410744ac5cb 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -272,7 +272,7 @@ static void tboot_copy_fadt(const struct acpi_table_fadt *fadt)
 		offsetof(struct acpi_table_facs, firmware_waking_vector);
 }
 
-void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
+static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
 {
 	static u32 acpi_shutdown_map[ACPI_S_STATE_COUNT] = {
 		/* S0,1,2: */ -1, -1, -1,
@@ -281,7 +281,7 @@ void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
 		/* S5: */ TB_SHUTDOWN_S5 };
 
 	if (!tboot_enabled())
-		return;
+		return 0;
 
 	tboot_copy_fadt(&acpi_gbl_FADT);
 	tboot->acpi_sinfo.pm1a_cnt_val = pm1a_control;
@@ -292,10 +292,11 @@ void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
 	if (sleep_state >= ACPI_S_STATE_COUNT ||
 	    acpi_shutdown_map[sleep_state] == -1) {
 		pr_warning("unsupported sleep state 0x%x\n", sleep_state);
-		return;
+		return -1;
 	}
 
 	tboot_shutdown(acpi_shutdown_map[sleep_state]);
+	return 0;
 }
 
 static atomic_t ap_wfs_count;
@@ -345,6 +346,8 @@ static __init int tboot_late_init(void)
 
 	atomic_set(&ap_wfs_count, 0);
 	register_hotcpu_notifier(&tboot_cpu_notifier);
+
+	acpi_os_set_prepare_sleep(&tboot_sleep);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c
index 9e540fee7009..ab40954e113e 100644
--- a/arch/x86/kernel/tce_64.c
+++ b/arch/x86/kernel/tce_64.c
@@ -34,6 +34,7 @@
 #include <asm/tce.h>
 #include <asm/calgary.h>
 #include <asm/proto.h>
+#include <asm/cacheflush.h>
 
 /* flush a tce at 'tceaddr' to main memory */
 static inline void flush_tce(void* tceaddr)
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 6bb7b8579e70..9d9d2f9e77a5 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -6,7 +6,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/desc.h>
-#include <asm/system.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/proto.h>
@@ -163,7 +162,7 @@ int regset_tls_get(struct task_struct *target, const struct user_regset *regset,
 {
 	const struct desc_struct *tls;
 
-	if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
 	    (count % sizeof(struct user_desc)) != 0)
 		return -EINVAL;
@@ -198,7 +197,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 	struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
 	const struct user_desc *info;
 
-	if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
 	    (count % sizeof(struct user_desc)) != 0)
 		return -EINVAL;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ec61d4c1b93b..ff9281f16029 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -50,7 +50,6 @@
 #include <asm/processor.h>
 #include <asm/debugreg.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
@@ -120,7 +119,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 		 * traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
 		 * On nmi (interrupt 2), do_trap should not be called.
 		 */
-		if (trapnr < 6)
+		if (trapnr < X86_TRAP_UD)
 			goto vm86_trap;
 		goto trap_signal;
 	}
@@ -133,7 +132,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 trap_signal:
 #endif
 	/*
-	 * We want error_code and trap_no set for userspace faults and
+	 * We want error_code and trap_nr set for userspace faults and
 	 * kernelspace faults which result in die(), but not
 	 * kernelspace faults which are fixed up.  die() gives the
 	 * process no chance to handle the signal and notice the
@@ -142,7 +141,7 @@ trap_signal:
 	 * delivered, faults.  See also do_general_protection below.
 	 */
 	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = trapnr;
+	tsk->thread.trap_nr = trapnr;
 
 #ifdef CONFIG_X86_64
 	if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
@@ -165,7 +164,7 @@ trap_signal:
 kernel_trap:
 	if (!fixup_exception(regs)) {
 		tsk->thread.error_code = error_code;
-		tsk->thread.trap_no = trapnr;
+		tsk->thread.trap_nr = trapnr;
 		die(str, regs, error_code);
 	}
 	return;
@@ -204,27 +203,31 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 	do_trap(trapnr, signr, str, regs, error_code, &info);		\
 }
 
-DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip)
-DO_ERROR(4, SIGSEGV, "overflow", overflow)
-DO_ERROR(5, SIGSEGV, "bounds", bounds)
-DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip)
-DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
-DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
-DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
+		regs->ip)
+DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
+DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN,
+		regs->ip)
+DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",
+		coprocessor_segment_overrun)
+DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
 #ifdef CONFIG_X86_32
-DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
 #endif
-DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
+		BUS_ADRALN, 0)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
 {
 	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-			12, SIGBUS) == NOTIFY_STOP)
+			X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
 		return;
 	preempt_conditional_sti(regs);
-	do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL);
+	do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
 	preempt_conditional_cli(regs);
 }
 
@@ -234,10 +237,10 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 	struct task_struct *tsk = current;
 
 	/* Return not checked because double check cannot be ignored */
-	notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV);
+	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
 	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = 8;
+	tsk->thread.trap_nr = X86_TRAP_DF;
 
 	/*
 	 * This is always a kernel trap and never fixable (and thus must
@@ -265,7 +268,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 		goto gp_in_kernel;
 
 	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = 13;
+	tsk->thread.trap_nr = X86_TRAP_GP;
 
 	if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
 			printk_ratelimit()) {
@@ -292,9 +295,9 @@ gp_in_kernel:
 		return;
 
 	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = 13;
-	if (notify_die(DIE_GPF, "general protection fault", regs,
-				error_code, 13, SIGSEGV) == NOTIFY_STOP)
+	tsk->thread.trap_nr = X86_TRAP_GP;
+	if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+			X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
 		return;
 	die("general protection fault", regs, error_code);
 }
@@ -303,13 +306,13 @@ gp_in_kernel:
 dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
-	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
-			== NOTIFY_STOP)
+	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
+				SIGTRAP) == NOTIFY_STOP)
 		return;
 #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 
-	if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
-			== NOTIFY_STOP)
+	if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
+			SIGTRAP) == NOTIFY_STOP)
 		return;
 
 	/*
@@ -318,7 +321,7 @@ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
 	 */
 	debug_stack_usage_inc();
 	preempt_conditional_sti(regs);
-	do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
+	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
 }
@@ -423,8 +426,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	preempt_conditional_sti(regs);
 
 	if (regs->flags & X86_VM_MASK) {
-		handle_vm86_trap((struct kernel_vm86_regs *) regs,
-				error_code, 1);
+		handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
+					X86_TRAP_DB);
 		preempt_conditional_cli(regs);
 		debug_stack_usage_dec();
 		return;
@@ -461,7 +464,8 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	struct task_struct *task = current;
 	siginfo_t info;
 	unsigned short err;
-	char *str = (trapnr == 16) ? "fpu exception" : "simd exception";
+	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
+						"simd exception";
 
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
 		return;
@@ -471,7 +475,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	{
 		if (!fixup_exception(regs)) {
 			task->thread.error_code = error_code;
-			task->thread.trap_no = trapnr;
+			task->thread.trap_nr = trapnr;
 			die(str, regs, error_code);
 		}
 		return;
@@ -481,12 +485,12 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	 * Save the info for the exception handler and clear the error.
 	 */
 	save_init_fpu(task);
-	task->thread.trap_no = trapnr;
+	task->thread.trap_nr = trapnr;
 	task->thread.error_code = error_code;
 	info.si_signo = SIGFPE;
 	info.si_errno = 0;
 	info.si_addr = (void __user *)regs->ip;
-	if (trapnr == 16) {
+	if (trapnr == X86_TRAP_MF) {
 		unsigned short cwd, swd;
 		/*
 		 * (~cwd & swd) will mask out exceptions that are not set to unmasked
@@ -530,10 +534,11 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
 		info.si_code = FPE_FLTRES;
 	} else {
 		/*
-		 * If we're using IRQ 13, or supposedly even some trap 16
-		 * implementations, it's possible we get a spurious trap...
+		 * If we're using IRQ 13, or supposedly even some trap
+		 * X86_TRAP_MF implementations, it's possible
+		 * we get a spurious trap, which is not an error.
 		 */
-		return;		/* Spurious trap, no error */
+		return;
 	}
 	force_sig_info(SIGFPE, &info, task);
 }
@@ -544,13 +549,13 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
 	ignore_fpu_irq = 1;
 #endif
 
-	math_error(regs, error_code, 16);
+	math_error(regs, error_code, X86_TRAP_MF);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-	math_error(regs, error_code, 19);
+	math_error(regs, error_code, X86_TRAP_XF);
 }
 
 dotraplinkage void
@@ -644,20 +649,21 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 	info.si_errno = 0;
 	info.si_code = ILL_BADSTK;
 	info.si_addr = NULL;
-	if (notify_die(DIE_TRAP, "iret exception",
-			regs, error_code, 32, SIGILL) == NOTIFY_STOP)
+	if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
+			X86_TRAP_IRET, SIGILL) == NOTIFY_STOP)
 		return;
-	do_trap(32, SIGILL, "iret exception", regs, error_code, &info);
+	do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
+		&info);
 }
 #endif
 
 /* Set of traps needed for early debugging. */
 void __init early_trap_init(void)
 {
-	set_intr_gate_ist(1, &debug, DEBUG_STACK);
+	set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
 	/* int3 can be called from all */
-	set_system_intr_gate_ist(3, &int3, DEBUG_STACK);
-	set_intr_gate(14, &page_fault);
+	set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+	set_intr_gate(X86_TRAP_PF, &page_fault);
 	load_idt(&idt_descr);
 }
 
@@ -673,30 +679,30 @@ void __init trap_init(void)
 	early_iounmap(p, 4);
 #endif
 
-	set_intr_gate(0, &divide_error);
-	set_intr_gate_ist(2, &nmi, NMI_STACK);
+	set_intr_gate(X86_TRAP_DE, &divide_error);
+	set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK);
 	/* int4 can be called from all */
-	set_system_intr_gate(4, &overflow);
-	set_intr_gate(5, &bounds);
-	set_intr_gate(6, &invalid_op);
-	set_intr_gate(7, &device_not_available);
+	set_system_intr_gate(X86_TRAP_OF, &overflow);
+	set_intr_gate(X86_TRAP_BR, &bounds);
+	set_intr_gate(X86_TRAP_UD, &invalid_op);
+	set_intr_gate(X86_TRAP_NM, &device_not_available);
 #ifdef CONFIG_X86_32
-	set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS);
+	set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS);
 #else
-	set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK);
+	set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK);
 #endif
-	set_intr_gate(9, &coprocessor_segment_overrun);
-	set_intr_gate(10, &invalid_TSS);
-	set_intr_gate(11, &segment_not_present);
-	set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK);
-	set_intr_gate(13, &general_protection);
-	set_intr_gate(15, &spurious_interrupt_bug);
-	set_intr_gate(16, &coprocessor_error);
-	set_intr_gate(17, &alignment_check);
+	set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun);
+	set_intr_gate(X86_TRAP_TS, &invalid_TSS);
+	set_intr_gate(X86_TRAP_NP, &segment_not_present);
+	set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+	set_intr_gate(X86_TRAP_GP, &general_protection);
+	set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug);
+	set_intr_gate(X86_TRAP_MF, &coprocessor_error);
+	set_intr_gate(X86_TRAP_AC, &alignment_check);
 #ifdef CONFIG_X86_MCE
-	set_intr_gate_ist(18, &machine_check, MCE_STACK);
+	set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK);
 #endif
-	set_intr_gate(19, &simd_coprocessor_error);
+	set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error);
 
 	/* Reserve all the builtin and the syscall vector: */
 	for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
@@ -721,7 +727,7 @@ void __init trap_init(void)
 
 #ifdef CONFIG_X86_64
 	memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16);
-	set_nmi_gate(1, &debug);
-	set_nmi_gate(3, &int3);
+	set_nmi_gate(X86_TRAP_DB, &debug);
+	set_nmi_gate(X86_TRAP_BP, &int3);
 #endif
 }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 183c5925a9fe..fc0a147e3727 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -630,7 +630,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 
 static unsigned long long cyc2ns_suspend;
 
-void save_sched_clock_state(void)
+void tsc_save_sched_clock_state(void)
 {
 	if (!sched_clock_stable)
 		return;
@@ -646,7 +646,7 @@ void save_sched_clock_state(void)
  * that sched_clock() continues from the point where it was left off during
  * suspend.
  */
-void restore_sched_clock_state(void)
+void tsc_restore_sched_clock_state(void)
 {
 	unsigned long long offset;
 	unsigned long flags;
@@ -933,6 +933,16 @@ static int __init init_tsc_clocksource(void)
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
 	}
+
+	/*
+	 * Trust the results of the earlier calibration on systems
+	 * exporting a reliable TSC.
+	 */
+	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+		clocksource_register_khz(&clocksource_tsc, tsc_khz);
+		return 0;
+	}
+
 	schedule_delayed_work(&tsc_irqwork, 0);
 	return 0;
 }
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 328cb37bb827..255f58ae71e8 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -569,7 +569,7 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno)
 	}
 	if (trapno != 1)
 		return 1; /* we let this handle by the calling routine */
-	current->thread.trap_no = trapno;
+	current->thread.trap_nr = trapno;
 	current->thread.error_code = error_code;
 	force_sig(SIGTRAP, current);
 	return 0;
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index b07ba9393564..f386dc49f988 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -52,10 +52,7 @@
 #include "vsyscall_trace.h"
 
 DEFINE_VVAR(int, vgetcpu_mode);
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
-{
-	.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
-};
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
 
@@ -80,20 +77,15 @@ early_param("vsyscall", vsyscall_setup);
 
 void update_vsyscall_tz(void)
 {
-	unsigned long flags;
-
-	write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
-	/* sys_tz has changed */
 	vsyscall_gtod_data.sys_tz = sys_tz;
-	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
 
 void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 			struct clocksource *clock, u32 mult)
 {
-	unsigned long flags;
+	struct timespec monotonic;
 
-	write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+	write_seqcount_begin(&vsyscall_gtod_data.seq);
 
 	/* copy vsyscall data */
 	vsyscall_gtod_data.clock.vclock_mode	= clock->archdata.vclock_mode;
@@ -101,12 +93,19 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 	vsyscall_gtod_data.clock.mask		= clock->mask;
 	vsyscall_gtod_data.clock.mult		= mult;
 	vsyscall_gtod_data.clock.shift		= clock->shift;
+
 	vsyscall_gtod_data.wall_time_sec	= wall_time->tv_sec;
 	vsyscall_gtod_data.wall_time_nsec	= wall_time->tv_nsec;
-	vsyscall_gtod_data.wall_to_monotonic	= *wtm;
+
+	monotonic = timespec_add(*wall_time, *wtm);
+	vsyscall_gtod_data.monotonic_time_sec	= monotonic.tv_sec;
+	vsyscall_gtod_data.monotonic_time_nsec	= monotonic.tv_nsec;
+
 	vsyscall_gtod_data.wall_time_coarse	= __current_kernel_time();
+	vsyscall_gtod_data.monotonic_time_coarse =
+		timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm);
 
-	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
+	write_seqcount_end(&vsyscall_gtod_data.seq);
 }
 
 static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
@@ -153,7 +152,7 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
 
 		thread->error_code	= 6;  /* user fault, no page, write */
 		thread->cr2		= ptr;
-		thread->trap_no		= 14;
+		thread->trap_nr		= X86_TRAP_PF;
 
 		memset(&info, 0, sizeof(info));
 		info.si_signo		= SIGSEGV;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 947a06ccc673..e9f265fd79ae 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -91,6 +91,7 @@ struct x86_init_ops x86_init __initdata = {
 };
 
 struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
+	.early_percpu_clock_init	= x86_init_noop,
 	.setup_percpu_clockev		= setup_secondary_APIC_clock,
 	.fixup_cpu_id			= x86_default_fixup_cpu_id,
 };
@@ -107,7 +108,9 @@ struct x86_platform_ops x86_platform = {
 	.is_untracked_pat_range		= is_ISA_range,
 	.nmi_init			= default_nmi_init,
 	.get_nmi_reason			= default_get_nmi_reason,
-	.i8042_detect			= default_i8042_detect
+	.i8042_detect			= default_i8042_detect,
+	.save_sched_clock_state 	= tsc_save_sched_clock_state,
+	.restore_sched_clock_state 	= tsc_restore_sched_clock_state,
 };
 
 EXPORT_SYMBOL_GPL(x86_platform);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 89b02bfaaca5..9fed5bedaad6 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -236,7 +236,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	const u32 kvm_supported_word6_x86_features =
 		F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
 		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
-		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
+		F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) |
 		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
 
 	/* cpuid 0xC0000001.edx */
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 5b97e1797a6d..26d1fb437eb5 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -43,4 +43,12 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
 }
 
+static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+	return best && (best->ecx & bit(X86_FEATURE_OSVW));
+}
+
 #endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0982507b962a..83756223f8aa 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -57,6 +57,7 @@
 #define OpDS              23ull  /* DS */
 #define OpFS              24ull  /* FS */
 #define OpGS              25ull  /* GS */
+#define OpMem8            26ull  /* 8-bit zero extended memory operand */
 
 #define OpBits             5  /* Width of operand field */
 #define OpMask             ((1ull << OpBits) - 1)
@@ -101,6 +102,7 @@
 #define SrcAcc      (OpAcc << SrcShift)
 #define SrcImmU16   (OpImmU16 << SrcShift)
 #define SrcDX       (OpDX << SrcShift)
+#define SrcMem8     (OpMem8 << SrcShift)
 #define SrcMask     (OpMask << SrcShift)
 #define BitOp       (1<<11)
 #define MemAbs      (1<<12)      /* Memory operand is absolute displacement */
@@ -858,8 +860,7 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 }
 
 static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
-				    struct operand *op,
-				    int inhibit_bytereg)
+				    struct operand *op)
 {
 	unsigned reg = ctxt->modrm_reg;
 	int highbyte_regs = ctxt->rex_prefix == 0;
@@ -876,7 +877,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
 	}
 
 	op->type = OP_REG;
-	if ((ctxt->d & ByteOp) && !inhibit_bytereg) {
+	if (ctxt->d & ByteOp) {
 		op->addr.reg = decode_register(reg, ctxt->regs, highbyte_regs);
 		op->bytes = 1;
 	} else {
@@ -1151,6 +1152,22 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 	return 1;
 }
 
+static int read_interrupt_descriptor(struct x86_emulate_ctxt *ctxt,
+				     u16 index, struct desc_struct *desc)
+{
+	struct desc_ptr dt;
+	ulong addr;
+
+	ctxt->ops->get_idt(ctxt, &dt);
+
+	if (dt.size < index * 8 + 7)
+		return emulate_gp(ctxt, index << 3 | 0x2);
+
+	addr = dt.address + index * 8;
+	return ctxt->ops->read_std(ctxt, addr, desc, sizeof *desc,
+				   &ctxt->exception);
+}
+
 static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt,
 				     u16 selector, struct desc_ptr *dt)
 {
@@ -1227,6 +1244,8 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 		seg_desc.type = 3;
 		seg_desc.p = 1;
 		seg_desc.s = 1;
+		if (ctxt->mode == X86EMUL_MODE_VM86)
+			seg_desc.dpl = 3;
 		goto load;
 	}
 
@@ -1891,6 +1910,17 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
 	ss->p = 1;
 }
 
+static bool vendor_intel(struct x86_emulate_ctxt *ctxt)
+{
+	u32 eax, ebx, ecx, edx;
+
+	eax = ecx = 0;
+	return ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)
+		&& ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx
+		&& ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx
+		&& edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx;
+}
+
 static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
 {
 	struct x86_emulate_ops *ops = ctxt->ops;
@@ -2007,6 +2037,14 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->mode == X86EMUL_MODE_REAL)
 		return emulate_gp(ctxt, 0);
 
+	/*
+	 * Not recognized on AMD in compat mode (but is recognized in legacy
+	 * mode).
+	 */
+	if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA)
+	    && !vendor_intel(ctxt))
+		return emulate_ud(ctxt);
+
 	/* XXX sysenter/sysexit have not been tested in 64bit mode.
 	* Therefore, we inject an #UD.
 	*/
@@ -2306,6 +2344,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
 		return emulate_gp(ctxt, 0);
 	ctxt->_eip = tss->eip;
 	ctxt->eflags = tss->eflags | 2;
+
+	/* General purpose registers */
 	ctxt->regs[VCPU_REGS_RAX] = tss->eax;
 	ctxt->regs[VCPU_REGS_RCX] = tss->ecx;
 	ctxt->regs[VCPU_REGS_RDX] = tss->edx;
@@ -2328,6 +2368,24 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
 	set_segment_selector(ctxt, tss->gs, VCPU_SREG_GS);
 
 	/*
+	 * If we're switching between Protected Mode and VM86, we need to make
+	 * sure to update the mode before loading the segment descriptors so
+	 * that the selectors are interpreted correctly.
+	 *
+	 * Need to get rflags to the vcpu struct immediately because it
+	 * influences the CPL which is checked at least when loading the segment
+	 * descriptors and when pushing an error code to the new kernel stack.
+	 *
+	 * TODO Introduce a separate ctxt->ops->set_cpl callback
+	 */
+	if (ctxt->eflags & X86_EFLAGS_VM)
+		ctxt->mode = X86EMUL_MODE_VM86;
+	else
+		ctxt->mode = X86EMUL_MODE_PROT32;
+
+	ctxt->ops->set_rflags(ctxt, ctxt->eflags);
+
+	/*
 	 * Now load segment descriptors. If fault happenes at this stage
 	 * it is handled in a context of new task
 	 */
@@ -2401,7 +2459,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 }
 
 static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
-				   u16 tss_selector, int reason,
+				   u16 tss_selector, int idt_index, int reason,
 				   bool has_error_code, u32 error_code)
 {
 	struct x86_emulate_ops *ops = ctxt->ops;
@@ -2423,12 +2481,35 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 
 	/* FIXME: check that next_tss_desc is tss */
 
-	if (reason != TASK_SWITCH_IRET) {
-		if ((tss_selector & 3) > next_tss_desc.dpl ||
-		    ops->cpl(ctxt) > next_tss_desc.dpl)
-			return emulate_gp(ctxt, 0);
+	/*
+	 * Check privileges. The three cases are task switch caused by...
+	 *
+	 * 1. jmp/call/int to task gate: Check against DPL of the task gate
+	 * 2. Exception/IRQ/iret: No check is performed
+	 * 3. jmp/call to TSS: Check agains DPL of the TSS
+	 */
+	if (reason == TASK_SWITCH_GATE) {
+		if (idt_index != -1) {
+			/* Software interrupts */
+			struct desc_struct task_gate_desc;
+			int dpl;
+
+			ret = read_interrupt_descriptor(ctxt, idt_index,
+							&task_gate_desc);
+			if (ret != X86EMUL_CONTINUE)
+				return ret;
+
+			dpl = task_gate_desc.dpl;
+			if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl)
+				return emulate_gp(ctxt, (idt_index << 3) | 0x2);
+		}
+	} else if (reason != TASK_SWITCH_IRET) {
+		int dpl = next_tss_desc.dpl;
+		if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl)
+			return emulate_gp(ctxt, tss_selector);
 	}
 
+
 	desc_limit = desc_limit_scaled(&next_tss_desc);
 	if (!next_tss_desc.p ||
 	    ((desc_limit < 0x67 && (next_tss_desc.type & 8)) ||
@@ -2481,7 +2562,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 }
 
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
-			 u16 tss_selector, int reason,
+			 u16 tss_selector, int idt_index, int reason,
 			 bool has_error_code, u32 error_code)
 {
 	int rc;
@@ -2489,7 +2570,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 	ctxt->_eip = ctxt->eip;
 	ctxt->dst.type = OP_NONE;
 
-	rc = emulator_do_task_switch(ctxt, tss_selector, reason,
+	rc = emulator_do_task_switch(ctxt, tss_selector, idt_index, reason,
 				     has_error_code, error_code);
 
 	if (rc == X86EMUL_CONTINUE)
@@ -3514,13 +3595,13 @@ static struct opcode twobyte_table[256] = {
 	I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr),
 	I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg),
 	I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg),
-	D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
+	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xB8 - 0xBF */
 	N, N,
 	G(BitOp, group8),
 	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc),
 	I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr),
-	D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
+	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xC0 - 0xCF */
 	D2bv(DstMem | SrcReg | ModRM | Lock),
 	N, D(DstMem | SrcReg | ModRM | Mov),
@@ -3602,9 +3683,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 
 	switch (d) {
 	case OpReg:
-		decode_register_operand(ctxt, op,
-			 op == &ctxt->dst &&
-			 ctxt->twobyte && (ctxt->b == 0xb6 || ctxt->b == 0xb7));
+		decode_register_operand(ctxt, op);
 		break;
 	case OpImmUByte:
 		rc = decode_imm(ctxt, op, 1, false);
@@ -3656,6 +3735,9 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	case OpImm:
 		rc = decode_imm(ctxt, op, imm_size(ctxt), true);
 		break;
+	case OpMem8:
+		ctxt->memop.bytes = 1;
+		goto mem_common;
 	case OpMem16:
 		ctxt->memop.bytes = 2;
 		goto mem_common;
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index b6a73537e1ef..81cf4fa4a2be 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -307,6 +307,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 		if (val & 0x10) {
 			s->init4 = val & 1;
 			s->last_irr = 0;
+			s->irr &= s->elcr;
 			s->imr = 0;
 			s->priority_add = 0;
 			s->special_mask = 0;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 31bfc6927bc0..858432287ab6 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -433,7 +433,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		break;
 
 	case APIC_DM_INIT:
-		if (level) {
+		if (!trig_mode || level) {
 			result = 1;
 			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -731,7 +731,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
 		u64 ns = 0;
 		struct kvm_vcpu *vcpu = apic->vcpu;
-		unsigned long this_tsc_khz = vcpu_tsc_khz(vcpu);
+		unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
 		unsigned long flags;
 
 		if (unlikely(!tscdeadline || !this_tsc_khz))
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 224b02c3cda9..4cb164268846 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -688,9 +688,8 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
 {
 	unsigned long idx;
 
-	idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
-	      (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
-	return &slot->lpage_info[level - 2][idx];
+	idx = gfn_to_index(gfn, slot->base_gfn, level);
+	return &slot->arch.lpage_info[level - 2][idx];
 }
 
 static void account_shadowed(struct kvm *kvm, gfn_t gfn)
@@ -946,7 +945,7 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn)
 	}
 }
 
-static unsigned long *__gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level,
+static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
 				    struct kvm_memory_slot *slot)
 {
 	struct kvm_lpage_info *linfo;
@@ -966,7 +965,7 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
 	struct kvm_memory_slot *slot;
 
 	slot = gfn_to_memslot(kvm, gfn);
-	return __gfn_to_rmap(kvm, gfn, level, slot);
+	return __gfn_to_rmap(gfn, level, slot);
 }
 
 static bool rmap_can_add(struct kvm_vcpu *vcpu)
@@ -988,7 +987,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 	return pte_list_add(vcpu, spte, rmapp);
 }
 
-static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
+static u64 *rmap_next(unsigned long *rmapp, u64 *spte)
 {
 	return pte_list_next(rmapp, spte);
 }
@@ -1018,8 +1017,8 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
 	u64 *spte;
 	int i, write_protected = 0;
 
-	rmapp = __gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL, slot);
-	spte = rmap_next(kvm, rmapp, NULL);
+	rmapp = __gfn_to_rmap(gfn, PT_PAGE_TABLE_LEVEL, slot);
+	spte = rmap_next(rmapp, NULL);
 	while (spte) {
 		BUG_ON(!(*spte & PT_PRESENT_MASK));
 		rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
@@ -1027,14 +1026,14 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
 			mmu_spte_update(spte, *spte & ~PT_WRITABLE_MASK);
 			write_protected = 1;
 		}
-		spte = rmap_next(kvm, rmapp, spte);
+		spte = rmap_next(rmapp, spte);
 	}
 
 	/* check for huge page mappings */
 	for (i = PT_DIRECTORY_LEVEL;
 	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
-		rmapp = __gfn_to_rmap(kvm, gfn, i, slot);
-		spte = rmap_next(kvm, rmapp, NULL);
+		rmapp = __gfn_to_rmap(gfn, i, slot);
+		spte = rmap_next(rmapp, NULL);
 		while (spte) {
 			BUG_ON(!(*spte & PT_PRESENT_MASK));
 			BUG_ON(!is_large_pte(*spte));
@@ -1045,7 +1044,7 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
 				spte = NULL;
 				write_protected = 1;
 			}
-			spte = rmap_next(kvm, rmapp, spte);
+			spte = rmap_next(rmapp, spte);
 		}
 	}
 
@@ -1066,7 +1065,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	u64 *spte;
 	int need_tlb_flush = 0;
 
-	while ((spte = rmap_next(kvm, rmapp, NULL))) {
+	while ((spte = rmap_next(rmapp, NULL))) {
 		BUG_ON(!(*spte & PT_PRESENT_MASK));
 		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte);
 		drop_spte(kvm, spte);
@@ -1085,14 +1084,14 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 
 	WARN_ON(pte_huge(*ptep));
 	new_pfn = pte_pfn(*ptep);
-	spte = rmap_next(kvm, rmapp, NULL);
+	spte = rmap_next(rmapp, NULL);
 	while (spte) {
 		BUG_ON(!is_shadow_present_pte(*spte));
 		rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte);
 		need_flush = 1;
 		if (pte_write(*ptep)) {
 			drop_spte(kvm, spte);
-			spte = rmap_next(kvm, rmapp, NULL);
+			spte = rmap_next(rmapp, NULL);
 		} else {
 			new_spte = *spte &~ (PT64_BASE_ADDR_MASK);
 			new_spte |= (u64)new_pfn << PAGE_SHIFT;
@@ -1102,7 +1101,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			new_spte &= ~shadow_accessed_mask;
 			mmu_spte_clear_track_bits(spte);
 			mmu_spte_set(spte, new_spte);
-			spte = rmap_next(kvm, rmapp, spte);
+			spte = rmap_next(rmapp, spte);
 		}
 	}
 	if (need_flush)
@@ -1176,7 +1175,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	if (!shadow_accessed_mask)
 		return kvm_unmap_rmapp(kvm, rmapp, data);
 
-	spte = rmap_next(kvm, rmapp, NULL);
+	spte = rmap_next(rmapp, NULL);
 	while (spte) {
 		int _young;
 		u64 _spte = *spte;
@@ -1186,7 +1185,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			young = 1;
 			clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
 		}
-		spte = rmap_next(kvm, rmapp, spte);
+		spte = rmap_next(rmapp, spte);
 	}
 	return young;
 }
@@ -1205,7 +1204,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	if (!shadow_accessed_mask)
 		goto out;
 
-	spte = rmap_next(kvm, rmapp, NULL);
+	spte = rmap_next(rmapp, NULL);
 	while (spte) {
 		u64 _spte = *spte;
 		BUG_ON(!(_spte & PT_PRESENT_MASK));
@@ -1214,7 +1213,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			young = 1;
 			break;
 		}
-		spte = rmap_next(kvm, rmapp, spte);
+		spte = rmap_next(rmapp, spte);
 	}
 out:
 	return young;
@@ -1391,11 +1390,6 @@ struct kvm_mmu_pages {
 	unsigned int nr;
 };
 
-#define for_each_unsync_children(bitmap, idx)		\
-	for (idx = find_first_bit(bitmap, 512);		\
-	     idx < 512;					\
-	     idx = find_next_bit(bitmap, 512, idx+1))
-
 static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
 			 int idx)
 {
@@ -1417,7 +1411,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
 {
 	int i, ret, nr_unsync_leaf = 0;
 
-	for_each_unsync_children(sp->unsync_child_bitmap, i) {
+	for_each_set_bit(i, sp->unsync_child_bitmap, 512) {
 		struct kvm_mmu_page *child;
 		u64 ent = sp->spt[i];
 
@@ -1803,6 +1797,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
 {
 	if (is_large_pte(*sptep)) {
 		drop_spte(vcpu->kvm, sptep);
+		--vcpu->kvm->stat.lpages;
 		kvm_flush_remote_tlbs(vcpu->kvm);
 	}
 }
@@ -3190,15 +3185,14 @@ static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
 #undef PTTYPE
 
 static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu *context,
-				  int level)
+				  struct kvm_mmu *context)
 {
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	u64 exb_bit_rsvd = 0;
 
 	if (!context->nx)
 		exb_bit_rsvd = rsvd_bits(63, 63);
-	switch (level) {
+	switch (context->root_level) {
 	case PT32_ROOT_LEVEL:
 		/* no rsvd bits for 2 level 4K page table entries */
 		context->rsvd_bits_mask[0][1] = 0;
@@ -3256,8 +3250,9 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 					int level)
 {
 	context->nx = is_nx(vcpu);
+	context->root_level = level;
 
-	reset_rsvds_bits_mask(vcpu, context, level);
+	reset_rsvds_bits_mask(vcpu, context);
 
 	ASSERT(is_pae(vcpu));
 	context->new_cr3 = paging_new_cr3;
@@ -3267,7 +3262,6 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 	context->invlpg = paging64_invlpg;
 	context->update_pte = paging64_update_pte;
 	context->free = paging_free;
-	context->root_level = level;
 	context->shadow_root_level = level;
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = false;
@@ -3284,8 +3278,9 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
 				 struct kvm_mmu *context)
 {
 	context->nx = false;
+	context->root_level = PT32_ROOT_LEVEL;
 
-	reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL);
+	reset_rsvds_bits_mask(vcpu, context);
 
 	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging32_page_fault;
@@ -3294,7 +3289,6 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
 	context->sync_page = paging32_sync_page;
 	context->invlpg = paging32_invlpg;
 	context->update_pte = paging32_update_pte;
-	context->root_level = PT32_ROOT_LEVEL;
 	context->shadow_root_level = PT32E_ROOT_LEVEL;
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = false;
@@ -3325,7 +3319,6 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	context->get_cr3 = get_cr3;
 	context->get_pdptr = kvm_pdptr_read;
 	context->inject_page_fault = kvm_inject_page_fault;
-	context->nx = is_nx(vcpu);
 
 	if (!is_paging(vcpu)) {
 		context->nx = false;
@@ -3333,19 +3326,19 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		context->root_level = 0;
 	} else if (is_long_mode(vcpu)) {
 		context->nx = is_nx(vcpu);
-		reset_rsvds_bits_mask(vcpu, context, PT64_ROOT_LEVEL);
-		context->gva_to_gpa = paging64_gva_to_gpa;
 		context->root_level = PT64_ROOT_LEVEL;
+		reset_rsvds_bits_mask(vcpu, context);
+		context->gva_to_gpa = paging64_gva_to_gpa;
 	} else if (is_pae(vcpu)) {
 		context->nx = is_nx(vcpu);
-		reset_rsvds_bits_mask(vcpu, context, PT32E_ROOT_LEVEL);
-		context->gva_to_gpa = paging64_gva_to_gpa;
 		context->root_level = PT32E_ROOT_LEVEL;
+		reset_rsvds_bits_mask(vcpu, context);
+		context->gva_to_gpa = paging64_gva_to_gpa;
 	} else {
 		context->nx = false;
-		reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL);
-		context->gva_to_gpa = paging32_gva_to_gpa;
 		context->root_level = PT32_ROOT_LEVEL;
+		reset_rsvds_bits_mask(vcpu, context);
+		context->gva_to_gpa = paging32_gva_to_gpa;
 	}
 
 	return 0;
@@ -3408,18 +3401,18 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 		g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested;
 	} else if (is_long_mode(vcpu)) {
 		g_context->nx = is_nx(vcpu);
-		reset_rsvds_bits_mask(vcpu, g_context, PT64_ROOT_LEVEL);
 		g_context->root_level = PT64_ROOT_LEVEL;
+		reset_rsvds_bits_mask(vcpu, g_context);
 		g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
 	} else if (is_pae(vcpu)) {
 		g_context->nx = is_nx(vcpu);
-		reset_rsvds_bits_mask(vcpu, g_context, PT32E_ROOT_LEVEL);
 		g_context->root_level = PT32E_ROOT_LEVEL;
+		reset_rsvds_bits_mask(vcpu, g_context);
 		g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
 	} else {
 		g_context->nx = false;
-		reset_rsvds_bits_mask(vcpu, g_context, PT32_ROOT_LEVEL);
 		g_context->root_level = PT32_ROOT_LEVEL;
+		reset_rsvds_bits_mask(vcpu, g_context);
 		g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
 	}
 
@@ -3555,7 +3548,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
  * If we're seeing too many writes to a page, it may no longer be a page table,
  * or we may be forking, in which case it is better to unmap the page.
  */
-static bool detect_write_flooding(struct kvm_mmu_page *sp, u64 *spte)
+static bool detect_write_flooding(struct kvm_mmu_page *sp)
 {
 	/*
 	 * Skip write-flooding detected for the sp whose level is 1, because
@@ -3664,10 +3657,8 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 
 	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
 	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) {
-		spte = get_written_sptes(sp, gpa, &npte);
-
 		if (detect_write_misaligned(sp, gpa, bytes) ||
-		      detect_write_flooding(sp, spte)) {
+		      detect_write_flooding(sp)) {
 			zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
 						     &invalid_list);
 			++vcpu->kvm->stat.mmu_flooded;
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index ea7b4fd34676..715da5a19a5b 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -200,13 +200,13 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 	slot = gfn_to_memslot(kvm, sp->gfn);
 	rmapp = &slot->rmap[sp->gfn - slot->base_gfn];
 
-	spte = rmap_next(kvm, rmapp, NULL);
+	spte = rmap_next(rmapp, NULL);
 	while (spte) {
 		if (is_writable_pte(*spte))
 			audit_printk(kvm, "shadow page has writable "
 				     "mappings: gfn %llx role %x\n",
 				     sp->gfn, sp->role.word);
-		spte = rmap_next(kvm, rmapp, spte);
+		spte = rmap_next(rmapp, spte);
 	}
 }
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 7aad5446f393..a73f0c104813 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -33,10 +33,11 @@ static struct kvm_arch_event_perf_mapping {
 	[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
 	[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
 	[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
+	[7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
 };
 
 /* mapping between fixed pmc index and arch_events array */
-int fixed_pmc_events[] = {1, 0, 2};
+int fixed_pmc_events[] = {1, 0, 7};
 
 static bool pmc_is_gp(struct kvm_pmc *pmc)
 {
@@ -210,6 +211,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	unsigned config, type = PERF_TYPE_RAW;
 	u8 event_select, unit_mask;
 
+	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
+		printk_once("kvm pmu: pin control bit is ignored\n");
+
 	pmc->eventsel = eventsel;
 
 	stop_counter(pmc);
@@ -220,7 +224,7 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
 	unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 
-	if (!(event_select & (ARCH_PERFMON_EVENTSEL_EDGE |
+	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
 				ARCH_PERFMON_EVENTSEL_INV |
 				ARCH_PERFMON_EVENTSEL_CMASK))) {
 		config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
@@ -413,7 +417,7 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data)
 	struct kvm_pmc *counters;
 	u64 ctr;
 
-	pmc &= (3u << 30) - 1;
+	pmc &= ~(3u << 30);
 	if (!fixed && pmc >= pmu->nr_arch_gp_counters)
 		return 1;
 	if (fixed && pmc >= pmu->nr_arch_fixed_counters)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e385214711cb..e334389e1c75 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -111,6 +111,12 @@ struct nested_state {
 #define MSRPM_OFFSETS	16
 static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 
+/*
+ * Set osvw_len to higher value when updated Revision Guides
+ * are published and we know what the new status bits are
+ */
+static uint64_t osvw_len = 4, osvw_status;
+
 struct vcpu_svm {
 	struct kvm_vcpu vcpu;
 	struct vmcb *vmcb;
@@ -177,11 +183,13 @@ static bool npt_enabled = true;
 #else
 static bool npt_enabled;
 #endif
-static int npt = 1;
 
+/* allow nested paging (virtualized MMU) for all guests */
+static int npt = true;
 module_param(npt, int, S_IRUGO);
 
-static int nested = 1;
+/* allow nested virtualization in KVM/SVM */
+static int nested = true;
 module_param(nested, int, S_IRUGO);
 
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
@@ -557,6 +565,27 @@ static void svm_init_erratum_383(void)
 	erratum_383_found = true;
 }
 
+static void svm_init_osvw(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Guests should see errata 400 and 415 as fixed (assuming that
+	 * HLT and IO instructions are intercepted).
+	 */
+	vcpu->arch.osvw.length = (osvw_len >= 3) ? (osvw_len) : 3;
+	vcpu->arch.osvw.status = osvw_status & ~(6ULL);
+
+	/*
+	 * By increasing VCPU's osvw.length to 3 we are telling the guest that
+	 * all osvw.status bits inside that length, including bit 0 (which is
+	 * reserved for erratum 298), are valid. However, if host processor's
+	 * osvw_len is 0 then osvw_status[0] carries no information. We need to
+	 * be conservative here and therefore we tell the guest that erratum 298
+	 * is present (because we really don't know).
+	 */
+	if (osvw_len == 0 && boot_cpu_data.x86 == 0x10)
+		vcpu->arch.osvw.status |= 1;
+}
+
 static int has_svm(void)
 {
 	const char *msg;
@@ -623,6 +652,36 @@ static int svm_hardware_enable(void *garbage)
 		__get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT;
 	}
 
+
+	/*
+	 * Get OSVW bits.
+	 *
+	 * Note that it is possible to have a system with mixed processor
+	 * revisions and therefore different OSVW bits. If bits are not the same
+	 * on different processors then choose the worst case (i.e. if erratum
+	 * is present on one processor and not on another then assume that the
+	 * erratum is present everywhere).
+	 */
+	if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) {
+		uint64_t len, status = 0;
+		int err;
+
+		len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err);
+		if (!err)
+			status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS,
+						      &err);
+
+		if (err)
+			osvw_status = osvw_len = 0;
+		else {
+			if (len < osvw_len)
+				osvw_len = len;
+			osvw_status |= status;
+			osvw_status &= (1ULL << osvw_len) - 1;
+		}
+	} else
+		osvw_status = osvw_len = 0;
+
 	svm_init_erratum_383();
 
 	amd_pmu_enable_virt();
@@ -910,20 +969,25 @@ static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc)
 	return _tsc;
 }
 
-static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
+static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 ratio;
 	u64 khz;
 
-	/* TSC scaling supported? */
-	if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR))
+	/* Guest TSC same frequency as host TSC? */
+	if (!scale) {
+		svm->tsc_ratio = TSC_RATIO_DEFAULT;
 		return;
+	}
 
-	/* TSC-Scaling disabled or guest TSC same frequency as host TSC? */
-	if (user_tsc_khz == 0) {
-		vcpu->arch.virtual_tsc_khz = 0;
-		svm->tsc_ratio = TSC_RATIO_DEFAULT;
+	/* TSC scaling supported? */
+	if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) {
+		if (user_tsc_khz > tsc_khz) {
+			vcpu->arch.tsc_catchup = 1;
+			vcpu->arch.tsc_always_catchup = 1;
+		} else
+			WARN(1, "user requested TSC rate below hardware speed\n");
 		return;
 	}
 
@@ -938,7 +1002,6 @@ static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
 				user_tsc_khz);
 		return;
 	}
-	vcpu->arch.virtual_tsc_khz = user_tsc_khz;
 	svm->tsc_ratio             = ratio;
 }
 
@@ -958,10 +1021,14 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
-static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
+static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	WARN_ON(adjustment < 0);
+	if (host)
+		adjustment = svm_scale_tsc(vcpu, adjustment);
+
 	svm->vmcb->control.tsc_offset += adjustment;
 	if (is_guest_mode(vcpu))
 		svm->nested.hsave->control.tsc_offset += adjustment;
@@ -1191,6 +1258,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (kvm_vcpu_is_bsp(&svm->vcpu))
 		svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
 
+	svm_init_osvw(&svm->vcpu);
+
 	return &svm->vcpu;
 
 free_page4:
@@ -1268,6 +1337,21 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 }
 
+static void svm_update_cpl(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	int cpl;
+
+	if (!is_protmode(vcpu))
+		cpl = 0;
+	else if (svm->vmcb->save.rflags & X86_EFLAGS_VM)
+		cpl = 3;
+	else
+		cpl = svm->vmcb->save.cs.selector & 0x3;
+
+	svm->vmcb->save.cpl = cpl;
+}
+
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 {
 	return to_svm(vcpu)->vmcb->save.rflags;
@@ -1275,7 +1359,11 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 
 static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
+	unsigned long old_rflags = to_svm(vcpu)->vmcb->save.rflags;
+
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
+	if ((old_rflags ^ rflags) & X86_EFLAGS_VM)
+		svm_update_cpl(vcpu);
 }
 
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
@@ -1543,9 +1631,7 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 		s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
 	}
 	if (seg == VCPU_SREG_CS)
-		svm->vmcb->save.cpl
-			= (svm->vmcb->save.cs.attrib
-			   >> SVM_SELECTOR_DPL_SHIFT) & 3;
+		svm_update_cpl(vcpu);
 
 	mark_dirty(svm->vmcb, VMCB_SEG);
 }
@@ -2735,7 +2821,10 @@ static int task_switch_interception(struct vcpu_svm *svm)
 	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR)))
 		skip_emulated_instruction(&svm->vcpu);
 
-	if (kvm_task_switch(&svm->vcpu, tss_selector, reason,
+	if (int_type != SVM_EXITINTINFO_TYPE_SOFT)
+		int_vec = -1;
+
+	if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason,
 				has_error_code, error_code) == EMULATE_FAIL) {
 		svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 246490f643b6..280751c84724 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -70,9 +70,6 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 static bool __read_mostly vmm_exclusive = 1;
 module_param(vmm_exclusive, bool, S_IRUGO);
 
-static bool __read_mostly yield_on_hlt = 1;
-module_param(yield_on_hlt, bool, S_IRUGO);
-
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
@@ -1655,17 +1652,6 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	vmx_set_interrupt_shadow(vcpu, 0);
 }
 
-static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
-{
-	/* Ensure that we clear the HLT state in the VMCS.  We don't need to
-	 * explicitly skip the instruction because if the HLT state is set, then
-	 * the instruction is already executing and RIP has already been
-	 * advanced. */
-	if (!yield_on_hlt &&
-	    vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT)
-		vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
-}
-
 /*
  * KVM wants to inject page-faults which it got to the guest. This function
  * checks whether in a nested guest, we need to inject them to L1 or L2.
@@ -1678,7 +1664,7 @@ static int nested_pf_handled(struct kvm_vcpu *vcpu)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
 	/* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */
-	if (!(vmcs12->exception_bitmap & PF_VECTOR))
+	if (!(vmcs12->exception_bitmap & (1u << PF_VECTOR)))
 		return 0;
 
 	nested_vmx_vmexit(vcpu);
@@ -1718,7 +1704,6 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 		intr_info |= INTR_TYPE_HARD_EXCEPTION;
 
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
-	vmx_clear_hlt(vcpu);
 }
 
 static bool vmx_rdtscp_supported(void)
@@ -1817,13 +1802,19 @@ u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Empty call-back. Needs to be implemented when VMX enables the SET_TSC_KHZ
- * ioctl. In this case the call-back should update internal vmx state to make
- * the changes effective.
+ * Engage any workarounds for mis-matched TSC rates.  Currently limited to
+ * software catchup for faster rates on slower CPUs.
  */
-static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
+static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 {
-	/* Nothing to do here */
+	if (!scale)
+		return;
+
+	if (user_tsc_khz > tsc_khz) {
+		vcpu->arch.tsc_catchup = 1;
+		vcpu->arch.tsc_always_catchup = 1;
+	} else
+		WARN(1, "user requested TSC rate below hardware speed\n");
 }
 
 /*
@@ -1850,7 +1841,7 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	}
 }
 
-static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
+static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host)
 {
 	u64 offset = vmcs_read64(TSC_OFFSET);
 	vmcs_write64(TSC_OFFSET, offset + adjustment);
@@ -2219,6 +2210,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
 			msr->data = data;
+			if (msr - vmx->guest_msrs < vmx->save_nmsrs)
+				kvm_set_shared_msr(msr->index, msr->data,
+						   msr->mask);
 			break;
 		}
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
@@ -2399,7 +2393,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 				&_pin_based_exec_control) < 0)
 		return -EIO;
 
-	min =
+	min = CPU_BASED_HLT_EXITING |
 #ifdef CONFIG_X86_64
 	      CPU_BASED_CR8_LOAD_EXITING |
 	      CPU_BASED_CR8_STORE_EXITING |
@@ -2414,9 +2408,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	      CPU_BASED_INVLPG_EXITING |
 	      CPU_BASED_RDPMC_EXITING;
 
-	if (yield_on_hlt)
-		min |= CPU_BASED_HLT_EXITING;
-
 	opt = CPU_BASED_TPR_SHADOW |
 	      CPU_BASED_USE_MSR_BITMAPS |
 	      CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
@@ -4003,7 +3994,6 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu)
 	} else
 		intr |= INTR_TYPE_EXT_INTR;
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr);
-	vmx_clear_hlt(vcpu);
 }
 
 static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
@@ -4035,7 +4025,6 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
 	}
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
 			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
-	vmx_clear_hlt(vcpu);
 }
 
 static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
@@ -4672,9 +4661,10 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 	bool has_error_code = false;
 	u32 error_code = 0;
 	u16 tss_selector;
-	int reason, type, idt_v;
+	int reason, type, idt_v, idt_index;
 
 	idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK);
+	idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK);
 	type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK);
 
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
@@ -4712,8 +4702,9 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 		       type != INTR_TYPE_NMI_INTR))
 		skip_emulated_instruction(vcpu);
 
-	if (kvm_task_switch(vcpu, tss_selector, reason,
-				has_error_code, error_code) == EMULATE_FAIL) {
+	if (kvm_task_switch(vcpu, tss_selector,
+			    type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason,
+			    has_error_code, error_code) == EMULATE_FAIL) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 54696b5f8443..4044ce0bf7c1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -97,6 +97,10 @@ EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
 u32  kvm_max_guest_tsc_khz;
 EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);
 
+/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
+static u32 tsc_tolerance_ppm = 250;
+module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
+
 #define KVM_NR_SHARED_MSRS 16
 
 struct kvm_shared_msrs_global {
@@ -969,50 +973,51 @@ static inline u64 get_kernel_ns(void)
 static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
 unsigned long max_tsc_khz;
 
-static inline int kvm_tsc_changes_freq(void)
+static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 {
-	int cpu = get_cpu();
-	int ret = !boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
-		  cpufreq_quick_get(cpu) != 0;
-	put_cpu();
-	return ret;
+	return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
+				   vcpu->arch.virtual_tsc_shift);
 }
 
-u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu)
+static u32 adjust_tsc_khz(u32 khz, s32 ppm)
 {
-	if (vcpu->arch.virtual_tsc_khz)
-		return vcpu->arch.virtual_tsc_khz;
-	else
-		return __this_cpu_read(cpu_tsc_khz);
+	u64 v = (u64)khz * (1000000 + ppm);
+	do_div(v, 1000000);
+	return v;
 }
 
-static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
+static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
 {
-	u64 ret;
-
-	WARN_ON(preemptible());
-	if (kvm_tsc_changes_freq())
-		printk_once(KERN_WARNING
-		 "kvm: unreliable cycle conversion on adjustable rate TSC\n");
-	ret = nsec * vcpu_tsc_khz(vcpu);
-	do_div(ret, USEC_PER_SEC);
-	return ret;
-}
+	u32 thresh_lo, thresh_hi;
+	int use_scaling = 0;
 
-static void kvm_init_tsc_catchup(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
-{
 	/* Compute a scale to convert nanoseconds in TSC cycles */
 	kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
-			   &vcpu->arch.tsc_catchup_shift,
-			   &vcpu->arch.tsc_catchup_mult);
+			   &vcpu->arch.virtual_tsc_shift,
+			   &vcpu->arch.virtual_tsc_mult);
+	vcpu->arch.virtual_tsc_khz = this_tsc_khz;
+
+	/*
+	 * Compute the variation in TSC rate which is acceptable
+	 * within the range of tolerance and decide if the
+	 * rate being applied is within that bounds of the hardware
+	 * rate.  If so, no scaling or compensation need be done.
+	 */
+	thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm);
+	thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm);
+	if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) {
+		pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi);
+		use_scaling = 1;
+	}
+	kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling);
 }
 
 static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
 {
-	u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.last_tsc_nsec,
-				      vcpu->arch.tsc_catchup_mult,
-				      vcpu->arch.tsc_catchup_shift);
-	tsc += vcpu->arch.last_tsc_write;
+	u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec,
+				      vcpu->arch.virtual_tsc_mult,
+				      vcpu->arch.virtual_tsc_shift);
+	tsc += vcpu->arch.this_tsc_write;
 	return tsc;
 }
 
@@ -1021,48 +1026,88 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 	struct kvm *kvm = vcpu->kvm;
 	u64 offset, ns, elapsed;
 	unsigned long flags;
-	s64 sdiff;
+	s64 usdiff;
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
 	offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
 	ns = get_kernel_ns();
 	elapsed = ns - kvm->arch.last_tsc_nsec;
-	sdiff = data - kvm->arch.last_tsc_write;
-	if (sdiff < 0)
-		sdiff = -sdiff;
+
+	/* n.b - signed multiplication and division required */
+	usdiff = data - kvm->arch.last_tsc_write;
+#ifdef CONFIG_X86_64
+	usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
+#else
+	/* do_div() only does unsigned */
+	asm("idivl %2; xor %%edx, %%edx"
+	    : "=A"(usdiff)
+	    : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
+#endif
+	do_div(elapsed, 1000);
+	usdiff -= elapsed;
+	if (usdiff < 0)
+		usdiff = -usdiff;
 
 	/*
-	 * Special case: close write to TSC within 5 seconds of
-	 * another CPU is interpreted as an attempt to synchronize
-	 * The 5 seconds is to accommodate host load / swapping as
-	 * well as any reset of TSC during the boot process.
-	 *
-	 * In that case, for a reliable TSC, we can match TSC offsets,
-	 * or make a best guest using elapsed value.
-	 */
-	if (sdiff < nsec_to_cycles(vcpu, 5ULL * NSEC_PER_SEC) &&
-	    elapsed < 5ULL * NSEC_PER_SEC) {
+	 * Special case: TSC write with a small delta (1 second) of virtual
+	 * cycle time against real time is interpreted as an attempt to
+	 * synchronize the CPU.
+         *
+	 * For a reliable TSC, we can match TSC offsets, and for an unstable
+	 * TSC, we add elapsed time in this computation.  We could let the
+	 * compensation code attempt to catch up if we fall behind, but
+	 * it's better to try to match offsets from the beginning.
+         */
+	if (usdiff < USEC_PER_SEC &&
+	    vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
 		if (!check_tsc_unstable()) {
-			offset = kvm->arch.last_tsc_offset;
+			offset = kvm->arch.cur_tsc_offset;
 			pr_debug("kvm: matched tsc offset for %llu\n", data);
 		} else {
 			u64 delta = nsec_to_cycles(vcpu, elapsed);
-			offset += delta;
+			data += delta;
+			offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
 			pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
 		}
-		ns = kvm->arch.last_tsc_nsec;
+	} else {
+		/*
+		 * We split periods of matched TSC writes into generations.
+		 * For each generation, we track the original measured
+		 * nanosecond time, offset, and write, so if TSCs are in
+		 * sync, we can match exact offset, and if not, we can match
+		 * exact software computaion in compute_guest_tsc()
+		 *
+		 * These values are tracked in kvm->arch.cur_xxx variables.
+		 */
+		kvm->arch.cur_tsc_generation++;
+		kvm->arch.cur_tsc_nsec = ns;
+		kvm->arch.cur_tsc_write = data;
+		kvm->arch.cur_tsc_offset = offset;
+		pr_debug("kvm: new tsc generation %u, clock %llu\n",
+			 kvm->arch.cur_tsc_generation, data);
 	}
+
+	/*
+	 * We also track th most recent recorded KHZ, write and time to
+	 * allow the matching interval to be extended at each write.
+	 */
 	kvm->arch.last_tsc_nsec = ns;
 	kvm->arch.last_tsc_write = data;
-	kvm->arch.last_tsc_offset = offset;
-	kvm_x86_ops->write_tsc_offset(vcpu, offset);
-	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+	kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;
 
 	/* Reset of TSC must disable overshoot protection below */
 	vcpu->arch.hv_clock.tsc_timestamp = 0;
-	vcpu->arch.last_tsc_write = data;
-	vcpu->arch.last_tsc_nsec = ns;
+	vcpu->arch.last_guest_tsc = data;
+
+	/* Keep track of which generation this VCPU has synchronized to */
+	vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation;
+	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
+	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
+
+	kvm_x86_ops->write_tsc_offset(vcpu, offset);
+	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 }
+
 EXPORT_SYMBOL_GPL(kvm_write_tsc);
 
 static int kvm_guest_time_update(struct kvm_vcpu *v)
@@ -1078,7 +1123,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	local_irq_save(flags);
 	tsc_timestamp = kvm_x86_ops->read_l1_tsc(v);
 	kernel_ns = get_kernel_ns();
-	this_tsc_khz = vcpu_tsc_khz(v);
+	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
 	if (unlikely(this_tsc_khz == 0)) {
 		local_irq_restore(flags);
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
@@ -1098,7 +1143,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	if (vcpu->tsc_catchup) {
 		u64 tsc = compute_guest_tsc(v, kernel_ns);
 		if (tsc > tsc_timestamp) {
-			kvm_x86_ops->adjust_tsc_offset(v, tsc - tsc_timestamp);
+			adjust_tsc_offset_guest(v, tsc - tsc_timestamp);
 			tsc_timestamp = tsc;
 		}
 	}
@@ -1130,7 +1175,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 * observed by the guest and ensure the new system time is greater.
 	 */
 	max_kernel_ns = 0;
-	if (vcpu->hv_clock.tsc_timestamp && vcpu->last_guest_tsc) {
+	if (vcpu->hv_clock.tsc_timestamp) {
 		max_kernel_ns = vcpu->last_guest_tsc -
 				vcpu->hv_clock.tsc_timestamp;
 		max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
@@ -1504,6 +1549,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	case MSR_K7_HWCR:
 		data &= ~(u64)0x40;	/* ignore flush filter disable */
 		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
+		data &= ~(u64)0x8;	/* ignore TLB cache disable */
 		if (data != 0) {
 			pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
 				data);
@@ -1676,6 +1722,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		 */
 		pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data);
 		break;
+	case MSR_AMD64_OSVW_ID_LENGTH:
+		if (!guest_cpuid_has_osvw(vcpu))
+			return 1;
+		vcpu->arch.osvw.length = data;
+		break;
+	case MSR_AMD64_OSVW_STATUS:
+		if (!guest_cpuid_has_osvw(vcpu))
+			return 1;
+		vcpu->arch.osvw.status = data;
+		break;
 	default:
 		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
 			return xen_hvm_config(vcpu, data);
@@ -1960,6 +2016,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		 */
 		data = 0xbe702111;
 		break;
+	case MSR_AMD64_OSVW_ID_LENGTH:
+		if (!guest_cpuid_has_osvw(vcpu))
+			return 1;
+		data = vcpu->arch.osvw.length;
+		break;
+	case MSR_AMD64_OSVW_STATUS:
+		if (!guest_cpuid_has_osvw(vcpu))
+			return 1;
+		data = vcpu->arch.osvw.status;
+		break;
 	default:
 		if (kvm_pmu_msr(vcpu, msr))
 			return kvm_pmu_get_msr(vcpu, msr, pdata);
@@ -2080,6 +2146,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_XSAVE:
 	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_GET_TSC_KHZ:
+	case KVM_CAP_PCI_2_3:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -2214,19 +2281,23 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
-	if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
-		/* Make sure TSC doesn't go backwards */
-		s64 tsc_delta;
-		u64 tsc;
 
-		tsc = kvm_x86_ops->read_l1_tsc(vcpu);
-		tsc_delta = !vcpu->arch.last_guest_tsc ? 0 :
-			     tsc - vcpu->arch.last_guest_tsc;
+	/* Apply any externally detected TSC adjustments (due to suspend) */
+	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
+		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+		vcpu->arch.tsc_offset_adjustment = 0;
+		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+	}
 
+	if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
+		s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
+				native_read_tsc() - vcpu->arch.last_host_tsc;
 		if (tsc_delta < 0)
 			mark_tsc_unstable("KVM discovered backwards TSC");
 		if (check_tsc_unstable()) {
-			kvm_x86_ops->adjust_tsc_offset(vcpu, -tsc_delta);
+			u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu,
+						vcpu->arch.last_guest_tsc);
+			kvm_x86_ops->write_tsc_offset(vcpu, offset);
 			vcpu->arch.tsc_catchup = 1;
 		}
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2243,7 +2314,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
-	vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu);
+	vcpu->arch.last_host_tsc = native_read_tsc();
 }
 
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
@@ -2785,26 +2856,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		u32 user_tsc_khz;
 
 		r = -EINVAL;
-		if (!kvm_has_tsc_control)
-			break;
-
 		user_tsc_khz = (u32)arg;
 
 		if (user_tsc_khz >= kvm_max_guest_tsc_khz)
 			goto out;
 
-		kvm_x86_ops->set_tsc_khz(vcpu, user_tsc_khz);
+		if (user_tsc_khz == 0)
+			user_tsc_khz = tsc_khz;
+
+		kvm_set_tsc_khz(vcpu, user_tsc_khz);
 
 		r = 0;
 		goto out;
 	}
 	case KVM_GET_TSC_KHZ: {
-		r = -EIO;
-		if (check_tsc_unstable())
-			goto out;
-
-		r = vcpu_tsc_khz(vcpu);
-
+		r = vcpu->arch.virtual_tsc_khz;
 		goto out;
 	}
 	default:
@@ -2815,6 +2881,11 @@ out:
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
 static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr)
 {
 	int ret;
@@ -2998,6 +3069,8 @@ static void write_protect_slot(struct kvm *kvm,
 			       unsigned long *dirty_bitmap,
 			       unsigned long nr_dirty_pages)
 {
+	spin_lock(&kvm->mmu_lock);
+
 	/* Not many dirty pages compared to # of shadow pages. */
 	if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) {
 		unsigned long gfn_offset;
@@ -3005,16 +3078,13 @@ static void write_protect_slot(struct kvm *kvm,
 		for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) {
 			unsigned long gfn = memslot->base_gfn + gfn_offset;
 
-			spin_lock(&kvm->mmu_lock);
 			kvm_mmu_rmap_write_protect(kvm, gfn, memslot);
-			spin_unlock(&kvm->mmu_lock);
 		}
 		kvm_flush_remote_tlbs(kvm);
-	} else {
-		spin_lock(&kvm->mmu_lock);
+	} else
 		kvm_mmu_slot_remove_write_access(kvm, memslot->id);
-		spin_unlock(&kvm->mmu_lock);
-	}
+
+	spin_unlock(&kvm->mmu_lock);
 }
 
 /*
@@ -3133,6 +3203,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EEXIST;
 		if (kvm->arch.vpic)
 			goto create_irqchip_unlock;
+		r = -EINVAL;
+		if (atomic_read(&kvm->online_vcpus))
+			goto create_irqchip_unlock;
 		r = -ENOMEM;
 		vpic = kvm_create_pic(kvm);
 		if (vpic) {
@@ -4063,6 +4136,11 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val)
 	return res;
 }
 
+static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val)
+{
+	kvm_set_rflags(emul_to_vcpu(ctxt), val);
+}
+
 static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt)
 {
 	return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt));
@@ -4244,6 +4322,7 @@ static struct x86_emulate_ops emulate_ops = {
 	.set_idt	     = emulator_set_idt,
 	.get_cr              = emulator_get_cr,
 	.set_cr              = emulator_set_cr,
+	.set_rflags          = emulator_set_rflags,
 	.cpl                 = emulator_get_cpl,
 	.get_dr              = emulator_get_dr,
 	.set_dr              = emulator_set_dr,
@@ -5288,6 +5367,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		profile_hit(KVM_PROFILING, (void *)rip);
 	}
 
+	if (unlikely(vcpu->arch.tsc_always_catchup))
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 
 	kvm_lapic_sync_from_vapic(vcpu);
 
@@ -5587,15 +5668,15 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
-		    bool has_error_code, u32 error_code)
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
+		    int reason, bool has_error_code, u32 error_code)
 {
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 	int ret;
 
 	init_emulate_ctxt(vcpu);
 
-	ret = emulator_task_switch(ctxt, tss_selector, reason,
+	ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason,
 				   has_error_code, error_code);
 
 	if (ret)
@@ -5928,13 +6009,88 @@ int kvm_arch_hardware_enable(void *garbage)
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
 	int i;
+	int ret;
+	u64 local_tsc;
+	u64 max_tsc = 0;
+	bool stable, backwards_tsc = false;
 
 	kvm_shared_msr_cpu_online();
-	list_for_each_entry(kvm, &vm_list, vm_list)
-		kvm_for_each_vcpu(i, vcpu, kvm)
-			if (vcpu->cpu == smp_processor_id())
-				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
-	return kvm_x86_ops->hardware_enable(garbage);
+	ret = kvm_x86_ops->hardware_enable(garbage);
+	if (ret != 0)
+		return ret;
+
+	local_tsc = native_read_tsc();
+	stable = !check_tsc_unstable();
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			if (!stable && vcpu->cpu == smp_processor_id())
+				set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+			if (stable && vcpu->arch.last_host_tsc > local_tsc) {
+				backwards_tsc = true;
+				if (vcpu->arch.last_host_tsc > max_tsc)
+					max_tsc = vcpu->arch.last_host_tsc;
+			}
+		}
+	}
+
+	/*
+	 * Sometimes, even reliable TSCs go backwards.  This happens on
+	 * platforms that reset TSC during suspend or hibernate actions, but
+	 * maintain synchronization.  We must compensate.  Fortunately, we can
+	 * detect that condition here, which happens early in CPU bringup,
+	 * before any KVM threads can be running.  Unfortunately, we can't
+	 * bring the TSCs fully up to date with real time, as we aren't yet far
+	 * enough into CPU bringup that we know how much real time has actually
+	 * elapsed; our helper function, get_kernel_ns() will be using boot
+	 * variables that haven't been updated yet.
+	 *
+	 * So we simply find the maximum observed TSC above, then record the
+	 * adjustment to TSC in each VCPU.  When the VCPU later gets loaded,
+	 * the adjustment will be applied.  Note that we accumulate
+	 * adjustments, in case multiple suspend cycles happen before some VCPU
+	 * gets a chance to run again.  In the event that no KVM threads get a
+	 * chance to run, we will miss the entire elapsed period, as we'll have
+	 * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may
+	 * loose cycle time.  This isn't too big a deal, since the loss will be
+	 * uniform across all VCPUs (not to mention the scenario is extremely
+	 * unlikely). It is possible that a second hibernate recovery happens
+	 * much faster than a first, causing the observed TSC here to be
+	 * smaller; this would require additional padding adjustment, which is
+	 * why we set last_host_tsc to the local tsc observed here.
+	 *
+	 * N.B. - this code below runs only on platforms with reliable TSC,
+	 * as that is the only way backwards_tsc is set above.  Also note
+	 * that this runs for ALL vcpus, which is not a bug; all VCPUs should
+	 * have the same delta_cyc adjustment applied if backwards_tsc
+	 * is detected.  Note further, this adjustment is only done once,
+	 * as we reset last_host_tsc on all VCPUs to stop this from being
+	 * called multiple times (one for each physical CPU bringup).
+	 *
+	 * Platforms with unnreliable TSCs don't have to deal with this, they
+	 * will be compensated by the logic in vcpu_load, which sets the TSC to
+	 * catchup mode.  This will catchup all VCPUs to real time, but cannot
+	 * guarantee that they stay in perfect synchronization.
+	 */
+	if (backwards_tsc) {
+		u64 delta_cyc = max_tsc - local_tsc;
+		list_for_each_entry(kvm, &vm_list, vm_list) {
+			kvm_for_each_vcpu(i, vcpu, kvm) {
+				vcpu->arch.tsc_offset_adjustment += delta_cyc;
+				vcpu->arch.last_host_tsc = local_tsc;
+			}
+
+			/*
+			 * We have to disable TSC offset matching.. if you were
+			 * booting a VM while issuing an S4 host suspend....
+			 * you may have some problem.  Solving this issue is
+			 * left as an exercise to the reader.
+			 */
+			kvm->arch.last_tsc_nsec = 0;
+			kvm->arch.last_tsc_write = 0;
+		}
+
+	}
+	return 0;
 }
 
 void kvm_arch_hardware_disable(void *garbage)
@@ -5958,6 +6114,11 @@ void kvm_arch_check_processor_compat(void *rtn)
 	kvm_x86_ops->check_processor_compatibility(rtn);
 }
 
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
+{
+	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct page *page;
@@ -5980,7 +6141,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	}
 	vcpu->arch.pio_data = page_address(page);
 
-	kvm_init_tsc_catchup(vcpu, max_tsc_khz);
+	kvm_set_tsc_khz(vcpu, max_tsc_khz);
 
 	r = kvm_mmu_create(vcpu);
 	if (r < 0)
@@ -6032,8 +6193,11 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 	free_page((unsigned long)vcpu->arch.pio_data);
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+	if (type)
+		return -EINVAL;
+
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
@@ -6093,6 +6257,65 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		put_page(kvm->arch.ept_identity_pagetable);
 }
 
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+	int i;
+
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) {
+			vfree(free->arch.lpage_info[i]);
+			free->arch.lpage_info[i] = NULL;
+		}
+	}
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	int i;
+
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		unsigned long ugfn;
+		int lpages;
+		int level = i + 2;
+
+		lpages = gfn_to_index(slot->base_gfn + npages - 1,
+				      slot->base_gfn, level) + 1;
+
+		slot->arch.lpage_info[i] =
+			vzalloc(lpages * sizeof(*slot->arch.lpage_info[i]));
+		if (!slot->arch.lpage_info[i])
+			goto out_free;
+
+		if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
+			slot->arch.lpage_info[i][0].write_count = 1;
+		if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
+			slot->arch.lpage_info[i][lpages - 1].write_count = 1;
+		ugfn = slot->userspace_addr >> PAGE_SHIFT;
+		/*
+		 * If the gfn and userspace address are not aligned wrt each
+		 * other, or if explicitly asked to, disable large page
+		 * support for this slot
+		 */
+		if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) ||
+		    !kvm_largepages_enabled()) {
+			unsigned long j;
+
+			for (j = 0; j < lpages; ++j)
+				slot->arch.lpage_info[i][j].write_count = 1;
+		}
+	}
+
+	return 0;
+
+out_free:
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		vfree(slot->arch.lpage_info[i]);
+		slot->arch.lpage_info[i] = NULL;
+	}
+	return -ENOMEM;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_memory_slot old,
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 7718541541d4..9b868124128d 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -28,6 +28,7 @@
 #include <linux/regset.h>
 
 #include <asm/uaccess.h>
+#include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/user.h>
 #include <asm/i387.h>
@@ -269,7 +270,7 @@ void math_emulate(struct math_emu_info *info)
 			FPU_EIP = FPU_ORIG_EIP;	/* Point to current FPU instruction. */
 
 			RE_ENTRANT_CHECK_OFF;
-			current->thread.trap_no = 16;
+			current->thread.trap_nr = X86_TRAP_MF;
 			current->thread.error_code = 0;
 			send_sig(SIGFPE, current, 1);
 			return;
@@ -662,7 +663,7 @@ static int valid_prefix(u_char *Byte, u_char __user **fpu_eip,
 void math_abort(struct math_emu_info *info, unsigned int signal)
 {
 	FPU_EIP = FPU_ORIG_EIP;
-	current->thread.trap_no = 16;
+	current->thread.trap_nr = X86_TRAP_MF;
 	current->thread.error_code = 0;
 	send_sig(signal, current, 1);
 	RE_ENTRANT_CHECK_OFF;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f0b4caf85c1a..3ecfd1aaf214 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -615,7 +615,7 @@ pgtable_bad(struct pt_regs *regs, unsigned long error_code,
 	dump_pagetable(address);
 
 	tsk->thread.cr2		= address;
-	tsk->thread.trap_no	= 14;
+	tsk->thread.trap_nr	= X86_TRAP_PF;
 	tsk->thread.error_code	= error_code;
 
 	if (__die("Bad pagetable", regs, error_code))
@@ -636,7 +636,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs)) {
 		if (current_thread_info()->sig_on_uaccess_error && signal) {
-			tsk->thread.trap_no = 14;
+			tsk->thread.trap_nr = X86_TRAP_PF;
 			tsk->thread.error_code = error_code | PF_USER;
 			tsk->thread.cr2 = address;
 
@@ -676,7 +676,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	tsk->thread.cr2		= address;
-	tsk->thread.trap_no	= 14;
+	tsk->thread.trap_nr	= X86_TRAP_PF;
 	tsk->thread.error_code	= error_code;
 
 	sig = SIGKILL;
@@ -754,7 +754,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		/* Kernel addresses are always protection faults: */
 		tsk->thread.cr2		= address;
 		tsk->thread.error_code	= error_code | (address >= TASK_SIZE);
-		tsk->thread.trap_no	= 14;
+		tsk->thread.trap_nr	= X86_TRAP_PF;
 
 		force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);
 
@@ -838,7 +838,7 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 
 	tsk->thread.cr2		= address;
 	tsk->thread.error_code	= error_code;
-	tsk->thread.trap_no	= 14;
+	tsk->thread.trap_nr	= X86_TRAP_PF;
 
 #ifdef CONFIG_MEMORY_FAILURE
 	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 6cabf6570d64..4f0cec7e4ffb 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -12,7 +12,6 @@
 #include <asm/page_types.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include <asm/proto.h>
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8663f6c47ccb..575d86f85ce4 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -35,7 +35,6 @@
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/dma.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 436a0309db33..fc18be0f6f29 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -35,7 +35,6 @@
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index cac718499256..a69bcb8c7621 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -10,7 +10,6 @@
 #include <linux/spinlock.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1c1c4f46a7c1..efb5b4b93711 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -70,7 +70,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 		return;
 	pxm = pa->proximity_domain;
 	apic_id = pa->apic_id;
-	if (!cpu_has_x2apic && (apic_id >= 0xff)) {
+	if (!apic->apic_id_valid(apic_id)) {
 		printk(KERN_INFO "SRAT: PXM %u -> X2APIC 0x%04x ignored\n",
 			 pxm, apic_id);
 		return;
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 66870223f8c5..877b9a1b2152 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -18,17 +18,17 @@
  * r9d : hlen = skb->len - skb->data_len
  */
 #define SKBDATA	%r8
-
-sk_load_word_ind:
-	.globl	sk_load_word_ind
-
-	add	%ebx,%esi	/* offset += X */
-#	test    %esi,%esi	/* if (offset < 0) goto bpf_error; */
-	js	bpf_error
+#define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
 
 sk_load_word:
 	.globl	sk_load_word
 
+	test	%esi,%esi
+	js	bpf_slow_path_word_neg
+
+sk_load_word_positive_offset:
+	.globl	sk_load_word_positive_offset
+
 	mov	%r9d,%eax		# hlen
 	sub	%esi,%eax		# hlen - offset
 	cmp	$3,%eax
@@ -37,16 +37,15 @@ sk_load_word:
 	bswap   %eax  			/* ntohl() */
 	ret
 
-
-sk_load_half_ind:
-	.globl sk_load_half_ind
-
-	add	%ebx,%esi	/* offset += X */
-	js	bpf_error
-
 sk_load_half:
 	.globl	sk_load_half
 
+	test	%esi,%esi
+	js	bpf_slow_path_half_neg
+
+sk_load_half_positive_offset:
+	.globl	sk_load_half_positive_offset
+
 	mov	%r9d,%eax
 	sub	%esi,%eax		#	hlen - offset
 	cmp	$1,%eax
@@ -55,14 +54,15 @@ sk_load_half:
 	rol	$8,%ax			# ntohs()
 	ret
 
-sk_load_byte_ind:
-	.globl sk_load_byte_ind
-	add	%ebx,%esi	/* offset += X */
-	js	bpf_error
-
 sk_load_byte:
 	.globl	sk_load_byte
 
+	test	%esi,%esi
+	js	bpf_slow_path_byte_neg
+
+sk_load_byte_positive_offset:
+	.globl	sk_load_byte_positive_offset
+
 	cmp	%esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
 	jle	bpf_slow_path_byte
 	movzbl	(SKBDATA,%rsi),%eax
@@ -73,25 +73,21 @@ sk_load_byte:
  *
  * Implements BPF_S_LDX_B_MSH : ldxb  4*([offset]&0xf)
  * Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value, already known positive
+ * Inputs : %esi is the offset value
  */
-ENTRY(sk_load_byte_msh)
-	CFI_STARTPROC
+sk_load_byte_msh:
+	.globl	sk_load_byte_msh
+	test	%esi,%esi
+	js	bpf_slow_path_byte_msh_neg
+
+sk_load_byte_msh_positive_offset:
+	.globl	sk_load_byte_msh_positive_offset
 	cmp	%esi,%r9d      /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
 	jle	bpf_slow_path_byte_msh
 	movzbl	(SKBDATA,%rsi),%ebx
 	and	$15,%bl
 	shl	$2,%bl
 	ret
-	CFI_ENDPROC
-ENDPROC(sk_load_byte_msh)
-
-bpf_error:
-# force a return 0 from jit handler
-	xor		%eax,%eax
-	mov		-8(%rbp),%rbx
-	leaveq
-	ret
 
 /* rsi contains offset and can be scratched */
 #define bpf_slow_path_common(LEN)		\
@@ -138,3 +134,67 @@ bpf_slow_path_byte_msh:
 	shl	$2,%al
 	xchg	%eax,%ebx
 	ret
+
+#define sk_negative_common(SIZE)				\
+	push	%rdi;	/* save skb */				\
+	push	%r9;						\
+	push	SKBDATA;					\
+/* rsi already has offset */					\
+	mov	$SIZE,%ecx;	/* size */			\
+	call	bpf_internal_load_pointer_neg_helper;		\
+	test	%rax,%rax;					\
+	pop	SKBDATA;					\
+	pop	%r9;						\
+	pop	%rdi;						\
+	jz	bpf_error
+
+
+bpf_slow_path_word_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
+	jl	bpf_error	/* offset lower -> error  */
+sk_load_word_negative_offset:
+	.globl	sk_load_word_negative_offset
+	sk_negative_common(4)
+	mov	(%rax), %eax
+	bswap	%eax
+	ret
+
+bpf_slow_path_half_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_half_negative_offset:
+	.globl	sk_load_half_negative_offset
+	sk_negative_common(2)
+	mov	(%rax),%ax
+	rol	$8,%ax
+	movzwl	%ax,%eax
+	ret
+
+bpf_slow_path_byte_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_byte_negative_offset:
+	.globl	sk_load_byte_negative_offset
+	sk_negative_common(1)
+	movzbl	(%rax), %eax
+	ret
+
+bpf_slow_path_byte_msh_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_byte_msh_negative_offset:
+	.globl	sk_load_byte_msh_negative_offset
+	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
+	sk_negative_common(1)
+	movzbl	(%rax),%eax
+	and	$15,%al
+	shl	$2,%al
+	xchg	%eax,%ebx
+	ret
+
+bpf_error:
+# force a return 0 from jit handler
+	xor		%eax,%eax
+	mov		-8(%rbp),%rbx
+	leaveq
+	ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5a5b6e4dd738..0597f95b6da6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -30,7 +30,10 @@ int bpf_jit_enable __read_mostly;
  * assembly code in arch/x86/net/bpf_jit.S
  */
 extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
-extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[];
+extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
+extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
+extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
 
 static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -117,6 +120,8 @@ static inline void bpf_flush_icache(void *start, void *end)
 	set_fs(old_fs);
 }
 
+#define CHOOSE_LOAD_FUNC(K, func) \
+	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
 void bpf_jit_compile(struct sk_filter *fp)
 {
@@ -473,44 +478,46 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
 				break;
 			case BPF_S_LD_W_ABS:
-				func = sk_load_word;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 common_load:			seen |= SEEN_DATAREF;
-				if ((int)K < 0) {
-					/* Abort the JIT because __load_pointer() is needed. */
-					goto out;
-				}
 				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K); /* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call */
 				break;
 			case BPF_S_LD_H_ABS:
-				func = sk_load_half;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_half);
 				goto common_load;
 			case BPF_S_LD_B_ABS:
-				func = sk_load_byte;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
 				goto common_load;
 			case BPF_S_LDX_B_MSH:
-				if ((int)K < 0) {
-					/* Abort the JIT because __load_pointer() is needed. */
-					goto out;
-				}
+				func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 				seen |= SEEN_DATAREF | SEEN_XREG;
-				t_offset = sk_load_byte_msh - (image + addrs[i]);
+				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K);	/* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
 				break;
 			case BPF_S_LD_W_IND:
-				func = sk_load_word_ind;
+				func = sk_load_word;
 common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 				t_offset = func - (image + addrs[i]);
-				EMIT1_off32(0xbe, K);	/* mov imm32,%esi   */
+				if (K) {
+					if (is_imm8(K)) {
+						EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */
+					} else {
+						EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
+						EMIT(K, 4);
+					}
+				} else {
+					EMIT2(0x89,0xde); /* mov %ebx,%esi */
+				}
 				EMIT1_off32(0xe8, t_offset);	/* call sk_load_xxx_ind */
 				break;
 			case BPF_S_LD_H_IND:
-				func = sk_load_half_ind;
+				func = sk_load_half;
 				goto common_load_ind;
 			case BPF_S_LD_B_IND:
-				func = sk_load_byte_ind;
+				func = sk_load_byte;
 				goto common_load_ind;
 			case BPF_S_JMP_JA:
 				t_offset = addrs[i + K] - addrs[i];
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index bff89dfe3619..d6aa6e8315d1 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -67,7 +67,7 @@ x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
 {
 	struct stack_frame_ia32 *head;
 
-	/* User process is 32-bit */
+	/* User process is IA32 */
 	if (!current || !test_thread_flag(TIF_IA32))
 		return 0;
 
diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts
index e70be38ce039..ce874f872cc6 100644
--- a/arch/x86/platform/ce4100/falconfalls.dts
+++ b/arch/x86/platform/ce4100/falconfalls.dts
@@ -208,16 +208,19 @@
 					interrupts = <14 1>;
 				};
 
-				gpio@b,1 {
+				pcigpio: gpio@b,1 {
+					#gpio-cells = <2>;
+					#interrupt-cells = <2>;
 					compatible = "pci8086,2e67.2",
 						   "pci8086,2e67",
 						   "pciclassff0000",
 						   "pciclassff00";
 
-					#gpio-cells = <2>;
 					reg = <0x15900 0x0 0x0 0x0 0x0>;
 					interrupts = <15 1>;
+					interrupt-controller;
 					gpio-controller;
+					intel,muxctl = <0>;
 				};
 
 				i2c-controller@b,2 {
diff --git a/arch/x86/platform/geode/Makefile b/arch/x86/platform/geode/Makefile
index 246b788847ff..5b51194f4c8d 100644
--- a/arch/x86/platform/geode/Makefile
+++ b/arch/x86/platform/geode/Makefile
@@ -1,2 +1,3 @@
 obj-$(CONFIG_ALIX)		+= alix.o
 obj-$(CONFIG_NET5501)		+= net5501.o
+obj-$(CONFIG_GEOS)		+= geos.o
diff --git a/arch/x86/platform/geode/geos.c b/arch/x86/platform/geode/geos.c
new file mode 100644
index 000000000000..c2e6d53558be
--- /dev/null
+++ b/arch/x86/platform/geode/geos.c
@@ -0,0 +1,128 @@
+/*
+ * System Specific setup for Traverse Technologies GEOS.
+ * At the moment this means setup of GPIO control of LEDs.
+ *
+ * Copyright (C) 2008 Constantin Baranov <const@mimas.ru>
+ * Copyright (C) 2011 Ed Wildgoose <kernel@wildgooses.com>
+ *                and Philip Prindeville <philipp@redfish-solutions.com>
+ *
+ * TODO: There are large similarities with leds-net5501.c
+ * by Alessandro Zummo <a.zummo@towertech.it>
+ * In the future leds-net5501.c should be migrated over to platform
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/leds.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+#include <linux/input.h>
+#include <linux/gpio_keys.h>
+#include <linux/dmi.h>
+
+#include <asm/geode.h>
+
+static struct gpio_keys_button geos_gpio_buttons[] = {
+	{
+		.code = KEY_RESTART,
+		.gpio = 3,
+		.active_low = 1,
+		.desc = "Reset button",
+		.type = EV_KEY,
+		.wakeup = 0,
+		.debounce_interval = 100,
+		.can_disable = 0,
+	}
+};
+static struct gpio_keys_platform_data geos_buttons_data = {
+	.buttons = geos_gpio_buttons,
+	.nbuttons = ARRAY_SIZE(geos_gpio_buttons),
+	.poll_interval = 20,
+};
+
+static struct platform_device geos_buttons_dev = {
+	.name = "gpio-keys-polled",
+	.id = 1,
+	.dev = {
+		.platform_data = &geos_buttons_data,
+	}
+};
+
+static struct gpio_led geos_leds[] = {
+	{
+		.name = "geos:1",
+		.gpio = 6,
+		.default_trigger = "default-on",
+		.active_low = 1,
+	},
+	{
+		.name = "geos:2",
+		.gpio = 25,
+		.default_trigger = "default-off",
+		.active_low = 1,
+	},
+	{
+		.name = "geos:3",
+		.gpio = 27,
+		.default_trigger = "default-off",
+		.active_low = 1,
+	},
+};
+
+static struct gpio_led_platform_data geos_leds_data = {
+	.num_leds = ARRAY_SIZE(geos_leds),
+	.leds = geos_leds,
+};
+
+static struct platform_device geos_leds_dev = {
+	.name = "leds-gpio",
+	.id = -1,
+	.dev.platform_data = &geos_leds_data,
+};
+
+static struct __initdata platform_device *geos_devs[] = {
+	&geos_buttons_dev,
+	&geos_leds_dev,
+};
+
+static void __init register_geos(void)
+{
+	/* Setup LED control through leds-gpio driver */
+	platform_add_devices(geos_devs, ARRAY_SIZE(geos_devs));
+}
+
+static int __init geos_init(void)
+{
+	const char *vendor, *product;
+
+	if (!is_geode())
+		return 0;
+
+	vendor = dmi_get_system_info(DMI_SYS_VENDOR);
+	if (!vendor || strcmp(vendor, "Traverse Technologies"))
+		return 0;
+
+	product = dmi_get_system_info(DMI_PRODUCT_NAME);
+	if (!product || strcmp(product, "Geos"))
+		return 0;
+
+	printk(KERN_INFO "%s: system is recognized as \"%s %s\"\n",
+	       KBUILD_MODNAME, vendor, product);
+
+	register_geos();
+
+	return 0;
+}
+
+module_init(geos_init);
+
+MODULE_AUTHOR("Philip Prindeville <philipp@redfish-solutions.com>");
+MODULE_DESCRIPTION("Traverse Technologies Geos System Setup");
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index 7cce722667b8..a4bee53c2e54 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -20,6 +20,8 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/syscore_ops.h>
+#include <linux/debugfs.h>
+#include <linux/mutex.h>
 
 #include <asm/geode.h>
 #include <asm/setup.h>
@@ -31,6 +33,15 @@ EXPORT_SYMBOL_GPL(olpc_platform_info);
 
 static DEFINE_SPINLOCK(ec_lock);
 
+/* debugfs interface to EC commands */
+#define EC_MAX_CMD_ARGS (5 + 1)	/* cmd byte + 5 args */
+#define EC_MAX_CMD_REPLY (8)
+
+static struct dentry *ec_debugfs_dir;
+static DEFINE_MUTEX(ec_debugfs_cmd_lock);
+static unsigned char ec_debugfs_resp[EC_MAX_CMD_REPLY];
+static unsigned int ec_debugfs_resp_bytes;
+
 /* EC event mask to be applied during suspend (defining wakeup sources). */
 static u16 ec_wakeup_mask;
 
@@ -269,6 +280,91 @@ int olpc_ec_sci_query(u16 *sci_value)
 }
 EXPORT_SYMBOL_GPL(olpc_ec_sci_query);
 
+static ssize_t ec_debugfs_cmd_write(struct file *file, const char __user *buf,
+				    size_t size, loff_t *ppos)
+{
+	int i, m;
+	unsigned char ec_cmd[EC_MAX_CMD_ARGS];
+	unsigned int ec_cmd_int[EC_MAX_CMD_ARGS];
+	char cmdbuf[64];
+	int ec_cmd_bytes;
+
+	mutex_lock(&ec_debugfs_cmd_lock);
+
+	size = simple_write_to_buffer(cmdbuf, sizeof(cmdbuf), ppos, buf, size);
+
+	m = sscanf(cmdbuf, "%x:%u %x %x %x %x %x", &ec_cmd_int[0],
+		   &ec_debugfs_resp_bytes,
+		   &ec_cmd_int[1], &ec_cmd_int[2], &ec_cmd_int[3],
+		   &ec_cmd_int[4], &ec_cmd_int[5]);
+	if (m < 2 || ec_debugfs_resp_bytes > EC_MAX_CMD_REPLY) {
+		/* reset to prevent overflow on read */
+		ec_debugfs_resp_bytes = 0;
+
+		printk(KERN_DEBUG "olpc-ec: bad ec cmd:  "
+		       "cmd:response-count [arg1 [arg2 ...]]\n");
+		size = -EINVAL;
+		goto out;
+	}
+
+	/* convert scanf'd ints to char */
+	ec_cmd_bytes = m - 2;
+	for (i = 0; i <= ec_cmd_bytes; i++)
+		ec_cmd[i] = ec_cmd_int[i];
+
+	printk(KERN_DEBUG "olpc-ec: debugfs cmd 0x%02x with %d args "
+	       "%02x %02x %02x %02x %02x, want %d returns\n",
+	       ec_cmd[0], ec_cmd_bytes, ec_cmd[1], ec_cmd[2], ec_cmd[3],
+	       ec_cmd[4], ec_cmd[5], ec_debugfs_resp_bytes);
+
+	olpc_ec_cmd(ec_cmd[0], (ec_cmd_bytes == 0) ? NULL : &ec_cmd[1],
+		    ec_cmd_bytes, ec_debugfs_resp, ec_debugfs_resp_bytes);
+
+	printk(KERN_DEBUG "olpc-ec: response "
+	       "%02x %02x %02x %02x %02x %02x %02x %02x (%d bytes expected)\n",
+	       ec_debugfs_resp[0], ec_debugfs_resp[1], ec_debugfs_resp[2],
+	       ec_debugfs_resp[3], ec_debugfs_resp[4], ec_debugfs_resp[5],
+	       ec_debugfs_resp[6], ec_debugfs_resp[7], ec_debugfs_resp_bytes);
+
+out:
+	mutex_unlock(&ec_debugfs_cmd_lock);
+	return size;
+}
+
+static ssize_t ec_debugfs_cmd_read(struct file *file, char __user *buf,
+				   size_t size, loff_t *ppos)
+{
+	unsigned int i, r;
+	char *rp;
+	char respbuf[64];
+
+	mutex_lock(&ec_debugfs_cmd_lock);
+	rp = respbuf;
+	rp += sprintf(rp, "%02x", ec_debugfs_resp[0]);
+	for (i = 1; i < ec_debugfs_resp_bytes; i++)
+		rp += sprintf(rp, ", %02x", ec_debugfs_resp[i]);
+	mutex_unlock(&ec_debugfs_cmd_lock);
+	rp += sprintf(rp, "\n");
+
+	r = rp - respbuf;
+	return simple_read_from_buffer(buf, size, ppos, respbuf, r);
+}
+
+static const struct file_operations ec_debugfs_genops = {
+	.write	 = ec_debugfs_cmd_write,
+	.read	 = ec_debugfs_cmd_read,
+};
+
+static void setup_debugfs(void)
+{
+	ec_debugfs_dir = debugfs_create_dir("olpc-ec", 0);
+	if (ec_debugfs_dir == ERR_PTR(-ENODEV))
+		return;
+
+	debugfs_create_file("cmd", 0600, ec_debugfs_dir, NULL,
+			    &ec_debugfs_genops);
+}
+
 static int olpc_ec_suspend(void)
 {
 	return olpc_ec_mask_write(ec_wakeup_mask);
@@ -372,6 +468,7 @@ static int __init olpc_init(void)
 	}
 
 	register_syscore_ops(&olpc_syscore_ops);
+	setup_debugfs();
 
 	return 0;
 }
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 4889655ba784..218cdb16163c 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -115,7 +115,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 void save_processor_state(void)
 {
 	__save_processor_state(&saved_context);
-	save_sched_clock_state();
+	x86_platform.save_sched_clock_state();
 }
 #ifdef CONFIG_X86_32
 EXPORT_SYMBOL(save_processor_state);
@@ -225,6 +225,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
 	fix_processor_context();
 
 	do_fpu_end();
+	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
 }
 
@@ -232,7 +233,6 @@ static void __restore_processor_state(struct saved_context *ctxt)
 void restore_processor_state(void)
 {
 	__restore_processor_state(&saved_context);
-	restore_sched_clock_state();
 }
 #ifdef CONFIG_X86_32
 EXPORT_SYMBOL(restore_processor_state);
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 3769079874d8..74202c1910cd 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -10,7 +10,6 @@
 #include <linux/suspend.h>
 #include <linux/bootmem.h>
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmzone.h>
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile
index 564b2476fede..3236aebc828d 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/syscalls/Makefile
@@ -10,8 +10,10 @@ syshdr := $(srctree)/$(src)/syscallhdr.sh
 systbl := $(srctree)/$(src)/syscalltbl.sh
 
 quiet_cmd_syshdr = SYSHDR  $@
-      cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' $< $@ \
-		   $(syshdr_abi_$(basetarget)) $(syshdr_pfx_$(basetarget))
+      cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \
+		   '$(syshdr_abi_$(basetarget))' \
+		   '$(syshdr_pfx_$(basetarget))' \
+		   '$(syshdr_offset_$(basetarget))'
 quiet_cmd_systbl = SYSTBL  $@
       cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@
 
@@ -24,18 +26,28 @@ syshdr_pfx_unistd_32_ia32 := ia32_
 $(out)/unistd_32_ia32.h: $(syscall32) $(syshdr)
 	$(call if_changed,syshdr)
 
-syshdr_abi_unistd_64 := 64
+syshdr_abi_unistd_x32 := common,x32
+syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT
+$(out)/unistd_x32.h: $(syscall64) $(syshdr)
+	$(call if_changed,syshdr)
+
+syshdr_abi_unistd_64 := common,64
 $(out)/unistd_64.h: $(syscall64) $(syshdr)
 	$(call if_changed,syshdr)
 
+syshdr_abi_unistd_64_x32 := x32
+syshdr_pfx_unistd_64_x32 := x32_
+$(out)/unistd_64_x32.h: $(syscall64) $(syshdr)
+	$(call if_changed,syshdr)
+
 $(out)/syscalls_32.h: $(syscall32) $(systbl)
 	$(call if_changed,systbl)
 $(out)/syscalls_64.h: $(syscall64) $(systbl)
 	$(call if_changed,systbl)
 
-syshdr-y			+= unistd_32.h unistd_64.h
+syshdr-y			+= unistd_32.h unistd_64.h unistd_x32.h
 syshdr-y			+= syscalls_32.h
-syshdr-$(CONFIG_X86_64)		+= unistd_32_ia32.h
+syshdr-$(CONFIG_X86_64)		+= unistd_32_ia32.h unistd_64_x32.h
 syshdr-$(CONFIG_X86_64)		+= syscalls_64.h
 
 targets	+= $(syshdr-y)
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index e7e67cc3c14b..29f9f0554f7d 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -181,7 +181,7 @@
 172	i386	prctl			sys_prctl
 173	i386	rt_sigreturn		ptregs_rt_sigreturn		stub32_rt_sigreturn
 174	i386	rt_sigaction		sys_rt_sigaction		sys32_rt_sigaction
-175	i386	rt_sigprocmask		sys_rt_sigprocmask		sys32_rt_sigprocmask
+175	i386	rt_sigprocmask		sys_rt_sigprocmask
 176	i386	rt_sigpending		sys_rt_sigpending		sys32_rt_sigpending
 177	i386	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait
 178	i386	rt_sigqueueinfo		sys_rt_sigqueueinfo		sys32_rt_sigqueueinfo
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index b440a8f7eefa..dd29a9ea27c5 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -4,317 +4,350 @@
 # The format is:
 # <number> <abi> <name> <entry point>
 #
-# The abi is always "64" for this file (for now.)
+# The abi is "common", "64" or "x32" for this file.
 #
-0	64	read			sys_read
-1	64	write			sys_write
-2	64	open			sys_open
-3	64	close			sys_close
-4	64	stat			sys_newstat
-5	64	fstat			sys_newfstat
-6	64	lstat			sys_newlstat
-7	64	poll			sys_poll
-8	64	lseek			sys_lseek
-9	64	mmap			sys_mmap
-10	64	mprotect		sys_mprotect
-11	64	munmap			sys_munmap
-12	64	brk			sys_brk
+0	common	read			sys_read
+1	common	write			sys_write
+2	common	open			sys_open
+3	common	close			sys_close
+4	common	stat			sys_newstat
+5	common	fstat			sys_newfstat
+6	common	lstat			sys_newlstat
+7	common	poll			sys_poll
+8	common	lseek			sys_lseek
+9	common	mmap			sys_mmap
+10	common	mprotect		sys_mprotect
+11	common	munmap			sys_munmap
+12	common	brk			sys_brk
 13	64	rt_sigaction		sys_rt_sigaction
-14	64	rt_sigprocmask		sys_rt_sigprocmask
+14	common	rt_sigprocmask		sys_rt_sigprocmask
 15	64	rt_sigreturn		stub_rt_sigreturn
 16	64	ioctl			sys_ioctl
-17	64	pread64			sys_pread64
-18	64	pwrite64		sys_pwrite64
+17	common	pread64			sys_pread64
+18	common	pwrite64		sys_pwrite64
 19	64	readv			sys_readv
 20	64	writev			sys_writev
-21	64	access			sys_access
-22	64	pipe			sys_pipe
-23	64	select			sys_select
-24	64	sched_yield		sys_sched_yield
-25	64	mremap			sys_mremap
-26	64	msync			sys_msync
-27	64	mincore			sys_mincore
-28	64	madvise			sys_madvise
-29	64	shmget			sys_shmget
-30	64	shmat			sys_shmat
-31	64	shmctl			sys_shmctl
-32	64	dup			sys_dup
-33	64	dup2			sys_dup2
-34	64	pause			sys_pause
-35	64	nanosleep		sys_nanosleep
-36	64	getitimer		sys_getitimer
-37	64	alarm			sys_alarm
-38	64	setitimer		sys_setitimer
-39	64	getpid			sys_getpid
-40	64	sendfile		sys_sendfile64
-41	64	socket			sys_socket
-42	64	connect			sys_connect
-43	64	accept			sys_accept
-44	64	sendto			sys_sendto
+21	common	access			sys_access
+22	common	pipe			sys_pipe
+23	common	select			sys_select
+24	common	sched_yield		sys_sched_yield
+25	common	mremap			sys_mremap
+26	common	msync			sys_msync
+27	common	mincore			sys_mincore
+28	common	madvise			sys_madvise
+29	common	shmget			sys_shmget
+30	common	shmat			sys_shmat
+31	common	shmctl			sys_shmctl
+32	common	dup			sys_dup
+33	common	dup2			sys_dup2
+34	common	pause			sys_pause
+35	common	nanosleep		sys_nanosleep
+36	common	getitimer		sys_getitimer
+37	common	alarm			sys_alarm
+38	common	setitimer		sys_setitimer
+39	common	getpid			sys_getpid
+40	common	sendfile		sys_sendfile64
+41	common	socket			sys_socket
+42	common	connect			sys_connect
+43	common	accept			sys_accept
+44	common	sendto			sys_sendto
 45	64	recvfrom		sys_recvfrom
 46	64	sendmsg			sys_sendmsg
 47	64	recvmsg			sys_recvmsg
-48	64	shutdown		sys_shutdown
-49	64	bind			sys_bind
-50	64	listen			sys_listen
-51	64	getsockname		sys_getsockname
-52	64	getpeername		sys_getpeername
-53	64	socketpair		sys_socketpair
-54	64	setsockopt		sys_setsockopt
-55	64	getsockopt		sys_getsockopt
-56	64	clone			stub_clone
-57	64	fork			stub_fork
-58	64	vfork			stub_vfork
+48	common	shutdown		sys_shutdown
+49	common	bind			sys_bind
+50	common	listen			sys_listen
+51	common	getsockname		sys_getsockname
+52	common	getpeername		sys_getpeername
+53	common	socketpair		sys_socketpair
+54	common	setsockopt		sys_setsockopt
+55	common	getsockopt		sys_getsockopt
+56	common	clone			stub_clone
+57	common	fork			stub_fork
+58	common	vfork			stub_vfork
 59	64	execve			stub_execve
-60	64	exit			sys_exit
-61	64	wait4			sys_wait4
-62	64	kill			sys_kill
-63	64	uname			sys_newuname
-64	64	semget			sys_semget
-65	64	semop			sys_semop
-66	64	semctl			sys_semctl
-67	64	shmdt			sys_shmdt
-68	64	msgget			sys_msgget
-69	64	msgsnd			sys_msgsnd
-70	64	msgrcv			sys_msgrcv
-71	64	msgctl			sys_msgctl
-72	64	fcntl			sys_fcntl
-73	64	flock			sys_flock
-74	64	fsync			sys_fsync
-75	64	fdatasync		sys_fdatasync
-76	64	truncate		sys_truncate
-77	64	ftruncate		sys_ftruncate
-78	64	getdents		sys_getdents
-79	64	getcwd			sys_getcwd
-80	64	chdir			sys_chdir
-81	64	fchdir			sys_fchdir
-82	64	rename			sys_rename
-83	64	mkdir			sys_mkdir
-84	64	rmdir			sys_rmdir
-85	64	creat			sys_creat
-86	64	link			sys_link
-87	64	unlink			sys_unlink
-88	64	symlink			sys_symlink
-89	64	readlink		sys_readlink
-90	64	chmod			sys_chmod
-91	64	fchmod			sys_fchmod
-92	64	chown			sys_chown
-93	64	fchown			sys_fchown
-94	64	lchown			sys_lchown
-95	64	umask			sys_umask
-96	64	gettimeofday		sys_gettimeofday
-97	64	getrlimit		sys_getrlimit
-98	64	getrusage		sys_getrusage
-99	64	sysinfo			sys_sysinfo
-100	64	times			sys_times
+60	common	exit			sys_exit
+61	common	wait4			sys_wait4
+62	common	kill			sys_kill
+63	common	uname			sys_newuname
+64	common	semget			sys_semget
+65	common	semop			sys_semop
+66	common	semctl			sys_semctl
+67	common	shmdt			sys_shmdt
+68	common	msgget			sys_msgget
+69	common	msgsnd			sys_msgsnd
+70	common	msgrcv			sys_msgrcv
+71	common	msgctl			sys_msgctl
+72	common	fcntl			sys_fcntl
+73	common	flock			sys_flock
+74	common	fsync			sys_fsync
+75	common	fdatasync		sys_fdatasync
+76	common	truncate		sys_truncate
+77	common	ftruncate		sys_ftruncate
+78	common	getdents		sys_getdents
+79	common	getcwd			sys_getcwd
+80	common	chdir			sys_chdir
+81	common	fchdir			sys_fchdir
+82	common	rename			sys_rename
+83	common	mkdir			sys_mkdir
+84	common	rmdir			sys_rmdir
+85	common	creat			sys_creat
+86	common	link			sys_link
+87	common	unlink			sys_unlink
+88	common	symlink			sys_symlink
+89	common	readlink		sys_readlink
+90	common	chmod			sys_chmod
+91	common	fchmod			sys_fchmod
+92	common	chown			sys_chown
+93	common	fchown			sys_fchown
+94	common	lchown			sys_lchown
+95	common	umask			sys_umask
+96	common	gettimeofday		sys_gettimeofday
+97	common	getrlimit		sys_getrlimit
+98	common	getrusage		sys_getrusage
+99	common	sysinfo			sys_sysinfo
+100	common	times			sys_times
 101	64	ptrace			sys_ptrace
-102	64	getuid			sys_getuid
-103	64	syslog			sys_syslog
-104	64	getgid			sys_getgid
-105	64	setuid			sys_setuid
-106	64	setgid			sys_setgid
-107	64	geteuid			sys_geteuid
-108	64	getegid			sys_getegid
-109	64	setpgid			sys_setpgid
-110	64	getppid			sys_getppid
-111	64	getpgrp			sys_getpgrp
-112	64	setsid			sys_setsid
-113	64	setreuid		sys_setreuid
-114	64	setregid		sys_setregid
-115	64	getgroups		sys_getgroups
-116	64	setgroups		sys_setgroups
-117	64	setresuid		sys_setresuid
-118	64	getresuid		sys_getresuid
-119	64	setresgid		sys_setresgid
-120	64	getresgid		sys_getresgid
-121	64	getpgid			sys_getpgid
-122	64	setfsuid		sys_setfsuid
-123	64	setfsgid		sys_setfsgid
-124	64	getsid			sys_getsid
-125	64	capget			sys_capget
-126	64	capset			sys_capset
+102	common	getuid			sys_getuid
+103	common	syslog			sys_syslog
+104	common	getgid			sys_getgid
+105	common	setuid			sys_setuid
+106	common	setgid			sys_setgid
+107	common	geteuid			sys_geteuid
+108	common	getegid			sys_getegid
+109	common	setpgid			sys_setpgid
+110	common	getppid			sys_getppid
+111	common	getpgrp			sys_getpgrp
+112	common	setsid			sys_setsid
+113	common	setreuid		sys_setreuid
+114	common	setregid		sys_setregid
+115	common	getgroups		sys_getgroups
+116	common	setgroups		sys_setgroups
+117	common	setresuid		sys_setresuid
+118	common	getresuid		sys_getresuid
+119	common	setresgid		sys_setresgid
+120	common	getresgid		sys_getresgid
+121	common	getpgid			sys_getpgid
+122	common	setfsuid		sys_setfsuid
+123	common	setfsgid		sys_setfsgid
+124	common	getsid			sys_getsid
+125	common	capget			sys_capget
+126	common	capset			sys_capset
 127	64	rt_sigpending		sys_rt_sigpending
 128	64	rt_sigtimedwait		sys_rt_sigtimedwait
 129	64	rt_sigqueueinfo		sys_rt_sigqueueinfo
-130	64	rt_sigsuspend		sys_rt_sigsuspend
+130	common	rt_sigsuspend		sys_rt_sigsuspend
 131	64	sigaltstack		stub_sigaltstack
-132	64	utime			sys_utime
-133	64	mknod			sys_mknod
+132	common	utime			sys_utime
+133	common	mknod			sys_mknod
 134	64	uselib
-135	64	personality		sys_personality
-136	64	ustat			sys_ustat
-137	64	statfs			sys_statfs
-138	64	fstatfs			sys_fstatfs
-139	64	sysfs			sys_sysfs
-140	64	getpriority		sys_getpriority
-141	64	setpriority		sys_setpriority
-142	64	sched_setparam		sys_sched_setparam
-143	64	sched_getparam		sys_sched_getparam
-144	64	sched_setscheduler	sys_sched_setscheduler
-145	64	sched_getscheduler	sys_sched_getscheduler
-146	64	sched_get_priority_max	sys_sched_get_priority_max
-147	64	sched_get_priority_min	sys_sched_get_priority_min
-148	64	sched_rr_get_interval	sys_sched_rr_get_interval
-149	64	mlock			sys_mlock
-150	64	munlock			sys_munlock
-151	64	mlockall		sys_mlockall
-152	64	munlockall		sys_munlockall
-153	64	vhangup			sys_vhangup
-154	64	modify_ldt		sys_modify_ldt
-155	64	pivot_root		sys_pivot_root
+135	common	personality		sys_personality
+136	common	ustat			sys_ustat
+137	common	statfs			sys_statfs
+138	common	fstatfs			sys_fstatfs
+139	common	sysfs			sys_sysfs
+140	common	getpriority		sys_getpriority
+141	common	setpriority		sys_setpriority
+142	common	sched_setparam		sys_sched_setparam
+143	common	sched_getparam		sys_sched_getparam
+144	common	sched_setscheduler	sys_sched_setscheduler
+145	common	sched_getscheduler	sys_sched_getscheduler
+146	common	sched_get_priority_max	sys_sched_get_priority_max
+147	common	sched_get_priority_min	sys_sched_get_priority_min
+148	common	sched_rr_get_interval	sys_sched_rr_get_interval
+149	common	mlock			sys_mlock
+150	common	munlock			sys_munlock
+151	common	mlockall		sys_mlockall
+152	common	munlockall		sys_munlockall
+153	common	vhangup			sys_vhangup
+154	common	modify_ldt		sys_modify_ldt
+155	common	pivot_root		sys_pivot_root
 156	64	_sysctl			sys_sysctl
-157	64	prctl			sys_prctl
-158	64	arch_prctl		sys_arch_prctl
-159	64	adjtimex		sys_adjtimex
-160	64	setrlimit		sys_setrlimit
-161	64	chroot			sys_chroot
-162	64	sync			sys_sync
-163	64	acct			sys_acct
-164	64	settimeofday		sys_settimeofday
-165	64	mount			sys_mount
-166	64	umount2			sys_umount
-167	64	swapon			sys_swapon
-168	64	swapoff			sys_swapoff
-169	64	reboot			sys_reboot
-170	64	sethostname		sys_sethostname
-171	64	setdomainname		sys_setdomainname
-172	64	iopl			stub_iopl
-173	64	ioperm			sys_ioperm
+157	common	prctl			sys_prctl
+158	common	arch_prctl		sys_arch_prctl
+159	common	adjtimex		sys_adjtimex
+160	common	setrlimit		sys_setrlimit
+161	common	chroot			sys_chroot
+162	common	sync			sys_sync
+163	common	acct			sys_acct
+164	common	settimeofday		sys_settimeofday
+165	common	mount			sys_mount
+166	common	umount2			sys_umount
+167	common	swapon			sys_swapon
+168	common	swapoff			sys_swapoff
+169	common	reboot			sys_reboot
+170	common	sethostname		sys_sethostname
+171	common	setdomainname		sys_setdomainname
+172	common	iopl			stub_iopl
+173	common	ioperm			sys_ioperm
 174	64	create_module
-175	64	init_module		sys_init_module
-176	64	delete_module		sys_delete_module
+175	common	init_module		sys_init_module
+176	common	delete_module		sys_delete_module
 177	64	get_kernel_syms
 178	64	query_module
-179	64	quotactl		sys_quotactl
+179	common	quotactl		sys_quotactl
 180	64	nfsservctl
-181	64	getpmsg
-182	64	putpmsg
-183	64	afs_syscall
-184	64	tuxcall
-185	64	security
-186	64	gettid			sys_gettid
-187	64	readahead		sys_readahead
-188	64	setxattr		sys_setxattr
-189	64	lsetxattr		sys_lsetxattr
-190	64	fsetxattr		sys_fsetxattr
-191	64	getxattr		sys_getxattr
-192	64	lgetxattr		sys_lgetxattr
-193	64	fgetxattr		sys_fgetxattr
-194	64	listxattr		sys_listxattr
-195	64	llistxattr		sys_llistxattr
-196	64	flistxattr		sys_flistxattr
-197	64	removexattr		sys_removexattr
-198	64	lremovexattr		sys_lremovexattr
-199	64	fremovexattr		sys_fremovexattr
-200	64	tkill			sys_tkill
-201	64	time			sys_time
-202	64	futex			sys_futex
-203	64	sched_setaffinity	sys_sched_setaffinity
-204	64	sched_getaffinity	sys_sched_getaffinity
+181	common	getpmsg
+182	common	putpmsg
+183	common	afs_syscall
+184	common	tuxcall
+185	common	security
+186	common	gettid			sys_gettid
+187	common	readahead		sys_readahead
+188	common	setxattr		sys_setxattr
+189	common	lsetxattr		sys_lsetxattr
+190	common	fsetxattr		sys_fsetxattr
+191	common	getxattr		sys_getxattr
+192	common	lgetxattr		sys_lgetxattr
+193	common	fgetxattr		sys_fgetxattr
+194	common	listxattr		sys_listxattr
+195	common	llistxattr		sys_llistxattr
+196	common	flistxattr		sys_flistxattr
+197	common	removexattr		sys_removexattr
+198	common	lremovexattr		sys_lremovexattr
+199	common	fremovexattr		sys_fremovexattr
+200	common	tkill			sys_tkill
+201	common	time			sys_time
+202	common	futex			sys_futex
+203	common	sched_setaffinity	sys_sched_setaffinity
+204	common	sched_getaffinity	sys_sched_getaffinity
 205	64	set_thread_area
-206	64	io_setup		sys_io_setup
-207	64	io_destroy		sys_io_destroy
-208	64	io_getevents		sys_io_getevents
-209	64	io_submit		sys_io_submit
-210	64	io_cancel		sys_io_cancel
+206	common	io_setup		sys_io_setup
+207	common	io_destroy		sys_io_destroy
+208	common	io_getevents		sys_io_getevents
+209	common	io_submit		sys_io_submit
+210	common	io_cancel		sys_io_cancel
 211	64	get_thread_area
-212	64	lookup_dcookie		sys_lookup_dcookie
-213	64	epoll_create		sys_epoll_create
+212	common	lookup_dcookie		sys_lookup_dcookie
+213	common	epoll_create		sys_epoll_create
 214	64	epoll_ctl_old
 215	64	epoll_wait_old
-216	64	remap_file_pages	sys_remap_file_pages
-217	64	getdents64		sys_getdents64
-218	64	set_tid_address		sys_set_tid_address
-219	64	restart_syscall		sys_restart_syscall
-220	64	semtimedop		sys_semtimedop
-221	64	fadvise64		sys_fadvise64
+216	common	remap_file_pages	sys_remap_file_pages
+217	common	getdents64		sys_getdents64
+218	common	set_tid_address		sys_set_tid_address
+219	common	restart_syscall		sys_restart_syscall
+220	common	semtimedop		sys_semtimedop
+221	common	fadvise64		sys_fadvise64
 222	64	timer_create		sys_timer_create
-223	64	timer_settime		sys_timer_settime
-224	64	timer_gettime		sys_timer_gettime
-225	64	timer_getoverrun	sys_timer_getoverrun
-226	64	timer_delete		sys_timer_delete
-227	64	clock_settime		sys_clock_settime
-228	64	clock_gettime		sys_clock_gettime
-229	64	clock_getres		sys_clock_getres
-230	64	clock_nanosleep		sys_clock_nanosleep
-231	64	exit_group		sys_exit_group
-232	64	epoll_wait		sys_epoll_wait
-233	64	epoll_ctl		sys_epoll_ctl
-234	64	tgkill			sys_tgkill
-235	64	utimes			sys_utimes
+223	common	timer_settime		sys_timer_settime
+224	common	timer_gettime		sys_timer_gettime
+225	common	timer_getoverrun	sys_timer_getoverrun
+226	common	timer_delete		sys_timer_delete
+227	common	clock_settime		sys_clock_settime
+228	common	clock_gettime		sys_clock_gettime
+229	common	clock_getres		sys_clock_getres
+230	common	clock_nanosleep		sys_clock_nanosleep
+231	common	exit_group		sys_exit_group
+232	common	epoll_wait		sys_epoll_wait
+233	common	epoll_ctl		sys_epoll_ctl
+234	common	tgkill			sys_tgkill
+235	common	utimes			sys_utimes
 236	64	vserver
-237	64	mbind			sys_mbind
-238	64	set_mempolicy		sys_set_mempolicy
-239	64	get_mempolicy		sys_get_mempolicy
-240	64	mq_open			sys_mq_open
-241	64	mq_unlink		sys_mq_unlink
-242	64	mq_timedsend		sys_mq_timedsend
-243	64	mq_timedreceive		sys_mq_timedreceive
+237	common	mbind			sys_mbind
+238	common	set_mempolicy		sys_set_mempolicy
+239	common	get_mempolicy		sys_get_mempolicy
+240	common	mq_open			sys_mq_open
+241	common	mq_unlink		sys_mq_unlink
+242	common	mq_timedsend		sys_mq_timedsend
+243	common	mq_timedreceive		sys_mq_timedreceive
 244	64	mq_notify		sys_mq_notify
-245	64	mq_getsetattr		sys_mq_getsetattr
+245	common	mq_getsetattr		sys_mq_getsetattr
 246	64	kexec_load		sys_kexec_load
 247	64	waitid			sys_waitid
-248	64	add_key			sys_add_key
-249	64	request_key		sys_request_key
-250	64	keyctl			sys_keyctl
-251	64	ioprio_set		sys_ioprio_set
-252	64	ioprio_get		sys_ioprio_get
-253	64	inotify_init		sys_inotify_init
-254	64	inotify_add_watch	sys_inotify_add_watch
-255	64	inotify_rm_watch	sys_inotify_rm_watch
-256	64	migrate_pages		sys_migrate_pages
-257	64	openat			sys_openat
-258	64	mkdirat			sys_mkdirat
-259	64	mknodat			sys_mknodat
-260	64	fchownat		sys_fchownat
-261	64	futimesat		sys_futimesat
-262	64	newfstatat		sys_newfstatat
-263	64	unlinkat		sys_unlinkat
-264	64	renameat		sys_renameat
-265	64	linkat			sys_linkat
-266	64	symlinkat		sys_symlinkat
-267	64	readlinkat		sys_readlinkat
-268	64	fchmodat		sys_fchmodat
-269	64	faccessat		sys_faccessat
-270	64	pselect6		sys_pselect6
-271	64	ppoll			sys_ppoll
-272	64	unshare			sys_unshare
+248	common	add_key			sys_add_key
+249	common	request_key		sys_request_key
+250	common	keyctl			sys_keyctl
+251	common	ioprio_set		sys_ioprio_set
+252	common	ioprio_get		sys_ioprio_get
+253	common	inotify_init		sys_inotify_init
+254	common	inotify_add_watch	sys_inotify_add_watch
+255	common	inotify_rm_watch	sys_inotify_rm_watch
+256	common	migrate_pages		sys_migrate_pages
+257	common	openat			sys_openat
+258	common	mkdirat			sys_mkdirat
+259	common	mknodat			sys_mknodat
+260	common	fchownat		sys_fchownat
+261	common	futimesat		sys_futimesat
+262	common	newfstatat		sys_newfstatat
+263	common	unlinkat		sys_unlinkat
+264	common	renameat		sys_renameat
+265	common	linkat			sys_linkat
+266	common	symlinkat		sys_symlinkat
+267	common	readlinkat		sys_readlinkat
+268	common	fchmodat		sys_fchmodat
+269	common	faccessat		sys_faccessat
+270	common	pselect6		sys_pselect6
+271	common	ppoll			sys_ppoll
+272	common	unshare			sys_unshare
 273	64	set_robust_list		sys_set_robust_list
 274	64	get_robust_list		sys_get_robust_list
-275	64	splice			sys_splice
-276	64	tee			sys_tee
-277	64	sync_file_range		sys_sync_file_range
+275	common	splice			sys_splice
+276	common	tee			sys_tee
+277	common	sync_file_range		sys_sync_file_range
 278	64	vmsplice		sys_vmsplice
 279	64	move_pages		sys_move_pages
-280	64	utimensat		sys_utimensat
-281	64	epoll_pwait		sys_epoll_pwait
-282	64	signalfd		sys_signalfd
-283	64	timerfd_create		sys_timerfd_create
-284	64	eventfd			sys_eventfd
-285	64	fallocate		sys_fallocate
-286	64	timerfd_settime		sys_timerfd_settime
-287	64	timerfd_gettime		sys_timerfd_gettime
-288	64	accept4			sys_accept4
-289	64	signalfd4		sys_signalfd4
-290	64	eventfd2		sys_eventfd2
-291	64	epoll_create1		sys_epoll_create1
-292	64	dup3			sys_dup3
-293	64	pipe2			sys_pipe2
-294	64	inotify_init1		sys_inotify_init1
+280	common	utimensat		sys_utimensat
+281	common	epoll_pwait		sys_epoll_pwait
+282	common	signalfd		sys_signalfd
+283	common	timerfd_create		sys_timerfd_create
+284	common	eventfd			sys_eventfd
+285	common	fallocate		sys_fallocate
+286	common	timerfd_settime		sys_timerfd_settime
+287	common	timerfd_gettime		sys_timerfd_gettime
+288	common	accept4			sys_accept4
+289	common	signalfd4		sys_signalfd4
+290	common	eventfd2		sys_eventfd2
+291	common	epoll_create1		sys_epoll_create1
+292	common	dup3			sys_dup3
+293	common	pipe2			sys_pipe2
+294	common	inotify_init1		sys_inotify_init1
 295	64	preadv			sys_preadv
 296	64	pwritev			sys_pwritev
 297	64	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo
-298	64	perf_event_open		sys_perf_event_open
+298	common	perf_event_open		sys_perf_event_open
 299	64	recvmmsg		sys_recvmmsg
-300	64	fanotify_init		sys_fanotify_init
-301	64	fanotify_mark		sys_fanotify_mark
-302	64	prlimit64		sys_prlimit64
-303	64	name_to_handle_at	sys_name_to_handle_at
-304	64	open_by_handle_at	sys_open_by_handle_at
-305	64	clock_adjtime		sys_clock_adjtime
-306	64	syncfs			sys_syncfs
+300	common	fanotify_init		sys_fanotify_init
+301	common	fanotify_mark		sys_fanotify_mark
+302	common	prlimit64		sys_prlimit64
+303	common	name_to_handle_at	sys_name_to_handle_at
+304	common	open_by_handle_at	sys_open_by_handle_at
+305	common	clock_adjtime		sys_clock_adjtime
+306	common	syncfs			sys_syncfs
 307	64	sendmmsg		sys_sendmmsg
-308	64	setns			sys_setns
-309	64	getcpu			sys_getcpu
+308	common	setns			sys_setns
+309	common	getcpu			sys_getcpu
 310	64	process_vm_readv	sys_process_vm_readv
 311	64	process_vm_writev	sys_process_vm_writev
+#
+# x32-specific system call numbers start at 512 to avoid cache impact
+# for native 64-bit operation.
+#
+512	x32	rt_sigaction		sys32_rt_sigaction
+513	x32	rt_sigreturn		stub_x32_rt_sigreturn
+514	x32	ioctl			compat_sys_ioctl
+515	x32	readv			compat_sys_readv
+516	x32	writev			compat_sys_writev
+517	x32	recvfrom		compat_sys_recvfrom
+518	x32	sendmsg			compat_sys_sendmsg
+519	x32	recvmsg			compat_sys_recvmsg
+520	x32	execve			stub_x32_execve
+521	x32	ptrace			compat_sys_ptrace
+522	x32	rt_sigpending		sys32_rt_sigpending
+523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait
+524	x32	rt_sigqueueinfo		sys32_rt_sigqueueinfo
+525	x32	sigaltstack		stub_x32_sigaltstack
+526	x32	timer_create		compat_sys_timer_create
+527	x32	mq_notify		compat_sys_mq_notify
+528	x32	kexec_load		compat_sys_kexec_load
+529	x32	waitid			compat_sys_waitid
+530	x32	set_robust_list		compat_sys_set_robust_list
+531	x32	get_robust_list		compat_sys_get_robust_list
+532	x32	vmsplice		compat_sys_vmsplice
+533	x32	move_pages		compat_sys_move_pages
+534	x32	preadv			compat_sys_preadv64
+535	x32	pwritev			compat_sys_pwritev64
+536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
+537	x32	recvmmsg		compat_sys_recvmmsg
+538	x32	sendmmsg		compat_sys_sendmmsg
+539	x32	process_vm_readv	compat_sys_process_vm_readv
+540	x32	process_vm_writev	compat_sys_process_vm_writev
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index b2b54d2edf53..9926e11a772d 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -15,8 +15,8 @@ config UML_X86
 	select GENERIC_FIND_FIRST_BIT
 
 config 64BIT
-	bool
-	default SUBARCH = "x86_64"
+	bool "64-bit kernel" if SUBARCH = "x86"
+	default SUBARCH != "i386"
 
 config X86_32
 	def_bool !64BIT
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 2c32df6fe231..04f82e020f2b 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -17,6 +17,16 @@
 #define ARCH_IS_STACKGROW(address) \
        (address + 65536 + 32 * sizeof(unsigned long) >= UPT_SP(&current->thread.regs.regs))
 
+#include <asm/user.h>
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+	__asm__ __volatile__("rep;nop": : :"memory");
+}
+
+#define cpu_relax()	rep_nop()
+
 #include <asm/processor-generic.h>
 
 #endif
diff --git a/arch/x86/um/asm/processor_32.h b/arch/x86/um/asm/processor_32.h
index 018f732704dd..6c6689e574ce 100644
--- a/arch/x86/um/asm/processor_32.h
+++ b/arch/x86/um/asm/processor_32.h
@@ -45,16 +45,6 @@ static inline void arch_copy_thread(struct arch_thread *from,
         memcpy(&to->tls_array, &from->tls_array, sizeof(from->tls_array));
 }
 
-#include <asm/user.h>
-
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
-{
-	__asm__ __volatile__("rep;nop": : :"memory");
-}
-
-#define cpu_relax()	rep_nop()
-
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter"). Stolen
diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h
index 61de92d916c3..4b02a8455bd1 100644
--- a/arch/x86/um/asm/processor_64.h
+++ b/arch/x86/um/asm/processor_64.h
@@ -14,14 +14,6 @@ struct arch_thread {
         struct faultinfo faultinfo;
 };
 
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
-{
-	__asm__ __volatile__("rep;nop": : :"memory");
-}
-
-#define cpu_relax()   rep_nop()
-
 #define INIT_ARCH_THREAD { .debugregs  		= { [ 0 ... 7 ] = 0 }, \
 			   .debugregs_seq	= 0, \
 			   .fs			= 0, \
@@ -37,8 +29,6 @@ static inline void arch_copy_thread(struct arch_thread *from,
 	to->fs = from->fs;
 }
 
-#include <asm/user.h>
-
 #define current_text_addr() \
 	({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; })
 
diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c
index a1fba5fb9dbe..17d88cf2c6c4 100644
--- a/arch/x86/um/bugs_32.c
+++ b/arch/x86/um/bugs_32.c
@@ -13,8 +13,6 @@
 static int host_has_cmov = 1;
 static jmp_buf cmov_test_return;
 
-#define TASK_PID(task) *((int *) &(((char *) (task))[HOST_TASK_PID]))
-
 static void cmov_sigill_test_handler(int sig)
 {
 	host_has_cmov = 0;
@@ -51,7 +49,7 @@ void arch_examine_signal(int sig, struct uml_pt_regs *regs)
 	 * This is testing for a cmov (0x0f 0x4x) instruction causing a
 	 * SIGILL in init.
 	 */
-	if ((sig != SIGILL) || (TASK_PID(get_current()) != 1))
+	if ((sig != SIGILL) || (get_current_pid() != 1))
 		return;
 
 	if (copy_from_user_proc(tmp, (void *) UPT_IP(regs), 2)) {
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index fe626c3ba01b..9924776f4265 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -35,6 +35,9 @@
 #define stub_sigaltstack sys_sigaltstack
 #define stub_rt_sigreturn sys_rt_sigreturn
 
+#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#define __SYSCALL_X32(nr, sym, compat) /* Not supported */
+
 #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
 #include <asm/syscalls_64.h>
 
diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c
index 5edf4f4bbf53..ce7e3607a870 100644
--- a/arch/x86/um/user-offsets.c
+++ b/arch/x86/um/user-offsets.c
@@ -15,6 +15,8 @@ static char syscalls[] = {
 };
 #else
 #define __SYSCALL_64(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_X32(nr, sym, compat) /* Not supported */
 static char syscalls[] = {
 #include <asm/syscalls_64.h>
 };
diff --git a/arch/x86/vdso/.gitignore b/arch/x86/vdso/.gitignore
index 60274d5746e1..3282874bc61d 100644
--- a/arch/x86/vdso/.gitignore
+++ b/arch/x86/vdso/.gitignore
@@ -1,5 +1,7 @@
 vdso.lds
 vdso-syms.lds
+vdsox32.lds
+vdsox32-syms.lds
 vdso32-syms.lds
 vdso32-syscall-syms.lds
 vdso32-sysenter-syms.lds
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 5d179502a52c..fd14be1d1472 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -3,21 +3,29 @@
 #
 
 VDSO64-$(CONFIG_X86_64)		:= y
+VDSOX32-$(CONFIG_X86_X32_ABI)	:= y
 VDSO32-$(CONFIG_X86_32)		:= y
 VDSO32-$(CONFIG_COMPAT)		:= y
 
 vdso-install-$(VDSO64-y)	+= vdso.so
+vdso-install-$(VDSOX32-y)	+= vdsox32.so
 vdso-install-$(VDSO32-y)	+= $(vdso32-images)
 
 
 # files to link into the vdso
 vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
 
+vobjs-$(VDSOX32-y) += $(vobjx32s-compat)
+
+# Filter out x32 objects.
+vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y))
+
 # files to link into kernel
 obj-$(VDSO64-y)			+= vma.o vdso.o
+obj-$(VDSOX32-y)		+= vdsox32.o
 obj-$(VDSO32-y)			+= vdso32.o vdso32-setup.o
 
-vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+vobjs := $(foreach F,$(vobj64s),$(obj)/$F)
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
@@ -73,6 +81,42 @@ $(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE
 	$(call if_changed,vdsosym)
 
 #
+# X32 processes use x32 vDSO to access 64bit kernel data.
+#
+# Build x32 vDSO image:
+# 1. Compile x32 vDSO as 64bit.
+# 2. Convert object files to x32.
+# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes
+# so that it can reach 64bit address space with 64bit pointers.
+#
+
+targets += vdsox32-syms.lds
+obj-$(VDSOX32-y)		+= vdsox32-syms.lds
+
+CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
+VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
+			   -Wl,-soname=linux-vdso.so.1 \
+			   -Wl,-z,max-page-size=4096 \
+			   -Wl,-z,common-page-size=4096
+
+vobjx32s-y := $(vobj64s:.o=-x32.o)
+vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
+
+# Convert 64bit object file to x32 for x32 vDSO.
+quiet_cmd_x32 = X32     $@
+      cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@
+
+$(obj)/%-x32.o: $(obj)/%.o FORCE
+	$(call if_changed,x32)
+
+targets += vdsox32.so vdsox32.so.dbg vdsox32.lds $(vobjx32s-y)
+
+$(obj)/vdsox32.o: $(src)/vdsox32.S $(obj)/vdsox32.so
+
+$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
+	$(call if_changed,vdso)
+
+#
 # Build multiple 32-bit vDSO images to choose from at boot time.
 #
 obj-$(VDSO32-y)			+= vdso32-syms.lds
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 6bc0e723b6e8..885eff49d6ab 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -70,100 +70,98 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 	return ret;
 }
 
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
+{
+	long ret;
+
+	asm("syscall" : "=a" (ret) :
+	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	return ret;
+}
+
+
 notrace static inline long vgetns(void)
 {
 	long v;
 	cycles_t cycles;
 	if (gtod->clock.vclock_mode == VCLOCK_TSC)
 		cycles = vread_tsc();
-	else
+	else if (gtod->clock.vclock_mode == VCLOCK_HPET)
 		cycles = vread_hpet();
+	else
+		return 0;
 	v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
 	return (v * gtod->clock.mult) >> gtod->clock.shift;
 }
 
-notrace static noinline int do_realtime(struct timespec *ts)
+/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
+notrace static int __always_inline do_realtime(struct timespec *ts)
 {
 	unsigned long seq, ns;
+	int mode;
+
 	do {
-		seq = read_seqbegin(&gtod->lock);
+		seq = read_seqcount_begin(&gtod->seq);
+		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
 		ts->tv_nsec = gtod->wall_time_nsec;
 		ns = vgetns();
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+
 	timespec_add_ns(ts, ns);
-	return 0;
+	return mode;
 }
 
-notrace static noinline int do_monotonic(struct timespec *ts)
+notrace static int do_monotonic(struct timespec *ts)
 {
-	unsigned long seq, ns, secs;
+	unsigned long seq, ns;
+	int mode;
+
 	do {
-		seq = read_seqbegin(&gtod->lock);
-		secs = gtod->wall_time_sec;
-		ns = gtod->wall_time_nsec + vgetns();
-		secs += gtod->wall_to_monotonic.tv_sec;
-		ns += gtod->wall_to_monotonic.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
-
-	/* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec
-	 * are all guaranteed to be nonnegative.
-	 */
-	while (ns >= NSEC_PER_SEC) {
-		ns -= NSEC_PER_SEC;
-		++secs;
-	}
-	ts->tv_sec = secs;
-	ts->tv_nsec = ns;
+		seq = read_seqcount_begin(&gtod->seq);
+		mode = gtod->clock.vclock_mode;
+		ts->tv_sec = gtod->monotonic_time_sec;
+		ts->tv_nsec = gtod->monotonic_time_nsec;
+		ns = vgetns();
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+	timespec_add_ns(ts, ns);
 
-	return 0;
+	return mode;
 }
 
-notrace static noinline int do_realtime_coarse(struct timespec *ts)
+notrace static int do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqbegin(&gtod->lock);
+		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	return 0;
 }
 
-notrace static noinline int do_monotonic_coarse(struct timespec *ts)
+notrace static int do_monotonic_coarse(struct timespec *ts)
 {
-	unsigned long seq, ns, secs;
+	unsigned long seq;
 	do {
-		seq = read_seqbegin(&gtod->lock);
-		secs = gtod->wall_time_coarse.tv_sec;
-		ns = gtod->wall_time_coarse.tv_nsec;
-		secs += gtod->wall_to_monotonic.tv_sec;
-		ns += gtod->wall_to_monotonic.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
-
-	/* wall_time_nsec and wall_to_monotonic.tv_nsec are
-	 * guaranteed to be between 0 and NSEC_PER_SEC.
-	 */
-	if (ns >= NSEC_PER_SEC) {
-		ns -= NSEC_PER_SEC;
-		++secs;
-	}
-	ts->tv_sec = secs;
-	ts->tv_nsec = ns;
+		seq = read_seqcount_begin(&gtod->seq);
+		ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
+		ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
 	return 0;
 }
 
 notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 {
+	int ret = VCLOCK_NONE;
+
 	switch (clock) {
 	case CLOCK_REALTIME:
-		if (likely(gtod->clock.vclock_mode != VCLOCK_NONE))
-			return do_realtime(ts);
+		ret = do_realtime(ts);
 		break;
 	case CLOCK_MONOTONIC:
-		if (likely(gtod->clock.vclock_mode != VCLOCK_NONE))
-			return do_monotonic(ts);
+		ret = do_monotonic(ts);
 		break;
 	case CLOCK_REALTIME_COARSE:
 		return do_realtime_coarse(ts);
@@ -171,32 +169,33 @@ notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 		return do_monotonic_coarse(ts);
 	}
 
-	return vdso_fallback_gettime(clock, ts);
+	if (ret == VCLOCK_NONE)
+		return vdso_fallback_gettime(clock, ts);
+	return 0;
 }
 int clock_gettime(clockid_t, struct timespec *)
 	__attribute__((weak, alias("__vdso_clock_gettime")));
 
 notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
-	long ret;
-	if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) {
-		if (likely(tv != NULL)) {
-			BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
-				     offsetof(struct timespec, tv_nsec) ||
-				     sizeof(*tv) != sizeof(struct timespec));
-			do_realtime((struct timespec *)tv);
-			tv->tv_usec /= 1000;
-		}
-		if (unlikely(tz != NULL)) {
-			/* Avoid memcpy. Some old compilers fail to inline it */
-			tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
-			tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
-		}
-		return 0;
+	long ret = VCLOCK_NONE;
+
+	if (likely(tv != NULL)) {
+		BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
+			     offsetof(struct timespec, tv_nsec) ||
+			     sizeof(*tv) != sizeof(struct timespec));
+		ret = do_realtime((struct timespec *)tv);
+		tv->tv_usec /= 1000;
 	}
-	asm("syscall" : "=a" (ret) :
-	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
-	return ret;
+	if (unlikely(tz != NULL)) {
+		/* Avoid memcpy. Some old compilers fail to inline it */
+		tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
+		tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
+	}
+
+	if (ret == VCLOCK_NONE)
+		return vdso_fallback_gtod(tv, tz);
+	return 0;
 }
 int gettimeofday(struct timeval *, struct timezone *)
 	__attribute__((weak, alias("__vdso_gettimeofday")));
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index a944020fa859..66e6d9359826 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -311,6 +311,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	int ret = 0;
 	bool compat;
 
+#ifdef CONFIG_X86_X32_ABI
+	if (test_thread_flag(TIF_X32))
+		return x32_setup_additional_pages(bprm, uses_interp);
+#endif
+
 	if (vdso_enabled == VDSO_DISABLED)
 		return 0;
 
diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S
new file mode 100644
index 000000000000..d6b9a7f42a8a
--- /dev/null
+++ b/arch/x86/vdso/vdsox32.S
@@ -0,0 +1,22 @@
+#include <asm/page_types.h>
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+__PAGE_ALIGNED_DATA
+
+	.globl vdsox32_start, vdsox32_end
+	.align PAGE_SIZE
+vdsox32_start:
+	.incbin "arch/x86/vdso/vdsox32.so"
+vdsox32_end:
+	.align PAGE_SIZE /* extra data here leaks to userspace. */
+
+.previous
+
+	.globl vdsox32_pages
+	.bss
+	.align 8
+	.type vdsox32_pages, @object
+vdsox32_pages:
+	.zero (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE * 8
+	.size vdsox32_pages, .-vdsox32_pages
diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/vdso/vdsox32.lds.S
new file mode 100644
index 000000000000..62272aa2ae0a
--- /dev/null
+++ b/arch/x86/vdso/vdsox32.lds.S
@@ -0,0 +1,28 @@
+/*
+ * Linker script for x32 vDSO.
+ * We #include the file to define the layout details.
+ * Here we only choose the prelinked virtual address.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.  We can define local symbols here called VDSO* to make their
+ * values visible using the asm-x86/vdso.h macros from the kernel proper.
+ */
+
+#define VDSO_PRELINK 0
+#include "vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+	LINUX_2.6 {
+	global:
+		__vdso_clock_gettime;
+		__vdso_gettimeofday;
+		__vdso_getcpu;
+		__vdso_time;
+	local: *;
+	};
+}
+
+VDSOX32_PRELINK = VDSO_PRELINK;
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 17e18279649f..00aaf047b39f 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -24,7 +24,44 @@ extern unsigned short vdso_sync_cpuid;
 extern struct page *vdso_pages[];
 static unsigned vdso_size;
 
-static void __init patch_vdso(void *vdso, size_t len)
+#ifdef CONFIG_X86_X32_ABI
+extern char vdsox32_start[], vdsox32_end[];
+extern struct page *vdsox32_pages[];
+static unsigned vdsox32_size;
+
+static void __init patch_vdsox32(void *vdso, size_t len)
+{
+	Elf32_Ehdr *hdr = vdso;
+	Elf32_Shdr *sechdrs, *alt_sec = 0;
+	char *secstrings;
+	void *alt_data;
+	int i;
+
+	BUG_ON(len < sizeof(Elf32_Ehdr));
+	BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0);
+
+	sechdrs = (void *)hdr + hdr->e_shoff;
+	secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (i = 1; i < hdr->e_shnum; i++) {
+		Elf32_Shdr *shdr = &sechdrs[i];
+		if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) {
+			alt_sec = shdr;
+			goto found;
+		}
+	}
+
+	/* If we get here, it's probably a bug. */
+	pr_warning("patch_vdsox32: .altinstructions not found\n");
+	return;  /* nothing to patch */
+
+found:
+	alt_data = (void *)hdr + alt_sec->sh_offset;
+	apply_alternatives(alt_data, alt_data + alt_sec->sh_size);
+}
+#endif
+
+static void __init patch_vdso64(void *vdso, size_t len)
 {
 	Elf64_Ehdr *hdr = vdso;
 	Elf64_Shdr *sechdrs, *alt_sec = 0;
@@ -47,7 +84,7 @@ static void __init patch_vdso(void *vdso, size_t len)
 	}
 
 	/* If we get here, it's probably a bug. */
-	pr_warning("patch_vdso: .altinstructions not found\n");
+	pr_warning("patch_vdso64: .altinstructions not found\n");
 	return;  /* nothing to patch */
 
 found:
@@ -60,12 +97,20 @@ static int __init init_vdso(void)
 	int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
 	int i;
 
-	patch_vdso(vdso_start, vdso_end - vdso_start);
+	patch_vdso64(vdso_start, vdso_end - vdso_start);
 
 	vdso_size = npages << PAGE_SHIFT;
 	for (i = 0; i < npages; i++)
 		vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
 
+#ifdef CONFIG_X86_X32_ABI
+	patch_vdsox32(vdsox32_start, vdsox32_end - vdsox32_start);
+	npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE;
+	vdsox32_size = npages << PAGE_SHIFT;
+	for (i = 0; i < npages; i++)
+		vdsox32_pages[i] = virt_to_page(vdsox32_start + i*PAGE_SIZE);
+#endif
+
 	return 0;
 }
 subsys_initcall(init_vdso);
@@ -103,7 +148,10 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 
 /* Setup a VMA at program startup for the vsyscall page.
    Not called for compat tasks */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+static int setup_additional_pages(struct linux_binprm *bprm,
+				  int uses_interp,
+				  struct page **pages,
+				  unsigned size)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
@@ -113,8 +161,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		return 0;
 
 	down_write(&mm->mmap_sem);
-	addr = vdso_addr(mm->start_stack, vdso_size);
-	addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0);
+	addr = vdso_addr(mm->start_stack, size);
+	addr = get_unmapped_area(NULL, addr, size, 0, 0);
 	if (IS_ERR_VALUE(addr)) {
 		ret = addr;
 		goto up_fail;
@@ -122,10 +170,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 
 	current->mm->context.vdso = (void *)addr;
 
-	ret = install_special_mapping(mm, addr, vdso_size,
+	ret = install_special_mapping(mm, addr, size,
 				      VM_READ|VM_EXEC|
 				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				      vdso_pages);
+				      pages);
 	if (ret) {
 		current->mm->context.vdso = NULL;
 		goto up_fail;
@@ -136,6 +184,20 @@ up_fail:
 	return ret;
 }
 
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	return setup_additional_pages(bprm, uses_interp, vdso_pages,
+				      vdso_size);
+}
+
+#ifdef CONFIG_X86_X32_ABI
+int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	return setup_additional_pages(bprm, uses_interp, vdsox32_pages,
+				      vdsox32_size);
+}
+#endif
+
 static __init int vdso_setup(char *s)
 {
 	vdso_enabled = simple_strtoul(s, NULL, 0);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b132ade26f77..4f51bebac02c 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -967,7 +967,7 @@ void xen_setup_shared_info(void)
 	xen_setup_mfn_list_list();
 }
 
-/* This is called once we have the cpu_possible_map */
+/* This is called once we have the cpu_possible_mask */
 void xen_setup_vcpu_info_placement(void)
 {
 	int cpu;
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index b480d4207a4c..967633ad98c4 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -12,8 +12,8 @@ int xen_swiotlb __read_mostly;
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
 	.mapping_error = xen_swiotlb_dma_mapping_error,
-	.alloc_coherent = xen_swiotlb_alloc_coherent,
-	.free_coherent = xen_swiotlb_free_coherent,
+	.alloc = xen_swiotlb_alloc_coherent,
+	.free = xen_swiotlb_free_coherent,
 	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig
index f932b30b47fb..ddab37b24741 100644
--- a/arch/xtensa/configs/iss_defconfig
+++ b/arch/xtensa/configs/iss_defconfig
@@ -113,7 +113,7 @@ CONFIG_DEFAULT_IOSCHED="noop"
 # CONFIG_INLINE_SPIN_LOCK_BH is not set
 # CONFIG_INLINE_SPIN_LOCK_IRQ is not set
 # CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set
-CONFIG_INLINE_SPIN_UNLOCK=y
+# CONFIG_UNINLINE_SPIN_UNLOCK is not set
 # CONFIG_INLINE_SPIN_UNLOCK_BH is not set
 CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
 # CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 23592eff67ad..b40989308775 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -18,7 +18,7 @@
 
 #ifdef __KERNEL__
 #include <asm/processor.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)	{ (i) }
 
diff --git a/arch/xtensa/include/asm/barrier.h b/arch/xtensa/include/asm/barrier.h
new file mode 100644
index 000000000000..55707a8009d3
--- /dev/null
+++ b/arch/xtensa/include/asm/barrier.h
@@ -0,0 +1,29 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2005 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_SYSTEM_H
+#define _XTENSA_SYSTEM_H
+
+#define smp_read_barrier_depends() do { } while(0)
+#define read_barrier_depends() do { } while(0)
+
+#define mb()  barrier()
+#define rmb() mb()
+#define wmb() mb()
+
+#ifdef CONFIG_SMP
+#error smp_* not defined
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#endif
+
+#define set_mb(var, value)	do { var = value; mb(); } while (0)
+
+#endif /* _XTENSA_SYSTEM_H */
diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h
index 40aa7fe77f66..5270197ddd36 100644
--- a/arch/xtensa/include/asm/bitops.h
+++ b/arch/xtensa/include/asm/bitops.h
@@ -21,7 +21,6 @@
 
 #include <asm/processor.h>
 #include <asm/byteorder.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_SMP
 # error SMP not supported on this architecture
diff --git a/arch/xtensa/include/asm/system.h b/arch/xtensa/include/asm/cmpxchg.h
index 1e7e09ab6cd7..e32149063d83 100644
--- a/arch/xtensa/include/asm/system.h
+++ b/arch/xtensa/include/asm/cmpxchg.h
@@ -1,5 +1,5 @@
 /*
- * include/asm-xtensa/system.h
+ * Atomic xchg and cmpxchg operations.
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
@@ -8,44 +8,12 @@
  * Copyright (C) 2001 - 2005 Tensilica Inc.
  */
 
-#ifndef _XTENSA_SYSTEM_H
-#define _XTENSA_SYSTEM_H
+#ifndef _XTENSA_CMPXCHG_H
+#define _XTENSA_CMPXCHG_H
 
-#include <linux/stringify.h>
-#include <linux/irqflags.h>
-
-#include <asm/processor.h>
-
-#define smp_read_barrier_depends() do { } while(0)
-#define read_barrier_depends() do { } while(0)
-
-#define mb()  barrier()
-#define rmb() mb()
-#define wmb() mb()
+#ifndef __ASSEMBLY__
 
-#ifdef CONFIG_SMP
-#error smp_* not defined
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#endif
-
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
-
-#if !defined (__ASSEMBLY__)
-
-/* * switch_to(n) should switch tasks to task nr n, first
- * checking that n isn't the current task, in which case it does nothing.
- */
-extern void *_switch_to(void *last, void *next);
-
-#endif	/* __ASSEMBLY__ */
-
-#define switch_to(prev,next,last)		\
-do {						\
-	(last) = _switch_to(prev, next);	\
-} while(0)
+#include <linux/stringify.h>
 
 /*
  * cmpxchg
@@ -158,27 +126,6 @@ __xchg(unsigned long x, volatile void * ptr, int size)
 	return x;
 }
 
-extern void set_except_vector(int n, void *addr);
-
-static inline void spill_registers(void)
-{
-	unsigned int a0, ps;
-
-	__asm__ __volatile__ (
-		"movi	a14," __stringify (PS_EXCM_BIT) " | 1\n\t"
-		"mov	a12, a0\n\t"
-		"rsr	a13," __stringify(SAR) "\n\t"
-		"xsr	a14," __stringify(PS) "\n\t"
-		"movi	a0, _spill_registers\n\t"
-		"rsync\n\t"
-		"callx0 a0\n\t"
-		"mov	a0, a12\n\t"
-		"wsr	a13," __stringify(SAR) "\n\t"
-		"wsr	a14," __stringify(PS) "\n\t"
-		:: "a" (&a0), "a" (&ps)
-		: "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15", "memory");
-}
-
-#define arch_align_stack(x) (x)
+#endif /* __ASSEMBLY__ */
 
-#endif	/* _XTENSA_SYSTEM_H */
+#endif /* _XTENSA_CMPXCHG_H */
diff --git a/arch/xtensa/include/asm/exec.h b/arch/xtensa/include/asm/exec.h
new file mode 100644
index 000000000000..af949e28cb32
--- /dev/null
+++ b/arch/xtensa/include/asm/exec.h
@@ -0,0 +1,14 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2005 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_EXEC_H
+#define _XTENSA_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* _XTENSA_EXEC_H */
diff --git a/arch/xtensa/include/asm/posix_types.h b/arch/xtensa/include/asm/posix_types.h
index 6b2190c35882..6e96be0d02d3 100644
--- a/arch/xtensa/include/asm/posix_types.h
+++ b/arch/xtensa/include/asm/posix_types.h
@@ -19,104 +19,21 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef unsigned long	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
 typedef unsigned short	__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned int	__kernel_size_t;
 typedef int		__kernel_ssize_t;
 typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_size_t __kernel_size_t
 
 typedef unsigned short	__kernel_old_uid_t;
 typedef unsigned short	__kernel_old_gid_t;
-typedef unsigned short	__kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifndef __GNUC__
-
-#define	__FD_SET(d, set)	((set)->fds_bits[__FDELT(d)] |= __FDMASK(d))
-#define	__FD_CLR(d, set)	((set)->fds_bits[__FDELT(d)] &= ~__FDMASK(d))
-#define	__FD_ISSET(d, set)	(!!((set)->fds_bits[__FDELT(d)] & __FDMASK(d)))
-#define	__FD_ZERO(set)	\
-  ((void) memset ((void *) (set), 0, sizeof (__kernel_fd_set)))
-
-#else /* __GNUC__ */
+#define __kernel_old_uid_t __kernel_old_uid_t
 
-#if defined(__KERNEL__)
-/* With GNU C, use inline functions instead so args are evaluated only once: */
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long fd, __kernel_fd_set *p)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned int *tmp = (unsigned int *)p->fds_bits;
-	int i;
+typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-			case 8:
-				tmp[0] = 0; tmp[1] = 0; tmp[2] = 0; tmp[3] = 0;
-				tmp[4] = 0; tmp[5] = 0; tmp[6] = 0; tmp[7] = 0;
-				return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
+#include <asm-generic/posix_types.h>
 
-#endif /* defined(__KERNEL__) */
-#endif /* __GNUC__ */
 #endif /* _XTENSA_POSIX_TYPES_H */
diff --git a/arch/xtensa/include/asm/setup.h b/arch/xtensa/include/asm/setup.h
index e3636520d8cc..9fa8ad979361 100644
--- a/arch/xtensa/include/asm/setup.h
+++ b/arch/xtensa/include/asm/setup.h
@@ -13,4 +13,6 @@
 
 #define COMMAND_LINE_SIZE	256
 
+extern void set_except_vector(int n, void *addr);
+
 #endif
diff --git a/arch/xtensa/include/asm/switch_to.h b/arch/xtensa/include/asm/switch_to.h
new file mode 100644
index 000000000000..6b73bf0eb1ff
--- /dev/null
+++ b/arch/xtensa/include/asm/switch_to.h
@@ -0,0 +1,22 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2005 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_SWITCH_TO_H
+#define _XTENSA_SWITCH_TO_H
+
+/* * switch_to(n) should switch tasks to task nr n, first
+ * checking that n isn't the current task, in which case it does nothing.
+ */
+extern void *_switch_to(void *last, void *next);
+
+#define switch_to(prev,next,last)		\
+do {						\
+	(last) = _switch_to(prev, next);	\
+} while(0)
+
+#endif /* _XTENSA_SWITCH_TO_H */
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index 3fa526fd3c99..6e4bb3b791ab 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -17,7 +17,9 @@
 #define _XTENSA_UACCESS_H
 
 #include <linux/errno.h>
+#ifndef __ASSEMBLY__
 #include <linux/prefetch.h>
+#endif
 #include <asm/types.h>
 
 #define VERIFY_READ    0
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 2c9004770c4e..6a2d6edf8f72 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -34,7 +34,6 @@
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/platform.h>
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index 2dff698ab02e..33eea4c16f12 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -24,7 +24,6 @@
 
 #include <asm/pgtable.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/elf.h>
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 1e5a034fe011..17e746f7be60 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -34,7 +34,6 @@
 # include <linux/seq_file.h>
 #endif
 
-#include <asm/system.h>
 #include <asm/bootparam.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index e64efac3b9db..bc1e14cf9369 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -381,6 +381,25 @@ static __always_inline unsigned long *stack_pointer(struct task_struct *task)
 	return sp;
 }
 
+static inline void spill_registers(void)
+{
+	unsigned int a0, ps;
+
+	__asm__ __volatile__ (
+		"movi	a14," __stringify (PS_EXCM_BIT) " | 1\n\t"
+		"mov	a12, a0\n\t"
+		"rsr	a13," __stringify(SAR) "\n\t"
+		"xsr	a14," __stringify(PS) "\n\t"
+		"movi	a0, _spill_registers\n\t"
+		"rsync\n\t"
+		"callx0 a0\n\t"
+		"mov	a0, a12\n\t"
+		"wsr	a13," __stringify(SAR) "\n\t"
+		"wsr	a14," __stringify(PS) "\n\t"
+		:: "a" (&a0), "a" (&ps)
+		: "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15", "memory");
+}
+
 void show_trace(struct task_struct *task, unsigned long *sp)
 {
 	unsigned long a0, a1, pc;
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index e367e3026436..b17885a0b508 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -19,7 +19,6 @@
 #include <asm/cacheflush.h>
 #include <asm/hardirq.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/pgalloc.h>
 
 unsigned long asid_cache = ASID_USER_FIRST;
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index 239461d8ea88..e2700b21395b 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -18,7 +18,6 @@
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 
 
diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index c22374bf9f1e..533de9550a82 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -613,8 +613,7 @@ out:
 	return err;
 }
 
-static struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type,
-						 u32 mask)
+struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask)
 {
 	struct crypto_alg *alg;
 
@@ -652,6 +651,7 @@ static struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type,
 
 	return ERR_PTR(crypto_givcipher_default(alg, type, mask));
 }
+EXPORT_SYMBOL_GPL(crypto_lookup_skcipher);
 
 int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name,
 			 u32 type, u32 mask)
diff --git a/crypto/aead.c b/crypto/aead.c
index c772b9c79ee7..0b8121ebec07 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -470,8 +470,7 @@ out:
 	return err;
 }
 
-static struct crypto_alg *crypto_lookup_aead(const char *name, u32 type,
-					     u32 mask)
+struct crypto_alg *crypto_lookup_aead(const char *name, u32 type, u32 mask)
 {
 	struct crypto_alg *alg;
 
@@ -503,6 +502,7 @@ static struct crypto_alg *crypto_lookup_aead(const char *name, u32 type,
 
 	return ERR_PTR(crypto_nivaead_default(alg, type, mask));
 }
+EXPORT_SYMBOL_GPL(crypto_lookup_aead);
 
 int crypto_grab_aead(struct crypto_aead_spawn *spawn, const char *name,
 		     u32 type, u32 mask)
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 84a5ac71ecb4..5a37eadb4e56 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -21,9 +21,13 @@
 #include <linux/module.h>
 #include <linux/crypto.h>
 #include <linux/cryptouser.h>
+#include <linux/sched.h>
 #include <net/netlink.h>
 #include <linux/security.h>
 #include <net/net_namespace.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+
 #include "internal.h"
 
 DEFINE_MUTEX(crypto_cfg_mutex);
@@ -301,6 +305,60 @@ static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return crypto_unregister_instance(alg);
 }
 
+static struct crypto_alg *crypto_user_skcipher_alg(const char *name, u32 type,
+						   u32 mask)
+{
+	int err;
+	struct crypto_alg *alg;
+
+	type = crypto_skcipher_type(type);
+	mask = crypto_skcipher_mask(mask);
+
+	for (;;) {
+		alg = crypto_lookup_skcipher(name,  type, mask);
+		if (!IS_ERR(alg))
+			return alg;
+
+		err = PTR_ERR(alg);
+		if (err != -EAGAIN)
+			break;
+		if (signal_pending(current)) {
+			err = -EINTR;
+			break;
+		}
+	}
+
+	return ERR_PTR(err);
+}
+
+static struct crypto_alg *crypto_user_aead_alg(const char *name, u32 type,
+					       u32 mask)
+{
+	int err;
+	struct crypto_alg *alg;
+
+	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
+	type |= CRYPTO_ALG_TYPE_AEAD;
+	mask &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
+	mask |= CRYPTO_ALG_TYPE_MASK;
+
+	for (;;) {
+		alg = crypto_lookup_aead(name,  type, mask);
+		if (!IS_ERR(alg))
+			return alg;
+
+		err = PTR_ERR(alg);
+		if (err != -EAGAIN)
+			break;
+		if (signal_pending(current)) {
+			err = -EINTR;
+			break;
+		}
+	}
+
+	return ERR_PTR(err);
+}
+
 static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct nlattr **attrs)
 {
@@ -325,7 +383,19 @@ static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	else
 		name = p->cru_name;
 
-	alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask);
+	switch (p->cru_type & p->cru_mask & CRYPTO_ALG_TYPE_MASK) {
+	case CRYPTO_ALG_TYPE_AEAD:
+		alg = crypto_user_aead_alg(name, p->cru_type, p->cru_mask);
+		break;
+	case CRYPTO_ALG_TYPE_GIVCIPHER:
+	case CRYPTO_ALG_TYPE_BLKCIPHER:
+	case CRYPTO_ALG_TYPE_ABLKCIPHER:
+		alg = crypto_user_skcipher_alg(name, p->cru_type, p->cru_mask);
+		break;
+	default:
+		alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask);
+	}
+
 	if (IS_ERR(alg))
 		return PTR_ERR(alg);
 
@@ -387,12 +457,20 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) &&
 	    (nlh->nlmsg_flags & NLM_F_DUMP))) {
+		struct crypto_alg *alg;
+		u16 dump_alloc = 0;
+
 		if (link->dump == NULL)
 			return -EINVAL;
+
+		list_for_each_entry(alg, &crypto_alg_list, cra_list)
+			dump_alloc += CRYPTO_REPORT_MAXSIZE;
+
 		{
 			struct netlink_dump_control c = {
 				.dump = link->dump,
 				.done = link->done,
+				.min_dump_alloc = dump_alloc,
 			};
 			return netlink_dump_start(crypto_nlsk, skb, nlh, &c);
 		}
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index 29a89dad68b6..b2c99dc1c5e2 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -280,11 +280,11 @@ static int pcrypt_aead_init_tfm(struct crypto_tfm *tfm)
 
 	ictx->tfm_count++;
 
-	cpu_index = ictx->tfm_count % cpumask_weight(cpu_active_mask);
+	cpu_index = ictx->tfm_count % cpumask_weight(cpu_online_mask);
 
-	ctx->cb_cpu = cpumask_first(cpu_active_mask);
+	ctx->cb_cpu = cpumask_first(cpu_online_mask);
 	for (cpu = 0; cpu < cpu_index; cpu++)
-		ctx->cb_cpu = cpumask_next(ctx->cb_cpu, cpu_active_mask);
+		ctx->cb_cpu = cpumask_next(ctx->cb_cpu, cpu_online_mask);
 
 	cipher = crypto_spawn_aead(crypto_instance_ctx(inst));
 
@@ -472,7 +472,7 @@ static int pcrypt_init_padata(struct padata_pcrypt *pcrypt,
 		goto err_free_padata;
 	}
 
-	cpumask_and(mask->mask, cpu_possible_mask, cpu_active_mask);
+	cpumask_and(mask->mask, cpu_possible_mask, cpu_online_mask);
 	rcu_assign_pointer(pcrypt->cb_cpumask, mask);
 
 	pcrypt->nblock.notifier_call = pcrypt_cpumask_change_notify;
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 6f0459cb745b..d236aef7e59f 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -50,6 +50,8 @@ source "drivers/i2c/Kconfig"
 
 source "drivers/spi/Kconfig"
 
+source "drivers/hsi/Kconfig"
+
 source "drivers/pps/Kconfig"
 
 source "drivers/ptp/Kconfig"
diff --git a/drivers/Makefile b/drivers/Makefile
index 262b19d6b627..95952c82bf16 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -53,6 +53,7 @@ obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
 obj-$(CONFIG_MTD)		+= mtd/
 obj-$(CONFIG_SPI)		+= spi/
+obj-y				+= hsi/
 obj-y				+= net/
 obj-$(CONFIG_ATM)		+= atm/
 obj-$(CONFIG_FUSION)		+= message/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 7556913aba45..47768ff87343 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -384,6 +384,15 @@ config ACPI_CUSTOM_METHOD
 	  load additional kernel modules after boot, this feature may be used
 	  to override that restriction).
 
+config ACPI_BGRT
+        tristate "Boottime Graphics Resource Table support"
+        default n
+        help
+	  This driver adds support for exposing the ACPI Boottime Graphics
+	  Resource Table, which allows the operating system to obtain
+	  data from the firmware boot splash. It will appear under
+	  /sys/firmware/acpi/bgrt/ .
+
 source "drivers/acpi/apei/Kconfig"
 
 endif	# ACPI
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 1567028d2038..47199e2a9130 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_ACPI_SBS)		+= sbs.o
 obj-$(CONFIG_ACPI_HED)		+= hed.o
 obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
 obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
+obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_driver.o processor_throttling.o
diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile
index 0ca208b6dcf0..793b8cc8e256 100644
--- a/drivers/acpi/acpica/Makefile
+++ b/drivers/acpi/acpica/Makefile
@@ -68,12 +68,14 @@ acpi-y +=		\
 
 acpi-y +=		\
 	hwacpi.o	\
+	hwesleep.o	\
 	hwgpe.o		\
 	hwpci.o		\
 	hwregs.o	\
 	hwsleep.o	\
 	hwvalid.o	\
-	hwxface.o
+	hwxface.o	\
+	hwxfsleep.o
 
 acpi-$(ACPI_FUTURE_USAGE) += hwtimer.o
 
diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h
index a44bd424f9f4..8a7d51bfb3b3 100644
--- a/drivers/acpi/acpica/accommon.h
+++ b/drivers/acpi/acpica/accommon.h
@@ -51,7 +51,6 @@
  *
  * Note: The order of these include files is important.
  */
-#include "acconfig.h"		/* Global configuration constants */
 #include "acmacros.h"		/* C macros */
 #include "aclocal.h"		/* Internal data types */
 #include "acobject.h"		/* ACPI internal object */
diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index deaa81979561..5e8abb07724f 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -111,7 +111,7 @@ acpi_status acpi_db_find_name_in_namespace(char *name_arg);
 
 void acpi_db_set_scope(char *name);
 
-acpi_status acpi_db_sleep(char *object_arg);
+ACPI_HW_DEPENDENT_RETURN_OK(acpi_status acpi_db_sleep(char *object_arg))
 
 void acpi_db_find_references(char *object_arg);
 
@@ -119,11 +119,13 @@ void acpi_db_display_locks(void);
 
 void acpi_db_display_resources(char *object_arg);
 
-void acpi_db_display_gpes(void);
+ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_db_display_gpes(void))
 
 void acpi_db_check_integrity(void);
 
-void acpi_db_generate_gpe(char *gpe_arg, char *block_arg);
+ACPI_HW_DEPENDENT_RETURN_VOID(void
+			      acpi_db_generate_gpe(char *gpe_arg,
+						   char *block_arg))
 
 void acpi_db_check_predefined_names(void);
 
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index c53caa521a30..d700f63e4701 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -69,11 +69,10 @@ acpi_ev_queue_notify_request(struct acpi_namespace_node *node,
  */
 acpi_status acpi_ev_init_global_lock_handler(void);
 
-acpi_status acpi_ev_acquire_global_lock(u16 timeout);
-
-acpi_status acpi_ev_release_global_lock(void);
-
-acpi_status acpi_ev_remove_global_lock_handler(void);
+ACPI_HW_DEPENDENT_RETURN_OK(acpi_status
+			    acpi_ev_acquire_global_lock(u16 timeout))
+ ACPI_HW_DEPENDENT_RETURN_OK(acpi_status acpi_ev_release_global_lock(void))
+ acpi_status acpi_ev_remove_global_lock_handler(void);
 
 /*
  * evgpe - Low-level GPE support
@@ -114,7 +113,9 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 			     struct acpi_gpe_block_info *gpe_block,
 			     void *context);
 
-acpi_status acpi_ev_delete_gpe_block(struct acpi_gpe_block_info *gpe_block);
+ACPI_HW_DEPENDENT_RETURN_OK(acpi_status
+			    acpi_ev_delete_gpe_block(struct acpi_gpe_block_info
+						     *gpe_block))
 
 u32
 acpi_ev_gpe_dispatch(struct acpi_namespace_node *gpe_device,
@@ -126,9 +127,10 @@ acpi_ev_gpe_dispatch(struct acpi_namespace_node *gpe_device,
  */
 acpi_status acpi_ev_gpe_initialize(void);
 
-void acpi_ev_update_gpes(acpi_owner_id table_owner_id);
+ACPI_HW_DEPENDENT_RETURN_VOID(void
+			      acpi_ev_update_gpes(acpi_owner_id table_owner_id))
 
-acpi_status
+ acpi_status
 acpi_ev_match_gpe_method(acpi_handle obj_handle,
 			 u32 level, void *context, void **return_value);
 
@@ -237,6 +239,5 @@ acpi_status acpi_ev_remove_sci_handler(void);
 
 u32 acpi_ev_initialize_sCI(u32 program_sCI);
 
-void acpi_ev_terminate(void);
-
+ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_ev_terminate(void))
 #endif				/* __ACEVENTS_H__  */
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 2853f7673f3b..4f7d3f57d05c 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -147,7 +147,7 @@ u8 acpi_gbl_system_awake_and_running;
  */
 u8 acpi_gbl_reduced_hardware;
 
-#endif
+#endif				/* DEFINE_ACPI_GLOBALS */
 
 /* Do not disassemble buffers to resource descriptors */
 
@@ -184,8 +184,12 @@ ACPI_EXTERN u32 acpi_gbl_trace_dbg_layer;
  * found in the RSDT/XSDT.
  */
 ACPI_EXTERN struct acpi_table_list acpi_gbl_root_table_list;
+
+#if (!ACPI_REDUCED_HARDWARE)
 ACPI_EXTERN struct acpi_table_facs *acpi_gbl_FACS;
 
+#endif				/* !ACPI_REDUCED_HARDWARE */
+
 /* These addresses are calculated from the FADT Event Block addresses */
 
 ACPI_EXTERN struct acpi_generic_address acpi_gbl_xpm1a_status;
@@ -397,10 +401,15 @@ ACPI_EXTERN struct acpi_fixed_event_handler
 ACPI_EXTERN struct acpi_gpe_xrupt_info *acpi_gbl_gpe_xrupt_list_head;
 ACPI_EXTERN struct acpi_gpe_block_info
 *acpi_gbl_gpe_fadt_blocks[ACPI_MAX_GPE_BLOCKS];
+
+#if (!ACPI_REDUCED_HARDWARE)
+
 ACPI_EXTERN u8 acpi_gbl_all_gpes_initialized;
 ACPI_EXTERN ACPI_GBL_EVENT_HANDLER acpi_gbl_global_event_handler;
 ACPI_EXTERN void *acpi_gbl_global_event_handler_context;
 
+#endif				/* !ACPI_REDUCED_HARDWARE */
+
 /*****************************************************************************
  *
  * Debugger globals
diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h
index 677793e938f5..5ccb99ae3a6f 100644
--- a/drivers/acpi/acpica/achware.h
+++ b/drivers/acpi/acpica/achware.h
@@ -81,6 +81,26 @@ acpi_status acpi_hw_register_write(u32 register_id, u32 value);
 acpi_status acpi_hw_clear_acpi_status(void);
 
 /*
+ * hwsleep - sleep/wake support (Legacy sleep registers)
+ */
+acpi_status acpi_hw_legacy_sleep(u8 sleep_state, u8 flags);
+
+acpi_status acpi_hw_legacy_wake_prep(u8 sleep_state, u8 flags);
+
+acpi_status acpi_hw_legacy_wake(u8 sleep_state, u8 flags);
+
+/*
+ * hwesleep - sleep/wake support (Extended FADT-V5 sleep registers)
+ */
+void acpi_hw_execute_sleep_method(char *method_name, u32 integer_argument);
+
+acpi_status acpi_hw_extended_sleep(u8 sleep_state, u8 flags);
+
+acpi_status acpi_hw_extended_wake_prep(u8 sleep_state, u8 flags);
+
+acpi_status acpi_hw_extended_wake(u8 sleep_state, u8 flags);
+
+/*
  * hwvalid - Port I/O with validation
  */
 acpi_status acpi_hw_read_port(acpi_io_address address, u32 *value, u32 width);
@@ -128,16 +148,4 @@ acpi_status
 acpi_hw_derive_pci_id(struct acpi_pci_id *pci_id,
 		      acpi_handle root_pci_device, acpi_handle pci_region);
 
-#ifdef	ACPI_FUTURE_USAGE
-/*
- * hwtimer - ACPI Timer prototypes
- */
-acpi_status acpi_get_timer_resolution(u32 * resolution);
-
-acpi_status acpi_get_timer(u32 * ticks);
-
-acpi_status
-acpi_get_timer_duration(u32 start_ticks, u32 end_ticks, u32 * time_elapsed);
-#endif				/* ACPI_FUTURE_USAGE */
-
 #endif				/* __ACHWARE_H__ */
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 3f24068837d5..e3922ca20e7f 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -370,6 +370,7 @@ struct acpi_predefined_data {
 /* Defines for Flags field above */
 
 #define ACPI_OBJECT_REPAIRED    1
+#define ACPI_OBJECT_WRAPPED     2
 
 /*
  * Bitmapped return value types
diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index ef338a96f5b2..f119f473f71a 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -516,6 +516,12 @@
 
 #endif				/* ACPI_DEBUG_OUTPUT */
 
+#if (!ACPI_REDUCED_HARDWARE)
+#define ACPI_HW_OPTIONAL_FUNCTION(addr)     addr
+#else
+#define ACPI_HW_OPTIONAL_FUNCTION(addr)     NULL
+#endif
+
 /*
  * Some code only gets executed when the debugger is built in.
  * Note that this is entirely independent of whether the
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 2c9e0f049523..9b19d4b86424 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -283,8 +283,9 @@ acpi_ns_repair_object(struct acpi_predefined_data *data,
 		      union acpi_operand_object **return_object_ptr);
 
 acpi_status
-acpi_ns_repair_package_list(struct acpi_predefined_data *data,
-			    union acpi_operand_object **obj_desc_ptr);
+acpi_ns_wrap_with_package(struct acpi_predefined_data *data,
+			  union acpi_operand_object *original_object,
+			  union acpi_operand_object **obj_desc_ptr);
 
 acpi_status
 acpi_ns_repair_null_element(struct acpi_predefined_data *data,
diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h
index d5bec304c823..6712965ba8ae 100644
--- a/drivers/acpi/acpica/actables.h
+++ b/drivers/acpi/acpica/actables.h
@@ -67,6 +67,11 @@ acpi_status acpi_tb_resize_root_table_list(void);
 
 acpi_status acpi_tb_verify_table(struct acpi_table_desc *table_desc);
 
+struct acpi_table_header *acpi_tb_table_override(struct acpi_table_header
+						 *table_header,
+						 struct acpi_table_desc
+						 *table_desc);
+
 acpi_status
 acpi_tb_add_table(struct acpi_table_desc *table_desc, u32 *table_index);
 
diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c
index 6729ebe2f1e6..07e4dc44f81c 100644
--- a/drivers/acpi/acpica/evevent.c
+++ b/drivers/acpi/acpica/evevent.c
@@ -47,7 +47,7 @@
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evevent")
-
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /* Local prototypes */
 static acpi_status acpi_ev_fixed_event_initialize(void);
 
@@ -291,3 +291,5 @@ static u32 acpi_ev_fixed_event_dispatch(u32 event)
 	return ((acpi_gbl_fixed_event_handlers[event].
 		 handler) (acpi_gbl_fixed_event_handlers[event].context));
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c
index 5e5683cb1f0d..cfeab38795d8 100644
--- a/drivers/acpi/acpica/evglock.c
+++ b/drivers/acpi/acpica/evglock.c
@@ -48,7 +48,7 @@
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evglock")
-
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /* Local prototypes */
 static u32 acpi_ev_global_lock_handler(void *context);
 
@@ -339,3 +339,5 @@ acpi_status acpi_ev_release_global_lock(void)
 	acpi_os_release_mutex(acpi_gbl_global_lock_mutex->mutex.os_mutex);
 	return_ACPI_STATUS(status);
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index 9e88cb6fb25e..8ba0e5f17091 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -48,7 +48,7 @@
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evgpe")
-
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /* Local prototypes */
 static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context);
 
@@ -766,3 +766,5 @@ acpi_ev_gpe_dispatch(struct acpi_namespace_node *gpe_device,
 
 	return_UINT32(ACPI_INTERRUPT_HANDLED);
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index be75339cd5dd..23a3ca86b2eb 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -48,7 +48,7 @@
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evgpeblk")
-
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /* Local prototypes */
 static acpi_status
 acpi_ev_install_gpe_block(struct acpi_gpe_block_info *gpe_block,
@@ -504,3 +504,5 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 
 	return_ACPI_STATUS(AE_OK);
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index adf7494da9db..da0add858f81 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -48,7 +48,7 @@
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evgpeinit")
-
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /*
  * Note: History of _PRW support in ACPICA
  *
@@ -440,3 +440,5 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 			  name, gpe_number));
 	return_ACPI_STATUS(AE_OK);
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index 25073932aa10..3c43796b8361 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -48,6 +48,7 @@
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evgpeutil")
 
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ev_walk_gpe_list
@@ -374,3 +375,5 @@ acpi_ev_delete_gpe_handlers(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 
 	return_ACPI_STATUS(AE_OK);
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index 84966f416463..51ef9f5e002d 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -108,27 +108,30 @@ acpi_ev_queue_notify_request(struct acpi_namespace_node * node,
 	ACPI_FUNCTION_NAME(ev_queue_notify_request);
 
 	/*
-	 * For value 3 (Ejection Request), some device method may need to be run.
-	 * For value 2 (Device Wake) if _PRW exists, the _PS0 method may need
-	 *   to be run.
+	 * For value 0x03 (Ejection Request), may need to run a device method.
+	 * For value 0x02 (Device Wake), if _PRW exists, may need to run
+	 *   the _PS0 method.
 	 * For value 0x80 (Status Change) on the power button or sleep button,
-	 *   initiate soft-off or sleep operation?
+	 *   initiate soft-off or sleep operation.
+	 *
+	 * For all cases, simply dispatch the notify to the handler.
 	 */
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-			  "Dispatching Notify on [%4.4s] Node %p Value 0x%2.2X (%s)\n",
-			  acpi_ut_get_node_name(node), node, notify_value,
-			  acpi_ut_get_notify_name(notify_value)));
+			  "Dispatching Notify on [%4.4s] (%s) Value 0x%2.2X (%s) Node %p\n",
+			  acpi_ut_get_node_name(node),
+			  acpi_ut_get_type_name(node->type), notify_value,
+			  acpi_ut_get_notify_name(notify_value), node));
 
 	/* Get the notify object attached to the NS Node */
 
 	obj_desc = acpi_ns_get_attached_object(node);
 	if (obj_desc) {
 
-		/* We have the notify object, Get the right handler */
+		/* We have the notify object, Get the correct handler */
 
 		switch (node->type) {
 
-			/* Notify allowed only on these types */
+			/* Notify is allowed only on these types */
 
 		case ACPI_TYPE_DEVICE:
 		case ACPI_TYPE_THERMAL:
@@ -152,7 +155,7 @@ acpi_ev_queue_notify_request(struct acpi_namespace_node * node,
 	}
 
 	/*
-	 * If there is any handler to run, schedule the dispatcher.
+	 * If there is a handler to run, schedule the dispatcher.
 	 * Check for:
 	 * 1) Global system notify handler
 	 * 2) Global device notify handler
@@ -270,6 +273,7 @@ static void ACPI_SYSTEM_XFACE acpi_ev_notify_dispatch(void *context)
 	acpi_ut_delete_generic_state(notify_info);
 }
 
+#if (!ACPI_REDUCED_HARDWARE)
 /******************************************************************************
  *
  * FUNCTION:    acpi_ev_terminate
@@ -338,3 +342,5 @@ void acpi_ev_terminate(void)
 	}
 	return_VOID;
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evsci.c b/drivers/acpi/acpica/evsci.c
index 26065c612e76..6a57aa2d70d1 100644
--- a/drivers/acpi/acpica/evsci.c
+++ b/drivers/acpi/acpica/evsci.c
@@ -48,7 +48,7 @@
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evsci")
-
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /* Local prototypes */
 static u32 ACPI_SYSTEM_XFACE acpi_ev_sci_xrupt_handler(void *context);
 
@@ -181,3 +181,5 @@ acpi_status acpi_ev_remove_sci_handler(void)
 
 	return_ACPI_STATUS(status);
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index 61944e89565a..44bef5744ebb 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -51,222 +51,6 @@
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evxface")
 
-/*******************************************************************************
- *
- * FUNCTION:    acpi_install_exception_handler
- *
- * PARAMETERS:  Handler         - Pointer to the handler function for the
- *                                event
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Saves the pointer to the handler function
- *
- ******************************************************************************/
-#ifdef ACPI_FUTURE_USAGE
-acpi_status acpi_install_exception_handler(acpi_exception_handler handler)
-{
-	acpi_status status;
-
-	ACPI_FUNCTION_TRACE(acpi_install_exception_handler);
-
-	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	/* Don't allow two handlers. */
-
-	if (acpi_gbl_exception_handler) {
-		status = AE_ALREADY_EXISTS;
-		goto cleanup;
-	}
-
-	/* Install the handler */
-
-	acpi_gbl_exception_handler = handler;
-
-      cleanup:
-	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
-	return_ACPI_STATUS(status);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_install_exception_handler)
-#endif				/*  ACPI_FUTURE_USAGE  */
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_install_global_event_handler
- *
- * PARAMETERS:  Handler         - Pointer to the global event handler function
- *              Context         - Value passed to the handler on each event
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Saves the pointer to the handler function. The global handler
- *              is invoked upon each incoming GPE and Fixed Event. It is
- *              invoked at interrupt level at the time of the event dispatch.
- *              Can be used to update event counters, etc.
- *
- ******************************************************************************/
-acpi_status
-acpi_install_global_event_handler(ACPI_GBL_EVENT_HANDLER handler, void *context)
-{
-	acpi_status status;
-
-	ACPI_FUNCTION_TRACE(acpi_install_global_event_handler);
-
-	/* Parameter validation */
-
-	if (!handler) {
-		return_ACPI_STATUS(AE_BAD_PARAMETER);
-	}
-
-	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	/* Don't allow two handlers. */
-
-	if (acpi_gbl_global_event_handler) {
-		status = AE_ALREADY_EXISTS;
-		goto cleanup;
-	}
-
-	acpi_gbl_global_event_handler = handler;
-	acpi_gbl_global_event_handler_context = context;
-
-      cleanup:
-	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
-	return_ACPI_STATUS(status);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_install_global_event_handler)
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_install_fixed_event_handler
- *
- * PARAMETERS:  Event           - Event type to enable.
- *              Handler         - Pointer to the handler function for the
- *                                event
- *              Context         - Value passed to the handler on each GPE
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Saves the pointer to the handler function and then enables the
- *              event.
- *
- ******************************************************************************/
-acpi_status
-acpi_install_fixed_event_handler(u32 event,
-				 acpi_event_handler handler, void *context)
-{
-	acpi_status status;
-
-	ACPI_FUNCTION_TRACE(acpi_install_fixed_event_handler);
-
-	/* Parameter validation */
-
-	if (event > ACPI_EVENT_MAX) {
-		return_ACPI_STATUS(AE_BAD_PARAMETER);
-	}
-
-	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	/* Don't allow two handlers. */
-
-	if (NULL != acpi_gbl_fixed_event_handlers[event].handler) {
-		status = AE_ALREADY_EXISTS;
-		goto cleanup;
-	}
-
-	/* Install the handler before enabling the event */
-
-	acpi_gbl_fixed_event_handlers[event].handler = handler;
-	acpi_gbl_fixed_event_handlers[event].context = context;
-
-	status = acpi_clear_event(event);
-	if (ACPI_SUCCESS(status))
-		status = acpi_enable_event(event, 0);
-	if (ACPI_FAILURE(status)) {
-		ACPI_WARNING((AE_INFO, "Could not enable fixed event 0x%X",
-			      event));
-
-		/* Remove the handler */
-
-		acpi_gbl_fixed_event_handlers[event].handler = NULL;
-		acpi_gbl_fixed_event_handlers[event].context = NULL;
-	} else {
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-				  "Enabled fixed event %X, Handler=%p\n", event,
-				  handler));
-	}
-
-      cleanup:
-	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
-	return_ACPI_STATUS(status);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_install_fixed_event_handler)
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_remove_fixed_event_handler
- *
- * PARAMETERS:  Event           - Event type to disable.
- *              Handler         - Address of the handler
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Disables the event and unregisters the event handler.
- *
- ******************************************************************************/
-acpi_status
-acpi_remove_fixed_event_handler(u32 event, acpi_event_handler handler)
-{
-	acpi_status status = AE_OK;
-
-	ACPI_FUNCTION_TRACE(acpi_remove_fixed_event_handler);
-
-	/* Parameter validation */
-
-	if (event > ACPI_EVENT_MAX) {
-		return_ACPI_STATUS(AE_BAD_PARAMETER);
-	}
-
-	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	/* Disable the event before removing the handler */
-
-	status = acpi_disable_event(event, 0);
-
-	/* Always Remove the handler */
-
-	acpi_gbl_fixed_event_handlers[event].handler = NULL;
-	acpi_gbl_fixed_event_handlers[event].context = NULL;
-
-	if (ACPI_FAILURE(status)) {
-		ACPI_WARNING((AE_INFO,
-			      "Could not write to fixed event enable register 0x%X",
-			      event));
-	} else {
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Disabled fixed event %X\n",
-				  event));
-	}
-
-	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
-	return_ACPI_STATUS(status);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_remove_fixed_event_handler)
 
 /*******************************************************************************
  *
@@ -334,6 +118,7 @@ acpi_add_handler_object(struct acpi_object_notify_handler *parent_obj,
 	return AE_OK;
 }
 
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_install_notify_handler
@@ -705,6 +490,224 @@ ACPI_EXPORT_SYMBOL(acpi_remove_notify_handler)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_install_exception_handler
+ *
+ * PARAMETERS:  Handler         - Pointer to the handler function for the
+ *                                event
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Saves the pointer to the handler function
+ *
+ ******************************************************************************/
+#ifdef ACPI_FUTURE_USAGE
+acpi_status acpi_install_exception_handler(acpi_exception_handler handler)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_install_exception_handler);
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Don't allow two handlers. */
+
+	if (acpi_gbl_exception_handler) {
+		status = AE_ALREADY_EXISTS;
+		goto cleanup;
+	}
+
+	/* Install the handler */
+
+	acpi_gbl_exception_handler = handler;
+
+      cleanup:
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_install_exception_handler)
+#endif				/*  ACPI_FUTURE_USAGE  */
+
+#if (!ACPI_REDUCED_HARDWARE)
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_install_global_event_handler
+ *
+ * PARAMETERS:  Handler         - Pointer to the global event handler function
+ *              Context         - Value passed to the handler on each event
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Saves the pointer to the handler function. The global handler
+ *              is invoked upon each incoming GPE and Fixed Event. It is
+ *              invoked at interrupt level at the time of the event dispatch.
+ *              Can be used to update event counters, etc.
+ *
+ ******************************************************************************/
+acpi_status
+acpi_install_global_event_handler(ACPI_GBL_EVENT_HANDLER handler, void *context)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_install_global_event_handler);
+
+	/* Parameter validation */
+
+	if (!handler) {
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
+	}
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Don't allow two handlers. */
+
+	if (acpi_gbl_global_event_handler) {
+		status = AE_ALREADY_EXISTS;
+		goto cleanup;
+	}
+
+	acpi_gbl_global_event_handler = handler;
+	acpi_gbl_global_event_handler_context = context;
+
+      cleanup:
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_install_global_event_handler)
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_install_fixed_event_handler
+ *
+ * PARAMETERS:  Event           - Event type to enable.
+ *              Handler         - Pointer to the handler function for the
+ *                                event
+ *              Context         - Value passed to the handler on each GPE
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Saves the pointer to the handler function and then enables the
+ *              event.
+ *
+ ******************************************************************************/
+acpi_status
+acpi_install_fixed_event_handler(u32 event,
+				 acpi_event_handler handler, void *context)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_install_fixed_event_handler);
+
+	/* Parameter validation */
+
+	if (event > ACPI_EVENT_MAX) {
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
+	}
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Don't allow two handlers. */
+
+	if (NULL != acpi_gbl_fixed_event_handlers[event].handler) {
+		status = AE_ALREADY_EXISTS;
+		goto cleanup;
+	}
+
+	/* Install the handler before enabling the event */
+
+	acpi_gbl_fixed_event_handlers[event].handler = handler;
+	acpi_gbl_fixed_event_handlers[event].context = context;
+
+	status = acpi_clear_event(event);
+	if (ACPI_SUCCESS(status))
+		status = acpi_enable_event(event, 0);
+	if (ACPI_FAILURE(status)) {
+		ACPI_WARNING((AE_INFO, "Could not enable fixed event 0x%X",
+			      event));
+
+		/* Remove the handler */
+
+		acpi_gbl_fixed_event_handlers[event].handler = NULL;
+		acpi_gbl_fixed_event_handlers[event].context = NULL;
+	} else {
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
+				  "Enabled fixed event %X, Handler=%p\n", event,
+				  handler));
+	}
+
+      cleanup:
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_install_fixed_event_handler)
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_remove_fixed_event_handler
+ *
+ * PARAMETERS:  Event           - Event type to disable.
+ *              Handler         - Address of the handler
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Disables the event and unregisters the event handler.
+ *
+ ******************************************************************************/
+acpi_status
+acpi_remove_fixed_event_handler(u32 event, acpi_event_handler handler)
+{
+	acpi_status status = AE_OK;
+
+	ACPI_FUNCTION_TRACE(acpi_remove_fixed_event_handler);
+
+	/* Parameter validation */
+
+	if (event > ACPI_EVENT_MAX) {
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
+	}
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Disable the event before removing the handler */
+
+	status = acpi_disable_event(event, 0);
+
+	/* Always Remove the handler */
+
+	acpi_gbl_fixed_event_handlers[event].handler = NULL;
+	acpi_gbl_fixed_event_handlers[event].context = NULL;
+
+	if (ACPI_FAILURE(status)) {
+		ACPI_WARNING((AE_INFO,
+			      "Could not write to fixed event enable register 0x%X",
+			      event));
+	} else {
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Disabled fixed event %X\n",
+				  event));
+	}
+
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_remove_fixed_event_handler)
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_install_gpe_handler
  *
  * PARAMETERS:  gpe_device      - Namespace node for the GPE (NULL for FADT
@@ -984,3 +987,4 @@ acpi_status acpi_release_global_lock(u32 handle)
 }
 
 ACPI_EXPORT_SYMBOL(acpi_release_global_lock)
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c
index 1768bbec1002..77cee5a5e891 100644
--- a/drivers/acpi/acpica/evxfevnt.c
+++ b/drivers/acpi/acpica/evxfevnt.c
@@ -49,6 +49,7 @@
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evxfevnt")
 
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /*******************************************************************************
  *
  * FUNCTION:    acpi_enable
@@ -352,3 +353,4 @@ acpi_status acpi_get_event_status(u32 event, acpi_event_status * event_status)
 }
 
 ACPI_EXPORT_SYMBOL(acpi_get_event_status)
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 33388fd69df4..86f9b343ebd4 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -50,6 +50,7 @@
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evxfgpe")
 
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /******************************************************************************
  *
  * FUNCTION:    acpi_update_all_gpes
@@ -695,3 +696,4 @@ acpi_get_gpe_device(u32 index, acpi_handle *gpe_device)
 }
 
 ACPI_EXPORT_SYMBOL(acpi_get_gpe_device)
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c
index d21ec5f0b3a9..d0b9ed5df97e 100644
--- a/drivers/acpi/acpica/hwacpi.c
+++ b/drivers/acpi/acpica/hwacpi.c
@@ -48,6 +48,7 @@
 #define _COMPONENT          ACPI_HARDWARE
 ACPI_MODULE_NAME("hwacpi")
 
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /******************************************************************************
  *
  * FUNCTION:    acpi_hw_set_mode
@@ -166,3 +167,5 @@ u32 acpi_hw_get_mode(void)
 		return_UINT32(ACPI_SYS_MODE_LEGACY);
 	}
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c
new file mode 100644
index 000000000000..29e859293edd
--- /dev/null
+++ b/drivers/acpi/acpica/hwesleep.c
@@ -0,0 +1,247 @@
+/******************************************************************************
+ *
+ * Name: hwesleep.c - ACPI Hardware Sleep/Wake Support functions for the
+ *                    extended FADT-V5 sleep registers.
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2012, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#include <acpi/acpi.h>
+#include "accommon.h"
+
+#define _COMPONENT          ACPI_HARDWARE
+ACPI_MODULE_NAME("hwesleep")
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_hw_execute_sleep_method
+ *
+ * PARAMETERS:  method_pathname     - Pathname of method to execute
+ *              integer_argument    - Argument to pass to the method
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Execute a sleep/wake related method with one integer argument
+ *              and no return value.
+ *
+ ******************************************************************************/
+void acpi_hw_execute_sleep_method(char *method_pathname, u32 integer_argument)
+{
+	struct acpi_object_list arg_list;
+	union acpi_object arg;
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(hw_execute_sleep_method);
+
+	/* One argument, integer_argument; No return value expected */
+
+	arg_list.count = 1;
+	arg_list.pointer = &arg;
+	arg.type = ACPI_TYPE_INTEGER;
+	arg.integer.value = (u64)integer_argument;
+
+	status = acpi_evaluate_object(NULL, method_pathname, &arg_list, NULL);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		ACPI_EXCEPTION((AE_INFO, status, "While executing method %s",
+				method_pathname));
+	}
+
+	return_VOID;
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_hw_extended_sleep
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state to enter
+ *              Flags               - ACPI_EXECUTE_GTS to run optional method
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Enter a system sleep state via the extended FADT sleep
+ *              registers (V5 FADT).
+ *              THIS FUNCTION MUST BE CALLED WITH INTERRUPTS DISABLED
+ *
+ ******************************************************************************/
+
+acpi_status acpi_hw_extended_sleep(u8 sleep_state, u8 flags)
+{
+	acpi_status status;
+	u8 sleep_type_value;
+	u64 sleep_status;
+
+	ACPI_FUNCTION_TRACE(hw_extended_sleep);
+
+	/* Extended sleep registers must be valid */
+
+	if (!acpi_gbl_FADT.sleep_control.address ||
+	    !acpi_gbl_FADT.sleep_status.address) {
+		return_ACPI_STATUS(AE_NOT_EXIST);
+	}
+
+	/* Clear wake status (WAK_STS) */
+
+	status = acpi_write(ACPI_X_WAKE_STATUS, &acpi_gbl_FADT.sleep_status);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	acpi_gbl_system_awake_and_running = FALSE;
+
+	/* Optionally execute _GTS (Going To Sleep) */
+
+	if (flags & ACPI_EXECUTE_GTS) {
+		acpi_hw_execute_sleep_method(METHOD_PATHNAME__GTS, sleep_state);
+	}
+
+	/* Flush caches, as per ACPI specification */
+
+	ACPI_FLUSH_CPU_CACHE();
+
+	/*
+	 * Set the SLP_TYP and SLP_EN bits.
+	 *
+	 * Note: We only use the first value returned by the \_Sx method
+	 * (acpi_gbl_sleep_type_a) - As per ACPI specification.
+	 */
+	ACPI_DEBUG_PRINT((ACPI_DB_INIT,
+			  "Entering sleep state [S%u]\n", sleep_state));
+
+	sleep_type_value =
+	    ((acpi_gbl_sleep_type_a << ACPI_X_SLEEP_TYPE_POSITION) &
+	     ACPI_X_SLEEP_TYPE_MASK);
+
+	status = acpi_write((sleep_type_value | ACPI_X_SLEEP_ENABLE),
+			    &acpi_gbl_FADT.sleep_control);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Wait for transition back to Working State */
+
+	do {
+		status = acpi_read(&sleep_status, &acpi_gbl_FADT.sleep_status);
+		if (ACPI_FAILURE(status)) {
+			return_ACPI_STATUS(status);
+		}
+
+	} while (!(((u8)sleep_status) & ACPI_X_WAKE_STATUS));
+
+	return_ACPI_STATUS(AE_OK);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_hw_extended_wake_prep
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state we just exited
+ *              Flags               - ACPI_EXECUTE_BFS to run optional method
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Perform first part of OS-independent ACPI cleanup after
+ *              a sleep. Called with interrupts ENABLED.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_hw_extended_wake_prep(u8 sleep_state, u8 flags)
+{
+	acpi_status status;
+	u8 sleep_type_value;
+
+	ACPI_FUNCTION_TRACE(hw_extended_wake_prep);
+
+	status = acpi_get_sleep_type_data(ACPI_STATE_S0,
+					  &acpi_gbl_sleep_type_a,
+					  &acpi_gbl_sleep_type_b);
+	if (ACPI_SUCCESS(status)) {
+		sleep_type_value =
+		    ((acpi_gbl_sleep_type_a << ACPI_X_SLEEP_TYPE_POSITION) &
+		     ACPI_X_SLEEP_TYPE_MASK);
+
+		(void)acpi_write((sleep_type_value | ACPI_X_SLEEP_ENABLE),
+				 &acpi_gbl_FADT.sleep_control);
+	}
+
+	/* Optionally execute _BFS (Back From Sleep) */
+
+	if (flags & ACPI_EXECUTE_BFS) {
+		acpi_hw_execute_sleep_method(METHOD_PATHNAME__BFS, sleep_state);
+	}
+	return_ACPI_STATUS(AE_OK);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_hw_extended_wake
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state we just exited
+ *              Flags               - Reserved, set to zero
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Perform OS-independent ACPI cleanup after a sleep
+ *              Called with interrupts ENABLED.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_hw_extended_wake(u8 sleep_state, u8 flags)
+{
+	ACPI_FUNCTION_TRACE(hw_extended_wake);
+
+	/* Ensure enter_sleep_state_prep -> enter_sleep_state ordering */
+
+	acpi_gbl_sleep_type_a = ACPI_SLEEP_TYPE_INVALID;
+
+	/* Execute the wake methods */
+
+	acpi_hw_execute_sleep_method(METHOD_PATHNAME__SST, ACPI_SST_WAKING);
+	acpi_hw_execute_sleep_method(METHOD_PATHNAME__WAK, sleep_state);
+
+	/*
+	 * Some BIOS code assumes that WAK_STS will be cleared on resume
+	 * and use it to determine whether the system is rebooting or
+	 * resuming. Clear WAK_STS for compatibility.
+	 */
+	(void)acpi_write(ACPI_X_WAKE_STATUS, &acpi_gbl_FADT.sleep_status);
+	acpi_gbl_system_awake_and_running = TRUE;
+
+	acpi_hw_execute_sleep_method(METHOD_PATHNAME__SST, ACPI_SST_WORKING);
+	return_ACPI_STATUS(AE_OK);
+}
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index 1a6894afef79..25bd28c4ae8d 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -48,7 +48,7 @@
 
 #define _COMPONENT          ACPI_HARDWARE
 ACPI_MODULE_NAME("hwgpe")
-
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /* Local prototypes */
 static acpi_status
 acpi_hw_enable_wakeup_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
@@ -479,3 +479,5 @@ acpi_status acpi_hw_enable_all_wakeup_gpes(void)
 	status = acpi_ev_walk_gpe_list(acpi_hw_enable_wakeup_gpe_block, NULL);
 	return_ACPI_STATUS(status);
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 4ea4eeb51bfd..6b6c83b87b52 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -51,6 +51,7 @@
 #define _COMPONENT          ACPI_HARDWARE
 ACPI_MODULE_NAME("hwregs")
 
+#if (!ACPI_REDUCED_HARDWARE)
 /* Local Prototypes */
 static acpi_status
 acpi_hw_read_multiple(u32 *value,
@@ -62,6 +63,8 @@ acpi_hw_write_multiple(u32 value,
 		       struct acpi_generic_address *register_a,
 		       struct acpi_generic_address *register_b);
 
+#endif				/* !ACPI_REDUCED_HARDWARE */
+
 /******************************************************************************
  *
  * FUNCTION:    acpi_hw_validate_register
@@ -154,6 +157,7 @@ acpi_hw_validate_register(struct acpi_generic_address *reg,
 acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg)
 {
 	u64 address;
+	u64 value64;
 	acpi_status status;
 
 	ACPI_FUNCTION_NAME(hw_read);
@@ -175,7 +179,9 @@ acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg)
 	 */
 	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
 		status = acpi_os_read_memory((acpi_physical_address)
-					     address, value, reg->bit_width);
+					     address, &value64, reg->bit_width);
+
+		*value = (u32)value64;
 	} else {		/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
 
 		status = acpi_hw_read_port((acpi_io_address)
@@ -225,7 +231,8 @@ acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg)
 	 */
 	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
 		status = acpi_os_write_memory((acpi_physical_address)
-					      address, value, reg->bit_width);
+					      address, (u64)value,
+					      reg->bit_width);
 	} else {		/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
 
 		status = acpi_hw_write_port((acpi_io_address)
@@ -240,6 +247,7 @@ acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg)
 	return (status);
 }
 
+#if (!ACPI_REDUCED_HARDWARE)
 /*******************************************************************************
  *
  * FUNCTION:    acpi_hw_clear_acpi_status
@@ -285,7 +293,7 @@ exit:
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_hw_get_register_bit_mask
+ * FUNCTION:    acpi_hw_get_bit_register_info
  *
  * PARAMETERS:  register_id         - Index of ACPI Register to access
  *
@@ -658,3 +666,5 @@ acpi_hw_write_multiple(u32 value,
 
 	return (status);
 }
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c
index 3c4a922a9fc2..0ed85cac3231 100644
--- a/drivers/acpi/acpica/hwsleep.c
+++ b/drivers/acpi/acpica/hwsleep.c
@@ -1,7 +1,7 @@
-
 /******************************************************************************
  *
- * Name: hwsleep.c - ACPI Hardware Sleep/Wake Interface
+ * Name: hwsleep.c - ACPI Hardware Sleep/Wake Support functions for the
+ *                   original/legacy sleep/PM registers.
  *
  *****************************************************************************/
 
@@ -43,213 +43,37 @@
  */
 
 #include <acpi/acpi.h>
+#include <linux/acpi.h>
 #include "accommon.h"
-#include "actables.h"
-#include <linux/tboot.h>
 #include <linux/module.h>
 
 #define _COMPONENT          ACPI_HARDWARE
 ACPI_MODULE_NAME("hwsleep")
 
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /*******************************************************************************
  *
- * FUNCTION:    acpi_set_firmware_waking_vector
- *
- * PARAMETERS:  physical_address    - 32-bit physical address of ACPI real mode
- *                                    entry point.
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Sets the 32-bit firmware_waking_vector field of the FACS
- *
- ******************************************************************************/
-acpi_status
-acpi_set_firmware_waking_vector(u32 physical_address)
-{
-	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector);
-
-
-	/*
-	 * According to the ACPI specification 2.0c and later, the 64-bit
-	 * waking vector should be cleared and the 32-bit waking vector should
-	 * be used, unless we want the wake-up code to be called by the BIOS in
-	 * Protected Mode.  Some systems (for example HP dv5-1004nr) are known
-	 * to fail to resume if the 64-bit vector is used.
-	 */
-
-	/* Set the 32-bit vector */
-
-	acpi_gbl_FACS->firmware_waking_vector = physical_address;
-
-	/* Clear the 64-bit vector if it exists */
-
-	if ((acpi_gbl_FACS->length > 32) && (acpi_gbl_FACS->version >= 1)) {
-		acpi_gbl_FACS->xfirmware_waking_vector = 0;
-	}
-
-	return_ACPI_STATUS(AE_OK);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector)
-
-#if ACPI_MACHINE_WIDTH == 64
-/*******************************************************************************
- *
- * FUNCTION:    acpi_set_firmware_waking_vector64
- *
- * PARAMETERS:  physical_address    - 64-bit physical address of ACPI protected
- *                                    mode entry point.
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Sets the 64-bit X_firmware_waking_vector field of the FACS, if
- *              it exists in the table. This function is intended for use with
- *              64-bit host operating systems.
- *
- ******************************************************************************/
-acpi_status
-acpi_set_firmware_waking_vector64(u64 physical_address)
-{
-	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector64);
-
-
-	/* Determine if the 64-bit vector actually exists */
-
-	if ((acpi_gbl_FACS->length <= 32) || (acpi_gbl_FACS->version < 1)) {
-		return_ACPI_STATUS(AE_NOT_EXIST);
-	}
-
-	/* Clear 32-bit vector, set the 64-bit X_ vector */
-
-	acpi_gbl_FACS->firmware_waking_vector = 0;
-	acpi_gbl_FACS->xfirmware_waking_vector = physical_address;
-
-	return_ACPI_STATUS(AE_OK);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector64)
-#endif
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_enter_sleep_state_prep
- *
- * PARAMETERS:  sleep_state         - Which sleep state to enter
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Prepare to enter a system sleep state (see ACPI 2.0 spec p 231)
- *              This function must execute with interrupts enabled.
- *              We break sleeping into 2 stages so that OSPM can handle
- *              various OS-specific tasks between the two steps.
- *
- ******************************************************************************/
-acpi_status acpi_enter_sleep_state_prep(u8 sleep_state)
-{
-	acpi_status status;
-	struct acpi_object_list arg_list;
-	union acpi_object arg;
-
-	ACPI_FUNCTION_TRACE(acpi_enter_sleep_state_prep);
-
-	/* _PSW methods could be run here to enable wake-on keyboard, LAN, etc. */
-
-	status = acpi_get_sleep_type_data(sleep_state,
-					  &acpi_gbl_sleep_type_a,
-					  &acpi_gbl_sleep_type_b);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	/* Setup parameter object */
-
-	arg_list.count = 1;
-	arg_list.pointer = &arg;
-
-	arg.type = ACPI_TYPE_INTEGER;
-	arg.integer.value = sleep_state;
-
-	/* Run the _PTS method */
-
-	status = acpi_evaluate_object(NULL, METHOD_NAME__PTS, &arg_list, NULL);
-	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-		return_ACPI_STATUS(status);
-	}
-
-	/* Setup the argument to _SST */
-
-	switch (sleep_state) {
-	case ACPI_STATE_S0:
-		arg.integer.value = ACPI_SST_WORKING;
-		break;
-
-	case ACPI_STATE_S1:
-	case ACPI_STATE_S2:
-	case ACPI_STATE_S3:
-		arg.integer.value = ACPI_SST_SLEEPING;
-		break;
-
-	case ACPI_STATE_S4:
-		arg.integer.value = ACPI_SST_SLEEP_CONTEXT;
-		break;
-
-	default:
-		arg.integer.value = ACPI_SST_INDICATOR_OFF;	/* Default is off */
-		break;
-	}
-
-	/*
-	 * Set the system indicators to show the desired sleep state.
-	 * _SST is an optional method (return no error if not found)
-	 */
-	status = acpi_evaluate_object(NULL, METHOD_NAME__SST, &arg_list, NULL);
-	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-		ACPI_EXCEPTION((AE_INFO, status,
-				"While executing method _SST"));
-	}
-
-	return_ACPI_STATUS(AE_OK);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_enter_sleep_state_prep)
-
-static unsigned int gts, bfs;
-module_param(gts, uint, 0644);
-module_param(bfs, uint, 0644);
-MODULE_PARM_DESC(gts, "Enable evaluation of _GTS on suspend.");
-MODULE_PARM_DESC(bfs, "Enable evaluation of _BFS on resume".);
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_enter_sleep_state
+ * FUNCTION:    acpi_hw_legacy_sleep
  *
  * PARAMETERS:  sleep_state         - Which sleep state to enter
+ *              Flags               - ACPI_EXECUTE_GTS to run optional method
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Enter a system sleep state (see ACPI 2.0 spec p 231)
+ * DESCRIPTION: Enter a system sleep state via the legacy FADT PM registers
  *              THIS FUNCTION MUST BE CALLED WITH INTERRUPTS DISABLED
  *
  ******************************************************************************/
-acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state)
+acpi_status acpi_hw_legacy_sleep(u8 sleep_state, u8 flags)
 {
-	u32 pm1a_control;
-	u32 pm1b_control;
 	struct acpi_bit_register_info *sleep_type_reg_info;
 	struct acpi_bit_register_info *sleep_enable_reg_info;
+	u32 pm1a_control;
+	u32 pm1b_control;
 	u32 in_value;
-	struct acpi_object_list arg_list;
-	union acpi_object arg;
 	acpi_status status;
 
-	ACPI_FUNCTION_TRACE(acpi_enter_sleep_state);
-
-	if ((acpi_gbl_sleep_type_a > ACPI_SLEEP_TYPE_MAX) ||
-	    (acpi_gbl_sleep_type_b > ACPI_SLEEP_TYPE_MAX)) {
-		ACPI_ERROR((AE_INFO, "Sleep values out of range: A=0x%X B=0x%X",
-			    acpi_gbl_sleep_type_a, acpi_gbl_sleep_type_b));
-		return_ACPI_STATUS(AE_AML_OPERAND_VALUE);
-	}
+	ACPI_FUNCTION_TRACE(hw_legacy_sleep);
 
 	sleep_type_reg_info =
 	    acpi_hw_get_bit_register_info(ACPI_BITREG_SLEEP_TYPE);
@@ -271,6 +95,18 @@ acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state)
 		return_ACPI_STATUS(status);
 	}
 
+	if (sleep_state != ACPI_STATE_S5) {
+		/*
+		 * Disable BM arbitration. This feature is contained within an
+		 * optional register (PM2 Control), so ignore a BAD_ADDRESS
+		 * exception.
+		 */
+		status = acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1);
+		if (ACPI_FAILURE(status) && (status != AE_BAD_ADDRESS)) {
+			return_ACPI_STATUS(status);
+		}
+	}
+
 	/*
 	 * 1) Disable/Clear all GPEs
 	 * 2) Enable all wakeup GPEs
@@ -286,18 +122,10 @@ acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state)
 		return_ACPI_STATUS(status);
 	}
 
-	if (gts) {
-		/* Execute the _GTS method */
-
-		arg_list.count = 1;
-		arg_list.pointer = &arg;
-		arg.type = ACPI_TYPE_INTEGER;
-		arg.integer.value = sleep_state;
+	/* Optionally execute _GTS (Going To Sleep) */
 
-		status = acpi_evaluate_object(NULL, METHOD_NAME__GTS, &arg_list, NULL);
-		if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-			return_ACPI_STATUS(status);
-		}
+	if (flags & ACPI_EXECUTE_GTS) {
+		acpi_hw_execute_sleep_method(METHOD_PATHNAME__GTS, sleep_state);
 	}
 
 	/* Get current value of PM1A control */
@@ -344,8 +172,12 @@ acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state)
 
 	ACPI_FLUSH_CPU_CACHE();
 
-	tboot_sleep(sleep_state, pm1a_control, pm1b_control);
-
+	status = acpi_os_prepare_sleep(sleep_state, pm1a_control,
+				       pm1b_control);
+	if (ACPI_SKIP(status))
+		return_ACPI_STATUS(AE_OK);
+	if (ACPI_FAILURE(status))
+		return_ACPI_STATUS(status);
 	/* Write #2: Write both SLP_TYP + SLP_EN */
 
 	status = acpi_hw_write_pm1_control(pm1a_control, pm1b_control);
@@ -375,114 +207,44 @@ acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state)
 		}
 	}
 
-	/* Wait until we enter sleep state */
-
-	do {
-		status = acpi_read_bit_register(ACPI_BITREG_WAKE_STATUS,
-						    &in_value);
-		if (ACPI_FAILURE(status)) {
-			return_ACPI_STATUS(status);
-		}
-
-		/* Spin until we wake */
-
-	} while (!in_value);
-
-	return_ACPI_STATUS(AE_OK);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_enter_sleep_state)
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_enter_sleep_state_s4bios
- *
- * PARAMETERS:  None
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Perform a S4 bios request.
- *              THIS FUNCTION MUST BE CALLED WITH INTERRUPTS DISABLED
- *
- ******************************************************************************/
-acpi_status asmlinkage acpi_enter_sleep_state_s4bios(void)
-{
-	u32 in_value;
-	acpi_status status;
-
-	ACPI_FUNCTION_TRACE(acpi_enter_sleep_state_s4bios);
-
-	/* Clear the wake status bit (PM1) */
-
-	status =
-	    acpi_write_bit_register(ACPI_BITREG_WAKE_STATUS, ACPI_CLEAR_STATUS);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	status = acpi_hw_clear_acpi_status();
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	/*
-	 * 1) Disable/Clear all GPEs
-	 * 2) Enable all wakeup GPEs
-	 */
-	status = acpi_hw_disable_all_gpes();
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-	acpi_gbl_system_awake_and_running = FALSE;
-
-	status = acpi_hw_enable_all_wakeup_gpes();
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	ACPI_FLUSH_CPU_CACHE();
-
-	status = acpi_hw_write_port(acpi_gbl_FADT.smi_command,
-				    (u32) acpi_gbl_FADT.S4bios_request, 8);
+	/* Wait for transition back to Working State */
 
 	do {
-		acpi_os_stall(1000);
 		status =
 		    acpi_read_bit_register(ACPI_BITREG_WAKE_STATUS, &in_value);
 		if (ACPI_FAILURE(status)) {
 			return_ACPI_STATUS(status);
 		}
+
 	} while (!in_value);
 
 	return_ACPI_STATUS(AE_OK);
 }
 
-ACPI_EXPORT_SYMBOL(acpi_enter_sleep_state_s4bios)
-
 /*******************************************************************************
  *
- * FUNCTION:    acpi_leave_sleep_state_prep
+ * FUNCTION:    acpi_hw_legacy_wake_prep
  *
- * PARAMETERS:  sleep_state         - Which sleep state we are exiting
+ * PARAMETERS:  sleep_state         - Which sleep state we just exited
+ *              Flags               - ACPI_EXECUTE_BFS to run optional method
  *
  * RETURN:      Status
  *
  * DESCRIPTION: Perform the first state of OS-independent ACPI cleanup after a
  *              sleep.
- *              Called with interrupts DISABLED.
+ *              Called with interrupts ENABLED.
  *
  ******************************************************************************/
-acpi_status acpi_leave_sleep_state_prep(u8 sleep_state)
+
+acpi_status acpi_hw_legacy_wake_prep(u8 sleep_state, u8 flags)
 {
-	struct acpi_object_list arg_list;
-	union acpi_object arg;
 	acpi_status status;
 	struct acpi_bit_register_info *sleep_type_reg_info;
 	struct acpi_bit_register_info *sleep_enable_reg_info;
 	u32 pm1a_control;
 	u32 pm1b_control;
 
-	ACPI_FUNCTION_TRACE(acpi_leave_sleep_state_prep);
+	ACPI_FUNCTION_TRACE(hw_legacy_wake_prep);
 
 	/*
 	 * Set SLP_TYPE and SLP_EN to state S0.
@@ -525,27 +287,20 @@ acpi_status acpi_leave_sleep_state_prep(u8 sleep_state)
 		}
 	}
 
-	if (bfs) {
-		/* Execute the _BFS method */
+	/* Optionally execute _BFS (Back From Sleep) */
 
-		arg_list.count = 1;
-		arg_list.pointer = &arg;
-		arg.type = ACPI_TYPE_INTEGER;
-		arg.integer.value = sleep_state;
-
-		status = acpi_evaluate_object(NULL, METHOD_NAME__BFS, &arg_list, NULL);
-		if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-			ACPI_EXCEPTION((AE_INFO, status, "During Method _BFS"));
-		}
+	if (flags & ACPI_EXECUTE_BFS) {
+		acpi_hw_execute_sleep_method(METHOD_PATHNAME__BFS, sleep_state);
 	}
 	return_ACPI_STATUS(status);
 }
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_leave_sleep_state
+ * FUNCTION:    acpi_hw_legacy_wake
  *
  * PARAMETERS:  sleep_state         - Which sleep state we just exited
+ *              Flags               - Reserved, set to zero
  *
  * RETURN:      Status
  *
@@ -553,31 +308,17 @@ acpi_status acpi_leave_sleep_state_prep(u8 sleep_state)
  *              Called with interrupts ENABLED.
  *
  ******************************************************************************/
-acpi_status acpi_leave_sleep_state(u8 sleep_state)
+
+acpi_status acpi_hw_legacy_wake(u8 sleep_state, u8 flags)
 {
-	struct acpi_object_list arg_list;
-	union acpi_object arg;
 	acpi_status status;
 
-	ACPI_FUNCTION_TRACE(acpi_leave_sleep_state);
+	ACPI_FUNCTION_TRACE(hw_legacy_wake);
 
 	/* Ensure enter_sleep_state_prep -> enter_sleep_state ordering */
 
 	acpi_gbl_sleep_type_a = ACPI_SLEEP_TYPE_INVALID;
-
-	/* Setup parameter object */
-
-	arg_list.count = 1;
-	arg_list.pointer = &arg;
-	arg.type = ACPI_TYPE_INTEGER;
-
-	/* Ignore any errors from these methods */
-
-	arg.integer.value = ACPI_SST_WAKING;
-	status = acpi_evaluate_object(NULL, METHOD_NAME__SST, &arg_list, NULL);
-	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-		ACPI_EXCEPTION((AE_INFO, status, "During Method _SST"));
-	}
+	acpi_hw_execute_sleep_method(METHOD_PATHNAME__SST, ACPI_SST_WAKING);
 
 	/*
 	 * GPEs must be enabled before _WAK is called as GPEs
@@ -591,46 +332,50 @@ acpi_status acpi_leave_sleep_state(u8 sleep_state)
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
+
 	status = acpi_hw_enable_all_runtime_gpes();
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
 
-	arg.integer.value = sleep_state;
-	status = acpi_evaluate_object(NULL, METHOD_NAME__WAK, &arg_list, NULL);
-	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-		ACPI_EXCEPTION((AE_INFO, status, "During Method _WAK"));
-	}
-	/* TBD: _WAK "sometimes" returns stuff - do we want to look at it? */
+	/*
+	 * Now we can execute _WAK, etc. Some machines require that the GPEs
+	 * are enabled before the wake methods are executed.
+	 */
+	acpi_hw_execute_sleep_method(METHOD_PATHNAME__WAK, sleep_state);
 
 	/*
-	 * Some BIOSes assume that WAK_STS will be cleared on resume and use
-	 * it to determine whether the system is rebooting or resuming. Clear
-	 * it for compatibility.
+	 * Some BIOS code assumes that WAK_STS will be cleared on resume
+	 * and use it to determine whether the system is rebooting or
+	 * resuming. Clear WAK_STS for compatibility.
 	 */
 	acpi_write_bit_register(ACPI_BITREG_WAKE_STATUS, 1);
-
 	acpi_gbl_system_awake_and_running = TRUE;
 
 	/* Enable power button */
 
 	(void)
 	    acpi_write_bit_register(acpi_gbl_fixed_event_info
-			      [ACPI_EVENT_POWER_BUTTON].
-			      enable_register_id, ACPI_ENABLE_EVENT);
+				    [ACPI_EVENT_POWER_BUTTON].
+				    enable_register_id, ACPI_ENABLE_EVENT);
 
 	(void)
 	    acpi_write_bit_register(acpi_gbl_fixed_event_info
-			      [ACPI_EVENT_POWER_BUTTON].
-			      status_register_id, ACPI_CLEAR_STATUS);
+				    [ACPI_EVENT_POWER_BUTTON].
+				    status_register_id, ACPI_CLEAR_STATUS);
 
-	arg.integer.value = ACPI_SST_WORKING;
-	status = acpi_evaluate_object(NULL, METHOD_NAME__SST, &arg_list, NULL);
-	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-		ACPI_EXCEPTION((AE_INFO, status, "During Method _SST"));
+	/*
+	 * Enable BM arbitration. This feature is contained within an
+	 * optional register (PM2 Control), so ignore a BAD_ADDRESS
+	 * exception.
+	 */
+	status = acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0);
+	if (ACPI_FAILURE(status) && (status != AE_BAD_ADDRESS)) {
+		return_ACPI_STATUS(status);
 	}
 
+	acpi_hw_execute_sleep_method(METHOD_PATHNAME__SST, ACPI_SST_WORKING);
 	return_ACPI_STATUS(status);
 }
 
-ACPI_EXPORT_SYMBOL(acpi_leave_sleep_state)
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index d4973d9da9f1..f1b2c3b94cac 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -49,6 +49,7 @@
 #define _COMPONENT          ACPI_HARDWARE
 ACPI_MODULE_NAME("hwtimer")
 
+#if (!ACPI_REDUCED_HARDWARE)	/* Entire module */
 /******************************************************************************
  *
  * FUNCTION:    acpi_get_timer_resolution
@@ -187,3 +188,4 @@ acpi_get_timer_duration(u32 start_ticks, u32 end_ticks, u32 * time_elapsed)
 }
 
 ACPI_EXPORT_SYMBOL(acpi_get_timer_duration)
+#endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 9d38eb6c0d0b..ab513a972c95 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -74,8 +74,7 @@ acpi_status acpi_reset(void)
 
 	/* Check if the reset register is supported */
 
-	if (!(acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER) ||
-	    !reset_reg->address) {
+	if (!reset_reg->address) {
 		return_ACPI_STATUS(AE_NOT_EXIST);
 	}
 
@@ -138,11 +137,6 @@ acpi_status acpi_read(u64 *return_value, struct acpi_generic_address *reg)
 		return (status);
 	}
 
-	width = reg->bit_width;
-	if (width == 64) {
-		width = 32;	/* Break into two 32-bit transfers */
-	}
-
 	/* Initialize entire 64-bit return value to zero */
 
 	*return_value = 0;
@@ -154,24 +148,17 @@ acpi_status acpi_read(u64 *return_value, struct acpi_generic_address *reg)
 	 */
 	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
 		status = acpi_os_read_memory((acpi_physical_address)
-					     address, &value, width);
+					     address, return_value,
+					     reg->bit_width);
 		if (ACPI_FAILURE(status)) {
 			return (status);
 		}
-		*return_value = value;
-
-		if (reg->bit_width == 64) {
-
-			/* Read the top 32 bits */
+	} else {		/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
 
-			status = acpi_os_read_memory((acpi_physical_address)
-						     (address + 4), &value, 32);
-			if (ACPI_FAILURE(status)) {
-				return (status);
-			}
-			*return_value |= ((u64)value << 32);
+		width = reg->bit_width;
+		if (width == 64) {
+			width = 32;	/* Break into two 32-bit transfers */
 		}
-	} else {		/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
 
 		status = acpi_hw_read_port((acpi_io_address)
 					   address, &value, width);
@@ -231,32 +218,22 @@ acpi_status acpi_write(u64 value, struct acpi_generic_address *reg)
 		return (status);
 	}
 
-	width = reg->bit_width;
-	if (width == 64) {
-		width = 32;	/* Break into two 32-bit transfers */
-	}
-
 	/*
 	 * Two address spaces supported: Memory or IO. PCI_Config is
 	 * not supported here because the GAS structure is insufficient
 	 */
 	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
 		status = acpi_os_write_memory((acpi_physical_address)
-					      address, ACPI_LODWORD(value),
-					      width);
+					      address, value, reg->bit_width);
 		if (ACPI_FAILURE(status)) {
 			return (status);
 		}
+	} else {		/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
 
-		if (reg->bit_width == 64) {
-			status = acpi_os_write_memory((acpi_physical_address)
-						      (address + 4),
-						      ACPI_HIDWORD(value), 32);
-			if (ACPI_FAILURE(status)) {
-				return (status);
-			}
+		width = reg->bit_width;
+		if (width == 64) {
+			width = 32;	/* Break into two 32-bit transfers */
 		}
-	} else {		/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
 
 		status = acpi_hw_write_port((acpi_io_address)
 					    address, ACPI_LODWORD(value),
@@ -286,6 +263,7 @@ acpi_status acpi_write(u64 value, struct acpi_generic_address *reg)
 
 ACPI_EXPORT_SYMBOL(acpi_write)
 
+#if (!ACPI_REDUCED_HARDWARE)
 /*******************************************************************************
  *
  * FUNCTION:    acpi_read_bit_register
@@ -453,7 +431,7 @@ unlock_and_exit:
 }
 
 ACPI_EXPORT_SYMBOL(acpi_write_bit_register)
-
+#endif				/* !ACPI_REDUCED_HARDWARE */
 /*******************************************************************************
  *
  * FUNCTION:    acpi_get_sleep_type_data
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
new file mode 100644
index 000000000000..762d059bb508
--- /dev/null
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -0,0 +1,431 @@
+/******************************************************************************
+ *
+ * Name: hwxfsleep.c - ACPI Hardware Sleep/Wake External Interfaces
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2012, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#include <acpi/acpi.h>
+#include "accommon.h"
+#include <linux/module.h>
+
+#define _COMPONENT          ACPI_HARDWARE
+ACPI_MODULE_NAME("hwxfsleep")
+
+/* Local prototypes */
+static acpi_status
+acpi_hw_sleep_dispatch(u8 sleep_state, u8 flags, u32 function_id);
+
+/*
+ * Dispatch table used to efficiently branch to the various sleep
+ * functions.
+ */
+#define ACPI_SLEEP_FUNCTION_ID         0
+#define ACPI_WAKE_PREP_FUNCTION_ID     1
+#define ACPI_WAKE_FUNCTION_ID          2
+
+/* Legacy functions are optional, based upon ACPI_REDUCED_HARDWARE */
+
+static struct acpi_sleep_functions acpi_sleep_dispatch[] = {
+	{ACPI_HW_OPTIONAL_FUNCTION(acpi_hw_legacy_sleep),
+	 acpi_hw_extended_sleep},
+	{ACPI_HW_OPTIONAL_FUNCTION(acpi_hw_legacy_wake_prep),
+	 acpi_hw_extended_wake_prep},
+	{ACPI_HW_OPTIONAL_FUNCTION(acpi_hw_legacy_wake), acpi_hw_extended_wake}
+};
+
+/*
+ * These functions are removed for the ACPI_REDUCED_HARDWARE case:
+ *      acpi_set_firmware_waking_vector
+ *      acpi_set_firmware_waking_vector64
+ *      acpi_enter_sleep_state_s4bios
+ */
+
+#if (!ACPI_REDUCED_HARDWARE)
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_set_firmware_waking_vector
+ *
+ * PARAMETERS:  physical_address    - 32-bit physical address of ACPI real mode
+ *                                    entry point.
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Sets the 32-bit firmware_waking_vector field of the FACS
+ *
+ ******************************************************************************/
+
+acpi_status acpi_set_firmware_waking_vector(u32 physical_address)
+{
+	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector);
+
+
+	/*
+	 * According to the ACPI specification 2.0c and later, the 64-bit
+	 * waking vector should be cleared and the 32-bit waking vector should
+	 * be used, unless we want the wake-up code to be called by the BIOS in
+	 * Protected Mode.  Some systems (for example HP dv5-1004nr) are known
+	 * to fail to resume if the 64-bit vector is used.
+	 */
+
+	/* Set the 32-bit vector */
+
+	acpi_gbl_FACS->firmware_waking_vector = physical_address;
+
+	/* Clear the 64-bit vector if it exists */
+
+	if ((acpi_gbl_FACS->length > 32) && (acpi_gbl_FACS->version >= 1)) {
+		acpi_gbl_FACS->xfirmware_waking_vector = 0;
+	}
+
+	return_ACPI_STATUS(AE_OK);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector)
+
+#if ACPI_MACHINE_WIDTH == 64
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_set_firmware_waking_vector64
+ *
+ * PARAMETERS:  physical_address    - 64-bit physical address of ACPI protected
+ *                                    mode entry point.
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Sets the 64-bit X_firmware_waking_vector field of the FACS, if
+ *              it exists in the table. This function is intended for use with
+ *              64-bit host operating systems.
+ *
+ ******************************************************************************/
+acpi_status acpi_set_firmware_waking_vector64(u64 physical_address)
+{
+	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector64);
+
+
+	/* Determine if the 64-bit vector actually exists */
+
+	if ((acpi_gbl_FACS->length <= 32) || (acpi_gbl_FACS->version < 1)) {
+		return_ACPI_STATUS(AE_NOT_EXIST);
+	}
+
+	/* Clear 32-bit vector, set the 64-bit X_ vector */
+
+	acpi_gbl_FACS->firmware_waking_vector = 0;
+	acpi_gbl_FACS->xfirmware_waking_vector = physical_address;
+	return_ACPI_STATUS(AE_OK);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector64)
+#endif
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_enter_sleep_state_s4bios
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Perform a S4 bios request.
+ *              THIS FUNCTION MUST BE CALLED WITH INTERRUPTS DISABLED
+ *
+ ******************************************************************************/
+acpi_status asmlinkage acpi_enter_sleep_state_s4bios(void)
+{
+	u32 in_value;
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_enter_sleep_state_s4bios);
+
+	/* Clear the wake status bit (PM1) */
+
+	status =
+	    acpi_write_bit_register(ACPI_BITREG_WAKE_STATUS, ACPI_CLEAR_STATUS);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	status = acpi_hw_clear_acpi_status();
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/*
+	 * 1) Disable/Clear all GPEs
+	 * 2) Enable all wakeup GPEs
+	 */
+	status = acpi_hw_disable_all_gpes();
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+	acpi_gbl_system_awake_and_running = FALSE;
+
+	status = acpi_hw_enable_all_wakeup_gpes();
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	ACPI_FLUSH_CPU_CACHE();
+
+	status = acpi_hw_write_port(acpi_gbl_FADT.smi_command,
+				    (u32)acpi_gbl_FADT.S4bios_request, 8);
+
+	do {
+		acpi_os_stall(1000);
+		status =
+		    acpi_read_bit_register(ACPI_BITREG_WAKE_STATUS, &in_value);
+		if (ACPI_FAILURE(status)) {
+			return_ACPI_STATUS(status);
+		}
+	} while (!in_value);
+
+	return_ACPI_STATUS(AE_OK);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_enter_sleep_state_s4bios)
+#endif				/* !ACPI_REDUCED_HARDWARE */
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_hw_sleep_dispatch
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state to enter/exit
+ *              function_id         - Sleep, wake_prep, or Wake
+ *
+ * RETURN:      Status from the invoked sleep handling function.
+ *
+ * DESCRIPTION: Dispatch a sleep/wake request to the appropriate handling
+ *              function.
+ *
+ ******************************************************************************/
+static acpi_status
+acpi_hw_sleep_dispatch(u8 sleep_state, u8 flags, u32 function_id)
+{
+	acpi_status status;
+	struct acpi_sleep_functions *sleep_functions =
+	    &acpi_sleep_dispatch[function_id];
+
+#if (!ACPI_REDUCED_HARDWARE)
+
+	/*
+	 * If the Hardware Reduced flag is set (from the FADT), we must
+	 * use the extended sleep registers
+	 */
+	if (acpi_gbl_reduced_hardware || acpi_gbl_FADT.sleep_control.address) {
+		status = sleep_functions->extended_function(sleep_state, flags);
+	} else {
+		/* Legacy sleep */
+
+		status = sleep_functions->legacy_function(sleep_state, flags);
+	}
+
+	return (status);
+
+#else
+	/*
+	 * For the case where reduced-hardware-only code is being generated,
+	 * we know that only the extended sleep registers are available
+	 */
+	status = sleep_functions->extended_function(sleep_state, flags);
+	return (status);
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_enter_sleep_state_prep
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state to enter
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Prepare to enter a system sleep state.
+ *              This function must execute with interrupts enabled.
+ *              We break sleeping into 2 stages so that OSPM can handle
+ *              various OS-specific tasks between the two steps.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_enter_sleep_state_prep(u8 sleep_state)
+{
+	acpi_status status;
+	struct acpi_object_list arg_list;
+	union acpi_object arg;
+	u32 sst_value;
+
+	ACPI_FUNCTION_TRACE(acpi_enter_sleep_state_prep);
+
+	status = acpi_get_sleep_type_data(sleep_state,
+					  &acpi_gbl_sleep_type_a,
+					  &acpi_gbl_sleep_type_b);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Execute the _PTS method (Prepare To Sleep) */
+
+	arg_list.count = 1;
+	arg_list.pointer = &arg;
+	arg.type = ACPI_TYPE_INTEGER;
+	arg.integer.value = sleep_state;
+
+	status =
+	    acpi_evaluate_object(NULL, METHOD_PATHNAME__PTS, &arg_list, NULL);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Setup the argument to the _SST method (System STatus) */
+
+	switch (sleep_state) {
+	case ACPI_STATE_S0:
+		sst_value = ACPI_SST_WORKING;
+		break;
+
+	case ACPI_STATE_S1:
+	case ACPI_STATE_S2:
+	case ACPI_STATE_S3:
+		sst_value = ACPI_SST_SLEEPING;
+		break;
+
+	case ACPI_STATE_S4:
+		sst_value = ACPI_SST_SLEEP_CONTEXT;
+		break;
+
+	default:
+		sst_value = ACPI_SST_INDICATOR_OFF;	/* Default is off */
+		break;
+	}
+
+	/*
+	 * Set the system indicators to show the desired sleep state.
+	 * _SST is an optional method (return no error if not found)
+	 */
+	acpi_hw_execute_sleep_method(METHOD_PATHNAME__SST, sst_value);
+	return_ACPI_STATUS(AE_OK);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_enter_sleep_state_prep)
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_enter_sleep_state
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state to enter
+ *              Flags               - ACPI_EXECUTE_GTS to run optional method
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Enter a system sleep state (see ACPI 2.0 spec p 231)
+ *              THIS FUNCTION MUST BE CALLED WITH INTERRUPTS DISABLED
+ *
+ ******************************************************************************/
+acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state, u8 flags)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_enter_sleep_state);
+
+	if ((acpi_gbl_sleep_type_a > ACPI_SLEEP_TYPE_MAX) ||
+	    (acpi_gbl_sleep_type_b > ACPI_SLEEP_TYPE_MAX)) {
+		ACPI_ERROR((AE_INFO, "Sleep values out of range: A=0x%X B=0x%X",
+			    acpi_gbl_sleep_type_a, acpi_gbl_sleep_type_b));
+		return_ACPI_STATUS(AE_AML_OPERAND_VALUE);
+	}
+
+	status =
+	    acpi_hw_sleep_dispatch(sleep_state, flags, ACPI_SLEEP_FUNCTION_ID);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_enter_sleep_state)
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_leave_sleep_state_prep
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state we are exiting
+ *              Flags               - ACPI_EXECUTE_BFS to run optional method
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Perform the first state of OS-independent ACPI cleanup after a
+ *              sleep.
+ *              Called with interrupts DISABLED.
+ *
+ ******************************************************************************/
+acpi_status acpi_leave_sleep_state_prep(u8 sleep_state, u8 flags)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_leave_sleep_state_prep);
+
+	status =
+	    acpi_hw_sleep_dispatch(sleep_state, flags,
+				   ACPI_WAKE_PREP_FUNCTION_ID);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_leave_sleep_state_prep)
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_leave_sleep_state
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state we are exiting
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Perform OS-independent ACPI cleanup after a sleep
+ *              Called with interrupts ENABLED.
+ *
+ ******************************************************************************/
+acpi_status acpi_leave_sleep_state(u8 sleep_state)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_leave_sleep_state);
+
+
+	status = acpi_hw_sleep_dispatch(sleep_state, 0, ACPI_WAKE_FUNCTION_ID);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_leave_sleep_state)
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index b7f2b3be79ac..3f7f3f6e7dd5 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -242,7 +242,20 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 
 		if (!obj_desc) {
 
-			/* No attached object, we are done */
+			/* No attached object. Some types should always have an object */
+
+			switch (type) {
+			case ACPI_TYPE_INTEGER:
+			case ACPI_TYPE_PACKAGE:
+			case ACPI_TYPE_BUFFER:
+			case ACPI_TYPE_STRING:
+			case ACPI_TYPE_METHOD:
+				acpi_os_printf("<No attached object>");
+				break;
+
+			default:
+				break;
+			}
 
 			acpi_os_printf("\n");
 			return (AE_OK);
diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c
index 30ea5bc53a78..3b5acb0eb406 100644
--- a/drivers/acpi/acpica/nsdumpdv.c
+++ b/drivers/acpi/acpica/nsdumpdv.c
@@ -121,7 +121,7 @@ void acpi_ns_dump_root_devices(void)
 		return;
 	}
 
-	status = acpi_get_handle(NULL, ACPI_NS_SYSTEM_BUS, &sys_bus_handle);
+	status = acpi_get_handle(NULL, METHOD_NAME__SB_, &sys_bus_handle);
 	if (ACPI_FAILURE(status)) {
 		return;
 	}
diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c
index bbe46a447d34..23ce09686418 100644
--- a/drivers/acpi/acpica/nspredef.c
+++ b/drivers/acpi/acpica/nspredef.c
@@ -638,8 +638,8 @@ acpi_ns_check_package(struct acpi_predefined_data *data,
 			/* Create the new outer package and populate it */
 
 			status =
-			    acpi_ns_repair_package_list(data,
-							return_object_ptr);
+			    acpi_ns_wrap_with_package(data, *elements,
+						      return_object_ptr);
 			if (ACPI_FAILURE(status)) {
 				return (status);
 			}
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index 9c35d20eb52b..5519a64a353f 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -71,11 +71,10 @@ ACPI_MODULE_NAME("nsrepair")
  * Buffer  -> String
  * Buffer  -> Package of Integers
  * Package -> Package of one Package
+ * An incorrect standalone object is wrapped with required outer package
  *
  * Additional possible repairs:
- *
  * Required package elements that are NULL replaced by Integer/String/Buffer
- * Incorrect standalone package wrapped with required outer package
  *
  ******************************************************************************/
 /* Local prototypes */
@@ -91,10 +90,6 @@ static acpi_status
 acpi_ns_convert_to_buffer(union acpi_operand_object *original_object,
 			  union acpi_operand_object **return_object);
 
-static acpi_status
-acpi_ns_convert_to_package(union acpi_operand_object *original_object,
-			   union acpi_operand_object **return_object);
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ns_repair_object
@@ -151,9 +146,24 @@ acpi_ns_repair_object(struct acpi_predefined_data *data,
 		}
 	}
 	if (expected_btypes & ACPI_RTYPE_PACKAGE) {
-		status = acpi_ns_convert_to_package(return_object, &new_object);
+		/*
+		 * A package is expected. We will wrap the existing object with a
+		 * new package object. It is often the case that if a variable-length
+		 * package is required, but there is only a single object needed, the
+		 * BIOS will return that object instead of wrapping it with a Package
+		 * object. Note: after the wrapping, the package will be validated
+		 * for correct contents (expected object type or types).
+		 */
+		status =
+		    acpi_ns_wrap_with_package(data, return_object, &new_object);
 		if (ACPI_SUCCESS(status)) {
-			goto object_repaired;
+			/*
+			 * The original object just had its reference count
+			 * incremented for being inserted into the new package.
+			 */
+			*return_object_ptr = new_object;	/* New Package object */
+			data->flags |= ACPI_OBJECT_REPAIRED;
+			return (AE_OK);
 		}
 	}
 
@@ -165,22 +175,27 @@ acpi_ns_repair_object(struct acpi_predefined_data *data,
 
 	/* Object was successfully repaired */
 
-	/*
-	 * If the original object is a package element, we need to:
-	 * 1. Set the reference count of the new object to match the
-	 *    reference count of the old object.
-	 * 2. Decrement the reference count of the original object.
-	 */
 	if (package_index != ACPI_NOT_PACKAGE_ELEMENT) {
-		new_object->common.reference_count =
-		    return_object->common.reference_count;
+		/*
+		 * The original object is a package element. We need to
+		 * decrement the reference count of the original object,
+		 * for removing it from the package.
+		 *
+		 * However, if the original object was just wrapped with a
+		 * package object as part of the repair, we don't need to
+		 * change the reference count.
+		 */
+		if (!(data->flags & ACPI_OBJECT_WRAPPED)) {
+			new_object->common.reference_count =
+			    return_object->common.reference_count;
 
-		if (return_object->common.reference_count > 1) {
-			return_object->common.reference_count--;
+			if (return_object->common.reference_count > 1) {
+				return_object->common.reference_count--;
+			}
 		}
 
 		ACPI_DEBUG_PRINT((ACPI_DB_REPAIR,
-				  "%s: Converted %s to expected %s at index %u\n",
+				  "%s: Converted %s to expected %s at Package index %u\n",
 				  data->pathname,
 				  acpi_ut_get_object_type_name(return_object),
 				  acpi_ut_get_object_type_name(new_object),
@@ -453,65 +468,6 @@ acpi_ns_convert_to_buffer(union acpi_operand_object *original_object,
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_ns_convert_to_package
- *
- * PARAMETERS:  original_object     - Object to be converted
- *              return_object       - Where the new converted object is returned
- *
- * RETURN:      Status. AE_OK if conversion was successful.
- *
- * DESCRIPTION: Attempt to convert a Buffer object to a Package. Each byte of
- *              the buffer is converted to a single integer package element.
- *
- ******************************************************************************/
-
-static acpi_status
-acpi_ns_convert_to_package(union acpi_operand_object *original_object,
-			   union acpi_operand_object **return_object)
-{
-	union acpi_operand_object *new_object;
-	union acpi_operand_object **elements;
-	u32 length;
-	u8 *buffer;
-
-	switch (original_object->common.type) {
-	case ACPI_TYPE_BUFFER:
-
-		/* Buffer-to-Package conversion */
-
-		length = original_object->buffer.length;
-		new_object = acpi_ut_create_package_object(length);
-		if (!new_object) {
-			return (AE_NO_MEMORY);
-		}
-
-		/* Convert each buffer byte to an integer package element */
-
-		elements = new_object->package.elements;
-		buffer = original_object->buffer.pointer;
-
-		while (length--) {
-			*elements =
-			    acpi_ut_create_integer_object((u64) *buffer);
-			if (!*elements) {
-				acpi_ut_remove_reference(new_object);
-				return (AE_NO_MEMORY);
-			}
-			elements++;
-			buffer++;
-		}
-		break;
-
-	default:
-		return (AE_AML_OPERAND_TYPE);
-	}
-
-	*return_object = new_object;
-	return (AE_OK);
-}
-
-/*******************************************************************************
- *
  * FUNCTION:    acpi_ns_repair_null_element
  *
  * PARAMETERS:  Data                - Pointer to validation data structure
@@ -677,55 +633,56 @@ acpi_ns_remove_null_elements(struct acpi_predefined_data *data,
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_ns_repair_package_list
+ * FUNCTION:    acpi_ns_wrap_with_package
  *
  * PARAMETERS:  Data                - Pointer to validation data structure
- *              obj_desc_ptr        - Pointer to the object to repair. The new
- *                                    package object is returned here,
- *                                    overwriting the old object.
+ *              original_object     - Pointer to the object to repair.
+ *              obj_desc_ptr        - The new package object is returned here
  *
  * RETURN:      Status, new object in *obj_desc_ptr
  *
- * DESCRIPTION: Repair a common problem with objects that are defined to return
- *              a variable-length Package of Packages. If the variable-length
- *              is one, some BIOS code mistakenly simply declares a single
- *              Package instead of a Package with one sub-Package. This
- *              function attempts to repair this error by wrapping a Package
- *              object around the original Package, creating the correct
- *              Package with one sub-Package.
+ * DESCRIPTION: Repair a common problem with objects that are defined to
+ *              return a variable-length Package of sub-objects. If there is
+ *              only one sub-object, some BIOS code mistakenly simply declares
+ *              the single object instead of a Package with one sub-object.
+ *              This function attempts to repair this error by wrapping a
+ *              Package object around the original object, creating the
+ *              correct and expected Package with one sub-object.
  *
  *              Names that can be repaired in this manner include:
- *              _ALR, _CSD, _HPX, _MLS, _PRT, _PSS, _TRT, TSS
+ *              _ALR, _CSD, _HPX, _MLS, _PLD, _PRT, _PSS, _TRT, _TSS,
+ *              _BCL, _DOD, _FIX, _Sx
  *
  ******************************************************************************/
 
 acpi_status
-acpi_ns_repair_package_list(struct acpi_predefined_data *data,
-			    union acpi_operand_object **obj_desc_ptr)
+acpi_ns_wrap_with_package(struct acpi_predefined_data *data,
+			  union acpi_operand_object *original_object,
+			  union acpi_operand_object **obj_desc_ptr)
 {
 	union acpi_operand_object *pkg_obj_desc;
 
-	ACPI_FUNCTION_NAME(ns_repair_package_list);
+	ACPI_FUNCTION_NAME(ns_wrap_with_package);
 
 	/*
 	 * Create the new outer package and populate it. The new package will
-	 * have a single element, the lone subpackage.
+	 * have a single element, the lone sub-object.
 	 */
 	pkg_obj_desc = acpi_ut_create_package_object(1);
 	if (!pkg_obj_desc) {
 		return (AE_NO_MEMORY);
 	}
 
-	pkg_obj_desc->package.elements[0] = *obj_desc_ptr;
+	pkg_obj_desc->package.elements[0] = original_object;
+
+	ACPI_DEBUG_PRINT((ACPI_DB_REPAIR,
+			  "%s: Wrapped %s with expected Package object\n",
+			  data->pathname,
+			  acpi_ut_get_object_type_name(original_object)));
 
 	/* Return the new object in the object pointer */
 
 	*obj_desc_ptr = pkg_obj_desc;
-	data->flags |= ACPI_OBJECT_REPAIRED;
-
-	ACPI_DEBUG_PRINT((ACPI_DB_REPAIR,
-			  "%s: Repaired incorrectly formed Package\n",
-			  data->pathname));
-
+	data->flags |= ACPI_OBJECT_REPAIRED | ACPI_OBJECT_WRAPPED;
 	return (AE_OK);
 }
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index a535b7afda5c..75113759f69d 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -341,7 +341,7 @@ acpi_status acpi_ns_build_internal_name(struct acpi_namestring_info *info)
 
 		if (!acpi_ns_valid_path_separator(*external_name) &&
 		    (*external_name != 0)) {
-			return_ACPI_STATUS(AE_BAD_PARAMETER);
+			return_ACPI_STATUS(AE_BAD_PATHNAME);
 		}
 
 		/* Move on the next segment */
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index c5d870406f41..4c9c760db4a4 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -363,10 +363,6 @@ static void acpi_tb_convert_fadt(void)
 	u32 address32;
 	u32 i;
 
-	/* Update the local FADT table header length */
-
-	acpi_gbl_FADT.header.length = sizeof(struct acpi_table_fadt);
-
 	/*
 	 * Expand the 32-bit FACS and DSDT addresses to 64-bit as necessary.
 	 * Later code will always use the X 64-bit field. Also, check for an
@@ -408,6 +404,10 @@ static void acpi_tb_convert_fadt(void)
 		acpi_gbl_FADT.boot_flags = 0;
 	}
 
+	/* Update the local FADT table header length */
+
+	acpi_gbl_FADT.header.length = sizeof(struct acpi_table_fadt);
+
 	/*
 	 * Expand the ACPI 1.0 32-bit addresses to the ACPI 2.0 64-bit "X"
 	 * generic address structures as necessary. Later code will always use
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 1aecf7baa4e0..c03500b4cc7a 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -114,7 +114,6 @@ acpi_tb_add_table(struct acpi_table_desc *table_desc, u32 *table_index)
 {
 	u32 i;
 	acpi_status status = AE_OK;
-	struct acpi_table_header *override_table = NULL;
 
 	ACPI_FUNCTION_TRACE(tb_add_table);
 
@@ -224,25 +223,10 @@ acpi_tb_add_table(struct acpi_table_desc *table_desc, u32 *table_index)
 	/*
 	 * ACPI Table Override:
 	 * Allow the host to override dynamically loaded tables.
+	 * NOTE: the table is fully mapped at this point, and the mapping will
+	 * be deleted by tb_table_override if the table is actually overridden.
 	 */
-	status = acpi_os_table_override(table_desc->pointer, &override_table);
-	if (ACPI_SUCCESS(status) && override_table) {
-		ACPI_INFO((AE_INFO,
-			   "%4.4s @ 0x%p Table override, replaced with:",
-			   table_desc->pointer->signature,
-			   ACPI_CAST_PTR(void, table_desc->address)));
-
-		/* We can delete the table that was passed as a parameter */
-
-		acpi_tb_delete_table(table_desc);
-
-		/* Setup descriptor for the new table */
-
-		table_desc->address = ACPI_PTR_TO_PHYSADDR(override_table);
-		table_desc->pointer = override_table;
-		table_desc->length = override_table->length;
-		table_desc->flags = ACPI_TABLE_ORIGIN_OVERRIDE;
-	}
+	(void)acpi_tb_table_override(table_desc->pointer, table_desc);
 
 	/* Add the table to the global root table list */
 
@@ -263,6 +247,95 @@ acpi_tb_add_table(struct acpi_table_desc *table_desc, u32 *table_index)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_tb_table_override
+ *
+ * PARAMETERS:  table_header        - Header for the original table
+ *              table_desc          - Table descriptor initialized for the
+ *                                    original table. May or may not be mapped.
+ *
+ * RETURN:      Pointer to the entire new table. NULL if table not overridden.
+ *              If overridden, installs the new table within the input table
+ *              descriptor.
+ *
+ * DESCRIPTION: Attempt table override by calling the OSL override functions.
+ *              Note: If the table is overridden, then the entire new table
+ *              is mapped and returned by this function.
+ *
+ ******************************************************************************/
+
+struct acpi_table_header *acpi_tb_table_override(struct acpi_table_header
+						 *table_header,
+						 struct acpi_table_desc
+						 *table_desc)
+{
+	acpi_status status;
+	struct acpi_table_header *new_table = NULL;
+	acpi_physical_address new_address = 0;
+	u32 new_table_length = 0;
+	u8 new_flags;
+	char *override_type;
+
+	/* (1) Attempt logical override (returns a logical address) */
+
+	status = acpi_os_table_override(table_header, &new_table);
+	if (ACPI_SUCCESS(status) && new_table) {
+		new_address = ACPI_PTR_TO_PHYSADDR(new_table);
+		new_table_length = new_table->length;
+		new_flags = ACPI_TABLE_ORIGIN_OVERRIDE;
+		override_type = "Logical";
+		goto finish_override;
+	}
+
+	/* (2) Attempt physical override (returns a physical address) */
+
+	status = acpi_os_physical_table_override(table_header,
+						 &new_address,
+						 &new_table_length);
+	if (ACPI_SUCCESS(status) && new_address && new_table_length) {
+
+		/* Map the entire new table */
+
+		new_table = acpi_os_map_memory(new_address, new_table_length);
+		if (!new_table) {
+			ACPI_EXCEPTION((AE_INFO, AE_NO_MEMORY,
+					"%4.4s %p Attempted physical table override failed",
+					table_header->signature,
+					ACPI_CAST_PTR(void,
+						      table_desc->address)));
+			return (NULL);
+		}
+
+		override_type = "Physical";
+		new_flags = ACPI_TABLE_ORIGIN_MAPPED;
+		goto finish_override;
+	}
+
+	return (NULL);		/* There was no override */
+
+      finish_override:
+
+	ACPI_INFO((AE_INFO,
+		   "%4.4s %p %s table override, new table: %p",
+		   table_header->signature,
+		   ACPI_CAST_PTR(void, table_desc->address),
+		   override_type, new_table));
+
+	/* We can now unmap/delete the original table (if fully mapped) */
+
+	acpi_tb_delete_table(table_desc);
+
+	/* Setup descriptor for the new table */
+
+	table_desc->address = new_address;
+	table_desc->pointer = new_table;
+	table_desc->length = new_table_length;
+	table_desc->flags = new_flags;
+
+	return (new_table);
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_tb_resize_root_table_list
  *
  * PARAMETERS:  None
@@ -396,7 +469,11 @@ void acpi_tb_delete_table(struct acpi_table_desc *table_desc)
 	case ACPI_TABLE_ORIGIN_ALLOCATED:
 		ACPI_FREE(table_desc->pointer);
 		break;
-	default:;
+
+		/* Not mapped or allocated, there is nothing we can do */
+
+	default:
+		return;
 	}
 
 	table_desc->pointer = NULL;
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 09ca39e14337..0a706cac37de 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -118,6 +118,7 @@ acpi_tb_check_xsdt(acpi_physical_address address)
 		return AE_OK;
 }
 
+#if (!ACPI_REDUCED_HARDWARE)
 /*******************************************************************************
  *
  * FUNCTION:    acpi_tb_initialize_facs
@@ -148,6 +149,7 @@ acpi_status acpi_tb_initialize_facs(void)
 								&acpi_gbl_FACS));
 	return status;
 }
+#endif				/* !ACPI_REDUCED_HARDWARE */
 
 /*******************************************************************************
  *
@@ -444,7 +446,7 @@ struct acpi_table_header *acpi_tb_copy_dsdt(u32 table_index)
  * RETURN:      None
  *
  * DESCRIPTION: Install an ACPI table into the global data structure. The
- *              table override mechanism is implemented here to allow the host
+ *              table override mechanism is called to allow the host
  *              OS to replace any table before it is installed in the root
  *              table array.
  *
@@ -454,11 +456,9 @@ void
 acpi_tb_install_table(acpi_physical_address address,
 		      char *signature, u32 table_index)
 {
-	u8 flags;
-	acpi_status status;
-	struct acpi_table_header *table_to_install;
-	struct acpi_table_header *mapped_table;
-	struct acpi_table_header *override_table = NULL;
+	struct acpi_table_header *table;
+	struct acpi_table_header *final_table;
+	struct acpi_table_desc *table_desc;
 
 	if (!address) {
 		ACPI_ERROR((AE_INFO,
@@ -469,69 +469,78 @@ acpi_tb_install_table(acpi_physical_address address,
 
 	/* Map just the table header */
 
-	mapped_table =
-	    acpi_os_map_memory(address, sizeof(struct acpi_table_header));
-	if (!mapped_table) {
+	table = acpi_os_map_memory(address, sizeof(struct acpi_table_header));
+	if (!table) {
+		ACPI_ERROR((AE_INFO,
+			    "Could not map memory for table [%s] at %p",
+			    signature, ACPI_CAST_PTR(void, address)));
 		return;
 	}
 
 	/* If a particular signature is expected (DSDT/FACS), it must match */
 
-	if (signature && !ACPI_COMPARE_NAME(mapped_table->signature, signature)) {
+	if (signature && !ACPI_COMPARE_NAME(table->signature, signature)) {
 		ACPI_ERROR((AE_INFO,
 			    "Invalid signature 0x%X for ACPI table, expected [%s]",
-			    *ACPI_CAST_PTR(u32, mapped_table->signature),
-			    signature));
+			    *ACPI_CAST_PTR(u32, table->signature), signature));
 		goto unmap_and_exit;
 	}
 
 	/*
+	 * Initialize the table entry. Set the pointer to NULL, since the
+	 * table is not fully mapped at this time.
+	 */
+	table_desc = &acpi_gbl_root_table_list.tables[table_index];
+
+	table_desc->address = address;
+	table_desc->pointer = NULL;
+	table_desc->length = table->length;
+	table_desc->flags = ACPI_TABLE_ORIGIN_MAPPED;
+	ACPI_MOVE_32_TO_32(table_desc->signature.ascii, table->signature);
+
+	/*
 	 * ACPI Table Override:
 	 *
 	 * Before we install the table, let the host OS override it with a new
 	 * one if desired. Any table within the RSDT/XSDT can be replaced,
 	 * including the DSDT which is pointed to by the FADT.
+	 *
+	 * NOTE: If the table is overridden, then final_table will contain a
+	 * mapped pointer to the full new table. If the table is not overridden,
+	 * or if there has been a physical override, then the table will be
+	 * fully mapped later (in verify table). In any case, we must
+	 * unmap the header that was mapped above.
 	 */
-	status = acpi_os_table_override(mapped_table, &override_table);
-	if (ACPI_SUCCESS(status) && override_table) {
-		ACPI_INFO((AE_INFO,
-			   "%4.4s @ 0x%p Table override, replaced with:",
-			   mapped_table->signature, ACPI_CAST_PTR(void,
-								  address)));
-
-		acpi_gbl_root_table_list.tables[table_index].pointer =
-		    override_table;
-		address = ACPI_PTR_TO_PHYSADDR(override_table);
-
-		table_to_install = override_table;
-		flags = ACPI_TABLE_ORIGIN_OVERRIDE;
-	} else {
-		table_to_install = mapped_table;
-		flags = ACPI_TABLE_ORIGIN_MAPPED;
+	final_table = acpi_tb_table_override(table, table_desc);
+	if (!final_table) {
+		final_table = table;	/* There was no override */
 	}
 
-	/* Initialize the table entry */
+	acpi_tb_print_table_header(table_desc->address, final_table);
 
-	acpi_gbl_root_table_list.tables[table_index].address = address;
-	acpi_gbl_root_table_list.tables[table_index].length =
-	    table_to_install->length;
-	acpi_gbl_root_table_list.tables[table_index].flags = flags;
-
-	ACPI_MOVE_32_TO_32(&
-			   (acpi_gbl_root_table_list.tables[table_index].
-			    signature), table_to_install->signature);
-
-	acpi_tb_print_table_header(address, table_to_install);
+	/* Set the global integer width (based upon revision of the DSDT) */
 
 	if (table_index == ACPI_TABLE_INDEX_DSDT) {
+		acpi_ut_set_integer_width(final_table->revision);
+	}
 
-		/* Global integer width is based upon revision of the DSDT */
-
-		acpi_ut_set_integer_width(table_to_install->revision);
+	/*
+	 * If we have a physical override during this early loading of the ACPI
+	 * tables, unmap the table for now. It will be mapped again later when
+	 * it is actually used. This supports very early loading of ACPI tables,
+	 * before virtual memory is fully initialized and running within the
+	 * host OS. Note: A logical override has the ACPI_TABLE_ORIGIN_OVERRIDE
+	 * flag set and will not be deleted below.
+	 */
+	if (final_table != table) {
+		acpi_tb_delete_table(table_desc);
 	}
 
       unmap_and_exit:
-	acpi_os_unmap_memory(mapped_table, sizeof(struct acpi_table_header));
+
+	/* Always unmap the table header that we mapped above */
+
+	acpi_os_unmap_memory(table, sizeof(struct acpi_table_header));
 }
 
 /*******************************************************************************
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index d42ede5260c7..684849949bf3 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -497,19 +497,20 @@ char *acpi_ut_get_mutex_name(u32 mutex_id)
 
 /* Names for Notify() values, used for debug output */
 
-static const char *acpi_gbl_notify_value_names[] = {
-	"Bus Check",
-	"Device Check",
-	"Device Wake",
-	"Eject Request",
-	"Device Check Light",
-	"Frequency Mismatch",
-	"Bus Mode Mismatch",
-	"Power Fault",
-	"Capabilities Check",
-	"Device PLD Check",
-	"Reserved",
-	"System Locality Update"
+static const char *acpi_gbl_notify_value_names[ACPI_NOTIFY_MAX + 1] = {
+	/* 00 */ "Bus Check",
+	/* 01 */ "Device Check",
+	/* 02 */ "Device Wake",
+	/* 03 */ "Eject Request",
+	/* 04 */ "Device Check Light",
+	/* 05 */ "Frequency Mismatch",
+	/* 06 */ "Bus Mode Mismatch",
+	/* 07 */ "Power Fault",
+	/* 08 */ "Capabilities Check",
+	/* 09 */ "Device PLD Check",
+	/* 10 */ "Reserved",
+	/* 11 */ "System Locality Update",
+	/* 12 */ "Shutdown Request"
 };
 
 const char *acpi_ut_get_notify_name(u32 notify_value)
@@ -519,9 +520,10 @@ const char *acpi_ut_get_notify_name(u32 notify_value)
 		return (acpi_gbl_notify_value_names[notify_value]);
 	} else if (notify_value <= ACPI_MAX_SYS_NOTIFY) {
 		return ("Reserved");
-	} else {		/* Greater or equal to 0x80 */
-
-		return ("**Device Specific**");
+	} else if (notify_value <= ACPI_MAX_DEVICE_SPECIFIC_NOTIFY) {
+		return ("Device Specific");
+	} else {
+		return ("Hardware Specific");
 	}
 }
 #endif
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index 4153584cf526..90f53b42eca9 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -140,6 +140,7 @@ const struct acpi_predefined_names acpi_gbl_pre_defined_names[] = {
 	{NULL, ACPI_TYPE_ANY, NULL}
 };
 
+#if (!ACPI_REDUCED_HARDWARE)
 /******************************************************************************
  *
  * Event and Hardware globals
@@ -236,6 +237,7 @@ struct acpi_fixed_event_info acpi_gbl_fixed_event_info[ACPI_NUM_FIXED_EVENTS] =
 					ACPI_BITMASK_RT_CLOCK_STATUS,
 					ACPI_BITMASK_RT_CLOCK_ENABLE},
 };
+#endif				/* !ACPI_REDUCED_HARDWARE */
 
 /*******************************************************************************
  *
@@ -286,6 +288,8 @@ acpi_status acpi_ut_init_globals(void)
 
 	acpi_gbl_owner_id_mask[ACPI_NUM_OWNERID_MASKS - 1] = 0x80000000;
 
+#if (!ACPI_REDUCED_HARDWARE)
+
 	/* GPE support */
 
 	acpi_gbl_gpe_xrupt_list_head = NULL;
@@ -294,6 +298,10 @@ acpi_status acpi_ut_init_globals(void)
 	acpi_current_gpe_count = 0;
 	acpi_gbl_all_gpes_initialized = FALSE;
 
+	acpi_gbl_global_event_handler = NULL;
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
+
 	/* Global handlers */
 
 	acpi_gbl_system_notify.handler = NULL;
@@ -302,7 +310,6 @@ acpi_status acpi_ut_init_globals(void)
 	acpi_gbl_init_handler = NULL;
 	acpi_gbl_table_handler = NULL;
 	acpi_gbl_interface_handler = NULL;
-	acpi_gbl_global_event_handler = NULL;
 
 	/* Global Lock support */
 
diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c
index 8359c0c5dc98..246798e4c938 100644
--- a/drivers/acpi/acpica/utinit.c
+++ b/drivers/acpi/acpica/utinit.c
@@ -53,27 +53,35 @@ ACPI_MODULE_NAME("utinit")
 /* Local prototypes */
 static void acpi_ut_terminate(void);
 
+#if (!ACPI_REDUCED_HARDWARE)
+
+static void acpi_ut_free_gpe_lists(void);
+
+#else
+
+#define acpi_ut_free_gpe_lists()
+#endif				/* !ACPI_REDUCED_HARDWARE */
+
+#if (!ACPI_REDUCED_HARDWARE)
 /******************************************************************************
  *
- * FUNCTION:    acpi_ut_terminate
+ * FUNCTION:    acpi_ut_free_gpe_lists
  *
  * PARAMETERS:  none
  *
  * RETURN:      none
  *
- * DESCRIPTION: Free global memory
+ * DESCRIPTION: Free global GPE lists
  *
  ******************************************************************************/
 
-static void acpi_ut_terminate(void)
+static void acpi_ut_free_gpe_lists(void)
 {
 	struct acpi_gpe_block_info *gpe_block;
 	struct acpi_gpe_block_info *next_gpe_block;
 	struct acpi_gpe_xrupt_info *gpe_xrupt_info;
 	struct acpi_gpe_xrupt_info *next_gpe_xrupt_info;
 
-	ACPI_FUNCTION_TRACE(ut_terminate);
-
 	/* Free global GPE blocks and related info structures */
 
 	gpe_xrupt_info = acpi_gbl_gpe_xrupt_list_head;
@@ -91,7 +99,26 @@ static void acpi_ut_terminate(void)
 		ACPI_FREE(gpe_xrupt_info);
 		gpe_xrupt_info = next_gpe_xrupt_info;
 	}
+}
+#endif				/* !ACPI_REDUCED_HARDWARE */
+
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_terminate
+ *
+ * PARAMETERS:  none
+ *
+ * RETURN:      none
+ *
+ * DESCRIPTION: Free global memory
+ *
+ ******************************************************************************/
+
+static void acpi_ut_terminate(void)
+{
+	ACPI_FUNCTION_TRACE(ut_terminate);
 
+	acpi_ut_free_gpe_lists();
 	acpi_ut_delete_address_lists();
 	return_VOID;
 }
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 644e8c8ebc4b..afa94f51ff0b 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -145,6 +145,8 @@ acpi_status acpi_enable_subsystem(u32 flags)
 
 	ACPI_FUNCTION_TRACE(acpi_enable_subsystem);
 
+#if (!ACPI_REDUCED_HARDWARE)
+
 	/* Enable ACPI mode */
 
 	if (!(flags & ACPI_NO_ACPI_ENABLE)) {
@@ -169,6 +171,7 @@ acpi_status acpi_enable_subsystem(u32 flags)
 		ACPI_WARNING((AE_INFO, "Could not map the FACS table"));
 		return_ACPI_STATUS(status);
 	}
+#endif				/* !ACPI_REDUCED_HARDWARE */
 
 	/*
 	 * Install the default op_region handlers. These are installed unless
@@ -184,7 +187,7 @@ acpi_status acpi_enable_subsystem(u32 flags)
 			return_ACPI_STATUS(status);
 		}
 	}
-
+#if (!ACPI_REDUCED_HARDWARE)
 	/*
 	 * Initialize ACPI Event handling (Fixed and General Purpose)
 	 *
@@ -220,6 +223,7 @@ acpi_status acpi_enable_subsystem(u32 flags)
 			return_ACPI_STATUS(status);
 		}
 	}
+#endif				/* !ACPI_REDUCED_HARDWARE */
 
 	return_ACPI_STATUS(status);
 }
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index e5d53b7ddc7e..5577762daee1 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -558,33 +558,48 @@ void apei_resources_release(struct apei_resources *resources)
 }
 EXPORT_SYMBOL_GPL(apei_resources_release);
 
-static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr)
+static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr,
+				u32 *access_bit_width)
 {
-	u32 width, space_id;
+	u32 bit_width, bit_offset, access_size_code, space_id;
 
-	width = reg->bit_width;
+	bit_width = reg->bit_width;
+	bit_offset = reg->bit_offset;
+	access_size_code = reg->access_width;
 	space_id = reg->space_id;
 	/* Handle possible alignment issues */
 	memcpy(paddr, &reg->address, sizeof(*paddr));
 	if (!*paddr) {
 		pr_warning(FW_BUG APEI_PFX
-			   "Invalid physical address in GAR [0x%llx/%u/%u]\n",
-			   *paddr, width, space_id);
+			   "Invalid physical address in GAR [0x%llx/%u/%u/%u/%u]\n",
+			   *paddr, bit_width, bit_offset, access_size_code,
+			   space_id);
 		return -EINVAL;
 	}
 
-	if ((width != 8) && (width != 16) && (width != 32) && (width != 64)) {
+	if (access_size_code < 1 || access_size_code > 4) {
 		pr_warning(FW_BUG APEI_PFX
-			   "Invalid bit width in GAR [0x%llx/%u/%u]\n",
-			   *paddr, width, space_id);
+			   "Invalid access size code in GAR [0x%llx/%u/%u/%u/%u]\n",
+			   *paddr, bit_width, bit_offset, access_size_code,
+			   space_id);
+		return -EINVAL;
+	}
+	*access_bit_width = 1UL << (access_size_code + 2);
+
+	if ((bit_width + bit_offset) > *access_bit_width) {
+		pr_warning(FW_BUG APEI_PFX
+			   "Invalid bit width + offset in GAR [0x%llx/%u/%u/%u/%u]\n",
+			   *paddr, bit_width, bit_offset, access_size_code,
+			   space_id);
 		return -EINVAL;
 	}
 
 	if (space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY &&
 	    space_id != ACPI_ADR_SPACE_SYSTEM_IO) {
 		pr_warning(FW_BUG APEI_PFX
-			   "Invalid address space type in GAR [0x%llx/%u/%u]\n",
-			   *paddr, width, space_id);
+			   "Invalid address space type in GAR [0x%llx/%u/%u/%u/%u]\n",
+			   *paddr, bit_width, bit_offset, access_size_code,
+			   space_id);
 		return -EINVAL;
 	}
 
@@ -595,23 +610,25 @@ static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr)
 int apei_read(u64 *val, struct acpi_generic_address *reg)
 {
 	int rc;
+	u32 access_bit_width;
 	u64 address;
 	acpi_status status;
 
-	rc = apei_check_gar(reg, &address);
+	rc = apei_check_gar(reg, &address, &access_bit_width);
 	if (rc)
 		return rc;
 
 	*val = 0;
 	switch(reg->space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_MEMORY:
-		status = acpi_os_read_memory64((acpi_physical_address)
-					     address, val, reg->bit_width);
+		status = acpi_os_read_memory((acpi_physical_address) address,
+					       val, access_bit_width);
 		if (ACPI_FAILURE(status))
 			return -EIO;
 		break;
 	case ACPI_ADR_SPACE_SYSTEM_IO:
-		status = acpi_os_read_port(address, (u32 *)val, reg->bit_width);
+		status = acpi_os_read_port(address, (u32 *)val,
+					   access_bit_width);
 		if (ACPI_FAILURE(status))
 			return -EIO;
 		break;
@@ -627,22 +644,23 @@ EXPORT_SYMBOL_GPL(apei_read);
 int apei_write(u64 val, struct acpi_generic_address *reg)
 {
 	int rc;
+	u32 access_bit_width;
 	u64 address;
 	acpi_status status;
 
-	rc = apei_check_gar(reg, &address);
+	rc = apei_check_gar(reg, &address, &access_bit_width);
 	if (rc)
 		return rc;
 
 	switch (reg->space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_MEMORY:
-		status = acpi_os_write_memory64((acpi_physical_address)
-					      address, val, reg->bit_width);
+		status = acpi_os_write_memory((acpi_physical_address) address,
+						val, access_bit_width);
 		if (ACPI_FAILURE(status))
 			return -EIO;
 		break;
 	case ACPI_ADR_SPACE_SYSTEM_IO:
-		status = acpi_os_write_port(address, val, reg->bit_width);
+		status = acpi_os_write_port(address, val, access_bit_width);
 		if (ACPI_FAILURE(status))
 			return -EIO;
 		break;
@@ -661,23 +679,24 @@ static int collect_res_callback(struct apei_exec_context *ctx,
 	struct apei_resources *resources = data;
 	struct acpi_generic_address *reg = &entry->register_region;
 	u8 ins = entry->instruction;
+	u32 access_bit_width;
 	u64 paddr;
 	int rc;
 
 	if (!(ctx->ins_table[ins].flags & APEI_EXEC_INS_ACCESS_REGISTER))
 		return 0;
 
-	rc = apei_check_gar(reg, &paddr);
+	rc = apei_check_gar(reg, &paddr, &access_bit_width);
 	if (rc)
 		return rc;
 
 	switch (reg->space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_MEMORY:
 		return apei_res_add(&resources->iomem, paddr,
-				    reg->bit_width / 8);
+				    access_bit_width / 8);
 	case ACPI_ADR_SPACE_SYSTEM_IO:
 		return apei_res_add(&resources->ioport, paddr,
-				    reg->bit_width / 8);
+				    access_bit_width / 8);
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
index 5d4189464d63..e6defd86b424 100644
--- a/drivers/acpi/apei/cper.c
+++ b/drivers/acpi/apei/cper.c
@@ -362,6 +362,7 @@ void apei_estatus_print(const char *pfx,
 		gedata_len = gdata->error_data_length;
 		apei_estatus_print_section(pfx, gdata, sec_no);
 		data_len -= gedata_len + sizeof(*gdata);
+		gdata = (void *)(gdata + 1) + gedata_len;
 		sec_no++;
 	}
 }
@@ -396,6 +397,7 @@ int apei_estatus_check(const struct acpi_hest_generic_status *estatus)
 		if (gedata_len > data_len - sizeof(*gdata))
 			return -EINVAL;
 		data_len -= gedata_len + sizeof(*gdata);
+		gdata = (void *)(gdata + 1) + gedata_len;
 	}
 	if (data_len)
 		return -EINVAL;
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 4ca087dd5f4f..8e1793649ec0 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -74,6 +74,8 @@ struct vendor_error_type_extension {
 	u8	reserved[3];
 };
 
+static u32 notrigger;
+
 static u32 vendor_flags;
 static struct debugfs_blob_wrapper vendor_blob;
 static char vendor_dev[64];
@@ -238,7 +240,7 @@ static void *einj_get_parameter_address(void)
 			return v5param;
 		}
 	}
-	if (paddrv4) {
+	if (param_extension && paddrv4) {
 		struct einj_parameter *v4param;
 
 		v4param = acpi_os_map_memory(paddrv4, sizeof(*v4param));
@@ -496,9 +498,11 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2)
 	if (rc)
 		return rc;
 	trigger_paddr = apei_exec_ctx_get_output(&ctx);
-	rc = __einj_error_trigger(trigger_paddr, type, param1, param2);
-	if (rc)
-		return rc;
+	if (notrigger == 0) {
+		rc = __einj_error_trigger(trigger_paddr, type, param1, param2);
+		if (rc)
+			return rc;
+	}
 	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_END_OPERATION);
 
 	return rc;
@@ -700,6 +704,11 @@ static int __init einj_init(void)
 					    einj_debug_dir, &error_param2);
 		if (!fentry)
 			goto err_unmap;
+
+		fentry = debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &notrigger);
+		if (!fentry)
+			goto err_unmap;
 	}
 
 	if (vendor_dev[0]) {
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index eb9fab5b96e4..e4d9d24eb73d 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -917,7 +917,7 @@ static int erst_check_table(struct acpi_table_erst *erst_tab)
 {
 	if ((erst_tab->header_length !=
 	     (sizeof(struct acpi_table_erst) - sizeof(erst_tab->header)))
-	    && (erst_tab->header_length != sizeof(struct acpi_table_einj)))
+	    && (erst_tab->header_length != sizeof(struct acpi_table_erst)))
 		return -EINVAL;
 	if (erst_tab->header.length < sizeof(struct acpi_table_erst))
 		return -EINVAL;
diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
new file mode 100644
index 000000000000..8cf6c46e99fb
--- /dev/null
+++ b/drivers/acpi/bgrt.c
@@ -0,0 +1,175 @@
+/*
+ * Copyright 2012 Red Hat, Inc <mjg@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/sysfs.h>
+#include <acpi/acpi.h>
+#include <acpi/acpi_bus.h>
+
+static struct acpi_table_bgrt *bgrt_tab;
+static struct kobject *bgrt_kobj;
+
+struct bmp_header {
+	u16 id;
+	u32 size;
+} __attribute ((packed));
+
+static struct bmp_header bmp_header;
+
+static ssize_t show_version(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->version);
+}
+static DEVICE_ATTR(version, S_IRUGO, show_version, NULL);
+
+static ssize_t show_status(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->status);
+}
+static DEVICE_ATTR(status, S_IRUGO, show_status, NULL);
+
+static ssize_t show_type(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_type);
+}
+static DEVICE_ATTR(type, S_IRUGO, show_type, NULL);
+
+static ssize_t show_xoffset(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_offset_x);
+}
+static DEVICE_ATTR(xoffset, S_IRUGO, show_xoffset, NULL);
+
+static ssize_t show_yoffset(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_offset_y);
+}
+static DEVICE_ATTR(yoffset, S_IRUGO, show_yoffset, NULL);
+
+static ssize_t show_image(struct file *file, struct kobject *kobj,
+	       struct bin_attribute *attr, char *buf, loff_t off, size_t count)
+{
+	int size = attr->size;
+	void __iomem *image = attr->private;
+
+	if (off >= size) {
+		count = 0;
+	} else {
+		if (off + count > size)
+			count = size - off;
+
+		memcpy_fromio(buf, image+off, count);
+	}
+
+	return count;
+}
+
+static struct bin_attribute image_attr = {
+	.attr = {
+		.name = "image",
+		.mode = S_IRUGO,
+	},
+	.read = show_image,
+};
+
+static struct attribute *bgrt_attributes[] = {
+	&dev_attr_version.attr,
+	&dev_attr_status.attr,
+	&dev_attr_type.attr,
+	&dev_attr_xoffset.attr,
+	&dev_attr_yoffset.attr,
+	NULL,
+};
+
+static struct attribute_group bgrt_attribute_group = {
+	.attrs = bgrt_attributes,
+};
+
+static int __init bgrt_init(void)
+{
+	acpi_status status;
+	int ret;
+	void __iomem *bgrt;
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	status = acpi_get_table("BGRT", 0,
+				(struct acpi_table_header **)&bgrt_tab);
+
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	sysfs_bin_attr_init(&image_attr);
+
+	bgrt = ioremap(bgrt_tab->image_address, sizeof(struct bmp_header));
+
+	if (!bgrt) {
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	memcpy_fromio(&bmp_header, bgrt, sizeof(bmp_header));
+	image_attr.size = bmp_header.size;
+	iounmap(bgrt);
+
+	image_attr.private = ioremap(bgrt_tab->image_address, image_attr.size);
+
+	if (!image_attr.private) {
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+
+	bgrt_kobj = kobject_create_and_add("bgrt", acpi_kobj);
+	if (!bgrt_kobj) {
+		ret = -EINVAL;
+		goto out_iounmap;
+	}
+
+	ret = sysfs_create_group(bgrt_kobj, &bgrt_attribute_group);
+	if (ret)
+		goto out_kobject;
+
+	ret = sysfs_create_bin_file(bgrt_kobj, &image_attr);
+	if (ret)
+		goto out_group;
+
+	return 0;
+
+out_group:
+	sysfs_remove_group(bgrt_kobj, &bgrt_attribute_group);
+out_kobject:
+	kobject_put(bgrt_kobj);
+out_iounmap:
+	iounmap(image_attr.private);
+out_err:
+	return ret;
+}
+
+static void __exit bgrt_exit(void)
+{
+	iounmap(image_attr.private);
+	sysfs_remove_group(bgrt_kobj, &bgrt_attribute_group);
+	sysfs_remove_bin_file(bgrt_kobj, &image_attr);
+}
+
+module_init(bgrt_init);
+module_exit(bgrt_exit);
+
+MODULE_AUTHOR("Matthew Garrett");
+MODULE_DESCRIPTION("BGRT boot graphic support");
+MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 9ecec98bc76e..3263b68cdfa3 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1010,6 +1010,7 @@ static int __init acpi_bus_init(void)
 }
 
 struct kobject *acpi_kobj;
+EXPORT_SYMBOL_GPL(acpi_kobj);
 
 static int __init acpi_init(void)
 {
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index b19a18dd994f..7edaccce6640 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -445,6 +445,16 @@ int ec_transaction(u8 command,
 
 EXPORT_SYMBOL(ec_transaction);
 
+/* Get the handle to the EC device */
+acpi_handle ec_get_handle(void)
+{
+	if (!first_ec)
+		return NULL;
+	return first_ec->handle;
+}
+
+EXPORT_SYMBOL(ec_get_handle);
+
 void acpi_ec_block_transactions(void)
 {
 	struct acpi_ec *ec = first_ec;
@@ -812,10 +822,10 @@ static int acpi_ec_add(struct acpi_device *device)
 		first_ec = ec;
 	device->driver_data = ec;
 
-	WARN(!request_region(ec->data_addr, 1, "EC data"),
-	     "Could not request EC data io port 0x%lx", ec->data_addr);
-	WARN(!request_region(ec->command_addr, 1, "EC cmd"),
-	     "Could not request EC cmd io port 0x%lx", ec->command_addr);
+	ret = !!request_region(ec->data_addr, 1, "EC data");
+	WARN(!ret, "Could not request EC data io port 0x%lx", ec->data_addr);
+	ret = !!request_region(ec->command_addr, 1, "EC cmd");
+	WARN(!ret, "Could not request EC cmd io port 0x%lx", ec->command_addr);
 
 	pr_info(PREFIX "GPE = 0x%lx, I/O: command/status = 0x%lx, data = 0x%lx\n",
 			  ec->gpe, ec->command_addr, ec->data_addr);
diff --git a/drivers/acpi/ec_sys.c b/drivers/acpi/ec_sys.c
index b258cab9061c..7586544fddb4 100644
--- a/drivers/acpi/ec_sys.c
+++ b/drivers/acpi/ec_sys.c
@@ -27,12 +27,6 @@ MODULE_PARM_DESC(write_support, "Dangerous, reboot and removal of battery may "
 
 static struct dentry *acpi_ec_debugfs_dir;
 
-static int acpi_ec_open_io(struct inode *i, struct file *f)
-{
-	f->private_data = i->i_private;
-	return 0;
-}
-
 static ssize_t acpi_ec_read_io(struct file *f, char __user *buf,
 			       size_t count, loff_t *off)
 {
@@ -95,7 +89,7 @@ static ssize_t acpi_ec_write_io(struct file *f, const char __user *buf,
 
 static const struct file_operations acpi_ec_io_ops = {
 	.owner = THIS_MODULE,
-	.open  = acpi_ec_open_io,
+	.open  = simple_open,
 	.read  = acpi_ec_read_io,
 	.write = acpi_ec_write_io,
 	.llseek = default_llseek,
diff --git a/drivers/acpi/nvs.c b/drivers/acpi/nvs.c
index 7a2035fa8c71..266bc58ce0ce 100644
--- a/drivers/acpi/nvs.c
+++ b/drivers/acpi/nvs.c
@@ -95,8 +95,8 @@ static int suspend_nvs_register(unsigned long start, unsigned long size)
 {
 	struct nvs_page *entry, *next;
 
-	pr_info("PM: Registering ACPI NVS region at %lx (%ld bytes)\n",
-		start, size);
+	pr_info("PM: Registering ACPI NVS region [mem %#010lx-%#010lx] (%ld bytes)\n",
+		start, start + size - 1, size);
 
 	while (size > 0) {
 		unsigned int nr_bytes;
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 412a1e04a922..ba14fb93c929 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -77,6 +77,9 @@ EXPORT_SYMBOL(acpi_in_debugger);
 extern char line_buf[80];
 #endif				/*ENABLE_DEBUGGER */
 
+static int (*__acpi_os_prepare_sleep)(u8 sleep_state, u32 pm1a_ctrl,
+				      u32 pm1b_ctrl);
+
 static acpi_osd_handler acpi_irq_handler;
 static void *acpi_irq_context;
 static struct workqueue_struct *kacpid_wq;
@@ -347,7 +350,7 @@ static void acpi_unmap(acpi_physical_address pg_off, void __iomem *vaddr)
 	unsigned long pfn;
 
 	pfn = pg_off >> PAGE_SHIFT;
-	if (page_is_ram(pfn))
+	if (should_use_kmap(pfn))
 		kunmap(pfn_to_page(pfn));
 	else
 		iounmap(vaddr);
@@ -554,6 +557,15 @@ acpi_os_table_override(struct acpi_table_header * existing_table,
 	return AE_OK;
 }
 
+acpi_status
+acpi_os_physical_table_override(struct acpi_table_header *existing_table,
+				acpi_physical_address * new_address,
+				u32 *new_table_length)
+{
+	return AE_SUPPORT;
+}
+
+
 static irqreturn_t acpi_irq(int irq, void *dev_id)
 {
 	u32 handled;
@@ -595,7 +607,8 @@ acpi_os_install_interrupt_handler(u32 gsi, acpi_osd_handler handler,
 
 	acpi_irq_handler = handler;
 	acpi_irq_context = context;
-	if (request_irq(irq, acpi_irq, IRQF_SHARED, "acpi", acpi_irq)) {
+	if (request_threaded_irq(irq, NULL, acpi_irq, IRQF_SHARED, "acpi",
+				 acpi_irq)) {
 		printk(KERN_ERR PREFIX "SCI (IRQ%d) allocation failed\n", irq);
 		acpi_irq_handler = NULL;
 		return AE_NOT_ACQUIRED;
@@ -699,49 +712,6 @@ acpi_status acpi_os_write_port(acpi_io_address port, u32 value, u32 width)
 
 EXPORT_SYMBOL(acpi_os_write_port);
 
-acpi_status
-acpi_os_read_memory(acpi_physical_address phys_addr, u32 * value, u32 width)
-{
-	void __iomem *virt_addr;
-	unsigned int size = width / 8;
-	bool unmap = false;
-	u32 dummy;
-
-	rcu_read_lock();
-	virt_addr = acpi_map_vaddr_lookup(phys_addr, size);
-	if (!virt_addr) {
-		rcu_read_unlock();
-		virt_addr = acpi_os_ioremap(phys_addr, size);
-		if (!virt_addr)
-			return AE_BAD_ADDRESS;
-		unmap = true;
-	}
-
-	if (!value)
-		value = &dummy;
-
-	switch (width) {
-	case 8:
-		*(u8 *) value = readb(virt_addr);
-		break;
-	case 16:
-		*(u16 *) value = readw(virt_addr);
-		break;
-	case 32:
-		*(u32 *) value = readl(virt_addr);
-		break;
-	default:
-		BUG();
-	}
-
-	if (unmap)
-		iounmap(virt_addr);
-	else
-		rcu_read_unlock();
-
-	return AE_OK;
-}
-
 #ifdef readq
 static inline u64 read64(const volatile void __iomem *addr)
 {
@@ -758,7 +728,7 @@ static inline u64 read64(const volatile void __iomem *addr)
 #endif
 
 acpi_status
-acpi_os_read_memory64(acpi_physical_address phys_addr, u64 *value, u32 width)
+acpi_os_read_memory(acpi_physical_address phys_addr, u64 *value, u32 width)
 {
 	void __iomem *virt_addr;
 	unsigned int size = width / 8;
@@ -803,45 +773,6 @@ acpi_os_read_memory64(acpi_physical_address phys_addr, u64 *value, u32 width)
 	return AE_OK;
 }
 
-acpi_status
-acpi_os_write_memory(acpi_physical_address phys_addr, u32 value, u32 width)
-{
-	void __iomem *virt_addr;
-	unsigned int size = width / 8;
-	bool unmap = false;
-
-	rcu_read_lock();
-	virt_addr = acpi_map_vaddr_lookup(phys_addr, size);
-	if (!virt_addr) {
-		rcu_read_unlock();
-		virt_addr = acpi_os_ioremap(phys_addr, size);
-		if (!virt_addr)
-			return AE_BAD_ADDRESS;
-		unmap = true;
-	}
-
-	switch (width) {
-	case 8:
-		writeb(value, virt_addr);
-		break;
-	case 16:
-		writew(value, virt_addr);
-		break;
-	case 32:
-		writel(value, virt_addr);
-		break;
-	default:
-		BUG();
-	}
-
-	if (unmap)
-		iounmap(virt_addr);
-	else
-		rcu_read_unlock();
-
-	return AE_OK;
-}
-
 #ifdef writeq
 static inline void write64(u64 val, volatile void __iomem *addr)
 {
@@ -856,7 +787,7 @@ static inline void write64(u64 val, volatile void __iomem *addr)
 #endif
 
 acpi_status
-acpi_os_write_memory64(acpi_physical_address phys_addr, u64 value, u32 width)
+acpi_os_write_memory(acpi_physical_address phys_addr, u64 value, u32 width)
 {
 	void __iomem *virt_addr;
 	unsigned int size = width / 8;
@@ -1641,3 +1572,24 @@ acpi_status acpi_os_terminate(void)
 
 	return AE_OK;
 }
+
+acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control,
+				  u32 pm1b_control)
+{
+	int rc = 0;
+	if (__acpi_os_prepare_sleep)
+		rc = __acpi_os_prepare_sleep(sleep_state,
+					     pm1a_control, pm1b_control);
+	if (rc < 0)
+		return AE_ERROR;
+	else if (rc > 0)
+		return AE_CTRL_SKIP;
+
+	return AE_OK;
+}
+
+void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
+			       u32 pm1a_ctrl, u32 pm1b_ctrl))
+{
+	__acpi_os_prepare_sleep = func;
+}
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 9ac2a9fa90ff..7049a7d27c4f 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -40,9 +40,11 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/pm_runtime.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
 #include "sleep.h"
+#include "internal.h"
 
 #define PREFIX "ACPI: "
 
@@ -77,6 +79,20 @@ static struct acpi_driver acpi_power_driver = {
 		},
 };
 
+/*
+ * A power managed device
+ * A device may rely on multiple power resources.
+ * */
+struct acpi_power_managed_device {
+	struct device *dev; /* The physical device */
+	acpi_handle *handle;
+};
+
+struct acpi_power_resource_device {
+	struct acpi_power_managed_device *device;
+	struct acpi_power_resource_device *next;
+};
+
 struct acpi_power_resource {
 	struct acpi_device * device;
 	acpi_bus_id name;
@@ -84,6 +100,9 @@ struct acpi_power_resource {
 	u32 order;
 	unsigned int ref_count;
 	struct mutex resource_lock;
+
+	/* List of devices relying on this power resource */
+	struct acpi_power_resource_device *devices;
 };
 
 static struct list_head acpi_power_resource_list;
@@ -183,8 +202,26 @@ static int acpi_power_get_list_state(struct acpi_handle_list *list, int *state)
 	return 0;
 }
 
+/* Resume the device when all power resources in _PR0 are on */
+static void acpi_power_on_device(struct acpi_power_managed_device *device)
+{
+	struct acpi_device *acpi_dev;
+	acpi_handle handle = device->handle;
+	int state;
+
+	if (acpi_bus_get_device(handle, &acpi_dev))
+		return;
+
+	if(acpi_power_get_inferred_state(acpi_dev, &state))
+		return;
+
+	if (state == ACPI_STATE_D0 && pm_runtime_suspended(device->dev))
+		pm_request_resume(device->dev);
+}
+
 static int __acpi_power_on(struct acpi_power_resource *resource)
 {
+	struct acpi_power_resource_device *device_list = resource->devices;
 	acpi_status status = AE_OK;
 
 	status = acpi_evaluate_object(resource->device->handle, "_ON", NULL, NULL);
@@ -197,6 +234,12 @@ static int __acpi_power_on(struct acpi_power_resource *resource)
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Power resource [%s] turned on\n",
 			  resource->name));
 
+	while (device_list) {
+		acpi_power_on_device(device_list->device);
+
+		device_list = device_list->next;
+	}
+
 	return 0;
 }
 
@@ -299,6 +342,125 @@ static int acpi_power_on_list(struct acpi_handle_list *list)
 	return result;
 }
 
+static void __acpi_power_resource_unregister_device(struct device *dev,
+		acpi_handle res_handle)
+{
+	struct acpi_power_resource *resource = NULL;
+	struct acpi_power_resource_device *prev, *curr;
+
+	if (acpi_power_get_context(res_handle, &resource))
+		return;
+
+	mutex_lock(&resource->resource_lock);
+	prev = NULL;
+	curr = resource->devices;
+	while (curr) {
+		if (curr->device->dev == dev) {
+			if (!prev)
+				resource->devices = curr->next;
+			else
+				prev->next = curr->next;
+
+			kfree(curr);
+			break;
+		}
+
+		prev = curr;
+		curr = curr->next;
+	}
+	mutex_unlock(&resource->resource_lock);
+}
+
+/* Unlink dev from all power resources in _PR0 */
+void acpi_power_resource_unregister_device(struct device *dev, acpi_handle handle)
+{
+	struct acpi_device *acpi_dev;
+	struct acpi_handle_list *list;
+	int i;
+
+	if (!dev || !handle)
+		return;
+
+	if (acpi_bus_get_device(handle, &acpi_dev))
+		return;
+
+	list = &acpi_dev->power.states[ACPI_STATE_D0].resources;
+
+	for (i = 0; i < list->count; i++)
+		__acpi_power_resource_unregister_device(dev,
+			list->handles[i]);
+}
+
+static int __acpi_power_resource_register_device(
+	struct acpi_power_managed_device *powered_device, acpi_handle handle)
+{
+	struct acpi_power_resource *resource = NULL;
+	struct acpi_power_resource_device *power_resource_device;
+	int result;
+
+	result = acpi_power_get_context(handle, &resource);
+	if (result)
+		return result;
+
+	power_resource_device = kzalloc(
+		sizeof(*power_resource_device), GFP_KERNEL);
+	if (!power_resource_device)
+		return -ENOMEM;
+
+	power_resource_device->device = powered_device;
+
+	mutex_lock(&resource->resource_lock);
+	power_resource_device->next = resource->devices;
+	resource->devices = power_resource_device;
+	mutex_unlock(&resource->resource_lock);
+
+	return 0;
+}
+
+/* Link dev to all power resources in _PR0 */
+int acpi_power_resource_register_device(struct device *dev, acpi_handle handle)
+{
+	struct acpi_device *acpi_dev;
+	struct acpi_handle_list *list;
+	struct acpi_power_managed_device *powered_device;
+	int i, ret;
+
+	if (!dev || !handle)
+		return -ENODEV;
+
+	ret = acpi_bus_get_device(handle, &acpi_dev);
+	if (ret)
+		goto no_power_resource;
+
+	if (!acpi_dev->power.flags.power_resources)
+		goto no_power_resource;
+
+	powered_device = kzalloc(sizeof(*powered_device), GFP_KERNEL);
+	if (!powered_device)
+		return -ENOMEM;
+
+	powered_device->dev = dev;
+	powered_device->handle = handle;
+
+	list = &acpi_dev->power.states[ACPI_STATE_D0].resources;
+
+	for (i = 0; i < list->count; i++) {
+		ret = __acpi_power_resource_register_device(powered_device,
+			list->handles[i]);
+
+		if (ret) {
+			acpi_power_resource_unregister_device(dev, handle);
+			break;
+		}
+	}
+
+	return ret;
+
+no_power_resource:
+	printk(KERN_WARNING PREFIX "Invalid Power Resource to register!");
+	return -ENODEV;
+}
+
 /**
  * acpi_device_sleep_wake - execute _DSW (Device Sleep Wake) or (deprecated in
  *                          ACPI 3.0) _PSW (Power State Wake)
@@ -500,14 +662,14 @@ int acpi_power_transition(struct acpi_device *device, int state)
 {
 	int result;
 
-	if (!device || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3))
+	if (!device || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3_COLD))
 		return -EINVAL;
 
 	if (device->power.state == state)
 		return 0;
 
 	if ((device->power.state < ACPI_STATE_D0)
-	    || (device->power.state > ACPI_STATE_D3))
+	    || (device->power.state > ACPI_STATE_D3_COLD))
 		return -ENODEV;
 
 	/* TBD: Resources must be ordered. */
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 2801b418d7bb..0734086537b8 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -46,7 +46,6 @@
 #include <linux/slab.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/cpu.h>
 #include <asm/delay.h>
 #include <asm/uaccess.h>
@@ -68,6 +67,7 @@
 #define ACPI_PROCESSOR_NOTIFY_PERFORMANCE 0x80
 #define ACPI_PROCESSOR_NOTIFY_POWER	0x81
 #define ACPI_PROCESSOR_NOTIFY_THROTTLING	0x82
+#define ACPI_PROCESSOR_DEVICE_HID	"ACPI0007"
 
 #define ACPI_PROCESSOR_LIMIT_USER	0
 #define ACPI_PROCESSOR_LIMIT_THERMAL	1
@@ -88,7 +88,7 @@ static int acpi_processor_start(struct acpi_processor *pr);
 
 static const struct acpi_device_id processor_device_ids[] = {
 	{ACPI_PROCESSOR_OBJECT_HID, 0},
-	{"ACPI0007", 0},
+	{ACPI_PROCESSOR_DEVICE_HID, 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, processor_device_ids);
@@ -536,8 +536,8 @@ static int __cpuinit acpi_processor_add(struct acpi_device *device)
 		return -ENOMEM;
 
 	if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
-		kfree(pr);
-		return -ENOMEM;
+		result = -ENOMEM;
+		goto err_free_pr;
 	}
 
 	pr->handle = device->handle;
@@ -577,7 +577,7 @@ static int __cpuinit acpi_processor_add(struct acpi_device *device)
 	dev = get_cpu_device(pr->id);
 	if (sysfs_create_link(&device->dev.kobj, &dev->kobj, "sysdev")) {
 		result = -EFAULT;
-		goto err_free_cpumask;
+		goto err_clear_processor;
 	}
 
 	/*
@@ -595,9 +595,15 @@ static int __cpuinit acpi_processor_add(struct acpi_device *device)
 
 err_remove_sysfs:
 	sysfs_remove_link(&device->dev.kobj, "sysdev");
+err_clear_processor:
+	/*
+	 * processor_device_array is not cleared to allow checks for buggy BIOS
+	 */ 
+	per_cpu(processors, pr->id) = NULL;
 err_free_cpumask:
 	free_cpumask_var(pr->throttling.shared_cpu_map);
-
+err_free_pr:
+	kfree(pr);
 	return result;
 }
 
@@ -742,20 +748,46 @@ static void acpi_processor_hotplug_notify(acpi_handle handle,
 	return;
 }
 
+static acpi_status is_processor_device(acpi_handle handle)
+{
+	struct acpi_device_info *info;
+	char *hid;
+	acpi_status status;
+
+	status = acpi_get_object_info(handle, &info);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	if (info->type == ACPI_TYPE_PROCESSOR) {
+		kfree(info);
+		return AE_OK;	/* found a processor object */
+	}
+
+	if (!(info->valid & ACPI_VALID_HID)) {
+		kfree(info);
+		return AE_ERROR;
+	}
+
+	hid = info->hardware_id.string;
+	if ((hid == NULL) || strcmp(hid, ACPI_PROCESSOR_DEVICE_HID)) {
+		kfree(info);
+		return AE_ERROR;
+	}
+
+	kfree(info);
+	return AE_OK;	/* found a processor device object */
+}
+
 static acpi_status
 processor_walk_namespace_cb(acpi_handle handle,
 			    u32 lvl, void *context, void **rv)
 {
 	acpi_status status;
 	int *action = context;
-	acpi_object_type type = 0;
 
-	status = acpi_get_type(handle, &type);
+	status = is_processor_device(handle);
 	if (ACPI_FAILURE(status))
-		return (AE_OK);
-
-	if (type != ACPI_TYPE_PROCESSOR)
-		return (AE_OK);
+		return AE_OK;	/* not a processor; continue to walk */
 
 	switch (*action) {
 	case INSTALL_NOTIFY_HANDLER:
@@ -773,7 +805,8 @@ processor_walk_namespace_cb(acpi_handle handle,
 		break;
 	}
 
-	return (AE_OK);
+	/* found a processor; skip walking underneath */
+	return AE_CTRL_DEPTH;
 }
 
 static acpi_status acpi_processor_hotadd_init(struct acpi_processor *pr)
@@ -831,7 +864,7 @@ void acpi_processor_install_hotplug_notify(void)
 {
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 	int action = INSTALL_NOTIFY_HANDLER;
-	acpi_walk_namespace(ACPI_TYPE_PROCESSOR,
+	acpi_walk_namespace(ACPI_TYPE_ANY,
 			    ACPI_ROOT_OBJECT,
 			    ACPI_UINT32_MAX,
 			    processor_walk_namespace_cb, NULL, &action, NULL);
@@ -844,7 +877,7 @@ void acpi_processor_uninstall_hotplug_notify(void)
 {
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 	int action = UNINSTALL_NOTIFY_HANDLER;
-	acpi_walk_namespace(ACPI_TYPE_PROCESSOR,
+	acpi_walk_namespace(ACPI_TYPE_ANY,
 			    ACPI_ROOT_OBJECT,
 			    ACPI_UINT32_MAX,
 			    processor_walk_namespace_cb, NULL, &action, NULL);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 0e8e2de2ed3e..b3447f63e46b 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -770,6 +770,35 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 	return index;
 }
 
+
+/**
+ * acpi_idle_play_dead - enters an ACPI state for long-term idle (i.e. off-lining)
+ * @dev: the target CPU
+ * @index: the index of suggested state
+ */
+static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
+{
+	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
+	struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
+
+	ACPI_FLUSH_CPU_CACHE();
+
+	while (1) {
+
+		if (cx->entry_method == ACPI_CSTATE_HALT)
+			halt();
+		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
+			inb(cx->address);
+			/* See comment in acpi_idle_do_entry() */
+			inl(acpi_gbl_FADT.xpm_timer_block.address);
+		} else
+			return -ENODEV;
+	}
+
+	/* Never reached */
+	return 0;
+}
+
 /**
  * acpi_idle_enter_simple - enters an ACPI state without BM handling
  * @dev: the target CPU
@@ -1077,12 +1106,14 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
 				state->flags |= CPUIDLE_FLAG_TIME_VALID;
 
 			state->enter = acpi_idle_enter_c1;
+			state->enter_dead = acpi_idle_play_dead;
 			drv->safe_state_index = count;
 			break;
 
 			case ACPI_STATE_C2:
 			state->flags |= CPUIDLE_FLAG_TIME_VALID;
 			state->enter = acpi_idle_enter_simple;
+			state->enter_dead = acpi_idle_play_dead;
 			drv->safe_state_index = count;
 			break;
 
@@ -1159,8 +1190,7 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 	 * to make the code that updates C-States be called once.
 	 */
 
-	if (smp_processor_id() == 0 &&
-			cpuidle_get_driver() == &acpi_idle_driver) {
+	if (pr->id == 0 && cpuidle_get_driver() == &acpi_idle_driver) {
 
 		cpuidle_pause_and_lock();
 		/* Protect against cpu-hotplug */
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index 3b599abf2b40..641b5450a0db 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -57,6 +57,27 @@ ACPI_MODULE_NAME("processor_thermal");
 static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
 static unsigned int acpi_thermal_cpufreq_is_init = 0;
 
+#define reduction_pctg(cpu) \
+	per_cpu(cpufreq_thermal_reduction_pctg, phys_package_first_cpu(cpu))
+
+/*
+ * Emulate "per package data" using per cpu data (which should really be
+ * provided elsewhere)
+ *
+ * Note we can lose a CPU on cpu hotunplug, in this case we forget the state
+ * temporarily. Fortunately that's not a big issue here (I hope)
+ */
+static int phys_package_first_cpu(int cpu)
+{
+	int i;
+	int id = topology_physical_package_id(cpu);
+
+	for_each_online_cpu(i)
+		if (topology_physical_package_id(i) == id)
+			return i;
+	return 0;
+}
+
 static int cpu_has_cpufreq(unsigned int cpu)
 {
 	struct cpufreq_policy policy;
@@ -76,7 +97,7 @@ static int acpi_thermal_cpufreq_notifier(struct notifier_block *nb,
 
 	max_freq = (
 	    policy->cpuinfo.max_freq *
-	    (100 - per_cpu(cpufreq_thermal_reduction_pctg, policy->cpu) * 20)
+	    (100 - reduction_pctg(policy->cpu) * 20)
 	) / 100;
 
 	cpufreq_verify_within_limits(policy, 0, max_freq);
@@ -102,16 +123,28 @@ static int cpufreq_get_cur_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return per_cpu(cpufreq_thermal_reduction_pctg, cpu);
+	return reduction_pctg(cpu);
 }
 
 static int cpufreq_set_cur_state(unsigned int cpu, int state)
 {
+	int i;
+
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	per_cpu(cpufreq_thermal_reduction_pctg, cpu) = state;
-	cpufreq_update_policy(cpu);
+	reduction_pctg(cpu) = state;
+
+	/*
+	 * Update all the CPUs in the same package because they all
+	 * contribute to the temperature and often share the same
+	 * frequency.
+	 */
+	for_each_online_cpu(i) {
+		if (topology_physical_package_id(i) ==
+		    topology_physical_package_id(cpu))
+			cpufreq_update_policy(i);
+	}
 	return 0;
 }
 
@@ -119,10 +152,6 @@ void acpi_thermal_cpufreq_init(void)
 {
 	int i;
 
-	for (i = 0; i < nr_cpu_ids; i++)
-		if (cpu_present(i))
-			per_cpu(cpufreq_thermal_reduction_pctg, i) = 0;
-
 	i = cpufreq_register_notifier(&acpi_thermal_cpufreq_notifier_block,
 				      CPUFREQ_POLICY_NOTIFIER);
 	if (!i)
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 605a2954ef17..1d02b7b5ade0 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -769,7 +769,7 @@ static int acpi_read_throttling_status(struct acpi_processor *pr,
 					u64 *value)
 {
 	u32 bit_width, bit_offset;
-	u64 ptc_value;
+	u32 ptc_value;
 	u64 ptc_mask;
 	struct acpi_processor_throttling *throttling;
 	int ret = -1;
@@ -777,12 +777,11 @@ static int acpi_read_throttling_status(struct acpi_processor *pr,
 	throttling = &pr->throttling;
 	switch (throttling->status_register.space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_IO:
-		ptc_value = 0;
 		bit_width = throttling->status_register.bit_width;
 		bit_offset = throttling->status_register.bit_offset;
 
 		acpi_os_read_port((acpi_io_address) throttling->status_register.
-				  address, (u32 *) &ptc_value,
+				  address, &ptc_value,
 				  (u32) (bit_width + bit_offset));
 		ptc_mask = (1 << bit_width) - 1;
 		*value = (u64) ((ptc_value >> bit_offset) & ptc_mask);
diff --git a/drivers/acpi/reboot.c b/drivers/acpi/reboot.c
index a6c77e8b37bd..c1d612435939 100644
--- a/drivers/acpi/reboot.c
+++ b/drivers/acpi/reboot.c
@@ -23,8 +23,7 @@ void acpi_reboot(void)
 	/* Is the reset register supported? The spec says we should be
 	 * checking the bit width and bit offset, but Windows ignores
 	 * these fields */
-	if (!(acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER))
-		return;
+	/* Ignore also acpi_gbl_FADT.flags.ACPI_FADT_RESET_REGISTER */
 
 	reset_value = acpi_gbl_FADT.reset_value;
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 8ab80bafe3f1..767e2dcb9616 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -880,18 +880,22 @@ static int acpi_bus_get_power_flags(struct acpi_device *device)
 			int j;
 
 			device->power.flags.power_resources = 1;
-			ps->flags.valid = 1;
 			for (j = 0; j < ps->resources.count; j++)
 				acpi_bus_add_power_resource(ps->resources.handles[j]);
 		}
 
+		/* The exist of _PR3 indicates D3Cold support */
+		if (i == ACPI_STATE_D3) {
+			status = acpi_get_handle(device->handle, object_name, &handle);
+			if (ACPI_SUCCESS(status))
+				device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
+		}
+
 		/* Evaluate "_PSx" to see if we can do explicit sets */
 		object_name[2] = 'S';
 		status = acpi_get_handle(device->handle, object_name, &handle);
-		if (ACPI_SUCCESS(status)) {
+		if (ACPI_SUCCESS(status))
 			ps->flags.explicit_set = 1;
-			ps->flags.valid = 1;
-		}
 
 		/* State is valid if we have some power control */
 		if (ps->resources.count || ps->flags.explicit_set)
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index ca191ff97844..1d661b5c3287 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -17,6 +17,8 @@
 #include <linux/suspend.h>
 #include <linux/reboot.h>
 #include <linux/acpi.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
 
 #include <asm/io.h>
 
@@ -26,6 +28,24 @@
 #include "internal.h"
 #include "sleep.h"
 
+static unsigned int gts, bfs;
+module_param(gts, uint, 0644);
+module_param(bfs, uint, 0644);
+MODULE_PARM_DESC(gts, "Enable evaluation of _GTS on suspend.");
+MODULE_PARM_DESC(bfs, "Enable evaluation of _BFS on resume".);
+
+static u8 wake_sleep_flags(void)
+{
+	u8 flags = ACPI_NO_OPTIONAL_METHODS;
+
+	if (gts)
+		flags |= ACPI_EXECUTE_GTS;
+	if (bfs)
+		flags |= ACPI_EXECUTE_BFS;
+
+	return flags;
+}
+
 static u8 sleep_states[ACPI_S_STATE_COUNT];
 
 static void acpi_sleep_tts_switch(u32 acpi_state)
@@ -243,6 +263,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state)
 {
 	acpi_status status = AE_OK;
 	u32 acpi_state = acpi_target_sleep_state;
+	u8 flags = wake_sleep_flags();
 	int error;
 
 	ACPI_FLUSH_CPU_CACHE();
@@ -250,7 +271,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state)
 	switch (acpi_state) {
 	case ACPI_STATE_S1:
 		barrier();
-		status = acpi_enter_sleep_state(acpi_state);
+		status = acpi_enter_sleep_state(acpi_state, flags);
 		break;
 
 	case ACPI_STATE_S3:
@@ -265,7 +286,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state)
 	acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1);
 
 	/* Reprogram control registers and execute _BFS */
-	acpi_leave_sleep_state_prep(acpi_state);
+	acpi_leave_sleep_state_prep(acpi_state, flags);
 
 	/* ACPI 3.0 specs (P62) says that it's the responsibility
 	 * of the OSPM to clear the status bit [ implying that the
@@ -529,27 +550,30 @@ static int acpi_hibernation_begin(void)
 
 static int acpi_hibernation_enter(void)
 {
+	u8 flags = wake_sleep_flags();
 	acpi_status status = AE_OK;
 
 	ACPI_FLUSH_CPU_CACHE();
 
 	/* This shouldn't return.  If it returns, we have a problem */
-	status = acpi_enter_sleep_state(ACPI_STATE_S4);
+	status = acpi_enter_sleep_state(ACPI_STATE_S4, flags);
 	/* Reprogram control registers and execute _BFS */
-	acpi_leave_sleep_state_prep(ACPI_STATE_S4);
+	acpi_leave_sleep_state_prep(ACPI_STATE_S4, flags);
 
 	return ACPI_SUCCESS(status) ? 0 : -EFAULT;
 }
 
 static void acpi_hibernation_leave(void)
 {
+	u8 flags = wake_sleep_flags();
+
 	/*
 	 * If ACPI is not enabled by the BIOS and the boot kernel, we need to
 	 * enable it here.
 	 */
 	acpi_enable();
 	/* Reprogram control registers and execute _BFS */
-	acpi_leave_sleep_state_prep(ACPI_STATE_S4);
+	acpi_leave_sleep_state_prep(ACPI_STATE_S4, flags);
 	/* Check the hardware signature */
 	if (facs && s4_hardware_signature != facs->hardware_signature) {
 		printk(KERN_EMERG "ACPI: Hardware changed while hibernated, "
@@ -730,6 +754,40 @@ int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p)
 
 #ifdef CONFIG_PM_SLEEP
 /**
+ * acpi_pm_device_run_wake - Enable/disable wake-up for given device.
+ * @phys_dev: Device to enable/disable the platform to wake-up the system for.
+ * @enable: Whether enable or disable the wake-up functionality.
+ *
+ * Find the ACPI device object corresponding to @pci_dev and try to
+ * enable/disable the GPE associated with it.
+ */
+int acpi_pm_device_run_wake(struct device *phys_dev, bool enable)
+{
+	struct acpi_device *dev;
+	acpi_handle handle;
+
+	if (!device_run_wake(phys_dev))
+		return -EINVAL;
+
+	handle = DEVICE_ACPI_HANDLE(phys_dev);
+	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &dev))) {
+		dev_dbg(phys_dev, "ACPI handle has no context in %s!\n",
+			__func__);
+		return -ENODEV;
+	}
+
+	if (enable) {
+		acpi_enable_wakeup_device_power(dev, ACPI_STATE_S0);
+		acpi_enable_gpe(dev->wakeup.gpe_device, dev->wakeup.gpe_number);
+	} else {
+		acpi_disable_gpe(dev->wakeup.gpe_device, dev->wakeup.gpe_number);
+		acpi_disable_wakeup_device_power(dev);
+	}
+
+	return 0;
+}
+
+/**
  *	acpi_pm_device_sleep_wake - enable or disable the system wake-up
  *                                  capability of given device
  *	@dev: device to handle
@@ -770,10 +828,12 @@ static void acpi_power_off_prepare(void)
 
 static void acpi_power_off(void)
 {
+	u8 flags = wake_sleep_flags();
+
 	/* acpi_sleep_prepare(ACPI_STATE_S5) should have already been called */
 	printk(KERN_DEBUG "%s called\n", __func__);
 	local_irq_disable();
-	acpi_enter_sleep_state(ACPI_STATE_S5);
+	acpi_enter_sleep_state(ACPI_STATE_S5, flags);
 }
 
 /*
@@ -788,13 +848,13 @@ static void __init acpi_gts_bfs_check(void)
 {
 	acpi_handle dummy;
 
-	if (ACPI_SUCCESS(acpi_get_handle(ACPI_ROOT_OBJECT, METHOD_NAME__GTS, &dummy)))
+	if (ACPI_SUCCESS(acpi_get_handle(ACPI_ROOT_OBJECT, METHOD_PATHNAME__GTS, &dummy)))
 	{
 		printk(KERN_NOTICE PREFIX "BIOS offers _GTS\n");
 		printk(KERN_NOTICE PREFIX "If \"acpi.gts=1\" improves suspend, "
 			"please notify linux-acpi@vger.kernel.org\n");
 	}
-	if (ACPI_SUCCESS(acpi_get_handle(ACPI_ROOT_OBJECT, METHOD_NAME__BFS, &dummy)))
+	if (ACPI_SUCCESS(acpi_get_handle(ACPI_ROOT_OBJECT, METHOD_PATHNAME__BFS, &dummy)))
 	{
 		printk(KERN_NOTICE PREFIX "BIOS offers _BFS\n");
 		printk(KERN_NOTICE PREFIX "If \"acpi.bfs=1\" improves resume, "
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 48fbc647b178..7dbebea1ec31 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -941,13 +941,13 @@ static int acpi_thermal_get_info(struct acpi_thermal *tz)
 	if (!tz)
 		return -EINVAL;
 
-	/* Get temperature [_TMP] (required) */
-	result = acpi_thermal_get_temperature(tz);
+	/* Get trip points [_CRT, _PSV, etc.] (required) */
+	result = acpi_thermal_get_trip_points(tz);
 	if (result)
 		return result;
 
-	/* Get trip points [_CRT, _PSV, etc.] (required) */
-	result = acpi_thermal_get_trip_points(tz);
+	/* Get temperature [_TMP] (required) */
+	result = acpi_thermal_get_temperature(tz);
 	if (result)
 		return result;
 
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index eaef02afc7cf..9577b6fa2650 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -548,27 +548,27 @@ acpi_video_device_EDID(struct acpi_video_device *device,
  *		1. 	The system BIOS should NOT automatically control the brightness 
  *			level of the LCD when the power changes from AC to DC.
  * Return Value:
- * 		-1	wrong arg.
+ *		-EINVAL	wrong arg.
  */
 
 static int
 acpi_video_bus_DOS(struct acpi_video_bus *video, int bios_flag, int lcd_flag)
 {
-	u64 status = 0;
+	acpi_status status;
 	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
 	struct acpi_object_list args = { 1, &arg0 };
 
 
-	if (bios_flag < 0 || bios_flag > 3 || lcd_flag < 0 || lcd_flag > 1) {
-		status = -1;
-		goto Failed;
-	}
+	if (bios_flag < 0 || bios_flag > 3 || lcd_flag < 0 || lcd_flag > 1)
+		return -EINVAL;
 	arg0.integer.value = (lcd_flag << 2) | bios_flag;
 	video->dos_setting = arg0.integer.value;
-	acpi_evaluate_object(video->device->handle, "_DOS", &args, NULL);
+	status = acpi_evaluate_object(video->device->handle, "_DOS",
+		&args, NULL);
+	if (ACPI_FAILURE(status))
+		return -EIO;
 
-      Failed:
-	return status;
+	return 0;
 }
 
 /*
@@ -1343,15 +1343,17 @@ static int
 acpi_video_bus_get_devices(struct acpi_video_bus *video,
 			   struct acpi_device *device)
 {
-	int status = 0;
+	int status;
 	struct acpi_device *dev;
 
-	acpi_video_device_enumerate(video);
+	status = acpi_video_device_enumerate(video);
+	if (status)
+		return status;
 
 	list_for_each_entry(dev, &device->children, node) {
 
 		status = acpi_video_bus_get_one_device(dev, video);
-		if (ACPI_FAILURE(status)) {
+		if (status) {
 			printk(KERN_WARNING PREFIX
 					"Can't attach device\n");
 			continue;
@@ -1653,15 +1655,20 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	mutex_init(&video->device_list_lock);
 	INIT_LIST_HEAD(&video->video_device_list);
 
-	acpi_video_bus_get_devices(video, device);
-	acpi_video_bus_start_devices(video);
+	error = acpi_video_bus_get_devices(video, device);
+	if (error)
+		goto err_free_video;
 
 	video->input = input = input_allocate_device();
 	if (!input) {
 		error = -ENOMEM;
-		goto err_stop_video;
+		goto err_put_video;
 	}
 
+	error = acpi_video_bus_start_devices(video);
+	if (error)
+		goto err_free_input_dev;
+
 	snprintf(video->phys, sizeof(video->phys),
 		"%s/video/input0", acpi_device_hid(video->device));
 
@@ -1682,7 +1689,7 @@ static int acpi_video_bus_add(struct acpi_device *device)
 
 	error = input_register_device(input);
 	if (error)
-		goto err_free_input_dev;
+		goto err_stop_video;
 
 	printk(KERN_INFO PREFIX "%s [%s] (multi-head: %s  rom: %s  post: %s)\n",
 	       ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device),
@@ -1692,14 +1699,19 @@ static int acpi_video_bus_add(struct acpi_device *device)
 
 	video->pm_nb.notifier_call = acpi_video_resume;
 	video->pm_nb.priority = 0;
-	register_pm_notifier(&video->pm_nb);
+	error = register_pm_notifier(&video->pm_nb);
+	if (error)
+		goto err_unregister_input_dev;
 
 	return 0;
 
- err_free_input_dev:
-	input_free_device(input);
+ err_unregister_input_dev:
+	input_unregister_device(input);
  err_stop_video:
 	acpi_video_bus_stop_devices(video);
+ err_free_input_dev:
+	input_free_device(input);
+ err_put_video:
 	acpi_video_bus_put_devices(video);
 	kfree(video->attached_array);
  err_free_video:
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index f3f0fe7e255a..45d8097ef4cf 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -23,7 +23,7 @@
  * Depending on whether ACPI graphics extensions (cmp. ACPI spec Appendix B)
  * are available, video.ko should be used to handle the device.
  *
- * Otherwise vendor specific drivers like thinkpad_acpi, asus_acpi,
+ * Otherwise vendor specific drivers like thinkpad_acpi, asus-laptop,
  * sony_acpi,... can take care about backlight brightness.
  *
  * If CONFIG_ACPI_VIDEO is neither set as "compiled in" (y) nor as a module (m)
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index 6ff612d099c3..2059ee460b0c 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -19,7 +19,6 @@
 #include <linux/atm_eni.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
 #include <asm/uaccess.h>
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 5072f8ac16fd..86fed1b91695 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -49,7 +49,6 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/string.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/drivers/atm/horizon.c b/drivers/atm/horizon.c
index 71c801bb6845..7d01c2a75256 100644
--- a/drivers/atm/horizon.c
+++ b/drivers/atm/horizon.c
@@ -43,7 +43,6 @@
 #include <linux/wait.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
 #include <asm/uaccess.h>
diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index 487a54739854..45d506363aba 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -16,7 +16,6 @@
 #include <linux/atm_idt77105.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <asm/param.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 9e373ba20308..d4386019af5d 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -56,7 +56,6 @@
 #include <linux/interrupt.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
-#include <asm/system.h>  
 #include <asm/io.h>  
 #include <linux/atomic.h>
 #include <asm/uaccess.h>  
diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c
index 90f1ccca9e52..02159345566c 100644
--- a/drivers/atm/suni.c
+++ b/drivers/atm/suni.c
@@ -22,7 +22,6 @@
 #include <linux/capability.h>
 #include <linux/atm_suni.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <asm/param.h>
 #include <asm/uaccess.h>
 #include <linux/atomic.h>
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index d889f56e8d8c..abe4e20b0766 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -24,7 +24,6 @@
 #include <linux/wait.h>
 #include <linux/slab.h>
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/string.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c
index e38ad243b4bb..07cbbc6fddb4 100644
--- a/drivers/base/dma-buf.c
+++ b/drivers/base/dma-buf.c
@@ -71,7 +71,7 @@ static inline int is_dma_buf_file(struct file *file)
  * ops, or error in allocating struct dma_buf, will return negative error.
  *
  */
-struct dma_buf *dma_buf_export(void *priv, struct dma_buf_ops *ops,
+struct dma_buf *dma_buf_export(void *priv, const struct dma_buf_ops *ops,
 				size_t size, int flags)
 {
 	struct dma_buf *dmabuf;
@@ -80,7 +80,9 @@ struct dma_buf *dma_buf_export(void *priv, struct dma_buf_ops *ops,
 	if (WARN_ON(!priv || !ops
 			  || !ops->map_dma_buf
 			  || !ops->unmap_dma_buf
-			  || !ops->release)) {
+			  || !ops->release
+			  || !ops->kmap_atomic
+			  || !ops->kmap)) {
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -107,17 +109,18 @@ EXPORT_SYMBOL_GPL(dma_buf_export);
 /**
  * dma_buf_fd - returns a file descriptor for the given dma_buf
  * @dmabuf:	[in]	pointer to dma_buf for which fd is required.
+ * @flags:      [in]    flags to give to fd
  *
  * On success, returns an associated 'fd'. Else, returns error.
  */
-int dma_buf_fd(struct dma_buf *dmabuf)
+int dma_buf_fd(struct dma_buf *dmabuf, int flags)
 {
 	int error, fd;
 
 	if (!dmabuf || !dmabuf->file)
 		return -EINVAL;
 
-	error = get_unused_fd();
+	error = get_unused_fd_flags(flags);
 	if (error < 0)
 		return error;
 	fd = error;
@@ -185,17 +188,18 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 	struct dma_buf_attachment *attach;
 	int ret;
 
-	if (WARN_ON(!dmabuf || !dev || !dmabuf->ops))
+	if (WARN_ON(!dmabuf || !dev))
 		return ERR_PTR(-EINVAL);
 
 	attach = kzalloc(sizeof(struct dma_buf_attachment), GFP_KERNEL);
 	if (attach == NULL)
-		goto err_alloc;
-
-	mutex_lock(&dmabuf->lock);
+		return ERR_PTR(-ENOMEM);
 
 	attach->dev = dev;
 	attach->dmabuf = dmabuf;
+
+	mutex_lock(&dmabuf->lock);
+
 	if (dmabuf->ops->attach) {
 		ret = dmabuf->ops->attach(dmabuf, dev, attach);
 		if (ret)
@@ -206,8 +210,6 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 	mutex_unlock(&dmabuf->lock);
 	return attach;
 
-err_alloc:
-	return ERR_PTR(-ENOMEM);
 err_attach:
 	kfree(attach);
 	mutex_unlock(&dmabuf->lock);
@@ -224,7 +226,7 @@ EXPORT_SYMBOL_GPL(dma_buf_attach);
  */
 void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 {
-	if (WARN_ON(!dmabuf || !attach || !dmabuf->ops))
+	if (WARN_ON(!dmabuf || !attach))
 		return;
 
 	mutex_lock(&dmabuf->lock);
@@ -255,13 +257,10 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 
 	might_sleep();
 
-	if (WARN_ON(!attach || !attach->dmabuf || !attach->dmabuf->ops))
+	if (WARN_ON(!attach || !attach->dmabuf))
 		return ERR_PTR(-EINVAL);
 
-	mutex_lock(&attach->dmabuf->lock);
-	if (attach->dmabuf->ops->map_dma_buf)
-		sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
-	mutex_unlock(&attach->dmabuf->lock);
+	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
 
 	return sg_table;
 }
@@ -273,19 +272,137 @@ EXPORT_SYMBOL_GPL(dma_buf_map_attachment);
  * dma_buf_ops.
  * @attach:	[in]	attachment to unmap buffer from
  * @sg_table:	[in]	scatterlist info of the buffer to unmap
+ * @direction:  [in]    direction of DMA transfer
  *
  */
 void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
-				struct sg_table *sg_table)
+				struct sg_table *sg_table,
+				enum dma_data_direction direction)
 {
-	if (WARN_ON(!attach || !attach->dmabuf || !sg_table
-			    || !attach->dmabuf->ops))
+	if (WARN_ON(!attach || !attach->dmabuf || !sg_table))
 		return;
 
-	mutex_lock(&attach->dmabuf->lock);
-	if (attach->dmabuf->ops->unmap_dma_buf)
-		attach->dmabuf->ops->unmap_dma_buf(attach, sg_table);
-	mutex_unlock(&attach->dmabuf->lock);
-
+	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table,
+						direction);
 }
 EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
+
+
+/**
+ * dma_buf_begin_cpu_access - Must be called before accessing a dma_buf from the
+ * cpu in the kernel context. Calls begin_cpu_access to allow exporter-specific
+ * preparations. Coherency is only guaranteed in the specified range for the
+ * specified access direction.
+ * @dma_buf:	[in]	buffer to prepare cpu access for.
+ * @start:	[in]	start of range for cpu access.
+ * @len:	[in]	length of range for cpu access.
+ * @direction:	[in]	length of range for cpu access.
+ *
+ * Can return negative error values, returns 0 on success.
+ */
+int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, size_t start, size_t len,
+			     enum dma_data_direction direction)
+{
+	int ret = 0;
+
+	if (WARN_ON(!dmabuf))
+		return -EINVAL;
+
+	if (dmabuf->ops->begin_cpu_access)
+		ret = dmabuf->ops->begin_cpu_access(dmabuf, start, len, direction);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dma_buf_begin_cpu_access);
+
+/**
+ * dma_buf_end_cpu_access - Must be called after accessing a dma_buf from the
+ * cpu in the kernel context. Calls end_cpu_access to allow exporter-specific
+ * actions. Coherency is only guaranteed in the specified range for the
+ * specified access direction.
+ * @dma_buf:	[in]	buffer to complete cpu access for.
+ * @start:	[in]	start of range for cpu access.
+ * @len:	[in]	length of range for cpu access.
+ * @direction:	[in]	length of range for cpu access.
+ *
+ * This call must always succeed.
+ */
+void dma_buf_end_cpu_access(struct dma_buf *dmabuf, size_t start, size_t len,
+			    enum dma_data_direction direction)
+{
+	WARN_ON(!dmabuf);
+
+	if (dmabuf->ops->end_cpu_access)
+		dmabuf->ops->end_cpu_access(dmabuf, start, len, direction);
+}
+EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access);
+
+/**
+ * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address
+ * space. The same restrictions as for kmap_atomic and friends apply.
+ * @dma_buf:	[in]	buffer to map page from.
+ * @page_num:	[in]	page in PAGE_SIZE units to map.
+ *
+ * This call must always succeed, any necessary preparations that might fail
+ * need to be done in begin_cpu_access.
+ */
+void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, unsigned long page_num)
+{
+	WARN_ON(!dmabuf);
+
+	return dmabuf->ops->kmap_atomic(dmabuf, page_num);
+}
+EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic);
+
+/**
+ * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic.
+ * @dma_buf:	[in]	buffer to unmap page from.
+ * @page_num:	[in]	page in PAGE_SIZE units to unmap.
+ * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap_atomic.
+ *
+ * This call must always succeed.
+ */
+void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, unsigned long page_num,
+			   void *vaddr)
+{
+	WARN_ON(!dmabuf);
+
+	if (dmabuf->ops->kunmap_atomic)
+		dmabuf->ops->kunmap_atomic(dmabuf, page_num, vaddr);
+}
+EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic);
+
+/**
+ * dma_buf_kmap - Map a page of the buffer object into kernel address space. The
+ * same restrictions as for kmap and friends apply.
+ * @dma_buf:	[in]	buffer to map page from.
+ * @page_num:	[in]	page in PAGE_SIZE units to map.
+ *
+ * This call must always succeed, any necessary preparations that might fail
+ * need to be done in begin_cpu_access.
+ */
+void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num)
+{
+	WARN_ON(!dmabuf);
+
+	return dmabuf->ops->kmap(dmabuf, page_num);
+}
+EXPORT_SYMBOL_GPL(dma_buf_kmap);
+
+/**
+ * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap.
+ * @dma_buf:	[in]	buffer to unmap page from.
+ * @page_num:	[in]	page in PAGE_SIZE units to unmap.
+ * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap.
+ *
+ * This call must always succeed.
+ */
+void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long page_num,
+		    void *vaddr)
+{
+	WARN_ON(!dmabuf);
+
+	if (dmabuf->ops->kunmap)
+		dmabuf->ops->kunmap(dmabuf, page_num, vaddr);
+}
+EXPORT_SYMBOL_GPL(dma_buf_kunmap);
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 6c9387d646ec..5401814c874d 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -16,10 +16,11 @@
 #include <linux/interrupt.h>
 #include <linux/bitops.h>
 #include <linux/mutex.h>
-#include <linux/kthread.h>
+#include <linux/workqueue.h>
 #include <linux/highmem.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 #define to_dev(obj) container_of(obj, struct device, kobj)
 
@@ -81,6 +82,11 @@ enum {
 
 static int loading_timeout = 60;	/* In seconds */
 
+static inline long firmware_loading_timeout(void)
+{
+	return loading_timeout > 0 ? loading_timeout * HZ : MAX_SCHEDULE_TIMEOUT;
+}
+
 /* fw_lock could be moved to 'struct firmware_priv' but since it is just
  * guarding for corner cases a global lock should be OK */
 static DEFINE_MUTEX(fw_lock);
@@ -440,13 +446,11 @@ fw_create_instance(struct firmware *firmware, const char *fw_name,
 {
 	struct firmware_priv *fw_priv;
 	struct device *f_dev;
-	int error;
 
 	fw_priv = kzalloc(sizeof(*fw_priv) + strlen(fw_name) + 1 , GFP_KERNEL);
 	if (!fw_priv) {
 		dev_err(device, "%s: kmalloc failed\n", __func__);
-		error = -ENOMEM;
-		goto err_out;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	fw_priv->fw = firmware;
@@ -463,98 +467,80 @@ fw_create_instance(struct firmware *firmware, const char *fw_name,
 	f_dev->parent = device;
 	f_dev->class = &firmware_class;
 
-	dev_set_uevent_suppress(f_dev, true);
-
-	/* Need to pin this module until class device is destroyed */
-	__module_get(THIS_MODULE);
-
-	error = device_add(f_dev);
-	if (error) {
-		dev_err(device, "%s: device_register failed\n", __func__);
-		goto err_put_dev;
-	}
-
-	error = device_create_bin_file(f_dev, &firmware_attr_data);
-	if (error) {
-		dev_err(device, "%s: sysfs_create_bin_file failed\n", __func__);
-		goto err_del_dev;
-	}
-
-	error = device_create_file(f_dev, &dev_attr_loading);
-	if (error) {
-		dev_err(device, "%s: device_create_file failed\n", __func__);
-		goto err_del_bin_attr;
-	}
-
-	if (uevent)
-		dev_set_uevent_suppress(f_dev, false);
-
 	return fw_priv;
-
-err_del_bin_attr:
-	device_remove_bin_file(f_dev, &firmware_attr_data);
-err_del_dev:
-	device_del(f_dev);
-err_put_dev:
-	put_device(f_dev);
-err_out:
-	return ERR_PTR(error);
 }
 
-static void fw_destroy_instance(struct firmware_priv *fw_priv)
-{
-	struct device *f_dev = &fw_priv->dev;
-
-	device_remove_file(f_dev, &dev_attr_loading);
-	device_remove_bin_file(f_dev, &firmware_attr_data);
-	device_unregister(f_dev);
-}
-
-static int _request_firmware(const struct firmware **firmware_p,
-			     const char *name, struct device *device,
-			     bool uevent, bool nowait)
+static struct firmware_priv *
+_request_firmware_prepare(const struct firmware **firmware_p, const char *name,
+			  struct device *device, bool uevent, bool nowait)
 {
-	struct firmware_priv *fw_priv;
 	struct firmware *firmware;
-	int retval = 0;
+	struct firmware_priv *fw_priv;
 
 	if (!firmware_p)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	*firmware_p = firmware = kzalloc(sizeof(*firmware), GFP_KERNEL);
 	if (!firmware) {
 		dev_err(device, "%s: kmalloc(struct firmware) failed\n",
 			__func__);
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	if (fw_get_builtin_firmware(firmware, name)) {
 		dev_dbg(device, "firmware: using built-in firmware %s\n", name);
-		return 0;
+		return NULL;
+	}
+
+	fw_priv = fw_create_instance(firmware, name, device, uevent, nowait);
+	if (IS_ERR(fw_priv)) {
+		release_firmware(firmware);
+		*firmware_p = NULL;
 	}
+	return fw_priv;
+}
 
-	read_lock_usermodehelper();
+static void _request_firmware_cleanup(const struct firmware **firmware_p)
+{
+	release_firmware(*firmware_p);
+	*firmware_p = NULL;
+}
 
-	if (WARN_ON(usermodehelper_is_disabled())) {
-		dev_err(device, "firmware: %s will not be loaded\n", name);
-		retval = -EBUSY;
-		goto out;
+static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
+				  long timeout)
+{
+	int retval = 0;
+	struct device *f_dev = &fw_priv->dev;
+
+	dev_set_uevent_suppress(f_dev, true);
+
+	/* Need to pin this module until class device is destroyed */
+	__module_get(THIS_MODULE);
+
+	retval = device_add(f_dev);
+	if (retval) {
+		dev_err(f_dev, "%s: device_register failed\n", __func__);
+		goto err_put_dev;
 	}
 
-	if (uevent)
-		dev_dbg(device, "firmware: requesting %s\n", name);
+	retval = device_create_bin_file(f_dev, &firmware_attr_data);
+	if (retval) {
+		dev_err(f_dev, "%s: sysfs_create_bin_file failed\n", __func__);
+		goto err_del_dev;
+	}
 
-	fw_priv = fw_create_instance(firmware, name, device, uevent, nowait);
-	if (IS_ERR(fw_priv)) {
-		retval = PTR_ERR(fw_priv);
-		goto out;
+	retval = device_create_file(f_dev, &dev_attr_loading);
+	if (retval) {
+		dev_err(f_dev, "%s: device_create_file failed\n", __func__);
+		goto err_del_bin_attr;
 	}
 
 	if (uevent) {
-		if (loading_timeout > 0)
+		dev_set_uevent_suppress(f_dev, false);
+		dev_dbg(f_dev, "firmware: requesting %s\n", fw_priv->fw_id);
+		if (timeout != MAX_SCHEDULE_TIMEOUT)
 			mod_timer(&fw_priv->timeout,
-				  round_jiffies_up(jiffies +
-						   loading_timeout * HZ));
+				  round_jiffies_up(jiffies + timeout));
 
 		kobject_uevent(&fw_priv->dev.kobj, KOBJ_ADD);
 	}
@@ -570,16 +556,13 @@ static int _request_firmware(const struct firmware **firmware_p,
 	fw_priv->fw = NULL;
 	mutex_unlock(&fw_lock);
 
-	fw_destroy_instance(fw_priv);
-
-out:
-	read_unlock_usermodehelper();
-
-	if (retval) {
-		release_firmware(firmware);
-		*firmware_p = NULL;
-	}
-
+	device_remove_file(f_dev, &dev_attr_loading);
+err_del_bin_attr:
+	device_remove_bin_file(f_dev, &firmware_attr_data);
+err_del_dev:
+	device_del(f_dev);
+err_put_dev:
+	put_device(f_dev);
 	return retval;
 }
 
@@ -602,7 +585,26 @@ int
 request_firmware(const struct firmware **firmware_p, const char *name,
                  struct device *device)
 {
-        return _request_firmware(firmware_p, name, device, true, false);
+	struct firmware_priv *fw_priv;
+	int ret;
+
+	fw_priv = _request_firmware_prepare(firmware_p, name, device, true,
+					    false);
+	if (IS_ERR_OR_NULL(fw_priv))
+		return PTR_RET(fw_priv);
+
+	ret = usermodehelper_read_trylock();
+	if (WARN_ON(ret)) {
+		dev_err(device, "firmware: %s will not be loaded\n", name);
+	} else {
+		ret = _request_firmware_load(fw_priv, true,
+					firmware_loading_timeout());
+		usermodehelper_read_unlock();
+	}
+	if (ret)
+		_request_firmware_cleanup(firmware_p);
+
+	return ret;
 }
 
 /**
@@ -629,25 +631,39 @@ struct firmware_work {
 	bool uevent;
 };
 
-static int request_firmware_work_func(void *arg)
+static void request_firmware_work_func(struct work_struct *work)
 {
-	struct firmware_work *fw_work = arg;
+	struct firmware_work *fw_work;
 	const struct firmware *fw;
+	struct firmware_priv *fw_priv;
+	long timeout;
 	int ret;
 
-	if (!arg) {
-		WARN_ON(1);
-		return 0;
+	fw_work = container_of(work, struct firmware_work, work);
+	fw_priv = _request_firmware_prepare(&fw, fw_work->name, fw_work->device,
+			fw_work->uevent, true);
+	if (IS_ERR_OR_NULL(fw_priv)) {
+		ret = PTR_RET(fw_priv);
+		goto out;
+	}
+
+	timeout = usermodehelper_read_lock_wait(firmware_loading_timeout());
+	if (timeout) {
+		ret = _request_firmware_load(fw_priv, fw_work->uevent, timeout);
+		usermodehelper_read_unlock();
+	} else {
+		dev_dbg(fw_work->device, "firmware: %s loading timed out\n",
+			fw_work->name);
+		ret = -EAGAIN;
 	}
+	if (ret)
+		_request_firmware_cleanup(&fw);
 
-	ret = _request_firmware(&fw, fw_work->name, fw_work->device,
-				fw_work->uevent, true);
+ out:
 	fw_work->cont(fw, fw_work->context);
 
 	module_put(fw_work->module);
 	kfree(fw_work);
-
-	return ret;
 }
 
 /**
@@ -673,7 +689,6 @@ request_firmware_nowait(
 	const char *name, struct device *device, gfp_t gfp, void *context,
 	void (*cont)(const struct firmware *fw, void *context))
 {
-	struct task_struct *task;
 	struct firmware_work *fw_work;
 
 	fw_work = kzalloc(sizeof (struct firmware_work), gfp);
@@ -692,15 +707,8 @@ request_firmware_nowait(
 		return -EFAULT;
 	}
 
-	task = kthread_run(request_firmware_work_func, fw_work,
-			    "firmware/%s", name);
-	if (IS_ERR(task)) {
-		fw_work->cont(NULL, fw_work->context);
-		module_put(fw_work->module);
-		kfree(fw_work);
-		return PTR_ERR(task);
-	}
-
+	INIT_WORK(&fw_work->work, request_firmware_work_func);
+	schedule_work(&fw_work->work);
 	return 0;
 }
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 541f821d4ea6..bd0f3949bcf9 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -532,6 +532,8 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	dev->power.suspend_time = ktime_set(0, 0);
 	dev->power.max_time_suspended_ns = -1;
 	dev->power.deferred_resume = false;
+	wake_up_all(&dev->power.wait_queue);
+
 	if (retval == -EAGAIN || retval == -EBUSY) {
 		dev->power.runtime_error = 0;
 
@@ -547,7 +549,6 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	} else {
 		pm_runtime_cancel_pending(dev);
 	}
-	wake_up_all(&dev->power.wait_queue);
 	goto out;
 }
 
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index 5157fa04c2f0..fb14a6343d4f 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -396,7 +396,7 @@ static int regcache_rbtree_sync(struct regmap *map, unsigned int min,
 							   map->cache_word_size);
 
 			/* Is this the hardware default?  If so skip. */
-			ret = regcache_lookup_reg(map, i);
+			ret = regcache_lookup_reg(map, regtmp);
 			if (ret >= 0 && val == map->reg_defaults[ret].def)
 				continue;
 
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 58517a5dac13..251eb70f83e7 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -27,12 +27,6 @@ static size_t regmap_calc_reg_len(int max_val, char *buf, size_t buf_size)
 	return strlen(buf);
 }
 
-static int regmap_open_file(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t regmap_name_read_file(struct file *file,
 				     char __user *user_buf, size_t count,
 				     loff_t *ppos)
@@ -57,7 +51,7 @@ static ssize_t regmap_name_read_file(struct file *file,
 }
 
 static const struct file_operations regmap_name_fops = {
-	.open = regmap_open_file,
+	.open = simple_open,
 	.read = regmap_name_read_file,
 	.llseek = default_llseek,
 };
@@ -174,7 +168,7 @@ static ssize_t regmap_map_write_file(struct file *file,
 #endif
 
 static const struct file_operations regmap_map_fops = {
-	.open = regmap_open_file,
+	.open = simple_open,
 	.read = regmap_map_read_file,
 	.write = regmap_map_write_file,
 	.llseek = default_llseek,
@@ -243,7 +237,7 @@ out:
 }
 
 static const struct file_operations regmap_access_fops = {
-	.open = regmap_open_file,
+	.open = simple_open,
 	.read = regmap_access_read_file,
 	.llseek = default_llseek,
 };
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 744f078f4dd8..b0b00d70c166 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -202,7 +202,6 @@ static int slow_floppy;
 
 #include <asm/dma.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 static int FLOPPY_IRQ = 6;
 static int FLOPPY_DMA = 2;
@@ -1031,37 +1030,6 @@ static int fd_wait_for_completion(unsigned long delay, timeout_fn function)
 	return 0;
 }
 
-static DEFINE_SPINLOCK(floppy_hlt_lock);
-static int hlt_disabled;
-static void floppy_disable_hlt(void)
-{
-	unsigned long flags;
-
-	WARN_ONCE(1, "floppy_disable_hlt() scheduled for removal in 2012");
-	spin_lock_irqsave(&floppy_hlt_lock, flags);
-	if (!hlt_disabled) {
-		hlt_disabled = 1;
-#ifdef HAVE_DISABLE_HLT
-		disable_hlt();
-#endif
-	}
-	spin_unlock_irqrestore(&floppy_hlt_lock, flags);
-}
-
-static void floppy_enable_hlt(void)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&floppy_hlt_lock, flags);
-	if (hlt_disabled) {
-		hlt_disabled = 0;
-#ifdef HAVE_DISABLE_HLT
-		enable_hlt();
-#endif
-	}
-	spin_unlock_irqrestore(&floppy_hlt_lock, flags);
-}
-
 static void setup_DMA(void)
 {
 	unsigned long f;
@@ -1106,7 +1074,6 @@ static void setup_DMA(void)
 	fd_enable_dma();
 	release_dma_lock(f);
 #endif
-	floppy_disable_hlt();
 }
 
 static void show_floppy(void);
@@ -1708,7 +1675,6 @@ irqreturn_t floppy_interrupt(int irq, void *dev_id)
 	fd_disable_dma();
 	release_dma_lock(f);
 
-	floppy_enable_hlt();
 	do_floppy = NULL;
 	if (fdc >= N_FDC || FDCS->address == -1) {
 		/* we don't even know which FDC is the culprit */
@@ -1857,8 +1823,6 @@ static void floppy_shutdown(unsigned long data)
 		show_floppy();
 	cancel_activity();
 
-	floppy_enable_hlt();
-
 	flags = claim_dma_lock();
 	fd_disable_dma();
 	release_dma_lock(flags);
@@ -4509,7 +4473,6 @@ static void floppy_release_irq_and_dma(void)
 #if N_FDC > 1
 	set_dor(1, ~8, 0);
 #endif
-	floppy_enable_hlt();
 
 	if (floppy_track_buffer && max_buffer_sectors) {
 		tmpsize = max_buffer_sectors * 1024;
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index b52c9ca146fc..bf397bf108b7 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -44,7 +44,6 @@
 #define HD_IRQ 14
 
 #define REALLY_SLOW_IO
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index c3f0ee16594d..061427a75d37 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -34,12 +34,11 @@
 #include <linux/kthread.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/types.h>
 
 #include <linux/nbd.h>
 
-#define LO_MAGIC 0x68797548
+#define NBD_MAGIC 0x68797548
 
 #ifdef NDEBUG
 #define dprintk(flags, fmt...)
@@ -116,7 +115,7 @@ static void nbd_end_request(struct request *req)
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
-static void sock_shutdown(struct nbd_device *lo, int lock)
+static void sock_shutdown(struct nbd_device *nbd, int lock)
 {
 	/* Forcibly shutdown the socket causing all listeners
 	 * to error
@@ -125,14 +124,14 @@ static void sock_shutdown(struct nbd_device *lo, int lock)
 	 * there should be a more generic interface rather than
 	 * calling socket ops directly here */
 	if (lock)
-		mutex_lock(&lo->tx_lock);
-	if (lo->sock) {
-		dev_warn(disk_to_dev(lo->disk), "shutting down socket\n");
-		kernel_sock_shutdown(lo->sock, SHUT_RDWR);
-		lo->sock = NULL;
+		mutex_lock(&nbd->tx_lock);
+	if (nbd->sock) {
+		dev_warn(disk_to_dev(nbd->disk), "shutting down socket\n");
+		kernel_sock_shutdown(nbd->sock, SHUT_RDWR);
+		nbd->sock = NULL;
 	}
 	if (lock)
-		mutex_unlock(&lo->tx_lock);
+		mutex_unlock(&nbd->tx_lock);
 }
 
 static void nbd_xmit_timeout(unsigned long arg)
@@ -147,17 +146,17 @@ static void nbd_xmit_timeout(unsigned long arg)
 /*
  *  Send or receive packet.
  */
-static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
+static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
 		int msg_flags)
 {
-	struct socket *sock = lo->sock;
+	struct socket *sock = nbd->sock;
 	int result;
 	struct msghdr msg;
 	struct kvec iov;
 	sigset_t blocked, oldset;
 
 	if (unlikely(!sock)) {
-		dev_err(disk_to_dev(lo->disk),
+		dev_err(disk_to_dev(nbd->disk),
 			"Attempted %s on closed socket in sock_xmit\n",
 			(send ? "send" : "recv"));
 		return -EINVAL;
@@ -181,15 +180,15 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
 		if (send) {
 			struct timer_list ti;
 
-			if (lo->xmit_timeout) {
+			if (nbd->xmit_timeout) {
 				init_timer(&ti);
 				ti.function = nbd_xmit_timeout;
 				ti.data = (unsigned long)current;
-				ti.expires = jiffies + lo->xmit_timeout;
+				ti.expires = jiffies + nbd->xmit_timeout;
 				add_timer(&ti);
 			}
 			result = kernel_sendmsg(sock, &msg, &iov, 1, size);
-			if (lo->xmit_timeout)
+			if (nbd->xmit_timeout)
 				del_timer_sync(&ti);
 		} else
 			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
@@ -201,7 +200,7 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
 				task_pid_nr(current), current->comm,
 				dequeue_signal_lock(current, &current->blocked, &info));
 			result = -EINTR;
-			sock_shutdown(lo, !send);
+			sock_shutdown(nbd, !send);
 			break;
 		}
 
@@ -219,18 +218,19 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
 	return result;
 }
 
-static inline int sock_send_bvec(struct nbd_device *lo, struct bio_vec *bvec,
+static inline int sock_send_bvec(struct nbd_device *nbd, struct bio_vec *bvec,
 		int flags)
 {
 	int result;
 	void *kaddr = kmap(bvec->bv_page);
-	result = sock_xmit(lo, 1, kaddr + bvec->bv_offset, bvec->bv_len, flags);
+	result = sock_xmit(nbd, 1, kaddr + bvec->bv_offset,
+			   bvec->bv_len, flags);
 	kunmap(bvec->bv_page);
 	return result;
 }
 
 /* always call with the tx_lock held */
-static int nbd_send_req(struct nbd_device *lo, struct request *req)
+static int nbd_send_req(struct nbd_device *nbd, struct request *req)
 {
 	int result, flags;
 	struct nbd_request request;
@@ -243,14 +243,14 @@ static int nbd_send_req(struct nbd_device *lo, struct request *req)
 	memcpy(request.handle, &req, sizeof(req));
 
 	dprintk(DBG_TX, "%s: request %p: sending control (%s@%llu,%uB)\n",
-			lo->disk->disk_name, req,
+			nbd->disk->disk_name, req,
 			nbdcmd_to_ascii(nbd_cmd(req)),
 			(unsigned long long)blk_rq_pos(req) << 9,
 			blk_rq_bytes(req));
-	result = sock_xmit(lo, 1, &request, sizeof(request),
+	result = sock_xmit(nbd, 1, &request, sizeof(request),
 			(nbd_cmd(req) == NBD_CMD_WRITE) ? MSG_MORE : 0);
 	if (result <= 0) {
-		dev_err(disk_to_dev(lo->disk),
+		dev_err(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
 		goto error_out;
 	}
@@ -267,10 +267,10 @@ static int nbd_send_req(struct nbd_device *lo, struct request *req)
 			if (!rq_iter_last(req, iter))
 				flags = MSG_MORE;
 			dprintk(DBG_TX, "%s: request %p: sending %d bytes data\n",
-					lo->disk->disk_name, req, bvec->bv_len);
-			result = sock_send_bvec(lo, bvec, flags);
+					nbd->disk->disk_name, req, bvec->bv_len);
+			result = sock_send_bvec(nbd, bvec, flags);
 			if (result <= 0) {
-				dev_err(disk_to_dev(lo->disk),
+				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
 					result);
 				goto error_out;
@@ -283,25 +283,25 @@ error_out:
 	return -EIO;
 }
 
-static struct request *nbd_find_request(struct nbd_device *lo,
+static struct request *nbd_find_request(struct nbd_device *nbd,
 					struct request *xreq)
 {
 	struct request *req, *tmp;
 	int err;
 
-	err = wait_event_interruptible(lo->active_wq, lo->active_req != xreq);
+	err = wait_event_interruptible(nbd->active_wq, nbd->active_req != xreq);
 	if (unlikely(err))
 		goto out;
 
-	spin_lock(&lo->queue_lock);
-	list_for_each_entry_safe(req, tmp, &lo->queue_head, queuelist) {
+	spin_lock(&nbd->queue_lock);
+	list_for_each_entry_safe(req, tmp, &nbd->queue_head, queuelist) {
 		if (req != xreq)
 			continue;
 		list_del_init(&req->queuelist);
-		spin_unlock(&lo->queue_lock);
+		spin_unlock(&nbd->queue_lock);
 		return req;
 	}
-	spin_unlock(&lo->queue_lock);
+	spin_unlock(&nbd->queue_lock);
 
 	err = -ENOENT;
 
@@ -309,78 +309,78 @@ out:
 	return ERR_PTR(err);
 }
 
-static inline int sock_recv_bvec(struct nbd_device *lo, struct bio_vec *bvec)
+static inline int sock_recv_bvec(struct nbd_device *nbd, struct bio_vec *bvec)
 {
 	int result;
 	void *kaddr = kmap(bvec->bv_page);
-	result = sock_xmit(lo, 0, kaddr + bvec->bv_offset, bvec->bv_len,
+	result = sock_xmit(nbd, 0, kaddr + bvec->bv_offset, bvec->bv_len,
 			MSG_WAITALL);
 	kunmap(bvec->bv_page);
 	return result;
 }
 
 /* NULL returned = something went wrong, inform userspace */
-static struct request *nbd_read_stat(struct nbd_device *lo)
+static struct request *nbd_read_stat(struct nbd_device *nbd)
 {
 	int result;
 	struct nbd_reply reply;
 	struct request *req;
 
 	reply.magic = 0;
-	result = sock_xmit(lo, 0, &reply, sizeof(reply), MSG_WAITALL);
+	result = sock_xmit(nbd, 0, &reply, sizeof(reply), MSG_WAITALL);
 	if (result <= 0) {
-		dev_err(disk_to_dev(lo->disk),
+		dev_err(disk_to_dev(nbd->disk),
 			"Receive control failed (result %d)\n", result);
 		goto harderror;
 	}
 
 	if (ntohl(reply.magic) != NBD_REPLY_MAGIC) {
-		dev_err(disk_to_dev(lo->disk), "Wrong magic (0x%lx)\n",
+		dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n",
 				(unsigned long)ntohl(reply.magic));
 		result = -EPROTO;
 		goto harderror;
 	}
 
-	req = nbd_find_request(lo, *(struct request **)reply.handle);
+	req = nbd_find_request(nbd, *(struct request **)reply.handle);
 	if (IS_ERR(req)) {
 		result = PTR_ERR(req);
 		if (result != -ENOENT)
 			goto harderror;
 
-		dev_err(disk_to_dev(lo->disk), "Unexpected reply (%p)\n",
+		dev_err(disk_to_dev(nbd->disk), "Unexpected reply (%p)\n",
 			reply.handle);
 		result = -EBADR;
 		goto harderror;
 	}
 
 	if (ntohl(reply.error)) {
-		dev_err(disk_to_dev(lo->disk), "Other side returned error (%d)\n",
+		dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
 			ntohl(reply.error));
 		req->errors++;
 		return req;
 	}
 
 	dprintk(DBG_RX, "%s: request %p: got reply\n",
-			lo->disk->disk_name, req);
+			nbd->disk->disk_name, req);
 	if (nbd_cmd(req) == NBD_CMD_READ) {
 		struct req_iterator iter;
 		struct bio_vec *bvec;
 
 		rq_for_each_segment(bvec, req, iter) {
-			result = sock_recv_bvec(lo, bvec);
+			result = sock_recv_bvec(nbd, bvec);
 			if (result <= 0) {
-				dev_err(disk_to_dev(lo->disk), "Receive data failed (result %d)\n",
+				dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
 					result);
 				req->errors++;
 				return req;
 			}
 			dprintk(DBG_RX, "%s: request %p: got %d bytes data\n",
-				lo->disk->disk_name, req, bvec->bv_len);
+				nbd->disk->disk_name, req, bvec->bv_len);
 		}
 	}
 	return req;
 harderror:
-	lo->harderror = result;
+	nbd->harderror = result;
 	return NULL;
 }
 
@@ -398,48 +398,48 @@ static struct device_attribute pid_attr = {
 	.show = pid_show,
 };
 
-static int nbd_do_it(struct nbd_device *lo)
+static int nbd_do_it(struct nbd_device *nbd)
 {
 	struct request *req;
 	int ret;
 
-	BUG_ON(lo->magic != LO_MAGIC);
+	BUG_ON(nbd->magic != NBD_MAGIC);
 
-	lo->pid = task_pid_nr(current);
-	ret = device_create_file(disk_to_dev(lo->disk), &pid_attr);
+	nbd->pid = task_pid_nr(current);
+	ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
 	if (ret) {
-		dev_err(disk_to_dev(lo->disk), "device_create_file failed!\n");
-		lo->pid = 0;
+		dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
+		nbd->pid = 0;
 		return ret;
 	}
 
-	while ((req = nbd_read_stat(lo)) != NULL)
+	while ((req = nbd_read_stat(nbd)) != NULL)
 		nbd_end_request(req);
 
-	device_remove_file(disk_to_dev(lo->disk), &pid_attr);
-	lo->pid = 0;
+	device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
+	nbd->pid = 0;
 	return 0;
 }
 
-static void nbd_clear_que(struct nbd_device *lo)
+static void nbd_clear_que(struct nbd_device *nbd)
 {
 	struct request *req;
 
-	BUG_ON(lo->magic != LO_MAGIC);
+	BUG_ON(nbd->magic != NBD_MAGIC);
 
 	/*
-	 * Because we have set lo->sock to NULL under the tx_lock, all
+	 * Because we have set nbd->sock to NULL under the tx_lock, all
 	 * modifications to the list must have completed by now.  For
 	 * the same reason, the active_req must be NULL.
 	 *
 	 * As a consequence, we don't need to take the spin lock while
 	 * purging the list here.
 	 */
-	BUG_ON(lo->sock);
-	BUG_ON(lo->active_req);
+	BUG_ON(nbd->sock);
+	BUG_ON(nbd->active_req);
 
-	while (!list_empty(&lo->queue_head)) {
-		req = list_entry(lo->queue_head.next, struct request,
+	while (!list_empty(&nbd->queue_head)) {
+		req = list_entry(nbd->queue_head.next, struct request,
 				 queuelist);
 		list_del_init(&req->queuelist);
 		req->errors++;
@@ -448,7 +448,7 @@ static void nbd_clear_que(struct nbd_device *lo)
 }
 
 
-static void nbd_handle_req(struct nbd_device *lo, struct request *req)
+static void nbd_handle_req(struct nbd_device *nbd, struct request *req)
 {
 	if (req->cmd_type != REQ_TYPE_FS)
 		goto error_out;
@@ -456,8 +456,8 @@ static void nbd_handle_req(struct nbd_device *lo, struct request *req)
 	nbd_cmd(req) = NBD_CMD_READ;
 	if (rq_data_dir(req) == WRITE) {
 		nbd_cmd(req) = NBD_CMD_WRITE;
-		if (lo->flags & NBD_READ_ONLY) {
-			dev_err(disk_to_dev(lo->disk),
+		if (nbd->flags & NBD_READ_ONLY) {
+			dev_err(disk_to_dev(nbd->disk),
 				"Write on read-only\n");
 			goto error_out;
 		}
@@ -465,29 +465,29 @@ static void nbd_handle_req(struct nbd_device *lo, struct request *req)
 
 	req->errors = 0;
 
-	mutex_lock(&lo->tx_lock);
-	if (unlikely(!lo->sock)) {
-		mutex_unlock(&lo->tx_lock);
-		dev_err(disk_to_dev(lo->disk),
+	mutex_lock(&nbd->tx_lock);
+	if (unlikely(!nbd->sock)) {
+		mutex_unlock(&nbd->tx_lock);
+		dev_err(disk_to_dev(nbd->disk),
 			"Attempted send on closed socket\n");
 		goto error_out;
 	}
 
-	lo->active_req = req;
+	nbd->active_req = req;
 
-	if (nbd_send_req(lo, req) != 0) {
-		dev_err(disk_to_dev(lo->disk), "Request send failed\n");
+	if (nbd_send_req(nbd, req) != 0) {
+		dev_err(disk_to_dev(nbd->disk), "Request send failed\n");
 		req->errors++;
 		nbd_end_request(req);
 	} else {
-		spin_lock(&lo->queue_lock);
-		list_add(&req->queuelist, &lo->queue_head);
-		spin_unlock(&lo->queue_lock);
+		spin_lock(&nbd->queue_lock);
+		list_add(&req->queuelist, &nbd->queue_head);
+		spin_unlock(&nbd->queue_lock);
 	}
 
-	lo->active_req = NULL;
-	mutex_unlock(&lo->tx_lock);
-	wake_up_all(&lo->active_wq);
+	nbd->active_req = NULL;
+	mutex_unlock(&nbd->tx_lock);
+	wake_up_all(&nbd->active_wq);
 
 	return;
 
@@ -498,28 +498,28 @@ error_out:
 
 static int nbd_thread(void *data)
 {
-	struct nbd_device *lo = data;
+	struct nbd_device *nbd = data;
 	struct request *req;
 
 	set_user_nice(current, -20);
-	while (!kthread_should_stop() || !list_empty(&lo->waiting_queue)) {
+	while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) {
 		/* wait for something to do */
-		wait_event_interruptible(lo->waiting_wq,
+		wait_event_interruptible(nbd->waiting_wq,
 					 kthread_should_stop() ||
-					 !list_empty(&lo->waiting_queue));
+					 !list_empty(&nbd->waiting_queue));
 
 		/* extract request */
-		if (list_empty(&lo->waiting_queue))
+		if (list_empty(&nbd->waiting_queue))
 			continue;
 
-		spin_lock_irq(&lo->queue_lock);
-		req = list_entry(lo->waiting_queue.next, struct request,
+		spin_lock_irq(&nbd->queue_lock);
+		req = list_entry(nbd->waiting_queue.next, struct request,
 				 queuelist);
 		list_del_init(&req->queuelist);
-		spin_unlock_irq(&lo->queue_lock);
+		spin_unlock_irq(&nbd->queue_lock);
 
 		/* handle request */
-		nbd_handle_req(lo, req);
+		nbd_handle_req(nbd, req);
 	}
 	return 0;
 }
@@ -527,7 +527,7 @@ static int nbd_thread(void *data)
 /*
  * We always wait for result of write, for now. It would be nice to make it optional
  * in future
- * if ((rq_data_dir(req) == WRITE) && (lo->flags & NBD_WRITE_NOCHK))
+ * if ((rq_data_dir(req) == WRITE) && (nbd->flags & NBD_WRITE_NOCHK))
  *   { printk( "Warning: Ignoring result!\n"); nbd_end_request( req ); }
  */
 
@@ -536,19 +536,19 @@ static void do_nbd_request(struct request_queue *q)
 	struct request *req;
 	
 	while ((req = blk_fetch_request(q)) != NULL) {
-		struct nbd_device *lo;
+		struct nbd_device *nbd;
 
 		spin_unlock_irq(q->queue_lock);
 
 		dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%x)\n",
 				req->rq_disk->disk_name, req, req->cmd_type);
 
-		lo = req->rq_disk->private_data;
+		nbd = req->rq_disk->private_data;
 
-		BUG_ON(lo->magic != LO_MAGIC);
+		BUG_ON(nbd->magic != NBD_MAGIC);
 
-		if (unlikely(!lo->sock)) {
-			dev_err(disk_to_dev(lo->disk),
+		if (unlikely(!nbd->sock)) {
+			dev_err(disk_to_dev(nbd->disk),
 				"Attempted send on closed socket\n");
 			req->errors++;
 			nbd_end_request(req);
@@ -556,11 +556,11 @@ static void do_nbd_request(struct request_queue *q)
 			continue;
 		}
 
-		spin_lock_irq(&lo->queue_lock);
-		list_add_tail(&req->queuelist, &lo->waiting_queue);
-		spin_unlock_irq(&lo->queue_lock);
+		spin_lock_irq(&nbd->queue_lock);
+		list_add_tail(&req->queuelist, &nbd->waiting_queue);
+		spin_unlock_irq(&nbd->queue_lock);
 
-		wake_up(&lo->waiting_wq);
+		wake_up(&nbd->waiting_wq);
 
 		spin_lock_irq(q->queue_lock);
 	}
@@ -568,32 +568,32 @@ static void do_nbd_request(struct request_queue *q)
 
 /* Must be called with tx_lock held */
 
-static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
+static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		       unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
 	case NBD_DISCONNECT: {
 		struct request sreq;
 
-		dev_info(disk_to_dev(lo->disk), "NBD_DISCONNECT\n");
+		dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
 
 		blk_rq_init(NULL, &sreq);
 		sreq.cmd_type = REQ_TYPE_SPECIAL;
 		nbd_cmd(&sreq) = NBD_CMD_DISC;
-		if (!lo->sock)
+		if (!nbd->sock)
 			return -EINVAL;
-		nbd_send_req(lo, &sreq);
+		nbd_send_req(nbd, &sreq);
                 return 0;
 	}
  
 	case NBD_CLEAR_SOCK: {
 		struct file *file;
 
-		lo->sock = NULL;
-		file = lo->file;
-		lo->file = NULL;
-		nbd_clear_que(lo);
-		BUG_ON(!list_empty(&lo->queue_head));
+		nbd->sock = NULL;
+		file = nbd->file;
+		nbd->file = NULL;
+		nbd_clear_que(nbd);
+		BUG_ON(!list_empty(&nbd->queue_head));
 		if (file)
 			fput(file);
 		return 0;
@@ -601,14 +601,14 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 
 	case NBD_SET_SOCK: {
 		struct file *file;
-		if (lo->file)
+		if (nbd->file)
 			return -EBUSY;
 		file = fget(arg);
 		if (file) {
 			struct inode *inode = file->f_path.dentry->d_inode;
 			if (S_ISSOCK(inode->i_mode)) {
-				lo->file = file;
-				lo->sock = SOCKET_I(inode);
+				nbd->file = file;
+				nbd->sock = SOCKET_I(inode);
 				if (max_part > 0)
 					bdev->bd_invalidated = 1;
 				return 0;
@@ -620,29 +620,29 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 	}
 
 	case NBD_SET_BLKSIZE:
-		lo->blksize = arg;
-		lo->bytesize &= ~(lo->blksize-1);
-		bdev->bd_inode->i_size = lo->bytesize;
-		set_blocksize(bdev, lo->blksize);
-		set_capacity(lo->disk, lo->bytesize >> 9);
+		nbd->blksize = arg;
+		nbd->bytesize &= ~(nbd->blksize-1);
+		bdev->bd_inode->i_size = nbd->bytesize;
+		set_blocksize(bdev, nbd->blksize);
+		set_capacity(nbd->disk, nbd->bytesize >> 9);
 		return 0;
 
 	case NBD_SET_SIZE:
-		lo->bytesize = arg & ~(lo->blksize-1);
-		bdev->bd_inode->i_size = lo->bytesize;
-		set_blocksize(bdev, lo->blksize);
-		set_capacity(lo->disk, lo->bytesize >> 9);
+		nbd->bytesize = arg & ~(nbd->blksize-1);
+		bdev->bd_inode->i_size = nbd->bytesize;
+		set_blocksize(bdev, nbd->blksize);
+		set_capacity(nbd->disk, nbd->bytesize >> 9);
 		return 0;
 
 	case NBD_SET_TIMEOUT:
-		lo->xmit_timeout = arg * HZ;
+		nbd->xmit_timeout = arg * HZ;
 		return 0;
 
 	case NBD_SET_SIZE_BLOCKS:
-		lo->bytesize = ((u64) arg) * lo->blksize;
-		bdev->bd_inode->i_size = lo->bytesize;
-		set_blocksize(bdev, lo->blksize);
-		set_capacity(lo->disk, lo->bytesize >> 9);
+		nbd->bytesize = ((u64) arg) * nbd->blksize;
+		bdev->bd_inode->i_size = nbd->bytesize;
+		set_blocksize(bdev, nbd->blksize);
+		set_capacity(nbd->disk, nbd->bytesize >> 9);
 		return 0;
 
 	case NBD_DO_IT: {
@@ -650,38 +650,38 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 		struct file *file;
 		int error;
 
-		if (lo->pid)
+		if (nbd->pid)
 			return -EBUSY;
-		if (!lo->file)
+		if (!nbd->file)
 			return -EINVAL;
 
-		mutex_unlock(&lo->tx_lock);
+		mutex_unlock(&nbd->tx_lock);
 
-		thread = kthread_create(nbd_thread, lo, lo->disk->disk_name);
+		thread = kthread_create(nbd_thread, nbd, nbd->disk->disk_name);
 		if (IS_ERR(thread)) {
-			mutex_lock(&lo->tx_lock);
+			mutex_lock(&nbd->tx_lock);
 			return PTR_ERR(thread);
 		}
 		wake_up_process(thread);
-		error = nbd_do_it(lo);
+		error = nbd_do_it(nbd);
 		kthread_stop(thread);
 
-		mutex_lock(&lo->tx_lock);
+		mutex_lock(&nbd->tx_lock);
 		if (error)
 			return error;
-		sock_shutdown(lo, 0);
-		file = lo->file;
-		lo->file = NULL;
-		nbd_clear_que(lo);
-		dev_warn(disk_to_dev(lo->disk), "queue cleared\n");
+		sock_shutdown(nbd, 0);
+		file = nbd->file;
+		nbd->file = NULL;
+		nbd_clear_que(nbd);
+		dev_warn(disk_to_dev(nbd->disk), "queue cleared\n");
 		if (file)
 			fput(file);
-		lo->bytesize = 0;
+		nbd->bytesize = 0;
 		bdev->bd_inode->i_size = 0;
-		set_capacity(lo->disk, 0);
+		set_capacity(nbd->disk, 0);
 		if (max_part > 0)
 			ioctl_by_bdev(bdev, BLKRRPART, 0);
-		return lo->harderror;
+		return nbd->harderror;
 	}
 
 	case NBD_CLEAR_QUE:
@@ -689,14 +689,14 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 		 * This is for compatibility only.  The queue is always cleared
 		 * by NBD_DO_IT or NBD_CLEAR_SOCK.
 		 */
-		BUG_ON(!lo->sock && !list_empty(&lo->queue_head));
+		BUG_ON(!nbd->sock && !list_empty(&nbd->queue_head));
 		return 0;
 
 	case NBD_PRINT_DEBUG:
-		dev_info(disk_to_dev(lo->disk),
+		dev_info(disk_to_dev(nbd->disk),
 			"next = %p, prev = %p, head = %p\n",
-			lo->queue_head.next, lo->queue_head.prev,
-			&lo->queue_head);
+			nbd->queue_head.next, nbd->queue_head.prev,
+			&nbd->queue_head);
 		return 0;
 	}
 	return -ENOTTY;
@@ -705,21 +705,21 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
-	struct nbd_device *lo = bdev->bd_disk->private_data;
+	struct nbd_device *nbd = bdev->bd_disk->private_data;
 	int error;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	BUG_ON(lo->magic != LO_MAGIC);
+	BUG_ON(nbd->magic != NBD_MAGIC);
 
 	/* Anyone capable of this syscall can do *real bad* things */
 	dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n",
-			lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg);
+		nbd->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg);
 
-	mutex_lock(&lo->tx_lock);
-	error = __nbd_ioctl(bdev, lo, cmd, arg);
-	mutex_unlock(&lo->tx_lock);
+	mutex_lock(&nbd->tx_lock);
+	error = __nbd_ioctl(bdev, nbd, cmd, arg);
+	mutex_unlock(&nbd->tx_lock);
 
 	return error;
 }
@@ -805,7 +805,7 @@ static int __init nbd_init(void)
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = nbd_dev[i].disk;
 		nbd_dev[i].file = NULL;
-		nbd_dev[i].magic = LO_MAGIC;
+		nbd_dev[i].magic = NBD_MAGIC;
 		nbd_dev[i].flags = 0;
 		INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
 		spin_lock_init(&nbd_dev[i].queue_lock);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index a6278e7e61a0..013c7a549fb6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -41,19 +41,35 @@
 
 #include "rbd_types.h"
 
-#define DRV_NAME "rbd"
-#define DRV_NAME_LONG "rbd (rados block device)"
+/*
+ * The basic unit of block I/O is a sector.  It is interpreted in a
+ * number of contexts in Linux (blk, bio, genhd), but the default is
+ * universally 512 bytes.  These symbols are just slightly more
+ * meaningful than the bare numbers they represent.
+ */
+#define	SECTOR_SHIFT	9
+#define	SECTOR_SIZE	(1ULL << SECTOR_SHIFT)
+
+#define RBD_DRV_NAME "rbd"
+#define RBD_DRV_NAME_LONG "rbd (rados block device)"
 
 #define RBD_MINORS_PER_MAJOR	256		/* max minors per blkdev */
 
-#define RBD_MAX_MD_NAME_LEN	(96 + sizeof(RBD_SUFFIX))
+#define RBD_MAX_MD_NAME_LEN	(RBD_MAX_OBJ_NAME_LEN + sizeof(RBD_SUFFIX))
 #define RBD_MAX_POOL_NAME_LEN	64
 #define RBD_MAX_SNAP_NAME_LEN	32
 #define RBD_MAX_OPT_LEN		1024
 
 #define RBD_SNAP_HEAD_NAME	"-"
 
+/*
+ * An RBD device name will be "rbd#", where the "rbd" comes from
+ * RBD_DRV_NAME above, and # is a unique integer identifier.
+ * MAX_INT_FORMAT_WIDTH is used in ensuring DEV_NAME_LEN is big
+ * enough to hold all possible device names.
+ */
 #define DEV_NAME_LEN		32
+#define MAX_INT_FORMAT_WIDTH	((5 * sizeof (int)) / 2 + 1)
 
 #define RBD_NOTIFY_TIMEOUT_DEFAULT 10
 
@@ -66,7 +82,6 @@ struct rbd_image_header {
 	__u8 obj_order;
 	__u8 crypt_type;
 	__u8 comp_type;
-	struct rw_semaphore snap_rwsem;
 	struct ceph_snap_context *snapc;
 	size_t snap_names_len;
 	u64 snap_seq;
@@ -83,7 +98,7 @@ struct rbd_options {
 };
 
 /*
- * an instance of the client.  multiple devices may share a client.
+ * an instance of the client.  multiple devices may share an rbd client.
  */
 struct rbd_client {
 	struct ceph_client	*client;
@@ -92,20 +107,9 @@ struct rbd_client {
 	struct list_head	node;
 };
 
-struct rbd_req_coll;
-
 /*
- * a single io request
+ * a request completion status
  */
-struct rbd_request {
-	struct request		*rq;		/* blk layer request */
-	struct bio		*bio;		/* cloned bio */
-	struct page		**pages;	/* list of used pages */
-	u64			len;
-	int			coll_index;
-	struct rbd_req_coll	*coll;
-};
-
 struct rbd_req_status {
 	int done;
 	int rc;
@@ -122,6 +126,18 @@ struct rbd_req_coll {
 	struct rbd_req_status	status[0];
 };
 
+/*
+ * a single io request
+ */
+struct rbd_request {
+	struct request		*rq;		/* blk layer request */
+	struct bio		*bio;		/* cloned bio */
+	struct page		**pages;	/* list of used pages */
+	u64			len;
+	int			coll_index;
+	struct rbd_req_coll	*coll;
+};
+
 struct rbd_snap {
 	struct	device		dev;
 	const char		*name;
@@ -140,7 +156,6 @@ struct rbd_device {
 	struct gendisk		*disk;		/* blkdev's gendisk and rq */
 	struct request_queue	*q;
 
-	struct ceph_client	*client;
 	struct rbd_client	*rbd_client;
 
 	char			name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */
@@ -157,6 +172,8 @@ struct rbd_device {
 	struct ceph_osd_event   *watch_event;
 	struct ceph_osd_request *watch_request;
 
+	/* protects updating the header */
+	struct rw_semaphore     header_rwsem;
 	char                    snap_name[RBD_MAX_SNAP_NAME_LEN];
 	u32 cur_snap;	/* index+1 of current snapshot within snap context
 			   0 - for the head */
@@ -171,15 +188,13 @@ struct rbd_device {
 	struct device		dev;
 };
 
-static struct bus_type rbd_bus_type = {
-	.name		= "rbd",
-};
-
-static spinlock_t node_lock;      /* protects client get/put */
-
 static DEFINE_MUTEX(ctl_mutex);	  /* Serialize open/close/setup/teardown */
+
 static LIST_HEAD(rbd_dev_list);    /* devices */
-static LIST_HEAD(rbd_client_list);      /* clients */
+static DEFINE_SPINLOCK(rbd_dev_list_lock);
+
+static LIST_HEAD(rbd_client_list);		/* clients */
+static DEFINE_SPINLOCK(rbd_client_list_lock);
 
 static int __rbd_init_snaps_header(struct rbd_device *rbd_dev);
 static void rbd_dev_release(struct device *dev);
@@ -190,12 +205,32 @@ static ssize_t rbd_snap_add(struct device *dev,
 static void __rbd_remove_snap_dev(struct rbd_device *rbd_dev,
 				  struct rbd_snap *snap);
 
+static ssize_t rbd_add(struct bus_type *bus, const char *buf,
+		       size_t count);
+static ssize_t rbd_remove(struct bus_type *bus, const char *buf,
+			  size_t count);
 
-static struct rbd_device *dev_to_rbd(struct device *dev)
+static struct bus_attribute rbd_bus_attrs[] = {
+	__ATTR(add, S_IWUSR, NULL, rbd_add),
+	__ATTR(remove, S_IWUSR, NULL, rbd_remove),
+	__ATTR_NULL
+};
+
+static struct bus_type rbd_bus_type = {
+	.name		= "rbd",
+	.bus_attrs	= rbd_bus_attrs,
+};
+
+static void rbd_root_dev_release(struct device *dev)
 {
-	return container_of(dev, struct rbd_device, dev);
 }
 
+static struct device rbd_root_dev = {
+	.init_name =    "rbd",
+	.release =      rbd_root_dev_release,
+};
+
+
 static struct device *rbd_get_dev(struct rbd_device *rbd_dev)
 {
 	return get_device(&rbd_dev->dev);
@@ -210,8 +245,7 @@ static int __rbd_update_snaps(struct rbd_device *rbd_dev);
 
 static int rbd_open(struct block_device *bdev, fmode_t mode)
 {
-	struct gendisk *disk = bdev->bd_disk;
-	struct rbd_device *rbd_dev = disk->private_data;
+	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
 
 	rbd_get_dev(rbd_dev);
 
@@ -256,9 +290,11 @@ static struct rbd_client *rbd_client_create(struct ceph_options *opt,
 	kref_init(&rbdc->kref);
 	INIT_LIST_HEAD(&rbdc->node);
 
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
 	rbdc->client = ceph_create_client(opt, rbdc, 0, 0);
 	if (IS_ERR(rbdc->client))
-		goto out_rbdc;
+		goto out_mutex;
 	opt = NULL; /* Now rbdc->client is responsible for opt */
 
 	ret = ceph_open_session(rbdc->client);
@@ -267,16 +303,19 @@ static struct rbd_client *rbd_client_create(struct ceph_options *opt,
 
 	rbdc->rbd_opts = rbd_opts;
 
-	spin_lock(&node_lock);
+	spin_lock(&rbd_client_list_lock);
 	list_add_tail(&rbdc->node, &rbd_client_list);
-	spin_unlock(&node_lock);
+	spin_unlock(&rbd_client_list_lock);
+
+	mutex_unlock(&ctl_mutex);
 
 	dout("rbd_client_create created %p\n", rbdc);
 	return rbdc;
 
 out_err:
 	ceph_destroy_client(rbdc->client);
-out_rbdc:
+out_mutex:
+	mutex_unlock(&ctl_mutex);
 	kfree(rbdc);
 out_opt:
 	if (opt)
@@ -324,7 +363,7 @@ static int parse_rbd_opts_token(char *c, void *private)
 	substring_t argstr[MAX_OPT_ARGS];
 	int token, intval, ret;
 
-	token = match_token((char *)c, rbdopt_tokens, argstr);
+	token = match_token(c, rbdopt_tokens, argstr);
 	if (token < 0)
 		return -EINVAL;
 
@@ -357,58 +396,54 @@ static int parse_rbd_opts_token(char *c, void *private)
  * Get a ceph client with specific addr and configuration, if one does
  * not exist create it.
  */
-static int rbd_get_client(struct rbd_device *rbd_dev, const char *mon_addr,
-			  char *options)
+static struct rbd_client *rbd_get_client(const char *mon_addr,
+					 size_t mon_addr_len,
+					 char *options)
 {
 	struct rbd_client *rbdc;
 	struct ceph_options *opt;
-	int ret;
 	struct rbd_options *rbd_opts;
 
 	rbd_opts = kzalloc(sizeof(*rbd_opts), GFP_KERNEL);
 	if (!rbd_opts)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	rbd_opts->notify_timeout = RBD_NOTIFY_TIMEOUT_DEFAULT;
 
-	ret = ceph_parse_options(&opt, options, mon_addr,
-				 mon_addr + strlen(mon_addr), parse_rbd_opts_token, rbd_opts);
-	if (ret < 0)
-		goto done_err;
+	opt = ceph_parse_options(options, mon_addr,
+				mon_addr + mon_addr_len,
+				parse_rbd_opts_token, rbd_opts);
+	if (IS_ERR(opt)) {
+		kfree(rbd_opts);
+		return ERR_CAST(opt);
+	}
 
-	spin_lock(&node_lock);
+	spin_lock(&rbd_client_list_lock);
 	rbdc = __rbd_client_find(opt);
 	if (rbdc) {
+		/* using an existing client */
+		kref_get(&rbdc->kref);
+		spin_unlock(&rbd_client_list_lock);
+
 		ceph_destroy_options(opt);
 		kfree(rbd_opts);
 
-		/* using an existing client */
-		kref_get(&rbdc->kref);
-		rbd_dev->rbd_client = rbdc;
-		rbd_dev->client = rbdc->client;
-		spin_unlock(&node_lock);
-		return 0;
+		return rbdc;
 	}
-	spin_unlock(&node_lock);
+	spin_unlock(&rbd_client_list_lock);
 
 	rbdc = rbd_client_create(opt, rbd_opts);
-	if (IS_ERR(rbdc)) {
-		ret = PTR_ERR(rbdc);
-		goto done_err;
-	}
 
-	rbd_dev->rbd_client = rbdc;
-	rbd_dev->client = rbdc->client;
-	return 0;
-done_err:
-	kfree(rbd_opts);
-	return ret;
+	if (IS_ERR(rbdc))
+		kfree(rbd_opts);
+
+	return rbdc;
 }
 
 /*
  * Destroy ceph client
  *
- * Caller must hold node_lock.
+ * Caller must hold rbd_client_list_lock.
  */
 static void rbd_client_release(struct kref *kref)
 {
@@ -428,11 +463,10 @@ static void rbd_client_release(struct kref *kref)
  */
 static void rbd_put_client(struct rbd_device *rbd_dev)
 {
-	spin_lock(&node_lock);
+	spin_lock(&rbd_client_list_lock);
 	kref_put(&rbd_dev->rbd_client->kref, rbd_client_release);
-	spin_unlock(&node_lock);
+	spin_unlock(&rbd_client_list_lock);
 	rbd_dev->rbd_client = NULL;
-	rbd_dev->client = NULL;
 }
 
 /*
@@ -457,21 +491,19 @@ static int rbd_header_from_disk(struct rbd_image_header *header,
 				 gfp_t gfp_flags)
 {
 	int i;
-	u32 snap_count = le32_to_cpu(ondisk->snap_count);
-	int ret = -ENOMEM;
+	u32 snap_count;
 
-	if (memcmp(ondisk, RBD_HEADER_TEXT, sizeof(RBD_HEADER_TEXT))) {
+	if (memcmp(ondisk, RBD_HEADER_TEXT, sizeof(RBD_HEADER_TEXT)))
 		return -ENXIO;
-	}
 
-	init_rwsem(&header->snap_rwsem);
-	header->snap_names_len = le64_to_cpu(ondisk->snap_names_len);
+	snap_count = le32_to_cpu(ondisk->snap_count);
 	header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
-				snap_count *
-				 sizeof(struct rbd_image_snap_ondisk),
+				snap_count * sizeof (*ondisk),
 				gfp_flags);
 	if (!header->snapc)
 		return -ENOMEM;
+
+	header->snap_names_len = le64_to_cpu(ondisk->snap_names_len);
 	if (snap_count) {
 		header->snap_names = kmalloc(header->snap_names_len,
 					     GFP_KERNEL);
@@ -498,8 +530,7 @@ static int rbd_header_from_disk(struct rbd_image_header *header,
 	header->snapc->num_snaps = snap_count;
 	header->total_snaps = snap_count;
 
-	if (snap_count &&
-	    allocated_snaps == snap_count) {
+	if (snap_count && allocated_snaps == snap_count) {
 		for (i = 0; i < snap_count; i++) {
 			header->snapc->snaps[i] =
 				le64_to_cpu(ondisk->snaps[i].id);
@@ -518,7 +549,7 @@ err_names:
 	kfree(header->snap_names);
 err_snapc:
 	kfree(header->snapc);
-	return ret;
+	return -ENOMEM;
 }
 
 static int snap_index(struct rbd_image_header *header, int snap_num)
@@ -542,35 +573,34 @@ static int snap_by_name(struct rbd_image_header *header, const char *snap_name,
 	int i;
 	char *p = header->snap_names;
 
-	for (i = 0; i < header->total_snaps; i++, p += strlen(p) + 1) {
-		if (strcmp(snap_name, p) == 0)
-			break;
-	}
-	if (i == header->total_snaps)
-		return -ENOENT;
-	if (seq)
-		*seq = header->snapc->snaps[i];
+	for (i = 0; i < header->total_snaps; i++) {
+		if (!strcmp(snap_name, p)) {
 
-	if (size)
-		*size = header->snap_sizes[i];
+			/* Found it.  Pass back its id and/or size */
 
-	return i;
+			if (seq)
+				*seq = header->snapc->snaps[i];
+			if (size)
+				*size = header->snap_sizes[i];
+			return i;
+		}
+		p += strlen(p) + 1;	/* Skip ahead to the next name */
+	}
+	return -ENOENT;
 }
 
-static int rbd_header_set_snap(struct rbd_device *dev,
-			       const char *snap_name,
-			       u64 *size)
+static int rbd_header_set_snap(struct rbd_device *dev, u64 *size)
 {
 	struct rbd_image_header *header = &dev->header;
 	struct ceph_snap_context *snapc = header->snapc;
 	int ret = -ENOENT;
 
-	down_write(&header->snap_rwsem);
+	BUILD_BUG_ON(sizeof (dev->snap_name) < sizeof (RBD_SNAP_HEAD_NAME));
 
-	if (!snap_name ||
-	    !*snap_name ||
-	    strcmp(snap_name, "-") == 0 ||
-	    strcmp(snap_name, RBD_SNAP_HEAD_NAME) == 0) {
+	down_write(&dev->header_rwsem);
+
+	if (!memcmp(dev->snap_name, RBD_SNAP_HEAD_NAME,
+		    sizeof (RBD_SNAP_HEAD_NAME))) {
 		if (header->total_snaps)
 			snapc->seq = header->snap_seq;
 		else
@@ -580,7 +610,7 @@ static int rbd_header_set_snap(struct rbd_device *dev,
 		if (size)
 			*size = header->image_size;
 	} else {
-		ret = snap_by_name(header, snap_name, &snapc->seq, size);
+		ret = snap_by_name(header, dev->snap_name, &snapc->seq, size);
 		if (ret < 0)
 			goto done;
 
@@ -590,7 +620,7 @@ static int rbd_header_set_snap(struct rbd_device *dev,
 
 	ret = 0;
 done:
-	up_write(&header->snap_rwsem);
+	up_write(&dev->header_rwsem);
 	return ret;
 }
 
@@ -717,7 +747,7 @@ static struct bio *bio_chain_clone(struct bio **old, struct bio **next,
 
 			/* split the bio. We'll release it either in the next
 			   call, or it will have to be released outside */
-			bp = bio_split(old_chain, (len - total) / 512ULL);
+			bp = bio_split(old_chain, (len - total) / SECTOR_SIZE);
 			if (!bp)
 				goto err_out;
 
@@ -857,7 +887,7 @@ static int rbd_do_request(struct request *rq,
 	struct timespec mtime = CURRENT_TIME;
 	struct rbd_request *req_data;
 	struct ceph_osd_request_head *reqhead;
-	struct rbd_image_header *header = &dev->header;
+	struct ceph_osd_client *osdc;
 
 	req_data = kzalloc(sizeof(*req_data), GFP_NOIO);
 	if (!req_data) {
@@ -874,15 +904,13 @@ static int rbd_do_request(struct request *rq,
 
 	dout("rbd_do_request obj=%s ofs=%lld len=%lld\n", obj, len, ofs);
 
-	down_read(&header->snap_rwsem);
+	down_read(&dev->header_rwsem);
 
-	req = ceph_osdc_alloc_request(&dev->client->osdc, flags,
-				      snapc,
-				      ops,
-				      false,
-				      GFP_NOIO, pages, bio);
+	osdc = &dev->rbd_client->client->osdc;
+	req = ceph_osdc_alloc_request(osdc, flags, snapc, ops,
+					false, GFP_NOIO, pages, bio);
 	if (!req) {
-		up_read(&header->snap_rwsem);
+		up_read(&dev->header_rwsem);
 		ret = -ENOMEM;
 		goto done_pages;
 	}
@@ -909,27 +937,27 @@ static int rbd_do_request(struct request *rq,
 	layout->fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
 	layout->fl_pg_preferred = cpu_to_le32(-1);
 	layout->fl_pg_pool = cpu_to_le32(dev->poolid);
-	ceph_calc_raw_layout(&dev->client->osdc, layout, snapid,
-			     ofs, &len, &bno, req, ops);
+	ceph_calc_raw_layout(osdc, layout, snapid, ofs, &len, &bno,
+				req, ops);
 
 	ceph_osdc_build_request(req, ofs, &len,
 				ops,
 				snapc,
 				&mtime,
 				req->r_oid, req->r_oid_len);
-	up_read(&header->snap_rwsem);
+	up_read(&dev->header_rwsem);
 
 	if (linger_req) {
-		ceph_osdc_set_request_linger(&dev->client->osdc, req);
+		ceph_osdc_set_request_linger(osdc, req);
 		*linger_req = req;
 	}
 
-	ret = ceph_osdc_start_request(&dev->client->osdc, req, false);
+	ret = ceph_osdc_start_request(osdc, req, false);
 	if (ret < 0)
 		goto done_err;
 
 	if (!rbd_cb) {
-		ret = ceph_osdc_wait_request(&dev->client->osdc, req);
+		ret = ceph_osdc_wait_request(osdc, req);
 		if (ver)
 			*ver = le64_to_cpu(req->r_reassert_version.version);
 		dout("reassert_ver=%lld\n",
@@ -1213,8 +1241,8 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 	rc = __rbd_update_snaps(dev);
 	mutex_unlock(&ctl_mutex);
 	if (rc)
-		pr_warning(DRV_NAME "%d got notification but failed to update"
-			   " snaps: %d\n", dev->major, rc);
+		pr_warning(RBD_DRV_NAME "%d got notification but failed to "
+			   " update snaps: %d\n", dev->major, rc);
 
 	rbd_req_sync_notify_ack(dev, ver, notify_id, dev->obj_md_name);
 }
@@ -1227,7 +1255,7 @@ static int rbd_req_sync_watch(struct rbd_device *dev,
 			      u64 ver)
 {
 	struct ceph_osd_req_op *ops;
-	struct ceph_osd_client *osdc = &dev->client->osdc;
+	struct ceph_osd_client *osdc = &dev->rbd_client->client->osdc;
 
 	int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_WATCH, 0);
 	if (ret < 0)
@@ -1314,7 +1342,7 @@ static int rbd_req_sync_notify(struct rbd_device *dev,
 		          const char *obj)
 {
 	struct ceph_osd_req_op *ops;
-	struct ceph_osd_client *osdc = &dev->client->osdc;
+	struct ceph_osd_client *osdc = &dev->rbd_client->client->osdc;
 	struct ceph_osd_event *event;
 	struct rbd_notify_info info;
 	int payload_len = sizeof(u32) + sizeof(u32);
@@ -1421,9 +1449,7 @@ static void rbd_rq_fn(struct request_queue *q)
 	struct request *rq;
 	struct bio_pair *bp = NULL;
 
-	rq = blk_fetch_request(q);
-
-	while (1) {
+	while ((rq = blk_fetch_request(q))) {
 		struct bio *bio;
 		struct bio *rq_bio, *next_bio = NULL;
 		bool do_write;
@@ -1441,32 +1467,32 @@ static void rbd_rq_fn(struct request_queue *q)
 		/* filter out block requests we don't understand */
 		if ((rq->cmd_type != REQ_TYPE_FS)) {
 			__blk_end_request_all(rq, 0);
-			goto next;
+			continue;
 		}
 
 		/* deduce our operation (read, write) */
 		do_write = (rq_data_dir(rq) == WRITE);
 
 		size = blk_rq_bytes(rq);
-		ofs = blk_rq_pos(rq) * 512ULL;
+		ofs = blk_rq_pos(rq) * SECTOR_SIZE;
 		rq_bio = rq->bio;
 		if (do_write && rbd_dev->read_only) {
 			__blk_end_request_all(rq, -EROFS);
-			goto next;
+			continue;
 		}
 
 		spin_unlock_irq(q->queue_lock);
 
 		dout("%s 0x%x bytes at 0x%llx\n",
 		     do_write ? "write" : "read",
-		     size, blk_rq_pos(rq) * 512ULL);
+		     size, blk_rq_pos(rq) * SECTOR_SIZE);
 
 		num_segs = rbd_get_num_segments(&rbd_dev->header, ofs, size);
 		coll = rbd_alloc_coll(num_segs);
 		if (!coll) {
 			spin_lock_irq(q->queue_lock);
 			__blk_end_request_all(rq, -ENOMEM);
-			goto next;
+			continue;
 		}
 
 		do {
@@ -1512,8 +1538,6 @@ next_seg:
 		if (bp)
 			bio_pair_release(bp);
 		spin_lock_irq(q->queue_lock);
-next:
-		rq = blk_fetch_request(q);
 	}
 }
 
@@ -1526,13 +1550,17 @@ static int rbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
 			  struct bio_vec *bvec)
 {
 	struct rbd_device *rbd_dev = q->queuedata;
-	unsigned int chunk_sectors = 1 << (rbd_dev->header.obj_order - 9);
-	sector_t sector = bmd->bi_sector + get_start_sect(bmd->bi_bdev);
-	unsigned int bio_sectors = bmd->bi_size >> 9;
+	unsigned int chunk_sectors;
+	sector_t sector;
+	unsigned int bio_sectors;
 	int max;
 
+	chunk_sectors = 1 << (rbd_dev->header.obj_order - SECTOR_SHIFT);
+	sector = bmd->bi_sector + get_start_sect(bmd->bi_bdev);
+	bio_sectors = bmd->bi_size >> SECTOR_SHIFT;
+
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1))
-				 + bio_sectors)) << 9;
+				 + bio_sectors)) << SECTOR_SHIFT;
 	if (max < 0)
 		max = 0; /* bio_add cannot handle a negative return */
 	if (max <= bvec->bv_len && bio_sectors == 0)
@@ -1565,15 +1593,16 @@ static int rbd_read_header(struct rbd_device *rbd_dev,
 	ssize_t rc;
 	struct rbd_image_header_ondisk *dh;
 	int snap_count = 0;
-	u64 snap_names_len = 0;
 	u64 ver;
+	size_t len;
 
+	/*
+	 * First reads the fixed-size header to determine the number
+	 * of snapshots, then re-reads it, along with all snapshot
+	 * records as well as their stored names.
+	 */
+	len = sizeof (*dh);
 	while (1) {
-		int len = sizeof(*dh) +
-			  snap_count * sizeof(struct rbd_image_snap_ondisk) +
-			  snap_names_len;
-
-		rc = -ENOMEM;
 		dh = kmalloc(len, GFP_KERNEL);
 		if (!dh)
 			return -ENOMEM;
@@ -1588,21 +1617,22 @@ static int rbd_read_header(struct rbd_device *rbd_dev,
 
 		rc = rbd_header_from_disk(header, dh, snap_count, GFP_KERNEL);
 		if (rc < 0) {
-			if (rc == -ENXIO) {
+			if (rc == -ENXIO)
 				pr_warning("unrecognized header format"
 					   " for image %s", rbd_dev->obj);
-			}
 			goto out_dh;
 		}
 
-		if (snap_count != header->total_snaps) {
-			snap_count = header->total_snaps;
-			snap_names_len = header->snap_names_len;
-			rbd_header_free(header);
-			kfree(dh);
-			continue;
-		}
-		break;
+		if (snap_count == header->total_snaps)
+			break;
+
+		snap_count = header->total_snaps;
+		len = sizeof (*dh) +
+			snap_count * sizeof(struct rbd_image_snap_ondisk) +
+			header->snap_names_len;
+
+		rbd_header_free(header);
+		kfree(dh);
 	}
 	header->obj_version = ver;
 
@@ -1623,13 +1653,14 @@ static int rbd_header_add_snap(struct rbd_device *dev,
 	int ret;
 	void *data, *p, *e;
 	u64 ver;
+	struct ceph_mon_client *monc;
 
 	/* we should create a snapshot only if we're pointing at the head */
 	if (dev->cur_snap)
 		return -EINVAL;
 
-	ret = ceph_monc_create_snapid(&dev->client->monc, dev->poolid,
-				      &new_snapid);
+	monc = &dev->rbd_client->client->monc;
+	ret = ceph_monc_create_snapid(monc, dev->poolid, &new_snapid);
 	dout("created snapid=%lld\n", new_snapid);
 	if (ret < 0)
 		return ret;
@@ -1684,9 +1715,9 @@ static int __rbd_update_snaps(struct rbd_device *rbd_dev)
 		return ret;
 
 	/* resized? */
-	set_capacity(rbd_dev->disk, h.image_size / 512ULL);
+	set_capacity(rbd_dev->disk, h.image_size / SECTOR_SIZE);
 
-	down_write(&rbd_dev->header.snap_rwsem);
+	down_write(&rbd_dev->header_rwsem);
 
 	snap_seq = rbd_dev->header.snapc->seq;
 	if (rbd_dev->header.total_snaps &&
@@ -1711,7 +1742,7 @@ static int __rbd_update_snaps(struct rbd_device *rbd_dev)
 
 	ret = __rbd_init_snaps_header(rbd_dev);
 
-	up_write(&rbd_dev->header.snap_rwsem);
+	up_write(&rbd_dev->header_rwsem);
 
 	return ret;
 }
@@ -1721,6 +1752,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	struct gendisk *disk;
 	struct request_queue *q;
 	int rc;
+	u64 segment_size;
 	u64 total_size = 0;
 
 	/* contact OSD, request size info about the object being mapped */
@@ -1733,7 +1765,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	if (rc)
 		return rc;
 
-	rc = rbd_header_set_snap(rbd_dev, rbd_dev->snap_name, &total_size);
+	rc = rbd_header_set_snap(rbd_dev, &total_size);
 	if (rc)
 		return rc;
 
@@ -1743,7 +1775,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	if (!disk)
 		goto out;
 
-	snprintf(disk->disk_name, sizeof(disk->disk_name), DRV_NAME "%d",
+	snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d",
 		 rbd_dev->id);
 	disk->major = rbd_dev->major;
 	disk->first_minor = 0;
@@ -1756,11 +1788,15 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	if (!q)
 		goto out_disk;
 
+	/* We use the default size, but let's be explicit about it. */
+	blk_queue_physical_block_size(q, SECTOR_SIZE);
+
 	/* set io sizes to object size */
-	blk_queue_max_hw_sectors(q, rbd_obj_bytes(&rbd_dev->header) / 512ULL);
-	blk_queue_max_segment_size(q, rbd_obj_bytes(&rbd_dev->header));
-	blk_queue_io_min(q, rbd_obj_bytes(&rbd_dev->header));
-	blk_queue_io_opt(q, rbd_obj_bytes(&rbd_dev->header));
+	segment_size = rbd_obj_bytes(&rbd_dev->header);
+	blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+	blk_queue_max_segment_size(q, segment_size);
+	blk_queue_io_min(q, segment_size);
+	blk_queue_io_opt(q, segment_size);
 
 	blk_queue_merge_bvec(q, rbd_merge_bvec);
 	disk->queue = q;
@@ -1771,7 +1807,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	rbd_dev->q = q;
 
 	/* finally, announce the disk to the world */
-	set_capacity(disk, total_size / 512ULL);
+	set_capacity(disk, total_size / SECTOR_SIZE);
 	add_disk(disk);
 
 	pr_info("%s: added with size 0x%llx\n",
@@ -1788,10 +1824,15 @@ out:
   sysfs
 */
 
+static struct rbd_device *dev_to_rbd_dev(struct device *dev)
+{
+	return container_of(dev, struct rbd_device, dev);
+}
+
 static ssize_t rbd_size_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	struct rbd_device *rbd_dev = dev_to_rbd(dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
 	return sprintf(buf, "%llu\n", (unsigned long long)rbd_dev->header.image_size);
 }
@@ -1799,7 +1840,7 @@ static ssize_t rbd_size_show(struct device *dev,
 static ssize_t rbd_major_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
-	struct rbd_device *rbd_dev = dev_to_rbd(dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
 	return sprintf(buf, "%d\n", rbd_dev->major);
 }
@@ -1807,15 +1848,16 @@ static ssize_t rbd_major_show(struct device *dev,
 static ssize_t rbd_client_id_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	struct rbd_device *rbd_dev = dev_to_rbd(dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
-	return sprintf(buf, "client%lld\n", ceph_client_id(rbd_dev->client));
+	return sprintf(buf, "client%lld\n",
+			ceph_client_id(rbd_dev->rbd_client->client));
 }
 
 static ssize_t rbd_pool_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	struct rbd_device *rbd_dev = dev_to_rbd(dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
 	return sprintf(buf, "%s\n", rbd_dev->pool_name);
 }
@@ -1823,7 +1865,7 @@ static ssize_t rbd_pool_show(struct device *dev,
 static ssize_t rbd_name_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	struct rbd_device *rbd_dev = dev_to_rbd(dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
 	return sprintf(buf, "%s\n", rbd_dev->obj);
 }
@@ -1832,7 +1874,7 @@ static ssize_t rbd_snap_show(struct device *dev,
 			     struct device_attribute *attr,
 			     char *buf)
 {
-	struct rbd_device *rbd_dev = dev_to_rbd(dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
 	return sprintf(buf, "%s\n", rbd_dev->snap_name);
 }
@@ -1842,7 +1884,7 @@ static ssize_t rbd_image_refresh(struct device *dev,
 				 const char *buf,
 				 size_t size)
 {
-	struct rbd_device *rbd_dev = dev_to_rbd(dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 	int rc;
 	int ret = size;
 
@@ -1907,7 +1949,7 @@ static ssize_t rbd_snap_size_show(struct device *dev,
 {
 	struct rbd_snap *snap = container_of(dev, struct rbd_snap, dev);
 
-	return sprintf(buf, "%lld\n", (long long)snap->size);
+	return sprintf(buf, "%zd\n", snap->size);
 }
 
 static ssize_t rbd_snap_id_show(struct device *dev,
@@ -1916,7 +1958,7 @@ static ssize_t rbd_snap_id_show(struct device *dev,
 {
 	struct rbd_snap *snap = container_of(dev, struct rbd_snap, dev);
 
-	return sprintf(buf, "%lld\n", (long long)snap->id);
+	return sprintf(buf, "%llu\n", (unsigned long long) snap->id);
 }
 
 static DEVICE_ATTR(snap_size, S_IRUGO, rbd_snap_size_show, NULL);
@@ -2088,19 +2130,9 @@ static int __rbd_init_snaps_header(struct rbd_device *rbd_dev)
 	return 0;
 }
 
-
-static void rbd_root_dev_release(struct device *dev)
-{
-}
-
-static struct device rbd_root_dev = {
-	.init_name =    "rbd",
-	.release =      rbd_root_dev_release,
-};
-
 static int rbd_bus_add_dev(struct rbd_device *rbd_dev)
 {
-	int ret = -ENOMEM;
+	int ret;
 	struct device *dev;
 	struct rbd_snap *snap;
 
@@ -2114,7 +2146,7 @@ static int rbd_bus_add_dev(struct rbd_device *rbd_dev)
 	dev_set_name(dev, "%d", rbd_dev->id);
 	ret = device_register(dev);
 	if (ret < 0)
-		goto done_free;
+		goto out;
 
 	list_for_each_entry(snap, &rbd_dev->snaps, node) {
 		ret = rbd_register_snap_dev(rbd_dev, snap,
@@ -2122,10 +2154,7 @@ static int rbd_bus_add_dev(struct rbd_device *rbd_dev)
 		if (ret < 0)
 			break;
 	}
-
-	mutex_unlock(&ctl_mutex);
-	return 0;
-done_free:
+out:
 	mutex_unlock(&ctl_mutex);
 	return ret;
 }
@@ -2154,104 +2183,250 @@ static int rbd_init_watch_dev(struct rbd_device *rbd_dev)
 	return ret;
 }
 
+static atomic64_t rbd_id_max = ATOMIC64_INIT(0);
+
+/*
+ * Get a unique rbd identifier for the given new rbd_dev, and add
+ * the rbd_dev to the global list.  The minimum rbd id is 1.
+ */
+static void rbd_id_get(struct rbd_device *rbd_dev)
+{
+	rbd_dev->id = atomic64_inc_return(&rbd_id_max);
+
+	spin_lock(&rbd_dev_list_lock);
+	list_add_tail(&rbd_dev->node, &rbd_dev_list);
+	spin_unlock(&rbd_dev_list_lock);
+}
+
+/*
+ * Remove an rbd_dev from the global list, and record that its
+ * identifier is no longer in use.
+ */
+static void rbd_id_put(struct rbd_device *rbd_dev)
+{
+	struct list_head *tmp;
+	int rbd_id = rbd_dev->id;
+	int max_id;
+
+	BUG_ON(rbd_id < 1);
+
+	spin_lock(&rbd_dev_list_lock);
+	list_del_init(&rbd_dev->node);
+
+	/*
+	 * If the id being "put" is not the current maximum, there
+	 * is nothing special we need to do.
+	 */
+	if (rbd_id != atomic64_read(&rbd_id_max)) {
+		spin_unlock(&rbd_dev_list_lock);
+		return;
+	}
+
+	/*
+	 * We need to update the current maximum id.  Search the
+	 * list to find out what it is.  We're more likely to find
+	 * the maximum at the end, so search the list backward.
+	 */
+	max_id = 0;
+	list_for_each_prev(tmp, &rbd_dev_list) {
+		struct rbd_device *rbd_dev;
+
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		if (rbd_id > max_id)
+			max_id = rbd_id;
+	}
+	spin_unlock(&rbd_dev_list_lock);
+
+	/*
+	 * The max id could have been updated by rbd_id_get(), in
+	 * which case it now accurately reflects the new maximum.
+	 * Be careful not to overwrite the maximum value in that
+	 * case.
+	 */
+	atomic64_cmpxchg(&rbd_id_max, rbd_id, max_id);
+}
+
+/*
+ * Skips over white space at *buf, and updates *buf to point to the
+ * first found non-space character (if any). Returns the length of
+ * the token (string of non-white space characters) found.  Note
+ * that *buf must be terminated with '\0'.
+ */
+static inline size_t next_token(const char **buf)
+{
+        /*
+        * These are the characters that produce nonzero for
+        * isspace() in the "C" and "POSIX" locales.
+        */
+        const char *spaces = " \f\n\r\t\v";
+
+        *buf += strspn(*buf, spaces);	/* Find start of token */
+
+	return strcspn(*buf, spaces);   /* Return token length */
+}
+
+/*
+ * Finds the next token in *buf, and if the provided token buffer is
+ * big enough, copies the found token into it.  The result, if
+ * copied, is guaranteed to be terminated with '\0'.  Note that *buf
+ * must be terminated with '\0' on entry.
+ *
+ * Returns the length of the token found (not including the '\0').
+ * Return value will be 0 if no token is found, and it will be >=
+ * token_size if the token would not fit.
+ *
+ * The *buf pointer will be updated to point beyond the end of the
+ * found token.  Note that this occurs even if the token buffer is
+ * too small to hold it.
+ */
+static inline size_t copy_token(const char **buf,
+				char *token,
+				size_t token_size)
+{
+        size_t len;
+
+	len = next_token(buf);
+	if (len < token_size) {
+		memcpy(token, *buf, len);
+		*(token + len) = '\0';
+	}
+	*buf += len;
+
+        return len;
+}
+
+/*
+ * This fills in the pool_name, obj, obj_len, snap_name, obj_len,
+ * rbd_dev, rbd_md_name, and name fields of the given rbd_dev, based
+ * on the list of monitor addresses and other options provided via
+ * /sys/bus/rbd/add.
+ */
+static int rbd_add_parse_args(struct rbd_device *rbd_dev,
+			      const char *buf,
+			      const char **mon_addrs,
+			      size_t *mon_addrs_size,
+			      char *options,
+			      size_t options_size)
+{
+	size_t	len;
+
+	/* The first four tokens are required */
+
+	len = next_token(&buf);
+	if (!len)
+		return -EINVAL;
+	*mon_addrs_size = len + 1;
+	*mon_addrs = buf;
+
+	buf += len;
+
+	len = copy_token(&buf, options, options_size);
+	if (!len || len >= options_size)
+		return -EINVAL;
+
+	len = copy_token(&buf, rbd_dev->pool_name, sizeof (rbd_dev->pool_name));
+	if (!len || len >= sizeof (rbd_dev->pool_name))
+		return -EINVAL;
+
+	len = copy_token(&buf, rbd_dev->obj, sizeof (rbd_dev->obj));
+	if (!len || len >= sizeof (rbd_dev->obj))
+		return -EINVAL;
+
+	/* We have the object length in hand, save it. */
+
+	rbd_dev->obj_len = len;
+
+	BUILD_BUG_ON(RBD_MAX_MD_NAME_LEN
+				< RBD_MAX_OBJ_NAME_LEN + sizeof (RBD_SUFFIX));
+	sprintf(rbd_dev->obj_md_name, "%s%s", rbd_dev->obj, RBD_SUFFIX);
+
+	/*
+	 * The snapshot name is optional, but it's an error if it's
+	 * too long.  If no snapshot is supplied, fill in the default.
+	 */
+	len = copy_token(&buf, rbd_dev->snap_name, sizeof (rbd_dev->snap_name));
+	if (!len)
+		memcpy(rbd_dev->snap_name, RBD_SNAP_HEAD_NAME,
+			sizeof (RBD_SNAP_HEAD_NAME));
+	else if (len >= sizeof (rbd_dev->snap_name))
+		return -EINVAL;
+
+	return 0;
+}
+
 static ssize_t rbd_add(struct bus_type *bus,
 		       const char *buf,
 		       size_t count)
 {
-	struct ceph_osd_client *osdc;
 	struct rbd_device *rbd_dev;
-	ssize_t rc = -ENOMEM;
-	int irc, new_id = 0;
-	struct list_head *tmp;
-	char *mon_dev_name;
-	char *options;
+	const char *mon_addrs = NULL;
+	size_t mon_addrs_size = 0;
+	char *options = NULL;
+	struct ceph_osd_client *osdc;
+	int rc = -ENOMEM;
 
 	if (!try_module_get(THIS_MODULE))
 		return -ENODEV;
 
-	mon_dev_name = kmalloc(RBD_MAX_OPT_LEN, GFP_KERNEL);
-	if (!mon_dev_name)
-		goto err_out_mod;
-
-	options = kmalloc(RBD_MAX_OPT_LEN, GFP_KERNEL);
-	if (!options)
-		goto err_mon_dev;
-
-	/* new rbd_device object */
 	rbd_dev = kzalloc(sizeof(*rbd_dev), GFP_KERNEL);
 	if (!rbd_dev)
-		goto err_out_opt;
+		goto err_nomem;
+	options = kmalloc(count, GFP_KERNEL);
+	if (!options)
+		goto err_nomem;
 
 	/* static rbd_device initialization */
 	spin_lock_init(&rbd_dev->lock);
 	INIT_LIST_HEAD(&rbd_dev->node);
 	INIT_LIST_HEAD(&rbd_dev->snaps);
+	init_rwsem(&rbd_dev->header_rwsem);
 
-	init_rwsem(&rbd_dev->header.snap_rwsem);
+	init_rwsem(&rbd_dev->header_rwsem);
 
 	/* generate unique id: find highest unique id, add one */
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	list_for_each(tmp, &rbd_dev_list) {
-		struct rbd_device *rbd_dev;
+	rbd_id_get(rbd_dev);
 
-		rbd_dev = list_entry(tmp, struct rbd_device, node);
-		if (rbd_dev->id >= new_id)
-			new_id = rbd_dev->id + 1;
-	}
-
-	rbd_dev->id = new_id;
-
-	/* add to global list */
-	list_add_tail(&rbd_dev->node, &rbd_dev_list);
+	/* Fill in the device name, now that we have its id. */
+	BUILD_BUG_ON(DEV_NAME_LEN
+			< sizeof (RBD_DRV_NAME) + MAX_INT_FORMAT_WIDTH);
+	sprintf(rbd_dev->name, "%s%d", RBD_DRV_NAME, rbd_dev->id);
 
 	/* parse add command */
-	if (sscanf(buf, "%" __stringify(RBD_MAX_OPT_LEN) "s "
-		   "%" __stringify(RBD_MAX_OPT_LEN) "s "
-		   "%" __stringify(RBD_MAX_POOL_NAME_LEN) "s "
-		   "%" __stringify(RBD_MAX_OBJ_NAME_LEN) "s"
-		   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
-		   mon_dev_name, options, rbd_dev->pool_name,
-		   rbd_dev->obj, rbd_dev->snap_name) < 4) {
-		rc = -EINVAL;
-		goto err_out_slot;
-	}
-
-	if (rbd_dev->snap_name[0] == 0)
-		rbd_dev->snap_name[0] = '-';
-
-	rbd_dev->obj_len = strlen(rbd_dev->obj);
-	snprintf(rbd_dev->obj_md_name, sizeof(rbd_dev->obj_md_name), "%s%s",
-		 rbd_dev->obj, RBD_SUFFIX);
-
-	/* initialize rest of new object */
-	snprintf(rbd_dev->name, DEV_NAME_LEN, DRV_NAME "%d", rbd_dev->id);
-	rc = rbd_get_client(rbd_dev, mon_dev_name, options);
-	if (rc < 0)
-		goto err_out_slot;
+	rc = rbd_add_parse_args(rbd_dev, buf, &mon_addrs, &mon_addrs_size,
+				options, count);
+	if (rc)
+		goto err_put_id;
 
-	mutex_unlock(&ctl_mutex);
+	rbd_dev->rbd_client = rbd_get_client(mon_addrs, mon_addrs_size - 1,
+						options);
+	if (IS_ERR(rbd_dev->rbd_client)) {
+		rc = PTR_ERR(rbd_dev->rbd_client);
+		goto err_put_id;
+	}
 
 	/* pick the pool */
-	osdc = &rbd_dev->client->osdc;
+	osdc = &rbd_dev->rbd_client->client->osdc;
 	rc = ceph_pg_poolid_by_name(osdc->osdmap, rbd_dev->pool_name);
 	if (rc < 0)
 		goto err_out_client;
 	rbd_dev->poolid = rc;
 
 	/* register our block device */
-	irc = register_blkdev(0, rbd_dev->name);
-	if (irc < 0) {
-		rc = irc;
+	rc = register_blkdev(0, rbd_dev->name);
+	if (rc < 0)
 		goto err_out_client;
-	}
-	rbd_dev->major = irc;
+	rbd_dev->major = rc;
 
 	rc = rbd_bus_add_dev(rbd_dev);
 	if (rc)
 		goto err_out_blkdev;
 
-	/* set up and announce blkdev mapping */
+	/*
+	 * At this point cleanup in the event of an error is the job
+	 * of the sysfs code (initiated by rbd_bus_del_dev()).
+	 *
+	 * Set up and announce blkdev mapping.
+	 */
 	rc = rbd_init_disk(rbd_dev);
 	if (rc)
 		goto err_out_bus;
@@ -2263,35 +2438,26 @@ static ssize_t rbd_add(struct bus_type *bus,
 	return count;
 
 err_out_bus:
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-	list_del_init(&rbd_dev->node);
-	mutex_unlock(&ctl_mutex);
-
 	/* this will also clean up rest of rbd_dev stuff */
 
 	rbd_bus_del_dev(rbd_dev);
 	kfree(options);
-	kfree(mon_dev_name);
 	return rc;
 
 err_out_blkdev:
 	unregister_blkdev(rbd_dev->major, rbd_dev->name);
 err_out_client:
 	rbd_put_client(rbd_dev);
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-err_out_slot:
-	list_del_init(&rbd_dev->node);
-	mutex_unlock(&ctl_mutex);
-
-	kfree(rbd_dev);
-err_out_opt:
+err_put_id:
+	rbd_id_put(rbd_dev);
+err_nomem:
 	kfree(options);
-err_mon_dev:
-	kfree(mon_dev_name);
-err_out_mod:
+	kfree(rbd_dev);
+
 	dout("Error adding device %s\n", buf);
 	module_put(THIS_MODULE);
-	return rc;
+
+	return (ssize_t) rc;
 }
 
 static struct rbd_device *__rbd_get_dev(unsigned long id)
@@ -2299,22 +2465,28 @@ static struct rbd_device *__rbd_get_dev(unsigned long id)
 	struct list_head *tmp;
 	struct rbd_device *rbd_dev;
 
+	spin_lock(&rbd_dev_list_lock);
 	list_for_each(tmp, &rbd_dev_list) {
 		rbd_dev = list_entry(tmp, struct rbd_device, node);
-		if (rbd_dev->id == id)
+		if (rbd_dev->id == id) {
+			spin_unlock(&rbd_dev_list_lock);
 			return rbd_dev;
+		}
 	}
+	spin_unlock(&rbd_dev_list_lock);
 	return NULL;
 }
 
 static void rbd_dev_release(struct device *dev)
 {
-	struct rbd_device *rbd_dev =
-			container_of(dev, struct rbd_device, dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
-	if (rbd_dev->watch_request)
-		ceph_osdc_unregister_linger_request(&rbd_dev->client->osdc,
+	if (rbd_dev->watch_request) {
+		struct ceph_client *client = rbd_dev->rbd_client->client;
+
+		ceph_osdc_unregister_linger_request(&client->osdc,
 						    rbd_dev->watch_request);
+	}
 	if (rbd_dev->watch_event)
 		rbd_req_sync_unwatch(rbd_dev, rbd_dev->obj_md_name);
 
@@ -2323,6 +2495,9 @@ static void rbd_dev_release(struct device *dev)
 	/* clean up and free blkdev */
 	rbd_free_disk(rbd_dev);
 	unregister_blkdev(rbd_dev->major, rbd_dev->name);
+
+	/* done with the id, and with the rbd_dev */
+	rbd_id_put(rbd_dev);
 	kfree(rbd_dev);
 
 	/* release module ref */
@@ -2355,8 +2530,6 @@ static ssize_t rbd_remove(struct bus_type *bus,
 		goto done;
 	}
 
-	list_del_init(&rbd_dev->node);
-
 	__rbd_remove_all_snaps(rbd_dev);
 	rbd_bus_del_dev(rbd_dev);
 
@@ -2370,7 +2543,7 @@ static ssize_t rbd_snap_add(struct device *dev,
 			    const char *buf,
 			    size_t count)
 {
-	struct rbd_device *rbd_dev = dev_to_rbd(dev);
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 	int ret;
 	char *name = kmalloc(count + 1, GFP_KERNEL);
 	if (!name)
@@ -2406,12 +2579,6 @@ err_unlock:
 	return ret;
 }
 
-static struct bus_attribute rbd_bus_attrs[] = {
-	__ATTR(add, S_IWUSR, NULL, rbd_add),
-	__ATTR(remove, S_IWUSR, NULL, rbd_remove),
-	__ATTR_NULL
-};
-
 /*
  * create control files in sysfs
  * /sys/bus/rbd/...
@@ -2420,21 +2587,21 @@ static int rbd_sysfs_init(void)
 {
 	int ret;
 
-	rbd_bus_type.bus_attrs = rbd_bus_attrs;
-
-	ret = bus_register(&rbd_bus_type);
-	 if (ret < 0)
+	ret = device_register(&rbd_root_dev);
+	if (ret < 0)
 		return ret;
 
-	ret = device_register(&rbd_root_dev);
+	ret = bus_register(&rbd_bus_type);
+	if (ret < 0)
+		device_unregister(&rbd_root_dev);
 
 	return ret;
 }
 
 static void rbd_sysfs_cleanup(void)
 {
-	device_unregister(&rbd_root_dev);
 	bus_unregister(&rbd_bus_type);
+	device_unregister(&rbd_root_dev);
 }
 
 int __init rbd_init(void)
@@ -2444,8 +2611,7 @@ int __init rbd_init(void)
 	rc = rbd_sysfs_init();
 	if (rc)
 		return rc;
-	spin_lock_init(&node_lock);
-	pr_info("loaded " DRV_NAME_LONG "\n");
+	pr_info("loaded " RBD_DRV_NAME_LONG "\n");
 	return 0;
 }
 
diff --git a/drivers/block/rbd_types.h b/drivers/block/rbd_types.h
index fc6c678aa2cb..950708688f17 100644
--- a/drivers/block/rbd_types.h
+++ b/drivers/block/rbd_types.h
@@ -41,10 +41,6 @@
 #define RBD_HEADER_SIGNATURE	"RBD"
 #define RBD_HEADER_VERSION	"001.005"
 
-struct rbd_info {
-	__le64 max_id;
-} __attribute__ ((packed));
-
 struct rbd_image_snap_ondisk {
 	__le64 id;
 	__le64 image_size;
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 48e8fee9f2d4..9dcf76a10bb6 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -839,10 +839,7 @@ static struct vio_driver vdc_port_driver = {
 	.id_table	= vdc_port_match,
 	.probe		= vdc_port_probe,
 	.remove		= vdc_port_remove,
-	.driver		= {
-		.name	= "vdc_port",
-		.owner	= THIS_MODULE,
-	}
+	.name		= "vdc_port",
 };
 
 static int __init vdc_init(void)
diff --git a/drivers/block/xd.c b/drivers/block/xd.c
index 51a972704db5..ff540520bada 100644
--- a/drivers/block/xd.c
+++ b/drivers/block/xd.c
@@ -52,7 +52,6 @@
 #include <linux/io.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/dma.h>
 
diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c
index 9c09d6f05dc9..308c8599ab55 100644
--- a/drivers/bluetooth/bt3c_cs.c
+++ b/drivers/bluetooth/bt3c_cs.c
@@ -39,7 +39,6 @@
 #include <linux/serial.h>
 #include <linux/serial_reg.h>
 #include <linux/bitops.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <linux/device.h>
diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c
index 6c20bbb54b71..428dbb7574bd 100644
--- a/drivers/bluetooth/btmrvl_debugfs.c
+++ b/drivers/bluetooth/btmrvl_debugfs.c
@@ -45,12 +45,6 @@ struct btmrvl_debugfs_data {
 	struct dentry *txdnldready;
 };
 
-static int btmrvl_open_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t btmrvl_hscfgcmd_write(struct file *file,
 			const char __user *ubuf, size_t count, loff_t *ppos)
 {
@@ -93,7 +87,7 @@ static ssize_t btmrvl_hscfgcmd_read(struct file *file, char __user *userbuf,
 static const struct file_operations btmrvl_hscfgcmd_fops = {
 	.read	= btmrvl_hscfgcmd_read,
 	.write	= btmrvl_hscfgcmd_write,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
@@ -134,7 +128,7 @@ static ssize_t btmrvl_psmode_read(struct file *file, char __user *userbuf,
 static const struct file_operations btmrvl_psmode_fops = {
 	.read	= btmrvl_psmode_read,
 	.write	= btmrvl_psmode_write,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
@@ -180,7 +174,7 @@ static ssize_t btmrvl_pscmd_read(struct file *file, char __user *userbuf,
 static const struct file_operations btmrvl_pscmd_fops = {
 	.read = btmrvl_pscmd_read,
 	.write = btmrvl_pscmd_write,
-	.open = btmrvl_open_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -221,7 +215,7 @@ static ssize_t btmrvl_gpiogap_read(struct file *file, char __user *userbuf,
 static const struct file_operations btmrvl_gpiogap_fops = {
 	.read	= btmrvl_gpiogap_read,
 	.write	= btmrvl_gpiogap_write,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
@@ -265,7 +259,7 @@ static ssize_t btmrvl_hscmd_read(struct file *file, char __user *userbuf,
 static const struct file_operations btmrvl_hscmd_fops = {
 	.read	= btmrvl_hscmd_read,
 	.write	= btmrvl_hscmd_write,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
@@ -305,7 +299,7 @@ static ssize_t btmrvl_hsmode_read(struct file *file, char __user * userbuf,
 static const struct file_operations btmrvl_hsmode_fops = {
 	.read	= btmrvl_hsmode_read,
 	.write	= btmrvl_hsmode_write,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
@@ -323,7 +317,7 @@ static ssize_t btmrvl_curpsmode_read(struct file *file, char __user *userbuf,
 
 static const struct file_operations btmrvl_curpsmode_fops = {
 	.read	= btmrvl_curpsmode_read,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
@@ -341,7 +335,7 @@ static ssize_t btmrvl_psstate_read(struct file *file, char __user * userbuf,
 
 static const struct file_operations btmrvl_psstate_fops = {
 	.read	= btmrvl_psstate_read,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
@@ -359,7 +353,7 @@ static ssize_t btmrvl_hsstate_read(struct file *file, char __user *userbuf,
 
 static const struct file_operations btmrvl_hsstate_fops = {
 	.read	= btmrvl_hsstate_read,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
@@ -378,7 +372,7 @@ static ssize_t btmrvl_txdnldready_read(struct file *file, char __user *userbuf,
 
 static const struct file_operations btmrvl_txdnldready_fops = {
 	.read	= btmrvl_txdnldready_read,
-	.open	= btmrvl_open_generic,
+	.open	= simple_open,
 	.llseek = default_llseek,
 };
 
diff --git a/drivers/bluetooth/btuart_cs.c b/drivers/bluetooth/btuart_cs.c
index 194224d07f7c..c4fc2f3fc32c 100644
--- a/drivers/bluetooth/btuart_cs.c
+++ b/drivers/bluetooth/btuart_cs.c
@@ -38,7 +38,6 @@
 #include <linux/serial.h>
 #include <linux/serial_reg.h>
 #include <linux/bitops.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <pcmcia/cistpl.h>
diff --git a/drivers/bluetooth/dtl1_cs.c b/drivers/bluetooth/dtl1_cs.c
index 049c0594a76b..6e8d96189684 100644
--- a/drivers/bluetooth/dtl1_cs.c
+++ b/drivers/bluetooth/dtl1_cs.c
@@ -38,7 +38,6 @@
 #include <linux/serial.h>
 #include <linux/serial_reg.h>
 #include <linux/bitops.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <pcmcia/cistpl.h>
diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h
index 5da67f165afa..7ea18a5fe71c 100644
--- a/drivers/char/agp/intel-agp.h
+++ b/drivers/char/agp/intel-agp.h
@@ -234,6 +234,7 @@
 #define PCI_DEVICE_ID_INTEL_IVYBRIDGE_M_GT2_IG		0x0166
 #define PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_HB		0x0158  /* Server */
 #define PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT1_IG		0x015A
+#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT2_IG		0x016A
 
 int intel_gmch_probe(struct pci_dev *pdev,
 			       struct agp_bridge_data *bridge);
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 5cf47ac2d401..7f025fb620de 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -1190,7 +1190,6 @@ static inline int needs_idle_maps(void)
 {
 #ifdef CONFIG_INTEL_IOMMU
 	const unsigned short gpu_devid = intel_private.pcidev->device;
-	extern int intel_iommu_gfx_mapped;
 
 	/* Query intel_iommu to see if we need the workaround. Presumably that
 	 * was loaded first.
@@ -1459,6 +1458,8 @@ static const struct intel_gtt_driver_description {
 	    "Ivybridge", &sandybridge_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT1_IG,
 	    "Ivybridge", &sandybridge_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT2_IG,
+	    "Ivybridge", &sandybridge_gtt_driver },
 	{ 0, NULL, NULL }
 };
 
diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c
index f4837a893dfa..46118f845948 100644
--- a/drivers/char/apm-emulation.c
+++ b/drivers/char/apm-emulation.c
@@ -31,7 +31,6 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 
-#include <asm/system.h>
 
 /*
  * The apm_bios device is one of the misc char devices.
@@ -302,7 +301,7 @@ apm_ioctl(struct file *filp, u_int cmd, u_long arg)
 			 * anything critical, chill a bit on each iteration.
 			 */
 			while (wait_event_freezable(apm_suspend_waitqueue,
-					as->suspend_state == SUSPEND_DONE))
+					as->suspend_state != SUSPEND_ACKED))
 				msleep(10);
 			break;
 		case SUSPEND_ACKTO:
diff --git a/drivers/char/ds1302.c b/drivers/char/ds1302.c
index ed8303f9890c..7d34b203718a 100644
--- a/drivers/char/ds1302.c
+++ b/drivers/char/ds1302.c
@@ -24,7 +24,6 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/rtc.h>
 #if defined(CONFIG_M32R)
 #include <asm/m32r.h>
diff --git a/drivers/char/efirtc.c b/drivers/char/efirtc.c
index 53c524e7b829..a082d00b0f11 100644
--- a/drivers/char/efirtc.c
+++ b/drivers/char/efirtc.c
@@ -37,7 +37,6 @@
 #include <linux/efi.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 #define EFI_RTC_VERSION		"0.4"
 
diff --git a/drivers/char/genrtc.c b/drivers/char/genrtc.c
index f773a9dd14f3..21cb980f1157 100644
--- a/drivers/char/genrtc.c
+++ b/drivers/char/genrtc.c
@@ -56,7 +56,6 @@
 #include <linux/workqueue.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/rtc.h>
 
 /*
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 0833896cf6f2..3845ab44c330 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -36,7 +36,6 @@
 #include <linux/io.h>
 
 #include <asm/current.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/div64.h>
 
diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c
index 2aa3977aae5e..9eb360ff8cab 100644
--- a/drivers/char/ipmi/ipmi_devintf.c
+++ b/drivers/char/ipmi/ipmi_devintf.c
@@ -34,7 +34,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/errno.h>
-#include <asm/system.h>
 #include <linux/poll.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
diff --git a/drivers/char/ipmi/ipmi_kcs_sm.c b/drivers/char/ipmi/ipmi_kcs_sm.c
index cf82fedae099..e53fc24c6af3 100644
--- a/drivers/char/ipmi/ipmi_kcs_sm.c
+++ b/drivers/char/ipmi/ipmi_kcs_sm.c
@@ -118,8 +118,8 @@ enum kcs_states {
 #define MAX_KCS_WRITE_SIZE IPMI_MAX_MSG_LENGTH
 
 /* Timeouts in microseconds. */
-#define IBF_RETRY_TIMEOUT 1000000
-#define OBF_RETRY_TIMEOUT 1000000
+#define IBF_RETRY_TIMEOUT 5000000
+#define OBF_RETRY_TIMEOUT 5000000
 #define MAX_ERROR_RETRIES 10
 #define ERROR0_OBF_WAIT_JIFFIES (2*HZ)
 
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 58c0e6387cf7..2c29942b1326 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -33,7 +33,6 @@
 
 #include <linux/module.h>
 #include <linux/errno.h>
-#include <asm/system.h>
 #include <linux/poll.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
@@ -46,6 +45,7 @@
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
+#include <linux/interrupt.h>
 
 #define PFX "IPMI message handler: "
 
@@ -53,6 +53,8 @@
 
 static struct ipmi_recv_msg *ipmi_alloc_recv_msg(void);
 static int ipmi_init_msghandler(void);
+static void smi_recv_tasklet(unsigned long);
+static void handle_new_recv_msgs(ipmi_smi_t intf);
 
 static int initialized;
 
@@ -355,12 +357,15 @@ struct ipmi_smi {
 	int curr_seq;
 
 	/*
-	 * Messages that were delayed for some reason (out of memory,
-	 * for instance), will go in here to be processed later in a
-	 * periodic timer interrupt.
+	 * Messages queued for delivery.  If delivery fails (out of memory
+	 * for instance), They will stay in here to be processed later in a
+	 * periodic timer interrupt.  The tasklet is for handling received
+	 * messages directly from the handler.
 	 */
 	spinlock_t       waiting_msgs_lock;
 	struct list_head waiting_msgs;
+	atomic_t	 watchdog_pretimeouts_to_deliver;
+	struct tasklet_struct recv_tasklet;
 
 	/*
 	 * The list of command receivers that are registered for commands
@@ -493,6 +498,8 @@ static void clean_up_interface_data(ipmi_smi_t intf)
 	struct cmd_rcvr  *rcvr, *rcvr2;
 	struct list_head list;
 
+	tasklet_kill(&intf->recv_tasklet);
+
 	free_smi_msg_list(&intf->waiting_msgs);
 	free_recv_msg_list(&intf->waiting_events);
 
@@ -2786,12 +2793,17 @@ channel_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 	return;
 }
 
-void ipmi_poll_interface(ipmi_user_t user)
+static void ipmi_poll(ipmi_smi_t intf)
 {
-	ipmi_smi_t intf = user->intf;
-
 	if (intf->handlers->poll)
 		intf->handlers->poll(intf->send_info);
+	/* In case something came in */
+	handle_new_recv_msgs(intf);
+}
+
+void ipmi_poll_interface(ipmi_user_t user)
+{
+	ipmi_poll(user->intf);
 }
 EXPORT_SYMBOL(ipmi_poll_interface);
 
@@ -2860,6 +2872,10 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 #endif
 	spin_lock_init(&intf->waiting_msgs_lock);
 	INIT_LIST_HEAD(&intf->waiting_msgs);
+	tasklet_init(&intf->recv_tasklet,
+		     smi_recv_tasklet,
+		     (unsigned long) intf);
+	atomic_set(&intf->watchdog_pretimeouts_to_deliver, 0);
 	spin_lock_init(&intf->events_lock);
 	INIT_LIST_HEAD(&intf->waiting_events);
 	intf->waiting_events_count = 0;
@@ -3622,11 +3638,11 @@ static int handle_bmc_rsp(ipmi_smi_t          intf,
 }
 
 /*
- * Handle a new message.  Return 1 if the message should be requeued,
+ * Handle a received message.  Return 1 if the message should be requeued,
  * 0 if the message should be freed, or -1 if the message should not
  * be freed or requeued.
  */
-static int handle_new_recv_msg(ipmi_smi_t          intf,
+static int handle_one_recv_msg(ipmi_smi_t          intf,
 			       struct ipmi_smi_msg *msg)
 {
 	int requeue;
@@ -3784,12 +3800,72 @@ static int handle_new_recv_msg(ipmi_smi_t          intf,
 	return requeue;
 }
 
+/*
+ * If there are messages in the queue or pretimeouts, handle them.
+ */
+static void handle_new_recv_msgs(ipmi_smi_t intf)
+{
+	struct ipmi_smi_msg  *smi_msg;
+	unsigned long        flags = 0;
+	int                  rv;
+	int                  run_to_completion = intf->run_to_completion;
+
+	/* See if any waiting messages need to be processed. */
+	if (!run_to_completion)
+		spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
+	while (!list_empty(&intf->waiting_msgs)) {
+		smi_msg = list_entry(intf->waiting_msgs.next,
+				     struct ipmi_smi_msg, link);
+		list_del(&smi_msg->link);
+		if (!run_to_completion)
+			spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
+		rv = handle_one_recv_msg(intf, smi_msg);
+		if (!run_to_completion)
+			spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
+		if (rv == 0) {
+			/* Message handled */
+			ipmi_free_smi_msg(smi_msg);
+		} else if (rv < 0) {
+			/* Fatal error on the message, del but don't free. */
+		} else {
+			/*
+			 * To preserve message order, quit if we
+			 * can't handle a message.
+			 */
+			list_add(&smi_msg->link, &intf->waiting_msgs);
+			break;
+		}
+	}
+	if (!run_to_completion)
+		spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
+
+	/*
+	 * If the pretimout count is non-zero, decrement one from it and
+	 * deliver pretimeouts to all the users.
+	 */
+	if (atomic_add_unless(&intf->watchdog_pretimeouts_to_deliver, -1, 0)) {
+		ipmi_user_t user;
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(user, &intf->users, link) {
+			if (user->handler->ipmi_watchdog_pretimeout)
+				user->handler->ipmi_watchdog_pretimeout(
+					user->handler_data);
+		}
+		rcu_read_unlock();
+	}
+}
+
+static void smi_recv_tasklet(unsigned long val)
+{
+	handle_new_recv_msgs((ipmi_smi_t) val);
+}
+
 /* Handle a new message from the lower layer. */
 void ipmi_smi_msg_received(ipmi_smi_t          intf,
 			   struct ipmi_smi_msg *msg)
 {
 	unsigned long flags = 0; /* keep us warning-free. */
-	int           rv;
 	int           run_to_completion;
 
 
@@ -3843,31 +3919,11 @@ void ipmi_smi_msg_received(ipmi_smi_t          intf,
 	run_to_completion = intf->run_to_completion;
 	if (!run_to_completion)
 		spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
-	if (!list_empty(&intf->waiting_msgs)) {
-		list_add_tail(&msg->link, &intf->waiting_msgs);
-		if (!run_to_completion)
-			spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
-		goto out;
-	}
+	list_add_tail(&msg->link, &intf->waiting_msgs);
 	if (!run_to_completion)
 		spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
 
-	rv = handle_new_recv_msg(intf, msg);
-	if (rv > 0) {
-		/*
-		 * Could not handle the message now, just add it to a
-		 * list to handle later.
-		 */
-		run_to_completion = intf->run_to_completion;
-		if (!run_to_completion)
-			spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
-		list_add_tail(&msg->link, &intf->waiting_msgs);
-		if (!run_to_completion)
-			spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
-	} else if (rv == 0) {
-		ipmi_free_smi_msg(msg);
-	}
-
+	tasklet_schedule(&intf->recv_tasklet);
  out:
 	return;
 }
@@ -3875,16 +3931,8 @@ EXPORT_SYMBOL(ipmi_smi_msg_received);
 
 void ipmi_smi_watchdog_pretimeout(ipmi_smi_t intf)
 {
-	ipmi_user_t user;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(user, &intf->users, link) {
-		if (!user->handler->ipmi_watchdog_pretimeout)
-			continue;
-
-		user->handler->ipmi_watchdog_pretimeout(user->handler_data);
-	}
-	rcu_read_unlock();
+	atomic_set(&intf->watchdog_pretimeouts_to_deliver, 1);
+	tasklet_schedule(&intf->recv_tasklet);
 }
 EXPORT_SYMBOL(ipmi_smi_watchdog_pretimeout);
 
@@ -3998,28 +4046,12 @@ static void ipmi_timeout_handler(long timeout_period)
 	ipmi_smi_t           intf;
 	struct list_head     timeouts;
 	struct ipmi_recv_msg *msg, *msg2;
-	struct ipmi_smi_msg  *smi_msg, *smi_msg2;
 	unsigned long        flags;
 	int                  i;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
-		/* See if any waiting messages need to be processed. */
-		spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
-		list_for_each_entry_safe(smi_msg, smi_msg2,
-					 &intf->waiting_msgs, link) {
-			if (!handle_new_recv_msg(intf, smi_msg)) {
-				list_del(&smi_msg->link);
-				ipmi_free_smi_msg(smi_msg);
-			} else {
-				/*
-				 * To preserve message order, quit if we
-				 * can't handle a message.
-				 */
-				break;
-			}
-		}
-		spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
+		tasklet_schedule(&intf->recv_tasklet);
 
 		/*
 		 * Go through the seq table and find any messages that
@@ -4173,12 +4205,48 @@ EXPORT_SYMBOL(ipmi_free_recv_msg);
 
 #ifdef CONFIG_IPMI_PANIC_EVENT
 
+static atomic_t panic_done_count = ATOMIC_INIT(0);
+
 static void dummy_smi_done_handler(struct ipmi_smi_msg *msg)
 {
+	atomic_dec(&panic_done_count);
 }
 
 static void dummy_recv_done_handler(struct ipmi_recv_msg *msg)
 {
+	atomic_dec(&panic_done_count);
+}
+
+/*
+ * Inside a panic, send a message and wait for a response.
+ */
+static void ipmi_panic_request_and_wait(ipmi_smi_t           intf,
+					struct ipmi_addr     *addr,
+					struct kernel_ipmi_msg *msg)
+{
+	struct ipmi_smi_msg  smi_msg;
+	struct ipmi_recv_msg recv_msg;
+	int rv;
+
+	smi_msg.done = dummy_smi_done_handler;
+	recv_msg.done = dummy_recv_done_handler;
+	atomic_add(2, &panic_done_count);
+	rv = i_ipmi_request(NULL,
+			    intf,
+			    addr,
+			    0,
+			    msg,
+			    intf,
+			    &smi_msg,
+			    &recv_msg,
+			    0,
+			    intf->channels[0].address,
+			    intf->channels[0].lun,
+			    0, 1); /* Don't retry, and don't wait. */
+	if (rv)
+		atomic_sub(2, &panic_done_count);
+	while (atomic_read(&panic_done_count) != 0)
+		ipmi_poll(intf);
 }
 
 #ifdef CONFIG_IPMI_PANIC_STRING
@@ -4217,8 +4285,6 @@ static void send_panic_events(char *str)
 	unsigned char                     data[16];
 	struct ipmi_system_interface_addr *si;
 	struct ipmi_addr                  addr;
-	struct ipmi_smi_msg               smi_msg;
-	struct ipmi_recv_msg              recv_msg;
 
 	si = (struct ipmi_system_interface_addr *) &addr;
 	si->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
@@ -4246,9 +4312,6 @@ static void send_panic_events(char *str)
 		data[7] = str[2];
 	}
 
-	smi_msg.done = dummy_smi_done_handler;
-	recv_msg.done = dummy_recv_done_handler;
-
 	/* For every registered interface, send the event. */
 	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
 		if (!intf->handlers)
@@ -4258,18 +4321,7 @@ static void send_panic_events(char *str)
 		intf->run_to_completion = 1;
 		/* Send the event announcing the panic. */
 		intf->handlers->set_run_to_completion(intf->send_info, 1);
-		i_ipmi_request(NULL,
-			       intf,
-			       &addr,
-			       0,
-			       &msg,
-			       intf,
-			       &smi_msg,
-			       &recv_msg,
-			       0,
-			       intf->channels[0].address,
-			       intf->channels[0].lun,
-			       0, 1); /* Don't retry, and don't wait. */
+		ipmi_panic_request_and_wait(intf, &addr, &msg);
 	}
 
 #ifdef CONFIG_IPMI_PANIC_STRING
@@ -4317,18 +4369,7 @@ static void send_panic_events(char *str)
 		msg.data = NULL;
 		msg.data_len = 0;
 		intf->null_user_handler = device_id_fetcher;
-		i_ipmi_request(NULL,
-			       intf,
-			       &addr,
-			       0,
-			       &msg,
-			       intf,
-			       &smi_msg,
-			       &recv_msg,
-			       0,
-			       intf->channels[0].address,
-			       intf->channels[0].lun,
-			       0, 1); /* Don't retry, and don't wait. */
+		ipmi_panic_request_and_wait(intf, &addr, &msg);
 
 		if (intf->local_event_generator) {
 			/* Request the event receiver from the local MC. */
@@ -4337,18 +4378,7 @@ static void send_panic_events(char *str)
 			msg.data = NULL;
 			msg.data_len = 0;
 			intf->null_user_handler = event_receiver_fetcher;
-			i_ipmi_request(NULL,
-				       intf,
-				       &addr,
-				       0,
-				       &msg,
-				       intf,
-				       &smi_msg,
-				       &recv_msg,
-				       0,
-				       intf->channels[0].address,
-				       intf->channels[0].lun,
-				       0, 1); /* no retry, and no wait. */
+			ipmi_panic_request_and_wait(intf, &addr, &msg);
 		}
 		intf->null_user_handler = NULL;
 
@@ -4405,18 +4435,7 @@ static void send_panic_events(char *str)
 			strncpy(data+5, p, 11);
 			p += size;
 
-			i_ipmi_request(NULL,
-				       intf,
-				       &addr,
-				       0,
-				       &msg,
-				       intf,
-				       &smi_msg,
-				       &recv_msg,
-				       0,
-				       intf->channels[0].address,
-				       intf->channels[0].lun,
-				       0, 1); /* no retry, and no wait. */
+			ipmi_panic_request_and_wait(intf, &addr, &msg);
 		}
 	}
 #endif /* CONFIG_IPMI_PANIC_STRING */
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 50fcf9c04569..1e638fff40ea 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -41,7 +41,6 @@
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <asm/system.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/timer.h>
@@ -171,7 +170,6 @@ struct smi_info {
 	struct si_sm_handlers  *handlers;
 	enum si_type           si_type;
 	spinlock_t             si_lock;
-	spinlock_t             msg_lock;
 	struct list_head       xmit_msgs;
 	struct list_head       hp_xmit_msgs;
 	struct ipmi_smi_msg    *curr_msg;
@@ -320,16 +318,8 @@ static int register_xaction_notifier(struct notifier_block *nb)
 static void deliver_recv_msg(struct smi_info *smi_info,
 			     struct ipmi_smi_msg *msg)
 {
-	/* Deliver the message to the upper layer with the lock
-	   released. */
-
-	if (smi_info->run_to_completion) {
-		ipmi_smi_msg_received(smi_info->intf, msg);
-	} else {
-		spin_unlock(&(smi_info->si_lock));
-		ipmi_smi_msg_received(smi_info->intf, msg);
-		spin_lock(&(smi_info->si_lock));
-	}
+	/* Deliver the message to the upper layer. */
+	ipmi_smi_msg_received(smi_info->intf, msg);
 }
 
 static void return_hosed_msg(struct smi_info *smi_info, int cCode)
@@ -358,13 +348,6 @@ static enum si_sm_result start_next_msg(struct smi_info *smi_info)
 	struct timeval t;
 #endif
 
-	/*
-	 * No need to save flags, we aleady have interrupts off and we
-	 * already hold the SMI lock.
-	 */
-	if (!smi_info->run_to_completion)
-		spin_lock(&(smi_info->msg_lock));
-
 	/* Pick the high priority queue first. */
 	if (!list_empty(&(smi_info->hp_xmit_msgs))) {
 		entry = smi_info->hp_xmit_msgs.next;
@@ -402,9 +385,6 @@ static enum si_sm_result start_next_msg(struct smi_info *smi_info)
 		rv = SI_SM_CALL_WITHOUT_DELAY;
 	}
  out:
-	if (!smi_info->run_to_completion)
-		spin_unlock(&(smi_info->msg_lock));
-
 	return rv;
 }
 
@@ -481,9 +461,7 @@ static void handle_flags(struct smi_info *smi_info)
 
 		start_clear_flags(smi_info);
 		smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT;
-		spin_unlock(&(smi_info->si_lock));
 		ipmi_smi_watchdog_pretimeout(smi_info->intf);
-		spin_lock(&(smi_info->si_lock));
 	} else if (smi_info->msg_flags & RECEIVE_MSG_AVAIL) {
 		/* Messages available. */
 		smi_info->curr_msg = ipmi_alloc_smi_msg();
@@ -889,19 +867,6 @@ static void sender(void                *send_info,
 	printk("**Enqueue: %d.%9.9d\n", t.tv_sec, t.tv_usec);
 #endif
 
-	/*
-	 * last_timeout_jiffies is updated here to avoid
-	 * smi_timeout() handler passing very large time_diff
-	 * value to smi_event_handler() that causes
-	 * the send command to abort.
-	 */
-	smi_info->last_timeout_jiffies = jiffies;
-
-	mod_timer(&smi_info->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
-
-	if (smi_info->thread)
-		wake_up_process(smi_info->thread);
-
 	if (smi_info->run_to_completion) {
 		/*
 		 * If we are running to completion, then throw it in
@@ -924,16 +889,29 @@ static void sender(void                *send_info,
 		return;
 	}
 
-	spin_lock_irqsave(&smi_info->msg_lock, flags);
+	spin_lock_irqsave(&smi_info->si_lock, flags);
 	if (priority > 0)
 		list_add_tail(&msg->link, &smi_info->hp_xmit_msgs);
 	else
 		list_add_tail(&msg->link, &smi_info->xmit_msgs);
-	spin_unlock_irqrestore(&smi_info->msg_lock, flags);
 
-	spin_lock_irqsave(&smi_info->si_lock, flags);
-	if (smi_info->si_state == SI_NORMAL && smi_info->curr_msg == NULL)
+	if (smi_info->si_state == SI_NORMAL && smi_info->curr_msg == NULL) {
+		/*
+		 * last_timeout_jiffies is updated here to avoid
+		 * smi_timeout() handler passing very large time_diff
+		 * value to smi_event_handler() that causes
+		 * the send command to abort.
+		 */
+		smi_info->last_timeout_jiffies = jiffies;
+
+		mod_timer(&smi_info->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
+
+		if (smi_info->thread)
+			wake_up_process(smi_info->thread);
+
 		start_next_msg(smi_info);
+		smi_event_handler(smi_info, 0);
+	}
 	spin_unlock_irqrestore(&smi_info->si_lock, flags);
 }
 
@@ -1034,16 +1012,19 @@ static int ipmi_thread(void *data)
 static void poll(void *send_info)
 {
 	struct smi_info *smi_info = send_info;
-	unsigned long flags;
+	unsigned long flags = 0;
+	int run_to_completion = smi_info->run_to_completion;
 
 	/*
 	 * Make sure there is some delay in the poll loop so we can
 	 * drive time forward and timeout things.
 	 */
 	udelay(10);
-	spin_lock_irqsave(&smi_info->si_lock, flags);
+	if (!run_to_completion)
+		spin_lock_irqsave(&smi_info->si_lock, flags);
 	smi_event_handler(smi_info, 10);
-	spin_unlock_irqrestore(&smi_info->si_lock, flags);
+	if (!run_to_completion)
+		spin_unlock_irqrestore(&smi_info->si_lock, flags);
 }
 
 static void request_events(void *send_info)
@@ -1680,10 +1661,8 @@ static struct smi_info *smi_info_alloc(void)
 {
 	struct smi_info *info = kzalloc(sizeof(*info), GFP_KERNEL);
 
-	if (info) {
+	if (info)
 		spin_lock_init(&info->si_lock);
-		spin_lock_init(&info->msg_lock);
-	}
 	return info;
 }
 
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 34767a6d7f42..7ed356e52035 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -153,7 +153,7 @@
 #endif
 
 static DEFINE_MUTEX(ipmi_watchdog_mutex);
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 static ipmi_user_t watchdog_user;
 static int watchdog_ifnum;
@@ -320,7 +320,7 @@ module_param(start_now, int, 0444);
 MODULE_PARM_DESC(start_now, "Set to 1 to start the watchdog as"
 		 "soon as the driver is loaded.");
 
-module_param(nowayout, int, 0644);
+module_param(nowayout, bool, 0644);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 		 "(default=CONFIG_WATCHDOG_NOWAYOUT)");
 
@@ -520,6 +520,7 @@ static void panic_halt_ipmi_heartbeat(void)
 	msg.cmd = IPMI_WDOG_RESET_TIMER;
 	msg.data = NULL;
 	msg.data_len = 0;
+	atomic_add(2, &panic_done_count);
 	rv = ipmi_request_supply_msgs(watchdog_user,
 				      (struct ipmi_addr *) &addr,
 				      0,
@@ -528,8 +529,8 @@ static void panic_halt_ipmi_heartbeat(void)
 				      &panic_halt_heartbeat_smi_msg,
 				      &panic_halt_heartbeat_recv_msg,
 				      1);
-	if (!rv)
-		atomic_add(2, &panic_done_count);
+	if (rv)
+		atomic_sub(2, &panic_done_count);
 }
 
 static struct ipmi_smi_msg panic_halt_smi_msg = {
@@ -553,16 +554,18 @@ static void panic_halt_ipmi_set_timeout(void)
 	/* Wait for the messages to be free. */
 	while (atomic_read(&panic_done_count) != 0)
 		ipmi_poll_interface(watchdog_user);
+	atomic_add(2, &panic_done_count);
 	rv = i_ipmi_set_timeout(&panic_halt_smi_msg,
 				&panic_halt_recv_msg,
 				&send_heartbeat_now);
-	if (!rv) {
-		atomic_add(2, &panic_done_count);
-		if (send_heartbeat_now)
-			panic_halt_ipmi_heartbeat();
-	} else
+	if (rv) {
+		atomic_sub(2, &panic_done_count);
 		printk(KERN_WARNING PFX
 		       "Unable to extend the watchdog timeout.");
+	} else {
+		if (send_heartbeat_now)
+			panic_halt_ipmi_heartbeat();
+	}
 	while (atomic_read(&panic_done_count) != 0)
 		ipmi_poll_interface(watchdog_user);
 }
@@ -1164,7 +1167,7 @@ static int wdog_reboot_handler(struct notifier_block *this,
 		if (code == SYS_POWER_OFF || code == SYS_HALT) {
 			/* Disable the WDT if we are shutting down. */
 			ipmi_watchdog_state = WDOG_TIMEOUT_NONE;
-			panic_halt_ipmi_set_timeout();
+			ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
 		} else if (ipmi_watchdog_state != WDOG_TIMEOUT_NONE) {
 			/* Set a long timer to let the reboot happens, but
 			   reboot if it hangs, but only if the watchdog
@@ -1172,7 +1175,7 @@ static int wdog_reboot_handler(struct notifier_block *this,
 			timeout = 120;
 			pretimeout = 0;
 			ipmi_watchdog_state = WDOG_TIMEOUT_RESET;
-			panic_halt_ipmi_set_timeout();
+			ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
 		}
 	}
 	return NOTIFY_OK;
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index f43485607063..a741e418b456 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -135,7 +135,6 @@
 
 #include <asm/irq.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 /* if you have more than 8 printers, remember to increase LP_NO */
 #define LP_NO 8
@@ -706,16 +705,13 @@ static long lp_compat_ioctl(struct file *file, unsigned int cmd,
 {
 	unsigned int minor;
 	struct timeval par_timeout;
-	struct compat_timeval __user *tc;
 	int ret;
 
 	minor = iminor(file->f_path.dentry->d_inode);
 	mutex_lock(&lp_mutex);
 	switch (cmd) {
 	case LPSETTIMEOUT:
-		tc = compat_ptr(arg);
-		if (get_user(par_timeout.tv_sec, &tc->tv_sec) ||
-		    get_user(par_timeout.tv_usec, &tc->tv_usec)) {
+		if (compat_get_timeval(&par_timeout, compat_ptr(arg))) {
 			ret = -EFAULT;
 			break;
 		}
diff --git a/drivers/char/mbcs.c b/drivers/char/mbcs.c
index 1aeaaba680d2..47ff7e470d87 100644
--- a/drivers/char/mbcs.c
+++ b/drivers/char/mbcs.c
@@ -28,7 +28,6 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/intr.h>
diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c
index 5c0d96a820fa..8b78750f1efe 100644
--- a/drivers/char/mspec.c
+++ b/drivers/char/mspec.c
@@ -44,7 +44,6 @@
 #include <linux/slab.h>
 #include <linux/numa.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <linux/atomic.h>
 #include <asm/tlbflush.h>
diff --git a/drivers/char/mwave/3780i.c b/drivers/char/mwave/3780i.c
index 492dbfb2efd6..881c9e595939 100644
--- a/drivers/char/mwave/3780i.c
+++ b/drivers/char/mwave/3780i.c
@@ -56,7 +56,6 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include "smapi.h"
 #include "mwavedd.h"
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index eaade8a1ecd7..9df78e2cc45d 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -111,7 +111,6 @@
 #include <linux/uaccess.h>
 #include <linux/mutex.h>
 
-#include <asm/system.h>
 
 static DEFINE_MUTEX(nvram_mutex);
 static DEFINE_SPINLOCK(nvram_state_lock);
diff --git a/drivers/char/nwflash.c b/drivers/char/nwflash.c
index bf586ae1ee83..d45c3345b4af 100644
--- a/drivers/char/nwflash.c
+++ b/drivers/char/nwflash.c
@@ -32,7 +32,6 @@
 #include <asm/io.h>
 #include <asm/leds.h>
 #include <asm/mach-types.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 /*****************************************************************************/
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index f6453df4921c..0a484b4a1b02 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -60,7 +60,6 @@
 #include <linux/ioctl.h>
 #include <linux/synclink.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/dma.h>
diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c
index 872e09a02d23..af9437488b6c 100644
--- a/drivers/char/rtc.c
+++ b/drivers/char/rtc.c
@@ -83,7 +83,6 @@
 #include <linux/ratelimit.h>
 
 #include <asm/current.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_X86
 #include <asm/hpet.h>
diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c
index 1ee8ce7d2762..45713f0e7d61 100644
--- a/drivers/char/sonypi.c
+++ b/drivers/char/sonypi.c
@@ -54,7 +54,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <linux/sonypi.h>
 
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index b58b56187065..ddf86b6500b7 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1038,12 +1038,6 @@ static struct attribute_group port_attribute_group = {
 	.attrs = port_sysfs_entries,
 };
 
-static int debugfs_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t debugfs_read(struct file *filp, char __user *ubuf,
 			    size_t count, loff_t *offp)
 {
@@ -1087,7 +1081,7 @@ static ssize_t debugfs_read(struct file *filp, char __user *ubuf,
 
 static const struct file_operations port_debugfs_ops = {
 	.owner = THIS_MODULE,
-	.open  = debugfs_open,
+	.open  = simple_open,
 	.read  = debugfs_read,
 };
 
diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c
index e90e1c74fd4c..31ba11ca75e1 100644
--- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c
+++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c
@@ -89,7 +89,6 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_OF
 /* For open firmware. */
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 9b3cd08cd0ed..165e1febae53 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -8,3 +8,40 @@ config HAVE_CLK_PREPARE
 
 config HAVE_MACH_CLKDEV
 	bool
+
+config COMMON_CLK
+	bool
+	select HAVE_CLK_PREPARE
+	---help---
+	  The common clock framework is a single definition of struct
+	  clk, useful across many platforms, as well as an
+	  implementation of the clock API in include/linux/clk.h.
+	  Architectures utilizing the common struct clk should select
+	  this option.
+
+menu "Common Clock Framework"
+	depends on COMMON_CLK
+
+config COMMON_CLK_DISABLE_UNUSED
+	bool "Disabled unused clocks at boot"
+	depends on COMMON_CLK
+	---help---
+	  Traverses the entire clock tree and disables any clocks that are
+	  enabled in hardware but have not been enabled by any device drivers.
+	  This saves power and keeps the software model of the clock in line
+	  with reality.
+
+	  If in doubt, say "N".
+
+config COMMON_CLK_DEBUG
+	bool "DebugFS representation of clock tree"
+	depends on COMMON_CLK
+	select DEBUG_FS
+	---help---
+	  Creates a directory hierchy in debugfs for visualizing the clk
+	  tree structure.  Each directory contains read-only members
+	  that export information specific to that clk node: clk_rate,
+	  clk_flags, clk_prepare_count, clk_enable_count &
+	  clk_notifier_count.
+
+endmenu
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 07613fa172c9..1f736bc11c4b 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -1,2 +1,4 @@
 
 obj-$(CONFIG_CLKDEV_LOOKUP)	+= clkdev.o
+obj-$(CONFIG_COMMON_CLK)	+= clk.o clk-fixed-rate.o clk-gate.o \
+				   clk-mux.o clk-divider.o
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
new file mode 100644
index 000000000000..d5ac6a75ea57
--- /dev/null
+++ b/drivers/clk/clk-divider.c
@@ -0,0 +1,200 @@
+/*
+ * Copyright (C) 2011 Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>
+ * Copyright (C) 2011 Richard Zhao, Linaro <richard.zhao@linaro.org>
+ * Copyright (C) 2011-2012 Mike Turquette, Linaro Ltd <mturquette@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Adjustable divider clock implementation
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/string.h>
+
+/*
+ * DOC: basic adjustable divider clock that cannot gate
+ *
+ * Traits of this clock:
+ * prepare - clk_prepare only ensures that parents are prepared
+ * enable - clk_enable only ensures that parents are enabled
+ * rate - rate is adjustable.  clk->rate = parent->rate / divisor
+ * parent - fixed parent.  No clk_set_parent support
+ */
+
+#define to_clk_divider(_hw) container_of(_hw, struct clk_divider, hw)
+
+#define div_mask(d)	((1 << (d->width)) - 1)
+
+static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	unsigned int div;
+
+	div = readl(divider->reg) >> divider->shift;
+	div &= div_mask(divider);
+
+	if (!(divider->flags & CLK_DIVIDER_ONE_BASED))
+		div++;
+
+	return parent_rate / div;
+}
+EXPORT_SYMBOL_GPL(clk_divider_recalc_rate);
+
+/*
+ * The reverse of DIV_ROUND_UP: The maximum number which
+ * divided by m is r
+ */
+#define MULT_ROUND_UP(r, m) ((r) * (m) + (m) - 1)
+
+static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
+		unsigned long *best_parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	int i, bestdiv = 0;
+	unsigned long parent_rate, best = 0, now, maxdiv;
+
+	if (!rate)
+		rate = 1;
+
+	maxdiv = (1 << divider->width);
+
+	if (divider->flags & CLK_DIVIDER_ONE_BASED)
+		maxdiv--;
+
+	if (!best_parent_rate) {
+		parent_rate = __clk_get_rate(__clk_get_parent(hw->clk));
+		bestdiv = DIV_ROUND_UP(parent_rate, rate);
+		bestdiv = bestdiv == 0 ? 1 : bestdiv;
+		bestdiv = bestdiv > maxdiv ? maxdiv : bestdiv;
+		return bestdiv;
+	}
+
+	/*
+	 * The maximum divider we can use without overflowing
+	 * unsigned long in rate * i below
+	 */
+	maxdiv = min(ULONG_MAX / rate, maxdiv);
+
+	for (i = 1; i <= maxdiv; i++) {
+		parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
+				MULT_ROUND_UP(rate, i));
+		now = parent_rate / i;
+		if (now <= rate && now > best) {
+			bestdiv = i;
+			best = now;
+			*best_parent_rate = parent_rate;
+		}
+	}
+
+	if (!bestdiv) {
+		bestdiv = (1 << divider->width);
+		if (divider->flags & CLK_DIVIDER_ONE_BASED)
+			bestdiv--;
+		*best_parent_rate = __clk_round_rate(__clk_get_parent(hw->clk), 1);
+	}
+
+	return bestdiv;
+}
+
+static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *prate)
+{
+	int div;
+	div = clk_divider_bestdiv(hw, rate, prate);
+
+	if (prate)
+		return *prate / div;
+	else {
+		unsigned long r;
+		r = __clk_get_rate(__clk_get_parent(hw->clk));
+		return r / div;
+	}
+}
+EXPORT_SYMBOL_GPL(clk_divider_round_rate);
+
+static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	unsigned int div;
+	unsigned long flags = 0;
+	u32 val;
+
+	div = __clk_get_rate(__clk_get_parent(hw->clk)) / rate;
+
+	if (!(divider->flags & CLK_DIVIDER_ONE_BASED))
+		div--;
+
+	if (div > div_mask(divider))
+		div = div_mask(divider);
+
+	if (divider->lock)
+		spin_lock_irqsave(divider->lock, flags);
+
+	val = readl(divider->reg);
+	val &= ~(div_mask(divider) << divider->shift);
+	val |= div << divider->shift;
+	writel(val, divider->reg);
+
+	if (divider->lock)
+		spin_unlock_irqrestore(divider->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(clk_divider_set_rate);
+
+struct clk_ops clk_divider_ops = {
+	.recalc_rate = clk_divider_recalc_rate,
+	.round_rate = clk_divider_round_rate,
+	.set_rate = clk_divider_set_rate,
+};
+EXPORT_SYMBOL_GPL(clk_divider_ops);
+
+struct clk *clk_register_divider(struct device *dev, const char *name,
+		const char *parent_name, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width,
+		u8 clk_divider_flags, spinlock_t *lock)
+{
+	struct clk_divider *div;
+	struct clk *clk;
+
+	div = kzalloc(sizeof(struct clk_divider), GFP_KERNEL);
+
+	if (!div) {
+		pr_err("%s: could not allocate divider clk\n", __func__);
+		return NULL;
+	}
+
+	/* struct clk_divider assignments */
+	div->reg = reg;
+	div->shift = shift;
+	div->width = width;
+	div->flags = clk_divider_flags;
+	div->lock = lock;
+
+	if (parent_name) {
+		div->parent[0] = kstrdup(parent_name, GFP_KERNEL);
+		if (!div->parent[0])
+			goto out;
+	}
+
+	clk = clk_register(dev, name,
+			&clk_divider_ops, &div->hw,
+			div->parent,
+			(parent_name ? 1 : 0),
+			flags);
+	if (clk)
+		return clk;
+
+out:
+	kfree(div->parent[0]);
+	kfree(div);
+
+	return NULL;
+}
diff --git a/drivers/clk/clk-fixed-rate.c b/drivers/clk/clk-fixed-rate.c
new file mode 100644
index 000000000000..90c79fb5d1bd
--- /dev/null
+++ b/drivers/clk/clk-fixed-rate.c
@@ -0,0 +1,82 @@
+/*
+ * Copyright (C) 2010-2011 Canonical Ltd <jeremy.kerr@canonical.com>
+ * Copyright (C) 2011-2012 Mike Turquette, Linaro Ltd <mturquette@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Fixed rate clock implementation
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/err.h>
+
+/*
+ * DOC: basic fixed-rate clock that cannot gate
+ *
+ * Traits of this clock:
+ * prepare - clk_(un)prepare only ensures parents are prepared
+ * enable - clk_enable only ensures parents are enabled
+ * rate - rate is always a fixed value.  No clk_set_rate support
+ * parent - fixed parent.  No clk_set_parent support
+ */
+
+#define to_clk_fixed_rate(_hw) container_of(_hw, struct clk_fixed_rate, hw)
+
+static unsigned long clk_fixed_rate_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	return to_clk_fixed_rate(hw)->fixed_rate;
+}
+EXPORT_SYMBOL_GPL(clk_fixed_rate_recalc_rate);
+
+struct clk_ops clk_fixed_rate_ops = {
+	.recalc_rate = clk_fixed_rate_recalc_rate,
+};
+EXPORT_SYMBOL_GPL(clk_fixed_rate_ops);
+
+struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
+		const char *parent_name, unsigned long flags,
+		unsigned long fixed_rate)
+{
+	struct clk_fixed_rate *fixed;
+	char **parent_names = NULL;
+	u8 len;
+
+	fixed = kzalloc(sizeof(struct clk_fixed_rate), GFP_KERNEL);
+
+	if (!fixed) {
+		pr_err("%s: could not allocate fixed clk\n", __func__);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* struct clk_fixed_rate assignments */
+	fixed->fixed_rate = fixed_rate;
+
+	if (parent_name) {
+		parent_names = kmalloc(sizeof(char *), GFP_KERNEL);
+
+		if (! parent_names)
+			goto out;
+
+		len = sizeof(char) * strlen(parent_name);
+
+		parent_names[0] = kmalloc(len, GFP_KERNEL);
+
+		if (!parent_names[0])
+			goto out;
+
+		strncpy(parent_names[0], parent_name, len);
+	}
+
+out:
+	return clk_register(dev, name,
+			&clk_fixed_rate_ops, &fixed->hw,
+			parent_names,
+			(parent_name ? 1 : 0),
+			flags);
+}
diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c
new file mode 100644
index 000000000000..b5902e2ef2fd
--- /dev/null
+++ b/drivers/clk/clk-gate.c
@@ -0,0 +1,150 @@
+/*
+ * Copyright (C) 2010-2011 Canonical Ltd <jeremy.kerr@canonical.com>
+ * Copyright (C) 2011-2012 Mike Turquette, Linaro Ltd <mturquette@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Gated clock implementation
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/string.h>
+
+/**
+ * DOC: basic gatable clock which can gate and ungate it's ouput
+ *
+ * Traits of this clock:
+ * prepare - clk_(un)prepare only ensures parent is (un)prepared
+ * enable - clk_enable and clk_disable are functional & control gating
+ * rate - inherits rate from parent.  No clk_set_rate support
+ * parent - fixed parent.  No clk_set_parent support
+ */
+
+#define to_clk_gate(_hw) container_of(_hw, struct clk_gate, hw)
+
+static void clk_gate_set_bit(struct clk_gate *gate)
+{
+	u32 reg;
+	unsigned long flags = 0;
+
+	if (gate->lock)
+		spin_lock_irqsave(gate->lock, flags);
+
+	reg = readl(gate->reg);
+	reg |= BIT(gate->bit_idx);
+	writel(reg, gate->reg);
+
+	if (gate->lock)
+		spin_unlock_irqrestore(gate->lock, flags);
+}
+
+static void clk_gate_clear_bit(struct clk_gate *gate)
+{
+	u32 reg;
+	unsigned long flags = 0;
+
+	if (gate->lock)
+		spin_lock_irqsave(gate->lock, flags);
+
+	reg = readl(gate->reg);
+	reg &= ~BIT(gate->bit_idx);
+	writel(reg, gate->reg);
+
+	if (gate->lock)
+		spin_unlock_irqrestore(gate->lock, flags);
+}
+
+static int clk_gate_enable(struct clk_hw *hw)
+{
+	struct clk_gate *gate = to_clk_gate(hw);
+
+	if (gate->flags & CLK_GATE_SET_TO_DISABLE)
+		clk_gate_clear_bit(gate);
+	else
+		clk_gate_set_bit(gate);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(clk_gate_enable);
+
+static void clk_gate_disable(struct clk_hw *hw)
+{
+	struct clk_gate *gate = to_clk_gate(hw);
+
+	if (gate->flags & CLK_GATE_SET_TO_DISABLE)
+		clk_gate_set_bit(gate);
+	else
+		clk_gate_clear_bit(gate);
+}
+EXPORT_SYMBOL_GPL(clk_gate_disable);
+
+static int clk_gate_is_enabled(struct clk_hw *hw)
+{
+	u32 reg;
+	struct clk_gate *gate = to_clk_gate(hw);
+
+	reg = readl(gate->reg);
+
+	/* if a set bit disables this clk, flip it before masking */
+	if (gate->flags & CLK_GATE_SET_TO_DISABLE)
+		reg ^= BIT(gate->bit_idx);
+
+	reg &= BIT(gate->bit_idx);
+
+	return reg ? 1 : 0;
+}
+EXPORT_SYMBOL_GPL(clk_gate_is_enabled);
+
+struct clk_ops clk_gate_ops = {
+	.enable = clk_gate_enable,
+	.disable = clk_gate_disable,
+	.is_enabled = clk_gate_is_enabled,
+};
+EXPORT_SYMBOL_GPL(clk_gate_ops);
+
+struct clk *clk_register_gate(struct device *dev, const char *name,
+		const char *parent_name, unsigned long flags,
+		void __iomem *reg, u8 bit_idx,
+		u8 clk_gate_flags, spinlock_t *lock)
+{
+	struct clk_gate *gate;
+	struct clk *clk;
+
+	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
+
+	if (!gate) {
+		pr_err("%s: could not allocate gated clk\n", __func__);
+		return NULL;
+	}
+
+	/* struct clk_gate assignments */
+	gate->reg = reg;
+	gate->bit_idx = bit_idx;
+	gate->flags = clk_gate_flags;
+	gate->lock = lock;
+
+	if (parent_name) {
+		gate->parent[0] = kstrdup(parent_name, GFP_KERNEL);
+		if (!gate->parent[0])
+			goto out;
+	}
+
+	clk = clk_register(dev, name,
+			&clk_gate_ops, &gate->hw,
+			gate->parent,
+			(parent_name ? 1 : 0),
+			flags);
+	if (clk)
+		return clk;
+out:
+	kfree(gate->parent[0]);
+	kfree(gate);
+
+	return NULL;
+}
diff --git a/drivers/clk/clk-mux.c b/drivers/clk/clk-mux.c
new file mode 100644
index 000000000000..c71ad1f41a97
--- /dev/null
+++ b/drivers/clk/clk-mux.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright (C) 2011 Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>
+ * Copyright (C) 2011 Richard Zhao, Linaro <richard.zhao@linaro.org>
+ * Copyright (C) 2011-2012 Mike Turquette, Linaro Ltd <mturquette@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Simple multiplexer clock implementation
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/err.h>
+
+/*
+ * DOC: basic adjustable multiplexer clock that cannot gate
+ *
+ * Traits of this clock:
+ * prepare - clk_prepare only ensures that parents are prepared
+ * enable - clk_enable only ensures that parents are enabled
+ * rate - rate is only affected by parent switching.  No clk_set_rate support
+ * parent - parent is adjustable through clk_set_parent
+ */
+
+#define to_clk_mux(_hw) container_of(_hw, struct clk_mux, hw)
+
+static u8 clk_mux_get_parent(struct clk_hw *hw)
+{
+	struct clk_mux *mux = to_clk_mux(hw);
+	u32 val;
+
+	/*
+	 * FIXME need a mux-specific flag to determine if val is bitwise or numeric
+	 * e.g. sys_clkin_ck's clksel field is 3 bits wide, but ranges from 0x1
+	 * to 0x7 (index starts at one)
+	 * OTOH, pmd_trace_clk_mux_ck uses a separate bit for each clock, so
+	 * val = 0x4 really means "bit 2, index starts at bit 0"
+	 */
+	val = readl(mux->reg) >> mux->shift;
+	val &= (1 << mux->width) - 1;
+
+	if (val && (mux->flags & CLK_MUX_INDEX_BIT))
+		val = ffs(val) - 1;
+
+	if (val && (mux->flags & CLK_MUX_INDEX_ONE))
+		val--;
+
+	if (val >= __clk_get_num_parents(hw->clk))
+		return -EINVAL;
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(clk_mux_get_parent);
+
+static int clk_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_mux *mux = to_clk_mux(hw);
+	u32 val;
+	unsigned long flags = 0;
+
+	if (mux->flags & CLK_MUX_INDEX_BIT)
+		index = (1 << ffs(index));
+
+	if (mux->flags & CLK_MUX_INDEX_ONE)
+		index++;
+
+	if (mux->lock)
+		spin_lock_irqsave(mux->lock, flags);
+
+	val = readl(mux->reg);
+	val &= ~(((1 << mux->width) - 1) << mux->shift);
+	val |= index << mux->shift;
+	writel(val, mux->reg);
+
+	if (mux->lock)
+		spin_unlock_irqrestore(mux->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(clk_mux_set_parent);
+
+struct clk_ops clk_mux_ops = {
+	.get_parent = clk_mux_get_parent,
+	.set_parent = clk_mux_set_parent,
+};
+EXPORT_SYMBOL_GPL(clk_mux_ops);
+
+struct clk *clk_register_mux(struct device *dev, const char *name,
+		char **parent_names, u8 num_parents, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width,
+		u8 clk_mux_flags, spinlock_t *lock)
+{
+	struct clk_mux *mux;
+
+	mux = kmalloc(sizeof(struct clk_mux), GFP_KERNEL);
+
+	if (!mux) {
+		pr_err("%s: could not allocate mux clk\n", __func__);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* struct clk_mux assignments */
+	mux->reg = reg;
+	mux->shift = shift;
+	mux->width = width;
+	mux->flags = clk_mux_flags;
+	mux->lock = lock;
+
+	return clk_register(dev, name, &clk_mux_ops, &mux->hw,
+			parent_names, num_parents, flags);
+}
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
new file mode 100644
index 000000000000..9cf6f59e3e19
--- /dev/null
+++ b/drivers/clk/clk.c
@@ -0,0 +1,1461 @@
+/*
+ * Copyright (C) 2010-2011 Canonical Ltd <jeremy.kerr@canonical.com>
+ * Copyright (C) 2011-2012 Linaro Ltd <mturquette@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Standard functionality for the common clock API.  See Documentation/clk.txt
+ */
+
+#include <linux/clk-private.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/err.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+static DEFINE_SPINLOCK(enable_lock);
+static DEFINE_MUTEX(prepare_lock);
+
+static HLIST_HEAD(clk_root_list);
+static HLIST_HEAD(clk_orphan_list);
+static LIST_HEAD(clk_notifier_list);
+
+/***        debugfs support        ***/
+
+#ifdef CONFIG_COMMON_CLK_DEBUG
+#include <linux/debugfs.h>
+
+static struct dentry *rootdir;
+static struct dentry *orphandir;
+static int inited = 0;
+
+/* caller must hold prepare_lock */
+static int clk_debug_create_one(struct clk *clk, struct dentry *pdentry)
+{
+	struct dentry *d;
+	int ret = -ENOMEM;
+
+	if (!clk || !pdentry) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	d = debugfs_create_dir(clk->name, pdentry);
+	if (!d)
+		goto out;
+
+	clk->dentry = d;
+
+	d = debugfs_create_u32("clk_rate", S_IRUGO, clk->dentry,
+			(u32 *)&clk->rate);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_x32("clk_flags", S_IRUGO, clk->dentry,
+			(u32 *)&clk->flags);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_prepare_count", S_IRUGO, clk->dentry,
+			(u32 *)&clk->prepare_count);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_enable_count", S_IRUGO, clk->dentry,
+			(u32 *)&clk->enable_count);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_notifier_count", S_IRUGO, clk->dentry,
+			(u32 *)&clk->notifier_count);
+	if (!d)
+		goto err_out;
+
+	ret = 0;
+	goto out;
+
+err_out:
+	debugfs_remove(clk->dentry);
+out:
+	return ret;
+}
+
+/* caller must hold prepare_lock */
+static int clk_debug_create_subtree(struct clk *clk, struct dentry *pdentry)
+{
+	struct clk *child;
+	struct hlist_node *tmp;
+	int ret = -EINVAL;;
+
+	if (!clk || !pdentry)
+		goto out;
+
+	ret = clk_debug_create_one(clk, pdentry);
+
+	if (ret)
+		goto out;
+
+	hlist_for_each_entry(child, tmp, &clk->children, child_node)
+		clk_debug_create_subtree(child, clk->dentry);
+
+	ret = 0;
+out:
+	return ret;
+}
+
+/**
+ * clk_debug_register - add a clk node to the debugfs clk tree
+ * @clk: the clk being added to the debugfs clk tree
+ *
+ * Dynamically adds a clk to the debugfs clk tree if debugfs has been
+ * initialized.  Otherwise it bails out early since the debugfs clk tree
+ * will be created lazily by clk_debug_init as part of a late_initcall.
+ *
+ * Caller must hold prepare_lock.  Only clk_init calls this function (so
+ * far) so this is taken care.
+ */
+static int clk_debug_register(struct clk *clk)
+{
+	struct clk *parent;
+	struct dentry *pdentry;
+	int ret = 0;
+
+	if (!inited)
+		goto out;
+
+	parent = clk->parent;
+
+	/*
+	 * Check to see if a clk is a root clk.  Also check that it is
+	 * safe to add this clk to debugfs
+	 */
+	if (!parent)
+		if (clk->flags & CLK_IS_ROOT)
+			pdentry = rootdir;
+		else
+			pdentry = orphandir;
+	else
+		if (parent->dentry)
+			pdentry = parent->dentry;
+		else
+			goto out;
+
+	ret = clk_debug_create_subtree(clk, pdentry);
+
+out:
+	return ret;
+}
+
+/**
+ * clk_debug_init - lazily create the debugfs clk tree visualization
+ *
+ * clks are often initialized very early during boot before memory can
+ * be dynamically allocated and well before debugfs is setup.
+ * clk_debug_init walks the clk tree hierarchy while holding
+ * prepare_lock and creates the topology as part of a late_initcall,
+ * thus insuring that clks initialized very early will still be
+ * represented in the debugfs clk tree.  This function should only be
+ * called once at boot-time, and all other clks added dynamically will
+ * be done so with clk_debug_register.
+ */
+static int __init clk_debug_init(void)
+{
+	struct clk *clk;
+	struct hlist_node *tmp;
+
+	rootdir = debugfs_create_dir("clk", NULL);
+
+	if (!rootdir)
+		return -ENOMEM;
+
+	orphandir = debugfs_create_dir("orphans", rootdir);
+
+	if (!orphandir)
+		return -ENOMEM;
+
+	mutex_lock(&prepare_lock);
+
+	hlist_for_each_entry(clk, tmp, &clk_root_list, child_node)
+		clk_debug_create_subtree(clk, rootdir);
+
+	hlist_for_each_entry(clk, tmp, &clk_orphan_list, child_node)
+		clk_debug_create_subtree(clk, orphandir);
+
+	inited = 1;
+
+	mutex_unlock(&prepare_lock);
+
+	return 0;
+}
+late_initcall(clk_debug_init);
+#else
+static inline int clk_debug_register(struct clk *clk) { return 0; }
+#endif /* CONFIG_COMMON_CLK_DEBUG */
+
+#ifdef CONFIG_COMMON_CLK_DISABLE_UNUSED
+/* caller must hold prepare_lock */
+static void clk_disable_unused_subtree(struct clk *clk)
+{
+	struct clk *child;
+	struct hlist_node *tmp;
+	unsigned long flags;
+
+	if (!clk)
+		goto out;
+
+	hlist_for_each_entry(child, tmp, &clk->children, child_node)
+		clk_disable_unused_subtree(child);
+
+	spin_lock_irqsave(&enable_lock, flags);
+
+	if (clk->enable_count)
+		goto unlock_out;
+
+	if (clk->flags & CLK_IGNORE_UNUSED)
+		goto unlock_out;
+
+	if (__clk_is_enabled(clk) && clk->ops->disable)
+		clk->ops->disable(clk->hw);
+
+unlock_out:
+	spin_unlock_irqrestore(&enable_lock, flags);
+
+out:
+	return;
+}
+
+static int clk_disable_unused(void)
+{
+	struct clk *clk;
+	struct hlist_node *tmp;
+
+	mutex_lock(&prepare_lock);
+
+	hlist_for_each_entry(clk, tmp, &clk_root_list, child_node)
+		clk_disable_unused_subtree(clk);
+
+	hlist_for_each_entry(clk, tmp, &clk_orphan_list, child_node)
+		clk_disable_unused_subtree(clk);
+
+	mutex_unlock(&prepare_lock);
+
+	return 0;
+}
+late_initcall(clk_disable_unused);
+#else
+static inline int clk_disable_unused(struct clk *clk) { return 0; }
+#endif /* CONFIG_COMMON_CLK_DISABLE_UNUSED */
+
+/***    helper functions   ***/
+
+inline const char *__clk_get_name(struct clk *clk)
+{
+	return !clk ? NULL : clk->name;
+}
+
+inline struct clk_hw *__clk_get_hw(struct clk *clk)
+{
+	return !clk ? NULL : clk->hw;
+}
+
+inline u8 __clk_get_num_parents(struct clk *clk)
+{
+	return !clk ? -EINVAL : clk->num_parents;
+}
+
+inline struct clk *__clk_get_parent(struct clk *clk)
+{
+	return !clk ? NULL : clk->parent;
+}
+
+inline int __clk_get_enable_count(struct clk *clk)
+{
+	return !clk ? -EINVAL : clk->enable_count;
+}
+
+inline int __clk_get_prepare_count(struct clk *clk)
+{
+	return !clk ? -EINVAL : clk->prepare_count;
+}
+
+unsigned long __clk_get_rate(struct clk *clk)
+{
+	unsigned long ret;
+
+	if (!clk) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = clk->rate;
+
+	if (clk->flags & CLK_IS_ROOT)
+		goto out;
+
+	if (!clk->parent)
+		ret = -ENODEV;
+
+out:
+	return ret;
+}
+
+inline unsigned long __clk_get_flags(struct clk *clk)
+{
+	return !clk ? -EINVAL : clk->flags;
+}
+
+int __clk_is_enabled(struct clk *clk)
+{
+	int ret;
+
+	if (!clk)
+		return -EINVAL;
+
+	/*
+	 * .is_enabled is only mandatory for clocks that gate
+	 * fall back to software usage counter if .is_enabled is missing
+	 */
+	if (!clk->ops->is_enabled) {
+		ret = clk->enable_count ? 1 : 0;
+		goto out;
+	}
+
+	ret = clk->ops->is_enabled(clk->hw);
+out:
+	return ret;
+}
+
+static struct clk *__clk_lookup_subtree(const char *name, struct clk *clk)
+{
+	struct clk *child;
+	struct clk *ret;
+	struct hlist_node *tmp;
+
+	if (!strcmp(clk->name, name))
+		return clk;
+
+	hlist_for_each_entry(child, tmp, &clk->children, child_node) {
+		ret = __clk_lookup_subtree(name, child);
+		if (ret)
+			return ret;
+	}
+
+	return NULL;
+}
+
+struct clk *__clk_lookup(const char *name)
+{
+	struct clk *root_clk;
+	struct clk *ret;
+	struct hlist_node *tmp;
+
+	if (!name)
+		return NULL;
+
+	/* search the 'proper' clk tree first */
+	hlist_for_each_entry(root_clk, tmp, &clk_root_list, child_node) {
+		ret = __clk_lookup_subtree(name, root_clk);
+		if (ret)
+			return ret;
+	}
+
+	/* if not found, then search the orphan tree */
+	hlist_for_each_entry(root_clk, tmp, &clk_orphan_list, child_node) {
+		ret = __clk_lookup_subtree(name, root_clk);
+		if (ret)
+			return ret;
+	}
+
+	return NULL;
+}
+
+/***        clk api        ***/
+
+void __clk_unprepare(struct clk *clk)
+{
+	if (!clk)
+		return;
+
+	if (WARN_ON(clk->prepare_count == 0))
+		return;
+
+	if (--clk->prepare_count > 0)
+		return;
+
+	WARN_ON(clk->enable_count > 0);
+
+	if (clk->ops->unprepare)
+		clk->ops->unprepare(clk->hw);
+
+	__clk_unprepare(clk->parent);
+}
+
+/**
+ * clk_unprepare - undo preparation of a clock source
+ * @clk: the clk being unprepare
+ *
+ * clk_unprepare may sleep, which differentiates it from clk_disable.  In a
+ * simple case, clk_unprepare can be used instead of clk_disable to gate a clk
+ * if the operation may sleep.  One example is a clk which is accessed over
+ * I2c.  In the complex case a clk gate operation may require a fast and a slow
+ * part.  It is this reason that clk_unprepare and clk_disable are not mutually
+ * exclusive.  In fact clk_disable must be called before clk_unprepare.
+ */
+void clk_unprepare(struct clk *clk)
+{
+	mutex_lock(&prepare_lock);
+	__clk_unprepare(clk);
+	mutex_unlock(&prepare_lock);
+}
+EXPORT_SYMBOL_GPL(clk_unprepare);
+
+int __clk_prepare(struct clk *clk)
+{
+	int ret = 0;
+
+	if (!clk)
+		return 0;
+
+	if (clk->prepare_count == 0) {
+		ret = __clk_prepare(clk->parent);
+		if (ret)
+			return ret;
+
+		if (clk->ops->prepare) {
+			ret = clk->ops->prepare(clk->hw);
+			if (ret) {
+				__clk_unprepare(clk->parent);
+				return ret;
+			}
+		}
+	}
+
+	clk->prepare_count++;
+
+	return 0;
+}
+
+/**
+ * clk_prepare - prepare a clock source
+ * @clk: the clk being prepared
+ *
+ * clk_prepare may sleep, which differentiates it from clk_enable.  In a simple
+ * case, clk_prepare can be used instead of clk_enable to ungate a clk if the
+ * operation may sleep.  One example is a clk which is accessed over I2c.  In
+ * the complex case a clk ungate operation may require a fast and a slow part.
+ * It is this reason that clk_prepare and clk_enable are not mutually
+ * exclusive.  In fact clk_prepare must be called before clk_enable.
+ * Returns 0 on success, -EERROR otherwise.
+ */
+int clk_prepare(struct clk *clk)
+{
+	int ret;
+
+	mutex_lock(&prepare_lock);
+	ret = __clk_prepare(clk);
+	mutex_unlock(&prepare_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_prepare);
+
+static void __clk_disable(struct clk *clk)
+{
+	if (!clk)
+		return;
+
+	if (WARN_ON(clk->enable_count == 0))
+		return;
+
+	if (--clk->enable_count > 0)
+		return;
+
+	if (clk->ops->disable)
+		clk->ops->disable(clk->hw);
+
+	__clk_disable(clk->parent);
+}
+
+/**
+ * clk_disable - gate a clock
+ * @clk: the clk being gated
+ *
+ * clk_disable must not sleep, which differentiates it from clk_unprepare.  In
+ * a simple case, clk_disable can be used instead of clk_unprepare to gate a
+ * clk if the operation is fast and will never sleep.  One example is a
+ * SoC-internal clk which is controlled via simple register writes.  In the
+ * complex case a clk gate operation may require a fast and a slow part.  It is
+ * this reason that clk_unprepare and clk_disable are not mutually exclusive.
+ * In fact clk_disable must be called before clk_unprepare.
+ */
+void clk_disable(struct clk *clk)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&enable_lock, flags);
+	__clk_disable(clk);
+	spin_unlock_irqrestore(&enable_lock, flags);
+}
+EXPORT_SYMBOL_GPL(clk_disable);
+
+static int __clk_enable(struct clk *clk)
+{
+	int ret = 0;
+
+	if (!clk)
+		return 0;
+
+	if (WARN_ON(clk->prepare_count == 0))
+		return -ESHUTDOWN;
+
+	if (clk->enable_count == 0) {
+		ret = __clk_enable(clk->parent);
+
+		if (ret)
+			return ret;
+
+		if (clk->ops->enable) {
+			ret = clk->ops->enable(clk->hw);
+			if (ret) {
+				__clk_disable(clk->parent);
+				return ret;
+			}
+		}
+	}
+
+	clk->enable_count++;
+	return 0;
+}
+
+/**
+ * clk_enable - ungate a clock
+ * @clk: the clk being ungated
+ *
+ * clk_enable must not sleep, which differentiates it from clk_prepare.  In a
+ * simple case, clk_enable can be used instead of clk_prepare to ungate a clk
+ * if the operation will never sleep.  One example is a SoC-internal clk which
+ * is controlled via simple register writes.  In the complex case a clk ungate
+ * operation may require a fast and a slow part.  It is this reason that
+ * clk_enable and clk_prepare are not mutually exclusive.  In fact clk_prepare
+ * must be called before clk_enable.  Returns 0 on success, -EERROR
+ * otherwise.
+ */
+int clk_enable(struct clk *clk)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&enable_lock, flags);
+	ret = __clk_enable(clk);
+	spin_unlock_irqrestore(&enable_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_enable);
+
+/**
+ * clk_get_rate - return the rate of clk
+ * @clk: the clk whose rate is being returned
+ *
+ * Simply returns the cached rate of the clk.  Does not query the hardware.  If
+ * clk is NULL then returns -EINVAL.
+ */
+unsigned long clk_get_rate(struct clk *clk)
+{
+	unsigned long rate;
+
+	mutex_lock(&prepare_lock);
+	rate = __clk_get_rate(clk);
+	mutex_unlock(&prepare_lock);
+
+	return rate;
+}
+EXPORT_SYMBOL_GPL(clk_get_rate);
+
+/**
+ * __clk_round_rate - round the given rate for a clk
+ * @clk: round the rate of this clock
+ *
+ * Caller must hold prepare_lock.  Useful for clk_ops such as .set_rate
+ */
+unsigned long __clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	unsigned long unused;
+
+	if (!clk)
+		return -EINVAL;
+
+	if (!clk->ops->round_rate)
+		return clk->rate;
+
+	if (clk->flags & CLK_SET_RATE_PARENT)
+		return clk->ops->round_rate(clk->hw, rate, &unused);
+	else
+		return clk->ops->round_rate(clk->hw, rate, NULL);
+}
+
+/**
+ * clk_round_rate - round the given rate for a clk
+ * @clk: the clk for which we are rounding a rate
+ * @rate: the rate which is to be rounded
+ *
+ * Takes in a rate as input and rounds it to a rate that the clk can actually
+ * use which is then returned.  If clk doesn't support round_rate operation
+ * then the parent rate is returned.
+ */
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	unsigned long ret;
+
+	mutex_lock(&prepare_lock);
+	ret = __clk_round_rate(clk, rate);
+	mutex_unlock(&prepare_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_round_rate);
+
+/**
+ * __clk_notify - call clk notifier chain
+ * @clk: struct clk * that is changing rate
+ * @msg: clk notifier type (see include/linux/clk.h)
+ * @old_rate: old clk rate
+ * @new_rate: new clk rate
+ *
+ * Triggers a notifier call chain on the clk rate-change notification
+ * for 'clk'.  Passes a pointer to the struct clk and the previous
+ * and current rates to the notifier callback.  Intended to be called by
+ * internal clock code only.  Returns NOTIFY_DONE from the last driver
+ * called if all went well, or NOTIFY_STOP or NOTIFY_BAD immediately if
+ * a driver returns that.
+ */
+static int __clk_notify(struct clk *clk, unsigned long msg,
+		unsigned long old_rate, unsigned long new_rate)
+{
+	struct clk_notifier *cn;
+	struct clk_notifier_data cnd;
+	int ret = NOTIFY_DONE;
+
+	cnd.clk = clk;
+	cnd.old_rate = old_rate;
+	cnd.new_rate = new_rate;
+
+	list_for_each_entry(cn, &clk_notifier_list, node) {
+		if (cn->clk == clk) {
+			ret = srcu_notifier_call_chain(&cn->notifier_head, msg,
+					&cnd);
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * __clk_recalc_rates
+ * @clk: first clk in the subtree
+ * @msg: notification type (see include/linux/clk.h)
+ *
+ * Walks the subtree of clks starting with clk and recalculates rates as it
+ * goes.  Note that if a clk does not implement the .recalc_rate callback then
+ * it is assumed that the clock will take on the rate of it's parent.
+ *
+ * clk_recalc_rates also propagates the POST_RATE_CHANGE notification,
+ * if necessary.
+ *
+ * Caller must hold prepare_lock.
+ */
+static void __clk_recalc_rates(struct clk *clk, unsigned long msg)
+{
+	unsigned long old_rate;
+	unsigned long parent_rate = 0;
+	struct hlist_node *tmp;
+	struct clk *child;
+
+	old_rate = clk->rate;
+
+	if (clk->parent)
+		parent_rate = clk->parent->rate;
+
+	if (clk->ops->recalc_rate)
+		clk->rate = clk->ops->recalc_rate(clk->hw, parent_rate);
+	else
+		clk->rate = parent_rate;
+
+	/*
+	 * ignore NOTIFY_STOP and NOTIFY_BAD return values for POST_RATE_CHANGE
+	 * & ABORT_RATE_CHANGE notifiers
+	 */
+	if (clk->notifier_count && msg)
+		__clk_notify(clk, msg, old_rate, clk->rate);
+
+	hlist_for_each_entry(child, tmp, &clk->children, child_node)
+		__clk_recalc_rates(child, msg);
+}
+
+/**
+ * __clk_speculate_rates
+ * @clk: first clk in the subtree
+ * @parent_rate: the "future" rate of clk's parent
+ *
+ * Walks the subtree of clks starting with clk, speculating rates as it
+ * goes and firing off PRE_RATE_CHANGE notifications as necessary.
+ *
+ * Unlike clk_recalc_rates, clk_speculate_rates exists only for sending
+ * pre-rate change notifications and returns early if no clks in the
+ * subtree have subscribed to the notifications.  Note that if a clk does not
+ * implement the .recalc_rate callback then it is assumed that the clock will
+ * take on the rate of it's parent.
+ *
+ * Caller must hold prepare_lock.
+ */
+static int __clk_speculate_rates(struct clk *clk, unsigned long parent_rate)
+{
+	struct hlist_node *tmp;
+	struct clk *child;
+	unsigned long new_rate;
+	int ret = NOTIFY_DONE;
+
+	if (clk->ops->recalc_rate)
+		new_rate = clk->ops->recalc_rate(clk->hw, parent_rate);
+	else
+		new_rate = parent_rate;
+
+	/* abort the rate change if a driver returns NOTIFY_BAD */
+	if (clk->notifier_count)
+		ret = __clk_notify(clk, PRE_RATE_CHANGE, clk->rate, new_rate);
+
+	if (ret == NOTIFY_BAD)
+		goto out;
+
+	hlist_for_each_entry(child, tmp, &clk->children, child_node) {
+		ret = __clk_speculate_rates(child, new_rate);
+		if (ret == NOTIFY_BAD)
+			break;
+	}
+
+out:
+	return ret;
+}
+
+static void clk_calc_subtree(struct clk *clk, unsigned long new_rate)
+{
+	struct clk *child;
+	struct hlist_node *tmp;
+
+	clk->new_rate = new_rate;
+
+	hlist_for_each_entry(child, tmp, &clk->children, child_node) {
+		if (child->ops->recalc_rate)
+			child->new_rate = child->ops->recalc_rate(child->hw, new_rate);
+		else
+			child->new_rate = new_rate;
+		clk_calc_subtree(child, child->new_rate);
+	}
+}
+
+/*
+ * calculate the new rates returning the topmost clock that has to be
+ * changed.
+ */
+static struct clk *clk_calc_new_rates(struct clk *clk, unsigned long rate)
+{
+	struct clk *top = clk;
+	unsigned long best_parent_rate = clk->parent->rate;
+	unsigned long new_rate;
+
+	if (!clk->ops->round_rate && !(clk->flags & CLK_SET_RATE_PARENT)) {
+		clk->new_rate = clk->rate;
+		return NULL;
+	}
+
+	if (!clk->ops->round_rate && (clk->flags & CLK_SET_RATE_PARENT)) {
+		top = clk_calc_new_rates(clk->parent, rate);
+		new_rate = clk->new_rate = clk->parent->new_rate;
+
+		goto out;
+	}
+
+	if (clk->flags & CLK_SET_RATE_PARENT)
+		new_rate = clk->ops->round_rate(clk->hw, rate, &best_parent_rate);
+	else
+		new_rate = clk->ops->round_rate(clk->hw, rate, NULL);
+
+	if (best_parent_rate != clk->parent->rate) {
+		top = clk_calc_new_rates(clk->parent, best_parent_rate);
+
+		goto out;
+	}
+
+out:
+	clk_calc_subtree(clk, new_rate);
+
+	return top;
+}
+
+/*
+ * Notify about rate changes in a subtree. Always walk down the whole tree
+ * so that in case of an error we can walk down the whole tree again and
+ * abort the change.
+ */
+static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long event)
+{
+	struct hlist_node *tmp;
+	struct clk *child, *fail_clk = NULL;
+	int ret = NOTIFY_DONE;
+
+	if (clk->rate == clk->new_rate)
+		return 0;
+
+	if (clk->notifier_count) {
+		ret = __clk_notify(clk, event, clk->rate, clk->new_rate);
+		if (ret == NOTIFY_BAD)
+			fail_clk = clk;
+	}
+
+	hlist_for_each_entry(child, tmp, &clk->children, child_node) {
+		clk = clk_propagate_rate_change(child, event);
+		if (clk)
+			fail_clk = clk;
+	}
+
+	return fail_clk;
+}
+
+/*
+ * walk down a subtree and set the new rates notifying the rate
+ * change on the way
+ */
+static void clk_change_rate(struct clk *clk)
+{
+	struct clk *child;
+	unsigned long old_rate;
+	struct hlist_node *tmp;
+
+	old_rate = clk->rate;
+
+	if (clk->ops->set_rate)
+		clk->ops->set_rate(clk->hw, clk->new_rate);
+
+	if (clk->ops->recalc_rate)
+		clk->rate = clk->ops->recalc_rate(clk->hw,
+				clk->parent->rate);
+	else
+		clk->rate = clk->parent->rate;
+
+	if (clk->notifier_count && old_rate != clk->rate)
+		__clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate);
+
+	hlist_for_each_entry(child, tmp, &clk->children, child_node)
+		clk_change_rate(child);
+}
+
+/**
+ * clk_set_rate - specify a new rate for clk
+ * @clk: the clk whose rate is being changed
+ * @rate: the new rate for clk
+ *
+ * In the simplest case clk_set_rate will only change the rate of clk.
+ *
+ * If clk has the CLK_SET_RATE_GATE flag set and it is enabled this call
+ * will fail; only when the clk is disabled will it be able to change
+ * its rate.
+ *
+ * Setting the CLK_SET_RATE_PARENT flag allows clk_set_rate to
+ * recursively propagate up to clk's parent; whether or not this happens
+ * depends on the outcome of clk's .round_rate implementation.  If
+ * *parent_rate is 0 after calling .round_rate then upstream parent
+ * propagation is ignored.  If *parent_rate comes back with a new rate
+ * for clk's parent then we propagate up to clk's parent and set it's
+ * rate.  Upward propagation will continue until either a clk does not
+ * support the CLK_SET_RATE_PARENT flag or .round_rate stops requesting
+ * changes to clk's parent_rate.  If there is a failure during upstream
+ * propagation then clk_set_rate will unwind and restore each clk's rate
+ * that had been successfully changed.  Afterwards a rate change abort
+ * notification will be propagated downstream, starting from the clk
+ * that failed.
+ *
+ * At the end of all of the rate setting, clk_set_rate internally calls
+ * __clk_recalc_rates and propagates the rate changes downstream,
+ * starting from the highest clk whose rate was changed.  This has the
+ * added benefit of propagating post-rate change notifiers.
+ *
+ * Note that while post-rate change and rate change abort notifications
+ * are guaranteed to be sent to a clk only once per call to
+ * clk_set_rate, pre-change notifications will be sent for every clk
+ * whose rate is changed.  Stacking pre-change notifications is noisy
+ * for the drivers subscribed to them, but this allows drivers to react
+ * to intermediate clk rate changes up until the point where the final
+ * rate is achieved at the end of upstream propagation.
+ *
+ * Returns 0 on success, -EERROR otherwise.
+ */
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	struct clk *top, *fail_clk;
+	int ret = 0;
+
+	/* prevent racing with updates to the clock topology */
+	mutex_lock(&prepare_lock);
+
+	/* bail early if nothing to do */
+	if (rate == clk->rate)
+		goto out;
+
+	/* calculate new rates and get the topmost changed clock */
+	top = clk_calc_new_rates(clk, rate);
+	if (!top) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* notify that we are about to change rates */
+	fail_clk = clk_propagate_rate_change(top, PRE_RATE_CHANGE);
+	if (fail_clk) {
+		pr_warn("%s: failed to set %s rate\n", __func__,
+				fail_clk->name);
+		clk_propagate_rate_change(top, ABORT_RATE_CHANGE);
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* change the rates */
+	clk_change_rate(top);
+
+	mutex_unlock(&prepare_lock);
+
+	return 0;
+out:
+	mutex_unlock(&prepare_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_rate);
+
+/**
+ * clk_get_parent - return the parent of a clk
+ * @clk: the clk whose parent gets returned
+ *
+ * Simply returns clk->parent.  Returns NULL if clk is NULL.
+ */
+struct clk *clk_get_parent(struct clk *clk)
+{
+	struct clk *parent;
+
+	mutex_lock(&prepare_lock);
+	parent = __clk_get_parent(clk);
+	mutex_unlock(&prepare_lock);
+
+	return parent;
+}
+EXPORT_SYMBOL_GPL(clk_get_parent);
+
+/*
+ * .get_parent is mandatory for clocks with multiple possible parents.  It is
+ * optional for single-parent clocks.  Always call .get_parent if it is
+ * available and WARN if it is missing for multi-parent clocks.
+ *
+ * For single-parent clocks without .get_parent, first check to see if the
+ * .parents array exists, and if so use it to avoid an expensive tree
+ * traversal.  If .parents does not exist then walk the tree with __clk_lookup.
+ */
+static struct clk *__clk_init_parent(struct clk *clk)
+{
+	struct clk *ret = NULL;
+	u8 index;
+
+	/* handle the trivial cases */
+
+	if (!clk->num_parents)
+		goto out;
+
+	if (clk->num_parents == 1) {
+		if (IS_ERR_OR_NULL(clk->parent))
+			ret = clk->parent = __clk_lookup(clk->parent_names[0]);
+		ret = clk->parent;
+		goto out;
+	}
+
+	if (!clk->ops->get_parent) {
+		WARN(!clk->ops->get_parent,
+			"%s: multi-parent clocks must implement .get_parent\n",
+			__func__);
+		goto out;
+	};
+
+	/*
+	 * Do our best to cache parent clocks in clk->parents.  This prevents
+	 * unnecessary and expensive calls to __clk_lookup.  We don't set
+	 * clk->parent here; that is done by the calling function
+	 */
+
+	index = clk->ops->get_parent(clk->hw);
+
+	if (!clk->parents)
+		clk->parents =
+			kmalloc((sizeof(struct clk*) * clk->num_parents),
+					GFP_KERNEL);
+
+	if (!clk->parents)
+		ret = __clk_lookup(clk->parent_names[index]);
+	else if (!clk->parents[index])
+		ret = clk->parents[index] =
+			__clk_lookup(clk->parent_names[index]);
+	else
+		ret = clk->parents[index];
+
+out:
+	return ret;
+}
+
+void __clk_reparent(struct clk *clk, struct clk *new_parent)
+{
+#ifdef CONFIG_COMMON_CLK_DEBUG
+	struct dentry *d;
+	struct dentry *new_parent_d;
+#endif
+
+	if (!clk || !new_parent)
+		return;
+
+	hlist_del(&clk->child_node);
+
+	if (new_parent)
+		hlist_add_head(&clk->child_node, &new_parent->children);
+	else
+		hlist_add_head(&clk->child_node, &clk_orphan_list);
+
+#ifdef CONFIG_COMMON_CLK_DEBUG
+	if (!inited)
+		goto out;
+
+	if (new_parent)
+		new_parent_d = new_parent->dentry;
+	else
+		new_parent_d = orphandir;
+
+	d = debugfs_rename(clk->dentry->d_parent, clk->dentry,
+			new_parent_d, clk->name);
+	if (d)
+		clk->dentry = d;
+	else
+		pr_debug("%s: failed to rename debugfs entry for %s\n",
+				__func__, clk->name);
+out:
+#endif
+
+	clk->parent = new_parent;
+
+	__clk_recalc_rates(clk, POST_RATE_CHANGE);
+}
+
+static int __clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	struct clk *old_parent;
+	unsigned long flags;
+	int ret = -EINVAL;
+	u8 i;
+
+	old_parent = clk->parent;
+
+	/* find index of new parent clock using cached parent ptrs */
+	for (i = 0; i < clk->num_parents; i++)
+		if (clk->parents[i] == parent)
+			break;
+
+	/*
+	 * find index of new parent clock using string name comparison
+	 * also try to cache the parent to avoid future calls to __clk_lookup
+	 */
+	if (i == clk->num_parents)
+		for (i = 0; i < clk->num_parents; i++)
+			if (!strcmp(clk->parent_names[i], parent->name)) {
+				clk->parents[i] = __clk_lookup(parent->name);
+				break;
+			}
+
+	if (i == clk->num_parents) {
+		pr_debug("%s: clock %s is not a possible parent of clock %s\n",
+				__func__, parent->name, clk->name);
+		goto out;
+	}
+
+	/* migrate prepare and enable */
+	if (clk->prepare_count)
+		__clk_prepare(parent);
+
+	/* FIXME replace with clk_is_enabled(clk) someday */
+	spin_lock_irqsave(&enable_lock, flags);
+	if (clk->enable_count)
+		__clk_enable(parent);
+	spin_unlock_irqrestore(&enable_lock, flags);
+
+	/* change clock input source */
+	ret = clk->ops->set_parent(clk->hw, i);
+
+	/* clean up old prepare and enable */
+	spin_lock_irqsave(&enable_lock, flags);
+	if (clk->enable_count)
+		__clk_disable(old_parent);
+	spin_unlock_irqrestore(&enable_lock, flags);
+
+	if (clk->prepare_count)
+		__clk_unprepare(old_parent);
+
+out:
+	return ret;
+}
+
+/**
+ * clk_set_parent - switch the parent of a mux clk
+ * @clk: the mux clk whose input we are switching
+ * @parent: the new input to clk
+ *
+ * Re-parent clk to use parent as it's new input source.  If clk has the
+ * CLK_SET_PARENT_GATE flag set then clk must be gated for this
+ * operation to succeed.  After successfully changing clk's parent
+ * clk_set_parent will update the clk topology, sysfs topology and
+ * propagate rate recalculation via __clk_recalc_rates.  Returns 0 on
+ * success, -EERROR otherwise.
+ */
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	int ret = 0;
+
+	if (!clk || !clk->ops)
+		return -EINVAL;
+
+	if (!clk->ops->set_parent)
+		return -ENOSYS;
+
+	/* prevent racing with updates to the clock topology */
+	mutex_lock(&prepare_lock);
+
+	if (clk->parent == parent)
+		goto out;
+
+	/* propagate PRE_RATE_CHANGE notifications */
+	if (clk->notifier_count)
+		ret = __clk_speculate_rates(clk, parent->rate);
+
+	/* abort if a driver objects */
+	if (ret == NOTIFY_STOP)
+		goto out;
+
+	/* only re-parent if the clock is not in use */
+	if ((clk->flags & CLK_SET_PARENT_GATE) && clk->prepare_count)
+		ret = -EBUSY;
+	else
+		ret = __clk_set_parent(clk, parent);
+
+	/* propagate ABORT_RATE_CHANGE if .set_parent failed */
+	if (ret) {
+		__clk_recalc_rates(clk, ABORT_RATE_CHANGE);
+		goto out;
+	}
+
+	/* propagate rate recalculation downstream */
+	__clk_reparent(clk, parent);
+
+out:
+	mutex_unlock(&prepare_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_parent);
+
+/**
+ * __clk_init - initialize the data structures in a struct clk
+ * @dev:	device initializing this clk, placeholder for now
+ * @clk:	clk being initialized
+ *
+ * Initializes the lists in struct clk, queries the hardware for the
+ * parent and rate and sets them both.
+ *
+ * Any struct clk passed into __clk_init must have the following members
+ * populated:
+ * 	.name
+ * 	.ops
+ * 	.hw
+ * 	.parent_names
+ * 	.num_parents
+ * 	.flags
+ *
+ * Essentially, everything that would normally be passed into clk_register is
+ * assumed to be initialized already in __clk_init.  The other members may be
+ * populated, but are optional.
+ *
+ * __clk_init is only exposed via clk-private.h and is intended for use with
+ * very large numbers of clocks that need to be statically initialized.  It is
+ * a layering violation to include clk-private.h from any code which implements
+ * a clock's .ops; as such any statically initialized clock data MUST be in a
+ * separate C file from the logic that implements it's operations.
+ */
+void __clk_init(struct device *dev, struct clk *clk)
+{
+	int i;
+	struct clk *orphan;
+	struct hlist_node *tmp, *tmp2;
+
+	if (!clk)
+		return;
+
+	mutex_lock(&prepare_lock);
+
+	/* check to see if a clock with this name is already registered */
+	if (__clk_lookup(clk->name))
+		goto out;
+
+	/* throw a WARN if any entries in parent_names are NULL */
+	for (i = 0; i < clk->num_parents; i++)
+		WARN(!clk->parent_names[i],
+				"%s: invalid NULL in %s's .parent_names\n",
+				__func__, clk->name);
+
+	/*
+	 * Allocate an array of struct clk *'s to avoid unnecessary string
+	 * look-ups of clk's possible parents.  This can fail for clocks passed
+	 * in to clk_init during early boot; thus any access to clk->parents[]
+	 * must always check for a NULL pointer and try to populate it if
+	 * necessary.
+	 *
+	 * If clk->parents is not NULL we skip this entire block.  This allows
+	 * for clock drivers to statically initialize clk->parents.
+	 */
+	if (clk->num_parents && !clk->parents) {
+		clk->parents = kmalloc((sizeof(struct clk*) * clk->num_parents),
+				GFP_KERNEL);
+		/*
+		 * __clk_lookup returns NULL for parents that have not been
+		 * clk_init'd; thus any access to clk->parents[] must check
+		 * for a NULL pointer.  We can always perform lazy lookups for
+		 * missing parents later on.
+		 */
+		if (clk->parents)
+			for (i = 0; i < clk->num_parents; i++)
+				clk->parents[i] =
+					__clk_lookup(clk->parent_names[i]);
+	}
+
+	clk->parent = __clk_init_parent(clk);
+
+	/*
+	 * Populate clk->parent if parent has already been __clk_init'd.  If
+	 * parent has not yet been __clk_init'd then place clk in the orphan
+	 * list.  If clk has set the CLK_IS_ROOT flag then place it in the root
+	 * clk list.
+	 *
+	 * Every time a new clk is clk_init'd then we walk the list of orphan
+	 * clocks and re-parent any that are children of the clock currently
+	 * being clk_init'd.
+	 */
+	if (clk->parent)
+		hlist_add_head(&clk->child_node,
+				&clk->parent->children);
+	else if (clk->flags & CLK_IS_ROOT)
+		hlist_add_head(&clk->child_node, &clk_root_list);
+	else
+		hlist_add_head(&clk->child_node, &clk_orphan_list);
+
+	/*
+	 * Set clk's rate.  The preferred method is to use .recalc_rate.  For
+	 * simple clocks and lazy developers the default fallback is to use the
+	 * parent's rate.  If a clock doesn't have a parent (or is orphaned)
+	 * then rate is set to zero.
+	 */
+	if (clk->ops->recalc_rate)
+		clk->rate = clk->ops->recalc_rate(clk->hw,
+				__clk_get_rate(clk->parent));
+	else if (clk->parent)
+		clk->rate = clk->parent->rate;
+	else
+		clk->rate = 0;
+
+	/*
+	 * walk the list of orphan clocks and reparent any that are children of
+	 * this clock
+	 */
+	hlist_for_each_entry_safe(orphan, tmp, tmp2, &clk_orphan_list, child_node)
+		for (i = 0; i < orphan->num_parents; i++)
+			if (!strcmp(clk->name, orphan->parent_names[i])) {
+				__clk_reparent(orphan, clk);
+				break;
+			}
+
+	/*
+	 * optional platform-specific magic
+	 *
+	 * The .init callback is not used by any of the basic clock types, but
+	 * exists for weird hardware that must perform initialization magic.
+	 * Please consider other ways of solving initialization problems before
+	 * using this callback, as it's use is discouraged.
+	 */
+	if (clk->ops->init)
+		clk->ops->init(clk->hw);
+
+	clk_debug_register(clk);
+
+out:
+	mutex_unlock(&prepare_lock);
+
+	return;
+}
+
+/**
+ * clk_register - allocate a new clock, register it and return an opaque cookie
+ * @dev: device that is registering this clock
+ * @name: clock name
+ * @ops: operations this clock supports
+ * @hw: link to hardware-specific clock data
+ * @parent_names: array of string names for all possible parents
+ * @num_parents: number of possible parents
+ * @flags: framework-level hints and quirks
+ *
+ * clk_register is the primary interface for populating the clock tree with new
+ * clock nodes.  It returns a pointer to the newly allocated struct clk which
+ * cannot be dereferenced by driver code but may be used in conjuction with the
+ * rest of the clock API.
+ */
+struct clk *clk_register(struct device *dev, const char *name,
+		const struct clk_ops *ops, struct clk_hw *hw,
+		char **parent_names, u8 num_parents, unsigned long flags)
+{
+	struct clk *clk;
+
+	clk = kzalloc(sizeof(*clk), GFP_KERNEL);
+	if (!clk)
+		return NULL;
+
+	clk->name = name;
+	clk->ops = ops;
+	clk->hw = hw;
+	clk->flags = flags;
+	clk->parent_names = parent_names;
+	clk->num_parents = num_parents;
+	hw->clk = clk;
+
+	__clk_init(dev, clk);
+
+	return clk;
+}
+EXPORT_SYMBOL_GPL(clk_register);
+
+/***        clk rate change notifiers        ***/
+
+/**
+ * clk_notifier_register - add a clk rate change notifier
+ * @clk: struct clk * to watch
+ * @nb: struct notifier_block * with callback info
+ *
+ * Request notification when clk's rate changes.  This uses an SRCU
+ * notifier because we want it to block and notifier unregistrations are
+ * uncommon.  The callbacks associated with the notifier must not
+ * re-enter into the clk framework by calling any top-level clk APIs;
+ * this will cause a nested prepare_lock mutex.
+ *
+ * Pre-change notifier callbacks will be passed the current, pre-change
+ * rate of the clk via struct clk_notifier_data.old_rate.  The new,
+ * post-change rate of the clk is passed via struct
+ * clk_notifier_data.new_rate.
+ *
+ * Post-change notifiers will pass the now-current, post-change rate of
+ * the clk in both struct clk_notifier_data.old_rate and struct
+ * clk_notifier_data.new_rate.
+ *
+ * Abort-change notifiers are effectively the opposite of pre-change
+ * notifiers: the original pre-change clk rate is passed in via struct
+ * clk_notifier_data.new_rate and the failed post-change rate is passed
+ * in via struct clk_notifier_data.old_rate.
+ *
+ * clk_notifier_register() must be called from non-atomic context.
+ * Returns -EINVAL if called with null arguments, -ENOMEM upon
+ * allocation failure; otherwise, passes along the return value of
+ * srcu_notifier_chain_register().
+ */
+int clk_notifier_register(struct clk *clk, struct notifier_block *nb)
+{
+	struct clk_notifier *cn;
+	int ret = -ENOMEM;
+
+	if (!clk || !nb)
+		return -EINVAL;
+
+	mutex_lock(&prepare_lock);
+
+	/* search the list of notifiers for this clk */
+	list_for_each_entry(cn, &clk_notifier_list, node)
+		if (cn->clk == clk)
+			break;
+
+	/* if clk wasn't in the notifier list, allocate new clk_notifier */
+	if (cn->clk != clk) {
+		cn = kzalloc(sizeof(struct clk_notifier), GFP_KERNEL);
+		if (!cn)
+			goto out;
+
+		cn->clk = clk;
+		srcu_init_notifier_head(&cn->notifier_head);
+
+		list_add(&cn->node, &clk_notifier_list);
+	}
+
+	ret = srcu_notifier_chain_register(&cn->notifier_head, nb);
+
+	clk->notifier_count++;
+
+out:
+	mutex_unlock(&prepare_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_notifier_register);
+
+/**
+ * clk_notifier_unregister - remove a clk rate change notifier
+ * @clk: struct clk *
+ * @nb: struct notifier_block * with callback info
+ *
+ * Request no further notification for changes to 'clk' and frees memory
+ * allocated in clk_notifier_register.
+ *
+ * Returns -EINVAL if called with null arguments; otherwise, passes
+ * along the return value of srcu_notifier_chain_unregister().
+ */
+int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb)
+{
+	struct clk_notifier *cn = NULL;
+	int ret = -EINVAL;
+
+	if (!clk || !nb)
+		return -EINVAL;
+
+	mutex_lock(&prepare_lock);
+
+	list_for_each_entry(cn, &clk_notifier_list, node)
+		if (cn->clk == clk)
+			break;
+
+	if (cn->clk == clk) {
+		ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb);
+
+		clk->notifier_count--;
+
+		/* XXX the notifier code should handle this better */
+		if (!cn->notifier_head.head) {
+			srcu_cleanup_notifier_head(&cn->notifier_head);
+			kfree(cn);
+		}
+
+	} else {
+		ret = -ENOENT;
+	}
+
+	mutex_unlock(&prepare_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_notifier_unregister);
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 999d6a03e436..5138927a416c 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -26,7 +26,6 @@ config CLKSRC_DBX500_PRCMU
 config CLKSRC_DBX500_PRCMU_SCHED_CLOCK
 	bool "Clocksource PRCMU Timer sched_clock"
 	depends on (CLKSRC_DBX500_PRCMU && !NOMADIK_MTU_SCHED_CLOCK)
-	select HAVE_SCHED_CLOCK
 	default y
 	help
 	  Use the always on PRCMU Timer as sched_clock
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 32d790dd8180..ffbb44685915 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -51,9 +51,6 @@ config ARM_S5PV210_CPUFREQ
 config ARM_EXYNOS_CPUFREQ
 	bool "SAMSUNG EXYNOS SoCs"
 	depends on ARCH_EXYNOS
-	select ARM_EXYNOS4210_CPUFREQ if CPU_EXYNOS4210
-	select ARM_EXYNOS4X12_CPUFREQ if (SOC_EXYNOS4212 || SOC_EXYNOS4412)
-	select ARM_EXYNOS5250_CPUFREQ if SOC_EXYNOS5250
 	default y
 	help
 	  This adds the CPUFreq driver common part for Samsung
@@ -62,20 +59,19 @@ config ARM_EXYNOS_CPUFREQ
 	  If in doubt, say N.
 
 config ARM_EXYNOS4210_CPUFREQ
-	bool "Samsung EXYNOS4210"
-	depends on ARCH_EXYNOS
+	def_bool CPU_EXYNOS4210
 	help
 	  This adds the CPUFreq driver for Samsung EXYNOS4210
 	  SoC (S5PV310 or S5PC210).
 
 config ARM_EXYNOS4X12_CPUFREQ
-	bool "Samsung EXYNOS4X12"
+	def_bool (SOC_EXYNOS4212 || SOC_EXYNOS4412)
 	help
 	  This adds the CPUFreq driver for Samsung EXYNOS4X12
 	  SoC (EXYNOS4212 or EXYNOS4412).
 
 config ARM_EXYNOS5250_CPUFREQ
-	bool "Samsung EXYNOS5250"
+	def_bool SOC_EXYNOS5250
 	help
 	  This adds the CPUFreq driver for Samsung EXYNOS5250
 	  SoC.
diff --git a/drivers/cpufreq/db8500-cpufreq.c b/drivers/cpufreq/db8500-cpufreq.c
index f5002015d82e..0bf1b8910eeb 100644
--- a/drivers/cpufreq/db8500-cpufreq.c
+++ b/drivers/cpufreq/db8500-cpufreq.c
@@ -22,11 +22,11 @@ static struct cpufreq_frequency_table freq_table[] = {
 	},
 	[1] = {
 		.index = 1,
-		.frequency = 300000,
+		.frequency = 400000,
 	},
 	[2] = {
 		.index = 2,
-		.frequency = 600000,
+		.frequency = 800000,
 	},
 	[3] = {
 		/* Used for MAX_OPP, if available */
@@ -113,12 +113,9 @@ static int __cpuinit db8500_cpufreq_init(struct cpufreq_policy *policy)
 
 	BUILD_BUG_ON(ARRAY_SIZE(idx2opp) + 1 != ARRAY_SIZE(freq_table));
 
-	if (!prcmu_is_u8400()) {
-		freq_table[1].frequency = 400000;
-		freq_table[2].frequency = 800000;
-		if (prcmu_has_arm_maxopp())
-			freq_table[3].frequency = 1000000;
-	}
+	if (prcmu_has_arm_maxopp())
+		freq_table[3].frequency = 1000000;
+
 	pr_info("db8500-cpufreq : Available frequencies:\n");
 	for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
 		pr_info("  %d Mhz\n", freq_table[i].frequency/1000);
@@ -145,7 +142,7 @@ static int __cpuinit db8500_cpufreq_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = 20 * 1000; /* in ns */
 
 	/* policy sharing between dual CPUs */
-	cpumask_copy(policy->cpus, &cpu_present_map);
+	cpumask_copy(policy->cpus, cpu_present_mask);
 
 	policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
 
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 67bbb06d0460..17fa04d08be9 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -27,7 +27,6 @@
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
 
-#include <asm/system.h>
 #include <asm/smp_plat.h>
 #include <asm/cpu.h>
 
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index cf7e1ee005a2..334cc2f1e9f1 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -27,7 +27,6 @@
 
 #include <asm/timer.h>		/* Needed for recalibrate_cpu_khz() */
 #include <asm/msr.h>
-#include <asm/system.h>
 #include <asm/cpu_device_id.h>
 
 #ifdef CONFIG_X86_POWERNOW_K7_ACPI
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 6588f43017bd..87411cebc577 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -53,6 +53,52 @@ static void cpuidle_kick_cpus(void) {}
 
 static int __cpuidle_register_device(struct cpuidle_device *dev);
 
+static inline int cpuidle_enter(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int index)
+{
+	struct cpuidle_state *target_state = &drv->states[index];
+	return target_state->enter(dev, drv, index);
+}
+
+static inline int cpuidle_enter_tk(struct cpuidle_device *dev,
+			       struct cpuidle_driver *drv, int index)
+{
+	return cpuidle_wrap_enter(dev, drv, index, cpuidle_enter);
+}
+
+typedef int (*cpuidle_enter_t)(struct cpuidle_device *dev,
+			       struct cpuidle_driver *drv, int index);
+
+static cpuidle_enter_t cpuidle_enter_ops;
+
+/**
+ * cpuidle_play_dead - cpu off-lining
+ *
+ * Only returns in case of an error
+ */
+int cpuidle_play_dead(void)
+{
+	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_driver *drv = cpuidle_get_driver();
+	int i, dead_state = -1;
+	int power_usage = -1;
+
+	/* Find lowest-power state that supports long-term idle */
+	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
+
+		if (s->power_usage < power_usage && s->enter_dead) {
+			power_usage = s->power_usage;
+			dead_state = i;
+		}
+	}
+
+	if (dead_state != -1)
+		return drv->states[dead_state].enter_dead(dev, dead_state);
+
+	return -ENODEV;
+}
+
 /**
  * cpuidle_idle_call - the main idle loop
  *
@@ -63,7 +109,6 @@ int cpuidle_idle_call(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
 	struct cpuidle_driver *drv = cpuidle_get_driver();
-	struct cpuidle_state *target_state;
 	int next_state, entered_state;
 
 	if (off)
@@ -92,12 +137,10 @@ int cpuidle_idle_call(void)
 		return 0;
 	}
 
-	target_state = &drv->states[next_state];
-
 	trace_power_start_rcuidle(POWER_CSTATE, next_state, dev->cpu);
 	trace_cpu_idle_rcuidle(next_state, dev->cpu);
 
-	entered_state = target_state->enter(dev, drv, next_state);
+	entered_state = cpuidle_enter_ops(dev, drv, next_state);
 
 	trace_power_end_rcuidle(dev->cpu);
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
@@ -110,6 +153,8 @@ int cpuidle_idle_call(void)
 		dev->states_usage[entered_state].time +=
 				(unsigned long long)dev->last_residency;
 		dev->states_usage[entered_state].usage++;
+	} else {
+		dev->last_residency = 0;
 	}
 
 	/* give the governor an opportunity to reflect on the outcome */
@@ -164,6 +209,37 @@ void cpuidle_resume_and_unlock(void)
 
 EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock);
 
+/**
+ * cpuidle_wrap_enter - performs timekeeping and irqen around enter function
+ * @dev: pointer to a valid cpuidle_device object
+ * @drv: pointer to a valid cpuidle_driver object
+ * @index: index of the target cpuidle state.
+ */
+int cpuidle_wrap_enter(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int index,
+				int (*enter)(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index))
+{
+	ktime_t time_start, time_end;
+	s64 diff;
+
+	time_start = ktime_get();
+
+	index = enter(dev, drv, index);
+
+	time_end = ktime_get();
+
+	local_irq_enable();
+
+	diff = ktime_to_us(ktime_sub(time_end, time_start));
+	if (diff > INT_MAX)
+		diff = INT_MAX;
+
+	dev->last_residency = (int) diff;
+
+	return index;
+}
+
 #ifdef CONFIG_ARCH_HAS_CPU_RELAX
 static int poll_idle(struct cpuidle_device *dev,
 		struct cpuidle_driver *drv, int index)
@@ -197,6 +273,7 @@ static void poll_idle_init(struct cpuidle_driver *drv)
 	state->power_usage = -1;
 	state->flags = 0;
 	state->enter = poll_idle;
+	state->disable = 0;
 }
 #else
 static void poll_idle_init(struct cpuidle_driver *drv) {}
@@ -212,13 +289,14 @@ static void poll_idle_init(struct cpuidle_driver *drv) {}
 int cpuidle_enable_device(struct cpuidle_device *dev)
 {
 	int ret, i;
+	struct cpuidle_driver *drv = cpuidle_get_driver();
 
 	if (dev->enabled)
 		return 0;
-	if (!cpuidle_get_driver() || !cpuidle_curr_governor)
+	if (!drv || !cpuidle_curr_governor)
 		return -EIO;
 	if (!dev->state_count)
-		return -EINVAL;
+		dev->state_count = drv->state_count;
 
 	if (dev->registered == 0) {
 		ret = __cpuidle_register_device(dev);
@@ -226,13 +304,16 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 			return ret;
 	}
 
-	poll_idle_init(cpuidle_get_driver());
+	cpuidle_enter_ops = drv->en_core_tk_irqen ?
+		cpuidle_enter_tk : cpuidle_enter;
+
+	poll_idle_init(drv);
 
 	if ((ret = cpuidle_add_state_sysfs(dev)))
 		return ret;
 
 	if (cpuidle_curr_governor->enable &&
-	    (ret = cpuidle_curr_governor->enable(cpuidle_get_driver(), dev)))
+	    (ret = cpuidle_curr_governor->enable(drv, dev)))
 		goto fail_sysfs;
 
 	for (i = 0; i < dev->state_count; i++) {
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 284d7af5a9c8..40cd3f3024df 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -47,7 +47,7 @@ static void __cpuidle_register_driver(struct cpuidle_driver *drv)
  */
 int cpuidle_register_driver(struct cpuidle_driver *drv)
 {
-	if (!drv)
+	if (!drv || !drv->state_count)
 		return -EINVAL;
 
 	if (cpuidle_disabled())
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index ad0952601ae2..06335756ea14 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -236,7 +236,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = &__get_cpu_var(menu_devices);
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
-	unsigned int power_usage = -1;
+	int power_usage = -1;
 	int i;
 	int multiplier;
 	struct timespec t;
@@ -280,7 +280,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * We want to default to C1 (hlt), not to busy polling
 	 * unless the timer is happening really really soon.
 	 */
-	if (data->expected_us > 5)
+	if (data->expected_us > 5 &&
+		drv->states[CPUIDLE_DRIVER_STATE_START].disable == 0)
 		data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
 
 	/*
@@ -290,6 +291,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
 
+		if (s->disable)
+			continue;
 		if (s->target_residency > data->predicted_us)
 			continue;
 		if (s->exit_latency > latency_req)
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 3fe41fe4851a..88032b4dc6d2 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -11,6 +11,7 @@
 #include <linux/sysfs.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/capability.h>
 
 #include "cpuidle.h"
 
@@ -222,6 +223,9 @@ struct cpuidle_state_attr {
 #define define_one_state_ro(_name, show) \
 static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0444, show, NULL)
 
+#define define_one_state_rw(_name, show, store) \
+static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0644, show, store)
+
 #define define_show_state_function(_name) \
 static ssize_t show_state_##_name(struct cpuidle_state *state, \
 			 struct cpuidle_state_usage *state_usage, char *buf) \
@@ -229,6 +233,24 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \
 	return sprintf(buf, "%u\n", state->_name);\
 }
 
+#define define_store_state_function(_name) \
+static ssize_t store_state_##_name(struct cpuidle_state *state, \
+		const char *buf, size_t size) \
+{ \
+	long value; \
+	int err; \
+	if (!capable(CAP_SYS_ADMIN)) \
+		return -EPERM; \
+	err = kstrtol(buf, 0, &value); \
+	if (err) \
+		return err; \
+	if (value) \
+		state->disable = 1; \
+	else \
+		state->disable = 0; \
+	return size; \
+}
+
 #define define_show_state_ull_function(_name) \
 static ssize_t show_state_##_name(struct cpuidle_state *state, \
 			struct cpuidle_state_usage *state_usage, char *buf) \
@@ -251,6 +273,8 @@ define_show_state_ull_function(usage)
 define_show_state_ull_function(time)
 define_show_state_str_function(name)
 define_show_state_str_function(desc)
+define_show_state_function(disable)
+define_store_state_function(disable)
 
 define_one_state_ro(name, show_state_name);
 define_one_state_ro(desc, show_state_desc);
@@ -258,6 +282,7 @@ define_one_state_ro(latency, show_state_exit_latency);
 define_one_state_ro(power, show_state_power_usage);
 define_one_state_ro(usage, show_state_usage);
 define_one_state_ro(time, show_state_time);
+define_one_state_rw(disable, show_state_disable, store_state_disable);
 
 static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_name.attr,
@@ -266,6 +291,7 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_power.attr,
 	&attr_usage.attr,
 	&attr_time.attr,
+	&attr_disable.attr,
 	NULL
 };
 
@@ -287,8 +313,22 @@ static ssize_t cpuidle_state_show(struct kobject * kobj,
 	return ret;
 }
 
+static ssize_t cpuidle_state_store(struct kobject *kobj,
+	struct attribute *attr, const char *buf, size_t size)
+{
+	int ret = -EIO;
+	struct cpuidle_state *state = kobj_to_state(kobj);
+	struct cpuidle_state_attr *cattr = attr_to_stateattr(attr);
+
+	if (cattr->store)
+		ret = cattr->store(state, buf, size);
+
+	return ret;
+}
+
 static const struct sysfs_ops cpuidle_state_sysfs_ops = {
 	.show = cpuidle_state_show,
+	.store = cpuidle_state_store,
 };
 
 static void cpuidle_state_sysfs_release(struct kobject *kobj)
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index f1a274994bb1..cf9da362d64f 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -201,7 +201,6 @@ config PL330_DMA
 	tristate "DMA API Driver for PL330"
 	select DMA_ENGINE
 	depends on ARM_AMBA
-	select PL330
 	help
 	  Select if your platform has one or more PL330 DMACs.
 	  You need to provide platform specific settings via
@@ -231,7 +230,7 @@ config IMX_SDMA
 
 config IMX_DMA
 	tristate "i.MX DMA support"
-	depends on IMX_HAVE_DMA_V1
+	depends on ARCH_MXC
 	select DMA_ENGINE
 	help
 	  Support the i.MX DMA engine. This engine is integrated into
@@ -252,6 +251,15 @@ config EP93XX_DMA
 	help
 	  Enable support for the Cirrus Logic EP93xx M2P/M2M DMA controller.
 
+config DMA_SA11X0
+	tristate "SA-11x0 DMA support"
+	depends on ARCH_SA1100
+	select DMA_ENGINE
+	help
+	  Support the DMA engine found on Intel StrongARM SA-1100 and
+	  SA-1110 SoCs.  This DMA engine can only be used with on-chip
+	  devices.
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 009a222e8283..86b795baba98 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -27,3 +27,4 @@ obj-$(CONFIG_PL330_DMA) += pl330.o
 obj-$(CONFIG_PCH_DMA) += pch_dma.o
 obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
 obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
+obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 8a281584458b..c301a8ec31aa 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -85,6 +85,8 @@
 #include <linux/slab.h>
 #include <asm/hardware/pl080.h>
 
+#include "dmaengine.h"
+
 #define DRIVER_NAME	"pl08xdmac"
 
 static struct amba_driver pl08x_amba_driver;
@@ -649,7 +651,7 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 			}
 
 			if ((bd.srcbus.addr % bd.srcbus.buswidth) ||
-					(bd.srcbus.addr % bd.srcbus.buswidth)) {
+					(bd.dstbus.addr % bd.dstbus.buswidth)) {
 				dev_err(&pl08x->adev->dev,
 					"%s src & dst address must be aligned to src"
 					" & dst width if peripheral is flow controller",
@@ -919,13 +921,10 @@ static dma_cookie_t pl08x_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(tx->chan);
 	struct pl08x_txd *txd = to_pl08x_txd(tx);
 	unsigned long flags;
+	dma_cookie_t cookie;
 
 	spin_lock_irqsave(&plchan->lock, flags);
-
-	plchan->chan.cookie += 1;
-	if (plchan->chan.cookie < 0)
-		plchan->chan.cookie = 1;
-	tx->cookie = plchan->chan.cookie;
+	cookie = dma_cookie_assign(tx);
 
 	/* Put this onto the pending list */
 	list_add_tail(&txd->node, &plchan->pend_list);
@@ -945,7 +944,7 @@ static dma_cookie_t pl08x_tx_submit(struct dma_async_tx_descriptor *tx)
 
 	spin_unlock_irqrestore(&plchan->lock, flags);
 
-	return tx->cookie;
+	return cookie;
 }
 
 static struct dma_async_tx_descriptor *pl08x_prep_dma_interrupt(
@@ -965,31 +964,17 @@ static enum dma_status pl08x_dma_tx_status(struct dma_chan *chan,
 		dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 	enum dma_status ret;
-	u32 bytesleft = 0;
 
-	last_used = plchan->chan.cookie;
-	last_complete = plchan->lc;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
-	if (ret == DMA_SUCCESS) {
-		dma_set_tx_state(txstate, last_complete, last_used, 0);
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_SUCCESS)
 		return ret;
-	}
 
 	/*
 	 * This cookie not complete yet
+	 * Get number of bytes left in the active transactions and queue
 	 */
-	last_used = plchan->chan.cookie;
-	last_complete = plchan->lc;
-
-	/* Get number of bytes left in the active transactions and queue */
-	bytesleft = pl08x_getbytes_chan(plchan);
-
-	dma_set_tx_state(txstate, last_complete, last_used,
-			 bytesleft);
+	dma_set_residue(txstate, pl08x_getbytes_chan(plchan));
 
 	if (plchan->state == PL08X_CHAN_PAUSED)
 		return DMA_PAUSED;
@@ -1139,6 +1124,8 @@ static int dma_set_runtime_config(struct dma_chan *chan,
 	cctl |= burst << PL080_CONTROL_SB_SIZE_SHIFT;
 	cctl |= burst << PL080_CONTROL_DB_SIZE_SHIFT;
 
+	plchan->device_fc = config->device_fc;
+
 	if (plchan->runtime_direction == DMA_DEV_TO_MEM) {
 		plchan->src_addr = config->src_addr;
 		plchan->src_cctl = pl08x_cctl(cctl) | PL080_CONTROL_DST_INCR |
@@ -1326,7 +1313,7 @@ static struct dma_async_tx_descriptor *pl08x_prep_dma_memcpy(
 static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	struct pl08x_driver_data *pl08x = plchan->host;
@@ -1370,7 +1357,7 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 		return NULL;
 	}
 
-	if (plchan->cd->device_fc)
+	if (plchan->device_fc)
 		tmp = (direction == DMA_MEM_TO_DEV) ? PL080_FLOW_MEM2PER_PER :
 			PL080_FLOW_PER2MEM_PER;
 	else
@@ -1541,7 +1528,7 @@ static void pl08x_tasklet(unsigned long data)
 
 	if (txd) {
 		/* Update last completed */
-		plchan->lc = txd->tx.cookie;
+		dma_cookie_complete(&txd->tx);
 	}
 
 	/* If a new descriptor is queued, set it up plchan->at is NULL here */
@@ -1722,8 +1709,7 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x,
 			 chan->name);
 
 		chan->chan.device = dmadev;
-		chan->chan.cookie = 0;
-		chan->lc = 0;
+		dma_cookie_init(&chan->chan);
 
 		spin_lock_init(&chan->lock);
 		INIT_LIST_HEAD(&chan->pend_list);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index f4aed5fc2cb6..7aa58d204892 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -27,6 +27,7 @@
 #include <linux/of_device.h>
 
 #include "at_hdmac_regs.h"
+#include "dmaengine.h"
 
 /*
  * Glossary
@@ -192,27 +193,6 @@ static void atc_desc_chain(struct at_desc **first, struct at_desc **prev,
 }
 
 /**
- * atc_assign_cookie - compute and assign new cookie
- * @atchan: channel we work on
- * @desc: descriptor to assign cookie for
- *
- * Called with atchan->lock held and bh disabled
- */
-static dma_cookie_t
-atc_assign_cookie(struct at_dma_chan *atchan, struct at_desc *desc)
-{
-	dma_cookie_t cookie = atchan->chan_common.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	atchan->chan_common.cookie = cookie;
-	desc->txd.cookie = cookie;
-
-	return cookie;
-}
-
-/**
  * atc_dostart - starts the DMA engine for real
  * @atchan: the channel we want to start
  * @first: first descriptor in the list we want to begin with
@@ -269,7 +249,7 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	dev_vdbg(chan2dev(&atchan->chan_common),
 		"descriptor %u complete\n", txd->cookie);
 
-	atchan->completed_cookie = txd->cookie;
+	dma_cookie_complete(txd);
 
 	/* move children to free_list */
 	list_splice_init(&desc->tx_list, &atchan->free_list);
@@ -547,7 +527,7 @@ static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx)
 	unsigned long		flags;
 
 	spin_lock_irqsave(&atchan->lock, flags);
-	cookie = atc_assign_cookie(atchan, desc);
+	cookie = dma_cookie_assign(tx);
 
 	if (list_empty(&atchan->active_list)) {
 		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
@@ -659,14 +639,16 @@ err_desc_get:
  * @sg_len: number of entries in @scatterlist
  * @direction: DMA direction
  * @flags: tx descriptor status flags
+ * @context: transaction context (ignored)
  */
 static struct dma_async_tx_descriptor *
 atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma_slave	*atslave = chan->private;
+	struct dma_slave_config	*sconfig = &atchan->dma_sconfig;
 	struct at_desc		*first = NULL;
 	struct at_desc		*prev = NULL;
 	u32			ctrla;
@@ -688,19 +670,18 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		return NULL;
 	}
 
-	reg_width = atslave->reg_width;
-
 	ctrla = ATC_DEFAULT_CTRLA | atslave->ctrla;
 	ctrlb = ATC_IEN;
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
+		reg_width = convert_buswidth(sconfig->dst_addr_width);
 		ctrla |=  ATC_DST_WIDTH(reg_width);
 		ctrlb |=  ATC_DST_ADDR_MODE_FIXED
 			| ATC_SRC_ADDR_MODE_INCR
 			| ATC_FC_MEM2PER
 			| ATC_SIF(AT_DMA_MEM_IF) | ATC_DIF(AT_DMA_PER_IF);
-		reg = atslave->tx_reg;
+		reg = sconfig->dst_addr;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct at_desc	*desc;
 			u32		len;
@@ -728,13 +709,14 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		}
 		break;
 	case DMA_DEV_TO_MEM:
+		reg_width = convert_buswidth(sconfig->src_addr_width);
 		ctrla |=  ATC_SRC_WIDTH(reg_width);
 		ctrlb |=  ATC_DST_ADDR_MODE_INCR
 			| ATC_SRC_ADDR_MODE_FIXED
 			| ATC_FC_PER2MEM
 			| ATC_SIF(AT_DMA_PER_IF) | ATC_DIF(AT_DMA_MEM_IF);
 
-		reg = atslave->rx_reg;
+		reg = sconfig->src_addr;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct at_desc	*desc;
 			u32		len;
@@ -810,12 +792,15 @@ err_out:
  * atc_dma_cyclic_fill_desc - Fill one period decriptor
  */
 static int
-atc_dma_cyclic_fill_desc(struct at_dma_slave *atslave, struct at_desc *desc,
+atc_dma_cyclic_fill_desc(struct dma_chan *chan, struct at_desc *desc,
 		unsigned int period_index, dma_addr_t buf_addr,
-		size_t period_len, enum dma_transfer_direction direction)
+		unsigned int reg_width, size_t period_len,
+		enum dma_transfer_direction direction)
 {
-	u32		ctrla;
-	unsigned int	reg_width = atslave->reg_width;
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma_slave	*atslave = chan->private;
+	struct dma_slave_config	*sconfig = &atchan->dma_sconfig;
+	u32			ctrla;
 
 	/* prepare common CRTLA value */
 	ctrla =   ATC_DEFAULT_CTRLA | atslave->ctrla
@@ -826,7 +811,7 @@ atc_dma_cyclic_fill_desc(struct at_dma_slave *atslave, struct at_desc *desc,
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
 		desc->lli.saddr = buf_addr + (period_len * period_index);
-		desc->lli.daddr = atslave->tx_reg;
+		desc->lli.daddr = sconfig->dst_addr;
 		desc->lli.ctrla = ctrla;
 		desc->lli.ctrlb = ATC_DST_ADDR_MODE_FIXED
 				| ATC_SRC_ADDR_MODE_INCR
@@ -836,7 +821,7 @@ atc_dma_cyclic_fill_desc(struct at_dma_slave *atslave, struct at_desc *desc,
 		break;
 
 	case DMA_DEV_TO_MEM:
-		desc->lli.saddr = atslave->rx_reg;
+		desc->lli.saddr = sconfig->src_addr;
 		desc->lli.daddr = buf_addr + (period_len * period_index);
 		desc->lli.ctrla = ctrla;
 		desc->lli.ctrlb = ATC_DST_ADDR_MODE_INCR
@@ -860,16 +845,20 @@ atc_dma_cyclic_fill_desc(struct at_dma_slave *atslave, struct at_desc *desc,
  * @buf_len: total number of bytes for the entire buffer
  * @period_len: number of bytes for each period
  * @direction: transfer direction, to or from device
+ * @context: transfer context (ignored)
  */
 static struct dma_async_tx_descriptor *
 atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma_slave	*atslave = chan->private;
+	struct dma_slave_config	*sconfig = &atchan->dma_sconfig;
 	struct at_desc		*first = NULL;
 	struct at_desc		*prev = NULL;
 	unsigned long		was_cyclic;
+	unsigned int		reg_width;
 	unsigned int		periods = buf_len / period_len;
 	unsigned int		i;
 
@@ -889,8 +878,13 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		return NULL;
 	}
 
+	if (sconfig->direction == DMA_MEM_TO_DEV)
+		reg_width = convert_buswidth(sconfig->dst_addr_width);
+	else
+		reg_width = convert_buswidth(sconfig->src_addr_width);
+
 	/* Check for too big/unaligned periods and unaligned DMA buffer */
-	if (atc_dma_cyclic_check_values(atslave->reg_width, buf_addr,
+	if (atc_dma_cyclic_check_values(reg_width, buf_addr,
 					period_len, direction))
 		goto err_out;
 
@@ -902,8 +896,8 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		if (!desc)
 			goto err_desc_get;
 
-		if (atc_dma_cyclic_fill_desc(atslave, desc, i, buf_addr,
-						period_len, direction))
+		if (atc_dma_cyclic_fill_desc(chan, desc, i, buf_addr,
+					     reg_width, period_len, direction))
 			goto err_desc_get;
 
 		atc_desc_chain(&first, &prev, desc);
@@ -926,6 +920,23 @@ err_out:
 	return NULL;
 }
 
+static int set_runtime_config(struct dma_chan *chan,
+			      struct dma_slave_config *sconfig)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+
+	/* Check if it is chan is configured for slave transfers */
+	if (!chan->private)
+		return -EINVAL;
+
+	memcpy(&atchan->dma_sconfig, sconfig, sizeof(*sconfig));
+
+	convert_burst(&atchan->dma_sconfig.src_maxburst);
+	convert_burst(&atchan->dma_sconfig.dst_maxburst);
+
+	return 0;
+}
+
 
 static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		       unsigned long arg)
@@ -986,6 +997,8 @@ static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		clear_bit(ATC_IS_CYCLIC, &atchan->status);
 
 		spin_unlock_irqrestore(&atchan->lock, flags);
+	} else if (cmd == DMA_SLAVE_CONFIG) {
+		return set_runtime_config(chan, (struct dma_slave_config *)arg);
 	} else {
 		return -ENXIO;
 	}
@@ -1016,26 +1029,20 @@ atc_tx_status(struct dma_chan *chan,
 
 	spin_lock_irqsave(&atchan->lock, flags);
 
-	last_complete = atchan->completed_cookie;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS) {
 		atc_cleanup_descriptors(atchan);
 
-		last_complete = atchan->completed_cookie;
-		last_used = chan->cookie;
-
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
+		ret = dma_cookie_status(chan, cookie, txstate);
 	}
 
+	last_complete = chan->completed_cookie;
+	last_used = chan->cookie;
+
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	if (ret != DMA_SUCCESS)
-		dma_set_tx_state(txstate, last_complete, last_used,
-			atc_first_active(atchan)->len);
-	else
-		dma_set_tx_state(txstate, last_complete, last_used, 0);
+		dma_set_residue(txstate, atc_first_active(atchan)->len);
 
 	if (atc_chan_is_paused(atchan))
 		ret = DMA_PAUSED;
@@ -1129,7 +1136,7 @@ static int atc_alloc_chan_resources(struct dma_chan *chan)
 	spin_lock_irqsave(&atchan->lock, flags);
 	atchan->descs_allocated = i;
 	list_splice(&tmp_list, &atchan->free_list);
-	atchan->completed_cookie = chan->cookie = 1;
+	dma_cookie_init(chan);
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	/* channel parameters */
@@ -1329,7 +1336,7 @@ static int __init at_dma_probe(struct platform_device *pdev)
 		struct at_dma_chan	*atchan = &atdma->chan[i];
 
 		atchan->chan_common.device = &atdma->dma_common;
-		atchan->chan_common.cookie = atchan->completed_cookie = 1;
+		dma_cookie_init(&atchan->chan_common);
 		list_add_tail(&atchan->chan_common.device_node,
 				&atdma->dma_common.channels);
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index a8d3277d60b5..897a8bcaec90 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -207,8 +207,8 @@ enum atc_status {
  * @save_cfg: configuration register that is saved on suspend/resume cycle
  * @save_dscr: for cyclic operations, preserve next descriptor address in
  *             the cyclic list on suspend/resume cycle
+ * @dma_sconfig: configuration for slave transfers, passed via DMA_SLAVE_CONFIG
  * @lock: serializes enqueue/dequeue operations to descriptors lists
- * @completed_cookie: identifier for the most recently completed operation
  * @active_list: list of descriptors dmaengine is being running on
  * @queue: list of descriptors ready to be submitted to engine
  * @free_list: list of descriptors usable by the channel
@@ -223,11 +223,11 @@ struct at_dma_chan {
 	struct tasklet_struct	tasklet;
 	u32			save_cfg;
 	u32			save_dscr;
+	struct dma_slave_config dma_sconfig;
 
 	spinlock_t		lock;
 
 	/* these other elements are all protected by lock */
-	dma_cookie_t		completed_cookie;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
@@ -245,6 +245,36 @@ static inline struct at_dma_chan *to_at_dma_chan(struct dma_chan *dchan)
 	return container_of(dchan, struct at_dma_chan, chan_common);
 }
 
+/*
+ * Fix sconfig's burst size according to at_hdmac. We need to convert them as:
+ * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3, 32 -> 4, 64 -> 5, 128 -> 6, 256 -> 7.
+ *
+ * This can be done by finding most significant bit set.
+ */
+static inline void convert_burst(u32 *maxburst)
+{
+	if (*maxburst > 1)
+		*maxburst = fls(*maxburst) - 2;
+	else
+		*maxburst = 0;
+}
+
+/*
+ * Fix sconfig's bus width according to at_hdmac.
+ * 1 byte -> 0, 2 bytes -> 1, 4 bytes -> 2.
+ */
+static inline u8 convert_buswidth(enum dma_slave_buswidth addr_width)
+{
+	switch (addr_width) {
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		return 1;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		return 2;
+	default:
+		/* For 1 byte width or fallback */
+		return 0;
+	}
+}
 
 /*--  Controller  ------------------------------------------------------*/
 
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index d65a718c0f9b..750925f9638b 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -24,6 +24,7 @@
 #include <mach/coh901318.h>
 
 #include "coh901318_lli.h"
+#include "dmaengine.h"
 
 #define COHC_2_DEV(cohc) (&cohc->chan.dev->device)
 
@@ -59,7 +60,6 @@ struct coh901318_base {
 struct coh901318_chan {
 	spinlock_t lock;
 	int allocated;
-	int completed;
 	int id;
 	int stopped;
 
@@ -104,13 +104,6 @@ static void coh901318_list_print(struct coh901318_chan *cohc,
 static struct coh901318_base *debugfs_dma_base;
 static struct dentry *dma_dentry;
 
-static int coh901318_debugfs_open(struct inode *inode, struct file *file)
-{
-
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static int coh901318_debugfs_read(struct file *file, char __user *buf,
 				  size_t count, loff_t *f_pos)
 {
@@ -158,7 +151,7 @@ static int coh901318_debugfs_read(struct file *file, char __user *buf,
 
 static const struct file_operations coh901318_debugfs_status_operations = {
 	.owner		= THIS_MODULE,
-	.open		= coh901318_debugfs_open,
+	.open		= simple_open,
 	.read		= coh901318_debugfs_read,
 	.llseek		= default_llseek,
 };
@@ -318,20 +311,6 @@ static int coh901318_prep_linked_list(struct coh901318_chan *cohc,
 
 	return 0;
 }
-static dma_cookie_t
-coh901318_assign_cookie(struct coh901318_chan *cohc,
-			struct coh901318_desc *cohd)
-{
-	dma_cookie_t cookie = cohc->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	cohc->chan.cookie = cookie;
-	cohd->desc.cookie = cookie;
-
-	return cookie;
-}
 
 static struct coh901318_desc *
 coh901318_desc_get(struct coh901318_chan *cohc)
@@ -705,7 +684,7 @@ static void dma_tasklet(unsigned long data)
 	callback_param = cohd_fin->desc.callback_param;
 
 	/* sign this job as completed on the channel */
-	cohc->completed = cohd_fin->desc.cookie;
+	dma_cookie_complete(&cohd_fin->desc);
 
 	/* release the lli allocation and remove the descriptor */
 	coh901318_lli_free(&cohc->base->pool, &cohd_fin->lli);
@@ -929,7 +908,7 @@ static int coh901318_alloc_chan_resources(struct dma_chan *chan)
 	coh901318_config(cohc, NULL);
 
 	cohc->allocated = 1;
-	cohc->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	spin_unlock_irqrestore(&cohc->lock, flags);
 
@@ -966,16 +945,16 @@ coh901318_tx_submit(struct dma_async_tx_descriptor *tx)
 						   desc);
 	struct coh901318_chan *cohc = to_coh901318_chan(tx->chan);
 	unsigned long flags;
+	dma_cookie_t cookie;
 
 	spin_lock_irqsave(&cohc->lock, flags);
-
-	tx->cookie = coh901318_assign_cookie(cohc, cohd);
+	cookie = dma_cookie_assign(tx);
 
 	coh901318_desc_queue(cohc, cohd);
 
 	spin_unlock_irqrestore(&cohc->lock, flags);
 
-	return tx->cookie;
+	return cookie;
 }
 
 static struct dma_async_tx_descriptor *
@@ -1035,7 +1014,7 @@ coh901318_prep_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 static struct dma_async_tx_descriptor *
 coh901318_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			unsigned int sg_len, enum dma_transfer_direction direction,
-			unsigned long flags)
+			unsigned long flags, void *context)
 {
 	struct coh901318_chan *cohc = to_coh901318_chan(chan);
 	struct coh901318_lli *lli;
@@ -1165,17 +1144,12 @@ coh901318_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		 struct dma_tx_state *txstate)
 {
 	struct coh901318_chan *cohc = to_coh901318_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	int ret;
-
-	last_complete = cohc->completed;
-	last_used = chan->cookie;
+	enum dma_status ret;
 
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
+	/* FIXME: should be conditional on ret != DMA_SUCCESS? */
+	dma_set_residue(txstate, coh901318_get_bytes_left(chan));
 
-	dma_set_tx_state(txstate, last_complete, last_used,
-			 coh901318_get_bytes_left(chan));
 	if (ret == DMA_IN_PROGRESS && cohc->stopped)
 		ret = DMA_PAUSED;
 
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index a6c6051ec858..767bcc31b365 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -510,8 +510,8 @@ struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, v
 					 dma_chan_name(chan));
 				list_del_rcu(&device->global_node);
 			} else if (err)
-				pr_debug("dmaengine: failed to get %s: (%d)\n",
-					 dma_chan_name(chan), err);
+				pr_debug("%s: failed to get %s: (%d)\n",
+					__func__, dma_chan_name(chan), err);
 			else
 				break;
 			if (--device->privatecnt == 0)
@@ -564,8 +564,8 @@ void dmaengine_get(void)
 				list_del_rcu(&device->global_node);
 				break;
 			} else if (err)
-				pr_err("dmaengine: failed to get %s: (%d)\n",
-				       dma_chan_name(chan), err);
+				pr_err("%s: failed to get %s: (%d)\n",
+					__func__, dma_chan_name(chan), err);
 		}
 	}
 
diff --git a/drivers/dma/dmaengine.h b/drivers/dma/dmaengine.h
new file mode 100644
index 000000000000..17f983a4e9ba
--- /dev/null
+++ b/drivers/dma/dmaengine.h
@@ -0,0 +1,89 @@
+/*
+ * The contents of this file are private to DMA engine drivers, and is not
+ * part of the API to be used by DMA engine users.
+ */
+#ifndef DMAENGINE_H
+#define DMAENGINE_H
+
+#include <linux/bug.h>
+#include <linux/dmaengine.h>
+
+/**
+ * dma_cookie_init - initialize the cookies for a DMA channel
+ * @chan: dma channel to initialize
+ */
+static inline void dma_cookie_init(struct dma_chan *chan)
+{
+	chan->cookie = DMA_MIN_COOKIE;
+	chan->completed_cookie = DMA_MIN_COOKIE;
+}
+
+/**
+ * dma_cookie_assign - assign a DMA engine cookie to the descriptor
+ * @tx: descriptor needing cookie
+ *
+ * Assign a unique non-zero per-channel cookie to the descriptor.
+ * Note: caller is expected to hold a lock to prevent concurrency.
+ */
+static inline dma_cookie_t dma_cookie_assign(struct dma_async_tx_descriptor *tx)
+{
+	struct dma_chan *chan = tx->chan;
+	dma_cookie_t cookie;
+
+	cookie = chan->cookie + 1;
+	if (cookie < DMA_MIN_COOKIE)
+		cookie = DMA_MIN_COOKIE;
+	tx->cookie = chan->cookie = cookie;
+
+	return cookie;
+}
+
+/**
+ * dma_cookie_complete - complete a descriptor
+ * @tx: descriptor to complete
+ *
+ * Mark this descriptor complete by updating the channels completed
+ * cookie marker.  Zero the descriptors cookie to prevent accidental
+ * repeated completions.
+ *
+ * Note: caller is expected to hold a lock to prevent concurrency.
+ */
+static inline void dma_cookie_complete(struct dma_async_tx_descriptor *tx)
+{
+	BUG_ON(tx->cookie < DMA_MIN_COOKIE);
+	tx->chan->completed_cookie = tx->cookie;
+	tx->cookie = 0;
+}
+
+/**
+ * dma_cookie_status - report cookie status
+ * @chan: dma channel
+ * @cookie: cookie we are interested in
+ * @state: dma_tx_state structure to return last/used cookies
+ *
+ * Report the status of the cookie, filling in the state structure if
+ * non-NULL.  No locking is required.
+ */
+static inline enum dma_status dma_cookie_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *state)
+{
+	dma_cookie_t used, complete;
+
+	used = chan->cookie;
+	complete = chan->completed_cookie;
+	barrier();
+	if (state) {
+		state->last = complete;
+		state->used = used;
+		state->residue = 0;
+	}
+	return dma_async_is_complete(cookie, complete, used);
+}
+
+static inline void dma_set_residue(struct dma_tx_state *state, u32 residue)
+{
+	if (state)
+		state->residue = residue;
+}
+
+#endif
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 9b592b02b5f4..7439079f5eed 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -9,6 +9,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/bitops.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
@@ -22,6 +23,7 @@
 #include <linux/slab.h>
 
 #include "dw_dmac_regs.h"
+#include "dmaengine.h"
 
 /*
  * This supports the Synopsys "DesignWare AHB Central DMA Controller",
@@ -33,19 +35,23 @@
  * which does not support descriptor writeback.
  */
 
-#define DWC_DEFAULT_CTLLO(private) ({				\
-		struct dw_dma_slave *__slave = (private);	\
-		int dms = __slave ? __slave->dst_master : 0;	\
-		int sms = __slave ? __slave->src_master : 1;	\
-		u8 smsize = __slave ? __slave->src_msize : DW_DMA_MSIZE_16; \
-		u8 dmsize = __slave ? __slave->dst_msize : DW_DMA_MSIZE_16; \
+#define DWC_DEFAULT_CTLLO(_chan) ({				\
+		struct dw_dma_slave *__slave = (_chan->private);	\
+		struct dw_dma_chan *_dwc = to_dw_dma_chan(_chan);	\
+		struct dma_slave_config	*_sconfig = &_dwc->dma_sconfig;	\
+		int _dms = __slave ? __slave->dst_master : 0;	\
+		int _sms = __slave ? __slave->src_master : 1;	\
+		u8 _smsize = __slave ? _sconfig->src_maxburst :	\
+			DW_DMA_MSIZE_16;			\
+		u8 _dmsize = __slave ? _sconfig->dst_maxburst :	\
+			DW_DMA_MSIZE_16;			\
 								\
-		(DWC_CTLL_DST_MSIZE(dmsize)			\
-		 | DWC_CTLL_SRC_MSIZE(smsize)			\
+		(DWC_CTLL_DST_MSIZE(_dmsize)			\
+		 | DWC_CTLL_SRC_MSIZE(_smsize)			\
 		 | DWC_CTLL_LLP_D_EN				\
 		 | DWC_CTLL_LLP_S_EN				\
-		 | DWC_CTLL_DMS(dms)				\
-		 | DWC_CTLL_SMS(sms));				\
+		 | DWC_CTLL_DMS(_dms)				\
+		 | DWC_CTLL_SMS(_sms));				\
 	})
 
 /*
@@ -151,21 +157,6 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	}
 }
 
-/* Called with dwc->lock held and bh disabled */
-static dma_cookie_t
-dwc_assign_cookie(struct dw_dma_chan *dwc, struct dw_desc *desc)
-{
-	dma_cookie_t cookie = dwc->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	dwc->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
-	return cookie;
-}
-
 static void dwc_initialize(struct dw_dma_chan *dwc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
@@ -192,7 +183,6 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
-	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
 
 	dwc->initialized = true;
@@ -245,7 +235,7 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
 	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	dwc->completed = txd->cookie;
+	dma_cookie_complete(txd);
 	if (callback_required) {
 		callback = txd->callback;
 		param = txd->callback_param;
@@ -329,12 +319,6 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	/*
-	 * Clear block interrupt flag before scanning so that we don't
-	 * miss any, and read LLP before RAW_XFER to ensure it is
-	 * valid if we decide to scan the list.
-	 */
-	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 	llp = channel_readl(dwc, LLP);
 	status_xfer = dma_readl(dw, RAW.XFER);
 
@@ -470,17 +454,16 @@ EXPORT_SYMBOL(dw_dma_get_dst_addr);
 
 /* called with dwc->lock held and all DMAC interrupts disabled */
 static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
-		u32 status_block, u32 status_err, u32 status_xfer)
+		u32 status_err, u32 status_xfer)
 {
 	unsigned long flags;
 
-	if (status_block & dwc->mask) {
+	if (dwc->mask) {
 		void (*callback)(void *param);
 		void *callback_param;
 
 		dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n",
 				channel_readl(dwc, LLP));
-		dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 
 		callback = dwc->cdesc->period_callback;
 		callback_param = dwc->cdesc->period_callback_param;
@@ -520,7 +503,6 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 		channel_writel(dwc, CTL_LO, 0);
 		channel_writel(dwc, CTL_HI, 0);
 
-		dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 		dma_writel(dw, CLEAR.ERROR, dwc->mask);
 		dma_writel(dw, CLEAR.XFER, dwc->mask);
 
@@ -537,36 +519,29 @@ static void dw_dma_tasklet(unsigned long data)
 {
 	struct dw_dma *dw = (struct dw_dma *)data;
 	struct dw_dma_chan *dwc;
-	u32 status_block;
 	u32 status_xfer;
 	u32 status_err;
 	int i;
 
-	status_block = dma_readl(dw, RAW.BLOCK);
 	status_xfer = dma_readl(dw, RAW.XFER);
 	status_err = dma_readl(dw, RAW.ERROR);
 
-	dev_vdbg(dw->dma.dev, "tasklet: status_block=%x status_err=%x\n",
-			status_block, status_err);
+	dev_vdbg(dw->dma.dev, "tasklet: status_err=%x\n", status_err);
 
 	for (i = 0; i < dw->dma.chancnt; i++) {
 		dwc = &dw->chan[i];
 		if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags))
-			dwc_handle_cyclic(dw, dwc, status_block, status_err,
-					status_xfer);
+			dwc_handle_cyclic(dw, dwc, status_err, status_xfer);
 		else if (status_err & (1 << i))
 			dwc_handle_error(dw, dwc);
-		else if ((status_block | status_xfer) & (1 << i))
+		else if (status_xfer & (1 << i))
 			dwc_scan_descriptors(dw, dwc);
 	}
 
 	/*
-	 * Re-enable interrupts. Block Complete interrupts are only
-	 * enabled if the INT_EN bit in the descriptor is set. This
-	 * will trigger a scan before the whole list is done.
+	 * Re-enable interrupts.
 	 */
 	channel_set_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_set_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask);
 }
 
@@ -583,7 +558,6 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
 	 * softirq handler.
 	 */
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
 
 	status = dma_readl(dw, STATUS_INT);
@@ -594,7 +568,6 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
 
 		/* Try to recover */
 		channel_clear_bit(dw, MASK.XFER, (1 << 8) - 1);
-		channel_clear_bit(dw, MASK.BLOCK, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.SRC_TRAN, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.DST_TRAN, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.ERROR, (1 << 8) - 1);
@@ -615,7 +588,7 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 	unsigned long		flags;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	cookie = dwc_assign_cookie(dwc, desc);
+	cookie = dma_cookie_assign(tx);
 
 	/*
 	 * REVISIT: We should attempt to chain as many descriptors as
@@ -674,7 +647,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	else
 		src_width = dst_width = 0;
 
-	ctllo = DWC_DEFAULT_CTLLO(chan->private)
+	ctllo = DWC_DEFAULT_CTLLO(chan)
 			| DWC_CTLL_DST_WIDTH(dst_width)
 			| DWC_CTLL_SRC_WIDTH(src_width)
 			| DWC_CTLL_DST_INC
@@ -731,10 +704,11 @@ err_desc_get:
 static struct dma_async_tx_descriptor *
 dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma_slave	*dws = chan->private;
+	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
 	struct dw_desc		*prev;
 	struct dw_desc		*first;
 	u32			ctllo;
@@ -750,25 +724,34 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (unlikely(!dws || !sg_len))
 		return NULL;
 
-	reg_width = dws->reg_width;
 	prev = first = NULL;
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
-		ctllo = (DWC_DEFAULT_CTLLO(chan->private)
+		reg_width = __fls(sconfig->dst_addr_width);
+		reg = sconfig->dst_addr;
+		ctllo = (DWC_DEFAULT_CTLLO(chan)
 				| DWC_CTLL_DST_WIDTH(reg_width)
 				| DWC_CTLL_DST_FIX
-				| DWC_CTLL_SRC_INC
-				| DWC_CTLL_FC(dws->fc));
-		reg = dws->tx_reg;
+				| DWC_CTLL_SRC_INC);
+
+		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
+			DWC_CTLL_FC(DW_DMA_FC_D_M2P);
+
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
 			u32		len, dlen, mem;
 
 			mem = sg_phys(sg);
 			len = sg_dma_len(sg);
-			mem_width = 2;
-			if (unlikely(mem & 3 || len & 3))
+
+			if (!((mem | len) & 7))
+				mem_width = 3;
+			else if (!((mem | len) & 3))
+				mem_width = 2;
+			else if (!((mem | len) & 1))
+				mem_width = 1;
+			else
 				mem_width = 0;
 
 slave_sg_todev_fill_desc:
@@ -812,21 +795,30 @@ slave_sg_todev_fill_desc:
 		}
 		break;
 	case DMA_DEV_TO_MEM:
-		ctllo = (DWC_DEFAULT_CTLLO(chan->private)
+		reg_width = __fls(sconfig->src_addr_width);
+		reg = sconfig->src_addr;
+		ctllo = (DWC_DEFAULT_CTLLO(chan)
 				| DWC_CTLL_SRC_WIDTH(reg_width)
 				| DWC_CTLL_DST_INC
-				| DWC_CTLL_SRC_FIX
-				| DWC_CTLL_FC(dws->fc));
+				| DWC_CTLL_SRC_FIX);
+
+		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
+			DWC_CTLL_FC(DW_DMA_FC_D_P2M);
 
-		reg = dws->rx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
 			u32		len, dlen, mem;
 
 			mem = sg_phys(sg);
 			len = sg_dma_len(sg);
-			mem_width = 2;
-			if (unlikely(mem & 3 || len & 3))
+
+			if (!((mem | len) & 7))
+				mem_width = 3;
+			else if (!((mem | len) & 3))
+				mem_width = 2;
+			else if (!((mem | len) & 1))
+				mem_width = 1;
+			else
 				mem_width = 0;
 
 slave_sg_fromdev_fill_desc:
@@ -890,6 +882,39 @@ err_desc_get:
 	return NULL;
 }
 
+/*
+ * Fix sconfig's burst size according to dw_dmac. We need to convert them as:
+ * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
+ *
+ * NOTE: burst size 2 is not supported by controller.
+ *
+ * This can be done by finding least significant bit set: n & (n - 1)
+ */
+static inline void convert_burst(u32 *maxburst)
+{
+	if (*maxburst > 1)
+		*maxburst = fls(*maxburst) - 2;
+	else
+		*maxburst = 0;
+}
+
+static int
+set_runtime_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+
+	/* Check if it is chan is configured for slave transfers */
+	if (!chan->private)
+		return -EINVAL;
+
+	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
+
+	convert_burst(&dwc->dma_sconfig.src_maxburst);
+	convert_burst(&dwc->dma_sconfig.dst_maxburst);
+
+	return 0;
+}
+
 static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		       unsigned long arg)
 {
@@ -939,8 +964,11 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		/* Flush all pending and queued descriptors */
 		list_for_each_entry_safe(desc, _desc, &list, desc_node)
 			dwc_descriptor_complete(dwc, desc, false);
-	} else
+	} else if (cmd == DMA_SLAVE_CONFIG) {
+		return set_runtime_config(chan, (struct dma_slave_config *)arg);
+	} else {
 		return -ENXIO;
+	}
 
 	return 0;
 }
@@ -951,28 +979,17 @@ dwc_tx_status(struct dma_chan *chan,
 	      struct dma_tx_state *txstate)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
-	dma_cookie_t		last_used;
-	dma_cookie_t		last_complete;
-	int			ret;
-
-	last_complete = dwc->completed;
-	last_used = chan->cookie;
+	enum dma_status		ret;
 
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS) {
 		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
 
-		last_complete = dwc->completed;
-		last_used = chan->cookie;
-
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
+		ret = dma_cookie_status(chan, cookie, txstate);
 	}
 
 	if (ret != DMA_SUCCESS)
-		dma_set_tx_state(txstate, last_complete, last_used,
-				dwc_first_active(dwc)->len);
-	else
-		dma_set_tx_state(txstate, last_complete, last_used, 0);
+		dma_set_residue(txstate, dwc_first_active(dwc)->len);
 
 	if (dwc->paused)
 		return DMA_PAUSED;
@@ -1004,7 +1021,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 		return -EIO;
 	}
 
-	dwc->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	/*
 	 * NOTE: some controllers may have additional features that we
@@ -1068,7 +1085,6 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 
 	/* Disable interrupts */
 	channel_clear_bit(dw, MASK.XFER, dwc->mask);
-	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_clear_bit(dw, MASK.ERROR, dwc->mask);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
@@ -1120,7 +1136,6 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 		return -EBUSY;
 	}
 
-	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 	dma_writel(dw, CLEAR.ERROR, dwc->mask);
 	dma_writel(dw, CLEAR.XFER, dwc->mask);
 
@@ -1175,11 +1190,11 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 		enum dma_transfer_direction direction)
 {
 	struct dw_dma_chan		*dwc = to_dw_dma_chan(chan);
+	struct dma_slave_config		*sconfig = &dwc->dma_sconfig;
 	struct dw_cyclic_desc		*cdesc;
 	struct dw_cyclic_desc		*retval = NULL;
 	struct dw_desc			*desc;
 	struct dw_desc			*last = NULL;
-	struct dw_dma_slave		*dws = chan->private;
 	unsigned long			was_cyclic;
 	unsigned int			reg_width;
 	unsigned int			periods;
@@ -1203,7 +1218,12 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 	}
 
 	retval = ERR_PTR(-EINVAL);
-	reg_width = dws->reg_width;
+
+	if (direction == DMA_MEM_TO_DEV)
+		reg_width = __ffs(sconfig->dst_addr_width);
+	else
+		reg_width = __ffs(sconfig->src_addr_width);
+
 	periods = buf_len / period_len;
 
 	/* Check for too big/unaligned periods and unaligned DMA buffer. */
@@ -1236,26 +1256,34 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 
 		switch (direction) {
 		case DMA_MEM_TO_DEV:
-			desc->lli.dar = dws->tx_reg;
+			desc->lli.dar = sconfig->dst_addr;
 			desc->lli.sar = buf_addr + (period_len * i);
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan->private)
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan)
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_FIX
 					| DWC_CTLL_SRC_INC
-					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
+
+			desc->lli.ctllo |= sconfig->device_fc ?
+				DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
+				DWC_CTLL_FC(DW_DMA_FC_D_M2P);
+
 			break;
 		case DMA_DEV_TO_MEM:
 			desc->lli.dar = buf_addr + (period_len * i);
-			desc->lli.sar = dws->rx_reg;
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan->private)
+			desc->lli.sar = sconfig->src_addr;
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan)
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_DST_INC
 					| DWC_CTLL_SRC_FIX
-					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
+
+			desc->lli.ctllo |= sconfig->device_fc ?
+				DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
+				DWC_CTLL_FC(DW_DMA_FC_D_P2M);
+
 			break;
 		default:
 			break;
@@ -1322,7 +1350,6 @@ void dw_dma_cyclic_free(struct dma_chan *chan)
 	while (dma_readl(dw, CH_EN) & dwc->mask)
 		cpu_relax();
 
-	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
 	dma_writel(dw, CLEAR.ERROR, dwc->mask);
 	dma_writel(dw, CLEAR.XFER, dwc->mask);
 
@@ -1347,7 +1374,6 @@ static void dw_dma_off(struct dw_dma *dw)
 	dma_writel(dw, CFG, 0);
 
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
@@ -1369,7 +1395,7 @@ static int __init dw_probe(struct platform_device *pdev)
 	int			err;
 	int			i;
 
-	pdata = pdev->dev.platform_data;
+	pdata = dev_get_platdata(&pdev->dev);
 	if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS)
 		return -EINVAL;
 
@@ -1423,7 +1449,7 @@ static int __init dw_probe(struct platform_device *pdev)
 		struct dw_dma_chan	*dwc = &dw->chan[i];
 
 		dwc->chan.device = &dw->dma;
-		dwc->chan.cookie = dwc->completed = 1;
+		dma_cookie_init(&dwc->chan);
 		if (pdata->chan_allocation_order == CHAN_ALLOCATION_ASCENDING)
 			list_add_tail(&dwc->chan.device_node,
 					&dw->dma.channels);
@@ -1432,7 +1458,7 @@ static int __init dw_probe(struct platform_device *pdev)
 
 		/* 7 is highest priority & 0 is lowest. */
 		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
-			dwc->priority = 7 - i;
+			dwc->priority = pdata->nr_channels - i - 1;
 		else
 			dwc->priority = i;
 
@@ -1449,13 +1475,11 @@ static int __init dw_probe(struct platform_device *pdev)
 
 	/* Clear/disable all interrupts on all channels. */
 	dma_writel(dw, CLEAR.XFER, dw->all_chan_mask);
-	dma_writel(dw, CLEAR.BLOCK, dw->all_chan_mask);
 	dma_writel(dw, CLEAR.SRC_TRAN, dw->all_chan_mask);
 	dma_writel(dw, CLEAR.DST_TRAN, dw->all_chan_mask);
 	dma_writel(dw, CLEAR.ERROR, dw->all_chan_mask);
 
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
@@ -1562,6 +1586,10 @@ static int dw_resume_noirq(struct device *dev)
 static const struct dev_pm_ops dw_dev_pm_ops = {
 	.suspend_noirq = dw_suspend_noirq,
 	.resume_noirq = dw_resume_noirq,
+	.freeze_noirq = dw_suspend_noirq,
+	.thaw_noirq = dw_resume_noirq,
+	.restore_noirq = dw_resume_noirq,
+	.poweroff_noirq = dw_suspend_noirq,
 };
 
 static struct platform_driver dw_driver = {
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index 5eef6946a367..f298f69ecbf9 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -13,6 +13,18 @@
 
 #define DW_DMA_MAX_NR_CHANNELS	8
 
+/* flow controller */
+enum dw_dma_fc {
+	DW_DMA_FC_D_M2M,
+	DW_DMA_FC_D_M2P,
+	DW_DMA_FC_D_P2M,
+	DW_DMA_FC_D_P2P,
+	DW_DMA_FC_P_P2M,
+	DW_DMA_FC_SP_P2P,
+	DW_DMA_FC_P_M2P,
+	DW_DMA_FC_DP_P2P,
+};
+
 /*
  * Redefine this macro to handle differences between 32- and 64-bit
  * addressing, big vs. little endian, etc.
@@ -146,13 +158,15 @@ struct dw_dma_chan {
 
 	/* these other elements are all protected by lock */
 	unsigned long		flags;
-	dma_cookie_t		completed;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
 	struct dw_cyclic_desc	*cdesc;
 
 	unsigned int		descs_allocated;
+
+	/* configuration passed via DMA_SLAVE_CONFIG */
+	struct dma_slave_config dma_sconfig;
 };
 
 static inline struct dw_dma_chan_regs __iomem *
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 59e7a965772b..e6f133b78dc2 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -28,6 +28,8 @@
 
 #include <mach/dma.h>
 
+#include "dmaengine.h"
+
 /* M2P registers */
 #define M2P_CONTROL			0x0000
 #define M2P_CONTROL_STALLINT		BIT(0)
@@ -122,7 +124,6 @@ struct ep93xx_dma_desc {
  * @lock: lock protecting the fields following
  * @flags: flags for the channel
  * @buffer: which buffer to use next (0/1)
- * @last_completed: last completed cookie value
  * @active: flattened chain of descriptors currently being processed
  * @queue: pending descriptors which are handled next
  * @free_list: list of free descriptors which can be used
@@ -157,7 +158,6 @@ struct ep93xx_dma_chan {
 #define EP93XX_DMA_IS_CYCLIC		0
 
 	int				buffer;
-	dma_cookie_t			last_completed;
 	struct list_head		active;
 	struct list_head		queue;
 	struct list_head		free_list;
@@ -703,7 +703,7 @@ static void ep93xx_dma_tasklet(unsigned long data)
 	desc = ep93xx_dma_get_active(edmac);
 	if (desc) {
 		if (desc->complete) {
-			edmac->last_completed = desc->txd.cookie;
+			dma_cookie_complete(&desc->txd);
 			list_splice_init(&edmac->active, &list);
 		}
 		callback = desc->txd.callback;
@@ -783,17 +783,10 @@ static dma_cookie_t ep93xx_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	unsigned long flags;
 
 	spin_lock_irqsave(&edmac->lock, flags);
-
-	cookie = edmac->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
+	cookie = dma_cookie_assign(tx);
 
 	desc = container_of(tx, struct ep93xx_dma_desc, txd);
 
-	edmac->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
 	/*
 	 * If nothing is currently prosessed, we push this descriptor
 	 * directly to the hardware. Otherwise we put the descriptor
@@ -861,8 +854,7 @@ static int ep93xx_dma_alloc_chan_resources(struct dma_chan *chan)
 		goto fail_clk_disable;
 
 	spin_lock_irq(&edmac->lock);
-	edmac->last_completed = 1;
-	edmac->chan.cookie = 1;
+	dma_cookie_init(&edmac->chan);
 	ret = edmac->edma->hw_setup(edmac);
 	spin_unlock_irq(&edmac->lock);
 
@@ -983,13 +975,14 @@ fail:
  * @sg_len: number of entries in @sgl
  * @dir: direction of tha DMA transfer
  * @flags: flags for the descriptor
+ * @context: operation context (ignored)
  *
  * Returns a valid DMA descriptor or %NULL in case of failure.
  */
 static struct dma_async_tx_descriptor *
 ep93xx_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			 unsigned int sg_len, enum dma_transfer_direction dir,
-			 unsigned long flags)
+			 unsigned long flags, void *context)
 {
 	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
 	struct ep93xx_dma_desc *desc, *first;
@@ -1056,6 +1049,7 @@ fail:
  * @buf_len: length of the buffer (in bytes)
  * @period_len: lenght of a single period
  * @dir: direction of the operation
+ * @context: operation context (ignored)
  *
  * Prepares a descriptor for cyclic DMA operation. This means that once the
  * descriptor is submitted, we will be submitting in a @period_len sized
@@ -1068,7 +1062,7 @@ fail:
 static struct dma_async_tx_descriptor *
 ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 			   size_t buf_len, size_t period_len,
-			   enum dma_transfer_direction dir)
+			   enum dma_transfer_direction dir, void *context)
 {
 	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
 	struct ep93xx_dma_desc *desc, *first;
@@ -1248,18 +1242,13 @@ static enum dma_status ep93xx_dma_tx_status(struct dma_chan *chan,
 					    struct dma_tx_state *state)
 {
 	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
-	dma_cookie_t last_used, last_completed;
 	enum dma_status ret;
 	unsigned long flags;
 
 	spin_lock_irqsave(&edmac->lock, flags);
-	last_used = chan->cookie;
-	last_completed = edmac->last_completed;
+	ret = dma_cookie_status(chan, cookie, state);
 	spin_unlock_irqrestore(&edmac->lock, flags);
 
-	ret = dma_async_is_complete(cookie, last_completed, last_used);
-	dma_set_tx_state(state, last_completed, last_used, 0);
-
 	return ret;
 }
 
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index b98070c33ca9..8f84761f98ba 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -35,6 +35,7 @@
 #include <linux/dmapool.h>
 #include <linux/of_platform.h>
 
+#include "dmaengine.h"
 #include "fsldma.h"
 
 #define chan_dbg(chan, fmt, arg...)					\
@@ -413,17 +414,10 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	 * assign cookies to all of the software descriptors
 	 * that make up this transaction
 	 */
-	cookie = chan->common.cookie;
 	list_for_each_entry(child, &desc->tx_list, node) {
-		cookie++;
-		if (cookie < DMA_MIN_COOKIE)
-			cookie = DMA_MIN_COOKIE;
-
-		child->async_tx.cookie = cookie;
+		cookie = dma_cookie_assign(&child->async_tx);
 	}
 
-	chan->common.cookie = cookie;
-
 	/* put this transaction onto the tail of the pending queue */
 	append_ld_queue(chan, desc);
 
@@ -765,6 +759,7 @@ fail:
  * @sg_len: number of entries in @scatterlist
  * @direction: DMA direction
  * @flags: DMAEngine flags
+ * @context: transaction context (ignored)
  *
  * Prepare a set of descriptors for a DMA_SLAVE transaction. Following the
  * DMA_SLAVE API, this gets the device-specific information from the
@@ -772,7 +767,8 @@ fail:
  */
 static struct dma_async_tx_descriptor *fsl_dma_prep_slave_sg(
 	struct dma_chan *dchan, struct scatterlist *sgl, unsigned int sg_len,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
 {
 	/*
 	 * This operation is not supported on the Freescale DMA controller
@@ -984,19 +980,14 @@ static enum dma_status fsl_tx_status(struct dma_chan *dchan,
 					struct dma_tx_state *txstate)
 {
 	struct fsldma_chan *chan = to_fsl_chan(dchan);
-	dma_cookie_t last_complete;
-	dma_cookie_t last_used;
+	enum dma_status ret;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chan->desc_lock, flags);
-
-	last_complete = chan->completed_cookie;
-	last_used = dchan->cookie;
-
+	ret = dma_cookie_status(dchan, cookie, txstate);
 	spin_unlock_irqrestore(&chan->desc_lock, flags);
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return ret;
 }
 
 /*----------------------------------------------------------------------------*/
@@ -1087,8 +1078,8 @@ static void dma_do_tasklet(unsigned long data)
 
 		desc = to_fsl_desc(chan->ld_running.prev);
 		cookie = desc->async_tx.cookie;
+		dma_cookie_complete(&desc->async_tx);
 
-		chan->completed_cookie = cookie;
 		chan_dbg(chan, "completed_cookie=%d\n", cookie);
 	}
 
@@ -1303,6 +1294,7 @@ static int __devinit fsl_dma_chan_probe(struct fsldma_device *fdev,
 	chan->idle = true;
 
 	chan->common.device = &fdev->common;
+	dma_cookie_init(&chan->common);
 
 	/* find the IRQ line, if it exists in the device tree */
 	chan->irq = irq_of_parse_and_map(node, 0);
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 9cb5aa57c677..f5c38791fc74 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -137,7 +137,6 @@ struct fsldma_device {
 struct fsldma_chan {
 	char name[8];			/* Channel name */
 	struct fsldma_chan_regs __iomem *regs;
-	dma_cookie_t completed_cookie;	/* The maximum cookie completed */
 	spinlock_t desc_lock;		/* Descriptor operation lock */
 	struct list_head ld_pending;	/* Link descriptors queue */
 	struct list_head ld_running;	/* Link descriptors queue */
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 38586ba8da91..a45b5d2a5987 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -5,6 +5,7 @@
  * found on i.MX1/21/27
  *
  * Copyright 2010 Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>
+ * Copyright 2012 Javier Martin, Vista Silicon <javier.martin@vista-silicon.com>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
@@ -22,37 +23,159 @@
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 #include <linux/dmaengine.h>
 #include <linux/module.h>
 
 #include <asm/irq.h>
-#include <mach/dma-v1.h>
+#include <mach/dma.h>
 #include <mach/hardware.h>
 
+#include "dmaengine.h"
+#define IMXDMA_MAX_CHAN_DESCRIPTORS	16
+#define IMX_DMA_CHANNELS  16
+
+#define IMX_DMA_2D_SLOTS	2
+#define IMX_DMA_2D_SLOT_A	0
+#define IMX_DMA_2D_SLOT_B	1
+
+#define IMX_DMA_LENGTH_LOOP	((unsigned int)-1)
+#define IMX_DMA_MEMSIZE_32	(0 << 4)
+#define IMX_DMA_MEMSIZE_8	(1 << 4)
+#define IMX_DMA_MEMSIZE_16	(2 << 4)
+#define IMX_DMA_TYPE_LINEAR	(0 << 10)
+#define IMX_DMA_TYPE_2D		(1 << 10)
+#define IMX_DMA_TYPE_FIFO	(2 << 10)
+
+#define IMX_DMA_ERR_BURST     (1 << 0)
+#define IMX_DMA_ERR_REQUEST   (1 << 1)
+#define IMX_DMA_ERR_TRANSFER  (1 << 2)
+#define IMX_DMA_ERR_BUFFER    (1 << 3)
+#define IMX_DMA_ERR_TIMEOUT   (1 << 4)
+
+#define DMA_DCR     0x00		/* Control Register */
+#define DMA_DISR    0x04		/* Interrupt status Register */
+#define DMA_DIMR    0x08		/* Interrupt mask Register */
+#define DMA_DBTOSR  0x0c		/* Burst timeout status Register */
+#define DMA_DRTOSR  0x10		/* Request timeout Register */
+#define DMA_DSESR   0x14		/* Transfer Error Status Register */
+#define DMA_DBOSR   0x18		/* Buffer overflow status Register */
+#define DMA_DBTOCR  0x1c		/* Burst timeout control Register */
+#define DMA_WSRA    0x40		/* W-Size Register A */
+#define DMA_XSRA    0x44		/* X-Size Register A */
+#define DMA_YSRA    0x48		/* Y-Size Register A */
+#define DMA_WSRB    0x4c		/* W-Size Register B */
+#define DMA_XSRB    0x50		/* X-Size Register B */
+#define DMA_YSRB    0x54		/* Y-Size Register B */
+#define DMA_SAR(x)  (0x80 + ((x) << 6))	/* Source Address Registers */
+#define DMA_DAR(x)  (0x84 + ((x) << 6))	/* Destination Address Registers */
+#define DMA_CNTR(x) (0x88 + ((x) << 6))	/* Count Registers */
+#define DMA_CCR(x)  (0x8c + ((x) << 6))	/* Control Registers */
+#define DMA_RSSR(x) (0x90 + ((x) << 6))	/* Request source select Registers */
+#define DMA_BLR(x)  (0x94 + ((x) << 6))	/* Burst length Registers */
+#define DMA_RTOR(x) (0x98 + ((x) << 6))	/* Request timeout Registers */
+#define DMA_BUCR(x) (0x98 + ((x) << 6))	/* Bus Utilization Registers */
+#define DMA_CCNR(x) (0x9C + ((x) << 6))	/* Channel counter Registers */
+
+#define DCR_DRST           (1<<1)
+#define DCR_DEN            (1<<0)
+#define DBTOCR_EN          (1<<15)
+#define DBTOCR_CNT(x)      ((x) & 0x7fff)
+#define CNTR_CNT(x)        ((x) & 0xffffff)
+#define CCR_ACRPT          (1<<14)
+#define CCR_DMOD_LINEAR    (0x0 << 12)
+#define CCR_DMOD_2D        (0x1 << 12)
+#define CCR_DMOD_FIFO      (0x2 << 12)
+#define CCR_DMOD_EOBFIFO   (0x3 << 12)
+#define CCR_SMOD_LINEAR    (0x0 << 10)
+#define CCR_SMOD_2D        (0x1 << 10)
+#define CCR_SMOD_FIFO      (0x2 << 10)
+#define CCR_SMOD_EOBFIFO   (0x3 << 10)
+#define CCR_MDIR_DEC       (1<<9)
+#define CCR_MSEL_B         (1<<8)
+#define CCR_DSIZ_32        (0x0 << 6)
+#define CCR_DSIZ_8         (0x1 << 6)
+#define CCR_DSIZ_16        (0x2 << 6)
+#define CCR_SSIZ_32        (0x0 << 4)
+#define CCR_SSIZ_8         (0x1 << 4)
+#define CCR_SSIZ_16        (0x2 << 4)
+#define CCR_REN            (1<<3)
+#define CCR_RPT            (1<<2)
+#define CCR_FRC            (1<<1)
+#define CCR_CEN            (1<<0)
+#define RTOR_EN            (1<<15)
+#define RTOR_CLK           (1<<14)
+#define RTOR_PSC           (1<<13)
+
+enum  imxdma_prep_type {
+	IMXDMA_DESC_MEMCPY,
+	IMXDMA_DESC_INTERLEAVED,
+	IMXDMA_DESC_SLAVE_SG,
+	IMXDMA_DESC_CYCLIC,
+};
+
+struct imx_dma_2d_config {
+	u16		xsr;
+	u16		ysr;
+	u16		wsr;
+	int		count;
+};
+
+struct imxdma_desc {
+	struct list_head		node;
+	struct dma_async_tx_descriptor	desc;
+	enum dma_status			status;
+	dma_addr_t			src;
+	dma_addr_t			dest;
+	size_t				len;
+	enum dma_transfer_direction	direction;
+	enum imxdma_prep_type		type;
+	/* For memcpy and interleaved */
+	unsigned int			config_port;
+	unsigned int			config_mem;
+	/* For interleaved transfers */
+	unsigned int			x;
+	unsigned int			y;
+	unsigned int			w;
+	/* For slave sg and cyclic */
+	struct scatterlist		*sg;
+	unsigned int			sgcount;
+};
+
 struct imxdma_channel {
+	int				hw_chaining;
+	struct timer_list		watchdog;
 	struct imxdma_engine		*imxdma;
 	unsigned int			channel;
-	unsigned int			imxdma_channel;
 
+	struct tasklet_struct		dma_tasklet;
+	struct list_head		ld_free;
+	struct list_head		ld_queue;
+	struct list_head		ld_active;
+	int				descs_allocated;
 	enum dma_slave_buswidth		word_size;
 	dma_addr_t			per_address;
 	u32				watermark_level;
 	struct dma_chan			chan;
-	spinlock_t			lock;
 	struct dma_async_tx_descriptor	desc;
-	dma_cookie_t			last_completed;
 	enum dma_status			status;
 	int				dma_request;
 	struct scatterlist		*sg_list;
+	u32				ccr_from_device;
+	u32				ccr_to_device;
+	bool				enabled_2d;
+	int				slot_2d;
 };
 
-#define MAX_DMA_CHANNELS 8
-
 struct imxdma_engine {
 	struct device			*dev;
 	struct device_dma_parameters	dma_parms;
 	struct dma_device		dma_device;
-	struct imxdma_channel		channel[MAX_DMA_CHANNELS];
+	void __iomem			*base;
+	struct clk			*dma_clk;
+	spinlock_t			lock;
+	struct imx_dma_2d_config	slots_2d[IMX_DMA_2D_SLOTS];
+	struct imxdma_channel		channel[IMX_DMA_CHANNELS];
 };
 
 static struct imxdma_channel *to_imxdma_chan(struct dma_chan *chan)
@@ -60,36 +183,418 @@ static struct imxdma_channel *to_imxdma_chan(struct dma_chan *chan)
 	return container_of(chan, struct imxdma_channel, chan);
 }
 
-static void imxdma_handle(struct imxdma_channel *imxdmac)
+static inline bool imxdma_chan_is_doing_cyclic(struct imxdma_channel *imxdmac)
+{
+	struct imxdma_desc *desc;
+
+	if (!list_empty(&imxdmac->ld_active)) {
+		desc = list_first_entry(&imxdmac->ld_active, struct imxdma_desc,
+					node);
+		if (desc->type == IMXDMA_DESC_CYCLIC)
+			return true;
+	}
+	return false;
+}
+
+
+
+static void imx_dmav1_writel(struct imxdma_engine *imxdma, unsigned val,
+			     unsigned offset)
+{
+	__raw_writel(val, imxdma->base + offset);
+}
+
+static unsigned imx_dmav1_readl(struct imxdma_engine *imxdma, unsigned offset)
+{
+	return __raw_readl(imxdma->base + offset);
+}
+
+static int imxdma_hw_chain(struct imxdma_channel *imxdmac)
+{
+	if (cpu_is_mx27())
+		return imxdmac->hw_chaining;
+	else
+		return 0;
+}
+
+/*
+ * imxdma_sg_next - prepare next chunk for scatter-gather DMA emulation
+ */
+static inline int imxdma_sg_next(struct imxdma_desc *d)
 {
-	if (imxdmac->desc.callback)
-		imxdmac->desc.callback(imxdmac->desc.callback_param);
-	imxdmac->last_completed = imxdmac->desc.cookie;
+	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct scatterlist *sg = d->sg;
+	unsigned long now;
+
+	now = min(d->len, sg->length);
+	if (d->len != IMX_DMA_LENGTH_LOOP)
+		d->len -= now;
+
+	if (d->direction == DMA_DEV_TO_MEM)
+		imx_dmav1_writel(imxdma, sg->dma_address,
+				 DMA_DAR(imxdmac->channel));
+	else
+		imx_dmav1_writel(imxdma, sg->dma_address,
+				 DMA_SAR(imxdmac->channel));
+
+	imx_dmav1_writel(imxdma, now, DMA_CNTR(imxdmac->channel));
+
+	dev_dbg(imxdma->dev, " %s channel: %d dst 0x%08x, src 0x%08x, "
+		"size 0x%08x\n", __func__, imxdmac->channel,
+		 imx_dmav1_readl(imxdma, DMA_DAR(imxdmac->channel)),
+		 imx_dmav1_readl(imxdma, DMA_SAR(imxdmac->channel)),
+		 imx_dmav1_readl(imxdma, DMA_CNTR(imxdmac->channel)));
+
+	return now;
 }
 
-static void imxdma_irq_handler(int channel, void *data)
+static void imxdma_enable_hw(struct imxdma_desc *d)
 {
-	struct imxdma_channel *imxdmac = data;
+	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	int channel = imxdmac->channel;
+	unsigned long flags;
+
+	dev_dbg(imxdma->dev, "%s channel %d\n", __func__, channel);
+
+	local_irq_save(flags);
+
+	imx_dmav1_writel(imxdma, 1 << channel, DMA_DISR);
+	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_DIMR) &
+			 ~(1 << channel), DMA_DIMR);
+	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_CCR(channel)) |
+			 CCR_CEN | CCR_ACRPT, DMA_CCR(channel));
+
+	if ((cpu_is_mx21() || cpu_is_mx27()) &&
+			d->sg && imxdma_hw_chain(imxdmac)) {
+		d->sg = sg_next(d->sg);
+		if (d->sg) {
+			u32 tmp;
+			imxdma_sg_next(d);
+			tmp = imx_dmav1_readl(imxdma, DMA_CCR(channel));
+			imx_dmav1_writel(imxdma, tmp | CCR_RPT | CCR_ACRPT,
+					 DMA_CCR(channel));
+		}
+	}
+
+	local_irq_restore(flags);
+}
+
+static void imxdma_disable_hw(struct imxdma_channel *imxdmac)
+{
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	int channel = imxdmac->channel;
+	unsigned long flags;
+
+	dev_dbg(imxdma->dev, "%s channel %d\n", __func__, channel);
+
+	if (imxdma_hw_chain(imxdmac))
+		del_timer(&imxdmac->watchdog);
+
+	local_irq_save(flags);
+	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_DIMR) |
+			 (1 << channel), DMA_DIMR);
+	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_CCR(channel)) &
+			 ~CCR_CEN, DMA_CCR(channel));
+	imx_dmav1_writel(imxdma, 1 << channel, DMA_DISR);
+	local_irq_restore(flags);
+}
+
+static void imxdma_watchdog(unsigned long data)
+{
+	struct imxdma_channel *imxdmac = (struct imxdma_channel *)data;
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	int channel = imxdmac->channel;
+
+	imx_dmav1_writel(imxdma, 0, DMA_CCR(channel));
 
-	imxdmac->status = DMA_SUCCESS;
-	imxdma_handle(imxdmac);
+	/* Tasklet watchdog error handler */
+	tasklet_schedule(&imxdmac->dma_tasklet);
+	dev_dbg(imxdma->dev, "channel %d: watchdog timeout!\n",
+		imxdmac->channel);
 }
 
-static void imxdma_err_handler(int channel, void *data, int error)
+static irqreturn_t imxdma_err_handler(int irq, void *dev_id)
 {
-	struct imxdma_channel *imxdmac = data;
+	struct imxdma_engine *imxdma = dev_id;
+	unsigned int err_mask;
+	int i, disr;
+	int errcode;
+
+	disr = imx_dmav1_readl(imxdma, DMA_DISR);
+
+	err_mask = imx_dmav1_readl(imxdma, DMA_DBTOSR) |
+		   imx_dmav1_readl(imxdma, DMA_DRTOSR) |
+		   imx_dmav1_readl(imxdma, DMA_DSESR)  |
+		   imx_dmav1_readl(imxdma, DMA_DBOSR);
+
+	if (!err_mask)
+		return IRQ_HANDLED;
+
+	imx_dmav1_writel(imxdma, disr & err_mask, DMA_DISR);
+
+	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
+		if (!(err_mask & (1 << i)))
+			continue;
+		errcode = 0;
+
+		if (imx_dmav1_readl(imxdma, DMA_DBTOSR) & (1 << i)) {
+			imx_dmav1_writel(imxdma, 1 << i, DMA_DBTOSR);
+			errcode |= IMX_DMA_ERR_BURST;
+		}
+		if (imx_dmav1_readl(imxdma, DMA_DRTOSR) & (1 << i)) {
+			imx_dmav1_writel(imxdma, 1 << i, DMA_DRTOSR);
+			errcode |= IMX_DMA_ERR_REQUEST;
+		}
+		if (imx_dmav1_readl(imxdma, DMA_DSESR) & (1 << i)) {
+			imx_dmav1_writel(imxdma, 1 << i, DMA_DSESR);
+			errcode |= IMX_DMA_ERR_TRANSFER;
+		}
+		if (imx_dmav1_readl(imxdma, DMA_DBOSR) & (1 << i)) {
+			imx_dmav1_writel(imxdma, 1 << i, DMA_DBOSR);
+			errcode |= IMX_DMA_ERR_BUFFER;
+		}
+		/* Tasklet error handler */
+		tasklet_schedule(&imxdma->channel[i].dma_tasklet);
+
+		printk(KERN_WARNING
+		       "DMA timeout on channel %d -%s%s%s%s\n", i,
+		       errcode & IMX_DMA_ERR_BURST ?    " burst" : "",
+		       errcode & IMX_DMA_ERR_REQUEST ?  " request" : "",
+		       errcode & IMX_DMA_ERR_TRANSFER ? " transfer" : "",
+		       errcode & IMX_DMA_ERR_BUFFER ?   " buffer" : "");
+	}
+	return IRQ_HANDLED;
+}
+
+static void dma_irq_handle_channel(struct imxdma_channel *imxdmac)
+{
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	int chno = imxdmac->channel;
+	struct imxdma_desc *desc;
+
+	spin_lock(&imxdma->lock);
+	if (list_empty(&imxdmac->ld_active)) {
+		spin_unlock(&imxdma->lock);
+		goto out;
+	}
+
+	desc = list_first_entry(&imxdmac->ld_active,
+				struct imxdma_desc,
+				node);
+	spin_unlock(&imxdma->lock);
+
+	if (desc->sg) {
+		u32 tmp;
+		desc->sg = sg_next(desc->sg);
+
+		if (desc->sg) {
+			imxdma_sg_next(desc);
+
+			tmp = imx_dmav1_readl(imxdma, DMA_CCR(chno));
+
+			if (imxdma_hw_chain(imxdmac)) {
+				/* FIXME: The timeout should probably be
+				 * configurable
+				 */
+				mod_timer(&imxdmac->watchdog,
+					jiffies + msecs_to_jiffies(500));
+
+				tmp |= CCR_CEN | CCR_RPT | CCR_ACRPT;
+				imx_dmav1_writel(imxdma, tmp, DMA_CCR(chno));
+			} else {
+				imx_dmav1_writel(imxdma, tmp & ~CCR_CEN,
+						 DMA_CCR(chno));
+				tmp |= CCR_CEN;
+			}
+
+			imx_dmav1_writel(imxdma, tmp, DMA_CCR(chno));
+
+			if (imxdma_chan_is_doing_cyclic(imxdmac))
+				/* Tasklet progression */
+				tasklet_schedule(&imxdmac->dma_tasklet);
+
+			return;
+		}
+
+		if (imxdma_hw_chain(imxdmac)) {
+			del_timer(&imxdmac->watchdog);
+			return;
+		}
+	}
+
+out:
+	imx_dmav1_writel(imxdma, 0, DMA_CCR(chno));
+	/* Tasklet irq */
+	tasklet_schedule(&imxdmac->dma_tasklet);
+}
+
+static irqreturn_t dma_irq_handler(int irq, void *dev_id)
+{
+	struct imxdma_engine *imxdma = dev_id;
+	int i, disr;
+
+	if (cpu_is_mx21() || cpu_is_mx27())
+		imxdma_err_handler(irq, dev_id);
+
+	disr = imx_dmav1_readl(imxdma, DMA_DISR);
+
+	dev_dbg(imxdma->dev, "%s called, disr=0x%08x\n", __func__, disr);
+
+	imx_dmav1_writel(imxdma, disr, DMA_DISR);
+	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
+		if (disr & (1 << i))
+			dma_irq_handle_channel(&imxdma->channel[i]);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int imxdma_xfer_desc(struct imxdma_desc *d)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	unsigned long flags;
+	int slot = -1;
+	int i;
+
+	/* Configure and enable */
+	switch (d->type) {
+	case IMXDMA_DESC_INTERLEAVED:
+		/* Try to get a free 2D slot */
+		spin_lock_irqsave(&imxdma->lock, flags);
+		for (i = 0; i < IMX_DMA_2D_SLOTS; i++) {
+			if ((imxdma->slots_2d[i].count > 0) &&
+			((imxdma->slots_2d[i].xsr != d->x) ||
+			(imxdma->slots_2d[i].ysr != d->y) ||
+			(imxdma->slots_2d[i].wsr != d->w)))
+				continue;
+			slot = i;
+			break;
+		}
+		if (slot < 0)
+			return -EBUSY;
+
+		imxdma->slots_2d[slot].xsr = d->x;
+		imxdma->slots_2d[slot].ysr = d->y;
+		imxdma->slots_2d[slot].wsr = d->w;
+		imxdma->slots_2d[slot].count++;
+
+		imxdmac->slot_2d = slot;
+		imxdmac->enabled_2d = true;
+		spin_unlock_irqrestore(&imxdma->lock, flags);
+
+		if (slot == IMX_DMA_2D_SLOT_A) {
+			d->config_mem &= ~CCR_MSEL_B;
+			d->config_port &= ~CCR_MSEL_B;
+			imx_dmav1_writel(imxdma, d->x, DMA_XSRA);
+			imx_dmav1_writel(imxdma, d->y, DMA_YSRA);
+			imx_dmav1_writel(imxdma, d->w, DMA_WSRA);
+		} else {
+			d->config_mem |= CCR_MSEL_B;
+			d->config_port |= CCR_MSEL_B;
+			imx_dmav1_writel(imxdma, d->x, DMA_XSRB);
+			imx_dmav1_writel(imxdma, d->y, DMA_YSRB);
+			imx_dmav1_writel(imxdma, d->w, DMA_WSRB);
+		}
+		/*
+		 * We fall-through here intentionally, since a 2D transfer is
+		 * similar to MEMCPY just adding the 2D slot configuration.
+		 */
+	case IMXDMA_DESC_MEMCPY:
+		imx_dmav1_writel(imxdma, d->src, DMA_SAR(imxdmac->channel));
+		imx_dmav1_writel(imxdma, d->dest, DMA_DAR(imxdmac->channel));
+		imx_dmav1_writel(imxdma, d->config_mem | (d->config_port << 2),
+			 DMA_CCR(imxdmac->channel));
+
+		imx_dmav1_writel(imxdma, d->len, DMA_CNTR(imxdmac->channel));
+
+		dev_dbg(imxdma->dev, "%s channel: %d dest=0x%08x src=0x%08x "
+			"dma_length=%d\n", __func__, imxdmac->channel,
+			d->dest, d->src, d->len);
+
+		break;
+	/* Cyclic transfer is the same as slave_sg with special sg configuration. */
+	case IMXDMA_DESC_CYCLIC:
+	case IMXDMA_DESC_SLAVE_SG:
+		if (d->direction == DMA_DEV_TO_MEM) {
+			imx_dmav1_writel(imxdma, imxdmac->per_address,
+					 DMA_SAR(imxdmac->channel));
+			imx_dmav1_writel(imxdma, imxdmac->ccr_from_device,
+					 DMA_CCR(imxdmac->channel));
+
+			dev_dbg(imxdma->dev, "%s channel: %d sg=%p sgcount=%d "
+				"total length=%d dev_addr=0x%08x (dev2mem)\n",
+				__func__, imxdmac->channel, d->sg, d->sgcount,
+				d->len, imxdmac->per_address);
+		} else if (d->direction == DMA_MEM_TO_DEV) {
+			imx_dmav1_writel(imxdma, imxdmac->per_address,
+					 DMA_DAR(imxdmac->channel));
+			imx_dmav1_writel(imxdma, imxdmac->ccr_to_device,
+					 DMA_CCR(imxdmac->channel));
+
+			dev_dbg(imxdma->dev, "%s channel: %d sg=%p sgcount=%d "
+				"total length=%d dev_addr=0x%08x (mem2dev)\n",
+				__func__, imxdmac->channel, d->sg, d->sgcount,
+				d->len, imxdmac->per_address);
+		} else {
+			dev_err(imxdma->dev, "%s channel: %d bad dma mode\n",
+				__func__, imxdmac->channel);
+			return -EINVAL;
+		}
+
+		imxdma_sg_next(d);
 
-	imxdmac->status = DMA_ERROR;
-	imxdma_handle(imxdmac);
+		break;
+	default:
+		return -EINVAL;
+	}
+	imxdma_enable_hw(d);
+	return 0;
 }
 
-static void imxdma_progression(int channel, void *data,
-		struct scatterlist *sg)
+static void imxdma_tasklet(unsigned long data)
 {
-	struct imxdma_channel *imxdmac = data;
+	struct imxdma_channel *imxdmac = (void *)data;
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc;
 
-	imxdmac->status = DMA_SUCCESS;
-	imxdma_handle(imxdmac);
+	spin_lock(&imxdma->lock);
+
+	if (list_empty(&imxdmac->ld_active)) {
+		/* Someone might have called terminate all */
+		goto out;
+	}
+	desc = list_first_entry(&imxdmac->ld_active, struct imxdma_desc, node);
+
+	if (desc->desc.callback)
+		desc->desc.callback(desc->desc.callback_param);
+
+	dma_cookie_complete(&desc->desc);
+
+	/* If we are dealing with a cyclic descriptor keep it on ld_active */
+	if (imxdma_chan_is_doing_cyclic(imxdmac))
+		goto out;
+
+	/* Free 2D slot if it was an interleaved transfer */
+	if (imxdmac->enabled_2d) {
+		imxdma->slots_2d[imxdmac->slot_2d].count--;
+		imxdmac->enabled_2d = false;
+	}
+
+	list_move_tail(imxdmac->ld_active.next, &imxdmac->ld_free);
+
+	if (!list_empty(&imxdmac->ld_queue)) {
+		desc = list_first_entry(&imxdmac->ld_queue, struct imxdma_desc,
+					node);
+		list_move_tail(imxdmac->ld_queue.next, &imxdmac->ld_active);
+		if (imxdma_xfer_desc(desc) < 0)
+			dev_warn(imxdma->dev, "%s: channel: %d couldn't xfer desc\n",
+				 __func__, imxdmac->channel);
+	}
+out:
+	spin_unlock(&imxdma->lock);
 }
 
 static int imxdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -97,13 +602,18 @@ static int imxdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct dma_slave_config *dmaengine_cfg = (void *)arg;
-	int ret;
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	unsigned long flags;
 	unsigned int mode = 0;
 
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
-		imxdmac->status = DMA_ERROR;
-		imx_dma_disable(imxdmac->imxdma_channel);
+		imxdma_disable_hw(imxdmac);
+
+		spin_lock_irqsave(&imxdma->lock, flags);
+		list_splice_tail_init(&imxdmac->ld_active, &imxdmac->ld_free);
+		list_splice_tail_init(&imxdmac->ld_queue, &imxdmac->ld_free);
+		spin_unlock_irqrestore(&imxdma->lock, flags);
 		return 0;
 	case DMA_SLAVE_CONFIG:
 		if (dmaengine_cfg->direction == DMA_DEV_TO_MEM) {
@@ -128,16 +638,22 @@ static int imxdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 			mode = IMX_DMA_MEMSIZE_32;
 			break;
 		}
-		ret = imx_dma_config_channel(imxdmac->imxdma_channel,
-				mode | IMX_DMA_TYPE_FIFO,
-				IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR,
-				imxdmac->dma_request, 1);
-
-		if (ret)
-			return ret;
 
-		imx_dma_config_burstlen(imxdmac->imxdma_channel,
-				imxdmac->watermark_level * imxdmac->word_size);
+		imxdmac->hw_chaining = 1;
+		if (!imxdma_hw_chain(imxdmac))
+			return -EINVAL;
+		imxdmac->ccr_from_device = (mode | IMX_DMA_TYPE_FIFO) |
+			((IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR) << 2) |
+			CCR_REN;
+		imxdmac->ccr_to_device =
+			(IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR) |
+			((mode | IMX_DMA_TYPE_FIFO) << 2) | CCR_REN;
+		imx_dmav1_writel(imxdma, imxdmac->dma_request,
+				 DMA_RSSR(imxdmac->channel));
+
+		/* Set burst length */
+		imx_dmav1_writel(imxdma, imxdmac->watermark_level *
+				imxdmac->word_size, DMA_BLR(imxdmac->channel));
 
 		return 0;
 	default:
@@ -151,43 +667,20 @@ static enum dma_status imxdma_tx_status(struct dma_chan *chan,
 					    dma_cookie_t cookie,
 					    struct dma_tx_state *txstate)
 {
-	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
-	dma_cookie_t last_used;
-	enum dma_status ret;
-
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, imxdmac->last_completed, last_used);
-	dma_set_tx_state(txstate, imxdmac->last_completed, last_used, 0);
-
-	return ret;
-}
-
-static dma_cookie_t imxdma_assign_cookie(struct imxdma_channel *imxdma)
-{
-	dma_cookie_t cookie = imxdma->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	imxdma->chan.cookie = cookie;
-	imxdma->desc.cookie = cookie;
-
-	return cookie;
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static dma_cookie_t imxdma_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(tx->chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	dma_cookie_t cookie;
+	unsigned long flags;
 
-	spin_lock_irq(&imxdmac->lock);
-
-	cookie = imxdma_assign_cookie(imxdmac);
-
-	imx_dma_enable(imxdmac->imxdma_channel);
-
-	spin_unlock_irq(&imxdmac->lock);
+	spin_lock_irqsave(&imxdma->lock, flags);
+	list_move_tail(imxdmac->ld_free.next, &imxdmac->ld_queue);
+	cookie = dma_cookie_assign(tx);
+	spin_unlock_irqrestore(&imxdma->lock, flags);
 
 	return cookie;
 }
@@ -197,23 +690,52 @@ static int imxdma_alloc_chan_resources(struct dma_chan *chan)
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct imx_dma_data *data = chan->private;
 
-	imxdmac->dma_request = data->dma_request;
+	if (data != NULL)
+		imxdmac->dma_request = data->dma_request;
 
-	dma_async_tx_descriptor_init(&imxdmac->desc, chan);
-	imxdmac->desc.tx_submit = imxdma_tx_submit;
-	/* txd.flags will be overwritten in prep funcs */
-	imxdmac->desc.flags = DMA_CTRL_ACK;
+	while (imxdmac->descs_allocated < IMXDMA_MAX_CHAN_DESCRIPTORS) {
+		struct imxdma_desc *desc;
 
-	imxdmac->status = DMA_SUCCESS;
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+		if (!desc)
+			break;
+		__memzero(&desc->desc, sizeof(struct dma_async_tx_descriptor));
+		dma_async_tx_descriptor_init(&desc->desc, chan);
+		desc->desc.tx_submit = imxdma_tx_submit;
+		/* txd.flags will be overwritten in prep funcs */
+		desc->desc.flags = DMA_CTRL_ACK;
+		desc->status = DMA_SUCCESS;
+
+		list_add_tail(&desc->node, &imxdmac->ld_free);
+		imxdmac->descs_allocated++;
+	}
 
-	return 0;
+	if (!imxdmac->descs_allocated)
+		return -ENOMEM;
+
+	return imxdmac->descs_allocated;
 }
 
 static void imxdma_free_chan_resources(struct dma_chan *chan)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc, *_desc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&imxdma->lock, flags);
+
+	imxdma_disable_hw(imxdmac);
+	list_splice_tail_init(&imxdmac->ld_active, &imxdmac->ld_free);
+	list_splice_tail_init(&imxdmac->ld_queue, &imxdmac->ld_free);
 
-	imx_dma_disable(imxdmac->imxdma_channel);
+	spin_unlock_irqrestore(&imxdma->lock, flags);
+
+	list_for_each_entry_safe(desc, _desc, &imxdmac->ld_free, node) {
+		kfree(desc);
+		imxdmac->descs_allocated--;
+	}
+	INIT_LIST_HEAD(&imxdmac->ld_free);
 
 	if (imxdmac->sg_list) {
 		kfree(imxdmac->sg_list);
@@ -224,27 +746,23 @@ static void imxdma_free_chan_resources(struct dma_chan *chan)
 static struct dma_async_tx_descriptor *imxdma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct scatterlist *sg;
-	int i, ret, dma_length = 0;
-	unsigned int dmamode;
+	int i, dma_length = 0;
+	struct imxdma_desc *desc;
 
-	if (imxdmac->status == DMA_IN_PROGRESS)
+	if (list_empty(&imxdmac->ld_free) ||
+	    imxdma_chan_is_doing_cyclic(imxdmac))
 		return NULL;
 
-	imxdmac->status = DMA_IN_PROGRESS;
+	desc = list_first_entry(&imxdmac->ld_free, struct imxdma_desc, node);
 
 	for_each_sg(sgl, sg, sg_len, i) {
 		dma_length += sg->length;
 	}
 
-	if (direction == DMA_DEV_TO_MEM)
-		dmamode = DMA_MODE_READ;
-	else
-		dmamode = DMA_MODE_WRITE;
-
 	switch (imxdmac->word_size) {
 	case DMA_SLAVE_BUSWIDTH_4_BYTES:
 		if (sgl->length & 3 || sgl->dma_address & 3)
@@ -260,37 +778,41 @@ static struct dma_async_tx_descriptor *imxdma_prep_slave_sg(
 		return NULL;
 	}
 
-	ret = imx_dma_setup_sg(imxdmac->imxdma_channel, sgl, sg_len,
-		 dma_length, imxdmac->per_address, dmamode);
-	if (ret)
-		return NULL;
+	desc->type = IMXDMA_DESC_SLAVE_SG;
+	desc->sg = sgl;
+	desc->sgcount = sg_len;
+	desc->len = dma_length;
+	desc->direction = direction;
+	if (direction == DMA_DEV_TO_MEM) {
+		desc->src = imxdmac->per_address;
+	} else {
+		desc->dest = imxdmac->per_address;
+	}
+	desc->desc.callback = NULL;
+	desc->desc.callback_param = NULL;
 
-	return &imxdmac->desc;
+	return &desc->desc;
 }
 
 static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
-	int i, ret;
+	struct imxdma_desc *desc;
+	int i;
 	unsigned int periods = buf_len / period_len;
-	unsigned int dmamode;
 
 	dev_dbg(imxdma->dev, "%s channel: %d buf_len=%d period_len=%d\n",
 			__func__, imxdmac->channel, buf_len, period_len);
 
-	if (imxdmac->status == DMA_IN_PROGRESS)
+	if (list_empty(&imxdmac->ld_free) ||
+	    imxdma_chan_is_doing_cyclic(imxdmac))
 		return NULL;
-	imxdmac->status = DMA_IN_PROGRESS;
 
-	ret = imx_dma_setup_progression_handler(imxdmac->imxdma_channel,
-			imxdma_progression);
-	if (ret) {
-		dev_err(imxdma->dev, "Failed to setup the DMA handler\n");
-		return NULL;
-	}
+	desc = list_first_entry(&imxdmac->ld_free, struct imxdma_desc, node);
 
 	if (imxdmac->sg_list)
 		kfree(imxdmac->sg_list);
@@ -316,62 +838,221 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
 	imxdmac->sg_list[periods].page_link =
 		((unsigned long)imxdmac->sg_list | 0x01) & ~0x02;
 
-	if (direction == DMA_DEV_TO_MEM)
-		dmamode = DMA_MODE_READ;
-	else
-		dmamode = DMA_MODE_WRITE;
+	desc->type = IMXDMA_DESC_CYCLIC;
+	desc->sg = imxdmac->sg_list;
+	desc->sgcount = periods;
+	desc->len = IMX_DMA_LENGTH_LOOP;
+	desc->direction = direction;
+	if (direction == DMA_DEV_TO_MEM) {
+		desc->src = imxdmac->per_address;
+	} else {
+		desc->dest = imxdmac->per_address;
+	}
+	desc->desc.callback = NULL;
+	desc->desc.callback_param = NULL;
+
+	return &desc->desc;
+}
+
+static struct dma_async_tx_descriptor *imxdma_prep_dma_memcpy(
+	struct dma_chan *chan, dma_addr_t dest,
+	dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc;
 
-	ret = imx_dma_setup_sg(imxdmac->imxdma_channel, imxdmac->sg_list, periods,
-		 IMX_DMA_LENGTH_LOOP, imxdmac->per_address, dmamode);
-	if (ret)
+	dev_dbg(imxdma->dev, "%s channel: %d src=0x%x dst=0x%x len=%d\n",
+			__func__, imxdmac->channel, src, dest, len);
+
+	if (list_empty(&imxdmac->ld_free) ||
+	    imxdma_chan_is_doing_cyclic(imxdmac))
 		return NULL;
 
-	return &imxdmac->desc;
+	desc = list_first_entry(&imxdmac->ld_free, struct imxdma_desc, node);
+
+	desc->type = IMXDMA_DESC_MEMCPY;
+	desc->src = src;
+	desc->dest = dest;
+	desc->len = len;
+	desc->direction = DMA_MEM_TO_MEM;
+	desc->config_port = IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR;
+	desc->config_mem = IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR;
+	desc->desc.callback = NULL;
+	desc->desc.callback_param = NULL;
+
+	return &desc->desc;
+}
+
+static struct dma_async_tx_descriptor *imxdma_prep_dma_interleaved(
+	struct dma_chan *chan, struct dma_interleaved_template *xt,
+	unsigned long flags)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc;
+
+	dev_dbg(imxdma->dev, "%s channel: %d src_start=0x%x dst_start=0x%x\n"
+		"   src_sgl=%s dst_sgl=%s numf=%d frame_size=%d\n", __func__,
+		imxdmac->channel, xt->src_start, xt->dst_start,
+		xt->src_sgl ? "true" : "false", xt->dst_sgl ? "true" : "false",
+		xt->numf, xt->frame_size);
+
+	if (list_empty(&imxdmac->ld_free) ||
+	    imxdma_chan_is_doing_cyclic(imxdmac))
+		return NULL;
+
+	if (xt->frame_size != 1 || xt->numf <= 0 || xt->dir != DMA_MEM_TO_MEM)
+		return NULL;
+
+	desc = list_first_entry(&imxdmac->ld_free, struct imxdma_desc, node);
+
+	desc->type = IMXDMA_DESC_INTERLEAVED;
+	desc->src = xt->src_start;
+	desc->dest = xt->dst_start;
+	desc->x = xt->sgl[0].size;
+	desc->y = xt->numf;
+	desc->w = xt->sgl[0].icg + desc->x;
+	desc->len = desc->x * desc->y;
+	desc->direction = DMA_MEM_TO_MEM;
+	desc->config_port = IMX_DMA_MEMSIZE_32;
+	desc->config_mem = IMX_DMA_MEMSIZE_32;
+	if (xt->src_sgl)
+		desc->config_mem |= IMX_DMA_TYPE_2D;
+	if (xt->dst_sgl)
+		desc->config_port |= IMX_DMA_TYPE_2D;
+	desc->desc.callback = NULL;
+	desc->desc.callback_param = NULL;
+
+	return &desc->desc;
 }
 
 static void imxdma_issue_pending(struct dma_chan *chan)
 {
-	/*
-	 * Nothing to do. We only have a single descriptor
-	 */
+	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+	struct imxdma_desc *desc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&imxdma->lock, flags);
+	if (list_empty(&imxdmac->ld_active) &&
+	    !list_empty(&imxdmac->ld_queue)) {
+		desc = list_first_entry(&imxdmac->ld_queue,
+					struct imxdma_desc, node);
+
+		if (imxdma_xfer_desc(desc) < 0) {
+			dev_warn(imxdma->dev,
+				 "%s: channel: %d couldn't issue DMA xfer\n",
+				 __func__, imxdmac->channel);
+		} else {
+			list_move_tail(imxdmac->ld_queue.next,
+				       &imxdmac->ld_active);
+		}
+	}
+	spin_unlock_irqrestore(&imxdma->lock, flags);
 }
 
 static int __init imxdma_probe(struct platform_device *pdev)
-{
+	{
 	struct imxdma_engine *imxdma;
 	int ret, i;
 
+
 	imxdma = kzalloc(sizeof(*imxdma), GFP_KERNEL);
 	if (!imxdma)
 		return -ENOMEM;
 
+	if (cpu_is_mx1()) {
+		imxdma->base = MX1_IO_ADDRESS(MX1_DMA_BASE_ADDR);
+	} else if (cpu_is_mx21()) {
+		imxdma->base = MX21_IO_ADDRESS(MX21_DMA_BASE_ADDR);
+	} else if (cpu_is_mx27()) {
+		imxdma->base = MX27_IO_ADDRESS(MX27_DMA_BASE_ADDR);
+	} else {
+		kfree(imxdma);
+		return 0;
+	}
+
+	imxdma->dma_clk = clk_get(NULL, "dma");
+	if (IS_ERR(imxdma->dma_clk))
+		return PTR_ERR(imxdma->dma_clk);
+	clk_enable(imxdma->dma_clk);
+
+	/* reset DMA module */
+	imx_dmav1_writel(imxdma, DCR_DRST, DMA_DCR);
+
+	if (cpu_is_mx1()) {
+		ret = request_irq(MX1_DMA_INT, dma_irq_handler, 0, "DMA", imxdma);
+		if (ret) {
+			dev_warn(imxdma->dev, "Can't register IRQ for DMA\n");
+			kfree(imxdma);
+			return ret;
+		}
+
+		ret = request_irq(MX1_DMA_ERR, imxdma_err_handler, 0, "DMA", imxdma);
+		if (ret) {
+			dev_warn(imxdma->dev, "Can't register ERRIRQ for DMA\n");
+			free_irq(MX1_DMA_INT, NULL);
+			kfree(imxdma);
+			return ret;
+		}
+	}
+
+	/* enable DMA module */
+	imx_dmav1_writel(imxdma, DCR_DEN, DMA_DCR);
+
+	/* clear all interrupts */
+	imx_dmav1_writel(imxdma, (1 << IMX_DMA_CHANNELS) - 1, DMA_DISR);
+
+	/* disable interrupts */
+	imx_dmav1_writel(imxdma, (1 << IMX_DMA_CHANNELS) - 1, DMA_DIMR);
+
 	INIT_LIST_HEAD(&imxdma->dma_device.channels);
 
 	dma_cap_set(DMA_SLAVE, imxdma->dma_device.cap_mask);
 	dma_cap_set(DMA_CYCLIC, imxdma->dma_device.cap_mask);
+	dma_cap_set(DMA_MEMCPY, imxdma->dma_device.cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, imxdma->dma_device.cap_mask);
+
+	/* Initialize 2D global parameters */
+	for (i = 0; i < IMX_DMA_2D_SLOTS; i++)
+		imxdma->slots_2d[i].count = 0;
+
+	spin_lock_init(&imxdma->lock);
 
 	/* Initialize channel parameters */
-	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
+	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
 		struct imxdma_channel *imxdmac = &imxdma->channel[i];
 
-		imxdmac->imxdma_channel = imx_dma_request_by_prio("dmaengine",
-				DMA_PRIO_MEDIUM);
-		if ((int)imxdmac->channel < 0) {
-			ret = -ENODEV;
-			goto err_init;
+		if (cpu_is_mx21() || cpu_is_mx27()) {
+			ret = request_irq(MX2x_INT_DMACH0 + i,
+					dma_irq_handler, 0, "DMA", imxdma);
+			if (ret) {
+				dev_warn(imxdma->dev, "Can't register IRQ %d "
+					 "for DMA channel %d\n",
+					 MX2x_INT_DMACH0 + i, i);
+				goto err_init;
+			}
+			init_timer(&imxdmac->watchdog);
+			imxdmac->watchdog.function = &imxdma_watchdog;
+			imxdmac->watchdog.data = (unsigned long)imxdmac;
 		}
 
-		imx_dma_setup_handlers(imxdmac->imxdma_channel,
-		       imxdma_irq_handler, imxdma_err_handler, imxdmac);
-
 		imxdmac->imxdma = imxdma;
-		spin_lock_init(&imxdmac->lock);
 
+		INIT_LIST_HEAD(&imxdmac->ld_queue);
+		INIT_LIST_HEAD(&imxdmac->ld_free);
+		INIT_LIST_HEAD(&imxdmac->ld_active);
+
+		tasklet_init(&imxdmac->dma_tasklet, imxdma_tasklet,
+			     (unsigned long)imxdmac);
 		imxdmac->chan.device = &imxdma->dma_device;
+		dma_cookie_init(&imxdmac->chan);
 		imxdmac->channel = i;
 
 		/* Add the channel to the DMAC list */
-		list_add_tail(&imxdmac->chan.device_node, &imxdma->dma_device.channels);
+		list_add_tail(&imxdmac->chan.device_node,
+			      &imxdma->dma_device.channels);
 	}
 
 	imxdma->dev = &pdev->dev;
@@ -382,11 +1063,14 @@ static int __init imxdma_probe(struct platform_device *pdev)
 	imxdma->dma_device.device_tx_status = imxdma_tx_status;
 	imxdma->dma_device.device_prep_slave_sg = imxdma_prep_slave_sg;
 	imxdma->dma_device.device_prep_dma_cyclic = imxdma_prep_dma_cyclic;
+	imxdma->dma_device.device_prep_dma_memcpy = imxdma_prep_dma_memcpy;
+	imxdma->dma_device.device_prep_interleaved_dma = imxdma_prep_dma_interleaved;
 	imxdma->dma_device.device_control = imxdma_control;
 	imxdma->dma_device.device_issue_pending = imxdma_issue_pending;
 
 	platform_set_drvdata(pdev, imxdma);
 
+	imxdma->dma_device.copy_align = 2; /* 2^2 = 4 bytes alignment */
 	imxdma->dma_device.dev->dma_parms = &imxdma->dma_parms;
 	dma_set_max_seg_size(imxdma->dma_device.dev, 0xffffff);
 
@@ -399,9 +1083,13 @@ static int __init imxdma_probe(struct platform_device *pdev)
 	return 0;
 
 err_init:
-	while (--i >= 0) {
-		struct imxdma_channel *imxdmac = &imxdma->channel[i];
-		imx_dma_free(imxdmac->imxdma_channel);
+
+	if (cpu_is_mx21() || cpu_is_mx27()) {
+		while (--i >= 0)
+			free_irq(MX2x_INT_DMACH0 + i, NULL);
+	} else if cpu_is_mx1() {
+		free_irq(MX1_DMA_INT, NULL);
+		free_irq(MX1_DMA_ERR, NULL);
 	}
 
 	kfree(imxdma);
@@ -415,10 +1103,12 @@ static int __exit imxdma_remove(struct platform_device *pdev)
 
         dma_async_device_unregister(&imxdma->dma_device);
 
-	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
-		struct imxdma_channel *imxdmac = &imxdma->channel[i];
-
-		 imx_dma_free(imxdmac->imxdma_channel);
+	if (cpu_is_mx21() || cpu_is_mx27()) {
+		for (i = 0; i < IMX_DMA_CHANNELS; i++)
+			free_irq(MX2x_INT_DMACH0 + i, NULL);
+	} else if cpu_is_mx1() {
+		free_irq(MX1_DMA_INT, NULL);
+		free_irq(MX1_DMA_ERR, NULL);
 	}
 
         kfree(imxdma);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 63540d3e2153..d3e38e28bb6b 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/bitops.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/clk.h>
@@ -41,6 +42,8 @@
 #include <mach/dma.h>
 #include <mach/hardware.h>
 
+#include "dmaengine.h"
+
 /* SDMA registers */
 #define SDMA_H_C0PTR		0x000
 #define SDMA_H_INTR		0x004
@@ -259,19 +262,18 @@ struct sdma_channel {
 	unsigned int			pc_from_device, pc_to_device;
 	unsigned long			flags;
 	dma_addr_t			per_address;
-	u32				event_mask0, event_mask1;
-	u32				watermark_level;
+	unsigned long			event_mask[2];
+	unsigned long			watermark_level;
 	u32				shp_addr, per_addr;
 	struct dma_chan			chan;
 	spinlock_t			lock;
 	struct dma_async_tx_descriptor	desc;
-	dma_cookie_t			last_completed;
 	enum dma_status			status;
 	unsigned int			chn_count;
 	unsigned int			chn_real_count;
 };
 
-#define IMX_DMA_SG_LOOP		(1 << 0)
+#define IMX_DMA_SG_LOOP		BIT(0)
 
 #define MAX_DMA_CHANNELS 32
 #define MXC_SDMA_DEFAULT_PRIORITY 1
@@ -345,9 +347,9 @@ static const struct of_device_id sdma_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, sdma_dt_ids);
 
-#define SDMA_H_CONFIG_DSPDMA	(1 << 12) /* indicates if the DSPDMA is used */
-#define SDMA_H_CONFIG_RTD_PINS	(1 << 11) /* indicates if Real-Time Debug pins are enabled */
-#define SDMA_H_CONFIG_ACR	(1 << 4)  /* indicates if AHB freq /core freq = 2 or 1 */
+#define SDMA_H_CONFIG_DSPDMA	BIT(12) /* indicates if the DSPDMA is used */
+#define SDMA_H_CONFIG_RTD_PINS	BIT(11) /* indicates if Real-Time Debug pins are enabled */
+#define SDMA_H_CONFIG_ACR	BIT(4)  /* indicates if AHB freq /core freq = 2 or 1 */
 #define SDMA_H_CONFIG_CSM	(3)       /* indicates which context switch mode is selected*/
 
 static inline u32 chnenbl_ofs(struct sdma_engine *sdma, unsigned int event)
@@ -362,37 +364,42 @@ static int sdma_config_ownership(struct sdma_channel *sdmac,
 {
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
-	u32 evt, mcu, dsp;
+	unsigned long evt, mcu, dsp;
 
 	if (event_override && mcu_override && dsp_override)
 		return -EINVAL;
 
-	evt = __raw_readl(sdma->regs + SDMA_H_EVTOVR);
-	mcu = __raw_readl(sdma->regs + SDMA_H_HOSTOVR);
-	dsp = __raw_readl(sdma->regs + SDMA_H_DSPOVR);
+	evt = readl_relaxed(sdma->regs + SDMA_H_EVTOVR);
+	mcu = readl_relaxed(sdma->regs + SDMA_H_HOSTOVR);
+	dsp = readl_relaxed(sdma->regs + SDMA_H_DSPOVR);
 
 	if (dsp_override)
-		dsp &= ~(1 << channel);
+		__clear_bit(channel, &dsp);
 	else
-		dsp |= (1 << channel);
+		__set_bit(channel, &dsp);
 
 	if (event_override)
-		evt &= ~(1 << channel);
+		__clear_bit(channel, &evt);
 	else
-		evt |= (1 << channel);
+		__set_bit(channel, &evt);
 
 	if (mcu_override)
-		mcu &= ~(1 << channel);
+		__clear_bit(channel, &mcu);
 	else
-		mcu |= (1 << channel);
+		__set_bit(channel, &mcu);
 
-	__raw_writel(evt, sdma->regs + SDMA_H_EVTOVR);
-	__raw_writel(mcu, sdma->regs + SDMA_H_HOSTOVR);
-	__raw_writel(dsp, sdma->regs + SDMA_H_DSPOVR);
+	writel_relaxed(evt, sdma->regs + SDMA_H_EVTOVR);
+	writel_relaxed(mcu, sdma->regs + SDMA_H_HOSTOVR);
+	writel_relaxed(dsp, sdma->regs + SDMA_H_DSPOVR);
 
 	return 0;
 }
 
+static void sdma_enable_channel(struct sdma_engine *sdma, int channel)
+{
+	writel(BIT(channel), sdma->regs + SDMA_H_START);
+}
+
 /*
  * sdma_run_channel - run a channel and wait till it's done
  */
@@ -404,7 +411,7 @@ static int sdma_run_channel(struct sdma_channel *sdmac)
 
 	init_completion(&sdmac->done);
 
-	__raw_writel(1 << channel, sdma->regs + SDMA_H_START);
+	sdma_enable_channel(sdma, channel);
 
 	ret = wait_for_completion_timeout(&sdmac->done, HZ);
 
@@ -451,12 +458,12 @@ static void sdma_event_enable(struct sdma_channel *sdmac, unsigned int event)
 {
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
-	u32 val;
+	unsigned long val;
 	u32 chnenbl = chnenbl_ofs(sdma, event);
 
-	val = __raw_readl(sdma->regs + chnenbl);
-	val |= (1 << channel);
-	__raw_writel(val, sdma->regs + chnenbl);
+	val = readl_relaxed(sdma->regs + chnenbl);
+	__set_bit(channel, &val);
+	writel_relaxed(val, sdma->regs + chnenbl);
 }
 
 static void sdma_event_disable(struct sdma_channel *sdmac, unsigned int event)
@@ -464,11 +471,11 @@ static void sdma_event_disable(struct sdma_channel *sdmac, unsigned int event)
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
 	u32 chnenbl = chnenbl_ofs(sdma, event);
-	u32 val;
+	unsigned long val;
 
-	val = __raw_readl(sdma->regs + chnenbl);
-	val &= ~(1 << channel);
-	__raw_writel(val, sdma->regs + chnenbl);
+	val = readl_relaxed(sdma->regs + chnenbl);
+	__clear_bit(channel, &val);
+	writel_relaxed(val, sdma->regs + chnenbl);
 }
 
 static void sdma_handle_channel_loop(struct sdma_channel *sdmac)
@@ -522,7 +529,7 @@ static void mxc_sdma_handle_channel_normal(struct sdma_channel *sdmac)
 	else
 		sdmac->status = DMA_SUCCESS;
 
-	sdmac->last_completed = sdmac->desc.cookie;
+	dma_cookie_complete(&sdmac->desc);
 	if (sdmac->desc.callback)
 		sdmac->desc.callback(sdmac->desc.callback_param);
 }
@@ -544,10 +551,10 @@ static void mxc_sdma_handle_channel(struct sdma_channel *sdmac)
 static irqreturn_t sdma_int_handler(int irq, void *dev_id)
 {
 	struct sdma_engine *sdma = dev_id;
-	u32 stat;
+	unsigned long stat;
 
-	stat = __raw_readl(sdma->regs + SDMA_H_INTR);
-	__raw_writel(stat, sdma->regs + SDMA_H_INTR);
+	stat = readl_relaxed(sdma->regs + SDMA_H_INTR);
+	writel_relaxed(stat, sdma->regs + SDMA_H_INTR);
 
 	while (stat) {
 		int channel = fls(stat) - 1;
@@ -555,7 +562,7 @@ static irqreturn_t sdma_int_handler(int irq, void *dev_id)
 
 		mxc_sdma_handle_channel(sdmac);
 
-		stat &= ~(1 << channel);
+		__clear_bit(channel, &stat);
 	}
 
 	return IRQ_HANDLED;
@@ -663,11 +670,11 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 		return load_address;
 
 	dev_dbg(sdma->dev, "load_address = %d\n", load_address);
-	dev_dbg(sdma->dev, "wml = 0x%08x\n", sdmac->watermark_level);
+	dev_dbg(sdma->dev, "wml = 0x%08x\n", (u32)sdmac->watermark_level);
 	dev_dbg(sdma->dev, "shp_addr = 0x%08x\n", sdmac->shp_addr);
 	dev_dbg(sdma->dev, "per_addr = 0x%08x\n", sdmac->per_addr);
-	dev_dbg(sdma->dev, "event_mask0 = 0x%08x\n", sdmac->event_mask0);
-	dev_dbg(sdma->dev, "event_mask1 = 0x%08x\n", sdmac->event_mask1);
+	dev_dbg(sdma->dev, "event_mask0 = 0x%08x\n", (u32)sdmac->event_mask[0]);
+	dev_dbg(sdma->dev, "event_mask1 = 0x%08x\n", (u32)sdmac->event_mask[1]);
 
 	mutex_lock(&sdma->channel_0_lock);
 
@@ -677,8 +684,8 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 	/* Send by context the event mask,base address for peripheral
 	 * and watermark level
 	 */
-	context->gReg[0] = sdmac->event_mask1;
-	context->gReg[1] = sdmac->event_mask0;
+	context->gReg[0] = sdmac->event_mask[1];
+	context->gReg[1] = sdmac->event_mask[0];
 	context->gReg[2] = sdmac->per_addr;
 	context->gReg[6] = sdmac->shp_addr;
 	context->gReg[7] = sdmac->watermark_level;
@@ -701,7 +708,7 @@ static void sdma_disable_channel(struct sdma_channel *sdmac)
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
 
-	__raw_writel(1 << channel, sdma->regs + SDMA_H_STATSTOP);
+	writel_relaxed(BIT(channel), sdma->regs + SDMA_H_STATSTOP);
 	sdmac->status = DMA_ERROR;
 }
 
@@ -711,13 +718,13 @@ static int sdma_config_channel(struct sdma_channel *sdmac)
 
 	sdma_disable_channel(sdmac);
 
-	sdmac->event_mask0 = 0;
-	sdmac->event_mask1 = 0;
+	sdmac->event_mask[0] = 0;
+	sdmac->event_mask[1] = 0;
 	sdmac->shp_addr = 0;
 	sdmac->per_addr = 0;
 
 	if (sdmac->event_id0) {
-		if (sdmac->event_id0 > 32)
+		if (sdmac->event_id0 >= sdmac->sdma->num_events)
 			return -EINVAL;
 		sdma_event_enable(sdmac, sdmac->event_id0);
 	}
@@ -740,15 +747,14 @@ static int sdma_config_channel(struct sdma_channel *sdmac)
 			(sdmac->peripheral_type != IMX_DMATYPE_DSP)) {
 		/* Handle multiple event channels differently */
 		if (sdmac->event_id1) {
-			sdmac->event_mask1 = 1 << (sdmac->event_id1 % 32);
+			sdmac->event_mask[1] = BIT(sdmac->event_id1 % 32);
 			if (sdmac->event_id1 > 31)
-				sdmac->watermark_level |= 1 << 31;
-			sdmac->event_mask0 = 1 << (sdmac->event_id0 % 32);
+				__set_bit(31, &sdmac->watermark_level);
+			sdmac->event_mask[0] = BIT(sdmac->event_id0 % 32);
 			if (sdmac->event_id0 > 31)
-				sdmac->watermark_level |= 1 << 30;
+				__set_bit(30, &sdmac->watermark_level);
 		} else {
-			sdmac->event_mask0 = 1 << sdmac->event_id0;
-			sdmac->event_mask1 = 1 << (sdmac->event_id0 - 32);
+			__set_bit(sdmac->event_id0, sdmac->event_mask);
 		}
 		/* Watermark Level */
 		sdmac->watermark_level |= sdmac->watermark_level;
@@ -774,7 +780,7 @@ static int sdma_set_channel_priority(struct sdma_channel *sdmac,
 		return -EINVAL;
 	}
 
-	__raw_writel(priority, sdma->regs + SDMA_CHNPRI_0 + 4 * channel);
+	writel_relaxed(priority, sdma->regs + SDMA_CHNPRI_0 + 4 * channel);
 
 	return 0;
 }
@@ -796,8 +802,6 @@ static int sdma_request_channel(struct sdma_channel *sdmac)
 	sdma->channel_control[channel].base_bd_ptr = sdmac->bd_phys;
 	sdma->channel_control[channel].current_bd_ptr = sdmac->bd_phys;
 
-	clk_enable(sdma->clk);
-
 	sdma_set_channel_priority(sdmac, MXC_SDMA_DEFAULT_PRIORITY);
 
 	init_completion(&sdmac->done);
@@ -810,24 +814,6 @@ out:
 	return ret;
 }
 
-static void sdma_enable_channel(struct sdma_engine *sdma, int channel)
-{
-	__raw_writel(1 << channel, sdma->regs + SDMA_H_START);
-}
-
-static dma_cookie_t sdma_assign_cookie(struct sdma_channel *sdmac)
-{
-	dma_cookie_t cookie = sdmac->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	sdmac->chan.cookie = cookie;
-	sdmac->desc.cookie = cookie;
-
-	return cookie;
-}
-
 static struct sdma_channel *to_sdma_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct sdma_channel, chan);
@@ -837,14 +823,11 @@ static dma_cookie_t sdma_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	unsigned long flags;
 	struct sdma_channel *sdmac = to_sdma_chan(tx->chan);
-	struct sdma_engine *sdma = sdmac->sdma;
 	dma_cookie_t cookie;
 
 	spin_lock_irqsave(&sdmac->lock, flags);
 
-	cookie = sdma_assign_cookie(sdmac);
-
-	sdma_enable_channel(sdma, sdmac->channel);
+	cookie = dma_cookie_assign(tx);
 
 	spin_unlock_irqrestore(&sdmac->lock, flags);
 
@@ -875,11 +858,14 @@ static int sdma_alloc_chan_resources(struct dma_chan *chan)
 
 	sdmac->peripheral_type = data->peripheral_type;
 	sdmac->event_id0 = data->dma_request;
-	ret = sdma_set_channel_priority(sdmac, prio);
+
+	clk_enable(sdmac->sdma->clk);
+
+	ret = sdma_request_channel(sdmac);
 	if (ret)
 		return ret;
 
-	ret = sdma_request_channel(sdmac);
+	ret = sdma_set_channel_priority(sdmac, prio);
 	if (ret)
 		return ret;
 
@@ -916,7 +902,7 @@ static void sdma_free_chan_resources(struct dma_chan *chan)
 static struct dma_async_tx_descriptor *sdma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
 	struct sdma_engine *sdma = sdmac->sdma;
@@ -1014,7 +1000,8 @@ err_out:
 
 static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
 	struct sdma_engine *sdma = sdmac->sdma;
@@ -1128,7 +1115,7 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan,
 
 	last_used = chan->cookie;
 
-	dma_set_tx_state(txstate, sdmac->last_completed, last_used,
+	dma_set_tx_state(txstate, chan->completed_cookie, last_used,
 			sdmac->chn_count - sdmac->chn_real_count);
 
 	return sdmac->status;
@@ -1136,9 +1123,11 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan,
 
 static void sdma_issue_pending(struct dma_chan *chan)
 {
-	/*
-	 * Nothing to do. We only have a single descriptor
-	 */
+	struct sdma_channel *sdmac = to_sdma_chan(chan);
+	struct sdma_engine *sdma = sdmac->sdma;
+
+	if (sdmac->status == DMA_IN_PROGRESS)
+		sdma_enable_channel(sdma, sdmac->channel);
 }
 
 #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1	34
@@ -1230,7 +1219,7 @@ static int __init sdma_init(struct sdma_engine *sdma)
 	clk_enable(sdma->clk);
 
 	/* Be sure SDMA has not started yet */
-	__raw_writel(0, sdma->regs + SDMA_H_C0PTR);
+	writel_relaxed(0, sdma->regs + SDMA_H_C0PTR);
 
 	sdma->channel_control = dma_alloc_coherent(NULL,
 			MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control) +
@@ -1253,11 +1242,11 @@ static int __init sdma_init(struct sdma_engine *sdma)
 
 	/* disable all channels */
 	for (i = 0; i < sdma->num_events; i++)
-		__raw_writel(0, sdma->regs + chnenbl_ofs(sdma, i));
+		writel_relaxed(0, sdma->regs + chnenbl_ofs(sdma, i));
 
 	/* All channels have priority 0 */
 	for (i = 0; i < MAX_DMA_CHANNELS; i++)
-		__raw_writel(0, sdma->regs + SDMA_CHNPRI_0 + i * 4);
+		writel_relaxed(0, sdma->regs + SDMA_CHNPRI_0 + i * 4);
 
 	ret = sdma_request_channel(&sdma->channel[0]);
 	if (ret)
@@ -1266,16 +1255,16 @@ static int __init sdma_init(struct sdma_engine *sdma)
 	sdma_config_ownership(&sdma->channel[0], false, true, false);
 
 	/* Set Command Channel (Channel Zero) */
-	__raw_writel(0x4050, sdma->regs + SDMA_CHN0ADDR);
+	writel_relaxed(0x4050, sdma->regs + SDMA_CHN0ADDR);
 
 	/* Set bits of CONFIG register but with static context switching */
 	/* FIXME: Check whether to set ACR bit depending on clock ratios */
-	__raw_writel(0, sdma->regs + SDMA_H_CONFIG);
+	writel_relaxed(0, sdma->regs + SDMA_H_CONFIG);
 
-	__raw_writel(ccb_phys, sdma->regs + SDMA_H_C0PTR);
+	writel_relaxed(ccb_phys, sdma->regs + SDMA_H_C0PTR);
 
 	/* Set bits of CONFIG register with given context switching mode */
-	__raw_writel(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
+	writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
 
 	/* Initializes channel's priorities */
 	sdma_set_channel_priority(&sdma->channel[0], 7);
@@ -1367,6 +1356,7 @@ static int __init sdma_probe(struct platform_device *pdev)
 		spin_lock_init(&sdmac->lock);
 
 		sdmac->chan.device = &sdma->dma_device;
+		dma_cookie_init(&sdmac->chan);
 		sdmac->channel = i;
 
 		/*
@@ -1387,7 +1377,9 @@ static int __init sdma_probe(struct platform_device *pdev)
 		sdma_add_scripts(sdma, pdata->script_addrs);
 
 	if (pdata) {
-		sdma_get_firmware(sdma, pdata->fw_name);
+		ret = sdma_get_firmware(sdma, pdata->fw_name);
+		if (ret)
+			dev_warn(&pdev->dev, "failed to get firmware from platform data\n");
 	} else {
 		/*
 		 * Because that device tree does not encode ROM script address,
@@ -1396,15 +1388,12 @@ static int __init sdma_probe(struct platform_device *pdev)
 		 */
 		ret = of_property_read_string(np, "fsl,sdma-ram-script-name",
 					      &fw_name);
-		if (ret) {
-			dev_err(&pdev->dev, "failed to get firmware name\n");
-			goto err_init;
-		}
-
-		ret = sdma_get_firmware(sdma, fw_name);
-		if (ret) {
-			dev_err(&pdev->dev, "failed to get firmware\n");
-			goto err_init;
+		if (ret)
+			dev_warn(&pdev->dev, "failed to get firmware name\n");
+		else {
+			ret = sdma_get_firmware(sdma, fw_name);
+			if (ret)
+				dev_warn(&pdev->dev, "failed to get firmware from device tree\n");
 		}
 	}
 
diff --git a/drivers/dma/intel_mid_dma.c b/drivers/dma/intel_mid_dma.c
index 74f70aadf9e4..c900ca7aaec4 100644
--- a/drivers/dma/intel_mid_dma.c
+++ b/drivers/dma/intel_mid_dma.c
@@ -29,6 +29,8 @@
 #include <linux/intel_mid_dma.h>
 #include <linux/module.h>
 
+#include "dmaengine.h"
+
 #define MAX_CHAN	4 /*max ch across controllers*/
 #include "intel_mid_dma_regs.h"
 
@@ -288,7 +290,7 @@ static void midc_descriptor_complete(struct intel_mid_dma_chan *midc,
 	struct intel_mid_dma_lli	*llitem;
 	void *param_txd = NULL;
 
-	midc->completed = txd->cookie;
+	dma_cookie_complete(txd);
 	callback_txd = txd->callback;
 	param_txd = txd->callback_param;
 
@@ -434,14 +436,7 @@ static dma_cookie_t intel_mid_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	dma_cookie_t		cookie;
 
 	spin_lock_bh(&midc->lock);
-	cookie = midc->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	midc->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
+	cookie = dma_cookie_assign(tx);
 
 	if (list_empty(&midc->active_list))
 		list_add_tail(&desc->desc_node, &midc->active_list);
@@ -482,31 +477,18 @@ static enum dma_status intel_mid_dma_tx_status(struct dma_chan *chan,
 						dma_cookie_t cookie,
 						struct dma_tx_state *txstate)
 {
-	struct intel_mid_dma_chan	*midc = to_intel_mid_dma_chan(chan);
-	dma_cookie_t		last_used;
-	dma_cookie_t		last_complete;
-	int				ret;
+	struct intel_mid_dma_chan *midc = to_intel_mid_dma_chan(chan);
+	enum dma_status ret;
 
-	last_complete = midc->completed;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS) {
 		spin_lock_bh(&midc->lock);
 		midc_scan_descriptors(to_middma_device(chan->device), midc);
 		spin_unlock_bh(&midc->lock);
 
-		last_complete = midc->completed;
-		last_used = chan->cookie;
-
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
+		ret = dma_cookie_status(chan, cookie, txstate);
 	}
 
-	if (txstate) {
-		txstate->last = last_complete;
-		txstate->used = last_used;
-		txstate->residue = 0;
-	}
 	return ret;
 }
 
@@ -732,13 +714,14 @@ err_desc_get:
  * @sg_len: length of sg txn
  * @direction: DMA transfer dirtn
  * @flags: DMA flags
+ * @context: transfer context (ignored)
  *
  * Prepares LLI based periphral transfer
  */
 static struct dma_async_tx_descriptor *intel_mid_dma_prep_slave_sg(
 			struct dma_chan *chan, struct scatterlist *sgl,
 			unsigned int sg_len, enum dma_transfer_direction direction,
-			unsigned long flags)
+			unsigned long flags, void *context)
 {
 	struct intel_mid_dma_chan *midc = NULL;
 	struct intel_mid_dma_slave *mids = NULL;
@@ -832,7 +815,6 @@ static void intel_mid_dma_free_chan_resources(struct dma_chan *chan)
 		/*trying to free ch in use!!!!!*/
 		pr_err("ERR_MDMA: trying to free ch in use\n");
 	}
-	pm_runtime_put(&mid->pdev->dev);
 	spin_lock_bh(&midc->lock);
 	midc->descs_allocated = 0;
 	list_for_each_entry_safe(desc, _desc, &midc->active_list, desc_node) {
@@ -853,6 +835,7 @@ static void intel_mid_dma_free_chan_resources(struct dma_chan *chan)
 	/* Disable CH interrupts */
 	iowrite32(MASK_INTR_REG(midc->ch_id), mid->dma_base + MASK_BLOCK);
 	iowrite32(MASK_INTR_REG(midc->ch_id), mid->dma_base + MASK_ERR);
+	pm_runtime_put(&mid->pdev->dev);
 }
 
 /**
@@ -886,7 +869,7 @@ static int intel_mid_dma_alloc_chan_resources(struct dma_chan *chan)
 		pm_runtime_put(&mid->pdev->dev);
 		return -EIO;
 	}
-	midc->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	spin_lock_bh(&midc->lock);
 	while (midc->descs_allocated < DESCS_PER_CHANNEL) {
@@ -1056,7 +1039,8 @@ static irqreturn_t intel_mid_dma_interrupt(int irq, void *data)
 	}
 	err_status &= mid->intr_mask;
 	if (err_status) {
-		iowrite32(MASK_INTR_REG(err_status), mid->dma_base + MASK_ERR);
+		iowrite32((err_status << INT_MASK_WE),
+			  mid->dma_base + MASK_ERR);
 		call_tasklet = 1;
 	}
 	if (call_tasklet)
@@ -1118,7 +1102,7 @@ static int mid_setup_dma(struct pci_dev *pdev)
 		struct intel_mid_dma_chan *midch = &dma->ch[i];
 
 		midch->chan.device = &dma->common;
-		midch->chan.cookie =  1;
+		dma_cookie_init(&midch->chan);
 		midch->ch_id = dma->chan_base + i;
 		pr_debug("MDMA:Init CH %d, ID %d\n", i, midch->ch_id);
 
diff --git a/drivers/dma/intel_mid_dma_regs.h b/drivers/dma/intel_mid_dma_regs.h
index c83d35b97bd8..1bfa9268feaf 100644
--- a/drivers/dma/intel_mid_dma_regs.h
+++ b/drivers/dma/intel_mid_dma_regs.h
@@ -165,7 +165,6 @@ union intel_mid_dma_cfg_hi {
  * @dma_base: MMIO register space DMA engine base pointer
  * @ch_id: DMA channel id
  * @lock: channel spinlock
- * @completed: DMA cookie
  * @active_list: current active descriptors
  * @queue: current queued up descriptors
  * @free_list: current free descriptors
@@ -183,7 +182,6 @@ struct intel_mid_dma_chan {
 	void __iomem		*dma_base;
 	int			ch_id;
 	spinlock_t		lock;
-	dma_cookie_t		completed;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index a4d6cb0c0343..31493d80e0e9 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -40,6 +40,8 @@
 #include "registers.h"
 #include "hw.h"
 
+#include "../dmaengine.h"
+
 int ioat_pending_level = 4;
 module_param(ioat_pending_level, int, 0644);
 MODULE_PARM_DESC(ioat_pending_level,
@@ -107,6 +109,7 @@ void ioat_init_channel(struct ioatdma_device *device, struct ioat_chan_common *c
 	chan->reg_base = device->reg_base + (0x80 * (idx + 1));
 	spin_lock_init(&chan->cleanup_lock);
 	chan->common.device = dma;
+	dma_cookie_init(&chan->common);
 	list_add_tail(&chan->common.device_node, &dma->channels);
 	device->idx[idx] = chan;
 	init_timer(&chan->timer);
@@ -235,12 +238,7 @@ static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
 
 	spin_lock_bh(&ioat->desc_lock);
 	/* cookie incr and addition to used_list must be atomic */
-	cookie = c->cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	c->cookie = cookie;
-	tx->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
 
 	/* write address into NextDescriptor field of last desc in chain */
@@ -603,8 +601,7 @@ static void __cleanup(struct ioat_dma_chan *ioat, unsigned long phys_complete)
 		 */
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
-			chan->completed_cookie = tx->cookie;
-			tx->cookie = 0;
+			dma_cookie_complete(tx);
 			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
 			ioat->active -= desc->hw->tx_cnt;
 			if (tx->callback) {
@@ -733,13 +730,15 @@ ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 {
 	struct ioat_chan_common *chan = to_chan_common(c);
 	struct ioatdma_device *device = chan->device;
+	enum dma_status ret;
 
-	if (ioat_tx_status(c, cookie, txstate) == DMA_SUCCESS)
-		return DMA_SUCCESS;
+	ret = dma_cookie_status(c, cookie, txstate);
+	if (ret == DMA_SUCCESS)
+		return ret;
 
 	device->cleanup_fn((unsigned long) c);
 
-	return ioat_tx_status(c, cookie, txstate);
+	return dma_cookie_status(c, cookie, txstate);
 }
 
 static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat)
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 5216c8a92a21..c7888bccd974 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -90,7 +90,6 @@ struct ioat_chan_common {
 	void __iomem *reg_base;
 	unsigned long last_completion;
 	spinlock_t cleanup_lock;
-	dma_cookie_t completed_cookie;
 	unsigned long state;
 	#define IOAT_COMPLETION_PENDING 0
 	#define IOAT_COMPLETION_ACK 1
@@ -143,28 +142,6 @@ static inline struct ioat_dma_chan *to_ioat_chan(struct dma_chan *c)
 	return container_of(chan, struct ioat_dma_chan, base);
 }
 
-/**
- * ioat_tx_status - poll the status of an ioat transaction
- * @c: channel handle
- * @cookie: transaction identifier
- * @txstate: if set, updated with the transaction state
- */
-static inline enum dma_status
-ioat_tx_status(struct dma_chan *c, dma_cookie_t cookie,
-		 struct dma_tx_state *txstate)
-{
-	struct ioat_chan_common *chan = to_chan_common(c);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-
-	last_used = c->cookie;
-	last_complete = chan->completed_cookie;
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	return dma_async_is_complete(cookie, last_complete, last_used);
-}
-
 /* wrapper around hardware descriptor format + additional software fields */
 
 /**
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 5d65f8377971..e8e110ff3d96 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -41,6 +41,8 @@
 #include "registers.h"
 #include "hw.h"
 
+#include "../dmaengine.h"
+
 int ioat_ring_alloc_order = 8;
 module_param(ioat_ring_alloc_order, int, 0644);
 MODULE_PARM_DESC(ioat_ring_alloc_order,
@@ -147,8 +149,7 @@ static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete)
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
 			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
-			chan->completed_cookie = tx->cookie;
-			tx->cookie = 0;
+			dma_cookie_complete(tx);
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
 				tx->callback = NULL;
@@ -398,13 +399,9 @@ static dma_cookie_t ioat2_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
 	struct dma_chan *c = tx->chan;
 	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
 	struct ioat_chan_common *chan = &ioat->base;
-	dma_cookie_t cookie = c->cookie;
+	dma_cookie_t cookie;
 
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	tx->cookie = cookie;
-	c->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
 
 	if (!test_and_set_bit(IOAT_COMPLETION_PENDING, &chan->state))
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index f519c93a61e7..2c4476c0e405 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -61,6 +61,7 @@
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/prefetch.h>
+#include "../dmaengine.h"
 #include "registers.h"
 #include "hw.h"
 #include "dma.h"
@@ -277,9 +278,8 @@ static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete)
 		dump_desc_dbg(ioat, desc);
 		tx = &desc->txd;
 		if (tx->cookie) {
-			chan->completed_cookie = tx->cookie;
+			dma_cookie_complete(tx);
 			ioat3_dma_unmap(ioat, desc, idx + i);
-			tx->cookie = 0;
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
 				tx->callback = NULL;
@@ -411,13 +411,15 @@ ioat3_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 		struct dma_tx_state *txstate)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	enum dma_status ret;
 
-	if (ioat_tx_status(c, cookie, txstate) == DMA_SUCCESS)
-		return DMA_SUCCESS;
+	ret = dma_cookie_status(c, cookie, txstate);
+	if (ret == DMA_SUCCESS)
+		return ret;
 
 	ioat3_cleanup(ioat);
 
-	return ioat_tx_status(c, cookie, txstate);
+	return dma_cookie_status(c, cookie, txstate);
 }
 
 static struct dma_async_tx_descriptor *
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index faf88b7e1e71..da6c4c2c066a 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -36,6 +36,8 @@
 
 #include <mach/adma.h>
 
+#include "dmaengine.h"
+
 #define to_iop_adma_chan(chan) container_of(chan, struct iop_adma_chan, common)
 #define to_iop_adma_device(dev) \
 	container_of(dev, struct iop_adma_device, common)
@@ -317,7 +319,7 @@ static void __iop_adma_slot_cleanup(struct iop_adma_chan *iop_chan)
 	}
 
 	if (cookie > 0) {
-		iop_chan->completed_cookie = cookie;
+		iop_chan->common.completed_cookie = cookie;
 		pr_debug("\tcompleted cookie %d\n", cookie);
 	}
 }
@@ -438,18 +440,6 @@ retry:
 	return NULL;
 }
 
-static dma_cookie_t
-iop_desc_assign_cookie(struct iop_adma_chan *iop_chan,
-	struct iop_adma_desc_slot *desc)
-{
-	dma_cookie_t cookie = iop_chan->common.cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	iop_chan->common.cookie = desc->async_tx.cookie = cookie;
-	return cookie;
-}
-
 static void iop_adma_check_threshold(struct iop_adma_chan *iop_chan)
 {
 	dev_dbg(iop_chan->device->common.dev, "pending: %d\n",
@@ -477,7 +467,7 @@ iop_adma_tx_submit(struct dma_async_tx_descriptor *tx)
 	slots_per_op = grp_start->slots_per_op;
 
 	spin_lock_bh(&iop_chan->lock);
-	cookie = iop_desc_assign_cookie(iop_chan, sw_desc);
+	cookie = dma_cookie_assign(tx);
 
 	old_chain_tail = list_entry(iop_chan->chain.prev,
 		struct iop_adma_desc_slot, chain_node);
@@ -904,24 +894,15 @@ static enum dma_status iop_adma_status(struct dma_chan *chan,
 					struct dma_tx_state *txstate)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	enum dma_status ret;
-
-	last_used = chan->cookie;
-	last_complete = iop_chan->completed_cookie;
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	int ret;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_SUCCESS)
 		return ret;
 
 	iop_adma_slot_cleanup(iop_chan);
 
-	last_used = chan->cookie;
-	last_complete = iop_chan->completed_cookie;
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static irqreturn_t iop_adma_eot_handler(int irq, void *data)
@@ -1565,6 +1546,7 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&iop_chan->chain);
 	INIT_LIST_HEAD(&iop_chan->all_slots);
 	iop_chan->common.device = dma_dev;
+	dma_cookie_init(&iop_chan->common);
 	list_add_tail(&iop_chan->common.device_node, &dma_dev->channels);
 
 	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) {
@@ -1642,16 +1624,12 @@ static void iop_chan_start_null_memcpy(struct iop_adma_chan *iop_chan)
 		iop_desc_set_dest_addr(grp_start, iop_chan, 0);
 		iop_desc_set_memcpy_src_addr(grp_start, 0);
 
-		cookie = iop_chan->common.cookie;
-		cookie++;
-		if (cookie <= 1)
-			cookie = 2;
+		cookie = dma_cookie_assign(&sw_desc->async_tx);
 
 		/* initialize the completed cookie to be less than
 		 * the most recently used cookie
 		 */
-		iop_chan->completed_cookie = cookie - 1;
-		iop_chan->common.cookie = sw_desc->async_tx.cookie = cookie;
+		iop_chan->common.completed_cookie = cookie - 1;
 
 		/* channel should not be busy */
 		BUG_ON(iop_chan_is_busy(iop_chan));
@@ -1699,16 +1677,12 @@ static void iop_chan_start_null_xor(struct iop_adma_chan *iop_chan)
 		iop_desc_set_xor_src_addr(grp_start, 0, 0);
 		iop_desc_set_xor_src_addr(grp_start, 1, 0);
 
-		cookie = iop_chan->common.cookie;
-		cookie++;
-		if (cookie <= 1)
-			cookie = 2;
+		cookie = dma_cookie_assign(&sw_desc->async_tx);
 
 		/* initialize the completed cookie to be less than
 		 * the most recently used cookie
 		 */
-		iop_chan->completed_cookie = cookie - 1;
-		iop_chan->common.cookie = sw_desc->async_tx.cookie = cookie;
+		iop_chan->common.completed_cookie = cookie - 1;
 
 		/* channel should not be busy */
 		BUG_ON(iop_chan_is_busy(iop_chan));
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index 6212b16e8cf2..62e3f8ec2461 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -25,6 +25,7 @@
 
 #include <mach/ipu.h>
 
+#include "../dmaengine.h"
 #include "ipu_intern.h"
 
 #define FS_VF_IN_VALID	0x00000002
@@ -866,14 +867,7 @@ static dma_cookie_t idmac_tx_submit(struct dma_async_tx_descriptor *tx)
 
 	dev_dbg(dev, "Submitting sg %p\n", &desc->sg[0]);
 
-	cookie = ichan->dma_chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	/* from dmaengine.h: "last cookie value returned to client" */
-	ichan->dma_chan.cookie = cookie;
-	tx->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 
 	/* ipu->lock can be taken under ichan->lock, but not v.v. */
 	spin_lock_irqsave(&ichan->lock, flags);
@@ -1295,7 +1289,7 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 	/* Flip the active buffer - even if update above failed */
 	ichan->active_buffer = !ichan->active_buffer;
 	if (done)
-		ichan->completed = desc->txd.cookie;
+		dma_cookie_complete(&desc->txd);
 
 	callback = desc->txd.callback;
 	callback_param = desc->txd.callback_param;
@@ -1341,7 +1335,8 @@ static void ipu_gc_tasklet(unsigned long arg)
 /* Allocate and initialise a transfer descriptor. */
 static struct dma_async_tx_descriptor *idmac_prep_slave_sg(struct dma_chan *chan,
 		struct scatterlist *sgl, unsigned int sg_len,
-		enum dma_transfer_direction direction, unsigned long tx_flags)
+		enum dma_transfer_direction direction, unsigned long tx_flags,
+		void *context)
 {
 	struct idmac_channel *ichan = to_idmac_chan(chan);
 	struct idmac_tx_desc *desc = NULL;
@@ -1510,8 +1505,7 @@ static int idmac_alloc_chan_resources(struct dma_chan *chan)
 	BUG_ON(chan->client_count > 1);
 	WARN_ON(ichan->status != IPU_CHANNEL_FREE);
 
-	chan->cookie		= 1;
-	ichan->completed	= -ENXIO;
+	dma_cookie_init(chan);
 
 	ret = ipu_irq_map(chan->chan_id);
 	if (ret < 0)
@@ -1600,9 +1594,7 @@ static void idmac_free_chan_resources(struct dma_chan *chan)
 static enum dma_status idmac_tx_status(struct dma_chan *chan,
 		       dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
-	struct idmac_channel *ichan = to_idmac_chan(chan);
-
-	dma_set_tx_state(txstate, ichan->completed, chan->cookie, 0);
+	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie, 0);
 	if (cookie != chan->cookie)
 		return DMA_ERROR;
 	return DMA_SUCCESS;
@@ -1638,11 +1630,10 @@ static int __init ipu_idmac_init(struct ipu *ipu)
 
 		ichan->status		= IPU_CHANNEL_FREE;
 		ichan->sec_chan_en	= false;
-		ichan->completed	= -ENXIO;
 		snprintf(ichan->eof_name, sizeof(ichan->eof_name), "IDMAC EOF %d", i);
 
 		dma_chan->device	= &idmac->dma;
-		dma_chan->cookie	= 1;
+		dma_cookie_init(dma_chan);
 		dma_chan->chan_id	= i;
 		list_add_tail(&dma_chan->device_node, &dma->channels);
 	}
diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c
index 4d6d4cf66949..2ab0a3d0eed5 100644
--- a/drivers/dma/mpc512x_dma.c
+++ b/drivers/dma/mpc512x_dma.c
@@ -44,6 +44,8 @@
 
 #include <linux/random.h>
 
+#include "dmaengine.h"
+
 /* Number of DMA Transfer descriptors allocated per channel */
 #define MPC_DMA_DESCRIPTORS	64
 
@@ -188,7 +190,6 @@ struct mpc_dma_chan {
 	struct list_head		completed;
 	struct mpc_dma_tcd		*tcd;
 	dma_addr_t			tcd_paddr;
-	dma_cookie_t			completed_cookie;
 
 	/* Lock for this structure */
 	spinlock_t			lock;
@@ -365,7 +366,7 @@ static void mpc_dma_process_completed(struct mpc_dma *mdma)
 		/* Free descriptors */
 		spin_lock_irqsave(&mchan->lock, flags);
 		list_splice_tail_init(&list, &mchan->free);
-		mchan->completed_cookie = last_cookie;
+		mchan->chan.completed_cookie = last_cookie;
 		spin_unlock_irqrestore(&mchan->lock, flags);
 	}
 }
@@ -438,13 +439,7 @@ static dma_cookie_t mpc_dma_tx_submit(struct dma_async_tx_descriptor *txd)
 		mpc_dma_execute(mchan);
 
 	/* Update cookie */
-	cookie = mchan->chan.cookie + 1;
-	if (cookie <= 0)
-		cookie = 1;
-
-	mchan->chan.cookie = cookie;
-	mdesc->desc.cookie = cookie;
-
+	cookie = dma_cookie_assign(txd);
 	spin_unlock_irqrestore(&mchan->lock, flags);
 
 	return cookie;
@@ -562,17 +557,14 @@ mpc_dma_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	       struct dma_tx_state *txstate)
 {
 	struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan);
+	enum dma_status ret;
 	unsigned long flags;
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 
 	spin_lock_irqsave(&mchan->lock, flags);
-	last_used = mchan->chan.cookie;
-	last_complete = mchan->completed_cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
 	spin_unlock_irqrestore(&mchan->lock, flags);
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return ret;
 }
 
 /* Prepare descriptor for memory to memory copy */
@@ -741,8 +733,7 @@ static int __devinit mpc_dma_probe(struct platform_device *op)
 		mchan = &mdma->channels[i];
 
 		mchan->chan.device = dma;
-		mchan->chan.cookie = 1;
-		mchan->completed_cookie = mchan->chan.cookie;
+		dma_cookie_init(&mchan->chan);
 
 		INIT_LIST_HEAD(&mchan->free);
 		INIT_LIST_HEAD(&mchan->prepared);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index e779b434af45..fa5d55fea46c 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -26,6 +26,8 @@
 #include <linux/platform_device.h>
 #include <linux/memory.h>
 #include <plat/mv_xor.h>
+
+#include "dmaengine.h"
 #include "mv_xor.h"
 
 static void mv_xor_issue_pending(struct dma_chan *chan);
@@ -435,7 +437,7 @@ static void __mv_xor_slot_cleanup(struct mv_xor_chan *mv_chan)
 	}
 
 	if (cookie > 0)
-		mv_chan->completed_cookie = cookie;
+		mv_chan->common.completed_cookie = cookie;
 }
 
 static void
@@ -534,18 +536,6 @@ retry:
 	return NULL;
 }
 
-static dma_cookie_t
-mv_desc_assign_cookie(struct mv_xor_chan *mv_chan,
-		      struct mv_xor_desc_slot *desc)
-{
-	dma_cookie_t cookie = mv_chan->common.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-	mv_chan->common.cookie = desc->async_tx.cookie = cookie;
-	return cookie;
-}
-
 /************************ DMA engine API functions ****************************/
 static dma_cookie_t
 mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
@@ -563,7 +553,7 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
 	grp_start = sw_desc->group_head;
 
 	spin_lock_bh(&mv_chan->lock);
-	cookie = mv_desc_assign_cookie(mv_chan, sw_desc);
+	cookie = dma_cookie_assign(tx);
 
 	if (list_empty(&mv_chan->chain))
 		list_splice_init(&sw_desc->tx_list, &mv_chan->chain);
@@ -820,27 +810,16 @@ static enum dma_status mv_xor_status(struct dma_chan *chan,
 					  struct dma_tx_state *txstate)
 {
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 	enum dma_status ret;
 
-	last_used = chan->cookie;
-	last_complete = mv_chan->completed_cookie;
-	mv_chan->is_complete_cookie = cookie;
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_SUCCESS) {
 		mv_xor_clean_completed_slots(mv_chan);
 		return ret;
 	}
 	mv_xor_slot_cleanup(mv_chan);
 
-	last_used = chan->cookie;
-	last_complete = mv_chan->completed_cookie;
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static void mv_dump_xor_regs(struct mv_xor_chan *chan)
@@ -1214,6 +1193,7 @@ static int __devinit mv_xor_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&mv_chan->completed_slots);
 	INIT_LIST_HEAD(&mv_chan->all_slots);
 	mv_chan->common.device = dma_dev;
+	dma_cookie_init(&mv_chan->common);
 
 	list_add_tail(&mv_chan->common.device_node, &dma_dev->channels);
 
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index 977b592e976b..654876b7ba1d 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -78,7 +78,6 @@ struct mv_xor_device {
 /**
  * struct mv_xor_chan - internal representation of a XOR channel
  * @pending: allows batching of hardware operations
- * @completed_cookie: identifier for the most recently completed operation
  * @lock: serializes enqueue/dequeue operations to the descriptors pool
  * @mmr_base: memory mapped register base
  * @idx: the index of the xor channel
@@ -93,7 +92,6 @@ struct mv_xor_device {
  */
 struct mv_xor_chan {
 	int			pending;
-	dma_cookie_t		completed_cookie;
 	spinlock_t		lock; /* protects the descriptor slot pool */
 	void __iomem		*mmr_base;
 	unsigned int		idx;
@@ -109,7 +107,6 @@ struct mv_xor_chan {
 #ifdef USE_TIMER
 	unsigned long		cleanup_time;
 	u32			current_on_last_cleanup;
-	dma_cookie_t		is_complete_cookie;
 #endif
 };
 
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index b06cd4ca626f..c81ef7e10e08 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -22,12 +22,14 @@
 #include <linux/platform_device.h>
 #include <linux/dmaengine.h>
 #include <linux/delay.h>
+#include <linux/fsl/mxs-dma.h>
 
 #include <asm/irq.h>
 #include <mach/mxs.h>
-#include <mach/dma.h>
 #include <mach/common.h>
 
+#include "dmaengine.h"
+
 /*
  * NOTE: The term "PIO" throughout the mxs-dma implementation means
  * PIO mode of mxs apbh-dma and apbx-dma.  With this working mode,
@@ -111,7 +113,6 @@ struct mxs_dma_chan {
 	struct mxs_dma_ccw		*ccw;
 	dma_addr_t			ccw_phys;
 	int				desc_count;
-	dma_cookie_t			last_completed;
 	enum dma_status			status;
 	unsigned int			flags;
 #define MXS_DMA_SG_LOOP			(1 << 0)
@@ -193,19 +194,6 @@ static void mxs_dma_resume_chan(struct mxs_dma_chan *mxs_chan)
 	mxs_chan->status = DMA_IN_PROGRESS;
 }
 
-static dma_cookie_t mxs_dma_assign_cookie(struct mxs_dma_chan *mxs_chan)
-{
-	dma_cookie_t cookie = mxs_chan->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	mxs_chan->chan.cookie = cookie;
-	mxs_chan->desc.cookie = cookie;
-
-	return cookie;
-}
-
 static struct mxs_dma_chan *to_mxs_dma_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct mxs_dma_chan, chan);
@@ -217,7 +205,7 @@ static dma_cookie_t mxs_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 
 	mxs_dma_enable_chan(mxs_chan);
 
-	return mxs_dma_assign_cookie(mxs_chan);
+	return dma_cookie_assign(tx);
 }
 
 static void mxs_dma_tasklet(unsigned long data)
@@ -274,7 +262,7 @@ static irqreturn_t mxs_dma_int_handler(int irq, void *dev_id)
 		stat1 &= ~(1 << channel);
 
 		if (mxs_chan->status == DMA_SUCCESS)
-			mxs_chan->last_completed = mxs_chan->desc.cookie;
+			dma_cookie_complete(&mxs_chan->desc);
 
 		/* schedule tasklet on this channel */
 		tasklet_schedule(&mxs_chan->tasklet);
@@ -349,10 +337,32 @@ static void mxs_dma_free_chan_resources(struct dma_chan *chan)
 	clk_disable_unprepare(mxs_dma->clk);
 }
 
+/*
+ * How to use the flags for ->device_prep_slave_sg() :
+ *    [1] If there is only one DMA command in the DMA chain, the code should be:
+ *            ......
+ *            ->device_prep_slave_sg(DMA_CTRL_ACK);
+ *            ......
+ *    [2] If there are two DMA commands in the DMA chain, the code should be
+ *            ......
+ *            ->device_prep_slave_sg(0);
+ *            ......
+ *            ->device_prep_slave_sg(DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+ *            ......
+ *    [3] If there are more than two DMA commands in the DMA chain, the code
+ *        should be:
+ *            ......
+ *            ->device_prep_slave_sg(0);                                // First
+ *            ......
+ *            ->device_prep_slave_sg(DMA_PREP_INTERRUPT [| DMA_CTRL_ACK]);
+ *            ......
+ *            ->device_prep_slave_sg(DMA_PREP_INTERRUPT | DMA_CTRL_ACK); // Last
+ *            ......
+ */
 static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long append)
+		unsigned long flags, void *context)
 {
 	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
@@ -360,6 +370,7 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
 	struct scatterlist *sg;
 	int i, j;
 	u32 *pio;
+	bool append = flags & DMA_PREP_INTERRUPT;
 	int idx = append ? mxs_chan->desc_count : 0;
 
 	if (mxs_chan->status == DMA_IN_PROGRESS && !append)
@@ -386,7 +397,6 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
 		ccw->bits |= CCW_CHAIN;
 		ccw->bits &= ~CCW_IRQ;
 		ccw->bits &= ~CCW_DEC_SEM;
-		ccw->bits &= ~CCW_WAIT4END;
 	} else {
 		idx = 0;
 	}
@@ -401,7 +411,8 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
 		ccw->bits = 0;
 		ccw->bits |= CCW_IRQ;
 		ccw->bits |= CCW_DEC_SEM;
-		ccw->bits |= CCW_WAIT4END;
+		if (flags & DMA_CTRL_ACK)
+			ccw->bits |= CCW_WAIT4END;
 		ccw->bits |= CCW_HALT_ON_TERM;
 		ccw->bits |= CCW_TERM_FLUSH;
 		ccw->bits |= BF_CCW(sg_len, PIO_NUM);
@@ -432,7 +443,8 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
 				ccw->bits &= ~CCW_CHAIN;
 				ccw->bits |= CCW_IRQ;
 				ccw->bits |= CCW_DEC_SEM;
-				ccw->bits |= CCW_WAIT4END;
+				if (flags & DMA_CTRL_ACK)
+					ccw->bits |= CCW_WAIT4END;
 			}
 		}
 	}
@@ -447,7 +459,8 @@ err_out:
 
 static struct dma_async_tx_descriptor *mxs_dma_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
@@ -538,7 +551,7 @@ static enum dma_status mxs_dma_tx_status(struct dma_chan *chan,
 	dma_cookie_t last_used;
 
 	last_used = chan->cookie;
-	dma_set_tx_state(txstate, mxs_chan->last_completed, last_used, 0);
+	dma_set_tx_state(txstate, chan->completed_cookie, last_used, 0);
 
 	return mxs_chan->status;
 }
@@ -630,6 +643,7 @@ static int __init mxs_dma_probe(struct platform_device *pdev)
 
 		mxs_chan->mxs_dma = mxs_dma;
 		mxs_chan->chan.device = &mxs_dma->dma_device;
+		dma_cookie_init(&mxs_chan->chan);
 
 		tasklet_init(&mxs_chan->tasklet, mxs_dma_tasklet,
 			     (unsigned long) mxs_chan);
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 823f58179f9d..65c0495a6d40 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -25,6 +25,8 @@
 #include <linux/module.h>
 #include <linux/pch_dma.h>
 
+#include "dmaengine.h"
+
 #define DRV_NAME "pch-dma"
 
 #define DMA_CTL0_DISABLE		0x0
@@ -105,7 +107,6 @@ struct pch_dma_chan {
 
 	spinlock_t		lock;
 
-	dma_cookie_t		completed_cookie;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
@@ -416,20 +417,6 @@ static void pdc_advance_work(struct pch_dma_chan *pd_chan)
 	}
 }
 
-static dma_cookie_t pdc_assign_cookie(struct pch_dma_chan *pd_chan,
-				      struct pch_dma_desc *desc)
-{
-	dma_cookie_t cookie = pd_chan->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	pd_chan->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
-	return cookie;
-}
-
 static dma_cookie_t pd_tx_submit(struct dma_async_tx_descriptor *txd)
 {
 	struct pch_dma_desc *desc = to_pd_desc(txd);
@@ -437,7 +424,7 @@ static dma_cookie_t pd_tx_submit(struct dma_async_tx_descriptor *txd)
 	dma_cookie_t cookie;
 
 	spin_lock(&pd_chan->lock);
-	cookie = pdc_assign_cookie(pd_chan, desc);
+	cookie = dma_cookie_assign(txd);
 
 	if (list_empty(&pd_chan->active_list)) {
 		list_add_tail(&desc->desc_node, &pd_chan->active_list);
@@ -544,7 +531,7 @@ static int pd_alloc_chan_resources(struct dma_chan *chan)
 	spin_lock_irq(&pd_chan->lock);
 	list_splice(&tmp_list, &pd_chan->free_list);
 	pd_chan->descs_allocated = i;
-	pd_chan->completed_cookie = chan->cookie = 1;
+	dma_cookie_init(chan);
 	spin_unlock_irq(&pd_chan->lock);
 
 	pdc_enable_irq(chan, 1);
@@ -578,19 +565,12 @@ static enum dma_status pd_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 				    struct dma_tx_state *txstate)
 {
 	struct pch_dma_chan *pd_chan = to_pd_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_completed;
-	int ret;
+	enum dma_status ret;
 
 	spin_lock_irq(&pd_chan->lock);
-	last_completed = pd_chan->completed_cookie;
-	last_used = chan->cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
 	spin_unlock_irq(&pd_chan->lock);
 
-	ret = dma_async_is_complete(cookie, last_completed, last_used);
-
-	dma_set_tx_state(txstate, last_completed, last_used, 0);
-
 	return ret;
 }
 
@@ -607,7 +587,8 @@ static void pd_issue_pending(struct dma_chan *chan)
 
 static struct dma_async_tx_descriptor *pd_prep_slave_sg(struct dma_chan *chan,
 			struct scatterlist *sgl, unsigned int sg_len,
-			enum dma_transfer_direction direction, unsigned long flags)
+			enum dma_transfer_direction direction, unsigned long flags,
+			void *context)
 {
 	struct pch_dma_chan *pd_chan = to_pd_chan(chan);
 	struct pch_dma_slave *pd_slave = chan->private;
@@ -932,7 +913,7 @@ static int __devinit pch_dma_probe(struct pci_dev *pdev,
 		struct pch_dma_chan *pd_chan = &pd->channels[i];
 
 		pd_chan->chan.device = &pd->dma;
-		pd_chan->chan.cookie = 1;
+		dma_cookie_init(&pd_chan->chan);
 
 		pd_chan->membase = &regs->desc[i];
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 16b66c827f19..282caf118be8 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1,4 +1,6 @@
-/* linux/drivers/dma/pl330.c
+/*
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
  * Copyright (C) 2010 Samsung Electronics Co. Ltd.
  *	Jaswinder Singh <jassi.brar@samsung.com>
@@ -9,10 +11,15 @@
  * (at your option) any later version.
  */
 
+#include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
 #include <linux/amba/bus.h>
@@ -21,8 +28,497 @@
 #include <linux/scatterlist.h>
 #include <linux/of.h>
 
+#include "dmaengine.h"
+#define PL330_MAX_CHAN		8
+#define PL330_MAX_IRQS		32
+#define PL330_MAX_PERI		32
+
+enum pl330_srccachectrl {
+	SCCTRL0,	/* Noncacheable and nonbufferable */
+	SCCTRL1,	/* Bufferable only */
+	SCCTRL2,	/* Cacheable, but do not allocate */
+	SCCTRL3,	/* Cacheable and bufferable, but do not allocate */
+	SINVALID1,
+	SINVALID2,
+	SCCTRL6,	/* Cacheable write-through, allocate on reads only */
+	SCCTRL7,	/* Cacheable write-back, allocate on reads only */
+};
+
+enum pl330_dstcachectrl {
+	DCCTRL0,	/* Noncacheable and nonbufferable */
+	DCCTRL1,	/* Bufferable only */
+	DCCTRL2,	/* Cacheable, but do not allocate */
+	DCCTRL3,	/* Cacheable and bufferable, but do not allocate */
+	DINVALID1,	/* AWCACHE = 0x1000 */
+	DINVALID2,
+	DCCTRL6,	/* Cacheable write-through, allocate on writes only */
+	DCCTRL7,	/* Cacheable write-back, allocate on writes only */
+};
+
+enum pl330_byteswap {
+	SWAP_NO,
+	SWAP_2,
+	SWAP_4,
+	SWAP_8,
+	SWAP_16,
+};
+
+enum pl330_reqtype {
+	MEMTOMEM,
+	MEMTODEV,
+	DEVTOMEM,
+	DEVTODEV,
+};
+
+/* Register and Bit field Definitions */
+#define DS			0x0
+#define DS_ST_STOP		0x0
+#define DS_ST_EXEC		0x1
+#define DS_ST_CMISS		0x2
+#define DS_ST_UPDTPC		0x3
+#define DS_ST_WFE		0x4
+#define DS_ST_ATBRR		0x5
+#define DS_ST_QBUSY		0x6
+#define DS_ST_WFP		0x7
+#define DS_ST_KILL		0x8
+#define DS_ST_CMPLT		0x9
+#define DS_ST_FLTCMP		0xe
+#define DS_ST_FAULT		0xf
+
+#define DPC			0x4
+#define INTEN			0x20
+#define ES			0x24
+#define INTSTATUS		0x28
+#define INTCLR			0x2c
+#define FSM			0x30
+#define FSC			0x34
+#define FTM			0x38
+
+#define _FTC			0x40
+#define FTC(n)			(_FTC + (n)*0x4)
+
+#define _CS			0x100
+#define CS(n)			(_CS + (n)*0x8)
+#define CS_CNS			(1 << 21)
+
+#define _CPC			0x104
+#define CPC(n)			(_CPC + (n)*0x8)
+
+#define _SA			0x400
+#define SA(n)			(_SA + (n)*0x20)
+
+#define _DA			0x404
+#define DA(n)			(_DA + (n)*0x20)
+
+#define _CC			0x408
+#define CC(n)			(_CC + (n)*0x20)
+
+#define CC_SRCINC		(1 << 0)
+#define CC_DSTINC		(1 << 14)
+#define CC_SRCPRI		(1 << 8)
+#define CC_DSTPRI		(1 << 22)
+#define CC_SRCNS		(1 << 9)
+#define CC_DSTNS		(1 << 23)
+#define CC_SRCIA		(1 << 10)
+#define CC_DSTIA		(1 << 24)
+#define CC_SRCBRSTLEN_SHFT	4
+#define CC_DSTBRSTLEN_SHFT	18
+#define CC_SRCBRSTSIZE_SHFT	1
+#define CC_DSTBRSTSIZE_SHFT	15
+#define CC_SRCCCTRL_SHFT	11
+#define CC_SRCCCTRL_MASK	0x7
+#define CC_DSTCCTRL_SHFT	25
+#define CC_DRCCCTRL_MASK	0x7
+#define CC_SWAP_SHFT		28
+
+#define _LC0			0x40c
+#define LC0(n)			(_LC0 + (n)*0x20)
+
+#define _LC1			0x410
+#define LC1(n)			(_LC1 + (n)*0x20)
+
+#define DBGSTATUS		0xd00
+#define DBG_BUSY		(1 << 0)
+
+#define DBGCMD			0xd04
+#define DBGINST0		0xd08
+#define DBGINST1		0xd0c
+
+#define CR0			0xe00
+#define CR1			0xe04
+#define CR2			0xe08
+#define CR3			0xe0c
+#define CR4			0xe10
+#define CRD			0xe14
+
+#define PERIPH_ID		0xfe0
+#define PERIPH_REV_SHIFT	20
+#define PERIPH_REV_MASK		0xf
+#define PERIPH_REV_R0P0		0
+#define PERIPH_REV_R1P0		1
+#define PERIPH_REV_R1P1		2
+#define PCELL_ID		0xff0
+
+#define CR0_PERIPH_REQ_SET	(1 << 0)
+#define CR0_BOOT_EN_SET		(1 << 1)
+#define CR0_BOOT_MAN_NS		(1 << 2)
+#define CR0_NUM_CHANS_SHIFT	4
+#define CR0_NUM_CHANS_MASK	0x7
+#define CR0_NUM_PERIPH_SHIFT	12
+#define CR0_NUM_PERIPH_MASK	0x1f
+#define CR0_NUM_EVENTS_SHIFT	17
+#define CR0_NUM_EVENTS_MASK	0x1f
+
+#define CR1_ICACHE_LEN_SHIFT	0
+#define CR1_ICACHE_LEN_MASK	0x7
+#define CR1_NUM_ICACHELINES_SHIFT	4
+#define CR1_NUM_ICACHELINES_MASK	0xf
+
+#define CRD_DATA_WIDTH_SHIFT	0
+#define CRD_DATA_WIDTH_MASK	0x7
+#define CRD_WR_CAP_SHIFT	4
+#define CRD_WR_CAP_MASK		0x7
+#define CRD_WR_Q_DEP_SHIFT	8
+#define CRD_WR_Q_DEP_MASK	0xf
+#define CRD_RD_CAP_SHIFT	12
+#define CRD_RD_CAP_MASK		0x7
+#define CRD_RD_Q_DEP_SHIFT	16
+#define CRD_RD_Q_DEP_MASK	0xf
+#define CRD_DATA_BUFF_SHIFT	20
+#define CRD_DATA_BUFF_MASK	0x3ff
+
+#define PART			0x330
+#define DESIGNER		0x41
+#define REVISION		0x0
+#define INTEG_CFG		0x0
+#define PERIPH_ID_VAL		((PART << 0) | (DESIGNER << 12))
+
+#define PCELL_ID_VAL		0xb105f00d
+
+#define PL330_STATE_STOPPED		(1 << 0)
+#define PL330_STATE_EXECUTING		(1 << 1)
+#define PL330_STATE_WFE			(1 << 2)
+#define PL330_STATE_FAULTING		(1 << 3)
+#define PL330_STATE_COMPLETING		(1 << 4)
+#define PL330_STATE_WFP			(1 << 5)
+#define PL330_STATE_KILLING		(1 << 6)
+#define PL330_STATE_FAULT_COMPLETING	(1 << 7)
+#define PL330_STATE_CACHEMISS		(1 << 8)
+#define PL330_STATE_UPDTPC		(1 << 9)
+#define PL330_STATE_ATBARRIER		(1 << 10)
+#define PL330_STATE_QUEUEBUSY		(1 << 11)
+#define PL330_STATE_INVALID		(1 << 15)
+
+#define PL330_STABLE_STATES (PL330_STATE_STOPPED | PL330_STATE_EXECUTING \
+				| PL330_STATE_WFE | PL330_STATE_FAULTING)
+
+#define CMD_DMAADDH		0x54
+#define CMD_DMAEND		0x00
+#define CMD_DMAFLUSHP		0x35
+#define CMD_DMAGO		0xa0
+#define CMD_DMALD		0x04
+#define CMD_DMALDP		0x25
+#define CMD_DMALP		0x20
+#define CMD_DMALPEND		0x28
+#define CMD_DMAKILL		0x01
+#define CMD_DMAMOV		0xbc
+#define CMD_DMANOP		0x18
+#define CMD_DMARMB		0x12
+#define CMD_DMASEV		0x34
+#define CMD_DMAST		0x08
+#define CMD_DMASTP		0x29
+#define CMD_DMASTZ		0x0c
+#define CMD_DMAWFE		0x36
+#define CMD_DMAWFP		0x30
+#define CMD_DMAWMB		0x13
+
+#define SZ_DMAADDH		3
+#define SZ_DMAEND		1
+#define SZ_DMAFLUSHP		2
+#define SZ_DMALD		1
+#define SZ_DMALDP		2
+#define SZ_DMALP		2
+#define SZ_DMALPEND		2
+#define SZ_DMAKILL		1
+#define SZ_DMAMOV		6
+#define SZ_DMANOP		1
+#define SZ_DMARMB		1
+#define SZ_DMASEV		2
+#define SZ_DMAST		1
+#define SZ_DMASTP		2
+#define SZ_DMASTZ		1
+#define SZ_DMAWFE		2
+#define SZ_DMAWFP		2
+#define SZ_DMAWMB		1
+#define SZ_DMAGO		6
+
+#define BRST_LEN(ccr)		((((ccr) >> CC_SRCBRSTLEN_SHFT) & 0xf) + 1)
+#define BRST_SIZE(ccr)		(1 << (((ccr) >> CC_SRCBRSTSIZE_SHFT) & 0x7))
+
+#define BYTE_TO_BURST(b, ccr)	((b) / BRST_SIZE(ccr) / BRST_LEN(ccr))
+#define BURST_TO_BYTE(c, ccr)	((c) * BRST_SIZE(ccr) * BRST_LEN(ccr))
+
+/*
+ * With 256 bytes, we can do more than 2.5MB and 5MB xfers per req
+ * at 1byte/burst for P<->M and M<->M respectively.
+ * For typical scenario, at 1word/burst, 10MB and 20MB xfers per req
+ * should be enough for P<->M and M<->M respectively.
+ */
+#define MCODE_BUFF_PER_REQ	256
+
+/* If the _pl330_req is available to the client */
+#define IS_FREE(req)	(*((u8 *)((req)->mc_cpu)) == CMD_DMAEND)
+
+/* Use this _only_ to wait on transient states */
+#define UNTIL(t, s)	while (!(_state(t) & (s))) cpu_relax();
+
+#ifdef PL330_DEBUG_MCGEN
+static unsigned cmd_line;
+#define PL330_DBGCMD_DUMP(off, x...)	do { \
+						printk("%x:", cmd_line); \
+						printk(x); \
+						cmd_line += off; \
+					} while (0)
+#define PL330_DBGMC_START(addr)		(cmd_line = addr)
+#else
+#define PL330_DBGCMD_DUMP(off, x...)	do {} while (0)
+#define PL330_DBGMC_START(addr)		do {} while (0)
+#endif
+
+/* The number of default descriptors */
+
 #define NR_DEFAULT_DESC	16
 
+/* Populated by the PL330 core driver for DMA API driver's info */
+struct pl330_config {
+	u32	periph_id;
+	u32	pcell_id;
+#define DMAC_MODE_NS	(1 << 0)
+	unsigned int	mode;
+	unsigned int	data_bus_width:10; /* In number of bits */
+	unsigned int	data_buf_dep:10;
+	unsigned int	num_chan:4;
+	unsigned int	num_peri:6;
+	u32		peri_ns;
+	unsigned int	num_events:6;
+	u32		irq_ns;
+};
+
+/* Handle to the DMAC provided to the PL330 core */
+struct pl330_info {
+	/* Owning device */
+	struct device *dev;
+	/* Size of MicroCode buffers for each channel. */
+	unsigned mcbufsz;
+	/* ioremap'ed address of PL330 registers. */
+	void __iomem	*base;
+	/* Client can freely use it. */
+	void	*client_data;
+	/* PL330 core data, Client must not touch it. */
+	void	*pl330_data;
+	/* Populated by the PL330 core driver during pl330_add */
+	struct pl330_config	pcfg;
+	/*
+	 * If the DMAC has some reset mechanism, then the
+	 * client may want to provide pointer to the method.
+	 */
+	void (*dmac_reset)(struct pl330_info *pi);
+};
+
+/**
+ * Request Configuration.
+ * The PL330 core does not modify this and uses the last
+ * working configuration if the request doesn't provide any.
+ *
+ * The Client may want to provide this info only for the
+ * first request and a request with new settings.
+ */
+struct pl330_reqcfg {
+	/* Address Incrementing */
+	unsigned dst_inc:1;
+	unsigned src_inc:1;
+
+	/*
+	 * For now, the SRC & DST protection levels
+	 * and burst size/length are assumed same.
+	 */
+	bool nonsecure;
+	bool privileged;
+	bool insnaccess;
+	unsigned brst_len:5;
+	unsigned brst_size:3; /* in power of 2 */
+
+	enum pl330_dstcachectrl dcctl;
+	enum pl330_srccachectrl scctl;
+	enum pl330_byteswap swap;
+	struct pl330_config *pcfg;
+};
+
+/*
+ * One cycle of DMAC operation.
+ * There may be more than one xfer in a request.
+ */
+struct pl330_xfer {
+	u32 src_addr;
+	u32 dst_addr;
+	/* Size to xfer */
+	u32 bytes;
+	/*
+	 * Pointer to next xfer in the list.
+	 * The last xfer in the req must point to NULL.
+	 */
+	struct pl330_xfer *next;
+};
+
+/* The xfer callbacks are made with one of these arguments. */
+enum pl330_op_err {
+	/* The all xfers in the request were success. */
+	PL330_ERR_NONE,
+	/* If req aborted due to global error. */
+	PL330_ERR_ABORT,
+	/* If req failed due to problem with Channel. */
+	PL330_ERR_FAIL,
+};
+
+/* A request defining Scatter-Gather List ending with NULL xfer. */
+struct pl330_req {
+	enum pl330_reqtype rqtype;
+	/* Index of peripheral for the xfer. */
+	unsigned peri:5;
+	/* Unique token for this xfer, set by the client. */
+	void *token;
+	/* Callback to be called after xfer. */
+	void (*xfer_cb)(void *token, enum pl330_op_err err);
+	/* If NULL, req will be done at last set parameters. */
+	struct pl330_reqcfg *cfg;
+	/* Pointer to first xfer in the request. */
+	struct pl330_xfer *x;
+};
+
+/*
+ * To know the status of the channel and DMAC, the client
+ * provides a pointer to this structure. The PL330 core
+ * fills it with current information.
+ */
+struct pl330_chanstatus {
+	/*
+	 * If the DMAC engine halted due to some error,
+	 * the client should remove-add DMAC.
+	 */
+	bool dmac_halted;
+	/*
+	 * If channel is halted due to some error,
+	 * the client should ABORT/FLUSH and START the channel.
+	 */
+	bool faulting;
+	/* Location of last load */
+	u32 src_addr;
+	/* Location of last store */
+	u32 dst_addr;
+	/*
+	 * Pointer to the currently active req, NULL if channel is
+	 * inactive, even though the requests may be present.
+	 */
+	struct pl330_req *top_req;
+	/* Pointer to req waiting second in the queue if any. */
+	struct pl330_req *wait_req;
+};
+
+enum pl330_chan_op {
+	/* Start the channel */
+	PL330_OP_START,
+	/* Abort the active xfer */
+	PL330_OP_ABORT,
+	/* Stop xfer and flush queue */
+	PL330_OP_FLUSH,
+};
+
+struct _xfer_spec {
+	u32 ccr;
+	struct pl330_req *r;
+	struct pl330_xfer *x;
+};
+
+enum dmamov_dst {
+	SAR = 0,
+	CCR,
+	DAR,
+};
+
+enum pl330_dst {
+	SRC = 0,
+	DST,
+};
+
+enum pl330_cond {
+	SINGLE,
+	BURST,
+	ALWAYS,
+};
+
+struct _pl330_req {
+	u32 mc_bus;
+	void *mc_cpu;
+	/* Number of bytes taken to setup MC for the req */
+	u32 mc_len;
+	struct pl330_req *r;
+	/* Hook to attach to DMAC's list of reqs with due callback */
+	struct list_head rqd;
+};
+
+/* ToBeDone for tasklet */
+struct _pl330_tbd {
+	bool reset_dmac;
+	bool reset_mngr;
+	u8 reset_chan;
+};
+
+/* A DMAC Thread */
+struct pl330_thread {
+	u8 id;
+	int ev;
+	/* If the channel is not yet acquired by any client */
+	bool free;
+	/* Parent DMAC */
+	struct pl330_dmac *dmac;
+	/* Only two at a time */
+	struct _pl330_req req[2];
+	/* Index of the last enqueued request */
+	unsigned lstenq;
+	/* Index of the last submitted request or -1 if the DMA is stopped */
+	int req_running;
+};
+
+enum pl330_dmac_state {
+	UNINIT,
+	INIT,
+	DYING,
+};
+
+/* A DMAC */
+struct pl330_dmac {
+	spinlock_t		lock;
+	/* Holds list of reqs with due callbacks */
+	struct list_head	req_done;
+	/* Pointer to platform specific stuff */
+	struct pl330_info	*pinfo;
+	/* Maximum possible events/irqs */
+	int			events[32];
+	/* BUS address of MicroCode buffer */
+	u32			mcode_bus;
+	/* CPU address of MicroCode buffer */
+	void			*mcode_cpu;
+	/* List of all Channel threads */
+	struct pl330_thread	*channels;
+	/* Pointer to the MANAGER thread */
+	struct pl330_thread	*manager;
+	/* To handle bad news in interrupt */
+	struct tasklet_struct	tasks;
+	struct _pl330_tbd	dmac_tbd;
+	/* State of DMAC operation */
+	enum pl330_dmac_state	state;
+};
+
 enum desc_status {
 	/* In the DMAC pool */
 	FREE,
@@ -51,9 +547,6 @@ struct dma_pl330_chan {
 	/* DMA-Engine Channel */
 	struct dma_chan chan;
 
-	/* Last completed cookie */
-	dma_cookie_t completed;
-
 	/* List of to be xfered descriptors */
 	struct list_head work_list;
 
@@ -117,6 +610,1599 @@ struct dma_pl330_desc {
 	struct dma_pl330_chan *pchan;
 };
 
+static inline void _callback(struct pl330_req *r, enum pl330_op_err err)
+{
+	if (r && r->xfer_cb)
+		r->xfer_cb(r->token, err);
+}
+
+static inline bool _queue_empty(struct pl330_thread *thrd)
+{
+	return (IS_FREE(&thrd->req[0]) && IS_FREE(&thrd->req[1]))
+		? true : false;
+}
+
+static inline bool _queue_full(struct pl330_thread *thrd)
+{
+	return (IS_FREE(&thrd->req[0]) || IS_FREE(&thrd->req[1]))
+		? false : true;
+}
+
+static inline bool is_manager(struct pl330_thread *thrd)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+
+	/* MANAGER is indexed at the end */
+	if (thrd->id == pl330->pinfo->pcfg.num_chan)
+		return true;
+	else
+		return false;
+}
+
+/* If manager of the thread is in Non-Secure mode */
+static inline bool _manager_ns(struct pl330_thread *thrd)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+
+	return (pl330->pinfo->pcfg.mode & DMAC_MODE_NS) ? true : false;
+}
+
+static inline u32 get_id(struct pl330_info *pi, u32 off)
+{
+	void __iomem *regs = pi->base;
+	u32 id = 0;
+
+	id |= (readb(regs + off + 0x0) << 0);
+	id |= (readb(regs + off + 0x4) << 8);
+	id |= (readb(regs + off + 0x8) << 16);
+	id |= (readb(regs + off + 0xc) << 24);
+
+	return id;
+}
+
+static inline u32 get_revision(u32 periph_id)
+{
+	return (periph_id >> PERIPH_REV_SHIFT) & PERIPH_REV_MASK;
+}
+
+static inline u32 _emit_ADDH(unsigned dry_run, u8 buf[],
+		enum pl330_dst da, u16 val)
+{
+	if (dry_run)
+		return SZ_DMAADDH;
+
+	buf[0] = CMD_DMAADDH;
+	buf[0] |= (da << 1);
+	*((u16 *)&buf[1]) = val;
+
+	PL330_DBGCMD_DUMP(SZ_DMAADDH, "\tDMAADDH %s %u\n",
+		da == 1 ? "DA" : "SA", val);
+
+	return SZ_DMAADDH;
+}
+
+static inline u32 _emit_END(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMAEND;
+
+	buf[0] = CMD_DMAEND;
+
+	PL330_DBGCMD_DUMP(SZ_DMAEND, "\tDMAEND\n");
+
+	return SZ_DMAEND;
+}
+
+static inline u32 _emit_FLUSHP(unsigned dry_run, u8 buf[], u8 peri)
+{
+	if (dry_run)
+		return SZ_DMAFLUSHP;
+
+	buf[0] = CMD_DMAFLUSHP;
+
+	peri &= 0x1f;
+	peri <<= 3;
+	buf[1] = peri;
+
+	PL330_DBGCMD_DUMP(SZ_DMAFLUSHP, "\tDMAFLUSHP %u\n", peri >> 3);
+
+	return SZ_DMAFLUSHP;
+}
+
+static inline u32 _emit_LD(unsigned dry_run, u8 buf[],	enum pl330_cond cond)
+{
+	if (dry_run)
+		return SZ_DMALD;
+
+	buf[0] = CMD_DMALD;
+
+	if (cond == SINGLE)
+		buf[0] |= (0 << 1) | (1 << 0);
+	else if (cond == BURST)
+		buf[0] |= (1 << 1) | (1 << 0);
+
+	PL330_DBGCMD_DUMP(SZ_DMALD, "\tDMALD%c\n",
+		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'));
+
+	return SZ_DMALD;
+}
+
+static inline u32 _emit_LDP(unsigned dry_run, u8 buf[],
+		enum pl330_cond cond, u8 peri)
+{
+	if (dry_run)
+		return SZ_DMALDP;
+
+	buf[0] = CMD_DMALDP;
+
+	if (cond == BURST)
+		buf[0] |= (1 << 1);
+
+	peri &= 0x1f;
+	peri <<= 3;
+	buf[1] = peri;
+
+	PL330_DBGCMD_DUMP(SZ_DMALDP, "\tDMALDP%c %u\n",
+		cond == SINGLE ? 'S' : 'B', peri >> 3);
+
+	return SZ_DMALDP;
+}
+
+static inline u32 _emit_LP(unsigned dry_run, u8 buf[],
+		unsigned loop, u8 cnt)
+{
+	if (dry_run)
+		return SZ_DMALP;
+
+	buf[0] = CMD_DMALP;
+
+	if (loop)
+		buf[0] |= (1 << 1);
+
+	cnt--; /* DMAC increments by 1 internally */
+	buf[1] = cnt;
+
+	PL330_DBGCMD_DUMP(SZ_DMALP, "\tDMALP_%c %u\n", loop ? '1' : '0', cnt);
+
+	return SZ_DMALP;
+}
+
+struct _arg_LPEND {
+	enum pl330_cond cond;
+	bool forever;
+	unsigned loop;
+	u8 bjump;
+};
+
+static inline u32 _emit_LPEND(unsigned dry_run, u8 buf[],
+		const struct _arg_LPEND *arg)
+{
+	enum pl330_cond cond = arg->cond;
+	bool forever = arg->forever;
+	unsigned loop = arg->loop;
+	u8 bjump = arg->bjump;
+
+	if (dry_run)
+		return SZ_DMALPEND;
+
+	buf[0] = CMD_DMALPEND;
+
+	if (loop)
+		buf[0] |= (1 << 2);
+
+	if (!forever)
+		buf[0] |= (1 << 4);
+
+	if (cond == SINGLE)
+		buf[0] |= (0 << 1) | (1 << 0);
+	else if (cond == BURST)
+		buf[0] |= (1 << 1) | (1 << 0);
+
+	buf[1] = bjump;
+
+	PL330_DBGCMD_DUMP(SZ_DMALPEND, "\tDMALP%s%c_%c bjmpto_%x\n",
+			forever ? "FE" : "END",
+			cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'),
+			loop ? '1' : '0',
+			bjump);
+
+	return SZ_DMALPEND;
+}
+
+static inline u32 _emit_KILL(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMAKILL;
+
+	buf[0] = CMD_DMAKILL;
+
+	return SZ_DMAKILL;
+}
+
+static inline u32 _emit_MOV(unsigned dry_run, u8 buf[],
+		enum dmamov_dst dst, u32 val)
+{
+	if (dry_run)
+		return SZ_DMAMOV;
+
+	buf[0] = CMD_DMAMOV;
+	buf[1] = dst;
+	*((u32 *)&buf[2]) = val;
+
+	PL330_DBGCMD_DUMP(SZ_DMAMOV, "\tDMAMOV %s 0x%x\n",
+		dst == SAR ? "SAR" : (dst == DAR ? "DAR" : "CCR"), val);
+
+	return SZ_DMAMOV;
+}
+
+static inline u32 _emit_NOP(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMANOP;
+
+	buf[0] = CMD_DMANOP;
+
+	PL330_DBGCMD_DUMP(SZ_DMANOP, "\tDMANOP\n");
+
+	return SZ_DMANOP;
+}
+
+static inline u32 _emit_RMB(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMARMB;
+
+	buf[0] = CMD_DMARMB;
+
+	PL330_DBGCMD_DUMP(SZ_DMARMB, "\tDMARMB\n");
+
+	return SZ_DMARMB;
+}
+
+static inline u32 _emit_SEV(unsigned dry_run, u8 buf[], u8 ev)
+{
+	if (dry_run)
+		return SZ_DMASEV;
+
+	buf[0] = CMD_DMASEV;
+
+	ev &= 0x1f;
+	ev <<= 3;
+	buf[1] = ev;
+
+	PL330_DBGCMD_DUMP(SZ_DMASEV, "\tDMASEV %u\n", ev >> 3);
+
+	return SZ_DMASEV;
+}
+
+static inline u32 _emit_ST(unsigned dry_run, u8 buf[], enum pl330_cond cond)
+{
+	if (dry_run)
+		return SZ_DMAST;
+
+	buf[0] = CMD_DMAST;
+
+	if (cond == SINGLE)
+		buf[0] |= (0 << 1) | (1 << 0);
+	else if (cond == BURST)
+		buf[0] |= (1 << 1) | (1 << 0);
+
+	PL330_DBGCMD_DUMP(SZ_DMAST, "\tDMAST%c\n",
+		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'A'));
+
+	return SZ_DMAST;
+}
+
+static inline u32 _emit_STP(unsigned dry_run, u8 buf[],
+		enum pl330_cond cond, u8 peri)
+{
+	if (dry_run)
+		return SZ_DMASTP;
+
+	buf[0] = CMD_DMASTP;
+
+	if (cond == BURST)
+		buf[0] |= (1 << 1);
+
+	peri &= 0x1f;
+	peri <<= 3;
+	buf[1] = peri;
+
+	PL330_DBGCMD_DUMP(SZ_DMASTP, "\tDMASTP%c %u\n",
+		cond == SINGLE ? 'S' : 'B', peri >> 3);
+
+	return SZ_DMASTP;
+}
+
+static inline u32 _emit_STZ(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMASTZ;
+
+	buf[0] = CMD_DMASTZ;
+
+	PL330_DBGCMD_DUMP(SZ_DMASTZ, "\tDMASTZ\n");
+
+	return SZ_DMASTZ;
+}
+
+static inline u32 _emit_WFE(unsigned dry_run, u8 buf[], u8 ev,
+		unsigned invalidate)
+{
+	if (dry_run)
+		return SZ_DMAWFE;
+
+	buf[0] = CMD_DMAWFE;
+
+	ev &= 0x1f;
+	ev <<= 3;
+	buf[1] = ev;
+
+	if (invalidate)
+		buf[1] |= (1 << 1);
+
+	PL330_DBGCMD_DUMP(SZ_DMAWFE, "\tDMAWFE %u%s\n",
+		ev >> 3, invalidate ? ", I" : "");
+
+	return SZ_DMAWFE;
+}
+
+static inline u32 _emit_WFP(unsigned dry_run, u8 buf[],
+		enum pl330_cond cond, u8 peri)
+{
+	if (dry_run)
+		return SZ_DMAWFP;
+
+	buf[0] = CMD_DMAWFP;
+
+	if (cond == SINGLE)
+		buf[0] |= (0 << 1) | (0 << 0);
+	else if (cond == BURST)
+		buf[0] |= (1 << 1) | (0 << 0);
+	else
+		buf[0] |= (0 << 1) | (1 << 0);
+
+	peri &= 0x1f;
+	peri <<= 3;
+	buf[1] = peri;
+
+	PL330_DBGCMD_DUMP(SZ_DMAWFP, "\tDMAWFP%c %u\n",
+		cond == SINGLE ? 'S' : (cond == BURST ? 'B' : 'P'), peri >> 3);
+
+	return SZ_DMAWFP;
+}
+
+static inline u32 _emit_WMB(unsigned dry_run, u8 buf[])
+{
+	if (dry_run)
+		return SZ_DMAWMB;
+
+	buf[0] = CMD_DMAWMB;
+
+	PL330_DBGCMD_DUMP(SZ_DMAWMB, "\tDMAWMB\n");
+
+	return SZ_DMAWMB;
+}
+
+struct _arg_GO {
+	u8 chan;
+	u32 addr;
+	unsigned ns;
+};
+
+static inline u32 _emit_GO(unsigned dry_run, u8 buf[],
+		const struct _arg_GO *arg)
+{
+	u8 chan = arg->chan;
+	u32 addr = arg->addr;
+	unsigned ns = arg->ns;
+
+	if (dry_run)
+		return SZ_DMAGO;
+
+	buf[0] = CMD_DMAGO;
+	buf[0] |= (ns << 1);
+
+	buf[1] = chan & 0x7;
+
+	*((u32 *)&buf[2]) = addr;
+
+	return SZ_DMAGO;
+}
+
+#define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t)
+
+/* Returns Time-Out */
+static bool _until_dmac_idle(struct pl330_thread *thrd)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	unsigned long loops = msecs_to_loops(5);
+
+	do {
+		/* Until Manager is Idle */
+		if (!(readl(regs + DBGSTATUS) & DBG_BUSY))
+			break;
+
+		cpu_relax();
+	} while (--loops);
+
+	if (!loops)
+		return true;
+
+	return false;
+}
+
+static inline void _execute_DBGINSN(struct pl330_thread *thrd,
+		u8 insn[], bool as_manager)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	u32 val;
+
+	val = (insn[0] << 16) | (insn[1] << 24);
+	if (!as_manager) {
+		val |= (1 << 0);
+		val |= (thrd->id << 8); /* Channel Number */
+	}
+	writel(val, regs + DBGINST0);
+
+	val = *((u32 *)&insn[2]);
+	writel(val, regs + DBGINST1);
+
+	/* If timed out due to halted state-machine */
+	if (_until_dmac_idle(thrd)) {
+		dev_err(thrd->dmac->pinfo->dev, "DMAC halted!\n");
+		return;
+	}
+
+	/* Get going */
+	writel(0, regs + DBGCMD);
+}
+
+/*
+ * Mark a _pl330_req as free.
+ * We do it by writing DMAEND as the first instruction
+ * because no valid request is going to have DMAEND as
+ * its first instruction to execute.
+ */
+static void mark_free(struct pl330_thread *thrd, int idx)
+{
+	struct _pl330_req *req = &thrd->req[idx];
+
+	_emit_END(0, req->mc_cpu);
+	req->mc_len = 0;
+
+	thrd->req_running = -1;
+}
+
+static inline u32 _state(struct pl330_thread *thrd)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	u32 val;
+
+	if (is_manager(thrd))
+		val = readl(regs + DS) & 0xf;
+	else
+		val = readl(regs + CS(thrd->id)) & 0xf;
+
+	switch (val) {
+	case DS_ST_STOP:
+		return PL330_STATE_STOPPED;
+	case DS_ST_EXEC:
+		return PL330_STATE_EXECUTING;
+	case DS_ST_CMISS:
+		return PL330_STATE_CACHEMISS;
+	case DS_ST_UPDTPC:
+		return PL330_STATE_UPDTPC;
+	case DS_ST_WFE:
+		return PL330_STATE_WFE;
+	case DS_ST_FAULT:
+		return PL330_STATE_FAULTING;
+	case DS_ST_ATBRR:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_ATBARRIER;
+	case DS_ST_QBUSY:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_QUEUEBUSY;
+	case DS_ST_WFP:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_WFP;
+	case DS_ST_KILL:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_KILLING;
+	case DS_ST_CMPLT:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_COMPLETING;
+	case DS_ST_FLTCMP:
+		if (is_manager(thrd))
+			return PL330_STATE_INVALID;
+		else
+			return PL330_STATE_FAULT_COMPLETING;
+	default:
+		return PL330_STATE_INVALID;
+	}
+}
+
+static void _stop(struct pl330_thread *thrd)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	u8 insn[6] = {0, 0, 0, 0, 0, 0};
+
+	if (_state(thrd) == PL330_STATE_FAULT_COMPLETING)
+		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
+
+	/* Return if nothing needs to be done */
+	if (_state(thrd) == PL330_STATE_COMPLETING
+		  || _state(thrd) == PL330_STATE_KILLING
+		  || _state(thrd) == PL330_STATE_STOPPED)
+		return;
+
+	_emit_KILL(0, insn);
+
+	/* Stop generating interrupts for SEV */
+	writel(readl(regs + INTEN) & ~(1 << thrd->ev), regs + INTEN);
+
+	_execute_DBGINSN(thrd, insn, is_manager(thrd));
+}
+
+/* Start doing req 'idx' of thread 'thrd' */
+static bool _trigger(struct pl330_thread *thrd)
+{
+	void __iomem *regs = thrd->dmac->pinfo->base;
+	struct _pl330_req *req;
+	struct pl330_req *r;
+	struct _arg_GO go;
+	unsigned ns;
+	u8 insn[6] = {0, 0, 0, 0, 0, 0};
+	int idx;
+
+	/* Return if already ACTIVE */
+	if (_state(thrd) != PL330_STATE_STOPPED)
+		return true;
+
+	idx = 1 - thrd->lstenq;
+	if (!IS_FREE(&thrd->req[idx]))
+		req = &thrd->req[idx];
+	else {
+		idx = thrd->lstenq;
+		if (!IS_FREE(&thrd->req[idx]))
+			req = &thrd->req[idx];
+		else
+			req = NULL;
+	}
+
+	/* Return if no request */
+	if (!req || !req->r)
+		return true;
+
+	r = req->r;
+
+	if (r->cfg)
+		ns = r->cfg->nonsecure ? 1 : 0;
+	else if (readl(regs + CS(thrd->id)) & CS_CNS)
+		ns = 1;
+	else
+		ns = 0;
+
+	/* See 'Abort Sources' point-4 at Page 2-25 */
+	if (_manager_ns(thrd) && !ns)
+		dev_info(thrd->dmac->pinfo->dev, "%s:%d Recipe for ABORT!\n",
+			__func__, __LINE__);
+
+	go.chan = thrd->id;
+	go.addr = req->mc_bus;
+	go.ns = ns;
+	_emit_GO(0, insn, &go);
+
+	/* Set to generate interrupts for SEV */
+	writel(readl(regs + INTEN) | (1 << thrd->ev), regs + INTEN);
+
+	/* Only manager can execute GO */
+	_execute_DBGINSN(thrd, insn, true);
+
+	thrd->req_running = idx;
+
+	return true;
+}
+
+static bool _start(struct pl330_thread *thrd)
+{
+	switch (_state(thrd)) {
+	case PL330_STATE_FAULT_COMPLETING:
+		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
+
+		if (_state(thrd) == PL330_STATE_KILLING)
+			UNTIL(thrd, PL330_STATE_STOPPED)
+
+	case PL330_STATE_FAULTING:
+		_stop(thrd);
+
+	case PL330_STATE_KILLING:
+	case PL330_STATE_COMPLETING:
+		UNTIL(thrd, PL330_STATE_STOPPED)
+
+	case PL330_STATE_STOPPED:
+		return _trigger(thrd);
+
+	case PL330_STATE_WFP:
+	case PL330_STATE_QUEUEBUSY:
+	case PL330_STATE_ATBARRIER:
+	case PL330_STATE_UPDTPC:
+	case PL330_STATE_CACHEMISS:
+	case PL330_STATE_EXECUTING:
+		return true;
+
+	case PL330_STATE_WFE: /* For RESUME, nothing yet */
+	default:
+		return false;
+	}
+}
+
+static inline int _ldst_memtomem(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs, int cyc)
+{
+	int off = 0;
+	struct pl330_config *pcfg = pxs->r->cfg->pcfg;
+
+	/* check lock-up free version */
+	if (get_revision(pcfg->periph_id) >= PERIPH_REV_R1P0) {
+		while (cyc--) {
+			off += _emit_LD(dry_run, &buf[off], ALWAYS);
+			off += _emit_ST(dry_run, &buf[off], ALWAYS);
+		}
+	} else {
+		while (cyc--) {
+			off += _emit_LD(dry_run, &buf[off], ALWAYS);
+			off += _emit_RMB(dry_run, &buf[off]);
+			off += _emit_ST(dry_run, &buf[off], ALWAYS);
+			off += _emit_WMB(dry_run, &buf[off]);
+		}
+	}
+
+	return off;
+}
+
+static inline int _ldst_devtomem(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs, int cyc)
+{
+	int off = 0;
+
+	while (cyc--) {
+		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri);
+		off += _emit_LDP(dry_run, &buf[off], SINGLE, pxs->r->peri);
+		off += _emit_ST(dry_run, &buf[off], ALWAYS);
+		off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri);
+	}
+
+	return off;
+}
+
+static inline int _ldst_memtodev(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs, int cyc)
+{
+	int off = 0;
+
+	while (cyc--) {
+		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri);
+		off += _emit_LD(dry_run, &buf[off], ALWAYS);
+		off += _emit_STP(dry_run, &buf[off], SINGLE, pxs->r->peri);
+		off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri);
+	}
+
+	return off;
+}
+
+static int _bursts(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs, int cyc)
+{
+	int off = 0;
+
+	switch (pxs->r->rqtype) {
+	case MEMTODEV:
+		off += _ldst_memtodev(dry_run, &buf[off], pxs, cyc);
+		break;
+	case DEVTOMEM:
+		off += _ldst_devtomem(dry_run, &buf[off], pxs, cyc);
+		break;
+	case MEMTOMEM:
+		off += _ldst_memtomem(dry_run, &buf[off], pxs, cyc);
+		break;
+	default:
+		off += 0x40000000; /* Scare off the Client */
+		break;
+	}
+
+	return off;
+}
+
+/* Returns bytes consumed and updates bursts */
+static inline int _loop(unsigned dry_run, u8 buf[],
+		unsigned long *bursts, const struct _xfer_spec *pxs)
+{
+	int cyc, cycmax, szlp, szlpend, szbrst, off;
+	unsigned lcnt0, lcnt1, ljmp0, ljmp1;
+	struct _arg_LPEND lpend;
+
+	/* Max iterations possible in DMALP is 256 */
+	if (*bursts >= 256*256) {
+		lcnt1 = 256;
+		lcnt0 = 256;
+		cyc = *bursts / lcnt1 / lcnt0;
+	} else if (*bursts > 256) {
+		lcnt1 = 256;
+		lcnt0 = *bursts / lcnt1;
+		cyc = 1;
+	} else {
+		lcnt1 = *bursts;
+		lcnt0 = 0;
+		cyc = 1;
+	}
+
+	szlp = _emit_LP(1, buf, 0, 0);
+	szbrst = _bursts(1, buf, pxs, 1);
+
+	lpend.cond = ALWAYS;
+	lpend.forever = false;
+	lpend.loop = 0;
+	lpend.bjump = 0;
+	szlpend = _emit_LPEND(1, buf, &lpend);
+
+	if (lcnt0) {
+		szlp *= 2;
+		szlpend *= 2;
+	}
+
+	/*
+	 * Max bursts that we can unroll due to limit on the
+	 * size of backward jump that can be encoded in DMALPEND
+	 * which is 8-bits and hence 255
+	 */
+	cycmax = (255 - (szlp + szlpend)) / szbrst;
+
+	cyc = (cycmax < cyc) ? cycmax : cyc;
+
+	off = 0;
+
+	if (lcnt0) {
+		off += _emit_LP(dry_run, &buf[off], 0, lcnt0);
+		ljmp0 = off;
+	}
+
+	off += _emit_LP(dry_run, &buf[off], 1, lcnt1);
+	ljmp1 = off;
+
+	off += _bursts(dry_run, &buf[off], pxs, cyc);
+
+	lpend.cond = ALWAYS;
+	lpend.forever = false;
+	lpend.loop = 1;
+	lpend.bjump = off - ljmp1;
+	off += _emit_LPEND(dry_run, &buf[off], &lpend);
+
+	if (lcnt0) {
+		lpend.cond = ALWAYS;
+		lpend.forever = false;
+		lpend.loop = 0;
+		lpend.bjump = off - ljmp0;
+		off += _emit_LPEND(dry_run, &buf[off], &lpend);
+	}
+
+	*bursts = lcnt1 * cyc;
+	if (lcnt0)
+		*bursts *= lcnt0;
+
+	return off;
+}
+
+static inline int _setup_loops(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs)
+{
+	struct pl330_xfer *x = pxs->x;
+	u32 ccr = pxs->ccr;
+	unsigned long c, bursts = BYTE_TO_BURST(x->bytes, ccr);
+	int off = 0;
+
+	while (bursts) {
+		c = bursts;
+		off += _loop(dry_run, &buf[off], &c, pxs);
+		bursts -= c;
+	}
+
+	return off;
+}
+
+static inline int _setup_xfer(unsigned dry_run, u8 buf[],
+		const struct _xfer_spec *pxs)
+{
+	struct pl330_xfer *x = pxs->x;
+	int off = 0;
+
+	/* DMAMOV SAR, x->src_addr */
+	off += _emit_MOV(dry_run, &buf[off], SAR, x->src_addr);
+	/* DMAMOV DAR, x->dst_addr */
+	off += _emit_MOV(dry_run, &buf[off], DAR, x->dst_addr);
+
+	/* Setup Loop(s) */
+	off += _setup_loops(dry_run, &buf[off], pxs);
+
+	return off;
+}
+
+/*
+ * A req is a sequence of one or more xfer units.
+ * Returns the number of bytes taken to setup the MC for the req.
+ */
+static int _setup_req(unsigned dry_run, struct pl330_thread *thrd,
+		unsigned index, struct _xfer_spec *pxs)
+{
+	struct _pl330_req *req = &thrd->req[index];
+	struct pl330_xfer *x;
+	u8 *buf = req->mc_cpu;
+	int off = 0;
+
+	PL330_DBGMC_START(req->mc_bus);
+
+	/* DMAMOV CCR, ccr */
+	off += _emit_MOV(dry_run, &buf[off], CCR, pxs->ccr);
+
+	x = pxs->r->x;
+	do {
+		/* Error if xfer length is not aligned at burst size */
+		if (x->bytes % (BRST_SIZE(pxs->ccr) * BRST_LEN(pxs->ccr)))
+			return -EINVAL;
+
+		pxs->x = x;
+		off += _setup_xfer(dry_run, &buf[off], pxs);
+
+		x = x->next;
+	} while (x);
+
+	/* DMASEV peripheral/event */
+	off += _emit_SEV(dry_run, &buf[off], thrd->ev);
+	/* DMAEND */
+	off += _emit_END(dry_run, &buf[off]);
+
+	return off;
+}
+
+static inline u32 _prepare_ccr(const struct pl330_reqcfg *rqc)
+{
+	u32 ccr = 0;
+
+	if (rqc->src_inc)
+		ccr |= CC_SRCINC;
+
+	if (rqc->dst_inc)
+		ccr |= CC_DSTINC;
+
+	/* We set same protection levels for Src and DST for now */
+	if (rqc->privileged)
+		ccr |= CC_SRCPRI | CC_DSTPRI;
+	if (rqc->nonsecure)
+		ccr |= CC_SRCNS | CC_DSTNS;
+	if (rqc->insnaccess)
+		ccr |= CC_SRCIA | CC_DSTIA;
+
+	ccr |= (((rqc->brst_len - 1) & 0xf) << CC_SRCBRSTLEN_SHFT);
+	ccr |= (((rqc->brst_len - 1) & 0xf) << CC_DSTBRSTLEN_SHFT);
+
+	ccr |= (rqc->brst_size << CC_SRCBRSTSIZE_SHFT);
+	ccr |= (rqc->brst_size << CC_DSTBRSTSIZE_SHFT);
+
+	ccr |= (rqc->scctl << CC_SRCCCTRL_SHFT);
+	ccr |= (rqc->dcctl << CC_DSTCCTRL_SHFT);
+
+	ccr |= (rqc->swap << CC_SWAP_SHFT);
+
+	return ccr;
+}
+
+static inline bool _is_valid(u32 ccr)
+{
+	enum pl330_dstcachectrl dcctl;
+	enum pl330_srccachectrl scctl;
+
+	dcctl = (ccr >> CC_DSTCCTRL_SHFT) & CC_DRCCCTRL_MASK;
+	scctl = (ccr >> CC_SRCCCTRL_SHFT) & CC_SRCCCTRL_MASK;
+
+	if (dcctl == DINVALID1 || dcctl == DINVALID2
+			|| scctl == SINVALID1 || scctl == SINVALID2)
+		return false;
+	else
+		return true;
+}
+
+/*
+ * Submit a list of xfers after which the client wants notification.
+ * Client is not notified after each xfer unit, just once after all
+ * xfer units are done or some error occurs.
+ */
+static int pl330_submit_req(void *ch_id, struct pl330_req *r)
+{
+	struct pl330_thread *thrd = ch_id;
+	struct pl330_dmac *pl330;
+	struct pl330_info *pi;
+	struct _xfer_spec xs;
+	unsigned long flags;
+	void __iomem *regs;
+	unsigned idx;
+	u32 ccr;
+	int ret = 0;
+
+	/* No Req or Unacquired Channel or DMAC */
+	if (!r || !thrd || thrd->free)
+		return -EINVAL;
+
+	pl330 = thrd->dmac;
+	pi = pl330->pinfo;
+	regs = pi->base;
+
+	if (pl330->state == DYING
+		|| pl330->dmac_tbd.reset_chan & (1 << thrd->id)) {
+		dev_info(thrd->dmac->pinfo->dev, "%s:%d\n",
+			__func__, __LINE__);
+		return -EAGAIN;
+	}
+
+	/* If request for non-existing peripheral */
+	if (r->rqtype != MEMTOMEM && r->peri >= pi->pcfg.num_peri) {
+		dev_info(thrd->dmac->pinfo->dev,
+				"%s:%d Invalid peripheral(%u)!\n",
+				__func__, __LINE__, r->peri);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	if (_queue_full(thrd)) {
+		ret = -EAGAIN;
+		goto xfer_exit;
+	}
+
+	/* Prefer Secure Channel */
+	if (!_manager_ns(thrd))
+		r->cfg->nonsecure = 0;
+	else
+		r->cfg->nonsecure = 1;
+
+	/* Use last settings, if not provided */
+	if (r->cfg)
+		ccr = _prepare_ccr(r->cfg);
+	else
+		ccr = readl(regs + CC(thrd->id));
+
+	/* If this req doesn't have valid xfer settings */
+	if (!_is_valid(ccr)) {
+		ret = -EINVAL;
+		dev_info(thrd->dmac->pinfo->dev, "%s:%d Invalid CCR(%x)!\n",
+			__func__, __LINE__, ccr);
+		goto xfer_exit;
+	}
+
+	idx = IS_FREE(&thrd->req[0]) ? 0 : 1;
+
+	xs.ccr = ccr;
+	xs.r = r;
+
+	/* First dry run to check if req is acceptable */
+	ret = _setup_req(1, thrd, idx, &xs);
+	if (ret < 0)
+		goto xfer_exit;
+
+	if (ret > pi->mcbufsz / 2) {
+		dev_info(thrd->dmac->pinfo->dev,
+			"%s:%d Trying increasing mcbufsz\n",
+				__func__, __LINE__);
+		ret = -ENOMEM;
+		goto xfer_exit;
+	}
+
+	/* Hook the request */
+	thrd->lstenq = idx;
+	thrd->req[idx].mc_len = _setup_req(0, thrd, idx, &xs);
+	thrd->req[idx].r = r;
+
+	ret = 0;
+
+xfer_exit:
+	spin_unlock_irqrestore(&pl330->lock, flags);
+
+	return ret;
+}
+
+static void pl330_dotask(unsigned long data)
+{
+	struct pl330_dmac *pl330 = (struct pl330_dmac *) data;
+	struct pl330_info *pi = pl330->pinfo;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	/* The DMAC itself gone nuts */
+	if (pl330->dmac_tbd.reset_dmac) {
+		pl330->state = DYING;
+		/* Reset the manager too */
+		pl330->dmac_tbd.reset_mngr = true;
+		/* Clear the reset flag */
+		pl330->dmac_tbd.reset_dmac = false;
+	}
+
+	if (pl330->dmac_tbd.reset_mngr) {
+		_stop(pl330->manager);
+		/* Reset all channels */
+		pl330->dmac_tbd.reset_chan = (1 << pi->pcfg.num_chan) - 1;
+		/* Clear the reset flag */
+		pl330->dmac_tbd.reset_mngr = false;
+	}
+
+	for (i = 0; i < pi->pcfg.num_chan; i++) {
+
+		if (pl330->dmac_tbd.reset_chan & (1 << i)) {
+			struct pl330_thread *thrd = &pl330->channels[i];
+			void __iomem *regs = pi->base;
+			enum pl330_op_err err;
+
+			_stop(thrd);
+
+			if (readl(regs + FSC) & (1 << thrd->id))
+				err = PL330_ERR_FAIL;
+			else
+				err = PL330_ERR_ABORT;
+
+			spin_unlock_irqrestore(&pl330->lock, flags);
+
+			_callback(thrd->req[1 - thrd->lstenq].r, err);
+			_callback(thrd->req[thrd->lstenq].r, err);
+
+			spin_lock_irqsave(&pl330->lock, flags);
+
+			thrd->req[0].r = NULL;
+			thrd->req[1].r = NULL;
+			mark_free(thrd, 0);
+			mark_free(thrd, 1);
+
+			/* Clear the reset flag */
+			pl330->dmac_tbd.reset_chan &= ~(1 << i);
+		}
+	}
+
+	spin_unlock_irqrestore(&pl330->lock, flags);
+
+	return;
+}
+
+/* Returns 1 if state was updated, 0 otherwise */
+static int pl330_update(const struct pl330_info *pi)
+{
+	struct _pl330_req *rqdone;
+	struct pl330_dmac *pl330;
+	unsigned long flags;
+	void __iomem *regs;
+	u32 val;
+	int id, ev, ret = 0;
+
+	if (!pi || !pi->pl330_data)
+		return 0;
+
+	regs = pi->base;
+	pl330 = pi->pl330_data;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	val = readl(regs + FSM) & 0x1;
+	if (val)
+		pl330->dmac_tbd.reset_mngr = true;
+	else
+		pl330->dmac_tbd.reset_mngr = false;
+
+	val = readl(regs + FSC) & ((1 << pi->pcfg.num_chan) - 1);
+	pl330->dmac_tbd.reset_chan |= val;
+	if (val) {
+		int i = 0;
+		while (i < pi->pcfg.num_chan) {
+			if (val & (1 << i)) {
+				dev_info(pi->dev,
+					"Reset Channel-%d\t CS-%x FTC-%x\n",
+						i, readl(regs + CS(i)),
+						readl(regs + FTC(i)));
+				_stop(&pl330->channels[i]);
+			}
+			i++;
+		}
+	}
+
+	/* Check which event happened i.e, thread notified */
+	val = readl(regs + ES);
+	if (pi->pcfg.num_events < 32
+			&& val & ~((1 << pi->pcfg.num_events) - 1)) {
+		pl330->dmac_tbd.reset_dmac = true;
+		dev_err(pi->dev, "%s:%d Unexpected!\n", __func__, __LINE__);
+		ret = 1;
+		goto updt_exit;
+	}
+
+	for (ev = 0; ev < pi->pcfg.num_events; ev++) {
+		if (val & (1 << ev)) { /* Event occurred */
+			struct pl330_thread *thrd;
+			u32 inten = readl(regs + INTEN);
+			int active;
+
+			/* Clear the event */
+			if (inten & (1 << ev))
+				writel(1 << ev, regs + INTCLR);
+
+			ret = 1;
+
+			id = pl330->events[ev];
+
+			thrd = &pl330->channels[id];
+
+			active = thrd->req_running;
+			if (active == -1) /* Aborted */
+				continue;
+
+			rqdone = &thrd->req[active];
+			mark_free(thrd, active);
+
+			/* Get going again ASAP */
+			_start(thrd);
+
+			/* For now, just make a list of callbacks to be done */
+			list_add_tail(&rqdone->rqd, &pl330->req_done);
+		}
+	}
+
+	/* Now that we are in no hurry, do the callbacks */
+	while (!list_empty(&pl330->req_done)) {
+		struct pl330_req *r;
+
+		rqdone = container_of(pl330->req_done.next,
+					struct _pl330_req, rqd);
+
+		list_del_init(&rqdone->rqd);
+
+		/* Detach the req */
+		r = rqdone->r;
+		rqdone->r = NULL;
+
+		spin_unlock_irqrestore(&pl330->lock, flags);
+		_callback(r, PL330_ERR_NONE);
+		spin_lock_irqsave(&pl330->lock, flags);
+	}
+
+updt_exit:
+	spin_unlock_irqrestore(&pl330->lock, flags);
+
+	if (pl330->dmac_tbd.reset_dmac
+			|| pl330->dmac_tbd.reset_mngr
+			|| pl330->dmac_tbd.reset_chan) {
+		ret = 1;
+		tasklet_schedule(&pl330->tasks);
+	}
+
+	return ret;
+}
+
+static int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
+{
+	struct pl330_thread *thrd = ch_id;
+	struct pl330_dmac *pl330;
+	unsigned long flags;
+	int ret = 0, active;
+
+	if (!thrd || thrd->free || thrd->dmac->state == DYING)
+		return -EINVAL;
+
+	pl330 = thrd->dmac;
+	active = thrd->req_running;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	switch (op) {
+	case PL330_OP_FLUSH:
+		/* Make sure the channel is stopped */
+		_stop(thrd);
+
+		thrd->req[0].r = NULL;
+		thrd->req[1].r = NULL;
+		mark_free(thrd, 0);
+		mark_free(thrd, 1);
+		break;
+
+	case PL330_OP_ABORT:
+		/* Make sure the channel is stopped */
+		_stop(thrd);
+
+		/* ABORT is only for the active req */
+		if (active == -1)
+			break;
+
+		thrd->req[active].r = NULL;
+		mark_free(thrd, active);
+
+		/* Start the next */
+	case PL330_OP_START:
+		if ((active == -1) && !_start(thrd))
+			ret = -EIO;
+		break;
+
+	default:
+		ret = -EINVAL;
+	}
+
+	spin_unlock_irqrestore(&pl330->lock, flags);
+	return ret;
+}
+
+/* Reserve an event */
+static inline int _alloc_event(struct pl330_thread *thrd)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+	struct pl330_info *pi = pl330->pinfo;
+	int ev;
+
+	for (ev = 0; ev < pi->pcfg.num_events; ev++)
+		if (pl330->events[ev] == -1) {
+			pl330->events[ev] = thrd->id;
+			return ev;
+		}
+
+	return -1;
+}
+
+static bool _chan_ns(const struct pl330_info *pi, int i)
+{
+	return pi->pcfg.irq_ns & (1 << i);
+}
+
+/* Upon success, returns IdentityToken for the
+ * allocated channel, NULL otherwise.
+ */
+static void *pl330_request_channel(const struct pl330_info *pi)
+{
+	struct pl330_thread *thrd = NULL;
+	struct pl330_dmac *pl330;
+	unsigned long flags;
+	int chans, i;
+
+	if (!pi || !pi->pl330_data)
+		return NULL;
+
+	pl330 = pi->pl330_data;
+
+	if (pl330->state == DYING)
+		return NULL;
+
+	chans = pi->pcfg.num_chan;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+
+	for (i = 0; i < chans; i++) {
+		thrd = &pl330->channels[i];
+		if ((thrd->free) && (!_manager_ns(thrd) ||
+					_chan_ns(pi, i))) {
+			thrd->ev = _alloc_event(thrd);
+			if (thrd->ev >= 0) {
+				thrd->free = false;
+				thrd->lstenq = 1;
+				thrd->req[0].r = NULL;
+				mark_free(thrd, 0);
+				thrd->req[1].r = NULL;
+				mark_free(thrd, 1);
+				break;
+			}
+		}
+		thrd = NULL;
+	}
+
+	spin_unlock_irqrestore(&pl330->lock, flags);
+
+	return thrd;
+}
+
+/* Release an event */
+static inline void _free_event(struct pl330_thread *thrd, int ev)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+	struct pl330_info *pi = pl330->pinfo;
+
+	/* If the event is valid and was held by the thread */
+	if (ev >= 0 && ev < pi->pcfg.num_events
+			&& pl330->events[ev] == thrd->id)
+		pl330->events[ev] = -1;
+}
+
+static void pl330_release_channel(void *ch_id)
+{
+	struct pl330_thread *thrd = ch_id;
+	struct pl330_dmac *pl330;
+	unsigned long flags;
+
+	if (!thrd || thrd->free)
+		return;
+
+	_stop(thrd);
+
+	_callback(thrd->req[1 - thrd->lstenq].r, PL330_ERR_ABORT);
+	_callback(thrd->req[thrd->lstenq].r, PL330_ERR_ABORT);
+
+	pl330 = thrd->dmac;
+
+	spin_lock_irqsave(&pl330->lock, flags);
+	_free_event(thrd, thrd->ev);
+	thrd->free = true;
+	spin_unlock_irqrestore(&pl330->lock, flags);
+}
+
+/* Initialize the structure for PL330 configuration, that can be used
+ * by the client driver the make best use of the DMAC
+ */
+static void read_dmac_config(struct pl330_info *pi)
+{
+	void __iomem *regs = pi->base;
+	u32 val;
+
+	val = readl(regs + CRD) >> CRD_DATA_WIDTH_SHIFT;
+	val &= CRD_DATA_WIDTH_MASK;
+	pi->pcfg.data_bus_width = 8 * (1 << val);
+
+	val = readl(regs + CRD) >> CRD_DATA_BUFF_SHIFT;
+	val &= CRD_DATA_BUFF_MASK;
+	pi->pcfg.data_buf_dep = val + 1;
+
+	val = readl(regs + CR0) >> CR0_NUM_CHANS_SHIFT;
+	val &= CR0_NUM_CHANS_MASK;
+	val += 1;
+	pi->pcfg.num_chan = val;
+
+	val = readl(regs + CR0);
+	if (val & CR0_PERIPH_REQ_SET) {
+		val = (val >> CR0_NUM_PERIPH_SHIFT) & CR0_NUM_PERIPH_MASK;
+		val += 1;
+		pi->pcfg.num_peri = val;
+		pi->pcfg.peri_ns = readl(regs + CR4);
+	} else {
+		pi->pcfg.num_peri = 0;
+	}
+
+	val = readl(regs + CR0);
+	if (val & CR0_BOOT_MAN_NS)
+		pi->pcfg.mode |= DMAC_MODE_NS;
+	else
+		pi->pcfg.mode &= ~DMAC_MODE_NS;
+
+	val = readl(regs + CR0) >> CR0_NUM_EVENTS_SHIFT;
+	val &= CR0_NUM_EVENTS_MASK;
+	val += 1;
+	pi->pcfg.num_events = val;
+
+	pi->pcfg.irq_ns = readl(regs + CR3);
+
+	pi->pcfg.periph_id = get_id(pi, PERIPH_ID);
+	pi->pcfg.pcell_id = get_id(pi, PCELL_ID);
+}
+
+static inline void _reset_thread(struct pl330_thread *thrd)
+{
+	struct pl330_dmac *pl330 = thrd->dmac;
+	struct pl330_info *pi = pl330->pinfo;
+
+	thrd->req[0].mc_cpu = pl330->mcode_cpu
+				+ (thrd->id * pi->mcbufsz);
+	thrd->req[0].mc_bus = pl330->mcode_bus
+				+ (thrd->id * pi->mcbufsz);
+	thrd->req[0].r = NULL;
+	mark_free(thrd, 0);
+
+	thrd->req[1].mc_cpu = thrd->req[0].mc_cpu
+				+ pi->mcbufsz / 2;
+	thrd->req[1].mc_bus = thrd->req[0].mc_bus
+				+ pi->mcbufsz / 2;
+	thrd->req[1].r = NULL;
+	mark_free(thrd, 1);
+}
+
+static int dmac_alloc_threads(struct pl330_dmac *pl330)
+{
+	struct pl330_info *pi = pl330->pinfo;
+	int chans = pi->pcfg.num_chan;
+	struct pl330_thread *thrd;
+	int i;
+
+	/* Allocate 1 Manager and 'chans' Channel threads */
+	pl330->channels = kzalloc((1 + chans) * sizeof(*thrd),
+					GFP_KERNEL);
+	if (!pl330->channels)
+		return -ENOMEM;
+
+	/* Init Channel threads */
+	for (i = 0; i < chans; i++) {
+		thrd = &pl330->channels[i];
+		thrd->id = i;
+		thrd->dmac = pl330;
+		_reset_thread(thrd);
+		thrd->free = true;
+	}
+
+	/* MANAGER is indexed at the end */
+	thrd = &pl330->channels[chans];
+	thrd->id = chans;
+	thrd->dmac = pl330;
+	thrd->free = false;
+	pl330->manager = thrd;
+
+	return 0;
+}
+
+static int dmac_alloc_resources(struct pl330_dmac *pl330)
+{
+	struct pl330_info *pi = pl330->pinfo;
+	int chans = pi->pcfg.num_chan;
+	int ret;
+
+	/*
+	 * Alloc MicroCode buffer for 'chans' Channel threads.
+	 * A channel's buffer offset is (Channel_Id * MCODE_BUFF_PERCHAN)
+	 */
+	pl330->mcode_cpu = dma_alloc_coherent(pi->dev,
+				chans * pi->mcbufsz,
+				&pl330->mcode_bus, GFP_KERNEL);
+	if (!pl330->mcode_cpu) {
+		dev_err(pi->dev, "%s:%d Can't allocate memory!\n",
+			__func__, __LINE__);
+		return -ENOMEM;
+	}
+
+	ret = dmac_alloc_threads(pl330);
+	if (ret) {
+		dev_err(pi->dev, "%s:%d Can't to create channels for DMAC!\n",
+			__func__, __LINE__);
+		dma_free_coherent(pi->dev,
+				chans * pi->mcbufsz,
+				pl330->mcode_cpu, pl330->mcode_bus);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int pl330_add(struct pl330_info *pi)
+{
+	struct pl330_dmac *pl330;
+	void __iomem *regs;
+	int i, ret;
+
+	if (!pi || !pi->dev)
+		return -EINVAL;
+
+	/* If already added */
+	if (pi->pl330_data)
+		return -EINVAL;
+
+	/*
+	 * If the SoC can perform reset on the DMAC, then do it
+	 * before reading its configuration.
+	 */
+	if (pi->dmac_reset)
+		pi->dmac_reset(pi);
+
+	regs = pi->base;
+
+	/* Check if we can handle this DMAC */
+	if ((get_id(pi, PERIPH_ID) & 0xfffff) != PERIPH_ID_VAL
+	   || get_id(pi, PCELL_ID) != PCELL_ID_VAL) {
+		dev_err(pi->dev, "PERIPH_ID 0x%x, PCELL_ID 0x%x !\n",
+			get_id(pi, PERIPH_ID), get_id(pi, PCELL_ID));
+		return -EINVAL;
+	}
+
+	/* Read the configuration of the DMAC */
+	read_dmac_config(pi);
+
+	if (pi->pcfg.num_events == 0) {
+		dev_err(pi->dev, "%s:%d Can't work without events!\n",
+			__func__, __LINE__);
+		return -EINVAL;
+	}
+
+	pl330 = kzalloc(sizeof(*pl330), GFP_KERNEL);
+	if (!pl330) {
+		dev_err(pi->dev, "%s:%d Can't allocate memory!\n",
+			__func__, __LINE__);
+		return -ENOMEM;
+	}
+
+	/* Assign the info structure and private data */
+	pl330->pinfo = pi;
+	pi->pl330_data = pl330;
+
+	spin_lock_init(&pl330->lock);
+
+	INIT_LIST_HEAD(&pl330->req_done);
+
+	/* Use default MC buffer size if not provided */
+	if (!pi->mcbufsz)
+		pi->mcbufsz = MCODE_BUFF_PER_REQ * 2;
+
+	/* Mark all events as free */
+	for (i = 0; i < pi->pcfg.num_events; i++)
+		pl330->events[i] = -1;
+
+	/* Allocate resources needed by the DMAC */
+	ret = dmac_alloc_resources(pl330);
+	if (ret) {
+		dev_err(pi->dev, "Unable to create channels for DMAC\n");
+		kfree(pl330);
+		return ret;
+	}
+
+	tasklet_init(&pl330->tasks, pl330_dotask, (unsigned long) pl330);
+
+	pl330->state = INIT;
+
+	return 0;
+}
+
+static int dmac_free_threads(struct pl330_dmac *pl330)
+{
+	struct pl330_info *pi = pl330->pinfo;
+	int chans = pi->pcfg.num_chan;
+	struct pl330_thread *thrd;
+	int i;
+
+	/* Release Channel threads */
+	for (i = 0; i < chans; i++) {
+		thrd = &pl330->channels[i];
+		pl330_release_channel((void *)thrd);
+	}
+
+	/* Free memory */
+	kfree(pl330->channels);
+
+	return 0;
+}
+
+static void dmac_free_resources(struct pl330_dmac *pl330)
+{
+	struct pl330_info *pi = pl330->pinfo;
+	int chans = pi->pcfg.num_chan;
+
+	dmac_free_threads(pl330);
+
+	dma_free_coherent(pi->dev, chans * pi->mcbufsz,
+				pl330->mcode_cpu, pl330->mcode_bus);
+}
+
+static void pl330_del(struct pl330_info *pi)
+{
+	struct pl330_dmac *pl330;
+
+	if (!pi || !pi->pl330_data)
+		return;
+
+	pl330 = pi->pl330_data;
+
+	pl330->state = UNINIT;
+
+	tasklet_kill(&pl330->tasks);
+
+	/* Free DMAC resources */
+	dmac_free_resources(pl330);
+
+	kfree(pl330);
+	pi->pl330_data = NULL;
+}
+
 /* forward declaration */
 static struct amba_driver pl330_driver;
 
@@ -234,7 +2320,7 @@ static void pl330_tasklet(unsigned long data)
 	/* Pick up ripe tomatoes */
 	list_for_each_entry_safe(desc, _dt, &pch->work_list, node)
 		if (desc->status == DONE) {
-			pch->completed = desc->txd.cookie;
+			dma_cookie_complete(&desc->txd);
 			list_move_tail(&desc->node, &list);
 		}
 
@@ -305,7 +2391,7 @@ static int pl330_alloc_chan_resources(struct dma_chan *chan)
 
 	spin_lock_irqsave(&pch->lock, flags);
 
-	pch->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 	pch->cyclic = false;
 
 	pch->pl330_chid = pl330_request_channel(&pdmac->pif);
@@ -340,7 +2426,6 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned
 		/* Mark all desc done */
 		list_for_each_entry_safe(desc, _dt, &pch->work_list , node) {
 			desc->status = DONE;
-			pch->completed = desc->txd.cookie;
 			list_move_tail(&desc->node, &list);
 		}
 
@@ -396,18 +2481,7 @@ static enum dma_status
 pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		 struct dma_tx_state *txstate)
 {
-	struct dma_pl330_chan *pch = to_pchan(chan);
-	dma_cookie_t last_done, last_used;
-	int ret;
-
-	last_done = pch->completed;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_done, last_used);
-
-	dma_set_tx_state(txstate, last_done, last_used, 0);
-
-	return ret;
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static void pl330_issue_pending(struct dma_chan *chan)
@@ -430,26 +2504,16 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&pch->lock, flags);
 
 	/* Assign cookies to all nodes */
-	cookie = tx->chan->cookie;
-
 	while (!list_empty(&last->node)) {
 		desc = list_entry(last->node.next, struct dma_pl330_desc, node);
 
-		if (++cookie < 0)
-			cookie = 1;
-		desc->txd.cookie = cookie;
+		dma_cookie_assign(&desc->txd);
 
 		list_move_tail(&desc->node, &pch->work_list);
 	}
 
-	if (++cookie < 0)
-		cookie = 1;
-	last->txd.cookie = cookie;
-
+	cookie = dma_cookie_assign(&last->txd);
 	list_add_tail(&last->node, &pch->work_list);
-
-	tx->chan->cookie = cookie;
-
 	spin_unlock_irqrestore(&pch->lock, flags);
 
 	return cookie;
@@ -553,6 +2617,7 @@ static struct dma_pl330_desc *pl330_get_desc(struct dma_pl330_chan *pch)
 	async_tx_ack(&desc->txd);
 
 	desc->req.peri = peri_id ? pch->chan.chan_id : 0;
+	desc->rqcfg.pcfg = &pch->dmac->pif.pcfg;
 
 	dma_async_tx_descriptor_init(&desc->txd, &pch->chan);
 
@@ -621,7 +2686,8 @@ static inline int get_burst_len(struct dma_pl330_desc *desc, size_t len)
 
 static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t len,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context)
 {
 	struct dma_pl330_desc *desc;
 	struct dma_pl330_chan *pch = to_pchan(chan);
@@ -711,7 +2777,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 static struct dma_async_tx_descriptor *
 pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flg)
+		unsigned long flg, void *context)
 {
 	struct dma_pl330_desc *first, *desc = NULL;
 	struct dma_pl330_chan *pch = to_pchan(chan);
@@ -829,7 +2895,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	if (IS_ERR(pdmac->clk)) {
 		dev_err(&adev->dev, "Cannot get operation clock.\n");
 		ret = -EINVAL;
-		goto probe_err1;
+		goto probe_err2;
 	}
 
 	amba_set_drvdata(adev, pdmac);
@@ -843,11 +2909,11 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	ret = request_irq(irq, pl330_irq_handler, 0,
 			dev_name(&adev->dev), pi);
 	if (ret)
-		goto probe_err2;
+		goto probe_err3;
 
 	ret = pl330_add(pi);
 	if (ret)
-		goto probe_err3;
+		goto probe_err4;
 
 	INIT_LIST_HEAD(&pdmac->desc_pool);
 	spin_lock_init(&pdmac->pool_lock);
@@ -904,7 +2970,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	ret = dma_async_device_register(pd);
 	if (ret) {
 		dev_err(&adev->dev, "unable to register DMAC\n");
-		goto probe_err4;
+		goto probe_err5;
 	}
 
 	dev_info(&adev->dev,
@@ -917,10 +2983,15 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 
 	return 0;
 
-probe_err4:
+probe_err5:
 	pl330_del(pi);
-probe_err3:
+probe_err4:
 	free_irq(irq, pi);
+probe_err3:
+#ifndef CONFIG_PM_RUNTIME
+	clk_disable(pdmac->clk);
+#endif
+	clk_put(pdmac->clk);
 probe_err2:
 	iounmap(pi->base);
 probe_err1:
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index fc457a7e8832..ced98826684a 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -46,6 +46,7 @@
 #include <asm/dcr.h>
 #include <asm/dcr-regs.h>
 #include "adma.h"
+#include "../dmaengine.h"
 
 enum ppc_adma_init_code {
 	PPC_ADMA_INIT_OK = 0,
@@ -1930,7 +1931,7 @@ static void __ppc440spe_adma_slot_cleanup(struct ppc440spe_adma_chan *chan)
 				if (end_of_chain && slot_cnt) {
 					/* Should wait for ZeroSum completion */
 					if (cookie > 0)
-						chan->completed_cookie = cookie;
+						chan->common.completed_cookie = cookie;
 					return;
 				}
 
@@ -1960,7 +1961,7 @@ static void __ppc440spe_adma_slot_cleanup(struct ppc440spe_adma_chan *chan)
 	BUG_ON(!seen_current);
 
 	if (cookie > 0) {
-		chan->completed_cookie = cookie;
+		chan->common.completed_cookie = cookie;
 		pr_debug("\tcompleted cookie %d\n", cookie);
 	}
 
@@ -2150,22 +2151,6 @@ static int ppc440spe_adma_alloc_chan_resources(struct dma_chan *chan)
 }
 
 /**
- * ppc440spe_desc_assign_cookie - assign a cookie
- */
-static dma_cookie_t ppc440spe_desc_assign_cookie(
-		struct ppc440spe_adma_chan *chan,
-		struct ppc440spe_adma_desc_slot *desc)
-{
-	dma_cookie_t cookie = chan->common.cookie;
-
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	chan->common.cookie = desc->async_tx.cookie = cookie;
-	return cookie;
-}
-
-/**
  * ppc440spe_rxor_set_region_data -
  */
 static void ppc440spe_rxor_set_region(struct ppc440spe_adma_desc_slot *desc,
@@ -2235,8 +2220,7 @@ static dma_cookie_t ppc440spe_adma_tx_submit(struct dma_async_tx_descriptor *tx)
 	slots_per_op = group_start->slots_per_op;
 
 	spin_lock_bh(&chan->lock);
-
-	cookie = ppc440spe_desc_assign_cookie(chan, sw_desc);
+	cookie = dma_cookie_assign(tx);
 
 	if (unlikely(list_empty(&chan->chain))) {
 		/* first peer */
@@ -3944,28 +3928,16 @@ static enum dma_status ppc440spe_adma_tx_status(struct dma_chan *chan,
 			dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct ppc440spe_adma_chan *ppc440spe_chan;
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 	enum dma_status ret;
 
 	ppc440spe_chan = to_ppc440spe_adma_chan(chan);
-	last_used = chan->cookie;
-	last_complete = ppc440spe_chan->completed_cookie;
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_SUCCESS)
 		return ret;
 
 	ppc440spe_adma_slot_cleanup(ppc440spe_chan);
 
-	last_used = chan->cookie;
-	last_complete = ppc440spe_chan->completed_cookie;
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 /**
@@ -4050,16 +4022,12 @@ static void ppc440spe_chan_start_null_xor(struct ppc440spe_adma_chan *chan)
 		async_tx_ack(&sw_desc->async_tx);
 		ppc440spe_desc_init_null_xor(group_start);
 
-		cookie = chan->common.cookie;
-		cookie++;
-		if (cookie <= 1)
-			cookie = 2;
+		cookie = dma_cookie_assign(&sw_desc->async_tx);
 
 		/* initialize the completed cookie to be less than
 		 * the most recently used cookie
 		 */
-		chan->completed_cookie = cookie - 1;
-		chan->common.cookie = sw_desc->async_tx.cookie = cookie;
+		chan->common.completed_cookie = cookie - 1;
 
 		/* channel should not be busy */
 		BUG_ON(ppc440spe_chan_is_busy(chan));
@@ -4529,6 +4497,7 @@ static int __devinit ppc440spe_adma_probe(struct platform_device *ofdev)
 	INIT_LIST_HEAD(&chan->all_slots);
 	chan->device = adev;
 	chan->common.device = &adev->common;
+	dma_cookie_init(&chan->common);
 	list_add_tail(&chan->common.device_node, &adev->common.channels);
 	tasklet_init(&chan->irq_tasklet, ppc440spe_adma_tasklet,
 		     (unsigned long)chan);
diff --git a/drivers/dma/ppc4xx/adma.h b/drivers/dma/ppc4xx/adma.h
index 8ada5a812e3b..26b7a5ed9ac7 100644
--- a/drivers/dma/ppc4xx/adma.h
+++ b/drivers/dma/ppc4xx/adma.h
@@ -81,7 +81,6 @@ struct ppc440spe_adma_device {
  * @common: common dmaengine channel object members
  * @all_slots: complete domain of slots usable by the channel
  * @pending: allows batching of hardware operations
- * @completed_cookie: identifier for the most recently completed operation
  * @slots_allocated: records the actual size of the descriptor slot pool
  * @hw_chain_inited: h/w descriptor chain initialization flag
  * @irq_tasklet: bottom half where ppc440spe_adma_slot_cleanup runs
@@ -99,7 +98,6 @@ struct ppc440spe_adma_chan {
 	struct list_head all_slots;
 	struct ppc440spe_adma_desc_slot *last_used;
 	int pending;
-	dma_cookie_t completed_cookie;
 	int slots_allocated;
 	int hw_chain_inited;
 	struct tasklet_struct irq_tasklet;
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
new file mode 100644
index 000000000000..ec78ccef9132
--- /dev/null
+++ b/drivers/dma/sa11x0-dma.c
@@ -0,0 +1,1109 @@
+/*
+ * SA11x0 DMAengine support
+ *
+ * Copyright (C) 2012 Russell King
+ *   Derived in part from arch/arm/mach-sa1100/dma.c,
+ *   Copyright (C) 2000, 2001 by Nicolas Pitre
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/sched.h>
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/sa11x0-dma.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#define NR_PHY_CHAN	6
+#define DMA_ALIGN	3
+#define DMA_MAX_SIZE	0x1fff
+#define DMA_CHUNK_SIZE	0x1000
+
+#define DMA_DDAR	0x00
+#define DMA_DCSR_S	0x04
+#define DMA_DCSR_C	0x08
+#define DMA_DCSR_R	0x0c
+#define DMA_DBSA	0x10
+#define DMA_DBTA	0x14
+#define DMA_DBSB	0x18
+#define DMA_DBTB	0x1c
+#define DMA_SIZE	0x20
+
+#define DCSR_RUN	(1 << 0)
+#define DCSR_IE		(1 << 1)
+#define DCSR_ERROR	(1 << 2)
+#define DCSR_DONEA	(1 << 3)
+#define DCSR_STRTA	(1 << 4)
+#define DCSR_DONEB	(1 << 5)
+#define DCSR_STRTB	(1 << 6)
+#define DCSR_BIU	(1 << 7)
+
+#define DDAR_RW		(1 << 0)	/* 0 = W, 1 = R */
+#define DDAR_E		(1 << 1)	/* 0 = LE, 1 = BE */
+#define DDAR_BS		(1 << 2)	/* 0 = BS4, 1 = BS8 */
+#define DDAR_DW		(1 << 3)	/* 0 = 8b, 1 = 16b */
+#define DDAR_Ser0UDCTr	(0x0 << 4)
+#define DDAR_Ser0UDCRc	(0x1 << 4)
+#define DDAR_Ser1SDLCTr	(0x2 << 4)
+#define DDAR_Ser1SDLCRc	(0x3 << 4)
+#define DDAR_Ser1UARTTr	(0x4 << 4)
+#define DDAR_Ser1UARTRc	(0x5 << 4)
+#define DDAR_Ser2ICPTr	(0x6 << 4)
+#define DDAR_Ser2ICPRc	(0x7 << 4)
+#define DDAR_Ser3UARTTr	(0x8 << 4)
+#define DDAR_Ser3UARTRc	(0x9 << 4)
+#define DDAR_Ser4MCP0Tr	(0xa << 4)
+#define DDAR_Ser4MCP0Rc	(0xb << 4)
+#define DDAR_Ser4MCP1Tr	(0xc << 4)
+#define DDAR_Ser4MCP1Rc	(0xd << 4)
+#define DDAR_Ser4SSPTr	(0xe << 4)
+#define DDAR_Ser4SSPRc	(0xf << 4)
+
+struct sa11x0_dma_sg {
+	u32			addr;
+	u32			len;
+};
+
+struct sa11x0_dma_desc {
+	struct dma_async_tx_descriptor tx;
+	u32			ddar;
+	size_t			size;
+
+	/* maybe protected by c->lock */
+	struct list_head	node;
+	unsigned		sglen;
+	struct sa11x0_dma_sg	sg[0];
+};
+
+struct sa11x0_dma_phy;
+
+struct sa11x0_dma_chan {
+	struct dma_chan		chan;
+	spinlock_t		lock;
+	dma_cookie_t		lc;
+
+	/* protected by c->lock */
+	struct sa11x0_dma_phy	*phy;
+	enum dma_status		status;
+	struct list_head	desc_submitted;
+	struct list_head	desc_issued;
+
+	/* protected by d->lock */
+	struct list_head	node;
+
+	u32			ddar;
+	const char		*name;
+};
+
+struct sa11x0_dma_phy {
+	void __iomem		*base;
+	struct sa11x0_dma_dev	*dev;
+	unsigned		num;
+
+	struct sa11x0_dma_chan	*vchan;
+
+	/* Protected by c->lock */
+	unsigned		sg_load;
+	struct sa11x0_dma_desc	*txd_load;
+	unsigned		sg_done;
+	struct sa11x0_dma_desc	*txd_done;
+#ifdef CONFIG_PM_SLEEP
+	u32			dbs[2];
+	u32			dbt[2];
+	u32			dcsr;
+#endif
+};
+
+struct sa11x0_dma_dev {
+	struct dma_device	slave;
+	void __iomem		*base;
+	spinlock_t		lock;
+	struct tasklet_struct	task;
+	struct list_head	chan_pending;
+	struct list_head	desc_complete;
+	struct sa11x0_dma_phy	phy[NR_PHY_CHAN];
+};
+
+static struct sa11x0_dma_chan *to_sa11x0_dma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct sa11x0_dma_chan, chan);
+}
+
+static struct sa11x0_dma_dev *to_sa11x0_dma(struct dma_device *dmadev)
+{
+	return container_of(dmadev, struct sa11x0_dma_dev, slave);
+}
+
+static struct sa11x0_dma_desc *to_sa11x0_dma_tx(struct dma_async_tx_descriptor *tx)
+{
+	return container_of(tx, struct sa11x0_dma_desc, tx);
+}
+
+static struct sa11x0_dma_desc *sa11x0_dma_next_desc(struct sa11x0_dma_chan *c)
+{
+	if (list_empty(&c->desc_issued))
+		return NULL;
+
+	return list_first_entry(&c->desc_issued, struct sa11x0_dma_desc, node);
+}
+
+static void sa11x0_dma_start_desc(struct sa11x0_dma_phy *p, struct sa11x0_dma_desc *txd)
+{
+	list_del(&txd->node);
+	p->txd_load = txd;
+	p->sg_load = 0;
+
+	dev_vdbg(p->dev->slave.dev, "pchan %u: txd %p[%x]: starting: DDAR:%x\n",
+		p->num, txd, txd->tx.cookie, txd->ddar);
+}
+
+static void noinline sa11x0_dma_start_sg(struct sa11x0_dma_phy *p,
+	struct sa11x0_dma_chan *c)
+{
+	struct sa11x0_dma_desc *txd = p->txd_load;
+	struct sa11x0_dma_sg *sg;
+	void __iomem *base = p->base;
+	unsigned dbsx, dbtx;
+	u32 dcsr;
+
+	if (!txd)
+		return;
+
+	dcsr = readl_relaxed(base + DMA_DCSR_R);
+
+	/* Don't try to load the next transfer if both buffers are started */
+	if ((dcsr & (DCSR_STRTA | DCSR_STRTB)) == (DCSR_STRTA | DCSR_STRTB))
+		return;
+
+	if (p->sg_load == txd->sglen) {
+		struct sa11x0_dma_desc *txn = sa11x0_dma_next_desc(c);
+
+		/*
+		 * We have reached the end of the current descriptor.
+		 * Peek at the next descriptor, and if compatible with
+		 * the current, start processing it.
+		 */
+		if (txn && txn->ddar == txd->ddar) {
+			txd = txn;
+			sa11x0_dma_start_desc(p, txn);
+		} else {
+			p->txd_load = NULL;
+			return;
+		}
+	}
+
+	sg = &txd->sg[p->sg_load++];
+
+	/* Select buffer to load according to channel status */
+	if (((dcsr & (DCSR_BIU | DCSR_STRTB)) == (DCSR_BIU | DCSR_STRTB)) ||
+	    ((dcsr & (DCSR_BIU | DCSR_STRTA)) == 0)) {
+		dbsx = DMA_DBSA;
+		dbtx = DMA_DBTA;
+		dcsr = DCSR_STRTA | DCSR_IE | DCSR_RUN;
+	} else {
+		dbsx = DMA_DBSB;
+		dbtx = DMA_DBTB;
+		dcsr = DCSR_STRTB | DCSR_IE | DCSR_RUN;
+	}
+
+	writel_relaxed(sg->addr, base + dbsx);
+	writel_relaxed(sg->len, base + dbtx);
+	writel(dcsr, base + DMA_DCSR_S);
+
+	dev_dbg(p->dev->slave.dev, "pchan %u: load: DCSR:%02x DBS%c:%08x DBT%c:%08x\n",
+		p->num, dcsr,
+		'A' + (dbsx == DMA_DBSB), sg->addr,
+		'A' + (dbtx == DMA_DBTB), sg->len);
+}
+
+static void noinline sa11x0_dma_complete(struct sa11x0_dma_phy *p,
+	struct sa11x0_dma_chan *c)
+{
+	struct sa11x0_dma_desc *txd = p->txd_done;
+
+	if (++p->sg_done == txd->sglen) {
+		struct sa11x0_dma_dev *d = p->dev;
+
+		dev_vdbg(d->slave.dev, "pchan %u: txd %p[%x]: completed\n",
+			p->num, p->txd_done, p->txd_done->tx.cookie);
+
+		c->lc = txd->tx.cookie;
+
+		spin_lock(&d->lock);
+		list_add_tail(&txd->node, &d->desc_complete);
+		spin_unlock(&d->lock);
+
+		p->sg_done = 0;
+		p->txd_done = p->txd_load;
+
+		tasklet_schedule(&d->task);
+	}
+
+	sa11x0_dma_start_sg(p, c);
+}
+
+static irqreturn_t sa11x0_dma_irq(int irq, void *dev_id)
+{
+	struct sa11x0_dma_phy *p = dev_id;
+	struct sa11x0_dma_dev *d = p->dev;
+	struct sa11x0_dma_chan *c;
+	u32 dcsr;
+
+	dcsr = readl_relaxed(p->base + DMA_DCSR_R);
+	if (!(dcsr & (DCSR_ERROR | DCSR_DONEA | DCSR_DONEB)))
+		return IRQ_NONE;
+
+	/* Clear reported status bits */
+	writel_relaxed(dcsr & (DCSR_ERROR | DCSR_DONEA | DCSR_DONEB),
+		p->base + DMA_DCSR_C);
+
+	dev_dbg(d->slave.dev, "pchan %u: irq: DCSR:%02x\n", p->num, dcsr);
+
+	if (dcsr & DCSR_ERROR) {
+		dev_err(d->slave.dev, "pchan %u: error. DCSR:%02x DDAR:%08x DBSA:%08x DBTA:%08x DBSB:%08x DBTB:%08x\n",
+			p->num, dcsr,
+			readl_relaxed(p->base + DMA_DDAR),
+			readl_relaxed(p->base + DMA_DBSA),
+			readl_relaxed(p->base + DMA_DBTA),
+			readl_relaxed(p->base + DMA_DBSB),
+			readl_relaxed(p->base + DMA_DBTB));
+	}
+
+	c = p->vchan;
+	if (c) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&c->lock, flags);
+		/*
+		 * Now that we're holding the lock, check that the vchan
+		 * really is associated with this pchan before touching the
+		 * hardware.  This should always succeed, because we won't
+		 * change p->vchan or c->phy while the channel is actively
+		 * transferring.
+		 */
+		if (c->phy == p) {
+			if (dcsr & DCSR_DONEA)
+				sa11x0_dma_complete(p, c);
+			if (dcsr & DCSR_DONEB)
+				sa11x0_dma_complete(p, c);
+		}
+		spin_unlock_irqrestore(&c->lock, flags);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void sa11x0_dma_start_txd(struct sa11x0_dma_chan *c)
+{
+	struct sa11x0_dma_desc *txd = sa11x0_dma_next_desc(c);
+
+	/* If the issued list is empty, we have no further txds to process */
+	if (txd) {
+		struct sa11x0_dma_phy *p = c->phy;
+
+		sa11x0_dma_start_desc(p, txd);
+		p->txd_done = txd;
+		p->sg_done = 0;
+
+		/* The channel should not have any transfers started */
+		WARN_ON(readl_relaxed(p->base + DMA_DCSR_R) &
+				      (DCSR_STRTA | DCSR_STRTB));
+
+		/* Clear the run and start bits before changing DDAR */
+		writel_relaxed(DCSR_RUN | DCSR_STRTA | DCSR_STRTB,
+			       p->base + DMA_DCSR_C);
+		writel_relaxed(txd->ddar, p->base + DMA_DDAR);
+
+		/* Try to start both buffers */
+		sa11x0_dma_start_sg(p, c);
+		sa11x0_dma_start_sg(p, c);
+	}
+}
+
+static void sa11x0_dma_tasklet(unsigned long arg)
+{
+	struct sa11x0_dma_dev *d = (struct sa11x0_dma_dev *)arg;
+	struct sa11x0_dma_phy *p;
+	struct sa11x0_dma_chan *c;
+	struct sa11x0_dma_desc *txd, *txn;
+	LIST_HEAD(head);
+	unsigned pch, pch_alloc = 0;
+
+	dev_dbg(d->slave.dev, "tasklet enter\n");
+
+	/* Get the completed tx descriptors */
+	spin_lock_irq(&d->lock);
+	list_splice_init(&d->desc_complete, &head);
+	spin_unlock_irq(&d->lock);
+
+	list_for_each_entry(txd, &head, node) {
+		c = to_sa11x0_dma_chan(txd->tx.chan);
+
+		dev_dbg(d->slave.dev, "vchan %p: txd %p[%x] completed\n",
+			c, txd, txd->tx.cookie);
+
+		spin_lock_irq(&c->lock);
+		p = c->phy;
+		if (p) {
+			if (!p->txd_done)
+				sa11x0_dma_start_txd(c);
+			if (!p->txd_done) {
+				/* No current txd associated with this channel */
+				dev_dbg(d->slave.dev, "pchan %u: free\n", p->num);
+
+				/* Mark this channel free */
+				c->phy = NULL;
+				p->vchan = NULL;
+			}
+		}
+		spin_unlock_irq(&c->lock);
+	}
+
+	spin_lock_irq(&d->lock);
+	for (pch = 0; pch < NR_PHY_CHAN; pch++) {
+		p = &d->phy[pch];
+
+		if (p->vchan == NULL && !list_empty(&d->chan_pending)) {
+			c = list_first_entry(&d->chan_pending,
+				struct sa11x0_dma_chan, node);
+			list_del_init(&c->node);
+
+			pch_alloc |= 1 << pch;
+
+			/* Mark this channel allocated */
+			p->vchan = c;
+
+			dev_dbg(d->slave.dev, "pchan %u: alloc vchan %p\n", pch, c);
+		}
+	}
+	spin_unlock_irq(&d->lock);
+
+	for (pch = 0; pch < NR_PHY_CHAN; pch++) {
+		if (pch_alloc & (1 << pch)) {
+			p = &d->phy[pch];
+			c = p->vchan;
+
+			spin_lock_irq(&c->lock);
+			c->phy = p;
+
+			sa11x0_dma_start_txd(c);
+			spin_unlock_irq(&c->lock);
+		}
+	}
+
+	/* Now free the completed tx descriptor, and call their callbacks */
+	list_for_each_entry_safe(txd, txn, &head, node) {
+		dma_async_tx_callback callback = txd->tx.callback;
+		void *callback_param = txd->tx.callback_param;
+
+		dev_dbg(d->slave.dev, "txd %p[%x]: callback and free\n",
+			txd, txd->tx.cookie);
+
+		kfree(txd);
+
+		if (callback)
+			callback(callback_param);
+	}
+
+	dev_dbg(d->slave.dev, "tasklet exit\n");
+}
+
+
+static void sa11x0_dma_desc_free(struct sa11x0_dma_dev *d, struct list_head *head)
+{
+	struct sa11x0_dma_desc *txd, *txn;
+
+	list_for_each_entry_safe(txd, txn, head, node) {
+		dev_dbg(d->slave.dev, "txd %p: freeing\n", txd);
+		kfree(txd);
+	}
+}
+
+static int sa11x0_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	return 0;
+}
+
+static void sa11x0_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
+	struct sa11x0_dma_dev *d = to_sa11x0_dma(chan->device);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&c->lock, flags);
+	spin_lock(&d->lock);
+	list_del_init(&c->node);
+	spin_unlock(&d->lock);
+
+	list_splice_tail_init(&c->desc_submitted, &head);
+	list_splice_tail_init(&c->desc_issued, &head);
+	spin_unlock_irqrestore(&c->lock, flags);
+
+	sa11x0_dma_desc_free(d, &head);
+}
+
+static dma_addr_t sa11x0_dma_pos(struct sa11x0_dma_phy *p)
+{
+	unsigned reg;
+	u32 dcsr;
+
+	dcsr = readl_relaxed(p->base + DMA_DCSR_R);
+
+	if ((dcsr & (DCSR_BIU | DCSR_STRTA)) == DCSR_STRTA ||
+	    (dcsr & (DCSR_BIU | DCSR_STRTB)) == DCSR_BIU)
+		reg = DMA_DBSA;
+	else
+		reg = DMA_DBSB;
+
+	return readl_relaxed(p->base + reg);
+}
+
+static enum dma_status sa11x0_dma_tx_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *state)
+{
+	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
+	struct sa11x0_dma_dev *d = to_sa11x0_dma(chan->device);
+	struct sa11x0_dma_phy *p;
+	struct sa11x0_dma_desc *txd;
+	dma_cookie_t last_used, last_complete;
+	unsigned long flags;
+	enum dma_status ret;
+	size_t bytes = 0;
+
+	last_used = c->chan.cookie;
+	last_complete = c->lc;
+
+	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	if (ret == DMA_SUCCESS) {
+		dma_set_tx_state(state, last_complete, last_used, 0);
+		return ret;
+	}
+
+	spin_lock_irqsave(&c->lock, flags);
+	p = c->phy;
+	ret = c->status;
+	if (p) {
+		dma_addr_t addr = sa11x0_dma_pos(p);
+
+		dev_vdbg(d->slave.dev, "tx_status: addr:%x\n", addr);
+
+		txd = p->txd_done;
+		if (txd) {
+			unsigned i;
+
+			for (i = 0; i < txd->sglen; i++) {
+				dev_vdbg(d->slave.dev, "tx_status: [%u] %x+%x\n",
+					i, txd->sg[i].addr, txd->sg[i].len);
+				if (addr >= txd->sg[i].addr &&
+				    addr < txd->sg[i].addr + txd->sg[i].len) {
+					unsigned len;
+
+					len = txd->sg[i].len -
+						(addr - txd->sg[i].addr);
+					dev_vdbg(d->slave.dev, "tx_status: [%u] +%x\n",
+						i, len);
+					bytes += len;
+					i++;
+					break;
+				}
+			}
+			for (; i < txd->sglen; i++) {
+				dev_vdbg(d->slave.dev, "tx_status: [%u] %x+%x ++\n",
+					i, txd->sg[i].addr, txd->sg[i].len);
+				bytes += txd->sg[i].len;
+			}
+		}
+		if (txd != p->txd_load && p->txd_load)
+			bytes += p->txd_load->size;
+	}
+	list_for_each_entry(txd, &c->desc_issued, node) {
+		bytes += txd->size;
+	}
+	spin_unlock_irqrestore(&c->lock, flags);
+
+	dma_set_tx_state(state, last_complete, last_used, bytes);
+
+	dev_vdbg(d->slave.dev, "tx_status: bytes 0x%zx\n", bytes);
+
+	return ret;
+}
+
+/*
+ * Move pending txds to the issued list, and re-init pending list.
+ * If not already pending, add this channel to the list of pending
+ * channels and trigger the tasklet to run.
+ */
+static void sa11x0_dma_issue_pending(struct dma_chan *chan)
+{
+	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
+	struct sa11x0_dma_dev *d = to_sa11x0_dma(chan->device);
+	unsigned long flags;
+
+	spin_lock_irqsave(&c->lock, flags);
+	list_splice_tail_init(&c->desc_submitted, &c->desc_issued);
+	if (!list_empty(&c->desc_issued)) {
+		spin_lock(&d->lock);
+		if (!c->phy && list_empty(&c->node)) {
+			list_add_tail(&c->node, &d->chan_pending);
+			tasklet_schedule(&d->task);
+			dev_dbg(d->slave.dev, "vchan %p: issued\n", c);
+		}
+		spin_unlock(&d->lock);
+	} else
+		dev_dbg(d->slave.dev, "vchan %p: nothing to issue\n", c);
+	spin_unlock_irqrestore(&c->lock, flags);
+}
+
+static dma_cookie_t sa11x0_dma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(tx->chan);
+	struct sa11x0_dma_desc *txd = to_sa11x0_dma_tx(tx);
+	unsigned long flags;
+
+	spin_lock_irqsave(&c->lock, flags);
+	c->chan.cookie += 1;
+	if (c->chan.cookie < 0)
+		c->chan.cookie = 1;
+	txd->tx.cookie = c->chan.cookie;
+
+	list_add_tail(&txd->node, &c->desc_submitted);
+	spin_unlock_irqrestore(&c->lock, flags);
+
+	dev_dbg(tx->chan->device->dev, "vchan %p: txd %p[%x]: submitted\n",
+		c, txd, txd->tx.cookie);
+
+	return txd->tx.cookie;
+}
+
+static struct dma_async_tx_descriptor *sa11x0_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sg, unsigned int sglen,
+	enum dma_transfer_direction dir, unsigned long flags, void *context)
+{
+	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
+	struct sa11x0_dma_desc *txd;
+	struct scatterlist *sgent;
+	unsigned i, j = sglen;
+	size_t size = 0;
+
+	/* SA11x0 channels can only operate in their native direction */
+	if (dir != (c->ddar & DDAR_RW ? DMA_DEV_TO_MEM : DMA_MEM_TO_DEV)) {
+		dev_err(chan->device->dev, "vchan %p: bad DMA direction: DDAR:%08x dir:%u\n",
+			c, c->ddar, dir);
+		return NULL;
+	}
+
+	/* Do not allow zero-sized txds */
+	if (sglen == 0)
+		return NULL;
+
+	for_each_sg(sg, sgent, sglen, i) {
+		dma_addr_t addr = sg_dma_address(sgent);
+		unsigned int len = sg_dma_len(sgent);
+
+		if (len > DMA_MAX_SIZE)
+			j += DIV_ROUND_UP(len, DMA_MAX_SIZE & ~DMA_ALIGN) - 1;
+		if (addr & DMA_ALIGN) {
+			dev_dbg(chan->device->dev, "vchan %p: bad buffer alignment: %08x\n",
+				c, addr);
+			return NULL;
+		}
+	}
+
+	txd = kzalloc(sizeof(*txd) + j * sizeof(txd->sg[0]), GFP_ATOMIC);
+	if (!txd) {
+		dev_dbg(chan->device->dev, "vchan %p: kzalloc failed\n", c);
+		return NULL;
+	}
+
+	j = 0;
+	for_each_sg(sg, sgent, sglen, i) {
+		dma_addr_t addr = sg_dma_address(sgent);
+		unsigned len = sg_dma_len(sgent);
+
+		size += len;
+
+		do {
+			unsigned tlen = len;
+
+			/*
+			 * Check whether the transfer will fit.  If not, try
+			 * to split the transfer up such that we end up with
+			 * equal chunks - but make sure that we preserve the
+			 * alignment.  This avoids small segments.
+			 */
+			if (tlen > DMA_MAX_SIZE) {
+				unsigned mult = DIV_ROUND_UP(tlen,
+					DMA_MAX_SIZE & ~DMA_ALIGN);
+
+				tlen = (tlen / mult) & ~DMA_ALIGN;
+			}
+
+			txd->sg[j].addr = addr;
+			txd->sg[j].len = tlen;
+
+			addr += tlen;
+			len -= tlen;
+			j++;
+		} while (len);
+	}
+
+	dma_async_tx_descriptor_init(&txd->tx, &c->chan);
+	txd->tx.flags = flags;
+	txd->tx.tx_submit = sa11x0_dma_tx_submit;
+	txd->ddar = c->ddar;
+	txd->size = size;
+	txd->sglen = j;
+
+	dev_dbg(chan->device->dev, "vchan %p: txd %p: size %u nr %u\n",
+		c, txd, txd->size, txd->sglen);
+
+	return &txd->tx;
+}
+
+static int sa11x0_dma_slave_config(struct sa11x0_dma_chan *c, struct dma_slave_config *cfg)
+{
+	u32 ddar = c->ddar & ((0xf << 4) | DDAR_RW);
+	dma_addr_t addr;
+	enum dma_slave_buswidth width;
+	u32 maxburst;
+
+	if (ddar & DDAR_RW) {
+		addr = cfg->src_addr;
+		width = cfg->src_addr_width;
+		maxburst = cfg->src_maxburst;
+	} else {
+		addr = cfg->dst_addr;
+		width = cfg->dst_addr_width;
+		maxburst = cfg->dst_maxburst;
+	}
+
+	if ((width != DMA_SLAVE_BUSWIDTH_1_BYTE &&
+	     width != DMA_SLAVE_BUSWIDTH_2_BYTES) ||
+	    (maxburst != 4 && maxburst != 8))
+		return -EINVAL;
+
+	if (width == DMA_SLAVE_BUSWIDTH_2_BYTES)
+		ddar |= DDAR_DW;
+	if (maxburst == 8)
+		ddar |= DDAR_BS;
+
+	dev_dbg(c->chan.device->dev, "vchan %p: dma_slave_config addr %x width %u burst %u\n",
+		c, addr, width, maxburst);
+
+	c->ddar = ddar | (addr & 0xf0000000) | (addr & 0x003ffffc) << 6;
+
+	return 0;
+}
+
+static int sa11x0_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+	unsigned long arg)
+{
+	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
+	struct sa11x0_dma_dev *d = to_sa11x0_dma(chan->device);
+	struct sa11x0_dma_phy *p;
+	LIST_HEAD(head);
+	unsigned long flags;
+	int ret;
+
+	switch (cmd) {
+	case DMA_SLAVE_CONFIG:
+		return sa11x0_dma_slave_config(c, (struct dma_slave_config *)arg);
+
+	case DMA_TERMINATE_ALL:
+		dev_dbg(d->slave.dev, "vchan %p: terminate all\n", c);
+		/* Clear the tx descriptor lists */
+		spin_lock_irqsave(&c->lock, flags);
+		list_splice_tail_init(&c->desc_submitted, &head);
+		list_splice_tail_init(&c->desc_issued, &head);
+
+		p = c->phy;
+		if (p) {
+			struct sa11x0_dma_desc *txd, *txn;
+
+			dev_dbg(d->slave.dev, "pchan %u: terminating\n", p->num);
+			/* vchan is assigned to a pchan - stop the channel */
+			writel(DCSR_RUN | DCSR_IE |
+				DCSR_STRTA | DCSR_DONEA |
+				DCSR_STRTB | DCSR_DONEB,
+				p->base + DMA_DCSR_C);
+
+			list_for_each_entry_safe(txd, txn, &d->desc_complete, node)
+				if (txd->tx.chan == &c->chan)
+					list_move(&txd->node, &head);
+
+			if (p->txd_load) {
+				if (p->txd_load != p->txd_done)
+					list_add_tail(&p->txd_load->node, &head);
+				p->txd_load = NULL;
+			}
+			if (p->txd_done) {
+				list_add_tail(&p->txd_done->node, &head);
+				p->txd_done = NULL;
+			}
+			c->phy = NULL;
+			spin_lock(&d->lock);
+			p->vchan = NULL;
+			spin_unlock(&d->lock);
+			tasklet_schedule(&d->task);
+		}
+		spin_unlock_irqrestore(&c->lock, flags);
+		sa11x0_dma_desc_free(d, &head);
+		ret = 0;
+		break;
+
+	case DMA_PAUSE:
+		dev_dbg(d->slave.dev, "vchan %p: pause\n", c);
+		spin_lock_irqsave(&c->lock, flags);
+		if (c->status == DMA_IN_PROGRESS) {
+			c->status = DMA_PAUSED;
+
+			p = c->phy;
+			if (p) {
+				writel(DCSR_RUN | DCSR_IE, p->base + DMA_DCSR_C);
+			} else {
+				spin_lock(&d->lock);
+				list_del_init(&c->node);
+				spin_unlock(&d->lock);
+			}
+		}
+		spin_unlock_irqrestore(&c->lock, flags);
+		ret = 0;
+		break;
+
+	case DMA_RESUME:
+		dev_dbg(d->slave.dev, "vchan %p: resume\n", c);
+		spin_lock_irqsave(&c->lock, flags);
+		if (c->status == DMA_PAUSED) {
+			c->status = DMA_IN_PROGRESS;
+
+			p = c->phy;
+			if (p) {
+				writel(DCSR_RUN | DCSR_IE, p->base + DMA_DCSR_S);
+			} else if (!list_empty(&c->desc_issued)) {
+				spin_lock(&d->lock);
+				list_add_tail(&c->node, &d->chan_pending);
+				spin_unlock(&d->lock);
+			}
+		}
+		spin_unlock_irqrestore(&c->lock, flags);
+		ret = 0;
+		break;
+
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
+struct sa11x0_dma_channel_desc {
+	u32 ddar;
+	const char *name;
+};
+
+#define CD(d1, d2) { .ddar = DDAR_##d1 | d2, .name = #d1 }
+static const struct sa11x0_dma_channel_desc chan_desc[] = {
+	CD(Ser0UDCTr, 0),
+	CD(Ser0UDCRc, DDAR_RW),
+	CD(Ser1SDLCTr, 0),
+	CD(Ser1SDLCRc, DDAR_RW),
+	CD(Ser1UARTTr, 0),
+	CD(Ser1UARTRc, DDAR_RW),
+	CD(Ser2ICPTr, 0),
+	CD(Ser2ICPRc, DDAR_RW),
+	CD(Ser3UARTTr, 0),
+	CD(Ser3UARTRc, DDAR_RW),
+	CD(Ser4MCP0Tr, 0),
+	CD(Ser4MCP0Rc, DDAR_RW),
+	CD(Ser4MCP1Tr, 0),
+	CD(Ser4MCP1Rc, DDAR_RW),
+	CD(Ser4SSPTr, 0),
+	CD(Ser4SSPRc, DDAR_RW),
+};
+
+static int __devinit sa11x0_dma_init_dmadev(struct dma_device *dmadev,
+	struct device *dev)
+{
+	unsigned i;
+
+	dmadev->chancnt = ARRAY_SIZE(chan_desc);
+	INIT_LIST_HEAD(&dmadev->channels);
+	dmadev->dev = dev;
+	dmadev->device_alloc_chan_resources = sa11x0_dma_alloc_chan_resources;
+	dmadev->device_free_chan_resources = sa11x0_dma_free_chan_resources;
+	dmadev->device_control = sa11x0_dma_control;
+	dmadev->device_tx_status = sa11x0_dma_tx_status;
+	dmadev->device_issue_pending = sa11x0_dma_issue_pending;
+
+	for (i = 0; i < dmadev->chancnt; i++) {
+		struct sa11x0_dma_chan *c;
+
+		c = kzalloc(sizeof(*c), GFP_KERNEL);
+		if (!c) {
+			dev_err(dev, "no memory for channel %u\n", i);
+			return -ENOMEM;
+		}
+
+		c->chan.device = dmadev;
+		c->status = DMA_IN_PROGRESS;
+		c->ddar = chan_desc[i].ddar;
+		c->name = chan_desc[i].name;
+		spin_lock_init(&c->lock);
+		INIT_LIST_HEAD(&c->desc_submitted);
+		INIT_LIST_HEAD(&c->desc_issued);
+		INIT_LIST_HEAD(&c->node);
+		list_add_tail(&c->chan.device_node, &dmadev->channels);
+	}
+
+	return dma_async_device_register(dmadev);
+}
+
+static int sa11x0_dma_request_irq(struct platform_device *pdev, int nr,
+	void *data)
+{
+	int irq = platform_get_irq(pdev, nr);
+
+	if (irq <= 0)
+		return -ENXIO;
+
+	return request_irq(irq, sa11x0_dma_irq, 0, dev_name(&pdev->dev), data);
+}
+
+static void sa11x0_dma_free_irq(struct platform_device *pdev, int nr,
+	void *data)
+{
+	int irq = platform_get_irq(pdev, nr);
+	if (irq > 0)
+		free_irq(irq, data);
+}
+
+static void sa11x0_dma_free_channels(struct dma_device *dmadev)
+{
+	struct sa11x0_dma_chan *c, *cn;
+
+	list_for_each_entry_safe(c, cn, &dmadev->channels, chan.device_node) {
+		list_del(&c->chan.device_node);
+		kfree(c);
+	}
+}
+
+static int __devinit sa11x0_dma_probe(struct platform_device *pdev)
+{
+	struct sa11x0_dma_dev *d;
+	struct resource *res;
+	unsigned i;
+	int ret;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENXIO;
+
+	d = kzalloc(sizeof(*d), GFP_KERNEL);
+	if (!d) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	spin_lock_init(&d->lock);
+	INIT_LIST_HEAD(&d->chan_pending);
+	INIT_LIST_HEAD(&d->desc_complete);
+
+	d->base = ioremap(res->start, resource_size(res));
+	if (!d->base) {
+		ret = -ENOMEM;
+		goto err_ioremap;
+	}
+
+	tasklet_init(&d->task, sa11x0_dma_tasklet, (unsigned long)d);
+
+	for (i = 0; i < NR_PHY_CHAN; i++) {
+		struct sa11x0_dma_phy *p = &d->phy[i];
+
+		p->dev = d;
+		p->num = i;
+		p->base = d->base + i * DMA_SIZE;
+		writel_relaxed(DCSR_RUN | DCSR_IE | DCSR_ERROR |
+			DCSR_DONEA | DCSR_STRTA | DCSR_DONEB | DCSR_STRTB,
+			p->base + DMA_DCSR_C);
+		writel_relaxed(0, p->base + DMA_DDAR);
+
+		ret = sa11x0_dma_request_irq(pdev, i, p);
+		if (ret) {
+			while (i) {
+				i--;
+				sa11x0_dma_free_irq(pdev, i, &d->phy[i]);
+			}
+			goto err_irq;
+		}
+	}
+
+	dma_cap_set(DMA_SLAVE, d->slave.cap_mask);
+	d->slave.device_prep_slave_sg = sa11x0_dma_prep_slave_sg;
+	ret = sa11x0_dma_init_dmadev(&d->slave, &pdev->dev);
+	if (ret) {
+		dev_warn(d->slave.dev, "failed to register slave async device: %d\n",
+			ret);
+		goto err_slave_reg;
+	}
+
+	platform_set_drvdata(pdev, d);
+	return 0;
+
+ err_slave_reg:
+	sa11x0_dma_free_channels(&d->slave);
+	for (i = 0; i < NR_PHY_CHAN; i++)
+		sa11x0_dma_free_irq(pdev, i, &d->phy[i]);
+ err_irq:
+	tasklet_kill(&d->task);
+	iounmap(d->base);
+ err_ioremap:
+	kfree(d);
+ err_alloc:
+	return ret;
+}
+
+static int __devexit sa11x0_dma_remove(struct platform_device *pdev)
+{
+	struct sa11x0_dma_dev *d = platform_get_drvdata(pdev);
+	unsigned pch;
+
+	dma_async_device_unregister(&d->slave);
+
+	sa11x0_dma_free_channels(&d->slave);
+	for (pch = 0; pch < NR_PHY_CHAN; pch++)
+		sa11x0_dma_free_irq(pdev, pch, &d->phy[pch]);
+	tasklet_kill(&d->task);
+	iounmap(d->base);
+	kfree(d);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int sa11x0_dma_suspend(struct device *dev)
+{
+	struct sa11x0_dma_dev *d = dev_get_drvdata(dev);
+	unsigned pch;
+
+	for (pch = 0; pch < NR_PHY_CHAN; pch++) {
+		struct sa11x0_dma_phy *p = &d->phy[pch];
+		u32 dcsr, saved_dcsr;
+
+		dcsr = saved_dcsr = readl_relaxed(p->base + DMA_DCSR_R);
+		if (dcsr & DCSR_RUN) {
+			writel(DCSR_RUN | DCSR_IE, p->base + DMA_DCSR_C);
+			dcsr = readl_relaxed(p->base + DMA_DCSR_R);
+		}
+
+		saved_dcsr &= DCSR_RUN | DCSR_IE;
+		if (dcsr & DCSR_BIU) {
+			p->dbs[0] = readl_relaxed(p->base + DMA_DBSB);
+			p->dbt[0] = readl_relaxed(p->base + DMA_DBTB);
+			p->dbs[1] = readl_relaxed(p->base + DMA_DBSA);
+			p->dbt[1] = readl_relaxed(p->base + DMA_DBTA);
+			saved_dcsr |= (dcsr & DCSR_STRTA ? DCSR_STRTB : 0) |
+				      (dcsr & DCSR_STRTB ? DCSR_STRTA : 0);
+		} else {
+			p->dbs[0] = readl_relaxed(p->base + DMA_DBSA);
+			p->dbt[0] = readl_relaxed(p->base + DMA_DBTA);
+			p->dbs[1] = readl_relaxed(p->base + DMA_DBSB);
+			p->dbt[1] = readl_relaxed(p->base + DMA_DBTB);
+			saved_dcsr |= dcsr & (DCSR_STRTA | DCSR_STRTB);
+		}
+		p->dcsr = saved_dcsr;
+
+		writel(DCSR_STRTA | DCSR_STRTB, p->base + DMA_DCSR_C);
+	}
+
+	return 0;
+}
+
+static int sa11x0_dma_resume(struct device *dev)
+{
+	struct sa11x0_dma_dev *d = dev_get_drvdata(dev);
+	unsigned pch;
+
+	for (pch = 0; pch < NR_PHY_CHAN; pch++) {
+		struct sa11x0_dma_phy *p = &d->phy[pch];
+		struct sa11x0_dma_desc *txd = NULL;
+		u32 dcsr = readl_relaxed(p->base + DMA_DCSR_R);
+
+		WARN_ON(dcsr & (DCSR_BIU | DCSR_STRTA | DCSR_STRTB | DCSR_RUN));
+
+		if (p->txd_done)
+			txd = p->txd_done;
+		else if (p->txd_load)
+			txd = p->txd_load;
+
+		if (!txd)
+			continue;
+
+		writel_relaxed(txd->ddar, p->base + DMA_DDAR);
+
+		writel_relaxed(p->dbs[0], p->base + DMA_DBSA);
+		writel_relaxed(p->dbt[0], p->base + DMA_DBTA);
+		writel_relaxed(p->dbs[1], p->base + DMA_DBSB);
+		writel_relaxed(p->dbt[1], p->base + DMA_DBTB);
+		writel_relaxed(p->dcsr, p->base + DMA_DCSR_S);
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops sa11x0_dma_pm_ops = {
+	.suspend_noirq = sa11x0_dma_suspend,
+	.resume_noirq = sa11x0_dma_resume,
+	.freeze_noirq = sa11x0_dma_suspend,
+	.thaw_noirq = sa11x0_dma_resume,
+	.poweroff_noirq = sa11x0_dma_suspend,
+	.restore_noirq = sa11x0_dma_resume,
+};
+
+static struct platform_driver sa11x0_dma_driver = {
+	.driver = {
+		.name	= "sa11x0-dma",
+		.owner	= THIS_MODULE,
+		.pm	= &sa11x0_dma_pm_ops,
+	},
+	.probe		= sa11x0_dma_probe,
+	.remove		= __devexit_p(sa11x0_dma_remove),
+};
+
+bool sa11x0_dma_filter_fn(struct dma_chan *chan, void *param)
+{
+	if (chan->device->dev->driver == &sa11x0_dma_driver.driver) {
+		struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
+		const char *p = param;
+
+		return !strcmp(c->name, p);
+	}
+	return false;
+}
+EXPORT_SYMBOL(sa11x0_dma_filter_fn);
+
+static int __init sa11x0_dma_init(void)
+{
+	return platform_driver_register(&sa11x0_dma_driver);
+}
+subsys_initcall(sa11x0_dma_init);
+
+static void __exit sa11x0_dma_exit(void)
+{
+	platform_driver_unregister(&sa11x0_dma_driver);
+}
+module_exit(sa11x0_dma_exit);
+
+MODULE_AUTHOR("Russell King");
+MODULE_DESCRIPTION("SA-11x0 DMA driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:sa11x0-dma");
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index 812fd76e9c18..19d7a8d3975d 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -30,6 +30,8 @@
 #include <linux/kdebug.h>
 #include <linux/spinlock.h>
 #include <linux/rculist.h>
+
+#include "dmaengine.h"
 #include "shdma.h"
 
 /* DMA descriptor control */
@@ -296,13 +298,7 @@ static dma_cookie_t sh_dmae_tx_submit(struct dma_async_tx_descriptor *tx)
 	else
 		power_up = false;
 
-	cookie = sh_chan->common.cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-
-	sh_chan->common.cookie = cookie;
-	tx->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 
 	/* Mark all chunks of this descriptor as submitted, move to the queue */
 	list_for_each_entry_safe(chunk, c, desc->node.prev, node) {
@@ -673,7 +669,8 @@ static struct dma_async_tx_descriptor *sh_dmae_prep_memcpy(
 
 static struct dma_async_tx_descriptor *sh_dmae_prep_slave_sg(
 	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
 {
 	struct sh_dmae_slave *param;
 	struct sh_dmae_chan *sh_chan;
@@ -764,12 +761,12 @@ static dma_async_tx_callback __ld_cleanup(struct sh_dmae_chan *sh_chan, bool all
 			cookie = tx->cookie;
 
 		if (desc->mark == DESC_COMPLETED && desc->chunks == 1) {
-			if (sh_chan->completed_cookie != desc->cookie - 1)
+			if (sh_chan->common.completed_cookie != desc->cookie - 1)
 				dev_dbg(sh_chan->dev,
 					"Completing cookie %d, expected %d\n",
 					desc->cookie,
-					sh_chan->completed_cookie + 1);
-			sh_chan->completed_cookie = desc->cookie;
+					sh_chan->common.completed_cookie + 1);
+			sh_chan->common.completed_cookie = desc->cookie;
 		}
 
 		/* Call callback on the last chunk */
@@ -823,7 +820,7 @@ static dma_async_tx_callback __ld_cleanup(struct sh_dmae_chan *sh_chan, bool all
 		 * Terminating and the loop completed normally: forgive
 		 * uncompleted cookies
 		 */
-		sh_chan->completed_cookie = sh_chan->common.cookie;
+		sh_chan->common.completed_cookie = sh_chan->common.cookie;
 
 	spin_unlock_irqrestore(&sh_chan->desc_lock, flags);
 
@@ -883,23 +880,14 @@ static enum dma_status sh_dmae_tx_status(struct dma_chan *chan,
 					struct dma_tx_state *txstate)
 {
 	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
 	enum dma_status status;
 	unsigned long flags;
 
 	sh_dmae_chan_ld_cleanup(sh_chan, false);
 
-	/* First read completed cookie to avoid a skew */
-	last_complete = sh_chan->completed_cookie;
-	rmb();
-	last_used = chan->cookie;
-	BUG_ON(last_complete < 0);
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
 	spin_lock_irqsave(&sh_chan->desc_lock, flags);
 
-	status = dma_async_is_complete(cookie, last_complete, last_used);
+	status = dma_cookie_status(chan, cookie, txstate);
 
 	/*
 	 * If we don't find cookie on the queue, it has been aborted and we have
@@ -1102,6 +1090,7 @@ static int __devinit sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id,
 
 	/* reference struct dma_device */
 	new_sh_chan->common.device = &shdev->common;
+	dma_cookie_init(&new_sh_chan->common);
 
 	new_sh_chan->dev = shdev->common.dev;
 	new_sh_chan->id = id;
diff --git a/drivers/dma/shdma.h b/drivers/dma/shdma.h
index 2b55a276dc5b..0b1d2c105f02 100644
--- a/drivers/dma/shdma.h
+++ b/drivers/dma/shdma.h
@@ -30,7 +30,6 @@ enum dmae_pm_state {
 };
 
 struct sh_dmae_chan {
-	dma_cookie_t completed_cookie;	/* The maximum cookie completed */
 	spinlock_t desc_lock;		/* Descriptor operation lock */
 	struct list_head ld_queue;	/* Link descriptors queue */
 	struct list_head ld_free;	/* Link descriptors free */
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 2333810d1688..434ad31174f2 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -18,6 +18,8 @@
 #include <linux/of_platform.h>
 #include <linux/sirfsoc_dma.h>
 
+#include "dmaengine.h"
+
 #define SIRFSOC_DMA_DESCRIPTORS                 16
 #define SIRFSOC_DMA_CHANNELS                    16
 
@@ -59,7 +61,6 @@ struct sirfsoc_dma_chan {
 	struct list_head		queued;
 	struct list_head		active;
 	struct list_head		completed;
-	dma_cookie_t			completed_cookie;
 	unsigned long			happened_cyclic;
 	unsigned long			completed_cyclic;
 
@@ -208,7 +209,7 @@ static void sirfsoc_dma_process_completed(struct sirfsoc_dma *sdma)
 			/* Free descriptors */
 			spin_lock_irqsave(&schan->lock, flags);
 			list_splice_tail_init(&list, &schan->free);
-			schan->completed_cookie = last_cookie;
+			schan->chan.completed_cookie = last_cookie;
 			spin_unlock_irqrestore(&schan->lock, flags);
 		} else {
 			/* for cyclic channel, desc is always in active list */
@@ -258,13 +259,7 @@ static dma_cookie_t sirfsoc_dma_tx_submit(struct dma_async_tx_descriptor *txd)
 	/* Move descriptor to queue */
 	list_move_tail(&sdesc->node, &schan->queued);
 
-	/* Update cookie */
-	cookie = schan->chan.cookie + 1;
-	if (cookie <= 0)
-		cookie = 1;
-
-	schan->chan.cookie = cookie;
-	sdesc->desc.cookie = cookie;
+	cookie = dma_cookie_assign(txd);
 
 	spin_unlock_irqrestore(&schan->lock, flags);
 
@@ -414,16 +409,13 @@ sirfsoc_dma_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 {
 	struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan);
 	unsigned long flags;
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
+	enum dma_status ret;
 
 	spin_lock_irqsave(&schan->lock, flags);
-	last_used = schan->chan.cookie;
-	last_complete = schan->completed_cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
 	spin_unlock_irqrestore(&schan->lock, flags);
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-	return dma_async_is_complete(cookie, last_complete, last_used);
+	return ret;
 }
 
 static struct dma_async_tx_descriptor *sirfsoc_dma_prep_interleaved(
@@ -497,7 +489,7 @@ err_dir:
 static struct dma_async_tx_descriptor *
 sirfsoc_dma_prep_cyclic(struct dma_chan *chan, dma_addr_t addr,
 	size_t buf_len, size_t period_len,
-	enum dma_transfer_direction direction)
+	enum dma_transfer_direction direction, void *context)
 {
 	struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan);
 	struct sirfsoc_dma_desc *sdesc = NULL;
@@ -635,8 +627,7 @@ static int __devinit sirfsoc_dma_probe(struct platform_device *op)
 		schan = &sdma->channels[i];
 
 		schan->chan.device = dma;
-		schan->chan.cookie = 1;
-		schan->completed_cookie = schan->chan.cookie;
+		dma_cookie_init(&schan->chan);
 
 		INIT_LIST_HEAD(&schan->free);
 		INIT_LIST_HEAD(&schan->prepared);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index cc5ecbc067a3..bdd41d4bfa8d 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -21,6 +21,7 @@
 
 #include <plat/ste_dma40.h>
 
+#include "dmaengine.h"
 #include "ste_dma40_ll.h"
 
 #define D40_NAME "dma40"
@@ -220,8 +221,6 @@ struct d40_base;
  *
  * @lock: A spinlock to protect this struct.
  * @log_num: The logical number, if any of this channel.
- * @completed: Starts with 1, after first interrupt it is set to dma engine's
- * current cookie.
  * @pending_tx: The number of pending transfers. Used between interrupt handler
  * and tasklet.
  * @busy: Set to true when transfer is ongoing on this channel.
@@ -250,8 +249,6 @@ struct d40_base;
 struct d40_chan {
 	spinlock_t			 lock;
 	int				 log_num;
-	/* ID of the most recent completed transfer */
-	int				 completed;
 	int				 pending_tx;
 	bool				 busy;
 	struct d40_phy_res		*phy_chan;
@@ -1223,21 +1220,14 @@ static dma_cookie_t d40_tx_submit(struct dma_async_tx_descriptor *tx)
 					     chan);
 	struct d40_desc *d40d = container_of(tx, struct d40_desc, txd);
 	unsigned long flags;
+	dma_cookie_t cookie;
 
 	spin_lock_irqsave(&d40c->lock, flags);
-
-	d40c->chan.cookie++;
-
-	if (d40c->chan.cookie < 0)
-		d40c->chan.cookie = 1;
-
-	d40d->txd.cookie = d40c->chan.cookie;
-
+	cookie = dma_cookie_assign(tx);
 	d40_desc_queue(d40c, d40d);
-
 	spin_unlock_irqrestore(&d40c->lock, flags);
 
-	return tx->cookie;
+	return cookie;
 }
 
 static int d40_start(struct d40_chan *d40c)
@@ -1357,7 +1347,7 @@ static void dma_tasklet(unsigned long data)
 		goto err;
 
 	if (!d40d->cyclic)
-		d40c->completed = d40d->txd.cookie;
+		dma_cookie_complete(&d40d->txd);
 
 	/*
 	 * If terminating a channel pending_tx is set to zero.
@@ -2182,7 +2172,7 @@ static int d40_alloc_chan_resources(struct dma_chan *chan)
 	bool is_free_phy;
 	spin_lock_irqsave(&d40c->lock, flags);
 
-	d40c->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	/* If no dma configuration is set use default configuration (memcpy) */
 	if (!d40c->configured) {
@@ -2299,7 +2289,8 @@ static struct dma_async_tx_descriptor *d40_prep_slave_sg(struct dma_chan *chan,
 							 struct scatterlist *sgl,
 							 unsigned int sg_len,
 							 enum dma_transfer_direction direction,
-							 unsigned long dma_flags)
+							 unsigned long dma_flags,
+							 void *context)
 {
 	if (direction != DMA_DEV_TO_MEM && direction != DMA_MEM_TO_DEV)
 		return NULL;
@@ -2310,7 +2301,7 @@ static struct dma_async_tx_descriptor *d40_prep_slave_sg(struct dma_chan *chan,
 static struct dma_async_tx_descriptor *
 dma40_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 		     size_t buf_len, size_t period_len,
-		     enum dma_transfer_direction direction)
+		     enum dma_transfer_direction direction, void *context)
 {
 	unsigned int periods = buf_len / period_len;
 	struct dma_async_tx_descriptor *txd;
@@ -2342,25 +2333,19 @@ static enum dma_status d40_tx_status(struct dma_chan *chan,
 				     struct dma_tx_state *txstate)
 {
 	struct d40_chan *d40c = container_of(chan, struct d40_chan, chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	int ret;
+	enum dma_status ret;
 
 	if (d40c->phy_chan == NULL) {
 		chan_err(d40c, "Cannot read status of unallocated channel\n");
 		return -EINVAL;
 	}
 
-	last_complete = d40c->completed;
-	last_used = chan->cookie;
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret != DMA_SUCCESS)
+		dma_set_residue(txstate, stedma40_residue(chan));
 
 	if (d40_is_paused(d40c))
 		ret = DMA_PAUSED;
-	else
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
-
-	dma_set_tx_state(txstate, last_complete, last_used,
-			 stedma40_residue(chan));
 
 	return ret;
 }
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index a6f9c1684a0f..4e0dff59901d 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -31,6 +31,8 @@
 
 #include <linux/timb_dma.h>
 
+#include "dmaengine.h"
+
 #define DRIVER_NAME "timb-dma"
 
 /* Global DMA registers */
@@ -84,7 +86,6 @@ struct timb_dma_chan {
 					especially the lists and descriptors,
 					from races between the tasklet and calls
 					from above */
-	dma_cookie_t		last_completed_cookie;
 	bool			ongoing;
 	struct list_head	active_list;
 	struct list_head	queue;
@@ -284,7 +285,7 @@ static void __td_finish(struct timb_dma_chan *td_chan)
 	else
 		iowrite32(0, td_chan->membase + TIMBDMA_OFFS_TX_DLAR);
 */
-	td_chan->last_completed_cookie = txd->cookie;
+	dma_cookie_complete(txd);
 	td_chan->ongoing = false;
 
 	callback = txd->callback;
@@ -349,12 +350,7 @@ static dma_cookie_t td_tx_submit(struct dma_async_tx_descriptor *txd)
 	dma_cookie_t cookie;
 
 	spin_lock_bh(&td_chan->lock);
-
-	cookie = txd->chan->cookie;
-	if (++cookie < 0)
-		cookie = 1;
-	txd->chan->cookie = cookie;
-	txd->cookie = cookie;
+	cookie = dma_cookie_assign(txd);
 
 	if (list_empty(&td_chan->active_list)) {
 		dev_dbg(chan2dev(txd->chan), "%s: started %u\n", __func__,
@@ -481,8 +477,7 @@ static int td_alloc_chan_resources(struct dma_chan *chan)
 	}
 
 	spin_lock_bh(&td_chan->lock);
-	td_chan->last_completed_cookie = 1;
-	chan->cookie = 1;
+	dma_cookie_init(chan);
 	spin_unlock_bh(&td_chan->lock);
 
 	return 0;
@@ -515,24 +510,13 @@ static void td_free_chan_resources(struct dma_chan *chan)
 static enum dma_status td_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 				    struct dma_tx_state *txstate)
 {
-	struct timb_dma_chan *td_chan =
-		container_of(chan, struct timb_dma_chan, chan);
-	dma_cookie_t		last_used;
-	dma_cookie_t		last_complete;
-	int			ret;
+	enum dma_status ret;
 
 	dev_dbg(chan2dev(chan), "%s: Entry\n", __func__);
 
-	last_complete = td_chan->last_completed_cookie;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
-
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
+	ret = dma_cookie_status(chan, cookie, txstate);
 
-	dev_dbg(chan2dev(chan),
-		"%s: exit, ret: %d, last_complete: %d, last_used: %d\n",
-		__func__, ret, last_complete, last_used);
+	dev_dbg(chan2dev(chan), "%s: exit, ret: %d\n", 	__func__, ret);
 
 	return ret;
 }
@@ -558,7 +542,8 @@ static void td_issue_pending(struct dma_chan *chan)
 
 static struct dma_async_tx_descriptor *td_prep_slave_sg(struct dma_chan *chan,
 	struct scatterlist *sgl, unsigned int sg_len,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
 {
 	struct timb_dma_chan *td_chan =
 		container_of(chan, struct timb_dma_chan, chan);
@@ -766,7 +751,7 @@ static int __devinit td_probe(struct platform_device *pdev)
 		}
 
 		td_chan->chan.device = &td->dma;
-		td_chan->chan.cookie = 1;
+		dma_cookie_init(&td_chan->chan);
 		spin_lock_init(&td_chan->lock);
 		INIT_LIST_HEAD(&td_chan->active_list);
 		INIT_LIST_HEAD(&td_chan->queue);
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 6122c364cf11..913f55c76c99 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -15,6 +15,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/scatterlist.h>
+
+#include "dmaengine.h"
 #include "txx9dmac.h"
 
 static struct txx9dmac_chan *to_txx9dmac_chan(struct dma_chan *chan)
@@ -279,21 +281,6 @@ static void txx9dmac_desc_put(struct txx9dmac_chan *dc,
 	}
 }
 
-/* Called with dc->lock held and bh disabled */
-static dma_cookie_t
-txx9dmac_assign_cookie(struct txx9dmac_chan *dc, struct txx9dmac_desc *desc)
-{
-	dma_cookie_t cookie = dc->chan.cookie;
-
-	if (++cookie < 0)
-		cookie = 1;
-
-	dc->chan.cookie = cookie;
-	desc->txd.cookie = cookie;
-
-	return cookie;
-}
-
 /*----------------------------------------------------------------------*/
 
 static void txx9dmac_dump_regs(struct txx9dmac_chan *dc)
@@ -424,7 +411,7 @@ txx9dmac_descriptor_complete(struct txx9dmac_chan *dc,
 	dev_vdbg(chan2dev(&dc->chan), "descriptor %u %p complete\n",
 		 txd->cookie, desc);
 
-	dc->completed = txd->cookie;
+	dma_cookie_complete(txd);
 	callback = txd->callback;
 	param = txd->callback_param;
 
@@ -738,7 +725,7 @@ static dma_cookie_t txx9dmac_tx_submit(struct dma_async_tx_descriptor *tx)
 	dma_cookie_t cookie;
 
 	spin_lock_bh(&dc->lock);
-	cookie = txx9dmac_assign_cookie(dc, desc);
+	cookie = dma_cookie_assign(tx);
 
 	dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u %p\n",
 		 desc->txd.cookie, desc);
@@ -846,7 +833,7 @@ txx9dmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 static struct dma_async_tx_descriptor *
 txx9dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags)
+		unsigned long flags, void *context)
 {
 	struct txx9dmac_chan *dc = to_txx9dmac_chan(chan);
 	struct txx9dmac_dev *ddev = dc->ddev;
@@ -972,27 +959,17 @@ txx9dmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		   struct dma_tx_state *txstate)
 {
 	struct txx9dmac_chan *dc = to_txx9dmac_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	int ret;
+	enum dma_status ret;
 
-	last_complete = dc->completed;
-	last_used = chan->cookie;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS) {
 		spin_lock_bh(&dc->lock);
 		txx9dmac_scan_descriptors(dc);
 		spin_unlock_bh(&dc->lock);
 
-		last_complete = dc->completed;
-		last_used = chan->cookie;
-
-		ret = dma_async_is_complete(cookie, last_complete, last_used);
+		ret = dma_cookie_status(chan, cookie, txstate);
 	}
 
-	dma_set_tx_state(txstate, last_complete, last_used, 0);
-
 	return ret;
 }
 
@@ -1057,7 +1034,7 @@ static int txx9dmac_alloc_chan_resources(struct dma_chan *chan)
 		return -EIO;
 	}
 
-	dc->completed = chan->cookie = 1;
+	dma_cookie_init(chan);
 
 	dc->ccr = TXX9_DMA_CCR_IMMCHN | TXX9_DMA_CCR_INTENE | CCR_LE;
 	txx9dmac_chan_set_SMPCHN(dc);
@@ -1186,7 +1163,7 @@ static int __init txx9dmac_chan_probe(struct platform_device *pdev)
 	dc->ddev->chan[ch] = dc;
 	dc->chan.device = &dc->dma;
 	list_add_tail(&dc->chan.device_node, &dc->chan.device->channels);
-	dc->chan.cookie = dc->completed = 1;
+	dma_cookie_init(&dc->chan);
 
 	if (is_dmac64(dc))
 		dc->ch_regs = &__txx9dmac_regs(dc->ddev)->CHAN[ch];
diff --git a/drivers/dma/txx9dmac.h b/drivers/dma/txx9dmac.h
index 365d42366b9f..f5a760598882 100644
--- a/drivers/dma/txx9dmac.h
+++ b/drivers/dma/txx9dmac.h
@@ -172,7 +172,6 @@ struct txx9dmac_chan {
 	spinlock_t		lock;
 
 	/* these other elements are all protected by lock */
-	dma_cookie_t		completed;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 5948a2194f50..fdffa1beca17 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -215,7 +215,7 @@ config EDAC_I7300
 config EDAC_SBRIDGE
 	tristate "Intel Sandy-Bridge Integrated MC"
 	depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
-	depends on EXPERIMENTAL
+	depends on PCI_MMCONFIG && EXPERIMENTAL
 	help
 	  Support for error detection and correction the Intel
 	  Sandy Bridge Integrated Memory Controller.
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index da09cd74bc5b..feef7733fae7 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -39,7 +39,7 @@ static LIST_HEAD(mc_devices);
 
 #ifdef CONFIG_EDAC_DEBUG
 
-static void edac_mc_dump_channel(struct channel_info *chan)
+static void edac_mc_dump_channel(struct rank_info *chan)
 {
 	debugf4("\tchannel = %p\n", chan);
 	debugf4("\tchannel->chan_idx = %d\n", chan->chan_idx);
@@ -156,7 +156,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
 {
 	struct mem_ctl_info *mci;
 	struct csrow_info *csi, *csrow;
-	struct channel_info *chi, *chp, *chan;
+	struct rank_info *chi, *chp, *chan;
 	void *pvt;
 	unsigned size;
 	int row, chn;
@@ -181,7 +181,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
 	 * rather than an imaginary chunk of memory located at address 0.
 	 */
 	csi = (struct csrow_info *)(((char *)mci) + ((unsigned long)csi));
-	chi = (struct channel_info *)(((char *)mci) + ((unsigned long)chi));
+	chi = (struct rank_info *)(((char *)mci) + ((unsigned long)chi));
 	pvt = sz_pvt ? (((char *)mci) + ((unsigned long)pvt)) : NULL;
 
 	/* setup index and various internal pointers */
diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c
index 2e23547b2f24..d500749464ea 100644
--- a/drivers/edac/i5100_edac.c
+++ b/drivers/edac/i5100_edac.c
@@ -49,7 +49,7 @@
 #define		I5100_FERR_NF_MEM_M6ERR_MASK	(1 << 6)
 #define		I5100_FERR_NF_MEM_M5ERR_MASK	(1 << 5)
 #define		I5100_FERR_NF_MEM_M4ERR_MASK	(1 << 4)
-#define		I5100_FERR_NF_MEM_M1ERR_MASK	1
+#define		I5100_FERR_NF_MEM_M1ERR_MASK	(1 << 1)
 #define		I5100_FERR_NF_MEM_ANY_MASK	\
 			(I5100_FERR_NF_MEM_M16ERR_MASK | \
 			I5100_FERR_NF_MEM_M15ERR_MASK | \
@@ -535,23 +535,20 @@ static void i5100_read_log(struct mem_ctl_info *mci, int chan,
 static void i5100_check_error(struct mem_ctl_info *mci)
 {
 	struct i5100_priv *priv = mci->pvt_info;
-	u32 dw;
-
+	u32 dw, dw2;
 
 	pci_read_config_dword(priv->mc, I5100_FERR_NF_MEM, &dw);
 	if (i5100_ferr_nf_mem_any(dw)) {
-		u32 dw2;
 
 		pci_read_config_dword(priv->mc, I5100_NERR_NF_MEM, &dw2);
-		if (dw2)
-			pci_write_config_dword(priv->mc, I5100_NERR_NF_MEM,
-					       dw2);
-		pci_write_config_dword(priv->mc, I5100_FERR_NF_MEM, dw);
 
 		i5100_read_log(mci, i5100_ferr_nf_mem_chan_indx(dw),
 			       i5100_ferr_nf_mem_any(dw),
 			       i5100_nerr_nf_mem_any(dw2));
+
+		pci_write_config_dword(priv->mc, I5100_NERR_NF_MEM, dw2);
 	}
+	pci_write_config_dword(priv->mc, I5100_FERR_NF_MEM, dw);
 }
 
 /* The i5100 chipset will scrub the entire memory once, then
diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c
index 67ec9626a330..1869a1018fb5 100644
--- a/drivers/edac/i5400_edac.c
+++ b/drivers/edac/i5400_edac.c
@@ -735,7 +735,7 @@ static int i5400_get_devices(struct mem_ctl_info *mci, int dev_idx)
 
 	/* Attempt to 'get' the MCH register we want */
 	pdev = NULL;
-	while (!pvt->branchmap_werrors || !pvt->fsb_error_regs) {
+	while (1) {
 		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
 				      PCI_DEVICE_ID_INTEL_5400_ERR, pdev);
 		if (!pdev) {
@@ -743,23 +743,42 @@ static int i5400_get_devices(struct mem_ctl_info *mci, int dev_idx)
 			i5400_printk(KERN_ERR,
 				"'system address,Process Bus' "
 				"device not found:"
-				"vendor 0x%x device 0x%x ERR funcs "
+				"vendor 0x%x device 0x%x ERR func 1 "
 				"(broken BIOS?)\n",
 				PCI_VENDOR_ID_INTEL,
 				PCI_DEVICE_ID_INTEL_5400_ERR);
-			goto error;
+			return -ENODEV;
 		}
 
-		/* Store device 16 funcs 1 and 2 */
-		switch (PCI_FUNC(pdev->devfn)) {
-		case 1:
-			pvt->branchmap_werrors = pdev;
-			break;
-		case 2:
-			pvt->fsb_error_regs = pdev;
+		/* Store device 16 func 1 */
+		if (PCI_FUNC(pdev->devfn) == 1)
 			break;
+	}
+	pvt->branchmap_werrors = pdev;
+
+	pdev = NULL;
+	while (1) {
+		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+				      PCI_DEVICE_ID_INTEL_5400_ERR, pdev);
+		if (!pdev) {
+			/* End of list, leave */
+			i5400_printk(KERN_ERR,
+				"'system address,Process Bus' "
+				"device not found:"
+				"vendor 0x%x device 0x%x ERR func 2 "
+				"(broken BIOS?)\n",
+				PCI_VENDOR_ID_INTEL,
+				PCI_DEVICE_ID_INTEL_5400_ERR);
+
+			pci_dev_put(pvt->branchmap_werrors);
+			return -ENODEV;
 		}
+
+		/* Store device 16 func 2 */
+		if (PCI_FUNC(pdev->devfn) == 2)
+			break;
 	}
+	pvt->fsb_error_regs = pdev;
 
 	debugf1("System Address, processor bus- PCI Bus ID: %s  %x:%x\n",
 		pci_name(pvt->system_address),
@@ -778,7 +797,10 @@ static int i5400_get_devices(struct mem_ctl_info *mci, int dev_idx)
 			"MC: 'BRANCH 0' device not found:"
 			"vendor 0x%x device 0x%x Func 0 (broken BIOS?)\n",
 			PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_5400_FBD0);
-		goto error;
+
+		pci_dev_put(pvt->fsb_error_regs);
+		pci_dev_put(pvt->branchmap_werrors);
+		return -ENODEV;
 	}
 
 	/* If this device claims to have more than 2 channels then
@@ -796,14 +818,14 @@ static int i5400_get_devices(struct mem_ctl_info *mci, int dev_idx)
 			"(broken BIOS?)\n",
 			PCI_VENDOR_ID_INTEL,
 			PCI_DEVICE_ID_INTEL_5400_FBD1);
-		goto error;
+
+		pci_dev_put(pvt->branch_0);
+		pci_dev_put(pvt->fsb_error_regs);
+		pci_dev_put(pvt->branchmap_werrors);
+		return -ENODEV;
 	}
 
 	return 0;
-
-error:
-	i5400_put_devices(mci);
-	return -ENODEV;
 }
 
 /*
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 36e1486eb9aa..d0c372e30de4 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -754,9 +754,7 @@ static int __init mce_amd_init(void)
 	if (c->x86_vendor != X86_VENDOR_AMD)
 		return 0;
 
-	if ((c->x86 < 0xf || c->x86 > 0x12) &&
-	    (c->x86 != 0x14 || c->x86_model > 0xf) &&
-	    (c->x86 != 0x15 || c->x86_model > 0xf))
+	if (c->x86 < 0xf || c->x86 > 0x15)
 		return 0;
 
 	fam_ops = kzalloc(sizeof(struct amd_decoder_ops), GFP_KERNEL);
@@ -797,7 +795,7 @@ static int __init mce_amd_init(void)
 		break;
 
 	default:
-		printk(KERN_WARNING "Huh? What family is that: %d?!\n", c->x86);
+		printk(KERN_WARNING "Huh? What family is it: 0x%x?!\n", c->x86);
 		kfree(fam_ops);
 		return -EINVAL;
 	}
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
index fc757069c6af..d427c69bb8b1 100644
--- a/drivers/edac/ppc4xx_edac.c
+++ b/drivers/edac/ppc4xx_edac.c
@@ -184,7 +184,7 @@ struct ppc4xx_ecc_status {
 
 /* Function Prototypes */
 
-static int ppc4xx_edac_probe(struct platform_device *device)
+static int ppc4xx_edac_probe(struct platform_device *device);
 static int ppc4xx_edac_remove(struct platform_device *device);
 
 /* Global Variables */
@@ -1068,7 +1068,7 @@ ppc4xx_edac_mc_init(struct mem_ctl_info *mci,
 
 	mci->mod_name		= PPC4XX_EDAC_MODULE_NAME;
 	mci->mod_ver		= PPC4XX_EDAC_MODULE_REVISION;
-	mci->ctl_name		= match->compatible,
+	mci->ctl_name		= ppc4xx_edac_match->compatible,
 	mci->dev_name		= np->full_name;
 
 	/* Initialize callbacks */
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 3a605f777712..a203536d90dd 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -20,6 +20,7 @@
 #include <linux/mmzone.h>
 #include <linux/smp.h>
 #include <linux/bitmap.h>
+#include <linux/math64.h>
 #include <asm/processor.h>
 #include <asm/mce.h>
 
@@ -670,6 +671,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	u32 reg;
 	u64 limit, prv = 0;
 	u64 tmp_mb;
+	u32 mb, kb;
 	u32 rir_way;
 
 	/*
@@ -682,8 +684,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	pvt->tolm = GET_TOLM(reg);
 	tmp_mb = (1 + pvt->tolm) >> 20;
 
-	debugf0("TOLM: %Lu.%03Lu GB (0x%016Lx)\n",
-		tmp_mb / 1000, tmp_mb % 1000, (u64)pvt->tolm);
+	mb = div_u64_rem(tmp_mb, 1000, &kb);
+	debugf0("TOLM: %u.%03u GB (0x%016Lx)\n",
+		mb, kb, (u64)pvt->tolm);
 
 	/* Address range is already 45:25 */
 	pci_read_config_dword(pvt->pci_sad1, TOHM,
@@ -691,8 +694,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	pvt->tohm = GET_TOHM(reg);
 	tmp_mb = (1 + pvt->tohm) >> 20;
 
-	debugf0("TOHM: %Lu.%03Lu GB (0x%016Lx)",
-		tmp_mb / 1000, tmp_mb % 1000, (u64)pvt->tohm);
+	mb = div_u64_rem(tmp_mb, 1000, &kb);
+	debugf0("TOHM: %u.%03u GB (0x%016Lx)",
+		mb, kb, (u64)pvt->tohm);
 
 	/*
 	 * Step 2) Get SAD range and SAD Interleave list
@@ -714,10 +718,11 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			break;
 
 		tmp_mb = (limit + 1) >> 20;
-		debugf0("SAD#%d %s up to %Lu.%03Lu GB (0x%016Lx) %s reg=0x%08x\n",
+		mb = div_u64_rem(tmp_mb, 1000, &kb);
+		debugf0("SAD#%d %s up to %u.%03u GB (0x%016Lx) %s reg=0x%08x\n",
 			n_sads,
 			get_dram_attr(reg),
-			tmp_mb / 1000, tmp_mb % 1000,
+			mb, kb,
 			((u64)tmp_mb) << 20L,
 			INTERLEAVE_MODE(reg) ? "Interleave: 8:6" : "Interleave: [8:6]XOR[18:16]",
 			reg);
@@ -747,8 +752,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			break;
 		tmp_mb = (limit + 1) >> 20;
 
-		debugf0("TAD#%d: up to %Lu.%03Lu GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n",
-			n_tads, tmp_mb / 1000, tmp_mb % 1000,
+		mb = div_u64_rem(tmp_mb, 1000, &kb);
+		debugf0("TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n",
+			n_tads, mb, kb,
 			((u64)tmp_mb) << 20L,
 			(u32)TAD_SOCK(reg),
 			(u32)TAD_CH(reg),
@@ -757,7 +763,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			(u32)TAD_TGT2(reg),
 			(u32)TAD_TGT3(reg),
 			reg);
-		prv = tmp_mb;
+		prv = limit;
 	}
 
 	/*
@@ -771,9 +777,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 					      tad_ch_nilv_offset[j],
 					      &reg);
 			tmp_mb = TAD_OFFSET(reg) >> 20;
-			debugf0("TAD CH#%d, offset #%d: %Lu.%03Lu GB (0x%016Lx), reg=0x%08x\n",
+			mb = div_u64_rem(tmp_mb, 1000, &kb);
+			debugf0("TAD CH#%d, offset #%d: %u.%03u GB (0x%016Lx), reg=0x%08x\n",
 				i, j,
-				tmp_mb / 1000, tmp_mb % 1000,
+				mb, kb,
 				((u64)tmp_mb) << 20L,
 				reg);
 		}
@@ -795,9 +802,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 
 			tmp_mb = RIR_LIMIT(reg) >> 20;
 			rir_way = 1 << RIR_WAY(reg);
-			debugf0("CH#%d RIR#%d, limit: %Lu.%03Lu GB (0x%016Lx), way: %d, reg=0x%08x\n",
+			mb = div_u64_rem(tmp_mb, 1000, &kb);
+			debugf0("CH#%d RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d, reg=0x%08x\n",
 				i, j,
-				tmp_mb / 1000, tmp_mb % 1000,
+				mb, kb,
 				((u64)tmp_mb) << 20L,
 				rir_way,
 				reg);
@@ -808,9 +816,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 						      &reg);
 				tmp_mb = RIR_OFFSET(reg) << 6;
 
-				debugf0("CH#%d RIR#%d INTL#%d, offset %Lu.%03Lu GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
+				mb = div_u64_rem(tmp_mb, 1000, &kb);
+				debugf0("CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
 					i, j, k,
-					tmp_mb / 1000, tmp_mb % 1000,
+					mb, kb,
 					((u64)tmp_mb) << 20L,
 					(u32)RIR_RNK_TGT(reg),
 					reg);
@@ -848,6 +857,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	u8			ch_way,sck_way;
 	u32			tad_offset;
 	u32			rir_way;
+	u32			mb, kb;
 	u64			ch_addr, offset, limit, prv = 0;
 
 
@@ -858,7 +868,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	 * range (e. g. VGA addresses). It is unlikely, however, that the
 	 * memory controller would generate an error on that range.
 	 */
-	if ((addr > (u64) pvt->tolm) && (addr < (1L << 32))) {
+	if ((addr > (u64) pvt->tolm) && (addr < (1LL << 32))) {
 		sprintf(msg, "Error at TOLM area, on addr 0x%08Lx", addr);
 		edac_mc_handle_ce_no_info(mci, msg);
 		return -EINVAL;
@@ -913,7 +923,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 		addr,
 		limit,
 		sad_way + 7,
-		INTERLEAVE_MODE(reg) ? "" : "XOR[18:16]");
+		interleave_mode ? "" : "XOR[18:16]");
 	if (interleave_mode)
 		idx = ((addr >> 6) ^ (addr >> 16)) & 7;
 	else
@@ -1053,7 +1063,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	ch_addr = addr & 0x7f;
 	/* Remove socket wayness and remove 6 bits */
 	addr >>= 6;
-	addr /= sck_xch;
+	addr = div_u64(addr, sck_xch);
 #if 0
 	/* Divide by channel way */
 	addr = addr / ch_way;
@@ -1073,10 +1083,10 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 			continue;
 
 		limit = RIR_LIMIT(reg);
-
-		debugf0("RIR#%d, limit: %Lu.%03Lu GB (0x%016Lx), way: %d\n",
+		mb = div_u64_rem(limit >> 20, 1000, &kb);
+		debugf0("RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d\n",
 			n_rir,
-			(limit >> 20) / 1000, (limit >> 20) % 1000,
+			mb, kb,
 			limit,
 			1 << RIR_WAY(reg));
 		if  (ch_addr <= limit)
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index 22c6df5f136d..2e6b24547e2a 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -44,7 +44,6 @@
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 
-#include <asm/system.h>
 
 #include "core.h"
 
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index afa7c83bd114..68109e9bb04e 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -40,7 +40,6 @@
 
 #include <linux/atomic.h>
 #include <asm/byteorder.h>
-#include <asm/system.h>
 
 #include "core.h"
 
diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c
index 255646ffc352..0de83508f321 100644
--- a/drivers/firewire/core-topology.c
+++ b/drivers/firewire/core-topology.c
@@ -31,7 +31,6 @@
 
 #include <linux/atomic.h>
 #include <asm/byteorder.h>
-#include <asm/system.h>
 
 #include "core.h"
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 187b3f2e797e..2b5460075a9f 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -46,7 +46,6 @@
 
 #include <asm/byteorder.h>
 #include <asm/page.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_PPC_PMAC
 #include <asm/pmac_feature.h>
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 000a29ffedae..b7e65d7eab64 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -52,7 +52,6 @@
 #include <linux/workqueue.h>
 
 #include <asm/byteorder.h>
-#include <asm/system.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 0409cf35adda..edadbdad31d0 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -236,6 +236,12 @@ config GPIO_MAX732X_IRQ
 	  Say yes here to enable the max732x to be used as an interrupt
 	  controller. It requires the driver to be built in the kernel.
 
+config GPIO_MC9S08DZ60
+	bool "MX35 3DS BOARD MC9S08DZ60 GPIO functions"
+	depends on I2C && MACH_MX35_3DS
+	help
+	  Select this to enable the MC9S08DZ60 GPIO driver
+
 config GPIO_PCA953X
 	tristate "PCA953x, PCA955x, TCA64xx, and MAX7310 I/O ports"
 	depends on I2C
@@ -422,6 +428,14 @@ config GPIO_ML_IOH
 	  Hub) which is for IVI(In-Vehicle Infotainment) use.
 	  This driver can access the IOH's GPIO device.
 
+config GPIO_SODAVILLE
+	bool "Intel Sodaville GPIO support"
+	depends on X86 && PCI && OF && BROKEN
+	select GPIO_GENERIC
+	select GENERIC_IRQ_CHIP
+	help
+	  Say Y here to support Intel Sodaville GPIO.
+
 config GPIO_TIMBERDALE
 	bool "Support for timberdale GPIO IP"
 	depends on MFD_TIMBERDALE && HAS_IOMEM
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 9a8fb54ae462..007f54bd0081 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_GPIO_MAX7300)	+= gpio-max7300.o
 obj-$(CONFIG_GPIO_MAX7301)	+= gpio-max7301.o
 obj-$(CONFIG_GPIO_MAX732X)	+= gpio-max732x.o
 obj-$(CONFIG_GPIO_MC33880)	+= gpio-mc33880.o
+obj-$(CONFIG_GPIO_MC9S08DZ60)	+= gpio-mc9s08dz60.o
 obj-$(CONFIG_GPIO_MCP23S08)	+= gpio-mcp23s08.o
 obj-$(CONFIG_GPIO_ML_IOH)	+= gpio-ml-ioh.o
 obj-$(CONFIG_GPIO_MPC5200)	+= gpio-mpc5200.o
@@ -46,6 +47,7 @@ obj-$(CONFIG_GPIO_RDC321X)	+= gpio-rdc321x.o
 obj-$(CONFIG_PLAT_SAMSUNG)	+= gpio-samsung.o
 obj-$(CONFIG_ARCH_SA1100)	+= gpio-sa1100.o
 obj-$(CONFIG_GPIO_SCH)		+= gpio-sch.o
+obj-$(CONFIG_GPIO_SODAVILLE)	+= gpio-sodaville.o
 obj-$(CONFIG_GPIO_STMPE)	+= gpio-stmpe.o
 obj-$(CONFIG_GPIO_SX150X)	+= gpio-sx150x.o
 obj-$(CONFIG_GPIO_TC3589X)	+= gpio-tc3589x.o
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index df0d59570a84..3d000169285d 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -313,10 +313,16 @@ static int gpio_to_irq_unbanked(struct gpio_chip *chip, unsigned offset)
 		return -ENODEV;
 }
 
-static int gpio_irq_type_unbanked(struct irq_data *d, unsigned trigger)
+static int gpio_irq_type_unbanked(struct irq_data *data, unsigned trigger)
 {
-	struct davinci_gpio_regs __iomem *g = irq2regs(d->irq);
-	u32 mask = (u32) irq_data_get_irq_handler_data(d);
+	struct davinci_gpio_controller *d;
+	struct davinci_gpio_regs __iomem *g;
+	struct davinci_soc_info *soc_info = &davinci_soc_info;
+	u32 mask;
+
+	d = (struct davinci_gpio_controller *)data->handler_data;
+	g = (struct davinci_gpio_regs __iomem *)d->regs;
+	mask = __gpio_mask(data->irq - soc_info->gpio_irq);
 
 	if (trigger & ~(IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
 		return -EINVAL;
@@ -380,7 +386,7 @@ static int __init davinci_gpio_irq_setup(void)
 	 * IRQ mux conflicts; gpio_irq_type_unbanked() is only for GPIOs.
 	 */
 	if (soc_info->gpio_unbanked) {
-		static struct irq_chip gpio_irqchip_unbanked;
+		static struct irq_chip_type gpio_unbanked;
 
 		/* pass "bank 0" GPIO IRQs to AINTC */
 		chips[0].chip.to_irq = gpio_to_irq_unbanked;
@@ -388,9 +394,10 @@ static int __init davinci_gpio_irq_setup(void)
 
 		/* AINTC handles mask/unmask; GPIO handles triggering */
 		irq = bank_irq;
-		gpio_irqchip_unbanked = *irq_get_chip(irq);
-		gpio_irqchip_unbanked.name = "GPIO-AINTC";
-		gpio_irqchip_unbanked.irq_set_type = gpio_irq_type_unbanked;
+		gpio_unbanked = *container_of(irq_get_chip(irq),
+					      struct irq_chip_type, chip);
+		gpio_unbanked.chip.name = "GPIO-AINTC";
+		gpio_unbanked.chip.irq_set_type = gpio_irq_type_unbanked;
 
 		/* default trigger: both edges */
 		g = gpio2regs(0);
@@ -399,9 +406,8 @@ static int __init davinci_gpio_irq_setup(void)
 
 		/* set the direct IRQs up to use that irqchip */
 		for (gpio = 0; gpio < soc_info->gpio_unbanked; gpio++, irq++) {
-			irq_set_chip(irq, &gpio_irqchip_unbanked);
-			irq_set_handler_data(irq, (void *)__gpio_mask(gpio));
-			irq_set_chip_data(irq, (__force void *)g);
+			irq_set_chip(irq, &gpio_unbanked.chip);
+			irq_set_handler_data(irq, &chips[gpio / 32]);
 			irq_set_status_flags(irq, IRQ_TYPE_EDGE_BOTH);
 		}
 
diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c
index 4ca5642e9776..776b772523e5 100644
--- a/drivers/gpio/gpio-ep93xx.c
+++ b/drivers/gpio/gpio-ep93xx.c
@@ -12,8 +12,6 @@
  *  published by the Free Software Foundation.
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -65,11 +63,6 @@ static void ep93xx_gpio_update_int_params(unsigned port)
 		EP93XX_GPIO_REG(int_en_register_offset[port]));
 }
 
-static inline void ep93xx_gpio_int_mask(unsigned line)
-{
-	gpio_int_unmasked[line >> 3] &= ~(1 << (line & 7));
-}
-
 static void ep93xx_gpio_int_debounce(unsigned int irq, bool enable)
 {
 	int line = irq_to_gpio(irq);
@@ -212,7 +205,6 @@ static int ep93xx_gpio_irq_type(struct irq_data *d, unsigned int type)
 		handler = handle_edge_irq;
 		break;
 	default:
-		pr_err("failed to set irq type %d for gpio %d\n", type, gpio);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c
index ddfacc5ce56d..61c2d08d37b6 100644
--- a/drivers/gpio/gpio-lpc32xx.c
+++ b/drivers/gpio/gpio-lpc32xx.c
@@ -59,12 +59,14 @@
 #define GPO3_PIN_TO_BIT(x)			(1 << (x))
 #define GPIO012_PIN_IN_SEL(x, y)		(((x) >> (y)) & 1)
 #define GPIO3_PIN_IN_SHIFT(x)			((x) == 5 ? 24 : 10 + (x))
-#define GPIO3_PIN_IN_SEL(x, y)			((x) >> GPIO3_PIN_IN_SHIFT(y))
+#define GPIO3_PIN_IN_SEL(x, y)			(((x) >> GPIO3_PIN_IN_SHIFT(y)) & 1)
 #define GPIO3_PIN5_IN_SEL(x)			(((x) >> 24) & 1)
 #define GPI3_PIN_IN_SEL(x, y)			(((x) >> (y)) & 1)
+#define GPO3_PIN_IN_SEL(x, y)			(((x) >> (y)) & 1)
 
 struct gpio_regs {
 	void __iomem *inp_state;
+	void __iomem *outp_state;
 	void __iomem *outp_set;
 	void __iomem *outp_clr;
 	void __iomem *dir_set;
@@ -145,6 +147,7 @@ static struct gpio_regs gpio_grp_regs_p2 = {
 
 static struct gpio_regs gpio_grp_regs_p3 = {
 	.inp_state	= LPC32XX_GPIO_P3_INP_STATE,
+	.outp_state	= LPC32XX_GPIO_P3_OUTP_STATE,
 	.outp_set	= LPC32XX_GPIO_P3_OUTP_SET,
 	.outp_clr	= LPC32XX_GPIO_P3_OUTP_CLR,
 	.dir_set	= LPC32XX_GPIO_P2_DIR_SET,
@@ -240,6 +243,12 @@ static int __get_gpi_state_p3(struct lpc32xx_gpio_chip *group,
 	return GPI3_PIN_IN_SEL(__raw_readl(group->gpio_grp->inp_state), pin);
 }
 
+static int __get_gpo_state_p3(struct lpc32xx_gpio_chip *group,
+	unsigned pin)
+{
+	return GPO3_PIN_IN_SEL(__raw_readl(group->gpio_grp->outp_state), pin);
+}
+
 /*
  * GENERIC_GPIO primitives.
  */
@@ -340,6 +349,13 @@ static void lpc32xx_gpo_set_value(struct gpio_chip *chip, unsigned pin,
 	__set_gpo_level_p3(group, pin, value);
 }
 
+static int lpc32xx_gpo_get_value(struct gpio_chip *chip, unsigned pin)
+{
+	struct lpc32xx_gpio_chip *group = to_lpc32xx_gpio(chip);
+
+	return __get_gpo_state_p3(group, pin);
+}
+
 static int lpc32xx_gpio_request(struct gpio_chip *chip, unsigned pin)
 {
 	if (pin < chip->ngpio)
@@ -427,6 +443,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = {
 			.label			= "gpo_p3",
 			.direction_output	= lpc32xx_gpio_dir_out_always,
 			.set			= lpc32xx_gpo_set_value,
+			.get			= lpc32xx_gpo_get_value,
 			.request		= lpc32xx_gpio_request,
 			.base			= LPC32XX_GPO_P3_GRP,
 			.ngpio			= LPC32XX_GPO_P3_MAX,
diff --git a/drivers/gpio/gpio-mc9s08dz60.c b/drivers/gpio/gpio-mc9s08dz60.c
new file mode 100644
index 000000000000..2738cc44d636
--- /dev/null
+++ b/drivers/gpio/gpio-mc9s08dz60.c
@@ -0,0 +1,161 @@
+/*
+ * Copyright 2009-2012 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * Author: Wu Guoxing <b39297@freescale.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+
+#define GPIO_GROUP_NUM 2
+#define GPIO_NUM_PER_GROUP 8
+#define GPIO_NUM (GPIO_GROUP_NUM*GPIO_NUM_PER_GROUP)
+
+struct mc9s08dz60 {
+	struct i2c_client *client;
+	struct gpio_chip chip;
+};
+
+static inline struct mc9s08dz60 *to_mc9s08dz60(struct gpio_chip *gc)
+{
+	return container_of(gc, struct mc9s08dz60, chip);
+}
+
+
+static void mc9s_gpio_to_reg_and_bit(int offset, u8 *reg, u8 *bit)
+{
+	*reg = 0x20 + offset / GPIO_NUM_PER_GROUP;
+	*bit = offset % GPIO_NUM_PER_GROUP;
+}
+
+static int mc9s08dz60_get_value(struct gpio_chip *gc, unsigned offset)
+{
+	u8 reg, bit;
+	s32 value;
+	struct mc9s08dz60 *mc9s = to_mc9s08dz60(gc);
+
+	mc9s_gpio_to_reg_and_bit(offset, &reg, &bit);
+	value = i2c_smbus_read_byte_data(mc9s->client, reg);
+
+	return (value >= 0) ? (value >> bit) & 0x1 : 0;
+}
+
+static int mc9s08dz60_set(struct mc9s08dz60 *mc9s, unsigned offset, int val)
+{
+	u8 reg, bit;
+	s32 value;
+
+	mc9s_gpio_to_reg_and_bit(offset, &reg, &bit);
+	value = i2c_smbus_read_byte_data(mc9s->client, reg);
+	if (value >= 0) {
+		if (val)
+			value |= 1 << bit;
+		else
+			value &= ~(1 << bit);
+
+		return i2c_smbus_write_byte_data(mc9s->client, reg, value);
+	} else
+		return value;
+
+}
+
+
+static void mc9s08dz60_set_value(struct gpio_chip *gc, unsigned offset, int val)
+{
+	struct mc9s08dz60 *mc9s = to_mc9s08dz60(gc);
+
+	mc9s08dz60_set(mc9s, offset, val);
+}
+
+static int mc9s08dz60_direction_output(struct gpio_chip *gc,
+				       unsigned offset, int val)
+{
+	struct mc9s08dz60 *mc9s = to_mc9s08dz60(gc);
+
+	return mc9s08dz60_set(mc9s, offset, val);
+}
+
+static int mc9s08dz60_probe(struct i2c_client *client,
+			    const struct i2c_device_id *id)
+{
+	int ret = 0;
+	struct mc9s08dz60 *mc9s;
+
+	mc9s = kzalloc(sizeof(*mc9s), GFP_KERNEL);
+	if (!mc9s)
+		return -ENOMEM;
+
+	mc9s->chip.label = client->name;
+	mc9s->chip.base = -1;
+	mc9s->chip.dev = &client->dev;
+	mc9s->chip.owner = THIS_MODULE;
+	mc9s->chip.ngpio = GPIO_NUM;
+	mc9s->chip.can_sleep = 1;
+	mc9s->chip.get = mc9s08dz60_get_value;
+	mc9s->chip.set = mc9s08dz60_set_value;
+	mc9s->chip.direction_output = mc9s08dz60_direction_output;
+	mc9s->client = client;
+	i2c_set_clientdata(client, mc9s);
+
+	ret = gpiochip_add(&mc9s->chip);
+	if (ret)
+		goto error;
+
+	return 0;
+
+ error:
+	kfree(mc9s);
+	return ret;
+}
+
+static int mc9s08dz60_remove(struct i2c_client *client)
+{
+	struct mc9s08dz60 *mc9s;
+	int ret;
+
+	mc9s = i2c_get_clientdata(client);
+
+	ret = gpiochip_remove(&mc9s->chip);
+	if (!ret)
+		kfree(mc9s);
+
+	return ret;
+
+}
+
+static const struct i2c_device_id mc9s08dz60_id[] = {
+	{"mc9s08dz60", 0},
+	{},
+};
+
+MODULE_DEVICE_TABLE(i2c, mc9s08dz60_id);
+
+static struct i2c_driver mc9s08dz60_i2c_driver = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "mc9s08dz60",
+	},
+	.probe = mc9s08dz60_probe,
+	.remove = mc9s08dz60_remove,
+	.id_table = mc9s08dz60_id,
+};
+
+module_i2c_driver(mc9s08dz60_i2c_driver);
+
+MODULE_AUTHOR("Freescale Semiconductor, Inc. "
+		"Wu Guoxing <b39297@freescale.com>");
+MODULE_DESCRIPTION("mc9s08dz60 gpio function on mx35 3ds board");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index f49bd6f47a50..1adc2ec1e383 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -19,9 +19,12 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
-#include <linux/slab.h>
+#include <linux/device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/irqdomain.h>
 
 #include <mach/hardware.h>
 #include <asm/irq.h>
@@ -50,10 +53,10 @@ struct gpio_regs {
 
 struct gpio_bank {
 	struct list_head node;
-	unsigned long pbase;
 	void __iomem *base;
 	u16 irq;
-	u16 virtual_irq_start;
+	int irq_base;
+	struct irq_domain *domain;
 	u32 suspend_wakeup;
 	u32 saved_wakeup;
 	u32 non_wakeup_gpios;
@@ -77,7 +80,6 @@ struct gpio_bank {
 	int stride;
 	u32 width;
 	int context_loss_count;
-	u16 id;
 	int power_mode;
 	bool workaround_enabled;
 
@@ -91,6 +93,11 @@ struct gpio_bank {
 #define GPIO_BIT(bank, gpio) (1 << GPIO_INDEX(bank, gpio))
 #define GPIO_MOD_CTRL_BIT	BIT(0)
 
+static int irq_to_gpio(struct gpio_bank *bank, unsigned int gpio_irq)
+{
+	return gpio_irq - bank->irq_base + bank->chip.base;
+}
+
 static void _set_gpio_direction(struct gpio_bank *bank, int gpio, int is_input)
 {
 	void __iomem *reg = bank->base;
@@ -113,10 +120,13 @@ static void _set_gpio_dataout_reg(struct gpio_bank *bank, int gpio, int enable)
 	void __iomem *reg = bank->base;
 	u32 l = GPIO_BIT(bank, gpio);
 
-	if (enable)
+	if (enable) {
 		reg += bank->regs->set_dataout;
-	else
+		bank->context.dataout |= l;
+	} else {
 		reg += bank->regs->clr_dataout;
+		bank->context.dataout &= ~l;
+	}
 
 	__raw_writel(l, reg);
 }
@@ -137,25 +147,25 @@ static void _set_gpio_dataout_mask(struct gpio_bank *bank, int gpio, int enable)
 	bank->context.dataout = l;
 }
 
-static int _get_gpio_datain(struct gpio_bank *bank, int gpio)
+static int _get_gpio_datain(struct gpio_bank *bank, int offset)
 {
 	void __iomem *reg = bank->base + bank->regs->datain;
 
-	return (__raw_readl(reg) & GPIO_BIT(bank, gpio)) != 0;
+	return (__raw_readl(reg) & (1 << offset)) != 0;
 }
 
-static int _get_gpio_dataout(struct gpio_bank *bank, int gpio)
+static int _get_gpio_dataout(struct gpio_bank *bank, int offset)
 {
 	void __iomem *reg = bank->base + bank->regs->dataout;
 
-	return (__raw_readl(reg) & GPIO_BIT(bank, gpio)) != 0;
+	return (__raw_readl(reg) & (1 << offset)) != 0;
 }
 
 static inline void _gpio_rmw(void __iomem *base, u32 reg, u32 mask, bool set)
 {
 	int l = __raw_readl(base + reg);
 
-	if (set) 
+	if (set)
 		l |= mask;
 	else
 		l &= ~mask;
@@ -238,7 +248,7 @@ static void _set_gpio_debounce(struct gpio_bank *bank, unsigned gpio,
 }
 
 static inline void set_gpio_trigger(struct gpio_bank *bank, int gpio,
-						int trigger)
+						unsigned trigger)
 {
 	void __iomem *base = bank->base;
 	u32 gpio_bit = 1 << gpio;
@@ -320,7 +330,8 @@ static void _toggle_gpio_edge_triggering(struct gpio_bank *bank, int gpio)
 static void _toggle_gpio_edge_triggering(struct gpio_bank *bank, int gpio) {}
 #endif
 
-static int _set_gpio_triggering(struct gpio_bank *bank, int gpio, int trigger)
+static int _set_gpio_triggering(struct gpio_bank *bank, int gpio,
+							unsigned trigger)
 {
 	void __iomem *reg = bank->base;
 	void __iomem *base = bank->base;
@@ -367,7 +378,7 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio, int trigger)
 
 static int gpio_irq_type(struct irq_data *d, unsigned type)
 {
-	struct gpio_bank *bank;
+	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned gpio;
 	int retval;
 	unsigned long flags;
@@ -375,13 +386,11 @@ static int gpio_irq_type(struct irq_data *d, unsigned type)
 	if (!cpu_class_is_omap2() && d->irq > IH_MPUIO_BASE)
 		gpio = OMAP_MPUIO(d->irq - IH_MPUIO_BASE);
 	else
-		gpio = d->irq - IH_GPIO_BASE;
+		gpio = irq_to_gpio(bank, d->irq);
 
 	if (type & ~IRQ_TYPE_SENSE_MASK)
 		return -EINVAL;
 
-	bank = irq_data_get_irq_chip_data(d);
-
 	if (!bank->regs->leveldetect0 &&
 		(type & (IRQ_TYPE_LEVEL_LOW|IRQ_TYPE_LEVEL_HIGH)))
 		return -EINVAL;
@@ -442,6 +451,7 @@ static void _enable_gpio_irqbank(struct gpio_bank *bank, int gpio_mask)
 	if (bank->regs->set_irqenable) {
 		reg += bank->regs->set_irqenable;
 		l = gpio_mask;
+		bank->context.irqenable1 |= gpio_mask;
 	} else {
 		reg += bank->regs->irqenable;
 		l = __raw_readl(reg);
@@ -449,10 +459,10 @@ static void _enable_gpio_irqbank(struct gpio_bank *bank, int gpio_mask)
 			l &= ~gpio_mask;
 		else
 			l |= gpio_mask;
+		bank->context.irqenable1 = l;
 	}
 
 	__raw_writel(l, reg);
-	bank->context.irqenable1 = l;
 }
 
 static void _disable_gpio_irqbank(struct gpio_bank *bank, int gpio_mask)
@@ -463,6 +473,7 @@ static void _disable_gpio_irqbank(struct gpio_bank *bank, int gpio_mask)
 	if (bank->regs->clr_irqenable) {
 		reg += bank->regs->clr_irqenable;
 		l = gpio_mask;
+		bank->context.irqenable1 &= ~gpio_mask;
 	} else {
 		reg += bank->regs->irqenable;
 		l = __raw_readl(reg);
@@ -470,15 +481,18 @@ static void _disable_gpio_irqbank(struct gpio_bank *bank, int gpio_mask)
 			l |= gpio_mask;
 		else
 			l &= ~gpio_mask;
+		bank->context.irqenable1 = l;
 	}
 
 	__raw_writel(l, reg);
-	bank->context.irqenable1 = l;
 }
 
 static inline void _set_gpio_irqenable(struct gpio_bank *bank, int gpio, int enable)
 {
-	_enable_gpio_irqbank(bank, GPIO_BIT(bank, gpio));
+	if (enable)
+		_enable_gpio_irqbank(bank, GPIO_BIT(bank, gpio));
+	else
+		_disable_gpio_irqbank(bank, GPIO_BIT(bank, gpio));
 }
 
 /*
@@ -495,7 +509,7 @@ static int _set_gpio_wakeup(struct gpio_bank *bank, int gpio, int enable)
 	unsigned long flags;
 
 	if (bank->non_wakeup_gpios & gpio_bit) {
-		dev_err(bank->dev, 
+		dev_err(bank->dev,
 			"Unable to modify wakeup on non-wakeup GPIO%d\n", gpio);
 		return -EINVAL;
 	}
@@ -506,6 +520,7 @@ static int _set_gpio_wakeup(struct gpio_bank *bank, int gpio, int enable)
 	else
 		bank->suspend_wakeup &= ~gpio_bit;
 
+	__raw_writel(bank->suspend_wakeup, bank->base + bank->regs->wkup_en);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
@@ -522,14 +537,10 @@ static void _reset_gpio(struct gpio_bank *bank, int gpio)
 /* Use disable_irq_wake() and enable_irq_wake() functions from drivers */
 static int gpio_wake_enable(struct irq_data *d, unsigned int enable)
 {
-	unsigned int gpio = d->irq - IH_GPIO_BASE;
-	struct gpio_bank *bank;
-	int retval;
-
-	bank = irq_data_get_irq_chip_data(d);
-	retval = _set_gpio_wakeup(bank, gpio, enable);
+	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned int gpio = irq_to_gpio(bank, d->irq);
 
-	return retval;
+	return _set_gpio_wakeup(bank, gpio, enable);
 }
 
 static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
@@ -671,13 +682,15 @@ static void gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 		if (!isr)
 			break;
 
-		gpio_irq = bank->virtual_irq_start;
+		gpio_irq = bank->irq_base;
 		for (; isr != 0; isr >>= 1, gpio_irq++) {
-			gpio_index = GPIO_INDEX(bank, irq_to_gpio(gpio_irq));
+			int gpio = irq_to_gpio(bank, gpio_irq);
 
 			if (!(isr & 1))
 				continue;
 
+			gpio_index = GPIO_INDEX(bank, gpio);
+
 			/*
 			 * Some chips can't respond to both rising and falling
 			 * at the same time.  If this irq was requested with
@@ -703,8 +716,8 @@ exit:
 
 static void gpio_irq_shutdown(struct irq_data *d)
 {
-	unsigned int gpio = d->irq - IH_GPIO_BASE;
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned int gpio = irq_to_gpio(bank, d->irq);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bank->lock, flags);
@@ -714,16 +727,16 @@ static void gpio_irq_shutdown(struct irq_data *d)
 
 static void gpio_ack_irq(struct irq_data *d)
 {
-	unsigned int gpio = d->irq - IH_GPIO_BASE;
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned int gpio = irq_to_gpio(bank, d->irq);
 
 	_clear_gpio_irqstatus(bank, gpio);
 }
 
 static void gpio_mask_irq(struct irq_data *d)
 {
-	unsigned int gpio = d->irq - IH_GPIO_BASE;
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned int gpio = irq_to_gpio(bank, d->irq);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bank->lock, flags);
@@ -734,8 +747,8 @@ static void gpio_mask_irq(struct irq_data *d)
 
 static void gpio_unmask_irq(struct irq_data *d)
 {
-	unsigned int gpio = d->irq - IH_GPIO_BASE;
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned int gpio = irq_to_gpio(bank, d->irq);
 	unsigned int irq_mask = GPIO_BIT(bank, gpio);
 	u32 trigger = irqd_get_trigger_type(d);
 	unsigned long flags;
@@ -852,19 +865,15 @@ static int gpio_is_input(struct gpio_bank *bank, int mask)
 static int gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct gpio_bank *bank;
-	void __iomem *reg;
-	int gpio;
 	u32 mask;
 
-	gpio = chip->base + offset;
 	bank = container_of(chip, struct gpio_bank, chip);
-	reg = bank->base;
-	mask = GPIO_BIT(bank, gpio);
+	mask = (1 << offset);
 
 	if (gpio_is_input(bank, mask))
-		return _get_gpio_datain(bank, gpio);
+		return _get_gpio_datain(bank, offset);
 	else
-		return _get_gpio_dataout(bank, gpio);
+		return _get_gpio_dataout(bank, offset);
 }
 
 static int gpio_output(struct gpio_chip *chip, unsigned offset, int value)
@@ -917,7 +926,7 @@ static int gpio_2irq(struct gpio_chip *chip, unsigned offset)
 	struct gpio_bank *bank;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	return bank->virtual_irq_start + offset;
+	return bank->irq_base + offset;
 }
 
 /*---------------------------------------------------------------------*/
@@ -970,7 +979,7 @@ static void omap_gpio_mod_init(struct gpio_bank *bank)
 		_gpio_rmw(base, bank->regs->ctrl, 0, 1);
 }
 
-static __init void
+static __devinit void
 omap_mpuio_alloc_gc(struct gpio_bank *bank, unsigned int irq_start,
 		    unsigned int num)
 {
@@ -1030,8 +1039,7 @@ static void __devinit omap_gpio_chip_init(struct gpio_bank *bank)
 
 	gpiochip_add(&bank->chip);
 
-	for (j = bank->virtual_irq_start;
-		     j < bank->virtual_irq_start + bank->width; j++) {
+	for (j = bank->irq_base; j < bank->irq_base + bank->width; j++) {
 		irq_set_lockdep_class(j, &gpio_lock_class);
 		irq_set_chip_data(j, bank);
 		if (bank->is_mpuio) {
@@ -1046,39 +1054,38 @@ static void __devinit omap_gpio_chip_init(struct gpio_bank *bank)
 	irq_set_handler_data(bank->irq, bank);
 }
 
+static const struct of_device_id omap_gpio_match[];
+
 static int __devinit omap_gpio_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
+	struct device_node *node = dev->of_node;
+	const struct of_device_id *match;
 	struct omap_gpio_platform_data *pdata;
 	struct resource *res;
 	struct gpio_bank *bank;
 	int ret = 0;
 
-	if (!pdev->dev.platform_data) {
-		ret = -EINVAL;
-		goto err_exit;
-	}
+	match = of_match_device(of_match_ptr(omap_gpio_match), dev);
+
+	pdata = match ? match->data : dev->platform_data;
+	if (!pdata)
+		return -EINVAL;
 
-	bank = kzalloc(sizeof(struct gpio_bank), GFP_KERNEL);
+	bank = devm_kzalloc(&pdev->dev, sizeof(struct gpio_bank), GFP_KERNEL);
 	if (!bank) {
-		dev_err(&pdev->dev, "Memory alloc failed for gpio_bank\n");
-		ret = -ENOMEM;
-		goto err_exit;
+		dev_err(dev, "Memory alloc failed\n");
+		return -ENOMEM;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (unlikely(!res)) {
-		dev_err(&pdev->dev, "GPIO Bank %i Invalid IRQ resource\n",
-				pdev->id);
-		ret = -ENODEV;
-		goto err_free;
+		dev_err(dev, "Invalid IRQ resource\n");
+		return -ENODEV;
 	}
 
 	bank->irq = res->start;
-	bank->id = pdev->id;
-
-	pdata = pdev->dev.platform_data;
-	bank->virtual_irq_start = pdata->virtual_irq_start;
-	bank->dev = &pdev->dev;
+	bank->dev = dev;
 	bank->dbck_flag = pdata->dbck_flag;
 	bank->stride = pdata->bank_stride;
 	bank->width = pdata->bank_width;
@@ -1087,6 +1094,18 @@ static int __devinit omap_gpio_probe(struct platform_device *pdev)
 	bank->loses_context = pdata->loses_context;
 	bank->get_context_loss_count = pdata->get_context_loss_count;
 	bank->regs = pdata->regs;
+#ifdef CONFIG_OF_GPIO
+	bank->chip.of_node = of_node_get(node);
+#endif
+
+	bank->irq_base = irq_alloc_descs(-1, 0, bank->width, 0);
+	if (bank->irq_base < 0) {
+		dev_err(dev, "Couldn't allocate IRQ numbers\n");
+		return -ENODEV;
+	}
+
+	bank->domain = irq_domain_add_legacy(node, bank->width, bank->irq_base,
+					     0, &irq_domain_simple_ops, NULL);
 
 	if (bank->regs->set_dataout && bank->regs->clr_dataout)
 		bank->set_dataout = _set_gpio_dataout_reg;
@@ -1098,18 +1117,20 @@ static int __devinit omap_gpio_probe(struct platform_device *pdev)
 	/* Static mapping, never released */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (unlikely(!res)) {
-		dev_err(&pdev->dev, "GPIO Bank %i Invalid mem resource\n",
-				pdev->id);
-		ret = -ENODEV;
-		goto err_free;
+		dev_err(dev, "Invalid mem resource\n");
+		return -ENODEV;
 	}
 
-	bank->base = ioremap(res->start, resource_size(res));
+	if (!devm_request_mem_region(dev, res->start, resource_size(res),
+				     pdev->name)) {
+		dev_err(dev, "Region already claimed\n");
+		return -EBUSY;
+	}
+
+	bank->base = devm_ioremap(dev, res->start, resource_size(res));
 	if (!bank->base) {
-		dev_err(&pdev->dev, "Could not ioremap gpio bank%i\n",
-				pdev->id);
-		ret = -ENOMEM;
-		goto err_free;
+		dev_err(dev, "Could not ioremap\n");
+		return -ENOMEM;
 	}
 
 	platform_set_drvdata(pdev, bank);
@@ -1130,11 +1151,6 @@ static int __devinit omap_gpio_probe(struct platform_device *pdev)
 	list_add_tail(&bank->node, &omap_gpio_list);
 
 	return ret;
-
-err_free:
-	kfree(bank);
-err_exit:
-	return ret;
 }
 
 #ifdef CONFIG_ARCH_OMAP2PLUS
@@ -1196,8 +1212,30 @@ static int omap_gpio_runtime_suspend(struct device *dev)
 	struct gpio_bank *bank = platform_get_drvdata(pdev);
 	u32 l1 = 0, l2 = 0;
 	unsigned long flags;
+	u32 wake_low, wake_hi;
 
 	spin_lock_irqsave(&bank->lock, flags);
+
+	/*
+	 * Only edges can generate a wakeup event to the PRCM.
+	 *
+	 * Therefore, ensure any wake-up capable GPIOs have
+	 * edge-detection enabled before going idle to ensure a wakeup
+	 * to the PRCM is generated on a GPIO transition. (c.f. 34xx
+	 * NDA TRM 25.5.3.1)
+	 *
+	 * The normal values will be restored upon ->runtime_resume()
+	 * by writing back the values saved in bank->context.
+	 */
+	wake_low = bank->context.leveldetect0 & bank->context.wake_en;
+	if (wake_low)
+		__raw_writel(wake_low | bank->context.fallingdetect,
+			     bank->base + bank->regs->fallingdetect);
+	wake_hi = bank->context.leveldetect1 & bank->context.wake_en;
+	if (wake_hi)
+		__raw_writel(wake_hi | bank->context.risingdetect,
+			     bank->base + bank->regs->risingdetect);
+
 	if (bank->power_mode != OFF_MODE) {
 		bank->power_mode = 0;
 		goto update_gpio_context_count;
@@ -1207,9 +1245,6 @@ static int omap_gpio_runtime_suspend(struct device *dev)
 	 * non-wakeup GPIOs.  Otherwise spurious IRQs will be
 	 * generated.  See OMAP2420 Errata item 1.101.
 	 */
-	if (!(bank->enabled_non_wakeup_gpios))
-		goto update_gpio_context_count;
-
 	bank->saved_datain = __raw_readl(bank->base +
 						bank->regs->datain);
 	l1 = __raw_readl(bank->base + bank->regs->fallingdetect);
@@ -1246,7 +1281,19 @@ static int omap_gpio_runtime_resume(struct device *dev)
 
 	spin_lock_irqsave(&bank->lock, flags);
 	_gpio_dbck_enable(bank);
-	if (!bank->enabled_non_wakeup_gpios || !bank->workaround_enabled) {
+
+	/*
+	 * In ->runtime_suspend(), level-triggered, wakeup-enabled
+	 * GPIOs were set to edge trigger also in order to be able to
+	 * generate a PRCM wakeup.  Here we restore the
+	 * pre-runtime_suspend() values for edge triggering.
+	 */
+	__raw_writel(bank->context.fallingdetect,
+		     bank->base + bank->regs->fallingdetect);
+	__raw_writel(bank->context.risingdetect,
+		     bank->base + bank->regs->risingdetect);
+
+	if (!bank->workaround_enabled) {
 		spin_unlock_irqrestore(&bank->lock, flags);
 		return 0;
 	}
@@ -1397,11 +1444,95 @@ static const struct dev_pm_ops gpio_pm_ops = {
 									NULL)
 };
 
+#if defined(CONFIG_OF)
+static struct omap_gpio_reg_offs omap2_gpio_regs = {
+	.revision =		OMAP24XX_GPIO_REVISION,
+	.direction =		OMAP24XX_GPIO_OE,
+	.datain =		OMAP24XX_GPIO_DATAIN,
+	.dataout =		OMAP24XX_GPIO_DATAOUT,
+	.set_dataout =		OMAP24XX_GPIO_SETDATAOUT,
+	.clr_dataout =		OMAP24XX_GPIO_CLEARDATAOUT,
+	.irqstatus =		OMAP24XX_GPIO_IRQSTATUS1,
+	.irqstatus2 =		OMAP24XX_GPIO_IRQSTATUS2,
+	.irqenable =		OMAP24XX_GPIO_IRQENABLE1,
+	.irqenable2 =		OMAP24XX_GPIO_IRQENABLE2,
+	.set_irqenable =	OMAP24XX_GPIO_SETIRQENABLE1,
+	.clr_irqenable =	OMAP24XX_GPIO_CLEARIRQENABLE1,
+	.debounce =		OMAP24XX_GPIO_DEBOUNCE_VAL,
+	.debounce_en =		OMAP24XX_GPIO_DEBOUNCE_EN,
+	.ctrl =			OMAP24XX_GPIO_CTRL,
+	.wkup_en =		OMAP24XX_GPIO_WAKE_EN,
+	.leveldetect0 =		OMAP24XX_GPIO_LEVELDETECT0,
+	.leveldetect1 =		OMAP24XX_GPIO_LEVELDETECT1,
+	.risingdetect =		OMAP24XX_GPIO_RISINGDETECT,
+	.fallingdetect =	OMAP24XX_GPIO_FALLINGDETECT,
+};
+
+static struct omap_gpio_reg_offs omap4_gpio_regs = {
+	.revision =		OMAP4_GPIO_REVISION,
+	.direction =		OMAP4_GPIO_OE,
+	.datain =		OMAP4_GPIO_DATAIN,
+	.dataout =		OMAP4_GPIO_DATAOUT,
+	.set_dataout =		OMAP4_GPIO_SETDATAOUT,
+	.clr_dataout =		OMAP4_GPIO_CLEARDATAOUT,
+	.irqstatus =		OMAP4_GPIO_IRQSTATUS0,
+	.irqstatus2 =		OMAP4_GPIO_IRQSTATUS1,
+	.irqenable =		OMAP4_GPIO_IRQSTATUSSET0,
+	.irqenable2 =		OMAP4_GPIO_IRQSTATUSSET1,
+	.set_irqenable =	OMAP4_GPIO_IRQSTATUSSET0,
+	.clr_irqenable =	OMAP4_GPIO_IRQSTATUSCLR0,
+	.debounce =		OMAP4_GPIO_DEBOUNCINGTIME,
+	.debounce_en =		OMAP4_GPIO_DEBOUNCENABLE,
+	.ctrl =			OMAP4_GPIO_CTRL,
+	.wkup_en =		OMAP4_GPIO_IRQWAKEN0,
+	.leveldetect0 =		OMAP4_GPIO_LEVELDETECT0,
+	.leveldetect1 =		OMAP4_GPIO_LEVELDETECT1,
+	.risingdetect =		OMAP4_GPIO_RISINGDETECT,
+	.fallingdetect =	OMAP4_GPIO_FALLINGDETECT,
+};
+
+static struct omap_gpio_platform_data omap2_pdata = {
+	.regs = &omap2_gpio_regs,
+	.bank_width = 32,
+	.dbck_flag = false,
+};
+
+static struct omap_gpio_platform_data omap3_pdata = {
+	.regs = &omap2_gpio_regs,
+	.bank_width = 32,
+	.dbck_flag = true,
+};
+
+static struct omap_gpio_platform_data omap4_pdata = {
+	.regs = &omap4_gpio_regs,
+	.bank_width = 32,
+	.dbck_flag = true,
+};
+
+static const struct of_device_id omap_gpio_match[] = {
+	{
+		.compatible = "ti,omap4-gpio",
+		.data = &omap4_pdata,
+	},
+	{
+		.compatible = "ti,omap3-gpio",
+		.data = &omap3_pdata,
+	},
+	{
+		.compatible = "ti,omap2-gpio",
+		.data = &omap2_pdata,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, omap_gpio_match);
+#endif
+
 static struct platform_driver omap_gpio_driver = {
 	.probe		= omap_gpio_probe,
 	.driver		= {
 		.name	= "omap_gpio",
 		.pm	= &gpio_pm_ops,
+		.of_match_table = of_match_ptr(omap_gpio_match),
 	},
 };
 
diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c
index 77c9cc70fa77..b4b5da4fd2cc 100644
--- a/drivers/gpio/gpio-pl061.c
+++ b/drivers/gpio/gpio-pl061.c
@@ -352,7 +352,12 @@ static int pl061_resume(struct device *dev)
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(pl061_dev_pm_ops, pl061_suspend, pl061_resume);
+static const struct dev_pm_ops pl061_dev_pm_ops = {
+	.suspend = pl061_suspend,
+	.resume = pl061_resume,
+	.freeze = pl061_suspend,
+	.restore = pl061_resume,
+};
 #endif
 
 static struct amba_id pl061_ids[] = {
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index b2d3ee1d183a..5689ce62fd81 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -22,6 +22,8 @@
 #include <linux/syscore_ops.h>
 #include <linux/slab.h>
 
+#include <mach/irqs.h>
+
 /*
  * We handle the GPIOs by banks, each bank covers up to 32 GPIOs with
  * one set of registers. The register offsets are organized below:
diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c
index 7eecf69362ee..8ea3b33d4b40 100644
--- a/drivers/gpio/gpio-sa1100.c
+++ b/drivers/gpio/gpio-sa1100.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 
 static int sa1100_gpio_get(struct gpio_chip *chip, unsigned offset)
 {
diff --git a/drivers/gpio/gpio-samsung.c b/drivers/gpio/gpio-samsung.c
index 0a79a1167a25..46277877b7ec 100644
--- a/drivers/gpio/gpio-samsung.c
+++ b/drivers/gpio/gpio-samsung.c
@@ -169,7 +169,7 @@ int s3c24xx_gpio_setpull_1down(struct samsung_gpio_chip *chip,
 	return s3c24xx_gpio_setpull_1(chip, off, pull, S3C_GPIO_PULL_DOWN);
 }
 
-static int exynos4_gpio_setpull(struct samsung_gpio_chip *chip,
+static int exynos_gpio_setpull(struct samsung_gpio_chip *chip,
 				unsigned int off, samsung_gpio_pull_t pull)
 {
 	if (pull == S3C_GPIO_PULL_UP)
@@ -178,7 +178,7 @@ static int exynos4_gpio_setpull(struct samsung_gpio_chip *chip,
 	return samsung_gpio_setpull_updown(chip, off, pull);
 }
 
-static samsung_gpio_pull_t exynos4_gpio_getpull(struct samsung_gpio_chip *chip,
+static samsung_gpio_pull_t exynos_gpio_getpull(struct samsung_gpio_chip *chip,
 						unsigned int off)
 {
 	samsung_gpio_pull_t pull;
@@ -452,9 +452,9 @@ static struct samsung_gpio_cfg s3c24xx_gpiocfg_banka = {
 };
 #endif
 
-static struct samsung_gpio_cfg exynos4_gpio_cfg = {
-	.set_pull	= exynos4_gpio_setpull,
-	.get_pull	= exynos4_gpio_getpull,
+static struct samsung_gpio_cfg exynos_gpio_cfg = {
+	.set_pull	= exynos_gpio_setpull,
+	.get_pull	= exynos_gpio_getpull,
 	.set_config	= samsung_gpio_setcfg_4bit,
 	.get_config	= samsung_gpio_getcfg_4bit,
 };
@@ -502,13 +502,13 @@ static struct samsung_gpio_cfg samsung_gpio_cfgs[] = {
 		.get_config	= samsung_gpio_getcfg_2bit,
 	},
 	[8] = {
-		.set_pull	= exynos4_gpio_setpull,
-		.get_pull	= exynos4_gpio_getpull,
+		.set_pull	= exynos_gpio_setpull,
+		.get_pull	= exynos_gpio_getpull,
 	},
 	[9] = {
 		.cfg_eint	= 0x3,
-		.set_pull	= exynos4_gpio_setpull,
-		.get_pull	= exynos4_gpio_getpull,
+		.set_pull	= exynos_gpio_setpull,
+		.get_pull	= exynos_gpio_getpull,
 	}
 };
 
@@ -2113,10 +2113,10 @@ static struct samsung_gpio_chip s5pv210_gpios_4bit[] = {
 };
 
 /*
- * Followings are the gpio banks in EXYNOS4210
+ * Followings are the gpio banks in EXYNOS SoCs
  *
  * The 'config' member when left to NULL, is initialized to the default
- * structure samsung_gpio_cfgs[3] in the init function below.
+ * structure exynos_gpio_cfg in the init function below.
  *
  * The 'base' member is also initialized in the init function below.
  * Note: The initialization of 'base' member of samsung_gpio_chip structure
@@ -2331,7 +2331,6 @@ static struct samsung_gpio_chip exynos4_gpios_2[] = {
 			.label	= "GPY6",
 		},
 	}, {
-		.base	= (S5P_VA_GPIO2 + 0xC00),
 		.config	= &samsung_gpio_cfgs[9],
 		.irq_base = IRQ_EINT(0),
 		.chip	= {
@@ -2341,7 +2340,6 @@ static struct samsung_gpio_chip exynos4_gpios_2[] = {
 			.to_irq	= samsung_gpiolib_to_irq,
 		},
 	}, {
-		.base	= (S5P_VA_GPIO2 + 0xC20),
 		.config	= &samsung_gpio_cfgs[9],
 		.irq_base = IRQ_EINT(8),
 		.chip	= {
@@ -2351,7 +2349,6 @@ static struct samsung_gpio_chip exynos4_gpios_2[] = {
 			.to_irq	= samsung_gpiolib_to_irq,
 		},
 	}, {
-		.base	= (S5P_VA_GPIO2 + 0xC40),
 		.config	= &samsung_gpio_cfgs[9],
 		.irq_base = IRQ_EINT(16),
 		.chip	= {
@@ -2361,7 +2358,6 @@ static struct samsung_gpio_chip exynos4_gpios_2[] = {
 			.to_irq	= samsung_gpiolib_to_irq,
 		},
 	}, {
-		.base	= (S5P_VA_GPIO2 + 0xC60),
 		.config	= &samsung_gpio_cfgs[9],
 		.irq_base = IRQ_EINT(24),
 		.chip	= {
@@ -2386,8 +2382,280 @@ static struct samsung_gpio_chip exynos4_gpios_3[] = {
 #endif
 };
 
-#if defined(CONFIG_ARCH_EXYNOS4) && defined(CONFIG_OF)
-static int exynos4_gpio_xlate(struct gpio_chip *gc,
+static struct samsung_gpio_chip exynos5_gpios_1[] = {
+#ifdef CONFIG_ARCH_EXYNOS5
+	{
+		.chip	= {
+			.base	= EXYNOS5_GPA0(0),
+			.ngpio	= EXYNOS5_GPIO_A0_NR,
+			.label	= "GPA0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPA1(0),
+			.ngpio	= EXYNOS5_GPIO_A1_NR,
+			.label	= "GPA1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPA2(0),
+			.ngpio	= EXYNOS5_GPIO_A2_NR,
+			.label	= "GPA2",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPB0(0),
+			.ngpio	= EXYNOS5_GPIO_B0_NR,
+			.label	= "GPB0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPB1(0),
+			.ngpio	= EXYNOS5_GPIO_B1_NR,
+			.label	= "GPB1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPB2(0),
+			.ngpio	= EXYNOS5_GPIO_B2_NR,
+			.label	= "GPB2",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPB3(0),
+			.ngpio	= EXYNOS5_GPIO_B3_NR,
+			.label	= "GPB3",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPC0(0),
+			.ngpio	= EXYNOS5_GPIO_C0_NR,
+			.label	= "GPC0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPC1(0),
+			.ngpio	= EXYNOS5_GPIO_C1_NR,
+			.label	= "GPC1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPC2(0),
+			.ngpio	= EXYNOS5_GPIO_C2_NR,
+			.label	= "GPC2",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPC3(0),
+			.ngpio	= EXYNOS5_GPIO_C3_NR,
+			.label	= "GPC3",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPD0(0),
+			.ngpio	= EXYNOS5_GPIO_D0_NR,
+			.label	= "GPD0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPD1(0),
+			.ngpio	= EXYNOS5_GPIO_D1_NR,
+			.label	= "GPD1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPY0(0),
+			.ngpio	= EXYNOS5_GPIO_Y0_NR,
+			.label	= "GPY0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPY1(0),
+			.ngpio	= EXYNOS5_GPIO_Y1_NR,
+			.label	= "GPY1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPY2(0),
+			.ngpio	= EXYNOS5_GPIO_Y2_NR,
+			.label	= "GPY2",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPY3(0),
+			.ngpio	= EXYNOS5_GPIO_Y3_NR,
+			.label	= "GPY3",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPY4(0),
+			.ngpio	= EXYNOS5_GPIO_Y4_NR,
+			.label	= "GPY4",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPY5(0),
+			.ngpio	= EXYNOS5_GPIO_Y5_NR,
+			.label	= "GPY5",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPY6(0),
+			.ngpio	= EXYNOS5_GPIO_Y6_NR,
+			.label	= "GPY6",
+		},
+	}, {
+		.config	= &samsung_gpio_cfgs[9],
+		.irq_base = IRQ_EINT(0),
+		.chip	= {
+			.base	= EXYNOS5_GPX0(0),
+			.ngpio	= EXYNOS5_GPIO_X0_NR,
+			.label	= "GPX0",
+			.to_irq	= samsung_gpiolib_to_irq,
+		},
+	}, {
+		.config	= &samsung_gpio_cfgs[9],
+		.irq_base = IRQ_EINT(8),
+		.chip	= {
+			.base	= EXYNOS5_GPX1(0),
+			.ngpio	= EXYNOS5_GPIO_X1_NR,
+			.label	= "GPX1",
+			.to_irq	= samsung_gpiolib_to_irq,
+		},
+	}, {
+		.config	= &samsung_gpio_cfgs[9],
+		.irq_base = IRQ_EINT(16),
+		.chip	= {
+			.base	= EXYNOS5_GPX2(0),
+			.ngpio	= EXYNOS5_GPIO_X2_NR,
+			.label	= "GPX2",
+			.to_irq	= samsung_gpiolib_to_irq,
+		},
+	}, {
+		.config	= &samsung_gpio_cfgs[9],
+		.irq_base = IRQ_EINT(24),
+		.chip	= {
+			.base	= EXYNOS5_GPX3(0),
+			.ngpio	= EXYNOS5_GPIO_X3_NR,
+			.label	= "GPX3",
+			.to_irq	= samsung_gpiolib_to_irq,
+		},
+	},
+#endif
+};
+
+static struct samsung_gpio_chip exynos5_gpios_2[] = {
+#ifdef CONFIG_ARCH_EXYNOS5
+	{
+		.chip	= {
+			.base	= EXYNOS5_GPE0(0),
+			.ngpio	= EXYNOS5_GPIO_E0_NR,
+			.label	= "GPE0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPE1(0),
+			.ngpio	= EXYNOS5_GPIO_E1_NR,
+			.label	= "GPE1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPF0(0),
+			.ngpio	= EXYNOS5_GPIO_F0_NR,
+			.label	= "GPF0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPF1(0),
+			.ngpio	= EXYNOS5_GPIO_F1_NR,
+			.label	= "GPF1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPG0(0),
+			.ngpio	= EXYNOS5_GPIO_G0_NR,
+			.label	= "GPG0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPG1(0),
+			.ngpio	= EXYNOS5_GPIO_G1_NR,
+			.label	= "GPG1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPG2(0),
+			.ngpio	= EXYNOS5_GPIO_G2_NR,
+			.label	= "GPG2",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPH0(0),
+			.ngpio	= EXYNOS5_GPIO_H0_NR,
+			.label	= "GPH0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPH1(0),
+			.ngpio	= EXYNOS5_GPIO_H1_NR,
+			.label	= "GPH1",
+
+		},
+	},
+#endif
+};
+
+static struct samsung_gpio_chip exynos5_gpios_3[] = {
+#ifdef CONFIG_ARCH_EXYNOS5
+	{
+		.chip	= {
+			.base	= EXYNOS5_GPV0(0),
+			.ngpio	= EXYNOS5_GPIO_V0_NR,
+			.label	= "GPV0",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPV1(0),
+			.ngpio	= EXYNOS5_GPIO_V1_NR,
+			.label	= "GPV1",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPV2(0),
+			.ngpio	= EXYNOS5_GPIO_V2_NR,
+			.label	= "GPV2",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPV3(0),
+			.ngpio	= EXYNOS5_GPIO_V3_NR,
+			.label	= "GPV3",
+		},
+	}, {
+		.chip	= {
+			.base	= EXYNOS5_GPV4(0),
+			.ngpio	= EXYNOS5_GPIO_V4_NR,
+			.label	= "GPV4",
+		},
+	},
+#endif
+};
+
+static struct samsung_gpio_chip exynos5_gpios_4[] = {
+#ifdef CONFIG_ARCH_EXYNOS5
+	{
+		.chip	= {
+			.base	= EXYNOS5_GPZ(0),
+			.ngpio	= EXYNOS5_GPIO_Z_NR,
+			.label	= "GPZ",
+		},
+	},
+#endif
+};
+
+
+#if defined(CONFIG_ARCH_EXYNOS) && defined(CONFIG_OF)
+static int exynos_gpio_xlate(struct gpio_chip *gc,
 			const struct of_phandle_args *gpiospec, u32 *flags)
 {
 	unsigned int pin;
@@ -2413,13 +2681,13 @@ static int exynos4_gpio_xlate(struct gpio_chip *gc,
 	return gpiospec->args[0];
 }
 
-static const struct of_device_id exynos4_gpio_dt_match[] __initdata = {
+static const struct of_device_id exynos_gpio_dt_match[] __initdata = {
 	{ .compatible = "samsung,exynos4-gpio", },
 	{}
 };
 
-static __init void exynos4_gpiolib_attach_ofnode(struct samsung_gpio_chip *chip,
-						 u64 base, u64 offset)
+static __init void exynos_gpiolib_attach_ofnode(struct samsung_gpio_chip *chip,
+						u64 base, u64 offset)
 {
 	struct gpio_chip *gc =  &chip->chip;
 	u64 address;
@@ -2429,28 +2697,29 @@ static __init void exynos4_gpiolib_attach_ofnode(struct samsung_gpio_chip *chip,
 
 	address = chip->base ? base + ((u32)chip->base & 0xfff) : base + offset;
 	gc->of_node = of_find_matching_node_by_address(NULL,
-			exynos4_gpio_dt_match, address);
+			exynos_gpio_dt_match, address);
 	if (!gc->of_node) {
 		pr_info("gpio: device tree node not found for gpio controller"
 			" with base address %08llx\n", address);
 		return;
 	}
 	gc->of_gpio_n_cells = 4;
-	gc->of_xlate = exynos4_gpio_xlate;
+	gc->of_xlate = exynos_gpio_xlate;
 }
-#elif defined(CONFIG_ARCH_EXYNOS4)
-static __init void exynos4_gpiolib_attach_ofnode(struct samsung_gpio_chip *chip,
-						 u64 base, u64 offset)
+#elif defined(CONFIG_ARCH_EXYNOS)
+static __init void exynos_gpiolib_attach_ofnode(struct samsung_gpio_chip *chip,
+						u64 base, u64 offset)
 {
 	return;
 }
-#endif /* defined(CONFIG_ARCH_EXYNOS4) && defined(CONFIG_OF) */
+#endif /* defined(CONFIG_ARCH_EXYNOS) && defined(CONFIG_OF) */
 
 /* TODO: cleanup soc_is_* */
 static __init int samsung_gpiolib_init(void)
 {
 	struct samsung_gpio_chip *chip;
 	int i, nr_chips;
+	void __iomem *gpio_base1, *gpio_base2, *gpio_base3, *gpio_base4;
 	int group = 0;
 
 	samsung_gpiolib_set_cfg(samsung_gpio_cfgs, ARRAY_SIZE(samsung_gpio_cfgs));
@@ -2516,66 +2785,200 @@ static __init int samsung_gpiolib_init(void)
 		s5p_register_gpioint_bank(IRQ_GPIOINT, 0, S5P_GPIOINT_GROUP_MAXNR);
 #endif
 	} else if (soc_is_exynos4210()) {
-		group = 0;
+#ifdef CONFIG_CPU_EXYNOS4210
+		void __iomem *gpx_base;
 
 		/* gpio part1 */
+		gpio_base1 = ioremap(EXYNOS4_PA_GPIO1, SZ_4K);
+		if (gpio_base1 == NULL) {
+			pr_err("unable to ioremap for gpio_base1\n");
+			goto err_ioremap1;
+		}
+
 		chip = exynos4_gpios_1;
 		nr_chips = ARRAY_SIZE(exynos4_gpios_1);
 
 		for (i = 0; i < nr_chips; i++, chip++) {
 			if (!chip->config) {
-				chip->config = &exynos4_gpio_cfg;
+				chip->config = &exynos_gpio_cfg;
 				chip->group = group++;
 			}
-#ifdef CONFIG_CPU_EXYNOS4210
-			exynos4_gpiolib_attach_ofnode(chip,
+			exynos_gpiolib_attach_ofnode(chip,
 					EXYNOS4_PA_GPIO1, i * 0x20);
-#endif
 		}
-		samsung_gpiolib_add_4bit_chips(exynos4_gpios_1, nr_chips, S5P_VA_GPIO1);
+		samsung_gpiolib_add_4bit_chips(exynos4_gpios_1,
+					       nr_chips, gpio_base1);
 
 		/* gpio part2 */
+		gpio_base2 = ioremap(EXYNOS4_PA_GPIO2, SZ_4K);
+		if (gpio_base2 == NULL) {
+			pr_err("unable to ioremap for gpio_base2\n");
+			goto err_ioremap2;
+		}
+
+		/* need to set base address for gpx */
+		chip = &exynos4_gpios_2[16];
+		gpx_base = gpio_base2 + 0xC00;
+		for (i = 0; i < 4; i++, chip++, gpx_base += 0x20)
+			chip->base = gpx_base;
+
 		chip = exynos4_gpios_2;
 		nr_chips = ARRAY_SIZE(exynos4_gpios_2);
 
 		for (i = 0; i < nr_chips; i++, chip++) {
 			if (!chip->config) {
-				chip->config = &exynos4_gpio_cfg;
+				chip->config = &exynos_gpio_cfg;
 				chip->group = group++;
 			}
-#ifdef CONFIG_CPU_EXYNOS4210
-			exynos4_gpiolib_attach_ofnode(chip,
+			exynos_gpiolib_attach_ofnode(chip,
 					EXYNOS4_PA_GPIO2, i * 0x20);
-#endif
 		}
-		samsung_gpiolib_add_4bit_chips(exynos4_gpios_2, nr_chips, S5P_VA_GPIO2);
+		samsung_gpiolib_add_4bit_chips(exynos4_gpios_2,
+					       nr_chips, gpio_base2);
 
 		/* gpio part3 */
+		gpio_base3 = ioremap(EXYNOS4_PA_GPIO3, SZ_256);
+		if (gpio_base3 == NULL) {
+			pr_err("unable to ioremap for gpio_base3\n");
+			goto err_ioremap3;
+		}
+
 		chip = exynos4_gpios_3;
 		nr_chips = ARRAY_SIZE(exynos4_gpios_3);
 
 		for (i = 0; i < nr_chips; i++, chip++) {
 			if (!chip->config) {
-				chip->config = &exynos4_gpio_cfg;
+				chip->config = &exynos_gpio_cfg;
 				chip->group = group++;
 			}
-#ifdef CONFIG_CPU_EXYNOS4210
-			exynos4_gpiolib_attach_ofnode(chip,
+			exynos_gpiolib_attach_ofnode(chip,
 					EXYNOS4_PA_GPIO3, i * 0x20);
-#endif
 		}
-		samsung_gpiolib_add_4bit_chips(exynos4_gpios_3, nr_chips, S5P_VA_GPIO3);
+		samsung_gpiolib_add_4bit_chips(exynos4_gpios_3,
+					       nr_chips, gpio_base3);
 
 #if defined(CONFIG_CPU_EXYNOS4210) && defined(CONFIG_S5P_GPIO_INT)
 		s5p_register_gpioint_bank(IRQ_GPIO_XA, 0, IRQ_GPIO1_NR_GROUPS);
 		s5p_register_gpioint_bank(IRQ_GPIO_XB, IRQ_GPIO1_NR_GROUPS, IRQ_GPIO2_NR_GROUPS);
 #endif
+
+#endif	/* CONFIG_CPU_EXYNOS4210 */
+	} else if (soc_is_exynos5250()) {
+#ifdef CONFIG_SOC_EXYNOS5250
+		void __iomem *gpx_base;
+
+		/* gpio part1 */
+		gpio_base1 = ioremap(EXYNOS5_PA_GPIO1, SZ_4K);
+		if (gpio_base1 == NULL) {
+			pr_err("unable to ioremap for gpio_base1\n");
+			goto err_ioremap1;
+		}
+
+		/* need to set base address for gpx */
+		chip = &exynos5_gpios_1[20];
+		gpx_base = gpio_base1 + 0xC00;
+		for (i = 0; i < 4; i++, chip++, gpx_base += 0x20)
+			chip->base = gpx_base;
+
+		chip = exynos5_gpios_1;
+		nr_chips = ARRAY_SIZE(exynos5_gpios_1);
+
+		for (i = 0; i < nr_chips; i++, chip++) {
+			if (!chip->config) {
+				chip->config = &exynos_gpio_cfg;
+				chip->group = group++;
+			}
+			exynos_gpiolib_attach_ofnode(chip,
+					EXYNOS5_PA_GPIO1, i * 0x20);
+		}
+		samsung_gpiolib_add_4bit_chips(exynos5_gpios_1,
+					       nr_chips, gpio_base1);
+
+		/* gpio part2 */
+		gpio_base2 = ioremap(EXYNOS5_PA_GPIO2, SZ_4K);
+		if (gpio_base2 == NULL) {
+			pr_err("unable to ioremap for gpio_base2\n");
+			goto err_ioremap2;
+		}
+
+		chip = exynos5_gpios_2;
+		nr_chips = ARRAY_SIZE(exynos5_gpios_2);
+
+		for (i = 0; i < nr_chips; i++, chip++) {
+			if (!chip->config) {
+				chip->config = &exynos_gpio_cfg;
+				chip->group = group++;
+			}
+			exynos_gpiolib_attach_ofnode(chip,
+					EXYNOS5_PA_GPIO2, i * 0x20);
+		}
+		samsung_gpiolib_add_4bit_chips(exynos5_gpios_2,
+					       nr_chips, gpio_base2);
+
+		/* gpio part3 */
+		gpio_base3 = ioremap(EXYNOS5_PA_GPIO3, SZ_4K);
+		if (gpio_base3 == NULL) {
+			pr_err("unable to ioremap for gpio_base3\n");
+			goto err_ioremap3;
+		}
+
+		/* need to set base address for gpv */
+		exynos5_gpios_3[0].base = gpio_base3;
+		exynos5_gpios_3[1].base = gpio_base3 + 0x20;
+		exynos5_gpios_3[2].base = gpio_base3 + 0x60;
+		exynos5_gpios_3[3].base = gpio_base3 + 0x80;
+		exynos5_gpios_3[4].base = gpio_base3 + 0xC0;
+
+		chip = exynos5_gpios_3;
+		nr_chips = ARRAY_SIZE(exynos5_gpios_3);
+
+		for (i = 0; i < nr_chips; i++, chip++) {
+			if (!chip->config) {
+				chip->config = &exynos_gpio_cfg;
+				chip->group = group++;
+			}
+			exynos_gpiolib_attach_ofnode(chip,
+					EXYNOS5_PA_GPIO3, i * 0x20);
+		}
+		samsung_gpiolib_add_4bit_chips(exynos5_gpios_3,
+					       nr_chips, gpio_base3);
+
+		/* gpio part4 */
+		gpio_base4 = ioremap(EXYNOS5_PA_GPIO4, SZ_4K);
+		if (gpio_base4 == NULL) {
+			pr_err("unable to ioremap for gpio_base4\n");
+			goto err_ioremap4;
+		}
+
+		chip = exynos5_gpios_4;
+		nr_chips = ARRAY_SIZE(exynos5_gpios_4);
+
+		for (i = 0; i < nr_chips; i++, chip++) {
+			if (!chip->config) {
+				chip->config = &exynos_gpio_cfg;
+				chip->group = group++;
+			}
+			exynos_gpiolib_attach_ofnode(chip,
+					EXYNOS5_PA_GPIO4, i * 0x20);
+		}
+		samsung_gpiolib_add_4bit_chips(exynos5_gpios_4,
+					       nr_chips, gpio_base4);
+#endif	/* CONFIG_SOC_EXYNOS5250 */
 	} else {
 		WARN(1, "Unknown SoC in gpio-samsung, no GPIOs added\n");
 		return -ENODEV;
 	}
 
 	return 0;
+
+err_ioremap4:
+	iounmap(gpio_base3);
+err_ioremap3:
+	iounmap(gpio_base2);
+err_ioremap2:
+	iounmap(gpio_base1);
+err_ioremap1:
+	return -ENOMEM;
 }
 core_initcall(samsung_gpiolib_init);
 
diff --git a/drivers/gpio/gpio-sodaville.c b/drivers/gpio/gpio-sodaville.c
new file mode 100644
index 000000000000..9ba15d31d242
--- /dev/null
+++ b/drivers/gpio/gpio-sodaville.c
@@ -0,0 +1,302 @@
+/*
+ *  GPIO interface for Intel Sodaville SoCs.
+ *
+ *  Copyright (c) 2010, 2011 Intel Corporation
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License 2 as published
+ *  by the Free Software Foundation.
+ *
+ */
+
+#include <linux/errno.h>
+#include <linux/gpio.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/of_irq.h>
+#include <linux/basic_mmio_gpio.h>
+
+#define DRV_NAME		"sdv_gpio"
+#define SDV_NUM_PUB_GPIOS	12
+#define PCI_DEVICE_ID_SDV_GPIO	0x2e67
+#define GPIO_BAR		0
+
+#define GPOUTR		0x00
+#define GPOER		0x04
+#define GPINR		0x08
+
+#define GPSTR		0x0c
+#define GPIT1R0		0x10
+#define GPIO_INT	0x14
+#define GPIT1R1		0x18
+
+#define GPMUXCTL	0x1c
+
+struct sdv_gpio_chip_data {
+	int irq_base;
+	void __iomem *gpio_pub_base;
+	struct irq_domain id;
+	struct irq_chip_generic *gc;
+	struct bgpio_chip bgpio;
+};
+
+static int sdv_gpio_pub_set_type(struct irq_data *d, unsigned int type)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct sdv_gpio_chip_data *sd = gc->private;
+	void __iomem *type_reg;
+	u32 irq_offs = d->irq - sd->irq_base;
+	u32 reg;
+
+	if (irq_offs < 8)
+		type_reg = sd->gpio_pub_base + GPIT1R0;
+	else
+		type_reg = sd->gpio_pub_base + GPIT1R1;
+
+	reg = readl(type_reg);
+
+	switch (type) {
+	case IRQ_TYPE_LEVEL_HIGH:
+		reg &= ~BIT(4 * (irq_offs % 8));
+		break;
+
+	case IRQ_TYPE_LEVEL_LOW:
+		reg |= BIT(4 * (irq_offs % 8));
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	writel(reg, type_reg);
+	return 0;
+}
+
+static irqreturn_t sdv_gpio_pub_irq_handler(int irq, void *data)
+{
+	struct sdv_gpio_chip_data *sd = data;
+	u32 irq_stat = readl(sd->gpio_pub_base + GPSTR);
+
+	irq_stat &= readl(sd->gpio_pub_base + GPIO_INT);
+	if (!irq_stat)
+		return IRQ_NONE;
+
+	while (irq_stat) {
+		u32 irq_bit = __fls(irq_stat);
+
+		irq_stat &= ~BIT(irq_bit);
+		generic_handle_irq(sd->irq_base + irq_bit);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int sdv_xlate(struct irq_domain *h, struct device_node *node,
+		const u32 *intspec, u32 intsize, irq_hw_number_t *out_hwirq,
+		u32 *out_type)
+{
+	u32 line, type;
+
+	if (node != h->of_node)
+		return -EINVAL;
+
+	if (intsize < 2)
+		return -EINVAL;
+
+	line = *intspec;
+	*out_hwirq = line;
+
+	intspec++;
+	type = *intspec;
+
+	switch (type) {
+	case IRQ_TYPE_LEVEL_LOW:
+	case IRQ_TYPE_LEVEL_HIGH:
+		*out_type = type;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct irq_domain_ops irq_domain_sdv_ops = {
+	.dt_translate	= sdv_xlate,
+};
+
+static __devinit int sdv_register_irqsupport(struct sdv_gpio_chip_data *sd,
+		struct pci_dev *pdev)
+{
+	struct irq_chip_type *ct;
+	int ret;
+
+	sd->irq_base = irq_alloc_descs(-1, 0, SDV_NUM_PUB_GPIOS, -1);
+	if (sd->irq_base < 0)
+		return sd->irq_base;
+
+	/* mask + ACK all interrupt sources */
+	writel(0, sd->gpio_pub_base + GPIO_INT);
+	writel((1 << 11) - 1, sd->gpio_pub_base + GPSTR);
+
+	ret = request_irq(pdev->irq, sdv_gpio_pub_irq_handler, IRQF_SHARED,
+			"sdv_gpio", sd);
+	if (ret)
+		goto out_free_desc;
+
+	sd->id.irq_base = sd->irq_base;
+	sd->id.of_node = of_node_get(pdev->dev.of_node);
+	sd->id.ops = &irq_domain_sdv_ops;
+
+	/*
+	 * This gpio irq controller latches level irqs. Testing shows that if
+	 * we unmask & ACK the IRQ before the source of the interrupt is gone
+	 * then the interrupt is active again.
+	 */
+	sd->gc = irq_alloc_generic_chip("sdv-gpio", 1, sd->irq_base,
+			sd->gpio_pub_base, handle_fasteoi_irq);
+	if (!sd->gc) {
+		ret = -ENOMEM;
+		goto out_free_irq;
+	}
+
+	sd->gc->private = sd;
+	ct = sd->gc->chip_types;
+	ct->type = IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW;
+	ct->regs.eoi = GPSTR;
+	ct->regs.mask = GPIO_INT;
+	ct->chip.irq_mask = irq_gc_mask_clr_bit;
+	ct->chip.irq_unmask = irq_gc_mask_set_bit;
+	ct->chip.irq_eoi = irq_gc_eoi;
+	ct->chip.irq_set_type = sdv_gpio_pub_set_type;
+
+	irq_setup_generic_chip(sd->gc, IRQ_MSK(SDV_NUM_PUB_GPIOS),
+			IRQ_GC_INIT_MASK_CACHE, IRQ_NOREQUEST,
+			IRQ_LEVEL | IRQ_NOPROBE);
+
+	irq_domain_add(&sd->id);
+	return 0;
+out_free_irq:
+	free_irq(pdev->irq, sd);
+out_free_desc:
+	irq_free_descs(sd->irq_base, SDV_NUM_PUB_GPIOS);
+	return ret;
+}
+
+static int __devinit sdv_gpio_probe(struct pci_dev *pdev,
+					const struct pci_device_id *pci_id)
+{
+	struct sdv_gpio_chip_data *sd;
+	unsigned long addr;
+	const void *prop;
+	int len;
+	int ret;
+	u32 mux_val;
+
+	sd = kzalloc(sizeof(struct sdv_gpio_chip_data), GFP_KERNEL);
+	if (!sd)
+		return -ENOMEM;
+	ret = pci_enable_device(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "can't enable device.\n");
+		goto done;
+	}
+
+	ret = pci_request_region(pdev, GPIO_BAR, DRV_NAME);
+	if (ret) {
+		dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", GPIO_BAR);
+		goto disable_pci;
+	}
+
+	addr = pci_resource_start(pdev, GPIO_BAR);
+	if (!addr)
+		goto release_reg;
+	sd->gpio_pub_base = ioremap(addr, pci_resource_len(pdev, GPIO_BAR));
+
+	prop = of_get_property(pdev->dev.of_node, "intel,muxctl", &len);
+	if (prop && len == 4) {
+		mux_val = of_read_number(prop, 1);
+		writel(mux_val, sd->gpio_pub_base + GPMUXCTL);
+	}
+
+	ret = bgpio_init(&sd->bgpio, &pdev->dev, 4,
+			sd->gpio_pub_base + GPINR, sd->gpio_pub_base + GPOUTR,
+			NULL, sd->gpio_pub_base + GPOER, NULL, false);
+	if (ret)
+		goto unmap;
+	sd->bgpio.gc.ngpio = SDV_NUM_PUB_GPIOS;
+
+	ret = gpiochip_add(&sd->bgpio.gc);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "gpiochip_add() failed.\n");
+		goto unmap;
+	}
+
+	ret = sdv_register_irqsupport(sd, pdev);
+	if (ret)
+		goto unmap;
+
+	pci_set_drvdata(pdev, sd);
+	dev_info(&pdev->dev, "Sodaville GPIO driver registered.\n");
+	return 0;
+
+unmap:
+	iounmap(sd->gpio_pub_base);
+release_reg:
+	pci_release_region(pdev, GPIO_BAR);
+disable_pci:
+	pci_disable_device(pdev);
+done:
+	kfree(sd);
+	return ret;
+}
+
+static void sdv_gpio_remove(struct pci_dev *pdev)
+{
+	struct sdv_gpio_chip_data *sd = pci_get_drvdata(pdev);
+
+	irq_domain_del(&sd->id);
+	free_irq(pdev->irq, sd);
+	irq_free_descs(sd->irq_base, SDV_NUM_PUB_GPIOS);
+
+	if (gpiochip_remove(&sd->bgpio.gc))
+		dev_err(&pdev->dev, "gpiochip_remove() failed.\n");
+
+	pci_release_region(pdev, GPIO_BAR);
+	iounmap(sd->gpio_pub_base);
+	pci_disable_device(pdev);
+	kfree(sd);
+}
+
+static struct pci_device_id sdv_gpio_pci_ids[] __devinitdata = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_SDV_GPIO) },
+	{ 0, },
+};
+
+static struct pci_driver sdv_gpio_driver = {
+	.name = DRV_NAME,
+	.id_table = sdv_gpio_pci_ids,
+	.probe = sdv_gpio_probe,
+	.remove = sdv_gpio_remove,
+};
+
+static int __init sdv_gpio_init(void)
+{
+	return pci_register_driver(&sdv_gpio_driver);
+}
+module_init(sdv_gpio_init);
+
+static void __exit sdv_gpio_exit(void)
+{
+	pci_unregister_driver(&sdv_gpio_driver);
+}
+module_exit(sdv_gpio_exit);
+
+MODULE_AUTHOR("Hans J. Koch <hjk@linutronix.de>");
+MODULE_DESCRIPTION("GPIO interface for Intel Sodaville SoCs");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 87a68a896abf..dce34727bbf8 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -54,7 +54,7 @@ static int stmpe_gpio_get(struct gpio_chip *chip, unsigned offset)
 	if (ret < 0)
 		return ret;
 
-	return ret & mask;
+	return !!(ret & mask);
 }
 
 static void stmpe_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
@@ -307,13 +307,11 @@ static int __devinit stmpe_gpio_probe(struct platform_device *pdev)
 	struct stmpe_gpio_platform_data *pdata;
 	struct stmpe_gpio *stmpe_gpio;
 	int ret;
-	int irq;
+	int irq = 0;
 
 	pdata = stmpe->pdata->gpio;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
 
 	stmpe_gpio = kzalloc(sizeof(struct stmpe_gpio), GFP_KERNEL);
 	if (!stmpe_gpio)
@@ -330,21 +328,28 @@ static int __devinit stmpe_gpio_probe(struct platform_device *pdev)
 	stmpe_gpio->chip.dev = &pdev->dev;
 	stmpe_gpio->chip.base = pdata ? pdata->gpio_base : -1;
 
-	stmpe_gpio->irq_base = stmpe->irq_base + STMPE_INT_GPIO(0);
+	if (irq >= 0)
+		stmpe_gpio->irq_base = stmpe->irq_base + STMPE_INT_GPIO(0);
+	else
+		dev_info(&pdev->dev,
+			"device configured in no-irq mode; "
+			"irqs are not available\n");
 
 	ret = stmpe_enable(stmpe, STMPE_BLOCK_GPIO);
 	if (ret)
 		goto out_free;
 
-	ret = stmpe_gpio_irq_init(stmpe_gpio);
-	if (ret)
-		goto out_disable;
+	if (irq >= 0) {
+		ret = stmpe_gpio_irq_init(stmpe_gpio);
+		if (ret)
+			goto out_disable;
 
-	ret = request_threaded_irq(irq, NULL, stmpe_gpio_irq, IRQF_ONESHOT,
-				   "stmpe-gpio", stmpe_gpio);
-	if (ret) {
-		dev_err(&pdev->dev, "unable to get irq: %d\n", ret);
-		goto out_removeirq;
+		ret = request_threaded_irq(irq, NULL, stmpe_gpio_irq,
+				IRQF_ONESHOT, "stmpe-gpio", stmpe_gpio);
+		if (ret) {
+			dev_err(&pdev->dev, "unable to get irq: %d\n", ret);
+			goto out_removeirq;
+		}
 	}
 
 	ret = gpiochip_add(&stmpe_gpio->chip);
@@ -361,9 +366,11 @@ static int __devinit stmpe_gpio_probe(struct platform_device *pdev)
 	return 0;
 
 out_freeirq:
-	free_irq(irq, stmpe_gpio);
+	if (irq >= 0)
+		free_irq(irq, stmpe_gpio);
 out_removeirq:
-	stmpe_gpio_irq_remove(stmpe_gpio);
+	if (irq >= 0)
+		stmpe_gpio_irq_remove(stmpe_gpio);
 out_disable:
 	stmpe_disable(stmpe, STMPE_BLOCK_GPIO);
 out_free:
@@ -391,8 +398,10 @@ static int __devexit stmpe_gpio_remove(struct platform_device *pdev)
 
 	stmpe_disable(stmpe, STMPE_BLOCK_GPIO);
 
-	free_irq(irq, stmpe_gpio);
-	stmpe_gpio_irq_remove(stmpe_gpio);
+	if (irq >= 0) {
+		free_irq(irq, stmpe_gpio);
+		stmpe_gpio_irq_remove(stmpe_gpio);
+	}
 	platform_set_drvdata(pdev, NULL);
 	kfree(stmpe_gpio);
 
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 6f17671260e1..12f349b3830d 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -22,7 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/irqdomain.h>
@@ -37,7 +37,8 @@
 #define GPIO_PORT(x)		(((x) >> 3) & 0x3)
 #define GPIO_BIT(x)		((x) & 0x7)
 
-#define GPIO_REG(x)		(GPIO_BANK(x) * 0x80 + GPIO_PORT(x) * 4)
+#define GPIO_REG(x)		(GPIO_BANK(x) * tegra_gpio_bank_stride + \
+					GPIO_PORT(x) * 4)
 
 #define GPIO_CNF(x)		(GPIO_REG(x) + 0x00)
 #define GPIO_OE(x)		(GPIO_REG(x) + 0x10)
@@ -48,12 +49,12 @@
 #define GPIO_INT_LVL(x)		(GPIO_REG(x) + 0x60)
 #define GPIO_INT_CLR(x)		(GPIO_REG(x) + 0x70)
 
-#define GPIO_MSK_CNF(x)		(GPIO_REG(x) + 0x800)
-#define GPIO_MSK_OE(x)		(GPIO_REG(x) + 0x810)
-#define GPIO_MSK_OUT(x)		(GPIO_REG(x) + 0X820)
-#define GPIO_MSK_INT_STA(x)	(GPIO_REG(x) + 0x840)
-#define GPIO_MSK_INT_ENB(x)	(GPIO_REG(x) + 0x850)
-#define GPIO_MSK_INT_LVL(x)	(GPIO_REG(x) + 0x860)
+#define GPIO_MSK_CNF(x)		(GPIO_REG(x) + tegra_gpio_upper_offset + 0x00)
+#define GPIO_MSK_OE(x)		(GPIO_REG(x) + tegra_gpio_upper_offset + 0x10)
+#define GPIO_MSK_OUT(x)		(GPIO_REG(x) + tegra_gpio_upper_offset + 0X20)
+#define GPIO_MSK_INT_STA(x)	(GPIO_REG(x) + tegra_gpio_upper_offset + 0x40)
+#define GPIO_MSK_INT_ENB(x)	(GPIO_REG(x) + tegra_gpio_upper_offset + 0x50)
+#define GPIO_MSK_INT_LVL(x)	(GPIO_REG(x) + tegra_gpio_upper_offset + 0x60)
 
 #define GPIO_INT_LVL_MASK		0x010101
 #define GPIO_INT_LVL_EDGE_RISING	0x000101
@@ -78,6 +79,8 @@ struct tegra_gpio_bank {
 static struct irq_domain *irq_domain;
 static void __iomem *regs;
 static u32 tegra_gpio_bank_count;
+static u32 tegra_gpio_bank_stride;
+static u32 tegra_gpio_upper_offset;
 static struct tegra_gpio_bank *tegra_gpio_banks;
 
 static inline void tegra_gpio_writel(u32 val, u32 reg)
@@ -109,11 +112,13 @@ void tegra_gpio_enable(int gpio)
 {
 	tegra_gpio_mask_write(GPIO_MSK_CNF(gpio), gpio, 1);
 }
+EXPORT_SYMBOL_GPL(tegra_gpio_enable);
 
 void tegra_gpio_disable(int gpio)
 {
 	tegra_gpio_mask_write(GPIO_MSK_CNF(gpio), gpio, 0);
 }
+EXPORT_SYMBOL_GPL(tegra_gpio_disable);
 
 static void tegra_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 {
@@ -331,6 +336,26 @@ static struct irq_chip tegra_gpio_irq_chip = {
 #endif
 };
 
+struct tegra_gpio_soc_config {
+	u32 bank_stride;
+	u32 upper_offset;
+};
+
+static struct tegra_gpio_soc_config tegra20_gpio_config = {
+	.bank_stride = 0x80,
+	.upper_offset = 0x800,
+};
+
+static struct tegra_gpio_soc_config tegra30_gpio_config = {
+	.bank_stride = 0x100,
+	.upper_offset = 0x80,
+};
+
+static struct of_device_id tegra_gpio_of_match[] __devinitdata = {
+	{ .compatible = "nvidia,tegra30-gpio", .data = &tegra30_gpio_config },
+	{ .compatible = "nvidia,tegra20-gpio", .data = &tegra20_gpio_config },
+	{ },
+};
 
 /* This lock class tells lockdep that GPIO irqs are in a different
  * category than their parents, so it won't report false recursion.
@@ -339,6 +364,8 @@ static struct lock_class_key gpio_lock_class;
 
 static int __devinit tegra_gpio_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *match;
+	struct tegra_gpio_soc_config *config;
 	int irq_base;
 	struct resource *res;
 	struct tegra_gpio_bank *bank;
@@ -346,6 +373,15 @@ static int __devinit tegra_gpio_probe(struct platform_device *pdev)
 	int i;
 	int j;
 
+	match = of_match_device(tegra_gpio_of_match, &pdev->dev);
+	if (match)
+		config = (struct tegra_gpio_soc_config *)match->data;
+	else
+		config = &tegra20_gpio_config;
+
+	tegra_gpio_bank_stride = config->bank_stride;
+	tegra_gpio_upper_offset = config->upper_offset;
+
 	for (;;) {
 		res = platform_get_resource(pdev, IORESOURCE_IRQ, tegra_gpio_bank_count);
 		if (!res)
@@ -400,7 +436,7 @@ static int __devinit tegra_gpio_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	for (i = 0; i < 7; i++) {
+	for (i = 0; i < tegra_gpio_bank_count; i++) {
 		for (j = 0; j < 4; j++) {
 			int gpio = tegra_gpio_compose(i, j, 0);
 			tegra_gpio_writel(0x00, GPIO_INT_ENB(gpio));
@@ -439,11 +475,6 @@ static int __devinit tegra_gpio_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id tegra_gpio_of_match[] __devinitdata = {
-	{ .compatible = "nvidia,tegra20-gpio", },
-	{ },
-};
-
 static struct platform_driver tegra_gpio_driver = {
 	.driver		= {
 		.name	= "tegra-gpio",
@@ -459,7 +490,7 @@ static int __init tegra_gpio_init(void)
 }
 postcore_initcall(tegra_gpio_init);
 
-void __init tegra_gpio_config(struct tegra_gpio_table *table, int num)
+void tegra_gpio_config(struct tegra_gpio_table *table, int num)
 {
 	int i;
 
@@ -483,7 +514,7 @@ static int dbg_gpio_show(struct seq_file *s, void *unused)
 	int i;
 	int j;
 
-	for (i = 0; i < 7; i++) {
+	for (i = 0; i < tegra_gpio_bank_count; i++) {
 		for (j = 0; j < 4; j++) {
 			int gpio = tegra_gpio_compose(i, j, 0);
 			seq_printf(s,
diff --git a/drivers/gpio/gpio-tps65910.c b/drivers/gpio/gpio-tps65910.c
index 91f45b965d1e..7eef648a3351 100644
--- a/drivers/gpio/gpio-tps65910.c
+++ b/drivers/gpio/gpio-tps65910.c
@@ -69,6 +69,7 @@ static int tps65910_gpio_input(struct gpio_chip *gc, unsigned offset)
 void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base)
 {
 	int ret;
+	struct tps65910_board *board_data;
 
 	if (!gpio_base)
 		return;
@@ -80,10 +81,10 @@ void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base)
 
 	switch(tps65910_chip_id(tps65910)) {
 	case TPS65910:
-		tps65910->gpio.ngpio	= 6;
+		tps65910->gpio.ngpio	= TPS65910_NUM_GPIO;
 		break;
 	case TPS65911:
-		tps65910->gpio.ngpio	= 9;
+		tps65910->gpio.ngpio	= TPS65911_NUM_GPIO;
 		break;
 	default:
 		return;
@@ -95,6 +96,21 @@ void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base)
 	tps65910->gpio.set		= tps65910_gpio_set;
 	tps65910->gpio.get		= tps65910_gpio_get;
 
+	/* Configure sleep control for gpios */
+	board_data = dev_get_platdata(tps65910->dev);
+	if (board_data) {
+		int i;
+		for (i = 0; i < tps65910->gpio.ngpio; ++i) {
+			if (board_data->en_gpio_sleep[i]) {
+				ret = tps65910_set_bits(tps65910,
+					TPS65910_GPIO0 + i, GPIO_SLEEP_MASK);
+				if (ret < 0)
+					dev_warn(tps65910->dev,
+						"GPIO Sleep setting failed\n");
+			}
+		}
+	}
+
 	ret = gpiochip_add(&tps65910->gpio);
 
 	if (ret)
diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c
index b8b4f228757c..94256fe7bf36 100644
--- a/drivers/gpio/gpio-twl4030.c
+++ b/drivers/gpio/gpio-twl4030.c
@@ -32,6 +32,8 @@
 #include <linux/irq.h>
 #include <linux/gpio.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/irqdomain.h>
 
 #include <linux/i2c/twl.h>
 
@@ -256,7 +258,8 @@ static int twl_request(struct gpio_chip *chip, unsigned offset)
 		 * and vMMC2 power supplies based on card presence.
 		 */
 		pdata = chip->dev->platform_data;
-		value |= pdata->mmc_cd & 0x03;
+		if (pdata)
+			value |= pdata->mmc_cd & 0x03;
 
 		status = gpio_twl4030_write(REG_GPIO_CTRL, value);
 	}
@@ -395,59 +398,70 @@ static int gpio_twl4030_remove(struct platform_device *pdev);
 static int __devinit gpio_twl4030_probe(struct platform_device *pdev)
 {
 	struct twl4030_gpio_platform_data *pdata = pdev->dev.platform_data;
-	int ret;
+	struct device_node *node = pdev->dev.of_node;
+	int ret, irq_base;
 
 	/* maybe setup IRQs */
-	if (pdata->irq_base) {
-		if (is_module()) {
-			dev_err(&pdev->dev,
-				"can't dispatch IRQs from modules\n");
-			goto no_irqs;
-		}
-		ret = twl4030_sih_setup(TWL4030_MODULE_GPIO);
-		if (ret < 0)
-			return ret;
-		WARN_ON(ret != pdata->irq_base);
-		twl4030_gpio_irq_base = ret;
+	if (is_module()) {
+		dev_err(&pdev->dev, "can't dispatch IRQs from modules\n");
+		goto no_irqs;
+	}
+
+	irq_base = irq_alloc_descs(-1, 0, TWL4030_GPIO_MAX, 0);
+	if (irq_base < 0) {
+		dev_err(&pdev->dev, "Failed to alloc irq_descs\n");
+		return irq_base;
 	}
 
+	irq_domain_add_legacy(node, TWL4030_GPIO_MAX, irq_base, 0,
+			      &irq_domain_simple_ops, NULL);
+
+	ret = twl4030_sih_setup(&pdev->dev, TWL4030_MODULE_GPIO, irq_base);
+	if (ret < 0)
+		return ret;
+
+	twl4030_gpio_irq_base = irq_base;
+
 no_irqs:
-	/*
-	 * NOTE:  boards may waste power if they don't set pullups
-	 * and pulldowns correctly ... default for non-ULPI pins is
-	 * pulldown, and some other pins may have external pullups
-	 * or pulldowns.  Careful!
-	 */
-	ret = gpio_twl4030_pulls(pdata->pullups, pdata->pulldowns);
-	if (ret)
-		dev_dbg(&pdev->dev, "pullups %.05x %.05x --> %d\n",
-				pdata->pullups, pdata->pulldowns,
-				ret);
-
-	ret = gpio_twl4030_debounce(pdata->debounce, pdata->mmc_cd);
-	if (ret)
-		dev_dbg(&pdev->dev, "debounce %.03x %.01x --> %d\n",
-				pdata->debounce, pdata->mmc_cd,
-				ret);
-
-	twl_gpiochip.base = pdata->gpio_base;
+	twl_gpiochip.base = -1;
 	twl_gpiochip.ngpio = TWL4030_GPIO_MAX;
 	twl_gpiochip.dev = &pdev->dev;
 
-	/* NOTE: we assume VIBRA_CTL.VIBRA_EN, in MODULE_AUDIO_VOICE,
-	 * is (still) clear if use_leds is set.
-	 */
-	if (pdata->use_leds)
-		twl_gpiochip.ngpio += 2;
+	if (pdata) {
+		twl_gpiochip.base = pdata->gpio_base;
+
+		/*
+		 * NOTE:  boards may waste power if they don't set pullups
+		 * and pulldowns correctly ... default for non-ULPI pins is
+		 * pulldown, and some other pins may have external pullups
+		 * or pulldowns.  Careful!
+		 */
+		ret = gpio_twl4030_pulls(pdata->pullups, pdata->pulldowns);
+		if (ret)
+			dev_dbg(&pdev->dev, "pullups %.05x %.05x --> %d\n",
+					pdata->pullups, pdata->pulldowns,
+					ret);
+
+		ret = gpio_twl4030_debounce(pdata->debounce, pdata->mmc_cd);
+		if (ret)
+			dev_dbg(&pdev->dev, "debounce %.03x %.01x --> %d\n",
+					pdata->debounce, pdata->mmc_cd,
+					ret);
+
+		/*
+		 * NOTE: we assume VIBRA_CTL.VIBRA_EN, in MODULE_AUDIO_VOICE,
+		 * is (still) clear if use_leds is set.
+		 */
+		if (pdata->use_leds)
+			twl_gpiochip.ngpio += 2;
+	}
 
 	ret = gpiochip_add(&twl_gpiochip);
 	if (ret < 0) {
-		dev_err(&pdev->dev,
-				"could not register gpiochip, %d\n",
-				ret);
+		dev_err(&pdev->dev, "could not register gpiochip, %d\n", ret);
 		twl_gpiochip.ngpio = 0;
 		gpio_twl4030_remove(pdev);
-	} else if (pdata->setup) {
+	} else if (pdata && pdata->setup) {
 		int status;
 
 		status = pdata->setup(&pdev->dev,
@@ -465,7 +479,7 @@ static int gpio_twl4030_remove(struct platform_device *pdev)
 	struct twl4030_gpio_platform_data *pdata = pdev->dev.platform_data;
 	int status;
 
-	if (pdata->teardown) {
+	if (pdata && pdata->teardown) {
 		status = pdata->teardown(&pdev->dev,
 				pdata->gpio_base, TWL4030_GPIO_MAX);
 		if (status) {
@@ -486,12 +500,21 @@ static int gpio_twl4030_remove(struct platform_device *pdev)
 	return -EIO;
 }
 
+static const struct of_device_id twl_gpio_match[] = {
+	{ .compatible = "ti,twl4030-gpio", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, twl_gpio_match);
+
 /* Note:  this hardware lives inside an I2C-based multi-function device. */
 MODULE_ALIAS("platform:twl4030_gpio");
 
 static struct platform_driver gpio_twl4030_driver = {
-	.driver.name	= "twl4030_gpio",
-	.driver.owner	= THIS_MODULE,
+	.driver = {
+		.name	= "twl4030_gpio",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(twl_gpio_match),
+	},
 	.probe		= gpio_twl4030_probe,
 	.remove		= gpio_twl4030_remove,
 };
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 17fdf4b6af93..5a75510d66bb 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -58,6 +58,8 @@ struct gpio_desc {
 #define FLAG_TRIG_FALL	5	/* trigger on falling edge */
 #define FLAG_TRIG_RISE	6	/* trigger on rising edge */
 #define FLAG_ACTIVE_LOW	7	/* sysfs value has active low */
+#define FLAG_OPEN_DRAIN	8	/* Gpio is open drain type */
+#define FLAG_OPEN_SOURCE 9	/* Gpio is open source type */
 
 #define ID_SHIFT	16	/* add new flags before this one */
 
@@ -873,6 +875,7 @@ void gpio_unexport(unsigned gpio)
 {
 	struct gpio_desc	*desc;
 	int			status = 0;
+	struct device		*dev = NULL;
 
 	if (!gpio_is_valid(gpio)) {
 		status = -EINVAL;
@@ -884,19 +887,20 @@ void gpio_unexport(unsigned gpio)
 	desc = &gpio_desc[gpio];
 
 	if (test_bit(FLAG_EXPORT, &desc->flags)) {
-		struct device	*dev = NULL;
 
 		dev = class_find_device(&gpio_class, NULL, desc, match_export);
 		if (dev) {
 			gpio_setup_irq(desc, dev, 0);
 			clear_bit(FLAG_EXPORT, &desc->flags);
-			put_device(dev);
-			device_unregister(dev);
 		} else
 			status = -ENODEV;
 	}
 
 	mutex_unlock(&sysfs_lock);
+	if (dev) {
+		device_unregister(dev);
+		put_device(dev);
+	}
 done:
 	if (status)
 		pr_debug("%s: gpio%d status %d\n", __func__, gpio, status);
@@ -1150,8 +1154,9 @@ EXPORT_SYMBOL_GPL(gpiochip_remove);
  * non-zero, this function will return to the caller and not iterate over any
  * more gpio_chips.
  */
-struct gpio_chip *gpiochip_find(void *data,
-				int (*match)(struct gpio_chip *chip, void *data))
+struct gpio_chip *gpiochip_find(const void *data,
+				int (*match)(struct gpio_chip *chip,
+					     const void *data))
 {
 	struct gpio_chip *chip = NULL;
 	unsigned long flags;
@@ -1261,6 +1266,8 @@ void gpio_free(unsigned gpio)
 		module_put(desc->chip->owner);
 		clear_bit(FLAG_ACTIVE_LOW, &desc->flags);
 		clear_bit(FLAG_REQUESTED, &desc->flags);
+		clear_bit(FLAG_OPEN_DRAIN, &desc->flags);
+		clear_bit(FLAG_OPEN_SOURCE, &desc->flags);
 	} else
 		WARN_ON(extra_checks);
 
@@ -1282,6 +1289,12 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 	if (err)
 		return err;
 
+	if (flags & GPIOF_OPEN_DRAIN)
+		set_bit(FLAG_OPEN_DRAIN, &gpio_desc[gpio].flags);
+
+	if (flags & GPIOF_OPEN_SOURCE)
+		set_bit(FLAG_OPEN_SOURCE, &gpio_desc[gpio].flags);
+
 	if (flags & GPIOF_DIR_IN)
 		err = gpio_direction_input(gpio);
 	else
@@ -1431,6 +1444,14 @@ int gpio_direction_output(unsigned gpio, int value)
 	struct gpio_desc	*desc = &gpio_desc[gpio];
 	int			status = -EINVAL;
 
+	/* Open drain pin should not be driven to 1 */
+	if (value && test_bit(FLAG_OPEN_DRAIN,  &desc->flags))
+		return gpio_direction_input(gpio);
+
+	/* Open source pin should not be driven to 0 */
+	if (!value && test_bit(FLAG_OPEN_SOURCE,  &desc->flags))
+		return gpio_direction_input(gpio);
+
 	spin_lock_irqsave(&gpio_lock, flags);
 
 	if (!gpio_is_valid(gpio))
@@ -1560,6 +1581,7 @@ int __gpio_get_value(unsigned gpio)
 	int value;
 
 	chip = gpio_to_chip(gpio);
+	/* Should be using gpio_get_value_cansleep() */
 	WARN_ON(chip->can_sleep);
 	value = chip->get ? chip->get(chip, gpio - chip->base) : 0;
 	trace_gpio_value(gpio, 1, value);
@@ -1567,6 +1589,57 @@ int __gpio_get_value(unsigned gpio)
 }
 EXPORT_SYMBOL_GPL(__gpio_get_value);
 
+/*
+ *  _gpio_set_open_drain_value() - Set the open drain gpio's value.
+ * @gpio: Gpio whose state need to be set.
+ * @chip: Gpio chip.
+ * @value: Non-zero for setting it HIGH otherise it will set to LOW.
+ */
+static void _gpio_set_open_drain_value(unsigned gpio,
+			struct gpio_chip *chip, int value)
+{
+	int err = 0;
+	if (value) {
+		err = chip->direction_input(chip, gpio - chip->base);
+		if (!err)
+			clear_bit(FLAG_IS_OUT, &gpio_desc[gpio].flags);
+	} else {
+		err = chip->direction_output(chip, gpio - chip->base, 0);
+		if (!err)
+			set_bit(FLAG_IS_OUT, &gpio_desc[gpio].flags);
+	}
+	trace_gpio_direction(gpio, value, err);
+	if (err < 0)
+		pr_err("%s: Error in set_value for open drain gpio%d err %d\n",
+					__func__, gpio, err);
+}
+
+/*
+ *  _gpio_set_open_source() - Set the open source gpio's value.
+ * @gpio: Gpio whose state need to be set.
+ * @chip: Gpio chip.
+ * @value: Non-zero for setting it HIGH otherise it will set to LOW.
+ */
+static void _gpio_set_open_source_value(unsigned gpio,
+			struct gpio_chip *chip, int value)
+{
+	int err = 0;
+	if (value) {
+		err = chip->direction_output(chip, gpio - chip->base, 1);
+		if (!err)
+			set_bit(FLAG_IS_OUT, &gpio_desc[gpio].flags);
+	} else {
+		err = chip->direction_input(chip, gpio - chip->base);
+		if (!err)
+			clear_bit(FLAG_IS_OUT, &gpio_desc[gpio].flags);
+	}
+	trace_gpio_direction(gpio, !value, err);
+	if (err < 0)
+		pr_err("%s: Error in set_value for open source gpio%d err %d\n",
+					__func__, gpio, err);
+}
+
+
 /**
  * __gpio_set_value() - assign a gpio's value
  * @gpio: gpio whose value will be assigned
@@ -1581,9 +1654,15 @@ void __gpio_set_value(unsigned gpio, int value)
 	struct gpio_chip	*chip;
 
 	chip = gpio_to_chip(gpio);
+	/* Should be using gpio_set_value_cansleep() */
 	WARN_ON(chip->can_sleep);
 	trace_gpio_value(gpio, 0, value);
-	chip->set(chip, gpio - chip->base, value);
+	if (test_bit(FLAG_OPEN_DRAIN,  &gpio_desc[gpio].flags))
+		_gpio_set_open_drain_value(gpio, chip, value);
+	else if (test_bit(FLAG_OPEN_SOURCE,  &gpio_desc[gpio].flags))
+		_gpio_set_open_source_value(gpio, chip, value);
+	else
+		chip->set(chip, gpio - chip->base, value);
 }
 EXPORT_SYMBOL_GPL(__gpio_set_value);
 
@@ -1650,7 +1729,12 @@ void gpio_set_value_cansleep(unsigned gpio, int value)
 	might_sleep_if(extra_checks);
 	chip = gpio_to_chip(gpio);
 	trace_gpio_value(gpio, 0, value);
-	chip->set(chip, gpio - chip->base, value);
+	if (test_bit(FLAG_OPEN_DRAIN,  &gpio_desc[gpio].flags))
+		_gpio_set_open_drain_value(gpio, chip, value);
+	else if (test_bit(FLAG_OPEN_SOURCE,  &gpio_desc[gpio].flags))
+		_gpio_set_open_source_value(gpio, chip, value);
+	else
+		chip->set(chip, gpio - chip->base, value);
 }
 EXPORT_SYMBOL_GPL(gpio_set_value_cansleep);
 
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index cc1148837e24..e354bc0b052a 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -9,6 +9,7 @@ menuconfig DRM
 	depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && MMU
 	select I2C
 	select I2C_ALGOBIT
+	select DMA_SHARED_BUFFER
 	help
 	  Kernel-level support for the Direct Rendering Infrastructure (DRI)
 	  introduced in XFree86 4.0. If you say Y here, you need to select
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index a858532806ae..c20da5bda355 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -12,7 +12,7 @@ drm-y       :=	drm_auth.o drm_buffer.o drm_bufs.o drm_cache.o \
 		drm_platform.o drm_sysfs.o drm_hashtab.o drm_mm.o \
 		drm_crtc.o drm_modes.o drm_edid.o \
 		drm_info.o drm_debugfs.o drm_encoder_slave.o \
-		drm_trace_points.o drm_global.o
+		drm_trace_points.o drm_global.o drm_prime.o
 
 drm-$(CONFIG_COMPAT) += drm_ioc32.o
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 0b65fbc8a630..6116e3b75393 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -136,6 +136,10 @@ static struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH|DRM_UNLOCKED),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED),
+
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 7740dd26f007..a0d6e894d97c 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -559,9 +559,13 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 		return -EINVAL;
 
 	/* Need to resize the fb object !!! */
-	if (var->bits_per_pixel > fb->bits_per_pixel || var->xres > fb->width || var->yres > fb->height) {
+	if (var->bits_per_pixel > fb->bits_per_pixel ||
+	    var->xres > fb->width || var->yres > fb->height ||
+	    var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
 		DRM_DEBUG("fb userspace requested width/height/bpp is greater than current fb "
-			  "object %dx%d-%d > %dx%d-%d\n", var->xres, var->yres, var->bits_per_pixel,
+			  "request %dx%d-%d (virtual %dx%d) > %dx%d-%d\n",
+			  var->xres, var->yres, var->bits_per_pixel,
+			  var->xres_virtual, var->yres_virtual,
 			  fb->width, fb->height, fb->bits_per_pixel);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 7348a3dab250..cdfbf27b2b3c 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -271,6 +271,9 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 	if (dev->driver->driver_features & DRIVER_GEM)
 		drm_gem_open(dev, priv);
 
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_init_file_private(&priv->prime);
+
 	if (dev->driver->open) {
 		ret = dev->driver->open(dev, priv);
 		if (ret < 0)
@@ -571,6 +574,10 @@ int drm_release(struct inode *inode, struct file *filp)
 
 	if (dev->driver->postclose)
 		dev->driver->postclose(dev, file_priv);
+
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_destroy_file_private(&file_priv->prime);
+
 	kfree(file_priv);
 
 	/* ========================================================
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 0ef358e53245..83114b5e3cee 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -35,6 +35,7 @@
 #include <linux/mman.h>
 #include <linux/pagemap.h>
 #include <linux/shmem_fs.h>
+#include <linux/dma-buf.h>
 #include "drmP.h"
 
 /** @file drm_gem.c
@@ -232,6 +233,10 @@ drm_gem_handle_delete(struct drm_file *filp, u32 handle)
 	idr_remove(&filp->object_idr, handle);
 	spin_unlock(&filp->table_lock);
 
+	if (obj->import_attach)
+		drm_prime_remove_imported_buf_handle(&filp->prime,
+				obj->import_attach->dmabuf);
+
 	if (dev->driver->gem_close_object)
 		dev->driver->gem_close_object(obj, filp);
 	drm_gem_object_handle_unreference_unlocked(obj);
@@ -527,6 +532,10 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	struct drm_gem_object *obj = ptr;
 	struct drm_device *dev = obj->dev;
 
+	if (obj->import_attach)
+		drm_prime_remove_imported_buf_handle(&file_priv->prime,
+				obj->import_attach->dmabuf);
+
 	if (dev->driver->gem_close_object)
 		dev->driver->gem_close_object(obj, file_priv);
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
new file mode 100644
index 000000000000..1bdf2b54eaf6
--- /dev/null
+++ b/drivers/gpu/drm/drm_prime.c
@@ -0,0 +1,304 @@
+/*
+ * Copyright © 2012 Red Hat
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *      Dave Airlie <airlied@redhat.com>
+ *      Rob Clark <rob.clark@linaro.org>
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/dma-buf.h>
+#include "drmP.h"
+
+/*
+ * DMA-BUF/GEM Object references and lifetime overview:
+ *
+ * On the export the dma_buf holds a reference to the exporting GEM
+ * object. It takes this reference in handle_to_fd_ioctl, when it
+ * first calls .prime_export and stores the exporting GEM object in
+ * the dma_buf priv. This reference is released when the dma_buf
+ * object goes away in the driver .release function.
+ *
+ * On the import the importing GEM object holds a reference to the
+ * dma_buf (which in turn holds a ref to the exporting GEM object).
+ * It takes that reference in the fd_to_handle ioctl.
+ * It calls dma_buf_get, creates an attachment to it and stores the
+ * attachment in the GEM object. When this attachment is destroyed
+ * when the imported object is destroyed, we remove the attachment
+ * and drop the reference to the dma_buf.
+ *
+ * Thus the chain of references always flows in one direction
+ * (avoiding loops): importing_gem -> dmabuf -> exporting_gem
+ *
+ * Self-importing: if userspace is using PRIME as a replacement for flink
+ * then it will get a fd->handle request for a GEM object that it created.
+ * Drivers should detect this situation and return back the gem object
+ * from the dma-buf private.
+ */
+
+struct drm_prime_member {
+	struct list_head entry;
+	struct dma_buf *dma_buf;
+	uint32_t handle;
+};
+
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+		struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+		int *prime_fd)
+{
+	struct drm_gem_object *obj;
+	void *buf;
+
+	obj = drm_gem_object_lookup(dev, file_priv, handle);
+	if (!obj)
+		return -ENOENT;
+
+	mutex_lock(&file_priv->prime.lock);
+	/* re-export the original imported object */
+	if (obj->import_attach) {
+		get_dma_buf(obj->import_attach->dmabuf);
+		*prime_fd = dma_buf_fd(obj->import_attach->dmabuf, flags);
+		drm_gem_object_unreference_unlocked(obj);
+		mutex_unlock(&file_priv->prime.lock);
+		return 0;
+	}
+
+	if (obj->export_dma_buf) {
+		get_dma_buf(obj->export_dma_buf);
+		*prime_fd = dma_buf_fd(obj->export_dma_buf, flags);
+		drm_gem_object_unreference_unlocked(obj);
+	} else {
+		buf = dev->driver->gem_prime_export(dev, obj, flags);
+		if (IS_ERR(buf)) {
+			/* normally the created dma-buf takes ownership of the ref,
+			 * but if that fails then drop the ref
+			 */
+			drm_gem_object_unreference_unlocked(obj);
+			mutex_unlock(&file_priv->prime.lock);
+			return PTR_ERR(buf);
+		}
+		obj->export_dma_buf = buf;
+		*prime_fd = dma_buf_fd(buf, flags);
+	}
+	mutex_unlock(&file_priv->prime.lock);
+	return 0;
+}
+EXPORT_SYMBOL(drm_gem_prime_handle_to_fd);
+
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+		struct drm_file *file_priv, int prime_fd, uint32_t *handle)
+{
+	struct dma_buf *dma_buf;
+	struct drm_gem_object *obj;
+	int ret;
+
+	dma_buf = dma_buf_get(prime_fd);
+	if (IS_ERR(dma_buf))
+		return PTR_ERR(dma_buf);
+
+	mutex_lock(&file_priv->prime.lock);
+
+	ret = drm_prime_lookup_imported_buf_handle(&file_priv->prime,
+			dma_buf, handle);
+	if (!ret) {
+		ret = 0;
+		goto out_put;
+	}
+
+	/* never seen this one, need to import */
+	obj = dev->driver->gem_prime_import(dev, dma_buf);
+	if (IS_ERR(obj)) {
+		ret = PTR_ERR(obj);
+		goto out_put;
+	}
+
+	ret = drm_gem_handle_create(file_priv, obj, handle);
+	drm_gem_object_unreference_unlocked(obj);
+	if (ret)
+		goto out_put;
+
+	ret = drm_prime_add_imported_buf_handle(&file_priv->prime,
+			dma_buf, *handle);
+	if (ret)
+		goto fail;
+
+	mutex_unlock(&file_priv->prime.lock);
+	return 0;
+
+fail:
+	/* hmm, if driver attached, we are relying on the free-object path
+	 * to detach.. which seems ok..
+	 */
+	drm_gem_object_handle_unreference_unlocked(obj);
+out_put:
+	dma_buf_put(dma_buf);
+	mutex_unlock(&file_priv->prime.lock);
+	return ret;
+}
+EXPORT_SYMBOL(drm_gem_prime_fd_to_handle);
+
+int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct drm_prime_handle *args = data;
+	uint32_t flags;
+
+	if (!drm_core_check_feature(dev, DRIVER_PRIME))
+		return -EINVAL;
+
+	if (!dev->driver->prime_handle_to_fd)
+		return -ENOSYS;
+
+	/* check flags are valid */
+	if (args->flags & ~DRM_CLOEXEC)
+		return -EINVAL;
+
+	/* we only want to pass DRM_CLOEXEC which is == O_CLOEXEC */
+	flags = args->flags & DRM_CLOEXEC;
+
+	return dev->driver->prime_handle_to_fd(dev, file_priv,
+			args->handle, flags, &args->fd);
+}
+
+int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct drm_prime_handle *args = data;
+
+	if (!drm_core_check_feature(dev, DRIVER_PRIME))
+		return -EINVAL;
+
+	if (!dev->driver->prime_fd_to_handle)
+		return -ENOSYS;
+
+	return dev->driver->prime_fd_to_handle(dev, file_priv,
+			args->fd, &args->handle);
+}
+
+/*
+ * drm_prime_pages_to_sg
+ *
+ * this helper creates an sg table object from a set of pages
+ * the driver is responsible for mapping the pages into the
+ * importers address space
+ */
+struct sg_table *drm_prime_pages_to_sg(struct page **pages, int nr_pages)
+{
+	struct sg_table *sg = NULL;
+	struct scatterlist *iter;
+	int i;
+	int ret;
+
+	sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
+	if (!sg)
+		goto out;
+
+	ret = sg_alloc_table(sg, nr_pages, GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	for_each_sg(sg->sgl, iter, nr_pages, i)
+		sg_set_page(iter, pages[i], PAGE_SIZE, 0);
+
+	return sg;
+out:
+	kfree(sg);
+	return NULL;
+}
+EXPORT_SYMBOL(drm_prime_pages_to_sg);
+
+/* helper function to cleanup a GEM/prime object */
+void drm_prime_gem_destroy(struct drm_gem_object *obj, struct sg_table *sg)
+{
+	struct dma_buf_attachment *attach;
+	struct dma_buf *dma_buf;
+	attach = obj->import_attach;
+	if (sg)
+		dma_buf_unmap_attachment(attach, sg, DMA_BIDIRECTIONAL);
+	dma_buf = attach->dmabuf;
+	dma_buf_detach(attach->dmabuf, attach);
+	/* remove the reference */
+	dma_buf_put(dma_buf);
+}
+EXPORT_SYMBOL(drm_prime_gem_destroy);
+
+void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv)
+{
+	INIT_LIST_HEAD(&prime_fpriv->head);
+	mutex_init(&prime_fpriv->lock);
+}
+EXPORT_SYMBOL(drm_prime_init_file_private);
+
+void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv)
+{
+	struct drm_prime_member *member, *safe;
+	list_for_each_entry_safe(member, safe, &prime_fpriv->head, entry) {
+		list_del(&member->entry);
+		kfree(member);
+	}
+}
+EXPORT_SYMBOL(drm_prime_destroy_file_private);
+
+int drm_prime_add_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf, uint32_t handle)
+{
+	struct drm_prime_member *member;
+
+	member = kmalloc(sizeof(*member), GFP_KERNEL);
+	if (!member)
+		return -ENOMEM;
+
+	member->dma_buf = dma_buf;
+	member->handle = handle;
+	list_add(&member->entry, &prime_fpriv->head);
+	return 0;
+}
+EXPORT_SYMBOL(drm_prime_add_imported_buf_handle);
+
+int drm_prime_lookup_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf, uint32_t *handle)
+{
+	struct drm_prime_member *member;
+
+	list_for_each_entry(member, &prime_fpriv->head, entry) {
+		if (member->dma_buf == dma_buf) {
+			*handle = member->handle;
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+EXPORT_SYMBOL(drm_prime_lookup_imported_buf_handle);
+
+void drm_prime_remove_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf)
+{
+	struct drm_prime_member *member, *safe;
+
+	mutex_lock(&prime_fpriv->lock);
+	list_for_each_entry_safe(member, safe, &prime_fpriv->head, entry) {
+		if (member->dma_buf == dma_buf) {
+			list_del(&member->entry);
+			kfree(member);
+		}
+	}
+	mutex_unlock(&prime_fpriv->lock);
+}
+EXPORT_SYMBOL(drm_prime_remove_imported_buf_handle);
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_output.c b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
index 4c2cb4a8ad98..5675d93b4205 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_output.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
@@ -244,7 +244,6 @@ static int mdfld_dsi_connector_set_property(struct drm_connector *connector,
 				uint64_t value)
 {
 	struct drm_encoder *encoder = connector->encoder;
-	struct backlight_device *psb_bd;
 
 	if (!strcmp(property->name, "scaling mode") && encoder) {
 		struct psb_intel_crtc *psb_crtc =
@@ -301,11 +300,15 @@ static int mdfld_dsi_connector_set_property(struct drm_connector *connector,
 									value))
 			goto set_prop_error;
 		else {
+#ifdef CONFIG_BACKLIGHT_CLASS_DEVICE
+			struct backlight_device *psb_bd;
+
 			psb_bd = mdfld_get_backlight_device();
 			if (psb_bd) {
 				psb_bd->props.brightness = value;
 				mdfld_set_brightness(psb_bd);
 			}
+#endif
 		}
 	}
 set_prop_done:
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index fdb7ccefffbd..b505b70dba05 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1502,14 +1502,6 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-static int
-i915_debugfs_common_open(struct inode *inode,
-			 struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t
 i915_wedged_read(struct file *filp,
 		 char __user *ubuf,
@@ -1560,7 +1552,7 @@ i915_wedged_write(struct file *filp,
 
 static const struct file_operations i915_wedged_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_debugfs_common_open,
+	.open = simple_open,
 	.read = i915_wedged_read,
 	.write = i915_wedged_write,
 	.llseek = default_llseek,
@@ -1622,7 +1614,7 @@ i915_max_freq_write(struct file *filp,
 
 static const struct file_operations i915_max_freq_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_debugfs_common_open,
+	.open = simple_open,
 	.read = i915_max_freq_read,
 	.write = i915_max_freq_write,
 	.llseek = default_llseek,
@@ -1693,7 +1685,7 @@ i915_cache_sharing_write(struct file *filp,
 
 static const struct file_operations i915_cache_sharing_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_debugfs_common_open,
+	.open = simple_open,
 	.read = i915_cache_sharing_read,
 	.write = i915_cache_sharing_write,
 	.llseek = default_llseek,
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 9341eb8ce93b..785f67f963ef 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1183,6 +1183,21 @@ static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
 	return can_switch;
 }
 
+static bool
+intel_enable_ppgtt(struct drm_device *dev)
+{
+	if (i915_enable_ppgtt >= 0)
+		return i915_enable_ppgtt;
+
+#ifdef CONFIG_INTEL_IOMMU
+	/* Disable ppgtt on SNB if VT-d is on. */
+	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped)
+		return false;
+#endif
+
+	return true;
+}
+
 static int i915_load_gem_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1197,7 +1212,7 @@ static int i915_load_gem_init(struct drm_device *dev)
 	drm_mm_init(&dev_priv->mm.stolen, 0, prealloc_size);
 
 	mutex_lock(&dev->struct_mutex);
-	if (i915_enable_ppgtt && HAS_ALIASING_PPGTT(dev)) {
+	if (intel_enable_ppgtt(dev) && HAS_ALIASING_PPGTT(dev)) {
 		/* PPGTT pdes are stolen from global gtt ptes, so shrink the
 		 * aperture accordingly when using aliasing ppgtt. */
 		gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE;
@@ -1207,8 +1222,10 @@ static int i915_load_gem_init(struct drm_device *dev)
 		i915_gem_do_init(dev, 0, mappable_size, gtt_size);
 
 		ret = i915_gem_init_aliasing_ppgtt(dev);
-		if (ret)
+		if (ret) {
+			mutex_unlock(&dev->struct_mutex);
 			return ret;
+		}
 	} else {
 		/* Let GEM Manage all of the aperture.
 		 *
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 0694e170a338..dfa55e7478fb 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -66,7 +66,11 @@ MODULE_PARM_DESC(semaphores,
 int i915_enable_rc6 __read_mostly = -1;
 module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
 MODULE_PARM_DESC(i915_enable_rc6,
-		"Enable power-saving render C-state 6 (default: -1 (use per-chip default)");
+		"Enable power-saving render C-state 6. "
+		"Different stages can be selected via bitmask values "
+		"(0 = disable; 1 = enable rc6; 2 = enable deep rc6; 4 = enable deepest rc6). "
+		"For example, 3 would enable rc6 and deep rc6, and 7 would enable everything. "
+		"default: -1 (use per-chip default)");
 
 int i915_enable_fbc __read_mostly = -1;
 module_param_named(i915_enable_fbc, i915_enable_fbc, int, 0600);
@@ -103,8 +107,8 @@ MODULE_PARM_DESC(enable_hangcheck,
 		"WARNING: Disabling this can cause system wide hangs. "
 		"(default: true)");
 
-bool i915_enable_ppgtt __read_mostly = 1;
-module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, bool, 0600);
+int i915_enable_ppgtt __read_mostly = -1;
+module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, int, 0600);
 MODULE_PARM_DESC(i915_enable_ppgtt,
 		"Enable PPGTT (default: true)");
 
@@ -292,6 +296,7 @@ static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_VGA_DEVICE(0x0152, &intel_ivybridge_d_info), /* GT1 desktop */
 	INTEL_VGA_DEVICE(0x0162, &intel_ivybridge_d_info), /* GT2 desktop */
 	INTEL_VGA_DEVICE(0x015a, &intel_ivybridge_d_info), /* GT1 server */
+	INTEL_VGA_DEVICE(0x016a, &intel_ivybridge_d_info), /* GT2 server */
 	{0, 0, 0}
 };
 
@@ -467,6 +472,10 @@ static int i915_drm_freeze(struct drm_device *dev)
 	/* Modeset on resume, not lid events */
 	dev_priv->modeset_on_lid = 0;
 
+	console_lock();
+	intel_fbdev_set_suspend(dev, 1);
+	console_unlock();
+
 	return 0;
 }
 
@@ -529,7 +538,9 @@ static int i915_drm_thaw(struct drm_device *dev)
 		drm_irq_install(dev);
 
 		/* Resume the modeset for every activated CRTC */
+		mutex_lock(&dev->mode_config.mutex);
 		drm_helper_resume_force_mode(dev);
+		mutex_unlock(&dev->mode_config.mutex);
 
 		if (IS_IRONLAKE_M(dev))
 			ironlake_enable_rc6(dev);
@@ -539,6 +550,9 @@ static int i915_drm_thaw(struct drm_device *dev)
 
 	dev_priv->modeset_on_lid = 0;
 
+	console_lock();
+	intel_fbdev_set_suspend(dev, 0);
+	console_unlock();
 	return error;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c0f19f572004..5fabc6c31fec 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1053,6 +1053,27 @@ struct drm_i915_file_private {
 
 #include "i915_trace.h"
 
+/**
+ * RC6 is a special power stage which allows the GPU to enter an very
+ * low-voltage mode when idle, using down to 0V while at this stage.  This
+ * stage is entered automatically when the GPU is idle when RC6 support is
+ * enabled, and as soon as new workload arises GPU wakes up automatically as well.
+ *
+ * There are different RC6 modes available in Intel GPU, which differentiate
+ * among each other with the latency required to enter and leave RC6 and
+ * voltage consumed by the GPU in different states.
+ *
+ * The combination of the following flags define which states GPU is allowed
+ * to enter, while RC6 is the normal RC6 state, RC6p is the deep RC6, and
+ * RC6pp is deepest RC6. Their support by hardware varies according to the
+ * GPU, BIOS, chipset and platform. RC6 is usually the safest one and the one
+ * which brings the most power savings; deeper states save more power, but
+ * require higher latency to switch to and wake up.
+ */
+#define INTEL_RC6_ENABLE			(1<<0)
+#define INTEL_RC6p_ENABLE			(1<<1)
+#define INTEL_RC6pp_ENABLE			(1<<2)
+
 extern struct drm_ioctl_desc i915_ioctls[];
 extern int i915_max_ioctl;
 extern unsigned int i915_fbpercrtc __always_unused;
@@ -1065,7 +1086,7 @@ extern int i915_vbt_sdvo_panel_type __read_mostly;
 extern int i915_enable_rc6 __read_mostly;
 extern int i915_enable_fbc __read_mostly;
 extern bool i915_enable_hangcheck __read_mostly;
-extern bool i915_enable_ppgtt __read_mostly;
+extern int i915_enable_ppgtt __read_mostly;
 
 extern int i915_suspend(struct drm_device *dev, pm_message_t state);
 extern int i915_resume(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1f441f5c2405..4c65c639f772 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1472,16 +1472,19 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 	list_move_tail(&obj->ring_list, &ring->active_list);
 
 	obj->last_rendering_seqno = seqno;
-	if (obj->fenced_gpu_access) {
-		struct drm_i915_fence_reg *reg;
-
-		BUG_ON(obj->fence_reg == I915_FENCE_REG_NONE);
 
+	if (obj->fenced_gpu_access) {
 		obj->last_fenced_seqno = seqno;
 		obj->last_fenced_ring = ring;
 
-		reg = &dev_priv->fence_regs[obj->fence_reg];
-		list_move_tail(&reg->lru_list, &dev_priv->mm.fence_list);
+		/* Bump MRU to take account of the delayed flush */
+		if (obj->fence_reg != I915_FENCE_REG_NONE) {
+			struct drm_i915_fence_reg *reg;
+
+			reg = &dev_priv->fence_regs[obj->fence_reg];
+			list_move_tail(&reg->lru_list,
+				       &dev_priv->mm.fence_list);
+		}
 	}
 }
 
@@ -3754,12 +3757,32 @@ void i915_gem_init_ppgtt(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	uint32_t pd_offset;
 	struct intel_ring_buffer *ring;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	uint32_t __iomem *pd_addr;
+	uint32_t pd_entry;
 	int i;
 
 	if (!dev_priv->mm.aliasing_ppgtt)
 		return;
 
-	pd_offset = dev_priv->mm.aliasing_ppgtt->pd_offset;
+
+	pd_addr = dev_priv->mm.gtt->gtt + ppgtt->pd_offset/sizeof(uint32_t);
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		dma_addr_t pt_addr;
+
+		if (dev_priv->mm.gtt->needs_dmar)
+			pt_addr = ppgtt->pt_dma_addr[i];
+		else
+			pt_addr = page_to_phys(ppgtt->pt_pages[i]);
+
+		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
+		pd_entry |= GEN6_PDE_VALID;
+
+		writel(pd_entry, pd_addr + i);
+	}
+	readl(pd_addr);
+
+	pd_offset = ppgtt->pd_offset;
 	pd_offset /= 64; /* in cachelines, */
 	pd_offset <<= 16;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 81687af00893..f51a696486cb 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -498,8 +498,8 @@ pin_and_fence_object(struct drm_i915_gem_object *obj,
 				if (ret)
 					goto err_unpin;
 			}
+			obj->pending_fenced_gpu_access = true;
 		}
-		obj->pending_fenced_gpu_access = need_fence;
 	}
 
 	entry->offset = obj->gtt_offset;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 2eacd78bb93b..a135c61f4119 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -65,9 +65,7 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_hw_ppgtt *ppgtt;
-	uint32_t pd_entry;
 	unsigned first_pd_entry_in_global_pt;
-	uint32_t __iomem *pd_addr;
 	int i;
 	int ret = -ENOMEM;
 
@@ -100,7 +98,6 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 			goto err_pt_alloc;
 	}
 
-	pd_addr = dev_priv->mm.gtt->gtt + first_pd_entry_in_global_pt;
 	for (i = 0; i < ppgtt->num_pd_entries; i++) {
 		dma_addr_t pt_addr;
 		if (dev_priv->mm.gtt->needs_dmar) {
@@ -117,13 +114,7 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 			ppgtt->pt_dma_addr[i] = pt_addr;
 		} else
 			pt_addr = page_to_phys(ppgtt->pt_pages[i]);
-
-		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
-		pd_entry |= GEN6_PDE_VALID;
-
-		writel(pd_entry, pd_addr + i);
 	}
-	readl(pd_addr);
 
 	ppgtt->scratch_page_dma_addr = dev_priv->mm.gtt->scratch_page_dma;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3886cf051bac..2abf4eb94039 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2385,6 +2385,7 @@
 #define   PIPECONF_DISABLE	0
 #define   PIPECONF_DOUBLE_WIDE	(1<<30)
 #define   I965_PIPECONF_ACTIVE	(1<<30)
+#define   PIPECONF_FRAME_START_DELAY_MASK (3<<27)
 #define   PIPECONF_SINGLE_WIDE	0
 #define   PIPECONF_PIPE_UNLOCKED 0
 #define   PIPECONF_PIPE_LOCKED	(1<<25)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 8168d8f8a634..b48fc2a8410c 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -24,6 +24,7 @@
  *    Eric Anholt <eric@anholt.net>
  *
  */
+#include <linux/dmi.h>
 #include <drm/drm_dp_helper.h>
 #include "drmP.h"
 #include "drm.h"
@@ -621,6 +622,26 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	dev_priv->edp.bpp = 18;
 }
 
+static int __init intel_no_opregion_vbt_callback(const struct dmi_system_id *id)
+{
+	DRM_DEBUG_KMS("Falling back to manually reading VBT from "
+		      "VBIOS ROM for %s\n",
+		      id->ident);
+	return 1;
+}
+
+static const struct dmi_system_id intel_no_opregion_vbt[] = {
+	{
+		.callback = intel_no_opregion_vbt_callback,
+		.ident = "ThinkCentre A57",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "97027RG"),
+		},
+	},
+	{ }
+};
+
 /**
  * intel_parse_bios - find VBT and initialize settings from the BIOS
  * @dev: DRM device
@@ -641,7 +662,7 @@ intel_parse_bios(struct drm_device *dev)
 	init_vbt_defaults(dev_priv);
 
 	/* XXX Should this validation be moved to intel_opregion.c? */
-	if (dev_priv->opregion.vbt) {
+	if (!dmi_check_system(intel_no_opregion_vbt) && dev_priv->opregion.vbt) {
 		struct vbt_header *vbt = dev_priv->opregion.vbt;
 		if (memcmp(vbt->signature, "$VBT", 4) == 0) {
 			DRM_DEBUG_KMS("Using VBT from OpRegion: %20s\n",
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d514719f65e2..91b35fd1db8c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5539,7 +5539,8 @@ void ironlake_init_pch_refclk(struct drm_device *dev)
 		if (intel_panel_use_ssc(dev_priv) && can_ssc) {
 			DRM_DEBUG_KMS("Using SSC on panel\n");
 			temp |= DREF_SSC1_ENABLE;
-		}
+		} else
+			temp &= ~DREF_SSC1_ENABLE;
 
 		/* Get SSC going before enabling the outputs */
 		I915_WRITE(PCH_DREF_CONTROL, temp);
@@ -7580,6 +7581,12 @@ static void intel_sanitize_modesetting(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 reg, val;
 
+	/* Clear any frame start delays used for debugging left by the BIOS */
+	for_each_pipe(pipe) {
+		reg = PIPECONF(pipe);
+		I915_WRITE(reg, I915_READ(reg) & ~PIPECONF_FRAME_START_DELAY_MASK);
+	}
+
 	if (HAS_PCH_SPLIT(dev))
 		return;
 
@@ -8215,7 +8222,7 @@ void intel_init_emon(struct drm_device *dev)
 	dev_priv->corr = (lcfuse & LCFUSE_HIV_MASK);
 }
 
-static bool intel_enable_rc6(struct drm_device *dev)
+static int intel_enable_rc6(struct drm_device *dev)
 {
 	/*
 	 * Respect the kernel parameter if it is set
@@ -8233,11 +8240,11 @@ static bool intel_enable_rc6(struct drm_device *dev)
 	 * Disable rc6 on Sandybridge
 	 */
 	if (INTEL_INFO(dev)->gen == 6) {
-		DRM_DEBUG_DRIVER("Sandybridge: RC6 disabled\n");
-		return 0;
+		DRM_DEBUG_DRIVER("Sandybridge: deep RC6 disabled\n");
+		return INTEL_RC6_ENABLE;
 	}
-	DRM_DEBUG_DRIVER("RC6 enabled\n");
-	return 1;
+	DRM_DEBUG_DRIVER("RC6 and deep RC6 enabled\n");
+	return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
 }
 
 void gen6_enable_rps(struct drm_i915_private *dev_priv)
@@ -8247,6 +8254,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	u32 pcu_mbox, rc6_mask = 0;
 	u32 gtfifodbg;
 	int cur_freq, min_freq, max_freq;
+	int rc6_mode;
 	int i;
 
 	/* Here begins a magic sequence of register writes to enable
@@ -8284,9 +8292,20 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_RC6p_THRESHOLD, 100000);
 	I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
 
-	if (intel_enable_rc6(dev_priv->dev))
-		rc6_mask = GEN6_RC_CTL_RC6_ENABLE |
-			((IS_GEN7(dev_priv->dev)) ? GEN6_RC_CTL_RC6p_ENABLE : 0);
+	rc6_mode = intel_enable_rc6(dev_priv->dev);
+	if (rc6_mode & INTEL_RC6_ENABLE)
+		rc6_mask |= GEN6_RC_CTL_RC6_ENABLE;
+
+	if (rc6_mode & INTEL_RC6p_ENABLE)
+		rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
+
+	if (rc6_mode & INTEL_RC6pp_ENABLE)
+		rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
+
+	DRM_INFO("Enabling RC6 states: RC6 %s, RC6p %s, RC6pp %s\n",
+			(rc6_mode & INTEL_RC6_ENABLE) ? "on" : "off",
+			(rc6_mode & INTEL_RC6p_ENABLE) ? "on" : "off",
+			(rc6_mode & INTEL_RC6pp_ENABLE) ? "on" : "off");
 
 	I915_WRITE(GEN6_RC_CONTROL,
 		   rc6_mask |
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9cec6c3937fa..5a14149b3794 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -382,7 +382,7 @@ extern int intel_framebuffer_init(struct drm_device *dev,
 				  struct drm_i915_gem_object *obj);
 extern int intel_fbdev_init(struct drm_device *dev);
 extern void intel_fbdev_fini(struct drm_device *dev);
-
+extern void intel_fbdev_set_suspend(struct drm_device *dev, int state);
 extern void intel_prepare_page_flip(struct drm_device *dev, int plane);
 extern void intel_finish_page_flip(struct drm_device *dev, int pipe);
 extern void intel_finish_page_flip_plane(struct drm_device *dev, int plane);
diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c
index 2d8766978388..19ecd78b8a2c 100644
--- a/drivers/gpu/drm/i915/intel_fb.c
+++ b/drivers/gpu/drm/i915/intel_fb.c
@@ -254,6 +254,16 @@ void intel_fbdev_fini(struct drm_device *dev)
 	kfree(dev_priv->fbdev);
 	dev_priv->fbdev = NULL;
 }
+
+void intel_fbdev_set_suspend(struct drm_device *dev, int state)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	if (!dev_priv->fbdev)
+		return;
+
+	fb_set_suspend(dev_priv->fbdev->helper.fbdev, state);
+}
+
 MODULE_LICENSE("GPL and additional rights");
 
 void intel_fb_output_poll_changed(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index c5c0973af8a1..95db2e988227 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -755,6 +755,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "hp st5747"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "MSI Wind Box DC500",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"),
+			DMI_MATCH(DMI_BOARD_NAME, "MS-7469"),
+		},
+	},
 
 	{ }	/* terminating entry */
 };
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index fc66af6a9448..e25581a9f60f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -626,7 +626,7 @@ gen6_ring_get_seqno(struct intel_ring_buffer *ring)
 	/* Workaround to force correct ordering between irq and seqno writes on
 	 * ivb (and maybe also on snb) by reading from a CS register (like
 	 * ACTHD) before reading the status page. */
-	if (IS_GEN7(dev))
+	if (IS_GEN6(dev) || IS_GEN7(dev))
 		intel_ring_get_active_head(ring);
 	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
 }
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 7aa0450399a1..a464771a7240 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -411,6 +411,9 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 
 	old_obj = intel_plane->obj;
 
+	src_w = src_w >> 16;
+	src_h = src_h >> 16;
+
 	/* Pipe must be running... */
 	if (!(I915_READ(PIPECONF(pipe)) & PIPECONF_ENABLE))
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index ca1639918f57..97a81260485a 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -13,6 +13,7 @@ config DRM_NOUVEAU
 	select ACPI_VIDEO if ACPI && X86 && BACKLIGHT_CLASS_DEVICE && VIDEO_OUTPUT_CONTROL && INPUT
 	select ACPI_WMI if ACPI
 	select MXM_WMI if ACPI
+	select POWER_SUPPLY
 	help
 	  Choose this option for open-source nVidia support.
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 637afe71de56..80963d05b54a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -177,14 +177,15 @@ bios_shadow_pci(struct nvbios *bios)
 
 	if (!pci_enable_rom(pdev)) {
 		void __iomem *rom = pci_map_rom(pdev, &length);
-		if (rom) {
+		if (rom && length) {
 			bios->data = kmalloc(length, GFP_KERNEL);
 			if (bios->data) {
 				memcpy_fromio(bios->data, rom, length);
 				bios->length = length;
 			}
-			pci_unmap_rom(pdev, rom);
 		}
+		if (rom)
+			pci_unmap_rom(pdev, rom);
 
 		pci_disable_rom(pdev);
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_channel.c b/drivers/gpu/drm/nouveau/nouveau_channel.c
index 44e6416d4a33..846afb0bfef4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_channel.c
+++ b/drivers/gpu/drm/nouveau/nouveau_channel.c
@@ -436,11 +436,11 @@ nouveau_ioctl_fifo_alloc(struct drm_device *dev, void *data,
 	}
 
 	if (dev_priv->card_type < NV_C0) {
-		init->subchan[0].handle = NvSw;
-		init->subchan[0].grclass = NV_SW;
-		init->nr_subchan = 1;
-	} else {
-		init->nr_subchan = 0;
+		init->subchan[0].handle = 0x00000000;
+		init->subchan[0].grclass = 0x0000;
+		init->subchan[1].handle = NvSw;
+		init->subchan[1].grclass = NV_SW;
+		init->nr_subchan = 2;
 	}
 
 	/* Named memory object area */
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 8f510fd956b0..fa860358add1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -654,10 +654,13 @@ nouveau_connector_detect_depth(struct drm_connector *connector)
 	if (nv_connector->edid && connector->display_info.bpc)
 		return;
 
-	/* if not, we're out of options unless we're LVDS, default to 6bpc */
-	connector->display_info.bpc = 6;
-	if (nv_encoder->dcb->type != OUTPUT_LVDS)
+	/* if not, we're out of options unless we're LVDS, default to 8bpc */
+	if (nv_encoder->dcb->type != OUTPUT_LVDS) {
+		connector->display_info.bpc = 8;
 		return;
+	}
+
+	connector->display_info.bpc = 6;
 
 	/* LVDS: panel straps */
 	if (bios->fp_no_ddc) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.h b/drivers/gpu/drm/nouveau/nouveau_dma.h
index bcf0fd9e313e..23d4edf992b7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dma.h
+++ b/drivers/gpu/drm/nouveau/nouveau_dma.h
@@ -48,8 +48,8 @@ void nv50_dma_push(struct nouveau_channel *, struct nouveau_bo *,
 
 /* Hardcoded object assignments to subchannels (subchannel id). */
 enum {
-	NvSubSw		= 0,
-	NvSubM2MF	= 1,
+	NvSubM2MF	= 0,
+	NvSubSw		= 1,
 	NvSub2D		= 2,
 	NvSubCtxSurf2D  = 2,
 	NvSubGdiRect    = 3,
diff --git a/drivers/gpu/drm/nouveau/nouveau_i2c.c b/drivers/gpu/drm/nouveau/nouveau_i2c.c
index 8f4f914d9eab..e2be95af2e52 100644
--- a/drivers/gpu/drm/nouveau/nouveau_i2c.c
+++ b/drivers/gpu/drm/nouveau/nouveau_i2c.c
@@ -315,8 +315,8 @@ nouveau_i2c_init(struct drm_device *dev)
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nvbios *bios = &dev_priv->vbios;
 	struct nouveau_i2c_chan *port;
+	u8 version = 0x00, entries, recordlen;
 	u8 *i2c, *entry, legacy[2][4] = {};
-	u8 version, entries, recordlen;
 	int ret, i;
 
 	INIT_LIST_HEAD(&dev_priv->i2c_ports);
@@ -346,12 +346,12 @@ nouveau_i2c_init(struct drm_device *dev)
 		if (i2c[7]) legacy[1][1] = i2c[7];
 	}
 
-	if (i2c && version >= 0x30) {
+	if (version >= 0x30) {
 		entry     = i2c[1] + i2c;
 		entries   = i2c[2];
 		recordlen = i2c[3];
 	} else
-	if (i2c) {
+	if (version) {
 		entry     = i2c;
 		entries   = 16;
 		recordlen = 4;
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index a3ae91fa8141..c2a8511e855a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -642,7 +642,7 @@ nouveau_card_channel_init(struct drm_device *dev)
 		OUT_RING  (chan, chan->vram_handle);
 		OUT_RING  (chan, chan->gart_handle);
 	} else
-	if (dev_priv->card_type <= NV_C0) {
+	if (dev_priv->card_type <= NV_D0) {
 		ret = nouveau_gpuobj_gr_new(chan, 0x9039, 0x9039);
 		if (ret)
 			goto error;
@@ -852,7 +852,7 @@ nouveau_card_init(struct drm_device *dev)
 	if (ret)
 		goto out_pm;
 
-	if (!dev_priv->noaccel) {
+	if (dev_priv->eng[NVOBJ_ENGINE_GR]) {
 		ret = nouveau_card_channel_init(dev);
 		if (ret)
 			goto out_fence;
diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c
index d1bd239cd9e9..5ce9bf51a8de 100644
--- a/drivers/gpu/drm/radeon/atom.c
+++ b/drivers/gpu/drm/radeon/atom.c
@@ -1306,8 +1306,11 @@ struct atom_context *atom_parse(struct card_info *card, void *bios)
 
 int atom_asic_init(struct atom_context *ctx)
 {
+	struct radeon_device *rdev = ctx->card->dev->dev_private;
 	int hwi = CU16(ctx->data_table + ATOM_DATA_FWI_PTR);
 	uint32_t ps[16];
+	int ret;
+
 	memset(ps, 0, 64);
 
 	ps[0] = cpu_to_le32(CU32(hwi + ATOM_FWI_DEFSCLK_PTR));
@@ -1317,7 +1320,17 @@ int atom_asic_init(struct atom_context *ctx)
 
 	if (!CU16(ctx->cmd_table + 4 + 2 * ATOM_CMD_INIT))
 		return 1;
-	return atom_execute_table(ctx, ATOM_CMD_INIT, ps);
+	ret = atom_execute_table(ctx, ATOM_CMD_INIT, ps);
+	if (ret)
+		return ret;
+
+	memset(ps, 0, 64);
+
+	if (rdev->family < CHIP_R600) {
+		if (CU16(ctx->cmd_table + 4 + 2 * ATOM_CMD_SPDFANCNTL))
+			atom_execute_table(ctx, ATOM_CMD_SPDFANCNTL, ps);
+	}
+	return ret;
 }
 
 void atom_destroy(struct atom_context *ctx)
diff --git a/drivers/gpu/drm/radeon/atom.h b/drivers/gpu/drm/radeon/atom.h
index 93cfe2086ba0..25fea631dad2 100644
--- a/drivers/gpu/drm/radeon/atom.h
+++ b/drivers/gpu/drm/radeon/atom.h
@@ -44,6 +44,7 @@
 #define ATOM_CMD_SETSCLK	0x0A
 #define ATOM_CMD_SETMCLK	0x0B
 #define ATOM_CMD_SETPCLK	0x0C
+#define ATOM_CMD_SPDFANCNTL	0x39
 
 #define ATOM_DATA_FWI_PTR	0xC
 #define ATOM_DATA_IIO_PTR	0x32
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 083b3eada001..b5ff1f7b6f7e 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -588,8 +588,8 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 		if (encoder->crtc == crtc) {
 			radeon_encoder = to_radeon_encoder(encoder);
 			connector = radeon_get_connector_for_encoder(encoder);
-			if (connector && connector->display_info.bpc)
-				bpc = connector->display_info.bpc;
+			/* if (connector && connector->display_info.bpc)
+				bpc = connector->display_info.bpc; */
 			encoder_mode = atombios_get_encoder_mode(encoder);
 			is_duallink = radeon_dig_monitor_is_duallink(encoder, mode->clock);
 			if ((radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT | ATOM_DEVICE_DFP_SUPPORT)) ||
@@ -965,7 +965,9 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 		struct radeon_connector_atom_dig *dig_connector =
 			radeon_connector->con_priv;
 		int dp_clock;
-		bpc = connector->display_info.bpc;
+
+		/* if (connector->display_info.bpc)
+			bpc = connector->display_info.bpc; */
 
 		switch (encoder_mode) {
 		case ATOM_ENCODER_MODE_DP_MST:
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 6c62be226804..c57d85664e77 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -405,10 +405,13 @@ static void dp_get_adjust_train(u8 link_status[DP_LINK_STATUS_SIZE],
 /* get bpc from the EDID */
 static int convert_bpc_to_bpp(int bpc)
 {
+#if 0
 	if (bpc == 0)
 		return 24;
 	else
 		return bpc * 3;
+#endif
+	return 24;
 }
 
 /* get the max pix clock supported by the link rate and lane num */
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 468b874336f9..e607c4d7dd98 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -541,7 +541,7 @@ atombios_dig_encoder_setup(struct drm_encoder *encoder, int action, int panel_mo
 		dp_clock = dig_connector->dp_clock;
 		dp_lane_count = dig_connector->dp_lane_count;
 		hpd_id = radeon_connector->hpd.hpd;
-		bpc = connector->display_info.bpc;
+		/* bpc = connector->display_info.bpc; */
 	}
 
 	/* no dig encoder assigned */
@@ -1159,7 +1159,7 @@ atombios_external_encoder_setup(struct drm_encoder *encoder,
 		dp_lane_count = dig_connector->dp_lane_count;
 		connector_object_id =
 			(radeon_connector->connector_object_id & OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
-		bpc = connector->display_info.bpc;
+		/* bpc = connector->display_info.bpc; */
 	}
 
 	memset(&args, 0, sizeof(args));
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index a58b37a2e65a..70089d32b80f 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -80,6 +80,9 @@ struct evergreen_cs_track {
 	bool			cb_dirty;
 	bool			db_dirty;
 	bool			streamout_dirty;
+	u32			htile_offset;
+	u32			htile_surface;
+	struct radeon_bo	*htile_bo;
 };
 
 static u32 evergreen_cs_get_aray_mode(u32 tiling_flags)
@@ -144,6 +147,9 @@ static void evergreen_cs_track_init(struct evergreen_cs_track *track)
 	track->db_s_read_bo = NULL;
 	track->db_s_write_bo = NULL;
 	track->db_dirty = true;
+	track->htile_bo = NULL;
+	track->htile_offset = 0xFFFFFFFF;
+	track->htile_surface = 0;
 
 	for (i = 0; i < 4; i++) {
 		track->vgt_strmout_size[i] = 0;
@@ -444,6 +450,62 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
 	return 0;
 }
 
+static int evergreen_cs_track_validate_htile(struct radeon_cs_parser *p,
+						unsigned nbx, unsigned nby)
+{
+	struct evergreen_cs_track *track = p->track;
+	unsigned long size;
+
+	if (track->htile_bo == NULL) {
+		dev_warn(p->dev, "%s:%d htile enabled without htile surface 0x%08x\n",
+				__func__, __LINE__, track->db_z_info);
+		return -EINVAL;
+	}
+
+	if (G_028ABC_LINEAR(track->htile_surface)) {
+		/* pitch must be 16 htiles aligned == 16 * 8 pixel aligned */
+		nbx = round_up(nbx, 16 * 8);
+		/* height is npipes htiles aligned == npipes * 8 pixel aligned */
+		nby = round_up(nby, track->npipes * 8);
+	} else {
+		switch (track->npipes) {
+		case 8:
+			nbx = round_up(nbx, 64 * 8);
+			nby = round_up(nby, 64 * 8);
+			break;
+		case 4:
+			nbx = round_up(nbx, 64 * 8);
+			nby = round_up(nby, 32 * 8);
+			break;
+		case 2:
+			nbx = round_up(nbx, 32 * 8);
+			nby = round_up(nby, 32 * 8);
+			break;
+		case 1:
+			nbx = round_up(nbx, 32 * 8);
+			nby = round_up(nby, 16 * 8);
+			break;
+		default:
+			dev_warn(p->dev, "%s:%d invalid num pipes %d\n",
+					__func__, __LINE__, track->npipes);
+			return -EINVAL;
+		}
+	}
+	/* compute number of htile */
+	nbx = nbx / 8;
+	nby = nby / 8;
+	size = nbx * nby * 4;
+	size += track->htile_offset;
+
+	if (size > radeon_bo_size(track->htile_bo)) {
+		dev_warn(p->dev, "%s:%d htile surface too small %ld for %ld (%d %d)\n",
+				__func__, __LINE__, radeon_bo_size(track->htile_bo),
+				size, nbx, nby);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p)
 {
 	struct evergreen_cs_track *track = p->track;
@@ -530,6 +592,14 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p)
 		return -EINVAL;
 	}
 
+	/* hyperz */
+	if (G_028040_TILE_SURFACE_ENABLE(track->db_z_info)) {
+		r = evergreen_cs_track_validate_htile(p, surf.nbx, surf.nby);
+		if (r) {
+			return r;
+		}
+	}
+
 	return 0;
 }
 
@@ -617,6 +687,14 @@ static int evergreen_cs_track_validate_depth(struct radeon_cs_parser *p)
 		return -EINVAL;
 	}
 
+	/* hyperz */
+	if (G_028040_TILE_SURFACE_ENABLE(track->db_z_info)) {
+		r = evergreen_cs_track_validate_htile(p, surf.nbx, surf.nby);
+		if (r) {
+			return r;
+		}
+	}
+
 	return 0;
 }
 
@@ -850,7 +928,7 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 				return r;
 		}
 		/* Check depth buffer */
-		if (G_028800_Z_WRITE_ENABLE(track->db_depth_control)) {
+		if (G_028800_Z_ENABLE(track->db_depth_control)) {
 			r = evergreen_cs_track_validate_depth(p);
 			if (r)
 				return r;
@@ -1616,6 +1694,23 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->cb_color_bo[tmp] = reloc->robj;
 		track->cb_dirty = true;
 		break;
+	case DB_HTILE_DATA_BASE:
+		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONTEXT_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		track->htile_offset = radeon_get_ib_value(p, idx);
+		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		track->htile_bo = reloc->robj;
+		track->db_dirty = true;
+		break;
+	case DB_HTILE_SURFACE:
+		/* 8x8 only */
+		track->htile_surface = radeon_get_ib_value(p, idx);
+		track->db_dirty = true;
+		break;
 	case CB_IMMED0_BASE:
 	case CB_IMMED1_BASE:
 	case CB_IMMED2_BASE:
@@ -1628,7 +1723,6 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_IMMED9_BASE:
 	case CB_IMMED10_BASE:
 	case CB_IMMED11_BASE:
-	case DB_HTILE_DATA_BASE:
 	case SQ_PGM_START_FS:
 	case SQ_PGM_START_ES:
 	case SQ_PGM_START_VS:
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index eb5708c7159d..b4eefc355f16 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -991,6 +991,14 @@
 #define   G_028008_SLICE_MAX(x)                        (((x) >> 13) & 0x7FF)
 #define   C_028008_SLICE_MAX                           0xFF001FFF
 #define DB_HTILE_DATA_BASE				0x28014
+#define DB_HTILE_SURFACE				0x28abc
+#define   S_028ABC_HTILE_WIDTH(x)                      (((x) & 0x1) << 0)
+#define   G_028ABC_HTILE_WIDTH(x)                      (((x) >> 0) & 0x1)
+#define   C_028ABC_HTILE_WIDTH                         0xFFFFFFFE
+#define   S_028ABC_HTILE_HEIGHT(x)                      (((x) & 0x1) << 1)
+#define   G_028ABC_HTILE_HEIGHT(x)                      (((x) >> 1) & 0x1)
+#define   C_028ABC_HTILE_HEIGHT                         0xFFFFFFFD
+#define   G_028ABC_LINEAR(x)                           (((x) >> 2) & 0x1)
 #define DB_Z_INFO					0x28040
 #       define Z_ARRAY_MODE(x)                          ((x) << 4)
 #       define DB_TILE_SPLIT(x)                         (((x) & 0x7) << 8)
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 0ec3f205f9c4..b8e12af304a9 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -78,6 +78,9 @@ struct r600_cs_track {
 	bool			cb_dirty;
 	bool			db_dirty;
 	bool			streamout_dirty;
+	struct radeon_bo	*htile_bo;
+	u64			htile_offset;
+	u32			htile_surface;
 };
 
 #define FMT_8_BIT(fmt, vc)   [fmt] = { 1, 1, 1, vc, CHIP_R600 }
@@ -321,6 +324,9 @@ static void r600_cs_track_init(struct r600_cs_track *track)
 	track->db_depth_size_idx = 0;
 	track->db_depth_control = 0xFFFFFFFF;
 	track->db_dirty = true;
+	track->htile_bo = NULL;
+	track->htile_offset = 0xFFFFFFFF;
+	track->htile_surface = 0;
 
 	for (i = 0; i < 4; i++) {
 		track->vgt_strmout_size[i] = 0;
@@ -455,12 +461,256 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	return 0;
 }
 
+static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
+{
+	struct r600_cs_track *track = p->track;
+	u32 nviews, bpe, ntiles, size, slice_tile_max, tmp;
+	u32 height_align, pitch_align, depth_align;
+	u32 pitch = 8192;
+	u32 height = 8192;
+	u64 base_offset, base_align;
+	struct array_mode_checker array_check;
+	int array_mode;
+	volatile u32 *ib = p->ib->ptr;
+
+
+	if (track->db_bo == NULL) {
+		dev_warn(p->dev, "z/stencil with no depth buffer\n");
+		return -EINVAL;
+	}
+	switch (G_028010_FORMAT(track->db_depth_info)) {
+	case V_028010_DEPTH_16:
+		bpe = 2;
+		break;
+	case V_028010_DEPTH_X8_24:
+	case V_028010_DEPTH_8_24:
+	case V_028010_DEPTH_X8_24_FLOAT:
+	case V_028010_DEPTH_8_24_FLOAT:
+	case V_028010_DEPTH_32_FLOAT:
+		bpe = 4;
+		break;
+	case V_028010_DEPTH_X24_8_32_FLOAT:
+		bpe = 8;
+		break;
+	default:
+		dev_warn(p->dev, "z/stencil with invalid format %d\n", G_028010_FORMAT(track->db_depth_info));
+		return -EINVAL;
+	}
+	if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
+		if (!track->db_depth_size_idx) {
+			dev_warn(p->dev, "z/stencil buffer size not set\n");
+			return -EINVAL;
+		}
+		tmp = radeon_bo_size(track->db_bo) - track->db_offset;
+		tmp = (tmp / bpe) >> 6;
+		if (!tmp) {
+			dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n",
+					track->db_depth_size, bpe, track->db_offset,
+					radeon_bo_size(track->db_bo));
+			return -EINVAL;
+		}
+		ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF);
+	} else {
+		size = radeon_bo_size(track->db_bo);
+		/* pitch in pixels */
+		pitch = (G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1) * 8;
+		slice_tile_max = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
+		slice_tile_max *= 64;
+		height = slice_tile_max / pitch;
+		if (height > 8192)
+			height = 8192;
+		base_offset = track->db_bo_mc + track->db_offset;
+		array_mode = G_028010_ARRAY_MODE(track->db_depth_info);
+		array_check.array_mode = array_mode;
+		array_check.group_size = track->group_size;
+		array_check.nbanks = track->nbanks;
+		array_check.npipes = track->npipes;
+		array_check.nsamples = track->nsamples;
+		array_check.blocksize = bpe;
+		if (r600_get_array_mode_alignment(&array_check,
+					&pitch_align, &height_align, &depth_align, &base_align)) {
+			dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
+					G_028010_ARRAY_MODE(track->db_depth_info),
+					track->db_depth_info);
+			return -EINVAL;
+		}
+		switch (array_mode) {
+		case V_028010_ARRAY_1D_TILED_THIN1:
+			/* don't break userspace */
+			height &= ~0x7;
+			break;
+		case V_028010_ARRAY_2D_TILED_THIN1:
+			break;
+		default:
+			dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
+					G_028010_ARRAY_MODE(track->db_depth_info),
+					track->db_depth_info);
+			return -EINVAL;
+		}
+
+		if (!IS_ALIGNED(pitch, pitch_align)) {
+			dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n",
+					__func__, __LINE__, pitch, pitch_align, array_mode);
+			return -EINVAL;
+		}
+		if (!IS_ALIGNED(height, height_align)) {
+			dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n",
+					__func__, __LINE__, height, height_align, array_mode);
+			return -EINVAL;
+		}
+		if (!IS_ALIGNED(base_offset, base_align)) {
+			dev_warn(p->dev, "%s offset 0x%llx, 0x%llx, %d not aligned\n", __func__,
+					base_offset, base_align, array_mode);
+			return -EINVAL;
+		}
+
+		ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
+		nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
+		tmp = ntiles * bpe * 64 * nviews;
+		if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
+			dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
+					array_mode,
+					track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
+					radeon_bo_size(track->db_bo));
+			return -EINVAL;
+		}
+	}
+
+	/* hyperz */
+	if (G_028010_TILE_SURFACE_ENABLE(track->db_depth_info)) {
+		unsigned long size;
+		unsigned nbx, nby;
+
+		if (track->htile_bo == NULL) {
+			dev_warn(p->dev, "%s:%d htile enabled without htile surface 0x%08x\n",
+				 __func__, __LINE__, track->db_depth_info);
+			return -EINVAL;
+		}
+		if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
+			dev_warn(p->dev, "%s:%d htile can't be enabled with bogus db_depth_size 0x%08x\n",
+				 __func__, __LINE__, track->db_depth_size);
+			return -EINVAL;
+		}
+
+		nbx = pitch;
+		nby = height;
+		if (G_028D24_LINEAR(track->htile_surface)) {
+			/* nbx must be 16 htiles aligned == 16 * 8 pixel aligned */
+			nbx = round_up(nbx, 16 * 8);
+			/* nby is npipes htiles aligned == npipes * 8 pixel aligned */
+			nby = round_up(nby, track->npipes * 8);
+		} else {
+			/* htile widht & nby (8 or 4) make 2 bits number */
+			tmp = track->htile_surface & 3;
+			/* align is htile align * 8, htile align vary according to
+			 * number of pipe and tile width and nby
+			 */
+			switch (track->npipes) {
+			case 8:
+				switch (tmp) {
+				case 3:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 8*/
+					nbx = round_up(nbx, 64 * 8);
+					nby = round_up(nby, 64 * 8);
+					break;
+				case 2:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 8*/
+				case 1:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 64 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				case 0:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			case 4:
+				switch (tmp) {
+				case 3:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 8*/
+					nbx = round_up(nbx, 64 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				case 2:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 8*/
+				case 1:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				case 0:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			case 2:
+				switch (tmp) {
+				case 3:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 8*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				case 2:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 8*/
+				case 1:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				case 0:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 16 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			case 1:
+				switch (tmp) {
+				case 3:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 8*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				case 2:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 8*/
+				case 1:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 16 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				case 0:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 16 * 8);
+					nby = round_up(nby, 8 * 8);
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			default:
+				dev_warn(p->dev, "%s:%d invalid num pipes %d\n",
+					 __func__, __LINE__, track->npipes);
+				return -EINVAL;
+			}
+		}
+		/* compute number of htile */
+		nbx = G_028D24_HTILE_WIDTH(track->htile_surface) ? nbx / 8 : nbx / 4;
+		nby = G_028D24_HTILE_HEIGHT(track->htile_surface) ? nby / 8 : nby / 4;
+		size = nbx * nby * 4;
+		size += track->htile_offset;
+
+		if (size > radeon_bo_size(track->htile_bo)) {
+			dev_warn(p->dev, "%s:%d htile surface too small %ld for %ld (%d %d)\n",
+				 __func__, __LINE__, radeon_bo_size(track->htile_bo),
+				 size, nbx, nby);
+			return -EINVAL;
+		}
+	}
+
+	track->db_dirty = false;
+	return 0;
+}
+
 static int r600_cs_track_check(struct radeon_cs_parser *p)
 {
 	struct r600_cs_track *track = p->track;
 	u32 tmp;
 	int r, i;
-	volatile u32 *ib = p->ib->ptr;
 
 	/* on legacy kernel we don't perform advanced check */
 	if (p->rdev == NULL)
@@ -513,124 +763,14 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 		track->cb_dirty = false;
 	}
 
-	if (track->db_dirty) {
-		/* Check depth buffer */
-		if (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
-			G_028800_Z_ENABLE(track->db_depth_control)) {
-			u32 nviews, bpe, ntiles, size, slice_tile_max;
-			u32 height, height_align, pitch, pitch_align, depth_align;
-			u64 base_offset, base_align;
-			struct array_mode_checker array_check;
-			int array_mode;
-
-			if (track->db_bo == NULL) {
-				dev_warn(p->dev, "z/stencil with no depth buffer\n");
-				return -EINVAL;
-			}
-			if (G_028010_TILE_SURFACE_ENABLE(track->db_depth_info)) {
-				dev_warn(p->dev, "this kernel doesn't support z/stencil htile\n");
-				return -EINVAL;
-			}
-			switch (G_028010_FORMAT(track->db_depth_info)) {
-			case V_028010_DEPTH_16:
-				bpe = 2;
-				break;
-			case V_028010_DEPTH_X8_24:
-			case V_028010_DEPTH_8_24:
-			case V_028010_DEPTH_X8_24_FLOAT:
-			case V_028010_DEPTH_8_24_FLOAT:
-			case V_028010_DEPTH_32_FLOAT:
-				bpe = 4;
-				break;
-			case V_028010_DEPTH_X24_8_32_FLOAT:
-				bpe = 8;
-				break;
-			default:
-				dev_warn(p->dev, "z/stencil with invalid format %d\n", G_028010_FORMAT(track->db_depth_info));
-				return -EINVAL;
-			}
-			if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
-				if (!track->db_depth_size_idx) {
-					dev_warn(p->dev, "z/stencil buffer size not set\n");
-					return -EINVAL;
-				}
-				tmp = radeon_bo_size(track->db_bo) - track->db_offset;
-				tmp = (tmp / bpe) >> 6;
-				if (!tmp) {
-					dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n",
-							track->db_depth_size, bpe, track->db_offset,
-							radeon_bo_size(track->db_bo));
-					return -EINVAL;
-				}
-				ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF);
-			} else {
-				size = radeon_bo_size(track->db_bo);
-				/* pitch in pixels */
-				pitch = (G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1) * 8;
-				slice_tile_max = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
-				slice_tile_max *= 64;
-				height = slice_tile_max / pitch;
-				if (height > 8192)
-					height = 8192;
-				base_offset = track->db_bo_mc + track->db_offset;
-				array_mode = G_028010_ARRAY_MODE(track->db_depth_info);
-				array_check.array_mode = array_mode;
-				array_check.group_size = track->group_size;
-				array_check.nbanks = track->nbanks;
-				array_check.npipes = track->npipes;
-				array_check.nsamples = track->nsamples;
-				array_check.blocksize = bpe;
-				if (r600_get_array_mode_alignment(&array_check,
-								  &pitch_align, &height_align, &depth_align, &base_align)) {
-					dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
-						 G_028010_ARRAY_MODE(track->db_depth_info),
-						 track->db_depth_info);
-					return -EINVAL;
-				}
-				switch (array_mode) {
-				case V_028010_ARRAY_1D_TILED_THIN1:
-					/* don't break userspace */
-					height &= ~0x7;
-					break;
-				case V_028010_ARRAY_2D_TILED_THIN1:
-					break;
-				default:
-					dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
-						 G_028010_ARRAY_MODE(track->db_depth_info),
-						 track->db_depth_info);
-					return -EINVAL;
-				}
-
-				if (!IS_ALIGNED(pitch, pitch_align)) {
-					dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n",
-						 __func__, __LINE__, pitch, pitch_align, array_mode);
-					return -EINVAL;
-				}
-				if (!IS_ALIGNED(height, height_align)) {
-					dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n",
-						 __func__, __LINE__, height, height_align, array_mode);
-					return -EINVAL;
-				}
-				if (!IS_ALIGNED(base_offset, base_align)) {
-					dev_warn(p->dev, "%s offset[%d] 0x%llx, 0x%llx, %d not aligned\n", __func__, i,
-						 base_offset, base_align, array_mode);
-					return -EINVAL;
-				}
-
-				ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
-				nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
-				tmp = ntiles * bpe * 64 * nviews;
-				if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
-					dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
-						 array_mode,
-						 track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
-						 radeon_bo_size(track->db_bo));
-					return -EINVAL;
-				}
-			}
-		}
-		track->db_dirty = false;
+	/* Check depth buffer */
+	if (track->db_dirty && (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
+		G_028800_Z_ENABLE(track->db_depth_control))) {
+		r = r600_cs_track_validate_db(p);
+		if (r)
+			return r;
 	}
+
 	return 0;
 }
 
@@ -1244,6 +1384,21 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_dirty = true;
 		break;
 	case DB_HTILE_DATA_BASE:
+		r = r600_cs_packet_next_reloc(p, &reloc);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONTEXT_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		track->htile_offset = radeon_get_ib_value(p, idx) << 8;
+		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		track->htile_bo = reloc->robj;
+		track->db_dirty = true;
+		break;
+	case DB_HTILE_SURFACE:
+		track->htile_surface = radeon_get_ib_value(p, idx);
+		track->db_dirty = true;
+		break;
 	case SQ_PGM_START_FS:
 	case SQ_PGM_START_ES:
 	case SQ_PGM_START_VS:
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 3568a2e345fa..59f9c993cc31 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -195,6 +195,14 @@
 #define		PREZ_MUST_WAIT_FOR_POSTZ_DONE			(1 << 31)
 #define	DB_DEPTH_BASE					0x2800C
 #define	DB_HTILE_DATA_BASE				0x28014
+#define	DB_HTILE_SURFACE				0x28D24
+#define   S_028D24_HTILE_WIDTH(x)                      (((x) & 0x1) << 0)
+#define   G_028D24_HTILE_WIDTH(x)                      (((x) >> 0) & 0x1)
+#define   C_028D24_HTILE_WIDTH                         0xFFFFFFFE
+#define   S_028D24_HTILE_HEIGHT(x)                      (((x) & 0x1) << 1)
+#define   G_028D24_HTILE_HEIGHT(x)                      (((x) >> 1) & 0x1)
+#define   C_028D24_HTILE_HEIGHT                         0xFFFFFFFD
+#define   G_028D24_LINEAR(x)                           (((x) >> 2) & 0x1)
 #define	DB_WATERMARKS					0x9838
 #define		DEPTH_FREE(x)					((x) << 0)
 #define		DEPTH_FLUSH(x)					((x) << 5)
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 91541e63d582..df6a4dbd93f8 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -233,7 +233,18 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 		bo->pin_count++;
 		if (gpu_addr)
 			*gpu_addr = radeon_bo_gpu_offset(bo);
-		WARN_ON_ONCE(max_offset != 0);
+
+		if (max_offset != 0) {
+			u64 domain_start;
+
+			if (domain == RADEON_GEM_DOMAIN_VRAM)
+				domain_start = bo->rdev->mc.vram_start;
+			else
+				domain_start = bo->rdev->mc.gtt_start;
+			WARN_ON_ONCE(max_offset <
+				     (radeon_bo_gpu_offset(bo) - domain_start));
+		}
+
 		return 0;
 	}
 	radeon_ttm_placement_from_domain(bo, domain);
diff --git a/drivers/gpu/drm/radeon/reg_srcs/cayman b/drivers/gpu/drm/radeon/reg_srcs/cayman
index aea63c415852..0f656b111c15 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/cayman
+++ b/drivers/gpu/drm/radeon/reg_srcs/cayman
@@ -509,7 +509,6 @@ cayman 0x9400
 0x00028AA8 IA_MULTI_VGT_PARAM
 0x00028AB4 VGT_REUSE_OFF
 0x00028AB8 VGT_VTX_CNT_EN
-0x00028ABC DB_HTILE_SURFACE
 0x00028AC0 DB_SRESULTS_COMPARE_STATE0
 0x00028AC4 DB_SRESULTS_COMPARE_STATE1
 0x00028AC8 DB_PRELOAD_CONTROL
diff --git a/drivers/gpu/drm/radeon/reg_srcs/evergreen b/drivers/gpu/drm/radeon/reg_srcs/evergreen
index 77c37202376f..b912a37689bf 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/evergreen
+++ b/drivers/gpu/drm/radeon/reg_srcs/evergreen
@@ -519,7 +519,6 @@ evergreen 0x9400
 0x00028AA4 VGT_INSTANCE_STEP_RATE_1
 0x00028AB4 VGT_REUSE_OFF
 0x00028AB8 VGT_VTX_CNT_EN
-0x00028ABC DB_HTILE_SURFACE
 0x00028AC0 DB_SRESULTS_COMPARE_STATE0
 0x00028AC4 DB_SRESULTS_COMPARE_STATE1
 0x00028AC8 DB_PRELOAD_CONTROL
diff --git a/drivers/gpu/drm/radeon/reg_srcs/r600 b/drivers/gpu/drm/radeon/reg_srcs/r600
index 626c24ea0b56..5e659b034d9a 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/r600
+++ b/drivers/gpu/drm/radeon/reg_srcs/r600
@@ -713,7 +713,6 @@ r600 0x9400
 0x0000A710 TD_VS_SAMPLER17_BORDER_RED
 0x00009508 TA_CNTL_AUX
 0x0002802C DB_DEPTH_CLEAR
-0x00028D24 DB_HTILE_SURFACE
 0x00028D34 DB_PREFETCH_LIMIT
 0x00028D30 DB_PRELOAD_CONTROL
 0x00028D0C DB_RENDER_CONTROL
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 5340c5f3987b..53673907a6a0 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -47,7 +47,7 @@ static struct vm_operations_struct udl_gem_vm_ops = {
 static const struct file_operations udl_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
-	.mmap = drm_gem_mmap,
+	.mmap = udl_drm_gem_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
 	.unlocked_ioctl	= drm_ioctl,
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 1612954a5bc4..96820d03a303 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -121,6 +121,7 @@ struct udl_gem_object *udl_gem_alloc_object(struct drm_device *dev,
 
 int udl_gem_vmap(struct udl_gem_object *obj);
 void udl_gem_vunmap(struct udl_gem_object *obj);
+int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
 int udl_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 852642dc1187..92f19ef329b0 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -71,6 +71,20 @@ int udl_dumb_destroy(struct drm_file *file, struct drm_device *dev,
 	return drm_gem_handle_delete(file, handle);
 }
 
+int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	int ret;
+
+	ret = drm_gem_mmap(filp, vma);
+	if (ret)
+		return ret;
+
+	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
+
+	return ret;
+}
+
 int udl_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct udl_gem_object *obj = to_udl_bo(vma->vm_private_data);
diff --git a/drivers/hid/hid-picolcd.c b/drivers/hid/hid-picolcd.c
index 12f9777c385d..45c3433f7986 100644
--- a/drivers/hid/hid-picolcd.c
+++ b/drivers/hid/hid-picolcd.c
@@ -1525,12 +1525,6 @@ static const struct file_operations picolcd_debug_reset_fops = {
 /*
  * The "eeprom" file
  */
-static int picolcd_debug_eeprom_open(struct inode *i, struct file *f)
-{
-	f->private_data = i->i_private;
-	return 0;
-}
-
 static ssize_t picolcd_debug_eeprom_read(struct file *f, char __user *u,
 		size_t s, loff_t *off)
 {
@@ -1618,7 +1612,7 @@ static ssize_t picolcd_debug_eeprom_write(struct file *f, const char __user *u,
  */
 static const struct file_operations picolcd_debug_eeprom_fops = {
 	.owner    = THIS_MODULE,
-	.open     = picolcd_debug_eeprom_open,
+	.open     = simple_open,
 	.read     = picolcd_debug_eeprom_read,
 	.write    = picolcd_debug_eeprom_write,
 	.llseek   = generic_file_llseek,
@@ -1627,12 +1621,6 @@ static const struct file_operations picolcd_debug_eeprom_fops = {
 /*
  * The "flash" file
  */
-static int picolcd_debug_flash_open(struct inode *i, struct file *f)
-{
-	f->private_data = i->i_private;
-	return 0;
-}
-
 /* record a flash address to buf (bounds check to be done by caller) */
 static int _picolcd_flash_setaddr(struct picolcd_data *data, u8 *buf, long off)
 {
@@ -1817,7 +1805,7 @@ static ssize_t picolcd_debug_flash_write(struct file *f, const char __user *u,
  */
 static const struct file_operations picolcd_debug_flash_fops = {
 	.owner    = THIS_MODULE,
-	.open     = picolcd_debug_flash_open,
+	.open     = simple_open,
 	.read     = picolcd_debug_flash_read,
 	.write    = picolcd_debug_flash_write,
 	.llseek   = generic_file_llseek,
diff --git a/drivers/hid/hid-wiimote-debug.c b/drivers/hid/hid-wiimote-debug.c
index 17dabc1f339e..eec329197c16 100644
--- a/drivers/hid/hid-wiimote-debug.c
+++ b/drivers/hid/hid-wiimote-debug.c
@@ -23,12 +23,6 @@ struct wiimote_debug {
 	struct dentry *drm;
 };
 
-static int wiidebug_eeprom_open(struct inode *i, struct file *f)
-{
-	f->private_data = i->i_private;
-	return 0;
-}
-
 static ssize_t wiidebug_eeprom_read(struct file *f, char __user *u, size_t s,
 								loff_t *off)
 {
@@ -83,7 +77,7 @@ static ssize_t wiidebug_eeprom_read(struct file *f, char __user *u, size_t s,
 
 static const struct file_operations wiidebug_eeprom_fops = {
 	.owner = THIS_MODULE,
-	.open = wiidebug_eeprom_open,
+	.open = simple_open,
 	.read = wiidebug_eeprom_read,
 	.llseek = generic_file_llseek,
 };
diff --git a/drivers/hsi/Kconfig b/drivers/hsi/Kconfig
new file mode 100644
index 000000000000..d94e38dd80c7
--- /dev/null
+++ b/drivers/hsi/Kconfig
@@ -0,0 +1,19 @@
+#
+# HSI driver configuration
+#
+menuconfig HSI
+	tristate "HSI support"
+	---help---
+	  The "High speed synchronous Serial Interface" is
+	  synchronous serial interface used mainly to connect
+	  application engines and cellular modems.
+
+if HSI
+
+config HSI_BOARDINFO
+	bool
+	default y
+
+source "drivers/hsi/clients/Kconfig"
+
+endif # HSI
diff --git a/drivers/hsi/Makefile b/drivers/hsi/Makefile
new file mode 100644
index 000000000000..9d5d33f90de2
--- /dev/null
+++ b/drivers/hsi/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for HSI
+#
+obj-$(CONFIG_HSI_BOARDINFO)	+= hsi_boardinfo.o
+obj-$(CONFIG_HSI)		+= hsi.o
+obj-y				+= clients/
diff --git a/drivers/hsi/clients/Kconfig b/drivers/hsi/clients/Kconfig
new file mode 100644
index 000000000000..3bacd275f479
--- /dev/null
+++ b/drivers/hsi/clients/Kconfig
@@ -0,0 +1,13 @@
+#
+# HSI clients configuration
+#
+
+comment "HSI clients"
+
+config HSI_CHAR
+	tristate "HSI/SSI character driver"
+	depends on HSI
+	---help---
+	  If you say Y here, you will enable the HSI/SSI character driver.
+	  This driver provides a simple character device interface for
+	  serial communication with the cellular modem over HSI/SSI bus.
diff --git a/drivers/hsi/clients/Makefile b/drivers/hsi/clients/Makefile
new file mode 100644
index 000000000000..327c0e27c8b0
--- /dev/null
+++ b/drivers/hsi/clients/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for HSI clients
+#
+
+obj-$(CONFIG_HSI_CHAR)	+= hsi_char.o
diff --git a/drivers/hsi/clients/hsi_char.c b/drivers/hsi/clients/hsi_char.c
new file mode 100644
index 000000000000..88a050df2389
--- /dev/null
+++ b/drivers/hsi/clients/hsi_char.c
@@ -0,0 +1,802 @@
+/*
+ * HSI character device driver, implements the character device
+ * interface.
+ *
+ * Copyright (C) 2010 Nokia Corporation. All rights reserved.
+ *
+ * Contact: Andras Domokos <andras.domokos@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/kmemleak.h>
+#include <linux/ioctl.h>
+#include <linux/wait.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/device.h>
+#include <linux/cdev.h>
+#include <linux/uaccess.h>
+#include <linux/scatterlist.h>
+#include <linux/stat.h>
+#include <linux/hsi/hsi.h>
+#include <linux/hsi/hsi_char.h>
+
+#define HSC_DEVS		16 /* Num of channels */
+#define HSC_MSGS		4
+
+#define HSC_RXBREAK		0
+
+#define HSC_ID_BITS		6
+#define HSC_PORT_ID_BITS	4
+#define HSC_ID_MASK		3
+#define HSC_PORT_ID_MASK	3
+#define HSC_CH_MASK		0xf
+
+/*
+ * We support up to 4 controllers that can have up to 4
+ * ports, which should currently be more than enough.
+ */
+#define HSC_BASEMINOR(id, port_id) \
+		((((id) & HSC_ID_MASK) << HSC_ID_BITS) | \
+		(((port_id) & HSC_PORT_ID_MASK) << HSC_PORT_ID_BITS))
+
+enum {
+	HSC_CH_OPEN,
+	HSC_CH_READ,
+	HSC_CH_WRITE,
+	HSC_CH_WLINE,
+};
+
+enum {
+	HSC_RX,
+	HSC_TX,
+};
+
+struct hsc_client_data;
+/**
+ * struct hsc_channel - hsi_char internal channel data
+ * @ch: channel number
+ * @flags: Keeps state of the channel (open/close, reading, writing)
+ * @free_msgs_list: List of free HSI messages/requests
+ * @rx_msgs_queue: List of pending RX requests
+ * @tx_msgs_queue: List of pending TX requests
+ * @lock: Serialize access to the lists
+ * @cl: reference to the associated hsi_client
+ * @cl_data: reference to the client data that this channels belongs to
+ * @rx_wait: RX requests wait queue
+ * @tx_wait: TX requests wait queue
+ */
+struct hsc_channel {
+	unsigned int		ch;
+	unsigned long		flags;
+	struct list_head	free_msgs_list;
+	struct list_head	rx_msgs_queue;
+	struct list_head	tx_msgs_queue;
+	spinlock_t		lock;
+	struct hsi_client	*cl;
+	struct hsc_client_data *cl_data;
+	wait_queue_head_t	rx_wait;
+	wait_queue_head_t	tx_wait;
+};
+
+/**
+ * struct hsc_client_data - hsi_char internal client data
+ * @cdev: Characther device associated to the hsi_client
+ * @lock: Lock to serialize open/close access
+ * @flags: Keeps track of port state (rx hwbreak armed)
+ * @usecnt: Use count for claiming the HSI port (mutex protected)
+ * @cl: Referece to the HSI client
+ * @channels: Array of channels accessible by the client
+ */
+struct hsc_client_data {
+	struct cdev		cdev;
+	struct mutex		lock;
+	unsigned long		flags;
+	unsigned int		usecnt;
+	struct hsi_client	*cl;
+	struct hsc_channel	channels[HSC_DEVS];
+};
+
+/* Stores the major number dynamically allocated for hsi_char */
+static unsigned int hsc_major;
+/* Maximum buffer size that hsi_char will accept from userspace */
+static unsigned int max_data_size = 0x1000;
+module_param(max_data_size, uint, S_IRUSR | S_IWUSR);
+MODULE_PARM_DESC(max_data_size, "max read/write data size [4,8..65536] (^2)");
+
+static void hsc_add_tail(struct hsc_channel *channel, struct hsi_msg *msg,
+							struct list_head *queue)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&channel->lock, flags);
+	list_add_tail(&msg->link, queue);
+	spin_unlock_irqrestore(&channel->lock, flags);
+}
+
+static struct hsi_msg *hsc_get_first_msg(struct hsc_channel *channel,
+							struct list_head *queue)
+{
+	struct hsi_msg *msg = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&channel->lock, flags);
+
+	if (list_empty(queue))
+		goto out;
+
+	msg = list_first_entry(queue, struct hsi_msg, link);
+	list_del(&msg->link);
+out:
+	spin_unlock_irqrestore(&channel->lock, flags);
+
+	return msg;
+}
+
+static inline void hsc_msg_free(struct hsi_msg *msg)
+{
+	kfree(sg_virt(msg->sgt.sgl));
+	hsi_free_msg(msg);
+}
+
+static void hsc_free_list(struct list_head *list)
+{
+	struct hsi_msg *msg, *tmp;
+
+	list_for_each_entry_safe(msg, tmp, list, link) {
+		list_del(&msg->link);
+		hsc_msg_free(msg);
+	}
+}
+
+static void hsc_reset_list(struct hsc_channel *channel, struct list_head *l)
+{
+	unsigned long flags;
+	LIST_HEAD(list);
+
+	spin_lock_irqsave(&channel->lock, flags);
+	list_splice_init(l, &list);
+	spin_unlock_irqrestore(&channel->lock, flags);
+
+	hsc_free_list(&list);
+}
+
+static inline struct hsi_msg *hsc_msg_alloc(unsigned int alloc_size)
+{
+	struct hsi_msg *msg;
+	void *buf;
+
+	msg = hsi_alloc_msg(1, GFP_KERNEL);
+	if (!msg)
+		goto out;
+	buf = kmalloc(alloc_size, GFP_KERNEL);
+	if (!buf) {
+		hsi_free_msg(msg);
+		goto out;
+	}
+	sg_init_one(msg->sgt.sgl, buf, alloc_size);
+	/* Ignore false positive, due to sg pointer handling */
+	kmemleak_ignore(buf);
+
+	return msg;
+out:
+	return NULL;
+}
+
+static inline int hsc_msgs_alloc(struct hsc_channel *channel)
+{
+	struct hsi_msg *msg;
+	int i;
+
+	for (i = 0; i < HSC_MSGS; i++) {
+		msg = hsc_msg_alloc(max_data_size);
+		if (!msg)
+			goto out;
+		msg->channel = channel->ch;
+		list_add_tail(&msg->link, &channel->free_msgs_list);
+	}
+
+	return 0;
+out:
+	hsc_free_list(&channel->free_msgs_list);
+
+	return -ENOMEM;
+}
+
+static inline unsigned int hsc_msg_len_get(struct hsi_msg *msg)
+{
+	return msg->sgt.sgl->length;
+}
+
+static inline void hsc_msg_len_set(struct hsi_msg *msg, unsigned int len)
+{
+	msg->sgt.sgl->length = len;
+}
+
+static void hsc_rx_completed(struct hsi_msg *msg)
+{
+	struct hsc_client_data *cl_data = hsi_client_drvdata(msg->cl);
+	struct hsc_channel *channel = cl_data->channels + msg->channel;
+
+	if (test_bit(HSC_CH_READ, &channel->flags)) {
+		hsc_add_tail(channel, msg, &channel->rx_msgs_queue);
+		wake_up(&channel->rx_wait);
+	} else {
+		hsc_add_tail(channel, msg, &channel->free_msgs_list);
+	}
+}
+
+static void hsc_rx_msg_destructor(struct hsi_msg *msg)
+{
+	msg->status = HSI_STATUS_ERROR;
+	hsc_msg_len_set(msg, 0);
+	hsc_rx_completed(msg);
+}
+
+static void hsc_tx_completed(struct hsi_msg *msg)
+{
+	struct hsc_client_data *cl_data = hsi_client_drvdata(msg->cl);
+	struct hsc_channel *channel = cl_data->channels + msg->channel;
+
+	if (test_bit(HSC_CH_WRITE, &channel->flags)) {
+		hsc_add_tail(channel, msg, &channel->tx_msgs_queue);
+		wake_up(&channel->tx_wait);
+	} else {
+		hsc_add_tail(channel, msg, &channel->free_msgs_list);
+	}
+}
+
+static void hsc_tx_msg_destructor(struct hsi_msg *msg)
+{
+	msg->status = HSI_STATUS_ERROR;
+	hsc_msg_len_set(msg, 0);
+	hsc_tx_completed(msg);
+}
+
+static void hsc_break_req_destructor(struct hsi_msg *msg)
+{
+	struct hsc_client_data *cl_data = hsi_client_drvdata(msg->cl);
+
+	hsi_free_msg(msg);
+	clear_bit(HSC_RXBREAK, &cl_data->flags);
+}
+
+static void hsc_break_received(struct hsi_msg *msg)
+{
+	struct hsc_client_data *cl_data = hsi_client_drvdata(msg->cl);
+	struct hsc_channel *channel = cl_data->channels;
+	int i, ret;
+
+	/* Broadcast HWBREAK on all channels */
+	for (i = 0; i < HSC_DEVS; i++, channel++) {
+		struct hsi_msg *msg2;
+
+		if (!test_bit(HSC_CH_READ, &channel->flags))
+			continue;
+		msg2 = hsc_get_first_msg(channel, &channel->free_msgs_list);
+		if (!msg2)
+			continue;
+		clear_bit(HSC_CH_READ, &channel->flags);
+		hsc_msg_len_set(msg2, 0);
+		msg2->status = HSI_STATUS_COMPLETED;
+		hsc_add_tail(channel, msg2, &channel->rx_msgs_queue);
+		wake_up(&channel->rx_wait);
+	}
+	hsi_flush(msg->cl);
+	ret = hsi_async_read(msg->cl, msg);
+	if (ret < 0)
+		hsc_break_req_destructor(msg);
+}
+
+static int hsc_break_request(struct hsi_client *cl)
+{
+	struct hsc_client_data *cl_data = hsi_client_drvdata(cl);
+	struct hsi_msg *msg;
+	int ret;
+
+	if (test_and_set_bit(HSC_RXBREAK, &cl_data->flags))
+		return -EBUSY;
+
+	msg = hsi_alloc_msg(0, GFP_KERNEL);
+	if (!msg) {
+		clear_bit(HSC_RXBREAK, &cl_data->flags);
+		return -ENOMEM;
+	}
+	msg->break_frame = 1;
+	msg->complete = hsc_break_received;
+	msg->destructor = hsc_break_req_destructor;
+	ret = hsi_async_read(cl, msg);
+	if (ret < 0)
+		hsc_break_req_destructor(msg);
+
+	return ret;
+}
+
+static int hsc_break_send(struct hsi_client *cl)
+{
+	struct hsi_msg *msg;
+	int ret;
+
+	msg = hsi_alloc_msg(0, GFP_ATOMIC);
+	if (!msg)
+		return -ENOMEM;
+	msg->break_frame = 1;
+	msg->complete = hsi_free_msg;
+	msg->destructor = hsi_free_msg;
+	ret = hsi_async_write(cl, msg);
+	if (ret < 0)
+		hsi_free_msg(msg);
+
+	return ret;
+}
+
+static int hsc_rx_set(struct hsi_client *cl, struct hsc_rx_config *rxc)
+{
+	struct hsi_config tmp;
+	int ret;
+
+	if ((rxc->mode != HSI_MODE_STREAM) && (rxc->mode != HSI_MODE_FRAME))
+		return -EINVAL;
+	if ((rxc->channels == 0) || (rxc->channels > HSC_DEVS))
+		return -EINVAL;
+	if (rxc->channels & (rxc->channels - 1))
+		return -EINVAL;
+	if ((rxc->flow != HSI_FLOW_SYNC) && (rxc->flow != HSI_FLOW_PIPE))
+		return -EINVAL;
+	tmp = cl->rx_cfg;
+	cl->rx_cfg.mode = rxc->mode;
+	cl->rx_cfg.channels = rxc->channels;
+	cl->rx_cfg.flow = rxc->flow;
+	ret = hsi_setup(cl);
+	if (ret < 0) {
+		cl->rx_cfg = tmp;
+		return ret;
+	}
+	if (rxc->mode == HSI_MODE_FRAME)
+		hsc_break_request(cl);
+
+	return ret;
+}
+
+static inline void hsc_rx_get(struct hsi_client *cl, struct hsc_rx_config *rxc)
+{
+	rxc->mode = cl->rx_cfg.mode;
+	rxc->channels = cl->rx_cfg.channels;
+	rxc->flow = cl->rx_cfg.flow;
+}
+
+static int hsc_tx_set(struct hsi_client *cl, struct hsc_tx_config *txc)
+{
+	struct hsi_config tmp;
+	int ret;
+
+	if ((txc->mode != HSI_MODE_STREAM) && (txc->mode != HSI_MODE_FRAME))
+		return -EINVAL;
+	if ((txc->channels == 0) || (txc->channels > HSC_DEVS))
+		return -EINVAL;
+	if (txc->channels & (txc->channels - 1))
+		return -EINVAL;
+	if ((txc->arb_mode != HSI_ARB_RR) && (txc->arb_mode != HSI_ARB_PRIO))
+		return -EINVAL;
+	tmp = cl->tx_cfg;
+	cl->tx_cfg.mode = txc->mode;
+	cl->tx_cfg.channels = txc->channels;
+	cl->tx_cfg.speed = txc->speed;
+	cl->tx_cfg.arb_mode = txc->arb_mode;
+	ret = hsi_setup(cl);
+	if (ret < 0) {
+		cl->tx_cfg = tmp;
+		return ret;
+	}
+
+	return ret;
+}
+
+static inline void hsc_tx_get(struct hsi_client *cl, struct hsc_tx_config *txc)
+{
+	txc->mode = cl->tx_cfg.mode;
+	txc->channels = cl->tx_cfg.channels;
+	txc->speed = cl->tx_cfg.speed;
+	txc->arb_mode = cl->tx_cfg.arb_mode;
+}
+
+static ssize_t hsc_read(struct file *file, char __user *buf, size_t len,
+						loff_t *ppos __maybe_unused)
+{
+	struct hsc_channel *channel = file->private_data;
+	struct hsi_msg *msg;
+	ssize_t ret;
+
+	if (len == 0)
+		return 0;
+	if (!IS_ALIGNED(len, sizeof(u32)))
+		return -EINVAL;
+	if (len > max_data_size)
+		len = max_data_size;
+	if (channel->ch >= channel->cl->rx_cfg.channels)
+		return -ECHRNG;
+	if (test_and_set_bit(HSC_CH_READ, &channel->flags))
+		return -EBUSY;
+	msg = hsc_get_first_msg(channel, &channel->free_msgs_list);
+	if (!msg) {
+		ret = -ENOSPC;
+		goto out;
+	}
+	hsc_msg_len_set(msg, len);
+	msg->complete = hsc_rx_completed;
+	msg->destructor = hsc_rx_msg_destructor;
+	ret = hsi_async_read(channel->cl, msg);
+	if (ret < 0) {
+		hsc_add_tail(channel, msg, &channel->free_msgs_list);
+		goto out;
+	}
+
+	ret = wait_event_interruptible(channel->rx_wait,
+					!list_empty(&channel->rx_msgs_queue));
+	if (ret < 0) {
+		clear_bit(HSC_CH_READ, &channel->flags);
+		hsi_flush(channel->cl);
+		return -EINTR;
+	}
+
+	msg = hsc_get_first_msg(channel, &channel->rx_msgs_queue);
+	if (msg) {
+		if (msg->status != HSI_STATUS_ERROR) {
+			ret = copy_to_user((void __user *)buf,
+			sg_virt(msg->sgt.sgl), hsc_msg_len_get(msg));
+			if (ret)
+				ret = -EFAULT;
+			else
+				ret = hsc_msg_len_get(msg);
+		} else {
+			ret = -EIO;
+		}
+		hsc_add_tail(channel, msg, &channel->free_msgs_list);
+	}
+out:
+	clear_bit(HSC_CH_READ, &channel->flags);
+
+	return ret;
+}
+
+static ssize_t hsc_write(struct file *file, const char __user *buf, size_t len,
+						loff_t *ppos __maybe_unused)
+{
+	struct hsc_channel *channel = file->private_data;
+	struct hsi_msg *msg;
+	ssize_t ret;
+
+	if ((len == 0) || !IS_ALIGNED(len, sizeof(u32)))
+		return -EINVAL;
+	if (len > max_data_size)
+		len = max_data_size;
+	if (channel->ch >= channel->cl->tx_cfg.channels)
+		return -ECHRNG;
+	if (test_and_set_bit(HSC_CH_WRITE, &channel->flags))
+		return -EBUSY;
+	msg = hsc_get_first_msg(channel, &channel->free_msgs_list);
+	if (!msg) {
+		clear_bit(HSC_CH_WRITE, &channel->flags);
+		return -ENOSPC;
+	}
+	if (copy_from_user(sg_virt(msg->sgt.sgl), (void __user *)buf, len)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	hsc_msg_len_set(msg, len);
+	msg->complete = hsc_tx_completed;
+	msg->destructor = hsc_tx_msg_destructor;
+	ret = hsi_async_write(channel->cl, msg);
+	if (ret < 0)
+		goto out;
+
+	ret = wait_event_interruptible(channel->tx_wait,
+					!list_empty(&channel->tx_msgs_queue));
+	if (ret < 0) {
+		clear_bit(HSC_CH_WRITE, &channel->flags);
+		hsi_flush(channel->cl);
+		return -EINTR;
+	}
+
+	msg = hsc_get_first_msg(channel, &channel->tx_msgs_queue);
+	if (msg) {
+		if (msg->status == HSI_STATUS_ERROR)
+			ret = -EIO;
+		else
+			ret = hsc_msg_len_get(msg);
+
+		hsc_add_tail(channel, msg, &channel->free_msgs_list);
+	}
+out:
+	clear_bit(HSC_CH_WRITE, &channel->flags);
+
+	return ret;
+}
+
+static long hsc_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct hsc_channel *channel = file->private_data;
+	unsigned int state;
+	struct hsc_rx_config rxc;
+	struct hsc_tx_config txc;
+	long ret = 0;
+
+	switch (cmd) {
+	case HSC_RESET:
+		hsi_flush(channel->cl);
+		break;
+	case HSC_SET_PM:
+		if (copy_from_user(&state, (void __user *)arg, sizeof(state)))
+			return -EFAULT;
+		if (state == HSC_PM_DISABLE) {
+			if (test_and_set_bit(HSC_CH_WLINE, &channel->flags))
+				return -EINVAL;
+			ret = hsi_start_tx(channel->cl);
+		} else if (state == HSC_PM_ENABLE) {
+			if (!test_and_clear_bit(HSC_CH_WLINE, &channel->flags))
+				return -EINVAL;
+			ret = hsi_stop_tx(channel->cl);
+		} else {
+			ret = -EINVAL;
+		}
+		break;
+	case HSC_SEND_BREAK:
+		return hsc_break_send(channel->cl);
+	case HSC_SET_RX:
+		if (copy_from_user(&rxc, (void __user *)arg, sizeof(rxc)))
+			return -EFAULT;
+		return hsc_rx_set(channel->cl, &rxc);
+	case HSC_GET_RX:
+		hsc_rx_get(channel->cl, &rxc);
+		if (copy_to_user((void __user *)arg, &rxc, sizeof(rxc)))
+			return -EFAULT;
+		break;
+	case HSC_SET_TX:
+		if (copy_from_user(&txc, (void __user *)arg, sizeof(txc)))
+			return -EFAULT;
+		return hsc_tx_set(channel->cl, &txc);
+	case HSC_GET_TX:
+		hsc_tx_get(channel->cl, &txc);
+		if (copy_to_user((void __user *)arg, &txc, sizeof(txc)))
+			return -EFAULT;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return ret;
+}
+
+static inline void __hsc_port_release(struct hsc_client_data *cl_data)
+{
+	BUG_ON(cl_data->usecnt == 0);
+
+	if (--cl_data->usecnt == 0) {
+		hsi_flush(cl_data->cl);
+		hsi_release_port(cl_data->cl);
+	}
+}
+
+static int hsc_open(struct inode *inode, struct file *file)
+{
+	struct hsc_client_data *cl_data;
+	struct hsc_channel *channel;
+	int ret = 0;
+
+	pr_debug("open, minor = %d\n", iminor(inode));
+
+	cl_data = container_of(inode->i_cdev, struct hsc_client_data, cdev);
+	mutex_lock(&cl_data->lock);
+	channel = cl_data->channels + (iminor(inode) & HSC_CH_MASK);
+
+	if (test_and_set_bit(HSC_CH_OPEN, &channel->flags)) {
+		ret = -EBUSY;
+		goto out;
+	}
+	/*
+	 * Check if we have already claimed the port associated to the HSI
+	 * client. If not then try to claim it, else increase its refcount
+	 */
+	if (cl_data->usecnt == 0) {
+		ret = hsi_claim_port(cl_data->cl, 0);
+		if (ret < 0)
+			goto out;
+		hsi_setup(cl_data->cl);
+	}
+	cl_data->usecnt++;
+
+	ret = hsc_msgs_alloc(channel);
+	if (ret < 0) {
+		__hsc_port_release(cl_data);
+		goto out;
+	}
+
+	file->private_data = channel;
+	mutex_unlock(&cl_data->lock);
+
+	return ret;
+out:
+	mutex_unlock(&cl_data->lock);
+
+	return ret;
+}
+
+static int hsc_release(struct inode *inode __maybe_unused, struct file *file)
+{
+	struct hsc_channel *channel = file->private_data;
+	struct hsc_client_data *cl_data = channel->cl_data;
+
+	mutex_lock(&cl_data->lock);
+	file->private_data = NULL;
+	if (test_and_clear_bit(HSC_CH_WLINE, &channel->flags))
+		hsi_stop_tx(channel->cl);
+	__hsc_port_release(cl_data);
+	hsc_reset_list(channel, &channel->rx_msgs_queue);
+	hsc_reset_list(channel, &channel->tx_msgs_queue);
+	hsc_reset_list(channel, &channel->free_msgs_list);
+	clear_bit(HSC_CH_READ, &channel->flags);
+	clear_bit(HSC_CH_WRITE, &channel->flags);
+	clear_bit(HSC_CH_OPEN, &channel->flags);
+	wake_up(&channel->rx_wait);
+	wake_up(&channel->tx_wait);
+	mutex_unlock(&cl_data->lock);
+
+	return 0;
+}
+
+static const struct file_operations hsc_fops = {
+	.owner		= THIS_MODULE,
+	.read		= hsc_read,
+	.write		= hsc_write,
+	.unlocked_ioctl	= hsc_ioctl,
+	.open		= hsc_open,
+	.release	= hsc_release,
+};
+
+static void __devinit hsc_channel_init(struct hsc_channel *channel)
+{
+	init_waitqueue_head(&channel->rx_wait);
+	init_waitqueue_head(&channel->tx_wait);
+	spin_lock_init(&channel->lock);
+	INIT_LIST_HEAD(&channel->free_msgs_list);
+	INIT_LIST_HEAD(&channel->rx_msgs_queue);
+	INIT_LIST_HEAD(&channel->tx_msgs_queue);
+}
+
+static int __devinit hsc_probe(struct device *dev)
+{
+	const char devname[] = "hsi_char";
+	struct hsc_client_data *cl_data;
+	struct hsc_channel *channel;
+	struct hsi_client *cl = to_hsi_client(dev);
+	unsigned int hsc_baseminor;
+	dev_t hsc_dev;
+	int ret;
+	int i;
+
+	cl_data = kzalloc(sizeof(*cl_data), GFP_KERNEL);
+	if (!cl_data) {
+		dev_err(dev, "Could not allocate hsc_client_data\n");
+		return -ENOMEM;
+	}
+	hsc_baseminor = HSC_BASEMINOR(hsi_id(cl), hsi_port_id(cl));
+	if (!hsc_major) {
+		ret = alloc_chrdev_region(&hsc_dev, hsc_baseminor,
+						HSC_DEVS, devname);
+		if (ret > 0)
+			hsc_major = MAJOR(hsc_dev);
+	} else {
+		hsc_dev = MKDEV(hsc_major, hsc_baseminor);
+		ret = register_chrdev_region(hsc_dev, HSC_DEVS, devname);
+	}
+	if (ret < 0) {
+		dev_err(dev, "Device %s allocation failed %d\n",
+					hsc_major ? "minor" : "major", ret);
+		goto out1;
+	}
+	mutex_init(&cl_data->lock);
+	hsi_client_set_drvdata(cl, cl_data);
+	cdev_init(&cl_data->cdev, &hsc_fops);
+	cl_data->cdev.owner = THIS_MODULE;
+	cl_data->cl = cl;
+	for (i = 0, channel = cl_data->channels; i < HSC_DEVS; i++, channel++) {
+		hsc_channel_init(channel);
+		channel->ch = i;
+		channel->cl = cl;
+		channel->cl_data = cl_data;
+	}
+
+	/* 1 hsi client -> N char devices (one for each channel) */
+	ret = cdev_add(&cl_data->cdev, hsc_dev, HSC_DEVS);
+	if (ret) {
+		dev_err(dev, "Could not add char device %d\n", ret);
+		goto out2;
+	}
+
+	return 0;
+out2:
+	unregister_chrdev_region(hsc_dev, HSC_DEVS);
+out1:
+	kfree(cl_data);
+
+	return ret;
+}
+
+static int __devexit hsc_remove(struct device *dev)
+{
+	struct hsi_client *cl = to_hsi_client(dev);
+	struct hsc_client_data *cl_data = hsi_client_drvdata(cl);
+	dev_t hsc_dev = cl_data->cdev.dev;
+
+	cdev_del(&cl_data->cdev);
+	unregister_chrdev_region(hsc_dev, HSC_DEVS);
+	hsi_client_set_drvdata(cl, NULL);
+	kfree(cl_data);
+
+	return 0;
+}
+
+static struct hsi_client_driver hsc_driver = {
+	.driver = {
+		.name	= "hsi_char",
+		.owner	= THIS_MODULE,
+		.probe	= hsc_probe,
+		.remove	= __devexit_p(hsc_remove),
+	},
+};
+
+static int __init hsc_init(void)
+{
+	int ret;
+
+	if ((max_data_size < 4) || (max_data_size > 0x10000) ||
+		(max_data_size & (max_data_size - 1))) {
+		pr_err("Invalid max read/write data size");
+		return -EINVAL;
+	}
+
+	ret = hsi_register_client_driver(&hsc_driver);
+	if (ret) {
+		pr_err("Error while registering HSI/SSI driver %d", ret);
+		return ret;
+	}
+
+	pr_info("HSI/SSI char device loaded\n");
+
+	return 0;
+}
+module_init(hsc_init);
+
+static void __exit hsc_exit(void)
+{
+	hsi_unregister_client_driver(&hsc_driver);
+	pr_info("HSI char device removed\n");
+}
+module_exit(hsc_exit);
+
+MODULE_AUTHOR("Andras Domokos <andras.domokos@nokia.com>");
+MODULE_ALIAS("hsi:hsi_char");
+MODULE_DESCRIPTION("HSI character device");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hsi/hsi.c b/drivers/hsi/hsi.c
new file mode 100644
index 000000000000..4e2d79b79334
--- /dev/null
+++ b/drivers/hsi/hsi.c
@@ -0,0 +1,494 @@
+/*
+ * HSI core.
+ *
+ * Copyright (C) 2010 Nokia Corporation. All rights reserved.
+ *
+ * Contact: Carlos Chinea <carlos.chinea@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ */
+#include <linux/hsi/hsi.h>
+#include <linux/compiler.h>
+#include <linux/rwsem.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/kobject.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include "hsi_core.h"
+
+static struct device_type hsi_ctrl = {
+	.name	= "hsi_controller",
+};
+
+static struct device_type hsi_cl = {
+	.name	= "hsi_client",
+};
+
+static struct device_type hsi_port = {
+	.name	= "hsi_port",
+};
+
+static ssize_t modalias_show(struct device *dev,
+			struct device_attribute *a __maybe_unused, char *buf)
+{
+	return sprintf(buf, "hsi:%s\n", dev_name(dev));
+}
+
+static struct device_attribute hsi_bus_dev_attrs[] = {
+	__ATTR_RO(modalias),
+	__ATTR_NULL,
+};
+
+static int hsi_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	if (dev->type == &hsi_cl)
+		add_uevent_var(env, "MODALIAS=hsi:%s", dev_name(dev));
+
+	return 0;
+}
+
+static int hsi_bus_match(struct device *dev, struct device_driver *driver)
+{
+	return strcmp(dev_name(dev), driver->name) == 0;
+}
+
+static struct bus_type hsi_bus_type = {
+	.name		= "hsi",
+	.dev_attrs	= hsi_bus_dev_attrs,
+	.match		= hsi_bus_match,
+	.uevent		= hsi_bus_uevent,
+};
+
+static void hsi_client_release(struct device *dev)
+{
+	kfree(to_hsi_client(dev));
+}
+
+static void hsi_new_client(struct hsi_port *port, struct hsi_board_info *info)
+{
+	struct hsi_client *cl;
+	unsigned long flags;
+
+	cl = kzalloc(sizeof(*cl), GFP_KERNEL);
+	if (!cl)
+		return;
+	cl->device.type = &hsi_cl;
+	cl->tx_cfg = info->tx_cfg;
+	cl->rx_cfg = info->rx_cfg;
+	cl->device.bus = &hsi_bus_type;
+	cl->device.parent = &port->device;
+	cl->device.release = hsi_client_release;
+	dev_set_name(&cl->device, info->name);
+	cl->device.platform_data = info->platform_data;
+	spin_lock_irqsave(&port->clock, flags);
+	list_add_tail(&cl->link, &port->clients);
+	spin_unlock_irqrestore(&port->clock, flags);
+	if (info->archdata)
+		cl->device.archdata = *info->archdata;
+	if (device_register(&cl->device) < 0) {
+		pr_err("hsi: failed to register client: %s\n", info->name);
+		kfree(cl);
+	}
+}
+
+static void hsi_scan_board_info(struct hsi_controller *hsi)
+{
+	struct hsi_cl_info *cl_info;
+	struct hsi_port	*p;
+
+	list_for_each_entry(cl_info, &hsi_board_list, list)
+		if (cl_info->info.hsi_id == hsi->id) {
+			p = hsi_find_port_num(hsi, cl_info->info.port);
+			if (!p)
+				continue;
+			hsi_new_client(p, &cl_info->info);
+		}
+}
+
+static int hsi_remove_client(struct device *dev, void *data __maybe_unused)
+{
+	struct hsi_client *cl = to_hsi_client(dev);
+	struct hsi_port *port = to_hsi_port(dev->parent);
+	unsigned long flags;
+
+	spin_lock_irqsave(&port->clock, flags);
+	list_del(&cl->link);
+	spin_unlock_irqrestore(&port->clock, flags);
+	device_unregister(dev);
+
+	return 0;
+}
+
+static int hsi_remove_port(struct device *dev, void *data __maybe_unused)
+{
+	device_for_each_child(dev, NULL, hsi_remove_client);
+	device_unregister(dev);
+
+	return 0;
+}
+
+static void hsi_controller_release(struct device *dev __maybe_unused)
+{
+}
+
+static void hsi_port_release(struct device *dev __maybe_unused)
+{
+}
+
+/**
+ * hsi_unregister_controller - Unregister an HSI controller
+ * @hsi: The HSI controller to register
+ */
+void hsi_unregister_controller(struct hsi_controller *hsi)
+{
+	device_for_each_child(&hsi->device, NULL, hsi_remove_port);
+	device_unregister(&hsi->device);
+}
+EXPORT_SYMBOL_GPL(hsi_unregister_controller);
+
+/**
+ * hsi_register_controller - Register an HSI controller and its ports
+ * @hsi: The HSI controller to register
+ *
+ * Returns -errno on failure, 0 on success.
+ */
+int hsi_register_controller(struct hsi_controller *hsi)
+{
+	unsigned int i;
+	int err;
+
+	hsi->device.type = &hsi_ctrl;
+	hsi->device.bus = &hsi_bus_type;
+	hsi->device.release = hsi_controller_release;
+	err = device_register(&hsi->device);
+	if (err < 0)
+		return err;
+	for (i = 0; i < hsi->num_ports; i++) {
+		hsi->port[i].device.parent = &hsi->device;
+		hsi->port[i].device.bus = &hsi_bus_type;
+		hsi->port[i].device.release = hsi_port_release;
+		hsi->port[i].device.type = &hsi_port;
+		INIT_LIST_HEAD(&hsi->port[i].clients);
+		spin_lock_init(&hsi->port[i].clock);
+		err = device_register(&hsi->port[i].device);
+		if (err < 0)
+			goto out;
+	}
+	/* Populate HSI bus with HSI clients */
+	hsi_scan_board_info(hsi);
+
+	return 0;
+out:
+	hsi_unregister_controller(hsi);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(hsi_register_controller);
+
+/**
+ * hsi_register_client_driver - Register an HSI client to the HSI bus
+ * @drv: HSI client driver to register
+ *
+ * Returns -errno on failure, 0 on success.
+ */
+int hsi_register_client_driver(struct hsi_client_driver *drv)
+{
+	drv->driver.bus = &hsi_bus_type;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(hsi_register_client_driver);
+
+static inline int hsi_dummy_msg(struct hsi_msg *msg __maybe_unused)
+{
+	return 0;
+}
+
+static inline int hsi_dummy_cl(struct hsi_client *cl __maybe_unused)
+{
+	return 0;
+}
+
+/**
+ * hsi_alloc_controller - Allocate an HSI controller and its ports
+ * @n_ports: Number of ports on the HSI controller
+ * @flags: Kernel allocation flags
+ *
+ * Return NULL on failure or a pointer to an hsi_controller on success.
+ */
+struct hsi_controller *hsi_alloc_controller(unsigned int n_ports, gfp_t flags)
+{
+	struct hsi_controller	*hsi;
+	struct hsi_port		*port;
+	unsigned int		i;
+
+	if (!n_ports)
+		return NULL;
+
+	port = kzalloc(sizeof(*port)*n_ports, flags);
+	if (!port)
+		return NULL;
+	hsi = kzalloc(sizeof(*hsi), flags);
+	if (!hsi)
+		goto out;
+	for (i = 0; i < n_ports; i++) {
+		dev_set_name(&port[i].device, "port%d", i);
+		port[i].num = i;
+		port[i].async = hsi_dummy_msg;
+		port[i].setup = hsi_dummy_cl;
+		port[i].flush = hsi_dummy_cl;
+		port[i].start_tx = hsi_dummy_cl;
+		port[i].stop_tx = hsi_dummy_cl;
+		port[i].release = hsi_dummy_cl;
+		mutex_init(&port[i].lock);
+	}
+	hsi->num_ports = n_ports;
+	hsi->port = port;
+
+	return hsi;
+out:
+	kfree(port);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(hsi_alloc_controller);
+
+/**
+ * hsi_free_controller - Free an HSI controller
+ * @hsi: Pointer to HSI controller
+ */
+void hsi_free_controller(struct hsi_controller *hsi)
+{
+	if (!hsi)
+		return;
+
+	kfree(hsi->port);
+	kfree(hsi);
+}
+EXPORT_SYMBOL_GPL(hsi_free_controller);
+
+/**
+ * hsi_free_msg - Free an HSI message
+ * @msg: Pointer to the HSI message
+ *
+ * Client is responsible to free the buffers pointed by the scatterlists.
+ */
+void hsi_free_msg(struct hsi_msg *msg)
+{
+	if (!msg)
+		return;
+	sg_free_table(&msg->sgt);
+	kfree(msg);
+}
+EXPORT_SYMBOL_GPL(hsi_free_msg);
+
+/**
+ * hsi_alloc_msg - Allocate an HSI message
+ * @nents: Number of memory entries
+ * @flags: Kernel allocation flags
+ *
+ * nents can be 0. This mainly makes sense for read transfer.
+ * In that case, HSI drivers will call the complete callback when
+ * there is data to be read without consuming it.
+ *
+ * Return NULL on failure or a pointer to an hsi_msg on success.
+ */
+struct hsi_msg *hsi_alloc_msg(unsigned int nents, gfp_t flags)
+{
+	struct hsi_msg *msg;
+	int err;
+
+	msg = kzalloc(sizeof(*msg), flags);
+	if (!msg)
+		return NULL;
+
+	if (!nents)
+		return msg;
+
+	err = sg_alloc_table(&msg->sgt, nents, flags);
+	if (unlikely(err)) {
+		kfree(msg);
+		msg = NULL;
+	}
+
+	return msg;
+}
+EXPORT_SYMBOL_GPL(hsi_alloc_msg);
+
+/**
+ * hsi_async - Submit an HSI transfer to the controller
+ * @cl: HSI client sending the transfer
+ * @msg: The HSI transfer passed to controller
+ *
+ * The HSI message must have the channel, ttype, complete and destructor
+ * fields set beforehand. If nents > 0 then the client has to initialize
+ * also the scatterlists to point to the buffers to write to or read from.
+ *
+ * HSI controllers relay on pre-allocated buffers from their clients and they
+ * do not allocate buffers on their own.
+ *
+ * Once the HSI message transfer finishes, the HSI controller calls the
+ * complete callback with the status and actual_len fields of the HSI message
+ * updated. The complete callback can be called before returning from
+ * hsi_async.
+ *
+ * Returns -errno on failure or 0 on success
+ */
+int hsi_async(struct hsi_client *cl, struct hsi_msg *msg)
+{
+	struct hsi_port *port = hsi_get_port(cl);
+
+	if (!hsi_port_claimed(cl))
+		return -EACCES;
+
+	WARN_ON_ONCE(!msg->destructor || !msg->complete);
+	msg->cl = cl;
+
+	return port->async(msg);
+}
+EXPORT_SYMBOL_GPL(hsi_async);
+
+/**
+ * hsi_claim_port - Claim the HSI client's port
+ * @cl: HSI client that wants to claim its port
+ * @share: Flag to indicate if the client wants to share the port or not.
+ *
+ * Returns -errno on failure, 0 on success.
+ */
+int hsi_claim_port(struct hsi_client *cl, unsigned int share)
+{
+	struct hsi_port *port = hsi_get_port(cl);
+	int err = 0;
+
+	mutex_lock(&port->lock);
+	if ((port->claimed) && (!port->shared || !share)) {
+		err = -EBUSY;
+		goto out;
+	}
+	if (!try_module_get(to_hsi_controller(port->device.parent)->owner)) {
+		err = -ENODEV;
+		goto out;
+	}
+	port->claimed++;
+	port->shared = !!share;
+	cl->pclaimed = 1;
+out:
+	mutex_unlock(&port->lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(hsi_claim_port);
+
+/**
+ * hsi_release_port - Release the HSI client's port
+ * @cl: HSI client which previously claimed its port
+ */
+void hsi_release_port(struct hsi_client *cl)
+{
+	struct hsi_port *port = hsi_get_port(cl);
+
+	mutex_lock(&port->lock);
+	/* Allow HW driver to do some cleanup */
+	port->release(cl);
+	if (cl->pclaimed)
+		port->claimed--;
+	BUG_ON(port->claimed < 0);
+	cl->pclaimed = 0;
+	if (!port->claimed)
+		port->shared = 0;
+	module_put(to_hsi_controller(port->device.parent)->owner);
+	mutex_unlock(&port->lock);
+}
+EXPORT_SYMBOL_GPL(hsi_release_port);
+
+static int hsi_start_rx(struct hsi_client *cl, void *data __maybe_unused)
+{
+	if (cl->hsi_start_rx)
+		(*cl->hsi_start_rx)(cl);
+
+	return 0;
+}
+
+static int hsi_stop_rx(struct hsi_client *cl, void *data __maybe_unused)
+{
+	if (cl->hsi_stop_rx)
+		(*cl->hsi_stop_rx)(cl);
+
+	return 0;
+}
+
+static int hsi_port_for_each_client(struct hsi_port *port, void *data,
+				int (*fn)(struct hsi_client *cl, void *data))
+{
+	struct hsi_client *cl;
+
+	spin_lock(&port->clock);
+	list_for_each_entry(cl, &port->clients, link) {
+		spin_unlock(&port->clock);
+		(*fn)(cl, data);
+		spin_lock(&port->clock);
+	}
+	spin_unlock(&port->clock);
+
+	return 0;
+}
+
+/**
+ * hsi_event -Notifies clients about port events
+ * @port: Port where the event occurred
+ * @event: The event type
+ *
+ * Clients should not be concerned about wake line behavior. However, due
+ * to a race condition in HSI HW protocol, clients need to be notified
+ * about wake line changes, so they can implement a workaround for it.
+ *
+ * Events:
+ * HSI_EVENT_START_RX - Incoming wake line high
+ * HSI_EVENT_STOP_RX - Incoming wake line down
+ */
+void hsi_event(struct hsi_port *port, unsigned int event)
+{
+	int (*fn)(struct hsi_client *cl, void *data);
+
+	switch (event) {
+	case HSI_EVENT_START_RX:
+		fn = hsi_start_rx;
+		break;
+	case HSI_EVENT_STOP_RX:
+		fn = hsi_stop_rx;
+		break;
+	default:
+		return;
+	}
+	hsi_port_for_each_client(port, NULL, fn);
+}
+EXPORT_SYMBOL_GPL(hsi_event);
+
+static int __init hsi_init(void)
+{
+	return bus_register(&hsi_bus_type);
+}
+postcore_initcall(hsi_init);
+
+static void __exit hsi_exit(void)
+{
+	bus_unregister(&hsi_bus_type);
+}
+module_exit(hsi_exit);
+
+MODULE_AUTHOR("Carlos Chinea <carlos.chinea@nokia.com>");
+MODULE_DESCRIPTION("High-speed Synchronous Serial Interface (HSI) framework");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hsi/hsi_boardinfo.c b/drivers/hsi/hsi_boardinfo.c
new file mode 100644
index 000000000000..e56bc6da5f98
--- /dev/null
+++ b/drivers/hsi/hsi_boardinfo.c
@@ -0,0 +1,62 @@
+/*
+ * HSI clients registration interface
+ *
+ * Copyright (C) 2010 Nokia Corporation. All rights reserved.
+ *
+ * Contact: Carlos Chinea <carlos.chinea@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ */
+#include <linux/hsi/hsi.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include "hsi_core.h"
+
+/*
+ * hsi_board_list is only used internally by the HSI framework.
+ * No one else is allowed to make use of it.
+ */
+LIST_HEAD(hsi_board_list);
+EXPORT_SYMBOL_GPL(hsi_board_list);
+
+/**
+ * hsi_register_board_info - Register HSI clients information
+ * @info: Array of HSI clients on the board
+ * @len: Length of the array
+ *
+ * HSI clients are statically declared and registered on board files.
+ *
+ * HSI clients will be automatically registered to the HSI bus once the
+ * controller and the port where the clients wishes to attach are registered
+ * to it.
+ *
+ * Return -errno on failure, 0 on success.
+ */
+int __init hsi_register_board_info(struct hsi_board_info const *info,
+							unsigned int len)
+{
+	struct hsi_cl_info *cl_info;
+
+	cl_info = kzalloc(sizeof(*cl_info) * len, GFP_KERNEL);
+	if (!cl_info)
+		return -ENOMEM;
+
+	for (; len; len--, info++, cl_info++) {
+		cl_info->info = *info;
+		list_add_tail(&cl_info->list, &hsi_board_list);
+	}
+
+	return 0;
+}
diff --git a/drivers/hsi/hsi_core.h b/drivers/hsi/hsi_core.h
new file mode 100644
index 000000000000..ab5c2fb175fd
--- /dev/null
+++ b/drivers/hsi/hsi_core.h
@@ -0,0 +1,35 @@
+/*
+ * HSI framework internal interfaces,
+ *
+ * Copyright (C) 2010 Nokia Corporation. All rights reserved.
+ *
+ * Contact: Carlos Chinea <carlos.chinea@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ */
+
+#ifndef __LINUX_HSI_CORE_H__
+#define __LINUX_HSI_CORE_H__
+
+#include <linux/hsi/hsi.h>
+
+struct hsi_cl_info {
+	struct list_head	list;
+	struct hsi_board_info	info;
+};
+
+extern struct list_head hsi_board_list;
+
+#endif /* __LINUX_HSI_CORE_H__ */
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 5b32d56dbb4d..8deedc1b9840 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -253,7 +253,8 @@ config SENSORS_K10TEMP
 	  If you say yes here you get support for the temperature
 	  sensor(s) inside your CPU. Supported are later revisions of
 	  the AMD Family 10h and all revisions of the AMD Family 11h,
-	  12h (Llano), 14h (Brazos) and 15h (Bulldozer) microarchitectures.
+	  12h (Llano), 14h (Brazos) and 15h (Bulldozer/Trinity)
+	  microarchitectures.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called k10temp.
@@ -425,7 +426,7 @@ config SENSORS_GL520SM
 
 config SENSORS_GPIO_FAN
 	tristate "GPIO fan"
-	depends on GENERIC_GPIO
+	depends on GPIOLIB
 	help
 	  If you say yes here you get support for fans connected to GPIO lines.
 
@@ -883,7 +884,7 @@ source drivers/hwmon/pmbus/Kconfig
 
 config SENSORS_SHT15
 	tristate "Sensiron humidity and temperature sensors. SHT15 and compat."
-	depends on GENERIC_GPIO
+	depends on GPIOLIB
 	help
 	  If you say yes here you get support for the Sensiron SHT10, SHT11,
 	  SHT15, SHT71, SHT75 humidity and temperature sensors.
diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c
index 554f046bcf20..145f13580ff0 100644
--- a/drivers/hwmon/acpi_power_meter.c
+++ b/drivers/hwmon/acpi_power_meter.c
@@ -632,6 +632,7 @@ static int register_ro_attrs(struct acpi_power_meter_resource *resource,
 		sensors->dev_attr.show = ro->show;
 		sensors->index = ro->index;
 
+		sysfs_attr_init(&sensors->dev_attr.attr);
 		res = device_create_file(dev, &sensors->dev_attr);
 		if (res) {
 			sensors->dev_attr.attr.name = NULL;
@@ -661,6 +662,7 @@ static int register_rw_attrs(struct acpi_power_meter_resource *resource,
 		sensors->dev_attr.store = rw->set;
 		sensors->index = rw->index;
 
+		sysfs_attr_init(&sensors->dev_attr.attr);
 		res = device_create_file(dev, &sensors->dev_attr);
 		if (res) {
 			sensors->dev_attr.attr.name = NULL;
diff --git a/drivers/hwmon/ad7314.c b/drivers/hwmon/ad7314.c
index 0e0cfcc36f8d..ce43642ef03e 100644
--- a/drivers/hwmon/ad7314.c
+++ b/drivers/hwmon/ad7314.c
@@ -128,6 +128,7 @@ static int __devinit ad7314_probe(struct spi_device *spi_dev)
 		ret = PTR_ERR(chip->hwmon_dev);
 		goto error_remove_group;
 	}
+	chip->spi_dev = spi_dev;
 
 	return 0;
 error_remove_group:
diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c
index ff37363ea5bc..44e1fd7f3d81 100644
--- a/drivers/hwmon/adm1031.c
+++ b/drivers/hwmon/adm1031.c
@@ -233,18 +233,15 @@ static const auto_chan_table_t auto_channel_select_table_adm1030 = {
  * nearest match if no exact match where found.
  */
 static int
-get_fan_auto_nearest(struct adm1031_data *data,
-		     int chan, u8 val, u8 reg, u8 *new_reg)
+get_fan_auto_nearest(struct adm1031_data *data, int chan, u8 val, u8 reg)
 {
 	int i;
 	int first_match = -1, exact_match = -1;
 	u8 other_reg_val =
 	    (*data->chan_select_table)[FAN_CHAN_FROM_REG(reg)][chan ? 0 : 1];
 
-	if (val == 0) {
-		*new_reg = 0;
+	if (val == 0)
 		return 0;
-	}
 
 	for (i = 0; i < 8; i++) {
 		if ((val == (*data->chan_select_table)[i][chan]) &&
@@ -264,13 +261,11 @@ get_fan_auto_nearest(struct adm1031_data *data,
 	}
 
 	if (exact_match >= 0)
-		*new_reg = exact_match;
+		return exact_match;
 	else if (first_match >= 0)
-		*new_reg = first_match;
-	else
-		return -EINVAL;
+		return first_match;
 
-	return 0;
+	return -EINVAL;
 }
 
 static ssize_t show_fan_auto_channel(struct device *dev,
@@ -301,11 +296,12 @@ set_fan_auto_channel(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&data->update_lock);
 
-	ret = get_fan_auto_nearest(data, nr, val, data->conf1, &reg);
-	if (ret) {
+	ret = get_fan_auto_nearest(data, nr, val, data->conf1);
+	if (ret < 0) {
 		mutex_unlock(&data->update_lock);
 		return ret;
 	}
+	reg = ret;
 	data->conf1 = FAN_CHAN_TO_REG(reg, data->conf1);
 	if ((data->conf1 & ADM1031_CONF1_AUTO_MODE) ^
 	    (old_fan_mode & ADM1031_CONF1_AUTO_MODE)) {
diff --git a/drivers/hwmon/f75375s.c b/drivers/hwmon/f75375s.c
index 729499e75210..ece4159bd453 100644
--- a/drivers/hwmon/f75375s.c
+++ b/drivers/hwmon/f75375s.c
@@ -276,6 +276,7 @@ static bool duty_mode_enabled(u8 pwm_enable)
 		return false;
 	default:
 		BUG();
+		return true;
 	}
 }
 
@@ -291,6 +292,7 @@ static bool auto_mode_enabled(u8 pwm_enable)
 		return true;
 	default:
 		BUG();
+		return false;
 	}
 }
 
diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c
index 8305d29459bd..519ce8b9c142 100644
--- a/drivers/hwmon/fschmd.c
+++ b/drivers/hwmon/fschmd.c
@@ -53,8 +53,8 @@
 static const unsigned short normal_i2c[] = { 0x73, I2C_CLIENT_END };
 
 /* Insmod parameters */
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 	__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index aba29d63f195..307bb325dde9 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -33,6 +33,9 @@ static bool force;
 module_param(force, bool, 0444);
 MODULE_PARM_DESC(force, "force loading on processors with erratum 319");
 
+/* PCI-IDs for Northbridge devices not used anywhere else */
+#define PCI_DEVICE_ID_AMD_15H_M10H_NB_F3	0x1403
+
 /* CPUID function 0x80000001, ebx */
 #define CPUID_PKGTYPE_MASK	0xf0000000
 #define CPUID_PKGTYPE_F		0x00000000
@@ -210,6 +213,7 @@ static DEFINE_PCI_DEVICE_TABLE(k10temp_id_table) = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_NB_F3) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, k10temp_id_table);
diff --git a/drivers/hwmon/max6639.c b/drivers/hwmon/max6639.c
index 193067e27b6f..de8f7adaccbd 100644
--- a/drivers/hwmon/max6639.c
+++ b/drivers/hwmon/max6639.c
@@ -596,8 +596,10 @@ static int max6639_remove(struct i2c_client *client)
 	return 0;
 }
 
-static int max6639_suspend(struct i2c_client *client, pm_message_t mesg)
+#ifdef CONFIG_PM_SLEEP
+static int max6639_suspend(struct device *dev)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	int data = i2c_smbus_read_byte_data(client, MAX6639_REG_GCONFIG);
 	if (data < 0)
 		return data;
@@ -606,8 +608,9 @@ static int max6639_suspend(struct i2c_client *client, pm_message_t mesg)
 			MAX6639_REG_GCONFIG, data | MAX6639_GCONFIG_STANDBY);
 }
 
-static int max6639_resume(struct i2c_client *client)
+static int max6639_resume(struct device *dev)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	int data = i2c_smbus_read_byte_data(client, MAX6639_REG_GCONFIG);
 	if (data < 0)
 		return data;
@@ -615,6 +618,7 @@ static int max6639_resume(struct i2c_client *client)
 	return i2c_smbus_write_byte_data(client,
 			MAX6639_REG_GCONFIG, data & ~MAX6639_GCONFIG_STANDBY);
 }
+#endif /* CONFIG_PM_SLEEP */
 
 static const struct i2c_device_id max6639_id[] = {
 	{"max6639", 0},
@@ -623,15 +627,18 @@ static const struct i2c_device_id max6639_id[] = {
 
 MODULE_DEVICE_TABLE(i2c, max6639_id);
 
+static const struct dev_pm_ops max6639_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(max6639_suspend, max6639_resume)
+};
+
 static struct i2c_driver max6639_driver = {
 	.class = I2C_CLASS_HWMON,
 	.driver = {
 		   .name = "max6639",
+		   .pm = &max6639_pm_ops,
 		   },
 	.probe = max6639_probe,
 	.remove = max6639_remove,
-	.suspend = max6639_suspend,
-	.resume = max6639_resume,
 	.id_table = max6639_id,
 	.detect = max6639_detect,
 	.address_list = normal_i2c,
diff --git a/drivers/hwmon/mc13783-adc.c b/drivers/hwmon/mc13783-adc.c
index 6c6b240a782e..ce86c5e3c2c2 100644
--- a/drivers/hwmon/mc13783-adc.c
+++ b/drivers/hwmon/mc13783-adc.c
@@ -59,7 +59,7 @@ static int mc13783_adc_read(struct device *dev,
 
 	ret = mc13xxx_adc_do_conversion(priv->mc13xxx,
 			MC13XXX_ADC_MODE_MULT_CHAN,
-			channel, sample);
+			channel, 0, 0, sample);
 	if (ret)
 		return ret;
 
diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c
index a25350cf9554..54922ed12978 100644
--- a/drivers/hwmon/w83627ehf.c
+++ b/drivers/hwmon/w83627ehf.c
@@ -2619,15 +2619,15 @@ static struct platform_driver w83627ehf_driver = {
 static int __init w83627ehf_find(int sioaddr, unsigned short *addr,
 				 struct w83627ehf_sio_data *sio_data)
 {
-	static const char __initdata sio_name_W83627EHF[] = "W83627EHF";
-	static const char __initdata sio_name_W83627EHG[] = "W83627EHG";
-	static const char __initdata sio_name_W83627DHG[] = "W83627DHG";
-	static const char __initdata sio_name_W83627DHG_P[] = "W83627DHG-P";
-	static const char __initdata sio_name_W83627UHG[] = "W83627UHG";
-	static const char __initdata sio_name_W83667HG[] = "W83667HG";
-	static const char __initdata sio_name_W83667HG_B[] = "W83667HG-B";
-	static const char __initdata sio_name_NCT6775[] = "NCT6775F";
-	static const char __initdata sio_name_NCT6776[] = "NCT6776F";
+	static const char sio_name_W83627EHF[] __initconst = "W83627EHF";
+	static const char sio_name_W83627EHG[] __initconst = "W83627EHG";
+	static const char sio_name_W83627DHG[] __initconst = "W83627DHG";
+	static const char sio_name_W83627DHG_P[] __initconst = "W83627DHG-P";
+	static const char sio_name_W83627UHG[] __initconst = "W83627UHG";
+	static const char sio_name_W83667HG[] __initconst = "W83667HG";
+	static const char sio_name_W83667HG_B[] __initconst = "W83667HG-B";
+	static const char sio_name_NCT6775[] __initconst = "NCT6775F";
+	static const char sio_name_NCT6776[] __initconst = "NCT6776F";
 
 	u16 val;
 	const char *sio_name;
diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c
index 834e49d1827b..d6b0bdd48651 100644
--- a/drivers/hwmon/w83793.c
+++ b/drivers/hwmon/w83793.c
@@ -71,8 +71,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in minutes. 2<= timeout <=255 (default="
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c
index acba1c686c65..7f0b83219744 100644
--- a/drivers/i2c/algos/i2c-algo-bit.c
+++ b/drivers/i2c/algos/i2c-algo-bit.c
@@ -15,7 +15,8 @@
 
     You should have received a copy of the GNU General Public License
     along with this program; if not, write to the Free Software
-    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
  * ------------------------------------------------------------------------- */
 
 /* With some changes from Frodo Looijaard <frodol@dds.nl>, Kyösti Mälkki
@@ -111,7 +112,7 @@ static int sclhi(struct i2c_algo_bit_data *adap)
 				break;
 			return -ETIMEDOUT;
 		}
-		cond_resched();
+		cpu_relax();
 	}
 #ifdef DEBUG
 	if (jiffies != start && i2c_debug >= 3)
diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index beb9ffe2564b..73133b1063f0 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -15,7 +15,8 @@
  *
  *  You should have received a copy of the GNU General Public License
  *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ *  MA 02110-1301 USA.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/i2c/algos/i2c-algo-pcf.c b/drivers/i2c/algos/i2c-algo-pcf.c
index 5eebf562ff31..5c2379522aa9 100644
--- a/drivers/i2c/algos/i2c-algo-pcf.c
+++ b/drivers/i2c/algos/i2c-algo-pcf.c
@@ -16,7 +16,8 @@
  *
  *  You should have received a copy of the GNU General Public License
  *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ *  MA 02110-1301 USA.
  *
  * With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi> and
  * Frodo Looijaard <frodol@dds.nl>, and also from Martin Bailey
diff --git a/drivers/i2c/algos/i2c-algo-pcf.h b/drivers/i2c/algos/i2c-algo-pcf.h
index 5263a9eeb8d7..1ec703ee788d 100644
--- a/drivers/i2c/algos/i2c-algo-pcf.h
+++ b/drivers/i2c/algos/i2c-algo-pcf.h
@@ -16,7 +16,8 @@
 
     You should have received a copy of the GNU General Public License
     along with this program; if not, write to the Free Software
-    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.		*/
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.							*/
 /* --------------------------------------------------------------------	*/
 
 /* With some changes from Frodo Looijaard <frodol@dds.nl> */
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 71c1b0a7535c..d2c5095deeac 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -103,6 +103,7 @@ config I2C_I801
 	    Patsburg (PCH)
 	    DH89xxCC (PCH)
 	    Panther Point (PCH)
+	    Lynx Point (PCH)
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-i801.
diff --git a/drivers/i2c/busses/i2c-acorn.c b/drivers/i2c/busses/i2c-acorn.c
index 86796488ef4f..ed9f48d566db 100644
--- a/drivers/i2c/busses/i2c-acorn.c
+++ b/drivers/i2c/busses/i2c-acorn.c
@@ -19,7 +19,6 @@
 
 #include <mach/hardware.h>
 #include <asm/hardware/ioc.h>
-#include <asm/system.h>
 
 #define FORCE_ONES	0xdc
 #define SCL		0x02
diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c
index a651779d9ff7..c0330a41db03 100644
--- a/drivers/i2c/busses/i2c-gpio.c
+++ b/drivers/i2c/busses/i2c-gpio.c
@@ -14,8 +14,15 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
-
-#include <asm/gpio.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/of_i2c.h>
+
+struct i2c_gpio_private_data {
+	struct i2c_adapter adap;
+	struct i2c_algo_bit_data bit_data;
+	struct i2c_gpio_platform_data pdata;
+};
 
 /* Toggle SDA by changing the direction of the pin */
 static void i2c_gpio_setsda_dir(void *data, int state)
@@ -78,24 +85,62 @@ static int i2c_gpio_getscl(void *data)
 	return gpio_get_value(pdata->scl_pin);
 }
 
+static int __devinit of_i2c_gpio_probe(struct device_node *np,
+			     struct i2c_gpio_platform_data *pdata)
+{
+	u32 reg;
+
+	if (of_gpio_count(np) < 2)
+		return -ENODEV;
+
+	pdata->sda_pin = of_get_gpio(np, 0);
+	pdata->scl_pin = of_get_gpio(np, 1);
+
+	if (!gpio_is_valid(pdata->sda_pin) || !gpio_is_valid(pdata->scl_pin)) {
+		pr_err("%s: invalid GPIO pins, sda=%d/scl=%d\n",
+		       np->full_name, pdata->sda_pin, pdata->scl_pin);
+		return -ENODEV;
+	}
+
+	of_property_read_u32(np, "i2c-gpio,delay-us", &pdata->udelay);
+
+	if (!of_property_read_u32(np, "i2c-gpio,timeout-ms", &reg))
+		pdata->timeout = msecs_to_jiffies(reg);
+
+	pdata->sda_is_open_drain =
+		of_property_read_bool(np, "i2c-gpio,sda-open-drain");
+	pdata->scl_is_open_drain =
+		of_property_read_bool(np, "i2c-gpio,scl-open-drain");
+	pdata->scl_is_output_only =
+		of_property_read_bool(np, "i2c-gpio,scl-output-only");
+
+	return 0;
+}
+
 static int __devinit i2c_gpio_probe(struct platform_device *pdev)
 {
+	struct i2c_gpio_private_data *priv;
 	struct i2c_gpio_platform_data *pdata;
 	struct i2c_algo_bit_data *bit_data;
 	struct i2c_adapter *adap;
 	int ret;
 
-	pdata = pdev->dev.platform_data;
-	if (!pdata)
-		return -ENXIO;
-
-	ret = -ENOMEM;
-	adap = kzalloc(sizeof(struct i2c_adapter), GFP_KERNEL);
-	if (!adap)
-		goto err_alloc_adap;
-	bit_data = kzalloc(sizeof(struct i2c_algo_bit_data), GFP_KERNEL);
-	if (!bit_data)
-		goto err_alloc_bit_data;
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	adap = &priv->adap;
+	bit_data = &priv->bit_data;
+	pdata = &priv->pdata;
+
+	if (pdev->dev.of_node) {
+		ret = of_i2c_gpio_probe(pdev->dev.of_node, pdata);
+		if (ret)
+			return ret;
+	} else {
+		if (!pdev->dev.platform_data)
+			return -ENXIO;
+		memcpy(pdata, pdev->dev.platform_data, sizeof(*pdata));
+	}
 
 	ret = gpio_request(pdata->sda_pin, "sda");
 	if (ret)
@@ -143,6 +188,7 @@ static int __devinit i2c_gpio_probe(struct platform_device *pdev)
 	adap->algo_data = bit_data;
 	adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
 	adap->dev.parent = &pdev->dev;
+	adap->dev.of_node = pdev->dev.of_node;
 
 	/*
 	 * If "dev->id" is negative we consider it as zero.
@@ -154,7 +200,9 @@ static int __devinit i2c_gpio_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_add_bus;
 
-	platform_set_drvdata(pdev, adap);
+	of_i2c_register_devices(adap);
+
+	platform_set_drvdata(pdev, priv);
 
 	dev_info(&pdev->dev, "using pins %u (SDA) and %u (SCL%s)\n",
 		 pdata->sda_pin, pdata->scl_pin,
@@ -168,34 +216,40 @@ err_add_bus:
 err_request_scl:
 	gpio_free(pdata->sda_pin);
 err_request_sda:
-	kfree(bit_data);
-err_alloc_bit_data:
-	kfree(adap);
-err_alloc_adap:
 	return ret;
 }
 
 static int __devexit i2c_gpio_remove(struct platform_device *pdev)
 {
+	struct i2c_gpio_private_data *priv;
 	struct i2c_gpio_platform_data *pdata;
 	struct i2c_adapter *adap;
 
-	adap = platform_get_drvdata(pdev);
-	pdata = pdev->dev.platform_data;
+	priv = platform_get_drvdata(pdev);
+	adap = &priv->adap;
+	pdata = &priv->pdata;
 
 	i2c_del_adapter(adap);
 	gpio_free(pdata->scl_pin);
 	gpio_free(pdata->sda_pin);
-	kfree(adap->algo_data);
-	kfree(adap);
 
 	return 0;
 }
 
+#if defined(CONFIG_OF)
+static const struct of_device_id i2c_gpio_dt_ids[] = {
+	{ .compatible = "i2c-gpio", },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(of, i2c_gpio_dt_ids);
+#endif
+
 static struct platform_driver i2c_gpio_driver = {
 	.driver		= {
 		.name	= "i2c-gpio",
 		.owner	= THIS_MODULE,
+		.of_match_table	= of_match_ptr(i2c_gpio_dt_ids),
 	},
 	.probe		= i2c_gpio_probe,
 	.remove		= __devexit_p(i2c_gpio_remove),
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 5d2e2816831f..ae2945a5e007 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -2,7 +2,7 @@
     Copyright (c) 1998 - 2002  Frodo Looijaard <frodol@dds.nl>,
     Philip Edelbrock <phil@netroedge.com>, and Mark D. Studebaker
     <mdsxyz123@yahoo.com>
-    Copyright (C) 2007, 2008   Jean Delvare <khali@linux-fr.org>
+    Copyright (C) 2007 - 2012  Jean Delvare <khali@linux-fr.org>
     Copyright (C) 2010         Intel Corporation,
                                David Woodhouse <dwmw2@infradead.org>
 
@@ -51,6 +51,7 @@
   Patsburg (PCH) IDF    0x1d72     32     hard     yes     yes     yes
   DH89xxCC (PCH)        0x2330     32     hard     yes     yes     yes
   Panther Point (PCH)   0x1e22     32     hard     yes     yes     yes
+  Lynx Point (PCH)      0x8c22     32     hard     yes     yes     yes
 
   Features supported by this driver:
   Software PEC                     no
@@ -105,7 +106,7 @@
 #define SMBHSTCNT_KILL		2
 
 /* Other settings */
-#define MAX_TIMEOUT		100
+#define MAX_RETRIES		400
 #define ENABLE_INT9		0	/* set to 0x01 to enable - untested */
 
 /* I801 command constants */
@@ -145,6 +146,7 @@
 #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_SMBUS	0x1e22
 #define PCI_DEVICE_ID_INTEL_DH89XXCC_SMBUS	0x2330
 #define PCI_DEVICE_ID_INTEL_5_3400_SERIES_SMBUS	0x3b30
+#define PCI_DEVICE_ID_INTEL_LYNXPOINT_SMBUS	0x8c22
 
 struct i801_priv {
 	struct i2c_adapter adapter;
@@ -215,7 +217,7 @@ static int i801_check_post(struct i801_priv *priv, int status, int timeout)
 		dev_dbg(&priv->pci_dev->dev, "Terminating the current operation\n");
 		outb_p(inb_p(SMBHSTCNT(priv)) | SMBHSTCNT_KILL,
 		       SMBHSTCNT(priv));
-		msleep(1);
+		usleep_range(1000, 2000);
 		outb_p(inb_p(SMBHSTCNT(priv)) & (~SMBHSTCNT_KILL),
 		       SMBHSTCNT(priv));
 
@@ -272,11 +274,11 @@ static int i801_transaction(struct i801_priv *priv, int xact)
 
 	/* We will always wait for a fraction of a second! */
 	do {
-		msleep(1);
+		usleep_range(250, 500);
 		status = inb_p(SMBHSTSTS(priv));
-	} while ((status & SMBHSTSTS_HOST_BUSY) && (timeout++ < MAX_TIMEOUT));
+	} while ((status & SMBHSTSTS_HOST_BUSY) && (timeout++ < MAX_RETRIES));
 
-	result = i801_check_post(priv, status, timeout > MAX_TIMEOUT);
+	result = i801_check_post(priv, status, timeout > MAX_RETRIES);
 	if (result < 0)
 		return result;
 
@@ -291,12 +293,12 @@ static void i801_wait_hwpec(struct i801_priv *priv)
 	int status;
 
 	do {
-		msleep(1);
+		usleep_range(250, 500);
 		status = inb_p(SMBHSTSTS(priv));
 	} while ((!(status & SMBHSTSTS_INTR))
-		 && (timeout++ < MAX_TIMEOUT));
+		 && (timeout++ < MAX_RETRIES));
 
-	if (timeout > MAX_TIMEOUT)
+	if (timeout > MAX_RETRIES)
 		dev_dbg(&priv->pci_dev->dev, "PEC Timeout!\n");
 
 	outb_p(status, SMBHSTSTS(priv));
@@ -380,12 +382,12 @@ static int i801_block_transaction_byte_by_byte(struct i801_priv *priv,
 		/* We will always wait for a fraction of a second! */
 		timeout = 0;
 		do {
-			msleep(1);
+			usleep_range(250, 500);
 			status = inb_p(SMBHSTSTS(priv));
 		} while ((!(status & SMBHSTSTS_BYTE_DONE))
-			 && (timeout++ < MAX_TIMEOUT));
+			 && (timeout++ < MAX_RETRIES));
 
-		result = i801_check_post(priv, status, timeout > MAX_TIMEOUT);
+		result = i801_check_post(priv, status, timeout > MAX_RETRIES);
 		if (result < 0)
 			return result;
 
@@ -633,6 +635,7 @@ static DEFINE_PCI_DEVICE_TABLE(i801_ids) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS_IDF2) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DH89XXCC_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_PANTHERPOINT_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LYNXPOINT_SMBUS) },
 	{ 0, }
 };
 
diff --git a/drivers/i2c/busses/i2c-isch.c b/drivers/i2c/busses/i2c-isch.c
index 6561d275b8cf..f90a6057508d 100644
--- a/drivers/i2c/busses/i2c-isch.c
+++ b/drivers/i2c/busses/i2c-isch.c
@@ -47,7 +47,7 @@
 #define SMBBLKDAT	(0x20 + sch_smba)
 
 /* Other settings */
-#define MAX_TIMEOUT	500
+#define MAX_RETRIES	5000
 
 /* I2C constants */
 #define SCH_QUICK		0x00
@@ -68,7 +68,7 @@ static int sch_transaction(void)
 {
 	int temp;
 	int result = 0;
-	int timeout = 0;
+	int retries = 0;
 
 	dev_dbg(&sch_adapter.dev, "Transaction (pre): CNT=%02x, CMD=%02x, "
 		"ADD=%02x, DAT0=%02x, DAT1=%02x\n", inb(SMBHSTCNT),
@@ -100,12 +100,12 @@ static int sch_transaction(void)
 	outb(inb(SMBHSTCNT) | 0x10, SMBHSTCNT);
 
 	do {
-		msleep(1);
+		usleep_range(100, 200);
 		temp = inb(SMBHSTSTS) & 0x0f;
-	} while ((temp & 0x08) && (timeout++ < MAX_TIMEOUT));
+	} while ((temp & 0x08) && (retries++ < MAX_RETRIES));
 
 	/* If the SMBus is still busy, we give up */
-	if (timeout > MAX_TIMEOUT) {
+	if (retries > MAX_RETRIES) {
 		dev_err(&sch_adapter.dev, "SMBus Timeout!\n");
 		result = -ETIMEDOUT;
 	}
diff --git a/drivers/i2c/i2c-boardinfo.c b/drivers/i2c/i2c-boardinfo.c
index 10274ffb66d7..f24cc64e2e8c 100644
--- a/drivers/i2c/i2c-boardinfo.c
+++ b/drivers/i2c/i2c-boardinfo.c
@@ -13,7 +13,8 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301 USA.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index e9c18939eda7..feb7dc359186 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -14,7 +14,8 @@
 
     You should have received a copy of the GNU General Public License
     along with this program; if not, write to the Free Software
-    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.		     */
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.							     */
 /* ------------------------------------------------------------------------- */
 
 /* With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi>.
diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h
index 9f9c57ff6708..18a8fd21d2c2 100644
--- a/drivers/i2c/i2c-core.h
+++ b/drivers/i2c/i2c-core.h
@@ -13,7 +13,8 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301 USA.
  */
 
 #include <linux/rwsem.h>
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 10e7f1e76586..45048323b75e 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -17,7 +17,8 @@
 
     You should have received a copy of the GNU General Public License
     along with this program; if not, write to the Free Software
-    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
 */
 
 /* Note that this is a complete rewrite of Simon Vogl's i2c-dev module.
diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c
index f61ccc1e5ea3..9836d08f7a77 100644
--- a/drivers/i2c/i2c-smbus.c
+++ b/drivers/i2c/i2c-smbus.c
@@ -16,7 +16,8 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301 USA.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/i2c/muxes/pca9541.c b/drivers/i2c/muxes/pca9541.c
index ed699c5aa79d..e0df9b6c66b3 100644
--- a/drivers/i2c/muxes/pca9541.c
+++ b/drivers/i2c/muxes/pca9541.c
@@ -393,18 +393,7 @@ static struct i2c_driver pca9541_driver = {
 	.id_table = pca9541_id,
 };
 
-static int __init pca9541_init(void)
-{
-	return i2c_add_driver(&pca9541_driver);
-}
-
-static void __exit pca9541_exit(void)
-{
-	i2c_del_driver(&pca9541_driver);
-}
-
-module_init(pca9541_init);
-module_exit(pca9541_exit);
+module_i2c_driver(pca9541_driver);
 
 MODULE_AUTHOR("Guenter Roeck <guenter.roeck@ericsson.com>");
 MODULE_DESCRIPTION("PCA9541 I2C master selector driver");
diff --git a/drivers/i2c/muxes/pca954x.c b/drivers/i2c/muxes/pca954x.c
index 6f8953664636..0e37ef27aa12 100644
--- a/drivers/i2c/muxes/pca954x.c
+++ b/drivers/i2c/muxes/pca954x.c
@@ -284,18 +284,7 @@ static struct i2c_driver pca954x_driver = {
 	.id_table	= pca954x_id,
 };
 
-static int __init pca954x_init(void)
-{
-	return i2c_add_driver(&pca954x_driver);
-}
-
-static void __exit pca954x_exit(void)
-{
-	i2c_del_driver(&pca954x_driver);
-}
-
-module_init(pca954x_init);
-module_exit(pca954x_exit);
+module_i2c_driver(pca954x_driver);
 
 MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
 MODULE_DESCRIPTION("PCA954x I2C mux/switch driver");
diff --git a/drivers/ide/ide-cs.c b/drivers/ide/ide-cs.c
index d2f3db3cf3ed..28e344ea514c 100644
--- a/drivers/ide/ide-cs.c
+++ b/drivers/ide/ide-cs.c
@@ -41,7 +41,6 @@
 #include <linux/major.h>
 #include <linux/delay.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
diff --git a/drivers/ide/qd65xx.c b/drivers/ide/qd65xx.c
index 8bbfe5557c7b..e03f4f19c1d6 100644
--- a/drivers/ide/qd65xx.c
+++ b/drivers/ide/qd65xx.c
@@ -29,7 +29,6 @@
 #include <linux/blkdev.h>
 #include <linux/ide.h>
 #include <linux/init.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #define DRV_NAME "qd65xx"
diff --git a/drivers/idle/i7300_idle.c b/drivers/idle/i7300_idle.c
index c976285d313e..fa080ebd568f 100644
--- a/drivers/idle/i7300_idle.c
+++ b/drivers/idle/i7300_idle.c
@@ -516,12 +516,6 @@ static struct notifier_block i7300_idle_nb = {
 
 MODULE_DEVICE_TABLE(pci, pci_tbl);
 
-int stats_open_generic(struct inode *inode, struct file *fp)
-{
-	fp->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t stats_read_ul(struct file *fp, char __user *ubuf, size_t count,
 				loff_t *off)
 {
@@ -534,7 +528,7 @@ static ssize_t stats_read_ul(struct file *fp, char __user *ubuf, size_t count,
 }
 
 static const struct file_operations idle_fops = {
-	.open	= stats_open_generic,
+	.open	= simple_open,
 	.read	= stats_read_ul,
 	.llseek = default_llseek,
 };
diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/infiniband/hw/ehca/ehca_reqs.c
index 9a3fbfca9b41..fd05f48f6b0b 100644
--- a/drivers/infiniband/hw/ehca/ehca_reqs.c
+++ b/drivers/infiniband/hw/ehca/ehca_reqs.c
@@ -42,7 +42,6 @@
  */
 
 
-#include <asm/system.h>
 #include "ehca_classes.h"
 #include "ehca_tools.h"
 #include "ehca_qes.h"
diff --git a/drivers/input/input-compat.c b/drivers/input/input-compat.c
index e46a86776a6b..64ca7113ff28 100644
--- a/drivers/input/input-compat.c
+++ b/drivers/input/input-compat.c
@@ -17,7 +17,7 @@
 int input_event_from_user(const char __user *buffer,
 			  struct input_event *event)
 {
-	if (INPUT_COMPAT_TEST) {
+	if (INPUT_COMPAT_TEST && !COMPAT_USE_64BIT_TIME) {
 		struct input_event_compat compat_event;
 
 		if (copy_from_user(&compat_event, buffer,
@@ -41,7 +41,7 @@ int input_event_from_user(const char __user *buffer,
 int input_event_to_user(char __user *buffer,
 			const struct input_event *event)
 {
-	if (INPUT_COMPAT_TEST) {
+	if (INPUT_COMPAT_TEST && !COMPAT_USE_64BIT_TIME) {
 		struct input_event_compat compat_event;
 
 		compat_event.time.tv_sec = event->time.tv_sec;
diff --git a/drivers/input/input-compat.h b/drivers/input/input-compat.h
index 22be27b424de..148f66fe3205 100644
--- a/drivers/input/input-compat.h
+++ b/drivers/input/input-compat.h
@@ -67,7 +67,7 @@ struct ff_effect_compat {
 
 static inline size_t input_event_size(void)
 {
-	return INPUT_COMPAT_TEST ?
+	return (INPUT_COMPAT_TEST && !COMPAT_USE_64BIT_TIME) ?
 		sizeof(struct input_event_compat) : sizeof(struct input_event);
 }
 
diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index c24ec2d5f926..26043cc6a016 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -13,7 +13,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/joystick.h>
diff --git a/drivers/input/joystick/amijoy.c b/drivers/input/joystick/amijoy.c
index 0bc86204213e..c65b5fa69f1e 100644
--- a/drivers/input/joystick/amijoy.c
+++ b/drivers/input/joystick/amijoy.c
@@ -35,7 +35,6 @@
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
 
-#include <asm/system.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
 
@@ -108,6 +107,9 @@ static int __init amijoy_init(void)
 	int i, j;
 	int err;
 
+	if (!MACH_IS_AMIGA)
+		return -ENODEV;
+
 	for (i = 0; i < 2; i++) {
 		if (!amijoy[i])
 			continue;
diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index ed1ed469d085..62bfce468f9f 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -28,14 +28,18 @@
 #include <linux/gpio.h>
 #include <linux/of_platform.h>
 #include <linux/of_gpio.h>
+#include <linux/spinlock.h>
 
 struct gpio_button_data {
-	struct gpio_keys_button *button;
+	const struct gpio_keys_button *button;
 	struct input_dev *input;
 	struct timer_list timer;
 	struct work_struct work;
-	int timer_debounce;	/* in msecs */
+	unsigned int timer_debounce;	/* in msecs */
+	unsigned int irq;
+	spinlock_t lock;
 	bool disabled;
+	bool key_pressed;
 };
 
 struct gpio_keys_drvdata {
@@ -114,7 +118,7 @@ static void gpio_keys_disable_button(struct gpio_button_data *bdata)
 		/*
 		 * Disable IRQ and possible debouncing timer.
 		 */
-		disable_irq(gpio_to_irq(bdata->button->gpio));
+		disable_irq(bdata->irq);
 		if (bdata->timer_debounce)
 			del_timer_sync(&bdata->timer);
 
@@ -135,7 +139,7 @@ static void gpio_keys_disable_button(struct gpio_button_data *bdata)
 static void gpio_keys_enable_button(struct gpio_button_data *bdata)
 {
 	if (bdata->disabled) {
-		enable_irq(gpio_to_irq(bdata->button->gpio));
+		enable_irq(bdata->irq);
 		bdata->disabled = false;
 	}
 }
@@ -195,7 +199,7 @@ static ssize_t gpio_keys_attr_show_helper(struct gpio_keys_drvdata *ddata,
  * @type: button type (%EV_KEY, %EV_SW)
  *
  * This function parses stringified bitmap from @buf and disables/enables
- * GPIO buttons accordinly. Returns 0 on success and negative error
+ * GPIO buttons accordingly. Returns 0 on success and negative error
  * on failure.
  */
 static ssize_t gpio_keys_attr_store_helper(struct gpio_keys_drvdata *ddata,
@@ -320,9 +324,9 @@ static struct attribute_group gpio_keys_attr_group = {
 	.attrs = gpio_keys_attrs,
 };
 
-static void gpio_keys_report_event(struct gpio_button_data *bdata)
+static void gpio_keys_gpio_report_event(struct gpio_button_data *bdata)
 {
-	struct gpio_keys_button *button = bdata->button;
+	const struct gpio_keys_button *button = bdata->button;
 	struct input_dev *input = bdata->input;
 	unsigned int type = button->type ?: EV_KEY;
 	int state = (gpio_get_value_cansleep(button->gpio) ? 1 : 0) ^ button->active_low;
@@ -336,27 +340,26 @@ static void gpio_keys_report_event(struct gpio_button_data *bdata)
 	input_sync(input);
 }
 
-static void gpio_keys_work_func(struct work_struct *work)
+static void gpio_keys_gpio_work_func(struct work_struct *work)
 {
 	struct gpio_button_data *bdata =
 		container_of(work, struct gpio_button_data, work);
 
-	gpio_keys_report_event(bdata);
+	gpio_keys_gpio_report_event(bdata);
 }
 
-static void gpio_keys_timer(unsigned long _data)
+static void gpio_keys_gpio_timer(unsigned long _data)
 {
-	struct gpio_button_data *data = (struct gpio_button_data *)_data;
+	struct gpio_button_data *bdata = (struct gpio_button_data *)_data;
 
-	schedule_work(&data->work);
+	schedule_work(&bdata->work);
 }
 
-static irqreturn_t gpio_keys_isr(int irq, void *dev_id)
+static irqreturn_t gpio_keys_gpio_isr(int irq, void *dev_id)
 {
 	struct gpio_button_data *bdata = dev_id;
-	struct gpio_keys_button *button = bdata->button;
 
-	BUG_ON(irq != gpio_to_irq(button->gpio));
+	BUG_ON(irq != bdata->irq);
 
 	if (bdata->timer_debounce)
 		mod_timer(&bdata->timer,
@@ -367,50 +370,133 @@ static irqreturn_t gpio_keys_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void gpio_keys_irq_timer(unsigned long _data)
+{
+	struct gpio_button_data *bdata = (struct gpio_button_data *)_data;
+	struct input_dev *input = bdata->input;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bdata->lock, flags);
+	if (bdata->key_pressed) {
+		input_event(input, EV_KEY, bdata->button->code, 0);
+		input_sync(input);
+		bdata->key_pressed = false;
+	}
+	spin_unlock_irqrestore(&bdata->lock, flags);
+}
+
+static irqreturn_t gpio_keys_irq_isr(int irq, void *dev_id)
+{
+	struct gpio_button_data *bdata = dev_id;
+	const struct gpio_keys_button *button = bdata->button;
+	struct input_dev *input = bdata->input;
+	unsigned long flags;
+
+	BUG_ON(irq != bdata->irq);
+
+	spin_lock_irqsave(&bdata->lock, flags);
+
+	if (!bdata->key_pressed) {
+		input_event(input, EV_KEY, button->code, 1);
+		input_sync(input);
+
+		if (!bdata->timer_debounce) {
+			input_event(input, EV_KEY, button->code, 0);
+			input_sync(input);
+			goto out;
+		}
+
+		bdata->key_pressed = true;
+	}
+
+	if (bdata->timer_debounce)
+		mod_timer(&bdata->timer,
+			jiffies + msecs_to_jiffies(bdata->timer_debounce));
+out:
+	spin_unlock_irqrestore(&bdata->lock, flags);
+	return IRQ_HANDLED;
+}
+
 static int __devinit gpio_keys_setup_key(struct platform_device *pdev,
+					 struct input_dev *input,
 					 struct gpio_button_data *bdata,
-					 struct gpio_keys_button *button)
+					 const struct gpio_keys_button *button)
 {
 	const char *desc = button->desc ? button->desc : "gpio_keys";
 	struct device *dev = &pdev->dev;
+	irq_handler_t isr;
 	unsigned long irqflags;
 	int irq, error;
 
-	setup_timer(&bdata->timer, gpio_keys_timer, (unsigned long)bdata);
-	INIT_WORK(&bdata->work, gpio_keys_work_func);
+	bdata->input = input;
+	bdata->button = button;
+	spin_lock_init(&bdata->lock);
 
-	error = gpio_request(button->gpio, desc);
-	if (error < 0) {
-		dev_err(dev, "failed to request GPIO %d, error %d\n",
-			button->gpio, error);
-		goto fail2;
-	}
+	if (gpio_is_valid(button->gpio)) {
 
-	error = gpio_direction_input(button->gpio);
-	if (error < 0) {
-		dev_err(dev, "failed to configure"
-			" direction for GPIO %d, error %d\n",
-			button->gpio, error);
-		goto fail3;
-	}
+		error = gpio_request(button->gpio, desc);
+		if (error < 0) {
+			dev_err(dev, "Failed to request GPIO %d, error %d\n",
+				button->gpio, error);
+			return error;
+		}
 
-	if (button->debounce_interval) {
-		error = gpio_set_debounce(button->gpio,
-					  button->debounce_interval * 1000);
-		/* use timer if gpiolib doesn't provide debounce */
-		if (error < 0)
-			bdata->timer_debounce = button->debounce_interval;
-	}
+		error = gpio_direction_input(button->gpio);
+		if (error < 0) {
+			dev_err(dev,
+				"Failed to configure direction for GPIO %d, error %d\n",
+				button->gpio, error);
+			goto fail;
+		}
 
-	irq = gpio_to_irq(button->gpio);
-	if (irq < 0) {
-		error = irq;
-		dev_err(dev, "Unable to get irq number for GPIO %d, error %d\n",
-			button->gpio, error);
-		goto fail3;
+		if (button->debounce_interval) {
+			error = gpio_set_debounce(button->gpio,
+					button->debounce_interval * 1000);
+			/* use timer if gpiolib doesn't provide debounce */
+			if (error < 0)
+				bdata->timer_debounce =
+						button->debounce_interval;
+		}
+
+		irq = gpio_to_irq(button->gpio);
+		if (irq < 0) {
+			error = irq;
+			dev_err(dev,
+				"Unable to get irq number for GPIO %d, error %d\n",
+				button->gpio, error);
+			goto fail;
+		}
+		bdata->irq = irq;
+
+		INIT_WORK(&bdata->work, gpio_keys_gpio_work_func);
+		setup_timer(&bdata->timer,
+			    gpio_keys_gpio_timer, (unsigned long)bdata);
+
+		isr = gpio_keys_gpio_isr;
+		irqflags = IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING;
+
+	} else {
+		if (!button->irq) {
+			dev_err(dev, "No IRQ specified\n");
+			return -EINVAL;
+		}
+		bdata->irq = button->irq;
+
+		if (button->type && button->type != EV_KEY) {
+			dev_err(dev, "Only EV_KEY allowed for IRQ buttons.\n");
+			return -EINVAL;
+		}
+
+		bdata->timer_debounce = button->debounce_interval;
+		setup_timer(&bdata->timer,
+			    gpio_keys_irq_timer, (unsigned long)bdata);
+
+		isr = gpio_keys_irq_isr;
+		irqflags = 0;
 	}
 
-	irqflags = IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING;
+	input_set_capability(input, button->type ?: EV_KEY, button->code);
+
 	/*
 	 * If platform has specified that the button can be disabled,
 	 * we don't want it to share the interrupt line.
@@ -418,18 +504,19 @@ static int __devinit gpio_keys_setup_key(struct platform_device *pdev,
 	if (!button->can_disable)
 		irqflags |= IRQF_SHARED;
 
-	error = request_threaded_irq(irq, NULL, gpio_keys_isr, irqflags, desc, bdata);
+	error = request_any_context_irq(bdata->irq, isr, irqflags, desc, bdata);
 	if (error < 0) {
 		dev_err(dev, "Unable to claim irq %d; error %d\n",
-			irq, error);
-		goto fail3;
+			bdata->irq, error);
+		goto fail;
 	}
 
 	return 0;
 
-fail3:
-	gpio_free(button->gpio);
-fail2:
+fail:
+	if (gpio_is_valid(button->gpio))
+		gpio_free(button->gpio);
+
 	return error;
 }
 
@@ -547,9 +634,19 @@ static int gpio_keys_get_devtree_pdata(struct device *dev,
 
 #endif
 
+static void gpio_remove_key(struct gpio_button_data *bdata)
+{
+	free_irq(bdata->irq, bdata);
+	if (bdata->timer_debounce)
+		del_timer_sync(&bdata->timer);
+	cancel_work_sync(&bdata->work);
+	if (gpio_is_valid(bdata->button->gpio))
+		gpio_free(bdata->button->gpio);
+}
+
 static int __devinit gpio_keys_probe(struct platform_device *pdev)
 {
-	struct gpio_keys_platform_data *pdata = pdev->dev.platform_data;
+	const struct gpio_keys_platform_data *pdata = pdev->dev.platform_data;
 	struct gpio_keys_drvdata *ddata;
 	struct device *dev = &pdev->dev;
 	struct gpio_keys_platform_data alt_pdata;
@@ -599,21 +696,15 @@ static int __devinit gpio_keys_probe(struct platform_device *pdev)
 		__set_bit(EV_REP, input->evbit);
 
 	for (i = 0; i < pdata->nbuttons; i++) {
-		struct gpio_keys_button *button = &pdata->buttons[i];
+		const struct gpio_keys_button *button = &pdata->buttons[i];
 		struct gpio_button_data *bdata = &ddata->data[i];
-		unsigned int type = button->type ?: EV_KEY;
-
-		bdata->input = input;
-		bdata->button = button;
 
-		error = gpio_keys_setup_key(pdev, bdata, button);
+		error = gpio_keys_setup_key(pdev, input, bdata, button);
 		if (error)
 			goto fail2;
 
 		if (button->wakeup)
 			wakeup = 1;
-
-		input_set_capability(input, type, button->code);
 	}
 
 	error = sysfs_create_group(&pdev->dev.kobj, &gpio_keys_attr_group);
@@ -630,9 +721,12 @@ static int __devinit gpio_keys_probe(struct platform_device *pdev)
 		goto fail3;
 	}
 
-	/* get current state of buttons */
-	for (i = 0; i < pdata->nbuttons; i++)
-		gpio_keys_report_event(&ddata->data[i]);
+	/* get current state of buttons that are connected to GPIOs */
+	for (i = 0; i < pdata->nbuttons; i++) {
+		struct gpio_button_data *bdata = &ddata->data[i];
+		if (gpio_is_valid(bdata->button->gpio))
+			gpio_keys_gpio_report_event(bdata);
+	}
 	input_sync(input);
 
 	device_init_wakeup(&pdev->dev, wakeup);
@@ -642,13 +736,8 @@ static int __devinit gpio_keys_probe(struct platform_device *pdev)
  fail3:
 	sysfs_remove_group(&pdev->dev.kobj, &gpio_keys_attr_group);
  fail2:
-	while (--i >= 0) {
-		free_irq(gpio_to_irq(pdata->buttons[i].gpio), &ddata->data[i]);
-		if (ddata->data[i].timer_debounce)
-			del_timer_sync(&ddata->data[i].timer);
-		cancel_work_sync(&ddata->data[i].work);
-		gpio_free(pdata->buttons[i].gpio);
-	}
+	while (--i >= 0)
+		gpio_remove_key(&ddata->data[i]);
 
 	platform_set_drvdata(pdev, NULL);
  fail1:
@@ -671,14 +760,8 @@ static int __devexit gpio_keys_remove(struct platform_device *pdev)
 
 	device_init_wakeup(&pdev->dev, 0);
 
-	for (i = 0; i < ddata->n_buttons; i++) {
-		int irq = gpio_to_irq(ddata->data[i].button->gpio);
-		free_irq(irq, &ddata->data[i]);
-		if (ddata->data[i].timer_debounce)
-			del_timer_sync(&ddata->data[i].timer);
-		cancel_work_sync(&ddata->data[i].work);
-		gpio_free(ddata->data[i].button->gpio);
-	}
+	for (i = 0; i < ddata->n_buttons; i++)
+		gpio_remove_key(&ddata->data[i]);
 
 	input_unregister_device(input);
 
@@ -703,11 +786,9 @@ static int gpio_keys_suspend(struct device *dev)
 
 	if (device_may_wakeup(dev)) {
 		for (i = 0; i < ddata->n_buttons; i++) {
-			struct gpio_keys_button *button = ddata->data[i].button;
-			if (button->wakeup) {
-				int irq = gpio_to_irq(button->gpio);
-				enable_irq_wake(irq);
-			}
+			struct gpio_button_data *bdata = &ddata->data[i];
+			if (bdata->button->wakeup)
+				enable_irq_wake(bdata->irq);
 		}
 	}
 
@@ -720,14 +801,12 @@ static int gpio_keys_resume(struct device *dev)
 	int i;
 
 	for (i = 0; i < ddata->n_buttons; i++) {
+		struct gpio_button_data *bdata = &ddata->data[i];
+		if (bdata->button->wakeup && device_may_wakeup(dev))
+			disable_irq_wake(bdata->irq);
 
-		struct gpio_keys_button *button = ddata->data[i].button;
-		if (button->wakeup && device_may_wakeup(dev)) {
-			int irq = gpio_to_irq(button->gpio);
-			disable_irq_wake(irq);
-		}
-
-		gpio_keys_report_event(&ddata->data[i]);
+		if (gpio_is_valid(bdata->button->gpio))
+			gpio_keys_gpio_report_event(bdata);
 	}
 	input_sync(ddata->input);
 
diff --git a/drivers/input/keyboard/jornada720_kbd.c b/drivers/input/keyboard/jornada720_kbd.c
index eeafc30b207b..9d639fa1afbd 100644
--- a/drivers/input/keyboard/jornada720_kbd.c
+++ b/drivers/input/keyboard/jornada720_kbd.c
@@ -27,6 +27,7 @@
 
 #include <mach/jornada720.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 
 MODULE_AUTHOR("Kristoffer Ericson <Kristoffer.Ericson@gmail.com>");
 MODULE_DESCRIPTION("HP Jornada 710/720/728 keyboard driver");
diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c
index 21c42f852343..fe4ac95ca6c8 100644
--- a/drivers/input/keyboard/tegra-kbc.c
+++ b/drivers/input/keyboard/tegra-kbc.c
@@ -630,6 +630,7 @@ tegra_kbc_dt_parse_pdata(struct platform_device *pdev)
 	if (!np)
 		return NULL;
 
+	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return NULL;
 
diff --git a/drivers/input/misc/88pm860x_onkey.c b/drivers/input/misc/88pm860x_onkey.c
index f2e0cbc5ab64..f9ce1835e4d7 100644
--- a/drivers/input/misc/88pm860x_onkey.c
+++ b/drivers/input/misc/88pm860x_onkey.c
@@ -105,6 +105,8 @@ static int __devinit pm860x_onkey_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, info);
+	device_init_wakeup(&pdev->dev, 1);
+
 	return 0;
 
 out_irq:
@@ -129,10 +131,34 @@ static int __devexit pm860x_onkey_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int pm860x_onkey_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct pm860x_chip *chip = dev_get_drvdata(pdev->dev.parent);
+
+	if (device_may_wakeup(dev))
+		chip->wakeup_flag |= 1 << PM8607_IRQ_ONKEY;
+	return 0;
+}
+static int pm860x_onkey_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct pm860x_chip *chip = dev_get_drvdata(pdev->dev.parent);
+
+	if (device_may_wakeup(dev))
+		chip->wakeup_flag &= ~(1 << PM8607_IRQ_ONKEY);
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(pm860x_onkey_pm_ops, pm860x_onkey_suspend, pm860x_onkey_resume);
+
 static struct platform_driver pm860x_onkey_driver = {
 	.driver		= {
 		.name	= "88pm860x-onkey",
 		.owner	= THIS_MODULE,
+		.pm	= &pm860x_onkey_pm_ops,
 	},
 	.probe		= pm860x_onkey_probe,
 	.remove		= __devexit_p(pm860x_onkey_remove),
diff --git a/drivers/input/mouse/amimouse.c b/drivers/input/mouse/amimouse.c
index ff5f61a0fd3a..5fa99341a39d 100644
--- a/drivers/input/mouse/amimouse.c
+++ b/drivers/input/mouse/amimouse.c
@@ -25,7 +25,6 @@
 
 #include <asm/irq.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
diff --git a/drivers/input/mouse/atarimouse.c b/drivers/input/mouse/atarimouse.c
index 5c4a692bf73a..d1c43236b125 100644
--- a/drivers/input/mouse/atarimouse.c
+++ b/drivers/input/mouse/atarimouse.c
@@ -47,7 +47,6 @@
 
 #include <asm/irq.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/atarihw.h>
 #include <asm/atarikb.h>
diff --git a/drivers/input/mouse/sentelic.c b/drivers/input/mouse/sentelic.c
index 2a77a52d2e62..a977bfaa6821 100644
--- a/drivers/input/mouse/sentelic.c
+++ b/drivers/input/mouse/sentelic.c
@@ -2,7 +2,7 @@
  * Finger Sensing Pad PS/2 mouse driver.
  *
  * Copyright (C) 2005-2007 Asia Vital Components Co., Ltd.
- * Copyright (C) 2005-2011 Tai-hwa Liang, Sentelic Corporation.
+ * Copyright (C) 2005-2012 Tai-hwa Liang, Sentelic Corporation.
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
@@ -21,6 +21,7 @@
 
 #include <linux/module.h>
 #include <linux/input.h>
+#include <linux/input/mt.h>
 #include <linux/ctype.h>
 #include <linux/libps2.h>
 #include <linux/serio.h>
@@ -36,6 +37,9 @@
 #define	FSP_CMD_TIMEOUT		200
 #define	FSP_CMD_TIMEOUT2	30
 
+#define	GET_ABS_X(packet)	((packet[1] << 2) | ((packet[3] >> 2) & 0x03))
+#define	GET_ABS_Y(packet)	((packet[2] << 2) | (packet[3] & 0x03))
+
 /** Driver version. */
 static const char fsp_drv_ver[] = "1.0.0-K";
 
@@ -128,8 +132,9 @@ static int fsp_reg_read(struct psmouse *psmouse, int reg_addr, int *reg_val)
  out:
 	ps2_end_command(ps2dev);
 	psmouse_activate(psmouse);
-	dev_dbg(&ps2dev->serio->dev, "READ REG: 0x%02x is 0x%02x (rc = %d)\n",
-		reg_addr, *reg_val, rc);
+	psmouse_dbg(psmouse,
+		    "READ REG: 0x%02x is 0x%02x (rc = %d)\n",
+		    reg_addr, *reg_val, rc);
 	return rc;
 }
 
@@ -179,8 +184,9 @@ static int fsp_reg_write(struct psmouse *psmouse, int reg_addr, int reg_val)
 
  out:
 	ps2_end_command(ps2dev);
-	dev_dbg(&ps2dev->serio->dev, "WRITE REG: 0x%02x to 0x%02x (rc = %d)\n",
-		reg_addr, reg_val, rc);
+	psmouse_dbg(psmouse,
+		    "WRITE REG: 0x%02x to 0x%02x (rc = %d)\n",
+		    reg_addr, reg_val, rc);
 	return rc;
 }
 
@@ -237,8 +243,9 @@ static int fsp_page_reg_read(struct psmouse *psmouse, int *reg_val)
  out:
 	ps2_end_command(ps2dev);
 	psmouse_activate(psmouse);
-	dev_dbg(&ps2dev->serio->dev, "READ PAGE REG: 0x%02x (rc = %d)\n",
-		*reg_val, rc);
+	psmouse_dbg(psmouse,
+		    "READ PAGE REG: 0x%02x (rc = %d)\n",
+		    *reg_val, rc);
 	return rc;
 }
 
@@ -274,8 +281,9 @@ static int fsp_page_reg_write(struct psmouse *psmouse, int reg_val)
 
  out:
 	ps2_end_command(ps2dev);
-	dev_dbg(&ps2dev->serio->dev, "WRITE PAGE REG: to 0x%02x (rc = %d)\n",
-		reg_val, rc);
+	psmouse_dbg(psmouse,
+		    "WRITE PAGE REG: to 0x%02x (rc = %d)\n",
+		    reg_val, rc);
 	return rc;
 }
 
@@ -319,7 +327,7 @@ static int fsp_opc_tag_enable(struct psmouse *psmouse, bool enable)
 	int res = 0;
 
 	if (fsp_reg_read(psmouse, FSP_REG_OPC_QDOWN, &v) == -1) {
-		dev_err(&psmouse->ps2dev.serio->dev, "Unable get OPC state.\n");
+		psmouse_err(psmouse, "Unable get OPC state.\n");
 		return -EIO;
 	}
 
@@ -336,8 +344,7 @@ static int fsp_opc_tag_enable(struct psmouse *psmouse, bool enable)
 	}
 
 	if (res != 0) {
-		dev_err(&psmouse->ps2dev.serio->dev,
-			"Unable to enable OPC tag.\n");
+		psmouse_err(psmouse, "Unable to enable OPC tag.\n");
 		res = -EIO;
 	}
 
@@ -615,18 +622,40 @@ static struct attribute_group fsp_attribute_group = {
 	.attrs = fsp_attributes,
 };
 
-#ifdef FSP_DEBUG
-static void fsp_packet_debug(unsigned char packet[])
+#ifdef	FSP_DEBUG
+static void fsp_packet_debug(struct psmouse *psmouse, unsigned char packet[])
 {
 	static unsigned int ps2_packet_cnt;
 	static unsigned int ps2_last_second;
 	unsigned int jiffies_msec;
+	const char *packet_type = "UNKNOWN";
+	unsigned short abs_x = 0, abs_y = 0;
+
+	/* Interpret & dump the packet data. */
+	switch (packet[0] >> FSP_PKT_TYPE_SHIFT) {
+	case FSP_PKT_TYPE_ABS:
+		packet_type = "Absolute";
+		abs_x = GET_ABS_X(packet);
+		abs_y = GET_ABS_Y(packet);
+		break;
+	case FSP_PKT_TYPE_NORMAL:
+		packet_type = "Normal";
+		break;
+	case FSP_PKT_TYPE_NOTIFY:
+		packet_type = "Notify";
+		break;
+	case FSP_PKT_TYPE_NORMAL_OPC:
+		packet_type = "Normal-OPC";
+		break;
+	}
 
 	ps2_packet_cnt++;
 	jiffies_msec = jiffies_to_msecs(jiffies);
 	psmouse_dbg(psmouse,
-		    "%08dms PS/2 packets: %02x, %02x, %02x, %02x\n",
-		    jiffies_msec, packet[0], packet[1], packet[2], packet[3]);
+		    "%08dms %s packets: %02x, %02x, %02x, %02x; "
+		    "abs_x: %d, abs_y: %d\n",
+		    jiffies_msec, packet_type,
+		    packet[0], packet[1], packet[2], packet[3], abs_x, abs_y);
 
 	if (jiffies_msec - ps2_last_second > 1000) {
 		psmouse_dbg(psmouse, "PS/2 packets/sec = %d\n", ps2_packet_cnt);
@@ -635,17 +664,29 @@ static void fsp_packet_debug(unsigned char packet[])
 	}
 }
 #else
-static void fsp_packet_debug(unsigned char packet[])
+static void fsp_packet_debug(struct psmouse *psmouse, unsigned char packet[])
 {
 }
 #endif
 
+static void fsp_set_slot(struct input_dev *dev, int slot, bool active,
+			 unsigned int x, unsigned int y)
+{
+	input_mt_slot(dev, slot);
+	input_mt_report_slot_state(dev, MT_TOOL_FINGER, active);
+	if (active) {
+		input_report_abs(dev, ABS_MT_POSITION_X, x);
+		input_report_abs(dev, ABS_MT_POSITION_Y, y);
+	}
+}
+
 static psmouse_ret_t fsp_process_byte(struct psmouse *psmouse)
 {
 	struct input_dev *dev = psmouse->dev;
 	struct fsp_data *ad = psmouse->private;
 	unsigned char *packet = psmouse->packet;
 	unsigned char button_status = 0, lscroll = 0, rscroll = 0;
+	unsigned short abs_x, abs_y, fgrs = 0;
 	int rel_x, rel_y;
 
 	if (psmouse->pktcnt < 4)
@@ -655,16 +696,76 @@ static psmouse_ret_t fsp_process_byte(struct psmouse *psmouse)
 	 * Full packet accumulated, process it
 	 */
 
+	fsp_packet_debug(psmouse, packet);
+
 	switch (psmouse->packet[0] >> FSP_PKT_TYPE_SHIFT) {
 	case FSP_PKT_TYPE_ABS:
-		dev_warn(&psmouse->ps2dev.serio->dev,
-			 "Unexpected absolute mode packet, ignored.\n");
+		abs_x = GET_ABS_X(packet);
+		abs_y = GET_ABS_Y(packet);
+
+		if (packet[0] & FSP_PB0_MFMC) {
+			/*
+			 * MFMC packet: assume that there are two fingers on
+			 * pad
+			 */
+			fgrs = 2;
+
+			/* MFMC packet */
+			if (packet[0] & FSP_PB0_MFMC_FGR2) {
+				/* 2nd finger */
+				if (ad->last_mt_fgr == 2) {
+					/*
+					 * workaround for buggy firmware
+					 * which doesn't clear MFMC bit if
+					 * the 1st finger is up
+					 */
+					fgrs = 1;
+					fsp_set_slot(dev, 0, false, 0, 0);
+				}
+				ad->last_mt_fgr = 2;
+
+				fsp_set_slot(dev, 1, fgrs == 2, abs_x, abs_y);
+			} else {
+				/* 1st finger */
+				if (ad->last_mt_fgr == 1) {
+					/*
+					 * workaround for buggy firmware
+					 * which doesn't clear MFMC bit if
+					 * the 2nd finger is up
+					 */
+					fgrs = 1;
+					fsp_set_slot(dev, 1, false, 0, 0);
+				}
+				ad->last_mt_fgr = 1;
+				fsp_set_slot(dev, 0, fgrs != 0, abs_x, abs_y);
+			}
+		} else {
+			/* SFAC packet */
+
+			/* no multi-finger information */
+			ad->last_mt_fgr = 0;
+
+			if (abs_x != 0 && abs_y != 0)
+				fgrs = 1;
+
+			fsp_set_slot(dev, 0, fgrs > 0, abs_x, abs_y);
+			fsp_set_slot(dev, 1, false, 0, 0);
+		}
+		if (fgrs > 0) {
+			input_report_abs(dev, ABS_X, abs_x);
+			input_report_abs(dev, ABS_Y, abs_y);
+		}
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+		input_report_key(dev, BTN_TOUCH, fgrs);
+		input_report_key(dev, BTN_TOOL_FINGER, fgrs == 1);
+		input_report_key(dev, BTN_TOOL_DOUBLETAP, fgrs == 2);
 		break;
 
 	case FSP_PKT_TYPE_NORMAL_OPC:
 		/* on-pad click, filter it if necessary */
 		if ((ad->flags & FSPDRV_FLAG_EN_OPC) != FSPDRV_FLAG_EN_OPC)
-			packet[0] &= ~BIT(0);
+			packet[0] &= ~FSP_PB0_LBTN;
 		/* fall through */
 
 	case FSP_PKT_TYPE_NORMAL:
@@ -711,8 +812,6 @@ static psmouse_ret_t fsp_process_byte(struct psmouse *psmouse)
 
 	input_sync(dev);
 
-	fsp_packet_debug(packet);
-
 	return PSMOUSE_FULL_PACKET;
 }
 
@@ -736,42 +835,106 @@ static int fsp_activate_protocol(struct psmouse *psmouse)
 
 	ps2_command(ps2dev, param, PSMOUSE_CMD_GETID);
 	if (param[0] != 0x04) {
-		dev_err(&psmouse->ps2dev.serio->dev,
-			"Unable to enable 4 bytes packet format.\n");
+		psmouse_err(psmouse,
+			    "Unable to enable 4 bytes packet format.\n");
 		return -EIO;
 	}
 
-	if (fsp_reg_read(psmouse, FSP_REG_SYSCTL5, &val)) {
-		dev_err(&psmouse->ps2dev.serio->dev,
-			"Unable to read SYSCTL5 register.\n");
-		return -EIO;
-	}
+	if (pad->ver < FSP_VER_STL3888_C0) {
+		/* Preparing relative coordinates output for older hardware */
+		if (fsp_reg_read(psmouse, FSP_REG_SYSCTL5, &val)) {
+			psmouse_err(psmouse,
+				    "Unable to read SYSCTL5 register.\n");
+			return -EIO;
+		}
 
-	val &= ~(FSP_BIT_EN_MSID7 | FSP_BIT_EN_MSID8 | FSP_BIT_EN_AUTO_MSID8);
-	/* Ensure we are not in absolute mode */
-	val &= ~FSP_BIT_EN_PKT_G0;
-	if (pad->buttons == 0x06) {
-		/* Left/Middle/Right & Scroll Up/Down/Right/Left */
-		val |= FSP_BIT_EN_MSID6;
-	}
+		if (fsp_get_buttons(psmouse, &pad->buttons)) {
+			psmouse_err(psmouse,
+				    "Unable to retrieve number of buttons.\n");
+			return -EIO;
+		}
 
-	if (fsp_reg_write(psmouse, FSP_REG_SYSCTL5, val)) {
-		dev_err(&psmouse->ps2dev.serio->dev,
-			"Unable to set up required mode bits.\n");
-		return -EIO;
+		val &= ~(FSP_BIT_EN_MSID7 | FSP_BIT_EN_MSID8 | FSP_BIT_EN_AUTO_MSID8);
+		/* Ensure we are not in absolute mode */
+		val &= ~FSP_BIT_EN_PKT_G0;
+		if (pad->buttons == 0x06) {
+			/* Left/Middle/Right & Scroll Up/Down/Right/Left */
+			val |= FSP_BIT_EN_MSID6;
+		}
+
+		if (fsp_reg_write(psmouse, FSP_REG_SYSCTL5, val)) {
+			psmouse_err(psmouse,
+				    "Unable to set up required mode bits.\n");
+			return -EIO;
+		}
+
+		/*
+		 * Enable OPC tags such that driver can tell the difference
+		 * between on-pad and real button click
+		 */
+		if (fsp_opc_tag_enable(psmouse, true))
+			psmouse_warn(psmouse,
+				     "Failed to enable OPC tag mode.\n");
+		/* enable on-pad click by default */
+		pad->flags |= FSPDRV_FLAG_EN_OPC;
+
+		/* Enable on-pad vertical and horizontal scrolling */
+		fsp_onpad_vscr(psmouse, true);
+		fsp_onpad_hscr(psmouse, true);
+	} else {
+		/* Enable absolute coordinates output for Cx/Dx hardware */
+		if (fsp_reg_write(psmouse, FSP_REG_SWC1,
+				  FSP_BIT_SWC1_EN_ABS_1F |
+				  FSP_BIT_SWC1_EN_ABS_2F |
+				  FSP_BIT_SWC1_EN_FUP_OUT |
+				  FSP_BIT_SWC1_EN_ABS_CON)) {
+			psmouse_err(psmouse,
+				    "Unable to enable absolute coordinates output.\n");
+			return -EIO;
+		}
 	}
 
-	/*
-	 * Enable OPC tags such that driver can tell the difference between
-	 * on-pad and real button click
-	 */
-	if (fsp_opc_tag_enable(psmouse, true))
-		dev_warn(&psmouse->ps2dev.serio->dev,
-			 "Failed to enable OPC tag mode.\n");
+	return 0;
+}
 
-	/* Enable on-pad vertical and horizontal scrolling */
-	fsp_onpad_vscr(psmouse, true);
-	fsp_onpad_hscr(psmouse, true);
+static int fsp_set_input_params(struct psmouse *psmouse)
+{
+	struct input_dev *dev = psmouse->dev;
+	struct fsp_data *pad = psmouse->private;
+
+	if (pad->ver < FSP_VER_STL3888_C0) {
+		__set_bit(BTN_MIDDLE, dev->keybit);
+		__set_bit(BTN_BACK, dev->keybit);
+		__set_bit(BTN_FORWARD, dev->keybit);
+		__set_bit(REL_WHEEL, dev->relbit);
+		__set_bit(REL_HWHEEL, dev->relbit);
+	} else {
+		/*
+		 * Hardware prior to Cx performs much better in relative mode;
+		 * hence, only enable absolute coordinates output as well as
+		 * multi-touch output for the newer hardware.
+		 *
+		 * Maximum coordinates can be computed as:
+		 *
+		 *	number of scanlines * 64 - 57
+		 *
+		 * where number of X/Y scanline lines are 16/12.
+		 */
+		int abs_x = 967, abs_y = 711;
+
+		__set_bit(EV_ABS, dev->evbit);
+		__clear_bit(EV_REL, dev->evbit);
+		__set_bit(BTN_TOUCH, dev->keybit);
+		__set_bit(BTN_TOOL_FINGER, dev->keybit);
+		__set_bit(BTN_TOOL_DOUBLETAP, dev->keybit);
+		__set_bit(INPUT_PROP_SEMI_MT, dev->propbit);
+
+		input_set_abs_params(dev, ABS_X, 0, abs_x, 0, 0);
+		input_set_abs_params(dev, ABS_Y, 0, abs_y, 0, 0);
+		input_mt_init_slots(dev, 2);
+		input_set_abs_params(dev, ABS_MT_POSITION_X, 0, abs_x, 0, 0);
+		input_set_abs_params(dev, ABS_MT_POSITION_Y, 0, abs_y, 0, 0);
+	}
 
 	return 0;
 }
@@ -829,18 +992,16 @@ static int fsp_reconnect(struct psmouse *psmouse)
 int fsp_init(struct psmouse *psmouse)
 {
 	struct fsp_data *priv;
-	int ver, rev, buttons;
+	int ver, rev;
 	int error;
 
 	if (fsp_get_version(psmouse, &ver) ||
-	    fsp_get_revision(psmouse, &rev) ||
-	    fsp_get_buttons(psmouse, &buttons)) {
+	    fsp_get_revision(psmouse, &rev)) {
 		return -ENODEV;
 	}
 
-	psmouse_info(psmouse,
-		     "Finger Sensing Pad, hw: %d.%d.%d, sw: %s, buttons: %d\n",
-		     ver >> 4, ver & 0x0F, rev, fsp_drv_ver, buttons & 7);
+	psmouse_info(psmouse, "Finger Sensing Pad, hw: %d.%d.%d, sw: %s\n",
+		     ver >> 4, ver & 0x0F, rev, fsp_drv_ver);
 
 	psmouse->private = priv = kzalloc(sizeof(struct fsp_data), GFP_KERNEL);
 	if (!priv)
@@ -848,17 +1009,6 @@ int fsp_init(struct psmouse *psmouse)
 
 	priv->ver = ver;
 	priv->rev = rev;
-	priv->buttons = buttons;
-
-	/* enable on-pad click by default */
-	priv->flags |= FSPDRV_FLAG_EN_OPC;
-
-	/* Set up various supported input event bits */
-	__set_bit(BTN_MIDDLE, psmouse->dev->keybit);
-	__set_bit(BTN_BACK, psmouse->dev->keybit);
-	__set_bit(BTN_FORWARD, psmouse->dev->keybit);
-	__set_bit(REL_WHEEL, psmouse->dev->relbit);
-	__set_bit(REL_HWHEEL, psmouse->dev->relbit);
 
 	psmouse->protocol_handler = fsp_process_byte;
 	psmouse->disconnect = fsp_disconnect;
@@ -866,16 +1016,20 @@ int fsp_init(struct psmouse *psmouse)
 	psmouse->cleanup = fsp_reset;
 	psmouse->pktsize = 4;
 
-	/* set default packet output based on number of buttons we found */
 	error = fsp_activate_protocol(psmouse);
 	if (error)
 		goto err_out;
 
+	/* Set up various supported input event bits */
+	error = fsp_set_input_params(psmouse);
+	if (error)
+		goto err_out;
+
 	error = sysfs_create_group(&psmouse->ps2dev.serio->dev.kobj,
 				   &fsp_attribute_group);
 	if (error) {
-		dev_err(&psmouse->ps2dev.serio->dev,
-			"Failed to create sysfs attributes (%d)", error);
+		psmouse_err(psmouse,
+			    "Failed to create sysfs attributes (%d)", error);
 		goto err_out;
 	}
 
diff --git a/drivers/input/mouse/sentelic.h b/drivers/input/mouse/sentelic.h
index 2e4af24f8c15..334de19e5ddb 100644
--- a/drivers/input/mouse/sentelic.h
+++ b/drivers/input/mouse/sentelic.h
@@ -2,7 +2,7 @@
  * Finger Sensing Pad PS/2 mouse driver.
  *
  * Copyright (C) 2005-2007 Asia Vital Components Co., Ltd.
- * Copyright (C) 2005-2011 Tai-hwa Liang, Sentelic Corporation.
+ * Copyright (C) 2005-2012 Tai-hwa Liang, Sentelic Corporation.
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
@@ -55,6 +55,16 @@
 #define	FSP_BIT_FIX_HSCR	BIT(5)
 #define	FSP_BIT_DRAG_LOCK	BIT(6)
 
+#define	FSP_REG_SWC1		(0x90)
+#define	FSP_BIT_SWC1_EN_ABS_1F	BIT(0)
+#define	FSP_BIT_SWC1_EN_GID	BIT(1)
+#define	FSP_BIT_SWC1_EN_ABS_2F	BIT(2)
+#define	FSP_BIT_SWC1_EN_FUP_OUT	BIT(3)
+#define	FSP_BIT_SWC1_EN_ABS_CON	BIT(4)
+#define	FSP_BIT_SWC1_GST_GRP0	BIT(5)
+#define	FSP_BIT_SWC1_GST_GRP1	BIT(6)
+#define	FSP_BIT_SWC1_BX_COMPAT	BIT(7)
+
 /* Finger-sensing Pad packet formating related definitions */
 
 /* absolute packet type */
@@ -64,12 +74,32 @@
 #define	FSP_PKT_TYPE_NORMAL_OPC	(0x03)
 #define	FSP_PKT_TYPE_SHIFT	(6)
 
+/* bit definitions for the first byte of report packet */
+#define	FSP_PB0_LBTN		BIT(0)
+#define	FSP_PB0_RBTN		BIT(1)
+#define	FSP_PB0_MBTN		BIT(2)
+#define	FSP_PB0_MFMC_FGR2	FSP_PB0_MBTN
+#define	FSP_PB0_MUST_SET	BIT(3)
+#define	FSP_PB0_PHY_BTN		BIT(4)
+#define	FSP_PB0_MFMC		BIT(5)
+
+/* hardware revisions */
+#define	FSP_VER_STL3888_A4	(0xC1)
+#define	FSP_VER_STL3888_B0	(0xD0)
+#define	FSP_VER_STL3888_B1	(0xD1)
+#define	FSP_VER_STL3888_B2	(0xD2)
+#define	FSP_VER_STL3888_C0	(0xE0)
+#define	FSP_VER_STL3888_C1	(0xE1)
+#define	FSP_VER_STL3888_D0	(0xE2)
+#define	FSP_VER_STL3888_D1	(0xE3)
+#define	FSP_VER_STL3888_E0	(0xE4)
+
 #ifdef __KERNEL__
 
 struct fsp_data {
 	unsigned char	ver;		/* hardware version */
 	unsigned char	rev;		/* hardware revison */
-	unsigned char	buttons;	/* Number of buttons */
+	unsigned int	buttons;	/* Number of buttons */
 	unsigned int	flags;
 #define	FSPDRV_FLAG_EN_OPC	(0x001)	/* enable on-pad clicking */
 
@@ -78,6 +108,7 @@ struct fsp_data {
 
 	unsigned char	last_reg;	/* Last register we requested read from */
 	unsigned char	last_val;
+	unsigned int	last_mt_fgr;	/* Last seen finger(multitouch) */
 };
 
 #ifdef CONFIG_MOUSE_PS2_SENTELIC
diff --git a/drivers/input/serio/ams_delta_serio.c b/drivers/input/serio/ams_delta_serio.c
index bd5b10eeeb40..f5fbdf94de3b 100644
--- a/drivers/input/serio/ams_delta_serio.c
+++ b/drivers/input/serio/ams_delta_serio.c
@@ -184,7 +184,7 @@ module_init(ams_delta_serio_init);
 static void __exit ams_delta_serio_exit(void)
 {
 	serio_unregister_port(ams_delta_serio);
-	free_irq(OMAP_GPIO_IRQ(AMS_DELTA_GPIO_PIN_KEYBRD_CLK), 0);
+	free_irq(gpio_to_irq(AMS_DELTA_GPIO_PIN_KEYBRD_CLK), 0);
 	gpio_free_array(ams_delta_gpios,
 			ARRAY_SIZE(ams_delta_gpios));
 }
diff --git a/drivers/input/serio/hp_sdc.c b/drivers/input/serio/hp_sdc.c
index be3316073ae7..09a089996ded 100644
--- a/drivers/input/serio/hp_sdc.c
+++ b/drivers/input/serio/hp_sdc.c
@@ -71,7 +71,6 @@
 #include <linux/slab.h>
 #include <linux/hil.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 /* Machine-specific abstraction */
 
diff --git a/drivers/input/serio/maceps2.c b/drivers/input/serio/maceps2.c
index 558200e96d0f..61da763b1209 100644
--- a/drivers/input/serio/maceps2.c
+++ b/drivers/input/serio/maceps2.c
@@ -21,7 +21,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/ip32/mace.h>
 #include <asm/ip32/ip32_ints.h>
 
diff --git a/drivers/input/serio/rpckbd.c b/drivers/input/serio/rpckbd.c
index 8b44ddc8041c..2af5df6a8fba 100644
--- a/drivers/input/serio/rpckbd.c
+++ b/drivers/input/serio/rpckbd.c
@@ -36,16 +36,19 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 
-#include <asm/irq.h>
 #include <mach/hardware.h>
 #include <asm/hardware/iomd.h>
-#include <asm/system.h>
 
 MODULE_AUTHOR("Vojtech Pavlik, Russell King");
 MODULE_DESCRIPTION("Acorn RiscPC PS/2 keyboard controller driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:kart");
 
+struct rpckbd_data {
+	int tx_irq;
+	int rx_irq;
+};
+
 static int rpckbd_write(struct serio *port, unsigned char val)
 {
 	while (!(iomd_readb(IOMD_KCTRL) & (1 << 7)))
@@ -78,19 +81,21 @@ static irqreturn_t rpckbd_tx(int irq, void *dev_id)
 
 static int rpckbd_open(struct serio *port)
 {
+	struct rpckbd_data *rpckbd = port->port_data;
+
 	/* Reset the keyboard state machine. */
 	iomd_writeb(0, IOMD_KCTRL);
 	iomd_writeb(8, IOMD_KCTRL);
 	iomd_readb(IOMD_KARTRX);
 
-	if (request_irq(IRQ_KEYBOARDRX, rpckbd_rx, 0, "rpckbd", port) != 0) {
+	if (request_irq(rpckbd->rx_irq, rpckbd_rx, 0, "rpckbd", port) != 0) {
 		printk(KERN_ERR "rpckbd.c: Could not allocate keyboard receive IRQ\n");
 		return -EBUSY;
 	}
 
-	if (request_irq(IRQ_KEYBOARDTX, rpckbd_tx, 0, "rpckbd", port) != 0) {
+	if (request_irq(rpckbd->tx_irq, rpckbd_tx, 0, "rpckbd", port) != 0) {
 		printk(KERN_ERR "rpckbd.c: Could not allocate keyboard transmit IRQ\n");
-		free_irq(IRQ_KEYBOARDRX, port);
+		free_irq(rpckbd->rx_irq, port);
 		return -EBUSY;
 	}
 
@@ -99,8 +104,10 @@ static int rpckbd_open(struct serio *port)
 
 static void rpckbd_close(struct serio *port)
 {
-	free_irq(IRQ_KEYBOARDRX, port);
-	free_irq(IRQ_KEYBOARDTX, port);
+	struct rpckbd_data *rpckbd = port->port_data;
+
+	free_irq(rpckbd->rx_irq, port);
+	free_irq(rpckbd->tx_irq, port);
 }
 
 /*
@@ -109,17 +116,35 @@ static void rpckbd_close(struct serio *port)
  */
 static int __devinit rpckbd_probe(struct platform_device *dev)
 {
+	struct rpckbd_data *rpckbd;
 	struct serio *serio;
+	int tx_irq, rx_irq;
+
+	rx_irq = platform_get_irq(dev, 0);
+	if (rx_irq <= 0)
+		return rx_irq < 0 ? rx_irq : -ENXIO;
+
+	tx_irq = platform_get_irq(dev, 1);
+	if (tx_irq <= 0)
+		return tx_irq < 0 ? tx_irq : -ENXIO;
 
 	serio = kzalloc(sizeof(struct serio), GFP_KERNEL);
-	if (!serio)
+	rpckbd = kzalloc(sizeof(*rpckbd), GFP_KERNEL);
+	if (!serio || !rpckbd) {
+		kfree(rpckbd);
+		kfree(serio);
 		return -ENOMEM;
+	}
+
+	rpckbd->rx_irq = rx_irq;
+	rpckbd->tx_irq = tx_irq;
 
 	serio->id.type		= SERIO_8042;
 	serio->write		= rpckbd_write;
 	serio->open		= rpckbd_open;
 	serio->close		= rpckbd_close;
 	serio->dev.parent	= &dev->dev;
+	serio->port_data	= rpckbd;
 	strlcpy(serio->name, "RiscPC PS/2 kbd port", sizeof(serio->name));
 	strlcpy(serio->phys, "rpckbd/serio0", sizeof(serio->phys));
 
@@ -131,7 +156,11 @@ static int __devinit rpckbd_probe(struct platform_device *dev)
 static int __devexit rpckbd_remove(struct platform_device *dev)
 {
 	struct serio *serio = platform_get_drvdata(dev);
+	struct rpckbd_data *rpckbd = serio->port_data;
+
 	serio_unregister_port(serio);
+	kfree(rpckbd);
+
 	return 0;
 }
 
diff --git a/drivers/input/serio/sa1111ps2.c b/drivers/input/serio/sa1111ps2.c
index 44fc8b4bcd81..389766707534 100644
--- a/drivers/input/serio/sa1111ps2.c
+++ b/drivers/input/serio/sa1111ps2.c
@@ -20,10 +20,29 @@
 #include <linux/spinlock.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <asm/hardware/sa1111.h>
 
+#define PS2CR		0x0000
+#define PS2STAT		0x0004
+#define PS2DATA		0x0008
+#define PS2CLKDIV	0x000c
+#define PS2PRECNT	0x0010
+
+#define PS2CR_ENA	0x08
+#define PS2CR_FKD	0x02
+#define PS2CR_FKC	0x01
+
+#define PS2STAT_STP	0x0100
+#define PS2STAT_TXE	0x0080
+#define PS2STAT_TXB	0x0040
+#define PS2STAT_RXF	0x0020
+#define PS2STAT_RXB	0x0010
+#define PS2STAT_ENA	0x0008
+#define PS2STAT_RXP	0x0004
+#define PS2STAT_KBD	0x0002
+#define PS2STAT_KBC	0x0001
+
 struct ps2if {
 	struct serio		*io;
 	struct sa1111_dev	*dev;
@@ -45,22 +64,22 @@ static irqreturn_t ps2_rxint(int irq, void *dev_id)
 	struct ps2if *ps2if = dev_id;
 	unsigned int scancode, flag, status;
 
-	status = sa1111_readl(ps2if->base + SA1111_PS2STAT);
+	status = sa1111_readl(ps2if->base + PS2STAT);
 	while (status & PS2STAT_RXF) {
 		if (status & PS2STAT_STP)
-			sa1111_writel(PS2STAT_STP, ps2if->base + SA1111_PS2STAT);
+			sa1111_writel(PS2STAT_STP, ps2if->base + PS2STAT);
 
 		flag = (status & PS2STAT_STP ? SERIO_FRAME : 0) |
 		       (status & PS2STAT_RXP ? 0 : SERIO_PARITY);
 
-		scancode = sa1111_readl(ps2if->base + SA1111_PS2DATA) & 0xff;
+		scancode = sa1111_readl(ps2if->base + PS2DATA) & 0xff;
 
 		if (hweight8(scancode) & 1)
 			flag ^= SERIO_PARITY;
 
 		serio_interrupt(ps2if->io, scancode, flag);
 
-		status = sa1111_readl(ps2if->base + SA1111_PS2STAT);
+		status = sa1111_readl(ps2if->base + PS2STAT);
         }
 
         return IRQ_HANDLED;
@@ -75,12 +94,12 @@ static irqreturn_t ps2_txint(int irq, void *dev_id)
 	unsigned int status;
 
 	spin_lock(&ps2if->lock);
-	status = sa1111_readl(ps2if->base + SA1111_PS2STAT);
+	status = sa1111_readl(ps2if->base + PS2STAT);
 	if (ps2if->head == ps2if->tail) {
 		disable_irq_nosync(irq);
 		/* done */
 	} else if (status & PS2STAT_TXE) {
-		sa1111_writel(ps2if->buf[ps2if->tail], ps2if->base + SA1111_PS2DATA);
+		sa1111_writel(ps2if->buf[ps2if->tail], ps2if->base + PS2DATA);
 		ps2if->tail = (ps2if->tail + 1) & (sizeof(ps2if->buf) - 1);
 	}
 	spin_unlock(&ps2if->lock);
@@ -103,8 +122,8 @@ static int ps2_write(struct serio *io, unsigned char val)
 	/*
 	 * If the TX register is empty, we can go straight out.
 	 */
-	if (sa1111_readl(ps2if->base + SA1111_PS2STAT) & PS2STAT_TXE) {
-		sa1111_writel(val, ps2if->base + SA1111_PS2DATA);
+	if (sa1111_readl(ps2if->base + PS2STAT) & PS2STAT_TXE) {
+		sa1111_writel(val, ps2if->base + PS2DATA);
 	} else {
 		if (ps2if->head == ps2if->tail)
 			enable_irq(ps2if->dev->irq[1]);
@@ -124,13 +143,16 @@ static int ps2_open(struct serio *io)
 	struct ps2if *ps2if = io->port_data;
 	int ret;
 
-	sa1111_enable_device(ps2if->dev);
+	ret = sa1111_enable_device(ps2if->dev);
+	if (ret)
+		return ret;
 
 	ret = request_irq(ps2if->dev->irq[0], ps2_rxint, 0,
 			  SA1111_DRIVER_NAME(ps2if->dev), ps2if);
 	if (ret) {
 		printk(KERN_ERR "sa1111ps2: could not allocate IRQ%d: %d\n",
 			ps2if->dev->irq[0], ret);
+		sa1111_disable_device(ps2if->dev);
 		return ret;
 	}
 
@@ -140,6 +162,7 @@ static int ps2_open(struct serio *io)
 		printk(KERN_ERR "sa1111ps2: could not allocate IRQ%d: %d\n",
 			ps2if->dev->irq[1], ret);
 		free_irq(ps2if->dev->irq[0], ps2if);
+		sa1111_disable_device(ps2if->dev);
 		return ret;
 	}
 
@@ -147,7 +170,7 @@ static int ps2_open(struct serio *io)
 
 	enable_irq_wake(ps2if->dev->irq[0]);
 
-	sa1111_writel(PS2CR_ENA, ps2if->base + SA1111_PS2CR);
+	sa1111_writel(PS2CR_ENA, ps2if->base + PS2CR);
 	return 0;
 }
 
@@ -155,7 +178,7 @@ static void ps2_close(struct serio *io)
 {
 	struct ps2if *ps2if = io->port_data;
 
-	sa1111_writel(0, ps2if->base + SA1111_PS2CR);
+	sa1111_writel(0, ps2if->base + PS2CR);
 
 	disable_irq_wake(ps2if->dev->irq[0]);
 
@@ -175,7 +198,7 @@ static void __devinit ps2_clear_input(struct ps2if *ps2if)
 	int maxread = 100;
 
 	while (maxread--) {
-		if ((sa1111_readl(ps2if->base + SA1111_PS2DATA) & 0xff) == 0xff)
+		if ((sa1111_readl(ps2if->base + PS2DATA) & 0xff) == 0xff)
 			break;
 	}
 }
@@ -185,11 +208,11 @@ static unsigned int __devinit ps2_test_one(struct ps2if *ps2if,
 {
 	unsigned int val;
 
-	sa1111_writel(PS2CR_ENA | mask, ps2if->base + SA1111_PS2CR);
+	sa1111_writel(PS2CR_ENA | mask, ps2if->base + PS2CR);
 
 	udelay(2);
 
-	val = sa1111_readl(ps2if->base + SA1111_PS2STAT);
+	val = sa1111_readl(ps2if->base + PS2STAT);
 	return val & (PS2STAT_KBC | PS2STAT_KBD);
 }
 
@@ -220,7 +243,7 @@ static int __devinit ps2_test(struct ps2if *ps2if)
 		ret = -ENODEV;
 	}
 
-	sa1111_writel(0, ps2if->base + SA1111_PS2CR);
+	sa1111_writel(0, ps2if->base + PS2CR);
 
 	return ret;
 }
@@ -274,8 +297,8 @@ static int __devinit ps2_probe(struct sa1111_dev *dev)
 	sa1111_enable_device(ps2if->dev);
 
 	/* Incoming clock is 8MHz */
-	sa1111_writel(0, ps2if->base + SA1111_PS2CLKDIV);
-	sa1111_writel(127, ps2if->base + SA1111_PS2PRECNT);
+	sa1111_writel(0, ps2if->base + PS2CLKDIV);
+	sa1111_writel(127, ps2if->base + PS2PRECNT);
 
 	/*
 	 * Flush any pending input.
@@ -330,6 +353,7 @@ static int __devexit ps2_remove(struct sa1111_dev *dev)
 static struct sa1111_driver ps2_driver = {
 	.drv = {
 		.name	= "sa1111-ps2",
+		.owner	= THIS_MODULE,
 	},
 	.devid		= SA1111_DEVID_PS2,
 	.probe		= ps2_probe,
diff --git a/drivers/input/tablet/Kconfig b/drivers/input/tablet/Kconfig
index e53f4081a586..bed7cbf84cfd 100644
--- a/drivers/input/tablet/Kconfig
+++ b/drivers/input/tablet/Kconfig
@@ -76,6 +76,7 @@ config TABLET_USB_KBTAB
 config TABLET_USB_WACOM
 	tristate "Wacom Intuos/Graphire tablet support (USB)"
 	depends on USB_ARCH_HAS_HCD
+	select POWER_SUPPLY
 	select USB
 	select NEW_LEDS
 	select LEDS_CLASS
diff --git a/drivers/input/tablet/wacom.h b/drivers/input/tablet/wacom.h
index 0783864a7dc2..b4842d0e61dd 100644
--- a/drivers/input/tablet/wacom.h
+++ b/drivers/input/tablet/wacom.h
@@ -88,6 +88,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/init.h>
 #include <linux/usb/input.h>
+#include <linux/power_supply.h>
 #include <asm/unaligned.h>
 
 /*
@@ -112,6 +113,7 @@ struct wacom {
 	struct urb *irq;
 	struct wacom_wac wacom_wac;
 	struct mutex lock;
+	struct work_struct work;
 	bool open;
 	char phys[32];
 	struct wacom_led {
@@ -120,8 +122,15 @@ struct wacom {
 		u8 hlv;       /* status led brightness button pressed (1..127) */
 		u8 img_lum;   /* OLED matrix display brightness */
 	} led;
+	struct power_supply battery;
 };
 
+static inline void wacom_schedule_work(struct wacom_wac *wacom_wac)
+{
+	struct wacom *wacom = container_of(wacom_wac, struct wacom, wacom_wac);
+	schedule_work(&wacom->work);
+}
+
 extern const struct usb_device_id wacom_ids[];
 
 void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len);
diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c
index ca28066dc81e..0d269212931e 100644
--- a/drivers/input/tablet/wacom_sys.c
+++ b/drivers/input/tablet/wacom_sys.c
@@ -167,6 +167,19 @@ static void wacom_close(struct input_dev *dev)
 		usb_autopm_put_interface(wacom->intf);
 }
 
+/*
+ * Static values for max X/Y and resolution of Pen interface is stored in
+ * features. This mean physical size of active area can be computed.
+ * This is useful to do when Pen and Touch have same active area of tablet.
+ * This means for Touch device, we only need to find max X/Y value and we
+ * have enough information to compute resolution of touch.
+ */
+static void wacom_set_phy_from_res(struct wacom_features *features)
+{
+	features->x_phy = (features->x_max * 100) / features->x_resolution;
+	features->y_phy = (features->y_max * 100) / features->y_resolution;
+}
+
 static int wacom_parse_logical_collection(unsigned char *report,
 					  struct wacom_features *features)
 {
@@ -178,15 +191,7 @@ static int wacom_parse_logical_collection(unsigned char *report,
 		features->pktlen = WACOM_PKGLEN_BBTOUCH3;
 		features->device_type = BTN_TOOL_FINGER;
 
-		/*
-		 * Stylus and Touch have same active area
-		 * so compute physical size based on stylus
-		 * data before its overwritten.
-		 */
-		features->x_phy =
-			(features->x_max * 100) / features->x_resolution;
-		features->y_phy =
-			(features->y_max * 100) / features->y_resolution;
+		wacom_set_phy_from_res(features);
 
 		features->x_max = features->y_max =
 			get_unaligned_le16(&report[10]);
@@ -422,6 +427,7 @@ static int wacom_query_tablet_data(struct usb_interface *intf, struct wacom_feat
 						report_id, rep_data, 4, 1);
 		} while ((error < 0 || rep_data[1] != 4) && limit++ < WAC_MSG_RETRIES);
 	} else if (features->type != TABLETPC &&
+		   features->type != WIRELESS &&
 		   features->device_type == BTN_TOOL_PEN) {
 		do {
 			rep_data[0] = 2;
@@ -454,6 +460,21 @@ static int wacom_retrieve_hid_descriptor(struct usb_interface *intf,
 	features->pressure_fuzz = 0;
 	features->distance_fuzz = 0;
 
+	/*
+	 * The wireless device HID is basic and layout conflicts with
+	 * other tablets (monitor and touch interface can look like pen).
+	 * Skip the query for this type and modify defaults based on
+	 * interface number.
+	 */
+	if (features->type == WIRELESS) {
+		if (intf->cur_altsetting->desc.bInterfaceNumber == 0) {
+			features->device_type = 0;
+		} else if (intf->cur_altsetting->desc.bInterfaceNumber == 2) {
+			features->device_type = BTN_TOOL_DOUBLETAP;
+			features->pktlen = WACOM_PKGLEN_BBTOUCH3;
+		}
+	}
+
 	/* only Tablet PCs and Bamboo P&T need to retrieve the info */
 	if ((features->type != TABLETPC) && (features->type != TABLETPC2FG) &&
 	    (features->type != BAMBOO_PT))
@@ -822,6 +843,152 @@ static void wacom_destroy_leds(struct wacom *wacom)
 	}
 }
 
+static enum power_supply_property wacom_battery_props[] = {
+	POWER_SUPPLY_PROP_CAPACITY
+};
+
+static int wacom_battery_get_property(struct power_supply *psy,
+				      enum power_supply_property psp,
+				      union power_supply_propval *val)
+{
+	struct wacom *wacom = container_of(psy, struct wacom, battery);
+	int ret = 0;
+
+	switch (psp) {
+		case POWER_SUPPLY_PROP_CAPACITY:
+			val->intval =
+				wacom->wacom_wac.battery_capacity * 100 / 31;
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+	}
+
+	return ret;
+}
+
+static int wacom_initialize_battery(struct wacom *wacom)
+{
+	int error = 0;
+
+	if (wacom->wacom_wac.features.quirks & WACOM_QUIRK_MONITOR) {
+		wacom->battery.properties = wacom_battery_props;
+		wacom->battery.num_properties = ARRAY_SIZE(wacom_battery_props);
+		wacom->battery.get_property = wacom_battery_get_property;
+		wacom->battery.name = "wacom_battery";
+		wacom->battery.type = POWER_SUPPLY_TYPE_BATTERY;
+		wacom->battery.use_for_apm = 0;
+
+		error = power_supply_register(&wacom->usbdev->dev,
+					      &wacom->battery);
+	}
+
+	return error;
+}
+
+static void wacom_destroy_battery(struct wacom *wacom)
+{
+	if (wacom->wacom_wac.features.quirks & WACOM_QUIRK_MONITOR)
+		power_supply_unregister(&wacom->battery);
+}
+
+static int wacom_register_input(struct wacom *wacom)
+{
+	struct input_dev *input_dev;
+	struct usb_interface *intf = wacom->intf;
+	struct usb_device *dev = interface_to_usbdev(intf);
+	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
+	int error;
+
+	input_dev = input_allocate_device();
+	if (!input_dev)
+		return -ENOMEM;
+
+	input_dev->name = wacom_wac->name;
+	input_dev->dev.parent = &intf->dev;
+	input_dev->open = wacom_open;
+	input_dev->close = wacom_close;
+	usb_to_input_id(dev, &input_dev->id);
+	input_set_drvdata(input_dev, wacom);
+
+	wacom_wac->input = input_dev;
+	wacom_setup_input_capabilities(input_dev, wacom_wac);
+
+	error = input_register_device(input_dev);
+	if (error) {
+		input_free_device(input_dev);
+		wacom_wac->input = NULL;
+	}
+
+	return error;
+}
+
+static void wacom_wireless_work(struct work_struct *work)
+{
+	struct wacom *wacom = container_of(work, struct wacom, work);
+	struct usb_device *usbdev = wacom->usbdev;
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+
+	/*
+	 * Regardless if this is a disconnect or a new tablet,
+	 * remove any existing input devices.
+	 */
+
+	/* Stylus interface */
+	wacom = usb_get_intfdata(usbdev->config->interface[1]);
+	if (wacom->wacom_wac.input)
+		input_unregister_device(wacom->wacom_wac.input);
+	wacom->wacom_wac.input = 0;
+
+	/* Touch interface */
+	wacom = usb_get_intfdata(usbdev->config->interface[2]);
+	if (wacom->wacom_wac.input)
+		input_unregister_device(wacom->wacom_wac.input);
+	wacom->wacom_wac.input = 0;
+
+	if (wacom_wac->pid == 0) {
+		printk(KERN_INFO "wacom: wireless tablet disconnected\n");
+	} else {
+		const struct usb_device_id *id = wacom_ids;
+
+		printk(KERN_INFO
+		       "wacom: wireless tablet connected with PID %x\n",
+		       wacom_wac->pid);
+
+		while (id->match_flags) {
+			if (id->idVendor == USB_VENDOR_ID_WACOM &&
+			    id->idProduct == wacom_wac->pid)
+				break;
+			id++;
+		}
+
+		if (!id->match_flags) {
+			printk(KERN_INFO
+			       "wacom: ignorning unknown PID.\n");
+			return;
+		}
+
+		/* Stylus interface */
+		wacom = usb_get_intfdata(usbdev->config->interface[1]);
+		wacom_wac = &wacom->wacom_wac;
+		wacom_wac->features =
+			*((struct wacom_features *)id->driver_info);
+		wacom_wac->features.device_type = BTN_TOOL_PEN;
+		wacom_register_input(wacom);
+
+		/* Touch interface */
+		wacom = usb_get_intfdata(usbdev->config->interface[2]);
+		wacom_wac = &wacom->wacom_wac;
+		wacom_wac->features =
+			*((struct wacom_features *)id->driver_info);
+		wacom_wac->features.pktlen = WACOM_PKGLEN_BBTOUCH3;
+		wacom_wac->features.device_type = BTN_TOOL_FINGER;
+		wacom_set_phy_from_res(&wacom_wac->features);
+		wacom_wac->features.x_max = wacom_wac->features.y_max = 4096;
+		wacom_register_input(wacom);
+	}
+}
+
 static int wacom_probe(struct usb_interface *intf, const struct usb_device_id *id)
 {
 	struct usb_device *dev = interface_to_usbdev(intf);
@@ -829,18 +996,14 @@ static int wacom_probe(struct usb_interface *intf, const struct usb_device_id *i
 	struct wacom *wacom;
 	struct wacom_wac *wacom_wac;
 	struct wacom_features *features;
-	struct input_dev *input_dev;
 	int error;
 
 	if (!id->driver_info)
 		return -EINVAL;
 
 	wacom = kzalloc(sizeof(struct wacom), GFP_KERNEL);
-	input_dev = input_allocate_device();
-	if (!wacom || !input_dev) {
-		error = -ENOMEM;
-		goto fail1;
-	}
+	if (!wacom)
+		return -ENOMEM;
 
 	wacom_wac = &wacom->wacom_wac;
 	wacom_wac->features = *((struct wacom_features *)id->driver_info);
@@ -866,11 +1029,10 @@ static int wacom_probe(struct usb_interface *intf, const struct usb_device_id *i
 	wacom->usbdev = dev;
 	wacom->intf = intf;
 	mutex_init(&wacom->lock);
+	INIT_WORK(&wacom->work, wacom_wireless_work);
 	usb_make_path(dev, wacom->phys, sizeof(wacom->phys));
 	strlcat(wacom->phys, "/input0", sizeof(wacom->phys));
 
-	wacom_wac->input = input_dev;
-
 	endpoint = &intf->cur_altsetting->endpoint[0].desc;
 
 	/* Retrieve the physical and logical size for OEM devices */
@@ -894,15 +1056,6 @@ static int wacom_probe(struct usb_interface *intf, const struct usb_device_id *i
 			goto fail3;
 	}
 
-	input_dev->name = wacom_wac->name;
-	input_dev->dev.parent = &intf->dev;
-	input_dev->open = wacom_open;
-	input_dev->close = wacom_close;
-	usb_to_input_id(dev, &input_dev->id);
-	input_set_drvdata(input_dev, wacom);
-
-	wacom_setup_input_capabilities(input_dev, wacom_wac);
-
 	usb_fill_int_urb(wacom->irq, dev,
 			 usb_rcvintpipe(dev, endpoint->bEndpointAddress),
 			 wacom_wac->data, features->pktlen,
@@ -914,22 +1067,34 @@ static int wacom_probe(struct usb_interface *intf, const struct usb_device_id *i
 	if (error)
 		goto fail4;
 
-	error = input_register_device(input_dev);
+	error = wacom_initialize_battery(wacom);
 	if (error)
 		goto fail5;
 
+	if (!(features->quirks & WACOM_QUIRK_NO_INPUT)) {
+		error = wacom_register_input(wacom);
+		if (error)
+			goto fail6;
+	}
+
 	/* Note that if query fails it is not a hard failure */
 	wacom_query_tablet_data(intf, features);
 
 	usb_set_intfdata(intf, wacom);
+
+	if (features->quirks & WACOM_QUIRK_MONITOR) {
+		if (usb_submit_urb(wacom->irq, GFP_KERNEL))
+			goto fail5;
+	}
+
 	return 0;
 
+ fail6: wacom_destroy_battery(wacom);
  fail5: wacom_destroy_leds(wacom);
  fail4:	wacom_remove_shared_data(wacom_wac);
  fail3:	usb_free_urb(wacom->irq);
  fail2:	usb_free_coherent(dev, WACOM_PKGLEN_MAX, wacom_wac->data, wacom->data_dma);
- fail1:	input_free_device(input_dev);
-	kfree(wacom);
+ fail1:	kfree(wacom);
 	return error;
 }
 
@@ -940,7 +1105,10 @@ static void wacom_disconnect(struct usb_interface *intf)
 	usb_set_intfdata(intf, NULL);
 
 	usb_kill_urb(wacom->irq);
-	input_unregister_device(wacom->wacom_wac.input);
+	cancel_work_sync(&wacom->work);
+	if (wacom->wacom_wac.input)
+		input_unregister_device(wacom->wacom_wac.input);
+	wacom_destroy_battery(wacom);
 	wacom_destroy_leds(wacom);
 	usb_free_urb(wacom->irq);
 	usb_free_coherent(interface_to_usbdev(intf), WACOM_PKGLEN_MAX,
@@ -972,7 +1140,8 @@ static int wacom_resume(struct usb_interface *intf)
 	wacom_query_tablet_data(intf, features);
 	wacom_led_control(wacom);
 
-	if (wacom->open && usb_submit_urb(wacom->irq, GFP_NOIO) < 0)
+	if ((wacom->open || features->quirks & WACOM_QUIRK_MONITOR)
+	     && usb_submit_urb(wacom->irq, GFP_NOIO) < 0)
 		rv = -EIO;
 
 	mutex_unlock(&wacom->lock);
diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c
index 89a96427faa0..cecd35c8f0b3 100644
--- a/drivers/input/tablet/wacom_wac.c
+++ b/drivers/input/tablet/wacom_wac.c
@@ -1044,6 +1044,35 @@ static int wacom_bpt_irq(struct wacom_wac *wacom, size_t len)
 	return 0;
 }
 
+static int wacom_wireless_irq(struct wacom_wac *wacom, size_t len)
+{
+	unsigned char *data = wacom->data;
+	int connected;
+
+	if (len != WACOM_PKGLEN_WIRELESS || data[0] != 0x80)
+		return 0;
+
+	connected = data[1] & 0x01;
+	if (connected) {
+		int pid, battery;
+
+		pid = get_unaligned_be16(&data[6]);
+		battery = data[5] & 0x3f;
+		if (wacom->pid != pid) {
+			wacom->pid = pid;
+			wacom_schedule_work(wacom);
+		}
+		wacom->battery_capacity = battery;
+	} else if (wacom->pid != 0) {
+		/* disconnected while previously connected */
+		wacom->pid = 0;
+		wacom_schedule_work(wacom);
+		wacom->battery_capacity = 0;
+	}
+
+	return 0;
+}
+
 void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 {
 	bool sync;
@@ -1094,6 +1123,10 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 		sync = wacom_bpt_irq(wacom_wac, len);
 		break;
 
+	case WIRELESS:
+		sync = wacom_wireless_irq(wacom_wac, len);
+		break;
+
 	default:
 		sync = false;
 		break;
@@ -1155,7 +1188,7 @@ void wacom_setup_device_quirks(struct wacom_features *features)
 
 	/* these device have multiple inputs */
 	if (features->type == TABLETPC || features->type == TABLETPC2FG ||
-	    features->type == BAMBOO_PT)
+	    features->type == BAMBOO_PT || features->type == WIRELESS)
 		features->quirks |= WACOM_QUIRK_MULTI_INPUT;
 
 	/* quirk for bamboo touch with 2 low res touches */
@@ -1167,6 +1200,16 @@ void wacom_setup_device_quirks(struct wacom_features *features)
 		features->y_fuzz <<= 5;
 		features->quirks |= WACOM_QUIRK_BBTOUCH_LOWRES;
 	}
+
+	if (features->type == WIRELESS) {
+
+		/* monitor never has input and pen/touch have delayed create */
+		features->quirks |= WACOM_QUIRK_NO_INPUT;
+
+		/* must be monitor interface if no device_type set */
+		if (!features->device_type)
+			features->quirks |= WACOM_QUIRK_MONITOR;
+	}
 }
 
 static unsigned int wacom_calculate_touch_res(unsigned int logical_max,
@@ -1640,6 +1683,9 @@ static const struct wacom_features wacom_features_0xEC =
 static const struct wacom_features wacom_features_0x47 =
 	{ "Wacom Intuos2 6x8",    WACOM_PKGLEN_INTUOS,    20320, 16240, 1023,
 	  31, INTUOS, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x84 =
+	{ "Wacom Wireless Receiver", WACOM_PKGLEN_WIRELESS, 0, 0, 0,
+	  0, WIRELESS, 0, 0 };
 static const struct wacom_features wacom_features_0xD0 =
 	{ "Wacom Bamboo 2FG",     WACOM_PKGLEN_BBFUN,     14720,  9200, 1023,
 	  31, BAMBOO_PT, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
@@ -1766,6 +1812,7 @@ const struct usb_device_id wacom_ids[] = {
 	{ USB_DEVICE_DETAILED(0xCE, USB_CLASS_HID,
 			      USB_INTERFACE_SUBCLASS_BOOT,
 			      USB_INTERFACE_PROTOCOL_MOUSE) },
+	{ USB_DEVICE_WACOM(0x84) },
 	{ USB_DEVICE_WACOM(0xD0) },
 	{ USB_DEVICE_WACOM(0xD1) },
 	{ USB_DEVICE_WACOM(0xD2) },
diff --git a/drivers/input/tablet/wacom_wac.h b/drivers/input/tablet/wacom_wac.h
index 4f0ba21b0196..ba5a334e54d6 100644
--- a/drivers/input/tablet/wacom_wac.h
+++ b/drivers/input/tablet/wacom_wac.h
@@ -24,6 +24,7 @@
 #define WACOM_PKGLEN_BBTOUCH	20
 #define WACOM_PKGLEN_BBTOUCH3	64
 #define WACOM_PKGLEN_BBPEN	10
+#define WACOM_PKGLEN_WIRELESS	32
 
 /* device IDs */
 #define STYLUS_DEVICE_ID	0x02
@@ -45,6 +46,8 @@
 /* device quirks */
 #define WACOM_QUIRK_MULTI_INPUT		0x0001
 #define WACOM_QUIRK_BBTOUCH_LOWRES	0x0002
+#define WACOM_QUIRK_NO_INPUT		0x0004
+#define WACOM_QUIRK_MONITOR		0x0008
 
 enum {
 	PENPARTNER = 0,
@@ -54,6 +57,7 @@ enum {
 	PL,
 	DTU,
 	BAMBOO_PT,
+	WIRELESS,
 	INTUOS,
 	INTUOS3S,
 	INTUOS3,
@@ -107,6 +111,8 @@ struct wacom_wac {
 	struct wacom_features features;
 	struct wacom_shared *shared;
 	struct input_dev *input;
+	int pid;
+	int battery_capacity;
 };
 
 #endif
diff --git a/drivers/input/touchscreen/jornada720_ts.c b/drivers/input/touchscreen/jornada720_ts.c
index c3848ad2325b..d9be6eac99b1 100644
--- a/drivers/input/touchscreen/jornada720_ts.c
+++ b/drivers/input/touchscreen/jornada720_ts.c
@@ -22,6 +22,7 @@
 
 #include <mach/hardware.h>
 #include <mach/jornada720.h>
+#include <mach/irqs.h>
 
 MODULE_AUTHOR("Kristoffer Ericson <kristoffer.ericson@gmail.com>");
 MODULE_DESCRIPTION("HP Jornada 710/720/728 touchscreen driver");
diff --git a/drivers/input/touchscreen/mc13783_ts.c b/drivers/input/touchscreen/mc13783_ts.c
index ede02743eac1..48dc5b0d26f1 100644
--- a/drivers/input/touchscreen/mc13783_ts.c
+++ b/drivers/input/touchscreen/mc13783_ts.c
@@ -39,6 +39,7 @@ struct mc13783_ts_priv {
 	struct delayed_work work;
 	struct workqueue_struct *workq;
 	unsigned int sample[4];
+	struct mc13xxx_ts_platform_data *touch;
 };
 
 static irqreturn_t mc13783_ts_handler(int irq, void *data)
@@ -125,7 +126,9 @@ static void mc13783_ts_work(struct work_struct *work)
 	unsigned int channel = 12;
 
 	if (mc13xxx_adc_do_conversion(priv->mc13xxx,
-				mode, channel, priv->sample) == 0)
+				mode, channel,
+				priv->touch->ato, priv->touch->atox,
+				priv->sample) == 0)
 		mc13783_ts_report_sample(priv);
 }
 
@@ -179,6 +182,12 @@ static int __init mc13783_ts_probe(struct platform_device *pdev)
 	INIT_DELAYED_WORK(&priv->work, mc13783_ts_work);
 	priv->mc13xxx = dev_get_drvdata(pdev->dev.parent);
 	priv->idev = idev;
+	priv->touch = dev_get_platdata(&pdev->dev);
+	if (!priv->touch) {
+		dev_err(&pdev->dev, "missing platform data\n");
+		ret = -ENODEV;
+		goto err_free_mem;
+	}
 
 	/*
 	 * We need separate workqueue because mc13783_adc_do_conversion
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index ae2ec929e52f..a5bee8e2dfce 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -2707,7 +2707,8 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
  * The exported alloc_coherent function for dma_ops.
  */
 static void *alloc_coherent(struct device *dev, size_t size,
-			    dma_addr_t *dma_addr, gfp_t flag)
+			    dma_addr_t *dma_addr, gfp_t flag,
+			    struct dma_attrs *attrs)
 {
 	unsigned long flags;
 	void *virt_addr;
@@ -2765,7 +2766,8 @@ out_free:
  * The exported free_coherent function for dma_ops.
  */
 static void free_coherent(struct device *dev, size_t size,
-			  void *virt_addr, dma_addr_t dma_addr)
+			  void *virt_addr, dma_addr_t dma_addr,
+			  struct dma_attrs *attrs)
 {
 	unsigned long flags;
 	struct protection_domain *domain;
@@ -2846,8 +2848,8 @@ static void __init prealloc_protection_domains(void)
 }
 
 static struct dma_map_ops amd_iommu_dma_ops = {
-	.alloc_coherent = alloc_coherent,
-	.free_coherent = free_coherent,
+	.alloc = alloc_coherent,
+	.free = free_coherent,
 	.map_page = map_page,
 	.unmap_page = unmap_page,
 	.map_sg = map_sg,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 132f93b05154..f93d5ac8f81c 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2949,7 +2949,8 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 }
 
 static void *intel_alloc_coherent(struct device *hwdev, size_t size,
-				  dma_addr_t *dma_handle, gfp_t flags)
+				  dma_addr_t *dma_handle, gfp_t flags,
+				  struct dma_attrs *attrs)
 {
 	void *vaddr;
 	int order;
@@ -2981,7 +2982,7 @@ static void *intel_alloc_coherent(struct device *hwdev, size_t size,
 }
 
 static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
-				dma_addr_t dma_handle)
+				dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	int order;
 
@@ -3126,8 +3127,8 @@ static int intel_mapping_error(struct device *dev, dma_addr_t dma_addr)
 }
 
 struct dma_map_ops intel_dma_ops = {
-	.alloc_coherent = intel_alloc_coherent,
-	.free_coherent = intel_free_coherent,
+	.alloc = intel_alloc_coherent,
+	.free = intel_free_coherent,
 	.map_sg = intel_map_sg,
 	.unmap_sg = intel_unmap_sg,
 	.map_page = intel_map_page,
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index 103dbd92e256..f55fc5dfbadc 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -323,15 +323,9 @@ err_out:
 	return count;
 }
 
-static int debug_open_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 #define DEBUG_FOPS(name)						\
 	static const struct file_operations debug_##name##_fops = {	\
-		.open = debug_open_generic,				\
+		.open = simple_open,					\
 		.read = debug_read_##name,				\
 		.write = debug_write_##name,				\
 		.llseek = generic_file_llseek,				\
@@ -339,7 +333,7 @@ static int debug_open_generic(struct inode *inode, struct file *file)
 
 #define DEBUG_FOPS_RO(name)						\
 	static const struct file_operations debug_##name##_fops = {	\
-		.open = debug_open_generic,				\
+		.open = simple_open,					\
 		.read = debug_read_##name,				\
 		.llseek = generic_file_llseek,				\
 	};
diff --git a/drivers/isdn/hardware/avm/avm_cs.c b/drivers/isdn/hardware/avm/avm_cs.c
index 44b50cc645e6..c21353d8e915 100644
--- a/drivers/isdn/hardware/avm/avm_cs.c
+++ b/drivers/isdn/hardware/avm/avm_cs.c
@@ -18,7 +18,6 @@
 #include <linux/serial.h>
 #include <linux/major.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
diff --git a/drivers/isdn/hisax/avma1_cs.c b/drivers/isdn/hisax/avma1_cs.c
index 33e3c94887d8..c644557ae614 100644
--- a/drivers/isdn/hisax/avma1_cs.c
+++ b/drivers/isdn/hisax/avma1_cs.c
@@ -18,7 +18,6 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
diff --git a/drivers/isdn/hisax/elsa_cs.c b/drivers/isdn/hisax/elsa_cs.c
index fe254e74a850..a8c4d3fc9a6d 100644
--- a/drivers/isdn/hisax/elsa_cs.c
+++ b/drivers/isdn/hisax/elsa_cs.c
@@ -44,7 +44,6 @@
 #include <linux/timer.h>
 #include <linux/ioport.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
diff --git a/drivers/isdn/hisax/sedlbauer_cs.c b/drivers/isdn/hisax/sedlbauer_cs.c
index 68f50495d166..f0dfc0c976eb 100644
--- a/drivers/isdn/hisax/sedlbauer_cs.c
+++ b/drivers/isdn/hisax/sedlbauer_cs.c
@@ -44,7 +44,6 @@
 #include <linux/timer.h>
 #include <linux/ioport.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
diff --git a/drivers/isdn/hisax/teles_cs.c b/drivers/isdn/hisax/teles_cs.c
index bfe94284b0d5..4deac451807c 100644
--- a/drivers/isdn/hisax/teles_cs.c
+++ b/drivers/isdn/hisax/teles_cs.c
@@ -25,7 +25,6 @@
 #include <linux/timer.h>
 #include <linux/ioport.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
diff --git a/drivers/isdn/i4l/isdn_bsdcomp.c b/drivers/isdn/i4l/isdn_bsdcomp.c
index 7f3c54d40474..c59e8d2c0675 100644
--- a/drivers/isdn/i4l/isdn_bsdcomp.c
+++ b/drivers/isdn/i4l/isdn_bsdcomp.c
@@ -69,7 +69,6 @@
 #include <linux/signal.h>	/* used in new tty drivers */
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/byteorder.h>
 #include <asm/types.h>
 
diff --git a/drivers/isdn/pcbit/layer2.c b/drivers/isdn/pcbit/layer2.c
index 682911f81138..a18e639b40d7 100644
--- a/drivers/isdn/pcbit/layer2.c
+++ b/drivers/isdn/pcbit/layer2.c
@@ -36,7 +36,6 @@
 
 #include <linux/isdnif.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 
diff --git a/drivers/leds/leds-88pm860x.c b/drivers/leds/leds-88pm860x.c
index 4ca00624bd18..5b61aaf7ac0f 100644
--- a/drivers/leds/leds-88pm860x.c
+++ b/drivers/leds/leds-88pm860x.c
@@ -114,6 +114,27 @@ static inline int __blink_ctl_mask(int port)
 	return ret;
 }
 
+static int led_power_set(struct pm860x_chip *chip, int port, int on)
+{
+	int ret = -EINVAL;
+
+	switch (port) {
+	case PM8606_LED1_RED:
+	case PM8606_LED1_GREEN:
+	case PM8606_LED1_BLUE:
+		ret = on ? pm8606_osc_enable(chip, RGB1_ENABLE) :
+			pm8606_osc_disable(chip, RGB1_ENABLE);
+		break;
+	case PM8606_LED2_RED:
+	case PM8606_LED2_GREEN:
+	case PM8606_LED2_BLUE:
+		ret = on ? pm8606_osc_enable(chip, RGB2_ENABLE) :
+			pm8606_osc_disable(chip, RGB2_ENABLE);
+		break;
+	}
+	return ret;
+}
+
 static void pm860x_led_work(struct work_struct *work)
 {
 
@@ -126,6 +147,7 @@ static void pm860x_led_work(struct work_struct *work)
 	chip = led->chip;
 	mutex_lock(&led->lock);
 	if ((led->current_brightness == 0) && led->brightness) {
+		led_power_set(chip, led->port, 1);
 		if (led->iset) {
 			pm860x_set_bits(led->i2c, __led_off(led->port),
 					LED_CURRENT_MASK, led->iset);
@@ -149,6 +171,7 @@ static void pm860x_led_work(struct work_struct *work)
 					LED_CURRENT_MASK, 0);
 			mask = __blink_ctl_mask(led->port);
 			pm860x_set_bits(led->i2c, PM8606_WLED3B, mask, 0);
+			led_power_set(chip, led->port, 0);
 		}
 	}
 	led->current_brightness = led->brightness;
diff --git a/drivers/macintosh/macio-adb.c b/drivers/macintosh/macio-adb.c
index b6ef8f590764..87de8d9bcfad 100644
--- a/drivers/macintosh/macio-adb.c
+++ b/drivers/macintosh/macio-adb.c
@@ -14,7 +14,6 @@
 #include <asm/pgtable.h>
 #include <asm/hydra.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
 
diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c
index c60d025044ee..fc71723cbc48 100644
--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -29,7 +29,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 
 #undef DEBUG
diff --git a/drivers/macintosh/therm_pm72.c b/drivers/macintosh/therm_pm72.c
index 0ff92c208005..97cfc5ac9fd0 100644
--- a/drivers/macintosh/therm_pm72.c
+++ b/drivers/macintosh/therm_pm72.c
@@ -127,7 +127,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/macio.h>
 
diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c
index 46c4e95f10d6..3b4a157714b1 100644
--- a/drivers/macintosh/therm_windtunnel.c
+++ b/drivers/macintosh/therm_windtunnel.c
@@ -41,7 +41,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/macio.h>
 
diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c
index 971bc9582a5f..86511c570dd8 100644
--- a/drivers/macintosh/via-cuda.c
+++ b/drivers/macintosh/via-cuda.c
@@ -26,7 +26,6 @@
 #include <asm/mac_via.h>
 #endif
 #include <asm/io.h>
-#include <asm/system.h>
 #include <linux/init.h>
 
 static volatile unsigned char __iomem *via;
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index c9570fcf1cce..3725f088f17e 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -34,7 +34,6 @@
 #include <asm/macintosh.h>
 #include <asm/macints.h>
 #include <asm/mac_via.h>
-#include <asm/system.h>
 
 static volatile unsigned char *via;
 
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 6cccd60c594e..22b8ce4191cc 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -50,7 +50,6 @@
 #include <asm/machdep.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/irq.h>
 #include <asm/pmac_feature.h>
diff --git a/drivers/macintosh/via-pmu68k.c b/drivers/macintosh/via-pmu68k.c
index aeb30d07d5a2..a00ee41f0573 100644
--- a/drivers/macintosh/via-pmu68k.c
+++ b/drivers/macintosh/via-pmu68k.c
@@ -37,7 +37,6 @@
 #include <asm/mac_via.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/macintosh/windfarm_lm75_sensor.c b/drivers/macintosh/windfarm_lm75_sensor.c
index 647c6add2193..4d6a90a1372b 100644
--- a/drivers/macintosh/windfarm_lm75_sensor.c
+++ b/drivers/macintosh/windfarm_lm75_sensor.c
@@ -18,7 +18,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/pmac_low_i2c.h>
 
diff --git a/drivers/macintosh/windfarm_pm121.c b/drivers/macintosh/windfarm_pm121.c
index 30e6195e19d4..04067e073aa9 100644
--- a/drivers/macintosh/windfarm_pm121.c
+++ b/drivers/macintosh/windfarm_pm121.c
@@ -215,7 +215,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/smu.h>
 
diff --git a/drivers/macintosh/windfarm_pm81.c b/drivers/macintosh/windfarm_pm81.c
index 749d174b0dc6..fc13d0f2663b 100644
--- a/drivers/macintosh/windfarm_pm81.c
+++ b/drivers/macintosh/windfarm_pm81.c
@@ -107,7 +107,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/smu.h>
 
diff --git a/drivers/macintosh/windfarm_pm91.c b/drivers/macintosh/windfarm_pm91.c
index 344273235124..a9430ed4f36c 100644
--- a/drivers/macintosh/windfarm_pm91.c
+++ b/drivers/macintosh/windfarm_pm91.c
@@ -41,7 +41,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/smu.h>
 
diff --git a/drivers/macintosh/windfarm_smu_controls.c b/drivers/macintosh/windfarm_smu_controls.c
index 43137b421f92..3c2be5193fd5 100644
--- a/drivers/macintosh/windfarm_smu_controls.c
+++ b/drivers/macintosh/windfarm_smu_controls.c
@@ -18,7 +18,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/smu.h>
 
diff --git a/drivers/macintosh/windfarm_smu_sensors.c b/drivers/macintosh/windfarm_smu_sensors.c
index 3c193504bb80..1cc4e4953d89 100644
--- a/drivers/macintosh/windfarm_smu_sensors.c
+++ b/drivers/macintosh/windfarm_smu_sensors.c
@@ -18,7 +18,6 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 #include <asm/smu.h>
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index faa4741df6d3..10f122a3a856 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -277,8 +277,8 @@ config DM_MIRROR
          needed for live data migration tools such as 'pvmove'.
 
 config DM_RAID
-       tristate "RAID 1/4/5/6 target (EXPERIMENTAL)"
-       depends on BLK_DEV_DM && EXPERIMENTAL
+       tristate "RAID 1/4/5/6 target"
+       depends on BLK_DEV_DM
        select MD_RAID1
        select MD_RAID456
        select BLK_DEV_MD
@@ -359,8 +359,8 @@ config DM_DELAY
 	If unsure, say N.
 
 config DM_UEVENT
-	bool "DM uevents (EXPERIMENTAL)"
-	depends on BLK_DEV_DM && EXPERIMENTAL
+	bool "DM uevents"
+	depends on BLK_DEV_DM
 	---help---
 	Generate udev events for DM events.
 
@@ -370,4 +370,24 @@ config DM_FLAKEY
        ---help---
          A target that intermittently fails I/O for debugging purposes.
 
+config DM_VERITY
+	tristate "Verity target support (EXPERIMENTAL)"
+	depends on BLK_DEV_DM && EXPERIMENTAL
+	select CRYPTO
+	select CRYPTO_HASH
+	select DM_BUFIO
+	---help---
+	  This device-mapper target creates a read-only device that
+	  transparently validates the data on one underlying device against
+	  a pre-generated tree of cryptographic checksums stored on a second
+	  device.
+
+	  You'll need to activate the digests you're going to use in the
+	  cryptoapi configuration.
+
+	  To compile this code as a module, choose M here: the module will
+	  be called dm-verity.
+
+	  If unsure, say N.
+
 endif # MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 046860c7a166..8b2e0dffe82e 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -42,6 +42,7 @@ obj-$(CONFIG_DM_LOG_USERSPACE)	+= dm-log-userspace.o
 obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
 obj-$(CONFIG_DM_RAID)	+= dm-raid.o
 obj-$(CONFIG_DM_THIN_PROVISIONING)	+= dm-thin-pool.o
+obj-$(CONFIG_DM_VERITY)		+= dm-verity.o
 
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index b6e58c7b6df5..cc06a1e52423 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -578,7 +578,7 @@ static void write_endio(struct bio *bio, int error)
 	struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
 
 	b->write_error = error;
-	if (error) {
+	if (unlikely(error)) {
 		struct dm_bufio_client *c = b->c;
 		(void)cmpxchg(&c->async_write_error, 0, error);
 	}
@@ -697,13 +697,20 @@ static void __wait_for_free_buffer(struct dm_bufio_client *c)
 	dm_bufio_lock(c);
 }
 
+enum new_flag {
+	NF_FRESH = 0,
+	NF_READ = 1,
+	NF_GET = 2,
+	NF_PREFETCH = 3
+};
+
 /*
  * Allocate a new buffer. If the allocation is not possible, wait until
  * some other thread frees a buffer.
  *
  * May drop the lock and regain it.
  */
-static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client *c)
+static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client *c, enum new_flag nf)
 {
 	struct dm_buffer *b;
 
@@ -726,6 +733,9 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client
 				return b;
 		}
 
+		if (nf == NF_PREFETCH)
+			return NULL;
+
 		if (!list_empty(&c->reserved_buffers)) {
 			b = list_entry(c->reserved_buffers.next,
 				       struct dm_buffer, lru_list);
@@ -743,9 +753,12 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client
 	}
 }
 
-static struct dm_buffer *__alloc_buffer_wait(struct dm_bufio_client *c)
+static struct dm_buffer *__alloc_buffer_wait(struct dm_bufio_client *c, enum new_flag nf)
 {
-	struct dm_buffer *b = __alloc_buffer_wait_no_callback(c);
+	struct dm_buffer *b = __alloc_buffer_wait_no_callback(c, nf);
+
+	if (!b)
+		return NULL;
 
 	if (c->alloc_callback)
 		c->alloc_callback(b);
@@ -865,32 +878,23 @@ static struct dm_buffer *__find(struct dm_bufio_client *c, sector_t block)
  * Getting a buffer
  *--------------------------------------------------------------*/
 
-enum new_flag {
-	NF_FRESH = 0,
-	NF_READ = 1,
-	NF_GET = 2
-};
-
 static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block,
-				     enum new_flag nf, struct dm_buffer **bp,
-				     int *need_submit)
+				     enum new_flag nf, int *need_submit)
 {
 	struct dm_buffer *b, *new_b = NULL;
 
 	*need_submit = 0;
 
 	b = __find(c, block);
-	if (b) {
-		b->hold_count++;
-		__relink_lru(b, test_bit(B_DIRTY, &b->state) ||
-			     test_bit(B_WRITING, &b->state));
-		return b;
-	}
+	if (b)
+		goto found_buffer;
 
 	if (nf == NF_GET)
 		return NULL;
 
-	new_b = __alloc_buffer_wait(c);
+	new_b = __alloc_buffer_wait(c, nf);
+	if (!new_b)
+		return NULL;
 
 	/*
 	 * We've had a period where the mutex was unlocked, so need to
@@ -899,10 +903,7 @@ static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block,
 	b = __find(c, block);
 	if (b) {
 		__free_buffer_wake(new_b);
-		b->hold_count++;
-		__relink_lru(b, test_bit(B_DIRTY, &b->state) ||
-			     test_bit(B_WRITING, &b->state));
-		return b;
+		goto found_buffer;
 	}
 
 	__check_watermark(c);
@@ -922,6 +923,24 @@ static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block,
 	*need_submit = 1;
 
 	return b;
+
+found_buffer:
+	if (nf == NF_PREFETCH)
+		return NULL;
+	/*
+	 * Note: it is essential that we don't wait for the buffer to be
+	 * read if dm_bufio_get function is used. Both dm_bufio_get and
+	 * dm_bufio_prefetch can be used in the driver request routine.
+	 * If the user called both dm_bufio_prefetch and dm_bufio_get on
+	 * the same buffer, it would deadlock if we waited.
+	 */
+	if (nf == NF_GET && unlikely(test_bit(B_READING, &b->state)))
+		return NULL;
+
+	b->hold_count++;
+	__relink_lru(b, test_bit(B_DIRTY, &b->state) ||
+		     test_bit(B_WRITING, &b->state));
+	return b;
 }
 
 /*
@@ -956,10 +975,10 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 	struct dm_buffer *b;
 
 	dm_bufio_lock(c);
-	b = __bufio_new(c, block, nf, bp, &need_submit);
+	b = __bufio_new(c, block, nf, &need_submit);
 	dm_bufio_unlock(c);
 
-	if (!b || IS_ERR(b))
+	if (!b)
 		return b;
 
 	if (need_submit)
@@ -1005,13 +1024,47 @@ void *dm_bufio_new(struct dm_bufio_client *c, sector_t block,
 }
 EXPORT_SYMBOL_GPL(dm_bufio_new);
 
+void dm_bufio_prefetch(struct dm_bufio_client *c,
+		       sector_t block, unsigned n_blocks)
+{
+	struct blk_plug plug;
+
+	blk_start_plug(&plug);
+	dm_bufio_lock(c);
+
+	for (; n_blocks--; block++) {
+		int need_submit;
+		struct dm_buffer *b;
+		b = __bufio_new(c, block, NF_PREFETCH, &need_submit);
+		if (unlikely(b != NULL)) {
+			dm_bufio_unlock(c);
+
+			if (need_submit)
+				submit_io(b, READ, b->block, read_endio);
+			dm_bufio_release(b);
+
+			dm_bufio_cond_resched();
+
+			if (!n_blocks)
+				goto flush_plug;
+			dm_bufio_lock(c);
+		}
+
+	}
+
+	dm_bufio_unlock(c);
+
+flush_plug:
+	blk_finish_plug(&plug);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_prefetch);
+
 void dm_bufio_release(struct dm_buffer *b)
 {
 	struct dm_bufio_client *c = b->c;
 
 	dm_bufio_lock(c);
 
-	BUG_ON(test_bit(B_READING, &b->state));
 	BUG_ON(!b->hold_count);
 
 	b->hold_count--;
@@ -1024,6 +1077,7 @@ void dm_bufio_release(struct dm_buffer *b)
 		 * invalid buffer.
 		 */
 		if ((b->read_error || b->write_error) &&
+		    !test_bit(B_READING, &b->state) &&
 		    !test_bit(B_WRITING, &b->state) &&
 		    !test_bit(B_DIRTY, &b->state)) {
 			__unlink_buffer(b);
@@ -1041,6 +1095,8 @@ void dm_bufio_mark_buffer_dirty(struct dm_buffer *b)
 
 	dm_bufio_lock(c);
 
+	BUG_ON(test_bit(B_READING, &b->state));
+
 	if (!test_and_set_bit(B_DIRTY, &b->state))
 		__relink_lru(b, LIST_DIRTY);
 
diff --git a/drivers/md/dm-bufio.h b/drivers/md/dm-bufio.h
index 5c4c3a04e381..b142946a9e32 100644
--- a/drivers/md/dm-bufio.h
+++ b/drivers/md/dm-bufio.h
@@ -63,6 +63,14 @@ void *dm_bufio_new(struct dm_bufio_client *c, sector_t block,
 		   struct dm_buffer **bp);
 
 /*
+ * Prefetch the specified blocks to the cache.
+ * The function starts to read the blocks and returns without waiting for
+ * I/O to finish.
+ */
+void dm_bufio_prefetch(struct dm_bufio_client *c,
+		       sector_t block, unsigned n_blocks);
+
+/*
  * Release a reference obtained with dm_bufio_{read,get,new}. The data
  * pointer and dm_buffer pointer is no longer valid after this call.
  */
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index db6b51639cee..3f06df59fd82 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -176,7 +176,6 @@ struct crypt_config {
 
 #define MIN_IOS        16
 #define MIN_POOL_PAGES 32
-#define MIN_BIO_PAGES  8
 
 static struct kmem_cache *_crypt_io_pool;
 
@@ -848,12 +847,11 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size,
 		}
 
 		/*
-		 * if additional pages cannot be allocated without waiting,
-		 * return a partially allocated bio, the caller will then try
-		 * to allocate additional bios while submitting this partial bio
+		 * If additional pages cannot be allocated without waiting,
+		 * return a partially-allocated bio.  The caller will then try
+		 * to allocate more bios while submitting this partial bio.
 		 */
-		if (i == (MIN_BIO_PAGES - 1))
-			gfp_mask = (gfp_mask | __GFP_NOWARN) & ~__GFP_WAIT;
+		gfp_mask = (gfp_mask | __GFP_NOWARN) & ~__GFP_WAIT;
 
 		len = (size > PAGE_SIZE) ? PAGE_SIZE : size;
 
@@ -1046,16 +1044,14 @@ static void kcryptd_queue_io(struct dm_crypt_io *io)
 	queue_work(cc->io_queue, &io->work);
 }
 
-static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io,
-					  int error, int async)
+static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 {
 	struct bio *clone = io->ctx.bio_out;
 	struct crypt_config *cc = io->target->private;
 
-	if (unlikely(error < 0)) {
+	if (unlikely(io->error < 0)) {
 		crypt_free_buffer_pages(cc, clone);
 		bio_put(clone);
-		io->error = -EIO;
 		crypt_dec_pending(io);
 		return;
 	}
@@ -1106,12 +1102,16 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		sector += bio_sectors(clone);
 
 		crypt_inc_pending(io);
+
 		r = crypt_convert(cc, &io->ctx);
+		if (r < 0)
+			io->error = -EIO;
+
 		crypt_finished = atomic_dec_and_test(&io->ctx.pending);
 
 		/* Encryption was already finished, submit io now */
 		if (crypt_finished) {
-			kcryptd_crypt_write_io_submit(io, r, 0);
+			kcryptd_crypt_write_io_submit(io, 0);
 
 			/*
 			 * If there was an error, do not try next fragments.
@@ -1162,11 +1162,8 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	crypt_dec_pending(io);
 }
 
-static void kcryptd_crypt_read_done(struct dm_crypt_io *io, int error)
+static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
 {
-	if (unlikely(error < 0))
-		io->error = -EIO;
-
 	crypt_dec_pending(io);
 }
 
@@ -1181,9 +1178,11 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 			   io->sector);
 
 	r = crypt_convert(cc, &io->ctx);
+	if (r < 0)
+		io->error = -EIO;
 
 	if (atomic_dec_and_test(&io->ctx.pending))
-		kcryptd_crypt_read_done(io, r);
+		kcryptd_crypt_read_done(io);
 
 	crypt_dec_pending(io);
 }
@@ -1204,15 +1203,18 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
 	if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post)
 		error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq);
 
+	if (error < 0)
+		io->error = -EIO;
+
 	mempool_free(req_of_dmreq(cc, dmreq), cc->req_pool);
 
 	if (!atomic_dec_and_test(&ctx->pending))
 		return;
 
 	if (bio_data_dir(io->base_bio) == READ)
-		kcryptd_crypt_read_done(io, error);
+		kcryptd_crypt_read_done(io);
 	else
-		kcryptd_crypt_write_io_submit(io, error, 1);
+		kcryptd_crypt_write_io_submit(io, 1);
 }
 
 static void kcryptd_crypt(struct work_struct *work)
@@ -1413,6 +1415,7 @@ static int crypt_ctr_cipher(struct dm_target *ti,
 	char *tmp, *cipher, *chainmode, *ivmode, *ivopts, *keycount;
 	char *cipher_api = NULL;
 	int cpu, ret = -EINVAL;
+	char dummy;
 
 	/* Convert to crypto api definition? */
 	if (strchr(cipher_in, '(')) {
@@ -1434,7 +1437,7 @@ static int crypt_ctr_cipher(struct dm_target *ti,
 
 	if (!keycount)
 		cc->tfms_count = 1;
-	else if (sscanf(keycount, "%u", &cc->tfms_count) != 1 ||
+	else if (sscanf(keycount, "%u%c", &cc->tfms_count, &dummy) != 1 ||
 		 !is_power_of_2(cc->tfms_count)) {
 		ti->error = "Bad cipher key count specification";
 		return -EINVAL;
@@ -1579,6 +1582,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	int ret;
 	struct dm_arg_set as;
 	const char *opt_string;
+	char dummy;
 
 	static struct dm_arg _args[] = {
 		{0, 1, "Invalid number of feature args"},
@@ -1636,7 +1640,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	ret = -EINVAL;
-	if (sscanf(argv[2], "%llu", &tmpll) != 1) {
+	if (sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid iv_offset sector";
 		goto bad;
 	}
@@ -1647,7 +1651,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	if (sscanf(argv[4], "%llu", &tmpll) != 1) {
+	if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
 	}
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index f18375dcedd9..2dc22dddb2ae 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -131,6 +131,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct delay_c *dc;
 	unsigned long long tmpll;
+	char dummy;
 
 	if (argc != 3 && argc != 6) {
 		ti->error = "requires exactly 3 or 6 arguments";
@@ -145,13 +146,13 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	dc->reads = dc->writes = 0;
 
-	if (sscanf(argv[1], "%llu", &tmpll) != 1) {
+	if (sscanf(argv[1], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
 	}
 	dc->start_read = tmpll;
 
-	if (sscanf(argv[2], "%u", &dc->read_delay) != 1) {
+	if (sscanf(argv[2], "%u%c", &dc->read_delay, &dummy) != 1) {
 		ti->error = "Invalid delay";
 		goto bad;
 	}
@@ -166,13 +167,13 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (argc == 3)
 		goto out;
 
-	if (sscanf(argv[4], "%llu", &tmpll) != 1) {
+	if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid write device sector";
 		goto bad_dev_read;
 	}
 	dc->start_write = tmpll;
 
-	if (sscanf(argv[5], "%u", &dc->write_delay) != 1) {
+	if (sscanf(argv[5], "%u%c", &dc->write_delay, &dummy) != 1) {
 		ti->error = "Invalid write delay";
 		goto bad_dev_read;
 	}
diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c
index 042e71996569..aa70f7d43a1a 100644
--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -283,7 +283,7 @@ int dm_exception_store_init(void)
 	return 0;
 
 persistent_fail:
-	dm_persistent_snapshot_exit();
+	dm_transient_snapshot_exit();
 transient_fail:
 	return r;
 }
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index b280c433e4a0..ac49c01f1a44 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -160,6 +160,7 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	unsigned long long tmpll;
 	struct dm_arg_set as;
 	const char *devname;
+	char dummy;
 
 	as.argc = argc;
 	as.argv = argv;
@@ -178,7 +179,7 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	devname = dm_shift_arg(&as);
 
-	if (sscanf(dm_shift_arg(&as), "%llu", &tmpll) != 1) {
+	if (sscanf(dm_shift_arg(&as), "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
 	}
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 1ce84ed0b765..a1a3e6df17b8 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -880,6 +880,7 @@ static int dev_set_geometry(struct dm_ioctl *param, size_t param_size)
 	struct hd_geometry geometry;
 	unsigned long indata[4];
 	char *geostr = (char *) param + param->data_start;
+	char dummy;
 
 	md = find_device(param);
 	if (!md)
@@ -891,8 +892,8 @@ static int dev_set_geometry(struct dm_ioctl *param, size_t param_size)
 		goto out;
 	}
 
-	x = sscanf(geostr, "%lu %lu %lu %lu", indata,
-		   indata + 1, indata + 2, indata + 3);
+	x = sscanf(geostr, "%lu %lu %lu %lu%c", indata,
+		   indata + 1, indata + 2, indata + 3, &dummy);
 
 	if (x != 4) {
 		DMWARN("Unable to interpret geometry settings.");
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 9728839f844a..3639eeab6042 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -29,6 +29,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct linear_c *lc;
 	unsigned long long tmp;
+	char dummy;
 
 	if (argc != 2) {
 		ti->error = "Invalid argument count";
@@ -41,7 +42,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		return -ENOMEM;
 	}
 
-	if (sscanf(argv[1], "%llu", &tmp) != 1) {
+	if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1) {
 		ti->error = "dm-linear: Invalid device sector";
 		goto bad;
 	}
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 3b52bb72bd1f..65ebaebf502b 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -369,6 +369,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 	unsigned int region_count;
 	size_t bitset_size, buf_size;
 	int r;
+	char dummy;
 
 	if (argc < 1 || argc > 2) {
 		DMWARN("wrong number of arguments to dirty region log");
@@ -387,7 +388,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 		}
 	}
 
-	if (sscanf(argv[0], "%u", &region_size) != 1 ||
+	if (sscanf(argv[0], "%u%c", &region_size, &dummy) != 1 ||
 	    !_check_region_size(ti, region_size)) {
 		DMWARN("invalid region size %s", argv[0]);
 		return -EINVAL;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 801d92d237cf..922a3385eead 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -226,6 +226,27 @@ static void free_multipath(struct multipath *m)
 	kfree(m);
 }
 
+static int set_mapinfo(struct multipath *m, union map_info *info)
+{
+	struct dm_mpath_io *mpio;
+
+	mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC);
+	if (!mpio)
+		return -ENOMEM;
+
+	memset(mpio, 0, sizeof(*mpio));
+	info->ptr = mpio;
+
+	return 0;
+}
+
+static void clear_mapinfo(struct multipath *m, union map_info *info)
+{
+	struct dm_mpath_io *mpio = info->ptr;
+
+	info->ptr = NULL;
+	mempool_free(mpio, m->mpio_pool);
+}
 
 /*-----------------------------------------------
  * Path selection
@@ -341,13 +362,14 @@ static int __must_push_back(struct multipath *m)
 }
 
 static int map_io(struct multipath *m, struct request *clone,
-		  struct dm_mpath_io *mpio, unsigned was_queued)
+		  union map_info *map_context, unsigned was_queued)
 {
 	int r = DM_MAPIO_REMAPPED;
 	size_t nr_bytes = blk_rq_bytes(clone);
 	unsigned long flags;
 	struct pgpath *pgpath;
 	struct block_device *bdev;
+	struct dm_mpath_io *mpio = map_context->ptr;
 
 	spin_lock_irqsave(&m->lock, flags);
 
@@ -423,7 +445,6 @@ static void dispatch_queued_ios(struct multipath *m)
 {
 	int r;
 	unsigned long flags;
-	struct dm_mpath_io *mpio;
 	union map_info *info;
 	struct request *clone, *n;
 	LIST_HEAD(cl);
@@ -436,16 +457,15 @@ static void dispatch_queued_ios(struct multipath *m)
 		list_del_init(&clone->queuelist);
 
 		info = dm_get_rq_mapinfo(clone);
-		mpio = info->ptr;
 
-		r = map_io(m, clone, mpio, 1);
+		r = map_io(m, clone, info, 1);
 		if (r < 0) {
-			mempool_free(mpio, m->mpio_pool);
+			clear_mapinfo(m, info);
 			dm_kill_unmapped_request(clone, r);
 		} else if (r == DM_MAPIO_REMAPPED)
 			dm_dispatch_request(clone);
 		else if (r == DM_MAPIO_REQUEUE) {
-			mempool_free(mpio, m->mpio_pool);
+			clear_mapinfo(m, info);
 			dm_requeue_unmapped_request(clone);
 		}
 	}
@@ -908,20 +928,16 @@ static int multipath_map(struct dm_target *ti, struct request *clone,
 			 union map_info *map_context)
 {
 	int r;
-	struct dm_mpath_io *mpio;
 	struct multipath *m = (struct multipath *) ti->private;
 
-	mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC);
-	if (!mpio)
+	if (set_mapinfo(m, map_context) < 0)
 		/* ENOMEM, requeue */
 		return DM_MAPIO_REQUEUE;
-	memset(mpio, 0, sizeof(*mpio));
 
-	map_context->ptr = mpio;
 	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-	r = map_io(m, clone, mpio, 0);
+	r = map_io(m, clone, map_context, 0);
 	if (r < 0 || r == DM_MAPIO_REQUEUE)
-		mempool_free(mpio, m->mpio_pool);
+		clear_mapinfo(m, map_context);
 
 	return r;
 }
@@ -1054,8 +1070,9 @@ static int switch_pg_num(struct multipath *m, const char *pgstr)
 	struct priority_group *pg;
 	unsigned pgnum;
 	unsigned long flags;
+	char dummy;
 
-	if (!pgstr || (sscanf(pgstr, "%u", &pgnum) != 1) || !pgnum ||
+	if (!pgstr || (sscanf(pgstr, "%u%c", &pgnum, &dummy) != 1) || !pgnum ||
 	    (pgnum > m->nr_priority_groups)) {
 		DMWARN("invalid PG number supplied to switch_pg_num");
 		return -EINVAL;
@@ -1085,8 +1102,9 @@ static int bypass_pg_num(struct multipath *m, const char *pgstr, int bypassed)
 {
 	struct priority_group *pg;
 	unsigned pgnum;
+	char dummy;
 
-	if (!pgstr || (sscanf(pgstr, "%u", &pgnum) != 1) || !pgnum ||
+	if (!pgstr || (sscanf(pgstr, "%u%c", &pgnum, &dummy) != 1) || !pgnum ||
 	    (pgnum > m->nr_priority_groups)) {
 		DMWARN("invalid PG number supplied to bypass_pg");
 		return -EINVAL;
@@ -1261,13 +1279,15 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 	struct path_selector *ps;
 	int r;
 
+	BUG_ON(!mpio);
+
 	r  = do_end_io(m, clone, error, mpio);
 	if (pgpath) {
 		ps = &pgpath->pg->ps;
 		if (ps->type->end_io)
 			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
 	}
-	mempool_free(mpio, m->mpio_pool);
+	clear_mapinfo(m, map_context);
 
 	return r;
 }
diff --git a/drivers/md/dm-queue-length.c b/drivers/md/dm-queue-length.c
index 03a837aa5ce6..3941fae0de9f 100644
--- a/drivers/md/dm-queue-length.c
+++ b/drivers/md/dm-queue-length.c
@@ -112,6 +112,7 @@ static int ql_add_path(struct path_selector *ps, struct dm_path *path,
 	struct selector *s = ps->context;
 	struct path_info *pi;
 	unsigned repeat_count = QL_MIN_IO;
+	char dummy;
 
 	/*
 	 * Arguments: [<repeat_count>]
@@ -123,7 +124,7 @@ static int ql_add_path(struct path_selector *ps, struct dm_path *path,
 		return -EINVAL;
 	}
 
-	if ((argc == 1) && (sscanf(argv[0], "%u", &repeat_count) != 1)) {
+	if ((argc == 1) && (sscanf(argv[0], "%u%c", &repeat_count, &dummy) != 1)) {
 		*error = "queue-length ps: invalid repeat count";
 		return -EINVAL;
 	}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index c5a875d7b882..b0ba52459ed7 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -604,7 +604,9 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
 		return 0;
 
 	if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, 1)) {
-		DMERR("Failed to read device superblock");
+		DMERR("Failed to read superblock of device at position %d",
+		      rdev->raid_disk);
+		set_bit(Faulty, &rdev->flags);
 		return -EINVAL;
 	}
 
@@ -855,9 +857,25 @@ static int super_validate(struct mddev *mddev, struct md_rdev *rdev)
 static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 {
 	int ret;
+	unsigned redundancy = 0;
+	struct raid_dev *dev;
 	struct md_rdev *rdev, *freshest;
 	struct mddev *mddev = &rs->md;
 
+	switch (rs->raid_type->level) {
+	case 1:
+		redundancy = rs->md.raid_disks - 1;
+		break;
+	case 4:
+	case 5:
+	case 6:
+		redundancy = rs->raid_type->parity_devs;
+		break;
+	default:
+		ti->error = "Unknown RAID type";
+		return -EINVAL;
+	}
+
 	freshest = NULL;
 	rdev_for_each(rdev, mddev) {
 		if (!rdev->meta_bdev)
@@ -872,6 +890,37 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 		case 0:
 			break;
 		default:
+			dev = container_of(rdev, struct raid_dev, rdev);
+			if (redundancy--) {
+				if (dev->meta_dev)
+					dm_put_device(ti, dev->meta_dev);
+
+				dev->meta_dev = NULL;
+				rdev->meta_bdev = NULL;
+
+				if (rdev->sb_page)
+					put_page(rdev->sb_page);
+
+				rdev->sb_page = NULL;
+
+				rdev->sb_loaded = 0;
+
+				/*
+				 * We might be able to salvage the data device
+				 * even though the meta device has failed.  For
+				 * now, we behave as though '- -' had been
+				 * set for this device in the table.
+				 */
+				if (dev->data_dev)
+					dm_put_device(ti, dev->data_dev);
+
+				dev->data_dev = NULL;
+				rdev->bdev = NULL;
+
+				list_del(&rdev->same_set);
+
+				continue;
+			}
 			ti->error = "Failed to load superblock";
 			return ret;
 		}
@@ -1214,7 +1263,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 1, 0},
+	.version = {1, 2, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9bfd057be686..d039de8322f0 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -924,8 +924,9 @@ static int get_mirror(struct mirror_set *ms, struct dm_target *ti,
 		      unsigned int mirror, char **argv)
 {
 	unsigned long long offset;
+	char dummy;
 
-	if (sscanf(argv[1], "%llu", &offset) != 1) {
+	if (sscanf(argv[1], "%llu%c", &offset, &dummy) != 1) {
 		ti->error = "Invalid offset";
 		return -EINVAL;
 	}
@@ -953,13 +954,14 @@ static struct dm_dirty_log *create_dirty_log(struct dm_target *ti,
 {
 	unsigned param_count;
 	struct dm_dirty_log *dl;
+	char dummy;
 
 	if (argc < 2) {
 		ti->error = "Insufficient mirror log arguments";
 		return NULL;
 	}
 
-	if (sscanf(argv[1], "%u", &param_count) != 1) {
+	if (sscanf(argv[1], "%u%c", &param_count, &dummy) != 1) {
 		ti->error = "Invalid mirror log argument count";
 		return NULL;
 	}
@@ -986,13 +988,14 @@ static int parse_features(struct mirror_set *ms, unsigned argc, char **argv,
 {
 	unsigned num_features;
 	struct dm_target *ti = ms->ti;
+	char dummy;
 
 	*args_used = 0;
 
 	if (!argc)
 		return 0;
 
-	if (sscanf(argv[0], "%u", &num_features) != 1) {
+	if (sscanf(argv[0], "%u%c", &num_features, &dummy) != 1) {
 		ti->error = "Invalid number of features";
 		return -EINVAL;
 	}
@@ -1036,6 +1039,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	unsigned int nr_mirrors, m, args_used;
 	struct mirror_set *ms;
 	struct dm_dirty_log *dl;
+	char dummy;
 
 	dl = create_dirty_log(ti, argc, argv, &args_used);
 	if (!dl)
@@ -1044,7 +1048,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	argv += args_used;
 	argc -= args_used;
 
-	if (!argc || sscanf(argv[0], "%u", &nr_mirrors) != 1 ||
+	if (!argc || sscanf(argv[0], "%u%c", &nr_mirrors, &dummy) != 1 ||
 	    nr_mirrors < 2 || nr_mirrors > DM_KCOPYD_MAX_REGIONS + 1) {
 		ti->error = "Invalid number of mirrors";
 		dm_dirty_log_destroy(dl);
diff --git a/drivers/md/dm-round-robin.c b/drivers/md/dm-round-robin.c
index 27f1d423b76c..6ab1192cdd5f 100644
--- a/drivers/md/dm-round-robin.c
+++ b/drivers/md/dm-round-robin.c
@@ -114,6 +114,7 @@ static int rr_add_path(struct path_selector *ps, struct dm_path *path,
 	struct selector *s = (struct selector *) ps->context;
 	struct path_info *pi;
 	unsigned repeat_count = RR_MIN_IO;
+	char dummy;
 
 	if (argc > 1) {
 		*error = "round-robin ps: incorrect number of arguments";
@@ -121,7 +122,7 @@ static int rr_add_path(struct path_selector *ps, struct dm_path *path,
 	}
 
 	/* First path argument is number of I/Os before switching path */
-	if ((argc == 1) && (sscanf(argv[0], "%u", &repeat_count) != 1)) {
+	if ((argc == 1) && (sscanf(argv[0], "%u%c", &repeat_count, &dummy) != 1)) {
 		*error = "round-robin ps: invalid repeat count";
 		return -EINVAL;
 	}
diff --git a/drivers/md/dm-service-time.c b/drivers/md/dm-service-time.c
index 59883bd78214..9df8f6bd6418 100644
--- a/drivers/md/dm-service-time.c
+++ b/drivers/md/dm-service-time.c
@@ -110,6 +110,7 @@ static int st_add_path(struct path_selector *ps, struct dm_path *path,
 	struct path_info *pi;
 	unsigned repeat_count = ST_MIN_IO;
 	unsigned relative_throughput = 1;
+	char dummy;
 
 	/*
 	 * Arguments: [<repeat_count> [<relative_throughput>]]
@@ -128,13 +129,13 @@ static int st_add_path(struct path_selector *ps, struct dm_path *path,
 		return -EINVAL;
 	}
 
-	if (argc && (sscanf(argv[0], "%u", &repeat_count) != 1)) {
+	if (argc && (sscanf(argv[0], "%u%c", &repeat_count, &dummy) != 1)) {
 		*error = "service-time ps: invalid repeat count";
 		return -EINVAL;
 	}
 
 	if ((argc == 2) &&
-	    (sscanf(argv[1], "%u", &relative_throughput) != 1 ||
+	    (sscanf(argv[1], "%u%c", &relative_throughput, &dummy) != 1 ||
 	     relative_throughput > ST_MAX_RELATIVE_THROUGHPUT)) {
 		*error = "service-time ps: invalid relative_throughput value";
 		return -EINVAL;
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 3d80cf0c152d..35c94ff24ad5 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -75,8 +75,9 @@ static int get_stripe(struct dm_target *ti, struct stripe_c *sc,
 		      unsigned int stripe, char **argv)
 {
 	unsigned long long start;
+	char dummy;
 
-	if (sscanf(argv[1], "%llu", &start) != 1)
+	if (sscanf(argv[1], "%llu%c", &start, &dummy) != 1)
 		return -EINVAL;
 
 	if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 63cc54289aff..2e227fbf1622 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -268,8 +268,7 @@ void dm_table_destroy(struct dm_table *t)
 	vfree(t->highs);
 
 	/* free the device list */
-	if (t->devices.next != &t->devices)
-		free_devices(&t->devices);
+	free_devices(&t->devices);
 
 	dm_free_md_mempools(t->mempools);
 
@@ -464,10 +463,11 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 	struct dm_dev_internal *dd;
 	unsigned int major, minor;
 	struct dm_table *t = ti->table;
+	char dummy;
 
 	BUG_ON(!t);
 
-	if (sscanf(path, "%u:%u", &major, &minor) == 2) {
+	if (sscanf(path, "%u:%u%c", &major, &minor, &dummy) == 2) {
 		/* Extract the major/minor numbers */
 		dev = MKDEV(major, minor);
 		if (MAJOR(dev) != major || MINOR(dev) != minor)
@@ -842,9 +842,10 @@ static int validate_next_arg(struct dm_arg *arg, struct dm_arg_set *arg_set,
 			     unsigned *value, char **error, unsigned grouped)
 {
 	const char *arg_str = dm_shift_arg(arg_set);
+	char dummy;
 
 	if (!arg_str ||
-	    (sscanf(arg_str, "%u", value) != 1) ||
+	    (sscanf(arg_str, "%u%c", value, &dummy) != 1) ||
 	    (*value < arg->min) ||
 	    (*value > arg->max) ||
 	    (grouped && arg_set->argc < *value)) {
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 237571af77fd..737d38865b69 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -614,7 +614,7 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		goto out;
 
-	r = dm_sm_root_size(pmd->metadata_sm, &data_len);
+	r = dm_sm_root_size(pmd->data_sm, &data_len);
 	if (r < 0)
 		goto out;
 
@@ -713,6 +713,9 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
 	if (r)
 		goto bad;
 
+	if (bdev_size > THIN_METADATA_MAX_SECTORS)
+		bdev_size = THIN_METADATA_MAX_SECTORS;
+
 	disk_super = dm_block_data(sblock);
 	disk_super->magic = cpu_to_le64(THIN_SUPERBLOCK_MAGIC);
 	disk_super->version = cpu_to_le32(THIN_VERSION);
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 859c16896877..ed4725e67c96 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -11,6 +11,19 @@
 
 #define THIN_METADATA_BLOCK_SIZE 4096
 
+/*
+ * The metadata device is currently limited in size.
+ *
+ * We have one block of index, which can hold 255 index entries.  Each
+ * index entry contains allocation info about 16k metadata blocks.
+ */
+#define THIN_METADATA_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
+
+/*
+ * A metadata device larger than 16GB triggers a warning.
+ */
+#define THIN_METADATA_MAX_SECTORS_WARNING (16 * (1024 * 1024 * 1024 >> SECTOR_SHIFT))
+
 /*----------------------------------------------------------------*/
 
 struct dm_pool_metadata;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index c3087575fef0..213ae32a0fc4 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -23,6 +23,7 @@
 #define DEFERRED_SET_SIZE 64
 #define MAPPING_POOL_SIZE 1024
 #define PRISON_CELLS 1024
+#define COMMIT_PERIOD HZ
 
 /*
  * The block size of the device holding pool data must be
@@ -32,16 +33,6 @@
 #define DATA_DEV_BLOCK_SIZE_MAX_SECTORS (1024 * 1024 * 1024 >> SECTOR_SHIFT)
 
 /*
- * The metadata device is currently limited in size.  The limitation is
- * checked lower down in dm-space-map-metadata, but we also check it here
- * so we can fail early.
- *
- * We have one block of index, which can hold 255 index entries.  Each
- * index entry contains allocation info about 16k metadata blocks.
- */
-#define METADATA_DEV_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
-
-/*
  * Device id is restricted to 24 bits.
  */
 #define MAX_DEV_ID ((1 << 24) - 1)
@@ -72,7 +63,7 @@
  * missed out if the io covers the block. (schedule_copy).
  *
  * iv) insert the new mapping into the origin's btree
- * (process_prepared_mappings).  This act of inserting breaks some
+ * (process_prepared_mapping).  This act of inserting breaks some
  * sharing of btree nodes between the two devices.  Breaking sharing only
  * effects the btree of that specific device.  Btrees for the other
  * devices that share the block never change.  The btree for the origin
@@ -124,7 +115,7 @@ struct cell {
 	struct hlist_node list;
 	struct bio_prison *prison;
 	struct cell_key key;
-	unsigned count;
+	struct bio *holder;
 	struct bio_list bios;
 };
 
@@ -220,54 +211,59 @@ static struct cell *__search_bucket(struct hlist_head *bucket,
  * This may block if a new cell needs allocating.  You must ensure that
  * cells will be unlocked even if the calling thread is blocked.
  *
- * Returns the number of entries in the cell prior to the new addition
- * or < 0 on failure.
+ * Returns 1 if the cell was already held, 0 if @inmate is the new holder.
  */
 static int bio_detain(struct bio_prison *prison, struct cell_key *key,
 		      struct bio *inmate, struct cell **ref)
 {
-	int r;
+	int r = 1;
 	unsigned long flags;
 	uint32_t hash = hash_key(prison, key);
-	struct cell *uninitialized_var(cell), *cell2 = NULL;
+	struct cell *cell, *cell2;
 
 	BUG_ON(hash > prison->nr_buckets);
 
 	spin_lock_irqsave(&prison->lock, flags);
+
 	cell = __search_bucket(prison->cells + hash, key);
+	if (cell) {
+		bio_list_add(&cell->bios, inmate);
+		goto out;
+	}
 
-	if (!cell) {
-		/*
-		 * Allocate a new cell
-		 */
-		spin_unlock_irqrestore(&prison->lock, flags);
-		cell2 = mempool_alloc(prison->cell_pool, GFP_NOIO);
-		spin_lock_irqsave(&prison->lock, flags);
+	/*
+	 * Allocate a new cell
+	 */
+	spin_unlock_irqrestore(&prison->lock, flags);
+	cell2 = mempool_alloc(prison->cell_pool, GFP_NOIO);
+	spin_lock_irqsave(&prison->lock, flags);
 
-		/*
-		 * We've been unlocked, so we have to double check that
-		 * nobody else has inserted this cell in the meantime.
-		 */
-		cell = __search_bucket(prison->cells + hash, key);
+	/*
+	 * We've been unlocked, so we have to double check that
+	 * nobody else has inserted this cell in the meantime.
+	 */
+	cell = __search_bucket(prison->cells + hash, key);
+	if (cell) {
+		mempool_free(cell2, prison->cell_pool);
+		bio_list_add(&cell->bios, inmate);
+		goto out;
+	}
 
-		if (!cell) {
-			cell = cell2;
-			cell2 = NULL;
+	/*
+	 * Use new cell.
+	 */
+	cell = cell2;
 
-			cell->prison = prison;
-			memcpy(&cell->key, key, sizeof(cell->key));
-			cell->count = 0;
-			bio_list_init(&cell->bios);
-			hlist_add_head(&cell->list, prison->cells + hash);
-		}
-	}
+	cell->prison = prison;
+	memcpy(&cell->key, key, sizeof(cell->key));
+	cell->holder = inmate;
+	bio_list_init(&cell->bios);
+	hlist_add_head(&cell->list, prison->cells + hash);
 
-	r = cell->count++;
-	bio_list_add(&cell->bios, inmate);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	r = 0;
 
-	if (cell2)
-		mempool_free(cell2, prison->cell_pool);
+out:
+	spin_unlock_irqrestore(&prison->lock, flags);
 
 	*ref = cell;
 
@@ -283,8 +279,8 @@ static void __cell_release(struct cell *cell, struct bio_list *inmates)
 
 	hlist_del(&cell->list);
 
-	if (inmates)
-		bio_list_merge(inmates, &cell->bios);
+	bio_list_add(inmates, cell->holder);
+	bio_list_merge(inmates, &cell->bios);
 
 	mempool_free(cell, prison->cell_pool);
 }
@@ -305,22 +301,44 @@ static void cell_release(struct cell *cell, struct bio_list *bios)
  * bio may be in the cell.  This function releases the cell, and also does
  * a sanity check.
  */
+static void __cell_release_singleton(struct cell *cell, struct bio *bio)
+{
+	hlist_del(&cell->list);
+	BUG_ON(cell->holder != bio);
+	BUG_ON(!bio_list_empty(&cell->bios));
+}
+
 static void cell_release_singleton(struct cell *cell, struct bio *bio)
 {
-	struct bio_prison *prison = cell->prison;
-	struct bio_list bios;
-	struct bio *b;
 	unsigned long flags;
-
-	bio_list_init(&bios);
+	struct bio_prison *prison = cell->prison;
 
 	spin_lock_irqsave(&prison->lock, flags);
-	__cell_release(cell, &bios);
+	__cell_release_singleton(cell, bio);
 	spin_unlock_irqrestore(&prison->lock, flags);
+}
+
+/*
+ * Sometimes we don't want the holder, just the additional bios.
+ */
+static void __cell_release_no_holder(struct cell *cell, struct bio_list *inmates)
+{
+	struct bio_prison *prison = cell->prison;
+
+	hlist_del(&cell->list);
+	bio_list_merge(inmates, &cell->bios);
 
-	b = bio_list_pop(&bios);
-	BUG_ON(b != bio);
-	BUG_ON(!bio_list_empty(&bios));
+	mempool_free(cell, prison->cell_pool);
+}
+
+static void cell_release_no_holder(struct cell *cell, struct bio_list *inmates)
+{
+	unsigned long flags;
+	struct bio_prison *prison = cell->prison;
+
+	spin_lock_irqsave(&prison->lock, flags);
+	__cell_release_no_holder(cell, inmates);
+	spin_unlock_irqrestore(&prison->lock, flags);
 }
 
 static void cell_error(struct cell *cell)
@@ -471,6 +489,13 @@ static void build_virtual_key(struct dm_thin_device *td, dm_block_t b,
  * devices.
  */
 struct new_mapping;
+
+struct pool_features {
+	unsigned zero_new_blocks:1;
+	unsigned discard_enabled:1;
+	unsigned discard_passdown:1;
+};
+
 struct pool {
 	struct list_head list;
 	struct dm_target *ti;	/* Only set if a pool target is bound */
@@ -484,7 +509,7 @@ struct pool {
 	dm_block_t offset_mask;
 	dm_block_t low_water_blocks;
 
-	unsigned zero_new_blocks:1;
+	struct pool_features pf;
 	unsigned low_water_triggered:1;	/* A dm event has been sent */
 	unsigned no_free_space:1;	/* A -ENOSPC warning has been issued */
 
@@ -493,17 +518,21 @@ struct pool {
 
 	struct workqueue_struct *wq;
 	struct work_struct worker;
+	struct delayed_work waker;
 
 	unsigned ref_count;
+	unsigned long last_commit_jiffies;
 
 	spinlock_t lock;
 	struct bio_list deferred_bios;
 	struct bio_list deferred_flush_bios;
 	struct list_head prepared_mappings;
+	struct list_head prepared_discards;
 
 	struct bio_list retry_on_resume_list;
 
-	struct deferred_set ds;	/* FIXME: move to thin_c */
+	struct deferred_set shared_read_ds;
+	struct deferred_set all_io_ds;
 
 	struct new_mapping *next_mapping;
 	mempool_t *mapping_pool;
@@ -521,7 +550,7 @@ struct pool_c {
 	struct dm_target_callbacks callbacks;
 
 	dm_block_t low_water_blocks;
-	unsigned zero_new_blocks:1;
+	struct pool_features pf;
 };
 
 /*
@@ -529,6 +558,7 @@ struct pool_c {
  */
 struct thin_c {
 	struct dm_dev *pool_dev;
+	struct dm_dev *origin_dev;
 	dm_thin_id dev_id;
 
 	struct pool *pool;
@@ -597,6 +627,13 @@ static struct pool *__pool_table_lookup_metadata_dev(struct block_device *md_dev
 
 /*----------------------------------------------------------------*/
 
+struct endio_hook {
+	struct thin_c *tc;
+	struct deferred_entry *shared_read_entry;
+	struct deferred_entry *all_io_entry;
+	struct new_mapping *overwrite_mapping;
+};
+
 static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master)
 {
 	struct bio *bio;
@@ -607,7 +644,8 @@ static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master)
 	bio_list_init(master);
 
 	while ((bio = bio_list_pop(&bios))) {
-		if (dm_get_mapinfo(bio)->ptr == tc)
+		struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
+		if (h->tc == tc)
 			bio_endio(bio, DM_ENDIO_REQUEUE);
 		else
 			bio_list_add(master, bio);
@@ -646,14 +684,16 @@ static void remap(struct thin_c *tc, struct bio *bio, dm_block_t block)
 		(bio->bi_sector & pool->offset_mask);
 }
 
-static void remap_and_issue(struct thin_c *tc, struct bio *bio,
-			    dm_block_t block)
+static void remap_to_origin(struct thin_c *tc, struct bio *bio)
+{
+	bio->bi_bdev = tc->origin_dev->bdev;
+}
+
+static void issue(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
 	unsigned long flags;
 
-	remap(tc, bio, block);
-
 	/*
 	 * Batch together any FUA/FLUSH bios we find and then issue
 	 * a single commit for them in process_deferred_bios().
@@ -666,6 +706,19 @@ static void remap_and_issue(struct thin_c *tc, struct bio *bio,
 		generic_make_request(bio);
 }
 
+static void remap_to_origin_and_issue(struct thin_c *tc, struct bio *bio)
+{
+	remap_to_origin(tc, bio);
+	issue(tc, bio);
+}
+
+static void remap_and_issue(struct thin_c *tc, struct bio *bio,
+			    dm_block_t block)
+{
+	remap(tc, bio, block);
+	issue(tc, bio);
+}
+
 /*
  * wake_worker() is used when new work is queued and when pool_resume is
  * ready to continue deferred IO processing.
@@ -680,21 +733,17 @@ static void wake_worker(struct pool *pool)
 /*
  * Bio endio functions.
  */
-struct endio_hook {
-	struct thin_c *tc;
-	bio_end_io_t *saved_bi_end_io;
-	struct deferred_entry *entry;
-};
-
 struct new_mapping {
 	struct list_head list;
 
-	int prepared;
+	unsigned quiesced:1;
+	unsigned prepared:1;
+	unsigned pass_discard:1;
 
 	struct thin_c *tc;
 	dm_block_t virt_block;
 	dm_block_t data_block;
-	struct cell *cell;
+	struct cell *cell, *cell2;
 	int err;
 
 	/*
@@ -711,7 +760,7 @@ static void __maybe_add_mapping(struct new_mapping *m)
 {
 	struct pool *pool = m->tc->pool;
 
-	if (list_empty(&m->list) && m->prepared) {
+	if (m->quiesced && m->prepared) {
 		list_add(&m->list, &pool->prepared_mappings);
 		wake_worker(pool);
 	}
@@ -734,7 +783,8 @@ static void copy_complete(int read_err, unsigned long write_err, void *context)
 static void overwrite_endio(struct bio *bio, int err)
 {
 	unsigned long flags;
-	struct new_mapping *m = dm_get_mapinfo(bio)->ptr;
+	struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
+	struct new_mapping *m = h->overwrite_mapping;
 	struct pool *pool = m->tc->pool;
 
 	m->err = err;
@@ -745,31 +795,6 @@ static void overwrite_endio(struct bio *bio, int err)
 	spin_unlock_irqrestore(&pool->lock, flags);
 }
 
-static void shared_read_endio(struct bio *bio, int err)
-{
-	struct list_head mappings;
-	struct new_mapping *m, *tmp;
-	struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
-	unsigned long flags;
-	struct pool *pool = h->tc->pool;
-
-	bio->bi_end_io = h->saved_bi_end_io;
-	bio_endio(bio, err);
-
-	INIT_LIST_HEAD(&mappings);
-	ds_dec(h->entry, &mappings);
-
-	spin_lock_irqsave(&pool->lock, flags);
-	list_for_each_entry_safe(m, tmp, &mappings, list) {
-		list_del(&m->list);
-		INIT_LIST_HEAD(&m->list);
-		__maybe_add_mapping(m);
-	}
-	spin_unlock_irqrestore(&pool->lock, flags);
-
-	mempool_free(h, pool->endio_hook_pool);
-}
-
 /*----------------------------------------------------------------*/
 
 /*
@@ -800,21 +825,16 @@ static void cell_defer(struct thin_c *tc, struct cell *cell,
  * Same as cell_defer above, except it omits one particular detainee,
  * a write bio that covers the block and has already been processed.
  */
-static void cell_defer_except(struct thin_c *tc, struct cell *cell,
-			      struct bio *exception)
+static void cell_defer_except(struct thin_c *tc, struct cell *cell)
 {
 	struct bio_list bios;
-	struct bio *bio;
 	struct pool *pool = tc->pool;
 	unsigned long flags;
 
 	bio_list_init(&bios);
-	cell_release(cell, &bios);
 
 	spin_lock_irqsave(&pool->lock, flags);
-	while ((bio = bio_list_pop(&bios)))
-		if (bio != exception)
-			bio_list_add(&pool->deferred_bios, bio);
+	cell_release_no_holder(cell, &pool->deferred_bios);
 	spin_unlock_irqrestore(&pool->lock, flags);
 
 	wake_worker(pool);
@@ -854,7 +874,7 @@ static void process_prepared_mapping(struct new_mapping *m)
 	 * the bios in the cell.
 	 */
 	if (bio) {
-		cell_defer_except(tc, m->cell, bio);
+		cell_defer_except(tc, m->cell);
 		bio_endio(bio, 0);
 	} else
 		cell_defer(tc, m->cell, m->data_block);
@@ -863,7 +883,30 @@ static void process_prepared_mapping(struct new_mapping *m)
 	mempool_free(m, tc->pool->mapping_pool);
 }
 
-static void process_prepared_mappings(struct pool *pool)
+static void process_prepared_discard(struct new_mapping *m)
+{
+	int r;
+	struct thin_c *tc = m->tc;
+
+	r = dm_thin_remove_block(tc->td, m->virt_block);
+	if (r)
+		DMERR("dm_thin_remove_block() failed");
+
+	/*
+	 * Pass the discard down to the underlying device?
+	 */
+	if (m->pass_discard)
+		remap_and_issue(tc, m->bio, m->data_block);
+	else
+		bio_endio(m->bio, 0);
+
+	cell_defer_except(tc, m->cell);
+	cell_defer_except(tc, m->cell2);
+	mempool_free(m, tc->pool->mapping_pool);
+}
+
+static void process_prepared(struct pool *pool, struct list_head *head,
+			     void (*fn)(struct new_mapping *))
 {
 	unsigned long flags;
 	struct list_head maps;
@@ -871,21 +914,27 @@ static void process_prepared_mappings(struct pool *pool)
 
 	INIT_LIST_HEAD(&maps);
 	spin_lock_irqsave(&pool->lock, flags);
-	list_splice_init(&pool->prepared_mappings, &maps);
+	list_splice_init(head, &maps);
 	spin_unlock_irqrestore(&pool->lock, flags);
 
 	list_for_each_entry_safe(m, tmp, &maps, list)
-		process_prepared_mapping(m);
+		fn(m);
 }
 
 /*
  * Deferred bio jobs.
  */
-static int io_overwrites_block(struct pool *pool, struct bio *bio)
+static int io_overlaps_block(struct pool *pool, struct bio *bio)
 {
-	return ((bio_data_dir(bio) == WRITE) &&
-		!(bio->bi_sector & pool->offset_mask)) &&
+	return !(bio->bi_sector & pool->offset_mask) &&
 		(bio->bi_size == (pool->sectors_per_block << SECTOR_SHIFT));
+
+}
+
+static int io_overwrites_block(struct pool *pool, struct bio *bio)
+{
+	return (bio_data_dir(bio) == WRITE) &&
+		io_overlaps_block(pool, bio);
 }
 
 static void save_and_set_endio(struct bio *bio, bio_end_io_t **save,
@@ -917,7 +966,8 @@ static struct new_mapping *get_next_mapping(struct pool *pool)
 }
 
 static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
-			  dm_block_t data_origin, dm_block_t data_dest,
+			  struct dm_dev *origin, dm_block_t data_origin,
+			  dm_block_t data_dest,
 			  struct cell *cell, struct bio *bio)
 {
 	int r;
@@ -925,6 +975,7 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	struct new_mapping *m = get_next_mapping(pool);
 
 	INIT_LIST_HEAD(&m->list);
+	m->quiesced = 0;
 	m->prepared = 0;
 	m->tc = tc;
 	m->virt_block = virt_block;
@@ -933,7 +984,8 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	m->err = 0;
 	m->bio = NULL;
 
-	ds_add_work(&pool->ds, &m->list);
+	if (!ds_add_work(&pool->shared_read_ds, &m->list))
+		m->quiesced = 1;
 
 	/*
 	 * IO to pool_dev remaps to the pool target's data_dev.
@@ -942,14 +994,15 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	 * bio immediately. Otherwise we use kcopyd to clone the data first.
 	 */
 	if (io_overwrites_block(pool, bio)) {
+		struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
+		h->overwrite_mapping = m;
 		m->bio = bio;
 		save_and_set_endio(bio, &m->saved_bi_end_io, overwrite_endio);
-		dm_get_mapinfo(bio)->ptr = m;
 		remap_and_issue(tc, bio, data_dest);
 	} else {
 		struct dm_io_region from, to;
 
-		from.bdev = tc->pool_dev->bdev;
+		from.bdev = origin->bdev;
 		from.sector = data_origin * pool->sectors_per_block;
 		from.count = pool->sectors_per_block;
 
@@ -967,6 +1020,22 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	}
 }
 
+static void schedule_internal_copy(struct thin_c *tc, dm_block_t virt_block,
+				   dm_block_t data_origin, dm_block_t data_dest,
+				   struct cell *cell, struct bio *bio)
+{
+	schedule_copy(tc, virt_block, tc->pool_dev,
+		      data_origin, data_dest, cell, bio);
+}
+
+static void schedule_external_copy(struct thin_c *tc, dm_block_t virt_block,
+				   dm_block_t data_dest,
+				   struct cell *cell, struct bio *bio)
+{
+	schedule_copy(tc, virt_block, tc->origin_dev,
+		      virt_block, data_dest, cell, bio);
+}
+
 static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 			  dm_block_t data_block, struct cell *cell,
 			  struct bio *bio)
@@ -975,6 +1044,7 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 	struct new_mapping *m = get_next_mapping(pool);
 
 	INIT_LIST_HEAD(&m->list);
+	m->quiesced = 1;
 	m->prepared = 0;
 	m->tc = tc;
 	m->virt_block = virt_block;
@@ -988,13 +1058,14 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 	 * zeroing pre-existing data, we can issue the bio immediately.
 	 * Otherwise we use kcopyd to zero the data first.
 	 */
-	if (!pool->zero_new_blocks)
+	if (!pool->pf.zero_new_blocks)
 		process_prepared_mapping(m);
 
 	else if (io_overwrites_block(pool, bio)) {
+		struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
+		h->overwrite_mapping = m;
 		m->bio = bio;
 		save_and_set_endio(bio, &m->saved_bi_end_io, overwrite_endio);
-		dm_get_mapinfo(bio)->ptr = m;
 		remap_and_issue(tc, bio, data_block);
 
 	} else {
@@ -1081,7 +1152,8 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
  */
 static void retry_on_resume(struct bio *bio)
 {
-	struct thin_c *tc = dm_get_mapinfo(bio)->ptr;
+	struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
+	struct thin_c *tc = h->tc;
 	struct pool *pool = tc->pool;
 	unsigned long flags;
 
@@ -1102,6 +1174,86 @@ static void no_space(struct cell *cell)
 		retry_on_resume(bio);
 }
 
+static void process_discard(struct thin_c *tc, struct bio *bio)
+{
+	int r;
+	struct pool *pool = tc->pool;
+	struct cell *cell, *cell2;
+	struct cell_key key, key2;
+	dm_block_t block = get_bio_block(tc, bio);
+	struct dm_thin_lookup_result lookup_result;
+	struct new_mapping *m;
+
+	build_virtual_key(tc->td, block, &key);
+	if (bio_detain(tc->pool->prison, &key, bio, &cell))
+		return;
+
+	r = dm_thin_find_block(tc->td, block, 1, &lookup_result);
+	switch (r) {
+	case 0:
+		/*
+		 * Check nobody is fiddling with this pool block.  This can
+		 * happen if someone's in the process of breaking sharing
+		 * on this block.
+		 */
+		build_data_key(tc->td, lookup_result.block, &key2);
+		if (bio_detain(tc->pool->prison, &key2, bio, &cell2)) {
+			cell_release_singleton(cell, bio);
+			break;
+		}
+
+		if (io_overlaps_block(pool, bio)) {
+			/*
+			 * IO may still be going to the destination block.  We must
+			 * quiesce before we can do the removal.
+			 */
+			m = get_next_mapping(pool);
+			m->tc = tc;
+			m->pass_discard = (!lookup_result.shared) & pool->pf.discard_passdown;
+			m->virt_block = block;
+			m->data_block = lookup_result.block;
+			m->cell = cell;
+			m->cell2 = cell2;
+			m->err = 0;
+			m->bio = bio;
+
+			if (!ds_add_work(&pool->all_io_ds, &m->list)) {
+				list_add(&m->list, &pool->prepared_discards);
+				wake_worker(pool);
+			}
+		} else {
+			/*
+			 * This path is hit if people are ignoring
+			 * limits->discard_granularity.  It ignores any
+			 * part of the discard that is in a subsequent
+			 * block.
+			 */
+			sector_t offset = bio->bi_sector - (block << pool->block_shift);
+			unsigned remaining = (pool->sectors_per_block - offset) << 9;
+			bio->bi_size = min(bio->bi_size, remaining);
+
+			cell_release_singleton(cell, bio);
+			cell_release_singleton(cell2, bio);
+			remap_and_issue(tc, bio, lookup_result.block);
+		}
+		break;
+
+	case -ENODATA:
+		/*
+		 * It isn't provisioned, just forget it.
+		 */
+		cell_release_singleton(cell, bio);
+		bio_endio(bio, 0);
+		break;
+
+	default:
+		DMERR("discard: find block unexpectedly returned %d", r);
+		cell_release_singleton(cell, bio);
+		bio_io_error(bio);
+		break;
+	}
+}
+
 static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block,
 			  struct cell_key *key,
 			  struct dm_thin_lookup_result *lookup_result,
@@ -1113,8 +1265,8 @@ static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block,
 	r = alloc_data_block(tc, &data_block);
 	switch (r) {
 	case 0:
-		schedule_copy(tc, block, lookup_result->block,
-			      data_block, cell, bio);
+		schedule_internal_copy(tc, block, lookup_result->block,
+				       data_block, cell, bio);
 		break;
 
 	case -ENOSPC:
@@ -1147,13 +1299,9 @@ static void process_shared_bio(struct thin_c *tc, struct bio *bio,
 	if (bio_data_dir(bio) == WRITE)
 		break_sharing(tc, bio, block, &key, lookup_result, cell);
 	else {
-		struct endio_hook *h;
-		h = mempool_alloc(pool->endio_hook_pool, GFP_NOIO);
+		struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
 
-		h->tc = tc;
-		h->entry = ds_inc(&pool->ds);
-		save_and_set_endio(bio, &h->saved_bi_end_io, shared_read_endio);
-		dm_get_mapinfo(bio)->ptr = h;
+		h->shared_read_entry = ds_inc(&pool->shared_read_ds);
 
 		cell_release_singleton(cell, bio);
 		remap_and_issue(tc, bio, lookup_result->block);
@@ -1188,7 +1336,10 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block
 	r = alloc_data_block(tc, &data_block);
 	switch (r) {
 	case 0:
-		schedule_zero(tc, block, data_block, cell, bio);
+		if (tc->origin_dev)
+			schedule_external_copy(tc, block, data_block, cell, bio);
+		else
+			schedule_zero(tc, block, data_block, cell, bio);
 		break;
 
 	case -ENOSPC:
@@ -1239,16 +1390,27 @@ static void process_bio(struct thin_c *tc, struct bio *bio)
 		break;
 
 	case -ENODATA:
-		provision_block(tc, bio, block, cell);
+		if (bio_data_dir(bio) == READ && tc->origin_dev) {
+			cell_release_singleton(cell, bio);
+			remap_to_origin_and_issue(tc, bio);
+		} else
+			provision_block(tc, bio, block, cell);
 		break;
 
 	default:
 		DMERR("dm_thin_find_block() failed, error = %d", r);
+		cell_release_singleton(cell, bio);
 		bio_io_error(bio);
 		break;
 	}
 }
 
+static int need_commit_due_to_time(struct pool *pool)
+{
+	return jiffies < pool->last_commit_jiffies ||
+	       jiffies > pool->last_commit_jiffies + COMMIT_PERIOD;
+}
+
 static void process_deferred_bios(struct pool *pool)
 {
 	unsigned long flags;
@@ -1264,7 +1426,9 @@ static void process_deferred_bios(struct pool *pool)
 	spin_unlock_irqrestore(&pool->lock, flags);
 
 	while ((bio = bio_list_pop(&bios))) {
-		struct thin_c *tc = dm_get_mapinfo(bio)->ptr;
+		struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
+		struct thin_c *tc = h->tc;
+
 		/*
 		 * If we've got no free new_mapping structs, and processing
 		 * this bio might require one, we pause until there are some
@@ -1277,7 +1441,11 @@ static void process_deferred_bios(struct pool *pool)
 
 			break;
 		}
-		process_bio(tc, bio);
+
+		if (bio->bi_rw & REQ_DISCARD)
+			process_discard(tc, bio);
+		else
+			process_bio(tc, bio);
 	}
 
 	/*
@@ -1290,7 +1458,7 @@ static void process_deferred_bios(struct pool *pool)
 	bio_list_init(&pool->deferred_flush_bios);
 	spin_unlock_irqrestore(&pool->lock, flags);
 
-	if (bio_list_empty(&bios))
+	if (bio_list_empty(&bios) && !need_commit_due_to_time(pool))
 		return;
 
 	r = dm_pool_commit_metadata(pool->pmd);
@@ -1301,6 +1469,7 @@ static void process_deferred_bios(struct pool *pool)
 			bio_io_error(bio);
 		return;
 	}
+	pool->last_commit_jiffies = jiffies;
 
 	while ((bio = bio_list_pop(&bios)))
 		generic_make_request(bio);
@@ -1310,10 +1479,22 @@ static void do_worker(struct work_struct *ws)
 {
 	struct pool *pool = container_of(ws, struct pool, worker);
 
-	process_prepared_mappings(pool);
+	process_prepared(pool, &pool->prepared_mappings, process_prepared_mapping);
+	process_prepared(pool, &pool->prepared_discards, process_prepared_discard);
 	process_deferred_bios(pool);
 }
 
+/*
+ * We want to commit periodically so that not too much
+ * unwritten data builds up.
+ */
+static void do_waker(struct work_struct *ws)
+{
+	struct pool *pool = container_of(to_delayed_work(ws), struct pool, waker);
+	wake_worker(pool);
+	queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
+}
+
 /*----------------------------------------------------------------*/
 
 /*
@@ -1335,6 +1516,19 @@ static void thin_defer_bio(struct thin_c *tc, struct bio *bio)
 	wake_worker(pool);
 }
 
+static struct endio_hook *thin_hook_bio(struct thin_c *tc, struct bio *bio)
+{
+	struct pool *pool = tc->pool;
+	struct endio_hook *h = mempool_alloc(pool->endio_hook_pool, GFP_NOIO);
+
+	h->tc = tc;
+	h->shared_read_entry = NULL;
+	h->all_io_entry = bio->bi_rw & REQ_DISCARD ? NULL : ds_inc(&pool->all_io_ds);
+	h->overwrite_mapping = NULL;
+
+	return h;
+}
+
 /*
  * Non-blocking function called from the thin target's map function.
  */
@@ -1347,12 +1541,8 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio,
 	struct dm_thin_device *td = tc->td;
 	struct dm_thin_lookup_result result;
 
-	/*
-	 * Save the thin context for easy access from the deferred bio later.
-	 */
-	map_context->ptr = tc;
-
-	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+	map_context->ptr = thin_hook_bio(tc, bio);
+	if (bio->bi_rw & (REQ_DISCARD | REQ_FLUSH | REQ_FUA)) {
 		thin_defer_bio(tc, bio);
 		return DM_MAPIO_SUBMITTED;
 	}
@@ -1434,7 +1624,7 @@ static int bind_control_target(struct pool *pool, struct dm_target *ti)
 
 	pool->ti = ti;
 	pool->low_water_blocks = pt->low_water_blocks;
-	pool->zero_new_blocks = pt->zero_new_blocks;
+	pool->pf = pt->pf;
 
 	return 0;
 }
@@ -1448,6 +1638,14 @@ static void unbind_control_target(struct pool *pool, struct dm_target *ti)
 /*----------------------------------------------------------------
  * Pool creation
  *--------------------------------------------------------------*/
+/* Initialize pool features. */
+static void pool_features_init(struct pool_features *pf)
+{
+	pf->zero_new_blocks = 1;
+	pf->discard_enabled = 1;
+	pf->discard_passdown = 1;
+}
+
 static void __pool_destroy(struct pool *pool)
 {
 	__pool_table_remove(pool);
@@ -1495,7 +1693,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	pool->block_shift = ffs(block_size) - 1;
 	pool->offset_mask = block_size - 1;
 	pool->low_water_blocks = 0;
-	pool->zero_new_blocks = 1;
+	pool_features_init(&pool->pf);
 	pool->prison = prison_create(PRISON_CELLS);
 	if (!pool->prison) {
 		*error = "Error creating pool's bio prison";
@@ -1523,14 +1721,17 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	}
 
 	INIT_WORK(&pool->worker, do_worker);
+	INIT_DELAYED_WORK(&pool->waker, do_waker);
 	spin_lock_init(&pool->lock);
 	bio_list_init(&pool->deferred_bios);
 	bio_list_init(&pool->deferred_flush_bios);
 	INIT_LIST_HEAD(&pool->prepared_mappings);
+	INIT_LIST_HEAD(&pool->prepared_discards);
 	pool->low_water_triggered = 0;
 	pool->no_free_space = 0;
 	bio_list_init(&pool->retry_on_resume_list);
-	ds_init(&pool->ds);
+	ds_init(&pool->shared_read_ds);
+	ds_init(&pool->all_io_ds);
 
 	pool->next_mapping = NULL;
 	pool->mapping_pool =
@@ -1549,6 +1750,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 		goto bad_endio_hook_pool;
 	}
 	pool->ref_count = 1;
+	pool->last_commit_jiffies = jiffies;
 	pool->pool_md = pool_md;
 	pool->md_dev = metadata_dev;
 	__pool_table_insert(pool);
@@ -1588,7 +1790,8 @@ static void __pool_dec(struct pool *pool)
 
 static struct pool *__pool_find(struct mapped_device *pool_md,
 				struct block_device *metadata_dev,
-				unsigned long block_size, char **error)
+				unsigned long block_size, char **error,
+				int *created)
 {
 	struct pool *pool = __pool_table_lookup_metadata_dev(metadata_dev);
 
@@ -1604,8 +1807,10 @@ static struct pool *__pool_find(struct mapped_device *pool_md,
 				return ERR_PTR(-EINVAL);
 			__pool_inc(pool);
 
-		} else
+		} else {
 			pool = pool_create(pool_md, metadata_dev, block_size, error);
+			*created = 1;
+		}
 	}
 
 	return pool;
@@ -1629,10 +1834,6 @@ static void pool_dtr(struct dm_target *ti)
 	mutex_unlock(&dm_thin_pool_table.mutex);
 }
 
-struct pool_features {
-	unsigned zero_new_blocks:1;
-};
-
 static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf,
 			       struct dm_target *ti)
 {
@@ -1641,7 +1842,7 @@ static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf,
 	const char *arg_name;
 
 	static struct dm_arg _args[] = {
-		{0, 1, "Invalid number of pool feature arguments"},
+		{0, 3, "Invalid number of pool feature arguments"},
 	};
 
 	/*
@@ -1661,6 +1862,12 @@ static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf,
 		if (!strcasecmp(arg_name, "skip_block_zeroing")) {
 			pf->zero_new_blocks = 0;
 			continue;
+		} else if (!strcasecmp(arg_name, "ignore_discard")) {
+			pf->discard_enabled = 0;
+			continue;
+		} else if (!strcasecmp(arg_name, "no_discard_passdown")) {
+			pf->discard_passdown = 0;
+			continue;
 		}
 
 		ti->error = "Unrecognised pool feature requested";
@@ -1678,10 +1885,12 @@ static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf,
  *
  * Optional feature arguments are:
  *	     skip_block_zeroing: skips the zeroing of newly-provisioned blocks.
+ *	     ignore_discard: disable discard
+ *	     no_discard_passdown: don't pass discards down to the data device
  */
 static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 {
-	int r;
+	int r, pool_created = 0;
 	struct pool_c *pt;
 	struct pool *pool;
 	struct pool_features pf;
@@ -1691,6 +1900,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	dm_block_t low_water_blocks;
 	struct dm_dev *metadata_dev;
 	sector_t metadata_dev_size;
+	char b[BDEVNAME_SIZE];
 
 	/*
 	 * FIXME Remove validation from scope of lock.
@@ -1712,11 +1922,9 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	}
 
 	metadata_dev_size = i_size_read(metadata_dev->bdev->bd_inode) >> SECTOR_SHIFT;
-	if (metadata_dev_size > METADATA_DEV_MAX_SECTORS) {
-		ti->error = "Metadata device is too large";
-		r = -EINVAL;
-		goto out_metadata;
-	}
+	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING)
+		DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.",
+		       bdevname(metadata_dev->bdev, b), THIN_METADATA_MAX_SECTORS);
 
 	r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev);
 	if (r) {
@@ -1742,8 +1950,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	/*
 	 * Set default pool features.
 	 */
-	memset(&pf, 0, sizeof(pf));
-	pf.zero_new_blocks = 1;
+	pool_features_init(&pf);
 
 	dm_consume_args(&as, 4);
 	r = parse_pool_features(&as, &pf, ti);
@@ -1757,20 +1964,58 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	}
 
 	pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev,
-			   block_size, &ti->error);
+			   block_size, &ti->error, &pool_created);
 	if (IS_ERR(pool)) {
 		r = PTR_ERR(pool);
 		goto out_free_pt;
 	}
 
+	/*
+	 * 'pool_created' reflects whether this is the first table load.
+	 * Top level discard support is not allowed to be changed after
+	 * initial load.  This would require a pool reload to trigger thin
+	 * device changes.
+	 */
+	if (!pool_created && pf.discard_enabled != pool->pf.discard_enabled) {
+		ti->error = "Discard support cannot be disabled once enabled";
+		r = -EINVAL;
+		goto out_flags_changed;
+	}
+
+	/*
+	 * If discard_passdown was enabled verify that the data device
+	 * supports discards.  Disable discard_passdown if not; otherwise
+	 * -EOPNOTSUPP will be returned.
+	 */
+	if (pf.discard_passdown) {
+		struct request_queue *q = bdev_get_queue(data_dev->bdev);
+		if (!q || !blk_queue_discard(q)) {
+			DMWARN("Discard unsupported by data device: Disabling discard passdown.");
+			pf.discard_passdown = 0;
+		}
+	}
+
 	pt->pool = pool;
 	pt->ti = ti;
 	pt->metadata_dev = metadata_dev;
 	pt->data_dev = data_dev;
 	pt->low_water_blocks = low_water_blocks;
-	pt->zero_new_blocks = pf.zero_new_blocks;
+	pt->pf = pf;
 	ti->num_flush_requests = 1;
-	ti->num_discard_requests = 0;
+	/*
+	 * Only need to enable discards if the pool should pass
+	 * them down to the data device.  The thin device's discard
+	 * processing will cause mappings to be removed from the btree.
+	 */
+	if (pf.discard_enabled && pf.discard_passdown) {
+		ti->num_discard_requests = 1;
+		/*
+		 * Setting 'discards_supported' circumvents the normal
+		 * stacking of discard limits (this keeps the pool and
+		 * thin devices' discard limits consistent).
+		 */
+		ti->discards_supported = 1;
+	}
 	ti->private = pt;
 
 	pt->callbacks.congested_fn = pool_is_congested;
@@ -1780,6 +2025,8 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	return 0;
 
+out_flags_changed:
+	__pool_dec(pool);
 out_free_pt:
 	kfree(pt);
 out:
@@ -1878,7 +2125,7 @@ static void pool_resume(struct dm_target *ti)
 	__requeue_bios(pool);
 	spin_unlock_irqrestore(&pool->lock, flags);
 
-	wake_worker(pool);
+	do_waker(&pool->waker.work);
 }
 
 static void pool_postsuspend(struct dm_target *ti)
@@ -1887,6 +2134,7 @@ static void pool_postsuspend(struct dm_target *ti)
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
 
+	cancel_delayed_work(&pool->waker);
 	flush_workqueue(pool->wq);
 
 	r = dm_pool_commit_metadata(pool->pmd);
@@ -2067,7 +2315,7 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv)
 static int pool_status(struct dm_target *ti, status_type_t type,
 		       char *result, unsigned maxlen)
 {
-	int r;
+	int r, count;
 	unsigned sz = 0;
 	uint64_t transaction_id;
 	dm_block_t nr_free_blocks_data;
@@ -2130,10 +2378,19 @@ static int pool_status(struct dm_target *ti, status_type_t type,
 		       (unsigned long)pool->sectors_per_block,
 		       (unsigned long long)pt->low_water_blocks);
 
-		DMEMIT("%u ", !pool->zero_new_blocks);
+		count = !pool->pf.zero_new_blocks + !pool->pf.discard_enabled +
+			!pool->pf.discard_passdown;
+		DMEMIT("%u ", count);
 
-		if (!pool->zero_new_blocks)
+		if (!pool->pf.zero_new_blocks)
 			DMEMIT("skip_block_zeroing ");
+
+		if (!pool->pf.discard_enabled)
+			DMEMIT("ignore_discard ");
+
+		if (!pool->pf.discard_passdown)
+			DMEMIT("no_discard_passdown ");
+
 		break;
 	}
 
@@ -2162,6 +2419,21 @@ static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
 	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
 }
 
+static void set_discard_limits(struct pool *pool, struct queue_limits *limits)
+{
+	/*
+	 * FIXME: these limits may be incompatible with the pool's data device
+	 */
+	limits->max_discard_sectors = pool->sectors_per_block;
+
+	/*
+	 * This is just a hint, and not enforced.  We have to cope with
+	 * bios that overlap 2 blocks.
+	 */
+	limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
+	limits->discard_zeroes_data = pool->pf.zero_new_blocks;
+}
+
 static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct pool_c *pt = ti->private;
@@ -2169,13 +2441,15 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 	blk_limits_io_min(limits, 0);
 	blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT);
+	if (pool->pf.discard_enabled)
+		set_discard_limits(pool, limits);
 }
 
 static struct target_type pool_target = {
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 0, 0},
+	.version = {1, 1, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -2202,6 +2476,8 @@ static void thin_dtr(struct dm_target *ti)
 	__pool_dec(tc->pool);
 	dm_pool_close_thin_device(tc->td);
 	dm_put_device(ti, tc->pool_dev);
+	if (tc->origin_dev)
+		dm_put_device(ti, tc->origin_dev);
 	kfree(tc);
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
@@ -2210,21 +2486,25 @@ static void thin_dtr(struct dm_target *ti)
 /*
  * Thin target parameters:
  *
- * <pool_dev> <dev_id>
+ * <pool_dev> <dev_id> [origin_dev]
  *
  * pool_dev: the path to the pool (eg, /dev/mapper/my_pool)
  * dev_id: the internal device identifier
+ * origin_dev: a device external to the pool that should act as the origin
+ *
+ * If the pool device has discards disabled, they get disabled for the thin
+ * device as well.
  */
 static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 {
 	int r;
 	struct thin_c *tc;
-	struct dm_dev *pool_dev;
+	struct dm_dev *pool_dev, *origin_dev;
 	struct mapped_device *pool_md;
 
 	mutex_lock(&dm_thin_pool_table.mutex);
 
-	if (argc != 2) {
+	if (argc != 2 && argc != 3) {
 		ti->error = "Invalid argument count";
 		r = -EINVAL;
 		goto out_unlock;
@@ -2237,6 +2517,15 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto out_unlock;
 	}
 
+	if (argc == 3) {
+		r = dm_get_device(ti, argv[2], FMODE_READ, &origin_dev);
+		if (r) {
+			ti->error = "Error opening origin device";
+			goto bad_origin_dev;
+		}
+		tc->origin_dev = origin_dev;
+	}
+
 	r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &pool_dev);
 	if (r) {
 		ti->error = "Error opening pool device";
@@ -2273,8 +2562,12 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	ti->split_io = tc->pool->sectors_per_block;
 	ti->num_flush_requests = 1;
-	ti->num_discard_requests = 0;
-	ti->discards_supported = 0;
+
+	/* In case the pool supports discards, pass them on. */
+	if (tc->pool->pf.discard_enabled) {
+		ti->discards_supported = 1;
+		ti->num_discard_requests = 1;
+	}
 
 	dm_put(pool_md);
 
@@ -2289,6 +2582,9 @@ bad_pool_lookup:
 bad_common:
 	dm_put_device(ti, tc->pool_dev);
 bad_pool_dev:
+	if (tc->origin_dev)
+		dm_put_device(ti, tc->origin_dev);
+bad_origin_dev:
 	kfree(tc);
 out_unlock:
 	mutex_unlock(&dm_thin_pool_table.mutex);
@@ -2299,11 +2595,46 @@ out_unlock:
 static int thin_map(struct dm_target *ti, struct bio *bio,
 		    union map_info *map_context)
 {
-	bio->bi_sector -= ti->begin;
+	bio->bi_sector = dm_target_offset(ti, bio->bi_sector);
 
 	return thin_bio_map(ti, bio, map_context);
 }
 
+static int thin_endio(struct dm_target *ti,
+		      struct bio *bio, int err,
+		      union map_info *map_context)
+{
+	unsigned long flags;
+	struct endio_hook *h = map_context->ptr;
+	struct list_head work;
+	struct new_mapping *m, *tmp;
+	struct pool *pool = h->tc->pool;
+
+	if (h->shared_read_entry) {
+		INIT_LIST_HEAD(&work);
+		ds_dec(h->shared_read_entry, &work);
+
+		spin_lock_irqsave(&pool->lock, flags);
+		list_for_each_entry_safe(m, tmp, &work, list) {
+			list_del(&m->list);
+			m->quiesced = 1;
+			__maybe_add_mapping(m);
+		}
+		spin_unlock_irqrestore(&pool->lock, flags);
+	}
+
+	if (h->all_io_entry) {
+		INIT_LIST_HEAD(&work);
+		ds_dec(h->all_io_entry, &work);
+		list_for_each_entry_safe(m, tmp, &work, list)
+			list_add(&m->list, &pool->prepared_discards);
+	}
+
+	mempool_free(h, pool->endio_hook_pool);
+
+	return 0;
+}
+
 static void thin_postsuspend(struct dm_target *ti)
 {
 	if (dm_noflush_suspending(ti))
@@ -2347,6 +2678,8 @@ static int thin_status(struct dm_target *ti, status_type_t type,
 			DMEMIT("%s %lu",
 			       format_dev_t(buf, tc->pool_dev->bdev->bd_dev),
 			       (unsigned long) tc->dev_id);
+			if (tc->origin_dev)
+				DMEMIT(" %s", format_dev_t(buf, tc->origin_dev->bdev->bd_dev));
 			break;
 		}
 	}
@@ -2377,18 +2710,21 @@ static int thin_iterate_devices(struct dm_target *ti,
 static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct thin_c *tc = ti->private;
+	struct pool *pool = tc->pool;
 
 	blk_limits_io_min(limits, 0);
-	blk_limits_io_opt(limits, tc->pool->sectors_per_block << SECTOR_SHIFT);
+	blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT);
+	set_discard_limits(pool, limits);
 }
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 0, 0},
+	.version = {1, 1, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
 	.map = thin_map,
+	.end_io = thin_endio,
 	.postsuspend = thin_postsuspend,
 	.status = thin_status,
 	.iterate_devices = thin_iterate_devices,
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
new file mode 100644
index 000000000000..fa365d39b612
--- /dev/null
+++ b/drivers/md/dm-verity.c
@@ -0,0 +1,913 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ *
+ * Author: Mikulas Patocka <mpatocka@redhat.com>
+ *
+ * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors
+ *
+ * This file is released under the GPLv2.
+ *
+ * In the file "/sys/module/dm_verity/parameters/prefetch_cluster" you can set
+ * default prefetch value. Data are read in "prefetch_cluster" chunks from the
+ * hash device. Setting this greatly improves performance when data and hash
+ * are on the same disk on different partitions on devices with poor random
+ * access behavior.
+ */
+
+#include "dm-bufio.h"
+
+#include <linux/module.h>
+#include <linux/device-mapper.h>
+#include <crypto/hash.h>
+
+#define DM_MSG_PREFIX			"verity"
+
+#define DM_VERITY_IO_VEC_INLINE		16
+#define DM_VERITY_MEMPOOL_SIZE		4
+#define DM_VERITY_DEFAULT_PREFETCH_SIZE	262144
+
+#define DM_VERITY_MAX_LEVELS		63
+
+static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE;
+
+module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR);
+
+struct dm_verity {
+	struct dm_dev *data_dev;
+	struct dm_dev *hash_dev;
+	struct dm_target *ti;
+	struct dm_bufio_client *bufio;
+	char *alg_name;
+	struct crypto_shash *tfm;
+	u8 *root_digest;	/* digest of the root block */
+	u8 *salt;		/* salt: its size is salt_size */
+	unsigned salt_size;
+	sector_t data_start;	/* data offset in 512-byte sectors */
+	sector_t hash_start;	/* hash start in blocks */
+	sector_t data_blocks;	/* the number of data blocks */
+	sector_t hash_blocks;	/* the number of hash blocks */
+	unsigned char data_dev_block_bits;	/* log2(data blocksize) */
+	unsigned char hash_dev_block_bits;	/* log2(hash blocksize) */
+	unsigned char hash_per_block_bits;	/* log2(hashes in hash block) */
+	unsigned char levels;	/* the number of tree levels */
+	unsigned char version;
+	unsigned digest_size;	/* digest size for the current hash algorithm */
+	unsigned shash_descsize;/* the size of temporary space for crypto */
+	int hash_failed;	/* set to 1 if hash of any block failed */
+
+	mempool_t *io_mempool;	/* mempool of struct dm_verity_io */
+	mempool_t *vec_mempool;	/* mempool of bio vector */
+
+	struct workqueue_struct *verify_wq;
+
+	/* starting blocks for each tree level. 0 is the lowest level. */
+	sector_t hash_level_block[DM_VERITY_MAX_LEVELS];
+};
+
+struct dm_verity_io {
+	struct dm_verity *v;
+	struct bio *bio;
+
+	/* original values of bio->bi_end_io and bio->bi_private */
+	bio_end_io_t *orig_bi_end_io;
+	void *orig_bi_private;
+
+	sector_t block;
+	unsigned n_blocks;
+
+	/* saved bio vector */
+	struct bio_vec *io_vec;
+	unsigned io_vec_size;
+
+	struct work_struct work;
+
+	/* A space for short vectors; longer vectors are allocated separately. */
+	struct bio_vec io_vec_inline[DM_VERITY_IO_VEC_INLINE];
+
+	/*
+	 * Three variably-size fields follow this struct:
+	 *
+	 * u8 hash_desc[v->shash_descsize];
+	 * u8 real_digest[v->digest_size];
+	 * u8 want_digest[v->digest_size];
+	 *
+	 * To access them use: io_hash_desc(), io_real_digest() and io_want_digest().
+	 */
+};
+
+static struct shash_desc *io_hash_desc(struct dm_verity *v, struct dm_verity_io *io)
+{
+	return (struct shash_desc *)(io + 1);
+}
+
+static u8 *io_real_digest(struct dm_verity *v, struct dm_verity_io *io)
+{
+	return (u8 *)(io + 1) + v->shash_descsize;
+}
+
+static u8 *io_want_digest(struct dm_verity *v, struct dm_verity_io *io)
+{
+	return (u8 *)(io + 1) + v->shash_descsize + v->digest_size;
+}
+
+/*
+ * Auxiliary structure appended to each dm-bufio buffer. If the value
+ * hash_verified is nonzero, hash of the block has been verified.
+ *
+ * The variable hash_verified is set to 0 when allocating the buffer, then
+ * it can be changed to 1 and it is never reset to 0 again.
+ *
+ * There is no lock around this value, a race condition can at worst cause
+ * that multiple processes verify the hash of the same buffer simultaneously
+ * and write 1 to hash_verified simultaneously.
+ * This condition is harmless, so we don't need locking.
+ */
+struct buffer_aux {
+	int hash_verified;
+};
+
+/*
+ * Initialize struct buffer_aux for a freshly created buffer.
+ */
+static void dm_bufio_alloc_callback(struct dm_buffer *buf)
+{
+	struct buffer_aux *aux = dm_bufio_get_aux_data(buf);
+
+	aux->hash_verified = 0;
+}
+
+/*
+ * Translate input sector number to the sector number on the target device.
+ */
+static sector_t verity_map_sector(struct dm_verity *v, sector_t bi_sector)
+{
+	return v->data_start + dm_target_offset(v->ti, bi_sector);
+}
+
+/*
+ * Return hash position of a specified block at a specified tree level
+ * (0 is the lowest level).
+ * The lowest "hash_per_block_bits"-bits of the result denote hash position
+ * inside a hash block. The remaining bits denote location of the hash block.
+ */
+static sector_t verity_position_at_level(struct dm_verity *v, sector_t block,
+					 int level)
+{
+	return block >> (level * v->hash_per_block_bits);
+}
+
+static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level,
+				 sector_t *hash_block, unsigned *offset)
+{
+	sector_t position = verity_position_at_level(v, block, level);
+	unsigned idx;
+
+	*hash_block = v->hash_level_block[level] + (position >> v->hash_per_block_bits);
+
+	if (!offset)
+		return;
+
+	idx = position & ((1 << v->hash_per_block_bits) - 1);
+	if (!v->version)
+		*offset = idx * v->digest_size;
+	else
+		*offset = idx << (v->hash_dev_block_bits - v->hash_per_block_bits);
+}
+
+/*
+ * Verify hash of a metadata block pertaining to the specified data block
+ * ("block" argument) at a specified level ("level" argument).
+ *
+ * On successful return, io_want_digest(v, io) contains the hash value for
+ * a lower tree level or for the data block (if we're at the lowest leve).
+ *
+ * If "skip_unverified" is true, unverified buffer is skipped and 1 is returned.
+ * If "skip_unverified" is false, unverified buffer is hashed and verified
+ * against current value of io_want_digest(v, io).
+ */
+static int verity_verify_level(struct dm_verity_io *io, sector_t block,
+			       int level, bool skip_unverified)
+{
+	struct dm_verity *v = io->v;
+	struct dm_buffer *buf;
+	struct buffer_aux *aux;
+	u8 *data;
+	int r;
+	sector_t hash_block;
+	unsigned offset;
+
+	verity_hash_at_level(v, block, level, &hash_block, &offset);
+
+	data = dm_bufio_read(v->bufio, hash_block, &buf);
+	if (unlikely(IS_ERR(data)))
+		return PTR_ERR(data);
+
+	aux = dm_bufio_get_aux_data(buf);
+
+	if (!aux->hash_verified) {
+		struct shash_desc *desc;
+		u8 *result;
+
+		if (skip_unverified) {
+			r = 1;
+			goto release_ret_r;
+		}
+
+		desc = io_hash_desc(v, io);
+		desc->tfm = v->tfm;
+		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+		r = crypto_shash_init(desc);
+		if (r < 0) {
+			DMERR("crypto_shash_init failed: %d", r);
+			goto release_ret_r;
+		}
+
+		if (likely(v->version >= 1)) {
+			r = crypto_shash_update(desc, v->salt, v->salt_size);
+			if (r < 0) {
+				DMERR("crypto_shash_update failed: %d", r);
+				goto release_ret_r;
+			}
+		}
+
+		r = crypto_shash_update(desc, data, 1 << v->hash_dev_block_bits);
+		if (r < 0) {
+			DMERR("crypto_shash_update failed: %d", r);
+			goto release_ret_r;
+		}
+
+		if (!v->version) {
+			r = crypto_shash_update(desc, v->salt, v->salt_size);
+			if (r < 0) {
+				DMERR("crypto_shash_update failed: %d", r);
+				goto release_ret_r;
+			}
+		}
+
+		result = io_real_digest(v, io);
+		r = crypto_shash_final(desc, result);
+		if (r < 0) {
+			DMERR("crypto_shash_final failed: %d", r);
+			goto release_ret_r;
+		}
+		if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) {
+			DMERR_LIMIT("metadata block %llu is corrupted",
+				(unsigned long long)hash_block);
+			v->hash_failed = 1;
+			r = -EIO;
+			goto release_ret_r;
+		} else
+			aux->hash_verified = 1;
+	}
+
+	data += offset;
+
+	memcpy(io_want_digest(v, io), data, v->digest_size);
+
+	dm_bufio_release(buf);
+	return 0;
+
+release_ret_r:
+	dm_bufio_release(buf);
+
+	return r;
+}
+
+/*
+ * Verify one "dm_verity_io" structure.
+ */
+static int verity_verify_io(struct dm_verity_io *io)
+{
+	struct dm_verity *v = io->v;
+	unsigned b;
+	int i;
+	unsigned vector = 0, offset = 0;
+
+	for (b = 0; b < io->n_blocks; b++) {
+		struct shash_desc *desc;
+		u8 *result;
+		int r;
+		unsigned todo;
+
+		if (likely(v->levels)) {
+			/*
+			 * First, we try to get the requested hash for
+			 * the current block. If the hash block itself is
+			 * verified, zero is returned. If it isn't, this
+			 * function returns 0 and we fall back to whole
+			 * chain verification.
+			 */
+			int r = verity_verify_level(io, io->block + b, 0, true);
+			if (likely(!r))
+				goto test_block_hash;
+			if (r < 0)
+				return r;
+		}
+
+		memcpy(io_want_digest(v, io), v->root_digest, v->digest_size);
+
+		for (i = v->levels - 1; i >= 0; i--) {
+			int r = verity_verify_level(io, io->block + b, i, false);
+			if (unlikely(r))
+				return r;
+		}
+
+test_block_hash:
+		desc = io_hash_desc(v, io);
+		desc->tfm = v->tfm;
+		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+		r = crypto_shash_init(desc);
+		if (r < 0) {
+			DMERR("crypto_shash_init failed: %d", r);
+			return r;
+		}
+
+		if (likely(v->version >= 1)) {
+			r = crypto_shash_update(desc, v->salt, v->salt_size);
+			if (r < 0) {
+				DMERR("crypto_shash_update failed: %d", r);
+				return r;
+			}
+		}
+
+		todo = 1 << v->data_dev_block_bits;
+		do {
+			struct bio_vec *bv;
+			u8 *page;
+			unsigned len;
+
+			BUG_ON(vector >= io->io_vec_size);
+			bv = &io->io_vec[vector];
+			page = kmap_atomic(bv->bv_page);
+			len = bv->bv_len - offset;
+			if (likely(len >= todo))
+				len = todo;
+			r = crypto_shash_update(desc,
+					page + bv->bv_offset + offset, len);
+			kunmap_atomic(page);
+			if (r < 0) {
+				DMERR("crypto_shash_update failed: %d", r);
+				return r;
+			}
+			offset += len;
+			if (likely(offset == bv->bv_len)) {
+				offset = 0;
+				vector++;
+			}
+			todo -= len;
+		} while (todo);
+
+		if (!v->version) {
+			r = crypto_shash_update(desc, v->salt, v->salt_size);
+			if (r < 0) {
+				DMERR("crypto_shash_update failed: %d", r);
+				return r;
+			}
+		}
+
+		result = io_real_digest(v, io);
+		r = crypto_shash_final(desc, result);
+		if (r < 0) {
+			DMERR("crypto_shash_final failed: %d", r);
+			return r;
+		}
+		if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) {
+			DMERR_LIMIT("data block %llu is corrupted",
+				(unsigned long long)(io->block + b));
+			v->hash_failed = 1;
+			return -EIO;
+		}
+	}
+	BUG_ON(vector != io->io_vec_size);
+	BUG_ON(offset);
+
+	return 0;
+}
+
+/*
+ * End one "io" structure with a given error.
+ */
+static void verity_finish_io(struct dm_verity_io *io, int error)
+{
+	struct bio *bio = io->bio;
+	struct dm_verity *v = io->v;
+
+	bio->bi_end_io = io->orig_bi_end_io;
+	bio->bi_private = io->orig_bi_private;
+
+	if (io->io_vec != io->io_vec_inline)
+		mempool_free(io->io_vec, v->vec_mempool);
+
+	mempool_free(io, v->io_mempool);
+
+	bio_endio(bio, error);
+}
+
+static void verity_work(struct work_struct *w)
+{
+	struct dm_verity_io *io = container_of(w, struct dm_verity_io, work);
+
+	verity_finish_io(io, verity_verify_io(io));
+}
+
+static void verity_end_io(struct bio *bio, int error)
+{
+	struct dm_verity_io *io = bio->bi_private;
+
+	if (error) {
+		verity_finish_io(io, error);
+		return;
+	}
+
+	INIT_WORK(&io->work, verity_work);
+	queue_work(io->v->verify_wq, &io->work);
+}
+
+/*
+ * Prefetch buffers for the specified io.
+ * The root buffer is not prefetched, it is assumed that it will be cached
+ * all the time.
+ */
+static void verity_prefetch_io(struct dm_verity *v, struct dm_verity_io *io)
+{
+	int i;
+
+	for (i = v->levels - 2; i >= 0; i--) {
+		sector_t hash_block_start;
+		sector_t hash_block_end;
+		verity_hash_at_level(v, io->block, i, &hash_block_start, NULL);
+		verity_hash_at_level(v, io->block + io->n_blocks - 1, i, &hash_block_end, NULL);
+		if (!i) {
+			unsigned cluster = *(volatile unsigned *)&dm_verity_prefetch_cluster;
+
+			cluster >>= v->data_dev_block_bits;
+			if (unlikely(!cluster))
+				goto no_prefetch_cluster;
+
+			if (unlikely(cluster & (cluster - 1)))
+				cluster = 1 << (fls(cluster) - 1);
+
+			hash_block_start &= ~(sector_t)(cluster - 1);
+			hash_block_end |= cluster - 1;
+			if (unlikely(hash_block_end >= v->hash_blocks))
+				hash_block_end = v->hash_blocks - 1;
+		}
+no_prefetch_cluster:
+		dm_bufio_prefetch(v->bufio, hash_block_start,
+				  hash_block_end - hash_block_start + 1);
+	}
+}
+
+/*
+ * Bio map function. It allocates dm_verity_io structure and bio vector and
+ * fills them. Then it issues prefetches and the I/O.
+ */
+static int verity_map(struct dm_target *ti, struct bio *bio,
+		      union map_info *map_context)
+{
+	struct dm_verity *v = ti->private;
+	struct dm_verity_io *io;
+
+	bio->bi_bdev = v->data_dev->bdev;
+	bio->bi_sector = verity_map_sector(v, bio->bi_sector);
+
+	if (((unsigned)bio->bi_sector | bio_sectors(bio)) &
+	    ((1 << (v->data_dev_block_bits - SECTOR_SHIFT)) - 1)) {
+		DMERR_LIMIT("unaligned io");
+		return -EIO;
+	}
+
+	if ((bio->bi_sector + bio_sectors(bio)) >>
+	    (v->data_dev_block_bits - SECTOR_SHIFT) > v->data_blocks) {
+		DMERR_LIMIT("io out of range");
+		return -EIO;
+	}
+
+	if (bio_data_dir(bio) == WRITE)
+		return -EIO;
+
+	io = mempool_alloc(v->io_mempool, GFP_NOIO);
+	io->v = v;
+	io->bio = bio;
+	io->orig_bi_end_io = bio->bi_end_io;
+	io->orig_bi_private = bio->bi_private;
+	io->block = bio->bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT);
+	io->n_blocks = bio->bi_size >> v->data_dev_block_bits;
+
+	bio->bi_end_io = verity_end_io;
+	bio->bi_private = io;
+	io->io_vec_size = bio->bi_vcnt - bio->bi_idx;
+	if (io->io_vec_size < DM_VERITY_IO_VEC_INLINE)
+		io->io_vec = io->io_vec_inline;
+	else
+		io->io_vec = mempool_alloc(v->vec_mempool, GFP_NOIO);
+	memcpy(io->io_vec, bio_iovec(bio),
+	       io->io_vec_size * sizeof(struct bio_vec));
+
+	verity_prefetch_io(v, io);
+
+	generic_make_request(bio);
+
+	return DM_MAPIO_SUBMITTED;
+}
+
+/*
+ * Status: V (valid) or C (corruption found)
+ */
+static int verity_status(struct dm_target *ti, status_type_t type,
+			 char *result, unsigned maxlen)
+{
+	struct dm_verity *v = ti->private;
+	unsigned sz = 0;
+	unsigned x;
+
+	switch (type) {
+	case STATUSTYPE_INFO:
+		DMEMIT("%c", v->hash_failed ? 'C' : 'V');
+		break;
+	case STATUSTYPE_TABLE:
+		DMEMIT("%u %s %s %u %u %llu %llu %s ",
+			v->version,
+			v->data_dev->name,
+			v->hash_dev->name,
+			1 << v->data_dev_block_bits,
+			1 << v->hash_dev_block_bits,
+			(unsigned long long)v->data_blocks,
+			(unsigned long long)v->hash_start,
+			v->alg_name
+			);
+		for (x = 0; x < v->digest_size; x++)
+			DMEMIT("%02x", v->root_digest[x]);
+		DMEMIT(" ");
+		if (!v->salt_size)
+			DMEMIT("-");
+		else
+			for (x = 0; x < v->salt_size; x++)
+				DMEMIT("%02x", v->salt[x]);
+		break;
+	}
+
+	return 0;
+}
+
+static int verity_ioctl(struct dm_target *ti, unsigned cmd,
+			unsigned long arg)
+{
+	struct dm_verity *v = ti->private;
+	int r = 0;
+
+	if (v->data_start ||
+	    ti->len != i_size_read(v->data_dev->bdev->bd_inode) >> SECTOR_SHIFT)
+		r = scsi_verify_blk_ioctl(NULL, cmd);
+
+	return r ? : __blkdev_driver_ioctl(v->data_dev->bdev, v->data_dev->mode,
+				     cmd, arg);
+}
+
+static int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
+			struct bio_vec *biovec, int max_size)
+{
+	struct dm_verity *v = ti->private;
+	struct request_queue *q = bdev_get_queue(v->data_dev->bdev);
+
+	if (!q->merge_bvec_fn)
+		return max_size;
+
+	bvm->bi_bdev = v->data_dev->bdev;
+	bvm->bi_sector = verity_map_sector(v, bvm->bi_sector);
+
+	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
+}
+
+static int verity_iterate_devices(struct dm_target *ti,
+				  iterate_devices_callout_fn fn, void *data)
+{
+	struct dm_verity *v = ti->private;
+
+	return fn(ti, v->data_dev, v->data_start, ti->len, data);
+}
+
+static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+	struct dm_verity *v = ti->private;
+
+	if (limits->logical_block_size < 1 << v->data_dev_block_bits)
+		limits->logical_block_size = 1 << v->data_dev_block_bits;
+
+	if (limits->physical_block_size < 1 << v->data_dev_block_bits)
+		limits->physical_block_size = 1 << v->data_dev_block_bits;
+
+	blk_limits_io_min(limits, limits->logical_block_size);
+}
+
+static void verity_dtr(struct dm_target *ti)
+{
+	struct dm_verity *v = ti->private;
+
+	if (v->verify_wq)
+		destroy_workqueue(v->verify_wq);
+
+	if (v->vec_mempool)
+		mempool_destroy(v->vec_mempool);
+
+	if (v->io_mempool)
+		mempool_destroy(v->io_mempool);
+
+	if (v->bufio)
+		dm_bufio_client_destroy(v->bufio);
+
+	kfree(v->salt);
+	kfree(v->root_digest);
+
+	if (v->tfm)
+		crypto_free_shash(v->tfm);
+
+	kfree(v->alg_name);
+
+	if (v->hash_dev)
+		dm_put_device(ti, v->hash_dev);
+
+	if (v->data_dev)
+		dm_put_device(ti, v->data_dev);
+
+	kfree(v);
+}
+
+/*
+ * Target parameters:
+ *	<version>	The current format is version 1.
+ *			Vsn 0 is compatible with original Chromium OS releases.
+ *	<data device>
+ *	<hash device>
+ *	<data block size>
+ *	<hash block size>
+ *	<the number of data blocks>
+ *	<hash start block>
+ *	<algorithm>
+ *	<digest>
+ *	<salt>		Hex string or "-" if no salt.
+ */
+static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+	struct dm_verity *v;
+	unsigned num;
+	unsigned long long num_ll;
+	int r;
+	int i;
+	sector_t hash_position;
+	char dummy;
+
+	v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL);
+	if (!v) {
+		ti->error = "Cannot allocate verity structure";
+		return -ENOMEM;
+	}
+	ti->private = v;
+	v->ti = ti;
+
+	if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) {
+		ti->error = "Device must be readonly";
+		r = -EINVAL;
+		goto bad;
+	}
+
+	if (argc != 10) {
+		ti->error = "Invalid argument count: exactly 10 arguments required";
+		r = -EINVAL;
+		goto bad;
+	}
+
+	if (sscanf(argv[0], "%d%c", &num, &dummy) != 1 ||
+	    num < 0 || num > 1) {
+		ti->error = "Invalid version";
+		r = -EINVAL;
+		goto bad;
+	}
+	v->version = num;
+
+	r = dm_get_device(ti, argv[1], FMODE_READ, &v->data_dev);
+	if (r) {
+		ti->error = "Data device lookup failed";
+		goto bad;
+	}
+
+	r = dm_get_device(ti, argv[2], FMODE_READ, &v->hash_dev);
+	if (r) {
+		ti->error = "Data device lookup failed";
+		goto bad;
+	}
+
+	if (sscanf(argv[3], "%u%c", &num, &dummy) != 1 ||
+	    !num || (num & (num - 1)) ||
+	    num < bdev_logical_block_size(v->data_dev->bdev) ||
+	    num > PAGE_SIZE) {
+		ti->error = "Invalid data device block size";
+		r = -EINVAL;
+		goto bad;
+	}
+	v->data_dev_block_bits = ffs(num) - 1;
+
+	if (sscanf(argv[4], "%u%c", &num, &dummy) != 1 ||
+	    !num || (num & (num - 1)) ||
+	    num < bdev_logical_block_size(v->hash_dev->bdev) ||
+	    num > INT_MAX) {
+		ti->error = "Invalid hash device block size";
+		r = -EINVAL;
+		goto bad;
+	}
+	v->hash_dev_block_bits = ffs(num) - 1;
+
+	if (sscanf(argv[5], "%llu%c", &num_ll, &dummy) != 1 ||
+	    num_ll << (v->data_dev_block_bits - SECTOR_SHIFT) !=
+	    (sector_t)num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) {
+		ti->error = "Invalid data blocks";
+		r = -EINVAL;
+		goto bad;
+	}
+	v->data_blocks = num_ll;
+
+	if (ti->len > (v->data_blocks << (v->data_dev_block_bits - SECTOR_SHIFT))) {
+		ti->error = "Data device is too small";
+		r = -EINVAL;
+		goto bad;
+	}
+
+	if (sscanf(argv[6], "%llu%c", &num_ll, &dummy) != 1 ||
+	    num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT) !=
+	    (sector_t)num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT)) {
+		ti->error = "Invalid hash start";
+		r = -EINVAL;
+		goto bad;
+	}
+	v->hash_start = num_ll;
+
+	v->alg_name = kstrdup(argv[7], GFP_KERNEL);
+	if (!v->alg_name) {
+		ti->error = "Cannot allocate algorithm name";
+		r = -ENOMEM;
+		goto bad;
+	}
+
+	v->tfm = crypto_alloc_shash(v->alg_name, 0, 0);
+	if (IS_ERR(v->tfm)) {
+		ti->error = "Cannot initialize hash function";
+		r = PTR_ERR(v->tfm);
+		v->tfm = NULL;
+		goto bad;
+	}
+	v->digest_size = crypto_shash_digestsize(v->tfm);
+	if ((1 << v->hash_dev_block_bits) < v->digest_size * 2) {
+		ti->error = "Digest size too big";
+		r = -EINVAL;
+		goto bad;
+	}
+	v->shash_descsize =
+		sizeof(struct shash_desc) + crypto_shash_descsize(v->tfm);
+
+	v->root_digest = kmalloc(v->digest_size, GFP_KERNEL);
+	if (!v->root_digest) {
+		ti->error = "Cannot allocate root digest";
+		r = -ENOMEM;
+		goto bad;
+	}
+	if (strlen(argv[8]) != v->digest_size * 2 ||
+	    hex2bin(v->root_digest, argv[8], v->digest_size)) {
+		ti->error = "Invalid root digest";
+		r = -EINVAL;
+		goto bad;
+	}
+
+	if (strcmp(argv[9], "-")) {
+		v->salt_size = strlen(argv[9]) / 2;
+		v->salt = kmalloc(v->salt_size, GFP_KERNEL);
+		if (!v->salt) {
+			ti->error = "Cannot allocate salt";
+			r = -ENOMEM;
+			goto bad;
+		}
+		if (strlen(argv[9]) != v->salt_size * 2 ||
+		    hex2bin(v->salt, argv[9], v->salt_size)) {
+			ti->error = "Invalid salt";
+			r = -EINVAL;
+			goto bad;
+		}
+	}
+
+	v->hash_per_block_bits =
+		fls((1 << v->hash_dev_block_bits) / v->digest_size) - 1;
+
+	v->levels = 0;
+	if (v->data_blocks)
+		while (v->hash_per_block_bits * v->levels < 64 &&
+		       (unsigned long long)(v->data_blocks - 1) >>
+		       (v->hash_per_block_bits * v->levels))
+			v->levels++;
+
+	if (v->levels > DM_VERITY_MAX_LEVELS) {
+		ti->error = "Too many tree levels";
+		r = -E2BIG;
+		goto bad;
+	}
+
+	hash_position = v->hash_start;
+	for (i = v->levels - 1; i >= 0; i--) {
+		sector_t s;
+		v->hash_level_block[i] = hash_position;
+		s = verity_position_at_level(v, v->data_blocks, i);
+		s = (s >> v->hash_per_block_bits) +
+		    !!(s & ((1 << v->hash_per_block_bits) - 1));
+		if (hash_position + s < hash_position) {
+			ti->error = "Hash device offset overflow";
+			r = -E2BIG;
+			goto bad;
+		}
+		hash_position += s;
+	}
+	v->hash_blocks = hash_position;
+
+	v->bufio = dm_bufio_client_create(v->hash_dev->bdev,
+		1 << v->hash_dev_block_bits, 1, sizeof(struct buffer_aux),
+		dm_bufio_alloc_callback, NULL);
+	if (IS_ERR(v->bufio)) {
+		ti->error = "Cannot initialize dm-bufio";
+		r = PTR_ERR(v->bufio);
+		v->bufio = NULL;
+		goto bad;
+	}
+
+	if (dm_bufio_get_device_size(v->bufio) < v->hash_blocks) {
+		ti->error = "Hash device is too small";
+		r = -E2BIG;
+		goto bad;
+	}
+
+	v->io_mempool = mempool_create_kmalloc_pool(DM_VERITY_MEMPOOL_SIZE,
+	  sizeof(struct dm_verity_io) + v->shash_descsize + v->digest_size * 2);
+	if (!v->io_mempool) {
+		ti->error = "Cannot allocate io mempool";
+		r = -ENOMEM;
+		goto bad;
+	}
+
+	v->vec_mempool = mempool_create_kmalloc_pool(DM_VERITY_MEMPOOL_SIZE,
+					BIO_MAX_PAGES * sizeof(struct bio_vec));
+	if (!v->vec_mempool) {
+		ti->error = "Cannot allocate vector mempool";
+		r = -ENOMEM;
+		goto bad;
+	}
+
+	/* WQ_UNBOUND greatly improves performance when running on ramdisk */
+	v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus());
+	if (!v->verify_wq) {
+		ti->error = "Cannot allocate workqueue";
+		r = -ENOMEM;
+		goto bad;
+	}
+
+	return 0;
+
+bad:
+	verity_dtr(ti);
+
+	return r;
+}
+
+static struct target_type verity_target = {
+	.name		= "verity",
+	.version	= {1, 0, 0},
+	.module		= THIS_MODULE,
+	.ctr		= verity_ctr,
+	.dtr		= verity_dtr,
+	.map		= verity_map,
+	.status		= verity_status,
+	.ioctl		= verity_ioctl,
+	.merge		= verity_merge,
+	.iterate_devices = verity_iterate_devices,
+	.io_hints	= verity_io_hints,
+};
+
+static int __init dm_verity_init(void)
+{
+	int r;
+
+	r = dm_register_target(&verity_target);
+	if (r < 0)
+		DMERR("register failed %d", r);
+
+	return r;
+}
+
+static void __exit dm_verity_exit(void)
+{
+	dm_unregister_target(&verity_target);
+}
+
+module_init(dm_verity_init);
+module_exit(dm_verity_exit);
+
+MODULE_AUTHOR("Mikulas Patocka <mpatocka@redhat.com>");
+MODULE_AUTHOR("Mandeep Baines <msb@chromium.org>");
+MODULE_AUTHOR("Will Drewry <wad@chromium.org>");
+MODULE_DESCRIPTION(DM_NAME " target for transparent disk integrity checking");
+MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b89c548ec3f8..e24143cc2040 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1016,6 +1016,7 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
 		/*
 		 * Store bio_set for cleanup.
 		 */
+		clone->bi_end_io = NULL;
 		clone->bi_private = md->bs;
 		bio_put(clone);
 		free_tio(md, tio);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index b0fcc7d02adb..fa211d80fc0a 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -198,6 +198,7 @@ out:
 static int linear_run (struct mddev *mddev)
 {
 	struct linear_conf *conf;
+	int ret;
 
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
@@ -211,7 +212,13 @@ static int linear_run (struct mddev *mddev)
 	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
 	mddev->queue->backing_dev_info.congested_fn = linear_congested;
 	mddev->queue->backing_dev_info.congested_data = mddev;
-	return md_integrity_register(mddev);
+
+	ret =  md_integrity_register(mddev);
+	if (ret) {
+		kfree(conf);
+		mddev->private = NULL;
+	}
+	return ret;
 }
 
 static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index d279c768f8f1..5709bfeab1e8 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -108,12 +108,9 @@ static inline void *value_base(struct node *n)
 	return &n->keys[le32_to_cpu(n->header.max_entries)];
 }
 
-/*
- * FIXME: Now that value size is stored in node we don't need the third parm.
- */
-static inline void *value_ptr(struct node *n, uint32_t index, size_t value_size)
+static inline void *value_ptr(struct node *n, uint32_t index)
 {
-	BUG_ON(value_size != le32_to_cpu(n->header.value_size));
+	uint32_t value_size = le32_to_cpu(n->header.value_size);
 	return value_base(n) + (value_size * index);
 }
 
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
index 023fbc2d389e..aa71e2359a07 100644
--- a/drivers/md/persistent-data/dm-btree-remove.c
+++ b/drivers/md/persistent-data/dm-btree-remove.c
@@ -61,20 +61,20 @@ static void node_shift(struct node *n, int shift)
 	if (shift < 0) {
 		shift = -shift;
 		BUG_ON(shift > nr_entries);
-		BUG_ON((void *) key_ptr(n, shift) >= value_ptr(n, shift, value_size));
+		BUG_ON((void *) key_ptr(n, shift) >= value_ptr(n, shift));
 		memmove(key_ptr(n, 0),
 			key_ptr(n, shift),
 			(nr_entries - shift) * sizeof(__le64));
-		memmove(value_ptr(n, 0, value_size),
-			value_ptr(n, shift, value_size),
+		memmove(value_ptr(n, 0),
+			value_ptr(n, shift),
 			(nr_entries - shift) * value_size);
 	} else {
 		BUG_ON(nr_entries + shift > le32_to_cpu(n->header.max_entries));
 		memmove(key_ptr(n, shift),
 			key_ptr(n, 0),
 			nr_entries * sizeof(__le64));
-		memmove(value_ptr(n, shift, value_size),
-			value_ptr(n, 0, value_size),
+		memmove(value_ptr(n, shift),
+			value_ptr(n, 0),
 			nr_entries * value_size);
 	}
 }
@@ -91,16 +91,16 @@ static void node_copy(struct node *left, struct node *right, int shift)
 		memcpy(key_ptr(left, nr_left),
 		       key_ptr(right, 0),
 		       shift * sizeof(__le64));
-		memcpy(value_ptr(left, nr_left, value_size),
-		       value_ptr(right, 0, value_size),
+		memcpy(value_ptr(left, nr_left),
+		       value_ptr(right, 0),
 		       shift * value_size);
 	} else {
 		BUG_ON(shift > le32_to_cpu(right->header.max_entries));
 		memcpy(key_ptr(right, 0),
 		       key_ptr(left, nr_left - shift),
 		       shift * sizeof(__le64));
-		memcpy(value_ptr(right, 0, value_size),
-		       value_ptr(left, nr_left - shift, value_size),
+		memcpy(value_ptr(right, 0),
+		       value_ptr(left, nr_left - shift),
 		       shift * value_size);
 	}
 }
@@ -120,26 +120,17 @@ static void delete_at(struct node *n, unsigned index)
 			key_ptr(n, index + 1),
 			nr_to_copy * sizeof(__le64));
 
-		memmove(value_ptr(n, index, value_size),
-			value_ptr(n, index + 1, value_size),
+		memmove(value_ptr(n, index),
+			value_ptr(n, index + 1),
 			nr_to_copy * value_size);
 	}
 
 	n->header.nr_entries = cpu_to_le32(nr_entries - 1);
 }
 
-static unsigned del_threshold(struct node *n)
-{
-	return le32_to_cpu(n->header.max_entries) / 3;
-}
-
 static unsigned merge_threshold(struct node *n)
 {
-	/*
-	 * The extra one is because we know we're potentially going to
-	 * delete an entry.
-	 */
-	return 2 * (le32_to_cpu(n->header.max_entries) / 3) + 1;
+	return le32_to_cpu(n->header.max_entries) / 3;
 }
 
 struct child {
@@ -175,7 +166,7 @@ static int init_child(struct dm_btree_info *info, struct node *parent,
 	if (inc)
 		inc_children(info->tm, result->n, &le64_type);
 
-	*((__le64 *) value_ptr(parent, index, sizeof(__le64))) =
+	*((__le64 *) value_ptr(parent, index)) =
 		cpu_to_le64(dm_block_location(result->block));
 
 	return 0;
@@ -188,6 +179,15 @@ static int exit_child(struct dm_btree_info *info, struct child *c)
 
 static void shift(struct node *left, struct node *right, int count)
 {
+	uint32_t nr_left = le32_to_cpu(left->header.nr_entries);
+	uint32_t nr_right = le32_to_cpu(right->header.nr_entries);
+	uint32_t max_entries = le32_to_cpu(left->header.max_entries);
+	uint32_t r_max_entries = le32_to_cpu(right->header.max_entries);
+
+	BUG_ON(max_entries != r_max_entries);
+	BUG_ON(nr_left - count > max_entries);
+	BUG_ON(nr_right + count > max_entries);
+
 	if (!count)
 		return;
 
@@ -199,13 +199,8 @@ static void shift(struct node *left, struct node *right, int count)
 		node_shift(right, count);
 	}
 
-	left->header.nr_entries =
-		cpu_to_le32(le32_to_cpu(left->header.nr_entries) - count);
-	BUG_ON(le32_to_cpu(left->header.nr_entries) > le32_to_cpu(left->header.max_entries));
-
-	right->header.nr_entries =
-		cpu_to_le32(le32_to_cpu(right->header.nr_entries) + count);
-	BUG_ON(le32_to_cpu(right->header.nr_entries) > le32_to_cpu(right->header.max_entries));
+	left->header.nr_entries = cpu_to_le32(nr_left - count);
+	right->header.nr_entries = cpu_to_le32(nr_right + count);
 }
 
 static void __rebalance2(struct dm_btree_info *info, struct node *parent,
@@ -215,8 +210,9 @@ static void __rebalance2(struct dm_btree_info *info, struct node *parent,
 	struct node *right = r->n;
 	uint32_t nr_left = le32_to_cpu(left->header.nr_entries);
 	uint32_t nr_right = le32_to_cpu(right->header.nr_entries);
+	unsigned threshold = 2 * merge_threshold(left) + 1;
 
-	if (nr_left + nr_right <= merge_threshold(left)) {
+	if (nr_left + nr_right < threshold) {
 		/*
 		 * Merge
 		 */
@@ -234,9 +230,6 @@ static void __rebalance2(struct dm_btree_info *info, struct node *parent,
 		 * Rebalance.
 		 */
 		unsigned target_left = (nr_left + nr_right) / 2;
-		unsigned shift_ = nr_left - target_left;
-		BUG_ON(le32_to_cpu(left->header.max_entries) <= nr_left - shift_);
-		BUG_ON(le32_to_cpu(right->header.max_entries) <= nr_right + shift_);
 		shift(left, right, nr_left - target_left);
 		*key_ptr(parent, r->index) = right->keys[0];
 	}
@@ -272,6 +265,84 @@ static int rebalance2(struct shadow_spine *s, struct dm_btree_info *info,
 	return exit_child(info, &right);
 }
 
+/*
+ * We dump as many entries from center as possible into left, then the rest
+ * in right, then rebalance2.  This wastes some cpu, but I want something
+ * simple atm.
+ */
+static void delete_center_node(struct dm_btree_info *info, struct node *parent,
+			       struct child *l, struct child *c, struct child *r,
+			       struct node *left, struct node *center, struct node *right,
+			       uint32_t nr_left, uint32_t nr_center, uint32_t nr_right)
+{
+	uint32_t max_entries = le32_to_cpu(left->header.max_entries);
+	unsigned shift = min(max_entries - nr_left, nr_center);
+
+	BUG_ON(nr_left + shift > max_entries);
+	node_copy(left, center, -shift);
+	left->header.nr_entries = cpu_to_le32(nr_left + shift);
+
+	if (shift != nr_center) {
+		shift = nr_center - shift;
+		BUG_ON((nr_right + shift) > max_entries);
+		node_shift(right, shift);
+		node_copy(center, right, shift);
+		right->header.nr_entries = cpu_to_le32(nr_right + shift);
+	}
+	*key_ptr(parent, r->index) = right->keys[0];
+
+	delete_at(parent, c->index);
+	r->index--;
+
+	dm_tm_dec(info->tm, dm_block_location(c->block));
+	__rebalance2(info, parent, l, r);
+}
+
+/*
+ * Redistributes entries among 3 sibling nodes.
+ */
+static void redistribute3(struct dm_btree_info *info, struct node *parent,
+			  struct child *l, struct child *c, struct child *r,
+			  struct node *left, struct node *center, struct node *right,
+			  uint32_t nr_left, uint32_t nr_center, uint32_t nr_right)
+{
+	int s;
+	uint32_t max_entries = le32_to_cpu(left->header.max_entries);
+	unsigned target = (nr_left + nr_center + nr_right) / 3;
+	BUG_ON(target > max_entries);
+
+	if (nr_left < nr_right) {
+		s = nr_left - target;
+
+		if (s < 0 && nr_center < -s) {
+			/* not enough in central node */
+			shift(left, center, nr_center);
+			s = nr_center - target;
+			shift(left, right, s);
+			nr_right += s;
+		} else
+			shift(left, center, s);
+
+		shift(center, right, target - nr_right);
+
+	} else {
+		s = target - nr_right;
+		if (s > 0 && nr_center < s) {
+			/* not enough in central node */
+			shift(center, right, nr_center);
+			s = target - nr_center;
+			shift(left, right, s);
+			nr_left -= s;
+		} else
+			shift(center, right, s);
+
+		shift(left, center, nr_left - target);
+	}
+
+	*key_ptr(parent, c->index) = center->keys[0];
+	*key_ptr(parent, r->index) = right->keys[0];
+}
+
 static void __rebalance3(struct dm_btree_info *info, struct node *parent,
 			 struct child *l, struct child *c, struct child *r)
 {
@@ -282,62 +353,18 @@ static void __rebalance3(struct dm_btree_info *info, struct node *parent,
 	uint32_t nr_left = le32_to_cpu(left->header.nr_entries);
 	uint32_t nr_center = le32_to_cpu(center->header.nr_entries);
 	uint32_t nr_right = le32_to_cpu(right->header.nr_entries);
-	uint32_t max_entries = le32_to_cpu(left->header.max_entries);
 
-	unsigned target;
+	unsigned threshold = merge_threshold(left) * 4 + 1;
 
 	BUG_ON(left->header.max_entries != center->header.max_entries);
 	BUG_ON(center->header.max_entries != right->header.max_entries);
 
-	if (((nr_left + nr_center + nr_right) / 2) < merge_threshold(center)) {
-		/*
-		 * Delete center node:
-		 *
-		 * We dump as many entries from center as possible into
-		 * left, then the rest in right, then rebalance2.  This
-		 * wastes some cpu, but I want something simple atm.
-		 */
-		unsigned shift = min(max_entries - nr_left, nr_center);
-
-		BUG_ON(nr_left + shift > max_entries);
-		node_copy(left, center, -shift);
-		left->header.nr_entries = cpu_to_le32(nr_left + shift);
-
-		if (shift != nr_center) {
-			shift = nr_center - shift;
-			BUG_ON((nr_right + shift) >= max_entries);
-			node_shift(right, shift);
-			node_copy(center, right, shift);
-			right->header.nr_entries = cpu_to_le32(nr_right + shift);
-		}
-		*key_ptr(parent, r->index) = right->keys[0];
-
-		delete_at(parent, c->index);
-		r->index--;
-
-		dm_tm_dec(info->tm, dm_block_location(c->block));
-		__rebalance2(info, parent, l, r);
-
-		return;
-	}
-
-	/*
-	 * Rebalance
-	 */
-	target = (nr_left + nr_center + nr_right) / 3;
-	BUG_ON(target > max_entries);
-
-	/*
-	 * Adjust the left node
-	 */
-	shift(left, center, nr_left - target);
-
-	/*
-	 * Adjust the right node
-	 */
-	shift(center, right, target - nr_right);
-	*key_ptr(parent, c->index) = center->keys[0];
-	*key_ptr(parent, r->index) = right->keys[0];
+	if ((nr_left + nr_center + nr_right) < threshold)
+		delete_center_node(info, parent, l, c, r, left, center, right,
+				   nr_left, nr_center, nr_right);
+	else
+		redistribute3(info, parent, l, c, r, left, center, right,
+			      nr_left, nr_center, nr_right);
 }
 
 static int rebalance3(struct shadow_spine *s, struct dm_btree_info *info,
@@ -441,9 +468,6 @@ static int rebalance_children(struct shadow_spine *s,
 	if (r)
 		return r;
 
-	if (child_entries > del_threshold(n))
-		return 0;
-
 	has_left_sibling = i > 0;
 	has_right_sibling = i < (le32_to_cpu(n->header.nr_entries) - 1);
 
@@ -496,7 +520,7 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info,
 		 */
 		if (shadow_has_parent(s)) {
 			__le64 location = cpu_to_le64(dm_block_location(shadow_current(s)));
-			memcpy(value_ptr(dm_block_data(shadow_parent(s)), i, sizeof(__le64)),
+			memcpy(value_ptr(dm_block_data(shadow_parent(s)), i),
 			       &location, sizeof(__le64));
 		}
 
@@ -553,7 +577,7 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
 
 		if (info->value_type.dec)
 			info->value_type.dec(info->value_type.context,
-					     value_ptr(n, index, info->value_type.size));
+					     value_ptr(n, index));
 
 		delete_at(n, index);
 	}
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index bd1e7ffbe26c..d12b2cc51f1a 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -74,8 +74,7 @@ void inc_children(struct dm_transaction_manager *tm, struct node *n,
 			dm_tm_inc(tm, value64(n, i));
 	else if (vt->inc)
 		for (i = 0; i < nr_entries; i++)
-			vt->inc(vt->context,
-				value_ptr(n, i, vt->size));
+			vt->inc(vt->context, value_ptr(n, i));
 }
 
 static int insert_at(size_t value_size, struct node *node, unsigned index,
@@ -281,7 +280,7 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
 
 				for (i = 0; i < f->nr_children; i++)
 					info->value_type.dec(info->value_type.context,
-							     value_ptr(f->n, i, info->value_type.size));
+							     value_ptr(f->n, i));
 			}
 			f->current_child = f->nr_children;
 		}
@@ -320,7 +319,7 @@ static int btree_lookup_raw(struct ro_spine *s, dm_block_t block, uint64_t key,
 	} while (!(flags & LEAF_NODE));
 
 	*result_key = le64_to_cpu(ro_node(s)->keys[i]);
-	memcpy(v, value_ptr(ro_node(s), i, value_size), value_size);
+	memcpy(v, value_ptr(ro_node(s), i), value_size);
 
 	return 0;
 }
@@ -432,7 +431,7 @@ static int btree_split_sibling(struct shadow_spine *s, dm_block_t root,
 
 	size = le32_to_cpu(ln->header.flags) & INTERNAL_NODE ?
 		sizeof(uint64_t) : s->info->value_type.size;
-	memcpy(value_ptr(rn, 0, size), value_ptr(ln, nr_left, size),
+	memcpy(value_ptr(rn, 0), value_ptr(ln, nr_left),
 	       size * nr_right);
 
 	/*
@@ -443,7 +442,7 @@ static int btree_split_sibling(struct shadow_spine *s, dm_block_t root,
 	pn = dm_block_data(parent);
 	location = cpu_to_le64(dm_block_location(left));
 	__dm_bless_for_disk(&location);
-	memcpy_disk(value_ptr(pn, parent_index, sizeof(__le64)),
+	memcpy_disk(value_ptr(pn, parent_index),
 		    &location, sizeof(__le64));
 
 	location = cpu_to_le64(dm_block_location(right));
@@ -529,8 +528,8 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
 
 	size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ?
 		sizeof(__le64) : s->info->value_type.size;
-	memcpy(value_ptr(ln, 0, size), value_ptr(pn, 0, size), nr_left * size);
-	memcpy(value_ptr(rn, 0, size), value_ptr(pn, nr_left, size),
+	memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size);
+	memcpy(value_ptr(rn, 0), value_ptr(pn, nr_left),
 	       nr_right * size);
 
 	/* new_parent should just point to l and r now */
@@ -545,12 +544,12 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
 	val = cpu_to_le64(dm_block_location(left));
 	__dm_bless_for_disk(&val);
 	pn->keys[0] = ln->keys[0];
-	memcpy_disk(value_ptr(pn, 0, sizeof(__le64)), &val, sizeof(__le64));
+	memcpy_disk(value_ptr(pn, 0), &val, sizeof(__le64));
 
 	val = cpu_to_le64(dm_block_location(right));
 	__dm_bless_for_disk(&val);
 	pn->keys[1] = rn->keys[0];
-	memcpy_disk(value_ptr(pn, 1, sizeof(__le64)), &val, sizeof(__le64));
+	memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64));
 
 	/*
 	 * rejig the spine.  This is ugly, since it knows too
@@ -595,7 +594,7 @@ static int btree_insert_raw(struct shadow_spine *s, dm_block_t root,
 			__le64 location = cpu_to_le64(dm_block_location(shadow_current(s)));
 
 			__dm_bless_for_disk(&location);
-			memcpy_disk(value_ptr(dm_block_data(shadow_parent(s)), i, sizeof(uint64_t)),
+			memcpy_disk(value_ptr(dm_block_data(shadow_parent(s)), i),
 				    &location, sizeof(__le64));
 		}
 
@@ -710,12 +709,12 @@ static int insert(struct dm_btree_info *info, dm_block_t root,
 		    (!info->value_type.equal ||
 		     !info->value_type.equal(
 			     info->value_type.context,
-			     value_ptr(n, index, info->value_type.size),
+			     value_ptr(n, index),
 			     value))) {
 			info->value_type.dec(info->value_type.context,
-					     value_ptr(n, index, info->value_type.size));
+					     value_ptr(n, index));
 		}
-		memcpy_disk(value_ptr(n, index, info->value_type.size),
+		memcpy_disk(value_ptr(n, index),
 			    value, info->value_type.size);
 	}
 
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index df2494c06cdc..ff3beed6ad2d 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -405,8 +405,6 @@ int sm_ll_insert(struct ll_disk *ll, dm_block_t b,
 		if (r < 0)
 			return r;
 
-#if 0
-		/* FIXME: dm_btree_remove doesn't handle this yet */
 		if (old > 2) {
 			r = dm_btree_remove(&ll->ref_count_info,
 					    ll->ref_count_root,
@@ -414,7 +412,6 @@ int sm_ll_insert(struct ll_disk *ll, dm_block_t b,
 			if (r)
 				return r;
 		}
-#endif
 
 	} else {
 		__le32 le_rc = cpu_to_le32(ref_count);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 6f31f5596e01..de63a1fc3737 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -407,6 +407,8 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
 	return array_sectors;
 }
 
+static int raid0_stop(struct mddev *mddev);
+
 static int raid0_run(struct mddev *mddev)
 {
 	struct r0conf *conf;
@@ -454,7 +456,12 @@ static int raid0_run(struct mddev *mddev)
 
 	blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
 	dump_zones(mddev);
-	return md_integrity_register(mddev);
+
+	ret = md_integrity_register(mddev);
+	if (ret)
+		raid0_stop(mddev);
+
+	return ret;
 }
 
 static int raid0_stop(struct mddev *mddev)
@@ -625,6 +632,7 @@ static void *raid0_takeover_raid10(struct mddev *mddev)
 static void *raid0_takeover_raid1(struct mddev *mddev)
 {
 	struct r0conf *priv_conf;
+	int chunksect;
 
 	/* Check layout:
 	 *  - (N - 1) mirror drives must be already faulty
@@ -635,10 +643,25 @@ static void *raid0_takeover_raid1(struct mddev *mddev)
 		return ERR_PTR(-EINVAL);
 	}
 
+	/*
+	 * a raid1 doesn't have the notion of chunk size, so
+	 * figure out the largest suitable size we can use.
+	 */
+	chunksect = 64 * 2; /* 64K by default */
+
+	/* The array must be an exact multiple of chunksize */
+	while (chunksect && (mddev->array_sectors & (chunksect - 1)))
+		chunksect >>= 1;
+
+	if ((chunksect << 9) < PAGE_SIZE)
+		/* array size does not allow a suitable chunk size */
+		return ERR_PTR(-EINVAL);
+
 	/* Set new parameters */
 	mddev->new_level = 0;
 	mddev->new_layout = 0;
-	mddev->new_chunk_sectors = 128; /* by default set chunk size to 64k */
+	mddev->new_chunk_sectors = chunksect;
+	mddev->chunk_sectors = chunksect;
 	mddev->delta_disks = 1 - mddev->raid_disks;
 	mddev->raid_disks = 1;
 	/* make sure it will be not marked as dirty */
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4a40a200d769..d35e4c991e38 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1738,7 +1738,7 @@ static int process_checks(struct r1bio *r1_bio)
 				s = sbio->bi_io_vec[j].bv_page;
 				if (memcmp(page_address(p),
 					   page_address(s),
-					   PAGE_SIZE))
+					   sbio->bi_io_vec[j].bv_len))
 					break;
 			}
 		} else
@@ -2386,8 +2386,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 		int ok = 1;
 		for (i = 0 ; i < conf->raid_disks * 2 ; i++)
 			if (r1_bio->bios[i]->bi_end_io == end_sync_write) {
-				struct md_rdev *rdev =
-					rcu_dereference(conf->mirrors[i].rdev);
+				struct md_rdev *rdev = conf->mirrors[i].rdev;
 				ok = rdev_set_badblocks(rdev, sector_nr,
 							min_bad, 0
 					) && ok;
@@ -2636,11 +2635,13 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
+static int stop(struct mddev *mddev);
 static int run(struct mddev *mddev)
 {
 	struct r1conf *conf;
 	int i;
 	struct md_rdev *rdev;
+	int ret;
 
 	if (mddev->level != 1) {
 		printk(KERN_ERR "md/raid1:%s: raid level not set to mirroring (%d)\n",
@@ -2705,7 +2706,11 @@ static int run(struct mddev *mddev)
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		blk_queue_merge_bvec(mddev->queue, raid1_mergeable_bvec);
 	}
-	return md_integrity_register(mddev);
+
+	ret =  md_integrity_register(mddev);
+	if (ret)
+		stop(mddev);
+	return ret;
 }
 
 static int stop(struct mddev *mddev)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3540316886f2..fff782189e48 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1821,7 +1821,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			for (j = 0; j < vcnt; j++)
 				if (memcmp(page_address(fbio->bi_io_vec[j].bv_page),
 					   page_address(tbio->bi_io_vec[j].bv_page),
-					   PAGE_SIZE))
+					   fbio->bi_io_vec[j].bv_len))
 					break;
 			if (j == vcnt)
 				continue;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 23ac880bba9a..f351422938e0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2471,39 +2471,41 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
 	int abort = 0;
 	int i;
 
-	md_done_sync(conf->mddev, STRIPE_SECTORS, 0);
 	clear_bit(STRIPE_SYNCING, &sh->state);
 	s->syncing = 0;
 	s->replacing = 0;
 	/* There is nothing more to do for sync/check/repair.
+	 * Don't even need to abort as that is handled elsewhere
+	 * if needed, and not always wanted e.g. if there is a known
+	 * bad block here.
 	 * For recover/replace we need to record a bad block on all
 	 * non-sync devices, or abort the recovery
 	 */
-	if (!test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery))
-		return;
-	/* During recovery devices cannot be removed, so locking and
-	 * refcounting of rdevs is not needed
-	 */
-	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = conf->disks[i].rdev;
-		if (rdev
-		    && !test_bit(Faulty, &rdev->flags)
-		    && !test_bit(In_sync, &rdev->flags)
-		    && !rdev_set_badblocks(rdev, sh->sector,
-					   STRIPE_SECTORS, 0))
-			abort = 1;
-		rdev = conf->disks[i].replacement;
-		if (rdev
-		    && !test_bit(Faulty, &rdev->flags)
-		    && !test_bit(In_sync, &rdev->flags)
-		    && !rdev_set_badblocks(rdev, sh->sector,
-					   STRIPE_SECTORS, 0))
-			abort = 1;
-	}
-	if (abort) {
-		conf->recovery_disabled = conf->mddev->recovery_disabled;
-		set_bit(MD_RECOVERY_INTR, &conf->mddev->recovery);
+	if (test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery)) {
+		/* During recovery devices cannot be removed, so
+		 * locking and refcounting of rdevs is not needed
+		 */
+		for (i = 0; i < conf->raid_disks; i++) {
+			struct md_rdev *rdev = conf->disks[i].rdev;
+			if (rdev
+			    && !test_bit(Faulty, &rdev->flags)
+			    && !test_bit(In_sync, &rdev->flags)
+			    && !rdev_set_badblocks(rdev, sh->sector,
+						   STRIPE_SECTORS, 0))
+				abort = 1;
+			rdev = conf->disks[i].replacement;
+			if (rdev
+			    && !test_bit(Faulty, &rdev->flags)
+			    && !test_bit(In_sync, &rdev->flags)
+			    && !rdev_set_badblocks(rdev, sh->sector,
+						   STRIPE_SECTORS, 0))
+				abort = 1;
+		}
+		if (abort)
+			conf->recovery_disabled =
+				conf->mddev->recovery_disabled;
 	}
+	md_done_sync(conf->mddev, STRIPE_SECTORS, !abort);
 }
 
 static int want_replace(struct stripe_head *sh, int disk_idx)
@@ -3203,7 +3205,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			/* Not in-sync */;
 		else if (is_bad) {
 			/* also not in-sync */
-			if (!test_bit(WriteErrorSeen, &rdev->flags)) {
+			if (!test_bit(WriteErrorSeen, &rdev->flags) &&
+			    test_bit(R5_UPTODATE, &dev->flags)) {
 				/* treat as in-sync, but with a read error
 				 * which we can now try to correct
 				 */
@@ -3276,12 +3279,14 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		/* If there is a failed device being replaced,
 		 *     we must be recovering.
 		 * else if we are after recovery_cp, we must be syncing
+		 * else if MD_RECOVERY_REQUESTED is set, we also are syncing.
 		 * else we can only be replacing
 		 * sync and recovery both need to read all devices, and so
 		 * use the same flag.
 		 */
 		if (do_recovery ||
-		    sh->sector >= conf->mddev->recovery_cp)
+		    sh->sector >= conf->mddev->recovery_cp ||
+		    test_bit(MD_RECOVERY_REQUESTED, &(conf->mddev->recovery)))
 			s->syncing = 1;
 		else
 			s->replacing = 1;
diff --git a/drivers/media/dvb/dvb-core/dmxdev.c b/drivers/media/dvb/dvb-core/dmxdev.c
index e4b5c03ae516..73970cd97af1 100644
--- a/drivers/media/dvb/dvb-core/dmxdev.c
+++ b/drivers/media/dvb/dvb-core/dmxdev.c
@@ -29,7 +29,6 @@
 #include <linux/ioctl.h>
 #include <linux/wait.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include "dmxdev.h"
 
 static int debug;
diff --git a/drivers/media/dvb/firewire/firedtv-fw.c b/drivers/media/dvb/firewire/firedtv-fw.c
index 864b6274c729..e24ec539a5fd 100644
--- a/drivers/media/dvb/firewire/firedtv-fw.c
+++ b/drivers/media/dvb/firewire/firedtv-fw.c
@@ -20,7 +20,6 @@
 #include <linux/workqueue.h>
 
 #include <asm/page.h>
-#include <asm/system.h>
 
 #include <dvb_demux.h>
 
diff --git a/drivers/media/dvb/ttpci/av7110.c b/drivers/media/dvb/ttpci/av7110.c
index 6ecbcf614878..4bd8bd56befc 100644
--- a/drivers/media/dvb/ttpci/av7110.c
+++ b/drivers/media/dvb/ttpci/av7110.c
@@ -53,7 +53,6 @@
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
 
-#include <asm/system.h>
 
 #include <linux/dvb/frontend.h>
 
diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c
index 421cf73858d3..f6b52d549430 100644
--- a/drivers/media/media-devnode.c
+++ b/drivers/media/media-devnode.c
@@ -40,7 +40,6 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
-#include <asm/system.h>
 
 #include <media/media-devnode.h>
 
diff --git a/drivers/media/video/davinci/vpbe_osd.c b/drivers/media/video/davinci/vpbe_osd.c
index d6488b79ae3b..bba299dbf396 100644
--- a/drivers/media/video/davinci/vpbe_osd.c
+++ b/drivers/media/video/davinci/vpbe_osd.c
@@ -28,7 +28,6 @@
 #include <linux/clk.h>
 #include <linux/slab.h>
 
-#include <mach/io.h>
 #include <mach/cputype.h>
 #include <mach/hardware.h>
 
diff --git a/drivers/media/video/davinci/vpbe_venc.c b/drivers/media/video/davinci/vpbe_venc.c
index 00e80f59d5d5..b21ecc8d134d 100644
--- a/drivers/media/video/davinci/vpbe_venc.c
+++ b/drivers/media/video/davinci/vpbe_venc.c
@@ -27,7 +27,6 @@
 
 #include <mach/hardware.h>
 #include <mach/mux.h>
-#include <mach/io.h>
 #include <mach/i2c.h>
 
 #include <linux/io.h>
diff --git a/drivers/media/video/ivtv/ivtv-driver.h b/drivers/media/video/ivtv/ivtv-driver.h
index f767df943954..2e220028aad2 100644
--- a/drivers/media/video/ivtv/ivtv-driver.h
+++ b/drivers/media/video/ivtv/ivtv-driver.h
@@ -54,7 +54,6 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 #include <linux/dvb/video.h>
diff --git a/drivers/media/video/mx3_camera.c b/drivers/media/video/mx3_camera.c
index 74522773e934..93c35ef5f0ad 100644
--- a/drivers/media/video/mx3_camera.c
+++ b/drivers/media/video/mx3_camera.c
@@ -286,7 +286,7 @@ static void mx3_videobuf_queue(struct vb2_buffer *vb)
 		sg_dma_address(sg)	= vb2_dma_contig_plane_dma_addr(vb, 0);
 		sg_dma_len(sg)		= new_size;
 
-		txd = ichan->dma_chan.device->device_prep_slave_sg(
+		txd = dmaengine_prep_slave_sg(
 			&ichan->dma_chan, sg, 1, DMA_DEV_TO_MEM,
 			DMA_PREP_INTERRUPT);
 		if (!txd)
diff --git a/drivers/media/video/timblogiw.c b/drivers/media/video/timblogiw.c
index 4ed1c7c28ae7..02194c056b00 100644
--- a/drivers/media/video/timblogiw.c
+++ b/drivers/media/video/timblogiw.c
@@ -564,7 +564,7 @@ static void buffer_queue(struct videobuf_queue *vq, struct videobuf_buffer *vb)
 
 	spin_unlock_irq(&fh->queue_lock);
 
-	desc = fh->chan->device->device_prep_slave_sg(fh->chan,
+	desc = dmaengine_prep_slave_sg(fh->chan,
 		buf->sg, sg_elems, DMA_DEV_TO_MEM,
 		DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
 	if (!desc) {
diff --git a/drivers/media/video/v4l2-common.c b/drivers/media/video/v4l2-common.c
index 5c6100fb4072..1baec8393306 100644
--- a/drivers/media/video/v4l2-common.c
+++ b/drivers/media/video/v4l2-common.c
@@ -55,7 +55,6 @@
 #include <linux/spi/spi.h>
 #endif
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/div64.h>
diff --git a/drivers/media/video/v4l2-dev.c b/drivers/media/video/v4l2-dev.c
index 041804b73ebd..70bec548d904 100644
--- a/drivers/media/video/v4l2-dev.c
+++ b/drivers/media/video/v4l2-dev.c
@@ -26,7 +26,6 @@
 #include <linux/kmod.h>
 #include <linux/slab.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/message/i2o/i2o_scsi.c b/drivers/message/i2o/i2o_scsi.c
index c8ed7b63fdf5..1d31d7284cbd 100644
--- a/drivers/message/i2o/i2o_scsi.c
+++ b/drivers/message/i2o/i2o_scsi.c
@@ -57,7 +57,6 @@
 #include <linux/scatterlist.h>
 
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
 
diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c
index 17dfe9bb6d27..87bd5ba38d5b 100644
--- a/drivers/mfd/88pm860x-core.c
+++ b/drivers/mfd/88pm860x-core.c
@@ -503,6 +503,101 @@ static void device_irq_exit(struct pm860x_chip *chip)
 		free_irq(chip->core_irq, chip);
 }
 
+int pm8606_osc_enable(struct pm860x_chip *chip, unsigned short client)
+{
+	int ret = -EIO;
+	struct i2c_client *i2c = (chip->id == CHIP_PM8606) ?
+		chip->client : chip->companion;
+
+	dev_dbg(chip->dev, "%s(B): client=0x%x\n", __func__, client);
+	dev_dbg(chip->dev, "%s(B): vote=0x%x status=%d\n",
+			__func__, chip->osc_vote,
+			chip->osc_status);
+
+	mutex_lock(&chip->osc_lock);
+	/* Update voting status */
+	chip->osc_vote |= client;
+	/* If reference group is off - turn on*/
+	if (chip->osc_status != PM8606_REF_GP_OSC_ON) {
+		chip->osc_status = PM8606_REF_GP_OSC_UNKNOWN;
+		/* Enable Reference group Vsys */
+		if (pm860x_set_bits(i2c, PM8606_VSYS,
+				PM8606_VSYS_EN, PM8606_VSYS_EN))
+			goto out;
+
+		/*Enable Internal Oscillator */
+		if (pm860x_set_bits(i2c, PM8606_MISC,
+				PM8606_MISC_OSC_EN, PM8606_MISC_OSC_EN))
+			goto out;
+		/* Update status (only if writes succeed) */
+		chip->osc_status = PM8606_REF_GP_OSC_ON;
+	}
+	mutex_unlock(&chip->osc_lock);
+
+	dev_dbg(chip->dev, "%s(A): vote=0x%x status=%d ret=%d\n",
+			__func__, chip->osc_vote,
+			chip->osc_status, ret);
+	return 0;
+out:
+	mutex_unlock(&chip->osc_lock);
+	return ret;
+}
+EXPORT_SYMBOL(pm8606_osc_enable);
+
+int pm8606_osc_disable(struct pm860x_chip *chip, unsigned short client)
+{
+	int ret = -EIO;
+	struct i2c_client *i2c = (chip->id == CHIP_PM8606) ?
+		chip->client : chip->companion;
+
+	dev_dbg(chip->dev, "%s(B): client=0x%x\n", __func__, client);
+	dev_dbg(chip->dev, "%s(B): vote=0x%x status=%d\n",
+			__func__, chip->osc_vote,
+			chip->osc_status);
+
+	mutex_lock(&chip->osc_lock);
+	/*Update voting status */
+	chip->osc_vote &= ~(client);
+	/* If reference group is off and this is the last client to release
+	 * - turn off */
+	if ((chip->osc_status != PM8606_REF_GP_OSC_OFF) &&
+			(chip->osc_vote == REF_GP_NO_CLIENTS)) {
+		chip->osc_status = PM8606_REF_GP_OSC_UNKNOWN;
+		/* Disable Reference group Vsys */
+		if (pm860x_set_bits(i2c, PM8606_VSYS, PM8606_VSYS_EN, 0))
+			goto out;
+		/* Disable Internal Oscillator */
+		if (pm860x_set_bits(i2c, PM8606_MISC, PM8606_MISC_OSC_EN, 0))
+			goto out;
+		chip->osc_status = PM8606_REF_GP_OSC_OFF;
+	}
+	mutex_unlock(&chip->osc_lock);
+
+	dev_dbg(chip->dev, "%s(A): vote=0x%x status=%d ret=%d\n",
+			__func__, chip->osc_vote,
+			chip->osc_status, ret);
+	return 0;
+out:
+	mutex_unlock(&chip->osc_lock);
+	return ret;
+}
+EXPORT_SYMBOL(pm8606_osc_disable);
+
+static void __devinit device_osc_init(struct i2c_client *i2c)
+{
+	struct pm860x_chip *chip = i2c_get_clientdata(i2c);
+
+	mutex_init(&chip->osc_lock);
+	/* init portofino reference group voting and status */
+	/* Disable Reference group Vsys */
+	pm860x_set_bits(i2c, PM8606_VSYS, PM8606_VSYS_EN, 0);
+	/* Disable Internal Oscillator */
+	pm860x_set_bits(i2c, PM8606_MISC, PM8606_MISC_OSC_EN, 0);
+
+	chip->osc_vote = REF_GP_NO_CLIENTS;
+	chip->osc_status = PM8606_REF_GP_OSC_OFF;
+}
+
 static void __devinit device_bk_init(struct pm860x_chip *chip,
 				     struct pm860x_platform_data *pdata)
 {
@@ -767,6 +862,15 @@ out:
 	return;
 }
 
+static void __devinit device_8606_init(struct pm860x_chip *chip,
+				       struct i2c_client *i2c,
+				       struct pm860x_platform_data *pdata)
+{
+	device_osc_init(i2c);
+	device_bk_init(chip, pdata);
+	device_led_init(chip, pdata);
+}
+
 int __devinit pm860x_device_init(struct pm860x_chip *chip,
 		       struct pm860x_platform_data *pdata)
 {
@@ -774,8 +878,7 @@ int __devinit pm860x_device_init(struct pm860x_chip *chip,
 
 	switch (chip->id) {
 	case CHIP_PM8606:
-		device_bk_init(chip, pdata);
-		device_led_init(chip, pdata);
+		device_8606_init(chip, chip->client, pdata);
 		break;
 	case CHIP_PM8607:
 		device_8607_init(chip, chip->client, pdata);
@@ -785,8 +888,7 @@ int __devinit pm860x_device_init(struct pm860x_chip *chip,
 	if (chip->companion) {
 		switch (chip->id) {
 		case CHIP_PM8607:
-			device_bk_init(chip, pdata);
-			device_led_init(chip, pdata);
+			device_8606_init(chip, chip->companion, pdata);
 			break;
 		case CHIP_PM8606:
 			device_8607_init(chip, chip->companion, pdata);
diff --git a/drivers/mfd/88pm860x-i2c.c b/drivers/mfd/88pm860x-i2c.c
index f93dd9571c3c..b2cfdc458561 100644
--- a/drivers/mfd/88pm860x-i2c.c
+++ b/drivers/mfd/88pm860x-i2c.c
@@ -334,10 +334,35 @@ static int __devexit pm860x_remove(struct i2c_client *client)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int pm860x_suspend(struct device *dev)
+{
+	struct i2c_client *client = container_of(dev, struct i2c_client, dev);
+	struct pm860x_chip *chip = i2c_get_clientdata(client);
+
+	if (device_may_wakeup(dev) && chip->wakeup_flag)
+		enable_irq_wake(chip->core_irq);
+	return 0;
+}
+
+static int pm860x_resume(struct device *dev)
+{
+	struct i2c_client *client = container_of(dev, struct i2c_client, dev);
+	struct pm860x_chip *chip = i2c_get_clientdata(client);
+
+	if (device_may_wakeup(dev) && chip->wakeup_flag)
+		disable_irq_wake(chip->core_irq);
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(pm860x_pm_ops, pm860x_suspend, pm860x_resume);
+
 static struct i2c_driver pm860x_driver = {
 	.driver	= {
 		.name	= "88PM860x",
 		.owner	= THIS_MODULE,
+		.pm     = &pm860x_pm_ops,
 	},
 	.probe		= pm860x_probe,
 	.remove		= __devexit_p(pm860x_remove),
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 1489c3540f96..29f463cc09cb 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -143,6 +143,21 @@ config TPS6507X
 	  This driver can also be built as a module.  If so, the module
 	  will be called tps6507x.
 
+config MFD_TPS65217
+	tristate "TPS65217 Power Management / White LED chips"
+	depends on I2C
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the TPS65217 series of
+	  Power Management / White LED chips.
+	  These include voltage regulators, lithium ion/polymer battery
+	  charger, wled and other features that are often used in portable
+	  devices.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called tps65217.
+
 config MFD_TPS6586X
 	bool "TPS6586x Power Management chips"
 	depends on I2C=y && GPIOLIB && GENERIC_HARDIRQS
@@ -162,6 +177,7 @@ config MFD_TPS65910
 	depends on I2C=y && GPIOLIB
 	select MFD_CORE
 	select GPIO_TPS65910
+	select REGMAP_I2C
 	help
 	  if you say yes here you get support for the TPS65910 series of
 	  Power Management chips.
@@ -171,7 +187,7 @@ config MFD_TPS65912
 	depends on GPIOLIB
 
 config MFD_TPS65912_I2C
-	bool "TPS95612 Power Management chip with I2C"
+	bool "TPS65912 Power Management chip with I2C"
 	select MFD_CORE
 	select MFD_TPS65912
 	depends on I2C=y && GPIOLIB
@@ -400,7 +416,7 @@ config MFD_MAX8997
 	depends on I2C=y && GENERIC_HARDIRQS
 	select MFD_CORE
 	help
-	  Say yes here to support for Maxim Semiconductor MAX8998/8966.
+	  Say yes here to support for Maxim Semiconductor MAX8997/8966.
 	  This is a Power Management IC with RTC, Flash, Fuel Gauge, Haptic,
 	  MUIC controls on chip.
 	  This driver provides common support for accessing the device;
@@ -812,6 +828,18 @@ config MFD_PM8XXX_IRQ
 config TPS65911_COMPARATOR
 	tristate
 
+config MFD_TPS65090
+	bool "TPS65090 Power Management chips"
+	depends on I2C=y && GENERIC_HARDIRQS
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the TPS65090 series of
+	  Power Management chips.
+	  This driver provides common support for accessing the device,
+	  additional drivers must be enabled in order to use the
+	  functionality of the device.
+
 config MFD_AAT2870_CORE
 	bool "Support for the AnalogicTech AAT2870"
 	select MFD_CORE
@@ -831,6 +859,28 @@ config MFD_INTEL_MSIC
 	  Passage) chip. This chip embeds audio, battery, GPIO, etc.
 	  devices used in Intel Medfield platforms.
 
+config MFD_RC5T583
+	bool "Ricoh RC5T583 Power Management system device"
+	depends on I2C=y && GENERIC_HARDIRQS
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  Select this option to get support for the RICOH583 Power
+	  Management system device.
+	  This driver provides common support for accessing the device
+	  through i2c interface. The device supports multiple sub-devices
+	  like GPIO, interrupts, RTC, LDO and DCDC regulators, onkey.
+	  Additional drivers must be enabled in order to use the
+	  different functionality of the device.
+
+config MFD_ANATOP
+	bool "Support for Freescale i.MX on-chip ANATOP controller"
+	depends on SOC_IMX6Q
+	help
+	  Select this option to enable Freescale i.MX on-chip ANATOP
+	  MFD controller. This controller embeds regulator and
+	  thermal devices for Freescale i.MX platforms.
+
 endmenu
 endif
 
@@ -848,8 +898,9 @@ config MCP_SA11X0
 
 # Chip drivers
 config MCP_UCB1200
-	tristate "Support for UCB1200 / UCB1300"
-	depends on MCP
+	bool "Support for UCB1200 / UCB1300"
+	depends on MCP_SA11X0
+	select MCP
 
 config MCP_UCB1200_TS
 	tristate "Touchscreen interface support"
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index b953bab934f7..05fa538c5efe 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_MFD_WM8994)	+= wm8994-core.o wm8994-irq.o wm8994-regmap.o
 obj-$(CONFIG_TPS6105X)		+= tps6105x.o
 obj-$(CONFIG_TPS65010)		+= tps65010.o
 obj-$(CONFIG_TPS6507X)		+= tps6507x.o
+obj-$(CONFIG_MFD_TPS65217)	+= tps65217.o
 obj-$(CONFIG_MFD_TPS65910)	+= tps65910.o tps65910-irq.o
 tps65912-objs                   := tps65912-core.o tps65912-irq.o
 obj-$(CONFIG_MFD_TPS65912)	+= tps65912.o
@@ -109,6 +110,9 @@ obj-$(CONFIG_MFD_OMAP_USB_HOST)	+= omap-usb-host.o
 obj-$(CONFIG_MFD_PM8921_CORE) 	+= pm8921-core.o
 obj-$(CONFIG_MFD_PM8XXX_IRQ) 	+= pm8xxx-irq.o
 obj-$(CONFIG_TPS65911_COMPARATOR)	+= tps65911-comparator.o
+obj-$(CONFIG_MFD_TPS65090)	+= tps65090.o
 obj-$(CONFIG_MFD_AAT2870_CORE)	+= aat2870-core.o
 obj-$(CONFIG_MFD_INTEL_MSIC)	+= intel_msic.o
+obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o
 obj-$(CONFIG_MFD_S5M_CORE)	+= s5m-core.o s5m-irq.o
+obj-$(CONFIG_MFD_ANATOP)	+= anatop-mfd.o
diff --git a/drivers/mfd/aat2870-core.c b/drivers/mfd/aat2870-core.c
index 3aa36eb5c79b..44a3fdbadef4 100644
--- a/drivers/mfd/aat2870-core.c
+++ b/drivers/mfd/aat2870-core.c
@@ -262,13 +262,6 @@ static ssize_t aat2870_dump_reg(struct aat2870_data *aat2870, char *buf)
 	return count;
 }
 
-static int aat2870_reg_open_file(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-
-	return 0;
-}
-
 static ssize_t aat2870_reg_read_file(struct file *file, char __user *user_buf,
 				     size_t count, loff_t *ppos)
 {
@@ -330,7 +323,7 @@ static ssize_t aat2870_reg_write_file(struct file *file,
 }
 
 static const struct file_operations aat2870_reg_fops = {
-	.open = aat2870_reg_open_file,
+	.open = simple_open,
 	.read = aat2870_reg_read_file,
 	.write = aat2870_reg_write_file,
 };
diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c
index 60107ee166fc..1efad20fb175 100644
--- a/drivers/mfd/ab3100-core.c
+++ b/drivers/mfd/ab3100-core.c
@@ -483,12 +483,6 @@ struct ab3100_get_set_reg_priv {
 	bool mode;
 };
 
-static int ab3100_get_set_reg_open_file(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t ab3100_get_set_reg(struct file *file,
 				  const char __user *user_buf,
 				  size_t count, loff_t *ppos)
@@ -583,7 +577,7 @@ static ssize_t ab3100_get_set_reg(struct file *file,
 }
 
 static const struct file_operations ab3100_get_set_reg_fops = {
-	.open = ab3100_get_set_reg_open_file,
+	.open = simple_open,
 	.write = ab3100_get_set_reg,
 	.llseek = noop_llseek,
 };
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index d295941c9a3d..1f08704f7ae8 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -32,6 +32,7 @@
 #define AB8500_IT_SOURCE6_REG		0x05
 #define AB8500_IT_SOURCE7_REG		0x06
 #define AB8500_IT_SOURCE8_REG		0x07
+#define AB9540_IT_SOURCE13_REG		0x0C
 #define AB8500_IT_SOURCE19_REG		0x12
 #define AB8500_IT_SOURCE20_REG		0x13
 #define AB8500_IT_SOURCE21_REG		0x14
@@ -53,6 +54,7 @@
 #define AB8500_IT_LATCH9_REG		0x28
 #define AB8500_IT_LATCH10_REG		0x29
 #define AB8500_IT_LATCH12_REG		0x2B
+#define AB9540_IT_LATCH13_REG		0x2C
 #define AB8500_IT_LATCH19_REG		0x32
 #define AB8500_IT_LATCH20_REG		0x33
 #define AB8500_IT_LATCH21_REG		0x34
@@ -90,21 +92,39 @@
 #define AB8500_IT_MASK24_REG		0x57
 
 #define AB8500_REV_REG			0x80
+#define AB8500_IC_NAME_REG		0x82
 #define AB8500_SWITCH_OFF_STATUS	0x00
 
 #define AB8500_TURN_ON_STATUS		0x00
 
+#define AB9540_MODEM_CTRL2_REG			0x23
+#define AB9540_MODEM_CTRL2_SWDBBRSTN_BIT	BIT(2)
+
 /*
  * Map interrupt numbers to the LATCH and MASK register offsets, Interrupt
- * numbers are indexed into this array with (num / 8).
+ * numbers are indexed into this array with (num / 8). The interupts are
+ * defined in linux/mfd/ab8500.h
  *
  * This is one off from the register names, i.e. AB8500_IT_MASK1_REG is at
  * offset 0.
  */
+/* AB8500 support */
 static const int ab8500_irq_regoffset[AB8500_NUM_IRQ_REGS] = {
 	0, 1, 2, 3, 4, 6, 7, 8, 9, 11, 18, 19, 20, 21,
 };
 
+/* AB9540 support */
+static const int ab9540_irq_regoffset[AB9540_NUM_IRQ_REGS] = {
+	0, 1, 2, 3, 4, 6, 7, 8, 9, 11, 18, 19, 20, 21, 12, 13, 24,
+};
+
+static const char ab8500_version_str[][7] = {
+	[AB8500_VERSION_AB8500] = "AB8500",
+	[AB8500_VERSION_AB8505] = "AB8505",
+	[AB8500_VERSION_AB9540] = "AB9540",
+	[AB8500_VERSION_AB8540] = "AB8540",
+};
+
 static int ab8500_get_chip_id(struct device *dev)
 {
 	struct ab8500 *ab8500;
@@ -127,9 +147,7 @@ static int set_register_interruptible(struct ab8500 *ab8500, u8 bank,
 
 	dev_vdbg(ab8500->dev, "wr: addr %#x <= %#x\n", addr, data);
 
-	ret = mutex_lock_interruptible(&ab8500->lock);
-	if (ret)
-		return ret;
+	mutex_lock(&ab8500->lock);
 
 	ret = ab8500->write(ab8500, addr, data);
 	if (ret < 0)
@@ -156,9 +174,7 @@ static int get_register_interruptible(struct ab8500 *ab8500, u8 bank,
 	 * bank on higher 8 bits and reg in lower */
 	u16 addr = ((u16)bank) << 8 | reg;
 
-	ret = mutex_lock_interruptible(&ab8500->lock);
-	if (ret)
-		return ret;
+	mutex_lock(&ab8500->lock);
 
 	ret = ab8500->read(ab8500, addr);
 	if (ret < 0)
@@ -185,31 +201,38 @@ static int mask_and_set_register_interruptible(struct ab8500 *ab8500, u8 bank,
 	u8 reg, u8 bitmask, u8 bitvalues)
 {
 	int ret;
-	u8 data;
 	/* put the u8 bank and u8 reg together into a an u16.
 	 * bank on higher 8 bits and reg in lower */
 	u16 addr = ((u16)bank) << 8 | reg;
 
-	ret = mutex_lock_interruptible(&ab8500->lock);
-	if (ret)
-		return ret;
+	mutex_lock(&ab8500->lock);
 
-	ret = ab8500->read(ab8500, addr);
-	if (ret < 0) {
-		dev_err(ab8500->dev, "failed to read reg %#x: %d\n",
-			addr, ret);
-		goto out;
-	}
+	if (ab8500->write_masked == NULL) {
+		u8 data;
 
-	data = (u8)ret;
-	data = (~bitmask & data) | (bitmask & bitvalues);
+		ret = ab8500->read(ab8500, addr);
+		if (ret < 0) {
+			dev_err(ab8500->dev, "failed to read reg %#x: %d\n",
+				addr, ret);
+			goto out;
+		}
 
-	ret = ab8500->write(ab8500, addr, data);
-	if (ret < 0)
-		dev_err(ab8500->dev, "failed to write reg %#x: %d\n",
-			addr, ret);
+		data = (u8)ret;
+		data = (~bitmask & data) | (bitmask & bitvalues);
+
+		ret = ab8500->write(ab8500, addr, data);
+		if (ret < 0)
+			dev_err(ab8500->dev, "failed to write reg %#x: %d\n",
+				addr, ret);
 
-	dev_vdbg(ab8500->dev, "mask: addr %#x => data %#x\n", addr, data);
+		dev_vdbg(ab8500->dev, "mask: addr %#x => data %#x\n", addr,
+			data);
+		goto out;
+	}
+	ret = ab8500->write_masked(ab8500, addr, bitmask, bitvalues);
+	if (ret < 0)
+		dev_err(ab8500->dev, "failed to modify reg %#x: %d\n", addr,
+			ret);
 out:
 	mutex_unlock(&ab8500->lock);
 	return ret;
@@ -248,7 +271,7 @@ static void ab8500_irq_sync_unlock(struct irq_data *data)
 	struct ab8500 *ab8500 = irq_data_get_irq_chip_data(data);
 	int i;
 
-	for (i = 0; i < AB8500_NUM_IRQ_REGS; i++) {
+	for (i = 0; i < ab8500->mask_size; i++) {
 		u8 old = ab8500->oldmask[i];
 		u8 new = ab8500->mask[i];
 		int reg;
@@ -256,14 +279,17 @@ static void ab8500_irq_sync_unlock(struct irq_data *data)
 		if (new == old)
 			continue;
 
-		/* Interrupt register 12 doesn't exist prior to version 2.0 */
-		if (ab8500_irq_regoffset[i] == 11 &&
-			ab8500->chip_id < AB8500_CUT2P0)
+		/*
+		 * Interrupt register 12 doesn't exist prior to AB8500 version
+		 * 2.0
+		 */
+		if (ab8500->irq_reg_offset[i] == 11 &&
+			is_ab8500_1p1_or_earlier(ab8500))
 			continue;
 
 		ab8500->oldmask[i] = new;
 
-		reg = AB8500_IT_MASK1_REG + ab8500_irq_regoffset[i];
+		reg = AB8500_IT_MASK1_REG + ab8500->irq_reg_offset[i];
 		set_register_interruptible(ab8500, AB8500_INTERRUPT, reg, new);
 	}
 
@@ -306,13 +332,16 @@ static irqreturn_t ab8500_irq(int irq, void *dev)
 
 	dev_vdbg(ab8500->dev, "interrupt\n");
 
-	for (i = 0; i < AB8500_NUM_IRQ_REGS; i++) {
-		int regoffset = ab8500_irq_regoffset[i];
+	for (i = 0; i < ab8500->mask_size; i++) {
+		int regoffset = ab8500->irq_reg_offset[i];
 		int status;
 		u8 value;
 
-		/* Interrupt register 12 doesn't exist prior to version 2.0 */
-		if (regoffset == 11 && ab8500->chip_id < AB8500_CUT2P0)
+		/*
+		 * Interrupt register 12 doesn't exist prior to AB8500 version
+		 * 2.0
+		 */
+		if (regoffset == 11 && is_ab8500_1p1_or_earlier(ab8500))
 			continue;
 
 		status = get_register_interruptible(ab8500, AB8500_INTERRUPT,
@@ -336,8 +365,16 @@ static int ab8500_irq_init(struct ab8500 *ab8500)
 {
 	int base = ab8500->irq_base;
 	int irq;
+	int num_irqs;
+
+	if (is_ab9540(ab8500))
+		num_irqs = AB9540_NR_IRQS;
+	else if (is_ab8505(ab8500))
+		num_irqs = AB8505_NR_IRQS;
+	else
+		num_irqs = AB8500_NR_IRQS;
 
-	for (irq = base; irq < base + AB8500_NR_IRQS; irq++) {
+	for (irq = base; irq < base + num_irqs; irq++) {
 		irq_set_chip_data(irq, ab8500);
 		irq_set_chip_and_handler(irq, &ab8500_irq_chip,
 					 handle_simple_irq);
@@ -356,8 +393,16 @@ static void ab8500_irq_remove(struct ab8500 *ab8500)
 {
 	int base = ab8500->irq_base;
 	int irq;
+	int num_irqs;
 
-	for (irq = base; irq < base + AB8500_NR_IRQS; irq++) {
+	if (is_ab9540(ab8500))
+		num_irqs = AB9540_NR_IRQS;
+	else if (is_ab8505(ab8500))
+		num_irqs = AB8505_NR_IRQS;
+	else
+		num_irqs = AB8500_NR_IRQS;
+
+	for (irq = base; irq < base + num_irqs; irq++) {
 #ifdef CONFIG_ARM
 		set_irq_flags(irq, 0);
 #endif
@@ -366,6 +411,7 @@ static void ab8500_irq_remove(struct ab8500 *ab8500)
 	}
 }
 
+/* AB8500 GPIO Resources */
 static struct resource __devinitdata ab8500_gpio_resources[] = {
 	{
 		.name	= "GPIO_INT6",
@@ -375,6 +421,28 @@ static struct resource __devinitdata ab8500_gpio_resources[] = {
 	}
 };
 
+/* AB9540 GPIO Resources */
+static struct resource __devinitdata ab9540_gpio_resources[] = {
+	{
+		.name	= "GPIO_INT6",
+		.start	= AB8500_INT_GPIO6R,
+		.end	= AB8500_INT_GPIO41F,
+		.flags	= IORESOURCE_IRQ,
+	},
+	{
+		.name	= "GPIO_INT14",
+		.start	= AB9540_INT_GPIO50R,
+		.end	= AB9540_INT_GPIO54R,
+		.flags	= IORESOURCE_IRQ,
+	},
+	{
+		.name	= "GPIO_INT15",
+		.start	= AB9540_INT_GPIO50F,
+		.end	= AB9540_INT_GPIO54F,
+		.flags	= IORESOURCE_IRQ,
+	}
+};
+
 static struct resource __devinitdata ab8500_gpadc_resources[] = {
 	{
 		.name	= "HW_CONV_END",
@@ -491,12 +559,6 @@ static struct resource __devinitdata ab8500_charger_resources[] = {
 		.flags = IORESOURCE_IRQ,
 	},
 	{
-		.name = "USB_CHARGE_DET_DONE",
-		.start = AB8500_INT_USB_CHG_DET_DONE,
-		.end = AB8500_INT_USB_CHG_DET_DONE,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
 		.name = "VBUS_OVV",
 		.start = AB8500_INT_VBUS_OVV,
 		.end = AB8500_INT_VBUS_OVV,
@@ -534,14 +596,8 @@ static struct resource __devinitdata ab8500_charger_resources[] = {
 	},
 	{
 		.name = "USB_CHARGER_NOT_OKR",
-		.start = AB8500_INT_USB_CHARGER_NOT_OK,
-		.end = AB8500_INT_USB_CHARGER_NOT_OK,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "USB_CHARGER_NOT_OKF",
-		.start = AB8500_INT_USB_CHARGER_NOT_OKF,
-		.end = AB8500_INT_USB_CHARGER_NOT_OKF,
+		.start = AB8500_INT_USB_CHARGER_NOT_OKR,
+		.end = AB8500_INT_USB_CHARGER_NOT_OKR,
 		.flags = IORESOURCE_IRQ,
 	},
 	{
@@ -616,6 +672,12 @@ static struct resource __devinitdata ab8500_fg_resources[] = {
 		.end = AB8500_INT_CC_INT_CALIB,
 		.flags = IORESOURCE_IRQ,
 	},
+	{
+		.name = "CCEOC",
+		.start = AB8500_INT_CCEOC,
+		.end = AB8500_INT_CCEOC,
+		.flags = IORESOURCE_IRQ,
+	},
 };
 
 static struct resource __devinitdata ab8500_chargalg_resources[] = {};
@@ -630,8 +692,8 @@ static struct resource __devinitdata ab8500_debug_resources[] = {
 	},
 	{
 		.name	= "IRQ_LAST",
-		.start	= AB8500_INT_USB_CHARGER_NOT_OKF,
-		.end	= AB8500_INT_USB_CHARGER_NOT_OKF,
+		.start	= AB8500_INT_XTAL32K_KO,
+		.end	= AB8500_INT_XTAL32K_KO,
 		.flags	= IORESOURCE_IRQ,
 	},
 };
@@ -691,7 +753,7 @@ static struct resource __devinitdata ab8500_temp_resources[] = {
 	},
 };
 
-static struct mfd_cell __devinitdata ab8500_devs[] = {
+static struct mfd_cell __devinitdata abx500_common_devs[] = {
 #ifdef CONFIG_DEBUG_FS
 	{
 		.name = "ab8500-debug",
@@ -706,11 +768,6 @@ static struct mfd_cell __devinitdata ab8500_devs[] = {
 		.name = "ab8500-regulator",
 	},
 	{
-		.name = "ab8500-gpio",
-		.num_resources = ARRAY_SIZE(ab8500_gpio_resources),
-		.resources = ab8500_gpio_resources,
-	},
-	{
 		.name = "ab8500-gpadc",
 		.num_resources = ARRAY_SIZE(ab8500_gpadc_resources),
 		.resources = ab8500_gpadc_resources,
@@ -748,11 +805,7 @@ static struct mfd_cell __devinitdata ab8500_devs[] = {
 	{
 		.name = "ab8500-codec",
 	},
-	{
-		.name = "ab8500-usb",
-		.num_resources = ARRAY_SIZE(ab8500_usb_resources),
-		.resources = ab8500_usb_resources,
-	},
+
 	{
 		.name = "ab8500-poweron-key",
 		.num_resources = ARRAY_SIZE(ab8500_poweronkey_db_resources),
@@ -781,6 +834,32 @@ static struct mfd_cell __devinitdata ab8500_devs[] = {
 	},
 };
 
+static struct mfd_cell __devinitdata ab8500_devs[] = {
+	{
+		.name = "ab8500-gpio",
+		.num_resources = ARRAY_SIZE(ab8500_gpio_resources),
+		.resources = ab8500_gpio_resources,
+	},
+	{
+		.name = "ab8500-usb",
+		.num_resources = ARRAY_SIZE(ab8500_usb_resources),
+		.resources = ab8500_usb_resources,
+	},
+};
+
+static struct mfd_cell __devinitdata ab9540_devs[] = {
+	{
+		.name = "ab8500-gpio",
+		.num_resources = ARRAY_SIZE(ab9540_gpio_resources),
+		.resources = ab9540_gpio_resources,
+	},
+	{
+		.name = "ab9540-usb",
+		.num_resources = ARRAY_SIZE(ab8500_usb_resources),
+		.resources = ab8500_usb_resources,
+	},
+};
+
 static ssize_t show_chip_id(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -842,9 +921,64 @@ static ssize_t show_turn_on_status(struct device *dev,
 	return sprintf(buf, "%#x\n", value);
 }
 
+static ssize_t show_ab9540_dbbrstn(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct ab8500 *ab8500;
+	int ret;
+	u8 value;
+
+	ab8500 = dev_get_drvdata(dev);
+
+	ret = get_register_interruptible(ab8500, AB8500_REGU_CTRL2,
+		AB9540_MODEM_CTRL2_REG, &value);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n",
+			(value & AB9540_MODEM_CTRL2_SWDBBRSTN_BIT) ? 1 : 0);
+}
+
+static ssize_t store_ab9540_dbbrstn(struct device *dev,
+	struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct ab8500 *ab8500;
+	int ret = count;
+	int err;
+	u8 bitvalues;
+
+	ab8500 = dev_get_drvdata(dev);
+
+	if (count > 0) {
+		switch (buf[0]) {
+		case '0':
+			bitvalues = 0;
+			break;
+		case '1':
+			bitvalues = AB9540_MODEM_CTRL2_SWDBBRSTN_BIT;
+			break;
+		default:
+			goto exit;
+		}
+
+		err = mask_and_set_register_interruptible(ab8500,
+			AB8500_REGU_CTRL2, AB9540_MODEM_CTRL2_REG,
+			AB9540_MODEM_CTRL2_SWDBBRSTN_BIT, bitvalues);
+		if (err)
+			dev_info(ab8500->dev,
+				"Failed to set DBBRSTN %c, err %#x\n",
+				buf[0], err);
+	}
+
+exit:
+	return ret;
+}
+
 static DEVICE_ATTR(chip_id, S_IRUGO, show_chip_id, NULL);
 static DEVICE_ATTR(switch_off_status, S_IRUGO, show_switch_off_status, NULL);
 static DEVICE_ATTR(turn_on_status, S_IRUGO, show_turn_on_status, NULL);
+static DEVICE_ATTR(dbbrstn, S_IRUGO | S_IWUSR,
+			show_ab9540_dbbrstn, store_ab9540_dbbrstn);
 
 static struct attribute *ab8500_sysfs_entries[] = {
 	&dev_attr_chip_id.attr,
@@ -853,11 +987,23 @@ static struct attribute *ab8500_sysfs_entries[] = {
 	NULL,
 };
 
+static struct attribute *ab9540_sysfs_entries[] = {
+	&dev_attr_chip_id.attr,
+	&dev_attr_switch_off_status.attr,
+	&dev_attr_turn_on_status.attr,
+	&dev_attr_dbbrstn.attr,
+	NULL,
+};
+
 static struct attribute_group ab8500_attr_group = {
 	.attrs	= ab8500_sysfs_entries,
 };
 
-int __devinit ab8500_init(struct ab8500 *ab8500)
+static struct attribute_group ab9540_attr_group = {
+	.attrs	= ab9540_sysfs_entries,
+};
+
+int __devinit ab8500_init(struct ab8500 *ab8500, enum ab8500_version version)
 {
 	struct ab8500_platform_data *plat = dev_get_platdata(ab8500->dev);
 	int ret;
@@ -870,25 +1016,45 @@ int __devinit ab8500_init(struct ab8500 *ab8500)
 	mutex_init(&ab8500->lock);
 	mutex_init(&ab8500->irq_lock);
 
+	if (version != AB8500_VERSION_UNDEFINED)
+		ab8500->version = version;
+	else {
+		ret = get_register_interruptible(ab8500, AB8500_MISC,
+			AB8500_IC_NAME_REG, &value);
+		if (ret < 0)
+			return ret;
+
+		ab8500->version = value;
+	}
+
 	ret = get_register_interruptible(ab8500, AB8500_MISC,
 		AB8500_REV_REG, &value);
 	if (ret < 0)
 		return ret;
 
-	switch (value) {
-	case AB8500_CUT1P0:
-	case AB8500_CUT1P1:
-	case AB8500_CUT2P0:
-	case AB8500_CUT3P0:
-	case AB8500_CUT3P3:
-		dev_info(ab8500->dev, "detected chip, revision: %#x\n", value);
-		break;
-	default:
-		dev_err(ab8500->dev, "unknown chip, revision: %#x\n", value);
-		return -EINVAL;
-	}
 	ab8500->chip_id = value;
 
+	dev_info(ab8500->dev, "detected chip, %s rev. %1x.%1x\n",
+			ab8500_version_str[ab8500->version],
+			ab8500->chip_id >> 4,
+			ab8500->chip_id & 0x0F);
+
+	/* Configure AB8500 or AB9540 IRQ */
+	if (is_ab9540(ab8500) || is_ab8505(ab8500)) {
+		ab8500->mask_size = AB9540_NUM_IRQ_REGS;
+		ab8500->irq_reg_offset = ab9540_irq_regoffset;
+	} else {
+		ab8500->mask_size = AB8500_NUM_IRQ_REGS;
+		ab8500->irq_reg_offset = ab8500_irq_regoffset;
+	}
+	ab8500->mask = kzalloc(ab8500->mask_size, GFP_KERNEL);
+	if (!ab8500->mask)
+		return -ENOMEM;
+	ab8500->oldmask = kzalloc(ab8500->mask_size, GFP_KERNEL);
+	if (!ab8500->oldmask) {
+		ret = -ENOMEM;
+		goto out_freemask;
+	}
 	/*
 	 * ab8500 has switched off due to (SWITCH_OFF_STATUS):
 	 * 0x01 Swoff bit programming
@@ -911,30 +1077,33 @@ int __devinit ab8500_init(struct ab8500 *ab8500)
 		plat->init(ab8500);
 
 	/* Clear and mask all interrupts */
-	for (i = 0; i < AB8500_NUM_IRQ_REGS; i++) {
-		/* Interrupt register 12 doesn't exist prior to version 2.0 */
-		if (ab8500_irq_regoffset[i] == 11 &&
-			ab8500->chip_id < AB8500_CUT2P0)
+	for (i = 0; i < ab8500->mask_size; i++) {
+		/*
+		 * Interrupt register 12 doesn't exist prior to AB8500 version
+		 * 2.0
+		 */
+		if (ab8500->irq_reg_offset[i] == 11 &&
+				is_ab8500_1p1_or_earlier(ab8500))
 			continue;
 
 		get_register_interruptible(ab8500, AB8500_INTERRUPT,
-			AB8500_IT_LATCH1_REG + ab8500_irq_regoffset[i],
+			AB8500_IT_LATCH1_REG + ab8500->irq_reg_offset[i],
 			&value);
 		set_register_interruptible(ab8500, AB8500_INTERRUPT,
-			AB8500_IT_MASK1_REG + ab8500_irq_regoffset[i], 0xff);
+			AB8500_IT_MASK1_REG + ab8500->irq_reg_offset[i], 0xff);
 	}
 
 	ret = abx500_register_ops(ab8500->dev, &ab8500_ops);
 	if (ret)
-		return ret;
+		goto out_freeoldmask;
 
-	for (i = 0; i < AB8500_NUM_IRQ_REGS; i++)
+	for (i = 0; i < ab8500->mask_size; i++)
 		ab8500->mask[i] = ab8500->oldmask[i] = 0xff;
 
 	if (ab8500->irq_base) {
 		ret = ab8500_irq_init(ab8500);
 		if (ret)
-			return ret;
+			goto out_freeoldmask;
 
 		ret = request_threaded_irq(ab8500->irq, NULL, ab8500_irq,
 					   IRQF_ONESHOT | IRQF_NO_SUSPEND,
@@ -943,17 +1112,34 @@ int __devinit ab8500_init(struct ab8500 *ab8500)
 			goto out_removeirq;
 	}
 
-	ret = mfd_add_devices(ab8500->dev, 0, ab8500_devs,
-			      ARRAY_SIZE(ab8500_devs), NULL,
+	ret = mfd_add_devices(ab8500->dev, 0, abx500_common_devs,
+			      ARRAY_SIZE(abx500_common_devs), NULL,
 			      ab8500->irq_base);
+
 	if (ret)
 		goto out_freeirq;
 
-	ret = sysfs_create_group(&ab8500->dev->kobj, &ab8500_attr_group);
+	if (is_ab9540(ab8500))
+		ret = mfd_add_devices(ab8500->dev, 0, ab9540_devs,
+			      ARRAY_SIZE(ab9540_devs), NULL,
+			      ab8500->irq_base);
+	else
+		ret = mfd_add_devices(ab8500->dev, 0, ab8500_devs,
+			      ARRAY_SIZE(ab9540_devs), NULL,
+			      ab8500->irq_base);
 	if (ret)
-		dev_err(ab8500->dev, "error creating sysfs entries\n");
+		goto out_freeirq;
 
-	return ret;
+	if (is_ab9540(ab8500))
+		ret = sysfs_create_group(&ab8500->dev->kobj,
+					&ab9540_attr_group);
+	else
+		ret = sysfs_create_group(&ab8500->dev->kobj,
+					&ab8500_attr_group);
+	if (ret)
+		dev_err(ab8500->dev, "error creating sysfs entries\n");
+	else
+		return ret;
 
 out_freeirq:
 	if (ab8500->irq_base)
@@ -961,18 +1147,27 @@ out_freeirq:
 out_removeirq:
 	if (ab8500->irq_base)
 		ab8500_irq_remove(ab8500);
+out_freeoldmask:
+	kfree(ab8500->oldmask);
+out_freemask:
+	kfree(ab8500->mask);
 
 	return ret;
 }
 
 int __devexit ab8500_exit(struct ab8500 *ab8500)
 {
-	sysfs_remove_group(&ab8500->dev->kobj, &ab8500_attr_group);
+	if (is_ab9540(ab8500))
+		sysfs_remove_group(&ab8500->dev->kobj, &ab9540_attr_group);
+	else
+		sysfs_remove_group(&ab8500->dev->kobj, &ab8500_attr_group);
 	mfd_remove_devices(ab8500->dev);
 	if (ab8500->irq_base) {
 		free_irq(ab8500->irq, ab8500);
 		ab8500_irq_remove(ab8500);
 	}
+	kfree(ab8500->oldmask);
+	kfree(ab8500->mask);
 
 	return 0;
 }
diff --git a/drivers/mfd/ab8500-i2c.c b/drivers/mfd/ab8500-i2c.c
index 087fecd71ce0..b83045f102be 100644
--- a/drivers/mfd/ab8500-i2c.c
+++ b/drivers/mfd/ab8500-i2c.c
@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/abx500/ab8500.h>
-#include <linux/mfd/db8500-prcmu.h>
+#include <linux/mfd/dbx500-prcmu.h>
 
 static int ab8500_i2c_write(struct ab8500 *ab8500, u16 addr, u8 data)
 {
@@ -23,6 +23,18 @@ static int ab8500_i2c_write(struct ab8500 *ab8500, u16 addr, u8 data)
 	return ret;
 }
 
+static int ab8500_i2c_write_masked(struct ab8500 *ab8500, u16 addr, u8 mask,
+	u8 data)
+{
+	int ret;
+
+	ret = prcmu_abb_write_masked((u8)(addr >> 8), (u8)(addr & 0xFF), &data,
+		&mask, 1);
+	if (ret < 0)
+		dev_err(ab8500->dev, "prcmu i2c error %d\n", ret);
+	return ret;
+}
+
 static int ab8500_i2c_read(struct ab8500 *ab8500, u16 addr)
 {
 	int ret;
@@ -38,6 +50,7 @@ static int ab8500_i2c_read(struct ab8500 *ab8500, u16 addr)
 
 static int __devinit ab8500_i2c_probe(struct platform_device *plf)
 {
+	const struct platform_device_id *platid = platform_get_device_id(plf);
 	struct ab8500 *ab8500;
 	struct resource *resource;
 	int ret;
@@ -58,13 +71,15 @@ static int __devinit ab8500_i2c_probe(struct platform_device *plf)
 
 	ab8500->read = ab8500_i2c_read;
 	ab8500->write = ab8500_i2c_write;
+	ab8500->write_masked = ab8500_i2c_write_masked;
 
 	platform_set_drvdata(plf, ab8500);
 
-	ret = ab8500_init(ab8500);
+	ret = ab8500_init(ab8500, platid->driver_data);
 	if (ret)
 		kfree(ab8500);
 
+
 	return ret;
 }
 
@@ -78,13 +93,22 @@ static int __devexit ab8500_i2c_remove(struct platform_device *plf)
 	return 0;
 }
 
+static const struct platform_device_id ab8500_id[] = {
+	{ "ab8500-i2c", AB8500_VERSION_AB8500 },
+	{ "ab8505-i2c", AB8500_VERSION_AB8505 },
+	{ "ab9540-i2c", AB8500_VERSION_AB9540 },
+	{ "ab8540-i2c", AB8500_VERSION_AB8540 },
+	{ }
+};
+
 static struct platform_driver ab8500_i2c_driver = {
 	.driver = {
 		.name = "ab8500-i2c",
 		.owner = THIS_MODULE,
 	},
 	.probe	= ab8500_i2c_probe,
-	.remove	= __devexit_p(ab8500_i2c_remove)
+	.remove	= __devexit_p(ab8500_i2c_remove),
+	.id_table = ab8500_id,
 };
 
 static int __init ab8500_i2c_init(void)
diff --git a/drivers/mfd/anatop-mfd.c b/drivers/mfd/anatop-mfd.c
new file mode 100644
index 000000000000..2af42480635e
--- /dev/null
+++ b/drivers/mfd/anatop-mfd.c
@@ -0,0 +1,137 @@
+/*
+ * Anatop MFD driver
+ *
+ * Copyright (C) 2012 Ying-Chun Liu (PaulLiu) <paul.liu@linaro.org>
+ * Copyright (C) 2012 Linaro
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <linux/mfd/anatop.h>
+
+u32 anatop_get_bits(struct anatop *adata, u32 addr, int bit_shift,
+		    int bit_width)
+{
+	u32 val, mask;
+
+	if (bit_width == 32)
+		mask = ~0;
+	else
+		mask = (1 << bit_width) - 1;
+
+	val = readl(adata->ioreg + addr);
+	val = (val >> bit_shift) & mask;
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(anatop_get_bits);
+
+void anatop_set_bits(struct anatop *adata, u32 addr, int bit_shift,
+		     int bit_width, u32 data)
+{
+	u32 val, mask;
+
+	if (bit_width == 32)
+		mask = ~0;
+	else
+		mask = (1 << bit_width) - 1;
+
+	spin_lock(&adata->reglock);
+	val = readl(adata->ioreg + addr) & ~(mask << bit_shift);
+	writel((data << bit_shift) | val, adata->ioreg + addr);
+	spin_unlock(&adata->reglock);
+}
+EXPORT_SYMBOL_GPL(anatop_set_bits);
+
+static const struct of_device_id of_anatop_match[] = {
+	{ .compatible = "fsl,imx6q-anatop", },
+	{ },
+};
+
+static int __devinit of_anatop_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	void *ioreg;
+	struct anatop *drvdata;
+
+	ioreg = of_iomap(np, 0);
+	if (!ioreg)
+		return -EADDRNOTAVAIL;
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+	drvdata->ioreg = ioreg;
+	spin_lock_init(&drvdata->reglock);
+	platform_set_drvdata(pdev, drvdata);
+	of_platform_populate(np, of_anatop_match, NULL, dev);
+
+	return 0;
+}
+
+static int __devexit of_anatop_remove(struct platform_device *pdev)
+{
+	struct anatop *drvdata;
+	drvdata = platform_get_drvdata(pdev);
+	iounmap(drvdata->ioreg);
+
+	return 0;
+}
+
+static struct platform_driver anatop_of_driver = {
+	.driver = {
+		.name = "anatop-mfd",
+		.owner = THIS_MODULE,
+		.of_match_table = of_anatop_match,
+	},
+	.probe		= of_anatop_probe,
+	.remove		= of_anatop_remove,
+};
+
+static int __init anatop_init(void)
+{
+	return platform_driver_register(&anatop_of_driver);
+}
+postcore_initcall(anatop_init);
+
+static void __exit anatop_exit(void)
+{
+	platform_driver_unregister(&anatop_of_driver);
+}
+module_exit(anatop_exit);
+
+MODULE_AUTHOR("Ying-Chun Liu (PaulLiu) <paul.liu@linaro.org>");
+MODULE_DESCRIPTION("ANATOP MFD driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index b85bbd7f0d19..1895cf9fab8c 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -525,6 +525,11 @@ static void asic3_gpio_set(struct gpio_chip *chip,
 	return;
 }
 
+static int asic3_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+	return (offset < ASIC3_NUM_GPIOS) ? IRQ_BOARD_START + offset : -ENXIO;
+}
+
 static __init int asic3_gpio_probe(struct platform_device *pdev,
 				   u16 *gpio_config, int num)
 {
@@ -976,6 +981,7 @@ static int __init asic3_probe(struct platform_device *pdev)
 	asic->gpio.set = asic3_gpio_set;
 	asic->gpio.direction_input = asic3_gpio_direction_input;
 	asic->gpio.direction_output = asic3_gpio_direction_output;
+	asic->gpio.to_irq = asic3_gpio_to_irq;
 
 	ret = asic3_gpio_probe(pdev,
 			       pdata->gpio_config,
diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c
index 5ddde2a9176a..7ff313fe9fb1 100644
--- a/drivers/mfd/da9052-core.c
+++ b/drivers/mfd/da9052-core.c
@@ -16,7 +16,6 @@
 #include <linux/input.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/mutex.h>
 #include <linux/mfd/core.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -647,8 +646,6 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id)
 	struct irq_desc *desc;
 	int ret;
 
-	mutex_init(&da9052->io_lock);
-
 	if (pdata && pdata->init != NULL)
 		pdata->init(da9052);
 
diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c
index 44b97c70a61f..36b88e395499 100644
--- a/drivers/mfd/da9052-i2c.c
+++ b/drivers/mfd/da9052-i2c.c
@@ -74,24 +74,27 @@ static int __devinit da9052_i2c_probe(struct i2c_client *client,
 
 	ret = da9052_i2c_enable_multiwrite(da9052);
 	if (ret < 0)
-		goto err;
+		goto err_regmap;
 
 	ret = da9052_device_init(da9052, id->driver_data);
 	if (ret != 0)
-		goto err;
+		goto err_regmap;
 
 	return 0;
 
+err_regmap:
+	regmap_exit(da9052->regmap);
 err:
 	kfree(da9052);
 	return ret;
 }
 
-static int da9052_i2c_remove(struct i2c_client *client)
+static int __devexit da9052_i2c_remove(struct i2c_client *client)
 {
 	struct da9052 *da9052 = i2c_get_clientdata(client);
 
 	da9052_device_exit(da9052);
+	regmap_exit(da9052->regmap);
 	kfree(da9052);
 
 	return 0;
@@ -107,7 +110,7 @@ static struct i2c_device_id da9052_i2c_id[] = {
 
 static struct i2c_driver da9052_i2c_driver = {
 	.probe = da9052_i2c_probe,
-	.remove = da9052_i2c_remove,
+	.remove = __devexit_p(da9052_i2c_remove),
 	.id_table = da9052_i2c_id,
 	.driver = {
 		.name = "da9052",
diff --git a/drivers/mfd/da9052-spi.c b/drivers/mfd/da9052-spi.c
index cdbc7cad326f..6faf149e8d94 100644
--- a/drivers/mfd/da9052-spi.c
+++ b/drivers/mfd/da9052-spi.c
@@ -21,7 +21,7 @@
 
 #include <linux/mfd/da9052/da9052.h>
 
-static int da9052_spi_probe(struct spi_device *spi)
+static int __devinit da9052_spi_probe(struct spi_device *spi)
 {
 	int ret;
 	const struct spi_device_id *id = spi_get_device_id(spi);
@@ -52,20 +52,23 @@ static int da9052_spi_probe(struct spi_device *spi)
 
 	ret = da9052_device_init(da9052, id->driver_data);
 	if (ret != 0)
-		goto err;
+		goto err_regmap;
 
 	return 0;
 
+err_regmap:
+	regmap_exit(da9052->regmap);
 err:
 	kfree(da9052);
 	return ret;
 }
 
-static int da9052_spi_remove(struct spi_device *spi)
+static int __devexit da9052_spi_remove(struct spi_device *spi)
 {
 	struct da9052 *da9052 = dev_get_drvdata(&spi->dev);
 
 	da9052_device_exit(da9052);
+	regmap_exit(da9052->regmap);
 	kfree(da9052);
 
 	return 0;
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index af8e0efedbe4..ebc1e8658226 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -30,6 +30,7 @@
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/regulator/db8500-prcmu.h>
 #include <linux/regulator/machine.h>
+#include <asm/hardware/gic.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/db8500-regs.h>
@@ -39,11 +40,6 @@
 /* Offset for the firmware version within the TCPM */
 #define PRCMU_FW_VERSION_OFFSET 0xA4
 
-/* PRCMU project numbers, defined by PRCMU FW */
-#define PRCMU_PROJECT_ID_8500V1_0 1
-#define PRCMU_PROJECT_ID_8500V2_0 2
-#define PRCMU_PROJECT_ID_8400V2_0 3
-
 /* Index of different voltages to be used when accessing AVSData */
 #define PRCM_AVS_BASE		0x2FC
 #define PRCM_AVS_VBB_RET	(PRCM_AVS_BASE + 0x0)
@@ -137,6 +133,8 @@
 #define PRCM_REQ_MB1_ARM_OPP			(PRCM_REQ_MB1 + 0x0)
 #define PRCM_REQ_MB1_APE_OPP			(PRCM_REQ_MB1 + 0x1)
 #define PRCM_REQ_MB1_PLL_ON_OFF			(PRCM_REQ_MB1 + 0x4)
+#define PLL_SOC0_OFF	0x1
+#define PLL_SOC0_ON	0x2
 #define PLL_SOC1_OFF	0x4
 #define PLL_SOC1_ON	0x8
 
@@ -266,6 +264,11 @@
 #define WAKEUP_BIT_GPIO7 BIT(30)
 #define WAKEUP_BIT_GPIO8 BIT(31)
 
+static struct {
+	bool valid;
+	struct prcmu_fw_version version;
+} fw_info;
+
 /*
  * This vector maps irq numbers to the bits in the bit field used in
  * communication with the PRCMU firmware.
@@ -341,11 +344,13 @@ static struct {
  * mb1_transfer - state needed for mailbox 1 communication.
  * @lock:	The transaction lock.
  * @work:	The transaction completion structure.
+ * @ape_opp:	The current APE OPP.
  * @ack:	Reply ("acknowledge") data.
  */
 static struct {
 	struct mutex lock;
 	struct completion work;
+	u8 ape_opp;
 	struct {
 		u8 header;
 		u8 arm_opp;
@@ -413,79 +418,102 @@ static struct {
 static atomic_t ac_wake_req_state = ATOMIC_INIT(0);
 
 /* Spinlocks */
+static DEFINE_SPINLOCK(prcmu_lock);
 static DEFINE_SPINLOCK(clkout_lock);
-static DEFINE_SPINLOCK(gpiocr_lock);
 
 /* Global var to runtime determine TCDM base for v2 or v1 */
 static __iomem void *tcdm_base;
 
 struct clk_mgt {
-	unsigned int offset;
+	void __iomem *reg;
 	u32 pllsw;
+	int branch;
+	bool clk38div;
+};
+
+enum {
+	PLL_RAW,
+	PLL_FIX,
+	PLL_DIV
 };
 
 static DEFINE_SPINLOCK(clk_mgt_lock);
 
-#define CLK_MGT_ENTRY(_name)[PRCMU_##_name] = { (PRCM_##_name##_MGT_OFF), 0 }
+#define CLK_MGT_ENTRY(_name, _branch, _clk38div)[PRCMU_##_name] = \
+	{ (PRCM_##_name##_MGT), 0 , _branch, _clk38div}
 struct clk_mgt clk_mgt[PRCMU_NUM_REG_CLOCKS] = {
-	CLK_MGT_ENTRY(SGACLK),
-	CLK_MGT_ENTRY(UARTCLK),
-	CLK_MGT_ENTRY(MSP02CLK),
-	CLK_MGT_ENTRY(MSP1CLK),
-	CLK_MGT_ENTRY(I2CCLK),
-	CLK_MGT_ENTRY(SDMMCCLK),
-	CLK_MGT_ENTRY(SLIMCLK),
-	CLK_MGT_ENTRY(PER1CLK),
-	CLK_MGT_ENTRY(PER2CLK),
-	CLK_MGT_ENTRY(PER3CLK),
-	CLK_MGT_ENTRY(PER5CLK),
-	CLK_MGT_ENTRY(PER6CLK),
-	CLK_MGT_ENTRY(PER7CLK),
-	CLK_MGT_ENTRY(LCDCLK),
-	CLK_MGT_ENTRY(BMLCLK),
-	CLK_MGT_ENTRY(HSITXCLK),
-	CLK_MGT_ENTRY(HSIRXCLK),
-	CLK_MGT_ENTRY(HDMICLK),
-	CLK_MGT_ENTRY(APEATCLK),
-	CLK_MGT_ENTRY(APETRACECLK),
-	CLK_MGT_ENTRY(MCDECLK),
-	CLK_MGT_ENTRY(IPI2CCLK),
-	CLK_MGT_ENTRY(DSIALTCLK),
-	CLK_MGT_ENTRY(DMACLK),
-	CLK_MGT_ENTRY(B2R2CLK),
-	CLK_MGT_ENTRY(TVCLK),
-	CLK_MGT_ENTRY(SSPCLK),
-	CLK_MGT_ENTRY(RNGCLK),
-	CLK_MGT_ENTRY(UICCCLK),
+	CLK_MGT_ENTRY(SGACLK, PLL_DIV, false),
+	CLK_MGT_ENTRY(UARTCLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(MSP02CLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(MSP1CLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(I2CCLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(SDMMCCLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(SLIMCLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(PER1CLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(PER2CLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(PER3CLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(PER5CLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(PER6CLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(PER7CLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(LCDCLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(BMLCLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(HSITXCLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(HSIRXCLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(HDMICLK, PLL_FIX, false),
+	CLK_MGT_ENTRY(APEATCLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(APETRACECLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(MCDECLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(IPI2CCLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(DSIALTCLK, PLL_FIX, false),
+	CLK_MGT_ENTRY(DMACLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(B2R2CLK, PLL_DIV, true),
+	CLK_MGT_ENTRY(TVCLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(SSPCLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(RNGCLK, PLL_FIX, true),
+	CLK_MGT_ENTRY(UICCCLK, PLL_FIX, false),
+};
+
+struct dsiclk {
+	u32 divsel_mask;
+	u32 divsel_shift;
+	u32 divsel;
+};
+
+static struct dsiclk dsiclk[2] = {
+	{
+		.divsel_mask = PRCM_DSI_PLLOUT_SEL_DSI0_PLLOUT_DIVSEL_MASK,
+		.divsel_shift = PRCM_DSI_PLLOUT_SEL_DSI0_PLLOUT_DIVSEL_SHIFT,
+		.divsel = PRCM_DSI_PLLOUT_SEL_PHI,
+	},
+	{
+		.divsel_mask = PRCM_DSI_PLLOUT_SEL_DSI1_PLLOUT_DIVSEL_MASK,
+		.divsel_shift = PRCM_DSI_PLLOUT_SEL_DSI1_PLLOUT_DIVSEL_SHIFT,
+		.divsel = PRCM_DSI_PLLOUT_SEL_PHI,
+	}
 };
 
-static struct regulator *hwacc_regulator[NUM_HW_ACC];
-static struct regulator *hwacc_ret_regulator[NUM_HW_ACC];
-
-static bool hwacc_enabled[NUM_HW_ACC];
-static bool hwacc_ret_enabled[NUM_HW_ACC];
-
-static const char *hwacc_regulator_name[NUM_HW_ACC] = {
-	[HW_ACC_SVAMMDSP]	= "hwacc-sva-mmdsp",
-	[HW_ACC_SVAPIPE]	= "hwacc-sva-pipe",
-	[HW_ACC_SIAMMDSP]	= "hwacc-sia-mmdsp",
-	[HW_ACC_SIAPIPE]	= "hwacc-sia-pipe",
-	[HW_ACC_SGA]		= "hwacc-sga",
-	[HW_ACC_B2R2]		= "hwacc-b2r2",
-	[HW_ACC_MCDE]		= "hwacc-mcde",
-	[HW_ACC_ESRAM1]		= "hwacc-esram1",
-	[HW_ACC_ESRAM2]		= "hwacc-esram2",
-	[HW_ACC_ESRAM3]		= "hwacc-esram3",
-	[HW_ACC_ESRAM4]		= "hwacc-esram4",
+struct dsiescclk {
+	u32 en;
+	u32 div_mask;
+	u32 div_shift;
 };
 
-static const char *hwacc_ret_regulator_name[NUM_HW_ACC] = {
-	[HW_ACC_SVAMMDSP]	= "hwacc-sva-mmdsp-ret",
-	[HW_ACC_SIAMMDSP]	= "hwacc-sia-mmdsp-ret",
-	[HW_ACC_ESRAM1]		= "hwacc-esram1-ret",
-	[HW_ACC_ESRAM2]		= "hwacc-esram2-ret",
-	[HW_ACC_ESRAM3]		= "hwacc-esram3-ret",
-	[HW_ACC_ESRAM4]		= "hwacc-esram4-ret",
+static struct dsiescclk dsiescclk[3] = {
+	{
+		.en = PRCM_DSITVCLK_DIV_DSI0_ESC_CLK_EN,
+		.div_mask = PRCM_DSITVCLK_DIV_DSI0_ESC_CLK_DIV_MASK,
+		.div_shift = PRCM_DSITVCLK_DIV_DSI0_ESC_CLK_DIV_SHIFT,
+	},
+	{
+		.en = PRCM_DSITVCLK_DIV_DSI1_ESC_CLK_EN,
+		.div_mask = PRCM_DSITVCLK_DIV_DSI1_ESC_CLK_DIV_MASK,
+		.div_shift = PRCM_DSITVCLK_DIV_DSI1_ESC_CLK_DIV_SHIFT,
+	},
+	{
+		.en = PRCM_DSITVCLK_DIV_DSI2_ESC_CLK_EN,
+		.div_mask = PRCM_DSITVCLK_DIV_DSI2_ESC_CLK_DIV_MASK,
+		.div_shift = PRCM_DSITVCLK_DIV_DSI2_ESC_CLK_DIV_SHIFT,
+	}
 };
 
 /*
@@ -503,9 +531,6 @@ static const char *hwacc_ret_regulator_name[NUM_HW_ACC] = {
 /* PLLDIV=12, PLLSW=4 (PLLDDR) */
 #define PRCMU_DSI_CLOCK_SETTING		0x0000008C
 
-/* PLLDIV=8, PLLSW=4 (PLLDDR) */
-#define PRCMU_DSI_CLOCK_SETTING_U8400	0x00000088
-
 /* DPI 50000000 Hz */
 #define PRCMU_DPI_CLOCK_SETTING		((1 << PRCMU_CLK_PLL_SW_SHIFT) | \
 					  (16 << PRCMU_CLK_PLL_DIV_SHIFT))
@@ -514,9 +539,6 @@ static const char *hwacc_ret_regulator_name[NUM_HW_ACC] = {
 /* D=101, N=1, R=4, SELDIV2=0 */
 #define PRCMU_PLLDSI_FREQ_SETTING	0x00040165
 
-/* D=70, N=1, R=3, SELDIV2=0 */
-#define PRCMU_PLLDSI_FREQ_SETTING_U8400	0x00030146
-
 #define PRCMU_ENABLE_PLLDSI		0x00000001
 #define PRCMU_DISABLE_PLLDSI		0x00000000
 #define PRCMU_RELEASE_RESET_DSS		0x0000400C
@@ -528,30 +550,17 @@ static const char *hwacc_ret_regulator_name[NUM_HW_ACC] = {
 
 #define PRCMU_PLLDSI_LOCKP_LOCKED	0x3
 
-static struct {
-	u8 project_number;
-	u8 api_version;
-	u8 func_version;
-	u8 errata;
-} prcmu_version;
-
-
 int db8500_prcmu_enable_dsipll(void)
 {
 	int i;
-	unsigned int plldsifreq;
 
 	/* Clear DSIPLL_RESETN */
 	writel(PRCMU_RESET_DSIPLL, PRCM_APE_RESETN_CLR);
 	/* Unclamp DSIPLL in/out */
 	writel(PRCMU_UNCLAMP_DSIPLL, PRCM_MMIP_LS_CLAMP_CLR);
 
-	if (prcmu_is_u8400())
-		plldsifreq = PRCMU_PLLDSI_FREQ_SETTING_U8400;
-	else
-		plldsifreq = PRCMU_PLLDSI_FREQ_SETTING;
 	/* Set DSI PLL FREQ */
-	writel(plldsifreq, PRCM_PLLDSI_FREQ);
+	writel(PRCMU_PLLDSI_FREQ_SETTING, PRCM_PLLDSI_FREQ);
 	writel(PRCMU_DSI_PLLOUT_SEL_SETTING, PRCM_DSI_PLLOUT_SEL);
 	/* Enable Escape clocks */
 	writel(PRCMU_ENABLE_ESCAPE_CLOCK_DIV, PRCM_DSITVCLK_DIV);
@@ -583,12 +592,6 @@ int db8500_prcmu_disable_dsipll(void)
 int db8500_prcmu_set_display_clocks(void)
 {
 	unsigned long flags;
-	unsigned int dsiclk;
-
-	if (prcmu_is_u8400())
-		dsiclk = PRCMU_DSI_CLOCK_SETTING_U8400;
-	else
-		dsiclk = PRCMU_DSI_CLOCK_SETTING;
 
 	spin_lock_irqsave(&clk_mgt_lock, flags);
 
@@ -596,7 +599,7 @@ int db8500_prcmu_set_display_clocks(void)
 	while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
 		cpu_relax();
 
-	writel(dsiclk, PRCM_HDMICLK_MGT);
+	writel(PRCMU_DSI_CLOCK_SETTING, PRCM_HDMICLK_MGT);
 	writel(PRCMU_DSI_LP_CLOCK_SETTING, PRCM_TVCLK_MGT);
 	writel(PRCMU_DPI_CLOCK_SETTING, PRCM_LCDCLK_MGT);
 
@@ -608,43 +611,41 @@ int db8500_prcmu_set_display_clocks(void)
 	return 0;
 }
 
-/**
- * prcmu_enable_spi2 - Enables pin muxing for SPI2 on OtherAlternateC1.
- */
-void prcmu_enable_spi2(void)
+u32 db8500_prcmu_read(unsigned int reg)
+{
+	return readl(_PRCMU_BASE + reg);
+}
+
+void db8500_prcmu_write(unsigned int reg, u32 value)
 {
-	u32 reg;
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpiocr_lock, flags);
-	reg = readl(PRCM_GPIOCR);
-	writel(reg | PRCM_GPIOCR_SPI2_SELECT, PRCM_GPIOCR);
-	spin_unlock_irqrestore(&gpiocr_lock, flags);
+	spin_lock_irqsave(&prcmu_lock, flags);
+	writel(value, (_PRCMU_BASE + reg));
+	spin_unlock_irqrestore(&prcmu_lock, flags);
 }
 
-/**
- * prcmu_disable_spi2 - Disables pin muxing for SPI2 on OtherAlternateC1.
- */
-void prcmu_disable_spi2(void)
+void db8500_prcmu_write_masked(unsigned int reg, u32 mask, u32 value)
 {
-	u32 reg;
+	u32 val;
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpiocr_lock, flags);
-	reg = readl(PRCM_GPIOCR);
-	writel(reg & ~PRCM_GPIOCR_SPI2_SELECT, PRCM_GPIOCR);
-	spin_unlock_irqrestore(&gpiocr_lock, flags);
+	spin_lock_irqsave(&prcmu_lock, flags);
+	val = readl(_PRCMU_BASE + reg);
+	val = ((val & ~mask) | (value & mask));
+	writel(val, (_PRCMU_BASE + reg));
+	spin_unlock_irqrestore(&prcmu_lock, flags);
 }
 
-bool prcmu_has_arm_maxopp(void)
+struct prcmu_fw_version *prcmu_get_fw_version(void)
 {
-	return (readb(tcdm_base + PRCM_AVS_VARM_MAX_OPP) &
-		PRCM_AVS_ISMODEENABLE_MASK) == PRCM_AVS_ISMODEENABLE_MASK;
+	return fw_info.valid ? &fw_info.version : NULL;
 }
 
-bool prcmu_is_u8400(void)
+bool prcmu_has_arm_maxopp(void)
 {
-	return prcmu_version.project_number == PRCMU_PROJECT_ID_8400V2_0;
+	return (readb(tcdm_base + PRCM_AVS_VARM_MAX_OPP) &
+		PRCM_AVS_ISMODEENABLE_MASK) == PRCM_AVS_ISMODEENABLE_MASK;
 }
 
 /**
@@ -787,6 +788,124 @@ int db8500_prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll)
 	return 0;
 }
 
+u8 db8500_prcmu_get_power_state_result(void)
+{
+	return readb(tcdm_base + PRCM_ACK_MB0_AP_PWRSTTR_STATUS);
+}
+
+/* This function decouple the gic from the prcmu */
+int db8500_prcmu_gic_decouple(void)
+{
+	u32 val = readl(PRCM_A9_MASK_REQ);
+
+	/* Set bit 0 register value to 1 */
+	writel(val | PRCM_A9_MASK_REQ_PRCM_A9_MASK_REQ,
+	       PRCM_A9_MASK_REQ);
+
+	/* Make sure the register is updated */
+	readl(PRCM_A9_MASK_REQ);
+
+	/* Wait a few cycles for the gic mask completion */
+	udelay(1);
+
+	return 0;
+}
+
+/* This function recouple the gic with the prcmu */
+int db8500_prcmu_gic_recouple(void)
+{
+	u32 val = readl(PRCM_A9_MASK_REQ);
+
+	/* Set bit 0 register value to 0 */
+	writel(val & ~PRCM_A9_MASK_REQ_PRCM_A9_MASK_REQ, PRCM_A9_MASK_REQ);
+
+	return 0;
+}
+
+#define PRCMU_GIC_NUMBER_REGS 5
+
+/*
+ * This function checks if there are pending irq on the gic. It only
+ * makes sense if the gic has been decoupled before with the
+ * db8500_prcmu_gic_decouple function. Disabling an interrupt only
+ * disables the forwarding of the interrupt to any CPU interface. It
+ * does not prevent the interrupt from changing state, for example
+ * becoming pending, or active and pending if it is already
+ * active. Hence, we have to check the interrupt is pending *and* is
+ * active.
+ */
+bool db8500_prcmu_gic_pending_irq(void)
+{
+	u32 pr; /* Pending register */
+	u32 er; /* Enable register */
+	void __iomem *dist_base = __io_address(U8500_GIC_DIST_BASE);
+	int i;
+
+        /* 5 registers. STI & PPI not skipped */
+	for (i = 0; i < PRCMU_GIC_NUMBER_REGS; i++) {
+
+		pr = readl_relaxed(dist_base + GIC_DIST_PENDING_SET + i * 4);
+		er = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+		if (pr & er)
+			return true; /* There is a pending interrupt */
+	}
+
+	return false;
+}
+
+/*
+ * This function checks if there are pending interrupt on the
+ * prcmu which has been delegated to monitor the irqs with the
+ * db8500_prcmu_copy_gic_settings function.
+ */
+bool db8500_prcmu_pending_irq(void)
+{
+	u32 it, im;
+	int i;
+
+	for (i = 0; i < PRCMU_GIC_NUMBER_REGS - 1; i++) {
+		it = readl(PRCM_ARMITVAL31TO0 + i * 4);
+		im = readl(PRCM_ARMITMSK31TO0 + i * 4);
+		if (it & im)
+			return true; /* There is a pending interrupt */
+	}
+
+	return false;
+}
+
+/*
+ * This function checks if the specified cpu is in in WFI. It's usage
+ * makes sense only if the gic is decoupled with the db8500_prcmu_gic_decouple
+ * function. Of course passing smp_processor_id() to this function will
+ * always return false...
+ */
+bool db8500_prcmu_is_cpu_in_wfi(int cpu)
+{
+	return readl(PRCM_ARM_WFI_STANDBY) & cpu ? PRCM_ARM_WFI_STANDBY_WFI1 :
+		     PRCM_ARM_WFI_STANDBY_WFI0;
+}
+
+/*
+ * This function copies the gic SPI settings to the prcmu in order to
+ * monitor them and abort/finish the retention/off sequence or state.
+ */
+int db8500_prcmu_copy_gic_settings(void)
+{
+	u32 er; /* Enable register */
+	void __iomem *dist_base = __io_address(U8500_GIC_DIST_BASE);
+	int i;
+
+        /* We skip the STI and PPI */
+	for (i = 0; i < PRCMU_GIC_NUMBER_REGS - 1; i++) {
+		er = readl_relaxed(dist_base +
+				   GIC_DIST_ENABLE_SET + (i + 1) * 4);
+		writel(er, PRCM_ARMITMSK31TO0 + i * 4);
+	}
+
+	return 0;
+}
+
 /* This function should only be called while mb0_transfer.lock is held. */
 static void config_wakeups(void)
 {
@@ -909,23 +1028,23 @@ int db8500_prcmu_get_arm_opp(void)
 }
 
 /**
- * prcmu_get_ddr_opp - get the current DDR OPP
+ * db8500_prcmu_get_ddr_opp - get the current DDR OPP
  *
  * Returns: the current DDR OPP
  */
-int prcmu_get_ddr_opp(void)
+int db8500_prcmu_get_ddr_opp(void)
 {
 	return readb(PRCM_DDR_SUBSYS_APE_MINBW);
 }
 
 /**
- * set_ddr_opp - set the appropriate DDR OPP
+ * db8500_set_ddr_opp - set the appropriate DDR OPP
  * @opp: The new DDR operating point to which transition is to be made
  * Returns: 0 on success, non-zero on failure
  *
  * This function sets the operating point of the DDR.
  */
-int prcmu_set_ddr_opp(u8 opp)
+int db8500_prcmu_set_ddr_opp(u8 opp)
 {
 	if (opp < DDR_100_OPP || opp > DDR_25_OPP)
 		return -EINVAL;
@@ -935,25 +1054,82 @@ int prcmu_set_ddr_opp(u8 opp)
 
 	return 0;
 }
+
+/* Divide the frequency of certain clocks by 2 for APE_50_PARTLY_25_OPP. */
+static void request_even_slower_clocks(bool enable)
+{
+	void __iomem *clock_reg[] = {
+		PRCM_ACLK_MGT,
+		PRCM_DMACLK_MGT
+	};
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&clk_mgt_lock, flags);
+
+	/* Grab the HW semaphore. */
+	while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
+		cpu_relax();
+
+	for (i = 0; i < ARRAY_SIZE(clock_reg); i++) {
+		u32 val;
+		u32 div;
+
+		val = readl(clock_reg[i]);
+		div = (val & PRCM_CLK_MGT_CLKPLLDIV_MASK);
+		if (enable) {
+			if ((div <= 1) || (div > 15)) {
+				pr_err("prcmu: Bad clock divider %d in %s\n",
+					div, __func__);
+				goto unlock_and_return;
+			}
+			div <<= 1;
+		} else {
+			if (div <= 2)
+				goto unlock_and_return;
+			div >>= 1;
+		}
+		val = ((val & ~PRCM_CLK_MGT_CLKPLLDIV_MASK) |
+			(div & PRCM_CLK_MGT_CLKPLLDIV_MASK));
+		writel(val, clock_reg[i]);
+	}
+
+unlock_and_return:
+	/* Release the HW semaphore. */
+	writel(0, PRCM_SEM);
+
+	spin_unlock_irqrestore(&clk_mgt_lock, flags);
+}
+
 /**
- * set_ape_opp - set the appropriate APE OPP
+ * db8500_set_ape_opp - set the appropriate APE OPP
  * @opp: The new APE operating point to which transition is to be made
  * Returns: 0 on success, non-zero on failure
  *
  * This function sets the operating point of the APE.
  */
-int prcmu_set_ape_opp(u8 opp)
+int db8500_prcmu_set_ape_opp(u8 opp)
 {
 	int r = 0;
 
+	if (opp == mb1_transfer.ape_opp)
+		return 0;
+
 	mutex_lock(&mb1_transfer.lock);
 
+	if (mb1_transfer.ape_opp == APE_50_PARTLY_25_OPP)
+		request_even_slower_clocks(false);
+
+	if ((opp != APE_100_OPP) && (mb1_transfer.ape_opp != APE_100_OPP))
+		goto skip_message;
+
 	while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
 		cpu_relax();
 
 	writeb(MB1H_ARM_APE_OPP, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
 	writeb(ARM_NO_CHANGE, (tcdm_base + PRCM_REQ_MB1_ARM_OPP));
-	writeb(opp, (tcdm_base + PRCM_REQ_MB1_APE_OPP));
+	writeb(((opp == APE_50_PARTLY_25_OPP) ? APE_50_OPP : opp),
+		(tcdm_base + PRCM_REQ_MB1_APE_OPP));
 
 	writel(MBOX_BIT(1), PRCM_MBOX_CPU_SET);
 	wait_for_completion(&mb1_transfer.work);
@@ -962,17 +1138,24 @@ int prcmu_set_ape_opp(u8 opp)
 		(mb1_transfer.ack.ape_opp != opp))
 		r = -EIO;
 
+skip_message:
+	if ((!r && (opp == APE_50_PARTLY_25_OPP)) ||
+		(r && (mb1_transfer.ape_opp == APE_50_PARTLY_25_OPP)))
+		request_even_slower_clocks(true);
+	if (!r)
+		mb1_transfer.ape_opp = opp;
+
 	mutex_unlock(&mb1_transfer.lock);
 
 	return r;
 }
 
 /**
- * prcmu_get_ape_opp - get the current APE OPP
+ * db8500_prcmu_get_ape_opp - get the current APE OPP
  *
  * Returns: the current APE OPP
  */
-int prcmu_get_ape_opp(void)
+int db8500_prcmu_get_ape_opp(void)
 {
 	return readb(tcdm_base + PRCM_ACK_MB1_CURRENT_APE_OPP);
 }
@@ -1056,7 +1239,9 @@ static int request_pll(u8 clock, bool enable)
 {
 	int r = 0;
 
-	if (clock == PRCMU_PLLSOC1)
+	if (clock == PRCMU_PLLSOC0)
+		clock = (enable ? PLL_SOC0_ON : PLL_SOC0_OFF);
+	else if (clock == PRCMU_PLLSOC1)
 		clock = (enable ? PLL_SOC1_ON : PLL_SOC1_OFF);
 	else
 		return -EINVAL;
@@ -1081,132 +1266,6 @@ static int request_pll(u8 clock, bool enable)
 }
 
 /**
- * prcmu_set_hwacc - set the power state of a h/w accelerator
- * @hwacc_dev: The hardware accelerator (enum hw_acc_dev).
- * @state: The new power state (enum hw_acc_state).
- *
- * This function sets the power state of a hardware accelerator.
- * This function should not be called from interrupt context.
- *
- * NOTE! Deprecated, to be removed when all users switched over to use the
- * regulator framework API.
- */
-int prcmu_set_hwacc(u16 hwacc_dev, u8 state)
-{
-	int r = 0;
-	bool ram_retention = false;
-	bool enable, enable_ret;
-
-	/* check argument */
-	BUG_ON(hwacc_dev >= NUM_HW_ACC);
-
-	/* get state of switches */
-	enable = hwacc_enabled[hwacc_dev];
-	enable_ret = hwacc_ret_enabled[hwacc_dev];
-
-	/* set flag if retention is possible */
-	switch (hwacc_dev) {
-	case HW_ACC_SVAMMDSP:
-	case HW_ACC_SIAMMDSP:
-	case HW_ACC_ESRAM1:
-	case HW_ACC_ESRAM2:
-	case HW_ACC_ESRAM3:
-	case HW_ACC_ESRAM4:
-		ram_retention = true;
-		break;
-	}
-
-	/* check argument */
-	BUG_ON(state > HW_ON);
-	BUG_ON(state == HW_OFF_RAMRET && !ram_retention);
-
-	/* modify enable flags */
-	switch (state) {
-	case HW_OFF:
-		enable_ret = false;
-		enable = false;
-		break;
-	case HW_ON:
-		enable = true;
-		break;
-	case HW_OFF_RAMRET:
-		enable_ret = true;
-		enable = false;
-		break;
-	}
-
-	/* get regulator (lazy) */
-	if (hwacc_regulator[hwacc_dev] == NULL) {
-		hwacc_regulator[hwacc_dev] = regulator_get(NULL,
-			hwacc_regulator_name[hwacc_dev]);
-		if (IS_ERR(hwacc_regulator[hwacc_dev])) {
-			pr_err("prcmu: failed to get supply %s\n",
-				hwacc_regulator_name[hwacc_dev]);
-			r = PTR_ERR(hwacc_regulator[hwacc_dev]);
-			goto out;
-		}
-	}
-
-	if (ram_retention) {
-		if (hwacc_ret_regulator[hwacc_dev] == NULL) {
-			hwacc_ret_regulator[hwacc_dev] = regulator_get(NULL,
-				hwacc_ret_regulator_name[hwacc_dev]);
-			if (IS_ERR(hwacc_ret_regulator[hwacc_dev])) {
-				pr_err("prcmu: failed to get supply %s\n",
-					hwacc_ret_regulator_name[hwacc_dev]);
-				r = PTR_ERR(hwacc_ret_regulator[hwacc_dev]);
-				goto out;
-			}
-		}
-	}
-
-	/* set regulators */
-	if (ram_retention) {
-		if (enable_ret && !hwacc_ret_enabled[hwacc_dev]) {
-			r = regulator_enable(hwacc_ret_regulator[hwacc_dev]);
-			if (r < 0) {
-				pr_err("prcmu_set_hwacc: ret enable failed\n");
-				goto out;
-			}
-			hwacc_ret_enabled[hwacc_dev] = true;
-		}
-	}
-
-	if (enable && !hwacc_enabled[hwacc_dev]) {
-		r = regulator_enable(hwacc_regulator[hwacc_dev]);
-		if (r < 0) {
-			pr_err("prcmu_set_hwacc: enable failed\n");
-			goto out;
-		}
-		hwacc_enabled[hwacc_dev] = true;
-	}
-
-	if (!enable && hwacc_enabled[hwacc_dev]) {
-		r = regulator_disable(hwacc_regulator[hwacc_dev]);
-		if (r < 0) {
-			pr_err("prcmu_set_hwacc: disable failed\n");
-			goto out;
-		}
-		hwacc_enabled[hwacc_dev] = false;
-	}
-
-	if (ram_retention) {
-		if (!enable_ret && hwacc_ret_enabled[hwacc_dev]) {
-			r = regulator_disable(hwacc_ret_regulator[hwacc_dev]);
-			if (r < 0) {
-				pr_err("prcmu_set_hwacc: ret disable failed\n");
-				goto out;
-			}
-			hwacc_ret_enabled[hwacc_dev] = false;
-		}
-	}
-
-out:
-	return r;
-}
-EXPORT_SYMBOL(prcmu_set_hwacc);
-
-/**
  * db8500_prcmu_set_epod - set the state of a EPOD (power domain)
  * @epod_id: The EPOD to set
  * @epod_state: The new EPOD state
@@ -1375,7 +1434,7 @@ static int request_timclk(bool enable)
 	return 0;
 }
 
-static int request_reg_clock(u8 clock, bool enable)
+static int request_clock(u8 clock, bool enable)
 {
 	u32 val;
 	unsigned long flags;
@@ -1386,14 +1445,14 @@ static int request_reg_clock(u8 clock, bool enable)
 	while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
 		cpu_relax();
 
-	val = readl(_PRCMU_BASE + clk_mgt[clock].offset);
+	val = readl(clk_mgt[clock].reg);
 	if (enable) {
 		val |= (PRCM_CLK_MGT_CLKEN | clk_mgt[clock].pllsw);
 	} else {
 		clk_mgt[clock].pllsw = (val & PRCM_CLK_MGT_CLKPLLSW_MASK);
 		val &= ~(PRCM_CLK_MGT_CLKEN | PRCM_CLK_MGT_CLKPLLSW_MASK);
 	}
-	writel(val, (_PRCMU_BASE + clk_mgt[clock].offset));
+	writel(val, clk_mgt[clock].reg);
 
 	/* Release the HW semaphore. */
 	writel(0, PRCM_SEM);
@@ -1413,7 +1472,7 @@ static int request_sga_clock(u8 clock, bool enable)
 		writel(val | PRCM_CGATING_BYPASS_ICN2, PRCM_CGATING_BYPASS);
 	}
 
-	ret = request_reg_clock(clock, enable);
+	ret = request_clock(clock, enable);
 
 	if (!ret && !enable) {
 		val = readl(PRCM_CGATING_BYPASS);
@@ -1423,6 +1482,78 @@ static int request_sga_clock(u8 clock, bool enable)
 	return ret;
 }
 
+static inline bool plldsi_locked(void)
+{
+	return (readl(PRCM_PLLDSI_LOCKP) &
+		(PRCM_PLLDSI_LOCKP_PRCM_PLLDSI_LOCKP10 |
+		 PRCM_PLLDSI_LOCKP_PRCM_PLLDSI_LOCKP3)) ==
+		(PRCM_PLLDSI_LOCKP_PRCM_PLLDSI_LOCKP10 |
+		 PRCM_PLLDSI_LOCKP_PRCM_PLLDSI_LOCKP3);
+}
+
+static int request_plldsi(bool enable)
+{
+	int r = 0;
+	u32 val;
+
+	writel((PRCM_MMIP_LS_CLAMP_DSIPLL_CLAMP |
+		PRCM_MMIP_LS_CLAMP_DSIPLL_CLAMPI), (enable ?
+		PRCM_MMIP_LS_CLAMP_CLR : PRCM_MMIP_LS_CLAMP_SET));
+
+	val = readl(PRCM_PLLDSI_ENABLE);
+	if (enable)
+		val |= PRCM_PLLDSI_ENABLE_PRCM_PLLDSI_ENABLE;
+	else
+		val &= ~PRCM_PLLDSI_ENABLE_PRCM_PLLDSI_ENABLE;
+	writel(val, PRCM_PLLDSI_ENABLE);
+
+	if (enable) {
+		unsigned int i;
+		bool locked = plldsi_locked();
+
+		for (i = 10; !locked && (i > 0); --i) {
+			udelay(100);
+			locked = plldsi_locked();
+		}
+		if (locked) {
+			writel(PRCM_APE_RESETN_DSIPLL_RESETN,
+				PRCM_APE_RESETN_SET);
+		} else {
+			writel((PRCM_MMIP_LS_CLAMP_DSIPLL_CLAMP |
+				PRCM_MMIP_LS_CLAMP_DSIPLL_CLAMPI),
+				PRCM_MMIP_LS_CLAMP_SET);
+			val &= ~PRCM_PLLDSI_ENABLE_PRCM_PLLDSI_ENABLE;
+			writel(val, PRCM_PLLDSI_ENABLE);
+			r = -EAGAIN;
+		}
+	} else {
+		writel(PRCM_APE_RESETN_DSIPLL_RESETN, PRCM_APE_RESETN_CLR);
+	}
+	return r;
+}
+
+static int request_dsiclk(u8 n, bool enable)
+{
+	u32 val;
+
+	val = readl(PRCM_DSI_PLLOUT_SEL);
+	val &= ~dsiclk[n].divsel_mask;
+	val |= ((enable ? dsiclk[n].divsel : PRCM_DSI_PLLOUT_SEL_OFF) <<
+		dsiclk[n].divsel_shift);
+	writel(val, PRCM_DSI_PLLOUT_SEL);
+	return 0;
+}
+
+static int request_dsiescclk(u8 n, bool enable)
+{
+	u32 val;
+
+	val = readl(PRCM_DSITVCLK_DIV);
+	enable ? (val |= dsiescclk[n].en) : (val &= ~dsiescclk[n].en);
+	writel(val, PRCM_DSITVCLK_DIV);
+	return 0;
+}
+
 /**
  * db8500_prcmu_request_clock() - Request for a clock to be enabled or disabled.
  * @clock:      The clock for which the request is made.
@@ -1433,21 +1564,435 @@ static int request_sga_clock(u8 clock, bool enable)
  */
 int db8500_prcmu_request_clock(u8 clock, bool enable)
 {
-	switch(clock) {
-	case PRCMU_SGACLK:
+	if (clock == PRCMU_SGACLK)
 		return request_sga_clock(clock, enable);
-	case PRCMU_TIMCLK:
+	else if (clock < PRCMU_NUM_REG_CLOCKS)
+		return request_clock(clock, enable);
+	else if (clock == PRCMU_TIMCLK)
 		return request_timclk(enable);
-	case PRCMU_SYSCLK:
+	else if ((clock == PRCMU_DSI0CLK) || (clock == PRCMU_DSI1CLK))
+		return request_dsiclk((clock - PRCMU_DSI0CLK), enable);
+	else if ((PRCMU_DSI0ESCCLK <= clock) && (clock <= PRCMU_DSI2ESCCLK))
+		return request_dsiescclk((clock - PRCMU_DSI0ESCCLK), enable);
+	else if (clock == PRCMU_PLLDSI)
+		return request_plldsi(enable);
+	else if (clock == PRCMU_SYSCLK)
 		return request_sysclk(enable);
-	case PRCMU_PLLSOC1:
+	else if ((clock == PRCMU_PLLSOC0) || (clock == PRCMU_PLLSOC1))
 		return request_pll(clock, enable);
+	else
+		return -EINVAL;
+}
+
+static unsigned long pll_rate(void __iomem *reg, unsigned long src_rate,
+	int branch)
+{
+	u64 rate;
+	u32 val;
+	u32 d;
+	u32 div = 1;
+
+	val = readl(reg);
+
+	rate = src_rate;
+	rate *= ((val & PRCM_PLL_FREQ_D_MASK) >> PRCM_PLL_FREQ_D_SHIFT);
+
+	d = ((val & PRCM_PLL_FREQ_N_MASK) >> PRCM_PLL_FREQ_N_SHIFT);
+	if (d > 1)
+		div *= d;
+
+	d = ((val & PRCM_PLL_FREQ_R_MASK) >> PRCM_PLL_FREQ_R_SHIFT);
+	if (d > 1)
+		div *= d;
+
+	if (val & PRCM_PLL_FREQ_SELDIV2)
+		div *= 2;
+
+	if ((branch == PLL_FIX) || ((branch == PLL_DIV) &&
+		(val & PRCM_PLL_FREQ_DIV2EN) &&
+		((reg == PRCM_PLLSOC0_FREQ) ||
+		 (reg == PRCM_PLLDDR_FREQ))))
+		div *= 2;
+
+	(void)do_div(rate, div);
+
+	return (unsigned long)rate;
+}
+
+#define ROOT_CLOCK_RATE 38400000
+
+static unsigned long clock_rate(u8 clock)
+{
+	u32 val;
+	u32 pllsw;
+	unsigned long rate = ROOT_CLOCK_RATE;
+
+	val = readl(clk_mgt[clock].reg);
+
+	if (val & PRCM_CLK_MGT_CLK38) {
+		if (clk_mgt[clock].clk38div && (val & PRCM_CLK_MGT_CLK38DIV))
+			rate /= 2;
+		return rate;
+	}
+
+	val |= clk_mgt[clock].pllsw;
+	pllsw = (val & PRCM_CLK_MGT_CLKPLLSW_MASK);
+
+	if (pllsw == PRCM_CLK_MGT_CLKPLLSW_SOC0)
+		rate = pll_rate(PRCM_PLLSOC0_FREQ, rate, clk_mgt[clock].branch);
+	else if (pllsw == PRCM_CLK_MGT_CLKPLLSW_SOC1)
+		rate = pll_rate(PRCM_PLLSOC1_FREQ, rate, clk_mgt[clock].branch);
+	else if (pllsw == PRCM_CLK_MGT_CLKPLLSW_DDR)
+		rate = pll_rate(PRCM_PLLDDR_FREQ, rate, clk_mgt[clock].branch);
+	else
+		return 0;
+
+	if ((clock == PRCMU_SGACLK) &&
+		(val & PRCM_SGACLK_MGT_SGACLKDIV_BY_2_5_EN)) {
+		u64 r = (rate * 10);
+
+		(void)do_div(r, 25);
+		return (unsigned long)r;
+	}
+	val &= PRCM_CLK_MGT_CLKPLLDIV_MASK;
+	if (val)
+		return rate / val;
+	else
+		return 0;
+}
+
+static unsigned long dsiclk_rate(u8 n)
+{
+	u32 divsel;
+	u32 div = 1;
+
+	divsel = readl(PRCM_DSI_PLLOUT_SEL);
+	divsel = ((divsel & dsiclk[n].divsel_mask) >> dsiclk[n].divsel_shift);
+
+	if (divsel == PRCM_DSI_PLLOUT_SEL_OFF)
+		divsel = dsiclk[n].divsel;
+
+	switch (divsel) {
+	case PRCM_DSI_PLLOUT_SEL_PHI_4:
+		div *= 2;
+	case PRCM_DSI_PLLOUT_SEL_PHI_2:
+		div *= 2;
+	case PRCM_DSI_PLLOUT_SEL_PHI:
+		return pll_rate(PRCM_PLLDSI_FREQ, clock_rate(PRCMU_HDMICLK),
+			PLL_RAW) / div;
 	default:
-		break;
+		return 0;
+	}
+}
+
+static unsigned long dsiescclk_rate(u8 n)
+{
+	u32 div;
+
+	div = readl(PRCM_DSITVCLK_DIV);
+	div = ((div & dsiescclk[n].div_mask) >> (dsiescclk[n].div_shift));
+	return clock_rate(PRCMU_TVCLK) / max((u32)1, div);
+}
+
+unsigned long prcmu_clock_rate(u8 clock)
+{
+	if (clock < PRCMU_NUM_REG_CLOCKS)
+		return clock_rate(clock);
+	else if (clock == PRCMU_TIMCLK)
+		return ROOT_CLOCK_RATE / 16;
+	else if (clock == PRCMU_SYSCLK)
+		return ROOT_CLOCK_RATE;
+	else if (clock == PRCMU_PLLSOC0)
+		return pll_rate(PRCM_PLLSOC0_FREQ, ROOT_CLOCK_RATE, PLL_RAW);
+	else if (clock == PRCMU_PLLSOC1)
+		return pll_rate(PRCM_PLLSOC1_FREQ, ROOT_CLOCK_RATE, PLL_RAW);
+	else if (clock == PRCMU_PLLDDR)
+		return pll_rate(PRCM_PLLDDR_FREQ, ROOT_CLOCK_RATE, PLL_RAW);
+	else if (clock == PRCMU_PLLDSI)
+		return pll_rate(PRCM_PLLDSI_FREQ, clock_rate(PRCMU_HDMICLK),
+			PLL_RAW);
+	else if ((clock == PRCMU_DSI0CLK) || (clock == PRCMU_DSI1CLK))
+		return dsiclk_rate(clock - PRCMU_DSI0CLK);
+	else if ((PRCMU_DSI0ESCCLK <= clock) && (clock <= PRCMU_DSI2ESCCLK))
+		return dsiescclk_rate(clock - PRCMU_DSI0ESCCLK);
+	else
+		return 0;
+}
+
+static unsigned long clock_source_rate(u32 clk_mgt_val, int branch)
+{
+	if (clk_mgt_val & PRCM_CLK_MGT_CLK38)
+		return ROOT_CLOCK_RATE;
+	clk_mgt_val &= PRCM_CLK_MGT_CLKPLLSW_MASK;
+	if (clk_mgt_val == PRCM_CLK_MGT_CLKPLLSW_SOC0)
+		return pll_rate(PRCM_PLLSOC0_FREQ, ROOT_CLOCK_RATE, branch);
+	else if (clk_mgt_val == PRCM_CLK_MGT_CLKPLLSW_SOC1)
+		return pll_rate(PRCM_PLLSOC1_FREQ, ROOT_CLOCK_RATE, branch);
+	else if (clk_mgt_val == PRCM_CLK_MGT_CLKPLLSW_DDR)
+		return pll_rate(PRCM_PLLDDR_FREQ, ROOT_CLOCK_RATE, branch);
+	else
+		return 0;
+}
+
+static u32 clock_divider(unsigned long src_rate, unsigned long rate)
+{
+	u32 div;
+
+	div = (src_rate / rate);
+	if (div == 0)
+		return 1;
+	if (rate < (src_rate / div))
+		div++;
+	return div;
+}
+
+static long round_clock_rate(u8 clock, unsigned long rate)
+{
+	u32 val;
+	u32 div;
+	unsigned long src_rate;
+	long rounded_rate;
+
+	val = readl(clk_mgt[clock].reg);
+	src_rate = clock_source_rate((val | clk_mgt[clock].pllsw),
+		clk_mgt[clock].branch);
+	div = clock_divider(src_rate, rate);
+	if (val & PRCM_CLK_MGT_CLK38) {
+		if (clk_mgt[clock].clk38div) {
+			if (div > 2)
+				div = 2;
+		} else {
+			div = 1;
+		}
+	} else if ((clock == PRCMU_SGACLK) && (div == 3)) {
+		u64 r = (src_rate * 10);
+
+		(void)do_div(r, 25);
+		if (r <= rate)
+			return (unsigned long)r;
+	}
+	rounded_rate = (src_rate / min(div, (u32)31));
+
+	return rounded_rate;
+}
+
+#define MIN_PLL_VCO_RATE 600000000ULL
+#define MAX_PLL_VCO_RATE 1680640000ULL
+
+static long round_plldsi_rate(unsigned long rate)
+{
+	long rounded_rate = 0;
+	unsigned long src_rate;
+	unsigned long rem;
+	u32 r;
+
+	src_rate = clock_rate(PRCMU_HDMICLK);
+	rem = rate;
+
+	for (r = 7; (rem > 0) && (r > 0); r--) {
+		u64 d;
+
+		d = (r * rate);
+		(void)do_div(d, src_rate);
+		if (d < 6)
+			d = 6;
+		else if (d > 255)
+			d = 255;
+		d *= src_rate;
+		if (((2 * d) < (r * MIN_PLL_VCO_RATE)) ||
+			((r * MAX_PLL_VCO_RATE) < (2 * d)))
+			continue;
+		(void)do_div(d, r);
+		if (rate < d) {
+			if (rounded_rate == 0)
+				rounded_rate = (long)d;
+			break;
+		}
+		if ((rate - d) < rem) {
+			rem = (rate - d);
+			rounded_rate = (long)d;
+		}
+	}
+	return rounded_rate;
+}
+
+static long round_dsiclk_rate(unsigned long rate)
+{
+	u32 div;
+	unsigned long src_rate;
+	long rounded_rate;
+
+	src_rate = pll_rate(PRCM_PLLDSI_FREQ, clock_rate(PRCMU_HDMICLK),
+		PLL_RAW);
+	div = clock_divider(src_rate, rate);
+	rounded_rate = (src_rate / ((div > 2) ? 4 : div));
+
+	return rounded_rate;
+}
+
+static long round_dsiescclk_rate(unsigned long rate)
+{
+	u32 div;
+	unsigned long src_rate;
+	long rounded_rate;
+
+	src_rate = clock_rate(PRCMU_TVCLK);
+	div = clock_divider(src_rate, rate);
+	rounded_rate = (src_rate / min(div, (u32)255));
+
+	return rounded_rate;
+}
+
+long prcmu_round_clock_rate(u8 clock, unsigned long rate)
+{
+	if (clock < PRCMU_NUM_REG_CLOCKS)
+		return round_clock_rate(clock, rate);
+	else if (clock == PRCMU_PLLDSI)
+		return round_plldsi_rate(rate);
+	else if ((clock == PRCMU_DSI0CLK) || (clock == PRCMU_DSI1CLK))
+		return round_dsiclk_rate(rate);
+	else if ((PRCMU_DSI0ESCCLK <= clock) && (clock <= PRCMU_DSI2ESCCLK))
+		return round_dsiescclk_rate(rate);
+	else
+		return (long)prcmu_clock_rate(clock);
+}
+
+static void set_clock_rate(u8 clock, unsigned long rate)
+{
+	u32 val;
+	u32 div;
+	unsigned long src_rate;
+	unsigned long flags;
+
+	spin_lock_irqsave(&clk_mgt_lock, flags);
+
+	/* Grab the HW semaphore. */
+	while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
+		cpu_relax();
+
+	val = readl(clk_mgt[clock].reg);
+	src_rate = clock_source_rate((val | clk_mgt[clock].pllsw),
+		clk_mgt[clock].branch);
+	div = clock_divider(src_rate, rate);
+	if (val & PRCM_CLK_MGT_CLK38) {
+		if (clk_mgt[clock].clk38div) {
+			if (div > 1)
+				val |= PRCM_CLK_MGT_CLK38DIV;
+			else
+				val &= ~PRCM_CLK_MGT_CLK38DIV;
+		}
+	} else if (clock == PRCMU_SGACLK) {
+		val &= ~(PRCM_CLK_MGT_CLKPLLDIV_MASK |
+			PRCM_SGACLK_MGT_SGACLKDIV_BY_2_5_EN);
+		if (div == 3) {
+			u64 r = (src_rate * 10);
+
+			(void)do_div(r, 25);
+			if (r <= rate) {
+				val |= PRCM_SGACLK_MGT_SGACLKDIV_BY_2_5_EN;
+				div = 0;
+			}
+		}
+		val |= min(div, (u32)31);
+	} else {
+		val &= ~PRCM_CLK_MGT_CLKPLLDIV_MASK;
+		val |= min(div, (u32)31);
+	}
+	writel(val, clk_mgt[clock].reg);
+
+	/* Release the HW semaphore. */
+	writel(0, PRCM_SEM);
+
+	spin_unlock_irqrestore(&clk_mgt_lock, flags);
+}
+
+static int set_plldsi_rate(unsigned long rate)
+{
+	unsigned long src_rate;
+	unsigned long rem;
+	u32 pll_freq = 0;
+	u32 r;
+
+	src_rate = clock_rate(PRCMU_HDMICLK);
+	rem = rate;
+
+	for (r = 7; (rem > 0) && (r > 0); r--) {
+		u64 d;
+		u64 hwrate;
+
+		d = (r * rate);
+		(void)do_div(d, src_rate);
+		if (d < 6)
+			d = 6;
+		else if (d > 255)
+			d = 255;
+		hwrate = (d * src_rate);
+		if (((2 * hwrate) < (r * MIN_PLL_VCO_RATE)) ||
+			((r * MAX_PLL_VCO_RATE) < (2 * hwrate)))
+			continue;
+		(void)do_div(hwrate, r);
+		if (rate < hwrate) {
+			if (pll_freq == 0)
+				pll_freq = (((u32)d << PRCM_PLL_FREQ_D_SHIFT) |
+					(r << PRCM_PLL_FREQ_R_SHIFT));
+			break;
+		}
+		if ((rate - hwrate) < rem) {
+			rem = (rate - hwrate);
+			pll_freq = (((u32)d << PRCM_PLL_FREQ_D_SHIFT) |
+				(r << PRCM_PLL_FREQ_R_SHIFT));
+		}
 	}
+	if (pll_freq == 0)
+		return -EINVAL;
+
+	pll_freq |= (1 << PRCM_PLL_FREQ_N_SHIFT);
+	writel(pll_freq, PRCM_PLLDSI_FREQ);
+
+	return 0;
+}
+
+static void set_dsiclk_rate(u8 n, unsigned long rate)
+{
+	u32 val;
+	u32 div;
+
+	div = clock_divider(pll_rate(PRCM_PLLDSI_FREQ,
+			clock_rate(PRCMU_HDMICLK), PLL_RAW), rate);
+
+	dsiclk[n].divsel = (div == 1) ? PRCM_DSI_PLLOUT_SEL_PHI :
+			   (div == 2) ? PRCM_DSI_PLLOUT_SEL_PHI_2 :
+			   /* else */	PRCM_DSI_PLLOUT_SEL_PHI_4;
+
+	val = readl(PRCM_DSI_PLLOUT_SEL);
+	val &= ~dsiclk[n].divsel_mask;
+	val |= (dsiclk[n].divsel << dsiclk[n].divsel_shift);
+	writel(val, PRCM_DSI_PLLOUT_SEL);
+}
+
+static void set_dsiescclk_rate(u8 n, unsigned long rate)
+{
+	u32 val;
+	u32 div;
+
+	div = clock_divider(clock_rate(PRCMU_TVCLK), rate);
+	val = readl(PRCM_DSITVCLK_DIV);
+	val &= ~dsiescclk[n].div_mask;
+	val |= (min(div, (u32)255) << dsiescclk[n].div_shift);
+	writel(val, PRCM_DSITVCLK_DIV);
+}
+
+int prcmu_set_clock_rate(u8 clock, unsigned long rate)
+{
 	if (clock < PRCMU_NUM_REG_CLOCKS)
-		return request_reg_clock(clock, enable);
-	return -EINVAL;
+		set_clock_rate(clock, rate);
+	else if (clock == PRCMU_PLLDSI)
+		return set_plldsi_rate(rate);
+	else if ((clock == PRCMU_DSI0CLK) || (clock == PRCMU_DSI1CLK))
+		set_dsiclk_rate((clock - PRCMU_DSI0CLK), rate);
+	else if ((PRCMU_DSI0ESCCLK <= clock) && (clock <= PRCMU_DSI2ESCCLK))
+		set_dsiescclk_rate((clock - PRCMU_DSI0ESCCLK), rate);
+	return 0;
 }
 
 int db8500_prcmu_config_esram0_deep_sleep(u8 state)
@@ -1476,7 +2021,7 @@ int db8500_prcmu_config_esram0_deep_sleep(u8 state)
 	return 0;
 }
 
-int prcmu_config_hotdog(u8 threshold)
+int db8500_prcmu_config_hotdog(u8 threshold)
 {
 	mutex_lock(&mb4_transfer.lock);
 
@@ -1494,7 +2039,7 @@ int prcmu_config_hotdog(u8 threshold)
 	return 0;
 }
 
-int prcmu_config_hotmon(u8 low, u8 high)
+int db8500_prcmu_config_hotmon(u8 low, u8 high)
 {
 	mutex_lock(&mb4_transfer.lock);
 
@@ -1533,7 +2078,7 @@ static int config_hot_period(u16 val)
 	return 0;
 }
 
-int prcmu_start_temp_sense(u16 cycles32k)
+int db8500_prcmu_start_temp_sense(u16 cycles32k)
 {
 	if (cycles32k == 0xFFFF)
 		return -EINVAL;
@@ -1541,7 +2086,7 @@ int prcmu_start_temp_sense(u16 cycles32k)
 	return config_hot_period(cycles32k);
 }
 
-int prcmu_stop_temp_sense(void)
+int db8500_prcmu_stop_temp_sense(void)
 {
 	return config_hot_period(0xFFFF);
 }
@@ -1570,7 +2115,7 @@ static int prcmu_a9wdog(u8 cmd, u8 d0, u8 d1, u8 d2, u8 d3)
 
 }
 
-int prcmu_config_a9wdog(u8 num, bool sleep_auto_off)
+int db8500_prcmu_config_a9wdog(u8 num, bool sleep_auto_off)
 {
 	BUG_ON(num == 0 || num > 0xf);
 	return prcmu_a9wdog(MB4H_A9WDOG_CONF, num, 0, 0,
@@ -1578,17 +2123,17 @@ int prcmu_config_a9wdog(u8 num, bool sleep_auto_off)
 			    A9WDOG_AUTO_OFF_DIS);
 }
 
-int prcmu_enable_a9wdog(u8 id)
+int db8500_prcmu_enable_a9wdog(u8 id)
 {
 	return prcmu_a9wdog(MB4H_A9WDOG_EN, id, 0, 0, 0);
 }
 
-int prcmu_disable_a9wdog(u8 id)
+int db8500_prcmu_disable_a9wdog(u8 id)
 {
 	return prcmu_a9wdog(MB4H_A9WDOG_DIS, id, 0, 0, 0);
 }
 
-int prcmu_kick_a9wdog(u8 id)
+int db8500_prcmu_kick_a9wdog(u8 id)
 {
 	return prcmu_a9wdog(MB4H_A9WDOG_KICK, id, 0, 0, 0);
 }
@@ -1596,16 +2141,8 @@ int prcmu_kick_a9wdog(u8 id)
 /*
  * timeout is 28 bit, in ms.
  */
-#define MAX_WATCHDOG_TIMEOUT 131000
-int prcmu_load_a9wdog(u8 id, u32 timeout)
+int db8500_prcmu_load_a9wdog(u8 id, u32 timeout)
 {
-	if (timeout > MAX_WATCHDOG_TIMEOUT)
-		/*
-		 * Due to calculation bug in prcmu fw, timeouts
-		 * can't be bigger than 131 seconds.
-		 */
-		return -EINVAL;
-
 	return prcmu_a9wdog(MB4H_A9WDOG_LOAD,
 			    (id & A9WDOG_ID_MASK) |
 			    /*
@@ -1619,41 +2156,6 @@ int prcmu_load_a9wdog(u8 id, u32 timeout)
 }
 
 /**
- * prcmu_set_clock_divider() - Configure the clock divider.
- * @clock:	The clock for which the request is made.
- * @divider:	The clock divider. (< 32)
- *
- * This function should only be used by the clock implementation.
- * Do not use it from any other place!
- */
-int prcmu_set_clock_divider(u8 clock, u8 divider)
-{
-	u32 val;
-	unsigned long flags;
-
-	if ((clock >= PRCMU_NUM_REG_CLOCKS) || (divider < 1) || (31 < divider))
-		return -EINVAL;
-
-	spin_lock_irqsave(&clk_mgt_lock, flags);
-
-	/* Grab the HW semaphore. */
-	while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
-		cpu_relax();
-
-	val = readl(_PRCMU_BASE + clk_mgt[clock].offset);
-	val &= ~(PRCM_CLK_MGT_CLKPLLDIV_MASK);
-	val |= (u32)divider;
-	writel(val, (_PRCMU_BASE + clk_mgt[clock].offset));
-
-	/* Release the HW semaphore. */
-	writel(0, PRCM_SEM);
-
-	spin_unlock_irqrestore(&clk_mgt_lock, flags);
-
-	return 0;
-}
-
-/**
  * prcmu_abb_read() - Read register value(s) from the ABB.
  * @slave:	The I2C slave address.
  * @reg:	The (start) register address.
@@ -1675,6 +2177,7 @@ int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
 	while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
 		cpu_relax();
 
+	writeb(0, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB5));
 	writeb(PRCMU_I2C_READ(slave), (tcdm_base + PRCM_REQ_MB5_I2C_SLAVE_OP));
 	writeb(PRCMU_I2C_STOP_EN, (tcdm_base + PRCM_REQ_MB5_I2C_HW_BITS));
 	writeb(reg, (tcdm_base + PRCM_REQ_MB5_I2C_REG));
@@ -1700,16 +2203,19 @@ int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
 }
 
 /**
- * prcmu_abb_write() - Write register value(s) to the ABB.
+ * prcmu_abb_write_masked() - Write masked register value(s) to the ABB.
  * @slave:	The I2C slave address.
  * @reg:	The (start) register address.
  * @value:	The value(s) to write.
+ * @mask:	The mask(s) to use.
  * @size:	The number of registers to write.
  *
- * Reads register value(s) from the ABB.
+ * Writes masked register value(s) to the ABB.
+ * For each @value, only the bits set to 1 in the corresponding @mask
+ * will be written. The other bits are not changed.
  * @size has to be 1 for the current firmware version.
  */
-int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
+int prcmu_abb_write_masked(u8 slave, u8 reg, u8 *value, u8 *mask, u8 size)
 {
 	int r;
 
@@ -1721,6 +2227,7 @@ int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
 	while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
 		cpu_relax();
 
+	writeb(~*mask, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB5));
 	writeb(PRCMU_I2C_WRITE(slave), (tcdm_base + PRCM_REQ_MB5_I2C_SLAVE_OP));
 	writeb(PRCMU_I2C_STOP_EN, (tcdm_base + PRCM_REQ_MB5_I2C_HW_BITS));
 	writeb(reg, (tcdm_base + PRCM_REQ_MB5_I2C_REG));
@@ -1743,6 +2250,23 @@ int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
 }
 
 /**
+ * prcmu_abb_write() - Write register value(s) to the ABB.
+ * @slave:	The I2C slave address.
+ * @reg:	The (start) register address.
+ * @value:	The value(s) to write.
+ * @size:	The number of registers to write.
+ *
+ * Writes register value(s) to the ABB.
+ * @size has to be 1 for the current firmware version.
+ */
+int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
+{
+	u8 mask = ~0;
+
+	return prcmu_abb_write_masked(slave, reg, value, &mask, size);
+}
+
+/**
  * prcmu_ac_wake_req - should be called whenever ARM wants to wakeup Modem
  */
 void prcmu_ac_wake_req(void)
@@ -1850,9 +2374,9 @@ u16 db8500_prcmu_get_reset_code(void)
 }
 
 /**
- * prcmu_reset_modem - ask the PRCMU to reset modem
+ * db8500_prcmu_reset_modem - ask the PRCMU to reset modem
  */
-void prcmu_modem_reset(void)
+void db8500_prcmu_modem_reset(void)
 {
 	mutex_lock(&mb1_transfer.lock);
 
@@ -2099,6 +2623,26 @@ static struct irq_chip prcmu_irq_chip = {
 	.irq_unmask	= prcmu_irq_unmask,
 };
 
+static char *fw_project_name(u8 project)
+{
+	switch (project) {
+	case PRCMU_FW_PROJECT_U8500:
+		return "U8500";
+	case PRCMU_FW_PROJECT_U8500_C2:
+		return "U8500 C2";
+	case PRCMU_FW_PROJECT_U9500:
+		return "U9500";
+	case PRCMU_FW_PROJECT_U9500_C2:
+		return "U9500 C2";
+	case PRCMU_FW_PROJECT_U8520:
+		return "U8520";
+	case PRCMU_FW_PROJECT_U8420:
+		return "U8420";
+	default:
+		return "Unknown";
+	}
+}
+
 void __init db8500_prcmu_early_init(void)
 {
 	unsigned int i;
@@ -2108,11 +2652,13 @@ void __init db8500_prcmu_early_init(void)
 		if (tcpm_base != NULL) {
 			u32 version;
 			version = readl(tcpm_base + PRCMU_FW_VERSION_OFFSET);
-			prcmu_version.project_number = version & 0xFF;
-			prcmu_version.api_version = (version >> 8) & 0xFF;
-			prcmu_version.func_version = (version >> 16) & 0xFF;
-			prcmu_version.errata = (version >> 24) & 0xFF;
-			pr_info("PRCMU firmware version %d.%d.%d\n",
+			fw_info.version.project = version & 0xFF;
+			fw_info.version.api_version = (version >> 8) & 0xFF;
+			fw_info.version.func_version = (version >> 16) & 0xFF;
+			fw_info.version.errata = (version >> 24) & 0xFF;
+			fw_info.valid = true;
+			pr_info("PRCMU firmware: %s, version %d.%d.%d\n",
+				fw_project_name(fw_info.version.project),
 				(version >> 8) & 0xFF, (version >> 16) & 0xFF,
 				(version >> 24) & 0xFF);
 			iounmap(tcpm_base);
@@ -2130,6 +2676,7 @@ void __init db8500_prcmu_early_init(void)
 	init_completion(&mb0_transfer.ac_wake_work);
 	mutex_init(&mb1_transfer.lock);
 	init_completion(&mb1_transfer.work);
+	mb1_transfer.ape_opp = APE_NO_CHANGE;
 	mutex_init(&mb2_transfer.lock);
 	init_completion(&mb2_transfer.work);
 	spin_lock_init(&mb2_transfer.auto_pm_lock);
@@ -2154,7 +2701,7 @@ void __init db8500_prcmu_early_init(void)
 	}
 }
 
-static void __init db8500_prcmu_init_clkforce(void)
+static void __init init_prcm_registers(void)
 {
 	u32 val;
 
@@ -2186,19 +2733,17 @@ static struct regulator_consumer_supply db8500_vape_consumers[] = {
 	REGULATOR_SUPPLY("vcore", "uart1"),
 	REGULATOR_SUPPLY("vcore", "uart2"),
 	REGULATOR_SUPPLY("v-ape", "nmk-ske-keypad.0"),
+	REGULATOR_SUPPLY("v-hsi", "ste_hsi.0"),
 };
 
 static struct regulator_consumer_supply db8500_vsmps2_consumers[] = {
-	/* CG2900 and CW1200 power to off-chip peripherals */
-	REGULATOR_SUPPLY("gbf_1v8", "cg2900-uart.0"),
-	REGULATOR_SUPPLY("wlan_1v8", "cw1200.0"),
 	REGULATOR_SUPPLY("musb_1v8", "ab8500-usb.0"),
 	/* AV8100 regulator */
 	REGULATOR_SUPPLY("hdmi_1v8", "0-0070"),
 };
 
 static struct regulator_consumer_supply db8500_b2r2_mcde_consumers[] = {
-	REGULATOR_SUPPLY("vsupply", "b2r2.0"),
+	REGULATOR_SUPPLY("vsupply", "b2r2_bus"),
 	REGULATOR_SUPPLY("vsupply", "mcde"),
 };
 
@@ -2235,6 +2780,7 @@ static struct regulator_consumer_supply db8500_esram12_consumers[] = {
 static struct regulator_consumer_supply db8500_esram34_consumers[] = {
 	REGULATOR_SUPPLY("v-esram34", "mcde"),
 	REGULATOR_SUPPLY("esram34", "cm_control"),
+	REGULATOR_SUPPLY("lcla_esram", "dma40.0"),
 };
 
 static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
@@ -2291,7 +2837,7 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
 		},
 	},
 	[DB8500_REGULATOR_SWITCH_SVAMMDSP] = {
-		.supply_regulator = "db8500-vape",
+		/* dependency to u8500-vape is handled outside regulator framework */
 		.constraints = {
 			.name = "db8500-sva-mmdsp",
 			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
@@ -2307,7 +2853,7 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
 		},
 	},
 	[DB8500_REGULATOR_SWITCH_SVAPIPE] = {
-		.supply_regulator = "db8500-vape",
+		/* dependency to u8500-vape is handled outside regulator framework */
 		.constraints = {
 			.name = "db8500-sva-pipe",
 			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
@@ -2316,7 +2862,7 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
 		.num_consumer_supplies = ARRAY_SIZE(db8500_svapipe_consumers),
 	},
 	[DB8500_REGULATOR_SWITCH_SIAMMDSP] = {
-		.supply_regulator = "db8500-vape",
+		/* dependency to u8500-vape is handled outside regulator framework */
 		.constraints = {
 			.name = "db8500-sia-mmdsp",
 			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
@@ -2331,7 +2877,7 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
 		},
 	},
 	[DB8500_REGULATOR_SWITCH_SIAPIPE] = {
-		.supply_regulator = "db8500-vape",
+		/* dependency to u8500-vape is handled outside regulator framework */
 		.constraints = {
 			.name = "db8500-sia-pipe",
 			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
@@ -2359,7 +2905,10 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
 		.num_consumer_supplies = ARRAY_SIZE(db8500_b2r2_mcde_consumers),
 	},
 	[DB8500_REGULATOR_SWITCH_ESRAM12] = {
-		.supply_regulator = "db8500-vape",
+		/*
+		 * esram12 is set in retention and supplied by Vsafe when Vape is off,
+		 * no need to hold Vape
+		 */
 		.constraints = {
 			.name = "db8500-esram12",
 			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
@@ -2374,7 +2923,10 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
 		},
 	},
 	[DB8500_REGULATOR_SWITCH_ESRAM34] = {
-		.supply_regulator = "db8500-vape",
+		/*
+		 * esram34 is set in retention and supplied by Vsafe when Vape is off,
+		 * no need to hold Vape
+		 */
 		.constraints = {
 			.name = "db8500-esram34",
 			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
@@ -2412,7 +2964,7 @@ static int __init db8500_prcmu_probe(struct platform_device *pdev)
 	if (ux500_is_svp())
 		return -ENODEV;
 
-	db8500_prcmu_init_clkforce();
+	init_prcm_registers();
 
 	/* Clean up the mailbox interrupts after pre-kernel code. */
 	writel(ALL_MBOX_BITS, PRCM_ARM_IT1_CLR);
diff --git a/drivers/mfd/dbx500-prcmu-regs.h b/drivers/mfd/dbx500-prcmu-regs.h
index ec22e9f15d32..3a0bf91d7780 100644
--- a/drivers/mfd/dbx500-prcmu-regs.h
+++ b/drivers/mfd/dbx500-prcmu-regs.h
@@ -17,41 +17,41 @@
 
 #define BITS(_start, _end) ((BIT(_end) - BIT(_start)) + BIT(_end))
 
-#define PRCM_SVACLK_MGT_OFF		0x008
-#define PRCM_SIACLK_MGT_OFF		0x00C
-#define PRCM_SGACLK_MGT_OFF		0x014
-#define PRCM_UARTCLK_MGT_OFF		0x018
-#define PRCM_MSP02CLK_MGT_OFF		0x01C
-#define PRCM_I2CCLK_MGT_OFF		0x020
-#define PRCM_SDMMCCLK_MGT_OFF		0x024
-#define PRCM_SLIMCLK_MGT_OFF		0x028
-#define PRCM_PER1CLK_MGT_OFF		0x02C
-#define PRCM_PER2CLK_MGT_OFF		0x030
-#define PRCM_PER3CLK_MGT_OFF		0x034
-#define PRCM_PER5CLK_MGT_OFF		0x038
-#define PRCM_PER6CLK_MGT_OFF		0x03C
-#define PRCM_PER7CLK_MGT_OFF		0x040
-#define PRCM_PWMCLK_MGT_OFF		0x044 /* for DB5500 */
-#define PRCM_IRDACLK_MGT_OFF		0x048 /* for DB5500 */
-#define PRCM_IRRCCLK_MGT_OFF		0x04C /* for DB5500 */
-#define PRCM_LCDCLK_MGT_OFF		0x044
-#define PRCM_BMLCLK_MGT_OFF		0x04C
-#define PRCM_HSITXCLK_MGT_OFF		0x050
-#define PRCM_HSIRXCLK_MGT_OFF		0x054
-#define PRCM_HDMICLK_MGT_OFF		0x058
-#define PRCM_APEATCLK_MGT_OFF		0x05C
-#define PRCM_APETRACECLK_MGT_OFF	0x060
-#define PRCM_MCDECLK_MGT_OFF		0x064
-#define PRCM_IPI2CCLK_MGT_OFF		0x068
-#define PRCM_DSIALTCLK_MGT_OFF		0x06C
-#define PRCM_DMACLK_MGT_OFF		0x074
-#define PRCM_B2R2CLK_MGT_OFF		0x078
-#define PRCM_TVCLK_MGT_OFF		0x07C
-#define PRCM_UNIPROCLK_MGT_OFF		0x278
-#define PRCM_SSPCLK_MGT_OFF		0x280
-#define PRCM_RNGCLK_MGT_OFF		0x284
-#define PRCM_UICCCLK_MGT_OFF		0x27C
-#define PRCM_MSP1CLK_MGT_OFF		0x288
+#define PRCM_CLK_MGT(_offset) (void __iomem *)(IO_ADDRESS(U8500_PRCMU_BASE) \
+	+ _offset)
+#define PRCM_ACLK_MGT		PRCM_CLK_MGT(0x004)
+#define PRCM_SVACLK_MGT		PRCM_CLK_MGT(0x008)
+#define PRCM_SIACLK_MGT		PRCM_CLK_MGT(0x00C)
+#define PRCM_SGACLK_MGT		PRCM_CLK_MGT(0x014)
+#define PRCM_UARTCLK_MGT	PRCM_CLK_MGT(0x018)
+#define PRCM_MSP02CLK_MGT	PRCM_CLK_MGT(0x01C)
+#define PRCM_I2CCLK_MGT		PRCM_CLK_MGT(0x020)
+#define PRCM_SDMMCCLK_MGT	PRCM_CLK_MGT(0x024)
+#define PRCM_SLIMCLK_MGT	PRCM_CLK_MGT(0x028)
+#define PRCM_PER1CLK_MGT	PRCM_CLK_MGT(0x02C)
+#define PRCM_PER2CLK_MGT	PRCM_CLK_MGT(0x030)
+#define PRCM_PER3CLK_MGT	PRCM_CLK_MGT(0x034)
+#define PRCM_PER5CLK_MGT	PRCM_CLK_MGT(0x038)
+#define PRCM_PER6CLK_MGT	PRCM_CLK_MGT(0x03C)
+#define PRCM_PER7CLK_MGT	PRCM_CLK_MGT(0x040)
+#define PRCM_LCDCLK_MGT		PRCM_CLK_MGT(0x044)
+#define PRCM_BMLCLK_MGT		PRCM_CLK_MGT(0x04C)
+#define PRCM_HSITXCLK_MGT	PRCM_CLK_MGT(0x050)
+#define PRCM_HSIRXCLK_MGT	PRCM_CLK_MGT(0x054)
+#define PRCM_HDMICLK_MGT	PRCM_CLK_MGT(0x058)
+#define PRCM_APEATCLK_MGT	PRCM_CLK_MGT(0x05C)
+#define PRCM_APETRACECLK_MGT	PRCM_CLK_MGT(0x060)
+#define PRCM_MCDECLK_MGT	PRCM_CLK_MGT(0x064)
+#define PRCM_IPI2CCLK_MGT	PRCM_CLK_MGT(0x068)
+#define PRCM_DSIALTCLK_MGT	PRCM_CLK_MGT(0x06C)
+#define PRCM_DMACLK_MGT		PRCM_CLK_MGT(0x074)
+#define PRCM_B2R2CLK_MGT	PRCM_CLK_MGT(0x078)
+#define PRCM_TVCLK_MGT		PRCM_CLK_MGT(0x07C)
+#define PRCM_UNIPROCLK_MGT	PRCM_CLK_MGT(0x278)
+#define PRCM_SSPCLK_MGT		PRCM_CLK_MGT(0x280)
+#define PRCM_RNGCLK_MGT		PRCM_CLK_MGT(0x284)
+#define PRCM_UICCCLK_MGT	PRCM_CLK_MGT(0x27C)
+#define PRCM_MSP1CLK_MGT	PRCM_CLK_MGT(0x288)
 
 #define PRCM_ARM_PLLDIVPS	(_PRCMU_BASE + 0x118)
 #define PRCM_ARM_PLLDIVPS_ARM_BRM_RATE		0x3f
@@ -79,6 +79,8 @@
 
 /* ARM WFI Standby signal register */
 #define PRCM_ARM_WFI_STANDBY    (_PRCMU_BASE + 0x130)
+#define PRCM_ARM_WFI_STANDBY_WFI0               0x08
+#define PRCM_ARM_WFI_STANDBY_WFI1               0x10
 #define PRCM_IOCR		(_PRCMU_BASE + 0x310)
 #define PRCM_IOCR_IOFORCE			0x1
 
@@ -131,20 +133,58 @@
 #define PRCM_MMIP_LS_CLAMP_SET     (_PRCMU_BASE + 0x420)
 #define PRCM_MMIP_LS_CLAMP_CLR     (_PRCMU_BASE + 0x424)
 
+#define PRCM_MMIP_LS_CLAMP_DSIPLL_CLAMP		BIT(11)
+#define PRCM_MMIP_LS_CLAMP_DSIPLL_CLAMPI	BIT(22)
+
 /* PRCMU clock/PLL/reset registers */
+#define PRCM_PLLSOC0_FREQ	   (_PRCMU_BASE + 0x080)
+#define PRCM_PLLSOC1_FREQ	   (_PRCMU_BASE + 0x084)
+#define PRCM_PLLDDR_FREQ	   (_PRCMU_BASE + 0x08C)
+#define PRCM_PLL_FREQ_D_SHIFT	0
+#define PRCM_PLL_FREQ_D_MASK	BITS(0, 7)
+#define PRCM_PLL_FREQ_N_SHIFT	8
+#define PRCM_PLL_FREQ_N_MASK	BITS(8, 13)
+#define PRCM_PLL_FREQ_R_SHIFT	16
+#define PRCM_PLL_FREQ_R_MASK	BITS(16, 18)
+#define PRCM_PLL_FREQ_SELDIV2	BIT(24)
+#define PRCM_PLL_FREQ_DIV2EN	BIT(25)
+
 #define PRCM_PLLDSI_FREQ           (_PRCMU_BASE + 0x500)
 #define PRCM_PLLDSI_ENABLE         (_PRCMU_BASE + 0x504)
 #define PRCM_PLLDSI_LOCKP          (_PRCMU_BASE + 0x508)
-#define PRCM_LCDCLK_MGT            (_PRCMU_BASE + PRCM_LCDCLK_MGT_OFF)
-#define PRCM_MCDECLK_MGT           (_PRCMU_BASE + PRCM_MCDECLK_MGT_OFF)
-#define PRCM_HDMICLK_MGT           (_PRCMU_BASE + PRCM_HDMICLK_MGT_OFF)
-#define PRCM_TVCLK_MGT             (_PRCMU_BASE + PRCM_TVCLK_MGT_OFF)
 #define PRCM_DSI_PLLOUT_SEL        (_PRCMU_BASE + 0x530)
 #define PRCM_DSITVCLK_DIV          (_PRCMU_BASE + 0x52C)
 #define PRCM_PLLDSI_LOCKP          (_PRCMU_BASE + 0x508)
 #define PRCM_APE_RESETN_SET        (_PRCMU_BASE + 0x1E4)
 #define PRCM_APE_RESETN_CLR        (_PRCMU_BASE + 0x1E8)
 
+#define PRCM_PLLDSI_ENABLE_PRCM_PLLDSI_ENABLE BIT(0)
+
+#define PRCM_PLLDSI_LOCKP_PRCM_PLLDSI_LOCKP10	BIT(0)
+#define PRCM_PLLDSI_LOCKP_PRCM_PLLDSI_LOCKP3	BIT(1)
+
+#define PRCM_DSI_PLLOUT_SEL_DSI0_PLLOUT_DIVSEL_SHIFT	0
+#define PRCM_DSI_PLLOUT_SEL_DSI0_PLLOUT_DIVSEL_MASK	BITS(0, 2)
+#define PRCM_DSI_PLLOUT_SEL_DSI1_PLLOUT_DIVSEL_SHIFT	8
+#define PRCM_DSI_PLLOUT_SEL_DSI1_PLLOUT_DIVSEL_MASK	BITS(8, 10)
+
+#define PRCM_DSI_PLLOUT_SEL_OFF		0
+#define PRCM_DSI_PLLOUT_SEL_PHI		1
+#define PRCM_DSI_PLLOUT_SEL_PHI_2	2
+#define PRCM_DSI_PLLOUT_SEL_PHI_4	3
+
+#define PRCM_DSITVCLK_DIV_DSI0_ESC_CLK_DIV_SHIFT	0
+#define PRCM_DSITVCLK_DIV_DSI0_ESC_CLK_DIV_MASK		BITS(0, 7)
+#define PRCM_DSITVCLK_DIV_DSI1_ESC_CLK_DIV_SHIFT	8
+#define PRCM_DSITVCLK_DIV_DSI1_ESC_CLK_DIV_MASK		BITS(8, 15)
+#define PRCM_DSITVCLK_DIV_DSI2_ESC_CLK_DIV_SHIFT	16
+#define PRCM_DSITVCLK_DIV_DSI2_ESC_CLK_DIV_MASK		BITS(16, 23)
+#define PRCM_DSITVCLK_DIV_DSI0_ESC_CLK_EN		BIT(24)
+#define PRCM_DSITVCLK_DIV_DSI1_ESC_CLK_EN		BIT(25)
+#define PRCM_DSITVCLK_DIV_DSI2_ESC_CLK_EN		BIT(26)
+
+#define PRCM_APE_RESETN_DSIPLL_RESETN BIT(14)
+
 #define PRCM_CLKOCR		   (_PRCMU_BASE + 0x1CC)
 #define PRCM_CLKOCR_CLKOUT0_REF_CLK	(1 << 0)
 #define PRCM_CLKOCR_CLKOUT0_MASK	BITS(0, 13)
@@ -183,9 +223,15 @@
 #define PRCM_CLKOCR_CLKOSEL1_MASK	BITS(22, 24)
 #define PRCM_CLKOCR_CLK1TYPE		BIT(28)
 
-#define PRCM_CLK_MGT_CLKPLLDIV_MASK	BITS(0, 4)
-#define PRCM_CLK_MGT_CLKPLLSW_MASK	BITS(5, 7)
-#define PRCM_CLK_MGT_CLKEN		BIT(8)
+#define PRCM_CLK_MGT_CLKPLLDIV_MASK		BITS(0, 4)
+#define PRCM_CLK_MGT_CLKPLLSW_SOC0		BIT(5)
+#define PRCM_CLK_MGT_CLKPLLSW_SOC1		BIT(6)
+#define PRCM_CLK_MGT_CLKPLLSW_DDR		BIT(7)
+#define PRCM_CLK_MGT_CLKPLLSW_MASK		BITS(5, 7)
+#define PRCM_CLK_MGT_CLKEN			BIT(8)
+#define PRCM_CLK_MGT_CLK38			BIT(9)
+#define PRCM_CLK_MGT_CLK38DIV			BIT(11)
+#define PRCM_SGACLK_MGT_SGACLKDIV_BY_2_5_EN	BIT(12)
 
 /* GPIOCR register */
 #define PRCM_GPIOCR_SPI2_SELECT BIT(23)
diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c
index 7122386b4e3c..9fd4f63c45cc 100644
--- a/drivers/mfd/mc13xxx-core.c
+++ b/drivers/mfd/mc13xxx-core.c
@@ -560,6 +560,8 @@ EXPORT_SYMBOL(mc13xxx_get_flags);
 
 #define MC13XXX_ADC1_CHAN0_SHIFT	5
 #define MC13XXX_ADC1_CHAN1_SHIFT	8
+#define MC13783_ADC1_ATO_SHIFT		11
+#define MC13783_ADC1_ATOX		(1 << 19)
 
 struct mc13xxx_adcdone_data {
 	struct mc13xxx *mc13xxx;
@@ -580,7 +582,8 @@ static irqreturn_t mc13xxx_handler_adcdone(int irq, void *data)
 #define MC13XXX_ADC_WORKING (1 << 0)
 
 int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode,
-		unsigned int channel, unsigned int *sample)
+		unsigned int channel, u8 ato, bool atox,
+		unsigned int *sample)
 {
 	u32 adc0, adc1, old_adc0;
 	int i, ret;
@@ -631,6 +634,9 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode,
 		return -EINVAL;
 	}
 
+	adc1 |= ato << MC13783_ADC1_ATO_SHIFT;
+	if (atox)
+		adc1 |= MC13783_ADC1_ATOX;
 	dev_dbg(&mc13xxx->spidev->dev, "%s: request irq\n", __func__);
 	mc13xxx_irq_request(mc13xxx, MC13XXX_IRQ_ADCDONE,
 			mc13xxx_handler_adcdone, __func__, &adcdone_data);
@@ -813,7 +819,8 @@ err_revision:
 		mc13xxx_add_subdevice(mc13xxx, "%s-rtc");
 
 	if (mc13xxx->flags & MC13XXX_USE_TOUCHSCREEN)
-		mc13xxx_add_subdevice(mc13xxx, "%s-ts");
+		mc13xxx_add_subdevice_pdata(mc13xxx, "%s-ts",
+				&pdata->touch, sizeof(pdata->touch));
 
 	if (pdata) {
 		mc13xxx_add_subdevice_pdata(mc13xxx, "%s-regulator",
diff --git a/drivers/mfd/mcp-core.c b/drivers/mfd/mcp-core.c
index 86cc3f7841cd..62e5e3617eb0 100644
--- a/drivers/mfd/mcp-core.c
+++ b/drivers/mfd/mcp-core.c
@@ -19,9 +19,6 @@
 #include <linux/string.h>
 #include <linux/mfd/mcp.h>
 
-#include <mach/dma.h>
-#include <asm/system.h>
-
 
 #define to_mcp(d)		container_of(d, struct mcp, attached_device)
 #define to_mcp_driver(d)	container_of(d, struct mcp_driver, drv)
@@ -48,39 +45,11 @@ static int mcp_bus_remove(struct device *dev)
 	return 0;
 }
 
-static int mcp_bus_suspend(struct device *dev, pm_message_t state)
-{
-	struct mcp *mcp = to_mcp(dev);
-	int ret = 0;
-
-	if (dev->driver) {
-		struct mcp_driver *drv = to_mcp_driver(dev->driver);
-
-		ret = drv->suspend(mcp, state);
-	}
-	return ret;
-}
-
-static int mcp_bus_resume(struct device *dev)
-{
-	struct mcp *mcp = to_mcp(dev);
-	int ret = 0;
-
-	if (dev->driver) {
-		struct mcp_driver *drv = to_mcp_driver(dev->driver);
-
-		ret = drv->resume(mcp);
-	}
-	return ret;
-}
-
 static struct bus_type mcp_bus_type = {
 	.name		= "mcp",
 	.match		= mcp_bus_match,
 	.probe		= mcp_bus_probe,
 	.remove		= mcp_bus_remove,
-	.suspend	= mcp_bus_suspend,
-	.resume		= mcp_bus_resume,
 };
 
 /**
@@ -208,6 +177,7 @@ struct mcp *mcp_host_alloc(struct device *parent, size_t size)
 	mcp = kzalloc(sizeof(struct mcp) + size, GFP_KERNEL);
 	if (mcp) {
 		spin_lock_init(&mcp->lock);
+		device_initialize(&mcp->attached_device);
 		mcp->attached_device.parent = parent;
 		mcp->attached_device.bus = &mcp_bus_type;
 		mcp->attached_device.dma_mask = parent->dma_mask;
@@ -217,18 +187,25 @@ struct mcp *mcp_host_alloc(struct device *parent, size_t size)
 }
 EXPORT_SYMBOL(mcp_host_alloc);
 
-int mcp_host_register(struct mcp *mcp)
+int mcp_host_add(struct mcp *mcp, void *pdata)
 {
+	mcp->attached_device.platform_data = pdata;
 	dev_set_name(&mcp->attached_device, "mcp0");
-	return device_register(&mcp->attached_device);
+	return device_add(&mcp->attached_device);
+}
+EXPORT_SYMBOL(mcp_host_add);
+
+void mcp_host_del(struct mcp *mcp)
+{
+	device_del(&mcp->attached_device);
 }
-EXPORT_SYMBOL(mcp_host_register);
+EXPORT_SYMBOL(mcp_host_del);
 
-void mcp_host_unregister(struct mcp *mcp)
+void mcp_host_free(struct mcp *mcp)
 {
-	device_unregister(&mcp->attached_device);
+	put_device(&mcp->attached_device);
 }
-EXPORT_SYMBOL(mcp_host_unregister);
+EXPORT_SYMBOL(mcp_host_free);
 
 int mcp_driver_register(struct mcp_driver *mcpdrv)
 {
diff --git a/drivers/mfd/mcp-sa11x0.c b/drivers/mfd/mcp-sa11x0.c
index 02c53a0766c4..c54e244ca0cf 100644
--- a/drivers/mfd/mcp-sa11x0.c
+++ b/drivers/mfd/mcp-sa11x0.c
@@ -13,51 +13,60 @@
  */
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 #include <linux/mfd/mcp.h>
 
-#include <mach/dma.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/system.h>
 #include <mach/mcp.h>
 
-#include <mach/assabet.h>
-
+#define DRIVER_NAME "sa11x0-mcp"
 
 struct mcp_sa11x0 {
-	u32	mccr0;
-	u32	mccr1;
+	void __iomem	*base0;
+	void __iomem	*base1;
+	u32		mccr0;
+	u32		mccr1;
 };
 
+/* Register offsets */
+#define MCCR0(m)	((m)->base0 + 0x00)
+#define MCDR0(m)	((m)->base0 + 0x08)
+#define MCDR1(m)	((m)->base0 + 0x0c)
+#define MCDR2(m)	((m)->base0 + 0x10)
+#define MCSR(m)		((m)->base0 + 0x18)
+#define MCCR1(m)	((m)->base1 + 0x00)
+
 #define priv(mcp)	((struct mcp_sa11x0 *)mcp_priv(mcp))
 
 static void
 mcp_sa11x0_set_telecom_divisor(struct mcp *mcp, unsigned int divisor)
 {
-	unsigned int mccr0;
+	struct mcp_sa11x0 *m = priv(mcp);
 
 	divisor /= 32;
 
-	mccr0 = Ser4MCCR0 & ~0x00007f00;
-	mccr0 |= divisor << 8;
-	Ser4MCCR0 = mccr0;
+	m->mccr0 &= ~0x00007f00;
+	m->mccr0 |= divisor << 8;
+	writel_relaxed(m->mccr0, MCCR0(m));
 }
 
 static void
 mcp_sa11x0_set_audio_divisor(struct mcp *mcp, unsigned int divisor)
 {
-	unsigned int mccr0;
+	struct mcp_sa11x0 *m = priv(mcp);
 
 	divisor /= 32;
 
-	mccr0 = Ser4MCCR0 & ~0x0000007f;
-	mccr0 |= divisor;
-	Ser4MCCR0 = mccr0;
+	m->mccr0 &= ~0x0000007f;
+	m->mccr0 |= divisor;
+	writel_relaxed(m->mccr0, MCCR0(m));
 }
 
 /*
@@ -69,14 +78,15 @@ mcp_sa11x0_set_audio_divisor(struct mcp *mcp, unsigned int divisor)
 static void
 mcp_sa11x0_write(struct mcp *mcp, unsigned int reg, unsigned int val)
 {
+	struct mcp_sa11x0 *m = priv(mcp);
 	int ret = -ETIME;
 	int i;
 
-	Ser4MCDR2 = reg << 17 | MCDR2_Wr | (val & 0xffff);
+	writel_relaxed(reg << 17 | MCDR2_Wr | (val & 0xffff), MCDR2(m));
 
 	for (i = 0; i < 2; i++) {
 		udelay(mcp->rw_timeout);
-		if (Ser4MCSR & MCSR_CWC) {
+		if (readl_relaxed(MCSR(m)) & MCSR_CWC) {
 			ret = 0;
 			break;
 		}
@@ -95,15 +105,16 @@ mcp_sa11x0_write(struct mcp *mcp, unsigned int reg, unsigned int val)
 static unsigned int
 mcp_sa11x0_read(struct mcp *mcp, unsigned int reg)
 {
+	struct mcp_sa11x0 *m = priv(mcp);
 	int ret = -ETIME;
 	int i;
 
-	Ser4MCDR2 = reg << 17 | MCDR2_Rd;
+	writel_relaxed(reg << 17 | MCDR2_Rd, MCDR2(m));
 
 	for (i = 0; i < 2; i++) {
 		udelay(mcp->rw_timeout);
-		if (Ser4MCSR & MCSR_CRC) {
-			ret = Ser4MCDR2 & 0xffff;
+		if (readl_relaxed(MCSR(m)) & MCSR_CRC) {
+			ret = readl_relaxed(MCDR2(m)) & 0xffff;
 			break;
 		}
 	}
@@ -116,13 +127,19 @@ mcp_sa11x0_read(struct mcp *mcp, unsigned int reg)
 
 static void mcp_sa11x0_enable(struct mcp *mcp)
 {
-	Ser4MCSR = -1;
-	Ser4MCCR0 |= MCCR0_MCE;
+	struct mcp_sa11x0 *m = priv(mcp);
+
+	writel(-1, MCSR(m));
+	m->mccr0 |= MCCR0_MCE;
+	writel_relaxed(m->mccr0, MCCR0(m));
 }
 
 static void mcp_sa11x0_disable(struct mcp *mcp)
 {
-	Ser4MCCR0 &= ~MCCR0_MCE;
+	struct mcp_sa11x0 *m = priv(mcp);
+
+	m->mccr0 &= ~MCCR0_MCE;
+	writel_relaxed(m->mccr0, MCCR0(m));
 }
 
 /*
@@ -137,55 +154,64 @@ static struct mcp_ops mcp_sa11x0 = {
 	.disable		= mcp_sa11x0_disable,
 };
 
-static int mcp_sa11x0_probe(struct platform_device *pdev)
+static int mcp_sa11x0_probe(struct platform_device *dev)
 {
-	struct mcp_plat_data *data = pdev->dev.platform_data;
+	struct mcp_plat_data *data = dev->dev.platform_data;
+	struct resource *mem0, *mem1;
+	struct mcp_sa11x0 *m;
 	struct mcp *mcp;
 	int ret;
 
 	if (!data)
 		return -ENODEV;
 
-	if (!request_mem_region(0x80060000, 0x60, "sa11x0-mcp"))
-		return -EBUSY;
+	mem0 = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	mem1 = platform_get_resource(dev, IORESOURCE_MEM, 1);
+	if (!mem0 || !mem1)
+		return -ENXIO;
+
+	if (!request_mem_region(mem0->start, resource_size(mem0),
+				DRIVER_NAME)) {
+		ret = -EBUSY;
+		goto err_mem0;
+	}
 
-	mcp = mcp_host_alloc(&pdev->dev, sizeof(struct mcp_sa11x0));
+	if (!request_mem_region(mem1->start, resource_size(mem1),
+				DRIVER_NAME)) {
+		ret = -EBUSY;
+		goto err_mem1;
+	}
+
+	mcp = mcp_host_alloc(&dev->dev, sizeof(struct mcp_sa11x0));
 	if (!mcp) {
 		ret = -ENOMEM;
-		goto release;
+		goto err_alloc;
 	}
 
 	mcp->owner		= THIS_MODULE;
 	mcp->ops		= &mcp_sa11x0;
 	mcp->sclk_rate		= data->sclk_rate;
-	mcp->dma_audio_rd	= DMA_Ser4MCP0Rd;
-	mcp->dma_audio_wr	= DMA_Ser4MCP0Wr;
-	mcp->dma_telco_rd	= DMA_Ser4MCP1Rd;
-	mcp->dma_telco_wr	= DMA_Ser4MCP1Wr;
-	mcp->gpio_base		= data->gpio_base;
 
-	platform_set_drvdata(pdev, mcp);
+	m = priv(mcp);
+	m->mccr0 = data->mccr0 | 0x7f7f;
+	m->mccr1 = data->mccr1;
 
-	if (machine_is_assabet()) {
-		ASSABET_BCR_set(ASSABET_BCR_CODEC_RST);
+	m->base0 = ioremap(mem0->start, resource_size(mem0));
+	m->base1 = ioremap(mem1->start, resource_size(mem1));
+	if (!m->base0 || !m->base1) {
+		ret = -ENOMEM;
+		goto err_ioremap;
 	}
 
-	/*
-	 * Setup the PPC unit correctly.
-	 */
-	PPDR &= ~PPC_RXD4;
-	PPDR |= PPC_TXD4 | PPC_SCLK | PPC_SFRM;
-	PSDR |= PPC_RXD4;
-	PSDR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-	PPSR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
+	platform_set_drvdata(dev, mcp);
 
 	/*
 	 * Initialise device.  Note that we initially
 	 * set the sampling rate to minimum.
 	 */
-	Ser4MCSR = -1;
-	Ser4MCCR1 = data->mccr1;
-	Ser4MCCR0 = data->mccr0 | 0x7f7f;
+	writel_relaxed(-1, MCSR(m));
+	writel_relaxed(m->mccr1, MCCR1(m));
+	writel_relaxed(m->mccr0, MCCR0(m));
 
 	/*
 	 * Calculate the read/write timeout (us) from the bit clock
@@ -195,62 +221,90 @@ static int mcp_sa11x0_probe(struct platform_device *pdev)
 	mcp->rw_timeout = (64 * 3 * 1000000 + mcp->sclk_rate - 1) /
 			  mcp->sclk_rate;
 
-	ret = mcp_host_register(mcp);
+	ret = mcp_host_add(mcp, data->codec_pdata);
 	if (ret == 0)
-		goto out;
+		return 0;
 
- release:
-	release_mem_region(0x80060000, 0x60);
-	platform_set_drvdata(pdev, NULL);
+	platform_set_drvdata(dev, NULL);
 
- out:
+ err_ioremap:
+	iounmap(m->base1);
+	iounmap(m->base0);
+	mcp_host_free(mcp);
+ err_alloc:
+	release_mem_region(mem1->start, resource_size(mem1));
+ err_mem1:
+	release_mem_region(mem0->start, resource_size(mem0));
+ err_mem0:
 	return ret;
 }
 
 static int mcp_sa11x0_remove(struct platform_device *dev)
 {
 	struct mcp *mcp = platform_get_drvdata(dev);
+	struct mcp_sa11x0 *m = priv(mcp);
+	struct resource *mem0, *mem1;
+
+	if (m->mccr0 & MCCR0_MCE)
+		dev_warn(&dev->dev,
+			 "device left active (missing disable call?)\n");
+
+	mem0 = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	mem1 = platform_get_resource(dev, IORESOURCE_MEM, 1);
 
 	platform_set_drvdata(dev, NULL);
-	mcp_host_unregister(mcp);
-	release_mem_region(0x80060000, 0x60);
+	mcp_host_del(mcp);
+	iounmap(m->base1);
+	iounmap(m->base0);
+	mcp_host_free(mcp);
+	release_mem_region(mem1->start, resource_size(mem1));
+	release_mem_region(mem0->start, resource_size(mem0));
 
 	return 0;
 }
 
-static int mcp_sa11x0_suspend(struct platform_device *dev, pm_message_t state)
+#ifdef CONFIG_PM_SLEEP
+static int mcp_sa11x0_suspend(struct device *dev)
 {
-	struct mcp *mcp = platform_get_drvdata(dev);
+	struct mcp_sa11x0 *m = priv(dev_get_drvdata(dev));
+
+	if (m->mccr0 & MCCR0_MCE)
+		dev_warn(dev, "device left active (missing disable call?)\n");
 
-	priv(mcp)->mccr0 = Ser4MCCR0;
-	priv(mcp)->mccr1 = Ser4MCCR1;
-	Ser4MCCR0 &= ~MCCR0_MCE;
+	writel(m->mccr0 & ~MCCR0_MCE, MCCR0(m));
 
 	return 0;
 }
 
-static int mcp_sa11x0_resume(struct platform_device *dev)
+static int mcp_sa11x0_resume(struct device *dev)
 {
-	struct mcp *mcp = platform_get_drvdata(dev);
+	struct mcp_sa11x0 *m = priv(dev_get_drvdata(dev));
 
-	Ser4MCCR1 = priv(mcp)->mccr1;
-	Ser4MCCR0 = priv(mcp)->mccr0;
+	writel_relaxed(m->mccr1, MCCR1(m));
+	writel_relaxed(m->mccr0, MCCR0(m));
 
 	return 0;
 }
-
-/*
- * The driver for the SA11x0 MCP port.
- */
-MODULE_ALIAS("platform:sa11x0-mcp");
+#endif
+
+static const struct dev_pm_ops mcp_sa11x0_pm_ops = {
+#ifdef CONFIG_PM_SLEEP
+	.suspend = mcp_sa11x0_suspend,
+	.freeze = mcp_sa11x0_suspend,
+	.poweroff = mcp_sa11x0_suspend,
+	.resume_noirq = mcp_sa11x0_resume,
+	.thaw_noirq = mcp_sa11x0_resume,
+	.restore_noirq = mcp_sa11x0_resume,
+#endif
+};
 
 static struct platform_driver mcp_sa11x0_driver = {
 	.probe		= mcp_sa11x0_probe,
 	.remove		= mcp_sa11x0_remove,
-	.suspend	= mcp_sa11x0_suspend,
-	.resume		= mcp_sa11x0_resume,
 	.driver		= {
-		.name	= "sa11x0-mcp",
+		.name	= DRIVER_NAME,
+		.owner	= THIS_MODULE,
+		.pm	= &mcp_sa11x0_pm_ops,
 	},
 };
 
@@ -259,6 +313,7 @@ static struct platform_driver mcp_sa11x0_driver = {
  */
 module_platform_driver(mcp_sa11x0_driver);
 
+MODULE_ALIAS("platform:" DRIVER_NAME);
 MODULE_AUTHOR("Russell King <rmk@arm.linux.org.uk>");
 MODULE_DESCRIPTION("SA11x0 multimedia communications port driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index 411f523d4878..ffc3d48676ae 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -162,7 +162,7 @@ int mfd_add_devices(struct device *parent, int id,
 	atomic_t *cnts;
 
 	/* initialize reference counting for all cells */
-	cnts = kcalloc(sizeof(*cnts), n_devs, GFP_KERNEL);
+	cnts = kcalloc(n_devs, sizeof(*cnts), GFP_KERNEL);
 	if (!cnts)
 		return -ENOMEM;
 
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 68ac2c55d5ae..95a2e546a489 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -170,7 +170,7 @@ struct usbhs_hcd_omap {
 /*-------------------------------------------------------------------------*/
 
 const char usbhs_driver_name[] = USBHS_DRIVER_NAME;
-static u64 usbhs_dmamask = ~(u32)0;
+static u64 usbhs_dmamask = DMA_BIT_MASK(32);
 
 /*-------------------------------------------------------------------------*/
 
@@ -223,7 +223,7 @@ static struct platform_device *omap_usbhs_alloc_child(const char *name,
 	}
 
 	child->dev.dma_mask		= &usbhs_dmamask;
-	child->dev.coherent_dma_mask	= 0xffffffff;
+	dma_set_coherent_mask(&child->dev, DMA_BIT_MASK(32));
 	child->dev.parent		= dev;
 
 	ret = platform_device_add(child);
@@ -799,14 +799,13 @@ static int __devinit usbhs_omap_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, omap);
 
+	omap_usbhs_init(dev);
 	ret = omap_usbhs_alloc_children(pdev);
 	if (ret) {
 		dev_err(dev, "omap_usbhs_alloc_children failed\n");
 		goto err_alloc;
 	}
 
-	omap_usbhs_init(dev);
-
 	goto end_probe;
 
 err_alloc:
diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c
index ff1a7e741ecd..189c2f07b83f 100644
--- a/drivers/mfd/pcf50633-core.c
+++ b/drivers/mfd/pcf50633-core.c
@@ -46,13 +46,7 @@ EXPORT_SYMBOL_GPL(pcf50633_read_block);
 int pcf50633_write_block(struct pcf50633 *pcf , u8 reg,
 					int nr_regs, u8 *data)
 {
-	int ret;
-
-	ret = regmap_raw_write(pcf->regmap, reg, data, nr_regs);
-	if (ret != 0)
-		return ret;
-
-	return nr_regs;
+	return regmap_raw_write(pcf->regmap, reg, data, nr_regs);
 }
 EXPORT_SYMBOL_GPL(pcf50633_write_block);
 
diff --git a/drivers/mfd/pcf50633-gpio.c b/drivers/mfd/pcf50633-gpio.c
index 9ab19a8f669d..d02ddf2ebd63 100644
--- a/drivers/mfd/pcf50633-gpio.c
+++ b/drivers/mfd/pcf50633-gpio.c
@@ -19,32 +19,7 @@
 
 #include <linux/mfd/pcf50633/core.h>
 #include <linux/mfd/pcf50633/gpio.h>
-
-enum pcf50633_regulator_id {
-	PCF50633_REGULATOR_AUTO,
-	PCF50633_REGULATOR_DOWN1,
-	PCF50633_REGULATOR_DOWN2,
-	PCF50633_REGULATOR_LDO1,
-	PCF50633_REGULATOR_LDO2,
-	PCF50633_REGULATOR_LDO3,
-	PCF50633_REGULATOR_LDO4,
-	PCF50633_REGULATOR_LDO5,
-	PCF50633_REGULATOR_LDO6,
-	PCF50633_REGULATOR_HCLDO,
-	PCF50633_REGULATOR_MEMLDO,
-};
-
-#define PCF50633_REG_AUTOOUT	0x1a
-#define PCF50633_REG_DOWN1OUT	0x1e
-#define PCF50633_REG_DOWN2OUT	0x22
-#define PCF50633_REG_MEMLDOOUT	0x26
-#define PCF50633_REG_LDO1OUT	0x2d
-#define PCF50633_REG_LDO2OUT	0x2f
-#define PCF50633_REG_LDO3OUT	0x31
-#define PCF50633_REG_LDO4OUT	0x33
-#define PCF50633_REG_LDO5OUT	0x35
-#define PCF50633_REG_LDO6OUT	0x37
-#define PCF50633_REG_HCLDOOUT	0x39
+#include <linux/mfd/pcf50633/pmic.h>
 
 static const u8 pcf50633_regulator_registers[PCF50633_NUM_REGULATORS] = {
 	[PCF50633_REGULATOR_AUTO]	= PCF50633_REG_AUTOOUT,
diff --git a/drivers/mfd/pcf50633-irq.c b/drivers/mfd/pcf50633-irq.c
index 048a3b903b01..498286cbb530 100644
--- a/drivers/mfd/pcf50633-irq.c
+++ b/drivers/mfd/pcf50633-irq.c
@@ -19,12 +19,7 @@
 #include <linux/slab.h>
 
 #include <linux/mfd/pcf50633/core.h>
-
-/* Two MBCS registers used during cold start */
-#define PCF50633_REG_MBCS1		0x4b
-#define PCF50633_REG_MBCS2		0x4c
-#define PCF50633_MBCS1_USBPRES 		0x01
-#define PCF50633_MBCS1_ADAPTPRES	0x01
+#include <linux/mfd/pcf50633/mbc.h>
 
 int pcf50633_register_irq(struct pcf50633 *pcf, int irq,
 			void (*handler) (int, void *), void *data)
diff --git a/drivers/mfd/rc5t583-irq.c b/drivers/mfd/rc5t583-irq.c
new file mode 100644
index 000000000000..fa6f80fad5f1
--- /dev/null
+++ b/drivers/mfd/rc5t583-irq.c
@@ -0,0 +1,408 @@
+/*
+ * Interrupt driver for RICOH583 power management chip.
+ *
+ * Copyright (c) 2011-2012, NVIDIA CORPORATION.  All rights reserved.
+ * Author: Laxman dewangan <ldewangan@nvidia.com>
+ *
+ * based on code
+ *      Copyright (C) 2011 RICOH COMPANY,LTD
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/i2c.h>
+#include <linux/mfd/rc5t583.h>
+
+enum int_type {
+	SYS_INT  = 0x1,
+	DCDC_INT = 0x2,
+	RTC_INT  = 0x4,
+	ADC_INT  = 0x8,
+	GPIO_INT = 0x10,
+};
+
+static int gpedge_add[] = {
+	RC5T583_GPIO_GPEDGE2,
+	RC5T583_GPIO_GPEDGE2
+};
+
+static int irq_en_add[] = {
+	RC5T583_INT_EN_SYS1,
+	RC5T583_INT_EN_SYS2,
+	RC5T583_INT_EN_DCDC,
+	RC5T583_INT_EN_RTC,
+	RC5T583_INT_EN_ADC1,
+	RC5T583_INT_EN_ADC2,
+	RC5T583_INT_EN_ADC3,
+	RC5T583_GPIO_EN_INT
+};
+
+static int irq_mon_add[] = {
+	RC5T583_INT_MON_SYS1,
+	RC5T583_INT_MON_SYS2,
+	RC5T583_INT_MON_DCDC,
+	RC5T583_INT_MON_RTC,
+	RC5T583_INT_IR_ADCL,
+	RC5T583_INT_IR_ADCH,
+	RC5T583_INT_IR_ADCEND,
+	RC5T583_INT_IR_GPIOF,
+	RC5T583_INT_IR_GPIOR
+};
+
+static int irq_clr_add[] = {
+	RC5T583_INT_IR_SYS1,
+	RC5T583_INT_IR_SYS2,
+	RC5T583_INT_IR_DCDC,
+	RC5T583_INT_IR_RTC,
+	RC5T583_INT_IR_ADCL,
+	RC5T583_INT_IR_ADCH,
+	RC5T583_INT_IR_ADCEND,
+	RC5T583_INT_IR_GPIOF,
+	RC5T583_INT_IR_GPIOR
+};
+
+static int main_int_type[] = {
+	SYS_INT,
+	SYS_INT,
+	DCDC_INT,
+	RTC_INT,
+	ADC_INT,
+	ADC_INT,
+	ADC_INT,
+	GPIO_INT,
+	GPIO_INT,
+};
+
+struct rc5t583_irq_data {
+	u8	int_type;
+	u8	master_bit;
+	u8	int_en_bit;
+	u8	mask_reg_index;
+	int	grp_index;
+};
+
+#define RC5T583_IRQ(_int_type, _master_bit, _grp_index, \
+			_int_bit, _mask_ind)		\
+	{						\
+		.int_type	= _int_type,		\
+		.master_bit	= _master_bit,		\
+		.grp_index	= _grp_index,		\
+		.int_en_bit	= _int_bit,		\
+		.mask_reg_index	= _mask_ind,		\
+	}
+
+static const struct rc5t583_irq_data rc5t583_irqs[RC5T583_MAX_IRQS] = {
+	[RC5T583_IRQ_ONKEY]		= RC5T583_IRQ(SYS_INT,  0, 0, 0, 0),
+	[RC5T583_IRQ_ACOK]		= RC5T583_IRQ(SYS_INT,  0, 1, 1, 0),
+	[RC5T583_IRQ_LIDOPEN]		= RC5T583_IRQ(SYS_INT,  0, 2, 2, 0),
+	[RC5T583_IRQ_PREOT]		= RC5T583_IRQ(SYS_INT,  0, 3, 3, 0),
+	[RC5T583_IRQ_CLKSTP]		= RC5T583_IRQ(SYS_INT,  0, 4, 4, 0),
+	[RC5T583_IRQ_ONKEY_OFF]		= RC5T583_IRQ(SYS_INT,  0, 5, 5, 0),
+	[RC5T583_IRQ_WD]		= RC5T583_IRQ(SYS_INT,  0, 7, 7, 0),
+	[RC5T583_IRQ_EN_PWRREQ1]	= RC5T583_IRQ(SYS_INT,  0, 8, 0, 1),
+	[RC5T583_IRQ_EN_PWRREQ2]	= RC5T583_IRQ(SYS_INT,  0, 9, 1, 1),
+	[RC5T583_IRQ_PRE_VINDET]	= RC5T583_IRQ(SYS_INT,  0, 10, 2, 1),
+
+	[RC5T583_IRQ_DC0LIM]		= RC5T583_IRQ(DCDC_INT, 1, 0, 0, 2),
+	[RC5T583_IRQ_DC1LIM]		= RC5T583_IRQ(DCDC_INT, 1, 1, 1, 2),
+	[RC5T583_IRQ_DC2LIM]		= RC5T583_IRQ(DCDC_INT, 1, 2, 2, 2),
+	[RC5T583_IRQ_DC3LIM]		= RC5T583_IRQ(DCDC_INT, 1, 3, 3, 2),
+
+	[RC5T583_IRQ_CTC]		= RC5T583_IRQ(RTC_INT,  2, 0, 0, 3),
+	[RC5T583_IRQ_YALE]		= RC5T583_IRQ(RTC_INT,  2, 5, 5, 3),
+	[RC5T583_IRQ_DALE]		= RC5T583_IRQ(RTC_INT,  2, 6, 6, 3),
+	[RC5T583_IRQ_WALE]		= RC5T583_IRQ(RTC_INT,  2, 7, 7, 3),
+
+	[RC5T583_IRQ_AIN1L]		= RC5T583_IRQ(ADC_INT,  3, 0, 0, 4),
+	[RC5T583_IRQ_AIN2L]		= RC5T583_IRQ(ADC_INT,  3, 1, 1, 4),
+	[RC5T583_IRQ_AIN3L]		= RC5T583_IRQ(ADC_INT,  3, 2, 2, 4),
+	[RC5T583_IRQ_VBATL]		= RC5T583_IRQ(ADC_INT,  3, 3, 3, 4),
+	[RC5T583_IRQ_VIN3L]		= RC5T583_IRQ(ADC_INT,  3, 4, 4, 4),
+	[RC5T583_IRQ_VIN8L]		= RC5T583_IRQ(ADC_INT,  3, 5, 5, 4),
+	[RC5T583_IRQ_AIN1H]		= RC5T583_IRQ(ADC_INT,  3, 6, 0, 5),
+	[RC5T583_IRQ_AIN2H]		= RC5T583_IRQ(ADC_INT,  3, 7, 1, 5),
+	[RC5T583_IRQ_AIN3H]		= RC5T583_IRQ(ADC_INT,  3, 8, 2, 5),
+	[RC5T583_IRQ_VBATH]		= RC5T583_IRQ(ADC_INT,  3, 9, 3, 5),
+	[RC5T583_IRQ_VIN3H]		= RC5T583_IRQ(ADC_INT,  3, 10, 4, 5),
+	[RC5T583_IRQ_VIN8H]		= RC5T583_IRQ(ADC_INT,  3, 11, 5, 5),
+	[RC5T583_IRQ_ADCEND]		= RC5T583_IRQ(ADC_INT,  3, 12, 0, 6),
+
+	[RC5T583_IRQ_GPIO0]		= RC5T583_IRQ(GPIO_INT, 4, 0, 0, 7),
+	[RC5T583_IRQ_GPIO1]		= RC5T583_IRQ(GPIO_INT, 4, 1, 1, 7),
+	[RC5T583_IRQ_GPIO2]		= RC5T583_IRQ(GPIO_INT, 4, 2, 2, 7),
+	[RC5T583_IRQ_GPIO3]		= RC5T583_IRQ(GPIO_INT, 4, 3, 3, 7),
+	[RC5T583_IRQ_GPIO4]		= RC5T583_IRQ(GPIO_INT, 4, 4, 4, 7),
+	[RC5T583_IRQ_GPIO5]		= RC5T583_IRQ(GPIO_INT, 4, 5, 5, 7),
+	[RC5T583_IRQ_GPIO6]		= RC5T583_IRQ(GPIO_INT, 4, 6, 6, 7),
+	[RC5T583_IRQ_GPIO7]		= RC5T583_IRQ(GPIO_INT, 4, 7, 7, 7),
+};
+
+static void rc5t583_irq_lock(struct irq_data *irq_data)
+{
+	struct rc5t583 *rc5t583 = irq_data_get_irq_chip_data(irq_data);
+	mutex_lock(&rc5t583->irq_lock);
+}
+
+static void rc5t583_irq_unmask(struct irq_data *irq_data)
+{
+	struct rc5t583 *rc5t583 = irq_data_get_irq_chip_data(irq_data);
+	unsigned int __irq = irq_data->irq - rc5t583->irq_base;
+	const struct rc5t583_irq_data *data = &rc5t583_irqs[__irq];
+
+	rc5t583->group_irq_en[data->grp_index] |= 1 << data->grp_index;
+	rc5t583->intc_inten_reg |= 1 << data->master_bit;
+	rc5t583->irq_en_reg[data->mask_reg_index] |= 1 << data->int_en_bit;
+}
+
+static void rc5t583_irq_mask(struct irq_data *irq_data)
+{
+	struct rc5t583 *rc5t583 = irq_data_get_irq_chip_data(irq_data);
+	unsigned int __irq = irq_data->irq - rc5t583->irq_base;
+	const struct rc5t583_irq_data *data = &rc5t583_irqs[__irq];
+
+	rc5t583->group_irq_en[data->grp_index] &= ~(1 << data->grp_index);
+	if (!rc5t583->group_irq_en[data->grp_index])
+		rc5t583->intc_inten_reg &= ~(1 << data->master_bit);
+
+	rc5t583->irq_en_reg[data->mask_reg_index] &= ~(1 << data->int_en_bit);
+}
+
+static int rc5t583_irq_set_type(struct irq_data *irq_data, unsigned int type)
+{
+	struct rc5t583 *rc5t583 = irq_data_get_irq_chip_data(irq_data);
+	unsigned int __irq = irq_data->irq - rc5t583->irq_base;
+	const struct rc5t583_irq_data *data = &rc5t583_irqs[__irq];
+	int val = 0;
+	int gpedge_index;
+	int gpedge_bit_pos;
+
+	/* Supporting only trigger level inetrrupt */
+	if ((data->int_type & GPIO_INT) && (type & IRQ_TYPE_EDGE_BOTH)) {
+		gpedge_index = data->int_en_bit / 4;
+		gpedge_bit_pos = data->int_en_bit % 4;
+
+		if (type & IRQ_TYPE_EDGE_FALLING)
+			val |= 0x2;
+
+		if (type & IRQ_TYPE_EDGE_RISING)
+			val |= 0x1;
+
+		rc5t583->gpedge_reg[gpedge_index] &= ~(3 << gpedge_bit_pos);
+		rc5t583->gpedge_reg[gpedge_index] |= (val << gpedge_bit_pos);
+		rc5t583_irq_unmask(irq_data);
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static void rc5t583_irq_sync_unlock(struct irq_data *irq_data)
+{
+	struct rc5t583 *rc5t583 = irq_data_get_irq_chip_data(irq_data);
+	int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(rc5t583->gpedge_reg); i++) {
+		ret = rc5t583_write(rc5t583->dev, gpedge_add[i],
+				rc5t583->gpedge_reg[i]);
+		if (ret < 0)
+			dev_warn(rc5t583->dev,
+				"Error in writing reg 0x%02x error: %d\n",
+				gpedge_add[i], ret);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(rc5t583->irq_en_reg); i++) {
+		ret = rc5t583_write(rc5t583->dev, irq_en_add[i],
+					rc5t583->irq_en_reg[i]);
+		if (ret < 0)
+			dev_warn(rc5t583->dev,
+				"Error in writing reg 0x%02x error: %d\n",
+				irq_en_add[i], ret);
+	}
+
+	ret = rc5t583_write(rc5t583->dev, RC5T583_INTC_INTEN,
+				rc5t583->intc_inten_reg);
+	if (ret < 0)
+		dev_warn(rc5t583->dev,
+			"Error in writing reg 0x%02x error: %d\n",
+			RC5T583_INTC_INTEN, ret);
+
+	mutex_unlock(&rc5t583->irq_lock);
+}
+#ifdef CONFIG_PM_SLEEP
+static int rc5t583_irq_set_wake(struct irq_data *irq_data, unsigned int on)
+{
+	struct rc5t583 *rc5t583 = irq_data_get_irq_chip_data(irq_data);
+	return irq_set_irq_wake(rc5t583->chip_irq, on);
+}
+#else
+#define rc5t583_irq_set_wake NULL
+#endif
+
+static irqreturn_t rc5t583_irq(int irq, void *data)
+{
+	struct rc5t583 *rc5t583 = data;
+	uint8_t int_sts[RC5T583_MAX_INTERRUPT_MASK_REGS];
+	uint8_t master_int;
+	int i;
+	int ret;
+	unsigned int rtc_int_sts = 0;
+
+	/* Clear the status */
+	for (i = 0; i < RC5T583_MAX_INTERRUPT_MASK_REGS; i++)
+		int_sts[i] = 0;
+
+	ret  = rc5t583_read(rc5t583->dev, RC5T583_INTC_INTMON, &master_int);
+	if (ret < 0) {
+		dev_err(rc5t583->dev,
+			"Error in reading reg 0x%02x error: %d\n",
+			RC5T583_INTC_INTMON, ret);
+		return IRQ_HANDLED;
+	}
+
+	for (i = 0; i < RC5T583_MAX_INTERRUPT_MASK_REGS; ++i) {
+		if (!(master_int & main_int_type[i]))
+			continue;
+
+		ret = rc5t583_read(rc5t583->dev, irq_mon_add[i], &int_sts[i]);
+		if (ret < 0) {
+			dev_warn(rc5t583->dev,
+				"Error in reading reg 0x%02x error: %d\n",
+				irq_mon_add[i], ret);
+			int_sts[i] = 0;
+			continue;
+		}
+
+		if (main_int_type[i] & RTC_INT) {
+			rtc_int_sts = 0;
+			if (int_sts[i] & 0x1)
+				rtc_int_sts |= BIT(6);
+			if (int_sts[i] & 0x2)
+				rtc_int_sts |= BIT(7);
+			if (int_sts[i] & 0x4)
+				rtc_int_sts |= BIT(0);
+			if (int_sts[i] & 0x8)
+				rtc_int_sts |= BIT(5);
+		}
+
+		ret = rc5t583_write(rc5t583->dev, irq_clr_add[i],
+				~int_sts[i]);
+		if (ret < 0)
+			dev_warn(rc5t583->dev,
+				"Error in reading reg 0x%02x error: %d\n",
+				irq_clr_add[i], ret);
+
+		if (main_int_type[i] & RTC_INT)
+			int_sts[i] = rtc_int_sts;
+	}
+
+	/* Merge gpio interrupts for rising and falling case*/
+	int_sts[7] |= int_sts[8];
+
+	/* Call interrupt handler if enabled */
+	for (i = 0; i < RC5T583_MAX_IRQS; ++i) {
+		const struct rc5t583_irq_data *data = &rc5t583_irqs[i];
+		if ((int_sts[data->mask_reg_index] & (1 << data->int_en_bit)) &&
+			(rc5t583->group_irq_en[data->master_bit] &
+					(1 << data->grp_index)))
+			handle_nested_irq(rc5t583->irq_base + i);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct irq_chip rc5t583_irq_chip = {
+	.name = "rc5t583-irq",
+	.irq_mask = rc5t583_irq_mask,
+	.irq_unmask = rc5t583_irq_unmask,
+	.irq_bus_lock = rc5t583_irq_lock,
+	.irq_bus_sync_unlock = rc5t583_irq_sync_unlock,
+	.irq_set_type = rc5t583_irq_set_type,
+	.irq_set_wake = rc5t583_irq_set_wake,
+};
+
+int rc5t583_irq_init(struct rc5t583 *rc5t583, int irq, int irq_base)
+{
+	int i, ret;
+
+	if (!irq_base) {
+		dev_warn(rc5t583->dev, "No interrupt support on IRQ base\n");
+		return -EINVAL;
+	}
+
+	mutex_init(&rc5t583->irq_lock);
+
+	/* Initailize all int register to 0 */
+	for (i = 0; i < RC5T583_MAX_INTERRUPT_MASK_REGS; i++)  {
+		ret = rc5t583_write(rc5t583->dev, irq_en_add[i],
+				rc5t583->irq_en_reg[i]);
+		if (ret < 0)
+			dev_warn(rc5t583->dev,
+				"Error in writing reg 0x%02x error: %d\n",
+				irq_en_add[i], ret);
+	}
+
+	for (i = 0; i < RC5T583_MAX_GPEDGE_REG; i++)  {
+		ret = rc5t583_write(rc5t583->dev, gpedge_add[i],
+				rc5t583->gpedge_reg[i]);
+		if (ret < 0)
+			dev_warn(rc5t583->dev,
+				"Error in writing reg 0x%02x error: %d\n",
+				gpedge_add[i], ret);
+	}
+
+	ret = rc5t583_write(rc5t583->dev, RC5T583_INTC_INTEN, 0x0);
+	if (ret < 0)
+		dev_warn(rc5t583->dev,
+			"Error in writing reg 0x%02x error: %d\n",
+			RC5T583_INTC_INTEN, ret);
+
+	/* Clear all interrupts in case they woke up active. */
+	for (i = 0; i < RC5T583_MAX_INTERRUPT_MASK_REGS; i++)  {
+		ret = rc5t583_write(rc5t583->dev, irq_clr_add[i], 0);
+		if (ret < 0)
+			dev_warn(rc5t583->dev,
+				"Error in writing reg 0x%02x error: %d\n",
+				irq_clr_add[i], ret);
+	}
+
+	rc5t583->irq_base = irq_base;
+	rc5t583->chip_irq = irq;
+
+	for (i = 0; i < RC5T583_MAX_IRQS; i++) {
+		int __irq = i + rc5t583->irq_base;
+		irq_set_chip_data(__irq, rc5t583);
+		irq_set_chip_and_handler(__irq, &rc5t583_irq_chip,
+					 handle_simple_irq);
+		irq_set_nested_thread(__irq, 1);
+#ifdef CONFIG_ARM
+		set_irq_flags(__irq, IRQF_VALID);
+#endif
+	}
+
+	ret = request_threaded_irq(irq, NULL, rc5t583_irq, IRQF_ONESHOT,
+				"rc5t583", rc5t583);
+	if (ret < 0)
+		dev_err(rc5t583->dev,
+			"Error in registering interrupt error: %d\n", ret);
+	return ret;
+}
+
+int rc5t583_irq_exit(struct rc5t583 *rc5t583)
+{
+	if (rc5t583->chip_irq)
+		free_irq(rc5t583->chip_irq, rc5t583);
+	return 0;
+}
diff --git a/drivers/mfd/rc5t583.c b/drivers/mfd/rc5t583.c
new file mode 100644
index 000000000000..99ef944c621d
--- /dev/null
+++ b/drivers/mfd/rc5t583.c
@@ -0,0 +1,386 @@
+/*
+ * Core driver access RC5T583 power management chip.
+ *
+ * Copyright (c) 2011-2012, NVIDIA CORPORATION.  All rights reserved.
+ * Author: Laxman dewangan <ldewangan@nvidia.com>
+ *
+ * Based on code
+ *	Copyright (C) 2011 RICOH COMPANY,LTD
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/rc5t583.h>
+#include <linux/regmap.h>
+
+#define RICOH_ONOFFSEL_REG	0x10
+#define RICOH_SWCTL_REG		0x5E
+
+struct deepsleep_control_data {
+	u8 reg_add;
+	u8 ds_pos_bit;
+};
+
+#define DEEPSLEEP_INIT(_id, _reg, _pos)		\
+	{					\
+		.reg_add = RC5T583_##_reg,	\
+		.ds_pos_bit = _pos,		\
+	}
+
+static struct deepsleep_control_data deepsleep_data[] = {
+	DEEPSLEEP_INIT(DC0, SLPSEQ1, 0),
+	DEEPSLEEP_INIT(DC1, SLPSEQ1, 4),
+	DEEPSLEEP_INIT(DC2, SLPSEQ2, 0),
+	DEEPSLEEP_INIT(DC3, SLPSEQ2, 4),
+	DEEPSLEEP_INIT(LDO0, SLPSEQ3, 0),
+	DEEPSLEEP_INIT(LDO1, SLPSEQ3, 4),
+	DEEPSLEEP_INIT(LDO2, SLPSEQ4, 0),
+	DEEPSLEEP_INIT(LDO3, SLPSEQ4, 4),
+	DEEPSLEEP_INIT(LDO4, SLPSEQ5, 0),
+	DEEPSLEEP_INIT(LDO5, SLPSEQ5, 4),
+	DEEPSLEEP_INIT(LDO6, SLPSEQ6, 0),
+	DEEPSLEEP_INIT(LDO7, SLPSEQ6, 4),
+	DEEPSLEEP_INIT(LDO8, SLPSEQ7, 0),
+	DEEPSLEEP_INIT(LDO9, SLPSEQ7, 4),
+	DEEPSLEEP_INIT(PSO0, SLPSEQ8, 0),
+	DEEPSLEEP_INIT(PSO1, SLPSEQ8, 4),
+	DEEPSLEEP_INIT(PSO2, SLPSEQ9, 0),
+	DEEPSLEEP_INIT(PSO3, SLPSEQ9, 4),
+	DEEPSLEEP_INIT(PSO4, SLPSEQ10, 0),
+	DEEPSLEEP_INIT(PSO5, SLPSEQ10, 4),
+	DEEPSLEEP_INIT(PSO6, SLPSEQ11, 0),
+	DEEPSLEEP_INIT(PSO7, SLPSEQ11, 4),
+};
+
+#define EXT_PWR_REQ		\
+	(RC5T583_EXT_PWRREQ1_CONTROL | RC5T583_EXT_PWRREQ2_CONTROL)
+
+static struct mfd_cell rc5t583_subdevs[] = {
+	{.name = "rc5t583-regulator",},
+	{.name = "rc5t583-rtc",      },
+	{.name = "rc5t583-key",      }
+};
+
+int rc5t583_write(struct device *dev, uint8_t reg, uint8_t val)
+{
+	struct rc5t583 *rc5t583 = dev_get_drvdata(dev);
+	return regmap_write(rc5t583->regmap, reg, val);
+}
+
+int rc5t583_read(struct device *dev, uint8_t reg, uint8_t *val)
+{
+	struct rc5t583 *rc5t583 = dev_get_drvdata(dev);
+	unsigned int ival;
+	int ret;
+	ret = regmap_read(rc5t583->regmap, reg, &ival);
+	if (!ret)
+		*val = (uint8_t)ival;
+	return ret;
+}
+
+int rc5t583_set_bits(struct device *dev, unsigned int reg,
+			unsigned int bit_mask)
+{
+	struct rc5t583 *rc5t583 = dev_get_drvdata(dev);
+	return regmap_update_bits(rc5t583->regmap, reg, bit_mask, bit_mask);
+}
+
+int rc5t583_clear_bits(struct device *dev, unsigned int reg,
+			unsigned int bit_mask)
+{
+	struct rc5t583 *rc5t583 = dev_get_drvdata(dev);
+	return regmap_update_bits(rc5t583->regmap, reg, bit_mask, 0);
+}
+
+int rc5t583_update(struct device *dev, unsigned int reg,
+		unsigned int val, unsigned int mask)
+{
+	struct rc5t583 *rc5t583 = dev_get_drvdata(dev);
+	return regmap_update_bits(rc5t583->regmap, reg, mask, val);
+}
+
+static int __rc5t583_set_ext_pwrreq1_control(struct device *dev,
+	int id, int ext_pwr, int slots)
+{
+	int ret;
+	uint8_t sleepseq_val;
+	unsigned int en_bit;
+	unsigned int slot_bit;
+
+	if (id == RC5T583_DS_DC0) {
+		dev_err(dev, "PWRREQ1 is invalid control for rail %d\n", id);
+		return -EINVAL;
+	}
+
+	en_bit = deepsleep_data[id].ds_pos_bit;
+	slot_bit = en_bit + 1;
+	ret = rc5t583_read(dev, deepsleep_data[id].reg_add, &sleepseq_val);
+	if (ret < 0) {
+		dev_err(dev, "Error in reading reg 0x%x\n",
+				deepsleep_data[id].reg_add);
+		return ret;
+	}
+
+	sleepseq_val &= ~(0xF << en_bit);
+	sleepseq_val |= BIT(en_bit);
+	sleepseq_val |= ((slots & 0x7) << slot_bit);
+	ret = rc5t583_set_bits(dev, RICOH_ONOFFSEL_REG, BIT(1));
+	if (ret < 0) {
+		dev_err(dev, "Error in updating the 0x%02x register\n",
+				RICOH_ONOFFSEL_REG);
+		return ret;
+	}
+
+	ret = rc5t583_write(dev, deepsleep_data[id].reg_add, sleepseq_val);
+	if (ret < 0) {
+		dev_err(dev, "Error in writing reg 0x%x\n",
+				deepsleep_data[id].reg_add);
+		return ret;
+	}
+
+	if (id == RC5T583_DS_LDO4) {
+		ret = rc5t583_write(dev, RICOH_SWCTL_REG, 0x1);
+		if (ret < 0)
+			dev_err(dev, "Error in writing reg 0x%x\n",
+				RICOH_SWCTL_REG);
+	}
+	return ret;
+}
+
+static int __rc5t583_set_ext_pwrreq2_control(struct device *dev,
+	int id, int ext_pwr)
+{
+	int ret;
+
+	if (id != RC5T583_DS_DC0) {
+		dev_err(dev, "PWRREQ2 is invalid control for rail %d\n", id);
+		return -EINVAL;
+	}
+
+	ret = rc5t583_set_bits(dev, RICOH_ONOFFSEL_REG, BIT(2));
+	if (ret < 0)
+		dev_err(dev, "Error in updating the ONOFFSEL 0x10 register\n");
+	return ret;
+}
+
+int rc5t583_ext_power_req_config(struct device *dev, int ds_id,
+	int ext_pwr_req, int deepsleep_slot_nr)
+{
+	if ((ext_pwr_req & EXT_PWR_REQ) == EXT_PWR_REQ)
+		return -EINVAL;
+
+	if (ext_pwr_req & RC5T583_EXT_PWRREQ1_CONTROL)
+		return __rc5t583_set_ext_pwrreq1_control(dev, ds_id,
+				ext_pwr_req, deepsleep_slot_nr);
+
+	if (ext_pwr_req & RC5T583_EXT_PWRREQ2_CONTROL)
+		return __rc5t583_set_ext_pwrreq2_control(dev,
+			ds_id, ext_pwr_req);
+	return 0;
+}
+
+static int rc5t583_clear_ext_power_req(struct rc5t583 *rc5t583,
+	struct rc5t583_platform_data *pdata)
+{
+	int ret;
+	int i;
+	uint8_t on_off_val = 0;
+
+	/*  Clear ONOFFSEL register */
+	if (pdata->enable_shutdown)
+		on_off_val = 0x1;
+
+	ret = rc5t583_write(rc5t583->dev, RICOH_ONOFFSEL_REG, on_off_val);
+	if (ret < 0)
+		dev_warn(rc5t583->dev, "Error in writing reg %d error: %d\n",
+					RICOH_ONOFFSEL_REG, ret);
+
+	ret = rc5t583_write(rc5t583->dev, RICOH_SWCTL_REG, 0x0);
+	if (ret < 0)
+		dev_warn(rc5t583->dev, "Error in writing reg %d error: %d\n",
+					RICOH_SWCTL_REG, ret);
+
+	/* Clear sleep sequence register */
+	for (i = RC5T583_SLPSEQ1; i <= RC5T583_SLPSEQ11; ++i) {
+		ret = rc5t583_write(rc5t583->dev, i, 0x0);
+		if (ret < 0)
+			dev_warn(rc5t583->dev,
+				"Error in writing reg 0x%02x error: %d\n",
+				i, ret);
+	}
+	return 0;
+}
+
+static bool volatile_reg(struct device *dev, unsigned int reg)
+{
+	/* Enable caching in interrupt registers */
+	switch (reg) {
+	case RC5T583_INT_EN_SYS1:
+	case RC5T583_INT_EN_SYS2:
+	case RC5T583_INT_EN_DCDC:
+	case RC5T583_INT_EN_RTC:
+	case RC5T583_INT_EN_ADC1:
+	case RC5T583_INT_EN_ADC2:
+	case RC5T583_INT_EN_ADC3:
+	case RC5T583_GPIO_GPEDGE1:
+	case RC5T583_GPIO_GPEDGE2:
+	case RC5T583_GPIO_EN_INT:
+		return false;
+
+	case RC5T583_GPIO_MON_IOIN:
+		/* This is gpio input register */
+		return true;
+
+	default:
+		/* Enable caching in gpio registers */
+		if ((reg >= RC5T583_GPIO_IOSEL) &&
+				(reg <= RC5T583_GPIO_GPOFUNC))
+			return false;
+
+		/* Enable caching in sleep seq registers */
+		if ((reg >= RC5T583_SLPSEQ1) && (reg <= RC5T583_SLPSEQ11))
+			return false;
+
+		/* Enable caching of regulator registers */
+		if ((reg >= RC5T583_REG_DC0CTL) && (reg <= RC5T583_REG_SR3CTL))
+			return false;
+		if ((reg >= RC5T583_REG_LDOEN1) &&
+					(reg <= RC5T583_REG_LDO9DAC_DS))
+			return false;
+
+		break;
+	}
+
+	return true;
+}
+
+static const struct regmap_config rc5t583_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.volatile_reg = volatile_reg,
+	.max_register = RC5T583_MAX_REGS,
+	.num_reg_defaults_raw = RC5T583_MAX_REGS,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static int __devinit rc5t583_i2c_probe(struct i2c_client *i2c,
+			      const struct i2c_device_id *id)
+{
+	struct rc5t583 *rc5t583;
+	struct rc5t583_platform_data *pdata = i2c->dev.platform_data;
+	int ret;
+	bool irq_init_success = false;
+
+	if (!pdata) {
+		dev_err(&i2c->dev, "Err: Platform data not found\n");
+		return -EINVAL;
+	}
+
+	rc5t583 = devm_kzalloc(&i2c->dev, sizeof(struct rc5t583), GFP_KERNEL);
+	if (!rc5t583) {
+		dev_err(&i2c->dev, "Memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	rc5t583->dev = &i2c->dev;
+	i2c_set_clientdata(i2c, rc5t583);
+
+	rc5t583->regmap = regmap_init_i2c(i2c, &rc5t583_regmap_config);
+	if (IS_ERR(rc5t583->regmap)) {
+		ret = PTR_ERR(rc5t583->regmap);
+		dev_err(&i2c->dev, "regmap initialization failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = rc5t583_clear_ext_power_req(rc5t583, pdata);
+	if (ret < 0)
+		goto err_irq_init;
+
+	if (i2c->irq) {
+		ret = rc5t583_irq_init(rc5t583, i2c->irq, pdata->irq_base);
+		/* Still continue with waring if irq init fails */
+		if (ret)
+			dev_warn(&i2c->dev, "IRQ init failed: %d\n", ret);
+		else
+			irq_init_success = true;
+	}
+
+	ret = mfd_add_devices(rc5t583->dev, -1, rc5t583_subdevs,
+			ARRAY_SIZE(rc5t583_subdevs), NULL, 0);
+	if (ret) {
+		dev_err(&i2c->dev, "add mfd devices failed: %d\n", ret);
+		goto err_add_devs;
+	}
+
+	return 0;
+
+err_add_devs:
+	if (irq_init_success)
+		rc5t583_irq_exit(rc5t583);
+err_irq_init:
+	regmap_exit(rc5t583->regmap);
+	return ret;
+}
+
+static int  __devexit rc5t583_i2c_remove(struct i2c_client *i2c)
+{
+	struct rc5t583 *rc5t583 = i2c_get_clientdata(i2c);
+
+	mfd_remove_devices(rc5t583->dev);
+	rc5t583_irq_exit(rc5t583);
+	regmap_exit(rc5t583->regmap);
+	return 0;
+}
+
+static const struct i2c_device_id rc5t583_i2c_id[] = {
+	{.name = "rc5t583", .driver_data = 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, rc5t583_i2c_id);
+
+static struct i2c_driver rc5t583_i2c_driver = {
+	.driver = {
+		   .name = "rc5t583",
+		   .owner = THIS_MODULE,
+		   },
+	.probe = rc5t583_i2c_probe,
+	.remove = __devexit_p(rc5t583_i2c_remove),
+	.id_table = rc5t583_i2c_id,
+};
+
+static int __init rc5t583_i2c_init(void)
+{
+	return i2c_add_driver(&rc5t583_i2c_driver);
+}
+subsys_initcall(rc5t583_i2c_init);
+
+static void __exit rc5t583_i2c_exit(void)
+{
+	i2c_del_driver(&rc5t583_i2c_driver);
+}
+
+module_exit(rc5t583_i2c_exit);
+
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_DESCRIPTION("RICOH RC5T583 power management system device driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/s5m-core.c b/drivers/mfd/s5m-core.c
index caadabeed8e9..48949d998d10 100644
--- a/drivers/mfd/s5m-core.c
+++ b/drivers/mfd/s5m-core.c
@@ -26,7 +26,27 @@
 #include <linux/mfd/s5m87xx/s5m-rtc.h>
 #include <linux/regmap.h>
 
-static struct mfd_cell s5m87xx_devs[] = {
+static struct mfd_cell s5m8751_devs[] = {
+	{
+		.name = "s5m8751-pmic",
+	}, {
+		.name = "s5m-charger",
+	}, {
+		.name = "s5m8751-codec",
+	},
+};
+
+static struct mfd_cell s5m8763_devs[] = {
+	{
+		.name = "s5m8763-pmic",
+	}, {
+		.name = "s5m-rtc",
+	}, {
+		.name = "s5m-charger",
+	},
+};
+
+static struct mfd_cell s5m8767_devs[] = {
 	{
 		.name = "s5m8767-pmic",
 	}, {
@@ -42,7 +62,7 @@ EXPORT_SYMBOL_GPL(s5m_reg_read);
 
 int s5m_bulk_read(struct s5m87xx_dev *s5m87xx, u8 reg, int count, u8 *buf)
 {
-	return regmap_bulk_read(s5m87xx->regmap, reg, buf, count);;
+	return regmap_bulk_read(s5m87xx->regmap, reg, buf, count);
 }
 EXPORT_SYMBOL_GPL(s5m_bulk_read);
 
@@ -54,7 +74,7 @@ EXPORT_SYMBOL_GPL(s5m_reg_write);
 
 int s5m_bulk_write(struct s5m87xx_dev *s5m87xx, u8 reg, int count, u8 *buf)
 {
-	return regmap_raw_write(s5m87xx->regmap, reg, buf, count * sizeof(u16));
+	return regmap_raw_write(s5m87xx->regmap, reg, buf, count);
 }
 EXPORT_SYMBOL_GPL(s5m_bulk_write);
 
@@ -74,10 +94,10 @@ static int s5m87xx_i2c_probe(struct i2c_client *i2c,
 {
 	struct s5m_platform_data *pdata = i2c->dev.platform_data;
 	struct s5m87xx_dev *s5m87xx;
-	int ret = 0;
-	int error;
+	int ret;
 
-	s5m87xx = kzalloc(sizeof(struct s5m87xx_dev), GFP_KERNEL);
+	s5m87xx = devm_kzalloc(&i2c->dev, sizeof(struct s5m87xx_dev),
+				GFP_KERNEL);
 	if (s5m87xx == NULL)
 		return -ENOMEM;
 
@@ -96,9 +116,9 @@ static int s5m87xx_i2c_probe(struct i2c_client *i2c,
 
 	s5m87xx->regmap = regmap_init_i2c(i2c, &s5m_regmap_config);
 	if (IS_ERR(s5m87xx->regmap)) {
-		error = PTR_ERR(s5m87xx->regmap);
+		ret = PTR_ERR(s5m87xx->regmap);
 		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
-			error);
+			ret);
 		goto err;
 	}
 
@@ -112,9 +132,23 @@ static int s5m87xx_i2c_probe(struct i2c_client *i2c,
 
 	pm_runtime_set_active(s5m87xx->dev);
 
-	ret = mfd_add_devices(s5m87xx->dev, -1,
-				s5m87xx_devs, ARRAY_SIZE(s5m87xx_devs),
-				NULL, 0);
+	switch (s5m87xx->device_type) {
+	case S5M8751X:
+		ret = mfd_add_devices(s5m87xx->dev, -1, s5m8751_devs,
+					ARRAY_SIZE(s5m8751_devs), NULL, 0);
+		break;
+	case S5M8763X:
+		ret = mfd_add_devices(s5m87xx->dev, -1, s5m8763_devs,
+					ARRAY_SIZE(s5m8763_devs), NULL, 0);
+		break;
+	case S5M8767X:
+		ret = mfd_add_devices(s5m87xx->dev, -1, s5m8767_devs,
+					ARRAY_SIZE(s5m8767_devs), NULL, 0);
+		break;
+	default:
+		/* If this happens the probe function is problem */
+		BUG();
+	}
 
 	if (ret < 0)
 		goto err;
@@ -126,7 +160,6 @@ err:
 	s5m_irq_exit(s5m87xx);
 	i2c_unregister_device(s5m87xx->rtc);
 	regmap_exit(s5m87xx->regmap);
-	kfree(s5m87xx);
 	return ret;
 }
 
@@ -138,7 +171,6 @@ static int s5m87xx_i2c_remove(struct i2c_client *i2c)
 	s5m_irq_exit(s5m87xx);
 	i2c_unregister_device(s5m87xx->rtc);
 	regmap_exit(s5m87xx->regmap);
-	kfree(s5m87xx);
 	return 0;
 }
 
diff --git a/drivers/mfd/s5m-irq.c b/drivers/mfd/s5m-irq.c
index de76dfb6f0ad..0236676085cf 100644
--- a/drivers/mfd/s5m-irq.c
+++ b/drivers/mfd/s5m-irq.c
@@ -342,7 +342,10 @@ int s5m_irq_resume(struct s5m87xx_dev *s5m87xx)
 			s5m8767_irq_thread(s5m87xx->irq_base, s5m87xx);
 			break;
 		default:
-			break;
+			dev_err(s5m87xx->dev,
+				"Unknown device type %d\n",
+				s5m87xx->device_type);
+			return -EINVAL;
 
 		}
 	}
@@ -444,7 +447,9 @@ int s5m_irq_init(struct s5m87xx_dev *s5m87xx)
 		}
 		break;
 	default:
-		break;
+		dev_err(s5m87xx->dev,
+			"Unknown device type %d\n", s5m87xx->device_type);
+		return -EINVAL;
 	}
 
 	if (!s5m87xx->ono)
@@ -467,12 +472,15 @@ int s5m_irq_init(struct s5m87xx_dev *s5m87xx)
 					IRQF_ONESHOT, "s5m87xx-ono", s5m87xx);
 		break;
 	default:
+		ret = -EINVAL;
 		break;
 	}
 
-	if (ret)
+	if (ret) {
 		dev_err(s5m87xx->dev, "Failed to request IRQ %d: %d\n",
 			s5m87xx->ono, ret);
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index f4d86117f44a..d927dd49acb3 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -387,14 +387,6 @@ int sm501_unit_power(struct device *dev, unsigned int unit, unsigned int to)
 
 EXPORT_SYMBOL_GPL(sm501_unit_power);
 
-
-/* Perform a rounded division. */
-static long sm501fb_round_div(long num, long denom)
-{
-        /* n / d + 1 / 2 = (2n + d) / 2d */
-        return (2 * num + denom) / (2 * denom);
-}
-
 /* clock value structure. */
 struct sm501_clock {
 	unsigned long mclk;
@@ -428,7 +420,7 @@ static int sm501_calc_clock(unsigned long freq,
 		/* try all 8 shift values.*/
 		for (shift = 0; shift < 8; shift++) {
 			/* Calculate difference to requested clock */
-			diff = sm501fb_round_div(mclk, divider << shift) - freq;
+			diff = DIV_ROUND_CLOSEST(mclk, divider << shift) - freq;
 			if (diff < 0)
 				diff = -diff;
 
diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c
index e07947e56b2a..2dd8d49cb30b 100644
--- a/drivers/mfd/stmpe.c
+++ b/drivers/mfd/stmpe.c
@@ -298,6 +298,11 @@ static struct mfd_cell stmpe_gpio_cell = {
 	.num_resources	= ARRAY_SIZE(stmpe_gpio_resources),
 };
 
+static struct mfd_cell stmpe_gpio_cell_noirq = {
+	.name		= "stmpe-gpio",
+	/* gpio cell resources consist of an irq only so no resources here */
+};
+
 /*
  * Keypad (1601, 2401, 2403)
  */
@@ -346,6 +351,13 @@ static struct stmpe_variant_block stmpe801_blocks[] = {
 	},
 };
 
+static struct stmpe_variant_block stmpe801_blocks_noirq[] = {
+	{
+		.cell	= &stmpe_gpio_cell_noirq,
+		.block	= STMPE_BLOCK_GPIO,
+	},
+};
+
 static int stmpe801_enable(struct stmpe *stmpe, unsigned int blocks,
 			   bool enable)
 {
@@ -367,6 +379,17 @@ static struct stmpe_variant_info stmpe801 = {
 	.enable		= stmpe801_enable,
 };
 
+static struct stmpe_variant_info stmpe801_noirq = {
+	.name		= "stmpe801",
+	.id_val		= STMPE801_ID,
+	.id_mask	= 0xffff,
+	.num_gpios	= 8,
+	.regs		= stmpe801_regs,
+	.blocks		= stmpe801_blocks_noirq,
+	.num_blocks	= ARRAY_SIZE(stmpe801_blocks_noirq),
+	.enable		= stmpe801_enable,
+};
+
 /*
  * Touchscreen (STMPE811 or STMPE610)
  */
@@ -712,7 +735,7 @@ static struct stmpe_variant_info stmpe2403 = {
 	.enable_autosleep	= stmpe1601_autosleep, /* same as stmpe1601 */
 };
 
-static struct stmpe_variant_info *stmpe_variant_info[] = {
+static struct stmpe_variant_info *stmpe_variant_info[STMPE_NBR_PARTS] = {
 	[STMPE610]	= &stmpe610,
 	[STMPE801]	= &stmpe801,
 	[STMPE811]	= &stmpe811,
@@ -721,6 +744,16 @@ static struct stmpe_variant_info *stmpe_variant_info[] = {
 	[STMPE2403]	= &stmpe2403,
 };
 
+/*
+ * These devices can be connected in a 'no-irq' configuration - the irq pin
+ * is not used and the device cannot interrupt the CPU. Here we only list
+ * devices which support this configuration - the driver will fail probing
+ * for any devices not listed here which are configured in this way.
+ */
+static struct stmpe_variant_info *stmpe_noirq_variant_info[STMPE_NBR_PARTS] = {
+	[STMPE801]	= &stmpe801_noirq,
+};
+
 static irqreturn_t stmpe_irq(int irq, void *data)
 {
 	struct stmpe *stmpe = data;
@@ -864,7 +897,7 @@ static int __devinit stmpe_chip_init(struct stmpe *stmpe)
 	unsigned int irq_trigger = stmpe->pdata->irq_trigger;
 	int autosleep_timeout = stmpe->pdata->autosleep_timeout;
 	struct stmpe_variant_info *variant = stmpe->variant;
-	u8 icr;
+	u8 icr = 0;
 	unsigned int id;
 	u8 data[2];
 	int ret;
@@ -887,31 +920,33 @@ static int __devinit stmpe_chip_init(struct stmpe *stmpe)
 	if (ret)
 		return ret;
 
-	if (id == STMPE801_ID)
-		icr = STMPE801_REG_SYS_CTRL_INT_EN;
-	else
-		icr = STMPE_ICR_LSB_GIM;
-
-	/* STMPE801 doesn't support Edge interrupts */
-	if (id != STMPE801_ID) {
-		if (irq_trigger == IRQF_TRIGGER_FALLING ||
-				irq_trigger == IRQF_TRIGGER_RISING)
-			icr |= STMPE_ICR_LSB_EDGE;
-	}
-
-	if (irq_trigger == IRQF_TRIGGER_RISING ||
-			irq_trigger == IRQF_TRIGGER_HIGH) {
+	if (stmpe->irq >= 0) {
 		if (id == STMPE801_ID)
-			icr |= STMPE801_REG_SYS_CTRL_INT_HI;
+			icr = STMPE801_REG_SYS_CTRL_INT_EN;
 		else
-			icr |= STMPE_ICR_LSB_HIGH;
-	}
+			icr = STMPE_ICR_LSB_GIM;
 
-	if (stmpe->pdata->irq_invert_polarity) {
-		if (id == STMPE801_ID)
-			icr ^= STMPE801_REG_SYS_CTRL_INT_HI;
-		else
-			icr ^= STMPE_ICR_LSB_HIGH;
+		/* STMPE801 doesn't support Edge interrupts */
+		if (id != STMPE801_ID) {
+			if (irq_trigger == IRQF_TRIGGER_FALLING ||
+					irq_trigger == IRQF_TRIGGER_RISING)
+				icr |= STMPE_ICR_LSB_EDGE;
+		}
+
+		if (irq_trigger == IRQF_TRIGGER_RISING ||
+				irq_trigger == IRQF_TRIGGER_HIGH) {
+			if (id == STMPE801_ID)
+				icr |= STMPE801_REG_SYS_CTRL_INT_HI;
+			else
+				icr |= STMPE_ICR_LSB_HIGH;
+		}
+
+		if (stmpe->pdata->irq_invert_polarity) {
+			if (id == STMPE801_ID)
+				icr ^= STMPE801_REG_SYS_CTRL_INT_HI;
+			else
+				icr ^= STMPE_ICR_LSB_HIGH;
+		}
 	}
 
 	if (stmpe->pdata->autosleep) {
@@ -1001,19 +1036,38 @@ int __devinit stmpe_probe(struct stmpe_client_info *ci, int partnum)
 		stmpe->irq = ci->irq;
 	}
 
+	if (stmpe->irq < 0) {
+		/* use alternate variant info for no-irq mode, if supported */
+		dev_info(stmpe->dev,
+			"%s configured in no-irq mode by platform data\n",
+			stmpe->variant->name);
+		if (!stmpe_noirq_variant_info[stmpe->partnum]) {
+			dev_err(stmpe->dev,
+				"%s does not support no-irq mode!\n",
+				stmpe->variant->name);
+			ret = -ENODEV;
+			goto free_gpio;
+		}
+		stmpe->variant = stmpe_noirq_variant_info[stmpe->partnum];
+	}
+
 	ret = stmpe_chip_init(stmpe);
 	if (ret)
 		goto free_gpio;
 
-	ret = stmpe_irq_init(stmpe);
-	if (ret)
-		goto free_gpio;
+	if (stmpe->irq >= 0) {
+		ret = stmpe_irq_init(stmpe);
+		if (ret)
+			goto free_gpio;
 
-	ret = request_threaded_irq(stmpe->irq, NULL, stmpe_irq,
-			pdata->irq_trigger | IRQF_ONESHOT, "stmpe", stmpe);
-	if (ret) {
-		dev_err(stmpe->dev, "failed to request IRQ: %d\n", ret);
-		goto out_removeirq;
+		ret = request_threaded_irq(stmpe->irq, NULL, stmpe_irq,
+				pdata->irq_trigger | IRQF_ONESHOT,
+				"stmpe", stmpe);
+		if (ret) {
+			dev_err(stmpe->dev, "failed to request IRQ: %d\n",
+					ret);
+			goto out_removeirq;
+		}
 	}
 
 	ret = stmpe_devices_init(stmpe);
@@ -1026,9 +1080,11 @@ int __devinit stmpe_probe(struct stmpe_client_info *ci, int partnum)
 
 out_removedevs:
 	mfd_remove_devices(stmpe->dev);
-	free_irq(stmpe->irq, stmpe);
+	if (stmpe->irq >= 0)
+		free_irq(stmpe->irq, stmpe);
 out_removeirq:
-	stmpe_irq_remove(stmpe);
+	if (stmpe->irq >= 0)
+		stmpe_irq_remove(stmpe);
 free_gpio:
 	if (pdata->irq_over_gpio)
 		gpio_free(pdata->irq_gpio);
@@ -1041,8 +1097,10 @@ int stmpe_remove(struct stmpe *stmpe)
 {
 	mfd_remove_devices(stmpe->dev);
 
-	free_irq(stmpe->irq, stmpe);
-	stmpe_irq_remove(stmpe);
+	if (stmpe->irq >= 0) {
+		free_irq(stmpe->irq, stmpe);
+		stmpe_irq_remove(stmpe);
+	}
 
 	if (stmpe->pdata->irq_over_gpio)
 		gpio_free(stmpe->pdata->irq_gpio);
@@ -1057,7 +1115,7 @@ static int stmpe_suspend(struct device *dev)
 {
 	struct stmpe *stmpe = dev_get_drvdata(dev);
 
-	if (device_may_wakeup(dev))
+	if (stmpe->irq >= 0 && device_may_wakeup(dev))
 		enable_irq_wake(stmpe->irq);
 
 	return 0;
@@ -1067,7 +1125,7 @@ static int stmpe_resume(struct device *dev)
 {
 	struct stmpe *stmpe = dev_get_drvdata(dev);
 
-	if (device_may_wakeup(dev))
+	if (stmpe->irq >= 0 && device_may_wakeup(dev))
 		disable_irq_wake(stmpe->irq);
 
 	return 0;
diff --git a/drivers/mfd/tps65090.c b/drivers/mfd/tps65090.c
new file mode 100644
index 000000000000..a66d4df51293
--- /dev/null
+++ b/drivers/mfd/tps65090.c
@@ -0,0 +1,387 @@
+/*
+ * Core driver for TI TPS65090 PMIC family
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/tps65090.h>
+#include <linux/regmap.h>
+#include <linux/err.h>
+
+#define NUM_INT_REG 2
+#define TOTAL_NUM_REG 0x18
+
+/* interrupt status registers */
+#define TPS65090_INT_STS	0x0
+#define TPS65090_INT_STS2	0x1
+
+/* interrupt mask registers */
+#define TPS65090_INT_MSK	0x2
+#define TPS65090_INT_MSK2	0x3
+
+struct tps65090_irq_data {
+	u8		mask_reg;
+	u8		mask_pos;
+};
+
+#define TPS65090_IRQ(_reg, _mask_pos)		\
+	{					\
+		.mask_reg	= (_reg),	\
+		.mask_pos	= (_mask_pos),	\
+	}
+
+static const struct tps65090_irq_data tps65090_irqs[] = {
+	[0]		= TPS65090_IRQ(0, 0),
+	[1]		= TPS65090_IRQ(0, 1),
+	[2]		= TPS65090_IRQ(0, 2),
+	[3]		= TPS65090_IRQ(0, 3),
+	[4]		= TPS65090_IRQ(0, 4),
+	[5]		= TPS65090_IRQ(0, 5),
+	[6]		= TPS65090_IRQ(0, 6),
+	[7]		= TPS65090_IRQ(0, 7),
+	[8]		= TPS65090_IRQ(1, 0),
+	[9]		= TPS65090_IRQ(1, 1),
+	[10]		= TPS65090_IRQ(1, 2),
+	[11]		= TPS65090_IRQ(1, 3),
+	[12]		= TPS65090_IRQ(1, 4),
+	[13]		= TPS65090_IRQ(1, 5),
+	[14]		= TPS65090_IRQ(1, 6),
+	[15]		= TPS65090_IRQ(1, 7),
+};
+
+static struct mfd_cell tps65090s[] = {
+	{
+		.name = "tps65910-pmic",
+	},
+	{
+		.name = "tps65910-regulator",
+	},
+};
+
+struct tps65090 {
+	struct mutex		lock;
+	struct device		*dev;
+	struct i2c_client	*client;
+	struct regmap		*rmap;
+	struct irq_chip		irq_chip;
+	struct mutex		irq_lock;
+	int			irq_base;
+	unsigned int		id;
+};
+
+int tps65090_write(struct device *dev, int reg, uint8_t val)
+{
+	struct tps65090 *tps = dev_get_drvdata(dev);
+	return regmap_write(tps->rmap, reg, val);
+}
+EXPORT_SYMBOL_GPL(tps65090_write);
+
+int tps65090_read(struct device *dev, int reg, uint8_t *val)
+{
+	struct tps65090 *tps = dev_get_drvdata(dev);
+	unsigned int temp_val;
+	int ret;
+	ret = regmap_read(tps->rmap, reg, &temp_val);
+	if (!ret)
+		*val = temp_val;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tps65090_read);
+
+int tps65090_set_bits(struct device *dev, int reg, uint8_t bit_num)
+{
+	struct tps65090 *tps = dev_get_drvdata(dev);
+	return regmap_update_bits(tps->rmap, reg, BIT(bit_num), ~0u);
+}
+EXPORT_SYMBOL_GPL(tps65090_set_bits);
+
+int tps65090_clr_bits(struct device *dev, int reg, uint8_t bit_num)
+{
+	struct tps65090 *tps = dev_get_drvdata(dev);
+	return regmap_update_bits(tps->rmap, reg, BIT(bit_num), 0u);
+}
+EXPORT_SYMBOL_GPL(tps65090_clr_bits);
+
+static void tps65090_irq_lock(struct irq_data *data)
+{
+	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(data);
+
+	mutex_lock(&tps65090->irq_lock);
+}
+
+static void tps65090_irq_mask(struct irq_data *irq_data)
+{
+	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(irq_data);
+	unsigned int __irq = irq_data->hwirq;
+	const struct tps65090_irq_data *data = &tps65090_irqs[__irq];
+
+	tps65090_set_bits(tps65090->dev, (TPS65090_INT_MSK + data->mask_reg),
+		data->mask_pos);
+}
+
+static void tps65090_irq_unmask(struct irq_data *irq_data)
+{
+	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(irq_data);
+	unsigned int __irq = irq_data->irq - tps65090->irq_base;
+	const struct tps65090_irq_data *data = &tps65090_irqs[__irq];
+
+	tps65090_clr_bits(tps65090->dev, (TPS65090_INT_MSK + data->mask_reg),
+		data->mask_pos);
+}
+
+static void tps65090_irq_sync_unlock(struct irq_data *data)
+{
+	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(data);
+
+	mutex_unlock(&tps65090->irq_lock);
+}
+
+static irqreturn_t tps65090_irq(int irq, void *data)
+{
+	struct tps65090 *tps65090 = data;
+	int ret = 0;
+	u8 status, mask;
+	unsigned long int acks = 0;
+	int i;
+
+	for (i = 0; i < NUM_INT_REG; i++) {
+		ret = tps65090_read(tps65090->dev, TPS65090_INT_MSK + i, &mask);
+		if (ret < 0) {
+			dev_err(tps65090->dev,
+				"failed to read mask reg [addr:%d]\n",
+				TPS65090_INT_MSK + i);
+			return IRQ_NONE;
+		}
+		ret = tps65090_read(tps65090->dev, TPS65090_INT_STS + i,
+			&status);
+		if (ret < 0) {
+			dev_err(tps65090->dev,
+				"failed to read status reg [addr:%d]\n",
+				 TPS65090_INT_STS + i);
+			return IRQ_NONE;
+		}
+		if (status) {
+			/* Ack only those interrupts which are not masked */
+			status &= (~mask);
+			ret = tps65090_write(tps65090->dev,
+					TPS65090_INT_STS + i, status);
+			if (ret < 0) {
+				dev_err(tps65090->dev,
+					"failed to write interrupt status\n");
+				return IRQ_NONE;
+			}
+			acks |= (status << (i * 8));
+		}
+	}
+
+	for_each_set_bit(i, &acks, ARRAY_SIZE(tps65090_irqs))
+		handle_nested_irq(tps65090->irq_base + i);
+	return acks ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static int __devinit tps65090_irq_init(struct tps65090 *tps65090, int irq,
+	int irq_base)
+{
+	int i, ret;
+
+	if (!irq_base) {
+		dev_err(tps65090->dev, "IRQ base not set\n");
+		return -EINVAL;
+	}
+
+	mutex_init(&tps65090->irq_lock);
+
+	for (i = 0; i < NUM_INT_REG; i++)
+		tps65090_write(tps65090->dev, TPS65090_INT_MSK + i, 0xFF);
+
+	for (i = 0; i < NUM_INT_REG; i++)
+		tps65090_write(tps65090->dev, TPS65090_INT_STS + i, 0xff);
+
+	tps65090->irq_base = irq_base;
+	tps65090->irq_chip.name = "tps65090";
+	tps65090->irq_chip.irq_mask = tps65090_irq_mask;
+	tps65090->irq_chip.irq_unmask = tps65090_irq_unmask;
+	tps65090->irq_chip.irq_bus_lock = tps65090_irq_lock;
+	tps65090->irq_chip.irq_bus_sync_unlock = tps65090_irq_sync_unlock;
+
+	for (i = 0; i < ARRAY_SIZE(tps65090_irqs); i++) {
+		int __irq = i + tps65090->irq_base;
+		irq_set_chip_data(__irq, tps65090);
+		irq_set_chip_and_handler(__irq, &tps65090->irq_chip,
+					 handle_simple_irq);
+		irq_set_nested_thread(__irq, 1);
+#ifdef CONFIG_ARM
+		set_irq_flags(__irq, IRQF_VALID);
+#endif
+	}
+
+	ret = request_threaded_irq(irq, NULL, tps65090_irq, IRQF_ONESHOT,
+				"tps65090", tps65090);
+	if (!ret) {
+		device_init_wakeup(tps65090->dev, 1);
+		enable_irq_wake(irq);
+	}
+
+	return ret;
+}
+
+static bool is_volatile_reg(struct device *dev, unsigned int reg)
+{
+	if ((reg == TPS65090_INT_STS) || (reg == TPS65090_INT_STS))
+		return true;
+	else
+		return false;
+}
+
+static const struct regmap_config tps65090_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = TOTAL_NUM_REG,
+	.num_reg_defaults_raw = TOTAL_NUM_REG,
+	.cache_type = REGCACHE_RBTREE,
+	.volatile_reg = is_volatile_reg,
+};
+
+static int __devinit tps65090_i2c_probe(struct i2c_client *client,
+					const struct i2c_device_id *id)
+{
+	struct tps65090_platform_data *pdata = client->dev.platform_data;
+	struct tps65090 *tps65090;
+	int ret;
+
+	if (!pdata) {
+		dev_err(&client->dev, "tps65090 requires platform data\n");
+		return -EINVAL;
+	}
+
+	tps65090 = devm_kzalloc(&client->dev, sizeof(struct tps65090),
+		GFP_KERNEL);
+	if (tps65090 == NULL)
+		return -ENOMEM;
+
+	tps65090->client = client;
+	tps65090->dev = &client->dev;
+	i2c_set_clientdata(client, tps65090);
+
+	mutex_init(&tps65090->lock);
+
+	if (client->irq) {
+		ret = tps65090_irq_init(tps65090, client->irq, pdata->irq_base);
+		if (ret) {
+			dev_err(&client->dev, "IRQ init failed with err: %d\n",
+				ret);
+			goto err_exit;
+		}
+	}
+
+	tps65090->rmap = regmap_init_i2c(tps65090->client,
+		&tps65090_regmap_config);
+	if (IS_ERR(tps65090->rmap)) {
+		dev_err(&client->dev, "regmap_init failed with err: %ld\n",
+			PTR_ERR(tps65090->rmap));
+		goto err_irq_exit;
+	};
+
+	ret = mfd_add_devices(tps65090->dev, -1, tps65090s,
+		ARRAY_SIZE(tps65090s), NULL, 0);
+	if (ret) {
+		dev_err(&client->dev, "add mfd devices failed with err: %d\n",
+			ret);
+		goto err_regmap_exit;
+	}
+
+	return 0;
+
+err_regmap_exit:
+	regmap_exit(tps65090->rmap);
+
+err_irq_exit:
+	if (client->irq)
+		free_irq(client->irq, tps65090);
+err_exit:
+	return ret;
+}
+
+static int __devexit tps65090_i2c_remove(struct i2c_client *client)
+{
+	struct tps65090 *tps65090 = i2c_get_clientdata(client);
+
+	mfd_remove_devices(tps65090->dev);
+	regmap_exit(tps65090->rmap);
+	if (client->irq)
+		free_irq(client->irq, tps65090);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int tps65090_i2c_suspend(struct i2c_client *client, pm_message_t state)
+{
+	if (client->irq)
+		disable_irq(client->irq);
+	return 0;
+}
+
+static int tps65090_i2c_resume(struct i2c_client *client)
+{
+	if (client->irq)
+		enable_irq(client->irq);
+	return 0;
+}
+#endif
+
+static const struct i2c_device_id tps65090_id_table[] = {
+	{ "tps65090", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, tps65090_id_table);
+
+static struct i2c_driver tps65090_driver = {
+	.driver	= {
+		.name	= "tps65090",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= tps65090_i2c_probe,
+	.remove		= __devexit_p(tps65090_i2c_remove),
+#ifdef CONFIG_PM
+	.suspend	= tps65090_i2c_suspend,
+	.resume		= tps65090_i2c_resume,
+#endif
+	.id_table	= tps65090_id_table,
+};
+
+static int __init tps65090_init(void)
+{
+	return i2c_add_driver(&tps65090_driver);
+}
+subsys_initcall(tps65090_init);
+
+static void __exit tps65090_exit(void)
+{
+	i2c_del_driver(&tps65090_driver);
+}
+module_exit(tps65090_exit);
+
+MODULE_DESCRIPTION("TPS65090 core driver");
+MODULE_AUTHOR("Venu Byravarasu <vbyravarasu@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
new file mode 100644
index 000000000000..f7d854e4cc62
--- /dev/null
+++ b/drivers/mfd/tps65217.c
@@ -0,0 +1,242 @@
+/*
+ * tps65217.c
+ *
+ * TPS65217 chip family multi-function driver
+ *
+ * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/regmap.h>
+#include <linux/err.h>
+
+#include <linux/mfd/core.h>
+#include <linux/mfd/tps65217.h>
+
+/**
+ * tps65217_reg_read: Read a single tps65217 register.
+ *
+ * @tps: Device to read from.
+ * @reg: Register to read.
+ * @val: Contians the value
+ */
+int tps65217_reg_read(struct tps65217 *tps, unsigned int reg,
+			unsigned int *val)
+{
+	return regmap_read(tps->regmap, reg, val);
+}
+EXPORT_SYMBOL_GPL(tps65217_reg_read);
+
+/**
+ * tps65217_reg_write: Write a single tps65217 register.
+ *
+ * @tps65217: Device to write to.
+ * @reg: Register to write to.
+ * @val: Value to write.
+ * @level: Password protected level
+ */
+int tps65217_reg_write(struct tps65217 *tps, unsigned int reg,
+			unsigned int val, unsigned int level)
+{
+	int ret;
+	unsigned int xor_reg_val;
+
+	switch (level) {
+	case TPS65217_PROTECT_NONE:
+		return regmap_write(tps->regmap, reg, val);
+	case TPS65217_PROTECT_L1:
+		xor_reg_val = reg ^ TPS65217_PASSWORD_REGS_UNLOCK;
+		ret = regmap_write(tps->regmap, TPS65217_REG_PASSWORD,
+							xor_reg_val);
+		if (ret < 0)
+			return ret;
+
+		return regmap_write(tps->regmap, reg, val);
+	case TPS65217_PROTECT_L2:
+		xor_reg_val = reg ^ TPS65217_PASSWORD_REGS_UNLOCK;
+		ret = regmap_write(tps->regmap, TPS65217_REG_PASSWORD,
+							xor_reg_val);
+		if (ret < 0)
+			return ret;
+		ret = regmap_write(tps->regmap, reg, val);
+		if (ret < 0)
+			return ret;
+		ret = regmap_write(tps->regmap, TPS65217_REG_PASSWORD,
+							xor_reg_val);
+		if (ret < 0)
+			return ret;
+		return regmap_write(tps->regmap, reg, val);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL_GPL(tps65217_reg_write);
+
+/**
+ * tps65217_update_bits: Modify bits w.r.t mask, val and level.
+ *
+ * @tps65217: Device to write to.
+ * @reg: Register to read-write to.
+ * @mask: Mask.
+ * @val: Value to write.
+ * @level: Password protected level
+ */
+int tps65217_update_bits(struct tps65217 *tps, unsigned int reg,
+		unsigned int mask, unsigned int val, unsigned int level)
+{
+	int ret;
+	unsigned int data;
+
+	ret = tps65217_reg_read(tps, reg, &data);
+	if (ret) {
+		dev_err(tps->dev, "Read from reg 0x%x failed\n", reg);
+		return ret;
+	}
+
+	data &= ~mask;
+	data |= val & mask;
+
+	ret = tps65217_reg_write(tps, reg, data, level);
+	if (ret)
+		dev_err(tps->dev, "Write for reg 0x%x failed\n", reg);
+
+	return ret;
+}
+
+int tps65217_set_bits(struct tps65217 *tps, unsigned int reg,
+		unsigned int mask, unsigned int val, unsigned int level)
+{
+	return tps65217_update_bits(tps, reg, mask, val, level);
+}
+EXPORT_SYMBOL_GPL(tps65217_set_bits);
+
+int tps65217_clear_bits(struct tps65217 *tps, unsigned int reg,
+		unsigned int mask, unsigned int level)
+{
+	return tps65217_update_bits(tps, reg, mask, 0, level);
+}
+EXPORT_SYMBOL_GPL(tps65217_clear_bits);
+
+static struct regmap_config tps65217_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+};
+
+static int __devinit tps65217_probe(struct i2c_client *client,
+				const struct i2c_device_id *ids)
+{
+	struct tps65217 *tps;
+	struct tps65217_board *pdata = client->dev.platform_data;
+	int i, ret;
+	unsigned int version;
+
+	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
+	if (!tps)
+		return -ENOMEM;
+
+	tps->pdata = pdata;
+	tps->regmap = regmap_init_i2c(client, &tps65217_regmap_config);
+	if (IS_ERR(tps->regmap)) {
+		ret = PTR_ERR(tps->regmap);
+		dev_err(tps->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	i2c_set_clientdata(client, tps);
+	tps->dev = &client->dev;
+
+	ret = tps65217_reg_read(tps, TPS65217_REG_CHIPID, &version);
+	if (ret < 0) {
+		dev_err(tps->dev, "Failed to read revision"
+					" register: %d\n", ret);
+		goto err_regmap;
+	}
+
+	dev_info(tps->dev, "TPS65217 ID %#x version 1.%d\n",
+			(version & TPS65217_CHIPID_CHIP_MASK) >> 4,
+			version & TPS65217_CHIPID_REV_MASK);
+
+	for (i = 0; i < TPS65217_NUM_REGULATOR; i++) {
+		struct platform_device *pdev;
+
+		pdev = platform_device_alloc("tps65217-pmic", i);
+		if (!pdev) {
+			dev_err(tps->dev, "Cannot create regulator %d\n", i);
+			continue;
+		}
+
+		pdev->dev.parent = tps->dev;
+		platform_device_add_data(pdev, &pdata->tps65217_init_data[i],
+					sizeof(pdata->tps65217_init_data[i]));
+		tps->regulator_pdev[i] = pdev;
+
+		platform_device_add(pdev);
+	}
+
+	return 0;
+
+err_regmap:
+	regmap_exit(tps->regmap);
+
+	return ret;
+}
+
+static int __devexit tps65217_remove(struct i2c_client *client)
+{
+	struct tps65217 *tps = i2c_get_clientdata(client);
+	int i;
+
+	for (i = 0; i < TPS65217_NUM_REGULATOR; i++)
+		platform_device_unregister(tps->regulator_pdev[i]);
+
+	regmap_exit(tps->regmap);
+
+	return 0;
+}
+
+static const struct i2c_device_id tps65217_id_table[] = {
+	{"tps65217", 0xF0},
+	{/* end of list */}
+};
+MODULE_DEVICE_TABLE(i2c, tps65217_id_table);
+
+static struct i2c_driver tps65217_driver = {
+	.driver		= {
+		.name	= "tps65217",
+	},
+	.id_table	= tps65217_id_table,
+	.probe		= tps65217_probe,
+	.remove		= __devexit_p(tps65217_remove),
+};
+
+static int __init tps65217_init(void)
+{
+	return i2c_add_driver(&tps65217_driver);
+}
+subsys_initcall(tps65217_init);
+
+static void __exit tps65217_exit(void)
+{
+	i2c_del_driver(&tps65217_driver);
+}
+module_exit(tps65217_exit);
+
+MODULE_AUTHOR("AnilKumar Ch <anilkumar@ti.com>");
+MODULE_DESCRIPTION("TPS65217 chip family multi-function driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/tps65910-irq.c b/drivers/mfd/tps65910-irq.c
index 95c0d7978bec..c9ed5c00a621 100644
--- a/drivers/mfd/tps65910-irq.c
+++ b/drivers/mfd/tps65910-irq.c
@@ -145,12 +145,23 @@ static void tps65910_irq_disable(struct irq_data *data)
 	tps65910->irq_mask |= ( 1 << irq_to_tps65910_irq(tps65910, data->irq));
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int tps65910_irq_set_wake(struct irq_data *data, unsigned int enable)
+{
+	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
+	return irq_set_irq_wake(tps65910->chip_irq, enable);
+}
+#else
+#define tps65910_irq_set_wake NULL
+#endif
+
 static struct irq_chip tps65910_irq_chip = {
 	.name = "tps65910",
 	.irq_bus_lock = tps65910_irq_lock,
 	.irq_bus_sync_unlock = tps65910_irq_sync_unlock,
 	.irq_disable = tps65910_irq_disable,
 	.irq_enable = tps65910_irq_enable,
+	.irq_set_wake = tps65910_irq_set_wake,
 };
 
 int tps65910_irq_init(struct tps65910 *tps65910, int irq,
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index 4392f6bca156..bf2b25ebf2ca 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -16,10 +16,12 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
+#include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
 #include <linux/gpio.h>
 #include <linux/mfd/core.h>
+#include <linux/regmap.h>
 #include <linux/mfd/tps65910.h>
 
 static struct mfd_cell tps65910s[] = {
@@ -38,99 +40,56 @@ static struct mfd_cell tps65910s[] = {
 static int tps65910_i2c_read(struct tps65910 *tps65910, u8 reg,
 				  int bytes, void *dest)
 {
-	struct i2c_client *i2c = tps65910->i2c_client;
-	struct i2c_msg xfer[2];
-	int ret;
-
-	/* Write register */
-	xfer[0].addr = i2c->addr;
-	xfer[0].flags = 0;
-	xfer[0].len = 1;
-	xfer[0].buf = &reg;
-
-	/* Read data */
-	xfer[1].addr = i2c->addr;
-	xfer[1].flags = I2C_M_RD;
-	xfer[1].len = bytes;
-	xfer[1].buf = dest;
-
-	ret = i2c_transfer(i2c->adapter, xfer, 2);
-	if (ret == 2)
-		ret = 0;
-	else if (ret >= 0)
-		ret = -EIO;
-
-	return ret;
+	return regmap_bulk_read(tps65910->regmap, reg, dest, bytes);
 }
 
 static int tps65910_i2c_write(struct tps65910 *tps65910, u8 reg,
-				   int bytes, void *src)
+				  int bytes, void *src)
 {
-	struct i2c_client *i2c = tps65910->i2c_client;
-	/* we add 1 byte for device register */
-	u8 msg[TPS65910_MAX_REGISTER + 1];
-	int ret;
-
-	if (bytes > TPS65910_MAX_REGISTER)
-		return -EINVAL;
-
-	msg[0] = reg;
-	memcpy(&msg[1], src, bytes);
-
-	ret = i2c_master_send(i2c, msg, bytes + 1);
-	if (ret < 0)
-		return ret;
-	if (ret != bytes + 1)
-		return -EIO;
-	return 0;
+	return regmap_bulk_write(tps65910->regmap, reg, src, bytes);
 }
 
 int tps65910_set_bits(struct tps65910 *tps65910, u8 reg, u8 mask)
 {
-	u8 data;
-	int err;
-
-	mutex_lock(&tps65910->io_mutex);
-	err = tps65910_i2c_read(tps65910, reg, 1, &data);
-	if (err) {
-		dev_err(tps65910->dev, "read from reg %x failed\n", reg);
-		goto out;
-	}
-
-	data |= mask;
-	err = tps65910_i2c_write(tps65910, reg, 1, &data);
-	if (err)
-		dev_err(tps65910->dev, "write to reg %x failed\n", reg);
-
-out:
-	mutex_unlock(&tps65910->io_mutex);
-	return err;
+	return regmap_update_bits(tps65910->regmap, reg, mask, mask);
 }
 EXPORT_SYMBOL_GPL(tps65910_set_bits);
 
 int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask)
 {
-	u8 data;
-	int err;
-
-	mutex_lock(&tps65910->io_mutex);
-	err = tps65910_i2c_read(tps65910, reg, 1, &data);
-	if (err) {
-		dev_err(tps65910->dev, "read from reg %x failed\n", reg);
-		goto out;
-	}
-
-	data &= ~mask;
-	err = tps65910_i2c_write(tps65910, reg, 1, &data);
-	if (err)
-		dev_err(tps65910->dev, "write to reg %x failed\n", reg);
-
-out:
-	mutex_unlock(&tps65910->io_mutex);
-	return err;
+	return regmap_update_bits(tps65910->regmap, reg, mask, 0);
 }
 EXPORT_SYMBOL_GPL(tps65910_clear_bits);
 
+static bool is_volatile_reg(struct device *dev, unsigned int reg)
+{
+	struct tps65910 *tps65910 = dev_get_drvdata(dev);
+
+	/*
+	 * Caching all regulator registers.
+	 * All regualator register address range is same for
+	 * TPS65910 and TPS65911
+	 */
+	if ((reg >= TPS65910_VIO) && (reg <= TPS65910_VDAC)) {
+		/* Check for non-existing register */
+		if (tps65910_chip_id(tps65910) == TPS65910)
+			if ((reg == TPS65911_VDDCTRL_OP) ||
+				(reg == TPS65911_VDDCTRL_SR))
+				return true;
+		return false;
+	}
+	return true;
+}
+
+static const struct regmap_config tps65910_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.volatile_reg = is_volatile_reg,
+	.max_register = TPS65910_MAX_REGISTER,
+	.num_reg_defaults_raw = TPS65910_MAX_REGISTER,
+	.cache_type = REGCACHE_RBTREE,
+};
+
 static int tps65910_i2c_probe(struct i2c_client *i2c,
 			    const struct i2c_device_id *id)
 {
@@ -161,6 +120,13 @@ static int tps65910_i2c_probe(struct i2c_client *i2c,
 	tps65910->write = tps65910_i2c_write;
 	mutex_init(&tps65910->io_mutex);
 
+	tps65910->regmap = regmap_init_i2c(i2c, &tps65910_regmap_config);
+	if (IS_ERR(tps65910->regmap)) {
+		ret = PTR_ERR(tps65910->regmap);
+		dev_err(&i2c->dev, "regmap initialization failed: %d\n", ret);
+		goto regmap_err;
+	}
+
 	ret = mfd_add_devices(tps65910->dev, -1,
 			      tps65910s, ARRAY_SIZE(tps65910s),
 			      NULL, 0);
@@ -178,6 +144,8 @@ static int tps65910_i2c_probe(struct i2c_client *i2c,
 	return ret;
 
 err:
+	regmap_exit(tps65910->regmap);
+regmap_err:
 	kfree(tps65910);
 	kfree(init_data);
 	return ret;
@@ -189,6 +157,7 @@ static int tps65910_i2c_remove(struct i2c_client *i2c)
 
 	tps65910_irq_exit(tps65910);
 	mfd_remove_devices(tps65910->dev);
+	regmap_exit(tps65910->regmap);
 	kfree(tps65910);
 
 	return 0;
diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c
index 806680d1bbb4..7c2267e71f8b 100644
--- a/drivers/mfd/twl-core.c
+++ b/drivers/mfd/twl-core.c
@@ -46,9 +46,7 @@
 #include <linux/i2c.h>
 #include <linux/i2c/twl.h>
 
-#if defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3)
-#include <plat/cpu.h>
-#endif
+#include "twl-core.h"
 
 /*
  * The TWL4030 "Triton 2" is one of a family of a multi-function "Power
@@ -116,8 +114,8 @@
 #define twl_has_watchdog()        false
 #endif
 
-#if defined(CONFIG_MFD_TWL4030_AUDIO) || defined(CONFIG_MFD_TWL4030_AUDIO_MODULE) ||\
-	defined(CONFIG_TWL6040_CORE) || defined(CONFIG_TWL6040_CORE_MODULE)
+#if defined(CONFIG_MFD_TWL4030_AUDIO) || \
+	defined(CONFIG_MFD_TWL4030_AUDIO_MODULE)
 #define twl_has_codec()	true
 #else
 #define twl_has_codec()	false
@@ -147,12 +145,10 @@
 #define SUB_CHIP_ID1 1
 #define SUB_CHIP_ID2 2
 #define SUB_CHIP_ID3 3
+#define SUB_CHIP_ID_INVAL 0xff
 
 #define TWL_MODULE_LAST TWL4030_MODULE_LAST
 
-#define TWL4030_NR_IRQS    34 /* core:8, power:8, gpio: 18 */
-#define TWL6030_NR_IRQS    20
-
 /* Base Address defns for twl4030_map[] */
 
 /* subchip/slave 0 - USB ID */
@@ -314,7 +310,7 @@ static struct twl_mapping twl6030_map[] = {
 	 * so they continue to match the order in this table.
 	 */
 	{ SUB_CHIP_ID1, TWL6030_BASEADD_USB },
-	{ SUB_CHIP_ID3, TWL6030_BASEADD_AUDIO },
+	{ SUB_CHIP_ID_INVAL, TWL6030_BASEADD_AUDIO },
 	{ SUB_CHIP_ID2, TWL6030_BASEADD_DIEID },
 	{ SUB_CHIP_ID2, TWL6030_BASEADD_RSV },
 	{ SUB_CHIP_ID1, TWL6030_BASEADD_PIH },
@@ -376,6 +372,11 @@ int twl_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes)
 		return -EPERM;
 	}
 	sid = twl_map[mod_no].sid;
+	if (unlikely(sid == SUB_CHIP_ID_INVAL)) {
+		pr_err("%s: module %d is not part of the pmic\n",
+		       DRIVER_NAME, mod_no);
+		return -EINVAL;
+	}
 	twl = &twl_modules[sid];
 
 	mutex_lock(&twl->xfer_lock);
@@ -433,6 +434,11 @@ int twl_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes)
 		return -EPERM;
 	}
 	sid = twl_map[mod_no].sid;
+	if (unlikely(sid == SUB_CHIP_ID_INVAL)) {
+		pr_err("%s: module %d is not part of the pmic\n",
+		       DRIVER_NAME, mod_no);
+		return -EINVAL;
+	}
 	twl = &twl_modules[sid];
 
 	mutex_lock(&twl->xfer_lock);
@@ -663,7 +669,8 @@ add_regulator(int num, struct regulator_init_data *pdata,
  */
 
 static int
-add_children(struct twl4030_platform_data *pdata, unsigned long features)
+add_children(struct twl4030_platform_data *pdata, unsigned irq_base,
+		unsigned long features)
 {
 	struct device	*child;
 	unsigned sub_chip_id;
@@ -671,7 +678,7 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 	if (twl_has_gpio() && pdata->gpio) {
 		child = add_child(SUB_CHIP_ID1, "twl4030_gpio",
 				pdata->gpio, sizeof(*pdata->gpio),
-				false, pdata->irq_base + GPIO_INTR_OFFSET, 0);
+				false, irq_base + GPIO_INTR_OFFSET, 0);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
 	}
@@ -679,7 +686,7 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 	if (twl_has_keypad() && pdata->keypad) {
 		child = add_child(SUB_CHIP_ID2, "twl4030_keypad",
 				pdata->keypad, sizeof(*pdata->keypad),
-				true, pdata->irq_base + KEYPAD_INTR_OFFSET, 0);
+				true, irq_base + KEYPAD_INTR_OFFSET, 0);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
 	}
@@ -687,7 +694,7 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 	if (twl_has_madc() && pdata->madc) {
 		child = add_child(2, "twl4030_madc",
 				pdata->madc, sizeof(*pdata->madc),
-				true, pdata->irq_base + MADC_INTR_OFFSET, 0);
+				true, irq_base + MADC_INTR_OFFSET, 0);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
 	}
@@ -703,7 +710,7 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 		sub_chip_id = twl_map[TWL_MODULE_RTC].sid;
 		child = add_child(sub_chip_id, "twl_rtc",
 				NULL, 0,
-				true, pdata->irq_base + RTC_INTR_OFFSET, 0);
+				true, irq_base + RTC_INTR_OFFSET, 0);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
 	}
@@ -756,8 +763,8 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 				pdata->usb, sizeof(*pdata->usb),
 				true,
 				/* irq0 = USB_PRES, irq1 = USB */
-				pdata->irq_base + USB_PRES_INTR_OFFSET,
-				pdata->irq_base + USB_INTR_OFFSET);
+				irq_base + USB_PRES_INTR_OFFSET,
+				irq_base + USB_INTR_OFFSET);
 
 		if (IS_ERR(child))
 			return PTR_ERR(child);
@@ -805,8 +812,8 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 			pdata->usb, sizeof(*pdata->usb),
 			true,
 			/* irq1 = VBUS_PRES, irq0 = USB ID */
-			pdata->irq_base + USBOTG_INTR_OFFSET,
-			pdata->irq_base + USB_PRES_INTR_OFFSET);
+			irq_base + USBOTG_INTR_OFFSET,
+			irq_base + USB_PRES_INTR_OFFSET);
 
 		if (IS_ERR(child))
 			return PTR_ERR(child);
@@ -833,7 +840,7 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 
 	if (twl_has_pwrbutton() && twl_class_is_4030()) {
 		child = add_child(1, "twl4030_pwrbutton",
-				NULL, 0, true, pdata->irq_base + 8 + 0, 0);
+				NULL, 0, true, irq_base + 8 + 0, 0);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
 	}
@@ -847,15 +854,6 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 			return PTR_ERR(child);
 	}
 
-	if (twl_has_codec() && pdata->audio && twl_class_is_6030()) {
-		sub_chip_id = twl_map[TWL_MODULE_AUDIO_VOICE].sid;
-		child = add_child(sub_chip_id, "twl6040",
-				pdata->audio, sizeof(*pdata->audio),
-				false, 0, 0);
-		if (IS_ERR(child))
-			return PTR_ERR(child);
-	}
-
 	/* twl4030 regulators */
 	if (twl_has_regulator() && twl_class_is_4030()) {
 		child = add_regulator(TWL4030_REG_VPLL1, pdata->vpll1,
@@ -1092,8 +1090,8 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 		child = add_child(3, "twl4030_bci",
 				pdata->bci, sizeof(*pdata->bci), false,
 				/* irq0 = CHG_PRES, irq1 = BCI */
-				pdata->irq_base + BCI_PRES_INTR_OFFSET,
-				pdata->irq_base + BCI_INTR_OFFSET);
+				irq_base + BCI_PRES_INTR_OFFSET,
+				irq_base + BCI_INTR_OFFSET);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
 	}
@@ -1193,26 +1191,24 @@ static void clocks_init(struct device *dev,
 
 /*----------------------------------------------------------------------*/
 
-int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end);
-int twl4030_exit_irq(void);
-int twl4030_init_chip_irq(const char *chip);
-int twl6030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end);
-int twl6030_exit_irq(void);
 
 static int twl_remove(struct i2c_client *client)
 {
-	unsigned i;
+	unsigned i, num_slaves;
 	int status;
 
-	if (twl_class_is_4030())
+	if (twl_class_is_4030()) {
 		status = twl4030_exit_irq();
-	else
+		num_slaves = TWL_NUM_SLAVES;
+	} else {
 		status = twl6030_exit_irq();
+		num_slaves = TWL_NUM_SLAVES - 1;
+	}
 
 	if (status < 0)
 		return status;
 
-	for (i = 0; i < TWL_NUM_SLAVES; i++) {
+	for (i = 0; i < num_slaves; i++) {
 		struct twl_client	*twl = &twl_modules[i];
 
 		if (twl->client && twl->client != client)
@@ -1223,20 +1219,15 @@ static int twl_remove(struct i2c_client *client)
 	return 0;
 }
 
-/* NOTE:  this driver only handles a single twl4030/tps659x0 chip */
+/* NOTE: This driver only handles a single twl4030/tps659x0 chip */
 static int __devinit
 twl_probe(struct i2c_client *client, const struct i2c_device_id *id)
 {
-	int				status;
-	unsigned			i;
 	struct twl4030_platform_data	*pdata = client->dev.platform_data;
 	struct device_node		*node = client->dev.of_node;
-	u8 temp;
-	int ret = 0;
-	int nr_irqs = TWL4030_NR_IRQS;
-
-	if ((id->driver_data) & TWL6030_CLASS)
-		nr_irqs = TWL6030_NR_IRQS;
+	int				irq_base = 0;
+	int				status;
+	unsigned			i, num_slaves;
 
 	if (node && !pdata) {
 		/*
@@ -1255,17 +1246,6 @@ twl_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		return -EINVAL;
 	}
 
-	status = irq_alloc_descs(-1, pdata->irq_base, nr_irqs, 0);
-	if (IS_ERR_VALUE(status)) {
-		dev_err(&client->dev, "Fail to allocate IRQ descs\n");
-		return status;
-	}
-
-	pdata->irq_base = status;
-	pdata->irq_end = pdata->irq_base + nr_irqs;
-	irq_domain_add_legacy(node, nr_irqs, pdata->irq_base, 0,
-			      &irq_domain_simple_ops, NULL);
-
 	if (i2c_check_functionality(client->adapter, I2C_FUNC_I2C) == 0) {
 		dev_dbg(&client->dev, "can't talk I2C?\n");
 		return -EIO;
@@ -1276,13 +1256,23 @@ twl_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		return -EBUSY;
 	}
 
-	for (i = 0; i < TWL_NUM_SLAVES; i++) {
-		struct twl_client	*twl = &twl_modules[i];
+	if ((id->driver_data) & TWL6030_CLASS) {
+		twl_id = TWL6030_CLASS_ID;
+		twl_map = &twl6030_map[0];
+		num_slaves = TWL_NUM_SLAVES - 1;
+	} else {
+		twl_id = TWL4030_CLASS_ID;
+		twl_map = &twl4030_map[0];
+		num_slaves = TWL_NUM_SLAVES;
+	}
+
+	for (i = 0; i < num_slaves; i++) {
+		struct twl_client *twl = &twl_modules[i];
 
 		twl->address = client->addr + i;
-		if (i == 0)
+		if (i == 0) {
 			twl->client = client;
-		else {
+		} else {
 			twl->client = i2c_new_dummy(client->adapter,
 					twl->address);
 			if (!twl->client) {
@@ -1294,22 +1284,16 @@ twl_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		}
 		mutex_init(&twl->xfer_lock);
 	}
+
 	inuse = true;
-	if ((id->driver_data) & TWL6030_CLASS) {
-		twl_id = TWL6030_CLASS_ID;
-		twl_map = &twl6030_map[0];
-	} else {
-		twl_id = TWL4030_CLASS_ID;
-		twl_map = &twl4030_map[0];
-	}
 
 	/* setup clock framework */
 	clocks_init(&client->dev, pdata->clock);
 
 	/* read TWL IDCODE Register */
 	if (twl_id == TWL4030_CLASS_ID) {
-		ret = twl_read_idcode_register();
-		WARN(ret < 0, "Error: reading twl_idcode register value\n");
+		status = twl_read_idcode_register();
+		WARN(status < 0, "Error: reading twl_idcode register value\n");
 	}
 
 	/* load power event scripts */
@@ -1317,31 +1301,31 @@ twl_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		twl4030_power_init(pdata->power);
 
 	/* Maybe init the T2 Interrupt subsystem */
-	if (client->irq
-			&& pdata->irq_base
-			&& pdata->irq_end > pdata->irq_base) {
+	if (client->irq) {
 		if (twl_class_is_4030()) {
 			twl4030_init_chip_irq(id->name);
-			status = twl4030_init_irq(client->irq, pdata->irq_base,
-			pdata->irq_end);
+			irq_base = twl4030_init_irq(&client->dev, client->irq);
 		} else {
-			status = twl6030_init_irq(client->irq, pdata->irq_base,
-			pdata->irq_end);
+			irq_base = twl6030_init_irq(&client->dev, client->irq);
 		}
 
-		if (status < 0)
+		if (irq_base < 0) {
+			status = irq_base;
 			goto fail;
+		}
 	}
 
-	/* Disable TWL4030/TWL5030 I2C Pull-up on I2C1 and I2C4(SR) interface.
+	/*
+	 * Disable TWL4030/TWL5030 I2C Pull-up on I2C1 and I2C4(SR) interface.
 	 * Program I2C_SCL_CTRL_PU(bit 0)=0, I2C_SDA_CTRL_PU (bit 2)=0,
 	 * SR_I2C_SCL_CTRL_PU(bit 4)=0 and SR_I2C_SDA_CTRL_PU(bit 6)=0.
 	 */
-
 	if (twl_class_is_4030()) {
+		u8 temp;
+
 		twl_i2c_read_u8(TWL4030_MODULE_INTBR, &temp, REG_GPPUPDCTR1);
 		temp &= ~(SR_I2C_SDA_CTRL_PU | SR_I2C_SCL_CTRL_PU | \
-		I2C_SDA_CTRL_PU | I2C_SCL_CTRL_PU);
+			I2C_SDA_CTRL_PU | I2C_SCL_CTRL_PU);
 		twl_i2c_write_u8(TWL4030_MODULE_INTBR, temp, REG_GPPUPDCTR1);
 	}
 
@@ -1349,11 +1333,12 @@ twl_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (node)
 		status = of_platform_populate(node, NULL, NULL, &client->dev);
 	if (status)
-		status = add_children(pdata, id->driver_data);
+		status = add_children(pdata, irq_base, id->driver_data);
 
 fail:
 	if (status < 0)
 		twl_remove(client);
+
 	return status;
 }
 
diff --git a/drivers/mfd/twl-core.h b/drivers/mfd/twl-core.h
index 8c50a556e986..6ff99dce714f 100644
--- a/drivers/mfd/twl-core.h
+++ b/drivers/mfd/twl-core.h
@@ -1,9 +1,9 @@
 #ifndef __TWL_CORE_H__
 #define __TWL_CORE_H__
 
-extern int twl6030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end);
+extern int twl6030_init_irq(struct device *dev, int irq_num);
 extern int twl6030_exit_irq(void);
-extern int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end);
+extern int twl4030_init_irq(struct device *dev, int irq_num);
 extern int twl4030_exit_irq(void);
 extern int twl4030_init_chip_irq(const char *chip);
 
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index b69bb517b102..5d656e814358 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -28,10 +28,12 @@
  */
 
 #include <linux/init.h>
+#include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/slab.h>
-
+#include <linux/of.h>
+#include <linux/irqdomain.h>
 #include <linux/i2c/twl.h>
 
 #include "twl-core.h"
@@ -53,13 +55,14 @@
  *	base + 8  .. base + 15	SIH for PWR_INT
  *	base + 16 .. base + 33	SIH for GPIO
  */
+#define TWL4030_CORE_NR_IRQS	8
+#define TWL4030_PWR_NR_IRQS	8
 
 /* PIH register offsets */
 #define REG_PIH_ISR_P1			0x01
 #define REG_PIH_ISR_P2			0x02
 #define REG_PIH_SIR			0x03	/* for testing */
 
-
 /* Linux could (eventually) use either IRQ line */
 static int irq_line;
 
@@ -111,7 +114,8 @@ static int nr_sih_modules;
 #define TWL4030_MODULE_INT_PWR		TWL4030_MODULE_INT
 
 
-/* Order in this table matches order in PIH_ISR.  That is,
+/*
+ * Order in this table matches order in PIH_ISR.  That is,
  * BIT(n) in PIH_ISR is sih_modules[n].
  */
 /* sih_modules_twl4030 is used both in twl4030 and twl5030 */
@@ -288,7 +292,6 @@ static unsigned twl4030_irq_base;
  */
 static irqreturn_t handle_twl4030_pih(int irq, void *devid)
 {
-	int		module_irq;
 	irqreturn_t	ret;
 	u8		pih_isr;
 
@@ -299,16 +302,18 @@ static irqreturn_t handle_twl4030_pih(int irq, void *devid)
 		return IRQ_NONE;
 	}
 
-	/* these handlers deal with the relevant SIH irq status */
-	for (module_irq = twl4030_irq_base;
-			pih_isr;
-			pih_isr >>= 1, module_irq++) {
-		if (pih_isr & 0x1)
-			handle_nested_irq(module_irq);
+	while (pih_isr) {
+		unsigned long	pending = __ffs(pih_isr);
+		unsigned int	irq;
+
+		pih_isr &= ~BIT(pending);
+		irq = pending + twl4030_irq_base;
+		handle_nested_irq(irq);
 	}
 
 	return IRQ_HANDLED;
 }
+
 /*----------------------------------------------------------------------*/
 
 /*
@@ -337,7 +342,6 @@ static int twl4030_init_sih_modules(unsigned line)
 	memset(buf, 0xff, sizeof buf);
 	sih = sih_modules;
 	for (i = 0; i < nr_sih_modules; i++, sih++) {
-
 		/* skip USB -- it's funky */
 		if (!sih->bytes_ixr)
 			continue;
@@ -352,7 +356,8 @@ static int twl4030_init_sih_modules(unsigned line)
 			pr_err("twl4030: err %d initializing %s %s\n",
 					status, sih->name, "IMR");
 
-		/* Maybe disable "exclusive" mode; buffer second pending irq;
+		/*
+		 * Maybe disable "exclusive" mode; buffer second pending irq;
 		 * set Clear-On-Read (COR) bit.
 		 *
 		 * NOTE that sometimes COR polarity is documented as being
@@ -382,7 +387,8 @@ static int twl4030_init_sih_modules(unsigned line)
 		if (sih->irq_lines <= line)
 			continue;
 
-		/* Clear pending interrupt status.  Either the read was
+		/*
+		 * Clear pending interrupt status.  Either the read was
 		 * enough, or we need to write those bits.  Repeat, in
 		 * case an IRQ is pending (PENDDIS=0) ... that's not
 		 * uncommon with PWR_INT.PWRON.
@@ -398,7 +404,8 @@ static int twl4030_init_sih_modules(unsigned line)
 				status = twl_i2c_write(sih->module, buf,
 					sih->mask[line].isr_offset,
 					sih->bytes_ixr);
-			/* else COR=1 means read sufficed.
+			/*
+			 * else COR=1 means read sufficed.
 			 * (for most SIH modules...)
 			 */
 		}
@@ -410,7 +417,8 @@ static int twl4030_init_sih_modules(unsigned line)
 static inline void activate_irq(int irq)
 {
 #ifdef CONFIG_ARM
-	/* ARM requires an extra step to clear IRQ_NOREQUEST, which it
+	/*
+	 * ARM requires an extra step to clear IRQ_NOREQUEST, which it
 	 * sets on behalf of every irq_chip.  Also sets IRQ_NOPROBE.
 	 */
 	set_irq_flags(irq, IRQF_VALID);
@@ -620,33 +628,24 @@ static irqreturn_t handle_twl4030_sih(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static unsigned twl4030_irq_next;
-
-/* returns the first IRQ used by this SIH bank,
- * or negative errno
- */
-int twl4030_sih_setup(int module)
+/* returns the first IRQ used by this SIH bank, or negative errno */
+int twl4030_sih_setup(struct device *dev, int module, int irq_base)
 {
 	int			sih_mod;
 	const struct sih	*sih = NULL;
 	struct sih_agent	*agent;
 	int			i, irq;
 	int			status = -EINVAL;
-	unsigned		irq_base = twl4030_irq_next;
 
 	/* only support modules with standard clear-on-read for now */
-	for (sih_mod = 0, sih = sih_modules;
-			sih_mod < nr_sih_modules;
+	for (sih_mod = 0, sih = sih_modules; sih_mod < nr_sih_modules;
 			sih_mod++, sih++) {
 		if (sih->module == module && sih->set_cor) {
-			if (!WARN((irq_base + sih->bits) > NR_IRQS,
-					"irq %d for %s too big\n",
-					irq_base + sih->bits,
-					sih->name))
-				status = 0;
+			status = 0;
 			break;
 		}
 	}
+
 	if (status < 0)
 		return status;
 
@@ -654,8 +653,6 @@ int twl4030_sih_setup(int module)
 	if (!agent)
 		return -ENOMEM;
 
-	status = 0;
-
 	agent->irq_base = irq_base;
 	agent->sih = sih;
 	agent->imr = ~0;
@@ -671,8 +668,6 @@ int twl4030_sih_setup(int module)
 		activate_irq(irq);
 	}
 
-	twl4030_irq_next += i;
-
 	/* replace generic PIH handler (handle_simple_irq) */
 	irq = sih_mod + twl4030_irq_base;
 	irq_set_handler_data(irq, agent);
@@ -680,26 +675,43 @@ int twl4030_sih_setup(int module)
 	status = request_threaded_irq(irq, NULL, handle_twl4030_sih, 0,
 				      agent->irq_name ?: sih->name, NULL);
 
-	pr_info("twl4030: %s (irq %d) chaining IRQs %d..%d\n", sih->name,
-			irq, irq_base, twl4030_irq_next - 1);
+	dev_info(dev, "%s (irq %d) chaining IRQs %d..%d\n", sih->name,
+			irq, irq_base, irq_base + i - 1);
 
 	return status < 0 ? status : irq_base;
 }
 
 /* FIXME need a call to reverse twl4030_sih_setup() ... */
 
-
 /*----------------------------------------------------------------------*/
 
 /* FIXME pass in which interrupt line we'll use ... */
 #define twl_irq_line	0
 
-int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
+int twl4030_init_irq(struct device *dev, int irq_num)
 {
 	static struct irq_chip	twl4030_irq_chip;
+	int			status, i;
+	int			irq_base, irq_end, nr_irqs;
+	struct			device_node *node = dev->of_node;
 
-	int			status;
-	int			i;
+	/*
+	 * TWL core and pwr interrupts must be contiguous because
+	 * the hwirqs numbers are defined contiguously from 1 to 15.
+	 * Create only one domain for both.
+	 */
+	nr_irqs = TWL4030_PWR_NR_IRQS + TWL4030_CORE_NR_IRQS;
+
+	irq_base = irq_alloc_descs(-1, 0, nr_irqs, 0);
+	if (IS_ERR_VALUE(irq_base)) {
+		dev_err(dev, "Fail to allocate IRQ descs\n");
+		return irq_base;
+	}
+
+	irq_domain_add_legacy(node, nr_irqs, irq_base, 0,
+			      &irq_domain_simple_ops, NULL);
+
+	irq_end = irq_base + TWL4030_CORE_NR_IRQS;
 
 	/*
 	 * Mask and clear all TWL4030 interrupts since initially we do
@@ -711,7 +723,8 @@ int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
 
 	twl4030_irq_base = irq_base;
 
-	/* install an irq handler for each of the SIH modules;
+	/*
+	 * Install an irq handler for each of the SIH modules;
 	 * clone dummy irq_chip since PIH can't *do* anything
 	 */
 	twl4030_irq_chip = dummy_irq_chip;
@@ -725,14 +738,14 @@ int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
 		irq_set_nested_thread(i, 1);
 		activate_irq(i);
 	}
-	twl4030_irq_next = i;
-	pr_info("twl4030: %s (irq %d) chaining IRQs %d..%d\n", "PIH",
-			irq_num, irq_base, twl4030_irq_next - 1);
+
+	dev_info(dev, "%s (irq %d) chaining IRQs %d..%d\n", "PIH",
+			irq_num, irq_base, irq_end);
 
 	/* ... and the PWR_INT module ... */
-	status = twl4030_sih_setup(TWL4030_MODULE_INT);
+	status = twl4030_sih_setup(dev, TWL4030_MODULE_INT, irq_end);
 	if (status < 0) {
-		pr_err("twl4030: sih_setup PWR INT --> %d\n", status);
+		dev_err(dev, "sih_setup PWR INT --> %d\n", status);
 		goto fail;
 	}
 
@@ -741,11 +754,11 @@ int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
 				      IRQF_ONESHOT,
 				      "TWL4030-PIH", NULL);
 	if (status < 0) {
-		pr_err("twl4030: could not claim irq%d: %d\n", irq_num, status);
+		dev_err(dev, "could not claim irq%d: %d\n", irq_num, status);
 		goto fail_rqirq;
 	}
 
-	return status;
+	return irq_base;
 fail_rqirq:
 	/* clean up twl4030_sih_setup */
 fail:
diff --git a/drivers/mfd/twl6030-irq.c b/drivers/mfd/twl6030-irq.c
index c6b456ad7342..b76902f1e44a 100644
--- a/drivers/mfd/twl6030-irq.c
+++ b/drivers/mfd/twl6030-irq.c
@@ -39,6 +39,8 @@
 #include <linux/i2c/twl.h>
 #include <linux/platform_device.h>
 #include <linux/suspend.h>
+#include <linux/of.h>
+#include <linux/irqdomain.h>
 
 #include "twl-core.h"
 
@@ -51,8 +53,8 @@
  *
  * We set up IRQs starting at a platform-specified base. An interrupt map table,
  * specifies mapping between interrupt number and the associated module.
- *
  */
+#define TWL6030_NR_IRQS    20
 
 static int twl6030_interrupt_mapping[24] = {
 	PWR_INTR_OFFSET,	/* Bit 0	PWRON			*/
@@ -185,8 +187,17 @@ static int twl6030_irq_thread(void *data)
 			}
 		local_irq_enable();
 		}
-		ret = twl_i2c_write(TWL_MODULE_PIH, sts.bytes,
-				REG_INT_STS_A, 3); /* clear INT_STS_A */
+
+		/*
+		 * NOTE:
+		 * Simulation confirms that documentation is wrong w.r.t the
+		 * interrupt status clear operation. A single *byte* write to
+		 * any one of STS_A to STS_C register results in all three
+		 * STS registers being reset. Since it does not matter which
+		 * value is written, all three registers are cleared on a
+		 * single byte write, so we just use 0x0 to clear.
+		 */
+		ret = twl_i2c_write_u8(TWL_MODULE_PIH, 0x00, REG_INT_STS_A);
 		if (ret)
 			pr_warning("twl6030: I2C error in clearing PIH ISR\n");
 
@@ -227,7 +238,7 @@ static inline void activate_irq(int irq)
 #endif
 }
 
-int twl6030_irq_set_wake(struct irq_data *d, unsigned int on)
+static int twl6030_irq_set_wake(struct irq_data *d, unsigned int on)
 {
 	if (on)
 		atomic_inc(&twl6030_wakeirqs);
@@ -237,11 +248,6 @@ int twl6030_irq_set_wake(struct irq_data *d, unsigned int on)
 	return 0;
 }
 
-/*----------------------------------------------------------------------*/
-
-static unsigned twl6030_irq_next;
-
-/*----------------------------------------------------------------------*/
 int twl6030_interrupt_unmask(u8 bit_mask, u8 offset)
 {
 	int ret;
@@ -311,7 +317,8 @@ int twl6030_mmc_card_detect_config(void)
 									ret);
 		return ret;
 	}
-	return 0;
+
+	return twl6030_irq_base + MMCDETECT_INTR_OFFSET;
 }
 EXPORT_SYMBOL(twl6030_mmc_card_detect_config);
 
@@ -340,29 +347,44 @@ int twl6030_mmc_card_detect(struct device *dev, int slot)
 }
 EXPORT_SYMBOL(twl6030_mmc_card_detect);
 
-int twl6030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
+int twl6030_init_irq(struct device *dev, int irq_num)
 {
-
-	int	status = 0;
-	int	i;
+	struct			device_node *node = dev->of_node;
+	int			nr_irqs, irq_base, irq_end;
 	struct task_struct	*task;
-	int ret;
-	u8 mask[4];
+	static struct irq_chip  twl6030_irq_chip;
+	int			status = 0;
+	int			i;
+	u8			mask[4];
+
+	nr_irqs = TWL6030_NR_IRQS;
+
+	irq_base = irq_alloc_descs(-1, 0, nr_irqs, 0);
+	if (IS_ERR_VALUE(irq_base)) {
+		dev_err(dev, "Fail to allocate IRQ descs\n");
+		return irq_base;
+	}
+
+	irq_domain_add_legacy(node, nr_irqs, irq_base, 0,
+			      &irq_domain_simple_ops, NULL);
+
+	irq_end = irq_base + nr_irqs;
 
-	static struct irq_chip	twl6030_irq_chip;
 	mask[1] = 0xFF;
 	mask[2] = 0xFF;
 	mask[3] = 0xFF;
-	ret = twl_i2c_write(TWL_MODULE_PIH, &mask[0],
-			REG_INT_MSK_LINE_A, 3); /* MASK ALL INT LINES */
-	ret = twl_i2c_write(TWL_MODULE_PIH, &mask[0],
-			REG_INT_MSK_STS_A, 3); /* MASK ALL INT STS */
-	ret = twl_i2c_write(TWL_MODULE_PIH, &mask[0],
-			REG_INT_STS_A, 3); /* clear INT_STS_A,B,C */
+
+	/* mask all int lines */
+	twl_i2c_write(TWL_MODULE_PIH, &mask[0], REG_INT_MSK_LINE_A, 3);
+	/* mask all int sts */
+	twl_i2c_write(TWL_MODULE_PIH, &mask[0], REG_INT_MSK_STS_A, 3);
+	/* clear INT_STS_A,B,C */
+	twl_i2c_write(TWL_MODULE_PIH, &mask[0], REG_INT_STS_A, 3);
 
 	twl6030_irq_base = irq_base;
 
-	/* install an irq handler for each of the modules;
+	/*
+	 * install an irq handler for each of the modules;
 	 * clone dummy irq_chip since PIH can't *do* anything
 	 */
 	twl6030_irq_chip = dummy_irq_chip;
@@ -377,30 +399,29 @@ int twl6030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
 		activate_irq(i);
 	}
 
-	twl6030_irq_next = i;
-	pr_info("twl6030: %s (irq %d) chaining IRQs %d..%d\n", "PIH",
-			irq_num, irq_base, twl6030_irq_next - 1);
+	dev_info(dev, "PIH (irq %d) chaining IRQs %d..%d\n",
+			irq_num, irq_base, irq_end);
 
 	/* install an irq handler to demultiplex the TWL6030 interrupt */
 	init_completion(&irq_event);
 
-	status = request_irq(irq_num, handle_twl6030_pih, 0,
-				"TWL6030-PIH", &irq_event);
+	status = request_irq(irq_num, handle_twl6030_pih, 0, "TWL6030-PIH",
+			     &irq_event);
 	if (status < 0) {
-		pr_err("twl6030: could not claim irq%d: %d\n", irq_num, status);
+		dev_err(dev, "could not claim irq %d: %d\n", irq_num, status);
 		goto fail_irq;
 	}
 
 	task = kthread_run(twl6030_irq_thread, (void *)irq_num, "twl6030-irq");
 	if (IS_ERR(task)) {
-		pr_err("twl6030: could not create irq %d thread!\n", irq_num);
+		dev_err(dev, "could not create irq %d thread!\n", irq_num);
 		status = PTR_ERR(task);
 		goto fail_kthread;
 	}
 
 	twl_irq = irq_num;
 	register_pm_notifier(&twl6030_irq_pm_notifier_block);
-	return status;
+	return irq_base;
 
 fail_kthread:
 	free_irq(irq_num, &irq_event);
@@ -408,6 +429,7 @@ fail_kthread:
 fail_irq:
 	for (i = irq_base; i < irq_end; i++)
 		irq_set_chip_and_handler(i, NULL, NULL);
+
 	return status;
 }
 
diff --git a/drivers/mfd/ucb1x00-assabet.c b/drivers/mfd/ucb1x00-assabet.c
index cea9da60850d..b63c0756a669 100644
--- a/drivers/mfd/ucb1x00-assabet.c
+++ b/drivers/mfd/ucb1x00-assabet.c
@@ -11,14 +11,15 @@
  */
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/device.h>
+#include <linux/err.h>
 #include <linux/fs.h>
+#include <linux/gpio_keys.h>
+#include <linux/input.h>
+#include <linux/platform_device.h>
 #include <linux/proc_fs.h>
-#include <linux/device.h>
 #include <linux/mfd/ucb1x00.h>
 
-#include <mach/dma.h>
-
-
 #define UCB1X00_ATTR(name,input)\
 static ssize_t name##_show(struct device *dev, struct device_attribute *attr, \
 			   char *buf)	\
@@ -38,14 +39,45 @@ UCB1X00_ATTR(batt_temp, UCB_ADC_INP_AD2);
 
 static int ucb1x00_assabet_add(struct ucb1x00_dev *dev)
 {
-	device_create_file(&dev->ucb->dev, &dev_attr_vbatt);
-	device_create_file(&dev->ucb->dev, &dev_attr_vcharger);
-	device_create_file(&dev->ucb->dev, &dev_attr_batt_temp);
+	struct ucb1x00 *ucb = dev->ucb;
+	struct platform_device *pdev;
+	struct gpio_keys_platform_data keys;
+	static struct gpio_keys_button buttons[6];
+	unsigned i;
+
+	memset(buttons, 0, sizeof(buttons));
+	memset(&keys, 0, sizeof(keys));
+
+	for (i = 0; i < ARRAY_SIZE(buttons); i++) {
+		buttons[i].code = BTN_0 + i;
+		buttons[i].gpio = ucb->gpio.base + i;
+		buttons[i].type = EV_KEY;
+		buttons[i].can_disable = true;
+	}
+
+	keys.buttons = buttons;
+	keys.nbuttons = ARRAY_SIZE(buttons);
+	keys.poll_interval = 50;
+	keys.name = "ucb1x00";
+
+	pdev = platform_device_register_data(&ucb->dev, "gpio-keys", -1,
+		&keys, sizeof(keys));
+
+	device_create_file(&ucb->dev, &dev_attr_vbatt);
+	device_create_file(&ucb->dev, &dev_attr_vcharger);
+	device_create_file(&ucb->dev, &dev_attr_batt_temp);
+
+	dev->priv = pdev;
 	return 0;
 }
 
 static void ucb1x00_assabet_remove(struct ucb1x00_dev *dev)
 {
+	struct platform_device *pdev = dev->priv;
+
+	if (!IS_ERR(pdev))
+		platform_device_unregister(pdev);
+
 	device_remove_file(&dev->ucb->dev, &dev_attr_batt_temp);
 	device_remove_file(&dev->ucb->dev, &dev_attr_vcharger);
 	device_remove_file(&dev->ucb->dev, &dev_attr_vbatt);
diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c
index febc90cdef7e..70f02daeb22a 100644
--- a/drivers/mfd/ucb1x00-core.c
+++ b/drivers/mfd/ucb1x00-core.c
@@ -23,14 +23,12 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
 #include <linux/mfd/ucb1x00.h>
+#include <linux/pm.h>
 #include <linux/gpio.h>
-#include <linux/semaphore.h>
-
-#include <mach/dma.h>
-#include <mach/hardware.h>
 
 static DEFINE_MUTEX(ucb1x00_mutex);
 static LIST_HEAD(ucb1x00_drivers);
@@ -102,7 +100,7 @@ void ucb1x00_io_write(struct ucb1x00 *ucb, unsigned int set, unsigned int clear)
  *	ucb1x00_enable must have been called to enable the comms
  *	before using this function.
  *
- *	This function does not take any semaphores or spinlocks.
+ *	This function does not take any mutexes or spinlocks.
  */
 unsigned int ucb1x00_io_read(struct ucb1x00 *ucb)
 {
@@ -120,14 +118,22 @@ static void ucb1x00_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	else
 		ucb->io_out &= ~(1 << offset);
 
+	ucb1x00_enable(ucb);
 	ucb1x00_reg_write(ucb, UCB_IO_DATA, ucb->io_out);
+	ucb1x00_disable(ucb);
 	spin_unlock_irqrestore(&ucb->io_lock, flags);
 }
 
 static int ucb1x00_gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct ucb1x00 *ucb = container_of(chip, struct ucb1x00, gpio);
-	return ucb1x00_reg_read(ucb, UCB_IO_DATA) & (1 << offset);
+	unsigned val;
+
+	ucb1x00_enable(ucb);
+	val = ucb1x00_reg_read(ucb, UCB_IO_DATA);
+	ucb1x00_disable(ucb);
+
+	return val & (1 << offset);
 }
 
 static int ucb1x00_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
@@ -137,7 +143,9 @@ static int ucb1x00_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 
 	spin_lock_irqsave(&ucb->io_lock, flags);
 	ucb->io_dir &= ~(1 << offset);
+	ucb1x00_enable(ucb);
 	ucb1x00_reg_write(ucb, UCB_IO_DIR, ucb->io_dir);
+	ucb1x00_disable(ucb);
 	spin_unlock_irqrestore(&ucb->io_lock, flags);
 
 	return 0;
@@ -157,6 +165,7 @@ static int ucb1x00_gpio_direction_output(struct gpio_chip *chip, unsigned offset
 	else
 		ucb->io_out &= ~mask;
 
+	ucb1x00_enable(ucb);
 	if (old != ucb->io_out)
 		ucb1x00_reg_write(ucb, UCB_IO_DATA, ucb->io_out);
 
@@ -164,11 +173,19 @@ static int ucb1x00_gpio_direction_output(struct gpio_chip *chip, unsigned offset
 		ucb->io_dir |= mask;
 		ucb1x00_reg_write(ucb, UCB_IO_DIR, ucb->io_dir);
 	}
+	ucb1x00_disable(ucb);
 	spin_unlock_irqrestore(&ucb->io_lock, flags);
 
 	return 0;
 }
 
+static int ucb1x00_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+	struct ucb1x00 *ucb = container_of(chip, struct ucb1x00, gpio);
+
+	return ucb->irq_base > 0 ? ucb->irq_base + offset : -ENXIO;
+}
+
 /*
  * UCB1300 data sheet says we must:
  *  1. enable ADC	=> 5us (including reference startup time)
@@ -186,7 +203,7 @@ static int ucb1x00_gpio_direction_output(struct gpio_chip *chip, unsigned offset
  *	Any code wishing to use the ADC converter must call this
  *	function prior to using it.
  *
- *	This function takes the ADC semaphore to prevent two or more
+ *	This function takes the ADC mutex to prevent two or more
  *	concurrent uses, and therefore may sleep.  As a result, it
  *	can only be called from process context, not interrupt
  *	context.
@@ -196,7 +213,7 @@ static int ucb1x00_gpio_direction_output(struct gpio_chip *chip, unsigned offset
  */
 void ucb1x00_adc_enable(struct ucb1x00 *ucb)
 {
-	down(&ucb->adc_sem);
+	mutex_lock(&ucb->adc_mutex);
 
 	ucb->adc_cr |= UCB_ADC_ENA;
 
@@ -218,7 +235,7 @@ void ucb1x00_adc_enable(struct ucb1x00 *ucb)
  *	complete (2 frames max without sync).
  *
  *	If called for a synchronised ADC conversion, it may sleep
- *	with the ADC semaphore held.
+ *	with the ADC mutex held.
  */
 unsigned int ucb1x00_adc_read(struct ucb1x00 *ucb, int adc_channel, int sync)
 {
@@ -246,7 +263,7 @@ unsigned int ucb1x00_adc_read(struct ucb1x00 *ucb, int adc_channel, int sync)
  *	ucb1x00_adc_disable - disable the ADC converter
  *	@ucb: UCB1x00 structure describing chip
  *
- *	Disable the ADC converter and release the ADC semaphore.
+ *	Disable the ADC converter and release the ADC mutex.
  */
 void ucb1x00_adc_disable(struct ucb1x00 *ucb)
 {
@@ -254,7 +271,7 @@ void ucb1x00_adc_disable(struct ucb1x00 *ucb)
 	ucb1x00_reg_write(ucb, UCB_ADC_CR, ucb->adc_cr);
 	ucb1x00_disable(ucb);
 
-	up(&ucb->adc_sem);
+	mutex_unlock(&ucb->adc_mutex);
 }
 
 /*
@@ -265,10 +282,9 @@ void ucb1x00_adc_disable(struct ucb1x00 *ucb)
  * SIBCLK to talk to the chip.  We leave the clock running until
  * we have finished processing all interrupts from the chip.
  */
-static irqreturn_t ucb1x00_irq(int irqnr, void *devid)
+static void ucb1x00_irq(unsigned int irq, struct irq_desc *desc)
 {
-	struct ucb1x00 *ucb = devid;
-	struct ucb1x00_irq *irq;
+	struct ucb1x00 *ucb = irq_desc_get_handler_data(desc);
 	unsigned int isr, i;
 
 	ucb1x00_enable(ucb);
@@ -276,157 +292,104 @@ static irqreturn_t ucb1x00_irq(int irqnr, void *devid)
 	ucb1x00_reg_write(ucb, UCB_IE_CLEAR, isr);
 	ucb1x00_reg_write(ucb, UCB_IE_CLEAR, 0);
 
-	for (i = 0, irq = ucb->irq_handler; i < 16 && isr; i++, isr >>= 1, irq++)
-		if (isr & 1 && irq->fn)
-			irq->fn(i, irq->devid);
+	for (i = 0; i < 16 && isr; i++, isr >>= 1, irq++)
+		if (isr & 1)
+			generic_handle_irq(ucb->irq_base + i);
 	ucb1x00_disable(ucb);
-
-	return IRQ_HANDLED;
 }
 
-/**
- *	ucb1x00_hook_irq - hook a UCB1x00 interrupt
- *	@ucb:   UCB1x00 structure describing chip
- *	@idx:   interrupt index
- *	@fn:    function to call when interrupt is triggered
- *	@devid: device id to pass to interrupt handler
- *
- *	Hook the specified interrupt.  You can only register one handler
- *	for each interrupt source.  The interrupt source is not enabled
- *	by this function; use ucb1x00_enable_irq instead.
- *
- *	Interrupt handlers will be called with other interrupts enabled.
- *
- *	Returns zero on success, or one of the following errors:
- *	 -EINVAL if the interrupt index is invalid
- *	 -EBUSY if the interrupt has already been hooked
- */
-int ucb1x00_hook_irq(struct ucb1x00 *ucb, unsigned int idx, void (*fn)(int, void *), void *devid)
+static void ucb1x00_irq_update(struct ucb1x00 *ucb, unsigned mask)
 {
-	struct ucb1x00_irq *irq;
-	int ret = -EINVAL;
-
-	if (idx < 16) {
-		irq = ucb->irq_handler + idx;
-		ret = -EBUSY;
-
-		spin_lock_irq(&ucb->lock);
-		if (irq->fn == NULL) {
-			irq->devid = devid;
-			irq->fn = fn;
-			ret = 0;
-		}
-		spin_unlock_irq(&ucb->lock);
-	}
-	return ret;
+	ucb1x00_enable(ucb);
+	if (ucb->irq_ris_enbl & mask)
+		ucb1x00_reg_write(ucb, UCB_IE_RIS, ucb->irq_ris_enbl &
+				  ucb->irq_mask);
+	if (ucb->irq_fal_enbl & mask)
+		ucb1x00_reg_write(ucb, UCB_IE_FAL, ucb->irq_fal_enbl &
+				  ucb->irq_mask);
+	ucb1x00_disable(ucb);
 }
 
-/**
- *	ucb1x00_enable_irq - enable an UCB1x00 interrupt source
- *	@ucb: UCB1x00 structure describing chip
- *	@idx: interrupt index
- *	@edges: interrupt edges to enable
- *
- *	Enable the specified interrupt to trigger on %UCB_RISING,
- *	%UCB_FALLING or both edges.  The interrupt should have been
- *	hooked by ucb1x00_hook_irq.
- */
-void ucb1x00_enable_irq(struct ucb1x00 *ucb, unsigned int idx, int edges)
+static void ucb1x00_irq_noop(struct irq_data *data)
 {
-	unsigned long flags;
+}
 
-	if (idx < 16) {
-		spin_lock_irqsave(&ucb->lock, flags);
+static void ucb1x00_irq_mask(struct irq_data *data)
+{
+	struct ucb1x00 *ucb = irq_data_get_irq_chip_data(data);
+	unsigned mask = 1 << (data->irq - ucb->irq_base);
 
-		ucb1x00_enable(ucb);
-		if (edges & UCB_RISING) {
-			ucb->irq_ris_enbl |= 1 << idx;
-			ucb1x00_reg_write(ucb, UCB_IE_RIS, ucb->irq_ris_enbl);
-		}
-		if (edges & UCB_FALLING) {
-			ucb->irq_fal_enbl |= 1 << idx;
-			ucb1x00_reg_write(ucb, UCB_IE_FAL, ucb->irq_fal_enbl);
-		}
-		ucb1x00_disable(ucb);
-		spin_unlock_irqrestore(&ucb->lock, flags);
-	}
+	raw_spin_lock(&ucb->irq_lock);
+	ucb->irq_mask &= ~mask;
+	ucb1x00_irq_update(ucb, mask);
+	raw_spin_unlock(&ucb->irq_lock);
 }
 
-/**
- *	ucb1x00_disable_irq - disable an UCB1x00 interrupt source
- *	@ucb: UCB1x00 structure describing chip
- *	@edges: interrupt edges to disable
- *
- *	Disable the specified interrupt triggering on the specified
- *	(%UCB_RISING, %UCB_FALLING or both) edges.
- */
-void ucb1x00_disable_irq(struct ucb1x00 *ucb, unsigned int idx, int edges)
+static void ucb1x00_irq_unmask(struct irq_data *data)
 {
-	unsigned long flags;
+	struct ucb1x00 *ucb = irq_data_get_irq_chip_data(data);
+	unsigned mask = 1 << (data->irq - ucb->irq_base);
 
-	if (idx < 16) {
-		spin_lock_irqsave(&ucb->lock, flags);
-
-		ucb1x00_enable(ucb);
-		if (edges & UCB_RISING) {
-			ucb->irq_ris_enbl &= ~(1 << idx);
-			ucb1x00_reg_write(ucb, UCB_IE_RIS, ucb->irq_ris_enbl);
-		}
-		if (edges & UCB_FALLING) {
-			ucb->irq_fal_enbl &= ~(1 << idx);
-			ucb1x00_reg_write(ucb, UCB_IE_FAL, ucb->irq_fal_enbl);
-		}
-		ucb1x00_disable(ucb);
-		spin_unlock_irqrestore(&ucb->lock, flags);
-	}
+	raw_spin_lock(&ucb->irq_lock);
+	ucb->irq_mask |= mask;
+	ucb1x00_irq_update(ucb, mask);
+	raw_spin_unlock(&ucb->irq_lock);
 }
 
-/**
- *	ucb1x00_free_irq - disable and free the specified UCB1x00 interrupt
- *	@ucb: UCB1x00 structure describing chip
- *	@idx: interrupt index
- *	@devid: device id.
- *
- *	Disable the interrupt source and remove the handler.  devid must
- *	match the devid passed when hooking the interrupt.
- *
- *	Returns zero on success, or one of the following errors:
- *	 -EINVAL if the interrupt index is invalid
- *	 -ENOENT if devid does not match
- */
-int ucb1x00_free_irq(struct ucb1x00 *ucb, unsigned int idx, void *devid)
+static int ucb1x00_irq_set_type(struct irq_data *data, unsigned int type)
 {
-	struct ucb1x00_irq *irq;
-	int ret;
+	struct ucb1x00 *ucb = irq_data_get_irq_chip_data(data);
+	unsigned mask = 1 << (data->irq - ucb->irq_base);
 
-	if (idx >= 16)
-		goto bad;
+	raw_spin_lock(&ucb->irq_lock);
+	if (type & IRQ_TYPE_EDGE_RISING)
+		ucb->irq_ris_enbl |= mask;
+	else
+		ucb->irq_ris_enbl &= ~mask;
 
-	irq = ucb->irq_handler + idx;
-	ret = -ENOENT;
+	if (type & IRQ_TYPE_EDGE_FALLING)
+		ucb->irq_fal_enbl |= mask;
+	else
+		ucb->irq_fal_enbl &= ~mask;
+	if (ucb->irq_mask & mask) {
+		ucb1x00_reg_write(ucb, UCB_IE_RIS, ucb->irq_ris_enbl &
+				  ucb->irq_mask);
+		ucb1x00_reg_write(ucb, UCB_IE_FAL, ucb->irq_fal_enbl &
+				  ucb->irq_mask);
+	}
+	raw_spin_unlock(&ucb->irq_lock);
 
-	spin_lock_irq(&ucb->lock);
-	if (irq->devid == devid) {
-		ucb->irq_ris_enbl &= ~(1 << idx);
-		ucb->irq_fal_enbl &= ~(1 << idx);
+	return 0;
+}
 
-		ucb1x00_enable(ucb);
-		ucb1x00_reg_write(ucb, UCB_IE_RIS, ucb->irq_ris_enbl);
-		ucb1x00_reg_write(ucb, UCB_IE_FAL, ucb->irq_fal_enbl);
-		ucb1x00_disable(ucb);
+static int ucb1x00_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	struct ucb1x00 *ucb = irq_data_get_irq_chip_data(data);
+	struct ucb1x00_plat_data *pdata = ucb->mcp->attached_device.platform_data;
+	unsigned mask = 1 << (data->irq - ucb->irq_base);
 
-		irq->fn = NULL;
-		irq->devid = NULL;
-		ret = 0;
-	}
-	spin_unlock_irq(&ucb->lock);
-	return ret;
+	if (!pdata || !pdata->can_wakeup)
+		return -EINVAL;
 
-bad:
-	printk(KERN_ERR "Freeing bad UCB1x00 irq %d\n", idx);
-	return -EINVAL;
+	raw_spin_lock(&ucb->irq_lock);
+	if (on)
+		ucb->irq_wake |= mask;
+	else
+		ucb->irq_wake &= ~mask;
+	raw_spin_unlock(&ucb->irq_lock);
+
+	return 0;
 }
 
+static struct irq_chip ucb1x00_irqchip = {
+	.name = "ucb1x00",
+	.irq_ack = ucb1x00_irq_noop,
+	.irq_mask = ucb1x00_irq_mask,
+	.irq_unmask = ucb1x00_irq_unmask,
+	.irq_set_type = ucb1x00_irq_set_type,
+	.irq_set_wake = ucb1x00_irq_set_wake,
+};
+
 static int ucb1x00_add_dev(struct ucb1x00 *ucb, struct ucb1x00_driver *drv)
 {
 	struct ucb1x00_dev *dev;
@@ -440,8 +403,8 @@ static int ucb1x00_add_dev(struct ucb1x00 *ucb, struct ucb1x00_driver *drv)
 		ret = drv->add(dev);
 
 		if (ret == 0) {
-			list_add(&dev->dev_node, &ucb->devs);
-			list_add(&dev->drv_node, &drv->devs);
+			list_add_tail(&dev->dev_node, &ucb->devs);
+			list_add_tail(&dev->drv_node, &drv->devs);
 		} else {
 			kfree(dev);
 		}
@@ -533,98 +496,126 @@ static struct class ucb1x00_class = {
 
 static int ucb1x00_probe(struct mcp *mcp)
 {
-	struct ucb1x00 *ucb;
+	struct ucb1x00_plat_data *pdata = mcp->attached_device.platform_data;
 	struct ucb1x00_driver *drv;
-	unsigned int id;
+	struct ucb1x00 *ucb;
+	unsigned id, i, irq_base;
 	int ret = -ENODEV;
-	int temp;
+
+	/* Tell the platform to deassert the UCB1x00 reset */
+	if (pdata && pdata->reset)
+		pdata->reset(UCB_RST_PROBE);
 
 	mcp_enable(mcp);
 	id = mcp_reg_read(mcp, UCB_ID);
+	mcp_disable(mcp);
 
 	if (id != UCB_ID_1200 && id != UCB_ID_1300 && id != UCB_ID_TC35143) {
 		printk(KERN_WARNING "UCB1x00 ID not found: %04x\n", id);
-		goto err_disable;
+		goto out;
 	}
 
 	ucb = kzalloc(sizeof(struct ucb1x00), GFP_KERNEL);
 	ret = -ENOMEM;
 	if (!ucb)
-		goto err_disable;
-
+		goto out;
 
+	device_initialize(&ucb->dev);
 	ucb->dev.class = &ucb1x00_class;
 	ucb->dev.parent = &mcp->attached_device;
 	dev_set_name(&ucb->dev, "ucb1x00");
 
-	spin_lock_init(&ucb->lock);
+	raw_spin_lock_init(&ucb->irq_lock);
 	spin_lock_init(&ucb->io_lock);
-	sema_init(&ucb->adc_sem, 1);
+	mutex_init(&ucb->adc_mutex);
 
 	ucb->id  = id;
 	ucb->mcp = mcp;
+
+	ret = device_add(&ucb->dev);
+	if (ret)
+		goto err_dev_add;
+
+	ucb1x00_enable(ucb);
 	ucb->irq = ucb1x00_detect_irq(ucb);
+	ucb1x00_disable(ucb);
 	if (ucb->irq == NO_IRQ) {
-		printk(KERN_ERR "UCB1x00: IRQ probe failed\n");
+		dev_err(&ucb->dev, "IRQ probe failed\n");
 		ret = -ENODEV;
-		goto err_free;
+		goto err_no_irq;
 	}
 
 	ucb->gpio.base = -1;
-	if (mcp->gpio_base != 0) {
+	irq_base = pdata ? pdata->irq_base : 0;
+	ucb->irq_base = irq_alloc_descs(-1, irq_base, 16, -1);
+	if (ucb->irq_base < 0) {
+		dev_err(&ucb->dev, "unable to allocate 16 irqs: %d\n",
+			ucb->irq_base);
+		goto err_irq_alloc;
+	}
+
+	for (i = 0; i < 16; i++) {
+		unsigned irq = ucb->irq_base + i;
+
+		irq_set_chip_and_handler(irq, &ucb1x00_irqchip, handle_edge_irq);
+		irq_set_chip_data(irq, ucb);
+		set_irq_flags(irq, IRQF_VALID | IRQ_NOREQUEST);
+	}
+
+	irq_set_irq_type(ucb->irq, IRQ_TYPE_EDGE_RISING);
+	irq_set_handler_data(ucb->irq, ucb);
+	irq_set_chained_handler(ucb->irq, ucb1x00_irq);
+
+	if (pdata && pdata->gpio_base) {
 		ucb->gpio.label = dev_name(&ucb->dev);
-		ucb->gpio.base = mcp->gpio_base;
+		ucb->gpio.dev = &ucb->dev;
+		ucb->gpio.owner = THIS_MODULE;
+		ucb->gpio.base = pdata->gpio_base;
 		ucb->gpio.ngpio = 10;
 		ucb->gpio.set = ucb1x00_gpio_set;
 		ucb->gpio.get = ucb1x00_gpio_get;
 		ucb->gpio.direction_input = ucb1x00_gpio_direction_input;
 		ucb->gpio.direction_output = ucb1x00_gpio_direction_output;
+		ucb->gpio.to_irq = ucb1x00_to_irq;
 		ret = gpiochip_add(&ucb->gpio);
 		if (ret)
-			goto err_free;
+			goto err_gpio_add;
 	} else
 		dev_info(&ucb->dev, "gpio_base not set so no gpiolib support");
 
-	ret = request_irq(ucb->irq, ucb1x00_irq, IRQF_TRIGGER_RISING,
-			  "UCB1x00", ucb);
-	if (ret) {
-		printk(KERN_ERR "ucb1x00: unable to grab irq%d: %d\n",
-			ucb->irq, ret);
-		goto err_gpio;
-	}
-
 	mcp_set_drvdata(mcp, ucb);
 
-	ret = device_register(&ucb->dev);
-	if (ret)
-		goto err_irq;
-
+	if (pdata)
+		device_set_wakeup_capable(&ucb->dev, pdata->can_wakeup);
 
 	INIT_LIST_HEAD(&ucb->devs);
 	mutex_lock(&ucb1x00_mutex);
-	list_add(&ucb->node, &ucb1x00_devices);
+	list_add_tail(&ucb->node, &ucb1x00_devices);
 	list_for_each_entry(drv, &ucb1x00_drivers, node) {
 		ucb1x00_add_dev(ucb, drv);
 	}
 	mutex_unlock(&ucb1x00_mutex);
 
-	goto out;
+	return ret;
 
- err_irq:
-	free_irq(ucb->irq, ucb);
- err_gpio:
-	if (ucb->gpio.base != -1)
-		temp = gpiochip_remove(&ucb->gpio);
- err_free:
-	kfree(ucb);
- err_disable:
-	mcp_disable(mcp);
+ err_gpio_add:
+	irq_set_chained_handler(ucb->irq, NULL);
+ err_irq_alloc:
+	if (ucb->irq_base > 0)
+		irq_free_descs(ucb->irq_base, 16);
+ err_no_irq:
+	device_del(&ucb->dev);
+ err_dev_add:
+	put_device(&ucb->dev);
  out:
+	if (pdata && pdata->reset)
+		pdata->reset(UCB_RST_PROBE_FAIL);
 	return ret;
 }
 
 static void ucb1x00_remove(struct mcp *mcp)
 {
+	struct ucb1x00_plat_data *pdata = mcp->attached_device.platform_data;
 	struct ucb1x00 *ucb = mcp_get_drvdata(mcp);
 	struct list_head *l, *n;
 	int ret;
@@ -643,8 +634,12 @@ static void ucb1x00_remove(struct mcp *mcp)
 			dev_err(&ucb->dev, "Can't remove gpio chip: %d\n", ret);
 	}
 
-	free_irq(ucb->irq, ucb);
+	irq_set_chained_handler(ucb->irq, NULL);
+	irq_free_descs(ucb->irq_base, 16);
 	device_unregister(&ucb->dev);
+
+	if (pdata && pdata->reset)
+		pdata->reset(UCB_RST_REMOVE);
 }
 
 int ucb1x00_register_driver(struct ucb1x00_driver *drv)
@@ -653,7 +648,7 @@ int ucb1x00_register_driver(struct ucb1x00_driver *drv)
 
 	INIT_LIST_HEAD(&drv->devs);
 	mutex_lock(&ucb1x00_mutex);
-	list_add(&drv->node, &ucb1x00_drivers);
+	list_add_tail(&drv->node, &ucb1x00_drivers);
 	list_for_each_entry(ucb, &ucb1x00_devices, node) {
 		ucb1x00_add_dev(ucb, drv);
 	}
@@ -674,44 +669,86 @@ void ucb1x00_unregister_driver(struct ucb1x00_driver *drv)
 	mutex_unlock(&ucb1x00_mutex);
 }
 
-static int ucb1x00_suspend(struct mcp *mcp, pm_message_t state)
+static int ucb1x00_suspend(struct device *dev)
 {
-	struct ucb1x00 *ucb = mcp_get_drvdata(mcp);
-	struct ucb1x00_dev *dev;
+	struct ucb1x00_plat_data *pdata = dev->platform_data;
+	struct ucb1x00 *ucb = dev_get_drvdata(dev);
+	struct ucb1x00_dev *udev;
 
 	mutex_lock(&ucb1x00_mutex);
-	list_for_each_entry(dev, &ucb->devs, dev_node) {
-		if (dev->drv->suspend)
-			dev->drv->suspend(dev, state);
+	list_for_each_entry(udev, &ucb->devs, dev_node) {
+		if (udev->drv->suspend)
+			udev->drv->suspend(udev);
 	}
 	mutex_unlock(&ucb1x00_mutex);
+
+	if (ucb->irq_wake) {
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&ucb->irq_lock, flags);
+		ucb1x00_enable(ucb);
+		ucb1x00_reg_write(ucb, UCB_IE_RIS, ucb->irq_ris_enbl &
+				  ucb->irq_wake);
+		ucb1x00_reg_write(ucb, UCB_IE_FAL, ucb->irq_fal_enbl &
+				  ucb->irq_wake);
+		ucb1x00_disable(ucb);
+		raw_spin_unlock_irqrestore(&ucb->irq_lock, flags);
+
+		enable_irq_wake(ucb->irq);
+	} else if (pdata && pdata->reset)
+		pdata->reset(UCB_RST_SUSPEND);
+
 	return 0;
 }
 
-static int ucb1x00_resume(struct mcp *mcp)
+static int ucb1x00_resume(struct device *dev)
 {
-	struct ucb1x00 *ucb = mcp_get_drvdata(mcp);
-	struct ucb1x00_dev *dev;
+	struct ucb1x00_plat_data *pdata = dev->platform_data;
+	struct ucb1x00 *ucb = dev_get_drvdata(dev);
+	struct ucb1x00_dev *udev;
+
+	if (!ucb->irq_wake && pdata && pdata->reset)
+		pdata->reset(UCB_RST_RESUME);
 
+	ucb1x00_enable(ucb);
 	ucb1x00_reg_write(ucb, UCB_IO_DATA, ucb->io_out);
 	ucb1x00_reg_write(ucb, UCB_IO_DIR, ucb->io_dir);
+
+	if (ucb->irq_wake) {
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&ucb->irq_lock, flags);
+		ucb1x00_reg_write(ucb, UCB_IE_RIS, ucb->irq_ris_enbl &
+				  ucb->irq_mask);
+		ucb1x00_reg_write(ucb, UCB_IE_FAL, ucb->irq_fal_enbl &
+				  ucb->irq_mask);
+		raw_spin_unlock_irqrestore(&ucb->irq_lock, flags);
+
+		disable_irq_wake(ucb->irq);
+	}
+	ucb1x00_disable(ucb);
+
 	mutex_lock(&ucb1x00_mutex);
-	list_for_each_entry(dev, &ucb->devs, dev_node) {
-		if (dev->drv->resume)
-			dev->drv->resume(dev);
+	list_for_each_entry(udev, &ucb->devs, dev_node) {
+		if (udev->drv->resume)
+			udev->drv->resume(udev);
 	}
 	mutex_unlock(&ucb1x00_mutex);
 	return 0;
 }
 
+static const struct dev_pm_ops ucb1x00_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(ucb1x00_suspend, ucb1x00_resume)
+};
+
 static struct mcp_driver ucb1x00_driver = {
 	.drv		= {
 		.name	= "ucb1x00",
+		.owner	= THIS_MODULE,
+		.pm	= &ucb1x00_pm_ops,
 	},
 	.probe		= ucb1x00_probe,
 	.remove		= ucb1x00_remove,
-	.suspend	= ucb1x00_suspend,
-	.resume		= ucb1x00_resume,
 };
 
 static int __init ucb1x00_init(void)
@@ -742,14 +779,10 @@ EXPORT_SYMBOL(ucb1x00_adc_enable);
 EXPORT_SYMBOL(ucb1x00_adc_read);
 EXPORT_SYMBOL(ucb1x00_adc_disable);
 
-EXPORT_SYMBOL(ucb1x00_hook_irq);
-EXPORT_SYMBOL(ucb1x00_free_irq);
-EXPORT_SYMBOL(ucb1x00_enable_irq);
-EXPORT_SYMBOL(ucb1x00_disable_irq);
-
 EXPORT_SYMBOL(ucb1x00_register_driver);
 EXPORT_SYMBOL(ucb1x00_unregister_driver);
 
+MODULE_ALIAS("mcp:ucb1x00");
 MODULE_AUTHOR("Russell King <rmk@arm.linux.org.uk>");
 MODULE_DESCRIPTION("UCB1x00 core driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/ucb1x00-ts.c b/drivers/mfd/ucb1x00-ts.c
index 63a3cbdfa3f3..1e0e20c0e082 100644
--- a/drivers/mfd/ucb1x00-ts.c
+++ b/drivers/mfd/ucb1x00-ts.c
@@ -20,8 +20,9 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
-#include <linux/smp.h>
+#include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/string.h>
@@ -32,7 +33,6 @@
 #include <linux/kthread.h>
 #include <linux/mfd/ucb1x00.h>
 
-#include <mach/dma.h>
 #include <mach/collie.h>
 #include <asm/mach-types.h>
 
@@ -42,6 +42,8 @@ struct ucb1x00_ts {
 	struct input_dev	*idev;
 	struct ucb1x00		*ucb;
 
+	spinlock_t		irq_lock;
+	unsigned		irq_disabled;
 	wait_queue_head_t	irq_wait;
 	struct task_struct	*rtask;
 	u16			x_res;
@@ -238,7 +240,12 @@ static int ucb1x00_thread(void *_ts)
 		if (ucb1x00_ts_pen_down(ts)) {
 			set_current_state(TASK_INTERRUPTIBLE);
 
-			ucb1x00_enable_irq(ts->ucb, UCB_IRQ_TSPX, machine_is_collie() ? UCB_RISING : UCB_FALLING);
+			spin_lock_irq(&ts->irq_lock);
+			if (ts->irq_disabled) {
+				ts->irq_disabled = 0;
+				enable_irq(ts->ucb->irq_base + UCB_IRQ_TSPX);
+			}
+			spin_unlock_irq(&ts->irq_lock);
 			ucb1x00_disable(ts->ucb);
 
 			/*
@@ -281,23 +288,37 @@ static int ucb1x00_thread(void *_ts)
  * We only detect touch screen _touches_ with this interrupt
  * handler, and even then we just schedule our task.
  */
-static void ucb1x00_ts_irq(int idx, void *id)
+static irqreturn_t ucb1x00_ts_irq(int irq, void *id)
 {
 	struct ucb1x00_ts *ts = id;
 
-	ucb1x00_disable_irq(ts->ucb, UCB_IRQ_TSPX, UCB_FALLING);
+	spin_lock(&ts->irq_lock);
+	ts->irq_disabled = 1;
+	disable_irq_nosync(ts->ucb->irq_base + UCB_IRQ_TSPX);
+	spin_unlock(&ts->irq_lock);
 	wake_up(&ts->irq_wait);
+
+	return IRQ_HANDLED;
 }
 
 static int ucb1x00_ts_open(struct input_dev *idev)
 {
 	struct ucb1x00_ts *ts = input_get_drvdata(idev);
+	unsigned long flags = 0;
 	int ret = 0;
 
 	BUG_ON(ts->rtask);
 
+	if (machine_is_collie())
+		flags = IRQF_TRIGGER_RISING;
+	else
+		flags = IRQF_TRIGGER_FALLING;
+
+	ts->irq_disabled = 0;
+
 	init_waitqueue_head(&ts->irq_wait);
-	ret = ucb1x00_hook_irq(ts->ucb, UCB_IRQ_TSPX, ucb1x00_ts_irq, ts);
+	ret = request_irq(ts->ucb->irq_base + UCB_IRQ_TSPX, ucb1x00_ts_irq,
+			  flags, "ucb1x00-ts", ts);
 	if (ret < 0)
 		goto out;
 
@@ -314,7 +335,7 @@ static int ucb1x00_ts_open(struct input_dev *idev)
 	if (!IS_ERR(ts->rtask)) {
 		ret = 0;
 	} else {
-		ucb1x00_free_irq(ts->ucb, UCB_IRQ_TSPX, ts);
+		free_irq(ts->ucb->irq_base + UCB_IRQ_TSPX, ts);
 		ts->rtask = NULL;
 		ret = -EFAULT;
 	}
@@ -334,7 +355,7 @@ static void ucb1x00_ts_close(struct input_dev *idev)
 		kthread_stop(ts->rtask);
 
 	ucb1x00_enable(ts->ucb);
-	ucb1x00_free_irq(ts->ucb, UCB_IRQ_TSPX, ts);
+	free_irq(ts->ucb->irq_base + UCB_IRQ_TSPX, ts);
 	ucb1x00_reg_write(ts->ucb, UCB_TS_CR, 0);
 	ucb1x00_disable(ts->ucb);
 }
@@ -359,11 +380,13 @@ static int ucb1x00_ts_add(struct ucb1x00_dev *dev)
 	ts->ucb = dev->ucb;
 	ts->idev = idev;
 	ts->adcsync = adcsync ? UCB_SYNC : UCB_NOSYNC;
+	spin_lock_init(&ts->irq_lock);
 
 	idev->name       = "Touchscreen panel";
 	idev->id.product = ts->ucb->id;
 	idev->open       = ucb1x00_ts_open;
 	idev->close      = ucb1x00_ts_close;
+	idev->dev.parent = &ts->ucb->dev;
 
 	idev->evbit[0]   = BIT_MASK(EV_ABS) | BIT_MASK(EV_KEY);
 	idev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH);
diff --git a/drivers/mfd/wm831x-spi.c b/drivers/mfd/wm831x-spi.c
index 745c87945664..4bceee98f0a4 100644
--- a/drivers/mfd/wm831x-spi.c
+++ b/drivers/mfd/wm831x-spi.c
@@ -89,7 +89,7 @@ static const struct spi_device_id wm831x_spi_ids[] = {
 	{ "wm8326", WM8326 },
 	{ },
 };
-MODULE_DEVICE_TABLE(spi, wm831x_spi_id);
+MODULE_DEVICE_TABLE(spi, wm831x_spi_ids);
 
 static struct spi_driver wm831x_spi_driver = {
 	.driver = {
diff --git a/drivers/mfd/wm8400-core.c b/drivers/mfd/wm8400-core.c
index 237764ae5f9b..1189a17f0f25 100644
--- a/drivers/mfd/wm8400-core.c
+++ b/drivers/mfd/wm8400-core.c
@@ -271,8 +271,7 @@ static int wm8400_init(struct wm8400 *wm8400,
 		return -EIO;
 	}
 	if (i != reg_data[WM8400_RESET_ID].default_val) {
-		dev_err(wm8400->dev, "Device is not a WM8400, ID is %x\n",
-			reg);
+		dev_err(wm8400->dev, "Device is not a WM8400, ID is %x\n", i);
 		return -ENODEV;
 	}
 
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index 98733d408fee..9d7ca1e978fa 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -639,7 +639,7 @@ static __devinit int wm8994_device_init(struct wm8994 *wm8994, int irq)
 	}
 
 	pm_runtime_enable(wm8994->dev);
-	pm_runtime_resume(wm8994->dev);
+	pm_runtime_idle(wm8994->dev);
 
 	return 0;
 
diff --git a/drivers/mfd/wm8994-regmap.c b/drivers/mfd/wm8994-regmap.c
index 7605b6095453..bfd25af6ecb1 100644
--- a/drivers/mfd/wm8994-regmap.c
+++ b/drivers/mfd/wm8994-regmap.c
@@ -20,7 +20,6 @@
 #include "wm8994.h"
 
 static struct reg_default wm1811_defaults[] = {
-	{ 0x0000, 0x1811 },    /* R0    - Software Reset */
 	{ 0x0001, 0x0000 },    /* R1    - Power Management (1) */
 	{ 0x0002, 0x6000 },    /* R2    - Power Management (2) */
 	{ 0x0003, 0x0000 },    /* R3    - Power Management (3) */
@@ -61,7 +60,7 @@ static struct reg_default wm1811_defaults[] = {
 	{ 0x0036, 0x0000 },    /* R54   - Speaker Mixer */
 	{ 0x0037, 0x0000 },    /* R55   - Additional Control */
 	{ 0x0038, 0x0000 },    /* R56   - AntiPOP (1) */
-	{ 0x0039, 0x0180 },    /* R57   - AntiPOP (2) */
+	{ 0x0039, 0x0000 },    /* R57   - AntiPOP (2) */
 	{ 0x003B, 0x000D },    /* R59   - LDO 1 */
 	{ 0x003C, 0x0003 },    /* R60   - LDO 2 */
 	{ 0x003D, 0x0039 },    /* R61   - MICBIAS1 */
@@ -69,16 +68,12 @@ static struct reg_default wm1811_defaults[] = {
 	{ 0x004C, 0x1F25 },    /* R76   - Charge Pump (1) */
 	{ 0x004D, 0xAB19 },    /* R77   - Charge Pump (2) */
 	{ 0x0051, 0x0004 },    /* R81   - Class W (1) */
-	{ 0x0054, 0x0000 },    /* R84   - DC Servo (1) */
 	{ 0x0055, 0x054A },    /* R85   - DC Servo (2) */
-	{ 0x0058, 0x0000 },    /* R88   - DC Servo Readback */
 	{ 0x0059, 0x0000 },    /* R89   - DC Servo (4) */
 	{ 0x0060, 0x0000 },    /* R96   - Analogue HP (1) */
 	{ 0x00C5, 0x0000 },    /* R197  - Class D Test (5) */
 	{ 0x00D0, 0x7600 },    /* R208  - Mic Detect 1 */
 	{ 0x00D1, 0x007F },    /* R209  - Mic Detect 2 */
-	{ 0x00D2, 0x0000 },    /* R210  - Mic Detect 3 */
-	{ 0x0100, 0x0100 },    /* R256  - Chip Revision */
 	{ 0x0101, 0x8004 },    /* R257  - Control Interface */
 	{ 0x0200, 0x0000 },    /* R512  - AIF1 Clocking (1) */
 	{ 0x0201, 0x0000 },    /* R513  - AIF1 Clocking (2) */
@@ -88,7 +83,6 @@ static struct reg_default wm1811_defaults[] = {
 	{ 0x0209, 0x0000 },    /* R521  - Clocking (2) */
 	{ 0x0210, 0x0083 },    /* R528  - AIF1 Rate */
 	{ 0x0211, 0x0083 },    /* R529  - AIF2 Rate */
-	{ 0x0212, 0x0000 },    /* R530  - Rate Status */
 	{ 0x0220, 0x0000 },    /* R544  - FLL1 Control (1) */
 	{ 0x0221, 0x0000 },    /* R545  - FLL1 Control (2) */
 	{ 0x0222, 0x0000 },    /* R546  - FLL1 Control (3) */
@@ -218,8 +212,6 @@ static struct reg_default wm1811_defaults[] = {
 	{ 0x070A, 0xA101 },    /* R1802 - GPIO 11 */
 	{ 0x0720, 0x0000 },    /* R1824 - Pull Control (1) */
 	{ 0x0721, 0x0156 },    /* R1825 - Pull Control (2) */
-	{ 0x0730, 0x0000 },    /* R1840 - Interrupt Status 1 */
-	{ 0x0731, 0x0000 },    /* R1841 - Interrupt Status 2 */
 	{ 0x0732, 0x0000 },    /* R1842 - Interrupt Raw Status 2 */
 	{ 0x0738, 0x07FF },    /* R1848 - Interrupt Status 1 Mask */
 	{ 0x0739, 0xDFEF },    /* R1849 - Interrupt Status 2 Mask */
@@ -228,7 +220,6 @@ static struct reg_default wm1811_defaults[] = {
 };
 
 static struct reg_default wm8994_defaults[] = {
-	{ 0x0000, 0x8994 },    /* R0     - Software Reset */ 
 	{ 0x0001, 0x0000 },    /* R1     - Power Management (1) */ 
 	{ 0x0002, 0x6000 },    /* R2     - Power Management (2) */ 
 	{ 0x0003, 0x0000 },    /* R3     - Power Management (3) */ 
@@ -275,12 +266,9 @@ static struct reg_default wm8994_defaults[] = {
 	{ 0x003C, 0x0003 },    /* R60    - LDO 2 */ 
 	{ 0x004C, 0x1F25 },    /* R76    - Charge Pump (1) */ 
 	{ 0x0051, 0x0004 },    /* R81    - Class W (1) */ 
-	{ 0x0054, 0x0000 },    /* R84    - DC Servo (1) */ 
 	{ 0x0055, 0x054A },    /* R85    - DC Servo (2) */ 
 	{ 0x0057, 0x0000 },    /* R87    - DC Servo (4) */ 
-	{ 0x0058, 0x0000 },    /* R88    - DC Servo Readback */ 
 	{ 0x0060, 0x0000 },    /* R96    - Analogue HP (1) */ 
-	{ 0x0100, 0x0003 },    /* R256   - Chip Revision */ 
 	{ 0x0101, 0x8004 },    /* R257   - Control Interface */ 
 	{ 0x0110, 0x0000 },    /* R272   - Write Sequencer Ctrl (1) */ 
 	{ 0x0111, 0x0000 },    /* R273   - Write Sequencer Ctrl (2) */ 
@@ -292,7 +280,6 @@ static struct reg_default wm8994_defaults[] = {
 	{ 0x0209, 0x0000 },    /* R521   - Clocking (2) */ 
 	{ 0x0210, 0x0083 },    /* R528   - AIF1 Rate */ 
 	{ 0x0211, 0x0083 },    /* R529   - AIF2 Rate */ 
-	{ 0x0212, 0x0000 },    /* R530   - Rate Status */ 
 	{ 0x0220, 0x0000 },    /* R544   - FLL1 Control (1) */ 
 	{ 0x0221, 0x0000 },    /* R545   - FLL1 Control (2) */ 
 	{ 0x0222, 0x0000 },    /* R546   - FLL1 Control (3) */ 
@@ -445,9 +432,6 @@ static struct reg_default wm8994_defaults[] = {
 	{ 0x070A, 0xA101 },    /* R1802  - GPIO 11 */ 
 	{ 0x0720, 0x0000 },    /* R1824  - Pull Control (1) */ 
 	{ 0x0721, 0x0156 },    /* R1825  - Pull Control (2) */ 
-	{ 0x0730, 0x0000 },    /* R1840  - Interrupt Status 1 */ 
-	{ 0x0731, 0x0000 },    /* R1841  - Interrupt Status 2 */ 
-	{ 0x0732, 0x0000 },    /* R1842  - Interrupt Raw Status 2 */ 
 	{ 0x0738, 0x07FF },    /* R1848  - Interrupt Status 1 Mask */ 
 	{ 0x0739, 0xFFFF },    /* R1849  - Interrupt Status 2 Mask */ 
 	{ 0x0740, 0x0000 },    /* R1856  - Interrupt Control */ 
@@ -455,7 +439,6 @@ static struct reg_default wm8994_defaults[] = {
 };
 
 static struct reg_default wm8958_defaults[] = {
-	{ 0x0000, 0x8958 },    /* R0     - Software Reset */ 
 	{ 0x0001, 0x0000 },    /* R1     - Power Management (1) */
 	{ 0x0002, 0x6000 },    /* R2     - Power Management (2) */
 	{ 0x0003, 0x0000 },    /* R3     - Power Management (3) */
@@ -970,6 +953,7 @@ static bool wm8994_readable_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case WM8994_DC_SERVO_READBACK:
+	case WM8994_MICBIAS:
 	case WM8994_WRITE_SEQUENCER_CTRL_1:
 	case WM8994_WRITE_SEQUENCER_CTRL_2:
 	case WM8994_AIF1_ADC2_LEFT_VOLUME:
diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c
index 1c034b80d408..6673e578b3e9 100644
--- a/drivers/misc/ibmasm/ibmasmfs.c
+++ b/drivers/misc/ibmasm/ibmasmfs.c
@@ -500,12 +500,6 @@ static ssize_t r_heartbeat_file_write(struct file *file, const char __user *buf,
 	return 1;
 }
 
-static int remote_settings_file_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static int remote_settings_file_close(struct inode *inode, struct file *file)
 {
 	return 0;
@@ -600,7 +594,7 @@ static const struct file_operations r_heartbeat_fops = {
 };
 
 static const struct file_operations remote_settings_fops = {
-	.open =		remote_settings_file_open,
+	.open =		simple_open,
 	.release =	remote_settings_file_close,
 	.read =		remote_settings_file_read,
 	.write =	remote_settings_file_write,
diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c
index 3f7ad83ed740..3aa9a969b373 100644
--- a/drivers/misc/kgdbts.c
+++ b/drivers/misc/kgdbts.c
@@ -134,12 +134,17 @@ static int force_hwbrks;
 static int hwbreaks_ok;
 static int hw_break_val;
 static int hw_break_val2;
+static int cont_instead_of_sstep;
+static unsigned long cont_thread_id;
+static unsigned long sstep_thread_id;
 #if defined(CONFIG_ARM) || defined(CONFIG_MIPS) || defined(CONFIG_SPARC)
 static int arch_needs_sstep_emulation = 1;
 #else
 static int arch_needs_sstep_emulation;
 #endif
+static unsigned long cont_addr;
 static unsigned long sstep_addr;
+static int restart_from_top_after_write;
 static int sstep_state;
 
 /* Storage for the registers, in GDB format. */
@@ -187,7 +192,8 @@ static int kgdbts_unreg_thread(void *ptr)
 	 */
 	while (!final_ack)
 		msleep_interruptible(1500);
-
+	/* Pause for any other threads to exit after final ack. */
+	msleep_interruptible(1000);
 	if (configured)
 		kgdb_unregister_io_module(&kgdbts_io_ops);
 	configured = 0;
@@ -211,7 +217,7 @@ static unsigned long lookup_addr(char *arg)
 	if (!strcmp(arg, "kgdbts_break_test"))
 		addr = (unsigned long)kgdbts_break_test;
 	else if (!strcmp(arg, "sys_open"))
-		addr = (unsigned long)sys_open;
+		addr = (unsigned long)do_sys_open;
 	else if (!strcmp(arg, "do_fork"))
 		addr = (unsigned long)do_fork;
 	else if (!strcmp(arg, "hw_break_val"))
@@ -283,6 +289,16 @@ static void hw_break_val_write(void)
 	hw_break_val++;
 }
 
+static int get_thread_id_continue(char *put_str, char *arg)
+{
+	char *ptr = &put_str[11];
+
+	if (put_str[1] != 'T' || put_str[2] != '0')
+		return 1;
+	kgdb_hex2long(&ptr, &cont_thread_id);
+	return 0;
+}
+
 static int check_and_rewind_pc(char *put_str, char *arg)
 {
 	unsigned long addr = lookup_addr(arg);
@@ -299,13 +315,21 @@ static int check_and_rewind_pc(char *put_str, char *arg)
 	if (addr + BREAK_INSTR_SIZE == ip)
 		offset = -BREAK_INSTR_SIZE;
 #endif
-	if (strcmp(arg, "silent") && ip + offset != addr) {
+
+	if (arch_needs_sstep_emulation && sstep_addr &&
+	    ip + offset == sstep_addr &&
+	    ((!strcmp(arg, "sys_open") || !strcmp(arg, "do_fork")))) {
+		/* This is special case for emulated single step */
+		v2printk("Emul: rewind hit single step bp\n");
+		restart_from_top_after_write = 1;
+	} else if (strcmp(arg, "silent") && ip + offset != addr) {
 		eprintk("kgdbts: BP mismatch %lx expected %lx\n",
 			   ip + offset, addr);
 		return 1;
 	}
 	/* Readjust the instruction pointer if needed */
 	ip += offset;
+	cont_addr = ip;
 #ifdef GDB_ADJUSTS_BREAK_OFFSET
 	instruction_pointer_set(&kgdbts_regs, ip);
 #endif
@@ -315,6 +339,8 @@ static int check_and_rewind_pc(char *put_str, char *arg)
 static int check_single_step(char *put_str, char *arg)
 {
 	unsigned long addr = lookup_addr(arg);
+	static int matched_id;
+
 	/*
 	 * From an arch indepent point of view the instruction pointer
 	 * should be on a different instruction
@@ -324,6 +350,29 @@ static int check_single_step(char *put_str, char *arg)
 	gdb_regs_to_pt_regs(kgdbts_gdb_regs, &kgdbts_regs);
 	v2printk("Singlestep stopped at IP: %lx\n",
 		   instruction_pointer(&kgdbts_regs));
+
+	if (sstep_thread_id != cont_thread_id) {
+		/*
+		 * Ensure we stopped in the same thread id as before, else the
+		 * debugger should continue until the original thread that was
+		 * single stepped is scheduled again, emulating gdb's behavior.
+		 */
+		v2printk("ThrID does not match: %lx\n", cont_thread_id);
+		if (arch_needs_sstep_emulation) {
+			if (matched_id &&
+			    instruction_pointer(&kgdbts_regs) != addr)
+				goto continue_test;
+			matched_id++;
+			ts.idx -= 2;
+			sstep_state = 0;
+			return 0;
+		}
+		cont_instead_of_sstep = 1;
+		ts.idx -= 4;
+		return 0;
+	}
+continue_test:
+	matched_id = 0;
 	if (instruction_pointer(&kgdbts_regs) == addr) {
 		eprintk("kgdbts: SingleStep failed at %lx\n",
 			   instruction_pointer(&kgdbts_regs));
@@ -365,10 +414,40 @@ static int got_break(char *put_str, char *arg)
 	return 1;
 }
 
+static void get_cont_catch(char *arg)
+{
+	/* Always send detach because the test is completed at this point */
+	fill_get_buf("D");
+}
+
+static int put_cont_catch(char *put_str, char *arg)
+{
+	/* This is at the end of the test and we catch any and all input */
+	v2printk("kgdbts: cleanup task: %lx\n", sstep_thread_id);
+	ts.idx--;
+	return 0;
+}
+
+static int emul_reset(char *put_str, char *arg)
+{
+	if (strncmp(put_str, "$OK", 3))
+		return 1;
+	if (restart_from_top_after_write) {
+		restart_from_top_after_write = 0;
+		ts.idx = -1;
+	}
+	return 0;
+}
+
 static void emul_sstep_get(char *arg)
 {
 	if (!arch_needs_sstep_emulation) {
-		fill_get_buf(arg);
+		if (cont_instead_of_sstep) {
+			cont_instead_of_sstep = 0;
+			fill_get_buf("c");
+		} else {
+			fill_get_buf(arg);
+		}
 		return;
 	}
 	switch (sstep_state) {
@@ -398,9 +477,11 @@ static void emul_sstep_get(char *arg)
 static int emul_sstep_put(char *put_str, char *arg)
 {
 	if (!arch_needs_sstep_emulation) {
-		if (!strncmp(put_str+1, arg, 2))
-			return 0;
-		return 1;
+		char *ptr = &put_str[11];
+		if (put_str[1] != 'T' || put_str[2] != '0')
+			return 1;
+		kgdb_hex2long(&ptr, &sstep_thread_id);
+		return 0;
 	}
 	switch (sstep_state) {
 	case 1:
@@ -411,8 +492,7 @@ static int emul_sstep_put(char *put_str, char *arg)
 		v2printk("Stopped at IP: %lx\n",
 			 instruction_pointer(&kgdbts_regs));
 		/* Want to stop at IP + break instruction size by default */
-		sstep_addr = instruction_pointer(&kgdbts_regs) +
-			BREAK_INSTR_SIZE;
+		sstep_addr = cont_addr + BREAK_INSTR_SIZE;
 		break;
 	case 2:
 		if (strncmp(put_str, "$OK", 3)) {
@@ -424,6 +504,9 @@ static int emul_sstep_put(char *put_str, char *arg)
 		if (strncmp(put_str, "$T0", 3)) {
 			eprintk("kgdbts: failed continue sstep\n");
 			return 1;
+		} else {
+			char *ptr = &put_str[11];
+			kgdb_hex2long(&ptr, &sstep_thread_id);
 		}
 		break;
 	case 4:
@@ -502,10 +585,10 @@ static struct test_struct bad_read_test[] = {
 static struct test_struct singlestep_break_test[] = {
 	{ "?", "S0*" }, /* Clear break points */
 	{ "kgdbts_break_test", "OK", sw_break, }, /* set sw breakpoint */
-	{ "c", "T0*", }, /* Continue */
+	{ "c", "T0*", NULL, get_thread_id_continue }, /* Continue */
+	{ "kgdbts_break_test", "OK", sw_rem_break }, /*remove breakpoint */
 	{ "g", "kgdbts_break_test", NULL, check_and_rewind_pc },
 	{ "write", "OK", write_regs }, /* Write registers */
-	{ "kgdbts_break_test", "OK", sw_rem_break }, /*remove breakpoint */
 	{ "s", "T0*", emul_sstep_get, emul_sstep_put }, /* Single step */
 	{ "g", "kgdbts_break_test", NULL, check_single_step },
 	{ "kgdbts_break_test", "OK", sw_break, }, /* set sw breakpoint */
@@ -523,16 +606,16 @@ static struct test_struct singlestep_break_test[] = {
 static struct test_struct do_fork_test[] = {
 	{ "?", "S0*" }, /* Clear break points */
 	{ "do_fork", "OK", sw_break, }, /* set sw breakpoint */
-	{ "c", "T0*", }, /* Continue */
-	{ "g", "do_fork", NULL, check_and_rewind_pc }, /* check location */
-	{ "write", "OK", write_regs }, /* Write registers */
+	{ "c", "T0*", NULL, get_thread_id_continue }, /* Continue */
 	{ "do_fork", "OK", sw_rem_break }, /*remove breakpoint */
+	{ "g", "do_fork", NULL, check_and_rewind_pc }, /* check location */
+	{ "write", "OK", write_regs, emul_reset }, /* Write registers */
 	{ "s", "T0*", emul_sstep_get, emul_sstep_put }, /* Single step */
 	{ "g", "do_fork", NULL, check_single_step },
 	{ "do_fork", "OK", sw_break, }, /* set sw breakpoint */
 	{ "7", "T0*", skip_back_repeat_test }, /* Loop based on repeat_test */
 	{ "D", "OK", NULL, final_ack_set }, /* detach and unregister I/O */
-	{ "", "" },
+	{ "", "", get_cont_catch, put_cont_catch },
 };
 
 /* Test for hitting a breakpoint at sys_open for what ever the number
@@ -541,16 +624,16 @@ static struct test_struct do_fork_test[] = {
 static struct test_struct sys_open_test[] = {
 	{ "?", "S0*" }, /* Clear break points */
 	{ "sys_open", "OK", sw_break, }, /* set sw breakpoint */
-	{ "c", "T0*", }, /* Continue */
-	{ "g", "sys_open", NULL, check_and_rewind_pc }, /* check location */
-	{ "write", "OK", write_regs }, /* Write registers */
+	{ "c", "T0*", NULL, get_thread_id_continue }, /* Continue */
 	{ "sys_open", "OK", sw_rem_break }, /*remove breakpoint */
+	{ "g", "sys_open", NULL, check_and_rewind_pc }, /* check location */
+	{ "write", "OK", write_regs, emul_reset }, /* Write registers */
 	{ "s", "T0*", emul_sstep_get, emul_sstep_put }, /* Single step */
 	{ "g", "sys_open", NULL, check_single_step },
 	{ "sys_open", "OK", sw_break, }, /* set sw breakpoint */
 	{ "7", "T0*", skip_back_repeat_test }, /* Loop based on repeat_test */
 	{ "D", "OK", NULL, final_ack_set }, /* detach and unregister I/O */
-	{ "", "" },
+	{ "", "", get_cont_catch, put_cont_catch },
 };
 
 /*
@@ -693,8 +776,8 @@ static int run_simple_test(int is_get_char, int chr)
 	/* This callback is a put char which is when kgdb sends data to
 	 * this I/O module.
 	 */
-	if (ts.tst[ts.idx].get[0] == '\0' &&
-		ts.tst[ts.idx].put[0] == '\0') {
+	if (ts.tst[ts.idx].get[0] == '\0' && ts.tst[ts.idx].put[0] == '\0' &&
+	    !ts.tst[ts.idx].get_handler) {
 		eprintk("kgdbts: ERROR: beyond end of test on"
 			   " '%s' line %i\n", ts.name, ts.idx);
 		return 0;
@@ -907,6 +990,17 @@ static void kgdbts_run_tests(void)
 	if (ptr)
 		sstep_test = simple_strtol(ptr+1, NULL, 10);
 
+	/* All HW break point tests */
+	if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT) {
+		hwbreaks_ok = 1;
+		v1printk("kgdbts:RUN hw breakpoint test\n");
+		run_breakpoint_test(1);
+		v1printk("kgdbts:RUN hw write breakpoint test\n");
+		run_hw_break_test(1);
+		v1printk("kgdbts:RUN access write breakpoint test\n");
+		run_hw_break_test(0);
+	}
+
 	/* required internal KGDB tests */
 	v1printk("kgdbts:RUN plant and detach test\n");
 	run_plant_and_detach_test(0);
@@ -924,35 +1018,11 @@ static void kgdbts_run_tests(void)
 
 	/* ===Optional tests=== */
 
-	/* All HW break point tests */
-	if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT) {
-		hwbreaks_ok = 1;
-		v1printk("kgdbts:RUN hw breakpoint test\n");
-		run_breakpoint_test(1);
-		v1printk("kgdbts:RUN hw write breakpoint test\n");
-		run_hw_break_test(1);
-		v1printk("kgdbts:RUN access write breakpoint test\n");
-		run_hw_break_test(0);
-	}
-
 	if (nmi_sleep) {
 		v1printk("kgdbts:RUN NMI sleep %i seconds test\n", nmi_sleep);
 		run_nmi_sleep_test(nmi_sleep);
 	}
 
-#ifdef CONFIG_DEBUG_RODATA
-	/* Until there is an api to write to read-only text segments, use
-	 * HW breakpoints for the remainder of any tests, else print a
-	 * failure message if hw breakpoints do not work.
-	 */
-	if (!(arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT && hwbreaks_ok)) {
-		eprintk("kgdbts: HW breakpoints do not work,"
-			"skipping remaining tests\n");
-		return;
-	}
-	force_hwbrks = 1;
-#endif /* CONFIG_DEBUG_RODATA */
-
 	/* If the do_fork test is run it will be the last test that is
 	 * executed because a kernel thread will be spawned at the very
 	 * end to unregister the debug hooks.
diff --git a/drivers/misc/sgi-gru/gru_instructions.h b/drivers/misc/sgi-gru/gru_instructions.h
index d95587cc794c..04d5170ac149 100644
--- a/drivers/misc/sgi-gru/gru_instructions.h
+++ b/drivers/misc/sgi-gru/gru_instructions.h
@@ -40,6 +40,7 @@ extern void gru_wait_abort_proc(void *cb);
 			*((volatile unsigned long *)(p)) = v; /* force st.rel */	\
 		} while (0)
 #elif defined(CONFIG_X86_64)
+#include <asm/cacheflush.h>
 #define __flush_cache(p)		clflush(p)
 #define gru_ordered_store_ulong(p, v)					\
 		do {							\
diff --git a/drivers/misc/sgi-xp/xp.h b/drivers/misc/sgi-xp/xp.h
index 851b2f25ce0e..c862cd4583cc 100644
--- a/drivers/misc/sgi-xp/xp.h
+++ b/drivers/misc/sgi-xp/xp.h
@@ -25,7 +25,6 @@
 #endif
 
 #if defined CONFIG_IA64
-#include <asm/system.h>
 #include <asm/sn/arch.h>	/* defines is_shub1() and is_shub2() */
 #define is_shub()	ia64_platform_is("sn2")
 #endif
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index e5a3c7b6dedb..eed213a5c8cb 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -41,7 +41,6 @@
 #include <linux/mmc/mmc.h>
 #include <linux/mmc/sd.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "queue.h"
@@ -1080,6 +1079,7 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 	struct mmc_blk_request *brq = &mqrq->brq;
 	struct request *req = mqrq->req;
 	struct mmc_blk_data *md = mq->data;
+	bool do_data_tag;
 
 	/*
 	 * Reliable writes are used to implement Forced Unit Access and
@@ -1156,6 +1156,16 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 		mmc_apply_rel_rw(brq, card, req);
 
 	/*
+	 * Data tag is used only during writing meta data to speed
+	 * up write and any subsequent read of this meta data
+	 */
+	do_data_tag = (card->ext_csd.data_tag_unit_size) &&
+		(req->cmd_flags & REQ_META) &&
+		(rq_data_dir(req) == WRITE) &&
+		((brq->data.blocks * brq->data.blksz) >=
+		 card->ext_csd.data_tag_unit_size);
+
+	/*
 	 * Pre-defined multi-block transfers are preferable to
 	 * open ended-ones (and necessary for reliable writes).
 	 * However, it is not sufficient to just send CMD23,
@@ -1173,13 +1183,13 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 	 * We'll avoid using CMD23-bounded multiblock writes for
 	 * these, while retaining features like reliable writes.
 	 */
-
-	if ((md->flags & MMC_BLK_CMD23) &&
-	    mmc_op_multi(brq->cmd.opcode) &&
-	    (do_rel_wr || !(card->quirks & MMC_QUIRK_BLK_NO_CMD23))) {
+	if ((md->flags & MMC_BLK_CMD23) && mmc_op_multi(brq->cmd.opcode) &&
+	    (do_rel_wr || !(card->quirks & MMC_QUIRK_BLK_NO_CMD23) ||
+	     do_data_tag)) {
 		brq->sbc.opcode = MMC_SET_BLOCK_COUNT;
 		brq->sbc.arg = brq->data.blocks |
-			(do_rel_wr ? (1 << 31) : 0);
+			(do_rel_wr ? (1 << 31) : 0) |
+			(do_data_tag ? (1 << 29) : 0);
 		brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC;
 		brq->mrq.sbc = &brq->sbc;
 	}
diff --git a/drivers/mmc/core/cd-gpio.c b/drivers/mmc/core/cd-gpio.c
index 082202ae4a03..29de31e260dd 100644
--- a/drivers/mmc/core/cd-gpio.c
+++ b/drivers/mmc/core/cd-gpio.c
@@ -28,13 +28,17 @@ static irqreturn_t mmc_cd_gpio_irqt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-int mmc_cd_gpio_request(struct mmc_host *host, unsigned int gpio,
-			unsigned int irq, unsigned long flags)
+int mmc_cd_gpio_request(struct mmc_host *host, unsigned int gpio)
 {
 	size_t len = strlen(dev_name(host->parent)) + 4;
-	struct mmc_cd_gpio *cd = kmalloc(sizeof(*cd) + len, GFP_KERNEL);
+	struct mmc_cd_gpio *cd;
+	int irq = gpio_to_irq(gpio);
 	int ret;
 
+	if (irq < 0)
+		return irq;
+
+	cd = kmalloc(sizeof(*cd) + len, GFP_KERNEL);
 	if (!cd)
 		return -ENOMEM;
 
@@ -45,7 +49,8 @@ int mmc_cd_gpio_request(struct mmc_host *host, unsigned int gpio,
 		goto egpioreq;
 
 	ret = request_threaded_irq(irq, NULL, mmc_cd_gpio_irqt,
-				   flags, cd->label, host);
+				   IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
+				   cd->label, host);
 	if (ret < 0)
 		goto eirqreq;
 
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 132378b89d76..14f262e9246d 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -188,6 +188,12 @@ mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 	struct scatterlist *sg;
 #endif
 
+	if (mrq->sbc) {
+		pr_debug("<%s: starting CMD%u arg %08x flags %08x>\n",
+			 mmc_hostname(host), mrq->sbc->opcode,
+			 mrq->sbc->arg, mrq->sbc->flags);
+	}
+
 	pr_debug("%s: starting CMD%u arg %08x flags %08x\n",
 		 mmc_hostname(host), mrq->cmd->opcode,
 		 mrq->cmd->arg, mrq->cmd->flags);
@@ -243,16 +249,17 @@ static void mmc_wait_done(struct mmc_request *mrq)
 	complete(&mrq->completion);
 }
 
-static void __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq)
+static int __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq)
 {
 	init_completion(&mrq->completion);
 	mrq->done = mmc_wait_done;
 	if (mmc_card_removed(host->card)) {
 		mrq->cmd->error = -ENOMEDIUM;
 		complete(&mrq->completion);
-		return;
+		return -ENOMEDIUM;
 	}
 	mmc_start_request(host, mrq);
+	return 0;
 }
 
 static void mmc_wait_for_req_done(struct mmc_host *host,
@@ -336,6 +343,7 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host,
 				    struct mmc_async_req *areq, int *error)
 {
 	int err = 0;
+	int start_err = 0;
 	struct mmc_async_req *data = host->areq;
 
 	/* Prepare a new request */
@@ -345,30 +353,23 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host,
 	if (host->areq) {
 		mmc_wait_for_req_done(host, host->areq->mrq);
 		err = host->areq->err_check(host->card, host->areq);
-		if (err) {
-			/* post process the completed failed request */
-			mmc_post_req(host, host->areq->mrq, 0);
-			if (areq)
-				/*
-				 * Cancel the new prepared request, because
-				 * it can't run until the failed
-				 * request has been properly handled.
-				 */
-				mmc_post_req(host, areq->mrq, -EINVAL);
-
-			host->areq = NULL;
-			goto out;
-		}
 	}
 
-	if (areq)
-		__mmc_start_req(host, areq->mrq);
+	if (!err && areq)
+		start_err = __mmc_start_req(host, areq->mrq);
 
 	if (host->areq)
 		mmc_post_req(host, host->areq->mrq, 0);
 
-	host->areq = areq;
- out:
+	 /* Cancel a prepared request if it was not started. */
+	if ((err || start_err) && areq)
+			mmc_post_req(host, areq->mrq, -EINVAL);
+
+	if (err)
+		host->areq = NULL;
+	else
+		host->areq = areq;
+
 	if (error)
 		*error = err;
 	return data;
@@ -599,105 +600,6 @@ unsigned int mmc_align_data_size(struct mmc_card *card, unsigned int sz)
 EXPORT_SYMBOL(mmc_align_data_size);
 
 /**
- *	mmc_host_enable - enable a host.
- *	@host: mmc host to enable
- *
- *	Hosts that support power saving can use the 'enable' and 'disable'
- *	methods to exit and enter power saving states. For more information
- *	see comments for struct mmc_host_ops.
- */
-int mmc_host_enable(struct mmc_host *host)
-{
-	if (!(host->caps & MMC_CAP_DISABLE))
-		return 0;
-
-	if (host->en_dis_recurs)
-		return 0;
-
-	if (host->nesting_cnt++)
-		return 0;
-
-	cancel_delayed_work_sync(&host->disable);
-
-	if (host->enabled)
-		return 0;
-
-	if (host->ops->enable) {
-		int err;
-
-		host->en_dis_recurs = 1;
-		mmc_host_clk_hold(host);
-		err = host->ops->enable(host);
-		mmc_host_clk_release(host);
-		host->en_dis_recurs = 0;
-
-		if (err) {
-			pr_debug("%s: enable error %d\n",
-				 mmc_hostname(host), err);
-			return err;
-		}
-	}
-	host->enabled = 1;
-	return 0;
-}
-EXPORT_SYMBOL(mmc_host_enable);
-
-static int mmc_host_do_disable(struct mmc_host *host, int lazy)
-{
-	if (host->ops->disable) {
-		int err;
-
-		host->en_dis_recurs = 1;
-		mmc_host_clk_hold(host);
-		err = host->ops->disable(host, lazy);
-		mmc_host_clk_release(host);
-		host->en_dis_recurs = 0;
-
-		if (err < 0) {
-			pr_debug("%s: disable error %d\n",
-				 mmc_hostname(host), err);
-			return err;
-		}
-		if (err > 0) {
-			unsigned long delay = msecs_to_jiffies(err);
-
-			mmc_schedule_delayed_work(&host->disable, delay);
-		}
-	}
-	host->enabled = 0;
-	return 0;
-}
-
-/**
- *	mmc_host_disable - disable a host.
- *	@host: mmc host to disable
- *
- *	Hosts that support power saving can use the 'enable' and 'disable'
- *	methods to exit and enter power saving states. For more information
- *	see comments for struct mmc_host_ops.
- */
-int mmc_host_disable(struct mmc_host *host)
-{
-	int err;
-
-	if (!(host->caps & MMC_CAP_DISABLE))
-		return 0;
-
-	if (host->en_dis_recurs)
-		return 0;
-
-	if (--host->nesting_cnt)
-		return 0;
-
-	if (!host->enabled)
-		return 0;
-
-	err = mmc_host_do_disable(host, 0);
-	return err;
-}
-EXPORT_SYMBOL(mmc_host_disable);
-
-/**
  *	__mmc_claim_host - exclusively claim a host
  *	@host: mmc host to claim
  *	@abort: whether or not the operation should be aborted
@@ -735,8 +637,8 @@ int __mmc_claim_host(struct mmc_host *host, atomic_t *abort)
 		wake_up(&host->wq);
 	spin_unlock_irqrestore(&host->lock, flags);
 	remove_wait_queue(&host->wq, &wait);
-	if (!stop)
-		mmc_host_enable(host);
+	if (host->ops->enable && !stop && host->claim_cnt == 1)
+		host->ops->enable(host);
 	return stop;
 }
 
@@ -761,21 +663,28 @@ int mmc_try_claim_host(struct mmc_host *host)
 		claimed_host = 1;
 	}
 	spin_unlock_irqrestore(&host->lock, flags);
+	if (host->ops->enable && claimed_host && host->claim_cnt == 1)
+		host->ops->enable(host);
 	return claimed_host;
 }
 EXPORT_SYMBOL(mmc_try_claim_host);
 
 /**
- *	mmc_do_release_host - release a claimed host
+ *	mmc_release_host - release a host
  *	@host: mmc host to release
  *
- *	If you successfully claimed a host, this function will
- *	release it again.
+ *	Release a MMC host, allowing others to claim the host
+ *	for their operations.
  */
-void mmc_do_release_host(struct mmc_host *host)
+void mmc_release_host(struct mmc_host *host)
 {
 	unsigned long flags;
 
+	WARN_ON(!host->claimed);
+
+	if (host->ops->disable && host->claim_cnt == 1)
+		host->ops->disable(host);
+
 	spin_lock_irqsave(&host->lock, flags);
 	if (--host->claim_cnt) {
 		/* Release for nested claim */
@@ -787,67 +696,6 @@ void mmc_do_release_host(struct mmc_host *host)
 		wake_up(&host->wq);
 	}
 }
-EXPORT_SYMBOL(mmc_do_release_host);
-
-void mmc_host_deeper_disable(struct work_struct *work)
-{
-	struct mmc_host *host =
-		container_of(work, struct mmc_host, disable.work);
-
-	/* If the host is claimed then we do not want to disable it anymore */
-	if (!mmc_try_claim_host(host))
-		return;
-	mmc_host_do_disable(host, 1);
-	mmc_do_release_host(host);
-}
-
-/**
- *	mmc_host_lazy_disable - lazily disable a host.
- *	@host: mmc host to disable
- *
- *	Hosts that support power saving can use the 'enable' and 'disable'
- *	methods to exit and enter power saving states. For more information
- *	see comments for struct mmc_host_ops.
- */
-int mmc_host_lazy_disable(struct mmc_host *host)
-{
-	if (!(host->caps & MMC_CAP_DISABLE))
-		return 0;
-
-	if (host->en_dis_recurs)
-		return 0;
-
-	if (--host->nesting_cnt)
-		return 0;
-
-	if (!host->enabled)
-		return 0;
-
-	if (host->disable_delay) {
-		mmc_schedule_delayed_work(&host->disable,
-				msecs_to_jiffies(host->disable_delay));
-		return 0;
-	} else
-		return mmc_host_do_disable(host, 1);
-}
-EXPORT_SYMBOL(mmc_host_lazy_disable);
-
-/**
- *	mmc_release_host - release a host
- *	@host: mmc host to release
- *
- *	Release a MMC host, allowing others to claim the host
- *	for their operations.
- */
-void mmc_release_host(struct mmc_host *host)
-{
-	WARN_ON(!host->claimed);
-
-	mmc_host_lazy_disable(host);
-
-	mmc_do_release_host(host);
-}
-
 EXPORT_SYMBOL(mmc_release_host);
 
 /*
@@ -2115,18 +1963,36 @@ int _mmc_detect_card_removed(struct mmc_host *host)
 int mmc_detect_card_removed(struct mmc_host *host)
 {
 	struct mmc_card *card = host->card;
+	int ret;
 
 	WARN_ON(!host->claimed);
+
+	if (!card)
+		return 1;
+
+	ret = mmc_card_removed(card);
 	/*
 	 * The card will be considered unchanged unless we have been asked to
 	 * detect a change or host requires polling to provide card detection.
 	 */
-	if (card && !host->detect_change && !(host->caps & MMC_CAP_NEEDS_POLL))
-		return mmc_card_removed(card);
+	if (!host->detect_change && !(host->caps & MMC_CAP_NEEDS_POLL) &&
+	    !(host->caps2 & MMC_CAP2_DETECT_ON_ERR))
+		return ret;
 
 	host->detect_change = 0;
+	if (!ret) {
+		ret = _mmc_detect_card_removed(host);
+		if (ret && (host->caps2 & MMC_CAP2_DETECT_ON_ERR)) {
+			/*
+			 * Schedule a detect work as soon as possible to let a
+			 * rescan handle the card removal.
+			 */
+			cancel_delayed_work(&host->detect);
+			mmc_detect_change(host, 0);
+		}
+	}
 
-	return _mmc_detect_card_removed(host);
+	return ret;
 }
 EXPORT_SYMBOL(mmc_detect_card_removed);
 
@@ -2203,8 +2069,6 @@ void mmc_stop_host(struct mmc_host *host)
 	spin_unlock_irqrestore(&host->lock, flags);
 #endif
 
-	if (host->caps & MMC_CAP_DISABLE)
-		cancel_delayed_work(&host->disable);
 	cancel_delayed_work_sync(&host->detect);
 	mmc_flush_scheduled_work();
 
@@ -2399,13 +2263,11 @@ int mmc_suspend_host(struct mmc_host *host)
 {
 	int err = 0;
 
-	if (host->caps & MMC_CAP_DISABLE)
-		cancel_delayed_work(&host->disable);
 	cancel_delayed_work(&host->detect);
 	mmc_flush_scheduled_work();
 	if (mmc_try_claim_host(host)) {
 		err = mmc_cache_ctrl(host, 0);
-		mmc_do_release_host(host);
+		mmc_release_host(host);
 	} else {
 		err = -EBUSY;
 	}
@@ -2426,7 +2288,7 @@ int mmc_suspend_host(struct mmc_host *host)
 			if (host->bus_ops->suspend) {
 				err = host->bus_ops->suspend(host);
 			}
-			mmc_do_release_host(host);
+			mmc_release_host(host);
 
 			if (err == -ENOSYS || !host->bus_ops->resume) {
 				/*
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index c3704e293a7b..91c84c7a1829 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -330,7 +330,6 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 	spin_lock_init(&host->lock);
 	init_waitqueue_head(&host->wq);
 	INIT_DELAYED_WORK(&host->detect, mmc_rescan);
-	INIT_DELAYED_WORK_DEFERRABLE(&host->disable, mmc_host_deeper_disable);
 #ifdef CONFIG_PM
 	host->pm_notify.notifier_call = mmc_pm_notify;
 #endif
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index 08a7852ade44..f2ab9e578126 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -14,7 +14,6 @@
 
 int mmc_register_host_class(void);
 void mmc_unregister_host_class(void);
-void mmc_host_deeper_disable(struct work_struct *work);
 
 #endif
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 2b9ed1401dc4..02914d609a91 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -519,6 +519,20 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd)
 			ext_csd[EXT_CSD_CACHE_SIZE + 1] << 8 |
 			ext_csd[EXT_CSD_CACHE_SIZE + 2] << 16 |
 			ext_csd[EXT_CSD_CACHE_SIZE + 3] << 24;
+
+		if (ext_csd[EXT_CSD_DATA_SECTOR_SIZE] == 1)
+			card->ext_csd.data_sector_size = 4096;
+		else
+			card->ext_csd.data_sector_size = 512;
+
+		if ((ext_csd[EXT_CSD_DATA_TAG_SUPPORT] & 1) &&
+		    (ext_csd[EXT_CSD_TAG_UNIT_SIZE] <= 8)) {
+			card->ext_csd.data_tag_unit_size =
+			((unsigned int) 1 << ext_csd[EXT_CSD_TAG_UNIT_SIZE]) *
+			(card->ext_csd.data_sector_size);
+		} else {
+			card->ext_csd.data_tag_unit_size = 0;
+		}
 	}
 
 out:
@@ -938,7 +952,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	 * If enhanced_area_en is TRUE, host needs to enable ERASE_GRP_DEF
 	 * bit.  This bit will be lost every time after a reset or power off.
 	 */
-	if (card->ext_csd.enhanced_area_en) {
+	if (card->ext_csd.enhanced_area_en ||
+	    (card->ext_csd.rev >= 3 && (host->caps2 & MMC_CAP2_HC_ERASE_SZ))) {
 		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				 EXT_CSD_ERASE_GROUP_DEF, 1,
 				 card->ext_csd.generic_cmd6_time);
@@ -1033,22 +1048,6 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	}
 
 	/*
-	 * Enable HPI feature (if supported)
-	 */
-	if (card->ext_csd.hpi) {
-		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			EXT_CSD_HPI_MGMT, 1, 0);
-		if (err && err != -EBADMSG)
-			goto free_card;
-		if (err) {
-			pr_warning("%s: Enabling HPI failed\n",
-				   mmc_hostname(card->host));
-			err = 0;
-		} else
-			card->ext_csd.hpi_en = 1;
-	}
-
-	/*
 	 * Compute bus speed.
 	 */
 	max_dtr = (unsigned int)-1;
@@ -1097,9 +1096,12 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		 * 4. execute tuning for HS200
 		 */
 		if ((host->caps2 & MMC_CAP2_HS200) &&
-		    card->host->ops->execute_tuning)
+		    card->host->ops->execute_tuning) {
+			mmc_host_clk_hold(card->host);
 			err = card->host->ops->execute_tuning(card->host,
 				MMC_SEND_TUNING_BLOCK_HS200);
+			mmc_host_clk_release(card->host);
+		}
 		if (err) {
 			pr_warning("%s: tuning execution failed\n",
 				   mmc_hostname(card->host));
@@ -1219,6 +1221,23 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	}
 
 	/*
+	 * Enable HPI feature (if supported)
+	 */
+	if (card->ext_csd.hpi) {
+		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+				EXT_CSD_HPI_MGMT, 1,
+				card->ext_csd.generic_cmd6_time);
+		if (err && err != -EBADMSG)
+			goto free_card;
+		if (err) {
+			pr_warning("%s: Enabling HPI failed\n",
+				   mmc_hostname(card->host));
+			err = 0;
+		} else
+			card->ext_csd.hpi_en = 1;
+	}
+
+	/*
 	 * If cache size is higher than 0, this indicates
 	 * the existence of cache and it can be turned on.
 	 */
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 4d41fa984c93..69370f494e05 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -553,18 +553,22 @@ int mmc_send_hpi_cmd(struct mmc_card *card, u32 *status)
 {
 	struct mmc_command cmd = {0};
 	unsigned int opcode;
-	unsigned int flags;
 	int err;
 
+	if (!card->ext_csd.hpi) {
+		pr_warning("%s: Card didn't support HPI command\n",
+			   mmc_hostname(card->host));
+		return -EINVAL;
+	}
+
 	opcode = card->ext_csd.hpi_cmd;
 	if (opcode == MMC_STOP_TRANSMISSION)
-		flags = MMC_RSP_R1 | MMC_CMD_AC;
+		cmd.flags = MMC_RSP_R1B | MMC_CMD_AC;
 	else if (opcode == MMC_SEND_STATUS)
-		flags = MMC_RSP_R1 | MMC_CMD_AC;
+		cmd.flags = MMC_RSP_R1 | MMC_CMD_AC;
 
 	cmd.opcode = opcode;
 	cmd.arg = card->rca << 16 | 1;
-	cmd.flags = flags;
 	cmd.cmd_timeout_ms = card->ext_csd.out_of_int_time;
 
 	err = mmc_wait_for_cmd(card->host, &cmd, 0);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index ecbee9bf87b2..2bc06e7344db 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -533,6 +533,31 @@ config MMC_DW_IDMAC
 	  Designware Mobile Storage IP block. This disables the external DMA
 	  interface.
 
+config MMC_DW_PLTFM
+	tristate "Synopsys Designware MCI Support as platform device"
+	depends on MMC_DW
+	default y
+	help
+	  This selects the common helper functions support for Host Controller
+	  Interface based platform driver. Please select this option if the IP
+	  is present as a platform device. This is the common interface for the
+	  Synopsys Designware IP.
+
+	  If you have a controller with this interface, say Y or M here.
+
+	  If unsure, say Y.
+
+config MMC_DW_PCI
+	tristate "Synopsys Designware MCI support on PCI bus"
+	depends on MMC_DW && PCI
+	help
+	  This selects the PCI bus for the Synopsys Designware Mobile Storage IP.
+	  Select this option if the IP is present on PCI platform.
+
+	  If you have a controller with this interface, say Y or M here.
+
+	  If unsure, say N.
+
 config MMC_SH_MMCIF
 	tristate "SuperH Internal MMCIF support"
 	depends on MMC_BLOCK && (SUPERH || ARCH_SHMOBILE)
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index 745f8fce2519..3e7e26d08073 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -39,6 +39,8 @@ obj-$(CONFIG_MMC_CB710)		+= cb710-mmc.o
 obj-$(CONFIG_MMC_VIA_SDMMC)	+= via-sdmmc.o
 obj-$(CONFIG_SDH_BFIN)		+= bfin_sdh.o
 obj-$(CONFIG_MMC_DW)		+= dw_mmc.o
+obj-$(CONFIG_MMC_DW_PLTFM)	+= dw_mmc-pltfm.o
+obj-$(CONFIG_MMC_DW_PCI)	+= dw_mmc-pci.o
 obj-$(CONFIG_MMC_SH_MMCIF)	+= sh_mmcif.o
 obj-$(CONFIG_MMC_JZ4740)	+= jz4740_mmc.o
 obj-$(CONFIG_MMC_VUB300)	+= vub300.o
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index e4449a54ae8f..9819dc09ce08 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -24,6 +24,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
+#include <linux/types.h>
 
 #include <linux/mmc/host.h>
 #include <linux/mmc/sdio.h>
@@ -173,6 +174,7 @@ struct atmel_mci {
 
 	struct atmel_mci_dma	dma;
 	struct dma_chan		*data_chan;
+	struct dma_slave_config	dma_conf;
 
 	u32			cmd_status;
 	u32			data_status;
@@ -863,16 +865,17 @@ atmci_prepare_data_dma(struct atmel_mci *host, struct mmc_data *data)
 
 	if (data->flags & MMC_DATA_READ) {
 		direction = DMA_FROM_DEVICE;
-		slave_dirn = DMA_DEV_TO_MEM;
+		host->dma_conf.direction = slave_dirn = DMA_DEV_TO_MEM;
 	} else {
 		direction = DMA_TO_DEVICE;
-		slave_dirn = DMA_MEM_TO_DEV;
+		host->dma_conf.direction = slave_dirn = DMA_MEM_TO_DEV;
 	}
 
 	sglen = dma_map_sg(chan->device->dev, data->sg,
 			data->sg_len, direction);
 
-	desc = chan->device->device_prep_slave_sg(chan,
+	dmaengine_slave_config(chan, &host->dma_conf);
+	desc = dmaengine_prep_slave_sg(chan,
 			data->sg, sglen, slave_dirn,
 			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc)
@@ -1960,10 +1963,6 @@ static bool atmci_configure_dma(struct atmel_mci *host)
 	if (pdata && find_slave_dev(pdata->dma_slave)) {
 		dma_cap_mask_t mask;
 
-		setup_dma_addr(pdata->dma_slave,
-			       host->mapbase + ATMCI_TDR,
-			       host->mapbase + ATMCI_RDR);
-
 		/* Try to grab a DMA channel */
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
@@ -1975,8 +1974,16 @@ static bool atmci_configure_dma(struct atmel_mci *host)
 		return false;
 	} else {
 		dev_info(&host->pdev->dev,
-					"Using %s for DMA transfers\n",
+					"using %s for DMA transfers\n",
 					dma_chan_name(host->dma.chan));
+
+		host->dma_conf.src_addr = host->mapbase + ATMCI_RDR;
+		host->dma_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		host->dma_conf.src_maxburst = 1;
+		host->dma_conf.dst_addr = host->mapbase + ATMCI_TDR;
+		host->dma_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		host->dma_conf.dst_maxburst = 1;
+		host->dma_conf.device_fc = false;
 		return true;
 	}
 }
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 64a8325a4a8a..c1f3673ae1ef 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -160,6 +160,16 @@ module_param(rw_threshold, uint, S_IRUGO);
 MODULE_PARM_DESC(rw_threshold,
 		"Read/Write threshold. Default = 32");
 
+static unsigned poll_threshold = 128;
+module_param(poll_threshold, uint, S_IRUGO);
+MODULE_PARM_DESC(poll_threshold,
+		 "Polling transaction size threshold. Default = 128");
+
+static unsigned poll_loopcount = 32;
+module_param(poll_loopcount, uint, S_IRUGO);
+MODULE_PARM_DESC(poll_loopcount,
+		 "Maximum polling loop count. Default = 32");
+
 static unsigned __initdata use_dma = 1;
 module_param(use_dma, uint, 0);
 MODULE_PARM_DESC(use_dma, "Whether to use DMA or not. Default = 1");
@@ -193,6 +203,7 @@ struct mmc_davinci_host {
 	bool use_dma;
 	bool do_dma;
 	bool sdio_int;
+	bool active_request;
 
 	/* Scatterlist DMA uses one or more parameter RAM entries:
 	 * the main one (associated with rxdma or txdma) plus zero or
@@ -219,6 +230,7 @@ struct mmc_davinci_host {
 #endif
 };
 
+static irqreturn_t mmc_davinci_irq(int irq, void *dev_id);
 
 /* PIO only */
 static void mmc_davinci_sg_to_buf(struct mmc_davinci_host *host)
@@ -376,7 +388,20 @@ static void mmc_davinci_start_command(struct mmc_davinci_host *host,
 
 	writel(cmd->arg, host->base + DAVINCI_MMCARGHL);
 	writel(cmd_reg,  host->base + DAVINCI_MMCCMD);
-	writel(im_val, host->base + DAVINCI_MMCIM);
+
+	host->active_request = true;
+
+	if (!host->do_dma && host->bytes_left <= poll_threshold) {
+		u32 count = poll_loopcount;
+
+		while (host->active_request && count--) {
+			mmc_davinci_irq(0, host);
+			cpu_relax();
+		}
+	}
+
+	if (host->active_request)
+		writel(im_val, host->base + DAVINCI_MMCIM);
 }
 
 /*----------------------------------------------------------------------*/
@@ -915,6 +940,7 @@ mmc_davinci_xfer_done(struct mmc_davinci_host *host, struct mmc_data *data)
 	if (!data->stop || (host->cmd && host->cmd->error)) {
 		mmc_request_done(host->mmc, data->mrq);
 		writel(0, host->base + DAVINCI_MMCIM);
+		host->active_request = false;
 	} else
 		mmc_davinci_start_command(host, data->stop);
 }
@@ -942,6 +968,7 @@ static void mmc_davinci_cmd_done(struct mmc_davinci_host *host,
 			cmd->mrq->cmd->retries = 0;
 		mmc_request_done(host->mmc, cmd->mrq);
 		writel(0, host->base + DAVINCI_MMCIM);
+		host->active_request = false;
 	}
 }
 
@@ -1009,12 +1036,33 @@ static irqreturn_t mmc_davinci_irq(int irq, void *dev_id)
 	 * by read. So, it is not unbouned loop even in the case of
 	 * non-dma.
 	 */
-	while (host->bytes_left && (status & (MMCST0_DXRDY | MMCST0_DRRDY))) {
-		davinci_fifo_data_trans(host, rw_threshold);
-		status = readl(host->base + DAVINCI_MMCST0);
-		if (!status)
-			break;
-		qstatus |= status;
+	if (host->bytes_left && (status & (MMCST0_DXRDY | MMCST0_DRRDY))) {
+		unsigned long im_val;
+
+		/*
+		 * If interrupts fire during the following loop, they will be
+		 * handled by the handler, but the PIC will still buffer these.
+		 * As a result, the handler will be called again to serve these
+		 * needlessly. In order to avoid these spurious interrupts,
+		 * keep interrupts masked during the loop.
+		 */
+		im_val = readl(host->base + DAVINCI_MMCIM);
+		writel(0, host->base + DAVINCI_MMCIM);
+
+		do {
+			davinci_fifo_data_trans(host, rw_threshold);
+			status = readl(host->base + DAVINCI_MMCST0);
+			qstatus |= status;
+		} while (host->bytes_left &&
+			 (status & (MMCST0_DXRDY | MMCST0_DRRDY)));
+
+		/*
+		 * If an interrupt is pending, it is assumed it will fire when
+		 * it is unmasked. This assumption is also taken when the MMCIM
+		 * is first set. Otherwise, writing to MMCIM after reading the
+		 * status is race-prone.
+		 */
+		writel(im_val, host->base + DAVINCI_MMCIM);
 	}
 
 	if (qstatus & MMCST0_DATDNE) {
@@ -1418,17 +1466,14 @@ static int davinci_mmcsd_suspend(struct device *dev)
 	struct mmc_davinci_host *host = platform_get_drvdata(pdev);
 	int ret;
 
-	mmc_host_enable(host->mmc);
 	ret = mmc_suspend_host(host->mmc);
 	if (!ret) {
 		writel(0, host->base + DAVINCI_MMCIM);
 		mmc_davinci_reset_ctrl(host, 1);
-		mmc_host_disable(host->mmc);
 		clk_disable(host->clk);
 		host->suspended = 1;
 	} else {
 		host->suspended = 0;
-		mmc_host_disable(host->mmc);
 	}
 
 	return ret;
@@ -1444,7 +1489,6 @@ static int davinci_mmcsd_resume(struct device *dev)
 		return 0;
 
 	clk_enable(host->clk);
-	mmc_host_enable(host->mmc);
 
 	mmc_davinci_reset_ctrl(host, 0);
 	ret = mmc_resume_host(host->mmc);
diff --git a/drivers/mmc/host/dw_mmc-pci.c b/drivers/mmc/host/dw_mmc-pci.c
new file mode 100644
index 000000000000..dc0d25a013e0
--- /dev/null
+++ b/drivers/mmc/host/dw_mmc-pci.c
@@ -0,0 +1,158 @@
+/*
+ * Synopsys DesignWare Multimedia Card PCI Interface driver
+ *
+ * Copyright (C) 2012 Vayavya Labs Pvt. Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/dw_mmc.h>
+#include "dw_mmc.h"
+
+#define PCI_BAR_NO 2
+#define COMPLETE_BAR 0
+#define SYNOPSYS_DW_MCI_VENDOR_ID 0x700
+#define SYNOPSYS_DW_MCI_DEVICE_ID 0x1107
+/* Defining the Capabilities */
+#define DW_MCI_CAPABILITIES (MMC_CAP_4_BIT_DATA | MMC_CAP_MMC_HIGHSPEED |\
+				MMC_CAP_SD_HIGHSPEED | MMC_CAP_8_BIT_DATA |\
+				MMC_CAP_SDIO_IRQ)
+
+static struct dw_mci_board pci_board_data = {
+	.num_slots			= 1,
+	.caps				= DW_MCI_CAPABILITIES,
+	.bus_hz				= 33 * 1000 * 1000,
+	.detect_delay_ms		= 200,
+	.fifo_depth			= 32,
+};
+
+static int __devinit dw_mci_pci_probe(struct pci_dev *pdev,
+				  const struct pci_device_id *entries)
+{
+	struct dw_mci *host;
+	int ret;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+	if (pci_request_regions(pdev, "dw_mmc_pci")) {
+		ret = -ENODEV;
+		goto err_disable_dev;
+	}
+
+	host = kzalloc(sizeof(struct dw_mci), GFP_KERNEL);
+	if (!host) {
+		ret = -ENOMEM;
+		goto err_release;
+	}
+
+	host->irq = pdev->irq;
+	host->irq_flags = IRQF_SHARED;
+	host->dev = pdev->dev;
+	host->pdata = &pci_board_data;
+
+	host->regs = pci_iomap(pdev, PCI_BAR_NO, COMPLETE_BAR);
+	if (!host->regs) {
+		ret = -EIO;
+		goto err_unmap;
+	}
+
+	pci_set_drvdata(pdev, host);
+	ret = dw_mci_probe(host);
+	if (ret)
+		goto err_probe_failed;
+	return ret;
+
+err_probe_failed:
+	pci_iounmap(pdev, host->regs);
+err_unmap:
+	kfree(host);
+err_release:
+	pci_release_regions(pdev);
+err_disable_dev:
+	pci_disable_device(pdev);
+	return ret;
+}
+
+static void __devexit dw_mci_pci_remove(struct pci_dev *pdev)
+{
+	struct dw_mci *host = pci_get_drvdata(pdev);
+
+	dw_mci_remove(host);
+	pci_set_drvdata(pdev, NULL);
+	pci_release_regions(pdev);
+	pci_iounmap(pdev, host->regs);
+	kfree(host);
+	pci_disable_device(pdev);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int dw_mci_pci_suspend(struct device *dev)
+{
+	int ret;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct dw_mci *host = pci_get_drvdata(pdev);
+
+	ret = dw_mci_suspend(host);
+	return ret;
+}
+
+static int dw_mci_pci_resume(struct device *dev)
+{
+	int ret;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct dw_mci *host = pci_get_drvdata(pdev);
+
+	ret = dw_mci_resume(host);
+	return ret;
+}
+#else
+#define dw_mci_pci_suspend	NULL
+#define dw_mci_pci_resume	NULL
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(dw_mci_pci_pmops, dw_mci_pci_suspend, dw_mci_pci_resume);
+
+static DEFINE_PCI_DEVICE_TABLE(dw_mci_pci_id) = {
+	{ PCI_DEVICE(SYNOPSYS_DW_MCI_VENDOR_ID, SYNOPSYS_DW_MCI_DEVICE_ID) },
+	{}
+};
+MODULE_DEVICE_TABLE(pci, dw_mci_pci_id);
+
+static struct pci_driver dw_mci_pci_driver = {
+	.name		= "dw_mmc_pci",
+	.id_table	= dw_mci_pci_id,
+	.probe		= dw_mci_pci_probe,
+	.remove		= dw_mci_pci_remove,
+	.driver		=	{
+		.pm =   &dw_mci_pci_pmops
+	},
+};
+
+static int __init dw_mci_init(void)
+{
+	return pci_register_driver(&dw_mci_pci_driver);
+}
+
+static void __exit dw_mci_exit(void)
+{
+	pci_unregister_driver(&dw_mci_pci_driver);
+}
+
+module_init(dw_mci_init);
+module_exit(dw_mci_exit);
+
+MODULE_DESCRIPTION("DW Multimedia Card PCI Interface driver");
+MODULE_AUTHOR("Shashidhar Hiremath <shashidharh@vayavyalabs.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/dw_mmc-pltfm.c b/drivers/mmc/host/dw_mmc-pltfm.c
new file mode 100644
index 000000000000..92ec3eb3aae7
--- /dev/null
+++ b/drivers/mmc/host/dw_mmc-pltfm.c
@@ -0,0 +1,134 @@
+/*
+ * Synopsys DesignWare Multimedia Card Interface driver
+ *
+ * Copyright (C) 2009 NXP Semiconductors
+ * Copyright (C) 2009, 2010 Imagination Technologies Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/dw_mmc.h>
+#include "dw_mmc.h"
+
+static int dw_mci_pltfm_probe(struct platform_device *pdev)
+{
+	struct dw_mci *host;
+	struct resource	*regs;
+	int ret;
+
+	host = kzalloc(sizeof(struct dw_mci), GFP_KERNEL);
+	if (!host)
+		return -ENOMEM;
+
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!regs) {
+		ret = -ENXIO;
+		goto err_free;
+	}
+
+	host->irq = platform_get_irq(pdev, 0);
+	if (host->irq < 0) {
+		ret = host->irq;
+		goto err_free;
+	}
+
+	host->dev = pdev->dev;
+	host->irq_flags = 0;
+	host->pdata = pdev->dev.platform_data;
+	ret = -ENOMEM;
+	host->regs = ioremap(regs->start, resource_size(regs));
+	if (!host->regs)
+		goto err_free;
+	platform_set_drvdata(pdev, host);
+	ret = dw_mci_probe(host);
+	if (ret)
+		goto err_out;
+	return ret;
+err_out:
+	iounmap(host->regs);
+err_free:
+	kfree(host);
+	return ret;
+}
+
+static int __exit dw_mci_pltfm_remove(struct platform_device *pdev)
+{
+	struct dw_mci *host = platform_get_drvdata(pdev);
+
+	platform_set_drvdata(pdev, NULL);
+	dw_mci_remove(host);
+	iounmap(host->regs);
+	kfree(host);
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+/*
+ * TODO: we should probably disable the clock to the card in the suspend path.
+ */
+static int dw_mci_pltfm_suspend(struct device *dev)
+{
+	int ret;
+	struct dw_mci *host = dev_get_drvdata(dev);
+
+	ret = dw_mci_suspend(host);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int dw_mci_pltfm_resume(struct device *dev)
+{
+	int ret;
+	struct dw_mci *host = dev_get_drvdata(dev);
+
+	ret = dw_mci_resume(host);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+#else
+#define dw_mci_pltfm_suspend	NULL
+#define dw_mci_pltfm_resume	NULL
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(dw_mci_pltfm_pmops, dw_mci_pltfm_suspend, dw_mci_pltfm_resume);
+
+static struct platform_driver dw_mci_pltfm_driver = {
+	.remove		= __exit_p(dw_mci_pltfm_remove),
+	.driver		= {
+		.name		= "dw_mmc",
+		.pm		= &dw_mci_pltfm_pmops,
+	},
+};
+
+static int __init dw_mci_init(void)
+{
+	return platform_driver_probe(&dw_mci_pltfm_driver, dw_mci_pltfm_probe);
+}
+
+static void __exit dw_mci_exit(void)
+{
+	platform_driver_unregister(&dw_mci_pltfm_driver);
+}
+
+module_init(dw_mci_init);
+module_exit(dw_mci_exit);
+
+MODULE_DESCRIPTION("DW Multimedia Card Interface driver");
+MODULE_AUTHOR("NXP Semiconductor VietNam");
+MODULE_AUTHOR("Imagination Technologies Ltd");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 8bec1c36b159..bf3c9b456aaf 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -268,7 +268,7 @@ static void dw_mci_start_command(struct dw_mci *host,
 				 struct mmc_command *cmd, u32 cmd_flags)
 {
 	host->cmd = cmd;
-	dev_vdbg(&host->pdev->dev,
+	dev_vdbg(&host->dev,
 		 "start command: ARGR=0x%08x CMDR=0x%08x\n",
 		 cmd->arg, cmd_flags);
 
@@ -295,15 +295,25 @@ static void dw_mci_stop_dma(struct dw_mci *host)
 	}
 }
 
+static int dw_mci_get_dma_dir(struct mmc_data *data)
+{
+	if (data->flags & MMC_DATA_WRITE)
+		return DMA_TO_DEVICE;
+	else
+		return DMA_FROM_DEVICE;
+}
+
 #ifdef CONFIG_MMC_DW_IDMAC
 static void dw_mci_dma_cleanup(struct dw_mci *host)
 {
 	struct mmc_data *data = host->data;
 
 	if (data)
-		dma_unmap_sg(&host->pdev->dev, data->sg, data->sg_len,
-			     ((data->flags & MMC_DATA_WRITE)
-			      ? DMA_TO_DEVICE : DMA_FROM_DEVICE));
+		if (!data->host_cookie)
+			dma_unmap_sg(&host->dev,
+				     data->sg,
+				     data->sg_len,
+				     dw_mci_get_dma_dir(data));
 }
 
 static void dw_mci_idmac_stop_dma(struct dw_mci *host)
@@ -326,7 +336,7 @@ static void dw_mci_idmac_complete_dma(struct dw_mci *host)
 {
 	struct mmc_data *data = host->data;
 
-	dev_vdbg(&host->pdev->dev, "DMA complete\n");
+	dev_vdbg(&host->dev, "DMA complete\n");
 
 	host->dma_ops->cleanup(host);
 
@@ -428,17 +438,15 @@ static struct dw_mci_dma_ops dw_mci_idmac_ops = {
 };
 #endif /* CONFIG_MMC_DW_IDMAC */
 
-static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
+static int dw_mci_pre_dma_transfer(struct dw_mci *host,
+				   struct mmc_data *data,
+				   bool next)
 {
 	struct scatterlist *sg;
-	unsigned int i, direction, sg_len;
-	u32 temp;
+	unsigned int i, sg_len;
 
-	host->using_dma = 0;
-
-	/* If we don't have a channel, we can't do DMA */
-	if (!host->use_dma)
-		return -ENODEV;
+	if (!next && data->host_cookie)
+		return data->host_cookie;
 
 	/*
 	 * We don't do DMA on "complex" transfers, i.e. with
@@ -447,6 +455,7 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 	 */
 	if (data->blocks * data->blksz < DW_MCI_DMA_THRESHOLD)
 		return -EINVAL;
+
 	if (data->blksz & 3)
 		return -EINVAL;
 
@@ -455,17 +464,74 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 			return -EINVAL;
 	}
 
-	host->using_dma = 1;
+	sg_len = dma_map_sg(&host->dev,
+			    data->sg,
+			    data->sg_len,
+			    dw_mci_get_dma_dir(data));
+	if (sg_len == 0)
+		return -EINVAL;
 
-	if (data->flags & MMC_DATA_READ)
-		direction = DMA_FROM_DEVICE;
-	else
-		direction = DMA_TO_DEVICE;
+	if (next)
+		data->host_cookie = sg_len;
 
-	sg_len = dma_map_sg(&host->pdev->dev, data->sg, data->sg_len,
-			    direction);
+	return sg_len;
+}
 
-	dev_vdbg(&host->pdev->dev,
+static void dw_mci_pre_req(struct mmc_host *mmc,
+			   struct mmc_request *mrq,
+			   bool is_first_req)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+
+	if (!slot->host->use_dma || !data)
+		return;
+
+	if (data->host_cookie) {
+		data->host_cookie = 0;
+		return;
+	}
+
+	if (dw_mci_pre_dma_transfer(slot->host, mrq->data, 1) < 0)
+		data->host_cookie = 0;
+}
+
+static void dw_mci_post_req(struct mmc_host *mmc,
+			    struct mmc_request *mrq,
+			    int err)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+
+	if (!slot->host->use_dma || !data)
+		return;
+
+	if (data->host_cookie)
+		dma_unmap_sg(&slot->host->dev,
+			     data->sg,
+			     data->sg_len,
+			     dw_mci_get_dma_dir(data));
+	data->host_cookie = 0;
+}
+
+static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
+{
+	int sg_len;
+	u32 temp;
+
+	host->using_dma = 0;
+
+	/* If we don't have a channel, we can't do DMA */
+	if (!host->use_dma)
+		return -ENODEV;
+
+	sg_len = dw_mci_pre_dma_transfer(host, data, 0);
+	if (sg_len < 0)
+		return sg_len;
+
+	host->using_dma = 1;
+
+	dev_vdbg(&host->dev,
 		 "sd sg_cpu: %#lx sg_dma: %#lx sg_len: %d\n",
 		 (unsigned long)host->sg_cpu, (unsigned long)host->sg_dma,
 		 sg_len);
@@ -579,8 +645,8 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot)
 			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
 
 		/* enable clock */
-		mci_writel(host, CLKENA, SDMMC_CLKEN_ENABLE |
-			   SDMMC_CLKEN_LOW_PWR);
+		mci_writel(host, CLKENA, ((SDMMC_CLKEN_ENABLE |
+			   SDMMC_CLKEN_LOW_PWR) << slot->id));
 
 		/* inform CIU */
 		mci_send_cmd(slot,
@@ -800,6 +866,8 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb)
 
 static const struct mmc_host_ops dw_mci_ops = {
 	.request		= dw_mci_request,
+	.pre_req		= dw_mci_pre_req,
+	.post_req		= dw_mci_post_req,
 	.set_ios		= dw_mci_set_ios,
 	.get_ro			= dw_mci_get_ro,
 	.get_cd			= dw_mci_get_cd,
@@ -821,12 +889,12 @@ static void dw_mci_request_end(struct dw_mci *host, struct mmc_request *mrq)
 		slot = list_entry(host->queue.next,
 				  struct dw_mci_slot, queue_node);
 		list_del(&slot->queue_node);
-		dev_vdbg(&host->pdev->dev, "list not empty: %s is next\n",
+		dev_vdbg(&host->dev, "list not empty: %s is next\n",
 			 mmc_hostname(slot->mmc));
 		host->state = STATE_SENDING_CMD;
 		dw_mci_start_request(host, slot);
 	} else {
-		dev_vdbg(&host->pdev->dev, "list empty\n");
+		dev_vdbg(&host->dev, "list empty\n");
 		host->state = STATE_IDLE;
 	}
 
@@ -965,7 +1033,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 					data->bytes_xfered = 0;
 					data->error = -ETIMEDOUT;
 				} else {
-					dev_err(&host->pdev->dev,
+					dev_err(&host->dev,
 						"data FIFO error "
 						"(status=%08x)\n",
 						status);
@@ -1682,7 +1750,7 @@ static int __init dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	struct mmc_host *mmc;
 	struct dw_mci_slot *slot;
 
-	mmc = mmc_alloc_host(sizeof(struct dw_mci_slot), &host->pdev->dev);
+	mmc = mmc_alloc_host(sizeof(struct dw_mci_slot), &host->dev);
 	if (!mmc)
 		return -ENOMEM;
 
@@ -1720,13 +1788,11 @@ static int __init dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	if (host->pdata->quirks & DW_MCI_QUIRK_HIGHSPEED)
 		mmc->caps |= MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED;
 
-#ifdef CONFIG_MMC_DW_IDMAC
-	mmc->max_segs = host->ring_size;
-	mmc->max_blk_size = 65536;
-	mmc->max_blk_count = host->ring_size;
-	mmc->max_seg_size = 0x1000;
-	mmc->max_req_size = mmc->max_seg_size * mmc->max_blk_count;
-#else
+	if (mmc->caps2 & MMC_CAP2_POWEROFF_NOTIFY)
+		mmc->power_notify_type = MMC_HOST_PW_NOTIFY_SHORT;
+	else
+		mmc->power_notify_type = MMC_HOST_PW_NOTIFY_NONE;
+
 	if (host->pdata->blk_settings) {
 		mmc->max_segs = host->pdata->blk_settings->max_segs;
 		mmc->max_blk_size = host->pdata->blk_settings->max_blk_size;
@@ -1735,13 +1801,20 @@ static int __init dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 		mmc->max_seg_size = host->pdata->blk_settings->max_seg_size;
 	} else {
 		/* Useful defaults if platform data is unset. */
+#ifdef CONFIG_MMC_DW_IDMAC
+		mmc->max_segs = host->ring_size;
+		mmc->max_blk_size = 65536;
+		mmc->max_blk_count = host->ring_size;
+		mmc->max_seg_size = 0x1000;
+		mmc->max_req_size = mmc->max_seg_size * mmc->max_blk_count;
+#else
 		mmc->max_segs = 64;
 		mmc->max_blk_size = 65536; /* BLKSIZ is 16 bits */
 		mmc->max_blk_count = 512;
 		mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count;
 		mmc->max_seg_size = mmc->max_req_size;
-	}
 #endif /* CONFIG_MMC_DW_IDMAC */
+	}
 
 	host->vmmc = regulator_get(mmc_dev(mmc), "vmmc");
 	if (IS_ERR(host->vmmc)) {
@@ -1789,10 +1862,10 @@ static void dw_mci_cleanup_slot(struct dw_mci_slot *slot, unsigned int id)
 static void dw_mci_init_dma(struct dw_mci *host)
 {
 	/* Alloc memory for sg translation */
-	host->sg_cpu = dma_alloc_coherent(&host->pdev->dev, PAGE_SIZE,
+	host->sg_cpu = dma_alloc_coherent(&host->dev, PAGE_SIZE,
 					  &host->sg_dma, GFP_KERNEL);
 	if (!host->sg_cpu) {
-		dev_err(&host->pdev->dev, "%s: could not alloc DMA memory\n",
+		dev_err(&host->dev, "%s: could not alloc DMA memory\n",
 			__func__);
 		goto no_dma;
 	}
@@ -1800,7 +1873,7 @@ static void dw_mci_init_dma(struct dw_mci *host)
 	/* Determine which DMA interface to use */
 #ifdef CONFIG_MMC_DW_IDMAC
 	host->dma_ops = &dw_mci_idmac_ops;
-	dev_info(&host->pdev->dev, "Using internal DMA controller.\n");
+	dev_info(&host->dev, "Using internal DMA controller.\n");
 #endif
 
 	if (!host->dma_ops)
@@ -1808,12 +1881,12 @@ static void dw_mci_init_dma(struct dw_mci *host)
 
 	if (host->dma_ops->init) {
 		if (host->dma_ops->init(host)) {
-			dev_err(&host->pdev->dev, "%s: Unable to initialize "
+			dev_err(&host->dev, "%s: Unable to initialize "
 				"DMA Controller.\n", __func__);
 			goto no_dma;
 		}
 	} else {
-		dev_err(&host->pdev->dev, "DMA initialization not found.\n");
+		dev_err(&host->dev, "DMA initialization not found.\n");
 		goto no_dma;
 	}
 
@@ -1821,7 +1894,7 @@ static void dw_mci_init_dma(struct dw_mci *host)
 	return;
 
 no_dma:
-	dev_info(&host->pdev->dev, "Using PIO mode.\n");
+	dev_info(&host->dev, "Using PIO mode.\n");
 	host->use_dma = 0;
 	return;
 }
@@ -1847,61 +1920,37 @@ static bool mci_wait_reset(struct device *dev, struct dw_mci *host)
 	return false;
 }
 
-static int dw_mci_probe(struct platform_device *pdev)
+int dw_mci_probe(struct dw_mci *host)
 {
-	struct dw_mci *host;
-	struct resource	*regs;
-	struct dw_mci_board *pdata;
-	int irq, ret, i, width;
+	int width, i, ret = 0;
 	u32 fifo_size;
 
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!regs)
-		return -ENXIO;
-
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
-
-	host = kzalloc(sizeof(struct dw_mci), GFP_KERNEL);
-	if (!host)
-		return -ENOMEM;
-
-	host->pdev = pdev;
-	host->pdata = pdata = pdev->dev.platform_data;
-	if (!pdata || !pdata->init) {
-		dev_err(&pdev->dev,
+	if (!host->pdata || !host->pdata->init) {
+		dev_err(&host->dev,
 			"Platform data must supply init function\n");
-		ret = -ENODEV;
-		goto err_freehost;
+		return -ENODEV;
 	}
 
-	if (!pdata->select_slot && pdata->num_slots > 1) {
-		dev_err(&pdev->dev,
+	if (!host->pdata->select_slot && host->pdata->num_slots > 1) {
+		dev_err(&host->dev,
 			"Platform data must supply select_slot function\n");
-		ret = -ENODEV;
-		goto err_freehost;
+		return -ENODEV;
 	}
 
-	if (!pdata->bus_hz) {
-		dev_err(&pdev->dev,
+	if (!host->pdata->bus_hz) {
+		dev_err(&host->dev,
 			"Platform data must supply bus speed\n");
-		ret = -ENODEV;
-		goto err_freehost;
+		return -ENODEV;
 	}
 
-	host->bus_hz = pdata->bus_hz;
-	host->quirks = pdata->quirks;
+	host->bus_hz = host->pdata->bus_hz;
+	host->quirks = host->pdata->quirks;
 
 	spin_lock_init(&host->lock);
 	INIT_LIST_HEAD(&host->queue);
 
-	ret = -ENOMEM;
-	host->regs = ioremap(regs->start, resource_size(regs));
-	if (!host->regs)
-		goto err_freehost;
 
-	host->dma_ops = pdata->dma_ops;
+	host->dma_ops = host->pdata->dma_ops;
 	dw_mci_init_dma(host);
 
 	/*
@@ -1931,7 +1980,7 @@ static int dw_mci_probe(struct platform_device *pdev)
 	}
 
 	/* Reset all blocks */
-	if (!mci_wait_reset(&pdev->dev, host)) {
+	if (!mci_wait_reset(&host->dev, host)) {
 		ret = -ENODEV;
 		goto err_dmaunmap;
 	}
@@ -1974,13 +2023,10 @@ static int dw_mci_probe(struct platform_device *pdev)
 	if (!dw_mci_card_workqueue)
 		goto err_dmaunmap;
 	INIT_WORK(&host->card_work, dw_mci_work_routine_card);
-
-	ret = request_irq(irq, dw_mci_interrupt, 0, "dw-mci", host);
+	ret = request_irq(host->irq, dw_mci_interrupt, host->irq_flags, "dw-mci", host);
 	if (ret)
 		goto err_workqueue;
 
-	platform_set_drvdata(pdev, host);
-
 	if (host->pdata->num_slots)
 		host->num_slots = host->pdata->num_slots;
 	else
@@ -2000,7 +2046,7 @@ static int dw_mci_probe(struct platform_device *pdev)
 	 * Need to check the version-id and set data-offset for DATA register.
 	 */
 	host->verid = SDMMC_GET_VERID(mci_readl(host, VERID));
-	dev_info(&pdev->dev, "Version ID is %04x\n", host->verid);
+	dev_info(&host->dev, "Version ID is %04x\n", host->verid);
 
 	if (host->verid < DW_MMC_240A)
 		host->data_offset = DATA_OFFSET;
@@ -2017,12 +2063,12 @@ static int dw_mci_probe(struct platform_device *pdev)
 		   DW_MCI_ERROR_FLAGS | SDMMC_INT_CD);
 	mci_writel(host, CTRL, SDMMC_CTRL_INT_ENABLE); /* Enable mci interrupt */
 
-	dev_info(&pdev->dev, "DW MMC controller at irq %d, "
+	dev_info(&host->dev, "DW MMC controller at irq %d, "
 		 "%d bit host data width, "
 		 "%u deep fifo\n",
-		 irq, width, fifo_size);
+		 host->irq, width, fifo_size);
 	if (host->quirks & DW_MCI_QUIRK_IDMAC_DTO)
-		dev_info(&pdev->dev, "Internal DMAC interrupt fix enabled.\n");
+		dev_info(&host->dev, "Internal DMAC interrupt fix enabled.\n");
 
 	return 0;
 
@@ -2033,7 +2079,7 @@ err_init_slot:
 			dw_mci_cleanup_slot(host->slot[i], i);
 		i--;
 	}
-	free_irq(irq, host);
+	free_irq(host->irq, host);
 
 err_workqueue:
 	destroy_workqueue(dw_mci_card_workqueue);
@@ -2041,33 +2087,26 @@ err_workqueue:
 err_dmaunmap:
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
-	dma_free_coherent(&host->pdev->dev, PAGE_SIZE,
+	dma_free_coherent(&host->dev, PAGE_SIZE,
 			  host->sg_cpu, host->sg_dma);
-	iounmap(host->regs);
 
 	if (host->vmmc) {
 		regulator_disable(host->vmmc);
 		regulator_put(host->vmmc);
 	}
-
-
-err_freehost:
-	kfree(host);
 	return ret;
 }
+EXPORT_SYMBOL(dw_mci_probe);
 
-static int __exit dw_mci_remove(struct platform_device *pdev)
+void dw_mci_remove(struct dw_mci *host)
 {
-	struct dw_mci *host = platform_get_drvdata(pdev);
 	int i;
 
 	mci_writel(host, RINTSTS, 0xFFFFFFFF);
 	mci_writel(host, INTMASK, 0); /* disable all mmc interrupt first */
 
-	platform_set_drvdata(pdev, NULL);
-
 	for (i = 0; i < host->num_slots; i++) {
-		dev_dbg(&pdev->dev, "remove slot %d\n", i);
+		dev_dbg(&host->dev, "remove slot %d\n", i);
 		if (host->slot[i])
 			dw_mci_cleanup_slot(host->slot[i], i);
 	}
@@ -2076,9 +2115,9 @@ static int __exit dw_mci_remove(struct platform_device *pdev)
 	mci_writel(host, CLKENA, 0);
 	mci_writel(host, CLKSRC, 0);
 
-	free_irq(platform_get_irq(pdev, 0), host);
+	free_irq(host->irq, host);
 	destroy_workqueue(dw_mci_card_workqueue);
-	dma_free_coherent(&pdev->dev, PAGE_SIZE, host->sg_cpu, host->sg_dma);
+	dma_free_coherent(&host->dev, PAGE_SIZE, host->sg_cpu, host->sg_dma);
 
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
@@ -2088,20 +2127,18 @@ static int __exit dw_mci_remove(struct platform_device *pdev)
 		regulator_put(host->vmmc);
 	}
 
-	iounmap(host->regs);
-
-	kfree(host);
-	return 0;
 }
+EXPORT_SYMBOL(dw_mci_remove);
+
+
 
 #ifdef CONFIG_PM_SLEEP
 /*
  * TODO: we should probably disable the clock to the card in the suspend path.
  */
-static int dw_mci_suspend(struct device *dev)
+int dw_mci_suspend(struct dw_mci *host)
 {
-	int i, ret;
-	struct dw_mci *host = dev_get_drvdata(dev);
+	int i, ret = 0;
 
 	for (i = 0; i < host->num_slots; i++) {
 		struct dw_mci_slot *slot = host->slot[i];
@@ -2123,11 +2160,11 @@ static int dw_mci_suspend(struct device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL(dw_mci_suspend);
 
-static int dw_mci_resume(struct device *dev)
+int dw_mci_resume(struct dw_mci *host)
 {
 	int i, ret;
-	struct dw_mci *host = dev_get_drvdata(dev);
 
 	if (host->vmmc)
 		regulator_enable(host->vmmc);
@@ -2135,7 +2172,7 @@ static int dw_mci_resume(struct device *dev)
 	if (host->dma_ops->init)
 		host->dma_ops->init(host);
 
-	if (!mci_wait_reset(dev, host)) {
+	if (!mci_wait_reset(&host->dev, host)) {
 		ret = -ENODEV;
 		return ret;
 	}
@@ -2157,32 +2194,19 @@ static int dw_mci_resume(struct device *dev)
 		if (ret < 0)
 			return ret;
 	}
-
 	return 0;
 }
-#else
-#define dw_mci_suspend	NULL
-#define dw_mci_resume	NULL
+EXPORT_SYMBOL(dw_mci_resume);
 #endif /* CONFIG_PM_SLEEP */
 
-static SIMPLE_DEV_PM_OPS(dw_mci_pmops, dw_mci_suspend, dw_mci_resume);
-
-static struct platform_driver dw_mci_driver = {
-	.remove		= __exit_p(dw_mci_remove),
-	.driver		= {
-		.name		= "dw_mmc",
-		.pm		= &dw_mci_pmops,
-	},
-};
-
 static int __init dw_mci_init(void)
 {
-	return platform_driver_probe(&dw_mci_driver, dw_mci_probe);
+	printk(KERN_INFO "Synopsys Designware Multimedia Card Interface Driver");
+	return 0;
 }
 
 static void __exit dw_mci_exit(void)
 {
-	platform_driver_unregister(&dw_mci_driver);
 }
 
 module_init(dw_mci_init);
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index df392a1143f2..15c27e17c23f 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -175,4 +175,11 @@
 	(*(volatile u64 __force *)((dev)->regs + SDMMC_##reg) = (value))
 #endif
 
+extern int dw_mci_probe(struct dw_mci *host);
+extern void dw_mci_remove(struct dw_mci *host);
+#ifdef CONFIG_PM
+extern int dw_mci_suspend(struct dw_mci *host);
+extern int dw_mci_resume(struct dw_mci *host);
+#endif
+
 #endif /* _DW_MMC_H_ */
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 983e244eca76..032b84791a16 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -30,6 +30,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/amba/mmci.h>
 #include <linux/pm_runtime.h>
+#include <linux/types.h>
 
 #include <asm/div64.h>
 #include <asm/io.h>
@@ -400,6 +401,7 @@ static int mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 		.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
 		.src_maxburst = variant->fifohalfsize >> 2, /* # of words */
 		.dst_maxburst = variant->fifohalfsize >> 2, /* # of words */
+		.device_fc = false,
 	};
 	struct dma_chan *chan;
 	struct dma_device *device;
@@ -441,7 +443,7 @@ static int mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 		return -EINVAL;
 
 	dmaengine_slave_config(chan, &conf);
-	desc = device->device_prep_slave_sg(chan, data->sg, nr_sg,
+	desc = dmaengine_prep_slave_sg(chan, data->sg, nr_sg,
 					    conf.direction, DMA_CTRL_ACK);
 	if (!desc)
 		goto unmap_exit;
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 4184b7946bbf..b2058b432320 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -33,6 +33,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/dmaengine.h>
+#include <linux/types.h>
 
 #include <asm/dma.h>
 #include <asm/irq.h>
@@ -254,7 +255,7 @@ static int mxcmci_setup_data(struct mxcmci_host *host, struct mmc_data *data)
 	if (nents != data->sg_len)
 		return -EINVAL;
 
-	host->desc = host->dma->device->device_prep_slave_sg(host->dma,
+	host->desc = dmaengine_prep_slave_sg(host->dma,
 		data->sg, data->sg_len, slave_dirn,
 		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
@@ -267,6 +268,7 @@ static int mxcmci_setup_data(struct mxcmci_host *host, struct mmc_data *data)
 	wmb();
 
 	dmaengine_submit(host->desc);
+	dma_async_issue_pending(host->dma);
 
 	return 0;
 }
@@ -710,6 +712,7 @@ static int mxcmci_setup_dma(struct mmc_host *mmc)
 	config->src_addr_width = 4;
 	config->dst_maxburst = host->burstlen;
 	config->src_maxburst = host->burstlen;
+	config->device_fc = false;
 
 	return dmaengine_slave_config(host->dma, config);
 }
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index 382c835d217c..b0f2ef988188 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -38,10 +38,10 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/module.h>
+#include <linux/fsl/mxs-dma.h>
 
 #include <mach/mxs.h>
 #include <mach/common.h>
-#include <mach/dma.h>
 #include <mach/mmc.h>
 
 #define DRIVER_NAME	"mxs-mmc"
@@ -305,7 +305,7 @@ static irqreturn_t mxs_mmc_irq_handler(int irq, void *dev_id)
 }
 
 static struct dma_async_tx_descriptor *mxs_mmc_prep_dma(
-	struct mxs_mmc_host *host, unsigned int append)
+	struct mxs_mmc_host *host, unsigned long flags)
 {
 	struct dma_async_tx_descriptor *desc;
 	struct mmc_data *data = host->data;
@@ -324,8 +324,8 @@ static struct dma_async_tx_descriptor *mxs_mmc_prep_dma(
 		sg_len = SSP_PIO_NUM;
 	}
 
-	desc = host->dmach->device->device_prep_slave_sg(host->dmach,
-				sgl, sg_len, host->slave_dirn, append);
+	desc = dmaengine_prep_slave_sg(host->dmach,
+				sgl, sg_len, host->slave_dirn, flags);
 	if (desc) {
 		desc->callback = mxs_mmc_dma_irq_callback;
 		desc->callback_param = host;
@@ -358,7 +358,7 @@ static void mxs_mmc_bc(struct mxs_mmc_host *host)
 	host->ssp_pio_words[2] = cmd1;
 	host->dma_dir = DMA_NONE;
 	host->slave_dirn = DMA_TRANS_NONE;
-	desc = mxs_mmc_prep_dma(host, 0);
+	desc = mxs_mmc_prep_dma(host, DMA_CTRL_ACK);
 	if (!desc)
 		goto out;
 
@@ -398,7 +398,7 @@ static void mxs_mmc_ac(struct mxs_mmc_host *host)
 	host->ssp_pio_words[2] = cmd1;
 	host->dma_dir = DMA_NONE;
 	host->slave_dirn = DMA_TRANS_NONE;
-	desc = mxs_mmc_prep_dma(host, 0);
+	desc = mxs_mmc_prep_dma(host, DMA_CTRL_ACK);
 	if (!desc)
 		goto out;
 
@@ -526,7 +526,7 @@ static void mxs_mmc_adtc(struct mxs_mmc_host *host)
 	host->data = data;
 	host->dma_dir = dma_data_dir;
 	host->slave_dirn = slave_dirn;
-	desc = mxs_mmc_prep_dma(host, 1);
+	desc = mxs_mmc_prep_dma(host, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc)
 		goto out;
 
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index fd0c661bbad3..47adb161d3ad 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -26,6 +26,9 @@
 #include <linux/platform_device.h>
 #include <linux/timer.h>
 #include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/of_device.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/core.h>
 #include <linux/mmc/mmc.h>
@@ -106,17 +109,6 @@
 #define SOFTRESET		(1 << 1)
 #define RESETDONE		(1 << 0)
 
-/*
- * FIXME: Most likely all the data using these _DEVID defines should come
- * from the platform_data, or implemented in controller and slot specific
- * functions.
- */
-#define OMAP_MMC1_DEVID		0
-#define OMAP_MMC2_DEVID		1
-#define OMAP_MMC3_DEVID		2
-#define OMAP_MMC4_DEVID		3
-#define OMAP_MMC5_DEVID		4
-
 #define MMC_AUTOSUSPEND_DELAY	100
 #define MMC_TIMEOUT_MS		20
 #define OMAP_MMC_MIN_CLOCK	400000
@@ -164,7 +156,6 @@ struct omap_hsmmc_host {
 	void	__iomem		*base;
 	resource_size_t		mapbase;
 	spinlock_t		irq_lock; /* Prevent races with irq handler */
-	unsigned int		id;
 	unsigned int		dma_len;
 	unsigned int		dma_sg_idx;
 	unsigned char		bus_mode;
@@ -179,7 +170,6 @@ struct omap_hsmmc_host {
 	int			got_dbclk;
 	int			response_busy;
 	int			context_loss;
-	int			dpm_state;
 	int			vdd;
 	int			protect_card;
 	int			reqs_blocked;
@@ -241,28 +231,7 @@ static int omap_hsmmc_resume_cdirq(struct device *dev, int slot)
 
 #ifdef CONFIG_REGULATOR
 
-static int omap_hsmmc_1_set_power(struct device *dev, int slot, int power_on,
-				  int vdd)
-{
-	struct omap_hsmmc_host *host =
-		platform_get_drvdata(to_platform_device(dev));
-	int ret;
-
-	if (mmc_slot(host).before_set_reg)
-		mmc_slot(host).before_set_reg(dev, slot, power_on, vdd);
-
-	if (power_on)
-		ret = mmc_regulator_set_ocr(host->mmc, host->vcc, vdd);
-	else
-		ret = mmc_regulator_set_ocr(host->mmc, host->vcc, 0);
-
-	if (mmc_slot(host).after_set_reg)
-		mmc_slot(host).after_set_reg(dev, slot, power_on, vdd);
-
-	return ret;
-}
-
-static int omap_hsmmc_235_set_power(struct device *dev, int slot, int power_on,
+static int omap_hsmmc_set_power(struct device *dev, int slot, int power_on,
 				   int vdd)
 {
 	struct omap_hsmmc_host *host =
@@ -275,6 +244,13 @@ static int omap_hsmmc_235_set_power(struct device *dev, int slot, int power_on,
 	 */
 	if (!host->vcc)
 		return 0;
+	/*
+	 * With DT, never turn OFF the regulator. This is because
+	 * the pbias cell programming support is still missing when
+	 * booting with Device tree
+	 */
+	if (of_have_populated_dt() && !vdd)
+		return 0;
 
 	if (mmc_slot(host).before_set_reg)
 		mmc_slot(host).before_set_reg(dev, slot, power_on, vdd);
@@ -318,106 +294,16 @@ static int omap_hsmmc_235_set_power(struct device *dev, int slot, int power_on,
 	return ret;
 }
 
-static int omap_hsmmc_4_set_power(struct device *dev, int slot, int power_on,
-					int vdd)
-{
-	return 0;
-}
-
-static int omap_hsmmc_1_set_sleep(struct device *dev, int slot, int sleep,
-				  int vdd, int cardsleep)
-{
-	struct omap_hsmmc_host *host =
-		platform_get_drvdata(to_platform_device(dev));
-	int mode = sleep ? REGULATOR_MODE_STANDBY : REGULATOR_MODE_NORMAL;
-
-	return regulator_set_mode(host->vcc, mode);
-}
-
-static int omap_hsmmc_235_set_sleep(struct device *dev, int slot, int sleep,
-				   int vdd, int cardsleep)
-{
-	struct omap_hsmmc_host *host =
-		platform_get_drvdata(to_platform_device(dev));
-	int err, mode;
-
-	/*
-	 * If we don't see a Vcc regulator, assume it's a fixed
-	 * voltage always-on regulator.
-	 */
-	if (!host->vcc)
-		return 0;
-
-	mode = sleep ? REGULATOR_MODE_STANDBY : REGULATOR_MODE_NORMAL;
-
-	if (!host->vcc_aux)
-		return regulator_set_mode(host->vcc, mode);
-
-	if (cardsleep) {
-		/* VCC can be turned off if card is asleep */
-		if (sleep)
-			err = mmc_regulator_set_ocr(host->mmc, host->vcc, 0);
-		else
-			err = mmc_regulator_set_ocr(host->mmc, host->vcc, vdd);
-	} else
-		err = regulator_set_mode(host->vcc, mode);
-	if (err)
-		return err;
-
-	if (!mmc_slot(host).vcc_aux_disable_is_sleep)
-		return regulator_set_mode(host->vcc_aux, mode);
-
-	if (sleep)
-		return regulator_disable(host->vcc_aux);
-	else
-		return regulator_enable(host->vcc_aux);
-}
-
-static int omap_hsmmc_4_set_sleep(struct device *dev, int slot, int sleep,
-					int vdd, int cardsleep)
-{
-	return 0;
-}
-
 static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 {
 	struct regulator *reg;
-	int ret = 0;
 	int ocr_value = 0;
 
-	switch (host->id) {
-	case OMAP_MMC1_DEVID:
-		/* On-chip level shifting via PBIAS0/PBIAS1 */
-		mmc_slot(host).set_power = omap_hsmmc_1_set_power;
-		mmc_slot(host).set_sleep = omap_hsmmc_1_set_sleep;
-		break;
-	case OMAP_MMC2_DEVID:
-	case OMAP_MMC3_DEVID:
-	case OMAP_MMC5_DEVID:
-		/* Off-chip level shifting, or none */
-		mmc_slot(host).set_power = omap_hsmmc_235_set_power;
-		mmc_slot(host).set_sleep = omap_hsmmc_235_set_sleep;
-		break;
-	case OMAP_MMC4_DEVID:
-		mmc_slot(host).set_power = omap_hsmmc_4_set_power;
-		mmc_slot(host).set_sleep = omap_hsmmc_4_set_sleep;
-	default:
-		pr_err("MMC%d configuration not supported!\n", host->id);
-		return -EINVAL;
-	}
+	mmc_slot(host).set_power = omap_hsmmc_set_power;
 
 	reg = regulator_get(host->dev, "vmmc");
 	if (IS_ERR(reg)) {
 		dev_dbg(host->dev, "vmmc regulator missing\n");
-		/*
-		* HACK: until fixed.c regulator is usable,
-		* we don't require a main regulator
-		* for MMC2 or MMC3
-		*/
-		if (host->id == OMAP_MMC1_DEVID) {
-			ret = PTR_ERR(reg);
-			goto err;
-		}
 	} else {
 		host->vcc = reg;
 		ocr_value = mmc_regulator_get_ocrmask(reg);
@@ -425,8 +311,8 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 			mmc_slot(host).ocr_mask = ocr_value;
 		} else {
 			if (!(mmc_slot(host).ocr_mask & ocr_value)) {
-				pr_err("MMC%d ocrmask %x is not supported\n",
-					host->id, mmc_slot(host).ocr_mask);
+				dev_err(host->dev, "ocrmask %x is not supported\n",
+					mmc_slot(host).ocr_mask);
 				mmc_slot(host).ocr_mask = 0;
 				return -EINVAL;
 			}
@@ -459,11 +345,6 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 	}
 
 	return 0;
-
-err:
-	mmc_slot(host).set_power = NULL;
-	mmc_slot(host).set_sleep = NULL;
-	return ret;
 }
 
 static void omap_hsmmc_reg_put(struct omap_hsmmc_host *host)
@@ -471,7 +352,6 @@ static void omap_hsmmc_reg_put(struct omap_hsmmc_host *host)
 	regulator_put(host->vcc);
 	regulator_put(host->vcc_aux);
 	mmc_slot(host).set_power = NULL;
-	mmc_slot(host).set_sleep = NULL;
 }
 
 static inline int omap_hsmmc_have_reg(void)
@@ -710,7 +590,7 @@ static int omap_hsmmc_context_restore(struct omap_hsmmc_host *host)
 	OMAP_HSMMC_WRITE(host->base, SYSCONFIG,
 			OMAP_HSMMC_READ(host->base, SYSCONFIG) | AUTOIDLE);
 
-	if (host->id == OMAP_MMC1_DEVID) {
+	if (host->pdata->controller_flags & OMAP_HSMMC_SUPPORTS_DUAL_VOLT) {
 		if (host->power_mode != MMC_POWER_OFF &&
 		    (1 << ios->vdd) <= MMC_VDD_23_24)
 			hctl = SDVS18;
@@ -1261,14 +1141,14 @@ static void omap_hsmmc_protect_card(struct omap_hsmmc_host *host)
 	host->reqs_blocked = 0;
 	if (mmc_slot(host).get_cover_state(host->dev, host->slot_id)) {
 		if (host->protect_card) {
-			pr_info("%s: cover is closed, "
+			dev_info(host->dev, "%s: cover is closed, "
 					 "card is now accessible\n",
 					 mmc_hostname(host->mmc));
 			host->protect_card = 0;
 		}
 	} else {
 		if (!host->protect_card) {
-			pr_info("%s: cover is open, "
+			dev_info(host->dev, "%s: cover is open, "
 					 "card is now inaccessible\n",
 					 mmc_hostname(host->mmc));
 			host->protect_card = 1;
@@ -1405,7 +1285,7 @@ static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host,
 
 	if (!next && data->host_cookie &&
 	    data->host_cookie != host->next_data.cookie) {
-		pr_warning("[%s] invalid cookie: data->host_cookie %d"
+		dev_warn(host->dev, "[%s] invalid cookie: data->host_cookie %d"
 		       " host->next_data.cookie %d\n",
 		       __func__, data->host_cookie, host->next_data.cookie);
 		data->host_cookie = 0;
@@ -1663,7 +1543,13 @@ static void omap_hsmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		 * of external transceiver; but they all handle 1.8V.
 		 */
 		if ((OMAP_HSMMC_READ(host->base, HCTL) & SDVSDET) &&
-			(ios->vdd == DUAL_VOLT_OCR_BIT)) {
+			(ios->vdd == DUAL_VOLT_OCR_BIT) &&
+			/*
+			 * With pbias cell programming missing, this
+			 * can't be allowed when booting with device
+			 * tree.
+			 */
+			(!of_have_populated_dt())) {
 				/*
 				 * The mmc_select_voltage fn of the core does
 				 * not seem to set the power_mode to
@@ -1748,7 +1634,7 @@ static int omap_hsmmc_enable_fclk(struct mmc_host *mmc)
 	return 0;
 }
 
-static int omap_hsmmc_disable_fclk(struct mmc_host *mmc, int lazy)
+static int omap_hsmmc_disable_fclk(struct mmc_host *mmc)
 {
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 
@@ -1782,15 +1668,8 @@ static int omap_hsmmc_regs_show(struct seq_file *s, void *data)
 	if (host->pdata->get_context_loss_count)
 		context_loss = host->pdata->get_context_loss_count(host->dev);
 
-	seq_printf(s, "mmc%d:\n"
-			" enabled:\t%d\n"
-			" dpm_state:\t%d\n"
-			" nesting_cnt:\t%d\n"
-			" ctx_loss:\t%d:%d\n"
-			"\nregs:\n",
-			mmc->index, mmc->enabled ? 1 : 0,
-			host->dpm_state, mmc->nesting_cnt,
-			host->context_loss, context_loss);
+	seq_printf(s, "mmc%d:\n ctx_loss:\t%d:%d\n\nregs:\n",
+			mmc->index, host->context_loss, context_loss);
 
 	if (host->suspended) {
 		seq_printf(s, "host suspended, can't read registers\n");
@@ -1847,6 +1726,65 @@ static void omap_hsmmc_debugfs(struct mmc_host *mmc)
 
 #endif
 
+#ifdef CONFIG_OF
+static u16 omap4_reg_offset = 0x100;
+
+static const struct of_device_id omap_mmc_of_match[] = {
+	{
+		.compatible = "ti,omap2-hsmmc",
+	},
+	{
+		.compatible = "ti,omap3-hsmmc",
+	},
+	{
+		.compatible = "ti,omap4-hsmmc",
+		.data = &omap4_reg_offset,
+	},
+	{},
+}
+MODULE_DEVICE_TABLE(of, omap_mmc_of_match);
+
+static struct omap_mmc_platform_data *of_get_hsmmc_pdata(struct device *dev)
+{
+	struct omap_mmc_platform_data *pdata;
+	struct device_node *np = dev->of_node;
+	u32 bus_width;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL; /* out of memory */
+
+	if (of_find_property(np, "ti,dual-volt", NULL))
+		pdata->controller_flags |= OMAP_HSMMC_SUPPORTS_DUAL_VOLT;
+
+	/* This driver only supports 1 slot */
+	pdata->nr_slots = 1;
+	pdata->slots[0].switch_pin = of_get_named_gpio(np, "cd-gpios", 0);
+	pdata->slots[0].gpio_wp = of_get_named_gpio(np, "wp-gpios", 0);
+
+	if (of_find_property(np, "ti,non-removable", NULL)) {
+		pdata->slots[0].nonremovable = true;
+		pdata->slots[0].no_regulator_off_init = true;
+	}
+	of_property_read_u32(np, "ti,bus-width", &bus_width);
+	if (bus_width == 4)
+		pdata->slots[0].caps |= MMC_CAP_4_BIT_DATA;
+	else if (bus_width == 8)
+		pdata->slots[0].caps |= MMC_CAP_8_BIT_DATA;
+
+	if (of_find_property(np, "ti,needs-special-reset", NULL))
+		pdata->slots[0].features |= HSMMC_HAS_UPDATED_RESET;
+
+	return pdata;
+}
+#else
+static inline struct omap_mmc_platform_data
+			*of_get_hsmmc_pdata(struct device *dev)
+{
+	return NULL;
+}
+#endif
+
 static int __init omap_hsmmc_probe(struct platform_device *pdev)
 {
 	struct omap_mmc_platform_data *pdata = pdev->dev.platform_data;
@@ -1854,6 +1792,16 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev)
 	struct omap_hsmmc_host *host = NULL;
 	struct resource *res;
 	int ret, irq;
+	const struct of_device_id *match;
+
+	match = of_match_device(of_match_ptr(omap_mmc_of_match), &pdev->dev);
+	if (match) {
+		pdata = of_get_hsmmc_pdata(&pdev->dev);
+		if (match->data) {
+			u16 *offsetp = match->data;
+			pdata->reg_offset = *offsetp;
+		}
+	}
 
 	if (pdata == NULL) {
 		dev_err(&pdev->dev, "Platform Data is missing\n");
@@ -1894,7 +1842,6 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev)
 	host->dev->dma_mask = &pdata->dma_mask;
 	host->dma_ch	= -1;
 	host->irq	= irq;
-	host->id	= pdev->id;
 	host->slot_id	= 0;
 	host->mapbase	= res->start;
 	host->base	= ioremap(host->mapbase, SZ_4K);
@@ -1912,8 +1859,12 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev)
 	if (mmc_slot(host).vcc_aux_disable_is_sleep)
 		mmc_slot(host).no_off = 1;
 
-	mmc->f_min	= OMAP_MMC_MIN_CLOCK;
-	mmc->f_max	= OMAP_MMC_MAX_CLOCK;
+	mmc->f_min = OMAP_MMC_MIN_CLOCK;
+
+	if (pdata->max_freq > 0)
+		mmc->f_max = pdata->max_freq;
+	else
+		mmc->f_max = OMAP_MMC_MAX_CLOCK;
 
 	spin_lock_init(&host->irq_lock);
 
@@ -1926,7 +1877,6 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev)
 
 	omap_hsmmc_context_save(host);
 
-	mmc->caps |= MMC_CAP_DISABLE;
 	if (host->pdata->controller_flags & OMAP_HSMMC_BROKEN_MULTIBLOCK_READ) {
 		dev_info(&pdev->dev, "multiblock reads disabled due to 35xx erratum 2.1.1.128; MMC read performance may suffer\n");
 		mmc->caps2 |= MMC_CAP2_NO_MULTI_READ;
@@ -1977,32 +1927,19 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev)
 
 	omap_hsmmc_conf_bus_power(host);
 
-	/* Select DMA lines */
-	switch (host->id) {
-	case OMAP_MMC1_DEVID:
-		host->dma_line_tx = OMAP24XX_DMA_MMC1_TX;
-		host->dma_line_rx = OMAP24XX_DMA_MMC1_RX;
-		break;
-	case OMAP_MMC2_DEVID:
-		host->dma_line_tx = OMAP24XX_DMA_MMC2_TX;
-		host->dma_line_rx = OMAP24XX_DMA_MMC2_RX;
-		break;
-	case OMAP_MMC3_DEVID:
-		host->dma_line_tx = OMAP34XX_DMA_MMC3_TX;
-		host->dma_line_rx = OMAP34XX_DMA_MMC3_RX;
-		break;
-	case OMAP_MMC4_DEVID:
-		host->dma_line_tx = OMAP44XX_DMA_MMC4_TX;
-		host->dma_line_rx = OMAP44XX_DMA_MMC4_RX;
-		break;
-	case OMAP_MMC5_DEVID:
-		host->dma_line_tx = OMAP44XX_DMA_MMC5_TX;
-		host->dma_line_rx = OMAP44XX_DMA_MMC5_RX;
-		break;
-	default:
-		dev_err(mmc_dev(host->mmc), "Invalid MMC id\n");
+	res = platform_get_resource_byname(pdev, IORESOURCE_DMA, "tx");
+	if (!res) {
+		dev_err(mmc_dev(host->mmc), "cannot get DMA TX channel\n");
+		goto err_irq;
+	}
+	host->dma_line_tx = res->start;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_DMA, "rx");
+	if (!res) {
+		dev_err(mmc_dev(host->mmc), "cannot get DMA RX channel\n");
 		goto err_irq;
 	}
+	host->dma_line_rx = res->start;
 
 	/* Request IRQ for MMC operations */
 	ret = request_irq(host->irq, omap_hsmmc_irq, 0,
@@ -2083,6 +2020,7 @@ err_irq_cd_init:
 err_irq:
 	pm_runtime_mark_last_busy(host->dev);
 	pm_runtime_put_autosuspend(host->dev);
+	pm_runtime_disable(host->dev);
 	clk_put(host->fclk);
 	if (host->got_dbclk) {
 		clk_disable(host->dbclk);
@@ -2269,6 +2207,7 @@ static struct platform_driver omap_hsmmc_driver = {
 		.name = DRIVER_NAME,
 		.owner = THIS_MODULE,
 		.pm = &omap_hsmmc_dev_pm_ops,
+		.of_match_table = of_match_ptr(omap_mmc_of_match),
 	},
 };
 
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 5d876ff86f37..f8eb1fb0c921 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -1,7 +1,7 @@
 /*
  * Freescale eSDHC controller driver.
  *
- * Copyright (c) 2007, 2010 Freescale Semiconductor, Inc.
+ * Copyright (c) 2007, 2010, 2012 Freescale Semiconductor, Inc.
  * Copyright (c) 2009 MontaVista Software, Inc.
  *
  * Authors: Xiaobo Xie <X.Xie@freescale.com>
@@ -14,6 +14,7 @@
  */
 
 #include <linux/io.h>
+#include <linux/of.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/mmc/host.h>
@@ -114,6 +115,34 @@ static unsigned int esdhc_of_get_min_clock(struct sdhci_host *host)
 	return pltfm_host->clock / 256 / 16;
 }
 
+static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
+{
+	/* Workaround to reduce the clock frequency for p1010 esdhc */
+	if (of_find_compatible_node(NULL, NULL, "fsl,p1010-esdhc")) {
+		if (clock > 20000000)
+			clock -= 5000000;
+		if (clock > 40000000)
+			clock -= 5000000;
+	}
+
+	/* Set the clock */
+	esdhc_set_clock(host, clock);
+}
+
+#ifdef CONFIG_PM
+static u32 esdhc_proctl;
+static void esdhc_of_suspend(struct sdhci_host *host)
+{
+	esdhc_proctl = sdhci_be32bs_readl(host, SDHCI_HOST_CONTROL);
+}
+
+static void esdhc_of_resume(struct sdhci_host *host)
+{
+	esdhc_of_enable_dma(host);
+	sdhci_be32bs_writel(host, esdhc_proctl, SDHCI_HOST_CONTROL);
+}
+#endif
+
 static struct sdhci_ops sdhci_esdhc_ops = {
 	.read_l = sdhci_be32bs_readl,
 	.read_w = esdhc_readw,
@@ -121,10 +150,14 @@ static struct sdhci_ops sdhci_esdhc_ops = {
 	.write_l = sdhci_be32bs_writel,
 	.write_w = esdhc_writew,
 	.write_b = esdhc_writeb,
-	.set_clock = esdhc_set_clock,
+	.set_clock = esdhc_of_set_clock,
 	.enable_dma = esdhc_of_enable_dma,
 	.get_max_clock = esdhc_of_get_max_clock,
 	.get_min_clock = esdhc_of_get_min_clock,
+#ifdef CONFIG_PM
+	.platform_suspend = esdhc_of_suspend,
+	.platform_resume = esdhc_of_resume,
+#endif
 };
 
 static struct sdhci_pltfm_data sdhci_esdhc_pdata = {
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index 6ebdc4010e7c..fbbebe251e01 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -29,6 +29,12 @@
 #include "sdhci.h"
 
 /*
+ * PCI device IDs
+ */
+#define PCI_DEVICE_ID_INTEL_PCH_SDIO0	0x8809
+#define PCI_DEVICE_ID_INTEL_PCH_SDIO1	0x880a
+
+/*
  * PCI registers
  */
 
@@ -47,6 +53,7 @@ struct sdhci_pci_slot;
 
 struct sdhci_pci_fixes {
 	unsigned int		quirks;
+	unsigned int		quirks2;
 	bool			allow_runtime_pm;
 
 	int			(*probe) (struct sdhci_pci_chip *);
@@ -73,6 +80,7 @@ struct sdhci_pci_chip {
 	struct pci_dev		*pdev;
 
 	unsigned int		quirks;
+	unsigned int		quirks2;
 	bool			allow_runtime_pm;
 	const struct sdhci_pci_fixes *fixes;
 
@@ -172,6 +180,12 @@ static int mrst_hc_probe(struct sdhci_pci_chip *chip)
 	return 0;
 }
 
+static int pch_hc_probe_slot(struct sdhci_pci_slot *slot)
+{
+	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA;
+	return 0;
+}
+
 #ifdef CONFIG_PM_RUNTIME
 
 static irqreturn_t sdhci_pci_sd_cd(int irq, void *dev_id)
@@ -244,7 +258,8 @@ static inline void sdhci_pci_remove_own_cd(struct sdhci_pci_slot *slot)
 static int mfd_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE;
-	slot->host->mmc->caps2 = MMC_CAP2_BOOTPART_NOACC;
+	slot->host->mmc->caps2 |= MMC_CAP2_BOOTPART_NOACC |
+				  MMC_CAP2_HC_ERASE_SZ;
 	return 0;
 }
 
@@ -271,6 +286,7 @@ static const struct sdhci_pci_fixes sdhci_intel_mfd_sd = {
 
 static const struct sdhci_pci_fixes sdhci_intel_mfd_sdio = {
 	.quirks		= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
+	.quirks2	= SDHCI_QUIRK2_HOST_OFF_CARD_ON,
 	.allow_runtime_pm = true,
 	.probe_slot	= mfd_sdio_probe_slot,
 };
@@ -281,6 +297,11 @@ static const struct sdhci_pci_fixes sdhci_intel_mfd_emmc = {
 	.probe_slot	= mfd_emmc_probe_slot,
 };
 
+static const struct sdhci_pci_fixes sdhci_intel_pch_sdio = {
+	.quirks		= SDHCI_QUIRK_BROKEN_ADMA,
+	.probe_slot	= pch_hc_probe_slot,
+};
+
 /* O2Micro extra registers */
 #define O2_SD_LOCK_WP		0xD3
 #define O2_SD_MULTI_VCC3V	0xEE
@@ -817,6 +838,22 @@ static const struct pci_device_id pci_ids[] __devinitdata = {
 	},
 
 	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_PCH_SDIO0,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_pch_sdio,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_PCH_SDIO1,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_pch_sdio,
+	},
+
+	{
 		.vendor		= PCI_VENDOR_ID_O2,
 		.device		= PCI_DEVICE_ID_O2_8120,
 		.subvendor	= PCI_ANY_ID,
@@ -1206,6 +1243,7 @@ static struct sdhci_pci_slot * __devinit sdhci_pci_probe_slot(
 	host->hw_name = "PCI";
 	host->ops = &sdhci_pci_ops;
 	host->quirks = chip->quirks;
+	host->quirks2 = chip->quirks2;
 
 	host->irq = pdev->irq;
 
@@ -1365,6 +1403,7 @@ static int __devinit sdhci_pci_probe(struct pci_dev *pdev,
 	chip->fixes = (const struct sdhci_pci_fixes *)ent->driver_data;
 	if (chip->fixes) {
 		chip->quirks = chip->fixes->quirks;
+		chip->quirks2 = chip->fixes->quirks2;
 		chip->allow_runtime_pm = chip->fixes->allow_runtime_pm;
 	}
 	chip->num_slots = slots;
@@ -1379,6 +1418,8 @@ static int __devinit sdhci_pci_probe(struct pci_dev *pdev,
 
 	slots = chip->num_slots;	/* Quirk may have changed this */
 
+	pci_enable_msi(pdev);
+
 	for (i = 0; i < slots; i++) {
 		slot = sdhci_pci_probe_slot(pdev, chip, first_bar, i);
 		if (IS_ERR(slot)) {
@@ -1397,6 +1438,8 @@ static int __devinit sdhci_pci_probe(struct pci_dev *pdev,
 	return 0;
 
 free:
+	pci_disable_msi(pdev);
+
 	pci_set_drvdata(pdev, NULL);
 	kfree(chip);
 
@@ -1419,6 +1462,8 @@ static void __devexit sdhci_pci_remove(struct pci_dev *pdev)
 		for (i = 0; i < chip->num_slots; i++)
 			sdhci_pci_remove_slot(chip->slots[i]);
 
+		pci_disable_msi(pdev);
+
 		pci_set_drvdata(pdev, NULL);
 		kfree(chip);
 	}
diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c
index b7f8b33c5f19..6dfa82e03c7e 100644
--- a/drivers/mmc/host/sdhci-spear.c
+++ b/drivers/mmc/host/sdhci-spear.c
@@ -300,20 +300,15 @@ static int sdhci_resume(struct device *dev)
 
 	return sdhci_resume_host(host);
 }
-
-const struct dev_pm_ops sdhci_pm_ops = {
-	.suspend	= sdhci_suspend,
-	.resume		= sdhci_resume,
-};
 #endif
 
+static SIMPLE_DEV_PM_OPS(sdhci_pm_ops, sdhci_suspend, sdhci_resume);
+
 static struct platform_driver sdhci_driver = {
 	.driver = {
 		.name	= "sdhci",
 		.owner	= THIS_MODULE,
-#ifdef CONFIG_PM
 		.pm	= &sdhci_pm_ops,
-#endif
 	},
 	.probe		= sdhci_probe,
 	.remove		= __devexit_p(sdhci_remove),
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index cb348569454b..53b26502f6e2 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -19,6 +19,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/gpio.h>
 #include <linux/mmc/card.h>
@@ -31,6 +32,19 @@
 
 #include "sdhci-pltfm.h"
 
+#define NVQUIRK_FORCE_SDHCI_SPEC_200	BIT(0)
+#define NVQUIRK_ENABLE_BLOCK_GAP_DET	BIT(1)
+
+struct sdhci_tegra_soc_data {
+	struct sdhci_pltfm_data *pdata;
+	u32 nvquirks;
+};
+
+struct sdhci_tegra {
+	const struct tegra_sdhci_platform_data *plat;
+	const struct sdhci_tegra_soc_data *soc_data;
+};
+
 static u32 tegra_sdhci_readl(struct sdhci_host *host, int reg)
 {
 	u32 val;
@@ -46,7 +60,12 @@ static u32 tegra_sdhci_readl(struct sdhci_host *host, int reg)
 
 static u16 tegra_sdhci_readw(struct sdhci_host *host, int reg)
 {
-	if (unlikely(reg == SDHCI_HOST_VERSION)) {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_tegra *tegra_host = pltfm_host->priv;
+	const struct sdhci_tegra_soc_data *soc_data = tegra_host->soc_data;
+
+	if (unlikely((soc_data->nvquirks & NVQUIRK_FORCE_SDHCI_SPEC_200) &&
+			(reg == SDHCI_HOST_VERSION))) {
 		/* Erratum: Version register is invalid in HW. */
 		return SDHCI_SPEC_200;
 	}
@@ -56,6 +75,10 @@ static u16 tegra_sdhci_readw(struct sdhci_host *host, int reg)
 
 static void tegra_sdhci_writel(struct sdhci_host *host, u32 val, int reg)
 {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_tegra *tegra_host = pltfm_host->priv;
+	const struct sdhci_tegra_soc_data *soc_data = tegra_host->soc_data;
+
 	/* Seems like we're getting spurious timeout and crc errors, so
 	 * disable signalling of them. In case of real errors software
 	 * timers should take care of eventually detecting them.
@@ -65,7 +88,8 @@ static void tegra_sdhci_writel(struct sdhci_host *host, u32 val, int reg)
 
 	writel(val, host->ioaddr + reg);
 
-	if (unlikely(reg == SDHCI_INT_ENABLE)) {
+	if (unlikely((soc_data->nvquirks & NVQUIRK_ENABLE_BLOCK_GAP_DET) &&
+			(reg == SDHCI_INT_ENABLE))) {
 		/* Erratum: Must enable block gap interrupt detection */
 		u8 gap_ctrl = readb(host->ioaddr + SDHCI_BLOCK_GAP_CONTROL);
 		if (val & SDHCI_INT_CARD_INT)
@@ -76,10 +100,11 @@ static void tegra_sdhci_writel(struct sdhci_host *host, u32 val, int reg)
 	}
 }
 
-static unsigned int tegra_sdhci_get_ro(struct sdhci_host *sdhci)
+static unsigned int tegra_sdhci_get_ro(struct sdhci_host *host)
 {
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(sdhci);
-	struct tegra_sdhci_platform_data *plat = pltfm_host->priv;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_tegra *tegra_host = pltfm_host->priv;
+	const struct tegra_sdhci_platform_data *plat = tegra_host->plat;
 
 	if (!gpio_is_valid(plat->wp_gpio))
 		return -1;
@@ -98,7 +123,8 @@ static irqreturn_t carddetect_irq(int irq, void *data)
 static int tegra_sdhci_8bit(struct sdhci_host *host, int bus_width)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct tegra_sdhci_platform_data *plat = pltfm_host->priv;
+	struct sdhci_tegra *tegra_host = pltfm_host->priv;
+	const struct tegra_sdhci_platform_data *plat = tegra_host->plat;
 	u32 ctrl;
 
 	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
@@ -124,16 +150,44 @@ static struct sdhci_ops tegra_sdhci_ops = {
 	.platform_8bit_width = tegra_sdhci_8bit,
 };
 
-static struct sdhci_pltfm_data sdhci_tegra_pdata = {
+#ifdef CONFIG_ARCH_TEGRA_2x_SOC
+static struct sdhci_pltfm_data sdhci_tegra20_pdata = {
+	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
+		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
+		  SDHCI_QUIRK_NO_HISPD_BIT |
+		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC,
+	.ops  = &tegra_sdhci_ops,
+};
+
+static struct sdhci_tegra_soc_data soc_data_tegra20 = {
+	.pdata = &sdhci_tegra20_pdata,
+	.nvquirks = NVQUIRK_FORCE_SDHCI_SPEC_200 |
+		    NVQUIRK_ENABLE_BLOCK_GAP_DET,
+};
+#endif
+
+#ifdef CONFIG_ARCH_TEGRA_3x_SOC
+static struct sdhci_pltfm_data sdhci_tegra30_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
+		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
 		  SDHCI_QUIRK_NO_HISPD_BIT |
 		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC,
 	.ops  = &tegra_sdhci_ops,
 };
 
+static struct sdhci_tegra_soc_data soc_data_tegra30 = {
+	.pdata = &sdhci_tegra30_pdata,
+};
+#endif
+
 static const struct of_device_id sdhci_tegra_dt_match[] __devinitdata = {
-	{ .compatible = "nvidia,tegra20-sdhci", },
+#ifdef CONFIG_ARCH_TEGRA_3x_SOC
+	{ .compatible = "nvidia,tegra30-sdhci", .data = &soc_data_tegra30 },
+#endif
+#ifdef CONFIG_ARCH_TEGRA_2x_SOC
+	{ .compatible = "nvidia,tegra20-sdhci", .data = &soc_data_tegra20 },
+#endif
 	{}
 };
 MODULE_DEVICE_TABLE(of, sdhci_dt_ids);
@@ -164,13 +218,22 @@ static struct tegra_sdhci_platform_data * __devinit sdhci_tegra_dt_parse_pdata(
 
 static int __devinit sdhci_tegra_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *match;
+	const struct sdhci_tegra_soc_data *soc_data;
+	struct sdhci_host *host;
 	struct sdhci_pltfm_host *pltfm_host;
 	struct tegra_sdhci_platform_data *plat;
-	struct sdhci_host *host;
+	struct sdhci_tegra *tegra_host;
 	struct clk *clk;
 	int rc;
 
-	host = sdhci_pltfm_init(pdev, &sdhci_tegra_pdata);
+	match = of_match_device(sdhci_tegra_dt_match, &pdev->dev);
+	if (match)
+		soc_data = match->data;
+	else
+		soc_data = &soc_data_tegra20;
+
+	host = sdhci_pltfm_init(pdev, soc_data->pdata);
 	if (IS_ERR(host))
 		return PTR_ERR(host);
 
@@ -187,7 +250,17 @@ static int __devinit sdhci_tegra_probe(struct platform_device *pdev)
 		goto err_no_plat;
 	}
 
-	pltfm_host->priv = plat;
+	tegra_host = devm_kzalloc(&pdev->dev, sizeof(*tegra_host), GFP_KERNEL);
+	if (!tegra_host) {
+		dev_err(mmc_dev(host->mmc), "failed to allocate tegra_host\n");
+		rc = -ENOMEM;
+		goto err_no_plat;
+	}
+
+	tegra_host->plat = plat;
+	tegra_host->soc_data = soc_data;
+
+	pltfm_host->priv = tegra_host;
 
 	if (gpio_is_valid(plat->power_gpio)) {
 		rc = gpio_request(plat->power_gpio, "sdhci_power");
@@ -283,7 +356,8 @@ static int __devexit sdhci_tegra_remove(struct platform_device *pdev)
 {
 	struct sdhci_host *host = platform_get_drvdata(pdev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct tegra_sdhci_platform_data *plat = pltfm_host->priv;
+	struct sdhci_tegra *tegra_host = pltfm_host->priv;
+	const struct tegra_sdhci_platform_data *plat = tegra_host->plat;
 	int dead = (readl(host->ioaddr + SDHCI_INT_STATUS) == 0xffffffff);
 
 	sdhci_remove_host(host, dead);
@@ -326,5 +400,5 @@ static struct platform_driver sdhci_tegra_driver = {
 module_platform_driver(sdhci_tegra_driver);
 
 MODULE_DESCRIPTION("SDHCI driver for Tegra");
-MODULE_AUTHOR(" Google, Inc.");
+MODULE_AUTHOR("Google, Inc.");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 8d66706824a6..8262cadfdab7 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2267,8 +2267,8 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 {
 	irqreturn_t result;
 	struct sdhci_host *host = dev_id;
-	u32 intmask;
-	int cardint = 0;
+	u32 intmask, unexpected = 0;
+	int cardint = 0, max_loops = 16;
 
 	spin_lock(&host->lock);
 
@@ -2286,6 +2286,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 		goto out;
 	}
 
+again:
 	DBG("*** %s got interrupt: 0x%08x\n",
 		mmc_hostname(host->mmc), intmask);
 
@@ -2344,19 +2345,23 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 	intmask &= ~SDHCI_INT_CARD_INT;
 
 	if (intmask) {
-		pr_err("%s: Unexpected interrupt 0x%08x.\n",
-			mmc_hostname(host->mmc), intmask);
-		sdhci_dumpregs(host);
-
+		unexpected |= intmask;
 		sdhci_writel(host, intmask, SDHCI_INT_STATUS);
 	}
 
 	result = IRQ_HANDLED;
 
-	mmiowb();
+	intmask = sdhci_readl(host, SDHCI_INT_STATUS);
+	if (intmask && --max_loops)
+		goto again;
 out:
 	spin_unlock(&host->lock);
 
+	if (unexpected) {
+		pr_err("%s: Unexpected interrupt 0x%08x.\n",
+			   mmc_hostname(host->mmc), unexpected);
+		sdhci_dumpregs(host);
+	}
 	/*
 	 * We have to delay this as it calls back into the driver.
 	 */
@@ -2379,6 +2384,9 @@ int sdhci_suspend_host(struct sdhci_host *host)
 	int ret;
 	bool has_tuning_timer;
 
+	if (host->ops->platform_suspend)
+		host->ops->platform_suspend(host);
+
 	sdhci_disable_card_detection(host);
 
 	/* Disable tuning since we are suspending */
@@ -2423,12 +2431,24 @@ int sdhci_resume_host(struct sdhci_host *host)
 	if (ret)
 		return ret;
 
-	sdhci_init(host, (host->mmc->pm_flags & MMC_PM_KEEP_POWER));
-	mmiowb();
+	if ((host->mmc->pm_flags & MMC_PM_KEEP_POWER) &&
+	    (host->quirks2 & SDHCI_QUIRK2_HOST_OFF_CARD_ON)) {
+		/* Card keeps power but host controller does not */
+		sdhci_init(host, 0);
+		host->pwr = 0;
+		host->clock = 0;
+		sdhci_do_set_ios(host, &host->mmc->ios);
+	} else {
+		sdhci_init(host, (host->mmc->pm_flags & MMC_PM_KEEP_POWER));
+		mmiowb();
+	}
 
 	ret = mmc_resume_host(host->mmc);
 	sdhci_enable_card_detection(host);
 
+	if (host->ops->platform_resume)
+		host->ops->platform_resume(host);
+
 	/* Set the re-tuning expiration flag */
 	if ((host->version >= SDHCI_SPEC_300) && host->tuning_count &&
 	    (host->tuning_mode == SDHCI_TUNING_MODE_1))
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index ad265b96b75b..f761f23d2a28 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -275,6 +275,8 @@ struct sdhci_ops {
 	void	(*platform_reset_exit)(struct sdhci_host *host, u8 mask);
 	int	(*set_uhs_signaling)(struct sdhci_host *host, unsigned int uhs);
 	void	(*hw_reset)(struct sdhci_host *host);
+	void	(*platform_suspend)(struct sdhci_host *host);
+	void	(*platform_resume)(struct sdhci_host *host);
 };
 
 #ifdef CONFIG_MMC_SDHCI_IO_ACCESSORS
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 75a485448796..aafaf0b6eb1c 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -286,7 +286,7 @@ static void sh_mmcif_start_dma_rx(struct sh_mmcif_host *host)
 			 DMA_FROM_DEVICE);
 	if (ret > 0) {
 		host->dma_active = true;
-		desc = chan->device->device_prep_slave_sg(chan, sg, ret,
+		desc = dmaengine_prep_slave_sg(chan, sg, ret,
 			DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	}
 
@@ -335,7 +335,7 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 			 DMA_TO_DEVICE);
 	if (ret > 0) {
 		host->dma_active = true;
-		desc = chan->device->device_prep_slave_sg(chan, sg, ret,
+		desc = dmaengine_prep_slave_sg(chan, sg, ret,
 			DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	}
 
@@ -746,7 +746,6 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 	case MMC_SET_WRITE_PROT:
 	case MMC_CLR_WRITE_PROT:
 	case MMC_ERASE:
-	case MMC_GEN_CMD:
 		tmp |= CMD_SET_RBSY;
 		break;
 	}
@@ -829,7 +828,6 @@ static void sh_mmcif_start_cmd(struct sh_mmcif_host *host,
 	case MMC_SET_WRITE_PROT:
 	case MMC_CLR_WRITE_PROT:
 	case MMC_ERASE:
-	case MMC_GEN_CMD:
 		mask = MASK_START_CMD | MASK_MRBSYE;
 		break;
 	default:
diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 58da3c44acc5..934b68e9efc3 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -90,6 +90,15 @@ static int sh_mobile_sdhi_write16_hook(struct tmio_mmc_host *host, int addr)
 	return 0;
 }
 
+static void sh_mobile_sdhi_cd_wakeup(const struct platform_device *pdev)
+{
+	mmc_detect_change(dev_get_drvdata(&pdev->dev), msecs_to_jiffies(100));
+}
+
+static const struct sh_mobile_sdhi_ops sdhi_ops = {
+	.cd_wakeup = sh_mobile_sdhi_cd_wakeup,
+};
+
 static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev)
 {
 	struct sh_mobile_sdhi *priv;
@@ -109,6 +118,12 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev)
 	mmc_data = &priv->mmc_data;
 	p->pdata = mmc_data;
 
+	if (p->init) {
+		ret = p->init(pdev, &sdhi_ops);
+		if (ret)
+			goto einit;
+	}
+
 	snprintf(clk_name, sizeof(clk_name), "sdhi%d", pdev->id);
 	priv->clk = clk_get(&pdev->dev, clk_name);
 	if (IS_ERR(priv->clk)) {
@@ -117,8 +132,6 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev)
 		goto eclkget;
 	}
 
-	clk_enable(priv->clk);
-
 	mmc_data->hclk = clk_get_rate(priv->clk);
 	mmc_data->set_pwr = sh_mobile_sdhi_set_pwr;
 	mmc_data->get_cd = sh_mobile_sdhi_get_cd;
@@ -129,6 +142,7 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev)
 			mmc_data->write16_hook = sh_mobile_sdhi_write16_hook;
 		mmc_data->ocr_mask = p->tmio_ocr_mask;
 		mmc_data->capabilities |= p->tmio_caps;
+		mmc_data->cd_gpio = p->cd_gpio;
 
 		if (p->dma_slave_tx > 0 && p->dma_slave_rx > 0) {
 			priv->param_tx.slave_id = p->dma_slave_tx;
@@ -211,7 +225,7 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "%s base at 0x%08lx clock rate %u MHz\n",
 		 mmc_hostname(host->mmc), (unsigned long)
-		 (platform_get_resource(pdev,IORESOURCE_MEM, 0)->start),
+		 (platform_get_resource(pdev, IORESOURCE_MEM, 0)->start),
 		 mmc_data->hclk / 1000000);
 
 	return ret;
@@ -232,9 +246,11 @@ eirq_sdio:
 eirq_card_detect:
 	tmio_mmc_host_remove(host);
 eprobe:
-	clk_disable(priv->clk);
 	clk_put(priv->clk);
 eclkget:
+	if (p->cleanup)
+		p->cleanup(pdev);
+einit:
 	kfree(priv);
 	return ret;
 }
@@ -258,8 +274,11 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev)
 		free_irq(irq, host);
 	}
 
-	clk_disable(priv->clk);
 	clk_put(priv->clk);
+
+	if (p->cleanup)
+		p->cleanup(pdev);
+
 	kfree(priv);
 
 	return 0;
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index f96c536d130a..d857f5c6e7d9 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -47,16 +47,14 @@ struct tmio_mmc_host {
 	struct mmc_request      *mrq;
 	struct mmc_data         *data;
 	struct mmc_host         *mmc;
-	unsigned int		sdio_irq_enabled;
+
+	/* Controller power state */
+	bool			power;
 
 	/* Callbacks for clock / power control */
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
 
-	int			pm_error;
-	/* recognise system-wide suspend in runtime PM methods */
-	bool			pm_global;
-
 	/* pio related stuff */
 	struct scatterlist      *sg_ptr;
 	struct scatterlist      *sg_orig;
@@ -86,6 +84,7 @@ struct tmio_mmc_host {
 	spinlock_t		lock;		/* protect host private data */
 	unsigned long		last_req_ts;
 	struct mutex		ios_lock;	/* protect set_ios() context */
+	bool			native_hotplug;
 };
 
 int tmio_mmc_host_probe(struct tmio_mmc_host **host,
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index 8253ec12003e..fff928604859 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -88,7 +88,7 @@ static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host)
 
 	ret = dma_map_sg(chan->device->dev, sg, host->sg_len, DMA_FROM_DEVICE);
 	if (ret > 0)
-		desc = chan->device->device_prep_slave_sg(chan, sg, ret,
+		desc = dmaengine_prep_slave_sg(chan, sg, ret,
 			DMA_DEV_TO_MEM, DMA_CTRL_ACK);
 
 	if (desc) {
@@ -169,7 +169,7 @@ static void tmio_mmc_start_dma_tx(struct tmio_mmc_host *host)
 
 	ret = dma_map_sg(chan->device->dev, sg, host->sg_len, DMA_TO_DEVICE);
 	if (ret > 0)
-		desc = chan->device->device_prep_slave_sg(chan, sg, ret,
+		desc = dmaengine_prep_slave_sg(chan, sg, ret,
 			DMA_MEM_TO_DEV, DMA_CTRL_ACK);
 
 	if (desc) {
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index e21988901c36..9a7996ade58e 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -34,6 +34,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/mfd/tmio.h>
+#include <linux/mmc/cd-gpio.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/tmio.h>
 #include <linux/module.h>
@@ -127,7 +128,6 @@ static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
 	if (enable) {
-		host->sdio_irq_enabled = 1;
 		host->sdio_irq_mask = TMIO_SDIO_MASK_ALL &
 					~TMIO_SDIO_STAT_IOIRQ;
 		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001);
@@ -136,7 +136,6 @@ static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 		host->sdio_irq_mask = TMIO_SDIO_MASK_ALL;
 		sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask);
 		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0000);
-		host->sdio_irq_enabled = 0;
 	}
 }
 
@@ -304,6 +303,7 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 {
 	struct mmc_data *data = host->data;
 	int c = cmd->opcode;
+	u32 irq_mask = TMIO_MASK_CMD;
 
 	/* Command 12 is handled by hardware */
 	if (cmd->opcode == 12 && !cmd->arg) {
@@ -339,7 +339,9 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 			c |= TRANSFER_READ;
 	}
 
-	tmio_mmc_enable_mmc_irqs(host, TMIO_MASK_CMD);
+	if (!host->native_hotplug)
+		irq_mask &= ~(TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT);
+	tmio_mmc_enable_mmc_irqs(host, irq_mask);
 
 	/* Fire off the command */
 	sd_ctrl_write32(host, CTL_ARG_REG, cmd->arg);
@@ -758,7 +760,7 @@ fail:
 static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct tmio_mmc_host *host = mmc_priv(mmc);
-	struct tmio_mmc_data *pdata = host->pdata;
+	struct device *dev = &host->pdev->dev;
 	unsigned long flags;
 
 	mutex_lock(&host->ios_lock);
@@ -766,13 +768,13 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	spin_lock_irqsave(&host->lock, flags);
 	if (host->mrq) {
 		if (IS_ERR(host->mrq)) {
-			dev_dbg(&host->pdev->dev,
+			dev_dbg(dev,
 				"%s.%d: concurrent .set_ios(), clk %u, mode %u\n",
 				current->comm, task_pid_nr(current),
 				ios->clock, ios->power_mode);
 			host->mrq = ERR_PTR(-EINTR);
 		} else {
-			dev_dbg(&host->pdev->dev,
+			dev_dbg(dev,
 				"%s.%d: CMD%u active since %lu, now %lu!\n",
 				current->comm, task_pid_nr(current),
 				host->mrq->cmd->opcode, host->last_req_ts, jiffies);
@@ -788,13 +790,15 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	/*
-	 * pdata->power == false only if COLD_CD is available, otherwise only
-	 * in short time intervals during probing or resuming
+	 * host->power toggles between false and true in both cases - either
+	 * or not the controller can be runtime-suspended during inactivity.
+	 * But if the controller has to be kept on, the runtime-pm usage_count
+	 * is kept positive, so no suspending actually takes place.
 	 */
 	if (ios->power_mode == MMC_POWER_ON && ios->clock) {
-		if (!pdata->power) {
-			pm_runtime_get_sync(&host->pdev->dev);
-			pdata->power = true;
+		if (!host->power) {
+			pm_runtime_get_sync(dev);
+			host->power = true;
 		}
 		tmio_mmc_set_clock(host, ios->clock);
 		/* power up SD bus */
@@ -805,9 +809,9 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	} else if (ios->power_mode != MMC_POWER_UP) {
 		if (host->set_pwr && ios->power_mode == MMC_POWER_OFF)
 			host->set_pwr(host->pdev, 0);
-		if (pdata->power) {
-			pdata->power = false;
-			pm_runtime_put(&host->pdev->dev);
+		if (host->power) {
+			host->power = false;
+			pm_runtime_put(dev);
 		}
 		tmio_mmc_clk_stop(host);
 	}
@@ -913,7 +917,11 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host,
 	else
 		mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
 
-	pdata->power = false;
+	_host->native_hotplug = !(pdata->flags & TMIO_MMC_USE_GPIO_CD ||
+				  mmc->caps & MMC_CAP_NEEDS_POLL ||
+				  mmc->caps & MMC_CAP_NONREMOVABLE);
+
+	_host->power = false;
 	pm_runtime_enable(&pdev->dev);
 	ret = pm_runtime_resume(&pdev->dev);
 	if (ret < 0)
@@ -926,14 +934,13 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host,
 	 *  3) a worker thread polls the sdhi - indicated by MMC_CAP_NEEDS_POLL
 	 *  4) the medium is non-removable - indicated by MMC_CAP_NONREMOVABLE
 	 *
-	 *  While we increment the rtpm counter for all scenarios when the mmc
-	 *  core activates us by calling an appropriate set_ios(), we must
+	 *  While we increment the runtime PM counter for all scenarios when
+	 *  the mmc core activates us by calling an appropriate set_ios(), we
+	 *  must additionally ensure that in case 2) the tmio mmc hardware stays
 	 *  additionally ensure that in case 2) the tmio mmc hardware stays
 	 *  powered on during runtime for the card detection to work.
 	 */
-	if (!(pdata->flags & TMIO_MMC_HAS_COLD_CD
-		|| mmc->caps & MMC_CAP_NEEDS_POLL
-		|| mmc->caps & MMC_CAP_NONREMOVABLE))
+	if (_host->native_hotplug)
 		pm_runtime_get_noresume(&pdev->dev);
 
 	tmio_mmc_clk_stop(_host);
@@ -963,9 +970,19 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host,
 		irq_mask |= TMIO_MASK_READOP;
 	if (!_host->chan_tx)
 		irq_mask |= TMIO_MASK_WRITEOP;
+	if (!_host->native_hotplug)
+		irq_mask &= ~(TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT);
 
 	tmio_mmc_enable_mmc_irqs(_host, irq_mask);
 
+	if (pdata->flags & TMIO_MMC_USE_GPIO_CD) {
+		ret = mmc_cd_gpio_request(mmc, pdata->cd_gpio);
+		if (ret < 0) {
+			tmio_mmc_host_remove(_host);
+			return ret;
+		}
+	}
+
 	*host = _host;
 
 	return 0;
@@ -983,22 +1000,22 @@ EXPORT_SYMBOL(tmio_mmc_host_probe);
 void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 {
 	struct platform_device *pdev = host->pdev;
+	struct tmio_mmc_data *pdata = host->pdata;
+	struct mmc_host *mmc = host->mmc;
 
-	/*
-	 * We don't have to manipulate pdata->power here: if there is a card in
-	 * the slot, the runtime PM is active and our .runtime_resume() will not
-	 * be run. If there is no card in the slot and the platform can suspend
-	 * the controller, the runtime PM is suspended and pdata->power == false,
-	 * so, our .runtime_resume() will not try to detect a card in the slot.
-	 */
-	if (host->pdata->flags & TMIO_MMC_HAS_COLD_CD
-		|| host->mmc->caps & MMC_CAP_NEEDS_POLL
-		|| host->mmc->caps & MMC_CAP_NONREMOVABLE)
+	if (pdata->flags & TMIO_MMC_USE_GPIO_CD)
+		/*
+		 * This means we can miss a card-eject, but this is anyway
+		 * possible, because of delayed processing of hotplug events.
+		 */
+		mmc_cd_gpio_free(mmc);
+
+	if (!host->native_hotplug)
 		pm_runtime_get_sync(&pdev->dev);
 
 	dev_pm_qos_hide_latency_limit(&pdev->dev);
 
-	mmc_remove_host(host->mmc);
+	mmc_remove_host(mmc);
 	cancel_work_sync(&host->done);
 	cancel_delayed_work_sync(&host->delayed_reset_work);
 	tmio_mmc_release_dma(host);
@@ -1007,7 +1024,7 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 	pm_runtime_disable(&pdev->dev);
 
 	iounmap(host->ctl);
-	mmc_free_host(host->mmc);
+	mmc_free_host(mmc);
 }
 EXPORT_SYMBOL(tmio_mmc_host_remove);
 
@@ -1021,8 +1038,6 @@ int tmio_mmc_host_suspend(struct device *dev)
 	if (!ret)
 		tmio_mmc_disable_mmc_irqs(host, TMIO_MASK_ALL);
 
-	host->pm_error = pm_runtime_put_sync(dev);
-
 	return ret;
 }
 EXPORT_SYMBOL(tmio_mmc_host_suspend);
@@ -1032,20 +1047,10 @@ int tmio_mmc_host_resume(struct device *dev)
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
-	/* The MMC core will perform the complete set up */
-	host->pdata->power = false;
-
-	host->pm_global = true;
-	if (!host->pm_error)
-		pm_runtime_get_sync(dev);
-
-	if (host->pm_global) {
-		/* Runtime PM resume callback didn't run */
-		tmio_mmc_reset(host);
-		tmio_mmc_enable_dma(host, true);
-		host->pm_global = false;
-	}
+	tmio_mmc_reset(host);
+	tmio_mmc_enable_dma(host, true);
 
+	/* The MMC core will perform the complete set up */
 	return mmc_resume_host(mmc);
 }
 EXPORT_SYMBOL(tmio_mmc_host_resume);
@@ -1062,19 +1067,10 @@ int tmio_mmc_host_runtime_resume(struct device *dev)
 {
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct tmio_mmc_host *host = mmc_priv(mmc);
-	struct tmio_mmc_data *pdata = host->pdata;
 
 	tmio_mmc_reset(host);
 	tmio_mmc_enable_dma(host, true);
 
-	if (pdata->power) {
-		/* Only entered after a card-insert interrupt */
-		if (!mmc->card)
-			tmio_mmc_set_ios(mmc, &mmc->ios);
-		mmc_detect_change(mmc, msecs_to_jiffies(100));
-	}
-	host->pm_global = false;
-
 	return 0;
 }
 EXPORT_SYMBOL(tmio_mmc_host_runtime_resume);
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 1be621841400..5760c1a4b3f6 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -1,6 +1,6 @@
 menuconfig MTD
 	tristate "Memory Technology Device (MTD) support"
-	depends on HAS_IOMEM
+	depends on GENERIC_IO
 	help
 	  Memory Technology Devices are flash, RAM and similar chips, often
 	  used for solid state file systems on embedded devices. This option
@@ -304,9 +304,6 @@ config MTD_OOPS
 	  buffer in a flash partition where it can be read back at some
 	  later point.
 
-	  To use, add console=ttyMTDx to the kernel command line,
-	  where x is the MTD device number to use.
-
 config MTD_SWAP
 	tristate "Swap on MTD device support"
 	depends on MTD && SWAP
diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index 9bcd1f415f43..dbbd2edfb812 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -87,7 +87,7 @@ static int cfi_intelext_partition_fixup(struct mtd_info *, struct cfi_private **
 
 static int cfi_intelext_point (struct mtd_info *mtd, loff_t from, size_t len,
 		     size_t *retlen, void **virt, resource_size_t *phys);
-static void cfi_intelext_unpoint(struct mtd_info *mtd, loff_t from, size_t len);
+static int cfi_intelext_unpoint(struct mtd_info *mtd, loff_t from, size_t len);
 
 static int chip_ready (struct map_info *map, struct flchip *chip, unsigned long adr, int mode);
 static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr, int mode);
@@ -262,9 +262,9 @@ static void fixup_st_m28w320cb(struct mtd_info *mtd)
 static void fixup_use_point(struct mtd_info *mtd)
 {
 	struct map_info *map = mtd->priv;
-	if (!mtd->point && map_is_linear(map)) {
-		mtd->point   = cfi_intelext_point;
-		mtd->unpoint = cfi_intelext_unpoint;
+	if (!mtd->_point && map_is_linear(map)) {
+		mtd->_point   = cfi_intelext_point;
+		mtd->_unpoint = cfi_intelext_unpoint;
 	}
 }
 
@@ -274,8 +274,8 @@ static void fixup_use_write_buffers(struct mtd_info *mtd)
 	struct cfi_private *cfi = map->fldrv_priv;
 	if (cfi->cfiq->BufWriteTimeoutTyp) {
 		printk(KERN_INFO "Using buffer write method\n" );
-		mtd->write = cfi_intelext_write_buffers;
-		mtd->writev = cfi_intelext_writev;
+		mtd->_write = cfi_intelext_write_buffers;
+		mtd->_writev = cfi_intelext_writev;
 	}
 }
 
@@ -443,15 +443,15 @@ struct mtd_info *cfi_cmdset_0001(struct map_info *map, int primary)
 	mtd->type = MTD_NORFLASH;
 
 	/* Fill in the default mtd operations */
-	mtd->erase   = cfi_intelext_erase_varsize;
-	mtd->read    = cfi_intelext_read;
-	mtd->write   = cfi_intelext_write_words;
-	mtd->sync    = cfi_intelext_sync;
-	mtd->lock    = cfi_intelext_lock;
-	mtd->unlock  = cfi_intelext_unlock;
-	mtd->is_locked = cfi_intelext_is_locked;
-	mtd->suspend = cfi_intelext_suspend;
-	mtd->resume  = cfi_intelext_resume;
+	mtd->_erase   = cfi_intelext_erase_varsize;
+	mtd->_read    = cfi_intelext_read;
+	mtd->_write   = cfi_intelext_write_words;
+	mtd->_sync    = cfi_intelext_sync;
+	mtd->_lock    = cfi_intelext_lock;
+	mtd->_unlock  = cfi_intelext_unlock;
+	mtd->_is_locked = cfi_intelext_is_locked;
+	mtd->_suspend = cfi_intelext_suspend;
+	mtd->_resume  = cfi_intelext_resume;
 	mtd->flags   = MTD_CAP_NORFLASH;
 	mtd->name    = map->name;
 	mtd->writesize = 1;
@@ -600,12 +600,12 @@ static struct mtd_info *cfi_intelext_setup(struct mtd_info *mtd)
 	}
 
 #ifdef CONFIG_MTD_OTP
-	mtd->read_fact_prot_reg = cfi_intelext_read_fact_prot_reg;
-	mtd->read_user_prot_reg = cfi_intelext_read_user_prot_reg;
-	mtd->write_user_prot_reg = cfi_intelext_write_user_prot_reg;
-	mtd->lock_user_prot_reg = cfi_intelext_lock_user_prot_reg;
-	mtd->get_fact_prot_info = cfi_intelext_get_fact_prot_info;
-	mtd->get_user_prot_info = cfi_intelext_get_user_prot_info;
+	mtd->_read_fact_prot_reg = cfi_intelext_read_fact_prot_reg;
+	mtd->_read_user_prot_reg = cfi_intelext_read_user_prot_reg;
+	mtd->_write_user_prot_reg = cfi_intelext_write_user_prot_reg;
+	mtd->_lock_user_prot_reg = cfi_intelext_lock_user_prot_reg;
+	mtd->_get_fact_prot_info = cfi_intelext_get_fact_prot_info;
+	mtd->_get_user_prot_info = cfi_intelext_get_user_prot_info;
 #endif
 
 	/* This function has the potential to distort the reality
@@ -1017,8 +1017,6 @@ static void put_chip(struct map_info *map, struct flchip *chip, unsigned long ad
 	case FL_READY:
 	case FL_STATUS:
 	case FL_JEDEC_QUERY:
-		/* We should really make set_vpp() count, rather than doing this */
-		DISABLE_VPP(map);
 		break;
 	default:
 		printk(KERN_ERR "%s: put_chip() called with oldstate %d!!\n", map->name, chip->oldstate);
@@ -1324,7 +1322,7 @@ static int cfi_intelext_point(struct mtd_info *mtd, loff_t from, size_t len,
 	int chipnum;
 	int ret = 0;
 
-	if (!map->virt || (from + len > mtd->size))
+	if (!map->virt)
 		return -EINVAL;
 
 	/* Now lock the chip(s) to POINT state */
@@ -1334,7 +1332,6 @@ static int cfi_intelext_point(struct mtd_info *mtd, loff_t from, size_t len,
 	ofs = from - (chipnum << cfi->chipshift);
 
 	*virt = map->virt + cfi->chips[chipnum].start + ofs;
-	*retlen = 0;
 	if (phys)
 		*phys = map->phys + cfi->chips[chipnum].start + ofs;
 
@@ -1369,12 +1366,12 @@ static int cfi_intelext_point(struct mtd_info *mtd, loff_t from, size_t len,
 	return 0;
 }
 
-static void cfi_intelext_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
+static int cfi_intelext_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long ofs;
-	int chipnum;
+	int chipnum, err = 0;
 
 	/* Now unlock the chip(s) POINT state */
 
@@ -1382,7 +1379,7 @@ static void cfi_intelext_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 	chipnum = (from >> cfi->chipshift);
 	ofs = from - (chipnum <<  cfi->chipshift);
 
-	while (len) {
+	while (len && !err) {
 		unsigned long thislen;
 		struct flchip *chip;
 
@@ -1400,8 +1397,10 @@ static void cfi_intelext_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 			chip->ref_point_counter--;
 			if(chip->ref_point_counter == 0)
 				chip->state = FL_READY;
-		} else
-			printk(KERN_ERR "%s: Warning: unpoint called on non pointed region\n", map->name); /* Should this give an error? */
+		} else {
+			printk(KERN_ERR "%s: Error: unpoint called on non pointed region\n", map->name);
+			err = -EINVAL;
+		}
 
 		put_chip(map, chip, chip->start);
 		mutex_unlock(&chip->mutex);
@@ -1410,6 +1409,8 @@ static void cfi_intelext_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 		ofs = 0;
 		chipnum++;
 	}
+
+	return err;
 }
 
 static inline int do_read_onechip(struct map_info *map, struct flchip *chip, loff_t adr, size_t len, u_char *buf)
@@ -1456,8 +1457,6 @@ static int cfi_intelext_read (struct mtd_info *mtd, loff_t from, size_t len, siz
 	chipnum = (from >> cfi->chipshift);
 	ofs = from - (chipnum <<  cfi->chipshift);
 
-	*retlen = 0;
-
 	while (len) {
 		unsigned long thislen;
 
@@ -1551,7 +1550,8 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip,
 	}
 
 	xip_enable(map, chip, adr);
- out:	put_chip(map, chip, adr);
+ out:	DISABLE_VPP(map);
+	put_chip(map, chip, adr);
 	mutex_unlock(&chip->mutex);
 	return ret;
 }
@@ -1565,10 +1565,6 @@ static int cfi_intelext_write_words (struct mtd_info *mtd, loff_t to , size_t le
 	int chipnum;
 	unsigned long ofs;
 
-	*retlen = 0;
-	if (!len)
-		return 0;
-
 	chipnum = to >> cfi->chipshift;
 	ofs = to  - (chipnum << cfi->chipshift);
 
@@ -1794,7 +1790,8 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 	}
 
 	xip_enable(map, chip, cmd_adr);
- out:	put_chip(map, chip, cmd_adr);
+ out:	DISABLE_VPP(map);
+	put_chip(map, chip, cmd_adr);
 	mutex_unlock(&chip->mutex);
 	return ret;
 }
@@ -1813,7 +1810,6 @@ static int cfi_intelext_writev (struct mtd_info *mtd, const struct kvec *vecs,
 	for (i = 0; i < count; i++)
 		len += vecs[i].iov_len;
 
-	*retlen = 0;
 	if (!len)
 		return 0;
 
@@ -1932,6 +1928,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 			ret = -EIO;
 		} else if (chipstatus & 0x20 && retries--) {
 			printk(KERN_DEBUG "block erase failed at 0x%08lx: status 0x%lx. Retrying...\n", adr, chipstatus);
+			DISABLE_VPP(map);
 			put_chip(map, chip, adr);
 			mutex_unlock(&chip->mutex);
 			goto retry;
@@ -1944,7 +1941,8 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 	}
 
 	xip_enable(map, chip, adr);
- out:	put_chip(map, chip, adr);
+ out:	DISABLE_VPP(map);
+	put_chip(map, chip, adr);
 	mutex_unlock(&chip->mutex);
 	return ret;
 }
@@ -2086,7 +2084,8 @@ static int __xipram do_xxlock_oneblock(struct map_info *map, struct flchip *chip
 	}
 
 	xip_enable(map, chip, adr);
-out:	put_chip(map, chip, adr);
+ out:	DISABLE_VPP(map);
+	put_chip(map, chip, adr);
 	mutex_unlock(&chip->mutex);
 	return ret;
 }
@@ -2483,7 +2482,7 @@ static int cfi_intelext_suspend(struct mtd_info *mtd)
 			   allowed to. Or should we return -EAGAIN, because the upper layers
 			   ought to have already shut down anything which was using the device
 			   anyway? The latter for now. */
-			printk(KERN_NOTICE "Flash device refused suspend due to active operation (state %d)\n", chip->oldstate);
+			printk(KERN_NOTICE "Flash device refused suspend due to active operation (state %d)\n", chip->state);
 			ret = -EAGAIN;
 		case FL_PM_SUSPENDED:
 			break;
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 8d70895a58d6..d02592e6a0f0 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -59,6 +59,9 @@ static void cfi_amdstd_resume (struct mtd_info *);
 static int cfi_amdstd_reboot(struct notifier_block *, unsigned long, void *);
 static int cfi_amdstd_secsi_read (struct mtd_info *, loff_t, size_t, size_t *, u_char *);
 
+static int cfi_amdstd_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
+				  size_t *retlen, const u_char *buf);
+
 static void cfi_amdstd_destroy(struct mtd_info *);
 
 struct mtd_info *cfi_cmdset_0002(struct map_info *, int);
@@ -189,7 +192,7 @@ static void fixup_use_write_buffers(struct mtd_info *mtd)
 	struct cfi_private *cfi = map->fldrv_priv;
 	if (cfi->cfiq->BufWriteTimeoutTyp) {
 		pr_debug("Using buffer write method\n" );
-		mtd->write = cfi_amdstd_write_buffers;
+		mtd->_write = cfi_amdstd_write_buffers;
 	}
 }
 
@@ -228,8 +231,8 @@ static void fixup_convert_atmel_pri(struct mtd_info *mtd)
 static void fixup_use_secsi(struct mtd_info *mtd)
 {
 	/* Setup for chips with a secsi area */
-	mtd->read_user_prot_reg = cfi_amdstd_secsi_read;
-	mtd->read_fact_prot_reg = cfi_amdstd_secsi_read;
+	mtd->_read_user_prot_reg = cfi_amdstd_secsi_read;
+	mtd->_read_fact_prot_reg = cfi_amdstd_secsi_read;
 }
 
 static void fixup_use_erase_chip(struct mtd_info *mtd)
@@ -238,7 +241,7 @@ static void fixup_use_erase_chip(struct mtd_info *mtd)
 	struct cfi_private *cfi = map->fldrv_priv;
 	if ((cfi->cfiq->NumEraseRegions == 1) &&
 		((cfi->cfiq->EraseRegionInfo[0] & 0xffff) == 0)) {
-		mtd->erase = cfi_amdstd_erase_chip;
+		mtd->_erase = cfi_amdstd_erase_chip;
 	}
 
 }
@@ -249,8 +252,8 @@ static void fixup_use_erase_chip(struct mtd_info *mtd)
  */
 static void fixup_use_atmel_lock(struct mtd_info *mtd)
 {
-	mtd->lock = cfi_atmel_lock;
-	mtd->unlock = cfi_atmel_unlock;
+	mtd->_lock = cfi_atmel_lock;
+	mtd->_unlock = cfi_atmel_unlock;
 	mtd->flags |= MTD_POWERUP_LOCK;
 }
 
@@ -429,12 +432,12 @@ struct mtd_info *cfi_cmdset_0002(struct map_info *map, int primary)
 	mtd->type = MTD_NORFLASH;
 
 	/* Fill in the default mtd operations */
-	mtd->erase   = cfi_amdstd_erase_varsize;
-	mtd->write   = cfi_amdstd_write_words;
-	mtd->read    = cfi_amdstd_read;
-	mtd->sync    = cfi_amdstd_sync;
-	mtd->suspend = cfi_amdstd_suspend;
-	mtd->resume  = cfi_amdstd_resume;
+	mtd->_erase   = cfi_amdstd_erase_varsize;
+	mtd->_write   = cfi_amdstd_write_words;
+	mtd->_read    = cfi_amdstd_read;
+	mtd->_sync    = cfi_amdstd_sync;
+	mtd->_suspend = cfi_amdstd_suspend;
+	mtd->_resume  = cfi_amdstd_resume;
 	mtd->flags   = MTD_CAP_NORFLASH;
 	mtd->name    = map->name;
 	mtd->writesize = 1;
@@ -443,6 +446,7 @@ struct mtd_info *cfi_cmdset_0002(struct map_info *map, int primary)
 	pr_debug("MTD %s(): write buffer size %d\n", __func__,
 			mtd->writebufsize);
 
+	mtd->_panic_write = cfi_amdstd_panic_write;
 	mtd->reboot_notifier.notifier_call = cfi_amdstd_reboot;
 
 	if (cfi->cfi_mode==CFI_MODE_CFI){
@@ -770,8 +774,6 @@ static void put_chip(struct map_info *map, struct flchip *chip, unsigned long ad
 
 	case FL_READY:
 	case FL_STATUS:
-		/* We should really make set_vpp() count, rather than doing this */
-		DISABLE_VPP(map);
 		break;
 	default:
 		printk(KERN_ERR "MTD: put_chip() called with oldstate %d!!\n", chip->oldstate);
@@ -1013,13 +1015,9 @@ static int cfi_amdstd_read (struct mtd_info *mtd, loff_t from, size_t len, size_
 	int ret = 0;
 
 	/* ofs: offset within the first chip that the first read should start */
-
 	chipnum = (from >> cfi->chipshift);
 	ofs = from - (chipnum <<  cfi->chipshift);
 
-
-	*retlen = 0;
-
 	while (len) {
 		unsigned long thislen;
 
@@ -1097,16 +1095,11 @@ static int cfi_amdstd_secsi_read (struct mtd_info *mtd, loff_t from, size_t len,
 	int chipnum;
 	int ret = 0;
 
-
 	/* ofs: offset within the first chip that the first read should start */
-
 	/* 8 secsi bytes per chip */
 	chipnum=from>>3;
 	ofs=from & 7;
 
-
-	*retlen = 0;
-
 	while (len) {
 		unsigned long thislen;
 
@@ -1234,6 +1227,7 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip,
 	xip_enable(map, chip, adr);
  op_done:
 	chip->state = FL_READY;
+	DISABLE_VPP(map);
 	put_chip(map, chip, adr);
 	mutex_unlock(&chip->mutex);
 
@@ -1251,10 +1245,6 @@ static int cfi_amdstd_write_words(struct mtd_info *mtd, loff_t to, size_t len,
 	unsigned long ofs, chipstart;
 	DECLARE_WAITQUEUE(wait, current);
 
-	*retlen = 0;
-	if (!len)
-		return 0;
-
 	chipnum = to >> cfi->chipshift;
 	ofs = to  - (chipnum << cfi->chipshift);
 	chipstart = cfi->chips[chipnum].start;
@@ -1476,6 +1466,7 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 	ret = -EIO;
  op_done:
 	chip->state = FL_READY;
+	DISABLE_VPP(map);
 	put_chip(map, chip, adr);
 	mutex_unlock(&chip->mutex);
 
@@ -1493,10 +1484,6 @@ static int cfi_amdstd_write_buffers(struct mtd_info *mtd, loff_t to, size_t len,
 	int chipnum;
 	unsigned long ofs;
 
-	*retlen = 0;
-	if (!len)
-		return 0;
-
 	chipnum = to >> cfi->chipshift;
 	ofs = to  - (chipnum << cfi->chipshift);
 
@@ -1562,6 +1549,238 @@ static int cfi_amdstd_write_buffers(struct mtd_info *mtd, loff_t to, size_t len,
 	return 0;
 }
 
+/*
+ * Wait for the flash chip to become ready to write data
+ *
+ * This is only called during the panic_write() path. When panic_write()
+ * is called, the kernel is in the process of a panic, and will soon be
+ * dead. Therefore we don't take any locks, and attempt to get access
+ * to the chip as soon as possible.
+ */
+static int cfi_amdstd_panic_wait(struct map_info *map, struct flchip *chip,
+				 unsigned long adr)
+{
+	struct cfi_private *cfi = map->fldrv_priv;
+	int retries = 10;
+	int i;
+
+	/*
+	 * If the driver thinks the chip is idle, and no toggle bits
+	 * are changing, then the chip is actually idle for sure.
+	 */
+	if (chip->state == FL_READY && chip_ready(map, adr))
+		return 0;
+
+	/*
+	 * Try several times to reset the chip and then wait for it
+	 * to become idle. The upper limit of a few milliseconds of
+	 * delay isn't a big problem: the kernel is dying anyway. It
+	 * is more important to save the messages.
+	 */
+	while (retries > 0) {
+		const unsigned long timeo = (HZ / 1000) + 1;
+
+		/* send the reset command */
+		map_write(map, CMD(0xF0), chip->start);
+
+		/* wait for the chip to become ready */
+		for (i = 0; i < jiffies_to_usecs(timeo); i++) {
+			if (chip_ready(map, adr))
+				return 0;
+
+			udelay(1);
+		}
+	}
+
+	/* the chip never became ready */
+	return -EBUSY;
+}
+
+/*
+ * Write out one word of data to a single flash chip during a kernel panic
+ *
+ * This is only called during the panic_write() path. When panic_write()
+ * is called, the kernel is in the process of a panic, and will soon be
+ * dead. Therefore we don't take any locks, and attempt to get access
+ * to the chip as soon as possible.
+ *
+ * The implementation of this routine is intentionally similar to
+ * do_write_oneword(), in order to ease code maintenance.
+ */
+static int do_panic_write_oneword(struct map_info *map, struct flchip *chip,
+				  unsigned long adr, map_word datum)
+{
+	const unsigned long uWriteTimeout = (HZ / 1000) + 1;
+	struct cfi_private *cfi = map->fldrv_priv;
+	int retry_cnt = 0;
+	map_word oldd;
+	int ret = 0;
+	int i;
+
+	adr += chip->start;
+
+	ret = cfi_amdstd_panic_wait(map, chip, adr);
+	if (ret)
+		return ret;
+
+	pr_debug("MTD %s(): PANIC WRITE 0x%.8lx(0x%.8lx)\n",
+			__func__, adr, datum.x[0]);
+
+	/*
+	 * Check for a NOP for the case when the datum to write is already
+	 * present - it saves time and works around buggy chips that corrupt
+	 * data at other locations when 0xff is written to a location that
+	 * already contains 0xff.
+	 */
+	oldd = map_read(map, adr);
+	if (map_word_equal(map, oldd, datum)) {
+		pr_debug("MTD %s(): NOP\n", __func__);
+		goto op_done;
+	}
+
+	ENABLE_VPP(map);
+
+retry:
+	cfi_send_gen_cmd(0xAA, cfi->addr_unlock1, chip->start, map, cfi, cfi->device_type, NULL);
+	cfi_send_gen_cmd(0x55, cfi->addr_unlock2, chip->start, map, cfi, cfi->device_type, NULL);
+	cfi_send_gen_cmd(0xA0, cfi->addr_unlock1, chip->start, map, cfi, cfi->device_type, NULL);
+	map_write(map, datum, adr);
+
+	for (i = 0; i < jiffies_to_usecs(uWriteTimeout); i++) {
+		if (chip_ready(map, adr))
+			break;
+
+		udelay(1);
+	}
+
+	if (!chip_good(map, adr, datum)) {
+		/* reset on all failures. */
+		map_write(map, CMD(0xF0), chip->start);
+		/* FIXME - should have reset delay before continuing */
+
+		if (++retry_cnt <= MAX_WORD_RETRIES)
+			goto retry;
+
+		ret = -EIO;
+	}
+
+op_done:
+	DISABLE_VPP(map);
+	return ret;
+}
+
+/*
+ * Write out some data during a kernel panic
+ *
+ * This is used by the mtdoops driver to save the dying messages from a
+ * kernel which has panic'd.
+ *
+ * This routine ignores all of the locking used throughout the rest of the
+ * driver, in order to ensure that the data gets written out no matter what
+ * state this driver (and the flash chip itself) was in when the kernel crashed.
+ *
+ * The implementation of this routine is intentionally similar to
+ * cfi_amdstd_write_words(), in order to ease code maintenance.
+ */
+static int cfi_amdstd_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
+				  size_t *retlen, const u_char *buf)
+{
+	struct map_info *map = mtd->priv;
+	struct cfi_private *cfi = map->fldrv_priv;
+	unsigned long ofs, chipstart;
+	int ret = 0;
+	int chipnum;
+
+	chipnum = to >> cfi->chipshift;
+	ofs = to - (chipnum << cfi->chipshift);
+	chipstart = cfi->chips[chipnum].start;
+
+	/* If it's not bus aligned, do the first byte write */
+	if (ofs & (map_bankwidth(map) - 1)) {
+		unsigned long bus_ofs = ofs & ~(map_bankwidth(map) - 1);
+		int i = ofs - bus_ofs;
+		int n = 0;
+		map_word tmp_buf;
+
+		ret = cfi_amdstd_panic_wait(map, &cfi->chips[chipnum], bus_ofs);
+		if (ret)
+			return ret;
+
+		/* Load 'tmp_buf' with old contents of flash */
+		tmp_buf = map_read(map, bus_ofs + chipstart);
+
+		/* Number of bytes to copy from buffer */
+		n = min_t(int, len, map_bankwidth(map) - i);
+
+		tmp_buf = map_word_load_partial(map, tmp_buf, buf, i, n);
+
+		ret = do_panic_write_oneword(map, &cfi->chips[chipnum],
+					     bus_ofs, tmp_buf);
+		if (ret)
+			return ret;
+
+		ofs += n;
+		buf += n;
+		(*retlen) += n;
+		len -= n;
+
+		if (ofs >> cfi->chipshift) {
+			chipnum++;
+			ofs = 0;
+			if (chipnum == cfi->numchips)
+				return 0;
+		}
+	}
+
+	/* We are now aligned, write as much as possible */
+	while (len >= map_bankwidth(map)) {
+		map_word datum;
+
+		datum = map_word_load(map, buf);
+
+		ret = do_panic_write_oneword(map, &cfi->chips[chipnum],
+					     ofs, datum);
+		if (ret)
+			return ret;
+
+		ofs += map_bankwidth(map);
+		buf += map_bankwidth(map);
+		(*retlen) += map_bankwidth(map);
+		len -= map_bankwidth(map);
+
+		if (ofs >> cfi->chipshift) {
+			chipnum++;
+			ofs = 0;
+			if (chipnum == cfi->numchips)
+				return 0;
+
+			chipstart = cfi->chips[chipnum].start;
+		}
+	}
+
+	/* Write the trailing bytes if any */
+	if (len & (map_bankwidth(map) - 1)) {
+		map_word tmp_buf;
+
+		ret = cfi_amdstd_panic_wait(map, &cfi->chips[chipnum], ofs);
+		if (ret)
+			return ret;
+
+		tmp_buf = map_read(map, ofs + chipstart);
+
+		tmp_buf = map_word_load_partial(map, tmp_buf, buf, 0, len);
+
+		ret = do_panic_write_oneword(map, &cfi->chips[chipnum],
+					     ofs, tmp_buf);
+		if (ret)
+			return ret;
+
+		(*retlen) += len;
+	}
+
+	return 0;
+}
+
 
 /*
  * Handle devices with one erase region, that only implement
@@ -1649,6 +1868,7 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
 
 	chip->state = FL_READY;
 	xip_enable(map, chip, adr);
+	DISABLE_VPP(map);
 	put_chip(map, chip, adr);
 	mutex_unlock(&chip->mutex);
 
@@ -1739,6 +1959,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 	}
 
 	chip->state = FL_READY;
+	DISABLE_VPP(map);
 	put_chip(map, chip, adr);
 	mutex_unlock(&chip->mutex);
 	return ret;
diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c
index 85e80180b65b..096993f9711e 100644
--- a/drivers/mtd/chips/cfi_cmdset_0020.c
+++ b/drivers/mtd/chips/cfi_cmdset_0020.c
@@ -228,15 +228,15 @@ static struct mtd_info *cfi_staa_setup(struct map_info *map)
 		}
 
 	/* Also select the correct geometry setup too */
-	mtd->erase = cfi_staa_erase_varsize;
-	mtd->read = cfi_staa_read;
-        mtd->write = cfi_staa_write_buffers;
-	mtd->writev = cfi_staa_writev;
-	mtd->sync = cfi_staa_sync;
-	mtd->lock = cfi_staa_lock;
-	mtd->unlock = cfi_staa_unlock;
-	mtd->suspend = cfi_staa_suspend;
-	mtd->resume = cfi_staa_resume;
+	mtd->_erase = cfi_staa_erase_varsize;
+	mtd->_read = cfi_staa_read;
+	mtd->_write = cfi_staa_write_buffers;
+	mtd->_writev = cfi_staa_writev;
+	mtd->_sync = cfi_staa_sync;
+	mtd->_lock = cfi_staa_lock;
+	mtd->_unlock = cfi_staa_unlock;
+	mtd->_suspend = cfi_staa_suspend;
+	mtd->_resume = cfi_staa_resume;
 	mtd->flags = MTD_CAP_NORFLASH & ~MTD_BIT_WRITEABLE;
 	mtd->writesize = 8; /* FIXME: Should be 0 for STMicro flashes w/out ECC */
 	mtd->writebufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize;
@@ -394,8 +394,6 @@ static int cfi_staa_read (struct mtd_info *mtd, loff_t from, size_t len, size_t
 	chipnum = (from >> cfi->chipshift);
 	ofs = from - (chipnum <<  cfi->chipshift);
 
-	*retlen = 0;
-
 	while (len) {
 		unsigned long thislen;
 
@@ -617,10 +615,6 @@ static int cfi_staa_write_buffers (struct mtd_info *mtd, loff_t to,
 	int chipnum;
 	unsigned long ofs;
 
-	*retlen = 0;
-	if (!len)
-		return 0;
-
 	chipnum = to >> cfi->chipshift;
 	ofs = to  - (chipnum << cfi->chipshift);
 
@@ -904,12 +898,6 @@ static int cfi_staa_erase_varsize(struct mtd_info *mtd,
 	int i, first;
 	struct mtd_erase_region_info *regions = mtd->eraseregions;
 
-	if (instr->addr > mtd->size)
-		return -EINVAL;
-
-	if ((instr->len + instr->addr) > mtd->size)
-		return -EINVAL;
-
 	/* Check that both start and end of the requested erase are
 	 * aligned with the erasesize at the appropriate addresses.
 	 */
@@ -1155,9 +1143,6 @@ static int cfi_staa_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	if (len & (mtd->erasesize -1))
 		return -EINVAL;
 
-	if ((len + ofs) > mtd->size)
-		return -EINVAL;
-
 	chipnum = ofs >> cfi->chipshift;
 	adr = ofs - (chipnum << cfi->chipshift);
 
diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c
index 8e464054a631..f992418f40a8 100644
--- a/drivers/mtd/chips/cfi_util.c
+++ b/drivers/mtd/chips/cfi_util.c
@@ -173,12 +173,6 @@ int cfi_varsize_frob(struct mtd_info *mtd, varsize_frob_t frob,
 	int i, first;
 	struct mtd_erase_region_info *regions = mtd->eraseregions;
 
-	if (ofs > mtd->size)
-		return -EINVAL;
-
-	if ((len + ofs) > mtd->size)
-		return -EINVAL;
-
 	/* Check that both start and end of the requested erase are
 	 * aligned with the erasesize at the appropriate addresses.
 	 */
diff --git a/drivers/mtd/chips/fwh_lock.h b/drivers/mtd/chips/fwh_lock.h
index 89c6595454a5..800b0e853e86 100644
--- a/drivers/mtd/chips/fwh_lock.h
+++ b/drivers/mtd/chips/fwh_lock.h
@@ -101,7 +101,7 @@ static void fixup_use_fwh_lock(struct mtd_info *mtd)
 {
 	printk(KERN_NOTICE "using fwh lock/unlock method\n");
 	/* Setup for the chips with the fwh lock method */
-	mtd->lock   = fwh_lock_varsize;
-	mtd->unlock = fwh_unlock_varsize;
+	mtd->_lock   = fwh_lock_varsize;
+	mtd->_unlock = fwh_unlock_varsize;
 }
 #endif /* FWH_LOCK_H */
diff --git a/drivers/mtd/chips/map_absent.c b/drivers/mtd/chips/map_absent.c
index f2b872946871..f7a5bca92aef 100644
--- a/drivers/mtd/chips/map_absent.c
+++ b/drivers/mtd/chips/map_absent.c
@@ -55,10 +55,10 @@ static struct mtd_info *map_absent_probe(struct map_info *map)
 	mtd->name 	= map->name;
 	mtd->type 	= MTD_ABSENT;
 	mtd->size 	= map->size;
-	mtd->erase 	= map_absent_erase;
-	mtd->read 	= map_absent_read;
-	mtd->write 	= map_absent_write;
-	mtd->sync 	= map_absent_sync;
+	mtd->_erase 	= map_absent_erase;
+	mtd->_read 	= map_absent_read;
+	mtd->_write 	= map_absent_write;
+	mtd->_sync 	= map_absent_sync;
 	mtd->flags 	= 0;
 	mtd->erasesize  = PAGE_SIZE;
 	mtd->writesize  = 1;
@@ -70,13 +70,11 @@ static struct mtd_info *map_absent_probe(struct map_info *map)
 
 static int map_absent_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf)
 {
-	*retlen = 0;
 	return -ENODEV;
 }
 
 static int map_absent_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf)
 {
-	*retlen = 0;
 	return -ENODEV;
 }
 
diff --git a/drivers/mtd/chips/map_ram.c b/drivers/mtd/chips/map_ram.c
index 67640ccb2d41..991c2a1c05d3 100644
--- a/drivers/mtd/chips/map_ram.c
+++ b/drivers/mtd/chips/map_ram.c
@@ -64,11 +64,11 @@ static struct mtd_info *map_ram_probe(struct map_info *map)
 	mtd->name = map->name;
 	mtd->type = MTD_RAM;
 	mtd->size = map->size;
-	mtd->erase = mapram_erase;
-	mtd->get_unmapped_area = mapram_unmapped_area;
-	mtd->read = mapram_read;
-	mtd->write = mapram_write;
-	mtd->sync = mapram_nop;
+	mtd->_erase = mapram_erase;
+	mtd->_get_unmapped_area = mapram_unmapped_area;
+	mtd->_read = mapram_read;
+	mtd->_write = mapram_write;
+	mtd->_sync = mapram_nop;
 	mtd->flags = MTD_CAP_RAM;
 	mtd->writesize = 1;
 
@@ -122,14 +122,10 @@ static int mapram_erase (struct mtd_info *mtd, struct erase_info *instr)
 	unsigned long i;
 
 	allff = map_word_ff(map);
-
 	for (i=0; i<instr->len; i += map_bankwidth(map))
 		map_write(map, allff, instr->addr + i);
-
 	instr->state = MTD_ERASE_DONE;
-
 	mtd_erase_callback(instr);
-
 	return 0;
 }
 
diff --git a/drivers/mtd/chips/map_rom.c b/drivers/mtd/chips/map_rom.c
index 593f73d480d2..47a43cf7e5c6 100644
--- a/drivers/mtd/chips/map_rom.c
+++ b/drivers/mtd/chips/map_rom.c
@@ -41,11 +41,11 @@ static struct mtd_info *map_rom_probe(struct map_info *map)
 	mtd->name = map->name;
 	mtd->type = MTD_ROM;
 	mtd->size = map->size;
-	mtd->get_unmapped_area = maprom_unmapped_area;
-	mtd->read = maprom_read;
-	mtd->write = maprom_write;
-	mtd->sync = maprom_nop;
-	mtd->erase = maprom_erase;
+	mtd->_get_unmapped_area = maprom_unmapped_area;
+	mtd->_read = maprom_read;
+	mtd->_write = maprom_write;
+	mtd->_sync = maprom_nop;
+	mtd->_erase = maprom_erase;
 	mtd->flags = MTD_CAP_ROM;
 	mtd->erasesize = map->size;
 	mtd->writesize = 1;
@@ -85,8 +85,7 @@ static void maprom_nop(struct mtd_info *mtd)
 
 static int maprom_write (struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf)
 {
-	printk(KERN_NOTICE "maprom_write called\n");
-	return -EIO;
+	return -EROFS;
 }
 
 static int maprom_erase (struct mtd_info *mtd, struct erase_info *info)
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 37b05c3f2792..4cdb2af7bf44 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -1,5 +1,6 @@
 menu "Self-contained MTD device drivers"
 	depends on MTD!=n
+	depends on HAS_IOMEM
 
 config MTD_PMC551
 	tristate "Ramix PMC551 PCI Mezzanine RAM card support"
@@ -102,6 +103,13 @@ config M25PXX_USE_FAST_READ
 	help
 	  This option enables FAST_READ access supported by ST M25Pxx.
 
+config MTD_SPEAR_SMI
+	tristate "SPEAR MTD NOR Support through SMI controller"
+	depends on PLAT_SPEAR
+	default y
+	help
+	  This enable SNOR support on SPEAR platforms using SMI controller
+
 config MTD_SST25L
 	tristate "Support SST25L (non JEDEC) SPI Flash chips"
 	depends on SPI_MASTER
diff --git a/drivers/mtd/devices/Makefile b/drivers/mtd/devices/Makefile
index 56c7cd462f11..a4dd1d822b6c 100644
--- a/drivers/mtd/devices/Makefile
+++ b/drivers/mtd/devices/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_MTD_LART)		+= lart.o
 obj-$(CONFIG_MTD_BLOCK2MTD)	+= block2mtd.o
 obj-$(CONFIG_MTD_DATAFLASH)	+= mtd_dataflash.o
 obj-$(CONFIG_MTD_M25P80)	+= m25p80.o
+obj-$(CONFIG_MTD_SPEAR_SMI)	+= spear_smi.o
 obj-$(CONFIG_MTD_SST25L)	+= sst25l.o
 
 CFLAGS_docg3.o			+= -I$(src)
\ No newline at end of file
diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index e7e46d1e7463..a4a80b742e65 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -104,14 +104,6 @@ static int block2mtd_read(struct mtd_info *mtd, loff_t from, size_t len,
 	int offset = from & (PAGE_SIZE-1);
 	int cpylen;
 
-	if (from > mtd->size)
-		return -EINVAL;
-	if (from + len > mtd->size)
-		len = mtd->size - from;
-
-	if (retlen)
-		*retlen = 0;
-
 	while (len) {
 		if ((offset + len) > PAGE_SIZE)
 			cpylen = PAGE_SIZE - offset;	// multiple pages
@@ -148,8 +140,6 @@ static int _block2mtd_write(struct block2mtd_dev *dev, const u_char *buf,
 	int offset = to & ~PAGE_MASK;	// page offset
 	int cpylen;
 
-	if (retlen)
-		*retlen = 0;
 	while (len) {
 		if ((offset+len) > PAGE_SIZE)
 			cpylen = PAGE_SIZE - offset;	// multiple pages
@@ -188,13 +178,6 @@ static int block2mtd_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct block2mtd_dev *dev = mtd->priv;
 	int err;
 
-	if (!len)
-		return 0;
-	if (to >= mtd->size)
-		return -ENOSPC;
-	if (to + len > mtd->size)
-		len = mtd->size - to;
-
 	mutex_lock(&dev->write_mutex);
 	err = _block2mtd_write(dev, buf, to, len, retlen);
 	mutex_unlock(&dev->write_mutex);
@@ -283,13 +266,14 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size)
 	dev->mtd.size = dev->blkdev->bd_inode->i_size & PAGE_MASK;
 	dev->mtd.erasesize = erase_size;
 	dev->mtd.writesize = 1;
+	dev->mtd.writebufsize = PAGE_SIZE;
 	dev->mtd.type = MTD_RAM;
 	dev->mtd.flags = MTD_CAP_RAM;
-	dev->mtd.erase = block2mtd_erase;
-	dev->mtd.write = block2mtd_write;
-	dev->mtd.writev = mtd_writev;
-	dev->mtd.sync = block2mtd_sync;
-	dev->mtd.read = block2mtd_read;
+	dev->mtd._erase = block2mtd_erase;
+	dev->mtd._write = block2mtd_write;
+	dev->mtd._writev = mtd_writev;
+	dev->mtd._sync = block2mtd_sync;
+	dev->mtd._read = block2mtd_read;
 	dev->mtd.priv = dev;
 	dev->mtd.owner = THIS_MODULE;
 
diff --git a/drivers/mtd/devices/doc2000.c b/drivers/mtd/devices/doc2000.c
index b1cdf6479019..a4eb8b5b85ec 100644
--- a/drivers/mtd/devices/doc2000.c
+++ b/drivers/mtd/devices/doc2000.c
@@ -562,14 +562,15 @@ void DoC2k_init(struct mtd_info *mtd)
 
 	mtd->type = MTD_NANDFLASH;
 	mtd->flags = MTD_CAP_NANDFLASH;
-	mtd->writesize = 512;
+	mtd->writebufsize = mtd->writesize = 512;
 	mtd->oobsize = 16;
+	mtd->ecc_strength = 2;
 	mtd->owner = THIS_MODULE;
-	mtd->erase = doc_erase;
-	mtd->read = doc_read;
-	mtd->write = doc_write;
-	mtd->read_oob = doc_read_oob;
-	mtd->write_oob = doc_write_oob;
+	mtd->_erase = doc_erase;
+	mtd->_read = doc_read;
+	mtd->_write = doc_write;
+	mtd->_read_oob = doc_read_oob;
+	mtd->_write_oob = doc_write_oob;
 	this->curfloor = -1;
 	this->curchip = -1;
 	mutex_init(&this->lock);
@@ -602,13 +603,7 @@ static int doc_read(struct mtd_info *mtd, loff_t from, size_t len,
 	int i, len256 = 0, ret=0;
 	size_t left = len;
 
-	/* Don't allow read past end of device */
-	if (from >= this->totlen)
-		return -EINVAL;
-
 	mutex_lock(&this->lock);
-
-	*retlen = 0;
 	while (left) {
 		len = left;
 
@@ -748,13 +743,7 @@ static int doc_write(struct mtd_info *mtd, loff_t to, size_t len,
 	size_t left = len;
 	int status;
 
-	/* Don't allow write past end of device */
-	if (to >= this->totlen)
-		return -EINVAL;
-
 	mutex_lock(&this->lock);
-
-	*retlen = 0;
 	while (left) {
 		len = left;
 
diff --git a/drivers/mtd/devices/doc2001.c b/drivers/mtd/devices/doc2001.c
index 7543b98f46c4..f6927955dab0 100644
--- a/drivers/mtd/devices/doc2001.c
+++ b/drivers/mtd/devices/doc2001.c
@@ -346,14 +346,15 @@ void DoCMil_init(struct mtd_info *mtd)
 
 	/* FIXME: erase size is not always 8KiB */
 	mtd->erasesize = 0x2000;
-	mtd->writesize = 512;
+	mtd->writebufsize = mtd->writesize = 512;
 	mtd->oobsize = 16;
+	mtd->ecc_strength = 2;
 	mtd->owner = THIS_MODULE;
-	mtd->erase = doc_erase;
-	mtd->read = doc_read;
-	mtd->write = doc_write;
-	mtd->read_oob = doc_read_oob;
-	mtd->write_oob = doc_write_oob;
+	mtd->_erase = doc_erase;
+	mtd->_read = doc_read;
+	mtd->_write = doc_write;
+	mtd->_read_oob = doc_read_oob;
+	mtd->_write_oob = doc_write_oob;
 	this->curfloor = -1;
 	this->curchip = -1;
 
@@ -383,10 +384,6 @@ static int doc_read (struct mtd_info *mtd, loff_t from, size_t len,
 	void __iomem *docptr = this->virtadr;
 	struct Nand *mychip = &this->chips[from >> (this->chipshift)];
 
-	/* Don't allow read past end of device */
-	if (from >= this->totlen)
-		return -EINVAL;
-
 	/* Don't allow a single read to cross a 512-byte block boundary */
 	if (from + len > ((from | 0x1ff) + 1))
 		len = ((from | 0x1ff) + 1) - from;
@@ -494,10 +491,6 @@ static int doc_write (struct mtd_info *mtd, loff_t to, size_t len,
 	void __iomem *docptr = this->virtadr;
 	struct Nand *mychip = &this->chips[to >> (this->chipshift)];
 
-	/* Don't allow write past end of device */
-	if (to >= this->totlen)
-		return -EINVAL;
-
 #if 0
 	/* Don't allow a single write to cross a 512-byte block boundary */
 	if (to + len > ( (to | 0x1ff) + 1))
@@ -599,7 +592,6 @@ static int doc_write (struct mtd_info *mtd, loff_t to, size_t len,
 		printk("Error programming flash\n");
 		/* Error in programming
 		   FIXME: implement Bad Block Replacement (in nftl.c ??) */
-		*retlen = 0;
 		ret = -EIO;
 	}
 	dummy = ReadDOC(docptr, LastDataRead);
diff --git a/drivers/mtd/devices/doc2001plus.c b/drivers/mtd/devices/doc2001plus.c
index 177510d0e7ee..04eb2e4aa50f 100644
--- a/drivers/mtd/devices/doc2001plus.c
+++ b/drivers/mtd/devices/doc2001plus.c
@@ -467,14 +467,15 @@ void DoCMilPlus_init(struct mtd_info *mtd)
 
 	mtd->type = MTD_NANDFLASH;
 	mtd->flags = MTD_CAP_NANDFLASH;
-	mtd->writesize = 512;
+	mtd->writebufsize = mtd->writesize = 512;
 	mtd->oobsize = 16;
+	mtd->ecc_strength = 2;
 	mtd->owner = THIS_MODULE;
-	mtd->erase = doc_erase;
-	mtd->read = doc_read;
-	mtd->write = doc_write;
-	mtd->read_oob = doc_read_oob;
-	mtd->write_oob = doc_write_oob;
+	mtd->_erase = doc_erase;
+	mtd->_read = doc_read;
+	mtd->_write = doc_write;
+	mtd->_read_oob = doc_read_oob;
+	mtd->_write_oob = doc_write_oob;
 	this->curfloor = -1;
 	this->curchip = -1;
 
@@ -581,10 +582,6 @@ static int doc_read(struct mtd_info *mtd, loff_t from, size_t len,
 	void __iomem * docptr = this->virtadr;
 	struct Nand *mychip = &this->chips[from >> (this->chipshift)];
 
-	/* Don't allow read past end of device */
-	if (from >= this->totlen)
-		return -EINVAL;
-
 	/* Don't allow a single read to cross a 512-byte block boundary */
 	if (from + len > ((from | 0x1ff) + 1))
 		len = ((from | 0x1ff) + 1) - from;
@@ -700,10 +697,6 @@ static int doc_write(struct mtd_info *mtd, loff_t to, size_t len,
 	void __iomem * docptr = this->virtadr;
 	struct Nand *mychip = &this->chips[to >> (this->chipshift)];
 
-	/* Don't allow write past end of device */
-	if (to >= this->totlen)
-		return -EINVAL;
-
 	/* Don't allow writes which aren't exactly one block (512 bytes) */
 	if ((to & 0x1ff) || (len != 0x200))
 		return -EINVAL;
@@ -800,7 +793,6 @@ static int doc_write(struct mtd_info *mtd, loff_t to, size_t len,
 		printk("MTD: Error 0x%x programming at 0x%x\n", dummy, (int)to);
 		/* Error in programming
 		   FIXME: implement Bad Block Replacement (in nftl.c ??) */
-		*retlen = 0;
 		ret = -EIO;
 	}
 	dummy = ReadDOC(docptr, Mplus_LastDataRead);
diff --git a/drivers/mtd/devices/docg3.c b/drivers/mtd/devices/docg3.c
index ad11ef0a81f4..8272c02668d6 100644
--- a/drivers/mtd/devices/docg3.c
+++ b/drivers/mtd/devices/docg3.c
@@ -80,14 +80,9 @@ static struct nand_ecclayout docg3_oobinfo = {
 	.oobavail = 8,
 };
 
-/**
- * struct docg3_bch - BCH engine
- */
-static struct bch_control *docg3_bch;
-
 static inline u8 doc_readb(struct docg3 *docg3, u16 reg)
 {
-	u8 val = readb(docg3->base + reg);
+	u8 val = readb(docg3->cascade->base + reg);
 
 	trace_docg3_io(0, 8, reg, (int)val);
 	return val;
@@ -95,7 +90,7 @@ static inline u8 doc_readb(struct docg3 *docg3, u16 reg)
 
 static inline u16 doc_readw(struct docg3 *docg3, u16 reg)
 {
-	u16 val = readw(docg3->base + reg);
+	u16 val = readw(docg3->cascade->base + reg);
 
 	trace_docg3_io(0, 16, reg, (int)val);
 	return val;
@@ -103,13 +98,13 @@ static inline u16 doc_readw(struct docg3 *docg3, u16 reg)
 
 static inline void doc_writeb(struct docg3 *docg3, u8 val, u16 reg)
 {
-	writeb(val, docg3->base + reg);
+	writeb(val, docg3->cascade->base + reg);
 	trace_docg3_io(1, 8, reg, val);
 }
 
 static inline void doc_writew(struct docg3 *docg3, u16 val, u16 reg)
 {
-	writew(val, docg3->base + reg);
+	writew(val, docg3->cascade->base + reg);
 	trace_docg3_io(1, 16, reg, val);
 }
 
@@ -643,7 +638,8 @@ static int doc_ecc_bch_fix_data(struct docg3 *docg3, void *buf, u8 *hwecc)
 
 	for (i = 0; i < DOC_ECC_BCH_SIZE; i++)
 		ecc[i] = bitrev8(hwecc[i]);
-	numerrs = decode_bch(docg3_bch, NULL, DOC_ECC_BCH_COVERED_BYTES,
+	numerrs = decode_bch(docg3->cascade->bch, NULL,
+			     DOC_ECC_BCH_COVERED_BYTES,
 			     NULL, ecc, NULL, errorpos);
 	BUG_ON(numerrs == -EINVAL);
 	if (numerrs < 0)
@@ -734,7 +730,7 @@ err:
  * doc_read_page_getbytes - Reads bytes from a prepared page
  * @docg3: the device
  * @len: the number of bytes to be read (must be a multiple of 4)
- * @buf: the buffer to be filled in
+ * @buf: the buffer to be filled in (or NULL is forget bytes)
  * @first: 1 if first time read, DOC_READADDRESS should be set
  *
  */
@@ -849,7 +845,7 @@ static int doc_read_oob(struct mtd_info *mtd, loff_t from,
 			struct mtd_oob_ops *ops)
 {
 	struct docg3 *docg3 = mtd->priv;
-	int block0, block1, page, ret, ofs = 0;
+	int block0, block1, page, ret, skip, ofs = 0;
 	u8 *oobbuf = ops->oobbuf;
 	u8 *buf = ops->datbuf;
 	size_t len, ooblen, nbdata, nboob;
@@ -869,34 +865,36 @@ static int doc_read_oob(struct mtd_info *mtd, loff_t from,
 
 	doc_dbg("doc_read_oob(from=%lld, mode=%d, data=(%p:%zu), oob=(%p:%zu))\n",
 		from, ops->mode, buf, len, oobbuf, ooblen);
-	if ((len % DOC_LAYOUT_PAGE_SIZE) || (ooblen % DOC_LAYOUT_OOB_SIZE) ||
-	    (from % DOC_LAYOUT_PAGE_SIZE))
+	if (ooblen % DOC_LAYOUT_OOB_SIZE)
 		return -EINVAL;
 
-	ret = -EINVAL;
-	calc_block_sector(from + len, &block0, &block1, &page, &ofs,
-			  docg3->reliable);
-	if (block1 > docg3->max_block)
-		goto err;
+	if (from + len > mtd->size)
+		return -EINVAL;
 
 	ops->oobretlen = 0;
 	ops->retlen = 0;
 	ret = 0;
+	skip = from % DOC_LAYOUT_PAGE_SIZE;
+	mutex_lock(&docg3->cascade->lock);
 	while (!ret && (len > 0 || ooblen > 0)) {
-		calc_block_sector(from, &block0, &block1, &page, &ofs,
+		calc_block_sector(from - skip, &block0, &block1, &page, &ofs,
 			docg3->reliable);
-		nbdata = min_t(size_t, len, (size_t)DOC_LAYOUT_PAGE_SIZE);
+		nbdata = min_t(size_t, len, DOC_LAYOUT_PAGE_SIZE - skip);
 		nboob = min_t(size_t, ooblen, (size_t)DOC_LAYOUT_OOB_SIZE);
 		ret = doc_read_page_prepare(docg3, block0, block1, page, ofs);
 		if (ret < 0)
-			goto err;
+			goto out;
 		ret = doc_read_page_ecc_init(docg3, DOC_ECC_BCH_TOTAL_BYTES);
 		if (ret < 0)
 			goto err_in_read;
-		ret = doc_read_page_getbytes(docg3, nbdata, buf, 1);
+		ret = doc_read_page_getbytes(docg3, skip, NULL, 1);
+		if (ret < skip)
+			goto err_in_read;
+		ret = doc_read_page_getbytes(docg3, nbdata, buf, 0);
 		if (ret < nbdata)
 			goto err_in_read;
-		doc_read_page_getbytes(docg3, DOC_LAYOUT_PAGE_SIZE - nbdata,
+		doc_read_page_getbytes(docg3,
+				       DOC_LAYOUT_PAGE_SIZE - nbdata - skip,
 				       NULL, 0);
 		ret = doc_read_page_getbytes(docg3, nboob, oobbuf, 0);
 		if (ret < nboob)
@@ -950,13 +948,15 @@ static int doc_read_oob(struct mtd_info *mtd, loff_t from,
 		len -= nbdata;
 		ooblen -= nboob;
 		from += DOC_LAYOUT_PAGE_SIZE;
+		skip = 0;
 	}
 
+out:
+	mutex_unlock(&docg3->cascade->lock);
 	return ret;
 err_in_read:
 	doc_read_page_finish(docg3);
-err:
-	return ret;
+	goto out;
 }
 
 /**
@@ -1114,10 +1114,10 @@ static int doc_get_op_status(struct docg3 *docg3)
  */
 static int doc_write_erase_wait_status(struct docg3 *docg3)
 {
-	int status, ret = 0;
+	int i, status, ret = 0;
 
-	if (!doc_is_ready(docg3))
-		usleep_range(3000, 3000);
+	for (i = 0; !doc_is_ready(docg3) && i < 5; i++)
+		msleep(20);
 	if (!doc_is_ready(docg3)) {
 		doc_dbg("Timeout reached and the chip is still not ready\n");
 		ret = -EAGAIN;
@@ -1196,18 +1196,19 @@ static int doc_erase(struct mtd_info *mtd, struct erase_info *info)
 	int block0, block1, page, ret, ofs = 0;
 
 	doc_dbg("doc_erase(from=%lld, len=%lld\n", info->addr, info->len);
-	doc_set_device_id(docg3, docg3->device_id);
 
 	info->state = MTD_ERASE_PENDING;
 	calc_block_sector(info->addr + info->len, &block0, &block1, &page,
 			  &ofs, docg3->reliable);
 	ret = -EINVAL;
-	if (block1 > docg3->max_block || page || ofs)
+	if (info->addr + info->len > mtd->size || page || ofs)
 		goto reset_err;
 
 	ret = 0;
 	calc_block_sector(info->addr, &block0, &block1, &page, &ofs,
 			  docg3->reliable);
+	mutex_lock(&docg3->cascade->lock);
+	doc_set_device_id(docg3, docg3->device_id);
 	doc_set_reliable_mode(docg3);
 	for (len = info->len; !ret && len > 0; len -= mtd->erasesize) {
 		info->state = MTD_ERASING;
@@ -1215,6 +1216,7 @@ static int doc_erase(struct mtd_info *mtd, struct erase_info *info)
 		block0 += 2;
 		block1 += 2;
 	}
+	mutex_unlock(&docg3->cascade->lock);
 
 	if (ret)
 		goto reset_err;
@@ -1401,7 +1403,7 @@ static int doc_write_oob(struct mtd_info *mtd, loff_t ofs,
 			 struct mtd_oob_ops *ops)
 {
 	struct docg3 *docg3 = mtd->priv;
-	int block0, block1, page, ret, pofs = 0, autoecc, oobdelta;
+	int ret, autoecc, oobdelta;
 	u8 *oobbuf = ops->oobbuf;
 	u8 *buf = ops->datbuf;
 	size_t len, ooblen;
@@ -1438,12 +1440,8 @@ static int doc_write_oob(struct mtd_info *mtd, loff_t ofs,
 	if (len && ooblen &&
 	    (len / DOC_LAYOUT_PAGE_SIZE) != (ooblen / oobdelta))
 		return -EINVAL;
-
-	ret = -EINVAL;
-	calc_block_sector(ofs + len, &block0, &block1, &page, &pofs,
-			  docg3->reliable);
-	if (block1 > docg3->max_block)
-		goto err;
+	if (ofs + len > mtd->size)
+		return -EINVAL;
 
 	ops->oobretlen = 0;
 	ops->retlen = 0;
@@ -1457,6 +1455,7 @@ static int doc_write_oob(struct mtd_info *mtd, loff_t ofs,
 	if (autoecc < 0)
 		return autoecc;
 
+	mutex_lock(&docg3->cascade->lock);
 	while (!ret && len > 0) {
 		memset(oob, 0, sizeof(oob));
 		if (ofs == docg3->oob_write_ofs)
@@ -1477,8 +1476,9 @@ static int doc_write_oob(struct mtd_info *mtd, loff_t ofs,
 		}
 		ops->retlen += DOC_LAYOUT_PAGE_SIZE;
 	}
-err:
+
 	doc_set_device_id(docg3, 0);
+	mutex_unlock(&docg3->cascade->lock);
 	return ret;
 }
 
@@ -1535,9 +1535,11 @@ static ssize_t dps0_is_key_locked(struct device *dev,
 	struct docg3 *docg3 = sysfs_dev2docg3(dev, attr);
 	int dps0;
 
+	mutex_lock(&docg3->cascade->lock);
 	doc_set_device_id(docg3, docg3->device_id);
 	dps0 = doc_register_readb(docg3, DOC_DPS0_STATUS);
 	doc_set_device_id(docg3, 0);
+	mutex_unlock(&docg3->cascade->lock);
 
 	return sprintf(buf, "%d\n", !(dps0 & DOC_DPS_KEY_OK));
 }
@@ -1548,9 +1550,11 @@ static ssize_t dps1_is_key_locked(struct device *dev,
 	struct docg3 *docg3 = sysfs_dev2docg3(dev, attr);
 	int dps1;
 
+	mutex_lock(&docg3->cascade->lock);
 	doc_set_device_id(docg3, docg3->device_id);
 	dps1 = doc_register_readb(docg3, DOC_DPS1_STATUS);
 	doc_set_device_id(docg3, 0);
+	mutex_unlock(&docg3->cascade->lock);
 
 	return sprintf(buf, "%d\n", !(dps1 & DOC_DPS_KEY_OK));
 }
@@ -1565,10 +1569,12 @@ static ssize_t dps0_insert_key(struct device *dev,
 	if (count != DOC_LAYOUT_DPS_KEY_LENGTH)
 		return -EINVAL;
 
+	mutex_lock(&docg3->cascade->lock);
 	doc_set_device_id(docg3, docg3->device_id);
 	for (i = 0; i < DOC_LAYOUT_DPS_KEY_LENGTH; i++)
 		doc_writeb(docg3, buf[i], DOC_DPS0_KEY);
 	doc_set_device_id(docg3, 0);
+	mutex_unlock(&docg3->cascade->lock);
 	return count;
 }
 
@@ -1582,10 +1588,12 @@ static ssize_t dps1_insert_key(struct device *dev,
 	if (count != DOC_LAYOUT_DPS_KEY_LENGTH)
 		return -EINVAL;
 
+	mutex_lock(&docg3->cascade->lock);
 	doc_set_device_id(docg3, docg3->device_id);
 	for (i = 0; i < DOC_LAYOUT_DPS_KEY_LENGTH; i++)
 		doc_writeb(docg3, buf[i], DOC_DPS1_KEY);
 	doc_set_device_id(docg3, 0);
+	mutex_unlock(&docg3->cascade->lock);
 	return count;
 }
 
@@ -1601,13 +1609,13 @@ static struct device_attribute doc_sys_attrs[DOC_MAX_NBFLOORS][4] = {
 };
 
 static int doc_register_sysfs(struct platform_device *pdev,
-			      struct mtd_info **floors)
+			      struct docg3_cascade *cascade)
 {
 	int ret = 0, floor, i = 0;
 	struct device *dev = &pdev->dev;
 
-	for (floor = 0; !ret && floor < DOC_MAX_NBFLOORS && floors[floor];
-	     floor++)
+	for (floor = 0; !ret && floor < DOC_MAX_NBFLOORS &&
+		     cascade->floors[floor]; floor++)
 		for (i = 0; !ret && i < 4; i++)
 			ret = device_create_file(dev, &doc_sys_attrs[floor][i]);
 	if (!ret)
@@ -1621,12 +1629,12 @@ static int doc_register_sysfs(struct platform_device *pdev,
 }
 
 static void doc_unregister_sysfs(struct platform_device *pdev,
-				 struct mtd_info **floors)
+				 struct docg3_cascade *cascade)
 {
 	struct device *dev = &pdev->dev;
 	int floor, i;
 
-	for (floor = 0; floor < DOC_MAX_NBFLOORS && floors[floor];
+	for (floor = 0; floor < DOC_MAX_NBFLOORS && cascade->floors[floor];
 	     floor++)
 		for (i = 0; i < 4; i++)
 			device_remove_file(dev, &doc_sys_attrs[floor][i]);
@@ -1640,7 +1648,11 @@ static int dbg_flashctrl_show(struct seq_file *s, void *p)
 	struct docg3 *docg3 = (struct docg3 *)s->private;
 
 	int pos = 0;
-	u8 fctrl = doc_register_readb(docg3, DOC_FLASHCONTROL);
+	u8 fctrl;
+
+	mutex_lock(&docg3->cascade->lock);
+	fctrl = doc_register_readb(docg3, DOC_FLASHCONTROL);
+	mutex_unlock(&docg3->cascade->lock);
 
 	pos += seq_printf(s,
 		 "FlashControl : 0x%02x (%s,CE# %s,%s,%s,flash %s)\n",
@@ -1658,9 +1670,12 @@ static int dbg_asicmode_show(struct seq_file *s, void *p)
 {
 	struct docg3 *docg3 = (struct docg3 *)s->private;
 
-	int pos = 0;
-	int pctrl = doc_register_readb(docg3, DOC_ASICMODE);
-	int mode = pctrl & 0x03;
+	int pos = 0, pctrl, mode;
+
+	mutex_lock(&docg3->cascade->lock);
+	pctrl = doc_register_readb(docg3, DOC_ASICMODE);
+	mode = pctrl & 0x03;
+	mutex_unlock(&docg3->cascade->lock);
 
 	pos += seq_printf(s,
 			 "%04x : RAM_WE=%d,RSTIN_RESET=%d,BDETCT_RESET=%d,WRITE_ENABLE=%d,POWERDOWN=%d,MODE=%d%d (",
@@ -1692,7 +1707,11 @@ static int dbg_device_id_show(struct seq_file *s, void *p)
 {
 	struct docg3 *docg3 = (struct docg3 *)s->private;
 	int pos = 0;
-	int id = doc_register_readb(docg3, DOC_DEVICESELECT);
+	int id;
+
+	mutex_lock(&docg3->cascade->lock);
+	id = doc_register_readb(docg3, DOC_DEVICESELECT);
+	mutex_unlock(&docg3->cascade->lock);
 
 	pos += seq_printf(s, "DeviceId = %d\n", id);
 	return pos;
@@ -1705,6 +1724,7 @@ static int dbg_protection_show(struct seq_file *s, void *p)
 	int pos = 0;
 	int protect, dps0, dps0_low, dps0_high, dps1, dps1_low, dps1_high;
 
+	mutex_lock(&docg3->cascade->lock);
 	protect = doc_register_readb(docg3, DOC_PROTECTION);
 	dps0 = doc_register_readb(docg3, DOC_DPS0_STATUS);
 	dps0_low = doc_register_readw(docg3, DOC_DPS0_ADDRLOW);
@@ -1712,6 +1732,7 @@ static int dbg_protection_show(struct seq_file *s, void *p)
 	dps1 = doc_register_readb(docg3, DOC_DPS1_STATUS);
 	dps1_low = doc_register_readw(docg3, DOC_DPS1_ADDRLOW);
 	dps1_high = doc_register_readw(docg3, DOC_DPS1_ADDRHIGH);
+	mutex_unlock(&docg3->cascade->lock);
 
 	pos += seq_printf(s, "Protection = 0x%02x (",
 			 protect);
@@ -1804,7 +1825,7 @@ static void __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
 
 	switch (chip_id) {
 	case DOC_CHIPID_G3:
-		mtd->name = kasprintf(GFP_KERNEL, "DiskOnChip G3 floor %d",
+		mtd->name = kasprintf(GFP_KERNEL, "docg3.%d",
 				      docg3->device_id);
 		docg3->max_block = 2047;
 		break;
@@ -1817,16 +1838,17 @@ static void __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
 	mtd->erasesize = DOC_LAYOUT_BLOCK_SIZE * DOC_LAYOUT_NBPLANES;
 	if (docg3->reliable == 2)
 		mtd->erasesize /= 2;
-	mtd->writesize = DOC_LAYOUT_PAGE_SIZE;
+	mtd->writebufsize = mtd->writesize = DOC_LAYOUT_PAGE_SIZE;
 	mtd->oobsize = DOC_LAYOUT_OOB_SIZE;
 	mtd->owner = THIS_MODULE;
-	mtd->erase = doc_erase;
-	mtd->read = doc_read;
-	mtd->write = doc_write;
-	mtd->read_oob = doc_read_oob;
-	mtd->write_oob = doc_write_oob;
-	mtd->block_isbad = doc_block_isbad;
+	mtd->_erase = doc_erase;
+	mtd->_read = doc_read;
+	mtd->_write = doc_write;
+	mtd->_read_oob = doc_read_oob;
+	mtd->_write_oob = doc_write_oob;
+	mtd->_block_isbad = doc_block_isbad;
 	mtd->ecclayout = &docg3_oobinfo;
+	mtd->ecc_strength = DOC_ECC_BCH_T;
 }
 
 /**
@@ -1834,6 +1856,7 @@ static void __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
  * @base: the io space where the device is probed
  * @floor: the floor of the probed device
  * @dev: the device
+ * @cascade: the cascade of chips this devices will belong to
  *
  * Checks whether a device at the specified IO range, and floor is available.
  *
@@ -1841,8 +1864,8 @@ static void __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
  * if a memory allocation failed. If floor 0 is checked, a reset of the ASIC is
  * launched.
  */
-static struct mtd_info *doc_probe_device(void __iomem *base, int floor,
-					 struct device *dev)
+static struct mtd_info * __init
+doc_probe_device(struct docg3_cascade *cascade, int floor, struct device *dev)
 {
 	int ret, bbt_nbpages;
 	u16 chip_id, chip_id_inv;
@@ -1865,7 +1888,7 @@ static struct mtd_info *doc_probe_device(void __iomem *base, int floor,
 
 	docg3->dev = dev;
 	docg3->device_id = floor;
-	docg3->base = base;
+	docg3->cascade = cascade;
 	doc_set_device_id(docg3, docg3->device_id);
 	if (!floor)
 		doc_set_asic_mode(docg3, DOC_ASICMODE_RESET);
@@ -1882,7 +1905,7 @@ static struct mtd_info *doc_probe_device(void __iomem *base, int floor,
 	switch (chip_id) {
 	case DOC_CHIPID_G3:
 		doc_info("Found a G3 DiskOnChip at addr %p, floor %d\n",
-			 base, floor);
+			 docg3->cascade->base, floor);
 		break;
 	default:
 		doc_err("Chip id %04x is not a DiskOnChip G3 chip\n", chip_id);
@@ -1927,10 +1950,12 @@ static void doc_release_device(struct mtd_info *mtd)
 static int docg3_resume(struct platform_device *pdev)
 {
 	int i;
+	struct docg3_cascade *cascade;
 	struct mtd_info **docg3_floors, *mtd;
 	struct docg3 *docg3;
 
-	docg3_floors = platform_get_drvdata(pdev);
+	cascade = platform_get_drvdata(pdev);
+	docg3_floors = cascade->floors;
 	mtd = docg3_floors[0];
 	docg3 = mtd->priv;
 
@@ -1952,11 +1977,13 @@ static int docg3_resume(struct platform_device *pdev)
 static int docg3_suspend(struct platform_device *pdev, pm_message_t state)
 {
 	int floor, i;
+	struct docg3_cascade *cascade;
 	struct mtd_info **docg3_floors, *mtd;
 	struct docg3 *docg3;
 	u8 ctrl, pwr_down;
 
-	docg3_floors = platform_get_drvdata(pdev);
+	cascade = platform_get_drvdata(pdev);
+	docg3_floors = cascade->floors;
 	for (floor = 0; floor < DOC_MAX_NBFLOORS; floor++) {
 		mtd = docg3_floors[floor];
 		if (!mtd)
@@ -2006,7 +2033,7 @@ static int __init docg3_probe(struct platform_device *pdev)
 	struct resource *ress;
 	void __iomem *base;
 	int ret, floor, found = 0;
-	struct mtd_info **docg3_floors;
+	struct docg3_cascade *cascade;
 
 	ret = -ENXIO;
 	ress = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2017,17 +2044,19 @@ static int __init docg3_probe(struct platform_device *pdev)
 	base = ioremap(ress->start, DOC_IOSPACE_SIZE);
 
 	ret = -ENOMEM;
-	docg3_floors = kzalloc(sizeof(*docg3_floors) * DOC_MAX_NBFLOORS,
-			       GFP_KERNEL);
-	if (!docg3_floors)
+	cascade = kzalloc(sizeof(*cascade) * DOC_MAX_NBFLOORS,
+			  GFP_KERNEL);
+	if (!cascade)
 		goto nomem1;
-	docg3_bch = init_bch(DOC_ECC_BCH_M, DOC_ECC_BCH_T,
+	cascade->base = base;
+	mutex_init(&cascade->lock);
+	cascade->bch = init_bch(DOC_ECC_BCH_M, DOC_ECC_BCH_T,
 			     DOC_ECC_BCH_PRIMPOLY);
-	if (!docg3_bch)
+	if (!cascade->bch)
 		goto nomem2;
 
 	for (floor = 0; floor < DOC_MAX_NBFLOORS; floor++) {
-		mtd = doc_probe_device(base, floor, dev);
+		mtd = doc_probe_device(cascade, floor, dev);
 		if (IS_ERR(mtd)) {
 			ret = PTR_ERR(mtd);
 			goto err_probe;
@@ -2038,7 +2067,7 @@ static int __init docg3_probe(struct platform_device *pdev)
 			else
 				continue;
 		}
-		docg3_floors[floor] = mtd;
+		cascade->floors[floor] = mtd;
 		ret = mtd_device_parse_register(mtd, part_probes, NULL, NULL,
 						0);
 		if (ret)
@@ -2046,26 +2075,26 @@ static int __init docg3_probe(struct platform_device *pdev)
 		found++;
 	}
 
-	ret = doc_register_sysfs(pdev, docg3_floors);
+	ret = doc_register_sysfs(pdev, cascade);
 	if (ret)
 		goto err_probe;
 	if (!found)
 		goto notfound;
 
-	platform_set_drvdata(pdev, docg3_floors);
-	doc_dbg_register(docg3_floors[0]->priv);
+	platform_set_drvdata(pdev, cascade);
+	doc_dbg_register(cascade->floors[0]->priv);
 	return 0;
 
 notfound:
 	ret = -ENODEV;
 	dev_info(dev, "No supported DiskOnChip found\n");
 err_probe:
-	free_bch(docg3_bch);
+	kfree(cascade->bch);
 	for (floor = 0; floor < DOC_MAX_NBFLOORS; floor++)
-		if (docg3_floors[floor])
-			doc_release_device(docg3_floors[floor]);
+		if (cascade->floors[floor])
+			doc_release_device(cascade->floors[floor]);
 nomem2:
-	kfree(docg3_floors);
+	kfree(cascade);
 nomem1:
 	iounmap(base);
 noress:
@@ -2080,19 +2109,19 @@ noress:
  */
 static int __exit docg3_release(struct platform_device *pdev)
 {
-	struct mtd_info **docg3_floors = platform_get_drvdata(pdev);
-	struct docg3 *docg3 = docg3_floors[0]->priv;
-	void __iomem *base = docg3->base;
+	struct docg3_cascade *cascade = platform_get_drvdata(pdev);
+	struct docg3 *docg3 = cascade->floors[0]->priv;
+	void __iomem *base = cascade->base;
 	int floor;
 
-	doc_unregister_sysfs(pdev, docg3_floors);
+	doc_unregister_sysfs(pdev, cascade);
 	doc_dbg_unregister(docg3);
 	for (floor = 0; floor < DOC_MAX_NBFLOORS; floor++)
-		if (docg3_floors[floor])
-			doc_release_device(docg3_floors[floor]);
+		if (cascade->floors[floor])
+			doc_release_device(cascade->floors[floor]);
 
-	kfree(docg3_floors);
-	free_bch(docg3_bch);
+	free_bch(docg3->cascade->bch);
+	kfree(cascade);
 	iounmap(base);
 	return 0;
 }
diff --git a/drivers/mtd/devices/docg3.h b/drivers/mtd/devices/docg3.h
index db0da436b493..19fb93f96a3a 100644
--- a/drivers/mtd/devices/docg3.h
+++ b/drivers/mtd/devices/docg3.h
@@ -22,6 +22,8 @@
 #ifndef _MTD_DOCG3_H
 #define _MTD_DOCG3_H
 
+#include <linux/mtd/mtd.h>
+
 /*
  * Flash memory areas :
  *   - 0x0000 .. 0x07ff : IPL
@@ -267,9 +269,23 @@
 #define DOC_LAYOUT_DPS_KEY_LENGTH	8
 
 /**
+ * struct docg3_cascade - Cascade of 1 to 4 docg3 chips
+ * @floors: floors (ie. one physical docg3 chip is one floor)
+ * @base: IO space to access all chips in the cascade
+ * @bch: the BCH correcting control structure
+ * @lock: lock to protect docg3 IO space from concurrent accesses
+ */
+struct docg3_cascade {
+	struct mtd_info *floors[DOC_MAX_NBFLOORS];
+	void __iomem *base;
+	struct bch_control *bch;
+	struct mutex lock;
+};
+
+/**
  * struct docg3 - DiskOnChip driver private data
  * @dev: the device currently under control
- * @base: mapped IO space
+ * @cascade: the cascade this device belongs to
  * @device_id: number of the cascaded DoCG3 device (0, 1, 2 or 3)
  * @if_cfg: if true, reads are on 16bits, else reads are on 8bits
 
@@ -287,7 +303,7 @@
  */
 struct docg3 {
 	struct device *dev;
-	void __iomem *base;
+	struct docg3_cascade *cascade;
 	unsigned int device_id:4;
 	unsigned int if_cfg:1;
 	unsigned int reliable:2;
diff --git a/drivers/mtd/devices/lart.c b/drivers/mtd/devices/lart.c
index 3a11ea628e58..82bd00af5cc3 100644
--- a/drivers/mtd/devices/lart.c
+++ b/drivers/mtd/devices/lart.c
@@ -367,9 +367,6 @@ static int flash_erase (struct mtd_info *mtd,struct erase_info *instr)
    printk (KERN_DEBUG "%s(addr = 0x%.8x, len = %d)\n", __func__, instr->addr, instr->len);
 #endif
 
-   /* sanity checks */
-   if (instr->addr + instr->len > mtd->size) return (-EINVAL);
-
    /*
 	* check that both start and end of the requested erase are
 	* aligned with the erasesize at the appropriate addresses.
@@ -440,10 +437,6 @@ static int flash_read (struct mtd_info *mtd,loff_t from,size_t len,size_t *retle
    printk (KERN_DEBUG "%s(from = 0x%.8x, len = %d)\n", __func__, (__u32)from, len);
 #endif
 
-   /* sanity checks */
-   if (!len) return (0);
-   if (from + len > mtd->size) return (-EINVAL);
-
    /* we always read len bytes */
    *retlen = len;
 
@@ -522,11 +515,8 @@ static int flash_write (struct mtd_info *mtd,loff_t to,size_t len,size_t *retlen
    printk (KERN_DEBUG "%s(to = 0x%.8x, len = %d)\n", __func__, (__u32)to, len);
 #endif
 
-   *retlen = 0;
-
    /* sanity checks */
    if (!len) return (0);
-   if (to + len > mtd->size) return (-EINVAL);
 
    /* first, we write a 0xFF.... padded byte until we reach a dword boundary */
    if (to & (BUSWIDTH - 1))
@@ -630,14 +620,15 @@ static int __init lart_flash_init (void)
    mtd.name = module_name;
    mtd.type = MTD_NORFLASH;
    mtd.writesize = 1;
+   mtd.writebufsize = 4;
    mtd.flags = MTD_CAP_NORFLASH;
    mtd.size = FLASH_BLOCKSIZE_PARAM * FLASH_NUMBLOCKS_16m_PARAM + FLASH_BLOCKSIZE_MAIN * FLASH_NUMBLOCKS_16m_MAIN;
    mtd.erasesize = FLASH_BLOCKSIZE_MAIN;
    mtd.numeraseregions = ARRAY_SIZE(erase_regions);
    mtd.eraseregions = erase_regions;
-   mtd.erase = flash_erase;
-   mtd.read = flash_read;
-   mtd.write = flash_write;
+   mtd._erase = flash_erase;
+   mtd._read = flash_read;
+   mtd._write = flash_write;
    mtd.owner = THIS_MODULE;
 
 #ifdef LART_DEBUG
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 7c60dddbefc0..1924d247c1cb 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -288,9 +288,6 @@ static int m25p80_erase(struct mtd_info *mtd, struct erase_info *instr)
 			__func__, (long long)instr->addr,
 			(long long)instr->len);
 
-	/* sanity checks */
-	if (instr->addr + instr->len > flash->mtd.size)
-		return -EINVAL;
 	div_u64_rem(instr->len, mtd->erasesize, &rem);
 	if (rem)
 		return -EINVAL;
@@ -349,13 +346,6 @@ static int m25p80_read(struct mtd_info *mtd, loff_t from, size_t len,
 	pr_debug("%s: %s from 0x%08x, len %zd\n", dev_name(&flash->spi->dev),
 			__func__, (u32)from, len);
 
-	/* sanity checks */
-	if (!len)
-		return 0;
-
-	if (from + len > flash->mtd.size)
-		return -EINVAL;
-
 	spi_message_init(&m);
 	memset(t, 0, (sizeof t));
 
@@ -371,9 +361,6 @@ static int m25p80_read(struct mtd_info *mtd, loff_t from, size_t len,
 	t[1].len = len;
 	spi_message_add_tail(&t[1], &m);
 
-	/* Byte count starts at zero. */
-	*retlen = 0;
-
 	mutex_lock(&flash->lock);
 
 	/* Wait till previous write/erase is done. */
@@ -417,15 +404,6 @@ static int m25p80_write(struct mtd_info *mtd, loff_t to, size_t len,
 	pr_debug("%s: %s to 0x%08x, len %zd\n", dev_name(&flash->spi->dev),
 			__func__, (u32)to, len);
 
-	*retlen = 0;
-
-	/* sanity checks */
-	if (!len)
-		return(0);
-
-	if (to + len > flash->mtd.size)
-		return -EINVAL;
-
 	spi_message_init(&m);
 	memset(t, 0, (sizeof t));
 
@@ -509,15 +487,6 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 	pr_debug("%s: %s to 0x%08x, len %zd\n", dev_name(&flash->spi->dev),
 			__func__, (u32)to, len);
 
-	*retlen = 0;
-
-	/* sanity checks */
-	if (!len)
-		return 0;
-
-	if (to + len > flash->mtd.size)
-		return -EINVAL;
-
 	spi_message_init(&m);
 	memset(t, 0, (sizeof t));
 
@@ -908,14 +877,14 @@ static int __devinit m25p_probe(struct spi_device *spi)
 	flash->mtd.writesize = 1;
 	flash->mtd.flags = MTD_CAP_NORFLASH;
 	flash->mtd.size = info->sector_size * info->n_sectors;
-	flash->mtd.erase = m25p80_erase;
-	flash->mtd.read = m25p80_read;
+	flash->mtd._erase = m25p80_erase;
+	flash->mtd._read = m25p80_read;
 
 	/* sst flash chips use AAI word program */
 	if (JEDEC_MFR(info->jedec_id) == CFI_MFR_SST)
-		flash->mtd.write = sst_write;
+		flash->mtd._write = sst_write;
 	else
-		flash->mtd.write = m25p80_write;
+		flash->mtd._write = m25p80_write;
 
 	/* prefer "small sector" erase if possible */
 	if (info->flags & SECT_4K) {
@@ -932,6 +901,7 @@ static int __devinit m25p_probe(struct spi_device *spi)
 	ppdata.of_node = spi->dev.of_node;
 	flash->mtd.dev.parent = &spi->dev;
 	flash->page_size = info->page_size;
+	flash->mtd.writebufsize = flash->page_size;
 
 	if (info->addr_width)
 		flash->addr_width = info->addr_width;
@@ -1004,21 +974,7 @@ static struct spi_driver m25p80_driver = {
 	 */
 };
 
-
-static int __init m25p80_init(void)
-{
-	return spi_register_driver(&m25p80_driver);
-}
-
-
-static void __exit m25p80_exit(void)
-{
-	spi_unregister_driver(&m25p80_driver);
-}
-
-
-module_init(m25p80_init);
-module_exit(m25p80_exit);
+module_spi_driver(m25p80_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Mike Lavender");
diff --git a/drivers/mtd/devices/ms02-nv.c b/drivers/mtd/devices/ms02-nv.c
index 8423fb6d4f26..182849d39c61 100644
--- a/drivers/mtd/devices/ms02-nv.c
+++ b/drivers/mtd/devices/ms02-nv.c
@@ -59,12 +59,8 @@ static int ms02nv_read(struct mtd_info *mtd, loff_t from,
 {
 	struct ms02nv_private *mp = mtd->priv;
 
-	if (from + len > mtd->size)
-		return -EINVAL;
-
 	memcpy(buf, mp->uaddr + from, len);
 	*retlen = len;
-
 	return 0;
 }
 
@@ -73,12 +69,8 @@ static int ms02nv_write(struct mtd_info *mtd, loff_t to,
 {
 	struct ms02nv_private *mp = mtd->priv;
 
-	if (to + len > mtd->size)
-		return -EINVAL;
-
 	memcpy(mp->uaddr + to, buf, len);
 	*retlen = len;
-
 	return 0;
 }
 
@@ -215,8 +207,8 @@ static int __init ms02nv_init_one(ulong addr)
 	mtd->size = fixsize;
 	mtd->name = (char *)ms02nv_name;
 	mtd->owner = THIS_MODULE;
-	mtd->read = ms02nv_read;
-	mtd->write = ms02nv_write;
+	mtd->_read = ms02nv_read;
+	mtd->_write = ms02nv_write;
 	mtd->writesize = 1;
 
 	ret = -EIO;
diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c
index 236057ead0d2..928fb0e6d73a 100644
--- a/drivers/mtd/devices/mtd_dataflash.c
+++ b/drivers/mtd/devices/mtd_dataflash.c
@@ -164,9 +164,6 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr)
 	      dev_name(&spi->dev), (long long)instr->addr,
 	      (long long)instr->len);
 
-	/* Sanity checks */
-	if (instr->addr + instr->len > mtd->size)
-		return -EINVAL;
 	div_u64_rem(instr->len, priv->page_size, &rem);
 	if (rem)
 		return -EINVAL;
@@ -252,14 +249,6 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len,
 	pr_debug("%s: read 0x%x..0x%x\n", dev_name(&priv->spi->dev),
 			(unsigned)from, (unsigned)(from + len));
 
-	*retlen = 0;
-
-	/* Sanity checks */
-	if (!len)
-		return 0;
-	if (from + len > mtd->size)
-		return -EINVAL;
-
 	/* Calculate flash page/byte address */
 	addr = (((unsigned)from / priv->page_size) << priv->page_offset)
 		+ ((unsigned)from % priv->page_size);
@@ -328,14 +317,6 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 	pr_debug("%s: write 0x%x..0x%x\n",
 		dev_name(&spi->dev), (unsigned)to, (unsigned)(to + len));
 
-	*retlen = 0;
-
-	/* Sanity checks */
-	if (!len)
-		return 0;
-	if ((to + len) > mtd->size)
-		return -EINVAL;
-
 	spi_message_init(&msg);
 
 	x[0].tx_buf = command = priv->command;
@@ -490,8 +471,6 @@ static ssize_t otp_read(struct spi_device *spi, unsigned base,
 
 	if ((off + len) > 64)
 		len = 64 - off;
-	if (len == 0)
-		return len;
 
 	spi_message_init(&m);
 
@@ -611,16 +590,16 @@ static int dataflash_write_user_otp(struct mtd_info *mtd,
 
 static char *otp_setup(struct mtd_info *device, char revision)
 {
-	device->get_fact_prot_info = dataflash_get_otp_info;
-	device->read_fact_prot_reg = dataflash_read_fact_otp;
-	device->get_user_prot_info = dataflash_get_otp_info;
-	device->read_user_prot_reg = dataflash_read_user_otp;
+	device->_get_fact_prot_info = dataflash_get_otp_info;
+	device->_read_fact_prot_reg = dataflash_read_fact_otp;
+	device->_get_user_prot_info = dataflash_get_otp_info;
+	device->_read_user_prot_reg = dataflash_read_user_otp;
 
 	/* rev c parts (at45db321c and at45db1281 only!) use a
 	 * different write procedure; not (yet?) implemented.
 	 */
 	if (revision > 'c')
-		device->write_user_prot_reg = dataflash_write_user_otp;
+		device->_write_user_prot_reg = dataflash_write_user_otp;
 
 	return ", OTP";
 }
@@ -672,9 +651,9 @@ add_dataflash_otp(struct spi_device *spi, char *name,
 	device->owner = THIS_MODULE;
 	device->type = MTD_DATAFLASH;
 	device->flags = MTD_WRITEABLE;
-	device->erase = dataflash_erase;
-	device->read = dataflash_read;
-	device->write = dataflash_write;
+	device->_erase = dataflash_erase;
+	device->_read = dataflash_read;
+	device->_write = dataflash_write;
 	device->priv = priv;
 
 	device->dev.parent = &spi->dev;
@@ -946,18 +925,7 @@ static struct spi_driver dataflash_driver = {
 	/* FIXME:  investigate suspend and resume... */
 };
 
-static int __init dataflash_init(void)
-{
-	return spi_register_driver(&dataflash_driver);
-}
-module_init(dataflash_init);
-
-static void __exit dataflash_exit(void)
-{
-	spi_unregister_driver(&dataflash_driver);
-}
-module_exit(dataflash_exit);
-
+module_spi_driver(dataflash_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Andrew Victor, David Brownell");
diff --git a/drivers/mtd/devices/mtdram.c b/drivers/mtd/devices/mtdram.c
index 2562689ba6b4..ec59d65897fb 100644
--- a/drivers/mtd/devices/mtdram.c
+++ b/drivers/mtd/devices/mtdram.c
@@ -34,34 +34,23 @@ static struct mtd_info *mtd_info;
 
 static int ram_erase(struct mtd_info *mtd, struct erase_info *instr)
 {
-	if (instr->addr + instr->len > mtd->size)
-		return -EINVAL;
-
 	memset((char *)mtd->priv + instr->addr, 0xff, instr->len);
-
 	instr->state = MTD_ERASE_DONE;
 	mtd_erase_callback(instr);
-
 	return 0;
 }
 
 static int ram_point(struct mtd_info *mtd, loff_t from, size_t len,
 		size_t *retlen, void **virt, resource_size_t *phys)
 {
-	if (from + len > mtd->size)
-		return -EINVAL;
-
-	/* can we return a physical address with this driver? */
-	if (phys)
-		return -EINVAL;
-
 	*virt = mtd->priv + from;
 	*retlen = len;
 	return 0;
 }
 
-static void ram_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
+static int ram_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
+	return 0;
 }
 
 /*
@@ -80,11 +69,7 @@ static unsigned long ram_get_unmapped_area(struct mtd_info *mtd,
 static int ram_read(struct mtd_info *mtd, loff_t from, size_t len,
 		size_t *retlen, u_char *buf)
 {
-	if (from + len > mtd->size)
-		return -EINVAL;
-
 	memcpy(buf, mtd->priv + from, len);
-
 	*retlen = len;
 	return 0;
 }
@@ -92,11 +77,7 @@ static int ram_read(struct mtd_info *mtd, loff_t from, size_t len,
 static int ram_write(struct mtd_info *mtd, loff_t to, size_t len,
 		size_t *retlen, const u_char *buf)
 {
-	if (to + len > mtd->size)
-		return -EINVAL;
-
 	memcpy((char *)mtd->priv + to, buf, len);
-
 	*retlen = len;
 	return 0;
 }
@@ -126,12 +107,12 @@ int mtdram_init_device(struct mtd_info *mtd, void *mapped_address,
 	mtd->priv = mapped_address;
 
 	mtd->owner = THIS_MODULE;
-	mtd->erase = ram_erase;
-	mtd->point = ram_point;
-	mtd->unpoint = ram_unpoint;
-	mtd->get_unmapped_area = ram_get_unmapped_area;
-	mtd->read = ram_read;
-	mtd->write = ram_write;
+	mtd->_erase = ram_erase;
+	mtd->_point = ram_point;
+	mtd->_unpoint = ram_unpoint;
+	mtd->_get_unmapped_area = ram_get_unmapped_area;
+	mtd->_read = ram_read;
+	mtd->_write = ram_write;
 
 	if (mtd_device_register(mtd, NULL, 0))
 		return -EIO;
diff --git a/drivers/mtd/devices/phram.c b/drivers/mtd/devices/phram.c
index 23423bd00b06..67823de68db6 100644
--- a/drivers/mtd/devices/phram.c
+++ b/drivers/mtd/devices/phram.c
@@ -33,45 +33,33 @@ struct phram_mtd_list {
 
 static LIST_HEAD(phram_list);
 
-
 static int phram_erase(struct mtd_info *mtd, struct erase_info *instr)
 {
 	u_char *start = mtd->priv;
 
-	if (instr->addr + instr->len > mtd->size)
-		return -EINVAL;
-
 	memset(start + instr->addr, 0xff, instr->len);
 
-	/* This'll catch a few races. Free the thing before returning :)
+	/*
+	 * This'll catch a few races. Free the thing before returning :)
 	 * I don't feel at all ashamed. This kind of thing is possible anyway
 	 * with flash, but unlikely.
 	 */
-
 	instr->state = MTD_ERASE_DONE;
-
 	mtd_erase_callback(instr);
-
 	return 0;
 }
 
 static int phram_point(struct mtd_info *mtd, loff_t from, size_t len,
 		size_t *retlen, void **virt, resource_size_t *phys)
 {
-	if (from + len > mtd->size)
-		return -EINVAL;
-
-	/* can we return a physical address with this driver? */
-	if (phys)
-		return -EINVAL;
-
 	*virt = mtd->priv + from;
 	*retlen = len;
 	return 0;
 }
 
-static void phram_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
+static int phram_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
+	return 0;
 }
 
 static int phram_read(struct mtd_info *mtd, loff_t from, size_t len,
@@ -79,14 +67,7 @@ static int phram_read(struct mtd_info *mtd, loff_t from, size_t len,
 {
 	u_char *start = mtd->priv;
 
-	if (from >= mtd->size)
-		return -EINVAL;
-
-	if (len > mtd->size - from)
-		len = mtd->size - from;
-
 	memcpy(buf, start + from, len);
-
 	*retlen = len;
 	return 0;
 }
@@ -96,20 +77,11 @@ static int phram_write(struct mtd_info *mtd, loff_t to, size_t len,
 {
 	u_char *start = mtd->priv;
 
-	if (to >= mtd->size)
-		return -EINVAL;
-
-	if (len > mtd->size - to)
-		len = mtd->size - to;
-
 	memcpy(start + to, buf, len);
-
 	*retlen = len;
 	return 0;
 }
 
-
-
 static void unregister_devices(void)
 {
 	struct phram_mtd_list *this, *safe;
@@ -142,11 +114,11 @@ static int register_device(char *name, unsigned long start, unsigned long len)
 	new->mtd.name = name;
 	new->mtd.size = len;
 	new->mtd.flags = MTD_CAP_RAM;
-        new->mtd.erase = phram_erase;
-	new->mtd.point = phram_point;
-	new->mtd.unpoint = phram_unpoint;
-	new->mtd.read = phram_read;
-	new->mtd.write = phram_write;
+	new->mtd._erase = phram_erase;
+	new->mtd._point = phram_point;
+	new->mtd._unpoint = phram_unpoint;
+	new->mtd._read = phram_read;
+	new->mtd._write = phram_write;
 	new->mtd.owner = THIS_MODULE;
 	new->mtd.type = MTD_RAM;
 	new->mtd.erasesize = PAGE_SIZE;
@@ -233,7 +205,17 @@ static inline void kill_final_newline(char *str)
 	return 1;		\
 } while (0)
 
-static int phram_setup(const char *val, struct kernel_param *kp)
+/*
+ * This shall contain the module parameter if any. It is of the form:
+ * - phram=<device>,<address>,<size> for module case
+ * - phram.phram=<device>,<address>,<size> for built-in case
+ * We leave 64 bytes for the device name, 12 for the address and 12 for the
+ * size.
+ * Example: phram.phram=rootfs,0xa0000000,512Mi
+ */
+static __initdata char phram_paramline[64+12+12];
+
+static int __init phram_setup(const char *val)
 {
 	char buf[64+12+12], *str = buf;
 	char *token[3];
@@ -282,12 +264,28 @@ static int phram_setup(const char *val, struct kernel_param *kp)
 	return ret;
 }
 
-module_param_call(phram, phram_setup, NULL, NULL, 000);
+static int __init phram_param_call(const char *val, struct kernel_param *kp)
+{
+	/*
+	 * This function is always called before 'init_phram()', whether
+	 * built-in or module.
+	 */
+	if (strlen(val) >= sizeof(phram_paramline))
+		return -ENOSPC;
+	strcpy(phram_paramline, val);
+
+	return 0;
+}
+
+module_param_call(phram, phram_param_call, NULL, NULL, 000);
 MODULE_PARM_DESC(phram, "Memory region to map. \"phram=<name>,<start>,<length>\"");
 
 
 static int __init init_phram(void)
 {
+	if (phram_paramline[0])
+		return phram_setup(phram_paramline);
+
 	return 0;
 }
 
diff --git a/drivers/mtd/devices/pmc551.c b/drivers/mtd/devices/pmc551.c
index ecff765579dd..0c51b988e1f8 100644
--- a/drivers/mtd/devices/pmc551.c
+++ b/drivers/mtd/devices/pmc551.c
@@ -93,14 +93,49 @@
 #include <linux/fs.h>
 #include <linux/ioctl.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <linux/pci.h>
-
 #include <linux/mtd/mtd.h>
-#include <linux/mtd/pmc551.h>
+
+#define PMC551_VERSION \
+	"Ramix PMC551 PCI Mezzanine Ram Driver. (C) 1999,2000 Nortel Networks.\n"
+
+#define PCI_VENDOR_ID_V3_SEMI 0x11b0
+#define PCI_DEVICE_ID_V3_SEMI_V370PDC 0x0200
+
+#define PMC551_PCI_MEM_MAP0 0x50
+#define PMC551_PCI_MEM_MAP1 0x54
+#define PMC551_PCI_MEM_MAP_MAP_ADDR_MASK 0x3ff00000
+#define PMC551_PCI_MEM_MAP_APERTURE_MASK 0x000000f0
+#define PMC551_PCI_MEM_MAP_REG_EN 0x00000002
+#define PMC551_PCI_MEM_MAP_ENABLE 0x00000001
+
+#define PMC551_SDRAM_MA  0x60
+#define PMC551_SDRAM_CMD 0x62
+#define PMC551_DRAM_CFG  0x64
+#define PMC551_SYS_CTRL_REG 0x78
+
+#define PMC551_DRAM_BLK0 0x68
+#define PMC551_DRAM_BLK1 0x6c
+#define PMC551_DRAM_BLK2 0x70
+#define PMC551_DRAM_BLK3 0x74
+#define PMC551_DRAM_BLK_GET_SIZE(x) (524288 << ((x >> 4) & 0x0f))
+#define PMC551_DRAM_BLK_SET_COL_MUX(x, v) (((x) & ~0x00007000) | (((v) & 0x7) << 12))
+#define PMC551_DRAM_BLK_SET_ROW_MUX(x, v) (((x) & ~0x00000f00) | (((v) & 0xf) << 8))
+
+struct mypriv {
+	struct pci_dev *dev;
+	u_char *start;
+	u32 base_map0;
+	u32 curr_map0;
+	u32 asize;
+	struct mtd_info *nextpmc551;
+};
 
 static struct mtd_info *pmc551list;
 
+static int pmc551_point(struct mtd_info *mtd, loff_t from, size_t len,
+			size_t *retlen, void **virt, resource_size_t *phys);
+
 static int pmc551_erase(struct mtd_info *mtd, struct erase_info *instr)
 {
 	struct mypriv *priv = mtd->priv;
@@ -116,16 +151,6 @@ static int pmc551_erase(struct mtd_info *mtd, struct erase_info *instr)
 #endif
 
 	end = instr->addr + instr->len - 1;
-
-	/* Is it past the end? */
-	if (end > mtd->size) {
-#ifdef CONFIG_MTD_PMC551_DEBUG
-		printk(KERN_DEBUG "pmc551_erase() out of bounds (%ld > %ld)\n",
-			(long)end, (long)mtd->size);
-#endif
-		return -EINVAL;
-	}
-
 	eoff_hi = end & ~(priv->asize - 1);
 	soff_hi = instr->addr & ~(priv->asize - 1);
 	eoff_lo = end & (priv->asize - 1);
@@ -179,18 +204,6 @@ static int pmc551_point(struct mtd_info *mtd, loff_t from, size_t len,
 	printk(KERN_DEBUG "pmc551_point(%ld, %ld)\n", (long)from, (long)len);
 #endif
 
-	if (from + len > mtd->size) {
-#ifdef CONFIG_MTD_PMC551_DEBUG
-		printk(KERN_DEBUG "pmc551_point() out of bounds (%ld > %ld)\n",
-			(long)from + len, (long)mtd->size);
-#endif
-		return -EINVAL;
-	}
-
-	/* can we return a physical address with this driver? */
-	if (phys)
-		return -EINVAL;
-
 	soff_hi = from & ~(priv->asize - 1);
 	soff_lo = from & (priv->asize - 1);
 
@@ -206,11 +219,12 @@ static int pmc551_point(struct mtd_info *mtd, loff_t from, size_t len,
 	return 0;
 }
 
-static void pmc551_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
+static int pmc551_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
 #ifdef CONFIG_MTD_PMC551_DEBUG
 	printk(KERN_DEBUG "pmc551_unpoint()\n");
 #endif
+	return 0;
 }
 
 static int pmc551_read(struct mtd_info *mtd, loff_t from, size_t len,
@@ -229,16 +243,6 @@ static int pmc551_read(struct mtd_info *mtd, loff_t from, size_t len,
 #endif
 
 	end = from + len - 1;
-
-	/* Is it past the end? */
-	if (end > mtd->size) {
-#ifdef CONFIG_MTD_PMC551_DEBUG
-		printk(KERN_DEBUG "pmc551_read() out of bounds (%ld > %ld)\n",
-			(long)end, (long)mtd->size);
-#endif
-		return -EINVAL;
-	}
-
 	soff_hi = from & ~(priv->asize - 1);
 	eoff_hi = end & ~(priv->asize - 1);
 	soff_lo = from & (priv->asize - 1);
@@ -296,16 +300,6 @@ static int pmc551_write(struct mtd_info *mtd, loff_t to, size_t len,
 #endif
 
 	end = to + len - 1;
-	/* Is it past the end?  or did the u32 wrap? */
-	if (end > mtd->size) {
-#ifdef CONFIG_MTD_PMC551_DEBUG
-		printk(KERN_DEBUG "pmc551_write() out of bounds (end: %ld, "
-			"size: %ld, to: %ld)\n", (long)end, (long)mtd->size,
-			(long)to);
-#endif
-		return -EINVAL;
-	}
-
 	soff_hi = to & ~(priv->asize - 1);
 	eoff_hi = end & ~(priv->asize - 1);
 	soff_lo = to & (priv->asize - 1);
@@ -359,7 +353,7 @@ static int pmc551_write(struct mtd_info *mtd, loff_t to, size_t len,
  * mechanism
  * returns the size of the memory region found.
  */
-static u32 fixup_pmc551(struct pci_dev *dev)
+static int fixup_pmc551(struct pci_dev *dev)
 {
 #ifdef CONFIG_MTD_PMC551_BUGFIX
 	u32 dram_data;
@@ -669,7 +663,7 @@ static int __init init_pmc551(void)
 	struct mypriv *priv;
 	int found = 0;
 	struct mtd_info *mtd;
-	u32 length = 0;
+	int length = 0;
 
 	if (msize) {
 		msize = (1 << (ffs(msize) - 1)) << 20;
@@ -787,11 +781,11 @@ static int __init init_pmc551(void)
 
 		mtd->size = msize;
 		mtd->flags = MTD_CAP_RAM;
-		mtd->erase = pmc551_erase;
-		mtd->read = pmc551_read;
-		mtd->write = pmc551_write;
-		mtd->point = pmc551_point;
-		mtd->unpoint = pmc551_unpoint;
+		mtd->_erase = pmc551_erase;
+		mtd->_read = pmc551_read;
+		mtd->_write = pmc551_write;
+		mtd->_point = pmc551_point;
+		mtd->_unpoint = pmc551_unpoint;
 		mtd->type = MTD_RAM;
 		mtd->name = "PMC551 RAM board";
 		mtd->erasesize = 0x10000;
diff --git a/drivers/mtd/devices/slram.c b/drivers/mtd/devices/slram.c
index e585263161b9..8f52fc858e48 100644
--- a/drivers/mtd/devices/slram.c
+++ b/drivers/mtd/devices/slram.c
@@ -42,7 +42,6 @@
 #include <linux/ioctl.h>
 #include <linux/init.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <linux/mtd/mtd.h>
 
@@ -76,7 +75,7 @@ static slram_mtd_list_t *slram_mtdlist = NULL;
 static int slram_erase(struct mtd_info *, struct erase_info *);
 static int slram_point(struct mtd_info *, loff_t, size_t, size_t *, void **,
 		resource_size_t *);
-static void slram_unpoint(struct mtd_info *, loff_t, size_t);
+static int slram_unpoint(struct mtd_info *, loff_t, size_t);
 static int slram_read(struct mtd_info *, loff_t, size_t, size_t *, u_char *);
 static int slram_write(struct mtd_info *, loff_t, size_t, size_t *, const u_char *);
 
@@ -84,21 +83,13 @@ static int slram_erase(struct mtd_info *mtd, struct erase_info *instr)
 {
 	slram_priv_t *priv = mtd->priv;
 
-	if (instr->addr + instr->len > mtd->size) {
-		return(-EINVAL);
-	}
-
 	memset(priv->start + instr->addr, 0xff, instr->len);
-
 	/* This'll catch a few races. Free the thing before returning :)
 	 * I don't feel at all ashamed. This kind of thing is possible anyway
 	 * with flash, but unlikely.
 	 */
-
 	instr->state = MTD_ERASE_DONE;
-
 	mtd_erase_callback(instr);
-
 	return(0);
 }
 
@@ -107,20 +98,14 @@ static int slram_point(struct mtd_info *mtd, loff_t from, size_t len,
 {
 	slram_priv_t *priv = mtd->priv;
 
-	/* can we return a physical address with this driver? */
-	if (phys)
-		return -EINVAL;
-
-	if (from + len > mtd->size)
-		return -EINVAL;
-
 	*virt = priv->start + from;
 	*retlen = len;
 	return(0);
 }
 
-static void slram_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
+static int slram_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
+	return 0;
 }
 
 static int slram_read(struct mtd_info *mtd, loff_t from, size_t len,
@@ -128,14 +113,7 @@ static int slram_read(struct mtd_info *mtd, loff_t from, size_t len,
 {
 	slram_priv_t *priv = mtd->priv;
 
-	if (from > mtd->size)
-		return -EINVAL;
-
-	if (from + len > mtd->size)
-		len = mtd->size - from;
-
 	memcpy(buf, priv->start + from, len);
-
 	*retlen = len;
 	return(0);
 }
@@ -145,11 +123,7 @@ static int slram_write(struct mtd_info *mtd, loff_t to, size_t len,
 {
 	slram_priv_t *priv = mtd->priv;
 
-	if (to + len > mtd->size)
-		return -EINVAL;
-
 	memcpy(priv->start + to, buf, len);
-
 	*retlen = len;
 	return(0);
 }
@@ -200,11 +174,11 @@ static int register_device(char *name, unsigned long start, unsigned long length
 	(*curmtd)->mtdinfo->name = name;
 	(*curmtd)->mtdinfo->size = length;
 	(*curmtd)->mtdinfo->flags = MTD_CAP_RAM;
-        (*curmtd)->mtdinfo->erase = slram_erase;
-	(*curmtd)->mtdinfo->point = slram_point;
-	(*curmtd)->mtdinfo->unpoint = slram_unpoint;
-	(*curmtd)->mtdinfo->read = slram_read;
-	(*curmtd)->mtdinfo->write = slram_write;
+	(*curmtd)->mtdinfo->_erase = slram_erase;
+	(*curmtd)->mtdinfo->_point = slram_point;
+	(*curmtd)->mtdinfo->_unpoint = slram_unpoint;
+	(*curmtd)->mtdinfo->_read = slram_read;
+	(*curmtd)->mtdinfo->_write = slram_write;
 	(*curmtd)->mtdinfo->owner = THIS_MODULE;
 	(*curmtd)->mtdinfo->type = MTD_RAM;
 	(*curmtd)->mtdinfo->erasesize = SLRAM_BLK_SZ;
diff --git a/drivers/mtd/devices/spear_smi.c b/drivers/mtd/devices/spear_smi.c
new file mode 100644
index 000000000000..797d43cd3550
--- /dev/null
+++ b/drivers/mtd/devices/spear_smi.c
@@ -0,0 +1,1147 @@
+/*
+ * SMI (Serial Memory Controller) device driver for Serial NOR Flash on
+ * SPEAr platform
+ * The serial nor interface is largely based on drivers/mtd/m25p80.c,
+ * however the SPI interface has been replaced by SMI.
+ *
+ * Copyright © 2010 STMicroelectronics.
+ * Ashish Priyadarshi
+ * Shiraz Hashim <shiraz.hashim@st.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/param.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spear_smi.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+/* SMI clock rate */
+#define SMI_MAX_CLOCK_FREQ	50000000 /* 50 MHz */
+
+/* MAX time out to safely come out of a erase or write busy conditions */
+#define SMI_PROBE_TIMEOUT	(HZ / 10)
+#define SMI_MAX_TIME_OUT	(3 * HZ)
+
+/* timeout for command completion */
+#define SMI_CMD_TIMEOUT		(HZ / 10)
+
+/* registers of smi */
+#define SMI_CR1		0x0	/* SMI control register 1 */
+#define SMI_CR2		0x4	/* SMI control register 2 */
+#define SMI_SR		0x8	/* SMI status register */
+#define SMI_TR		0xC	/* SMI transmit register */
+#define SMI_RR		0x10	/* SMI receive register */
+
+/* defines for control_reg 1 */
+#define BANK_EN		(0xF << 0)	/* enables all banks */
+#define DSEL_TIME	(0x6 << 4)	/* Deselect time 6 + 1 SMI_CK periods */
+#define SW_MODE		(0x1 << 28)	/* enables SW Mode */
+#define WB_MODE		(0x1 << 29)	/* Write Burst Mode */
+#define FAST_MODE	(0x1 << 15)	/* Fast Mode */
+#define HOLD1		(0x1 << 16)	/* Clock Hold period selection */
+
+/* defines for control_reg 2 */
+#define SEND		(0x1 << 7)	/* Send data */
+#define TFIE		(0x1 << 8)	/* Transmission Flag Interrupt Enable */
+#define WCIE		(0x1 << 9)	/* Write Complete Interrupt Enable */
+#define RD_STATUS_REG	(0x1 << 10)	/* reads status reg */
+#define WE		(0x1 << 11)	/* Write Enable */
+
+#define TX_LEN_SHIFT	0
+#define RX_LEN_SHIFT	4
+#define BANK_SHIFT	12
+
+/* defines for status register */
+#define SR_WIP		0x1	/* Write in progress */
+#define SR_WEL		0x2	/* Write enable latch */
+#define SR_BP0		0x4	/* Block protect 0 */
+#define SR_BP1		0x8	/* Block protect 1 */
+#define SR_BP2		0x10	/* Block protect 2 */
+#define SR_SRWD		0x80	/* SR write protect */
+#define TFF		0x100	/* Transfer Finished Flag */
+#define WCF		0x200	/* Transfer Finished Flag */
+#define ERF1		0x400	/* Forbidden Write Request */
+#define ERF2		0x800	/* Forbidden Access */
+
+#define WM_SHIFT	12
+
+/* flash opcodes */
+#define OPCODE_RDID	0x9f	/* Read JEDEC ID */
+
+/* Flash Device Ids maintenance section */
+
+/* data structure to maintain flash ids from different vendors */
+struct flash_device {
+	char *name;
+	u8 erase_cmd;
+	u32 device_id;
+	u32 pagesize;
+	unsigned long sectorsize;
+	unsigned long size_in_bytes;
+};
+
+#define FLASH_ID(n, es, id, psize, ssize, size)	\
+{				\
+	.name = n,		\
+	.erase_cmd = es,	\
+	.device_id = id,	\
+	.pagesize = psize,	\
+	.sectorsize = ssize,	\
+	.size_in_bytes = size	\
+}
+
+static struct flash_device flash_devices[] = {
+	FLASH_ID("st m25p16"     , 0xd8, 0x00152020, 0x100, 0x10000, 0x200000),
+	FLASH_ID("st m25p32"     , 0xd8, 0x00162020, 0x100, 0x10000, 0x400000),
+	FLASH_ID("st m25p64"     , 0xd8, 0x00172020, 0x100, 0x10000, 0x800000),
+	FLASH_ID("st m25p128"    , 0xd8, 0x00182020, 0x100, 0x40000, 0x1000000),
+	FLASH_ID("st m25p05"     , 0xd8, 0x00102020, 0x80 , 0x8000 , 0x10000),
+	FLASH_ID("st m25p10"     , 0xd8, 0x00112020, 0x80 , 0x8000 , 0x20000),
+	FLASH_ID("st m25p20"     , 0xd8, 0x00122020, 0x100, 0x10000, 0x40000),
+	FLASH_ID("st m25p40"     , 0xd8, 0x00132020, 0x100, 0x10000, 0x80000),
+	FLASH_ID("st m25p80"     , 0xd8, 0x00142020, 0x100, 0x10000, 0x100000),
+	FLASH_ID("st m45pe10"    , 0xd8, 0x00114020, 0x100, 0x10000, 0x20000),
+	FLASH_ID("st m45pe20"    , 0xd8, 0x00124020, 0x100, 0x10000, 0x40000),
+	FLASH_ID("st m45pe40"    , 0xd8, 0x00134020, 0x100, 0x10000, 0x80000),
+	FLASH_ID("st m45pe80"    , 0xd8, 0x00144020, 0x100, 0x10000, 0x100000),
+	FLASH_ID("sp s25fl004"   , 0xd8, 0x00120201, 0x100, 0x10000, 0x80000),
+	FLASH_ID("sp s25fl008"   , 0xd8, 0x00130201, 0x100, 0x10000, 0x100000),
+	FLASH_ID("sp s25fl016"   , 0xd8, 0x00140201, 0x100, 0x10000, 0x200000),
+	FLASH_ID("sp s25fl032"   , 0xd8, 0x00150201, 0x100, 0x10000, 0x400000),
+	FLASH_ID("sp s25fl064"   , 0xd8, 0x00160201, 0x100, 0x10000, 0x800000),
+	FLASH_ID("atmel 25f512"  , 0x52, 0x0065001F, 0x80 , 0x8000 , 0x10000),
+	FLASH_ID("atmel 25f1024" , 0x52, 0x0060001F, 0x100, 0x8000 , 0x20000),
+	FLASH_ID("atmel 25f2048" , 0x52, 0x0063001F, 0x100, 0x10000, 0x40000),
+	FLASH_ID("atmel 25f4096" , 0x52, 0x0064001F, 0x100, 0x10000, 0x80000),
+	FLASH_ID("atmel 25fs040" , 0xd7, 0x0004661F, 0x100, 0x10000, 0x80000),
+	FLASH_ID("mac 25l512"    , 0xd8, 0x001020C2, 0x010, 0x10000, 0x10000),
+	FLASH_ID("mac 25l1005"   , 0xd8, 0x001120C2, 0x010, 0x10000, 0x20000),
+	FLASH_ID("mac 25l2005"   , 0xd8, 0x001220C2, 0x010, 0x10000, 0x40000),
+	FLASH_ID("mac 25l4005"   , 0xd8, 0x001320C2, 0x010, 0x10000, 0x80000),
+	FLASH_ID("mac 25l4005a"  , 0xd8, 0x001320C2, 0x010, 0x10000, 0x80000),
+	FLASH_ID("mac 25l8005"   , 0xd8, 0x001420C2, 0x010, 0x10000, 0x100000),
+	FLASH_ID("mac 25l1605"   , 0xd8, 0x001520C2, 0x100, 0x10000, 0x200000),
+	FLASH_ID("mac 25l1605a"  , 0xd8, 0x001520C2, 0x010, 0x10000, 0x200000),
+	FLASH_ID("mac 25l3205"   , 0xd8, 0x001620C2, 0x100, 0x10000, 0x400000),
+	FLASH_ID("mac 25l3205a"  , 0xd8, 0x001620C2, 0x100, 0x10000, 0x400000),
+	FLASH_ID("mac 25l6405"   , 0xd8, 0x001720C2, 0x100, 0x10000, 0x800000),
+};
+
+/* Define spear specific structures */
+
+struct spear_snor_flash;
+
+/**
+ * struct spear_smi - Structure for SMI Device
+ *
+ * @clk: functional clock
+ * @status: current status register of SMI.
+ * @clk_rate: functional clock rate of SMI (default: SMI_MAX_CLOCK_FREQ)
+ * @lock: lock to prevent parallel access of SMI.
+ * @io_base: base address for registers of SMI.
+ * @pdev: platform device
+ * @cmd_complete: queue to wait for command completion of NOR-flash.
+ * @num_flashes: number of flashes actually present on board.
+ * @flash: separate structure for each Serial NOR-flash attached to SMI.
+ */
+struct spear_smi {
+	struct clk *clk;
+	u32 status;
+	unsigned long clk_rate;
+	struct mutex lock;
+	void __iomem *io_base;
+	struct platform_device *pdev;
+	wait_queue_head_t cmd_complete;
+	u32 num_flashes;
+	struct spear_snor_flash *flash[MAX_NUM_FLASH_CHIP];
+};
+
+/**
+ * struct spear_snor_flash - Structure for Serial NOR Flash
+ *
+ * @bank: Bank number(0, 1, 2, 3) for each NOR-flash.
+ * @dev_id: Device ID of NOR-flash.
+ * @lock: lock to manage flash read, write and erase operations
+ * @mtd: MTD info for each NOR-flash.
+ * @num_parts: Total number of partition in each bank of NOR-flash.
+ * @parts: Partition info for each bank of NOR-flash.
+ * @page_size: Page size of NOR-flash.
+ * @base_addr: Base address of NOR-flash.
+ * @erase_cmd: erase command may vary on different flash types
+ * @fast_mode: flash supports read in fast mode
+ */
+struct spear_snor_flash {
+	u32 bank;
+	u32 dev_id;
+	struct mutex lock;
+	struct mtd_info mtd;
+	u32 num_parts;
+	struct mtd_partition *parts;
+	u32 page_size;
+	void __iomem *base_addr;
+	u8 erase_cmd;
+	u8 fast_mode;
+};
+
+static inline struct spear_snor_flash *get_flash_data(struct mtd_info *mtd)
+{
+	return container_of(mtd, struct spear_snor_flash, mtd);
+}
+
+/**
+ * spear_smi_read_sr - Read status register of flash through SMI
+ * @dev: structure of SMI information.
+ * @bank: bank to which flash is connected
+ *
+ * This routine will return the status register of the flash chip present at the
+ * given bank.
+ */
+static int spear_smi_read_sr(struct spear_smi *dev, u32 bank)
+{
+	int ret;
+	u32 ctrlreg1;
+
+	mutex_lock(&dev->lock);
+	dev->status = 0; /* Will be set in interrupt handler */
+
+	ctrlreg1 = readl(dev->io_base + SMI_CR1);
+	/* program smi in hw mode */
+	writel(ctrlreg1 & ~(SW_MODE | WB_MODE), dev->io_base + SMI_CR1);
+
+	/* performing a rsr instruction in hw mode */
+	writel((bank << BANK_SHIFT) | RD_STATUS_REG | TFIE,
+			dev->io_base + SMI_CR2);
+
+	/* wait for tff */
+	ret = wait_event_interruptible_timeout(dev->cmd_complete,
+			dev->status & TFF, SMI_CMD_TIMEOUT);
+
+	/* copy dev->status (lower 16 bits) in order to release lock */
+	if (ret > 0)
+		ret = dev->status & 0xffff;
+	else
+		ret = -EIO;
+
+	/* restore the ctrl regs state */
+	writel(ctrlreg1, dev->io_base + SMI_CR1);
+	writel(0, dev->io_base + SMI_CR2);
+	mutex_unlock(&dev->lock);
+
+	return ret;
+}
+
+/**
+ * spear_smi_wait_till_ready - wait till flash is ready
+ * @dev: structure of SMI information.
+ * @bank: flash corresponding to this bank
+ * @timeout: timeout for busy wait condition
+ *
+ * This routine checks for WIP (write in progress) bit in Status register
+ * If successful the routine returns 0 else -EBUSY
+ */
+static int spear_smi_wait_till_ready(struct spear_smi *dev, u32 bank,
+		unsigned long timeout)
+{
+	unsigned long finish;
+	int status;
+
+	finish = jiffies + timeout;
+	do {
+		status = spear_smi_read_sr(dev, bank);
+		if (status < 0)
+			continue; /* try till timeout */
+		else if (!(status & SR_WIP))
+			return 0;
+
+		cond_resched();
+	} while (!time_after_eq(jiffies, finish));
+
+	dev_err(&dev->pdev->dev, "smi controller is busy, timeout\n");
+	return status;
+}
+
+/**
+ * spear_smi_int_handler - SMI Interrupt Handler.
+ * @irq: irq number
+ * @dev_id: structure of SMI device, embedded in dev_id.
+ *
+ * The handler clears all interrupt conditions and records the status in
+ * dev->status which is used by the driver later.
+ */
+static irqreturn_t spear_smi_int_handler(int irq, void *dev_id)
+{
+	u32 status = 0;
+	struct spear_smi *dev = dev_id;
+
+	status = readl(dev->io_base + SMI_SR);
+
+	if (unlikely(!status))
+		return IRQ_NONE;
+
+	/* clear all interrupt conditions */
+	writel(0, dev->io_base + SMI_SR);
+
+	/* copy the status register in dev->status */
+	dev->status |= status;
+
+	/* send the completion */
+	wake_up_interruptible(&dev->cmd_complete);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * spear_smi_hw_init - initializes the smi controller.
+ * @dev: structure of smi device
+ *
+ * this routine initializes the smi controller wit the default values
+ */
+static void spear_smi_hw_init(struct spear_smi *dev)
+{
+	unsigned long rate = 0;
+	u32 prescale = 0;
+	u32 val;
+
+	rate = clk_get_rate(dev->clk);
+
+	/* functional clock of smi */
+	prescale = DIV_ROUND_UP(rate, dev->clk_rate);
+
+	/*
+	 * setting the standard values, fast mode, prescaler for
+	 * SMI_MAX_CLOCK_FREQ (50MHz) operation and bank enable
+	 */
+	val = HOLD1 | BANK_EN | DSEL_TIME | (prescale << 8);
+
+	mutex_lock(&dev->lock);
+	writel(val, dev->io_base + SMI_CR1);
+	mutex_unlock(&dev->lock);
+}
+
+/**
+ * get_flash_index - match chip id from a flash list.
+ * @flash_id: a valid nor flash chip id obtained from board.
+ *
+ * try to validate the chip id by matching from a list, if not found then simply
+ * returns negative. In case of success returns index in to the flash devices
+ * array.
+ */
+static int get_flash_index(u32 flash_id)
+{
+	int index;
+
+	/* Matches chip-id to entire list of 'serial-nor flash' ids */
+	for (index = 0; index < ARRAY_SIZE(flash_devices); index++) {
+		if (flash_devices[index].device_id == flash_id)
+			return index;
+	}
+
+	/* Memory chip is not listed and not supported */
+	return -ENODEV;
+}
+
+/**
+ * spear_smi_write_enable - Enable the flash to do write operation
+ * @dev: structure of SMI device
+ * @bank: enable write for flash connected to this bank
+ *
+ * Set write enable latch with Write Enable command.
+ * Returns 0 on success.
+ */
+static int spear_smi_write_enable(struct spear_smi *dev, u32 bank)
+{
+	int ret;
+	u32 ctrlreg1;
+
+	mutex_lock(&dev->lock);
+	dev->status = 0; /* Will be set in interrupt handler */
+
+	ctrlreg1 = readl(dev->io_base + SMI_CR1);
+	/* program smi in h/w mode */
+	writel(ctrlreg1 & ~SW_MODE, dev->io_base + SMI_CR1);
+
+	/* give the flash, write enable command */
+	writel((bank << BANK_SHIFT) | WE | TFIE, dev->io_base + SMI_CR2);
+
+	ret = wait_event_interruptible_timeout(dev->cmd_complete,
+			dev->status & TFF, SMI_CMD_TIMEOUT);
+
+	/* restore the ctrl regs state */
+	writel(ctrlreg1, dev->io_base + SMI_CR1);
+	writel(0, dev->io_base + SMI_CR2);
+
+	if (ret <= 0) {
+		ret = -EIO;
+		dev_err(&dev->pdev->dev,
+			"smi controller failed on write enable\n");
+	} else {
+		/* check whether write mode status is set for required bank */
+		if (dev->status & (1 << (bank + WM_SHIFT)))
+			ret = 0;
+		else {
+			dev_err(&dev->pdev->dev, "couldn't enable write\n");
+			ret = -EIO;
+		}
+	}
+
+	mutex_unlock(&dev->lock);
+	return ret;
+}
+
+static inline u32
+get_sector_erase_cmd(struct spear_snor_flash *flash, u32 offset)
+{
+	u32 cmd;
+	u8 *x = (u8 *)&cmd;
+
+	x[0] = flash->erase_cmd;
+	x[1] = offset >> 16;
+	x[2] = offset >> 8;
+	x[3] = offset;
+
+	return cmd;
+}
+
+/**
+ * spear_smi_erase_sector - erase one sector of flash
+ * @dev: structure of SMI information
+ * @command: erase command to be send
+ * @bank: bank to which this command needs to be send
+ * @bytes: size of command
+ *
+ * Erase one sector of flash memory at offset ``offset'' which is any
+ * address within the sector which should be erased.
+ * Returns 0 if successful, non-zero otherwise.
+ */
+static int spear_smi_erase_sector(struct spear_smi *dev,
+		u32 bank, u32 command, u32 bytes)
+{
+	u32 ctrlreg1 = 0;
+	int ret;
+
+	ret = spear_smi_wait_till_ready(dev, bank, SMI_MAX_TIME_OUT);
+	if (ret)
+		return ret;
+
+	ret = spear_smi_write_enable(dev, bank);
+	if (ret)
+		return ret;
+
+	mutex_lock(&dev->lock);
+
+	ctrlreg1 = readl(dev->io_base + SMI_CR1);
+	writel((ctrlreg1 | SW_MODE) & ~WB_MODE, dev->io_base + SMI_CR1);
+
+	/* send command in sw mode */
+	writel(command, dev->io_base + SMI_TR);
+
+	writel((bank << BANK_SHIFT) | SEND | TFIE | (bytes << TX_LEN_SHIFT),
+			dev->io_base + SMI_CR2);
+
+	ret = wait_event_interruptible_timeout(dev->cmd_complete,
+			dev->status & TFF, SMI_CMD_TIMEOUT);
+
+	if (ret <= 0) {
+		ret = -EIO;
+		dev_err(&dev->pdev->dev, "sector erase failed\n");
+	} else
+		ret = 0; /* success */
+
+	/* restore ctrl regs */
+	writel(ctrlreg1, dev->io_base + SMI_CR1);
+	writel(0, dev->io_base + SMI_CR2);
+
+	mutex_unlock(&dev->lock);
+	return ret;
+}
+
+/**
+ * spear_mtd_erase - perform flash erase operation as requested by user
+ * @mtd: Provides the memory characteristics
+ * @e_info: Provides the erase information
+ *
+ * Erase an address range on the flash chip. The address range may extend
+ * one or more erase sectors. Return an error is there is a problem erasing.
+ */
+static int spear_mtd_erase(struct mtd_info *mtd, struct erase_info *e_info)
+{
+	struct spear_snor_flash *flash = get_flash_data(mtd);
+	struct spear_smi *dev = mtd->priv;
+	u32 addr, command, bank;
+	int len, ret;
+
+	if (!flash || !dev)
+		return -ENODEV;
+
+	bank = flash->bank;
+	if (bank > dev->num_flashes - 1) {
+		dev_err(&dev->pdev->dev, "Invalid Bank Num");
+		return -EINVAL;
+	}
+
+	addr = e_info->addr;
+	len = e_info->len;
+
+	mutex_lock(&flash->lock);
+
+	/* now erase sectors in loop */
+	while (len) {
+		command = get_sector_erase_cmd(flash, addr);
+		/* preparing the command for flash */
+		ret = spear_smi_erase_sector(dev, bank, command, 4);
+		if (ret) {
+			e_info->state = MTD_ERASE_FAILED;
+			mutex_unlock(&flash->lock);
+			return ret;
+		}
+		addr += mtd->erasesize;
+		len -= mtd->erasesize;
+	}
+
+	mutex_unlock(&flash->lock);
+	e_info->state = MTD_ERASE_DONE;
+	mtd_erase_callback(e_info);
+
+	return 0;
+}
+
+/**
+ * spear_mtd_read - performs flash read operation as requested by the user
+ * @mtd: MTD information of the memory bank
+ * @from: Address from which to start read
+ * @len: Number of bytes to be read
+ * @retlen: Fills the Number of bytes actually read
+ * @buf: Fills this after reading
+ *
+ * Read an address range from the flash chip. The address range
+ * may be any size provided it is within the physical boundaries.
+ * Returns 0 on success, non zero otherwise
+ */
+static int spear_mtd_read(struct mtd_info *mtd, loff_t from, size_t len,
+		size_t *retlen, u8 *buf)
+{
+	struct spear_snor_flash *flash = get_flash_data(mtd);
+	struct spear_smi *dev = mtd->priv;
+	void *src;
+	u32 ctrlreg1, val;
+	int ret;
+
+	if (!flash || !dev)
+		return -ENODEV;
+
+	if (flash->bank > dev->num_flashes - 1) {
+		dev_err(&dev->pdev->dev, "Invalid Bank Num");
+		return -EINVAL;
+	}
+
+	/* select address as per bank number */
+	src = flash->base_addr + from;
+
+	mutex_lock(&flash->lock);
+
+	/* wait till previous write/erase is done. */
+	ret = spear_smi_wait_till_ready(dev, flash->bank, SMI_MAX_TIME_OUT);
+	if (ret) {
+		mutex_unlock(&flash->lock);
+		return ret;
+	}
+
+	mutex_lock(&dev->lock);
+	/* put smi in hw mode not wbt mode */
+	ctrlreg1 = val = readl(dev->io_base + SMI_CR1);
+	val &= ~(SW_MODE | WB_MODE);
+	if (flash->fast_mode)
+		val |= FAST_MODE;
+
+	writel(val, dev->io_base + SMI_CR1);
+
+	memcpy_fromio(buf, (u8 *)src, len);
+
+	/* restore ctrl reg1 */
+	writel(ctrlreg1, dev->io_base + SMI_CR1);
+	mutex_unlock(&dev->lock);
+
+	*retlen = len;
+	mutex_unlock(&flash->lock);
+
+	return 0;
+}
+
+static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank,
+		void *dest, const void *src, size_t len)
+{
+	int ret;
+	u32 ctrlreg1;
+
+	/* wait until finished previous write command. */
+	ret = spear_smi_wait_till_ready(dev, bank, SMI_MAX_TIME_OUT);
+	if (ret)
+		return ret;
+
+	/* put smi in write enable */
+	ret = spear_smi_write_enable(dev, bank);
+	if (ret)
+		return ret;
+
+	/* put smi in hw, write burst mode */
+	mutex_lock(&dev->lock);
+
+	ctrlreg1 = readl(dev->io_base + SMI_CR1);
+	writel((ctrlreg1 | WB_MODE) & ~SW_MODE, dev->io_base + SMI_CR1);
+
+	memcpy_toio(dest, src, len);
+
+	writel(ctrlreg1, dev->io_base + SMI_CR1);
+
+	mutex_unlock(&dev->lock);
+	return 0;
+}
+
+/**
+ * spear_mtd_write - performs write operation as requested by the user.
+ * @mtd: MTD information of the memory bank.
+ * @to:	Address to write.
+ * @len: Number of bytes to be written.
+ * @retlen: Number of bytes actually wrote.
+ * @buf: Buffer from which the data to be taken.
+ *
+ * Write an address range to the flash chip. Data must be written in
+ * flash_page_size chunks. The address range may be any size provided
+ * it is within the physical boundaries.
+ * Returns 0 on success, non zero otherwise
+ */
+static int spear_mtd_write(struct mtd_info *mtd, loff_t to, size_t len,
+		size_t *retlen, const u8 *buf)
+{
+	struct spear_snor_flash *flash = get_flash_data(mtd);
+	struct spear_smi *dev = mtd->priv;
+	void *dest;
+	u32 page_offset, page_size;
+	int ret;
+
+	if (!flash || !dev)
+		return -ENODEV;
+
+	if (flash->bank > dev->num_flashes - 1) {
+		dev_err(&dev->pdev->dev, "Invalid Bank Num");
+		return -EINVAL;
+	}
+
+	/* select address as per bank number */
+	dest = flash->base_addr + to;
+	mutex_lock(&flash->lock);
+
+	page_offset = (u32)to % flash->page_size;
+
+	/* do if all the bytes fit onto one page */
+	if (page_offset + len <= flash->page_size) {
+		ret = spear_smi_cpy_toio(dev, flash->bank, dest, buf, len);
+		if (!ret)
+			*retlen += len;
+	} else {
+		u32 i;
+
+		/* the size of data remaining on the first page */
+		page_size = flash->page_size - page_offset;
+
+		ret = spear_smi_cpy_toio(dev, flash->bank, dest, buf,
+				page_size);
+		if (ret)
+			goto err_write;
+		else
+			*retlen += page_size;
+
+		/* write everything in pagesize chunks */
+		for (i = page_size; i < len; i += page_size) {
+			page_size = len - i;
+			if (page_size > flash->page_size)
+				page_size = flash->page_size;
+
+			ret = spear_smi_cpy_toio(dev, flash->bank, dest + i,
+					buf + i, page_size);
+			if (ret)
+				break;
+			else
+				*retlen += page_size;
+		}
+	}
+
+err_write:
+	mutex_unlock(&flash->lock);
+
+	return ret;
+}
+
+/**
+ * spear_smi_probe_flash - Detects the NOR Flash chip.
+ * @dev: structure of SMI information.
+ * @bank: bank on which flash must be probed
+ *
+ * This routine will check whether there exists a flash chip on a given memory
+ * bank ID.
+ * Return index of the probed flash in flash devices structure
+ */
+static int spear_smi_probe_flash(struct spear_smi *dev, u32 bank)
+{
+	int ret;
+	u32 val = 0;
+
+	ret = spear_smi_wait_till_ready(dev, bank, SMI_PROBE_TIMEOUT);
+	if (ret)
+		return ret;
+
+	mutex_lock(&dev->lock);
+
+	dev->status = 0; /* Will be set in interrupt handler */
+	/* put smi in sw mode */
+	val = readl(dev->io_base + SMI_CR1);
+	writel(val | SW_MODE, dev->io_base + SMI_CR1);
+
+	/* send readid command in sw mode */
+	writel(OPCODE_RDID, dev->io_base + SMI_TR);
+
+	val = (bank << BANK_SHIFT) | SEND | (1 << TX_LEN_SHIFT) |
+		(3 << RX_LEN_SHIFT) | TFIE;
+	writel(val, dev->io_base + SMI_CR2);
+
+	/* wait for TFF */
+	ret = wait_event_interruptible_timeout(dev->cmd_complete,
+			dev->status & TFF, SMI_CMD_TIMEOUT);
+	if (ret <= 0) {
+		ret = -ENODEV;
+		goto err_probe;
+	}
+
+	/* get memory chip id */
+	val = readl(dev->io_base + SMI_RR);
+	val &= 0x00ffffff;
+	ret = get_flash_index(val);
+
+err_probe:
+	/* clear sw mode */
+	val = readl(dev->io_base + SMI_CR1);
+	writel(val & ~SW_MODE, dev->io_base + SMI_CR1);
+
+	mutex_unlock(&dev->lock);
+	return ret;
+}
+
+
+#ifdef CONFIG_OF
+static int __devinit spear_smi_probe_config_dt(struct platform_device *pdev,
+					       struct device_node *np)
+{
+	struct spear_smi_plat_data *pdata = dev_get_platdata(&pdev->dev);
+	struct device_node *pp = NULL;
+	const __be32 *addr;
+	u32 val;
+	int len;
+	int i = 0;
+
+	if (!np)
+		return -ENODEV;
+
+	of_property_read_u32(np, "clock-rate", &val);
+	pdata->clk_rate = val;
+
+	pdata->board_flash_info = devm_kzalloc(&pdev->dev,
+					       sizeof(*pdata->board_flash_info),
+					       GFP_KERNEL);
+
+	/* Fill structs for each subnode (flash device) */
+	while ((pp = of_get_next_child(np, pp))) {
+		struct spear_smi_flash_info *flash_info;
+
+		flash_info = &pdata->board_flash_info[i];
+		pdata->np[i] = pp;
+
+		/* Read base-addr and size from DT */
+		addr = of_get_property(pp, "reg", &len);
+		pdata->board_flash_info->mem_base = be32_to_cpup(&addr[0]);
+		pdata->board_flash_info->size = be32_to_cpup(&addr[1]);
+
+		if (of_get_property(pp, "st,smi-fast-mode", NULL))
+			pdata->board_flash_info->fast_mode = 1;
+
+		i++;
+	}
+
+	pdata->num_flashes = i;
+
+	return 0;
+}
+#else
+static int __devinit spear_smi_probe_config_dt(struct platform_device *pdev,
+					       struct device_node *np)
+{
+	return -ENOSYS;
+}
+#endif
+
+static int spear_smi_setup_banks(struct platform_device *pdev,
+				 u32 bank, struct device_node *np)
+{
+	struct spear_smi *dev = platform_get_drvdata(pdev);
+	struct mtd_part_parser_data ppdata = {};
+	struct spear_smi_flash_info *flash_info;
+	struct spear_smi_plat_data *pdata;
+	struct spear_snor_flash *flash;
+	struct mtd_partition *parts = NULL;
+	int count = 0;
+	int flash_index;
+	int ret = 0;
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (bank > pdata->num_flashes - 1)
+		return -EINVAL;
+
+	flash_info = &pdata->board_flash_info[bank];
+	if (!flash_info)
+		return -ENODEV;
+
+	flash = kzalloc(sizeof(*flash), GFP_ATOMIC);
+	if (!flash)
+		return -ENOMEM;
+	flash->bank = bank;
+	flash->fast_mode = flash_info->fast_mode ? 1 : 0;
+	mutex_init(&flash->lock);
+
+	/* verify whether nor flash is really present on board */
+	flash_index = spear_smi_probe_flash(dev, bank);
+	if (flash_index < 0) {
+		dev_info(&dev->pdev->dev, "smi-nor%d not found\n", bank);
+		ret = flash_index;
+		goto err_probe;
+	}
+	/* map the memory for nor flash chip */
+	flash->base_addr = ioremap(flash_info->mem_base, flash_info->size);
+	if (!flash->base_addr) {
+		ret = -EIO;
+		goto err_probe;
+	}
+
+	dev->flash[bank] = flash;
+	flash->mtd.priv = dev;
+
+	if (flash_info->name)
+		flash->mtd.name = flash_info->name;
+	else
+		flash->mtd.name = flash_devices[flash_index].name;
+
+	flash->mtd.type = MTD_NORFLASH;
+	flash->mtd.writesize = 1;
+	flash->mtd.flags = MTD_CAP_NORFLASH;
+	flash->mtd.size = flash_info->size;
+	flash->mtd.erasesize = flash_devices[flash_index].sectorsize;
+	flash->page_size = flash_devices[flash_index].pagesize;
+	flash->mtd.writebufsize = flash->page_size;
+	flash->erase_cmd = flash_devices[flash_index].erase_cmd;
+	flash->mtd._erase = spear_mtd_erase;
+	flash->mtd._read = spear_mtd_read;
+	flash->mtd._write = spear_mtd_write;
+	flash->dev_id = flash_devices[flash_index].device_id;
+
+	dev_info(&dev->pdev->dev, "mtd .name=%s .size=%llx(%lluM)\n",
+			flash->mtd.name, flash->mtd.size,
+			flash->mtd.size / (1024 * 1024));
+
+	dev_info(&dev->pdev->dev, ".erasesize = 0x%x(%uK)\n",
+			flash->mtd.erasesize, flash->mtd.erasesize / 1024);
+
+#ifndef CONFIG_OF
+	if (flash_info->partitions) {
+		parts = flash_info->partitions;
+		count = flash_info->nr_partitions;
+	}
+#endif
+	ppdata.of_node = np;
+
+	ret = mtd_device_parse_register(&flash->mtd, NULL, &ppdata, parts,
+					count);
+	if (ret) {
+		dev_err(&dev->pdev->dev, "Err MTD partition=%d\n", ret);
+		goto err_map;
+	}
+
+	return 0;
+
+err_map:
+	iounmap(flash->base_addr);
+
+err_probe:
+	kfree(flash);
+	return ret;
+}
+
+/**
+ * spear_smi_probe - Entry routine
+ * @pdev: platform device structure
+ *
+ * This is the first routine which gets invoked during booting and does all
+ * initialization/allocation work. The routine looks for available memory banks,
+ * and do proper init for any found one.
+ * Returns 0 on success, non zero otherwise
+ */
+static int __devinit spear_smi_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct spear_smi_plat_data *pdata = NULL;
+	struct spear_smi *dev;
+	struct resource *smi_base;
+	int irq, ret = 0;
+	int i;
+
+	if (np) {
+		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+		if (!pdata) {
+			pr_err("%s: ERROR: no memory", __func__);
+			ret = -ENOMEM;
+			goto err;
+		}
+		pdev->dev.platform_data = pdata;
+		ret = spear_smi_probe_config_dt(pdev, np);
+		if (ret) {
+			ret = -ENODEV;
+			dev_err(&pdev->dev, "no platform data\n");
+			goto err;
+		}
+	} else {
+		pdata = dev_get_platdata(&pdev->dev);
+		if (pdata < 0) {
+			ret = -ENODEV;
+			dev_err(&pdev->dev, "no platform data\n");
+			goto err;
+		}
+	}
+
+	smi_base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!smi_base) {
+		ret = -ENODEV;
+		dev_err(&pdev->dev, "invalid smi base address\n");
+		goto err;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		ret = -ENODEV;
+		dev_err(&pdev->dev, "invalid smi irq\n");
+		goto err;
+	}
+
+	dev = kzalloc(sizeof(*dev), GFP_ATOMIC);
+	if (!dev) {
+		ret = -ENOMEM;
+		dev_err(&pdev->dev, "mem alloc fail\n");
+		goto err;
+	}
+
+	smi_base = request_mem_region(smi_base->start, resource_size(smi_base),
+			pdev->name);
+	if (!smi_base) {
+		ret = -EBUSY;
+		dev_err(&pdev->dev, "request mem region fail\n");
+		goto err_mem;
+	}
+
+	dev->io_base = ioremap(smi_base->start, resource_size(smi_base));
+	if (!dev->io_base) {
+		ret = -EIO;
+		dev_err(&pdev->dev, "ioremap fail\n");
+		goto err_ioremap;
+	}
+
+	dev->pdev = pdev;
+	dev->clk_rate = pdata->clk_rate;
+
+	if (dev->clk_rate < 0 || dev->clk_rate > SMI_MAX_CLOCK_FREQ)
+		dev->clk_rate = SMI_MAX_CLOCK_FREQ;
+
+	dev->num_flashes = pdata->num_flashes;
+
+	if (dev->num_flashes > MAX_NUM_FLASH_CHIP) {
+		dev_err(&pdev->dev, "exceeding max number of flashes\n");
+		dev->num_flashes = MAX_NUM_FLASH_CHIP;
+	}
+
+	dev->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(dev->clk)) {
+		ret = PTR_ERR(dev->clk);
+		goto err_clk;
+	}
+
+	ret = clk_enable(dev->clk);
+	if (ret)
+		goto err_clk_enable;
+
+	ret = request_irq(irq, spear_smi_int_handler, 0, pdev->name, dev);
+	if (ret) {
+		dev_err(&dev->pdev->dev, "SMI IRQ allocation failed\n");
+		goto err_irq;
+	}
+
+	mutex_init(&dev->lock);
+	init_waitqueue_head(&dev->cmd_complete);
+	spear_smi_hw_init(dev);
+	platform_set_drvdata(pdev, dev);
+
+	/* loop for each serial nor-flash which is connected to smi */
+	for (i = 0; i < dev->num_flashes; i++) {
+		ret = spear_smi_setup_banks(pdev, i, pdata->np[i]);
+		if (ret) {
+			dev_err(&dev->pdev->dev, "bank setup failed\n");
+			goto err_bank_setup;
+		}
+	}
+
+	return 0;
+
+err_bank_setup:
+	free_irq(irq, dev);
+	platform_set_drvdata(pdev, NULL);
+err_irq:
+	clk_disable(dev->clk);
+err_clk_enable:
+	clk_put(dev->clk);
+err_clk:
+	iounmap(dev->io_base);
+err_ioremap:
+	release_mem_region(smi_base->start, resource_size(smi_base));
+err_mem:
+	kfree(dev);
+err:
+	return ret;
+}
+
+/**
+ * spear_smi_remove - Exit routine
+ * @pdev: platform device structure
+ *
+ * free all allocations and delete the partitions.
+ */
+static int __devexit spear_smi_remove(struct platform_device *pdev)
+{
+	struct spear_smi *dev;
+	struct spear_smi_plat_data *pdata;
+	struct spear_snor_flash *flash;
+	struct resource *smi_base;
+	int ret;
+	int i, irq;
+
+	dev = platform_get_drvdata(pdev);
+	if (!dev) {
+		dev_err(&pdev->dev, "dev is null\n");
+		return -ENODEV;
+	}
+
+	pdata = dev_get_platdata(&pdev->dev);
+
+	/* clean up for all nor flash */
+	for (i = 0; i < dev->num_flashes; i++) {
+		flash = dev->flash[i];
+		if (!flash)
+			continue;
+
+		/* clean up mtd stuff */
+		ret = mtd_device_unregister(&flash->mtd);
+		if (ret)
+			dev_err(&pdev->dev, "error removing mtd\n");
+
+		iounmap(flash->base_addr);
+		kfree(flash);
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	free_irq(irq, dev);
+
+	clk_disable(dev->clk);
+	clk_put(dev->clk);
+	iounmap(dev->io_base);
+	kfree(dev);
+
+	smi_base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(smi_base->start, resource_size(smi_base));
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+int spear_smi_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct spear_smi *dev = platform_get_drvdata(pdev);
+
+	if (dev && dev->clk)
+		clk_disable(dev->clk);
+
+	return 0;
+}
+
+int spear_smi_resume(struct platform_device *pdev)
+{
+	struct spear_smi *dev = platform_get_drvdata(pdev);
+	int ret = -EPERM;
+
+	if (dev && dev->clk)
+		ret = clk_enable(dev->clk);
+
+	if (!ret)
+		spear_smi_hw_init(dev);
+	return ret;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id spear_smi_id_table[] = {
+	{ .compatible = "st,spear600-smi" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, spear_smi_id_table);
+#endif
+
+static struct platform_driver spear_smi_driver = {
+	.driver = {
+		.name = "smi",
+		.bus = &platform_bus_type,
+		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(spear_smi_id_table),
+	},
+	.probe = spear_smi_probe,
+	.remove = __devexit_p(spear_smi_remove),
+	.suspend = spear_smi_suspend,
+	.resume = spear_smi_resume,
+};
+
+static int spear_smi_init(void)
+{
+	return platform_driver_register(&spear_smi_driver);
+}
+module_init(spear_smi_init);
+
+static void spear_smi_exit(void)
+{
+	platform_driver_unregister(&spear_smi_driver);
+}
+module_exit(spear_smi_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ashish Priyadarshi, Shiraz Hashim <shiraz.hashim@st.com>");
+MODULE_DESCRIPTION("MTD SMI driver for serial nor flash chips");
diff --git a/drivers/mtd/devices/sst25l.c b/drivers/mtd/devices/sst25l.c
index 5fc198350b94..ab8a2f4c8d60 100644
--- a/drivers/mtd/devices/sst25l.c
+++ b/drivers/mtd/devices/sst25l.c
@@ -175,9 +175,6 @@ static int sst25l_erase(struct mtd_info *mtd, struct erase_info *instr)
 	int err;
 
 	/* Sanity checks */
-	if (instr->addr + instr->len > flash->mtd.size)
-		return -EINVAL;
-
 	if ((uint32_t)instr->len % mtd->erasesize)
 		return -EINVAL;
 
@@ -223,16 +220,6 @@ static int sst25l_read(struct mtd_info *mtd, loff_t from, size_t len,
 	unsigned char command[4];
 	int ret;
 
-	/* Sanity checking */
-	if (len == 0)
-		return 0;
-
-	if (from + len > flash->mtd.size)
-		return -EINVAL;
-
-	if (retlen)
-		*retlen = 0;
-
 	spi_message_init(&message);
 	memset(&transfer, 0, sizeof(transfer));
 
@@ -274,13 +261,6 @@ static int sst25l_write(struct mtd_info *mtd, loff_t to, size_t len,
 	int i, j, ret, bytes, copied = 0;
 	unsigned char command[5];
 
-	/* Sanity checks */
-	if (!len)
-		return 0;
-
-	if (to + len > flash->mtd.size)
-		return -EINVAL;
-
 	if ((uint32_t)to % mtd->writesize)
 		return -EINVAL;
 
@@ -402,10 +382,11 @@ static int __devinit sst25l_probe(struct spi_device *spi)
 	flash->mtd.flags	= MTD_CAP_NORFLASH;
 	flash->mtd.erasesize	= flash_info->erase_size;
 	flash->mtd.writesize	= flash_info->page_size;
+	flash->mtd.writebufsize	= flash_info->page_size;
 	flash->mtd.size		= flash_info->page_size * flash_info->nr_pages;
-	flash->mtd.erase	= sst25l_erase;
-	flash->mtd.read		= sst25l_read;
-	flash->mtd.write 	= sst25l_write;
+	flash->mtd._erase	= sst25l_erase;
+	flash->mtd._read		= sst25l_read;
+	flash->mtd._write 	= sst25l_write;
 
 	dev_info(&spi->dev, "%s (%lld KiB)\n", flash_info->name,
 		 (long long)flash->mtd.size >> 10);
@@ -418,9 +399,9 @@ static int __devinit sst25l_probe(struct spi_device *spi)
 	      flash->mtd.numeraseregions);
 
 
-	ret = mtd_device_parse_register(&flash->mtd, NULL, 0,
-			data ? data->parts : NULL,
-			data ? data->nr_parts : 0);
+	ret = mtd_device_parse_register(&flash->mtd, NULL, NULL,
+					data ? data->parts : NULL,
+					data ? data->nr_parts : 0);
 	if (ret) {
 		kfree(flash);
 		dev_set_drvdata(&spi->dev, NULL);
@@ -450,18 +431,7 @@ static struct spi_driver sst25l_driver = {
 	.remove		= __devexit_p(sst25l_remove),
 };
 
-static int __init sst25l_init(void)
-{
-	return spi_register_driver(&sst25l_driver);
-}
-
-static void __exit sst25l_exit(void)
-{
-	spi_unregister_driver(&sst25l_driver);
-}
-
-module_init(sst25l_init);
-module_exit(sst25l_exit);
+module_spi_driver(sst25l_driver);
 
 MODULE_DESCRIPTION("MTD SPI driver for SST25L Flash chips");
 MODULE_AUTHOR("Andre Renaud <andre@bluewatersys.com>, "
diff --git a/drivers/mtd/inftlcore.c b/drivers/mtd/inftlcore.c
index 28646c95cfb8..3af351484098 100644
--- a/drivers/mtd/inftlcore.c
+++ b/drivers/mtd/inftlcore.c
@@ -56,7 +56,7 @@ static void inftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 	if (memcmp(mtd->name, "DiskOnChip", 10))
 		return;
 
-	if (!mtd->block_isbad) {
+	if (!mtd->_block_isbad) {
 		printk(KERN_ERR
 "INFTL no longer supports the old DiskOnChip drivers loaded via docprobe.\n"
 "Please use the new diskonchip driver under the NAND subsystem.\n");
diff --git a/drivers/mtd/lpddr/lpddr_cmds.c b/drivers/mtd/lpddr/lpddr_cmds.c
index 536bbceaeaad..d3cfe26beeaa 100644
--- a/drivers/mtd/lpddr/lpddr_cmds.c
+++ b/drivers/mtd/lpddr/lpddr_cmds.c
@@ -40,7 +40,7 @@ static int lpddr_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len);
 static int lpddr_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len);
 static int lpddr_point(struct mtd_info *mtd, loff_t adr, size_t len,
 			size_t *retlen, void **mtdbuf, resource_size_t *phys);
-static void lpddr_unpoint(struct mtd_info *mtd, loff_t adr, size_t len);
+static int lpddr_unpoint(struct mtd_info *mtd, loff_t adr, size_t len);
 static int get_chip(struct map_info *map, struct flchip *chip, int mode);
 static int chip_ready(struct map_info *map, struct flchip *chip, int mode);
 static void put_chip(struct map_info *map, struct flchip *chip);
@@ -63,18 +63,18 @@ struct mtd_info *lpddr_cmdset(struct map_info *map)
 	mtd->type = MTD_NORFLASH;
 
 	/* Fill in the default mtd operations */
-	mtd->read = lpddr_read;
+	mtd->_read = lpddr_read;
 	mtd->type = MTD_NORFLASH;
 	mtd->flags = MTD_CAP_NORFLASH;
 	mtd->flags &= ~MTD_BIT_WRITEABLE;
-	mtd->erase = lpddr_erase;
-	mtd->write = lpddr_write_buffers;
-	mtd->writev = lpddr_writev;
-	mtd->lock = lpddr_lock;
-	mtd->unlock = lpddr_unlock;
+	mtd->_erase = lpddr_erase;
+	mtd->_write = lpddr_write_buffers;
+	mtd->_writev = lpddr_writev;
+	mtd->_lock = lpddr_lock;
+	mtd->_unlock = lpddr_unlock;
 	if (map_is_linear(map)) {
-		mtd->point = lpddr_point;
-		mtd->unpoint = lpddr_unpoint;
+		mtd->_point = lpddr_point;
+		mtd->_unpoint = lpddr_unpoint;
 	}
 	mtd->size = 1 << lpddr->qinfo->DevSizeShift;
 	mtd->erasesize = 1 << lpddr->qinfo->UniformBlockSizeShift;
@@ -530,14 +530,12 @@ static int lpddr_point(struct mtd_info *mtd, loff_t adr, size_t len,
 	struct flchip *chip = &lpddr->chips[chipnum];
 	int ret = 0;
 
-	if (!map->virt || (adr + len > mtd->size))
+	if (!map->virt)
 		return -EINVAL;
 
 	/* ofs: offset within the first chip that the first read should start */
 	ofs = adr - (chipnum << lpddr->chipshift);
-
 	*mtdbuf = (void *)map->virt + chip->start + ofs;
-	*retlen = 0;
 
 	while (len) {
 		unsigned long thislen;
@@ -575,11 +573,11 @@ static int lpddr_point(struct mtd_info *mtd, loff_t adr, size_t len,
 	return 0;
 }
 
-static void lpddr_unpoint (struct mtd_info *mtd, loff_t adr, size_t len)
+static int lpddr_unpoint (struct mtd_info *mtd, loff_t adr, size_t len)
 {
 	struct map_info *map = mtd->priv;
 	struct lpddr_private *lpddr = map->fldrv_priv;
-	int chipnum = adr >> lpddr->chipshift;
+	int chipnum = adr >> lpddr->chipshift, err = 0;
 	unsigned long ofs;
 
 	/* ofs: offset within the first chip that the first read should start */
@@ -603,9 +601,11 @@ static void lpddr_unpoint (struct mtd_info *mtd, loff_t adr, size_t len)
 			chip->ref_point_counter--;
 			if (chip->ref_point_counter == 0)
 				chip->state = FL_READY;
-		} else
+		} else {
 			printk(KERN_WARNING "%s: Warning: unpoint called on non"
 					"pointed region\n", map->name);
+			err = -EINVAL;
+		}
 
 		put_chip(map, chip);
 		mutex_unlock(&chip->mutex);
@@ -614,6 +614,8 @@ static void lpddr_unpoint (struct mtd_info *mtd, loff_t adr, size_t len)
 		ofs = 0;
 		chipnum++;
 	}
+
+	return err;
 }
 
 static int lpddr_write_buffers(struct mtd_info *mtd, loff_t to, size_t len,
@@ -637,13 +639,11 @@ static int lpddr_writev(struct mtd_info *mtd, const struct kvec *vecs,
 	int chipnum;
 	unsigned long ofs, vec_seek, i;
 	int wbufsize = 1 << lpddr->qinfo->BufSizeShift;
-
 	size_t len = 0;
 
 	for (i = 0; i < count; i++)
 		len += vecs[i].iov_len;
 
-	*retlen = 0;
 	if (!len)
 		return 0;
 
@@ -688,9 +688,6 @@ static int lpddr_erase(struct mtd_info *mtd, struct erase_info *instr)
 	ofs = instr->addr;
 	len = instr->len;
 
-	if (ofs > mtd->size || (len + ofs) > mtd->size)
-		return -EINVAL;
-
 	while (len > 0) {
 		ret = do_erase_oneblock(mtd, ofs);
 		if (ret)
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index 6c5c431c64af..8af67cfd671a 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -1,5 +1,6 @@
 menu "Mapping drivers for chip access"
 	depends on MTD!=n
+	depends on HAS_IOMEM
 
 config MTD_COMPLEX_MAPPINGS
 	bool "Support non-linear mappings of flash chips"
diff --git a/drivers/mtd/maps/bfin-async-flash.c b/drivers/mtd/maps/bfin-async-flash.c
index 650126c361f1..ef5cde84a8b3 100644
--- a/drivers/mtd/maps/bfin-async-flash.c
+++ b/drivers/mtd/maps/bfin-async-flash.c
@@ -164,8 +164,8 @@ static int __devinit bfin_flash_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	mtd_device_parse_register(state->mtd, part_probe_types, 0,
-			pdata->parts, pdata->nr_parts);
+	mtd_device_parse_register(state->mtd, part_probe_types, NULL,
+				  pdata->parts, pdata->nr_parts);
 
 	platform_set_drvdata(pdev, state);
 
diff --git a/drivers/mtd/maps/dc21285.c b/drivers/mtd/maps/dc21285.c
index f43b365b848c..080f06053bd4 100644
--- a/drivers/mtd/maps/dc21285.c
+++ b/drivers/mtd/maps/dc21285.c
@@ -196,7 +196,7 @@ static int __init init_dc21285(void)
 
 	dc21285_mtd->owner = THIS_MODULE;
 
-	mtd_device_parse_register(dc21285_mtd, probes, 0, NULL, 0);
+	mtd_device_parse_register(dc21285_mtd, probes, NULL, NULL, 0);
 
 	if(machine_is_ebsa285()) {
 		/*
diff --git a/drivers/mtd/maps/gpio-addr-flash.c b/drivers/mtd/maps/gpio-addr-flash.c
index 33cce895859f..e4de96ba52b3 100644
--- a/drivers/mtd/maps/gpio-addr-flash.c
+++ b/drivers/mtd/maps/gpio-addr-flash.c
@@ -252,8 +252,8 @@ static int __devinit gpio_flash_probe(struct platform_device *pdev)
 	}
 
 
-	mtd_device_parse_register(state->mtd, part_probe_types, 0,
-			pdata->parts, pdata->nr_parts);
+	mtd_device_parse_register(state->mtd, part_probe_types, NULL,
+				  pdata->parts, pdata->nr_parts);
 
 	return 0;
 }
diff --git a/drivers/mtd/maps/h720x-flash.c b/drivers/mtd/maps/h720x-flash.c
index 49c14187fc66..8ed6cb4529d8 100644
--- a/drivers/mtd/maps/h720x-flash.c
+++ b/drivers/mtd/maps/h720x-flash.c
@@ -85,8 +85,8 @@ static int __init h720x_mtd_init(void)
 	if (mymtd) {
 		mymtd->owner = THIS_MODULE;
 
-		mtd_device_parse_register(mymtd, NULL, 0,
-				h720x_partitions, NUM_PARTITIONS);
+		mtd_device_parse_register(mymtd, NULL, NULL,
+					  h720x_partitions, NUM_PARTITIONS);
 		return 0;
 	}
 
diff --git a/drivers/mtd/maps/impa7.c b/drivers/mtd/maps/impa7.c
index f47aedb24366..834a06c56f56 100644
--- a/drivers/mtd/maps/impa7.c
+++ b/drivers/mtd/maps/impa7.c
@@ -91,7 +91,7 @@ static int __init init_impa7(void)
 		if (impa7_mtd[i]) {
 			impa7_mtd[i]->owner = THIS_MODULE;
 			devicesfound++;
-			mtd_device_parse_register(impa7_mtd[i], NULL, 0,
+			mtd_device_parse_register(impa7_mtd[i], NULL, NULL,
 						  partitions,
 						  ARRAY_SIZE(partitions));
 		}
diff --git a/drivers/mtd/maps/intel_vr_nor.c b/drivers/mtd/maps/intel_vr_nor.c
index 08c239604ee4..92e1f41634c7 100644
--- a/drivers/mtd/maps/intel_vr_nor.c
+++ b/drivers/mtd/maps/intel_vr_nor.c
@@ -72,7 +72,7 @@ static int __devinit vr_nor_init_partitions(struct vr_nor_mtd *p)
 {
 	/* register the flash bank */
 	/* partition the flash bank */
-	return mtd_device_parse_register(p->info, NULL, 0, NULL, 0);
+	return mtd_device_parse_register(p->info, NULL, NULL, NULL, 0);
 }
 
 static void __devexit vr_nor_destroy_mtd_setup(struct vr_nor_mtd *p)
diff --git a/drivers/mtd/maps/ixp2000.c b/drivers/mtd/maps/ixp2000.c
index fc7d4d0d9a4e..4a41ced0f710 100644
--- a/drivers/mtd/maps/ixp2000.c
+++ b/drivers/mtd/maps/ixp2000.c
@@ -226,7 +226,7 @@ static int ixp2000_flash_probe(struct platform_device *dev)
 	}
 	info->mtd->owner = THIS_MODULE;
 
-	err = mtd_device_parse_register(info->mtd, probes, 0, NULL, 0);
+	err = mtd_device_parse_register(info->mtd, probes, NULL, NULL, 0);
 	if (err)
 		goto Error;
 
diff --git a/drivers/mtd/maps/ixp4xx.c b/drivers/mtd/maps/ixp4xx.c
index 8b5410162d70..e864fc6c58f9 100644
--- a/drivers/mtd/maps/ixp4xx.c
+++ b/drivers/mtd/maps/ixp4xx.c
@@ -182,6 +182,9 @@ static int ixp4xx_flash_probe(struct platform_device *dev)
 {
 	struct flash_platform_data *plat = dev->dev.platform_data;
 	struct ixp4xx_flash_info *info;
+	struct mtd_part_parser_data ppdata = {
+		.origin = dev->resource->start,
+	};
 	int err = -1;
 
 	if (!plat)
@@ -247,7 +250,7 @@ static int ixp4xx_flash_probe(struct platform_device *dev)
 	/* Use the fast version */
 	info->map.write = ixp4xx_write16;
 
-	err = mtd_device_parse_register(info->mtd, probes, dev->resource->start,
+	err = mtd_device_parse_register(info->mtd, probes, &ppdata,
 			plat->parts, plat->nr_parts);
 	if (err) {
 		printk(KERN_ERR "Could not parse partitions\n");
diff --git a/drivers/mtd/maps/l440gx.c b/drivers/mtd/maps/l440gx.c
index dd0360ba2412..74bd98ee635f 100644
--- a/drivers/mtd/maps/l440gx.c
+++ b/drivers/mtd/maps/l440gx.c
@@ -27,17 +27,21 @@ static struct mtd_info *mymtd;
 
 
 /* Is this really the vpp port? */
+static DEFINE_SPINLOCK(l440gx_vpp_lock);
+static int l440gx_vpp_refcnt;
 static void l440gx_set_vpp(struct map_info *map, int vpp)
 {
-	unsigned long l;
+	unsigned long flags;
 
-	l = inl(VPP_PORT);
+	spin_lock_irqsave(&l440gx_vpp_lock, flags);
 	if (vpp) {
-		l |= 1;
+		if (++l440gx_vpp_refcnt == 1)   /* first nested 'on' */
+			outl(inl(VPP_PORT) | 1, VPP_PORT);
 	} else {
-		l &= ~1;
+		if (--l440gx_vpp_refcnt == 0)   /* last nested 'off' */
+			outl(inl(VPP_PORT) & ~1, VPP_PORT);
 	}
-	outl(l, VPP_PORT);
+	spin_unlock_irqrestore(&l440gx_vpp_lock, flags);
 }
 
 static struct map_info l440gx_map = {
diff --git a/drivers/mtd/maps/lantiq-flash.c b/drivers/mtd/maps/lantiq-flash.c
index 7b889de9477b..b5401e355745 100644
--- a/drivers/mtd/maps/lantiq-flash.c
+++ b/drivers/mtd/maps/lantiq-flash.c
@@ -45,6 +45,7 @@ struct ltq_mtd {
 };
 
 static char ltq_map_name[] = "ltq_nor";
+static const char *ltq_probe_types[] __devinitconst = { "cmdlinepart", NULL };
 
 static map_word
 ltq_read16(struct map_info *map, unsigned long adr)
@@ -168,8 +169,9 @@ ltq_mtd_probe(struct platform_device *pdev)
 	cfi->addr_unlock1 ^= 1;
 	cfi->addr_unlock2 ^= 1;
 
-	err = mtd_device_parse_register(ltq_mtd->mtd, NULL, 0,
-			ltq_mtd_data->parts, ltq_mtd_data->nr_parts);
+	err = mtd_device_parse_register(ltq_mtd->mtd, ltq_probe_types, NULL,
+					ltq_mtd_data->parts,
+					ltq_mtd_data->nr_parts);
 	if (err) {
 		dev_err(&pdev->dev, "failed to add partitions\n");
 		goto err_destroy;
diff --git a/drivers/mtd/maps/latch-addr-flash.c b/drivers/mtd/maps/latch-addr-flash.c
index 8fed58e3a4a8..3c7ad17fca78 100644
--- a/drivers/mtd/maps/latch-addr-flash.c
+++ b/drivers/mtd/maps/latch-addr-flash.c
@@ -199,8 +199,9 @@ static int __devinit latch_addr_flash_probe(struct platform_device *dev)
 	}
 	info->mtd->owner = THIS_MODULE;
 
-	mtd_device_parse_register(info->mtd, NULL, 0,
-			latch_addr_data->parts, latch_addr_data->nr_parts);
+	mtd_device_parse_register(info->mtd, NULL, NULL,
+				  latch_addr_data->parts,
+				  latch_addr_data->nr_parts);
 	return 0;
 
 iounmap:
diff --git a/drivers/mtd/maps/pcmciamtd.c b/drivers/mtd/maps/pcmciamtd.c
index e8e9fec23553..a3cfad392ed6 100644
--- a/drivers/mtd/maps/pcmciamtd.c
+++ b/drivers/mtd/maps/pcmciamtd.c
@@ -14,7 +14,6 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
@@ -295,13 +294,24 @@ static void pcmcia_copy_to(struct map_info *map, unsigned long to, const void *f
 }
 
 
+static DEFINE_SPINLOCK(pcmcia_vpp_lock);
+static int pcmcia_vpp_refcnt;
 static void pcmciamtd_set_vpp(struct map_info *map, int on)
 {
 	struct pcmciamtd_dev *dev = (struct pcmciamtd_dev *)map->map_priv_1;
 	struct pcmcia_device *link = dev->p_dev;
+	unsigned long flags;
 
 	pr_debug("dev = %p on = %d vpp = %d\n\n", dev, on, dev->vpp);
-	pcmcia_fixup_vpp(link, on ? dev->vpp : 0);
+	spin_lock_irqsave(&pcmcia_vpp_lock, flags);
+	if (on) {
+		if (++pcmcia_vpp_refcnt == 1)   /* first nested 'on' */
+			pcmcia_fixup_vpp(link, dev->vpp);
+	} else {
+		if (--pcmcia_vpp_refcnt == 0)   /* last nested 'off' */
+			pcmcia_fixup_vpp(link, 0);
+	}
+	spin_unlock_irqrestore(&pcmcia_vpp_lock, flags);
 }
 
 
diff --git a/drivers/mtd/maps/physmap.c b/drivers/mtd/maps/physmap.c
index abc562653b31..21b0b713cacb 100644
--- a/drivers/mtd/maps/physmap.c
+++ b/drivers/mtd/maps/physmap.c
@@ -27,6 +27,8 @@ struct physmap_flash_info {
 	struct mtd_info		*mtd[MAX_RESOURCES];
 	struct mtd_info		*cmtd;
 	struct map_info		map[MAX_RESOURCES];
+	spinlock_t		vpp_lock;
+	int			vpp_refcnt;
 };
 
 static int physmap_flash_remove(struct platform_device *dev)
@@ -63,12 +65,26 @@ static void physmap_set_vpp(struct map_info *map, int state)
 {
 	struct platform_device *pdev;
 	struct physmap_flash_data *physmap_data;
+	struct physmap_flash_info *info;
+	unsigned long flags;
 
 	pdev = (struct platform_device *)map->map_priv_1;
 	physmap_data = pdev->dev.platform_data;
 
-	if (physmap_data->set_vpp)
-		physmap_data->set_vpp(pdev, state);
+	if (!physmap_data->set_vpp)
+		return;
+
+	info = platform_get_drvdata(pdev);
+
+	spin_lock_irqsave(&info->vpp_lock, flags);
+	if (state) {
+		if (++info->vpp_refcnt == 1)    /* first nested 'on' */
+			physmap_data->set_vpp(pdev, 1);
+	} else {
+		if (--info->vpp_refcnt == 0)    /* last nested 'off' */
+			physmap_data->set_vpp(pdev, 0);
+	}
+	spin_unlock_irqrestore(&info->vpp_lock, flags);
 }
 
 static const char *rom_probe_types[] = {
@@ -172,9 +188,11 @@ static int physmap_flash_probe(struct platform_device *dev)
 	if (err)
 		goto err_out;
 
+	spin_lock_init(&info->vpp_lock);
+
 	part_types = physmap_data->part_probe_types ? : part_probe_types;
 
-	mtd_device_parse_register(info->cmtd, part_types, 0,
+	mtd_device_parse_register(info->cmtd, part_types, NULL,
 				  physmap_data->parts, physmap_data->nr_parts);
 	return 0;
 
diff --git a/drivers/mtd/maps/plat-ram.c b/drivers/mtd/maps/plat-ram.c
index 45876d0e5b8e..891558de3ec1 100644
--- a/drivers/mtd/maps/plat-ram.c
+++ b/drivers/mtd/maps/plat-ram.c
@@ -222,8 +222,9 @@ static int platram_probe(struct platform_device *pdev)
 	/* check to see if there are any available partitions, or wether
 	 * to add this device whole */
 
-	err = mtd_device_parse_register(info->mtd, pdata->probes, 0,
-			pdata->partitions, pdata->nr_partitions);
+	err = mtd_device_parse_register(info->mtd, pdata->probes, NULL,
+					pdata->partitions,
+					pdata->nr_partitions);
 	if (!err)
 		dev_info(&pdev->dev, "registered mtd device\n");
 
diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c
index 436d121185b1..81884c277405 100644
--- a/drivers/mtd/maps/pxa2xx-flash.c
+++ b/drivers/mtd/maps/pxa2xx-flash.c
@@ -98,7 +98,8 @@ static int __devinit pxa2xx_flash_probe(struct platform_device *pdev)
 	}
 	info->mtd->owner = THIS_MODULE;
 
-	mtd_device_parse_register(info->mtd, probes, 0, flash->parts, flash->nr_parts);
+	mtd_device_parse_register(info->mtd, probes, NULL, flash->parts,
+				  flash->nr_parts);
 
 	platform_set_drvdata(pdev, info);
 	return 0;
diff --git a/drivers/mtd/maps/rbtx4939-flash.c b/drivers/mtd/maps/rbtx4939-flash.c
index 3da63fc6f16e..6f52e1f288b6 100644
--- a/drivers/mtd/maps/rbtx4939-flash.c
+++ b/drivers/mtd/maps/rbtx4939-flash.c
@@ -102,8 +102,8 @@ static int rbtx4939_flash_probe(struct platform_device *dev)
 	info->mtd->owner = THIS_MODULE;
 	if (err)
 		goto err_out;
-	err = mtd_device_parse_register(info->mtd, NULL, 0,
-			pdata->parts, pdata->nr_parts);
+	err = mtd_device_parse_register(info->mtd, NULL, NULL, pdata->parts,
+					pdata->nr_parts);
 
 	if (err)
 		goto err_out;
diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c
index 502821997707..a675bdbcb0fe 100644
--- a/drivers/mtd/maps/sa1100-flash.c
+++ b/drivers/mtd/maps/sa1100-flash.c
@@ -23,106 +23,6 @@
 #include <asm/sizes.h>
 #include <asm/mach/flash.h>
 
-#if 0
-/*
- * This is here for documentation purposes only - until these people
- * submit their machine types.  It will be gone January 2005.
- */
-static struct mtd_partition consus_partitions[] = {
-	{
-		.name		= "Consus boot firmware",
-		.offset		= 0,
-		.size		= 0x00040000,
-		.mask_flags	= MTD_WRITABLE, /* force read-only */
-	}, {
-		.name		= "Consus kernel",
-		.offset		= 0x00040000,
-		.size		= 0x00100000,
-		.mask_flags	= 0,
-	}, {
-		.name		= "Consus disk",
-		.offset		= 0x00140000,
-		/* The rest (up to 16M) for jffs.  We could put 0 and
-		   make it find the size automatically, but right now
-		   i have 32 megs.  jffs will use all 32 megs if given
-		   the chance, and this leads to horrible problems
-		   when you try to re-flash the image because blob
-		   won't erase the whole partition. */
-		.size		= 0x01000000 - 0x00140000,
-		.mask_flags	= 0,
-	}, {
-		/* this disk is a secondary disk, which can be used as
-		   needed, for simplicity, make it the size of the other
-		   consus partition, although realistically it could be
-		   the remainder of the disk (depending on the file
-		   system used) */
-		 .name		= "Consus disk2",
-		 .offset	= 0x01000000,
-		 .size		= 0x01000000 - 0x00140000,
-		 .mask_flags	= 0,
-	}
-};
-
-/* Frodo has 2 x 16M 28F128J3A flash chips in bank 0: */
-static struct mtd_partition frodo_partitions[] =
-{
-	{
-		.name		= "bootloader",
-		.size		= 0x00040000,
-		.offset		= 0x00000000,
-		.mask_flags	= MTD_WRITEABLE
-	}, {
-		.name		= "bootloader params",
-		.size		= 0x00040000,
-		.offset		= MTDPART_OFS_APPEND,
-		.mask_flags	= MTD_WRITEABLE
-	}, {
-		.name		= "kernel",
-		.size		= 0x00100000,
-		.offset		= MTDPART_OFS_APPEND,
-		.mask_flags	= MTD_WRITEABLE
-	}, {
-		.name		= "ramdisk",
-		.size		= 0x00400000,
-		.offset		= MTDPART_OFS_APPEND,
-		.mask_flags	= MTD_WRITEABLE
-	}, {
-		.name		= "file system",
-		.size		= MTDPART_SIZ_FULL,
-		.offset		= MTDPART_OFS_APPEND
-	}
-};
-
-static struct mtd_partition jornada56x_partitions[] = {
-	{
-		.name		= "bootldr",
-		.size		= 0x00040000,
-		.offset		= 0,
-		.mask_flags	= MTD_WRITEABLE,
-	}, {
-		.name		= "rootfs",
-		.size		= MTDPART_SIZ_FULL,
-		.offset		= MTDPART_OFS_APPEND,
-	}
-};
-
-static void jornada56x_set_vpp(int vpp)
-{
-	if (vpp)
-		GPSR = GPIO_GPIO26;
-	else
-		GPCR = GPIO_GPIO26;
-	GPDR |= GPIO_GPIO26;
-}
-
-/*
- * Machine        Phys          Size    set_vpp
- * Consus    : SA1100_CS0_PHYS SZ_32M
- * Frodo     : SA1100_CS0_PHYS SZ_32M
- * Jornada56x: SA1100_CS0_PHYS SZ_32M jornada56x_set_vpp
- */
-#endif
-
 struct sa_subdev_info {
 	char name[16];
 	struct map_info map;
@@ -136,10 +36,22 @@ struct sa_info {
 	struct sa_subdev_info	subdev[0];
 };
 
+static DEFINE_SPINLOCK(sa1100_vpp_lock);
+static int sa1100_vpp_refcnt;
 static void sa1100_set_vpp(struct map_info *map, int on)
 {
 	struct sa_subdev_info *subdev = container_of(map, struct sa_subdev_info, map);
-	subdev->plat->set_vpp(on);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sa1100_vpp_lock, flags);
+	if (on) {
+		if (++sa1100_vpp_refcnt == 1)   /* first nested 'on' */
+			subdev->plat->set_vpp(1);
+	} else {
+		if (--sa1100_vpp_refcnt == 0)   /* last nested 'off' */
+			subdev->plat->set_vpp(0);
+	}
+	spin_unlock_irqrestore(&sa1100_vpp_lock, flags);
 }
 
 static void sa1100_destroy_subdev(struct sa_subdev_info *subdev)
@@ -352,8 +264,8 @@ static int __devinit sa1100_mtd_probe(struct platform_device *pdev)
 	/*
 	 * Partition selection stuff.
 	 */
-	mtd_device_parse_register(info->mtd, part_probes, 0,
-			plat->parts, plat->nr_parts);
+	mtd_device_parse_register(info->mtd, part_probes, NULL, plat->parts,
+				  plat->nr_parts);
 
 	platform_set_drvdata(pdev, info);
 	err = 0;
@@ -373,21 +285,9 @@ static int __exit sa1100_mtd_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static void sa1100_mtd_shutdown(struct platform_device *dev)
-{
-	struct sa_info *info = platform_get_drvdata(dev);
-	if (info && mtd_suspend(info->mtd) == 0)
-		mtd_resume(info->mtd);
-}
-#else
-#define sa1100_mtd_shutdown NULL
-#endif
-
 static struct platform_driver sa1100_mtd_driver = {
 	.probe		= sa1100_mtd_probe,
 	.remove		= __exit_p(sa1100_mtd_remove),
-	.shutdown	= sa1100_mtd_shutdown,
 	.driver		= {
 		.name	= "sa1100-mtd",
 		.owner	= THIS_MODULE,
diff --git a/drivers/mtd/maps/solutionengine.c b/drivers/mtd/maps/solutionengine.c
index 496c40704aff..9d900ada6708 100644
--- a/drivers/mtd/maps/solutionengine.c
+++ b/drivers/mtd/maps/solutionengine.c
@@ -92,8 +92,8 @@ static int __init init_soleng_maps(void)
 		mtd_device_register(eprom_mtd, NULL, 0);
 	}
 
-	mtd_device_parse_register(flash_mtd, probes, 0,
-			superh_se_partitions, NUM_PARTITIONS);
+	mtd_device_parse_register(flash_mtd, probes, NULL,
+				  superh_se_partitions, NUM_PARTITIONS);
 
 	return 0;
 }
diff --git a/drivers/mtd/maps/uclinux.c b/drivers/mtd/maps/uclinux.c
index 6793074f3f40..cfff454f628b 100644
--- a/drivers/mtd/maps/uclinux.c
+++ b/drivers/mtd/maps/uclinux.c
@@ -85,7 +85,7 @@ static int __init uclinux_mtd_init(void)
 	}
 
 	mtd->owner = THIS_MODULE;
-	mtd->point = uclinux_point;
+	mtd->_point = uclinux_point;
 	mtd->priv = mapp;
 
 	uclinux_ram_mtdinfo = mtd;
diff --git a/drivers/mtd/maps/vmu-flash.c b/drivers/mtd/maps/vmu-flash.c
index 3a04b078576a..2e2b0945edc7 100644
--- a/drivers/mtd/maps/vmu-flash.c
+++ b/drivers/mtd/maps/vmu-flash.c
@@ -360,9 +360,6 @@ static int vmu_flash_read(struct mtd_info *mtd, loff_t from, size_t len,
 	int index = 0, retval, partition, leftover, numblocks;
 	unsigned char cx;
 
-	if (len < 1)
-		return -EIO;
-
 	mpart = mtd->priv;
 	mdev = mpart->mdev;
 	partition = mpart->partition;
@@ -434,11 +431,6 @@ static int vmu_flash_write(struct mtd_info *mtd, loff_t to, size_t len,
 	partition = mpart->partition;
 	card = maple_get_drvdata(mdev);
 
-	/* simple sanity checks */
-	if (len < 1) {
-		error = -EIO;
-		goto failed;
-	}
 	numblocks = card->parts[partition].numblocks;
 	if (to + len > numblocks * card->blocklen)
 		len = numblocks * card->blocklen - to;
@@ -544,9 +536,9 @@ static void vmu_queryblocks(struct mapleq *mq)
 	mtd_cur->flags = MTD_WRITEABLE|MTD_NO_ERASE;
 	mtd_cur->size = part_cur->numblocks * card->blocklen;
 	mtd_cur->erasesize = card->blocklen;
-	mtd_cur->write = vmu_flash_write;
-	mtd_cur->read = vmu_flash_read;
-	mtd_cur->sync = vmu_flash_sync;
+	mtd_cur->_write = vmu_flash_write;
+	mtd_cur->_read = vmu_flash_read;
+	mtd_cur->_sync = vmu_flash_sync;
 	mtd_cur->writesize = card->blocklen;
 
 	mpart = kmalloc(sizeof(struct mdev_part), GFP_KERNEL);
diff --git a/drivers/mtd/maps/wr_sbc82xx_flash.c b/drivers/mtd/maps/wr_sbc82xx_flash.c
index aa7e0cb2893c..71b0ba797912 100644
--- a/drivers/mtd/maps/wr_sbc82xx_flash.c
+++ b/drivers/mtd/maps/wr_sbc82xx_flash.c
@@ -142,7 +142,7 @@ static int __init init_sbc82xx_flash(void)
 			nr_parts = ARRAY_SIZE(smallflash_parts);
 		}
 
-		mtd_device_parse_register(sbcmtd[i], part_probes, 0,
+		mtd_device_parse_register(sbcmtd[i], part_probes, NULL,
 					  defparts, nr_parts);
 	}
 	return 0;
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 424ca5f93c6c..f1f06715d4e0 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -233,6 +233,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 	ret = __get_mtd_device(dev->mtd);
 	if (ret)
 		goto error_release;
+	dev->file_mode = mode;
 
 unlock:
 	dev->open++;
diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c
index af6591237b9b..6c6d80736fad 100644
--- a/drivers/mtd/mtdblock.c
+++ b/drivers/mtd/mtdblock.c
@@ -321,8 +321,12 @@ static int mtdblock_release(struct mtd_blktrans_dev *mbd)
 	mutex_unlock(&mtdblk->cache_mutex);
 
 	if (!--mtdblk->count) {
-		/* It was the last usage. Free the cache */
-		mtd_sync(mbd->mtd);
+		/*
+		 * It was the last usage. Free the cache, but only sync if
+		 * opened for writing.
+		 */
+		if (mbd->file_mode & FMODE_WRITE)
+			mtd_sync(mbd->mtd);
 		vfree(mtdblk->cache_data);
 	}
 
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index c57ae92ebda4..94eb05b1afdf 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -39,7 +39,6 @@
 #include <asm/uaccess.h>
 
 static DEFINE_MUTEX(mtd_mutex);
-static struct vfsmount *mtd_inode_mnt __read_mostly;
 
 /*
  * Data structure to hold the pointer to the mtd device as well
@@ -75,7 +74,9 @@ static loff_t mtdchar_lseek(struct file *file, loff_t offset, int orig)
 	return -EINVAL;
 }
 
-
+static int count;
+static struct vfsmount *mnt;
+static struct file_system_type mtd_inodefs_type;
 
 static int mtdchar_open(struct inode *inode, struct file *file)
 {
@@ -92,6 +93,10 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 	if ((file->f_mode & FMODE_WRITE) && (minor & 1))
 		return -EACCES;
 
+	ret = simple_pin_fs(&mtd_inodefs_type, &mnt, &count);
+	if (ret)
+		return ret;
+
 	mutex_lock(&mtd_mutex);
 	mtd = get_mtd_device(NULL, devnum);
 
@@ -106,7 +111,7 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 		goto out;
 	}
 
-	mtd_ino = iget_locked(mtd_inode_mnt->mnt_sb, devnum);
+	mtd_ino = iget_locked(mnt->mnt_sb, devnum);
 	if (!mtd_ino) {
 		put_mtd_device(mtd);
 		ret = -ENOMEM;
@@ -141,6 +146,7 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 
 out:
 	mutex_unlock(&mtd_mutex);
+	simple_release_fs(&mnt, &count);
 	return ret;
 } /* mtdchar_open */
 
@@ -162,6 +168,7 @@ static int mtdchar_close(struct inode *inode, struct file *file)
 	put_mtd_device(mtd);
 	file->private_data = NULL;
 	kfree(mfi);
+	simple_release_fs(&mnt, &count);
 
 	return 0;
 } /* mtdchar_close */
@@ -405,7 +412,7 @@ static int mtdchar_writeoob(struct file *file, struct mtd_info *mtd,
 	if (length > 4096)
 		return -EINVAL;
 
-	if (!mtd->write_oob)
+	if (!mtd->_write_oob)
 		ret = -EOPNOTSUPP;
 	else
 		ret = access_ok(VERIFY_READ, ptr, length) ? 0 : -EFAULT;
@@ -576,7 +583,7 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd,
 			!access_ok(VERIFY_READ, req.usr_data, req.len) ||
 			!access_ok(VERIFY_READ, req.usr_oob, req.ooblen))
 		return -EFAULT;
-	if (!mtd->write_oob)
+	if (!mtd->_write_oob)
 		return -EOPNOTSUPP;
 
 	ops.mode = req.mode;
@@ -1175,10 +1182,15 @@ static const struct file_operations mtd_fops = {
 #endif
 };
 
+static const struct super_operations mtd_ops = {
+	.drop_inode = generic_delete_inode,
+	.statfs = simple_statfs,
+};
+
 static struct dentry *mtd_inodefs_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
-	return mount_pseudo(fs_type, "mtd_inode:", NULL, NULL, MTD_INODE_FS_MAGIC);
+	return mount_pseudo(fs_type, "mtd_inode:", &mtd_ops, NULL, MTD_INODE_FS_MAGIC);
 }
 
 static struct file_system_type mtd_inodefs_type = {
@@ -1187,26 +1199,6 @@ static struct file_system_type mtd_inodefs_type = {
        .kill_sb = kill_anon_super,
 };
 
-static void mtdchar_notify_add(struct mtd_info *mtd)
-{
-}
-
-static void mtdchar_notify_remove(struct mtd_info *mtd)
-{
-	struct inode *mtd_ino = ilookup(mtd_inode_mnt->mnt_sb, mtd->index);
-
-	if (mtd_ino) {
-		/* Destroy the inode if it exists */
-		clear_nlink(mtd_ino);
-		iput(mtd_ino);
-	}
-}
-
-static struct mtd_notifier mtdchar_notifier = {
-	.add = mtdchar_notify_add,
-	.remove = mtdchar_notify_remove,
-};
-
 static int __init init_mtdchar(void)
 {
 	int ret;
@@ -1224,19 +1216,8 @@ static int __init init_mtdchar(void)
 		pr_notice("Can't register mtd_inodefs filesystem: %d\n", ret);
 		goto err_unregister_chdev;
 	}
-
-	mtd_inode_mnt = kern_mount(&mtd_inodefs_type);
-	if (IS_ERR(mtd_inode_mnt)) {
-		ret = PTR_ERR(mtd_inode_mnt);
-		pr_notice("Error mounting mtd_inodefs filesystem: %d\n", ret);
-		goto err_unregister_filesystem;
-	}
-	register_mtd_user(&mtdchar_notifier);
-
 	return ret;
 
-err_unregister_filesystem:
-	unregister_filesystem(&mtd_inodefs_type);
 err_unregister_chdev:
 	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 	return ret;
@@ -1244,8 +1225,6 @@ err_unregister_chdev:
 
 static void __exit cleanup_mtdchar(void)
 {
-	unregister_mtd_user(&mtdchar_notifier);
-	kern_unmount(mtd_inode_mnt);
 	unregister_filesystem(&mtd_inodefs_type);
 	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 }
diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index 1ed5103b219b..b9000563b9f4 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -72,8 +72,6 @@ concat_read(struct mtd_info *mtd, loff_t from, size_t len,
 	int ret = 0, err;
 	int i;
 
-	*retlen = 0;
-
 	for (i = 0; i < concat->num_subdev; i++) {
 		struct mtd_info *subdev = concat->subdev[i];
 		size_t size, retsize;
@@ -126,11 +124,6 @@ concat_write(struct mtd_info *mtd, loff_t to, size_t len,
 	int err = -EINVAL;
 	int i;
 
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-
-	*retlen = 0;
-
 	for (i = 0; i < concat->num_subdev; i++) {
 		struct mtd_info *subdev = concat->subdev[i];
 		size_t size, retsize;
@@ -145,11 +138,7 @@ concat_write(struct mtd_info *mtd, loff_t to, size_t len,
 		else
 			size = len;
 
-		if (!(subdev->flags & MTD_WRITEABLE))
-			err = -EROFS;
-		else
-			err = mtd_write(subdev, to, size, &retsize, buf);
-
+		err = mtd_write(subdev, to, size, &retsize, buf);
 		if (err)
 			break;
 
@@ -176,19 +165,10 @@ concat_writev(struct mtd_info *mtd, const struct kvec *vecs,
 	int i;
 	int err = -EINVAL;
 
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-
-	*retlen = 0;
-
 	/* Calculate total length of data */
 	for (i = 0; i < count; i++)
 		total_len += vecs[i].iov_len;
 
-	/* Do not allow write past end of device */
-	if ((to + total_len) > mtd->size)
-		return -EINVAL;
-
 	/* Check alignment */
 	if (mtd->writesize > 1) {
 		uint64_t __to = to;
@@ -224,12 +204,8 @@ concat_writev(struct mtd_info *mtd, const struct kvec *vecs,
 		old_iov_len = vecs_copy[entry_high].iov_len;
 		vecs_copy[entry_high].iov_len = size;
 
-		if (!(subdev->flags & MTD_WRITEABLE))
-			err = -EROFS;
-		else
-			err = mtd_writev(subdev, &vecs_copy[entry_low],
-					 entry_high - entry_low + 1, to,
-					 &retsize);
+		err = mtd_writev(subdev, &vecs_copy[entry_low],
+				 entry_high - entry_low + 1, to, &retsize);
 
 		vecs_copy[entry_high].iov_len = old_iov_len - size;
 		vecs_copy[entry_high].iov_base += size;
@@ -403,15 +379,6 @@ static int concat_erase(struct mtd_info *mtd, struct erase_info *instr)
 	uint64_t length, offset = 0;
 	struct erase_info *erase;
 
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-
-	if (instr->addr > concat->mtd.size)
-		return -EINVAL;
-
-	if (instr->len + instr->addr > concat->mtd.size)
-		return -EINVAL;
-
 	/*
 	 * Check for proper erase block alignment of the to-be-erased area.
 	 * It is easier to do this based on the super device's erase
@@ -459,8 +426,6 @@ static int concat_erase(struct mtd_info *mtd, struct erase_info *instr)
 			return -EINVAL;
 	}
 
-	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
-
 	/* make a local copy of instr to avoid modifying the caller's struct */
 	erase = kmalloc(sizeof (struct erase_info), GFP_KERNEL);
 
@@ -499,10 +464,6 @@ static int concat_erase(struct mtd_info *mtd, struct erase_info *instr)
 		else
 			erase->len = length;
 
-		if (!(subdev->flags & MTD_WRITEABLE)) {
-			err = -EROFS;
-			break;
-		}
 		length -= erase->len;
 		if ((err = concat_dev_erase(subdev, erase))) {
 			/* sanity check: should never happen since
@@ -538,9 +499,6 @@ static int concat_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct mtd_concat *concat = CONCAT(mtd);
 	int i, err = -EINVAL;
 
-	if ((len + ofs) > mtd->size)
-		return -EINVAL;
-
 	for (i = 0; i < concat->num_subdev; i++) {
 		struct mtd_info *subdev = concat->subdev[i];
 		uint64_t size;
@@ -575,9 +533,6 @@ static int concat_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct mtd_concat *concat = CONCAT(mtd);
 	int i, err = 0;
 
-	if ((len + ofs) > mtd->size)
-		return -EINVAL;
-
 	for (i = 0; i < concat->num_subdev; i++) {
 		struct mtd_info *subdev = concat->subdev[i];
 		uint64_t size;
@@ -650,9 +605,6 @@ static int concat_block_isbad(struct mtd_info *mtd, loff_t ofs)
 	if (!mtd_can_have_bb(concat->subdev[0]))
 		return res;
 
-	if (ofs > mtd->size)
-		return -EINVAL;
-
 	for (i = 0; i < concat->num_subdev; i++) {
 		struct mtd_info *subdev = concat->subdev[i];
 
@@ -673,12 +625,6 @@ static int concat_block_markbad(struct mtd_info *mtd, loff_t ofs)
 	struct mtd_concat *concat = CONCAT(mtd);
 	int i, err = -EINVAL;
 
-	if (!mtd_can_have_bb(concat->subdev[0]))
-		return 0;
-
-	if (ofs > mtd->size)
-		return -EINVAL;
-
 	for (i = 0; i < concat->num_subdev; i++) {
 		struct mtd_info *subdev = concat->subdev[i];
 
@@ -716,10 +662,6 @@ static unsigned long concat_get_unmapped_area(struct mtd_info *mtd,
 			continue;
 		}
 
-		/* we've found the subdev over which the mapping will reside */
-		if (offset + len > subdev->size)
-			return (unsigned long) -EINVAL;
-
 		return mtd_get_unmapped_area(subdev, len, offset, flags);
 	}
 
@@ -777,16 +719,16 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to c
 	concat->mtd.subpage_sft = subdev[0]->subpage_sft;
 	concat->mtd.oobsize = subdev[0]->oobsize;
 	concat->mtd.oobavail = subdev[0]->oobavail;
-	if (subdev[0]->writev)
-		concat->mtd.writev = concat_writev;
-	if (subdev[0]->read_oob)
-		concat->mtd.read_oob = concat_read_oob;
-	if (subdev[0]->write_oob)
-		concat->mtd.write_oob = concat_write_oob;
-	if (subdev[0]->block_isbad)
-		concat->mtd.block_isbad = concat_block_isbad;
-	if (subdev[0]->block_markbad)
-		concat->mtd.block_markbad = concat_block_markbad;
+	if (subdev[0]->_writev)
+		concat->mtd._writev = concat_writev;
+	if (subdev[0]->_read_oob)
+		concat->mtd._read_oob = concat_read_oob;
+	if (subdev[0]->_write_oob)
+		concat->mtd._write_oob = concat_write_oob;
+	if (subdev[0]->_block_isbad)
+		concat->mtd._block_isbad = concat_block_isbad;
+	if (subdev[0]->_block_markbad)
+		concat->mtd._block_markbad = concat_block_markbad;
 
 	concat->mtd.ecc_stats.badblocks = subdev[0]->ecc_stats.badblocks;
 
@@ -833,8 +775,8 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to c
 		if (concat->mtd.writesize   !=  subdev[i]->writesize ||
 		    concat->mtd.subpage_sft != subdev[i]->subpage_sft ||
 		    concat->mtd.oobsize    !=  subdev[i]->oobsize ||
-		    !concat->mtd.read_oob  != !subdev[i]->read_oob ||
-		    !concat->mtd.write_oob != !subdev[i]->write_oob) {
+		    !concat->mtd._read_oob  != !subdev[i]->_read_oob ||
+		    !concat->mtd._write_oob != !subdev[i]->_write_oob) {
 			kfree(concat);
 			printk("Incompatible OOB or ECC data on \"%s\"\n",
 			       subdev[i]->name);
@@ -849,15 +791,15 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to c
 	concat->num_subdev = num_devs;
 	concat->mtd.name = name;
 
-	concat->mtd.erase = concat_erase;
-	concat->mtd.read = concat_read;
-	concat->mtd.write = concat_write;
-	concat->mtd.sync = concat_sync;
-	concat->mtd.lock = concat_lock;
-	concat->mtd.unlock = concat_unlock;
-	concat->mtd.suspend = concat_suspend;
-	concat->mtd.resume = concat_resume;
-	concat->mtd.get_unmapped_area = concat_get_unmapped_area;
+	concat->mtd._erase = concat_erase;
+	concat->mtd._read = concat_read;
+	concat->mtd._write = concat_write;
+	concat->mtd._sync = concat_sync;
+	concat->mtd._lock = concat_lock;
+	concat->mtd._unlock = concat_unlock;
+	concat->mtd._suspend = concat_suspend;
+	concat->mtd._resume = concat_resume;
+	concat->mtd._get_unmapped_area = concat_get_unmapped_area;
 
 	/*
 	 * Combine the erase block size info of the subdevices:
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 9a9ce71a71fc..c837507dfb1c 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -107,7 +107,7 @@ static LIST_HEAD(mtd_notifiers);
  */
 static void mtd_release(struct device *dev)
 {
-	struct mtd_info *mtd = dev_get_drvdata(dev);
+	struct mtd_info __maybe_unused *mtd = dev_get_drvdata(dev);
 	dev_t index = MTD_DEVT(mtd->index);
 
 	/* remove /dev/mtdXro node if needed */
@@ -126,7 +126,7 @@ static int mtd_cls_resume(struct device *dev)
 {
 	struct mtd_info *mtd = dev_get_drvdata(dev);
 
-	if (mtd && mtd->resume)
+	if (mtd)
 		mtd_resume(mtd);
 	return 0;
 }
@@ -610,8 +610,8 @@ int __get_mtd_device(struct mtd_info *mtd)
 	if (!try_module_get(mtd->owner))
 		return -ENODEV;
 
-	if (mtd->get_device) {
-		err = mtd->get_device(mtd);
+	if (mtd->_get_device) {
+		err = mtd->_get_device(mtd);
 
 		if (err) {
 			module_put(mtd->owner);
@@ -675,14 +675,267 @@ void __put_mtd_device(struct mtd_info *mtd)
 	--mtd->usecount;
 	BUG_ON(mtd->usecount < 0);
 
-	if (mtd->put_device)
-		mtd->put_device(mtd);
+	if (mtd->_put_device)
+		mtd->_put_device(mtd);
 
 	module_put(mtd->owner);
 }
 EXPORT_SYMBOL_GPL(__put_mtd_device);
 
 /*
+ * Erase is an asynchronous operation.  Device drivers are supposed
+ * to call instr->callback() whenever the operation completes, even
+ * if it completes with a failure.
+ * Callers are supposed to pass a callback function and wait for it
+ * to be called before writing to the block.
+ */
+int mtd_erase(struct mtd_info *mtd, struct erase_info *instr)
+{
+	if (instr->addr > mtd->size || instr->len > mtd->size - instr->addr)
+		return -EINVAL;
+	if (!(mtd->flags & MTD_WRITEABLE))
+		return -EROFS;
+	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
+	if (!instr->len) {
+		instr->state = MTD_ERASE_DONE;
+		mtd_erase_callback(instr);
+		return 0;
+	}
+	return mtd->_erase(mtd, instr);
+}
+EXPORT_SYMBOL_GPL(mtd_erase);
+
+/*
+ * This stuff for eXecute-In-Place. phys is optional and may be set to NULL.
+ */
+int mtd_point(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
+	      void **virt, resource_size_t *phys)
+{
+	*retlen = 0;
+	*virt = NULL;
+	if (phys)
+		*phys = 0;
+	if (!mtd->_point)
+		return -EOPNOTSUPP;
+	if (from < 0 || from > mtd->size || len > mtd->size - from)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	return mtd->_point(mtd, from, len, retlen, virt, phys);
+}
+EXPORT_SYMBOL_GPL(mtd_point);
+
+/* We probably shouldn't allow XIP if the unpoint isn't a NULL */
+int mtd_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
+{
+	if (!mtd->_point)
+		return -EOPNOTSUPP;
+	if (from < 0 || from > mtd->size || len > mtd->size - from)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	return mtd->_unpoint(mtd, from, len);
+}
+EXPORT_SYMBOL_GPL(mtd_unpoint);
+
+/*
+ * Allow NOMMU mmap() to directly map the device (if not NULL)
+ * - return the address to which the offset maps
+ * - return -ENOSYS to indicate refusal to do the mapping
+ */
+unsigned long mtd_get_unmapped_area(struct mtd_info *mtd, unsigned long len,
+				    unsigned long offset, unsigned long flags)
+{
+	if (!mtd->_get_unmapped_area)
+		return -EOPNOTSUPP;
+	if (offset > mtd->size || len > mtd->size - offset)
+		return -EINVAL;
+	return mtd->_get_unmapped_area(mtd, len, offset, flags);
+}
+EXPORT_SYMBOL_GPL(mtd_get_unmapped_area);
+
+int mtd_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
+	     u_char *buf)
+{
+	*retlen = 0;
+	if (from < 0 || from > mtd->size || len > mtd->size - from)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	return mtd->_read(mtd, from, len, retlen, buf);
+}
+EXPORT_SYMBOL_GPL(mtd_read);
+
+int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
+	      const u_char *buf)
+{
+	*retlen = 0;
+	if (to < 0 || to > mtd->size || len > mtd->size - to)
+		return -EINVAL;
+	if (!mtd->_write || !(mtd->flags & MTD_WRITEABLE))
+		return -EROFS;
+	if (!len)
+		return 0;
+	return mtd->_write(mtd, to, len, retlen, buf);
+}
+EXPORT_SYMBOL_GPL(mtd_write);
+
+/*
+ * In blackbox flight recorder like scenarios we want to make successful writes
+ * in interrupt context. panic_write() is only intended to be called when its
+ * known the kernel is about to panic and we need the write to succeed. Since
+ * the kernel is not going to be running for much longer, this function can
+ * break locks and delay to ensure the write succeeds (but not sleep).
+ */
+int mtd_panic_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
+		    const u_char *buf)
+{
+	*retlen = 0;
+	if (!mtd->_panic_write)
+		return -EOPNOTSUPP;
+	if (to < 0 || to > mtd->size || len > mtd->size - to)
+		return -EINVAL;
+	if (!(mtd->flags & MTD_WRITEABLE))
+		return -EROFS;
+	if (!len)
+		return 0;
+	return mtd->_panic_write(mtd, to, len, retlen, buf);
+}
+EXPORT_SYMBOL_GPL(mtd_panic_write);
+
+/*
+ * Method to access the protection register area, present in some flash
+ * devices. The user data is one time programmable but the factory data is read
+ * only.
+ */
+int mtd_get_fact_prot_info(struct mtd_info *mtd, struct otp_info *buf,
+			   size_t len)
+{
+	if (!mtd->_get_fact_prot_info)
+		return -EOPNOTSUPP;
+	if (!len)
+		return 0;
+	return mtd->_get_fact_prot_info(mtd, buf, len);
+}
+EXPORT_SYMBOL_GPL(mtd_get_fact_prot_info);
+
+int mtd_read_fact_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
+			   size_t *retlen, u_char *buf)
+{
+	*retlen = 0;
+	if (!mtd->_read_fact_prot_reg)
+		return -EOPNOTSUPP;
+	if (!len)
+		return 0;
+	return mtd->_read_fact_prot_reg(mtd, from, len, retlen, buf);
+}
+EXPORT_SYMBOL_GPL(mtd_read_fact_prot_reg);
+
+int mtd_get_user_prot_info(struct mtd_info *mtd, struct otp_info *buf,
+			   size_t len)
+{
+	if (!mtd->_get_user_prot_info)
+		return -EOPNOTSUPP;
+	if (!len)
+		return 0;
+	return mtd->_get_user_prot_info(mtd, buf, len);
+}
+EXPORT_SYMBOL_GPL(mtd_get_user_prot_info);
+
+int mtd_read_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
+			   size_t *retlen, u_char *buf)
+{
+	*retlen = 0;
+	if (!mtd->_read_user_prot_reg)
+		return -EOPNOTSUPP;
+	if (!len)
+		return 0;
+	return mtd->_read_user_prot_reg(mtd, from, len, retlen, buf);
+}
+EXPORT_SYMBOL_GPL(mtd_read_user_prot_reg);
+
+int mtd_write_user_prot_reg(struct mtd_info *mtd, loff_t to, size_t len,
+			    size_t *retlen, u_char *buf)
+{
+	*retlen = 0;
+	if (!mtd->_write_user_prot_reg)
+		return -EOPNOTSUPP;
+	if (!len)
+		return 0;
+	return mtd->_write_user_prot_reg(mtd, to, len, retlen, buf);
+}
+EXPORT_SYMBOL_GPL(mtd_write_user_prot_reg);
+
+int mtd_lock_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len)
+{
+	if (!mtd->_lock_user_prot_reg)
+		return -EOPNOTSUPP;
+	if (!len)
+		return 0;
+	return mtd->_lock_user_prot_reg(mtd, from, len);
+}
+EXPORT_SYMBOL_GPL(mtd_lock_user_prot_reg);
+
+/* Chip-supported device locking */
+int mtd_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
+{
+	if (!mtd->_lock)
+		return -EOPNOTSUPP;
+	if (ofs < 0 || ofs > mtd->size || len > mtd->size - ofs)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	return mtd->_lock(mtd, ofs, len);
+}
+EXPORT_SYMBOL_GPL(mtd_lock);
+
+int mtd_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
+{
+	if (!mtd->_unlock)
+		return -EOPNOTSUPP;
+	if (ofs < 0 || ofs > mtd->size || len > mtd->size - ofs)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	return mtd->_unlock(mtd, ofs, len);
+}
+EXPORT_SYMBOL_GPL(mtd_unlock);
+
+int mtd_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
+{
+	if (!mtd->_is_locked)
+		return -EOPNOTSUPP;
+	if (ofs < 0 || ofs > mtd->size || len > mtd->size - ofs)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	return mtd->_is_locked(mtd, ofs, len);
+}
+EXPORT_SYMBOL_GPL(mtd_is_locked);
+
+int mtd_block_isbad(struct mtd_info *mtd, loff_t ofs)
+{
+	if (!mtd->_block_isbad)
+		return 0;
+	if (ofs < 0 || ofs > mtd->size)
+		return -EINVAL;
+	return mtd->_block_isbad(mtd, ofs);
+}
+EXPORT_SYMBOL_GPL(mtd_block_isbad);
+
+int mtd_block_markbad(struct mtd_info *mtd, loff_t ofs)
+{
+	if (!mtd->_block_markbad)
+		return -EOPNOTSUPP;
+	if (ofs < 0 || ofs > mtd->size)
+		return -EINVAL;
+	if (!(mtd->flags & MTD_WRITEABLE))
+		return -EROFS;
+	return mtd->_block_markbad(mtd, ofs);
+}
+EXPORT_SYMBOL_GPL(mtd_block_markbad);
+
+/*
  * default_mtd_writev - the default writev method
  * @mtd: mtd device description object pointer
  * @vecs: the vectors to write
@@ -729,9 +982,11 @@ int mtd_writev(struct mtd_info *mtd, const struct kvec *vecs,
 	       unsigned long count, loff_t to, size_t *retlen)
 {
 	*retlen = 0;
-	if (!mtd->writev)
+	if (!(mtd->flags & MTD_WRITEABLE))
+		return -EROFS;
+	if (!mtd->_writev)
 		return default_mtd_writev(mtd, vecs, count, to, retlen);
-	return mtd->writev(mtd, vecs, count, to, retlen);
+	return mtd->_writev(mtd, vecs, count, to, retlen);
 }
 EXPORT_SYMBOL_GPL(mtd_writev);
 
diff --git a/drivers/mtd/mtdoops.c b/drivers/mtd/mtdoops.c
index 3ce99e00a49e..ae36d7e1e913 100644
--- a/drivers/mtd/mtdoops.c
+++ b/drivers/mtd/mtdoops.c
@@ -169,7 +169,7 @@ static void mtdoops_workfunc_erase(struct work_struct *work)
 			cxt->nextpage = 0;
 	}
 
-	while (mtd_can_have_bb(mtd)) {
+	while (1) {
 		ret = mtd_block_isbad(mtd, cxt->nextpage * record_size);
 		if (!ret)
 			break;
@@ -199,9 +199,9 @@ badblock:
 		return;
 	}
 
-	if (mtd_can_have_bb(mtd) && ret == -EIO) {
+	if (ret == -EIO) {
 		ret = mtd_block_markbad(mtd, cxt->nextpage * record_size);
-		if (ret < 0) {
+		if (ret < 0 && ret != -EOPNOTSUPP) {
 			printk(KERN_ERR "mtdoops: block_markbad failed, aborting\n");
 			return;
 		}
@@ -257,8 +257,7 @@ static void find_next_position(struct mtdoops_context *cxt)
 	size_t retlen;
 
 	for (page = 0; page < cxt->oops_pages; page++) {
-		if (mtd_can_have_bb(mtd) &&
-		    mtd_block_isbad(mtd, page * record_size))
+		if (mtd_block_isbad(mtd, page * record_size))
 			continue;
 		/* Assume the page is used */
 		mark_page_used(cxt, page);
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index a3d44c3416b4..9651c06de0a9 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -65,12 +65,8 @@ static int part_read(struct mtd_info *mtd, loff_t from, size_t len,
 	int res;
 
 	stats = part->master->ecc_stats;
-
-	if (from >= mtd->size)
-		len = 0;
-	else if (from + len > mtd->size)
-		len = mtd->size - from;
-	res = mtd_read(part->master, from + part->offset, len, retlen, buf);
+	res = part->master->_read(part->master, from + part->offset, len,
+				  retlen, buf);
 	if (unlikely(res)) {
 		if (mtd_is_bitflip(res))
 			mtd->ecc_stats.corrected += part->master->ecc_stats.corrected - stats.corrected;
@@ -84,19 +80,16 @@ static int part_point(struct mtd_info *mtd, loff_t from, size_t len,
 		size_t *retlen, void **virt, resource_size_t *phys)
 {
 	struct mtd_part *part = PART(mtd);
-	if (from >= mtd->size)
-		len = 0;
-	else if (from + len > mtd->size)
-		len = mtd->size - from;
-	return mtd_point(part->master, from + part->offset, len, retlen,
-			 virt, phys);
+
+	return part->master->_point(part->master, from + part->offset, len,
+				    retlen, virt, phys);
 }
 
-static void part_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
+static int part_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
 	struct mtd_part *part = PART(mtd);
 
-	mtd_unpoint(part->master, from + part->offset, len);
+	return part->master->_unpoint(part->master, from + part->offset, len);
 }
 
 static unsigned long part_get_unmapped_area(struct mtd_info *mtd,
@@ -107,7 +100,8 @@ static unsigned long part_get_unmapped_area(struct mtd_info *mtd,
 	struct mtd_part *part = PART(mtd);
 
 	offset += part->offset;
-	return mtd_get_unmapped_area(part->master, len, offset, flags);
+	return part->master->_get_unmapped_area(part->master, len, offset,
+						flags);
 }
 
 static int part_read_oob(struct mtd_info *mtd, loff_t from,
@@ -138,7 +132,7 @@ static int part_read_oob(struct mtd_info *mtd, loff_t from,
 			return -EINVAL;
 	}
 
-	res = mtd_read_oob(part->master, from + part->offset, ops);
+	res = part->master->_read_oob(part->master, from + part->offset, ops);
 	if (unlikely(res)) {
 		if (mtd_is_bitflip(res))
 			mtd->ecc_stats.corrected++;
@@ -152,55 +146,46 @@ static int part_read_user_prot_reg(struct mtd_info *mtd, loff_t from,
 		size_t len, size_t *retlen, u_char *buf)
 {
 	struct mtd_part *part = PART(mtd);
-	return mtd_read_user_prot_reg(part->master, from, len, retlen, buf);
+	return part->master->_read_user_prot_reg(part->master, from, len,
+						 retlen, buf);
 }
 
 static int part_get_user_prot_info(struct mtd_info *mtd,
 		struct otp_info *buf, size_t len)
 {
 	struct mtd_part *part = PART(mtd);
-	return mtd_get_user_prot_info(part->master, buf, len);
+	return part->master->_get_user_prot_info(part->master, buf, len);
 }
 
 static int part_read_fact_prot_reg(struct mtd_info *mtd, loff_t from,
 		size_t len, size_t *retlen, u_char *buf)
 {
 	struct mtd_part *part = PART(mtd);
-	return mtd_read_fact_prot_reg(part->master, from, len, retlen, buf);
+	return part->master->_read_fact_prot_reg(part->master, from, len,
+						 retlen, buf);
 }
 
 static int part_get_fact_prot_info(struct mtd_info *mtd, struct otp_info *buf,
 		size_t len)
 {
 	struct mtd_part *part = PART(mtd);
-	return mtd_get_fact_prot_info(part->master, buf, len);
+	return part->master->_get_fact_prot_info(part->master, buf, len);
 }
 
 static int part_write(struct mtd_info *mtd, loff_t to, size_t len,
 		size_t *retlen, const u_char *buf)
 {
 	struct mtd_part *part = PART(mtd);
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-	if (to >= mtd->size)
-		len = 0;
-	else if (to + len > mtd->size)
-		len = mtd->size - to;
-	return mtd_write(part->master, to + part->offset, len, retlen, buf);
+	return part->master->_write(part->master, to + part->offset, len,
+				    retlen, buf);
 }
 
 static int part_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
 		size_t *retlen, const u_char *buf)
 {
 	struct mtd_part *part = PART(mtd);
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-	if (to >= mtd->size)
-		len = 0;
-	else if (to + len > mtd->size)
-		len = mtd->size - to;
-	return mtd_panic_write(part->master, to + part->offset, len, retlen,
-			       buf);
+	return part->master->_panic_write(part->master, to + part->offset, len,
+					  retlen, buf);
 }
 
 static int part_write_oob(struct mtd_info *mtd, loff_t to,
@@ -208,50 +193,43 @@ static int part_write_oob(struct mtd_info *mtd, loff_t to,
 {
 	struct mtd_part *part = PART(mtd);
 
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-
 	if (to >= mtd->size)
 		return -EINVAL;
 	if (ops->datbuf && to + ops->len > mtd->size)
 		return -EINVAL;
-	return mtd_write_oob(part->master, to + part->offset, ops);
+	return part->master->_write_oob(part->master, to + part->offset, ops);
 }
 
 static int part_write_user_prot_reg(struct mtd_info *mtd, loff_t from,
 		size_t len, size_t *retlen, u_char *buf)
 {
 	struct mtd_part *part = PART(mtd);
-	return mtd_write_user_prot_reg(part->master, from, len, retlen, buf);
+	return part->master->_write_user_prot_reg(part->master, from, len,
+						  retlen, buf);
 }
 
 static int part_lock_user_prot_reg(struct mtd_info *mtd, loff_t from,
 		size_t len)
 {
 	struct mtd_part *part = PART(mtd);
-	return mtd_lock_user_prot_reg(part->master, from, len);
+	return part->master->_lock_user_prot_reg(part->master, from, len);
 }
 
 static int part_writev(struct mtd_info *mtd, const struct kvec *vecs,
 		unsigned long count, loff_t to, size_t *retlen)
 {
 	struct mtd_part *part = PART(mtd);
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-	return mtd_writev(part->master, vecs, count, to + part->offset,
-			  retlen);
+	return part->master->_writev(part->master, vecs, count,
+				     to + part->offset, retlen);
 }
 
 static int part_erase(struct mtd_info *mtd, struct erase_info *instr)
 {
 	struct mtd_part *part = PART(mtd);
 	int ret;
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-	if (instr->addr >= mtd->size)
-		return -EINVAL;
+
 	instr->addr += part->offset;
-	ret = mtd_erase(part->master, instr);
+	ret = part->master->_erase(part->master, instr);
 	if (ret) {
 		if (instr->fail_addr != MTD_FAIL_ADDR_UNKNOWN)
 			instr->fail_addr -= part->offset;
@@ -262,7 +240,7 @@ static int part_erase(struct mtd_info *mtd, struct erase_info *instr)
 
 void mtd_erase_callback(struct erase_info *instr)
 {
-	if (instr->mtd->erase == part_erase) {
+	if (instr->mtd->_erase == part_erase) {
 		struct mtd_part *part = PART(instr->mtd);
 
 		if (instr->fail_addr != MTD_FAIL_ADDR_UNKNOWN)
@@ -277,52 +255,44 @@ EXPORT_SYMBOL_GPL(mtd_erase_callback);
 static int part_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct mtd_part *part = PART(mtd);
-	if ((len + ofs) > mtd->size)
-		return -EINVAL;
-	return mtd_lock(part->master, ofs + part->offset, len);
+	return part->master->_lock(part->master, ofs + part->offset, len);
 }
 
 static int part_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct mtd_part *part = PART(mtd);
-	if ((len + ofs) > mtd->size)
-		return -EINVAL;
-	return mtd_unlock(part->master, ofs + part->offset, len);
+	return part->master->_unlock(part->master, ofs + part->offset, len);
 }
 
 static int part_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct mtd_part *part = PART(mtd);
-	if ((len + ofs) > mtd->size)
-		return -EINVAL;
-	return mtd_is_locked(part->master, ofs + part->offset, len);
+	return part->master->_is_locked(part->master, ofs + part->offset, len);
 }
 
 static void part_sync(struct mtd_info *mtd)
 {
 	struct mtd_part *part = PART(mtd);
-	mtd_sync(part->master);
+	part->master->_sync(part->master);
 }
 
 static int part_suspend(struct mtd_info *mtd)
 {
 	struct mtd_part *part = PART(mtd);
-	return mtd_suspend(part->master);
+	return part->master->_suspend(part->master);
 }
 
 static void part_resume(struct mtd_info *mtd)
 {
 	struct mtd_part *part = PART(mtd);
-	mtd_resume(part->master);
+	part->master->_resume(part->master);
 }
 
 static int part_block_isbad(struct mtd_info *mtd, loff_t ofs)
 {
 	struct mtd_part *part = PART(mtd);
-	if (ofs >= mtd->size)
-		return -EINVAL;
 	ofs += part->offset;
-	return mtd_block_isbad(part->master, ofs);
+	return part->master->_block_isbad(part->master, ofs);
 }
 
 static int part_block_markbad(struct mtd_info *mtd, loff_t ofs)
@@ -330,12 +300,8 @@ static int part_block_markbad(struct mtd_info *mtd, loff_t ofs)
 	struct mtd_part *part = PART(mtd);
 	int res;
 
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-	if (ofs >= mtd->size)
-		return -EINVAL;
 	ofs += part->offset;
-	res = mtd_block_markbad(part->master, ofs);
+	res = part->master->_block_markbad(part->master, ofs);
 	if (!res)
 		mtd->ecc_stats.badblocks++;
 	return res;
@@ -410,54 +376,55 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 	 */
 	slave->mtd.dev.parent = master->dev.parent;
 
-	slave->mtd.read = part_read;
-	slave->mtd.write = part_write;
+	slave->mtd._read = part_read;
+	slave->mtd._write = part_write;
 
-	if (master->panic_write)
-		slave->mtd.panic_write = part_panic_write;
+	if (master->_panic_write)
+		slave->mtd._panic_write = part_panic_write;
 
-	if (master->point && master->unpoint) {
-		slave->mtd.point = part_point;
-		slave->mtd.unpoint = part_unpoint;
+	if (master->_point && master->_unpoint) {
+		slave->mtd._point = part_point;
+		slave->mtd._unpoint = part_unpoint;
 	}
 
-	if (master->get_unmapped_area)
-		slave->mtd.get_unmapped_area = part_get_unmapped_area;
-	if (master->read_oob)
-		slave->mtd.read_oob = part_read_oob;
-	if (master->write_oob)
-		slave->mtd.write_oob = part_write_oob;
-	if (master->read_user_prot_reg)
-		slave->mtd.read_user_prot_reg = part_read_user_prot_reg;
-	if (master->read_fact_prot_reg)
-		slave->mtd.read_fact_prot_reg = part_read_fact_prot_reg;
-	if (master->write_user_prot_reg)
-		slave->mtd.write_user_prot_reg = part_write_user_prot_reg;
-	if (master->lock_user_prot_reg)
-		slave->mtd.lock_user_prot_reg = part_lock_user_prot_reg;
-	if (master->get_user_prot_info)
-		slave->mtd.get_user_prot_info = part_get_user_prot_info;
-	if (master->get_fact_prot_info)
-		slave->mtd.get_fact_prot_info = part_get_fact_prot_info;
-	if (master->sync)
-		slave->mtd.sync = part_sync;
-	if (!partno && !master->dev.class && master->suspend && master->resume) {
-			slave->mtd.suspend = part_suspend;
-			slave->mtd.resume = part_resume;
+	if (master->_get_unmapped_area)
+		slave->mtd._get_unmapped_area = part_get_unmapped_area;
+	if (master->_read_oob)
+		slave->mtd._read_oob = part_read_oob;
+	if (master->_write_oob)
+		slave->mtd._write_oob = part_write_oob;
+	if (master->_read_user_prot_reg)
+		slave->mtd._read_user_prot_reg = part_read_user_prot_reg;
+	if (master->_read_fact_prot_reg)
+		slave->mtd._read_fact_prot_reg = part_read_fact_prot_reg;
+	if (master->_write_user_prot_reg)
+		slave->mtd._write_user_prot_reg = part_write_user_prot_reg;
+	if (master->_lock_user_prot_reg)
+		slave->mtd._lock_user_prot_reg = part_lock_user_prot_reg;
+	if (master->_get_user_prot_info)
+		slave->mtd._get_user_prot_info = part_get_user_prot_info;
+	if (master->_get_fact_prot_info)
+		slave->mtd._get_fact_prot_info = part_get_fact_prot_info;
+	if (master->_sync)
+		slave->mtd._sync = part_sync;
+	if (!partno && !master->dev.class && master->_suspend &&
+	    master->_resume) {
+			slave->mtd._suspend = part_suspend;
+			slave->mtd._resume = part_resume;
 	}
-	if (master->writev)
-		slave->mtd.writev = part_writev;
-	if (master->lock)
-		slave->mtd.lock = part_lock;
-	if (master->unlock)
-		slave->mtd.unlock = part_unlock;
-	if (master->is_locked)
-		slave->mtd.is_locked = part_is_locked;
-	if (master->block_isbad)
-		slave->mtd.block_isbad = part_block_isbad;
-	if (master->block_markbad)
-		slave->mtd.block_markbad = part_block_markbad;
-	slave->mtd.erase = part_erase;
+	if (master->_writev)
+		slave->mtd._writev = part_writev;
+	if (master->_lock)
+		slave->mtd._lock = part_lock;
+	if (master->_unlock)
+		slave->mtd._unlock = part_unlock;
+	if (master->_is_locked)
+		slave->mtd._is_locked = part_is_locked;
+	if (master->_block_isbad)
+		slave->mtd._block_isbad = part_block_isbad;
+	if (master->_block_markbad)
+		slave->mtd._block_markbad = part_block_markbad;
+	slave->mtd._erase = part_erase;
 	slave->master = master;
 	slave->offset = part->offset;
 
@@ -549,7 +516,8 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 	}
 
 	slave->mtd.ecclayout = master->ecclayout;
-	if (master->block_isbad) {
+	slave->mtd.ecc_strength = master->ecc_strength;
+	if (master->_block_isbad) {
 		uint64_t offs = 0;
 
 		while (offs < slave->mtd.size) {
@@ -761,7 +729,7 @@ int parse_mtd_partitions(struct mtd_info *master, const char **types,
 	for ( ; ret <= 0 && *types; types++) {
 		parser = get_partition_parser(*types);
 		if (!parser && !request_module("%s", *types))
-				parser = get_partition_parser(*types);
+			parser = get_partition_parser(*types);
 		if (!parser)
 			continue;
 		ret = (*parser->parse_fn)(master, pparts, data);
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 3d8d2d83995f..7d17cecad69d 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -246,6 +246,7 @@ config MTD_NAND_BCM_UMI_HWCS
 config MTD_NAND_DISKONCHIP
 	tristate "DiskOnChip 2000, Millennium and Millennium Plus (NAND reimplementation) (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
+	depends on HAS_IOMEM
 	select REED_SOLOMON
 	select REED_SOLOMON_DEC16
 	help
@@ -313,6 +314,26 @@ config MTD_NAND_DISKONCHIP_BBTWRITE
 	  load time (assuming you build diskonchip as a module) with the module
 	  parameter "inftl_bbt_write=1".
 
+config MTD_NAND_DOCG4
+	tristate "Support for DiskOnChip G4 (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	select BCH
+	select BITREVERSE
+	help
+	  Support for diskonchip G4 nand flash, found in various smartphones and
+	  PDAs, among them the Palm Treo680, HTC Prophet and Wizard, Toshiba
+	  Portege G900, Asus P526, and O2 XDA Zinc.
+
+	  With this driver you will be able to use UBI and create a ubifs on the
+	  device, so you may wish to consider enabling UBI and UBIFS as well.
+
+	  These devices ship with the Mys/Sandisk SAFTL formatting, for which
+	  there is currently no mtd parser, so you may want to use command line
+	  partitioning to segregate write-protected blocks. On the Treo680, the
+	  first five erase blocks (256KiB each) are write-protected, followed
+	  by the block containing the saftl partition table.  This is probably
+	  typical.
+
 config MTD_NAND_SHARPSL
 	tristate "Support for NAND Flash on Sharp SL Series (C7xx + others)"
 	depends on ARCH_PXA
@@ -420,7 +441,6 @@ config MTD_NAND_NANDSIM
 config MTD_NAND_GPMI_NAND
         bool "GPMI NAND Flash Controller driver"
         depends on MTD_NAND && (SOC_IMX23 || SOC_IMX28)
-	select MTD_CMDLINE_PARTS
         help
 	 Enables NAND Flash support for IMX23 or IMX28.
 	 The GPMI controller is very powerful, with the help of BCH
@@ -431,6 +451,7 @@ config MTD_NAND_GPMI_NAND
 
 config MTD_NAND_PLATFORM
 	tristate "Support for generic platform NAND driver"
+	depends on HAS_IOMEM
 	help
 	  This implements a generic NAND driver for on-SOC platform
 	  devices. You will need to provide platform-specific functions
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 19bc8cb1d187..d4b4d8739bd8 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_MTD_NAND_PPCHAMELEONEVB)	+= ppchameleonevb.o
 obj-$(CONFIG_MTD_NAND_S3C2410)		+= s3c2410.o
 obj-$(CONFIG_MTD_NAND_DAVINCI)		+= davinci_nand.o
 obj-$(CONFIG_MTD_NAND_DISKONCHIP)	+= diskonchip.o
+obj-$(CONFIG_MTD_NAND_DOCG4)		+= docg4.o
 obj-$(CONFIG_MTD_NAND_FSMC)		+= fsmc_nand.o
 obj-$(CONFIG_MTD_NAND_H1900)		+= h1910.o
 obj-$(CONFIG_MTD_NAND_RTC_FROM4)	+= rtc_from4.o
diff --git a/drivers/mtd/nand/alauda.c b/drivers/mtd/nand/alauda.c
index 6a5ff64a139e..4f20e1d8bef1 100644
--- a/drivers/mtd/nand/alauda.c
+++ b/drivers/mtd/nand/alauda.c
@@ -585,12 +585,13 @@ static int alauda_init_media(struct alauda *al)
 	mtd->writesize = 1<<card->pageshift;
 	mtd->type = MTD_NANDFLASH;
 	mtd->flags = MTD_CAP_NANDFLASH;
-	mtd->read = alauda_read;
-	mtd->write = alauda_write;
-	mtd->erase = alauda_erase;
-	mtd->block_isbad = alauda_isbad;
+	mtd->_read = alauda_read;
+	mtd->_write = alauda_write;
+	mtd->_erase = alauda_erase;
+	mtd->_block_isbad = alauda_isbad;
 	mtd->priv = al;
 	mtd->owner = THIS_MODULE;
+	mtd->ecc_strength = 1;
 
 	err = mtd_device_register(mtd, NULL, 0);
 	if (err) {
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index 35b4fb55dbd6..2165576a1c67 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -27,6 +27,10 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/of_mtd.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
@@ -34,22 +38,10 @@
 #include <linux/dmaengine.h>
 #include <linux/gpio.h>
 #include <linux/io.h>
+#include <linux/platform_data/atmel.h>
 
-#include <mach/board.h>
 #include <mach/cpu.h>
 
-#ifdef CONFIG_MTD_NAND_ATMEL_ECC_HW
-#define hard_ecc	1
-#else
-#define hard_ecc	0
-#endif
-
-#ifdef CONFIG_MTD_NAND_ATMEL_ECC_NONE
-#define no_ecc		1
-#else
-#define no_ecc		0
-#endif
-
 static int use_dma = 1;
 module_param(use_dma, int, 0);
 
@@ -95,7 +87,7 @@ struct atmel_nand_host {
 	struct mtd_info		mtd;
 	void __iomem		*io_base;
 	dma_addr_t		io_phys;
-	struct atmel_nand_data	*board;
+	struct atmel_nand_data	board;
 	struct device		*dev;
 	void __iomem		*ecc;
 
@@ -113,8 +105,8 @@ static int cpu_has_dma(void)
  */
 static void atmel_nand_enable(struct atmel_nand_host *host)
 {
-	if (gpio_is_valid(host->board->enable_pin))
-		gpio_set_value(host->board->enable_pin, 0);
+	if (gpio_is_valid(host->board.enable_pin))
+		gpio_set_value(host->board.enable_pin, 0);
 }
 
 /*
@@ -122,8 +114,8 @@ static void atmel_nand_enable(struct atmel_nand_host *host)
  */
 static void atmel_nand_disable(struct atmel_nand_host *host)
 {
-	if (gpio_is_valid(host->board->enable_pin))
-		gpio_set_value(host->board->enable_pin, 1);
+	if (gpio_is_valid(host->board.enable_pin))
+		gpio_set_value(host->board.enable_pin, 1);
 }
 
 /*
@@ -144,9 +136,9 @@ static void atmel_nand_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl
 		return;
 
 	if (ctrl & NAND_CLE)
-		writeb(cmd, host->io_base + (1 << host->board->cle));
+		writeb(cmd, host->io_base + (1 << host->board.cle));
 	else
-		writeb(cmd, host->io_base + (1 << host->board->ale));
+		writeb(cmd, host->io_base + (1 << host->board.ale));
 }
 
 /*
@@ -157,8 +149,8 @@ static int atmel_nand_device_ready(struct mtd_info *mtd)
 	struct nand_chip *nand_chip = mtd->priv;
 	struct atmel_nand_host *host = nand_chip->priv;
 
-	return gpio_get_value(host->board->rdy_pin) ^
-                !!host->board->rdy_pin_active_low;
+	return gpio_get_value(host->board.rdy_pin) ^
+                !!host->board.rdy_pin_active_low;
 }
 
 /*
@@ -273,7 +265,7 @@ static void atmel_read_buf(struct mtd_info *mtd, u8 *buf, int len)
 		if (atmel_nand_dma_op(mtd, buf, len, 1) == 0)
 			return;
 
-	if (host->board->bus_width_16)
+	if (host->board.bus_width_16)
 		atmel_read_buf16(mtd, buf, len);
 	else
 		atmel_read_buf8(mtd, buf, len);
@@ -289,7 +281,7 @@ static void atmel_write_buf(struct mtd_info *mtd, const u8 *buf, int len)
 		if (atmel_nand_dma_op(mtd, (void *)buf, len, 0) == 0)
 			return;
 
-	if (host->board->bus_width_16)
+	if (host->board.bus_width_16)
 		atmel_write_buf16(mtd, buf, len);
 	else
 		atmel_write_buf8(mtd, buf, len);
@@ -481,6 +473,56 @@ static void atmel_nand_hwctl(struct mtd_info *mtd, int mode)
 	}
 }
 
+#if defined(CONFIG_OF)
+static int __devinit atmel_of_init_port(struct atmel_nand_host *host,
+					 struct device_node *np)
+{
+	u32 val;
+	int ecc_mode;
+	struct atmel_nand_data *board = &host->board;
+	enum of_gpio_flags flags;
+
+	if (of_property_read_u32(np, "atmel,nand-addr-offset", &val) == 0) {
+		if (val >= 32) {
+			dev_err(host->dev, "invalid addr-offset %u\n", val);
+			return -EINVAL;
+		}
+		board->ale = val;
+	}
+
+	if (of_property_read_u32(np, "atmel,nand-cmd-offset", &val) == 0) {
+		if (val >= 32) {
+			dev_err(host->dev, "invalid cmd-offset %u\n", val);
+			return -EINVAL;
+		}
+		board->cle = val;
+	}
+
+	ecc_mode = of_get_nand_ecc_mode(np);
+
+	board->ecc_mode = ecc_mode < 0 ? NAND_ECC_SOFT : ecc_mode;
+
+	board->on_flash_bbt = of_get_nand_on_flash_bbt(np);
+
+	if (of_get_nand_bus_width(np) == 16)
+		board->bus_width_16 = 1;
+
+	board->rdy_pin = of_get_gpio_flags(np, 0, &flags);
+	board->rdy_pin_active_low = (flags == OF_GPIO_ACTIVE_LOW);
+
+	board->enable_pin = of_get_gpio(np, 1);
+	board->det_pin = of_get_gpio(np, 2);
+
+	return 0;
+}
+#else
+static int __devinit atmel_of_init_port(struct atmel_nand_host *host,
+					 struct device_node *np)
+{
+	return -EINVAL;
+}
+#endif
+
 /*
  * Probe for the NAND device.
  */
@@ -491,6 +533,7 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 	struct nand_chip *nand_chip;
 	struct resource *regs;
 	struct resource *mem;
+	struct mtd_part_parser_data ppdata = {};
 	int res;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -517,8 +560,15 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 
 	mtd = &host->mtd;
 	nand_chip = &host->nand_chip;
-	host->board = pdev->dev.platform_data;
 	host->dev = &pdev->dev;
+	if (pdev->dev.of_node) {
+		res = atmel_of_init_port(host, pdev->dev.of_node);
+		if (res)
+			goto err_nand_ioremap;
+	} else {
+		memcpy(&host->board, pdev->dev.platform_data,
+		       sizeof(struct atmel_nand_data));
+	}
 
 	nand_chip->priv = host;		/* link the private data structures */
 	mtd->priv = nand_chip;
@@ -529,36 +579,36 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 	nand_chip->IO_ADDR_W = host->io_base;
 	nand_chip->cmd_ctrl = atmel_nand_cmd_ctrl;
 
-	if (gpio_is_valid(host->board->rdy_pin))
+	if (gpio_is_valid(host->board.rdy_pin))
 		nand_chip->dev_ready = atmel_nand_device_ready;
 
+	nand_chip->ecc.mode = host->board.ecc_mode;
+
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (!regs && hard_ecc) {
+	if (!regs && nand_chip->ecc.mode == NAND_ECC_HW) {
 		printk(KERN_ERR "atmel_nand: can't get I/O resource "
 				"regs\nFalling back on software ECC\n");
+		nand_chip->ecc.mode = NAND_ECC_SOFT;
 	}
 
-	nand_chip->ecc.mode = NAND_ECC_SOFT;	/* enable ECC */
-	if (no_ecc)
-		nand_chip->ecc.mode = NAND_ECC_NONE;
-	if (hard_ecc && regs) {
+	if (nand_chip->ecc.mode == NAND_ECC_HW) {
 		host->ecc = ioremap(regs->start, resource_size(regs));
 		if (host->ecc == NULL) {
 			printk(KERN_ERR "atmel_nand: ioremap failed\n");
 			res = -EIO;
 			goto err_ecc_ioremap;
 		}
-		nand_chip->ecc.mode = NAND_ECC_HW;
 		nand_chip->ecc.calculate = atmel_nand_calculate;
 		nand_chip->ecc.correct = atmel_nand_correct;
 		nand_chip->ecc.hwctl = atmel_nand_hwctl;
 		nand_chip->ecc.read_page = atmel_nand_read_page;
 		nand_chip->ecc.bytes = 4;
+		nand_chip->ecc.strength = 1;
 	}
 
 	nand_chip->chip_delay = 20;		/* 20us command delay time */
 
-	if (host->board->bus_width_16)	/* 16-bit bus width */
+	if (host->board.bus_width_16)	/* 16-bit bus width */
 		nand_chip->options |= NAND_BUSWIDTH_16;
 
 	nand_chip->read_buf = atmel_read_buf;
@@ -567,15 +617,15 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, host);
 	atmel_nand_enable(host);
 
-	if (gpio_is_valid(host->board->det_pin)) {
-		if (gpio_get_value(host->board->det_pin)) {
+	if (gpio_is_valid(host->board.det_pin)) {
+		if (gpio_get_value(host->board.det_pin)) {
 			printk(KERN_INFO "No SmartMedia card inserted.\n");
 			res = -ENXIO;
 			goto err_no_card;
 		}
 	}
 
-	if (on_flash_bbt) {
+	if (host->board.on_flash_bbt || on_flash_bbt) {
 		printk(KERN_INFO "atmel_nand: Use On Flash BBT\n");
 		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
 	}
@@ -650,8 +700,9 @@ static int __init atmel_nand_probe(struct platform_device *pdev)
 	}
 
 	mtd->name = "atmel_nand";
-	res = mtd_device_parse_register(mtd, NULL, 0,
-			host->board->parts, host->board->num_parts);
+	ppdata.of_node = pdev->dev.of_node;
+	res = mtd_device_parse_register(mtd, NULL, &ppdata,
+			host->board.parts, host->board.num_parts);
 	if (!res)
 		return res;
 
@@ -695,11 +746,21 @@ static int __exit atmel_nand_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#if defined(CONFIG_OF)
+static const struct of_device_id atmel_nand_dt_ids[] = {
+	{ .compatible = "atmel,at91rm9200-nand" },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(of, atmel_nand_dt_ids);
+#endif
+
 static struct platform_driver atmel_nand_driver = {
 	.remove		= __exit_p(atmel_nand_remove),
 	.driver		= {
 		.name	= "atmel_nand",
 		.owner	= THIS_MODULE,
+		.of_match_table	= of_match_ptr(atmel_nand_dt_ids),
 	},
 };
 
diff --git a/drivers/mtd/nand/bcm_umi_nand.c b/drivers/mtd/nand/bcm_umi_nand.c
index 50387fd4009b..6908cdde3065 100644
--- a/drivers/mtd/nand/bcm_umi_nand.c
+++ b/drivers/mtd/nand/bcm_umi_nand.c
@@ -31,7 +31,6 @@
 #include <linux/mtd/partitions.h>
 
 #include <asm/mach-types.h>
-#include <asm/system.h>
 
 #include <mach/reg_nand.h>
 #include <mach/reg_umi.h>
@@ -476,6 +475,14 @@ static int __devinit bcm_umi_nand_probe(struct platform_device *pdev)
 			largepage_bbt.options = NAND_BBT_SCAN2NDPAGE;
 		this->badblock_pattern = &largepage_bbt;
 	}
+
+	/*
+	 * FIXME: ecc strength value of 6 bits per 512 bytes of data is a
+	 * conservative guess, given 13 ecc bytes and using bch alg.
+	 * (Assume Galois field order m=15 to allow a margin of error.)
+	 */
+	this->ecc.strength = 6;
+
 #endif
 
 	/* Now finish off the scan, now that ecc.layout has been initialized. */
@@ -488,7 +495,7 @@ static int __devinit bcm_umi_nand_probe(struct platform_device *pdev)
 
 	/* Register the partitions */
 	board_mtd->name = "bcm_umi-nand";
-	mtd_device_parse_register(board_mtd, NULL, 0, NULL, 0);
+	mtd_device_parse_register(board_mtd, NULL, NULL, NULL, 0);
 
 	/* Return happy */
 	return 0;
diff --git a/drivers/mtd/nand/bf5xx_nand.c b/drivers/mtd/nand/bf5xx_nand.c
index dd899cb5d366..d7b86b925de5 100644
--- a/drivers/mtd/nand/bf5xx_nand.c
+++ b/drivers/mtd/nand/bf5xx_nand.c
@@ -702,9 +702,11 @@ static int bf5xx_nand_scan(struct mtd_info *mtd)
 		if (likely(mtd->writesize >= 512)) {
 			chip->ecc.size = 512;
 			chip->ecc.bytes = 6;
+			chip->ecc.strength = 2;
 		} else {
 			chip->ecc.size = 256;
 			chip->ecc.bytes = 3;
+			chip->ecc.strength = 1;
 			bfin_write_NFC_CTL(bfin_read_NFC_CTL() & ~(1 << NFC_PG_SIZE_OFFSET));
 			SSYNC();
 		}
diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index 72d3f23490c5..2a96e1a12062 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -783,6 +783,7 @@ static int __devinit cafe_nand_probe(struct pci_dev *pdev,
 	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
 	cafe->nand.ecc.size = mtd->writesize;
 	cafe->nand.ecc.bytes = 14;
+	cafe->nand.ecc.strength = 4;
 	cafe->nand.ecc.hwctl  = (void *)cafe_nand_bug;
 	cafe->nand.ecc.calculate = (void *)cafe_nand_bug;
 	cafe->nand.ecc.correct  = (void *)cafe_nand_bug;
@@ -799,7 +800,7 @@ static int __devinit cafe_nand_probe(struct pci_dev *pdev,
 	pci_set_drvdata(pdev, mtd);
 
 	mtd->name = "cafe_nand";
-	mtd_device_parse_register(mtd, part_probes, 0, NULL, 0);
+	mtd_device_parse_register(mtd, part_probes, NULL, NULL, 0);
 
 	goto out;
 
diff --git a/drivers/mtd/nand/cmx270_nand.c b/drivers/mtd/nand/cmx270_nand.c
index 737ef9a04fdb..1024bfc05c86 100644
--- a/drivers/mtd/nand/cmx270_nand.c
+++ b/drivers/mtd/nand/cmx270_nand.c
@@ -219,7 +219,7 @@ static int __init cmx270_init(void)
 	}
 
 	/* Register the partitions */
-	ret = mtd_device_parse_register(cmx270_nand_mtd, NULL, 0,
+	ret = mtd_device_parse_register(cmx270_nand_mtd, NULL, NULL,
 					partition_info, NUM_PARTITIONS);
 	if (ret)
 		goto err_scan;
diff --git a/drivers/mtd/nand/cs553x_nand.c b/drivers/mtd/nand/cs553x_nand.c
index 414afa793563..821c34c62500 100644
--- a/drivers/mtd/nand/cs553x_nand.c
+++ b/drivers/mtd/nand/cs553x_nand.c
@@ -248,6 +248,8 @@ static int __init cs553x_init_one(int cs, int mmio, unsigned long adr)
 		goto out_ior;
 	}
 
+	this->ecc.strength = 1;
+
 	new_mtd->name = kasprintf(GFP_KERNEL, "cs553x_nand_cs%d", cs);
 
 	cs553x_mtd[cs] = new_mtd;
@@ -313,7 +315,7 @@ static int __init cs553x_init(void)
 	for (i = 0; i < NR_CS553X_CONTROLLERS; i++) {
 		if (cs553x_mtd[i]) {
 			/* If any devices registered, return success. Else the last error. */
-			mtd_device_parse_register(cs553x_mtd[i], NULL, 0,
+			mtd_device_parse_register(cs553x_mtd[i], NULL, NULL,
 						  NULL, 0);
 			err = 0;
 		}
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 6e566156956f..d94b03c207af 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -641,6 +641,7 @@ static int __init nand_davinci_probe(struct platform_device *pdev)
 			info->chip.ecc.bytes = 3;
 		}
 		info->chip.ecc.size = 512;
+		info->chip.ecc.strength = pdata->ecc_bits;
 		break;
 	default:
 		ret = -EINVAL;
@@ -752,8 +753,8 @@ syndrome_done:
 	if (ret < 0)
 		goto err_scan;
 
-	ret = mtd_device_parse_register(&info->mtd, NULL, 0,
-			pdata->parts, pdata->nr_parts);
+	ret = mtd_device_parse_register(&info->mtd, NULL, NULL, pdata->parts,
+					pdata->nr_parts);
 
 	if (ret < 0)
 		goto err_scan;
diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index 3984d488f9ab..a9e57d686297 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -1590,6 +1590,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 			ECC_15BITS * (denali->mtd.writesize /
 			ECC_SECTOR_SIZE)))) {
 		/* if MLC OOB size is large enough, use 15bit ECC*/
+		denali->nand.ecc.strength = 15;
 		denali->nand.ecc.layout = &nand_15bit_oob;
 		denali->nand.ecc.bytes = ECC_15BITS;
 		iowrite32(15, denali->flash_reg + ECC_CORRECTION);
@@ -1600,12 +1601,14 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 				" contain 8bit ECC correction codes");
 		goto failed_req_irq;
 	} else {
+		denali->nand.ecc.strength = 8;
 		denali->nand.ecc.layout = &nand_8bit_oob;
 		denali->nand.ecc.bytes = ECC_8BITS;
 		iowrite32(8, denali->flash_reg + ECC_CORRECTION);
 	}
 
 	denali->nand.ecc.bytes *= denali->devnum;
+	denali->nand.ecc.strength *= denali->devnum;
 	denali->nand.ecc.layout->eccbytes *=
 		denali->mtd.writesize / ECC_SECTOR_SIZE;
 	denali->nand.ecc.layout->oobfree[0].offset =
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index df921e7a496c..e2ca067631cf 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -1653,6 +1653,7 @@ static int __init doc_probe(unsigned long physadr)
 	nand->ecc.mode		= NAND_ECC_HW_SYNDROME;
 	nand->ecc.size		= 512;
 	nand->ecc.bytes		= 6;
+	nand->ecc.strength	= 2;
 	nand->bbt_options	= NAND_BBT_USE_FLASH;
 
 	doc->physadr		= physadr;
diff --git a/drivers/mtd/nand/docg4.c b/drivers/mtd/nand/docg4.c
new file mode 100644
index 000000000000..b08202664543
--- /dev/null
+++ b/drivers/mtd/nand/docg4.c
@@ -0,0 +1,1377 @@
+/*
+ *  Copyright © 2012 Mike Dunn <mikedunn@newsguy.com>
+ *
+ * mtd nand driver for M-Systems DiskOnChip G4
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * Tested on the Palm Treo 680.  The G4 is also present on Toshiba Portege, Asus
+ * P526, some HTC smartphones (Wizard, Prophet, ...), O2 XDA Zinc, maybe others.
+ * Should work on these as well.  Let me know!
+ *
+ * TODO:
+ *
+ *  Mechanism for management of password-protected areas
+ *
+ *  Hamming ecc when reading oob only
+ *
+ *  According to the M-Sys documentation, this device is also available in a
+ *  "dual-die" configuration having a 256MB capacity, but no mechanism for
+ *  detecting this variant is documented.  Currently this driver assumes 128MB
+ *  capacity.
+ *
+ *  Support for multiple cascaded devices ("floors").  Not sure which gadgets
+ *  contain multiple G4s in a cascaded configuration, if any.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/bitops.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/bch.h>
+#include <linux/bitrev.h>
+
+/*
+ * You'll want to ignore badblocks if you're reading a partition that contains
+ * data written by the TrueFFS library (i.e., by PalmOS, Windows, etc), since
+ * it does not use mtd nand's method for marking bad blocks (using oob area).
+ * This will also skip the check of the "page written" flag.
+ */
+static bool ignore_badblocks;
+module_param(ignore_badblocks, bool, 0);
+MODULE_PARM_DESC(ignore_badblocks, "no badblock checking performed");
+
+struct docg4_priv {
+	struct mtd_info	*mtd;
+	struct device *dev;
+	void __iomem *virtadr;
+	int status;
+	struct {
+		unsigned int command;
+		int column;
+		int page;
+	} last_command;
+	uint8_t oob_buf[16];
+	uint8_t ecc_buf[7];
+	int oob_page;
+	struct bch_control *bch;
+};
+
+/*
+ * Defines prefixed with DOCG4 are unique to the diskonchip G4.  All others are
+ * shared with other diskonchip devices (P3, G3 at least).
+ *
+ * Functions with names prefixed with docg4_ are mtd / nand interface functions
+ * (though they may also be called internally).  All others are internal.
+ */
+
+#define DOC_IOSPACE_DATA		0x0800
+
+/* register offsets */
+#define DOC_CHIPID			0x1000
+#define DOC_DEVICESELECT		0x100a
+#define DOC_ASICMODE			0x100c
+#define DOC_DATAEND			0x101e
+#define DOC_NOP				0x103e
+
+#define DOC_FLASHSEQUENCE		0x1032
+#define DOC_FLASHCOMMAND		0x1034
+#define DOC_FLASHADDRESS		0x1036
+#define DOC_FLASHCONTROL		0x1038
+#define DOC_ECCCONF0			0x1040
+#define DOC_ECCCONF1			0x1042
+#define DOC_HAMMINGPARITY		0x1046
+#define DOC_BCH_SYNDROM(idx)		(0x1048 + idx)
+
+#define DOC_ASICMODECONFIRM		0x1072
+#define DOC_CHIPID_INV			0x1074
+#define DOC_POWERMODE			0x107c
+
+#define DOCG4_MYSTERY_REG		0x1050
+
+/* apparently used only to write oob bytes 6 and 7 */
+#define DOCG4_OOB_6_7			0x1052
+
+/* DOC_FLASHSEQUENCE register commands */
+#define DOC_SEQ_RESET			0x00
+#define DOCG4_SEQ_PAGE_READ		0x03
+#define DOCG4_SEQ_FLUSH			0x29
+#define DOCG4_SEQ_PAGEWRITE		0x16
+#define DOCG4_SEQ_PAGEPROG		0x1e
+#define DOCG4_SEQ_BLOCKERASE		0x24
+
+/* DOC_FLASHCOMMAND register commands */
+#define DOCG4_CMD_PAGE_READ             0x00
+#define DOC_CMD_ERASECYCLE2		0xd0
+#define DOCG4_CMD_FLUSH                 0x70
+#define DOCG4_CMD_READ2                 0x30
+#define DOC_CMD_PROG_BLOCK_ADDR		0x60
+#define DOCG4_CMD_PAGEWRITE		0x80
+#define DOC_CMD_PROG_CYCLE2		0x10
+#define DOC_CMD_RESET			0xff
+
+/* DOC_POWERMODE register bits */
+#define DOC_POWERDOWN_READY		0x80
+
+/* DOC_FLASHCONTROL register bits */
+#define DOC_CTRL_CE			0x10
+#define DOC_CTRL_UNKNOWN		0x40
+#define DOC_CTRL_FLASHREADY		0x01
+
+/* DOC_ECCCONF0 register bits */
+#define DOC_ECCCONF0_READ_MODE		0x8000
+#define DOC_ECCCONF0_UNKNOWN		0x2000
+#define DOC_ECCCONF0_ECC_ENABLE	        0x1000
+#define DOC_ECCCONF0_DATA_BYTES_MASK	0x07ff
+
+/* DOC_ECCCONF1 register bits */
+#define DOC_ECCCONF1_BCH_SYNDROM_ERR	0x80
+#define DOC_ECCCONF1_ECC_ENABLE         0x07
+#define DOC_ECCCONF1_PAGE_IS_WRITTEN	0x20
+
+/* DOC_ASICMODE register bits */
+#define DOC_ASICMODE_RESET		0x00
+#define DOC_ASICMODE_NORMAL		0x01
+#define DOC_ASICMODE_POWERDOWN		0x02
+#define DOC_ASICMODE_MDWREN		0x04
+#define DOC_ASICMODE_BDETCT_RESET	0x08
+#define DOC_ASICMODE_RSTIN_RESET	0x10
+#define DOC_ASICMODE_RAM_WE		0x20
+
+/* good status values read after read/write/erase operations */
+#define DOCG4_PROGSTATUS_GOOD          0x51
+#define DOCG4_PROGSTATUS_GOOD_2        0xe0
+
+/*
+ * On read operations (page and oob-only), the first byte read from I/O reg is a
+ * status.  On error, it reads 0x73; otherwise, it reads either 0x71 (first read
+ * after reset only) or 0x51, so bit 1 is presumed to be an error indicator.
+ */
+#define DOCG4_READ_ERROR           0x02 /* bit 1 indicates read error */
+
+/* anatomy of the device */
+#define DOCG4_CHIP_SIZE        0x8000000
+#define DOCG4_PAGE_SIZE        0x200
+#define DOCG4_PAGES_PER_BLOCK  0x200
+#define DOCG4_BLOCK_SIZE       (DOCG4_PAGES_PER_BLOCK * DOCG4_PAGE_SIZE)
+#define DOCG4_NUMBLOCKS        (DOCG4_CHIP_SIZE / DOCG4_BLOCK_SIZE)
+#define DOCG4_OOB_SIZE         0x10
+#define DOCG4_CHIP_SHIFT       27    /* log_2(DOCG4_CHIP_SIZE) */
+#define DOCG4_PAGE_SHIFT       9     /* log_2(DOCG4_PAGE_SIZE) */
+#define DOCG4_ERASE_SHIFT      18    /* log_2(DOCG4_BLOCK_SIZE) */
+
+/* all but the last byte is included in ecc calculation */
+#define DOCG4_BCH_SIZE         (DOCG4_PAGE_SIZE + DOCG4_OOB_SIZE - 1)
+
+#define DOCG4_USERDATA_LEN     520 /* 512 byte page plus 8 oob avail to user */
+
+/* expected values from the ID registers */
+#define DOCG4_IDREG1_VALUE     0x0400
+#define DOCG4_IDREG2_VALUE     0xfbff
+
+/* primitive polynomial used to build the Galois field used by hw ecc gen */
+#define DOCG4_PRIMITIVE_POLY   0x4443
+
+#define DOCG4_M                14  /* Galois field is of order 2^14 */
+#define DOCG4_T                4   /* BCH alg corrects up to 4 bit errors */
+
+#define DOCG4_FACTORY_BBT_PAGE 16 /* page where read-only factory bbt lives */
+
+/*
+ * Oob bytes 0 - 6 are available to the user.
+ * Byte 7 is hamming ecc for first 7 bytes.  Bytes 8 - 14 are hw-generated ecc.
+ * Byte 15 (the last) is used by the driver as a "page written" flag.
+ */
+static struct nand_ecclayout docg4_oobinfo = {
+	.eccbytes = 9,
+	.eccpos = {7, 8, 9, 10, 11, 12, 13, 14, 15},
+	.oobavail = 7,
+	.oobfree = { {0, 7} }
+};
+
+/*
+ * The device has a nop register which M-Sys claims is for the purpose of
+ * inserting precise delays.  But beware; at least some operations fail if the
+ * nop writes are replaced with a generic delay!
+ */
+static inline void write_nop(void __iomem *docptr)
+{
+	writew(0, docptr + DOC_NOP);
+}
+
+static void docg4_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
+{
+	int i;
+	struct nand_chip *nand = mtd->priv;
+	uint16_t *p = (uint16_t *) buf;
+	len >>= 1;
+
+	for (i = 0; i < len; i++)
+		p[i] = readw(nand->IO_ADDR_R);
+}
+
+static void docg4_write_buf16(struct mtd_info *mtd, const uint8_t *buf, int len)
+{
+	int i;
+	struct nand_chip *nand = mtd->priv;
+	uint16_t *p = (uint16_t *) buf;
+	len >>= 1;
+
+	for (i = 0; i < len; i++)
+		writew(p[i], nand->IO_ADDR_W);
+}
+
+static int poll_status(struct docg4_priv *doc)
+{
+	/*
+	 * Busy-wait for the FLASHREADY bit to be set in the FLASHCONTROL
+	 * register.  Operations known to take a long time (e.g., block erase)
+	 * should sleep for a while before calling this.
+	 */
+
+	uint16_t flash_status;
+	unsigned int timeo;
+	void __iomem *docptr = doc->virtadr;
+
+	dev_dbg(doc->dev, "%s...\n", __func__);
+
+	/* hardware quirk requires reading twice initially */
+	flash_status = readw(docptr + DOC_FLASHCONTROL);
+
+	timeo = 1000;
+	do {
+		cpu_relax();
+		flash_status = readb(docptr + DOC_FLASHCONTROL);
+	} while (!(flash_status & DOC_CTRL_FLASHREADY) && --timeo);
+
+
+	if (!timeo) {
+		dev_err(doc->dev, "%s: timed out!\n", __func__);
+		return NAND_STATUS_FAIL;
+	}
+
+	if (unlikely(timeo < 50))
+		dev_warn(doc->dev, "%s: nearly timed out; %d remaining\n",
+			 __func__, timeo);
+
+	return 0;
+}
+
+
+static int docg4_wait(struct mtd_info *mtd, struct nand_chip *nand)
+{
+
+	struct docg4_priv *doc = nand->priv;
+	int status = NAND_STATUS_WP;       /* inverse logic?? */
+	dev_dbg(doc->dev, "%s...\n", __func__);
+
+	/* report any previously unreported error */
+	if (doc->status) {
+		status |= doc->status;
+		doc->status = 0;
+		return status;
+	}
+
+	status |= poll_status(doc);
+	return status;
+}
+
+static void docg4_select_chip(struct mtd_info *mtd, int chip)
+{
+	/*
+	 * Select among multiple cascaded chips ("floors").  Multiple floors are
+	 * not yet supported, so the only valid non-negative value is 0.
+	 */
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+
+	dev_dbg(doc->dev, "%s: chip %d\n", __func__, chip);
+
+	if (chip < 0)
+		return;		/* deselected */
+
+	if (chip > 0)
+		dev_warn(doc->dev, "multiple floors currently unsupported\n");
+
+	writew(0, docptr + DOC_DEVICESELECT);
+}
+
+static void reset(struct mtd_info *mtd)
+{
+	/* full device reset */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+
+	writew(DOC_ASICMODE_RESET | DOC_ASICMODE_MDWREN,
+	       docptr + DOC_ASICMODE);
+	writew(~(DOC_ASICMODE_RESET | DOC_ASICMODE_MDWREN),
+	       docptr + DOC_ASICMODECONFIRM);
+	write_nop(docptr);
+
+	writew(DOC_ASICMODE_NORMAL | DOC_ASICMODE_MDWREN,
+	       docptr + DOC_ASICMODE);
+	writew(~(DOC_ASICMODE_NORMAL | DOC_ASICMODE_MDWREN),
+	       docptr + DOC_ASICMODECONFIRM);
+
+	writew(DOC_ECCCONF1_ECC_ENABLE, docptr + DOC_ECCCONF1);
+
+	poll_status(doc);
+}
+
+static void read_hw_ecc(void __iomem *docptr, uint8_t *ecc_buf)
+{
+	/* read the 7 hw-generated ecc bytes */
+
+	int i;
+	for (i = 0; i < 7; i++) { /* hw quirk; read twice */
+		ecc_buf[i] = readb(docptr + DOC_BCH_SYNDROM(i));
+		ecc_buf[i] = readb(docptr + DOC_BCH_SYNDROM(i));
+	}
+}
+
+static int correct_data(struct mtd_info *mtd, uint8_t *buf, int page)
+{
+	/*
+	 * Called after a page read when hardware reports bitflips.
+	 * Up to four bitflips can be corrected.
+	 */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+	int i, numerrs, errpos[4];
+	const uint8_t blank_read_hwecc[8] = {
+		0xcf, 0x72, 0xfc, 0x1b, 0xa9, 0xc7, 0xb9, 0 };
+
+	read_hw_ecc(docptr, doc->ecc_buf); /* read 7 hw-generated ecc bytes */
+
+	/* check if read error is due to a blank page */
+	if (!memcmp(doc->ecc_buf, blank_read_hwecc, 7))
+		return 0;	/* yes */
+
+	/* skip additional check of "written flag" if ignore_badblocks */
+	if (ignore_badblocks == false) {
+
+		/*
+		 * If the hw ecc bytes are not those of a blank page, there's
+		 * still a chance that the page is blank, but was read with
+		 * errors.  Check the "written flag" in last oob byte, which
+		 * is set to zero when a page is written.  If more than half
+		 * the bits are set, assume a blank page.  Unfortunately, the
+		 * bit flips(s) are not reported in stats.
+		 */
+
+		if (doc->oob_buf[15]) {
+			int bit, numsetbits = 0;
+			unsigned long written_flag = doc->oob_buf[15];
+			for_each_set_bit(bit, &written_flag, 8)
+				numsetbits++;
+			if (numsetbits > 4) { /* assume blank */
+				dev_warn(doc->dev,
+					 "error(s) in blank page "
+					 "at offset %08x\n",
+					 page * DOCG4_PAGE_SIZE);
+				return 0;
+			}
+		}
+	}
+
+	/*
+	 * The hardware ecc unit produces oob_ecc ^ calc_ecc.  The kernel's bch
+	 * algorithm is used to decode this.  However the hw operates on page
+	 * data in a bit order that is the reverse of that of the bch alg,
+	 * requiring that the bits be reversed on the result.  Thanks to Ivan
+	 * Djelic for his analysis!
+	 */
+	for (i = 0; i < 7; i++)
+		doc->ecc_buf[i] = bitrev8(doc->ecc_buf[i]);
+
+	numerrs = decode_bch(doc->bch, NULL, DOCG4_USERDATA_LEN, NULL,
+			     doc->ecc_buf, NULL, errpos);
+
+	if (numerrs == -EBADMSG) {
+		dev_warn(doc->dev, "uncorrectable errors at offset %08x\n",
+			 page * DOCG4_PAGE_SIZE);
+		return -EBADMSG;
+	}
+
+	BUG_ON(numerrs < 0);	/* -EINVAL, or anything other than -EBADMSG */
+
+	/* undo last step in BCH alg (modulo mirroring not needed) */
+	for (i = 0; i < numerrs; i++)
+		errpos[i] = (errpos[i] & ~7)|(7-(errpos[i] & 7));
+
+	/* fix the errors */
+	for (i = 0; i < numerrs; i++) {
+
+		/* ignore if error within oob ecc bytes */
+		if (errpos[i] > DOCG4_USERDATA_LEN * 8)
+			continue;
+
+		/* if error within oob area preceeding ecc bytes... */
+		if (errpos[i] > DOCG4_PAGE_SIZE * 8)
+			change_bit(errpos[i] - DOCG4_PAGE_SIZE * 8,
+				   (unsigned long *)doc->oob_buf);
+
+		else    /* error in page data */
+			change_bit(errpos[i], (unsigned long *)buf);
+	}
+
+	dev_notice(doc->dev, "%d error(s) corrected at offset %08x\n",
+		   numerrs, page * DOCG4_PAGE_SIZE);
+
+	return numerrs;
+}
+
+static uint8_t docg4_read_byte(struct mtd_info *mtd)
+{
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+
+	dev_dbg(doc->dev, "%s\n", __func__);
+
+	if (doc->last_command.command == NAND_CMD_STATUS) {
+		int status;
+
+		/*
+		 * Previous nand command was status request, so nand
+		 * infrastructure code expects to read the status here.  If an
+		 * error occurred in a previous operation, report it.
+		 */
+		doc->last_command.command = 0;
+
+		if (doc->status) {
+			status = doc->status;
+			doc->status = 0;
+		}
+
+		/* why is NAND_STATUS_WP inverse logic?? */
+		else
+			status = NAND_STATUS_WP | NAND_STATUS_READY;
+
+		return status;
+	}
+
+	dev_warn(doc->dev, "unexpectd call to read_byte()\n");
+
+	return 0;
+}
+
+static void write_addr(struct docg4_priv *doc, uint32_t docg4_addr)
+{
+	/* write the four address bytes packed in docg4_addr to the device */
+
+	void __iomem *docptr = doc->virtadr;
+	writeb(docg4_addr & 0xff, docptr + DOC_FLASHADDRESS);
+	docg4_addr >>= 8;
+	writeb(docg4_addr & 0xff, docptr + DOC_FLASHADDRESS);
+	docg4_addr >>= 8;
+	writeb(docg4_addr & 0xff, docptr + DOC_FLASHADDRESS);
+	docg4_addr >>= 8;
+	writeb(docg4_addr & 0xff, docptr + DOC_FLASHADDRESS);
+}
+
+static int read_progstatus(struct docg4_priv *doc)
+{
+	/*
+	 * This apparently checks the status of programming.  Done after an
+	 * erasure, and after page data is written.  On error, the status is
+	 * saved, to be later retrieved by the nand infrastructure code.
+	 */
+	void __iomem *docptr = doc->virtadr;
+
+	/* status is read from the I/O reg */
+	uint16_t status1 = readw(docptr + DOC_IOSPACE_DATA);
+	uint16_t status2 = readw(docptr + DOC_IOSPACE_DATA);
+	uint16_t status3 = readw(docptr + DOCG4_MYSTERY_REG);
+
+	dev_dbg(doc->dev, "docg4: %s: %02x %02x %02x\n",
+	      __func__, status1, status2, status3);
+
+	if (status1 != DOCG4_PROGSTATUS_GOOD
+	    || status2 != DOCG4_PROGSTATUS_GOOD_2
+	    || status3 != DOCG4_PROGSTATUS_GOOD_2) {
+		doc->status = NAND_STATUS_FAIL;
+		dev_warn(doc->dev, "read_progstatus failed: "
+			 "%02x, %02x, %02x\n", status1, status2, status3);
+		return -EIO;
+	}
+	return 0;
+}
+
+static int pageprog(struct mtd_info *mtd)
+{
+	/*
+	 * Final step in writing a page.  Writes the contents of its
+	 * internal buffer out to the flash array, or some such.
+	 */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+	int retval = 0;
+
+	dev_dbg(doc->dev, "docg4: %s\n", __func__);
+
+	writew(DOCG4_SEQ_PAGEPROG, docptr + DOC_FLASHSEQUENCE);
+	writew(DOC_CMD_PROG_CYCLE2, docptr + DOC_FLASHCOMMAND);
+	write_nop(docptr);
+	write_nop(docptr);
+
+	/* Just busy-wait; usleep_range() slows things down noticeably. */
+	poll_status(doc);
+
+	writew(DOCG4_SEQ_FLUSH, docptr + DOC_FLASHSEQUENCE);
+	writew(DOCG4_CMD_FLUSH, docptr + DOC_FLASHCOMMAND);
+	writew(DOC_ECCCONF0_READ_MODE | 4, docptr + DOC_ECCCONF0);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+
+	retval = read_progstatus(doc);
+	writew(0, docptr + DOC_DATAEND);
+	write_nop(docptr);
+	poll_status(doc);
+	write_nop(docptr);
+
+	return retval;
+}
+
+static void sequence_reset(struct mtd_info *mtd)
+{
+	/* common starting sequence for all operations */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+
+	writew(DOC_CTRL_UNKNOWN | DOC_CTRL_CE, docptr + DOC_FLASHCONTROL);
+	writew(DOC_SEQ_RESET, docptr + DOC_FLASHSEQUENCE);
+	writew(DOC_CMD_RESET, docptr + DOC_FLASHCOMMAND);
+	write_nop(docptr);
+	write_nop(docptr);
+	poll_status(doc);
+	write_nop(docptr);
+}
+
+static void read_page_prologue(struct mtd_info *mtd, uint32_t docg4_addr)
+{
+	/* first step in reading a page */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+
+	dev_dbg(doc->dev,
+	      "docg4: %s: g4 page %08x\n", __func__, docg4_addr);
+
+	sequence_reset(mtd);
+
+	writew(DOCG4_SEQ_PAGE_READ, docptr + DOC_FLASHSEQUENCE);
+	writew(DOCG4_CMD_PAGE_READ, docptr + DOC_FLASHCOMMAND);
+	write_nop(docptr);
+
+	write_addr(doc, docg4_addr);
+
+	write_nop(docptr);
+	writew(DOCG4_CMD_READ2, docptr + DOC_FLASHCOMMAND);
+	write_nop(docptr);
+	write_nop(docptr);
+
+	poll_status(doc);
+}
+
+static void write_page_prologue(struct mtd_info *mtd, uint32_t docg4_addr)
+{
+	/* first step in writing a page */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+
+	dev_dbg(doc->dev,
+	      "docg4: %s: g4 addr: %x\n", __func__, docg4_addr);
+	sequence_reset(mtd);
+	writew(DOCG4_SEQ_PAGEWRITE, docptr + DOC_FLASHSEQUENCE);
+	writew(DOCG4_CMD_PAGEWRITE, docptr + DOC_FLASHCOMMAND);
+	write_nop(docptr);
+	write_addr(doc, docg4_addr);
+	write_nop(docptr);
+	write_nop(docptr);
+	poll_status(doc);
+}
+
+static uint32_t mtd_to_docg4_address(int page, int column)
+{
+	/*
+	 * Convert mtd address to format used by the device, 32 bit packed.
+	 *
+	 * Some notes on G4 addressing... The M-Sys documentation on this device
+	 * claims that pages are 2K in length, and indeed, the format of the
+	 * address used by the device reflects that.  But within each page are
+	 * four 512 byte "sub-pages", each with its own oob data that is
+	 * read/written immediately after the 512 bytes of page data.  This oob
+	 * data contains the ecc bytes for the preceeding 512 bytes.
+	 *
+	 * Rather than tell the mtd nand infrastructure that page size is 2k,
+	 * with four sub-pages each, we engage in a little subterfuge and tell
+	 * the infrastructure code that pages are 512 bytes in size.  This is
+	 * done because during the course of reverse-engineering the device, I
+	 * never observed an instance where an entire 2K "page" was read or
+	 * written as a unit.  Each "sub-page" is always addressed individually,
+	 * its data read/written, and ecc handled before the next "sub-page" is
+	 * addressed.
+	 *
+	 * This requires us to convert addresses passed by the mtd nand
+	 * infrastructure code to those used by the device.
+	 *
+	 * The address that is written to the device consists of four bytes: the
+	 * first two are the 2k page number, and the second is the index into
+	 * the page.  The index is in terms of 16-bit half-words and includes
+	 * the preceeding oob data, so e.g., the index into the second
+	 * "sub-page" is 0x108, and the full device address of the start of mtd
+	 * page 0x201 is 0x00800108.
+	 */
+	int g4_page = page / 4;	                      /* device's 2K page */
+	int g4_index = (page % 4) * 0x108 + column/2; /* offset into page */
+	return (g4_page << 16) | g4_index;	      /* pack */
+}
+
+static void docg4_command(struct mtd_info *mtd, unsigned command, int column,
+			  int page_addr)
+{
+	/* handle standard nand commands */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	uint32_t g4_addr = mtd_to_docg4_address(page_addr, column);
+
+	dev_dbg(doc->dev, "%s %x, page_addr=%x, column=%x\n",
+	      __func__, command, page_addr, column);
+
+	/*
+	 * Save the command and its arguments.  This enables emulation of
+	 * standard flash devices, and also some optimizations.
+	 */
+	doc->last_command.command = command;
+	doc->last_command.column = column;
+	doc->last_command.page = page_addr;
+
+	switch (command) {
+
+	case NAND_CMD_RESET:
+		reset(mtd);
+		break;
+
+	case NAND_CMD_READ0:
+		read_page_prologue(mtd, g4_addr);
+		break;
+
+	case NAND_CMD_STATUS:
+		/* next call to read_byte() will expect a status */
+		break;
+
+	case NAND_CMD_SEQIN:
+		write_page_prologue(mtd, g4_addr);
+
+		/* hack for deferred write of oob bytes */
+		if (doc->oob_page == page_addr)
+			memcpy(nand->oob_poi, doc->oob_buf, 16);
+		break;
+
+	case NAND_CMD_PAGEPROG:
+		pageprog(mtd);
+		break;
+
+	/* we don't expect these, based on review of nand_base.c */
+	case NAND_CMD_READOOB:
+	case NAND_CMD_READID:
+	case NAND_CMD_ERASE1:
+	case NAND_CMD_ERASE2:
+		dev_warn(doc->dev, "docg4_command: "
+			 "unexpected nand command 0x%x\n", command);
+		break;
+
+	}
+}
+
+static int read_page(struct mtd_info *mtd, struct nand_chip *nand,
+		     uint8_t *buf, int page, bool use_ecc)
+{
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+	uint16_t status, edc_err, *buf16;
+
+	dev_dbg(doc->dev, "%s: page %08x\n", __func__, page);
+
+	writew(DOC_ECCCONF0_READ_MODE |
+	       DOC_ECCCONF0_ECC_ENABLE |
+	       DOC_ECCCONF0_UNKNOWN |
+	       DOCG4_BCH_SIZE,
+	       docptr + DOC_ECCCONF0);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+
+	/* the 1st byte from the I/O reg is a status; the rest is page data */
+	status = readw(docptr + DOC_IOSPACE_DATA);
+	if (status & DOCG4_READ_ERROR) {
+		dev_err(doc->dev,
+			"docg4_read_page: bad status: 0x%02x\n", status);
+		writew(0, docptr + DOC_DATAEND);
+		return -EIO;
+	}
+
+	dev_dbg(doc->dev, "%s: status = 0x%x\n", __func__, status);
+
+	docg4_read_buf(mtd, buf, DOCG4_PAGE_SIZE); /* read the page data */
+
+	/*
+	 * Diskonchips read oob immediately after a page read.  Mtd
+	 * infrastructure issues a separate command for reading oob after the
+	 * page is read.  So we save the oob bytes in a local buffer and just
+	 * copy it if the next command reads oob from the same page.
+	 */
+
+	/* first 14 oob bytes read from I/O reg */
+	docg4_read_buf(mtd, doc->oob_buf, 14);
+
+	/* last 2 read from another reg */
+	buf16 = (uint16_t *)(doc->oob_buf + 14);
+	*buf16 = readw(docptr + DOCG4_MYSTERY_REG);
+
+	write_nop(docptr);
+
+	if (likely(use_ecc == true)) {
+
+		/* read the register that tells us if bitflip(s) detected  */
+		edc_err = readw(docptr + DOC_ECCCONF1);
+		edc_err = readw(docptr + DOC_ECCCONF1);
+		dev_dbg(doc->dev, "%s: edc_err = 0x%02x\n", __func__, edc_err);
+
+		/* If bitflips are reported, attempt to correct with ecc */
+		if (edc_err & DOC_ECCCONF1_BCH_SYNDROM_ERR) {
+			int bits_corrected = correct_data(mtd, buf, page);
+			if (bits_corrected == -EBADMSG)
+				mtd->ecc_stats.failed++;
+			else
+				mtd->ecc_stats.corrected += bits_corrected;
+		}
+	}
+
+	writew(0, docptr + DOC_DATAEND);
+	return 0;
+}
+
+
+static int docg4_read_page_raw(struct mtd_info *mtd, struct nand_chip *nand,
+			       uint8_t *buf, int page)
+{
+	return read_page(mtd, nand, buf, page, false);
+}
+
+static int docg4_read_page(struct mtd_info *mtd, struct nand_chip *nand,
+			   uint8_t *buf, int page)
+{
+	return read_page(mtd, nand, buf, page, true);
+}
+
+static int docg4_read_oob(struct mtd_info *mtd, struct nand_chip *nand,
+			  int page, int sndcmd)
+{
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+	uint16_t status;
+
+	dev_dbg(doc->dev, "%s: page %x\n", __func__, page);
+
+	/*
+	 * Oob bytes are read as part of a normal page read.  If the previous
+	 * nand command was a read of the page whose oob is now being read, just
+	 * copy the oob bytes that we saved in a local buffer and avoid a
+	 * separate oob read.
+	 */
+	if (doc->last_command.command == NAND_CMD_READ0 &&
+	    doc->last_command.page == page) {
+		memcpy(nand->oob_poi, doc->oob_buf, 16);
+		return 0;
+	}
+
+	/*
+	 * Separate read of oob data only.
+	 */
+	docg4_command(mtd, NAND_CMD_READ0, nand->ecc.size, page);
+
+	writew(DOC_ECCCONF0_READ_MODE | DOCG4_OOB_SIZE, docptr + DOC_ECCCONF0);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+
+	/* the 1st byte from the I/O reg is a status; the rest is oob data */
+	status = readw(docptr + DOC_IOSPACE_DATA);
+	if (status & DOCG4_READ_ERROR) {
+		dev_warn(doc->dev,
+			 "docg4_read_oob failed: status = 0x%02x\n", status);
+		return -EIO;
+	}
+
+	dev_dbg(doc->dev, "%s: status = 0x%x\n", __func__, status);
+
+	docg4_read_buf(mtd, nand->oob_poi, 16);
+
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	writew(0, docptr + DOC_DATAEND);
+	write_nop(docptr);
+
+	return 0;
+}
+
+static void docg4_erase_block(struct mtd_info *mtd, int page)
+{
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+	uint16_t g4_page;
+
+	dev_dbg(doc->dev, "%s: page %04x\n", __func__, page);
+
+	sequence_reset(mtd);
+
+	writew(DOCG4_SEQ_BLOCKERASE, docptr + DOC_FLASHSEQUENCE);
+	writew(DOC_CMD_PROG_BLOCK_ADDR, docptr + DOC_FLASHCOMMAND);
+	write_nop(docptr);
+
+	/* only 2 bytes of address are written to specify erase block */
+	g4_page = (uint16_t)(page / 4);  /* to g4's 2k page addressing */
+	writeb(g4_page & 0xff, docptr + DOC_FLASHADDRESS);
+	g4_page >>= 8;
+	writeb(g4_page & 0xff, docptr + DOC_FLASHADDRESS);
+	write_nop(docptr);
+
+	/* start the erasure */
+	writew(DOC_CMD_ERASECYCLE2, docptr + DOC_FLASHCOMMAND);
+	write_nop(docptr);
+	write_nop(docptr);
+
+	usleep_range(500, 1000); /* erasure is long; take a snooze */
+	poll_status(doc);
+	writew(DOCG4_SEQ_FLUSH, docptr + DOC_FLASHSEQUENCE);
+	writew(DOCG4_CMD_FLUSH, docptr + DOC_FLASHCOMMAND);
+	writew(DOC_ECCCONF0_READ_MODE | 4, docptr + DOC_ECCCONF0);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+	write_nop(docptr);
+
+	read_progstatus(doc);
+
+	writew(0, docptr + DOC_DATAEND);
+	write_nop(docptr);
+	poll_status(doc);
+	write_nop(docptr);
+}
+
+static void write_page(struct mtd_info *mtd, struct nand_chip *nand,
+		       const uint8_t *buf, bool use_ecc)
+{
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+	uint8_t ecc_buf[8];
+
+	dev_dbg(doc->dev, "%s...\n", __func__);
+
+	writew(DOC_ECCCONF0_ECC_ENABLE |
+	       DOC_ECCCONF0_UNKNOWN |
+	       DOCG4_BCH_SIZE,
+	       docptr + DOC_ECCCONF0);
+	write_nop(docptr);
+
+	/* write the page data */
+	docg4_write_buf16(mtd, buf, DOCG4_PAGE_SIZE);
+
+	/* oob bytes 0 through 5 are written to I/O reg */
+	docg4_write_buf16(mtd, nand->oob_poi, 6);
+
+	/* oob byte 6 written to a separate reg */
+	writew(nand->oob_poi[6], docptr + DOCG4_OOB_6_7);
+
+	write_nop(docptr);
+	write_nop(docptr);
+
+	/* write hw-generated ecc bytes to oob */
+	if (likely(use_ecc == true)) {
+		/* oob byte 7 is hamming code */
+		uint8_t hamming = readb(docptr + DOC_HAMMINGPARITY);
+		hamming = readb(docptr + DOC_HAMMINGPARITY); /* 2nd read */
+		writew(hamming, docptr + DOCG4_OOB_6_7);
+		write_nop(docptr);
+
+		/* read the 7 bch bytes from ecc regs */
+		read_hw_ecc(docptr, ecc_buf);
+		ecc_buf[7] = 0;         /* clear the "page written" flag */
+	}
+
+	/* write user-supplied bytes to oob */
+	else {
+		writew(nand->oob_poi[7], docptr + DOCG4_OOB_6_7);
+		write_nop(docptr);
+		memcpy(ecc_buf, &nand->oob_poi[8], 8);
+	}
+
+	docg4_write_buf16(mtd, ecc_buf, 8);
+	write_nop(docptr);
+	write_nop(docptr);
+	writew(0, docptr + DOC_DATAEND);
+	write_nop(docptr);
+}
+
+static void docg4_write_page_raw(struct mtd_info *mtd, struct nand_chip *nand,
+				 const uint8_t *buf)
+{
+	return write_page(mtd, nand, buf, false);
+}
+
+static void docg4_write_page(struct mtd_info *mtd, struct nand_chip *nand,
+			     const uint8_t *buf)
+{
+	return write_page(mtd, nand, buf, true);
+}
+
+static int docg4_write_oob(struct mtd_info *mtd, struct nand_chip *nand,
+			   int page)
+{
+	/*
+	 * Writing oob-only is not really supported, because MLC nand must write
+	 * oob bytes at the same time as page data.  Nonetheless, we save the
+	 * oob buffer contents here, and then write it along with the page data
+	 * if the same page is subsequently written.  This allows user space
+	 * utilities that write the oob data prior to the page data to work
+	 * (e.g., nandwrite).  The disdvantage is that, if the intention was to
+	 * write oob only, the operation is quietly ignored.  Also, oob can get
+	 * corrupted if two concurrent processes are running nandwrite.
+	 */
+
+	/* note that bytes 7..14 are hw generated hamming/ecc and overwritten */
+	struct docg4_priv *doc = nand->priv;
+	doc->oob_page = page;
+	memcpy(doc->oob_buf, nand->oob_poi, 16);
+	return 0;
+}
+
+static int __init read_factory_bbt(struct mtd_info *mtd)
+{
+	/*
+	 * The device contains a read-only factory bad block table.  Read it and
+	 * update the memory-based bbt accordingly.
+	 */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	uint32_t g4_addr = mtd_to_docg4_address(DOCG4_FACTORY_BBT_PAGE, 0);
+	uint8_t *buf;
+	int i, block, status;
+
+	buf = kzalloc(DOCG4_PAGE_SIZE, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	read_page_prologue(mtd, g4_addr);
+	status = docg4_read_page(mtd, nand, buf, DOCG4_FACTORY_BBT_PAGE);
+	if (status)
+		goto exit;
+
+	/*
+	 * If no memory-based bbt was created, exit.  This will happen if module
+	 * parameter ignore_badblocks is set.  Then why even call this function?
+	 * For an unknown reason, block erase always fails if it's the first
+	 * operation after device power-up.  The above read ensures it never is.
+	 * Ugly, I know.
+	 */
+	if (nand->bbt == NULL)  /* no memory-based bbt */
+		goto exit;
+
+	/*
+	 * Parse factory bbt and update memory-based bbt.  Factory bbt format is
+	 * simple: one bit per block, block numbers increase left to right (msb
+	 * to lsb).  Bit clear means bad block.
+	 */
+	for (i = block = 0; block < DOCG4_NUMBLOCKS; block += 8, i++) {
+		int bitnum;
+		unsigned long bits = ~buf[i];
+		for_each_set_bit(bitnum, &bits, 8) {
+			int badblock = block + 7 - bitnum;
+			nand->bbt[badblock / 4] |=
+				0x03 << ((badblock % 4) * 2);
+			mtd->ecc_stats.badblocks++;
+			dev_notice(doc->dev, "factory-marked bad block: %d\n",
+				   badblock);
+		}
+	}
+ exit:
+	kfree(buf);
+	return status;
+}
+
+static int docg4_block_markbad(struct mtd_info *mtd, loff_t ofs)
+{
+	/*
+	 * Mark a block as bad.  Bad blocks are marked in the oob area of the
+	 * first page of the block.  The default scan_bbt() in the nand
+	 * infrastructure code works fine for building the memory-based bbt
+	 * during initialization, as does the nand infrastructure function that
+	 * checks if a block is bad by reading the bbt.  This function replaces
+	 * the nand default because writes to oob-only are not supported.
+	 */
+
+	int ret, i;
+	uint8_t *buf;
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	struct nand_bbt_descr *bbtd = nand->badblock_pattern;
+	int block = (int)(ofs >> nand->bbt_erase_shift);
+	int page = (int)(ofs >> nand->page_shift);
+	uint32_t g4_addr = mtd_to_docg4_address(page, 0);
+
+	dev_dbg(doc->dev, "%s: %08llx\n", __func__, ofs);
+
+	if (unlikely(ofs & (DOCG4_BLOCK_SIZE - 1)))
+		dev_warn(doc->dev, "%s: ofs %llx not start of block!\n",
+			 __func__, ofs);
+
+	/* allocate blank buffer for page data */
+	buf = kzalloc(DOCG4_PAGE_SIZE, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	/* update bbt in memory */
+	nand->bbt[block / 4] |= 0x01 << ((block & 0x03) * 2);
+
+	/* write bit-wise negation of pattern to oob buffer */
+	memset(nand->oob_poi, 0xff, mtd->oobsize);
+	for (i = 0; i < bbtd->len; i++)
+		nand->oob_poi[bbtd->offs + i] = ~bbtd->pattern[i];
+
+	/* write first page of block */
+	write_page_prologue(mtd, g4_addr);
+	docg4_write_page(mtd, nand, buf);
+	ret = pageprog(mtd);
+	if (!ret)
+		mtd->ecc_stats.badblocks++;
+
+	kfree(buf);
+
+	return ret;
+}
+
+static int docg4_block_neverbad(struct mtd_info *mtd, loff_t ofs, int getchip)
+{
+	/* only called when module_param ignore_badblocks is set */
+	return 0;
+}
+
+static int docg4_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	/*
+	 * Put the device into "deep power-down" mode.  Note that CE# must be
+	 * deasserted for this to take effect.  The xscale, e.g., can be
+	 * configured to float this signal when the processor enters power-down,
+	 * and a suitable pull-up ensures its deassertion.
+	 */
+
+	int i;
+	uint8_t pwr_down;
+	struct docg4_priv *doc = platform_get_drvdata(pdev);
+	void __iomem *docptr = doc->virtadr;
+
+	dev_dbg(doc->dev, "%s...\n", __func__);
+
+	/* poll the register that tells us we're ready to go to sleep */
+	for (i = 0; i < 10; i++) {
+		pwr_down = readb(docptr + DOC_POWERMODE);
+		if (pwr_down & DOC_POWERDOWN_READY)
+			break;
+		usleep_range(1000, 4000);
+	}
+
+	if (pwr_down & DOC_POWERDOWN_READY) {
+		dev_err(doc->dev, "suspend failed; "
+			"timeout polling DOC_POWERDOWN_READY\n");
+		return -EIO;
+	}
+
+	writew(DOC_ASICMODE_POWERDOWN | DOC_ASICMODE_MDWREN,
+	       docptr + DOC_ASICMODE);
+	writew(~(DOC_ASICMODE_POWERDOWN | DOC_ASICMODE_MDWREN),
+	       docptr + DOC_ASICMODECONFIRM);
+
+	write_nop(docptr);
+
+	return 0;
+}
+
+static int docg4_resume(struct platform_device *pdev)
+{
+
+	/*
+	 * Exit power-down.  Twelve consecutive reads of the address below
+	 * accomplishes this, assuming CE# has been asserted.
+	 */
+
+	struct docg4_priv *doc = platform_get_drvdata(pdev);
+	void __iomem *docptr = doc->virtadr;
+	int i;
+
+	dev_dbg(doc->dev, "%s...\n", __func__);
+
+	for (i = 0; i < 12; i++)
+		readb(docptr + 0x1fff);
+
+	return 0;
+}
+
+static void __init init_mtd_structs(struct mtd_info *mtd)
+{
+	/* initialize mtd and nand data structures */
+
+	/*
+	 * Note that some of the following initializations are not usually
+	 * required within a nand driver because they are performed by the nand
+	 * infrastructure code as part of nand_scan().  In this case they need
+	 * to be initialized here because we skip call to nand_scan_ident() (the
+	 * first half of nand_scan()).  The call to nand_scan_ident() is skipped
+	 * because for this device the chip id is not read in the manner of a
+	 * standard nand device.  Unfortunately, nand_scan_ident() does other
+	 * things as well, such as call nand_set_defaults().
+	 */
+
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+
+	mtd->size = DOCG4_CHIP_SIZE;
+	mtd->name = "Msys_Diskonchip_G4";
+	mtd->writesize = DOCG4_PAGE_SIZE;
+	mtd->erasesize = DOCG4_BLOCK_SIZE;
+	mtd->oobsize = DOCG4_OOB_SIZE;
+	nand->chipsize = DOCG4_CHIP_SIZE;
+	nand->chip_shift = DOCG4_CHIP_SHIFT;
+	nand->bbt_erase_shift = nand->phys_erase_shift = DOCG4_ERASE_SHIFT;
+	nand->chip_delay = 20;
+	nand->page_shift = DOCG4_PAGE_SHIFT;
+	nand->pagemask = 0x3ffff;
+	nand->badblockpos = NAND_LARGE_BADBLOCK_POS;
+	nand->badblockbits = 8;
+	nand->ecc.layout = &docg4_oobinfo;
+	nand->ecc.mode = NAND_ECC_HW_SYNDROME;
+	nand->ecc.size = DOCG4_PAGE_SIZE;
+	nand->ecc.prepad = 8;
+	nand->ecc.bytes	= 8;
+	nand->ecc.strength = DOCG4_T;
+	nand->options =
+		NAND_BUSWIDTH_16 | NAND_NO_SUBPAGE_WRITE | NAND_NO_AUTOINCR;
+	nand->IO_ADDR_R = nand->IO_ADDR_W = doc->virtadr + DOC_IOSPACE_DATA;
+	nand->controller = &nand->hwcontrol;
+	spin_lock_init(&nand->controller->lock);
+	init_waitqueue_head(&nand->controller->wq);
+
+	/* methods */
+	nand->cmdfunc = docg4_command;
+	nand->waitfunc = docg4_wait;
+	nand->select_chip = docg4_select_chip;
+	nand->read_byte = docg4_read_byte;
+	nand->block_markbad = docg4_block_markbad;
+	nand->read_buf = docg4_read_buf;
+	nand->write_buf = docg4_write_buf16;
+	nand->scan_bbt = nand_default_bbt;
+	nand->erase_cmd = docg4_erase_block;
+	nand->ecc.read_page = docg4_read_page;
+	nand->ecc.write_page = docg4_write_page;
+	nand->ecc.read_page_raw = docg4_read_page_raw;
+	nand->ecc.write_page_raw = docg4_write_page_raw;
+	nand->ecc.read_oob = docg4_read_oob;
+	nand->ecc.write_oob = docg4_write_oob;
+
+	/*
+	 * The way the nand infrastructure code is written, a memory-based bbt
+	 * is not created if NAND_SKIP_BBTSCAN is set.  With no memory bbt,
+	 * nand->block_bad() is used.  So when ignoring bad blocks, we skip the
+	 * scan and define a dummy block_bad() which always returns 0.
+	 */
+	if (ignore_badblocks) {
+		nand->options |= NAND_SKIP_BBTSCAN;
+		nand->block_bad	= docg4_block_neverbad;
+	}
+
+}
+
+static int __init read_id_reg(struct mtd_info *mtd)
+{
+	struct nand_chip *nand = mtd->priv;
+	struct docg4_priv *doc = nand->priv;
+	void __iomem *docptr = doc->virtadr;
+	uint16_t id1, id2;
+
+	/* check for presence of g4 chip by reading id registers */
+	id1 = readw(docptr + DOC_CHIPID);
+	id1 = readw(docptr + DOCG4_MYSTERY_REG);
+	id2 = readw(docptr + DOC_CHIPID_INV);
+	id2 = readw(docptr + DOCG4_MYSTERY_REG);
+
+	if (id1 == DOCG4_IDREG1_VALUE && id2 == DOCG4_IDREG2_VALUE) {
+		dev_info(doc->dev,
+			 "NAND device: 128MiB Diskonchip G4 detected\n");
+		return 0;
+	}
+
+	return -ENODEV;
+}
+
+static char const *part_probes[] = { "cmdlinepart", "saftlpart", NULL };
+
+static int __init probe_docg4(struct platform_device *pdev)
+{
+	struct mtd_info *mtd;
+	struct nand_chip *nand;
+	void __iomem *virtadr;
+	struct docg4_priv *doc;
+	int len, retval;
+	struct resource *r;
+	struct device *dev = &pdev->dev;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (r == NULL) {
+		dev_err(dev, "no io memory resource defined!\n");
+		return -ENODEV;
+	}
+
+	virtadr = ioremap(r->start, resource_size(r));
+	if (!virtadr) {
+		dev_err(dev, "Diskonchip ioremap failed: %pR\n", r);
+		return -EIO;
+	}
+
+	len = sizeof(struct mtd_info) + sizeof(struct nand_chip) +
+		sizeof(struct docg4_priv);
+	mtd = kzalloc(len, GFP_KERNEL);
+	if (mtd == NULL) {
+		retval = -ENOMEM;
+		goto fail;
+	}
+	nand = (struct nand_chip *) (mtd + 1);
+	doc = (struct docg4_priv *) (nand + 1);
+	mtd->priv = nand;
+	nand->priv = doc;
+	mtd->owner = THIS_MODULE;
+	doc->virtadr = virtadr;
+	doc->dev = dev;
+
+	init_mtd_structs(mtd);
+
+	/* initialize kernel bch algorithm */
+	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
+	if (doc->bch == NULL) {
+		retval = -EINVAL;
+		goto fail;
+	}
+
+	platform_set_drvdata(pdev, doc);
+
+	reset(mtd);
+	retval = read_id_reg(mtd);
+	if (retval == -ENODEV) {
+		dev_warn(dev, "No diskonchip G4 device found.\n");
+		goto fail;
+	}
+
+	retval = nand_scan_tail(mtd);
+	if (retval)
+		goto fail;
+
+	retval = read_factory_bbt(mtd);
+	if (retval)
+		goto fail;
+
+	retval = mtd_device_parse_register(mtd, part_probes, NULL, NULL, 0);
+	if (retval)
+		goto fail;
+
+	doc->mtd = mtd;
+	return 0;
+
+ fail:
+	iounmap(virtadr);
+	if (mtd) {
+		/* re-declarations avoid compiler warning */
+		struct nand_chip *nand = mtd->priv;
+		struct docg4_priv *doc = nand->priv;
+		nand_release(mtd); /* deletes partitions and mtd devices */
+		platform_set_drvdata(pdev, NULL);
+		free_bch(doc->bch);
+		kfree(mtd);
+	}
+
+	return retval;
+}
+
+static int __exit cleanup_docg4(struct platform_device *pdev)
+{
+	struct docg4_priv *doc = platform_get_drvdata(pdev);
+	nand_release(doc->mtd);
+	platform_set_drvdata(pdev, NULL);
+	free_bch(doc->bch);
+	kfree(doc->mtd);
+	iounmap(doc->virtadr);
+	return 0;
+}
+
+static struct platform_driver docg4_driver = {
+	.driver		= {
+		.name	= "docg4",
+		.owner	= THIS_MODULE,
+	},
+	.suspend	= docg4_suspend,
+	.resume		= docg4_resume,
+	.remove		= __exit_p(cleanup_docg4),
+};
+
+static int __init docg4_init(void)
+{
+	return platform_driver_probe(&docg4_driver, probe_docg4);
+}
+
+static void __exit docg4_exit(void)
+{
+	platform_driver_unregister(&docg4_driver);
+}
+
+module_init(docg4_init);
+module_exit(docg4_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mike Dunn");
+MODULE_DESCRIPTION("M-Systems DiskOnChip G4 device driver");
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 7195ee6efe12..80b5264f0a32 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -813,6 +813,12 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 				&fsl_elbc_oob_sp_eccm1 : &fsl_elbc_oob_sp_eccm0;
 		chip->ecc.size = 512;
 		chip->ecc.bytes = 3;
+		chip->ecc.strength = 1;
+		/*
+		 * FIXME: can hardware ecc correct 4 bitflips if page size is
+		 * 2k?  Then does hardware report number of corrections for this
+		 * case?  If so, ecc_stats reporting needs to be fixed as well.
+		 */
 	} else {
 		/* otherwise fall back to default software ECC */
 		chip->ecc.mode = NAND_ECC_SOFT;
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index e53b76064133..1b8330e1155a 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -17,6 +17,10 @@
  */
 
 #include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-direction.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -27,6 +31,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/nand_ecc.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 #include <linux/slab.h>
@@ -34,7 +39,7 @@
 #include <linux/amba/bus.h>
 #include <mtd/mtd-abi.h>
 
-static struct nand_ecclayout fsmc_ecc1_layout = {
+static struct nand_ecclayout fsmc_ecc1_128_layout = {
 	.eccbytes = 24,
 	.eccpos = {2, 3, 4, 18, 19, 20, 34, 35, 36, 50, 51, 52,
 		66, 67, 68, 82, 83, 84, 98, 99, 100, 114, 115, 116},
@@ -50,7 +55,127 @@ static struct nand_ecclayout fsmc_ecc1_layout = {
 	}
 };
 
-static struct nand_ecclayout fsmc_ecc4_lp_layout = {
+static struct nand_ecclayout fsmc_ecc1_64_layout = {
+	.eccbytes = 12,
+	.eccpos = {2, 3, 4, 18, 19, 20, 34, 35, 36, 50, 51, 52},
+	.oobfree = {
+		{.offset = 8, .length = 8},
+		{.offset = 24, .length = 8},
+		{.offset = 40, .length = 8},
+		{.offset = 56, .length = 8},
+	}
+};
+
+static struct nand_ecclayout fsmc_ecc1_16_layout = {
+	.eccbytes = 3,
+	.eccpos = {2, 3, 4},
+	.oobfree = {
+		{.offset = 8, .length = 8},
+	}
+};
+
+/*
+ * ECC4 layout for NAND of pagesize 8192 bytes & OOBsize 256 bytes. 13*16 bytes
+ * of OB size is reserved for ECC, Byte no. 0 & 1 reserved for bad block and 46
+ * bytes are free for use.
+ */
+static struct nand_ecclayout fsmc_ecc4_256_layout = {
+	.eccbytes = 208,
+	.eccpos = {  2,   3,   4,   5,   6,   7,   8,
+		9,  10,  11,  12,  13,  14,
+		18,  19,  20,  21,  22,  23,  24,
+		25,  26,  27,  28,  29,  30,
+		34,  35,  36,  37,  38,  39,  40,
+		41,  42,  43,  44,  45,  46,
+		50,  51,  52,  53,  54,  55,  56,
+		57,  58,  59,  60,  61,  62,
+		66,  67,  68,  69,  70,  71,  72,
+		73,  74,  75,  76,  77,  78,
+		82,  83,  84,  85,  86,  87,  88,
+		89,  90,  91,  92,  93,  94,
+		98,  99, 100, 101, 102, 103, 104,
+		105, 106, 107, 108, 109, 110,
+		114, 115, 116, 117, 118, 119, 120,
+		121, 122, 123, 124, 125, 126,
+		130, 131, 132, 133, 134, 135, 136,
+		137, 138, 139, 140, 141, 142,
+		146, 147, 148, 149, 150, 151, 152,
+		153, 154, 155, 156, 157, 158,
+		162, 163, 164, 165, 166, 167, 168,
+		169, 170, 171, 172, 173, 174,
+		178, 179, 180, 181, 182, 183, 184,
+		185, 186, 187, 188, 189, 190,
+		194, 195, 196, 197, 198, 199, 200,
+		201, 202, 203, 204, 205, 206,
+		210, 211, 212, 213, 214, 215, 216,
+		217, 218, 219, 220, 221, 222,
+		226, 227, 228, 229, 230, 231, 232,
+		233, 234, 235, 236, 237, 238,
+		242, 243, 244, 245, 246, 247, 248,
+		249, 250, 251, 252, 253, 254
+	},
+	.oobfree = {
+		{.offset = 15, .length = 3},
+		{.offset = 31, .length = 3},
+		{.offset = 47, .length = 3},
+		{.offset = 63, .length = 3},
+		{.offset = 79, .length = 3},
+		{.offset = 95, .length = 3},
+		{.offset = 111, .length = 3},
+		{.offset = 127, .length = 3},
+		{.offset = 143, .length = 3},
+		{.offset = 159, .length = 3},
+		{.offset = 175, .length = 3},
+		{.offset = 191, .length = 3},
+		{.offset = 207, .length = 3},
+		{.offset = 223, .length = 3},
+		{.offset = 239, .length = 3},
+		{.offset = 255, .length = 1}
+	}
+};
+
+/*
+ * ECC4 layout for NAND of pagesize 4096 bytes & OOBsize 224 bytes. 13*8 bytes
+ * of OOB size is reserved for ECC, Byte no. 0 & 1 reserved for bad block & 118
+ * bytes are free for use.
+ */
+static struct nand_ecclayout fsmc_ecc4_224_layout = {
+	.eccbytes = 104,
+	.eccpos = {  2,   3,   4,   5,   6,   7,   8,
+		9,  10,  11,  12,  13,  14,
+		18,  19,  20,  21,  22,  23,  24,
+		25,  26,  27,  28,  29,  30,
+		34,  35,  36,  37,  38,  39,  40,
+		41,  42,  43,  44,  45,  46,
+		50,  51,  52,  53,  54,  55,  56,
+		57,  58,  59,  60,  61,  62,
+		66,  67,  68,  69,  70,  71,  72,
+		73,  74,  75,  76,  77,  78,
+		82,  83,  84,  85,  86,  87,  88,
+		89,  90,  91,  92,  93,  94,
+		98,  99, 100, 101, 102, 103, 104,
+		105, 106, 107, 108, 109, 110,
+		114, 115, 116, 117, 118, 119, 120,
+		121, 122, 123, 124, 125, 126
+	},
+	.oobfree = {
+		{.offset = 15, .length = 3},
+		{.offset = 31, .length = 3},
+		{.offset = 47, .length = 3},
+		{.offset = 63, .length = 3},
+		{.offset = 79, .length = 3},
+		{.offset = 95, .length = 3},
+		{.offset = 111, .length = 3},
+		{.offset = 127, .length = 97}
+	}
+};
+
+/*
+ * ECC4 layout for NAND of pagesize 4096 bytes & OOBsize 128 bytes. 13*8 bytes
+ * of OOB size is reserved for ECC, Byte no. 0 & 1 reserved for bad block & 22
+ * bytes are free for use.
+ */
+static struct nand_ecclayout fsmc_ecc4_128_layout = {
 	.eccbytes = 104,
 	.eccpos = {  2,   3,   4,   5,   6,   7,   8,
 		9,  10,  11,  12,  13,  14,
@@ -82,6 +207,45 @@ static struct nand_ecclayout fsmc_ecc4_lp_layout = {
 };
 
 /*
+ * ECC4 layout for NAND of pagesize 2048 bytes & OOBsize 64 bytes. 13*4 bytes of
+ * OOB size is reserved for ECC, Byte no. 0 & 1 reserved for bad block and 10
+ * bytes are free for use.
+ */
+static struct nand_ecclayout fsmc_ecc4_64_layout = {
+	.eccbytes = 52,
+	.eccpos = {  2,   3,   4,   5,   6,   7,   8,
+		9,  10,  11,  12,  13,  14,
+		18,  19,  20,  21,  22,  23,  24,
+		25,  26,  27,  28,  29,  30,
+		34,  35,  36,  37,  38,  39,  40,
+		41,  42,  43,  44,  45,  46,
+		50,  51,  52,  53,  54,  55,  56,
+		57,  58,  59,  60,  61,  62,
+	},
+	.oobfree = {
+		{.offset = 15, .length = 3},
+		{.offset = 31, .length = 3},
+		{.offset = 47, .length = 3},
+		{.offset = 63, .length = 1},
+	}
+};
+
+/*
+ * ECC4 layout for NAND of pagesize 512 bytes & OOBsize 16 bytes. 13 bytes of
+ * OOB size is reserved for ECC, Byte no. 4 & 5 reserved for bad block and One
+ * byte is free for use.
+ */
+static struct nand_ecclayout fsmc_ecc4_16_layout = {
+	.eccbytes = 13,
+	.eccpos = { 0,  1,  2,  3,  6,  7, 8,
+		9, 10, 11, 12, 13, 14
+	},
+	.oobfree = {
+		{.offset = 15, .length = 1},
+	}
+};
+
+/*
  * ECC placement definitions in oobfree type format.
  * There are 13 bytes of ecc for every 512 byte block and it has to be read
  * consecutively and immediately after the 512 byte data block for hardware to
@@ -103,16 +267,6 @@ static struct fsmc_eccplace fsmc_ecc4_lp_place = {
 	}
 };
 
-static struct nand_ecclayout fsmc_ecc4_sp_layout = {
-	.eccbytes = 13,
-	.eccpos = { 0,  1,  2,  3,  6,  7, 8,
-		9, 10, 11, 12, 13, 14
-	},
-	.oobfree = {
-		{.offset = 15, .length = 1},
-	}
-};
-
 static struct fsmc_eccplace fsmc_ecc4_sp_place = {
 	.eccplace = {
 		{.offset = 0, .length = 4},
@@ -120,75 +274,24 @@ static struct fsmc_eccplace fsmc_ecc4_sp_place = {
 	}
 };
 
-/*
- * Default partition tables to be used if the partition information not
- * provided through platform data.
- *
- * Default partition layout for small page(= 512 bytes) devices
- * Size for "Root file system" is updated in driver based on actual device size
- */
-static struct mtd_partition partition_info_16KB_blk[] = {
-	{
-		.name = "X-loader",
-		.offset = 0,
-		.size = 4*0x4000,
-	},
-	{
-		.name = "U-Boot",
-		.offset = 0x10000,
-		.size = 20*0x4000,
-	},
-	{
-		.name = "Kernel",
-		.offset = 0x60000,
-		.size = 256*0x4000,
-	},
-	{
-		.name = "Root File System",
-		.offset = 0x460000,
-		.size = MTDPART_SIZ_FULL,
-	},
-};
-
-/*
- * Default partition layout for large page(> 512 bytes) devices
- * Size for "Root file system" is updated in driver based on actual device size
- */
-static struct mtd_partition partition_info_128KB_blk[] = {
-	{
-		.name = "X-loader",
-		.offset = 0,
-		.size = 4*0x20000,
-	},
-	{
-		.name = "U-Boot",
-		.offset = 0x80000,
-		.size = 12*0x20000,
-	},
-	{
-		.name = "Kernel",
-		.offset = 0x200000,
-		.size = 48*0x20000,
-	},
-	{
-		.name = "Root File System",
-		.offset = 0x800000,
-		.size = MTDPART_SIZ_FULL,
-	},
-};
-
-
 /**
  * struct fsmc_nand_data - structure for FSMC NAND device state
  *
  * @pid:		Part ID on the AMBA PrimeCell format
  * @mtd:		MTD info for a NAND flash.
  * @nand:		Chip related info for a NAND flash.
+ * @partitions:		Partition info for a NAND Flash.
+ * @nr_partitions:	Total number of partition of a NAND flash.
  *
  * @ecc_place:		ECC placing locations in oobfree type format.
  * @bank:		Bank number for probed device.
  * @clk:		Clock structure for FSMC.
  *
+ * @read_dma_chan:	DMA channel for read access
+ * @write_dma_chan:	DMA channel for write access to NAND
+ * @dma_access_complete: Completion structure
+ *
+ * @data_pa:		NAND Physical port for Data.
  * @data_va:		NAND port for Data.
  * @cmd_va:		NAND port for Command.
  * @addr_va:		NAND port for Address.
@@ -198,16 +301,23 @@ struct fsmc_nand_data {
 	u32			pid;
 	struct mtd_info		mtd;
 	struct nand_chip	nand;
+	struct mtd_partition	*partitions;
+	unsigned int		nr_partitions;
 
 	struct fsmc_eccplace	*ecc_place;
 	unsigned int		bank;
+	struct device		*dev;
+	enum access_mode	mode;
 	struct clk		*clk;
 
-	struct resource		*resregs;
-	struct resource		*rescmd;
-	struct resource		*resaddr;
-	struct resource		*resdata;
+	/* DMA related objects */
+	struct dma_chan		*read_dma_chan;
+	struct dma_chan		*write_dma_chan;
+	struct completion	dma_access_complete;
+
+	struct fsmc_nand_timings *dev_timings;
 
+	dma_addr_t		data_pa;
 	void __iomem		*data_va;
 	void __iomem		*cmd_va;
 	void __iomem		*addr_va;
@@ -251,28 +361,29 @@ static void fsmc_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
 	struct nand_chip *this = mtd->priv;
 	struct fsmc_nand_data *host = container_of(mtd,
 					struct fsmc_nand_data, mtd);
-	struct fsmc_regs *regs = host->regs_va;
+	void *__iomem *regs = host->regs_va;
 	unsigned int bank = host->bank;
 
 	if (ctrl & NAND_CTRL_CHANGE) {
+		u32 pc;
+
 		if (ctrl & NAND_CLE) {
-			this->IO_ADDR_R = (void __iomem *)host->cmd_va;
-			this->IO_ADDR_W = (void __iomem *)host->cmd_va;
+			this->IO_ADDR_R = host->cmd_va;
+			this->IO_ADDR_W = host->cmd_va;
 		} else if (ctrl & NAND_ALE) {
-			this->IO_ADDR_R = (void __iomem *)host->addr_va;
-			this->IO_ADDR_W = (void __iomem *)host->addr_va;
+			this->IO_ADDR_R = host->addr_va;
+			this->IO_ADDR_W = host->addr_va;
 		} else {
-			this->IO_ADDR_R = (void __iomem *)host->data_va;
-			this->IO_ADDR_W = (void __iomem *)host->data_va;
+			this->IO_ADDR_R = host->data_va;
+			this->IO_ADDR_W = host->data_va;
 		}
 
-		if (ctrl & NAND_NCE) {
-			writel(readl(&regs->bank_regs[bank].pc) | FSMC_ENABLE,
-					&regs->bank_regs[bank].pc);
-		} else {
-			writel(readl(&regs->bank_regs[bank].pc) & ~FSMC_ENABLE,
-				       &regs->bank_regs[bank].pc);
-		}
+		pc = readl(FSMC_NAND_REG(regs, bank, PC));
+		if (ctrl & NAND_NCE)
+			pc |= FSMC_ENABLE;
+		else
+			pc &= ~FSMC_ENABLE;
+		writel(pc, FSMC_NAND_REG(regs, bank, PC));
 	}
 
 	mb();
@@ -287,22 +398,42 @@ static void fsmc_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
  * This routine initializes timing parameters related to NAND memory access in
  * FSMC registers
  */
-static void __init fsmc_nand_setup(struct fsmc_regs *regs, uint32_t bank,
-				   uint32_t busw)
+static void fsmc_nand_setup(void __iomem *regs, uint32_t bank,
+			   uint32_t busw, struct fsmc_nand_timings *timings)
 {
 	uint32_t value = FSMC_DEVTYPE_NAND | FSMC_ENABLE | FSMC_WAITON;
+	uint32_t tclr, tar, thiz, thold, twait, tset;
+	struct fsmc_nand_timings *tims;
+	struct fsmc_nand_timings default_timings = {
+		.tclr	= FSMC_TCLR_1,
+		.tar	= FSMC_TAR_1,
+		.thiz	= FSMC_THIZ_1,
+		.thold	= FSMC_THOLD_4,
+		.twait	= FSMC_TWAIT_6,
+		.tset	= FSMC_TSET_0,
+	};
+
+	if (timings)
+		tims = timings;
+	else
+		tims = &default_timings;
+
+	tclr = (tims->tclr & FSMC_TCLR_MASK) << FSMC_TCLR_SHIFT;
+	tar = (tims->tar & FSMC_TAR_MASK) << FSMC_TAR_SHIFT;
+	thiz = (tims->thiz & FSMC_THIZ_MASK) << FSMC_THIZ_SHIFT;
+	thold = (tims->thold & FSMC_THOLD_MASK) << FSMC_THOLD_SHIFT;
+	twait = (tims->twait & FSMC_TWAIT_MASK) << FSMC_TWAIT_SHIFT;
+	tset = (tims->tset & FSMC_TSET_MASK) << FSMC_TSET_SHIFT;
 
 	if (busw)
-		writel(value | FSMC_DEVWID_16, &regs->bank_regs[bank].pc);
+		writel(value | FSMC_DEVWID_16, FSMC_NAND_REG(regs, bank, PC));
 	else
-		writel(value | FSMC_DEVWID_8, &regs->bank_regs[bank].pc);
-
-	writel(readl(&regs->bank_regs[bank].pc) | FSMC_TCLR_1 | FSMC_TAR_1,
-	       &regs->bank_regs[bank].pc);
-	writel(FSMC_THIZ_1 | FSMC_THOLD_4 | FSMC_TWAIT_6 | FSMC_TSET_0,
-	       &regs->bank_regs[bank].comm);
-	writel(FSMC_THIZ_1 | FSMC_THOLD_4 | FSMC_TWAIT_6 | FSMC_TSET_0,
-	       &regs->bank_regs[bank].attrib);
+		writel(value | FSMC_DEVWID_8, FSMC_NAND_REG(regs, bank, PC));
+
+	writel(readl(FSMC_NAND_REG(regs, bank, PC)) | tclr | tar,
+			FSMC_NAND_REG(regs, bank, PC));
+	writel(thiz | thold | twait | tset, FSMC_NAND_REG(regs, bank, COMM));
+	writel(thiz | thold | twait | tset, FSMC_NAND_REG(regs, bank, ATTRIB));
 }
 
 /*
@@ -312,15 +443,15 @@ static void fsmc_enable_hwecc(struct mtd_info *mtd, int mode)
 {
 	struct fsmc_nand_data *host = container_of(mtd,
 					struct fsmc_nand_data, mtd);
-	struct fsmc_regs *regs = host->regs_va;
+	void __iomem *regs = host->regs_va;
 	uint32_t bank = host->bank;
 
-	writel(readl(&regs->bank_regs[bank].pc) & ~FSMC_ECCPLEN_256,
-		       &regs->bank_regs[bank].pc);
-	writel(readl(&regs->bank_regs[bank].pc) & ~FSMC_ECCEN,
-			&regs->bank_regs[bank].pc);
-	writel(readl(&regs->bank_regs[bank].pc) | FSMC_ECCEN,
-			&regs->bank_regs[bank].pc);
+	writel(readl(FSMC_NAND_REG(regs, bank, PC)) & ~FSMC_ECCPLEN_256,
+			FSMC_NAND_REG(regs, bank, PC));
+	writel(readl(FSMC_NAND_REG(regs, bank, PC)) & ~FSMC_ECCEN,
+			FSMC_NAND_REG(regs, bank, PC));
+	writel(readl(FSMC_NAND_REG(regs, bank, PC)) | FSMC_ECCEN,
+			FSMC_NAND_REG(regs, bank, PC));
 }
 
 /*
@@ -333,37 +464,42 @@ static int fsmc_read_hwecc_ecc4(struct mtd_info *mtd, const uint8_t *data,
 {
 	struct fsmc_nand_data *host = container_of(mtd,
 					struct fsmc_nand_data, mtd);
-	struct fsmc_regs *regs = host->regs_va;
+	void __iomem *regs = host->regs_va;
 	uint32_t bank = host->bank;
 	uint32_t ecc_tmp;
 	unsigned long deadline = jiffies + FSMC_BUSY_WAIT_TIMEOUT;
 
 	do {
-		if (readl(&regs->bank_regs[bank].sts) & FSMC_CODE_RDY)
+		if (readl(FSMC_NAND_REG(regs, bank, STS)) & FSMC_CODE_RDY)
 			break;
 		else
 			cond_resched();
 	} while (!time_after_eq(jiffies, deadline));
 
-	ecc_tmp = readl(&regs->bank_regs[bank].ecc1);
+	if (time_after_eq(jiffies, deadline)) {
+		dev_err(host->dev, "calculate ecc timed out\n");
+		return -ETIMEDOUT;
+	}
+
+	ecc_tmp = readl(FSMC_NAND_REG(regs, bank, ECC1));
 	ecc[0] = (uint8_t) (ecc_tmp >> 0);
 	ecc[1] = (uint8_t) (ecc_tmp >> 8);
 	ecc[2] = (uint8_t) (ecc_tmp >> 16);
 	ecc[3] = (uint8_t) (ecc_tmp >> 24);
 
-	ecc_tmp = readl(&regs->bank_regs[bank].ecc2);
+	ecc_tmp = readl(FSMC_NAND_REG(regs, bank, ECC2));
 	ecc[4] = (uint8_t) (ecc_tmp >> 0);
 	ecc[5] = (uint8_t) (ecc_tmp >> 8);
 	ecc[6] = (uint8_t) (ecc_tmp >> 16);
 	ecc[7] = (uint8_t) (ecc_tmp >> 24);
 
-	ecc_tmp = readl(&regs->bank_regs[bank].ecc3);
+	ecc_tmp = readl(FSMC_NAND_REG(regs, bank, ECC3));
 	ecc[8] = (uint8_t) (ecc_tmp >> 0);
 	ecc[9] = (uint8_t) (ecc_tmp >> 8);
 	ecc[10] = (uint8_t) (ecc_tmp >> 16);
 	ecc[11] = (uint8_t) (ecc_tmp >> 24);
 
-	ecc_tmp = readl(&regs->bank_regs[bank].sts);
+	ecc_tmp = readl(FSMC_NAND_REG(regs, bank, STS));
 	ecc[12] = (uint8_t) (ecc_tmp >> 16);
 
 	return 0;
@@ -379,11 +515,11 @@ static int fsmc_read_hwecc_ecc1(struct mtd_info *mtd, const uint8_t *data,
 {
 	struct fsmc_nand_data *host = container_of(mtd,
 					struct fsmc_nand_data, mtd);
-	struct fsmc_regs *regs = host->regs_va;
+	void __iomem *regs = host->regs_va;
 	uint32_t bank = host->bank;
 	uint32_t ecc_tmp;
 
-	ecc_tmp = readl(&regs->bank_regs[bank].ecc1);
+	ecc_tmp = readl(FSMC_NAND_REG(regs, bank, ECC1));
 	ecc[0] = (uint8_t) (ecc_tmp >> 0);
 	ecc[1] = (uint8_t) (ecc_tmp >> 8);
 	ecc[2] = (uint8_t) (ecc_tmp >> 16);
@@ -391,6 +527,166 @@ static int fsmc_read_hwecc_ecc1(struct mtd_info *mtd, const uint8_t *data,
 	return 0;
 }
 
+/* Count the number of 0's in buff upto a max of max_bits */
+static int count_written_bits(uint8_t *buff, int size, int max_bits)
+{
+	int k, written_bits = 0;
+
+	for (k = 0; k < size; k++) {
+		written_bits += hweight8(~buff[k]);
+		if (written_bits > max_bits)
+			break;
+	}
+
+	return written_bits;
+}
+
+static void dma_complete(void *param)
+{
+	struct fsmc_nand_data *host = param;
+
+	complete(&host->dma_access_complete);
+}
+
+static int dma_xfer(struct fsmc_nand_data *host, void *buffer, int len,
+		enum dma_data_direction direction)
+{
+	struct dma_chan *chan;
+	struct dma_device *dma_dev;
+	struct dma_async_tx_descriptor *tx;
+	dma_addr_t dma_dst, dma_src, dma_addr;
+	dma_cookie_t cookie;
+	unsigned long flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
+	int ret;
+
+	if (direction == DMA_TO_DEVICE)
+		chan = host->write_dma_chan;
+	else if (direction == DMA_FROM_DEVICE)
+		chan = host->read_dma_chan;
+	else
+		return -EINVAL;
+
+	dma_dev = chan->device;
+	dma_addr = dma_map_single(dma_dev->dev, buffer, len, direction);
+
+	if (direction == DMA_TO_DEVICE) {
+		dma_src = dma_addr;
+		dma_dst = host->data_pa;
+		flags |= DMA_COMPL_SRC_UNMAP_SINGLE | DMA_COMPL_SKIP_DEST_UNMAP;
+	} else {
+		dma_src = host->data_pa;
+		dma_dst = dma_addr;
+		flags |= DMA_COMPL_DEST_UNMAP_SINGLE | DMA_COMPL_SKIP_SRC_UNMAP;
+	}
+
+	tx = dma_dev->device_prep_dma_memcpy(chan, dma_dst, dma_src,
+			len, flags);
+
+	if (!tx) {
+		dev_err(host->dev, "device_prep_dma_memcpy error\n");
+		dma_unmap_single(dma_dev->dev, dma_addr, len, direction);
+		return -EIO;
+	}
+
+	tx->callback = dma_complete;
+	tx->callback_param = host;
+	cookie = tx->tx_submit(tx);
+
+	ret = dma_submit_error(cookie);
+	if (ret) {
+		dev_err(host->dev, "dma_submit_error %d\n", cookie);
+		return ret;
+	}
+
+	dma_async_issue_pending(chan);
+
+	ret =
+	wait_for_completion_interruptible_timeout(&host->dma_access_complete,
+				msecs_to_jiffies(3000));
+	if (ret <= 0) {
+		chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+		dev_err(host->dev, "wait_for_completion_timeout\n");
+		return ret ? ret : -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+/*
+ * fsmc_write_buf - write buffer to chip
+ * @mtd:	MTD device structure
+ * @buf:	data buffer
+ * @len:	number of bytes to write
+ */
+static void fsmc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
+{
+	int i;
+	struct nand_chip *chip = mtd->priv;
+
+	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+			IS_ALIGNED(len, sizeof(uint32_t))) {
+		uint32_t *p = (uint32_t *)buf;
+		len = len >> 2;
+		for (i = 0; i < len; i++)
+			writel(p[i], chip->IO_ADDR_W);
+	} else {
+		for (i = 0; i < len; i++)
+			writeb(buf[i], chip->IO_ADDR_W);
+	}
+}
+
+/*
+ * fsmc_read_buf - read chip data into buffer
+ * @mtd:	MTD device structure
+ * @buf:	buffer to store date
+ * @len:	number of bytes to read
+ */
+static void fsmc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
+{
+	int i;
+	struct nand_chip *chip = mtd->priv;
+
+	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+			IS_ALIGNED(len, sizeof(uint32_t))) {
+		uint32_t *p = (uint32_t *)buf;
+		len = len >> 2;
+		for (i = 0; i < len; i++)
+			p[i] = readl(chip->IO_ADDR_R);
+	} else {
+		for (i = 0; i < len; i++)
+			buf[i] = readb(chip->IO_ADDR_R);
+	}
+}
+
+/*
+ * fsmc_read_buf_dma - read chip data into buffer
+ * @mtd:	MTD device structure
+ * @buf:	buffer to store date
+ * @len:	number of bytes to read
+ */
+static void fsmc_read_buf_dma(struct mtd_info *mtd, uint8_t *buf, int len)
+{
+	struct fsmc_nand_data *host;
+
+	host = container_of(mtd, struct fsmc_nand_data, mtd);
+	dma_xfer(host, buf, len, DMA_FROM_DEVICE);
+}
+
+/*
+ * fsmc_write_buf_dma - write buffer to chip
+ * @mtd:	MTD device structure
+ * @buf:	data buffer
+ * @len:	number of bytes to write
+ */
+static void fsmc_write_buf_dma(struct mtd_info *mtd, const uint8_t *buf,
+		int len)
+{
+	struct fsmc_nand_data *host;
+
+	host = container_of(mtd, struct fsmc_nand_data, mtd);
+	dma_xfer(host, (void *)buf, len, DMA_TO_DEVICE);
+}
+
 /*
  * fsmc_read_page_hwecc
  * @mtd:	mtd info structure
@@ -426,7 +722,6 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
 	uint8_t *oob = (uint8_t *)&ecc_oob[0];
 
 	for (i = 0, s = 0; s < eccsteps; s++, i += eccbytes, p += eccsize) {
-
 		chip->cmdfunc(mtd, NAND_CMD_READ0, s * eccsize, page);
 		chip->ecc.hwctl(mtd, NAND_ECC_READ);
 		chip->read_buf(mtd, p, eccsize);
@@ -437,17 +732,19 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
 			group++;
 
 			/*
-			* length is intentionally kept a higher multiple of 2
-			* to read at least 13 bytes even in case of 16 bit NAND
-			* devices
-			*/
-			len = roundup(len, 2);
+			 * length is intentionally kept a higher multiple of 2
+			 * to read at least 13 bytes even in case of 16 bit NAND
+			 * devices
+			 */
+			if (chip->options & NAND_BUSWIDTH_16)
+				len = roundup(len, 2);
+
 			chip->cmdfunc(mtd, NAND_CMD_READOOB, off, page);
 			chip->read_buf(mtd, oob + j, len);
 			j += len;
 		}
 
-		memcpy(&ecc_code[i], oob, 13);
+		memcpy(&ecc_code[i], oob, chip->ecc.bytes);
 		chip->ecc.calculate(mtd, p, &ecc_calc[i]);
 
 		stat = chip->ecc.correct(mtd, p, &ecc_code[i], &ecc_calc[i]);
@@ -461,7 +758,7 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
 }
 
 /*
- * fsmc_correct_data
+ * fsmc_bch8_correct_data
  * @mtd:	mtd info structure
  * @dat:	buffer of read data
  * @read_ecc:	ecc read from device spare area
@@ -470,19 +767,51 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
  * calc_ecc is a 104 bit information containing maximum of 8 error
  * offset informations of 13 bits each in 512 bytes of read data.
  */
-static int fsmc_correct_data(struct mtd_info *mtd, uint8_t *dat,
+static int fsmc_bch8_correct_data(struct mtd_info *mtd, uint8_t *dat,
 			     uint8_t *read_ecc, uint8_t *calc_ecc)
 {
 	struct fsmc_nand_data *host = container_of(mtd,
 					struct fsmc_nand_data, mtd);
-	struct fsmc_regs *regs = host->regs_va;
+	struct nand_chip *chip = mtd->priv;
+	void __iomem *regs = host->regs_va;
 	unsigned int bank = host->bank;
-	uint16_t err_idx[8];
-	uint64_t ecc_data[2];
+	uint32_t err_idx[8];
 	uint32_t num_err, i;
+	uint32_t ecc1, ecc2, ecc3, ecc4;
+
+	num_err = (readl(FSMC_NAND_REG(regs, bank, STS)) >> 10) & 0xF;
+
+	/* no bit flipping */
+	if (likely(num_err == 0))
+		return 0;
+
+	/* too many errors */
+	if (unlikely(num_err > 8)) {
+		/*
+		 * This is a temporary erase check. A newly erased page read
+		 * would result in an ecc error because the oob data is also
+		 * erased to FF and the calculated ecc for an FF data is not
+		 * FF..FF.
+		 * This is a workaround to skip performing correction in case
+		 * data is FF..FF
+		 *
+		 * Logic:
+		 * For every page, each bit written as 0 is counted until these
+		 * number of bits are greater than 8 (the maximum correction
+		 * capability of FSMC for each 512 + 13 bytes)
+		 */
+
+		int bits_ecc = count_written_bits(read_ecc, chip->ecc.bytes, 8);
+		int bits_data = count_written_bits(dat, chip->ecc.size, 8);
+
+		if ((bits_ecc + bits_data) <= 8) {
+			if (bits_data)
+				memset(dat, 0xff, chip->ecc.size);
+			return bits_data;
+		}
 
-	/* The calculated ecc is actually the correction index in data */
-	memcpy(ecc_data, calc_ecc, 13);
+		return -EBADMSG;
+	}
 
 	/*
 	 * ------------------- calc_ecc[] bit wise -----------|--13 bits--|
@@ -493,27 +822,26 @@ static int fsmc_correct_data(struct mtd_info *mtd, uint8_t *dat,
 	 * uint64_t array and error offset indexes are populated in err_idx
 	 * array
 	 */
-	for (i = 0; i < 8; i++) {
-		if (i == 4) {
-			err_idx[4] = ((ecc_data[1] & 0x1) << 12) | ecc_data[0];
-			ecc_data[1] >>= 1;
-			continue;
-		}
-		err_idx[i] = (ecc_data[i/4] & 0x1FFF);
-		ecc_data[i/4] >>= 13;
-	}
-
-	num_err = (readl(&regs->bank_regs[bank].sts) >> 10) & 0xF;
-
-	if (num_err == 0xF)
-		return -EBADMSG;
+	ecc1 = readl(FSMC_NAND_REG(regs, bank, ECC1));
+	ecc2 = readl(FSMC_NAND_REG(regs, bank, ECC2));
+	ecc3 = readl(FSMC_NAND_REG(regs, bank, ECC3));
+	ecc4 = readl(FSMC_NAND_REG(regs, bank, STS));
+
+	err_idx[0] = (ecc1 >> 0) & 0x1FFF;
+	err_idx[1] = (ecc1 >> 13) & 0x1FFF;
+	err_idx[2] = (((ecc2 >> 0) & 0x7F) << 6) | ((ecc1 >> 26) & 0x3F);
+	err_idx[3] = (ecc2 >> 7) & 0x1FFF;
+	err_idx[4] = (((ecc3 >> 0) & 0x1) << 12) | ((ecc2 >> 20) & 0xFFF);
+	err_idx[5] = (ecc3 >> 1) & 0x1FFF;
+	err_idx[6] = (ecc3 >> 14) & 0x1FFF;
+	err_idx[7] = (((ecc4 >> 16) & 0xFF) << 5) | ((ecc3 >> 27) & 0x1F);
 
 	i = 0;
 	while (num_err--) {
 		change_bit(0, (unsigned long *)&err_idx[i]);
 		change_bit(1, (unsigned long *)&err_idx[i]);
 
-		if (err_idx[i] <= 512 * 8) {
+		if (err_idx[i] < chip->ecc.size * 8) {
 			change_bit(err_idx[i], (unsigned long *)dat);
 			i++;
 		}
@@ -521,6 +849,44 @@ static int fsmc_correct_data(struct mtd_info *mtd, uint8_t *dat,
 	return i;
 }
 
+static bool filter(struct dma_chan *chan, void *slave)
+{
+	chan->private = slave;
+	return true;
+}
+
+#ifdef CONFIG_OF
+static int __devinit fsmc_nand_probe_config_dt(struct platform_device *pdev,
+					       struct device_node *np)
+{
+	struct fsmc_nand_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	u32 val;
+
+	/* Set default NAND width to 8 bits */
+	pdata->width = 8;
+	if (!of_property_read_u32(np, "bank-width", &val)) {
+		if (val == 2) {
+			pdata->width = 16;
+		} else if (val != 1) {
+			dev_err(&pdev->dev, "invalid bank-width %u\n", val);
+			return -EINVAL;
+		}
+	}
+	of_property_read_u32(np, "st,ale-off", &pdata->ale_off);
+	of_property_read_u32(np, "st,cle-off", &pdata->cle_off);
+	if (of_get_property(np, "nand-skip-bbtscan", NULL))
+		pdata->options = NAND_SKIP_BBTSCAN;
+
+	return 0;
+}
+#else
+static int __devinit fsmc_nand_probe_config_dt(struct platform_device *pdev,
+					       struct device_node *np)
+{
+	return -ENOSYS;
+}
+#endif
+
 /*
  * fsmc_nand_probe - Probe function
  * @pdev:       platform device structure
@@ -528,102 +894,109 @@ static int fsmc_correct_data(struct mtd_info *mtd, uint8_t *dat,
 static int __init fsmc_nand_probe(struct platform_device *pdev)
 {
 	struct fsmc_nand_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct device_node __maybe_unused *np = pdev->dev.of_node;
+	struct mtd_part_parser_data ppdata = {};
 	struct fsmc_nand_data *host;
 	struct mtd_info *mtd;
 	struct nand_chip *nand;
-	struct fsmc_regs *regs;
 	struct resource *res;
+	dma_cap_mask_t mask;
 	int ret = 0;
 	u32 pid;
 	int i;
 
+	if (np) {
+		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+		pdev->dev.platform_data = pdata;
+		ret = fsmc_nand_probe_config_dt(pdev, np);
+		if (ret) {
+			dev_err(&pdev->dev, "no platform data\n");
+			return -ENODEV;
+		}
+	}
+
 	if (!pdata) {
 		dev_err(&pdev->dev, "platform data is NULL\n");
 		return -EINVAL;
 	}
 
 	/* Allocate memory for the device structure (and zero it) */
-	host = kzalloc(sizeof(*host), GFP_KERNEL);
+	host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
 	if (!host) {
 		dev_err(&pdev->dev, "failed to allocate device structure\n");
 		return -ENOMEM;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
-	if (!res) {
-		ret = -EIO;
-		goto err_probe1;
-	}
+	if (!res)
+		return -EINVAL;
 
-	host->resdata = request_mem_region(res->start, resource_size(res),
-			pdev->name);
-	if (!host->resdata) {
-		ret = -EIO;
-		goto err_probe1;
+	if (!devm_request_mem_region(&pdev->dev, res->start, resource_size(res),
+				pdev->name)) {
+		dev_err(&pdev->dev, "Failed to get memory data resourse\n");
+		return -ENOENT;
 	}
 
-	host->data_va = ioremap(res->start, resource_size(res));
+	host->data_pa = (dma_addr_t)res->start;
+	host->data_va = devm_ioremap(&pdev->dev, res->start,
+			resource_size(res));
 	if (!host->data_va) {
-		ret = -EIO;
-		goto err_probe1;
+		dev_err(&pdev->dev, "data ioremap failed\n");
+		return -ENOMEM;
 	}
 
-	host->resaddr = request_mem_region(res->start + PLAT_NAND_ALE,
-			resource_size(res), pdev->name);
-	if (!host->resaddr) {
-		ret = -EIO;
-		goto err_probe1;
+	if (!devm_request_mem_region(&pdev->dev, res->start + pdata->ale_off,
+			resource_size(res), pdev->name)) {
+		dev_err(&pdev->dev, "Failed to get memory ale resourse\n");
+		return -ENOENT;
 	}
 
-	host->addr_va = ioremap(res->start + PLAT_NAND_ALE, resource_size(res));
+	host->addr_va = devm_ioremap(&pdev->dev, res->start + pdata->ale_off,
+			resource_size(res));
 	if (!host->addr_va) {
-		ret = -EIO;
-		goto err_probe1;
+		dev_err(&pdev->dev, "ale ioremap failed\n");
+		return -ENOMEM;
 	}
 
-	host->rescmd = request_mem_region(res->start + PLAT_NAND_CLE,
-			resource_size(res), pdev->name);
-	if (!host->rescmd) {
-		ret = -EIO;
-		goto err_probe1;
+	if (!devm_request_mem_region(&pdev->dev, res->start + pdata->cle_off,
+			resource_size(res), pdev->name)) {
+		dev_err(&pdev->dev, "Failed to get memory cle resourse\n");
+		return -ENOENT;
 	}
 
-	host->cmd_va = ioremap(res->start + PLAT_NAND_CLE, resource_size(res));
+	host->cmd_va = devm_ioremap(&pdev->dev, res->start + pdata->cle_off,
+			resource_size(res));
 	if (!host->cmd_va) {
-		ret = -EIO;
-		goto err_probe1;
+		dev_err(&pdev->dev, "ale ioremap failed\n");
+		return -ENOMEM;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "fsmc_regs");
-	if (!res) {
-		ret = -EIO;
-		goto err_probe1;
-	}
+	if (!res)
+		return -EINVAL;
 
-	host->resregs = request_mem_region(res->start, resource_size(res),
-			pdev->name);
-	if (!host->resregs) {
-		ret = -EIO;
-		goto err_probe1;
+	if (!devm_request_mem_region(&pdev->dev, res->start, resource_size(res),
+			pdev->name)) {
+		dev_err(&pdev->dev, "Failed to get memory regs resourse\n");
+		return -ENOENT;
 	}
 
-	host->regs_va = ioremap(res->start, resource_size(res));
+	host->regs_va = devm_ioremap(&pdev->dev, res->start,
+			resource_size(res));
 	if (!host->regs_va) {
-		ret = -EIO;
-		goto err_probe1;
+		dev_err(&pdev->dev, "regs ioremap failed\n");
+		return -ENOMEM;
 	}
 
 	host->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		dev_err(&pdev->dev, "failed to fetch block clock\n");
-		ret = PTR_ERR(host->clk);
-		host->clk = NULL;
-		goto err_probe1;
+		return PTR_ERR(host->clk);
 	}
 
 	ret = clk_enable(host->clk);
 	if (ret)
-		goto err_probe1;
+		goto err_clk_enable;
 
 	/*
 	 * This device ID is actually a common AMBA ID as used on the
@@ -639,7 +1012,14 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 
 	host->bank = pdata->bank;
 	host->select_chip = pdata->select_bank;
-	regs = host->regs_va;
+	host->partitions = pdata->partitions;
+	host->nr_partitions = pdata->nr_partitions;
+	host->dev = &pdev->dev;
+	host->dev_timings = pdata->nand_timings;
+	host->mode = pdata->mode;
+
+	if (host->mode == USE_DMA_ACCESS)
+		init_completion(&host->dma_access_complete);
 
 	/* Link all private pointers */
 	mtd = &host->mtd;
@@ -658,21 +1038,53 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	nand->ecc.size = 512;
 	nand->options = pdata->options;
 	nand->select_chip = fsmc_select_chip;
+	nand->badblockbits = 7;
 
 	if (pdata->width == FSMC_NAND_BW16)
 		nand->options |= NAND_BUSWIDTH_16;
 
-	fsmc_nand_setup(regs, host->bank, nand->options & NAND_BUSWIDTH_16);
+	switch (host->mode) {
+	case USE_DMA_ACCESS:
+		dma_cap_zero(mask);
+		dma_cap_set(DMA_MEMCPY, mask);
+		host->read_dma_chan = dma_request_channel(mask, filter,
+				pdata->read_dma_priv);
+		if (!host->read_dma_chan) {
+			dev_err(&pdev->dev, "Unable to get read dma channel\n");
+			goto err_req_read_chnl;
+		}
+		host->write_dma_chan = dma_request_channel(mask, filter,
+				pdata->write_dma_priv);
+		if (!host->write_dma_chan) {
+			dev_err(&pdev->dev, "Unable to get write dma channel\n");
+			goto err_req_write_chnl;
+		}
+		nand->read_buf = fsmc_read_buf_dma;
+		nand->write_buf = fsmc_write_buf_dma;
+		break;
+
+	default:
+	case USE_WORD_ACCESS:
+		nand->read_buf = fsmc_read_buf;
+		nand->write_buf = fsmc_write_buf;
+		break;
+	}
+
+	fsmc_nand_setup(host->regs_va, host->bank,
+			nand->options & NAND_BUSWIDTH_16,
+			host->dev_timings);
 
 	if (AMBA_REV_BITS(host->pid) >= 8) {
 		nand->ecc.read_page = fsmc_read_page_hwecc;
 		nand->ecc.calculate = fsmc_read_hwecc_ecc4;
-		nand->ecc.correct = fsmc_correct_data;
+		nand->ecc.correct = fsmc_bch8_correct_data;
 		nand->ecc.bytes = 13;
+		nand->ecc.strength = 8;
 	} else {
 		nand->ecc.calculate = fsmc_read_hwecc_ecc1;
 		nand->ecc.correct = nand_correct_data;
 		nand->ecc.bytes = 3;
+		nand->ecc.strength = 1;
 	}
 
 	/*
@@ -681,19 +1093,52 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	if (nand_scan_ident(&host->mtd, 1, NULL)) {
 		ret = -ENXIO;
 		dev_err(&pdev->dev, "No NAND Device found!\n");
-		goto err_probe;
+		goto err_scan_ident;
 	}
 
 	if (AMBA_REV_BITS(host->pid) >= 8) {
-		if (host->mtd.writesize == 512) {
-			nand->ecc.layout = &fsmc_ecc4_sp_layout;
+		switch (host->mtd.oobsize) {
+		case 16:
+			nand->ecc.layout = &fsmc_ecc4_16_layout;
 			host->ecc_place = &fsmc_ecc4_sp_place;
-		} else {
-			nand->ecc.layout = &fsmc_ecc4_lp_layout;
+			break;
+		case 64:
+			nand->ecc.layout = &fsmc_ecc4_64_layout;
+			host->ecc_place = &fsmc_ecc4_lp_place;
+			break;
+		case 128:
+			nand->ecc.layout = &fsmc_ecc4_128_layout;
+			host->ecc_place = &fsmc_ecc4_lp_place;
+			break;
+		case 224:
+			nand->ecc.layout = &fsmc_ecc4_224_layout;
 			host->ecc_place = &fsmc_ecc4_lp_place;
+			break;
+		case 256:
+			nand->ecc.layout = &fsmc_ecc4_256_layout;
+			host->ecc_place = &fsmc_ecc4_lp_place;
+			break;
+		default:
+			printk(KERN_WARNING "No oob scheme defined for "
+			       "oobsize %d\n", mtd->oobsize);
+			BUG();
 		}
 	} else {
-		nand->ecc.layout = &fsmc_ecc1_layout;
+		switch (host->mtd.oobsize) {
+		case 16:
+			nand->ecc.layout = &fsmc_ecc1_16_layout;
+			break;
+		case 64:
+			nand->ecc.layout = &fsmc_ecc1_64_layout;
+			break;
+		case 128:
+			nand->ecc.layout = &fsmc_ecc1_128_layout;
+			break;
+		default:
+			printk(KERN_WARNING "No oob scheme defined for "
+			       "oobsize %d\n", mtd->oobsize);
+			BUG();
+		}
 	}
 
 	/* Second stage of scan to fill MTD data-structures */
@@ -713,13 +1158,9 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	 * Check for partition info passed
 	 */
 	host->mtd.name = "nand";
-	ret = mtd_device_parse_register(&host->mtd, NULL, 0,
-			host->mtd.size <= 0x04000000 ?
-				partition_info_16KB_blk :
-				partition_info_128KB_blk,
-			host->mtd.size <= 0x04000000 ?
-				ARRAY_SIZE(partition_info_16KB_blk) :
-				ARRAY_SIZE(partition_info_128KB_blk));
+	ppdata.of_node = np;
+	ret = mtd_device_parse_register(&host->mtd, NULL, &ppdata,
+					host->partitions, host->nr_partitions);
 	if (ret)
 		goto err_probe;
 
@@ -728,32 +1169,16 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	return 0;
 
 err_probe:
+err_scan_ident:
+	if (host->mode == USE_DMA_ACCESS)
+		dma_release_channel(host->write_dma_chan);
+err_req_write_chnl:
+	if (host->mode == USE_DMA_ACCESS)
+		dma_release_channel(host->read_dma_chan);
+err_req_read_chnl:
 	clk_disable(host->clk);
-err_probe1:
-	if (host->clk)
-		clk_put(host->clk);
-	if (host->regs_va)
-		iounmap(host->regs_va);
-	if (host->resregs)
-		release_mem_region(host->resregs->start,
-				resource_size(host->resregs));
-	if (host->cmd_va)
-		iounmap(host->cmd_va);
-	if (host->rescmd)
-		release_mem_region(host->rescmd->start,
-				resource_size(host->rescmd));
-	if (host->addr_va)
-		iounmap(host->addr_va);
-	if (host->resaddr)
-		release_mem_region(host->resaddr->start,
-				resource_size(host->resaddr));
-	if (host->data_va)
-		iounmap(host->data_va);
-	if (host->resdata)
-		release_mem_region(host->resdata->start,
-				resource_size(host->resdata));
-
-	kfree(host);
+err_clk_enable:
+	clk_put(host->clk);
 	return ret;
 }
 
@@ -768,24 +1193,15 @@ static int fsmc_nand_remove(struct platform_device *pdev)
 
 	if (host) {
 		nand_release(&host->mtd);
+
+		if (host->mode == USE_DMA_ACCESS) {
+			dma_release_channel(host->write_dma_chan);
+			dma_release_channel(host->read_dma_chan);
+		}
 		clk_disable(host->clk);
 		clk_put(host->clk);
-
-		iounmap(host->regs_va);
-		release_mem_region(host->resregs->start,
-				resource_size(host->resregs));
-		iounmap(host->cmd_va);
-		release_mem_region(host->rescmd->start,
-				resource_size(host->rescmd));
-		iounmap(host->addr_va);
-		release_mem_region(host->resaddr->start,
-				resource_size(host->resaddr));
-		iounmap(host->data_va);
-		release_mem_region(host->resdata->start,
-				resource_size(host->resdata));
-
-		kfree(host);
 	}
+
 	return 0;
 }
 
@@ -801,15 +1217,24 @@ static int fsmc_nand_suspend(struct device *dev)
 static int fsmc_nand_resume(struct device *dev)
 {
 	struct fsmc_nand_data *host = dev_get_drvdata(dev);
-	if (host)
+	if (host) {
 		clk_enable(host->clk);
+		fsmc_nand_setup(host->regs_va, host->bank,
+				host->nand.options & NAND_BUSWIDTH_16,
+				host->dev_timings);
+	}
 	return 0;
 }
 
-static const struct dev_pm_ops fsmc_nand_pm_ops = {
-	.suspend = fsmc_nand_suspend,
-	.resume = fsmc_nand_resume,
+static SIMPLE_DEV_PM_OPS(fsmc_nand_pm_ops, fsmc_nand_suspend, fsmc_nand_resume);
+#endif
+
+#ifdef CONFIG_OF
+static const struct of_device_id fsmc_nand_id_table[] = {
+	{ .compatible = "st,spear600-fsmc-nand" },
+	{}
 };
+MODULE_DEVICE_TABLE(of, fsmc_nand_id_table);
 #endif
 
 static struct platform_driver fsmc_nand_driver = {
@@ -817,6 +1242,7 @@ static struct platform_driver fsmc_nand_driver = {
 	.driver = {
 		.owner = THIS_MODULE,
 		.name = "fsmc-nand",
+		.of_match_table = of_match_ptr(fsmc_nand_id_table),
 #ifdef CONFIG_PM
 		.pm = &fsmc_nand_pm_ops,
 #endif
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
index 7db6555ed3ba..e8ea7107932e 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
@@ -835,7 +835,7 @@ int gpmi_send_command(struct gpmi_nand_data *this)
 		| BM_GPMI_CTRL0_ADDRESS_INCREMENT
 		| BF_GPMI_CTRL0_XFER_COUNT(this->command_length);
 	pio[1] = pio[2] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 					(struct scatterlist *)pio,
 					ARRAY_SIZE(pio), DMA_TRANS_NONE, 0);
 	if (!desc) {
@@ -848,8 +848,10 @@ int gpmi_send_command(struct gpmi_nand_data *this)
 
 	sg_init_one(sgl, this->cmd_buffer, this->command_length);
 	dma_map_sg(this->dev, sgl, 1, DMA_TO_DEVICE);
-	desc = channel->device->device_prep_slave_sg(channel,
-					sgl, 1, DMA_MEM_TO_DEV, 1);
+	desc = dmaengine_prep_slave_sg(channel,
+				sgl, 1, DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+
 	if (!desc) {
 		pr_err("step 2 error\n");
 		return -1;
@@ -880,8 +882,7 @@ int gpmi_send_data(struct gpmi_nand_data *this)
 		| BF_GPMI_CTRL0_ADDRESS(address)
 		| BF_GPMI_CTRL0_XFER_COUNT(this->upper_len);
 	pio[1] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
-					(struct scatterlist *)pio,
+	desc = dmaengine_prep_slave_sg(channel, (struct scatterlist *)pio,
 					ARRAY_SIZE(pio), DMA_TRANS_NONE, 0);
 	if (!desc) {
 		pr_err("step 1 error\n");
@@ -890,8 +891,9 @@ int gpmi_send_data(struct gpmi_nand_data *this)
 
 	/* [2] send DMA request */
 	prepare_data_dma(this, DMA_TO_DEVICE);
-	desc = channel->device->device_prep_slave_sg(channel, &this->data_sgl,
-						1, DMA_MEM_TO_DEV, 1);
+	desc = dmaengine_prep_slave_sg(channel, &this->data_sgl,
+					1, DMA_MEM_TO_DEV,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		pr_err("step 2 error\n");
 		return -1;
@@ -916,7 +918,7 @@ int gpmi_read_data(struct gpmi_nand_data *this)
 		| BF_GPMI_CTRL0_ADDRESS(BV_GPMI_CTRL0_ADDRESS__NAND_DATA)
 		| BF_GPMI_CTRL0_XFER_COUNT(this->upper_len);
 	pio[1] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 					(struct scatterlist *)pio,
 					ARRAY_SIZE(pio), DMA_TRANS_NONE, 0);
 	if (!desc) {
@@ -926,8 +928,9 @@ int gpmi_read_data(struct gpmi_nand_data *this)
 
 	/* [2] : send DMA request */
 	prepare_data_dma(this, DMA_FROM_DEVICE);
-	desc = channel->device->device_prep_slave_sg(channel, &this->data_sgl,
-						1, DMA_DEV_TO_MEM, 1);
+	desc = dmaengine_prep_slave_sg(channel, &this->data_sgl,
+					1, DMA_DEV_TO_MEM,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		pr_err("step 2 error\n");
 		return -1;
@@ -972,9 +975,10 @@ int gpmi_send_page(struct gpmi_nand_data *this,
 	pio[4] = payload;
 	pio[5] = auxiliary;
 
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 					(struct scatterlist *)pio,
-					ARRAY_SIZE(pio), DMA_TRANS_NONE, 0);
+					ARRAY_SIZE(pio), DMA_TRANS_NONE,
+					DMA_CTRL_ACK);
 	if (!desc) {
 		pr_err("step 2 error\n");
 		return -1;
@@ -1007,7 +1011,7 @@ int gpmi_read_page(struct gpmi_nand_data *this,
 		| BF_GPMI_CTRL0_ADDRESS(address)
 		| BF_GPMI_CTRL0_XFER_COUNT(0);
 	pio[1] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 				(struct scatterlist *)pio, 2,
 				DMA_TRANS_NONE, 0);
 	if (!desc) {
@@ -1036,9 +1040,10 @@ int gpmi_read_page(struct gpmi_nand_data *this,
 	pio[3] = geo->page_size;
 	pio[4] = payload;
 	pio[5] = auxiliary;
-	desc = channel->device->device_prep_slave_sg(channel,
+	desc = dmaengine_prep_slave_sg(channel,
 					(struct scatterlist *)pio,
-					ARRAY_SIZE(pio), DMA_TRANS_NONE, 1);
+					ARRAY_SIZE(pio), DMA_TRANS_NONE,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		pr_err("step 2 error\n");
 		return -1;
@@ -1055,9 +1060,11 @@ int gpmi_read_page(struct gpmi_nand_data *this,
 		| BF_GPMI_CTRL0_ADDRESS(address)
 		| BF_GPMI_CTRL0_XFER_COUNT(geo->page_size);
 	pio[1] = 0;
-	desc = channel->device->device_prep_slave_sg(channel,
-				(struct scatterlist *)pio, 2,
-				DMA_TRANS_NONE, 1);
+	pio[2] = 0; /* clear GPMI_HW_GPMI_ECCCTRL, disable the BCH. */
+	desc = dmaengine_prep_slave_sg(channel,
+				(struct scatterlist *)pio, 3,
+				DMA_TRANS_NONE,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		pr_err("step 3 error\n");
 		return -1;
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index 493ec2fcf97f..75b1dde16358 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -1124,7 +1124,7 @@ static int gpmi_block_markbad(struct mtd_info *mtd, loff_t ofs)
 		chip->bbt[block >> 2] |= 0x01 << ((block & 0x03) << 1);
 
 	/* Do we have a flash based bad block table ? */
-	if (chip->options & NAND_BBT_USE_FLASH)
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
 		ret = nand_update_bbt(mtd, ofs);
 	else {
 		chipnr = (int)(ofs >> chip->chip_shift);
@@ -1155,7 +1155,7 @@ static int gpmi_block_markbad(struct mtd_info *mtd, loff_t ofs)
 	return ret;
 }
 
-static int __devinit nand_boot_set_geometry(struct gpmi_nand_data *this)
+static int nand_boot_set_geometry(struct gpmi_nand_data *this)
 {
 	struct boot_rom_geometry *geometry = &this->rom_geometry;
 
@@ -1182,7 +1182,7 @@ static int __devinit nand_boot_set_geometry(struct gpmi_nand_data *this)
 }
 
 static const char  *fingerprint = "STMP";
-static int __devinit mx23_check_transcription_stamp(struct gpmi_nand_data *this)
+static int mx23_check_transcription_stamp(struct gpmi_nand_data *this)
 {
 	struct boot_rom_geometry *rom_geo = &this->rom_geometry;
 	struct device *dev = this->dev;
@@ -1239,7 +1239,7 @@ static int __devinit mx23_check_transcription_stamp(struct gpmi_nand_data *this)
 }
 
 /* Writes a transcription stamp. */
-static int __devinit mx23_write_transcription_stamp(struct gpmi_nand_data *this)
+static int mx23_write_transcription_stamp(struct gpmi_nand_data *this)
 {
 	struct device *dev = this->dev;
 	struct boot_rom_geometry *rom_geo = &this->rom_geometry;
@@ -1322,7 +1322,7 @@ static int __devinit mx23_write_transcription_stamp(struct gpmi_nand_data *this)
 	return 0;
 }
 
-static int __devinit mx23_boot_init(struct gpmi_nand_data  *this)
+static int mx23_boot_init(struct gpmi_nand_data  *this)
 {
 	struct device *dev = this->dev;
 	struct nand_chip *chip = &this->nand;
@@ -1391,7 +1391,7 @@ static int __devinit mx23_boot_init(struct gpmi_nand_data  *this)
 	return 0;
 }
 
-static int __devinit nand_boot_init(struct gpmi_nand_data  *this)
+static int nand_boot_init(struct gpmi_nand_data  *this)
 {
 	nand_boot_set_geometry(this);
 
@@ -1401,7 +1401,7 @@ static int __devinit nand_boot_init(struct gpmi_nand_data  *this)
 	return 0;
 }
 
-static int __devinit gpmi_set_geometry(struct gpmi_nand_data *this)
+static int gpmi_set_geometry(struct gpmi_nand_data *this)
 {
 	int ret;
 
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
index e023bccb7781..ec6180d4ff8f 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
@@ -20,7 +20,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
-#include <mach/dma.h>
+#include <linux/fsl/mxs-dma.h>
 
 struct resources {
 	void          *gpmi_regs;
diff --git a/drivers/mtd/nand/h1910.c b/drivers/mtd/nand/h1910.c
index 5dc6f0d92f1a..11e487813428 100644
--- a/drivers/mtd/nand/h1910.c
+++ b/drivers/mtd/nand/h1910.c
@@ -135,8 +135,8 @@ static int __init h1910_init(void)
 	}
 
 	/* Register the partitions */
-	mtd_device_parse_register(h1910_nand_mtd, NULL, 0,
-			partition_info, NUM_PARTITIONS);
+	mtd_device_parse_register(h1910_nand_mtd, NULL, NULL, partition_info,
+				  NUM_PARTITIONS);
 
 	/* Return happy */
 	return 0;
diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c
index ac3b9f255e00..e4147e8acb7c 100644
--- a/drivers/mtd/nand/jz4740_nand.c
+++ b/drivers/mtd/nand/jz4740_nand.c
@@ -332,6 +332,11 @@ static int __devinit jz_nand_probe(struct platform_device *pdev)
 	chip->ecc.mode		= NAND_ECC_HW_OOB_FIRST;
 	chip->ecc.size		= 512;
 	chip->ecc.bytes		= 9;
+	chip->ecc.strength	= 2;
+	/*
+	 * FIXME: ecc_strength value of 2 bits per 512 bytes of data is a
+	 * conservative guess, given 9 ecc bytes and reed-solomon alg.
+	 */
 
 	if (pdata)
 		chip->ecc.layout = pdata->ecc_layout;
@@ -367,9 +372,9 @@ static int __devinit jz_nand_probe(struct platform_device *pdev)
 		goto err_gpio_free;
 	}
 
-	ret = mtd_device_parse_register(mtd, NULL, 0,
-			pdata ? pdata->partitions : NULL,
-			pdata ? pdata->num_partitions : 0);
+	ret = mtd_device_parse_register(mtd, NULL, NULL,
+					pdata ? pdata->partitions : NULL,
+					pdata ? pdata->num_partitions : 0);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to add mtd device\n");
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 74a43b818d0e..cc0678a967c1 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -1225,9 +1225,16 @@ static int __init mxcnd_probe(struct platform_device *pdev)
 		goto escan;
 	}
 
+	if (this->ecc.mode == NAND_ECC_HW) {
+		if (nfc_is_v1())
+			this->ecc.strength = 1;
+		else
+			this->ecc.strength = (host->eccsize == 4) ? 4 : 8;
+	}
+
 	/* Register the partitions */
-	mtd_device_parse_register(mtd, part_probes, 0,
-			pdata->parts, pdata->nr_parts);
+	mtd_device_parse_register(mtd, part_probes, NULL, pdata->parts,
+				  pdata->nr_parts);
 
 	platform_set_drvdata(pdev, host);
 
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 8a393f9e6027..47b19c0bb070 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -123,12 +123,6 @@ static int check_offs_len(struct mtd_info *mtd,
 		ret = -EINVAL;
 	}
 
-	/* Do not allow past end of device */
-	if (ofs + len > mtd->size) {
-		pr_debug("%s: past end of device\n", __func__);
-		ret = -EINVAL;
-	}
-
 	return ret;
 }
 
@@ -338,7 +332,7 @@ static int nand_verify_buf16(struct mtd_info *mtd, const uint8_t *buf, int len)
  */
 static int nand_block_bad(struct mtd_info *mtd, loff_t ofs, int getchip)
 {
-	int page, chipnr, res = 0;
+	int page, chipnr, res = 0, i = 0;
 	struct nand_chip *chip = mtd->priv;
 	u16 bad;
 
@@ -356,23 +350,29 @@ static int nand_block_bad(struct mtd_info *mtd, loff_t ofs, int getchip)
 		chip->select_chip(mtd, chipnr);
 	}
 
-	if (chip->options & NAND_BUSWIDTH_16) {
-		chip->cmdfunc(mtd, NAND_CMD_READOOB, chip->badblockpos & 0xFE,
-			      page);
-		bad = cpu_to_le16(chip->read_word(mtd));
-		if (chip->badblockpos & 0x1)
-			bad >>= 8;
-		else
-			bad &= 0xFF;
-	} else {
-		chip->cmdfunc(mtd, NAND_CMD_READOOB, chip->badblockpos, page);
-		bad = chip->read_byte(mtd);
-	}
+	do {
+		if (chip->options & NAND_BUSWIDTH_16) {
+			chip->cmdfunc(mtd, NAND_CMD_READOOB,
+					chip->badblockpos & 0xFE, page);
+			bad = cpu_to_le16(chip->read_word(mtd));
+			if (chip->badblockpos & 0x1)
+				bad >>= 8;
+			else
+				bad &= 0xFF;
+		} else {
+			chip->cmdfunc(mtd, NAND_CMD_READOOB, chip->badblockpos,
+					page);
+			bad = chip->read_byte(mtd);
+		}
 
-	if (likely(chip->badblockbits == 8))
-		res = bad != 0xFF;
-	else
-		res = hweight8(bad) < chip->badblockbits;
+		if (likely(chip->badblockbits == 8))
+			res = bad != 0xFF;
+		else
+			res = hweight8(bad) < chip->badblockbits;
+		ofs += mtd->writesize;
+		page = (int)(ofs >> chip->page_shift) & chip->pagemask;
+		i++;
+	} while (!res && i < 2 && (chip->bbt_options & NAND_BBT_SCAN2NDPAGE));
 
 	if (getchip)
 		nand_release_device(mtd);
@@ -386,51 +386,79 @@ static int nand_block_bad(struct mtd_info *mtd, loff_t ofs, int getchip)
  * @ofs: offset from device start
  *
  * This is the default implementation, which can be overridden by a hardware
- * specific driver.
+ * specific driver. We try operations in the following order, according to our
+ * bbt_options (NAND_BBT_NO_OOB_BBM and NAND_BBT_USE_FLASH):
+ *  (1) erase the affected block, to allow OOB marker to be written cleanly
+ *  (2) update in-memory BBT
+ *  (3) write bad block marker to OOB area of affected block
+ *  (4) update flash-based BBT
+ * Note that we retain the first error encountered in (3) or (4), finish the
+ * procedures, and dump the error in the end.
 */
 static int nand_default_block_markbad(struct mtd_info *mtd, loff_t ofs)
 {
 	struct nand_chip *chip = mtd->priv;
 	uint8_t buf[2] = { 0, 0 };
-	int block, ret, i = 0;
+	int block, res, ret = 0, i = 0;
+	int write_oob = !(chip->bbt_options & NAND_BBT_NO_OOB_BBM);
 
-	if (chip->bbt_options & NAND_BBT_SCANLASTPAGE)
-		ofs += mtd->erasesize - mtd->writesize;
+	if (write_oob) {
+		struct erase_info einfo;
+
+		/* Attempt erase before marking OOB */
+		memset(&einfo, 0, sizeof(einfo));
+		einfo.mtd = mtd;
+		einfo.addr = ofs;
+		einfo.len = 1 << chip->phys_erase_shift;
+		nand_erase_nand(mtd, &einfo, 0);
+	}
 
 	/* Get block number */
 	block = (int)(ofs >> chip->bbt_erase_shift);
+	/* Mark block bad in memory-based BBT */
 	if (chip->bbt)
 		chip->bbt[block >> 2] |= 0x01 << ((block & 0x03) << 1);
 
-	/* Do we have a flash based bad block table? */
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		ret = nand_update_bbt(mtd, ofs);
-	else {
+	/* Write bad block marker to OOB */
+	if (write_oob) {
 		struct mtd_oob_ops ops;
+		loff_t wr_ofs = ofs;
 
 		nand_get_device(chip, mtd, FL_WRITING);
 
-		/*
-		 * Write to first two pages if necessary. If we write to more
-		 * than one location, the first error encountered quits the
-		 * procedure. We write two bytes per location, so we dont have
-		 * to mess with 16 bit access.
-		 */
-		ops.len = ops.ooblen = 2;
 		ops.datbuf = NULL;
 		ops.oobbuf = buf;
-		ops.ooboffs = chip->badblockpos & ~0x01;
+		ops.ooboffs = chip->badblockpos;
+		if (chip->options & NAND_BUSWIDTH_16) {
+			ops.ooboffs &= ~0x01;
+			ops.len = ops.ooblen = 2;
+		} else {
+			ops.len = ops.ooblen = 1;
+		}
 		ops.mode = MTD_OPS_PLACE_OOB;
+
+		/* Write to first/last page(s) if necessary */
+		if (chip->bbt_options & NAND_BBT_SCANLASTPAGE)
+			wr_ofs += mtd->erasesize - mtd->writesize;
 		do {
-			ret = nand_do_write_oob(mtd, ofs, &ops);
+			res = nand_do_write_oob(mtd, wr_ofs, &ops);
+			if (!ret)
+				ret = res;
 
 			i++;
-			ofs += mtd->writesize;
-		} while (!ret && (chip->bbt_options & NAND_BBT_SCAN2NDPAGE) &&
-				i < 2);
+			wr_ofs += mtd->writesize;
+		} while ((chip->bbt_options & NAND_BBT_SCAN2NDPAGE) && i < 2);
 
 		nand_release_device(mtd);
 	}
+
+	/* Update flash-based bad block table */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		res = nand_update_bbt(mtd, ofs);
+		if (!ret)
+			ret = res;
+	}
+
 	if (!ret)
 		mtd->ecc_stats.badblocks++;
 
@@ -1586,25 +1614,14 @@ static int nand_read(struct mtd_info *mtd, loff_t from, size_t len,
 	struct mtd_oob_ops ops;
 	int ret;
 
-	/* Do not allow reads past end of device */
-	if ((from + len) > mtd->size)
-		return -EINVAL;
-	if (!len)
-		return 0;
-
 	nand_get_device(chip, mtd, FL_READING);
-
 	ops.len = len;
 	ops.datbuf = buf;
 	ops.oobbuf = NULL;
 	ops.mode = 0;
-
 	ret = nand_do_read_ops(mtd, from, &ops);
-
 	*retlen = ops.retlen;
-
 	nand_release_device(mtd);
-
 	return ret;
 }
 
@@ -2293,12 +2310,6 @@ static int panic_nand_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct mtd_oob_ops ops;
 	int ret;
 
-	/* Do not allow reads past end of device */
-	if ((to + len) > mtd->size)
-		return -EINVAL;
-	if (!len)
-		return 0;
-
 	/* Wait for the device to get ready */
 	panic_nand_wait(mtd, chip, 400);
 
@@ -2333,25 +2344,14 @@ static int nand_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct mtd_oob_ops ops;
 	int ret;
 
-	/* Do not allow reads past end of device */
-	if ((to + len) > mtd->size)
-		return -EINVAL;
-	if (!len)
-		return 0;
-
 	nand_get_device(chip, mtd, FL_WRITING);
-
 	ops.len = len;
 	ops.datbuf = (uint8_t *)buf;
 	ops.oobbuf = NULL;
 	ops.mode = 0;
-
 	ret = nand_do_write_ops(mtd, to, &ops);
-
 	*retlen = ops.retlen;
-
 	nand_release_device(mtd);
-
 	return ret;
 }
 
@@ -2550,8 +2550,6 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 	if (check_offs_len(mtd, instr->addr, instr->len))
 		return -EINVAL;
 
-	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
-
 	/* Grab the lock and see if the device is available */
 	nand_get_device(chip, mtd, FL_ERASING);
 
@@ -2715,10 +2713,6 @@ static void nand_sync(struct mtd_info *mtd)
  */
 static int nand_block_isbad(struct mtd_info *mtd, loff_t offs)
 {
-	/* Check for invalid offset */
-	if (offs > mtd->size)
-		return -EINVAL;
-
 	return nand_block_checkbad(mtd, offs, 1, 0);
 }
 
@@ -2857,7 +2851,6 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip,
 		chip->read_byte(mtd) != 'F' || chip->read_byte(mtd) != 'I')
 		return 0;
 
-	pr_info("ONFI flash detected\n");
 	chip->cmdfunc(mtd, NAND_CMD_PARAM, 0, -1);
 	for (i = 0; i < 3; i++) {
 		chip->read_buf(mtd, (uint8_t *)p, sizeof(*p));
@@ -2898,7 +2891,8 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip,
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 	mtd->erasesize = le32_to_cpu(p->pages_per_block) * mtd->writesize;
 	mtd->oobsize = le16_to_cpu(p->spare_bytes_per_page);
-	chip->chipsize = (uint64_t)le32_to_cpu(p->blocks_per_lun) * mtd->erasesize;
+	chip->chipsize = le32_to_cpu(p->blocks_per_lun);
+	chip->chipsize *= (uint64_t)mtd->erasesize * p->lun_count;
 	*busw = 0;
 	if (le16_to_cpu(p->features) & 1)
 		*busw = NAND_BUSWIDTH_16;
@@ -2907,6 +2901,7 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip,
 	chip->options |= (NAND_NO_READRDY |
 			NAND_NO_AUTOINCR) & NAND_CHIPOPTIONS_MSK;
 
+	pr_info("ONFI flash detected\n");
 	return 1;
 }
 
@@ -3238,6 +3233,10 @@ int nand_scan_tail(struct mtd_info *mtd)
 	int i;
 	struct nand_chip *chip = mtd->priv;
 
+	/* New bad blocks should be marked in OOB, flash-based BBT, or both */
+	BUG_ON((chip->bbt_options & NAND_BBT_NO_OOB_BBM) &&
+			!(chip->bbt_options & NAND_BBT_USE_FLASH));
+
 	if (!(chip->options & NAND_OWN_BUFFERS))
 		chip->buffers = kmalloc(sizeof(*chip->buffers), GFP_KERNEL);
 	if (!chip->buffers)
@@ -3350,6 +3349,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		if (!chip->ecc.size)
 			chip->ecc.size = 256;
 		chip->ecc.bytes = 3;
+		chip->ecc.strength = 1;
 		break;
 
 	case NAND_ECC_SOFT_BCH:
@@ -3384,6 +3384,8 @@ int nand_scan_tail(struct mtd_info *mtd)
 			pr_warn("BCH ECC initialization failed!\n");
 			BUG();
 		}
+		chip->ecc.strength =
+			chip->ecc.bytes*8 / fls(8*chip->ecc.size);
 		break;
 
 	case NAND_ECC_NONE:
@@ -3397,6 +3399,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		chip->ecc.write_oob = nand_write_oob_std;
 		chip->ecc.size = mtd->writesize;
 		chip->ecc.bytes = 0;
+		chip->ecc.strength = 0;
 		break;
 
 	default:
@@ -3461,25 +3464,26 @@ int nand_scan_tail(struct mtd_info *mtd)
 	mtd->type = MTD_NANDFLASH;
 	mtd->flags = (chip->options & NAND_ROM) ? MTD_CAP_ROM :
 						MTD_CAP_NANDFLASH;
-	mtd->erase = nand_erase;
-	mtd->point = NULL;
-	mtd->unpoint = NULL;
-	mtd->read = nand_read;
-	mtd->write = nand_write;
-	mtd->panic_write = panic_nand_write;
-	mtd->read_oob = nand_read_oob;
-	mtd->write_oob = nand_write_oob;
-	mtd->sync = nand_sync;
-	mtd->lock = NULL;
-	mtd->unlock = NULL;
-	mtd->suspend = nand_suspend;
-	mtd->resume = nand_resume;
-	mtd->block_isbad = nand_block_isbad;
-	mtd->block_markbad = nand_block_markbad;
+	mtd->_erase = nand_erase;
+	mtd->_point = NULL;
+	mtd->_unpoint = NULL;
+	mtd->_read = nand_read;
+	mtd->_write = nand_write;
+	mtd->_panic_write = panic_nand_write;
+	mtd->_read_oob = nand_read_oob;
+	mtd->_write_oob = nand_write_oob;
+	mtd->_sync = nand_sync;
+	mtd->_lock = NULL;
+	mtd->_unlock = NULL;
+	mtd->_suspend = nand_suspend;
+	mtd->_resume = nand_resume;
+	mtd->_block_isbad = nand_block_isbad;
+	mtd->_block_markbad = nand_block_markbad;
 	mtd->writebufsize = mtd->writesize;
 
-	/* propagate ecc.layout to mtd_info */
+	/* propagate ecc info to mtd_info */
 	mtd->ecclayout = chip->ecc.layout;
+	mtd->ecc_strength = chip->ecc.strength * chip->ecc.steps;
 
 	/* Check, if we should skip the bad block table scan */
 	if (chip->options & NAND_SKIP_BBTSCAN)
diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c
index ec688548c880..2b6f632cf274 100644
--- a/drivers/mtd/nand/ndfc.c
+++ b/drivers/mtd/nand/ndfc.c
@@ -179,6 +179,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc,
 	chip->ecc.mode = NAND_ECC_HW;
 	chip->ecc.size = 256;
 	chip->ecc.bytes = 3;
+	chip->ecc.strength = 1;
 	chip->priv = ndfc;
 
 	ndfc->mtd.priv = chip;
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index b3a883e2a22f..c2b0bba9d8b3 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1058,6 +1058,7 @@ static int __devinit omap_nand_probe(struct platform_device *pdev)
 		(pdata->ecc_opt == OMAP_ECC_HAMMING_CODE_HW_ROMCODE)) {
 		info->nand.ecc.bytes            = 3;
 		info->nand.ecc.size             = 512;
+		info->nand.ecc.strength         = 1;
 		info->nand.ecc.calculate        = omap_calculate_ecc;
 		info->nand.ecc.hwctl            = omap_enable_hwecc;
 		info->nand.ecc.correct          = omap_correct_data;
@@ -1101,8 +1102,8 @@ static int __devinit omap_nand_probe(struct platform_device *pdev)
 		goto out_release_mem_region;
 	}
 
-	mtd_device_parse_register(&info->mtd, NULL, 0,
-			pdata->parts, pdata->nr_parts);
+	mtd_device_parse_register(&info->mtd, NULL, NULL, pdata->parts,
+				  pdata->nr_parts);
 
 	platform_set_drvdata(pdev, &info->mtd);
 
diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c
index 29f505adaf84..1d3bfb26080c 100644
--- a/drivers/mtd/nand/orion_nand.c
+++ b/drivers/mtd/nand/orion_nand.c
@@ -129,8 +129,8 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	}
 
 	mtd->name = "orion_nand";
-	ret = mtd_device_parse_register(mtd, NULL, 0,
-			board->parts, board->nr_parts);
+	ret = mtd_device_parse_register(mtd, NULL, NULL, board->parts,
+					board->nr_parts);
 	if (ret) {
 		nand_release(mtd);
 		goto no_dev;
diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c
index 7f2da6953357..6404e6e81b10 100644
--- a/drivers/mtd/nand/plat_nand.c
+++ b/drivers/mtd/nand/plat_nand.c
@@ -99,8 +99,9 @@ static int __devinit plat_nand_probe(struct platform_device *pdev)
 	}
 
 	err = mtd_device_parse_register(&data->mtd,
-			pdata->chip.part_probe_types, 0,
-			pdata->chip.partitions, pdata->chip.nr_partitions);
+					pdata->chip.part_probe_types, NULL,
+					pdata->chip.partitions,
+					pdata->chip.nr_partitions);
 
 	if (!err)
 		return err;
diff --git a/drivers/mtd/nand/ppchameleonevb.c b/drivers/mtd/nand/ppchameleonevb.c
index 7e52af51a198..0ddd90e5788f 100644
--- a/drivers/mtd/nand/ppchameleonevb.c
+++ b/drivers/mtd/nand/ppchameleonevb.c
@@ -275,11 +275,10 @@ static int __init ppchameleonevb_init(void)
 	ppchameleon_mtd->name = "ppchameleon-nand";
 
 	/* Register the partitions */
-	mtd_device_parse_register(ppchameleon_mtd, NULL, 0,
-			ppchameleon_mtd->size == NAND_SMALL_SIZE ?
-				partition_info_me :
-				partition_info_hi,
-			NUM_PARTITIONS);
+	mtd_device_parse_register(ppchameleon_mtd, NULL, NULL,
+				  ppchameleon_mtd->size == NAND_SMALL_SIZE ?
+					partition_info_me : partition_info_hi,
+				  NUM_PARTITIONS);
 
  nand_evb_init:
 	/****************************
@@ -365,11 +364,10 @@ static int __init ppchameleonevb_init(void)
 	ppchameleonevb_mtd->name = NAND_EVB_MTD_NAME;
 
 	/* Register the partitions */
-	mtd_device_parse_register(ppchameleonevb_mtd, NULL, 0,
-			ppchameleon_mtd->size == NAND_SMALL_SIZE ?
-				partition_info_me :
-				partition_info_hi,
-			NUM_PARTITIONS);
+	mtd_device_parse_register(ppchameleonevb_mtd, NULL, NULL,
+				  ppchameleon_mtd->size == NAND_SMALL_SIZE ?
+				  partition_info_me : partition_info_hi,
+				  NUM_PARTITIONS);
 
 	/* Return happy */
 	return 0;
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 5c3d719c37e6..def50caa6f84 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -1002,6 +1002,7 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd)
 KEEP_CONFIG:
 	chip->ecc.mode = NAND_ECC_HW;
 	chip->ecc.size = host->page_size;
+	chip->ecc.strength = 1;
 
 	chip->options = NAND_NO_AUTOINCR;
 	chip->options |= NAND_NO_READRDY;
@@ -1228,8 +1229,9 @@ static int pxa3xx_nand_probe(struct platform_device *pdev)
 			continue;
 		}
 
-		ret = mtd_device_parse_register(info->host[cs]->mtd, NULL, 0,
-				pdata->parts[cs], pdata->nr_parts[cs]);
+		ret = mtd_device_parse_register(info->host[cs]->mtd, NULL,
+						NULL, pdata->parts[cs],
+						pdata->nr_parts[cs]);
 		if (!ret)
 			probe_success = 1;
 	}
diff --git a/drivers/mtd/nand/r852.c b/drivers/mtd/nand/r852.c
index 769a4e096b3c..c2040187c813 100644
--- a/drivers/mtd/nand/r852.c
+++ b/drivers/mtd/nand/r852.c
@@ -891,6 +891,7 @@ int  r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
 	chip->ecc.size = R852_DMA_LEN;
 	chip->ecc.bytes = SM_OOB_SIZE;
+	chip->ecc.strength = 2;
 	chip->ecc.hwctl = r852_ecc_hwctl;
 	chip->ecc.calculate = r852_ecc_calculate;
 	chip->ecc.correct = r852_ecc_correct;
diff --git a/drivers/mtd/nand/rtc_from4.c b/drivers/mtd/nand/rtc_from4.c
index f309addc2fa0..e55b5cfbe145 100644
--- a/drivers/mtd/nand/rtc_from4.c
+++ b/drivers/mtd/nand/rtc_from4.c
@@ -527,6 +527,7 @@ static int __init rtc_from4_init(void)
 	this->ecc.mode = NAND_ECC_HW_SYNDROME;
 	this->ecc.size = 512;
 	this->ecc.bytes = 8;
+	this->ecc.strength = 3;
 	/* return the status of extra status and ECC checks */
 	this->errstat = rtc_from4_errstat;
 	/* set the nand_oobinfo to support FPGA H/W error detection */
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index 868685db6712..91121f33f743 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -751,8 +751,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 	if (set)
 		mtd->mtd.name = set->name;
 
-	return mtd_device_parse_register(&mtd->mtd, NULL, 0,
-			set->partitions, set->nr_partitions);
+	return mtd_device_parse_register(&mtd->mtd, NULL, NULL,
+					 set->partitions, set->nr_partitions);
 }
 
 /**
@@ -823,6 +823,7 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info,
 		chip->ecc.calculate = s3c2410_nand_calculate_ecc;
 		chip->ecc.correct   = s3c2410_nand_correct_data;
 		chip->ecc.mode	    = NAND_ECC_HW;
+		chip->ecc.strength  = 1;
 
 		switch (info->cpu_type) {
 		case TYPE_S3C2410:
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 93b1f74321c2..e9b2b260de3a 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 
 #include <linux/mtd/mtd.h>
@@ -283,7 +284,7 @@ static void write_fiforeg(struct sh_flctl *flctl, int rlen, int offset)
 static void set_cmd_regs(struct mtd_info *mtd, uint32_t cmd, uint32_t flcmcdr_val)
 {
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	uint32_t flcmncr_val = readl(FLCMNCR(flctl)) & ~SEL_16BIT;
+	uint32_t flcmncr_val = flctl->flcmncr_base & ~SEL_16BIT;
 	uint32_t flcmdcr_val, addr_len_bytes = 0;
 
 	/* Set SNAND bit if page size is 2048byte */
@@ -303,6 +304,7 @@ static void set_cmd_regs(struct mtd_info *mtd, uint32_t cmd, uint32_t flcmcdr_va
 		break;
 	case NAND_CMD_READ0:
 	case NAND_CMD_READOOB:
+	case NAND_CMD_RNDOUT:
 		addr_len_bytes = flctl->rw_ADRCNT;
 		flcmdcr_val |= CDSRC_E;
 		if (flctl->chip.options & NAND_BUSWIDTH_16)
@@ -320,6 +322,7 @@ static void set_cmd_regs(struct mtd_info *mtd, uint32_t cmd, uint32_t flcmcdr_va
 		break;
 	case NAND_CMD_READID:
 		flcmncr_val &= ~SNAND_E;
+		flcmdcr_val |= CDSRC_E;
 		addr_len_bytes = ADRCNT_1;
 		break;
 	case NAND_CMD_STATUS:
@@ -513,6 +516,8 @@ static void flctl_cmdfunc(struct mtd_info *mtd, unsigned int command,
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
 	uint32_t read_cmd = 0;
 
+	pm_runtime_get_sync(&flctl->pdev->dev);
+
 	flctl->read_bytes = 0;
 	if (command != NAND_CMD_PAGEPROG)
 		flctl->index = 0;
@@ -525,7 +530,6 @@ static void flctl_cmdfunc(struct mtd_info *mtd, unsigned int command,
 			execmd_read_page_sector(mtd, page_addr);
 			break;
 		}
-		empty_fifo(flctl);
 		if (flctl->page_size)
 			set_cmd_regs(mtd, command, (NAND_CMD_READSTART << 8)
 				| command);
@@ -547,7 +551,6 @@ static void flctl_cmdfunc(struct mtd_info *mtd, unsigned int command,
 			break;
 		}
 
-		empty_fifo(flctl);
 		if (flctl->page_size) {
 			set_cmd_regs(mtd, command, (NAND_CMD_READSTART << 8)
 				| NAND_CMD_READ0);
@@ -559,15 +562,35 @@ static void flctl_cmdfunc(struct mtd_info *mtd, unsigned int command,
 		flctl->read_bytes = mtd->oobsize;
 		goto read_normal_exit;
 
+	case NAND_CMD_RNDOUT:
+		if (flctl->hwecc)
+			break;
+
+		if (flctl->page_size)
+			set_cmd_regs(mtd, command, (NAND_CMD_RNDOUTSTART << 8)
+				| command);
+		else
+			set_cmd_regs(mtd, command, command);
+
+		set_addr(mtd, column, 0);
+
+		flctl->read_bytes = mtd->writesize + mtd->oobsize - column;
+		goto read_normal_exit;
+
 	case NAND_CMD_READID:
-		empty_fifo(flctl);
 		set_cmd_regs(mtd, command, command);
-		set_addr(mtd, 0, 0);
 
-		flctl->read_bytes = 4;
+		/* READID is always performed using an 8-bit bus */
+		if (flctl->chip.options & NAND_BUSWIDTH_16)
+			column <<= 1;
+		set_addr(mtd, column, 0);
+
+		flctl->read_bytes = 8;
 		writel(flctl->read_bytes, FLDTCNTR(flctl)); /* set read size */
+		empty_fifo(flctl);
 		start_translation(flctl);
-		read_datareg(flctl, 0);	/* read and end */
+		read_fiforeg(flctl, flctl->read_bytes, 0);
+		wait_completion(flctl);
 		break;
 
 	case NAND_CMD_ERASE1:
@@ -650,29 +673,55 @@ static void flctl_cmdfunc(struct mtd_info *mtd, unsigned int command,
 	default:
 		break;
 	}
-	return;
+	goto runtime_exit;
 
 read_normal_exit:
 	writel(flctl->read_bytes, FLDTCNTR(flctl));	/* set read size */
+	empty_fifo(flctl);
 	start_translation(flctl);
 	read_fiforeg(flctl, flctl->read_bytes, 0);
 	wait_completion(flctl);
+runtime_exit:
+	pm_runtime_put_sync(&flctl->pdev->dev);
 	return;
 }
 
 static void flctl_select_chip(struct mtd_info *mtd, int chipnr)
 {
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	uint32_t flcmncr_val = readl(FLCMNCR(flctl));
+	int ret;
 
 	switch (chipnr) {
 	case -1:
-		flcmncr_val &= ~CE0_ENABLE;
-		writel(flcmncr_val, FLCMNCR(flctl));
+		flctl->flcmncr_base &= ~CE0_ENABLE;
+
+		pm_runtime_get_sync(&flctl->pdev->dev);
+		writel(flctl->flcmncr_base, FLCMNCR(flctl));
+
+		if (flctl->qos_request) {
+			dev_pm_qos_remove_request(&flctl->pm_qos);
+			flctl->qos_request = 0;
+		}
+
+		pm_runtime_put_sync(&flctl->pdev->dev);
 		break;
 	case 0:
-		flcmncr_val |= CE0_ENABLE;
-		writel(flcmncr_val, FLCMNCR(flctl));
+		flctl->flcmncr_base |= CE0_ENABLE;
+
+		if (!flctl->qos_request) {
+			ret = dev_pm_qos_add_request(&flctl->pdev->dev,
+							&flctl->pm_qos, 100);
+			if (ret < 0)
+				dev_err(&flctl->pdev->dev,
+					"PM QoS request failed: %d\n", ret);
+			flctl->qos_request = 1;
+		}
+
+		if (flctl->holden) {
+			pm_runtime_get_sync(&flctl->pdev->dev);
+			writel(HOLDEN, FLHOLDCR(flctl));
+			pm_runtime_put_sync(&flctl->pdev->dev);
+		}
 		break;
 	default:
 		BUG();
@@ -730,11 +779,6 @@ static int flctl_verify_buf(struct mtd_info *mtd, const u_char *buf, int len)
 	return 0;
 }
 
-static void flctl_register_init(struct sh_flctl *flctl, unsigned long val)
-{
-	writel(val, FLCMNCR(flctl));
-}
-
 static int flctl_chip_init_tail(struct mtd_info *mtd)
 {
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
@@ -781,13 +825,13 @@ static int flctl_chip_init_tail(struct mtd_info *mtd)
 
 		chip->ecc.size = 512;
 		chip->ecc.bytes = 10;
+		chip->ecc.strength = 4;
 		chip->ecc.read_page = flctl_read_page_hwecc;
 		chip->ecc.write_page = flctl_write_page_hwecc;
 		chip->ecc.mode = NAND_ECC_HW;
 
 		/* 4 symbols ECC enabled */
-		writel(readl(FLCMNCR(flctl)) | _4ECCEN | ECCPOS2 | ECCPOS_02,
-				FLCMNCR(flctl));
+		flctl->flcmncr_base |= _4ECCEN | ECCPOS2 | ECCPOS_02;
 	} else {
 		chip->ecc.mode = NAND_ECC_SOFT;
 	}
@@ -819,13 +863,13 @@ static int __devinit flctl_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(&pdev->dev, "failed to get I/O memory\n");
-		goto err;
+		goto err_iomap;
 	}
 
 	flctl->reg = ioremap(res->start, resource_size(res));
 	if (flctl->reg == NULL) {
 		dev_err(&pdev->dev, "failed to remap I/O memory\n");
-		goto err;
+		goto err_iomap;
 	}
 
 	platform_set_drvdata(pdev, flctl);
@@ -833,9 +877,9 @@ static int __devinit flctl_probe(struct platform_device *pdev)
 	nand = &flctl->chip;
 	flctl_mtd->priv = nand;
 	flctl->pdev = pdev;
+	flctl->flcmncr_base = pdata->flcmncr_val;
 	flctl->hwecc = pdata->has_hwecc;
-
-	flctl_register_init(flctl, pdata->flcmncr_val);
+	flctl->holden = pdata->use_holden;
 
 	nand->options = NAND_NO_AUTOINCR;
 
@@ -855,23 +899,28 @@ static int __devinit flctl_probe(struct platform_device *pdev)
 		nand->read_word = flctl_read_word;
 	}
 
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_resume(&pdev->dev);
+
 	ret = nand_scan_ident(flctl_mtd, 1, NULL);
 	if (ret)
-		goto err;
+		goto err_chip;
 
 	ret = flctl_chip_init_tail(flctl_mtd);
 	if (ret)
-		goto err;
+		goto err_chip;
 
 	ret = nand_scan_tail(flctl_mtd);
 	if (ret)
-		goto err;
+		goto err_chip;
 
 	mtd_device_register(flctl_mtd, pdata->parts, pdata->nr_parts);
 
 	return 0;
 
-err:
+err_chip:
+	pm_runtime_disable(&pdev->dev);
+err_iomap:
 	kfree(flctl);
 	return ret;
 }
@@ -881,6 +930,7 @@ static int __devexit flctl_remove(struct platform_device *pdev)
 	struct sh_flctl *flctl = platform_get_drvdata(pdev);
 
 	nand_release(&flctl->mtd);
+	pm_runtime_disable(&pdev->dev);
 	kfree(flctl);
 
 	return 0;
diff --git a/drivers/mtd/nand/sharpsl.c b/drivers/mtd/nand/sharpsl.c
index b175c0fd8b93..3421e3762a5a 100644
--- a/drivers/mtd/nand/sharpsl.c
+++ b/drivers/mtd/nand/sharpsl.c
@@ -167,6 +167,7 @@ static int __devinit sharpsl_nand_probe(struct platform_device *pdev)
 	this->ecc.mode = NAND_ECC_HW;
 	this->ecc.size = 256;
 	this->ecc.bytes = 3;
+	this->ecc.strength = 1;
 	this->badblock_pattern = data->badblock_pattern;
 	this->ecc.layout = data->ecc_layout;
 	this->ecc.hwctl = sharpsl_nand_enable_hwecc;
@@ -181,8 +182,8 @@ static int __devinit sharpsl_nand_probe(struct platform_device *pdev)
 	/* Register the partitions */
 	sharpsl->mtd.name = "sharpsl-nand";
 
-	err = mtd_device_parse_register(&sharpsl->mtd, NULL, 0,
-			data->partitions, data->nr_partitions);
+	err = mtd_device_parse_register(&sharpsl->mtd, NULL, NULL,
+					data->partitions, data->nr_partitions);
 	if (err)
 		goto err_add;
 
diff --git a/drivers/mtd/nand/tmio_nand.c b/drivers/mtd/nand/tmio_nand.c
index 6caa0cd9d6a7..5aa518081c51 100644
--- a/drivers/mtd/nand/tmio_nand.c
+++ b/drivers/mtd/nand/tmio_nand.c
@@ -430,6 +430,7 @@ static int tmio_probe(struct platform_device *dev)
 	nand_chip->ecc.mode = NAND_ECC_HW;
 	nand_chip->ecc.size = 512;
 	nand_chip->ecc.bytes = 6;
+	nand_chip->ecc.strength = 2;
 	nand_chip->ecc.hwctl = tmio_nand_enable_hwecc;
 	nand_chip->ecc.calculate = tmio_nand_calculate_ecc;
 	nand_chip->ecc.correct = tmio_nand_correct_data;
@@ -456,9 +457,9 @@ static int tmio_probe(struct platform_device *dev)
 		goto err_scan;
 	}
 	/* Register the partitions */
-	retval = mtd_device_parse_register(mtd, NULL, 0,
-			data ? data->partition : NULL,
-			data ? data->num_partitions : 0);
+	retval = mtd_device_parse_register(mtd, NULL, NULL,
+					   data ? data->partition : NULL,
+					   data ? data->num_partitions : 0);
 	if (!retval)
 		return retval;
 
diff --git a/drivers/mtd/nand/txx9ndfmc.c b/drivers/mtd/nand/txx9ndfmc.c
index c7c4f1d11c77..26398dcf21cf 100644
--- a/drivers/mtd/nand/txx9ndfmc.c
+++ b/drivers/mtd/nand/txx9ndfmc.c
@@ -356,6 +356,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		/* txx9ndfmc_nand_scan will overwrite ecc.size and ecc.bytes */
 		chip->ecc.size = 256;
 		chip->ecc.bytes = 3;
+		chip->ecc.strength = 1;
 		chip->chip_delay = 100;
 		chip->controller = &drvdata->hw_control;
 
@@ -386,7 +387,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		}
 		mtd->name = txx9_priv->mtdname;
 
-		mtd_device_parse_register(mtd, NULL, 0, NULL, 0);
+		mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
 		drvdata->mtds[i] = mtd;
 	}
 
diff --git a/drivers/mtd/nftlcore.c b/drivers/mtd/nftlcore.c
index a75382aff5f6..c5f4ebf4b384 100644
--- a/drivers/mtd/nftlcore.c
+++ b/drivers/mtd/nftlcore.c
@@ -56,13 +56,6 @@ static void nftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 	if (memcmp(mtd->name, "DiskOnChip", 10))
 		return;
 
-	if (!mtd_can_have_bb(mtd)) {
-		printk(KERN_ERR
-"NFTL no longer supports the old DiskOnChip drivers loaded via docprobe.\n"
-"Please use the new diskonchip driver under the NAND subsystem.\n");
-		return;
-	}
-
 	pr_debug("NFTL: add_mtd for %s\n", mtd->name);
 
 	nftl = kzalloc(sizeof(struct NFTLrecord), GFP_KERNEL);
diff --git a/drivers/mtd/onenand/Kconfig b/drivers/mtd/onenand/Kconfig
index 772ad2966619..91467bb03634 100644
--- a/drivers/mtd/onenand/Kconfig
+++ b/drivers/mtd/onenand/Kconfig
@@ -1,6 +1,7 @@
 menuconfig MTD_ONENAND
 	tristate "OneNAND Device Support"
 	depends on MTD
+	depends on HAS_IOMEM
 	help
 	  This enables support for accessing all type of OneNAND flash
 	  devices. For further information see
diff --git a/drivers/mtd/onenand/generic.c b/drivers/mtd/onenand/generic.c
index 0ccd5bff2544..1c4f97c63e62 100644
--- a/drivers/mtd/onenand/generic.c
+++ b/drivers/mtd/onenand/generic.c
@@ -70,9 +70,9 @@ static int __devinit generic_onenand_probe(struct platform_device *pdev)
 		goto out_iounmap;
 	}
 
-	err = mtd_device_parse_register(&info->mtd, NULL, 0,
-			pdata ? pdata->parts : NULL,
-			pdata ? pdata->nr_parts : 0);
+	err = mtd_device_parse_register(&info->mtd, NULL, NULL,
+					pdata ? pdata->parts : NULL,
+					pdata ? pdata->nr_parts : 0);
 
 	platform_set_drvdata(pdev, info);
 
diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c
index 7e9ea6852b67..398a82783848 100644
--- a/drivers/mtd/onenand/omap2.c
+++ b/drivers/mtd/onenand/omap2.c
@@ -751,9 +751,9 @@ static int __devinit omap2_onenand_probe(struct platform_device *pdev)
 	if ((r = onenand_scan(&c->mtd, 1)) < 0)
 		goto err_release_regulator;
 
-	r = mtd_device_parse_register(&c->mtd, NULL, 0,
-			pdata ? pdata->parts : NULL,
-			pdata ? pdata->nr_parts : 0);
+	r = mtd_device_parse_register(&c->mtd, NULL, NULL,
+				      pdata ? pdata->parts : NULL,
+				      pdata ? pdata->nr_parts : 0);
 	if (r)
 		goto err_release_onenand;
 
diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c
index a061bc163da2..b3ce12ef359e 100644
--- a/drivers/mtd/onenand/onenand_base.c
+++ b/drivers/mtd/onenand/onenand_base.c
@@ -1753,16 +1753,6 @@ static int onenand_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
 	pr_debug("%s: to = 0x%08x, len = %i\n", __func__, (unsigned int)to,
 			(int)len);
 
-	/* Initialize retlen, in case of early exit */
-	*retlen = 0;
-
-	/* Do not allow writes past end of device */
-	if (unlikely((to + len) > mtd->size)) {
-		printk(KERN_ERR "%s: Attempt write to past end of device\n",
-			__func__);
-		return -EINVAL;
-	}
-
 	/* Reject writes, which are not page aligned */
         if (unlikely(NOTALIGNED(to) || NOTALIGNED(len))) {
 		printk(KERN_ERR "%s: Attempt to write not page aligned data\n",
@@ -1890,13 +1880,6 @@ static int onenand_write_ops_nolock(struct mtd_info *mtd, loff_t to,
 	ops->retlen = 0;
 	ops->oobretlen = 0;
 
-	/* Do not allow writes past end of device */
-	if (unlikely((to + len) > mtd->size)) {
-		printk(KERN_ERR "%s: Attempt write to past end of device\n",
-			__func__);
-		return -EINVAL;
-	}
-
 	/* Reject writes, which are not page aligned */
         if (unlikely(NOTALIGNED(to) || NOTALIGNED(len))) {
 		printk(KERN_ERR "%s: Attempt to write not page aligned data\n",
@@ -2493,12 +2476,6 @@ static int onenand_erase(struct mtd_info *mtd, struct erase_info *instr)
 			(unsigned long long)instr->addr,
 			(unsigned long long)instr->len);
 
-	/* Do not allow erase past end of device */
-	if (unlikely((len + addr) > mtd->size)) {
-		printk(KERN_ERR "%s: Erase past end of device\n", __func__);
-		return -EINVAL;
-	}
-
 	if (FLEXONENAND(this)) {
 		/* Find the eraseregion of this address */
 		int i = flexonenand_region(mtd, addr);
@@ -2525,8 +2502,6 @@ static int onenand_erase(struct mtd_info *mtd, struct erase_info *instr)
 		return -EINVAL;
 	}
 
-	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
-
 	/* Grab the lock and see if the device is available */
 	onenand_get_device(mtd, FL_ERASING);
 
@@ -4103,33 +4078,34 @@ int onenand_scan(struct mtd_info *mtd, int maxchips)
 	mtd->oobavail = this->ecclayout->oobavail;
 
 	mtd->ecclayout = this->ecclayout;
+	mtd->ecc_strength = 1;
 
 	/* Fill in remaining MTD driver data */
 	mtd->type = ONENAND_IS_MLC(this) ? MTD_MLCNANDFLASH : MTD_NANDFLASH;
 	mtd->flags = MTD_CAP_NANDFLASH;
-	mtd->erase = onenand_erase;
-	mtd->point = NULL;
-	mtd->unpoint = NULL;
-	mtd->read = onenand_read;
-	mtd->write = onenand_write;
-	mtd->read_oob = onenand_read_oob;
-	mtd->write_oob = onenand_write_oob;
-	mtd->panic_write = onenand_panic_write;
+	mtd->_erase = onenand_erase;
+	mtd->_point = NULL;
+	mtd->_unpoint = NULL;
+	mtd->_read = onenand_read;
+	mtd->_write = onenand_write;
+	mtd->_read_oob = onenand_read_oob;
+	mtd->_write_oob = onenand_write_oob;
+	mtd->_panic_write = onenand_panic_write;
 #ifdef CONFIG_MTD_ONENAND_OTP
-	mtd->get_fact_prot_info = onenand_get_fact_prot_info;
-	mtd->read_fact_prot_reg = onenand_read_fact_prot_reg;
-	mtd->get_user_prot_info = onenand_get_user_prot_info;
-	mtd->read_user_prot_reg = onenand_read_user_prot_reg;
-	mtd->write_user_prot_reg = onenand_write_user_prot_reg;
-	mtd->lock_user_prot_reg = onenand_lock_user_prot_reg;
+	mtd->_get_fact_prot_info = onenand_get_fact_prot_info;
+	mtd->_read_fact_prot_reg = onenand_read_fact_prot_reg;
+	mtd->_get_user_prot_info = onenand_get_user_prot_info;
+	mtd->_read_user_prot_reg = onenand_read_user_prot_reg;
+	mtd->_write_user_prot_reg = onenand_write_user_prot_reg;
+	mtd->_lock_user_prot_reg = onenand_lock_user_prot_reg;
 #endif
-	mtd->sync = onenand_sync;
-	mtd->lock = onenand_lock;
-	mtd->unlock = onenand_unlock;
-	mtd->suspend = onenand_suspend;
-	mtd->resume = onenand_resume;
-	mtd->block_isbad = onenand_block_isbad;
-	mtd->block_markbad = onenand_block_markbad;
+	mtd->_sync = onenand_sync;
+	mtd->_lock = onenand_lock;
+	mtd->_unlock = onenand_unlock;
+	mtd->_suspend = onenand_suspend;
+	mtd->_resume = onenand_resume;
+	mtd->_block_isbad = onenand_block_isbad;
+	mtd->_block_markbad = onenand_block_markbad;
 	mtd->owner = THIS_MODULE;
 	mtd->writebufsize = mtd->writesize;
 
diff --git a/drivers/mtd/onenand/samsung.c b/drivers/mtd/onenand/samsung.c
index fa1ee43f735b..8e4b3f2742ba 100644
--- a/drivers/mtd/onenand/samsung.c
+++ b/drivers/mtd/onenand/samsung.c
@@ -923,7 +923,7 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 		r = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 		if (!r) {
 			dev_err(&pdev->dev, "no buffer memory resource defined\n");
-			return -ENOENT;
+			err = -ENOENT;
 			goto ahb_resource_failed;
 		}
 
@@ -964,7 +964,7 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 		r = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 		if (!r) {
 			dev_err(&pdev->dev, "no dma memory resource defined\n");
-			return -ENOENT;
+			err = -ENOENT;
 			goto dma_resource_failed;
 		}
 
@@ -1014,7 +1014,7 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 	if (s3c_read_reg(MEM_CFG_OFFSET) & ONENAND_SYS_CFG1_SYNC_READ)
 		dev_info(&onenand->pdev->dev, "OneNAND Sync. Burst Read enabled\n");
 
-	err = mtd_device_parse_register(mtd, NULL, 0,
+	err = mtd_device_parse_register(mtd, NULL, NULL,
 					pdata ? pdata->parts : NULL,
 					pdata ? pdata->nr_parts : 0);
 
diff --git a/drivers/mtd/redboot.c b/drivers/mtd/redboot.c
index 48970c14beff..580035c803d6 100644
--- a/drivers/mtd/redboot.c
+++ b/drivers/mtd/redboot.c
@@ -78,8 +78,7 @@ static int parse_redboot_partitions(struct mtd_info *master,
 
 	if ( directory < 0 ) {
 		offset = master->size + directory * master->erasesize;
-		while (mtd_can_have_bb(master) &&
-		       mtd_block_isbad(master, offset)) {
+		while (mtd_block_isbad(master, offset)) {
 			if (!offset) {
 			nogood:
 				printk(KERN_NOTICE "Failed to find a non-bad block to check for RedBoot partition table\n");
@@ -89,8 +88,7 @@ static int parse_redboot_partitions(struct mtd_info *master,
 		}
 	} else {
 		offset = directory * master->erasesize;
-		while (mtd_can_have_bb(master) &&
-		       mtd_block_isbad(master, offset)) {
+		while (mtd_block_isbad(master, offset)) {
 			offset += master->erasesize;
 			if (offset == master->size)
 				goto nogood;
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index 072ed5970e2f..9e2dfd517aa5 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -1256,7 +1256,7 @@ static void sm_remove_dev(struct mtd_blktrans_dev *dev)
 
 static struct mtd_blktrans_ops sm_ftl_ops = {
 	.name		= "smblk",
-	.major		= -1,
+	.major		= 0,
 	.part_bits	= SM_FTL_PARTN_BITS,
 	.blksize	= SM_SECTOR_SIZE,
 	.getgeo		= sm_getgeo,
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index e2cdebf40840..61af9bb560ab 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -386,19 +386,11 @@ out:
 	return count;
 }
 
-static int default_open(struct inode *inode, struct file *file)
-{
-	if (inode->i_private)
-		file->private_data = inode->i_private;
-
-	return 0;
-}
-
 /* File operations for all UBI debugfs files */
 static const struct file_operations dfs_fops = {
 	.read   = dfs_file_read,
 	.write  = dfs_file_write,
-	.open   = default_open,
+	.open	= simple_open,
 	.llseek = no_llseek,
 	.owner  = THIS_MODULE,
 };
diff --git a/drivers/mtd/ubi/gluebi.c b/drivers/mtd/ubi/gluebi.c
index 941bc3c05d6e..90b98822d9a4 100644
--- a/drivers/mtd/ubi/gluebi.c
+++ b/drivers/mtd/ubi/gluebi.c
@@ -174,11 +174,7 @@ static int gluebi_read(struct mtd_info *mtd, loff_t from, size_t len,
 	int err = 0, lnum, offs, total_read;
 	struct gluebi_device *gluebi;
 
-	if (len < 0 || from < 0 || from + len > mtd->size)
-		return -EINVAL;
-
 	gluebi = container_of(mtd, struct gluebi_device, mtd);
-
 	lnum = div_u64_rem(from, mtd->erasesize, &offs);
 	total_read = len;
 	while (total_read) {
@@ -218,14 +214,7 @@ static int gluebi_write(struct mtd_info *mtd, loff_t to, size_t len,
 	int err = 0, lnum, offs, total_written;
 	struct gluebi_device *gluebi;
 
-	if (len < 0 || to < 0 || len + to > mtd->size)
-		return -EINVAL;
-
 	gluebi = container_of(mtd, struct gluebi_device, mtd);
-
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-
 	lnum = div_u64_rem(to, mtd->erasesize, &offs);
 
 	if (len % mtd->writesize || offs % mtd->writesize)
@@ -265,21 +254,13 @@ static int gluebi_erase(struct mtd_info *mtd, struct erase_info *instr)
 	int err, i, lnum, count;
 	struct gluebi_device *gluebi;
 
-	if (instr->addr < 0 || instr->addr > mtd->size - mtd->erasesize)
-		return -EINVAL;
-	if (instr->len < 0 || instr->addr + instr->len > mtd->size)
-		return -EINVAL;
 	if (mtd_mod_by_ws(instr->addr, mtd) || mtd_mod_by_ws(instr->len, mtd))
 		return -EINVAL;
 
 	lnum = mtd_div_by_eb(instr->addr, mtd);
 	count = mtd_div_by_eb(instr->len, mtd);
-
 	gluebi = container_of(mtd, struct gluebi_device, mtd);
 
-	if (!(mtd->flags & MTD_WRITEABLE))
-		return -EROFS;
-
 	for (i = 0; i < count - 1; i++) {
 		err = ubi_leb_unmap(gluebi->desc, lnum + i);
 		if (err)
@@ -340,11 +321,11 @@ static int gluebi_create(struct ubi_device_info *di,
 	mtd->owner      = THIS_MODULE;
 	mtd->writesize  = di->min_io_size;
 	mtd->erasesize  = vi->usable_leb_size;
-	mtd->read       = gluebi_read;
-	mtd->write      = gluebi_write;
-	mtd->erase      = gluebi_erase;
-	mtd->get_device = gluebi_get_device;
-	mtd->put_device = gluebi_put_device;
+	mtd->_read       = gluebi_read;
+	mtd->_write      = gluebi_write;
+	mtd->_erase      = gluebi_erase;
+	mtd->_get_device = gluebi_get_device;
+	mtd->_put_device = gluebi_put_device;
 
 	/*
 	 * In case of dynamic a volume, MTD device size is just volume size. In
diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c
index 9abd4eb86dc1..dd5e04813b76 100644
--- a/drivers/net/appletalk/cops.c
+++ b/drivers/net/appletalk/cops.c
@@ -70,7 +70,6 @@ static const char *version =
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c
index 6057b30417a2..0910dce3996d 100644
--- a/drivers/net/appletalk/ltpc.c
+++ b/drivers/net/appletalk/ltpc.c
@@ -229,7 +229,6 @@ static int dma;
 #include <linux/bitops.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/io.h>
 
diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c
index 980e65c14936..5bed4c4e2508 100644
--- a/drivers/net/arcnet/com20020_cs.c
+++ b/drivers/net/arcnet/com20020_cs.c
@@ -47,7 +47,6 @@
 #include <pcmcia/ds.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #define VERSION "arcnet: COM20020 PCMCIA support loaded.\n"
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a20b5850e7ce..62d2409bb293 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -54,7 +54,6 @@
 #include <linux/inet.h>
 #include <linux/bitops.h>
 #include <linux/io.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <linux/uaccess.h>
 #include <linux/errno.h>
@@ -2035,6 +2034,9 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
 	write_unlock_bh(&bond->lock);
 	unblock_netpoll_tx();
 
+	if (bond->slave_cnt == 0)
+		call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev);
+
 	bond_compute_features(bond);
 	if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
 	    (old_features & NETIF_F_VLAN_CHALLENGED))
@@ -3008,7 +3010,11 @@ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks)
 					   trans_start + delta_in_ticks)) ||
 			    bond->curr_active_slave != slave) {
 				slave->link = BOND_LINK_UP;
-				bond->current_arp_slave = NULL;
+				if (bond->current_arp_slave) {
+					bond_set_slave_inactive_flags(
+						bond->current_arp_slave);
+					bond->current_arp_slave = NULL;
+				}
 
 				pr_info("%s: link status definitely up for interface %s.\n",
 					bond->dev->name, slave->dev->name);
@@ -3702,17 +3708,52 @@ static void bond_set_multicast_list(struct net_device *bond_dev)
 	read_unlock(&bond->lock);
 }
 
-static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms)
+static int bond_neigh_init(struct neighbour *n)
 {
-	struct bonding *bond = netdev_priv(dev);
+	struct bonding *bond = netdev_priv(n->dev);
 	struct slave *slave = bond->first_slave;
+	const struct net_device_ops *slave_ops;
+	struct neigh_parms parms;
+	int ret;
+
+	if (!slave)
+		return 0;
+
+	slave_ops = slave->dev->netdev_ops;
+
+	if (!slave_ops->ndo_neigh_setup)
+		return 0;
+
+	parms.neigh_setup = NULL;
+	parms.neigh_cleanup = NULL;
+	ret = slave_ops->ndo_neigh_setup(slave->dev, &parms);
+	if (ret)
+		return ret;
+
+	/*
+	 * Assign slave's neigh_cleanup to neighbour in case cleanup is called
+	 * after the last slave has been detached.  Assumes that all slaves
+	 * utilize the same neigh_cleanup (true at this writing as only user
+	 * is ipoib).
+	 */
+	n->parms->neigh_cleanup = parms.neigh_cleanup;
+
+	if (!parms.neigh_setup)
+		return 0;
+
+	return parms.neigh_setup(n);
+}
+
+/*
+ * The bonding ndo_neigh_setup is called at init time beofre any
+ * slave exists. So we must declare proxy setup function which will
+ * be used at run time to resolve the actual slave neigh param setup.
+ */
+static int bond_neigh_setup(struct net_device *dev,
+			    struct neigh_parms *parms)
+{
+	parms->neigh_setup   = bond_neigh_init;
 
-	if (slave) {
-		const struct net_device_ops *slave_ops
-			= slave->dev->netdev_ops;
-		if (slave_ops->ndo_neigh_setup)
-			return slave_ops->ndo_neigh_setup(slave->dev, parms);
-	}
 	return 0;
 }
 
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
index 96391c36fa74..b71ce9bf0afb 100644
--- a/drivers/net/caif/caif_spi.c
+++ b/drivers/net/caif/caif_spi.c
@@ -127,12 +127,6 @@ static inline void dev_debugfs_rem(struct cfspi *cfspi)
 	debugfs_remove(cfspi->dbgfs_dir);
 }
 
-static int dbgfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t dbgfs_state(struct file *file, char __user *user_buf,
 			   size_t count, loff_t *ppos)
 {
@@ -243,13 +237,13 @@ static ssize_t dbgfs_frame(struct file *file, char __user *user_buf,
 }
 
 static const struct file_operations dbgfs_state_fops = {
-	.open = dbgfs_open,
+	.open = simple_open,
 	.read = dbgfs_state,
 	.owner = THIS_MODULE
 };
 
 static const struct file_operations dbgfs_frame_fops = {
-	.open = dbgfs_open,
+	.open = simple_open,
 	.read = dbgfs_frame,
 	.owner = THIS_MODULE
 };
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 98a5a7d867f5..034c16b60e96 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -40,7 +40,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c
index 7cb2785e209d..ec03b401620a 100644
--- a/drivers/net/cris/eth_v10.c
+++ b/drivers/net/cris/eth_v10.c
@@ -35,7 +35,6 @@
 #include <asm/io.h>         /* CRIS_LED_* I/O functions */
 #include <asm/irq.h>
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/ethernet.h>
 #include <asm/cache.h>
 #include <arch/io_interface_mux.h>
diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c
index e61b2f82ba3a..66df93638085 100644
--- a/drivers/net/ethernet/3com/3c574_cs.c
+++ b/drivers/net/ethernet/3com/3c574_cs.c
@@ -95,7 +95,6 @@ earlier 3Com products.
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 /*====================================================================*/
 
diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c
index b23253b9f742..a556c01e011b 100644
--- a/drivers/net/ethernet/3com/3c589_cs.c
+++ b/drivers/net/ethernet/3com/3c589_cs.c
@@ -50,7 +50,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 /* To minimize the size of the driver source I only define operating
    constants if they are used several times.  You'll need the manual
diff --git a/drivers/net/ethernet/8390/3c503.c b/drivers/net/ethernet/8390/3c503.c
index fbab1367505f..49d76bd0dc86 100644
--- a/drivers/net/ethernet/8390/3c503.c
+++ b/drivers/net/ethernet/8390/3c503.c
@@ -54,7 +54,6 @@ static const char version[] =
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 #include "8390.h"
diff --git a/drivers/net/ethernet/8390/ac3200.c b/drivers/net/ethernet/8390/ac3200.c
index 5337dd0a59b0..ccf07942ff6e 100644
--- a/drivers/net/ethernet/8390/ac3200.c
+++ b/drivers/net/ethernet/8390/ac3200.c
@@ -34,7 +34,6 @@ static const char version[] =
 #include <linux/init.h>
 #include <linux/interrupt.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c
index 3ad5d2f9a49c..923959275a82 100644
--- a/drivers/net/ethernet/8390/apne.c
+++ b/drivers/net/ethernet/8390/apne.c
@@ -39,7 +39,6 @@
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/setup.h>
 #include <asm/amigaints.h>
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index 211efbf82b56..203ff9dccadb 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -31,7 +31,6 @@
 
 #include <net/ax88796.h>
 
-#include <asm/system.h>
 
 /* Rename the lib8390.c functions to show that they are in this driver */
 #define __ei_open ax_ei_open
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index c5bd8eb7a9f5..e1b3941bd149 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -46,7 +46,6 @@
 #include <pcmcia/cisreg.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/net/ethernet/8390/e2100.c b/drivers/net/ethernet/8390/e2100.c
index d16dc53c1813..ed55ce85ebbf 100644
--- a/drivers/net/ethernet/8390/e2100.c
+++ b/drivers/net/ethernet/8390/e2100.c
@@ -48,7 +48,6 @@ static const char version[] =
 #include <linux/delay.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/es3210.c b/drivers/net/ethernet/8390/es3210.c
index 6428f9e7a554..ba1b5c95531f 100644
--- a/drivers/net/ethernet/8390/es3210.c
+++ b/drivers/net/ethernet/8390/es3210.c
@@ -59,7 +59,6 @@ static const char version[] =
 #include <linux/etherdevice.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c
index 89cba45c35ca..8322c54972f3 100644
--- a/drivers/net/ethernet/8390/etherh.c
+++ b/drivers/net/ethernet/8390/etherh.c
@@ -45,9 +45,9 @@
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/ecard.h>
 #include <asm/io.h>
+#include <asm/system_info.h>
 
 #define EI_SHIFT(x)	(ei_local->reg_offset[x])
 
diff --git a/drivers/net/ethernet/8390/hp-plus.c b/drivers/net/ethernet/8390/hp-plus.c
index d42938b6b596..52f70f999c00 100644
--- a/drivers/net/ethernet/8390/hp-plus.c
+++ b/drivers/net/ethernet/8390/hp-plus.c
@@ -33,7 +33,6 @@ static const char version[] =
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include "8390.h"
diff --git a/drivers/net/ethernet/8390/hp.c b/drivers/net/ethernet/8390/hp.c
index 113f1e075a26..37fa89aa4578 100644
--- a/drivers/net/ethernet/8390/hp.c
+++ b/drivers/net/ethernet/8390/hp.c
@@ -33,7 +33,6 @@ static const char version[] =
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include "8390.h"
diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c
index e77f624e8194..b329f5c0d62b 100644
--- a/drivers/net/ethernet/8390/lib8390.c
+++ b/drivers/net/ethernet/8390/lib8390.c
@@ -57,7 +57,6 @@
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/bitops.h>
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <asm/irq.h>
diff --git a/drivers/net/ethernet/8390/lne390.c b/drivers/net/ethernet/8390/lne390.c
index 69490ae018ea..479409bf2e3c 100644
--- a/drivers/net/ethernet/8390/lne390.c
+++ b/drivers/net/ethernet/8390/lne390.c
@@ -46,7 +46,6 @@ static const char *version =
 #include <linux/etherdevice.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index af5d9822cad9..88ccc8b14f0a 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -37,7 +37,6 @@
 #include <linux/bitops.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/hwtest.h>
 #include <asm/macints.h>
diff --git a/drivers/net/ethernet/8390/ne-h8300.c b/drivers/net/ethernet/8390/ne-h8300.c
index 9b9c77d5a65c..7fc28f2d28a6 100644
--- a/drivers/net/ethernet/8390/ne-h8300.c
+++ b/drivers/net/ethernet/8390/ne-h8300.c
@@ -29,7 +29,6 @@ static const char version1[] =
 #include <linux/etherdevice.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c
index f92ea2a65a57..d04911d33b64 100644
--- a/drivers/net/ethernet/8390/ne.c
+++ b/drivers/net/ethernet/8390/ne.c
@@ -53,7 +53,6 @@ static const char version2[] =
 #include <linux/jiffies.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include "8390.h"
diff --git a/drivers/net/ethernet/8390/ne2.c b/drivers/net/ethernet/8390/ne2.c
index 922b32036c63..ef85839f43d8 100644
--- a/drivers/net/ethernet/8390/ne2.c
+++ b/drivers/net/ethernet/8390/ne2.c
@@ -76,7 +76,6 @@ static const char *version = "ne2.c:v0.91 Nov 16 1998 Wim Dumon <wimpie@kotnet.o
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c
index 3fab04a0034a..5e8845febfb8 100644
--- a/drivers/net/ethernet/8390/ne2k-pci.c
+++ b/drivers/net/ethernet/8390/ne2k-pci.c
@@ -54,7 +54,6 @@ static int options[MAX_UNITS];
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/uaccess.h>
diff --git a/drivers/net/ethernet/8390/ne3210.c b/drivers/net/ethernet/8390/ne3210.c
index 2a3e8057feae..a2f8b2b8e27c 100644
--- a/drivers/net/ethernet/8390/ne3210.c
+++ b/drivers/net/ethernet/8390/ne3210.c
@@ -39,7 +39,6 @@
 #include <linux/mm.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index f2a4e5de18c4..de1af0bfed4c 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -49,7 +49,6 @@
 #include <pcmcia/cisreg.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/net/ethernet/8390/smc-mca.c b/drivers/net/ethernet/8390/smc-mca.c
index 77efec44fea0..7a68590f2804 100644
--- a/drivers/net/ethernet/8390/smc-mca.c
+++ b/drivers/net/ethernet/8390/smc-mca.c
@@ -47,7 +47,6 @@
 #include <linux/etherdevice.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c
index 1cc306a83ff7..b0fbce39661a 100644
--- a/drivers/net/ethernet/8390/smc-ultra.c
+++ b/drivers/net/ethernet/8390/smc-ultra.c
@@ -69,7 +69,6 @@ static const char version[] =
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/smc-ultra32.c b/drivers/net/ethernet/8390/smc-ultra32.c
index bb87053eb3da..923e42aedcfd 100644
--- a/drivers/net/ethernet/8390/smc-ultra32.c
+++ b/drivers/net/ethernet/8390/smc-ultra32.c
@@ -57,7 +57,6 @@ static const char *version = "smc-ultra32.c: 06/97 v1.00\n";
 #include <linux/etherdevice.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c
index 3b903759980a..8df4c4157230 100644
--- a/drivers/net/ethernet/8390/stnic.c
+++ b/drivers/net/ethernet/8390/stnic.c
@@ -17,7 +17,6 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <mach-se/mach/se.h>
 #include <asm/machvec.h>
diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c
index c175fadb597b..03eb3eed49fa 100644
--- a/drivers/net/ethernet/8390/wd.c
+++ b/drivers/net/ethernet/8390/wd.c
@@ -39,7 +39,6 @@ static const char version[] =
 #include <linux/etherdevice.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c
index bcd27323b203..7818e6397e91 100644
--- a/drivers/net/ethernet/8390/zorro8390.c
+++ b/drivers/net/ethernet/8390/zorro8390.c
@@ -31,7 +31,6 @@
 #include <linux/zorro.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/amigaints.h>
 #include <asm/amigahw.h>
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 6c3b1c0adaa0..7219123fa0a4 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -78,7 +78,6 @@
 #include <net/sock.h>
 #include <net/ip.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/byteorder.h>
diff --git a/drivers/net/ethernet/amd/7990.c b/drivers/net/ethernet/amd/7990.c
index 1b046f58d58f..6e722dc37db7 100644
--- a/drivers/net/ethernet/amd/7990.c
+++ b/drivers/net/ethernet/amd/7990.c
@@ -33,7 +33,6 @@
 #include <linux/socket.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/pgtable.h>
diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c
index cc7b9e46780c..e10ffad525a7 100644
--- a/drivers/net/ethernet/amd/am79c961a.c
+++ b/drivers/net/ethernet/amd/am79c961a.c
@@ -30,7 +30,6 @@
 #include <linux/io.h>
 
 #include <mach/hardware.h>
-#include <asm/system.h>
 
 #define TX_BUFFERS 15
 #define RX_BUFFERS 25
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 9f62504d0086..64d0d9c1afa2 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -88,7 +88,6 @@ Revision History:
 #include <linux/crc32.h>
 #include <linux/dma-mapping.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index 7dc508e5c72e..75299f500ee5 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -64,7 +64,6 @@
 #include <linux/types.h>
 
 #include <asm/addrspace.h>
-#include <asm/system.h>
 
 #include <asm/dec/interrupts.h>
 #include <asm/dec/ioasic.h>
diff --git a/drivers/net/ethernet/amd/hplance.c b/drivers/net/ethernet/amd/hplance.c
index 4e2d68a4de8a..8baff4e5d964 100644
--- a/drivers/net/ethernet/amd/hplance.c
+++ b/drivers/net/ethernet/amd/hplance.c
@@ -22,7 +22,6 @@
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 
diff --git a/drivers/net/ethernet/amd/mvme147.c b/drivers/net/ethernet/amd/mvme147.c
index 56bc47a94186..9af3c307862c 100644
--- a/drivers/net/ethernet/amd/mvme147.c
+++ b/drivers/net/ethernet/amd/mvme147.c
@@ -22,7 +22,6 @@
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/mvme147hw.h>
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index ebdb9e238a8d..9f59bf63514b 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -154,7 +154,6 @@ Include Files
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 /* ----------------------------------------------------------------------------
 Defines
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index e3fe3504e198..d7a3533d990b 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -95,7 +95,6 @@ static char lancestr[] = "LANCE";
 #include <linux/of_device.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/pgtable.h>
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 583da06e715d..5a58cff78dc2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1863,7 +1863,6 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 		 * bnx2x_periodic_task().
 		 */
 		smp_mb();
-		queue_delayed_work(bnx2x_wq, &bp->period_task, 0);
 	} else
 		bp->port.pmf = 0;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
index cd6dfa9eaa3a..b9b263323436 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
@@ -25,31 +25,31 @@
 	(IRO[149].base + ((funcId) * IRO[149].m1))
 #define CSTORM_IGU_MODE_OFFSET (IRO[157].base)
 #define CSTORM_ISCSI_CQ_SIZE_OFFSET(pfId) \
-	(IRO[315].base + ((pfId) * IRO[315].m1))
-#define CSTORM_ISCSI_CQ_SQN_SIZE_OFFSET(pfId) \
 	(IRO[316].base + ((pfId) * IRO[316].m1))
+#define CSTORM_ISCSI_CQ_SQN_SIZE_OFFSET(pfId) \
+	(IRO[317].base + ((pfId) * IRO[317].m1))
 #define CSTORM_ISCSI_EQ_CONS_OFFSET(pfId, iscsiEqId) \
-	(IRO[308].base + ((pfId) * IRO[308].m1) + ((iscsiEqId) * IRO[308].m2))
+	(IRO[309].base + ((pfId) * IRO[309].m1) + ((iscsiEqId) * IRO[309].m2))
 #define CSTORM_ISCSI_EQ_NEXT_EQE_ADDR_OFFSET(pfId, iscsiEqId) \
-	(IRO[310].base + ((pfId) * IRO[310].m1) + ((iscsiEqId) * IRO[310].m2))
+	(IRO[311].base + ((pfId) * IRO[311].m1) + ((iscsiEqId) * IRO[311].m2))
 #define CSTORM_ISCSI_EQ_NEXT_PAGE_ADDR_OFFSET(pfId, iscsiEqId) \
-	(IRO[309].base + ((pfId) * IRO[309].m1) + ((iscsiEqId) * IRO[309].m2))
+	(IRO[310].base + ((pfId) * IRO[310].m1) + ((iscsiEqId) * IRO[310].m2))
 #define CSTORM_ISCSI_EQ_NEXT_PAGE_ADDR_VALID_OFFSET(pfId, iscsiEqId) \
-	(IRO[311].base + ((pfId) * IRO[311].m1) + ((iscsiEqId) * IRO[311].m2))
+	(IRO[312].base + ((pfId) * IRO[312].m1) + ((iscsiEqId) * IRO[312].m2))
 #define CSTORM_ISCSI_EQ_PROD_OFFSET(pfId, iscsiEqId) \
-	(IRO[307].base + ((pfId) * IRO[307].m1) + ((iscsiEqId) * IRO[307].m2))
+	(IRO[308].base + ((pfId) * IRO[308].m1) + ((iscsiEqId) * IRO[308].m2))
 #define CSTORM_ISCSI_EQ_SB_INDEX_OFFSET(pfId, iscsiEqId) \
-	(IRO[313].base + ((pfId) * IRO[313].m1) + ((iscsiEqId) * IRO[313].m2))
+	(IRO[314].base + ((pfId) * IRO[314].m1) + ((iscsiEqId) * IRO[314].m2))
 #define CSTORM_ISCSI_EQ_SB_NUM_OFFSET(pfId, iscsiEqId) \
-	(IRO[312].base + ((pfId) * IRO[312].m1) + ((iscsiEqId) * IRO[312].m2))
+	(IRO[313].base + ((pfId) * IRO[313].m1) + ((iscsiEqId) * IRO[313].m2))
 #define CSTORM_ISCSI_HQ_SIZE_OFFSET(pfId) \
-	(IRO[314].base + ((pfId) * IRO[314].m1))
+	(IRO[315].base + ((pfId) * IRO[315].m1))
 #define CSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfId) \
-	(IRO[306].base + ((pfId) * IRO[306].m1))
+	(IRO[307].base + ((pfId) * IRO[307].m1))
 #define CSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfId) \
-	(IRO[305].base + ((pfId) * IRO[305].m1))
+	(IRO[306].base + ((pfId) * IRO[306].m1))
 #define CSTORM_ISCSI_PAGE_SIZE_OFFSET(pfId) \
-	(IRO[304].base + ((pfId) * IRO[304].m1))
+	(IRO[305].base + ((pfId) * IRO[305].m1))
 #define CSTORM_RECORD_SLOW_PATH_OFFSET(funcId) \
 	(IRO[151].base + ((funcId) * IRO[151].m1))
 #define CSTORM_SP_STATUS_BLOCK_DATA_OFFSET(pfId) \
@@ -96,37 +96,37 @@
 #define TSTORM_FUNC_EN_OFFSET(funcId) \
 	(IRO[103].base + ((funcId) * IRO[103].m1))
 #define TSTORM_ISCSI_ERROR_BITMAP_OFFSET(pfId) \
-	(IRO[271].base + ((pfId) * IRO[271].m1))
-#define TSTORM_ISCSI_L2_ISCSI_OOO_CID_TABLE_OFFSET(pfId) \
 	(IRO[272].base + ((pfId) * IRO[272].m1))
-#define TSTORM_ISCSI_L2_ISCSI_OOO_CLIENT_ID_TABLE_OFFSET(pfId) \
+#define TSTORM_ISCSI_L2_ISCSI_OOO_CID_TABLE_OFFSET(pfId) \
 	(IRO[273].base + ((pfId) * IRO[273].m1))
-#define TSTORM_ISCSI_L2_ISCSI_OOO_PROD_OFFSET(pfId) \
+#define TSTORM_ISCSI_L2_ISCSI_OOO_CLIENT_ID_TABLE_OFFSET(pfId) \
 	(IRO[274].base + ((pfId) * IRO[274].m1))
+#define TSTORM_ISCSI_L2_ISCSI_OOO_PROD_OFFSET(pfId) \
+	(IRO[275].base + ((pfId) * IRO[275].m1))
 #define TSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfId) \
-	(IRO[270].base + ((pfId) * IRO[270].m1))
+	(IRO[271].base + ((pfId) * IRO[271].m1))
 #define TSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfId) \
-	(IRO[269].base + ((pfId) * IRO[269].m1))
+	(IRO[270].base + ((pfId) * IRO[270].m1))
 #define TSTORM_ISCSI_PAGE_SIZE_OFFSET(pfId) \
-	(IRO[268].base + ((pfId) * IRO[268].m1))
+	(IRO[269].base + ((pfId) * IRO[269].m1))
 #define TSTORM_ISCSI_RQ_SIZE_OFFSET(pfId) \
-	(IRO[267].base + ((pfId) * IRO[267].m1))
+	(IRO[268].base + ((pfId) * IRO[268].m1))
 #define TSTORM_ISCSI_TCP_LOCAL_ADV_WND_OFFSET(pfId) \
-	(IRO[276].base + ((pfId) * IRO[276].m1))
+	(IRO[277].base + ((pfId) * IRO[277].m1))
 #define TSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(pfId) \
-	(IRO[263].base + ((pfId) * IRO[263].m1))
-#define TSTORM_ISCSI_TCP_VARS_LSB_LOCAL_MAC_ADDR_OFFSET(pfId) \
 	(IRO[264].base + ((pfId) * IRO[264].m1))
-#define TSTORM_ISCSI_TCP_VARS_MID_LOCAL_MAC_ADDR_OFFSET(pfId) \
+#define TSTORM_ISCSI_TCP_VARS_LSB_LOCAL_MAC_ADDR_OFFSET(pfId) \
 	(IRO[265].base + ((pfId) * IRO[265].m1))
-#define TSTORM_ISCSI_TCP_VARS_MSB_LOCAL_MAC_ADDR_OFFSET(pfId) \
+#define TSTORM_ISCSI_TCP_VARS_MID_LOCAL_MAC_ADDR_OFFSET(pfId) \
 	(IRO[266].base + ((pfId) * IRO[266].m1))
+#define TSTORM_ISCSI_TCP_VARS_MSB_LOCAL_MAC_ADDR_OFFSET(pfId) \
+	(IRO[267].base + ((pfId) * IRO[267].m1))
 #define TSTORM_MAC_FILTER_CONFIG_OFFSET(pfId) \
 	(IRO[202].base + ((pfId) * IRO[202].m1))
 #define TSTORM_RECORD_SLOW_PATH_OFFSET(funcId) \
 	(IRO[105].base + ((funcId) * IRO[105].m1))
 #define TSTORM_TCP_MAX_CWND_OFFSET(pfId) \
-	(IRO[216].base + ((pfId) * IRO[216].m1))
+	(IRO[217].base + ((pfId) * IRO[217].m1))
 #define TSTORM_VF_TO_PF_OFFSET(funcId) \
 	(IRO[104].base + ((funcId) * IRO[104].m1))
 #define USTORM_AGG_DATA_OFFSET (IRO[206].base)
@@ -140,29 +140,29 @@
 #define USTORM_ETH_PAUSE_ENABLED_OFFSET(portId) \
 	(IRO[183].base + ((portId) * IRO[183].m1))
 #define USTORM_FCOE_EQ_PROD_OFFSET(pfId) \
-	(IRO[317].base + ((pfId) * IRO[317].m1))
+	(IRO[318].base + ((pfId) * IRO[318].m1))
 #define USTORM_FUNC_EN_OFFSET(funcId) \
 	(IRO[178].base + ((funcId) * IRO[178].m1))
 #define USTORM_ISCSI_CQ_SIZE_OFFSET(pfId) \
-	(IRO[281].base + ((pfId) * IRO[281].m1))
-#define USTORM_ISCSI_CQ_SQN_SIZE_OFFSET(pfId) \
 	(IRO[282].base + ((pfId) * IRO[282].m1))
+#define USTORM_ISCSI_CQ_SQN_SIZE_OFFSET(pfId) \
+	(IRO[283].base + ((pfId) * IRO[283].m1))
 #define USTORM_ISCSI_ERROR_BITMAP_OFFSET(pfId) \
-	(IRO[286].base + ((pfId) * IRO[286].m1))
+	(IRO[287].base + ((pfId) * IRO[287].m1))
 #define USTORM_ISCSI_GLOBAL_BUF_PHYS_ADDR_OFFSET(pfId) \
-	(IRO[283].base + ((pfId) * IRO[283].m1))
+	(IRO[284].base + ((pfId) * IRO[284].m1))
 #define USTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfId) \
-	(IRO[279].base + ((pfId) * IRO[279].m1))
+	(IRO[280].base + ((pfId) * IRO[280].m1))
 #define USTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfId) \
-	(IRO[278].base + ((pfId) * IRO[278].m1))
+	(IRO[279].base + ((pfId) * IRO[279].m1))
 #define USTORM_ISCSI_PAGE_SIZE_OFFSET(pfId) \
-	(IRO[277].base + ((pfId) * IRO[277].m1))
+	(IRO[278].base + ((pfId) * IRO[278].m1))
 #define USTORM_ISCSI_R2TQ_SIZE_OFFSET(pfId) \
-	(IRO[280].base + ((pfId) * IRO[280].m1))
+	(IRO[281].base + ((pfId) * IRO[281].m1))
 #define USTORM_ISCSI_RQ_BUFFER_SIZE_OFFSET(pfId) \
-	(IRO[284].base + ((pfId) * IRO[284].m1))
-#define USTORM_ISCSI_RQ_SIZE_OFFSET(pfId) \
 	(IRO[285].base + ((pfId) * IRO[285].m1))
+#define USTORM_ISCSI_RQ_SIZE_OFFSET(pfId) \
+	(IRO[286].base + ((pfId) * IRO[286].m1))
 #define USTORM_MEM_WORKAROUND_ADDRESS_OFFSET(pfId) \
 	(IRO[182].base + ((pfId) * IRO[182].m1))
 #define USTORM_RECORD_SLOW_PATH_OFFSET(funcId) \
@@ -188,39 +188,39 @@
 #define XSTORM_FUNC_EN_OFFSET(funcId) \
 	(IRO[47].base + ((funcId) * IRO[47].m1))
 #define XSTORM_ISCSI_HQ_SIZE_OFFSET(pfId) \
-	(IRO[294].base + ((pfId) * IRO[294].m1))
+	(IRO[295].base + ((pfId) * IRO[295].m1))
 #define XSTORM_ISCSI_LOCAL_MAC_ADDR0_OFFSET(pfId) \
-	(IRO[297].base + ((pfId) * IRO[297].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR1_OFFSET(pfId) \
 	(IRO[298].base + ((pfId) * IRO[298].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR2_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR1_OFFSET(pfId) \
 	(IRO[299].base + ((pfId) * IRO[299].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR3_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR2_OFFSET(pfId) \
 	(IRO[300].base + ((pfId) * IRO[300].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR4_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR3_OFFSET(pfId) \
 	(IRO[301].base + ((pfId) * IRO[301].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR5_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR4_OFFSET(pfId) \
 	(IRO[302].base + ((pfId) * IRO[302].m1))
-#define XSTORM_ISCSI_LOCAL_VLAN_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR5_OFFSET(pfId) \
 	(IRO[303].base + ((pfId) * IRO[303].m1))
+#define XSTORM_ISCSI_LOCAL_VLAN_OFFSET(pfId) \
+	(IRO[304].base + ((pfId) * IRO[304].m1))
 #define XSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfId) \
-	(IRO[293].base + ((pfId) * IRO[293].m1))
+	(IRO[294].base + ((pfId) * IRO[294].m1))
 #define XSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfId) \
-	(IRO[292].base + ((pfId) * IRO[292].m1))
+	(IRO[293].base + ((pfId) * IRO[293].m1))
 #define XSTORM_ISCSI_PAGE_SIZE_OFFSET(pfId) \
-	(IRO[291].base + ((pfId) * IRO[291].m1))
+	(IRO[292].base + ((pfId) * IRO[292].m1))
 #define XSTORM_ISCSI_R2TQ_SIZE_OFFSET(pfId) \
-	(IRO[296].base + ((pfId) * IRO[296].m1))
+	(IRO[297].base + ((pfId) * IRO[297].m1))
 #define XSTORM_ISCSI_SQ_SIZE_OFFSET(pfId) \
-	(IRO[295].base + ((pfId) * IRO[295].m1))
+	(IRO[296].base + ((pfId) * IRO[296].m1))
 #define XSTORM_ISCSI_TCP_VARS_ADV_WND_SCL_OFFSET(pfId) \
-	(IRO[290].base + ((pfId) * IRO[290].m1))
+	(IRO[291].base + ((pfId) * IRO[291].m1))
 #define XSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(pfId) \
-	(IRO[289].base + ((pfId) * IRO[289].m1))
+	(IRO[290].base + ((pfId) * IRO[290].m1))
 #define XSTORM_ISCSI_TCP_VARS_TOS_OFFSET(pfId) \
-	(IRO[288].base + ((pfId) * IRO[288].m1))
+	(IRO[289].base + ((pfId) * IRO[289].m1))
 #define XSTORM_ISCSI_TCP_VARS_TTL_OFFSET(pfId) \
-	(IRO[287].base + ((pfId) * IRO[287].m1))
+	(IRO[288].base + ((pfId) * IRO[288].m1))
 #define XSTORM_RATE_SHAPING_PER_VN_VARS_OFFSET(pfId) \
 	(IRO[44].base + ((pfId) * IRO[44].m1))
 #define XSTORM_RECORD_SLOW_PATH_OFFSET(funcId) \
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 71e5bd00e8be..ff882a482094 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -1340,7 +1340,14 @@ static void bnx2x_update_pfc_xmac(struct link_params *params,
 		pfc1_val |= XMAC_PFC_CTRL_HI_REG_PFC_REFRESH_EN |
 			XMAC_PFC_CTRL_HI_REG_PFC_STATS_EN |
 			XMAC_PFC_CTRL_HI_REG_RX_PFC_EN |
-			XMAC_PFC_CTRL_HI_REG_TX_PFC_EN;
+			XMAC_PFC_CTRL_HI_REG_TX_PFC_EN |
+			XMAC_PFC_CTRL_HI_REG_FORCE_PFC_XON;
+		/* Write pause and PFC registers */
+		REG_WR(bp, xmac_base + XMAC_REG_PAUSE_CTRL, pause_val);
+		REG_WR(bp, xmac_base + XMAC_REG_PFC_CTRL, pfc0_val);
+		REG_WR(bp, xmac_base + XMAC_REG_PFC_CTRL_HI, pfc1_val);
+		pfc1_val &= ~XMAC_PFC_CTRL_HI_REG_FORCE_PFC_XON;
+
 	}
 
 	/* Write pause and PFC registers */
@@ -3574,6 +3581,33 @@ static void bnx2x_ext_phy_update_adv_fc(struct bnx2x_phy *phy,
 	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE) {
 		bnx2x_cl22_read(bp, phy, 0x4, &ld_pause);
 		bnx2x_cl22_read(bp, phy, 0x5, &lp_pause);
+	} else if (CHIP_IS_E3(bp) &&
+		SINGLE_MEDIA_DIRECT(params)) {
+		u8 lane = bnx2x_get_warpcore_lane(phy, params);
+		u16 gp_status, gp_mask;
+		bnx2x_cl45_read(bp, phy,
+				MDIO_AN_DEVAD, MDIO_WC_REG_GP2_STATUS_GP_2_4,
+				&gp_status);
+		gp_mask = (MDIO_WC_REG_GP2_STATUS_GP_2_4_CL73_AN_CMPL |
+			   MDIO_WC_REG_GP2_STATUS_GP_2_4_CL37_LP_AN_CAP) <<
+			lane;
+		if ((gp_status & gp_mask) == gp_mask) {
+			bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+					MDIO_AN_REG_ADV_PAUSE, &ld_pause);
+			bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+					MDIO_AN_REG_LP_AUTO_NEG, &lp_pause);
+		} else {
+			bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+					MDIO_AN_REG_CL37_FC_LD, &ld_pause);
+			bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+					MDIO_AN_REG_CL37_FC_LP, &lp_pause);
+			ld_pause = ((ld_pause &
+				     MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_BOTH)
+				    << 3);
+			lp_pause = ((lp_pause &
+				     MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_BOTH)
+				    << 3);
+		}
 	} else {
 		bnx2x_cl45_read(bp, phy,
 				MDIO_AN_DEVAD,
@@ -3625,7 +3659,23 @@ static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
 	u16 val16 = 0, lane, bam37 = 0;
 	struct bnx2x *bp = params->bp;
 	DP(NETIF_MSG_LINK, "Enable Auto Negotiation for KR\n");
-
+	/* Set to default registers that may be overriden by 10G force */
+	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+			 MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X2, 0x7);
+	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+			 MDIO_WC_REG_PAR_DET_10G_CTRL, 0);
+	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+			 MDIO_WC_REG_CL72_USERB0_CL72_MISC1_CONTROL, 0);
+	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+			MDIO_WC_REG_XGXSBLK1_LANECTRL0, 0xff);
+	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+			MDIO_WC_REG_XGXSBLK1_LANECTRL1, 0x5555);
+	bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD,
+			 MDIO_WC_REG_IEEE0BLK_AUTONEGNP, 0x0);
+	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+			 MDIO_WC_REG_RX66_CONTROL, 0x7415);
+	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+			 MDIO_WC_REG_SERDESDIGITAL_MISC2, 0x6190);
 	/* Disable Autoneg: re-enable it after adv is done. */
 	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
 			 MDIO_WC_REG_IEEE0BLK_MIICNTL, 0);
@@ -3868,13 +3918,13 @@ static void bnx2x_warpcore_set_10G_XFI(struct bnx2x_phy *phy,
 
 	} else {
 		misc1_val |= 0x9;
-		tap_val = ((0x12 << MDIO_WC_REG_TX_FIR_TAP_POST_TAP_OFFSET) |
-			   (0x2d << MDIO_WC_REG_TX_FIR_TAP_MAIN_TAP_OFFSET) |
-			   (0x00 << MDIO_WC_REG_TX_FIR_TAP_PRE_TAP_OFFSET));
+		tap_val = ((0x0f << MDIO_WC_REG_TX_FIR_TAP_POST_TAP_OFFSET) |
+			   (0x2b << MDIO_WC_REG_TX_FIR_TAP_MAIN_TAP_OFFSET) |
+			   (0x02 << MDIO_WC_REG_TX_FIR_TAP_PRE_TAP_OFFSET));
 		tx_driver_val =
-		      ((0x02 << MDIO_WC_REG_TX0_TX_DRIVER_POST2_COEFF_OFFSET) |
+		      ((0x03 << MDIO_WC_REG_TX0_TX_DRIVER_POST2_COEFF_OFFSET) |
 		       (0x02 << MDIO_WC_REG_TX0_TX_DRIVER_IDRIVER_OFFSET) |
-		       (0x02 << MDIO_WC_REG_TX0_TX_DRIVER_IPRE_DRIVER_OFFSET));
+		       (0x06 << MDIO_WC_REG_TX0_TX_DRIVER_IPRE_DRIVER_OFFSET));
 	}
 	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
 			 MDIO_WC_REG_SERDESDIGITAL_MISC1, misc1_val);
@@ -4290,7 +4340,7 @@ static void bnx2x_warpcore_config_init(struct bnx2x_phy *phy,
 		switch (serdes_net_if) {
 		case PORT_HW_CFG_NET_SERDES_IF_KR:
 			/* Enable KR Auto Neg */
-			if (params->loopback_mode == LOOPBACK_NONE)
+			if (params->loopback_mode != LOOPBACK_EXT)
 				bnx2x_warpcore_enable_AN_KR(phy, params, vars);
 			else {
 				DP(NETIF_MSG_LINK, "Setting KR 10G-Force\n");
@@ -6076,12 +6126,14 @@ int bnx2x_set_led(struct link_params *params,
 
 		tmp = EMAC_RD(bp, EMAC_REG_EMAC_LED);
 		if (params->phy[EXT_PHY1].type ==
-			  PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE)
-			EMAC_WR(bp, EMAC_REG_EMAC_LED, tmp & 0xfff1);
-		else {
-			EMAC_WR(bp, EMAC_REG_EMAC_LED,
-				(tmp | EMAC_LED_OVERRIDE));
-		}
+			PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE)
+			tmp &= ~(EMAC_LED_1000MB_OVERRIDE |
+				EMAC_LED_100MB_OVERRIDE |
+				EMAC_LED_10MB_OVERRIDE);
+		else
+			tmp |= EMAC_LED_OVERRIDE;
+
+		EMAC_WR(bp, EMAC_REG_EMAC_LED, tmp);
 		break;
 
 	case LED_MODE_OPER:
@@ -6131,10 +6183,15 @@ int bnx2x_set_led(struct link_params *params,
 				       hw_led_mode);
 		} else if ((params->phy[EXT_PHY1].type ==
 			    PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE) &&
-			   (mode != LED_MODE_OPER)) {
+			   (mode == LED_MODE_ON)) {
 			REG_WR(bp, NIG_REG_LED_MODE_P0 + port*4, 0);
 			tmp = EMAC_RD(bp, EMAC_REG_EMAC_LED);
-			EMAC_WR(bp, EMAC_REG_EMAC_LED, tmp | 0x3);
+			EMAC_WR(bp, EMAC_REG_EMAC_LED, tmp |
+				EMAC_LED_OVERRIDE | EMAC_LED_1000MB_OVERRIDE);
+			/* Break here; otherwise, it'll disable the
+			 * intended override.
+			 */
+			break;
 		} else
 			REG_WR(bp, NIG_REG_LED_MODE_P0 + port*4,
 			       hw_led_mode);
@@ -6149,13 +6206,9 @@ int bnx2x_set_led(struct link_params *params,
 			       LED_BLINK_RATE_VAL_E1X_E2);
 		REG_WR(bp, NIG_REG_LED_CONTROL_BLINK_RATE_ENA_P0 +
 		       port*4, 1);
-		if ((params->phy[EXT_PHY1].type !=
-		     PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE) &&
-		    (mode != LED_MODE_OPER)) {
-			tmp = EMAC_RD(bp, EMAC_REG_EMAC_LED);
-			EMAC_WR(bp, EMAC_REG_EMAC_LED,
-				(tmp & (~EMAC_LED_OVERRIDE)));
-		}
+		tmp = EMAC_RD(bp, EMAC_REG_EMAC_LED);
+		EMAC_WR(bp, EMAC_REG_EMAC_LED,
+			(tmp & (~EMAC_LED_OVERRIDE)));
 
 		if (CHIP_IS_E1(bp) &&
 		    ((speed == SPEED_2500) ||
@@ -6736,6 +6789,12 @@ int bnx2x_link_update(struct link_params *params, struct link_vars *vars)
 			  SINGLE_MEDIA_DIRECT(params)) &&
 			 (phy_vars[active_external_phy].fault_detected == 0));
 
+	/* Update the PFC configuration in case it was changed */
+	if (params->feature_config_flags & FEATURE_CONFIG_PFC_ENABLED)
+		vars->link_status |= LINK_STATUS_PFC_ENABLED;
+	else
+		vars->link_status &= ~LINK_STATUS_PFC_ENABLED;
+
 	if (vars->link_up)
 		rc = bnx2x_update_link_up(params, vars, link_10g_plus);
 	else
@@ -7909,7 +7968,9 @@ static int bnx2x_verify_sfp_module(struct bnx2x_phy *phy,
 	netdev_err(bp->dev,  "Warning: Unqualified SFP+ module detected,"
 			      " Port %d from %s part number %s\n",
 			 params->port, vendor_name, vendor_pn);
-	phy->flags |= FLAGS_SFP_NOT_APPROVED;
+	if ((val & PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_MASK) !=
+	    PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_WARNING_MSG)
+		phy->flags |= FLAGS_SFP_NOT_APPROVED;
 	return -EINVAL;
 }
 
@@ -8948,6 +9009,12 @@ static int bnx2x_8727_config_init(struct bnx2x_phy *phy,
 		tmp2 &= 0xFFEF;
 		bnx2x_cl45_write(bp, phy,
 			MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_OPT_CFG_REG, tmp2);
+		bnx2x_cl45_read(bp, phy,
+				MDIO_PMA_DEVAD, MDIO_PMA_REG_PHY_IDENTIFIER,
+				&tmp2);
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD, MDIO_PMA_REG_PHY_IDENTIFIER,
+				 (tmp2 & 0x7fff));
 	}
 
 	return 0;
@@ -9123,12 +9190,11 @@ static u8 bnx2x_8727_read_status(struct bnx2x_phy *phy,
 				 MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL,
 				 ((1<<5) | (1<<2)));
 	}
-	DP(NETIF_MSG_LINK, "Enabling 8727 TX laser if SFP is approved\n");
-	bnx2x_8727_specific_func(phy, params, ENABLE_TX);
-	/* If transmitter is disabled, ignore false link up indication */
-	bnx2x_cl45_read(bp, phy,
-			MDIO_PMA_DEVAD, MDIO_PMA_REG_PHY_IDENTIFIER, &val1);
-	if (val1 & (1<<15)) {
+
+	if (!(phy->flags & FLAGS_SFP_NOT_APPROVED)) {
+		DP(NETIF_MSG_LINK, "Enabling 8727 TX laser\n");
+		bnx2x_sfp_set_transmitter(params, phy, 1);
+	} else {
 		DP(NETIF_MSG_LINK, "Tx is disabled\n");
 		return 0;
 	}
@@ -9220,8 +9286,7 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy,
 
 	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) {
 		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, 0x400f, &fw_ver1);
-		bnx2x_save_spirom_version(bp, port,
-				((fw_ver1 & 0xf000)>>5) | (fw_ver1 & 0x7f),
+		bnx2x_save_spirom_version(bp, port, fw_ver1 & 0xfff,
 				phy->ver_addr);
 	} else {
 		/* For 32-bit registers in 848xx, access via MDIO2ARM i/f. */
@@ -9642,6 +9707,15 @@ static int bnx2x_84833_hw_reset_phy(struct bnx2x_phy *phy,
 				other_shmem_base_addr));
 
 	u32 shmem_base_path[2];
+
+	/* Work around for 84833 LED failure inside RESET status */
+	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+		MDIO_AN_REG_8481_LEGACY_MII_CTRL,
+		MDIO_AN_REG_8481_MII_CTRL_FORCE_1G);
+	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+		MDIO_AN_REG_8481_1G_100T_EXT_CTRL,
+		MIDO_AN_REG_8481_EXT_CTRL_FORCE_LEDS_OFF);
+
 	shmem_base_path[0] = params->shmem_base;
 	shmem_base_path[1] = other_shmem_base_addr;
 
@@ -9951,7 +10025,7 @@ static void bnx2x_848x3_link_reset(struct bnx2x_phy *phy,
 	u8 port;
 	u16 val16;
 
-	if (!(CHIP_IS_E1(bp)))
+	if (!(CHIP_IS_E1x(bp)))
 		port = BP_PATH(bp);
 	else
 		port = params->port;
@@ -9978,7 +10052,7 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 	u16 val;
 	u8 port;
 
-	if (!(CHIP_IS_E1(bp)))
+	if (!(CHIP_IS_E1x(bp)))
 		port = BP_PATH(bp);
 	else
 		port = params->port;
@@ -11893,6 +11967,9 @@ int bnx2x_phy_init(struct link_params *params, struct link_vars *vars)
 
 	bnx2x_emac_init(params, vars);
 
+	if (params->feature_config_flags & FEATURE_CONFIG_PFC_ENABLED)
+		vars->link_status |= LINK_STATUS_PFC_ENABLED;
+
 	if (params->num_phys == 0) {
 		DP(NETIF_MSG_LINK, "No phy found for initialization !!\n");
 		return -EINVAL;
@@ -11973,10 +12050,10 @@ int bnx2x_link_reset(struct link_params *params, struct link_vars *vars,
 	 * Hold it as vars low
 	 */
 	 /* clear link led */
+	bnx2x_set_mdio_clk(bp, params->chip_id, port);
 	bnx2x_set_led(params, vars, LED_MODE_OFF, 0);
 
 	if (reset_ext_phy) {
-		bnx2x_set_mdio_clk(bp, params->chip_id, port);
 		for (phy_index = EXT_PHY1; phy_index < params->num_phys;
 		      phy_index++) {
 			if (params->phy[phy_index].link_reset) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 4532172c9fd6..bbd387492a80 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -5359,6 +5359,7 @@
 #define XMAC_CTRL_REG_TX_EN					 (0x1<<0)
 #define XMAC_PAUSE_CTRL_REG_RX_PAUSE_EN				 (0x1<<18)
 #define XMAC_PAUSE_CTRL_REG_TX_PAUSE_EN				 (0x1<<17)
+#define XMAC_PFC_CTRL_HI_REG_FORCE_PFC_XON			 (0x1<<1)
 #define XMAC_PFC_CTRL_HI_REG_PFC_REFRESH_EN			 (0x1<<0)
 #define XMAC_PFC_CTRL_HI_REG_PFC_STATS_EN			 (0x1<<3)
 #define XMAC_PFC_CTRL_HI_REG_RX_PFC_EN				 (0x1<<4)
@@ -6825,10 +6826,13 @@ Theotherbitsarereservedandshouldbezero*/
 
 #define MDIO_AN_REG_8481_10GBASE_T_AN_CTRL	0x0020
 #define MDIO_AN_REG_8481_LEGACY_MII_CTRL	0xffe0
+#define MDIO_AN_REG_8481_MII_CTRL_FORCE_1G	0x40
 #define MDIO_AN_REG_8481_LEGACY_MII_STATUS	0xffe1
 #define MDIO_AN_REG_8481_LEGACY_AN_ADV		0xffe4
 #define MDIO_AN_REG_8481_LEGACY_AN_EXPANSION	0xffe6
 #define MDIO_AN_REG_8481_1000T_CTRL		0xffe9
+#define MDIO_AN_REG_8481_1G_100T_EXT_CTRL	0xfff0
+#define MIDO_AN_REG_8481_EXT_CTRL_FORCE_LEDS_OFF	0x0008
 #define MDIO_AN_REG_8481_EXPANSION_REG_RD_RW	0xfff5
 #define MDIO_AN_REG_8481_EXPANSION_REG_ACCESS	0xfff7
 #define MDIO_AN_REG_8481_AUX_CTRL		0xfff8
@@ -6948,6 +6952,10 @@ Theotherbitsarereservedandshouldbezero*/
 #define MDIO_WC_REG_GP2_STATUS_GP_2_2			0x81d2
 #define MDIO_WC_REG_GP2_STATUS_GP_2_3			0x81d3
 #define MDIO_WC_REG_GP2_STATUS_GP_2_4			0x81d4
+#define MDIO_WC_REG_GP2_STATUS_GP_2_4_CL73_AN_CMPL 0x1000
+#define MDIO_WC_REG_GP2_STATUS_GP_2_4_CL37_AN_CMPL 0x0100
+#define MDIO_WC_REG_GP2_STATUS_GP_2_4_CL37_LP_AN_CAP 0x0010
+#define MDIO_WC_REG_GP2_STATUS_GP_2_4_CL37_AN_CAP 0x1
 #define MDIO_WC_REG_UC_INFO_B0_DEAD_TRAP		0x81EE
 #define MDIO_WC_REG_UC_INFO_B1_VERSION			0x81F0
 #define MDIO_WC_REG_UC_INFO_B1_FIRMWARE_MODE		0x81F2
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 86097981e1e1..0c3e7c70ffbc 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -48,7 +48,6 @@
 #include <net/checksum.h>
 #include <net/ip.h>
 
-#include <asm/system.h>
 #include <linux/io.h>
 #include <asm/byteorder.h>
 #include <linux/uaccess.h>
@@ -2779,7 +2778,9 @@ static void tg3_power_down_phy(struct tg3 *tp, bool do_low_power)
 	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5700 ||
 	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5704 ||
 	    (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5780 &&
-	     (tp->phy_flags & TG3_PHYFLG_MII_SERDES)))
+	     (tp->phy_flags & TG3_PHYFLG_MII_SERDES)) ||
+	    (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 &&
+	     !tp->pci_fn))
 		return;
 
 	if (GET_CHIP_REV(tp->pci_chip_rev_id) == CHIPREV_5784_AX ||
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 05ff076af06d..b126b98065a9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2000,13 +2000,6 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 /*
  * debugfs support
  */
-
-static int mem_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t mem_read(struct file *file, char __user *buf, size_t count,
 			loff_t *ppos)
 {
@@ -2050,7 +2043,7 @@ static ssize_t mem_read(struct file *file, char __user *buf, size_t count,
 
 static const struct file_operations mem_debugfs_fops = {
 	.owner   = THIS_MODULE,
-	.open    = mem_open,
+	.open    = simple_open,
 	.read    = mem_read,
 	.llseek  = default_llseek,
 };
diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 30fee428c489..b9406cbfc180 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -148,7 +148,6 @@
 #include <linux/delay.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <linux/atomic.h>
diff --git a/drivers/net/ethernet/cirrus/mac89x0.c b/drivers/net/ethernet/cirrus/mac89x0.c
index 932fdccc339a..e285f384b096 100644
--- a/drivers/net/ethernet/cirrus/mac89x0.c
+++ b/drivers/net/ethernet/cirrus/mac89x0.c
@@ -99,7 +99,6 @@ static char *version =
 #include <linux/bitops.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/hwtest.h>
 #include <asm/macints.h>
diff --git a/drivers/net/ethernet/dlink/de600.c b/drivers/net/ethernet/dlink/de600.c
index 682750c052c8..414f0eea1049 100644
--- a/drivers/net/ethernet/dlink/de600.c
+++ b/drivers/net/ethernet/dlink/de600.c
@@ -46,7 +46,6 @@ static const char version[] = "de600.c: $Revision: 1.41-2.5 $,  Bjorn Ekwall (bj
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/in.h>
-#include <asm/system.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/dlink/de620.c b/drivers/net/ethernet/dlink/de620.c
index afc5aaac6b60..2e2bc60ee811 100644
--- a/drivers/net/ethernet/dlink/de620.c
+++ b/drivers/net/ethernet/dlink/de620.c
@@ -122,7 +122,6 @@ static const char version[] =
 #include <linux/skbuff.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 /* Constant definitions for the DE-620 registers, commands and bits */
 #include "de620.h"
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 4e3cd2f8debb..17a46e76123f 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3945,6 +3945,8 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 		}
 
 	if (max_speed == SPEED_1000) {
+		unsigned int snums = qe_get_num_of_snums();
+
 		/* configure muram FIFOs for gigabit operation */
 		ug_info->uf_info.urfs = UCC_GETH_URFS_GIGA_INIT;
 		ug_info->uf_info.urfet = UCC_GETH_URFET_GIGA_INIT;
@@ -3954,11 +3956,11 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 		ug_info->uf_info.utftt = UCC_GETH_UTFTT_GIGA_INIT;
 		ug_info->numThreadsTx = UCC_GETH_NUM_OF_THREADS_4;
 
-		/* If QE's snum number is 46 which means we need to support
+		/* If QE's snum number is 46/76 which means we need to support
 		 * 4 UECs at 1000Base-T simultaneously, we need to allocate
 		 * more Threads to Rx.
 		 */
-		if (qe_get_num_of_snums() == 46)
+		if ((snums == 76) || (snums == 46))
 			ug_info->numThreadsRx = UCC_GETH_NUM_OF_THREADS_6;
 		else
 			ug_info->numThreadsRx = UCC_GETH_NUM_OF_THREADS_4;
diff --git a/drivers/net/ethernet/fujitsu/at1700.c b/drivers/net/ethernet/fujitsu/at1700.c
index 586b46fd4eed..3d94797c8f9b 100644
--- a/drivers/net/ethernet/fujitsu/at1700.c
+++ b/drivers/net/ethernet/fujitsu/at1700.c
@@ -52,7 +52,6 @@
 #include <linux/crc32.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/fujitsu/eth16i.c b/drivers/net/ethernet/fujitsu/eth16i.c
index c3f0178fb5cb..a992d1f7e0d2 100644
--- a/drivers/net/ethernet/fujitsu/eth16i.c
+++ b/drivers/net/ethernet/fujitsu/eth16i.c
@@ -163,7 +163,6 @@ static char *version =
 #include <linux/jiffies.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/dma.h>
 
 
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index 0230319ddb59..2418faf2251a 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -57,7 +57,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 /*====================================================================*/
 
diff --git a/drivers/net/ethernet/i825xx/3c507.c b/drivers/net/ethernet/i825xx/3c507.c
index ed6925f11479..e8984b059905 100644
--- a/drivers/net/ethernet/i825xx/3c507.c
+++ b/drivers/net/ethernet/i825xx/3c507.c
@@ -63,7 +63,6 @@ static const char version[] =
 
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 /* use 0 for production, 1 for verification, 2..7 for debug */
diff --git a/drivers/net/ethernet/i825xx/3c527.c b/drivers/net/ethernet/i825xx/3c527.c
index ef43f3e951c5..278e791afe00 100644
--- a/drivers/net/ethernet/i825xx/3c527.c
+++ b/drivers/net/ethernet/i825xx/3c527.c
@@ -106,7 +106,6 @@ DRV_NAME ".c:v" DRV_VERSION " " DRV_RELDATE " Richard Procter <rnp@paradise.net.
 #include <linux/semaphore.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/i825xx/eepro.c b/drivers/net/ethernet/i825xx/eepro.c
index 7a4ad4a07917..7f49fd54c521 100644
--- a/drivers/net/ethernet/i825xx/eepro.c
+++ b/drivers/net/ethernet/i825xx/eepro.c
@@ -148,7 +148,6 @@ static const char version[] =
 #include <linux/bitops.h>
 #include <linux/ethtool.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/i825xx/eexpress.c b/drivers/net/ethernet/i825xx/eexpress.c
index 3fc649e54a32..cc2e66ad4436 100644
--- a/drivers/net/ethernet/i825xx/eexpress.c
+++ b/drivers/net/ethernet/i825xx/eexpress.c
@@ -116,7 +116,6 @@
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/ethernet/i825xx/ether1.c b/drivers/net/ethernet/i825xx/ether1.c
index 406a12b46404..067db3f13e91 100644
--- a/drivers/net/ethernet/i825xx/ether1.c
+++ b/drivers/net/ethernet/i825xx/ether1.c
@@ -48,7 +48,6 @@
 #include <linux/skbuff.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/ecard.h>
diff --git a/drivers/net/ethernet/i825xx/znet.c b/drivers/net/ethernet/i825xx/znet.c
index a43649735a04..bd1f1ef91e19 100644
--- a/drivers/net/ethernet/i825xx/znet.c
+++ b/drivers/net/ethernet/i825xx/znet.c
@@ -100,7 +100,6 @@
 #include <linux/if_arp.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index e877371680a9..9010cea68bc3 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1616,11 +1616,8 @@ static struct vio_driver ibmveth_driver = {
 	.probe		= ibmveth_probe,
 	.remove		= ibmveth_remove,
 	.get_desired_dma = ibmveth_get_desired_dma,
-	.driver		= {
-		.name	= ibmveth_driver_name,
-		.owner	= THIS_MODULE,
-		.pm = &ibmveth_pm_ops,
-	}
+	.name		= ibmveth_driver_name,
+	.pm		= &ibmveth_pm_ops,
 };
 
 static int __init ibmveth_module_init(void)
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 86cdd4793992..b83897f76ee3 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -161,6 +161,12 @@ struct e1000_info;
 /* Time to wait before putting the device into D3 if there's no link (in ms). */
 #define LINK_TIMEOUT		100
 
+/*
+ * Count for polling __E1000_RESET condition every 10-20msec.
+ * Experimentation has shown the reset can take approximately 210msec.
+ */
+#define E1000_CHECK_RESET_COUNT		25
+
 #define DEFAULT_RDTR			0
 #define DEFAULT_RADV			8
 #define BURST_RDTR			0x20
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index f88dac614dec..851f7937db29 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1060,6 +1060,13 @@ static void e1000_print_hw_hang(struct work_struct *work)
 		ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
 		/* execute the writes immediately */
 		e1e_flush();
+		/*
+		 * Due to rare timing issues, write to TIDV again to ensure
+		 * the write is successful
+		 */
+		ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
+		/* execute the writes immediately */
+		e1e_flush();
 		adapter->tx_hang_recheck = true;
 		return;
 	}
@@ -3615,6 +3622,16 @@ static void e1000e_flush_descriptors(struct e1000_adapter *adapter)
 
 	/* execute the writes immediately */
 	e1e_flush();
+
+	/*
+	 * due to rare timing issues, write to TIDV/RDTR again to ensure the
+	 * write is successful
+	 */
+	ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
+	ew32(RDTR, adapter->rx_int_delay | E1000_RDTR_FPD);
+
+	/* execute the writes immediately */
+	e1e_flush();
 }
 
 static void e1000e_update_stats(struct e1000_adapter *adapter);
@@ -3967,6 +3984,10 @@ static int e1000_close(struct net_device *netdev)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = adapter->pdev;
+	int count = E1000_CHECK_RESET_COUNT;
+
+	while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
+		usleep_range(10000, 20000);
 
 	WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
 
@@ -5471,6 +5492,11 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	netif_device_detach(netdev);
 
 	if (netif_running(netdev)) {
+		int count = E1000_CHECK_RESET_COUNT;
+
+		while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
+			usleep_range(10000, 20000);
+
 		WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
 		e1000e_down(adapter);
 		e1000_free_irq(adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index dde65f951400..652e4b09546d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -44,62 +44,94 @@
 #define DCB_NO_HW_CHG   1  /* DCB configuration did not change */
 #define DCB_HW_CHG      2  /* DCB configuration changed, no reset */
 
-int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *src_dcb_cfg,
-                       struct ixgbe_dcb_config *dst_dcb_cfg, int tc_max)
+int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *scfg,
+		       struct ixgbe_dcb_config *dcfg, int tc_max)
 {
-	struct tc_configuration *src_tc_cfg = NULL;
-	struct tc_configuration *dst_tc_cfg = NULL;
-	int i;
+	struct tc_configuration *src = NULL;
+	struct tc_configuration *dst = NULL;
+	int i, j;
+	int tx = DCB_TX_CONFIG;
+	int rx = DCB_RX_CONFIG;
+	int changes = 0;
 
-	if (!src_dcb_cfg || !dst_dcb_cfg)
-		return -EINVAL;
+	if (!scfg || !dcfg)
+		return changes;
 
 	for (i = DCB_PG_ATTR_TC_0; i < tc_max + DCB_PG_ATTR_TC_0; i++) {
-		src_tc_cfg = &src_dcb_cfg->tc_config[i - DCB_PG_ATTR_TC_0];
-		dst_tc_cfg = &dst_dcb_cfg->tc_config[i - DCB_PG_ATTR_TC_0];
+		src = &scfg->tc_config[i - DCB_PG_ATTR_TC_0];
+		dst = &dcfg->tc_config[i - DCB_PG_ATTR_TC_0];
 
-		dst_tc_cfg->path[DCB_TX_CONFIG].prio_type =
-				src_tc_cfg->path[DCB_TX_CONFIG].prio_type;
+		if (dst->path[tx].prio_type != src->path[tx].prio_type) {
+			dst->path[tx].prio_type = src->path[tx].prio_type;
+			changes |= BIT_PG_TX;
+		}
 
-		dst_tc_cfg->path[DCB_TX_CONFIG].bwg_id =
-				src_tc_cfg->path[DCB_TX_CONFIG].bwg_id;
+		if (dst->path[tx].bwg_id != src->path[tx].bwg_id) {
+			dst->path[tx].bwg_id = src->path[tx].bwg_id;
+			changes |= BIT_PG_TX;
+		}
 
-		dst_tc_cfg->path[DCB_TX_CONFIG].bwg_percent =
-				src_tc_cfg->path[DCB_TX_CONFIG].bwg_percent;
+		if (dst->path[tx].bwg_percent != src->path[tx].bwg_percent) {
+			dst->path[tx].bwg_percent = src->path[tx].bwg_percent;
+			changes |= BIT_PG_TX;
+		}
 
-		dst_tc_cfg->path[DCB_TX_CONFIG].up_to_tc_bitmap =
-				src_tc_cfg->path[DCB_TX_CONFIG].up_to_tc_bitmap;
+		if (dst->path[tx].up_to_tc_bitmap !=
+				src->path[tx].up_to_tc_bitmap) {
+			dst->path[tx].up_to_tc_bitmap =
+				src->path[tx].up_to_tc_bitmap;
+			changes |= (BIT_PG_TX | BIT_PFC | BIT_APP_UPCHG);
+		}
 
-		dst_tc_cfg->path[DCB_RX_CONFIG].prio_type =
-				src_tc_cfg->path[DCB_RX_CONFIG].prio_type;
+		if (dst->path[rx].prio_type != src->path[rx].prio_type) {
+			dst->path[rx].prio_type = src->path[rx].prio_type;
+			changes |= BIT_PG_RX;
+		}
 
-		dst_tc_cfg->path[DCB_RX_CONFIG].bwg_id =
-				src_tc_cfg->path[DCB_RX_CONFIG].bwg_id;
+		if (dst->path[rx].bwg_id != src->path[rx].bwg_id) {
+			dst->path[rx].bwg_id = src->path[rx].bwg_id;
+			changes |= BIT_PG_RX;
+		}
 
-		dst_tc_cfg->path[DCB_RX_CONFIG].bwg_percent =
-				src_tc_cfg->path[DCB_RX_CONFIG].bwg_percent;
+		if (dst->path[rx].bwg_percent != src->path[rx].bwg_percent) {
+			dst->path[rx].bwg_percent = src->path[rx].bwg_percent;
+			changes |= BIT_PG_RX;
+		}
 
-		dst_tc_cfg->path[DCB_RX_CONFIG].up_to_tc_bitmap =
-				src_tc_cfg->path[DCB_RX_CONFIG].up_to_tc_bitmap;
+		if (dst->path[rx].up_to_tc_bitmap !=
+				src->path[rx].up_to_tc_bitmap) {
+			dst->path[rx].up_to_tc_bitmap =
+				src->path[rx].up_to_tc_bitmap;
+			changes |= (BIT_PG_RX | BIT_PFC | BIT_APP_UPCHG);
+		}
 	}
 
 	for (i = DCB_PG_ATTR_BW_ID_0; i < DCB_PG_ATTR_BW_ID_MAX; i++) {
-		dst_dcb_cfg->bw_percentage[DCB_TX_CONFIG]
-			[i-DCB_PG_ATTR_BW_ID_0] = src_dcb_cfg->bw_percentage
-				[DCB_TX_CONFIG][i-DCB_PG_ATTR_BW_ID_0];
-		dst_dcb_cfg->bw_percentage[DCB_RX_CONFIG]
-			[i-DCB_PG_ATTR_BW_ID_0] = src_dcb_cfg->bw_percentage
-				[DCB_RX_CONFIG][i-DCB_PG_ATTR_BW_ID_0];
+		j = i - DCB_PG_ATTR_BW_ID_0;
+		if (dcfg->bw_percentage[tx][j] != scfg->bw_percentage[tx][j]) {
+			dcfg->bw_percentage[tx][j] = scfg->bw_percentage[tx][j];
+			changes |= BIT_PG_TX;
+		}
+		if (dcfg->bw_percentage[rx][j] != scfg->bw_percentage[rx][j]) {
+			dcfg->bw_percentage[rx][j] = scfg->bw_percentage[rx][j];
+			changes |= BIT_PG_RX;
+		}
 	}
 
 	for (i = DCB_PFC_UP_ATTR_0; i < DCB_PFC_UP_ATTR_MAX; i++) {
-		dst_dcb_cfg->tc_config[i - DCB_PFC_UP_ATTR_0].dcb_pfc =
-			src_dcb_cfg->tc_config[i - DCB_PFC_UP_ATTR_0].dcb_pfc;
+		j = i - DCB_PFC_UP_ATTR_0;
+		if (dcfg->tc_config[j].dcb_pfc != scfg->tc_config[j].dcb_pfc) {
+			dcfg->tc_config[j].dcb_pfc = scfg->tc_config[j].dcb_pfc;
+			changes |= BIT_PFC;
+		}
 	}
 
-	dst_dcb_cfg->pfc_mode_enable = src_dcb_cfg->pfc_mode_enable;
+	if (dcfg->pfc_mode_enable != scfg->pfc_mode_enable) {
+		dcfg->pfc_mode_enable = scfg->pfc_mode_enable;
+		changes |= BIT_PFC;
+	}
 
-	return 0;
+	return changes;
 }
 
 static u8 ixgbe_dcbnl_get_state(struct net_device *netdev)
@@ -179,20 +211,6 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 	if (up_map != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap =
 			up_map;
-
-	if ((adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type !=
-	     adapter->dcb_cfg.tc_config[tc].path[0].prio_type) ||
-	    (adapter->temp_dcb_cfg.tc_config[tc].path[0].bwg_id !=
-	     adapter->dcb_cfg.tc_config[tc].path[0].bwg_id) ||
-	    (adapter->temp_dcb_cfg.tc_config[tc].path[0].bwg_percent !=
-	     adapter->dcb_cfg.tc_config[tc].path[0].bwg_percent) ||
-	    (adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap !=
-	     adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap))
-		adapter->dcb_set_bitmap |= BIT_PG_TX;
-
-	if (adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap !=
-	     adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap)
-		adapter->dcb_set_bitmap |= BIT_PFC | BIT_APP_UPCHG;
 }
 
 static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
@@ -201,10 +219,6 @@ static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
 	adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] = bw_pct;
-
-	if (adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] !=
-	    adapter->dcb_cfg.bw_percentage[0][bwg_id])
-		adapter->dcb_set_bitmap |= BIT_PG_TX;
 }
 
 static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
@@ -223,20 +237,6 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 	if (up_map != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap =
 			up_map;
-
-	if ((adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type !=
-	     adapter->dcb_cfg.tc_config[tc].path[1].prio_type) ||
-	    (adapter->temp_dcb_cfg.tc_config[tc].path[1].bwg_id !=
-	     adapter->dcb_cfg.tc_config[tc].path[1].bwg_id) ||
-	    (adapter->temp_dcb_cfg.tc_config[tc].path[1].bwg_percent !=
-	     adapter->dcb_cfg.tc_config[tc].path[1].bwg_percent) ||
-	    (adapter->temp_dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap !=
-	     adapter->dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap))
-		adapter->dcb_set_bitmap |= BIT_PG_RX;
-
-	if (adapter->temp_dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap !=
-	     adapter->dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap)
-		adapter->dcb_set_bitmap |= BIT_PFC;
 }
 
 static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
@@ -245,10 +245,6 @@ static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
 	adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] = bw_pct;
-
-	if (adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] !=
-	    adapter->dcb_cfg.bw_percentage[1][bwg_id])
-		adapter->dcb_set_bitmap |= BIT_PG_RX;
 }
 
 static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
@@ -298,10 +294,8 @@ static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 
 	adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc = setting;
 	if (adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc !=
-	    adapter->dcb_cfg.tc_config[priority].dcb_pfc) {
-		adapter->dcb_set_bitmap |= BIT_PFC;
+	    adapter->dcb_cfg.tc_config[priority].dcb_pfc)
 		adapter->temp_dcb_cfg.pfc_mode_enable = true;
-	}
 }
 
 static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
@@ -336,7 +330,8 @@ static void ixgbe_dcbnl_devreset(struct net_device *dev)
 static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	int ret, i;
+	int ret = DCB_NO_HW_CHG;
+	int i;
 #ifdef IXGBE_FCOE
 	struct dcb_app app = {
 			      .selector = DCB_APP_IDTYPE_ETHTYPE,
@@ -355,12 +350,13 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 
 	/* Fail command if not in CEE mode */
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
-		return 1;
+		return ret;
 
-	ret = ixgbe_copy_dcb_cfg(&adapter->temp_dcb_cfg, &adapter->dcb_cfg,
-				 MAX_TRAFFIC_CLASS);
-	if (ret)
-		return DCB_NO_HW_CHG;
+	adapter->dcb_set_bitmap |= ixgbe_copy_dcb_cfg(&adapter->temp_dcb_cfg,
+						      &adapter->dcb_cfg,
+						      MAX_TRAFFIC_CLASS);
+	if (!adapter->dcb_set_bitmap)
+		return ret;
 
 	if (adapter->dcb_cfg.pfc_mode_enable) {
 		switch (adapter->hw.mac.type) {
@@ -420,6 +416,8 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 
 		for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
 			netdev_set_prio_tc_map(netdev, i, prio_tc[i]);
+
+		ret = DCB_HW_CHG_RST;
 	}
 
 	if (adapter->dcb_set_bitmap & BIT_PFC) {
@@ -430,7 +428,8 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 				     DCB_TX_CONFIG, prio_tc);
 		ixgbe_dcb_unpack_pfc(&adapter->dcb_cfg, &pfc_en);
 		ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc_en, prio_tc);
-		ret = DCB_HW_CHG;
+		if (ret != DCB_HW_CHG_RST)
+			ret = DCB_HW_CHG;
 	}
 
 	if (adapter->dcb_cfg.pfc_mode_enable)
@@ -531,9 +530,6 @@ static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
 	adapter->temp_dcb_cfg.pfc_mode_enable = state;
-	if (adapter->temp_dcb_cfg.pfc_mode_enable !=
-		adapter->dcb_cfg.pfc_mode_enable)
-		adapter->dcb_set_bitmap |= BIT_PFC;
 }
 
 /**
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index f30db1c46600..bc58f1dc22f5 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -55,7 +55,6 @@
 #include <linux/crc32.h>
 
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/bitops.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 153d33210e89..c8950da60e6b 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -57,7 +57,6 @@
 #include <linux/types.h>
 #include <linux/inet_lro.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 
 static char mv643xx_eth_driver_name[] = "mv643xx_eth";
 static char mv643xx_eth_driver_version[] = "1.4";
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 44bad608eed7..1db023b075a1 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -43,7 +43,6 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 #include <linux/pxa168_eth.h>
 
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 20a59322c79d..7732474263da 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -1767,13 +1767,14 @@ static int sky2_open(struct net_device *dev)
 
 	sky2_hw_up(sky2);
 
+	/* Enable interrupts from phy/mac for port */
+	imask = sky2_read32(hw, B0_IMSK);
+
 	if (hw->chip_id == CHIP_ID_YUKON_OPT ||
 	    hw->chip_id == CHIP_ID_YUKON_PRM ||
 	    hw->chip_id == CHIP_ID_YUKON_OP_2)
 		imask |= Y2_IS_PHY_QLNK;	/* enable PHY Quick Link */
 
-	/* Enable interrupts from phy/mac for port */
-	imask = sky2_read32(hw, B0_IMSK);
 	imask |= portirq_msk[port];
 	sky2_write32(hw, B0_IMSK, imask);
 	sky2_read32(hw, B0_IMSK);
@@ -2468,6 +2469,17 @@ static int sky2_change_mtu(struct net_device *dev, int new_mtu)
 	return err;
 }
 
+static inline bool needs_copy(const struct rx_ring_info *re,
+			      unsigned length)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	/* Some architectures need the IP header to be aligned */
+	if (!IS_ALIGNED(re->data_addr + ETH_HLEN, sizeof(u32)))
+		return true;
+#endif
+	return length < copybreak;
+}
+
 /* For small just reuse existing skb for next receive */
 static struct sk_buff *receive_copy(struct sky2_port *sky2,
 				    const struct rx_ring_info *re,
@@ -2598,7 +2610,7 @@ static struct sk_buff *sky2_receive(struct net_device *dev,
 		goto error;
 
 okay:
-	if (length < copybreak)
+	if (needs_copy(re, length))
 		skb = receive_copy(sky2, re, length);
 	else
 		skb = receive_new(sky2, re, length);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 3879c5eee62b..47e1c0ff1775 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -86,8 +86,9 @@
 
 #define MLX4_EN_WATCHDOG_TIMEOUT	(15 * HZ)
 
-#define MLX4_EN_ALLOC_ORDER	2
-#define MLX4_EN_ALLOC_SIZE	(PAGE_SIZE << MLX4_EN_ALLOC_ORDER)
+/* Use the maximum between 16384 and a single page */
+#define MLX4_EN_ALLOC_SIZE	PAGE_ALIGN(16384)
+#define MLX4_EN_ALLOC_ORDER	get_order(MLX4_EN_ALLOC_SIZE)
 
 #define MLX4_EN_MAX_LRO_DESCRIPTORS	32
 
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index 0686b93f1857..f84dd2dc82b6 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -458,7 +458,7 @@ static int ks8842_tx_frame_dma(struct sk_buff *skb, struct net_device *netdev)
 	if (sg_dma_len(&ctl->sg) % 4)
 		sg_dma_len(&ctl->sg) += 4 - sg_dma_len(&ctl->sg) % 4;
 
-	ctl->adesc = ctl->chan->device->device_prep_slave_sg(ctl->chan,
+	ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
 		&ctl->sg, 1, DMA_MEM_TO_DEV,
 		DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
 	if (!ctl->adesc)
@@ -570,7 +570,7 @@ static int __ks8842_start_new_rx_dma(struct net_device *netdev)
 
 		sg_dma_len(sg) = DMA_BUFFER_SIZE;
 
-		ctl->adesc = ctl->chan->device->device_prep_slave_sg(ctl->chan,
+		ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
 			sg, 1, DMA_DEV_TO_MEM,
 			DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
 
diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c
index 5b89fd377ae3..95dd39ffb230 100644
--- a/drivers/net/ethernet/natsemi/jazzsonic.c
+++ b/drivers/net/ethernet/natsemi/jazzsonic.c
@@ -38,7 +38,6 @@
 #include <linux/slab.h>
 
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/dma.h>
diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c
index e640e23460de..b9680ba5a325 100644
--- a/drivers/net/ethernet/natsemi/macsonic.c
+++ b/drivers/net/ethernet/natsemi/macsonic.c
@@ -53,7 +53,6 @@
 #include <linux/slab.h>
 
 #include <asm/bootinfo.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/hwtest.h>
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index c24b46cbfe27..d52728b3c436 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -121,7 +121,6 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #define DRV_NAME "ns83820"
 
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index eb2ab048cbca..bb367582c1e8 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -81,7 +81,6 @@
 #include <linux/prefetch.h>
 #include <net/tcp.h>
 
-#include <asm/system.h>
 #include <asm/div64.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 84952b308f83..d93a088debc3 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -69,7 +69,6 @@
 #include <linux/io.h>
 
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #define TX_WORK_PER_LOOP  64
 #define RX_WORK_PER_LOOP  64
diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c
index 46c1932048cb..e02f04d7f3ad 100644
--- a/drivers/net/ethernet/realtek/atp.c
+++ b/drivers/net/ethernet/realtek/atp.c
@@ -140,7 +140,6 @@ static int xcvr[NUM_UNITS]; 			/* The data transfer mode. */
 #include <linux/delay.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 074a5741baf3..71393ea8ef51 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -29,7 +29,6 @@
 #include <linux/pci-aspm.h>
 #include <linux/prefetch.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
@@ -5812,7 +5811,10 @@ static void __rtl8169_resume(struct net_device *dev)
 
 	rtl_pll_power_up(tp);
 
+	rtl_lock_work(tp);
+	napi_enable(&tp->napi);
 	set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
+	rtl_unlock_work(tp);
 
 	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 5999e961defa..be3c22179161 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -912,7 +912,7 @@ static int sh_eth_dev_init(struct net_device *ndev)
 	/* all sh_eth int mask */
 	sh_eth_write(ndev, 0, EESIPR);
 
-#if defined(__LITTLE_ENDIAN__)
+#if defined(__LITTLE_ENDIAN)
 	if (mdp->cd->hw_swap)
 		sh_eth_write(ndev, EDMR_EL, EDMR);
 	else
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 2d80feadc861..57b8e1fc5d15 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -694,7 +694,7 @@ enum TSU_FWSLC_BIT {
  */
 struct sh_eth_txdesc {
 	u32 status;		/* TD0 */
-#if defined(CONFIG_CPU_LITTLE_ENDIAN)
+#if defined(__LITTLE_ENDIAN)
 	u16 pad0;		/* TD1 */
 	u16 buffer_length;	/* TD1 */
 #else
@@ -711,7 +711,7 @@ struct sh_eth_txdesc {
  */
 struct sh_eth_rxdesc {
 	u32 status;		/* RD0 */
-#if defined(CONFIG_CPU_LITTLE_ENDIAN)
+#if defined(__LITTLE_ENDIAN)
 	u16 frame_length;	/* RD1 */
 	u16 buffer_length;	/* RD1 */
 #else
diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c
index 7b819bd8c416..df808ac8cb65 100644
--- a/drivers/net/ethernet/seeq/ether3.c
+++ b/drivers/net/ethernet/seeq/ether3.c
@@ -64,7 +64,6 @@
 #include <linux/delay.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/ecard.h>
 #include <asm/io.h>
 
diff --git a/drivers/net/ethernet/seeq/seeq8005.c b/drivers/net/ethernet/seeq/seeq8005.c
index 798990774446..698edbbfc149 100644
--- a/drivers/net/ethernet/seeq/seeq8005.c
+++ b/drivers/net/ethernet/seeq/seeq8005.c
@@ -47,7 +47,6 @@ static const char version[] =
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/sfc/mtd.c b/drivers/net/ethernet/sfc/mtd.c
index 26b3c23b0b6f..758148379b0e 100644
--- a/drivers/net/ethernet/sfc/mtd.c
+++ b/drivers/net/ethernet/sfc/mtd.c
@@ -193,7 +193,7 @@ static int efx_mtd_erase(struct mtd_info *mtd, struct erase_info *erase)
 		erase->state = MTD_ERASE_DONE;
 	} else {
 		erase->state = MTD_ERASE_FAILED;
-		erase->fail_addr = 0xffffffff;
+		erase->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
 	}
 	mtd_erase_callback(erase);
 	return rc;
@@ -263,10 +263,10 @@ static int efx_mtd_probe_device(struct efx_nic *efx, struct efx_mtd *efx_mtd)
 		part->mtd.owner = THIS_MODULE;
 		part->mtd.priv = efx_mtd;
 		part->mtd.name = part->name;
-		part->mtd.erase = efx_mtd_erase;
-		part->mtd.read = efx_mtd->ops->read;
-		part->mtd.write = efx_mtd->ops->write;
-		part->mtd.sync = efx_mtd_sync;
+		part->mtd._erase = efx_mtd_erase;
+		part->mtd._read = efx_mtd->ops->read;
+		part->mtd._write = efx_mtd->ops->write;
+		part->mtd._sync = efx_mtd_sync;
 
 		if (mtd_device_register(&part->mtd, NULL, 0))
 			goto fail;
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index d12e48a7861d..04393b5fef71 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -53,7 +53,6 @@
 #include <pcmcia/ss.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 /*====================================================================*/
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 1dc4fad593e7..fee449355014 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2280,7 +2280,7 @@ static int __devinit smc_drv_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_release_io;
 #if defined(CONFIG_SA1100_ASSABET)
-	NCR_0 |= NCR_ENET_OSC_EN;
+	neponset_ncr_set(NCR_ENET_OSC_EN);
 #endif
 	platform_set_drvdata(pdev, ndev);
 	ret = smc_enable_device(pdev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 90d5c4c75d25..a64f0d422e76 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1784,10 +1784,12 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	struct mac_device_info *mac;
 
 	/* Identify the MAC HW device */
-	if (priv->plat->has_gmac)
+	if (priv->plat->has_gmac) {
+		priv->dev->priv_flags |= IFF_UNICAST_FLT;
 		mac = dwmac1000_setup(priv->ioaddr);
-	else
+	} else {
 		mac = dwmac100_setup(priv->ioaddr);
+	}
 	if (!mac)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 3c2295560732..ce4df61b4b56 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -99,7 +99,6 @@
 #include <net/checksum.h>
 
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index f359863b5340..2a83fc57edba 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -35,7 +35,6 @@
 #include <asm/openprom.h>
 #include <asm/oplib.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 
 #include "sunbmac.h"
 
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 8707d59ed545..dfd4b1d13a51 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -41,7 +41,6 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index afb19a6d7c52..dfc00c4683e5 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -36,7 +36,6 @@
 #include <linux/bitops.h>
 #include <linux/dma-mapping.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/byteorder.h>
diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c
index 139d6b410d68..7d4a040d84a2 100644
--- a/drivers/net/ethernet/sun/sunqe.c
+++ b/drivers/net/ethernet/sun/sunqe.c
@@ -28,7 +28,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/byteorder.h>
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 92a037a8228a..38e3ae9155b7 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1259,10 +1259,7 @@ static struct vio_driver vnet_port_driver = {
 	.id_table	= vnet_port_match,
 	.probe		= vnet_port_probe,
 	.remove		= vnet_port_remove,
-	.driver		= {
-		.name	= "vnet_port",
-		.owner	= THIS_MODULE,
-	}
+	.name		= "vnet_port",
 };
 
 static int __init vnet_init(void)
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index 840e0e9031f5..277c93e9ff4d 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -50,7 +50,6 @@
 #include <linux/platform_device.h>
 #include <linux/gfp.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/tsi108.h>
 
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 47b411fe3ecb..0459c096629f 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -503,30 +503,32 @@ static int rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid);
 static int rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid);
 static void rhine_restart_tx(struct net_device *dev);
 
-static void rhine_wait_bit(struct rhine_private *rp, u8 reg, u8 mask, bool high)
+static void rhine_wait_bit(struct rhine_private *rp, u8 reg, u8 mask, bool low)
 {
 	void __iomem *ioaddr = rp->base;
 	int i;
 
 	for (i = 0; i < 1024; i++) {
-		if (high ^ !!(ioread8(ioaddr + reg) & mask))
+		bool has_mask_bits = !!(ioread8(ioaddr + reg) & mask);
+
+		if (low ^ has_mask_bits)
 			break;
 		udelay(10);
 	}
 	if (i > 64) {
 		netif_dbg(rp, hw, rp->dev, "%s bit wait (%02x/%02x) cycle "
-			  "count: %04d\n", high ? "high" : "low", reg, mask, i);
+			  "count: %04d\n", low ? "low" : "high", reg, mask, i);
 	}
 }
 
 static void rhine_wait_bit_high(struct rhine_private *rp, u8 reg, u8 mask)
 {
-	rhine_wait_bit(rp, reg, mask, true);
+	rhine_wait_bit(rp, reg, mask, false);
 }
 
 static void rhine_wait_bit_low(struct rhine_private *rp, u8 reg, u8 mask)
 {
-	rhine_wait_bit(rp, reg, mask, false);
+	rhine_wait_bit(rp, reg, mask, true);
 }
 
 static u32 rhine_get_events(struct rhine_private *rp)
diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index 5c69c6f93fb8..94a1f94f74b8 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -89,7 +89,6 @@
 #include <pcmcia/ciscode.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #ifndef MANFID_COMPAQ
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 2a5a34d2d67b..64783a0d545a 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -13,7 +13,6 @@
  */
 
 #include <linux/module.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c
index f1aea0c98333..acb636963e90 100644
--- a/drivers/net/hamradio/baycom_par.c
+++ b/drivers/net/hamradio/baycom_par.c
@@ -86,7 +86,6 @@
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 /* --------------------------------------------------------------------- */
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 18d8affecd1b..76d54774ba82 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -69,7 +69,6 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index bc02968cee16..aed1a6105b24 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -17,7 +17,6 @@
  * Copyright (C) 2004, 05 Thomas Osterried DL9SAU <thomas@x-berg.in-berlin.de>
  */
 #include <linux/module.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <asm/uaccess.h>
 #include <linux/crc16.h>
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 33655814448e..efc6c97163a7 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -177,7 +177,6 @@
 #include <net/ax25.h>
 
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 696327773fbe..5a6412ecce73 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -52,7 +52,6 @@
 #include <linux/bitops.h>
 #include <linux/random.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/firmware.h>
diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index 248c4f17846c..b6a2bdeff595 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -43,7 +43,6 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <asm/cache.h>
 #include <asm/byteorder.h>
 #include <asm/io.h>
diff --git a/drivers/net/irda/Kconfig b/drivers/net/irda/Kconfig
index e535137eb2d0..468047866c8c 100644
--- a/drivers/net/irda/Kconfig
+++ b/drivers/net/irda/Kconfig
@@ -356,7 +356,7 @@ config VLSI_FIR
 
 config SA1100_FIR
 	tristate "SA1100 Internal IR"
-	depends on ARCH_SA1100 && IRDA
+	depends on ARCH_SA1100 && IRDA && DMA_SA11X0
 
 config VIA_FIR
 	tristate "VIA VT8231/VT1211 SIR/MIR/FIR"
diff --git a/drivers/net/irda/donauboe.c b/drivers/net/irda/donauboe.c
index 617a446d126c..4351296dde32 100644
--- a/drivers/net/irda/donauboe.c
+++ b/drivers/net/irda/donauboe.c
@@ -156,7 +156,6 @@
 #include <linux/pci.h>
 #include <linux/rtnetlink.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <net/irda/wrapper.h>
diff --git a/drivers/net/irda/sa1100_ir.c b/drivers/net/irda/sa1100_ir.c
index da2705061a60..e25067552b20 100644
--- a/drivers/net/irda/sa1100_ir.c
+++ b/drivers/net/irda/sa1100_ir.c
@@ -15,7 +15,7 @@
  *  This driver takes one kernel command line parameter, sa1100ir=, with
  *  the following options:
  *	max_rate:baudrate	- set the maximum baud rate
- *	power_leve:level	- set the transmitter power level
+ *	power_level:level	- set the transmitter power level
  *	tx_lpm:0|1		- set transmit low power mode
  */
 #include <linux/module.h>
@@ -30,13 +30,13 @@
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/sa11x0-dma.h>
 
 #include <net/irda/irda.h>
 #include <net/irda/wrapper.h>
 #include <net/irda/irda_device.h>
 
-#include <asm/irq.h>
-#include <mach/dma.h>
 #include <mach/hardware.h>
 #include <asm/mach/irda.h>
 
@@ -44,8 +44,15 @@ static int power_level = 3;
 static int tx_lpm;
 static int max_rate = 4000000;
 
+struct sa1100_buf {
+	struct device		*dev;
+	struct sk_buff		*skb;
+	struct scatterlist	sg;
+	struct dma_chan		*chan;
+	dma_cookie_t		cookie;
+};
+
 struct sa1100_irda {
-	unsigned char		hscr0;
 	unsigned char		utcr4;
 	unsigned char		power;
 	unsigned char		open;
@@ -53,12 +60,8 @@ struct sa1100_irda {
 	int			speed;
 	int			newspeed;
 
-	struct sk_buff		*txskb;
-	struct sk_buff		*rxskb;
-	dma_addr_t		txbuf_dma;
-	dma_addr_t		rxbuf_dma;
-	dma_regs_t		*txdma;
-	dma_regs_t		*rxdma;
+	struct sa1100_buf	dma_rx;
+	struct sa1100_buf	dma_tx;
 
 	struct device		*dev;
 	struct irda_platform_data *pdata;
@@ -67,23 +70,103 @@ struct sa1100_irda {
 
 	iobuff_t		tx_buff;
 	iobuff_t		rx_buff;
+
+	int (*tx_start)(struct sk_buff *, struct net_device *, struct sa1100_irda *);
+	irqreturn_t (*irq)(struct net_device *, struct sa1100_irda *);
 };
 
+static int sa1100_irda_set_speed(struct sa1100_irda *, int);
+
 #define IS_FIR(si)		((si)->speed >= 4000000)
 
 #define HPSIR_MAX_RXLEN		2047
 
+static struct dma_slave_config sa1100_irda_sir_tx = {
+	.direction	= DMA_TO_DEVICE,
+	.dst_addr	= __PREG(Ser2UTDR),
+	.dst_addr_width	= DMA_SLAVE_BUSWIDTH_1_BYTE,
+	.dst_maxburst	= 4,
+};
+
+static struct dma_slave_config sa1100_irda_fir_rx = {
+	.direction	= DMA_FROM_DEVICE,
+	.src_addr	= __PREG(Ser2HSDR),
+	.src_addr_width	= DMA_SLAVE_BUSWIDTH_1_BYTE,
+	.src_maxburst	= 8,
+};
+
+static struct dma_slave_config sa1100_irda_fir_tx = {
+	.direction	= DMA_TO_DEVICE,
+	.dst_addr	= __PREG(Ser2HSDR),
+	.dst_addr_width	= DMA_SLAVE_BUSWIDTH_1_BYTE,
+	.dst_maxburst	= 8,
+};
+
+static unsigned sa1100_irda_dma_xferred(struct sa1100_buf *buf)
+{
+	struct dma_chan *chan = buf->chan;
+	struct dma_tx_state state;
+	enum dma_status status;
+
+	status = chan->device->device_tx_status(chan, buf->cookie, &state);
+	if (status != DMA_PAUSED)
+		return 0;
+
+	return sg_dma_len(&buf->sg) - state.residue;
+}
+
+static int sa1100_irda_dma_request(struct device *dev, struct sa1100_buf *buf,
+	const char *name, struct dma_slave_config *cfg)
+{
+	dma_cap_mask_t m;
+	int ret;
+
+	dma_cap_zero(m);
+	dma_cap_set(DMA_SLAVE, m);
+
+	buf->chan = dma_request_channel(m, sa11x0_dma_filter_fn, (void *)name);
+	if (!buf->chan) {
+		dev_err(dev, "unable to request DMA channel for %s\n",
+			name);
+		return -ENOENT;
+	}
+
+	ret = dmaengine_slave_config(buf->chan, cfg);
+	if (ret)
+		dev_warn(dev, "DMA slave_config for %s returned %d\n",
+			name, ret);
+
+	buf->dev = buf->chan->device->dev;
+
+	return 0;
+}
+
+static void sa1100_irda_dma_start(struct sa1100_buf *buf,
+	enum dma_transfer_direction dir, dma_async_tx_callback cb, void *cb_p)
+{
+	struct dma_async_tx_descriptor *desc;
+	struct dma_chan *chan = buf->chan;
+
+	desc = dmaengine_prep_slave_sg(chan, &buf->sg, 1, dir,
+			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (desc) {
+		desc->callback = cb;
+		desc->callback_param = cb_p;
+		buf->cookie = dmaengine_submit(desc);
+		dma_async_issue_pending(chan);
+	}
+}
+
 /*
  * Allocate and map the receive buffer, unless it is already allocated.
  */
 static int sa1100_irda_rx_alloc(struct sa1100_irda *si)
 {
-	if (si->rxskb)
+	if (si->dma_rx.skb)
 		return 0;
 
-	si->rxskb = alloc_skb(HPSIR_MAX_RXLEN + 1, GFP_ATOMIC);
-
-	if (!si->rxskb) {
+	si->dma_rx.skb = alloc_skb(HPSIR_MAX_RXLEN + 1, GFP_ATOMIC);
+	if (!si->dma_rx.skb) {
 		printk(KERN_ERR "sa1100_ir: out of memory for RX SKB\n");
 		return -ENOMEM;
 	}
@@ -92,11 +175,14 @@ static int sa1100_irda_rx_alloc(struct sa1100_irda *si)
 	 * Align any IP headers that may be contained
 	 * within the frame.
 	 */
-	skb_reserve(si->rxskb, 1);
+	skb_reserve(si->dma_rx.skb, 1);
+
+	sg_set_buf(&si->dma_rx.sg, si->dma_rx.skb->data, HPSIR_MAX_RXLEN);
+	if (dma_map_sg(si->dma_rx.dev, &si->dma_rx.sg, 1, DMA_FROM_DEVICE) == 0) {
+		dev_kfree_skb_any(si->dma_rx.skb);
+		return -ENOMEM;
+	}
 
-	si->rxbuf_dma = dma_map_single(si->dev, si->rxskb->data,
-					HPSIR_MAX_RXLEN,
-					DMA_FROM_DEVICE);
 	return 0;
 }
 
@@ -106,7 +192,7 @@ static int sa1100_irda_rx_alloc(struct sa1100_irda *si)
  */
 static void sa1100_irda_rx_dma_start(struct sa1100_irda *si)
 {
-	if (!si->rxskb) {
+	if (!si->dma_rx.skb) {
 		printk(KERN_ERR "sa1100_ir: rx buffer went missing\n");
 		return;
 	}
@@ -114,254 +200,87 @@ static void sa1100_irda_rx_dma_start(struct sa1100_irda *si)
 	/*
 	 * First empty receive FIFO
 	 */
-	Ser2HSCR0 = si->hscr0 | HSCR0_HSSP;
+	Ser2HSCR0 = HSCR0_HSSP;
 
 	/*
 	 * Enable the DMA, receiver and receive interrupt.
 	 */
-	sa1100_clear_dma(si->rxdma);
-	sa1100_start_dma(si->rxdma, si->rxbuf_dma, HPSIR_MAX_RXLEN);
-	Ser2HSCR0 = si->hscr0 | HSCR0_HSSP | HSCR0_RXE;
+	dmaengine_terminate_all(si->dma_rx.chan);
+	sa1100_irda_dma_start(&si->dma_rx, DMA_DEV_TO_MEM, NULL, NULL);
+
+	Ser2HSCR0 = HSCR0_HSSP | HSCR0_RXE;
 }
 
-/*
- * Set the IrDA communications speed.
- */
-static int sa1100_irda_set_speed(struct sa1100_irda *si, int speed)
+static void sa1100_irda_check_speed(struct sa1100_irda *si)
 {
-	unsigned long flags;
-	int brd, ret = -EINVAL;
-
-	switch (speed) {
-	case 9600:	case 19200:	case 38400:
-	case 57600:	case 115200:
-		brd = 3686400 / (16 * speed) - 1;
-
-		/*
-		 * Stop the receive DMA.
-		 */
-		if (IS_FIR(si))
-			sa1100_stop_dma(si->rxdma);
-
-		local_irq_save(flags);
-
-		Ser2UTCR3 = 0;
-		Ser2HSCR0 = HSCR0_UART;
-
-		Ser2UTCR1 = brd >> 8;
-		Ser2UTCR2 = brd;
-
-		/*
-		 * Clear status register
-		 */
-		Ser2UTSR0 = UTSR0_REB | UTSR0_RBB | UTSR0_RID;
-		Ser2UTCR3 = UTCR3_RIE | UTCR3_RXE | UTCR3_TXE;
-
-		if (si->pdata->set_speed)
-			si->pdata->set_speed(si->dev, speed);
-
-		si->speed = speed;
-
-		local_irq_restore(flags);
-		ret = 0;
-		break;
-
-	case 4000000:
-		local_irq_save(flags);
-
-		si->hscr0 = 0;
-
-		Ser2HSSR0 = 0xff;
-		Ser2HSCR0 = si->hscr0 | HSCR0_HSSP;
-		Ser2UTCR3 = 0;
-
-		si->speed = speed;
-
-		if (si->pdata->set_speed)
-			si->pdata->set_speed(si->dev, speed);
-
-		sa1100_irda_rx_alloc(si);
-		sa1100_irda_rx_dma_start(si);
-
-		local_irq_restore(flags);
-
-		break;
-
-	default:
-		break;
+	if (si->newspeed) {
+		sa1100_irda_set_speed(si, si->newspeed);
+		si->newspeed = 0;
 	}
-
-	return ret;
 }
 
 /*
- * Control the power state of the IrDA transmitter.
- * State:
- *  0 - off
- *  1 - short range, lowest power
- *  2 - medium range, medium power
- *  3 - maximum range, high power
- *
- * Currently, only assabet is known to support this.
+ * HP-SIR format support.
  */
-static int
-__sa1100_irda_set_power(struct sa1100_irda *si, unsigned int state)
+static void sa1100_irda_sirtxdma_irq(void *id)
 {
-	int ret = 0;
-	if (si->pdata->set_power)
-		ret = si->pdata->set_power(si->dev, state);
-	return ret;
-}
-
-static inline int
-sa1100_set_power(struct sa1100_irda *si, unsigned int state)
-{
-	int ret;
-
-	ret = __sa1100_irda_set_power(si, state);
-	if (ret == 0)
-		si->power = state;
+	struct net_device *dev = id;
+	struct sa1100_irda *si = netdev_priv(dev);
 
-	return ret;
-}
+	dma_unmap_sg(si->dma_tx.dev, &si->dma_tx.sg, 1, DMA_TO_DEVICE);
+	dev_kfree_skb(si->dma_tx.skb);
+	si->dma_tx.skb = NULL;
 
-static int sa1100_irda_startup(struct sa1100_irda *si)
-{
-	int ret;
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += sg_dma_len(&si->dma_tx.sg);
 
-	/*
-	 * Ensure that the ports for this device are setup correctly.
-	 */
-	if (si->pdata->startup)	{
-		ret = si->pdata->startup(si->dev);
-		if (ret)
-			return ret;
-	}
-
-	/*
-	 * Configure PPC for IRDA - we want to drive TXD2 low.
-	 * We also want to drive this pin low during sleep.
-	 */
-	PPSR &= ~PPC_TXD2;
-	PSDR &= ~PPC_TXD2;
-	PPDR |= PPC_TXD2;
-
-	/*
-	 * Enable HP-SIR modulation, and ensure that the port is disabled.
-	 */
-	Ser2UTCR3 = 0;
-	Ser2HSCR0 = HSCR0_UART;
-	Ser2UTCR4 = si->utcr4;
-	Ser2UTCR0 = UTCR0_8BitData;
-	Ser2HSCR2 = HSCR2_TrDataH | HSCR2_RcDataL;
+	/* We need to ensure that the transmitter has finished. */
+	do
+		rmb();
+	while (Ser2UTSR1 & UTSR1_TBY);
 
 	/*
-	 * Clear status register
+	 * Ok, we've finished transmitting.  Now enable the receiver.
+	 * Sometimes we get a receive IRQ immediately after a transmit...
 	 */
 	Ser2UTSR0 = UTSR0_REB | UTSR0_RBB | UTSR0_RID;
+	Ser2UTCR3 = UTCR3_RIE | UTCR3_RXE | UTCR3_TXE;
 
-	ret = sa1100_irda_set_speed(si, si->speed = 9600);
-	if (ret) {
-		Ser2UTCR3 = 0;
-		Ser2HSCR0 = 0;
-
-		if (si->pdata->shutdown)
-			si->pdata->shutdown(si->dev);
-	}
-
-	return ret;
-}
-
-static void sa1100_irda_shutdown(struct sa1100_irda *si)
-{
-	/*
-	 * Stop all DMA activity.
-	 */
-	sa1100_stop_dma(si->rxdma);
-	sa1100_stop_dma(si->txdma);
-
-	/* Disable the port. */
-	Ser2UTCR3 = 0;
-	Ser2HSCR0 = 0;
+	sa1100_irda_check_speed(si);
 
-	if (si->pdata->shutdown)
-		si->pdata->shutdown(si->dev);
+	/* I'm hungry! */
+	netif_wake_queue(dev);
 }
 
-#ifdef CONFIG_PM
-/*
- * Suspend the IrDA interface.
- */
-static int sa1100_irda_suspend(struct platform_device *pdev, pm_message_t state)
+static int sa1100_irda_sir_tx_start(struct sk_buff *skb, struct net_device *dev,
+	struct sa1100_irda *si)
 {
-	struct net_device *dev = platform_get_drvdata(pdev);
-	struct sa1100_irda *si;
-
-	if (!dev)
-		return 0;
-
-	si = netdev_priv(dev);
-	if (si->open) {
-		/*
-		 * Stop the transmit queue
-		 */
-		netif_device_detach(dev);
-		disable_irq(dev->irq);
-		sa1100_irda_shutdown(si);
-		__sa1100_irda_set_power(si, 0);
+	si->tx_buff.data = si->tx_buff.head;
+	si->tx_buff.len  = async_wrap_skb(skb, si->tx_buff.data,
+					  si->tx_buff.truesize);
+
+	si->dma_tx.skb = skb;
+	sg_set_buf(&si->dma_tx.sg, si->tx_buff.data, si->tx_buff.len);
+	if (dma_map_sg(si->dma_tx.dev, &si->dma_tx.sg, 1, DMA_TO_DEVICE) == 0) {
+		si->dma_tx.skb = NULL;
+		netif_wake_queue(dev);
+		dev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
 	}
 
-	return 0;
-}
-
-/*
- * Resume the IrDA interface.
- */
-static int sa1100_irda_resume(struct platform_device *pdev)
-{
-	struct net_device *dev = platform_get_drvdata(pdev);
-	struct sa1100_irda *si;
-
-	if (!dev)
-		return 0;
+	sa1100_irda_dma_start(&si->dma_tx, DMA_MEM_TO_DEV, sa1100_irda_sirtxdma_irq, dev);
 
-	si = netdev_priv(dev);
-	if (si->open) {
-		/*
-		 * If we missed a speed change, initialise at the new speed
-		 * directly.  It is debatable whether this is actually
-		 * required, but in the interests of continuing from where
-		 * we left off it is desirable.  The converse argument is
-		 * that we should re-negotiate at 9600 baud again.
-		 */
-		if (si->newspeed) {
-			si->speed = si->newspeed;
-			si->newspeed = 0;
-		}
-
-		sa1100_irda_startup(si);
-		__sa1100_irda_set_power(si, si->power);
-		enable_irq(dev->irq);
-
-		/*
-		 * This automatically wakes up the queue
-		 */
-		netif_device_attach(dev);
-	}
+	/*
+	 * The mean turn-around time is enforced by XBOF padding,
+	 * so we don't have to do anything special here.
+	 */
+	Ser2UTCR3 = UTCR3_TXE;
 
-	return 0;
+	return NETDEV_TX_OK;
 }
-#else
-#define sa1100_irda_suspend	NULL
-#define sa1100_irda_resume	NULL
-#endif
 
-/*
- * HP-SIR format interrupt service routines.
- */
-static void sa1100_irda_hpsir_irq(struct net_device *dev)
+static irqreturn_t sa1100_irda_sir_irq(struct net_device *dev, struct sa1100_irda *si)
 {
-	struct sa1100_irda *si = netdev_priv(dev);
 	int status;
 
 	status = Ser2UTSR0;
@@ -414,51 +333,96 @@ static void sa1100_irda_hpsir_irq(struct net_device *dev)
 
 	}
 
-	if (status & UTSR0_TFS && si->tx_buff.len) {
-		/*
-		 * Transmitter FIFO is not full
-		 */
-		do {
-			Ser2UTDR = *si->tx_buff.data++;
-			si->tx_buff.len -= 1;
-		} while (Ser2UTSR1 & UTSR1_TNF && si->tx_buff.len);
+	return IRQ_HANDLED;
+}
 
-		if (si->tx_buff.len == 0) {
-			dev->stats.tx_packets++;
-			dev->stats.tx_bytes += si->tx_buff.data -
-					      si->tx_buff.head;
+/*
+ * FIR format support.
+ */
+static void sa1100_irda_firtxdma_irq(void *id)
+{
+	struct net_device *dev = id;
+	struct sa1100_irda *si = netdev_priv(dev);
+	struct sk_buff *skb;
 
-			/*
-			 * We need to ensure that the transmitter has
-			 * finished.
-			 */
-			do
-				rmb();
-			while (Ser2UTSR1 & UTSR1_TBY);
+	/*
+	 * Wait for the transmission to complete.  Unfortunately,
+	 * the hardware doesn't give us an interrupt to indicate
+	 * "end of frame".
+	 */
+	do
+		rmb();
+	while (!(Ser2HSSR0 & HSSR0_TUR) || Ser2HSSR1 & HSSR1_TBY);
 
-			/*
-			 * Ok, we've finished transmitting.  Now enable
-			 * the receiver.  Sometimes we get a receive IRQ
-			 * immediately after a transmit...
-			 */
-			Ser2UTSR0 = UTSR0_REB | UTSR0_RBB | UTSR0_RID;
-			Ser2UTCR3 = UTCR3_RIE | UTCR3_RXE | UTCR3_TXE;
+	/*
+	 * Clear the transmit underrun bit.
+	 */
+	Ser2HSSR0 = HSSR0_TUR;
 
-			if (si->newspeed) {
-				sa1100_irda_set_speed(si, si->newspeed);
-				si->newspeed = 0;
-			}
+	/*
+	 * Do we need to change speed?  Note that we're lazy
+	 * here - we don't free the old dma_rx.skb.  We don't need
+	 * to allocate a buffer either.
+	 */
+	sa1100_irda_check_speed(si);
 
-			/* I'm hungry! */
-			netif_wake_queue(dev);
-		}
+	/*
+	 * Start reception.  This disables the transmitter for
+	 * us.  This will be using the existing RX buffer.
+	 */
+	sa1100_irda_rx_dma_start(si);
+
+	/* Account and free the packet. */
+	skb = si->dma_tx.skb;
+	if (skb) {
+		dma_unmap_sg(si->dma_tx.dev, &si->dma_tx.sg, 1,
+			     DMA_TO_DEVICE);
+		dev->stats.tx_packets ++;
+		dev->stats.tx_bytes += skb->len;
+		dev_kfree_skb_irq(skb);
+		si->dma_tx.skb = NULL;
 	}
+
+	/*
+	 * Make sure that the TX queue is available for sending
+	 * (for retries).  TX has priority over RX at all times.
+	 */
+	netif_wake_queue(dev);
+}
+
+static int sa1100_irda_fir_tx_start(struct sk_buff *skb, struct net_device *dev,
+	struct sa1100_irda *si)
+{
+	int mtt = irda_get_mtt(skb);
+
+	si->dma_tx.skb = skb;
+	sg_set_buf(&si->dma_tx.sg, skb->data, skb->len);
+	if (dma_map_sg(si->dma_tx.dev, &si->dma_tx.sg, 1, DMA_TO_DEVICE) == 0) {
+		si->dma_tx.skb = NULL;
+		netif_wake_queue(dev);
+		dev->stats.tx_dropped++;
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
+	sa1100_irda_dma_start(&si->dma_tx, DMA_MEM_TO_DEV, sa1100_irda_firtxdma_irq, dev);
+
+	/*
+	 * If we have a mean turn-around time, impose the specified
+	 * specified delay.  We could shorten this by timing from
+	 * the point we received the packet.
+	 */
+	if (mtt)
+		udelay(mtt);
+
+	Ser2HSCR0 = HSCR0_HSSP | HSCR0_TXE;
+
+	return NETDEV_TX_OK;
 }
 
 static void sa1100_irda_fir_error(struct sa1100_irda *si, struct net_device *dev)
 {
-	struct sk_buff *skb = si->rxskb;
-	dma_addr_t dma_addr;
+	struct sk_buff *skb = si->dma_rx.skb;
 	unsigned int len, stat, data;
 
 	if (!skb) {
@@ -469,11 +433,10 @@ static void sa1100_irda_fir_error(struct sa1100_irda *si, struct net_device *dev
 	/*
 	 * Get the current data position.
 	 */
-	dma_addr = sa1100_get_dma_pos(si->rxdma);
-	len = dma_addr - si->rxbuf_dma;
+	len = sa1100_irda_dma_xferred(&si->dma_rx);
 	if (len > HPSIR_MAX_RXLEN)
 		len = HPSIR_MAX_RXLEN;
-	dma_unmap_single(si->dev, si->rxbuf_dma, len, DMA_FROM_DEVICE);
+	dma_unmap_sg(si->dma_rx.dev, &si->dma_rx.sg, 1, DMA_FROM_DEVICE);
 
 	do {
 		/*
@@ -501,7 +464,7 @@ static void sa1100_irda_fir_error(struct sa1100_irda *si, struct net_device *dev
 	} while (Ser2HSSR0 & HSSR0_EIF);
 
 	if (stat & HSSR1_EOF) {
-		si->rxskb = NULL;
+		si->dma_rx.skb = NULL;
 
 		skb_put(skb, len);
 		skb->dev = dev;
@@ -518,28 +481,23 @@ static void sa1100_irda_fir_error(struct sa1100_irda *si, struct net_device *dev
 		netif_rx(skb);
 	} else {
 		/*
-		 * Remap the buffer.
+		 * Remap the buffer - it was previously mapped, and we
+		 * hope that this succeeds.
 		 */
-		si->rxbuf_dma = dma_map_single(si->dev, si->rxskb->data,
-						HPSIR_MAX_RXLEN,
-						DMA_FROM_DEVICE);
+		dma_map_sg(si->dma_rx.dev, &si->dma_rx.sg, 1, DMA_FROM_DEVICE);
 	}
 }
 
 /*
- * FIR format interrupt service routine.  We only have to
- * handle RX events; transmit events go via the TX DMA handler.
- *
- * No matter what, we disable RX, process, and the restart RX.
+ * We only have to handle RX events here; transmit events go via the TX
+ * DMA handler. We disable RX, process, and the restart RX.
  */
-static void sa1100_irda_fir_irq(struct net_device *dev)
+static irqreturn_t sa1100_irda_fir_irq(struct net_device *dev, struct sa1100_irda *si)
 {
-	struct sa1100_irda *si = netdev_priv(dev);
-
 	/*
 	 * Stop RX DMA
 	 */
-	sa1100_stop_dma(si->rxdma);
+	dmaengine_pause(si->dma_rx.chan);
 
 	/*
 	 * Framing error - we throw away the packet completely.
@@ -555,7 +513,7 @@ static void sa1100_irda_fir_irq(struct net_device *dev)
 		/*
 		 * Clear out the DMA...
 		 */
-		Ser2HSCR0 = si->hscr0 | HSCR0_HSSP;
+		Ser2HSCR0 = HSCR0_HSSP;
 
 		/*
 		 * Clear selected status bits now, so we
@@ -577,74 +535,124 @@ static void sa1100_irda_fir_irq(struct net_device *dev)
 	 * No matter what happens, we must restart reception.
 	 */
 	sa1100_irda_rx_dma_start(si);
-}
 
-static irqreturn_t sa1100_irda_irq(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	if (IS_FIR(((struct sa1100_irda *)netdev_priv(dev))))
-		sa1100_irda_fir_irq(dev);
-	else
-		sa1100_irda_hpsir_irq(dev);
 	return IRQ_HANDLED;
 }
 
 /*
- * TX DMA completion handler.
+ * Set the IrDA communications speed.
  */
-static void sa1100_irda_txdma_irq(void *id)
+static int sa1100_irda_set_speed(struct sa1100_irda *si, int speed)
 {
-	struct net_device *dev = id;
-	struct sa1100_irda *si = netdev_priv(dev);
-	struct sk_buff *skb = si->txskb;
+	unsigned long flags;
+	int brd, ret = -EINVAL;
 
-	si->txskb = NULL;
+	switch (speed) {
+	case 9600:	case 19200:	case 38400:
+	case 57600:	case 115200:
+		brd = 3686400 / (16 * speed) - 1;
 
-	/*
-	 * Wait for the transmission to complete.  Unfortunately,
-	 * the hardware doesn't give us an interrupt to indicate
-	 * "end of frame".
-	 */
-	do
-		rmb();
-	while (!(Ser2HSSR0 & HSSR0_TUR) || Ser2HSSR1 & HSSR1_TBY);
+		/* Stop the receive DMA, and configure transmit. */
+		if (IS_FIR(si)) {
+			dmaengine_terminate_all(si->dma_rx.chan);
+			dmaengine_slave_config(si->dma_tx.chan,
+						&sa1100_irda_sir_tx);
+		}
 
-	/*
-	 * Clear the transmit underrun bit.
-	 */
-	Ser2HSSR0 = HSSR0_TUR;
+		local_irq_save(flags);
 
-	/*
-	 * Do we need to change speed?  Note that we're lazy
-	 * here - we don't free the old rxskb.  We don't need
-	 * to allocate a buffer either.
-	 */
-	if (si->newspeed) {
-		sa1100_irda_set_speed(si, si->newspeed);
-		si->newspeed = 0;
-	}
+		Ser2UTCR3 = 0;
+		Ser2HSCR0 = HSCR0_UART;
 
-	/*
-	 * Start reception.  This disables the transmitter for
-	 * us.  This will be using the existing RX buffer.
-	 */
-	sa1100_irda_rx_dma_start(si);
+		Ser2UTCR1 = brd >> 8;
+		Ser2UTCR2 = brd;
 
-	/*
-	 * Account and free the packet.
-	 */
-	if (skb) {
-		dma_unmap_single(si->dev, si->txbuf_dma, skb->len, DMA_TO_DEVICE);
-		dev->stats.tx_packets ++;
-		dev->stats.tx_bytes += skb->len;
-		dev_kfree_skb_irq(skb);
+		/*
+		 * Clear status register
+		 */
+		Ser2UTSR0 = UTSR0_REB | UTSR0_RBB | UTSR0_RID;
+		Ser2UTCR3 = UTCR3_RIE | UTCR3_RXE | UTCR3_TXE;
+
+		if (si->pdata->set_speed)
+			si->pdata->set_speed(si->dev, speed);
+
+		si->speed = speed;
+		si->tx_start = sa1100_irda_sir_tx_start;
+		si->irq = sa1100_irda_sir_irq;
+
+		local_irq_restore(flags);
+		ret = 0;
+		break;
+
+	case 4000000:
+		if (!IS_FIR(si))
+			dmaengine_slave_config(si->dma_tx.chan,
+						&sa1100_irda_fir_tx);
+
+		local_irq_save(flags);
+
+		Ser2HSSR0 = 0xff;
+		Ser2HSCR0 = HSCR0_HSSP;
+		Ser2UTCR3 = 0;
+
+		si->speed = speed;
+		si->tx_start = sa1100_irda_fir_tx_start;
+		si->irq = sa1100_irda_fir_irq;
+
+		if (si->pdata->set_speed)
+			si->pdata->set_speed(si->dev, speed);
+
+		sa1100_irda_rx_alloc(si);
+		sa1100_irda_rx_dma_start(si);
+
+		local_irq_restore(flags);
+
+		break;
+
+	default:
+		break;
 	}
 
-	/*
-	 * Make sure that the TX queue is available for sending
-	 * (for retries).  TX has priority over RX at all times.
-	 */
-	netif_wake_queue(dev);
+	return ret;
+}
+
+/*
+ * Control the power state of the IrDA transmitter.
+ * State:
+ *  0 - off
+ *  1 - short range, lowest power
+ *  2 - medium range, medium power
+ *  3 - maximum range, high power
+ *
+ * Currently, only assabet is known to support this.
+ */
+static int
+__sa1100_irda_set_power(struct sa1100_irda *si, unsigned int state)
+{
+	int ret = 0;
+	if (si->pdata->set_power)
+		ret = si->pdata->set_power(si->dev, state);
+	return ret;
+}
+
+static inline int
+sa1100_set_power(struct sa1100_irda *si, unsigned int state)
+{
+	int ret;
+
+	ret = __sa1100_irda_set_power(si, state);
+	if (ret == 0)
+		si->power = state;
+
+	return ret;
+}
+
+static irqreturn_t sa1100_irda_irq(int irq, void *dev_id)
+{
+	struct net_device *dev = dev_id;
+	struct sa1100_irda *si = netdev_priv(dev);
+
+	return si->irq(dev, si);
 }
 
 static int sa1100_irda_hard_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -660,62 +668,19 @@ static int sa1100_irda_hard_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (speed != si->speed && speed != -1)
 		si->newspeed = speed;
 
-	/*
-	 * If this is an empty frame, we can bypass a lot.
-	 */
+	/* If this is an empty frame, we can bypass a lot. */
 	if (skb->len == 0) {
-		if (si->newspeed) {
-			si->newspeed = 0;
-			sa1100_irda_set_speed(si, speed);
-		}
+		sa1100_irda_check_speed(si);
 		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
 
-	if (!IS_FIR(si)) {
-		netif_stop_queue(dev);
-
-		si->tx_buff.data = si->tx_buff.head;
-		si->tx_buff.len  = async_wrap_skb(skb, si->tx_buff.data,
-						  si->tx_buff.truesize);
-
-		/*
-		 * Set the transmit interrupt enable.  This will fire
-		 * off an interrupt immediately.  Note that we disable
-		 * the receiver so we won't get spurious characteres
-		 * received.
-		 */
-		Ser2UTCR3 = UTCR3_TIE | UTCR3_TXE;
-
-		dev_kfree_skb(skb);
-	} else {
-		int mtt = irda_get_mtt(skb);
-
-		/*
-		 * We must not be transmitting...
-		 */
-		BUG_ON(si->txskb);
-
-		netif_stop_queue(dev);
-
-		si->txskb = skb;
-		si->txbuf_dma = dma_map_single(si->dev, skb->data,
-					 skb->len, DMA_TO_DEVICE);
-
-		sa1100_start_dma(si->txdma, si->txbuf_dma, skb->len);
-
-		/*
-		 * If we have a mean turn-around time, impose the specified
-		 * specified delay.  We could shorten this by timing from
-		 * the point we received the packet.
-		 */
-		if (mtt)
-			udelay(mtt);
+	netif_stop_queue(dev);
 
-		Ser2HSCR0 = si->hscr0 | HSCR0_HSSP | HSCR0_TXE;
-	}
+	/* We must not already have a skb to transmit... */
+	BUG_ON(si->dma_tx.skb);
 
-	return NETDEV_TX_OK;
+	return si->tx_start(skb, dev, si);
 }
 
 static int
@@ -762,6 +727,69 @@ sa1100_irda_ioctl(struct net_device *dev, struct ifreq *ifreq, int cmd)
 	return ret;
 }
 
+static int sa1100_irda_startup(struct sa1100_irda *si)
+{
+	int ret;
+
+	/*
+	 * Ensure that the ports for this device are setup correctly.
+	 */
+	if (si->pdata->startup)	{
+		ret = si->pdata->startup(si->dev);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * Configure PPC for IRDA - we want to drive TXD2 low.
+	 * We also want to drive this pin low during sleep.
+	 */
+	PPSR &= ~PPC_TXD2;
+	PSDR &= ~PPC_TXD2;
+	PPDR |= PPC_TXD2;
+
+	/*
+	 * Enable HP-SIR modulation, and ensure that the port is disabled.
+	 */
+	Ser2UTCR3 = 0;
+	Ser2HSCR0 = HSCR0_UART;
+	Ser2UTCR4 = si->utcr4;
+	Ser2UTCR0 = UTCR0_8BitData;
+	Ser2HSCR2 = HSCR2_TrDataH | HSCR2_RcDataL;
+
+	/*
+	 * Clear status register
+	 */
+	Ser2UTSR0 = UTSR0_REB | UTSR0_RBB | UTSR0_RID;
+
+	ret = sa1100_irda_set_speed(si, si->speed = 9600);
+	if (ret) {
+		Ser2UTCR3 = 0;
+		Ser2HSCR0 = 0;
+
+		if (si->pdata->shutdown)
+			si->pdata->shutdown(si->dev);
+	}
+
+	return ret;
+}
+
+static void sa1100_irda_shutdown(struct sa1100_irda *si)
+{
+	/*
+	 * Stop all DMA activity.
+	 */
+	dmaengine_terminate_all(si->dma_rx.chan);
+	dmaengine_terminate_all(si->dma_tx.chan);
+
+	/* Disable the port. */
+	Ser2UTCR3 = 0;
+	Ser2HSCR0 = 0;
+
+	if (si->pdata->shutdown)
+		si->pdata->shutdown(si->dev);
+}
+
 static int sa1100_irda_start(struct net_device *dev)
 {
 	struct sa1100_irda *si = netdev_priv(dev);
@@ -769,26 +797,17 @@ static int sa1100_irda_start(struct net_device *dev)
 
 	si->speed = 9600;
 
-	err = request_irq(dev->irq, sa1100_irda_irq, 0, dev->name, dev);
-	if (err)
-		goto err_irq;
-
-	err = sa1100_request_dma(DMA_Ser2HSSPRd, "IrDA receive",
-				 NULL, NULL, &si->rxdma);
+	err = sa1100_irda_dma_request(si->dev, &si->dma_rx, "Ser2ICPRc",
+				&sa1100_irda_fir_rx);
 	if (err)
 		goto err_rx_dma;
 
-	err = sa1100_request_dma(DMA_Ser2HSSPWr, "IrDA transmit",
-				 sa1100_irda_txdma_irq, dev, &si->txdma);
+	err = sa1100_irda_dma_request(si->dev, &si->dma_tx, "Ser2ICPTr",
+				&sa1100_irda_sir_tx);
 	if (err)
 		goto err_tx_dma;
 
 	/*
-	 * The interrupt must remain disabled for now.
-	 */
-	disable_irq(dev->irq);
-
-	/*
 	 * Setup the serial port for the specified speed.
 	 */
 	err = sa1100_irda_startup(si);
@@ -803,44 +822,60 @@ static int sa1100_irda_start(struct net_device *dev)
 	if (!si->irlap)
 		goto err_irlap;
 
+	err = request_irq(dev->irq, sa1100_irda_irq, 0, dev->name, dev);
+	if (err)
+		goto err_irq;
+
 	/*
 	 * Now enable the interrupt and start the queue
 	 */
 	si->open = 1;
 	sa1100_set_power(si, power_level); /* low power mode */
-	enable_irq(dev->irq);
+
 	netif_start_queue(dev);
 	return 0;
 
+err_irq:
+	irlap_close(si->irlap);
 err_irlap:
 	si->open = 0;
 	sa1100_irda_shutdown(si);
 err_startup:
-	sa1100_free_dma(si->txdma);
+	dma_release_channel(si->dma_tx.chan);
 err_tx_dma:
-	sa1100_free_dma(si->rxdma);
+	dma_release_channel(si->dma_rx.chan);
 err_rx_dma:
-	free_irq(dev->irq, dev);
-err_irq:
 	return err;
 }
 
 static int sa1100_irda_stop(struct net_device *dev)
 {
 	struct sa1100_irda *si = netdev_priv(dev);
+	struct sk_buff *skb;
+
+	netif_stop_queue(dev);
 
-	disable_irq(dev->irq);
+	si->open = 0;
 	sa1100_irda_shutdown(si);
 
 	/*
-	 * If we have been doing DMA receive, make sure we
+	 * If we have been doing any DMA activity, make sure we
 	 * tidy that up cleanly.
 	 */
-	if (si->rxskb) {
-		dma_unmap_single(si->dev, si->rxbuf_dma, HPSIR_MAX_RXLEN,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb(si->rxskb);
-		si->rxskb = NULL;
+	skb = si->dma_rx.skb;
+	if (skb) {
+		dma_unmap_sg(si->dma_rx.dev, &si->dma_rx.sg, 1,
+			     DMA_FROM_DEVICE);
+		dev_kfree_skb(skb);
+		si->dma_rx.skb = NULL;
+	}
+
+	skb = si->dma_tx.skb;
+	if (skb) {
+		dma_unmap_sg(si->dma_tx.dev, &si->dma_tx.sg, 1,
+			     DMA_TO_DEVICE);
+		dev_kfree_skb(skb);
+		si->dma_tx.skb = NULL;
 	}
 
 	/* Stop IrLAP */
@@ -849,14 +884,11 @@ static int sa1100_irda_stop(struct net_device *dev)
 		si->irlap = NULL;
 	}
 
-	netif_stop_queue(dev);
-	si->open = 0;
-
 	/*
 	 * Free resources
 	 */
-	sa1100_free_dma(si->txdma);
-	sa1100_free_dma(si->rxdma);
+	dma_release_channel(si->dma_tx.chan);
+	dma_release_channel(si->dma_rx.chan);
 	free_irq(dev->irq, dev);
 
 	sa1100_set_power(si, 0);
@@ -888,11 +920,15 @@ static int sa1100_irda_probe(struct platform_device *pdev)
 	struct net_device *dev;
 	struct sa1100_irda *si;
 	unsigned int baudrate_mask;
-	int err;
+	int err, irq;
 
 	if (!pdev->dev.platform_data)
 		return -EINVAL;
 
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0)
+		return irq < 0 ? irq : -ENXIO;
+
 	err = request_mem_region(__PREG(Ser2UTCR0), 0x24, "IrDA") ? 0 : -EBUSY;
 	if (err)
 		goto err_mem_1;
@@ -907,22 +943,27 @@ static int sa1100_irda_probe(struct platform_device *pdev)
 	if (!dev)
 		goto err_mem_4;
 
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
 	si = netdev_priv(dev);
 	si->dev = &pdev->dev;
 	si->pdata = pdev->dev.platform_data;
 
+	sg_init_table(&si->dma_rx.sg, 1);
+	sg_init_table(&si->dma_tx.sg, 1);
+
 	/*
 	 * Initialise the HP-SIR buffers
 	 */
 	err = sa1100_irda_init_iobuf(&si->rx_buff, 14384);
 	if (err)
 		goto err_mem_5;
-	err = sa1100_irda_init_iobuf(&si->tx_buff, 4000);
+	err = sa1100_irda_init_iobuf(&si->tx_buff, IRDA_SIR_MAX_FRAME);
 	if (err)
 		goto err_mem_5;
 
 	dev->netdev_ops	= &sa1100_irda_netdev_ops;
-	dev->irq	= IRQ_Ser2ICP;
+	dev->irq	= irq;
 
 	irda_init_max_qos_capabilies(&si->qos);
 
@@ -996,6 +1037,74 @@ static int sa1100_irda_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM
+/*
+ * Suspend the IrDA interface.
+ */
+static int sa1100_irda_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct net_device *dev = platform_get_drvdata(pdev);
+	struct sa1100_irda *si;
+
+	if (!dev)
+		return 0;
+
+	si = netdev_priv(dev);
+	if (si->open) {
+		/*
+		 * Stop the transmit queue
+		 */
+		netif_device_detach(dev);
+		disable_irq(dev->irq);
+		sa1100_irda_shutdown(si);
+		__sa1100_irda_set_power(si, 0);
+	}
+
+	return 0;
+}
+
+/*
+ * Resume the IrDA interface.
+ */
+static int sa1100_irda_resume(struct platform_device *pdev)
+{
+	struct net_device *dev = platform_get_drvdata(pdev);
+	struct sa1100_irda *si;
+
+	if (!dev)
+		return 0;
+
+	si = netdev_priv(dev);
+	if (si->open) {
+		/*
+		 * If we missed a speed change, initialise at the new speed
+		 * directly.  It is debatable whether this is actually
+		 * required, but in the interests of continuing from where
+		 * we left off it is desirable.  The converse argument is
+		 * that we should re-negotiate at 9600 baud again.
+		 */
+		if (si->newspeed) {
+			si->speed = si->newspeed;
+			si->newspeed = 0;
+		}
+
+		sa1100_irda_startup(si);
+		__sa1100_irda_set_power(si, si->power);
+		enable_irq(dev->irq);
+
+		/*
+		 * This automatically wakes up the queue
+		 */
+		netif_device_attach(dev);
+	}
+
+	return 0;
+}
+#else
+#define sa1100_irda_suspend	NULL
+#define sa1100_irda_resume	NULL
+#endif
+
 static struct platform_driver sa1100ir_driver = {
 	.probe		= sa1100_irda_probe,
 	.remove		= sa1100_irda_remove,
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index b71998d0b5b4..32eb94ece6c1 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -41,7 +41,6 @@
 #include <linux/in.h>
 #include <linux/init.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 0856e1b7a849..f08c85acf761 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -162,7 +162,8 @@ static int ip101a_g_config_init(struct phy_device *phydev)
 	/* Enable Auto Power Saving mode */
 	c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
 	c |= IP101A_G_APS_ON;
-	return c;
+
+	return phy_write(phydev, IP10XX_SPEC_CTRL_STATUS, c);
 }
 
 static int ip175c_read_status(struct phy_device *phydev)
diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c
index 1a5a316cc968..bed62d9c53c8 100644
--- a/drivers/net/plip/plip.c
+++ b/drivers/net/plip/plip.c
@@ -113,7 +113,6 @@ static const char version[] = "NET3 PLIP version 2.4-parport gniibe@mri.co.jp\n"
 
 #include <net/neighbour.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/byteorder.h>
 
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 159da2905fe9..33f8c51968b6 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -235,7 +235,7 @@ struct ppp_net {
 /* Prototypes. */
 static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 			struct file *file, unsigned int cmd, unsigned long arg);
-static void ppp_xmit_process(struct ppp *ppp);
+static int ppp_xmit_process(struct ppp *ppp);
 static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb);
 static void ppp_push(struct ppp *ppp);
 static void ppp_channel_push(struct channel *pch);
@@ -968,9 +968,9 @@ ppp_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	proto = npindex_to_proto[npi];
 	put_unaligned_be16(proto, pp);
 
-	netif_stop_queue(dev);
 	skb_queue_tail(&ppp->file.xq, skb);
-	ppp_xmit_process(ppp);
+	if (!ppp_xmit_process(ppp))
+		netif_stop_queue(dev);
 	return NETDEV_TX_OK;
 
  outf:
@@ -1048,10 +1048,11 @@ static void ppp_setup(struct net_device *dev)
  * Called to do any work queued up on the transmit side
  * that can now be done.
  */
-static void
+static int
 ppp_xmit_process(struct ppp *ppp)
 {
 	struct sk_buff *skb;
+	int ret = 0;
 
 	ppp_xmit_lock(ppp);
 	if (!ppp->closing) {
@@ -1061,10 +1062,13 @@ ppp_xmit_process(struct ppp *ppp)
 			ppp_send_frame(ppp, skb);
 		/* If there's no work left to do, tell the core net
 		   code that we can accept some more. */
-		if (!ppp->xmit_pending && !skb_peek(&ppp->file.xq))
+		if (!ppp->xmit_pending && !skb_peek(&ppp->file.xq)) {
 			netif_wake_queue(ppp->dev);
+			ret = 1;
+		}
 	}
 	ppp_xmit_unlock(ppp);
+	return ret;
 }
 
 static inline struct sk_buff *
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index a57f05726b57..91d25888a1b9 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -375,8 +375,8 @@ static void rionet_remove(struct rio_dev *rdev)
 	struct net_device *ndev = rio_get_drvdata(rdev);
 	struct rionet_peer *peer, *tmp;
 
-	free_pages((unsigned long)rionet_active, rdev->net->hport->sys_size ?
-					__fls(sizeof(void *)) + 4 : 0);
+	free_pages((unsigned long)rionet_active, get_order(sizeof(void *) *
+			RIO_MAX_ROUTE_ENTRIES(rdev->net->hport->sys_size)));
 	unregister_netdev(ndev);
 	free_netdev(ndev);
 
@@ -432,15 +432,16 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev)
 	int rc = 0;
 	struct rionet_private *rnet;
 	u16 device_id;
+	const size_t rionet_active_bytes = sizeof(void *) *
+				RIO_MAX_ROUTE_ENTRIES(mport->sys_size);
 
 	rionet_active = (struct rio_dev **)__get_free_pages(GFP_KERNEL,
-			mport->sys_size ? __fls(sizeof(void *)) + 4 : 0);
+			get_order(rionet_active_bytes));
 	if (!rionet_active) {
 		rc = -ENOMEM;
 		goto out;
 	}
-	memset((void *)rionet_active, 0, sizeof(void *) *
-				RIO_MAX_ROUTE_ENTRIES(mport->sys_size));
+	memset((void *)rionet_active, 0, rionet_active_bytes);
 
 	/* Set up private area */
 	rnet = netdev_priv(ndev);
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 0a0a6643cf3a..1252d9c726a7 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -75,7 +75,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <linux/timer.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <net/checksum.h>
 #include <asm/unaligned.h>
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 69345dfae0fd..d4c9db3da22a 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -64,7 +64,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/sched.h>
diff --git a/drivers/net/tokenring/3c359.c b/drivers/net/tokenring/3c359.c
index d7c292aa76b1..b15ac81d46fa 100644
--- a/drivers/net/tokenring/3c359.c
+++ b/drivers/net/tokenring/3c359.c
@@ -68,7 +68,6 @@
 #include <net/checksum.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "3c359.h"
 
diff --git a/drivers/net/tokenring/abyss.c b/drivers/net/tokenring/abyss.c
index 515f122777ab..b715e6b444da 100644
--- a/drivers/net/tokenring/abyss.c
+++ b/drivers/net/tokenring/abyss.c
@@ -33,7 +33,6 @@
 #include <linux/netdevice.h>
 #include <linux/trdevice.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/tokenring/ibmtr_cs.c b/drivers/net/tokenring/ibmtr_cs.c
index 91b684630fc5..356e28e4881b 100644
--- a/drivers/net/tokenring/ibmtr_cs.c
+++ b/drivers/net/tokenring/ibmtr_cs.c
@@ -63,7 +63,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #define PCMCIA
 #include "ibmtr.c"
diff --git a/drivers/net/tokenring/lanstreamer.c b/drivers/net/tokenring/lanstreamer.c
index 8d71e0d29062..3e4b4f091113 100644
--- a/drivers/net/tokenring/lanstreamer.c
+++ b/drivers/net/tokenring/lanstreamer.c
@@ -127,7 +127,6 @@
 #include <net/checksum.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "lanstreamer.h"
 
diff --git a/drivers/net/tokenring/madgemc.c b/drivers/net/tokenring/madgemc.c
index 1cdc034f6aec..28adcdf3b14c 100644
--- a/drivers/net/tokenring/madgemc.c
+++ b/drivers/net/tokenring/madgemc.c
@@ -28,7 +28,6 @@ static const char version[] = "madgemc.c: v0.91 23/01/2000 by Adam Fritzler\n";
 #include <linux/netdevice.h>
 #include <linux/trdevice.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/tokenring/olympic.c b/drivers/net/tokenring/olympic.c
index fd8dce90c957..0e234741cc79 100644
--- a/drivers/net/tokenring/olympic.c
+++ b/drivers/net/tokenring/olympic.c
@@ -106,7 +106,6 @@
 #include <net/net_namespace.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "olympic.h"
 
diff --git a/drivers/net/tokenring/proteon.c b/drivers/net/tokenring/proteon.c
index 8d362e64a40e..62d90e40f9ec 100644
--- a/drivers/net/tokenring/proteon.c
+++ b/drivers/net/tokenring/proteon.c
@@ -31,7 +31,6 @@ static const char version[] = "proteon.c: v1.00 02/01/2003 by Jochen Friedrich\n
 #include <linux/trdevice.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/pci.h>
diff --git a/drivers/net/tokenring/skisa.c b/drivers/net/tokenring/skisa.c
index 46db5c5395b2..ee11e93dc30e 100644
--- a/drivers/net/tokenring/skisa.c
+++ b/drivers/net/tokenring/skisa.c
@@ -38,7 +38,6 @@ static const char version[] = "skisa.c: v1.03 09/12/2002 by Jochen Friedrich\n";
 #include <linux/trdevice.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/pci.h>
diff --git a/drivers/net/tokenring/smctr.c b/drivers/net/tokenring/smctr.c
index 029846a98636..cb35fb79e016 100644
--- a/drivers/net/tokenring/smctr.c
+++ b/drivers/net/tokenring/smctr.c
@@ -49,7 +49,6 @@
 #include <linux/bitops.h>
 #include <linux/firmware.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
diff --git a/drivers/net/tokenring/tms380tr.c b/drivers/net/tokenring/tms380tr.c
index 102f896bbc58..be4813e0366c 100644
--- a/drivers/net/tokenring/tms380tr.c
+++ b/drivers/net/tokenring/tms380tr.c
@@ -98,7 +98,6 @@ static const char version[] = "tms380tr.c: v1.10 30/12/2002 by Christoph Goos, A
 #include <linux/firmware.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
diff --git a/drivers/net/tokenring/tmspci.c b/drivers/net/tokenring/tmspci.c
index d3e788a9cd1c..fb9918da5792 100644
--- a/drivers/net/tokenring/tmspci.c
+++ b/drivers/net/tokenring/tmspci.c
@@ -34,7 +34,6 @@
 #include <linux/netdevice.h>
 #include <linux/trdevice.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 74d7f76d14a3..bb8c72c79c6f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -69,7 +69,6 @@
 #include <net/rtnetlink.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 /* Uncomment to enable debugging */
diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c
index 439690be519f..685a4e22c768 100644
--- a/drivers/net/usb/cdc_eem.c
+++ b/drivers/net/usb/cdc_eem.c
@@ -93,6 +93,7 @@ static int eem_bind(struct usbnet *dev, struct usb_interface *intf)
 	/* no jumbogram (16K) support for now */
 
 	dev->net->hard_header_len += EEM_HEAD + ETH_FCS_LEN;
+	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
 
 	return 0;
 }
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 6dda2fe5b15b..d363b31053da 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -85,32 +85,6 @@
 #define INT_CRERR_CNT		0x06
 #define INT_COL_CNT		0x07
 
-/* Transmit status register errors */
-#define TSR_ECOL		(1<<5)
-#define TSR_LCOL		(1<<4)
-#define TSR_LOSS_CRS		(1<<3)
-#define TSR_JBR			(1<<2)
-#define TSR_ERRORS		(TSR_ECOL | TSR_LCOL | TSR_LOSS_CRS | TSR_JBR)
-/* Receive status register errors */
-#define RSR_CRC			(1<<2)
-#define RSR_FAE			(1<<1)
-#define RSR_ERRORS		(RSR_CRC | RSR_FAE)
-
-/* Media status register definitions */
-#define MSR_DUPLEX		(1<<4)
-#define MSR_SPEED		(1<<3)
-#define MSR_LINK		(1<<2)
-
-/* Interrupt pipe data */
-#define INT_TSR			0x00
-#define INT_RSR			0x01
-#define INT_MSR			0x02
-#define INT_WAKSR		0x03
-#define INT_TXOK_CNT		0x04
-#define INT_RXLOST_CNT		0x05
-#define INT_CRERR_CNT		0x06
-#define INT_COL_CNT		0x07
-
 
 #define	RTL8150_MTU		1540
 #define	RTL8150_TX_TIMEOUT	(HZ)
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 423eb26386c8..d70ede7a7f96 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -290,8 +290,8 @@ config FARSYNC
 	  Frame Relay or X.25/LAPB.
 
 	  If you want the module to be automatically loaded when the interface
-	  is referenced then you should add "alias hdlcX farsync" to
-	  /etc/modprobe.conf for each interface, where X is 0, 1, 2, ..., or
+	  is referenced then you should add "alias hdlcX farsync" to a file
+	  in /etc/modprobe.d/ for each interface, where X is 0, 1, 2, ..., or
 	  simply use "alias hdlc* farsync" to indicate all of them.
 
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 48ab38a34c5a..147614ed86aa 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -50,7 +50,6 @@
 
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/uaccess.h>
diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c
index fe8d060d8fff..c676de7de024 100644
--- a/drivers/net/wan/dscc4.c
+++ b/drivers/net/wan/dscc4.c
@@ -93,7 +93,6 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/cache.h>
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
diff --git a/drivers/net/wan/hd64570.c b/drivers/net/wan/hd64570.c
index 33b67d88fceb..cf4903355a34 100644
--- a/drivers/net/wan/hd64570.c
+++ b/drivers/net/wan/hd64570.c
@@ -40,7 +40,6 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include "hd64570.h"
 
diff --git a/drivers/net/wan/hd64572.c b/drivers/net/wan/hd64572.c
index efc0db101183..e2779faa6c4f 100644
--- a/drivers/net/wan/hd64572.c
+++ b/drivers/net/wan/hd64572.c
@@ -40,7 +40,6 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include "hd64572.h"
 
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 7beeb9b88a3b..a73b49eb87e3 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -35,7 +35,6 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index c8531612eea9..de3bbf43fc5a 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -54,7 +54,6 @@
 #include <linux/sdla.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/uaccess.h>
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index e862369b4a6d..d7a65e141d1a 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -18,7 +18,6 @@
 
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/net/wimax/i2400m/debugfs.c
index 129ba36bd04d..4b66ab1d0e5c 100644
--- a/drivers/net/wimax/i2400m/debugfs.c
+++ b/drivers/net/wimax/i2400m/debugfs.c
@@ -53,17 +53,6 @@ struct dentry *debugfs_create_netdev_queue_stopped(
 				   &fops_netdev_queue_stopped);
 }
 
-
-/*
- * inode->i_private has the @data argument to debugfs_create_file()
- */
-static
-int i2400m_stats_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
 /*
  * We don't allow partial reads of this file, as then the reader would
  * get weirdly confused data as it is updated.
@@ -117,7 +106,7 @@ ssize_t i2400m_rx_stats_write(struct file *filp, const char __user *buffer,
 static
 const struct file_operations i2400m_rx_stats_fops = {
 	.owner =	THIS_MODULE,
-	.open =		i2400m_stats_open,
+	.open =		simple_open,
 	.read =		i2400m_rx_stats_read,
 	.write =	i2400m_rx_stats_write,
 	.llseek =	default_llseek,
@@ -170,7 +159,7 @@ ssize_t i2400m_tx_stats_write(struct file *filp, const char __user *buffer,
 static
 const struct file_operations i2400m_tx_stats_fops = {
 	.owner =	THIS_MODULE,
-	.open =		i2400m_stats_open,
+	.open =		simple_open,
 	.read =		i2400m_tx_stats_read,
 	.write =	i2400m_tx_stats_write,
 	.llseek =	default_llseek,
diff --git a/drivers/net/wireless/airo.c b/drivers/net/wireless/airo.c
index ddc061dd150c..520a4b2eb9cc 100644
--- a/drivers/net/wireless/airo.c
+++ b/drivers/net/wireless/airo.c
@@ -37,7 +37,6 @@
 #include <linux/scatterlist.h>
 #include <linux/crypto.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/wireless/airo_cs.c b/drivers/net/wireless/airo_cs.c
index c983c10e0f6a..630577dd3a7a 100644
--- a/drivers/net/wireless/airo_cs.c
+++ b/drivers/net/wireless/airo_cs.c
@@ -37,7 +37,6 @@
 #include <pcmcia/ds.h>
 
 #include <linux/io.h>
-#include <asm/system.h>
 
 #include "airo.h"
 
diff --git a/drivers/net/wireless/ath/ath5k/debug.c b/drivers/net/wireless/ath/ath5k/debug.c
index 8c5ce8b0c734..e5e8f45d86ac 100644
--- a/drivers/net/wireless/ath/ath5k/debug.c
+++ b/drivers/net/wireless/ath/ath5k/debug.c
@@ -71,13 +71,6 @@ static unsigned int ath5k_debug;
 module_param_named(debug, ath5k_debug, uint, 0);
 
 
-static int ath5k_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
-
 /* debugfs: registers */
 
 struct reg {
@@ -265,7 +258,7 @@ static ssize_t write_file_beacon(struct file *file,
 static const struct file_operations fops_beacon = {
 	.read = read_file_beacon,
 	.write = write_file_beacon,
-	.open = ath5k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -285,7 +278,7 @@ static ssize_t write_file_reset(struct file *file,
 
 static const struct file_operations fops_reset = {
 	.write = write_file_reset,
-	.open = ath5k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = noop_llseek,
 };
@@ -365,7 +358,7 @@ static ssize_t write_file_debug(struct file *file,
 static const struct file_operations fops_debug = {
 	.read = read_file_debug,
 	.write = write_file_debug,
-	.open = ath5k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -477,7 +470,7 @@ static ssize_t write_file_antenna(struct file *file,
 static const struct file_operations fops_antenna = {
 	.read = read_file_antenna,
 	.write = write_file_antenna,
-	.open = ath5k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -532,7 +525,7 @@ static ssize_t read_file_misc(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_misc = {
 	.read = read_file_misc,
-	.open = ath5k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 };
 
@@ -647,7 +640,7 @@ static ssize_t write_file_frameerrors(struct file *file,
 static const struct file_operations fops_frameerrors = {
 	.read = read_file_frameerrors,
 	.write = write_file_frameerrors,
-	.open = ath5k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -810,7 +803,7 @@ static ssize_t write_file_ani(struct file *file,
 static const struct file_operations fops_ani = {
 	.read = read_file_ani,
 	.write = write_file_ani,
-	.open = ath5k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -881,7 +874,7 @@ static ssize_t write_file_queue(struct file *file,
 static const struct file_operations fops_queue = {
 	.read = read_file_queue,
 	.write = write_file_queue,
-	.open = ath5k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
diff --git a/drivers/net/wireless/ath/ath6kl/debug.c b/drivers/net/wireless/ath/ath6kl/debug.c
index 552adb3f80d0..d01403a263ff 100644
--- a/drivers/net/wireless/ath/ath6kl/debug.c
+++ b/drivers/net/wireless/ath/ath6kl/debug.c
@@ -217,12 +217,6 @@ void dump_cred_dist_stats(struct htc_target *target)
 		   target->credit_info->cur_free_credits);
 }
 
-static int ath6kl_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 void ath6kl_debug_war(struct ath6kl *ar, enum ath6kl_war war)
 {
 	switch (war) {
@@ -263,7 +257,7 @@ static ssize_t read_file_war_stats(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_war_stats = {
 	.read = read_file_war_stats,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -488,7 +482,7 @@ static ssize_t ath6kl_fwlog_mask_write(struct file *file,
 }
 
 static const struct file_operations fops_fwlog_mask = {
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.read = ath6kl_fwlog_mask_read,
 	.write = ath6kl_fwlog_mask_write,
 	.owner = THIS_MODULE,
@@ -634,7 +628,7 @@ static ssize_t read_file_tgt_stats(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_tgt_stats = {
 	.read = read_file_tgt_stats,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -699,7 +693,7 @@ static ssize_t read_file_credit_dist_stats(struct file *file,
 
 static const struct file_operations fops_credit_dist_stats = {
 	.read = read_file_credit_dist_stats,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -802,7 +796,7 @@ static ssize_t ath6kl_endpoint_stats_write(struct file *file,
 }
 
 static const struct file_operations fops_endpoint_stats = {
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.read = ath6kl_endpoint_stats_read,
 	.write = ath6kl_endpoint_stats_write,
 	.owner = THIS_MODULE,
@@ -875,7 +869,7 @@ static ssize_t ath6kl_regread_write(struct file *file,
 static const struct file_operations fops_diag_reg_read = {
 	.read = ath6kl_regread_read,
 	.write = ath6kl_regread_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -999,7 +993,7 @@ static ssize_t ath6kl_lrssi_roam_read(struct file *file,
 static const struct file_operations fops_lrssi_roam_threshold = {
 	.read = ath6kl_lrssi_roam_read,
 	.write = ath6kl_lrssi_roam_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1061,7 +1055,7 @@ static ssize_t ath6kl_regwrite_write(struct file *file,
 static const struct file_operations fops_diag_reg_write = {
 	.read = ath6kl_regwrite_read,
 	.write = ath6kl_regwrite_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1166,7 +1160,7 @@ static ssize_t ath6kl_roam_table_read(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_roam_table = {
 	.read = ath6kl_roam_table_read,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1204,7 +1198,7 @@ static ssize_t ath6kl_force_roam_write(struct file *file,
 
 static const struct file_operations fops_force_roam = {
 	.write = ath6kl_force_roam_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1244,7 +1238,7 @@ static ssize_t ath6kl_roam_mode_write(struct file *file,
 
 static const struct file_operations fops_roam_mode = {
 	.write = ath6kl_roam_mode_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1286,7 +1280,7 @@ static ssize_t ath6kl_keepalive_write(struct file *file,
 }
 
 static const struct file_operations fops_keepalive = {
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.read = ath6kl_keepalive_read,
 	.write = ath6kl_keepalive_write,
 	.owner = THIS_MODULE,
@@ -1331,7 +1325,7 @@ static ssize_t ath6kl_disconnect_timeout_write(struct file *file,
 }
 
 static const struct file_operations fops_disconnect_timeout = {
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.read = ath6kl_disconnect_timeout_read,
 	.write = ath6kl_disconnect_timeout_write,
 	.owner = THIS_MODULE,
@@ -1512,7 +1506,7 @@ static ssize_t ath6kl_create_qos_write(struct file *file,
 
 static const struct file_operations fops_create_qos = {
 	.write = ath6kl_create_qos_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1560,7 +1554,7 @@ static ssize_t ath6kl_delete_qos_write(struct file *file,
 
 static const struct file_operations fops_delete_qos = {
 	.write = ath6kl_delete_qos_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1593,7 +1587,7 @@ static ssize_t ath6kl_bgscan_int_write(struct file *file,
 
 static const struct file_operations fops_bgscan_int = {
 	.write = ath6kl_bgscan_int_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1651,7 +1645,7 @@ static ssize_t ath6kl_listen_int_read(struct file *file,
 static const struct file_operations fops_listen_int = {
 	.read = ath6kl_listen_int_read,
 	.write = ath6kl_listen_int_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1711,7 +1705,7 @@ static ssize_t ath6kl_power_params_write(struct file *file,
 
 static const struct file_operations fops_power_params = {
 	.write = ath6kl_power_params_write,
-	.open = ath6kl_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index 35d1c8e91d1c..ff47b32ecaf4 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -26,11 +26,6 @@
 #define REG_READ_D(_ah, _reg) \
 	ath9k_hw_common(_ah)->ops->read((_ah), (_reg))
 
-static int ath9k_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
 
 static ssize_t ath9k_debugfs_read_buf(struct file *file, char __user *user_buf,
 				      size_t count, loff_t *ppos)
@@ -83,7 +78,7 @@ static ssize_t write_file_debug(struct file *file, const char __user *user_buf,
 static const struct file_operations fops_debug = {
 	.read = read_file_debug,
 	.write = write_file_debug,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -129,7 +124,7 @@ static ssize_t write_file_tx_chainmask(struct file *file, const char __user *use
 static const struct file_operations fops_tx_chainmask = {
 	.read = read_file_tx_chainmask,
 	.write = write_file_tx_chainmask,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -172,7 +167,7 @@ static ssize_t write_file_rx_chainmask(struct file *file, const char __user *use
 static const struct file_operations fops_rx_chainmask = {
 	.read = read_file_rx_chainmask,
 	.write = write_file_rx_chainmask,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -223,7 +218,7 @@ static ssize_t write_file_disable_ani(struct file *file,
 static const struct file_operations fops_disable_ani = {
 	.read = read_file_disable_ani,
 	.write = write_file_disable_ani,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -324,7 +319,7 @@ static ssize_t read_file_dma(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_dma = {
 	.read = read_file_dma,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -446,7 +441,7 @@ static ssize_t read_file_interrupt(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_interrupt = {
 	.read = read_file_interrupt,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -852,28 +847,28 @@ void ath_debug_stat_tx(struct ath_softc *sc, struct ath_buf *bf,
 
 static const struct file_operations fops_xmit = {
 	.read = read_file_xmit,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
 
 static const struct file_operations fops_stations = {
 	.read = read_file_stations,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
 
 static const struct file_operations fops_misc = {
 	.read = read_file_misc,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
 
 static const struct file_operations fops_reset = {
 	.read = read_file_reset,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1016,7 +1011,7 @@ void ath_debug_stat_rx(struct ath_softc *sc, struct ath_rx_status *rs)
 
 static const struct file_operations fops_recv = {
 	.read = read_file_recv,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1055,7 +1050,7 @@ static ssize_t write_file_regidx(struct file *file, const char __user *user_buf,
 static const struct file_operations fops_regidx = {
 	.read = read_file_regidx,
 	.write = write_file_regidx,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1102,7 +1097,7 @@ static ssize_t write_file_regval(struct file *file, const char __user *user_buf,
 static const struct file_operations fops_regval = {
 	.read = read_file_regval,
 	.write = write_file_regval,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1191,7 +1186,7 @@ static ssize_t read_file_dump_nfcal(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_dump_nfcal = {
 	.read = read_file_dump_nfcal,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1219,7 +1214,7 @@ static ssize_t read_file_base_eeprom(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_base_eeprom = {
 	.read = read_file_base_eeprom,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1247,7 +1242,7 @@ static ssize_t read_file_modal_eeprom(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_modal_eeprom = {
 	.read = read_file_modal_eeprom,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
diff --git a/drivers/net/wireless/ath/ath9k/dfs_debug.c b/drivers/net/wireless/ath/ath9k/dfs_debug.c
index 106d031d834a..4364c103ed33 100644
--- a/drivers/net/wireless/ath/ath9k/dfs_debug.c
+++ b/drivers/net/wireless/ath/ath9k/dfs_debug.c
@@ -60,16 +60,9 @@ static ssize_t read_file_dfs(struct file *file, char __user *user_buf,
 	return retval;
 }
 
-static int ath9k_dfs_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-
-	return 0;
-}
-
 static const struct file_operations fops_dfs_stats = {
 	.read = read_file_dfs,
-	.open = ath9k_dfs_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
index d3ff33c71aa5..3035deb7a0cd 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
@@ -16,12 +16,6 @@
 
 #include "htc.h"
 
-static int ath9k_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t read_file_tgt_int_stats(struct file *file, char __user *user_buf,
 				       size_t count, loff_t *ppos)
 {
@@ -75,7 +69,7 @@ static ssize_t read_file_tgt_int_stats(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_tgt_int_stats = {
 	.read = read_file_tgt_int_stats,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -145,7 +139,7 @@ static ssize_t read_file_tgt_tx_stats(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_tgt_tx_stats = {
 	.read = read_file_tgt_tx_stats,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -191,7 +185,7 @@ static ssize_t read_file_tgt_rx_stats(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_tgt_rx_stats = {
 	.read = read_file_tgt_rx_stats,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -243,7 +237,7 @@ static ssize_t read_file_xmit(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_xmit = {
 	.read = read_file_xmit,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -364,7 +358,7 @@ static ssize_t read_file_recv(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_recv = {
 	.read = read_file_recv,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -399,7 +393,7 @@ static ssize_t read_file_slot(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_slot = {
 	.read = read_file_slot,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -446,7 +440,7 @@ static ssize_t read_file_queue(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_queue = {
 	.read = read_file_queue,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -487,7 +481,7 @@ static ssize_t write_file_debug(struct file *file, const char __user *user_buf,
 static const struct file_operations fops_debug = {
 	.read = read_file_debug,
 	.write = write_file_debug,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -636,7 +630,7 @@ static ssize_t read_file_base_eeprom(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_base_eeprom = {
 	.read = read_file_base_eeprom,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -917,7 +911,7 @@ static ssize_t read_file_modal_eeprom(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_modal_eeprom = {
 	.read = read_file_modal_eeprom,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c
index 4f848493fece..08bb45532701 100644
--- a/drivers/net/wireless/ath/ath9k/rc.c
+++ b/drivers/net/wireless/ath/ath9k/rc.c
@@ -1480,12 +1480,6 @@ static void ath_rate_update(void *priv, struct ieee80211_supported_band *sband,
 
 #ifdef CONFIG_ATH9K_DEBUGFS
 
-static int ath9k_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t read_file_rcstat(struct file *file, char __user *user_buf,
 				size_t count, loff_t *ppos)
 {
@@ -1553,7 +1547,7 @@ static ssize_t read_file_rcstat(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_rcstat = {
 	.read = read_file_rcstat,
-	.open = ath9k_debugfs_open,
+	.open = simple_open,
 	.owner = THIS_MODULE
 };
 
diff --git a/drivers/net/wireless/ath/carl9170/debug.c b/drivers/net/wireless/ath/carl9170/debug.c
index 3c164226687f..93fe6003a493 100644
--- a/drivers/net/wireless/ath/carl9170/debug.c
+++ b/drivers/net/wireless/ath/carl9170/debug.c
@@ -48,11 +48,6 @@
 #define ADD(buf, off, max, fmt, args...)				\
 	off += snprintf(&buf[off], max - off, fmt, ##args);
 
-static int carl9170_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
 
 struct carl9170_debugfs_fops {
 	unsigned int read_bufsize;
@@ -178,7 +173,7 @@ static const struct carl9170_debugfs_fops carl_debugfs_##name ##_ops = {\
 	.attr = _attr,							\
 	.req_dev_state = _dstate,					\
 	.fops = {							\
-		.open	= carl9170_debugfs_open,			\
+		.open	= simple_open,					\
 		.read	= carl9170_debugfs_read,			\
 		.write	= carl9170_debugfs_write,			\
 		.owner	= THIS_MODULE					\
diff --git a/drivers/net/wireless/atmel.c b/drivers/net/wireless/atmel.c
index 3010cee7b95a..6c87a823f5a9 100644
--- a/drivers/net/wireless/atmel.c
+++ b/drivers/net/wireless/atmel.c
@@ -50,7 +50,6 @@
 #include <linux/timer.h>
 #include <asm/byteorder.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/wireless/atmel_cs.c b/drivers/net/wireless/atmel_cs.c
index ec295c4f677d..ded03d226a71 100644
--- a/drivers/net/wireless/atmel_cs.c
+++ b/drivers/net/wireless/atmel_cs.c
@@ -48,7 +48,6 @@
 #include <pcmcia/ciscode.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <linux/wireless.h>
 
 #include "atmel.h"
diff --git a/drivers/net/wireless/b43/debugfs.c b/drivers/net/wireless/b43/debugfs.c
index e751fdee89b2..e807bd930647 100644
--- a/drivers/net/wireless/b43/debugfs.c
+++ b/drivers/net/wireless/b43/debugfs.c
@@ -500,12 +500,6 @@ out:
 
 #undef fappend
 
-static int b43_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t b43_debugfs_read(struct file *file, char __user *userbuf,
 				size_t count, loff_t *ppos)
 {
@@ -624,7 +618,7 @@ out_unlock:
 		.read	= _read,				\
 		.write	= _write,				\
 		.fops	= {					\
-			.open	= b43_debugfs_open,		\
+			.open	= simple_open,			\
 			.read	= b43_debugfs_read,		\
 			.write	= b43_debugfs_write,		\
 			.llseek = generic_file_llseek,		\
diff --git a/drivers/net/wireless/b43legacy/debugfs.c b/drivers/net/wireless/b43legacy/debugfs.c
index 5e28ad0d6d17..1965edb765a2 100644
--- a/drivers/net/wireless/b43legacy/debugfs.c
+++ b/drivers/net/wireless/b43legacy/debugfs.c
@@ -197,12 +197,6 @@ static int restart_write_file(struct b43legacy_wldev *dev, const char *buf, size
 
 #undef fappend
 
-static int b43legacy_debugfs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t b43legacy_debugfs_read(struct file *file, char __user *userbuf,
 				size_t count, loff_t *ppos)
 {
@@ -331,7 +325,7 @@ out_unlock:
 		.read	= _read,				\
 		.write	= _write,				\
 		.fops	= {					\
-			.open	= b43legacy_debugfs_open,		\
+			.open	= simple_open,				\
 			.read	= b43legacy_debugfs_read,		\
 			.write	= b43legacy_debugfs_write,		\
 			.llseek = generic_file_llseek,			\
diff --git a/drivers/net/wireless/iwlegacy/3945-rs.c b/drivers/net/wireless/iwlegacy/3945-rs.c
index 70bee1a4d876..4b10157d8686 100644
--- a/drivers/net/wireless/iwlegacy/3945-rs.c
+++ b/drivers/net/wireless/iwlegacy/3945-rs.c
@@ -821,12 +821,6 @@ out:
 }
 
 #ifdef CONFIG_MAC80211_DEBUGFS
-static int
-il3945_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
 
 static ssize_t
 il3945_sta_dbgfs_stats_table_read(struct file *file, char __user *user_buf,
@@ -862,7 +856,7 @@ il3945_sta_dbgfs_stats_table_read(struct file *file, char __user *user_buf,
 
 static const struct file_operations rs_sta_dbgfs_stats_table_ops = {
 	.read = il3945_sta_dbgfs_stats_table_read,
-	.open = il3945_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
diff --git a/drivers/net/wireless/iwlegacy/4965-rs.c b/drivers/net/wireless/iwlegacy/4965-rs.c
index d7e2856e41d3..11ab1247fae1 100644
--- a/drivers/net/wireless/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/iwlegacy/4965-rs.c
@@ -2518,12 +2518,6 @@ il4965_rs_free_sta(void *il_r, struct ieee80211_sta *sta, void *il_sta)
 }
 
 #ifdef CONFIG_MAC80211_DEBUGFS
-static int
-il4965_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
 
 static void
 il4965_rs_dbgfs_set_mcs(struct il_lq_sta *lq_sta, u32 * rate_n_flags, int idx)
@@ -2695,7 +2689,7 @@ il4965_rs_sta_dbgfs_scale_table_read(struct file *file, char __user *user_buf,
 static const struct file_operations rs_sta_dbgfs_scale_table_ops = {
 	.write = il4965_rs_sta_dbgfs_scale_table_write,
 	.read = il4965_rs_sta_dbgfs_scale_table_read,
-	.open = il4965_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -2740,7 +2734,7 @@ il4965_rs_sta_dbgfs_stats_table_read(struct file *file, char __user *user_buf,
 
 static const struct file_operations rs_sta_dbgfs_stats_table_ops = {
 	.read = il4965_rs_sta_dbgfs_stats_table_read,
-	.open = il4965_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -2768,7 +2762,7 @@ il4965_rs_sta_dbgfs_rate_scale_data_read(struct file *file,
 
 static const struct file_operations rs_sta_dbgfs_rate_scale_data_ops = {
 	.read = il4965_rs_sta_dbgfs_rate_scale_data_read,
-	.open = il4965_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
diff --git a/drivers/net/wireless/iwlegacy/debug.c b/drivers/net/wireless/iwlegacy/debug.c
index 229849150aac..eff26501d60a 100644
--- a/drivers/net/wireless/iwlegacy/debug.c
+++ b/drivers/net/wireless/iwlegacy/debug.c
@@ -160,18 +160,12 @@ static ssize_t il_dbgfs_##name##_write(struct file *file,              \
 					const char __user *user_buf,    \
 					size_t count, loff_t *ppos);
 
-static int
-il_dbgfs_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
 
 #define DEBUGFS_READ_FILE_OPS(name)				\
 	DEBUGFS_READ_FUNC(name);				\
 static const struct file_operations il_dbgfs_##name##_ops = {	\
 	.read = il_dbgfs_##name##_read,				\
-	.open = il_dbgfs_open_file_generic,			\
+	.open = simple_open,					\
 	.llseek = generic_file_llseek,				\
 };
 
@@ -179,7 +173,7 @@ static const struct file_operations il_dbgfs_##name##_ops = {	\
 	DEBUGFS_WRITE_FUNC(name);				\
 static const struct file_operations il_dbgfs_##name##_ops = {	\
 	.write = il_dbgfs_##name##_write,			\
-	.open = il_dbgfs_open_file_generic,			\
+	.open = simple_open,					\
 	.llseek = generic_file_llseek,				\
 };
 
@@ -189,7 +183,7 @@ static const struct file_operations il_dbgfs_##name##_ops = {	\
 static const struct file_operations il_dbgfs_##name##_ops = {	\
 	.write = il_dbgfs_##name##_write,			\
 	.read = il_dbgfs_##name##_read,				\
-	.open = il_dbgfs_open_file_generic,			\
+	.open = simple_open,					\
 	.llseek = generic_file_llseek,				\
 };
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c
index 53f8c51cfcdb..7e590b349dd7 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c
@@ -3083,11 +3083,6 @@ static void rs_free_sta(void *priv_r, struct ieee80211_sta *sta,
 }
 
 #ifdef CONFIG_MAC80211_DEBUGFS
-static int open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
 static void rs_dbgfs_set_mcs(struct iwl_lq_sta *lq_sta,
 			     u32 *rate_n_flags, int index)
 {
@@ -3226,7 +3221,7 @@ static ssize_t rs_sta_dbgfs_scale_table_read(struct file *file,
 static const struct file_operations rs_sta_dbgfs_scale_table_ops = {
 	.write = rs_sta_dbgfs_scale_table_write,
 	.read = rs_sta_dbgfs_scale_table_read,
-	.open = open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 static ssize_t rs_sta_dbgfs_stats_table_read(struct file *file,
@@ -3269,7 +3264,7 @@ static ssize_t rs_sta_dbgfs_stats_table_read(struct file *file,
 
 static const struct file_operations rs_sta_dbgfs_stats_table_ops = {
 	.read = rs_sta_dbgfs_stats_table_read,
-	.open = open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -3295,7 +3290,7 @@ static ssize_t rs_sta_dbgfs_rate_scale_data_read(struct file *file,
 
 static const struct file_operations rs_sta_dbgfs_rate_scale_data_ops = {
 	.read = rs_sta_dbgfs_rate_scale_data_read,
-	.open = open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-debugfs.c b/drivers/net/wireless/iwlwifi/iwl-debugfs.c
index b7b1c04f2fba..2bbaebd99ad4 100644
--- a/drivers/net/wireless/iwlwifi/iwl-debugfs.c
+++ b/drivers/net/wireless/iwlwifi/iwl-debugfs.c
@@ -84,17 +84,11 @@ static ssize_t iwl_dbgfs_##name##_write(struct file *file,              \
 					size_t count, loff_t *ppos);
 
 
-static int iwl_dbgfs_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 #define DEBUGFS_READ_FILE_OPS(name)                                     \
 	DEBUGFS_READ_FUNC(name);                                        \
 static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 	.read = iwl_dbgfs_##name##_read,                       		\
-	.open = iwl_dbgfs_open_file_generic,                    	\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
@@ -102,7 +96,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 	DEBUGFS_WRITE_FUNC(name);                                       \
 static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 	.write = iwl_dbgfs_##name##_write,                              \
-	.open = iwl_dbgfs_open_file_generic,                    	\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
@@ -113,7 +107,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 	.write = iwl_dbgfs_##name##_write,                              \
 	.read = iwl_dbgfs_##name##_read,                                \
-	.open = iwl_dbgfs_open_file_generic,                            \
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c
index b4f796c82e1e..4d7b30d3e648 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c
+++ b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c
@@ -1898,17 +1898,11 @@ static ssize_t iwl_dbgfs_##name##_write(struct file *file,              \
 					size_t count, loff_t *ppos);
 
 
-static int iwl_dbgfs_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 #define DEBUGFS_READ_FILE_OPS(name)					\
 	DEBUGFS_READ_FUNC(name);					\
 static const struct file_operations iwl_dbgfs_##name##_ops = {		\
 	.read = iwl_dbgfs_##name##_read,				\
-	.open = iwl_dbgfs_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
@@ -1916,7 +1910,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = {		\
 	DEBUGFS_WRITE_FUNC(name);                                       \
 static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 	.write = iwl_dbgfs_##name##_write,                              \
-	.open = iwl_dbgfs_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
@@ -1926,7 +1920,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 static const struct file_operations iwl_dbgfs_##name##_ops = {		\
 	.write = iwl_dbgfs_##name##_write,				\
 	.read = iwl_dbgfs_##name##_read,				\
-	.open = iwl_dbgfs_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
diff --git a/drivers/net/wireless/iwmc3200wifi/debugfs.c b/drivers/net/wireless/iwmc3200wifi/debugfs.c
index 87eef5773a02..b6199d124bb9 100644
--- a/drivers/net/wireless/iwmc3200wifi/debugfs.c
+++ b/drivers/net/wireless/iwmc3200wifi/debugfs.c
@@ -99,12 +99,6 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_iwm_dbg_modules,
 			iwm_debugfs_u32_read, iwm_debugfs_dbg_modules_write,
 			"%llu\n");
 
-static int iwm_generic_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
 
 static ssize_t iwm_debugfs_txq_read(struct file *filp, char __user *buffer,
 				   size_t count, loff_t *ppos)
@@ -401,28 +395,28 @@ out:
 
 static const struct file_operations iwm_debugfs_txq_fops = {
 	.owner =	THIS_MODULE,
-	.open =		iwm_generic_open,
+	.open =		simple_open,
 	.read =		iwm_debugfs_txq_read,
 	.llseek =	default_llseek,
 };
 
 static const struct file_operations iwm_debugfs_tx_credit_fops = {
 	.owner =	THIS_MODULE,
-	.open =		iwm_generic_open,
+	.open =		simple_open,
 	.read =		iwm_debugfs_tx_credit_read,
 	.llseek =	default_llseek,
 };
 
 static const struct file_operations iwm_debugfs_rx_ticket_fops = {
 	.owner =	THIS_MODULE,
-	.open =		iwm_generic_open,
+	.open =		simple_open,
 	.read =		iwm_debugfs_rx_ticket_read,
 	.llseek =	default_llseek,
 };
 
 static const struct file_operations iwm_debugfs_fw_err_fops = {
 	.owner =	THIS_MODULE,
-	.open =		iwm_generic_open,
+	.open =		simple_open,
 	.read =		iwm_debugfs_fw_err_read,
 	.llseek =	default_llseek,
 };
diff --git a/drivers/net/wireless/iwmc3200wifi/sdio.c b/drivers/net/wireless/iwmc3200wifi/sdio.c
index 764b40dd24ad..0042f204b07f 100644
--- a/drivers/net/wireless/iwmc3200wifi/sdio.c
+++ b/drivers/net/wireless/iwmc3200wifi/sdio.c
@@ -264,13 +264,6 @@ static int if_sdio_send_chunk(struct iwm_priv *iwm, u8 *buf, int count)
 	return ret;
 }
 
-/* debugfs hooks */
-static int iwm_debugfs_sdio_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t iwm_debugfs_sdio_read(struct file *filp, char __user *buffer,
 				     size_t count, loff_t *ppos)
 {
@@ -363,7 +356,7 @@ err:
 
 static const struct file_operations iwm_debugfs_sdio_fops = {
 	.owner =	THIS_MODULE,
-	.open =		iwm_debugfs_sdio_open,
+	.open =		simple_open,
 	.read =		iwm_debugfs_sdio_read,
 	.llseek =	default_llseek,
 };
diff --git a/drivers/net/wireless/libertas/debugfs.c b/drivers/net/wireless/libertas/debugfs.c
index c192671610fc..a06cc283e23d 100644
--- a/drivers/net/wireless/libertas/debugfs.c
+++ b/drivers/net/wireless/libertas/debugfs.c
@@ -21,12 +21,6 @@ static char *szStates[] = {
 static void lbs_debug_init(struct lbs_private *priv);
 #endif
 
-static int open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t write_file_dummy(struct file *file, const char __user *buf,
                                 size_t count, loff_t *ppos)
 {
@@ -696,7 +690,7 @@ out_unlock:
 
 #define FOPS(fread, fwrite) { \
 	.owner = THIS_MODULE, \
-	.open = open_file_generic, \
+	.open = simple_open, \
 	.read = (fread), \
 	.write = (fwrite), \
 	.llseek = generic_file_llseek, \
@@ -962,7 +956,7 @@ static ssize_t lbs_debugfs_write(struct file *f, const char __user *buf,
 
 static const struct file_operations lbs_debug_fops = {
 	.owner = THIS_MODULE,
-	.open = open_file_generic,
+	.open = simple_open,
 	.write = lbs_debugfs_write,
 	.read = lbs_debugfs_read,
 	.llseek = default_llseek,
diff --git a/drivers/net/wireless/mwifiex/debugfs.c b/drivers/net/wireless/mwifiex/debugfs.c
index d26a78b6b3c4..1a845074c52a 100644
--- a/drivers/net/wireless/mwifiex/debugfs.c
+++ b/drivers/net/wireless/mwifiex/debugfs.c
@@ -140,18 +140,6 @@ static struct mwifiex_debug_data items[] = {
 static int num_of_items = ARRAY_SIZE(items);
 
 /*
- * Generic proc file open handler.
- *
- * This function is called every time a file is accessed for read or write.
- */
-static int
-mwifiex_open_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
-/*
  * Proc info file read handler.
  *
  * This function is called when the 'info' file is opened for reading.
@@ -676,19 +664,19 @@ done:
 static const struct file_operations mwifiex_dfs_##name##_fops = {       \
 	.read = mwifiex_##name##_read,                                  \
 	.write = mwifiex_##name##_write,                                \
-	.open = mwifiex_open_generic,                                   \
+	.open = simple_open,                                            \
 };
 
 #define MWIFIEX_DFS_FILE_READ_OPS(name)                                 \
 static const struct file_operations mwifiex_dfs_##name##_fops = {       \
 	.read = mwifiex_##name##_read,                                  \
-	.open = mwifiex_open_generic,                                   \
+	.open = simple_open,                                            \
 };
 
 #define MWIFIEX_DFS_FILE_WRITE_OPS(name)                                \
 static const struct file_operations mwifiex_dfs_##name##_fops = {       \
 	.write = mwifiex_##name##_write,                                \
-	.open = mwifiex_open_generic,                                   \
+	.open = simple_open,                                            \
 };
 
 
diff --git a/drivers/net/wireless/prism54/islpci_mgt.c b/drivers/net/wireless/prism54/islpci_mgt.c
index 851fa10241e1..c5404cb59e08 100644
--- a/drivers/net/wireless/prism54/islpci_mgt.c
+++ b/drivers/net/wireless/prism54/islpci_mgt.c
@@ -24,7 +24,6 @@
 #include <linux/slab.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <linux/if_arp.h>
 
 #include "prismcompat.h"
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 04fec1fa6e0b..86a738bf591c 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -53,7 +53,6 @@
 #include <net/iw_handler.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/net/wireless/wl1251/debugfs.c b/drivers/net/wireless/wl1251/debugfs.c
index 6c274007d200..448da1f8c22f 100644
--- a/drivers/net/wireless/wl1251/debugfs.c
+++ b/drivers/net/wireless/wl1251/debugfs.c
@@ -47,7 +47,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf,	\
 									\
 static const struct file_operations name## _ops = {			\
 	.read = name## _read,						\
-	.open = wl1251_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek	= generic_file_llseek,					\
 };
 
@@ -84,7 +84,7 @@ static ssize_t sub## _ ##name## _read(struct file *file,		\
 									\
 static const struct file_operations sub## _ ##name## _ops = {		\
 	.read = sub## _ ##name## _read,					\
-	.open = wl1251_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek	= generic_file_llseek,					\
 };
 
@@ -117,12 +117,6 @@ out:
 	mutex_unlock(&wl->mutex);
 }
 
-static int wl1251_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 DEBUGFS_FWSTATS_FILE(tx, internal_desc_overflow, 20, "%u");
 
 DEBUGFS_FWSTATS_FILE(rx, out_of_mem, 20, "%u");
@@ -235,7 +229,7 @@ static ssize_t tx_queue_len_read(struct file *file, char __user *userbuf,
 
 static const struct file_operations tx_queue_len_ops = {
 	.read = tx_queue_len_read,
-	.open = wl1251_open_file_generic,
+	.open = simple_open,
 	.llseek = generic_file_llseek,
 };
 
@@ -257,7 +251,7 @@ static ssize_t tx_queue_status_read(struct file *file, char __user *userbuf,
 
 static const struct file_operations tx_queue_status_ops = {
 	.read = tx_queue_status_read,
-	.open = wl1251_open_file_generic,
+	.open = simple_open,
 	.llseek = generic_file_llseek,
 };
 
diff --git a/drivers/net/wireless/wl12xx/debugfs.c b/drivers/net/wireless/wl12xx/debugfs.c
index e1cf72765965..564d49575c94 100644
--- a/drivers/net/wireless/wl12xx/debugfs.c
+++ b/drivers/net/wireless/wl12xx/debugfs.c
@@ -63,7 +63,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf,	\
 									\
 static const struct file_operations name## _ops = {			\
 	.read = name## _read,						\
-	.open = wl1271_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek	= generic_file_llseek,					\
 };
 
@@ -96,7 +96,7 @@ static ssize_t sub## _ ##name## _read(struct file *file,		\
 									\
 static const struct file_operations sub## _ ##name## _ops = {		\
 	.read = sub## _ ##name## _read,					\
-	.open = wl1271_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek	= generic_file_llseek,					\
 };
 
@@ -126,12 +126,6 @@ out:
 	mutex_unlock(&wl->mutex);
 }
 
-static int wl1271_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 DEBUGFS_FWSTATS_FILE(tx, internal_desc_overflow, "%u");
 
 DEBUGFS_FWSTATS_FILE(rx, out_of_mem, "%u");
@@ -243,7 +237,7 @@ static ssize_t tx_queue_len_read(struct file *file, char __user *userbuf,
 
 static const struct file_operations tx_queue_len_ops = {
 	.read = tx_queue_len_read,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -289,7 +283,7 @@ static ssize_t gpio_power_write(struct file *file,
 static const struct file_operations gpio_power_ops = {
 	.read = gpio_power_read,
 	.write = gpio_power_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -308,7 +302,7 @@ static ssize_t start_recovery_write(struct file *file,
 
 static const struct file_operations start_recovery_ops = {
 	.write = start_recovery_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -372,7 +366,7 @@ out:
 static const struct file_operations dynamic_ps_timeout_ops = {
 	.read = dynamic_ps_timeout_read,
 	.write = dynamic_ps_timeout_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -441,7 +435,7 @@ out:
 static const struct file_operations forced_ps_ops = {
 	.read = forced_ps_read,
 	.write = forced_ps_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -483,7 +477,7 @@ static ssize_t split_scan_timeout_write(struct file *file,
 static const struct file_operations split_scan_timeout_ops = {
 	.read = split_scan_timeout_read,
 	.write = split_scan_timeout_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -566,7 +560,7 @@ static ssize_t driver_state_read(struct file *file, char __user *user_buf,
 
 static const struct file_operations driver_state_ops = {
 	.read = driver_state_read,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -675,7 +669,7 @@ static ssize_t vifs_state_read(struct file *file, char __user *user_buf,
 
 static const struct file_operations vifs_state_ops = {
 	.read = vifs_state_read,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -733,7 +727,7 @@ static ssize_t dtim_interval_write(struct file *file,
 static const struct file_operations dtim_interval_ops = {
 	.read = dtim_interval_read,
 	.write = dtim_interval_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -791,7 +785,7 @@ static ssize_t suspend_dtim_interval_write(struct file *file,
 static const struct file_operations suspend_dtim_interval_ops = {
 	.read = suspend_dtim_interval_read,
 	.write = suspend_dtim_interval_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -849,7 +843,7 @@ static ssize_t beacon_interval_write(struct file *file,
 static const struct file_operations beacon_interval_ops = {
 	.read = beacon_interval_read,
 	.write = beacon_interval_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -904,7 +898,7 @@ static ssize_t rx_streaming_interval_read(struct file *file,
 static const struct file_operations rx_streaming_interval_ops = {
 	.read = rx_streaming_interval_read,
 	.write = rx_streaming_interval_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -959,7 +953,7 @@ static ssize_t rx_streaming_always_read(struct file *file,
 static const struct file_operations rx_streaming_always_ops = {
 	.read = rx_streaming_always_read,
 	.write = rx_streaming_always_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
@@ -1003,7 +997,7 @@ out:
 
 static const struct file_operations beacon_filtering_ops = {
 	.write = beacon_filtering_write,
-	.open = wl1271_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c
index 98fbf54f6004..00f6e69c1dcd 100644
--- a/drivers/net/wireless/wl3501_cs.c
+++ b/drivers/net/wireless/wl3501_cs.c
@@ -53,7 +53,6 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include "wl3501.h"
 
diff --git a/drivers/nubus/nubus.c b/drivers/nubus/nubus.c
index b764ac22d523..44d01afafe9c 100644
--- a/drivers/nubus/nubus.c
+++ b/drivers/nubus/nubus.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/hwtest.h>
 #include <linux/proc_fs.h>
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 6ea51dcbc728..8e84ce9765a9 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -91,4 +91,8 @@ config OF_PCI_IRQ
 	help
 	  OpenFirmware PCI IRQ routing helpers
 
+config OF_MTD
+	depends on MTD
+	def_bool y
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index a73f5a51ff4c..aa90e602c8a7 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_OF_SELFTEST) += selftest.o
 obj-$(CONFIG_OF_MDIO)	+= of_mdio.o
 obj-$(CONFIG_OF_PCI)	+= of_pci.o
 obj-$(CONFIG_OF_PCI_IRQ)  += of_pci_irq.o
+obj-$(CONFIG_OF_MTD)	+= of_mtd.o
diff --git a/drivers/of/gpio.c b/drivers/of/gpio.c
index 7e62d15d60f6..bba81216b4db 100644
--- a/drivers/of/gpio.c
+++ b/drivers/of/gpio.c
@@ -78,8 +78,9 @@ err0:
 EXPORT_SYMBOL(of_get_named_gpio_flags);
 
 /**
- * of_gpio_count - Count GPIOs for a device
+ * of_gpio_named_count - Count GPIOs for a device
  * @np:		device node to count GPIOs for
+ * @propname:	property name containing gpio specifier(s)
  *
  * The function returns the count of GPIOs specified for a node.
  *
@@ -93,14 +94,14 @@ EXPORT_SYMBOL(of_get_named_gpio_flags);
  * defines four GPIOs (so this function will return 4), two of which
  * are not specified.
  */
-unsigned int of_gpio_count(struct device_node *np)
+unsigned int of_gpio_named_count(struct device_node *np, const char* propname)
 {
 	unsigned int cnt = 0;
 
 	do {
 		int ret;
 
-		ret = of_parse_phandle_with_args(np, "gpios", "#gpio-cells",
+		ret = of_parse_phandle_with_args(np, propname, "#gpio-cells",
 						 cnt, NULL);
 		/* A hole in the gpios = <> counts anyway. */
 		if (ret < 0 && ret != -EEXIST)
@@ -109,7 +110,7 @@ unsigned int of_gpio_count(struct device_node *np)
 
 	return cnt;
 }
-EXPORT_SYMBOL(of_gpio_count);
+EXPORT_SYMBOL(of_gpio_named_count);
 
 /**
  * of_gpio_simple_xlate - translate gpio_spec to the GPIO number and flags
@@ -228,7 +229,7 @@ void of_gpiochip_remove(struct gpio_chip *chip)
 }
 
 /* Private function for resolving node pointer to gpio_chip */
-static int of_gpiochip_is_match(struct gpio_chip *chip, void *data)
+static int of_gpiochip_is_match(struct gpio_chip *chip, const void *data)
 {
 	return chip->of_node == data;
 }
diff --git a/drivers/of/of_mtd.c b/drivers/of/of_mtd.c
new file mode 100644
index 000000000000..e7cad627a5d1
--- /dev/null
+++ b/drivers/of/of_mtd.c
@@ -0,0 +1,85 @@
+/*
+ * Copyright 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
+ *
+ * OF helpers for mtd.
+ *
+ * This file is released under the GPLv2
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/of_mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/export.h>
+
+/**
+ * It maps 'enum nand_ecc_modes_t' found in include/linux/mtd/nand.h
+ * into the device tree binding of 'nand-ecc', so that MTD
+ * device driver can get nand ecc from device tree.
+ */
+static const char *nand_ecc_modes[] = {
+	[NAND_ECC_NONE]		= "none",
+	[NAND_ECC_SOFT]		= "soft",
+	[NAND_ECC_HW]		= "hw",
+	[NAND_ECC_HW_SYNDROME]	= "hw_syndrome",
+	[NAND_ECC_HW_OOB_FIRST]	= "hw_oob_first",
+	[NAND_ECC_SOFT_BCH]	= "soft_bch",
+};
+
+/**
+ * of_get_nand_ecc_mode - Get nand ecc mode for given device_node
+ * @np:	Pointer to the given device_node
+ *
+ * The function gets ecc mode string from property 'nand-ecc-mode',
+ * and return its index in nand_ecc_modes table, or errno in error case.
+ */
+const int of_get_nand_ecc_mode(struct device_node *np)
+{
+	const char *pm;
+	int err, i;
+
+	err = of_property_read_string(np, "nand-ecc-mode", &pm);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(nand_ecc_modes); i++)
+		if (!strcasecmp(pm, nand_ecc_modes[i]))
+			return i;
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(of_get_nand_ecc_mode);
+
+/**
+ * of_get_nand_bus_width - Get nand bus witdh for given device_node
+ * @np:	Pointer to the given device_node
+ *
+ * return bus width option, or errno in error case.
+ */
+int of_get_nand_bus_width(struct device_node *np)
+{
+	u32 val;
+
+	if (of_property_read_u32(np, "nand-bus-width", &val))
+		return 8;
+
+	switch(val) {
+	case 8:
+	case 16:
+		return val;
+	default:
+		return -EIO;
+	}
+}
+EXPORT_SYMBOL_GPL(of_get_nand_bus_width);
+
+/**
+ * of_get_nand_on_flash_bbt - Get nand on flash bbt for given device_node
+ * @np:	Pointer to the given device_node
+ *
+ * return true if present false other wise
+ */
+bool of_get_nand_on_flash_bbt(struct device_node *np)
+{
+	return of_property_read_bool(np, "nand-on-flash-bbt");
+}
+EXPORT_SYMBOL_GPL(of_get_nand_on_flash_bbt);
diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c
index ee8fd037bb53..849357c1045c 100644
--- a/drivers/oprofile/oprofilefs.c
+++ b/drivers/oprofile/oprofilefs.c
@@ -117,25 +117,17 @@ static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_
 }
 
 
-static int default_open(struct inode *inode, struct file *filp)
-{
-	if (inode->i_private)
-		filp->private_data = inode->i_private;
-	return 0;
-}
-
-
 static const struct file_operations ulong_fops = {
 	.read		= ulong_read_file,
 	.write		= ulong_write_file,
-	.open		= default_open,
+	.open		= simple_open,
 	.llseek		= default_llseek,
 };
 
 
 static const struct file_operations ulong_ro_fops = {
 	.read		= ulong_read_file,
-	.open		= default_open,
+	.open		= simple_open,
 	.llseek		= default_llseek,
 };
 
@@ -187,7 +179,7 @@ static ssize_t atomic_read_file(struct file *file, char __user *buf, size_t coun
 
 static const struct file_operations atomic_ro_fops = {
 	.read		= atomic_read_file,
-	.open		= default_open,
+	.open		= simple_open,
 	.llseek		= default_llseek,
 };
 
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index 0610e91bceb2..432d4bbcc62a 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -55,7 +55,6 @@
 
 #include <asm/pdc.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/hardware.h>
 
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 95930d016235..1f9e9fefb8e7 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -140,7 +140,6 @@
 #include <asm/pdc.h>
 #include <asm/pdcpat.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <asm/io.h>		/* read/write functions */
 #ifdef CONFIG_SUPERIO
 #include <asm/superio.h>
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index e8857647e210..052fa230bc77 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -43,7 +43,6 @@
 #include <asm/pdc.h>
 #include <asm/pdcpat.h>
 #include <asm/page.h>
-#include <asm/system.h>
 
 #include <asm/ropes.h>
 #include <asm/hardware.h>	/* for register_parisc_driver() stuff */
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 060fd22a1103..0f150f271c2a 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -277,40 +277,6 @@ static int acpi_pci_sleep_wake(struct pci_dev *dev, bool enable)
 	return 0;
 }
 
-/**
- * acpi_dev_run_wake - Enable/disable wake-up for given device.
- * @phys_dev: Device to enable/disable the platform to wake-up the system for.
- * @enable: Whether enable or disable the wake-up functionality.
- *
- * Find the ACPI device object corresponding to @pci_dev and try to
- * enable/disable the GPE associated with it.
- */
-static int acpi_dev_run_wake(struct device *phys_dev, bool enable)
-{
-	struct acpi_device *dev;
-	acpi_handle handle;
-
-	if (!device_run_wake(phys_dev))
-		return -EINVAL;
-
-	handle = DEVICE_ACPI_HANDLE(phys_dev);
-	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &dev))) {
-		dev_dbg(phys_dev, "ACPI handle has no context in %s!\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	if (enable) {
-		acpi_enable_wakeup_device_power(dev, ACPI_STATE_S0);
-		acpi_enable_gpe(dev->wakeup.gpe_device, dev->wakeup.gpe_number);
-	} else {
-		acpi_disable_gpe(dev->wakeup.gpe_device, dev->wakeup.gpe_number);
-		acpi_disable_wakeup_device_power(dev);
-	}
-
-	return 0;
-}
-
 static void acpi_pci_propagate_run_wake(struct pci_bus *bus, bool enable)
 {
 	while (bus->parent) {
@@ -318,14 +284,14 @@ static void acpi_pci_propagate_run_wake(struct pci_bus *bus, bool enable)
 
 		if (bridge->pme_interrupt)
 			return;
-		if (!acpi_dev_run_wake(&bridge->dev, enable))
+		if (!acpi_pm_device_run_wake(&bridge->dev, enable))
 			return;
 		bus = bus->parent;
 	}
 
 	/* We have reached the root bus. */
 	if (bus->bridge)
-		acpi_dev_run_wake(bus->bridge, enable);
+		acpi_pm_device_run_wake(bus->bridge, enable);
 }
 
 static int acpi_pci_run_wake(struct pci_dev *dev, bool enable)
@@ -333,7 +299,7 @@ static int acpi_pci_run_wake(struct pci_dev *dev, bool enable)
 	if (dev->pme_interrupt)
 		return 0;
 
-	if (!acpi_dev_run_wake(&dev->dev, enable))
+	if (!acpi_pm_device_run_wake(&dev->dev, enable))
 		return 0;
 
 	acpi_pci_propagate_run_wake(dev->bus, enable);
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 4bdef24cd412..b500840a143b 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -508,9 +508,6 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev)
 	int pos;
 	u32 reg32;
 
-	if (aspm_disabled)
-		return 0;
-
 	/*
 	 * Some functions in a slot might not all be PCIe functions,
 	 * very strange. Disable ASPM for the whole slot
@@ -519,6 +516,16 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev)
 		pos = pci_pcie_cap(child);
 		if (!pos)
 			return -EINVAL;
+
+		/*
+		 * If ASPM is disabled then we're not going to change
+		 * the BIOS state. It's safe to continue even if it's a
+		 * pre-1.1 device
+		 */
+
+		if (aspm_disabled)
+			continue;
+
 		/*
 		 * Disable ASPM for pre-1.1 PCIe device, we follow MS to use
 		 * RBER bit to determine if a function is 1.1 version device
diff --git a/drivers/pcmcia/at91_cf.c b/drivers/pcmcia/at91_cf.c
index 1dd68f502634..9694c1e783a5 100644
--- a/drivers/pcmcia/at91_cf.c
+++ b/drivers/pcmcia/at91_cf.c
@@ -16,13 +16,13 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/gpio.h>
 
 #include <pcmcia/ss.h>
 
 #include <mach/hardware.h>
 #include <asm/io.h>
 #include <asm/sizes.h>
-#include <asm/gpio.h>
 
 #include <mach/board.h>
 #include <mach/at91rm9200_mc.h>
@@ -70,7 +70,7 @@ static irqreturn_t at91_cf_irq(int irq, void *_cf)
 {
 	struct at91_cf_socket *cf = _cf;
 
-	if (irq == cf->board->det_pin) {
+	if (irq == gpio_to_irq(cf->board->det_pin)) {
 		unsigned present = at91_cf_present(cf);
 
 		/* kick pccard as needed */
@@ -96,8 +96,8 @@ static int at91_cf_get_status(struct pcmcia_socket *s, u_int *sp)
 
 	/* NOTE: CF is always 3VCARD */
 	if (at91_cf_present(cf)) {
-		int rdy	= cf->board->irq_pin;	/* RDY/nIRQ */
-		int vcc	= cf->board->vcc_pin;
+		int rdy	= gpio_is_valid(cf->board->irq_pin);	/* RDY/nIRQ */
+		int vcc	= gpio_is_valid(cf->board->vcc_pin);
 
 		*sp = SS_DETECT | SS_3VCARD;
 		if (!rdy || gpio_get_value(rdy))
@@ -118,7 +118,7 @@ at91_cf_set_socket(struct pcmcia_socket *sock, struct socket_state_t *s)
 	cf = container_of(sock, struct at91_cf_socket, socket);
 
 	/* switch Vcc if needed and possible */
-	if (cf->board->vcc_pin) {
+	if (gpio_is_valid(cf->board->vcc_pin)) {
 		switch (s->Vcc) {
 			case 0:
 				gpio_set_value(cf->board->vcc_pin, 0);
@@ -222,7 +222,7 @@ static int __init at91_cf_probe(struct platform_device *pdev)
 	struct resource		*io;
 	int			status;
 
-	if (!board || !board->det_pin || !board->rst_pin)
+	if (!board || !gpio_is_valid(board->det_pin) || !gpio_is_valid(board->rst_pin))
 		return -ENODEV;
 
 	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -242,7 +242,7 @@ static int __init at91_cf_probe(struct platform_device *pdev)
 	status = gpio_request(board->det_pin, "cf_det");
 	if (status < 0)
 		goto fail0;
-	status = request_irq(board->det_pin, at91_cf_irq, 0, driver_name, cf);
+	status = request_irq(gpio_to_irq(board->det_pin), at91_cf_irq, 0, driver_name, cf);
 	if (status < 0)
 		goto fail00;
 	device_init_wakeup(&pdev->dev, 1);
@@ -251,7 +251,7 @@ static int __init at91_cf_probe(struct platform_device *pdev)
 	if (status < 0)
 		goto fail0a;
 
-	if (board->vcc_pin) {
+	if (gpio_is_valid(board->vcc_pin)) {
 		status = gpio_request(board->vcc_pin, "cf_vcc");
 		if (status < 0)
 			goto fail0b;
@@ -263,15 +263,15 @@ static int __init at91_cf_probe(struct platform_device *pdev)
 	 * unless we report that we handle everything (sigh).
 	 * (Note:  DK board doesn't wire the IRQ pin...)
 	 */
-	if (board->irq_pin) {
+	if (gpio_is_valid(board->irq_pin)) {
 		status = gpio_request(board->irq_pin, "cf_irq");
 		if (status < 0)
 			goto fail0c;
-		status = request_irq(board->irq_pin, at91_cf_irq,
+		status = request_irq(gpio_to_irq(board->irq_pin), at91_cf_irq,
 				IRQF_SHARED, driver_name, cf);
 		if (status < 0)
 			goto fail0d;
-		cf->socket.pci_irq = board->irq_pin;
+		cf->socket.pci_irq = gpio_to_irq(board->irq_pin);
 	} else
 		cf->socket.pci_irq = nr_irqs + 1;
 
@@ -290,7 +290,7 @@ static int __init at91_cf_probe(struct platform_device *pdev)
 	}
 
 	pr_info("%s: irqs det #%d, io #%d\n", driver_name,
-		board->det_pin, board->irq_pin);
+		gpio_to_irq(board->det_pin), gpio_to_irq(board->irq_pin));
 
 	cf->socket.owner = THIS_MODULE;
 	cf->socket.dev.parent = &pdev->dev;
@@ -312,19 +312,19 @@ fail2:
 fail1:
 	if (cf->socket.io_offset)
 		iounmap((void __iomem *) cf->socket.io_offset);
-	if (board->irq_pin) {
-		free_irq(board->irq_pin, cf);
+	if (gpio_is_valid(board->irq_pin)) {
+		free_irq(gpio_to_irq(board->irq_pin), cf);
 fail0d:
 		gpio_free(board->irq_pin);
 	}
 fail0c:
-	if (board->vcc_pin)
+	if (gpio_is_valid(board->vcc_pin))
 		gpio_free(board->vcc_pin);
 fail0b:
 	gpio_free(board->rst_pin);
 fail0a:
 	device_init_wakeup(&pdev->dev, 0);
-	free_irq(board->det_pin, cf);
+	free_irq(gpio_to_irq(board->det_pin), cf);
 fail00:
 	gpio_free(board->det_pin);
 fail0:
@@ -341,15 +341,15 @@ static int __exit at91_cf_remove(struct platform_device *pdev)
 	pcmcia_unregister_socket(&cf->socket);
 	release_mem_region(io->start, resource_size(io));
 	iounmap((void __iomem *) cf->socket.io_offset);
-	if (board->irq_pin) {
-		free_irq(board->irq_pin, cf);
+	if (gpio_is_valid(board->irq_pin)) {
+		free_irq(gpio_to_irq(board->irq_pin), cf);
 		gpio_free(board->irq_pin);
 	}
-	if (board->vcc_pin)
+	if (gpio_is_valid(board->vcc_pin))
 		gpio_free(board->vcc_pin);
 	gpio_free(board->rst_pin);
 	device_init_wakeup(&pdev->dev, 0);
-	free_irq(board->det_pin, cf);
+	free_irq(gpio_to_irq(board->det_pin), cf);
 	gpio_free(board->det_pin);
 	kfree(cf);
 	return 0;
@@ -363,9 +363,9 @@ static int at91_cf_suspend(struct platform_device *pdev, pm_message_t mesg)
 	struct at91_cf_data	*board = cf->board;
 
 	if (device_may_wakeup(&pdev->dev)) {
-		enable_irq_wake(board->det_pin);
-		if (board->irq_pin)
-			enable_irq_wake(board->irq_pin);
+		enable_irq_wake(gpio_to_irq(board->det_pin));
+		if (gpio_is_valid(board->irq_pin))
+			enable_irq_wake(gpio_to_irq(board->irq_pin));
 	}
 	return 0;
 }
@@ -376,9 +376,9 @@ static int at91_cf_resume(struct platform_device *pdev)
 	struct at91_cf_data	*board = cf->board;
 
 	if (device_may_wakeup(&pdev->dev)) {
-		disable_irq_wake(board->det_pin);
-		if (board->irq_pin)
-			disable_irq_wake(board->irq_pin);
+		disable_irq_wake(gpio_to_irq(board->det_pin));
+		if (gpio_is_valid(board->irq_pin))
+			disable_irq_wake(gpio_to_irq(board->irq_pin));
 	}
 
 	return 0;
diff --git a/drivers/pcmcia/bcm63xx_pcmcia.c b/drivers/pcmcia/bcm63xx_pcmcia.c
index 693577e0fefc..c2e997a570bf 100644
--- a/drivers/pcmcia/bcm63xx_pcmcia.c
+++ b/drivers/pcmcia/bcm63xx_pcmcia.c
@@ -475,7 +475,7 @@ static void __devexit bcm63xx_cb_exit(struct pci_dev *dev)
 	bcm63xx_cb_dev = NULL;
 }
 
-static struct pci_device_id bcm63xx_cb_table[] = {
+static DEFINE_PCI_DEVICE_TABLE(bcm63xx_cb_table) = {
 	{
 		.vendor		= PCI_VENDOR_ID_BROADCOM,
 		.device		= BCM6348_CPU_ID,
diff --git a/drivers/pcmcia/bfin_cf_pcmcia.c b/drivers/pcmcia/bfin_cf_pcmcia.c
index 49221395101e..ac1a2232eab9 100644
--- a/drivers/pcmcia/bfin_cf_pcmcia.c
+++ b/drivers/pcmcia/bfin_cf_pcmcia.c
@@ -310,18 +310,7 @@ static struct platform_driver bfin_cf_driver = {
 	.remove = __devexit_p(bfin_cf_remove),
 };
 
-static int __init bfin_cf_init(void)
-{
-	return platform_driver_register(&bfin_cf_driver);
-}
-
-static void __exit bfin_cf_exit(void)
-{
-	platform_driver_unregister(&bfin_cf_driver);
-}
-
-module_init(bfin_cf_init);
-module_exit(bfin_cf_exit);
+module_platform_driver(bfin_cf_driver);
 
 MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
 MODULE_DESCRIPTION("BFIN CF/PCMCIA Driver");
diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c
index d9ea192c4001..673c14ea11e3 100644
--- a/drivers/pcmcia/cs.c
+++ b/drivers/pcmcia/cs.c
@@ -29,7 +29,6 @@
 #include <linux/device.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 
 #include <pcmcia/ss.h>
diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c
index 5b7c22784aff..a484b1fb3382 100644
--- a/drivers/pcmcia/db1xxx_ss.c
+++ b/drivers/pcmcia/db1xxx_ss.c
@@ -172,12 +172,12 @@ static int db1x_pcmcia_setup_irqs(struct db1x_pcmcia_sock *sock)
 	if ((sock->board_type == BOARD_TYPE_DB1200) ||
 	    (sock->board_type == BOARD_TYPE_DB1300)) {
 		ret = request_irq(sock->insert_irq, db1200_pcmcia_cdirq,
-				  IRQF_DISABLED, "pcmcia_insert", sock);
+				  0, "pcmcia_insert", sock);
 		if (ret)
 			goto out1;
 
 		ret = request_irq(sock->eject_irq, db1200_pcmcia_cdirq,
-				  IRQF_DISABLED, "pcmcia_eject", sock);
+				  0, "pcmcia_eject", sock);
 		if (ret) {
 			free_irq(sock->insert_irq, sock);
 			goto out1;
@@ -580,18 +580,7 @@ static struct platform_driver db1x_pcmcia_socket_driver = {
 	.remove		= __devexit_p(db1x_pcmcia_socket_remove),
 };
 
-int __init db1x_pcmcia_socket_load(void)
-{
-	return platform_driver_register(&db1x_pcmcia_socket_driver);
-}
-
-void  __exit db1x_pcmcia_socket_unload(void)
-{
-	platform_driver_unregister(&db1x_pcmcia_socket_driver);
-}
-
-module_init(db1x_pcmcia_socket_load);
-module_exit(db1x_pcmcia_socket_unload);
+module_platform_driver(db1x_pcmcia_socket_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("PCMCIA Socket Services for Alchemy Db/Pb1x00 boards");
diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c
index 06ad3e5e7d3d..7647d232e9e2 100644
--- a/drivers/pcmcia/electra_cf.c
+++ b/drivers/pcmcia/electra_cf.c
@@ -365,17 +365,7 @@ static struct platform_driver electra_cf_driver = {
 	.remove   = electra_cf_remove,
 };
 
-static int __init electra_cf_init(void)
-{
-	return platform_driver_register(&electra_cf_driver);
-}
-module_init(electra_cf_init);
-
-static void __exit electra_cf_exit(void)
-{
-	platform_driver_unregister(&electra_cf_driver);
-}
-module_exit(electra_cf_exit);
+module_platform_driver(electra_cf_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR ("Olof Johansson <olof@lixom.net>");
diff --git a/drivers/pcmcia/i82092.c b/drivers/pcmcia/i82092.c
index 3e447d0387b7..4e8831bdb6ef 100644
--- a/drivers/pcmcia/i82092.c
+++ b/drivers/pcmcia/i82092.c
@@ -17,7 +17,6 @@
 
 #include <pcmcia/ss.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include "i82092aa.h"
@@ -26,14 +25,9 @@
 MODULE_LICENSE("GPL");
 
 /* PCI core routines */
-static struct pci_device_id i82092aa_pci_ids[] = {
-	{
-	      .vendor = PCI_VENDOR_ID_INTEL,
-	      .device = PCI_DEVICE_ID_INTEL_82092AA_0,
-	      .subvendor = PCI_ANY_ID,
-	      .subdevice = PCI_ANY_ID,
-	 },
-	 {} 
+static DEFINE_PCI_DEVICE_TABLE(i82092aa_pci_ids) = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82092AA_0) },
+	{ }
 };
 MODULE_DEVICE_TABLE(pci, i82092aa_pci_ids);
 
diff --git a/drivers/pcmcia/i82365.c b/drivers/pcmcia/i82365.c
index 72a033a2acdb..e6f3d17dd2b4 100644
--- a/drivers/pcmcia/i82365.c
+++ b/drivers/pcmcia/i82365.c
@@ -48,7 +48,6 @@
 #include <linux/bitops.h>
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/ss.h>
 
diff --git a/drivers/pcmcia/m32r_cfc.c b/drivers/pcmcia/m32r_cfc.c
index 2adb0106a039..a26f38c6402a 100644
--- a/drivers/pcmcia/m32r_cfc.c
+++ b/drivers/pcmcia/m32r_cfc.c
@@ -24,7 +24,6 @@
 #include <linux/bitops.h>
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/ss.h>
 
diff --git a/drivers/pcmcia/m32r_pcc.c b/drivers/pcmcia/m32r_pcc.c
index 1511ff71c87b..296514155cd5 100644
--- a/drivers/pcmcia/m32r_pcc.c
+++ b/drivers/pcmcia/m32r_pcc.c
@@ -24,7 +24,6 @@
 #include <linux/bitops.h>
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/addrspace.h>
 
 #include <pcmcia/ss.h>
diff --git a/drivers/pcmcia/m8xx_pcmcia.c b/drivers/pcmcia/m8xx_pcmcia.c
index 271a590a5f3c..a3a851e49321 100644
--- a/drivers/pcmcia/m8xx_pcmcia.c
+++ b/drivers/pcmcia/m8xx_pcmcia.c
@@ -52,7 +52,6 @@
 #include <linux/of_platform.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/mpc8xx.h>
 #include <asm/8xx_immap.h>
@@ -1304,15 +1303,4 @@ static struct platform_driver m8xx_pcmcia_driver = {
 	.remove = m8xx_remove,
 };
 
-static int __init m8xx_init(void)
-{
-	return platform_driver_register(&m8xx_pcmcia_driver);
-}
-
-static void __exit m8xx_exit(void)
-{
-	platform_driver_unregister(&m8xx_pcmcia_driver);
-}
-
-module_init(m8xx_init);
-module_exit(m8xx_exit);
+module_platform_driver(m8xx_pcmcia_driver);
diff --git a/drivers/pcmcia/pd6729.c b/drivers/pcmcia/pd6729.c
index 96c72e90b79c..253e3867dec7 100644
--- a/drivers/pcmcia/pd6729.c
+++ b/drivers/pcmcia/pd6729.c
@@ -19,7 +19,6 @@
 
 #include <pcmcia/ss.h>
 
-#include <asm/system.h>
 
 #include "pd6729.h"
 #include "i82365.h"
@@ -763,13 +762,8 @@ static void __devexit pd6729_pci_remove(struct pci_dev *dev)
 	kfree(socket);
 }
 
-static struct pci_device_id pd6729_pci_ids[] = {
-	{
-		.vendor		= PCI_VENDOR_ID_CIRRUS,
-		.device		= PCI_DEVICE_ID_CIRRUS_6729,
-		.subvendor	= PCI_ANY_ID,
-		.subdevice	= PCI_ANY_ID,
-	},
+static DEFINE_PCI_DEVICE_TABLE(pd6729_pci_ids) = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_6729) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, pd6729_pci_ids);
diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c
index 66a54222bbf4..490bb82b5bdb 100644
--- a/drivers/pcmcia/pxa2xx_base.c
+++ b/drivers/pcmcia/pxa2xx_base.c
@@ -29,7 +29,6 @@
 #include <mach/smemc.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <mach/pxa2xx-regs.h>
 #include <asm/mach-types.h>
 
diff --git a/drivers/pcmcia/pxa2xx_viper.c b/drivers/pcmcia/pxa2xx_viper.c
index adfae4987a42..cb0c37ec7f24 100644
--- a/drivers/pcmcia/pxa2xx_viper.c
+++ b/drivers/pcmcia/pxa2xx_viper.c
@@ -177,18 +177,7 @@ static struct platform_driver viper_pcmcia_driver = {
 	.id_table	= viper_pcmcia_id_table,
 };
 
-static int __init viper_pcmcia_init(void)
-{
-	return platform_driver_register(&viper_pcmcia_driver);
-}
-
-static void __exit viper_pcmcia_exit(void)
-{
-	return platform_driver_unregister(&viper_pcmcia_driver);
-}
-
-module_init(viper_pcmcia_init);
-module_exit(viper_pcmcia_exit);
+module_platform_driver(viper_pcmcia_driver);
 
 MODULE_DEVICE_TABLE(platform, viper_pcmcia_id_table);
 MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/sa1111_generic.c b/drivers/pcmcia/sa1111_generic.c
index ef5848f65241..70f728ce1856 100644
--- a/drivers/pcmcia/sa1111_generic.c
+++ b/drivers/pcmcia/sa1111_generic.c
@@ -22,6 +22,40 @@
 
 #include "sa1111_generic.h"
 
+/*
+ * These are offsets from the above base.
+ */
+#define PCCR	0x0000
+#define PCSSR	0x0004
+#define PCSR	0x0008
+
+#define PCSR_S0_READY	(1<<0)
+#define PCSR_S1_READY	(1<<1)
+#define PCSR_S0_DETECT	(1<<2)
+#define PCSR_S1_DETECT	(1<<3)
+#define PCSR_S0_VS1	(1<<4)
+#define PCSR_S0_VS2	(1<<5)
+#define PCSR_S1_VS1	(1<<6)
+#define PCSR_S1_VS2	(1<<7)
+#define PCSR_S0_WP	(1<<8)
+#define PCSR_S1_WP	(1<<9)
+#define PCSR_S0_BVD1	(1<<10)
+#define PCSR_S0_BVD2	(1<<11)
+#define PCSR_S1_BVD1	(1<<12)
+#define PCSR_S1_BVD2	(1<<13)
+
+#define PCCR_S0_RST	(1<<0)
+#define PCCR_S1_RST	(1<<1)
+#define PCCR_S0_FLT	(1<<2)
+#define PCCR_S1_FLT	(1<<3)
+#define PCCR_S0_PWAITEN	(1<<4)
+#define PCCR_S1_PWAITEN	(1<<5)
+#define PCCR_S0_PSE	(1<<6)
+#define PCCR_S1_PSE	(1<<7)
+
+#define PCSSR_S0_SLEEP	(1<<0)
+#define PCSSR_S1_SLEEP	(1<<1)
+
 #define IDX_IRQ_S0_READY_NINT	(0)
 #define IDX_IRQ_S0_CD_VALID	(1)
 #define IDX_IRQ_S0_BVD1_STSCHG	(2)
@@ -32,7 +66,7 @@
 void sa1111_pcmcia_socket_state(struct soc_pcmcia_socket *skt, struct pcmcia_state *state)
 {
 	struct sa1111_pcmcia_socket *s = to_skt(skt);
-	unsigned long status = sa1111_readl(s->dev->mapbase + SA1111_PCSR);
+	unsigned long status = sa1111_readl(s->dev->mapbase + PCSR);
 
 	switch (skt->nr) {
 	case 0:
@@ -88,10 +122,10 @@ int sa1111_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_s
 		pccr_set_mask |= PCCR_S0_FLT|PCCR_S1_FLT;
 
 	local_irq_save(flags);
-	val = sa1111_readl(s->dev->mapbase + SA1111_PCCR);
+	val = sa1111_readl(s->dev->mapbase + PCCR);
 	val &= ~pccr_skt_mask;
 	val |= pccr_set_mask & pccr_skt_mask;
-	sa1111_writel(val, s->dev->mapbase + SA1111_PCCR);
+	sa1111_writel(val, s->dev->mapbase + PCCR);
 	local_irq_restore(flags);
 
 	return 0;
@@ -141,20 +175,26 @@ int sa1111_pcmcia_add(struct sa1111_dev *dev, struct pcmcia_low_level *ops,
 static int pcmcia_probe(struct sa1111_dev *dev)
 {
 	void __iomem *base;
+	int ret;
+
+	ret = sa1111_enable_device(dev);
+	if (ret)
+		return ret;
 
 	dev_set_drvdata(&dev->dev, NULL);
 
-	if (!request_mem_region(dev->res.start, 512,
-				SA1111_DRIVER_NAME(dev)))
+	if (!request_mem_region(dev->res.start, 512, SA1111_DRIVER_NAME(dev))) {
+		sa1111_disable_device(dev);
 		return -EBUSY;
+	}
 
 	base = dev->mapbase;
 
 	/*
 	 * Initialise the suspend state.
 	 */
-	sa1111_writel(PCSSR_S0_SLEEP | PCSSR_S1_SLEEP, base + SA1111_PCSSR);
-	sa1111_writel(PCCR_S0_FLT | PCCR_S1_FLT, base + SA1111_PCCR);
+	sa1111_writel(PCSSR_S0_SLEEP | PCSSR_S1_SLEEP, base + PCSSR);
+	sa1111_writel(PCCR_S0_FLT | PCCR_S1_FLT, base + PCCR);
 
 #ifdef CONFIG_SA1100_BADGE4
 	pcmcia_badge4_init(&dev->dev);
@@ -184,6 +224,7 @@ static int __devexit pcmcia_remove(struct sa1111_dev *dev)
 	}
 
 	release_mem_region(dev->res.start, 512);
+	sa1111_disable_device(dev);
 	return 0;
 }
 
diff --git a/drivers/pcmcia/sa1111_neponset.c b/drivers/pcmcia/sa1111_neponset.c
index 50f297d850e7..1d78739c4c07 100644
--- a/drivers/pcmcia/sa1111_neponset.c
+++ b/drivers/pcmcia/sa1111_neponset.c
@@ -94,12 +94,7 @@ neponset_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_sta
 
 	ret = sa1111_pcmcia_configure_socket(skt, state);
 	if (ret == 0) {
-		unsigned long flags;
-
-		local_irq_save(flags);
-		NCR_0 = (NCR_0 & ~ncr_mask) | ncr_set;
-
-		local_irq_restore(flags);
+		neponset_ncr_frob(ncr_mask, ncr_set);
 		sa1111_set_io(s->dev, pa_dwr_mask, pa_dwr_set);
 	}
 
diff --git a/drivers/pcmcia/sa11xx_base.c b/drivers/pcmcia/sa11xx_base.c
index a3ee89a6dd0e..6eecd7cddf57 100644
--- a/drivers/pcmcia/sa11xx_base.c
+++ b/drivers/pcmcia/sa11xx_base.c
@@ -41,7 +41,6 @@
 
 #include <mach/hardware.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include "soc_common.h"
 #include "sa11xx_base.h"
diff --git a/drivers/pcmcia/soc_common.c b/drivers/pcmcia/soc_common.c
index e0433f571962..a2bc6ee1702e 100644
--- a/drivers/pcmcia/soc_common.c
+++ b/drivers/pcmcia/soc_common.c
@@ -46,7 +46,6 @@
 #include <linux/timer.h>
 
 #include <mach/hardware.h>
-#include <asm/system.h>
 
 #include "soc_common.h"
 
diff --git a/drivers/pcmcia/socket_sysfs.c b/drivers/pcmcia/socket_sysfs.c
index 71aeed93037c..d6881514d38e 100644
--- a/drivers/pcmcia/socket_sysfs.c
+++ b/drivers/pcmcia/socket_sysfs.c
@@ -23,7 +23,6 @@
 #include <linux/pm.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 
 #include <pcmcia/ss.h>
diff --git a/drivers/pcmcia/tcic.c b/drivers/pcmcia/tcic.c
index 310160bffe38..cbe15fc37411 100644
--- a/drivers/pcmcia/tcic.c
+++ b/drivers/pcmcia/tcic.c
@@ -47,7 +47,6 @@
 #include <linux/bitops.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/ss.h>
 #include "tcic.h"
diff --git a/drivers/pcmcia/vrc4173_cardu.c b/drivers/pcmcia/vrc4173_cardu.c
index c6d36b3a6ce8..cd0a315d922b 100644
--- a/drivers/pcmcia/vrc4173_cardu.c
+++ b/drivers/pcmcia/vrc4173_cardu.c
@@ -563,11 +563,8 @@ static int __devinit vrc4173_cardu_setup(char *options)
 
 __setup("vrc4173_cardu=", vrc4173_cardu_setup);
 
-static struct pci_device_id vrc4173_cardu_id_table[] __devinitdata = {
-	{	.vendor		= PCI_VENDOR_ID_NEC,
-		.device		= PCI_DEVICE_ID_NEC_NAPCCARD,
-		.subvendor	= PCI_ANY_ID,
-		.subdevice	= PCI_ANY_ID, },
+static DEFINE_PCI_DEVICE_TABLE(vrc4173_cardu_id_table) = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_NAPCCARD) },
         {0, }
 };
 
diff --git a/drivers/pcmcia/xxs1500_ss.c b/drivers/pcmcia/xxs1500_ss.c
index 379f4218857d..fd5fbd10aad0 100644
--- a/drivers/pcmcia/xxs1500_ss.c
+++ b/drivers/pcmcia/xxs1500_ss.c
@@ -21,7 +21,6 @@
 #include <pcmcia/cistpl.h>
 
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/mach-au1x00/au1000.h>
 
 #define MEM_MAP_SIZE	0x400000
@@ -321,18 +320,7 @@ static struct platform_driver xxs1500_pcmcia_socket_driver = {
 	.remove		= __devexit_p(xxs1500_pcmcia_remove),
 };
 
-int __init xxs1500_pcmcia_socket_load(void)
-{
-	return platform_driver_register(&xxs1500_pcmcia_socket_driver);
-}
-
-void  __exit xxs1500_pcmcia_socket_unload(void)
-{
-	platform_driver_unregister(&xxs1500_pcmcia_socket_driver);
-}
-
-module_init(xxs1500_pcmcia_socket_load);
-module_exit(xxs1500_pcmcia_socket_unload);
+module_platform_driver(xxs1500_pcmcia_socket_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("PCMCIA Socket Services for MyCable XXS1500 systems");
diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c
index 849c0c11d2af..d07f9ac8c41d 100644
--- a/drivers/pcmcia/yenta_socket.c
+++ b/drivers/pcmcia/yenta_socket.c
@@ -1352,7 +1352,7 @@ static const struct dev_pm_ops yenta_pm_ops = {
 		.driver_data	= CARDBUS_TYPE_##type,	\
 	}
 
-static struct pci_device_id yenta_table[] = {
+static DEFINE_PCI_DEVICE_TABLE(yenta_table) = {
 	CB_ID(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_1031, TI),
 
 	/*
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 2dc02c972ce9..2a262f5c5c0c 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -26,6 +26,10 @@ config ACER_WMI
 	depends on RFKILL || RFKILL = n
 	depends on ACPI_WMI
 	select INPUT_SPARSEKMAP
+	# Acer WMI depends on ACPI_VIDEO when ACPI is enabled
+	# but for select to work, need to select ACPI_VIDEO's dependencies, ick
+        select VIDEO_OUTPUT_CONTROL if ACPI
+        select ACPI_VIDEO if ACPI
 	---help---
 	  This is a driver for newer Acer (and Wistron) laptops. It adds
 	  wireless radio and bluetooth control, and on some laptops,
@@ -54,7 +58,6 @@ config ACERHDF
 config ASUS_LAPTOP
 	tristate "Asus Laptop Extras"
 	depends on ACPI
-	depends on !ACPI_ASUS
 	select LEDS_CLASS
 	select NEW_LEDS
 	select BACKLIGHT_CLASS_DEVICE
@@ -460,10 +463,9 @@ config INTEL_MENLOW
 	  If unsure, say N.
 
 config EEEPC_LAPTOP
-	tristate "Eee PC Hotkey Driver (EXPERIMENTAL)"
+	tristate "Eee PC Hotkey Driver"
 	depends on ACPI
 	depends on INPUT
-	depends on EXPERIMENTAL
 	depends on RFKILL || RFKILL = n
 	depends on HOTPLUG_PCI
 	select BACKLIGHT_CLASS_DEVICE
@@ -482,11 +484,10 @@ config EEEPC_LAPTOP
 	  doesn't work on your Eee PC, try eeepc-wmi instead.
 
 config ASUS_WMI
-	tristate "ASUS WMI Driver (EXPERIMENTAL)"
+	tristate "ASUS WMI Driver"
 	depends on ACPI_WMI
 	depends on INPUT
 	depends on HWMON
-	depends on EXPERIMENTAL
 	depends on BACKLIGHT_CLASS_DEVICE
 	depends on RFKILL || RFKILL = n
 	depends on HOTPLUG_PCI
@@ -501,7 +502,7 @@ config ASUS_WMI
 	  be called asus-wmi.
 
 config ASUS_NB_WMI
-	tristate "Asus Notebook WMI Driver (EXPERIMENTAL)"
+	tristate "Asus Notebook WMI Driver"
 	depends on ASUS_WMI
 	---help---
 	  This is a driver for newer Asus notebooks. It adds extra features
@@ -514,7 +515,7 @@ config ASUS_NB_WMI
 	  here.
 
 config EEEPC_WMI
-	tristate "Eee PC WMI Driver (EXPERIMENTAL)"
+	tristate "Eee PC WMI Driver"
 	depends on ASUS_WMI
 	---help---
 	  This is a driver for newer Eee PC laptops. It adds extra features
@@ -559,38 +560,6 @@ config MSI_WMI
 	 To compile this driver as a module, choose M here: the module will
 	 be called msi-wmi.
 
-config ACPI_ASUS
-	tristate "ASUS/Medion Laptop Extras (DEPRECATED)"
-	depends on ACPI
-	select BACKLIGHT_CLASS_DEVICE
-	---help---
-	  This driver provides support for extra features of ACPI-compatible
-	  ASUS laptops. As some of Medion laptops are made by ASUS, it may also
-	  support some Medion laptops (such as 9675 for example).  It makes all
-	  the extra buttons generate standard ACPI events that go through
-	  /proc/acpi/events, and (on some models) adds support for changing the
-	  display brightness and output, switching the LCD backlight on and off,
-	  and most importantly, allows you to blink those fancy LEDs intended
-	  for reporting mail and wireless status.
-
-	  Note: display switching code is currently considered EXPERIMENTAL,
-	  toying with these values may even lock your machine.
-
-	  All settings are changed via /proc/acpi/asus directory entries. Owner
-	  and group for these entries can be set with asus_uid and asus_gid
-	  parameters.
-
-	  More information and a userspace daemon for handling the extra buttons
-	  at <http://acpi4asus.sf.net>.
-
-	  If you have an ACPI-compatible ASUS laptop, say Y or M here. This
-	  driver is still under development, so if your laptop is unsupported or
-	  something works not quite as expected, please use the mailing list
-	  available on the above page (acpi4asus-user@lists.sourceforge.net).
-
-	  NOTE: This driver is deprecated and will probably be removed soon,
-	  use asus-laptop instead.
-
 config TOPSTAR_LAPTOP
 	tristate "Topstar Laptop Extras"
 	depends on ACPI
@@ -604,6 +573,7 @@ config TOPSTAR_LAPTOP
 config ACPI_TOSHIBA
 	tristate "Toshiba Laptop Extras"
 	depends on ACPI
+	depends on ACPI_WMI
 	select LEDS_CLASS
 	select NEW_LEDS
 	depends on BACKLIGHT_CLASS_DEVICE
@@ -746,13 +716,18 @@ config XO15_EBOOK
 
 config SAMSUNG_LAPTOP
 	tristate "Samsung Laptop driver"
-	depends on RFKILL && BACKLIGHT_CLASS_DEVICE && X86
+	depends on X86
+	depends on RFKILL || RFKILL = n
+	depends on BACKLIGHT_CLASS_DEVICE
+	select LEDS_CLASS
+	select NEW_LEDS
 	---help---
 	  This module implements a driver for a wide range of different
 	  Samsung laptops.  It offers control over the different
-	  function keys, wireless LED, LCD backlight level, and
-	  sometimes provides a "performance_control" sysfs file to allow
-	  the performance level of the laptop to be changed.
+	  function keys, wireless LED, LCD backlight level.
+
+	  It may also provide some sysfs files described in
+	  <file:Documentation/ABI/testing/sysfs-platform-samsung-laptop>
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called samsung-laptop.
@@ -781,4 +756,14 @@ config SAMSUNG_Q10
 	  This driver provides support for backlight control on Samsung Q10
 	  and related laptops, including Dell Latitude X200.
 
+config APPLE_GMUX
+	tristate "Apple Gmux Driver"
+	depends on PNP
+	select BACKLIGHT_CLASS_DEVICE
+	---help---
+	  This driver provides support for the gmux device found on many
+	  Apple laptops, which controls the display mux for the hybrid
+	  graphics as well as the backlight. Currently only backlight
+	  control is supported by the driver.
+
 endif # X86_PLATFORM_DEVICES
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index bb947657d490..bf7e4f935b17 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -29,9 +29,12 @@ obj-$(CONFIG_PANASONIC_LAPTOP)	+= panasonic-laptop.o
 obj-$(CONFIG_INTEL_MENLOW)	+= intel_menlow.o
 obj-$(CONFIG_ACPI_WMI)		+= wmi.o
 obj-$(CONFIG_MSI_WMI)		+= msi-wmi.o
-obj-$(CONFIG_ACPI_ASUS)		+= asus_acpi.o
 obj-$(CONFIG_TOPSTAR_LAPTOP)	+= topstar-laptop.o
+
+# toshiba_acpi must link after wmi to ensure that wmi devices are found
+# before toshiba_acpi initializes
 obj-$(CONFIG_ACPI_TOSHIBA)	+= toshiba_acpi.o
+
 obj-$(CONFIG_TOSHIBA_BT_RFKILL)	+= toshiba_bluetooth.o
 obj-$(CONFIG_INTEL_SCU_IPC)	+= intel_scu_ipc.o
 obj-$(CONFIG_INTEL_SCU_IPC_UTIL) += intel_scu_ipcutil.o
@@ -46,3 +49,4 @@ obj-$(CONFIG_MXM_WMI)		+= mxm-wmi.o
 obj-$(CONFIG_INTEL_MID_POWER_BUTTON)	+= intel_mid_powerbtn.o
 obj-$(CONFIG_INTEL_OAKTRAIL)	+= intel_oaktrail.o
 obj-$(CONFIG_SAMSUNG_Q10)	+= samsung-q10.o
+obj-$(CONFIG_APPLE_GMUX)	+= apple-gmux.o
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 1e5290b5396d..c1a3fd8e1243 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -43,6 +43,7 @@
 #include <linux/input/sparse-keymap.h>
 
 #include <acpi/acpi_drivers.h>
+#include <acpi/video.h>
 
 MODULE_AUTHOR("Carlos Corbacho");
 MODULE_DESCRIPTION("Acer Laptop WMI Extras Driver");
@@ -105,13 +106,19 @@ static const struct key_entry acer_wmi_keymap[] = {
 	{KE_KEY, 0x22, {KEY_PROG2} },    /* Arcade */
 	{KE_KEY, 0x23, {KEY_PROG3} },    /* P_Key */
 	{KE_KEY, 0x24, {KEY_PROG4} },    /* Social networking_Key */
+	{KE_KEY, 0x29, {KEY_PROG3} },    /* P_Key for TM8372 */
 	{KE_IGNORE, 0x41, {KEY_MUTE} },
 	{KE_IGNORE, 0x42, {KEY_PREVIOUSSONG} },
+	{KE_IGNORE, 0x4d, {KEY_PREVIOUSSONG} },
 	{KE_IGNORE, 0x43, {KEY_NEXTSONG} },
+	{KE_IGNORE, 0x4e, {KEY_NEXTSONG} },
 	{KE_IGNORE, 0x44, {KEY_PLAYPAUSE} },
+	{KE_IGNORE, 0x4f, {KEY_PLAYPAUSE} },
 	{KE_IGNORE, 0x45, {KEY_STOP} },
+	{KE_IGNORE, 0x50, {KEY_STOP} },
 	{KE_IGNORE, 0x48, {KEY_VOLUMEUP} },
 	{KE_IGNORE, 0x49, {KEY_VOLUMEDOWN} },
+	{KE_IGNORE, 0x4a, {KEY_VOLUMEDOWN} },
 	{KE_IGNORE, 0x61, {KEY_SWITCHVIDEOMODE} },
 	{KE_IGNORE, 0x62, {KEY_BRIGHTNESSUP} },
 	{KE_IGNORE, 0x63, {KEY_BRIGHTNESSDOWN} },
@@ -153,7 +160,14 @@ struct lm_return_value {
 	u16 reserved;
 } __attribute__((packed));
 
-struct wmid3_gds_input_param {	/* Get Device Status input parameter */
+struct wmid3_gds_set_input_param {     /* Set Device Status input parameter */
+	u8 function_num;        /* Function Number */
+	u8 hotkey_number;       /* Hotkey Number */
+	u16 devices;            /* Set Device */
+	u8 volume_value;        /* Volume Value */
+} __attribute__((packed));
+
+struct wmid3_gds_get_input_param {     /* Get Device Status input parameter */
 	u8 function_num;	/* Function Number */
 	u8 hotkey_number;	/* Hotkey Number */
 	u16 devices;		/* Get Device */
@@ -171,6 +185,11 @@ struct hotkey_function_type_aa {
 	u8 length;
 	u16 handle;
 	u16 commun_func_bitmap;
+	u16 application_func_bitmap;
+	u16 media_func_bitmap;
+	u16 display_func_bitmap;
+	u16 others_func_bitmap;
+	u8 commun_fn_key_number;
 } __attribute__((packed));
 
 /*
@@ -207,6 +226,7 @@ static int force_series;
 static bool ec_raw_mode;
 static bool has_type_aa;
 static u16 commun_func_bitmap;
+static u8 commun_fn_key_number;
 
 module_param(mailled, int, 0444);
 module_param(brightness, int, 0444);
@@ -468,6 +488,15 @@ static struct dmi_system_id acer_quirks[] = {
 	},
 	{
 		.callback = dmi_matched,
+		.ident = "Lenovo Ideapad S205 (Brazos)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Brazos"),
+		},
+		.driver_data = &quirk_lenovo_ideapad_s205,
+	},
+	{
+		.callback = dmi_matched,
 		.ident = "Lenovo 3000 N200",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -478,6 +507,25 @@ static struct dmi_system_id acer_quirks[] = {
 	{}
 };
 
+static int video_set_backlight_video_vendor(const struct dmi_system_id *d)
+{
+	interface->capability &= ~ACER_CAP_BRIGHTNESS;
+	pr_info("Brightness must be controlled by generic video driver\n");
+	return 0;
+}
+
+static const struct dmi_system_id video_vendor_dmi_table[] = {
+	{
+		.callback = video_set_backlight_video_vendor,
+		.ident = "Acer TravelMate 4750",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 4750"),
+		},
+	},
+	{}
+};
+
 /* Find which quirks are needed for a particular vendor/ model pair */
 static void find_quirks(void)
 {
@@ -536,8 +584,7 @@ struct acpi_buffer *result)
 	return status;
 }
 
-static acpi_status AMW0_get_u32(u32 *value, u32 cap,
-struct wmi_interface *iface)
+static acpi_status AMW0_get_u32(u32 *value, u32 cap)
 {
 	int err;
 	u8 result;
@@ -607,7 +654,7 @@ struct wmi_interface *iface)
 	return AE_OK;
 }
 
-static acpi_status AMW0_set_u32(u32 value, u32 cap, struct wmi_interface *iface)
+static acpi_status AMW0_set_u32(u32 value, u32 cap)
 {
 	struct wmab_args args;
 
@@ -692,6 +739,7 @@ static const struct acpi_device_id norfkill_ids[] = {
 	{ "VPC2004", 0},
 	{ "IBM0068", 0},
 	{ "LEN0068", 0},
+	{ "SNY5001", 0},	/* sony-laptop in charge */
 	{ "", 0},
 };
 
@@ -827,8 +875,7 @@ WMI_execute_u32(u32 method_id, u32 in, u32 *out)
 	return status;
 }
 
-static acpi_status WMID_get_u32(u32 *value, u32 cap,
-struct wmi_interface *iface)
+static acpi_status WMID_get_u32(u32 *value, u32 cap)
 {
 	acpi_status status;
 	u8 tmp;
@@ -864,7 +911,7 @@ struct wmi_interface *iface)
 	return status;
 }
 
-static acpi_status WMID_set_u32(u32 value, u32 cap, struct wmi_interface *iface)
+static acpi_status WMID_set_u32(u32 value, u32 cap)
 {
 	u32 method_id = 0;
 	char param;
@@ -912,13 +959,13 @@ static acpi_status wmid3_get_device_status(u32 *value, u16 device)
 	struct wmid3_gds_return_value return_value;
 	acpi_status status;
 	union acpi_object *obj;
-	struct wmid3_gds_input_param params = {
+	struct wmid3_gds_get_input_param params = {
 		.function_num = 0x1,
-		.hotkey_number = 0x01,
+		.hotkey_number = commun_fn_key_number,
 		.devices = device,
 	};
 	struct acpi_buffer input = {
-		sizeof(struct wmid3_gds_input_param),
+		sizeof(struct wmid3_gds_get_input_param),
 		&params
 	};
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -981,19 +1028,28 @@ static acpi_status wmid3_set_device_status(u32 value, u16 device)
 	acpi_status status;
 	union acpi_object *obj;
 	u16 devices;
-	struct wmid3_gds_input_param params = {
+	struct wmid3_gds_get_input_param get_params = {
 		.function_num = 0x1,
-		.hotkey_number = 0x01,
+		.hotkey_number = commun_fn_key_number,
 		.devices = commun_func_bitmap,
 	};
-	struct acpi_buffer input = {
-		sizeof(struct wmid3_gds_input_param),
-		&params
+	struct acpi_buffer get_input = {
+		sizeof(struct wmid3_gds_get_input_param),
+		&get_params
+	};
+	struct wmid3_gds_set_input_param set_params = {
+		.function_num = 0x2,
+		.hotkey_number = commun_fn_key_number,
+		.devices = commun_func_bitmap,
+	};
+	struct acpi_buffer set_input = {
+		sizeof(struct wmid3_gds_set_input_param),
+		&set_params
 	};
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct acpi_buffer output2 = { ACPI_ALLOCATE_BUFFER, NULL };
 
-	status = wmi_evaluate_method(WMID_GUID3, 0, 0x2, &input, &output);
+	status = wmi_evaluate_method(WMID_GUID3, 0, 0x2, &get_input, &output);
 	if (ACPI_FAILURE(status))
 		return status;
 
@@ -1006,7 +1062,7 @@ static acpi_status wmid3_set_device_status(u32 value, u16 device)
 		return AE_ERROR;
 	}
 	if (obj->buffer.length != 8) {
-		pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+		pr_warn("Unknown buffer length %d\n", obj->buffer.length);
 		kfree(obj);
 		return AE_ERROR;
 	}
@@ -1015,18 +1071,16 @@ static acpi_status wmid3_set_device_status(u32 value, u16 device)
 	kfree(obj);
 
 	if (return_value.error_code || return_value.ec_return_value) {
-		pr_warning("Get Current Device Status failed: "
-			"0x%x - 0x%x\n", return_value.error_code,
+		pr_warn("Get Current Device Status failed: 0x%x - 0x%x\n",
+			return_value.error_code,
 			return_value.ec_return_value);
 		return status;
 	}
 
 	devices = return_value.devices;
-	params.function_num = 0x2;
-	params.hotkey_number = 0x01;
-	params.devices = (value) ? (devices | device) : (devices & ~device);
+	set_params.devices = (value) ? (devices | device) : (devices & ~device);
 
-	status = wmi_evaluate_method(WMID_GUID3, 0, 0x1, &input, &output2);
+	status = wmi_evaluate_method(WMID_GUID3, 0, 0x1, &set_input, &output2);
 	if (ACPI_FAILURE(status))
 		return status;
 
@@ -1039,7 +1093,7 @@ static acpi_status wmid3_set_device_status(u32 value, u16 device)
 		return AE_ERROR;
 	}
 	if (obj->buffer.length != 4) {
-		pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+		pr_warn("Unknown buffer length %d\n", obj->buffer.length);
 		kfree(obj);
 		return AE_ERROR;
 	}
@@ -1048,8 +1102,8 @@ static acpi_status wmid3_set_device_status(u32 value, u16 device)
 	kfree(obj);
 
 	if (return_value.error_code || return_value.ec_return_value)
-		pr_warning("Set Device Status failed: "
-			"0x%x - 0x%x\n", return_value.error_code,
+		pr_warn("Set Device Status failed: 0x%x - 0x%x\n",
+			return_value.error_code,
 			return_value.ec_return_value);
 
 	return status;
@@ -1096,6 +1150,8 @@ static void type_aa_dmi_decode(const struct dmi_header *header, void *dummy)
 		interface->capability |= ACER_CAP_THREEG;
 	if (type_aa->commun_func_bitmap & ACER_WMID3_GDS_BLUETOOTH)
 		interface->capability |= ACER_CAP_BLUETOOTH;
+
+	commun_fn_key_number = type_aa->commun_fn_key_number;
 }
 
 static acpi_status WMID_set_capabilities(void)
@@ -1154,15 +1210,15 @@ static acpi_status get_u32(u32 *value, u32 cap)
 
 	switch (interface->type) {
 	case ACER_AMW0:
-		status = AMW0_get_u32(value, cap, interface);
+		status = AMW0_get_u32(value, cap);
 		break;
 	case ACER_AMW0_V2:
 		if (cap == ACER_CAP_MAILLED) {
-			status = AMW0_get_u32(value, cap, interface);
+			status = AMW0_get_u32(value, cap);
 			break;
 		}
 	case ACER_WMID:
-		status = WMID_get_u32(value, cap, interface);
+		status = WMID_get_u32(value, cap);
 		break;
 	case ACER_WMID_v2:
 		if (cap & (ACER_CAP_WIRELESS |
@@ -1170,7 +1226,7 @@ static acpi_status get_u32(u32 *value, u32 cap)
 			   ACER_CAP_THREEG))
 			status = wmid_v2_get_u32(value, cap);
 		else if (wmi_has_guid(WMID_GUID2))
-			status = WMID_get_u32(value, cap, interface);
+			status = WMID_get_u32(value, cap);
 		break;
 	}
 
@@ -1184,10 +1240,10 @@ static acpi_status set_u32(u32 value, u32 cap)
 	if (interface->capability & cap) {
 		switch (interface->type) {
 		case ACER_AMW0:
-			return AMW0_set_u32(value, cap, interface);
+			return AMW0_set_u32(value, cap);
 		case ACER_AMW0_V2:
 			if (cap == ACER_CAP_MAILLED)
-				return AMW0_set_u32(value, cap, interface);
+				return AMW0_set_u32(value, cap);
 
 			/*
 			 * On some models, some WMID methods don't toggle
@@ -1197,21 +1253,21 @@ static acpi_status set_u32(u32 value, u32 cap)
 			 */
 			if (cap == ACER_CAP_WIRELESS ||
 				cap == ACER_CAP_BLUETOOTH) {
-				status = WMID_set_u32(value, cap, interface);
+				status = WMID_set_u32(value, cap);
 				if (ACPI_FAILURE(status))
 					return status;
 
-				return AMW0_set_u32(value, cap, interface);
+				return AMW0_set_u32(value, cap);
 			}
 		case ACER_WMID:
-			return WMID_set_u32(value, cap, interface);
+			return WMID_set_u32(value, cap);
 		case ACER_WMID_v2:
 			if (cap & (ACER_CAP_WIRELESS |
 				   ACER_CAP_BLUETOOTH |
 				   ACER_CAP_THREEG))
 				return wmid_v2_set_u32(value, cap);
 			else if (wmi_has_guid(WMID_GUID2))
-				return WMID_set_u32(value, cap, interface);
+				return WMID_set_u32(value, cap);
 		default:
 			return AE_BAD_PARAMETER;
 		}
@@ -1488,8 +1544,8 @@ static ssize_t show_bool_threeg(struct device *dev,
 	u32 result; \
 	acpi_status status;
 
-	pr_info("This threeg sysfs will be removed in 2012"
-		" - used by: %s\n", current->comm);
+	pr_info("This threeg sysfs will be removed in 2012 - used by: %s\n",
+		current->comm);
 	status = get_u32(&result, ACER_CAP_THREEG);
 	if (ACPI_SUCCESS(status))
 		return sprintf(buf, "%u\n", result);
@@ -1501,8 +1557,8 @@ static ssize_t set_bool_threeg(struct device *dev,
 {
 	u32 tmp = simple_strtoul(buf, NULL, 10);
 	acpi_status status = set_u32(tmp, ACER_CAP_THREEG);
-	pr_info("This threeg sysfs will be removed in 2012"
-		" - used by: %s\n", current->comm);
+	pr_info("This threeg sysfs will be removed in 2012 - used by: %s\n",
+		current->comm);
 	if (ACPI_FAILURE(status))
 		return -EINVAL;
 	return count;
@@ -1513,8 +1569,8 @@ static DEVICE_ATTR(threeg, S_IRUGO | S_IWUSR, show_bool_threeg,
 static ssize_t show_interface(struct device *dev, struct device_attribute *attr,
 	char *buf)
 {
-	pr_info("This interface sysfs will be removed in 2012"
-		" - used by: %s\n", current->comm);
+	pr_info("This interface sysfs will be removed in 2012 - used by: %s\n",
+		current->comm);
 	switch (interface->type) {
 	case ACER_AMW0:
 		return sprintf(buf, "AMW0\n");
@@ -1981,9 +2037,13 @@ static int __init acer_wmi_init(void)
 	set_quirks();
 
 	if (acpi_video_backlight_support()) {
-		interface->capability &= ~ACER_CAP_BRIGHTNESS;
-		pr_info("Brightness must be controlled by "
-		       "generic video driver\n");
+		if (dmi_check_system(video_vendor_dmi_table)) {
+			acpi_video_unregister();
+		} else {
+			interface->capability &= ~ACER_CAP_BRIGHTNESS;
+			pr_info("Brightness must be controlled by "
+				"acpi video driver\n");
+		}
 	}
 
 	if (wmi_has_guid(WMID_GUID3)) {
@@ -2008,7 +2068,7 @@ static int __init acer_wmi_init(void)
 
 	err = platform_driver_register(&acer_platform_driver);
 	if (err) {
-		pr_err("Unable to register platform driver.\n");
+		pr_err("Unable to register platform driver\n");
 		goto error_platform_register;
 	}
 
diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index 760c6d7624fe..bc8384c6f3eb 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -244,12 +244,11 @@ static void acerhdf_change_fanstate(int state)
 	unsigned char cmd;
 
 	if (verbose)
-		pr_notice("fan %s\n", (state == ACERHDF_FAN_OFF) ?
-				"OFF" : "ON");
+		pr_notice("fan %s\n", state == ACERHDF_FAN_OFF ? "OFF" : "ON");
 
 	if ((state != ACERHDF_FAN_OFF) && (state != ACERHDF_FAN_AUTO)) {
 		pr_err("invalid fan state %d requested, setting to auto!\n",
-			state);
+		       state);
 		state = ACERHDF_FAN_AUTO;
 	}
 
@@ -264,19 +263,18 @@ static void acerhdf_check_param(struct thermal_zone_device *thermal)
 {
 	if (fanon > ACERHDF_MAX_FANON) {
 		pr_err("fanon temperature too high, set to %d\n",
-				ACERHDF_MAX_FANON);
+		       ACERHDF_MAX_FANON);
 		fanon = ACERHDF_MAX_FANON;
 	}
 
 	if (kernelmode && prev_interval != interval) {
 		if (interval > ACERHDF_MAX_INTERVAL) {
 			pr_err("interval too high, set to %d\n",
-				ACERHDF_MAX_INTERVAL);
+			       ACERHDF_MAX_INTERVAL);
 			interval = ACERHDF_MAX_INTERVAL;
 		}
 		if (verbose)
-			pr_notice("interval changed to: %d\n",
-					interval);
+			pr_notice("interval changed to: %d\n", interval);
 		thermal->polling_delay = interval*1000;
 		prev_interval = interval;
 	}
@@ -587,8 +585,8 @@ static int acerhdf_check_hardware(void)
 	}
 
 	if (!bios_cfg) {
-		pr_err("unknown (unsupported) BIOS version %s/%s/%s, "
-			"please report, aborting!\n", vendor, product, version);
+		pr_err("unknown (unsupported) BIOS version %s/%s/%s, please report, aborting!\n",
+		       vendor, product, version);
 		return -EINVAL;
 	}
 
@@ -598,8 +596,7 @@ static int acerhdf_check_hardware(void)
 	 */
 	if (!kernelmode) {
 		pr_notice("Fan control off, to enable do:\n");
-		pr_notice("echo -n \"enabled\" > "
-			"/sys/class/thermal/thermal_zone0/mode\n");
+		pr_notice("echo -n \"enabled\" > /sys/class/thermal/thermal_zone0/mode\n");
 	}
 
 	return 0;
diff --git a/drivers/platform/x86/amilo-rfkill.c b/drivers/platform/x86/amilo-rfkill.c
index 19170bb7700b..a514bf66fdd7 100644
--- a/drivers/platform/x86/amilo-rfkill.c
+++ b/drivers/platform/x86/amilo-rfkill.c
@@ -97,9 +97,12 @@ static struct rfkill *amilo_rfkill_dev;
 
 static int __devinit amilo_rfkill_probe(struct platform_device *device)
 {
+	int rc;
 	const struct dmi_system_id *system_id =
 		dmi_first_match(amilo_rfkill_id_table);
-	int rc;
+
+	if (!system_id)
+		return -ENXIO;
 
 	amilo_rfkill_dev = rfkill_alloc(KBUILD_MODNAME, &device->dev,
 					RFKILL_TYPE_WLAN,
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
new file mode 100644
index 000000000000..8a582bdfdc76
--- /dev/null
+++ b/drivers/platform/x86/apple-gmux.c
@@ -0,0 +1,244 @@
+/*
+ *  Gmux driver for Apple laptops
+ *
+ *  Copyright (C) Canonical Ltd. <seth.forshee@canonical.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/backlight.h>
+#include <linux/acpi.h>
+#include <linux/pnp.h>
+#include <linux/apple_bl.h>
+#include <linux/slab.h>
+#include <acpi/video.h>
+#include <asm/io.h>
+
+struct apple_gmux_data {
+	unsigned long iostart;
+	unsigned long iolen;
+
+	struct backlight_device *bdev;
+};
+
+/*
+ * gmux port offsets. Many of these are not yet used, but may be in the
+ * future, and it's useful to have them documented here anyhow.
+ */
+#define GMUX_PORT_VERSION_MAJOR		0x04
+#define GMUX_PORT_VERSION_MINOR		0x05
+#define GMUX_PORT_VERSION_RELEASE	0x06
+#define GMUX_PORT_SWITCH_DISPLAY	0x10
+#define GMUX_PORT_SWITCH_GET_DISPLAY	0x11
+#define GMUX_PORT_INTERRUPT_ENABLE	0x14
+#define GMUX_PORT_INTERRUPT_STATUS	0x16
+#define GMUX_PORT_SWITCH_DDC		0x28
+#define GMUX_PORT_SWITCH_EXTERNAL	0x40
+#define GMUX_PORT_SWITCH_GET_EXTERNAL	0x41
+#define GMUX_PORT_DISCRETE_POWER	0x50
+#define GMUX_PORT_MAX_BRIGHTNESS	0x70
+#define GMUX_PORT_BRIGHTNESS		0x74
+
+#define GMUX_MIN_IO_LEN			(GMUX_PORT_BRIGHTNESS + 4)
+
+#define GMUX_INTERRUPT_ENABLE		0xff
+#define GMUX_INTERRUPT_DISABLE		0x00
+
+#define GMUX_INTERRUPT_STATUS_ACTIVE	0
+#define GMUX_INTERRUPT_STATUS_DISPLAY	(1 << 0)
+#define GMUX_INTERRUPT_STATUS_POWER	(1 << 2)
+#define GMUX_INTERRUPT_STATUS_HOTPLUG	(1 << 3)
+
+#define GMUX_BRIGHTNESS_MASK		0x00ffffff
+#define GMUX_MAX_BRIGHTNESS		GMUX_BRIGHTNESS_MASK
+
+static inline u8 gmux_read8(struct apple_gmux_data *gmux_data, int port)
+{
+	return inb(gmux_data->iostart + port);
+}
+
+static inline void gmux_write8(struct apple_gmux_data *gmux_data, int port,
+			       u8 val)
+{
+	outb(val, gmux_data->iostart + port);
+}
+
+static inline u32 gmux_read32(struct apple_gmux_data *gmux_data, int port)
+{
+	return inl(gmux_data->iostart + port);
+}
+
+static int gmux_get_brightness(struct backlight_device *bd)
+{
+	struct apple_gmux_data *gmux_data = bl_get_data(bd);
+	return gmux_read32(gmux_data, GMUX_PORT_BRIGHTNESS) &
+	       GMUX_BRIGHTNESS_MASK;
+}
+
+static int gmux_update_status(struct backlight_device *bd)
+{
+	struct apple_gmux_data *gmux_data = bl_get_data(bd);
+	u32 brightness = bd->props.brightness;
+
+	/*
+	 * Older gmux versions require writing out lower bytes first then
+	 * setting the upper byte to 0 to flush the values. Newer versions
+	 * accept a single u32 write, but the old method also works, so we
+	 * just use the old method for all gmux versions.
+	 */
+	gmux_write8(gmux_data, GMUX_PORT_BRIGHTNESS, brightness);
+	gmux_write8(gmux_data, GMUX_PORT_BRIGHTNESS + 1, brightness >> 8);
+	gmux_write8(gmux_data, GMUX_PORT_BRIGHTNESS + 2, brightness >> 16);
+	gmux_write8(gmux_data, GMUX_PORT_BRIGHTNESS + 3, 0);
+
+	return 0;
+}
+
+static const struct backlight_ops gmux_bl_ops = {
+	.get_brightness = gmux_get_brightness,
+	.update_status = gmux_update_status,
+};
+
+static int __devinit gmux_probe(struct pnp_dev *pnp,
+				const struct pnp_device_id *id)
+{
+	struct apple_gmux_data *gmux_data;
+	struct resource *res;
+	struct backlight_properties props;
+	struct backlight_device *bdev;
+	u8 ver_major, ver_minor, ver_release;
+	int ret = -ENXIO;
+
+	gmux_data = kzalloc(sizeof(*gmux_data), GFP_KERNEL);
+	if (!gmux_data)
+		return -ENOMEM;
+	pnp_set_drvdata(pnp, gmux_data);
+
+	res = pnp_get_resource(pnp, IORESOURCE_IO, 0);
+	if (!res) {
+		pr_err("Failed to find gmux I/O resource\n");
+		goto err_free;
+	}
+
+	gmux_data->iostart = res->start;
+	gmux_data->iolen = res->end - res->start;
+
+	if (gmux_data->iolen < GMUX_MIN_IO_LEN) {
+		pr_err("gmux I/O region too small (%lu < %u)\n",
+		       gmux_data->iolen, GMUX_MIN_IO_LEN);
+		goto err_free;
+	}
+
+	if (!request_region(gmux_data->iostart, gmux_data->iolen,
+			    "Apple gmux")) {
+		pr_err("gmux I/O already in use\n");
+		goto err_free;
+	}
+
+	/*
+	 * On some machines the gmux is in ACPI even thought the machine
+	 * doesn't really have a gmux. Check for invalid version information
+	 * to detect this.
+	 */
+	ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR);
+	ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR);
+	ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE);
+	if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) {
+		pr_info("gmux device not present\n");
+		ret = -ENODEV;
+		goto err_release;
+	}
+
+	pr_info("Found gmux version %d.%d.%d\n", ver_major, ver_minor,
+		ver_release);
+
+	memset(&props, 0, sizeof(props));
+	props.type = BACKLIGHT_PLATFORM;
+	props.max_brightness = gmux_read32(gmux_data, GMUX_PORT_MAX_BRIGHTNESS);
+
+	/*
+	 * Currently it's assumed that the maximum brightness is less than
+	 * 2^24 for compatibility with old gmux versions. Cap the max
+	 * brightness at this value, but print a warning if the hardware
+	 * reports something higher so that it can be fixed.
+	 */
+	if (WARN_ON(props.max_brightness > GMUX_MAX_BRIGHTNESS))
+		props.max_brightness = GMUX_MAX_BRIGHTNESS;
+
+	bdev = backlight_device_register("gmux_backlight", &pnp->dev,
+					 gmux_data, &gmux_bl_ops, &props);
+	if (IS_ERR(bdev)) {
+		ret = PTR_ERR(bdev);
+		goto err_release;
+	}
+
+	gmux_data->bdev = bdev;
+	bdev->props.brightness = gmux_get_brightness(bdev);
+	backlight_update_status(bdev);
+
+	/*
+	 * The backlight situation on Macs is complicated. If the gmux is
+	 * present it's the best choice, because it always works for
+	 * backlight control and supports more levels than other options.
+	 * Disable the other backlight choices.
+	 */
+	acpi_video_unregister();
+	apple_bl_unregister();
+
+	return 0;
+
+err_release:
+	release_region(gmux_data->iostart, gmux_data->iolen);
+err_free:
+	kfree(gmux_data);
+	return ret;
+}
+
+static void __devexit gmux_remove(struct pnp_dev *pnp)
+{
+	struct apple_gmux_data *gmux_data = pnp_get_drvdata(pnp);
+
+	backlight_device_unregister(gmux_data->bdev);
+	release_region(gmux_data->iostart, gmux_data->iolen);
+	kfree(gmux_data);
+
+	acpi_video_register();
+	apple_bl_register();
+}
+
+static const struct pnp_device_id gmux_device_ids[] = {
+	{"APP000B", 0},
+	{"", 0}
+};
+
+static struct pnp_driver gmux_pnp_driver = {
+	.name		= "apple-gmux",
+	.probe		= gmux_probe,
+	.remove		= __devexit_p(gmux_remove),
+	.id_table	= gmux_device_ids,
+};
+
+static int __init apple_gmux_init(void)
+{
+	return pnp_register_driver(&gmux_pnp_driver);
+}
+
+static void __exit apple_gmux_exit(void)
+{
+	pnp_unregister_driver(&gmux_pnp_driver);
+}
+
+module_init(apple_gmux_init);
+module_exit(apple_gmux_exit);
+
+MODULE_AUTHOR("Seth Forshee <seth.forshee@canonical.com>");
+MODULE_DESCRIPTION("Apple Gmux Driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(pnp, gmux_device_ids);
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index b7944f903886..e38f91be0b10 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -81,6 +81,19 @@ static uint wapf = 1;
 module_param(wapf, uint, 0444);
 MODULE_PARM_DESC(wapf, "WAPF value");
 
+static char *wled_type = "unknown";
+static char *bled_type = "unknown";
+
+module_param(wled_type, charp, 0444);
+MODULE_PARM_DESC(wlan_status, "Set the wled type on boot "
+		 "(unknown, led or rfkill). "
+		 "default is unknown");
+
+module_param(bled_type, charp, 0444);
+MODULE_PARM_DESC(bled_type, "Set the bled type on boot "
+		 "(unknown, led or rfkill). "
+		 "default is unknown");
+
 static int wlan_status = 1;
 static int bluetooth_status = 1;
 static int wimax_status = -1;
@@ -137,6 +150,11 @@ MODULE_PARM_DESC(als_status, "Set the ALS status on boot "
 #define WM_RSTS		0x08    /* internal wimax */
 #define WW_RSTS		0x20    /* internal wwan */
 
+/* WLED and BLED type */
+#define TYPE_UNKNOWN	0
+#define TYPE_LED	1
+#define TYPE_RFKILL	2
+
 /* LED */
 #define METHOD_MLED		"MLED"
 #define METHOD_TLED		"TLED"
@@ -218,8 +236,9 @@ struct asus_led {
 /*
  * Same thing for rfkill
  */
-struct asus_pega_rfkill {
-	int control_id;		/* type of control. Maps to PEGA_* values */
+struct asus_rfkill {
+	/* type of control. Maps to PEGA_* values or *_RSTS  */
+	int control_id;
 	struct rfkill *rfkill;
 	struct asus_laptop *asus;
 };
@@ -240,6 +259,8 @@ struct asus_laptop {
 	struct key_entry *keymap;
 	struct input_polled_dev *pega_accel_poll;
 
+	struct asus_led wled;
+	struct asus_led bled;
 	struct asus_led mled;
 	struct asus_led tled;
 	struct asus_led rled;
@@ -248,6 +269,8 @@ struct asus_laptop {
 	struct asus_led kled;
 	struct workqueue_struct *led_workqueue;
 
+	int wled_type;
+	int bled_type;
 	int wireless_status;
 	bool have_rsts;
 	bool is_pega_lucid;
@@ -256,11 +279,11 @@ struct asus_laptop {
 	int pega_acc_y;
 	int pega_acc_z;
 
-	struct rfkill *gps_rfkill;
-
-	struct asus_pega_rfkill wlanrfk;
-	struct asus_pega_rfkill btrfk;
-	struct asus_pega_rfkill wwanrfk;
+	struct asus_rfkill wlan;
+	struct asus_rfkill bluetooth;
+	struct asus_rfkill wwan;
+	struct asus_rfkill wimax;
+	struct asus_rfkill gps;
 
 	acpi_handle handle;	/* the handle of the hotk device */
 	u32 ledd_status;	/* status of the LED display */
@@ -274,6 +297,7 @@ static const struct key_entry asus_keymap[] = {
 	{KE_KEY, 0x02, { KEY_SCREENLOCK } },
 	{KE_KEY, 0x05, { KEY_WLAN } },
 	{KE_KEY, 0x08, { KEY_F13 } },
+	{KE_KEY, 0x09, { KEY_PROG2 } }, /* Dock */
 	{KE_KEY, 0x17, { KEY_ZOOM } },
 	{KE_KEY, 0x1f, { KEY_BATTERY } },
 	/* End of Lenovo SL Specific keycodes */
@@ -299,6 +323,8 @@ static const struct key_entry asus_keymap[] = {
 	{KE_KEY, 0x62, { KEY_SWITCHVIDEOMODE } },
 	{KE_KEY, 0x63, { KEY_SWITCHVIDEOMODE } },
 	{KE_KEY, 0x6B, { KEY_F13 } }, /* Lock Touchpad */
+	{KE_KEY, 0x6C, { KEY_SLEEP } }, /* Suspend */
+	{KE_KEY, 0x6D, { KEY_SLEEP } }, /* Hibernate */
 	{KE_KEY, 0x7E, { KEY_BLUETOOTH } },
 	{KE_KEY, 0x7D, { KEY_BLUETOOTH } },
 	{KE_KEY, 0x82, { KEY_CAMERA } },
@@ -601,6 +627,10 @@ static enum led_brightness asus_kled_cdev_get(struct led_classdev *led_cdev)
 
 static void asus_led_exit(struct asus_laptop *asus)
 {
+	if (!IS_ERR_OR_NULL(asus->wled.led.dev))
+		led_classdev_unregister(&asus->wled.led);
+	if (!IS_ERR_OR_NULL(asus->bled.led.dev))
+		led_classdev_unregister(&asus->bled.led);
 	if (!IS_ERR_OR_NULL(asus->mled.led.dev))
 		led_classdev_unregister(&asus->mled.led);
 	if (!IS_ERR_OR_NULL(asus->tled.led.dev))
@@ -642,7 +672,7 @@ static int asus_led_register(struct asus_laptop *asus,
 
 static int asus_led_init(struct asus_laptop *asus)
 {
-	int r;
+	int r = 0;
 
 	/*
 	 * The Pegatron Lucid has no physical leds, but all methods are
@@ -661,6 +691,16 @@ static int asus_led_init(struct asus_laptop *asus)
 	if (!asus->led_workqueue)
 		return -ENOMEM;
 
+	if (asus->wled_type == TYPE_LED)
+		r = asus_led_register(asus, &asus->wled, "asus::wlan",
+				      METHOD_WLAN);
+	if (r)
+		goto error;
+	if (asus->bled_type == TYPE_LED)
+		r = asus_led_register(asus, &asus->bled, "asus::bluetooth",
+				      METHOD_BLUETOOTH);
+	if (r)
+		goto error;
 	r = asus_led_register(asus, &asus->mled, "asus::mail", METHOD_MLED);
 	if (r)
 		goto error;
@@ -963,7 +1003,7 @@ static ssize_t store_wlan(struct device *dev, struct device_attribute *attr,
 	return sysfs_acpi_set(asus, buf, count, METHOD_WLAN);
 }
 
-/*
+/*e
  * Bluetooth
  */
 static int asus_bluetooth_set(struct asus_laptop *asus, int status)
@@ -1228,7 +1268,7 @@ static ssize_t store_gps(struct device *dev, struct device_attribute *attr,
 	ret = asus_gps_switch(asus, !!value);
 	if (ret)
 		return ret;
-	rfkill_set_sw_state(asus->gps_rfkill, !value);
+	rfkill_set_sw_state(asus->gps.rfkill, !value);
 	return rv;
 }
 
@@ -1246,90 +1286,139 @@ static const struct rfkill_ops asus_gps_rfkill_ops = {
 	.set_block = asus_gps_rfkill_set,
 };
 
+static int asus_rfkill_set(void *data, bool blocked)
+{
+	struct asus_rfkill *rfk = data;
+	struct asus_laptop *asus = rfk->asus;
+
+	if (rfk->control_id == WL_RSTS)
+		return asus_wlan_set(asus, !blocked);
+	else if (rfk->control_id == BT_RSTS)
+		return asus_bluetooth_set(asus, !blocked);
+	else if (rfk->control_id == WM_RSTS)
+		return asus_wimax_set(asus, !blocked);
+	else if (rfk->control_id == WW_RSTS)
+		return asus_wwan_set(asus, !blocked);
+
+	return -EINVAL;
+}
+
+static const struct rfkill_ops asus_rfkill_ops = {
+	.set_block = asus_rfkill_set,
+};
+
+static void asus_rfkill_terminate(struct asus_rfkill *rfk)
+{
+	if (!rfk->rfkill)
+		return ;
+
+	rfkill_unregister(rfk->rfkill);
+	rfkill_destroy(rfk->rfkill);
+	rfk->rfkill = NULL;
+}
+
 static void asus_rfkill_exit(struct asus_laptop *asus)
 {
-	if (asus->gps_rfkill) {
-		rfkill_unregister(asus->gps_rfkill);
-		rfkill_destroy(asus->gps_rfkill);
-		asus->gps_rfkill = NULL;
-	}
+	asus_rfkill_terminate(&asus->wwan);
+	asus_rfkill_terminate(&asus->bluetooth);
+	asus_rfkill_terminate(&asus->wlan);
+	asus_rfkill_terminate(&asus->gps);
 }
 
-static int asus_rfkill_init(struct asus_laptop *asus)
+static int asus_rfkill_setup(struct asus_laptop *asus, struct asus_rfkill *rfk,
+			     const char *name, int control_id, int type,
+			     const struct rfkill_ops *ops)
 {
 	int result;
 
-	if (acpi_check_handle(asus->handle, METHOD_GPS_ON, NULL) ||
-	    acpi_check_handle(asus->handle, METHOD_GPS_OFF, NULL) ||
-	    acpi_check_handle(asus->handle, METHOD_GPS_STATUS, NULL))
-		return 0;
-
-	asus->gps_rfkill = rfkill_alloc("asus-gps", &asus->platform_device->dev,
-					RFKILL_TYPE_GPS,
-					&asus_gps_rfkill_ops, asus);
-	if (!asus->gps_rfkill)
+	rfk->control_id = control_id;
+	rfk->asus = asus;
+	rfk->rfkill = rfkill_alloc(name, &asus->platform_device->dev,
+				   type, ops, rfk);
+	if (!rfk->rfkill)
 		return -EINVAL;
 
-	result = rfkill_register(asus->gps_rfkill);
+	result = rfkill_register(rfk->rfkill);
 	if (result) {
-		rfkill_destroy(asus->gps_rfkill);
-		asus->gps_rfkill = NULL;
+		rfkill_destroy(rfk->rfkill);
+		rfk->rfkill = NULL;
 	}
 
 	return result;
 }
 
-static int pega_rfkill_set(void *data, bool blocked)
+static int asus_rfkill_init(struct asus_laptop *asus)
 {
-	struct asus_pega_rfkill *pega_rfk = data;
+	int result = 0;
 
-	int ret = asus_pega_lucid_set(pega_rfk->asus, pega_rfk->control_id, !blocked);
-	pr_warn("Setting rfkill %d, to %d; returned %d\n", pega_rfk->control_id, !blocked, ret);
+	if (asus->is_pega_lucid)
+		return -ENODEV;
 
-	return ret;
-}
+	if (!acpi_check_handle(asus->handle, METHOD_GPS_ON, NULL) &&
+	    !acpi_check_handle(asus->handle, METHOD_GPS_OFF, NULL) &&
+	    !acpi_check_handle(asus->handle, METHOD_GPS_STATUS, NULL))
+		result = asus_rfkill_setup(asus, &asus->gps, "asus-gps",
+					   -1, RFKILL_TYPE_GPS,
+					   &asus_gps_rfkill_ops);
+	if (result)
+		goto exit;
 
-static const struct rfkill_ops pega_rfkill_ops = {
-	.set_block = pega_rfkill_set,
-};
 
-static void pega_rfkill_terminate(struct asus_pega_rfkill *pega_rfk)
-{
-	pr_warn("Terminating %d\n", pega_rfk->control_id);
-	if (pega_rfk->rfkill) {
-		rfkill_unregister(pega_rfk->rfkill);
-		rfkill_destroy(pega_rfk->rfkill);
-		pega_rfk->rfkill = NULL;
-	}
-}
+	if (!acpi_check_handle(asus->handle, METHOD_WLAN, NULL) &&
+	    asus->wled_type == TYPE_RFKILL)
+		result = asus_rfkill_setup(asus, &asus->wlan, "asus-wlan",
+					   WL_RSTS, RFKILL_TYPE_WLAN,
+					   &asus_rfkill_ops);
+	if (result)
+		goto exit;
 
-static void pega_rfkill_exit(struct asus_laptop *asus)
-{
-	pega_rfkill_terminate(&asus->wwanrfk);
-	pega_rfkill_terminate(&asus->btrfk);
-	pega_rfkill_terminate(&asus->wlanrfk);
+	if (!acpi_check_handle(asus->handle, METHOD_BLUETOOTH, NULL) &&
+	    asus->bled_type == TYPE_RFKILL)
+		result = asus_rfkill_setup(asus, &asus->bluetooth,
+					   "asus-bluetooth", BT_RSTS,
+					   RFKILL_TYPE_BLUETOOTH,
+					   &asus_rfkill_ops);
+	if (result)
+		goto exit;
+
+	if (!acpi_check_handle(asus->handle, METHOD_WWAN, NULL))
+		result = asus_rfkill_setup(asus, &asus->wwan, "asus-wwan",
+					   WW_RSTS, RFKILL_TYPE_WWAN,
+					   &asus_rfkill_ops);
+	if (result)
+		goto exit;
+
+	if (!acpi_check_handle(asus->handle, METHOD_WIMAX, NULL))
+		result = asus_rfkill_setup(asus, &asus->wimax, "asus-wimax",
+					   WM_RSTS, RFKILL_TYPE_WIMAX,
+					   &asus_rfkill_ops);
+	if (result)
+		goto exit;
+
+exit:
+	if (result)
+		asus_rfkill_exit(asus);
+
+	return result;
 }
 
-static int pega_rfkill_setup(struct asus_laptop *asus, struct asus_pega_rfkill *pega_rfk,
-		const char *name, int controlid, int rfkill_type)
+static int pega_rfkill_set(void *data, bool blocked)
 {
-	int result;
+	struct asus_rfkill *rfk = data;
 
-	pr_warn("Setting up rfk %s, control %d, type %d\n", name, controlid, rfkill_type);
-	pega_rfk->control_id = controlid;
-	pega_rfk->asus = asus;
-	pega_rfk->rfkill = rfkill_alloc(name, &asus->platform_device->dev,
-					rfkill_type, &pega_rfkill_ops, pega_rfk);
-	if (!pega_rfk->rfkill)
-		return -EINVAL;
+	int ret = asus_pega_lucid_set(rfk->asus, rfk->control_id, !blocked);
+	return ret;
+}
 
-	result = rfkill_register(pega_rfk->rfkill);
-	if (result) {
-		rfkill_destroy(pega_rfk->rfkill);
-		pega_rfk->rfkill = NULL;
-	}
+static const struct rfkill_ops pega_rfkill_ops = {
+	.set_block = pega_rfkill_set,
+};
 
-	return result;
+static int pega_rfkill_setup(struct asus_laptop *asus, struct asus_rfkill *rfk,
+			     const char *name, int controlid, int rfkill_type)
+{
+	return asus_rfkill_setup(asus, rfk, name, controlid, rfkill_type,
+				 &pega_rfkill_ops);
 }
 
 static int pega_rfkill_init(struct asus_laptop *asus)
@@ -1339,22 +1428,22 @@ static int pega_rfkill_init(struct asus_laptop *asus)
 	if(!asus->is_pega_lucid)
 		return -ENODEV;
 
-	ret = pega_rfkill_setup(asus, &asus->wlanrfk, "pega-wlan", PEGA_WLAN, RFKILL_TYPE_WLAN);
-	if(ret)
-		return ret;
-	ret = pega_rfkill_setup(asus, &asus->btrfk, "pega-bt", PEGA_BLUETOOTH, RFKILL_TYPE_BLUETOOTH);
+	ret = pega_rfkill_setup(asus, &asus->wlan, "pega-wlan",
+				PEGA_WLAN, RFKILL_TYPE_WLAN);
 	if(ret)
-		goto err_btrfk;
-	ret = pega_rfkill_setup(asus, &asus->wwanrfk, "pega-wwan", PEGA_WWAN, RFKILL_TYPE_WWAN);
+		goto exit;
+
+	ret = pega_rfkill_setup(asus, &asus->bluetooth, "pega-bt",
+				PEGA_BLUETOOTH, RFKILL_TYPE_BLUETOOTH);
 	if(ret)
-		goto err_wwanrfk;
+		goto exit;
 
-	pr_warn("Pega rfkill init succeeded\n");
-	return 0;
-err_wwanrfk:
-	pega_rfkill_terminate(&asus->btrfk);
-err_btrfk:
-	pega_rfkill_terminate(&asus->wlanrfk);
+	ret = pega_rfkill_setup(asus, &asus->wwan, "pega-wwan",
+				PEGA_WWAN, RFKILL_TYPE_WWAN);
+
+exit:
+	if (ret)
+		asus_rfkill_exit(asus);
 
 	return ret;
 }
@@ -1364,8 +1453,10 @@ err_btrfk:
  */
 static void asus_input_notify(struct asus_laptop *asus, int event)
 {
-	if (asus->inputdev)
-		sparse_keymap_report_event(asus->inputdev, event, 1, true);
+	if (!asus->inputdev)
+		return ;
+	if (!sparse_keymap_report_event(asus->inputdev, event, 1, true))
+		pr_info("Unknown key %x pressed\n", event);
 }
 
 static int asus_input_init(struct asus_laptop *asus)
@@ -1375,7 +1466,7 @@ static int asus_input_init(struct asus_laptop *asus)
 
 	input = input_allocate_device();
 	if (!input) {
-		pr_info("Unable to allocate input device\n");
+		pr_warn("Unable to allocate input device\n");
 		return -ENOMEM;
 	}
 	input->name = "Asus Laptop extra buttons";
@@ -1390,7 +1481,7 @@ static int asus_input_init(struct asus_laptop *asus)
 	}
 	error = input_register_device(input);
 	if (error) {
-		pr_info("Unable to register input device\n");
+		pr_warn("Unable to register input device\n");
 		goto err_free_keymap;
 	}
 
@@ -1688,7 +1779,16 @@ static int __devinit asus_acpi_init(struct asus_laptop *asus)
 	if (result)
 		return result;
 
-	/* WLED and BLED are on by default */
+	if (!strcmp(bled_type, "led"))
+		asus->bled_type = TYPE_LED;
+	else if (!strcmp(bled_type, "rfkill"))
+		asus->bled_type = TYPE_RFKILL;
+
+	if (!strcmp(wled_type, "led"))
+		asus->wled_type = TYPE_LED;
+	else if (!strcmp(wled_type, "rfkill"))
+		asus->wled_type = TYPE_RFKILL;
+
 	if (bluetooth_status >= 0)
 		asus_bluetooth_set(asus, !!bluetooth_status);
 
@@ -1786,7 +1886,7 @@ static int __devinit asus_acpi_add(struct acpi_device *device)
 		goto fail_led;
 
 	result = asus_rfkill_init(asus);
-	if (result)
+	if (result && result != -ENODEV)
 		goto fail_rfkill;
 
 	result = pega_accel_init(asus);
@@ -1828,7 +1928,6 @@ static int asus_acpi_remove(struct acpi_device *device, int type)
 	asus_led_exit(asus);
 	asus_input_exit(asus);
 	pega_accel_exit(asus);
-	pega_rfkill_exit(asus);
 	asus_platform_exit(asus);
 
 	kfree(asus->name);
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index b0859d4183e8..99a30b513137 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -25,6 +25,7 @@
 #include <linux/init.h>
 #include <linux/input.h>
 #include <linux/input/sparse-keymap.h>
+#include <linux/fb.h>
 
 #include "asus-wmi.h"
 
@@ -51,9 +52,14 @@ static uint wapf;
 module_param(wapf, uint, 0444);
 MODULE_PARM_DESC(wapf, "WAPF value");
 
+static struct quirk_entry quirk_asus_unknown = {
+};
+
 static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver)
 {
-	driver->wapf = wapf;
+	driver->quirks = &quirk_asus_unknown;
+	driver->quirks->wapf = wapf;
+	driver->panel_power = FB_BLANK_UNBLANK;
 }
 
 static const struct key_entry asus_nb_wmi_keymap[] = {
@@ -70,6 +76,8 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
 	{ KE_KEY, 0x50, { KEY_EMAIL } },
 	{ KE_KEY, 0x51, { KEY_WWW } },
 	{ KE_KEY, 0x55, { KEY_CALC } },
+	{ KE_IGNORE, 0x57, },  /* Battery mode */
+	{ KE_IGNORE, 0x58, },  /* AC mode */
 	{ KE_KEY, 0x5C, { KEY_F15 } },  /* Power Gear key */
 	{ KE_KEY, 0x5D, { KEY_WLAN } }, /* Wireless console Toggle */
 	{ KE_KEY, 0x5E, { KEY_WLAN } }, /* Wireless console Enable */
@@ -99,7 +107,7 @@ static struct asus_wmi_driver asus_nb_wmi_driver = {
 	.keymap = asus_nb_wmi_keymap,
 	.input_name = "Asus WMI hotkeys",
 	.input_phys = ASUS_NB_WMI_FILE "/input0",
-	.quirks = asus_nb_wmi_quirks,
+	.detect_quirks = asus_nb_wmi_quirks,
 };
 
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 9929246895de..77aadde5281c 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -411,7 +411,7 @@ static int kbd_led_read(struct asus_wmi *asus, int *level, int *env)
 
 	if (retval >= 0) {
 		if (level)
-			*level = retval & 0x80 ? retval & 0x7F : 0;
+			*level = retval & 0x7F;
 		if (env)
 			*env = (retval >> 8) & 0x7F;
 		retval = 0;
@@ -784,7 +784,8 @@ static int asus_new_rfkill(struct asus_wmi *asus,
 	arfkill->dev_id = dev_id;
 	arfkill->asus = asus;
 
-	if (dev_id == ASUS_WMI_DEVID_WLAN && asus->driver->hotplug_wireless)
+	if (dev_id == ASUS_WMI_DEVID_WLAN &&
+	    asus->driver->quirks->hotplug_wireless)
 		*rfkill = rfkill_alloc(name, &asus->platform_device->dev, type,
 				       &asus_rfkill_wlan_ops, arfkill);
 	else
@@ -895,7 +896,7 @@ static int asus_wmi_rfkill_init(struct asus_wmi *asus)
 	if (result && result != -ENODEV)
 		goto exit;
 
-	if (!asus->driver->hotplug_wireless)
+	if (!asus->driver->quirks->hotplug_wireless)
 		goto exit;
 
 	result = asus_setup_pci_hotplug(asus);
@@ -1075,7 +1076,12 @@ static int asus_wmi_hwmon_init(struct asus_wmi *asus)
  */
 static int read_backlight_power(struct asus_wmi *asus)
 {
-	int ret = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_BACKLIGHT);
+	int ret;
+	if (asus->driver->quirks->store_backlight_power)
+		ret = !asus->driver->panel_power;
+	else
+		ret = asus_wmi_get_devstate_simple(asus,
+						   ASUS_WMI_DEVID_BACKLIGHT);
 
 	if (ret < 0)
 		return ret;
@@ -1116,26 +1122,51 @@ static int read_brightness(struct backlight_device *bd)
 	return retval & ASUS_WMI_DSTS_BRIGHTNESS_MASK;
 }
 
-static int update_bl_status(struct backlight_device *bd)
+static u32 get_scalar_command(struct backlight_device *bd)
 {
 	struct asus_wmi *asus = bl_get_data(bd);
-	u32 ctrl_param;
-	int power, err;
+	u32 ctrl_param = 0;
 
-	ctrl_param = bd->props.brightness;
+	if ((asus->driver->brightness < bd->props.brightness) ||
+	    bd->props.brightness == bd->props.max_brightness)
+		ctrl_param = 0x00008001;
+	else if ((asus->driver->brightness > bd->props.brightness) ||
+		 bd->props.brightness == 0)
+		ctrl_param = 0x00008000;
 
-	err = asus_wmi_set_devstate(ASUS_WMI_DEVID_BRIGHTNESS,
-				    ctrl_param, NULL);
+	asus->driver->brightness = bd->props.brightness;
 
-	if (err < 0)
-		return err;
+	return ctrl_param;
+}
+
+static int update_bl_status(struct backlight_device *bd)
+{
+	struct asus_wmi *asus = bl_get_data(bd);
+	u32 ctrl_param;
+	int power, err = 0;
 
 	power = read_backlight_power(asus);
 	if (power != -ENODEV && bd->props.power != power) {
 		ctrl_param = !!(bd->props.power == FB_BLANK_UNBLANK);
 		err = asus_wmi_set_devstate(ASUS_WMI_DEVID_BACKLIGHT,
 					    ctrl_param, NULL);
+		if (asus->driver->quirks->store_backlight_power)
+			asus->driver->panel_power = bd->props.power;
+
+		/* When using scalar brightness, updating the brightness
+		 * will mess with the backlight power */
+		if (asus->driver->quirks->scalar_panel_brightness)
+			return err;
 	}
+
+	if (asus->driver->quirks->scalar_panel_brightness)
+		ctrl_param = get_scalar_command(bd);
+	else
+		ctrl_param = bd->props.brightness;
+
+	err = asus_wmi_set_devstate(ASUS_WMI_DEVID_BRIGHTNESS,
+				    ctrl_param, NULL);
+
 	return err;
 }
 
@@ -1196,10 +1227,15 @@ static int asus_wmi_backlight_init(struct asus_wmi *asus)
 
 	asus->backlight_device = bd;
 
+	if (asus->driver->quirks->store_backlight_power)
+		asus->driver->panel_power = power;
+
 	bd->props.brightness = read_brightness(bd);
 	bd->props.power = power;
 	backlight_update_status(bd);
 
+	asus->driver->brightness = bd->props.brightness;
+
 	return 0;
 }
 
@@ -1441,9 +1477,9 @@ static int asus_wmi_platform_init(struct asus_wmi *asus)
 
 	/* CWAP allow to define the behavior of the Fn+F2 key,
 	 * this method doesn't seems to be present on Eee PCs */
-	if (asus->driver->wapf >= 0)
+	if (asus->driver->quirks->wapf >= 0)
 		asus_wmi_set_devstate(ASUS_WMI_DEVID_CWAP,
-				      asus->driver->wapf, NULL);
+				      asus->driver->quirks->wapf, NULL);
 
 	return asus_wmi_sysfs_init(asus->platform_device);
 }
@@ -1622,8 +1658,8 @@ static int asus_wmi_add(struct platform_device *pdev)
 	wdrv->platform_device = pdev;
 	platform_set_drvdata(asus->platform_device, asus);
 
-	if (wdrv->quirks)
-		wdrv->quirks(asus->driver);
+	if (wdrv->detect_quirks)
+		wdrv->detect_quirks(asus->driver);
 
 	err = asus_wmi_platform_init(asus);
 	if (err)
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index 8147c10161cc..d43b66742004 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -35,9 +35,16 @@ struct module;
 struct key_entry;
 struct asus_wmi;
 
+struct quirk_entry {
+	bool hotplug_wireless;
+	bool scalar_panel_brightness;
+	bool store_backlight_power;
+	int wapf;
+};
+
 struct asus_wmi_driver {
-	bool			hotplug_wireless;
-	int			wapf;
+	int			brightness;
+	int			panel_power;
 
 	const char		*name;
 	struct module		*owner;
@@ -47,13 +54,14 @@ struct asus_wmi_driver {
 	const struct key_entry	*keymap;
 	const char		*input_name;
 	const char		*input_phys;
+	struct quirk_entry	*quirks;
 	/* Returns new code, value, and autorelease values in arguments.
 	 * Return ASUS_WMI_KEY_IGNORE in code if event should be ignored. */
 	void (*key_filter) (struct asus_wmi_driver *driver, int *code,
 			    unsigned int *value, bool *autorelease);
 
 	int (*probe) (struct platform_device *device);
-	void (*quirks) (struct asus_wmi_driver *driver);
+	void (*detect_quirks) (struct asus_wmi_driver *driver);
 
 	struct platform_driver	platform_driver;
 	struct platform_device *platform_device;
diff --git a/drivers/platform/x86/asus_acpi.c b/drivers/platform/x86/asus_acpi.c
deleted file mode 100644
index 6f966d6c062b..000000000000
--- a/drivers/platform/x86/asus_acpi.c
+++ /dev/null
@@ -1,1513 +0,0 @@
-/*
- *  asus_acpi.c - Asus Laptop ACPI Extras
- *
- *
- *  Copyright (C) 2002-2005 Julien Lerouge, 2003-2006 Karol Kozimor
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
- *  The development page for this driver is located at
- *  http://sourceforge.net/projects/acpi4asus/
- *
- *  Credits:
- *  Pontus Fuchs   - Helper functions, cleanup
- *  Johann Wiesner - Small compile fixes
- *  John Belmonte  - ACPI code for Toshiba laptop was a good starting point.
- *  �ic Burghard  - LED display support for W1N
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/backlight.h>
-#include <acpi/acpi_drivers.h>
-#include <acpi/acpi_bus.h>
-#include <asm/uaccess.h>
-
-#define ASUS_ACPI_VERSION "0.30"
-
-#define PROC_ASUS       "asus"	/* The directory */
-#define PROC_MLED       "mled"
-#define PROC_WLED       "wled"
-#define PROC_TLED       "tled"
-#define PROC_BT         "bluetooth"
-#define PROC_LEDD       "ledd"
-#define PROC_INFO       "info"
-#define PROC_LCD        "lcd"
-#define PROC_BRN        "brn"
-#define PROC_DISP       "disp"
-
-#define ACPI_HOTK_NAME          "Asus Laptop ACPI Extras Driver"
-#define ACPI_HOTK_CLASS         "hotkey"
-#define ACPI_HOTK_DEVICE_NAME   "Hotkey"
-
-/*
- * Some events we use, same for all Asus
- */
-#define BR_UP       0x10
-#define BR_DOWN     0x20
-
-/*
- * Flags for hotk status
- */
-#define MLED_ON     0x01	/* Mail LED */
-#define WLED_ON     0x02	/* Wireless LED */
-#define TLED_ON     0x04	/* Touchpad LED */
-#define BT_ON       0x08	/* Internal Bluetooth */
-
-MODULE_AUTHOR("Julien Lerouge, Karol Kozimor");
-MODULE_DESCRIPTION(ACPI_HOTK_NAME);
-MODULE_LICENSE("GPL");
-
-static uid_t asus_uid;
-static gid_t asus_gid;
-module_param(asus_uid, uint, 0);
-MODULE_PARM_DESC(asus_uid, "UID for entries in /proc/acpi/asus");
-module_param(asus_gid, uint, 0);
-MODULE_PARM_DESC(asus_gid, "GID for entries in /proc/acpi/asus");
-
-/* For each model, all features implemented,
- * those marked with R are relative to HOTK, A for absolute */
-struct model_data {
-	char *name;		/* name of the laptop________________A */
-	char *mt_mled;		/* method to handle mled_____________R */
-	char *mled_status;	/* node to handle mled reading_______A */
-	char *mt_wled;		/* method to handle wled_____________R */
-	char *wled_status;	/* node to handle wled reading_______A */
-	char *mt_tled;		/* method to handle tled_____________R */
-	char *tled_status;	/* node to handle tled reading_______A */
-	char *mt_ledd;		/* method to handle LED display______R */
-	char *mt_bt_switch;	/* method to switch Bluetooth on/off_R */
-	char *bt_status;	/* no model currently supports this__? */
-	char *mt_lcd_switch;	/* method to turn LCD on/off_________A */
-	char *lcd_status;	/* node to read LCD panel state______A */
-	char *brightness_up;	/* method to set brightness up_______A */
-	char *brightness_down;	/* method to set brightness down ____A */
-	char *brightness_set;	/* method to set absolute brightness_R */
-	char *brightness_get;	/* method to get absolute brightness_R */
-	char *brightness_status;/* node to get brightness____________A */
-	char *display_set;	/* method to set video output________R */
-	char *display_get;	/* method to get video output________R */
-};
-
-/*
- * This is the main structure, we can use it to store anything interesting
- * about the hotk device
- */
-struct asus_hotk {
-	struct acpi_device *device;	/* the device we are in */
-	acpi_handle handle;		/* the handle of the hotk device */
-	char status;			/* status of the hotk, for LEDs */
-	u32 ledd_status;		/* status of the LED display */
-	struct model_data *methods;	/* methods available on the laptop */
-	u8 brightness;			/* brightness level */
-	enum {
-		A1x = 0,	/* A1340D, A1300F */
-		A2x,		/* A2500H */
-		A4G,		/* A4700G */
-		D1x,		/* D1 */
-		L2D,		/* L2000D */
-		L3C,		/* L3800C */
-		L3D,		/* L3400D */
-		L3H,		/* L3H, L2000E, L5D */
-		L4R,		/* L4500R */
-		L5x,		/* L5800C */
-		L8L,		/* L8400L */
-		M1A,		/* M1300A */
-		M2E,		/* M2400E, L4400L */
-		M6N,		/* M6800N, W3400N */
-		M6R,		/* M6700R, A3000G */
-		P30,		/* Samsung P30 */
-		S1x,		/* S1300A, but also L1400B and M2400A (L84F) */
-		S2x,		/* S200 (J1 reported), Victor MP-XP7210 */
-		W1N,		/* W1000N */
-		W5A,		/* W5A */
-		W3V,            /* W3030V */
-		xxN,		/* M2400N, M3700N, M5200N, M6800N,
-							 S1300N, S5200N*/
-		A4S,            /* Z81sp */
-		F3Sa,		/* (Centrino) */
-		R1F,
-		END_MODEL
-	} model;		/* Models currently supported */
-	u16 event_count[128];	/* Count for each event TODO make this better */
-};
-
-/* Here we go */
-#define A1x_PREFIX "\\_SB.PCI0.ISA.EC0."
-#define L3C_PREFIX "\\_SB.PCI0.PX40.ECD0."
-#define M1A_PREFIX "\\_SB.PCI0.PX40.EC0."
-#define P30_PREFIX "\\_SB.PCI0.LPCB.EC0."
-#define S1x_PREFIX "\\_SB.PCI0.PX40."
-#define S2x_PREFIX A1x_PREFIX
-#define xxN_PREFIX "\\_SB.PCI0.SBRG.EC0."
-
-static struct model_data model_conf[END_MODEL] = {
-	/*
-	 * TODO I have seen a SWBX and AIBX method on some models, like L1400B,
-	 * it seems to be a kind of switch, but what for ?
-	 */
-
-	{
-	 .name = "A1x",
-	 .mt_mled = "MLED",
-	 .mled_status = "\\MAIL",
-	 .mt_lcd_switch = A1x_PREFIX "_Q10",
-	 .lcd_status = "\\BKLI",
-	 .brightness_up = A1x_PREFIX "_Q0E",
-	 .brightness_down = A1x_PREFIX "_Q0F"},
-
-	{
-	 .name = "A2x",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .wled_status = "\\SG66",
-	 .mt_lcd_switch = "\\Q10",
-	 .lcd_status = "\\BAOF",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-	{
-	 .name = "A4G",
-	 .mt_mled = "MLED",
-/* WLED present, but not controlled by ACPI */
-	 .mt_lcd_switch = xxN_PREFIX "_Q10",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\ADVG"},
-
-	{
-	 .name = "D1x",
-	 .mt_mled = "MLED",
-	 .mt_lcd_switch = "\\Q0D",
-	 .lcd_status = "\\GP11",
-	 .brightness_up = "\\Q0C",
-	 .brightness_down = "\\Q0B",
-	 .brightness_status = "\\BLVL",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-	{
-	 .name = "L2D",
-	 .mt_mled = "MLED",
-	 .mled_status = "\\SGP6",
-	 .mt_wled = "WLED",
-	 .wled_status = "\\RCP3",
-	 .mt_lcd_switch = "\\Q10",
-	 .lcd_status = "\\SGP0",
-	 .brightness_up = "\\Q0E",
-	 .brightness_down = "\\Q0F",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-	{
-	 .name = "L3C",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = L3C_PREFIX "_Q10",
-	 .lcd_status = "\\GL32",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\_SB.PCI0.PCI1.VGAC.NMAP"},
-
-	{
-	 .name = "L3D",
-	 .mt_mled = "MLED",
-	 .mled_status = "\\MALD",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = "\\Q10",
-	 .lcd_status = "\\BKLG",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-	{
-	 .name = "L3H",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = "EHK",
-	 .lcd_status = "\\_SB.PCI0.PM.PBC",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-	{
-	 .name = "L4R",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .wled_status = "\\_SB.PCI0.SBRG.SG13",
-	 .mt_lcd_switch = xxN_PREFIX "_Q10",
-	 .lcd_status = "\\_SB.PCI0.SBSM.SEO4",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\_SB.PCI0.P0P1.VGA.GETD"},
-
-	{
-	 .name = "L5x",
-	 .mt_mled = "MLED",
-/* WLED present, but not controlled by ACPI */
-	 .mt_tled = "TLED",
-	 .mt_lcd_switch = "\\Q0D",
-	 .lcd_status = "\\BAOF",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-	{
-	 .name = "L8L"
-/* No features, but at least support the hotkeys */
-	 },
-
-	{
-	 .name = "M1A",
-	 .mt_mled = "MLED",
-	 .mt_lcd_switch = M1A_PREFIX "Q10",
-	 .lcd_status = "\\PNOF",
-	 .brightness_up = M1A_PREFIX "Q0E",
-	 .brightness_down = M1A_PREFIX "Q0F",
-	 .brightness_status = "\\BRIT",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-	{
-	 .name = "M2E",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = "\\Q10",
-	 .lcd_status = "\\GP06",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-	{
-	 .name = "M6N",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .wled_status = "\\_SB.PCI0.SBRG.SG13",
-	 .mt_lcd_switch = xxN_PREFIX "_Q10",
-	 .lcd_status = "\\_SB.BKLT",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\SSTE"},
-
-	{
-	 .name = "M6R",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = xxN_PREFIX "_Q10",
-	 .lcd_status = "\\_SB.PCI0.SBSM.SEO4",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\_SB.PCI0.P0P1.VGA.GETD"},
-
-	{
-	 .name = "P30",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = P30_PREFIX "_Q0E",
-	 .lcd_status = "\\BKLT",
-	 .brightness_up = P30_PREFIX "_Q68",
-	 .brightness_down = P30_PREFIX "_Q69",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\DNXT"},
-
-	{
-	 .name = "S1x",
-	 .mt_mled = "MLED",
-	 .mled_status = "\\EMLE",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = S1x_PREFIX "Q10",
-	 .lcd_status = "\\PNOF",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV"},
-
-	{
-	 .name = "S2x",
-	 .mt_mled = "MLED",
-	 .mled_status = "\\MAIL",
-	 .mt_lcd_switch = S2x_PREFIX "_Q10",
-	 .lcd_status = "\\BKLI",
-	 .brightness_up = S2x_PREFIX "_Q0B",
-	 .brightness_down = S2x_PREFIX "_Q0A"},
-
-	{
-	 .name = "W1N",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .mt_ledd = "SLCM",
-	 .mt_lcd_switch = xxN_PREFIX "_Q10",
-	 .lcd_status = "\\BKLT",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\ADVG"},
-
-	{
-	 .name = "W5A",
-	 .mt_bt_switch = "BLED",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = xxN_PREFIX "_Q10",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\ADVG"},
-
-	{
-	 .name = "W3V",
-	 .mt_mled = "MLED",
-	 .mt_wled = "WLED",
-	 .mt_lcd_switch = xxN_PREFIX "_Q10",
-	 .lcd_status = "\\BKLT",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	 .display_get = "\\INFB"},
-
-       {
-	 .name = "xxN",
-	 .mt_mled = "MLED",
-/* WLED present, but not controlled by ACPI */
-	 .mt_lcd_switch = xxN_PREFIX "_Q10",
-	 .lcd_status = "\\BKLT",
-	 .brightness_set = "SPLV",
-	 .brightness_get = "GPLV",
-	 .display_set = "SDSP",
-	.display_get = "\\ADVG"},
-
-	{
-		.name              = "A4S",
-		.brightness_set    = "SPLV",
-		.brightness_get    = "GPLV",
-		.mt_bt_switch      = "BLED",
-		.mt_wled           = "WLED"
-	},
-
-	{
-		.name		= "F3Sa",
-		.mt_bt_switch	= "BLED",
-		.mt_wled	= "WLED",
-		.mt_mled	= "MLED",
-		.brightness_get	= "GPLV",
-		.brightness_set	= "SPLV",
-		.mt_lcd_switch	= "\\_SB.PCI0.SBRG.EC0._Q10",
-		.lcd_status	= "\\_SB.PCI0.SBRG.EC0.RPIN",
-		.display_get	= "\\ADVG",
-		.display_set	= "SDSP",
-	},
-	{
-		.name = "R1F",
-		.mt_bt_switch = "BLED",
-		.mt_mled = "MLED",
-		.mt_wled = "WLED",
-		.mt_lcd_switch = "\\Q10",
-		.lcd_status = "\\GP06",
-		.brightness_set = "SPLV",
-		.brightness_get = "GPLV",
-		.display_set = "SDSP",
-		.display_get = "\\INFB"
-	}
-};
-
-/* procdir we use */
-static struct proc_dir_entry *asus_proc_dir;
-
-static struct backlight_device *asus_backlight_device;
-
-/*
- * This header is made available to allow proper configuration given model,
- * revision number , ... this info cannot go in struct asus_hotk because it is
- * available before the hotk
- */
-static struct acpi_table_header *asus_info;
-
-/* The actual device the driver binds to */
-static struct asus_hotk *hotk;
-
-/*
- * The hotkey driver and autoloading declaration
- */
-static int asus_hotk_add(struct acpi_device *device);
-static int asus_hotk_remove(struct acpi_device *device, int type);
-static void asus_hotk_notify(struct acpi_device *device, u32 event);
-
-static const struct acpi_device_id asus_device_ids[] = {
-	{"ATK0100", 0},
-	{"", 0},
-};
-MODULE_DEVICE_TABLE(acpi, asus_device_ids);
-
-static struct acpi_driver asus_hotk_driver = {
-	.name = "asus_acpi",
-	.class = ACPI_HOTK_CLASS,
-	.owner = THIS_MODULE,
-	.ids = asus_device_ids,
-	.flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS,
-	.ops = {
-		.add = asus_hotk_add,
-		.remove = asus_hotk_remove,
-		.notify = asus_hotk_notify,
-		},
-};
-
-/*
- * This function evaluates an ACPI method, given an int as parameter, the
- * method is searched within the scope of the handle, can be NULL. The output
- * of the method is written is output, which can also be NULL
- *
- * returns 1 if write is successful, 0 else.
- */
-static int write_acpi_int(acpi_handle handle, const char *method, int val,
-			  struct acpi_buffer *output)
-{
-	struct acpi_object_list params;	/* list of input parameters (int) */
-	union acpi_object in_obj;	/* the only param we use */
-	acpi_status status;
-
-	params.count = 1;
-	params.pointer = &in_obj;
-	in_obj.type = ACPI_TYPE_INTEGER;
-	in_obj.integer.value = val;
-
-	status = acpi_evaluate_object(handle, (char *)method, &params, output);
-	return (status == AE_OK);
-}
-
-static int read_acpi_int(acpi_handle handle, const char *method, int *val)
-{
-	struct acpi_buffer output;
-	union acpi_object out_obj;
-	acpi_status status;
-
-	output.length = sizeof(out_obj);
-	output.pointer = &out_obj;
-
-	status = acpi_evaluate_object(handle, (char *)method, NULL, &output);
-	*val = out_obj.integer.value;
-	return (status == AE_OK) && (out_obj.type == ACPI_TYPE_INTEGER);
-}
-
-static int asus_info_proc_show(struct seq_file *m, void *v)
-{
-	int temp;
-
-	seq_printf(m, ACPI_HOTK_NAME " " ASUS_ACPI_VERSION "\n");
-	seq_printf(m, "Model reference    : %s\n", hotk->methods->name);
-	/*
-	 * The SFUN method probably allows the original driver to get the list
-	 * of features supported by a given model. For now, 0x0100 or 0x0800
-	 * bit signifies that the laptop is equipped with a Wi-Fi MiniPCI card.
-	 * The significance of others is yet to be found.
-	 */
-	if (read_acpi_int(hotk->handle, "SFUN", &temp))
-		seq_printf(m, "SFUN value         : 0x%04x\n", temp);
-	/*
-	 * Another value for userspace: the ASYM method returns 0x02 for
-	 * battery low and 0x04 for battery critical, its readings tend to be
-	 * more accurate than those provided by _BST.
-	 * Note: since not all the laptops provide this method, errors are
-	 * silently ignored.
-	 */
-	if (read_acpi_int(hotk->handle, "ASYM", &temp))
-		seq_printf(m, "ASYM value         : 0x%04x\n", temp);
-	if (asus_info) {
-		seq_printf(m, "DSDT length        : %d\n", asus_info->length);
-		seq_printf(m, "DSDT checksum      : %d\n", asus_info->checksum);
-		seq_printf(m, "DSDT revision      : %d\n", asus_info->revision);
-		seq_printf(m, "OEM id             : %.*s\n", ACPI_OEM_ID_SIZE, asus_info->oem_id);
-		seq_printf(m, "OEM table id       : %.*s\n", ACPI_OEM_TABLE_ID_SIZE, asus_info->oem_table_id);
-		seq_printf(m, "OEM revision       : 0x%x\n", asus_info->oem_revision);
-		seq_printf(m, "ASL comp vendor id : %.*s\n", ACPI_NAME_SIZE, asus_info->asl_compiler_id);
-		seq_printf(m, "ASL comp revision  : 0x%x\n", asus_info->asl_compiler_revision);
-	}
-
-	return 0;
-}
-
-static int asus_info_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, asus_info_proc_show, NULL);
-}
-
-static const struct file_operations asus_info_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= asus_info_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-/*
- * /proc handlers
- * We write our info in page, we begin at offset off and cannot write more
- * than count bytes. We set eof to 1 if we handle those 2 values. We return the
- * number of bytes written in page
- */
-
-/* Generic LED functions */
-static int read_led(const char *ledname, int ledmask)
-{
-	if (ledname) {
-		int led_status;
-
-		if (read_acpi_int(NULL, ledname, &led_status))
-			return led_status;
-		else
-			pr_warn("Error reading LED status\n");
-	}
-	return (hotk->status & ledmask) ? 1 : 0;
-}
-
-static int parse_arg(const char __user *buf, unsigned long count, int *val)
-{
-	char s[32];
-	if (!count)
-		return 0;
-	if (count > 31)
-		return -EINVAL;
-	if (copy_from_user(s, buf, count))
-		return -EFAULT;
-	s[count] = 0;
-	if (sscanf(s, "%i", val) != 1)
-		return -EINVAL;
-	return count;
-}
-
-/* FIXME: kill extraneous args so it can be called independently */
-static int
-write_led(const char __user *buffer, unsigned long count,
-	  char *ledname, int ledmask, int invert)
-{
-	int rv, value;
-	int led_out = 0;
-
-	rv = parse_arg(buffer, count, &value);
-	if (rv > 0)
-		led_out = value ? 1 : 0;
-
-	hotk->status =
-	    (led_out) ? (hotk->status | ledmask) : (hotk->status & ~ledmask);
-
-	if (invert)		/* invert target value */
-		led_out = !led_out;
-
-	if (!write_acpi_int(hotk->handle, ledname, led_out, NULL))
-		pr_warn("LED (%s) write failed\n", ledname);
-
-	return rv;
-}
-
-/*
- * Proc handlers for MLED
- */
-static int mled_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%d\n", read_led(hotk->methods->mled_status, MLED_ON));
-	return 0;
-}
-
-static int mled_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mled_proc_show, NULL);
-}
-
-static ssize_t mled_proc_write(struct file *file, const char __user *buffer,
-		size_t count, loff_t *pos)
-{
-	return write_led(buffer, count, hotk->methods->mt_mled, MLED_ON, 1);
-}
-
-static const struct file_operations mled_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= mled_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= mled_proc_write,
-};
-
-/*
- * Proc handlers for LED display
- */
-static int ledd_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "0x%08x\n", hotk->ledd_status);
-	return 0;
-}
-
-static int ledd_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ledd_proc_show, NULL);
-}
-
-static ssize_t ledd_proc_write(struct file *file, const char __user *buffer,
-		size_t count, loff_t *pos)
-{
-	int rv, value;
-
-	rv = parse_arg(buffer, count, &value);
-	if (rv > 0) {
-		if (!write_acpi_int
-		    (hotk->handle, hotk->methods->mt_ledd, value, NULL))
-			pr_warn("LED display write failed\n");
-		else
-			hotk->ledd_status = (u32) value;
-	}
-	return rv;
-}
-
-static const struct file_operations ledd_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ledd_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= ledd_proc_write,
-};
-
-/*
- * Proc handlers for WLED
- */
-static int wled_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%d\n", read_led(hotk->methods->wled_status, WLED_ON));
-	return 0;
-}
-
-static int wled_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wled_proc_show, NULL);
-}
-
-static ssize_t wled_proc_write(struct file *file, const char __user *buffer,
-		size_t count, loff_t *pos)
-{
-	return write_led(buffer, count, hotk->methods->mt_wled, WLED_ON, 0);
-}
-
-static const struct file_operations wled_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= wled_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= wled_proc_write,
-};
-
-/*
- * Proc handlers for Bluetooth
- */
-static int bluetooth_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%d\n", read_led(hotk->methods->bt_status, BT_ON));
-	return 0;
-}
-
-static int bluetooth_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, bluetooth_proc_show, NULL);
-}
-
-static ssize_t bluetooth_proc_write(struct file *file,
-		const char __user *buffer, size_t count, loff_t *pos)
-{
-	/* Note: mt_bt_switch controls both internal Bluetooth adapter's
-	   presence and its LED */
-	return write_led(buffer, count, hotk->methods->mt_bt_switch, BT_ON, 0);
-}
-
-static const struct file_operations bluetooth_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= bluetooth_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= bluetooth_proc_write,
-};
-
-/*
- * Proc handlers for TLED
- */
-static int tled_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%d\n", read_led(hotk->methods->tled_status, TLED_ON));
-	return 0;
-}
-
-static int tled_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, tled_proc_show, NULL);
-}
-
-static ssize_t tled_proc_write(struct file *file, const char __user *buffer,
-		size_t count, loff_t *pos)
-{
-	return write_led(buffer, count, hotk->methods->mt_tled, TLED_ON, 0);
-}
-
-static const struct file_operations tled_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= tled_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= tled_proc_write,
-};
-
-static int get_lcd_state(void)
-{
-	int lcd = 0;
-
-	if (hotk->model == L3H) {
-		/* L3H and the like have to be handled differently */
-		acpi_status status = 0;
-		struct acpi_object_list input;
-		union acpi_object mt_params[2];
-		struct acpi_buffer output;
-		union acpi_object out_obj;
-
-		input.count = 2;
-		input.pointer = mt_params;
-		/* Note: the following values are partly guessed up, but
-		   otherwise they seem to work */
-		mt_params[0].type = ACPI_TYPE_INTEGER;
-		mt_params[0].integer.value = 0x02;
-		mt_params[1].type = ACPI_TYPE_INTEGER;
-		mt_params[1].integer.value = 0x02;
-
-		output.length = sizeof(out_obj);
-		output.pointer = &out_obj;
-
-		status =
-		    acpi_evaluate_object(NULL, hotk->methods->lcd_status,
-					 &input, &output);
-		if (status != AE_OK)
-			return -1;
-		if (out_obj.type == ACPI_TYPE_INTEGER)
-			/* That's what the AML code does */
-			lcd = out_obj.integer.value >> 8;
-	} else if (hotk->model == F3Sa) {
-		unsigned long long tmp;
-		union acpi_object param;
-		struct acpi_object_list input;
-		acpi_status status;
-
-		/* Read pin 11 */
-		param.type = ACPI_TYPE_INTEGER;
-		param.integer.value = 0x11;
-		input.count = 1;
-		input.pointer = &param;
-
-		status = acpi_evaluate_integer(NULL, hotk->methods->lcd_status,
-						&input, &tmp);
-		if (status != AE_OK)
-			return -1;
-
-		lcd = tmp;
-	} else {
-		/* We don't have to check anything if we are here */
-		if (!read_acpi_int(NULL, hotk->methods->lcd_status, &lcd))
-			pr_warn("Error reading LCD status\n");
-
-		if (hotk->model == L2D)
-			lcd = ~lcd;
-	}
-
-	return (lcd & 1);
-}
-
-static int set_lcd_state(int value)
-{
-	int lcd = 0;
-	acpi_status status = 0;
-
-	lcd = value ? 1 : 0;
-	if (lcd != get_lcd_state()) {
-		/* switch */
-		if (hotk->model != L3H) {
-			status =
-			    acpi_evaluate_object(NULL,
-						 hotk->methods->mt_lcd_switch,
-						 NULL, NULL);
-		} else {
-			/* L3H and the like must be handled differently */
-			if (!write_acpi_int
-			    (hotk->handle, hotk->methods->mt_lcd_switch, 0x07,
-			     NULL))
-				status = AE_ERROR;
-			/* L3H's AML executes EHK (0x07) upon Fn+F7 keypress,
-			   the exact behaviour is simulated here */
-		}
-		if (ACPI_FAILURE(status))
-			pr_warn("Error switching LCD\n");
-	}
-	return 0;
-
-}
-
-static int lcd_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%d\n", get_lcd_state());
-	return 0;
-}
-
-static int lcd_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, lcd_proc_show, NULL);
-}
-
-static ssize_t lcd_proc_write(struct file *file, const char __user *buffer,
-	       size_t count, loff_t *pos)
-{
-	int rv, value;
-
-	rv = parse_arg(buffer, count, &value);
-	if (rv > 0)
-		set_lcd_state(value);
-	return rv;
-}
-
-static const struct file_operations lcd_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= lcd_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= lcd_proc_write,
-};
-
-static int read_brightness(struct backlight_device *bd)
-{
-	int value;
-
-	if (hotk->methods->brightness_get) {	/* SPLV/GPLV laptop */
-		if (!read_acpi_int(hotk->handle, hotk->methods->brightness_get,
-				   &value))
-			pr_warn("Error reading brightness\n");
-	} else if (hotk->methods->brightness_status) {	/* For D1 for example */
-		if (!read_acpi_int(NULL, hotk->methods->brightness_status,
-				   &value))
-			pr_warn("Error reading brightness\n");
-	} else			/* No GPLV method */
-		value = hotk->brightness;
-	return value;
-}
-
-/*
- * Change the brightness level
- */
-static int set_brightness(int value)
-{
-	acpi_status status = 0;
-	int ret = 0;
-
-	/* SPLV laptop */
-	if (hotk->methods->brightness_set) {
-		if (!write_acpi_int(hotk->handle, hotk->methods->brightness_set,
-				    value, NULL)) {
-			pr_warn("Error changing brightness\n");
-			ret = -EIO;
-		}
-		goto out;
-	}
-
-	/* No SPLV method if we are here, act as appropriate */
-	value -= read_brightness(NULL);
-	while (value != 0) {
-		status = acpi_evaluate_object(NULL, (value > 0) ?
-					      hotk->methods->brightness_up :
-					      hotk->methods->brightness_down,
-					      NULL, NULL);
-		(value > 0) ? value-- : value++;
-		if (ACPI_FAILURE(status)) {
-			pr_warn("Error changing brightness\n");
-			ret = -EIO;
-		}
-	}
-out:
-	return ret;
-}
-
-static int set_brightness_status(struct backlight_device *bd)
-{
-	return set_brightness(bd->props.brightness);
-}
-
-static int brn_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%d\n", read_brightness(NULL));
-	return 0;
-}
-
-static int brn_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, brn_proc_show, NULL);
-}
-
-static ssize_t brn_proc_write(struct file *file, const char __user *buffer,
-	       size_t count, loff_t *pos)
-{
-	int rv, value;
-
-	rv = parse_arg(buffer, count, &value);
-	if (rv > 0) {
-		value = (0 < value) ? ((15 < value) ? 15 : value) : 0;
-		/* 0 <= value <= 15 */
-		set_brightness(value);
-	}
-	return rv;
-}
-
-static const struct file_operations brn_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= brn_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= brn_proc_write,
-};
-
-static void set_display(int value)
-{
-	/* no sanity check needed for now */
-	if (!write_acpi_int(hotk->handle, hotk->methods->display_set,
-			    value, NULL))
-		pr_warn("Error setting display\n");
-	return;
-}
-
-/*
- * Now, *this* one could be more user-friendly, but so far, no-one has
- * complained. The significance of bits is the same as in proc_write_disp()
- */
-static int disp_proc_show(struct seq_file *m, void *v)
-{
-	int value = 0;
-
-	if (!read_acpi_int(hotk->handle, hotk->methods->display_get, &value))
-		pr_warn("Error reading display status\n");
-	value &= 0x07;	/* needed for some models, shouldn't hurt others */
-	seq_printf(m, "%d\n", value);
-	return 0;
-}
-
-static int disp_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, disp_proc_show, NULL);
-}
-
-/*
- * Experimental support for display switching. As of now: 1 should activate
- * the LCD output, 2 should do for CRT, and 4 for TV-Out. Any combination
- * (bitwise) of these will suffice. I never actually tested 3 displays hooked
- * up simultaneously, so be warned. See the acpi4asus README for more info.
- */
-static ssize_t disp_proc_write(struct file *file, const char __user *buffer,
-		size_t count, loff_t *pos)
-{
-	int rv, value;
-
-	rv = parse_arg(buffer, count, &value);
-	if (rv > 0)
-		set_display(value);
-	return rv;
-}
-
-static const struct file_operations disp_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= disp_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= disp_proc_write,
-};
-
-static int
-asus_proc_add(char *name, const struct file_operations *proc_fops, umode_t mode,
-		     struct acpi_device *device)
-{
-	struct proc_dir_entry *proc;
-
-	proc = proc_create_data(name, mode, acpi_device_dir(device),
-				proc_fops, acpi_driver_data(device));
-	if (!proc) {
-		pr_warn("  Unable to create %s fs entry\n", name);
-		return -1;
-	}
-	proc->uid = asus_uid;
-	proc->gid = asus_gid;
-	return 0;
-}
-
-static int asus_hotk_add_fs(struct acpi_device *device)
-{
-	struct proc_dir_entry *proc;
-	umode_t mode;
-
-	if ((asus_uid == 0) && (asus_gid == 0)) {
-		mode = S_IFREG | S_IRUGO | S_IWUSR | S_IWGRP;
-	} else {
-		mode = S_IFREG | S_IRUSR | S_IRGRP | S_IWUSR | S_IWGRP;
-		pr_warn("  asus_uid and asus_gid parameters are "
-			"deprecated, use chown and chmod instead!\n");
-	}
-
-	acpi_device_dir(device) = asus_proc_dir;
-	if (!acpi_device_dir(device))
-		return -ENODEV;
-
-	proc = proc_create(PROC_INFO, mode, acpi_device_dir(device),
-			   &asus_info_proc_fops);
-	if (proc) {
-		proc->uid = asus_uid;
-		proc->gid = asus_gid;
-	} else {
-		pr_warn("  Unable to create " PROC_INFO " fs entry\n");
-	}
-
-	if (hotk->methods->mt_wled) {
-		asus_proc_add(PROC_WLED, &wled_proc_fops, mode, device);
-	}
-
-	if (hotk->methods->mt_ledd) {
-		asus_proc_add(PROC_LEDD, &ledd_proc_fops, mode, device);
-	}
-
-	if (hotk->methods->mt_mled) {
-		asus_proc_add(PROC_MLED, &mled_proc_fops, mode, device);
-	}
-
-	if (hotk->methods->mt_tled) {
-		asus_proc_add(PROC_TLED, &tled_proc_fops, mode, device);
-	}
-
-	if (hotk->methods->mt_bt_switch) {
-		asus_proc_add(PROC_BT, &bluetooth_proc_fops, mode, device);
-	}
-
-	/*
-	 * We need both read node and write method as LCD switch is also
-	 * accessible from the keyboard
-	 */
-	if (hotk->methods->mt_lcd_switch && hotk->methods->lcd_status) {
-		asus_proc_add(PROC_LCD, &lcd_proc_fops, mode, device);
-	}
-
-	if ((hotk->methods->brightness_up && hotk->methods->brightness_down) ||
-	    (hotk->methods->brightness_get && hotk->methods->brightness_set)) {
-		asus_proc_add(PROC_BRN, &brn_proc_fops, mode, device);
-	}
-
-	if (hotk->methods->display_set) {
-		asus_proc_add(PROC_DISP, &disp_proc_fops, mode, device);
-	}
-
-	return 0;
-}
-
-static int asus_hotk_remove_fs(struct acpi_device *device)
-{
-	if (acpi_device_dir(device)) {
-		remove_proc_entry(PROC_INFO, acpi_device_dir(device));
-		if (hotk->methods->mt_wled)
-			remove_proc_entry(PROC_WLED, acpi_device_dir(device));
-		if (hotk->methods->mt_mled)
-			remove_proc_entry(PROC_MLED, acpi_device_dir(device));
-		if (hotk->methods->mt_tled)
-			remove_proc_entry(PROC_TLED, acpi_device_dir(device));
-		if (hotk->methods->mt_ledd)
-			remove_proc_entry(PROC_LEDD, acpi_device_dir(device));
-		if (hotk->methods->mt_bt_switch)
-			remove_proc_entry(PROC_BT, acpi_device_dir(device));
-		if (hotk->methods->mt_lcd_switch && hotk->methods->lcd_status)
-			remove_proc_entry(PROC_LCD, acpi_device_dir(device));
-		if ((hotk->methods->brightness_up
-		     && hotk->methods->brightness_down)
-		    || (hotk->methods->brightness_get
-			&& hotk->methods->brightness_set))
-			remove_proc_entry(PROC_BRN, acpi_device_dir(device));
-		if (hotk->methods->display_set)
-			remove_proc_entry(PROC_DISP, acpi_device_dir(device));
-	}
-	return 0;
-}
-
-static void asus_hotk_notify(struct acpi_device *device, u32 event)
-{
-	/* TODO Find a better way to handle events count. */
-	if (!hotk)
-		return;
-
-	/*
-	 * The BIOS *should* be sending us device events, but apparently
-	 * Asus uses system events instead, so just ignore any device
-	 * events we get.
-	 */
-	if (event > ACPI_MAX_SYS_NOTIFY)
-		return;
-
-	if ((event & ~((u32) BR_UP)) < 16)
-		hotk->brightness = (event & ~((u32) BR_UP));
-	else if ((event & ~((u32) BR_DOWN)) < 16)
-		hotk->brightness = (event & ~((u32) BR_DOWN));
-
-	acpi_bus_generate_proc_event(hotk->device, event,
-				hotk->event_count[event % 128]++);
-
-	return;
-}
-
-/*
- * Match the model string to the list of supported models. Return END_MODEL if
- * no match or model is NULL.
- */
-static int asus_model_match(char *model)
-{
-	if (model == NULL)
-		return END_MODEL;
-
-	if (strncmp(model, "L3D", 3) == 0)
-		return L3D;
-	else if (strncmp(model, "L2E", 3) == 0 ||
-		 strncmp(model, "L3H", 3) == 0 || strncmp(model, "L5D", 3) == 0)
-		return L3H;
-	else if (strncmp(model, "L3", 2) == 0 || strncmp(model, "L2B", 3) == 0)
-		return L3C;
-	else if (strncmp(model, "L8L", 3) == 0)
-		return L8L;
-	else if (strncmp(model, "L4R", 3) == 0)
-		return L4R;
-	else if (strncmp(model, "M6N", 3) == 0 || strncmp(model, "W3N", 3) == 0)
-		return M6N;
-	else if (strncmp(model, "M6R", 3) == 0 || strncmp(model, "A3G", 3) == 0)
-		return M6R;
-	else if (strncmp(model, "M2N", 3) == 0 ||
-		 strncmp(model, "M3N", 3) == 0 ||
-		 strncmp(model, "M5N", 3) == 0 ||
-		 strncmp(model, "S1N", 3) == 0 ||
-		 strncmp(model, "S5N", 3) == 0)
-		return xxN;
-	else if (strncmp(model, "M1", 2) == 0)
-		return M1A;
-	else if (strncmp(model, "M2", 2) == 0 || strncmp(model, "L4E", 3) == 0)
-		return M2E;
-	else if (strncmp(model, "L2", 2) == 0)
-		return L2D;
-	else if (strncmp(model, "L8", 2) == 0)
-		return S1x;
-	else if (strncmp(model, "D1", 2) == 0)
-		return D1x;
-	else if (strncmp(model, "A1", 2) == 0)
-		return A1x;
-	else if (strncmp(model, "A2", 2) == 0)
-		return A2x;
-	else if (strncmp(model, "J1", 2) == 0)
-		return S2x;
-	else if (strncmp(model, "L5", 2) == 0)
-		return L5x;
-	else if (strncmp(model, "A4G", 3) == 0)
-		return A4G;
-	else if (strncmp(model, "W1N", 3) == 0)
-		return W1N;
-	else if (strncmp(model, "W3V", 3) == 0)
-		return W3V;
-	else if (strncmp(model, "W5A", 3) == 0)
-		return W5A;
-	else if (strncmp(model, "R1F", 3) == 0)
-		return R1F;
-	else if (strncmp(model, "A4S", 3) == 0)
-		return A4S;
-	else if (strncmp(model, "F3Sa", 4) == 0)
-		return F3Sa;
-	else
-		return END_MODEL;
-}
-
-/*
- * This function is used to initialize the hotk with right values. In this
- * method, we can make all the detection we want, and modify the hotk struct
- */
-static int asus_hotk_get_info(void)
-{
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *model = NULL;
-	int bsts_result;
-	char *string = NULL;
-	acpi_status status;
-
-	/*
-	 * Get DSDT headers early enough to allow for differentiating between
-	 * models, but late enough to allow acpi_bus_register_driver() to fail
-	 * before doing anything ACPI-specific. Should we encounter a machine,
-	 * which needs special handling (i.e. its hotkey device has a different
-	 * HID), this bit will be moved. A global variable asus_info contains
-	 * the DSDT header.
-	 */
-	status = acpi_get_table(ACPI_SIG_DSDT, 1, &asus_info);
-	if (ACPI_FAILURE(status))
-		pr_warn("  Couldn't get the DSDT table header\n");
-
-	/* We have to write 0 on init this far for all ASUS models */
-	if (!write_acpi_int(hotk->handle, "INIT", 0, &buffer)) {
-		pr_err("  Hotkey initialization failed\n");
-		return -ENODEV;
-	}
-
-	/* This needs to be called for some laptops to init properly */
-	if (!read_acpi_int(hotk->handle, "BSTS", &bsts_result))
-		pr_warn("  Error calling BSTS\n");
-	else if (bsts_result)
-		pr_notice("  BSTS called, 0x%02x returned\n", bsts_result);
-
-	/*
-	 * Try to match the object returned by INIT to the specific model.
-	 * Handle every possible object (or the lack of thereof) the DSDT
-	 * writers might throw at us. When in trouble, we pass NULL to
-	 * asus_model_match() and try something completely different.
-	 */
-	if (buffer.pointer) {
-		model = buffer.pointer;
-		switch (model->type) {
-		case ACPI_TYPE_STRING:
-			string = model->string.pointer;
-			break;
-		case ACPI_TYPE_BUFFER:
-			string = model->buffer.pointer;
-			break;
-		default:
-			kfree(model);
-			model = NULL;
-			break;
-		}
-	}
-	hotk->model = asus_model_match(string);
-	if (hotk->model == END_MODEL) {	/* match failed */
-		if (asus_info &&
-		    strncmp(asus_info->oem_table_id, "ODEM", 4) == 0) {
-			hotk->model = P30;
-			pr_notice("  Samsung P30 detected, supported\n");
-			hotk->methods = &model_conf[hotk->model];
-			kfree(model);
-			return 0;
-		} else {
-			hotk->model = M2E;
-			pr_notice("  unsupported model %s, trying default values\n",
-				  string);
-			pr_notice("  send /proc/acpi/dsdt to the developers\n");
-			kfree(model);
-			return -ENODEV;
-		}
-	}
-	hotk->methods = &model_conf[hotk->model];
-	pr_notice("  %s model detected, supported\n", string);
-
-	/* Sort of per-model blacklist */
-	if (strncmp(string, "L2B", 3) == 0)
-		hotk->methods->lcd_status = NULL;
-	/* L2B is similar enough to L3C to use its settings, with this only
-	   exception */
-	else if (strncmp(string, "A3G", 3) == 0)
-		hotk->methods->lcd_status = "\\BLFG";
-	/* A3G is like M6R */
-	else if (strncmp(string, "S5N", 3) == 0 ||
-		 strncmp(string, "M5N", 3) == 0 ||
-		 strncmp(string, "W3N", 3) == 0)
-		hotk->methods->mt_mled = NULL;
-	/* S5N, M5N and W3N have no MLED */
-	else if (strncmp(string, "L5D", 3) == 0)
-		hotk->methods->mt_wled = NULL;
-	/* L5D's WLED is not controlled by ACPI */
-	else if (strncmp(string, "M2N", 3) == 0 ||
-		 strncmp(string, "W3V", 3) == 0 ||
-		 strncmp(string, "S1N", 3) == 0)
-		hotk->methods->mt_wled = "WLED";
-	/* M2N, S1N and W3V have a usable WLED */
-	else if (asus_info) {
-		if (strncmp(asus_info->oem_table_id, "L1", 2) == 0)
-			hotk->methods->mled_status = NULL;
-		/* S1300A reports L84F, but L1400B too, account for that */
-	}
-
-	kfree(model);
-
-	return 0;
-}
-
-static int asus_hotk_check(void)
-{
-	int result = 0;
-
-	result = acpi_bus_get_status(hotk->device);
-	if (result)
-		return result;
-
-	if (hotk->device->status.present) {
-		result = asus_hotk_get_info();
-	} else {
-		pr_err("  Hotkey device not present, aborting\n");
-		return -EINVAL;
-	}
-
-	return result;
-}
-
-static int asus_hotk_found;
-
-static int asus_hotk_add(struct acpi_device *device)
-{
-	acpi_status status = AE_OK;
-	int result;
-
-	pr_notice("Asus Laptop ACPI Extras version %s\n", ASUS_ACPI_VERSION);
-
-	hotk = kzalloc(sizeof(struct asus_hotk), GFP_KERNEL);
-	if (!hotk)
-		return -ENOMEM;
-
-	hotk->handle = device->handle;
-	strcpy(acpi_device_name(device), ACPI_HOTK_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_HOTK_CLASS);
-	device->driver_data = hotk;
-	hotk->device = device;
-
-	result = asus_hotk_check();
-	if (result)
-		goto end;
-
-	result = asus_hotk_add_fs(device);
-	if (result)
-		goto end;
-
-	/* For laptops without GPLV: init the hotk->brightness value */
-	if ((!hotk->methods->brightness_get)
-	    && (!hotk->methods->brightness_status)
-	    && (hotk->methods->brightness_up && hotk->methods->brightness_down)) {
-		status =
-		    acpi_evaluate_object(NULL, hotk->methods->brightness_down,
-					 NULL, NULL);
-		if (ACPI_FAILURE(status))
-			pr_warn("  Error changing brightness\n");
-		else {
-			status =
-			    acpi_evaluate_object(NULL,
-						 hotk->methods->brightness_up,
-						 NULL, NULL);
-			if (ACPI_FAILURE(status))
-				pr_warn("  Strange, error changing brightness\n");
-		}
-	}
-
-	asus_hotk_found = 1;
-
-	/* LED display is off by default */
-	hotk->ledd_status = 0xFFF;
-
-end:
-	if (result)
-		kfree(hotk);
-
-	return result;
-}
-
-static int asus_hotk_remove(struct acpi_device *device, int type)
-{
-	asus_hotk_remove_fs(device);
-
-	kfree(hotk);
-
-	return 0;
-}
-
-static const struct backlight_ops asus_backlight_data = {
-	.get_brightness = read_brightness,
-	.update_status  = set_brightness_status,
-};
-
-static void asus_acpi_exit(void)
-{
-	if (asus_backlight_device)
-		backlight_device_unregister(asus_backlight_device);
-
-	acpi_bus_unregister_driver(&asus_hotk_driver);
-	remove_proc_entry(PROC_ASUS, acpi_root_dir);
-
-	return;
-}
-
-static int __init asus_acpi_init(void)
-{
-	struct backlight_properties props;
-	int result;
-
-	result = acpi_bus_register_driver(&asus_hotk_driver);
-	if (result < 0)
-		return result;
-
-	asus_proc_dir = proc_mkdir(PROC_ASUS, acpi_root_dir);
-	if (!asus_proc_dir) {
-		pr_err("Unable to create /proc entry\n");
-		acpi_bus_unregister_driver(&asus_hotk_driver);
-		return -ENODEV;
-	}
-
-	/*
-	 * This is a bit of a kludge.  We only want this module loaded
-	 * for ASUS systems, but there's currently no way to probe the
-	 * ACPI namespace for ASUS HIDs.  So we just return failure if
-	 * we didn't find one, which will cause the module to be
-	 * unloaded.
-	 */
-	if (!asus_hotk_found) {
-		acpi_bus_unregister_driver(&asus_hotk_driver);
-		remove_proc_entry(PROC_ASUS, acpi_root_dir);
-		return -ENODEV;
-	}
-
-	memset(&props, 0, sizeof(struct backlight_properties));
-	props.type = BACKLIGHT_PLATFORM;
-	props.max_brightness = 15;
-	asus_backlight_device = backlight_device_register("asus", NULL, NULL,
-							  &asus_backlight_data,
-							  &props);
-	if (IS_ERR(asus_backlight_device)) {
-		pr_err("Could not register asus backlight device\n");
-		asus_backlight_device = NULL;
-		asus_acpi_exit();
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-module_init(asus_acpi_init);
-module_exit(asus_acpi_exit);
diff --git a/drivers/platform/x86/compal-laptop.c b/drivers/platform/x86/compal-laptop.c
index d96734478324..1887e2f166a4 100644
--- a/drivers/platform/x86/compal-laptop.c
+++ b/drivers/platform/x86/compal-laptop.c
@@ -882,6 +882,7 @@ static struct dmi_system_id __initdata compal_dmi_table[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(dmi, compal_dmi_table);
 
 static void initialize_power_supply_data(struct compal_data *data)
 {
@@ -1097,16 +1098,3 @@ MODULE_AUTHOR("Roald Frederickx (roald.frederickx@gmail.com)");
 MODULE_DESCRIPTION("Compal Laptop Support");
 MODULE_VERSION(DRIVER_VERSION);
 MODULE_LICENSE("GPL");
-
-MODULE_ALIAS("dmi:*:rnIFL90:rvrIFT00:*");
-MODULE_ALIAS("dmi:*:rnIFL90:rvrREFERENCE:*");
-MODULE_ALIAS("dmi:*:rnIFL91:rvrIFT00:*");
-MODULE_ALIAS("dmi:*:rnJFL92:rvrIFT00:*");
-MODULE_ALIAS("dmi:*:rnIFT00:rvrIFT00:*");
-MODULE_ALIAS("dmi:*:rnJHL90:rvrREFERENCE:*");
-MODULE_ALIAS("dmi:*:svnDellInc.:pnInspiron910:*");
-MODULE_ALIAS("dmi:*:svnDellInc.:pnInspiron1010:*");
-MODULE_ALIAS("dmi:*:svnDellInc.:pnInspiron1011:*");
-MODULE_ALIAS("dmi:*:svnDellInc.:pnInspiron1012:*");
-MODULE_ALIAS("dmi:*:svnDellInc.:pnInspiron1110:*");
-MODULE_ALIAS("dmi:*:svnDellInc.:pnInspiron1210:*");
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index d93e962f2610..a05fc9c955d8 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -117,6 +117,7 @@ static const struct dmi_system_id __initdata dell_device_table[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(dmi, dell_device_table);
 
 static struct dmi_system_id __devinitdata dell_blacklist[] = {
 	/* Supported by compal-laptop */
@@ -184,6 +185,33 @@ static struct dmi_system_id __devinitdata dell_quirks[] = {
 		},
 		.driver_data = &quirk_dell_vostro_v130,
 	},
+	{
+		.callback = dmi_matched,
+		.ident = "Dell Vostro 3555",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 3555"),
+		},
+		.driver_data = &quirk_dell_vostro_v130,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "Dell Inspiron N311z",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron N311z"),
+		},
+		.driver_data = &quirk_dell_vostro_v130,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "Dell Inspiron M5110",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron M5110"),
+		},
+		.driver_data = &quirk_dell_vostro_v130,
+	},
 };
 
 static struct calling_interface_buffer *buffer;
@@ -236,9 +264,7 @@ static void __init find_tokens(const struct dmi_header *dm, void *dummy)
 {
 	switch (dm->type) {
 	case 0xd4: /* Indexed IO */
-		break;
 	case 0xd5: /* Protected Area Type 1 */
-		break;
 	case 0xd6: /* Protected Area Type 2 */
 		break;
 	case 0xda: /* Calling interface */
@@ -615,6 +641,7 @@ static void touchpad_led_set(struct led_classdev *led_cdev,
 static struct led_classdev touchpad_led = {
 	.name = "dell-laptop::touchpad",
 	.brightness_set = touchpad_led_set,
+	.flags = LED_CORE_SUSPENDRESUME,
 };
 
 static int __devinit touchpad_led_init(struct device *dev)
@@ -794,6 +821,3 @@ module_exit(dell_exit);
 MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>");
 MODULE_DESCRIPTION("Dell laptop driver");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("dmi:*svnDellInc.:*:ct8:*");
-MODULE_ALIAS("dmi:*svnDellInc.:*:ct9:*");
-MODULE_ALIAS("dmi:*svnDellComputerCorporation.:*:ct8:*");
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index d9a9e2bedb30..dab91b48d22c 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -1251,6 +1251,14 @@ static void eeepc_input_exit(struct eeepc_laptop *eeepc)
 /*
  * ACPI driver
  */
+static void eeepc_input_notify(struct eeepc_laptop *eeepc, int event)
+{
+	if (!eeepc->inputdev)
+		return ;
+	if (!sparse_keymap_report_event(eeepc->inputdev, event, 1, true))
+		pr_info("Unknown key %x pressed\n", event);
+}
+
 static void eeepc_acpi_notify(struct acpi_device *device, u32 event)
 {
 	struct eeepc_laptop *eeepc = acpi_driver_data(device);
@@ -1287,12 +1295,11 @@ static void eeepc_acpi_notify(struct acpi_device *device, u32 event)
 				* event will be desired value (or else ignored)
 				*/
 			}
-			sparse_keymap_report_event(eeepc->inputdev, event,
-						   1, true);
+			eeepc_input_notify(eeepc, event);
 		}
 	} else {
 		/* Everything else is a bona-fide keypress event */
-		sparse_keymap_report_event(eeepc->inputdev, event, 1, true);
+		eeepc_input_notify(eeepc, event);
 	}
 }
 
diff --git a/drivers/platform/x86/eeepc-wmi.c b/drivers/platform/x86/eeepc-wmi.c
index 9f6e64302b45..656761380342 100644
--- a/drivers/platform/x86/eeepc-wmi.c
+++ b/drivers/platform/x86/eeepc-wmi.c
@@ -32,6 +32,7 @@
 #include <linux/input.h>
 #include <linux/input/sparse-keymap.h>
 #include <linux/dmi.h>
+#include <linux/fb.h>
 #include <acpi/acpi_bus.h>
 
 #include "asus-wmi.h"
@@ -84,9 +85,81 @@ static const struct key_entry eeepc_wmi_keymap[] = {
 	{ KE_KEY, 0xed, { KEY_CAMERA_DOWN } },
 	{ KE_KEY, 0xee, { KEY_CAMERA_LEFT } },
 	{ KE_KEY, 0xef, { KEY_CAMERA_RIGHT } },
+	{ KE_KEY, 0xf3, { KEY_MENU } },
+	{ KE_KEY, 0xf5, { KEY_HOMEPAGE } },
+	{ KE_KEY, 0xf6, { KEY_ESC } },
 	{ KE_END, 0},
 };
 
+static struct quirk_entry quirk_asus_unknown = {
+};
+
+static struct quirk_entry quirk_asus_1000h = {
+	.hotplug_wireless = true,
+};
+
+static struct quirk_entry quirk_asus_et2012_type1 = {
+	.store_backlight_power = true,
+};
+
+static struct quirk_entry quirk_asus_et2012_type3 = {
+	.scalar_panel_brightness = true,
+	.store_backlight_power = true,
+};
+
+static struct quirk_entry *quirks;
+
+static void et2012_quirks(void)
+{
+	const struct dmi_device *dev = NULL;
+	char oemstring[30];
+
+	while ((dev = dmi_find_device(DMI_DEV_TYPE_OEM_STRING, NULL, dev))) {
+		if (sscanf(dev->name, "AEMS%24c", oemstring) == 1) {
+			if (oemstring[18] == '1')
+				quirks = &quirk_asus_et2012_type1;
+			else if (oemstring[18] == '3')
+				quirks = &quirk_asus_et2012_type3;
+			break;
+		}
+	}
+}
+
+static int dmi_matched(const struct dmi_system_id *dmi)
+{
+	char *model;
+
+	quirks = dmi->driver_data;
+
+	model = (char *)dmi->matches[1].substr;
+	if (unlikely(strncmp(model, "ET2012", 6) == 0))
+		et2012_quirks();
+
+	return 1;
+}
+
+static struct dmi_system_id asus_quirks[] = {
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK Computer INC. 1000H",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "1000H"),
+		},
+		.driver_data = &quirk_asus_1000h,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK Computer INC. ET2012E/I",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ET2012"),
+		},
+		.driver_data = &quirk_asus_unknown,
+	},
+	{},
+};
+
 static void eeepc_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code,
 				 unsigned int *value, bool *autorelease)
 {
@@ -141,33 +214,16 @@ static int eeepc_wmi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void eeepc_dmi_check(struct asus_wmi_driver *driver)
-{
-	const char *model;
-
-	model = dmi_get_system_info(DMI_PRODUCT_NAME);
-	if (!model)
-		return;
-
-	/*
-	 * Whitelist for wlan hotplug
-	 *
-	 * Asus 1000H needs the current hotplug code to handle
-	 * Fn+F2 correctly. We may add other Asus here later, but
-	 * it seems that most of the laptops supported by asus-wmi
-	 * don't need to be on this list
-	 */
-	if (strcmp(model, "1000H") == 0) {
-		driver->hotplug_wireless = true;
-		pr_info("wlan hotplug enabled\n");
-	}
-}
-
 static void eeepc_wmi_quirks(struct asus_wmi_driver *driver)
 {
-	driver->hotplug_wireless = hotplug_wireless;
-	driver->wapf = -1;
-	eeepc_dmi_check(driver);
+	quirks = &quirk_asus_unknown;
+	quirks->hotplug_wireless = hotplug_wireless;
+
+	dmi_check_system(asus_quirks);
+
+	driver->quirks = quirks;
+	driver->quirks->wapf = -1;
+	driver->panel_power = FB_BLANK_UNBLANK;
 }
 
 static struct asus_wmi_driver asus_wmi_driver = {
@@ -179,7 +235,7 @@ static struct asus_wmi_driver asus_wmi_driver = {
 	.input_phys = EEEPC_WMI_FILE "/input0",
 	.key_filter = eeepc_wmi_key_filter,
 	.probe = eeepc_wmi_probe,
-	.quirks = eeepc_wmi_quirks,
+	.detect_quirks = eeepc_wmi_quirks,
 };
 
 
diff --git a/drivers/platform/x86/hdaps.c b/drivers/platform/x86/hdaps.c
index ba68d4e7a779..7387f97a2941 100644
--- a/drivers/platform/x86/hdaps.c
+++ b/drivers/platform/x86/hdaps.c
@@ -375,7 +375,7 @@ static ssize_t hdaps_variance_show(struct device *dev,
 static ssize_t hdaps_temp1_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	u8 temp;
+	u8 uninitialized_var(temp);
 	int ret;
 
 	ret = hdaps_readb_one(HDAPS_PORT_TEMP1, &temp);
@@ -388,7 +388,7 @@ static ssize_t hdaps_temp1_show(struct device *dev,
 static ssize_t hdaps_temp2_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	u8 temp;
+	u8 uninitialized_var(temp);
 	int ret;
 
 	ret = hdaps_readb_one(HDAPS_PORT_TEMP2, &temp);
diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c
index 88a98cff5a44..f7ba316e0ed6 100644
--- a/drivers/platform/x86/intel_ips.c
+++ b/drivers/platform/x86/intel_ips.c
@@ -609,25 +609,16 @@ static bool mcp_exceeded(struct ips_driver *ips)
 	bool ret = false;
 	u32 temp_limit;
 	u32 avg_power;
-	const char *msg = "MCP limit exceeded: ";
 
 	spin_lock_irqsave(&ips->turbo_status_lock, flags);
 
 	temp_limit = ips->mcp_temp_limit * 100;
-	if (ips->mcp_avg_temp > temp_limit) {
-		dev_info(&ips->dev->dev,
-			"%sAvg temp %u, limit %u\n", msg, ips->mcp_avg_temp,
-			temp_limit);
+	if (ips->mcp_avg_temp > temp_limit)
 		ret = true;
-	}
 
 	avg_power = ips->cpu_avg_power + ips->mch_avg_power;
-	if (avg_power > ips->mcp_power_limit) {
-		dev_info(&ips->dev->dev,
-			"%sAvg power %u, limit %u\n", msg, avg_power,
-			ips->mcp_power_limit);
+	if (avg_power > ips->mcp_power_limit)
 		ret = true;
-	}
 
 	spin_unlock_irqrestore(&ips->turbo_status_lock, flags);
 
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 0903a883e9f4..0a3594c7e912 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -142,17 +142,7 @@ static struct platform_driver mfld_pb_driver = {
 	.remove	= __devexit_p(mfld_pb_remove),
 };
 
-static int __init mfld_pb_init(void)
-{
-	return platform_driver_register(&mfld_pb_driver);
-}
-module_init(mfld_pb_init);
-
-static void __exit mfld_pb_exit(void)
-{
-	platform_driver_unregister(&mfld_pb_driver);
-}
-module_exit(mfld_pb_exit);
+module_platform_driver(mfld_pb_driver);
 
 MODULE_AUTHOR("Hong Liu <hong.liu@intel.com>");
 MODULE_DESCRIPTION("Intel Medfield Power Button Driver");
diff --git a/drivers/platform/x86/intel_mid_thermal.c b/drivers/platform/x86/intel_mid_thermal.c
index 2ee9766737ea..5ae9cd9c7e6e 100644
--- a/drivers/platform/x86/intel_mid_thermal.c
+++ b/drivers/platform/x86/intel_mid_thermal.c
@@ -549,6 +549,7 @@ static int mid_thermal_remove(struct platform_device *pdev)
 
 static const struct platform_device_id therm_id_table[] = {
 	{ DRIVER_NAME, 1 },
+	{ "msic_thermal", 1 },
 	{ }
 };
 
@@ -564,18 +565,7 @@ static struct platform_driver mid_thermal_driver = {
 	.id_table = therm_id_table,
 };
 
-static int __init mid_thermal_module_init(void)
-{
-	return platform_driver_register(&mid_thermal_driver);
-}
-
-static void __exit mid_thermal_module_exit(void)
-{
-	platform_driver_unregister(&mid_thermal_driver);
-}
-
-module_init(mid_thermal_module_init);
-module_exit(mid_thermal_module_exit);
+module_platform_driver(mid_thermal_driver);
 
 MODULE_AUTHOR("Durgadoss R <durgadoss.r@intel.com>");
 MODULE_DESCRIPTION("Intel Medfield Platform Thermal Driver");
diff --git a/drivers/platform/x86/intel_oaktrail.c b/drivers/platform/x86/intel_oaktrail.c
index 6ee0b5c90933..79a0c2f6be53 100644
--- a/drivers/platform/x86/intel_oaktrail.c
+++ b/drivers/platform/x86/intel_oaktrail.c
@@ -313,6 +313,7 @@ static struct dmi_system_id __initdata oaktrail_dmi_table[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(dmi, oaktrail_dmi_table);
 
 static int __init oaktrail_init(void)
 {
@@ -394,4 +395,3 @@ MODULE_AUTHOR("Yin Kangkai (kangkai.yin@intel.com)");
 MODULE_DESCRIPTION("Intel Oaktrail Platform ACPI Extras");
 MODULE_VERSION(DRIVER_VERSION);
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("dmi:*:svnIntelCorporation:pnOakTrailplatform:*");
diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c
index fd73ea89b857..e2a34b42ddc1 100644
--- a/drivers/platform/x86/samsung-laptop.c
+++ b/drivers/platform/x86/samsung-laptop.c
@@ -17,10 +17,18 @@
 #include <linux/delay.h>
 #include <linux/pci.h>
 #include <linux/backlight.h>
+#include <linux/leds.h>
 #include <linux/fb.h>
 #include <linux/dmi.h>
 #include <linux/platform_device.h>
 #include <linux/rfkill.h>
+#include <linux/acpi.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/ctype.h>
+#if (defined CONFIG_ACPI_VIDEO || defined CONFIG_ACPI_VIDEO_MODULE)
+#include <acpi/video.h>
+#endif
 
 /*
  * This driver is needed because a number of Samsung laptops do not hook
@@ -41,9 +49,20 @@
 #define SABI_IFACE_COMPLETE		0x04
 #define SABI_IFACE_DATA			0x05
 
-/* Structure to get data back to the calling function */
-struct sabi_retval {
-	u8 retval[20];
+#define WL_STATUS_WLAN			0x0
+#define WL_STATUS_BT			0x2
+
+/* Structure get/set data using sabi */
+struct sabi_data {
+	union {
+		struct {
+			u32 d0;
+			u32 d1;
+			u16 d2;
+			u8  d3;
+		};
+		u8 data[11];
+	};
 };
 
 struct sabi_header_offsets {
@@ -60,8 +79,8 @@ struct sabi_commands {
 	 * Brightness is 0 - 8, as described above.
 	 * Value 0 is for the BIOS to use
 	 */
-	u8 get_brightness;
-	u8 set_brightness;
+	u16 get_brightness;
+	u16 set_brightness;
 
 	/*
 	 * first byte:
@@ -72,40 +91,56 @@ struct sabi_commands {
 	 * 0x03 - 3G is on
 	 * TODO, verify 3G is correct, that doesn't seem right...
 	 */
-	u8 get_wireless_button;
-	u8 set_wireless_button;
+	u16 get_wireless_button;
+	u16 set_wireless_button;
 
 	/* 0 is off, 1 is on */
-	u8 get_backlight;
-	u8 set_backlight;
+	u16 get_backlight;
+	u16 set_backlight;
 
 	/*
 	 * 0x80 or 0x00 - no action
 	 * 0x81 - recovery key pressed
 	 */
-	u8 get_recovery_mode;
-	u8 set_recovery_mode;
+	u16 get_recovery_mode;
+	u16 set_recovery_mode;
 
 	/*
 	 * on seclinux: 0 is low, 1 is high,
 	 * on swsmi: 0 is normal, 1 is silent, 2 is turbo
 	 */
-	u8 get_performance_level;
-	u8 set_performance_level;
+	u16 get_performance_level;
+	u16 set_performance_level;
+
+	/* 0x80 is off, 0x81 is on */
+	u16 get_battery_life_extender;
+	u16 set_battery_life_extender;
+
+	/* 0x80 is off, 0x81 is on */
+	u16 get_usb_charge;
+	u16 set_usb_charge;
+
+	/* the first byte is for bluetooth and the third one is for wlan */
+	u16 get_wireless_status;
+	u16 set_wireless_status;
+
+	/* 0x81 to read, (0x82 | level << 8) to set, 0xaabb to enable */
+	u16 kbd_backlight;
 
 	/*
 	 * Tell the BIOS that Linux is running on this machine.
 	 * 81 is on, 80 is off
 	 */
-	u8 set_linux;
+	u16 set_linux;
 };
 
 struct sabi_performance_level {
 	const char *name;
-	u8 value;
+	u16 value;
 };
 
 struct sabi_config {
+	int sabi_version;
 	const char *test_string;
 	u16 main_function;
 	const struct sabi_header_offsets header_offsets;
@@ -117,6 +152,10 @@ struct sabi_config {
 
 static const struct sabi_config sabi_configs[] = {
 	{
+		/* I don't know if it is really 2, but it it is
+		 * less than 3 anyway */
+		.sabi_version = 2,
+
 		.test_string = "SECLINUX",
 
 		.main_function = 0x4c49,
@@ -146,6 +185,17 @@ static const struct sabi_config sabi_configs[] = {
 			.get_performance_level = 0x08,
 			.set_performance_level = 0x09,
 
+			.get_battery_life_extender = 0xFFFF,
+			.set_battery_life_extender = 0xFFFF,
+
+			.get_usb_charge = 0xFFFF,
+			.set_usb_charge = 0xFFFF,
+
+			.get_wireless_status = 0xFFFF,
+			.set_wireless_status = 0xFFFF,
+
+			.kbd_backlight = 0xFFFF,
+
 			.set_linux = 0x0a,
 		},
 
@@ -164,6 +214,8 @@ static const struct sabi_config sabi_configs[] = {
 		.max_brightness = 8,
 	},
 	{
+		.sabi_version = 3,
+
 		.test_string = "SwSmi@",
 
 		.main_function = 0x5843,
@@ -193,6 +245,17 @@ static const struct sabi_config sabi_configs[] = {
 			.get_performance_level = 0x31,
 			.set_performance_level = 0x32,
 
+			.get_battery_life_extender = 0x65,
+			.set_battery_life_extender = 0x66,
+
+			.get_usb_charge = 0x67,
+			.set_usb_charge = 0x68,
+
+			.get_wireless_status = 0x69,
+			.set_wireless_status = 0x6a,
+
+			.kbd_backlight = 0x78,
+
 			.set_linux = 0xff,
 		},
 
@@ -217,16 +280,82 @@ static const struct sabi_config sabi_configs[] = {
 	{ },
 };
 
-static const struct sabi_config *sabi_config;
+/*
+ * samsung-laptop/    - debugfs root directory
+ *   f0000_segment    - dump f0000 segment
+ *   command          - current command
+ *   data             - current data
+ *   d0, d1, d2, d3   - data fields
+ *   call             - call SABI using command and data
+ *
+ * This allow to call arbitrary sabi commands wihout
+ * modifying the driver at all.
+ * For example, setting the keyboard backlight brightness to 5
+ *
+ *  echo 0x78 > command
+ *  echo 0x0582 > d0
+ *  echo 0 > d1
+ *  echo 0 > d2
+ *  echo 0 > d3
+ *  cat call
+ */
+
+struct samsung_laptop_debug {
+	struct dentry *root;
+	struct sabi_data data;
+	u16 command;
+
+	struct debugfs_blob_wrapper f0000_wrapper;
+	struct debugfs_blob_wrapper data_wrapper;
+	struct debugfs_blob_wrapper sdiag_wrapper;
+};
+
+struct samsung_laptop;
+
+struct samsung_rfkill {
+	struct samsung_laptop *samsung;
+	struct rfkill *rfkill;
+	enum rfkill_type type;
+};
+
+struct samsung_laptop {
+	const struct sabi_config *config;
+
+	void __iomem *sabi;
+	void __iomem *sabi_iface;
+	void __iomem *f0000_segment;
+
+	struct mutex sabi_mutex;
+
+	struct platform_device *platform_device;
+	struct backlight_device *backlight_device;
+
+	struct samsung_rfkill wlan;
+	struct samsung_rfkill bluetooth;
+
+	struct led_classdev kbd_led;
+	int kbd_led_wk;
+	struct workqueue_struct *led_workqueue;
+	struct work_struct kbd_led_work;
+
+	struct samsung_laptop_debug debug;
+	struct samsung_quirks *quirks;
+
+	bool handle_backlight;
+	bool has_stepping_quirk;
+
+	char sdiag[64];
+};
+
+struct samsung_quirks {
+	bool broken_acpi_video;
+};
+
+static struct samsung_quirks samsung_unknown = {};
 
-static void __iomem *sabi;
-static void __iomem *sabi_iface;
-static void __iomem *f0000_segment;
-static struct backlight_device *backlight_device;
-static struct mutex sabi_mutex;
-static struct platform_device *sdev;
-static struct rfkill *rfk;
-static bool has_stepping_quirk;
+static struct samsung_quirks samsung_broken_acpi_video = {
+	.broken_acpi_video = true,
+};
 
 static bool force;
 module_param(force, bool, 0);
@@ -237,176 +366,143 @@ static bool debug;
 module_param(debug, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(debug, "Debug enabled or not");
 
-static int sabi_get_command(u8 command, struct sabi_retval *sretval)
+static int sabi_command(struct samsung_laptop *samsung, u16 command,
+			struct sabi_data *in,
+			struct sabi_data *out)
 {
-	int retval = 0;
-	u16 port = readw(sabi + sabi_config->header_offsets.port);
+	const struct sabi_config *config = samsung->config;
+	int ret = 0;
+	u16 port = readw(samsung->sabi + config->header_offsets.port);
 	u8 complete, iface_data;
 
-	mutex_lock(&sabi_mutex);
-
-	/* enable memory to be able to write to it */
-	outb(readb(sabi + sabi_config->header_offsets.en_mem), port);
-
-	/* write out the command */
-	writew(sabi_config->main_function, sabi_iface + SABI_IFACE_MAIN);
-	writew(command, sabi_iface + SABI_IFACE_SUB);
-	writeb(0, sabi_iface + SABI_IFACE_COMPLETE);
-	outb(readb(sabi + sabi_config->header_offsets.iface_func), port);
-
-	/* write protect memory to make it safe */
-	outb(readb(sabi + sabi_config->header_offsets.re_mem), port);
+	mutex_lock(&samsung->sabi_mutex);
 
-	/* see if the command actually succeeded */
-	complete = readb(sabi_iface + SABI_IFACE_COMPLETE);
-	iface_data = readb(sabi_iface + SABI_IFACE_DATA);
-	if (complete != 0xaa || iface_data == 0xff) {
-		pr_warn("SABI get command 0x%02x failed with completion flag 0x%02x and data 0x%02x\n",
-		        command, complete, iface_data);
-		retval = -EINVAL;
-		goto exit;
+	if (debug) {
+		if (in)
+			pr_info("SABI command:0x%04x "
+				"data:{0x%08x, 0x%08x, 0x%04x, 0x%02x}",
+				command, in->d0, in->d1, in->d2, in->d3);
+		else
+			pr_info("SABI command:0x%04x", command);
 	}
-	/*
-	 * Save off the data into a structure so the caller use it.
-	 * Right now we only want the first 4 bytes,
-	 * There are commands that need more, but not for the ones we
-	 * currently care about.
-	 */
-	sretval->retval[0] = readb(sabi_iface + SABI_IFACE_DATA);
-	sretval->retval[1] = readb(sabi_iface + SABI_IFACE_DATA + 1);
-	sretval->retval[2] = readb(sabi_iface + SABI_IFACE_DATA + 2);
-	sretval->retval[3] = readb(sabi_iface + SABI_IFACE_DATA + 3);
-
-exit:
-	mutex_unlock(&sabi_mutex);
-	return retval;
-
-}
-
-static int sabi_set_command(u8 command, u8 data)
-{
-	int retval = 0;
-	u16 port = readw(sabi + sabi_config->header_offsets.port);
-	u8 complete, iface_data;
-
-	mutex_lock(&sabi_mutex);
 
 	/* enable memory to be able to write to it */
-	outb(readb(sabi + sabi_config->header_offsets.en_mem), port);
+	outb(readb(samsung->sabi + config->header_offsets.en_mem), port);
 
 	/* write out the command */
-	writew(sabi_config->main_function, sabi_iface + SABI_IFACE_MAIN);
-	writew(command, sabi_iface + SABI_IFACE_SUB);
-	writeb(0, sabi_iface + SABI_IFACE_COMPLETE);
-	writeb(data, sabi_iface + SABI_IFACE_DATA);
-	outb(readb(sabi + sabi_config->header_offsets.iface_func), port);
+	writew(config->main_function, samsung->sabi_iface + SABI_IFACE_MAIN);
+	writew(command, samsung->sabi_iface + SABI_IFACE_SUB);
+	writeb(0, samsung->sabi_iface + SABI_IFACE_COMPLETE);
+	if (in) {
+		writel(in->d0, samsung->sabi_iface + SABI_IFACE_DATA);
+		writel(in->d1, samsung->sabi_iface + SABI_IFACE_DATA + 4);
+		writew(in->d2, samsung->sabi_iface + SABI_IFACE_DATA + 8);
+		writeb(in->d3, samsung->sabi_iface + SABI_IFACE_DATA + 10);
+	}
+	outb(readb(samsung->sabi + config->header_offsets.iface_func), port);
 
 	/* write protect memory to make it safe */
-	outb(readb(sabi + sabi_config->header_offsets.re_mem), port);
+	outb(readb(samsung->sabi + config->header_offsets.re_mem), port);
 
 	/* see if the command actually succeeded */
-	complete = readb(sabi_iface + SABI_IFACE_COMPLETE);
-	iface_data = readb(sabi_iface + SABI_IFACE_DATA);
+	complete = readb(samsung->sabi_iface + SABI_IFACE_COMPLETE);
+	iface_data = readb(samsung->sabi_iface + SABI_IFACE_DATA);
+
+	/* iface_data = 0xFF happens when a command is not known
+	 * so we only add a warning in debug mode since we will
+	 * probably issue some unknown command at startup to find
+	 * out which features are supported */
+	if (complete != 0xaa || (iface_data == 0xff && debug))
+		pr_warn("SABI command 0x%04x failed with"
+			" completion flag 0x%02x and interface data 0x%02x",
+			command, complete, iface_data);
+
 	if (complete != 0xaa || iface_data == 0xff) {
-		pr_warn("SABI set command 0x%02x failed with completion flag 0x%02x and data 0x%02x\n",
-		       command, complete, iface_data);
-		retval = -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 
-	mutex_unlock(&sabi_mutex);
-	return retval;
-}
-
-static void test_backlight(void)
-{
-	struct sabi_retval sretval;
-
-	sabi_get_command(sabi_config->commands.get_backlight, &sretval);
-	printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]);
-
-	sabi_set_command(sabi_config->commands.set_backlight, 0);
-	printk(KERN_DEBUG "backlight should be off\n");
-
-	sabi_get_command(sabi_config->commands.get_backlight, &sretval);
-	printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]);
-
-	msleep(1000);
+	if (out) {
+		out->d0 = readl(samsung->sabi_iface + SABI_IFACE_DATA);
+		out->d1 = readl(samsung->sabi_iface + SABI_IFACE_DATA + 4);
+		out->d2 = readw(samsung->sabi_iface + SABI_IFACE_DATA + 2);
+		out->d3 = readb(samsung->sabi_iface + SABI_IFACE_DATA + 1);
+	}
 
-	sabi_set_command(sabi_config->commands.set_backlight, 1);
-	printk(KERN_DEBUG "backlight should be on\n");
+	if (debug && out) {
+		pr_info("SABI return data:{0x%08x, 0x%08x, 0x%04x, 0x%02x}",
+			out->d0, out->d1, out->d2, out->d3);
+	}
 
-	sabi_get_command(sabi_config->commands.get_backlight, &sretval);
-	printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]);
+exit:
+	mutex_unlock(&samsung->sabi_mutex);
+	return ret;
 }
 
-static void test_wireless(void)
+/* simple wrappers usable with most commands */
+static int sabi_set_commandb(struct samsung_laptop *samsung,
+			     u16 command, u8 data)
 {
-	struct sabi_retval sretval;
-
-	sabi_get_command(sabi_config->commands.get_wireless_button, &sretval);
-	printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]);
-
-	sabi_set_command(sabi_config->commands.set_wireless_button, 0);
-	printk(KERN_DEBUG "wireless led should be off\n");
-
-	sabi_get_command(sabi_config->commands.get_wireless_button, &sretval);
-	printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]);
+	struct sabi_data in = { { { .d0 = 0, .d1 = 0, .d2 = 0, .d3 = 0 } } };
 
-	msleep(1000);
-
-	sabi_set_command(sabi_config->commands.set_wireless_button, 1);
-	printk(KERN_DEBUG "wireless led should be on\n");
-
-	sabi_get_command(sabi_config->commands.get_wireless_button, &sretval);
-	printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]);
+	in.data[0] = data;
+	return sabi_command(samsung, command, &in, NULL);
 }
 
-static u8 read_brightness(void)
+static int read_brightness(struct samsung_laptop *samsung)
 {
-	struct sabi_retval sretval;
+	const struct sabi_config *config = samsung->config;
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data sretval;
 	int user_brightness = 0;
 	int retval;
 
-	retval = sabi_get_command(sabi_config->commands.get_brightness,
-				  &sretval);
-	if (!retval) {
-		user_brightness = sretval.retval[0];
-		if (user_brightness > sabi_config->min_brightness)
-			user_brightness -= sabi_config->min_brightness;
-		else
-			user_brightness = 0;
-	}
+	retval = sabi_command(samsung, commands->get_brightness,
+			      NULL, &sretval);
+	if (retval)
+		return retval;
+
+	user_brightness = sretval.data[0];
+	if (user_brightness > config->min_brightness)
+		user_brightness -= config->min_brightness;
+	else
+		user_brightness = 0;
+
 	return user_brightness;
 }
 
-static void set_brightness(u8 user_brightness)
+static void set_brightness(struct samsung_laptop *samsung, u8 user_brightness)
 {
-	u8 user_level = user_brightness + sabi_config->min_brightness;
+	const struct sabi_config *config = samsung->config;
+	const struct sabi_commands *commands = &samsung->config->commands;
+	u8 user_level = user_brightness + config->min_brightness;
 
-	if (has_stepping_quirk && user_level != 0) {
+	if (samsung->has_stepping_quirk && user_level != 0) {
 		/*
 		 * short circuit if the specified level is what's already set
 		 * to prevent the screen from flickering needlessly
 		 */
-		if (user_brightness == read_brightness())
+		if (user_brightness == read_brightness(samsung))
 			return;
 
-		sabi_set_command(sabi_config->commands.set_brightness, 0);
+		sabi_set_commandb(samsung, commands->set_brightness, 0);
 	}
 
-	sabi_set_command(sabi_config->commands.set_brightness, user_level);
+	sabi_set_commandb(samsung, commands->set_brightness, user_level);
 }
 
 static int get_brightness(struct backlight_device *bd)
 {
-	return (int)read_brightness();
+	struct samsung_laptop *samsung = bl_get_data(bd);
+
+	return read_brightness(samsung);
 }
 
-static void check_for_stepping_quirk(void)
+static void check_for_stepping_quirk(struct samsung_laptop *samsung)
 {
-	u8 initial_level;
-	u8 check_level;
-	u8 orig_level = read_brightness();
+	int initial_level;
+	int check_level;
+	int orig_level = read_brightness(samsung);
 
 	/*
 	 * Some laptops exhibit the strange behaviour of stepping toward
@@ -416,34 +512,38 @@ static void check_for_stepping_quirk(void)
 	 */
 
 	if (orig_level == 0)
-		set_brightness(1);
+		set_brightness(samsung, 1);
 
-	initial_level = read_brightness();
+	initial_level = read_brightness(samsung);
 
 	if (initial_level <= 2)
 		check_level = initial_level + 2;
 	else
 		check_level = initial_level - 2;
 
-	has_stepping_quirk = false;
-	set_brightness(check_level);
+	samsung->has_stepping_quirk = false;
+	set_brightness(samsung, check_level);
 
-	if (read_brightness() != check_level) {
-		has_stepping_quirk = true;
+	if (read_brightness(samsung) != check_level) {
+		samsung->has_stepping_quirk = true;
 		pr_info("enabled workaround for brightness stepping quirk\n");
 	}
 
-	set_brightness(orig_level);
+	set_brightness(samsung, orig_level);
 }
 
 static int update_status(struct backlight_device *bd)
 {
-	set_brightness(bd->props.brightness);
+	struct samsung_laptop *samsung = bl_get_data(bd);
+	const struct sabi_commands *commands = &samsung->config->commands;
+
+	set_brightness(samsung, bd->props.brightness);
 
 	if (bd->props.power == FB_BLANK_UNBLANK)
-		sabi_set_command(sabi_config->commands.set_backlight, 1);
+		sabi_set_commandb(samsung, commands->set_backlight, 1);
 	else
-		sabi_set_command(sabi_config->commands.set_backlight, 0);
+		sabi_set_commandb(samsung, commands->set_backlight, 0);
+
 	return 0;
 }
 
@@ -452,66 +552,101 @@ static const struct backlight_ops backlight_ops = {
 	.update_status	= update_status,
 };
 
-static int rfkill_set(void *data, bool blocked)
+static int seclinux_rfkill_set(void *data, bool blocked)
 {
-	/* Do something with blocked...*/
-	/*
-	 * blocked == false is on
-	 * blocked == true is off
-	 */
-	if (blocked)
-		sabi_set_command(sabi_config->commands.set_wireless_button, 0);
-	else
-		sabi_set_command(sabi_config->commands.set_wireless_button, 1);
+	struct samsung_rfkill *srfkill = data;
+	struct samsung_laptop *samsung = srfkill->samsung;
+	const struct sabi_commands *commands = &samsung->config->commands;
 
-	return 0;
+	return sabi_set_commandb(samsung, commands->set_wireless_button,
+				 !blocked);
 }
 
-static struct rfkill_ops rfkill_ops = {
-	.set_block = rfkill_set,
+static struct rfkill_ops seclinux_rfkill_ops = {
+	.set_block = seclinux_rfkill_set,
 };
 
-static int init_wireless(struct platform_device *sdev)
+static int swsmi_wireless_status(struct samsung_laptop *samsung,
+				 struct sabi_data *data)
 {
-	int retval;
+	const struct sabi_commands *commands = &samsung->config->commands;
 
-	rfk = rfkill_alloc("samsung-wifi", &sdev->dev, RFKILL_TYPE_WLAN,
-			   &rfkill_ops, NULL);
-	if (!rfk)
-		return -ENOMEM;
-
-	retval = rfkill_register(rfk);
-	if (retval) {
-		rfkill_destroy(rfk);
-		return -ENODEV;
-	}
+	return sabi_command(samsung, commands->get_wireless_status,
+			    NULL, data);
+}
 
-	return 0;
+static int swsmi_rfkill_set(void *priv, bool blocked)
+{
+	struct samsung_rfkill *srfkill = priv;
+	struct samsung_laptop *samsung = srfkill->samsung;
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data data;
+	int ret, i;
+
+	ret = swsmi_wireless_status(samsung, &data);
+	if (ret)
+		return ret;
+
+	/* Don't set the state for non-present devices */
+	for (i = 0; i < 4; i++)
+		if (data.data[i] == 0x02)
+			data.data[1] = 0;
+
+	if (srfkill->type == RFKILL_TYPE_WLAN)
+		data.data[WL_STATUS_WLAN] = !blocked;
+	else if (srfkill->type == RFKILL_TYPE_BLUETOOTH)
+		data.data[WL_STATUS_BT] = !blocked;
+
+	return sabi_command(samsung, commands->set_wireless_status,
+			    &data, &data);
 }
 
-static void destroy_wireless(void)
+static void swsmi_rfkill_query(struct rfkill *rfkill, void *priv)
 {
-	rfkill_unregister(rfk);
-	rfkill_destroy(rfk);
+	struct samsung_rfkill *srfkill = priv;
+	struct samsung_laptop *samsung = srfkill->samsung;
+	struct sabi_data data;
+	int ret;
+
+	ret = swsmi_wireless_status(samsung, &data);
+	if (ret)
+		return ;
+
+	if (srfkill->type == RFKILL_TYPE_WLAN)
+		ret = data.data[WL_STATUS_WLAN];
+	else if (srfkill->type == RFKILL_TYPE_BLUETOOTH)
+		ret = data.data[WL_STATUS_BT];
+	else
+		return ;
+
+	rfkill_set_sw_state(rfkill, !ret);
 }
 
+static struct rfkill_ops swsmi_rfkill_ops = {
+	.set_block = swsmi_rfkill_set,
+	.query = swsmi_rfkill_query,
+};
+
 static ssize_t get_performance_level(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	struct sabi_retval sretval;
+	struct samsung_laptop *samsung = dev_get_drvdata(dev);
+	const struct sabi_config *config = samsung->config;
+	const struct sabi_commands *commands = &config->commands;
+	struct sabi_data sretval;
 	int retval;
 	int i;
 
 	/* Read the state */
-	retval = sabi_get_command(sabi_config->commands.get_performance_level,
-				  &sretval);
+	retval = sabi_command(samsung, commands->get_performance_level,
+			      NULL, &sretval);
 	if (retval)
 		return retval;
 
 	/* The logic is backwards, yeah, lots of fun... */
-	for (i = 0; sabi_config->performance_levels[i].name; ++i) {
-		if (sretval.retval[0] == sabi_config->performance_levels[i].value)
-			return sprintf(buf, "%s\n", sabi_config->performance_levels[i].name);
+	for (i = 0; config->performance_levels[i].name; ++i) {
+		if (sretval.data[0] == config->performance_levels[i].value)
+			return sprintf(buf, "%s\n", config->performance_levels[i].name);
 	}
 	return sprintf(buf, "%s\n", "unknown");
 }
@@ -520,269 +655,178 @@ static ssize_t set_performance_level(struct device *dev,
 				struct device_attribute *attr, const char *buf,
 				size_t count)
 {
-	if (count >= 1) {
-		int i;
-		for (i = 0; sabi_config->performance_levels[i].name; ++i) {
-			const struct sabi_performance_level *level =
-				&sabi_config->performance_levels[i];
-			if (!strncasecmp(level->name, buf, strlen(level->name))) {
-				sabi_set_command(sabi_config->commands.set_performance_level,
-						 level->value);
-				break;
-			}
+	struct samsung_laptop *samsung = dev_get_drvdata(dev);
+	const struct sabi_config *config = samsung->config;
+	const struct sabi_commands *commands = &config->commands;
+	int i;
+
+	if (count < 1)
+		return count;
+
+	for (i = 0; config->performance_levels[i].name; ++i) {
+		const struct sabi_performance_level *level =
+			&config->performance_levels[i];
+		if (!strncasecmp(level->name, buf, strlen(level->name))) {
+			sabi_set_commandb(samsung,
+					  commands->set_performance_level,
+					  level->value);
+			break;
 		}
-		if (!sabi_config->performance_levels[i].name)
-			return -EINVAL;
 	}
+
+	if (!config->performance_levels[i].name)
+		return -EINVAL;
+
 	return count;
 }
+
 static DEVICE_ATTR(performance_level, S_IWUSR | S_IRUGO,
 		   get_performance_level, set_performance_level);
 
+static int read_battery_life_extender(struct samsung_laptop *samsung)
+{
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data data;
+	int retval;
+
+	if (commands->get_battery_life_extender == 0xFFFF)
+		return -ENODEV;
+
+	memset(&data, 0, sizeof(data));
+	data.data[0] = 0x80;
+	retval = sabi_command(samsung, commands->get_battery_life_extender,
+			      &data, &data);
 
-static int __init dmi_check_cb(const struct dmi_system_id *id)
+	if (retval)
+		return retval;
+
+	if (data.data[0] != 0 && data.data[0] != 1)
+		return -ENODEV;
+
+	return data.data[0];
+}
+
+static int write_battery_life_extender(struct samsung_laptop *samsung,
+				       int enabled)
 {
-	pr_info("found laptop model '%s'\n",
-		id->ident);
-	return 1;
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data data;
+
+	memset(&data, 0, sizeof(data));
+	data.data[0] = 0x80 | enabled;
+	return sabi_command(samsung, commands->set_battery_life_extender,
+			    &data, NULL);
 }
 
-static struct dmi_system_id __initdata samsung_dmi_table[] = {
-	{
-		.ident = "N128",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N128"),
-			DMI_MATCH(DMI_BOARD_NAME, "N128"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "N130",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N130"),
-			DMI_MATCH(DMI_BOARD_NAME, "N130"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "N510",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N510"),
-			DMI_MATCH(DMI_BOARD_NAME, "N510"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "X125",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X125"),
-			DMI_MATCH(DMI_BOARD_NAME, "X125"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "X120/X170",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X120/X170"),
-			DMI_MATCH(DMI_BOARD_NAME, "X120/X170"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "NC10",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "NC10"),
-			DMI_MATCH(DMI_BOARD_NAME, "NC10"),
-		},
-		.callback = dmi_check_cb,
-	},
-		{
-		.ident = "NP-Q45",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "SQ45S70S"),
-			DMI_MATCH(DMI_BOARD_NAME, "SQ45S70S"),
-		},
-		.callback = dmi_check_cb,
-		},
-	{
-		.ident = "X360",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X360"),
-			DMI_MATCH(DMI_BOARD_NAME, "X360"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "R410 Plus",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "R410P"),
-			DMI_MATCH(DMI_BOARD_NAME, "R460"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "R518",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "R518"),
-			DMI_MATCH(DMI_BOARD_NAME, "R518"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "R519/R719",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "R519/R719"),
-			DMI_MATCH(DMI_BOARD_NAME, "R519/R719"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "N150/N210/N220",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220"),
-			DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "N220",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N220"),
-			DMI_MATCH(DMI_BOARD_NAME, "N220"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "N150/N210/N220/N230",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220/N230"),
-			DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220/N230"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "N150P/N210P/N220P",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N150P/N210P/N220P"),
-			DMI_MATCH(DMI_BOARD_NAME, "N150P/N210P/N220P"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "R700",
-		.matches = {
-		      DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-		      DMI_MATCH(DMI_PRODUCT_NAME, "SR700"),
-		      DMI_MATCH(DMI_BOARD_NAME, "SR700"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "R530/R730",
-		.matches = {
-		      DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-		      DMI_MATCH(DMI_PRODUCT_NAME, "R530/R730"),
-		      DMI_MATCH(DMI_BOARD_NAME, "R530/R730"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "NF110/NF210/NF310",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "NF110/NF210/NF310"),
-			DMI_MATCH(DMI_BOARD_NAME, "NF110/NF210/NF310"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "N145P/N250P/N260P",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N145P/N250P/N260P"),
-			DMI_MATCH(DMI_BOARD_NAME, "N145P/N250P/N260P"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "R70/R71",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR,
-					"SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "R70/R71"),
-			DMI_MATCH(DMI_BOARD_NAME, "R70/R71"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "P460",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "P460"),
-			DMI_MATCH(DMI_BOARD_NAME, "P460"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "R528/R728",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "R528/R728"),
-			DMI_MATCH(DMI_BOARD_NAME, "R528/R728"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{
-		.ident = "NC210/NC110",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "NC210/NC110"),
-			DMI_MATCH(DMI_BOARD_NAME, "NC210/NC110"),
-		},
-		.callback = dmi_check_cb,
-	},
-		{
-		.ident = "X520",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X520"),
-			DMI_MATCH(DMI_BOARD_NAME, "X520"),
-		},
-		.callback = dmi_check_cb,
-	},
-	{ },
+static ssize_t get_battery_life_extender(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct samsung_laptop *samsung = dev_get_drvdata(dev);
+	int ret;
+
+	ret = read_battery_life_extender(samsung);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", ret);
+}
+
+static ssize_t set_battery_life_extender(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct samsung_laptop *samsung = dev_get_drvdata(dev);
+	int ret, value;
+
+	if (!count || sscanf(buf, "%i", &value) != 1)
+		return -EINVAL;
+
+	ret = write_battery_life_extender(samsung, !!value);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR(battery_life_extender, S_IWUSR | S_IRUGO,
+		   get_battery_life_extender, set_battery_life_extender);
+
+static int read_usb_charge(struct samsung_laptop *samsung)
+{
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data data;
+	int retval;
+
+	if (commands->get_usb_charge == 0xFFFF)
+		return -ENODEV;
+
+	memset(&data, 0, sizeof(data));
+	data.data[0] = 0x80;
+	retval = sabi_command(samsung, commands->get_usb_charge,
+			      &data, &data);
+
+	if (retval)
+		return retval;
+
+	if (data.data[0] != 0 && data.data[0] != 1)
+		return -ENODEV;
+
+	return data.data[0];
+}
+
+static int write_usb_charge(struct samsung_laptop *samsung,
+			    int enabled)
+{
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data data;
+
+	memset(&data, 0, sizeof(data));
+	data.data[0] = 0x80 | enabled;
+	return sabi_command(samsung, commands->set_usb_charge,
+			    &data, NULL);
+}
+
+static ssize_t get_usb_charge(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct samsung_laptop *samsung = dev_get_drvdata(dev);
+	int ret;
+
+	ret = read_usb_charge(samsung);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", ret);
+}
+
+static ssize_t set_usb_charge(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct samsung_laptop *samsung = dev_get_drvdata(dev);
+	int ret, value;
+
+	if (!count || sscanf(buf, "%i", &value) != 1)
+		return -EINVAL;
+
+	ret = write_usb_charge(samsung, !!value);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR(usb_charge, S_IWUSR | S_IRUGO,
+		   get_usb_charge, set_usb_charge);
+
+static struct attribute *platform_attributes[] = {
+	&dev_attr_performance_level.attr,
+	&dev_attr_battery_life_extender.attr,
+	&dev_attr_usb_charge.attr,
+	NULL
 };
-MODULE_DEVICE_TABLE(dmi, samsung_dmi_table);
 
 static int find_signature(void __iomem *memcheck, const char *testStr)
 {
@@ -803,153 +847,772 @@ static int find_signature(void __iomem *memcheck, const char *testStr)
 	return loca;
 }
 
-static int __init samsung_init(void)
+static void samsung_rfkill_exit(struct samsung_laptop *samsung)
 {
-	struct backlight_properties props;
-	struct sabi_retval sretval;
-	unsigned int ifaceP;
-	int i;
-	int loca;
+	if (samsung->wlan.rfkill) {
+		rfkill_unregister(samsung->wlan.rfkill);
+		rfkill_destroy(samsung->wlan.rfkill);
+		samsung->wlan.rfkill = NULL;
+	}
+	if (samsung->bluetooth.rfkill) {
+		rfkill_unregister(samsung->bluetooth.rfkill);
+		rfkill_destroy(samsung->bluetooth.rfkill);
+		samsung->bluetooth.rfkill = NULL;
+	}
+}
+
+static int samsung_new_rfkill(struct samsung_laptop *samsung,
+			      struct samsung_rfkill *arfkill,
+			      const char *name, enum rfkill_type type,
+			      const struct rfkill_ops *ops,
+			      int blocked)
+{
+	struct rfkill **rfkill = &arfkill->rfkill;
+	int ret;
+
+	arfkill->type = type;
+	arfkill->samsung = samsung;
+
+	*rfkill = rfkill_alloc(name, &samsung->platform_device->dev,
+			       type, ops, arfkill);
+
+	if (!*rfkill)
+		return -EINVAL;
+
+	if (blocked != -1)
+		rfkill_init_sw_state(*rfkill, blocked);
+
+	ret = rfkill_register(*rfkill);
+	if (ret) {
+		rfkill_destroy(*rfkill);
+		*rfkill = NULL;
+		return ret;
+	}
+	return 0;
+}
+
+static int __init samsung_rfkill_init_seclinux(struct samsung_laptop *samsung)
+{
+	return samsung_new_rfkill(samsung, &samsung->wlan, "samsung-wlan",
+				  RFKILL_TYPE_WLAN, &seclinux_rfkill_ops, -1);
+}
+
+static int __init samsung_rfkill_init_swsmi(struct samsung_laptop *samsung)
+{
+	struct sabi_data data;
+	int ret;
+
+	ret = swsmi_wireless_status(samsung, &data);
+	if (ret) {
+		/* Some swsmi laptops use the old seclinux way to control
+		 * wireless devices */
+		if (ret == -EINVAL)
+			ret = samsung_rfkill_init_seclinux(samsung);
+		return ret;
+	}
+
+	/* 0x02 seems to mean that the device is no present/available */
+
+	if (data.data[WL_STATUS_WLAN] != 0x02)
+		ret = samsung_new_rfkill(samsung, &samsung->wlan,
+					 "samsung-wlan",
+					 RFKILL_TYPE_WLAN,
+					 &swsmi_rfkill_ops,
+					 !data.data[WL_STATUS_WLAN]);
+	if (ret)
+		goto exit;
+
+	if (data.data[WL_STATUS_BT] != 0x02)
+		ret = samsung_new_rfkill(samsung, &samsung->bluetooth,
+					 "samsung-bluetooth",
+					 RFKILL_TYPE_BLUETOOTH,
+					 &swsmi_rfkill_ops,
+					 !data.data[WL_STATUS_BT]);
+	if (ret)
+		goto exit;
+
+exit:
+	if (ret)
+		samsung_rfkill_exit(samsung);
+
+	return ret;
+}
+
+static int __init samsung_rfkill_init(struct samsung_laptop *samsung)
+{
+	if (samsung->config->sabi_version == 2)
+		return samsung_rfkill_init_seclinux(samsung);
+	if (samsung->config->sabi_version == 3)
+		return samsung_rfkill_init_swsmi(samsung);
+	return 0;
+}
+
+static int kbd_backlight_enable(struct samsung_laptop *samsung)
+{
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data data;
 	int retval;
 
-	mutex_init(&sabi_mutex);
+	if (commands->kbd_backlight == 0xFFFF)
+		return -ENODEV;
+
+	memset(&data, 0, sizeof(data));
+	data.d0 = 0xaabb;
+	retval = sabi_command(samsung, commands->kbd_backlight,
+			      &data, &data);
 
-	if (!force && !dmi_check_system(samsung_dmi_table))
+	if (retval)
+		return retval;
+
+	if (data.d0 != 0xccdd)
 		return -ENODEV;
+	return 0;
+}
 
-	f0000_segment = ioremap_nocache(0xf0000, 0xffff);
-	if (!f0000_segment) {
-		pr_err("Can't map the segment at 0xf0000\n");
-		return -EINVAL;
+static int kbd_backlight_read(struct samsung_laptop *samsung)
+{
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data data;
+	int retval;
+
+	memset(&data, 0, sizeof(data));
+	data.data[0] = 0x81;
+	retval = sabi_command(samsung, commands->kbd_backlight,
+			      &data, &data);
+
+	if (retval)
+		return retval;
+
+	return data.data[0];
+}
+
+static int kbd_backlight_write(struct samsung_laptop *samsung, int brightness)
+{
+	const struct sabi_commands *commands = &samsung->config->commands;
+	struct sabi_data data;
+
+	memset(&data, 0, sizeof(data));
+	data.d0 = 0x82 | ((brightness & 0xFF) << 8);
+	return sabi_command(samsung, commands->kbd_backlight,
+			    &data, NULL);
+}
+
+static void kbd_led_update(struct work_struct *work)
+{
+	struct samsung_laptop *samsung;
+
+	samsung = container_of(work, struct samsung_laptop, kbd_led_work);
+	kbd_backlight_write(samsung, samsung->kbd_led_wk);
+}
+
+static void kbd_led_set(struct led_classdev *led_cdev,
+			enum led_brightness value)
+{
+	struct samsung_laptop *samsung;
+
+	samsung = container_of(led_cdev, struct samsung_laptop, kbd_led);
+
+	if (value > samsung->kbd_led.max_brightness)
+		value = samsung->kbd_led.max_brightness;
+	else if (value < 0)
+		value = 0;
+
+	samsung->kbd_led_wk = value;
+	queue_work(samsung->led_workqueue, &samsung->kbd_led_work);
+}
+
+static enum led_brightness kbd_led_get(struct led_classdev *led_cdev)
+{
+	struct samsung_laptop *samsung;
+
+	samsung = container_of(led_cdev, struct samsung_laptop, kbd_led);
+	return kbd_backlight_read(samsung);
+}
+
+static void samsung_leds_exit(struct samsung_laptop *samsung)
+{
+	if (!IS_ERR_OR_NULL(samsung->kbd_led.dev))
+		led_classdev_unregister(&samsung->kbd_led);
+	if (samsung->led_workqueue)
+		destroy_workqueue(samsung->led_workqueue);
+}
+
+static int __init samsung_leds_init(struct samsung_laptop *samsung)
+{
+	int ret = 0;
+
+	samsung->led_workqueue = create_singlethread_workqueue("led_workqueue");
+	if (!samsung->led_workqueue)
+		return -ENOMEM;
+
+	if (kbd_backlight_enable(samsung) >= 0) {
+		INIT_WORK(&samsung->kbd_led_work, kbd_led_update);
+
+		samsung->kbd_led.name = "samsung::kbd_backlight";
+		samsung->kbd_led.brightness_set = kbd_led_set;
+		samsung->kbd_led.brightness_get = kbd_led_get;
+		samsung->kbd_led.max_brightness = 8;
+
+		ret = led_classdev_register(&samsung->platform_device->dev,
+					   &samsung->kbd_led);
+	}
+
+	if (ret)
+		samsung_leds_exit(samsung);
+
+	return ret;
+}
+
+static void samsung_backlight_exit(struct samsung_laptop *samsung)
+{
+	if (samsung->backlight_device) {
+		backlight_device_unregister(samsung->backlight_device);
+		samsung->backlight_device = NULL;
+	}
+}
+
+static int __init samsung_backlight_init(struct samsung_laptop *samsung)
+{
+	struct backlight_device *bd;
+	struct backlight_properties props;
+
+	if (!samsung->handle_backlight)
+		return 0;
+
+	memset(&props, 0, sizeof(struct backlight_properties));
+	props.type = BACKLIGHT_PLATFORM;
+	props.max_brightness = samsung->config->max_brightness -
+		samsung->config->min_brightness;
+
+	bd = backlight_device_register("samsung",
+				       &samsung->platform_device->dev,
+				       samsung, &backlight_ops,
+				       &props);
+	if (IS_ERR(bd))
+		return PTR_ERR(bd);
+
+	samsung->backlight_device = bd;
+	samsung->backlight_device->props.brightness = read_brightness(samsung);
+	samsung->backlight_device->props.power = FB_BLANK_UNBLANK;
+	backlight_update_status(samsung->backlight_device);
+
+	return 0;
+}
+
+static umode_t samsung_sysfs_is_visible(struct kobject *kobj,
+				       struct attribute *attr, int idx)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct samsung_laptop *samsung = platform_get_drvdata(pdev);
+	bool ok = true;
+
+	if (attr == &dev_attr_performance_level.attr)
+		ok = !!samsung->config->performance_levels[0].name;
+	if (attr == &dev_attr_battery_life_extender.attr)
+		ok = !!(read_battery_life_extender(samsung) >= 0);
+	if (attr == &dev_attr_usb_charge.attr)
+		ok = !!(read_usb_charge(samsung) >= 0);
+
+	return ok ? attr->mode : 0;
+}
+
+static struct attribute_group platform_attribute_group = {
+	.is_visible = samsung_sysfs_is_visible,
+	.attrs = platform_attributes
+};
+
+static void samsung_sysfs_exit(struct samsung_laptop *samsung)
+{
+	struct platform_device *device = samsung->platform_device;
+
+	sysfs_remove_group(&device->dev.kobj, &platform_attribute_group);
+}
+
+static int __init samsung_sysfs_init(struct samsung_laptop *samsung)
+{
+	struct platform_device *device = samsung->platform_device;
+
+	return sysfs_create_group(&device->dev.kobj, &platform_attribute_group);
+
+}
+
+static int show_call(struct seq_file *m, void *data)
+{
+	struct samsung_laptop *samsung = m->private;
+	struct sabi_data *sdata = &samsung->debug.data;
+	int ret;
+
+	seq_printf(m, "SABI 0x%04x {0x%08x, 0x%08x, 0x%04x, 0x%02x}\n",
+		   samsung->debug.command,
+		   sdata->d0, sdata->d1, sdata->d2, sdata->d3);
+
+	ret = sabi_command(samsung, samsung->debug.command, sdata, sdata);
+
+	if (ret) {
+		seq_printf(m, "SABI command 0x%04x failed\n",
+			   samsung->debug.command);
+		return ret;
+	}
+
+	seq_printf(m, "SABI {0x%08x, 0x%08x, 0x%04x, 0x%02x}\n",
+		   sdata->d0, sdata->d1, sdata->d2, sdata->d3);
+	return 0;
+}
+
+static int samsung_debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_call, inode->i_private);
+}
+
+static const struct file_operations samsung_laptop_call_io_ops = {
+	.owner = THIS_MODULE,
+	.open = samsung_debugfs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static void samsung_debugfs_exit(struct samsung_laptop *samsung)
+{
+	debugfs_remove_recursive(samsung->debug.root);
+}
+
+static int samsung_debugfs_init(struct samsung_laptop *samsung)
+{
+	struct dentry *dent;
+
+	samsung->debug.root = debugfs_create_dir("samsung-laptop", NULL);
+	if (!samsung->debug.root) {
+		pr_err("failed to create debugfs directory");
+		goto error_debugfs;
+	}
+
+	samsung->debug.f0000_wrapper.data = samsung->f0000_segment;
+	samsung->debug.f0000_wrapper.size = 0xffff;
+
+	samsung->debug.data_wrapper.data = &samsung->debug.data;
+	samsung->debug.data_wrapper.size = sizeof(samsung->debug.data);
+
+	samsung->debug.sdiag_wrapper.data = samsung->sdiag;
+	samsung->debug.sdiag_wrapper.size = strlen(samsung->sdiag);
+
+	dent = debugfs_create_u16("command", S_IRUGO | S_IWUSR,
+				  samsung->debug.root, &samsung->debug.command);
+	if (!dent)
+		goto error_debugfs;
+
+	dent = debugfs_create_u32("d0", S_IRUGO | S_IWUSR, samsung->debug.root,
+				  &samsung->debug.data.d0);
+	if (!dent)
+		goto error_debugfs;
+
+	dent = debugfs_create_u32("d1", S_IRUGO | S_IWUSR, samsung->debug.root,
+				  &samsung->debug.data.d1);
+	if (!dent)
+		goto error_debugfs;
+
+	dent = debugfs_create_u16("d2", S_IRUGO | S_IWUSR, samsung->debug.root,
+				  &samsung->debug.data.d2);
+	if (!dent)
+		goto error_debugfs;
+
+	dent = debugfs_create_u8("d3", S_IRUGO | S_IWUSR, samsung->debug.root,
+				 &samsung->debug.data.d3);
+	if (!dent)
+		goto error_debugfs;
+
+	dent = debugfs_create_blob("data", S_IRUGO | S_IWUSR,
+				   samsung->debug.root,
+				   &samsung->debug.data_wrapper);
+	if (!dent)
+		goto error_debugfs;
+
+	dent = debugfs_create_blob("f0000_segment", S_IRUSR | S_IWUSR,
+				   samsung->debug.root,
+				   &samsung->debug.f0000_wrapper);
+	if (!dent)
+		goto error_debugfs;
+
+	dent = debugfs_create_file("call", S_IFREG | S_IRUGO,
+				   samsung->debug.root, samsung,
+				   &samsung_laptop_call_io_ops);
+	if (!dent)
+		goto error_debugfs;
+
+	dent = debugfs_create_blob("sdiag", S_IRUGO | S_IWUSR,
+				   samsung->debug.root,
+				   &samsung->debug.sdiag_wrapper);
+	if (!dent)
+		goto error_debugfs;
+
+	return 0;
+
+error_debugfs:
+	samsung_debugfs_exit(samsung);
+	return -ENOMEM;
+}
+
+static void samsung_sabi_exit(struct samsung_laptop *samsung)
+{
+	const struct sabi_config *config = samsung->config;
+
+	/* Turn off "Linux" mode in the BIOS */
+	if (config && config->commands.set_linux != 0xff)
+		sabi_set_commandb(samsung, config->commands.set_linux, 0x80);
+
+	if (samsung->sabi_iface) {
+		iounmap(samsung->sabi_iface);
+		samsung->sabi_iface = NULL;
+	}
+	if (samsung->f0000_segment) {
+		iounmap(samsung->f0000_segment);
+		samsung->f0000_segment = NULL;
+	}
+
+	samsung->config = NULL;
+}
+
+static __init void samsung_sabi_infos(struct samsung_laptop *samsung, int loca,
+				      unsigned int ifaceP)
+{
+	const struct sabi_config *config = samsung->config;
+
+	printk(KERN_DEBUG "This computer supports SABI==%x\n",
+	       loca + 0xf0000 - 6);
+
+	printk(KERN_DEBUG "SABI header:\n");
+	printk(KERN_DEBUG " SMI Port Number = 0x%04x\n",
+	       readw(samsung->sabi + config->header_offsets.port));
+	printk(KERN_DEBUG " SMI Interface Function = 0x%02x\n",
+	       readb(samsung->sabi + config->header_offsets.iface_func));
+	printk(KERN_DEBUG " SMI enable memory buffer = 0x%02x\n",
+	       readb(samsung->sabi + config->header_offsets.en_mem));
+	printk(KERN_DEBUG " SMI restore memory buffer = 0x%02x\n",
+	       readb(samsung->sabi + config->header_offsets.re_mem));
+	printk(KERN_DEBUG " SABI data offset = 0x%04x\n",
+	       readw(samsung->sabi + config->header_offsets.data_offset));
+	printk(KERN_DEBUG " SABI data segment = 0x%04x\n",
+	       readw(samsung->sabi + config->header_offsets.data_segment));
+
+	printk(KERN_DEBUG " SABI pointer = 0x%08x\n", ifaceP);
+}
+
+static void __init samsung_sabi_diag(struct samsung_laptop *samsung)
+{
+	int loca = find_signature(samsung->f0000_segment, "SDiaG@");
+	int i;
+
+	if (loca == 0xffff)
+		return ;
+
+	/* Example:
+	 * Ident: @SDiaG@686XX-N90X3A/966-SEC-07HL-S90X3A
+	 *
+	 * Product name: 90X3A
+	 * BIOS Version: 07HL
+	 */
+	loca += 1;
+	for (i = 0; loca < 0xffff && i < sizeof(samsung->sdiag) - 1; loca++) {
+		char temp = readb(samsung->f0000_segment + loca);
+
+		if (isalnum(temp) || temp == '/' || temp == '-')
+			samsung->sdiag[i++] = temp;
+		else
+			break ;
 	}
 
+	if (debug && samsung->sdiag[0])
+		pr_info("sdiag: %s", samsung->sdiag);
+}
+
+static int __init samsung_sabi_init(struct samsung_laptop *samsung)
+{
+	const struct sabi_config *config = NULL;
+	const struct sabi_commands *commands;
+	unsigned int ifaceP;
+	int ret = 0;
+	int i;
+	int loca;
+
+	samsung->f0000_segment = ioremap_nocache(0xf0000, 0xffff);
+	if (!samsung->f0000_segment) {
+		if (debug || force)
+			pr_err("Can't map the segment at 0xf0000\n");
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	samsung_sabi_diag(samsung);
+
 	/* Try to find one of the signatures in memory to find the header */
 	for (i = 0; sabi_configs[i].test_string != 0; ++i) {
-		sabi_config = &sabi_configs[i];
-		loca = find_signature(f0000_segment, sabi_config->test_string);
+		samsung->config = &sabi_configs[i];
+		loca = find_signature(samsung->f0000_segment,
+				      samsung->config->test_string);
 		if (loca != 0xffff)
 			break;
 	}
 
 	if (loca == 0xffff) {
-		pr_err("This computer does not support SABI\n");
-		goto error_no_signature;
+		if (debug || force)
+			pr_err("This computer does not support SABI\n");
+		ret = -ENODEV;
+		goto exit;
 	}
 
+	config = samsung->config;
+	commands = &config->commands;
+
 	/* point to the SMI port Number */
 	loca += 1;
-	sabi = (f0000_segment + loca);
-
-	if (debug) {
-		printk(KERN_DEBUG "This computer supports SABI==%x\n",
-			loca + 0xf0000 - 6);
-		printk(KERN_DEBUG "SABI header:\n");
-		printk(KERN_DEBUG " SMI Port Number = 0x%04x\n",
-			readw(sabi + sabi_config->header_offsets.port));
-		printk(KERN_DEBUG " SMI Interface Function = 0x%02x\n",
-			readb(sabi + sabi_config->header_offsets.iface_func));
-		printk(KERN_DEBUG " SMI enable memory buffer = 0x%02x\n",
-			readb(sabi + sabi_config->header_offsets.en_mem));
-		printk(KERN_DEBUG " SMI restore memory buffer = 0x%02x\n",
-			readb(sabi + sabi_config->header_offsets.re_mem));
-		printk(KERN_DEBUG " SABI data offset = 0x%04x\n",
-			readw(sabi + sabi_config->header_offsets.data_offset));
-		printk(KERN_DEBUG " SABI data segment = 0x%04x\n",
-			readw(sabi + sabi_config->header_offsets.data_segment));
-	}
+	samsung->sabi = (samsung->f0000_segment + loca);
 
 	/* Get a pointer to the SABI Interface */
-	ifaceP = (readw(sabi + sabi_config->header_offsets.data_segment) & 0x0ffff) << 4;
-	ifaceP += readw(sabi + sabi_config->header_offsets.data_offset) & 0x0ffff;
-	sabi_iface = ioremap_nocache(ifaceP, 16);
-	if (!sabi_iface) {
-		pr_err("Can't remap %x\n", ifaceP);
-		goto error_no_signature;
-	}
-	if (debug) {
-		printk(KERN_DEBUG "ifaceP = 0x%08x\n", ifaceP);
-		printk(KERN_DEBUG "sabi_iface = %p\n", sabi_iface);
+	ifaceP = (readw(samsung->sabi + config->header_offsets.data_segment) & 0x0ffff) << 4;
+	ifaceP += readw(samsung->sabi + config->header_offsets.data_offset) & 0x0ffff;
 
-		test_backlight();
-		test_wireless();
+	if (debug)
+		samsung_sabi_infos(samsung, loca, ifaceP);
 
-		retval = sabi_get_command(sabi_config->commands.get_brightness,
-					  &sretval);
-		printk(KERN_DEBUG "brightness = 0x%02x\n", sretval.retval[0]);
+	samsung->sabi_iface = ioremap_nocache(ifaceP, 16);
+	if (!samsung->sabi_iface) {
+		pr_err("Can't remap %x\n", ifaceP);
+		ret = -EINVAL;
+		goto exit;
 	}
 
 	/* Turn on "Linux" mode in the BIOS */
-	if (sabi_config->commands.set_linux != 0xff) {
-		retval = sabi_set_command(sabi_config->commands.set_linux,
-					  0x81);
+	if (commands->set_linux != 0xff) {
+		int retval = sabi_set_commandb(samsung,
+					       commands->set_linux, 0x81);
 		if (retval) {
 			pr_warn("Linux mode was not set!\n");
-			goto error_no_platform;
+			ret = -ENODEV;
+			goto exit;
 		}
 	}
 
 	/* Check for stepping quirk */
-	check_for_stepping_quirk();
+	if (samsung->handle_backlight)
+		check_for_stepping_quirk(samsung);
 
-	/* knock up a platform device to hang stuff off of */
-	sdev = platform_device_register_simple("samsung", -1, NULL, 0);
-	if (IS_ERR(sdev))
-		goto error_no_platform;
+	pr_info("detected SABI interface: %s\n",
+		samsung->config->test_string);
 
-	/* create a backlight device to talk to this one */
-	memset(&props, 0, sizeof(struct backlight_properties));
-	props.type = BACKLIGHT_PLATFORM;
-	props.max_brightness = sabi_config->max_brightness -
-				sabi_config->min_brightness;
-	backlight_device = backlight_device_register("samsung", &sdev->dev,
-						     NULL, &backlight_ops,
-						     &props);
-	if (IS_ERR(backlight_device))
-		goto error_no_backlight;
-
-	backlight_device->props.brightness = read_brightness();
-	backlight_device->props.power = FB_BLANK_UNBLANK;
-	backlight_update_status(backlight_device);
-
-	retval = init_wireless(sdev);
-	if (retval)
-		goto error_no_rfk;
+exit:
+	if (ret)
+		samsung_sabi_exit(samsung);
 
-	retval = device_create_file(&sdev->dev, &dev_attr_performance_level);
-	if (retval)
-		goto error_file_create;
+	return ret;
+}
+
+static void samsung_platform_exit(struct samsung_laptop *samsung)
+{
+	if (samsung->platform_device) {
+		platform_device_unregister(samsung->platform_device);
+		samsung->platform_device = NULL;
+	}
+}
+
+static int __init samsung_platform_init(struct samsung_laptop *samsung)
+{
+	struct platform_device *pdev;
+
+	pdev = platform_device_register_simple("samsung", -1, NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
 
+	samsung->platform_device = pdev;
+	platform_set_drvdata(samsung->platform_device, samsung);
 	return 0;
+}
+
+static struct samsung_quirks *quirks;
+
+static int __init samsung_dmi_matched(const struct dmi_system_id *d)
+{
+	quirks = d->driver_data;
+	return 0;
+}
+
+static struct dmi_system_id __initdata samsung_dmi_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR,
+					"SAMSUNG ELECTRONICS CO., LTD."),
+			DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR,
+					"SAMSUNG ELECTRONICS CO., LTD."),
+			DMI_MATCH(DMI_CHASSIS_TYPE, "9"), /* Laptop */
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR,
+					"SAMSUNG ELECTRONICS CO., LTD."),
+			DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR,
+					"SAMSUNG ELECTRONICS CO., LTD."),
+			DMI_MATCH(DMI_CHASSIS_TYPE, "14"), /* Sub-Notebook */
+		},
+	},
+	/* Specific DMI ids for laptop with quirks */
+	{
+	 .callback = samsung_dmi_matched,
+	 .ident = "N150P",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "N150P"),
+		DMI_MATCH(DMI_BOARD_NAME, "N150P"),
+		},
+	 .driver_data = &samsung_broken_acpi_video,
+	},
+	{
+	 .callback = samsung_dmi_matched,
+	 .ident = "N145P/N250P/N260P",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "N145P/N250P/N260P"),
+		DMI_MATCH(DMI_BOARD_NAME, "N145P/N250P/N260P"),
+		},
+	 .driver_data = &samsung_broken_acpi_video,
+	},
+	{
+	 .callback = samsung_dmi_matched,
+	 .ident = "N150/N210/N220",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220"),
+		DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220"),
+		},
+	 .driver_data = &samsung_broken_acpi_video,
+	},
+	{
+	 .callback = samsung_dmi_matched,
+	 .ident = "NF110/NF210/NF310",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "NF110/NF210/NF310"),
+		DMI_MATCH(DMI_BOARD_NAME, "NF110/NF210/NF310"),
+		},
+	 .driver_data = &samsung_broken_acpi_video,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(dmi, samsung_dmi_table);
 
-error_file_create:
-	destroy_wireless();
+static struct platform_device *samsung_platform_device;
 
-error_no_rfk:
-	backlight_device_unregister(backlight_device);
+static int __init samsung_init(void)
+{
+	struct samsung_laptop *samsung;
+	int ret;
 
-error_no_backlight:
-	platform_device_unregister(sdev);
+	quirks = &samsung_unknown;
+	if (!force && !dmi_check_system(samsung_dmi_table))
+		return -ENODEV;
+
+	samsung = kzalloc(sizeof(*samsung), GFP_KERNEL);
+	if (!samsung)
+		return -ENOMEM;
 
-error_no_platform:
-	iounmap(sabi_iface);
+	mutex_init(&samsung->sabi_mutex);
+	samsung->handle_backlight = true;
+	samsung->quirks = quirks;
 
-error_no_signature:
-	iounmap(f0000_segment);
-	return -EINVAL;
+
+#if (defined CONFIG_ACPI_VIDEO || defined CONFIG_ACPI_VIDEO_MODULE)
+	/* Don't handle backlight here if the acpi video already handle it */
+	if (acpi_video_backlight_support()) {
+		if (samsung->quirks->broken_acpi_video) {
+			pr_info("Disabling ACPI video driver\n");
+			acpi_video_unregister();
+		} else {
+			samsung->handle_backlight = false;
+		}
+	}
+#endif
+
+	ret = samsung_platform_init(samsung);
+	if (ret)
+		goto error_platform;
+
+	ret = samsung_sabi_init(samsung);
+	if (ret)
+		goto error_sabi;
+
+#ifdef CONFIG_ACPI
+	/* Only log that if we are really on a sabi platform */
+	if (acpi_video_backlight_support() &&
+	    !samsung->quirks->broken_acpi_video)
+		pr_info("Backlight controlled by ACPI video driver\n");
+#endif
+
+	ret = samsung_sysfs_init(samsung);
+	if (ret)
+		goto error_sysfs;
+
+	ret = samsung_backlight_init(samsung);
+	if (ret)
+		goto error_backlight;
+
+	ret = samsung_rfkill_init(samsung);
+	if (ret)
+		goto error_rfkill;
+
+	ret = samsung_leds_init(samsung);
+	if (ret)
+		goto error_leds;
+
+	ret = samsung_debugfs_init(samsung);
+	if (ret)
+		goto error_debugfs;
+
+	samsung_platform_device = samsung->platform_device;
+	return ret;
+
+error_debugfs:
+	samsung_leds_exit(samsung);
+error_leds:
+	samsung_rfkill_exit(samsung);
+error_rfkill:
+	samsung_backlight_exit(samsung);
+error_backlight:
+	samsung_sysfs_exit(samsung);
+error_sysfs:
+	samsung_sabi_exit(samsung);
+error_sabi:
+	samsung_platform_exit(samsung);
+error_platform:
+	kfree(samsung);
+	return ret;
 }
 
 static void __exit samsung_exit(void)
 {
-	/* Turn off "Linux" mode in the BIOS */
-	if (sabi_config->commands.set_linux != 0xff)
-		sabi_set_command(sabi_config->commands.set_linux, 0x80);
-
-	device_remove_file(&sdev->dev, &dev_attr_performance_level);
-	backlight_device_unregister(backlight_device);
-	destroy_wireless();
-	iounmap(sabi_iface);
-	iounmap(f0000_segment);
-	platform_device_unregister(sdev);
+	struct samsung_laptop *samsung;
+
+	samsung = platform_get_drvdata(samsung_platform_device);
+
+	samsung_debugfs_exit(samsung);
+	samsung_leds_exit(samsung);
+	samsung_rfkill_exit(samsung);
+	samsung_backlight_exit(samsung);
+	samsung_sysfs_exit(samsung);
+	samsung_sabi_exit(samsung);
+	samsung_platform_exit(samsung);
+
+	kfree(samsung);
+	samsung_platform_device = NULL;
 }
 
 module_init(samsung_init);
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index c006dee5ebfe..8a51795aa02a 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -127,7 +127,7 @@ MODULE_PARM_DESC(minor,
 		 "default is -1 (automatic)");
 #endif
 
-static int kbd_backlight;	/* = 1 */
+static int kbd_backlight = 1;
 module_param(kbd_backlight, int, 0444);
 MODULE_PARM_DESC(kbd_backlight,
 		 "set this to 0 to disable keyboard backlight, "
@@ -347,6 +347,7 @@ static void sony_laptop_report_input_event(u8 event)
 	struct input_dev *jog_dev = sony_laptop_input.jog_dev;
 	struct input_dev *key_dev = sony_laptop_input.key_dev;
 	struct sony_laptop_keypress kp = { NULL };
+	int scancode = -1;
 
 	if (event == SONYPI_EVENT_FNKEY_RELEASED ||
 			event == SONYPI_EVENT_ANYBUTTON_RELEASED) {
@@ -380,8 +381,8 @@ static void sony_laptop_report_input_event(u8 event)
 			dprintk("sony_laptop_report_input_event, event not known: %d\n", event);
 			break;
 		}
-		if (sony_laptop_input_index[event] != -1) {
-			kp.key = sony_laptop_input_keycode_map[sony_laptop_input_index[event]];
+		if ((scancode = sony_laptop_input_index[event]) != -1) {
+			kp.key = sony_laptop_input_keycode_map[scancode];
 			if (kp.key != KEY_UNKNOWN)
 				kp.dev = key_dev;
 		}
@@ -389,9 +390,11 @@ static void sony_laptop_report_input_event(u8 event)
 	}
 
 	if (kp.dev) {
+		/* if we have a scancode we emit it so we can always
+		    remap the key */
+		if (scancode != -1)
+			input_event(kp.dev, EV_MSC, MSC_SCAN, scancode);
 		input_report_key(kp.dev, kp.key, 1);
-		/* we emit the scancode so we can always remap the key */
-		input_event(kp.dev, EV_MSC, MSC_SCAN, event);
 		input_sync(kp.dev);
 
 		/* schedule key release */
@@ -466,7 +469,7 @@ static int sony_laptop_setup_input(struct acpi_device *acpi_device)
 	jog_dev->name = "Sony Vaio Jogdial";
 	jog_dev->id.bustype = BUS_ISA;
 	jog_dev->id.vendor = PCI_VENDOR_ID_SONY;
-	key_dev->dev.parent = &acpi_device->dev;
+	jog_dev->dev.parent = &acpi_device->dev;
 
 	input_set_capability(jog_dev, EV_KEY, BTN_MIDDLE);
 	input_set_capability(jog_dev, EV_REL, REL_WHEEL);
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index ea0c6075b720..d68c0002f4a2 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -8658,7 +8658,7 @@ static int __must_check __init get_thinkpad_model_data(
 	}
 
 	s = dmi_get_system_info(DMI_PRODUCT_VERSION);
-	if (s && !strnicmp(s, "ThinkPad", 8)) {
+	if (s && !(strnicmp(s, "ThinkPad", 8) && strnicmp(s, "Lenovo", 6))) {
 		tp->model_str = kstrdup(s, GFP_KERNEL);
 		if (!tp->model_str)
 			return -ENOMEM;
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index dcdc1f4a4624..ee79ce64d9df 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -52,6 +52,8 @@
 #include <linux/input/sparse-keymap.h>
 #include <linux/leds.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/i8042.h>
 
 #include <asm/uaccess.h>
 
@@ -61,6 +63,11 @@ MODULE_AUTHOR("John Belmonte");
 MODULE_DESCRIPTION("Toshiba Laptop ACPI Extras Driver");
 MODULE_LICENSE("GPL");
 
+#define TOSHIBA_WMI_EVENT_GUID "59142400-C6A3-40FA-BADB-8A2652834100"
+
+/* Scan code for Fn key on TOS1900 models */
+#define TOS1900_FN_SCAN		0x6e
+
 /* Toshiba ACPI method paths */
 #define METHOD_VIDEO_OUT	"\\_SB_.VALX.DSSX"
 
@@ -95,6 +102,8 @@ MODULE_LICENSE("GPL");
 #define HCI_WIRELESS			0x0056
 
 /* field definitions */
+#define HCI_HOTKEY_DISABLE		0x0b
+#define HCI_HOTKEY_ENABLE		0x09
 #define HCI_LCD_BRIGHTNESS_BITS		3
 #define HCI_LCD_BRIGHTNESS_SHIFT	(16-HCI_LCD_BRIGHTNESS_BITS)
 #define HCI_LCD_BRIGHTNESS_LEVELS	(1 << HCI_LCD_BRIGHTNESS_BITS)
@@ -111,6 +120,7 @@ struct toshiba_acpi_dev {
 	const char *method_hci;
 	struct rfkill *bt_rfk;
 	struct input_dev *hotkey_dev;
+	struct work_struct hotkey_work;
 	struct backlight_device *backlight_dev;
 	struct led_classdev led_dev;
 
@@ -118,14 +128,18 @@ struct toshiba_acpi_dev {
 	int last_key_event;
 	int key_event_valid;
 
-	int illumination_supported:1;
-	int video_supported:1;
-	int fan_supported:1;
-	int system_event_supported:1;
+	unsigned int illumination_supported:1;
+	unsigned int video_supported:1;
+	unsigned int fan_supported:1;
+	unsigned int system_event_supported:1;
+	unsigned int ntfy_supported:1;
+	unsigned int info_supported:1;
 
 	struct mutex mutex;
 };
 
+static struct toshiba_acpi_dev *toshiba_acpi;
+
 static const struct acpi_device_id toshiba_device_ids[] = {
 	{"TOS6200", 0},
 	{"TOS6208", 0},
@@ -138,6 +152,8 @@ static const struct key_entry toshiba_acpi_keymap[] __devinitconst = {
 	{ KE_KEY, 0x101, { KEY_MUTE } },
 	{ KE_KEY, 0x102, { KEY_ZOOMOUT } },
 	{ KE_KEY, 0x103, { KEY_ZOOMIN } },
+	{ KE_KEY, 0x12c, { KEY_KBDILLUMTOGGLE } },
+	{ KE_KEY, 0x139, { KEY_ZOOMRESET } },
 	{ KE_KEY, 0x13b, { KEY_COFFEE } },
 	{ KE_KEY, 0x13c, { KEY_BATTERY } },
 	{ KE_KEY, 0x13d, { KEY_SLEEP } },
@@ -146,7 +162,7 @@ static const struct key_entry toshiba_acpi_keymap[] __devinitconst = {
 	{ KE_KEY, 0x140, { KEY_BRIGHTNESSDOWN } },
 	{ KE_KEY, 0x141, { KEY_BRIGHTNESSUP } },
 	{ KE_KEY, 0x142, { KEY_WLAN } },
-	{ KE_KEY, 0x143, { KEY_PROG1 } },
+	{ KE_KEY, 0x143, { KEY_TOUCHPAD_TOGGLE } },
 	{ KE_KEY, 0x17f, { KEY_FN } },
 	{ KE_KEY, 0xb05, { KEY_PROG2 } },
 	{ KE_KEY, 0xb06, { KEY_WWW } },
@@ -156,6 +172,7 @@ static const struct key_entry toshiba_acpi_keymap[] __devinitconst = {
 	{ KE_KEY, 0xb32, { KEY_NEXTSONG } },
 	{ KE_KEY, 0xb33, { KEY_PLAYPAUSE } },
 	{ KE_KEY, 0xb5a, { KEY_MEDIA } },
+	{ KE_IGNORE, 0x1430, { KEY_RESERVED } },
 	{ KE_END, 0 },
 };
 
@@ -847,10 +864,78 @@ static const struct backlight_ops toshiba_backlight_data = {
         .update_status  = set_lcd_status,
 };
 
+static bool toshiba_acpi_i8042_filter(unsigned char data, unsigned char str,
+				      struct serio *port)
+{
+	if (str & 0x20)
+		return false;
+
+	if (unlikely(data == 0xe0))
+		return false;
+
+	if ((data & 0x7f) == TOS1900_FN_SCAN) {
+		schedule_work(&toshiba_acpi->hotkey_work);
+		return true;
+	}
+
+	return false;
+}
+
+static void toshiba_acpi_hotkey_work(struct work_struct *work)
+{
+	acpi_handle ec_handle = ec_get_handle();
+	acpi_status status;
+
+	if (!ec_handle)
+		return;
+
+	status = acpi_evaluate_object(ec_handle, "NTFY", NULL, NULL);
+	if (ACPI_FAILURE(status))
+		pr_err("ACPI NTFY method execution failed\n");
+}
+
+/*
+ * Returns hotkey scancode, or < 0 on failure.
+ */
+static int toshiba_acpi_query_hotkey(struct toshiba_acpi_dev *dev)
+{
+	struct acpi_buffer buf;
+	union acpi_object out_obj;
+	acpi_status status;
+
+	buf.pointer = &out_obj;
+	buf.length = sizeof(out_obj);
+
+	status = acpi_evaluate_object(dev->acpi_dev->handle, "INFO",
+				      NULL, &buf);
+	if (ACPI_FAILURE(status) || out_obj.type != ACPI_TYPE_INTEGER) {
+		pr_err("ACPI INFO method execution failed\n");
+		return -EIO;
+	}
+
+	return out_obj.integer.value;
+}
+
+static void toshiba_acpi_report_hotkey(struct toshiba_acpi_dev *dev,
+				       int scancode)
+{
+	if (scancode == 0x100)
+		return;
+
+	/* act on key press; ignore key release */
+	if (scancode & 0x80)
+		return;
+
+	if (!sparse_keymap_report_event(dev->hotkey_dev, scancode, 1, true))
+		pr_info("Unknown key %x\n", scancode);
+}
+
 static int __devinit toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev)
 {
 	acpi_status status;
+	acpi_handle ec_handle, handle;
 	int error;
+	u32 hci_result;
 
 	dev->hotkey_dev = input_allocate_device();
 	if (!dev->hotkey_dev) {
@@ -866,21 +951,67 @@ static int __devinit toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev)
 	if (error)
 		goto err_free_dev;
 
+	/*
+	 * For some machines the SCI responsible for providing hotkey
+	 * notification doesn't fire. We can trigger the notification
+	 * whenever the Fn key is pressed using the NTFY method, if
+	 * supported, so if it's present set up an i8042 key filter
+	 * for this purpose.
+	 */
+	status = AE_ERROR;
+	ec_handle = ec_get_handle();
+	if (ec_handle)
+		status = acpi_get_handle(ec_handle, "NTFY", &handle);
+
+	if (ACPI_SUCCESS(status)) {
+		INIT_WORK(&dev->hotkey_work, toshiba_acpi_hotkey_work);
+
+		error = i8042_install_filter(toshiba_acpi_i8042_filter);
+		if (error) {
+			pr_err("Error installing key filter\n");
+			goto err_free_keymap;
+		}
+
+		dev->ntfy_supported = 1;
+	}
+
+	/*
+	 * Determine hotkey query interface. Prefer using the INFO
+	 * method when it is available.
+	 */
+	status = acpi_get_handle(dev->acpi_dev->handle, "INFO", &handle);
+	if (ACPI_SUCCESS(status)) {
+		dev->info_supported = 1;
+	} else {
+		hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
+		if (hci_result == HCI_SUCCESS)
+			dev->system_event_supported = 1;
+	}
+
+	if (!dev->info_supported && !dev->system_event_supported) {
+		pr_warn("No hotkey query interface found\n");
+		goto err_remove_filter;
+	}
+
 	status = acpi_evaluate_object(dev->acpi_dev->handle, "ENAB", NULL, NULL);
 	if (ACPI_FAILURE(status)) {
 		pr_info("Unable to enable hotkeys\n");
 		error = -ENODEV;
-		goto err_free_keymap;
+		goto err_remove_filter;
 	}
 
 	error = input_register_device(dev->hotkey_dev);
 	if (error) {
 		pr_info("Unable to register input device\n");
-		goto err_free_keymap;
+		goto err_remove_filter;
 	}
 
+	hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_ENABLE, &hci_result);
 	return 0;
 
+ err_remove_filter:
+	if (dev->ntfy_supported)
+		i8042_remove_filter(toshiba_acpi_i8042_filter);
  err_free_keymap:
 	sparse_keymap_free(dev->hotkey_dev);
  err_free_dev:
@@ -895,6 +1026,11 @@ static int toshiba_acpi_remove(struct acpi_device *acpi_dev, int type)
 
 	remove_toshiba_proc_entries(dev);
 
+	if (dev->ntfy_supported) {
+		i8042_remove_filter(toshiba_acpi_i8042_filter);
+		cancel_work_sync(&dev->hotkey_work);
+	}
+
 	if (dev->hotkey_dev) {
 		input_unregister_device(dev->hotkey_dev);
 		sparse_keymap_free(dev->hotkey_dev);
@@ -911,6 +1047,9 @@ static int toshiba_acpi_remove(struct acpi_device *acpi_dev, int type)
 	if (dev->illumination_supported)
 		led_classdev_unregister(&dev->led_dev);
 
+	if (toshiba_acpi)
+		toshiba_acpi = NULL;
+
 	kfree(dev);
 
 	return 0;
@@ -936,12 +1075,14 @@ static int __devinit toshiba_acpi_add(struct acpi_device *acpi_dev)
 {
 	struct toshiba_acpi_dev *dev;
 	const char *hci_method;
-	u32 hci_result;
 	u32 dummy;
 	bool bt_present;
 	int ret = 0;
 	struct backlight_properties props;
 
+	if (toshiba_acpi)
+		return -EBUSY;
+
 	pr_info("Toshiba Laptop ACPI Extras version %s\n",
 	       TOSHIBA_ACPI_VERSION);
 
@@ -963,11 +1104,6 @@ static int __devinit toshiba_acpi_add(struct acpi_device *acpi_dev)
 
 	mutex_init(&dev->mutex);
 
-	/* enable event fifo */
-	hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
-	if (hci_result == HCI_SUCCESS)
-		dev->system_event_supported = 1;
-
 	props.type = BACKLIGHT_PLATFORM;
 	props.max_brightness = HCI_LCD_BRIGHTNESS_LEVELS - 1;
 	dev->backlight_dev = backlight_device_register("toshiba",
@@ -1024,6 +1160,8 @@ static int __devinit toshiba_acpi_add(struct acpi_device *acpi_dev)
 
 	create_toshiba_proc_entries(dev);
 
+	toshiba_acpi = dev;
+
 	return 0;
 
 error:
@@ -1036,40 +1174,64 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event)
 	struct toshiba_acpi_dev *dev = acpi_driver_data(acpi_dev);
 	u32 hci_result, value;
 	int retries = 3;
+	int scancode;
 
-	if (!dev->system_event_supported || event != 0x80)
+	if (event != 0x80)
 		return;
 
-	do {
-		hci_read1(dev, HCI_SYSTEM_EVENT, &value, &hci_result);
-		switch (hci_result) {
-		case HCI_SUCCESS:
-			if (value == 0x100)
-				continue;
-			/* act on key press; ignore key release */
-			if (value & 0x80)
-				continue;
-
-			if (!sparse_keymap_report_event(dev->hotkey_dev,
-							value, 1, true)) {
-				pr_info("Unknown key %x\n",
-				       value);
+	if (dev->info_supported) {
+		scancode = toshiba_acpi_query_hotkey(dev);
+		if (scancode < 0)
+			pr_err("Failed to query hotkey event\n");
+		else if (scancode != 0)
+			toshiba_acpi_report_hotkey(dev, scancode);
+	} else if (dev->system_event_supported) {
+		do {
+			hci_read1(dev, HCI_SYSTEM_EVENT, &value, &hci_result);
+			switch (hci_result) {
+			case HCI_SUCCESS:
+				toshiba_acpi_report_hotkey(dev, (int)value);
+				break;
+			case HCI_NOT_SUPPORTED:
+				/*
+				 * This is a workaround for an unresolved
+				 * issue on some machines where system events
+				 * sporadically become disabled.
+				 */
+				hci_write1(dev, HCI_SYSTEM_EVENT, 1,
+					   &hci_result);
+				pr_notice("Re-enabled hotkeys\n");
+				/* fall through */
+			default:
+				retries--;
+				break;
 			}
-			break;
-		case HCI_NOT_SUPPORTED:
-			/* This is a workaround for an unresolved issue on
-			 * some machines where system events sporadically
-			 * become disabled. */
-			hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
-			pr_notice("Re-enabled hotkeys\n");
-			/* fall through */
-		default:
-			retries--;
-			break;
-		}
-	} while (retries && hci_result != HCI_EMPTY);
+		} while (retries && hci_result != HCI_EMPTY);
+	}
+}
+
+static int toshiba_acpi_suspend(struct acpi_device *acpi_dev,
+				pm_message_t state)
+{
+	struct toshiba_acpi_dev *dev = acpi_driver_data(acpi_dev);
+	u32 result;
+
+	if (dev->hotkey_dev)
+		hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_DISABLE, &result);
+
+	return 0;
 }
 
+static int toshiba_acpi_resume(struct acpi_device *acpi_dev)
+{
+	struct toshiba_acpi_dev *dev = acpi_driver_data(acpi_dev);
+	u32 result;
+
+	if (dev->hotkey_dev)
+		hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_ENABLE, &result);
+
+	return 0;
+}
 
 static struct acpi_driver toshiba_acpi_driver = {
 	.name	= "Toshiba ACPI driver",
@@ -1080,6 +1242,8 @@ static struct acpi_driver toshiba_acpi_driver = {
 		.add		= toshiba_acpi_add,
 		.remove		= toshiba_acpi_remove,
 		.notify		= toshiba_acpi_notify,
+		.suspend	= toshiba_acpi_suspend,
+		.resume		= toshiba_acpi_resume,
 	},
 };
 
@@ -1087,6 +1251,14 @@ static int __init toshiba_acpi_init(void)
 {
 	int ret;
 
+	/*
+	 * Machines with this WMI guid aren't supported due to bugs in
+	 * their AML. This check relies on wmi initializing before
+	 * toshiba_acpi to guarantee guids have been identified.
+	 */
+	if (wmi_has_guid(TOSHIBA_WMI_EVENT_GUID))
+		return -ENODEV;
+
 	toshiba_proc_dir = proc_mkdir(PROC_TOSHIBA, acpi_root_dir);
 	if (!toshiba_proc_dir) {
 		pr_err("Unable to create proc dir " PROC_TOSHIBA "\n");
diff --git a/drivers/platform/x86/xo1-rfkill.c b/drivers/platform/x86/xo1-rfkill.c
index e549eeeda121..41781ed8301c 100644
--- a/drivers/platform/x86/xo1-rfkill.c
+++ b/drivers/platform/x86/xo1-rfkill.c
@@ -67,19 +67,8 @@ static struct platform_driver xo1_rfkill_driver = {
 	.remove		= __devexit_p(xo1_rfkill_remove),
 };
 
-static int __init xo1_rfkill_init(void)
-{
-	return platform_driver_register(&xo1_rfkill_driver);
-}
-
-static void __exit xo1_rfkill_exit(void)
-{
-	platform_driver_unregister(&xo1_rfkill_driver);
-}
+module_platform_driver(xo1_rfkill_driver);
 
 MODULE_AUTHOR("Daniel Drake <dsd@laptop.org>");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:xo1-rfkill");
-
-module_init(xo1_rfkill_init);
-module_exit(xo1_rfkill_exit);
diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c
index b00c17612a89..d21e8f59c84e 100644
--- a/drivers/pnp/pnpacpi/core.c
+++ b/drivers/pnp/pnpacpi/core.c
@@ -321,9 +321,14 @@ static int __init acpi_pnp_match(struct device *dev, void *_pnp)
 {
 	struct acpi_device *acpi = to_acpi_device(dev);
 	struct pnp_dev *pnp = _pnp;
+	struct device *physical_device;
+
+	physical_device = acpi_get_physical_device(acpi->handle);
+	if (physical_device)
+		put_device(physical_device);
 
 	/* true means it matched */
-	return !acpi_get_physical_device(acpi->handle)
+	return !physical_device
 	    && compare_pnp_id(pnp->id, acpi_device_hid(acpi));
 }
 
diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c
index b859d16cf78c..769d265b221b 100644
--- a/drivers/pnp/pnpbios/bioscalls.c
+++ b/drivers/pnp/pnpbios/bioscalls.c
@@ -17,7 +17,6 @@
 
 #include <asm/page.h>
 #include <asm/desc.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 #include "pnpbios.h"
diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c
index cfe86853feb2..9d4222648640 100644
--- a/drivers/pnp/pnpbios/core.c
+++ b/drivers/pnp/pnpbios/core.c
@@ -65,7 +65,6 @@
 
 #include <asm/page.h>
 #include <asm/desc.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 #include "../base.h"
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 459f66437fe9..99dc29f2f2f2 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -249,7 +249,7 @@ config CHARGER_TWL4030
 	  Say Y here to enable support for TWL4030 Battery Charge Interface.
 
 config CHARGER_LP8727
-	tristate "National Semiconductor LP8727 charger driver"
+	tristate "TI/National Semiconductor LP8727 charger driver"
 	depends on I2C
 	help
 	  Say Y here to enable support for LP8727 Charger Driver.
@@ -288,4 +288,23 @@ config CHARGER_MAX8998
 	  Say Y to enable support for the battery charger control sysfs and
 	  platform data of MAX8998/LP3974 PMICs.
 
+config CHARGER_SMB347
+	tristate "Summit Microelectronics SMB347 Battery Charger"
+	depends on I2C
+	help
+	  Say Y to include support for Summit Microelectronics SMB347
+	  Battery Charger.
+
+config AB8500_BM
+	bool "AB8500 Battery Management Driver"
+	depends on AB8500_CORE && AB8500_GPADC
+	help
+	  Say Y to include support for AB5500 battery management.
+
+config AB8500_BATTERY_THERM_ON_BATCTRL
+	bool "Thermistor connected on BATCTRL ADC"
+	depends on AB8500_BM
+	help
+	  Say Y to enable battery temperature measurements using
+	  thermistor connected on BATCTRL ADC.
 endif # POWER_SUPPLY
diff --git a/drivers/power/Makefile b/drivers/power/Makefile
index c590fa533406..b6b243416c0e 100644
--- a/drivers/power/Makefile
+++ b/drivers/power/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_BATTERY_S3C_ADC)	+= s3c_adc_battery.o
 obj-$(CONFIG_CHARGER_PCF50633)	+= pcf50633-charger.o
 obj-$(CONFIG_BATTERY_JZ4740)	+= jz4740-battery.o
 obj-$(CONFIG_BATTERY_INTEL_MID)	+= intel_mid_battery.o
+obj-$(CONFIG_AB8500_BM)		+= ab8500_charger.o ab8500_btemp.o ab8500_fg.o abx500_chargalg.o
 obj-$(CONFIG_CHARGER_ISP1704)	+= isp1704_charger.o
 obj-$(CONFIG_CHARGER_MAX8903)	+= max8903_charger.o
 obj-$(CONFIG_CHARGER_TWL4030)	+= twl4030_charger.o
@@ -42,3 +43,4 @@ obj-$(CONFIG_CHARGER_GPIO)	+= gpio-charger.o
 obj-$(CONFIG_CHARGER_MANAGER)	+= charger-manager.o
 obj-$(CONFIG_CHARGER_MAX8997)	+= max8997_charger.o
 obj-$(CONFIG_CHARGER_MAX8998)	+= max8998_charger.o
+obj-$(CONFIG_CHARGER_SMB347)	+= smb347-charger.o
diff --git a/drivers/power/ab8500_btemp.c b/drivers/power/ab8500_btemp.c
new file mode 100644
index 000000000000..d8bb99394ac0
--- /dev/null
+++ b/drivers/power/ab8500_btemp.c
@@ -0,0 +1,1124 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2012
+ *
+ * Battery temperature driver for AB8500
+ *
+ * License Terms: GNU General Public License v2
+ * Author:
+ *	Johan Palsson <johan.palsson@stericsson.com>
+ *	Karl Komierowski <karl.komierowski@stericsson.com>
+ *	Arun R Murthy <arun.murthy@stericsson.com>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/completion.h>
+#include <linux/workqueue.h>
+#include <linux/mfd/abx500/ab8500.h>
+#include <linux/mfd/abx500.h>
+#include <linux/mfd/abx500/ab8500-bm.h>
+#include <linux/mfd/abx500/ab8500-gpadc.h>
+#include <linux/jiffies.h>
+
+#define VTVOUT_V			1800
+
+#define BTEMP_THERMAL_LOW_LIMIT		-10
+#define BTEMP_THERMAL_MED_LIMIT		0
+#define BTEMP_THERMAL_HIGH_LIMIT_52	52
+#define BTEMP_THERMAL_HIGH_LIMIT_57	57
+#define BTEMP_THERMAL_HIGH_LIMIT_62	62
+
+#define BTEMP_BATCTRL_CURR_SRC_7UA	7
+#define BTEMP_BATCTRL_CURR_SRC_20UA	20
+
+#define to_ab8500_btemp_device_info(x) container_of((x), \
+	struct ab8500_btemp, btemp_psy);
+
+/**
+ * struct ab8500_btemp_interrupts - ab8500 interrupts
+ * @name:	name of the interrupt
+ * @isr		function pointer to the isr
+ */
+struct ab8500_btemp_interrupts {
+	char *name;
+	irqreturn_t (*isr)(int irq, void *data);
+};
+
+struct ab8500_btemp_events {
+	bool batt_rem;
+	bool btemp_high;
+	bool btemp_medhigh;
+	bool btemp_lowmed;
+	bool btemp_low;
+	bool ac_conn;
+	bool usb_conn;
+};
+
+struct ab8500_btemp_ranges {
+	int btemp_high_limit;
+	int btemp_med_limit;
+	int btemp_low_limit;
+};
+
+/**
+ * struct ab8500_btemp - ab8500 BTEMP device information
+ * @dev:		Pointer to the structure device
+ * @node:		List of AB8500 BTEMPs, hence prepared for reentrance
+ * @curr_source:	What current source we use, in uA
+ * @bat_temp:		Battery temperature in degree Celcius
+ * @prev_bat_temp	Last dispatched battery temperature
+ * @parent:		Pointer to the struct ab8500
+ * @gpadc:		Pointer to the struct gpadc
+ * @fg:			Pointer to the struct fg
+ * @pdata:		Pointer to the abx500_btemp platform data
+ * @bat:		Pointer to the abx500_bm platform data
+ * @btemp_psy:		Structure for BTEMP specific battery properties
+ * @events:		Structure for information about events triggered
+ * @btemp_ranges:	Battery temperature range structure
+ * @btemp_wq:		Work queue for measuring the temperature periodically
+ * @btemp_periodic_work:	Work for measuring the temperature periodically
+ */
+struct ab8500_btemp {
+	struct device *dev;
+	struct list_head node;
+	int curr_source;
+	int bat_temp;
+	int prev_bat_temp;
+	struct ab8500 *parent;
+	struct ab8500_gpadc *gpadc;
+	struct ab8500_fg *fg;
+	struct abx500_btemp_platform_data *pdata;
+	struct abx500_bm_data *bat;
+	struct power_supply btemp_psy;
+	struct ab8500_btemp_events events;
+	struct ab8500_btemp_ranges btemp_ranges;
+	struct workqueue_struct *btemp_wq;
+	struct delayed_work btemp_periodic_work;
+};
+
+/* BTEMP power supply properties */
+static enum power_supply_property ab8500_btemp_props[] = {
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_TEMP,
+};
+
+static LIST_HEAD(ab8500_btemp_list);
+
+/**
+ * ab8500_btemp_get() - returns a reference to the primary AB8500 BTEMP
+ * (i.e. the first BTEMP in the instance list)
+ */
+struct ab8500_btemp *ab8500_btemp_get(void)
+{
+	struct ab8500_btemp *btemp;
+	btemp = list_first_entry(&ab8500_btemp_list, struct ab8500_btemp, node);
+
+	return btemp;
+}
+
+/**
+ * ab8500_btemp_batctrl_volt_to_res() - convert batctrl voltage to resistance
+ * @di:		pointer to the ab8500_btemp structure
+ * @v_batctrl:	measured batctrl voltage
+ * @inst_curr:	measured instant current
+ *
+ * This function returns the battery resistance that is
+ * derived from the BATCTRL voltage.
+ * Returns value in Ohms.
+ */
+static int ab8500_btemp_batctrl_volt_to_res(struct ab8500_btemp *di,
+	int v_batctrl, int inst_curr)
+{
+	int rbs;
+
+	if (is_ab8500_1p1_or_earlier(di->parent)) {
+		/*
+		 * For ABB cut1.0 and 1.1 BAT_CTRL is internally
+		 * connected to 1.8V through a 450k resistor
+		 */
+		return (450000 * (v_batctrl)) / (1800 - v_batctrl);
+	}
+
+	if (di->bat->adc_therm == ABx500_ADC_THERM_BATCTRL) {
+		/*
+		 * If the battery has internal NTC, we use the current
+		 * source to calculate the resistance, 7uA or 20uA
+		 */
+		rbs = (v_batctrl * 1000
+		       - di->bat->gnd_lift_resistance * inst_curr)
+		      / di->curr_source;
+	} else {
+		/*
+		 * BAT_CTRL is internally
+		 * connected to 1.8V through a 80k resistor
+		 */
+		rbs = (80000 * (v_batctrl)) / (1800 - v_batctrl);
+	}
+
+	return rbs;
+}
+
+/**
+ * ab8500_btemp_read_batctrl_voltage() - measure batctrl voltage
+ * @di:		pointer to the ab8500_btemp structure
+ *
+ * This function returns the voltage on BATCTRL. Returns value in mV.
+ */
+static int ab8500_btemp_read_batctrl_voltage(struct ab8500_btemp *di)
+{
+	int vbtemp;
+	static int prev;
+
+	vbtemp = ab8500_gpadc_convert(di->gpadc, BAT_CTRL);
+	if (vbtemp < 0) {
+		dev_err(di->dev,
+			"%s gpadc conversion failed, using previous value",
+			__func__);
+		return prev;
+	}
+	prev = vbtemp;
+	return vbtemp;
+}
+
+/**
+ * ab8500_btemp_curr_source_enable() - enable/disable batctrl current source
+ * @di:		pointer to the ab8500_btemp structure
+ * @enable:	enable or disable the current source
+ *
+ * Enable or disable the current sources for the BatCtrl AD channel
+ */
+static int ab8500_btemp_curr_source_enable(struct ab8500_btemp *di,
+	bool enable)
+{
+	int curr;
+	int ret = 0;
+
+	/*
+	 * BATCTRL current sources are included on AB8500 cut2.0
+	 * and future versions
+	 */
+	if (is_ab8500_1p1_or_earlier(di->parent))
+		return 0;
+
+	/* Only do this for batteries with internal NTC */
+	if (di->bat->adc_therm == ABx500_ADC_THERM_BATCTRL && enable) {
+		if (di->curr_source == BTEMP_BATCTRL_CURR_SRC_7UA)
+			curr = BAT_CTRL_7U_ENA;
+		else
+			curr = BAT_CTRL_20U_ENA;
+
+		dev_dbg(di->dev, "Set BATCTRL %duA\n", di->curr_source);
+
+		ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_CHARGER, AB8500_BAT_CTRL_CURRENT_SOURCE,
+			FORCE_BAT_CTRL_CMP_HIGH, FORCE_BAT_CTRL_CMP_HIGH);
+		if (ret) {
+			dev_err(di->dev, "%s failed setting cmp_force\n",
+				__func__);
+			return ret;
+		}
+
+		/*
+		 * We have to wait one 32kHz cycle before enabling
+		 * the current source, since ForceBatCtrlCmpHigh needs
+		 * to be written in a separate cycle
+		 */
+		udelay(32);
+
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_CHARGER, AB8500_BAT_CTRL_CURRENT_SOURCE,
+			FORCE_BAT_CTRL_CMP_HIGH | curr);
+		if (ret) {
+			dev_err(di->dev, "%s failed enabling current source\n",
+				__func__);
+			goto disable_curr_source;
+		}
+	} else if (di->bat->adc_therm == ABx500_ADC_THERM_BATCTRL && !enable) {
+		dev_dbg(di->dev, "Disable BATCTRL curr source\n");
+
+		/* Write 0 to the curr bits */
+		ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_CHARGER, AB8500_BAT_CTRL_CURRENT_SOURCE,
+			BAT_CTRL_7U_ENA | BAT_CTRL_20U_ENA,
+			~(BAT_CTRL_7U_ENA | BAT_CTRL_20U_ENA));
+		if (ret) {
+			dev_err(di->dev, "%s failed disabling current source\n",
+				__func__);
+			goto disable_curr_source;
+		}
+
+		/* Enable Pull-Up and comparator */
+		ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_CHARGER,	AB8500_BAT_CTRL_CURRENT_SOURCE,
+			BAT_CTRL_PULL_UP_ENA | BAT_CTRL_CMP_ENA,
+			BAT_CTRL_PULL_UP_ENA | BAT_CTRL_CMP_ENA);
+		if (ret) {
+			dev_err(di->dev, "%s failed enabling PU and comp\n",
+				__func__);
+			goto enable_pu_comp;
+		}
+
+		/*
+		 * We have to wait one 32kHz cycle before disabling
+		 * ForceBatCtrlCmpHigh since this needs to be written
+		 * in a separate cycle
+		 */
+		udelay(32);
+
+		/* Disable 'force comparator' */
+		ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_CHARGER, AB8500_BAT_CTRL_CURRENT_SOURCE,
+			FORCE_BAT_CTRL_CMP_HIGH, ~FORCE_BAT_CTRL_CMP_HIGH);
+		if (ret) {
+			dev_err(di->dev, "%s failed disabling force comp\n",
+				__func__);
+			goto disable_force_comp;
+		}
+	}
+	return ret;
+
+	/*
+	 * We have to try unsetting FORCE_BAT_CTRL_CMP_HIGH one more time
+	 * if we got an error above
+	 */
+disable_curr_source:
+	/* Write 0 to the curr bits */
+	ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_CHARGER, AB8500_BAT_CTRL_CURRENT_SOURCE,
+			BAT_CTRL_7U_ENA | BAT_CTRL_20U_ENA,
+			~(BAT_CTRL_7U_ENA | BAT_CTRL_20U_ENA));
+	if (ret) {
+		dev_err(di->dev, "%s failed disabling current source\n",
+			__func__);
+		return ret;
+	}
+enable_pu_comp:
+	/* Enable Pull-Up and comparator */
+	ret = abx500_mask_and_set_register_interruptible(di->dev,
+		AB8500_CHARGER,	AB8500_BAT_CTRL_CURRENT_SOURCE,
+		BAT_CTRL_PULL_UP_ENA | BAT_CTRL_CMP_ENA,
+		BAT_CTRL_PULL_UP_ENA | BAT_CTRL_CMP_ENA);
+	if (ret) {
+		dev_err(di->dev, "%s failed enabling PU and comp\n",
+			__func__);
+		return ret;
+	}
+
+disable_force_comp:
+	/*
+	 * We have to wait one 32kHz cycle before disabling
+	 * ForceBatCtrlCmpHigh since this needs to be written
+	 * in a separate cycle
+	 */
+	udelay(32);
+
+	/* Disable 'force comparator' */
+	ret = abx500_mask_and_set_register_interruptible(di->dev,
+		AB8500_CHARGER, AB8500_BAT_CTRL_CURRENT_SOURCE,
+		FORCE_BAT_CTRL_CMP_HIGH, ~FORCE_BAT_CTRL_CMP_HIGH);
+	if (ret) {
+		dev_err(di->dev, "%s failed disabling force comp\n",
+			__func__);
+		return ret;
+	}
+
+	return ret;
+}
+
+/**
+ * ab8500_btemp_get_batctrl_res() - get battery resistance
+ * @di:		pointer to the ab8500_btemp structure
+ *
+ * This function returns the battery pack identification resistance.
+ * Returns value in Ohms.
+ */
+static int ab8500_btemp_get_batctrl_res(struct ab8500_btemp *di)
+{
+	int ret;
+	int batctrl = 0;
+	int res;
+	int inst_curr;
+	int i;
+
+	/*
+	 * BATCTRL current sources are included on AB8500 cut2.0
+	 * and future versions
+	 */
+	ret = ab8500_btemp_curr_source_enable(di, true);
+	if (ret) {
+		dev_err(di->dev, "%s curr source enabled failed\n", __func__);
+		return ret;
+	}
+
+	if (!di->fg)
+		di->fg = ab8500_fg_get();
+	if (!di->fg) {
+		dev_err(di->dev, "No fg found\n");
+		return -EINVAL;
+	}
+
+	ret = ab8500_fg_inst_curr_start(di->fg);
+
+	if (ret) {
+		dev_err(di->dev, "Failed to start current measurement\n");
+		return ret;
+	}
+
+	/*
+	 * Since there is no interrupt when current measurement is done,
+	 * loop for over 250ms (250ms is one sample conversion time
+	 * with 32.768 Khz RTC clock). Note that a stop time must be set
+	 * since the ab8500_btemp_read_batctrl_voltage call can block and
+	 * take an unknown amount of time to complete.
+	 */
+	i = 0;
+
+	do {
+		batctrl += ab8500_btemp_read_batctrl_voltage(di);
+		i++;
+		msleep(20);
+	} while (!ab8500_fg_inst_curr_done(di->fg));
+	batctrl /= i;
+
+	ret = ab8500_fg_inst_curr_finalize(di->fg, &inst_curr);
+	if (ret) {
+		dev_err(di->dev, "Failed to finalize current measurement\n");
+		return ret;
+	}
+
+	res = ab8500_btemp_batctrl_volt_to_res(di, batctrl, inst_curr);
+
+	ret = ab8500_btemp_curr_source_enable(di, false);
+	if (ret) {
+		dev_err(di->dev, "%s curr source disable failed\n", __func__);
+		return ret;
+	}
+
+	dev_dbg(di->dev, "%s batctrl: %d res: %d inst_curr: %d samples: %d\n",
+		__func__, batctrl, res, inst_curr, i);
+
+	return res;
+}
+
+/**
+ * ab8500_btemp_res_to_temp() - resistance to temperature
+ * @di:		pointer to the ab8500_btemp structure
+ * @tbl:	pointer to the resiatance to temperature table
+ * @tbl_size:	size of the resistance to temperature table
+ * @res:	resistance to calculate the temperature from
+ *
+ * This function returns the battery temperature in degrees Celcius
+ * based on the NTC resistance.
+ */
+static int ab8500_btemp_res_to_temp(struct ab8500_btemp *di,
+	const struct abx500_res_to_temp *tbl, int tbl_size, int res)
+{
+	int i, temp;
+	/*
+	 * Calculate the formula for the straight line
+	 * Simple interpolation if we are within
+	 * the resistance table limits, extrapolate
+	 * if resistance is outside the limits.
+	 */
+	if (res > tbl[0].resist)
+		i = 0;
+	else if (res <= tbl[tbl_size - 1].resist)
+		i = tbl_size - 2;
+	else {
+		i = 0;
+		while (!(res <= tbl[i].resist &&
+			res > tbl[i + 1].resist))
+			i++;
+	}
+
+	temp = tbl[i].temp + ((tbl[i + 1].temp - tbl[i].temp) *
+		(res - tbl[i].resist)) / (tbl[i + 1].resist - tbl[i].resist);
+	return temp;
+}
+
+/**
+ * ab8500_btemp_measure_temp() - measure battery temperature
+ * @di:		pointer to the ab8500_btemp structure
+ *
+ * Returns battery temperature (on success) else the previous temperature
+ */
+static int ab8500_btemp_measure_temp(struct ab8500_btemp *di)
+{
+	int temp;
+	static int prev;
+	int rbat, rntc, vntc;
+	u8 id;
+
+	id = di->bat->batt_id;
+
+	if (di->bat->adc_therm == ABx500_ADC_THERM_BATCTRL &&
+			id != BATTERY_UNKNOWN) {
+
+		rbat = ab8500_btemp_get_batctrl_res(di);
+		if (rbat < 0) {
+			dev_err(di->dev, "%s get batctrl res failed\n",
+				__func__);
+			/*
+			 * Return out-of-range temperature so that
+			 * charging is stopped
+			 */
+			return BTEMP_THERMAL_LOW_LIMIT;
+		}
+
+		temp = ab8500_btemp_res_to_temp(di,
+			di->bat->bat_type[id].r_to_t_tbl,
+			di->bat->bat_type[id].n_temp_tbl_elements, rbat);
+	} else {
+		vntc = ab8500_gpadc_convert(di->gpadc, BTEMP_BALL);
+		if (vntc < 0) {
+			dev_err(di->dev,
+				"%s gpadc conversion failed,"
+				" using previous value\n", __func__);
+			return prev;
+		}
+		/*
+		 * The PCB NTC is sourced from VTVOUT via a 230kOhm
+		 * resistor.
+		 */
+		rntc = 230000 * vntc / (VTVOUT_V - vntc);
+
+		temp = ab8500_btemp_res_to_temp(di,
+			di->bat->bat_type[id].r_to_t_tbl,
+			di->bat->bat_type[id].n_temp_tbl_elements, rntc);
+		prev = temp;
+	}
+	dev_dbg(di->dev, "Battery temperature is %d\n", temp);
+	return temp;
+}
+
+/**
+ * ab8500_btemp_id() - Identify the connected battery
+ * @di:		pointer to the ab8500_btemp structure
+ *
+ * This function will try to identify the battery by reading the ID
+ * resistor. Some brands use a combined ID resistor with a NTC resistor to
+ * both be able to identify and to read the temperature of it.
+ */
+static int ab8500_btemp_id(struct ab8500_btemp *di)
+{
+	int res;
+	u8 i;
+
+	di->curr_source = BTEMP_BATCTRL_CURR_SRC_7UA;
+	di->bat->batt_id = BATTERY_UNKNOWN;
+
+	res =  ab8500_btemp_get_batctrl_res(di);
+	if (res < 0) {
+		dev_err(di->dev, "%s get batctrl res failed\n", __func__);
+		return -ENXIO;
+	}
+
+	/* BATTERY_UNKNOWN is defined on position 0, skip it! */
+	for (i = BATTERY_UNKNOWN + 1; i < di->bat->n_btypes; i++) {
+		if ((res <= di->bat->bat_type[i].resis_high) &&
+			(res >= di->bat->bat_type[i].resis_low)) {
+			dev_dbg(di->dev, "Battery detected on %s"
+				" low %d < res %d < high: %d"
+				" index: %d\n",
+				di->bat->adc_therm == ABx500_ADC_THERM_BATCTRL ?
+				"BATCTRL" : "BATTEMP",
+				di->bat->bat_type[i].resis_low, res,
+				di->bat->bat_type[i].resis_high, i);
+
+			di->bat->batt_id = i;
+			break;
+		}
+	}
+
+	if (di->bat->batt_id == BATTERY_UNKNOWN) {
+		dev_warn(di->dev, "Battery identified as unknown"
+			", resistance %d Ohm\n", res);
+		return -ENXIO;
+	}
+
+	/*
+	 * We only have to change current source if the
+	 * detected type is Type 1, else we use the 7uA source
+	 */
+	if (di->bat->adc_therm == ABx500_ADC_THERM_BATCTRL &&
+			di->bat->batt_id == 1) {
+		dev_dbg(di->dev, "Set BATCTRL current source to 20uA\n");
+		di->curr_source = BTEMP_BATCTRL_CURR_SRC_20UA;
+	}
+
+	return di->bat->batt_id;
+}
+
+/**
+ * ab8500_btemp_periodic_work() - Measuring the temperature periodically
+ * @work:	pointer to the work_struct structure
+ *
+ * Work function for measuring the temperature periodically
+ */
+static void ab8500_btemp_periodic_work(struct work_struct *work)
+{
+	int interval;
+	struct ab8500_btemp *di = container_of(work,
+		struct ab8500_btemp, btemp_periodic_work.work);
+
+	di->bat_temp = ab8500_btemp_measure_temp(di);
+
+	if (di->bat_temp != di->prev_bat_temp) {
+		di->prev_bat_temp = di->bat_temp;
+		power_supply_changed(&di->btemp_psy);
+	}
+
+	if (di->events.ac_conn || di->events.usb_conn)
+		interval = di->bat->temp_interval_chg;
+	else
+		interval = di->bat->temp_interval_nochg;
+
+	/* Schedule a new measurement */
+	queue_delayed_work(di->btemp_wq,
+		&di->btemp_periodic_work,
+		round_jiffies(interval * HZ));
+}
+
+/**
+ * ab8500_btemp_batctrlindb_handler() - battery removal detected
+ * @irq:       interrupt number
+ * @_di:       void pointer that has to address of ab8500_btemp
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_btemp_batctrlindb_handler(int irq, void *_di)
+{
+	struct ab8500_btemp *di = _di;
+	dev_err(di->dev, "Battery removal detected!\n");
+
+	di->events.batt_rem = true;
+	power_supply_changed(&di->btemp_psy);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_btemp_templow_handler() - battery temp lower than 10 degrees
+ * @irq:       interrupt number
+ * @_di:       void pointer that has to address of ab8500_btemp
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_btemp_templow_handler(int irq, void *_di)
+{
+	struct ab8500_btemp *di = _di;
+
+	if (is_ab8500_2p0_or_earlier(di->parent)) {
+		dev_dbg(di->dev, "Ignore false btemp low irq"
+			" for ABB cut 1.0, 1.1 and 2.0\n");
+	} else {
+		dev_crit(di->dev, "Battery temperature lower than -10deg c\n");
+
+		di->events.btemp_low = true;
+		di->events.btemp_high = false;
+		di->events.btemp_medhigh = false;
+		di->events.btemp_lowmed = false;
+		power_supply_changed(&di->btemp_psy);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_btemp_temphigh_handler() - battery temp higher than max temp
+ * @irq:       interrupt number
+ * @_di:       void pointer that has to address of ab8500_btemp
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_btemp_temphigh_handler(int irq, void *_di)
+{
+	struct ab8500_btemp *di = _di;
+
+	dev_crit(di->dev, "Battery temperature is higher than MAX temp\n");
+
+	di->events.btemp_high = true;
+	di->events.btemp_medhigh = false;
+	di->events.btemp_lowmed = false;
+	di->events.btemp_low = false;
+	power_supply_changed(&di->btemp_psy);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_btemp_lowmed_handler() - battery temp between low and medium
+ * @irq:       interrupt number
+ * @_di:       void pointer that has to address of ab8500_btemp
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_btemp_lowmed_handler(int irq, void *_di)
+{
+	struct ab8500_btemp *di = _di;
+
+	dev_dbg(di->dev, "Battery temperature is between low and medium\n");
+
+	di->events.btemp_lowmed = true;
+	di->events.btemp_medhigh = false;
+	di->events.btemp_high = false;
+	di->events.btemp_low = false;
+	power_supply_changed(&di->btemp_psy);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_btemp_medhigh_handler() - battery temp between medium and high
+ * @irq:       interrupt number
+ * @_di:       void pointer that has to address of ab8500_btemp
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_btemp_medhigh_handler(int irq, void *_di)
+{
+	struct ab8500_btemp *di = _di;
+
+	dev_dbg(di->dev, "Battery temperature is between medium and high\n");
+
+	di->events.btemp_medhigh = true;
+	di->events.btemp_lowmed = false;
+	di->events.btemp_high = false;
+	di->events.btemp_low = false;
+	power_supply_changed(&di->btemp_psy);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_btemp_periodic() - Periodic temperature measurements
+ * @di:		pointer to the ab8500_btemp structure
+ * @enable:	enable or disable periodic temperature measurements
+ *
+ * Starts of stops periodic temperature measurements. Periodic measurements
+ * should only be done when a charger is connected.
+ */
+static void ab8500_btemp_periodic(struct ab8500_btemp *di,
+	bool enable)
+{
+	dev_dbg(di->dev, "Enable periodic temperature measurements: %d\n",
+		enable);
+	/*
+	 * Make sure a new measurement is done directly by cancelling
+	 * any pending work
+	 */
+	cancel_delayed_work_sync(&di->btemp_periodic_work);
+
+	if (enable)
+		queue_delayed_work(di->btemp_wq, &di->btemp_periodic_work, 0);
+}
+
+/**
+ * ab8500_btemp_get_temp() - get battery temperature
+ * @di:		pointer to the ab8500_btemp structure
+ *
+ * Returns battery temperature
+ */
+static int ab8500_btemp_get_temp(struct ab8500_btemp *di)
+{
+	int temp = 0;
+
+	/*
+	 * The BTEMP events are not reliabe on AB8500 cut2.0
+	 * and prior versions
+	 */
+	if (is_ab8500_2p0_or_earlier(di->parent)) {
+		temp = di->bat_temp * 10;
+	} else {
+		if (di->events.btemp_low) {
+			if (temp > di->btemp_ranges.btemp_low_limit)
+				temp = di->btemp_ranges.btemp_low_limit;
+			else
+				temp = di->bat_temp * 10;
+		} else if (di->events.btemp_high) {
+			if (temp < di->btemp_ranges.btemp_high_limit)
+				temp = di->btemp_ranges.btemp_high_limit;
+			else
+				temp = di->bat_temp * 10;
+		} else if (di->events.btemp_lowmed) {
+			if (temp > di->btemp_ranges.btemp_med_limit)
+				temp = di->btemp_ranges.btemp_med_limit;
+			else
+				temp = di->bat_temp * 10;
+		} else if (di->events.btemp_medhigh) {
+			if (temp < di->btemp_ranges.btemp_med_limit)
+				temp = di->btemp_ranges.btemp_med_limit;
+			else
+				temp = di->bat_temp * 10;
+		} else
+			temp = di->bat_temp * 10;
+	}
+	return temp;
+}
+
+/**
+ * ab8500_btemp_get_batctrl_temp() - get the temperature
+ * @btemp:      pointer to the btemp structure
+ *
+ * Returns the batctrl temperature in millidegrees
+ */
+int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp)
+{
+	return btemp->bat_temp * 1000;
+}
+
+/**
+ * ab8500_btemp_get_property() - get the btemp properties
+ * @psy:        pointer to the power_supply structure
+ * @psp:        pointer to the power_supply_property structure
+ * @val:        pointer to the power_supply_propval union
+ *
+ * This function gets called when an application tries to get the btemp
+ * properties by reading the sysfs files.
+ * online:	presence of the battery
+ * present:	presence of the battery
+ * technology:	battery technology
+ * temp:	battery temperature
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_btemp_get_property(struct power_supply *psy,
+	enum power_supply_property psp,
+	union power_supply_propval *val)
+{
+	struct ab8500_btemp *di;
+
+	di = to_ab8500_btemp_device_info(psy);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_PRESENT:
+	case POWER_SUPPLY_PROP_ONLINE:
+		if (di->events.batt_rem)
+			val->intval = 0;
+		else
+			val->intval = 1;
+		break;
+	case POWER_SUPPLY_PROP_TECHNOLOGY:
+		val->intval = di->bat->bat_type[di->bat->batt_id].name;
+		break;
+	case POWER_SUPPLY_PROP_TEMP:
+		val->intval = ab8500_btemp_get_temp(di);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data)
+{
+	struct power_supply *psy;
+	struct power_supply *ext;
+	struct ab8500_btemp *di;
+	union power_supply_propval ret;
+	int i, j;
+	bool psy_found = false;
+
+	psy = (struct power_supply *)data;
+	ext = dev_get_drvdata(dev);
+	di = to_ab8500_btemp_device_info(psy);
+
+	/*
+	 * For all psy where the name of your driver
+	 * appears in any supplied_to
+	 */
+	for (i = 0; i < ext->num_supplicants; i++) {
+		if (!strcmp(ext->supplied_to[i], psy->name))
+			psy_found = true;
+	}
+
+	if (!psy_found)
+		return 0;
+
+	/* Go through all properties for the psy */
+	for (j = 0; j < ext->num_properties; j++) {
+		enum power_supply_property prop;
+		prop = ext->properties[j];
+
+		if (ext->get_property(ext, prop, &ret))
+			continue;
+
+		switch (prop) {
+		case POWER_SUPPLY_PROP_PRESENT:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_MAINS:
+				/* AC disconnected */
+				if (!ret.intval && di->events.ac_conn) {
+					di->events.ac_conn = false;
+				}
+				/* AC connected */
+				else if (ret.intval && !di->events.ac_conn) {
+					di->events.ac_conn = true;
+					if (!di->events.usb_conn)
+						ab8500_btemp_periodic(di, true);
+				}
+				break;
+			case POWER_SUPPLY_TYPE_USB:
+				/* USB disconnected */
+				if (!ret.intval && di->events.usb_conn) {
+					di->events.usb_conn = false;
+				}
+				/* USB connected */
+				else if (ret.intval && !di->events.usb_conn) {
+					di->events.usb_conn = true;
+					if (!di->events.ac_conn)
+						ab8500_btemp_periodic(di, true);
+				}
+				break;
+			default:
+				break;
+			}
+			break;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+/**
+ * ab8500_btemp_external_power_changed() - callback for power supply changes
+ * @psy:       pointer to the structure power_supply
+ *
+ * This function is pointing to the function pointer external_power_changed
+ * of the structure power_supply.
+ * This function gets executed when there is a change in the external power
+ * supply to the btemp.
+ */
+static void ab8500_btemp_external_power_changed(struct power_supply *psy)
+{
+	struct ab8500_btemp *di = to_ab8500_btemp_device_info(psy);
+
+	class_for_each_device(power_supply_class, NULL,
+		&di->btemp_psy, ab8500_btemp_get_ext_psy_data);
+}
+
+/* ab8500 btemp driver interrupts and their respective isr */
+static struct ab8500_btemp_interrupts ab8500_btemp_irq[] = {
+	{"BAT_CTRL_INDB", ab8500_btemp_batctrlindb_handler},
+	{"BTEMP_LOW", ab8500_btemp_templow_handler},
+	{"BTEMP_HIGH", ab8500_btemp_temphigh_handler},
+	{"BTEMP_LOW_MEDIUM", ab8500_btemp_lowmed_handler},
+	{"BTEMP_MEDIUM_HIGH", ab8500_btemp_medhigh_handler},
+};
+
+#if defined(CONFIG_PM)
+static int ab8500_btemp_resume(struct platform_device *pdev)
+{
+	struct ab8500_btemp *di = platform_get_drvdata(pdev);
+
+	ab8500_btemp_periodic(di, true);
+
+	return 0;
+}
+
+static int ab8500_btemp_suspend(struct platform_device *pdev,
+	pm_message_t state)
+{
+	struct ab8500_btemp *di = platform_get_drvdata(pdev);
+
+	ab8500_btemp_periodic(di, false);
+
+	return 0;
+}
+#else
+#define ab8500_btemp_suspend      NULL
+#define ab8500_btemp_resume       NULL
+#endif
+
+static int __devexit ab8500_btemp_remove(struct platform_device *pdev)
+{
+	struct ab8500_btemp *di = platform_get_drvdata(pdev);
+	int i, irq;
+
+	/* Disable interrupts */
+	for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
+		irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
+		free_irq(irq, di);
+	}
+
+	/* Delete the work queue */
+	destroy_workqueue(di->btemp_wq);
+
+	flush_scheduled_work();
+	power_supply_unregister(&di->btemp_psy);
+	platform_set_drvdata(pdev, NULL);
+	kfree(di);
+
+	return 0;
+}
+
+static int __devinit ab8500_btemp_probe(struct platform_device *pdev)
+{
+	int irq, i, ret = 0;
+	u8 val;
+	struct abx500_bm_plat_data *plat_data;
+
+	struct ab8500_btemp *di =
+		kzalloc(sizeof(struct ab8500_btemp), GFP_KERNEL);
+	if (!di)
+		return -ENOMEM;
+
+	/* get parent data */
+	di->dev = &pdev->dev;
+	di->parent = dev_get_drvdata(pdev->dev.parent);
+	di->gpadc = ab8500_gpadc_get("ab8500-gpadc.0");
+
+	/* get btemp specific platform data */
+	plat_data = pdev->dev.platform_data;
+	di->pdata = plat_data->btemp;
+	if (!di->pdata) {
+		dev_err(di->dev, "no btemp platform data supplied\n");
+		ret = -EINVAL;
+		goto free_device_info;
+	}
+
+	/* get battery specific platform data */
+	di->bat = plat_data->battery;
+	if (!di->bat) {
+		dev_err(di->dev, "no battery platform data supplied\n");
+		ret = -EINVAL;
+		goto free_device_info;
+	}
+
+	/* BTEMP supply */
+	di->btemp_psy.name = "ab8500_btemp";
+	di->btemp_psy.type = POWER_SUPPLY_TYPE_BATTERY;
+	di->btemp_psy.properties = ab8500_btemp_props;
+	di->btemp_psy.num_properties = ARRAY_SIZE(ab8500_btemp_props);
+	di->btemp_psy.get_property = ab8500_btemp_get_property;
+	di->btemp_psy.supplied_to = di->pdata->supplied_to;
+	di->btemp_psy.num_supplicants = di->pdata->num_supplicants;
+	di->btemp_psy.external_power_changed =
+		ab8500_btemp_external_power_changed;
+
+
+	/* Create a work queue for the btemp */
+	di->btemp_wq =
+		create_singlethread_workqueue("ab8500_btemp_wq");
+	if (di->btemp_wq == NULL) {
+		dev_err(di->dev, "failed to create work queue\n");
+		goto free_device_info;
+	}
+
+	/* Init work for measuring temperature periodically */
+	INIT_DELAYED_WORK_DEFERRABLE(&di->btemp_periodic_work,
+		ab8500_btemp_periodic_work);
+
+	/* Identify the battery */
+	if (ab8500_btemp_id(di) < 0)
+		dev_warn(di->dev, "failed to identify the battery\n");
+
+	/* Set BTEMP thermal limits. Low and Med are fixed */
+	di->btemp_ranges.btemp_low_limit = BTEMP_THERMAL_LOW_LIMIT;
+	di->btemp_ranges.btemp_med_limit = BTEMP_THERMAL_MED_LIMIT;
+
+	ret = abx500_get_register_interruptible(di->dev, AB8500_CHARGER,
+		AB8500_BTEMP_HIGH_TH, &val);
+	if (ret < 0) {
+		dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+		goto free_btemp_wq;
+	}
+	switch (val) {
+	case BTEMP_HIGH_TH_57_0:
+	case BTEMP_HIGH_TH_57_1:
+		di->btemp_ranges.btemp_high_limit =
+			BTEMP_THERMAL_HIGH_LIMIT_57;
+		break;
+	case BTEMP_HIGH_TH_52:
+		di->btemp_ranges.btemp_high_limit =
+			BTEMP_THERMAL_HIGH_LIMIT_52;
+		break;
+	case BTEMP_HIGH_TH_62:
+		di->btemp_ranges.btemp_high_limit =
+			BTEMP_THERMAL_HIGH_LIMIT_62;
+		break;
+	}
+
+	/* Register BTEMP power supply class */
+	ret = power_supply_register(di->dev, &di->btemp_psy);
+	if (ret) {
+		dev_err(di->dev, "failed to register BTEMP psy\n");
+		goto free_btemp_wq;
+	}
+
+	/* Register interrupts */
+	for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
+		irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
+		ret = request_threaded_irq(irq, NULL, ab8500_btemp_irq[i].isr,
+			IRQF_SHARED | IRQF_NO_SUSPEND,
+			ab8500_btemp_irq[i].name, di);
+
+		if (ret) {
+			dev_err(di->dev, "failed to request %s IRQ %d: %d\n"
+				, ab8500_btemp_irq[i].name, irq, ret);
+			goto free_irq;
+		}
+		dev_dbg(di->dev, "Requested %s IRQ %d: %d\n",
+			ab8500_btemp_irq[i].name, irq, ret);
+	}
+
+	platform_set_drvdata(pdev, di);
+
+	/* Kick off periodic temperature measurements */
+	ab8500_btemp_periodic(di, true);
+	list_add_tail(&di->node, &ab8500_btemp_list);
+
+	return ret;
+
+free_irq:
+	power_supply_unregister(&di->btemp_psy);
+
+	/* We also have to free all successfully registered irqs */
+	for (i = i - 1; i >= 0; i--) {
+		irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
+		free_irq(irq, di);
+	}
+free_btemp_wq:
+	destroy_workqueue(di->btemp_wq);
+free_device_info:
+	kfree(di);
+
+	return ret;
+}
+
+static struct platform_driver ab8500_btemp_driver = {
+	.probe = ab8500_btemp_probe,
+	.remove = __devexit_p(ab8500_btemp_remove),
+	.suspend = ab8500_btemp_suspend,
+	.resume = ab8500_btemp_resume,
+	.driver = {
+		.name = "ab8500-btemp",
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init ab8500_btemp_init(void)
+{
+	return platform_driver_register(&ab8500_btemp_driver);
+}
+
+static void __exit ab8500_btemp_exit(void)
+{
+	platform_driver_unregister(&ab8500_btemp_driver);
+}
+
+subsys_initcall_sync(ab8500_btemp_init);
+module_exit(ab8500_btemp_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Johan Palsson, Karl Komierowski, Arun R Murthy");
+MODULE_ALIAS("platform:ab8500-btemp");
+MODULE_DESCRIPTION("AB8500 battery temperature driver");
diff --git a/drivers/power/ab8500_charger.c b/drivers/power/ab8500_charger.c
new file mode 100644
index 000000000000..e2b4accbec88
--- /dev/null
+++ b/drivers/power/ab8500_charger.c
@@ -0,0 +1,2789 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2012
+ *
+ * Charger driver for AB8500
+ *
+ * License Terms: GNU General Public License v2
+ * Author:
+ *	Johan Palsson <johan.palsson@stericsson.com>
+ *	Karl Komierowski <karl.komierowski@stericsson.com>
+ *	Arun R Murthy <arun.murthy@stericsson.com>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/completion.h>
+#include <linux/regulator/consumer.h>
+#include <linux/err.h>
+#include <linux/workqueue.h>
+#include <linux/kobject.h>
+#include <linux/mfd/abx500/ab8500.h>
+#include <linux/mfd/abx500.h>
+#include <linux/mfd/abx500/ab8500-bm.h>
+#include <linux/mfd/abx500/ab8500-gpadc.h>
+#include <linux/mfd/abx500/ux500_chargalg.h>
+#include <linux/usb/otg.h>
+
+/* Charger constants */
+#define NO_PW_CONN			0
+#define AC_PW_CONN			1
+#define USB_PW_CONN			2
+
+#define MAIN_WDOG_ENA			0x01
+#define MAIN_WDOG_KICK			0x02
+#define MAIN_WDOG_DIS			0x00
+#define CHARG_WD_KICK			0x01
+#define MAIN_CH_ENA			0x01
+#define MAIN_CH_NO_OVERSHOOT_ENA_N	0x02
+#define USB_CH_ENA			0x01
+#define USB_CHG_NO_OVERSHOOT_ENA_N	0x02
+#define MAIN_CH_DET			0x01
+#define MAIN_CH_CV_ON			0x04
+#define USB_CH_CV_ON			0x08
+#define VBUS_DET_DBNC100		0x02
+#define VBUS_DET_DBNC1			0x01
+#define OTP_ENABLE_WD			0x01
+
+#define MAIN_CH_INPUT_CURR_SHIFT	4
+#define VBUS_IN_CURR_LIM_SHIFT		4
+
+#define LED_INDICATOR_PWM_ENA		0x01
+#define LED_INDICATOR_PWM_DIS		0x00
+#define LED_IND_CUR_5MA			0x04
+#define LED_INDICATOR_PWM_DUTY_252_256	0xBF
+
+/* HW failure constants */
+#define MAIN_CH_TH_PROT			0x02
+#define VBUS_CH_NOK			0x08
+#define USB_CH_TH_PROT			0x02
+#define VBUS_OVV_TH			0x01
+#define MAIN_CH_NOK			0x01
+#define VBUS_DET			0x80
+
+/* UsbLineStatus register bit masks */
+#define AB8500_USB_LINK_STATUS		0x78
+#define AB8500_STD_HOST_SUSP		0x18
+
+/* Watchdog timeout constant */
+#define WD_TIMER			0x30 /* 4min */
+#define WD_KICK_INTERVAL		(60 * HZ)
+
+/* Lowest charger voltage is 3.39V -> 0x4E */
+#define LOW_VOLT_REG			0x4E
+
+/* UsbLineStatus register - usb types */
+enum ab8500_charger_link_status {
+	USB_STAT_NOT_CONFIGURED,
+	USB_STAT_STD_HOST_NC,
+	USB_STAT_STD_HOST_C_NS,
+	USB_STAT_STD_HOST_C_S,
+	USB_STAT_HOST_CHG_NM,
+	USB_STAT_HOST_CHG_HS,
+	USB_STAT_HOST_CHG_HS_CHIRP,
+	USB_STAT_DEDICATED_CHG,
+	USB_STAT_ACA_RID_A,
+	USB_STAT_ACA_RID_B,
+	USB_STAT_ACA_RID_C_NM,
+	USB_STAT_ACA_RID_C_HS,
+	USB_STAT_ACA_RID_C_HS_CHIRP,
+	USB_STAT_HM_IDGND,
+	USB_STAT_RESERVED,
+	USB_STAT_NOT_VALID_LINK,
+};
+
+enum ab8500_usb_state {
+	AB8500_BM_USB_STATE_RESET_HS,	/* HighSpeed Reset */
+	AB8500_BM_USB_STATE_RESET_FS,	/* FullSpeed/LowSpeed Reset */
+	AB8500_BM_USB_STATE_CONFIGURED,
+	AB8500_BM_USB_STATE_SUSPEND,
+	AB8500_BM_USB_STATE_RESUME,
+	AB8500_BM_USB_STATE_MAX,
+};
+
+/* VBUS input current limits supported in AB8500 in mA */
+#define USB_CH_IP_CUR_LVL_0P05		50
+#define USB_CH_IP_CUR_LVL_0P09		98
+#define USB_CH_IP_CUR_LVL_0P19		193
+#define USB_CH_IP_CUR_LVL_0P29		290
+#define USB_CH_IP_CUR_LVL_0P38		380
+#define USB_CH_IP_CUR_LVL_0P45		450
+#define USB_CH_IP_CUR_LVL_0P5		500
+#define USB_CH_IP_CUR_LVL_0P6		600
+#define USB_CH_IP_CUR_LVL_0P7		700
+#define USB_CH_IP_CUR_LVL_0P8		800
+#define USB_CH_IP_CUR_LVL_0P9		900
+#define USB_CH_IP_CUR_LVL_1P0		1000
+#define USB_CH_IP_CUR_LVL_1P1		1100
+#define USB_CH_IP_CUR_LVL_1P3		1300
+#define USB_CH_IP_CUR_LVL_1P4		1400
+#define USB_CH_IP_CUR_LVL_1P5		1500
+
+#define VBAT_TRESH_IP_CUR_RED		3800
+
+#define to_ab8500_charger_usb_device_info(x) container_of((x), \
+	struct ab8500_charger, usb_chg)
+#define to_ab8500_charger_ac_device_info(x) container_of((x), \
+	struct ab8500_charger, ac_chg)
+
+/**
+ * struct ab8500_charger_interrupts - ab8500 interupts
+ * @name:	name of the interrupt
+ * @isr		function pointer to the isr
+ */
+struct ab8500_charger_interrupts {
+	char *name;
+	irqreturn_t (*isr)(int irq, void *data);
+};
+
+struct ab8500_charger_info {
+	int charger_connected;
+	int charger_online;
+	int charger_voltage;
+	int cv_active;
+	bool wd_expired;
+};
+
+struct ab8500_charger_event_flags {
+	bool mainextchnotok;
+	bool main_thermal_prot;
+	bool usb_thermal_prot;
+	bool vbus_ovv;
+	bool usbchargernotok;
+	bool chgwdexp;
+	bool vbus_collapse;
+};
+
+struct ab8500_charger_usb_state {
+	bool usb_changed;
+	int usb_current;
+	enum ab8500_usb_state state;
+	spinlock_t usb_lock;
+};
+
+/**
+ * struct ab8500_charger - ab8500 Charger device information
+ * @dev:		Pointer to the structure device
+ * @max_usb_in_curr:	Max USB charger input current
+ * @vbus_detected:	VBUS detected
+ * @vbus_detected_start:
+ *			VBUS detected during startup
+ * @ac_conn:		This will be true when the AC charger has been plugged
+ * @vddadc_en_ac:	Indicate if VDD ADC supply is enabled because AC
+ *			charger is enabled
+ * @vddadc_en_usb:	Indicate if VDD ADC supply is enabled because USB
+ *			charger is enabled
+ * @vbat		Battery voltage
+ * @old_vbat		Previously measured battery voltage
+ * @autopower		Indicate if we should have automatic pwron after pwrloss
+ * @parent:		Pointer to the struct ab8500
+ * @gpadc:		Pointer to the struct gpadc
+ * @pdata:		Pointer to the abx500_charger platform data
+ * @bat:		Pointer to the abx500_bm platform data
+ * @flags:		Structure for information about events triggered
+ * @usb_state:		Structure for usb stack information
+ * @ac_chg:		AC charger power supply
+ * @usb_chg:		USB charger power supply
+ * @ac:			Structure that holds the AC charger properties
+ * @usb:		Structure that holds the USB charger properties
+ * @regu:		Pointer to the struct regulator
+ * @charger_wq:		Work queue for the IRQs and checking HW state
+ * @check_vbat_work	Work for checking vbat threshold to adjust vbus current
+ * @check_hw_failure_work:	Work for checking HW state
+ * @check_usbchgnotok_work:	Work for checking USB charger not ok status
+ * @kick_wd_work:		Work for kicking the charger watchdog in case
+ *				of ABB rev 1.* due to the watchog logic bug
+ * @ac_work:			Work for checking AC charger connection
+ * @detect_usb_type_work:	Work for detecting the USB type connected
+ * @usb_link_status_work:	Work for checking the new USB link status
+ * @usb_state_changed_work:	Work for checking USB state
+ * @check_main_thermal_prot_work:
+ *				Work for checking Main thermal status
+ * @check_usb_thermal_prot_work:
+ *				Work for checking USB thermal status
+ */
+struct ab8500_charger {
+	struct device *dev;
+	int max_usb_in_curr;
+	bool vbus_detected;
+	bool vbus_detected_start;
+	bool ac_conn;
+	bool vddadc_en_ac;
+	bool vddadc_en_usb;
+	int vbat;
+	int old_vbat;
+	bool autopower;
+	struct ab8500 *parent;
+	struct ab8500_gpadc *gpadc;
+	struct abx500_charger_platform_data *pdata;
+	struct abx500_bm_data *bat;
+	struct ab8500_charger_event_flags flags;
+	struct ab8500_charger_usb_state usb_state;
+	struct ux500_charger ac_chg;
+	struct ux500_charger usb_chg;
+	struct ab8500_charger_info ac;
+	struct ab8500_charger_info usb;
+	struct regulator *regu;
+	struct workqueue_struct *charger_wq;
+	struct delayed_work check_vbat_work;
+	struct delayed_work check_hw_failure_work;
+	struct delayed_work check_usbchgnotok_work;
+	struct delayed_work kick_wd_work;
+	struct work_struct ac_work;
+	struct work_struct detect_usb_type_work;
+	struct work_struct usb_link_status_work;
+	struct work_struct usb_state_changed_work;
+	struct work_struct check_main_thermal_prot_work;
+	struct work_struct check_usb_thermal_prot_work;
+	struct usb_phy *usb_phy;
+	struct notifier_block nb;
+};
+
+/* AC properties */
+static enum power_supply_property ab8500_charger_ac_props[] = {
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_VOLTAGE_AVG,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+};
+
+/* USB properties */
+static enum power_supply_property ab8500_charger_usb_props[] = {
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_CURRENT_AVG,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_VOLTAGE_AVG,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+};
+
+/**
+ * ab8500_power_loss_handling - set how we handle powerloss.
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Magic nummbers are from STE HW department.
+ */
+static void ab8500_power_loss_handling(struct ab8500_charger *di)
+{
+	u8 reg;
+	int ret;
+
+	dev_dbg(di->dev, "Autopower : %d\n", di->autopower);
+
+	/* read the autopower register */
+	ret = abx500_get_register_interruptible(di->dev, 0x15, 0x00, &reg);
+	if (ret) {
+		dev_err(di->dev, "%d write failed\n", __LINE__);
+		return;
+	}
+
+	/* enable the OPT emulation registers */
+	ret = abx500_set_register_interruptible(di->dev, 0x11, 0x00, 0x2);
+	if (ret) {
+		dev_err(di->dev, "%d write failed\n", __LINE__);
+		return;
+	}
+
+	if (di->autopower)
+		reg |= 0x8;
+	else
+		reg &= ~0x8;
+
+	/* write back the changed value to autopower reg */
+	ret = abx500_set_register_interruptible(di->dev, 0x15, 0x00, reg);
+	if (ret) {
+		dev_err(di->dev, "%d write failed\n", __LINE__);
+		return;
+	}
+
+	/* disable the set OTP registers again */
+	ret = abx500_set_register_interruptible(di->dev, 0x11, 0x00, 0x0);
+	if (ret) {
+		dev_err(di->dev, "%d write failed\n", __LINE__);
+		return;
+	}
+}
+
+/**
+ * ab8500_power_supply_changed - a wrapper with local extentions for
+ * power_supply_changed
+ * @di:	  pointer to the ab8500_charger structure
+ * @psy:  pointer to power_supply_that have changed.
+ *
+ */
+static void ab8500_power_supply_changed(struct ab8500_charger *di,
+					struct power_supply *psy)
+{
+	if (di->pdata->autopower_cfg) {
+		if (!di->usb.charger_connected &&
+		    !di->ac.charger_connected &&
+		    di->autopower) {
+			di->autopower = false;
+			ab8500_power_loss_handling(di);
+		} else if (!di->autopower &&
+			   (di->ac.charger_connected ||
+			    di->usb.charger_connected)) {
+			di->autopower = true;
+			ab8500_power_loss_handling(di);
+		}
+	}
+	power_supply_changed(psy);
+}
+
+static void ab8500_charger_set_usb_connected(struct ab8500_charger *di,
+	bool connected)
+{
+	if (connected != di->usb.charger_connected) {
+		dev_dbg(di->dev, "USB connected:%i\n", connected);
+		di->usb.charger_connected = connected;
+		sysfs_notify(&di->usb_chg.psy.dev->kobj, NULL, "present");
+	}
+}
+
+/**
+ * ab8500_charger_get_ac_voltage() - get ac charger voltage
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Returns ac charger voltage (on success)
+ */
+static int ab8500_charger_get_ac_voltage(struct ab8500_charger *di)
+{
+	int vch;
+
+	/* Only measure voltage if the charger is connected */
+	if (di->ac.charger_connected) {
+		vch = ab8500_gpadc_convert(di->gpadc, MAIN_CHARGER_V);
+		if (vch < 0)
+			dev_err(di->dev, "%s gpadc conv failed,\n", __func__);
+	} else {
+		vch = 0;
+	}
+	return vch;
+}
+
+/**
+ * ab8500_charger_ac_cv() - check if the main charger is in CV mode
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Returns ac charger CV mode (on success) else error code
+ */
+static int ab8500_charger_ac_cv(struct ab8500_charger *di)
+{
+	u8 val;
+	int ret = 0;
+
+	/* Only check CV mode if the charger is online */
+	if (di->ac.charger_online) {
+		ret = abx500_get_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_CH_STATUS1_REG, &val);
+		if (ret < 0) {
+			dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+			return 0;
+		}
+
+		if (val & MAIN_CH_CV_ON)
+			ret = 1;
+		else
+			ret = 0;
+	}
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_get_vbus_voltage() - get vbus voltage
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * This function returns the vbus voltage.
+ * Returns vbus voltage (on success)
+ */
+static int ab8500_charger_get_vbus_voltage(struct ab8500_charger *di)
+{
+	int vch;
+
+	/* Only measure voltage if the charger is connected */
+	if (di->usb.charger_connected) {
+		vch = ab8500_gpadc_convert(di->gpadc, VBUS_V);
+		if (vch < 0)
+			dev_err(di->dev, "%s gpadc conv failed\n", __func__);
+	} else {
+		vch = 0;
+	}
+	return vch;
+}
+
+/**
+ * ab8500_charger_get_usb_current() - get usb charger current
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * This function returns the usb charger current.
+ * Returns usb current (on success) and error code on failure
+ */
+static int ab8500_charger_get_usb_current(struct ab8500_charger *di)
+{
+	int ich;
+
+	/* Only measure current if the charger is online */
+	if (di->usb.charger_online) {
+		ich = ab8500_gpadc_convert(di->gpadc, USB_CHARGER_C);
+		if (ich < 0)
+			dev_err(di->dev, "%s gpadc conv failed\n", __func__);
+	} else {
+		ich = 0;
+	}
+	return ich;
+}
+
+/**
+ * ab8500_charger_get_ac_current() - get ac charger current
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * This function returns the ac charger current.
+ * Returns ac current (on success) and error code on failure.
+ */
+static int ab8500_charger_get_ac_current(struct ab8500_charger *di)
+{
+	int ich;
+
+	/* Only measure current if the charger is online */
+	if (di->ac.charger_online) {
+		ich = ab8500_gpadc_convert(di->gpadc, MAIN_CHARGER_C);
+		if (ich < 0)
+			dev_err(di->dev, "%s gpadc conv failed\n", __func__);
+	} else {
+		ich = 0;
+	}
+	return ich;
+}
+
+/**
+ * ab8500_charger_usb_cv() - check if the usb charger is in CV mode
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Returns ac charger CV mode (on success) else error code
+ */
+static int ab8500_charger_usb_cv(struct ab8500_charger *di)
+{
+	int ret;
+	u8 val;
+
+	/* Only check CV mode if the charger is online */
+	if (di->usb.charger_online) {
+		ret = abx500_get_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_CH_USBCH_STAT1_REG, &val);
+		if (ret < 0) {
+			dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+			return 0;
+		}
+
+		if (val & USB_CH_CV_ON)
+			ret = 1;
+		else
+			ret = 0;
+	} else {
+		ret = 0;
+	}
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_detect_chargers() - Detect the connected chargers
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Returns the type of charger connected.
+ * For USB it will not mean we can actually charge from it
+ * but that there is a USB cable connected that we have to
+ * identify. This is used during startup when we don't get
+ * interrupts of the charger detection
+ *
+ * Returns an integer value, that means,
+ * NO_PW_CONN  no power supply is connected
+ * AC_PW_CONN  if the AC power supply is connected
+ * USB_PW_CONN  if the USB power supply is connected
+ * AC_PW_CONN + USB_PW_CONN if USB and AC power supplies are both connected
+ */
+static int ab8500_charger_detect_chargers(struct ab8500_charger *di)
+{
+	int result = NO_PW_CONN;
+	int ret;
+	u8 val;
+
+	/* Check for AC charger */
+	ret = abx500_get_register_interruptible(di->dev, AB8500_CHARGER,
+		AB8500_CH_STATUS1_REG, &val);
+	if (ret < 0) {
+		dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+		return ret;
+	}
+
+	if (val & MAIN_CH_DET)
+		result = AC_PW_CONN;
+
+	/* Check for USB charger */
+	ret = abx500_get_register_interruptible(di->dev, AB8500_CHARGER,
+		AB8500_CH_USBCH_STAT1_REG, &val);
+	if (ret < 0) {
+		dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+		return ret;
+	}
+
+	if ((val & VBUS_DET_DBNC1) && (val & VBUS_DET_DBNC100))
+		result |= USB_PW_CONN;
+
+	return result;
+}
+
+/**
+ * ab8500_charger_max_usb_curr() - get the max curr for the USB type
+ * @di:			pointer to the ab8500_charger structure
+ * @link_status:	the identified USB type
+ *
+ * Get the maximum current that is allowed to be drawn from the host
+ * based on the USB type.
+ * Returns error code in case of failure else 0 on success
+ */
+static int ab8500_charger_max_usb_curr(struct ab8500_charger *di,
+	enum ab8500_charger_link_status link_status)
+{
+	int ret = 0;
+
+	switch (link_status) {
+	case USB_STAT_STD_HOST_NC:
+	case USB_STAT_STD_HOST_C_NS:
+	case USB_STAT_STD_HOST_C_S:
+		dev_dbg(di->dev, "USB Type - Standard host is "
+			"detected through USB driver\n");
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P09;
+		break;
+	case USB_STAT_HOST_CHG_HS_CHIRP:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P5;
+		break;
+	case USB_STAT_HOST_CHG_HS:
+	case USB_STAT_ACA_RID_C_HS:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P9;
+		break;
+	case USB_STAT_ACA_RID_A:
+		/*
+		 * Dedicated charger level minus maximum current accessory
+		 * can consume (300mA). Closest level is 1100mA
+		 */
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_1P1;
+		break;
+	case USB_STAT_ACA_RID_B:
+		/*
+		 * Dedicated charger level minus 120mA (20mA for ACA and
+		 * 100mA for potential accessory). Closest level is 1300mA
+		 */
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_1P3;
+		break;
+	case USB_STAT_DEDICATED_CHG:
+	case USB_STAT_HOST_CHG_NM:
+	case USB_STAT_ACA_RID_C_HS_CHIRP:
+	case USB_STAT_ACA_RID_C_NM:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_1P5;
+		break;
+	case USB_STAT_RESERVED:
+		/*
+		 * This state is used to indicate that VBUS has dropped below
+		 * the detection level 4 times in a row. This is due to the
+		 * charger output current is set to high making the charger
+		 * voltage collapse. This have to be propagated through to
+		 * chargalg. This is done using the property
+		 * POWER_SUPPLY_PROP_CURRENT_AVG = 1
+		 */
+		di->flags.vbus_collapse = true;
+		dev_dbg(di->dev, "USB Type - USB_STAT_RESERVED "
+			"VBUS has collapsed\n");
+		ret = -1;
+		break;
+	case USB_STAT_HM_IDGND:
+	case USB_STAT_NOT_CONFIGURED:
+	case USB_STAT_NOT_VALID_LINK:
+		dev_err(di->dev, "USB Type - Charging not allowed\n");
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P05;
+		ret = -ENXIO;
+		break;
+	default:
+		dev_err(di->dev, "USB Type - Unknown\n");
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P05;
+		ret = -ENXIO;
+		break;
+	};
+
+	dev_dbg(di->dev, "USB Type - 0x%02x MaxCurr: %d",
+		link_status, di->max_usb_in_curr);
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_read_usb_type() - read the type of usb connected
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Detect the type of the plugged USB
+ * Returns error code in case of failure else 0 on success
+ */
+static int ab8500_charger_read_usb_type(struct ab8500_charger *di)
+{
+	int ret;
+	u8 val;
+
+	ret = abx500_get_register_interruptible(di->dev,
+		AB8500_INTERRUPT, AB8500_IT_SOURCE21_REG, &val);
+	if (ret < 0) {
+		dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+		return ret;
+	}
+	ret = abx500_get_register_interruptible(di->dev, AB8500_USB,
+		AB8500_USB_LINE_STAT_REG, &val);
+	if (ret < 0) {
+		dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+		return ret;
+	}
+
+	/* get the USB type */
+	val = (val & AB8500_USB_LINK_STATUS) >> 3;
+	ret = ab8500_charger_max_usb_curr(di,
+		(enum ab8500_charger_link_status) val);
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_detect_usb_type() - get the type of usb connected
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Detect the type of the plugged USB
+ * Returns error code in case of failure else 0 on success
+ */
+static int ab8500_charger_detect_usb_type(struct ab8500_charger *di)
+{
+	int i, ret;
+	u8 val;
+
+	/*
+	 * On getting the VBUS rising edge detect interrupt there
+	 * is a 250ms delay after which the register UsbLineStatus
+	 * is filled with valid data.
+	 */
+	for (i = 0; i < 10; i++) {
+		msleep(250);
+		ret = abx500_get_register_interruptible(di->dev,
+			AB8500_INTERRUPT, AB8500_IT_SOURCE21_REG,
+			&val);
+		if (ret < 0) {
+			dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+			return ret;
+		}
+		ret = abx500_get_register_interruptible(di->dev, AB8500_USB,
+			AB8500_USB_LINE_STAT_REG, &val);
+		if (ret < 0) {
+			dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+			return ret;
+		}
+		/*
+		 * Until the IT source register is read the UsbLineStatus
+		 * register is not updated, hence doing the same
+		 * Revisit this:
+		 */
+
+		/* get the USB type */
+		val = (val & AB8500_USB_LINK_STATUS) >> 3;
+		if (val)
+			break;
+	}
+	ret = ab8500_charger_max_usb_curr(di,
+		(enum ab8500_charger_link_status) val);
+
+	return ret;
+}
+
+/*
+ * This array maps the raw hex value to charger voltage used by the AB8500
+ * Values taken from the UM0836
+ */
+static int ab8500_charger_voltage_map[] = {
+	3500 ,
+	3525 ,
+	3550 ,
+	3575 ,
+	3600 ,
+	3625 ,
+	3650 ,
+	3675 ,
+	3700 ,
+	3725 ,
+	3750 ,
+	3775 ,
+	3800 ,
+	3825 ,
+	3850 ,
+	3875 ,
+	3900 ,
+	3925 ,
+	3950 ,
+	3975 ,
+	4000 ,
+	4025 ,
+	4050 ,
+	4060 ,
+	4070 ,
+	4080 ,
+	4090 ,
+	4100 ,
+	4110 ,
+	4120 ,
+	4130 ,
+	4140 ,
+	4150 ,
+	4160 ,
+	4170 ,
+	4180 ,
+	4190 ,
+	4200 ,
+	4210 ,
+	4220 ,
+	4230 ,
+	4240 ,
+	4250 ,
+	4260 ,
+	4270 ,
+	4280 ,
+	4290 ,
+	4300 ,
+	4310 ,
+	4320 ,
+	4330 ,
+	4340 ,
+	4350 ,
+	4360 ,
+	4370 ,
+	4380 ,
+	4390 ,
+	4400 ,
+	4410 ,
+	4420 ,
+	4430 ,
+	4440 ,
+	4450 ,
+	4460 ,
+	4470 ,
+	4480 ,
+	4490 ,
+	4500 ,
+	4510 ,
+	4520 ,
+	4530 ,
+	4540 ,
+	4550 ,
+	4560 ,
+	4570 ,
+	4580 ,
+	4590 ,
+	4600 ,
+};
+
+/*
+ * This array maps the raw hex value to charger current used by the AB8500
+ * Values taken from the UM0836
+ */
+static int ab8500_charger_current_map[] = {
+	100 ,
+	200 ,
+	300 ,
+	400 ,
+	500 ,
+	600 ,
+	700 ,
+	800 ,
+	900 ,
+	1000 ,
+	1100 ,
+	1200 ,
+	1300 ,
+	1400 ,
+	1500 ,
+};
+
+/*
+ * This array maps the raw hex value to VBUS input current used by the AB8500
+ * Values taken from the UM0836
+ */
+static int ab8500_charger_vbus_in_curr_map[] = {
+	USB_CH_IP_CUR_LVL_0P05,
+	USB_CH_IP_CUR_LVL_0P09,
+	USB_CH_IP_CUR_LVL_0P19,
+	USB_CH_IP_CUR_LVL_0P29,
+	USB_CH_IP_CUR_LVL_0P38,
+	USB_CH_IP_CUR_LVL_0P45,
+	USB_CH_IP_CUR_LVL_0P5,
+	USB_CH_IP_CUR_LVL_0P6,
+	USB_CH_IP_CUR_LVL_0P7,
+	USB_CH_IP_CUR_LVL_0P8,
+	USB_CH_IP_CUR_LVL_0P9,
+	USB_CH_IP_CUR_LVL_1P0,
+	USB_CH_IP_CUR_LVL_1P1,
+	USB_CH_IP_CUR_LVL_1P3,
+	USB_CH_IP_CUR_LVL_1P4,
+	USB_CH_IP_CUR_LVL_1P5,
+};
+
+static int ab8500_voltage_to_regval(int voltage)
+{
+	int i;
+
+	/* Special case for voltage below 3.5V */
+	if (voltage < ab8500_charger_voltage_map[0])
+		return LOW_VOLT_REG;
+
+	for (i = 1; i < ARRAY_SIZE(ab8500_charger_voltage_map); i++) {
+		if (voltage < ab8500_charger_voltage_map[i])
+			return i - 1;
+	}
+
+	/* If not last element, return error */
+	i = ARRAY_SIZE(ab8500_charger_voltage_map) - 1;
+	if (voltage == ab8500_charger_voltage_map[i])
+		return i;
+	else
+		return -1;
+}
+
+static int ab8500_current_to_regval(int curr)
+{
+	int i;
+
+	if (curr < ab8500_charger_current_map[0])
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(ab8500_charger_current_map); i++) {
+		if (curr < ab8500_charger_current_map[i])
+			return i - 1;
+	}
+
+	/* If not last element, return error */
+	i = ARRAY_SIZE(ab8500_charger_current_map) - 1;
+	if (curr == ab8500_charger_current_map[i])
+		return i;
+	else
+		return -1;
+}
+
+static int ab8500_vbus_in_curr_to_regval(int curr)
+{
+	int i;
+
+	if (curr < ab8500_charger_vbus_in_curr_map[0])
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(ab8500_charger_vbus_in_curr_map); i++) {
+		if (curr < ab8500_charger_vbus_in_curr_map[i])
+			return i - 1;
+	}
+
+	/* If not last element, return error */
+	i = ARRAY_SIZE(ab8500_charger_vbus_in_curr_map) - 1;
+	if (curr == ab8500_charger_vbus_in_curr_map[i])
+		return i;
+	else
+		return -1;
+}
+
+/**
+ * ab8500_charger_get_usb_cur() - get usb current
+ * @di:		pointer to the ab8500_charger structre
+ *
+ * The usb stack provides the maximum current that can be drawn from
+ * the standard usb host. This will be in mA.
+ * This function converts current in mA to a value that can be written
+ * to the register. Returns -1 if charging is not allowed
+ */
+static int ab8500_charger_get_usb_cur(struct ab8500_charger *di)
+{
+	switch (di->usb_state.usb_current) {
+	case 100:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P09;
+		break;
+	case 200:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P19;
+		break;
+	case 300:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P29;
+		break;
+	case 400:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P38;
+		break;
+	case 500:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P5;
+		break;
+	default:
+		di->max_usb_in_curr = USB_CH_IP_CUR_LVL_0P05;
+		return -1;
+		break;
+	};
+	return 0;
+}
+
+/**
+ * ab8500_charger_set_vbus_in_curr() - set VBUS input current limit
+ * @di:		pointer to the ab8500_charger structure
+ * @ich_in:	charger input current limit
+ *
+ * Sets the current that can be drawn from the USB host
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_charger_set_vbus_in_curr(struct ab8500_charger *di,
+		int ich_in)
+{
+	int ret;
+	int input_curr_index;
+	int min_value;
+
+	/* We should always use to lowest current limit */
+	min_value = min(di->bat->chg_params->usb_curr_max, ich_in);
+
+	switch (min_value) {
+	case 100:
+		if (di->vbat < VBAT_TRESH_IP_CUR_RED)
+			min_value = USB_CH_IP_CUR_LVL_0P05;
+		break;
+	case 500:
+		if (di->vbat < VBAT_TRESH_IP_CUR_RED)
+			min_value = USB_CH_IP_CUR_LVL_0P45;
+		break;
+	default:
+		break;
+	}
+
+	input_curr_index = ab8500_vbus_in_curr_to_regval(min_value);
+	if (input_curr_index < 0) {
+		dev_err(di->dev, "VBUS input current limit too high\n");
+		return -ENXIO;
+	}
+
+	ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+		AB8500_USBCH_IPT_CRNTLVL_REG,
+		input_curr_index << VBUS_IN_CURR_LIM_SHIFT);
+	if (ret)
+		dev_err(di->dev, "%s write failed\n", __func__);
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_led_en() - turn on/off chargign led
+ * @di:		pointer to the ab8500_charger structure
+ * @on:		flag to turn on/off the chargign led
+ *
+ * Power ON/OFF charging LED indication
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_charger_led_en(struct ab8500_charger *di, int on)
+{
+	int ret;
+
+	if (on) {
+		/* Power ON charging LED indicator, set LED current to 5mA */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_LED_INDICATOR_PWM_CTRL,
+			(LED_IND_CUR_5MA | LED_INDICATOR_PWM_ENA));
+		if (ret) {
+			dev_err(di->dev, "Power ON LED failed\n");
+			return ret;
+		}
+		/* LED indicator PWM duty cycle 252/256 */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_LED_INDICATOR_PWM_DUTY,
+			LED_INDICATOR_PWM_DUTY_252_256);
+		if (ret) {
+			dev_err(di->dev, "Set LED PWM duty cycle failed\n");
+			return ret;
+		}
+	} else {
+		/* Power off charging LED indicator */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_LED_INDICATOR_PWM_CTRL,
+			LED_INDICATOR_PWM_DIS);
+		if (ret) {
+			dev_err(di->dev, "Power-off LED failed\n");
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_ac_en() - enable or disable ac charging
+ * @di:		pointer to the ab8500_charger structure
+ * @enable:	enable/disable flag
+ * @vset:	charging voltage
+ * @iset:	charging current
+ *
+ * Enable/Disable AC/Mains charging and turns on/off the charging led
+ * respectively.
+ **/
+static int ab8500_charger_ac_en(struct ux500_charger *charger,
+	int enable, int vset, int iset)
+{
+	int ret;
+	int volt_index;
+	int curr_index;
+	int input_curr_index;
+	u8 overshoot = 0;
+
+	struct ab8500_charger *di = to_ab8500_charger_ac_device_info(charger);
+
+	if (enable) {
+		/* Check if AC is connected */
+		if (!di->ac.charger_connected) {
+			dev_err(di->dev, "AC charger not connected\n");
+			return -ENXIO;
+		}
+
+		/* Enable AC charging */
+		dev_dbg(di->dev, "Enable AC: %dmV %dmA\n", vset, iset);
+
+		/*
+		 * Due to a bug in AB8500, BTEMP_HIGH/LOW interrupts
+		 * will be triggered everytime we enable the VDD ADC supply.
+		 * This will turn off charging for a short while.
+		 * It can be avoided by having the supply on when
+		 * there is a charger enabled. Normally the VDD ADC supply
+		 * is enabled everytime a GPADC conversion is triggered. We will
+		 * force it to be enabled from this driver to have
+		 * the GPADC module independant of the AB8500 chargers
+		 */
+		if (!di->vddadc_en_ac) {
+			regulator_enable(di->regu);
+			di->vddadc_en_ac = true;
+		}
+
+		/* Check if the requested voltage or current is valid */
+		volt_index = ab8500_voltage_to_regval(vset);
+		curr_index = ab8500_current_to_regval(iset);
+		input_curr_index = ab8500_current_to_regval(
+			di->bat->chg_params->ac_curr_max);
+		if (volt_index < 0 || curr_index < 0 || input_curr_index < 0) {
+			dev_err(di->dev,
+				"Charger voltage or current too high, "
+				"charging not started\n");
+			return -ENXIO;
+		}
+
+		/* ChVoltLevel: maximum battery charging voltage */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_CH_VOLT_LVL_REG, (u8) volt_index);
+		if (ret) {
+			dev_err(di->dev, "%s write failed\n", __func__);
+			return ret;
+		}
+		/* MainChInputCurr: current that can be drawn from the charger*/
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_MCH_IPT_CURLVL_REG,
+			input_curr_index << MAIN_CH_INPUT_CURR_SHIFT);
+		if (ret) {
+			dev_err(di->dev, "%s write failed\n", __func__);
+			return ret;
+		}
+		/* ChOutputCurentLevel: protected output current */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_CH_OPT_CRNTLVL_REG, (u8) curr_index);
+		if (ret) {
+			dev_err(di->dev, "%s write failed\n", __func__);
+			return ret;
+		}
+
+		/* Check if VBAT overshoot control should be enabled */
+		if (!di->bat->enable_overshoot)
+			overshoot = MAIN_CH_NO_OVERSHOOT_ENA_N;
+
+		/* Enable Main Charger */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_MCH_CTRL1, MAIN_CH_ENA | overshoot);
+		if (ret) {
+			dev_err(di->dev, "%s write failed\n", __func__);
+			return ret;
+		}
+
+		/* Power on charging LED indication */
+		ret = ab8500_charger_led_en(di, true);
+		if (ret < 0)
+			dev_err(di->dev, "failed to enable LED\n");
+
+		di->ac.charger_online = 1;
+	} else {
+		/* Disable AC charging */
+		if (is_ab8500_1p1_or_earlier(di->parent)) {
+			/*
+			 * For ABB revision 1.0 and 1.1 there is a bug in the
+			 * watchdog logic. That means we have to continously
+			 * kick the charger watchdog even when no charger is
+			 * connected. This is only valid once the AC charger
+			 * has been enabled. This is a bug that is not handled
+			 * by the algorithm and the watchdog have to be kicked
+			 * by the charger driver when the AC charger
+			 * is disabled
+			 */
+			if (di->ac_conn) {
+				queue_delayed_work(di->charger_wq,
+					&di->kick_wd_work,
+					round_jiffies(WD_KICK_INTERVAL));
+			}
+
+			/*
+			 * We can't turn off charging completely
+			 * due to a bug in AB8500 cut1.
+			 * If we do, charging will not start again.
+			 * That is why we set the lowest voltage
+			 * and current possible
+			 */
+			ret = abx500_set_register_interruptible(di->dev,
+				AB8500_CHARGER,
+				AB8500_CH_VOLT_LVL_REG, CH_VOL_LVL_3P5);
+			if (ret) {
+				dev_err(di->dev,
+					"%s write failed\n", __func__);
+				return ret;
+			}
+
+			ret = abx500_set_register_interruptible(di->dev,
+				AB8500_CHARGER,
+				AB8500_CH_OPT_CRNTLVL_REG, CH_OP_CUR_LVL_0P1);
+			if (ret) {
+				dev_err(di->dev,
+					"%s write failed\n", __func__);
+				return ret;
+			}
+		} else {
+			ret = abx500_set_register_interruptible(di->dev,
+				AB8500_CHARGER,
+				AB8500_MCH_CTRL1, 0);
+			if (ret) {
+				dev_err(di->dev,
+					"%s write failed\n", __func__);
+				return ret;
+			}
+		}
+
+		ret = ab8500_charger_led_en(di, false);
+		if (ret < 0)
+			dev_err(di->dev, "failed to disable LED\n");
+
+		di->ac.charger_online = 0;
+		di->ac.wd_expired = false;
+
+		/* Disable regulator if enabled */
+		if (di->vddadc_en_ac) {
+			regulator_disable(di->regu);
+			di->vddadc_en_ac = false;
+		}
+
+		dev_dbg(di->dev, "%s Disabled AC charging\n", __func__);
+	}
+	ab8500_power_supply_changed(di, &di->ac_chg.psy);
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_usb_en() - enable usb charging
+ * @di:		pointer to the ab8500_charger structure
+ * @enable:	enable/disable flag
+ * @vset:	charging voltage
+ * @ich_out:	charger output current
+ *
+ * Enable/Disable USB charging and turns on/off the charging led respectively.
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_charger_usb_en(struct ux500_charger *charger,
+	int enable, int vset, int ich_out)
+{
+	int ret;
+	int volt_index;
+	int curr_index;
+	u8 overshoot = 0;
+
+	struct ab8500_charger *di = to_ab8500_charger_usb_device_info(charger);
+
+	if (enable) {
+		/* Check if USB is connected */
+		if (!di->usb.charger_connected) {
+			dev_err(di->dev, "USB charger not connected\n");
+			return -ENXIO;
+		}
+
+		/*
+		 * Due to a bug in AB8500, BTEMP_HIGH/LOW interrupts
+		 * will be triggered everytime we enable the VDD ADC supply.
+		 * This will turn off charging for a short while.
+		 * It can be avoided by having the supply on when
+		 * there is a charger enabled. Normally the VDD ADC supply
+		 * is enabled everytime a GPADC conversion is triggered. We will
+		 * force it to be enabled from this driver to have
+		 * the GPADC module independant of the AB8500 chargers
+		 */
+		if (!di->vddadc_en_usb) {
+			regulator_enable(di->regu);
+			di->vddadc_en_usb = true;
+		}
+
+		/* Enable USB charging */
+		dev_dbg(di->dev, "Enable USB: %dmV %dmA\n", vset, ich_out);
+
+		/* Check if the requested voltage or current is valid */
+		volt_index = ab8500_voltage_to_regval(vset);
+		curr_index = ab8500_current_to_regval(ich_out);
+		if (volt_index < 0 || curr_index < 0) {
+			dev_err(di->dev,
+				"Charger voltage or current too high, "
+				"charging not started\n");
+			return -ENXIO;
+		}
+
+		/* ChVoltLevel: max voltage upto which battery can be charged */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_CH_VOLT_LVL_REG, (u8) volt_index);
+		if (ret) {
+			dev_err(di->dev, "%s write failed\n", __func__);
+			return ret;
+		}
+		/* USBChInputCurr: current that can be drawn from the usb */
+		ret = ab8500_charger_set_vbus_in_curr(di, di->max_usb_in_curr);
+		if (ret) {
+			dev_err(di->dev, "setting USBChInputCurr failed\n");
+			return ret;
+		}
+		/* ChOutputCurentLevel: protected output current */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_CH_OPT_CRNTLVL_REG, (u8) curr_index);
+		if (ret) {
+			dev_err(di->dev, "%s write failed\n", __func__);
+			return ret;
+		}
+		/* Check if VBAT overshoot control should be enabled */
+		if (!di->bat->enable_overshoot)
+			overshoot = USB_CHG_NO_OVERSHOOT_ENA_N;
+
+		/* Enable USB Charger */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_USBCH_CTRL1_REG, USB_CH_ENA | overshoot);
+		if (ret) {
+			dev_err(di->dev, "%s write failed\n", __func__);
+			return ret;
+		}
+
+		/* If success power on charging LED indication */
+		ret = ab8500_charger_led_en(di, true);
+		if (ret < 0)
+			dev_err(di->dev, "failed to enable LED\n");
+
+		queue_delayed_work(di->charger_wq, &di->check_vbat_work, HZ);
+
+		di->usb.charger_online = 1;
+	} else {
+		/* Disable USB charging */
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_CHARGER,
+			AB8500_USBCH_CTRL1_REG, 0);
+		if (ret) {
+			dev_err(di->dev,
+				"%s write failed\n", __func__);
+			return ret;
+		}
+
+		ret = ab8500_charger_led_en(di, false);
+		if (ret < 0)
+			dev_err(di->dev, "failed to disable LED\n");
+
+		di->usb.charger_online = 0;
+		di->usb.wd_expired = false;
+
+		/* Disable regulator if enabled */
+		if (di->vddadc_en_usb) {
+			regulator_disable(di->regu);
+			di->vddadc_en_usb = false;
+		}
+
+		dev_dbg(di->dev, "%s Disabled USB charging\n", __func__);
+
+		/* Cancel any pending Vbat check work */
+		if (delayed_work_pending(&di->check_vbat_work))
+			cancel_delayed_work(&di->check_vbat_work);
+
+	}
+	ab8500_power_supply_changed(di, &di->usb_chg.psy);
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_watchdog_kick() - kick charger watchdog
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Kick charger watchdog
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_charger_watchdog_kick(struct ux500_charger *charger)
+{
+	int ret;
+	struct ab8500_charger *di;
+
+	if (charger->psy.type == POWER_SUPPLY_TYPE_MAINS)
+		di = to_ab8500_charger_ac_device_info(charger);
+	else if (charger->psy.type == POWER_SUPPLY_TYPE_USB)
+		di = to_ab8500_charger_usb_device_info(charger);
+	else
+		return -ENXIO;
+
+	ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+		AB8500_CHARG_WD_CTRL, CHARG_WD_KICK);
+	if (ret)
+		dev_err(di->dev, "Failed to kick WD!\n");
+
+	return ret;
+}
+
+/**
+ * ab8500_charger_update_charger_current() - update charger current
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Update the charger output current for the specified charger
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_charger_update_charger_current(struct ux500_charger *charger,
+		int ich_out)
+{
+	int ret;
+	int curr_index;
+	struct ab8500_charger *di;
+
+	if (charger->psy.type == POWER_SUPPLY_TYPE_MAINS)
+		di = to_ab8500_charger_ac_device_info(charger);
+	else if (charger->psy.type == POWER_SUPPLY_TYPE_USB)
+		di = to_ab8500_charger_usb_device_info(charger);
+	else
+		return -ENXIO;
+
+	curr_index = ab8500_current_to_regval(ich_out);
+	if (curr_index < 0) {
+		dev_err(di->dev,
+			"Charger current too high, "
+			"charging not started\n");
+		return -ENXIO;
+	}
+
+	ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+		AB8500_CH_OPT_CRNTLVL_REG, (u8) curr_index);
+	if (ret) {
+		dev_err(di->dev, "%s write failed\n", __func__);
+		return ret;
+	}
+
+	/* Reset the main and usb drop input current measurement counter */
+	ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+				AB8500_CHARGER_CTRL,
+				0x1);
+	if (ret) {
+		dev_err(di->dev, "%s write failed\n", __func__);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int ab8500_charger_get_ext_psy_data(struct device *dev, void *data)
+{
+	struct power_supply *psy;
+	struct power_supply *ext;
+	struct ab8500_charger *di;
+	union power_supply_propval ret;
+	int i, j;
+	bool psy_found = false;
+	struct ux500_charger *usb_chg;
+
+	usb_chg = (struct ux500_charger *)data;
+	psy = &usb_chg->psy;
+
+	di = to_ab8500_charger_usb_device_info(usb_chg);
+
+	ext = dev_get_drvdata(dev);
+
+	/* For all psy where the driver name appears in any supplied_to */
+	for (i = 0; i < ext->num_supplicants; i++) {
+		if (!strcmp(ext->supplied_to[i], psy->name))
+			psy_found = true;
+	}
+
+	if (!psy_found)
+		return 0;
+
+	/* Go through all properties for the psy */
+	for (j = 0; j < ext->num_properties; j++) {
+		enum power_supply_property prop;
+		prop = ext->properties[j];
+
+		if (ext->get_property(ext, prop, &ret))
+			continue;
+
+		switch (prop) {
+		case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				di->vbat = ret.intval / 1000;
+				break;
+			default:
+				break;
+			}
+			break;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+/**
+ * ab8500_charger_check_vbat_work() - keep vbus current within spec
+ * @work	pointer to the work_struct structure
+ *
+ * Due to a asic bug it is necessary to lower the input current to the vbus
+ * charger when charging with at some specific levels. This issue is only valid
+ * for below a certain battery voltage. This function makes sure that the
+ * the allowed current limit isn't exceeded.
+ */
+static void ab8500_charger_check_vbat_work(struct work_struct *work)
+{
+	int t = 10;
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, check_vbat_work.work);
+
+	class_for_each_device(power_supply_class, NULL,
+		&di->usb_chg.psy, ab8500_charger_get_ext_psy_data);
+
+	/* First run old_vbat is 0. */
+	if (di->old_vbat == 0)
+		di->old_vbat = di->vbat;
+
+	if (!((di->old_vbat <= VBAT_TRESH_IP_CUR_RED &&
+		di->vbat <= VBAT_TRESH_IP_CUR_RED) ||
+		(di->old_vbat > VBAT_TRESH_IP_CUR_RED &&
+		di->vbat > VBAT_TRESH_IP_CUR_RED))) {
+
+		dev_dbg(di->dev, "Vbat did cross threshold, curr: %d, new: %d,"
+			" old: %d\n", di->max_usb_in_curr, di->vbat,
+			di->old_vbat);
+		ab8500_charger_set_vbus_in_curr(di, di->max_usb_in_curr);
+		power_supply_changed(&di->usb_chg.psy);
+	}
+
+	di->old_vbat = di->vbat;
+
+	/*
+	 * No need to check the battery voltage every second when not close to
+	 * the threshold.
+	 */
+	if (di->vbat < (VBAT_TRESH_IP_CUR_RED + 100) &&
+		(di->vbat > (VBAT_TRESH_IP_CUR_RED - 100)))
+			t = 1;
+
+	queue_delayed_work(di->charger_wq, &di->check_vbat_work, t * HZ);
+}
+
+/**
+ * ab8500_charger_check_hw_failure_work() - check main charger failure
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for checking the main charger status
+ */
+static void ab8500_charger_check_hw_failure_work(struct work_struct *work)
+{
+	int ret;
+	u8 reg_value;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, check_hw_failure_work.work);
+
+	/* Check if the status bits for HW failure is still active */
+	if (di->flags.mainextchnotok) {
+		ret = abx500_get_register_interruptible(di->dev,
+			AB8500_CHARGER, AB8500_CH_STATUS2_REG, &reg_value);
+		if (ret < 0) {
+			dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+			return;
+		}
+		if (!(reg_value & MAIN_CH_NOK)) {
+			di->flags.mainextchnotok = false;
+			ab8500_power_supply_changed(di, &di->ac_chg.psy);
+		}
+	}
+	if (di->flags.vbus_ovv) {
+		ret = abx500_get_register_interruptible(di->dev,
+			AB8500_CHARGER, AB8500_CH_USBCH_STAT2_REG,
+			&reg_value);
+		if (ret < 0) {
+			dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+			return;
+		}
+		if (!(reg_value & VBUS_OVV_TH)) {
+			di->flags.vbus_ovv = false;
+			ab8500_power_supply_changed(di, &di->usb_chg.psy);
+		}
+	}
+	/* If we still have a failure, schedule a new check */
+	if (di->flags.mainextchnotok || di->flags.vbus_ovv) {
+		queue_delayed_work(di->charger_wq,
+			&di->check_hw_failure_work, round_jiffies(HZ));
+	}
+}
+
+/**
+ * ab8500_charger_kick_watchdog_work() - kick the watchdog
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for kicking the charger watchdog.
+ *
+ * For ABB revision 1.0 and 1.1 there is a bug in the watchdog
+ * logic. That means we have to continously kick the charger
+ * watchdog even when no charger is connected. This is only
+ * valid once the AC charger has been enabled. This is
+ * a bug that is not handled by the algorithm and the
+ * watchdog have to be kicked by the charger driver
+ * when the AC charger is disabled
+ */
+static void ab8500_charger_kick_watchdog_work(struct work_struct *work)
+{
+	int ret;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, kick_wd_work.work);
+
+	ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+		AB8500_CHARG_WD_CTRL, CHARG_WD_KICK);
+	if (ret)
+		dev_err(di->dev, "Failed to kick WD!\n");
+
+	/* Schedule a new watchdog kick */
+	queue_delayed_work(di->charger_wq,
+		&di->kick_wd_work, round_jiffies(WD_KICK_INTERVAL));
+}
+
+/**
+ * ab8500_charger_ac_work() - work to get and set main charger status
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for checking the main charger status
+ */
+static void ab8500_charger_ac_work(struct work_struct *work)
+{
+	int ret;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, ac_work);
+
+	/*
+	 * Since we can't be sure that the events are received
+	 * synchronously, we have the check if the main charger is
+	 * connected by reading the status register
+	 */
+	ret = ab8500_charger_detect_chargers(di);
+	if (ret < 0)
+		return;
+
+	if (ret & AC_PW_CONN) {
+		di->ac.charger_connected = 1;
+		di->ac_conn = true;
+	} else {
+		di->ac.charger_connected = 0;
+	}
+
+	ab8500_power_supply_changed(di, &di->ac_chg.psy);
+	sysfs_notify(&di->ac_chg.psy.dev->kobj, NULL, "present");
+}
+
+/**
+ * ab8500_charger_detect_usb_type_work() - work to detect USB type
+ * @work:	Pointer to the work_struct structure
+ *
+ * Detect the type of USB plugged
+ */
+static void ab8500_charger_detect_usb_type_work(struct work_struct *work)
+{
+	int ret;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, detect_usb_type_work);
+
+	/*
+	 * Since we can't be sure that the events are received
+	 * synchronously, we have the check if is
+	 * connected by reading the status register
+	 */
+	ret = ab8500_charger_detect_chargers(di);
+	if (ret < 0)
+		return;
+
+	if (!(ret & USB_PW_CONN)) {
+		di->vbus_detected = 0;
+		ab8500_charger_set_usb_connected(di, false);
+		ab8500_power_supply_changed(di, &di->usb_chg.psy);
+	} else {
+		di->vbus_detected = 1;
+
+		if (is_ab8500_1p1_or_earlier(di->parent)) {
+			ret = ab8500_charger_detect_usb_type(di);
+			if (!ret) {
+				ab8500_charger_set_usb_connected(di, true);
+				ab8500_power_supply_changed(di,
+							    &di->usb_chg.psy);
+			}
+		} else {
+			/* For ABB cut2.0 and onwards we have an IRQ,
+			 * USB_LINK_STATUS that will be triggered when the USB
+			 * link status changes. The exception is USB connected
+			 * during startup. Then we don't get a
+			 * USB_LINK_STATUS IRQ
+			 */
+			if (di->vbus_detected_start) {
+				di->vbus_detected_start = false;
+				ret = ab8500_charger_detect_usb_type(di);
+				if (!ret) {
+					ab8500_charger_set_usb_connected(di,
+						true);
+					ab8500_power_supply_changed(di,
+						&di->usb_chg.psy);
+				}
+			}
+		}
+	}
+}
+
+/**
+ * ab8500_charger_usb_link_status_work() - work to detect USB type
+ * @work:	pointer to the work_struct structure
+ *
+ * Detect the type of USB plugged
+ */
+static void ab8500_charger_usb_link_status_work(struct work_struct *work)
+{
+	int ret;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, usb_link_status_work);
+
+	/*
+	 * Since we can't be sure that the events are received
+	 * synchronously, we have the check if  is
+	 * connected by reading the status register
+	 */
+	ret = ab8500_charger_detect_chargers(di);
+	if (ret < 0)
+		return;
+
+	if (!(ret & USB_PW_CONN)) {
+		di->vbus_detected = 0;
+		ab8500_charger_set_usb_connected(di, false);
+		ab8500_power_supply_changed(di, &di->usb_chg.psy);
+	} else {
+		di->vbus_detected = 1;
+		ret = ab8500_charger_read_usb_type(di);
+		if (!ret) {
+			/* Update maximum input current */
+			ret = ab8500_charger_set_vbus_in_curr(di,
+					di->max_usb_in_curr);
+			if (ret)
+				return;
+
+			ab8500_charger_set_usb_connected(di, true);
+			ab8500_power_supply_changed(di, &di->usb_chg.psy);
+		} else if (ret == -ENXIO) {
+			/* No valid charger type detected */
+			ab8500_charger_set_usb_connected(di, false);
+			ab8500_power_supply_changed(di, &di->usb_chg.psy);
+		}
+	}
+}
+
+static void ab8500_charger_usb_state_changed_work(struct work_struct *work)
+{
+	int ret;
+	unsigned long flags;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, usb_state_changed_work);
+
+	if (!di->vbus_detected)
+		return;
+
+	spin_lock_irqsave(&di->usb_state.usb_lock, flags);
+	di->usb_state.usb_changed = false;
+	spin_unlock_irqrestore(&di->usb_state.usb_lock, flags);
+
+	/*
+	 * wait for some time until you get updates from the usb stack
+	 * and negotiations are completed
+	 */
+	msleep(250);
+
+	if (di->usb_state.usb_changed)
+		return;
+
+	dev_dbg(di->dev, "%s USB state: 0x%02x mA: %d\n",
+		__func__, di->usb_state.state, di->usb_state.usb_current);
+
+	switch (di->usb_state.state) {
+	case AB8500_BM_USB_STATE_RESET_HS:
+	case AB8500_BM_USB_STATE_RESET_FS:
+	case AB8500_BM_USB_STATE_SUSPEND:
+	case AB8500_BM_USB_STATE_MAX:
+		ab8500_charger_set_usb_connected(di, false);
+		ab8500_power_supply_changed(di, &di->usb_chg.psy);
+		break;
+
+	case AB8500_BM_USB_STATE_RESUME:
+		/*
+		 * when suspend->resume there should be delay
+		 * of 1sec for enabling charging
+		 */
+		msleep(1000);
+		/* Intentional fall through */
+	case AB8500_BM_USB_STATE_CONFIGURED:
+		/*
+		 * USB is configured, enable charging with the charging
+		 * input current obtained from USB driver
+		 */
+		if (!ab8500_charger_get_usb_cur(di)) {
+			/* Update maximum input current */
+			ret = ab8500_charger_set_vbus_in_curr(di,
+					di->max_usb_in_curr);
+			if (ret)
+				return;
+
+			ab8500_charger_set_usb_connected(di, true);
+			ab8500_power_supply_changed(di, &di->usb_chg.psy);
+		}
+		break;
+
+	default:
+		break;
+	};
+}
+
+/**
+ * ab8500_charger_check_usbchargernotok_work() - check USB chg not ok status
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for checking the USB charger Not OK status
+ */
+static void ab8500_charger_check_usbchargernotok_work(struct work_struct *work)
+{
+	int ret;
+	u8 reg_value;
+	bool prev_status;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, check_usbchgnotok_work.work);
+
+	/* Check if the status bit for usbchargernotok is still active */
+	ret = abx500_get_register_interruptible(di->dev,
+		AB8500_CHARGER, AB8500_CH_USBCH_STAT2_REG, &reg_value);
+	if (ret < 0) {
+		dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+		return;
+	}
+	prev_status = di->flags.usbchargernotok;
+
+	if (reg_value & VBUS_CH_NOK) {
+		di->flags.usbchargernotok = true;
+		/* Check again in 1sec */
+		queue_delayed_work(di->charger_wq,
+			&di->check_usbchgnotok_work, HZ);
+	} else {
+		di->flags.usbchargernotok = false;
+		di->flags.vbus_collapse = false;
+	}
+
+	if (prev_status != di->flags.usbchargernotok)
+		ab8500_power_supply_changed(di, &di->usb_chg.psy);
+}
+
+/**
+ * ab8500_charger_check_main_thermal_prot_work() - check main thermal status
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for checking the Main thermal prot status
+ */
+static void ab8500_charger_check_main_thermal_prot_work(
+	struct work_struct *work)
+{
+	int ret;
+	u8 reg_value;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, check_main_thermal_prot_work);
+
+	/* Check if the status bit for main_thermal_prot is still active */
+	ret = abx500_get_register_interruptible(di->dev,
+		AB8500_CHARGER, AB8500_CH_STATUS2_REG, &reg_value);
+	if (ret < 0) {
+		dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+		return;
+	}
+	if (reg_value & MAIN_CH_TH_PROT)
+		di->flags.main_thermal_prot = true;
+	else
+		di->flags.main_thermal_prot = false;
+
+	ab8500_power_supply_changed(di, &di->ac_chg.psy);
+}
+
+/**
+ * ab8500_charger_check_usb_thermal_prot_work() - check usb thermal status
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for checking the USB thermal prot status
+ */
+static void ab8500_charger_check_usb_thermal_prot_work(
+	struct work_struct *work)
+{
+	int ret;
+	u8 reg_value;
+
+	struct ab8500_charger *di = container_of(work,
+		struct ab8500_charger, check_usb_thermal_prot_work);
+
+	/* Check if the status bit for usb_thermal_prot is still active */
+	ret = abx500_get_register_interruptible(di->dev,
+		AB8500_CHARGER, AB8500_CH_USBCH_STAT2_REG, &reg_value);
+	if (ret < 0) {
+		dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+		return;
+	}
+	if (reg_value & USB_CH_TH_PROT)
+		di->flags.usb_thermal_prot = true;
+	else
+		di->flags.usb_thermal_prot = false;
+
+	ab8500_power_supply_changed(di, &di->usb_chg.psy);
+}
+
+/**
+ * ab8500_charger_mainchunplugdet_handler() - main charger unplugged
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_mainchunplugdet_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev, "Main charger unplugged\n");
+	queue_work(di->charger_wq, &di->ac_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_mainchplugdet_handler() - main charger plugged
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_mainchplugdet_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev, "Main charger plugged\n");
+	queue_work(di->charger_wq, &di->ac_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_mainextchnotok_handler() - main charger not ok
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_mainextchnotok_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev, "Main charger not ok\n");
+	di->flags.mainextchnotok = true;
+	ab8500_power_supply_changed(di, &di->ac_chg.psy);
+
+	/* Schedule a new HW failure check */
+	queue_delayed_work(di->charger_wq, &di->check_hw_failure_work, 0);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_mainchthprotr_handler() - Die temp is above main charger
+ * thermal protection threshold
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_mainchthprotr_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev,
+		"Die temp above Main charger thermal protection threshold\n");
+	queue_work(di->charger_wq, &di->check_main_thermal_prot_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_mainchthprotf_handler() - Die temp is below main charger
+ * thermal protection threshold
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_mainchthprotf_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev,
+		"Die temp ok for Main charger thermal protection threshold\n");
+	queue_work(di->charger_wq, &di->check_main_thermal_prot_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_vbusdetf_handler() - VBUS falling detected
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_vbusdetf_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev, "VBUS falling detected\n");
+	queue_work(di->charger_wq, &di->detect_usb_type_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_vbusdetr_handler() - VBUS rising detected
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_vbusdetr_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	di->vbus_detected = true;
+	dev_dbg(di->dev, "VBUS rising detected\n");
+	queue_work(di->charger_wq, &di->detect_usb_type_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_usblinkstatus_handler() - USB link status has changed
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_usblinkstatus_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev, "USB link status changed\n");
+
+	queue_work(di->charger_wq, &di->usb_link_status_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_usbchthprotr_handler() - Die temp is above usb charger
+ * thermal protection threshold
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_usbchthprotr_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev,
+		"Die temp above USB charger thermal protection threshold\n");
+	queue_work(di->charger_wq, &di->check_usb_thermal_prot_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_usbchthprotf_handler() - Die temp is below usb charger
+ * thermal protection threshold
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_usbchthprotf_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev,
+		"Die temp ok for USB charger thermal protection threshold\n");
+	queue_work(di->charger_wq, &di->check_usb_thermal_prot_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_usbchargernotokr_handler() - USB charger not ok detected
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_usbchargernotokr_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev, "Not allowed USB charger detected\n");
+	queue_delayed_work(di->charger_wq, &di->check_usbchgnotok_work, 0);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_chwdexp_handler() - Charger watchdog expired
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_chwdexp_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev, "Charger watchdog expired\n");
+
+	/*
+	 * The charger that was online when the watchdog expired
+	 * needs to be restarted for charging to start again
+	 */
+	if (di->ac.charger_online) {
+		di->ac.wd_expired = true;
+		ab8500_power_supply_changed(di, &di->ac_chg.psy);
+	}
+	if (di->usb.charger_online) {
+		di->usb.wd_expired = true;
+		ab8500_power_supply_changed(di, &di->usb_chg.psy);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_vbusovv_handler() - VBUS overvoltage detected
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_charger structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_charger_vbusovv_handler(int irq, void *_di)
+{
+	struct ab8500_charger *di = _di;
+
+	dev_dbg(di->dev, "VBUS overvoltage detected\n");
+	di->flags.vbus_ovv = true;
+	ab8500_power_supply_changed(di, &di->usb_chg.psy);
+
+	/* Schedule a new HW failure check */
+	queue_delayed_work(di->charger_wq, &di->check_hw_failure_work, 0);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_charger_ac_get_property() - get the ac/mains properties
+ * @psy:       pointer to the power_supply structure
+ * @psp:       pointer to the power_supply_property structure
+ * @val:       pointer to the power_supply_propval union
+ *
+ * This function gets called when an application tries to get the ac/mains
+ * properties by reading the sysfs files.
+ * AC/Mains properties are online, present and voltage.
+ * online:     ac/mains charging is in progress or not
+ * present:    presence of the ac/mains
+ * voltage:    AC/Mains voltage
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_charger_ac_get_property(struct power_supply *psy,
+	enum power_supply_property psp,
+	union power_supply_propval *val)
+{
+	struct ab8500_charger *di;
+
+	di = to_ab8500_charger_ac_device_info(psy_to_ux500_charger(psy));
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_HEALTH:
+		if (di->flags.mainextchnotok)
+			val->intval = POWER_SUPPLY_HEALTH_UNSPEC_FAILURE;
+		else if (di->ac.wd_expired || di->usb.wd_expired)
+			val->intval = POWER_SUPPLY_HEALTH_DEAD;
+		else if (di->flags.main_thermal_prot)
+			val->intval = POWER_SUPPLY_HEALTH_OVERHEAT;
+		else
+			val->intval = POWER_SUPPLY_HEALTH_GOOD;
+		break;
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = di->ac.charger_online;
+		break;
+	case POWER_SUPPLY_PROP_PRESENT:
+		val->intval = di->ac.charger_connected;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		di->ac.charger_voltage = ab8500_charger_get_ac_voltage(di);
+		val->intval = di->ac.charger_voltage * 1000;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_AVG:
+		/*
+		 * This property is used to indicate when CV mode is entered
+		 * for the AC charger
+		 */
+		di->ac.cv_active = ab8500_charger_ac_cv(di);
+		val->intval = di->ac.cv_active;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		val->intval = ab8500_charger_get_ac_current(di) * 1000;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * ab8500_charger_usb_get_property() - get the usb properties
+ * @psy:        pointer to the power_supply structure
+ * @psp:        pointer to the power_supply_property structure
+ * @val:        pointer to the power_supply_propval union
+ *
+ * This function gets called when an application tries to get the usb
+ * properties by reading the sysfs files.
+ * USB properties are online, present and voltage.
+ * online:     usb charging is in progress or not
+ * present:    presence of the usb
+ * voltage:    vbus voltage
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_charger_usb_get_property(struct power_supply *psy,
+	enum power_supply_property psp,
+	union power_supply_propval *val)
+{
+	struct ab8500_charger *di;
+
+	di = to_ab8500_charger_usb_device_info(psy_to_ux500_charger(psy));
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_HEALTH:
+		if (di->flags.usbchargernotok)
+			val->intval = POWER_SUPPLY_HEALTH_UNSPEC_FAILURE;
+		else if (di->ac.wd_expired || di->usb.wd_expired)
+			val->intval = POWER_SUPPLY_HEALTH_DEAD;
+		else if (di->flags.usb_thermal_prot)
+			val->intval = POWER_SUPPLY_HEALTH_OVERHEAT;
+		else if (di->flags.vbus_ovv)
+			val->intval = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
+		else
+			val->intval = POWER_SUPPLY_HEALTH_GOOD;
+		break;
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = di->usb.charger_online;
+		break;
+	case POWER_SUPPLY_PROP_PRESENT:
+		val->intval = di->usb.charger_connected;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		di->usb.charger_voltage = ab8500_charger_get_vbus_voltage(di);
+		val->intval = di->usb.charger_voltage * 1000;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_AVG:
+		/*
+		 * This property is used to indicate when CV mode is entered
+		 * for the USB charger
+		 */
+		di->usb.cv_active = ab8500_charger_usb_cv(di);
+		val->intval = di->usb.cv_active;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		val->intval = ab8500_charger_get_usb_current(di) * 1000;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_AVG:
+		/*
+		 * This property is used to indicate when VBUS has collapsed
+		 * due to too high output current from the USB charger
+		 */
+		if (di->flags.vbus_collapse)
+			val->intval = 1;
+		else
+			val->intval = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * ab8500_charger_init_hw_registers() - Set up charger related registers
+ * @di:		pointer to the ab8500_charger structure
+ *
+ * Set up charger OVV, watchdog and maximum voltage registers as well as
+ * charging of the backup battery
+ */
+static int ab8500_charger_init_hw_registers(struct ab8500_charger *di)
+{
+	int ret = 0;
+
+	/* Setup maximum charger current and voltage for ABB cut2.0 */
+	if (!is_ab8500_1p1_or_earlier(di->parent)) {
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_CHARGER,
+			AB8500_CH_VOLT_LVL_MAX_REG, CH_VOL_LVL_4P6);
+		if (ret) {
+			dev_err(di->dev,
+				"failed to set CH_VOLT_LVL_MAX_REG\n");
+			goto out;
+		}
+
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_CHARGER,
+			AB8500_CH_OPT_CRNTLVL_MAX_REG, CH_OP_CUR_LVL_1P6);
+		if (ret) {
+			dev_err(di->dev,
+				"failed to set CH_OPT_CRNTLVL_MAX_REG\n");
+			goto out;
+		}
+	}
+
+	/* VBUS OVV set to 6.3V and enable automatic current limitiation */
+	ret = abx500_set_register_interruptible(di->dev,
+		AB8500_CHARGER,
+		AB8500_USBCH_CTRL2_REG,
+		VBUS_OVV_SELECT_6P3V | VBUS_AUTO_IN_CURR_LIM_ENA);
+	if (ret) {
+		dev_err(di->dev, "failed to set VBUS OVV\n");
+		goto out;
+	}
+
+	/* Enable main watchdog in OTP */
+	ret = abx500_set_register_interruptible(di->dev,
+		AB8500_OTP_EMUL, AB8500_OTP_CONF_15, OTP_ENABLE_WD);
+	if (ret) {
+		dev_err(di->dev, "failed to enable main WD in OTP\n");
+		goto out;
+	}
+
+	/* Enable main watchdog */
+	ret = abx500_set_register_interruptible(di->dev,
+		AB8500_SYS_CTRL2_BLOCK,
+		AB8500_MAIN_WDOG_CTRL_REG, MAIN_WDOG_ENA);
+	if (ret) {
+		dev_err(di->dev, "faile to enable main watchdog\n");
+		goto out;
+	}
+
+	/*
+	 * Due to internal synchronisation, Enable and Kick watchdog bits
+	 * cannot be enabled in a single write.
+	 * A minimum delay of 2*32 kHz period (62.5µs) must be inserted
+	 * between writing Enable then Kick bits.
+	 */
+	udelay(63);
+
+	/* Kick main watchdog */
+	ret = abx500_set_register_interruptible(di->dev,
+		AB8500_SYS_CTRL2_BLOCK,
+		AB8500_MAIN_WDOG_CTRL_REG,
+		(MAIN_WDOG_ENA | MAIN_WDOG_KICK));
+	if (ret) {
+		dev_err(di->dev, "failed to kick main watchdog\n");
+		goto out;
+	}
+
+	/* Disable main watchdog */
+	ret = abx500_set_register_interruptible(di->dev,
+		AB8500_SYS_CTRL2_BLOCK,
+		AB8500_MAIN_WDOG_CTRL_REG, MAIN_WDOG_DIS);
+	if (ret) {
+		dev_err(di->dev, "failed to disable main watchdog\n");
+		goto out;
+	}
+
+	/* Set watchdog timeout */
+	ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+		AB8500_CH_WD_TIMER_REG, WD_TIMER);
+	if (ret) {
+		dev_err(di->dev, "failed to set charger watchdog timeout\n");
+		goto out;
+	}
+
+	/* Backup battery voltage and current */
+	ret = abx500_set_register_interruptible(di->dev,
+		AB8500_RTC,
+		AB8500_RTC_BACKUP_CHG_REG,
+		di->bat->bkup_bat_v |
+		di->bat->bkup_bat_i);
+	if (ret) {
+		dev_err(di->dev, "failed to setup backup battery charging\n");
+		goto out;
+	}
+
+	/* Enable backup battery charging */
+	abx500_mask_and_set_register_interruptible(di->dev,
+		AB8500_RTC, AB8500_RTC_CTRL_REG,
+		RTC_BUP_CH_ENA, RTC_BUP_CH_ENA);
+	if (ret < 0)
+		dev_err(di->dev, "%s mask and set failed\n", __func__);
+
+out:
+	return ret;
+}
+
+/*
+ * ab8500 charger driver interrupts and their respective isr
+ */
+static struct ab8500_charger_interrupts ab8500_charger_irq[] = {
+	{"MAIN_CH_UNPLUG_DET", ab8500_charger_mainchunplugdet_handler},
+	{"MAIN_CHARGE_PLUG_DET", ab8500_charger_mainchplugdet_handler},
+	{"MAIN_EXT_CH_NOT_OK", ab8500_charger_mainextchnotok_handler},
+	{"MAIN_CH_TH_PROT_R", ab8500_charger_mainchthprotr_handler},
+	{"MAIN_CH_TH_PROT_F", ab8500_charger_mainchthprotf_handler},
+	{"VBUS_DET_F", ab8500_charger_vbusdetf_handler},
+	{"VBUS_DET_R", ab8500_charger_vbusdetr_handler},
+	{"USB_LINK_STATUS", ab8500_charger_usblinkstatus_handler},
+	{"USB_CH_TH_PROT_R", ab8500_charger_usbchthprotr_handler},
+	{"USB_CH_TH_PROT_F", ab8500_charger_usbchthprotf_handler},
+	{"USB_CHARGER_NOT_OKR", ab8500_charger_usbchargernotokr_handler},
+	{"VBUS_OVV", ab8500_charger_vbusovv_handler},
+	{"CH_WD_EXP", ab8500_charger_chwdexp_handler},
+};
+
+static int ab8500_charger_usb_notifier_call(struct notifier_block *nb,
+		unsigned long event, void *power)
+{
+	struct ab8500_charger *di =
+		container_of(nb, struct ab8500_charger, nb);
+	enum ab8500_usb_state bm_usb_state;
+	unsigned mA = *((unsigned *)power);
+
+	if (event != USB_EVENT_VBUS) {
+		dev_dbg(di->dev, "not a standard host, returning\n");
+		return NOTIFY_DONE;
+	}
+
+	/* TODO: State is fabricate  here. See if charger really needs USB
+	 * state or if mA is enough
+	 */
+	if ((di->usb_state.usb_current == 2) && (mA > 2))
+		bm_usb_state = AB8500_BM_USB_STATE_RESUME;
+	else if (mA == 0)
+		bm_usb_state = AB8500_BM_USB_STATE_RESET_HS;
+	else if (mA == 2)
+		bm_usb_state = AB8500_BM_USB_STATE_SUSPEND;
+	else if (mA >= 8) /* 8, 100, 500 */
+		bm_usb_state = AB8500_BM_USB_STATE_CONFIGURED;
+	else /* Should never occur */
+		bm_usb_state = AB8500_BM_USB_STATE_RESET_FS;
+
+	dev_dbg(di->dev, "%s usb_state: 0x%02x mA: %d\n",
+		__func__, bm_usb_state, mA);
+
+	spin_lock(&di->usb_state.usb_lock);
+	di->usb_state.usb_changed = true;
+	spin_unlock(&di->usb_state.usb_lock);
+
+	di->usb_state.state = bm_usb_state;
+	di->usb_state.usb_current = mA;
+
+	queue_work(di->charger_wq, &di->usb_state_changed_work);
+
+	return NOTIFY_OK;
+}
+
+#if defined(CONFIG_PM)
+static int ab8500_charger_resume(struct platform_device *pdev)
+{
+	int ret;
+	struct ab8500_charger *di = platform_get_drvdata(pdev);
+
+	/*
+	 * For ABB revision 1.0 and 1.1 there is a bug in the watchdog
+	 * logic. That means we have to continously kick the charger
+	 * watchdog even when no charger is connected. This is only
+	 * valid once the AC charger has been enabled. This is
+	 * a bug that is not handled by the algorithm and the
+	 * watchdog have to be kicked by the charger driver
+	 * when the AC charger is disabled
+	 */
+	if (di->ac_conn && is_ab8500_1p1_or_earlier(di->parent)) {
+		ret = abx500_set_register_interruptible(di->dev, AB8500_CHARGER,
+			AB8500_CHARG_WD_CTRL, CHARG_WD_KICK);
+		if (ret)
+			dev_err(di->dev, "Failed to kick WD!\n");
+
+		/* If not already pending start a new timer */
+		if (!delayed_work_pending(
+			&di->kick_wd_work)) {
+			queue_delayed_work(di->charger_wq, &di->kick_wd_work,
+				round_jiffies(WD_KICK_INTERVAL));
+		}
+	}
+
+	/* If we still have a HW failure, schedule a new check */
+	if (di->flags.mainextchnotok || di->flags.vbus_ovv) {
+		queue_delayed_work(di->charger_wq,
+			&di->check_hw_failure_work, 0);
+	}
+
+	return 0;
+}
+
+static int ab8500_charger_suspend(struct platform_device *pdev,
+	pm_message_t state)
+{
+	struct ab8500_charger *di = platform_get_drvdata(pdev);
+
+	/* Cancel any pending HW failure check */
+	if (delayed_work_pending(&di->check_hw_failure_work))
+		cancel_delayed_work(&di->check_hw_failure_work);
+
+	return 0;
+}
+#else
+#define ab8500_charger_suspend      NULL
+#define ab8500_charger_resume       NULL
+#endif
+
+static int __devexit ab8500_charger_remove(struct platform_device *pdev)
+{
+	struct ab8500_charger *di = platform_get_drvdata(pdev);
+	int i, irq, ret;
+
+	/* Disable AC charging */
+	ab8500_charger_ac_en(&di->ac_chg, false, 0, 0);
+
+	/* Disable USB charging */
+	ab8500_charger_usb_en(&di->usb_chg, false, 0, 0);
+
+	/* Disable interrupts */
+	for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
+		irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
+		free_irq(irq, di);
+	}
+
+	/* disable the regulator */
+	regulator_put(di->regu);
+
+	/* Backup battery voltage and current disable */
+	ret = abx500_mask_and_set_register_interruptible(di->dev,
+		AB8500_RTC, AB8500_RTC_CTRL_REG, RTC_BUP_CH_ENA, 0);
+	if (ret < 0)
+		dev_err(di->dev, "%s mask and set failed\n", __func__);
+
+	usb_unregister_notifier(di->usb_phy, &di->nb);
+	usb_put_transceiver(di->usb_phy);
+
+	/* Delete the work queue */
+	destroy_workqueue(di->charger_wq);
+
+	flush_scheduled_work();
+	power_supply_unregister(&di->usb_chg.psy);
+	power_supply_unregister(&di->ac_chg.psy);
+	platform_set_drvdata(pdev, NULL);
+	kfree(di);
+
+	return 0;
+}
+
+static int __devinit ab8500_charger_probe(struct platform_device *pdev)
+{
+	int irq, i, charger_status, ret = 0;
+	struct abx500_bm_plat_data *plat_data;
+
+	struct ab8500_charger *di =
+		kzalloc(sizeof(struct ab8500_charger), GFP_KERNEL);
+	if (!di)
+		return -ENOMEM;
+
+	/* get parent data */
+	di->dev = &pdev->dev;
+	di->parent = dev_get_drvdata(pdev->dev.parent);
+	di->gpadc = ab8500_gpadc_get("ab8500-gpadc.0");
+
+	/* initialize lock */
+	spin_lock_init(&di->usb_state.usb_lock);
+
+	/* get charger specific platform data */
+	plat_data = pdev->dev.platform_data;
+	di->pdata = plat_data->charger;
+
+	if (!di->pdata) {
+		dev_err(di->dev, "no charger platform data supplied\n");
+		ret = -EINVAL;
+		goto free_device_info;
+	}
+
+	/* get battery specific platform data */
+	di->bat = plat_data->battery;
+	if (!di->bat) {
+		dev_err(di->dev, "no battery platform data supplied\n");
+		ret = -EINVAL;
+		goto free_device_info;
+	}
+
+	di->autopower = false;
+
+	/* AC supply */
+	/* power_supply base class */
+	di->ac_chg.psy.name = "ab8500_ac";
+	di->ac_chg.psy.type = POWER_SUPPLY_TYPE_MAINS;
+	di->ac_chg.psy.properties = ab8500_charger_ac_props;
+	di->ac_chg.psy.num_properties = ARRAY_SIZE(ab8500_charger_ac_props);
+	di->ac_chg.psy.get_property = ab8500_charger_ac_get_property;
+	di->ac_chg.psy.supplied_to = di->pdata->supplied_to;
+	di->ac_chg.psy.num_supplicants = di->pdata->num_supplicants;
+	/* ux500_charger sub-class */
+	di->ac_chg.ops.enable = &ab8500_charger_ac_en;
+	di->ac_chg.ops.kick_wd = &ab8500_charger_watchdog_kick;
+	di->ac_chg.ops.update_curr = &ab8500_charger_update_charger_current;
+	di->ac_chg.max_out_volt = ab8500_charger_voltage_map[
+		ARRAY_SIZE(ab8500_charger_voltage_map) - 1];
+	di->ac_chg.max_out_curr = ab8500_charger_current_map[
+		ARRAY_SIZE(ab8500_charger_current_map) - 1];
+
+	/* USB supply */
+	/* power_supply base class */
+	di->usb_chg.psy.name = "ab8500_usb";
+	di->usb_chg.psy.type = POWER_SUPPLY_TYPE_USB;
+	di->usb_chg.psy.properties = ab8500_charger_usb_props;
+	di->usb_chg.psy.num_properties = ARRAY_SIZE(ab8500_charger_usb_props);
+	di->usb_chg.psy.get_property = ab8500_charger_usb_get_property;
+	di->usb_chg.psy.supplied_to = di->pdata->supplied_to;
+	di->usb_chg.psy.num_supplicants = di->pdata->num_supplicants;
+	/* ux500_charger sub-class */
+	di->usb_chg.ops.enable = &ab8500_charger_usb_en;
+	di->usb_chg.ops.kick_wd = &ab8500_charger_watchdog_kick;
+	di->usb_chg.ops.update_curr = &ab8500_charger_update_charger_current;
+	di->usb_chg.max_out_volt = ab8500_charger_voltage_map[
+		ARRAY_SIZE(ab8500_charger_voltage_map) - 1];
+	di->usb_chg.max_out_curr = ab8500_charger_current_map[
+		ARRAY_SIZE(ab8500_charger_current_map) - 1];
+
+
+	/* Create a work queue for the charger */
+	di->charger_wq =
+		create_singlethread_workqueue("ab8500_charger_wq");
+	if (di->charger_wq == NULL) {
+		dev_err(di->dev, "failed to create work queue\n");
+		goto free_device_info;
+	}
+
+	/* Init work for HW failure check */
+	INIT_DELAYED_WORK_DEFERRABLE(&di->check_hw_failure_work,
+		ab8500_charger_check_hw_failure_work);
+	INIT_DELAYED_WORK_DEFERRABLE(&di->check_usbchgnotok_work,
+		ab8500_charger_check_usbchargernotok_work);
+
+	/*
+	 * For ABB revision 1.0 and 1.1 there is a bug in the watchdog
+	 * logic. That means we have to continously kick the charger
+	 * watchdog even when no charger is connected. This is only
+	 * valid once the AC charger has been enabled. This is
+	 * a bug that is not handled by the algorithm and the
+	 * watchdog have to be kicked by the charger driver
+	 * when the AC charger is disabled
+	 */
+	INIT_DELAYED_WORK_DEFERRABLE(&di->kick_wd_work,
+		ab8500_charger_kick_watchdog_work);
+
+	INIT_DELAYED_WORK_DEFERRABLE(&di->check_vbat_work,
+		ab8500_charger_check_vbat_work);
+
+	/* Init work for charger detection */
+	INIT_WORK(&di->usb_link_status_work,
+		ab8500_charger_usb_link_status_work);
+	INIT_WORK(&di->ac_work, ab8500_charger_ac_work);
+	INIT_WORK(&di->detect_usb_type_work,
+		ab8500_charger_detect_usb_type_work);
+
+	INIT_WORK(&di->usb_state_changed_work,
+		ab8500_charger_usb_state_changed_work);
+
+	/* Init work for checking HW status */
+	INIT_WORK(&di->check_main_thermal_prot_work,
+		ab8500_charger_check_main_thermal_prot_work);
+	INIT_WORK(&di->check_usb_thermal_prot_work,
+		ab8500_charger_check_usb_thermal_prot_work);
+
+	/*
+	 * VDD ADC supply needs to be enabled from this driver when there
+	 * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
+	 * interrupts during charging
+	 */
+	di->regu = regulator_get(di->dev, "vddadc");
+	if (IS_ERR(di->regu)) {
+		ret = PTR_ERR(di->regu);
+		dev_err(di->dev, "failed to get vddadc regulator\n");
+		goto free_charger_wq;
+	}
+
+
+	/* Initialize OVV, and other registers */
+	ret = ab8500_charger_init_hw_registers(di);
+	if (ret) {
+		dev_err(di->dev, "failed to initialize ABB registers\n");
+		goto free_regulator;
+	}
+
+	/* Register AC charger class */
+	ret = power_supply_register(di->dev, &di->ac_chg.psy);
+	if (ret) {
+		dev_err(di->dev, "failed to register AC charger\n");
+		goto free_regulator;
+	}
+
+	/* Register USB charger class */
+	ret = power_supply_register(di->dev, &di->usb_chg.psy);
+	if (ret) {
+		dev_err(di->dev, "failed to register USB charger\n");
+		goto free_ac;
+	}
+
+	di->usb_phy = usb_get_transceiver();
+	if (!di->usb_phy) {
+		dev_err(di->dev, "failed to get usb transceiver\n");
+		ret = -EINVAL;
+		goto free_usb;
+	}
+	di->nb.notifier_call = ab8500_charger_usb_notifier_call;
+	ret = usb_register_notifier(di->usb_phy, &di->nb);
+	if (ret) {
+		dev_err(di->dev, "failed to register usb notifier\n");
+		goto put_usb_phy;
+	}
+
+	/* Identify the connected charger types during startup */
+	charger_status = ab8500_charger_detect_chargers(di);
+	if (charger_status & AC_PW_CONN) {
+		di->ac.charger_connected = 1;
+		di->ac_conn = true;
+		ab8500_power_supply_changed(di, &di->ac_chg.psy);
+		sysfs_notify(&di->ac_chg.psy.dev->kobj, NULL, "present");
+	}
+
+	if (charger_status & USB_PW_CONN) {
+		dev_dbg(di->dev, "VBUS Detect during startup\n");
+		di->vbus_detected = true;
+		di->vbus_detected_start = true;
+		queue_work(di->charger_wq,
+			&di->detect_usb_type_work);
+	}
+
+	/* Register interrupts */
+	for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
+		irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
+		ret = request_threaded_irq(irq, NULL, ab8500_charger_irq[i].isr,
+			IRQF_SHARED | IRQF_NO_SUSPEND,
+			ab8500_charger_irq[i].name, di);
+
+		if (ret != 0) {
+			dev_err(di->dev, "failed to request %s IRQ %d: %d\n"
+				, ab8500_charger_irq[i].name, irq, ret);
+			goto free_irq;
+		}
+		dev_dbg(di->dev, "Requested %s IRQ %d: %d\n",
+			ab8500_charger_irq[i].name, irq, ret);
+	}
+
+	platform_set_drvdata(pdev, di);
+
+	return ret;
+
+free_irq:
+	usb_unregister_notifier(di->usb_phy, &di->nb);
+
+	/* We also have to free all successfully registered irqs */
+	for (i = i - 1; i >= 0; i--) {
+		irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
+		free_irq(irq, di);
+	}
+put_usb_phy:
+	usb_put_transceiver(di->usb_phy);
+free_usb:
+	power_supply_unregister(&di->usb_chg.psy);
+free_ac:
+	power_supply_unregister(&di->ac_chg.psy);
+free_regulator:
+	regulator_put(di->regu);
+free_charger_wq:
+	destroy_workqueue(di->charger_wq);
+free_device_info:
+	kfree(di);
+
+	return ret;
+}
+
+static struct platform_driver ab8500_charger_driver = {
+	.probe = ab8500_charger_probe,
+	.remove = __devexit_p(ab8500_charger_remove),
+	.suspend = ab8500_charger_suspend,
+	.resume = ab8500_charger_resume,
+	.driver = {
+		.name = "ab8500-charger",
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init ab8500_charger_init(void)
+{
+	return platform_driver_register(&ab8500_charger_driver);
+}
+
+static void __exit ab8500_charger_exit(void)
+{
+	platform_driver_unregister(&ab8500_charger_driver);
+}
+
+subsys_initcall_sync(ab8500_charger_init);
+module_exit(ab8500_charger_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Johan Palsson, Karl Komierowski, Arun R Murthy");
+MODULE_ALIAS("platform:ab8500-charger");
+MODULE_DESCRIPTION("AB8500 charger management driver");
diff --git a/drivers/power/ab8500_fg.c b/drivers/power/ab8500_fg.c
new file mode 100644
index 000000000000..c22f2f05657e
--- /dev/null
+++ b/drivers/power/ab8500_fg.c
@@ -0,0 +1,2637 @@
+/*
+ * Copyright (C) ST-Ericsson AB 2012
+ *
+ * Main and Back-up battery management driver.
+ *
+ * Note: Backup battery management is required in case of Li-Ion battery and not
+ * for capacitive battery. HREF boards have capacitive battery and hence backup
+ * battery management is not used and the supported code is available in this
+ * driver.
+ *
+ * License Terms: GNU General Public License v2
+ * Author:
+ *	Johan Palsson <johan.palsson@stericsson.com>
+ *	Karl Komierowski <karl.komierowski@stericsson.com>
+ *	Arun R Murthy <arun.murthy@stericsson.com>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/kobject.h>
+#include <linux/mfd/abx500/ab8500.h>
+#include <linux/mfd/abx500.h>
+#include <linux/slab.h>
+#include <linux/mfd/abx500/ab8500-bm.h>
+#include <linux/delay.h>
+#include <linux/mfd/abx500/ab8500-gpadc.h>
+#include <linux/mfd/abx500.h>
+#include <linux/time.h>
+#include <linux/completion.h>
+
+#define MILLI_TO_MICRO			1000
+#define FG_LSB_IN_MA			1627
+#define QLSB_NANO_AMP_HOURS_X10		1129
+#define INS_CURR_TIMEOUT		(3 * HZ)
+
+#define SEC_TO_SAMPLE(S)		(S * 4)
+
+#define NBR_AVG_SAMPLES			20
+
+#define LOW_BAT_CHECK_INTERVAL		(2 * HZ)
+
+#define VALID_CAPACITY_SEC		(45 * 60) /* 45 minutes */
+#define BATT_OK_MIN			2360 /* mV */
+#define BATT_OK_INCREMENT		50 /* mV */
+#define BATT_OK_MAX_NR_INCREMENTS	0xE
+
+/* FG constants */
+#define BATT_OVV			0x01
+
+#define interpolate(x, x1, y1, x2, y2) \
+	((y1) + ((((y2) - (y1)) * ((x) - (x1))) / ((x2) - (x1))));
+
+#define to_ab8500_fg_device_info(x) container_of((x), \
+	struct ab8500_fg, fg_psy);
+
+/**
+ * struct ab8500_fg_interrupts - ab8500 fg interupts
+ * @name:	name of the interrupt
+ * @isr		function pointer to the isr
+ */
+struct ab8500_fg_interrupts {
+	char *name;
+	irqreturn_t (*isr)(int irq, void *data);
+};
+
+enum ab8500_fg_discharge_state {
+	AB8500_FG_DISCHARGE_INIT,
+	AB8500_FG_DISCHARGE_INITMEASURING,
+	AB8500_FG_DISCHARGE_INIT_RECOVERY,
+	AB8500_FG_DISCHARGE_RECOVERY,
+	AB8500_FG_DISCHARGE_READOUT_INIT,
+	AB8500_FG_DISCHARGE_READOUT,
+	AB8500_FG_DISCHARGE_WAKEUP,
+};
+
+static char *discharge_state[] = {
+	"DISCHARGE_INIT",
+	"DISCHARGE_INITMEASURING",
+	"DISCHARGE_INIT_RECOVERY",
+	"DISCHARGE_RECOVERY",
+	"DISCHARGE_READOUT_INIT",
+	"DISCHARGE_READOUT",
+	"DISCHARGE_WAKEUP",
+};
+
+enum ab8500_fg_charge_state {
+	AB8500_FG_CHARGE_INIT,
+	AB8500_FG_CHARGE_READOUT,
+};
+
+static char *charge_state[] = {
+	"CHARGE_INIT",
+	"CHARGE_READOUT",
+};
+
+enum ab8500_fg_calibration_state {
+	AB8500_FG_CALIB_INIT,
+	AB8500_FG_CALIB_WAIT,
+	AB8500_FG_CALIB_END,
+};
+
+struct ab8500_fg_avg_cap {
+	int avg;
+	int samples[NBR_AVG_SAMPLES];
+	__kernel_time_t time_stamps[NBR_AVG_SAMPLES];
+	int pos;
+	int nbr_samples;
+	int sum;
+};
+
+struct ab8500_fg_battery_capacity {
+	int max_mah_design;
+	int max_mah;
+	int mah;
+	int permille;
+	int level;
+	int prev_mah;
+	int prev_percent;
+	int prev_level;
+	int user_mah;
+};
+
+struct ab8500_fg_flags {
+	bool fg_enabled;
+	bool conv_done;
+	bool charging;
+	bool fully_charged;
+	bool force_full;
+	bool low_bat_delay;
+	bool low_bat;
+	bool bat_ovv;
+	bool batt_unknown;
+	bool calibrate;
+	bool user_cap;
+	bool batt_id_received;
+};
+
+struct inst_curr_result_list {
+	struct list_head list;
+	int *result;
+};
+
+/**
+ * struct ab8500_fg - ab8500 FG device information
+ * @dev:		Pointer to the structure device
+ * @node:		a list of AB8500 FGs, hence prepared for reentrance
+ * @irq			holds the CCEOC interrupt number
+ * @vbat:		Battery voltage in mV
+ * @vbat_nom:		Nominal battery voltage in mV
+ * @inst_curr:		Instantenous battery current in mA
+ * @avg_curr:		Average battery current in mA
+ * @bat_temp		battery temperature
+ * @fg_samples:		Number of samples used in the FG accumulation
+ * @accu_charge:	Accumulated charge from the last conversion
+ * @recovery_cnt:	Counter for recovery mode
+ * @high_curr_cnt:	Counter for high current mode
+ * @init_cnt:		Counter for init mode
+ * @recovery_needed:	Indicate if recovery is needed
+ * @high_curr_mode:	Indicate if we're in high current mode
+ * @init_capacity:	Indicate if initial capacity measuring should be done
+ * @turn_off_fg:	True if fg was off before current measurement
+ * @calib_state		State during offset calibration
+ * @discharge_state:	Current discharge state
+ * @charge_state:	Current charge state
+ * @ab8500_fg_complete	Completion struct used for the instant current reading
+ * @flags:		Structure for information about events triggered
+ * @bat_cap:		Structure for battery capacity specific parameters
+ * @avg_cap:		Average capacity filter
+ * @parent:		Pointer to the struct ab8500
+ * @gpadc:		Pointer to the struct gpadc
+ * @pdata:		Pointer to the abx500_fg platform data
+ * @bat:		Pointer to the abx500_bm platform data
+ * @fg_psy:		Structure that holds the FG specific battery properties
+ * @fg_wq:		Work queue for running the FG algorithm
+ * @fg_periodic_work:	Work to run the FG algorithm periodically
+ * @fg_low_bat_work:	Work to check low bat condition
+ * @fg_reinit_work	Work used to reset and reinitialise the FG algorithm
+ * @fg_work:		Work to run the FG algorithm instantly
+ * @fg_acc_cur_work:	Work to read the FG accumulator
+ * @fg_check_hw_failure_work:	Work for checking HW state
+ * @cc_lock:		Mutex for locking the CC
+ * @fg_kobject:		Structure of type kobject
+ */
+struct ab8500_fg {
+	struct device *dev;
+	struct list_head node;
+	int irq;
+	int vbat;
+	int vbat_nom;
+	int inst_curr;
+	int avg_curr;
+	int bat_temp;
+	int fg_samples;
+	int accu_charge;
+	int recovery_cnt;
+	int high_curr_cnt;
+	int init_cnt;
+	bool recovery_needed;
+	bool high_curr_mode;
+	bool init_capacity;
+	bool turn_off_fg;
+	enum ab8500_fg_calibration_state calib_state;
+	enum ab8500_fg_discharge_state discharge_state;
+	enum ab8500_fg_charge_state charge_state;
+	struct completion ab8500_fg_complete;
+	struct ab8500_fg_flags flags;
+	struct ab8500_fg_battery_capacity bat_cap;
+	struct ab8500_fg_avg_cap avg_cap;
+	struct ab8500 *parent;
+	struct ab8500_gpadc *gpadc;
+	struct abx500_fg_platform_data *pdata;
+	struct abx500_bm_data *bat;
+	struct power_supply fg_psy;
+	struct workqueue_struct *fg_wq;
+	struct delayed_work fg_periodic_work;
+	struct delayed_work fg_low_bat_work;
+	struct delayed_work fg_reinit_work;
+	struct work_struct fg_work;
+	struct work_struct fg_acc_cur_work;
+	struct delayed_work fg_check_hw_failure_work;
+	struct mutex cc_lock;
+	struct kobject fg_kobject;
+};
+static LIST_HEAD(ab8500_fg_list);
+
+/**
+ * ab8500_fg_get() - returns a reference to the primary AB8500 fuel gauge
+ * (i.e. the first fuel gauge in the instance list)
+ */
+struct ab8500_fg *ab8500_fg_get(void)
+{
+	struct ab8500_fg *fg;
+
+	if (list_empty(&ab8500_fg_list))
+		return NULL;
+
+	fg = list_first_entry(&ab8500_fg_list, struct ab8500_fg, node);
+	return fg;
+}
+
+/* Main battery properties */
+static enum power_supply_property ab8500_fg_props[] = {
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CURRENT_AVG,
+	POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN,
+	POWER_SUPPLY_PROP_ENERGY_FULL,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+};
+
+/*
+ * This array maps the raw hex value to lowbat voltage used by the AB8500
+ * Values taken from the UM0836
+ */
+static int ab8500_fg_lowbat_voltage_map[] = {
+	2300 ,
+	2325 ,
+	2350 ,
+	2375 ,
+	2400 ,
+	2425 ,
+	2450 ,
+	2475 ,
+	2500 ,
+	2525 ,
+	2550 ,
+	2575 ,
+	2600 ,
+	2625 ,
+	2650 ,
+	2675 ,
+	2700 ,
+	2725 ,
+	2750 ,
+	2775 ,
+	2800 ,
+	2825 ,
+	2850 ,
+	2875 ,
+	2900 ,
+	2925 ,
+	2950 ,
+	2975 ,
+	3000 ,
+	3025 ,
+	3050 ,
+	3075 ,
+	3100 ,
+	3125 ,
+	3150 ,
+	3175 ,
+	3200 ,
+	3225 ,
+	3250 ,
+	3275 ,
+	3300 ,
+	3325 ,
+	3350 ,
+	3375 ,
+	3400 ,
+	3425 ,
+	3450 ,
+	3475 ,
+	3500 ,
+	3525 ,
+	3550 ,
+	3575 ,
+	3600 ,
+	3625 ,
+	3650 ,
+	3675 ,
+	3700 ,
+	3725 ,
+	3750 ,
+	3775 ,
+	3800 ,
+	3825 ,
+	3850 ,
+	3850 ,
+};
+
+static u8 ab8500_volt_to_regval(int voltage)
+{
+	int i;
+
+	if (voltage < ab8500_fg_lowbat_voltage_map[0])
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(ab8500_fg_lowbat_voltage_map); i++) {
+		if (voltage < ab8500_fg_lowbat_voltage_map[i])
+			return (u8) i - 1;
+	}
+
+	/* If not captured above, return index of last element */
+	return (u8) ARRAY_SIZE(ab8500_fg_lowbat_voltage_map) - 1;
+}
+
+/**
+ * ab8500_fg_is_low_curr() - Low or high current mode
+ * @di:		pointer to the ab8500_fg structure
+ * @curr:	the current to base or our decision on
+ *
+ * Low current mode if the current consumption is below a certain threshold
+ */
+static int ab8500_fg_is_low_curr(struct ab8500_fg *di, int curr)
+{
+	/*
+	 * We want to know if we're in low current mode
+	 */
+	if (curr > -di->bat->fg_params->high_curr_threshold)
+		return true;
+	else
+		return false;
+}
+
+/**
+ * ab8500_fg_add_cap_sample() - Add capacity to average filter
+ * @di:		pointer to the ab8500_fg structure
+ * @sample:	the capacity in mAh to add to the filter
+ *
+ * A capacity is added to the filter and a new mean capacity is calculated and
+ * returned
+ */
+static int ab8500_fg_add_cap_sample(struct ab8500_fg *di, int sample)
+{
+	struct timespec ts;
+	struct ab8500_fg_avg_cap *avg = &di->avg_cap;
+
+	getnstimeofday(&ts);
+
+	do {
+		avg->sum += sample - avg->samples[avg->pos];
+		avg->samples[avg->pos] = sample;
+		avg->time_stamps[avg->pos] = ts.tv_sec;
+		avg->pos++;
+
+		if (avg->pos == NBR_AVG_SAMPLES)
+			avg->pos = 0;
+
+		if (avg->nbr_samples < NBR_AVG_SAMPLES)
+			avg->nbr_samples++;
+
+		/*
+		 * Check the time stamp for each sample. If too old,
+		 * replace with latest sample
+		 */
+	} while (ts.tv_sec - VALID_CAPACITY_SEC > avg->time_stamps[avg->pos]);
+
+	avg->avg = avg->sum / avg->nbr_samples;
+
+	return avg->avg;
+}
+
+/**
+ * ab8500_fg_clear_cap_samples() - Clear average filter
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * The capacity filter is is reset to zero.
+ */
+static void ab8500_fg_clear_cap_samples(struct ab8500_fg *di)
+{
+	int i;
+	struct ab8500_fg_avg_cap *avg = &di->avg_cap;
+
+	avg->pos = 0;
+	avg->nbr_samples = 0;
+	avg->sum = 0;
+	avg->avg = 0;
+
+	for (i = 0; i < NBR_AVG_SAMPLES; i++) {
+		avg->samples[i] = 0;
+		avg->time_stamps[i] = 0;
+	}
+}
+
+/**
+ * ab8500_fg_fill_cap_sample() - Fill average filter
+ * @di:		pointer to the ab8500_fg structure
+ * @sample:	the capacity in mAh to fill the filter with
+ *
+ * The capacity filter is filled with a capacity in mAh
+ */
+static void ab8500_fg_fill_cap_sample(struct ab8500_fg *di, int sample)
+{
+	int i;
+	struct timespec ts;
+	struct ab8500_fg_avg_cap *avg = &di->avg_cap;
+
+	getnstimeofday(&ts);
+
+	for (i = 0; i < NBR_AVG_SAMPLES; i++) {
+		avg->samples[i] = sample;
+		avg->time_stamps[i] = ts.tv_sec;
+	}
+
+	avg->pos = 0;
+	avg->nbr_samples = NBR_AVG_SAMPLES;
+	avg->sum = sample * NBR_AVG_SAMPLES;
+	avg->avg = sample;
+}
+
+/**
+ * ab8500_fg_coulomb_counter() - enable coulomb counter
+ * @di:		pointer to the ab8500_fg structure
+ * @enable:	enable/disable
+ *
+ * Enable/Disable coulomb counter.
+ * On failure returns negative value.
+ */
+static int ab8500_fg_coulomb_counter(struct ab8500_fg *di, bool enable)
+{
+	int ret = 0;
+	mutex_lock(&di->cc_lock);
+	if (enable) {
+		/* To be able to reprogram the number of samples, we have to
+		 * first stop the CC and then enable it again */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
+			AB8500_RTC_CC_CONF_REG, 0x00);
+		if (ret)
+			goto cc_err;
+
+		/* Program the samples */
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_NCOV_ACCU,
+			di->fg_samples);
+		if (ret)
+			goto cc_err;
+
+		/* Start the CC */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
+			AB8500_RTC_CC_CONF_REG,
+			(CC_DEEP_SLEEP_ENA | CC_PWR_UP_ENA));
+		if (ret)
+			goto cc_err;
+
+		di->flags.fg_enabled = true;
+	} else {
+		/* Clear any pending read requests */
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_CTRL_REG, 0);
+		if (ret)
+			goto cc_err;
+
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_NCOV_ACCU_CTRL, 0);
+		if (ret)
+			goto cc_err;
+
+		/* Stop the CC */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
+			AB8500_RTC_CC_CONF_REG, 0);
+		if (ret)
+			goto cc_err;
+
+		di->flags.fg_enabled = false;
+
+	}
+	dev_dbg(di->dev, " CC enabled: %d Samples: %d\n",
+		enable, di->fg_samples);
+
+	mutex_unlock(&di->cc_lock);
+
+	return ret;
+cc_err:
+	dev_err(di->dev, "%s Enabling coulomb counter failed\n", __func__);
+	mutex_unlock(&di->cc_lock);
+	return ret;
+}
+
+/**
+ * ab8500_fg_inst_curr_start() - start battery instantaneous current
+ * @di:         pointer to the ab8500_fg structure
+ *
+ * Returns 0 or error code
+ * Note: This is part "one" and has to be called before
+ * ab8500_fg_inst_curr_finalize()
+ */
+ int ab8500_fg_inst_curr_start(struct ab8500_fg *di)
+{
+	u8 reg_val;
+	int ret;
+
+	mutex_lock(&di->cc_lock);
+
+	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
+		AB8500_RTC_CC_CONF_REG, &reg_val);
+	if (ret < 0)
+		goto fail;
+
+	if (!(reg_val & CC_PWR_UP_ENA)) {
+		dev_dbg(di->dev, "%s Enable FG\n", __func__);
+		di->turn_off_fg = true;
+
+		/* Program the samples */
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_NCOV_ACCU,
+			SEC_TO_SAMPLE(10));
+		if (ret)
+			goto fail;
+
+		/* Start the CC */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
+			AB8500_RTC_CC_CONF_REG,
+			(CC_DEEP_SLEEP_ENA | CC_PWR_UP_ENA));
+		if (ret)
+			goto fail;
+	} else {
+		di->turn_off_fg = false;
+	}
+
+	/* Return and WFI */
+	INIT_COMPLETION(di->ab8500_fg_complete);
+	enable_irq(di->irq);
+
+	/* Note: cc_lock is still locked */
+	return 0;
+fail:
+	mutex_unlock(&di->cc_lock);
+	return ret;
+}
+
+/**
+ * ab8500_fg_inst_curr_done() - check if fg conversion is done
+ * @di:         pointer to the ab8500_fg structure
+ *
+ * Returns 1 if conversion done, 0 if still waiting
+ */
+int ab8500_fg_inst_curr_done(struct ab8500_fg *di)
+{
+	return completion_done(&di->ab8500_fg_complete);
+}
+
+/**
+ * ab8500_fg_inst_curr_finalize() - battery instantaneous current
+ * @di:         pointer to the ab8500_fg structure
+ * @res:	battery instantenous current(on success)
+ *
+ * Returns 0 or an error code
+ * Note: This is part "two" and has to be called at earliest 250 ms
+ * after ab8500_fg_inst_curr_start()
+ */
+int ab8500_fg_inst_curr_finalize(struct ab8500_fg *di, int *res)
+{
+	u8 low, high;
+	int val;
+	int ret;
+	int timeout;
+
+	if (!completion_done(&di->ab8500_fg_complete)) {
+		timeout = wait_for_completion_timeout(&di->ab8500_fg_complete,
+			INS_CURR_TIMEOUT);
+		dev_dbg(di->dev, "Finalize time: %d ms\n",
+			((INS_CURR_TIMEOUT - timeout) * 1000) / HZ);
+		if (!timeout) {
+			ret = -ETIME;
+			disable_irq(di->irq);
+			dev_err(di->dev, "completion timed out [%d]\n",
+				__LINE__);
+			goto fail;
+		}
+	}
+
+	disable_irq(di->irq);
+
+	ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_CTRL_REG,
+			READ_REQ, READ_REQ);
+
+	/* 100uS between read request and read is needed */
+	usleep_range(100, 100);
+
+	/* Read CC Sample conversion value Low and high */
+	ret = abx500_get_register_interruptible(di->dev, AB8500_GAS_GAUGE,
+		AB8500_GASG_CC_SMPL_CNVL_REG,  &low);
+	if (ret < 0)
+		goto fail;
+
+	ret = abx500_get_register_interruptible(di->dev, AB8500_GAS_GAUGE,
+		AB8500_GASG_CC_SMPL_CNVH_REG,  &high);
+	if (ret < 0)
+		goto fail;
+
+	/*
+	 * negative value for Discharging
+	 * convert 2's compliment into decimal
+	 */
+	if (high & 0x10)
+		val = (low | (high << 8) | 0xFFFFE000);
+	else
+		val = (low | (high << 8));
+
+	/*
+	 * Convert to unit value in mA
+	 * Full scale input voltage is
+	 * 66.660mV => LSB = 66.660mV/(4096*res) = 1.627mA
+	 * Given a 250ms conversion cycle time the LSB corresponds
+	 * to 112.9 nAh. Convert to current by dividing by the conversion
+	 * time in hours (250ms = 1 / (3600 * 4)h)
+	 * 112.9nAh assumes 10mOhm, but fg_res is in 0.1mOhm
+	 */
+	val = (val * QLSB_NANO_AMP_HOURS_X10 * 36 * 4) /
+		(1000 * di->bat->fg_res);
+
+	if (di->turn_off_fg) {
+		dev_dbg(di->dev, "%s Disable FG\n", __func__);
+
+		/* Clear any pending read requests */
+		ret = abx500_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_CTRL_REG, 0);
+		if (ret)
+			goto fail;
+
+		/* Stop the CC */
+		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
+			AB8500_RTC_CC_CONF_REG, 0);
+		if (ret)
+			goto fail;
+	}
+	mutex_unlock(&di->cc_lock);
+	(*res) = val;
+
+	return 0;
+fail:
+	mutex_unlock(&di->cc_lock);
+	return ret;
+}
+
+/**
+ * ab8500_fg_inst_curr_blocking() - battery instantaneous current
+ * @di:         pointer to the ab8500_fg structure
+ * @res:	battery instantenous current(on success)
+ *
+ * Returns 0 else error code
+ */
+int ab8500_fg_inst_curr_blocking(struct ab8500_fg *di)
+{
+	int ret;
+	int res = 0;
+
+	ret = ab8500_fg_inst_curr_start(di);
+	if (ret) {
+		dev_err(di->dev, "Failed to initialize fg_inst\n");
+		return 0;
+	}
+
+	ret = ab8500_fg_inst_curr_finalize(di, &res);
+	if (ret) {
+		dev_err(di->dev, "Failed to finalize fg_inst\n");
+		return 0;
+	}
+
+	return res;
+}
+
+/**
+ * ab8500_fg_acc_cur_work() - average battery current
+ * @work:	pointer to the work_struct structure
+ *
+ * Updated the average battery current obtained from the
+ * coulomb counter.
+ */
+static void ab8500_fg_acc_cur_work(struct work_struct *work)
+{
+	int val;
+	int ret;
+	u8 low, med, high;
+
+	struct ab8500_fg *di = container_of(work,
+		struct ab8500_fg, fg_acc_cur_work);
+
+	mutex_lock(&di->cc_lock);
+	ret = abx500_set_register_interruptible(di->dev, AB8500_GAS_GAUGE,
+		AB8500_GASG_CC_NCOV_ACCU_CTRL, RD_NCONV_ACCU_REQ);
+	if (ret)
+		goto exit;
+
+	ret = abx500_get_register_interruptible(di->dev, AB8500_GAS_GAUGE,
+		AB8500_GASG_CC_NCOV_ACCU_LOW,  &low);
+	if (ret < 0)
+		goto exit;
+
+	ret = abx500_get_register_interruptible(di->dev, AB8500_GAS_GAUGE,
+		AB8500_GASG_CC_NCOV_ACCU_MED,  &med);
+	if (ret < 0)
+		goto exit;
+
+	ret = abx500_get_register_interruptible(di->dev, AB8500_GAS_GAUGE,
+		AB8500_GASG_CC_NCOV_ACCU_HIGH, &high);
+	if (ret < 0)
+		goto exit;
+
+	/* Check for sign bit in case of negative value, 2's compliment */
+	if (high & 0x10)
+		val = (low | (med << 8) | (high << 16) | 0xFFE00000);
+	else
+		val = (low | (med << 8) | (high << 16));
+
+	/*
+	 * Convert to uAh
+	 * Given a 250ms conversion cycle time the LSB corresponds
+	 * to 112.9 nAh.
+	 * 112.9nAh assumes 10mOhm, but fg_res is in 0.1mOhm
+	 */
+	di->accu_charge = (val * QLSB_NANO_AMP_HOURS_X10) /
+		(100 * di->bat->fg_res);
+
+	/*
+	 * Convert to unit value in mA
+	 * Full scale input voltage is
+	 * 66.660mV => LSB = 66.660mV/(4096*res) = 1.627mA
+	 * Given a 250ms conversion cycle time the LSB corresponds
+	 * to 112.9 nAh. Convert to current by dividing by the conversion
+	 * time in hours (= samples / (3600 * 4)h)
+	 * 112.9nAh assumes 10mOhm, but fg_res is in 0.1mOhm
+	 */
+	di->avg_curr = (val * QLSB_NANO_AMP_HOURS_X10 * 36) /
+		(1000 * di->bat->fg_res * (di->fg_samples / 4));
+
+	di->flags.conv_done = true;
+
+	mutex_unlock(&di->cc_lock);
+
+	queue_work(di->fg_wq, &di->fg_work);
+
+	return;
+exit:
+	dev_err(di->dev,
+		"Failed to read or write gas gauge registers\n");
+	mutex_unlock(&di->cc_lock);
+	queue_work(di->fg_wq, &di->fg_work);
+}
+
+/**
+ * ab8500_fg_bat_voltage() - get battery voltage
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Returns battery voltage(on success) else error code
+ */
+static int ab8500_fg_bat_voltage(struct ab8500_fg *di)
+{
+	int vbat;
+	static int prev;
+
+	vbat = ab8500_gpadc_convert(di->gpadc, MAIN_BAT_V);
+	if (vbat < 0) {
+		dev_err(di->dev,
+			"%s gpadc conversion failed, using previous value\n",
+			__func__);
+		return prev;
+	}
+
+	prev = vbat;
+	return vbat;
+}
+
+/**
+ * ab8500_fg_volt_to_capacity() - Voltage based capacity
+ * @di:		pointer to the ab8500_fg structure
+ * @voltage:	The voltage to convert to a capacity
+ *
+ * Returns battery capacity in per mille based on voltage
+ */
+static int ab8500_fg_volt_to_capacity(struct ab8500_fg *di, int voltage)
+{
+	int i, tbl_size;
+	struct abx500_v_to_cap *tbl;
+	int cap = 0;
+
+	tbl = di->bat->bat_type[di->bat->batt_id].v_to_cap_tbl,
+	tbl_size = di->bat->bat_type[di->bat->batt_id].n_v_cap_tbl_elements;
+
+	for (i = 0; i < tbl_size; ++i) {
+		if (voltage > tbl[i].voltage)
+			break;
+	}
+
+	if ((i > 0) && (i < tbl_size)) {
+		cap = interpolate(voltage,
+			tbl[i].voltage,
+			tbl[i].capacity * 10,
+			tbl[i-1].voltage,
+			tbl[i-1].capacity * 10);
+	} else if (i == 0) {
+		cap = 1000;
+	} else {
+		cap = 0;
+	}
+
+	dev_dbg(di->dev, "%s Vbat: %d, Cap: %d per mille",
+		__func__, voltage, cap);
+
+	return cap;
+}
+
+/**
+ * ab8500_fg_uncomp_volt_to_capacity() - Uncompensated voltage based capacity
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Returns battery capacity based on battery voltage that is not compensated
+ * for the voltage drop due to the load
+ */
+static int ab8500_fg_uncomp_volt_to_capacity(struct ab8500_fg *di)
+{
+	di->vbat = ab8500_fg_bat_voltage(di);
+	return ab8500_fg_volt_to_capacity(di, di->vbat);
+}
+
+/**
+ * ab8500_fg_battery_resistance() - Returns the battery inner resistance
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Returns battery inner resistance added with the fuel gauge resistor value
+ * to get the total resistance in the whole link from gnd to bat+ node.
+ */
+static int ab8500_fg_battery_resistance(struct ab8500_fg *di)
+{
+	int i, tbl_size;
+	struct batres_vs_temp *tbl;
+	int resist = 0;
+
+	tbl = di->bat->bat_type[di->bat->batt_id].batres_tbl;
+	tbl_size = di->bat->bat_type[di->bat->batt_id].n_batres_tbl_elements;
+
+	for (i = 0; i < tbl_size; ++i) {
+		if (di->bat_temp / 10 > tbl[i].temp)
+			break;
+	}
+
+	if ((i > 0) && (i < tbl_size)) {
+		resist = interpolate(di->bat_temp / 10,
+			tbl[i].temp,
+			tbl[i].resist,
+			tbl[i-1].temp,
+			tbl[i-1].resist);
+	} else if (i == 0) {
+		resist = tbl[0].resist;
+	} else {
+		resist = tbl[tbl_size - 1].resist;
+	}
+
+	dev_dbg(di->dev, "%s Temp: %d battery internal resistance: %d"
+	    " fg resistance %d, total: %d (mOhm)\n",
+		__func__, di->bat_temp, resist, di->bat->fg_res / 10,
+		(di->bat->fg_res / 10) + resist);
+
+	/* fg_res variable is in 0.1mOhm */
+	resist += di->bat->fg_res / 10;
+
+	return resist;
+}
+
+/**
+ * ab8500_fg_load_comp_volt_to_capacity() - Load compensated voltage based capacity
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Returns battery capacity based on battery voltage that is load compensated
+ * for the voltage drop
+ */
+static int ab8500_fg_load_comp_volt_to_capacity(struct ab8500_fg *di)
+{
+	int vbat_comp, res;
+	int i = 0;
+	int vbat = 0;
+
+	ab8500_fg_inst_curr_start(di);
+
+	do {
+		vbat += ab8500_fg_bat_voltage(di);
+		i++;
+		msleep(5);
+	} while (!ab8500_fg_inst_curr_done(di));
+
+	ab8500_fg_inst_curr_finalize(di, &di->inst_curr);
+
+	di->vbat = vbat / i;
+	res = ab8500_fg_battery_resistance(di);
+
+	/* Use Ohms law to get the load compensated voltage */
+	vbat_comp = di->vbat - (di->inst_curr * res) / 1000;
+
+	dev_dbg(di->dev, "%s Measured Vbat: %dmV,Compensated Vbat %dmV, "
+		"R: %dmOhm, Current: %dmA Vbat Samples: %d\n",
+		__func__, di->vbat, vbat_comp, res, di->inst_curr, i);
+
+	return ab8500_fg_volt_to_capacity(di, vbat_comp);
+}
+
+/**
+ * ab8500_fg_convert_mah_to_permille() - Capacity in mAh to permille
+ * @di:		pointer to the ab8500_fg structure
+ * @cap_mah:	capacity in mAh
+ *
+ * Converts capacity in mAh to capacity in permille
+ */
+static int ab8500_fg_convert_mah_to_permille(struct ab8500_fg *di, int cap_mah)
+{
+	return (cap_mah * 1000) / di->bat_cap.max_mah_design;
+}
+
+/**
+ * ab8500_fg_convert_permille_to_mah() - Capacity in permille to mAh
+ * @di:		pointer to the ab8500_fg structure
+ * @cap_pm:	capacity in permille
+ *
+ * Converts capacity in permille to capacity in mAh
+ */
+static int ab8500_fg_convert_permille_to_mah(struct ab8500_fg *di, int cap_pm)
+{
+	return cap_pm * di->bat_cap.max_mah_design / 1000;
+}
+
+/**
+ * ab8500_fg_convert_mah_to_uwh() - Capacity in mAh to uWh
+ * @di:		pointer to the ab8500_fg structure
+ * @cap_mah:	capacity in mAh
+ *
+ * Converts capacity in mAh to capacity in uWh
+ */
+static int ab8500_fg_convert_mah_to_uwh(struct ab8500_fg *di, int cap_mah)
+{
+	u64 div_res;
+	u32 div_rem;
+
+	div_res = ((u64) cap_mah) * ((u64) di->vbat_nom);
+	div_rem = do_div(div_res, 1000);
+
+	/* Make sure to round upwards if necessary */
+	if (div_rem >= 1000 / 2)
+		div_res++;
+
+	return (int) div_res;
+}
+
+/**
+ * ab8500_fg_calc_cap_charging() - Calculate remaining capacity while charging
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Return the capacity in mAh based on previous calculated capcity and the FG
+ * accumulator register value. The filter is filled with this capacity
+ */
+static int ab8500_fg_calc_cap_charging(struct ab8500_fg *di)
+{
+	dev_dbg(di->dev, "%s cap_mah %d accu_charge %d\n",
+		__func__,
+		di->bat_cap.mah,
+		di->accu_charge);
+
+	/* Capacity should not be less than 0 */
+	if (di->bat_cap.mah + di->accu_charge > 0)
+		di->bat_cap.mah += di->accu_charge;
+	else
+		di->bat_cap.mah = 0;
+	/*
+	 * We force capacity to 100% once when the algorithm
+	 * reports that it's full.
+	 */
+	if (di->bat_cap.mah >= di->bat_cap.max_mah_design ||
+		di->flags.force_full) {
+		di->bat_cap.mah = di->bat_cap.max_mah_design;
+	}
+
+	ab8500_fg_fill_cap_sample(di, di->bat_cap.mah);
+	di->bat_cap.permille =
+		ab8500_fg_convert_mah_to_permille(di, di->bat_cap.mah);
+
+	/* We need to update battery voltage and inst current when charging */
+	di->vbat = ab8500_fg_bat_voltage(di);
+	di->inst_curr = ab8500_fg_inst_curr_blocking(di);
+
+	return di->bat_cap.mah;
+}
+
+/**
+ * ab8500_fg_calc_cap_discharge_voltage() - Capacity in discharge with voltage
+ * @di:		pointer to the ab8500_fg structure
+ * @comp:	if voltage should be load compensated before capacity calc
+ *
+ * Return the capacity in mAh based on the battery voltage. The voltage can
+ * either be load compensated or not. This value is added to the filter and a
+ * new mean value is calculated and returned.
+ */
+static int ab8500_fg_calc_cap_discharge_voltage(struct ab8500_fg *di, bool comp)
+{
+	int permille, mah;
+
+	if (comp)
+		permille = ab8500_fg_load_comp_volt_to_capacity(di);
+	else
+		permille = ab8500_fg_uncomp_volt_to_capacity(di);
+
+	mah = ab8500_fg_convert_permille_to_mah(di, permille);
+
+	di->bat_cap.mah = ab8500_fg_add_cap_sample(di, mah);
+	di->bat_cap.permille =
+		ab8500_fg_convert_mah_to_permille(di, di->bat_cap.mah);
+
+	return di->bat_cap.mah;
+}
+
+/**
+ * ab8500_fg_calc_cap_discharge_fg() - Capacity in discharge with FG
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Return the capacity in mAh based on previous calculated capcity and the FG
+ * accumulator register value. This value is added to the filter and a
+ * new mean value is calculated and returned.
+ */
+static int ab8500_fg_calc_cap_discharge_fg(struct ab8500_fg *di)
+{
+	int permille_volt, permille;
+
+	dev_dbg(di->dev, "%s cap_mah %d accu_charge %d\n",
+		__func__,
+		di->bat_cap.mah,
+		di->accu_charge);
+
+	/* Capacity should not be less than 0 */
+	if (di->bat_cap.mah + di->accu_charge > 0)
+		di->bat_cap.mah += di->accu_charge;
+	else
+		di->bat_cap.mah = 0;
+
+	if (di->bat_cap.mah >= di->bat_cap.max_mah_design)
+		di->bat_cap.mah = di->bat_cap.max_mah_design;
+
+	/*
+	 * Check against voltage based capacity. It can not be lower
+	 * than what the uncompensated voltage says
+	 */
+	permille = ab8500_fg_convert_mah_to_permille(di, di->bat_cap.mah);
+	permille_volt = ab8500_fg_uncomp_volt_to_capacity(di);
+
+	if (permille < permille_volt) {
+		di->bat_cap.permille = permille_volt;
+		di->bat_cap.mah = ab8500_fg_convert_permille_to_mah(di,
+			di->bat_cap.permille);
+
+		dev_dbg(di->dev, "%s voltage based: perm %d perm_volt %d\n",
+			__func__,
+			permille,
+			permille_volt);
+
+		ab8500_fg_fill_cap_sample(di, di->bat_cap.mah);
+	} else {
+		ab8500_fg_fill_cap_sample(di, di->bat_cap.mah);
+		di->bat_cap.permille =
+			ab8500_fg_convert_mah_to_permille(di, di->bat_cap.mah);
+	}
+
+	return di->bat_cap.mah;
+}
+
+/**
+ * ab8500_fg_capacity_level() - Get the battery capacity level
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Get the battery capacity level based on the capacity in percent
+ */
+static int ab8500_fg_capacity_level(struct ab8500_fg *di)
+{
+	int ret, percent;
+
+	percent = di->bat_cap.permille / 10;
+
+	if (percent <= di->bat->cap_levels->critical ||
+		di->flags.low_bat)
+		ret = POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL;
+	else if (percent <= di->bat->cap_levels->low)
+		ret = POWER_SUPPLY_CAPACITY_LEVEL_LOW;
+	else if (percent <= di->bat->cap_levels->normal)
+		ret = POWER_SUPPLY_CAPACITY_LEVEL_NORMAL;
+	else if (percent <= di->bat->cap_levels->high)
+		ret = POWER_SUPPLY_CAPACITY_LEVEL_HIGH;
+	else
+		ret = POWER_SUPPLY_CAPACITY_LEVEL_FULL;
+
+	return ret;
+}
+
+/**
+ * ab8500_fg_check_capacity_limits() - Check if capacity has changed
+ * @di:		pointer to the ab8500_fg structure
+ * @init:	capacity is allowed to go up in init mode
+ *
+ * Check if capacity or capacity limit has changed and notify the system
+ * about it using the power_supply framework
+ */
+static void ab8500_fg_check_capacity_limits(struct ab8500_fg *di, bool init)
+{
+	bool changed = false;
+
+	di->bat_cap.level = ab8500_fg_capacity_level(di);
+
+	if (di->bat_cap.level != di->bat_cap.prev_level) {
+		/*
+		 * We do not allow reported capacity level to go up
+		 * unless we're charging or if we're in init
+		 */
+		if (!(!di->flags.charging && di->bat_cap.level >
+			di->bat_cap.prev_level) || init) {
+			dev_dbg(di->dev, "level changed from %d to %d\n",
+				di->bat_cap.prev_level,
+				di->bat_cap.level);
+			di->bat_cap.prev_level = di->bat_cap.level;
+			changed = true;
+		} else {
+			dev_dbg(di->dev, "level not allowed to go up "
+				"since no charger is connected: %d to %d\n",
+				di->bat_cap.prev_level,
+				di->bat_cap.level);
+		}
+	}
+
+	/*
+	 * If we have received the LOW_BAT IRQ, set capacity to 0 to initiate
+	 * shutdown
+	 */
+	if (di->flags.low_bat) {
+		dev_dbg(di->dev, "Battery low, set capacity to 0\n");
+		di->bat_cap.prev_percent = 0;
+		di->bat_cap.permille = 0;
+		di->bat_cap.prev_mah = 0;
+		di->bat_cap.mah = 0;
+		changed = true;
+	} else if (di->flags.fully_charged) {
+		/*
+		 * We report 100% if algorithm reported fully charged
+		 * unless capacity drops too much
+		 */
+		if (di->flags.force_full) {
+			di->bat_cap.prev_percent = di->bat_cap.permille / 10;
+			di->bat_cap.prev_mah = di->bat_cap.mah;
+		} else if (!di->flags.force_full &&
+			di->bat_cap.prev_percent !=
+			(di->bat_cap.permille) / 10 &&
+			(di->bat_cap.permille / 10) <
+			di->bat->fg_params->maint_thres) {
+			dev_dbg(di->dev,
+				"battery reported full "
+				"but capacity dropping: %d\n",
+				di->bat_cap.permille / 10);
+			di->bat_cap.prev_percent = di->bat_cap.permille / 10;
+			di->bat_cap.prev_mah = di->bat_cap.mah;
+
+			changed = true;
+		}
+	} else if (di->bat_cap.prev_percent != di->bat_cap.permille / 10) {
+		if (di->bat_cap.permille / 10 == 0) {
+			/*
+			 * We will not report 0% unless we've got
+			 * the LOW_BAT IRQ, no matter what the FG
+			 * algorithm says.
+			 */
+			di->bat_cap.prev_percent = 1;
+			di->bat_cap.permille = 1;
+			di->bat_cap.prev_mah = 1;
+			di->bat_cap.mah = 1;
+
+			changed = true;
+		} else if (!(!di->flags.charging &&
+			(di->bat_cap.permille / 10) >
+			di->bat_cap.prev_percent) || init) {
+			/*
+			 * We do not allow reported capacity to go up
+			 * unless we're charging or if we're in init
+			 */
+			dev_dbg(di->dev,
+				"capacity changed from %d to %d (%d)\n",
+				di->bat_cap.prev_percent,
+				di->bat_cap.permille / 10,
+				di->bat_cap.permille);
+			di->bat_cap.prev_percent = di->bat_cap.permille / 10;
+			di->bat_cap.prev_mah = di->bat_cap.mah;
+
+			changed = true;
+		} else {
+			dev_dbg(di->dev, "capacity not allowed to go up since "
+				"no charger is connected: %d to %d (%d)\n",
+				di->bat_cap.prev_percent,
+				di->bat_cap.permille / 10,
+				di->bat_cap.permille);
+		}
+	}
+
+	if (changed) {
+		power_supply_changed(&di->fg_psy);
+		if (di->flags.fully_charged && di->flags.force_full) {
+			dev_dbg(di->dev, "Battery full, notifying.\n");
+			di->flags.force_full = false;
+			sysfs_notify(&di->fg_kobject, NULL, "charge_full");
+		}
+		sysfs_notify(&di->fg_kobject, NULL, "charge_now");
+	}
+}
+
+static void ab8500_fg_charge_state_to(struct ab8500_fg *di,
+	enum ab8500_fg_charge_state new_state)
+{
+	dev_dbg(di->dev, "Charge state from %d [%s] to %d [%s]\n",
+		di->charge_state,
+		charge_state[di->charge_state],
+		new_state,
+		charge_state[new_state]);
+
+	di->charge_state = new_state;
+}
+
+static void ab8500_fg_discharge_state_to(struct ab8500_fg *di,
+	enum ab8500_fg_discharge_state new_state)
+{
+	dev_dbg(di->dev, "Disharge state from %d [%s] to %d [%s]\n",
+		di->discharge_state,
+		discharge_state[di->discharge_state],
+		new_state,
+		discharge_state[new_state]);
+
+	di->discharge_state = new_state;
+}
+
+/**
+ * ab8500_fg_algorithm_charging() - FG algorithm for when charging
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Battery capacity calculation state machine for when we're charging
+ */
+static void ab8500_fg_algorithm_charging(struct ab8500_fg *di)
+{
+	/*
+	 * If we change to discharge mode
+	 * we should start with recovery
+	 */
+	if (di->discharge_state != AB8500_FG_DISCHARGE_INIT_RECOVERY)
+		ab8500_fg_discharge_state_to(di,
+			AB8500_FG_DISCHARGE_INIT_RECOVERY);
+
+	switch (di->charge_state) {
+	case AB8500_FG_CHARGE_INIT:
+		di->fg_samples = SEC_TO_SAMPLE(
+			di->bat->fg_params->accu_charging);
+
+		ab8500_fg_coulomb_counter(di, true);
+		ab8500_fg_charge_state_to(di, AB8500_FG_CHARGE_READOUT);
+
+		break;
+
+	case AB8500_FG_CHARGE_READOUT:
+		/*
+		 * Read the FG and calculate the new capacity
+		 */
+		mutex_lock(&di->cc_lock);
+		if (!di->flags.conv_done) {
+			/* Wasn't the CC IRQ that got us here */
+			mutex_unlock(&di->cc_lock);
+			dev_dbg(di->dev, "%s CC conv not done\n",
+				__func__);
+
+			break;
+		}
+		di->flags.conv_done = false;
+		mutex_unlock(&di->cc_lock);
+
+		ab8500_fg_calc_cap_charging(di);
+
+		break;
+
+	default:
+		break;
+	}
+
+	/* Check capacity limits */
+	ab8500_fg_check_capacity_limits(di, false);
+}
+
+static void force_capacity(struct ab8500_fg *di)
+{
+	int cap;
+
+	ab8500_fg_clear_cap_samples(di);
+	cap = di->bat_cap.user_mah;
+	if (cap > di->bat_cap.max_mah_design) {
+		dev_dbg(di->dev, "Remaining cap %d can't be bigger than total"
+			" %d\n", cap, di->bat_cap.max_mah_design);
+		cap = di->bat_cap.max_mah_design;
+	}
+	ab8500_fg_fill_cap_sample(di, di->bat_cap.user_mah);
+	di->bat_cap.permille = ab8500_fg_convert_mah_to_permille(di, cap);
+	di->bat_cap.mah = cap;
+	ab8500_fg_check_capacity_limits(di, true);
+}
+
+static bool check_sysfs_capacity(struct ab8500_fg *di)
+{
+	int cap, lower, upper;
+	int cap_permille;
+
+	cap = di->bat_cap.user_mah;
+
+	cap_permille = ab8500_fg_convert_mah_to_permille(di,
+		di->bat_cap.user_mah);
+
+	lower = di->bat_cap.permille - di->bat->fg_params->user_cap_limit * 10;
+	upper = di->bat_cap.permille + di->bat->fg_params->user_cap_limit * 10;
+
+	if (lower < 0)
+		lower = 0;
+	/* 1000 is permille, -> 100 percent */
+	if (upper > 1000)
+		upper = 1000;
+
+	dev_dbg(di->dev, "Capacity limits:"
+		" (Lower: %d User: %d Upper: %d) [user: %d, was: %d]\n",
+		lower, cap_permille, upper, cap, di->bat_cap.mah);
+
+	/* If within limits, use the saved capacity and exit estimation...*/
+	if (cap_permille > lower && cap_permille < upper) {
+		dev_dbg(di->dev, "OK! Using users cap %d uAh now\n", cap);
+		force_capacity(di);
+		return true;
+	}
+	dev_dbg(di->dev, "Capacity from user out of limits, ignoring");
+	return false;
+}
+
+/**
+ * ab8500_fg_algorithm_discharging() - FG algorithm for when discharging
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Battery capacity calculation state machine for when we're discharging
+ */
+static void ab8500_fg_algorithm_discharging(struct ab8500_fg *di)
+{
+	int sleep_time;
+
+	/* If we change to charge mode we should start with init */
+	if (di->charge_state != AB8500_FG_CHARGE_INIT)
+		ab8500_fg_charge_state_to(di, AB8500_FG_CHARGE_INIT);
+
+	switch (di->discharge_state) {
+	case AB8500_FG_DISCHARGE_INIT:
+		/* We use the FG IRQ to work on */
+		di->init_cnt = 0;
+		di->fg_samples = SEC_TO_SAMPLE(di->bat->fg_params->init_timer);
+		ab8500_fg_coulomb_counter(di, true);
+		ab8500_fg_discharge_state_to(di,
+			AB8500_FG_DISCHARGE_INITMEASURING);
+
+		/* Intentional fallthrough */
+	case AB8500_FG_DISCHARGE_INITMEASURING:
+		/*
+		 * Discard a number of samples during startup.
+		 * After that, use compensated voltage for a few
+		 * samples to get an initial capacity.
+		 * Then go to READOUT
+		 */
+		sleep_time = di->bat->fg_params->init_timer;
+
+		/* Discard the first [x] seconds */
+		if (di->init_cnt >
+			di->bat->fg_params->init_discard_time) {
+			ab8500_fg_calc_cap_discharge_voltage(di, true);
+
+			ab8500_fg_check_capacity_limits(di, true);
+		}
+
+		di->init_cnt += sleep_time;
+		if (di->init_cnt > di->bat->fg_params->init_total_time)
+			ab8500_fg_discharge_state_to(di,
+				AB8500_FG_DISCHARGE_READOUT_INIT);
+
+		break;
+
+	case AB8500_FG_DISCHARGE_INIT_RECOVERY:
+		di->recovery_cnt = 0;
+		di->recovery_needed = true;
+		ab8500_fg_discharge_state_to(di,
+			AB8500_FG_DISCHARGE_RECOVERY);
+
+		/* Intentional fallthrough */
+
+	case AB8500_FG_DISCHARGE_RECOVERY:
+		sleep_time = di->bat->fg_params->recovery_sleep_timer;
+
+		/*
+		 * We should check the power consumption
+		 * If low, go to READOUT (after x min) or
+		 * RECOVERY_SLEEP if time left.
+		 * If high, go to READOUT
+		 */
+		di->inst_curr = ab8500_fg_inst_curr_blocking(di);
+
+		if (ab8500_fg_is_low_curr(di, di->inst_curr)) {
+			if (di->recovery_cnt >
+				di->bat->fg_params->recovery_total_time) {
+				di->fg_samples = SEC_TO_SAMPLE(
+					di->bat->fg_params->accu_high_curr);
+				ab8500_fg_coulomb_counter(di, true);
+				ab8500_fg_discharge_state_to(di,
+					AB8500_FG_DISCHARGE_READOUT);
+				di->recovery_needed = false;
+			} else {
+				queue_delayed_work(di->fg_wq,
+					&di->fg_periodic_work,
+					sleep_time * HZ);
+			}
+			di->recovery_cnt += sleep_time;
+		} else {
+			di->fg_samples = SEC_TO_SAMPLE(
+				di->bat->fg_params->accu_high_curr);
+			ab8500_fg_coulomb_counter(di, true);
+			ab8500_fg_discharge_state_to(di,
+				AB8500_FG_DISCHARGE_READOUT);
+		}
+		break;
+
+	case AB8500_FG_DISCHARGE_READOUT_INIT:
+		di->fg_samples = SEC_TO_SAMPLE(
+			di->bat->fg_params->accu_high_curr);
+		ab8500_fg_coulomb_counter(di, true);
+		ab8500_fg_discharge_state_to(di,
+				AB8500_FG_DISCHARGE_READOUT);
+		break;
+
+	case AB8500_FG_DISCHARGE_READOUT:
+		di->inst_curr = ab8500_fg_inst_curr_blocking(di);
+
+		if (ab8500_fg_is_low_curr(di, di->inst_curr)) {
+			/* Detect mode change */
+			if (di->high_curr_mode) {
+				di->high_curr_mode = false;
+				di->high_curr_cnt = 0;
+			}
+
+			if (di->recovery_needed) {
+				ab8500_fg_discharge_state_to(di,
+					AB8500_FG_DISCHARGE_RECOVERY);
+
+				queue_delayed_work(di->fg_wq,
+					&di->fg_periodic_work, 0);
+
+				break;
+			}
+
+			ab8500_fg_calc_cap_discharge_voltage(di, true);
+		} else {
+			mutex_lock(&di->cc_lock);
+			if (!di->flags.conv_done) {
+				/* Wasn't the CC IRQ that got us here */
+				mutex_unlock(&di->cc_lock);
+				dev_dbg(di->dev, "%s CC conv not done\n",
+					__func__);
+
+				break;
+			}
+			di->flags.conv_done = false;
+			mutex_unlock(&di->cc_lock);
+
+			/* Detect mode change */
+			if (!di->high_curr_mode) {
+				di->high_curr_mode = true;
+				di->high_curr_cnt = 0;
+			}
+
+			di->high_curr_cnt +=
+				di->bat->fg_params->accu_high_curr;
+			if (di->high_curr_cnt >
+				di->bat->fg_params->high_curr_time)
+				di->recovery_needed = true;
+
+			ab8500_fg_calc_cap_discharge_fg(di);
+		}
+
+		ab8500_fg_check_capacity_limits(di, false);
+
+		break;
+
+	case AB8500_FG_DISCHARGE_WAKEUP:
+		ab8500_fg_coulomb_counter(di, true);
+		di->inst_curr = ab8500_fg_inst_curr_blocking(di);
+
+		ab8500_fg_calc_cap_discharge_voltage(di, true);
+
+		di->fg_samples = SEC_TO_SAMPLE(
+			di->bat->fg_params->accu_high_curr);
+		ab8500_fg_coulomb_counter(di, true);
+		ab8500_fg_discharge_state_to(di,
+				AB8500_FG_DISCHARGE_READOUT);
+
+		ab8500_fg_check_capacity_limits(di, false);
+
+		break;
+
+	default:
+		break;
+	}
+}
+
+/**
+ * ab8500_fg_algorithm_calibrate() - Internal columb counter offset calibration
+ * @di:		pointer to the ab8500_fg structure
+ *
+ */
+static void ab8500_fg_algorithm_calibrate(struct ab8500_fg *di)
+{
+	int ret;
+
+	switch (di->calib_state) {
+	case AB8500_FG_CALIB_INIT:
+		dev_dbg(di->dev, "Calibration ongoing...\n");
+
+		ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_CTRL_REG,
+			CC_INT_CAL_N_AVG_MASK, CC_INT_CAL_SAMPLES_8);
+		if (ret < 0)
+			goto err;
+
+		ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_CTRL_REG,
+			CC_INTAVGOFFSET_ENA, CC_INTAVGOFFSET_ENA);
+		if (ret < 0)
+			goto err;
+		di->calib_state = AB8500_FG_CALIB_WAIT;
+		break;
+	case AB8500_FG_CALIB_END:
+		ret = abx500_mask_and_set_register_interruptible(di->dev,
+			AB8500_GAS_GAUGE, AB8500_GASG_CC_CTRL_REG,
+			CC_MUXOFFSET, CC_MUXOFFSET);
+		if (ret < 0)
+			goto err;
+		di->flags.calibrate = false;
+		dev_dbg(di->dev, "Calibration done...\n");
+		queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+		break;
+	case AB8500_FG_CALIB_WAIT:
+		dev_dbg(di->dev, "Calibration WFI\n");
+	default:
+		break;
+	}
+	return;
+err:
+	/* Something went wrong, don't calibrate then */
+	dev_err(di->dev, "failed to calibrate the CC\n");
+	di->flags.calibrate = false;
+	di->calib_state = AB8500_FG_CALIB_INIT;
+	queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+}
+
+/**
+ * ab8500_fg_algorithm() - Entry point for the FG algorithm
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Entry point for the battery capacity calculation state machine
+ */
+static void ab8500_fg_algorithm(struct ab8500_fg *di)
+{
+	if (di->flags.calibrate)
+		ab8500_fg_algorithm_calibrate(di);
+	else {
+		if (di->flags.charging)
+			ab8500_fg_algorithm_charging(di);
+		else
+			ab8500_fg_algorithm_discharging(di);
+	}
+
+	dev_dbg(di->dev, "[FG_DATA] %d %d %d %d %d %d %d %d %d "
+		"%d %d %d %d %d %d %d\n",
+		di->bat_cap.max_mah_design,
+		di->bat_cap.mah,
+		di->bat_cap.permille,
+		di->bat_cap.level,
+		di->bat_cap.prev_mah,
+		di->bat_cap.prev_percent,
+		di->bat_cap.prev_level,
+		di->vbat,
+		di->inst_curr,
+		di->avg_curr,
+		di->accu_charge,
+		di->flags.charging,
+		di->charge_state,
+		di->discharge_state,
+		di->high_curr_mode,
+		di->recovery_needed);
+}
+
+/**
+ * ab8500_fg_periodic_work() - Run the FG state machine periodically
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for periodic work
+ */
+static void ab8500_fg_periodic_work(struct work_struct *work)
+{
+	struct ab8500_fg *di = container_of(work, struct ab8500_fg,
+		fg_periodic_work.work);
+
+	if (di->init_capacity) {
+		/* A dummy read that will return 0 */
+		di->inst_curr = ab8500_fg_inst_curr_blocking(di);
+		/* Get an initial capacity calculation */
+		ab8500_fg_calc_cap_discharge_voltage(di, true);
+		ab8500_fg_check_capacity_limits(di, true);
+		di->init_capacity = false;
+
+		queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+	} else if (di->flags.user_cap) {
+		if (check_sysfs_capacity(di)) {
+			ab8500_fg_check_capacity_limits(di, true);
+			if (di->flags.charging)
+				ab8500_fg_charge_state_to(di,
+					AB8500_FG_CHARGE_INIT);
+			else
+				ab8500_fg_discharge_state_to(di,
+					AB8500_FG_DISCHARGE_READOUT_INIT);
+		}
+		di->flags.user_cap = false;
+		queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+	} else
+		ab8500_fg_algorithm(di);
+
+}
+
+/**
+ * ab8500_fg_check_hw_failure_work() - Check OVV_BAT condition
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for checking the OVV_BAT condition
+ */
+static void ab8500_fg_check_hw_failure_work(struct work_struct *work)
+{
+	int ret;
+	u8 reg_value;
+
+	struct ab8500_fg *di = container_of(work, struct ab8500_fg,
+		fg_check_hw_failure_work.work);
+
+	/*
+	 * If we have had a battery over-voltage situation,
+	 * check ovv-bit to see if it should be reset.
+	 */
+	if (di->flags.bat_ovv) {
+		ret = abx500_get_register_interruptible(di->dev,
+			AB8500_CHARGER, AB8500_CH_STAT_REG,
+			&reg_value);
+		if (ret < 0) {
+			dev_err(di->dev, "%s ab8500 read failed\n", __func__);
+			return;
+		}
+		if ((reg_value & BATT_OVV) != BATT_OVV) {
+			dev_dbg(di->dev, "Battery recovered from OVV\n");
+			di->flags.bat_ovv = false;
+			power_supply_changed(&di->fg_psy);
+			return;
+		}
+
+		/* Not yet recovered from ovv, reschedule this test */
+		queue_delayed_work(di->fg_wq, &di->fg_check_hw_failure_work,
+				   round_jiffies(HZ));
+	}
+}
+
+/**
+ * ab8500_fg_low_bat_work() - Check LOW_BAT condition
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for checking the LOW_BAT condition
+ */
+static void ab8500_fg_low_bat_work(struct work_struct *work)
+{
+	int vbat;
+
+	struct ab8500_fg *di = container_of(work, struct ab8500_fg,
+		fg_low_bat_work.work);
+
+	vbat = ab8500_fg_bat_voltage(di);
+
+	/* Check if LOW_BAT still fulfilled */
+	if (vbat < di->bat->fg_params->lowbat_threshold) {
+		di->flags.low_bat = true;
+		dev_warn(di->dev, "Battery voltage still LOW\n");
+
+		/*
+		 * We need to re-schedule this check to be able to detect
+		 * if the voltage increases again during charging
+		 */
+		queue_delayed_work(di->fg_wq, &di->fg_low_bat_work,
+			round_jiffies(LOW_BAT_CHECK_INTERVAL));
+	} else {
+		di->flags.low_bat = false;
+		dev_warn(di->dev, "Battery voltage OK again\n");
+	}
+
+	/* This is needed to dispatch LOW_BAT */
+	ab8500_fg_check_capacity_limits(di, false);
+
+	/* Set this flag to check if LOW_BAT IRQ still occurs */
+	di->flags.low_bat_delay = false;
+}
+
+/**
+ * ab8500_fg_battok_calc - calculate the bit pattern corresponding
+ * to the target voltage.
+ * @di:       pointer to the ab8500_fg structure
+ * @target    target voltage
+ *
+ * Returns bit pattern closest to the target voltage
+ * valid return values are 0-14. (0-BATT_OK_MAX_NR_INCREMENTS)
+ */
+
+static int ab8500_fg_battok_calc(struct ab8500_fg *di, int target)
+{
+	if (target > BATT_OK_MIN +
+		(BATT_OK_INCREMENT * BATT_OK_MAX_NR_INCREMENTS))
+		return BATT_OK_MAX_NR_INCREMENTS;
+	if (target < BATT_OK_MIN)
+		return 0;
+	return (target - BATT_OK_MIN) / BATT_OK_INCREMENT;
+}
+
+/**
+ * ab8500_fg_battok_init_hw_register - init battok levels
+ * @di:       pointer to the ab8500_fg structure
+ *
+ */
+
+static int ab8500_fg_battok_init_hw_register(struct ab8500_fg *di)
+{
+	int selected;
+	int sel0;
+	int sel1;
+	int cbp_sel0;
+	int cbp_sel1;
+	int ret;
+	int new_val;
+
+	sel0 = di->bat->fg_params->battok_falling_th_sel0;
+	sel1 = di->bat->fg_params->battok_raising_th_sel1;
+
+	cbp_sel0 = ab8500_fg_battok_calc(di, sel0);
+	cbp_sel1 = ab8500_fg_battok_calc(di, sel1);
+
+	selected = BATT_OK_MIN + cbp_sel0 * BATT_OK_INCREMENT;
+
+	if (selected != sel0)
+		dev_warn(di->dev, "Invalid voltage step:%d, using %d %d\n",
+			sel0, selected, cbp_sel0);
+
+	selected = BATT_OK_MIN + cbp_sel1 * BATT_OK_INCREMENT;
+
+	if (selected != sel1)
+		dev_warn(di->dev, "Invalid voltage step:%d, using %d %d\n",
+			sel1, selected, cbp_sel1);
+
+	new_val = cbp_sel0 | (cbp_sel1 << 4);
+
+	dev_dbg(di->dev, "using: %x %d %d\n", new_val, cbp_sel0, cbp_sel1);
+	ret = abx500_set_register_interruptible(di->dev, AB8500_SYS_CTRL2_BLOCK,
+		AB8500_BATT_OK_REG, new_val);
+	return ret;
+}
+
+/**
+ * ab8500_fg_instant_work() - Run the FG state machine instantly
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for instant work
+ */
+static void ab8500_fg_instant_work(struct work_struct *work)
+{
+	struct ab8500_fg *di = container_of(work, struct ab8500_fg, fg_work);
+
+	ab8500_fg_algorithm(di);
+}
+
+/**
+ * ab8500_fg_cc_data_end_handler() - isr to get battery avg current.
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_fg structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_fg_cc_data_end_handler(int irq, void *_di)
+{
+	struct ab8500_fg *di = _di;
+	complete(&di->ab8500_fg_complete);
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_fg_cc_convend_handler() - isr to get battery avg current.
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_fg structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_fg_cc_int_calib_handler(int irq, void *_di)
+{
+	struct ab8500_fg *di = _di;
+	di->calib_state = AB8500_FG_CALIB_END;
+	queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_fg_cc_convend_handler() - isr to get battery avg current.
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_fg structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_fg_cc_convend_handler(int irq, void *_di)
+{
+	struct ab8500_fg *di = _di;
+
+	queue_work(di->fg_wq, &di->fg_acc_cur_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_fg_batt_ovv_handler() - Battery OVV occured
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_fg structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_fg_batt_ovv_handler(int irq, void *_di)
+{
+	struct ab8500_fg *di = _di;
+
+	dev_dbg(di->dev, "Battery OVV\n");
+	di->flags.bat_ovv = true;
+	power_supply_changed(&di->fg_psy);
+
+	/* Schedule a new HW failure check */
+	queue_delayed_work(di->fg_wq, &di->fg_check_hw_failure_work, 0);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_fg_lowbatf_handler() - Battery voltage is below LOW threshold
+ * @irq:       interrupt number
+ * @_di:       pointer to the ab8500_fg structure
+ *
+ * Returns IRQ status(IRQ_HANDLED)
+ */
+static irqreturn_t ab8500_fg_lowbatf_handler(int irq, void *_di)
+{
+	struct ab8500_fg *di = _di;
+
+	if (!di->flags.low_bat_delay) {
+		dev_warn(di->dev, "Battery voltage is below LOW threshold\n");
+		di->flags.low_bat_delay = true;
+		/*
+		 * Start a timer to check LOW_BAT again after some time
+		 * This is done to avoid shutdown on single voltage dips
+		 */
+		queue_delayed_work(di->fg_wq, &di->fg_low_bat_work,
+			round_jiffies(LOW_BAT_CHECK_INTERVAL));
+	}
+	return IRQ_HANDLED;
+}
+
+/**
+ * ab8500_fg_get_property() - get the fg properties
+ * @psy:	pointer to the power_supply structure
+ * @psp:	pointer to the power_supply_property structure
+ * @val:	pointer to the power_supply_propval union
+ *
+ * This function gets called when an application tries to get the
+ * fg properties by reading the sysfs files.
+ * voltage_now:		battery voltage
+ * current_now:		battery instant current
+ * current_avg:		battery average current
+ * charge_full_design:	capacity where battery is considered full
+ * charge_now:		battery capacity in nAh
+ * capacity:		capacity in percent
+ * capacity_level:	capacity level
+ *
+ * Returns error code in case of failure else 0 on success
+ */
+static int ab8500_fg_get_property(struct power_supply *psy,
+	enum power_supply_property psp,
+	union power_supply_propval *val)
+{
+	struct ab8500_fg *di;
+
+	di = to_ab8500_fg_device_info(psy);
+
+	/*
+	 * If battery is identified as unknown and charging of unknown
+	 * batteries is disabled, we always report 100% capacity and
+	 * capacity level UNKNOWN, since we can't calculate
+	 * remaining capacity
+	 */
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		if (di->flags.bat_ovv)
+			val->intval = BATT_OVV_VALUE * 1000;
+		else
+			val->intval = di->vbat * 1000;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		val->intval = di->inst_curr * 1000;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_AVG:
+		val->intval = di->avg_curr * 1000;
+		break;
+	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
+		val->intval = ab8500_fg_convert_mah_to_uwh(di,
+				di->bat_cap.max_mah_design);
+		break;
+	case POWER_SUPPLY_PROP_ENERGY_FULL:
+		val->intval = ab8500_fg_convert_mah_to_uwh(di,
+				di->bat_cap.max_mah);
+		break;
+	case POWER_SUPPLY_PROP_ENERGY_NOW:
+		if (di->flags.batt_unknown && !di->bat->chg_unknown_bat &&
+				di->flags.batt_id_received)
+			val->intval = ab8500_fg_convert_mah_to_uwh(di,
+					di->bat_cap.max_mah);
+		else
+			val->intval = ab8500_fg_convert_mah_to_uwh(di,
+					di->bat_cap.prev_mah);
+		break;
+	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
+		val->intval = di->bat_cap.max_mah_design;
+		break;
+	case POWER_SUPPLY_PROP_CHARGE_FULL:
+		val->intval = di->bat_cap.max_mah;
+		break;
+	case POWER_SUPPLY_PROP_CHARGE_NOW:
+		if (di->flags.batt_unknown && !di->bat->chg_unknown_bat &&
+				di->flags.batt_id_received)
+			val->intval = di->bat_cap.max_mah;
+		else
+			val->intval = di->bat_cap.prev_mah;
+		break;
+	case POWER_SUPPLY_PROP_CAPACITY:
+		if (di->flags.batt_unknown && !di->bat->chg_unknown_bat &&
+				di->flags.batt_id_received)
+			val->intval = 100;
+		else
+			val->intval = di->bat_cap.prev_percent;
+		break;
+	case POWER_SUPPLY_PROP_CAPACITY_LEVEL:
+		if (di->flags.batt_unknown && !di->bat->chg_unknown_bat &&
+				di->flags.batt_id_received)
+			val->intval = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN;
+		else
+			val->intval = di->bat_cap.prev_level;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data)
+{
+	struct power_supply *psy;
+	struct power_supply *ext;
+	struct ab8500_fg *di;
+	union power_supply_propval ret;
+	int i, j;
+	bool psy_found = false;
+
+	psy = (struct power_supply *)data;
+	ext = dev_get_drvdata(dev);
+	di = to_ab8500_fg_device_info(psy);
+
+	/*
+	 * For all psy where the name of your driver
+	 * appears in any supplied_to
+	 */
+	for (i = 0; i < ext->num_supplicants; i++) {
+		if (!strcmp(ext->supplied_to[i], psy->name))
+			psy_found = true;
+	}
+
+	if (!psy_found)
+		return 0;
+
+	/* Go through all properties for the psy */
+	for (j = 0; j < ext->num_properties; j++) {
+		enum power_supply_property prop;
+		prop = ext->properties[j];
+
+		if (ext->get_property(ext, prop, &ret))
+			continue;
+
+		switch (prop) {
+		case POWER_SUPPLY_PROP_STATUS:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				switch (ret.intval) {
+				case POWER_SUPPLY_STATUS_UNKNOWN:
+				case POWER_SUPPLY_STATUS_DISCHARGING:
+				case POWER_SUPPLY_STATUS_NOT_CHARGING:
+					if (!di->flags.charging)
+						break;
+					di->flags.charging = false;
+					di->flags.fully_charged = false;
+					queue_work(di->fg_wq, &di->fg_work);
+					break;
+				case POWER_SUPPLY_STATUS_FULL:
+					if (di->flags.fully_charged)
+						break;
+					di->flags.fully_charged = true;
+					di->flags.force_full = true;
+					/* Save current capacity as maximum */
+					di->bat_cap.max_mah = di->bat_cap.mah;
+					queue_work(di->fg_wq, &di->fg_work);
+					break;
+				case POWER_SUPPLY_STATUS_CHARGING:
+					if (di->flags.charging)
+						break;
+					di->flags.charging = true;
+					di->flags.fully_charged = false;
+					queue_work(di->fg_wq, &di->fg_work);
+					break;
+				};
+			default:
+				break;
+			};
+			break;
+		case POWER_SUPPLY_PROP_TECHNOLOGY:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				if (!di->flags.batt_id_received) {
+					const struct abx500_battery_type *b;
+
+					b = &(di->bat->bat_type[di->bat->batt_id]);
+
+					di->flags.batt_id_received = true;
+
+					di->bat_cap.max_mah_design =
+						MILLI_TO_MICRO *
+						b->charge_full_design;
+
+					di->bat_cap.max_mah =
+						di->bat_cap.max_mah_design;
+
+					di->vbat_nom = b->nominal_voltage;
+				}
+
+				if (ret.intval)
+					di->flags.batt_unknown = false;
+				else
+					di->flags.batt_unknown = true;
+				break;
+			default:
+				break;
+			}
+			break;
+		case POWER_SUPPLY_PROP_TEMP:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+			    if (di->flags.batt_id_received)
+				di->bat_temp = ret.intval;
+				break;
+			default:
+				break;
+			}
+			break;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+/**
+ * ab8500_fg_init_hw_registers() - Set up FG related registers
+ * @di:		pointer to the ab8500_fg structure
+ *
+ * Set up battery OVV, low battery voltage registers
+ */
+static int ab8500_fg_init_hw_registers(struct ab8500_fg *di)
+{
+	int ret;
+
+	/* Set VBAT OVV threshold */
+	ret = abx500_mask_and_set_register_interruptible(di->dev,
+		AB8500_CHARGER,
+		AB8500_BATT_OVV,
+		BATT_OVV_TH_4P75,
+		BATT_OVV_TH_4P75);
+	if (ret) {
+		dev_err(di->dev, "failed to set BATT_OVV\n");
+		goto out;
+	}
+
+	/* Enable VBAT OVV detection */
+	ret = abx500_mask_and_set_register_interruptible(di->dev,
+		AB8500_CHARGER,
+		AB8500_BATT_OVV,
+		BATT_OVV_ENA,
+		BATT_OVV_ENA);
+	if (ret) {
+		dev_err(di->dev, "failed to enable BATT_OVV\n");
+		goto out;
+	}
+
+	/* Low Battery Voltage */
+	ret = abx500_set_register_interruptible(di->dev,
+		AB8500_SYS_CTRL2_BLOCK,
+		AB8500_LOW_BAT_REG,
+		ab8500_volt_to_regval(
+			di->bat->fg_params->lowbat_threshold) << 1 |
+		LOW_BAT_ENABLE);
+	if (ret) {
+		dev_err(di->dev, "%s write failed\n", __func__);
+		goto out;
+	}
+
+	/* Battery OK threshold */
+	ret = ab8500_fg_battok_init_hw_register(di);
+	if (ret) {
+		dev_err(di->dev, "BattOk init write failed.\n");
+		goto out;
+	}
+out:
+	return ret;
+}
+
+/**
+ * ab8500_fg_external_power_changed() - callback for power supply changes
+ * @psy:       pointer to the structure power_supply
+ *
+ * This function is the entry point of the pointer external_power_changed
+ * of the structure power_supply.
+ * This function gets executed when there is a change in any external power
+ * supply that this driver needs to be notified of.
+ */
+static void ab8500_fg_external_power_changed(struct power_supply *psy)
+{
+	struct ab8500_fg *di = to_ab8500_fg_device_info(psy);
+
+	class_for_each_device(power_supply_class, NULL,
+		&di->fg_psy, ab8500_fg_get_ext_psy_data);
+}
+
+/**
+ * abab8500_fg_reinit_work() - work to reset the FG algorithm
+ * @work:	pointer to the work_struct structure
+ *
+ * Used to reset the current battery capacity to be able to
+ * retrigger a new voltage base capacity calculation. For
+ * test and verification purpose.
+ */
+static void ab8500_fg_reinit_work(struct work_struct *work)
+{
+	struct ab8500_fg *di = container_of(work, struct ab8500_fg,
+		fg_reinit_work.work);
+
+	if (di->flags.calibrate == false) {
+		dev_dbg(di->dev, "Resetting FG state machine to init.\n");
+		ab8500_fg_clear_cap_samples(di);
+		ab8500_fg_calc_cap_discharge_voltage(di, true);
+		ab8500_fg_charge_state_to(di, AB8500_FG_CHARGE_INIT);
+		ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_INIT);
+		queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+
+	} else {
+		dev_err(di->dev, "Residual offset calibration ongoing "
+			"retrying..\n");
+		/* Wait one second until next try*/
+		queue_delayed_work(di->fg_wq, &di->fg_reinit_work,
+			round_jiffies(1));
+	}
+}
+
+/**
+ * ab8500_fg_reinit() - forces FG algorithm to reinitialize with current values
+ *
+ * This function can be used to force the FG algorithm to recalculate a new
+ * voltage based battery capacity.
+ */
+void ab8500_fg_reinit(void)
+{
+	struct ab8500_fg *di = ab8500_fg_get();
+	/* User won't be notified if a null pointer returned. */
+	if (di != NULL)
+		queue_delayed_work(di->fg_wq, &di->fg_reinit_work, 0);
+}
+
+/* Exposure to the sysfs interface */
+
+struct ab8500_fg_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct ab8500_fg *, char *);
+	ssize_t (*store)(struct ab8500_fg *, const char *, size_t);
+};
+
+static ssize_t charge_full_show(struct ab8500_fg *di, char *buf)
+{
+	return sprintf(buf, "%d\n", di->bat_cap.max_mah);
+}
+
+static ssize_t charge_full_store(struct ab8500_fg *di, const char *buf,
+				 size_t count)
+{
+	unsigned long charge_full;
+	ssize_t ret = -EINVAL;
+
+	ret = strict_strtoul(buf, 10, &charge_full);
+
+	dev_dbg(di->dev, "Ret %zd charge_full %lu", ret, charge_full);
+
+	if (!ret) {
+		di->bat_cap.max_mah = (int) charge_full;
+		ret = count;
+	}
+	return ret;
+}
+
+static ssize_t charge_now_show(struct ab8500_fg *di, char *buf)
+{
+	return sprintf(buf, "%d\n", di->bat_cap.prev_mah);
+}
+
+static ssize_t charge_now_store(struct ab8500_fg *di, const char *buf,
+				 size_t count)
+{
+	unsigned long charge_now;
+	ssize_t ret;
+
+	ret = strict_strtoul(buf, 10, &charge_now);
+
+	dev_dbg(di->dev, "Ret %zd charge_now %lu was %d",
+		ret, charge_now, di->bat_cap.prev_mah);
+
+	if (!ret) {
+		di->bat_cap.user_mah = (int) charge_now;
+		di->flags.user_cap = true;
+		ret = count;
+		queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+	}
+	return ret;
+}
+
+static struct ab8500_fg_sysfs_entry charge_full_attr =
+	__ATTR(charge_full, 0644, charge_full_show, charge_full_store);
+
+static struct ab8500_fg_sysfs_entry charge_now_attr =
+	__ATTR(charge_now, 0644, charge_now_show, charge_now_store);
+
+static ssize_t
+ab8500_fg_show(struct kobject *kobj, struct attribute *attr, char *buf)
+{
+	struct ab8500_fg_sysfs_entry *entry;
+	struct ab8500_fg *di;
+
+	entry = container_of(attr, struct ab8500_fg_sysfs_entry, attr);
+	di = container_of(kobj, struct ab8500_fg, fg_kobject);
+
+	if (!entry->show)
+		return -EIO;
+
+	return entry->show(di, buf);
+}
+static ssize_t
+ab8500_fg_store(struct kobject *kobj, struct attribute *attr, const char *buf,
+		size_t count)
+{
+	struct ab8500_fg_sysfs_entry *entry;
+	struct ab8500_fg *di;
+
+	entry = container_of(attr, struct ab8500_fg_sysfs_entry, attr);
+	di = container_of(kobj, struct ab8500_fg, fg_kobject);
+
+	if (!entry->store)
+		return -EIO;
+
+	return entry->store(di, buf, count);
+}
+
+static const struct sysfs_ops ab8500_fg_sysfs_ops = {
+	.show = ab8500_fg_show,
+	.store = ab8500_fg_store,
+};
+
+static struct attribute *ab8500_fg_attrs[] = {
+	&charge_full_attr.attr,
+	&charge_now_attr.attr,
+	NULL,
+};
+
+static struct kobj_type ab8500_fg_ktype = {
+	.sysfs_ops = &ab8500_fg_sysfs_ops,
+	.default_attrs = ab8500_fg_attrs,
+};
+
+/**
+ * ab8500_chargalg_sysfs_exit() - de-init of sysfs entry
+ * @di:                pointer to the struct ab8500_chargalg
+ *
+ * This function removes the entry in sysfs.
+ */
+static void ab8500_fg_sysfs_exit(struct ab8500_fg *di)
+{
+	kobject_del(&di->fg_kobject);
+}
+
+/**
+ * ab8500_chargalg_sysfs_init() - init of sysfs entry
+ * @di:                pointer to the struct ab8500_chargalg
+ *
+ * This function adds an entry in sysfs.
+ * Returns error code in case of failure else 0(on success)
+ */
+static int ab8500_fg_sysfs_init(struct ab8500_fg *di)
+{
+	int ret = 0;
+
+	ret = kobject_init_and_add(&di->fg_kobject,
+		&ab8500_fg_ktype,
+		NULL, "battery");
+	if (ret < 0)
+		dev_err(di->dev, "failed to create sysfs entry\n");
+
+	return ret;
+}
+/* Exposure to the sysfs interface <<END>> */
+
+#if defined(CONFIG_PM)
+static int ab8500_fg_resume(struct platform_device *pdev)
+{
+	struct ab8500_fg *di = platform_get_drvdata(pdev);
+
+	/*
+	 * Change state if we're not charging. If we're charging we will wake
+	 * up on the FG IRQ
+	 */
+	if (!di->flags.charging) {
+		ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_WAKEUP);
+		queue_work(di->fg_wq, &di->fg_work);
+	}
+
+	return 0;
+}
+
+static int ab8500_fg_suspend(struct platform_device *pdev,
+	pm_message_t state)
+{
+	struct ab8500_fg *di = platform_get_drvdata(pdev);
+
+	flush_delayed_work(&di->fg_periodic_work);
+
+	/*
+	 * If the FG is enabled we will disable it before going to suspend
+	 * only if we're not charging
+	 */
+	if (di->flags.fg_enabled && !di->flags.charging)
+		ab8500_fg_coulomb_counter(di, false);
+
+	return 0;
+}
+#else
+#define ab8500_fg_suspend      NULL
+#define ab8500_fg_resume       NULL
+#endif
+
+static int __devexit ab8500_fg_remove(struct platform_device *pdev)
+{
+	int ret = 0;
+	struct ab8500_fg *di = platform_get_drvdata(pdev);
+
+	list_del(&di->node);
+
+	/* Disable coulomb counter */
+	ret = ab8500_fg_coulomb_counter(di, false);
+	if (ret)
+		dev_err(di->dev, "failed to disable coulomb counter\n");
+
+	destroy_workqueue(di->fg_wq);
+	ab8500_fg_sysfs_exit(di);
+
+	flush_scheduled_work();
+	power_supply_unregister(&di->fg_psy);
+	platform_set_drvdata(pdev, NULL);
+	kfree(di);
+	return ret;
+}
+
+/* ab8500 fg driver interrupts and their respective isr */
+static struct ab8500_fg_interrupts ab8500_fg_irq[] = {
+	{"NCONV_ACCU", ab8500_fg_cc_convend_handler},
+	{"BATT_OVV", ab8500_fg_batt_ovv_handler},
+	{"LOW_BAT_F", ab8500_fg_lowbatf_handler},
+	{"CC_INT_CALIB", ab8500_fg_cc_int_calib_handler},
+	{"CCEOC", ab8500_fg_cc_data_end_handler},
+};
+
+static int __devinit ab8500_fg_probe(struct platform_device *pdev)
+{
+	int i, irq;
+	int ret = 0;
+	struct abx500_bm_plat_data *plat_data;
+
+	struct ab8500_fg *di =
+		kzalloc(sizeof(struct ab8500_fg), GFP_KERNEL);
+	if (!di)
+		return -ENOMEM;
+
+	mutex_init(&di->cc_lock);
+
+	/* get parent data */
+	di->dev = &pdev->dev;
+	di->parent = dev_get_drvdata(pdev->dev.parent);
+	di->gpadc = ab8500_gpadc_get("ab8500-gpadc.0");
+
+	/* get fg specific platform data */
+	plat_data = pdev->dev.platform_data;
+	di->pdata = plat_data->fg;
+	if (!di->pdata) {
+		dev_err(di->dev, "no fg platform data supplied\n");
+		ret = -EINVAL;
+		goto free_device_info;
+	}
+
+	/* get battery specific platform data */
+	di->bat = plat_data->battery;
+	if (!di->bat) {
+		dev_err(di->dev, "no battery platform data supplied\n");
+		ret = -EINVAL;
+		goto free_device_info;
+	}
+
+	di->fg_psy.name = "ab8500_fg";
+	di->fg_psy.type = POWER_SUPPLY_TYPE_BATTERY;
+	di->fg_psy.properties = ab8500_fg_props;
+	di->fg_psy.num_properties = ARRAY_SIZE(ab8500_fg_props);
+	di->fg_psy.get_property = ab8500_fg_get_property;
+	di->fg_psy.supplied_to = di->pdata->supplied_to;
+	di->fg_psy.num_supplicants = di->pdata->num_supplicants;
+	di->fg_psy.external_power_changed = ab8500_fg_external_power_changed;
+
+	di->bat_cap.max_mah_design = MILLI_TO_MICRO *
+		di->bat->bat_type[di->bat->batt_id].charge_full_design;
+
+	di->bat_cap.max_mah = di->bat_cap.max_mah_design;
+
+	di->vbat_nom = di->bat->bat_type[di->bat->batt_id].nominal_voltage;
+
+	di->init_capacity = true;
+
+	ab8500_fg_charge_state_to(di, AB8500_FG_CHARGE_INIT);
+	ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_INIT);
+
+	/* Create a work queue for running the FG algorithm */
+	di->fg_wq = create_singlethread_workqueue("ab8500_fg_wq");
+	if (di->fg_wq == NULL) {
+		dev_err(di->dev, "failed to create work queue\n");
+		goto free_device_info;
+	}
+
+	/* Init work for running the fg algorithm instantly */
+	INIT_WORK(&di->fg_work, ab8500_fg_instant_work);
+
+	/* Init work for getting the battery accumulated current */
+	INIT_WORK(&di->fg_acc_cur_work, ab8500_fg_acc_cur_work);
+
+	/* Init work for reinitialising the fg algorithm */
+	INIT_DELAYED_WORK_DEFERRABLE(&di->fg_reinit_work,
+		ab8500_fg_reinit_work);
+
+	/* Work delayed Queue to run the state machine */
+	INIT_DELAYED_WORK_DEFERRABLE(&di->fg_periodic_work,
+		ab8500_fg_periodic_work);
+
+	/* Work to check low battery condition */
+	INIT_DELAYED_WORK_DEFERRABLE(&di->fg_low_bat_work,
+		ab8500_fg_low_bat_work);
+
+	/* Init work for HW failure check */
+	INIT_DELAYED_WORK_DEFERRABLE(&di->fg_check_hw_failure_work,
+		ab8500_fg_check_hw_failure_work);
+
+	/* Initialize OVV, and other registers */
+	ret = ab8500_fg_init_hw_registers(di);
+	if (ret) {
+		dev_err(di->dev, "failed to initialize registers\n");
+		goto free_inst_curr_wq;
+	}
+
+	/* Consider battery unknown until we're informed otherwise */
+	di->flags.batt_unknown = true;
+	di->flags.batt_id_received = false;
+
+	/* Register FG power supply class */
+	ret = power_supply_register(di->dev, &di->fg_psy);
+	if (ret) {
+		dev_err(di->dev, "failed to register FG psy\n");
+		goto free_inst_curr_wq;
+	}
+
+	di->fg_samples = SEC_TO_SAMPLE(di->bat->fg_params->init_timer);
+	ab8500_fg_coulomb_counter(di, true);
+
+	/* Initialize completion used to notify completion of inst current */
+	init_completion(&di->ab8500_fg_complete);
+
+	/* Register interrupts */
+	for (i = 0; i < ARRAY_SIZE(ab8500_fg_irq); i++) {
+		irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
+		ret = request_threaded_irq(irq, NULL, ab8500_fg_irq[i].isr,
+			IRQF_SHARED | IRQF_NO_SUSPEND,
+			ab8500_fg_irq[i].name, di);
+
+		if (ret != 0) {
+			dev_err(di->dev, "failed to request %s IRQ %d: %d\n"
+				, ab8500_fg_irq[i].name, irq, ret);
+			goto free_irq;
+		}
+		dev_dbg(di->dev, "Requested %s IRQ %d: %d\n",
+			ab8500_fg_irq[i].name, irq, ret);
+	}
+	di->irq = platform_get_irq_byname(pdev, "CCEOC");
+	disable_irq(di->irq);
+
+	platform_set_drvdata(pdev, di);
+
+	ret = ab8500_fg_sysfs_init(di);
+	if (ret) {
+		dev_err(di->dev, "failed to create sysfs entry\n");
+		goto free_irq;
+	}
+
+	/* Calibrate the fg first time */
+	di->flags.calibrate = true;
+	di->calib_state = AB8500_FG_CALIB_INIT;
+
+	/* Use room temp as default value until we get an update from driver. */
+	di->bat_temp = 210;
+
+	/* Run the FG algorithm */
+	queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+
+	list_add_tail(&di->node, &ab8500_fg_list);
+
+	return ret;
+
+free_irq:
+	power_supply_unregister(&di->fg_psy);
+
+	/* We also have to free all successfully registered irqs */
+	for (i = i - 1; i >= 0; i--) {
+		irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
+		free_irq(irq, di);
+	}
+free_inst_curr_wq:
+	destroy_workqueue(di->fg_wq);
+free_device_info:
+	kfree(di);
+
+	return ret;
+}
+
+static struct platform_driver ab8500_fg_driver = {
+	.probe = ab8500_fg_probe,
+	.remove = __devexit_p(ab8500_fg_remove),
+	.suspend = ab8500_fg_suspend,
+	.resume = ab8500_fg_resume,
+	.driver = {
+		.name = "ab8500-fg",
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init ab8500_fg_init(void)
+{
+	return platform_driver_register(&ab8500_fg_driver);
+}
+
+static void __exit ab8500_fg_exit(void)
+{
+	platform_driver_unregister(&ab8500_fg_driver);
+}
+
+subsys_initcall_sync(ab8500_fg_init);
+module_exit(ab8500_fg_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Johan Palsson, Karl Komierowski");
+MODULE_ALIAS("platform:ab8500-fg");
+MODULE_DESCRIPTION("AB8500 Fuel Gauge driver");
diff --git a/drivers/power/abx500_chargalg.c b/drivers/power/abx500_chargalg.c
new file mode 100644
index 000000000000..804b88c760d6
--- /dev/null
+++ b/drivers/power/abx500_chargalg.c
@@ -0,0 +1,1921 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2012
+ *
+ * Charging algorithm driver for abx500 variants
+ *
+ * License Terms: GNU General Public License v2
+ * Authors:
+ *	Johan Palsson <johan.palsson@stericsson.com>
+ *	Karl Komierowski <karl.komierowski@stericsson.com>
+ *	Arun R Murthy <arun.murthy@stericsson.com>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/completion.h>
+#include <linux/workqueue.h>
+#include <linux/kobject.h>
+#include <linux/mfd/abx500.h>
+#include <linux/mfd/abx500/ux500_chargalg.h>
+#include <linux/mfd/abx500/ab8500-bm.h>
+
+/* Watchdog kick interval */
+#define CHG_WD_INTERVAL			(6 * HZ)
+
+/* End-of-charge criteria counter */
+#define EOC_COND_CNT			10
+
+/* Recharge criteria counter */
+#define RCH_COND_CNT			3
+
+#define to_abx500_chargalg_device_info(x) container_of((x), \
+	struct abx500_chargalg, chargalg_psy);
+
+enum abx500_chargers {
+	NO_CHG,
+	AC_CHG,
+	USB_CHG,
+};
+
+struct abx500_chargalg_charger_info {
+	enum abx500_chargers conn_chg;
+	enum abx500_chargers prev_conn_chg;
+	enum abx500_chargers online_chg;
+	enum abx500_chargers prev_online_chg;
+	enum abx500_chargers charger_type;
+	bool usb_chg_ok;
+	bool ac_chg_ok;
+	int usb_volt;
+	int usb_curr;
+	int ac_volt;
+	int ac_curr;
+	int usb_vset;
+	int usb_iset;
+	int ac_vset;
+	int ac_iset;
+};
+
+struct abx500_chargalg_suspension_status {
+	bool suspended_change;
+	bool ac_suspended;
+	bool usb_suspended;
+};
+
+struct abx500_chargalg_battery_data {
+	int temp;
+	int volt;
+	int avg_curr;
+	int inst_curr;
+	int percent;
+};
+
+enum abx500_chargalg_states {
+	STATE_HANDHELD_INIT,
+	STATE_HANDHELD,
+	STATE_CHG_NOT_OK_INIT,
+	STATE_CHG_NOT_OK,
+	STATE_HW_TEMP_PROTECT_INIT,
+	STATE_HW_TEMP_PROTECT,
+	STATE_NORMAL_INIT,
+	STATE_NORMAL,
+	STATE_WAIT_FOR_RECHARGE_INIT,
+	STATE_WAIT_FOR_RECHARGE,
+	STATE_MAINTENANCE_A_INIT,
+	STATE_MAINTENANCE_A,
+	STATE_MAINTENANCE_B_INIT,
+	STATE_MAINTENANCE_B,
+	STATE_TEMP_UNDEROVER_INIT,
+	STATE_TEMP_UNDEROVER,
+	STATE_TEMP_LOWHIGH_INIT,
+	STATE_TEMP_LOWHIGH,
+	STATE_SUSPENDED_INIT,
+	STATE_SUSPENDED,
+	STATE_OVV_PROTECT_INIT,
+	STATE_OVV_PROTECT,
+	STATE_SAFETY_TIMER_EXPIRED_INIT,
+	STATE_SAFETY_TIMER_EXPIRED,
+	STATE_BATT_REMOVED_INIT,
+	STATE_BATT_REMOVED,
+	STATE_WD_EXPIRED_INIT,
+	STATE_WD_EXPIRED,
+};
+
+static const char *states[] = {
+	"HANDHELD_INIT",
+	"HANDHELD",
+	"CHG_NOT_OK_INIT",
+	"CHG_NOT_OK",
+	"HW_TEMP_PROTECT_INIT",
+	"HW_TEMP_PROTECT",
+	"NORMAL_INIT",
+	"NORMAL",
+	"WAIT_FOR_RECHARGE_INIT",
+	"WAIT_FOR_RECHARGE",
+	"MAINTENANCE_A_INIT",
+	"MAINTENANCE_A",
+	"MAINTENANCE_B_INIT",
+	"MAINTENANCE_B",
+	"TEMP_UNDEROVER_INIT",
+	"TEMP_UNDEROVER",
+	"TEMP_LOWHIGH_INIT",
+	"TEMP_LOWHIGH",
+	"SUSPENDED_INIT",
+	"SUSPENDED",
+	"OVV_PROTECT_INIT",
+	"OVV_PROTECT",
+	"SAFETY_TIMER_EXPIRED_INIT",
+	"SAFETY_TIMER_EXPIRED",
+	"BATT_REMOVED_INIT",
+	"BATT_REMOVED",
+	"WD_EXPIRED_INIT",
+	"WD_EXPIRED",
+};
+
+struct abx500_chargalg_events {
+	bool batt_unknown;
+	bool mainextchnotok;
+	bool batt_ovv;
+	bool batt_rem;
+	bool btemp_underover;
+	bool btemp_lowhigh;
+	bool main_thermal_prot;
+	bool usb_thermal_prot;
+	bool main_ovv;
+	bool vbus_ovv;
+	bool usbchargernotok;
+	bool safety_timer_expired;
+	bool maintenance_timer_expired;
+	bool ac_wd_expired;
+	bool usb_wd_expired;
+	bool ac_cv_active;
+	bool usb_cv_active;
+	bool vbus_collapsed;
+};
+
+/**
+ * struct abx500_charge_curr_maximization - Charger maximization parameters
+ * @original_iset:	the non optimized/maximised charger current
+ * @current_iset:	the charging current used at this moment
+ * @test_delta_i:	the delta between the current we want to charge and the
+			current that is really going into the battery
+ * @condition_cnt:	number of iterations needed before a new charger current
+			is set
+ * @max_current:	maximum charger current
+ * @wait_cnt:		to avoid too fast current step down in case of charger
+ *			voltage collapse, we insert this delay between step
+ *			down
+ * @level:		tells in how many steps the charging current has been
+			increased
+ */
+struct abx500_charge_curr_maximization {
+	int original_iset;
+	int current_iset;
+	int test_delta_i;
+	int condition_cnt;
+	int max_current;
+	int wait_cnt;
+	u8 level;
+};
+
+enum maxim_ret {
+	MAXIM_RET_NOACTION,
+	MAXIM_RET_CHANGE,
+	MAXIM_RET_IBAT_TOO_HIGH,
+};
+
+/**
+ * struct abx500_chargalg - abx500 Charging algorithm device information
+ * @dev:		pointer to the structure device
+ * @charge_status:	battery operating status
+ * @eoc_cnt:		counter used to determine end-of_charge
+ * @rch_cnt:		counter used to determine start of recharge
+ * @maintenance_chg:	indicate if maintenance charge is active
+ * @t_hyst_norm		temperature hysteresis when the temperature has been
+ *			over or under normal limits
+ * @t_hyst_lowhigh	temperature hysteresis when the temperature has been
+ *			over or under the high or low limits
+ * @charge_state:	current state of the charging algorithm
+ * @ccm			charging current maximization parameters
+ * @chg_info:		information about connected charger types
+ * @batt_data:		data of the battery
+ * @susp_status:	current charger suspension status
+ * @pdata:		pointer to the abx500_chargalg platform data
+ * @bat:		pointer to the abx500_bm platform data
+ * @chargalg_psy:	structure that holds the battery properties exposed by
+ *			the charging algorithm
+ * @events:		structure for information about events triggered
+ * @chargalg_wq:		work queue for running the charging algorithm
+ * @chargalg_periodic_work:	work to run the charging algorithm periodically
+ * @chargalg_wd_work:		work to kick the charger watchdog periodically
+ * @chargalg_work:		work to run the charging algorithm instantly
+ * @safety_timer:		charging safety timer
+ * @maintenance_timer:		maintenance charging timer
+ * @chargalg_kobject:		structure of type kobject
+ */
+struct abx500_chargalg {
+	struct device *dev;
+	int charge_status;
+	int eoc_cnt;
+	int rch_cnt;
+	bool maintenance_chg;
+	int t_hyst_norm;
+	int t_hyst_lowhigh;
+	enum abx500_chargalg_states charge_state;
+	struct abx500_charge_curr_maximization ccm;
+	struct abx500_chargalg_charger_info chg_info;
+	struct abx500_chargalg_battery_data batt_data;
+	struct abx500_chargalg_suspension_status susp_status;
+	struct abx500_chargalg_platform_data *pdata;
+	struct abx500_bm_data *bat;
+	struct power_supply chargalg_psy;
+	struct ux500_charger *ac_chg;
+	struct ux500_charger *usb_chg;
+	struct abx500_chargalg_events events;
+	struct workqueue_struct *chargalg_wq;
+	struct delayed_work chargalg_periodic_work;
+	struct delayed_work chargalg_wd_work;
+	struct work_struct chargalg_work;
+	struct timer_list safety_timer;
+	struct timer_list maintenance_timer;
+	struct kobject chargalg_kobject;
+};
+
+/* Main battery properties */
+static enum power_supply_property abx500_chargalg_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_HEALTH,
+};
+
+/**
+ * abx500_chargalg_safety_timer_expired() - Expiration of the safety timer
+ * @data:	pointer to the abx500_chargalg structure
+ *
+ * This function gets called when the safety timer for the charger
+ * expires
+ */
+static void abx500_chargalg_safety_timer_expired(unsigned long data)
+{
+	struct abx500_chargalg *di = (struct abx500_chargalg *) data;
+	dev_err(di->dev, "Safety timer expired\n");
+	di->events.safety_timer_expired = true;
+
+	/* Trigger execution of the algorithm instantly */
+	queue_work(di->chargalg_wq, &di->chargalg_work);
+}
+
+/**
+ * abx500_chargalg_maintenance_timer_expired() - Expiration of
+ * the maintenance timer
+ * @i:		pointer to the abx500_chargalg structure
+ *
+ * This function gets called when the maintenence timer
+ * expires
+ */
+static void abx500_chargalg_maintenance_timer_expired(unsigned long data)
+{
+
+	struct abx500_chargalg *di = (struct abx500_chargalg *) data;
+	dev_dbg(di->dev, "Maintenance timer expired\n");
+	di->events.maintenance_timer_expired = true;
+
+	/* Trigger execution of the algorithm instantly */
+	queue_work(di->chargalg_wq, &di->chargalg_work);
+}
+
+/**
+ * abx500_chargalg_state_to() - Change charge state
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * This function gets called when a charge state change should occur
+ */
+static void abx500_chargalg_state_to(struct abx500_chargalg *di,
+	enum abx500_chargalg_states state)
+{
+	dev_dbg(di->dev,
+		"State changed: %s (From state: [%d] %s =to=> [%d] %s )\n",
+		di->charge_state == state ? "NO" : "YES",
+		di->charge_state,
+		states[di->charge_state],
+		state,
+		states[state]);
+
+	di->charge_state = state;
+}
+
+/**
+ * abx500_chargalg_check_charger_connection() - Check charger connection change
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * This function will check if there is a change in the charger connection
+ * and change charge state accordingly. AC has precedence over USB.
+ */
+static int abx500_chargalg_check_charger_connection(struct abx500_chargalg *di)
+{
+	if (di->chg_info.conn_chg != di->chg_info.prev_conn_chg ||
+		di->susp_status.suspended_change) {
+		/*
+		 * Charger state changed or suspension
+		 * has changed since last update
+		 */
+		if ((di->chg_info.conn_chg & AC_CHG) &&
+			!di->susp_status.ac_suspended) {
+			dev_dbg(di->dev, "Charging source is AC\n");
+			if (di->chg_info.charger_type != AC_CHG) {
+				di->chg_info.charger_type = AC_CHG;
+				abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+			}
+		} else if ((di->chg_info.conn_chg & USB_CHG) &&
+			!di->susp_status.usb_suspended) {
+			dev_dbg(di->dev, "Charging source is USB\n");
+			di->chg_info.charger_type = USB_CHG;
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		} else if (di->chg_info.conn_chg &&
+			(di->susp_status.ac_suspended ||
+			di->susp_status.usb_suspended)) {
+			dev_dbg(di->dev, "Charging is suspended\n");
+			di->chg_info.charger_type = NO_CHG;
+			abx500_chargalg_state_to(di, STATE_SUSPENDED_INIT);
+		} else {
+			dev_dbg(di->dev, "Charging source is OFF\n");
+			di->chg_info.charger_type = NO_CHG;
+			abx500_chargalg_state_to(di, STATE_HANDHELD_INIT);
+		}
+		di->chg_info.prev_conn_chg = di->chg_info.conn_chg;
+		di->susp_status.suspended_change = false;
+	}
+	return di->chg_info.conn_chg;
+}
+
+/**
+ * abx500_chargalg_start_safety_timer() - Start charging safety timer
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * The safety timer is used to avoid overcharging of old or bad batteries.
+ * There are different timers for AC and USB
+ */
+static void abx500_chargalg_start_safety_timer(struct abx500_chargalg *di)
+{
+	unsigned long timer_expiration = 0;
+
+	switch (di->chg_info.charger_type) {
+	case AC_CHG:
+		timer_expiration =
+		round_jiffies(jiffies +
+			(di->bat->main_safety_tmr_h * 3600 * HZ));
+		break;
+
+	case USB_CHG:
+		timer_expiration =
+		round_jiffies(jiffies +
+			(di->bat->usb_safety_tmr_h * 3600 * HZ));
+		break;
+
+	default:
+		dev_err(di->dev, "Unknown charger to charge from\n");
+		break;
+	}
+
+	di->events.safety_timer_expired = false;
+	di->safety_timer.expires = timer_expiration;
+	if (!timer_pending(&di->safety_timer))
+		add_timer(&di->safety_timer);
+	else
+		mod_timer(&di->safety_timer, timer_expiration);
+}
+
+/**
+ * abx500_chargalg_stop_safety_timer() - Stop charging safety timer
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * The safety timer is stopped whenever the NORMAL state is exited
+ */
+static void abx500_chargalg_stop_safety_timer(struct abx500_chargalg *di)
+{
+	di->events.safety_timer_expired = false;
+	del_timer(&di->safety_timer);
+}
+
+/**
+ * abx500_chargalg_start_maintenance_timer() - Start charging maintenance timer
+ * @di:		pointer to the abx500_chargalg structure
+ * @duration:	duration of ther maintenance timer in hours
+ *
+ * The maintenance timer is used to maintain the charge in the battery once
+ * the battery is considered full. These timers are chosen to match the
+ * discharge curve of the battery
+ */
+static void abx500_chargalg_start_maintenance_timer(struct abx500_chargalg *di,
+	int duration)
+{
+	unsigned long timer_expiration;
+
+	/* Convert from hours to jiffies */
+	timer_expiration = round_jiffies(jiffies + (duration * 3600 * HZ));
+
+	di->events.maintenance_timer_expired = false;
+	di->maintenance_timer.expires = timer_expiration;
+	if (!timer_pending(&di->maintenance_timer))
+		add_timer(&di->maintenance_timer);
+	else
+		mod_timer(&di->maintenance_timer, timer_expiration);
+}
+
+/**
+ * abx500_chargalg_stop_maintenance_timer() - Stop maintenance timer
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * The maintenance timer is stopped whenever maintenance ends or when another
+ * state is entered
+ */
+static void abx500_chargalg_stop_maintenance_timer(struct abx500_chargalg *di)
+{
+	di->events.maintenance_timer_expired = false;
+	del_timer(&di->maintenance_timer);
+}
+
+/**
+ * abx500_chargalg_kick_watchdog() - Kick charger watchdog
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * The charger watchdog have to be kicked periodically whenever the charger is
+ * on, else the ABB will reset the system
+ */
+static int abx500_chargalg_kick_watchdog(struct abx500_chargalg *di)
+{
+	/* Check if charger exists and kick watchdog if charging */
+	if (di->ac_chg && di->ac_chg->ops.kick_wd &&
+			di->chg_info.online_chg & AC_CHG)
+		return di->ac_chg->ops.kick_wd(di->ac_chg);
+	else if (di->usb_chg && di->usb_chg->ops.kick_wd &&
+			di->chg_info.online_chg & USB_CHG)
+		return di->usb_chg->ops.kick_wd(di->usb_chg);
+
+	return -ENXIO;
+}
+
+/**
+ * abx500_chargalg_ac_en() - Turn on/off the AC charger
+ * @di:		pointer to the abx500_chargalg structure
+ * @enable:	charger on/off
+ * @vset:	requested charger output voltage
+ * @iset:	requested charger output current
+ *
+ * The AC charger will be turned on/off with the requested charge voltage and
+ * current
+ */
+static int abx500_chargalg_ac_en(struct abx500_chargalg *di, int enable,
+	int vset, int iset)
+{
+	if (!di->ac_chg || !di->ac_chg->ops.enable)
+		return -ENXIO;
+
+	/* Select maximum of what both the charger and the battery supports */
+	if (di->ac_chg->max_out_volt)
+		vset = min(vset, di->ac_chg->max_out_volt);
+	if (di->ac_chg->max_out_curr)
+		iset = min(iset, di->ac_chg->max_out_curr);
+
+	di->chg_info.ac_iset = iset;
+	di->chg_info.ac_vset = vset;
+
+	return di->ac_chg->ops.enable(di->ac_chg, enable, vset, iset);
+}
+
+/**
+ * abx500_chargalg_usb_en() - Turn on/off the USB charger
+ * @di:		pointer to the abx500_chargalg structure
+ * @enable:	charger on/off
+ * @vset:	requested charger output voltage
+ * @iset:	requested charger output current
+ *
+ * The USB charger will be turned on/off with the requested charge voltage and
+ * current
+ */
+static int abx500_chargalg_usb_en(struct abx500_chargalg *di, int enable,
+	int vset, int iset)
+{
+	if (!di->usb_chg || !di->usb_chg->ops.enable)
+		return -ENXIO;
+
+	/* Select maximum of what both the charger and the battery supports */
+	if (di->usb_chg->max_out_volt)
+		vset = min(vset, di->usb_chg->max_out_volt);
+	if (di->usb_chg->max_out_curr)
+		iset = min(iset, di->usb_chg->max_out_curr);
+
+	di->chg_info.usb_iset = iset;
+	di->chg_info.usb_vset = vset;
+
+	return di->usb_chg->ops.enable(di->usb_chg, enable, vset, iset);
+}
+
+/**
+ * abx500_chargalg_update_chg_curr() - Update charger current
+ * @di:		pointer to the abx500_chargalg structure
+ * @iset:	requested charger output current
+ *
+ * The charger output current will be updated for the charger
+ * that is currently in use
+ */
+static int abx500_chargalg_update_chg_curr(struct abx500_chargalg *di,
+		int iset)
+{
+	/* Check if charger exists and update current if charging */
+	if (di->ac_chg && di->ac_chg->ops.update_curr &&
+			di->chg_info.charger_type & AC_CHG) {
+		/*
+		 * Select maximum of what both the charger
+		 * and the battery supports
+		 */
+		if (di->ac_chg->max_out_curr)
+			iset = min(iset, di->ac_chg->max_out_curr);
+
+		di->chg_info.ac_iset = iset;
+
+		return di->ac_chg->ops.update_curr(di->ac_chg, iset);
+	} else if (di->usb_chg && di->usb_chg->ops.update_curr &&
+			di->chg_info.charger_type & USB_CHG) {
+		/*
+		 * Select maximum of what both the charger
+		 * and the battery supports
+		 */
+		if (di->usb_chg->max_out_curr)
+			iset = min(iset, di->usb_chg->max_out_curr);
+
+		di->chg_info.usb_iset = iset;
+
+		return di->usb_chg->ops.update_curr(di->usb_chg, iset);
+	}
+
+	return -ENXIO;
+}
+
+/**
+ * abx500_chargalg_stop_charging() - Stop charging
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * This function is called from any state where charging should be stopped.
+ * All charging is disabled and all status parameters and timers are changed
+ * accordingly
+ */
+static void abx500_chargalg_stop_charging(struct abx500_chargalg *di)
+{
+	abx500_chargalg_ac_en(di, false, 0, 0);
+	abx500_chargalg_usb_en(di, false, 0, 0);
+	abx500_chargalg_stop_safety_timer(di);
+	abx500_chargalg_stop_maintenance_timer(di);
+	di->charge_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
+	di->maintenance_chg = false;
+	cancel_delayed_work(&di->chargalg_wd_work);
+	power_supply_changed(&di->chargalg_psy);
+}
+
+/**
+ * abx500_chargalg_hold_charging() - Pauses charging
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * This function is called in the case where maintenance charging has been
+ * disabled and instead a battery voltage mode is entered to check when the
+ * battery voltage has reached a certain recharge voltage
+ */
+static void abx500_chargalg_hold_charging(struct abx500_chargalg *di)
+{
+	abx500_chargalg_ac_en(di, false, 0, 0);
+	abx500_chargalg_usb_en(di, false, 0, 0);
+	abx500_chargalg_stop_safety_timer(di);
+	abx500_chargalg_stop_maintenance_timer(di);
+	di->charge_status = POWER_SUPPLY_STATUS_CHARGING;
+	di->maintenance_chg = false;
+	cancel_delayed_work(&di->chargalg_wd_work);
+	power_supply_changed(&di->chargalg_psy);
+}
+
+/**
+ * abx500_chargalg_start_charging() - Start the charger
+ * @di:		pointer to the abx500_chargalg structure
+ * @vset:	requested charger output voltage
+ * @iset:	requested charger output current
+ *
+ * A charger will be enabled depending on the requested charger type that was
+ * detected previously.
+ */
+static void abx500_chargalg_start_charging(struct abx500_chargalg *di,
+	int vset, int iset)
+{
+	switch (di->chg_info.charger_type) {
+	case AC_CHG:
+		dev_dbg(di->dev,
+			"AC parameters: Vset %d, Ich %d\n", vset, iset);
+		abx500_chargalg_usb_en(di, false, 0, 0);
+		abx500_chargalg_ac_en(di, true, vset, iset);
+		break;
+
+	case USB_CHG:
+		dev_dbg(di->dev,
+			"USB parameters: Vset %d, Ich %d\n", vset, iset);
+		abx500_chargalg_ac_en(di, false, 0, 0);
+		abx500_chargalg_usb_en(di, true, vset, iset);
+		break;
+
+	default:
+		dev_err(di->dev, "Unknown charger to charge from\n");
+		break;
+	}
+}
+
+/**
+ * abx500_chargalg_check_temp() - Check battery temperature ranges
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * The battery temperature is checked against the predefined limits and the
+ * charge state is changed accordingly
+ */
+static void abx500_chargalg_check_temp(struct abx500_chargalg *di)
+{
+	if (di->batt_data.temp > (di->bat->temp_low + di->t_hyst_norm) &&
+		di->batt_data.temp < (di->bat->temp_high - di->t_hyst_norm)) {
+		/* Temp OK! */
+		di->events.btemp_underover = false;
+		di->events.btemp_lowhigh = false;
+		di->t_hyst_norm = 0;
+		di->t_hyst_lowhigh = 0;
+	} else {
+		if (((di->batt_data.temp >= di->bat->temp_high) &&
+			(di->batt_data.temp <
+				(di->bat->temp_over - di->t_hyst_lowhigh))) ||
+			((di->batt_data.temp >
+				(di->bat->temp_under + di->t_hyst_lowhigh)) &&
+			(di->batt_data.temp <= di->bat->temp_low))) {
+			/* TEMP minor!!!!! */
+			di->events.btemp_underover = false;
+			di->events.btemp_lowhigh = true;
+			di->t_hyst_norm = di->bat->temp_hysteresis;
+			di->t_hyst_lowhigh = 0;
+		} else if (di->batt_data.temp <= di->bat->temp_under ||
+			di->batt_data.temp >= di->bat->temp_over) {
+			/* TEMP major!!!!! */
+			di->events.btemp_underover = true;
+			di->events.btemp_lowhigh = false;
+			di->t_hyst_norm = 0;
+			di->t_hyst_lowhigh = di->bat->temp_hysteresis;
+		} else {
+		/* Within hysteresis */
+		dev_dbg(di->dev, "Within hysteresis limit temp: %d "
+				"hyst_lowhigh %d, hyst normal %d\n",
+				di->batt_data.temp, di->t_hyst_lowhigh,
+				di->t_hyst_norm);
+		}
+	}
+}
+
+/**
+ * abx500_chargalg_check_charger_voltage() - Check charger voltage
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * Charger voltage is checked against maximum limit
+ */
+static void abx500_chargalg_check_charger_voltage(struct abx500_chargalg *di)
+{
+	if (di->chg_info.usb_volt > di->bat->chg_params->usb_volt_max)
+		di->chg_info.usb_chg_ok = false;
+	else
+		di->chg_info.usb_chg_ok = true;
+
+	if (di->chg_info.ac_volt > di->bat->chg_params->ac_volt_max)
+		di->chg_info.ac_chg_ok = false;
+	else
+		di->chg_info.ac_chg_ok = true;
+
+}
+
+/**
+ * abx500_chargalg_end_of_charge() - Check if end-of-charge criteria is fulfilled
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * End-of-charge criteria is fulfilled when the battery voltage is above a
+ * certain limit and the battery current is below a certain limit for a
+ * predefined number of consecutive seconds. If true, the battery is full
+ */
+static void abx500_chargalg_end_of_charge(struct abx500_chargalg *di)
+{
+	if (di->charge_status == POWER_SUPPLY_STATUS_CHARGING &&
+		di->charge_state == STATE_NORMAL &&
+		!di->maintenance_chg && (di->batt_data.volt >=
+		di->bat->bat_type[di->bat->batt_id].termination_vol ||
+		di->events.usb_cv_active || di->events.ac_cv_active) &&
+		di->batt_data.avg_curr <
+		di->bat->bat_type[di->bat->batt_id].termination_curr &&
+		di->batt_data.avg_curr > 0) {
+		if (++di->eoc_cnt >= EOC_COND_CNT) {
+			di->eoc_cnt = 0;
+			di->charge_status = POWER_SUPPLY_STATUS_FULL;
+			di->maintenance_chg = true;
+			dev_dbg(di->dev, "EOC reached!\n");
+			power_supply_changed(&di->chargalg_psy);
+		} else {
+			dev_dbg(di->dev,
+				" EOC limit reached for the %d"
+				" time, out of %d before EOC\n",
+				di->eoc_cnt,
+				EOC_COND_CNT);
+		}
+	} else {
+		di->eoc_cnt = 0;
+	}
+}
+
+static void init_maxim_chg_curr(struct abx500_chargalg *di)
+{
+	di->ccm.original_iset =
+		di->bat->bat_type[di->bat->batt_id].normal_cur_lvl;
+	di->ccm.current_iset =
+		di->bat->bat_type[di->bat->batt_id].normal_cur_lvl;
+	di->ccm.test_delta_i = di->bat->maxi->charger_curr_step;
+	di->ccm.max_current = di->bat->maxi->chg_curr;
+	di->ccm.condition_cnt = di->bat->maxi->wait_cycles;
+	di->ccm.level = 0;
+}
+
+/**
+ * abx500_chargalg_chg_curr_maxim - increases the charger current to
+ *			compensate for the system load
+ * @di		pointer to the abx500_chargalg structure
+ *
+ * This maximization function is used to raise the charger current to get the
+ * battery current as close to the optimal value as possible. The battery
+ * current during charging is affected by the system load
+ */
+static enum maxim_ret abx500_chargalg_chg_curr_maxim(struct abx500_chargalg *di)
+{
+	int delta_i;
+
+	if (!di->bat->maxi->ena_maxi)
+		return MAXIM_RET_NOACTION;
+
+	delta_i = di->ccm.original_iset - di->batt_data.inst_curr;
+
+	if (di->events.vbus_collapsed) {
+		dev_dbg(di->dev, "Charger voltage has collapsed %d\n",
+				di->ccm.wait_cnt);
+		if (di->ccm.wait_cnt == 0) {
+			dev_dbg(di->dev, "lowering current\n");
+			di->ccm.wait_cnt++;
+			di->ccm.condition_cnt = di->bat->maxi->wait_cycles;
+			di->ccm.max_current =
+				di->ccm.current_iset - di->ccm.test_delta_i;
+			di->ccm.current_iset = di->ccm.max_current;
+			di->ccm.level--;
+			return MAXIM_RET_CHANGE;
+		} else {
+			dev_dbg(di->dev, "waiting\n");
+			/* Let's go in here twice before lowering curr again */
+			di->ccm.wait_cnt = (di->ccm.wait_cnt + 1) % 3;
+			return MAXIM_RET_NOACTION;
+		}
+	}
+
+	di->ccm.wait_cnt = 0;
+
+	if ((di->batt_data.inst_curr > di->ccm.original_iset)) {
+		dev_dbg(di->dev, " Maximization Ibat (%dmA) too high"
+			" (limit %dmA) (current iset: %dmA)!\n",
+			di->batt_data.inst_curr, di->ccm.original_iset,
+			di->ccm.current_iset);
+
+		if (di->ccm.current_iset == di->ccm.original_iset)
+			return MAXIM_RET_NOACTION;
+
+		di->ccm.condition_cnt = di->bat->maxi->wait_cycles;
+		di->ccm.current_iset = di->ccm.original_iset;
+		di->ccm.level = 0;
+
+		return MAXIM_RET_IBAT_TOO_HIGH;
+	}
+
+	if (delta_i > di->ccm.test_delta_i &&
+		(di->ccm.current_iset + di->ccm.test_delta_i) <
+		di->ccm.max_current) {
+		if (di->ccm.condition_cnt-- == 0) {
+			/* Increse the iset with cco.test_delta_i */
+			di->ccm.condition_cnt = di->bat->maxi->wait_cycles;
+			di->ccm.current_iset += di->ccm.test_delta_i;
+			di->ccm.level++;
+			dev_dbg(di->dev, " Maximization needed, increase"
+				" with %d mA to %dmA (Optimal ibat: %d)"
+				" Level %d\n",
+				di->ccm.test_delta_i,
+				di->ccm.current_iset,
+				di->ccm.original_iset,
+				di->ccm.level);
+			return MAXIM_RET_CHANGE;
+		} else {
+			return MAXIM_RET_NOACTION;
+		}
+	}  else {
+		di->ccm.condition_cnt = di->bat->maxi->wait_cycles;
+		return MAXIM_RET_NOACTION;
+	}
+}
+
+static void handle_maxim_chg_curr(struct abx500_chargalg *di)
+{
+	enum maxim_ret ret;
+	int result;
+
+	ret = abx500_chargalg_chg_curr_maxim(di);
+	switch (ret) {
+	case MAXIM_RET_CHANGE:
+		result = abx500_chargalg_update_chg_curr(di,
+			di->ccm.current_iset);
+		if (result)
+			dev_err(di->dev, "failed to set chg curr\n");
+		break;
+	case MAXIM_RET_IBAT_TOO_HIGH:
+		result = abx500_chargalg_update_chg_curr(di,
+			di->bat->bat_type[di->bat->batt_id].normal_cur_lvl);
+		if (result)
+			dev_err(di->dev, "failed to set chg curr\n");
+		break;
+
+	case MAXIM_RET_NOACTION:
+	default:
+		/* Do nothing..*/
+		break;
+	}
+}
+
+static int abx500_chargalg_get_ext_psy_data(struct device *dev, void *data)
+{
+	struct power_supply *psy;
+	struct power_supply *ext;
+	struct abx500_chargalg *di;
+	union power_supply_propval ret;
+	int i, j;
+	bool psy_found = false;
+
+	psy = (struct power_supply *)data;
+	ext = dev_get_drvdata(dev);
+	di = to_abx500_chargalg_device_info(psy);
+	/* For all psy where the driver name appears in any supplied_to */
+	for (i = 0; i < ext->num_supplicants; i++) {
+		if (!strcmp(ext->supplied_to[i], psy->name))
+			psy_found = true;
+	}
+	if (!psy_found)
+		return 0;
+
+	/* Go through all properties for the psy */
+	for (j = 0; j < ext->num_properties; j++) {
+		enum power_supply_property prop;
+		prop = ext->properties[j];
+
+		/* Initialize chargers if not already done */
+		if (!di->ac_chg &&
+			ext->type == POWER_SUPPLY_TYPE_MAINS)
+			di->ac_chg = psy_to_ux500_charger(ext);
+		else if (!di->usb_chg &&
+			ext->type == POWER_SUPPLY_TYPE_USB)
+			di->usb_chg = psy_to_ux500_charger(ext);
+
+		if (ext->get_property(ext, prop, &ret))
+			continue;
+		switch (prop) {
+		case POWER_SUPPLY_PROP_PRESENT:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				/* Battery present */
+				if (ret.intval)
+					di->events.batt_rem = false;
+				/* Battery removed */
+				else
+					di->events.batt_rem = true;
+				break;
+			case POWER_SUPPLY_TYPE_MAINS:
+				/* AC disconnected */
+				if (!ret.intval &&
+					(di->chg_info.conn_chg & AC_CHG)) {
+					di->chg_info.prev_conn_chg =
+						di->chg_info.conn_chg;
+					di->chg_info.conn_chg &= ~AC_CHG;
+				}
+				/* AC connected */
+				else if (ret.intval &&
+					!(di->chg_info.conn_chg & AC_CHG)) {
+					di->chg_info.prev_conn_chg =
+						di->chg_info.conn_chg;
+					di->chg_info.conn_chg |= AC_CHG;
+				}
+				break;
+			case POWER_SUPPLY_TYPE_USB:
+				/* USB disconnected */
+				if (!ret.intval &&
+					(di->chg_info.conn_chg & USB_CHG)) {
+					di->chg_info.prev_conn_chg =
+						di->chg_info.conn_chg;
+					di->chg_info.conn_chg &= ~USB_CHG;
+				}
+				/* USB connected */
+				else if (ret.intval &&
+					!(di->chg_info.conn_chg & USB_CHG)) {
+					di->chg_info.prev_conn_chg =
+						di->chg_info.conn_chg;
+					di->chg_info.conn_chg |= USB_CHG;
+				}
+				break;
+			default:
+				break;
+			}
+			break;
+
+		case POWER_SUPPLY_PROP_ONLINE:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				break;
+			case POWER_SUPPLY_TYPE_MAINS:
+				/* AC offline */
+				if (!ret.intval &&
+					(di->chg_info.online_chg & AC_CHG)) {
+					di->chg_info.prev_online_chg =
+						di->chg_info.online_chg;
+					di->chg_info.online_chg &= ~AC_CHG;
+				}
+				/* AC online */
+				else if (ret.intval &&
+					!(di->chg_info.online_chg & AC_CHG)) {
+					di->chg_info.prev_online_chg =
+						di->chg_info.online_chg;
+					di->chg_info.online_chg |= AC_CHG;
+					queue_delayed_work(di->chargalg_wq,
+						&di->chargalg_wd_work, 0);
+				}
+				break;
+			case POWER_SUPPLY_TYPE_USB:
+				/* USB offline */
+				if (!ret.intval &&
+					(di->chg_info.online_chg & USB_CHG)) {
+					di->chg_info.prev_online_chg =
+						di->chg_info.online_chg;
+					di->chg_info.online_chg &= ~USB_CHG;
+				}
+				/* USB online */
+				else if (ret.intval &&
+					!(di->chg_info.online_chg & USB_CHG)) {
+					di->chg_info.prev_online_chg =
+						di->chg_info.online_chg;
+					di->chg_info.online_chg |= USB_CHG;
+					queue_delayed_work(di->chargalg_wq,
+						&di->chargalg_wd_work, 0);
+				}
+				break;
+			default:
+				break;
+			}
+			break;
+
+		case POWER_SUPPLY_PROP_HEALTH:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				break;
+			case POWER_SUPPLY_TYPE_MAINS:
+				switch (ret.intval) {
+				case POWER_SUPPLY_HEALTH_UNSPEC_FAILURE:
+					di->events.mainextchnotok = true;
+					di->events.main_thermal_prot = false;
+					di->events.main_ovv = false;
+					di->events.ac_wd_expired = false;
+					break;
+				case POWER_SUPPLY_HEALTH_DEAD:
+					di->events.ac_wd_expired = true;
+					di->events.mainextchnotok = false;
+					di->events.main_ovv = false;
+					di->events.main_thermal_prot = false;
+					break;
+				case POWER_SUPPLY_HEALTH_COLD:
+				case POWER_SUPPLY_HEALTH_OVERHEAT:
+					di->events.main_thermal_prot = true;
+					di->events.mainextchnotok = false;
+					di->events.main_ovv = false;
+					di->events.ac_wd_expired = false;
+					break;
+				case POWER_SUPPLY_HEALTH_OVERVOLTAGE:
+					di->events.main_ovv = true;
+					di->events.mainextchnotok = false;
+					di->events.main_thermal_prot = false;
+					di->events.ac_wd_expired = false;
+					break;
+				case POWER_SUPPLY_HEALTH_GOOD:
+					di->events.main_thermal_prot = false;
+					di->events.mainextchnotok = false;
+					di->events.main_ovv = false;
+					di->events.ac_wd_expired = false;
+					break;
+				default:
+					break;
+				}
+				break;
+
+			case POWER_SUPPLY_TYPE_USB:
+				switch (ret.intval) {
+				case POWER_SUPPLY_HEALTH_UNSPEC_FAILURE:
+					di->events.usbchargernotok = true;
+					di->events.usb_thermal_prot = false;
+					di->events.vbus_ovv = false;
+					di->events.usb_wd_expired = false;
+					break;
+				case POWER_SUPPLY_HEALTH_DEAD:
+					di->events.usb_wd_expired = true;
+					di->events.usbchargernotok = false;
+					di->events.usb_thermal_prot = false;
+					di->events.vbus_ovv = false;
+					break;
+				case POWER_SUPPLY_HEALTH_COLD:
+				case POWER_SUPPLY_HEALTH_OVERHEAT:
+					di->events.usb_thermal_prot = true;
+					di->events.usbchargernotok = false;
+					di->events.vbus_ovv = false;
+					di->events.usb_wd_expired = false;
+					break;
+				case POWER_SUPPLY_HEALTH_OVERVOLTAGE:
+					di->events.vbus_ovv = true;
+					di->events.usbchargernotok = false;
+					di->events.usb_thermal_prot = false;
+					di->events.usb_wd_expired = false;
+					break;
+				case POWER_SUPPLY_HEALTH_GOOD:
+					di->events.usbchargernotok = false;
+					di->events.usb_thermal_prot = false;
+					di->events.vbus_ovv = false;
+					di->events.usb_wd_expired = false;
+					break;
+				default:
+					break;
+				}
+			default:
+				break;
+			}
+			break;
+
+		case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				di->batt_data.volt = ret.intval / 1000;
+				break;
+			case POWER_SUPPLY_TYPE_MAINS:
+				di->chg_info.ac_volt = ret.intval / 1000;
+				break;
+			case POWER_SUPPLY_TYPE_USB:
+				di->chg_info.usb_volt = ret.intval / 1000;
+				break;
+			default:
+				break;
+			}
+			break;
+
+		case POWER_SUPPLY_PROP_VOLTAGE_AVG:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_MAINS:
+				/* AVG is used to indicate when we are
+				 * in CV mode */
+				if (ret.intval)
+					di->events.ac_cv_active = true;
+				else
+					di->events.ac_cv_active = false;
+
+				break;
+			case POWER_SUPPLY_TYPE_USB:
+				/* AVG is used to indicate when we are
+				 * in CV mode */
+				if (ret.intval)
+					di->events.usb_cv_active = true;
+				else
+					di->events.usb_cv_active = false;
+
+				break;
+			default:
+				break;
+			}
+			break;
+
+		case POWER_SUPPLY_PROP_TECHNOLOGY:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				if (ret.intval)
+					di->events.batt_unknown = false;
+				else
+					di->events.batt_unknown = true;
+
+				break;
+			default:
+				break;
+			}
+			break;
+
+		case POWER_SUPPLY_PROP_TEMP:
+			di->batt_data.temp = ret.intval / 10;
+			break;
+
+		case POWER_SUPPLY_PROP_CURRENT_NOW:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_MAINS:
+					di->chg_info.ac_curr =
+						ret.intval / 1000;
+					break;
+			case POWER_SUPPLY_TYPE_USB:
+					di->chg_info.usb_curr =
+						ret.intval / 1000;
+				break;
+			case POWER_SUPPLY_TYPE_BATTERY:
+				di->batt_data.inst_curr = ret.intval / 1000;
+				break;
+			default:
+				break;
+			}
+			break;
+
+		case POWER_SUPPLY_PROP_CURRENT_AVG:
+			switch (ext->type) {
+			case POWER_SUPPLY_TYPE_BATTERY:
+				di->batt_data.avg_curr = ret.intval / 1000;
+				break;
+			case POWER_SUPPLY_TYPE_USB:
+				if (ret.intval)
+					di->events.vbus_collapsed = true;
+				else
+					di->events.vbus_collapsed = false;
+				break;
+			default:
+				break;
+			}
+			break;
+		case POWER_SUPPLY_PROP_CAPACITY:
+			di->batt_data.percent = ret.intval;
+			break;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+/**
+ * abx500_chargalg_external_power_changed() - callback for power supply changes
+ * @psy:       pointer to the structure power_supply
+ *
+ * This function is the entry point of the pointer external_power_changed
+ * of the structure power_supply.
+ * This function gets executed when there is a change in any external power
+ * supply that this driver needs to be notified of.
+ */
+static void abx500_chargalg_external_power_changed(struct power_supply *psy)
+{
+	struct abx500_chargalg *di = to_abx500_chargalg_device_info(psy);
+
+	/*
+	 * Trigger execution of the algorithm instantly and read
+	 * all power_supply properties there instead
+	 */
+	queue_work(di->chargalg_wq, &di->chargalg_work);
+}
+
+/**
+ * abx500_chargalg_algorithm() - Main function for the algorithm
+ * @di:		pointer to the abx500_chargalg structure
+ *
+ * This is the main control function for the charging algorithm.
+ * It is called periodically or when something happens that will
+ * trigger a state change
+ */
+static void abx500_chargalg_algorithm(struct abx500_chargalg *di)
+{
+	int charger_status;
+
+	/* Collect data from all power_supply class devices */
+	class_for_each_device(power_supply_class, NULL,
+		&di->chargalg_psy, abx500_chargalg_get_ext_psy_data);
+
+	abx500_chargalg_end_of_charge(di);
+	abx500_chargalg_check_temp(di);
+	abx500_chargalg_check_charger_voltage(di);
+
+	charger_status = abx500_chargalg_check_charger_connection(di);
+	/*
+	 * First check if we have a charger connected.
+	 * Also we don't allow charging of unknown batteries if configured
+	 * this way
+	 */
+	if (!charger_status ||
+		(di->events.batt_unknown && !di->bat->chg_unknown_bat)) {
+		if (di->charge_state != STATE_HANDHELD) {
+			di->events.safety_timer_expired = false;
+			abx500_chargalg_state_to(di, STATE_HANDHELD_INIT);
+		}
+	}
+
+	/* If suspended, we should not continue checking the flags */
+	else if (di->charge_state == STATE_SUSPENDED_INIT ||
+		di->charge_state == STATE_SUSPENDED) {
+		/* We don't do anything here, just don,t continue */
+	}
+
+	/* Safety timer expiration */
+	else if (di->events.safety_timer_expired) {
+		if (di->charge_state != STATE_SAFETY_TIMER_EXPIRED)
+			abx500_chargalg_state_to(di,
+				STATE_SAFETY_TIMER_EXPIRED_INIT);
+	}
+	/*
+	 * Check if any interrupts has occured
+	 * that will prevent us from charging
+	 */
+
+	/* Battery removed */
+	else if (di->events.batt_rem) {
+		if (di->charge_state != STATE_BATT_REMOVED)
+			abx500_chargalg_state_to(di, STATE_BATT_REMOVED_INIT);
+	}
+	/* Main or USB charger not ok. */
+	else if (di->events.mainextchnotok || di->events.usbchargernotok) {
+		/*
+		 * If vbus_collapsed is set, we have to lower the charger
+		 * current, which is done in the normal state below
+		 */
+		if (di->charge_state != STATE_CHG_NOT_OK &&
+				!di->events.vbus_collapsed)
+			abx500_chargalg_state_to(di, STATE_CHG_NOT_OK_INIT);
+	}
+	/* VBUS, Main or VBAT OVV. */
+	else if (di->events.vbus_ovv ||
+			di->events.main_ovv ||
+			di->events.batt_ovv ||
+			!di->chg_info.usb_chg_ok ||
+			!di->chg_info.ac_chg_ok) {
+		if (di->charge_state != STATE_OVV_PROTECT)
+			abx500_chargalg_state_to(di, STATE_OVV_PROTECT_INIT);
+	}
+	/* USB Thermal, stop charging */
+	else if (di->events.main_thermal_prot ||
+		di->events.usb_thermal_prot) {
+		if (di->charge_state != STATE_HW_TEMP_PROTECT)
+			abx500_chargalg_state_to(di,
+				STATE_HW_TEMP_PROTECT_INIT);
+	}
+	/* Battery temp over/under */
+	else if (di->events.btemp_underover) {
+		if (di->charge_state != STATE_TEMP_UNDEROVER)
+			abx500_chargalg_state_to(di,
+				STATE_TEMP_UNDEROVER_INIT);
+	}
+	/* Watchdog expired */
+	else if (di->events.ac_wd_expired ||
+		di->events.usb_wd_expired) {
+		if (di->charge_state != STATE_WD_EXPIRED)
+			abx500_chargalg_state_to(di, STATE_WD_EXPIRED_INIT);
+	}
+	/* Battery temp high/low */
+	else if (di->events.btemp_lowhigh) {
+		if (di->charge_state != STATE_TEMP_LOWHIGH)
+			abx500_chargalg_state_to(di, STATE_TEMP_LOWHIGH_INIT);
+	}
+
+	dev_dbg(di->dev,
+		"[CHARGALG] Vb %d Ib_avg %d Ib_inst %d Tb %d Cap %d Maint %d "
+		"State %s Active_chg %d Chg_status %d AC %d USB %d "
+		"AC_online %d USB_online %d AC_CV %d USB_CV %d AC_I %d "
+		"USB_I %d AC_Vset %d AC_Iset %d USB_Vset %d USB_Iset %d\n",
+		di->batt_data.volt,
+		di->batt_data.avg_curr,
+		di->batt_data.inst_curr,
+		di->batt_data.temp,
+		di->batt_data.percent,
+		di->maintenance_chg,
+		states[di->charge_state],
+		di->chg_info.charger_type,
+		di->charge_status,
+		di->chg_info.conn_chg & AC_CHG,
+		di->chg_info.conn_chg & USB_CHG,
+		di->chg_info.online_chg & AC_CHG,
+		di->chg_info.online_chg & USB_CHG,
+		di->events.ac_cv_active,
+		di->events.usb_cv_active,
+		di->chg_info.ac_curr,
+		di->chg_info.usb_curr,
+		di->chg_info.ac_vset,
+		di->chg_info.ac_iset,
+		di->chg_info.usb_vset,
+		di->chg_info.usb_iset);
+
+	switch (di->charge_state) {
+	case STATE_HANDHELD_INIT:
+		abx500_chargalg_stop_charging(di);
+		di->charge_status = POWER_SUPPLY_STATUS_DISCHARGING;
+		abx500_chargalg_state_to(di, STATE_HANDHELD);
+		/* Intentional fallthrough */
+
+	case STATE_HANDHELD:
+		break;
+
+	case STATE_SUSPENDED_INIT:
+		if (di->susp_status.ac_suspended)
+			abx500_chargalg_ac_en(di, false, 0, 0);
+		if (di->susp_status.usb_suspended)
+			abx500_chargalg_usb_en(di, false, 0, 0);
+		abx500_chargalg_stop_safety_timer(di);
+		abx500_chargalg_stop_maintenance_timer(di);
+		di->charge_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		di->maintenance_chg = false;
+		abx500_chargalg_state_to(di, STATE_SUSPENDED);
+		power_supply_changed(&di->chargalg_psy);
+		/* Intentional fallthrough */
+
+	case STATE_SUSPENDED:
+		/* CHARGING is suspended */
+		break;
+
+	case STATE_BATT_REMOVED_INIT:
+		abx500_chargalg_stop_charging(di);
+		abx500_chargalg_state_to(di, STATE_BATT_REMOVED);
+		/* Intentional fallthrough */
+
+	case STATE_BATT_REMOVED:
+		if (!di->events.batt_rem)
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		break;
+
+	case STATE_HW_TEMP_PROTECT_INIT:
+		abx500_chargalg_stop_charging(di);
+		abx500_chargalg_state_to(di, STATE_HW_TEMP_PROTECT);
+		/* Intentional fallthrough */
+
+	case STATE_HW_TEMP_PROTECT:
+		if (!di->events.main_thermal_prot &&
+				!di->events.usb_thermal_prot)
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		break;
+
+	case STATE_OVV_PROTECT_INIT:
+		abx500_chargalg_stop_charging(di);
+		abx500_chargalg_state_to(di, STATE_OVV_PROTECT);
+		/* Intentional fallthrough */
+
+	case STATE_OVV_PROTECT:
+		if (!di->events.vbus_ovv &&
+				!di->events.main_ovv &&
+				!di->events.batt_ovv &&
+				di->chg_info.usb_chg_ok &&
+				di->chg_info.ac_chg_ok)
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		break;
+
+	case STATE_CHG_NOT_OK_INIT:
+		abx500_chargalg_stop_charging(di);
+		abx500_chargalg_state_to(di, STATE_CHG_NOT_OK);
+		/* Intentional fallthrough */
+
+	case STATE_CHG_NOT_OK:
+		if (!di->events.mainextchnotok &&
+				!di->events.usbchargernotok)
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		break;
+
+	case STATE_SAFETY_TIMER_EXPIRED_INIT:
+		abx500_chargalg_stop_charging(di);
+		abx500_chargalg_state_to(di, STATE_SAFETY_TIMER_EXPIRED);
+		/* Intentional fallthrough */
+
+	case STATE_SAFETY_TIMER_EXPIRED:
+		/* We exit this state when charger is removed */
+		break;
+
+	case STATE_NORMAL_INIT:
+		abx500_chargalg_start_charging(di,
+			di->bat->bat_type[di->bat->batt_id].normal_vol_lvl,
+			di->bat->bat_type[di->bat->batt_id].normal_cur_lvl);
+		abx500_chargalg_state_to(di, STATE_NORMAL);
+		abx500_chargalg_start_safety_timer(di);
+		abx500_chargalg_stop_maintenance_timer(di);
+		init_maxim_chg_curr(di);
+		di->charge_status = POWER_SUPPLY_STATUS_CHARGING;
+		di->eoc_cnt = 0;
+		di->maintenance_chg = false;
+		power_supply_changed(&di->chargalg_psy);
+
+		break;
+
+	case STATE_NORMAL:
+		handle_maxim_chg_curr(di);
+		if (di->charge_status == POWER_SUPPLY_STATUS_FULL &&
+			di->maintenance_chg) {
+			if (di->bat->no_maintenance)
+				abx500_chargalg_state_to(di,
+					STATE_WAIT_FOR_RECHARGE_INIT);
+			else
+				abx500_chargalg_state_to(di,
+					STATE_MAINTENANCE_A_INIT);
+		}
+		break;
+
+	/* This state will be used when the maintenance state is disabled */
+	case STATE_WAIT_FOR_RECHARGE_INIT:
+		abx500_chargalg_hold_charging(di);
+		abx500_chargalg_state_to(di, STATE_WAIT_FOR_RECHARGE);
+		di->rch_cnt = RCH_COND_CNT;
+		/* Intentional fallthrough */
+
+	case STATE_WAIT_FOR_RECHARGE:
+		if (di->batt_data.volt <=
+			di->bat->bat_type[di->bat->batt_id].recharge_vol) {
+			if (di->rch_cnt-- == 0)
+				abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		} else
+			di->rch_cnt = RCH_COND_CNT;
+		break;
+
+	case STATE_MAINTENANCE_A_INIT:
+		abx500_chargalg_stop_safety_timer(di);
+		abx500_chargalg_start_maintenance_timer(di,
+			di->bat->bat_type[
+				di->bat->batt_id].maint_a_chg_timer_h);
+		abx500_chargalg_start_charging(di,
+			di->bat->bat_type[
+				di->bat->batt_id].maint_a_vol_lvl,
+			di->bat->bat_type[
+				di->bat->batt_id].maint_a_cur_lvl);
+		abx500_chargalg_state_to(di, STATE_MAINTENANCE_A);
+		power_supply_changed(&di->chargalg_psy);
+		/* Intentional fallthrough*/
+
+	case STATE_MAINTENANCE_A:
+		if (di->events.maintenance_timer_expired) {
+			abx500_chargalg_stop_maintenance_timer(di);
+			abx500_chargalg_state_to(di, STATE_MAINTENANCE_B_INIT);
+		}
+		break;
+
+	case STATE_MAINTENANCE_B_INIT:
+		abx500_chargalg_start_maintenance_timer(di,
+			di->bat->bat_type[
+				di->bat->batt_id].maint_b_chg_timer_h);
+		abx500_chargalg_start_charging(di,
+			di->bat->bat_type[
+				di->bat->batt_id].maint_b_vol_lvl,
+			di->bat->bat_type[
+				di->bat->batt_id].maint_b_cur_lvl);
+		abx500_chargalg_state_to(di, STATE_MAINTENANCE_B);
+		power_supply_changed(&di->chargalg_psy);
+		/* Intentional fallthrough*/
+
+	case STATE_MAINTENANCE_B:
+		if (di->events.maintenance_timer_expired) {
+			abx500_chargalg_stop_maintenance_timer(di);
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		}
+		break;
+
+	case STATE_TEMP_LOWHIGH_INIT:
+		abx500_chargalg_start_charging(di,
+			di->bat->bat_type[
+				di->bat->batt_id].low_high_vol_lvl,
+			di->bat->bat_type[
+				di->bat->batt_id].low_high_cur_lvl);
+		abx500_chargalg_stop_maintenance_timer(di);
+		di->charge_status = POWER_SUPPLY_STATUS_CHARGING;
+		abx500_chargalg_state_to(di, STATE_TEMP_LOWHIGH);
+		power_supply_changed(&di->chargalg_psy);
+		/* Intentional fallthrough */
+
+	case STATE_TEMP_LOWHIGH:
+		if (!di->events.btemp_lowhigh)
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		break;
+
+	case STATE_WD_EXPIRED_INIT:
+		abx500_chargalg_stop_charging(di);
+		abx500_chargalg_state_to(di, STATE_WD_EXPIRED);
+		/* Intentional fallthrough */
+
+	case STATE_WD_EXPIRED:
+		if (!di->events.ac_wd_expired &&
+				!di->events.usb_wd_expired)
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		break;
+
+	case STATE_TEMP_UNDEROVER_INIT:
+		abx500_chargalg_stop_charging(di);
+		abx500_chargalg_state_to(di, STATE_TEMP_UNDEROVER);
+		/* Intentional fallthrough */
+
+	case STATE_TEMP_UNDEROVER:
+		if (!di->events.btemp_underover)
+			abx500_chargalg_state_to(di, STATE_NORMAL_INIT);
+		break;
+	}
+
+	/* Start charging directly if the new state is a charge state */
+	if (di->charge_state == STATE_NORMAL_INIT ||
+			di->charge_state == STATE_MAINTENANCE_A_INIT ||
+			di->charge_state == STATE_MAINTENANCE_B_INIT)
+		queue_work(di->chargalg_wq, &di->chargalg_work);
+}
+
+/**
+ * abx500_chargalg_periodic_work() - Periodic work for the algorithm
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for the charging algorithm
+ */
+static void abx500_chargalg_periodic_work(struct work_struct *work)
+{
+	struct abx500_chargalg *di = container_of(work,
+		struct abx500_chargalg, chargalg_periodic_work.work);
+
+	abx500_chargalg_algorithm(di);
+
+	/*
+	 * If a charger is connected then the battery has to be monitored
+	 * frequently, else the work can be delayed.
+	 */
+	if (di->chg_info.conn_chg)
+		queue_delayed_work(di->chargalg_wq,
+			&di->chargalg_periodic_work,
+			di->bat->interval_charging * HZ);
+	else
+		queue_delayed_work(di->chargalg_wq,
+			&di->chargalg_periodic_work,
+			di->bat->interval_not_charging * HZ);
+}
+
+/**
+ * abx500_chargalg_wd_work() - periodic work to kick the charger watchdog
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for kicking the charger watchdog
+ */
+static void abx500_chargalg_wd_work(struct work_struct *work)
+{
+	int ret;
+	struct abx500_chargalg *di = container_of(work,
+		struct abx500_chargalg, chargalg_wd_work.work);
+
+	dev_dbg(di->dev, "abx500_chargalg_wd_work\n");
+
+	ret = abx500_chargalg_kick_watchdog(di);
+	if (ret < 0)
+		dev_err(di->dev, "failed to kick watchdog\n");
+
+	queue_delayed_work(di->chargalg_wq,
+		&di->chargalg_wd_work, CHG_WD_INTERVAL);
+}
+
+/**
+ * abx500_chargalg_work() - Work to run the charging algorithm instantly
+ * @work:	pointer to the work_struct structure
+ *
+ * Work queue function for calling the charging algorithm
+ */
+static void abx500_chargalg_work(struct work_struct *work)
+{
+	struct abx500_chargalg *di = container_of(work,
+		struct abx500_chargalg, chargalg_work);
+
+	abx500_chargalg_algorithm(di);
+}
+
+/**
+ * abx500_chargalg_get_property() - get the chargalg properties
+ * @psy:	pointer to the power_supply structure
+ * @psp:	pointer to the power_supply_property structure
+ * @val:	pointer to the power_supply_propval union
+ *
+ * This function gets called when an application tries to get the
+ * chargalg properties by reading the sysfs files.
+ * status:     charging/discharging/full/unknown
+ * health:     health of the battery
+ * Returns error code in case of failure else 0 on success
+ */
+static int abx500_chargalg_get_property(struct power_supply *psy,
+	enum power_supply_property psp,
+	union power_supply_propval *val)
+{
+	struct abx500_chargalg *di;
+
+	di = to_abx500_chargalg_device_info(psy);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_STATUS:
+		val->intval = di->charge_status;
+		break;
+	case POWER_SUPPLY_PROP_HEALTH:
+		if (di->events.batt_ovv) {
+			val->intval = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
+		} else if (di->events.btemp_underover) {
+			if (di->batt_data.temp <= di->bat->temp_under)
+				val->intval = POWER_SUPPLY_HEALTH_COLD;
+			else
+				val->intval = POWER_SUPPLY_HEALTH_OVERHEAT;
+		} else {
+			val->intval = POWER_SUPPLY_HEALTH_GOOD;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Exposure to the sysfs interface */
+
+/**
+ * abx500_chargalg_sysfs_charger() - sysfs store operations
+ * @kobj:      pointer to the struct kobject
+ * @attr:      pointer to the struct attribute
+ * @buf:       buffer that holds the parameter passed from userspace
+ * @length:    length of the parameter passed
+ *
+ * Returns length of the buffer(input taken from user space) on success
+ * else error code on failure
+ * The operation to be performed on passing the parameters from the user space.
+ */
+static ssize_t abx500_chargalg_sysfs_charger(struct kobject *kobj,
+	struct attribute *attr, const char *buf, size_t length)
+{
+	struct abx500_chargalg *di = container_of(kobj,
+		struct abx500_chargalg, chargalg_kobject);
+	long int param;
+	int ac_usb;
+	int ret;
+	char entry = *attr->name;
+
+	switch (entry) {
+	case 'c':
+		ret = strict_strtol(buf, 10, &param);
+		if (ret < 0)
+			return ret;
+
+		ac_usb = param;
+		switch (ac_usb) {
+		case 0:
+			/* Disable charging */
+			di->susp_status.ac_suspended = true;
+			di->susp_status.usb_suspended = true;
+			di->susp_status.suspended_change = true;
+			/* Trigger a state change */
+			queue_work(di->chargalg_wq,
+				&di->chargalg_work);
+			break;
+		case 1:
+			/* Enable AC Charging */
+			di->susp_status.ac_suspended = false;
+			di->susp_status.suspended_change = true;
+			/* Trigger a state change */
+			queue_work(di->chargalg_wq,
+				&di->chargalg_work);
+			break;
+		case 2:
+			/* Enable USB charging */
+			di->susp_status.usb_suspended = false;
+			di->susp_status.suspended_change = true;
+			/* Trigger a state change */
+			queue_work(di->chargalg_wq,
+				&di->chargalg_work);
+			break;
+		default:
+			dev_info(di->dev, "Wrong input\n"
+				"Enter 0. Disable AC/USB Charging\n"
+				"1. Enable AC charging\n"
+				"2. Enable USB Charging\n");
+		};
+		break;
+	};
+	return strlen(buf);
+}
+
+static struct attribute abx500_chargalg_en_charger = \
+{
+	.name = "chargalg",
+	.mode = S_IWUGO,
+};
+
+static struct attribute *abx500_chargalg_chg[] = {
+	&abx500_chargalg_en_charger,
+	NULL
+};
+
+static const struct sysfs_ops abx500_chargalg_sysfs_ops = {
+	.store = abx500_chargalg_sysfs_charger,
+};
+
+static struct kobj_type abx500_chargalg_ktype = {
+	.sysfs_ops = &abx500_chargalg_sysfs_ops,
+	.default_attrs = abx500_chargalg_chg,
+};
+
+/**
+ * abx500_chargalg_sysfs_exit() - de-init of sysfs entry
+ * @di:                pointer to the struct abx500_chargalg
+ *
+ * This function removes the entry in sysfs.
+ */
+static void abx500_chargalg_sysfs_exit(struct abx500_chargalg *di)
+{
+	kobject_del(&di->chargalg_kobject);
+}
+
+/**
+ * abx500_chargalg_sysfs_init() - init of sysfs entry
+ * @di:                pointer to the struct abx500_chargalg
+ *
+ * This function adds an entry in sysfs.
+ * Returns error code in case of failure else 0(on success)
+ */
+static int abx500_chargalg_sysfs_init(struct abx500_chargalg *di)
+{
+	int ret = 0;
+
+	ret = kobject_init_and_add(&di->chargalg_kobject,
+		&abx500_chargalg_ktype,
+		NULL, "abx500_chargalg");
+	if (ret < 0)
+		dev_err(di->dev, "failed to create sysfs entry\n");
+
+	return ret;
+}
+/* Exposure to the sysfs interface <<END>> */
+
+#if defined(CONFIG_PM)
+static int abx500_chargalg_resume(struct platform_device *pdev)
+{
+	struct abx500_chargalg *di = platform_get_drvdata(pdev);
+
+	/* Kick charger watchdog if charging (any charger online) */
+	if (di->chg_info.online_chg)
+		queue_delayed_work(di->chargalg_wq, &di->chargalg_wd_work, 0);
+
+	/*
+	 * Run the charging algorithm directly to be sure we don't
+	 * do it too seldom
+	 */
+	queue_delayed_work(di->chargalg_wq, &di->chargalg_periodic_work, 0);
+
+	return 0;
+}
+
+static int abx500_chargalg_suspend(struct platform_device *pdev,
+	pm_message_t state)
+{
+	struct abx500_chargalg *di = platform_get_drvdata(pdev);
+
+	if (di->chg_info.online_chg)
+		cancel_delayed_work_sync(&di->chargalg_wd_work);
+
+	cancel_delayed_work_sync(&di->chargalg_periodic_work);
+
+	return 0;
+}
+#else
+#define abx500_chargalg_suspend      NULL
+#define abx500_chargalg_resume       NULL
+#endif
+
+static int __devexit abx500_chargalg_remove(struct platform_device *pdev)
+{
+	struct abx500_chargalg *di = platform_get_drvdata(pdev);
+
+	/* sysfs interface to enable/disbale charging from user space */
+	abx500_chargalg_sysfs_exit(di);
+
+	/* Delete the work queue */
+	destroy_workqueue(di->chargalg_wq);
+
+	flush_scheduled_work();
+	power_supply_unregister(&di->chargalg_psy);
+	platform_set_drvdata(pdev, NULL);
+	kfree(di);
+
+	return 0;
+}
+
+static int __devinit abx500_chargalg_probe(struct platform_device *pdev)
+{
+	struct abx500_bm_plat_data *plat_data;
+	int ret = 0;
+
+	struct abx500_chargalg *di =
+		kzalloc(sizeof(struct abx500_chargalg), GFP_KERNEL);
+	if (!di)
+		return -ENOMEM;
+
+	/* get device struct */
+	di->dev = &pdev->dev;
+
+	plat_data = pdev->dev.platform_data;
+	di->pdata = plat_data->chargalg;
+	di->bat = plat_data->battery;
+
+	/* chargalg supply */
+	di->chargalg_psy.name = "abx500_chargalg";
+	di->chargalg_psy.type = POWER_SUPPLY_TYPE_BATTERY;
+	di->chargalg_psy.properties = abx500_chargalg_props;
+	di->chargalg_psy.num_properties = ARRAY_SIZE(abx500_chargalg_props);
+	di->chargalg_psy.get_property = abx500_chargalg_get_property;
+	di->chargalg_psy.supplied_to = di->pdata->supplied_to;
+	di->chargalg_psy.num_supplicants = di->pdata->num_supplicants;
+	di->chargalg_psy.external_power_changed =
+		abx500_chargalg_external_power_changed;
+
+	/* Initilialize safety timer */
+	init_timer(&di->safety_timer);
+	di->safety_timer.function = abx500_chargalg_safety_timer_expired;
+	di->safety_timer.data = (unsigned long) di;
+
+	/* Initilialize maintenance timer */
+	init_timer(&di->maintenance_timer);
+	di->maintenance_timer.function =
+		abx500_chargalg_maintenance_timer_expired;
+	di->maintenance_timer.data = (unsigned long) di;
+
+	/* Create a work queue for the chargalg */
+	di->chargalg_wq =
+		create_singlethread_workqueue("abx500_chargalg_wq");
+	if (di->chargalg_wq == NULL) {
+		dev_err(di->dev, "failed to create work queue\n");
+		goto free_device_info;
+	}
+
+	/* Init work for chargalg */
+	INIT_DELAYED_WORK_DEFERRABLE(&di->chargalg_periodic_work,
+		abx500_chargalg_periodic_work);
+	INIT_DELAYED_WORK_DEFERRABLE(&di->chargalg_wd_work,
+		abx500_chargalg_wd_work);
+
+	/* Init work for chargalg */
+	INIT_WORK(&di->chargalg_work, abx500_chargalg_work);
+
+	/* To detect charger at startup */
+	di->chg_info.prev_conn_chg = -1;
+
+	/* Register chargalg power supply class */
+	ret = power_supply_register(di->dev, &di->chargalg_psy);
+	if (ret) {
+		dev_err(di->dev, "failed to register chargalg psy\n");
+		goto free_chargalg_wq;
+	}
+
+	platform_set_drvdata(pdev, di);
+
+	/* sysfs interface to enable/disable charging from user space */
+	ret = abx500_chargalg_sysfs_init(di);
+	if (ret) {
+		dev_err(di->dev, "failed to create sysfs entry\n");
+		goto free_psy;
+	}
+
+	/* Run the charging algorithm */
+	queue_delayed_work(di->chargalg_wq, &di->chargalg_periodic_work, 0);
+
+	dev_info(di->dev, "probe success\n");
+	return ret;
+
+free_psy:
+	power_supply_unregister(&di->chargalg_psy);
+free_chargalg_wq:
+	destroy_workqueue(di->chargalg_wq);
+free_device_info:
+	kfree(di);
+
+	return ret;
+}
+
+static struct platform_driver abx500_chargalg_driver = {
+	.probe = abx500_chargalg_probe,
+	.remove = __devexit_p(abx500_chargalg_remove),
+	.suspend = abx500_chargalg_suspend,
+	.resume = abx500_chargalg_resume,
+	.driver = {
+		.name = "abx500-chargalg",
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init abx500_chargalg_init(void)
+{
+	return platform_driver_register(&abx500_chargalg_driver);
+}
+
+static void __exit abx500_chargalg_exit(void)
+{
+	platform_driver_unregister(&abx500_chargalg_driver);
+}
+
+module_init(abx500_chargalg_init);
+module_exit(abx500_chargalg_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Johan Palsson, Karl Komierowski");
+MODULE_ALIAS("platform:abx500-chargalg");
+MODULE_DESCRIPTION("abx500 battery charging algorithm");
diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c
index 88fd9710bda2..9eca9f1ff0ea 100644
--- a/drivers/power/charger-manager.c
+++ b/drivers/power/charger-manager.c
@@ -134,12 +134,11 @@ static int get_batt_uV(struct charger_manager *cm, int *uV)
 	union power_supply_propval val;
 	int ret;
 
-	if (cm->fuel_gauge)
-		ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
-				POWER_SUPPLY_PROP_VOLTAGE_NOW, &val);
-	else
+	if (!cm->fuel_gauge)
 		return -ENODEV;
 
+	ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+				POWER_SUPPLY_PROP_VOLTAGE_NOW, &val);
 	if (ret)
 		return ret;
 
@@ -245,9 +244,7 @@ static int try_charger_enable(struct charger_manager *cm, bool enable)
 	struct charger_desc *desc = cm->desc;
 
 	/* Ignore if it's redundent command */
-	if (enable && cm->charger_enabled)
-		return 0;
-	if (!enable && !cm->charger_enabled)
+	if (enable == cm->charger_enabled)
 		return 0;
 
 	if (enable) {
@@ -309,9 +306,7 @@ static void uevent_notify(struct charger_manager *cm, const char *event)
 
 		if (!strncmp(env_str_save, event, UEVENT_BUF_SIZE))
 			return; /* Duplicated. */
-		else
-			strncpy(env_str_save, event, UEVENT_BUF_SIZE);
-
+		strncpy(env_str_save, event, UEVENT_BUF_SIZE);
 		return;
 	}
 
@@ -387,8 +382,10 @@ static bool cm_monitor(void)
 
 	mutex_lock(&cm_list_mtx);
 
-	list_for_each_entry(cm, &cm_list, entry)
-		stop = stop || _cm_monitor(cm);
+	list_for_each_entry(cm, &cm_list, entry) {
+		if (_cm_monitor(cm))
+			stop = true;
+	}
 
 	mutex_unlock(&cm_list_mtx);
 
@@ -402,7 +399,8 @@ static int charger_get_property(struct power_supply *psy,
 	struct charger_manager *cm = container_of(psy,
 			struct charger_manager, charger_psy);
 	struct charger_desc *desc = cm->desc;
-	int i, ret = 0, uV;
+	int ret = 0;
+	int uV;
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
@@ -428,8 +426,7 @@ static int charger_get_property(struct power_supply *psy,
 			val->intval = 0;
 		break;
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
-		ret = get_batt_uV(cm, &i);
-		val->intval = i;
+		ret = get_batt_uV(cm, &val->intval);
 		break;
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
 		ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
@@ -697,8 +694,10 @@ bool cm_suspend_again(void)
 	mutex_lock(&cm_list_mtx);
 	list_for_each_entry(cm, &cm_list, entry) {
 		if (cm->status_save_ext_pwr_inserted != is_ext_pwr_online(cm) ||
-		    cm->status_save_batt != is_batt_present(cm))
+		    cm->status_save_batt != is_batt_present(cm)) {
 			ret = false;
+			break;
+		}
 	}
 	mutex_unlock(&cm_list_mtx);
 
@@ -855,11 +854,10 @@ static int charger_manager_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, cm);
 
-	memcpy(&cm->charger_psy, &psy_default,
-				sizeof(psy_default));
+	memcpy(&cm->charger_psy, &psy_default, sizeof(psy_default));
+
 	if (!desc->psy_name) {
-		strncpy(cm->psy_name_buf, psy_default.name,
-				PSY_NAME_MAX);
+		strncpy(cm->psy_name_buf, psy_default.name, PSY_NAME_MAX);
 	} else {
 		strncpy(cm->psy_name_buf, desc->psy_name, PSY_NAME_MAX);
 	}
@@ -894,15 +892,15 @@ static int charger_manager_probe(struct platform_device *pdev)
 				POWER_SUPPLY_PROP_CURRENT_NOW;
 		cm->charger_psy.num_properties++;
 	}
-	if (!desc->measure_battery_temp) {
-		cm->charger_psy.properties[cm->charger_psy.num_properties] =
-				POWER_SUPPLY_PROP_TEMP_AMBIENT;
-		cm->charger_psy.num_properties++;
-	}
+
 	if (desc->measure_battery_temp) {
 		cm->charger_psy.properties[cm->charger_psy.num_properties] =
 				POWER_SUPPLY_PROP_TEMP;
 		cm->charger_psy.num_properties++;
+	} else {
+		cm->charger_psy.properties[cm->charger_psy.num_properties] =
+				POWER_SUPPLY_PROP_TEMP_AMBIENT;
+		cm->charger_psy.num_properties++;
 	}
 
 	ret = power_supply_register(NULL, &cm->charger_psy);
@@ -933,9 +931,8 @@ static int charger_manager_probe(struct platform_device *pdev)
 	return 0;
 
 err_chg_enable:
-	if (desc->charger_regulators)
-		regulator_bulk_free(desc->num_charger_regulators,
-					desc->charger_regulators);
+	regulator_bulk_free(desc->num_charger_regulators,
+			    desc->charger_regulators);
 err_bulk_get:
 	power_supply_unregister(&cm->charger_psy);
 err_register:
@@ -961,10 +958,8 @@ static int __devexit charger_manager_remove(struct platform_device *pdev)
 	list_del(&cm->entry);
 	mutex_unlock(&cm_list_mtx);
 
-	if (desc->charger_regulators)
-		regulator_bulk_free(desc->num_charger_regulators,
-					desc->charger_regulators);
-
+	regulator_bulk_free(desc->num_charger_regulators,
+			    desc->charger_regulators);
 	power_supply_unregister(&cm->charger_psy);
 	kfree(cm->charger_psy.properties);
 	kfree(cm->charger_stat);
@@ -982,9 +977,7 @@ MODULE_DEVICE_TABLE(platform, charger_manager_id);
 
 static int cm_suspend_prepare(struct device *dev)
 {
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct charger_manager *cm = platform_get_drvdata(pdev);
+	struct charger_manager *cm = dev_get_drvdata(dev);
 
 	if (!cm_suspended) {
 		if (rtc_dev) {
@@ -1020,9 +1013,7 @@ static int cm_suspend_prepare(struct device *dev)
 
 static void cm_suspend_complete(struct device *dev)
 {
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct charger_manager *cm = platform_get_drvdata(pdev);
+	struct charger_manager *cm = dev_get_drvdata(dev);
 
 	if (cm_suspended) {
 		if (rtc_dev) {
diff --git a/drivers/power/da9052-battery.c b/drivers/power/da9052-battery.c
index e8ea47a53dee..a5f6a0ec1572 100644
--- a/drivers/power/da9052-battery.c
+++ b/drivers/power/da9052-battery.c
@@ -612,6 +612,7 @@ static s32 __devinit da9052_bat_probe(struct platform_device *pdev)
 	 if (ret)
 		goto err;
 
+	platform_set_drvdata(pdev, bat);
 	return 0;
 
 err:
@@ -633,6 +634,7 @@ static int __devexit da9052_bat_remove(struct platform_device *pdev)
 		free_irq(bat->da9052->irq_base + irq, bat);
 	}
 	power_supply_unregister(&bat->psy);
+	kfree(bat);
 
 	return 0;
 }
@@ -645,18 +647,7 @@ static struct platform_driver da9052_bat_driver = {
 		.owner = THIS_MODULE,
 	},
 };
-
-static int __init da9052_bat_init(void)
-{
-	return platform_driver_register(&da9052_bat_driver);
-}
-module_init(da9052_bat_init);
-
-static void __exit da9052_bat_exit(void)
-{
-	platform_driver_unregister(&da9052_bat_driver);
-}
-module_exit(da9052_bat_exit);
+module_platform_driver(da9052_bat_driver);
 
 MODULE_DESCRIPTION("DA9052 BAT Device Driver");
 MODULE_AUTHOR("David Dajun Chen <dchen@diasemi.com>");
diff --git a/drivers/power/ds2782_battery.c b/drivers/power/ds2782_battery.c
index bfbce5de49da..6bb6e2f5ea81 100644
--- a/drivers/power/ds2782_battery.c
+++ b/drivers/power/ds2782_battery.c
@@ -403,18 +403,7 @@ static struct i2c_driver ds278x_battery_driver = {
 	.remove		= ds278x_battery_remove,
 	.id_table	= ds278x_id,
 };
-
-static int __init ds278x_init(void)
-{
-	return i2c_add_driver(&ds278x_battery_driver);
-}
-module_init(ds278x_init);
-
-static void __exit ds278x_exit(void)
-{
-	i2c_del_driver(&ds278x_battery_driver);
-}
-module_exit(ds278x_exit);
+module_i2c_driver(ds278x_battery_driver);
 
 MODULE_AUTHOR("Ryan Mallon");
 MODULE_DESCRIPTION("Maxim/Dallas DS2782 Stand-Alone Fuel Gauage IC driver");
diff --git a/drivers/power/isp1704_charger.c b/drivers/power/isp1704_charger.c
index 1289a5f790a1..39eb50f35f09 100644
--- a/drivers/power/isp1704_charger.c
+++ b/drivers/power/isp1704_charger.c
@@ -480,6 +480,7 @@ fail0:
 
 	dev_err(&pdev->dev, "failed to register isp1704 with error %d\n", ret);
 
+	isp1704_charger_set_power(isp, 0);
 	return ret;
 }
 
diff --git a/drivers/power/lp8727_charger.c b/drivers/power/lp8727_charger.c
index c53dd1292f81..d8b75780bfef 100644
--- a/drivers/power/lp8727_charger.c
+++ b/drivers/power/lp8727_charger.c
@@ -1,6 +1,7 @@
 /*
- * Driver for LP8727 Micro/Mini USB IC with intergrated charger
+ * Driver for LP8727 Micro/Mini USB IC with integrated charger
  *
+ *			Copyright (C) 2011 Texas Instruments
  *			Copyright (C) 2011 National Semiconductor
  *
  * This program is free software; you can redistribute it and/or modify
@@ -25,7 +26,7 @@
 #define INT1		0x4
 #define INT2		0x5
 #define STATUS1		0x6
-#define STATUS2 	0x7
+#define STATUS2		0x7
 #define CHGCTRL2	0x9
 
 /* CTRL1 register */
@@ -91,7 +92,7 @@ struct lp8727_chg {
 	enum lp8727_dev_id devid;
 };
 
-static int lp8727_i2c_read(struct lp8727_chg *pchg, u8 reg, u8 *data, u8 len)
+static int lp8727_read_bytes(struct lp8727_chg *pchg, u8 reg, u8 *data, u8 len)
 {
 	s32 ret;
 
@@ -102,29 +103,22 @@ static int lp8727_i2c_read(struct lp8727_chg *pchg, u8 reg, u8 *data, u8 len)
 	return (ret != len) ? -EIO : 0;
 }
 
-static int lp8727_i2c_write(struct lp8727_chg *pchg, u8 reg, u8 *data, u8 len)
+static inline int lp8727_read_byte(struct lp8727_chg *pchg, u8 reg, u8 *data)
 {
-	s32 ret;
+	return lp8727_read_bytes(pchg, reg, data, 1);
+}
+
+static int lp8727_write_byte(struct lp8727_chg *pchg, u8 reg, u8 data)
+{
+	int ret;
 
 	mutex_lock(&pchg->xfer_lock);
-	ret = i2c_smbus_write_i2c_block_data(pchg->client, reg, len, data);
+	ret = i2c_smbus_write_byte_data(pchg->client, reg, data);
 	mutex_unlock(&pchg->xfer_lock);
 
 	return ret;
 }
 
-static inline int lp8727_i2c_read_byte(struct lp8727_chg *pchg, u8 reg,
-				       u8 *data)
-{
-	return lp8727_i2c_read(pchg, reg, data, 1);
-}
-
-static inline int lp8727_i2c_write_byte(struct lp8727_chg *pchg, u8 reg,
-					u8 *data)
-{
-	return lp8727_i2c_write(pchg, reg, data, 1);
-}
-
 static int lp8727_is_charger_attached(const char *name, int id)
 {
 	if (name) {
@@ -137,37 +131,41 @@ static int lp8727_is_charger_attached(const char *name, int id)
 	return (id >= ID_TA && id <= ID_USB_CHG) ? 1 : 0;
 }
 
-static void lp8727_init_device(struct lp8727_chg *pchg)
+static int lp8727_init_device(struct lp8727_chg *pchg)
 {
 	u8 val;
+	int ret;
 
 	val = ID200_EN | ADC_EN | CP_EN;
-	if (lp8727_i2c_write_byte(pchg, CTRL1, &val))
-		dev_err(pchg->dev, "i2c write err : addr=0x%.2x\n", CTRL1);
+	ret = lp8727_write_byte(pchg, CTRL1, val);
+	if (ret)
+		return ret;
 
 	val = INT_EN | CHGDET_EN;
-	if (lp8727_i2c_write_byte(pchg, CTRL2, &val))
-		dev_err(pchg->dev, "i2c write err : addr=0x%.2x\n", CTRL2);
+	ret = lp8727_write_byte(pchg, CTRL2, val);
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
 static int lp8727_is_dedicated_charger(struct lp8727_chg *pchg)
 {
 	u8 val;
-	lp8727_i2c_read_byte(pchg, STATUS1, &val);
-	return (val & DCPORT);
+	lp8727_read_byte(pchg, STATUS1, &val);
+	return val & DCPORT;
 }
 
 static int lp8727_is_usb_charger(struct lp8727_chg *pchg)
 {
 	u8 val;
-	lp8727_i2c_read_byte(pchg, STATUS1, &val);
-	return (val & CHPORT);
+	lp8727_read_byte(pchg, STATUS1, &val);
+	return val & CHPORT;
 }
 
 static void lp8727_ctrl_switch(struct lp8727_chg *pchg, u8 sw)
 {
-	u8 val = sw;
-	lp8727_i2c_write_byte(pchg, SWCTRL, &val);
+	lp8727_write_byte(pchg, SWCTRL, sw);
 }
 
 static void lp8727_id_detection(struct lp8727_chg *pchg, u8 id, int vbusin)
@@ -207,9 +205,9 @@ static void lp8727_enable_chgdet(struct lp8727_chg *pchg)
 {
 	u8 val;
 
-	lp8727_i2c_read_byte(pchg, CTRL2, &val);
+	lp8727_read_byte(pchg, CTRL2, &val);
 	val |= CHGDET_EN;
-	lp8727_i2c_write_byte(pchg, CTRL2, &val);
+	lp8727_write_byte(pchg, CTRL2, val);
 }
 
 static void lp8727_delayed_func(struct work_struct *_work)
@@ -218,7 +216,7 @@ static void lp8727_delayed_func(struct work_struct *_work)
 	struct lp8727_chg *pchg =
 	    container_of(_work, struct lp8727_chg, work.work);
 
-	if (lp8727_i2c_read(pchg, INT1, intstat, 2)) {
+	if (lp8727_read_bytes(pchg, INT1, intstat, 2)) {
 		dev_err(pchg->dev, "can not read INT registers\n");
 		return;
 	}
@@ -244,20 +242,22 @@ static irqreturn_t lp8727_isr_func(int irq, void *ptr)
 	return IRQ_HANDLED;
 }
 
-static void lp8727_intr_config(struct lp8727_chg *pchg)
+static int lp8727_intr_config(struct lp8727_chg *pchg)
 {
 	INIT_DELAYED_WORK(&pchg->work, lp8727_delayed_func);
 
 	pchg->irqthread = create_singlethread_workqueue("lp8727-irqthd");
-	if (!pchg->irqthread)
+	if (!pchg->irqthread) {
 		dev_err(pchg->dev, "can not create thread for lp8727\n");
-
-	if (request_threaded_irq(pchg->client->irq,
-				 NULL,
-				 lp8727_isr_func,
-				 IRQF_TRIGGER_FALLING, "lp8727_irq", pchg)) {
-		dev_err(pchg->dev, "lp8727 irq can not be registered\n");
+		return -ENOMEM;
 	}
+
+	return request_threaded_irq(pchg->client->irq,
+				NULL,
+				lp8727_isr_func,
+				IRQF_TRIGGER_FALLING,
+				"lp8727_irq",
+				pchg);
 }
 
 static enum power_supply_property lp8727_charger_prop[] = {
@@ -300,7 +300,7 @@ static int lp8727_battery_get_property(struct power_supply *psy,
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
 		if (lp8727_is_charger_attached(psy->name, pchg->devid)) {
-			lp8727_i2c_read_byte(pchg, STATUS1, &read);
+			lp8727_read_byte(pchg, STATUS1, &read);
 			if (((read & CHGSTAT) >> 4) == EOC)
 				val->intval = POWER_SUPPLY_STATUS_FULL;
 			else
@@ -310,7 +310,7 @@ static int lp8727_battery_get_property(struct power_supply *psy,
 		}
 		break;
 	case POWER_SUPPLY_PROP_HEALTH:
-		lp8727_i2c_read_byte(pchg, STATUS2, &read);
+		lp8727_read_byte(pchg, STATUS2, &read);
 		read = (read & TEMP_STAT) >> 5;
 		if (read >= 0x1 && read <= 0x3)
 			val->intval = POWER_SUPPLY_HEALTH_OVERHEAT;
@@ -351,7 +351,7 @@ static void lp8727_charger_changed(struct power_supply *psy)
 			eoc_level = pchg->chg_parm->eoc_level;
 			ichg = pchg->chg_parm->ichg;
 			val = (ichg << 4) | eoc_level;
-			lp8727_i2c_write_byte(pchg, CHGCTRL2, &val);
+			lp8727_write_byte(pchg, CHGCTRL2, val);
 		}
 	}
 }
@@ -439,15 +439,29 @@ static int lp8727_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 
 	mutex_init(&pchg->xfer_lock);
 
-	lp8727_init_device(pchg);
-	lp8727_intr_config(pchg);
+	ret = lp8727_init_device(pchg);
+	if (ret) {
+		dev_err(pchg->dev, "i2c communication err: %d", ret);
+		goto error;
+	}
+
+	ret = lp8727_intr_config(pchg);
+	if (ret) {
+		dev_err(pchg->dev, "irq handler err: %d", ret);
+		goto error;
+	}
 
 	ret = lp8727_register_psy(pchg);
-	if (ret)
-		dev_err(pchg->dev,
-			"can not register power supplies. err=%d", ret);
+	if (ret) {
+		dev_err(pchg->dev, "power supplies register err: %d", ret);
+		goto error;
+	}
 
 	return 0;
+
+error:
+	kfree(pchg);
+	return ret;
 }
 
 static int __devexit lp8727_remove(struct i2c_client *cl)
@@ -466,6 +480,7 @@ static const struct i2c_device_id lp8727_ids[] = {
 	{"lp8727", 0},
 	{ }
 };
+MODULE_DEVICE_TABLE(i2c, lp8727_ids);
 
 static struct i2c_driver lp8727_driver = {
 	.driver = {
@@ -475,21 +490,9 @@ static struct i2c_driver lp8727_driver = {
 	.remove = __devexit_p(lp8727_remove),
 	.id_table = lp8727_ids,
 };
+module_i2c_driver(lp8727_driver);
 
-static int __init lp8727_init(void)
-{
-	return i2c_add_driver(&lp8727_driver);
-}
-
-static void __exit lp8727_exit(void)
-{
-	i2c_del_driver(&lp8727_driver);
-}
-
-module_init(lp8727_init);
-module_exit(lp8727_exit);
-
-MODULE_DESCRIPTION("National Semiconductor LP8727 charger driver");
-MODULE_AUTHOR
-    ("Woogyom Kim <milo.kim@ti.com>, Daniel Jeong <daniel.jeong@ti.com>");
+MODULE_DESCRIPTION("TI/National Semiconductor LP8727 charger driver");
+MODULE_AUTHOR("Woogyom Kim <milo.kim@ti.com>, "
+	      "Daniel Jeong <daniel.jeong@ti.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c
index 2f2f9a6f54fa..c284143cfcd7 100644
--- a/drivers/power/max17040_battery.c
+++ b/drivers/power/max17040_battery.c
@@ -290,18 +290,7 @@ static struct i2c_driver max17040_i2c_driver = {
 	.resume		= max17040_resume,
 	.id_table	= max17040_id,
 };
-
-static int __init max17040_init(void)
-{
-	return i2c_add_driver(&max17040_i2c_driver);
-}
-module_init(max17040_init);
-
-static void __exit max17040_exit(void)
-{
-	i2c_del_driver(&max17040_i2c_driver);
-}
-module_exit(max17040_exit);
+module_i2c_driver(max17040_i2c_driver);
 
 MODULE_AUTHOR("Minkyu Kang <mk7.kang@samsung.com>");
 MODULE_DESCRIPTION("MAX17040 Fuel Gauge");
diff --git a/drivers/power/max17042_battery.c b/drivers/power/max17042_battery.c
index 86acee2f9889..04620c2cb388 100644
--- a/drivers/power/max17042_battery.c
+++ b/drivers/power/max17042_battery.c
@@ -26,14 +26,47 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
 #include <linux/mod_devicetable.h>
 #include <linux/power_supply.h>
 #include <linux/power/max17042_battery.h>
+#include <linux/of.h>
+
+/* Status register bits */
+#define STATUS_POR_BIT         (1 << 1)
+#define STATUS_BST_BIT         (1 << 3)
+#define STATUS_VMN_BIT         (1 << 8)
+#define STATUS_TMN_BIT         (1 << 9)
+#define STATUS_SMN_BIT         (1 << 10)
+#define STATUS_BI_BIT          (1 << 11)
+#define STATUS_VMX_BIT         (1 << 12)
+#define STATUS_TMX_BIT         (1 << 13)
+#define STATUS_SMX_BIT         (1 << 14)
+#define STATUS_BR_BIT          (1 << 15)
+
+/* Interrupt mask bits */
+#define CONFIG_ALRT_BIT_ENBL	(1 << 2)
+#define STATUS_INTR_SOCMIN_BIT	(1 << 10)
+#define STATUS_INTR_SOCMAX_BIT	(1 << 14)
+
+#define VFSOC0_LOCK		0x0000
+#define VFSOC0_UNLOCK		0x0080
+#define MODEL_UNLOCK1	0X0059
+#define MODEL_UNLOCK2	0X00C4
+#define MODEL_LOCK1		0X0000
+#define MODEL_LOCK2		0X0000
+
+#define dQ_ACC_DIV	0x4
+#define dP_ACC_100	0x1900
+#define dP_ACC_200	0x3200
 
 struct max17042_chip {
 	struct i2c_client *client;
 	struct power_supply battery;
 	struct max17042_platform_data *pdata;
+	struct work_struct work;
+	int    init_complete;
 };
 
 static int max17042_write_reg(struct i2c_client *client, u8 reg, u16 value)
@@ -87,6 +120,9 @@ static int max17042_get_property(struct power_supply *psy,
 				struct max17042_chip, battery);
 	int ret;
 
+	if (!chip->init_complete)
+		return -EAGAIN;
+
 	switch (psp) {
 	case POWER_SUPPLY_PROP_PRESENT:
 		ret = max17042_read_reg(chip->client, MAX17042_STATUS);
@@ -136,21 +172,18 @@ static int max17042_get_property(struct power_supply *psy,
 		val->intval = ret * 625 / 8;
 		break;
 	case POWER_SUPPLY_PROP_CAPACITY:
-		ret = max17042_read_reg(chip->client, MAX17042_SOC);
+		ret = max17042_read_reg(chip->client, MAX17042_RepSOC);
 		if (ret < 0)
 			return ret;
 
 		val->intval = ret >> 8;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_FULL:
-		ret = max17042_read_reg(chip->client, MAX17042_RepSOC);
+		ret = max17042_read_reg(chip->client, MAX17042_FullCAP);
 		if (ret < 0)
 			return ret;
 
-		if ((ret >> 8) >= MAX17042_BATTERY_FULL)
-			val->intval = 1;
-		else if (ret >= 0)
-			val->intval = 0;
+		val->intval = ret * 1000 / 2;
 		break;
 	case POWER_SUPPLY_PROP_TEMP:
 		ret = max17042_read_reg(chip->client, MAX17042_TEMP);
@@ -210,22 +243,419 @@ static int max17042_get_property(struct power_supply *psy,
 	return 0;
 }
 
+static int max17042_write_verify_reg(struct i2c_client *client,
+				u8 reg, u16 value)
+{
+	int retries = 8;
+	int ret;
+	u16 read_value;
+
+	do {
+		ret = i2c_smbus_write_word_data(client, reg, value);
+		read_value =  max17042_read_reg(client, reg);
+		if (read_value != value) {
+			ret = -EIO;
+			retries--;
+		}
+	} while (retries && read_value != value);
+
+	if (ret < 0)
+		dev_err(&client->dev, "%s: err %d\n", __func__, ret);
+
+	return ret;
+}
+
+static inline void max17042_override_por(
+	struct i2c_client *client, u8 reg, u16 value)
+{
+	if (value)
+		max17042_write_reg(client, reg, value);
+}
+
+static inline void max10742_unlock_model(struct max17042_chip *chip)
+{
+	struct i2c_client *client = chip->client;
+	max17042_write_reg(client, MAX17042_MLOCKReg1, MODEL_UNLOCK1);
+	max17042_write_reg(client, MAX17042_MLOCKReg2, MODEL_UNLOCK2);
+}
+
+static inline void max10742_lock_model(struct max17042_chip *chip)
+{
+	struct i2c_client *client = chip->client;
+	max17042_write_reg(client, MAX17042_MLOCKReg1, MODEL_LOCK1);
+	max17042_write_reg(client, MAX17042_MLOCKReg2, MODEL_LOCK2);
+}
+
+static inline void max17042_write_model_data(struct max17042_chip *chip,
+					u8 addr, int size)
+{
+	struct i2c_client *client = chip->client;
+	int i;
+	for (i = 0; i < size; i++)
+		max17042_write_reg(client, addr + i,
+				chip->pdata->config_data->cell_char_tbl[i]);
+}
+
+static inline void max17042_read_model_data(struct max17042_chip *chip,
+					u8 addr, u16 *data, int size)
+{
+	struct i2c_client *client = chip->client;
+	int i;
+
+	for (i = 0; i < size; i++)
+		data[i] = max17042_read_reg(client, addr + i);
+}
+
+static inline int max17042_model_data_compare(struct max17042_chip *chip,
+					u16 *data1, u16 *data2, int size)
+{
+	int i;
+
+	if (memcmp(data1, data2, size)) {
+		dev_err(&chip->client->dev, "%s compare failed\n", __func__);
+		for (i = 0; i < size; i++)
+			dev_info(&chip->client->dev, "0x%x, 0x%x",
+				data1[i], data2[i]);
+		dev_info(&chip->client->dev, "\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int max17042_init_model(struct max17042_chip *chip)
+{
+	int ret;
+	int table_size =
+		sizeof(chip->pdata->config_data->cell_char_tbl)/sizeof(u16);
+	u16 *temp_data;
+
+	temp_data = kzalloc(table_size, GFP_KERNEL);
+	if (!temp_data)
+		return -ENOMEM;
+
+	max10742_unlock_model(chip);
+	max17042_write_model_data(chip, MAX17042_MODELChrTbl,
+				table_size);
+	max17042_read_model_data(chip, MAX17042_MODELChrTbl, temp_data,
+				table_size);
+
+	ret = max17042_model_data_compare(
+		chip,
+		chip->pdata->config_data->cell_char_tbl,
+		temp_data,
+		table_size);
+
+	max10742_lock_model(chip);
+	kfree(temp_data);
+
+	return ret;
+}
+
+static int max17042_verify_model_lock(struct max17042_chip *chip)
+{
+	int i;
+	int table_size =
+		sizeof(chip->pdata->config_data->cell_char_tbl);
+	u16 *temp_data;
+	int ret = 0;
+
+	temp_data = kzalloc(table_size, GFP_KERNEL);
+	if (!temp_data)
+		return -ENOMEM;
+
+	max17042_read_model_data(chip, MAX17042_MODELChrTbl, temp_data,
+				table_size);
+	for (i = 0; i < table_size; i++)
+		if (temp_data[i])
+			ret = -EINVAL;
+
+	kfree(temp_data);
+	return ret;
+}
+
+static void max17042_write_config_regs(struct max17042_chip *chip)
+{
+	struct max17042_config_data *config = chip->pdata->config_data;
+
+	max17042_write_reg(chip->client, MAX17042_CONFIG, config->config);
+	max17042_write_reg(chip->client, MAX17042_LearnCFG, config->learn_cfg);
+	max17042_write_reg(chip->client, MAX17042_FilterCFG,
+			config->filter_cfg);
+	max17042_write_reg(chip->client, MAX17042_RelaxCFG, config->relax_cfg);
+}
+
+static void  max17042_write_custom_regs(struct max17042_chip *chip)
+{
+	struct max17042_config_data *config = chip->pdata->config_data;
+
+	max17042_write_verify_reg(chip->client, MAX17042_RCOMP0,
+				config->rcomp0);
+	max17042_write_verify_reg(chip->client, MAX17042_TempCo,
+				config->tcompc0);
+	max17042_write_reg(chip->client, MAX17042_EmptyTempCo,
+			config->empty_tempco);
+	max17042_write_verify_reg(chip->client, MAX17042_K_empty0,
+				config->kempty0);
+	max17042_write_verify_reg(chip->client, MAX17042_ICHGTerm,
+				config->ichgt_term);
+}
+
+static void max17042_update_capacity_regs(struct max17042_chip *chip)
+{
+	struct max17042_config_data *config = chip->pdata->config_data;
+
+	max17042_write_verify_reg(chip->client, MAX17042_FullCAP,
+				config->fullcap);
+	max17042_write_reg(chip->client, MAX17042_DesignCap,
+			config->design_cap);
+	max17042_write_verify_reg(chip->client, MAX17042_FullCAPNom,
+				config->fullcapnom);
+}
+
+static void max17042_reset_vfsoc0_reg(struct max17042_chip *chip)
+{
+	u16 vfSoc;
+
+	vfSoc = max17042_read_reg(chip->client, MAX17042_VFSOC);
+	max17042_write_reg(chip->client, MAX17042_VFSOC0Enable, VFSOC0_UNLOCK);
+	max17042_write_verify_reg(chip->client, MAX17042_VFSOC0, vfSoc);
+	max17042_write_reg(chip->client, MAX17042_VFSOC0Enable, VFSOC0_LOCK);
+}
+
+static void max17042_load_new_capacity_params(struct max17042_chip *chip)
+{
+	u16 full_cap0, rep_cap, dq_acc, vfSoc;
+	u32 rem_cap;
+
+	struct max17042_config_data *config = chip->pdata->config_data;
+
+	full_cap0 = max17042_read_reg(chip->client, MAX17042_FullCAP0);
+	vfSoc = max17042_read_reg(chip->client, MAX17042_VFSOC);
+
+	/* fg_vfSoc needs to shifted by 8 bits to get the
+	 * perc in 1% accuracy, to get the right rem_cap multiply
+	 * full_cap0, fg_vfSoc and devide by 100
+	 */
+	rem_cap = ((vfSoc >> 8) * full_cap0) / 100;
+	max17042_write_verify_reg(chip->client, MAX17042_RemCap, (u16)rem_cap);
+
+	rep_cap = (u16)rem_cap;
+	max17042_write_verify_reg(chip->client, MAX17042_RepCap, rep_cap);
+
+	/* Write dQ_acc to 200% of Capacity and dP_acc to 200% */
+	dq_acc = config->fullcap / dQ_ACC_DIV;
+	max17042_write_verify_reg(chip->client, MAX17042_dQacc, dq_acc);
+	max17042_write_verify_reg(chip->client, MAX17042_dPacc, dP_ACC_200);
+
+	max17042_write_verify_reg(chip->client, MAX17042_FullCAP,
+			config->fullcap);
+	max17042_write_reg(chip->client, MAX17042_DesignCap,
+			config->design_cap);
+	max17042_write_verify_reg(chip->client, MAX17042_FullCAPNom,
+			config->fullcapnom);
+}
+
+/*
+ * Block write all the override values coming from platform data.
+ * This function MUST be called before the POR initialization proceedure
+ * specified by maxim.
+ */
+static inline void max17042_override_por_values(struct max17042_chip *chip)
+{
+	struct i2c_client *client = chip->client;
+	struct max17042_config_data *config = chip->pdata->config_data;
+
+	max17042_override_por(client, MAX17042_TGAIN, config->tgain);
+	max17042_override_por(client, MAx17042_TOFF, config->toff);
+	max17042_override_por(client, MAX17042_CGAIN, config->cgain);
+	max17042_override_por(client, MAX17042_COFF, config->coff);
+
+	max17042_override_por(client, MAX17042_VALRT_Th, config->valrt_thresh);
+	max17042_override_por(client, MAX17042_TALRT_Th, config->talrt_thresh);
+	max17042_override_por(client, MAX17042_SALRT_Th,
+			config->soc_alrt_thresh);
+	max17042_override_por(client, MAX17042_CONFIG, config->config);
+	max17042_override_por(client, MAX17042_SHDNTIMER, config->shdntimer);
+
+	max17042_override_por(client, MAX17042_DesignCap, config->design_cap);
+	max17042_override_por(client, MAX17042_ICHGTerm, config->ichgt_term);
+
+	max17042_override_por(client, MAX17042_AtRate, config->at_rate);
+	max17042_override_por(client, MAX17042_LearnCFG, config->learn_cfg);
+	max17042_override_por(client, MAX17042_FilterCFG, config->filter_cfg);
+	max17042_override_por(client, MAX17042_RelaxCFG, config->relax_cfg);
+	max17042_override_por(client, MAX17042_MiscCFG, config->misc_cfg);
+	max17042_override_por(client, MAX17042_MaskSOC, config->masksoc);
+
+	max17042_override_por(client, MAX17042_FullCAP, config->fullcap);
+	max17042_override_por(client, MAX17042_FullCAPNom, config->fullcapnom);
+	max17042_override_por(client, MAX17042_SOC_empty, config->socempty);
+	max17042_override_por(client, MAX17042_LAvg_empty, config->lavg_empty);
+	max17042_override_por(client, MAX17042_dQacc, config->dqacc);
+	max17042_override_por(client, MAX17042_dPacc, config->dpacc);
+
+	max17042_override_por(client, MAX17042_V_empty, config->vempty);
+	max17042_override_por(client, MAX17042_TempNom, config->temp_nom);
+	max17042_override_por(client, MAX17042_TempLim, config->temp_lim);
+	max17042_override_por(client, MAX17042_FCTC, config->fctc);
+	max17042_override_por(client, MAX17042_RCOMP0, config->rcomp0);
+	max17042_override_por(client, MAX17042_TempCo, config->tcompc0);
+	max17042_override_por(client, MAX17042_EmptyTempCo,
+			config->empty_tempco);
+	max17042_override_por(client, MAX17042_K_empty0, config->kempty0);
+}
+
+static int max17042_init_chip(struct max17042_chip *chip)
+{
+	int ret;
+	int val;
+
+	max17042_override_por_values(chip);
+	/* After Power up, the MAX17042 requires 500mS in order
+	 * to perform signal debouncing and initial SOC reporting
+	 */
+	msleep(500);
+
+	/* Initialize configaration */
+	max17042_write_config_regs(chip);
+
+	/* write cell characterization data */
+	ret = max17042_init_model(chip);
+	if (ret) {
+		dev_err(&chip->client->dev, "%s init failed\n",
+			__func__);
+		return -EIO;
+	}
+	max17042_verify_model_lock(chip);
+	if (ret) {
+		dev_err(&chip->client->dev, "%s lock verify failed\n",
+			__func__);
+		return -EIO;
+	}
+	/* write custom parameters */
+	max17042_write_custom_regs(chip);
+
+	/* update capacity params */
+	max17042_update_capacity_regs(chip);
+
+	/* delay must be atleast 350mS to allow VFSOC
+	 * to be calculated from the new configuration
+	 */
+	msleep(350);
+
+	/* reset vfsoc0 reg */
+	max17042_reset_vfsoc0_reg(chip);
+
+	/* load new capacity params */
+	max17042_load_new_capacity_params(chip);
+
+	/* Init complete, Clear the POR bit */
+	val = max17042_read_reg(chip->client, MAX17042_STATUS);
+	max17042_write_reg(chip->client, MAX17042_STATUS,
+			val & (~STATUS_POR_BIT));
+	return 0;
+}
+
+static void max17042_set_soc_threshold(struct max17042_chip *chip, u16 off)
+{
+	u16 soc, soc_tr;
+
+	/* program interrupt thesholds such that we should
+	 * get interrupt for every 'off' perc change in the soc
+	 */
+	soc = max17042_read_reg(chip->client, MAX17042_RepSOC) >> 8;
+	soc_tr = (soc + off) << 8;
+	soc_tr |= (soc - off);
+	max17042_write_reg(chip->client, MAX17042_SALRT_Th, soc_tr);
+}
+
+static irqreturn_t max17042_thread_handler(int id, void *dev)
+{
+	struct max17042_chip *chip = dev;
+	u16 val;
+
+	val = max17042_read_reg(chip->client, MAX17042_STATUS);
+	if ((val & STATUS_INTR_SOCMIN_BIT) ||
+		(val & STATUS_INTR_SOCMAX_BIT)) {
+		dev_info(&chip->client->dev, "SOC threshold INTR\n");
+		max17042_set_soc_threshold(chip, 1);
+	}
+
+	power_supply_changed(&chip->battery);
+	return IRQ_HANDLED;
+}
+
+static void max17042_init_worker(struct work_struct *work)
+{
+	struct max17042_chip *chip = container_of(work,
+				struct max17042_chip, work);
+	int ret;
+
+	/* Initialize registers according to values from the platform data */
+	if (chip->pdata->enable_por_init && chip->pdata->config_data) {
+		ret = max17042_init_chip(chip);
+		if (ret)
+			return;
+	}
+
+	chip->init_complete = 1;
+}
+
+#ifdef CONFIG_OF
+static struct max17042_platform_data *
+max17042_get_pdata(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	u32 prop;
+	struct max17042_platform_data *pdata;
+
+	if (!np)
+		return dev->platform_data;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL;
+
+	/*
+	 * Require current sense resistor value to be specified for
+	 * current-sense functionality to be enabled at all.
+	 */
+	if (of_property_read_u32(np, "maxim,rsns-microohm", &prop) == 0) {
+		pdata->r_sns = prop;
+		pdata->enable_current_sense = true;
+	}
+
+	return pdata;
+}
+#else
+static struct max17042_platform_data *
+max17042_get_pdata(struct device *dev)
+{
+	return dev->platform_data;
+}
+#endif
+
 static int __devinit max17042_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
 	struct max17042_chip *chip;
 	int ret;
+	int reg;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA))
 		return -EIO;
 
-	chip = kzalloc(sizeof(*chip), GFP_KERNEL);
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
 
 	chip->client = client;
-	chip->pdata = client->dev.platform_data;
+	chip->pdata = max17042_get_pdata(&client->dev);
+	if (!chip->pdata) {
+		dev_err(&client->dev, "no platform data provided\n");
+		return -EINVAL;
+	}
 
 	i2c_set_clientdata(client, chip);
 
@@ -243,17 +673,9 @@ static int __devinit max17042_probe(struct i2c_client *client,
 	if (chip->pdata->r_sns == 0)
 		chip->pdata->r_sns = MAX17042_DEFAULT_SNS_RESISTOR;
 
-	ret = power_supply_register(&client->dev, &chip->battery);
-	if (ret) {
-		dev_err(&client->dev, "failed: power supply register\n");
-		kfree(chip);
-		return ret;
-	}
-
-	/* Initialize registers according to values from the platform data */
 	if (chip->pdata->init_data)
 		max17042_set_reg(client, chip->pdata->init_data,
-				 chip->pdata->num_init_data);
+				chip->pdata->num_init_data);
 
 	if (!chip->pdata->enable_current_sense) {
 		max17042_write_reg(client, MAX17042_CGAIN, 0x0000);
@@ -261,7 +683,34 @@ static int __devinit max17042_probe(struct i2c_client *client,
 		max17042_write_reg(client, MAX17042_LearnCFG, 0x0007);
 	}
 
-	return 0;
+	if (client->irq) {
+		ret = request_threaded_irq(client->irq, NULL,
+						max17042_thread_handler,
+						IRQF_TRIGGER_FALLING,
+						chip->battery.name, chip);
+		if (!ret) {
+			reg =  max17042_read_reg(client, MAX17042_CONFIG);
+			reg |= CONFIG_ALRT_BIT_ENBL;
+			max17042_write_reg(client, MAX17042_CONFIG, reg);
+			max17042_set_soc_threshold(chip, 1);
+		} else
+			dev_err(&client->dev, "%s(): cannot get IRQ\n",
+				__func__);
+	}
+
+	reg = max17042_read_reg(chip->client, MAX17042_STATUS);
+
+	if (reg & STATUS_POR_BIT) {
+		INIT_WORK(&chip->work, max17042_init_worker);
+		schedule_work(&chip->work);
+	} else {
+		chip->init_complete = 1;
+	}
+
+	ret = power_supply_register(&client->dev, &chip->battery);
+	if (ret)
+		dev_err(&client->dev, "failed: power supply register\n");
+	return ret;
 }
 
 static int __devexit max17042_remove(struct i2c_client *client)
@@ -269,10 +718,17 @@ static int __devexit max17042_remove(struct i2c_client *client)
 	struct max17042_chip *chip = i2c_get_clientdata(client);
 
 	power_supply_unregister(&chip->battery);
-	kfree(chip);
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id max17042_dt_match[] = {
+	{ .compatible = "maxim,max17042" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, max17042_dt_match);
+#endif
+
 static const struct i2c_device_id max17042_id[] = {
 	{ "max17042", 0 },
 	{ }
@@ -282,23 +738,13 @@ MODULE_DEVICE_TABLE(i2c, max17042_id);
 static struct i2c_driver max17042_i2c_driver = {
 	.driver	= {
 		.name	= "max17042",
+		.of_match_table = of_match_ptr(max17042_dt_match),
 	},
 	.probe		= max17042_probe,
 	.remove		= __devexit_p(max17042_remove),
 	.id_table	= max17042_id,
 };
-
-static int __init max17042_init(void)
-{
-	return i2c_add_driver(&max17042_i2c_driver);
-}
-module_init(max17042_init);
-
-static void __exit max17042_exit(void)
-{
-	i2c_del_driver(&max17042_i2c_driver);
-}
-module_exit(max17042_exit);
+module_i2c_driver(max17042_i2c_driver);
 
 MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
 MODULE_DESCRIPTION("MAX17042 Fuel Gauge");
diff --git a/drivers/power/sbs-battery.c b/drivers/power/sbs-battery.c
index 9ff8af069da6..06b659d91790 100644
--- a/drivers/power/sbs-battery.c
+++ b/drivers/power/sbs-battery.c
@@ -852,18 +852,7 @@ static struct i2c_driver sbs_battery_driver = {
 		.of_match_table = sbs_dt_ids,
 	},
 };
-
-static int __init sbs_battery_init(void)
-{
-	return i2c_add_driver(&sbs_battery_driver);
-}
-module_init(sbs_battery_init);
-
-static void __exit sbs_battery_exit(void)
-{
-	i2c_del_driver(&sbs_battery_driver);
-}
-module_exit(sbs_battery_exit);
+module_i2c_driver(sbs_battery_driver);
 
 MODULE_DESCRIPTION("SBS battery monitor driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/power/smb347-charger.c b/drivers/power/smb347-charger.c
new file mode 100644
index 000000000000..ce1694d1a365
--- /dev/null
+++ b/drivers/power/smb347-charger.c
@@ -0,0 +1,1294 @@
+/*
+ * Summit Microelectronics SMB347 Battery Charger Driver
+ *
+ * Copyright (C) 2011, Intel Corporation
+ *
+ * Authors: Bruce E. Robertson <bruce.e.robertson@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/gpio.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/i2c.h>
+#include <linux/mutex.h>
+#include <linux/power_supply.h>
+#include <linux/power/smb347-charger.h>
+#include <linux/seq_file.h>
+
+/*
+ * Configuration registers. These are mirrored to volatile RAM and can be
+ * written once %CMD_A_ALLOW_WRITE is set in %CMD_A register. They will be
+ * reloaded from non-volatile registers after POR.
+ */
+#define CFG_CHARGE_CURRENT			0x00
+#define CFG_CHARGE_CURRENT_FCC_MASK		0xe0
+#define CFG_CHARGE_CURRENT_FCC_SHIFT		5
+#define CFG_CHARGE_CURRENT_PCC_MASK		0x18
+#define CFG_CHARGE_CURRENT_PCC_SHIFT		3
+#define CFG_CHARGE_CURRENT_TC_MASK		0x07
+#define CFG_CURRENT_LIMIT			0x01
+#define CFG_CURRENT_LIMIT_DC_MASK		0xf0
+#define CFG_CURRENT_LIMIT_DC_SHIFT		4
+#define CFG_CURRENT_LIMIT_USB_MASK		0x0f
+#define CFG_FLOAT_VOLTAGE			0x03
+#define CFG_FLOAT_VOLTAGE_THRESHOLD_MASK	0xc0
+#define CFG_FLOAT_VOLTAGE_THRESHOLD_SHIFT	6
+#define CFG_STAT				0x05
+#define CFG_STAT_DISABLED			BIT(5)
+#define CFG_STAT_ACTIVE_HIGH			BIT(7)
+#define CFG_PIN					0x06
+#define CFG_PIN_EN_CTRL_MASK			0x60
+#define CFG_PIN_EN_CTRL_ACTIVE_HIGH		0x40
+#define CFG_PIN_EN_CTRL_ACTIVE_LOW		0x60
+#define CFG_PIN_EN_APSD_IRQ			BIT(1)
+#define CFG_PIN_EN_CHARGER_ERROR		BIT(2)
+#define CFG_THERM				0x07
+#define CFG_THERM_SOFT_HOT_COMPENSATION_MASK	0x03
+#define CFG_THERM_SOFT_HOT_COMPENSATION_SHIFT	0
+#define CFG_THERM_SOFT_COLD_COMPENSATION_MASK	0x0c
+#define CFG_THERM_SOFT_COLD_COMPENSATION_SHIFT	2
+#define CFG_THERM_MONITOR_DISABLED		BIT(4)
+#define CFG_SYSOK				0x08
+#define CFG_SYSOK_SUSPEND_HARD_LIMIT_DISABLED	BIT(2)
+#define CFG_OTHER				0x09
+#define CFG_OTHER_RID_MASK			0xc0
+#define CFG_OTHER_RID_ENABLED_AUTO_OTG		0xc0
+#define CFG_OTG					0x0a
+#define CFG_OTG_TEMP_THRESHOLD_MASK		0x30
+#define CFG_OTG_TEMP_THRESHOLD_SHIFT		4
+#define CFG_OTG_CC_COMPENSATION_MASK		0xc0
+#define CFG_OTG_CC_COMPENSATION_SHIFT		6
+#define CFG_TEMP_LIMIT				0x0b
+#define CFG_TEMP_LIMIT_SOFT_HOT_MASK		0x03
+#define CFG_TEMP_LIMIT_SOFT_HOT_SHIFT		0
+#define CFG_TEMP_LIMIT_SOFT_COLD_MASK		0x0c
+#define CFG_TEMP_LIMIT_SOFT_COLD_SHIFT		2
+#define CFG_TEMP_LIMIT_HARD_HOT_MASK		0x30
+#define CFG_TEMP_LIMIT_HARD_HOT_SHIFT		4
+#define CFG_TEMP_LIMIT_HARD_COLD_MASK		0xc0
+#define CFG_TEMP_LIMIT_HARD_COLD_SHIFT		6
+#define CFG_FAULT_IRQ				0x0c
+#define CFG_FAULT_IRQ_DCIN_UV			BIT(2)
+#define CFG_STATUS_IRQ				0x0d
+#define CFG_STATUS_IRQ_TERMINATION_OR_TAPER	BIT(4)
+#define CFG_ADDRESS				0x0e
+
+/* Command registers */
+#define CMD_A					0x30
+#define CMD_A_CHG_ENABLED			BIT(1)
+#define CMD_A_SUSPEND_ENABLED			BIT(2)
+#define CMD_A_ALLOW_WRITE			BIT(7)
+#define CMD_B					0x31
+#define CMD_C					0x33
+
+/* Interrupt Status registers */
+#define IRQSTAT_A				0x35
+#define IRQSTAT_C				0x37
+#define IRQSTAT_C_TERMINATION_STAT		BIT(0)
+#define IRQSTAT_C_TERMINATION_IRQ		BIT(1)
+#define IRQSTAT_C_TAPER_IRQ			BIT(3)
+#define IRQSTAT_E				0x39
+#define IRQSTAT_E_USBIN_UV_STAT			BIT(0)
+#define IRQSTAT_E_USBIN_UV_IRQ			BIT(1)
+#define IRQSTAT_E_DCIN_UV_STAT			BIT(4)
+#define IRQSTAT_E_DCIN_UV_IRQ			BIT(5)
+#define IRQSTAT_F				0x3a
+
+/* Status registers */
+#define STAT_A					0x3b
+#define STAT_A_FLOAT_VOLTAGE_MASK		0x3f
+#define STAT_B					0x3c
+#define STAT_C					0x3d
+#define STAT_C_CHG_ENABLED			BIT(0)
+#define STAT_C_CHG_MASK				0x06
+#define STAT_C_CHG_SHIFT			1
+#define STAT_C_CHARGER_ERROR			BIT(6)
+#define STAT_E					0x3f
+
+/**
+ * struct smb347_charger - smb347 charger instance
+ * @lock: protects concurrent access to online variables
+ * @client: pointer to i2c client
+ * @mains: power_supply instance for AC/DC power
+ * @usb: power_supply instance for USB power
+ * @battery: power_supply instance for battery
+ * @mains_online: is AC/DC input connected
+ * @usb_online: is USB input connected
+ * @charging_enabled: is charging enabled
+ * @dentry: for debugfs
+ * @pdata: pointer to platform data
+ */
+struct smb347_charger {
+	struct mutex		lock;
+	struct i2c_client	*client;
+	struct power_supply	mains;
+	struct power_supply	usb;
+	struct power_supply	battery;
+	bool			mains_online;
+	bool			usb_online;
+	bool			charging_enabled;
+	struct dentry		*dentry;
+	const struct smb347_charger_platform_data *pdata;
+};
+
+/* Fast charge current in uA */
+static const unsigned int fcc_tbl[] = {
+	700000,
+	900000,
+	1200000,
+	1500000,
+	1800000,
+	2000000,
+	2200000,
+	2500000,
+};
+
+/* Pre-charge current in uA */
+static const unsigned int pcc_tbl[] = {
+	100000,
+	150000,
+	200000,
+	250000,
+};
+
+/* Termination current in uA */
+static const unsigned int tc_tbl[] = {
+	37500,
+	50000,
+	100000,
+	150000,
+	200000,
+	250000,
+	500000,
+	600000,
+};
+
+/* Input current limit in uA */
+static const unsigned int icl_tbl[] = {
+	300000,
+	500000,
+	700000,
+	900000,
+	1200000,
+	1500000,
+	1800000,
+	2000000,
+	2200000,
+	2500000,
+};
+
+/* Charge current compensation in uA */
+static const unsigned int ccc_tbl[] = {
+	250000,
+	700000,
+	900000,
+	1200000,
+};
+
+/* Convert register value to current using lookup table */
+static int hw_to_current(const unsigned int *tbl, size_t size, unsigned int val)
+{
+	if (val >= size)
+		return -EINVAL;
+	return tbl[val];
+}
+
+/* Convert current to register value using lookup table */
+static int current_to_hw(const unsigned int *tbl, size_t size, unsigned int val)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		if (val < tbl[i])
+			break;
+	return i > 0 ? i - 1 : -EINVAL;
+}
+
+static int smb347_read(struct smb347_charger *smb, u8 reg)
+{
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(smb->client, reg);
+	if (ret < 0)
+		dev_warn(&smb->client->dev, "failed to read reg 0x%x: %d\n",
+			 reg, ret);
+	return ret;
+}
+
+static int smb347_write(struct smb347_charger *smb, u8 reg, u8 val)
+{
+	int ret;
+
+	ret = i2c_smbus_write_byte_data(smb->client, reg, val);
+	if (ret < 0)
+		dev_warn(&smb->client->dev, "failed to write reg 0x%x: %d\n",
+			 reg, ret);
+	return ret;
+}
+
+/**
+ * smb347_update_status - updates the charging status
+ * @smb: pointer to smb347 charger instance
+ *
+ * Function checks status of the charging and updates internal state
+ * accordingly. Returns %0 if there is no change in status, %1 if the
+ * status has changed and negative errno in case of failure.
+ */
+static int smb347_update_status(struct smb347_charger *smb)
+{
+	bool usb = false;
+	bool dc = false;
+	int ret;
+
+	ret = smb347_read(smb, IRQSTAT_E);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Dc and usb are set depending on whether they are enabled in
+	 * platform data _and_ whether corresponding undervoltage is set.
+	 */
+	if (smb->pdata->use_mains)
+		dc = !(ret & IRQSTAT_E_DCIN_UV_STAT);
+	if (smb->pdata->use_usb)
+		usb = !(ret & IRQSTAT_E_USBIN_UV_STAT);
+
+	mutex_lock(&smb->lock);
+	ret = smb->mains_online != dc || smb->usb_online != usb;
+	smb->mains_online = dc;
+	smb->usb_online = usb;
+	mutex_unlock(&smb->lock);
+
+	return ret;
+}
+
+/*
+ * smb347_is_online - returns whether input power source is connected
+ * @smb: pointer to smb347 charger instance
+ *
+ * Returns %true if input power source is connected. Note that this is
+ * dependent on what platform has configured for usable power sources. For
+ * example if USB is disabled, this will return %false even if the USB
+ * cable is connected.
+ */
+static bool smb347_is_online(struct smb347_charger *smb)
+{
+	bool ret;
+
+	mutex_lock(&smb->lock);
+	ret = smb->usb_online || smb->mains_online;
+	mutex_unlock(&smb->lock);
+
+	return ret;
+}
+
+/**
+ * smb347_charging_status - returns status of charging
+ * @smb: pointer to smb347 charger instance
+ *
+ * Function returns charging status. %0 means no charging is in progress,
+ * %1 means pre-charging, %2 fast-charging and %3 taper-charging.
+ */
+static int smb347_charging_status(struct smb347_charger *smb)
+{
+	int ret;
+
+	if (!smb347_is_online(smb))
+		return 0;
+
+	ret = smb347_read(smb, STAT_C);
+	if (ret < 0)
+		return 0;
+
+	return (ret & STAT_C_CHG_MASK) >> STAT_C_CHG_SHIFT;
+}
+
+static int smb347_charging_set(struct smb347_charger *smb, bool enable)
+{
+	int ret = 0;
+
+	if (smb->pdata->enable_control != SMB347_CHG_ENABLE_SW) {
+		dev_dbg(&smb->client->dev,
+			"charging enable/disable in SW disabled\n");
+		return 0;
+	}
+
+	mutex_lock(&smb->lock);
+	if (smb->charging_enabled != enable) {
+		ret = smb347_read(smb, CMD_A);
+		if (ret < 0)
+			goto out;
+
+		smb->charging_enabled = enable;
+
+		if (enable)
+			ret |= CMD_A_CHG_ENABLED;
+		else
+			ret &= ~CMD_A_CHG_ENABLED;
+
+		ret = smb347_write(smb, CMD_A, ret);
+	}
+out:
+	mutex_unlock(&smb->lock);
+	return ret;
+}
+
+static inline int smb347_charging_enable(struct smb347_charger *smb)
+{
+	return smb347_charging_set(smb, true);
+}
+
+static inline int smb347_charging_disable(struct smb347_charger *smb)
+{
+	return smb347_charging_set(smb, false);
+}
+
+static int smb347_update_online(struct smb347_charger *smb)
+{
+	int ret;
+
+	/*
+	 * Depending on whether valid power source is connected or not, we
+	 * disable or enable the charging. We do it manually because it
+	 * depends on how the platform has configured the valid inputs.
+	 */
+	if (smb347_is_online(smb)) {
+		ret = smb347_charging_enable(smb);
+		if (ret < 0)
+			dev_err(&smb->client->dev,
+				"failed to enable charging\n");
+	} else {
+		ret = smb347_charging_disable(smb);
+		if (ret < 0)
+			dev_err(&smb->client->dev,
+				"failed to disable charging\n");
+	}
+
+	return ret;
+}
+
+static int smb347_set_charge_current(struct smb347_charger *smb)
+{
+	int ret, val;
+
+	ret = smb347_read(smb, CFG_CHARGE_CURRENT);
+	if (ret < 0)
+		return ret;
+
+	if (smb->pdata->max_charge_current) {
+		val = current_to_hw(fcc_tbl, ARRAY_SIZE(fcc_tbl),
+				    smb->pdata->max_charge_current);
+		if (val < 0)
+			return val;
+
+		ret &= ~CFG_CHARGE_CURRENT_FCC_MASK;
+		ret |= val << CFG_CHARGE_CURRENT_FCC_SHIFT;
+	}
+
+	if (smb->pdata->pre_charge_current) {
+		val = current_to_hw(pcc_tbl, ARRAY_SIZE(pcc_tbl),
+				    smb->pdata->pre_charge_current);
+		if (val < 0)
+			return val;
+
+		ret &= ~CFG_CHARGE_CURRENT_PCC_MASK;
+		ret |= val << CFG_CHARGE_CURRENT_PCC_SHIFT;
+	}
+
+	if (smb->pdata->termination_current) {
+		val = current_to_hw(tc_tbl, ARRAY_SIZE(tc_tbl),
+				    smb->pdata->termination_current);
+		if (val < 0)
+			return val;
+
+		ret &= ~CFG_CHARGE_CURRENT_TC_MASK;
+		ret |= val;
+	}
+
+	return smb347_write(smb, CFG_CHARGE_CURRENT, ret);
+}
+
+static int smb347_set_current_limits(struct smb347_charger *smb)
+{
+	int ret, val;
+
+	ret = smb347_read(smb, CFG_CURRENT_LIMIT);
+	if (ret < 0)
+		return ret;
+
+	if (smb->pdata->mains_current_limit) {
+		val = current_to_hw(icl_tbl, ARRAY_SIZE(icl_tbl),
+				    smb->pdata->mains_current_limit);
+		if (val < 0)
+			return val;
+
+		ret &= ~CFG_CURRENT_LIMIT_DC_MASK;
+		ret |= val << CFG_CURRENT_LIMIT_DC_SHIFT;
+	}
+
+	if (smb->pdata->usb_hc_current_limit) {
+		val = current_to_hw(icl_tbl, ARRAY_SIZE(icl_tbl),
+				    smb->pdata->usb_hc_current_limit);
+		if (val < 0)
+			return val;
+
+		ret &= ~CFG_CURRENT_LIMIT_USB_MASK;
+		ret |= val;
+	}
+
+	return smb347_write(smb, CFG_CURRENT_LIMIT, ret);
+}
+
+static int smb347_set_voltage_limits(struct smb347_charger *smb)
+{
+	int ret, val;
+
+	ret = smb347_read(smb, CFG_FLOAT_VOLTAGE);
+	if (ret < 0)
+		return ret;
+
+	if (smb->pdata->pre_to_fast_voltage) {
+		val = smb->pdata->pre_to_fast_voltage;
+
+		/* uV */
+		val = clamp_val(val, 2400000, 3000000) - 2400000;
+		val /= 200000;
+
+		ret &= ~CFG_FLOAT_VOLTAGE_THRESHOLD_MASK;
+		ret |= val << CFG_FLOAT_VOLTAGE_THRESHOLD_SHIFT;
+	}
+
+	if (smb->pdata->max_charge_voltage) {
+		val = smb->pdata->max_charge_voltage;
+
+		/* uV */
+		val = clamp_val(val, 3500000, 4500000) - 3500000;
+		val /= 20000;
+
+		ret |= val;
+	}
+
+	return smb347_write(smb, CFG_FLOAT_VOLTAGE, ret);
+}
+
+static int smb347_set_temp_limits(struct smb347_charger *smb)
+{
+	bool enable_therm_monitor = false;
+	int ret, val;
+
+	if (smb->pdata->chip_temp_threshold) {
+		val = smb->pdata->chip_temp_threshold;
+
+		/* degree C */
+		val = clamp_val(val, 100, 130) - 100;
+		val /= 10;
+
+		ret = smb347_read(smb, CFG_OTG);
+		if (ret < 0)
+			return ret;
+
+		ret &= ~CFG_OTG_TEMP_THRESHOLD_MASK;
+		ret |= val << CFG_OTG_TEMP_THRESHOLD_SHIFT;
+
+		ret = smb347_write(smb, CFG_OTG, ret);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = smb347_read(smb, CFG_TEMP_LIMIT);
+	if (ret < 0)
+		return ret;
+
+	if (smb->pdata->soft_cold_temp_limit != SMB347_TEMP_USE_DEFAULT) {
+		val = smb->pdata->soft_cold_temp_limit;
+
+		val = clamp_val(val, 0, 15);
+		val /= 5;
+		/* this goes from higher to lower so invert the value */
+		val = ~val & 0x3;
+
+		ret &= ~CFG_TEMP_LIMIT_SOFT_COLD_MASK;
+		ret |= val << CFG_TEMP_LIMIT_SOFT_COLD_SHIFT;
+
+		enable_therm_monitor = true;
+	}
+
+	if (smb->pdata->soft_hot_temp_limit != SMB347_TEMP_USE_DEFAULT) {
+		val = smb->pdata->soft_hot_temp_limit;
+
+		val = clamp_val(val, 40, 55) - 40;
+		val /= 5;
+
+		ret &= ~CFG_TEMP_LIMIT_SOFT_HOT_MASK;
+		ret |= val << CFG_TEMP_LIMIT_SOFT_HOT_SHIFT;
+
+		enable_therm_monitor = true;
+	}
+
+	if (smb->pdata->hard_cold_temp_limit != SMB347_TEMP_USE_DEFAULT) {
+		val = smb->pdata->hard_cold_temp_limit;
+
+		val = clamp_val(val, -5, 10) + 5;
+		val /= 5;
+		/* this goes from higher to lower so invert the value */
+		val = ~val & 0x3;
+
+		ret &= ~CFG_TEMP_LIMIT_HARD_COLD_MASK;
+		ret |= val << CFG_TEMP_LIMIT_HARD_COLD_SHIFT;
+
+		enable_therm_monitor = true;
+	}
+
+	if (smb->pdata->hard_hot_temp_limit != SMB347_TEMP_USE_DEFAULT) {
+		val = smb->pdata->hard_hot_temp_limit;
+
+		val = clamp_val(val, 50, 65) - 50;
+		val /= 5;
+
+		ret &= ~CFG_TEMP_LIMIT_HARD_HOT_MASK;
+		ret |= val << CFG_TEMP_LIMIT_HARD_HOT_SHIFT;
+
+		enable_therm_monitor = true;
+	}
+
+	ret = smb347_write(smb, CFG_TEMP_LIMIT, ret);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * If any of the temperature limits are set, we also enable the
+	 * thermistor monitoring.
+	 *
+	 * When soft limits are hit, the device will start to compensate
+	 * current and/or voltage depending on the configuration.
+	 *
+	 * When hard limit is hit, the device will suspend charging
+	 * depending on the configuration.
+	 */
+	if (enable_therm_monitor) {
+		ret = smb347_read(smb, CFG_THERM);
+		if (ret < 0)
+			return ret;
+
+		ret &= ~CFG_THERM_MONITOR_DISABLED;
+
+		ret = smb347_write(smb, CFG_THERM, ret);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (smb->pdata->suspend_on_hard_temp_limit) {
+		ret = smb347_read(smb, CFG_SYSOK);
+		if (ret < 0)
+			return ret;
+
+		ret &= ~CFG_SYSOK_SUSPEND_HARD_LIMIT_DISABLED;
+
+		ret = smb347_write(smb, CFG_SYSOK, ret);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (smb->pdata->soft_temp_limit_compensation !=
+	    SMB347_SOFT_TEMP_COMPENSATE_DEFAULT) {
+		val = smb->pdata->soft_temp_limit_compensation & 0x3;
+
+		ret = smb347_read(smb, CFG_THERM);
+		if (ret < 0)
+			return ret;
+
+		ret &= ~CFG_THERM_SOFT_HOT_COMPENSATION_MASK;
+		ret |= val << CFG_THERM_SOFT_HOT_COMPENSATION_SHIFT;
+
+		ret &= ~CFG_THERM_SOFT_COLD_COMPENSATION_MASK;
+		ret |= val << CFG_THERM_SOFT_COLD_COMPENSATION_SHIFT;
+
+		ret = smb347_write(smb, CFG_THERM, ret);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (smb->pdata->charge_current_compensation) {
+		val = current_to_hw(ccc_tbl, ARRAY_SIZE(ccc_tbl),
+				    smb->pdata->charge_current_compensation);
+		if (val < 0)
+			return val;
+
+		ret = smb347_read(smb, CFG_OTG);
+		if (ret < 0)
+			return ret;
+
+		ret &= ~CFG_OTG_CC_COMPENSATION_MASK;
+		ret |= (val & 0x3) << CFG_OTG_CC_COMPENSATION_SHIFT;
+
+		ret = smb347_write(smb, CFG_OTG, ret);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
+}
+
+/*
+ * smb347_set_writable - enables/disables writing to non-volatile registers
+ * @smb: pointer to smb347 charger instance
+ *
+ * You can enable/disable writing to the non-volatile configuration
+ * registers by calling this function.
+ *
+ * Returns %0 on success and negative errno in case of failure.
+ */
+static int smb347_set_writable(struct smb347_charger *smb, bool writable)
+{
+	int ret;
+
+	ret = smb347_read(smb, CMD_A);
+	if (ret < 0)
+		return ret;
+
+	if (writable)
+		ret |= CMD_A_ALLOW_WRITE;
+	else
+		ret &= ~CMD_A_ALLOW_WRITE;
+
+	return smb347_write(smb, CMD_A, ret);
+}
+
+static int smb347_hw_init(struct smb347_charger *smb)
+{
+	int ret;
+
+	ret = smb347_set_writable(smb, true);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Program the platform specific configuration values to the device
+	 * first.
+	 */
+	ret = smb347_set_charge_current(smb);
+	if (ret < 0)
+		goto fail;
+
+	ret = smb347_set_current_limits(smb);
+	if (ret < 0)
+		goto fail;
+
+	ret = smb347_set_voltage_limits(smb);
+	if (ret < 0)
+		goto fail;
+
+	ret = smb347_set_temp_limits(smb);
+	if (ret < 0)
+		goto fail;
+
+	/* If USB charging is disabled we put the USB in suspend mode */
+	if (!smb->pdata->use_usb) {
+		ret = smb347_read(smb, CMD_A);
+		if (ret < 0)
+			goto fail;
+
+		ret |= CMD_A_SUSPEND_ENABLED;
+
+		ret = smb347_write(smb, CMD_A, ret);
+		if (ret < 0)
+			goto fail;
+	}
+
+	ret = smb347_read(smb, CFG_OTHER);
+	if (ret < 0)
+		goto fail;
+
+	/*
+	 * If configured by platform data, we enable hardware Auto-OTG
+	 * support for driving VBUS. Otherwise we disable it.
+	 */
+	ret &= ~CFG_OTHER_RID_MASK;
+	if (smb->pdata->use_usb_otg)
+		ret |= CFG_OTHER_RID_ENABLED_AUTO_OTG;
+
+	ret = smb347_write(smb, CFG_OTHER, ret);
+	if (ret < 0)
+		goto fail;
+
+	ret = smb347_read(smb, CFG_PIN);
+	if (ret < 0)
+		goto fail;
+
+	/*
+	 * Make the charging functionality controllable by a write to the
+	 * command register unless pin control is specified in the platform
+	 * data.
+	 */
+	ret &= ~CFG_PIN_EN_CTRL_MASK;
+
+	switch (smb->pdata->enable_control) {
+	case SMB347_CHG_ENABLE_SW:
+		/* Do nothing, 0 means i2c control */
+		break;
+	case SMB347_CHG_ENABLE_PIN_ACTIVE_LOW:
+		ret |= CFG_PIN_EN_CTRL_ACTIVE_LOW;
+		break;
+	case SMB347_CHG_ENABLE_PIN_ACTIVE_HIGH:
+		ret |= CFG_PIN_EN_CTRL_ACTIVE_HIGH;
+		break;
+	}
+
+	/* Disable Automatic Power Source Detection (APSD) interrupt. */
+	ret &= ~CFG_PIN_EN_APSD_IRQ;
+
+	ret = smb347_write(smb, CFG_PIN, ret);
+	if (ret < 0)
+		goto fail;
+
+	ret = smb347_update_status(smb);
+	if (ret < 0)
+		goto fail;
+
+	ret = smb347_update_online(smb);
+
+fail:
+	smb347_set_writable(smb, false);
+	return ret;
+}
+
+static irqreturn_t smb347_interrupt(int irq, void *data)
+{
+	struct smb347_charger *smb = data;
+	int stat_c, irqstat_e, irqstat_c;
+	irqreturn_t ret = IRQ_NONE;
+
+	stat_c = smb347_read(smb, STAT_C);
+	if (stat_c < 0) {
+		dev_warn(&smb->client->dev, "reading STAT_C failed\n");
+		return IRQ_NONE;
+	}
+
+	irqstat_c = smb347_read(smb, IRQSTAT_C);
+	if (irqstat_c < 0) {
+		dev_warn(&smb->client->dev, "reading IRQSTAT_C failed\n");
+		return IRQ_NONE;
+	}
+
+	irqstat_e = smb347_read(smb, IRQSTAT_E);
+	if (irqstat_e < 0) {
+		dev_warn(&smb->client->dev, "reading IRQSTAT_E failed\n");
+		return IRQ_NONE;
+	}
+
+	/*
+	 * If we get charger error we report the error back to user and
+	 * disable charging.
+	 */
+	if (stat_c & STAT_C_CHARGER_ERROR) {
+		dev_err(&smb->client->dev,
+			"error in charger, disabling charging\n");
+
+		smb347_charging_disable(smb);
+		power_supply_changed(&smb->battery);
+
+		ret = IRQ_HANDLED;
+	}
+
+	/*
+	 * If we reached the termination current the battery is charged and
+	 * we can update the status now. Charging is automatically
+	 * disabled by the hardware.
+	 */
+	if (irqstat_c & (IRQSTAT_C_TERMINATION_IRQ | IRQSTAT_C_TAPER_IRQ)) {
+		if (irqstat_c & IRQSTAT_C_TERMINATION_STAT)
+			power_supply_changed(&smb->battery);
+		ret = IRQ_HANDLED;
+	}
+
+	/*
+	 * If we got an under voltage interrupt it means that AC/USB input
+	 * was connected or disconnected.
+	 */
+	if (irqstat_e & (IRQSTAT_E_USBIN_UV_IRQ | IRQSTAT_E_DCIN_UV_IRQ)) {
+		if (smb347_update_status(smb) > 0) {
+			smb347_update_online(smb);
+			power_supply_changed(&smb->mains);
+			power_supply_changed(&smb->usb);
+		}
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static int smb347_irq_set(struct smb347_charger *smb, bool enable)
+{
+	int ret;
+
+	ret = smb347_set_writable(smb, true);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Enable/disable interrupts for:
+	 *	- under voltage
+	 *	- termination current reached
+	 *	- charger error
+	 */
+	if (enable) {
+		ret = smb347_write(smb, CFG_FAULT_IRQ, CFG_FAULT_IRQ_DCIN_UV);
+		if (ret < 0)
+			goto fail;
+
+		ret = smb347_write(smb, CFG_STATUS_IRQ,
+				   CFG_STATUS_IRQ_TERMINATION_OR_TAPER);
+		if (ret < 0)
+			goto fail;
+
+		ret = smb347_read(smb, CFG_PIN);
+		if (ret < 0)
+			goto fail;
+
+		ret |= CFG_PIN_EN_CHARGER_ERROR;
+
+		ret = smb347_write(smb, CFG_PIN, ret);
+	} else {
+		ret = smb347_write(smb, CFG_FAULT_IRQ, 0);
+		if (ret < 0)
+			goto fail;
+
+		ret = smb347_write(smb, CFG_STATUS_IRQ, 0);
+		if (ret < 0)
+			goto fail;
+
+		ret = smb347_read(smb, CFG_PIN);
+		if (ret < 0)
+			goto fail;
+
+		ret &= ~CFG_PIN_EN_CHARGER_ERROR;
+
+		ret = smb347_write(smb, CFG_PIN, ret);
+	}
+
+fail:
+	smb347_set_writable(smb, false);
+	return ret;
+}
+
+static inline int smb347_irq_enable(struct smb347_charger *smb)
+{
+	return smb347_irq_set(smb, true);
+}
+
+static inline int smb347_irq_disable(struct smb347_charger *smb)
+{
+	return smb347_irq_set(smb, false);
+}
+
+static int smb347_irq_init(struct smb347_charger *smb)
+{
+	const struct smb347_charger_platform_data *pdata = smb->pdata;
+	int ret, irq = gpio_to_irq(pdata->irq_gpio);
+
+	ret = gpio_request_one(pdata->irq_gpio, GPIOF_IN, smb->client->name);
+	if (ret < 0)
+		goto fail;
+
+	ret = request_threaded_irq(irq, NULL, smb347_interrupt,
+				   IRQF_TRIGGER_FALLING, smb->client->name,
+				   smb);
+	if (ret < 0)
+		goto fail_gpio;
+
+	ret = smb347_set_writable(smb, true);
+	if (ret < 0)
+		goto fail_irq;
+
+	/*
+	 * Configure the STAT output to be suitable for interrupts: disable
+	 * all other output (except interrupts) and make it active low.
+	 */
+	ret = smb347_read(smb, CFG_STAT);
+	if (ret < 0)
+		goto fail_readonly;
+
+	ret &= ~CFG_STAT_ACTIVE_HIGH;
+	ret |= CFG_STAT_DISABLED;
+
+	ret = smb347_write(smb, CFG_STAT, ret);
+	if (ret < 0)
+		goto fail_readonly;
+
+	ret = smb347_irq_enable(smb);
+	if (ret < 0)
+		goto fail_readonly;
+
+	smb347_set_writable(smb, false);
+	smb->client->irq = irq;
+	return 0;
+
+fail_readonly:
+	smb347_set_writable(smb, false);
+fail_irq:
+	free_irq(irq, smb);
+fail_gpio:
+	gpio_free(pdata->irq_gpio);
+fail:
+	smb->client->irq = 0;
+	return ret;
+}
+
+static int smb347_mains_get_property(struct power_supply *psy,
+				     enum power_supply_property prop,
+				     union power_supply_propval *val)
+{
+	struct smb347_charger *smb =
+		container_of(psy, struct smb347_charger, mains);
+
+	if (prop == POWER_SUPPLY_PROP_ONLINE) {
+		val->intval = smb->mains_online;
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static enum power_supply_property smb347_mains_properties[] = {
+	POWER_SUPPLY_PROP_ONLINE,
+};
+
+static int smb347_usb_get_property(struct power_supply *psy,
+				   enum power_supply_property prop,
+				   union power_supply_propval *val)
+{
+	struct smb347_charger *smb =
+		container_of(psy, struct smb347_charger, usb);
+
+	if (prop == POWER_SUPPLY_PROP_ONLINE) {
+		val->intval = smb->usb_online;
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static enum power_supply_property smb347_usb_properties[] = {
+	POWER_SUPPLY_PROP_ONLINE,
+};
+
+static int smb347_battery_get_property(struct power_supply *psy,
+				       enum power_supply_property prop,
+				       union power_supply_propval *val)
+{
+	struct smb347_charger *smb =
+			container_of(psy, struct smb347_charger, battery);
+	const struct smb347_charger_platform_data *pdata = smb->pdata;
+	int ret;
+
+	ret = smb347_update_status(smb);
+	if (ret < 0)
+		return ret;
+
+	switch (prop) {
+	case POWER_SUPPLY_PROP_STATUS:
+		if (!smb347_is_online(smb)) {
+			val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+			break;
+		}
+		if (smb347_charging_status(smb))
+			val->intval = POWER_SUPPLY_STATUS_CHARGING;
+		else
+			val->intval = POWER_SUPPLY_STATUS_FULL;
+		break;
+
+	case POWER_SUPPLY_PROP_CHARGE_TYPE:
+		if (!smb347_is_online(smb))
+			return -ENODATA;
+
+		/*
+		 * We handle trickle and pre-charging the same, and taper
+		 * and none the same.
+		 */
+		switch (smb347_charging_status(smb)) {
+		case 1:
+			val->intval = POWER_SUPPLY_CHARGE_TYPE_TRICKLE;
+			break;
+		case 2:
+			val->intval = POWER_SUPPLY_CHARGE_TYPE_FAST;
+			break;
+		default:
+			val->intval = POWER_SUPPLY_CHARGE_TYPE_NONE;
+			break;
+		}
+		break;
+
+	case POWER_SUPPLY_PROP_TECHNOLOGY:
+		val->intval = pdata->battery_info.technology;
+		break;
+
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+		val->intval = pdata->battery_info.voltage_min_design;
+		break;
+
+	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
+		val->intval = pdata->battery_info.voltage_max_design;
+		break;
+
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		if (!smb347_is_online(smb))
+			return -ENODATA;
+		ret = smb347_read(smb, STAT_A);
+		if (ret < 0)
+			return ret;
+
+		ret &= STAT_A_FLOAT_VOLTAGE_MASK;
+		if (ret > 0x3d)
+			ret = 0x3d;
+
+		val->intval = 3500000 + ret * 20000;
+		break;
+
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		if (!smb347_is_online(smb))
+			return -ENODATA;
+
+		ret = smb347_read(smb, STAT_B);
+		if (ret < 0)
+			return ret;
+
+		/*
+		 * The current value is composition of FCC and PCC values
+		 * and we can detect which table to use from bit 5.
+		 */
+		if (ret & 0x20) {
+			val->intval = hw_to_current(fcc_tbl,
+						    ARRAY_SIZE(fcc_tbl),
+						    ret & 7);
+		} else {
+			ret >>= 3;
+			val->intval = hw_to_current(pcc_tbl,
+						    ARRAY_SIZE(pcc_tbl),
+						    ret & 7);
+		}
+		break;
+
+	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
+		val->intval = pdata->battery_info.charge_full_design;
+		break;
+
+	case POWER_SUPPLY_PROP_MODEL_NAME:
+		val->strval = pdata->battery_info.name;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static enum power_supply_property smb347_battery_properties[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_CHARGE_TYPE,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
+	POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+};
+
+static int smb347_debugfs_show(struct seq_file *s, void *data)
+{
+	struct smb347_charger *smb = s->private;
+	int ret;
+	u8 reg;
+
+	seq_printf(s, "Control registers:\n");
+	seq_printf(s, "==================\n");
+	for (reg = CFG_CHARGE_CURRENT; reg <= CFG_ADDRESS; reg++) {
+		ret = smb347_read(smb, reg);
+		seq_printf(s, "0x%02x:\t0x%02x\n", reg, ret);
+	}
+	seq_printf(s, "\n");
+
+	seq_printf(s, "Command registers:\n");
+	seq_printf(s, "==================\n");
+	ret = smb347_read(smb, CMD_A);
+	seq_printf(s, "0x%02x:\t0x%02x\n", CMD_A, ret);
+	ret = smb347_read(smb, CMD_B);
+	seq_printf(s, "0x%02x:\t0x%02x\n", CMD_B, ret);
+	ret = smb347_read(smb, CMD_C);
+	seq_printf(s, "0x%02x:\t0x%02x\n", CMD_C, ret);
+	seq_printf(s, "\n");
+
+	seq_printf(s, "Interrupt status registers:\n");
+	seq_printf(s, "===========================\n");
+	for (reg = IRQSTAT_A; reg <= IRQSTAT_F; reg++) {
+		ret = smb347_read(smb, reg);
+		seq_printf(s, "0x%02x:\t0x%02x\n", reg, ret);
+	}
+	seq_printf(s, "\n");
+
+	seq_printf(s, "Status registers:\n");
+	seq_printf(s, "=================\n");
+	for (reg = STAT_A; reg <= STAT_E; reg++) {
+		ret = smb347_read(smb, reg);
+		seq_printf(s, "0x%02x:\t0x%02x\n", reg, ret);
+	}
+
+	return 0;
+}
+
+static int smb347_debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, smb347_debugfs_show, inode->i_private);
+}
+
+static const struct file_operations smb347_debugfs_fops = {
+	.open		= smb347_debugfs_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int smb347_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	static char *battery[] = { "smb347-battery" };
+	const struct smb347_charger_platform_data *pdata;
+	struct device *dev = &client->dev;
+	struct smb347_charger *smb;
+	int ret;
+
+	pdata = dev->platform_data;
+	if (!pdata)
+		return -EINVAL;
+
+	if (!pdata->use_mains && !pdata->use_usb)
+		return -EINVAL;
+
+	smb = devm_kzalloc(dev, sizeof(*smb), GFP_KERNEL);
+	if (!smb)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, smb);
+
+	mutex_init(&smb->lock);
+	smb->client = client;
+	smb->pdata = pdata;
+
+	ret = smb347_hw_init(smb);
+	if (ret < 0)
+		return ret;
+
+	smb->mains.name = "smb347-mains";
+	smb->mains.type = POWER_SUPPLY_TYPE_MAINS;
+	smb->mains.get_property = smb347_mains_get_property;
+	smb->mains.properties = smb347_mains_properties;
+	smb->mains.num_properties = ARRAY_SIZE(smb347_mains_properties);
+	smb->mains.supplied_to = battery;
+	smb->mains.num_supplicants = ARRAY_SIZE(battery);
+
+	smb->usb.name = "smb347-usb";
+	smb->usb.type = POWER_SUPPLY_TYPE_USB;
+	smb->usb.get_property = smb347_usb_get_property;
+	smb->usb.properties = smb347_usb_properties;
+	smb->usb.num_properties = ARRAY_SIZE(smb347_usb_properties);
+	smb->usb.supplied_to = battery;
+	smb->usb.num_supplicants = ARRAY_SIZE(battery);
+
+	smb->battery.name = "smb347-battery";
+	smb->battery.type = POWER_SUPPLY_TYPE_BATTERY;
+	smb->battery.get_property = smb347_battery_get_property;
+	smb->battery.properties = smb347_battery_properties;
+	smb->battery.num_properties = ARRAY_SIZE(smb347_battery_properties);
+
+	ret = power_supply_register(dev, &smb->mains);
+	if (ret < 0)
+		return ret;
+
+	ret = power_supply_register(dev, &smb->usb);
+	if (ret < 0) {
+		power_supply_unregister(&smb->mains);
+		return ret;
+	}
+
+	ret = power_supply_register(dev, &smb->battery);
+	if (ret < 0) {
+		power_supply_unregister(&smb->usb);
+		power_supply_unregister(&smb->mains);
+		return ret;
+	}
+
+	/*
+	 * Interrupt pin is optional. If it is connected, we setup the
+	 * interrupt support here.
+	 */
+	if (pdata->irq_gpio >= 0) {
+		ret = smb347_irq_init(smb);
+		if (ret < 0) {
+			dev_warn(dev, "failed to initialize IRQ: %d\n", ret);
+			dev_warn(dev, "disabling IRQ support\n");
+		}
+	}
+
+	smb->dentry = debugfs_create_file("smb347-regs", S_IRUSR, NULL, smb,
+					  &smb347_debugfs_fops);
+	return 0;
+}
+
+static int smb347_remove(struct i2c_client *client)
+{
+	struct smb347_charger *smb = i2c_get_clientdata(client);
+
+	if (!IS_ERR_OR_NULL(smb->dentry))
+		debugfs_remove(smb->dentry);
+
+	if (client->irq) {
+		smb347_irq_disable(smb);
+		free_irq(client->irq, smb);
+		gpio_free(smb->pdata->irq_gpio);
+	}
+
+	power_supply_unregister(&smb->battery);
+	power_supply_unregister(&smb->usb);
+	power_supply_unregister(&smb->mains);
+	return 0;
+}
+
+static const struct i2c_device_id smb347_id[] = {
+	{ "smb347", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, smb347_id);
+
+static struct i2c_driver smb347_driver = {
+	.driver = {
+		.name = "smb347",
+	},
+	.probe        = smb347_probe,
+	.remove       = __devexit_p(smb347_remove),
+	.id_table     = smb347_id,
+};
+
+static int __init smb347_init(void)
+{
+	return i2c_add_driver(&smb347_driver);
+}
+module_init(smb347_init);
+
+static void __exit smb347_exit(void)
+{
+	i2c_del_driver(&smb347_driver);
+}
+module_exit(smb347_exit);
+
+MODULE_AUTHOR("Bruce E. Robertson <bruce.e.robertson@intel.com>");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_DESCRIPTION("SMB347 battery charger driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("i2c:smb347");
diff --git a/drivers/power/z2_battery.c b/drivers/power/z2_battery.c
index 636ebb2a0e80..8c9a607ea77a 100644
--- a/drivers/power/z2_battery.c
+++ b/drivers/power/z2_battery.c
@@ -316,19 +316,7 @@ static struct i2c_driver z2_batt_driver = {
 	.remove		= __devexit_p(z2_batt_remove),
 	.id_table	= z2_batt_id,
 };
-
-static int __init z2_batt_init(void)
-{
-	return i2c_add_driver(&z2_batt_driver);
-}
-
-static void __exit z2_batt_exit(void)
-{
-	i2c_del_driver(&z2_batt_driver);
-}
-
-module_init(z2_batt_init);
-module_exit(z2_batt_exit);
+module_i2c_driver(z2_batt_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Peter Edwards <sweetlilmre@gmail.com>");
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 17499a55113d..53969af17558 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -138,9 +138,10 @@ static int __devinit anatop_regulator_probe(struct platform_device *pdev)
 	rdesc->type = REGULATOR_VOLTAGE;
 	rdesc->owner = THIS_MODULE;
 	sreg->mfd = anatopmfd;
-	ret = of_property_read_u32(np, "reg", &sreg->control_reg);
+	ret = of_property_read_u32(np, "anatop-reg-offset",
+				   &sreg->control_reg);
 	if (ret) {
-		dev_err(dev, "no reg property set\n");
+		dev_err(dev, "no anatop-reg-offset property set\n");
 		goto anatop_probe_end;
 	}
 	ret = of_property_read_u32(np, "anatop-vol-bit-width",
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index c056abd7562a..e70dd382a009 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2992,14 +2992,14 @@ void regulator_unregister(struct regulator_dev *rdev)
 	if (rdev == NULL)
 		return;
 
+	if (rdev->supply)
+		regulator_put(rdev->supply);
 	mutex_lock(&regulator_list_mutex);
 	debugfs_remove_recursive(rdev->debugfs);
 	flush_work_sync(&rdev->disable_work.work);
 	WARN_ON(rdev->open_count);
 	unset_regulator_supplies(rdev);
 	list_del(&rdev->list);
-	if (rdev->supply)
-		regulator_put(rdev->supply);
 	kfree(rdev->constraints);
 	device_unregister(&rdev->dev);
 	mutex_unlock(&regulator_list_mutex);
diff --git a/drivers/regulator/fixed-helper.c b/drivers/regulator/fixed-helper.c
index 30d0a15b8949..cacd33c9d042 100644
--- a/drivers/regulator/fixed-helper.c
+++ b/drivers/regulator/fixed-helper.c
@@ -18,7 +18,6 @@ static void regulator_fixed_release(struct device *dev)
 
 /**
  * regulator_register_fixed - register a no-op fixed regulator
- * @name: supply name
  * @id: platform device id
  * @supplies: consumers for this regulator
  * @num_supplies: number of consumers
@@ -32,7 +31,7 @@ struct platform_device *regulator_register_fixed(int id,
 	if (!data)
 		return NULL;
 
-	data->cfg.supply_name = "dummy";
+	data->cfg.supply_name = "fixed-dummy";
 	data->cfg.microvolts = 0;
 	data->cfg.gpio = -EINVAL;
 	data->cfg.enabled_at_boot = 1;
diff --git a/drivers/regulator/mc13892-regulator.c b/drivers/regulator/mc13892-regulator.c
index e8cfc99dd8f0..845aa2263b8a 100644
--- a/drivers/regulator/mc13892-regulator.c
+++ b/drivers/regulator/mc13892-regulator.c
@@ -552,7 +552,7 @@ static int __devinit mc13892_regulator_probe(struct platform_device *pdev)
 	mc13xxx_lock(mc13892);
 	ret = mc13xxx_reg_read(mc13892, MC13892_REVISION, &val);
 	if (ret)
-		goto err_free;
+		goto err_unlock;
 
 	/* enable switch auto mode */
 	if ((val & 0x0000FFFF) == 0x45d0) {
@@ -562,7 +562,7 @@ static int __devinit mc13892_regulator_probe(struct platform_device *pdev)
 			MC13892_SWITCHERS4_SW1MODE_AUTO |
 			MC13892_SWITCHERS4_SW2MODE_AUTO);
 		if (ret)
-			goto err_free;
+			goto err_unlock;
 
 		ret = mc13xxx_reg_rmw(mc13892, MC13892_SWITCHERS5,
 			MC13892_SWITCHERS5_SW3MODE_M |
@@ -570,7 +570,7 @@ static int __devinit mc13892_regulator_probe(struct platform_device *pdev)
 			MC13892_SWITCHERS5_SW3MODE_AUTO |
 			MC13892_SWITCHERS5_SW4MODE_AUTO);
 		if (ret)
-			goto err_free;
+			goto err_unlock;
 	}
 	mc13xxx_unlock(mc13892);
 
@@ -612,10 +612,10 @@ static int __devinit mc13892_regulator_probe(struct platform_device *pdev)
 err:
 	while (--i >= 0)
 		regulator_unregister(priv->regulators[i]);
+	return ret;
 
-err_free:
+err_unlock:
 	mc13xxx_unlock(mc13892);
-
 	return ret;
 }
 
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index 58447db15de1..4ca2db059004 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -311,8 +311,7 @@ static int s5m8767_set_voltage(struct regulator_dev *rdev,
 	struct s5m8767_info *s5m8767 = rdev_get_drvdata(rdev);
 	const struct s5m_voltage_desc *desc;
 	int reg_id = rdev_get_id(rdev);
-	int reg, mask, ret;
-	int i;
+	int sel, reg, mask, ret;
 	u8 val;
 
 	switch (reg_id) {
@@ -333,19 +332,20 @@ static int s5m8767_set_voltage(struct regulator_dev *rdev,
 
 	desc = reg_voltage_map[reg_id];
 
-	i = s5m8767_convert_voltage_to_sel(desc, min_uV, max_uV);
-	if (i < 0)
-		return i;
+	sel = s5m8767_convert_voltage_to_sel(desc, min_uV, max_uV);
+	if (sel < 0)
+		return sel;
 
 	ret = s5m8767_get_voltage_register(rdev, &reg);
 	if (ret)
 		return ret;
 
 	s5m_reg_read(s5m8767->iodev, reg, &val);
-	val = val & mask;
+	val &= ~mask;
+	val |= sel;
 
 	ret = s5m_reg_write(s5m8767->iodev, reg, val);
-	*selector = i;
+	*selector = sel;
 
 	return ret;
 }
diff --git a/drivers/regulator/tps6586x-regulator.c b/drivers/regulator/tps6586x-regulator.c
index 29b615ce3aff..cfc1f16f7771 100644
--- a/drivers/regulator/tps6586x-regulator.c
+++ b/drivers/regulator/tps6586x-regulator.c
@@ -79,6 +79,11 @@ static int tps6586x_ldo_list_voltage(struct regulator_dev *rdev,
 				     unsigned selector)
 {
 	struct tps6586x_regulator *info = rdev_get_drvdata(rdev);
+	int rid = rdev_get_id(rdev);
+
+	/* LDO0 has minimal voltage 1.2V rather than 1.25V */
+	if ((rid == TPS6586X_ID_LDO_0) && (selector == 0))
+		return (info->voltages[0] - 50) * 1000;
 
 	return info->voltages[selector] * 1000;
 }
diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c
index 4904a40b0d46..ff810e787eac 100644
--- a/drivers/regulator/wm831x-dcdc.c
+++ b/drivers/regulator/wm831x-dcdc.c
@@ -380,13 +380,15 @@ static int wm831x_buckv_set_current_limit(struct regulator_dev *rdev,
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(wm831x_dcdc_ilim); i++) {
-		if (max_uA <= wm831x_dcdc_ilim[i])
+		if ((min_uA <= wm831x_dcdc_ilim[i]) &&
+		    (wm831x_dcdc_ilim[i] <= max_uA))
 			break;
 	}
 	if (i == ARRAY_SIZE(wm831x_dcdc_ilim))
 		return -EINVAL;
 
-	return wm831x_set_bits(wm831x, reg, WM831X_DC1_HC_THR_MASK, i);
+	return wm831x_set_bits(wm831x, reg, WM831X_DC1_HC_THR_MASK,
+			       i << WM831X_DC1_HC_THR_SHIFT);
 }
 
 static int wm831x_buckv_get_current_limit(struct regulator_dev *rdev)
@@ -400,7 +402,8 @@ static int wm831x_buckv_get_current_limit(struct regulator_dev *rdev)
 	if (val < 0)
 		return val;
 
-	return wm831x_dcdc_ilim[val & WM831X_DC1_HC_THR_MASK];
+	val = (val & WM831X_DC1_HC_THR_MASK) >> WM831X_DC1_HC_THR_SHIFT;
+	return wm831x_dcdc_ilim[val];
 }
 
 static struct regulator_ops wm831x_buckv_ops = {
diff --git a/drivers/regulator/wm831x-isink.c b/drivers/regulator/wm831x-isink.c
index 634aac3f2d5f..b414e09c5620 100644
--- a/drivers/regulator/wm831x-isink.c
+++ b/drivers/regulator/wm831x-isink.c
@@ -101,7 +101,7 @@ static int wm831x_isink_set_current(struct regulator_dev *rdev,
 
 	for (i = 0; i < ARRAY_SIZE(wm831x_isinkv_values); i++) {
 		int val = wm831x_isinkv_values[i];
-		if (min_uA >= val && val <= max_uA) {
+		if (min_uA <= val && val <= max_uA) {
 			ret = wm831x_set_bits(wm831x, isink->reg,
 					      WM831X_CS1_ISEL_MASK, i);
 			return ret;
diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c
index f1e4ab0f9fda..641e9f6499d1 100644
--- a/drivers/regulator/wm831x-ldo.c
+++ b/drivers/regulator/wm831x-ldo.c
@@ -506,22 +506,19 @@ static int wm831x_aldo_set_mode(struct regulator_dev *rdev,
 {
 	struct wm831x_ldo *ldo = rdev_get_drvdata(rdev);
 	struct wm831x *wm831x = ldo->wm831x;
-	int ctrl_reg = ldo->base + WM831X_LDO_CONTROL;
 	int on_reg = ldo->base + WM831X_LDO_ON_CONTROL;
 	int ret;
 
 
 	switch (mode) {
 	case REGULATOR_MODE_NORMAL:
-		ret = wm831x_set_bits(wm831x, on_reg,
-				      WM831X_LDO7_ON_MODE, 0);
+		ret = wm831x_set_bits(wm831x, on_reg, WM831X_LDO7_ON_MODE, 0);
 		if (ret < 0)
 			return ret;
 		break;
 
 	case REGULATOR_MODE_IDLE:
-		ret = wm831x_set_bits(wm831x, ctrl_reg,
-				      WM831X_LDO7_ON_MODE,
+		ret = wm831x_set_bits(wm831x, on_reg, WM831X_LDO7_ON_MODE,
 				      WM831X_LDO7_ON_MODE);
 		if (ret < 0)
 			return ret;
diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c
index ab1e183a74b5..05ecfb872319 100644
--- a/drivers/regulator/wm8350-regulator.c
+++ b/drivers/regulator/wm8350-regulator.c
@@ -99,7 +99,7 @@ static int get_isink_val(int min_uA, int max_uA, u16 *setting)
 {
 	int i;
 
-	for (i = ARRAY_SIZE(isink_cur) - 1; i >= 0; i--) {
+	for (i = 0; i < ARRAY_SIZE(isink_cur); i++) {
 		if (min_uA <= isink_cur[i] && max_uA >= isink_cur[i]) {
 			*setting = i;
 			return 0;
@@ -186,7 +186,7 @@ static int wm8350_isink_get_current(struct regulator_dev *rdev)
 		return 0;
 	}
 
-	return DIV_ROUND_CLOSEST(isink_cur[val], 100);
+	return isink_cur[val];
 }
 
 /* turn on ISINK followed by DCDC */
@@ -495,25 +495,25 @@ static int wm8350_dcdc_set_suspend_enable(struct regulator_dev *rdev)
 		val = wm8350_reg_read(wm8350, WM8350_DCDC1_LOW_POWER)
 			& ~WM8350_DCDC_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC1_LOW_POWER,
-			wm8350->pmic.dcdc1_hib_mode);
+			val | wm8350->pmic.dcdc1_hib_mode);
 		break;
 	case WM8350_DCDC_3:
 		val = wm8350_reg_read(wm8350, WM8350_DCDC3_LOW_POWER)
 			& ~WM8350_DCDC_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC3_LOW_POWER,
-			wm8350->pmic.dcdc3_hib_mode);
+			val | wm8350->pmic.dcdc3_hib_mode);
 		break;
 	case WM8350_DCDC_4:
 		val = wm8350_reg_read(wm8350, WM8350_DCDC4_LOW_POWER)
 			& ~WM8350_DCDC_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC4_LOW_POWER,
-			wm8350->pmic.dcdc4_hib_mode);
+			val | wm8350->pmic.dcdc4_hib_mode);
 		break;
 	case WM8350_DCDC_6:
 		val = wm8350_reg_read(wm8350, WM8350_DCDC6_LOW_POWER)
 			& ~WM8350_DCDC_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC6_LOW_POWER,
-			wm8350->pmic.dcdc6_hib_mode);
+			val | wm8350->pmic.dcdc6_hib_mode);
 		break;
 	case WM8350_DCDC_2:
 	case WM8350_DCDC_5:
@@ -535,25 +535,25 @@ static int wm8350_dcdc_set_suspend_disable(struct regulator_dev *rdev)
 		val = wm8350_reg_read(wm8350, WM8350_DCDC1_LOW_POWER);
 		wm8350->pmic.dcdc1_hib_mode = val & WM8350_DCDC_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC1_LOW_POWER,
-			WM8350_DCDC_HIB_MODE_DIS);
+				 val | WM8350_DCDC_HIB_MODE_DIS);
 		break;
 	case WM8350_DCDC_3:
 		val = wm8350_reg_read(wm8350, WM8350_DCDC3_LOW_POWER);
 		wm8350->pmic.dcdc3_hib_mode = val & WM8350_DCDC_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC3_LOW_POWER,
-			WM8350_DCDC_HIB_MODE_DIS);
+				 val | WM8350_DCDC_HIB_MODE_DIS);
 		break;
 	case WM8350_DCDC_4:
 		val = wm8350_reg_read(wm8350, WM8350_DCDC4_LOW_POWER);
 		wm8350->pmic.dcdc4_hib_mode = val & WM8350_DCDC_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC4_LOW_POWER,
-			WM8350_DCDC_HIB_MODE_DIS);
+				 val | WM8350_DCDC_HIB_MODE_DIS);
 		break;
 	case WM8350_DCDC_6:
 		val = wm8350_reg_read(wm8350, WM8350_DCDC6_LOW_POWER);
 		wm8350->pmic.dcdc6_hib_mode = val & WM8350_DCDC_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC6_LOW_POWER,
-			WM8350_DCDC_HIB_MODE_DIS);
+				 val | WM8350_DCDC_HIB_MODE_DIS);
 		break;
 	case WM8350_DCDC_2:
 	case WM8350_DCDC_5:
@@ -575,13 +575,13 @@ static int wm8350_dcdc25_set_suspend_enable(struct regulator_dev *rdev)
 		val = wm8350_reg_read(wm8350, WM8350_DCDC2_CONTROL)
 		    & ~WM8350_DC2_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC2_CONTROL, val |
-				 WM8350_DC2_HIB_MODE_ACTIVE);
+		    (WM8350_DC2_HIB_MODE_ACTIVE << WM8350_DC2_HIB_MODE_SHIFT));
 		break;
 	case WM8350_DCDC_5:
 		val = wm8350_reg_read(wm8350, WM8350_DCDC5_CONTROL)
-		    & ~WM8350_DC2_HIB_MODE_MASK;
+		    & ~WM8350_DC5_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC5_CONTROL, val |
-				 WM8350_DC5_HIB_MODE_ACTIVE);
+		    (WM8350_DC5_HIB_MODE_ACTIVE << WM8350_DC5_HIB_MODE_SHIFT));
 		break;
 	default:
 		return -EINVAL;
@@ -600,13 +600,13 @@ static int wm8350_dcdc25_set_suspend_disable(struct regulator_dev *rdev)
 		val = wm8350_reg_read(wm8350, WM8350_DCDC2_CONTROL)
 		    & ~WM8350_DC2_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC2_CONTROL, val |
-				 WM8350_DC2_HIB_MODE_DISABLE);
+		    (WM8350_DC2_HIB_MODE_DISABLE << WM8350_DC2_HIB_MODE_SHIFT));
 		break;
 	case WM8350_DCDC_5:
 		val = wm8350_reg_read(wm8350, WM8350_DCDC5_CONTROL)
-		    & ~WM8350_DC2_HIB_MODE_MASK;
+		    & ~WM8350_DC5_HIB_MODE_MASK;
 		wm8350_reg_write(wm8350, WM8350_DCDC5_CONTROL, val |
-				 WM8350_DC2_HIB_MODE_DISABLE);
+		    (WM8350_DC5_HIB_MODE_DISABLE << WM8350_DC5_HIB_MODE_SHIFT));
 		break;
 	default:
 		return -EINVAL;
@@ -749,7 +749,7 @@ static int wm8350_ldo_set_suspend_disable(struct regulator_dev *rdev)
 
 	/* all LDOs have same mV bits */
 	val = wm8350_reg_read(wm8350, volt_reg) & ~WM8350_LDO1_HIB_MODE_MASK;
-	wm8350_reg_write(wm8350, volt_reg, WM8350_LDO1_HIB_MODE_DIS);
+	wm8350_reg_write(wm8350, volt_reg, val | WM8350_LDO1_HIB_MODE_DIS);
 	return 0;
 }
 
diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c
index 70277a530133..85d31a69e117 100644
--- a/drivers/remoteproc/remoteproc_debugfs.c
+++ b/drivers/remoteproc/remoteproc_debugfs.c
@@ -50,16 +50,9 @@ static ssize_t rproc_trace_read(struct file *filp, char __user *userbuf,
 	return simple_read_from_buffer(userbuf, count, ppos, trace->va, len);
 }
 
-static int rproc_open_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-
-	return 0;
-}
-
 static const struct file_operations trace_rproc_ops = {
 	.read = rproc_trace_read,
-	.open = rproc_open_generic,
+	.open = simple_open,
 	.llseek	= generic_file_llseek,
 };
 
@@ -94,7 +87,7 @@ static ssize_t rproc_state_read(struct file *filp, char __user *userbuf,
 
 static const struct file_operations rproc_state_ops = {
 	.read = rproc_state_read,
-	.open = rproc_open_generic,
+	.open = simple_open,
 	.llseek	= generic_file_llseek,
 };
 
@@ -114,7 +107,7 @@ static ssize_t rproc_name_read(struct file *filp, char __user *userbuf,
 
 static const struct file_operations rproc_name_ops = {
 	.read = rproc_name_read,
-	.open = rproc_open_generic,
+	.open = simple_open,
 	.llseek	= generic_file_llseek,
 };
 
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index dc87eda65814..eb415bd76494 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -458,6 +458,11 @@ int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled)
 	if (rtc->uie_rtctimer.enabled == enabled)
 		goto out;
 
+	if (rtc->uie_unsupported) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (enabled) {
 		struct rtc_time tm;
 		ktime_t now, onesec;
diff --git a/drivers/rtc/rtc-88pm860x.c b/drivers/rtc/rtc-88pm860x.c
index f04761e6622d..feddefc42109 100644
--- a/drivers/rtc/rtc-88pm860x.c
+++ b/drivers/rtc/rtc-88pm860x.c
@@ -72,9 +72,9 @@ static int pm860x_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	struct pm860x_rtc_info *info = dev_get_drvdata(dev);
 
 	if (enabled)
-		pm860x_set_bits(info->i2c, PM8607_RTC1, ALARM, ALARM);
+		pm860x_set_bits(info->i2c, PM8607_RTC1, ALARM_EN, ALARM_EN);
 	else
-		pm860x_set_bits(info->i2c, PM8607_RTC1, ALARM, 0);
+		pm860x_set_bits(info->i2c, PM8607_RTC1, ALARM_EN, 0);
 	return 0;
 }
 
@@ -376,6 +376,9 @@ static int __devinit pm860x_rtc_probe(struct platform_device *pdev)
 	INIT_DELAYED_WORK(&info->calib_work, calibrate_vrtc_work);
 	schedule_delayed_work(&info->calib_work, VRTC_CALIB_INTERVAL);
 #endif	/* VRTC_CALIBRATION */
+
+	device_init_wakeup(&pdev->dev, 1);
+
 	return 0;
 out_rtc:
 	free_irq(info->irq, info);
@@ -401,10 +404,34 @@ static int __devexit pm860x_rtc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int pm860x_rtc_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct pm860x_chip *chip = dev_get_drvdata(pdev->dev.parent);
+
+	if (device_may_wakeup(dev))
+		chip->wakeup_flag |= 1 << PM8607_IRQ_RTC;
+	return 0;
+}
+static int pm860x_rtc_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct pm860x_chip *chip = dev_get_drvdata(pdev->dev.parent);
+
+	if (device_may_wakeup(dev))
+		chip->wakeup_flag &= ~(1 << PM8607_IRQ_RTC);
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(pm860x_rtc_pm_ops, pm860x_rtc_suspend, pm860x_rtc_resume);
+
 static struct platform_driver pm860x_rtc_driver = {
 	.driver		= {
 		.name	= "88pm860x-rtc",
 		.owner	= THIS_MODULE,
+		.pm	= &pm860x_rtc_pm_ops,
 	},
 	.probe		= pm860x_rtc_probe,
 	.remove		= __devexit_p(pm860x_rtc_remove),
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index e954a759ba85..42f5f829b3ee 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -360,6 +360,8 @@ static int __devinit mpc5121_rtc_probe(struct platform_device *op)
 						&mpc5200_rtc_ops, THIS_MODULE);
 	}
 
+	rtc->rtc->uie_unsupported = 1;
+
 	if (IS_ERR(rtc->rtc)) {
 		err = PTR_ERR(rtc->rtc);
 		goto out_free_irq;
diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c
index 1300962486d1..b2185f4255aa 100644
--- a/drivers/rtc/rtc-mv.c
+++ b/drivers/rtc/rtc-mv.c
@@ -12,6 +12,7 @@
 #include <linux/bcd.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
 #include <linux/delay.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
@@ -294,11 +295,19 @@ static int __exit mv_rtc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static struct of_device_id rtc_mv_of_match_table[] = {
+	{ .compatible = "mrvl,orion-rtc", },
+	{}
+};
+#endif
+
 static struct platform_driver mv_rtc_driver = {
 	.remove		= __exit_p(mv_rtc_remove),
 	.driver		= {
 		.name	= "rtc-mv",
 		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(rtc_mv_of_match_table),
 	},
 };
 
diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c
index fa512ed42017..50a5c4adee48 100644
--- a/drivers/rtc/rtc-sa1100.c
+++ b/drivers/rtc/rtc-sa1100.c
@@ -33,9 +33,10 @@
 #include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/bitops.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
-#include <asm/irq.h>
+#include <mach/irqs.h>
 
 #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP)
 #include <mach/regs-rtc.h>
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index 168525a9c292..231a1d85127b 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -21,6 +21,7 @@
 #include <asm/chpid.h>
 #include <asm/sclp.h>
 #include <asm/setup.h>
+#include <asm/ctl_reg.h>
 
 #include "sclp.h"
 
diff --git a/drivers/s390/cio/crw.c b/drivers/s390/cio/crw.c
index 425f741a280c..d0a2dff43fb4 100644
--- a/drivers/s390/cio/crw.c
+++ b/drivers/s390/cio/crw.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/wait.h>
 #include <asm/crw.h>
+#include <asm/ctl_reg.h>
 
 static DEFINE_MUTEX(crw_handler_mutex);
 static crw_handler_t crw_handlers[NR_RSCS];
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 2a0dfcb0bc42..35c685c374e9 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -1458,7 +1458,6 @@ int qdio_establish(struct qdio_initialize *init_data)
 	}
 
 	qdio_setup_ssqd_info(irq_ptr);
-	DBF_EVENT("qib ac:%4x", irq_ptr->qib.ac);
 
 	qdio_detect_hsicq(irq_ptr);
 
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index 452989a7ec13..ecf12f0aca7b 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -311,7 +311,8 @@ void qdio_setup_ssqd_info(struct qdio_irq *irq_ptr)
 
 	check_and_setup_qebsm(irq_ptr, qdioac, irq_ptr->ssqd_desc.sch_token);
 	process_ac_flags(irq_ptr, qdioac);
-	DBF_EVENT("qdioac:%4x", qdioac);
+	DBF_EVENT("ac 1:%2x 2:%4x", qdioac, irq_ptr->ssqd_desc.qdioac2);
+	DBF_EVENT("3:%4x qib:%4x", irq_ptr->ssqd_desc.qdioac3, irq_ptr->qib.ac);
 }
 
 void qdio_release_memory(struct qdio_irq *irq_ptr)
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 12ae1817b172..7e9a72eb2fe0 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -42,10 +42,10 @@
 #include <asm/reset.h>
 #include <asm/airq.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/isc.h>
 #include <linux/hrtimer.h>
 #include <linux/ktime.h>
+#include <asm/facility.h>
 
 #include "ap_bus.h"
 
diff --git a/drivers/sbus/char/flash.c b/drivers/sbus/char/flash.c
index 826157f38694..327657e2e264 100644
--- a/drivers/sbus/char/flash.c
+++ b/drivers/sbus/char/flash.c
@@ -16,7 +16,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
diff --git a/drivers/sbus/char/openprom.c b/drivers/sbus/char/openprom.c
index 8d6e508222b8..2236aea3ca2f 100644
--- a/drivers/sbus/char/openprom.c
+++ b/drivers/sbus/char/openprom.c
@@ -40,7 +40,6 @@
 #include <linux/fs.h>
 #include <asm/oplib.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/openpromio.h>
 #ifdef CONFIG_PCI
diff --git a/drivers/sbus/char/uctrl.c b/drivers/sbus/char/uctrl.c
index 0b31658ccde5..a9e468cc1cac 100644
--- a/drivers/sbus/char/uctrl.c
+++ b/drivers/sbus/char/uctrl.c
@@ -19,7 +19,6 @@
 
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index f672491774eb..a3adfb4357f5 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -129,7 +129,6 @@
 #include <linux/interrupt.h>
 #include <linux/device.h>
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/byteorder.h>
diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c
index f66c33b9ab41..d4da3708763b 100644
--- a/drivers/scsi/BusLogic.c
+++ b/drivers/scsi/BusLogic.c
@@ -47,7 +47,6 @@
 
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index a06e608789e3..29684c8142b0 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -619,6 +619,7 @@ config SCSI_ARCMSR
 
 source "drivers/scsi/megaraid/Kconfig.megaraid"
 source "drivers/scsi/mpt2sas/Kconfig"
+source "drivers/scsi/ufs/Kconfig"
 
 config SCSI_HPTIOP
 	tristate "HighPoint RocketRAID 3xxx/4xxx Controller support"
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index ad24e065b1e5..8deedeaf5608 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -108,6 +108,7 @@ obj-$(CONFIG_MEGARAID_LEGACY)	+= megaraid.o
 obj-$(CONFIG_MEGARAID_NEWGEN)	+= megaraid/
 obj-$(CONFIG_MEGARAID_SAS)	+= megaraid/
 obj-$(CONFIG_SCSI_MPT2SAS)	+= mpt2sas/
+obj-$(CONFIG_SCSI_UFSHCD)	+= ufs/
 obj-$(CONFIG_SCSI_ACARD)	+= atp870u.o
 obj-$(CONFIG_SCSI_SUNESP)	+= esp_scsi.o	sun_esp.o
 obj-$(CONFIG_SCSI_GDTH)		+= gdth.o
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index bfd618a69499..374c4edf4fcb 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -41,7 +41,6 @@
 #include <linux/firmware.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c
index f17c92cf808b..19a36945e6fd 100644
--- a/drivers/scsi/aha152x.c
+++ b/drivers/scsi/aha152x.c
@@ -239,7 +239,6 @@
 #include <asm/irq.h>
 #include <linux/io.h>
 #include <linux/blkdev.h>
-#include <asm/system.h>
 #include <linux/completion.h>
 #include <linux/errno.h>
 #include <linux/string.h>
diff --git a/drivers/scsi/aha1542.c b/drivers/scsi/aha1542.c
index ed119cedaae0..ede91f378000 100644
--- a/drivers/scsi/aha1542.c
+++ b/drivers/scsi/aha1542.c
@@ -42,7 +42,6 @@
 #include <linux/slab.h>
 
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include "scsi.h"
diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c
index 1c10b796c1a2..a3e6ed353917 100644
--- a/drivers/scsi/aha1740.c
+++ b/drivers/scsi/aha1740.c
@@ -53,7 +53,6 @@
 #include <linux/gfp.h>
 
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include "scsi.h"
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index 7d48700257a7..9328121804bb 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -341,10 +341,10 @@ MODULE_PARM_DESC(aic79xx,
 "				(0/256ms,1/128ms,2/64ms,3/32ms)\n"
 "	slowcrc			Turn on the SLOWCRC bit (Rev B only)\n"		 
 "\n"
-"	Sample /etc/modprobe.conf line:\n"
-"		Enable verbose logging\n"
-"		Set tag depth on Controller 2/Target 2 to 10 tags\n"
-"		Shorten the selection timeout to 128ms\n"
+"	Sample modprobe configuration file:\n"
+"	#	Enable verbose logging\n"
+"	#	Set tag depth on Controller 2/Target 2 to 10 tags\n"
+"	#	Shorten the selection timeout to 128ms\n"
 "\n"
 "	options aic79xx 'aic79xx=verbose.tag_info:{{}.{}.{..10}}.seltime:1'\n"
 );
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index c6251bb4f438..5a477cdc780d 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -360,10 +360,10 @@ MODULE_PARM_DESC(aic7xxx,
 "	seltime:<int>		Selection Timeout\n"
 "				(0/256ms,1/128ms,2/64ms,3/32ms)\n"
 "\n"
-"	Sample /etc/modprobe.conf line:\n"
-"		Toggle EISA/VLB probing\n"
-"		Set tag depth on Controller 1/Target 1 to 10 tags\n"
-"		Shorten the selection timeout to 128ms\n"
+"	Sample modprobe configuration file:\n"
+"	#	Toggle EISA/VLB probing\n"
+"	#	Set tag depth on Controller 1/Target 1 to 10 tags\n"
+"	#	Shorten the selection timeout to 128ms\n"
 "\n"
 "	options aic7xxx 'aic7xxx=probe_eisa_vl.tag_info:{{}.{.10}}.seltime:1'\n"
 );
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 2fe9e90e53d9..cbde1dca45ad 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -61,7 +61,6 @@
 #include <linux/aer.h>
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index c454e44cf51c..b330438ac662 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -138,7 +138,6 @@
 #include <linux/stringify.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/ecard.h>
 
 #include "../scsi.h"
diff --git a/drivers/scsi/arm/arxescsi.c b/drivers/scsi/arm/arxescsi.c
index a750aa72b8ef..2a28b4ad1975 100644
--- a/drivers/scsi/arm/arxescsi.c
+++ b/drivers/scsi/arm/arxescsi.c
@@ -305,7 +305,7 @@ arxescsi_probe(struct expansion_card *ec, const struct ecard_id *id)
 	info->base = base;
 
 	info->info.scsi.io_base		= base + 0x2000;
-	info->info.scsi.irq		= NO_IRQ;
+	info->info.scsi.irq		= 0;
 	info->info.scsi.dma		= NO_DMA;
 	info->info.scsi.io_shift	= 5;
 	info->info.ifcfg.clockrate	= 24; /* MHz */
diff --git a/drivers/scsi/arm/cumana_1.c b/drivers/scsi/arm/cumana_1.c
index a3398fe70a9c..c3b99c93637a 100644
--- a/drivers/scsi/arm/cumana_1.c
+++ b/drivers/scsi/arm/cumana_1.c
@@ -12,7 +12,6 @@
 
 #include <asm/ecard.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "../scsi.h"
 #include <scsi/scsi_host.h>
diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c
index e85c40b6e19b..6206a666a8ec 100644
--- a/drivers/scsi/arm/fas216.c
+++ b/drivers/scsi/arm/fas216.c
@@ -2176,7 +2176,7 @@ static void fas216_done(FAS216_Info *info, unsigned int result)
 	fn = (void (*)(FAS216_Info *, struct scsi_cmnd *, unsigned int))SCpnt->host_scribble;
 	fn(info, SCpnt, result);
 
-	if (info->scsi.irq != NO_IRQ) {
+	if (info->scsi.irq) {
 		spin_lock_irqsave(&info->host_lock, flags);
 		if (info->scsi.phase == PHASE_IDLE)
 			fas216_kick(info);
@@ -2276,7 +2276,7 @@ static int fas216_noqueue_command_lck(struct scsi_cmnd *SCpnt,
 	 * We should only be using this if we don't have an interrupt.
 	 * Provide some "incentive" to use the queueing code.
 	 */
-	BUG_ON(info->scsi.irq != NO_IRQ);
+	BUG_ON(info->scsi.irq);
 
 	info->internal_done = 0;
 	fas216_queue_command_lck(SCpnt, fas216_internal_done);
diff --git a/drivers/scsi/arm/fas216.h b/drivers/scsi/arm/fas216.h
index 84b7127c0121..df2e1b3ddfe2 100644
--- a/drivers/scsi/arm/fas216.h
+++ b/drivers/scsi/arm/fas216.h
@@ -12,10 +12,6 @@
 #ifndef FAS216_H
 #define FAS216_H
 
-#ifndef NO_IRQ
-#define NO_IRQ 255
-#endif
-
 #include <scsi/scsi_eh.h>
 
 #include "queue.h"
diff --git a/drivers/scsi/arm/oak.c b/drivers/scsi/arm/oak.c
index 849cdf89f7bb..d25f944b59c2 100644
--- a/drivers/scsi/arm/oak.c
+++ b/drivers/scsi/arm/oak.c
@@ -13,7 +13,6 @@
 
 #include <asm/ecard.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "../scsi.h"
 #include <scsi/scsi_host.h>
diff --git a/drivers/scsi/atp870u.c b/drivers/scsi/atp870u.c
index 7e6eca4a125e..68ce08552f69 100644
--- a/drivers/scsi/atp870u.c
+++ b/drivers/scsi/atp870u.c
@@ -30,7 +30,6 @@
 #include <linux/blkdev.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <scsi/scsi.h>
@@ -2583,7 +2582,7 @@ static int atp870u_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * this than via the PCI device table
 	 */
 	if (ent->device == PCI_DEVICE_ID_ARTOP_AEC7610) {
-		error = pci_read_config_byte(pdev, PCI_CLASS_REVISION, &atpdev->chip_ver);
+		atpdev->chip_ver = pdev->revision;
 		if (atpdev->chip_ver < 2)
 			goto err_eio;
 	}
@@ -2602,7 +2601,7 @@ static int atp870u_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	base_io &= 0xfffffff8;
 
 	if ((ent->device == ATP880_DEVID1)||(ent->device == ATP880_DEVID2)) {
-		error = pci_read_config_byte(pdev, PCI_CLASS_REVISION, &atpdev->chip_ver);
+		atpdev->chip_ver = pdev->revision;
 		pci_write_config_byte(pdev, PCI_LATENCY_TIMER, 0x80);//JCC082803
 
 		host_id = inb(base_io + 0x39);
diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h
index a796de935054..4ad7e368bbc2 100644
--- a/drivers/scsi/bfa/bfa.h
+++ b/drivers/scsi/bfa/bfa.h
@@ -225,9 +225,9 @@ struct bfa_faa_args_s {
 };
 
 struct bfa_iocfc_s {
+	bfa_fsm_t		fsm;
 	struct bfa_s		*bfa;
 	struct bfa_iocfc_cfg_s	cfg;
-	int			action;
 	u32		req_cq_pi[BFI_IOC_MAX_CQS];
 	u32		rsp_cq_ci[BFI_IOC_MAX_CQS];
 	u8		hw_qid[BFI_IOC_MAX_CQS];
@@ -236,7 +236,9 @@ struct bfa_iocfc_s {
 	struct bfa_cb_qe_s	dis_hcb_qe;
 	struct bfa_cb_qe_s	en_hcb_qe;
 	struct bfa_cb_qe_s	stats_hcb_qe;
-	bfa_boolean_t		cfgdone;
+	bfa_boolean_t		submod_enabled;
+	bfa_boolean_t		cb_reqd;	/* Driver call back reqd */
+	bfa_status_t		op_status;	/* Status of bfa iocfc op */
 
 	struct bfa_dma_s	cfg_info;
 	struct bfi_iocfc_cfg_s *cfginfo;
@@ -341,8 +343,6 @@ void bfa_hwct_msix_getvecs(struct bfa_s *bfa, u32 *vecmap, u32 *nvecs,
 void bfa_hwct_msix_get_rme_range(struct bfa_s *bfa, u32 *start,
 				 u32 *end);
 void bfa_iocfc_get_bootwwns(struct bfa_s *bfa, u8 *nwwns, wwn_t *wwns);
-wwn_t bfa_iocfc_get_pwwn(struct bfa_s *bfa);
-wwn_t bfa_iocfc_get_nwwn(struct bfa_s *bfa);
 int bfa_iocfc_get_pbc_vports(struct bfa_s *bfa,
 				struct bfi_pbc_vport_s *pbc_vport);
 
@@ -428,7 +428,6 @@ bfa_status_t bfa_iocfc_israttr_set(struct bfa_s *bfa,
 
 void bfa_iocfc_enable(struct bfa_s *bfa);
 void bfa_iocfc_disable(struct bfa_s *bfa);
-void bfa_iocfc_cb_dconf_modinit(struct bfa_s *bfa, bfa_status_t status);
 #define bfa_timer_start(_bfa, _timer, _timercb, _arg, _timeout)		\
 	bfa_timer_begin(&(_bfa)->timer_mod, _timer, _timercb, _arg, _timeout)
 
diff --git a/drivers/scsi/bfa/bfa_core.c b/drivers/scsi/bfa/bfa_core.c
index 4bd546bcc240..456e5762977d 100644
--- a/drivers/scsi/bfa/bfa_core.c
+++ b/drivers/scsi/bfa/bfa_core.c
@@ -200,13 +200,431 @@ enum {
 #define DEF_CFG_NUM_SBOOT_LUNS		16
 
 /*
+ * IOCFC state machine definitions/declarations
+ */
+bfa_fsm_state_decl(bfa_iocfc, stopped, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, initing, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, dconf_read, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, init_cfg_wait,
+		   struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, init_cfg_done,
+		   struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, operational,
+		   struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, dconf_write,
+		   struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, stopping, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, enabling, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, cfg_wait, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, disabling, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, disabled, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, failed, struct bfa_iocfc_s, enum iocfc_event);
+bfa_fsm_state_decl(bfa_iocfc, init_failed,
+		   struct bfa_iocfc_s, enum iocfc_event);
+
+/*
  * forward declaration for IOC FC functions
  */
+static void bfa_iocfc_start_submod(struct bfa_s *bfa);
+static void bfa_iocfc_disable_submod(struct bfa_s *bfa);
+static void bfa_iocfc_send_cfg(void *bfa_arg);
 static void bfa_iocfc_enable_cbfn(void *bfa_arg, enum bfa_status status);
 static void bfa_iocfc_disable_cbfn(void *bfa_arg);
 static void bfa_iocfc_hbfail_cbfn(void *bfa_arg);
 static void bfa_iocfc_reset_cbfn(void *bfa_arg);
 static struct bfa_ioc_cbfn_s bfa_iocfc_cbfn;
+static void bfa_iocfc_init_cb(void *bfa_arg, bfa_boolean_t complete);
+static void bfa_iocfc_stop_cb(void *bfa_arg, bfa_boolean_t compl);
+static void bfa_iocfc_enable_cb(void *bfa_arg, bfa_boolean_t compl);
+static void bfa_iocfc_disable_cb(void *bfa_arg, bfa_boolean_t compl);
+
+static void
+bfa_iocfc_sm_stopped_entry(struct bfa_iocfc_s *iocfc)
+{
+}
+
+static void
+bfa_iocfc_sm_stopped(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_INIT:
+	case IOCFC_E_ENABLE:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_initing);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_initing_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_ioc_enable(&iocfc->bfa->ioc);
+}
+
+static void
+bfa_iocfc_sm_initing(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_IOC_ENABLED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_dconf_read);
+		break;
+	case IOCFC_E_IOC_FAILED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_init_failed);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_dconf_read_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_dconf_modinit(iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_dconf_read(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_DCONF_DONE:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_init_cfg_wait);
+		break;
+	case IOCFC_E_IOC_FAILED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_init_failed);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_init_cfg_wait_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_iocfc_send_cfg(iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_init_cfg_wait(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_CFG_DONE:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_init_cfg_done);
+		break;
+	case IOCFC_E_IOC_FAILED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_init_failed);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_init_cfg_done_entry(struct bfa_iocfc_s *iocfc)
+{
+	iocfc->bfa->iocfc.op_status = BFA_STATUS_OK;
+	bfa_cb_queue(iocfc->bfa, &iocfc->bfa->iocfc.init_hcb_qe,
+		     bfa_iocfc_init_cb, iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_init_cfg_done(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_START:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_operational);
+		break;
+	case IOCFC_E_STOP:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_stopping);
+		break;
+	case IOCFC_E_DISABLE:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_disabling);
+		break;
+	case IOCFC_E_IOC_FAILED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_failed);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_operational_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_fcport_init(iocfc->bfa);
+	bfa_iocfc_start_submod(iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_operational(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_STOP:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_dconf_write);
+		break;
+	case IOCFC_E_DISABLE:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_disabling);
+		break;
+	case IOCFC_E_IOC_FAILED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_failed);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_dconf_write_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_dconf_modexit(iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_dconf_write(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_DCONF_DONE:
+	case IOCFC_E_IOC_FAILED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_stopping);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_stopping_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_ioc_disable(&iocfc->bfa->ioc);
+}
+
+static void
+bfa_iocfc_sm_stopping(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_IOC_DISABLED:
+		bfa_isr_disable(iocfc->bfa);
+		bfa_iocfc_disable_submod(iocfc->bfa);
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_stopped);
+		iocfc->bfa->iocfc.op_status = BFA_STATUS_OK;
+		bfa_cb_queue(iocfc->bfa, &iocfc->bfa->iocfc.stop_hcb_qe,
+			     bfa_iocfc_stop_cb, iocfc->bfa);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_enabling_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_ioc_enable(&iocfc->bfa->ioc);
+}
+
+static void
+bfa_iocfc_sm_enabling(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_IOC_ENABLED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_cfg_wait);
+		break;
+	case IOCFC_E_IOC_FAILED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_failed);
+
+		if (iocfc->bfa->iocfc.cb_reqd == BFA_FALSE)
+			break;
+
+		iocfc->bfa->iocfc.op_status = BFA_STATUS_FAILED;
+		bfa_cb_queue(iocfc->bfa, &iocfc->bfa->iocfc.en_hcb_qe,
+			     bfa_iocfc_enable_cb, iocfc->bfa);
+		iocfc->bfa->iocfc.cb_reqd = BFA_FALSE;
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_cfg_wait_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_iocfc_send_cfg(iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_cfg_wait(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_CFG_DONE:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_operational);
+		if (iocfc->bfa->iocfc.cb_reqd == BFA_FALSE)
+			break;
+
+		iocfc->bfa->iocfc.op_status = BFA_STATUS_OK;
+		bfa_cb_queue(iocfc->bfa, &iocfc->bfa->iocfc.en_hcb_qe,
+			     bfa_iocfc_enable_cb, iocfc->bfa);
+		iocfc->bfa->iocfc.cb_reqd = BFA_FALSE;
+		break;
+	case IOCFC_E_IOC_FAILED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_failed);
+		if (iocfc->bfa->iocfc.cb_reqd == BFA_FALSE)
+			break;
+
+		iocfc->bfa->iocfc.op_status = BFA_STATUS_FAILED;
+		bfa_cb_queue(iocfc->bfa, &iocfc->bfa->iocfc.en_hcb_qe,
+			     bfa_iocfc_enable_cb, iocfc->bfa);
+		iocfc->bfa->iocfc.cb_reqd = BFA_FALSE;
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_disabling_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_ioc_disable(&iocfc->bfa->ioc);
+}
+
+static void
+bfa_iocfc_sm_disabling(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_IOC_DISABLED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_disabled);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_disabled_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_isr_disable(iocfc->bfa);
+	bfa_iocfc_disable_submod(iocfc->bfa);
+	iocfc->bfa->iocfc.op_status = BFA_STATUS_OK;
+	bfa_cb_queue(iocfc->bfa, &iocfc->bfa->iocfc.dis_hcb_qe,
+		     bfa_iocfc_disable_cb, iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_disabled(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_STOP:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_dconf_write);
+		break;
+	case IOCFC_E_ENABLE:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_enabling);
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_failed_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_isr_disable(iocfc->bfa);
+	bfa_iocfc_disable_submod(iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_failed(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_STOP:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_dconf_write);
+		break;
+	case IOCFC_E_DISABLE:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_disabling);
+		break;
+	case IOCFC_E_IOC_ENABLED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_cfg_wait);
+		break;
+	case IOCFC_E_IOC_FAILED:
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
+
+static void
+bfa_iocfc_sm_init_failed_entry(struct bfa_iocfc_s *iocfc)
+{
+	bfa_isr_disable(iocfc->bfa);
+	iocfc->bfa->iocfc.op_status = BFA_STATUS_FAILED;
+	bfa_cb_queue(iocfc->bfa, &iocfc->bfa->iocfc.init_hcb_qe,
+		     bfa_iocfc_init_cb, iocfc->bfa);
+}
+
+static void
+bfa_iocfc_sm_init_failed(struct bfa_iocfc_s *iocfc, enum iocfc_event event)
+{
+	bfa_trc(iocfc->bfa, event);
+
+	switch (event) {
+	case IOCFC_E_STOP:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_stopping);
+		break;
+	case IOCFC_E_DISABLE:
+		bfa_ioc_disable(&iocfc->bfa->ioc);
+		break;
+	case IOCFC_E_IOC_ENABLED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_dconf_read);
+		break;
+	case IOCFC_E_IOC_DISABLED:
+		bfa_fsm_set_state(iocfc, bfa_iocfc_sm_stopped);
+		iocfc->bfa->iocfc.op_status = BFA_STATUS_OK;
+		bfa_cb_queue(iocfc->bfa, &iocfc->bfa->iocfc.dis_hcb_qe,
+			     bfa_iocfc_disable_cb, iocfc->bfa);
+		break;
+	case IOCFC_E_IOC_FAILED:
+		break;
+	default:
+		bfa_sm_fault(iocfc->bfa, event);
+		break;
+	}
+}
 
 /*
  * BFA Interrupt handling functions
@@ -231,16 +649,19 @@ bfa_reqq_resume(struct bfa_s *bfa, int qid)
 	}
 }
 
-static inline void
+bfa_boolean_t
 bfa_isr_rspq(struct bfa_s *bfa, int qid)
 {
 	struct bfi_msg_s *m;
 	u32	pi, ci;
 	struct list_head *waitq;
+	bfa_boolean_t ret;
 
 	ci = bfa_rspq_ci(bfa, qid);
 	pi = bfa_rspq_pi(bfa, qid);
 
+	ret = (ci != pi);
+
 	while (ci != pi) {
 		m = bfa_rspq_elem(bfa, qid, ci);
 		WARN_ON(m->mhdr.msg_class >= BFI_MC_MAX);
@@ -260,6 +681,8 @@ bfa_isr_rspq(struct bfa_s *bfa, int qid)
 	waitq = bfa_reqq(bfa, qid);
 	if (!list_empty(waitq))
 		bfa_reqq_resume(bfa, qid);
+
+	return ret;
 }
 
 static inline void
@@ -320,6 +743,7 @@ bfa_intx(struct bfa_s *bfa)
 {
 	u32 intr, qintr;
 	int queue;
+	bfa_boolean_t rspq_comp = BFA_FALSE;
 
 	intr = readl(bfa->iocfc.bfa_regs.intr_status);
 
@@ -332,11 +756,12 @@ bfa_intx(struct bfa_s *bfa)
 	 */
 	if (bfa->queue_process) {
 		for (queue = 0; queue < BFI_IOC_MAX_CQS; queue++)
-			bfa_isr_rspq(bfa, queue);
+			if (bfa_isr_rspq(bfa, queue))
+				rspq_comp = BFA_TRUE;
 	}
 
 	if (!intr)
-		return BFA_TRUE;
+		return (qintr | rspq_comp) ? BFA_TRUE : BFA_FALSE;
 
 	/*
 	 * CPE completion queue interrupt
@@ -525,11 +950,9 @@ bfa_iocfc_send_cfg(void *bfa_arg)
 	 * Enable interrupt coalescing if it is driver init path
 	 * and not ioc disable/enable path.
 	 */
-	if (!iocfc->cfgdone)
+	if (bfa_fsm_cmp_state(iocfc, bfa_iocfc_sm_init_cfg_wait))
 		cfg_info->intr_attr.coalesce = BFA_TRUE;
 
-	iocfc->cfgdone = BFA_FALSE;
-
 	/*
 	 * dma map IOC configuration itself
 	 */
@@ -549,8 +972,6 @@ bfa_iocfc_init_mem(struct bfa_s *bfa, void *bfad, struct bfa_iocfc_cfg_s *cfg,
 
 	bfa->bfad = bfad;
 	iocfc->bfa = bfa;
-	iocfc->action = BFA_IOCFC_ACT_NONE;
-
 	iocfc->cfg = *cfg;
 
 	/*
@@ -683,6 +1104,8 @@ bfa_iocfc_start_submod(struct bfa_s *bfa)
 
 	for (i = 0; hal_mods[i]; i++)
 		hal_mods[i]->start(bfa);
+
+	bfa->iocfc.submod_enabled = BFA_TRUE;
 }
 
 /*
@@ -693,8 +1116,13 @@ bfa_iocfc_disable_submod(struct bfa_s *bfa)
 {
 	int		i;
 
+	if (bfa->iocfc.submod_enabled == BFA_FALSE)
+		return;
+
 	for (i = 0; hal_mods[i]; i++)
 		hal_mods[i]->iocdisable(bfa);
+
+	bfa->iocfc.submod_enabled = BFA_FALSE;
 }
 
 static void
@@ -702,15 +1130,8 @@ bfa_iocfc_init_cb(void *bfa_arg, bfa_boolean_t complete)
 {
 	struct bfa_s	*bfa = bfa_arg;
 
-	if (complete) {
-		if (bfa->iocfc.cfgdone && BFA_DCONF_MOD(bfa)->flashdone)
-			bfa_cb_init(bfa->bfad, BFA_STATUS_OK);
-		else
-			bfa_cb_init(bfa->bfad, BFA_STATUS_FAILED);
-	} else {
-		if (bfa->iocfc.cfgdone)
-			bfa->iocfc.action = BFA_IOCFC_ACT_NONE;
-	}
+	if (complete)
+		bfa_cb_init(bfa->bfad, bfa->iocfc.op_status);
 }
 
 static void
@@ -721,8 +1142,6 @@ bfa_iocfc_stop_cb(void *bfa_arg, bfa_boolean_t compl)
 
 	if (compl)
 		complete(&bfad->comp);
-	else
-		bfa->iocfc.action = BFA_IOCFC_ACT_NONE;
 }
 
 static void
@@ -794,8 +1213,6 @@ bfa_iocfc_cfgrsp(struct bfa_s *bfa)
 	fwcfg->num_uf_bufs    = be16_to_cpu(fwcfg->num_uf_bufs);
 	fwcfg->num_rports     = be16_to_cpu(fwcfg->num_rports);
 
-	iocfc->cfgdone = BFA_TRUE;
-
 	/*
 	 * configure queue register offsets as learnt from firmware
 	 */
@@ -811,22 +1228,13 @@ bfa_iocfc_cfgrsp(struct bfa_s *bfa)
 	 */
 	bfa_msix_queue_install(bfa);
 
-	/*
-	 * Configuration is complete - initialize/start submodules
-	 */
-	bfa_fcport_init(bfa);
-
-	if (iocfc->action == BFA_IOCFC_ACT_INIT) {
-		if (BFA_DCONF_MOD(bfa)->flashdone == BFA_TRUE)
-			bfa_cb_queue(bfa, &iocfc->init_hcb_qe,
-				bfa_iocfc_init_cb, bfa);
-	} else {
-		if (bfa->iocfc.action == BFA_IOCFC_ACT_ENABLE)
-			bfa_cb_queue(bfa, &bfa->iocfc.en_hcb_qe,
-					bfa_iocfc_enable_cb, bfa);
-		bfa_iocfc_start_submod(bfa);
+	if (bfa->iocfc.cfgrsp->pbc_cfg.pbc_pwwn != 0) {
+		bfa->ioc.attr->pwwn = bfa->iocfc.cfgrsp->pbc_cfg.pbc_pwwn;
+		bfa->ioc.attr->nwwn = bfa->iocfc.cfgrsp->pbc_cfg.pbc_nwwn;
+		bfa_fsm_send_event(iocfc, IOCFC_E_CFG_DONE);
 	}
 }
+
 void
 bfa_iocfc_reset_queues(struct bfa_s *bfa)
 {
@@ -840,6 +1248,23 @@ bfa_iocfc_reset_queues(struct bfa_s *bfa)
 	}
 }
 
+/*
+ *	Process FAA pwwn msg from fw.
+ */
+static void
+bfa_iocfc_process_faa_addr(struct bfa_s *bfa, struct bfi_faa_addr_msg_s *msg)
+{
+	struct bfa_iocfc_s		*iocfc   = &bfa->iocfc;
+	struct bfi_iocfc_cfgrsp_s	*cfgrsp  = iocfc->cfgrsp;
+
+	cfgrsp->pbc_cfg.pbc_pwwn = msg->pwwn;
+	cfgrsp->pbc_cfg.pbc_nwwn = msg->nwwn;
+
+	bfa->ioc.attr->pwwn = msg->pwwn;
+	bfa->ioc.attr->nwwn = msg->nwwn;
+	bfa_fsm_send_event(iocfc, IOCFC_E_CFG_DONE);
+}
+
 /* Fabric Assigned Address specific functions */
 
 /*
@@ -855,84 +1280,13 @@ bfa_faa_validate_request(struct bfa_s *bfa)
 		if ((ioc_type != BFA_IOC_TYPE_FC) || bfa_mfg_is_mezz(card_type))
 			return BFA_STATUS_FEATURE_NOT_SUPPORTED;
 	} else {
-		if (!bfa_ioc_is_acq_addr(&bfa->ioc))
-			return BFA_STATUS_IOC_NON_OP;
+		return BFA_STATUS_IOC_NON_OP;
 	}
 
 	return BFA_STATUS_OK;
 }
 
 bfa_status_t
-bfa_faa_enable(struct bfa_s *bfa, bfa_cb_iocfc_t cbfn, void *cbarg)
-{
-	struct bfi_faa_en_dis_s faa_enable_req;
-	struct bfa_iocfc_s	*iocfc = &bfa->iocfc;
-	bfa_status_t		status;
-
-	iocfc->faa_args.faa_cb.faa_cbfn = cbfn;
-	iocfc->faa_args.faa_cb.faa_cbarg = cbarg;
-
-	status = bfa_faa_validate_request(bfa);
-	if (status != BFA_STATUS_OK)
-		return status;
-
-	if (iocfc->faa_args.busy == BFA_TRUE)
-		return BFA_STATUS_DEVBUSY;
-
-	if (iocfc->faa_args.faa_state == BFA_FAA_ENABLED)
-		return BFA_STATUS_FAA_ENABLED;
-
-	if (bfa_fcport_is_trunk_enabled(bfa))
-		return BFA_STATUS_ERROR_TRUNK_ENABLED;
-
-	bfa_fcport_cfg_faa(bfa, BFA_FAA_ENABLED);
-	iocfc->faa_args.busy = BFA_TRUE;
-
-	memset(&faa_enable_req, 0, sizeof(struct bfi_faa_en_dis_s));
-	bfi_h2i_set(faa_enable_req.mh, BFI_MC_IOCFC,
-		BFI_IOCFC_H2I_FAA_ENABLE_REQ, bfa_fn_lpu(bfa));
-
-	bfa_ioc_mbox_send(&bfa->ioc, &faa_enable_req,
-			sizeof(struct bfi_faa_en_dis_s));
-
-	return BFA_STATUS_OK;
-}
-
-bfa_status_t
-bfa_faa_disable(struct bfa_s *bfa, bfa_cb_iocfc_t cbfn,
-		void *cbarg)
-{
-	struct bfi_faa_en_dis_s faa_disable_req;
-	struct bfa_iocfc_s	*iocfc = &bfa->iocfc;
-	bfa_status_t		status;
-
-	iocfc->faa_args.faa_cb.faa_cbfn = cbfn;
-	iocfc->faa_args.faa_cb.faa_cbarg = cbarg;
-
-	status = bfa_faa_validate_request(bfa);
-	if (status != BFA_STATUS_OK)
-		return status;
-
-	if (iocfc->faa_args.busy == BFA_TRUE)
-		return BFA_STATUS_DEVBUSY;
-
-	if (iocfc->faa_args.faa_state == BFA_FAA_DISABLED)
-		return BFA_STATUS_FAA_DISABLED;
-
-	bfa_fcport_cfg_faa(bfa, BFA_FAA_DISABLED);
-	iocfc->faa_args.busy = BFA_TRUE;
-
-	memset(&faa_disable_req, 0, sizeof(struct bfi_faa_en_dis_s));
-	bfi_h2i_set(faa_disable_req.mh, BFI_MC_IOCFC,
-		BFI_IOCFC_H2I_FAA_DISABLE_REQ, bfa_fn_lpu(bfa));
-
-	bfa_ioc_mbox_send(&bfa->ioc, &faa_disable_req,
-		sizeof(struct bfi_faa_en_dis_s));
-
-	return BFA_STATUS_OK;
-}
-
-bfa_status_t
 bfa_faa_query(struct bfa_s *bfa, struct bfa_faa_attr_s *attr,
 		bfa_cb_iocfc_t cbfn, void *cbarg)
 {
@@ -963,38 +1317,6 @@ bfa_faa_query(struct bfa_s *bfa, struct bfa_faa_attr_s *attr,
 }
 
 /*
- *	FAA enable response
- */
-static void
-bfa_faa_enable_reply(struct bfa_iocfc_s *iocfc,
-		struct bfi_faa_en_dis_rsp_s *rsp)
-{
-	void	*cbarg = iocfc->faa_args.faa_cb.faa_cbarg;
-	bfa_status_t	status = rsp->status;
-
-	WARN_ON(!iocfc->faa_args.faa_cb.faa_cbfn);
-
-	iocfc->faa_args.faa_cb.faa_cbfn(cbarg, status);
-	iocfc->faa_args.busy = BFA_FALSE;
-}
-
-/*
- *	FAA disable response
- */
-static void
-bfa_faa_disable_reply(struct bfa_iocfc_s *iocfc,
-		struct bfi_faa_en_dis_rsp_s *rsp)
-{
-	void	*cbarg = iocfc->faa_args.faa_cb.faa_cbarg;
-	bfa_status_t	status = rsp->status;
-
-	WARN_ON(!iocfc->faa_args.faa_cb.faa_cbfn);
-
-	iocfc->faa_args.faa_cb.faa_cbfn(cbarg, status);
-	iocfc->faa_args.busy = BFA_FALSE;
-}
-
-/*
  *	FAA query response
  */
 static void
@@ -1023,25 +1345,10 @@ bfa_iocfc_enable_cbfn(void *bfa_arg, enum bfa_status status)
 {
 	struct bfa_s	*bfa = bfa_arg;
 
-	if (status == BFA_STATUS_FAA_ACQ_ADDR) {
-		bfa_cb_queue(bfa, &bfa->iocfc.init_hcb_qe,
-				bfa_iocfc_init_cb, bfa);
-		return;
-	}
-
-	if (status != BFA_STATUS_OK) {
-		bfa_isr_disable(bfa);
-		if (bfa->iocfc.action == BFA_IOCFC_ACT_INIT)
-			bfa_cb_queue(bfa, &bfa->iocfc.init_hcb_qe,
-				     bfa_iocfc_init_cb, bfa);
-		else if (bfa->iocfc.action == BFA_IOCFC_ACT_ENABLE)
-			bfa_cb_queue(bfa, &bfa->iocfc.en_hcb_qe,
-					bfa_iocfc_enable_cb, bfa);
-		return;
-	}
-
-	bfa_iocfc_send_cfg(bfa);
-	bfa_dconf_modinit(bfa);
+	if (status == BFA_STATUS_OK)
+		bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_IOC_ENABLED);
+	else
+		bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_IOC_FAILED);
 }
 
 /*
@@ -1052,17 +1359,7 @@ bfa_iocfc_disable_cbfn(void *bfa_arg)
 {
 	struct bfa_s	*bfa = bfa_arg;
 
-	bfa_isr_disable(bfa);
-	bfa_iocfc_disable_submod(bfa);
-
-	if (bfa->iocfc.action == BFA_IOCFC_ACT_STOP)
-		bfa_cb_queue(bfa, &bfa->iocfc.stop_hcb_qe, bfa_iocfc_stop_cb,
-			     bfa);
-	else {
-		WARN_ON(bfa->iocfc.action != BFA_IOCFC_ACT_DISABLE);
-		bfa_cb_queue(bfa, &bfa->iocfc.dis_hcb_qe, bfa_iocfc_disable_cb,
-			     bfa);
-	}
+	bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_IOC_DISABLED);
 }
 
 /*
@@ -1074,13 +1371,7 @@ bfa_iocfc_hbfail_cbfn(void *bfa_arg)
 	struct bfa_s	*bfa = bfa_arg;
 
 	bfa->queue_process = BFA_FALSE;
-
-	bfa_isr_disable(bfa);
-	bfa_iocfc_disable_submod(bfa);
-
-	if (bfa->iocfc.action == BFA_IOCFC_ACT_INIT)
-		bfa_cb_queue(bfa, &bfa->iocfc.init_hcb_qe, bfa_iocfc_init_cb,
-			     bfa);
+	bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_IOC_FAILED);
 }
 
 /*
@@ -1095,7 +1386,6 @@ bfa_iocfc_reset_cbfn(void *bfa_arg)
 	bfa_isr_enable(bfa);
 }
 
-
 /*
  * Query IOC memory requirement information.
  */
@@ -1171,6 +1461,12 @@ bfa_iocfc_attach(struct bfa_s *bfa, void *bfad, struct bfa_iocfc_cfg_s *cfg,
 	INIT_LIST_HEAD(&bfa->comp_q);
 	for (i = 0; i < BFI_IOC_MAX_CQS; i++)
 		INIT_LIST_HEAD(&bfa->reqq_waitq[i]);
+
+	bfa->iocfc.cb_reqd = BFA_FALSE;
+	bfa->iocfc.op_status = BFA_STATUS_OK;
+	bfa->iocfc.submod_enabled = BFA_FALSE;
+
+	bfa_fsm_set_state(&bfa->iocfc, bfa_iocfc_sm_stopped);
 }
 
 /*
@@ -1179,8 +1475,7 @@ bfa_iocfc_attach(struct bfa_s *bfa, void *bfad, struct bfa_iocfc_cfg_s *cfg,
 void
 bfa_iocfc_init(struct bfa_s *bfa)
 {
-	bfa->iocfc.action = BFA_IOCFC_ACT_INIT;
-	bfa_ioc_enable(&bfa->ioc);
+	bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_INIT);
 }
 
 /*
@@ -1190,8 +1485,7 @@ bfa_iocfc_init(struct bfa_s *bfa)
 void
 bfa_iocfc_start(struct bfa_s *bfa)
 {
-	if (bfa->iocfc.cfgdone)
-		bfa_iocfc_start_submod(bfa);
+	bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_START);
 }
 
 /*
@@ -1201,12 +1495,8 @@ bfa_iocfc_start(struct bfa_s *bfa)
 void
 bfa_iocfc_stop(struct bfa_s *bfa)
 {
-	bfa->iocfc.action = BFA_IOCFC_ACT_STOP;
-
 	bfa->queue_process = BFA_FALSE;
-	bfa_dconf_modexit(bfa);
-	if (BFA_DCONF_MOD(bfa)->flashdone == BFA_TRUE)
-		bfa_ioc_disable(&bfa->ioc);
+	bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_STOP);
 }
 
 void
@@ -1226,13 +1516,9 @@ bfa_iocfc_isr(void *bfaarg, struct bfi_mbmsg_s *m)
 	case BFI_IOCFC_I2H_UPDATEQ_RSP:
 		iocfc->updateq_cbfn(iocfc->updateq_cbarg, BFA_STATUS_OK);
 		break;
-	case BFI_IOCFC_I2H_FAA_ENABLE_RSP:
-		bfa_faa_enable_reply(iocfc,
-			(struct bfi_faa_en_dis_rsp_s *)msg);
-		break;
-	case BFI_IOCFC_I2H_FAA_DISABLE_RSP:
-		bfa_faa_disable_reply(iocfc,
-			(struct bfi_faa_en_dis_rsp_s *)msg);
+	case BFI_IOCFC_I2H_ADDR_MSG:
+		bfa_iocfc_process_faa_addr(bfa,
+				(struct bfi_faa_addr_msg_s *)msg);
 		break;
 	case BFI_IOCFC_I2H_FAA_QUERY_RSP:
 		bfa_faa_query_reply(iocfc, (bfi_faa_query_rsp_t *)msg);
@@ -1306,8 +1592,8 @@ bfa_iocfc_enable(struct bfa_s *bfa)
 {
 	bfa_plog_str(bfa->plog, BFA_PL_MID_HAL, BFA_PL_EID_MISC, 0,
 		     "IOC Enable");
-	bfa->iocfc.action = BFA_IOCFC_ACT_ENABLE;
-	bfa_ioc_enable(&bfa->ioc);
+	bfa->iocfc.cb_reqd = BFA_TRUE;
+	bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_ENABLE);
 }
 
 void
@@ -1315,17 +1601,16 @@ bfa_iocfc_disable(struct bfa_s *bfa)
 {
 	bfa_plog_str(bfa->plog, BFA_PL_MID_HAL, BFA_PL_EID_MISC, 0,
 		     "IOC Disable");
-	bfa->iocfc.action = BFA_IOCFC_ACT_DISABLE;
 
 	bfa->queue_process = BFA_FALSE;
-	bfa_ioc_disable(&bfa->ioc);
+	bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_DISABLE);
 }
 
-
 bfa_boolean_t
 bfa_iocfc_is_operational(struct bfa_s *bfa)
 {
-	return bfa_ioc_is_operational(&bfa->ioc) && bfa->iocfc.cfgdone;
+	return bfa_ioc_is_operational(&bfa->ioc) &&
+		bfa_fsm_cmp_state(&bfa->iocfc, bfa_iocfc_sm_operational);
 }
 
 /*
@@ -1567,16 +1852,6 @@ bfa_comp_free(struct bfa_s *bfa, struct list_head *comp_q)
 	}
 }
 
-void
-bfa_iocfc_cb_dconf_modinit(struct bfa_s *bfa, bfa_status_t status)
-{
-	if (bfa->iocfc.action == BFA_IOCFC_ACT_INIT) {
-		if (bfa->iocfc.cfgdone == BFA_TRUE)
-			bfa_cb_queue(bfa, &bfa->iocfc.init_hcb_qe,
-				bfa_iocfc_init_cb, bfa);
-	}
-}
-
 /*
  * Return the list of PCI vendor/device id lists supported by this
  * BFA instance.
diff --git a/drivers/scsi/bfa/bfa_defs_svc.h b/drivers/scsi/bfa/bfa_defs_svc.h
index cb07c628b2f1..36756ce0e58f 100644
--- a/drivers/scsi/bfa/bfa_defs_svc.h
+++ b/drivers/scsi/bfa/bfa_defs_svc.h
@@ -52,7 +52,7 @@ struct bfa_iocfc_fwcfg_s {
 	u16		num_uf_bufs;	/*  unsolicited recv buffers	*/
 	u8		num_cqs;
 	u8		fw_tick_res;	/*  FW clock resolution in ms */
-	u8		rsvd[2];
+	u8		rsvd[6];
 };
 #pragma pack()
 
diff --git a/drivers/scsi/bfa/bfa_fcs_lport.c b/drivers/scsi/bfa/bfa_fcs_lport.c
index d4f951fe753e..5d2a1307e5ce 100644
--- a/drivers/scsi/bfa/bfa_fcs_lport.c
+++ b/drivers/scsi/bfa/bfa_fcs_lport.c
@@ -5717,6 +5717,8 @@ bfa_fcs_vport_free(struct bfa_fcs_vport_s *vport)
 
 	if (vport_drv->comp_del)
 		complete(vport_drv->comp_del);
+	else
+		kfree(vport_drv);
 
 	bfa_lps_delete(vport->lps);
 }
diff --git a/drivers/scsi/bfa/bfa_fcs_rport.c b/drivers/scsi/bfa/bfa_fcs_rport.c
index 52628d5d3c9b..fe0463a1db04 100644
--- a/drivers/scsi/bfa/bfa_fcs_rport.c
+++ b/drivers/scsi/bfa/bfa_fcs_rport.c
@@ -2169,7 +2169,10 @@ bfa_fcs_rport_update(struct bfa_fcs_rport_s *rport, struct fc_logi_s *plogi)
 	 * - MAX receive frame size
 	 */
 	rport->cisc = plogi->csp.cisc;
-	rport->maxfrsize = be16_to_cpu(plogi->class3.rxsz);
+	if (be16_to_cpu(plogi->class3.rxsz) < be16_to_cpu(plogi->csp.rxsz))
+		rport->maxfrsize = be16_to_cpu(plogi->class3.rxsz);
+	else
+		rport->maxfrsize = be16_to_cpu(plogi->csp.rxsz);
 
 	bfa_trc(port->fcs, be16_to_cpu(plogi->csp.bbcred));
 	bfa_trc(port->fcs, port->fabric->bb_credit);
diff --git a/drivers/scsi/bfa/bfa_ioc.c b/drivers/scsi/bfa/bfa_ioc.c
index eca7ab78085b..14e6284e48e4 100644
--- a/drivers/scsi/bfa/bfa_ioc.c
+++ b/drivers/scsi/bfa/bfa_ioc.c
@@ -88,7 +88,6 @@ static void bfa_ioc_hb_monitor(struct bfa_ioc_s *ioc);
 static void bfa_ioc_mbox_poll(struct bfa_ioc_s *ioc);
 static void bfa_ioc_mbox_flush(struct bfa_ioc_s *ioc);
 static void bfa_ioc_recover(struct bfa_ioc_s *ioc);
-static void bfa_ioc_check_attr_wwns(struct bfa_ioc_s *ioc);
 static void bfa_ioc_event_notify(struct bfa_ioc_s *ioc ,
 				enum bfa_ioc_event_e event);
 static void bfa_ioc_disable_comp(struct bfa_ioc_s *ioc);
@@ -97,7 +96,6 @@ static void bfa_ioc_debug_save_ftrc(struct bfa_ioc_s *ioc);
 static void bfa_ioc_fail_notify(struct bfa_ioc_s *ioc);
 static void bfa_ioc_pf_fwmismatch(struct bfa_ioc_s *ioc);
 
-
 /*
  * IOC state machine definitions/declarations
  */
@@ -114,7 +112,6 @@ enum ioc_event {
 	IOC_E_HWERROR		= 10,	/*  hardware error interrupt	*/
 	IOC_E_TIMEOUT		= 11,	/*  timeout			*/
 	IOC_E_HWFAILED		= 12,	/*  PCI mapping failure notice	*/
-	IOC_E_FWRSP_ACQ_ADDR	= 13,	/*  Acquiring address		*/
 };
 
 bfa_fsm_state_decl(bfa_ioc, uninit, struct bfa_ioc_s, enum ioc_event);
@@ -127,7 +124,6 @@ bfa_fsm_state_decl(bfa_ioc, fail, struct bfa_ioc_s, enum ioc_event);
 bfa_fsm_state_decl(bfa_ioc, disabling, struct bfa_ioc_s, enum ioc_event);
 bfa_fsm_state_decl(bfa_ioc, disabled, struct bfa_ioc_s, enum ioc_event);
 bfa_fsm_state_decl(bfa_ioc, hwfail, struct bfa_ioc_s, enum ioc_event);
-bfa_fsm_state_decl(bfa_ioc, acq_addr, struct bfa_ioc_s, enum ioc_event);
 
 static struct bfa_sm_table_s ioc_sm_table[] = {
 	{BFA_SM(bfa_ioc_sm_uninit), BFA_IOC_UNINIT},
@@ -140,7 +136,6 @@ static struct bfa_sm_table_s ioc_sm_table[] = {
 	{BFA_SM(bfa_ioc_sm_disabling), BFA_IOC_DISABLING},
 	{BFA_SM(bfa_ioc_sm_disabled), BFA_IOC_DISABLED},
 	{BFA_SM(bfa_ioc_sm_hwfail), BFA_IOC_HWFAIL},
-	{BFA_SM(bfa_ioc_sm_acq_addr), BFA_IOC_ACQ_ADDR},
 };
 
 /*
@@ -371,17 +366,9 @@ bfa_ioc_sm_getattr(struct bfa_ioc_s *ioc, enum ioc_event event)
 	switch (event) {
 	case IOC_E_FWRSP_GETATTR:
 		bfa_ioc_timer_stop(ioc);
-		bfa_ioc_check_attr_wwns(ioc);
-		bfa_ioc_hb_monitor(ioc);
 		bfa_fsm_set_state(ioc, bfa_ioc_sm_op);
 		break;
 
-	case IOC_E_FWRSP_ACQ_ADDR:
-		bfa_ioc_timer_stop(ioc);
-		bfa_ioc_hb_monitor(ioc);
-		bfa_fsm_set_state(ioc, bfa_ioc_sm_acq_addr);
-		break;
-
 	case IOC_E_PFFAILED:
 	case IOC_E_HWERROR:
 		bfa_ioc_timer_stop(ioc);
@@ -406,51 +393,6 @@ bfa_ioc_sm_getattr(struct bfa_ioc_s *ioc, enum ioc_event event)
 	}
 }
 
-/*
- * Acquiring address from fabric (entry function)
- */
-static void
-bfa_ioc_sm_acq_addr_entry(struct bfa_ioc_s *ioc)
-{
-}
-
-/*
- *	Acquiring address from the fabric
- */
-static void
-bfa_ioc_sm_acq_addr(struct bfa_ioc_s *ioc, enum ioc_event event)
-{
-	bfa_trc(ioc, event);
-
-	switch (event) {
-	case IOC_E_FWRSP_GETATTR:
-		bfa_ioc_check_attr_wwns(ioc);
-		bfa_fsm_set_state(ioc, bfa_ioc_sm_op);
-		break;
-
-	case IOC_E_PFFAILED:
-	case IOC_E_HWERROR:
-		bfa_hb_timer_stop(ioc);
-	case IOC_E_HBFAIL:
-		ioc->cbfn->enable_cbfn(ioc->bfa, BFA_STATUS_IOC_FAILURE);
-		bfa_fsm_set_state(ioc, bfa_ioc_sm_fail);
-		if (event != IOC_E_PFFAILED)
-			bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_GETATTRFAIL);
-		break;
-
-	case IOC_E_DISABLE:
-		bfa_hb_timer_stop(ioc);
-		bfa_fsm_set_state(ioc, bfa_ioc_sm_disabling);
-		break;
-
-	case IOC_E_ENABLE:
-		break;
-
-	default:
-		bfa_sm_fault(ioc, event);
-	}
-}
-
 static void
 bfa_ioc_sm_op_entry(struct bfa_ioc_s *ioc)
 {
@@ -458,6 +400,7 @@ bfa_ioc_sm_op_entry(struct bfa_ioc_s *ioc)
 
 	ioc->cbfn->enable_cbfn(ioc->bfa, BFA_STATUS_OK);
 	bfa_ioc_event_notify(ioc, BFA_IOC_E_ENABLED);
+	bfa_ioc_hb_monitor(ioc);
 	BFA_LOG(KERN_INFO, bfad, bfa_log_level, "IOC enabled\n");
 	bfa_ioc_aen_post(ioc, BFA_IOC_AEN_ENABLE);
 }
@@ -738,26 +681,60 @@ static void
 bfa_iocpf_sm_fwcheck_entry(struct bfa_iocpf_s *iocpf)
 {
 	struct bfi_ioc_image_hdr_s	fwhdr;
-	u32	fwstate = readl(iocpf->ioc->ioc_regs.ioc_fwstate);
+	u32	r32, fwstate, pgnum, pgoff, loff = 0;
+	int	i;
+
+	/*
+	 * Spin on init semaphore to serialize.
+	 */
+	r32 = readl(iocpf->ioc->ioc_regs.ioc_init_sem_reg);
+	while (r32 & 0x1) {
+		udelay(20);
+		r32 = readl(iocpf->ioc->ioc_regs.ioc_init_sem_reg);
+	}
 
 	/* h/w sem init */
-	if (fwstate == BFI_IOC_UNINIT)
+	fwstate = readl(iocpf->ioc->ioc_regs.ioc_fwstate);
+	if (fwstate == BFI_IOC_UNINIT) {
+		writel(1, iocpf->ioc->ioc_regs.ioc_init_sem_reg);
 		goto sem_get;
+	}
 
 	bfa_ioc_fwver_get(iocpf->ioc, &fwhdr);
 
-	if (swab32(fwhdr.exec) == BFI_FWBOOT_TYPE_NORMAL)
+	if (swab32(fwhdr.exec) == BFI_FWBOOT_TYPE_NORMAL) {
+		writel(1, iocpf->ioc->ioc_regs.ioc_init_sem_reg);
 		goto sem_get;
+	}
+
+	/*
+	 * Clear fwver hdr
+	 */
+	pgnum = PSS_SMEM_PGNUM(iocpf->ioc->ioc_regs.smem_pg0, loff);
+	pgoff = PSS_SMEM_PGOFF(loff);
+	writel(pgnum, iocpf->ioc->ioc_regs.host_page_num_fn);
+
+	for (i = 0; i < sizeof(struct bfi_ioc_image_hdr_s) / sizeof(u32); i++) {
+		bfa_mem_write(iocpf->ioc->ioc_regs.smem_page_start, loff, 0);
+		loff += sizeof(u32);
+	}
 
 	bfa_trc(iocpf->ioc, fwstate);
-	bfa_trc(iocpf->ioc, fwhdr.exec);
+	bfa_trc(iocpf->ioc, swab32(fwhdr.exec));
 	writel(BFI_IOC_UNINIT, iocpf->ioc->ioc_regs.ioc_fwstate);
+	writel(BFI_IOC_UNINIT, iocpf->ioc->ioc_regs.alt_ioc_fwstate);
 
 	/*
-	 * Try to lock and then unlock the semaphore.
+	 * Unlock the hw semaphore. Should be here only once per boot.
 	 */
 	readl(iocpf->ioc->ioc_regs.ioc_sem_reg);
 	writel(1, iocpf->ioc->ioc_regs.ioc_sem_reg);
+
+	/*
+	 * unlock init semaphore.
+	 */
+	writel(1, iocpf->ioc->ioc_regs.ioc_init_sem_reg);
+
 sem_get:
 	bfa_ioc_hw_sem_get(iocpf->ioc);
 }
@@ -1707,11 +1684,6 @@ bfa_ioc_download_fw(struct bfa_ioc_s *ioc, u32 boot_type,
 	u32 i;
 	u32 asicmode;
 
-	/*
-	 * Initialize LMEM first before code download
-	 */
-	bfa_ioc_lmem_init(ioc);
-
 	bfa_trc(ioc, bfa_cb_image_get_size(bfa_ioc_asic_gen(ioc)));
 	fwimg = bfa_cb_image_get_chunk(bfa_ioc_asic_gen(ioc), chunkno);
 
@@ -1999,6 +1971,12 @@ bfa_ioc_pll_init(struct bfa_ioc_s *ioc)
 	bfa_ioc_pll_init_asic(ioc);
 
 	ioc->pllinit = BFA_TRUE;
+
+	/*
+	 * Initialize LMEM
+	 */
+	bfa_ioc_lmem_init(ioc);
+
 	/*
 	 *  release semaphore.
 	 */
@@ -2122,10 +2100,6 @@ bfa_ioc_isr(struct bfa_ioc_s *ioc, struct bfi_mbmsg_s *m)
 		bfa_ioc_getattr_reply(ioc);
 		break;
 
-	case BFI_IOC_I2H_ACQ_ADDR_REPLY:
-		bfa_fsm_send_event(ioc, IOC_E_FWRSP_ACQ_ADDR);
-		break;
-
 	default:
 		bfa_trc(ioc, msg->mh.msg_id);
 		WARN_ON(1);
@@ -2416,15 +2390,6 @@ bfa_ioc_is_disabled(struct bfa_ioc_s *ioc)
 }
 
 /*
- * Return TRUE if IOC is in acquiring address state
- */
-bfa_boolean_t
-bfa_ioc_is_acq_addr(struct bfa_ioc_s *ioc)
-{
-	return bfa_fsm_cmp_state(ioc, bfa_ioc_sm_acq_addr);
-}
-
-/*
  * return true if IOC firmware is different.
  */
 bfa_boolean_t
@@ -2916,17 +2881,6 @@ bfa_ioc_recover(struct bfa_ioc_s *ioc)
 	bfa_fsm_send_event(ioc, IOC_E_HBFAIL);
 }
 
-static void
-bfa_ioc_check_attr_wwns(struct bfa_ioc_s *ioc)
-{
-	if (bfa_ioc_get_type(ioc) == BFA_IOC_TYPE_LL)
-		return;
-	if (ioc->attr->nwwn == 0)
-		bfa_ioc_aen_post(ioc, BFA_IOC_AEN_INVALID_NWWN);
-	if (ioc->attr->pwwn == 0)
-		bfa_ioc_aen_post(ioc, BFA_IOC_AEN_INVALID_PWWN);
-}
-
 /*
  *  BFA IOC PF private functions
  */
@@ -4495,7 +4449,7 @@ bfa_flash_read_part(struct bfa_flash_s *flash, enum bfa_flash_part_type type,
  */
 
 #define BFA_DIAG_MEMTEST_TOV	50000	/* memtest timeout in msec */
-#define BFA_DIAG_FWPING_TOV	1000	/* msec */
+#define CT2_BFA_DIAG_MEMTEST_TOV	(9*30*1000)  /* 4.5 min */
 
 /* IOC event handler */
 static void
@@ -4772,7 +4726,7 @@ diag_ledtest_send(struct bfa_diag_s *diag, struct bfa_diag_ledtest_s *ledtest)
 }
 
 static void
-diag_ledtest_comp(struct bfa_diag_s *diag, struct bfi_diag_ledtest_rsp_s * msg)
+diag_ledtest_comp(struct bfa_diag_s *diag, struct bfi_diag_ledtest_rsp_s *msg)
 {
 	bfa_trc(diag, diag->ledtest.lock);
 	diag->ledtest.lock = BFA_FALSE;
@@ -4850,6 +4804,8 @@ bfa_diag_memtest(struct bfa_diag_s *diag, struct bfa_diag_memtest_s *memtest,
 		u32 pattern, struct bfa_diag_memtest_result *result,
 		bfa_cb_diag_t cbfn, void *cbarg)
 {
+	u32	memtest_tov;
+
 	bfa_trc(diag, pattern);
 
 	if (!bfa_ioc_adapter_is_disabled(diag->ioc))
@@ -4869,8 +4825,10 @@ bfa_diag_memtest(struct bfa_diag_s *diag, struct bfa_diag_memtest_s *memtest,
 	/* download memtest code and take LPU0 out of reset */
 	bfa_ioc_boot(diag->ioc, BFI_FWBOOT_TYPE_MEMTEST, BFI_FWBOOT_ENV_OS);
 
+	memtest_tov = (bfa_ioc_asic_gen(diag->ioc) == BFI_ASIC_GEN_CT2) ?
+		       CT2_BFA_DIAG_MEMTEST_TOV : BFA_DIAG_MEMTEST_TOV;
 	bfa_timer_begin(diag->ioc->timer_mod, &diag->timer,
-			bfa_diag_memtest_done, diag, BFA_DIAG_MEMTEST_TOV);
+			bfa_diag_memtest_done, diag, memtest_tov);
 	diag->timer_active = 1;
 	return BFA_STATUS_OK;
 }
@@ -5641,24 +5599,27 @@ bfa_dconf_sm_uninit(struct bfa_dconf_mod_s *dconf, enum bfa_dconf_event event)
 	case BFA_DCONF_SM_INIT:
 		if (dconf->min_cfg) {
 			bfa_trc(dconf->bfa, dconf->min_cfg);
+			bfa_fsm_send_event(&dconf->bfa->iocfc,
+					IOCFC_E_DCONF_DONE);
 			return;
 		}
 		bfa_sm_set_state(dconf, bfa_dconf_sm_flash_read);
-		dconf->flashdone = BFA_FALSE;
-		bfa_trc(dconf->bfa, dconf->flashdone);
+		bfa_timer_start(dconf->bfa, &dconf->timer,
+			bfa_dconf_timer, dconf, BFA_DCONF_UPDATE_TOV);
 		bfa_status = bfa_flash_read_part(BFA_FLASH(dconf->bfa),
 					BFA_FLASH_PART_DRV, dconf->instance,
 					dconf->dconf,
 					sizeof(struct bfa_dconf_s), 0,
 					bfa_dconf_init_cb, dconf->bfa);
 		if (bfa_status != BFA_STATUS_OK) {
+			bfa_timer_stop(&dconf->timer);
 			bfa_dconf_init_cb(dconf->bfa, BFA_STATUS_FAILED);
 			bfa_sm_set_state(dconf, bfa_dconf_sm_uninit);
 			return;
 		}
 		break;
 	case BFA_DCONF_SM_EXIT:
-		dconf->flashdone = BFA_TRUE;
+		bfa_fsm_send_event(&dconf->bfa->iocfc, IOCFC_E_DCONF_DONE);
 	case BFA_DCONF_SM_IOCDISABLE:
 	case BFA_DCONF_SM_WR:
 	case BFA_DCONF_SM_FLASH_COMP:
@@ -5679,15 +5640,20 @@ bfa_dconf_sm_flash_read(struct bfa_dconf_mod_s *dconf,
 
 	switch (event) {
 	case BFA_DCONF_SM_FLASH_COMP:
+		bfa_timer_stop(&dconf->timer);
 		bfa_sm_set_state(dconf, bfa_dconf_sm_ready);
 		break;
 	case BFA_DCONF_SM_TIMEOUT:
 		bfa_sm_set_state(dconf, bfa_dconf_sm_ready);
+		bfa_fsm_send_event(&dconf->bfa->iocfc, IOCFC_E_IOC_FAILED);
 		break;
 	case BFA_DCONF_SM_EXIT:
-		dconf->flashdone = BFA_TRUE;
-		bfa_trc(dconf->bfa, dconf->flashdone);
+		bfa_timer_stop(&dconf->timer);
+		bfa_sm_set_state(dconf, bfa_dconf_sm_uninit);
+		bfa_fsm_send_event(&dconf->bfa->iocfc, IOCFC_E_DCONF_DONE);
+		break;
 	case BFA_DCONF_SM_IOCDISABLE:
+		bfa_timer_stop(&dconf->timer);
 		bfa_sm_set_state(dconf, bfa_dconf_sm_uninit);
 		break;
 	default:
@@ -5710,9 +5676,8 @@ bfa_dconf_sm_ready(struct bfa_dconf_mod_s *dconf, enum bfa_dconf_event event)
 		bfa_sm_set_state(dconf, bfa_dconf_sm_dirty);
 		break;
 	case BFA_DCONF_SM_EXIT:
-		dconf->flashdone = BFA_TRUE;
-		bfa_trc(dconf->bfa, dconf->flashdone);
 		bfa_sm_set_state(dconf, bfa_dconf_sm_uninit);
+		bfa_fsm_send_event(&dconf->bfa->iocfc, IOCFC_E_DCONF_DONE);
 		break;
 	case BFA_DCONF_SM_INIT:
 	case BFA_DCONF_SM_IOCDISABLE:
@@ -5774,9 +5739,7 @@ bfa_dconf_sm_final_sync(struct bfa_dconf_mod_s *dconf,
 		bfa_timer_stop(&dconf->timer);
 	case BFA_DCONF_SM_TIMEOUT:
 		bfa_sm_set_state(dconf, bfa_dconf_sm_uninit);
-		dconf->flashdone = BFA_TRUE;
-		bfa_trc(dconf->bfa, dconf->flashdone);
-		bfa_ioc_disable(&dconf->bfa->ioc);
+		bfa_fsm_send_event(&dconf->bfa->iocfc, IOCFC_E_DCONF_DONE);
 		break;
 	default:
 		bfa_sm_fault(dconf->bfa, event);
@@ -5823,8 +5786,8 @@ bfa_dconf_sm_iocdown_dirty(struct bfa_dconf_mod_s *dconf,
 		bfa_sm_set_state(dconf, bfa_dconf_sm_dirty);
 		break;
 	case BFA_DCONF_SM_EXIT:
-		dconf->flashdone = BFA_TRUE;
 		bfa_sm_set_state(dconf, bfa_dconf_sm_uninit);
+		bfa_fsm_send_event(&dconf->bfa->iocfc, IOCFC_E_DCONF_DONE);
 		break;
 	case BFA_DCONF_SM_IOCDISABLE:
 		break;
@@ -5865,11 +5828,6 @@ bfa_dconf_attach(struct bfa_s *bfa, void *bfad, struct bfa_iocfc_cfg_s *cfg,
 	if (cfg->drvcfg.min_cfg) {
 		bfa_mem_kva_curp(dconf) += sizeof(struct bfa_dconf_hdr_s);
 		dconf->min_cfg = BFA_TRUE;
-		/*
-		 * Set the flashdone flag to TRUE explicitly as no flash
-		 * write will happen in min_cfg mode.
-		 */
-		dconf->flashdone = BFA_TRUE;
 	} else {
 		dconf->min_cfg = BFA_FALSE;
 		bfa_mem_kva_curp(dconf) += sizeof(struct bfa_dconf_s);
@@ -5885,9 +5843,7 @@ bfa_dconf_init_cb(void *arg, bfa_status_t status)
 	struct bfa_s *bfa = arg;
 	struct bfa_dconf_mod_s *dconf = BFA_DCONF_MOD(bfa);
 
-	dconf->flashdone = BFA_TRUE;
-	bfa_trc(bfa, dconf->flashdone);
-	bfa_iocfc_cb_dconf_modinit(bfa, status);
+	bfa_sm_send_event(dconf, BFA_DCONF_SM_FLASH_COMP);
 	if (status == BFA_STATUS_OK) {
 		bfa_dconf_read_data_valid(bfa) = BFA_TRUE;
 		if (dconf->dconf->hdr.signature != BFI_DCONF_SIGNATURE)
@@ -5895,7 +5851,7 @@ bfa_dconf_init_cb(void *arg, bfa_status_t status)
 		if (dconf->dconf->hdr.version != BFI_DCONF_VERSION)
 			dconf->dconf->hdr.version = BFI_DCONF_VERSION;
 	}
-	bfa_sm_send_event(dconf, BFA_DCONF_SM_FLASH_COMP);
+	bfa_fsm_send_event(&bfa->iocfc, IOCFC_E_DCONF_DONE);
 }
 
 void
@@ -5977,7 +5933,5 @@ void
 bfa_dconf_modexit(struct bfa_s *bfa)
 {
 	struct bfa_dconf_mod_s *dconf = BFA_DCONF_MOD(bfa);
-	BFA_DCONF_MOD(bfa)->flashdone = BFA_FALSE;
-	bfa_trc(bfa, BFA_DCONF_MOD(bfa)->flashdone);
 	bfa_sm_send_event(dconf, BFA_DCONF_SM_EXIT);
 }
diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h
index 546d46b37101..1a99d4b5b50f 100644
--- a/drivers/scsi/bfa/bfa_ioc.h
+++ b/drivers/scsi/bfa/bfa_ioc.h
@@ -373,6 +373,22 @@ struct bfa_cb_qe_s {
 };
 
 /*
+ * IOCFC state machine definitions/declarations
+ */
+enum iocfc_event {
+	IOCFC_E_INIT		= 1,	/* IOCFC init request		*/
+	IOCFC_E_START		= 2,	/* IOCFC mod start request	*/
+	IOCFC_E_STOP		= 3,	/* IOCFC stop request		*/
+	IOCFC_E_ENABLE		= 4,	/* IOCFC enable request		*/
+	IOCFC_E_DISABLE		= 5,	/* IOCFC disable request	*/
+	IOCFC_E_IOC_ENABLED	= 6,	/* IOC enabled message		*/
+	IOCFC_E_IOC_DISABLED	= 7,	/* IOC disabled message		*/
+	IOCFC_E_IOC_FAILED	= 8,	/* failure notice by IOC sm	*/
+	IOCFC_E_DCONF_DONE	= 9,	/* dconf read/write done	*/
+	IOCFC_E_CFG_DONE	= 10,	/* IOCFC config complete	*/
+};
+
+/*
  * ASIC block configurtion related
  */
 
@@ -706,7 +722,6 @@ struct bfa_dconf_s {
 struct bfa_dconf_mod_s {
 	bfa_sm_t		sm;
 	u8			instance;
-	bfa_boolean_t		flashdone;
 	bfa_boolean_t		read_data_valid;
 	bfa_boolean_t		min_cfg;
 	struct bfa_timer_s	timer;
diff --git a/drivers/scsi/bfa/bfa_ioc_ct.c b/drivers/scsi/bfa/bfa_ioc_ct.c
index d1b8f0caaa79..2eb0c6a2938d 100644
--- a/drivers/scsi/bfa/bfa_ioc_ct.c
+++ b/drivers/scsi/bfa/bfa_ioc_ct.c
@@ -786,17 +786,73 @@ bfa_ioc_ct2_mac_reset(void __iomem *rb)
 }
 
 #define CT2_NFC_MAX_DELAY	1000
+#define CT2_NFC_VER_VALID	0x143
+#define BFA_IOC_PLL_POLL	1000000
+
+static bfa_boolean_t
+bfa_ioc_ct2_nfc_halted(void __iomem *rb)
+{
+	u32	r32;
+
+	r32 = readl(rb + CT2_NFC_CSR_SET_REG);
+	if (r32 & __NFC_CONTROLLER_HALTED)
+		return BFA_TRUE;
+
+	return BFA_FALSE;
+}
+
+static void
+bfa_ioc_ct2_nfc_resume(void __iomem *rb)
+{
+	u32	r32;
+	int i;
+
+	writel(__HALT_NFC_CONTROLLER, rb + CT2_NFC_CSR_CLR_REG);
+	for (i = 0; i < CT2_NFC_MAX_DELAY; i++) {
+		r32 = readl(rb + CT2_NFC_CSR_SET_REG);
+		if (!(r32 & __NFC_CONTROLLER_HALTED))
+			return;
+		udelay(1000);
+	}
+	WARN_ON(1);
+}
+
 bfa_status_t
 bfa_ioc_ct2_pll_init(void __iomem *rb, enum bfi_asic_mode mode)
 {
-	u32	wgn, r32;
-	int i;
+	u32 wgn, r32, nfc_ver, i;
 
-	/*
-	 * Initialize PLL if not already done by NFC
-	 */
 	wgn = readl(rb + CT2_WGN_STATUS);
-	if (!(wgn & __GLBL_PF_VF_CFG_RDY)) {
+	nfc_ver = readl(rb + CT2_RSC_GPR15_REG);
+
+	if ((wgn == (__A2T_AHB_LOAD | __WGN_READY)) &&
+	    (nfc_ver >= CT2_NFC_VER_VALID)) {
+		if (bfa_ioc_ct2_nfc_halted(rb))
+			bfa_ioc_ct2_nfc_resume(rb);
+
+		writel(__RESET_AND_START_SCLK_LCLK_PLLS,
+		       rb + CT2_CSI_FW_CTL_SET_REG);
+
+		for (i = 0; i < BFA_IOC_PLL_POLL; i++) {
+			r32 = readl(rb + CT2_APP_PLL_LCLK_CTL_REG);
+			if (r32 & __RESET_AND_START_SCLK_LCLK_PLLS)
+				break;
+		}
+
+		WARN_ON(!(r32 & __RESET_AND_START_SCLK_LCLK_PLLS));
+
+		for (i = 0; i < BFA_IOC_PLL_POLL; i++) {
+			r32 = readl(rb + CT2_APP_PLL_LCLK_CTL_REG);
+			if (!(r32 & __RESET_AND_START_SCLK_LCLK_PLLS))
+				break;
+		}
+
+		WARN_ON(r32 & __RESET_AND_START_SCLK_LCLK_PLLS);
+		udelay(1000);
+
+		r32 = readl(rb + CT2_CSI_FW_CTL_REG);
+		WARN_ON(r32 & __RESET_AND_START_SCLK_LCLK_PLLS);
+	} else {
 		writel(__HALT_NFC_CONTROLLER, rb + CT2_NFC_CSR_SET_REG);
 		for (i = 0; i < CT2_NFC_MAX_DELAY; i++) {
 			r32 = readl(rb + CT2_NFC_CSR_SET_REG);
@@ -804,57 +860,62 @@ bfa_ioc_ct2_pll_init(void __iomem *rb, enum bfi_asic_mode mode)
 				break;
 			udelay(1000);
 		}
-	}
 
-	/*
-	 * Mask the interrupts and clear any
-	 * pending interrupts.
-	 */
-	writel(1, (rb + CT2_LPU0_HOSTFN_MBOX0_MSK));
-	writel(1, (rb + CT2_LPU1_HOSTFN_MBOX0_MSK));
-
-	r32 = readl((rb + CT2_LPU0_HOSTFN_CMD_STAT));
-	if (r32 == 1) {
-		writel(1, (rb + CT2_LPU0_HOSTFN_CMD_STAT));
-		readl((rb + CT2_LPU0_HOSTFN_CMD_STAT));
+		bfa_ioc_ct2_mac_reset(rb);
+		bfa_ioc_ct2_sclk_init(rb);
+		bfa_ioc_ct2_lclk_init(rb);
+
+		/*
+		 * release soft reset on s_clk & l_clk
+		 */
+		r32 = readl(rb + CT2_APP_PLL_SCLK_CTL_REG);
+		writel(r32 & ~__APP_PLL_SCLK_LOGIC_SOFT_RESET,
+		       (rb + CT2_APP_PLL_SCLK_CTL_REG));
+
+		/*
+		 * release soft reset on s_clk & l_clk
+		 */
+		r32 = readl(rb + CT2_APP_PLL_LCLK_CTL_REG);
+		writel(r32 & ~__APP_PLL_LCLK_LOGIC_SOFT_RESET,
+		      (rb + CT2_APP_PLL_LCLK_CTL_REG));
 	}
-	r32 = readl((rb + CT2_LPU1_HOSTFN_CMD_STAT));
-	if (r32 == 1) {
-		writel(1, (rb + CT2_LPU1_HOSTFN_CMD_STAT));
-		readl((rb + CT2_LPU1_HOSTFN_CMD_STAT));
-	}
-
-	bfa_ioc_ct2_mac_reset(rb);
-	bfa_ioc_ct2_sclk_init(rb);
-	bfa_ioc_ct2_lclk_init(rb);
-
-	/*
-	 * release soft reset on s_clk & l_clk
-	 */
-	r32 = readl((rb + CT2_APP_PLL_SCLK_CTL_REG));
-	writel(r32 & ~__APP_PLL_SCLK_LOGIC_SOFT_RESET,
-		(rb + CT2_APP_PLL_SCLK_CTL_REG));
-
-	/*
-	 * release soft reset on s_clk & l_clk
-	 */
-	r32 = readl((rb + CT2_APP_PLL_LCLK_CTL_REG));
-	writel(r32 & ~__APP_PLL_LCLK_LOGIC_SOFT_RESET,
-		(rb + CT2_APP_PLL_LCLK_CTL_REG));
 
 	/*
 	 * Announce flash device presence, if flash was corrupted.
 	 */
 	if (wgn == (__WGN_READY | __GLBL_PF_VF_CFG_RDY)) {
-		r32 = readl((rb + PSS_GPIO_OUT_REG));
+		r32 = readl(rb + PSS_GPIO_OUT_REG);
 		writel(r32 & ~1, (rb + PSS_GPIO_OUT_REG));
-		r32 = readl((rb + PSS_GPIO_OE_REG));
+		r32 = readl(rb + PSS_GPIO_OE_REG);
 		writel(r32 | 1, (rb + PSS_GPIO_OE_REG));
 	}
 
+	/*
+	 * Mask the interrupts and clear any
+	 * pending interrupts.
+	 */
+	writel(1, (rb + CT2_LPU0_HOSTFN_MBOX0_MSK));
+	writel(1, (rb + CT2_LPU1_HOSTFN_MBOX0_MSK));
+
+	/* For first time initialization, no need to clear interrupts */
+	r32 = readl(rb + HOST_SEM5_REG);
+	if (r32 & 0x1) {
+		r32 = readl(rb + CT2_LPU0_HOSTFN_CMD_STAT);
+		if (r32 == 1) {
+			writel(1, rb + CT2_LPU0_HOSTFN_CMD_STAT);
+			readl((rb + CT2_LPU0_HOSTFN_CMD_STAT));
+		}
+		r32 = readl(rb + CT2_LPU1_HOSTFN_CMD_STAT);
+		if (r32 == 1) {
+			writel(1, rb + CT2_LPU1_HOSTFN_CMD_STAT);
+			readl(rb + CT2_LPU1_HOSTFN_CMD_STAT);
+		}
+	}
+
 	bfa_ioc_ct2_mem_init(rb);
 
-	writel(BFI_IOC_UNINIT, (rb + CT2_BFA_IOC0_STATE_REG));
-	writel(BFI_IOC_UNINIT, (rb + CT2_BFA_IOC1_STATE_REG));
+	writel(BFI_IOC_UNINIT, rb + CT2_BFA_IOC0_STATE_REG);
+	writel(BFI_IOC_UNINIT, rb + CT2_BFA_IOC1_STATE_REG);
+
 	return BFA_STATUS_OK;
 }
diff --git a/drivers/scsi/bfa/bfa_svc.c b/drivers/scsi/bfa/bfa_svc.c
index aa8a0eaf91f9..2e856e6710f7 100644
--- a/drivers/scsi/bfa/bfa_svc.c
+++ b/drivers/scsi/bfa/bfa_svc.c
@@ -1280,6 +1280,7 @@ bfa_lps_sm_loginwait(struct bfa_lps_s *lps, enum bfa_lps_event event)
 	switch (event) {
 	case BFA_LPS_SM_RESUME:
 		bfa_sm_set_state(lps, bfa_lps_sm_login);
+		bfa_lps_send_login(lps);
 		break;
 
 	case BFA_LPS_SM_OFFLINE:
@@ -1578,7 +1579,7 @@ bfa_lps_login_rsp(struct bfa_s *bfa, struct bfi_lps_login_rsp_s *rsp)
 		break;
 
 	case BFA_STATUS_VPORT_MAX:
-		if (!rsp->ext_status)
+		if (rsp->ext_status)
 			bfa_lps_no_res(lps, rsp->ext_status);
 		break;
 
@@ -3084,33 +3085,6 @@ bfa_fcport_set_wwns(struct bfa_fcport_s *fcport)
 }
 
 static void
-bfa_fcport_send_txcredit(void *port_cbarg)
-{
-
-	struct bfa_fcport_s *fcport = port_cbarg;
-	struct bfi_fcport_set_svc_params_req_s *m;
-
-	/*
-	 * check for room in queue to send request now
-	 */
-	m = bfa_reqq_next(fcport->bfa, BFA_REQQ_PORT);
-	if (!m) {
-		bfa_trc(fcport->bfa, fcport->cfg.tx_bbcredit);
-		return;
-	}
-
-	bfi_h2i_set(m->mh, BFI_MC_FCPORT, BFI_FCPORT_H2I_SET_SVC_PARAMS_REQ,
-			bfa_fn_lpu(fcport->bfa));
-	m->tx_bbcredit = cpu_to_be16((u16)fcport->cfg.tx_bbcredit);
-	m->bb_scn = fcport->cfg.bb_scn;
-
-	/*
-	 * queue I/O message to firmware
-	 */
-	bfa_reqq_produce(fcport->bfa, BFA_REQQ_PORT, m->mh);
-}
-
-static void
 bfa_fcport_qos_stats_swap(struct bfa_qos_stats_s *d,
 	struct bfa_qos_stats_s *s)
 {
@@ -3602,26 +3576,24 @@ bfa_fcport_cfg_speed(struct bfa_s *bfa, enum bfa_port_speed speed)
 		return BFA_STATUS_UNSUPP_SPEED;
 	}
 
-	/* For Mezz card, port speed entered needs to be checked */
-	if (bfa_mfg_is_mezz(fcport->bfa->ioc.attr->card_type)) {
-		if (bfa_ioc_get_type(&fcport->bfa->ioc) == BFA_IOC_TYPE_FC) {
-			/* For CT2, 1G is not supported */
-			if ((speed == BFA_PORT_SPEED_1GBPS) &&
-			    (bfa_asic_id_ct2(bfa->ioc.pcidev.device_id)))
-				return BFA_STATUS_UNSUPP_SPEED;
+	/* Port speed entered needs to be checked */
+	if (bfa_ioc_get_type(&fcport->bfa->ioc) == BFA_IOC_TYPE_FC) {
+		/* For CT2, 1G is not supported */
+		if ((speed == BFA_PORT_SPEED_1GBPS) &&
+		    (bfa_asic_id_ct2(bfa->ioc.pcidev.device_id)))
+			return BFA_STATUS_UNSUPP_SPEED;
 
-			/* Already checked for Auto Speed and Max Speed supp */
-			if (!(speed == BFA_PORT_SPEED_1GBPS ||
-			      speed == BFA_PORT_SPEED_2GBPS ||
-			      speed == BFA_PORT_SPEED_4GBPS ||
-			      speed == BFA_PORT_SPEED_8GBPS ||
-			      speed == BFA_PORT_SPEED_16GBPS ||
-			      speed == BFA_PORT_SPEED_AUTO))
-				return BFA_STATUS_UNSUPP_SPEED;
-		} else {
-			if (speed != BFA_PORT_SPEED_10GBPS)
-				return BFA_STATUS_UNSUPP_SPEED;
-		}
+		/* Already checked for Auto Speed and Max Speed supp */
+		if (!(speed == BFA_PORT_SPEED_1GBPS ||
+		      speed == BFA_PORT_SPEED_2GBPS ||
+		      speed == BFA_PORT_SPEED_4GBPS ||
+		      speed == BFA_PORT_SPEED_8GBPS ||
+		      speed == BFA_PORT_SPEED_16GBPS ||
+		      speed == BFA_PORT_SPEED_AUTO))
+			return BFA_STATUS_UNSUPP_SPEED;
+	} else {
+		if (speed != BFA_PORT_SPEED_10GBPS)
+			return BFA_STATUS_UNSUPP_SPEED;
 	}
 
 	fcport->cfg.speed = speed;
@@ -3765,7 +3737,6 @@ bfa_fcport_set_tx_bbcredit(struct bfa_s *bfa, u16 tx_bbcredit, u8 bb_scn)
 	fcport->cfg.bb_scn = bb_scn;
 	if (bb_scn)
 		fcport->bbsc_op_state = BFA_TRUE;
-	bfa_fcport_send_txcredit(fcport);
 }
 
 /*
@@ -3825,8 +3796,6 @@ bfa_fcport_get_attr(struct bfa_s *bfa, struct bfa_port_attr_s *attr)
 			attr->port_state = BFA_PORT_ST_IOCDIS;
 		else if (bfa_ioc_fw_mismatch(&fcport->bfa->ioc))
 			attr->port_state = BFA_PORT_ST_FWMISMATCH;
-		else if (bfa_ioc_is_acq_addr(&fcport->bfa->ioc))
-			attr->port_state = BFA_PORT_ST_ACQ_ADDR;
 	}
 
 	/* FCoE vlan */
diff --git a/drivers/scsi/bfa/bfa_svc.h b/drivers/scsi/bfa/bfa_svc.h
index b52cbb6bcd5a..f30067564639 100644
--- a/drivers/scsi/bfa/bfa_svc.h
+++ b/drivers/scsi/bfa/bfa_svc.h
@@ -663,10 +663,6 @@ void bfa_cb_lps_fdisclogo_comp(void *bfad, void *uarg);
 void bfa_cb_lps_cvl_event(void *bfad, void *uarg);
 
 /* FAA specific APIs */
-bfa_status_t bfa_faa_enable(struct bfa_s *bfa,
-			bfa_cb_iocfc_t cbfn, void *cbarg);
-bfa_status_t bfa_faa_disable(struct bfa_s *bfa,
-			bfa_cb_iocfc_t cbfn, void *cbarg);
 bfa_status_t bfa_faa_query(struct bfa_s *bfa, struct bfa_faa_attr_s *attr,
 			bfa_cb_iocfc_t cbfn, void *cbarg);
 
diff --git a/drivers/scsi/bfa/bfad_attr.c b/drivers/scsi/bfa/bfad_attr.c
index 1938fe0473e9..7b1ecd2b3ffe 100644
--- a/drivers/scsi/bfa/bfad_attr.c
+++ b/drivers/scsi/bfa/bfad_attr.c
@@ -442,6 +442,43 @@ bfad_im_vport_create(struct fc_vport *fc_vport, bool disable)
 	return status;
 }
 
+int
+bfad_im_issue_fc_host_lip(struct Scsi_Host *shost)
+{
+	struct bfad_im_port_s *im_port =
+			(struct bfad_im_port_s *) shost->hostdata[0];
+	struct bfad_s *bfad = im_port->bfad;
+	struct bfad_hal_comp fcomp;
+	unsigned long flags;
+	uint32_t status;
+
+	init_completion(&fcomp.comp);
+	spin_lock_irqsave(&bfad->bfad_lock, flags);
+	status = bfa_port_disable(&bfad->bfa.modules.port,
+					bfad_hcb_comp, &fcomp);
+	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
+
+	if (status != BFA_STATUS_OK)
+		return -EIO;
+
+	wait_for_completion(&fcomp.comp);
+	if (fcomp.status != BFA_STATUS_OK)
+		return -EIO;
+
+	spin_lock_irqsave(&bfad->bfad_lock, flags);
+	status = bfa_port_enable(&bfad->bfa.modules.port,
+					bfad_hcb_comp, &fcomp);
+	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
+	if (status != BFA_STATUS_OK)
+		return -EIO;
+
+	wait_for_completion(&fcomp.comp);
+	if (fcomp.status != BFA_STATUS_OK)
+		return -EIO;
+
+	return 0;
+}
+
 static int
 bfad_im_vport_delete(struct fc_vport *fc_vport)
 {
@@ -457,8 +494,11 @@ bfad_im_vport_delete(struct fc_vport *fc_vport)
 	unsigned long flags;
 	struct completion fcomp;
 
-	if (im_port->flags & BFAD_PORT_DELETE)
-		goto free_scsi_host;
+	if (im_port->flags & BFAD_PORT_DELETE) {
+		bfad_scsi_host_free(bfad, im_port);
+		list_del(&vport->list_entry);
+		return 0;
+	}
 
 	port = im_port->port;
 
@@ -489,7 +529,6 @@ bfad_im_vport_delete(struct fc_vport *fc_vport)
 
 	wait_for_completion(vport->comp_del);
 
-free_scsi_host:
 	bfad_scsi_host_free(bfad, im_port);
 	list_del(&vport->list_entry);
 	kfree(vport);
@@ -579,7 +618,7 @@ struct fc_function_template bfad_im_fc_function_template = {
 	.show_rport_dev_loss_tmo = 1,
 	.get_rport_dev_loss_tmo = bfad_im_get_rport_loss_tmo,
 	.set_rport_dev_loss_tmo = bfad_im_set_rport_loss_tmo,
-
+	.issue_fc_host_lip = bfad_im_issue_fc_host_lip,
 	.vport_create = bfad_im_vport_create,
 	.vport_delete = bfad_im_vport_delete,
 	.vport_disable = bfad_im_vport_disable,
diff --git a/drivers/scsi/bfa/bfad_bsg.c b/drivers/scsi/bfa/bfad_bsg.c
index 8005c6c5a080..e1f4b10df42a 100644
--- a/drivers/scsi/bfa/bfad_bsg.c
+++ b/drivers/scsi/bfa/bfad_bsg.c
@@ -1288,50 +1288,6 @@ out:
 }
 
 int
-bfad_iocmd_faa_enable(struct bfad_s *bfad, void *cmd)
-{
-	struct bfa_bsg_gen_s *iocmd = (struct bfa_bsg_gen_s *)cmd;
-	unsigned long   flags;
-	struct bfad_hal_comp    fcomp;
-
-	init_completion(&fcomp.comp);
-	iocmd->status = BFA_STATUS_OK;
-	spin_lock_irqsave(&bfad->bfad_lock, flags);
-	iocmd->status = bfa_faa_enable(&bfad->bfa, bfad_hcb_comp, &fcomp);
-	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
-
-	if (iocmd->status != BFA_STATUS_OK)
-		goto out;
-
-	wait_for_completion(&fcomp.comp);
-	iocmd->status = fcomp.status;
-out:
-	return 0;
-}
-
-int
-bfad_iocmd_faa_disable(struct bfad_s *bfad, void *cmd)
-{
-	struct bfa_bsg_gen_s *iocmd = (struct bfa_bsg_gen_s *)cmd;
-	unsigned long   flags;
-	struct bfad_hal_comp    fcomp;
-
-	init_completion(&fcomp.comp);
-	iocmd->status = BFA_STATUS_OK;
-	spin_lock_irqsave(&bfad->bfad_lock, flags);
-	iocmd->status = bfa_faa_disable(&bfad->bfa, bfad_hcb_comp, &fcomp);
-	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
-
-	if (iocmd->status != BFA_STATUS_OK)
-		goto out;
-
-	wait_for_completion(&fcomp.comp);
-	iocmd->status = fcomp.status;
-out:
-	return 0;
-}
-
-int
 bfad_iocmd_faa_query(struct bfad_s *bfad, void *cmd)
 {
 	struct bfa_bsg_faa_attr_s *iocmd = (struct bfa_bsg_faa_attr_s *)cmd;
@@ -1918,6 +1874,7 @@ bfad_iocmd_debug_fw_core(struct bfad_s *bfad, void *cmd,
 	struct bfa_bsg_debug_s *iocmd = (struct bfa_bsg_debug_s *)cmd;
 	void	*iocmd_bufptr;
 	unsigned long	flags;
+	u32 offset;
 
 	if (bfad_chk_iocmd_sz(payload_len, sizeof(struct bfa_bsg_debug_s),
 			BFA_DEBUG_FW_CORE_CHUNK_SZ) != BFA_STATUS_OK) {
@@ -1935,8 +1892,10 @@ bfad_iocmd_debug_fw_core(struct bfad_s *bfad, void *cmd,
 
 	iocmd_bufptr = (char *)iocmd + sizeof(struct bfa_bsg_debug_s);
 	spin_lock_irqsave(&bfad->bfad_lock, flags);
+	offset = iocmd->offset;
 	iocmd->status = bfa_ioc_debug_fwcore(&bfad->bfa.ioc, iocmd_bufptr,
-				(u32 *)&iocmd->offset, &iocmd->bufsz);
+				&offset, &iocmd->bufsz);
+	iocmd->offset = offset;
 	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
 out:
 	return 0;
@@ -2633,12 +2592,6 @@ bfad_iocmd_handler(struct bfad_s *bfad, unsigned int cmd, void *iocmd,
 	case IOCMD_FLASH_DISABLE_OPTROM:
 		rc = bfad_iocmd_ablk_optrom(bfad, cmd, iocmd);
 		break;
-	case IOCMD_FAA_ENABLE:
-		rc = bfad_iocmd_faa_enable(bfad, iocmd);
-		break;
-	case IOCMD_FAA_DISABLE:
-		rc = bfad_iocmd_faa_disable(bfad, iocmd);
-		break;
 	case IOCMD_FAA_QUERY:
 		rc = bfad_iocmd_faa_query(bfad, iocmd);
 		break;
@@ -2809,9 +2762,16 @@ bfad_im_bsg_vendor_request(struct fc_bsg_job *job)
 	struct bfad_im_port_s *im_port =
 			(struct bfad_im_port_s *) job->shost->hostdata[0];
 	struct bfad_s *bfad = im_port->bfad;
+	struct request_queue *request_q = job->req->q;
 	void *payload_kbuf;
 	int rc = -EINVAL;
 
+	/*
+	 * Set the BSG device request_queue size to 256 to support
+	 * payloads larger than 512*1024K bytes.
+	 */
+	blk_queue_max_segments(request_q, 256);
+
 	/* Allocate a temp buffer to hold the passed in user space command */
 	payload_kbuf = kzalloc(job->request_payload.payload_len, GFP_KERNEL);
 	if (!payload_kbuf) {
diff --git a/drivers/scsi/bfa/bfad_bsg.h b/drivers/scsi/bfa/bfad_bsg.h
index e859adb9aa9e..17ad67283130 100644
--- a/drivers/scsi/bfa/bfad_bsg.h
+++ b/drivers/scsi/bfa/bfad_bsg.h
@@ -83,8 +83,6 @@ enum {
 	IOCMD_PORT_CFG_MODE,
 	IOCMD_FLASH_ENABLE_OPTROM,
 	IOCMD_FLASH_DISABLE_OPTROM,
-	IOCMD_FAA_ENABLE,
-	IOCMD_FAA_DISABLE,
 	IOCMD_FAA_QUERY,
 	IOCMD_CEE_GET_ATTR,
 	IOCMD_CEE_GET_STATS,
diff --git a/drivers/scsi/bfa/bfad_drv.h b/drivers/scsi/bfa/bfad_drv.h
index dc5b9d99c450..7f74f1d19124 100644
--- a/drivers/scsi/bfa/bfad_drv.h
+++ b/drivers/scsi/bfa/bfad_drv.h
@@ -56,7 +56,7 @@
 #ifdef BFA_DRIVER_VERSION
 #define BFAD_DRIVER_VERSION    BFA_DRIVER_VERSION
 #else
-#define BFAD_DRIVER_VERSION    "3.0.2.2"
+#define BFAD_DRIVER_VERSION    "3.0.23.0"
 #endif
 
 #define BFAD_PROTO_NAME FCPI_NAME
diff --git a/drivers/scsi/bfa/bfi_ms.h b/drivers/scsi/bfa/bfi_ms.h
index 0d9f1fb50db0..d4220e13cafa 100644
--- a/drivers/scsi/bfa/bfi_ms.h
+++ b/drivers/scsi/bfa/bfi_ms.h
@@ -28,17 +28,15 @@ enum bfi_iocfc_h2i_msgs {
 	BFI_IOCFC_H2I_CFG_REQ		= 1,
 	BFI_IOCFC_H2I_SET_INTR_REQ	= 2,
 	BFI_IOCFC_H2I_UPDATEQ_REQ	= 3,
-	BFI_IOCFC_H2I_FAA_ENABLE_REQ	= 4,
-	BFI_IOCFC_H2I_FAA_DISABLE_REQ	= 5,
-	BFI_IOCFC_H2I_FAA_QUERY_REQ	= 6,
+	BFI_IOCFC_H2I_FAA_QUERY_REQ	= 4,
+	BFI_IOCFC_H2I_ADDR_REQ		= 5,
 };
 
 enum bfi_iocfc_i2h_msgs {
 	BFI_IOCFC_I2H_CFG_REPLY		= BFA_I2HM(1),
 	BFI_IOCFC_I2H_UPDATEQ_RSP	= BFA_I2HM(3),
-	BFI_IOCFC_I2H_FAA_ENABLE_RSP	= BFA_I2HM(4),
-	BFI_IOCFC_I2H_FAA_DISABLE_RSP	= BFA_I2HM(5),
-	BFI_IOCFC_I2H_FAA_QUERY_RSP	= BFA_I2HM(6),
+	BFI_IOCFC_I2H_FAA_QUERY_RSP	= BFA_I2HM(4),
+	BFI_IOCFC_I2H_ADDR_MSG		= BFA_I2HM(5),
 };
 
 struct bfi_iocfc_cfg_s {
@@ -184,6 +182,13 @@ struct bfi_faa_en_dis_s {
 	struct bfi_mhdr_s mh;	/* common msg header    */
 };
 
+struct bfi_faa_addr_msg_s {
+	struct  bfi_mhdr_s mh;	/* common msg header	*/
+	u8	rsvd[4];
+	wwn_t	pwwn;		/* Fabric acquired PWWN	*/
+	wwn_t	nwwn;		/* Fabric acquired PWWN	*/
+};
+
 /*
  * BFI_IOCFC_H2I_FAA_QUERY_REQ message
  */
diff --git a/drivers/scsi/bfa/bfi_reg.h b/drivers/scsi/bfa/bfi_reg.h
index d892064b64a8..ed5f159e1867 100644
--- a/drivers/scsi/bfa/bfi_reg.h
+++ b/drivers/scsi/bfa/bfi_reg.h
@@ -335,11 +335,17 @@ enum {
 #define __PMM_1T_PNDB_P			0x00000002
 #define CT2_PMM_1T_CONTROL_REG_P1	0x00023c1c
 #define CT2_WGN_STATUS			0x00014990
+#define __A2T_AHB_LOAD			0x00000800
 #define __WGN_READY			0x00000400
 #define __GLBL_PF_VF_CFG_RDY		0x00000200
+#define CT2_NFC_CSR_CLR_REG		0x00027420
 #define CT2_NFC_CSR_SET_REG		0x00027424
 #define __HALT_NFC_CONTROLLER		0x00000002
 #define __NFC_CONTROLLER_HALTED		0x00001000
+#define CT2_RSC_GPR15_REG		0x0002765c
+#define CT2_CSI_FW_CTL_REG		0x00027080
+#define CT2_CSI_FW_CTL_SET_REG		0x00027088
+#define __RESET_AND_START_SCLK_LCLK_PLLS 0x00010000
 
 #define CT2_CSI_MAC0_CONTROL_REG	0x000270d0
 #define __CSI_MAC_RESET			0x00000010
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index abd72a01856d..c1c6a92a0b98 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -439,13 +439,13 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 	fr->fr_dev = lport;
 
 	bg = &bnx2fc_global;
-	spin_lock_bh(&bg->fcoe_rx_list.lock);
+	spin_lock(&bg->fcoe_rx_list.lock);
 
 	__skb_queue_tail(&bg->fcoe_rx_list, skb);
 	if (bg->fcoe_rx_list.qlen == 1)
 		wake_up_process(bg->thread);
 
-	spin_unlock_bh(&bg->fcoe_rx_list.lock);
+	spin_unlock(&bg->fcoe_rx_list.lock);
 
 	return 0;
 err:
diff --git a/drivers/scsi/dtc.c b/drivers/scsi/dtc.c
index c2677ba29c74..4b11bb04f5c4 100644
--- a/drivers/scsi/dtc.c
+++ b/drivers/scsi/dtc.c
@@ -72,7 +72,6 @@
 #endif
 
 
-#include <asm/system.h>
 #include <linux/module.h>
 #include <linux/signal.h>
 #include <linux/blkdev.h>
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index ae7d15c44e2a..335e85192807 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1436,7 +1436,7 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev,
 		goto err;
 
 	fps = &per_cpu(fcoe_percpu, cpu);
-	spin_lock_bh(&fps->fcoe_rx_list.lock);
+	spin_lock(&fps->fcoe_rx_list.lock);
 	if (unlikely(!fps->thread)) {
 		/*
 		 * The targeted CPU is not ready, let's target
@@ -1447,12 +1447,12 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev,
 				"ready for incoming skb- using first online "
 				"CPU.\n");
 
-		spin_unlock_bh(&fps->fcoe_rx_list.lock);
+		spin_unlock(&fps->fcoe_rx_list.lock);
 		cpu = cpumask_first(cpu_online_mask);
 		fps = &per_cpu(fcoe_percpu, cpu);
-		spin_lock_bh(&fps->fcoe_rx_list.lock);
+		spin_lock(&fps->fcoe_rx_list.lock);
 		if (!fps->thread) {
-			spin_unlock_bh(&fps->fcoe_rx_list.lock);
+			spin_unlock(&fps->fcoe_rx_list.lock);
 			goto err;
 		}
 	}
@@ -1463,24 +1463,17 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev,
 	 * so we're free to queue skbs into it's queue.
 	 */
 
-	/* If this is a SCSI-FCP frame, and this is already executing on the
-	 * correct CPU, and the queue for this CPU is empty, then go ahead
-	 * and process the frame directly in the softirq context.
-	 * This lets us process completions without context switching from the
-	 * NET_RX softirq, to our receive processing thread, and then back to
-	 * BLOCK softirq context.
+	/*
+	 * Note: We used to have a set of conditions under which we would
+	 * call fcoe_recv_frame directly, rather than queuing to the rx list
+	 * as it could save a few cycles, but doing so is prohibited, as
+	 * fcoe_recv_frame has several paths that may sleep, which is forbidden
+	 * in softirq context.
 	 */
-	if (fh->fh_type == FC_TYPE_FCP &&
-	    cpu == smp_processor_id() &&
-	    skb_queue_empty(&fps->fcoe_rx_list)) {
-		spin_unlock_bh(&fps->fcoe_rx_list.lock);
-		fcoe_recv_frame(skb);
-	} else {
-		__skb_queue_tail(&fps->fcoe_rx_list, skb);
-		if (fps->fcoe_rx_list.qlen == 1)
-			wake_up_process(fps->thread);
-		spin_unlock_bh(&fps->fcoe_rx_list.lock);
-	}
+	__skb_queue_tail(&fps->fcoe_rx_list, skb);
+	if (fps->thread->state == TASK_INTERRUPTIBLE)
+		wake_up_process(fps->thread);
+	spin_unlock(&fps->fcoe_rx_list.lock);
 
 	return 0;
 err:
@@ -1797,23 +1790,29 @@ static int fcoe_percpu_receive_thread(void *arg)
 {
 	struct fcoe_percpu_s *p = arg;
 	struct sk_buff *skb;
+	struct sk_buff_head tmp;
+
+	skb_queue_head_init(&tmp);
 
 	set_user_nice(current, -20);
 
 	while (!kthread_should_stop()) {
 
 		spin_lock_bh(&p->fcoe_rx_list.lock);
-		while ((skb = __skb_dequeue(&p->fcoe_rx_list)) == NULL) {
+		skb_queue_splice_init(&p->fcoe_rx_list, &tmp);
+		spin_unlock_bh(&p->fcoe_rx_list.lock);
+
+		while ((skb = __skb_dequeue(&tmp)) != NULL)
+			fcoe_recv_frame(skb);
+
+		spin_lock_bh(&p->fcoe_rx_list.lock);
+		if (!skb_queue_len(&p->fcoe_rx_list)) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			spin_unlock_bh(&p->fcoe_rx_list.lock);
 			schedule();
 			set_current_state(TASK_RUNNING);
-			if (kthread_should_stop())
-				return 0;
-			spin_lock_bh(&p->fcoe_rx_list.lock);
-		}
-		spin_unlock_bh(&p->fcoe_rx_list.lock);
-		fcoe_recv_frame(skb);
+		} else
+			spin_unlock_bh(&p->fcoe_rx_list.lock);
 	}
 	return 0;
 }
@@ -2187,8 +2186,12 @@ static int fcoe_create(struct net_device *netdev, enum fip_state fip_mode)
 	/* start FIP Discovery and FLOGI */
 	lport->boot_time = jiffies;
 	fc_fabric_login(lport);
-	if (!fcoe_link_ok(lport))
+	if (!fcoe_link_ok(lport)) {
+		rtnl_unlock();
 		fcoe_ctlr_link_up(&fcoe->ctlr);
+		mutex_unlock(&fcoe_config_mutex);
+		return rc;
+	}
 
 out_nodev:
 	rtnl_unlock();
@@ -2261,31 +2264,14 @@ static int fcoe_link_ok(struct fc_lport *lport)
 static void fcoe_percpu_clean(struct fc_lport *lport)
 {
 	struct fcoe_percpu_s *pp;
-	struct fcoe_rcv_info *fr;
-	struct sk_buff_head *list;
-	struct sk_buff *skb, *next;
-	struct sk_buff *head;
+	struct sk_buff *skb;
 	unsigned int cpu;
 
 	for_each_possible_cpu(cpu) {
 		pp = &per_cpu(fcoe_percpu, cpu);
-		spin_lock_bh(&pp->fcoe_rx_list.lock);
-		list = &pp->fcoe_rx_list;
-		head = list->next;
-		for (skb = head; skb != (struct sk_buff *)list;
-		     skb = next) {
-			next = skb->next;
-			fr = fcoe_dev_from_skb(skb);
-			if (fr->fr_dev == lport) {
-				__skb_unlink(skb, list);
-				kfree_skb(skb);
-			}
-		}
 
-		if (!pp->thread || !cpu_online(cpu)) {
-			spin_unlock_bh(&pp->fcoe_rx_list.lock);
+		if (!pp->thread || !cpu_online(cpu))
 			continue;
-		}
 
 		skb = dev_alloc_skb(0);
 		if (!skb) {
@@ -2294,6 +2280,7 @@ static void fcoe_percpu_clean(struct fc_lport *lport)
 		}
 		skb->destructor = fcoe_percpu_flush_done;
 
+		spin_lock_bh(&pp->fcoe_rx_list.lock);
 		__skb_queue_tail(&pp->fcoe_rx_list, skb);
 		if (pp->fcoe_rx_list.qlen == 1)
 			wake_up_process(pp->thread);
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index e7522dcc296e..249a106888d9 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -242,7 +242,7 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip)
 		printk(KERN_INFO "libfcoe: host%d: FIP selected "
 		       "Fibre-Channel Forwarder MAC %pM\n",
 		       fip->lp->host->host_no, sel->fcf_mac);
-		memcpy(fip->dest_addr, sel->fcf_mac, ETH_ALEN);
+		memcpy(fip->dest_addr, sel->fcoe_mac, ETH_ALEN);
 		fip->map_dest = 0;
 	}
 unlock:
@@ -824,6 +824,7 @@ static int fcoe_ctlr_parse_adv(struct fcoe_ctlr *fip,
 			memcpy(fcf->fcf_mac,
 			       ((struct fip_mac_desc *)desc)->fd_mac,
 			       ETH_ALEN);
+			memcpy(fcf->fcoe_mac, fcf->fcf_mac, ETH_ALEN);
 			if (!is_valid_ether_addr(fcf->fcf_mac)) {
 				LIBFCOE_FIP_DBG(fip,
 					"Invalid MAC addr %pM in FIP adv\n",
@@ -1013,6 +1014,7 @@ static void fcoe_ctlr_recv_els(struct fcoe_ctlr *fip, struct sk_buff *skb)
 	struct fip_desc *desc;
 	struct fip_encaps *els;
 	struct fcoe_dev_stats *stats;
+	struct fcoe_fcf *sel;
 	enum fip_desc_type els_dtype = 0;
 	u8 els_op;
 	u8 sub;
@@ -1040,7 +1042,8 @@ static void fcoe_ctlr_recv_els(struct fcoe_ctlr *fip, struct sk_buff *skb)
 			goto drop;
 		/* Drop ELS if there are duplicate critical descriptors */
 		if (desc->fip_dtype < 32) {
-			if (desc_mask & 1U << desc->fip_dtype) {
+			if ((desc->fip_dtype != FIP_DT_MAC) &&
+			    (desc_mask & 1U << desc->fip_dtype)) {
 				LIBFCOE_FIP_DBG(fip, "Duplicate Critical "
 						"Descriptors in FIP ELS\n");
 				goto drop;
@@ -1049,17 +1052,32 @@ static void fcoe_ctlr_recv_els(struct fcoe_ctlr *fip, struct sk_buff *skb)
 		}
 		switch (desc->fip_dtype) {
 		case FIP_DT_MAC:
+			sel = fip->sel_fcf;
 			if (desc_cnt == 1) {
 				LIBFCOE_FIP_DBG(fip, "FIP descriptors "
 						"received out of order\n");
 				goto drop;
 			}
+			/*
+			 * Some switch implementations send two MAC descriptors,
+			 * with first MAC(granted_mac) being the FPMA, and the
+			 * second one(fcoe_mac) is used as destination address
+			 * for sending/receiving FCoE packets. FIP traffic is
+			 * sent using fip_mac. For regular switches, both
+			 * fip_mac and fcoe_mac would be the same.
+			 */
+			if (desc_cnt == 2)
+				memcpy(granted_mac,
+				       ((struct fip_mac_desc *)desc)->fd_mac,
+				       ETH_ALEN);
 
 			if (dlen != sizeof(struct fip_mac_desc))
 				goto len_err;
-			memcpy(granted_mac,
-			       ((struct fip_mac_desc *)desc)->fd_mac,
-			       ETH_ALEN);
+
+			if ((desc_cnt == 3) && (sel))
+				memcpy(sel->fcoe_mac,
+				       ((struct fip_mac_desc *)desc)->fd_mac,
+				       ETH_ALEN);
 			break;
 		case FIP_DT_FLOGI:
 		case FIP_DT_FDISC:
@@ -1273,11 +1291,6 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 		 * No Vx_Port description. Clear all NPIV ports,
 		 * followed by physical port
 		 */
-		mutex_lock(&lport->lp_mutex);
-		list_for_each_entry(vn_port, &lport->vports, list)
-			fc_lport_reset(vn_port);
-		mutex_unlock(&lport->lp_mutex);
-
 		mutex_lock(&fip->ctlr_mutex);
 		per_cpu_ptr(lport->dev_stats,
 			    get_cpu())->VLinkFailureCount++;
@@ -1285,6 +1298,11 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 		fcoe_ctlr_reset(fip);
 		mutex_unlock(&fip->ctlr_mutex);
 
+		mutex_lock(&lport->lp_mutex);
+		list_for_each_entry(vn_port, &lport->vports, list)
+			fc_lport_reset(vn_port);
+		mutex_unlock(&lport->lp_mutex);
+
 		fc_lport_reset(fip->lp);
 		fcoe_ctlr_solicit(fip, NULL);
 	} else {
diff --git a/drivers/scsi/fd_mcs.c b/drivers/scsi/fd_mcs.c
index a2c6135d337e..53bfcaa86f09 100644
--- a/drivers/scsi/fd_mcs.c
+++ b/drivers/scsi/fd_mcs.c
@@ -93,7 +93,6 @@
 #include <linux/mca-legacy.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "scsi.h"
 #include <scsi/scsi_host.h>
diff --git a/drivers/scsi/fdomain.c b/drivers/scsi/fdomain.c
index 643f6d500fe7..1a2a1e5824e3 100644
--- a/drivers/scsi/fdomain.c
+++ b/drivers/scsi/fdomain.c
@@ -282,7 +282,6 @@
 #include <linux/slab.h>
 #include <scsi/scsicam.h>
 
-#include <asm/system.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c
index 81182badfeb1..1a5954f0915a 100644
--- a/drivers/scsi/g_NCR5380.c
+++ b/drivers/scsi/g_NCR5380.c
@@ -100,7 +100,6 @@
 #undef NCR5380_STAT_LIMIT
 #endif
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <linux/signal.h>
 #include <linux/blkdev.h>
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index d42ec921de46..5d72274c507f 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -129,7 +129,6 @@
 #include <linux/reboot.h>
 
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <linux/spinlock.h>
diff --git a/drivers/scsi/ibmmca.c b/drivers/scsi/ibmmca.c
index 67fc8ffd52e6..cd09132d5d7d 100644
--- a/drivers/scsi/ibmmca.c
+++ b/drivers/scsi/ibmmca.c
@@ -32,7 +32,6 @@
 #include <linux/spinlock.h>
 #include <linux/init.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include "scsi.h"
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index bdfa223a7dbb..134a0ae85bb7 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -4890,11 +4890,8 @@ static struct vio_driver ibmvfc_driver = {
 	.probe = ibmvfc_probe,
 	.remove = ibmvfc_remove,
 	.get_desired_dma = ibmvfc_get_desired_dma,
-	.driver = {
-		.name = IBMVFC_NAME,
-		.owner = THIS_MODULE,
-		.pm = &ibmvfc_pm_ops,
-	}
+	.name = IBMVFC_NAME,
+	.pm = &ibmvfc_pm_ops,
 };
 
 static struct fc_function_template ibmvfc_transport_functions = {
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index e984951baeb6..3a6c4742951e 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -2061,11 +2061,8 @@ static struct vio_driver ibmvscsi_driver = {
 	.probe = ibmvscsi_probe,
 	.remove = ibmvscsi_remove,
 	.get_desired_dma = ibmvscsi_get_desired_dma,
-	.driver = {
-		.name = "ibmvscsi",
-		.owner = THIS_MODULE,
-		.pm = &ibmvscsi_pm_ops,
-	}
+	.name = "ibmvscsi",
+	.pm = &ibmvscsi_pm_ops,
 };
 
 static struct srp_function_template ibmvscsi_transport_functions = {
diff --git a/drivers/scsi/ibmvscsi/ibmvstgt.c b/drivers/scsi/ibmvscsi/ibmvstgt.c
index 2256babe0474..aa7ed81e9237 100644
--- a/drivers/scsi/ibmvscsi/ibmvstgt.c
+++ b/drivers/scsi/ibmvscsi/ibmvstgt.c
@@ -918,10 +918,7 @@ static struct vio_driver ibmvstgt_driver = {
 	.id_table = ibmvstgt_device_table,
 	.probe = ibmvstgt_probe,
 	.remove = ibmvstgt_remove,
-	.driver = {
-		.name = "ibmvscsis",
-		.owner = THIS_MODULE,
-	}
+	.name = "ibmvscsis",
 };
 
 static int get_system_info(void)
diff --git a/drivers/scsi/in2000.c b/drivers/scsi/in2000.c
index 112f1bec7756..deb5b6d8398e 100644
--- a/drivers/scsi/in2000.c
+++ b/drivers/scsi/in2000.c
@@ -123,7 +123,6 @@
 #include <linux/stat.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include "scsi.h"
 #include <scsi/scsi_host.h>
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index cdfe5a16de2a..e002cd466e9a 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -104,7 +104,9 @@ static DEFINE_SPINLOCK(ipr_driver_lock);
 static const struct ipr_chip_cfg_t ipr_chip_cfg[] = {
 	{ /* Gemstone, Citrine, Obsidian, and Obsidian-E */
 		.mailbox = 0x0042C,
+		.max_cmds = 100,
 		.cache_line_size = 0x20,
+		.clear_isr = 1,
 		{
 			.set_interrupt_mask_reg = 0x0022C,
 			.clr_interrupt_mask_reg = 0x00230,
@@ -126,7 +128,9 @@ static const struct ipr_chip_cfg_t ipr_chip_cfg[] = {
 	},
 	{ /* Snipe and Scamp */
 		.mailbox = 0x0052C,
+		.max_cmds = 100,
 		.cache_line_size = 0x20,
+		.clear_isr = 1,
 		{
 			.set_interrupt_mask_reg = 0x00288,
 			.clr_interrupt_mask_reg = 0x0028C,
@@ -148,7 +152,9 @@ static const struct ipr_chip_cfg_t ipr_chip_cfg[] = {
 	},
 	{ /* CRoC */
 		.mailbox = 0x00044,
+		.max_cmds = 1000,
 		.cache_line_size = 0x20,
+		.clear_isr = 0,
 		{
 			.set_interrupt_mask_reg = 0x00010,
 			.clr_interrupt_mask_reg = 0x00018,
@@ -847,8 +853,6 @@ static void ipr_do_req(struct ipr_cmnd *ipr_cmd,
 
 	ipr_trc_hook(ipr_cmd, IPR_TRACE_START, 0);
 
-	mb();
-
 	ipr_send_command(ipr_cmd);
 }
 
@@ -982,8 +986,6 @@ static void ipr_send_hcam(struct ipr_ioa_cfg *ioa_cfg, u8 type,
 
 		ipr_trc_hook(ipr_cmd, IPR_TRACE_START, IPR_IOA_RES_ADDR);
 
-		mb();
-
 		ipr_send_command(ipr_cmd);
 	} else {
 		list_add_tail(&hostrcb->queue, &ioa_cfg->hostrcb_free_q);
@@ -4339,8 +4341,7 @@ static struct ipr_resource_entry *ipr_find_starget(struct scsi_target *starget)
 
 	list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
 		if ((res->bus == starget->channel) &&
-		    (res->target == starget->id) &&
-		    (res->lun == 0)) {
+		    (res->target == starget->id)) {
 			return res;
 		}
 	}
@@ -4414,12 +4415,14 @@ static void ipr_target_destroy(struct scsi_target *starget)
 	struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *) shost->hostdata;
 
 	if (ioa_cfg->sis64) {
-		if (starget->channel == IPR_ARRAY_VIRTUAL_BUS)
-			clear_bit(starget->id, ioa_cfg->array_ids);
-		else if (starget->channel == IPR_VSET_VIRTUAL_BUS)
-			clear_bit(starget->id, ioa_cfg->vset_ids);
-		else if (starget->channel == 0)
-			clear_bit(starget->id, ioa_cfg->target_ids);
+		if (!ipr_find_starget(starget)) {
+			if (starget->channel == IPR_ARRAY_VIRTUAL_BUS)
+				clear_bit(starget->id, ioa_cfg->array_ids);
+			else if (starget->channel == IPR_VSET_VIRTUAL_BUS)
+				clear_bit(starget->id, ioa_cfg->vset_ids);
+			else if (starget->channel == 0)
+				clear_bit(starget->id, ioa_cfg->target_ids);
+		}
 	}
 
 	if (sata_port) {
@@ -5048,12 +5051,14 @@ static irqreturn_t ipr_handle_other_interrupt(struct ipr_ioa_cfg *ioa_cfg,
 		del_timer(&ioa_cfg->reset_cmd->timer);
 		ipr_reset_ioa_job(ioa_cfg->reset_cmd);
 	} else if ((int_reg & IPR_PCII_HRRQ_UPDATED) == int_reg) {
-		if (ipr_debug && printk_ratelimit())
-			dev_err(&ioa_cfg->pdev->dev,
-				"Spurious interrupt detected. 0x%08X\n", int_reg);
-		writel(IPR_PCII_HRRQ_UPDATED, ioa_cfg->regs.clr_interrupt_reg32);
-		int_reg = readl(ioa_cfg->regs.sense_interrupt_reg32);
-		return IRQ_NONE;
+		if (ioa_cfg->clear_isr) {
+			if (ipr_debug && printk_ratelimit())
+				dev_err(&ioa_cfg->pdev->dev,
+					"Spurious interrupt detected. 0x%08X\n", int_reg);
+			writel(IPR_PCII_HRRQ_UPDATED, ioa_cfg->regs.clr_interrupt_reg32);
+			int_reg = readl(ioa_cfg->regs.sense_interrupt_reg32);
+			return IRQ_NONE;
+		}
 	} else {
 		if (int_reg & IPR_PCII_IOA_UNIT_CHECKED)
 			ioa_cfg->ioa_unit_checked = 1;
@@ -5153,6 +5158,9 @@ static irqreturn_t ipr_isr(int irq, void *devp)
 			}
 		}
 
+		if (ipr_cmd && !ioa_cfg->clear_isr)
+			break;
+
 		if (ipr_cmd != NULL) {
 			/* Clear the PCI interrupt */
 			num_hrrq = 0;
@@ -5854,14 +5862,12 @@ static int ipr_queuecommand_lck(struct scsi_cmnd *scsi_cmd,
 			rc = ipr_build_ioadl(ioa_cfg, ipr_cmd);
 	}
 
-	if (likely(rc == 0)) {
-		mb();
-		ipr_send_command(ipr_cmd);
-	} else {
-		 list_move_tail(&ipr_cmd->queue, &ioa_cfg->free_q);
-		 return SCSI_MLQUEUE_HOST_BUSY;
+	if (unlikely(rc != 0)) {
+		list_move_tail(&ipr_cmd->queue, &ioa_cfg->free_q);
+		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
+	ipr_send_command(ipr_cmd);
 	return 0;
 }
 
@@ -6239,8 +6245,6 @@ static unsigned int ipr_qc_issue(struct ata_queued_cmd *qc)
 		return AC_ERR_INVALID;
 	}
 
-	mb();
-
 	ipr_send_command(ipr_cmd);
 
 	return 0;
@@ -8277,6 +8281,10 @@ static void ipr_free_cmd_blks(struct ipr_ioa_cfg *ioa_cfg)
 	if (ioa_cfg->ipr_cmd_pool)
 		pci_pool_destroy (ioa_cfg->ipr_cmd_pool);
 
+	kfree(ioa_cfg->ipr_cmnd_list);
+	kfree(ioa_cfg->ipr_cmnd_list_dma);
+	ioa_cfg->ipr_cmnd_list = NULL;
+	ioa_cfg->ipr_cmnd_list_dma = NULL;
 	ioa_cfg->ipr_cmd_pool = NULL;
 }
 
@@ -8352,11 +8360,19 @@ static int __devinit ipr_alloc_cmd_blks(struct ipr_ioa_cfg *ioa_cfg)
 	int i;
 
 	ioa_cfg->ipr_cmd_pool = pci_pool_create (IPR_NAME, ioa_cfg->pdev,
-						 sizeof(struct ipr_cmnd), 16, 0);
+						 sizeof(struct ipr_cmnd), 512, 0);
 
 	if (!ioa_cfg->ipr_cmd_pool)
 		return -ENOMEM;
 
+	ioa_cfg->ipr_cmnd_list = kcalloc(IPR_NUM_CMD_BLKS, sizeof(struct ipr_cmnd *), GFP_KERNEL);
+	ioa_cfg->ipr_cmnd_list_dma = kcalloc(IPR_NUM_CMD_BLKS, sizeof(dma_addr_t), GFP_KERNEL);
+
+	if (!ioa_cfg->ipr_cmnd_list || !ioa_cfg->ipr_cmnd_list_dma) {
+		ipr_free_cmd_blks(ioa_cfg);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < IPR_NUM_CMD_BLKS; i++) {
 		ipr_cmd = pci_pool_alloc (ioa_cfg->ipr_cmd_pool, GFP_KERNEL, &dma_addr);
 
@@ -8584,6 +8600,7 @@ static void __devinit ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
 	host->max_channel = IPR_MAX_BUS_TO_SCAN;
 	host->unique_id = host->host_no;
 	host->max_cmd_len = IPR_MAX_CDB_LEN;
+	host->can_queue = ioa_cfg->max_cmds;
 	pci_set_drvdata(pdev, ioa_cfg);
 
 	p = &ioa_cfg->chip_cfg->regs;
@@ -8768,6 +8785,8 @@ static int __devinit ipr_probe_ioa(struct pci_dev *pdev,
 	/* set SIS 32 or SIS 64 */
 	ioa_cfg->sis64 = ioa_cfg->ipr_chip->sis_type == IPR_SIS64 ? 1 : 0;
 	ioa_cfg->chip_cfg = ioa_cfg->ipr_chip->cfg;
+	ioa_cfg->clear_isr = ioa_cfg->chip_cfg->clear_isr;
+	ioa_cfg->max_cmds = ioa_cfg->chip_cfg->max_cmds;
 
 	if (ipr_transop_timeout)
 		ioa_cfg->transop_timeout = ipr_transop_timeout;
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index f94eaee2ff16..153b8bd91d1e 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -38,8 +38,8 @@
 /*
  * Literals
  */
-#define IPR_DRIVER_VERSION "2.5.2"
-#define IPR_DRIVER_DATE "(April 27, 2011)"
+#define IPR_DRIVER_VERSION "2.5.3"
+#define IPR_DRIVER_DATE "(March 10, 2012)"
 
 /*
  * IPR_MAX_CMD_PER_LUN: This defines the maximum number of outstanding
@@ -53,7 +53,7 @@
  * IPR_NUM_BASE_CMD_BLKS: This defines the maximum number of
  *	ops the mid-layer can send to the adapter.
  */
-#define IPR_NUM_BASE_CMD_BLKS				100
+#define IPR_NUM_BASE_CMD_BLKS			(ioa_cfg->max_cmds)
 
 #define PCI_DEVICE_ID_IBM_OBSIDIAN_E	0x0339
 
@@ -153,7 +153,7 @@
 #define IPR_NUM_INTERNAL_CMD_BLKS	(IPR_NUM_HCAMS + \
                                      ((IPR_NUM_RESET_RELOAD_RETRIES + 1) * 2) + 4)
 
-#define IPR_MAX_COMMANDS		IPR_NUM_BASE_CMD_BLKS
+#define IPR_MAX_COMMANDS		100
 #define IPR_NUM_CMD_BLKS		(IPR_NUM_BASE_CMD_BLKS + \
 						IPR_NUM_INTERNAL_CMD_BLKS)
 
@@ -1305,7 +1305,9 @@ struct ipr_interrupts {
 
 struct ipr_chip_cfg_t {
 	u32 mailbox;
+	u16 max_cmds;
 	u8 cache_line_size;
+	u8 clear_isr;
 	struct ipr_interrupt_offsets regs;
 };
 
@@ -1388,6 +1390,7 @@ struct ipr_ioa_cfg {
 	u8 sis64:1;
 	u8 dump_timeout:1;
 	u8 cfg_locked:1;
+	u8 clear_isr:1;
 
 	u8 revid;
 
@@ -1501,8 +1504,9 @@ struct ipr_ioa_cfg {
 	struct ata_host ata_host;
 	char ipr_cmd_label[8];
 #define IPR_CMD_LABEL		"ipr_cmd"
-	struct ipr_cmnd *ipr_cmnd_list[IPR_NUM_CMD_BLKS];
-	dma_addr_t ipr_cmnd_list_dma[IPR_NUM_CMD_BLKS];
+	u32 max_cmds;
+	struct ipr_cmnd **ipr_cmnd_list;
+	dma_addr_t *ipr_cmnd_list_dma;
 }; /* struct ipr_ioa_cfg */
 
 struct ipr_cmnd {
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 630291f01826..aceffadb21c7 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -2263,7 +2263,18 @@ struct fc_exch_mgr *fc_exch_mgr_alloc(struct fc_lport *lport,
 	mp->class = class;
 	/* adjust em exch xid range for offload */
 	mp->min_xid = min_xid;
-	mp->max_xid = max_xid;
+
+       /* reduce range so per cpu pool fits into PCPU_MIN_UNIT_SIZE pool */
+	pool_exch_range = (PCPU_MIN_UNIT_SIZE - sizeof(*pool)) /
+		sizeof(struct fc_exch *);
+	if ((max_xid - min_xid + 1) / (fc_cpu_mask + 1) > pool_exch_range) {
+		mp->max_xid = pool_exch_range * (fc_cpu_mask + 1) +
+			min_xid - 1;
+	} else {
+		mp->max_xid = max_xid;
+		pool_exch_range = (mp->max_xid - mp->min_xid + 1) /
+			(fc_cpu_mask + 1);
+	}
 
 	mp->ep_pool = mempool_create_slab_pool(2, fc_em_cachep);
 	if (!mp->ep_pool)
@@ -2274,7 +2285,6 @@ struct fc_exch_mgr *fc_exch_mgr_alloc(struct fc_lport *lport,
 	 * divided across all cpus. The exch pointers array memory is
 	 * allocated for exch range per pool.
 	 */
-	pool_exch_range = (mp->max_xid - mp->min_xid + 1) / (fc_cpu_mask + 1);
 	mp->pool_max_index = pool_exch_range - 1;
 
 	/*
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index bd5d31d022d9..ef9560dff295 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -1743,8 +1743,16 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp,
 	mfs = ntohs(flp->fl_csp.sp_bb_data) &
 		FC_SP_BB_DATA_MASK;
 	if (mfs >= FC_SP_MIN_MAX_PAYLOAD &&
-	    mfs < lport->mfs)
+	    mfs <= lport->mfs) {
 		lport->mfs = mfs;
+		fc_host_maxframe_size(lport->host) = mfs;
+	} else {
+		FC_LPORT_DBG(lport, "FLOGI bad mfs:%hu response, "
+			     "lport->mfs:%hu\n", mfs, lport->mfs);
+		fc_lport_error(lport, fp);
+		goto err;
+	}
+
 	csp_flags = ntohs(flp->fl_csp.sp_features);
 	r_a_tov = ntohl(flp->fl_csp.sp_r_a_tov);
 	e_d_tov = ntohl(flp->fl_csp.sp_e_d_tov);
diff --git a/drivers/scsi/lpfc/Makefile b/drivers/scsi/lpfc/Makefile
index 88928f00aa2d..fe5d396aca73 100644
--- a/drivers/scsi/lpfc/Makefile
+++ b/drivers/scsi/lpfc/Makefile
@@ -1,7 +1,7 @@
 #/*******************************************************************
 # * This file is part of the Emulex Linux Device Driver for         *
 # * Fibre Channel Host Bus Adapters.                                *
-# * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
+# * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
 # * EMULEX and SLI are trademarks of Emulex.                        *
 # * www.emulex.com                                                  *
 # *                                                                 *
@@ -22,6 +22,8 @@
 ccflags-$(GCOV) := -fprofile-arcs -ftest-coverage
 ccflags-$(GCOV) += -O0
 
+ccflags-y += -Werror
+
 obj-$(CONFIG_SCSI_LPFC) := lpfc.o
 
 lpfc-objs := lpfc_mem.o lpfc_sli.o lpfc_ct.o lpfc_els.o lpfc_hbadisc.o	\
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 5fc044ff656e..3a1ffdd6d831 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -840,6 +840,8 @@ struct lpfc_hba {
 	struct dentry *debug_dumpData;   /* BlockGuard BPL */
 	struct dentry *debug_dumpDif;    /* BlockGuard BPL */
 	struct dentry *debug_InjErrLBA;  /* LBA to inject errors at */
+	struct dentry *debug_InjErrNPortID;  /* NPortID to inject errors at */
+	struct dentry *debug_InjErrWWPN;  /* WWPN to inject errors at */
 	struct dentry *debug_writeGuard; /* inject write guard_tag errors */
 	struct dentry *debug_writeApp;   /* inject write app_tag errors */
 	struct dentry *debug_writeRef;   /* inject write ref_tag errors */
@@ -854,6 +856,8 @@ struct lpfc_hba {
 	uint32_t lpfc_injerr_rgrd_cnt;
 	uint32_t lpfc_injerr_rapp_cnt;
 	uint32_t lpfc_injerr_rref_cnt;
+	uint32_t lpfc_injerr_nportid;
+	struct lpfc_name lpfc_injerr_wwpn;
 	sector_t lpfc_injerr_lba;
 #define LPFC_INJERR_LBA_OFF	(sector_t)(-1)
 
@@ -908,6 +912,8 @@ struct lpfc_hba {
 	atomic_t fast_event_count;
 	uint32_t fcoe_eventtag;
 	uint32_t fcoe_eventtag_at_fcf_scan;
+	uint32_t fcoe_cvl_eventtag;
+	uint32_t fcoe_cvl_eventtag_attn;
 	struct lpfc_fcf fcf;
 	uint8_t fc_map[3];
 	uint8_t valid_vlan;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 296ad5bc4240..5eb2bc116183 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -2575,7 +2575,7 @@ LPFC_VPORT_ATTR_HEX_RW(log_verbose, 0x0, 0x0, 0xffffffff,
 # lpfc_enable_da_id: This turns on the DA_ID CT command that deregisters
 # objects that have been registered with the nameserver after login.
 */
-LPFC_VPORT_ATTR_R(enable_da_id, 0, 0, 1,
+LPFC_VPORT_ATTR_R(enable_da_id, 1, 0, 1,
 		  "Deregister nameserver objects before LOGO");
 
 /*
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 22e17be04d8a..af04b0d6688d 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2007-2011 Emulex.  All rights reserved.           *
+ * Copyright (C) 2007-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -997,38 +997,41 @@ lpfc_debugfs_dumpDataDif_write(struct file *file, const char __user *buf,
 	return nbytes;
 }
 
-static int
-lpfc_debugfs_dif_err_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t
 lpfc_debugfs_dif_err_read(struct file *file, char __user *buf,
 	size_t nbytes, loff_t *ppos)
 {
 	struct dentry *dent = file->f_dentry;
 	struct lpfc_hba *phba = file->private_data;
-	char cbuf[16];
+	char cbuf[32];
+	uint64_t tmp = 0;
 	int cnt = 0;
 
 	if (dent == phba->debug_writeGuard)
-		cnt = snprintf(cbuf, 16, "%u\n", phba->lpfc_injerr_wgrd_cnt);
+		cnt = snprintf(cbuf, 32, "%u\n", phba->lpfc_injerr_wgrd_cnt);
 	else if (dent == phba->debug_writeApp)
-		cnt = snprintf(cbuf, 16, "%u\n", phba->lpfc_injerr_wapp_cnt);
+		cnt = snprintf(cbuf, 32, "%u\n", phba->lpfc_injerr_wapp_cnt);
 	else if (dent == phba->debug_writeRef)
-		cnt = snprintf(cbuf, 16, "%u\n", phba->lpfc_injerr_wref_cnt);
+		cnt = snprintf(cbuf, 32, "%u\n", phba->lpfc_injerr_wref_cnt);
 	else if (dent == phba->debug_readGuard)
-		cnt = snprintf(cbuf, 16, "%u\n", phba->lpfc_injerr_rgrd_cnt);
+		cnt = snprintf(cbuf, 32, "%u\n", phba->lpfc_injerr_rgrd_cnt);
 	else if (dent == phba->debug_readApp)
-		cnt = snprintf(cbuf, 16, "%u\n", phba->lpfc_injerr_rapp_cnt);
+		cnt = snprintf(cbuf, 32, "%u\n", phba->lpfc_injerr_rapp_cnt);
 	else if (dent == phba->debug_readRef)
-		cnt = snprintf(cbuf, 16, "%u\n", phba->lpfc_injerr_rref_cnt);
-	else if (dent == phba->debug_InjErrLBA)
-		cnt = snprintf(cbuf, 16, "0x%lx\n",
-				 (unsigned long) phba->lpfc_injerr_lba);
-	else
+		cnt = snprintf(cbuf, 32, "%u\n", phba->lpfc_injerr_rref_cnt);
+	else if (dent == phba->debug_InjErrNPortID)
+		cnt = snprintf(cbuf, 32, "0x%06x\n", phba->lpfc_injerr_nportid);
+	else if (dent == phba->debug_InjErrWWPN) {
+		memcpy(&tmp, &phba->lpfc_injerr_wwpn, sizeof(struct lpfc_name));
+		tmp = cpu_to_be64(tmp);
+		cnt = snprintf(cbuf, 32, "0x%016llx\n", tmp);
+	} else if (dent == phba->debug_InjErrLBA) {
+		if (phba->lpfc_injerr_lba == (sector_t)(-1))
+			cnt = snprintf(cbuf, 32, "off\n");
+		else
+			cnt = snprintf(cbuf, 32, "0x%llx\n",
+				 (uint64_t) phba->lpfc_injerr_lba);
+	} else
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 			 "0547 Unknown debugfs error injection entry\n");
 
@@ -1042,7 +1045,7 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 	struct dentry *dent = file->f_dentry;
 	struct lpfc_hba *phba = file->private_data;
 	char dstbuf[32];
-	unsigned long tmp;
+	uint64_t tmp = 0;
 	int size;
 
 	memset(dstbuf, 0, 32);
@@ -1050,7 +1053,12 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 	if (copy_from_user(dstbuf, buf, size))
 		return 0;
 
-	if (strict_strtoul(dstbuf, 0, &tmp))
+	if (dent == phba->debug_InjErrLBA) {
+		if ((buf[0] == 'o') && (buf[1] == 'f') && (buf[2] == 'f'))
+			tmp = (uint64_t)(-1);
+	}
+
+	if ((tmp == 0) && (kstrtoull(dstbuf, 0, &tmp)))
 		return 0;
 
 	if (dent == phba->debug_writeGuard)
@@ -1067,7 +1075,12 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 		phba->lpfc_injerr_rref_cnt = (uint32_t)tmp;
 	else if (dent == phba->debug_InjErrLBA)
 		phba->lpfc_injerr_lba = (sector_t)tmp;
-	else
+	else if (dent == phba->debug_InjErrNPortID)
+		phba->lpfc_injerr_nportid = (uint32_t)(tmp & Mask_DID);
+	else if (dent == phba->debug_InjErrWWPN) {
+		tmp = cpu_to_be64(tmp);
+		memcpy(&phba->lpfc_injerr_wwpn, &tmp, sizeof(struct lpfc_name));
+	} else
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 			 "0548 Unknown debugfs error injection entry\n");
 
@@ -3521,7 +3534,7 @@ static const struct file_operations lpfc_debugfs_op_dumpDif = {
 #undef lpfc_debugfs_op_dif_err
 static const struct file_operations lpfc_debugfs_op_dif_err = {
 	.owner =	THIS_MODULE,
-	.open =		lpfc_debugfs_dif_err_open,
+	.open =		simple_open,
 	.llseek =	lpfc_debugfs_lseek,
 	.read =		lpfc_debugfs_dif_err_read,
 	.write =	lpfc_debugfs_dif_err_write,
@@ -3949,6 +3962,28 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 		}
 		phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
 
+		snprintf(name, sizeof(name), "InjErrNPortID");
+		phba->debug_InjErrNPortID =
+			debugfs_create_file(name, S_IFREG|S_IRUGO|S_IWUSR,
+			phba->hba_debugfs_root,
+			phba, &lpfc_debugfs_op_dif_err);
+		if (!phba->debug_InjErrNPortID) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
+				"0809 Cannot create debugfs InjErrNPortID\n");
+			goto debug_failed;
+		}
+
+		snprintf(name, sizeof(name), "InjErrWWPN");
+		phba->debug_InjErrWWPN =
+			debugfs_create_file(name, S_IFREG|S_IRUGO|S_IWUSR,
+			phba->hba_debugfs_root,
+			phba, &lpfc_debugfs_op_dif_err);
+		if (!phba->debug_InjErrWWPN) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
+				"0810 Cannot create debugfs InjErrWWPN\n");
+			goto debug_failed;
+		}
+
 		snprintf(name, sizeof(name), "writeGuardInjErr");
 		phba->debug_writeGuard =
 			debugfs_create_file(name, S_IFREG|S_IRUGO|S_IWUSR,
@@ -4321,6 +4356,14 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 			debugfs_remove(phba->debug_InjErrLBA); /* InjErrLBA */
 			phba->debug_InjErrLBA = NULL;
 		}
+		if (phba->debug_InjErrNPortID) {	 /* InjErrNPortID */
+			debugfs_remove(phba->debug_InjErrNPortID);
+			phba->debug_InjErrNPortID = NULL;
+		}
+		if (phba->debug_InjErrWWPN) {
+			debugfs_remove(phba->debug_InjErrWWPN); /* InjErrWWPN */
+			phba->debug_InjErrWWPN = NULL;
+		}
 		if (phba->debug_writeGuard) {
 			debugfs_remove(phba->debug_writeGuard); /* writeGuard */
 			phba->debug_writeGuard = NULL;
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 8db2fb3b45ec..3407b39e0a3f 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -925,9 +925,17 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 * due to new FCF discovery
 		 */
 		if ((phba->hba_flag & HBA_FIP_SUPPORT) &&
-		    (phba->fcf.fcf_flag & FCF_DISCOVERY) &&
-		    !((irsp->ulpStatus == IOSTAT_LOCAL_REJECT) &&
-		     (irsp->un.ulpWord[4] == IOERR_SLI_ABORTED))) {
+		    (phba->fcf.fcf_flag & FCF_DISCOVERY)) {
+			if (phba->link_state < LPFC_LINK_UP)
+				goto stop_rr_fcf_flogi;
+			if ((phba->fcoe_cvl_eventtag_attn ==
+			     phba->fcoe_cvl_eventtag) &&
+			    (irsp->ulpStatus == IOSTAT_LOCAL_REJECT) &&
+			    (irsp->un.ulpWord[4] == IOERR_SLI_ABORTED))
+				goto stop_rr_fcf_flogi;
+			else
+				phba->fcoe_cvl_eventtag_attn =
+					phba->fcoe_cvl_eventtag;
 			lpfc_printf_log(phba, KERN_WARNING, LOG_FIP | LOG_ELS,
 					"2611 FLOGI failed on FCF (x%x), "
 					"status:x%x/x%x, tmo:x%x, perform "
@@ -943,6 +951,7 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				goto out;
 		}
 
+stop_rr_fcf_flogi:
 		/* FLOGI failure */
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
 				"2858 FLOGI failure Status:x%x/x%x TMO:x%x\n",
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 343d87ba4df8..b507536dc5b5 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -2843,7 +2843,14 @@ lpfc_mbx_cmpl_reg_vfi(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	struct lpfc_vport *vport = mboxq->vport;
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 
-	if (mboxq->u.mb.mbxStatus) {
+	/*
+	 * VFI not supported for interface type 0, so ignore any mailbox
+	 * error (except VFI in use) and continue with the discovery.
+	 */
+	if (mboxq->u.mb.mbxStatus &&
+	    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+			LPFC_SLI_INTF_IF_TYPE_0) &&
+	    mboxq->u.mb.mbxStatus != MBX_VFI_IN_USE) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_MBOX,
 			 "2018 REG_VFI mbxStatus error x%x "
 			 "HBA state x%x\n",
@@ -5673,14 +5680,13 @@ lpfc_fcf_inuse(struct lpfc_hba *phba)
 				ret = 1;
 				spin_unlock_irq(shost->host_lock);
 				goto out;
-			} else {
+			} else if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+				ret = 1;
 				lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
-					"2624 RPI %x DID %x flg %x still "
-					"logged in\n",
-					ndlp->nlp_rpi, ndlp->nlp_DID,
-					ndlp->nlp_flag);
-				if (ndlp->nlp_flag & NLP_RPI_REGISTERED)
-					ret = 1;
+						"2624 RPI %x DID %x flag %x "
+						"still logged in\n",
+						ndlp->nlp_rpi, ndlp->nlp_DID,
+						ndlp->nlp_flag);
 			}
 		}
 		spin_unlock_irq(shost->host_lock);
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 9e2b9b227e1a..91f09761bd32 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2009 Emulex.  All rights reserved.                *
+ * Copyright (C) 2009-2012 Emulex.  All rights reserved.                *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -338,6 +338,12 @@ struct lpfc_cqe {
 #define CQE_CODE_XRI_ABORTED		0x5
 #define CQE_CODE_RECEIVE_V1		0x9
 
+/*
+ * Define mask value for xri_aborted and wcqe completed CQE extended status.
+ * Currently, extended status is limited to 9 bits (0x0 -> 0x103) .
+ */
+#define WCQE_PARAM_MASK		0x1FF;
+
 /* completion queue entry for wqe completions */
 struct lpfc_wcqe_complete {
 	uint32_t word0;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index b38f99f3be32..9598fdcb08ab 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -2704,16 +2704,14 @@ lpfc_offline_prep(struct lpfc_hba * phba)
 				}
 				spin_lock_irq(shost->host_lock);
 				ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-
+				spin_unlock_irq(shost->host_lock);
 				/*
 				 * Whenever an SLI4 port goes offline, free the
-				 * RPI.  A new RPI when the adapter port comes
-				 * back online.
+				 * RPI. Get a new RPI when the adapter port
+				 * comes back online.
 				 */
 				if (phba->sli_rev == LPFC_SLI_REV4)
 					lpfc_sli4_free_rpi(phba, ndlp->nlp_rpi);
-
-				spin_unlock_irq(shost->host_lock);
 				lpfc_unreg_rpi(vports[i], ndlp);
 			}
 		}
@@ -2786,9 +2784,13 @@ lpfc_scsi_buf_update(struct lpfc_hba *phba)
 
 	spin_lock_irq(&phba->hbalock);
 	spin_lock(&phba->scsi_buf_list_lock);
-	list_for_each_entry_safe(sb, sb_next, &phba->lpfc_scsi_buf_list, list)
+	list_for_each_entry_safe(sb, sb_next, &phba->lpfc_scsi_buf_list, list) {
 		sb->cur_iocbq.sli4_xritag =
 			phba->sli4_hba.xri_ids[sb->cur_iocbq.sli4_lxritag];
+		set_bit(sb->cur_iocbq.sli4_lxritag, phba->sli4_hba.xri_bmask);
+		phba->sli4_hba.max_cfg_param.xri_used++;
+		phba->sli4_hba.xri_count++;
+	}
 	spin_unlock(&phba->scsi_buf_list_lock);
 	spin_unlock_irq(&phba->hbalock);
 	return 0;
@@ -3723,6 +3725,7 @@ lpfc_sli4_async_fip_evt(struct lpfc_hba *phba,
 		break;
 
 	case LPFC_FIP_EVENT_TYPE_FCF_DEAD:
+		phba->fcoe_cvl_eventtag = acqe_fip->event_tag;
 		lpfc_printf_log(phba, KERN_ERR, LOG_FIP | LOG_DISCOVERY,
 			"2549 FCF (x%x) disconnected from network, "
 			"tag:x%x\n", acqe_fip->index, acqe_fip->event_tag);
@@ -3784,6 +3787,7 @@ lpfc_sli4_async_fip_evt(struct lpfc_hba *phba,
 		}
 		break;
 	case LPFC_FIP_EVENT_TYPE_CVL:
+		phba->fcoe_cvl_eventtag = acqe_fip->event_tag;
 		lpfc_printf_log(phba, KERN_ERR, LOG_FIP | LOG_DISCOVERY,
 			"2718 Clear Virtual Link Received for VPI 0x%x"
 			" tag 0x%x\n", acqe_fip->index, acqe_fip->event_tag);
@@ -5226,8 +5230,7 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 	 * rpi is normalized to a zero base because the physical rpi is
 	 * port based.
 	 */
-	curr_rpi_range = phba->sli4_hba.next_rpi -
-		phba->sli4_hba.max_cfg_param.rpi_base;
+	curr_rpi_range = phba->sli4_hba.next_rpi;
 	spin_unlock_irq(&phba->hbalock);
 
 	/*
@@ -5818,10 +5821,9 @@ lpfc_sli4_post_status_check(struct lpfc_hba *phba)
 					readl(phba->sli4_hba.u.if_type2.
 					      ERR2regaddr);
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"2888 Port Error Detected "
-					"during POST: "
-					"port status reg 0x%x, "
-					"port_smphr reg 0x%x, "
+					"2888 Unrecoverable port error "
+					"following POST: port status reg "
+					"0x%x, port_smphr reg 0x%x, "
 					"error 1=0x%x, error 2=0x%x\n",
 					reg_data.word0,
 					portsmphr_reg.word0,
@@ -6142,7 +6144,6 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 		phba->sli4_hba.next_xri = phba->sli4_hba.max_cfg_param.xri_base;
 		phba->vpi_base = phba->sli4_hba.max_cfg_param.vpi_base;
 		phba->vfi_base = phba->sli4_hba.max_cfg_param.vfi_base;
-		phba->sli4_hba.next_rpi = phba->sli4_hba.max_cfg_param.rpi_base;
 		phba->max_vpi = (phba->sli4_hba.max_cfg_param.max_vpi > 0) ?
 				(phba->sli4_hba.max_cfg_param.max_vpi - 1) : 0;
 		phba->max_vports = phba->max_vpi;
@@ -7231,6 +7232,7 @@ lpfc_pci_function_reset(struct lpfc_hba *phba)
 	uint32_t rdy_chk, num_resets = 0, reset_again = 0;
 	union lpfc_sli4_cfg_shdr *shdr;
 	struct lpfc_register reg_data;
+	uint16_t devid;
 
 	if_type = bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf);
 	switch (if_type) {
@@ -7277,7 +7279,9 @@ lpfc_pci_function_reset(struct lpfc_hba *phba)
 			       LPFC_SLIPORT_INIT_PORT);
 			writel(reg_data.word0, phba->sli4_hba.u.if_type2.
 			       CTRLregaddr);
-
+			/* flush */
+			pci_read_config_word(phba->pcidev,
+					     PCI_DEVICE_ID, &devid);
 			/*
 			 * Poll the Port Status Register and wait for RDY for
 			 * up to 10 seconds.  If the port doesn't respond, treat
@@ -7315,11 +7319,10 @@ lpfc_pci_function_reset(struct lpfc_hba *phba)
 				phba->work_status[1] = readl(
 					phba->sli4_hba.u.if_type2.ERR2regaddr);
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"2890 Port Error Detected "
-					"during Port Reset: "
-					"port status reg 0x%x, "
+					"2890 Port error detected during port "
+					"reset(%d): port status reg 0x%x, "
 					"error 1=0x%x, error 2=0x%x\n",
-					reg_data.word0,
+					num_resets, reg_data.word0,
 					phba->work_status[0],
 					phba->work_status[1]);
 				rc = -ENODEV;
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 7b6b2aa5795a..15ca2a9a0cdd 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -1,7 +1,7 @@
  /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2009 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -440,11 +440,15 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		spin_unlock_irq(shost->host_lock);
 		stat.un.b.lsRjtRsnCode = LSRJT_INVALID_CMD;
 		stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE;
-		lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb,
+		rc = lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb,
 			ndlp, mbox);
+		if (rc)
+			mempool_free(mbox, phba->mbox_mem_pool);
 		return 1;
 	}
-	lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, mbox);
+	rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, mbox);
+	if (rc)
+		mempool_free(mbox, phba->mbox_mem_pool);
 	return 1;
 out:
 	stat.un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC;
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index efc055b6bac4..88f3a83dbd2e 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -39,8 +39,8 @@
 #include "lpfc_sli4.h"
 #include "lpfc_nl.h"
 #include "lpfc_disc.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
@@ -51,13 +51,19 @@
 int _dump_buf_done;
 
 static char *dif_op_str[] = {
-	"SCSI_PROT_NORMAL",
-	"SCSI_PROT_READ_INSERT",
-	"SCSI_PROT_WRITE_STRIP",
-	"SCSI_PROT_READ_STRIP",
-	"SCSI_PROT_WRITE_INSERT",
-	"SCSI_PROT_READ_PASS",
-	"SCSI_PROT_WRITE_PASS",
+	"PROT_NORMAL",
+	"PROT_READ_INSERT",
+	"PROT_WRITE_STRIP",
+	"PROT_READ_STRIP",
+	"PROT_WRITE_INSERT",
+	"PROT_READ_PASS",
+	"PROT_WRITE_PASS",
+};
+
+static char *dif_grd_str[] = {
+	"NO_GUARD",
+	"DIF_CRC",
+	"DIX_IP",
 };
 
 struct scsi_dif_tuple {
@@ -1281,10 +1287,14 @@ lpfc_cmd_blksize(struct scsi_cmnd *sc)
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 
-#define BG_ERR_INIT	1
-#define BG_ERR_TGT	2
-#define BG_ERR_SWAP	3
-#define BG_ERR_CHECK	4
+/* Return if if error injection is detected by Initiator */
+#define BG_ERR_INIT	0x1
+/* Return if if error injection is detected by Target */
+#define BG_ERR_TGT	0x2
+/* Return if if swapping CSUM<-->CRC is required for error injection */
+#define BG_ERR_SWAP	0x10
+/* Return if disabling Guard/Ref/App checking is required for error injection */
+#define BG_ERR_CHECK	0x20
 
 /**
  * lpfc_bg_err_inject - Determine if we should inject an error
@@ -1294,10 +1304,7 @@ lpfc_cmd_blksize(struct scsi_cmnd *sc)
  * @apptag: (out) BlockGuard application tag for transmitted data
  * @new_guard (in) Value to replace CRC with if needed
  *
- * Returns (1) if error injection is detected by Initiator
- * Returns (2) if error injection is detected by Target
- * Returns (3) if swapping CSUM->CRC is required for error injection
- * Returns (4) disabling Guard/Ref/App checking is required for error injection
+ * Returns BG_ERR_* bit mask or 0 if request ignored
  **/
 static int
 lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
@@ -1305,7 +1312,10 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 {
 	struct scatterlist *sgpe; /* s/g prot entry */
 	struct scatterlist *sgde; /* s/g data entry */
+	struct lpfc_scsi_buf *lpfc_cmd = NULL;
 	struct scsi_dif_tuple *src = NULL;
+	struct lpfc_nodelist *ndlp;
+	struct lpfc_rport_data *rdata;
 	uint32_t op = scsi_get_prot_op(sc);
 	uint32_t blksize;
 	uint32_t numblks;
@@ -1318,8 +1328,9 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 
 	sgpe = scsi_prot_sglist(sc);
 	sgde = scsi_sglist(sc);
-
 	lba = scsi_get_lba(sc);
+
+	/* First check if we need to match the LBA */
 	if (phba->lpfc_injerr_lba != LPFC_INJERR_LBA_OFF) {
 		blksize = lpfc_cmd_blksize(sc);
 		numblks = (scsi_bufflen(sc) + blksize - 1) / blksize;
@@ -1334,66 +1345,123 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 				sizeof(struct scsi_dif_tuple);
 			if (numblks < blockoff)
 				blockoff = numblks;
-			src = (struct scsi_dif_tuple *)sg_virt(sgpe);
-			src += blockoff;
 		}
 	}
 
+	/* Next check if we need to match the remote NPortID or WWPN */
+	rdata = sc->device->hostdata;
+	if (rdata && rdata->pnode) {
+		ndlp = rdata->pnode;
+
+		/* Make sure we have the right NPortID if one is specified */
+		if (phba->lpfc_injerr_nportid  &&
+			(phba->lpfc_injerr_nportid != ndlp->nlp_DID))
+			return 0;
+
+		/*
+		 * Make sure we have the right WWPN if one is specified.
+		 * wwn[0] should be a non-zero NAA in a good WWPN.
+		 */
+		if (phba->lpfc_injerr_wwpn.u.wwn[0]  &&
+			(memcmp(&ndlp->nlp_portname, &phba->lpfc_injerr_wwpn,
+				sizeof(struct lpfc_name)) != 0))
+			return 0;
+	}
+
+	/* Setup a ptr to the protection data if the SCSI host provides it */
+	if (sgpe) {
+		src = (struct scsi_dif_tuple *)sg_virt(sgpe);
+		src += blockoff;
+		lpfc_cmd = (struct lpfc_scsi_buf *)sc->host_scribble;
+	}
+
 	/* Should we change the Reference Tag */
 	if (reftag) {
 		if (phba->lpfc_injerr_wref_cnt) {
 			switch (op) {
 			case SCSI_PROT_WRITE_PASS:
-				if (blockoff && src) {
-					/* Insert error in middle of the IO */
+				if (src) {
+					/*
+					 * For WRITE_PASS, force the error
+					 * to be sent on the wire. It should
+					 * be detected by the Target.
+					 * If blockoff != 0 error will be
+					 * inserted in middle of the IO.
+					 */
 
 					lpfc_printf_log(phba, KERN_ERR, LOG_BG,
 					"9076 BLKGRD: Injecting reftag error: "
 					"write lba x%lx + x%x oldrefTag x%x\n",
 					(unsigned long)lba, blockoff,
-					src->ref_tag);
+					be32_to_cpu(src->ref_tag));
 
 					/*
-					 * NOTE, this will change ref tag in
-					 * the memory location forever!
+					 * Save the old ref_tag so we can
+					 * restore it on completion.
 					 */
-					src->ref_tag = 0xDEADBEEF;
+					if (lpfc_cmd) {
+						lpfc_cmd->prot_data_type =
+							LPFC_INJERR_REFTAG;
+						lpfc_cmd->prot_data_segment =
+							src;
+						lpfc_cmd->prot_data =
+							src->ref_tag;
+					}
+					src->ref_tag = cpu_to_be32(0xDEADBEEF);
 					phba->lpfc_injerr_wref_cnt--;
-					phba->lpfc_injerr_lba =
-						LPFC_INJERR_LBA_OFF;
-					rc = BG_ERR_CHECK;
+					if (phba->lpfc_injerr_wref_cnt == 0) {
+						phba->lpfc_injerr_nportid = 0;
+						phba->lpfc_injerr_lba =
+							LPFC_INJERR_LBA_OFF;
+						memset(&phba->lpfc_injerr_wwpn,
+						  0, sizeof(struct lpfc_name));
+					}
+					rc = BG_ERR_TGT | BG_ERR_CHECK;
+
 					break;
 				}
 				/* Drop thru */
-			case SCSI_PROT_WRITE_STRIP:
+			case SCSI_PROT_WRITE_INSERT:
 				/*
-				 * For WRITE_STRIP and WRITE_PASS,
-				 * force the error on data
-				 * being copied from SLI-Host to SLI-Port.
+				 * For WRITE_INSERT, force the error
+				 * to be sent on the wire. It should be
+				 * detected by the Target.
 				 */
+				/* DEADBEEF will be the reftag on the wire */
 				*reftag = 0xDEADBEEF;
 				phba->lpfc_injerr_wref_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
-				rc = BG_ERR_INIT;
+				if (phba->lpfc_injerr_wref_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+					LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
+				rc = BG_ERR_TGT | BG_ERR_CHECK;
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
-					"9077 BLKGRD: Injecting reftag error: "
+					"9078 BLKGRD: Injecting reftag error: "
 					"write lba x%lx\n", (unsigned long)lba);
 				break;
-			case SCSI_PROT_WRITE_INSERT:
+			case SCSI_PROT_WRITE_STRIP:
 				/*
-				 * For WRITE_INSERT, force the
-				 * error to be sent on the wire. It should be
-				 * detected by the Target.
+				 * For WRITE_STRIP and WRITE_PASS,
+				 * force the error on data
+				 * being copied from SLI-Host to SLI-Port.
 				 */
-				/* DEADBEEF will be the reftag on the wire */
 				*reftag = 0xDEADBEEF;
 				phba->lpfc_injerr_wref_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
-				rc = BG_ERR_TGT;
+				if (phba->lpfc_injerr_wref_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+						LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
+				rc = BG_ERR_INIT;
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
-					"9078 BLKGRD: Injecting reftag error: "
+					"9077 BLKGRD: Injecting reftag error: "
 					"write lba x%lx\n", (unsigned long)lba);
 				break;
 			}
@@ -1401,11 +1469,6 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		if (phba->lpfc_injerr_rref_cnt) {
 			switch (op) {
 			case SCSI_PROT_READ_INSERT:
-				/*
-				 * For READ_INSERT, it doesn't make sense
-				 * to change the reftag.
-				 */
-				break;
 			case SCSI_PROT_READ_STRIP:
 			case SCSI_PROT_READ_PASS:
 				/*
@@ -1415,7 +1478,13 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 				 */
 				*reftag = 0xDEADBEEF;
 				phba->lpfc_injerr_rref_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
+				if (phba->lpfc_injerr_rref_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+						LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
 				rc = BG_ERR_INIT;
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
@@ -1431,56 +1500,87 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		if (phba->lpfc_injerr_wapp_cnt) {
 			switch (op) {
 			case SCSI_PROT_WRITE_PASS:
-				if (blockoff && src) {
-					/* Insert error in middle of the IO */
+				if (src) {
+					/*
+					 * For WRITE_PASS, force the error
+					 * to be sent on the wire. It should
+					 * be detected by the Target.
+					 * If blockoff != 0 error will be
+					 * inserted in middle of the IO.
+					 */
 
 					lpfc_printf_log(phba, KERN_ERR, LOG_BG,
 					"9080 BLKGRD: Injecting apptag error: "
 					"write lba x%lx + x%x oldappTag x%x\n",
 					(unsigned long)lba, blockoff,
-					src->app_tag);
+					be16_to_cpu(src->app_tag));
 
 					/*
-					 * NOTE, this will change app tag in
-					 * the memory location forever!
+					 * Save the old app_tag so we can
+					 * restore it on completion.
 					 */
-					src->app_tag = 0xDEAD;
+					if (lpfc_cmd) {
+						lpfc_cmd->prot_data_type =
+							LPFC_INJERR_APPTAG;
+						lpfc_cmd->prot_data_segment =
+							src;
+						lpfc_cmd->prot_data =
+							src->app_tag;
+					}
+					src->app_tag = cpu_to_be16(0xDEAD);
 					phba->lpfc_injerr_wapp_cnt--;
-					phba->lpfc_injerr_lba =
-						LPFC_INJERR_LBA_OFF;
-					rc = BG_ERR_CHECK;
+					if (phba->lpfc_injerr_wapp_cnt == 0) {
+						phba->lpfc_injerr_nportid = 0;
+						phba->lpfc_injerr_lba =
+							LPFC_INJERR_LBA_OFF;
+						memset(&phba->lpfc_injerr_wwpn,
+						  0, sizeof(struct lpfc_name));
+					}
+					rc = BG_ERR_TGT | BG_ERR_CHECK;
 					break;
 				}
 				/* Drop thru */
-			case SCSI_PROT_WRITE_STRIP:
+			case SCSI_PROT_WRITE_INSERT:
 				/*
-				 * For WRITE_STRIP and WRITE_PASS,
-				 * force the error on data
-				 * being copied from SLI-Host to SLI-Port.
+				 * For WRITE_INSERT, force the
+				 * error to be sent on the wire. It should be
+				 * detected by the Target.
 				 */
+				/* DEAD will be the apptag on the wire */
 				*apptag = 0xDEAD;
 				phba->lpfc_injerr_wapp_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
-				rc = BG_ERR_INIT;
+				if (phba->lpfc_injerr_wapp_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+						LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
+				rc = BG_ERR_TGT | BG_ERR_CHECK;
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
-					"0812 BLKGRD: Injecting apptag error: "
+					"0813 BLKGRD: Injecting apptag error: "
 					"write lba x%lx\n", (unsigned long)lba);
 				break;
-			case SCSI_PROT_WRITE_INSERT:
+			case SCSI_PROT_WRITE_STRIP:
 				/*
-				 * For WRITE_INSERT, force the
-				 * error to be sent on the wire. It should be
-				 * detected by the Target.
+				 * For WRITE_STRIP and WRITE_PASS,
+				 * force the error on data
+				 * being copied from SLI-Host to SLI-Port.
 				 */
-				/* DEAD will be the apptag on the wire */
 				*apptag = 0xDEAD;
 				phba->lpfc_injerr_wapp_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
-				rc = BG_ERR_TGT;
+				if (phba->lpfc_injerr_wapp_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+						LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
+				rc = BG_ERR_INIT;
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
-					"0813 BLKGRD: Injecting apptag error: "
+					"0812 BLKGRD: Injecting apptag error: "
 					"write lba x%lx\n", (unsigned long)lba);
 				break;
 			}
@@ -1488,11 +1588,6 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		if (phba->lpfc_injerr_rapp_cnt) {
 			switch (op) {
 			case SCSI_PROT_READ_INSERT:
-				/*
-				 * For READ_INSERT, it doesn't make sense
-				 * to change the apptag.
-				 */
-				break;
 			case SCSI_PROT_READ_STRIP:
 			case SCSI_PROT_READ_PASS:
 				/*
@@ -1502,7 +1597,13 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 				 */
 				*apptag = 0xDEAD;
 				phba->lpfc_injerr_rapp_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
+				if (phba->lpfc_injerr_rapp_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+						LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
 				rc = BG_ERR_INIT;
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
@@ -1519,57 +1620,51 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		if (phba->lpfc_injerr_wgrd_cnt) {
 			switch (op) {
 			case SCSI_PROT_WRITE_PASS:
-				if (blockoff && src) {
-					/* Insert error in middle of the IO */
-
-					lpfc_printf_log(phba, KERN_ERR, LOG_BG,
-					"0815 BLKGRD: Injecting guard error: "
-					"write lba x%lx + x%x oldgrdTag x%x\n",
-					(unsigned long)lba, blockoff,
-					src->guard_tag);
-
-					/*
-					 * NOTE, this will change guard tag in
-					 * the memory location forever!
-					 */
-					src->guard_tag = 0xDEAD;
-					phba->lpfc_injerr_wgrd_cnt--;
-					phba->lpfc_injerr_lba =
-						LPFC_INJERR_LBA_OFF;
-					rc = BG_ERR_CHECK;
-					break;
-				}
+				rc = BG_ERR_CHECK;
 				/* Drop thru */
-			case SCSI_PROT_WRITE_STRIP:
+
+			case SCSI_PROT_WRITE_INSERT:
 				/*
-				 * For WRITE_STRIP and WRITE_PASS,
-				 * force the error on data
-				 * being copied from SLI-Host to SLI-Port.
+				 * For WRITE_INSERT, force the
+				 * error to be sent on the wire. It should be
+				 * detected by the Target.
 				 */
 				phba->lpfc_injerr_wgrd_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
+				if (phba->lpfc_injerr_wgrd_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+						LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
 
-				rc = BG_ERR_SWAP;
+				rc |= BG_ERR_TGT | BG_ERR_SWAP;
 				/* Signals the caller to swap CRC->CSUM */
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
-					"0816 BLKGRD: Injecting guard error: "
+					"0817 BLKGRD: Injecting guard error: "
 					"write lba x%lx\n", (unsigned long)lba);
 				break;
-			case SCSI_PROT_WRITE_INSERT:
+			case SCSI_PROT_WRITE_STRIP:
 				/*
-				 * For WRITE_INSERT, force the
-				 * error to be sent on the wire. It should be
-				 * detected by the Target.
+				 * For WRITE_STRIP and WRITE_PASS,
+				 * force the error on data
+				 * being copied from SLI-Host to SLI-Port.
 				 */
 				phba->lpfc_injerr_wgrd_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
+				if (phba->lpfc_injerr_wgrd_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+						LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
 
-				rc = BG_ERR_SWAP;
+				rc = BG_ERR_INIT | BG_ERR_SWAP;
 				/* Signals the caller to swap CRC->CSUM */
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
-					"0817 BLKGRD: Injecting guard error: "
+					"0816 BLKGRD: Injecting guard error: "
 					"write lba x%lx\n", (unsigned long)lba);
 				break;
 			}
@@ -1577,11 +1672,6 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		if (phba->lpfc_injerr_rgrd_cnt) {
 			switch (op) {
 			case SCSI_PROT_READ_INSERT:
-				/*
-				 * For READ_INSERT, it doesn't make sense
-				 * to change the guard tag.
-				 */
-				break;
 			case SCSI_PROT_READ_STRIP:
 			case SCSI_PROT_READ_PASS:
 				/*
@@ -1589,11 +1679,16 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 				 * error on data being read off the wire. It
 				 * should force an IO error to the driver.
 				 */
-				*apptag = 0xDEAD;
 				phba->lpfc_injerr_rgrd_cnt--;
-				phba->lpfc_injerr_lba = LPFC_INJERR_LBA_OFF;
+				if (phba->lpfc_injerr_rgrd_cnt == 0) {
+					phba->lpfc_injerr_nportid = 0;
+					phba->lpfc_injerr_lba =
+						LPFC_INJERR_LBA_OFF;
+					memset(&phba->lpfc_injerr_wwpn,
+						0, sizeof(struct lpfc_name));
+				}
 
-				rc = BG_ERR_SWAP;
+				rc = BG_ERR_INIT | BG_ERR_SWAP;
 				/* Signals the caller to swap CRC->CSUM */
 
 				lpfc_printf_log(phba, KERN_ERR, LOG_BG,
@@ -1629,20 +1724,20 @@ lpfc_sc_to_bg_opcodes(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		switch (scsi_get_prot_op(sc)) {
 		case SCSI_PROT_READ_INSERT:
 		case SCSI_PROT_WRITE_STRIP:
-			*txop = BG_OP_IN_CSUM_OUT_NODIF;
 			*rxop = BG_OP_IN_NODIF_OUT_CSUM;
+			*txop = BG_OP_IN_CSUM_OUT_NODIF;
 			break;
 
 		case SCSI_PROT_READ_STRIP:
 		case SCSI_PROT_WRITE_INSERT:
-			*txop = BG_OP_IN_NODIF_OUT_CRC;
 			*rxop = BG_OP_IN_CRC_OUT_NODIF;
+			*txop = BG_OP_IN_NODIF_OUT_CRC;
 			break;
 
 		case SCSI_PROT_READ_PASS:
 		case SCSI_PROT_WRITE_PASS:
-			*txop = BG_OP_IN_CSUM_OUT_CRC;
 			*rxop = BG_OP_IN_CRC_OUT_CSUM;
+			*txop = BG_OP_IN_CSUM_OUT_CRC;
 			break;
 
 		case SCSI_PROT_NORMAL:
@@ -1658,20 +1753,20 @@ lpfc_sc_to_bg_opcodes(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		switch (scsi_get_prot_op(sc)) {
 		case SCSI_PROT_READ_STRIP:
 		case SCSI_PROT_WRITE_INSERT:
-			*txop = BG_OP_IN_NODIF_OUT_CRC;
 			*rxop = BG_OP_IN_CRC_OUT_NODIF;
+			*txop = BG_OP_IN_NODIF_OUT_CRC;
 			break;
 
 		case SCSI_PROT_READ_PASS:
 		case SCSI_PROT_WRITE_PASS:
-			*txop = BG_OP_IN_CRC_OUT_CRC;
 			*rxop = BG_OP_IN_CRC_OUT_CRC;
+			*txop = BG_OP_IN_CRC_OUT_CRC;
 			break;
 
 		case SCSI_PROT_READ_INSERT:
 		case SCSI_PROT_WRITE_STRIP:
-			*txop = BG_OP_IN_CRC_OUT_NODIF;
 			*rxop = BG_OP_IN_NODIF_OUT_CRC;
+			*txop = BG_OP_IN_CRC_OUT_NODIF;
 			break;
 
 		case SCSI_PROT_NORMAL:
@@ -1710,20 +1805,20 @@ lpfc_bg_err_opcodes(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		switch (scsi_get_prot_op(sc)) {
 		case SCSI_PROT_READ_INSERT:
 		case SCSI_PROT_WRITE_STRIP:
-			*txop = BG_OP_IN_CRC_OUT_NODIF;
 			*rxop = BG_OP_IN_NODIF_OUT_CRC;
+			*txop = BG_OP_IN_CRC_OUT_NODIF;
 			break;
 
 		case SCSI_PROT_READ_STRIP:
 		case SCSI_PROT_WRITE_INSERT:
-			*txop = BG_OP_IN_NODIF_OUT_CSUM;
 			*rxop = BG_OP_IN_CSUM_OUT_NODIF;
+			*txop = BG_OP_IN_NODIF_OUT_CSUM;
 			break;
 
 		case SCSI_PROT_READ_PASS:
 		case SCSI_PROT_WRITE_PASS:
-			*txop = BG_OP_IN_CRC_OUT_CRC;
-			*rxop = BG_OP_IN_CRC_OUT_CRC;
+			*rxop = BG_OP_IN_CSUM_OUT_CRC;
+			*txop = BG_OP_IN_CRC_OUT_CSUM;
 			break;
 
 		case SCSI_PROT_NORMAL:
@@ -1735,20 +1830,20 @@ lpfc_bg_err_opcodes(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		switch (scsi_get_prot_op(sc)) {
 		case SCSI_PROT_READ_STRIP:
 		case SCSI_PROT_WRITE_INSERT:
-			*txop = BG_OP_IN_NODIF_OUT_CSUM;
 			*rxop = BG_OP_IN_CSUM_OUT_NODIF;
+			*txop = BG_OP_IN_NODIF_OUT_CSUM;
 			break;
 
 		case SCSI_PROT_READ_PASS:
 		case SCSI_PROT_WRITE_PASS:
-			*txop = BG_OP_IN_CSUM_OUT_CRC;
-			*rxop = BG_OP_IN_CRC_OUT_CSUM;
+			*rxop = BG_OP_IN_CSUM_OUT_CSUM;
+			*txop = BG_OP_IN_CSUM_OUT_CSUM;
 			break;
 
 		case SCSI_PROT_READ_INSERT:
 		case SCSI_PROT_WRITE_STRIP:
-			*txop = BG_OP_IN_CSUM_OUT_NODIF;
 			*rxop = BG_OP_IN_NODIF_OUT_CSUM;
+			*txop = BG_OP_IN_CSUM_OUT_NODIF;
 			break;
 
 		case SCSI_PROT_NORMAL:
@@ -1817,11 +1912,11 @@ lpfc_bg_setup_bpl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	reftag = (uint32_t)scsi_get_lba(sc); /* Truncate LBA */
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	rc = lpfc_bg_err_inject(phba, sc, &reftag, 0, 1);
+	rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1);
 	if (rc) {
-		if (rc == BG_ERR_SWAP)
+		if (rc & BG_ERR_SWAP)
 			lpfc_bg_err_opcodes(phba, sc, &txop, &rxop);
-		if (rc == BG_ERR_CHECK)
+		if (rc & BG_ERR_CHECK)
 			checking = 0;
 	}
 #endif
@@ -1964,11 +2059,11 @@ lpfc_bg_setup_bpl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	reftag = (uint32_t)scsi_get_lba(sc); /* Truncate LBA */
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	rc = lpfc_bg_err_inject(phba, sc, &reftag, 0, 1);
+	rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1);
 	if (rc) {
-		if (rc == BG_ERR_SWAP)
+		if (rc & BG_ERR_SWAP)
 			lpfc_bg_err_opcodes(phba, sc, &txop, &rxop);
-		if (rc == BG_ERR_CHECK)
+		if (rc & BG_ERR_CHECK)
 			checking = 0;
 	}
 #endif
@@ -2172,11 +2267,11 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	reftag = (uint32_t)scsi_get_lba(sc); /* Truncate LBA */
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	rc = lpfc_bg_err_inject(phba, sc, &reftag, 0, 1);
+	rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1);
 	if (rc) {
-		if (rc == BG_ERR_SWAP)
+		if (rc & BG_ERR_SWAP)
 			lpfc_bg_err_opcodes(phba, sc, &txop, &rxop);
-		if (rc == BG_ERR_CHECK)
+		if (rc & BG_ERR_CHECK)
 			checking = 0;
 	}
 #endif
@@ -2312,11 +2407,11 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	reftag = (uint32_t)scsi_get_lba(sc); /* Truncate LBA */
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	rc = lpfc_bg_err_inject(phba, sc, &reftag, 0, 1);
+	rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1);
 	if (rc) {
-		if (rc == BG_ERR_SWAP)
+		if (rc & BG_ERR_SWAP)
 			lpfc_bg_err_opcodes(phba, sc, &txop, &rxop);
-		if (rc == BG_ERR_CHECK)
+		if (rc & BG_ERR_CHECK)
 			checking = 0;
 	}
 #endif
@@ -2788,7 +2883,7 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 		/* No error was reported - problem in FW? */
 		cmd->result = ScsiResult(DID_ERROR, 0);
 		lpfc_printf_log(phba, KERN_ERR, LOG_BG,
-			"9057 BLKGRD: no errors reported!\n");
+			"9057 BLKGRD: Unknown error reported!\n");
 	}
 
 out:
@@ -3460,6 +3555,37 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	/* pick up SLI4 exhange busy status from HBA */
 	lpfc_cmd->exch_busy = pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY;
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (lpfc_cmd->prot_data_type) {
+		struct scsi_dif_tuple *src = NULL;
+
+		src =  (struct scsi_dif_tuple *)lpfc_cmd->prot_data_segment;
+		/*
+		 * Used to restore any changes to protection
+		 * data for error injection.
+		 */
+		switch (lpfc_cmd->prot_data_type) {
+		case LPFC_INJERR_REFTAG:
+			src->ref_tag =
+				lpfc_cmd->prot_data;
+			break;
+		case LPFC_INJERR_APPTAG:
+			src->app_tag =
+				(uint16_t)lpfc_cmd->prot_data;
+			break;
+		case LPFC_INJERR_GUARD:
+			src->guard_tag =
+				(uint16_t)lpfc_cmd->prot_data;
+			break;
+		default:
+			break;
+		}
+
+		lpfc_cmd->prot_data = 0;
+		lpfc_cmd->prot_data_type = 0;
+		lpfc_cmd->prot_data_segment = NULL;
+	}
+#endif
 	if (pnode && NLP_CHK_NODE_ACT(pnode))
 		atomic_dec(&pnode->cmd_pending);
 
@@ -4061,15 +4187,6 @@ lpfc_queuecommand_lck(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
 		cmnd->result = err;
 		goto out_fail_command;
 	}
-	/*
-	 * Do not let the mid-layer retry I/O too fast. If an I/O is retried
-	 * without waiting a bit then indicate that the device is busy.
-	 */
-	if (cmnd->retries &&
-	    time_before(jiffies, (cmnd->jiffies_at_alloc +
-				  msecs_to_jiffies(LPFC_RETRY_PAUSE *
-						   cmnd->retries))))
-		return SCSI_MLQUEUE_DEVICE_BUSY;
 	ndlp = rdata->pnode;
 
 	if ((scsi_get_prot_op(cmnd) != SCSI_PROT_NORMAL) &&
@@ -4119,63 +4236,48 @@ lpfc_queuecommand_lck(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
 	if (scsi_get_prot_op(cmnd) != SCSI_PROT_NORMAL) {
 		if (vport->phba->cfg_enable_bg) {
 			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
-				"9033 BLKGRD: rcvd protected cmd:%02x op:%02x "
-				"str=%s\n",
-				cmnd->cmnd[0], scsi_get_prot_op(cmnd),
-				dif_op_str[scsi_get_prot_op(cmnd)]);
-			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
-				"9034 BLKGRD: CDB: %02x %02x %02x %02x %02x "
-				"%02x %02x %02x %02x %02x\n",
-				cmnd->cmnd[0], cmnd->cmnd[1], cmnd->cmnd[2],
-				cmnd->cmnd[3], cmnd->cmnd[4], cmnd->cmnd[5],
-				cmnd->cmnd[6], cmnd->cmnd[7], cmnd->cmnd[8],
-				cmnd->cmnd[9]);
+				"9033 BLKGRD: rcvd protected cmd:%02x op=%s "
+				"guard=%s\n", cmnd->cmnd[0],
+				dif_op_str[scsi_get_prot_op(cmnd)],
+				dif_grd_str[scsi_host_get_guard(shost)]);
 			if (cmnd->cmnd[0] == READ_10)
 				lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
 					"9035 BLKGRD: READ @ sector %llu, "
-					"count %u\n",
+					"cnt %u, rpt %d\n",
 					(unsigned long long)scsi_get_lba(cmnd),
-					blk_rq_sectors(cmnd->request));
+					blk_rq_sectors(cmnd->request),
+					(cmnd->cmnd[1]>>5));
 			else if (cmnd->cmnd[0] == WRITE_10)
 				lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
 					"9036 BLKGRD: WRITE @ sector %llu, "
-					"count %u cmd=%p\n",
+					"cnt %u, wpt %d\n",
 					(unsigned long long)scsi_get_lba(cmnd),
 					blk_rq_sectors(cmnd->request),
-					cmnd);
+					(cmnd->cmnd[1]>>5));
 		}
 
 		err = lpfc_bg_scsi_prep_dma_buf(phba, lpfc_cmd);
 	} else {
 		if (vport->phba->cfg_enable_bg) {
 			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
-					"9038 BLKGRD: rcvd unprotected cmd:"
-					"%02x op:%02x str=%s\n",
-					cmnd->cmnd[0], scsi_get_prot_op(cmnd),
-					dif_op_str[scsi_get_prot_op(cmnd)]);
-				lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
-					"9039 BLKGRD: CDB: %02x %02x %02x "
-					"%02x %02x %02x %02x %02x %02x %02x\n",
-					cmnd->cmnd[0], cmnd->cmnd[1],
-					cmnd->cmnd[2], cmnd->cmnd[3],
-					cmnd->cmnd[4], cmnd->cmnd[5],
-					cmnd->cmnd[6], cmnd->cmnd[7],
-					cmnd->cmnd[8], cmnd->cmnd[9]);
+				"9038 BLKGRD: rcvd unprotected cmd:"
+				"%02x op=%s guard=%s\n", cmnd->cmnd[0],
+				dif_op_str[scsi_get_prot_op(cmnd)],
+				dif_grd_str[scsi_host_get_guard(shost)]);
 			if (cmnd->cmnd[0] == READ_10)
 				lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
 					"9040 dbg: READ @ sector %llu, "
-					"count %u\n",
+					"cnt %u, rpt %d\n",
 					(unsigned long long)scsi_get_lba(cmnd),
-					 blk_rq_sectors(cmnd->request));
+					 blk_rq_sectors(cmnd->request),
+					(cmnd->cmnd[1]>>5));
 			else if (cmnd->cmnd[0] == WRITE_10)
 				lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
-					 "9041 dbg: WRITE @ sector %llu, "
-					 "count %u cmd=%p\n",
-					 (unsigned long long)scsi_get_lba(cmnd),
-					 blk_rq_sectors(cmnd->request), cmnd);
-			else
-				lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
-					 "9042 dbg: parser not implemented\n");
+					"9041 dbg: WRITE @ sector %llu, "
+					"cnt %u, wpt %d\n",
+					(unsigned long long)scsi_get_lba(cmnd),
+					blk_rq_sectors(cmnd->request),
+					(cmnd->cmnd[1]>>5));
 		}
 		err = lpfc_scsi_prep_dma_buf(phba, lpfc_cmd);
 	}
diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h
index 9075a08cf781..21a2ffe67eac 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.h
+++ b/drivers/scsi/lpfc/lpfc_scsi.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2006 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -150,9 +150,18 @@ struct lpfc_scsi_buf {
 	struct lpfc_iocbq cur_iocbq;
 	wait_queue_head_t *waitq;
 	unsigned long start_time;
+
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	/* Used to restore any changes to protection data for error injection */
+	void *prot_data_segment;
+	uint32_t prot_data;
+	uint32_t prot_data_type;
+#define	LPFC_INJERR_REFTAG	1
+#define	LPFC_INJERR_APPTAG	2
+#define	LPFC_INJERR_GUARD	3
+#endif
 };
 
 #define LPFC_SCSI_DMA_EXT_SIZE 264
 #define LPFC_BPL_SIZE          1024
-#define LPFC_RETRY_PAUSE       300
 #define MDAC_DIRECT_CMD                  0x22
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index e0e4d8d18244..dbaf5b963bff 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -5578,8 +5578,6 @@ lpfc_sli4_alloc_resource_identifiers(struct lpfc_hba *phba)
 		for (i = 0; i < count; i++)
 			phba->sli4_hba.rpi_ids[i] = base + i;
 
-		lpfc_sli4_node_prep(phba);
-
 		/* VPIs. */
 		count = phba->sli4_hba.max_cfg_param.max_vpi;
 		base = phba->sli4_hba.max_cfg_param.vpi_base;
@@ -5613,6 +5611,8 @@ lpfc_sli4_alloc_resource_identifiers(struct lpfc_hba *phba)
 			rc = -ENOMEM;
 			goto free_vpi_ids;
 		}
+		phba->sli4_hba.max_cfg_param.xri_used = 0;
+		phba->sli4_hba.xri_count = 0;
 		phba->sli4_hba.xri_ids = kzalloc(count *
 						 sizeof(uint16_t),
 						 GFP_KERNEL);
@@ -6147,6 +6147,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		rc = -ENODEV;
 		goto out_free_mbox;
 	}
+	lpfc_sli4_node_prep(phba);
 
 	/* Create all the SLI4 queues */
 	rc = lpfc_sli4_queue_create(phba);
@@ -7251,11 +7252,13 @@ lpfc_sli4_post_async_mbox(struct lpfc_hba *phba)
 
 out_not_finished:
 	spin_lock_irqsave(&phba->hbalock, iflags);
-	mboxq->u.mb.mbxStatus = MBX_NOT_FINISHED;
-	__lpfc_mbox_cmpl_put(phba, mboxq);
-	/* Release the token */
-	psli->sli_flag &= ~LPFC_SLI_MBOX_ACTIVE;
-	phba->sli.mbox_active = NULL;
+	if (phba->sli.mbox_active) {
+		mboxq->u.mb.mbxStatus = MBX_NOT_FINISHED;
+		__lpfc_mbox_cmpl_put(phba, mboxq);
+		/* Release the token */
+		psli->sli_flag &= ~LPFC_SLI_MBOX_ACTIVE;
+		phba->sli.mbox_active = NULL;
+	}
 	spin_unlock_irqrestore(&phba->hbalock, iflags);
 
 	return MBX_NOT_FINISHED;
@@ -7743,6 +7746,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 			if (pcmd && (*pcmd == ELS_CMD_FLOGI ||
 				*pcmd == ELS_CMD_SCR ||
 				*pcmd == ELS_CMD_FDISC ||
+				*pcmd == ELS_CMD_LOGO ||
 				*pcmd == ELS_CMD_PLOGI)) {
 				bf_set(els_req64_sp, &wqe->els_req, 1);
 				bf_set(els_req64_sid, &wqe->els_req,
@@ -8385,6 +8389,7 @@ lpfc_sli4_abts_err_handler(struct lpfc_hba *phba,
 			   struct sli4_wcqe_xri_aborted *axri)
 {
 	struct lpfc_vport *vport;
+	uint32_t ext_status = 0;
 
 	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
@@ -8396,12 +8401,20 @@ lpfc_sli4_abts_err_handler(struct lpfc_hba *phba,
 	vport = ndlp->vport;
 	lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
 			"3116 Port generated FCP XRI ABORT event on "
-			"vpi %d rpi %d xri x%x status 0x%x\n",
+			"vpi %d rpi %d xri x%x status 0x%x parameter x%x\n",
 			ndlp->vport->vpi, ndlp->nlp_rpi,
 			bf_get(lpfc_wcqe_xa_xri, axri),
-			bf_get(lpfc_wcqe_xa_status, axri));
+			bf_get(lpfc_wcqe_xa_status, axri),
+			axri->parameter);
 
-	if (bf_get(lpfc_wcqe_xa_status, axri) == IOSTAT_LOCAL_REJECT)
+	/*
+	 * Catch the ABTS protocol failure case.  Older OCe FW releases returned
+	 * LOCAL_REJECT and 0 for a failed ABTS exchange and later OCe and
+	 * LPe FW releases returned LOCAL_REJECT and SEQUENCE_TIMEOUT.
+	 */
+	ext_status = axri->parameter & WCQE_PARAM_MASK;
+	if ((bf_get(lpfc_wcqe_xa_status, axri) == IOSTAT_LOCAL_REJECT) &&
+	    ((ext_status == IOERR_SEQUENCE_TIMEOUT) || (ext_status == 0)))
 		lpfc_sli_abts_recover_port(vport, ndlp);
 }
 
@@ -9807,12 +9820,11 @@ lpfc_sli_mbox_sys_shutdown(struct lpfc_hba *phba)
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(LPFC_MBOX_TMO * 1000) + jiffies;
+
 	spin_lock_irq(&phba->hbalock);
 	psli->sli_flag |= LPFC_SLI_ASYNC_MBX_BLK;
-	spin_unlock_irq(&phba->hbalock);
 
 	if (psli->sli_flag & LPFC_SLI_ACTIVE) {
-		spin_lock_irq(&phba->hbalock);
 		/* Determine how long we might wait for the active mailbox
 		 * command to be gracefully completed by firmware.
 		 */
@@ -9831,7 +9843,9 @@ lpfc_sli_mbox_sys_shutdown(struct lpfc_hba *phba)
 				 */
 				break;
 		}
-	}
+	} else
+		spin_unlock_irq(&phba->hbalock);
+
 	lpfc_sli_mbox_sys_flush(phba);
 }
 
@@ -13272,7 +13286,7 @@ lpfc_sli4_post_els_sgl_list_ext(struct lpfc_hba *phba)
 	LPFC_MBOXQ_t *mbox;
 	uint32_t reqlen, alloclen, index;
 	uint32_t mbox_tmo;
-	uint16_t rsrc_start, rsrc_size, els_xri_cnt;
+	uint16_t rsrc_start, rsrc_size, els_xri_cnt, post_els_xri_cnt;
 	uint16_t xritag_start = 0, lxri = 0;
 	struct lpfc_rsrc_blks *rsrc_blk;
 	int cnt, ttl_cnt, rc = 0;
@@ -13294,6 +13308,7 @@ lpfc_sli4_post_els_sgl_list_ext(struct lpfc_hba *phba)
 
 	cnt = 0;
 	ttl_cnt = 0;
+	post_els_xri_cnt = els_xri_cnt;
 	list_for_each_entry(rsrc_blk, &phba->sli4_hba.lpfc_xri_blk_list,
 			    list) {
 		rsrc_start = rsrc_blk->rsrc_start;
@@ -13303,11 +13318,12 @@ lpfc_sli4_post_els_sgl_list_ext(struct lpfc_hba *phba)
 				"3014 Working ELS Extent start %d, cnt %d\n",
 				rsrc_start, rsrc_size);
 
-		loop_cnt = min(els_xri_cnt, rsrc_size);
-		if (ttl_cnt + loop_cnt >= els_xri_cnt) {
-			loop_cnt = els_xri_cnt - ttl_cnt;
-			ttl_cnt = els_xri_cnt;
-		}
+		loop_cnt = min(post_els_xri_cnt, rsrc_size);
+		if (loop_cnt < post_els_xri_cnt) {
+			post_els_xri_cnt -= loop_cnt;
+			ttl_cnt += loop_cnt;
+		} else
+			ttl_cnt += post_els_xri_cnt;
 
 		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (!mbox)
@@ -14203,15 +14219,14 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_hba *phba,
 		 * field and RX_ID from ABTS for RX_ID field.
 		 */
 		bf_set(lpfc_abts_orig, &icmd->un.bls_rsp, LPFC_ABTS_UNSOL_RSP);
-		bf_set(lpfc_abts_rxid, &icmd->un.bls_rsp, rxid);
 	} else {
 		/* ABTS sent by initiator to CT exchange, construction
 		 * of BA_ACC will need to allocate a new XRI as for the
-		 * XRI_TAG and RX_ID fields.
+		 * XRI_TAG field.
 		 */
 		bf_set(lpfc_abts_orig, &icmd->un.bls_rsp, LPFC_ABTS_UNSOL_INT);
-		bf_set(lpfc_abts_rxid, &icmd->un.bls_rsp, NO_XRI);
 	}
+	bf_set(lpfc_abts_rxid, &icmd->un.bls_rsp, rxid);
 	bf_set(lpfc_abts_oxid, &icmd->un.bls_rsp, oxid);
 
 	/* Xmit CT abts response on exchange <xid> */
@@ -15042,6 +15057,7 @@ lpfc_sli4_fcf_scan_read_fcf_rec(struct lpfc_hba *phba, uint16_t fcf_index)
 	LPFC_MBOXQ_t *mboxq;
 
 	phba->fcoe_eventtag_at_fcf_scan = phba->fcoe_eventtag;
+	phba->fcoe_cvl_eventtag_attn = phba->fcoe_cvl_eventtag;
 	mboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mboxq) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index f2a2602e5c35..25cefc254b76 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -18,7 +18,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "8.3.29"
+#define LPFC_DRIVER_VERSION "8.3.30"
 #define LPFC_DRIVER_NAME		"lpfc"
 #define LPFC_SP_DRIVER_HANDLER_NAME	"lpfc:sp"
 #define LPFC_FP_DRIVER_HANDLER_NAME	"lpfc:fp"
diff --git a/drivers/scsi/mac53c94.c b/drivers/scsi/mac53c94.c
index e6173376605d..e5cd8d8d4ce7 100644
--- a/drivers/scsi/mac53c94.c
+++ b/drivers/scsi/mac53c94.c
@@ -22,7 +22,6 @@
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/pci-bridge.h>
 #include <asm/macio.h>
 
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index 2bccfbe5661e..24828b54773a 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -43,7 +43,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include <asm/macintosh.h>
 #include <asm/macints.h>
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index 494474779532..e8a04ae3276a 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -33,7 +33,6 @@
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/prom.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/hydra.h>
 #include <asm/processor.h>
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c
index 5e69f468535f..8a59a772fdf2 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
@@ -657,7 +657,7 @@ _base_sas_log_info(struct MPT2SAS_ADAPTER *ioc , u32 log_info)
 		return;
 
 	/* eat the loginfos associated with task aborts */
-	if (ioc->ignore_loginfos && (log_info == 30050000 || log_info ==
+	if (ioc->ignore_loginfos && (log_info == 0x30050000 || log_info ==
 	    0x31140000 || log_info == 0x31130000))
 		return;
 
@@ -2060,12 +2060,10 @@ _base_display_ioc_capabilities(struct MPT2SAS_ADAPTER *ioc)
 {
 	int i = 0;
 	char desc[16];
-	u8 revision;
 	u32 iounit_pg1_flags;
 	u32 bios_version;
 
 	bios_version = le32_to_cpu(ioc->bios_pg3.BiosVersion);
-	pci_read_config_byte(ioc->pdev, PCI_CLASS_REVISION, &revision);
 	strncpy(desc, ioc->manu_pg0.ChipName, 16);
 	printk(MPT2SAS_INFO_FMT "%s: FWVersion(%02d.%02d.%02d.%02d), "
 	   "ChipRevision(0x%02x), BiosVersion(%02d.%02d.%02d.%02d)\n",
@@ -2074,7 +2072,7 @@ _base_display_ioc_capabilities(struct MPT2SAS_ADAPTER *ioc)
 	   (ioc->facts.FWVersion.Word & 0x00FF0000) >> 16,
 	   (ioc->facts.FWVersion.Word & 0x0000FF00) >> 8,
 	   ioc->facts.FWVersion.Word & 0x000000FF,
-	   revision,
+	   ioc->pdev->revision,
 	   (bios_version & 0xFF000000) >> 24,
 	   (bios_version & 0x00FF0000) >> 16,
 	   (bios_version & 0x0000FF00) >> 8,
diff --git a/drivers/scsi/mpt2sas/mpt2sas_ctl.c b/drivers/scsi/mpt2sas/mpt2sas_ctl.c
index 7fceb899029e..3b9a28efea82 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_ctl.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_ctl.c
@@ -1026,7 +1026,6 @@ _ctl_getiocinfo(void __user *arg)
 {
 	struct mpt2_ioctl_iocinfo karg;
 	struct MPT2SAS_ADAPTER *ioc;
-	u8 revision;
 
 	if (copy_from_user(&karg, arg, sizeof(karg))) {
 		printk(KERN_ERR "failure at %s:%d/%s()!\n",
@@ -1046,8 +1045,7 @@ _ctl_getiocinfo(void __user *arg)
 		karg.adapter_type = MPT2_IOCTL_INTERFACE_SAS2;
 	if (ioc->pfacts)
 		karg.port_number = ioc->pfacts[0].PortNumber;
-	pci_read_config_byte(ioc->pdev, PCI_CLASS_REVISION, &revision);
-	karg.hw_rev = revision;
+	karg.hw_rev = ioc->pdev->revision;
 	karg.pci_id = ioc->pdev->device;
 	karg.subsystem_device = ioc->pdev->subsystem_device;
 	karg.subsystem_vendor = ioc->pdev->subsystem_vendor;
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index 4b3b4755945c..5982a587babc 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -115,7 +115,6 @@
 
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/nsp32.c b/drivers/scsi/nsp32.c
index 002924963cd8..62b616891a33 100644
--- a/drivers/scsi/nsp32.c
+++ b/drivers/scsi/nsp32.c
@@ -38,7 +38,6 @@
 #include <linux/dma-mapping.h>
 
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index de0b1a704fb5..21883a2d6324 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -54,7 +54,6 @@ static const char * osst_version = "0.99.4";
 #include <linux/mutex.h>
 #include <asm/uaccess.h>
 #include <asm/dma.h>
-#include <asm/system.h>
 
 /* The driver prints some debugging information on the console if DEBUG
    is defined and non-zero. */
diff --git a/drivers/scsi/pas16.c b/drivers/scsi/pas16.c
index f2018b46f494..2f72c9807b12 100644
--- a/drivers/scsi/pas16.c
+++ b/drivers/scsi/pas16.c
@@ -113,7 +113,6 @@
  
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <linux/signal.h>
 #include <linux/proc_fs.h>
 #include <asm/io.h>
diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index 3619f6eeeeda..9d82ee5c10de 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -2093,6 +2093,7 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	struct ata_task_resp *resp ;
 	u32 *sata_resp;
 	struct pm8001_device *pm8001_dev;
+	unsigned long flags;
 
 	psataPayload = (struct sata_completion_resp *)(piomb + 4);
 	status = le32_to_cpu(psataPayload->status);
@@ -2382,26 +2383,26 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		ts->stat = SAS_DEV_NO_RESPONSE;
 		break;
 	}
-	spin_lock_irq(&t->task_state_lock);
+	spin_lock_irqsave(&t->task_state_lock, flags);
 	t->task_state_flags &= ~SAS_TASK_STATE_PENDING;
 	t->task_state_flags &= ~SAS_TASK_AT_INITIATOR;
 	t->task_state_flags |= SAS_TASK_STATE_DONE;
 	if (unlikely((t->task_state_flags & SAS_TASK_STATE_ABORTED))) {
-		spin_unlock_irq(&t->task_state_lock);
+		spin_unlock_irqrestore(&t->task_state_lock, flags);
 		PM8001_FAIL_DBG(pm8001_ha,
 			pm8001_printk("task 0x%p done with io_status 0x%x"
 			" resp 0x%x stat 0x%x but aborted by upper layer!\n",
 			t, status, ts->resp, ts->stat));
 		pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
 	} else if (t->uldd_task) {
-		spin_unlock_irq(&t->task_state_lock);
+		spin_unlock_irqrestore(&t->task_state_lock, flags);
 		pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
 		mb();/* ditto */
 		spin_unlock_irq(&pm8001_ha->lock);
 		t->task_done(t);
 		spin_lock_irq(&pm8001_ha->lock);
 	} else if (!t->uldd_task) {
-		spin_unlock_irq(&t->task_state_lock);
+		spin_unlock_irqrestore(&t->task_state_lock, flags);
 		pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
 		mb();/*ditto*/
 		spin_unlock_irq(&pm8001_ha->lock);
@@ -2423,6 +2424,7 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 	u32 tag = le32_to_cpu(psataPayload->tag);
 	u32 port_id = le32_to_cpu(psataPayload->port_id);
 	u32 dev_id = le32_to_cpu(psataPayload->device_id);
+	unsigned long flags;
 
 	ccb = &pm8001_ha->ccb_info[tag];
 	t = ccb->task;
@@ -2593,26 +2595,26 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 		ts->stat = SAS_OPEN_TO;
 		break;
 	}
-	spin_lock_irq(&t->task_state_lock);
+	spin_lock_irqsave(&t->task_state_lock, flags);
 	t->task_state_flags &= ~SAS_TASK_STATE_PENDING;
 	t->task_state_flags &= ~SAS_TASK_AT_INITIATOR;
 	t->task_state_flags |= SAS_TASK_STATE_DONE;
 	if (unlikely((t->task_state_flags & SAS_TASK_STATE_ABORTED))) {
-		spin_unlock_irq(&t->task_state_lock);
+		spin_unlock_irqrestore(&t->task_state_lock, flags);
 		PM8001_FAIL_DBG(pm8001_ha,
 			pm8001_printk("task 0x%p done with io_status 0x%x"
 			" resp 0x%x stat 0x%x but aborted by upper layer!\n",
 			t, event, ts->resp, ts->stat));
 		pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
 	} else if (t->uldd_task) {
-		spin_unlock_irq(&t->task_state_lock);
+		spin_unlock_irqrestore(&t->task_state_lock, flags);
 		pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
 		mb();/* ditto */
 		spin_unlock_irq(&pm8001_ha->lock);
 		t->task_done(t);
 		spin_lock_irq(&pm8001_ha->lock);
 	} else if (!t->uldd_task) {
-		spin_unlock_irq(&t->task_state_lock);
+		spin_unlock_irqrestore(&t->task_state_lock, flags);
 		pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
 		mb();/*ditto*/
 		spin_unlock_irq(&pm8001_ha->lock);
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index d838205ab169..6c6486f626ee 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -359,7 +359,6 @@
 #include <asm/byteorder.h>
 #include <asm/processor.h>
 #include <asm/types.h>
-#include <asm/system.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/qla4xxx/ql4_isr.c b/drivers/scsi/qla4xxx/ql4_isr.c
index 7c9f28b7da72..fc542a9bb106 100644
--- a/drivers/scsi/qla4xxx/ql4_isr.c
+++ b/drivers/scsi/qla4xxx/ql4_isr.c
@@ -431,9 +431,9 @@ static void qla4xxx_mbox_status_entry(struct scsi_qla_host *ha,
 				  mbox_sts_entry->out_mbox[6]));
 
 		if (mbox_sts_entry->out_mbox[0] == MBOX_STS_COMMAND_COMPLETE)
-			status = QLA_SUCCESS;
+			status = ISCSI_PING_SUCCESS;
 		else
-			status = QLA_ERROR;
+			status = mbox_sts_entry->out_mbox[6];
 
 		data_size = sizeof(mbox_sts_entry->out_mbox);
 
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 3d9419460e0c..ee47820c30a6 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -834,7 +834,7 @@ static enum blk_eh_timer_return qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc)
 static void qla4xxx_set_port_speed(struct Scsi_Host *shost)
 {
 	struct scsi_qla_host *ha = to_qla_host(shost);
-	struct iscsi_cls_host *ihost = shost_priv(shost);
+	struct iscsi_cls_host *ihost = shost->shost_data;
 	uint32_t speed = ISCSI_PORT_SPEED_UNKNOWN;
 
 	qla4xxx_get_firmware_state(ha);
@@ -859,7 +859,7 @@ static void qla4xxx_set_port_speed(struct Scsi_Host *shost)
 static void qla4xxx_set_port_state(struct Scsi_Host *shost)
 {
 	struct scsi_qla_host *ha = to_qla_host(shost);
-	struct iscsi_cls_host *ihost = shost_priv(shost);
+	struct iscsi_cls_host *ihost = shost->shost_data;
 	uint32_t state = ISCSI_PORT_STATE_DOWN;
 
 	if (test_bit(AF_LINK_UP, &ha->flags))
@@ -3445,7 +3445,6 @@ static void qla4xxx_free_adapter(struct scsi_qla_host *ha)
 int qla4_8xxx_iospace_config(struct scsi_qla_host *ha)
 {
 	int status = 0;
-	uint8_t revision_id;
 	unsigned long mem_base, mem_len, db_base, db_len;
 	struct pci_dev *pdev = ha->pdev;
 
@@ -3457,10 +3456,9 @@ int qla4_8xxx_iospace_config(struct scsi_qla_host *ha)
 		goto iospace_error_exit;
 	}
 
-	pci_read_config_byte(pdev, PCI_REVISION_ID, &revision_id);
 	DEBUG2(printk(KERN_INFO "%s: revision-id=%d\n",
-	    __func__, revision_id));
-	ha->revision_id = revision_id;
+	    __func__, pdev->revision));
+	ha->revision_id = pdev->revision;
 
 	/* remap phys address */
 	mem_base = pci_resource_start(pdev, 0); /* 0 is for BAR 0 */
diff --git a/drivers/scsi/qla4xxx/ql4_version.h b/drivers/scsi/qla4xxx/ql4_version.h
index ede9af944141..97b30c108e36 100644
--- a/drivers/scsi/qla4xxx/ql4_version.h
+++ b/drivers/scsi/qla4xxx/ql4_version.h
@@ -5,4 +5,4 @@
  * See LICENSE.qla4xxx for copyright and licensing details.
  */
 
-#define QLA4XXX_DRIVER_VERSION	"5.02.00-k15"
+#define QLA4XXX_DRIVER_VERSION	"5.02.00-k16"
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index e40dc1cb09a0..b191dd549207 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -35,7 +35,6 @@
 #include "qlogicpti.h"
 
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/ptrace.h>
 #include <asm/pgtable.h>
 #include <asm/oplib.h>
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 591856131c4e..182d5a57ab74 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -101,6 +101,7 @@ static const char * scsi_debug_version_date = "20100324";
 #define DEF_LBPU 0
 #define DEF_LBPWS 0
 #define DEF_LBPWS10 0
+#define DEF_LBPRZ 1
 #define DEF_LOWEST_ALIGNED 0
 #define DEF_NO_LUN_0   0
 #define DEF_NUM_PARTS   0
@@ -186,6 +187,7 @@ static int scsi_debug_vpd_use_hostno = DEF_VPD_USE_HOSTNO;
 static unsigned int scsi_debug_lbpu = DEF_LBPU;
 static unsigned int scsi_debug_lbpws = DEF_LBPWS;
 static unsigned int scsi_debug_lbpws10 = DEF_LBPWS10;
+static unsigned int scsi_debug_lbprz = DEF_LBPRZ;
 static unsigned int scsi_debug_unmap_alignment = DEF_UNMAP_ALIGNMENT;
 static unsigned int scsi_debug_unmap_granularity = DEF_UNMAP_GRANULARITY;
 static unsigned int scsi_debug_unmap_max_blocks = DEF_UNMAP_MAX_BLOCKS;
@@ -775,10 +777,10 @@ static int inquiry_evpd_b1(unsigned char *arr)
 	return 0x3c;
 }
 
-/* Thin provisioning VPD page (SBC-3) */
+/* Logical block provisioning VPD page (SBC-3) */
 static int inquiry_evpd_b2(unsigned char *arr)
 {
-	memset(arr, 0, 0x8);
+	memset(arr, 0, 0x4);
 	arr[0] = 0;			/* threshold exponent */
 
 	if (scsi_debug_lbpu)
@@ -790,7 +792,10 @@ static int inquiry_evpd_b2(unsigned char *arr)
 	if (scsi_debug_lbpws10)
 		arr[1] |= 1 << 5;
 
-	return 0x8;
+	if (scsi_debug_lbprz)
+		arr[1] |= 1 << 2;
+
+	return 0x4;
 }
 
 #define SDEBUG_LONG_INQ_SZ 96
@@ -1071,8 +1076,11 @@ static int resp_readcap16(struct scsi_cmnd * scp,
 	arr[13] = scsi_debug_physblk_exp & 0xf;
 	arr[14] = (scsi_debug_lowest_aligned >> 8) & 0x3f;
 
-	if (scsi_debug_lbp())
+	if (scsi_debug_lbp()) {
 		arr[14] |= 0x80; /* LBPME */
+		if (scsi_debug_lbprz)
+			arr[14] |= 0x40; /* LBPRZ */
+	}
 
 	arr[15] = scsi_debug_lowest_aligned & 0xff;
 
@@ -2046,10 +2054,13 @@ static void unmap_region(sector_t lba, unsigned int len)
 		block = lba + alignment;
 		rem = do_div(block, granularity);
 
-		if (rem == 0 && lba + granularity <= end &&
-		    block < map_size)
+		if (rem == 0 && lba + granularity <= end && block < map_size) {
 			clear_bit(block, map_storep);
-
+			if (scsi_debug_lbprz)
+				memset(fake_storep +
+				       block * scsi_debug_sector_size, 0,
+				       scsi_debug_sector_size);
+		}
 		lba += granularity - rem;
 	}
 }
@@ -2731,6 +2742,7 @@ module_param_named(guard, scsi_debug_guard, int, S_IRUGO);
 module_param_named(lbpu, scsi_debug_lbpu, int, S_IRUGO);
 module_param_named(lbpws, scsi_debug_lbpws, int, S_IRUGO);
 module_param_named(lbpws10, scsi_debug_lbpws10, int, S_IRUGO);
+module_param_named(lbprz, scsi_debug_lbprz, int, S_IRUGO);
 module_param_named(lowest_aligned, scsi_debug_lowest_aligned, int, S_IRUGO);
 module_param_named(max_luns, scsi_debug_max_luns, int, S_IRUGO | S_IWUSR);
 module_param_named(max_queue, scsi_debug_max_queue, int, S_IRUGO | S_IWUSR);
@@ -2772,6 +2784,7 @@ MODULE_PARM_DESC(guard, "protection checksum: 0=crc, 1=ip (def=0)");
 MODULE_PARM_DESC(lbpu, "enable LBP, support UNMAP command (def=0)");
 MODULE_PARM_DESC(lbpws, "enable LBP, support WRITE SAME(16) with UNMAP bit (def=0)");
 MODULE_PARM_DESC(lbpws10, "enable LBP, support WRITE SAME(10) with UNMAP bit (def=0)");
+MODULE_PARM_DESC(lbprz, "unmapped blocks return 0 on read (def=1)");
 MODULE_PARM_DESC(lowest_aligned, "lowest aligned lba (def=0)");
 MODULE_PARM_DESC(max_luns, "number of LUNs per target to simulate(def=1)");
 MODULE_PARM_DESC(max_queue, "max number of queued commands (1 to 255(def))");
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index fac31730addf..1cf640e575da 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1486,7 +1486,7 @@ void iscsi_post_host_event(uint32_t host_no, struct iscsi_transport *transport,
 	struct iscsi_uevent *ev;
 	int len = NLMSG_SPACE(sizeof(*ev) + data_size);
 
-	skb = alloc_skb(len, GFP_KERNEL);
+	skb = alloc_skb(len, GFP_NOIO);
 	if (!skb) {
 		printk(KERN_ERR "gracefully ignored host event (%d):%d OOM\n",
 		       host_no, code);
@@ -1504,7 +1504,7 @@ void iscsi_post_host_event(uint32_t host_no, struct iscsi_transport *transport,
 	if (data_size)
 		memcpy((char *)ev + sizeof(*ev), data, data_size);
 
-	iscsi_multicast_skb(skb, ISCSI_NL_GRP_ISCSID, GFP_KERNEL);
+	iscsi_multicast_skb(skb, ISCSI_NL_GRP_ISCSID, GFP_NOIO);
 }
 EXPORT_SYMBOL_GPL(iscsi_post_host_event);
 
@@ -1517,7 +1517,7 @@ void iscsi_ping_comp_event(uint32_t host_no, struct iscsi_transport *transport,
 	struct iscsi_uevent *ev;
 	int len = NLMSG_SPACE(sizeof(*ev) + data_size);
 
-	skb = alloc_skb(len, GFP_KERNEL);
+	skb = alloc_skb(len, GFP_NOIO);
 	if (!skb) {
 		printk(KERN_ERR "gracefully ignored ping comp: OOM\n");
 		return;
@@ -1533,7 +1533,7 @@ void iscsi_ping_comp_event(uint32_t host_no, struct iscsi_transport *transport,
 	ev->r.ping_comp.data_size = data_size;
 	memcpy((char *)ev + sizeof(*ev), data, data_size);
 
-	iscsi_multicast_skb(skb, ISCSI_NL_GRP_ISCSID, GFP_KERNEL);
+	iscsi_multicast_skb(skb, ISCSI_NL_GRP_ISCSID, GFP_NOIO);
 }
 EXPORT_SYMBOL_GPL(iscsi_ping_comp_event);
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 09e3df42a402..5ba5c2a9e8e9 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -664,7 +664,7 @@ static void sd_unprep_fn(struct request_queue *q, struct request *rq)
 }
 
 /**
- *	sd_init_command - build a scsi (read or write) command from
+ *	sd_prep_fn - build a scsi (read or write) command from
  *	information in the request structure.
  *	@SCpnt: pointer to mid-level's per scsi command structure that
  *	contains request and into which the scsi command is written
@@ -711,7 +711,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 	ret = BLKPREP_KILL;
 
 	SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt,
-					"sd_init_command: block=%llu, "
+					"sd_prep_fn: block=%llu, "
 					"count=%d\n",
 					(unsigned long long)block,
 					this_count));
@@ -1212,9 +1212,14 @@ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
 	retval = -ENODEV;
 
 	if (scsi_block_when_processing_errors(sdp)) {
+		retval = scsi_autopm_get_device(sdp);
+		if (retval)
+			goto out;
+
 		sshdr  = kzalloc(sizeof(*sshdr), GFP_KERNEL);
 		retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, SD_MAX_RETRIES,
 					      sshdr);
+		scsi_autopm_put_device(sdp);
 	}
 
 	/* failed to execute TUR, assume media not present */
@@ -2644,8 +2649,8 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
  *	(e.g. /dev/sda). More precisely it is the block device major 
  *	and minor number that is chosen here.
  *
- *	Assume sd_attach is not re-entrant (for time being)
- *	Also think about sd_attach() and sd_remove() running coincidentally.
+ *	Assume sd_probe is not re-entrant (for time being)
+ *	Also think about sd_probe() and sd_remove() running coincidentally.
  **/
 static int sd_probe(struct device *dev)
 {
@@ -2660,7 +2665,7 @@ static int sd_probe(struct device *dev)
 		goto out;
 
 	SCSI_LOG_HLQUEUE(3, sdev_printk(KERN_INFO, sdp,
-					"sd_attach\n"));
+					"sd_probe\n"));
 
 	error = -ENOMEM;
 	sdkp = kzalloc(sizeof(*sdkp), GFP_KERNEL);
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 9262cdfa4b23..e41998cb098e 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -42,7 +42,6 @@ static const char *verstr = "20101219";
 
 #include <asm/uaccess.h>
 #include <asm/dma.h>
-#include <asm/system.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_dbg.h>
@@ -1106,6 +1105,12 @@ static int check_tape(struct scsi_tape *STp, struct file *filp)
                                     STp->drv_buffer));
 		}
 		STp->drv_write_prot = ((STp->buffer)->b_data[2] & 0x80) != 0;
+		if (!STp->drv_buffer && STp->immediate_filemark) {
+			printk(KERN_WARNING
+			    "%s: non-buffered tape: disabling writing immediate filemarks\n",
+			    name);
+			STp->immediate_filemark = 0;
+		}
 	}
 	st_release_request(SRpnt);
 	SRpnt = NULL;
@@ -1314,6 +1319,8 @@ static int st_flush(struct file *filp, fl_owner_t id)
 
 		memset(cmd, 0, MAX_COMMAND_SIZE);
 		cmd[0] = WRITE_FILEMARKS;
+		if (STp->immediate_filemark)
+			cmd[1] = 1;
 		cmd[4] = 1 + STp->two_fm;
 
 		SRpnt = st_do_scsi(NULL, STp, cmd, 0, DMA_NONE,
@@ -2181,8 +2188,9 @@ static void st_log_options(struct scsi_tape * STp, struct st_modedef * STm, char
 		       name, STm->defaults_for_writes, STp->omit_blklims, STp->can_partitions,
 		       STp->scsi2_logical);
 		printk(KERN_INFO
-		       "%s:    sysv: %d nowait: %d sili: %d\n", name, STm->sysv, STp->immediate,
-			STp->sili);
+		       "%s:    sysv: %d nowait: %d sili: %d nowait_filemark: %d\n",
+		       name, STm->sysv, STp->immediate, STp->sili,
+		       STp->immediate_filemark);
 		printk(KERN_INFO "%s:    debugging: %d\n",
 		       name, debugging);
 	}
@@ -2224,6 +2232,7 @@ static int st_set_options(struct scsi_tape *STp, long options)
 			STp->can_partitions = (options & MT_ST_CAN_PARTITIONS) != 0;
 		STp->scsi2_logical = (options & MT_ST_SCSI2LOGICAL) != 0;
 		STp->immediate = (options & MT_ST_NOWAIT) != 0;
+		STp->immediate_filemark = (options & MT_ST_NOWAIT_EOF) != 0;
 		STm->sysv = (options & MT_ST_SYSV) != 0;
 		STp->sili = (options & MT_ST_SILI) != 0;
 		DEB( debugging = (options & MT_ST_DEBUGGING) != 0;
@@ -2255,6 +2264,8 @@ static int st_set_options(struct scsi_tape *STp, long options)
 			STp->scsi2_logical = value;
 		if ((options & MT_ST_NOWAIT) != 0)
 			STp->immediate = value;
+		if ((options & MT_ST_NOWAIT_EOF) != 0)
+			STp->immediate_filemark = value;
 		if ((options & MT_ST_SYSV) != 0)
 			STm->sysv = value;
 		if ((options & MT_ST_SILI) != 0)
@@ -2714,7 +2725,8 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon
 		cmd[0] = WRITE_FILEMARKS;
 		if (cmd_in == MTWSM)
 			cmd[1] = 2;
-		if (cmd_in == MTWEOFI)
+		if (cmd_in == MTWEOFI ||
+		    (cmd_in == MTWEOF && STp->immediate_filemark))
 			cmd[1] |= 1;
 		cmd[2] = (arg >> 16);
 		cmd[3] = (arg >> 8);
@@ -4093,6 +4105,7 @@ static int st_probe(struct device *dev)
 	tpnt->scsi2_logical = ST_SCSI2LOGICAL;
 	tpnt->sili = ST_SILI;
 	tpnt->immediate = ST_NOWAIT;
+	tpnt->immediate_filemark = 0;
 	tpnt->default_drvbuffer = 0xff;		/* No forced buffering */
 	tpnt->partition = 0;
 	tpnt->new_partition = 0;
@@ -4478,6 +4491,7 @@ st_options_show(struct device *dev, struct device_attribute *attr, char *buf)
 	options |= STp->scsi2_logical ? MT_ST_SCSI2LOGICAL : 0;
 	options |= STm->sysv ? MT_ST_SYSV : 0;
 	options |= STp->immediate ? MT_ST_NOWAIT : 0;
+	options |= STp->immediate_filemark ? MT_ST_NOWAIT_EOF : 0;
 	options |= STp->sili ? MT_ST_SILI : 0;
 
 	l = snprintf(buf, PAGE_SIZE, "0x%08x\n", options);
diff --git a/drivers/scsi/st.h b/drivers/scsi/st.h
index f91a67c6d968..ea35632b986c 100644
--- a/drivers/scsi/st.h
+++ b/drivers/scsi/st.h
@@ -120,6 +120,7 @@ struct scsi_tape {
 	unsigned char c_algo;			/* compression algorithm */
 	unsigned char pos_unknown;			/* after reset position unknown */
 	unsigned char sili;			/* use SILI when reading in variable b mode */
+	unsigned char immediate_filemark;	/* write filemark immediately */
 	int tape_type;
 	int long_timeout;	/* timeout for commands known to take long time */
 
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index baf7328de956..6e25889db9d4 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -63,7 +63,6 @@
 #include <linux/blkdev.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <asm/sun3ints.h>
 #include <asm/dvma.h>
diff --git a/drivers/scsi/sun3_scsi_vme.c b/drivers/scsi/sun3_scsi_vme.c
index fbba78e5722e..a3dd55d1d2fd 100644
--- a/drivers/scsi/sun3_scsi_vme.c
+++ b/drivers/scsi/sun3_scsi_vme.c
@@ -25,7 +25,6 @@
 #include <linux/blkdev.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <asm/sun3ints.h>
 #include <asm/dvma.h>
diff --git a/drivers/scsi/sym53c416.c b/drivers/scsi/sym53c416.c
index 012c86edd59f..ac4eca6a5328 100644
--- a/drivers/scsi/sym53c416.c
+++ b/drivers/scsi/sym53c416.c
@@ -37,7 +37,6 @@
 #include <linux/proc_fs.h>
 #include <linux/spinlock.h>
 #include <asm/dma.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <linux/blkdev.h>
 #include <linux/isapnp.h>
diff --git a/drivers/scsi/t128.c b/drivers/scsi/t128.c
index 041eaaace2c3..d672d97fb84a 100644
--- a/drivers/scsi/t128.c
+++ b/drivers/scsi/t128.c
@@ -106,7 +106,6 @@
  * $Log: t128.c,v $
  */
 
-#include <asm/system.h>
 #include <linux/signal.h>
 #include <linux/io.h>
 #include <linux/blkdev.h>
diff --git a/drivers/scsi/u14-34f.c b/drivers/scsi/u14-34f.c
index 90e104d6b558..9c216e563568 100644
--- a/drivers/scsi/u14-34f.c
+++ b/drivers/scsi/u14-34f.c
@@ -410,7 +410,6 @@
 #include <linux/ioport.h>
 #include <linux/delay.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
diff --git a/drivers/scsi/ufs/Kconfig b/drivers/scsi/ufs/Kconfig
new file mode 100644
index 000000000000..8f27f9d6f91d
--- /dev/null
+++ b/drivers/scsi/ufs/Kconfig
@@ -0,0 +1,49 @@
+#
+# Kernel configuration file for the UFS Host Controller
+#
+# This code is based on drivers/scsi/ufs/Kconfig
+# Copyright (C) 2011  Samsung Samsung India Software Operations
+#
+# Santosh Yaraganavi <santosh.sy@samsung.com>
+# Vinayak Holikatti <h.vinayak@samsung.com>
+
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# NO WARRANTY
+# THE PROGRAM IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OR
+# CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED INCLUDING, WITHOUT
+# LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE, NON-INFRINGEMENT,
+# MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Each Recipient is
+# solely responsible for determining the appropriateness of using and
+# distributing the Program and assumes all risks associated with its
+# exercise of rights under this Agreement, including but not limited to
+# the risks and costs of program errors, damage to or loss of data,
+# programs or equipment, and unavailability or interruption of operations.
+
+# DISCLAIMER OF LIABILITY
+# NEITHER RECIPIENT NOR ANY CONTRIBUTORS SHALL HAVE ANY LIABILITY FOR ANY
+# DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING WITHOUT LIMITATION LOST PROFITS), HOWEVER CAUSED AND
+# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
+# TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+# USE OR DISTRIBUTION OF THE PROGRAM OR THE EXERCISE OF ANY RIGHTS GRANTED
+# HEREUNDER, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGES
+
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301,
+# USA.
+
+config SCSI_UFSHCD
+	tristate "Universal Flash Storage host controller driver"
+	depends on PCI && SCSI
+	---help---
+	This is a generic driver which supports PCIe UFS Host controllers.
diff --git a/drivers/scsi/ufs/Makefile b/drivers/scsi/ufs/Makefile
new file mode 100644
index 000000000000..adf7895a6a91
--- /dev/null
+++ b/drivers/scsi/ufs/Makefile
@@ -0,0 +1,2 @@
+# UFSHCD makefile
+obj-$(CONFIG_SCSI_UFSHCD) += ufshcd.o
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
new file mode 100644
index 000000000000..b207529f8d54
--- /dev/null
+++ b/drivers/scsi/ufs/ufs.h
@@ -0,0 +1,207 @@
+/*
+ * Universal Flash Storage Host controller driver
+ *
+ * This code is based on drivers/scsi/ufs/ufs.h
+ * Copyright (C) 2011-2012 Samsung India Software Operations
+ *
+ * Santosh Yaraganavi <santosh.sy@samsung.com>
+ * Vinayak Holikatti <h.vinayak@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * NO WARRANTY
+ * THE PROGRAM IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OR
+ * CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED INCLUDING, WITHOUT
+ * LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE, NON-INFRINGEMENT,
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Each Recipient is
+ * solely responsible for determining the appropriateness of using and
+ * distributing the Program and assumes all risks associated with its
+ * exercise of rights under this Agreement, including but not limited to
+ * the risks and costs of program errors, damage to or loss of data,
+ * programs or equipment, and unavailability or interruption of operations.
+
+ * DISCLAIMER OF LIABILITY
+ * NEITHER RECIPIENT NOR ANY CONTRIBUTORS SHALL HAVE ANY LIABILITY FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING WITHOUT LIMITATION LOST PROFITS), HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
+ * TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OR DISTRIBUTION OF THE PROGRAM OR THE EXERCISE OF ANY RIGHTS GRANTED
+ * HEREUNDER, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGES
+
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301,
+ * USA.
+ */
+
+#ifndef _UFS_H
+#define _UFS_H
+
+#define MAX_CDB_SIZE	16
+
+#define UPIU_HEADER_DWORD(byte3, byte2, byte1, byte0)\
+			((byte3 << 24) | (byte2 << 16) |\
+			 (byte1 << 8) | (byte0))
+
+/*
+ * UFS Protocol Information Unit related definitions
+ */
+
+/* Task management functions */
+enum {
+	UFS_ABORT_TASK		= 0x01,
+	UFS_ABORT_TASK_SET	= 0x02,
+	UFS_CLEAR_TASK_SET	= 0x04,
+	UFS_LOGICAL_RESET	= 0x08,
+	UFS_QUERY_TASK		= 0x80,
+	UFS_QUERY_TASK_SET	= 0x81,
+};
+
+/* UTP UPIU Transaction Codes Initiator to Target */
+enum {
+	UPIU_TRANSACTION_NOP_OUT	= 0x00,
+	UPIU_TRANSACTION_COMMAND	= 0x01,
+	UPIU_TRANSACTION_DATA_OUT	= 0x02,
+	UPIU_TRANSACTION_TASK_REQ	= 0x04,
+	UPIU_TRANSACTION_QUERY_REQ	= 0x26,
+};
+
+/* UTP UPIU Transaction Codes Target to Initiator */
+enum {
+	UPIU_TRANSACTION_NOP_IN		= 0x20,
+	UPIU_TRANSACTION_RESPONSE	= 0x21,
+	UPIU_TRANSACTION_DATA_IN	= 0x22,
+	UPIU_TRANSACTION_TASK_RSP	= 0x24,
+	UPIU_TRANSACTION_READY_XFER	= 0x31,
+	UPIU_TRANSACTION_QUERY_RSP	= 0x36,
+};
+
+/* UPIU Read/Write flags */
+enum {
+	UPIU_CMD_FLAGS_NONE	= 0x00,
+	UPIU_CMD_FLAGS_WRITE	= 0x20,
+	UPIU_CMD_FLAGS_READ	= 0x40,
+};
+
+/* UPIU Task Attributes */
+enum {
+	UPIU_TASK_ATTR_SIMPLE	= 0x00,
+	UPIU_TASK_ATTR_ORDERED	= 0x01,
+	UPIU_TASK_ATTR_HEADQ	= 0x02,
+	UPIU_TASK_ATTR_ACA	= 0x03,
+};
+
+/* UTP QUERY Transaction Specific Fields OpCode */
+enum {
+	UPIU_QUERY_OPCODE_NOP		= 0x0,
+	UPIU_QUERY_OPCODE_READ_DESC	= 0x1,
+	UPIU_QUERY_OPCODE_WRITE_DESC	= 0x2,
+	UPIU_QUERY_OPCODE_READ_ATTR	= 0x3,
+	UPIU_QUERY_OPCODE_WRITE_ATTR	= 0x4,
+	UPIU_QUERY_OPCODE_READ_FLAG	= 0x5,
+	UPIU_QUERY_OPCODE_SET_FLAG	= 0x6,
+	UPIU_QUERY_OPCODE_CLEAR_FLAG	= 0x7,
+	UPIU_QUERY_OPCODE_TOGGLE_FLAG	= 0x8,
+};
+
+/* UTP Transfer Request Command Type (CT) */
+enum {
+	UPIU_COMMAND_SET_TYPE_SCSI	= 0x0,
+	UPIU_COMMAND_SET_TYPE_UFS	= 0x1,
+	UPIU_COMMAND_SET_TYPE_QUERY	= 0x2,
+};
+
+enum {
+	MASK_SCSI_STATUS	= 0xFF,
+	MASK_TASK_RESPONSE	= 0xFF00,
+	MASK_RSP_UPIU_RESULT	= 0xFFFF,
+};
+
+/* Task management service response */
+enum {
+	UPIU_TASK_MANAGEMENT_FUNC_COMPL		= 0x00,
+	UPIU_TASK_MANAGEMENT_FUNC_NOT_SUPPORTED = 0x04,
+	UPIU_TASK_MANAGEMENT_FUNC_SUCCEEDED	= 0x08,
+	UPIU_TASK_MANAGEMENT_FUNC_FAILED	= 0x05,
+	UPIU_INCORRECT_LOGICAL_UNIT_NO		= 0x09,
+};
+/**
+ * struct utp_upiu_header - UPIU header structure
+ * @dword_0: UPIU header DW-0
+ * @dword_1: UPIU header DW-1
+ * @dword_2: UPIU header DW-2
+ */
+struct utp_upiu_header {
+	u32 dword_0;
+	u32 dword_1;
+	u32 dword_2;
+};
+
+/**
+ * struct utp_upiu_cmd - Command UPIU structure
+ * @header: UPIU header structure DW-0 to DW-2
+ * @data_transfer_len: Data Transfer Length DW-3
+ * @cdb: Command Descriptor Block CDB DW-4 to DW-7
+ */
+struct utp_upiu_cmd {
+	struct utp_upiu_header header;
+	u32 exp_data_transfer_len;
+	u8 cdb[MAX_CDB_SIZE];
+};
+
+/**
+ * struct utp_upiu_rsp - Response UPIU structure
+ * @header: UPIU header DW-0 to DW-2
+ * @residual_transfer_count: Residual transfer count DW-3
+ * @reserved: Reserved double words DW-4 to DW-7
+ * @sense_data_len: Sense data length DW-8 U16
+ * @sense_data: Sense data field DW-8 to DW-12
+ */
+struct utp_upiu_rsp {
+	struct utp_upiu_header header;
+	u32 residual_transfer_count;
+	u32 reserved[4];
+	u16 sense_data_len;
+	u8 sense_data[18];
+};
+
+/**
+ * struct utp_upiu_task_req - Task request UPIU structure
+ * @header - UPIU header structure DW0 to DW-2
+ * @input_param1: Input parameter 1 DW-3
+ * @input_param2: Input parameter 2 DW-4
+ * @input_param3: Input parameter 3 DW-5
+ * @reserved: Reserved double words DW-6 to DW-7
+ */
+struct utp_upiu_task_req {
+	struct utp_upiu_header header;
+	u32 input_param1;
+	u32 input_param2;
+	u32 input_param3;
+	u32 reserved[2];
+};
+
+/**
+ * struct utp_upiu_task_rsp - Task Management Response UPIU structure
+ * @header: UPIU header structure DW0-DW-2
+ * @output_param1: Ouput parameter 1 DW3
+ * @output_param2: Output parameter 2 DW4
+ * @reserved: Reserved double words DW-5 to DW-7
+ */
+struct utp_upiu_task_rsp {
+	struct utp_upiu_header header;
+	u32 output_param1;
+	u32 output_param2;
+	u32 reserved[3];
+};
+
+#endif /* End of Header */
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
new file mode 100644
index 000000000000..52b96e8bf92e
--- /dev/null
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -0,0 +1,1978 @@
+/*
+ * Universal Flash Storage Host controller driver
+ *
+ * This code is based on drivers/scsi/ufs/ufshcd.c
+ * Copyright (C) 2011-2012 Samsung India Software Operations
+ *
+ * Santosh Yaraganavi <santosh.sy@samsung.com>
+ * Vinayak Holikatti <h.vinayak@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * NO WARRANTY
+ * THE PROGRAM IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OR
+ * CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED INCLUDING, WITHOUT
+ * LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE, NON-INFRINGEMENT,
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Each Recipient is
+ * solely responsible for determining the appropriateness of using and
+ * distributing the Program and assumes all risks associated with its
+ * exercise of rights under this Agreement, including but not limited to
+ * the risks and costs of program errors, damage to or loss of data,
+ * programs or equipment, and unavailability or interruption of operations.
+
+ * DISCLAIMER OF LIABILITY
+ * NEITHER RECIPIENT NOR ANY CONTRIBUTORS SHALL HAVE ANY LIABILITY FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING WITHOUT LIMITATION LOST PROFITS), HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
+ * TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OR DISTRIBUTION OF THE PROGRAM OR THE EXERCISE OF ANY RIGHTS GRANTED
+ * HEREUNDER, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGES
+
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301,
+ * USA.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+#include <linux/bitops.h>
+
+#include <asm/irq.h>
+#include <asm/byteorder.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi_tcq.h>
+#include <scsi/scsi_dbg.h>
+#include <scsi/scsi_eh.h>
+
+#include "ufs.h"
+#include "ufshci.h"
+
+#define UFSHCD "ufshcd"
+#define UFSHCD_DRIVER_VERSION "0.1"
+
+enum {
+	UFSHCD_MAX_CHANNEL	= 0,
+	UFSHCD_MAX_ID		= 1,
+	UFSHCD_MAX_LUNS		= 8,
+	UFSHCD_CMD_PER_LUN	= 32,
+	UFSHCD_CAN_QUEUE	= 32,
+};
+
+/* UFSHCD states */
+enum {
+	UFSHCD_STATE_OPERATIONAL,
+	UFSHCD_STATE_RESET,
+	UFSHCD_STATE_ERROR,
+};
+
+/* Interrupt configuration options */
+enum {
+	UFSHCD_INT_DISABLE,
+	UFSHCD_INT_ENABLE,
+	UFSHCD_INT_CLEAR,
+};
+
+/* Interrupt aggregation options */
+enum {
+	INT_AGGR_RESET,
+	INT_AGGR_CONFIG,
+};
+
+/**
+ * struct uic_command - UIC command structure
+ * @command: UIC command
+ * @argument1: UIC command argument 1
+ * @argument2: UIC command argument 2
+ * @argument3: UIC command argument 3
+ * @cmd_active: Indicate if UIC command is outstanding
+ * @result: UIC command result
+ */
+struct uic_command {
+	u32 command;
+	u32 argument1;
+	u32 argument2;
+	u32 argument3;
+	int cmd_active;
+	int result;
+};
+
+/**
+ * struct ufs_hba - per adapter private structure
+ * @mmio_base: UFSHCI base register address
+ * @ucdl_base_addr: UFS Command Descriptor base address
+ * @utrdl_base_addr: UTP Transfer Request Descriptor base address
+ * @utmrdl_base_addr: UTP Task Management Descriptor base address
+ * @ucdl_dma_addr: UFS Command Descriptor DMA address
+ * @utrdl_dma_addr: UTRDL DMA address
+ * @utmrdl_dma_addr: UTMRDL DMA address
+ * @host: Scsi_Host instance of the driver
+ * @pdev: PCI device handle
+ * @lrb: local reference block
+ * @outstanding_tasks: Bits representing outstanding task requests
+ * @outstanding_reqs: Bits representing outstanding transfer requests
+ * @capabilities: UFS Controller Capabilities
+ * @nutrs: Transfer Request Queue depth supported by controller
+ * @nutmrs: Task Management Queue depth supported by controller
+ * @active_uic_cmd: handle of active UIC command
+ * @ufshcd_tm_wait_queue: wait queue for task management
+ * @tm_condition: condition variable for task management
+ * @ufshcd_state: UFSHCD states
+ * @int_enable_mask: Interrupt Mask Bits
+ * @uic_workq: Work queue for UIC completion handling
+ * @feh_workq: Work queue for fatal controller error handling
+ * @errors: HBA errors
+ */
+struct ufs_hba {
+	void __iomem *mmio_base;
+
+	/* Virtual memory reference */
+	struct utp_transfer_cmd_desc *ucdl_base_addr;
+	struct utp_transfer_req_desc *utrdl_base_addr;
+	struct utp_task_req_desc *utmrdl_base_addr;
+
+	/* DMA memory reference */
+	dma_addr_t ucdl_dma_addr;
+	dma_addr_t utrdl_dma_addr;
+	dma_addr_t utmrdl_dma_addr;
+
+	struct Scsi_Host *host;
+	struct pci_dev *pdev;
+
+	struct ufshcd_lrb *lrb;
+
+	unsigned long outstanding_tasks;
+	unsigned long outstanding_reqs;
+
+	u32 capabilities;
+	int nutrs;
+	int nutmrs;
+	u32 ufs_version;
+
+	struct uic_command active_uic_cmd;
+	wait_queue_head_t ufshcd_tm_wait_queue;
+	unsigned long tm_condition;
+
+	u32 ufshcd_state;
+	u32 int_enable_mask;
+
+	/* Work Queues */
+	struct work_struct uic_workq;
+	struct work_struct feh_workq;
+
+	/* HBA Errors */
+	u32 errors;
+};
+
+/**
+ * struct ufshcd_lrb - local reference block
+ * @utr_descriptor_ptr: UTRD address of the command
+ * @ucd_cmd_ptr: UCD address of the command
+ * @ucd_rsp_ptr: Response UPIU address for this command
+ * @ucd_prdt_ptr: PRDT address of the command
+ * @cmd: pointer to SCSI command
+ * @sense_buffer: pointer to sense buffer address of the SCSI command
+ * @sense_bufflen: Length of the sense buffer
+ * @scsi_status: SCSI status of the command
+ * @command_type: SCSI, UFS, Query.
+ * @task_tag: Task tag of the command
+ * @lun: LUN of the command
+ */
+struct ufshcd_lrb {
+	struct utp_transfer_req_desc *utr_descriptor_ptr;
+	struct utp_upiu_cmd *ucd_cmd_ptr;
+	struct utp_upiu_rsp *ucd_rsp_ptr;
+	struct ufshcd_sg_entry *ucd_prdt_ptr;
+
+	struct scsi_cmnd *cmd;
+	u8 *sense_buffer;
+	unsigned int sense_bufflen;
+	int scsi_status;
+
+	int command_type;
+	int task_tag;
+	unsigned int lun;
+};
+
+/**
+ * ufshcd_get_ufs_version - Get the UFS version supported by the HBA
+ * @hba - Pointer to adapter instance
+ *
+ * Returns UFSHCI version supported by the controller
+ */
+static inline u32 ufshcd_get_ufs_version(struct ufs_hba *hba)
+{
+	return readl(hba->mmio_base + REG_UFS_VERSION);
+}
+
+/**
+ * ufshcd_is_device_present - Check if any device connected to
+ *			      the host controller
+ * @reg_hcs - host controller status register value
+ *
+ * Returns 0 if device present, non-zero if no device detected
+ */
+static inline int ufshcd_is_device_present(u32 reg_hcs)
+{
+	return (DEVICE_PRESENT & reg_hcs) ? 0 : -1;
+}
+
+/**
+ * ufshcd_get_tr_ocs - Get the UTRD Overall Command Status
+ * @lrb: pointer to local command reference block
+ *
+ * This function is used to get the OCS field from UTRD
+ * Returns the OCS field in the UTRD
+ */
+static inline int ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp)
+{
+	return lrbp->utr_descriptor_ptr->header.dword_2 & MASK_OCS;
+}
+
+/**
+ * ufshcd_get_tmr_ocs - Get the UTMRD Overall Command Status
+ * @task_req_descp: pointer to utp_task_req_desc structure
+ *
+ * This function is used to get the OCS field from UTMRD
+ * Returns the OCS field in the UTMRD
+ */
+static inline int
+ufshcd_get_tmr_ocs(struct utp_task_req_desc *task_req_descp)
+{
+	return task_req_descp->header.dword_2 & MASK_OCS;
+}
+
+/**
+ * ufshcd_get_tm_free_slot - get a free slot for task management request
+ * @hba: per adapter instance
+ *
+ * Returns maximum number of task management request slots in case of
+ * task management queue full or returns the free slot number
+ */
+static inline int ufshcd_get_tm_free_slot(struct ufs_hba *hba)
+{
+	return find_first_zero_bit(&hba->outstanding_tasks, hba->nutmrs);
+}
+
+/**
+ * ufshcd_utrl_clear - Clear a bit in UTRLCLR register
+ * @hba: per adapter instance
+ * @pos: position of the bit to be cleared
+ */
+static inline void ufshcd_utrl_clear(struct ufs_hba *hba, u32 pos)
+{
+	writel(~(1 << pos),
+		(hba->mmio_base + REG_UTP_TRANSFER_REQ_LIST_CLEAR));
+}
+
+/**
+ * ufshcd_get_lists_status - Check UCRDY, UTRLRDY and UTMRLRDY
+ * @reg: Register value of host controller status
+ *
+ * Returns integer, 0 on Success and positive value if failed
+ */
+static inline int ufshcd_get_lists_status(u32 reg)
+{
+	/*
+	 * The mask 0xFF is for the following HCS register bits
+	 * Bit		Description
+	 *  0		Device Present
+	 *  1		UTRLRDY
+	 *  2		UTMRLRDY
+	 *  3		UCRDY
+	 *  4		HEI
+	 *  5		DEI
+	 * 6-7		reserved
+	 */
+	return (((reg) & (0xFF)) >> 1) ^ (0x07);
+}
+
+/**
+ * ufshcd_get_uic_cmd_result - Get the UIC command result
+ * @hba: Pointer to adapter instance
+ *
+ * This function gets the result of UIC command completion
+ * Returns 0 on success, non zero value on error
+ */
+static inline int ufshcd_get_uic_cmd_result(struct ufs_hba *hba)
+{
+	return readl(hba->mmio_base + REG_UIC_COMMAND_ARG_2) &
+	       MASK_UIC_COMMAND_RESULT;
+}
+
+/**
+ * ufshcd_free_hba_memory - Free allocated memory for LRB, request
+ *			    and task lists
+ * @hba: Pointer to adapter instance
+ */
+static inline void ufshcd_free_hba_memory(struct ufs_hba *hba)
+{
+	size_t utmrdl_size, utrdl_size, ucdl_size;
+
+	kfree(hba->lrb);
+
+	if (hba->utmrdl_base_addr) {
+		utmrdl_size = sizeof(struct utp_task_req_desc) * hba->nutmrs;
+		dma_free_coherent(&hba->pdev->dev, utmrdl_size,
+				  hba->utmrdl_base_addr, hba->utmrdl_dma_addr);
+	}
+
+	if (hba->utrdl_base_addr) {
+		utrdl_size =
+		(sizeof(struct utp_transfer_req_desc) * hba->nutrs);
+		dma_free_coherent(&hba->pdev->dev, utrdl_size,
+				  hba->utrdl_base_addr, hba->utrdl_dma_addr);
+	}
+
+	if (hba->ucdl_base_addr) {
+		ucdl_size =
+		(sizeof(struct utp_transfer_cmd_desc) * hba->nutrs);
+		dma_free_coherent(&hba->pdev->dev, ucdl_size,
+				  hba->ucdl_base_addr, hba->ucdl_dma_addr);
+	}
+}
+
+/**
+ * ufshcd_is_valid_req_rsp - checks if controller TR response is valid
+ * @ucd_rsp_ptr: pointer to response UPIU
+ *
+ * This function checks the response UPIU for valid transaction type in
+ * response field
+ * Returns 0 on success, non-zero on failure
+ */
+static inline int
+ufshcd_is_valid_req_rsp(struct utp_upiu_rsp *ucd_rsp_ptr)
+{
+	return ((be32_to_cpu(ucd_rsp_ptr->header.dword_0) >> 24) ==
+		 UPIU_TRANSACTION_RESPONSE) ? 0 : DID_ERROR << 16;
+}
+
+/**
+ * ufshcd_get_rsp_upiu_result - Get the result from response UPIU
+ * @ucd_rsp_ptr: pointer to response UPIU
+ *
+ * This function gets the response status and scsi_status from response UPIU
+ * Returns the response result code.
+ */
+static inline int
+ufshcd_get_rsp_upiu_result(struct utp_upiu_rsp *ucd_rsp_ptr)
+{
+	return be32_to_cpu(ucd_rsp_ptr->header.dword_1) & MASK_RSP_UPIU_RESULT;
+}
+
+/**
+ * ufshcd_config_int_aggr - Configure interrupt aggregation values.
+ *		Currently there is no use case where we want to configure
+ *		interrupt aggregation dynamically. So to configure interrupt
+ *		aggregation, #define INT_AGGR_COUNTER_THRESHOLD_VALUE and
+ *		INT_AGGR_TIMEOUT_VALUE are used.
+ * @hba: per adapter instance
+ * @option: Interrupt aggregation option
+ */
+static inline void
+ufshcd_config_int_aggr(struct ufs_hba *hba, int option)
+{
+	switch (option) {
+	case INT_AGGR_RESET:
+		writel((INT_AGGR_ENABLE |
+			INT_AGGR_COUNTER_AND_TIMER_RESET),
+			(hba->mmio_base +
+			 REG_UTP_TRANSFER_REQ_INT_AGG_CONTROL));
+		break;
+	case INT_AGGR_CONFIG:
+		writel((INT_AGGR_ENABLE |
+			INT_AGGR_PARAM_WRITE |
+			INT_AGGR_COUNTER_THRESHOLD_VALUE |
+			INT_AGGR_TIMEOUT_VALUE),
+			(hba->mmio_base +
+			 REG_UTP_TRANSFER_REQ_INT_AGG_CONTROL));
+		break;
+	}
+}
+
+/**
+ * ufshcd_enable_run_stop_reg - Enable run-stop registers,
+ *			When run-stop registers are set to 1, it indicates the
+ *			host controller that it can process the requests
+ * @hba: per adapter instance
+ */
+static void ufshcd_enable_run_stop_reg(struct ufs_hba *hba)
+{
+	writel(UTP_TASK_REQ_LIST_RUN_STOP_BIT,
+	       (hba->mmio_base +
+		REG_UTP_TASK_REQ_LIST_RUN_STOP));
+	writel(UTP_TRANSFER_REQ_LIST_RUN_STOP_BIT,
+	       (hba->mmio_base +
+		REG_UTP_TRANSFER_REQ_LIST_RUN_STOP));
+}
+
+/**
+ * ufshcd_hba_stop - Send controller to reset state
+ * @hba: per adapter instance
+ */
+static inline void ufshcd_hba_stop(struct ufs_hba *hba)
+{
+	writel(CONTROLLER_DISABLE, (hba->mmio_base + REG_CONTROLLER_ENABLE));
+}
+
+/**
+ * ufshcd_hba_start - Start controller initialization sequence
+ * @hba: per adapter instance
+ */
+static inline void ufshcd_hba_start(struct ufs_hba *hba)
+{
+	writel(CONTROLLER_ENABLE , (hba->mmio_base + REG_CONTROLLER_ENABLE));
+}
+
+/**
+ * ufshcd_is_hba_active - Get controller state
+ * @hba: per adapter instance
+ *
+ * Returns zero if controller is active, 1 otherwise
+ */
+static inline int ufshcd_is_hba_active(struct ufs_hba *hba)
+{
+	return (readl(hba->mmio_base + REG_CONTROLLER_ENABLE) & 0x1) ? 0 : 1;
+}
+
+/**
+ * ufshcd_send_command - Send SCSI or device management commands
+ * @hba: per adapter instance
+ * @task_tag: Task tag of the command
+ */
+static inline
+void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
+{
+	__set_bit(task_tag, &hba->outstanding_reqs);
+	writel((1 << task_tag),
+	       (hba->mmio_base + REG_UTP_TRANSFER_REQ_DOOR_BELL));
+}
+
+/**
+ * ufshcd_copy_sense_data - Copy sense data in case of check condition
+ * @lrb - pointer to local reference block
+ */
+static inline void ufshcd_copy_sense_data(struct ufshcd_lrb *lrbp)
+{
+	int len;
+	if (lrbp->sense_buffer) {
+		len = be16_to_cpu(lrbp->ucd_rsp_ptr->sense_data_len);
+		memcpy(lrbp->sense_buffer,
+			lrbp->ucd_rsp_ptr->sense_data,
+			min_t(int, len, SCSI_SENSE_BUFFERSIZE));
+	}
+}
+
+/**
+ * ufshcd_hba_capabilities - Read controller capabilities
+ * @hba: per adapter instance
+ */
+static inline void ufshcd_hba_capabilities(struct ufs_hba *hba)
+{
+	hba->capabilities =
+		readl(hba->mmio_base + REG_CONTROLLER_CAPABILITIES);
+
+	/* nutrs and nutmrs are 0 based values */
+	hba->nutrs = (hba->capabilities & MASK_TRANSFER_REQUESTS_SLOTS) + 1;
+	hba->nutmrs =
+	((hba->capabilities & MASK_TASK_MANAGEMENT_REQUEST_SLOTS) >> 16) + 1;
+}
+
+/**
+ * ufshcd_send_uic_command - Send UIC commands to unipro layers
+ * @hba: per adapter instance
+ * @uic_command: UIC command
+ */
+static inline void
+ufshcd_send_uic_command(struct ufs_hba *hba, struct uic_command *uic_cmnd)
+{
+	/* Write Args */
+	writel(uic_cmnd->argument1,
+	      (hba->mmio_base + REG_UIC_COMMAND_ARG_1));
+	writel(uic_cmnd->argument2,
+	      (hba->mmio_base + REG_UIC_COMMAND_ARG_2));
+	writel(uic_cmnd->argument3,
+	      (hba->mmio_base + REG_UIC_COMMAND_ARG_3));
+
+	/* Write UIC Cmd */
+	writel((uic_cmnd->command & COMMAND_OPCODE_MASK),
+	       (hba->mmio_base + REG_UIC_COMMAND));
+}
+
+/**
+ * ufshcd_map_sg - Map scatter-gather list to prdt
+ * @lrbp - pointer to local reference block
+ *
+ * Returns 0 in case of success, non-zero value in case of failure
+ */
+static int ufshcd_map_sg(struct ufshcd_lrb *lrbp)
+{
+	struct ufshcd_sg_entry *prd_table;
+	struct scatterlist *sg;
+	struct scsi_cmnd *cmd;
+	int sg_segments;
+	int i;
+
+	cmd = lrbp->cmd;
+	sg_segments = scsi_dma_map(cmd);
+	if (sg_segments < 0)
+		return sg_segments;
+
+	if (sg_segments) {
+		lrbp->utr_descriptor_ptr->prd_table_length =
+					cpu_to_le16((u16) (sg_segments));
+
+		prd_table = (struct ufshcd_sg_entry *)lrbp->ucd_prdt_ptr;
+
+		scsi_for_each_sg(cmd, sg, sg_segments, i) {
+			prd_table[i].size  =
+				cpu_to_le32(((u32) sg_dma_len(sg))-1);
+			prd_table[i].base_addr =
+				cpu_to_le32(lower_32_bits(sg->dma_address));
+			prd_table[i].upper_addr =
+				cpu_to_le32(upper_32_bits(sg->dma_address));
+		}
+	} else {
+		lrbp->utr_descriptor_ptr->prd_table_length = 0;
+	}
+
+	return 0;
+}
+
+/**
+ * ufshcd_int_config - enable/disable interrupts
+ * @hba: per adapter instance
+ * @option: interrupt option
+ */
+static void ufshcd_int_config(struct ufs_hba *hba, u32 option)
+{
+	switch (option) {
+	case UFSHCD_INT_ENABLE:
+		writel(hba->int_enable_mask,
+		      (hba->mmio_base + REG_INTERRUPT_ENABLE));
+		break;
+	case UFSHCD_INT_DISABLE:
+		if (hba->ufs_version == UFSHCI_VERSION_10)
+			writel(INTERRUPT_DISABLE_MASK_10,
+			      (hba->mmio_base + REG_INTERRUPT_ENABLE));
+		else
+			writel(INTERRUPT_DISABLE_MASK_11,
+			       (hba->mmio_base + REG_INTERRUPT_ENABLE));
+		break;
+	}
+}
+
+/**
+ * ufshcd_compose_upiu - form UFS Protocol Information Unit(UPIU)
+ * @lrb - pointer to local reference block
+ */
+static void ufshcd_compose_upiu(struct ufshcd_lrb *lrbp)
+{
+	struct utp_transfer_req_desc *req_desc;
+	struct utp_upiu_cmd *ucd_cmd_ptr;
+	u32 data_direction;
+	u32 upiu_flags;
+
+	ucd_cmd_ptr = lrbp->ucd_cmd_ptr;
+	req_desc = lrbp->utr_descriptor_ptr;
+
+	switch (lrbp->command_type) {
+	case UTP_CMD_TYPE_SCSI:
+		if (lrbp->cmd->sc_data_direction == DMA_FROM_DEVICE) {
+			data_direction = UTP_DEVICE_TO_HOST;
+			upiu_flags = UPIU_CMD_FLAGS_READ;
+		} else if (lrbp->cmd->sc_data_direction == DMA_TO_DEVICE) {
+			data_direction = UTP_HOST_TO_DEVICE;
+			upiu_flags = UPIU_CMD_FLAGS_WRITE;
+		} else {
+			data_direction = UTP_NO_DATA_TRANSFER;
+			upiu_flags = UPIU_CMD_FLAGS_NONE;
+		}
+
+		/* Transfer request descriptor header fields */
+		req_desc->header.dword_0 =
+			cpu_to_le32(data_direction | UTP_SCSI_COMMAND);
+
+		/*
+		 * assigning invalid value for command status. Controller
+		 * updates OCS on command completion, with the command
+		 * status
+		 */
+		req_desc->header.dword_2 =
+			cpu_to_le32(OCS_INVALID_COMMAND_STATUS);
+
+		/* command descriptor fields */
+		ucd_cmd_ptr->header.dword_0 =
+			cpu_to_be32(UPIU_HEADER_DWORD(UPIU_TRANSACTION_COMMAND,
+						      upiu_flags,
+						      lrbp->lun,
+						      lrbp->task_tag));
+		ucd_cmd_ptr->header.dword_1 =
+			cpu_to_be32(
+				UPIU_HEADER_DWORD(UPIU_COMMAND_SET_TYPE_SCSI,
+						  0,
+						  0,
+						  0));
+
+		/* Total EHS length and Data segment length will be zero */
+		ucd_cmd_ptr->header.dword_2 = 0;
+
+		ucd_cmd_ptr->exp_data_transfer_len =
+			cpu_to_be32(lrbp->cmd->transfersize);
+
+		memcpy(ucd_cmd_ptr->cdb,
+		       lrbp->cmd->cmnd,
+		       (min_t(unsigned short,
+			      lrbp->cmd->cmd_len,
+			      MAX_CDB_SIZE)));
+		break;
+	case UTP_CMD_TYPE_DEV_MANAGE:
+		/* For query function implementation */
+		break;
+	case UTP_CMD_TYPE_UFS:
+		/* For UFS native command implementation */
+		break;
+	} /* end of switch */
+}
+
+/**
+ * ufshcd_queuecommand - main entry point for SCSI requests
+ * @cmd: command from SCSI Midlayer
+ * @done: call back function
+ *
+ * Returns 0 for success, non-zero in case of failure
+ */
+static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
+{
+	struct ufshcd_lrb *lrbp;
+	struct ufs_hba *hba;
+	unsigned long flags;
+	int tag;
+	int err = 0;
+
+	hba = shost_priv(host);
+
+	tag = cmd->request->tag;
+
+	if (hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL) {
+		err = SCSI_MLQUEUE_HOST_BUSY;
+		goto out;
+	}
+
+	lrbp = &hba->lrb[tag];
+
+	lrbp->cmd = cmd;
+	lrbp->sense_bufflen = SCSI_SENSE_BUFFERSIZE;
+	lrbp->sense_buffer = cmd->sense_buffer;
+	lrbp->task_tag = tag;
+	lrbp->lun = cmd->device->lun;
+
+	lrbp->command_type = UTP_CMD_TYPE_SCSI;
+
+	/* form UPIU before issuing the command */
+	ufshcd_compose_upiu(lrbp);
+	err = ufshcd_map_sg(lrbp);
+	if (err)
+		goto out;
+
+	/* issue command to the controller */
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_send_command(hba, tag);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+out:
+	return err;
+}
+
+/**
+ * ufshcd_memory_alloc - allocate memory for host memory space data structures
+ * @hba: per adapter instance
+ *
+ * 1. Allocate DMA memory for Command Descriptor array
+ *	Each command descriptor consist of Command UPIU, Response UPIU and PRDT
+ * 2. Allocate DMA memory for UTP Transfer Request Descriptor List (UTRDL).
+ * 3. Allocate DMA memory for UTP Task Management Request Descriptor List
+ *	(UTMRDL)
+ * 4. Allocate memory for local reference block(lrb).
+ *
+ * Returns 0 for success, non-zero in case of failure
+ */
+static int ufshcd_memory_alloc(struct ufs_hba *hba)
+{
+	size_t utmrdl_size, utrdl_size, ucdl_size;
+
+	/* Allocate memory for UTP command descriptors */
+	ucdl_size = (sizeof(struct utp_transfer_cmd_desc) * hba->nutrs);
+	hba->ucdl_base_addr = dma_alloc_coherent(&hba->pdev->dev,
+						 ucdl_size,
+						 &hba->ucdl_dma_addr,
+						 GFP_KERNEL);
+
+	/*
+	 * UFSHCI requires UTP command descriptor to be 128 byte aligned.
+	 * make sure hba->ucdl_dma_addr is aligned to PAGE_SIZE
+	 * if hba->ucdl_dma_addr is aligned to PAGE_SIZE, then it will
+	 * be aligned to 128 bytes as well
+	 */
+	if (!hba->ucdl_base_addr ||
+	    WARN_ON(hba->ucdl_dma_addr & (PAGE_SIZE - 1))) {
+		dev_err(&hba->pdev->dev,
+			"Command Descriptor Memory allocation failed\n");
+		goto out;
+	}
+
+	/*
+	 * Allocate memory for UTP Transfer descriptors
+	 * UFSHCI requires 1024 byte alignment of UTRD
+	 */
+	utrdl_size = (sizeof(struct utp_transfer_req_desc) * hba->nutrs);
+	hba->utrdl_base_addr = dma_alloc_coherent(&hba->pdev->dev,
+						  utrdl_size,
+						  &hba->utrdl_dma_addr,
+						  GFP_KERNEL);
+	if (!hba->utrdl_base_addr ||
+	    WARN_ON(hba->utrdl_dma_addr & (PAGE_SIZE - 1))) {
+		dev_err(&hba->pdev->dev,
+			"Transfer Descriptor Memory allocation failed\n");
+		goto out;
+	}
+
+	/*
+	 * Allocate memory for UTP Task Management descriptors
+	 * UFSHCI requires 1024 byte alignment of UTMRD
+	 */
+	utmrdl_size = sizeof(struct utp_task_req_desc) * hba->nutmrs;
+	hba->utmrdl_base_addr = dma_alloc_coherent(&hba->pdev->dev,
+						   utmrdl_size,
+						   &hba->utmrdl_dma_addr,
+						   GFP_KERNEL);
+	if (!hba->utmrdl_base_addr ||
+	    WARN_ON(hba->utmrdl_dma_addr & (PAGE_SIZE - 1))) {
+		dev_err(&hba->pdev->dev,
+		"Task Management Descriptor Memory allocation failed\n");
+		goto out;
+	}
+
+	/* Allocate memory for local reference block */
+	hba->lrb = kcalloc(hba->nutrs, sizeof(struct ufshcd_lrb), GFP_KERNEL);
+	if (!hba->lrb) {
+		dev_err(&hba->pdev->dev, "LRB Memory allocation failed\n");
+		goto out;
+	}
+	return 0;
+out:
+	ufshcd_free_hba_memory(hba);
+	return -ENOMEM;
+}
+
+/**
+ * ufshcd_host_memory_configure - configure local reference block with
+ *				memory offsets
+ * @hba: per adapter instance
+ *
+ * Configure Host memory space
+ * 1. Update Corresponding UTRD.UCDBA and UTRD.UCDBAU with UCD DMA
+ * address.
+ * 2. Update each UTRD with Response UPIU offset, Response UPIU length
+ * and PRDT offset.
+ * 3. Save the corresponding addresses of UTRD, UCD.CMD, UCD.RSP and UCD.PRDT
+ * into local reference block.
+ */
+static void ufshcd_host_memory_configure(struct ufs_hba *hba)
+{
+	struct utp_transfer_cmd_desc *cmd_descp;
+	struct utp_transfer_req_desc *utrdlp;
+	dma_addr_t cmd_desc_dma_addr;
+	dma_addr_t cmd_desc_element_addr;
+	u16 response_offset;
+	u16 prdt_offset;
+	int cmd_desc_size;
+	int i;
+
+	utrdlp = hba->utrdl_base_addr;
+	cmd_descp = hba->ucdl_base_addr;
+
+	response_offset =
+		offsetof(struct utp_transfer_cmd_desc, response_upiu);
+	prdt_offset =
+		offsetof(struct utp_transfer_cmd_desc, prd_table);
+
+	cmd_desc_size = sizeof(struct utp_transfer_cmd_desc);
+	cmd_desc_dma_addr = hba->ucdl_dma_addr;
+
+	for (i = 0; i < hba->nutrs; i++) {
+		/* Configure UTRD with command descriptor base address */
+		cmd_desc_element_addr =
+				(cmd_desc_dma_addr + (cmd_desc_size * i));
+		utrdlp[i].command_desc_base_addr_lo =
+				cpu_to_le32(lower_32_bits(cmd_desc_element_addr));
+		utrdlp[i].command_desc_base_addr_hi =
+				cpu_to_le32(upper_32_bits(cmd_desc_element_addr));
+
+		/* Response upiu and prdt offset should be in double words */
+		utrdlp[i].response_upiu_offset =
+				cpu_to_le16((response_offset >> 2));
+		utrdlp[i].prd_table_offset =
+				cpu_to_le16((prdt_offset >> 2));
+		utrdlp[i].response_upiu_length =
+				cpu_to_le16(ALIGNED_UPIU_SIZE);
+
+		hba->lrb[i].utr_descriptor_ptr = (utrdlp + i);
+		hba->lrb[i].ucd_cmd_ptr =
+			(struct utp_upiu_cmd *)(cmd_descp + i);
+		hba->lrb[i].ucd_rsp_ptr =
+			(struct utp_upiu_rsp *)cmd_descp[i].response_upiu;
+		hba->lrb[i].ucd_prdt_ptr =
+			(struct ufshcd_sg_entry *)cmd_descp[i].prd_table;
+	}
+}
+
+/**
+ * ufshcd_dme_link_startup - Notify Unipro to perform link startup
+ * @hba: per adapter instance
+ *
+ * UIC_CMD_DME_LINK_STARTUP command must be issued to Unipro layer,
+ * in order to initialize the Unipro link startup procedure.
+ * Once the Unipro links are up, the device connected to the controller
+ * is detected.
+ *
+ * Returns 0 on success, non-zero value on failure
+ */
+static int ufshcd_dme_link_startup(struct ufs_hba *hba)
+{
+	struct uic_command *uic_cmd;
+	unsigned long flags;
+
+	/* check if controller is ready to accept UIC commands */
+	if (((readl(hba->mmio_base + REG_CONTROLLER_STATUS)) &
+	    UIC_COMMAND_READY) == 0x0) {
+		dev_err(&hba->pdev->dev,
+			"Controller not ready"
+			" to accept UIC commands\n");
+		return -EIO;
+	}
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+
+	/* form UIC command */
+	uic_cmd = &hba->active_uic_cmd;
+	uic_cmd->command = UIC_CMD_DME_LINK_STARTUP;
+	uic_cmd->argument1 = 0;
+	uic_cmd->argument2 = 0;
+	uic_cmd->argument3 = 0;
+
+	/* enable UIC related interrupts */
+	hba->int_enable_mask |= UIC_COMMAND_COMPL;
+	ufshcd_int_config(hba, UFSHCD_INT_ENABLE);
+
+	/* sending UIC commands to controller */
+	ufshcd_send_uic_command(hba, uic_cmd);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	return 0;
+}
+
+/**
+ * ufshcd_make_hba_operational - Make UFS controller operational
+ * @hba: per adapter instance
+ *
+ * To bring UFS host controller to operational state,
+ * 1. Check if device is present
+ * 2. Configure run-stop-registers
+ * 3. Enable required interrupts
+ * 4. Configure interrupt aggregation
+ *
+ * Returns 0 on success, non-zero value on failure
+ */
+static int ufshcd_make_hba_operational(struct ufs_hba *hba)
+{
+	int err = 0;
+	u32 reg;
+
+	/* check if device present */
+	reg = readl((hba->mmio_base + REG_CONTROLLER_STATUS));
+	if (ufshcd_is_device_present(reg)) {
+		dev_err(&hba->pdev->dev, "cc: Device not present\n");
+		err = -ENXIO;
+		goto out;
+	}
+
+	/*
+	 * UCRDY, UTMRLDY and UTRLRDY bits must be 1
+	 * DEI, HEI bits must be 0
+	 */
+	if (!(ufshcd_get_lists_status(reg))) {
+		ufshcd_enable_run_stop_reg(hba);
+	} else {
+		dev_err(&hba->pdev->dev,
+			"Host controller not ready to process requests");
+		err = -EIO;
+		goto out;
+	}
+
+	/* Enable required interrupts */
+	hba->int_enable_mask |= (UTP_TRANSFER_REQ_COMPL |
+				 UIC_ERROR |
+				 UTP_TASK_REQ_COMPL |
+				 DEVICE_FATAL_ERROR |
+				 CONTROLLER_FATAL_ERROR |
+				 SYSTEM_BUS_FATAL_ERROR);
+	ufshcd_int_config(hba, UFSHCD_INT_ENABLE);
+
+	/* Configure interrupt aggregation */
+	ufshcd_config_int_aggr(hba, INT_AGGR_CONFIG);
+
+	if (hba->ufshcd_state == UFSHCD_STATE_RESET)
+		scsi_unblock_requests(hba->host);
+
+	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
+	scsi_scan_host(hba->host);
+out:
+	return err;
+}
+
+/**
+ * ufshcd_hba_enable - initialize the controller
+ * @hba: per adapter instance
+ *
+ * The controller resets itself and controller firmware initialization
+ * sequence kicks off. When controller is ready it will set
+ * the Host Controller Enable bit to 1.
+ *
+ * Returns 0 on success, non-zero value on failure
+ */
+static int ufshcd_hba_enable(struct ufs_hba *hba)
+{
+	int retry;
+
+	/*
+	 * msleep of 1 and 5 used in this function might result in msleep(20),
+	 * but it was necessary to send the UFS FPGA to reset mode during
+	 * development and testing of this driver. msleep can be changed to
+	 * mdelay and retry count can be reduced based on the controller.
+	 */
+	if (!ufshcd_is_hba_active(hba)) {
+
+		/* change controller state to "reset state" */
+		ufshcd_hba_stop(hba);
+
+		/*
+		 * This delay is based on the testing done with UFS host
+		 * controller FPGA. The delay can be changed based on the
+		 * host controller used.
+		 */
+		msleep(5);
+	}
+
+	/* start controller initialization sequence */
+	ufshcd_hba_start(hba);
+
+	/*
+	 * To initialize a UFS host controller HCE bit must be set to 1.
+	 * During initialization the HCE bit value changes from 1->0->1.
+	 * When the host controller completes initialization sequence
+	 * it sets the value of HCE bit to 1. The same HCE bit is read back
+	 * to check if the controller has completed initialization sequence.
+	 * So without this delay the value HCE = 1, set in the previous
+	 * instruction might be read back.
+	 * This delay can be changed based on the controller.
+	 */
+	msleep(1);
+
+	/* wait for the host controller to complete initialization */
+	retry = 10;
+	while (ufshcd_is_hba_active(hba)) {
+		if (retry) {
+			retry--;
+		} else {
+			dev_err(&hba->pdev->dev,
+				"Controller enable failed\n");
+			return -EIO;
+		}
+		msleep(5);
+	}
+	return 0;
+}
+
+/**
+ * ufshcd_initialize_hba - start the initialization process
+ * @hba: per adapter instance
+ *
+ * 1. Enable the controller via ufshcd_hba_enable.
+ * 2. Program the Transfer Request List Address with the starting address of
+ * UTRDL.
+ * 3. Program the Task Management Request List Address with starting address
+ * of UTMRDL.
+ *
+ * Returns 0 on success, non-zero value on failure.
+ */
+static int ufshcd_initialize_hba(struct ufs_hba *hba)
+{
+	if (ufshcd_hba_enable(hba))
+		return -EIO;
+
+	/* Configure UTRL and UTMRL base address registers */
+	writel(hba->utrdl_dma_addr,
+	       (hba->mmio_base + REG_UTP_TRANSFER_REQ_LIST_BASE_L));
+	writel(lower_32_bits(hba->utrdl_dma_addr),
+	       (hba->mmio_base + REG_UTP_TRANSFER_REQ_LIST_BASE_H));
+	writel(hba->utmrdl_dma_addr,
+	       (hba->mmio_base + REG_UTP_TASK_REQ_LIST_BASE_L));
+	writel(upper_32_bits(hba->utmrdl_dma_addr),
+	       (hba->mmio_base + REG_UTP_TASK_REQ_LIST_BASE_H));
+
+	/* Initialize unipro link startup procedure */
+	return ufshcd_dme_link_startup(hba);
+}
+
+/**
+ * ufshcd_do_reset - reset the host controller
+ * @hba: per adapter instance
+ *
+ * Returns SUCCESS/FAILED
+ */
+static int ufshcd_do_reset(struct ufs_hba *hba)
+{
+	struct ufshcd_lrb *lrbp;
+	unsigned long flags;
+	int tag;
+
+	/* block commands from midlayer */
+	scsi_block_requests(hba->host);
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	hba->ufshcd_state = UFSHCD_STATE_RESET;
+
+	/* send controller to reset state */
+	ufshcd_hba_stop(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	/* abort outstanding commands */
+	for (tag = 0; tag < hba->nutrs; tag++) {
+		if (test_bit(tag, &hba->outstanding_reqs)) {
+			lrbp = &hba->lrb[tag];
+			scsi_dma_unmap(lrbp->cmd);
+			lrbp->cmd->result = DID_RESET << 16;
+			lrbp->cmd->scsi_done(lrbp->cmd);
+			lrbp->cmd = NULL;
+		}
+	}
+
+	/* clear outstanding request/task bit maps */
+	hba->outstanding_reqs = 0;
+	hba->outstanding_tasks = 0;
+
+	/* start the initialization process */
+	if (ufshcd_initialize_hba(hba)) {
+		dev_err(&hba->pdev->dev,
+			"Reset: Controller initialization failed\n");
+		return FAILED;
+	}
+	return SUCCESS;
+}
+
+/**
+ * ufshcd_slave_alloc - handle initial SCSI device configurations
+ * @sdev: pointer to SCSI device
+ *
+ * Returns success
+ */
+static int ufshcd_slave_alloc(struct scsi_device *sdev)
+{
+	struct ufs_hba *hba;
+
+	hba = shost_priv(sdev->host);
+	sdev->tagged_supported = 1;
+
+	/* Mode sense(6) is not supported by UFS, so use Mode sense(10) */
+	sdev->use_10_for_ms = 1;
+	scsi_set_tag_type(sdev, MSG_SIMPLE_TAG);
+
+	/*
+	 * Inform SCSI Midlayer that the LUN queue depth is same as the
+	 * controller queue depth. If a LUN queue depth is less than the
+	 * controller queue depth and if the LUN reports
+	 * SAM_STAT_TASK_SET_FULL, the LUN queue depth will be adjusted
+	 * with scsi_adjust_queue_depth.
+	 */
+	scsi_activate_tcq(sdev, hba->nutrs);
+	return 0;
+}
+
+/**
+ * ufshcd_slave_destroy - remove SCSI device configurations
+ * @sdev: pointer to SCSI device
+ */
+static void ufshcd_slave_destroy(struct scsi_device *sdev)
+{
+	struct ufs_hba *hba;
+
+	hba = shost_priv(sdev->host);
+	scsi_deactivate_tcq(sdev, hba->nutrs);
+}
+
+/**
+ * ufshcd_task_req_compl - handle task management request completion
+ * @hba: per adapter instance
+ * @index: index of the completed request
+ *
+ * Returns SUCCESS/FAILED
+ */
+static int ufshcd_task_req_compl(struct ufs_hba *hba, u32 index)
+{
+	struct utp_task_req_desc *task_req_descp;
+	struct utp_upiu_task_rsp *task_rsp_upiup;
+	unsigned long flags;
+	int ocs_value;
+	int task_result;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+
+	/* Clear completed tasks from outstanding_tasks */
+	__clear_bit(index, &hba->outstanding_tasks);
+
+	task_req_descp = hba->utmrdl_base_addr;
+	ocs_value = ufshcd_get_tmr_ocs(&task_req_descp[index]);
+
+	if (ocs_value == OCS_SUCCESS) {
+		task_rsp_upiup = (struct utp_upiu_task_rsp *)
+				task_req_descp[index].task_rsp_upiu;
+		task_result = be32_to_cpu(task_rsp_upiup->header.dword_1);
+		task_result = ((task_result & MASK_TASK_RESPONSE) >> 8);
+
+		if (task_result != UPIU_TASK_MANAGEMENT_FUNC_COMPL ||
+		    task_result != UPIU_TASK_MANAGEMENT_FUNC_SUCCEEDED)
+			task_result = FAILED;
+	} else {
+		task_result = FAILED;
+		dev_err(&hba->pdev->dev,
+			"trc: Invalid ocs = %x\n", ocs_value);
+	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	return task_result;
+}
+
+/**
+ * ufshcd_adjust_lun_qdepth - Update LUN queue depth if device responds with
+ *			      SAM_STAT_TASK_SET_FULL SCSI command status.
+ * @cmd: pointer to SCSI command
+ */
+static void ufshcd_adjust_lun_qdepth(struct scsi_cmnd *cmd)
+{
+	struct ufs_hba *hba;
+	int i;
+	int lun_qdepth = 0;
+
+	hba = shost_priv(cmd->device->host);
+
+	/*
+	 * LUN queue depth can be obtained by counting outstanding commands
+	 * on the LUN.
+	 */
+	for (i = 0; i < hba->nutrs; i++) {
+		if (test_bit(i, &hba->outstanding_reqs)) {
+
+			/*
+			 * Check if the outstanding command belongs
+			 * to the LUN which reported SAM_STAT_TASK_SET_FULL.
+			 */
+			if (cmd->device->lun == hba->lrb[i].lun)
+				lun_qdepth++;
+		}
+	}
+
+	/*
+	 * LUN queue depth will be total outstanding commands, except the
+	 * command for which the LUN reported SAM_STAT_TASK_SET_FULL.
+	 */
+	scsi_adjust_queue_depth(cmd->device, MSG_SIMPLE_TAG, lun_qdepth - 1);
+}
+
+/**
+ * ufshcd_scsi_cmd_status - Update SCSI command result based on SCSI status
+ * @lrb: pointer to local reference block of completed command
+ * @scsi_status: SCSI command status
+ *
+ * Returns value base on SCSI command status
+ */
+static inline int
+ufshcd_scsi_cmd_status(struct ufshcd_lrb *lrbp, int scsi_status)
+{
+	int result = 0;
+
+	switch (scsi_status) {
+	case SAM_STAT_GOOD:
+		result |= DID_OK << 16 |
+			  COMMAND_COMPLETE << 8 |
+			  SAM_STAT_GOOD;
+		break;
+	case SAM_STAT_CHECK_CONDITION:
+		result |= DID_OK << 16 |
+			  COMMAND_COMPLETE << 8 |
+			  SAM_STAT_CHECK_CONDITION;
+		ufshcd_copy_sense_data(lrbp);
+		break;
+	case SAM_STAT_BUSY:
+		result |= SAM_STAT_BUSY;
+		break;
+	case SAM_STAT_TASK_SET_FULL:
+
+		/*
+		 * If a LUN reports SAM_STAT_TASK_SET_FULL, then the LUN queue
+		 * depth needs to be adjusted to the exact number of
+		 * outstanding commands the LUN can handle at any given time.
+		 */
+		ufshcd_adjust_lun_qdepth(lrbp->cmd);
+		result |= SAM_STAT_TASK_SET_FULL;
+		break;
+	case SAM_STAT_TASK_ABORTED:
+		result |= SAM_STAT_TASK_ABORTED;
+		break;
+	default:
+		result |= DID_ERROR << 16;
+		break;
+	} /* end of switch */
+
+	return result;
+}
+
+/**
+ * ufshcd_transfer_rsp_status - Get overall status of the response
+ * @hba: per adapter instance
+ * @lrb: pointer to local reference block of completed command
+ *
+ * Returns result of the command to notify SCSI midlayer
+ */
+static inline int
+ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
+{
+	int result = 0;
+	int scsi_status;
+	int ocs;
+
+	/* overall command status of utrd */
+	ocs = ufshcd_get_tr_ocs(lrbp);
+
+	switch (ocs) {
+	case OCS_SUCCESS:
+
+		/* check if the returned transfer response is valid */
+		result = ufshcd_is_valid_req_rsp(lrbp->ucd_rsp_ptr);
+		if (result) {
+			dev_err(&hba->pdev->dev,
+				"Invalid response = %x\n", result);
+			break;
+		}
+
+		/*
+		 * get the response UPIU result to extract
+		 * the SCSI command status
+		 */
+		result = ufshcd_get_rsp_upiu_result(lrbp->ucd_rsp_ptr);
+
+		/*
+		 * get the result based on SCSI status response
+		 * to notify the SCSI midlayer of the command status
+		 */
+		scsi_status = result & MASK_SCSI_STATUS;
+		result = ufshcd_scsi_cmd_status(lrbp, scsi_status);
+		break;
+	case OCS_ABORTED:
+		result |= DID_ABORT << 16;
+		break;
+	case OCS_INVALID_CMD_TABLE_ATTR:
+	case OCS_INVALID_PRDT_ATTR:
+	case OCS_MISMATCH_DATA_BUF_SIZE:
+	case OCS_MISMATCH_RESP_UPIU_SIZE:
+	case OCS_PEER_COMM_FAILURE:
+	case OCS_FATAL_ERROR:
+	default:
+		result |= DID_ERROR << 16;
+		dev_err(&hba->pdev->dev,
+		"OCS error from controller = %x\n", ocs);
+		break;
+	} /* end of switch */
+
+	return result;
+}
+
+/**
+ * ufshcd_transfer_req_compl - handle SCSI and query command completion
+ * @hba: per adapter instance
+ */
+static void ufshcd_transfer_req_compl(struct ufs_hba *hba)
+{
+	struct ufshcd_lrb *lrb;
+	unsigned long completed_reqs;
+	u32 tr_doorbell;
+	int result;
+	int index;
+
+	lrb = hba->lrb;
+	tr_doorbell =
+		readl(hba->mmio_base + REG_UTP_TRANSFER_REQ_DOOR_BELL);
+	completed_reqs = tr_doorbell ^ hba->outstanding_reqs;
+
+	for (index = 0; index < hba->nutrs; index++) {
+		if (test_bit(index, &completed_reqs)) {
+
+			result = ufshcd_transfer_rsp_status(hba, &lrb[index]);
+
+			if (lrb[index].cmd) {
+				scsi_dma_unmap(lrb[index].cmd);
+				lrb[index].cmd->result = result;
+				lrb[index].cmd->scsi_done(lrb[index].cmd);
+
+				/* Mark completed command as NULL in LRB */
+				lrb[index].cmd = NULL;
+			}
+		} /* end of if */
+	} /* end of for */
+
+	/* clear corresponding bits of completed commands */
+	hba->outstanding_reqs ^= completed_reqs;
+
+	/* Reset interrupt aggregation counters */
+	ufshcd_config_int_aggr(hba, INT_AGGR_RESET);
+}
+
+/**
+ * ufshcd_uic_cc_handler - handle UIC command completion
+ * @work: pointer to a work queue structure
+ *
+ * Returns 0 on success, non-zero value on failure
+ */
+static void ufshcd_uic_cc_handler (struct work_struct *work)
+{
+	struct ufs_hba *hba;
+
+	hba = container_of(work, struct ufs_hba, uic_workq);
+
+	if ((hba->active_uic_cmd.command == UIC_CMD_DME_LINK_STARTUP) &&
+	    !(ufshcd_get_uic_cmd_result(hba))) {
+
+		if (ufshcd_make_hba_operational(hba))
+			dev_err(&hba->pdev->dev,
+				"cc: hba not operational state\n");
+		return;
+	}
+}
+
+/**
+ * ufshcd_fatal_err_handler - handle fatal errors
+ * @hba: per adapter instance
+ */
+static void ufshcd_fatal_err_handler(struct work_struct *work)
+{
+	struct ufs_hba *hba;
+	hba = container_of(work, struct ufs_hba, feh_workq);
+
+	/* check if reset is already in progress */
+	if (hba->ufshcd_state != UFSHCD_STATE_RESET)
+		ufshcd_do_reset(hba);
+}
+
+/**
+ * ufshcd_err_handler - Check for fatal errors
+ * @work: pointer to a work queue structure
+ */
+static void ufshcd_err_handler(struct ufs_hba *hba)
+{
+	u32 reg;
+
+	if (hba->errors & INT_FATAL_ERRORS)
+		goto fatal_eh;
+
+	if (hba->errors & UIC_ERROR) {
+
+		reg = readl(hba->mmio_base +
+			    REG_UIC_ERROR_CODE_PHY_ADAPTER_LAYER);
+		if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT)
+			goto fatal_eh;
+	}
+	return;
+fatal_eh:
+	hba->ufshcd_state = UFSHCD_STATE_ERROR;
+	schedule_work(&hba->feh_workq);
+}
+
+/**
+ * ufshcd_tmc_handler - handle task management function completion
+ * @hba: per adapter instance
+ */
+static void ufshcd_tmc_handler(struct ufs_hba *hba)
+{
+	u32 tm_doorbell;
+
+	tm_doorbell = readl(hba->mmio_base + REG_UTP_TASK_REQ_DOOR_BELL);
+	hba->tm_condition = tm_doorbell ^ hba->outstanding_tasks;
+	wake_up_interruptible(&hba->ufshcd_tm_wait_queue);
+}
+
+/**
+ * ufshcd_sl_intr - Interrupt service routine
+ * @hba: per adapter instance
+ * @intr_status: contains interrupts generated by the controller
+ */
+static void ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
+{
+	hba->errors = UFSHCD_ERROR_MASK & intr_status;
+	if (hba->errors)
+		ufshcd_err_handler(hba);
+
+	if (intr_status & UIC_COMMAND_COMPL)
+		schedule_work(&hba->uic_workq);
+
+	if (intr_status & UTP_TASK_REQ_COMPL)
+		ufshcd_tmc_handler(hba);
+
+	if (intr_status & UTP_TRANSFER_REQ_COMPL)
+		ufshcd_transfer_req_compl(hba);
+}
+
+/**
+ * ufshcd_intr - Main interrupt service routine
+ * @irq: irq number
+ * @__hba: pointer to adapter instance
+ *
+ * Returns IRQ_HANDLED - If interrupt is valid
+ *		IRQ_NONE - If invalid interrupt
+ */
+static irqreturn_t ufshcd_intr(int irq, void *__hba)
+{
+	u32 intr_status;
+	irqreturn_t retval = IRQ_NONE;
+	struct ufs_hba *hba = __hba;
+
+	spin_lock(hba->host->host_lock);
+	intr_status = readl(hba->mmio_base + REG_INTERRUPT_STATUS);
+
+	if (intr_status) {
+		ufshcd_sl_intr(hba, intr_status);
+
+		/* If UFSHCI 1.0 then clear interrupt status register */
+		if (hba->ufs_version == UFSHCI_VERSION_10)
+			writel(intr_status,
+			       (hba->mmio_base + REG_INTERRUPT_STATUS));
+		retval = IRQ_HANDLED;
+	}
+	spin_unlock(hba->host->host_lock);
+	return retval;
+}
+
+/**
+ * ufshcd_issue_tm_cmd - issues task management commands to controller
+ * @hba: per adapter instance
+ * @lrbp: pointer to local reference block
+ *
+ * Returns SUCCESS/FAILED
+ */
+static int
+ufshcd_issue_tm_cmd(struct ufs_hba *hba,
+		    struct ufshcd_lrb *lrbp,
+		    u8 tm_function)
+{
+	struct utp_task_req_desc *task_req_descp;
+	struct utp_upiu_task_req *task_req_upiup;
+	struct Scsi_Host *host;
+	unsigned long flags;
+	int free_slot = 0;
+	int err;
+
+	host = hba->host;
+
+	spin_lock_irqsave(host->host_lock, flags);
+
+	/* If task management queue is full */
+	free_slot = ufshcd_get_tm_free_slot(hba);
+	if (free_slot >= hba->nutmrs) {
+		spin_unlock_irqrestore(host->host_lock, flags);
+		dev_err(&hba->pdev->dev, "Task management queue full\n");
+		err = FAILED;
+		goto out;
+	}
+
+	task_req_descp = hba->utmrdl_base_addr;
+	task_req_descp += free_slot;
+
+	/* Configure task request descriptor */
+	task_req_descp->header.dword_0 = cpu_to_le32(UTP_REQ_DESC_INT_CMD);
+	task_req_descp->header.dword_2 =
+			cpu_to_le32(OCS_INVALID_COMMAND_STATUS);
+
+	/* Configure task request UPIU */
+	task_req_upiup =
+		(struct utp_upiu_task_req *) task_req_descp->task_req_upiu;
+	task_req_upiup->header.dword_0 =
+		cpu_to_be32(UPIU_HEADER_DWORD(UPIU_TRANSACTION_TASK_REQ, 0,
+					      lrbp->lun, lrbp->task_tag));
+	task_req_upiup->header.dword_1 =
+	cpu_to_be32(UPIU_HEADER_DWORD(0, tm_function, 0, 0));
+
+	task_req_upiup->input_param1 = lrbp->lun;
+	task_req_upiup->input_param1 =
+		cpu_to_be32(task_req_upiup->input_param1);
+	task_req_upiup->input_param2 = lrbp->task_tag;
+	task_req_upiup->input_param2 =
+		cpu_to_be32(task_req_upiup->input_param2);
+
+	/* send command to the controller */
+	__set_bit(free_slot, &hba->outstanding_tasks);
+	writel((1 << free_slot),
+	       (hba->mmio_base + REG_UTP_TASK_REQ_DOOR_BELL));
+
+	spin_unlock_irqrestore(host->host_lock, flags);
+
+	/* wait until the task management command is completed */
+	err =
+	wait_event_interruptible_timeout(hba->ufshcd_tm_wait_queue,
+					 (test_bit(free_slot,
+					 &hba->tm_condition) != 0),
+					 60 * HZ);
+	if (!err) {
+		dev_err(&hba->pdev->dev,
+			"Task management command timed-out\n");
+		err = FAILED;
+		goto out;
+	}
+	clear_bit(free_slot, &hba->tm_condition);
+	return ufshcd_task_req_compl(hba, free_slot);
+out:
+	return err;
+}
+
+/**
+ * ufshcd_device_reset - reset device and abort all the pending commands
+ * @cmd: SCSI command pointer
+ *
+ * Returns SUCCESS/FAILED
+ */
+static int ufshcd_device_reset(struct scsi_cmnd *cmd)
+{
+	struct Scsi_Host *host;
+	struct ufs_hba *hba;
+	unsigned int tag;
+	u32 pos;
+	int err;
+
+	host = cmd->device->host;
+	hba = shost_priv(host);
+	tag = cmd->request->tag;
+
+	err = ufshcd_issue_tm_cmd(hba, &hba->lrb[tag], UFS_LOGICAL_RESET);
+	if (err)
+		goto out;
+
+	for (pos = 0; pos < hba->nutrs; pos++) {
+		if (test_bit(pos, &hba->outstanding_reqs) &&
+		    (hba->lrb[tag].lun == hba->lrb[pos].lun)) {
+
+			/* clear the respective UTRLCLR register bit */
+			ufshcd_utrl_clear(hba, pos);
+
+			clear_bit(pos, &hba->outstanding_reqs);
+
+			if (hba->lrb[pos].cmd) {
+				scsi_dma_unmap(hba->lrb[pos].cmd);
+				hba->lrb[pos].cmd->result =
+						DID_ABORT << 16;
+				hba->lrb[pos].cmd->scsi_done(cmd);
+				hba->lrb[pos].cmd = NULL;
+			}
+		}
+	} /* end of for */
+out:
+	return err;
+}
+
+/**
+ * ufshcd_host_reset - Main reset function registered with scsi layer
+ * @cmd: SCSI command pointer
+ *
+ * Returns SUCCESS/FAILED
+ */
+static int ufshcd_host_reset(struct scsi_cmnd *cmd)
+{
+	struct ufs_hba *hba;
+
+	hba = shost_priv(cmd->device->host);
+
+	if (hba->ufshcd_state == UFSHCD_STATE_RESET)
+		return SUCCESS;
+
+	return (ufshcd_do_reset(hba) == SUCCESS) ? SUCCESS : FAILED;
+}
+
+/**
+ * ufshcd_abort - abort a specific command
+ * @cmd: SCSI command pointer
+ *
+ * Returns SUCCESS/FAILED
+ */
+static int ufshcd_abort(struct scsi_cmnd *cmd)
+{
+	struct Scsi_Host *host;
+	struct ufs_hba *hba;
+	unsigned long flags;
+	unsigned int tag;
+	int err;
+
+	host = cmd->device->host;
+	hba = shost_priv(host);
+	tag = cmd->request->tag;
+
+	spin_lock_irqsave(host->host_lock, flags);
+
+	/* check if command is still pending */
+	if (!(test_bit(tag, &hba->outstanding_reqs))) {
+		err = FAILED;
+		spin_unlock_irqrestore(host->host_lock, flags);
+		goto out;
+	}
+	spin_unlock_irqrestore(host->host_lock, flags);
+
+	err = ufshcd_issue_tm_cmd(hba, &hba->lrb[tag], UFS_ABORT_TASK);
+	if (err)
+		goto out;
+
+	scsi_dma_unmap(cmd);
+
+	spin_lock_irqsave(host->host_lock, flags);
+
+	/* clear the respective UTRLCLR register bit */
+	ufshcd_utrl_clear(hba, tag);
+
+	__clear_bit(tag, &hba->outstanding_reqs);
+	hba->lrb[tag].cmd = NULL;
+	spin_unlock_irqrestore(host->host_lock, flags);
+out:
+	return err;
+}
+
+static struct scsi_host_template ufshcd_driver_template = {
+	.module			= THIS_MODULE,
+	.name			= UFSHCD,
+	.proc_name		= UFSHCD,
+	.queuecommand		= ufshcd_queuecommand,
+	.slave_alloc		= ufshcd_slave_alloc,
+	.slave_destroy		= ufshcd_slave_destroy,
+	.eh_abort_handler	= ufshcd_abort,
+	.eh_device_reset_handler = ufshcd_device_reset,
+	.eh_host_reset_handler	= ufshcd_host_reset,
+	.this_id		= -1,
+	.sg_tablesize		= SG_ALL,
+	.cmd_per_lun		= UFSHCD_CMD_PER_LUN,
+	.can_queue		= UFSHCD_CAN_QUEUE,
+};
+
+/**
+ * ufshcd_shutdown - main function to put the controller in reset state
+ * @pdev: pointer to PCI device handle
+ */
+static void ufshcd_shutdown(struct pci_dev *pdev)
+{
+	ufshcd_hba_stop((struct ufs_hba *)pci_get_drvdata(pdev));
+}
+
+#ifdef CONFIG_PM
+/**
+ * ufshcd_suspend - suspend power management function
+ * @pdev: pointer to PCI device handle
+ * @state: power state
+ *
+ * Returns -ENOSYS
+ */
+static int ufshcd_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	/*
+	 * TODO:
+	 * 1. Block SCSI requests from SCSI midlayer
+	 * 2. Change the internal driver state to non operational
+	 * 3. Set UTRLRSR and UTMRLRSR bits to zero
+	 * 4. Wait until outstanding commands are completed
+	 * 5. Set HCE to zero to send the UFS host controller to reset state
+	 */
+
+	return -ENOSYS;
+}
+
+/**
+ * ufshcd_resume - resume power management function
+ * @pdev: pointer to PCI device handle
+ *
+ * Returns -ENOSYS
+ */
+static int ufshcd_resume(struct pci_dev *pdev)
+{
+	/*
+	 * TODO:
+	 * 1. Set HCE to 1, to start the UFS host controller
+	 * initialization process
+	 * 2. Set UTRLRSR and UTMRLRSR bits to 1
+	 * 3. Change the internal driver state to operational
+	 * 4. Unblock SCSI requests from SCSI midlayer
+	 */
+
+	return -ENOSYS;
+}
+#endif /* CONFIG_PM */
+
+/**
+ * ufshcd_hba_free - free allocated memory for
+ *			host memory space data structures
+ * @hba: per adapter instance
+ */
+static void ufshcd_hba_free(struct ufs_hba *hba)
+{
+	iounmap(hba->mmio_base);
+	ufshcd_free_hba_memory(hba);
+	pci_release_regions(hba->pdev);
+}
+
+/**
+ * ufshcd_remove - de-allocate PCI/SCSI host and host memory space
+ *		data structure memory
+ * @pdev - pointer to PCI handle
+ */
+static void ufshcd_remove(struct pci_dev *pdev)
+{
+	struct ufs_hba *hba = pci_get_drvdata(pdev);
+
+	/* disable interrupts */
+	ufshcd_int_config(hba, UFSHCD_INT_DISABLE);
+	free_irq(pdev->irq, hba);
+
+	ufshcd_hba_stop(hba);
+	ufshcd_hba_free(hba);
+
+	scsi_remove_host(hba->host);
+	scsi_host_put(hba->host);
+	pci_set_drvdata(pdev, NULL);
+	pci_clear_master(pdev);
+	pci_disable_device(pdev);
+}
+
+/**
+ * ufshcd_set_dma_mask - Set dma mask based on the controller
+ *			 addressing capability
+ * @pdev: PCI device structure
+ *
+ * Returns 0 for success, non-zero for failure
+ */
+static int ufshcd_set_dma_mask(struct ufs_hba *hba)
+{
+	int err;
+	u64 dma_mask;
+
+	/*
+	 * If controller supports 64 bit addressing mode, then set the DMA
+	 * mask to 64-bit, else set the DMA mask to 32-bit
+	 */
+	if (hba->capabilities & MASK_64_ADDRESSING_SUPPORT)
+		dma_mask = DMA_BIT_MASK(64);
+	else
+		dma_mask = DMA_BIT_MASK(32);
+
+	err = pci_set_dma_mask(hba->pdev, dma_mask);
+	if (err)
+		return err;
+
+	err = pci_set_consistent_dma_mask(hba->pdev, dma_mask);
+
+	return err;
+}
+
+/**
+ * ufshcd_probe - probe routine of the driver
+ * @pdev: pointer to PCI device handle
+ * @id: PCI device id
+ *
+ * Returns 0 on success, non-zero value on failure
+ */
+static int __devinit
+ufshcd_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct Scsi_Host *host;
+	struct ufs_hba *hba;
+	int err;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "pci_enable_device failed\n");
+		goto out_error;
+	}
+
+	pci_set_master(pdev);
+
+	host = scsi_host_alloc(&ufshcd_driver_template,
+				sizeof(struct ufs_hba));
+	if (!host) {
+		dev_err(&pdev->dev, "scsi_host_alloc failed\n");
+		err = -ENOMEM;
+		goto out_disable;
+	}
+	hba = shost_priv(host);
+
+	err = pci_request_regions(pdev, UFSHCD);
+	if (err < 0) {
+		dev_err(&pdev->dev, "request regions failed\n");
+		goto out_disable;
+	}
+
+	hba->mmio_base = pci_ioremap_bar(pdev, 0);
+	if (!hba->mmio_base) {
+		dev_err(&pdev->dev, "memory map failed\n");
+		err = -ENOMEM;
+		goto out_release_regions;
+	}
+
+	hba->host = host;
+	hba->pdev = pdev;
+
+	/* Read capabilities registers */
+	ufshcd_hba_capabilities(hba);
+
+	/* Get UFS version supported by the controller */
+	hba->ufs_version = ufshcd_get_ufs_version(hba);
+
+	err = ufshcd_set_dma_mask(hba);
+	if (err) {
+		dev_err(&pdev->dev, "set dma mask failed\n");
+		goto out_iounmap;
+	}
+
+	/* Allocate memory for host memory space */
+	err = ufshcd_memory_alloc(hba);
+	if (err) {
+		dev_err(&pdev->dev, "Memory allocation failed\n");
+		goto out_iounmap;
+	}
+
+	/* Configure LRB */
+	ufshcd_host_memory_configure(hba);
+
+	host->can_queue = hba->nutrs;
+	host->cmd_per_lun = hba->nutrs;
+	host->max_id = UFSHCD_MAX_ID;
+	host->max_lun = UFSHCD_MAX_LUNS;
+	host->max_channel = UFSHCD_MAX_CHANNEL;
+	host->unique_id = host->host_no;
+	host->max_cmd_len = MAX_CDB_SIZE;
+
+	/* Initailize wait queue for task management */
+	init_waitqueue_head(&hba->ufshcd_tm_wait_queue);
+
+	/* Initialize work queues */
+	INIT_WORK(&hba->uic_workq, ufshcd_uic_cc_handler);
+	INIT_WORK(&hba->feh_workq, ufshcd_fatal_err_handler);
+
+	/* IRQ registration */
+	err = request_irq(pdev->irq, ufshcd_intr, IRQF_SHARED, UFSHCD, hba);
+	if (err) {
+		dev_err(&pdev->dev, "request irq failed\n");
+		goto out_lrb_free;
+	}
+
+	/* Enable SCSI tag mapping */
+	err = scsi_init_shared_tag_map(host, host->can_queue);
+	if (err) {
+		dev_err(&pdev->dev, "init shared queue failed\n");
+		goto out_free_irq;
+	}
+
+	pci_set_drvdata(pdev, hba);
+
+	err = scsi_add_host(host, &pdev->dev);
+	if (err) {
+		dev_err(&pdev->dev, "scsi_add_host failed\n");
+		goto out_free_irq;
+	}
+
+	/* Initialization routine */
+	err = ufshcd_initialize_hba(hba);
+	if (err) {
+		dev_err(&pdev->dev, "Initialization failed\n");
+		goto out_free_irq;
+	}
+
+	return 0;
+
+out_free_irq:
+	free_irq(pdev->irq, hba);
+out_lrb_free:
+	ufshcd_free_hba_memory(hba);
+out_iounmap:
+	iounmap(hba->mmio_base);
+out_release_regions:
+	pci_release_regions(pdev);
+out_disable:
+	scsi_host_put(host);
+	pci_clear_master(pdev);
+	pci_disable_device(pdev);
+out_error:
+	return err;
+}
+
+static DEFINE_PCI_DEVICE_TABLE(ufshcd_pci_tbl) = {
+	{ PCI_VENDOR_ID_SAMSUNG, 0xC00C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
+	{ }	/* terminate list */
+};
+
+MODULE_DEVICE_TABLE(pci, ufshcd_pci_tbl);
+
+static struct pci_driver ufshcd_pci_driver = {
+	.name = UFSHCD,
+	.id_table = ufshcd_pci_tbl,
+	.probe = ufshcd_probe,
+	.remove = __devexit_p(ufshcd_remove),
+	.shutdown = ufshcd_shutdown,
+#ifdef CONFIG_PM
+	.suspend = ufshcd_suspend,
+	.resume = ufshcd_resume,
+#endif
+};
+
+/**
+ * ufshcd_init - Driver registration routine
+ */
+static int __init ufshcd_init(void)
+{
+	return pci_register_driver(&ufshcd_pci_driver);
+}
+module_init(ufshcd_init);
+
+/**
+ * ufshcd_exit - Driver exit clean-up routine
+ */
+static void __exit ufshcd_exit(void)
+{
+	pci_unregister_driver(&ufshcd_pci_driver);
+}
+module_exit(ufshcd_exit);
+
+
+MODULE_AUTHOR("Santosh Yaragnavi <santosh.sy@samsung.com>, "
+	      "Vinayak Holikatti <h.vinayak@samsung.com>");
+MODULE_DESCRIPTION("Generic UFS host controller driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(UFSHCD_DRIVER_VERSION);
diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h
new file mode 100644
index 000000000000..6e3510f71167
--- /dev/null
+++ b/drivers/scsi/ufs/ufshci.h
@@ -0,0 +1,376 @@
+/*
+ * Universal Flash Storage Host controller driver
+ *
+ * This code is based on drivers/scsi/ufs/ufshci.h
+ * Copyright (C) 2011-2012 Samsung India Software Operations
+ *
+ * Santosh Yaraganavi <santosh.sy@samsung.com>
+ * Vinayak Holikatti <h.vinayak@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * NO WARRANTY
+ * THE PROGRAM IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OR
+ * CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED INCLUDING, WITHOUT
+ * LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE, NON-INFRINGEMENT,
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Each Recipient is
+ * solely responsible for determining the appropriateness of using and
+ * distributing the Program and assumes all risks associated with its
+ * exercise of rights under this Agreement, including but not limited to
+ * the risks and costs of program errors, damage to or loss of data,
+ * programs or equipment, and unavailability or interruption of operations.
+
+ * DISCLAIMER OF LIABILITY
+ * NEITHER RECIPIENT NOR ANY CONTRIBUTORS SHALL HAVE ANY LIABILITY FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING WITHOUT LIMITATION LOST PROFITS), HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
+ * TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OR DISTRIBUTION OF THE PROGRAM OR THE EXERCISE OF ANY RIGHTS GRANTED
+ * HEREUNDER, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGES
+
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301,
+ * USA.
+ */
+
+#ifndef _UFSHCI_H
+#define _UFSHCI_H
+
+enum {
+	TASK_REQ_UPIU_SIZE_DWORDS	= 8,
+	TASK_RSP_UPIU_SIZE_DWORDS	= 8,
+	ALIGNED_UPIU_SIZE		= 128,
+};
+
+/* UFSHCI Registers */
+enum {
+	REG_CONTROLLER_CAPABILITIES		= 0x00,
+	REG_UFS_VERSION				= 0x08,
+	REG_CONTROLLER_DEV_ID			= 0x10,
+	REG_CONTROLLER_PROD_ID			= 0x14,
+	REG_INTERRUPT_STATUS			= 0x20,
+	REG_INTERRUPT_ENABLE			= 0x24,
+	REG_CONTROLLER_STATUS			= 0x30,
+	REG_CONTROLLER_ENABLE			= 0x34,
+	REG_UIC_ERROR_CODE_PHY_ADAPTER_LAYER	= 0x38,
+	REG_UIC_ERROR_CODE_DATA_LINK_LAYER	= 0x3C,
+	REG_UIC_ERROR_CODE_NETWORK_LAYER	= 0x40,
+	REG_UIC_ERROR_CODE_TRANSPORT_LAYER	= 0x44,
+	REG_UIC_ERROR_CODE_DME			= 0x48,
+	REG_UTP_TRANSFER_REQ_INT_AGG_CONTROL	= 0x4C,
+	REG_UTP_TRANSFER_REQ_LIST_BASE_L	= 0x50,
+	REG_UTP_TRANSFER_REQ_LIST_BASE_H	= 0x54,
+	REG_UTP_TRANSFER_REQ_DOOR_BELL		= 0x58,
+	REG_UTP_TRANSFER_REQ_LIST_CLEAR		= 0x5C,
+	REG_UTP_TRANSFER_REQ_LIST_RUN_STOP	= 0x60,
+	REG_UTP_TASK_REQ_LIST_BASE_L		= 0x70,
+	REG_UTP_TASK_REQ_LIST_BASE_H		= 0x74,
+	REG_UTP_TASK_REQ_DOOR_BELL		= 0x78,
+	REG_UTP_TASK_REQ_LIST_CLEAR		= 0x7C,
+	REG_UTP_TASK_REQ_LIST_RUN_STOP		= 0x80,
+	REG_UIC_COMMAND				= 0x90,
+	REG_UIC_COMMAND_ARG_1			= 0x94,
+	REG_UIC_COMMAND_ARG_2			= 0x98,
+	REG_UIC_COMMAND_ARG_3			= 0x9C,
+};
+
+/* Controller capability masks */
+enum {
+	MASK_TRANSFER_REQUESTS_SLOTS		= 0x0000001F,
+	MASK_TASK_MANAGEMENT_REQUEST_SLOTS	= 0x00070000,
+	MASK_64_ADDRESSING_SUPPORT		= 0x01000000,
+	MASK_OUT_OF_ORDER_DATA_DELIVERY_SUPPORT	= 0x02000000,
+	MASK_UIC_DME_TEST_MODE_SUPPORT		= 0x04000000,
+};
+
+/* UFS Version 08h */
+#define MINOR_VERSION_NUM_MASK		UFS_MASK(0xFFFF, 0)
+#define MAJOR_VERSION_NUM_MASK		UFS_MASK(0xFFFF, 16)
+
+/* Controller UFSHCI version */
+enum {
+	UFSHCI_VERSION_10 = 0x00010000,
+	UFSHCI_VERSION_11 = 0x00010100,
+};
+
+/*
+ * HCDDID - Host Controller Identification Descriptor
+ *	  - Device ID and Device Class 10h
+ */
+#define DEVICE_CLASS	UFS_MASK(0xFFFF, 0)
+#define DEVICE_ID	UFS_MASK(0xFF, 24)
+
+/*
+ * HCPMID - Host Controller Identification Descriptor
+ *	  - Product/Manufacturer ID  14h
+ */
+#define MANUFACTURE_ID_MASK	UFS_MASK(0xFFFF, 0)
+#define PRODUCT_ID_MASK		UFS_MASK(0xFFFF, 16)
+
+#define UFS_BIT(x)	(1L << (x))
+
+#define UTP_TRANSFER_REQ_COMPL			UFS_BIT(0)
+#define UIC_DME_END_PT_RESET			UFS_BIT(1)
+#define UIC_ERROR				UFS_BIT(2)
+#define UIC_TEST_MODE				UFS_BIT(3)
+#define UIC_POWER_MODE				UFS_BIT(4)
+#define UIC_HIBERNATE_EXIT			UFS_BIT(5)
+#define UIC_HIBERNATE_ENTER			UFS_BIT(6)
+#define UIC_LINK_LOST				UFS_BIT(7)
+#define UIC_LINK_STARTUP			UFS_BIT(8)
+#define UTP_TASK_REQ_COMPL			UFS_BIT(9)
+#define UIC_COMMAND_COMPL			UFS_BIT(10)
+#define DEVICE_FATAL_ERROR			UFS_BIT(11)
+#define CONTROLLER_FATAL_ERROR			UFS_BIT(16)
+#define SYSTEM_BUS_FATAL_ERROR			UFS_BIT(17)
+
+#define UFSHCD_ERROR_MASK	(UIC_ERROR |\
+				DEVICE_FATAL_ERROR |\
+				CONTROLLER_FATAL_ERROR |\
+				SYSTEM_BUS_FATAL_ERROR)
+
+#define INT_FATAL_ERRORS	(DEVICE_FATAL_ERROR |\
+				CONTROLLER_FATAL_ERROR |\
+				SYSTEM_BUS_FATAL_ERROR)
+
+/* HCS - Host Controller Status 30h */
+#define DEVICE_PRESENT				UFS_BIT(0)
+#define UTP_TRANSFER_REQ_LIST_READY		UFS_BIT(1)
+#define UTP_TASK_REQ_LIST_READY			UFS_BIT(2)
+#define UIC_COMMAND_READY			UFS_BIT(3)
+#define HOST_ERROR_INDICATOR			UFS_BIT(4)
+#define DEVICE_ERROR_INDICATOR			UFS_BIT(5)
+#define UIC_POWER_MODE_CHANGE_REQ_STATUS_MASK	UFS_MASK(0x7, 8)
+
+/* HCE - Host Controller Enable 34h */
+#define CONTROLLER_ENABLE	UFS_BIT(0)
+#define CONTROLLER_DISABLE	0x0
+
+/* UECPA - Host UIC Error Code PHY Adapter Layer 38h */
+#define UIC_PHY_ADAPTER_LAYER_ERROR			UFS_BIT(31)
+#define UIC_PHY_ADAPTER_LAYER_ERROR_CODE_MASK		0x1F
+
+/* UECDL - Host UIC Error Code Data Link Layer 3Ch */
+#define UIC_DATA_LINK_LAYER_ERROR		UFS_BIT(31)
+#define UIC_DATA_LINK_LAYER_ERROR_CODE_MASK	0x7FFF
+#define UIC_DATA_LINK_LAYER_ERROR_PA_INIT	0x2000
+
+/* UECN - Host UIC Error Code Network Layer 40h */
+#define UIC_NETWORK_LAYER_ERROR			UFS_BIT(31)
+#define UIC_NETWORK_LAYER_ERROR_CODE_MASK	0x7
+
+/* UECT - Host UIC Error Code Transport Layer 44h */
+#define UIC_TRANSPORT_LAYER_ERROR		UFS_BIT(31)
+#define UIC_TRANSPORT_LAYER_ERROR_CODE_MASK	0x7F
+
+/* UECDME - Host UIC Error Code DME 48h */
+#define UIC_DME_ERROR			UFS_BIT(31)
+#define UIC_DME_ERROR_CODE_MASK		0x1
+
+#define INT_AGGR_TIMEOUT_VAL_MASK		0xFF
+#define INT_AGGR_COUNTER_THRESHOLD_MASK		UFS_MASK(0x1F, 8)
+#define INT_AGGR_COUNTER_AND_TIMER_RESET	UFS_BIT(16)
+#define INT_AGGR_STATUS_BIT			UFS_BIT(20)
+#define INT_AGGR_PARAM_WRITE			UFS_BIT(24)
+#define INT_AGGR_ENABLE				UFS_BIT(31)
+
+/* UTRLRSR - UTP Transfer Request Run-Stop Register 60h */
+#define UTP_TRANSFER_REQ_LIST_RUN_STOP_BIT	UFS_BIT(0)
+
+/* UTMRLRSR - UTP Task Management Request Run-Stop Register 80h */
+#define UTP_TASK_REQ_LIST_RUN_STOP_BIT		UFS_BIT(0)
+
+/* UICCMD - UIC Command */
+#define COMMAND_OPCODE_MASK		0xFF
+#define GEN_SELECTOR_INDEX_MASK		0xFFFF
+
+#define MIB_ATTRIBUTE_MASK		UFS_MASK(0xFFFF, 16)
+#define RESET_LEVEL			0xFF
+
+#define ATTR_SET_TYPE_MASK		UFS_MASK(0xFF, 16)
+#define CONFIG_RESULT_CODE_MASK		0xFF
+#define GENERIC_ERROR_CODE_MASK		0xFF
+
+/* UIC Commands */
+enum {
+	UIC_CMD_DME_GET			= 0x01,
+	UIC_CMD_DME_SET			= 0x02,
+	UIC_CMD_DME_PEER_GET		= 0x03,
+	UIC_CMD_DME_PEER_SET		= 0x04,
+	UIC_CMD_DME_POWERON		= 0x10,
+	UIC_CMD_DME_POWEROFF		= 0x11,
+	UIC_CMD_DME_ENABLE		= 0x12,
+	UIC_CMD_DME_RESET		= 0x14,
+	UIC_CMD_DME_END_PT_RST		= 0x15,
+	UIC_CMD_DME_LINK_STARTUP	= 0x16,
+	UIC_CMD_DME_HIBER_ENTER		= 0x17,
+	UIC_CMD_DME_HIBER_EXIT		= 0x18,
+	UIC_CMD_DME_TEST_MODE		= 0x1A,
+};
+
+/* UIC Config result code / Generic error code */
+enum {
+	UIC_CMD_RESULT_SUCCESS			= 0x00,
+	UIC_CMD_RESULT_INVALID_ATTR		= 0x01,
+	UIC_CMD_RESULT_FAILURE			= 0x01,
+	UIC_CMD_RESULT_INVALID_ATTR_VALUE	= 0x02,
+	UIC_CMD_RESULT_READ_ONLY_ATTR		= 0x03,
+	UIC_CMD_RESULT_WRITE_ONLY_ATTR		= 0x04,
+	UIC_CMD_RESULT_BAD_INDEX		= 0x05,
+	UIC_CMD_RESULT_LOCKED_ATTR		= 0x06,
+	UIC_CMD_RESULT_BAD_TEST_FEATURE_INDEX	= 0x07,
+	UIC_CMD_RESULT_PEER_COMM_FAILURE	= 0x08,
+	UIC_CMD_RESULT_BUSY			= 0x09,
+	UIC_CMD_RESULT_DME_FAILURE		= 0x0A,
+};
+
+#define MASK_UIC_COMMAND_RESULT			0xFF
+
+#define INT_AGGR_COUNTER_THRESHOLD_VALUE	(0x1F << 8)
+#define INT_AGGR_TIMEOUT_VALUE			(0x02)
+
+/* Interrupt disable masks */
+enum {
+	/* Interrupt disable mask for UFSHCI v1.0 */
+	INTERRUPT_DISABLE_MASK_10	= 0xFFFF,
+
+	/* Interrupt disable mask for UFSHCI v1.1 */
+	INTERRUPT_DISABLE_MASK_11	= 0x0,
+};
+
+/*
+ * Request Descriptor Definitions
+ */
+
+/* Transfer request command type */
+enum {
+	UTP_CMD_TYPE_SCSI		= 0x0,
+	UTP_CMD_TYPE_UFS		= 0x1,
+	UTP_CMD_TYPE_DEV_MANAGE		= 0x2,
+};
+
+enum {
+	UTP_SCSI_COMMAND		= 0x00000000,
+	UTP_NATIVE_UFS_COMMAND		= 0x10000000,
+	UTP_DEVICE_MANAGEMENT_FUNCTION	= 0x20000000,
+	UTP_REQ_DESC_INT_CMD		= 0x01000000,
+};
+
+/* UTP Transfer Request Data Direction (DD) */
+enum {
+	UTP_NO_DATA_TRANSFER	= 0x00000000,
+	UTP_HOST_TO_DEVICE	= 0x02000000,
+	UTP_DEVICE_TO_HOST	= 0x04000000,
+};
+
+/* Overall command status values */
+enum {
+	OCS_SUCCESS			= 0x0,
+	OCS_INVALID_CMD_TABLE_ATTR	= 0x1,
+	OCS_INVALID_PRDT_ATTR		= 0x2,
+	OCS_MISMATCH_DATA_BUF_SIZE	= 0x3,
+	OCS_MISMATCH_RESP_UPIU_SIZE	= 0x4,
+	OCS_PEER_COMM_FAILURE		= 0x5,
+	OCS_ABORTED			= 0x6,
+	OCS_FATAL_ERROR			= 0x7,
+	OCS_INVALID_COMMAND_STATUS	= 0x0F,
+	MASK_OCS			= 0x0F,
+};
+
+/**
+ * struct ufshcd_sg_entry - UFSHCI PRD Entry
+ * @base_addr: Lower 32bit physical address DW-0
+ * @upper_addr: Upper 32bit physical address DW-1
+ * @reserved: Reserved for future use DW-2
+ * @size: size of physical segment DW-3
+ */
+struct ufshcd_sg_entry {
+	u32    base_addr;
+	u32    upper_addr;
+	u32    reserved;
+	u32    size;
+};
+
+/**
+ * struct utp_transfer_cmd_desc - UFS Command Descriptor structure
+ * @command_upiu: Command UPIU Frame address
+ * @response_upiu: Response UPIU Frame address
+ * @prd_table: Physical Region Descriptor
+ */
+struct utp_transfer_cmd_desc {
+	u8 command_upiu[ALIGNED_UPIU_SIZE];
+	u8 response_upiu[ALIGNED_UPIU_SIZE];
+	struct ufshcd_sg_entry    prd_table[SG_ALL];
+};
+
+/**
+ * struct request_desc_header - Descriptor Header common to both UTRD and UTMRD
+ * @dword0: Descriptor Header DW0
+ * @dword1: Descriptor Header DW1
+ * @dword2: Descriptor Header DW2
+ * @dword3: Descriptor Header DW3
+ */
+struct request_desc_header {
+	u32 dword_0;
+	u32 dword_1;
+	u32 dword_2;
+	u32 dword_3;
+};
+
+/**
+ * struct utp_transfer_req_desc - UTRD structure
+ * @header: UTRD header DW-0 to DW-3
+ * @command_desc_base_addr_lo: UCD base address low DW-4
+ * @command_desc_base_addr_hi: UCD base address high DW-5
+ * @response_upiu_length: response UPIU length DW-6
+ * @response_upiu_offset: response UPIU offset DW-6
+ * @prd_table_length: Physical region descriptor length DW-7
+ * @prd_table_offset: Physical region descriptor offset DW-7
+ */
+struct utp_transfer_req_desc {
+
+	/* DW 0-3 */
+	struct request_desc_header header;
+
+	/* DW 4-5*/
+	u32  command_desc_base_addr_lo;
+	u32  command_desc_base_addr_hi;
+
+	/* DW 6 */
+	u16  response_upiu_length;
+	u16  response_upiu_offset;
+
+	/* DW 7 */
+	u16  prd_table_length;
+	u16  prd_table_offset;
+};
+
+/**
+ * struct utp_task_req_desc - UTMRD structure
+ * @header: UTMRD header DW-0 to DW-3
+ * @task_req_upiu: Pointer to task request UPIU DW-4 to DW-11
+ * @task_rsp_upiu: Pointer to task response UPIU DW12 to DW-19
+ */
+struct utp_task_req_desc {
+
+	/* DW 0-3 */
+	struct request_desc_header header;
+
+	/* DW 4-11 */
+	u32 task_req_upiu[TASK_REQ_UPIU_SIZE_DWORDS];
+
+	/* DW 12-19 */
+	u32 task_rsp_upiu[TASK_RSP_UPIU_SIZE_DWORDS];
+};
+
+#endif /* End of Header */
diff --git a/drivers/scsi/ultrastor.c b/drivers/scsi/ultrastor.c
index 7e22b737dfd8..14e0c40a68c9 100644
--- a/drivers/scsi/ultrastor.c
+++ b/drivers/scsi/ultrastor.c
@@ -141,7 +141,6 @@
 #include <linux/delay.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 
 #define ULTRASTOR_PRIVATE	/* Get the private stuff from ultrastor.h */
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 7264116185d5..4411d4224401 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -17,7 +17,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  *
- * Maintained by: Alok N Kataria <akataria@vmware.com>
+ * Maintained by: Arvind Kumar <arvindkumar@vmware.com>
  *
  */
 
@@ -1178,11 +1178,67 @@ static int __devinit pvscsi_allocate_sg(struct pvscsi_adapter *adapter)
 	return 0;
 }
 
+/*
+ * Query the device, fetch the config info and return the
+ * maximum number of targets on the adapter. In case of
+ * failure due to any reason return default i.e. 16.
+ */
+static u32 pvscsi_get_max_targets(struct pvscsi_adapter *adapter)
+{
+	struct PVSCSICmdDescConfigCmd cmd;
+	struct PVSCSIConfigPageHeader *header;
+	struct device *dev;
+	dma_addr_t configPagePA;
+	void *config_page;
+	u32 numPhys = 16;
+
+	dev = pvscsi_dev(adapter);
+	config_page = pci_alloc_consistent(adapter->dev, PAGE_SIZE,
+					   &configPagePA);
+	if (!config_page) {
+		dev_warn(dev, "vmw_pvscsi: failed to allocate memory for config page\n");
+		goto exit;
+	}
+	BUG_ON(configPagePA & ~PAGE_MASK);
+
+	/* Fetch config info from the device. */
+	cmd.configPageAddress = ((u64)PVSCSI_CONFIG_CONTROLLER_ADDRESS) << 32;
+	cmd.configPageNum = PVSCSI_CONFIG_PAGE_CONTROLLER;
+	cmd.cmpAddr = configPagePA;
+	cmd._pad = 0;
+
+	/*
+	 * Mark the completion page header with error values. If the device
+	 * completes the command successfully, it sets the status values to
+	 * indicate success.
+	 */
+	header = config_page;
+	memset(header, 0, sizeof *header);
+	header->hostStatus = BTSTAT_INVPARAM;
+	header->scsiStatus = SDSTAT_CHECK;
+
+	pvscsi_write_cmd_desc(adapter, PVSCSI_CMD_CONFIG, &cmd, sizeof cmd);
+
+	if (header->hostStatus == BTSTAT_SUCCESS &&
+	    header->scsiStatus == SDSTAT_GOOD) {
+		struct PVSCSIConfigPageController *config;
+
+		config = config_page;
+		numPhys = config->numPhys;
+	} else
+		dev_warn(dev, "vmw_pvscsi: PVSCSI_CMD_CONFIG failed. hostStatus = 0x%x, scsiStatus = 0x%x\n",
+			 header->hostStatus, header->scsiStatus);
+	pci_free_consistent(adapter->dev, PAGE_SIZE, config_page, configPagePA);
+exit:
+	return numPhys;
+}
+
 static int __devinit pvscsi_probe(struct pci_dev *pdev,
 				  const struct pci_device_id *id)
 {
 	struct pvscsi_adapter *adapter;
 	struct Scsi_Host *host;
+	struct device *dev;
 	unsigned int i;
 	unsigned long flags = 0;
 	int error;
@@ -1272,6 +1328,13 @@ static int __devinit pvscsi_probe(struct pci_dev *pdev,
 	}
 
 	/*
+	 * Ask the device for max number of targets.
+	 */
+	host->max_id = pvscsi_get_max_targets(adapter);
+	dev = pvscsi_dev(adapter);
+	dev_info(dev, "vmw_pvscsi: host->max_id: %u\n", host->max_id);
+
+	/*
 	 * From this point on we should reset the adapter if anything goes
 	 * wrong.
 	 */
diff --git a/drivers/scsi/vmw_pvscsi.h b/drivers/scsi/vmw_pvscsi.h
index 62e36e75715e..3546e8662e30 100644
--- a/drivers/scsi/vmw_pvscsi.h
+++ b/drivers/scsi/vmw_pvscsi.h
@@ -17,7 +17,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  *
- * Maintained by: Alok N Kataria <akataria@vmware.com>
+ * Maintained by: Arvind Kumar <arvindkumar@vmware.com>
  *
  */
 
@@ -26,7 +26,7 @@
 
 #include <linux/types.h>
 
-#define PVSCSI_DRIVER_VERSION_STRING   "1.0.1.0-k"
+#define PVSCSI_DRIVER_VERSION_STRING   "1.0.2.0-k"
 
 #define PVSCSI_MAX_NUM_SG_ENTRIES_PER_SEGMENT 128
 
@@ -39,28 +39,45 @@
  * host adapter status/error codes
  */
 enum HostBusAdapterStatus {
-   BTSTAT_SUCCESS       = 0x00,  /* CCB complete normally with no errors */
-   BTSTAT_LINKED_COMMAND_COMPLETED           = 0x0a,
-   BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG = 0x0b,
-   BTSTAT_DATA_UNDERRUN = 0x0c,
-   BTSTAT_SELTIMEO      = 0x11,  /* SCSI selection timeout */
-   BTSTAT_DATARUN       = 0x12,  /* data overrun/underrun */
-   BTSTAT_BUSFREE       = 0x13,  /* unexpected bus free */
-   BTSTAT_INVPHASE      = 0x14,  /* invalid bus phase or sequence requested by target */
-   BTSTAT_LUNMISMATCH   = 0x17,  /* linked CCB has different LUN from first CCB */
-   BTSTAT_SENSFAILED    = 0x1b,  /* auto request sense failed */
-   BTSTAT_TAGREJECT     = 0x1c,  /* SCSI II tagged queueing message rejected by target */
-   BTSTAT_BADMSG        = 0x1d,  /* unsupported message received by the host adapter */
-   BTSTAT_HAHARDWARE    = 0x20,  /* host adapter hardware failed */
-   BTSTAT_NORESPONSE    = 0x21,  /* target did not respond to SCSI ATN, sent a SCSI RST */
-   BTSTAT_SENTRST       = 0x22,  /* host adapter asserted a SCSI RST */
-   BTSTAT_RECVRST       = 0x23,  /* other SCSI devices asserted a SCSI RST */
-   BTSTAT_DISCONNECT    = 0x24,  /* target device reconnected improperly (w/o tag) */
-   BTSTAT_BUSRESET      = 0x25,  /* host adapter issued BUS device reset */
-   BTSTAT_ABORTQUEUE    = 0x26,  /* abort queue generated */
-   BTSTAT_HASOFTWARE    = 0x27,  /* host adapter software error */
-   BTSTAT_HATIMEOUT     = 0x30,  /* host adapter hardware timeout error */
-   BTSTAT_SCSIPARITY    = 0x34,  /* SCSI parity error detected */
+	BTSTAT_SUCCESS       = 0x00,  /* CCB complete normally with no errors */
+	BTSTAT_LINKED_COMMAND_COMPLETED           = 0x0a,
+	BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG = 0x0b,
+	BTSTAT_DATA_UNDERRUN = 0x0c,
+	BTSTAT_SELTIMEO      = 0x11,  /* SCSI selection timeout */
+	BTSTAT_DATARUN       = 0x12,  /* data overrun/underrun */
+	BTSTAT_BUSFREE       = 0x13,  /* unexpected bus free */
+	BTSTAT_INVPHASE      = 0x14,  /* invalid bus phase or sequence
+				       * requested by target */
+	BTSTAT_LUNMISMATCH   = 0x17,  /* linked CCB has different LUN from
+				       * first CCB */
+	BTSTAT_INVPARAM      = 0x1a,  /* invalid parameter in CCB or segment
+				       * list */
+	BTSTAT_SENSFAILED    = 0x1b,  /* auto request sense failed */
+	BTSTAT_TAGREJECT     = 0x1c,  /* SCSI II tagged queueing message
+				       * rejected by target */
+	BTSTAT_BADMSG        = 0x1d,  /* unsupported message received by the
+				       * host adapter */
+	BTSTAT_HAHARDWARE    = 0x20,  /* host adapter hardware failed */
+	BTSTAT_NORESPONSE    = 0x21,  /* target did not respond to SCSI ATN,
+				       * sent a SCSI RST */
+	BTSTAT_SENTRST       = 0x22,  /* host adapter asserted a SCSI RST */
+	BTSTAT_RECVRST       = 0x23,  /* other SCSI devices asserted a SCSI
+				       * RST */
+	BTSTAT_DISCONNECT    = 0x24,  /* target device reconnected improperly
+				       * (w/o tag) */
+	BTSTAT_BUSRESET      = 0x25,  /* host adapter issued BUS device reset */
+	BTSTAT_ABORTQUEUE    = 0x26,  /* abort queue generated */
+	BTSTAT_HASOFTWARE    = 0x27,  /* host adapter software error */
+	BTSTAT_HATIMEOUT     = 0x30,  /* host adapter hardware timeout error */
+	BTSTAT_SCSIPARITY    = 0x34,  /* SCSI parity error detected */
+};
+
+/*
+ * SCSI device status values.
+ */
+enum ScsiDeviceStatus {
+	SDSTAT_GOOD  = 0x00, /* No errors. */
+	SDSTAT_CHECK = 0x02, /* Check condition. */
 };
 
 /*
@@ -114,6 +131,29 @@ struct PVSCSICmdDescResetDevice {
 } __packed;
 
 /*
+ * Command descriptor for PVSCSI_CMD_CONFIG --
+ */
+
+struct PVSCSICmdDescConfigCmd {
+	u64 cmpAddr;
+	u64 configPageAddress;
+	u32 configPageNum;
+	u32 _pad;
+} __packed;
+
+enum PVSCSIConfigPageType {
+	PVSCSI_CONFIG_PAGE_CONTROLLER = 0x1958,
+	PVSCSI_CONFIG_PAGE_PHY        = 0x1959,
+	PVSCSI_CONFIG_PAGE_DEVICE     = 0x195a,
+};
+
+enum PVSCSIConfigPageAddressType {
+	PVSCSI_CONFIG_CONTROLLER_ADDRESS = 0x2120,
+	PVSCSI_CONFIG_BUSTARGET_ADDRESS  = 0x2121,
+	PVSCSI_CONFIG_PHY_ADDRESS        = 0x2122,
+};
+
+/*
  * Command descriptor for PVSCSI_CMD_ABORT_CMD --
  *
  * - currently does not support specifying the LUN.
@@ -332,6 +372,27 @@ struct PVSCSIRingCmpDesc {
 	u32	_pad[2];
 } __packed;
 
+struct PVSCSIConfigPageHeader {
+	u32 pageNum;
+	u16 numDwords;
+	u16 hostStatus;
+	u16 scsiStatus;
+	u16 reserved[3];
+} __packed;
+
+struct PVSCSIConfigPageController {
+	struct PVSCSIConfigPageHeader header;
+	u64 nodeWWN; /* Device name as defined in the SAS spec. */
+	u16 manufacturer[64];
+	u16 serialNumber[64];
+	u16 opromVersion[32];
+	u16 hwVersion[32];
+	u16 firmwareVersion[32];
+	u32 numPhys;
+	u8  useConsecutivePhyWWNs;
+	u8  reserved[3];
+} __packed;
+
 /*
  * Interrupt status / IRQ bits.
  */
diff --git a/drivers/scsi/wd7000.c b/drivers/scsi/wd7000.c
index 9ee0afef2d16..d89a5dfd3ade 100644
--- a/drivers/scsi/wd7000.c
+++ b/drivers/scsi/wd7000.c
@@ -179,7 +179,6 @@
 #include <linux/stat.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 #include <asm/dma.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/sh/intc/balancing.c b/drivers/sh/intc/balancing.c
index cec7a96f2c09..bc780807ccb0 100644
--- a/drivers/sh/intc/balancing.c
+++ b/drivers/sh/intc/balancing.c
@@ -9,7 +9,7 @@
  */
 #include "internals.h"
 
-static unsigned long dist_handle[NR_IRQS];
+static unsigned long dist_handle[INTC_NR_IRQS];
 
 void intc_balancing_enable(unsigned int irq)
 {
diff --git a/drivers/sh/intc/chip.c b/drivers/sh/intc/chip.c
index 7b246efa94ea..012df2676a26 100644
--- a/drivers/sh/intc/chip.c
+++ b/drivers/sh/intc/chip.c
@@ -2,13 +2,14 @@
  * IRQ chip definitions for INTC IRQs.
  *
  * Copyright (C) 2007, 2008 Magnus Damm
- * Copyright (C) 2009, 2010 Paul Mundt
+ * Copyright (C) 2009 - 2012 Paul Mundt
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
 #include <linux/cpumask.h>
+#include <linux/bsearch.h>
 #include <linux/io.h>
 #include "internals.h"
 
@@ -58,11 +59,6 @@ static void intc_disable(struct irq_data *data)
 	}
 }
 
-static int intc_set_wake(struct irq_data *data, unsigned int on)
-{
-	return 0; /* allow wakeup, but setup hardware in intc_suspend() */
-}
-
 #ifdef CONFIG_SMP
 /*
  * This is held with the irq desc lock held, so we don't require any
@@ -78,7 +74,7 @@ static int intc_set_affinity(struct irq_data *data,
 
 	cpumask_copy(data->affinity, cpumask);
 
-	return 0;
+	return IRQ_SET_MASK_OK_NOCOPY;
 }
 #endif
 
@@ -122,28 +118,12 @@ static struct intc_handle_int *intc_find_irq(struct intc_handle_int *hp,
 					     unsigned int nr_hp,
 					     unsigned int irq)
 {
-	int i;
-
-	/*
-	 * this doesn't scale well, but...
-	 *
-	 * this function should only be used for cerain uncommon
-	 * operations such as intc_set_priority() and intc_set_type()
-	 * and in those rare cases performance doesn't matter that much.
-	 * keeping the memory footprint low is more important.
-	 *
-	 * one rather simple way to speed this up and still keep the
-	 * memory footprint down is to make sure the array is sorted
-	 * and then perform a bisect to lookup the irq.
-	 */
-	for (i = 0; i < nr_hp; i++) {
-		if ((hp + i)->irq != irq)
-			continue;
+	struct intc_handle_int key;
 
-		return hp + i;
-	}
+	key.irq = irq;
+	key.handle = 0;
 
-	return NULL;
+	return bsearch(&key, hp, nr_hp, sizeof(*hp), intc_handle_int_cmp);
 }
 
 int intc_set_priority(unsigned int irq, unsigned int prio)
@@ -223,10 +203,9 @@ struct irq_chip intc_irq_chip	= {
 	.irq_mask_ack		= intc_mask_ack,
 	.irq_enable		= intc_enable,
 	.irq_disable		= intc_disable,
-	.irq_shutdown		= intc_disable,
 	.irq_set_type		= intc_set_type,
-	.irq_set_wake		= intc_set_wake,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= intc_set_affinity,
 #endif
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c
index e53e449b4eca..7e562ccb6997 100644
--- a/drivers/sh/intc/core.c
+++ b/drivers/sh/intc/core.c
@@ -2,7 +2,7 @@
  * Shared interrupt handling code for IPR and INTC2 types of IRQs.
  *
  * Copyright (C) 2007, 2008 Magnus Damm
- * Copyright (C) 2009, 2010 Paul Mundt
+ * Copyright (C) 2009 - 2012 Paul Mundt
  *
  * Based on intc2.c and ipr.c
  *
@@ -31,18 +31,19 @@
 #include <linux/spinlock.h>
 #include <linux/radix-tree.h>
 #include <linux/export.h>
+#include <linux/sort.h>
 #include "internals.h"
 
 LIST_HEAD(intc_list);
 DEFINE_RAW_SPINLOCK(intc_big_lock);
-unsigned int nr_intc_controllers;
+static unsigned int nr_intc_controllers;
 
 /*
  * Default priority level
  * - this needs to be at least 2 for 5-bit priorities on 7780
  */
 static unsigned int default_prio_level = 2;	/* 2 - 16 */
-static unsigned int intc_prio_level[NR_IRQS];	/* for now */
+static unsigned int intc_prio_level[INTC_NR_IRQS];	/* for now */
 
 unsigned int intc_get_dfl_prio_level(void)
 {
@@ -267,6 +268,9 @@ int __init register_intc_controller(struct intc_desc *desc)
 			k += save_reg(d, k, hw->prio_regs[i].set_reg, smp);
 			k += save_reg(d, k, hw->prio_regs[i].clr_reg, smp);
 		}
+
+		sort(d->prio, hw->nr_prio_regs, sizeof(*d->prio),
+		     intc_handle_int_cmp, NULL);
 	}
 
 	if (hw->sense_regs) {
@@ -277,6 +281,9 @@ int __init register_intc_controller(struct intc_desc *desc)
 
 		for (i = 0; i < hw->nr_sense_regs; i++)
 			k += save_reg(d, k, hw->sense_regs[i].reg, 0);
+
+		sort(d->sense, hw->nr_sense_regs, sizeof(*d->sense),
+		     intc_handle_int_cmp, NULL);
 	}
 
 	if (hw->subgroups)
diff --git a/drivers/sh/intc/handle.c b/drivers/sh/intc/handle.c
index 057ce56829bf..7863a44918a2 100644
--- a/drivers/sh/intc/handle.c
+++ b/drivers/sh/intc/handle.c
@@ -13,7 +13,7 @@
 #include <linux/spinlock.h>
 #include "internals.h"
 
-static unsigned long ack_handle[NR_IRQS];
+static unsigned long ack_handle[INTC_NR_IRQS];
 
 static intc_enum __init intc_grp_id(struct intc_desc *desc,
 				    intc_enum enum_id)
@@ -172,9 +172,8 @@ intc_get_prio_handle(struct intc_desc *desc, struct intc_desc_int *d,
 	return 0;
 }
 
-static unsigned int __init intc_ack_data(struct intc_desc *desc,
-					  struct intc_desc_int *d,
-					  intc_enum enum_id)
+static unsigned int intc_ack_data(struct intc_desc *desc,
+				  struct intc_desc_int *d, intc_enum enum_id)
 {
 	struct intc_mask_reg *mr = desc->hw.ack_regs;
 	unsigned int i, j, fn, mode;
diff --git a/drivers/sh/intc/internals.h b/drivers/sh/intc/internals.h
index b0e9155ff739..f034a979a16f 100644
--- a/drivers/sh/intc/internals.h
+++ b/drivers/sh/intc/internals.h
@@ -108,6 +108,14 @@ static inline void activate_irq(int irq)
 #endif
 }
 
+static inline int intc_handle_int_cmp(const void *a, const void *b)
+{
+	const struct intc_handle_int *_a = a;
+	const struct intc_handle_int *_b = b;
+
+	return _a->irq - _b->irq;
+}
+
 /* access.c */
 extern unsigned long
 (*intc_reg_fns[])(unsigned long addr, unsigned long h, unsigned long data);
@@ -157,7 +165,6 @@ void _intc_enable(struct irq_data *data, unsigned long handle);
 /* core.c */
 extern struct list_head intc_list;
 extern raw_spinlock_t intc_big_lock;
-extern unsigned int nr_intc_controllers;
 extern struct bus_type intc_subsys;
 
 unsigned int intc_get_dfl_prio_level(void);
diff --git a/drivers/sh/intc/virq.c b/drivers/sh/intc/virq.c
index c7ec49ffd9f6..93cec21e788b 100644
--- a/drivers/sh/intc/virq.c
+++ b/drivers/sh/intc/virq.c
@@ -17,7 +17,7 @@
 #include <linux/export.h>
 #include "internals.h"
 
-static struct intc_map_entry intc_irq_xlate[NR_IRQS];
+static struct intc_map_entry intc_irq_xlate[INTC_NR_IRQS];
 
 struct intc_virq_list {
 	unsigned int irq;
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 8418eb036651..b9f0192758d6 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
+#include <linux/types.h>
 
 #include "spi-dw.h"
 
@@ -136,6 +137,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	txconf.dst_maxburst = LNW_DMA_MSIZE_16;
 	txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	txconf.device_fc = false;
 
 	txchan->device->device_control(txchan, DMA_SLAVE_CONFIG,
 				       (unsigned long) &txconf);
@@ -144,7 +146,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	dws->tx_sgl.dma_address = dws->tx_dma;
 	dws->tx_sgl.length = dws->len;
 
-	txdesc = txchan->device->device_prep_slave_sg(txchan,
+	txdesc = dmaengine_prep_slave_sg(txchan,
 				&dws->tx_sgl,
 				1,
 				DMA_MEM_TO_DEV,
@@ -158,6 +160,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	rxconf.src_maxburst = LNW_DMA_MSIZE_16;
 	rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	rxconf.device_fc = false;
 
 	rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG,
 				       (unsigned long) &rxconf);
@@ -166,7 +169,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	dws->rx_sgl.dma_address = dws->rx_dma;
 	dws->rx_sgl.length = dws->len;
 
-	rxdesc = rxchan->device->device_prep_slave_sg(rxchan,
+	rxdesc = dmaengine_prep_slave_sg(rxchan,
 				&dws->rx_sgl,
 				1,
 				DMA_DEV_TO_MEM,
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index 082458d73ce9..d1a495f64e2d 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -63,12 +63,6 @@ struct chip_data {
 };
 
 #ifdef CONFIG_DEBUG_FS
-static int spi_show_regs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 #define SPI_REGS_BUFSIZE	1024
 static ssize_t  spi_show_regs(struct file *file, char __user *user_buf,
 				size_t count, loff_t *ppos)
@@ -128,7 +122,7 @@ static ssize_t  spi_show_regs(struct file *file, char __user *user_buf,
 
 static const struct file_operations mrst_spi_regs_ops = {
 	.owner		= THIS_MODULE,
-	.open		= spi_show_regs_open,
+	.open		= simple_open,
 	.read		= spi_show_regs,
 	.llseek		= default_llseek,
 };
diff --git a/drivers/spi/spi-ep93xx.c b/drivers/spi/spi-ep93xx.c
index d46e55c720b7..6db2887852d6 100644
--- a/drivers/spi/spi-ep93xx.c
+++ b/drivers/spi/spi-ep93xx.c
@@ -633,8 +633,8 @@ ep93xx_spi_dma_prepare(struct ep93xx_spi *espi, enum dma_data_direction dir)
 	if (!nents)
 		return ERR_PTR(-ENOMEM);
 
-	txd = chan->device->device_prep_slave_sg(chan, sgt->sgl, nents,
-						 slave_dirn, DMA_CTRL_ACK);
+	txd = dmaengine_prep_slave_sg(chan, sgt->sgl, nents,
+					slave_dirn, DMA_CTRL_ACK);
 	if (!txd) {
 		dma_unmap_sg(chan->device->dev, sgt->sgl, sgt->nents, dir);
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c
index 610f7391456e..9b0d71696039 100644
--- a/drivers/spi/spi-omap-uwire.c
+++ b/drivers/spi/spi-omap-uwire.c
@@ -47,7 +47,6 @@
 #include <linux/spi/spi_bitbang.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
 #include <asm/io.h>
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 13448c832c44..e496f799b7a9 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -359,11 +359,6 @@ static int orion_spi_setup(struct spi_device *spi)
 
 	orion_spi = spi_master_get_devdata(spi->master);
 
-	/* Fix ac timing if required.   */
-	if (orion_spi->spi_info->enable_clock_fix)
-		orion_spi_setbits(orion_spi, ORION_SPI_IF_CONFIG_REG,
-				  (1 << 14));
-
 	if ((spi->max_speed_hz == 0)
 			|| (spi->max_speed_hz > orion_spi->max_speed))
 		spi->max_speed_hz = orion_spi->max_speed;
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index dc8485d1e883..96f0da66b185 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -880,10 +880,12 @@ static int configure_dma(struct pl022 *pl022)
 	struct dma_slave_config rx_conf = {
 		.src_addr = SSP_DR(pl022->phybase),
 		.direction = DMA_DEV_TO_MEM,
+		.device_fc = false,
 	};
 	struct dma_slave_config tx_conf = {
 		.dst_addr = SSP_DR(pl022->phybase),
 		.direction = DMA_MEM_TO_DEV,
+		.device_fc = false,
 	};
 	unsigned int pages;
 	int ret;
@@ -1017,7 +1019,7 @@ static int configure_dma(struct pl022 *pl022)
 		goto err_tx_sgmap;
 
 	/* Send both scatterlists */
-	rxdesc = rxchan->device->device_prep_slave_sg(rxchan,
+	rxdesc = dmaengine_prep_slave_sg(rxchan,
 				      pl022->sgt_rx.sgl,
 				      rx_sglen,
 				      DMA_DEV_TO_MEM,
@@ -1025,7 +1027,7 @@ static int configure_dma(struct pl022 *pl022)
 	if (!rxdesc)
 		goto err_rxdesc;
 
-	txdesc = txchan->device->device_prep_slave_sg(txchan,
+	txdesc = dmaengine_prep_slave_sg(txchan,
 				      pl022->sgt_tx.sgl,
 				      tx_sglen,
 				      DMA_MEM_TO_DEV,
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index 5c6fa5ed3366..ec47d3bdfd13 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -1099,7 +1099,7 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 		sg_dma_address(sg) = dma->rx_buf_dma + sg->offset;
 	}
 	sg = dma->sg_rx_p;
-	desc_rx = dma->chan_rx->device->device_prep_slave_sg(dma->chan_rx, sg,
+	desc_rx = dmaengine_prep_slave_sg(dma->chan_rx, sg,
 					num, DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_rx) {
@@ -1158,7 +1158,7 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 		sg_dma_address(sg) = dma->tx_buf_dma + sg->offset;
 	}
 	sg = dma->sg_tx_p;
-	desc_tx = dma->chan_tx->device->device_prep_slave_sg(dma->chan_tx,
+	desc_tx = dmaengine_prep_slave_sg(dma->chan_tx,
 					sg, num, DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_tx) {
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index 59e095362c81..c2832124bb3e 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -381,8 +381,7 @@ int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
 
 repeat:
 	fdt = files_fdtable(files);
-	fd = find_next_zero_bit(fdt->open_fds->fds_bits, fdt->max_fds,
-				files->next_fd);
+	fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, files->next_fd);
 
 	/*
 	 * N.B. For clone tasks sharing a files structure, this test
@@ -410,11 +409,11 @@ repeat:
 		goto repeat;
 	}
 
-	FD_SET(fd, fdt->open_fds);
+	__set_open_fd(fd, fdt);
 	if (flags & O_CLOEXEC)
-		FD_SET(fd, fdt->close_on_exec);
+		__set_close_on_exec(fd, fdt);
 	else
-		FD_CLR(fd, fdt->close_on_exec);
+		__clear_close_on_exec(fd, fdt);
 	files->next_fd = fd + 1;
 #if 1
 	/* Sanity check */
@@ -455,7 +454,7 @@ static void task_fd_install(
 static void __put_unused_fd(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = files_fdtable(files);
-	__FD_CLR(fd, fdt->open_fds);
+	__clear_open_fd(fd, fdt);
 	if (fd < files->next_fd)
 		files->next_fd = fd;
 }
@@ -481,7 +480,7 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
 	if (!filp)
 		goto out_unlock;
 	rcu_assign_pointer(fdt->fd[fd], NULL);
-	FD_CLR(fd, fdt->close_on_exec);
+	__clear_close_on_exec(fd, fdt);
 	__put_unused_fd(files, fd);
 	spin_unlock(&files->file_lock);
 	retval = filp_close(filp, files);
diff --git a/drivers/staging/asus_oled/README b/drivers/staging/asus_oled/README
index 0d82a6d5fa58..2d721232467a 100644
--- a/drivers/staging/asus_oled/README
+++ b/drivers/staging/asus_oled/README
@@ -52,7 +52,7 @@ Configuration
 
    There is only one option: start_off.
    You can use it by: 'modprobe asus_oled start_off=1', or by adding this
-   line to /etc/modprobe.conf:
+   line to /etc/modprobe.d/asus_oled.conf:
    options asus_oled start_off=1
 
    With this option provided, asus_oled driver will switch off the display
diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c
index db1fd63aaab3..bf185e2807d1 100644
--- a/drivers/staging/comedi/drivers.c
+++ b/drivers/staging/comedi/drivers.c
@@ -42,7 +42,6 @@
 #include <linux/cdev.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
-#include <asm/system.h>
 
 #include "comedidev.h"
 #include "internal.h"
diff --git a/drivers/staging/comedi/drivers/cb_pcidas64.c b/drivers/staging/comedi/drivers/cb_pcidas64.c
index c9e8c4785768..915157d47805 100644
--- a/drivers/staging/comedi/drivers/cb_pcidas64.c
+++ b/drivers/staging/comedi/drivers/cb_pcidas64.c
@@ -86,7 +86,6 @@ TODO:
 #include "../comedidev.h"
 #include <linux/delay.h>
 #include <linux/interrupt.h>
-#include <asm/system.h>
 
 #include "comedi_pci.h"
 #include "8253.h"
diff --git a/drivers/staging/comedi/drivers/mite.c b/drivers/staging/comedi/drivers/mite.c
index fd274e9c7b78..13e9c8071696 100644
--- a/drivers/staging/comedi/drivers/mite.c
+++ b/drivers/staging/comedi/drivers/mite.c
@@ -55,7 +55,6 @@
 #include "comedi_pci.h"
 #include "../comedidev.h"
 
-#include <asm/system.h>
 
 #define PCI_MITE_SIZE		4096
 #define PCI_DAQ_SIZE		4096
diff --git a/drivers/staging/crystalhd/bc_dts_defs.h b/drivers/staging/crystalhd/bc_dts_defs.h
index 8cd51a7aad8e..647e116e10de 100644
--- a/drivers/staging/crystalhd/bc_dts_defs.h
+++ b/drivers/staging/crystalhd/bc_dts_defs.h
@@ -26,6 +26,8 @@
 #ifndef _BC_DTS_DEFS_H_
 #define _BC_DTS_DEFS_H_
 
+#include <linux/types.h>
+
 /* BIT Mask */
 #define BC_BIT(_x)		(1 << (_x))
 
diff --git a/drivers/staging/crystalhd/crystalhd.h b/drivers/staging/crystalhd/crystalhd.h
index 3f4d79515026..b3a550bd5b06 100644
--- a/drivers/staging/crystalhd/crystalhd.h
+++ b/drivers/staging/crystalhd/crystalhd.h
@@ -1,7 +1,6 @@
 #ifndef _CRYSTALHD_H_
 #define _CRYSTALHD_H_
 
-#include <asm/system.h>
 #include "bc_dts_defs.h"
 #include "crystalhd_misc.h"
 #include "bc_dts_glob_lnx.h"
diff --git a/drivers/staging/crystalhd/crystalhd_lnx.h b/drivers/staging/crystalhd/crystalhd_lnx.h
index a81f9298b0a1..a9e36336d097 100644
--- a/drivers/staging/crystalhd/crystalhd_lnx.h
+++ b/drivers/staging/crystalhd/crystalhd_lnx.h
@@ -45,7 +45,6 @@
 #include <linux/io.h>
 #include <asm/irq.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <linux/uaccess.h>
 
 #include "crystalhd.h"
diff --git a/drivers/staging/crystalhd/crystalhd_misc.h b/drivers/staging/crystalhd/crystalhd_misc.h
index 84c87938a831..8cdaa7a34814 100644
--- a/drivers/staging/crystalhd/crystalhd_misc.h
+++ b/drivers/staging/crystalhd/crystalhd_misc.h
@@ -37,6 +37,7 @@
 #include <linux/ioctl.h>
 #include <linux/dma-mapping.h>
 #include <linux/sched.h>
+#include "bc_dts_glob_lnx.h"
 
 /* Global log level variable defined in crystal_misc.c file */
 extern uint32_t g_linklog_level;
diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c
index 3f919babe79b..886f5650444e 100644
--- a/drivers/staging/et131x/et131x.c
+++ b/drivers/staging/et131x/et131x.c
@@ -70,7 +70,6 @@
 #include <linux/delay.h>
 #include <linux/bitops.h>
 #include <linux/io.h>
-#include <asm/system.h>
 
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/staging/ft1000/ft1000-pcmcia/ft1000_hw.c b/drivers/staging/ft1000/ft1000-pcmcia/ft1000_hw.c
index 7569aa0f24d1..c4a8a0a26eb5 100644
--- a/drivers/staging/ft1000/ft1000-pcmcia/ft1000_hw.c
+++ b/drivers/staging/ft1000/ft1000-pcmcia/ft1000_hw.c
@@ -29,7 +29,6 @@
 #include <linux/interrupt.h>
 #include <linux/in.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/bitops.h>
 
 #include <linux/netdevice.h>
diff --git a/drivers/staging/media/go7007/go7007-driver.c b/drivers/staging/media/go7007/go7007-driver.c
index 6c9279a6d606..ece2dd146487 100644
--- a/drivers/staging/media/go7007/go7007-driver.c
+++ b/drivers/staging/media/go7007/go7007-driver.c
@@ -30,7 +30,6 @@
 #include <linux/mutex.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <linux/videodev2.h>
 #include <media/tuner.h>
 #include <media/v4l2-common.h>
diff --git a/drivers/staging/media/go7007/go7007-i2c.c b/drivers/staging/media/go7007/go7007-i2c.c
index b8cfa1a6eaeb..6bc82aaeef11 100644
--- a/drivers/staging/media/go7007/go7007-i2c.c
+++ b/drivers/staging/media/go7007/go7007-i2c.c
@@ -26,7 +26,6 @@
 #include <linux/i2c.h>
 #include <linux/mutex.h>
 #include <linux/uaccess.h>
-#include <asm/system.h>
 
 #include "go7007-priv.h"
 #include "wis-i2c.h"
diff --git a/drivers/staging/media/go7007/go7007-v4l2.c b/drivers/staging/media/go7007/go7007-v4l2.c
index f91658670e34..3ef4cd8b4de3 100644
--- a/drivers/staging/media/go7007/go7007-v4l2.c
+++ b/drivers/staging/media/go7007/go7007-v4l2.c
@@ -34,7 +34,6 @@
 #include <linux/i2c.h>
 #include <linux/mutex.h>
 #include <linux/uaccess.h>
-#include <asm/system.h>
 
 #include "go7007.h"
 #include "go7007-priv.h"
diff --git a/drivers/staging/media/go7007/snd-go7007.c b/drivers/staging/media/go7007/snd-go7007.c
index d071c838ac2a..5af29ff68bfd 100644
--- a/drivers/staging/media/go7007/snd-go7007.c
+++ b/drivers/staging/media/go7007/snd-go7007.c
@@ -29,7 +29,6 @@
 #include <linux/mutex.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/initval.h>
diff --git a/drivers/staging/media/lirc/lirc_serial.c b/drivers/staging/media/lirc/lirc_serial.c
index 97352cf6bd98..3295ea63f3eb 100644
--- a/drivers/staging/media/lirc/lirc_serial.c
+++ b/drivers/staging/media/lirc/lirc_serial.c
@@ -66,7 +66,6 @@
 #include <linux/poll.h>
 #include <linux/platform_device.h>
 
-#include <asm/system.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/fcntl.h>
diff --git a/drivers/staging/media/lirc/lirc_sir.c b/drivers/staging/media/lirc/lirc_sir.c
index c94382b917ac..945d9623550b 100644
--- a/drivers/staging/media/lirc/lirc_sir.c
+++ b/drivers/staging/media/lirc/lirc_sir.c
@@ -49,7 +49,6 @@
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/poll.h>
-#include <asm/system.h>
 #include <linux/io.h>
 #include <asm/irq.h>
 #include <linux/fcntl.h>
diff --git a/drivers/staging/mei/wd.c b/drivers/staging/mei/wd.c
index a6910da78a64..cf4c29d10e7f 100644
--- a/drivers/staging/mei/wd.c
+++ b/drivers/staging/mei/wd.c
@@ -323,6 +323,7 @@ static int mei_wd_ops_set_timeout(struct watchdog_device *wd_dev, unsigned int t
 	mutex_lock(&dev->device_lock);
 
 	dev->wd_timeout = timeout;
+	wd_dev->timeout = timeout;
 	mei_wd_set_start_timeout(dev, dev->wd_timeout);
 
 	mutex_unlock(&dev->device_lock);
diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c
index 4683d5f355c0..6183573f112f 100644
--- a/drivers/staging/panel/panel.c
+++ b/drivers/staging/panel/panel.c
@@ -58,7 +58,6 @@
 
 #include <linux/io.h>
 #include <linux/uaccess.h>
-#include <asm/system.h>
 
 #define LCD_MINOR		156
 #define KEYPAD_MINOR		185
diff --git a/drivers/staging/sbe-2t3e3/io.c b/drivers/staging/sbe-2t3e3/io.c
index b458ff034067..9a50bcc59594 100644
--- a/drivers/staging/sbe-2t3e3/io.c
+++ b/drivers/staging/sbe-2t3e3/io.c
@@ -11,7 +11,6 @@
  */
 
 #include <linux/ip.h>
-#include <asm/system.h>
 #include "2t3e3.h"
 #include "ctrl.h"
 
diff --git a/drivers/staging/ste_rmi4/Makefile b/drivers/staging/ste_rmi4/Makefile
index 176f46900571..e4c03351420f 100644
--- a/drivers/staging/ste_rmi4/Makefile
+++ b/drivers/staging/ste_rmi4/Makefile
@@ -2,4 +2,4 @@
 # Makefile for the RMI4 touchscreen driver.
 #
 obj-$(CONFIG_TOUCHSCREEN_SYNAPTICS_I2C_RMI4) += synaptics_i2c_rmi4.o
-obj-$(CONFIG_MACH_U8500) += board-mop500-u8500uib-rmi4.o
+obj-$(CONFIG_MACH_MOP500) += board-mop500-u8500uib-rmi4.o
diff --git a/drivers/staging/telephony/phonedev.c b/drivers/staging/telephony/phonedev.c
index 1915af201175..1dd0b6717ccc 100644
--- a/drivers/staging/telephony/phonedev.c
+++ b/drivers/staging/telephony/phonedev.c
@@ -24,7 +24,6 @@
 #include <linux/phonedev.h>
 #include <linux/init.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include <linux/kmod.h>
 #include <linux/sem.h>
diff --git a/drivers/staging/tidspbridge/include/dspbridge/host_os.h b/drivers/staging/tidspbridge/include/dspbridge/host_os.h
index a2f31c69d12e..ed00d3da3205 100644
--- a/drivers/staging/tidspbridge/include/dspbridge/host_os.h
+++ b/drivers/staging/tidspbridge/include/dspbridge/host_os.h
@@ -17,7 +17,6 @@
 #ifndef _HOST_OS_H_
 #define _HOST_OS_H_
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <linux/semaphore.h>
 #include <linux/uaccess.h>
diff --git a/drivers/staging/wlags49_h2/wl_cs.c b/drivers/staging/wlags49_h2/wl_cs.c
index a2cbb29c3f59..7084f414846e 100644
--- a/drivers/staging/wlags49_h2/wl_cs.c
+++ b/drivers/staging/wlags49_h2/wl_cs.c
@@ -74,7 +74,6 @@
 #include <linux/in.h>
 #include <linux/delay.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/bitops.h>
 
 #include <linux/netdevice.h>
diff --git a/drivers/staging/wlags49_h2/wl_main.c b/drivers/staging/wlags49_h2/wl_main.c
index dab603e0f452..d5bf0a7012f2 100644
--- a/drivers/staging/wlags49_h2/wl_main.c
+++ b/drivers/staging/wlags49_h2/wl_main.c
@@ -86,8 +86,7 @@
 // #include <linux/in.h>
 // #include <linux/delay.h>
 // #include <asm/io.h>
-// #include <asm/system.h>
-// #include <asm/bitops.h>
+// // #include <asm/bitops.h>
 #include <linux/unistd.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/staging/wlags49_h2/wl_netdev.c b/drivers/staging/wlags49_h2/wl_netdev.c
index 9c16f5478a75..90820ff1aced 100644
--- a/drivers/staging/wlags49_h2/wl_netdev.c
+++ b/drivers/staging/wlags49_h2/wl_netdev.c
@@ -79,8 +79,7 @@
 // #include <linux/delay.h>
 // #include <linux/skbuff.h>
 // #include <asm/io.h>
-// #include <asm/system.h>
-// #include <asm/bitops.h>
+// // #include <asm/bitops.h>
 
 #include <linux/netdevice.h>
 #include <linux/ethtool.h>
diff --git a/drivers/staging/wlags49_h2/wl_pci.c b/drivers/staging/wlags49_h2/wl_pci.c
index 2bd9b84ace8e..3df990c7306a 100644
--- a/drivers/staging/wlags49_h2/wl_pci.c
+++ b/drivers/staging/wlags49_h2/wl_pci.c
@@ -77,7 +77,6 @@
 #include <linux/interrupt.h>
 #include <linux/in.h>
 #include <linux/delay.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/bitops.h>
diff --git a/drivers/staging/wlags49_h2/wl_util.c b/drivers/staging/wlags49_h2/wl_util.c
index b748a3ff7954..f104e6f1e980 100644
--- a/drivers/staging/wlags49_h2/wl_util.c
+++ b/drivers/staging/wlags49_h2/wl_util.c
@@ -73,8 +73,7 @@
 // #include <linux/in.h>
 // #include <linux/delay.h>
 // #include <asm/io.h>
-// #include <asm/system.h>
-// #include <asm/bitops.h>
+// // #include <asm/bitops.h>
 
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index f7f71b2d3101..514a691abea0 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -18,3 +18,11 @@ config THERMAL_HWMON
 	depends on THERMAL
 	depends on HWMON=y || HWMON=THERMAL
 	default y
+
+config SPEAR_THERMAL
+	bool "SPEAr thermal sensor driver"
+	depends on THERMAL
+	depends on PLAT_SPEAR
+	help
+	  Enable this to plug the SPEAr thermal sensor driver into the Linux
+	  thermal framework
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 31108a01c22e..a9fff0bf4b14 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -3,3 +3,4 @@
 #
 
 obj-$(CONFIG_THERMAL)		+= thermal_sys.o
+obj-$(CONFIG_SPEAR_THERMAL)		+= spear_thermal.o
\ No newline at end of file
diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c
new file mode 100644
index 000000000000..c2e32df3b164
--- /dev/null
+++ b/drivers/thermal/spear_thermal.c
@@ -0,0 +1,206 @@
+/*
+ * SPEAr thermal driver.
+ *
+ * Copyright (C) 2011-2012 ST Microelectronics
+ * Author: Vincenzo Frascino <vincenzo.frascino@st.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/spear_thermal.h>
+#include <linux/thermal.h>
+
+#define MD_FACTOR	1000
+
+/* SPEAr Thermal Sensor Dev Structure */
+struct spear_thermal_dev {
+	/* pointer to base address of the thermal sensor */
+	void __iomem *thermal_base;
+	/* clk structure */
+	struct clk *clk;
+	/* pointer to thermal flags */
+	unsigned int flags;
+};
+
+static inline int thermal_get_temp(struct thermal_zone_device *thermal,
+				unsigned long *temp)
+{
+	struct spear_thermal_dev *stdev = thermal->devdata;
+
+	/*
+	 * Data are ready to be read after 628 usec from POWERDOWN signal
+	 * (PDN) = 1
+	 */
+	*temp = (readl_relaxed(stdev->thermal_base) & 0x7F) * MD_FACTOR;
+	return 0;
+}
+
+static struct thermal_zone_device_ops ops = {
+	.get_temp = thermal_get_temp,
+};
+
+#ifdef CONFIG_PM
+static int spear_thermal_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
+	struct spear_thermal_dev *stdev = spear_thermal->devdata;
+	unsigned int actual_mask = 0;
+
+	/* Disable SPEAr Thermal Sensor */
+	actual_mask = readl_relaxed(stdev->thermal_base);
+	writel_relaxed(actual_mask & ~stdev->flags, stdev->thermal_base);
+
+	clk_disable(stdev->clk);
+	dev_info(dev, "Suspended.\n");
+
+	return 0;
+}
+
+static int spear_thermal_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
+	struct spear_thermal_dev *stdev = spear_thermal->devdata;
+	unsigned int actual_mask = 0;
+	int ret = 0;
+
+	ret = clk_enable(stdev->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't enable clock\n");
+		return ret;
+	}
+
+	/* Enable SPEAr Thermal Sensor */
+	actual_mask = readl_relaxed(stdev->thermal_base);
+	writel_relaxed(actual_mask | stdev->flags, stdev->thermal_base);
+
+	dev_info(dev, "Resumed.\n");
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(spear_thermal_pm_ops, spear_thermal_suspend,
+		spear_thermal_resume);
+
+static int spear_thermal_probe(struct platform_device *pdev)
+{
+	struct thermal_zone_device *spear_thermal = NULL;
+	struct spear_thermal_dev *stdev;
+	struct spear_thermal_pdata *pdata;
+	int ret = 0;
+	struct resource *stres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	if (!stres) {
+		dev_err(&pdev->dev, "memory resource missing\n");
+		return -ENODEV;
+	}
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "platform data is NULL\n");
+		return -EINVAL;
+	}
+
+	stdev = devm_kzalloc(&pdev->dev, sizeof(*stdev), GFP_KERNEL);
+	if (!stdev) {
+		dev_err(&pdev->dev, "kzalloc fail\n");
+		return -ENOMEM;
+	}
+
+	/* Enable thermal sensor */
+	stdev->thermal_base = devm_ioremap(&pdev->dev, stres->start,
+			resource_size(stres));
+	if (!stdev->thermal_base) {
+		dev_err(&pdev->dev, "ioremap failed\n");
+		return -ENOMEM;
+	}
+
+	stdev->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(stdev->clk)) {
+		dev_err(&pdev->dev, "Can't get clock\n");
+		return PTR_ERR(stdev->clk);
+	}
+
+	ret = clk_enable(stdev->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't enable clock\n");
+		goto put_clk;
+	}
+
+	stdev->flags = pdata->thermal_flags;
+	writel_relaxed(stdev->flags, stdev->thermal_base);
+
+	spear_thermal = thermal_zone_device_register("spear_thermal", 0,
+				stdev, &ops, 0, 0, 0, 0);
+	if (IS_ERR(spear_thermal)) {
+		dev_err(&pdev->dev, "thermal zone device is NULL\n");
+		ret = PTR_ERR(spear_thermal);
+		goto disable_clk;
+	}
+
+	platform_set_drvdata(pdev, spear_thermal);
+
+	dev_info(&spear_thermal->device, "Thermal Sensor Loaded at: 0x%p.\n",
+			stdev->thermal_base);
+
+	return 0;
+
+disable_clk:
+	clk_disable(stdev->clk);
+put_clk:
+	clk_put(stdev->clk);
+
+	return ret;
+}
+
+static int spear_thermal_exit(struct platform_device *pdev)
+{
+	unsigned int actual_mask = 0;
+	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
+	struct spear_thermal_dev *stdev = spear_thermal->devdata;
+
+	thermal_zone_device_unregister(spear_thermal);
+	platform_set_drvdata(pdev, NULL);
+
+	/* Disable SPEAr Thermal Sensor */
+	actual_mask = readl_relaxed(stdev->thermal_base);
+	writel_relaxed(actual_mask & ~stdev->flags, stdev->thermal_base);
+
+	clk_disable(stdev->clk);
+	clk_put(stdev->clk);
+
+	return 0;
+}
+
+static struct platform_driver spear_thermal_driver = {
+	.probe = spear_thermal_probe,
+	.remove = spear_thermal_exit,
+	.driver = {
+		.name = "spear_thermal",
+		.owner = THIS_MODULE,
+		.pm = &spear_thermal_pm_ops,
+	},
+};
+
+module_platform_driver(spear_thermal_driver);
+
+MODULE_AUTHOR("Vincenzo Frascino <vincenzo.frascino@st.com>");
+MODULE_DESCRIPTION("SPEAr thermal driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index 220ce7e31cf5..022bacb71a7e 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -23,6 +23,8 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -39,8 +41,6 @@ MODULE_AUTHOR("Zhang Rui");
 MODULE_DESCRIPTION("Generic thermal management sysfs support");
 MODULE_LICENSE("GPL");
 
-#define PREFIX "Thermal: "
-
 struct thermal_cooling_device_instance {
 	int id;
 	char name[THERMAL_NAME_LENGTH];
@@ -60,13 +60,11 @@ static LIST_HEAD(thermal_tz_list);
 static LIST_HEAD(thermal_cdev_list);
 static DEFINE_MUTEX(thermal_list_lock);
 
-static unsigned int thermal_event_seqnum;
-
 static int get_idr(struct idr *idr, struct mutex *lock, int *id)
 {
 	int err;
 
-      again:
+again:
 	if (unlikely(idr_pre_get(idr, GFP_KERNEL) == 0))
 		return -ENOMEM;
 
@@ -152,9 +150,9 @@ mode_store(struct device *dev, struct device_attribute *attr,
 	if (!tz->ops->set_mode)
 		return -EPERM;
 
-	if (!strncmp(buf, "enabled", sizeof("enabled")))
+	if (!strncmp(buf, "enabled", sizeof("enabled") - 1))
 		result = tz->ops->set_mode(tz, THERMAL_DEVICE_ENABLED);
-	else if (!strncmp(buf, "disabled", sizeof("disabled")))
+	else if (!strncmp(buf, "disabled", sizeof("disabled") - 1))
 		result = tz->ops->set_mode(tz, THERMAL_DEVICE_DISABLED);
 	else
 		result = -EINVAL;
@@ -283,8 +281,7 @@ passive_show(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(type, 0444, type_show, NULL);
 static DEVICE_ATTR(temp, 0444, temp_show, NULL);
 static DEVICE_ATTR(mode, 0644, mode_show, mode_store);
-static DEVICE_ATTR(passive, S_IRUGO | S_IWUSR, passive_show, \
-		   passive_store);
+static DEVICE_ATTR(passive, S_IRUGO | S_IWUSR, passive_show, passive_store);
 
 static struct device_attribute trip_point_attrs[] = {
 	__ATTR(trip_point_0_type, 0444, trip_point_type_show, NULL),
@@ -313,22 +310,6 @@ static struct device_attribute trip_point_attrs[] = {
 	__ATTR(trip_point_11_temp, 0444, trip_point_temp_show, NULL),
 };
 
-#define TRIP_POINT_ATTR_ADD(_dev, _index, result)     \
-do {    \
-	result = device_create_file(_dev,	\
-				&trip_point_attrs[_index * 2]);	\
-	if (result)	\
-		break;	\
-	result = device_create_file(_dev,	\
-			&trip_point_attrs[_index * 2 + 1]);	\
-} while (0)
-
-#define TRIP_POINT_ATTR_REMOVE(_dev, _index)	\
-do {	\
-	device_remove_file(_dev, &trip_point_attrs[_index * 2]);	\
-	device_remove_file(_dev, &trip_point_attrs[_index * 2 + 1]);	\
-} while (0)
-
 /* sys I/F for cooling device */
 #define to_cooling_device(_dev)	\
 	container_of(_dev, struct thermal_cooling_device, device)
@@ -835,15 +816,14 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 		return 0;
 
 	device_remove_file(&tz->device, &dev->attr);
-      remove_symbol_link:
+remove_symbol_link:
 	sysfs_remove_link(&tz->device.kobj, dev->name);
-      release_idr:
+release_idr:
 	release_idr(&tz->idr, &tz->lock, dev->id);
-      free_mem:
+free_mem:
 	kfree(dev);
 	return result;
 }
-
 EXPORT_SYMBOL(thermal_zone_bind_cooling_device);
 
 /**
@@ -873,14 +853,13 @@ int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
 
 	return -ENODEV;
 
-      unbind:
+unbind:
 	device_remove_file(&tz->device, &pos->attr);
 	sysfs_remove_link(&tz->device.kobj, pos->name);
 	release_idr(&tz->idr, &tz->lock, pos->id);
 	kfree(pos);
 	return 0;
 }
-
 EXPORT_SYMBOL(thermal_zone_unbind_cooling_device);
 
 static void thermal_release(struct device *dev)
@@ -888,7 +867,8 @@ static void thermal_release(struct device *dev)
 	struct thermal_zone_device *tz;
 	struct thermal_cooling_device *cdev;
 
-	if (!strncmp(dev_name(dev), "thermal_zone", sizeof "thermal_zone" - 1)) {
+	if (!strncmp(dev_name(dev), "thermal_zone",
+		     sizeof("thermal_zone") - 1)) {
 		tz = to_thermal_zone(dev);
 		kfree(tz);
 	} else {
@@ -908,8 +888,9 @@ static struct class thermal_class = {
  * @devdata:	device private data.
  * @ops:		standard thermal cooling devices callbacks.
  */
-struct thermal_cooling_device *thermal_cooling_device_register(
-     char *type, void *devdata, const struct thermal_cooling_device_ops *ops)
+struct thermal_cooling_device *
+thermal_cooling_device_register(char *type, void *devdata,
+				const struct thermal_cooling_device_ops *ops)
 {
 	struct thermal_cooling_device *cdev;
 	struct thermal_zone_device *pos;
@@ -974,12 +955,11 @@ struct thermal_cooling_device *thermal_cooling_device_register(
 	if (!result)
 		return cdev;
 
-      unregister:
+unregister:
 	release_idr(&thermal_cdev_idr, &thermal_idr_lock, cdev->id);
 	device_unregister(&cdev->device);
 	return ERR_PTR(result);
 }
-
 EXPORT_SYMBOL(thermal_cooling_device_register);
 
 /**
@@ -1024,7 +1004,6 @@ void thermal_cooling_device_unregister(struct
 	device_unregister(&cdev->device);
 	return;
 }
-
 EXPORT_SYMBOL(thermal_cooling_device_unregister);
 
 /**
@@ -1044,8 +1023,7 @@ void thermal_zone_device_update(struct thermal_zone_device *tz)
 
 	if (tz->ops->get_temp(tz, &temp)) {
 		/* get_temp failed - retry it later */
-		printk(KERN_WARNING PREFIX "failed to read out thermal zone "
-		       "%d\n", tz->id);
+		pr_warn("failed to read out thermal zone %d\n", tz->id);
 		goto leave;
 	}
 
@@ -1060,9 +1038,8 @@ void thermal_zone_device_update(struct thermal_zone_device *tz)
 					ret = tz->ops->notify(tz, count,
 							      trip_type);
 				if (!ret) {
-					printk(KERN_EMERG
-					       "Critical temperature reached (%ld C), shutting down.\n",
-					       temp/1000);
+					pr_emerg("Critical temperature reached (%ld C), shutting down\n",
+						 temp/1000);
 					orderly_poweroff(true);
 				}
 			}
@@ -1100,7 +1077,7 @@ void thermal_zone_device_update(struct thermal_zone_device *tz)
 
 	tz->last_temperature = temp;
 
-      leave:
+leave:
 	if (tz->passive)
 		thermal_zone_device_set_polling(tz, tz->passive_delay);
 	else if (tz->polling_delay)
@@ -1199,7 +1176,12 @@ struct thermal_zone_device *thermal_zone_device_register(char *type,
 	}
 
 	for (count = 0; count < trips; count++) {
-		TRIP_POINT_ATTR_ADD(&tz->device, count, result);
+		result = device_create_file(&tz->device,
+					    &trip_point_attrs[count * 2]);
+		if (result)
+			break;
+		result = device_create_file(&tz->device,
+					    &trip_point_attrs[count * 2 + 1]);
 		if (result)
 			goto unregister;
 		tz->ops->get_trip_type(tz, count, &trip_type);
@@ -1235,12 +1217,11 @@ struct thermal_zone_device *thermal_zone_device_register(char *type,
 	if (!result)
 		return tz;
 
-      unregister:
+unregister:
 	release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
 	device_unregister(&tz->device);
 	return ERR_PTR(result);
 }
-
 EXPORT_SYMBOL(thermal_zone_device_register);
 
 /**
@@ -1279,9 +1260,12 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	if (tz->ops->get_mode)
 		device_remove_file(&tz->device, &dev_attr_mode);
 
-	for (count = 0; count < tz->trips; count++)
-		TRIP_POINT_ATTR_REMOVE(&tz->device, count);
-
+	for (count = 0; count < tz->trips; count++) {
+		device_remove_file(&tz->device,
+				   &trip_point_attrs[count * 2]);
+		device_remove_file(&tz->device,
+				   &trip_point_attrs[count * 2 + 1]);
+	}
 	thermal_remove_hwmon_sysfs(tz);
 	release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
 	idr_destroy(&tz->idr);
@@ -1289,7 +1273,6 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	device_unregister(&tz->device);
 	return;
 }
-
 EXPORT_SYMBOL(thermal_zone_device_unregister);
 
 #ifdef CONFIG_NET
@@ -1312,10 +1295,11 @@ int thermal_generate_netlink_event(u32 orig, enum events event)
 	void *msg_header;
 	int size;
 	int result;
+	static unsigned int thermal_event_seqnum;
 
 	/* allocate memory */
-	size = nla_total_size(sizeof(struct thermal_genl_event)) + \
-				nla_total_size(0);
+	size = nla_total_size(sizeof(struct thermal_genl_event)) +
+	       nla_total_size(0);
 
 	skb = genlmsg_new(size, GFP_ATOMIC);
 	if (!skb)
@@ -1331,8 +1315,8 @@ int thermal_generate_netlink_event(u32 orig, enum events event)
 	}
 
 	/* fill the data */
-	attr = nla_reserve(skb, THERMAL_GENL_ATTR_EVENT, \
-			sizeof(struct thermal_genl_event));
+	attr = nla_reserve(skb, THERMAL_GENL_ATTR_EVENT,
+			   sizeof(struct thermal_genl_event));
 
 	if (!attr) {
 		nlmsg_free(skb);
@@ -1359,7 +1343,7 @@ int thermal_generate_netlink_event(u32 orig, enum events event)
 
 	result = genlmsg_multicast(skb, 0, thermal_event_mcgrp.id, GFP_ATOMIC);
 	if (result)
-		printk(KERN_INFO "failed to send netlink event:%d", result);
+		pr_info("failed to send netlink event:%d\n", result);
 
 	return result;
 }
diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index afadcd43d14e..24145c30c9b0 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -85,7 +85,6 @@ static char *serial_version = "4.30";
 
 #include <asm/setup.h>
 
-#include <asm/system.h>
 
 #include <asm/irq.h>
 
diff --git a/drivers/tty/hvc/hvc_vio.c b/drivers/tty/hvc/hvc_vio.c
index 3a0d53d6368f..ee307799271a 100644
--- a/drivers/tty/hvc/hvc_vio.c
+++ b/drivers/tty/hvc/hvc_vio.c
@@ -310,11 +310,8 @@ static int __devexit hvc_vio_remove(struct vio_dev *vdev)
 static struct vio_driver hvc_vio_driver = {
 	.id_table	= hvc_driver_table,
 	.probe		= hvc_vio_probe,
-	.remove		= __devexit_p(hvc_vio_remove),
-	.driver		= {
-		.name	= hvc_driver_name,
-		.owner	= THIS_MODULE,
-	}
+	.remove		= hvc_vio_remove,
+	.name		= hvc_driver_name,
 };
 
 static int __init hvc_vio_init(void)
diff --git a/drivers/tty/hvc/hvcs.c b/drivers/tty/hvc/hvcs.c
index d23759183b47..3436436fe2d7 100644
--- a/drivers/tty/hvc/hvcs.c
+++ b/drivers/tty/hvc/hvcs.c
@@ -879,10 +879,7 @@ static struct vio_driver hvcs_vio_driver = {
 	.id_table	= hvcs_driver_table,
 	.probe		= hvcs_probe,
 	.remove		= __devexit_p(hvcs_remove),
-	.driver		= {
-		.name	= hvcs_driver_name,
-		.owner	= THIS_MODULE,
-	}
+	.name		= hvcs_driver_name,
 };
 
 /* Only called from hvcs_get_pi please */
diff --git a/drivers/tty/isicom.c b/drivers/tty/isicom.c
index 03c14979accf..e1235accab74 100644
--- a/drivers/tty/isicom.c
+++ b/drivers/tty/isicom.c
@@ -102,7 +102,7 @@
  *	You can find the original tools for this direct from Multitech
  *		ftp://ftp.multitech.com/ISI-Cards/
  *
- *	Having installed the cards the module options (/etc/modprobe.conf)
+ *	Having installed the cards the module options (/etc/modprobe.d/)
  *
  *	options isicom   io=card1,card2,card3,card4 irq=card1,card2,card3,card4
  *
@@ -133,7 +133,6 @@
 
 #include <linux/uaccess.h>
 #include <linux/io.h>
-#include <asm/system.h>
 
 #include <linux/pci.h>
 
diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c
index 8a8d0440bab0..324467d28a54 100644
--- a/drivers/tty/moxa.c
+++ b/drivers/tty/moxa.c
@@ -46,7 +46,6 @@
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c
index 17ff377e4129..c6f372dd5623 100644
--- a/drivers/tty/mxser.c
+++ b/drivers/tty/mxser.c
@@ -41,7 +41,6 @@
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/uaccess.h>
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index a09ce3ef5d74..1b2db9a3038c 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -102,7 +102,6 @@
 #include <linux/if.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/termios.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index d2256d08ee7e..94b6eda87afd 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -50,7 +50,6 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 
 /* number of characters left in xmit buffer before select has we have room */
 #define WAKEUP_CHARS 256
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index f96ecaec24f8..eeae7fafe9a7 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -27,7 +27,6 @@
 #include <linux/devpts_fs.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 
 #ifdef CONFIG_UNIX98_PTYS
 static struct tty_driver *ptm_driver;
diff --git a/drivers/tty/serial/21285.c b/drivers/tty/serial/21285.c
index f899996b4363..a44345a2dbb4 100644
--- a/drivers/tty/serial/21285.c
+++ b/drivers/tty/serial/21285.c
@@ -16,6 +16,7 @@
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
+#include <asm/system_info.h>
 #include <asm/hardware/dec21285.h>
 #include <mach/hardware.h>
 
diff --git a/drivers/tty/serial/68328serial.c b/drivers/tty/serial/68328serial.c
index 7398390e7e65..5ce782529d65 100644
--- a/drivers/tty/serial/68328serial.c
+++ b/drivers/tty/serial/68328serial.c
@@ -39,7 +39,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/delay.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/tty/serial/8250/serial_cs.c b/drivers/tty/serial/8250/serial_cs.c
index 86090605a84e..29b695d041ec 100644
--- a/drivers/tty/serial/8250/serial_cs.c
+++ b/drivers/tty/serial/8250/serial_cs.c
@@ -43,7 +43,6 @@
 #include <linux/delay.h>
 #include <linux/major.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 20d795d9b591..0c65c9e66986 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -51,6 +51,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
 #include <linux/delay.h>
+#include <linux/types.h>
 
 #include <asm/io.h>
 #include <asm/sizes.h>
@@ -271,6 +272,7 @@ static void pl011_dma_probe_initcall(struct uart_amba_port *uap)
 		.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE,
 		.direction = DMA_MEM_TO_DEV,
 		.dst_maxburst = uap->fifosize >> 1,
+		.device_fc = false,
 	};
 	struct dma_chan *chan;
 	dma_cap_mask_t mask;
@@ -304,6 +306,7 @@ static void pl011_dma_probe_initcall(struct uart_amba_port *uap)
 			.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE,
 			.direction = DMA_DEV_TO_MEM,
 			.src_maxburst = uap->fifosize >> 1,
+			.device_fc = false,
 		};
 
 		chan = dma_request_channel(mask, plat->dma_filter, plat->dma_rx_param);
@@ -481,7 +484,7 @@ static int pl011_dma_tx_refill(struct uart_amba_port *uap)
 		return -EBUSY;
 	}
 
-	desc = dma_dev->device_prep_slave_sg(chan, &dmatx->sg, 1, DMA_MEM_TO_DEV,
+	desc = dmaengine_prep_slave_sg(chan, &dmatx->sg, 1, DMA_MEM_TO_DEV,
 					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		dma_unmap_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE);
@@ -664,7 +667,6 @@ static void pl011_dma_rx_callback(void *data);
 static int pl011_dma_rx_trigger_dma(struct uart_amba_port *uap)
 {
 	struct dma_chan *rxchan = uap->dmarx.chan;
-	struct dma_device *dma_dev;
 	struct pl011_dmarx_data *dmarx = &uap->dmarx;
 	struct dma_async_tx_descriptor *desc;
 	struct pl011_sgbuf *sgbuf;
@@ -675,8 +677,7 @@ static int pl011_dma_rx_trigger_dma(struct uart_amba_port *uap)
 	/* Start the RX DMA job */
 	sgbuf = uap->dmarx.use_buf_b ?
 		&uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a;
-	dma_dev = rxchan->device;
-	desc = rxchan->device->device_prep_slave_sg(rxchan, &sgbuf->sg, 1,
+	desc = dmaengine_prep_slave_sg(rxchan, &sgbuf->sg, 1,
 					DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	/*
diff --git a/drivers/tty/serial/crisv10.c b/drivers/tty/serial/crisv10.c
index 23d791696879..5b07c0c3a10c 100644
--- a/drivers/tty/serial/crisv10.c
+++ b/drivers/tty/serial/crisv10.c
@@ -34,9 +34,9 @@ static char *serial_version = "$Revision: 1.25 $";
 
 #include <asm/irq.h>
 #include <asm/dma.h>
-#include <asm/system.h>
 
 #include <arch/svinto.h>
+#include <arch/system.h>
 
 /* non-arch dependent serial structures are in linux/serial.h */
 #include <linux/serial.h>
diff --git a/drivers/tty/serial/dz.c b/drivers/tty/serial/dz.c
index e3699a84049f..6491b8644a7f 100644
--- a/drivers/tty/serial/dz.c
+++ b/drivers/tty/serial/dz.c
@@ -52,7 +52,6 @@
 #include <linux/atomic.h>
 #include <asm/bootinfo.h>
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <asm/dec/interrupts.h>
 #include <asm/dec/kn01.h>
diff --git a/drivers/tty/serial/icom.c b/drivers/tty/serial/icom.c
index d55709a7a75a..defc4e3393a3 100644
--- a/drivers/tty/serial/icom.c
+++ b/drivers/tty/serial/icom.c
@@ -52,7 +52,6 @@
 #include <linux/firmware.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/uaccess.h>
diff --git a/drivers/tty/serial/mfd.c b/drivers/tty/serial/mfd.c
index a9234ba8f8d5..c4b50af46c44 100644
--- a/drivers/tty/serial/mfd.c
+++ b/drivers/tty/serial/mfd.c
@@ -127,11 +127,6 @@ static inline void serial_out(struct uart_hsu_port *up, int offset, int value)
 
 #define HSU_REGS_BUFSIZE	1024
 
-static int hsu_show_regs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
 
 static ssize_t port_show_regs(struct file *file, char __user *user_buf,
 				size_t count, loff_t *ppos)
@@ -231,14 +226,14 @@ static ssize_t dma_show_regs(struct file *file, char __user *user_buf,
 
 static const struct file_operations port_regs_ops = {
 	.owner		= THIS_MODULE,
-	.open		= hsu_show_regs_open,
+	.open		= simple_open,
 	.read		= port_show_regs,
 	.llseek		= default_llseek,
 };
 
 static const struct file_operations dma_regs_ops = {
 	.owner		= THIS_MODULE,
-	.open		= hsu_show_regs_open,
+	.open		= simple_open,
 	.read		= dma_show_regs,
 	.llseek		= default_llseek,
 };
diff --git a/drivers/tty/serial/msm_serial_hs.c b/drivers/tty/serial/msm_serial_hs.c
index 5e85e1e14c44..fca13dc73e23 100644
--- a/drivers/tty/serial/msm_serial_hs.c
+++ b/drivers/tty/serial/msm_serial_hs.c
@@ -50,7 +50,6 @@
 
 #include <linux/atomic.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include <mach/hardware.h>
 #include <mach/dma.h>
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 332f2eb8abbc..08b9962b8fda 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -304,11 +304,7 @@ static const int trigger_level_1[4] = { 1, 1, 1, 1 };
 #ifdef CONFIG_DEBUG_FS
 
 #define PCH_REGS_BUFSIZE	1024
-static int pch_show_regs_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
+
 
 static ssize_t port_show_regs(struct file *file, char __user *user_buf,
 				size_t count, loff_t *ppos)
@@ -362,7 +358,7 @@ static ssize_t port_show_regs(struct file *file, char __user *user_buf,
 
 static const struct file_operations port_regs_ops = {
 	.owner		= THIS_MODULE,
-	.open		= pch_show_regs_open,
+	.open		= simple_open,
 	.read		= port_show_regs,
 	.llseek		= default_llseek,
 };
@@ -844,7 +840,7 @@ static int dma_handle_rx(struct eg20t_port *priv)
 
 	sg_dma_address(sg) = priv->rx_buf_dma;
 
-	desc = priv->chan_rx->device->device_prep_slave_sg(priv->chan_rx,
+	desc = dmaengine_prep_slave_sg(priv->chan_rx,
 			sg, 1, DMA_DEV_TO_MEM,
 			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
@@ -1003,7 +999,7 @@ static unsigned int dma_handle_tx(struct eg20t_port *priv)
 			sg_dma_len(sg) = size;
 	}
 
-	desc = priv->chan_tx->device->device_prep_slave_sg(priv->chan_tx,
+	desc = dmaengine_prep_slave_sg(priv->chan_tx,
 					priv->sg_tx_p, nent, DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
diff --git a/drivers/tty/serial/sa1100.c b/drivers/tty/serial/sa1100.c
index ef7a21a6a01b..2ca5959ec3fa 100644
--- a/drivers/tty/serial/sa1100.c
+++ b/drivers/tty/serial/sa1100.c
@@ -38,6 +38,7 @@
 
 #include <asm/irq.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <asm/mach/serial_sa1100.h>
 
 /* We've been assigned a range on the "Low-density serial ports" major */
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 61b7fd2729cd..bf461cf99616 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1229,17 +1229,20 @@ static void sci_dma_tx_complete(void *arg)
 	port->icount.tx += sg_dma_len(&s->sg_tx);
 
 	async_tx_ack(s->desc_tx);
-	s->cookie_tx = -EINVAL;
 	s->desc_tx = NULL;
 
 	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
 		uart_write_wakeup(port);
 
 	if (!uart_circ_empty(xmit)) {
+		s->cookie_tx = 0;
 		schedule_work(&s->work_tx);
-	} else if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) {
-		u16 ctrl = sci_in(port, SCSCR);
-		sci_out(port, SCSCR, ctrl & ~SCSCR_TIE);
+	} else {
+		s->cookie_tx = -EINVAL;
+		if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) {
+			u16 ctrl = sci_in(port, SCSCR);
+			sci_out(port, SCSCR, ctrl & ~SCSCR_TIE);
+		}
 	}
 
 	spin_unlock_irqrestore(&port->lock, flags);
@@ -1338,7 +1341,7 @@ static void sci_submit_rx(struct sci_port *s)
 		struct scatterlist *sg = &s->sg_rx[i];
 		struct dma_async_tx_descriptor *desc;
 
-		desc = chan->device->device_prep_slave_sg(chan,
+		desc = dmaengine_prep_slave_sg(chan,
 			sg, 1, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT);
 
 		if (desc) {
@@ -1453,7 +1456,7 @@ static void work_fn_tx(struct work_struct *work)
 
 	BUG_ON(!sg_dma_len(sg));
 
-	desc = chan->device->device_prep_slave_sg(chan,
+	desc = dmaengine_prep_slave_sg(chan,
 			sg, s->sg_len_tx, DMA_MEM_TO_DEV,
 			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
@@ -1501,8 +1504,10 @@ static void sci_start_tx(struct uart_port *port)
 	}
 
 	if (s->chan_tx && !uart_circ_empty(&s->port.state->xmit) &&
-	    s->cookie_tx < 0)
+	    s->cookie_tx < 0) {
+		s->cookie_tx = 0;
 		schedule_work(&s->work_tx);
+	}
 #endif
 
 	if (!s->chan_tx || port->type == PORT_SCIFA || port->type == PORT_SCIFB) {
diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index 3ba5d285c2d0..505961cfd934 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -23,6 +23,7 @@
 #include <asm/spitfire.h>
 #include <asm/prom.h>
 #include <asm/irq.h>
+#include <asm/setup.h>
 
 #if defined(CONFIG_MAGIC_SYSRQ)
 #define SUPPORT_SYSRQ
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 62dacd0ba526..f0d93eb7e6ec 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -37,6 +37,7 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/prom.h>
+#include <asm/setup.h>
 
 #if defined(CONFIG_SERIAL_SUNSAB_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 #define SUPPORT_SYSRQ
diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index d3ca6da129fe..675303b8ed84 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -41,6 +41,7 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/prom.h>
+#include <asm/setup.h>
 
 #if defined(CONFIG_SERIAL_SUNSU_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 #define SUPPORT_SYSRQ
diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index da4415842a43..babd9470982b 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -37,6 +37,7 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/prom.h>
+#include <asm/setup.h>
 
 #if defined(CONFIG_SERIAL_SUNZILOG_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 #define SUPPORT_SYSRQ
@@ -1580,7 +1581,7 @@ static int __init sunzilog_init(void)
 	if (err)
 		goto out_unregister_uart;
 
-	if (!zilog_irq) {
+	if (zilog_irq) {
 		struct uart_sunzilog_port *up = sunzilog_irq_chain;
 		err = request_irq(zilog_irq, sunzilog_interrupt, IRQF_SHARED,
 				  "zs", sunzilog_irq_chain);
@@ -1621,7 +1622,7 @@ static void __exit sunzilog_exit(void)
 {
 	platform_driver_unregister(&zs_driver);
 
-	if (!zilog_irq) {
+	if (zilog_irq) {
 		struct uart_sunzilog_port *up = sunzilog_irq_chain;
 
 		/* Disable Interrupts */
diff --git a/drivers/tty/serial/zs.c b/drivers/tty/serial/zs.c
index b7455b526080..4001eee6c08d 100644
--- a/drivers/tty/serial/zs.c
+++ b/drivers/tty/serial/zs.c
@@ -67,7 +67,6 @@
 #include <linux/types.h>
 
 #include <linux/atomic.h>
-#include <asm/system.h>
 
 #include <asm/dec/interrupts.h>
 #include <asm/dec/ioasic_addrs.h>
diff --git a/drivers/tty/synclink.c b/drivers/tty/synclink.c
index 8e518da85fd5..593d40ad0a6b 100644
--- a/drivers/tty/synclink.c
+++ b/drivers/tty/synclink.c
@@ -86,7 +86,6 @@
 #include <linux/ioctl.h>
 #include <linux/synclink.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/dma.h>
diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c
index 34b1a3c43066..aa1debf97cc7 100644
--- a/drivers/tty/synclink_gt.c
+++ b/drivers/tty/synclink_gt.c
@@ -73,7 +73,6 @@
 #include <linux/hdlc.h>
 #include <linux/synclink.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/dma.h>
diff --git a/drivers/tty/synclinkmp.c b/drivers/tty/synclinkmp.c
index 4fb6c4b31b79..a3dddc12d2fe 100644
--- a/drivers/tty/synclinkmp.c
+++ b/drivers/tty/synclinkmp.c
@@ -58,7 +58,6 @@
 #include <linux/delay.h>
 #include <linux/ioctl.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/dma.h>
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 136e86faa1e1..05728894a88c 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -327,7 +327,7 @@ static void send_sig_all(int sig)
 		if (is_global_init(p))
 			continue;
 
-		force_sig(sig, p);
+		do_send_sig_info(sig, SEND_SIG_FORCED, p, true);
 	}
 	read_unlock(&tasklist_lock);
 }
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index dd8a938510ca..d939bd705c71 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -97,7 +97,6 @@
 #include <linux/ratelimit.h>
 
 #include <linux/uaccess.h>
-#include <asm/system.h>
 
 #include <linux/kbd_kern.h>
 #include <linux/vt_kern.h>
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 9314d93c1a20..a1b9a2f68567 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -23,7 +23,6 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #undef TTY_DEBUG_WAIT_UNTIL_SENT
 
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 84c4a7d5603e..3bdd4b19dd06 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -99,7 +99,6 @@
 #include <linux/notifier.h>
 #include <linux/device.h>
 #include <linux/io.h>
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <linux/kdb.h>
 #include <linux/ctype.h>
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index 48ac6e781ba2..cbd8f5f80596 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -44,7 +44,7 @@ config USB_ARCH_HAS_EHCI
 	default y if PPC_MPC512x
 	default y if ARCH_IXP4XX
 	default y if ARCH_W90X900
-	default y if ARCH_AT91SAM9G45
+	default y if ARCH_AT91
 	default y if ARCH_MXC
 	default y if ARCH_OMAP3
 	default y if ARCH_CNS3XXX
diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c
index cefa0c8b5b6a..d2b9af59cba9 100644
--- a/drivers/usb/core/inode.c
+++ b/drivers/usb/core/inode.c
@@ -428,18 +428,10 @@ static loff_t default_file_lseek (struct file *file, loff_t offset, int orig)
 	return retval;
 }
 
-static int default_open (struct inode *inode, struct file *file)
-{
-	if (inode->i_private)
-		file->private_data = inode->i_private;
-
-	return 0;
-}
-
 static const struct file_operations default_file_operations = {
 	.read =		default_read_file,
 	.write =	default_write_file,
-	.open =		default_open,
+	.open =		simple_open,
 	.llseek =	default_file_lseek,
 };
 
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 26c0b75f152e..2633f7595116 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -137,7 +137,7 @@ choice
 
 config USB_AT91
 	tristate "Atmel AT91 USB Device Port"
-	depends on ARCH_AT91 && !ARCH_AT91SAM9RL && !ARCH_AT91SAM9G45
+	depends on ARCH_AT91
 	help
 	   Many Atmel AT91 processors (such as the AT91RM2000) have a
 	   full speed USB Device Port with support for five configurable
diff --git a/drivers/usb/gadget/amd5536udc.c b/drivers/usb/gadget/amd5536udc.c
index 2204a4c68d85..77779271f487 100644
--- a/drivers/usb/gadget/amd5536udc.c
+++ b/drivers/usb/gadget/amd5536udc.c
@@ -54,7 +54,6 @@
 #include <linux/prefetch.h>
 
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 /* gadget stack */
diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c
index 2db5f68f7960..0c935d7c65bd 100644
--- a/drivers/usb/gadget/at91_udc.c
+++ b/drivers/usb/gadget/at91_udc.c
@@ -29,12 +29,13 @@
 #include <linux/clk.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
 
 #include <asm/byteorder.h>
 #include <mach/hardware.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/gpio.h>
 
 #include <mach/board.h>
@@ -1707,7 +1708,27 @@ static void at91udc_shutdown(struct platform_device *dev)
 	spin_unlock_irqrestore(&udc->lock, flags);
 }
 
-static int __init at91udc_probe(struct platform_device *pdev)
+static void __devinit at91udc_of_init(struct at91_udc *udc,
+				     struct device_node *np)
+{
+	struct at91_udc_data *board = &udc->board;
+	u32 val;
+	enum of_gpio_flags flags;
+
+	if (of_property_read_u32(np, "atmel,vbus-polled", &val) == 0)
+		board->vbus_polled = 1;
+
+	board->vbus_pin = of_get_named_gpio_flags(np, "atmel,vbus-gpio", 0,
+						  &flags);
+	board->vbus_active_low = (flags & OF_GPIO_ACTIVE_LOW) ? 1 : 0;
+
+	board->pullup_pin = of_get_named_gpio_flags(np, "atmel,pullup-gpio", 0,
+						  &flags);
+
+	board->pullup_active_low = (flags & OF_GPIO_ACTIVE_LOW) ? 1 : 0;
+}
+
+static int __devinit at91udc_probe(struct platform_device *pdev)
 {
 	struct device	*dev = &pdev->dev;
 	struct at91_udc	*udc;
@@ -1742,7 +1763,11 @@ static int __init at91udc_probe(struct platform_device *pdev)
 	/* init software state */
 	udc = &controller;
 	udc->gadget.dev.parent = dev;
-	udc->board = *(struct at91_udc_data *) dev->platform_data;
+	if (pdev->dev.of_node)
+		at91udc_of_init(udc, pdev->dev.of_node);
+	else
+		memcpy(&udc->board, dev->platform_data,
+		       sizeof(struct at91_udc_data));
 	udc->pdev = pdev;
 	udc->enabled = 0;
 	spin_lock_init(&udc->lock);
@@ -1971,6 +1996,15 @@ static int at91udc_resume(struct platform_device *pdev)
 #define	at91udc_resume	NULL
 #endif
 
+#if defined(CONFIG_OF)
+static const struct of_device_id at91_udc_dt_ids[] = {
+	{ .compatible = "atmel,at91rm9200-udc" },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(of, at91_udc_dt_ids);
+#endif
+
 static struct platform_driver at91_udc_driver = {
 	.remove		= __exit_p(at91udc_remove),
 	.shutdown	= at91udc_shutdown,
@@ -1979,6 +2013,7 @@ static struct platform_driver at91_udc_driver = {
 	.driver		= {
 		.name	= (char *) driver_name,
 		.owner	= THIS_MODULE,
+		.of_match_table	= of_match_ptr(at91_udc_dt_ids),
 	},
 };
 
diff --git a/drivers/usb/gadget/dummy_hcd.c b/drivers/usb/gadget/dummy_hcd.c
index e1cd56c5e2a8..a6dfd2164166 100644
--- a/drivers/usb/gadget/dummy_hcd.c
+++ b/drivers/usb/gadget/dummy_hcd.c
@@ -44,7 +44,6 @@
 #include <asm/byteorder.h>
 #include <linux/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #define DRIVER_DESC	"USB Host+Gadget Emulator"
diff --git a/drivers/usb/gadget/fsl_udc_core.c b/drivers/usb/gadget/fsl_udc_core.c
index b30e21fdbb1b..5f94e79cd6b9 100644
--- a/drivers/usb/gadget/fsl_udc_core.c
+++ b/drivers/usb/gadget/fsl_udc_core.c
@@ -43,7 +43,6 @@
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 #include <asm/dma.h>
 
diff --git a/drivers/usb/gadget/goku_udc.c b/drivers/usb/gadget/goku_udc.c
index e1dfd32dc805..e151d6b87dee 100644
--- a/drivers/usb/gadget/goku_udc.c
+++ b/drivers/usb/gadget/goku_udc.c
@@ -43,7 +43,6 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 
diff --git a/drivers/usb/gadget/langwell_udc.c b/drivers/usb/gadget/langwell_udc.c
index edd52d963f14..f9cedd52cf20 100644
--- a/drivers/usb/gadget/langwell_udc.c
+++ b/drivers/usb/gadget/langwell_udc.c
@@ -32,7 +32,6 @@
 #include <linux/pm.h>
 #include <linux/io.h>
 #include <linux/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include "langwell_udc.h"
diff --git a/drivers/usb/gadget/mv_udc_core.c b/drivers/usb/gadget/mv_udc_core.c
index 19bbe80c2f8c..a73cf406e2a4 100644
--- a/drivers/usb/gadget/mv_udc_core.c
+++ b/drivers/usb/gadget/mv_udc_core.c
@@ -34,7 +34,6 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/platform_data/mv_usb.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include "mv_udc.h"
diff --git a/drivers/usb/gadget/net2272.c b/drivers/usb/gadget/net2272.c
index 01ae56f47174..43ac7482fa91 100644
--- a/drivers/usb/gadget/net2272.c
+++ b/drivers/usb/gadget/net2272.c
@@ -42,7 +42,6 @@
 #include <linux/usb/gadget.h>
 
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include "net2272.h"
diff --git a/drivers/usb/gadget/net2280.c b/drivers/usb/gadget/net2280.c
index a5ccabc37f30..ac335af154ba 100644
--- a/drivers/usb/gadget/net2280.c
+++ b/drivers/usb/gadget/net2280.c
@@ -59,7 +59,6 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 
diff --git a/drivers/usb/gadget/omap_udc.c b/drivers/usb/gadget/omap_udc.c
index b44830df593e..3b4b6dd0f95a 100644
--- a/drivers/usb/gadget/omap_udc.c
+++ b/drivers/usb/gadget/omap_udc.c
@@ -40,7 +40,6 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 #include <asm/mach-types.h>
 
diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c
index d83134b0f78a..4e4dc1f5f388 100644
--- a/drivers/usb/gadget/printer.c
+++ b/drivers/usb/gadget/printer.c
@@ -34,7 +34,6 @@
 #include <asm/byteorder.h>
 #include <linux/io.h>
 #include <linux/irq.h>
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/usb/gadget/pxa25x_udc.c b/drivers/usb/gadget/pxa25x_udc.c
index 1b33634f2736..41ed69c96d8c 100644
--- a/drivers/usb/gadget/pxa25x_udc.c
+++ b/drivers/usb/gadget/pxa25x_udc.c
@@ -41,7 +41,6 @@
 #include <asm/byteorder.h>
 #include <asm/dma.h>
 #include <asm/gpio.h>
-#include <asm/system.h>
 #include <asm/mach-types.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/usb/gadget/rndis.c b/drivers/usb/gadget/rndis.c
index d3cdffea9c8a..73a934a170d1 100644
--- a/drivers/usb/gadget/rndis.c
+++ b/drivers/usb/gadget/rndis.c
@@ -34,7 +34,6 @@
 
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 
diff --git a/drivers/usb/gadget/s3c2410_udc.c b/drivers/usb/gadget/s3c2410_udc.c
index ab9c65e2c1d5..195524cde6c3 100644
--- a/drivers/usb/gadget/s3c2410_udc.c
+++ b/drivers/usb/gadget/s3c2410_udc.c
@@ -37,7 +37,6 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 #include <mach/irqs.h>
 
diff --git a/drivers/usb/host/ehci-atmel.c b/drivers/usb/host/ehci-atmel.c
index a5a3ef1f0096..cf14c95a6700 100644
--- a/drivers/usb/host/ehci-atmel.c
+++ b/drivers/usb/host/ehci-atmel.c
@@ -13,6 +13,8 @@
 
 #include <linux/clk.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
 
 /* interface and function clocks */
 static struct clk *iclk, *fclk;
@@ -115,6 +117,8 @@ static const struct hc_driver ehci_atmel_hc_driver = {
 	.clear_tt_buffer_complete	= ehci_clear_tt_buffer_complete,
 };
 
+static u64 at91_ehci_dma_mask = DMA_BIT_MASK(32);
+
 static int __devinit ehci_atmel_drv_probe(struct platform_device *pdev)
 {
 	struct usb_hcd *hcd;
@@ -137,6 +141,13 @@ static int __devinit ehci_atmel_drv_probe(struct platform_device *pdev)
 		goto fail_create_hcd;
 	}
 
+	/* Right now device-tree probed devices don't get dma_mask set.
+	 * Since shared usb code relies on it, set it here for now.
+	 * Once we have dma capability bindings this can go away.
+	 */
+	if (!pdev->dev.dma_mask)
+		pdev->dev.dma_mask = &at91_ehci_dma_mask;
+
 	hcd = usb_create_hcd(driver, &pdev->dev, dev_name(&pdev->dev));
 	if (!hcd) {
 		retval = -ENOMEM;
@@ -225,9 +236,21 @@ static int __devexit ehci_atmel_drv_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id atmel_ehci_dt_ids[] = {
+	{ .compatible = "atmel,at91sam9g45-ehci" },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(of, atmel_ehci_dt_ids);
+#endif
+
 static struct platform_driver ehci_atmel_driver = {
 	.probe		= ehci_atmel_drv_probe,
 	.remove		= __devexit_p(ehci_atmel_drv_remove),
 	.shutdown	= usb_hcd_platform_shutdown,
-	.driver.name	= "atmel-ehci",
+	.driver		= {
+		.name	= "atmel-ehci",
+		.of_match_table	= of_match_ptr(atmel_ehci_dt_ids),
+	},
 };
diff --git a/drivers/usb/host/ehci-dbg.c b/drivers/usb/host/ehci-dbg.c
index fd9109d7eb0e..680e1a31fb87 100644
--- a/drivers/usb/host/ehci-dbg.c
+++ b/drivers/usb/host/ehci-dbg.c
@@ -352,7 +352,6 @@ static int debug_async_open(struct inode *, struct file *);
 static int debug_periodic_open(struct inode *, struct file *);
 static int debug_registers_open(struct inode *, struct file *);
 static int debug_async_open(struct inode *, struct file *);
-static int debug_lpm_open(struct inode *, struct file *);
 static ssize_t debug_lpm_read(struct file *file, char __user *user_buf,
 				   size_t count, loff_t *ppos);
 static ssize_t debug_lpm_write(struct file *file, const char __user *buffer,
@@ -385,7 +384,7 @@ static const struct file_operations debug_registers_fops = {
 };
 static const struct file_operations debug_lpm_fops = {
 	.owner		= THIS_MODULE,
-	.open		= debug_lpm_open,
+	.open		= simple_open,
 	.read		= debug_lpm_read,
 	.write		= debug_lpm_write,
 	.release	= debug_lpm_close,
@@ -970,12 +969,6 @@ static int debug_registers_open(struct inode *inode, struct file *file)
 	return file->private_data ? 0 : -ENOMEM;
 }
 
-static int debug_lpm_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static int debug_lpm_close(struct inode *inode, struct file *file)
 {
 	return 0;
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index aede6374e4b6..057cdda7a489 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -45,7 +45,6 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #if defined(CONFIG_PPC_PS3)
diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index 924880087a74..9e65e3091c8a 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -70,7 +70,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 #include "isp116x.h"
diff --git a/drivers/usb/host/isp1362-hcd.c b/drivers/usb/host/isp1362-hcd.c
index 9e63cdf1ab75..2ed112d3e159 100644
--- a/drivers/usb/host/isp1362-hcd.c
+++ b/drivers/usb/host/isp1362-hcd.c
@@ -84,7 +84,6 @@
 #include <linux/prefetch.h>
 
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 8e855eb0bf89..09f597ad6e00 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -14,6 +14,8 @@
 
 #include <linux/clk.h>
 #include <linux/platform_device.h>
+#include <linux/of_platform.h>
+#include <linux/of_gpio.h>
 
 #include <mach/hardware.h>
 #include <asm/gpio.h>
@@ -25,6 +27,10 @@
 #error "CONFIG_ARCH_AT91 must be defined."
 #endif
 
+#define valid_port(index)	((index) >= 0 && (index) < AT91_MAX_USBH_PORTS)
+#define at91_for_each_port(index)	\
+		for ((index) = 0; (index) < AT91_MAX_USBH_PORTS; (index)++)
+
 /* interface and function clocks; sometimes also an AHB clock */
 static struct clk *iclk, *fclk, *hclk;
 static int clocked;
@@ -238,26 +244,26 @@ ohci_at91_start (struct usb_hcd *hcd)
 
 static void ohci_at91_usb_set_power(struct at91_usbh_data *pdata, int port, int enable)
 {
-	if (port < 0 || port >= 2)
+	if (!valid_port(port))
 		return;
 
 	if (!gpio_is_valid(pdata->vbus_pin[port]))
 		return;
 
 	gpio_set_value(pdata->vbus_pin[port],
-		       !pdata->vbus_pin_active_low[port] ^ enable);
+		       pdata->vbus_pin_active_low[port] ^ enable);
 }
 
 static int ohci_at91_usb_get_power(struct at91_usbh_data *pdata, int port)
 {
-	if (port < 0 || port >= 2)
+	if (!valid_port(port))
 		return -EINVAL;
 
 	if (!gpio_is_valid(pdata->vbus_pin[port]))
 		return -EINVAL;
 
 	return gpio_get_value(pdata->vbus_pin[port]) ^
-		!pdata->vbus_pin_active_low[port];
+		pdata->vbus_pin_active_low[port];
 }
 
 /*
@@ -269,9 +275,9 @@ static int ohci_at91_hub_status_data(struct usb_hcd *hcd, char *buf)
 	int length = ohci_hub_status_data(hcd, buf);
 	int port;
 
-	for (port = 0; port < ARRAY_SIZE(pdata->overcurrent_pin); port++) {
+	at91_for_each_port(port) {
 		if (pdata->overcurrent_changed[port]) {
-			if (! length)
+			if (!length)
 				length = 1;
 			buf[0] |= 1 << (port + 1);
 		}
@@ -295,11 +301,17 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		"ohci_at91_hub_control(%p,0x%04x,0x%04x,0x%04x,%p,%04x)\n",
 		hcd, typeReq, wValue, wIndex, buf, wLength);
 
+	wIndex--;
+
 	switch (typeReq) {
 	case SetPortFeature:
 		if (wValue == USB_PORT_FEAT_POWER) {
 			dev_dbg(hcd->self.controller, "SetPortFeat: POWER\n");
-			ohci_at91_usb_set_power(pdata, wIndex - 1, 1);
+			if (valid_port(wIndex)) {
+				ohci_at91_usb_set_power(pdata, wIndex, 1);
+				ret = 0;
+			}
+
 			goto out;
 		}
 		break;
@@ -310,9 +322,9 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			dev_dbg(hcd->self.controller,
 				"ClearPortFeature: C_OVER_CURRENT\n");
 
-			if (wIndex == 1 || wIndex == 2) {
-				pdata->overcurrent_changed[wIndex-1] = 0;
-				pdata->overcurrent_status[wIndex-1] = 0;
+			if (valid_port(wIndex)) {
+				pdata->overcurrent_changed[wIndex] = 0;
+				pdata->overcurrent_status[wIndex] = 0;
 			}
 
 			goto out;
@@ -321,9 +333,8 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			dev_dbg(hcd->self.controller,
 				"ClearPortFeature: OVER_CURRENT\n");
 
-			if (wIndex == 1 || wIndex == 2) {
-				pdata->overcurrent_status[wIndex-1] = 0;
-			}
+			if (valid_port(wIndex))
+				pdata->overcurrent_status[wIndex] = 0;
 
 			goto out;
 
@@ -331,15 +342,15 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			dev_dbg(hcd->self.controller,
 				"ClearPortFeature: POWER\n");
 
-			if (wIndex == 1 || wIndex == 2) {
-				ohci_at91_usb_set_power(pdata, wIndex - 1, 0);
+			if (valid_port(wIndex)) {
+				ohci_at91_usb_set_power(pdata, wIndex, 0);
 				return 0;
 			}
 		}
 		break;
 	}
 
-	ret = ohci_hub_control(hcd, typeReq, wValue, wIndex, buf, wLength);
+	ret = ohci_hub_control(hcd, typeReq, wValue, wIndex + 1, buf, wLength);
 	if (ret)
 		goto out;
 
@@ -375,18 +386,15 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 
 		dev_dbg(hcd->self.controller, "GetPortStatus(%d)\n", wIndex);
 
-		if (wIndex == 1 || wIndex == 2) {
-			if (! ohci_at91_usb_get_power(pdata, wIndex-1)) {
+		if (valid_port(wIndex)) {
+			if (!ohci_at91_usb_get_power(pdata, wIndex))
 				*data &= ~cpu_to_le32(RH_PS_PPS);
-			}
 
-			if (pdata->overcurrent_changed[wIndex-1]) {
+			if (pdata->overcurrent_changed[wIndex])
 				*data |= cpu_to_le32(RH_PS_OCIC);
-			}
 
-			if (pdata->overcurrent_status[wIndex-1]) {
+			if (pdata->overcurrent_status[wIndex])
 				*data |= cpu_to_le32(RH_PS_POCI);
-			}
 		}
 	}
 
@@ -448,14 +456,14 @@ static irqreturn_t ohci_hcd_at91_overcurrent_irq(int irq, void *data)
 
 	/* From the GPIO notifying the over-current situation, find
 	 * out the corresponding port */
-	for (port = 0; port < ARRAY_SIZE(pdata->overcurrent_pin); port++) {
+	at91_for_each_port(port) {
 		if (gpio_to_irq(pdata->overcurrent_pin[port]) == irq) {
 			gpio = pdata->overcurrent_pin[port];
 			break;
 		}
 	}
 
-	if (port == ARRAY_SIZE(pdata->overcurrent_pin)) {
+	if (port == AT91_MAX_USBH_PORTS) {
 		dev_err(& pdev->dev, "overcurrent interrupt from unknown GPIO\n");
 		return IRQ_HANDLED;
 	}
@@ -465,7 +473,7 @@ static irqreturn_t ohci_hcd_at91_overcurrent_irq(int irq, void *data)
 	/* When notified of an over-current situation, disable power
 	   on the corresponding port, and mark this port in
 	   over-current. */
-	if (! val) {
+	if (!val) {
 		ohci_at91_usb_set_power(pdata, port, 0);
 		pdata->overcurrent_status[port]  = 1;
 		pdata->overcurrent_changed[port] = 1;
@@ -477,34 +485,133 @@ static irqreturn_t ohci_hcd_at91_overcurrent_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id at91_ohci_dt_ids[] = {
+	{ .compatible = "atmel,at91rm9200-ohci" },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(of, at91_ohci_dt_ids);
+
+static u64 at91_ohci_dma_mask = DMA_BIT_MASK(32);
+
+static int __devinit ohci_at91_of_init(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	int i, gpio;
+	enum of_gpio_flags flags;
+	struct at91_usbh_data	*pdata;
+	u32 ports;
+
+	if (!np)
+		return 0;
+
+	/* Right now device-tree probed devices don't get dma_mask set.
+	 * Since shared usb code relies on it, set it here for now.
+	 * Once we have dma capability bindings this can go away.
+	 */
+	if (!pdev->dev.dma_mask)
+		pdev->dev.dma_mask = &at91_ohci_dma_mask;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	if (!of_property_read_u32(np, "num-ports", &ports))
+		pdata->ports = ports;
+
+	at91_for_each_port(i) {
+		gpio = of_get_named_gpio_flags(np, "atmel,vbus-gpio", i, &flags);
+		pdata->vbus_pin[i] = gpio;
+		if (!gpio_is_valid(gpio))
+			continue;
+		pdata->vbus_pin_active_low[i] = flags & OF_GPIO_ACTIVE_LOW;
+	}
+
+	at91_for_each_port(i)
+		pdata->overcurrent_pin[i] =
+			of_get_named_gpio_flags(np, "atmel,oc-gpio", i, &flags);
+
+	pdev->dev.platform_data = pdata;
+
+	return 0;
+}
+#else
+static int __devinit ohci_at91_of_init(struct platform_device *pdev)
+{
+	return 0;
+}
+#endif
+
 /*-------------------------------------------------------------------------*/
 
 static int ohci_hcd_at91_drv_probe(struct platform_device *pdev)
 {
-	struct at91_usbh_data	*pdata = pdev->dev.platform_data;
+	struct at91_usbh_data	*pdata;
 	int			i;
+	int			gpio;
+	int			ret;
+
+	ret = ohci_at91_of_init(pdev);
+	if (ret)
+		return ret;
+
+	pdata = pdev->dev.platform_data;
 
 	if (pdata) {
-		for (i = 0; i < ARRAY_SIZE(pdata->vbus_pin); i++) {
+		at91_for_each_port(i) {
 			if (!gpio_is_valid(pdata->vbus_pin[i]))
 				continue;
-			gpio_request(pdata->vbus_pin[i], "ohci_vbus");
+			gpio = pdata->vbus_pin[i];
+
+			ret = gpio_request(gpio, "ohci_vbus");
+			if (ret) {
+				dev_err(&pdev->dev,
+					"can't request vbus gpio %d\n", gpio);
+				continue;
+			}
+			ret = gpio_direction_output(gpio,
+						!pdata->vbus_pin_active_low[i]);
+			if (ret) {
+				dev_err(&pdev->dev,
+					"can't put vbus gpio %d as output %d\n",
+					gpio, !pdata->vbus_pin_active_low[i]);
+				gpio_free(gpio);
+				continue;
+			}
+
 			ohci_at91_usb_set_power(pdata, i, 1);
 		}
 
-		for (i = 0; i < ARRAY_SIZE(pdata->overcurrent_pin); i++) {
-			int ret;
-
+		at91_for_each_port(i) {
 			if (!gpio_is_valid(pdata->overcurrent_pin[i]))
 				continue;
-			gpio_request(pdata->overcurrent_pin[i], "ohci_overcurrent");
+			gpio = pdata->overcurrent_pin[i];
+
+			ret = gpio_request(gpio, "ohci_overcurrent");
+			if (ret) {
+				dev_err(&pdev->dev,
+					"can't request overcurrent gpio %d\n",
+					gpio);
+				continue;
+			}
+
+			ret = gpio_direction_input(gpio);
+			if (ret) {
+				dev_err(&pdev->dev,
+					"can't configure overcurrent gpio %d as input\n",
+					gpio);
+				gpio_free(gpio);
+				continue;
+			}
 
-			ret = request_irq(gpio_to_irq(pdata->overcurrent_pin[i]),
+			ret = request_irq(gpio_to_irq(gpio),
 					  ohci_hcd_at91_overcurrent_irq,
 					  IRQF_SHARED, "ohci_overcurrent", pdev);
 			if (ret) {
-				gpio_free(pdata->overcurrent_pin[i]);
-				dev_warn(& pdev->dev, "cannot get GPIO IRQ for overcurrent\n");
+				gpio_free(gpio);
+				dev_err(&pdev->dev,
+					"can't get gpio IRQ for overcurrent\n");
 			}
 		}
 	}
@@ -519,14 +626,14 @@ static int ohci_hcd_at91_drv_remove(struct platform_device *pdev)
 	int			i;
 
 	if (pdata) {
-		for (i = 0; i < ARRAY_SIZE(pdata->vbus_pin); i++) {
+		at91_for_each_port(i) {
 			if (!gpio_is_valid(pdata->vbus_pin[i]))
 				continue;
 			ohci_at91_usb_set_power(pdata, i, 0);
 			gpio_free(pdata->vbus_pin[i]);
 		}
 
-		for (i = 0; i < ARRAY_SIZE(pdata->overcurrent_pin); i++) {
+		at91_for_each_port(i) {
 			if (!gpio_is_valid(pdata->overcurrent_pin[i]))
 				continue;
 			free_irq(gpio_to_irq(pdata->overcurrent_pin[i]), pdev);
@@ -596,5 +703,6 @@ static struct platform_driver ohci_hcd_at91_driver = {
 	.driver		= {
 		.name	= "at91_ohci",
 		.owner	= THIS_MODULE,
+		.of_match_table	= of_match_ptr(at91_ohci_dt_ids),
 	},
 };
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 543e90e336b8..235171f29460 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -42,7 +42,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
 
diff --git a/drivers/usb/host/ohci-sa1111.c b/drivers/usb/host/ohci-sa1111.c
index 4bde4f9821ba..e1004fb37bd9 100644
--- a/drivers/usb/host/ohci-sa1111.c
+++ b/drivers/usb/host/ohci-sa1111.c
@@ -16,29 +16,115 @@
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <mach/assabet.h>
-#include <mach/badge4.h>
 #include <asm/hardware/sa1111.h>
 
 #ifndef CONFIG_SA1111
 #error "This file is SA-1111 bus glue.  CONFIG_SA1111 must be defined."
 #endif
 
-extern int usb_disabled(void);
+#define USB_STATUS	0x0118
+#define USB_RESET	0x011c
+#define USB_IRQTEST	0x0120
+
+#define USB_RESET_FORCEIFRESET	(1 << 0)
+#define USB_RESET_FORCEHCRESET	(1 << 1)
+#define USB_RESET_CLKGENRESET	(1 << 2)
+#define USB_RESET_SIMSCALEDOWN	(1 << 3)
+#define USB_RESET_USBINTTEST	(1 << 4)
+#define USB_RESET_SLEEPSTBYEN	(1 << 5)
+#define USB_RESET_PWRSENSELOW	(1 << 6)
+#define USB_RESET_PWRCTRLLOW	(1 << 7)
+
+#define USB_STATUS_IRQHCIRMTWKUP  (1 <<  7)
+#define USB_STATUS_IRQHCIBUFFACC  (1 <<  8)
+#define USB_STATUS_NIRQHCIM       (1 <<  9)
+#define USB_STATUS_NHCIMFCLR      (1 << 10)
+#define USB_STATUS_USBPWRSENSE    (1 << 11)
 
-/*-------------------------------------------------------------------------*/
+#if 0
+static void dump_hci_status(struct usb_hcd *hcd, const char *label)
+{
+	unsigned long status = sa1111_readl(hcd->regs + USB_STATUS);
+
+	dbg("%s USB_STATUS = { %s%s%s%s%s}", label,
+	     ((status & USB_STATUS_IRQHCIRMTWKUP) ? "IRQHCIRMTWKUP " : ""),
+	     ((status & USB_STATUS_IRQHCIBUFFACC) ? "IRQHCIBUFFACC " : ""),
+	     ((status & USB_STATUS_NIRQHCIM) ? "" : "IRQHCIM "),
+	     ((status & USB_STATUS_NHCIMFCLR) ? "" : "HCIMFCLR "),
+	     ((status & USB_STATUS_USBPWRSENSE) ? "USBPWRSENSE " : ""));
+}
+#endif
 
-static void sa1111_start_hc(struct sa1111_dev *dev)
+static int ohci_sa1111_reset(struct usb_hcd *hcd)
 {
-	unsigned int usb_rst = 0;
+	struct ohci_hcd *ohci = hcd_to_ohci(hcd);
+
+	ohci_hcd_init(ohci);
+	return ohci_init(ohci);
+}
 
-	printk(KERN_DEBUG "%s: starting SA-1111 OHCI USB Controller\n",
-	       __FILE__);
+static int __devinit ohci_sa1111_start(struct usb_hcd *hcd)
+{
+	struct ohci_hcd	*ohci = hcd_to_ohci(hcd);
+	int ret;
 
-#ifdef CONFIG_SA1100_BADGE4
-	if (machine_is_badge4()) {
-		badge4_set_5V(BADGE4_5V_USB, 1);
+	ret = ohci_run(ohci);
+	if (ret < 0) {
+		ohci_err(ohci, "can't start\n");
+		ohci_stop(hcd);
 	}
+	return ret;
+}
+
+static const struct hc_driver ohci_sa1111_hc_driver = {
+	.description =		hcd_name,
+	.product_desc =		"SA-1111 OHCI",
+	.hcd_priv_size =	sizeof(struct ohci_hcd),
+
+	/*
+	 * generic hardware linkage
+	 */
+	.irq =			ohci_irq,
+	.flags =		HCD_USB11 | HCD_MEMORY,
+
+	/*
+	 * basic lifecycle operations
+	 */
+	.reset =		ohci_sa1111_reset,
+	.start =		ohci_sa1111_start,
+	.stop =			ohci_stop,
+	.shutdown =		ohci_shutdown,
+
+	/*
+	 * managing i/o requests and associated device resources
+	 */
+	.urb_enqueue =		ohci_urb_enqueue,
+	.urb_dequeue =		ohci_urb_dequeue,
+	.endpoint_disable =	ohci_endpoint_disable,
+
+	/*
+	 * scheduling support
+	 */
+	.get_frame_number =	ohci_get_frame,
+
+	/*
+	 * root hub support
+	 */
+	.hub_status_data =	ohci_hub_status_data,
+	.hub_control =		ohci_hub_control,
+#ifdef	CONFIG_PM
+	.bus_suspend =		ohci_bus_suspend,
+	.bus_resume =		ohci_bus_resume,
 #endif
+	.start_port_reset =	ohci_start_port_reset,
+};
+
+static int sa1111_start_hc(struct sa1111_dev *dev)
+{
+	unsigned int usb_rst = 0;
+	int ret;
+
+	dev_dbg(&dev->dev, "starting SA-1111 OHCI USB Controller\n");
 
 	if (machine_is_xp860() ||
 	    machine_has_neponset() ||
@@ -51,220 +137,121 @@ static void sa1111_start_hc(struct sa1111_dev *dev)
 	 * host controller in reset.
 	 */
 	sa1111_writel(usb_rst | USB_RESET_FORCEIFRESET | USB_RESET_FORCEHCRESET,
-		      dev->mapbase + SA1111_USB_RESET);
+		      dev->mapbase + USB_RESET);
 
 	/*
 	 * Now, carefully enable the USB clock, and take
 	 * the USB host controller out of reset.
 	 */
-	sa1111_enable_device(dev);
-	udelay(11);
-	sa1111_writel(usb_rst, dev->mapbase + SA1111_USB_RESET);
+	ret = sa1111_enable_device(dev);
+	if (ret == 0) {
+		udelay(11);
+		sa1111_writel(usb_rst, dev->mapbase + USB_RESET);
+	}
+
+	return ret;
 }
 
 static void sa1111_stop_hc(struct sa1111_dev *dev)
 {
 	unsigned int usb_rst;
-	printk(KERN_DEBUG "%s: stopping SA-1111 OHCI USB Controller\n",
-	       __FILE__);
+
+	dev_dbg(&dev->dev, "stopping SA-1111 OHCI USB Controller\n");
 
 	/*
 	 * Put the USB host controller into reset.
 	 */
-	usb_rst = sa1111_readl(dev->mapbase + SA1111_USB_RESET);
+	usb_rst = sa1111_readl(dev->mapbase + USB_RESET);
 	sa1111_writel(usb_rst | USB_RESET_FORCEIFRESET | USB_RESET_FORCEHCRESET,
-		      dev->mapbase + SA1111_USB_RESET);
+		      dev->mapbase + USB_RESET);
 
 	/*
 	 * Stop the USB clock.
 	 */
 	sa1111_disable_device(dev);
-
-#ifdef CONFIG_SA1100_BADGE4
-	if (machine_is_badge4()) {
-		/* Disable power to the USB bus */
-		badge4_set_5V(BADGE4_5V_USB, 0);
-	}
-#endif
-}
-
-
-/*-------------------------------------------------------------------------*/
-
-#if 0
-static void dump_hci_status(struct usb_hcd *hcd, const char *label)
-{
-	unsigned long status = sa1111_readl(hcd->regs + SA1111_USB_STATUS);
-
-	dbg ("%s USB_STATUS = { %s%s%s%s%s}", label,
-	     ((status & USB_STATUS_IRQHCIRMTWKUP) ? "IRQHCIRMTWKUP " : ""),
-	     ((status & USB_STATUS_IRQHCIBUFFACC) ? "IRQHCIBUFFACC " : ""),
-	     ((status & USB_STATUS_NIRQHCIM) ? "" : "IRQHCIM "),
-	     ((status & USB_STATUS_NHCIMFCLR) ? "" : "HCIMFCLR "),
-	     ((status & USB_STATUS_USBPWRSENSE) ? "USBPWRSENSE " : ""));
 }
-#endif
-
-/*-------------------------------------------------------------------------*/
-
-/* configure so an HC device and id are always provided */
-/* always called with process context; sleeping is OK */
-
 
 /**
- * usb_hcd_sa1111_probe - initialize SA-1111-based HCDs
- * Context: !in_interrupt()
+ * ohci_hcd_sa1111_probe - initialize SA-1111-based HCDs
  *
  * Allocates basic resources for this USB host controller, and
- * then invokes the start() method for the HCD associated with it
- * through the hotplug entry's driver_data.
- *
- * Store this function in the HCD's struct pci_driver as probe().
+ * then invokes the start() method for the HCD associated with it.
  */
-int usb_hcd_sa1111_probe (const struct hc_driver *driver,
-			  struct sa1111_dev *dev)
+static int ohci_hcd_sa1111_probe(struct sa1111_dev *dev)
 {
 	struct usb_hcd *hcd;
-	int retval;
+	int ret;
 
-	hcd = usb_create_hcd (driver, &dev->dev, "sa1111");
+	if (usb_disabled())
+		return -ENODEV;
+
+	hcd = usb_create_hcd(&ohci_sa1111_hc_driver, &dev->dev, "sa1111");
 	if (!hcd)
 		return -ENOMEM;
+
 	hcd->rsrc_start = dev->res.start;
 	hcd->rsrc_len = resource_size(&dev->res);
 
 	if (!request_mem_region(hcd->rsrc_start, hcd->rsrc_len, hcd_name)) {
 		dbg("request_mem_region failed");
-		retval = -EBUSY;
+		ret = -EBUSY;
 		goto err1;
 	}
+
 	hcd->regs = dev->mapbase;
 
-	sa1111_start_hc(dev);
-	ohci_hcd_init(hcd_to_ohci(hcd));
+	ret = sa1111_start_hc(dev);
+	if (ret)
+		goto err2;
 
-	retval = usb_add_hcd(hcd, dev->irq[1], 0);
-	if (retval == 0)
-		return retval;
+	ret = usb_add_hcd(hcd, dev->irq[1], 0);
+	if (ret == 0)
+		return ret;
 
 	sa1111_stop_hc(dev);
+ err2:
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
  err1:
 	usb_put_hcd(hcd);
-	return retval;
+	return ret;
 }
 
-
-/* may be called without controller electrically present */
-/* may be called with controller, bus, and devices active */
-
 /**
- * usb_hcd_sa1111_remove - shutdown processing for SA-1111-based HCDs
+ * ohci_hcd_sa1111_remove - shutdown processing for SA-1111-based HCDs
  * @dev: USB Host Controller being removed
- * Context: !in_interrupt()
- *
- * Reverses the effect of usb_hcd_sa1111_probe(), first invoking
- * the HCD's stop() method.  It is always called from a thread
- * context, normally "rmmod", "apmd", or something similar.
  *
+ * Reverses the effect of ohci_hcd_sa1111_probe(), first invoking
+ * the HCD's stop() method.
  */
-void usb_hcd_sa1111_remove (struct usb_hcd *hcd, struct sa1111_dev *dev)
+static int ohci_hcd_sa1111_remove(struct sa1111_dev *dev)
 {
+	struct usb_hcd *hcd = sa1111_get_drvdata(dev);
+
 	usb_remove_hcd(hcd);
 	sa1111_stop_hc(dev);
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
 	usb_put_hcd(hcd);
-}
-
-/*-------------------------------------------------------------------------*/
 
-static int __devinit
-ohci_sa1111_start (struct usb_hcd *hcd)
-{
-	struct ohci_hcd	*ohci = hcd_to_ohci (hcd);
-	int		ret;
-
-	if ((ret = ohci_init(ohci)) < 0)
-		return ret;
-
-	if ((ret = ohci_run (ohci)) < 0) {
-		err ("can't start %s", hcd->self.bus_name);
-		ohci_stop (hcd);
-		return ret;
-	}
 	return 0;
 }
 
-/*-------------------------------------------------------------------------*/
-
-static const struct hc_driver ohci_sa1111_hc_driver = {
-	.description =		hcd_name,
-	.product_desc =		"SA-1111 OHCI",
-	.hcd_priv_size =	sizeof(struct ohci_hcd),
-
-	/*
-	 * generic hardware linkage
-	 */
-	.irq =			ohci_irq,
-	.flags =		HCD_USB11 | HCD_MEMORY,
-
-	/*
-	 * basic lifecycle operations
-	 */
-	.start =		ohci_sa1111_start,
-	.stop =			ohci_stop,
-
-	/*
-	 * managing i/o requests and associated device resources
-	 */
-	.urb_enqueue =		ohci_urb_enqueue,
-	.urb_dequeue =		ohci_urb_dequeue,
-	.endpoint_disable =	ohci_endpoint_disable,
-
-	/*
-	 * scheduling support
-	 */
-	.get_frame_number =	ohci_get_frame,
-
-	/*
-	 * root hub support
-	 */
-	.hub_status_data =	ohci_hub_status_data,
-	.hub_control =		ohci_hub_control,
-#ifdef	CONFIG_PM
-	.bus_suspend =		ohci_bus_suspend,
-	.bus_resume =		ohci_bus_resume,
-#endif
-	.start_port_reset =	ohci_start_port_reset,
-};
-
-/*-------------------------------------------------------------------------*/
-
-static int ohci_hcd_sa1111_drv_probe(struct sa1111_dev *dev)
-{
-	int ret;
-
-	if (usb_disabled())
-		return -ENODEV;
-
-	ret = usb_hcd_sa1111_probe(&ohci_sa1111_hc_driver, dev);
-	return ret;
-}
-
-static int ohci_hcd_sa1111_drv_remove(struct sa1111_dev *dev)
+static void ohci_hcd_sa1111_shutdown(struct sa1111_dev *dev)
 {
 	struct usb_hcd *hcd = sa1111_get_drvdata(dev);
 
-	usb_hcd_sa1111_remove(hcd, dev);
-	return 0;
+	if (test_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags)) {
+		hcd->driver->shutdown(hcd);
+		sa1111_stop_hc(dev);
+	}
 }
 
 static struct sa1111_driver ohci_hcd_sa1111_driver = {
 	.drv = {
 		.name	= "sa1111-ohci",
+		.owner	= THIS_MODULE,
 	},
 	.devid		= SA1111_DEVID_USB,
-	.probe		= ohci_hcd_sa1111_drv_probe,
-	.remove		= ohci_hcd_sa1111_drv_remove,
+	.probe		= ohci_hcd_sa1111_probe,
+	.remove		= ohci_hcd_sa1111_remove,
+	.shutdown	= ohci_hcd_sa1111_shutdown,
 };
-
diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
index 015c7c62ed49..3b38030b02a8 100644
--- a/drivers/usb/host/oxu210hp-hcd.c
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -40,7 +40,6 @@
 #include <linux/io.h>
 
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include <linux/irq.h>
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index 2a2cce2d2fa7..91ce1c02e617 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -51,7 +51,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c
index 16dd6a6abf00..dbbd1ba25224 100644
--- a/drivers/usb/host/u132-hcd.c
+++ b/drivers/usb/host/u132-hcd.c
@@ -55,7 +55,6 @@
 #include <linux/mutex.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 	/* FIXME ohci.h is ONLY for internal use by the OHCI driver.
diff --git a/drivers/usb/host/uhci-hcd.c b/drivers/usb/host/uhci-hcd.c
index e37dea87bb56..e4db350602b8 100644
--- a/drivers/usb/host/uhci-hcd.c
+++ b/drivers/usb/host/uhci-hcd.c
@@ -45,7 +45,6 @@
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include "uhci-hcd.h"
 
diff --git a/drivers/usb/musb/ux500_dma.c b/drivers/usb/musb/ux500_dma.c
index 97cb45916c43..d05c7fbbb703 100644
--- a/drivers/usb/musb/ux500_dma.c
+++ b/drivers/usb/musb/ux500_dma.c
@@ -115,12 +115,12 @@ static bool ux500_configure_channel(struct dma_channel *channel,
 	slave_conf.dst_addr = usb_fifo_addr;
 	slave_conf.dst_addr_width = addr_width;
 	slave_conf.dst_maxburst = 16;
+	slave_conf.device_fc = false;
 
 	dma_chan->device->device_control(dma_chan, DMA_SLAVE_CONFIG,
 					     (unsigned long) &slave_conf);
 
-	dma_desc = dma_chan->device->
-			device_prep_slave_sg(dma_chan, &sg, 1, direction,
+	dma_desc = dmaengine_prep_slave_sg(dma_chan, &sg, 1, direction,
 					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!dma_desc)
 		return false;
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index 3648c82a17fe..6ec7f838d7fa 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -786,9 +786,8 @@ static void xfer_work(struct work_struct *work)
 	sg_dma_address(&sg) = pkt->dma + pkt->actual;
 	sg_dma_len(&sg) = pkt->trans;
 
-	desc = chan->device->device_prep_slave_sg(chan, &sg, 1, dir,
-						  DMA_PREP_INTERRUPT |
-						  DMA_CTRL_ACK);
+	desc = dmaengine_prep_slave_sg(chan, &sg, 1, dir,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc)
 		return;
 
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 7c229d304684..ff8605b4b4be 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1724,7 +1724,8 @@ static void ftdi_HE_TIRA1_setup(struct ftdi_private *priv)
 
 /*
  * Module parameter to control latency timer for NDI FTDI-based USB devices.
- * If this value is not set in modprobe.conf.local its value will be set to 1ms.
+ * If this value is not set in /etc/modprobe.d/ its value will be set
+ * to 1ms.
  */
 static int ndi_latency_timer = 1;
 
diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig
index fe2d803a6347..7691c866637b 100644
--- a/drivers/usb/storage/Kconfig
+++ b/drivers/usb/storage/Kconfig
@@ -222,7 +222,7 @@ config USB_LIBUSUAL
 	  for usb-storage and ub drivers, and allows to switch binding
 	  of these devices without rebuilding modules.
 
-	  Typical syntax of /etc/modprobe.conf is:
+	  Typical syntax of /etc/modprobe.d/*conf is:
 
 		options libusual bias="ub"
 
diff --git a/drivers/uwb/uwb-debug.c b/drivers/uwb/uwb-debug.c
index 2eecec0c13c9..6ec45beb7af5 100644
--- a/drivers/uwb/uwb-debug.c
+++ b/drivers/uwb/uwb-debug.c
@@ -159,13 +159,6 @@ static int cmd_ie_rm(struct uwb_rc *rc, struct uwb_dbg_cmd_ie *ie_to_rm)
 	return uwb_rc_ie_rm(rc, ie_to_rm->data[0]);
 }
 
-static int command_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-
-	return 0;
-}
-
 static ssize_t command_write(struct file *file, const char __user *buf,
 			 size_t len, loff_t *off)
 {
@@ -206,7 +199,7 @@ static ssize_t command_write(struct file *file, const char __user *buf,
 }
 
 static const struct file_operations command_fops = {
-	.open   = command_open,
+	.open	= simple_open,
 	.write  = command_write,
 	.read   = NULL,
 	.llseek = no_llseek,
diff --git a/drivers/video/amifb.c b/drivers/video/amifb.c
index f23cae094f1b..887df9d81422 100644
--- a/drivers/video/amifb.c
+++ b/drivers/video/amifb.c
@@ -53,7 +53,6 @@
 #include <linux/platform_device.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
diff --git a/drivers/video/backlight/88pm860x_bl.c b/drivers/video/backlight/88pm860x_bl.c
index 915943af3f21..f49181c73113 100644
--- a/drivers/video/backlight/88pm860x_bl.c
+++ b/drivers/video/backlight/88pm860x_bl.c
@@ -67,6 +67,28 @@ static inline int wled_idc(int port)
 	return ret;
 }
 
+static int backlight_power_set(struct pm860x_chip *chip, int port,
+		int on)
+{
+	int ret = -EINVAL;
+
+	switch (port) {
+	case PM8606_BACKLIGHT1:
+		ret = on ? pm8606_osc_enable(chip, WLED1_DUTY) :
+			pm8606_osc_disable(chip, WLED1_DUTY);
+		break;
+	case PM8606_BACKLIGHT2:
+		ret = on ? pm8606_osc_enable(chip, WLED2_DUTY) :
+			pm8606_osc_disable(chip, WLED2_DUTY);
+		break;
+	case PM8606_BACKLIGHT3:
+		ret = on ? pm8606_osc_enable(chip, WLED3_DUTY) :
+			pm8606_osc_disable(chip, WLED3_DUTY);
+		break;
+	}
+	return ret;
+}
+
 static int pm860x_backlight_set(struct backlight_device *bl, int brightness)
 {
 	struct pm860x_backlight_data *data = bl_get_data(bl);
@@ -79,6 +101,9 @@ static int pm860x_backlight_set(struct backlight_device *bl, int brightness)
 	else
 		value = brightness;
 
+	if (brightness)
+		backlight_power_set(chip, data->port, 1);
+
 	ret = pm860x_reg_write(data->i2c, wled_a(data->port), value);
 	if (ret < 0)
 		goto out;
@@ -115,6 +140,9 @@ static int pm860x_backlight_set(struct backlight_device *bl, int brightness)
 	if (ret < 0)
 		goto out;
 
+	if (brightness == 0)
+		backlight_power_set(chip, data->port, 0);
+
 	dev_dbg(chip->dev, "set brightness %d\n", value);
 	data->current_brightness = value;
 	return 0;
@@ -170,7 +198,6 @@ static int pm860x_backlight_probe(struct platform_device *pdev)
 	struct backlight_device *bl;
 	struct resource *res;
 	struct backlight_properties props;
-	unsigned char value;
 	char name[MFD_NAME_SIZE];
 	int ret;
 
@@ -217,26 +244,6 @@ static int pm860x_backlight_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, bl);
 
-	/* Enable reference VSYS */
-	ret = pm860x_reg_read(data->i2c, PM8606_VSYS);
-	if (ret < 0)
-		goto out;
-	if ((ret & PM8606_VSYS_EN) == 0) {
-		value = ret | PM8606_VSYS_EN;
-		ret = pm860x_reg_write(data->i2c, PM8606_VSYS, value);
-		if (ret < 0)
-			goto out;
-	}
-	/* Enable reference OSC */
-	ret = pm860x_reg_read(data->i2c, PM8606_MISC);
-	if (ret < 0)
-		goto out;
-	if ((ret & PM8606_MISC_OSC_EN) == 0) {
-		value = ret | PM8606_MISC_OSC_EN;
-		ret = pm860x_reg_write(data->i2c, PM8606_MISC, value);
-		if (ret < 0)
-			goto out;
-	}
 	/* read current backlight */
 	ret = pm860x_backlight_get_brightness(bl);
 	if (ret < 0)
diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index 7ed9991fa747..af16884491ed 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -245,6 +245,12 @@ config BACKLIGHT_DA903X
 	  If you have a LCD backlight connected to the WLED output of DA9030
 	  or DA9034 WLED output, say Y here to enable this driver.
 
+config BACKLIGHT_DA9052
+	tristate "Dialog DA9052/DA9053 WLED"
+	depends on PMIC_DA9052
+	help
+	  Enable the Backlight Driver for DA9052-BC and DA9053-AA/Bx PMICs.
+
 config BACKLIGHT_MAX8925
 	tristate "Backlight driver for MAX8925"
 	depends on MFD_MAX8925
diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile
index 8071eb656147..36855ae887d6 100644
--- a/drivers/video/backlight/Makefile
+++ b/drivers/video/backlight/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_BACKLIGHT_PROGEAR) += progear_bl.o
 obj-$(CONFIG_BACKLIGHT_CARILLO_RANCH) += cr_bllcd.o
 obj-$(CONFIG_BACKLIGHT_PWM)	+= pwm_bl.o
 obj-$(CONFIG_BACKLIGHT_DA903X)	+= da903x_bl.o
+obj-$(CONFIG_BACKLIGHT_DA9052)	+= da9052_bl.o
 obj-$(CONFIG_BACKLIGHT_MAX8925)	+= max8925_bl.o
 obj-$(CONFIG_BACKLIGHT_APPLE)	+= apple_bl.o
 obj-$(CONFIG_BACKLIGHT_TOSA)	+= tosa_bl.o
diff --git a/drivers/video/backlight/apple_bl.c b/drivers/video/backlight/apple_bl.c
index be98d152b7fd..a523b255e124 100644
--- a/drivers/video/backlight/apple_bl.c
+++ b/drivers/video/backlight/apple_bl.c
@@ -24,6 +24,7 @@
 #include <linux/io.h>
 #include <linux/pci.h>
 #include <linux/acpi.h>
+#include <linux/atomic.h>
 
 static struct backlight_device *apple_backlight_device;
 
@@ -221,14 +222,32 @@ static struct acpi_driver apple_bl_driver = {
 	},
 };
 
+static atomic_t apple_bl_registered = ATOMIC_INIT(0);
+
+int apple_bl_register(void)
+{
+	if (atomic_xchg(&apple_bl_registered, 1) == 0)
+		return acpi_bus_register_driver(&apple_bl_driver);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apple_bl_register);
+
+void apple_bl_unregister(void)
+{
+	if (atomic_xchg(&apple_bl_registered, 0) == 1)
+		acpi_bus_unregister_driver(&apple_bl_driver);
+}
+EXPORT_SYMBOL_GPL(apple_bl_unregister);
+
 static int __init apple_bl_init(void)
 {
-	return acpi_bus_register_driver(&apple_bl_driver);
+	return apple_bl_register();
 }
 
 static void __exit apple_bl_exit(void)
 {
-	acpi_bus_unregister_driver(&apple_bl_driver);
+	apple_bl_unregister();
 }
 
 module_init(apple_bl_init);
diff --git a/drivers/video/backlight/da9052_bl.c b/drivers/video/backlight/da9052_bl.c
new file mode 100644
index 000000000000..b628d68f5162
--- /dev/null
+++ b/drivers/video/backlight/da9052_bl.c
@@ -0,0 +1,187 @@
+/*
+ * Backlight Driver for Dialog DA9052 PMICs
+ *
+ * Copyright(c) 2012 Dialog Semiconductor Ltd.
+ *
+ * Author: David Dajun Chen <dchen@diasemi.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/fb.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <linux/mfd/da9052/da9052.h>
+#include <linux/mfd/da9052/reg.h>
+
+#define DA9052_MAX_BRIGHTNESS		0xFF
+
+enum {
+	DA9052_WLEDS_OFF,
+	DA9052_WLEDS_ON,
+};
+
+enum {
+	DA9052_TYPE_WLED1,
+	DA9052_TYPE_WLED2,
+	DA9052_TYPE_WLED3,
+};
+
+static unsigned char wled_bank[] = {
+	DA9052_LED1_CONF_REG,
+	DA9052_LED2_CONF_REG,
+	DA9052_LED3_CONF_REG,
+};
+
+struct da9052_bl {
+	struct da9052 *da9052;
+	uint brightness;
+	uint state;
+	uint led_reg;
+};
+
+static int da9052_adjust_wled_brightness(struct da9052_bl *wleds)
+{
+	unsigned char boost_en;
+	unsigned char i_sink;
+	int ret;
+
+	boost_en = 0x3F;
+	i_sink = 0xFF;
+	if (wleds->state == DA9052_WLEDS_OFF) {
+		boost_en = 0x00;
+		i_sink = 0x00;
+	}
+
+	ret = da9052_reg_write(wleds->da9052, DA9052_BOOST_REG, boost_en);
+	if (ret < 0)
+		return ret;
+
+	ret = da9052_reg_write(wleds->da9052, DA9052_LED_CONT_REG, i_sink);
+	if (ret < 0)
+		return ret;
+
+	ret = da9052_reg_write(wleds->da9052, wled_bank[wleds->led_reg], 0x0);
+	if (ret < 0)
+		return ret;
+
+	msleep(10);
+
+	if (wleds->brightness) {
+		ret = da9052_reg_write(wleds->da9052, wled_bank[wleds->led_reg],
+				       wleds->brightness);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int da9052_backlight_update_status(struct backlight_device *bl)
+{
+	int brightness = bl->props.brightness;
+	struct da9052_bl *wleds = bl_get_data(bl);
+
+	wleds->brightness = brightness;
+	wleds->state = DA9052_WLEDS_ON;
+
+	return da9052_adjust_wled_brightness(wleds);
+}
+
+static int da9052_backlight_get_brightness(struct backlight_device *bl)
+{
+	struct da9052_bl *wleds = bl_get_data(bl);
+
+	return wleds->brightness;
+}
+
+static const struct backlight_ops da9052_backlight_ops = {
+	.update_status = da9052_backlight_update_status,
+	.get_brightness = da9052_backlight_get_brightness,
+};
+
+static int da9052_backlight_probe(struct platform_device *pdev)
+{
+	struct backlight_device *bl;
+	struct backlight_properties props;
+	struct da9052_bl *wleds;
+
+	wleds = devm_kzalloc(&pdev->dev, sizeof(struct da9052_bl), GFP_KERNEL);
+	if (!wleds)
+		return -ENOMEM;
+
+	wleds->da9052 = dev_get_drvdata(pdev->dev.parent);
+	wleds->brightness = 0;
+	wleds->led_reg = platform_get_device_id(pdev)->driver_data;
+	wleds->state = DA9052_WLEDS_OFF;
+
+	props.type = BACKLIGHT_RAW;
+	props.max_brightness = DA9052_MAX_BRIGHTNESS;
+
+	bl = backlight_device_register(pdev->name, wleds->da9052->dev, wleds,
+				       &da9052_backlight_ops, &props);
+	if (IS_ERR(bl)) {
+		dev_err(&pdev->dev, "Failed to register backlight\n");
+		devm_kfree(&pdev->dev, wleds);
+		return PTR_ERR(bl);
+	}
+
+	bl->props.max_brightness = DA9052_MAX_BRIGHTNESS;
+	bl->props.brightness = 0;
+	platform_set_drvdata(pdev, bl);
+
+	return da9052_adjust_wled_brightness(wleds);
+}
+
+static int da9052_backlight_remove(struct platform_device *pdev)
+{
+	struct backlight_device *bl = platform_get_drvdata(pdev);
+	struct da9052_bl *wleds = bl_get_data(bl);
+
+	wleds->brightness = 0;
+	wleds->state = DA9052_WLEDS_OFF;
+	da9052_adjust_wled_brightness(wleds);
+	backlight_device_unregister(bl);
+	devm_kfree(&pdev->dev, wleds);
+
+	return 0;
+}
+
+static struct platform_device_id da9052_wled_ids[] = {
+	{
+		.name		= "da9052-wled1",
+		.driver_data	= DA9052_TYPE_WLED1,
+	},
+	{
+		.name		= "da9052-wled2",
+		.driver_data	= DA9052_TYPE_WLED2,
+	},
+	{
+		.name		= "da9052-wled3",
+		.driver_data	= DA9052_TYPE_WLED3,
+	},
+};
+
+static struct platform_driver da9052_wled_driver = {
+	.probe		= da9052_backlight_probe,
+	.remove		= da9052_backlight_remove,
+	.id_table	= da9052_wled_ids,
+	.driver	= {
+		.name	= "da9052-wled",
+		.owner	= THIS_MODULE,
+	},
+};
+
+module_platform_driver(da9052_wled_driver);
+
+MODULE_AUTHOR("David Dajun Chen <dchen@diasemi.com>");
+MODULE_DESCRIPTION("Backlight driver for DA9052 PMIC");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:da9052-backlight");
diff --git a/drivers/video/backlight/locomolcd.c b/drivers/video/backlight/locomolcd.c
index be20b5cbe26c..3a6d5419e3e3 100644
--- a/drivers/video/backlight/locomolcd.c
+++ b/drivers/video/backlight/locomolcd.c
@@ -229,14 +229,7 @@ static struct locomo_driver poodle_lcd_driver = {
 
 static int __init locomolcd_init(void)
 {
-	int ret = locomo_driver_register(&poodle_lcd_driver);
-	if (ret)
-		return ret;
-
-#ifdef CONFIG_SA1100_COLLIE
-	sa1100fb_lcd_power = locomolcd_power;
-#endif
-	return 0;
+	return locomo_driver_register(&poodle_lcd_driver);
 }
 
 static void __exit locomolcd_exit(void)
diff --git a/drivers/video/backlight/tosa_lcd.c b/drivers/video/backlight/tosa_lcd.c
index a2161f631a83..2231aec23918 100644
--- a/drivers/video/backlight/tosa_lcd.c
+++ b/drivers/video/backlight/tosa_lcd.c
@@ -271,7 +271,7 @@ static int tosa_lcd_resume(struct spi_device *spi)
 }
 #else
 #define tosa_lcd_suspend	NULL
-#define tosa_lcd_reume NULL
+#define tosa_lcd_resume NULL
 #endif
 
 static struct spi_driver tosa_lcd_driver = {
diff --git a/drivers/video/bt431.h b/drivers/video/bt431.h
index c826f2787bad..04e0cfbba538 100644
--- a/drivers/video/bt431.h
+++ b/drivers/video/bt431.h
@@ -8,7 +8,6 @@
  *	archive for more details.
  */
 #include <linux/types.h>
-#include <asm/system.h>
 
 /*
  * Bt431 cursor generator registers, 32-bit aligned.
diff --git a/drivers/video/bt455.h b/drivers/video/bt455.h
index b7591fea7add..80f61b03e9ae 100644
--- a/drivers/video/bt455.h
+++ b/drivers/video/bt455.h
@@ -8,7 +8,6 @@
  *	archive for more details.
  */
 #include <linux/types.h>
-#include <asm/system.h>
 
 /*
  * Bt455 byte-wide registers, 32-bit aligned.
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index 8745637e4b7e..2e471c22abf5 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -77,7 +77,6 @@
 #include <linux/crc32.h> /* For counting font checksums */
 #include <asm/fb.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include "fbcon.h"
 
diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c
index a122d9287d16..6d1596629040 100644
--- a/drivers/video/console/newport_con.c
+++ b/drivers/video/console/newport_con.c
@@ -22,7 +22,6 @@
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/gio_device.h>
diff --git a/drivers/video/cyber2000fb.c b/drivers/video/cyber2000fb.c
index 850380795b05..c1527f5b47ee 100644
--- a/drivers/video/cyber2000fb.c
+++ b/drivers/video/cyber2000fb.c
@@ -51,7 +51,6 @@
 #include <linux/i2c-algo-bit.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 
 #ifdef __arm__
 #include <asm/mach-types.h>
diff --git a/drivers/video/dnfb.c b/drivers/video/dnfb.c
index ec56d2544c73..49e3dda1a361 100644
--- a/drivers/video/dnfb.c
+++ b/drivers/video/dnfb.c
@@ -7,7 +7,6 @@
 #include <linux/platform_device.h>
 
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
diff --git a/drivers/video/mx3fb.c b/drivers/video/mx3fb.c
index 727a5149d818..eec0d7b748eb 100644
--- a/drivers/video/mx3fb.c
+++ b/drivers/video/mx3fb.c
@@ -337,7 +337,7 @@ static void sdc_enable_channel(struct mx3fb_info *mx3_fbi)
 
 	/* This enables the channel */
 	if (mx3_fbi->cookie < 0) {
-		mx3_fbi->txd = dma_chan->device->device_prep_slave_sg(dma_chan,
+		mx3_fbi->txd = dmaengine_prep_slave_sg(dma_chan,
 		      &mx3_fbi->sg[0], 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
 		if (!mx3_fbi->txd) {
 			dev_err(mx3fb->dev, "Cannot allocate descriptor on %d\n",
@@ -1091,7 +1091,7 @@ static int mx3fb_pan_display(struct fb_var_screeninfo *var,
 	if (mx3_fbi->txd)
 		async_tx_ack(mx3_fbi->txd);
 
-	txd = dma_chan->device->device_prep_slave_sg(dma_chan, sg +
+	txd = dmaengine_prep_slave_sg(dma_chan, sg +
 		mx3_fbi->cur_ipu_buf, 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
 	if (!txd) {
 		dev_err(fbi->device,
diff --git a/drivers/video/neofb.c b/drivers/video/neofb.c
index fb3f67391105..afc9521173ef 100644
--- a/drivers/video/neofb.c
+++ b/drivers/video/neofb.c
@@ -71,7 +71,6 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_MTRR
 #include <asm/mtrr.h>
diff --git a/drivers/video/omap2/vrfb.c b/drivers/video/omap2/vrfb.c
index fd2271600370..4e5b960c32c8 100644
--- a/drivers/video/omap2/vrfb.c
+++ b/drivers/video/omap2/vrfb.c
@@ -27,7 +27,6 @@
 #include <linux/bitops.h>
 #include <linux/mutex.h>
 
-#include <mach/io.h>
 #include <plat/vrfb.h>
 #include <plat/sdrc.h>
 
diff --git a/drivers/video/pmag-ba-fb.c b/drivers/video/pmag-ba-fb.c
index 0c69fa20251b..9b4a60b52a4c 100644
--- a/drivers/video/pmag-ba-fb.c
+++ b/drivers/video/pmag-ba-fb.c
@@ -33,7 +33,6 @@
 #include <linux/types.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <video/pmag-ba-fb.h>
 
diff --git a/drivers/video/pmagb-b-fb.c b/drivers/video/pmagb-b-fb.c
index 22fcb9a3d5c0..4e7a9c46e112 100644
--- a/drivers/video/pmagb-b-fb.c
+++ b/drivers/video/pmagb-b-fb.c
@@ -29,7 +29,6 @@
 #include <linux/types.h>
 
 #include <asm/io.h>
-#include <asm/system.h>
 
 #include <video/pmagb-b-fb.h>
 
diff --git a/drivers/video/q40fb.c b/drivers/video/q40fb.c
index f5a39f5aa900..a104e8cd2f54 100644
--- a/drivers/video/q40fb.c
+++ b/drivers/video/q40fb.c
@@ -20,7 +20,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/q40_master.h>
 #include <linux/fb.h>
 #include <linux/module.h>
diff --git a/drivers/video/sa1100fb.c b/drivers/video/sa1100fb.c
index 98d55d0e2da5..b6325848ad61 100644
--- a/drivers/video/sa1100fb.c
+++ b/drivers/video/sa1100fb.c
@@ -173,282 +173,48 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/cpufreq.h>
+#include <linux/gpio.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/mutex.h>
 #include <linux/io.h>
 
+#include <video/sa1100fb.h>
+
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <mach/assabet.h>
 #include <mach/shannon.h>
 
 /*
- * debugging?
- */
-#define DEBUG 0
-/*
  * Complain if VAR is out of range.
  */
 #define DEBUG_VAR 1
 
-#undef ASSABET_PAL_VIDEO
-
 #include "sa1100fb.h"
 
-extern void (*sa1100fb_backlight_power)(int on);
-extern void (*sa1100fb_lcd_power)(int on);
-
-static struct sa1100fb_rgb rgb_4 = {
+static const struct sa1100fb_rgb rgb_4 = {
 	.red	= { .offset = 0,  .length = 4, },
 	.green	= { .offset = 0,  .length = 4, },
 	.blue	= { .offset = 0,  .length = 4, },
 	.transp	= { .offset = 0,  .length = 0, },
 };
 
-static struct sa1100fb_rgb rgb_8 = {
+static const struct sa1100fb_rgb rgb_8 = {
 	.red	= { .offset = 0,  .length = 8, },
 	.green	= { .offset = 0,  .length = 8, },
 	.blue	= { .offset = 0,  .length = 8, },
 	.transp	= { .offset = 0,  .length = 0, },
 };
 
-static struct sa1100fb_rgb def_rgb_16 = {
+static const struct sa1100fb_rgb def_rgb_16 = {
 	.red	= { .offset = 11, .length = 5, },
 	.green	= { .offset = 5,  .length = 6, },
 	.blue	= { .offset = 0,  .length = 5, },
 	.transp	= { .offset = 0,  .length = 0, },
 };
 
-#ifdef CONFIG_SA1100_ASSABET
-#ifndef ASSABET_PAL_VIDEO
-/*
- * The assabet uses a sharp LQ039Q2DS54 LCD module.  It is actually
- * takes an RGB666 signal, but we provide it with an RGB565 signal
- * instead (def_rgb_16).
- */
-static struct sa1100fb_mach_info lq039q2ds54_info __initdata = {
-	.pixclock	= 171521,	.bpp		= 16,
-	.xres		= 320,		.yres		= 240,
-
-	.hsync_len	= 5,		.vsync_len	= 1,
-	.left_margin	= 61,		.upper_margin	= 3,
-	.right_margin	= 9,		.lower_margin	= 0,
-
-	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
-
-	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
-	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
-};
-#else
-static struct sa1100fb_mach_info pal_info __initdata = {
-	.pixclock	= 67797,	.bpp		= 16,
-	.xres		= 640,		.yres		= 512,
-
-	.hsync_len	= 64,		.vsync_len	= 6,
-	.left_margin	= 125,		.upper_margin	= 70,
-	.right_margin	= 115,		.lower_margin	= 36,
-
-	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
-	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(512),
-};
-#endif
-#endif
-
-#ifdef CONFIG_SA1100_H3600
-static struct sa1100fb_mach_info h3600_info __initdata = {
-	.pixclock	= 174757, 	.bpp		= 16,
-	.xres		= 320,		.yres		= 240,
-
-	.hsync_len	= 3,		.vsync_len	= 3,
-	.left_margin	= 12,		.upper_margin	= 10,
-	.right_margin	= 17,		.lower_margin	= 1,
-
-	.cmap_static	= 1,
-
-	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
-	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
-};
-
-static struct sa1100fb_rgb h3600_rgb_16 = {
-	.red	= { .offset = 12, .length = 4, },
-	.green	= { .offset = 7,  .length = 4, },
-	.blue	= { .offset = 1,  .length = 4, },
-	.transp	= { .offset = 0,  .length = 0, },
-};
-#endif
-
-#ifdef CONFIG_SA1100_H3100
-static struct sa1100fb_mach_info h3100_info __initdata = {
-	.pixclock	= 406977, 	.bpp		= 4,
-	.xres		= 320,		.yres		= 240,
-
-	.hsync_len	= 26,		.vsync_len	= 41,
-	.left_margin	= 4,		.upper_margin	= 0,
-	.right_margin	= 4,		.lower_margin	= 0,
-
-	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
-	.cmap_greyscale	= 1,
-	.cmap_inverse	= 1,
-
-	.lccr0		= LCCR0_Mono | LCCR0_4PixMono | LCCR0_Sngl | LCCR0_Pas,
-	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
-};
-#endif
-
-#ifdef CONFIG_SA1100_COLLIE
-static struct sa1100fb_mach_info collie_info __initdata = {
-	.pixclock	= 171521,	.bpp		= 16,
-	.xres		= 320,		.yres		= 240,
-
-	.hsync_len	= 5,		.vsync_len	= 1,
-	.left_margin	= 11,		.upper_margin	= 2,
-	.right_margin	= 30,		.lower_margin	= 0,
-
-	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
-
-	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
-	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
-};
-#endif
-
-#ifdef LART_GREY_LCD
-static struct sa1100fb_mach_info lart_grey_info __initdata = {
-	.pixclock	= 150000,	.bpp		= 4,
-	.xres		= 320,		.yres		= 240,
-
-	.hsync_len	= 1,		.vsync_len	= 1,
-	.left_margin	= 4,		.upper_margin	= 0,
-	.right_margin	= 2,		.lower_margin	= 0,
-
-	.cmap_greyscale	= 1,
-	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
-
-	.lccr0		= LCCR0_Mono | LCCR0_Sngl | LCCR0_Pas | LCCR0_4PixMono,
-	.lccr3		= LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(512),
-};
-#endif
-#ifdef LART_COLOR_LCD
-static struct sa1100fb_mach_info lart_color_info __initdata = {
-	.pixclock	= 150000,	.bpp		= 16,
-	.xres		= 320,		.yres		= 240,
-
-	.hsync_len	= 2,		.vsync_len	= 3,
-	.left_margin	= 69,		.upper_margin	= 14,
-	.right_margin	= 8,		.lower_margin	= 4,
-
-	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
-	.lccr3		= LCCR3_OutEnH | LCCR3_PixFlEdg | LCCR3_ACBsDiv(512),
-};
-#endif
-#ifdef LART_VIDEO_OUT
-static struct sa1100fb_mach_info lart_video_info __initdata = {
-	.pixclock	= 39721,	.bpp		= 16,
-	.xres		= 640,		.yres		= 480,
-
-	.hsync_len	= 95,		.vsync_len	= 2,
-	.left_margin	= 40,		.upper_margin	= 32,
-	.right_margin	= 24,		.lower_margin	= 11,
-
-	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
-
-	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
-	.lccr3		= LCCR3_OutEnL | LCCR3_PixFlEdg | LCCR3_ACBsDiv(512),
-};
-#endif
-
-#ifdef LART_KIT01_LCD
-static struct sa1100fb_mach_info lart_kit01_info __initdata = {
-	.pixclock	= 63291,	.bpp		= 16,
-	.xres		= 640,		.yres		= 480,
-
-	.hsync_len	= 64,		.vsync_len	= 3,
-	.left_margin	= 122,		.upper_margin	= 45,
-	.right_margin	= 10,		.lower_margin	= 10,
-
-	.lccr0		= LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
-	.lccr3		= LCCR3_OutEnH | LCCR3_PixFlEdg
-};
-#endif
-
-#ifdef CONFIG_SA1100_SHANNON
-static struct sa1100fb_mach_info shannon_info __initdata = {
-	.pixclock	= 152500,	.bpp		= 8,
-	.xres		= 640,		.yres		= 480,
-
-	.hsync_len	= 4,		.vsync_len	= 3,
-	.left_margin	= 2,		.upper_margin	= 0,
-	.right_margin	= 1,		.lower_margin	= 0,
-
-	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
-
-	.lccr0		= LCCR0_Color | LCCR0_Dual | LCCR0_Pas,
-	.lccr3		= LCCR3_ACBsDiv(512),
-};
-#endif
-
 
 
-static struct sa1100fb_mach_info * __init
-sa1100fb_get_machine_info(struct sa1100fb_info *fbi)
-{
-	struct sa1100fb_mach_info *inf = NULL;
-
-	/*
-	 *            R        G       B       T
-	 * default  {11,5}, { 5,6}, { 0,5}, { 0,0}
-	 * h3600    {12,4}, { 7,4}, { 1,4}, { 0,0}
-	 * freebird { 8,4}, { 4,4}, { 0,4}, {12,4}
-	 */
-#ifdef CONFIG_SA1100_ASSABET
-	if (machine_is_assabet()) {
-#ifndef ASSABET_PAL_VIDEO
-		inf = &lq039q2ds54_info;
-#else
-		inf = &pal_info;
-#endif
-	}
-#endif
-#ifdef CONFIG_SA1100_H3100
-	if (machine_is_h3100()) {
-		inf = &h3100_info;
-	}
-#endif
-#ifdef CONFIG_SA1100_H3600
-	if (machine_is_h3600()) {
-		inf = &h3600_info;
-		fbi->rgb[RGB_16] = &h3600_rgb_16;
-	}
-#endif
-#ifdef CONFIG_SA1100_COLLIE
-	if (machine_is_collie()) {
-		inf = &collie_info;
-	}
-#endif
-#ifdef CONFIG_SA1100_LART
-	if (machine_is_lart()) {
-#ifdef LART_GREY_LCD
-		inf = &lart_grey_info;
-#endif
-#ifdef LART_COLOR_LCD
-		inf = &lart_color_info;
-#endif
-#ifdef LART_VIDEO_OUT
-		inf = &lart_video_info;
-#endif
-#ifdef LART_KIT01_LCD
-		inf = &lart_kit01_info;
-#endif
-	}
-#endif
-#ifdef CONFIG_SA1100_SHANNON
-	if (machine_is_shannon()) {
-		inf = &shannon_info;
-	}
-#endif
-	return inf;
-}
-
 static int sa1100fb_activate_var(struct fb_var_screeninfo *var, struct sa1100fb_info *);
 static void set_ctrlr_state(struct sa1100fb_info *fbi, u_int state);
 
@@ -533,7 +299,7 @@ sa1100fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 	 * is what you poke into the framebuffer to produce the
 	 * colour you requested.
 	 */
-	if (fbi->cmap_inverse) {
+	if (fbi->inf->cmap_inverse) {
 		red   = 0xffff - red;
 		green = 0xffff - green;
 		blue  = 0xffff - blue;
@@ -607,14 +373,14 @@ sa1100fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 		var->xres = MIN_XRES;
 	if (var->yres < MIN_YRES)
 		var->yres = MIN_YRES;
-	if (var->xres > fbi->max_xres)
-		var->xres = fbi->max_xres;
-	if (var->yres > fbi->max_yres)
-		var->yres = fbi->max_yres;
+	if (var->xres > fbi->inf->xres)
+		var->xres = fbi->inf->xres;
+	if (var->yres > fbi->inf->yres)
+		var->yres = fbi->inf->yres;
 	var->xres_virtual = max(var->xres_virtual, var->xres);
 	var->yres_virtual = max(var->yres_virtual, var->yres);
 
-	DPRINTK("var->bits_per_pixel=%d\n", var->bits_per_pixel);
+	dev_dbg(fbi->dev, "var->bits_per_pixel=%d\n", var->bits_per_pixel);
 	switch (var->bits_per_pixel) {
 	case 4:
 		rgbidx = RGB_4;
@@ -638,16 +404,16 @@ sa1100fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 	var->blue   = fbi->rgb[rgbidx]->blue;
 	var->transp = fbi->rgb[rgbidx]->transp;
 
-	DPRINTK("RGBT length = %d:%d:%d:%d\n",
+	dev_dbg(fbi->dev, "RGBT length = %d:%d:%d:%d\n",
 		var->red.length, var->green.length, var->blue.length,
 		var->transp.length);
 
-	DPRINTK("RGBT offset = %d:%d:%d:%d\n",
+	dev_dbg(fbi->dev, "RGBT offset = %d:%d:%d:%d\n",
 		var->red.offset, var->green.offset, var->blue.offset,
 		var->transp.offset);
 
 #ifdef CONFIG_CPU_FREQ
-	printk(KERN_DEBUG "dma period = %d ps, clock = %d kHz\n",
+	dev_dbg(fbi->dev, "dma period = %d ps, clock = %d kHz\n",
 		sa1100fb_display_dma_period(var),
 		cpufreq_get(smp_processor_id()));
 #endif
@@ -655,22 +421,10 @@ sa1100fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 	return 0;
 }
 
-static inline void sa1100fb_set_truecolor(u_int is_true_color)
+static void sa1100fb_set_visual(struct sa1100fb_info *fbi, u32 visual)
 {
-	if (machine_is_assabet()) {
-#if 1		// phase 4 or newer Assabet's
-		if (is_true_color)
-			ASSABET_BCR_set(ASSABET_BCR_LCD_12RGB);
-		else
-			ASSABET_BCR_clear(ASSABET_BCR_LCD_12RGB);
-#else
-		// older Assabet's
-		if (is_true_color)
-			ASSABET_BCR_clear(ASSABET_BCR_LCD_12RGB);
-		else
-			ASSABET_BCR_set(ASSABET_BCR_LCD_12RGB);
-#endif
-	}
+	if (fbi->inf->set_visual)
+		fbi->inf->set_visual(visual);
 }
 
 /*
@@ -683,11 +437,11 @@ static int sa1100fb_set_par(struct fb_info *info)
 	struct fb_var_screeninfo *var = &info->var;
 	unsigned long palette_mem_size;
 
-	DPRINTK("set_par\n");
+	dev_dbg(fbi->dev, "set_par\n");
 
 	if (var->bits_per_pixel == 16)
 		fbi->fb.fix.visual = FB_VISUAL_TRUECOLOR;
-	else if (!fbi->cmap_static)
+	else if (!fbi->inf->cmap_static)
 		fbi->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR;
 	else {
 		/*
@@ -704,7 +458,7 @@ static int sa1100fb_set_par(struct fb_info *info)
 
 	palette_mem_size = fbi->palette_size * sizeof(u16);
 
-	DPRINTK("palette_mem_size = 0x%08lx\n", (u_long) palette_mem_size);
+	dev_dbg(fbi->dev, "palette_mem_size = 0x%08lx\n", palette_mem_size);
 
 	fbi->palette_cpu = (u16 *)(fbi->map_cpu + PAGE_SIZE - palette_mem_size);
 	fbi->palette_dma = fbi->map_dma + PAGE_SIZE - palette_mem_size;
@@ -712,7 +466,7 @@ static int sa1100fb_set_par(struct fb_info *info)
 	/*
 	 * Set (any) board control register to handle new color depth
 	 */
-	sa1100fb_set_truecolor(fbi->fb.fix.visual == FB_VISUAL_TRUECOLOR);
+	sa1100fb_set_visual(fbi, fbi->fb.fix.visual);
 	sa1100fb_activate_var(var, fbi);
 
 	return 0;
@@ -728,7 +482,7 @@ sa1100fb_set_cmap(struct fb_cmap *cmap, int kspc, int con,
 	/*
 	 * Make sure the user isn't doing something stupid.
 	 */
-	if (!kspc && (fbi->fb.var.bits_per_pixel == 16 || fbi->cmap_static))
+	if (!kspc && (fbi->fb.var.bits_per_pixel == 16 || fbi->inf->cmap_static))
 		return -EINVAL;
 
 	return gen_set_cmap(cmap, kspc, con, info);
@@ -775,7 +529,7 @@ static int sa1100fb_blank(int blank, struct fb_info *info)
 	struct sa1100fb_info *fbi = (struct sa1100fb_info *)info;
 	int i;
 
-	DPRINTK("sa1100fb_blank: blank=%d\n", blank);
+	dev_dbg(fbi->dev, "sa1100fb_blank: blank=%d\n", blank);
 
 	switch (blank) {
 	case FB_BLANK_POWERDOWN:
@@ -863,43 +617,43 @@ static int sa1100fb_activate_var(struct fb_var_screeninfo *var, struct sa1100fb_
 	u_int half_screen_size, yres, pcd;
 	u_long flags;
 
-	DPRINTK("Configuring SA1100 LCD\n");
+	dev_dbg(fbi->dev, "Configuring SA1100 LCD\n");
 
-	DPRINTK("var: xres=%d hslen=%d lm=%d rm=%d\n",
+	dev_dbg(fbi->dev, "var: xres=%d hslen=%d lm=%d rm=%d\n",
 		var->xres, var->hsync_len,
 		var->left_margin, var->right_margin);
-	DPRINTK("var: yres=%d vslen=%d um=%d bm=%d\n",
+	dev_dbg(fbi->dev, "var: yres=%d vslen=%d um=%d bm=%d\n",
 		var->yres, var->vsync_len,
 		var->upper_margin, var->lower_margin);
 
 #if DEBUG_VAR
 	if (var->xres < 16        || var->xres > 1024)
-		printk(KERN_ERR "%s: invalid xres %d\n",
+		dev_err(fbi->dev, "%s: invalid xres %d\n",
 			fbi->fb.fix.id, var->xres);
 	if (var->hsync_len < 1    || var->hsync_len > 64)
-		printk(KERN_ERR "%s: invalid hsync_len %d\n",
+		dev_err(fbi->dev, "%s: invalid hsync_len %d\n",
 			fbi->fb.fix.id, var->hsync_len);
 	if (var->left_margin < 1  || var->left_margin > 255)
-		printk(KERN_ERR "%s: invalid left_margin %d\n",
+		dev_err(fbi->dev, "%s: invalid left_margin %d\n",
 			fbi->fb.fix.id, var->left_margin);
 	if (var->right_margin < 1 || var->right_margin > 255)
-		printk(KERN_ERR "%s: invalid right_margin %d\n",
+		dev_err(fbi->dev, "%s: invalid right_margin %d\n",
 			fbi->fb.fix.id, var->right_margin);
 	if (var->yres < 1         || var->yres > 1024)
-		printk(KERN_ERR "%s: invalid yres %d\n",
+		dev_err(fbi->dev, "%s: invalid yres %d\n",
 			fbi->fb.fix.id, var->yres);
 	if (var->vsync_len < 1    || var->vsync_len > 64)
-		printk(KERN_ERR "%s: invalid vsync_len %d\n",
+		dev_err(fbi->dev, "%s: invalid vsync_len %d\n",
 			fbi->fb.fix.id, var->vsync_len);
 	if (var->upper_margin < 0 || var->upper_margin > 255)
-		printk(KERN_ERR "%s: invalid upper_margin %d\n",
+		dev_err(fbi->dev, "%s: invalid upper_margin %d\n",
 			fbi->fb.fix.id, var->upper_margin);
 	if (var->lower_margin < 0 || var->lower_margin > 255)
-		printk(KERN_ERR "%s: invalid lower_margin %d\n",
+		dev_err(fbi->dev, "%s: invalid lower_margin %d\n",
 			fbi->fb.fix.id, var->lower_margin);
 #endif
 
-	new_regs.lccr0 = fbi->lccr0 |
+	new_regs.lccr0 = fbi->inf->lccr0 |
 		LCCR0_LEN | LCCR0_LDM | LCCR0_BAM |
 		LCCR0_ERM | LCCR0_LtlEnd | LCCR0_DMADel(0);
 
@@ -914,7 +668,7 @@ static int sa1100fb_activate_var(struct fb_var_screeninfo *var, struct sa1100fb_
 	 * the YRES parameter.
 	 */
 	yres = var->yres;
-	if (fbi->lccr0 & LCCR0_Dual)
+	if (fbi->inf->lccr0 & LCCR0_Dual)
 		yres /= 2;
 
 	new_regs.lccr2 =
@@ -924,14 +678,14 @@ static int sa1100fb_activate_var(struct fb_var_screeninfo *var, struct sa1100fb_
 		LCCR2_EndFrmDel(var->lower_margin);
 
 	pcd = get_pcd(var->pixclock, cpufreq_get(0));
-	new_regs.lccr3 = LCCR3_PixClkDiv(pcd) | fbi->lccr3 |
+	new_regs.lccr3 = LCCR3_PixClkDiv(pcd) | fbi->inf->lccr3 |
 		(var->sync & FB_SYNC_HOR_HIGH_ACT ? LCCR3_HorSnchH : LCCR3_HorSnchL) |
 		(var->sync & FB_SYNC_VERT_HIGH_ACT ? LCCR3_VrtSnchH : LCCR3_VrtSnchL);
 
-	DPRINTK("nlccr0 = 0x%08lx\n", new_regs.lccr0);
-	DPRINTK("nlccr1 = 0x%08lx\n", new_regs.lccr1);
-	DPRINTK("nlccr2 = 0x%08lx\n", new_regs.lccr2);
-	DPRINTK("nlccr3 = 0x%08lx\n", new_regs.lccr3);
+	dev_dbg(fbi->dev, "nlccr0 = 0x%08lx\n", new_regs.lccr0);
+	dev_dbg(fbi->dev, "nlccr1 = 0x%08lx\n", new_regs.lccr1);
+	dev_dbg(fbi->dev, "nlccr2 = 0x%08lx\n", new_regs.lccr2);
+	dev_dbg(fbi->dev, "nlccr3 = 0x%08lx\n", new_regs.lccr3);
 
 	half_screen_size = var->bits_per_pixel;
 	half_screen_size = half_screen_size * var->xres * var->yres / 16;
@@ -951,9 +705,12 @@ static int sa1100fb_activate_var(struct fb_var_screeninfo *var, struct sa1100fb_
 	 * Only update the registers if the controller is enabled
 	 * and something has changed.
 	 */
-	if ((LCCR0 != fbi->reg_lccr0)       || (LCCR1 != fbi->reg_lccr1) ||
-	    (LCCR2 != fbi->reg_lccr2)       || (LCCR3 != fbi->reg_lccr3) ||
-	    (DBAR1 != fbi->dbar1) || (DBAR2 != fbi->dbar2))
+	if (readl_relaxed(fbi->base + LCCR0) != fbi->reg_lccr0 ||
+	    readl_relaxed(fbi->base + LCCR1) != fbi->reg_lccr1 ||
+	    readl_relaxed(fbi->base + LCCR2) != fbi->reg_lccr2 ||
+	    readl_relaxed(fbi->base + LCCR3) != fbi->reg_lccr3 ||
+	    readl_relaxed(fbi->base + DBAR1) != fbi->dbar1 ||
+	    readl_relaxed(fbi->base + DBAR2) != fbi->dbar2)
 		sa1100fb_schedule_work(fbi, C_REENABLE);
 
 	return 0;
@@ -967,18 +724,18 @@ static int sa1100fb_activate_var(struct fb_var_screeninfo *var, struct sa1100fb_
  */
 static inline void __sa1100fb_backlight_power(struct sa1100fb_info *fbi, int on)
 {
-	DPRINTK("backlight o%s\n", on ? "n" : "ff");
+	dev_dbg(fbi->dev, "backlight o%s\n", on ? "n" : "ff");
 
-	if (sa1100fb_backlight_power)
-		sa1100fb_backlight_power(on);
+	if (fbi->inf->backlight_power)
+		fbi->inf->backlight_power(on);
 }
 
 static inline void __sa1100fb_lcd_power(struct sa1100fb_info *fbi, int on)
 {
-	DPRINTK("LCD power o%s\n", on ? "n" : "ff");
+	dev_dbg(fbi->dev, "LCD power o%s\n", on ? "n" : "ff");
 
-	if (sa1100fb_lcd_power)
-		sa1100fb_lcd_power(on);
+	if (fbi->inf->lcd_power)
+		fbi->inf->lcd_power(on);
 }
 
 static void sa1100fb_setup_gpio(struct sa1100fb_info *fbi)
@@ -1008,14 +765,25 @@ static void sa1100fb_setup_gpio(struct sa1100fb_info *fbi)
 	}
 
 	if (mask) {
+		unsigned long flags;
+
+		/*
+		 * SA-1100 requires the GPIO direction register set
+		 * appropriately for the alternate function.  Hence
+		 * we set it here via bitmask rather than excessive
+		 * fiddling via the GPIO subsystem - and even then
+		 * we'll still have to deal with GAFR.
+		 */
+		local_irq_save(flags);
 		GPDR |= mask;
 		GAFR |= mask;
+		local_irq_restore(flags);
 	}
 }
 
 static void sa1100fb_enable_controller(struct sa1100fb_info *fbi)
 {
-	DPRINTK("Enabling LCD controller\n");
+	dev_dbg(fbi->dev, "Enabling LCD controller\n");
 
 	/*
 	 * Make sure the mode bits are present in the first palette entry
@@ -1024,43 +792,46 @@ static void sa1100fb_enable_controller(struct sa1100fb_info *fbi)
 	fbi->palette_cpu[0] |= palette_pbs(&fbi->fb.var);
 
 	/* Sequence from 11.7.10 */
-	LCCR3 = fbi->reg_lccr3;
-	LCCR2 = fbi->reg_lccr2;
-	LCCR1 = fbi->reg_lccr1;
-	LCCR0 = fbi->reg_lccr0 & ~LCCR0_LEN;
-	DBAR1 = fbi->dbar1;
-	DBAR2 = fbi->dbar2;
-	LCCR0 |= LCCR0_LEN;
-
-	if (machine_is_shannon()) {
-		GPDR |= SHANNON_GPIO_DISP_EN;
-		GPSR |= SHANNON_GPIO_DISP_EN;
-	}
-
-	DPRINTK("DBAR1 = 0x%08x\n", DBAR1);
-	DPRINTK("DBAR2 = 0x%08x\n", DBAR2);
-	DPRINTK("LCCR0 = 0x%08x\n", LCCR0);
-	DPRINTK("LCCR1 = 0x%08x\n", LCCR1);
-	DPRINTK("LCCR2 = 0x%08x\n", LCCR2);
-	DPRINTK("LCCR3 = 0x%08x\n", LCCR3);
+	writel_relaxed(fbi->reg_lccr3, fbi->base + LCCR3);
+	writel_relaxed(fbi->reg_lccr2, fbi->base + LCCR2);
+	writel_relaxed(fbi->reg_lccr1, fbi->base + LCCR1);
+	writel_relaxed(fbi->reg_lccr0 & ~LCCR0_LEN, fbi->base + LCCR0);
+	writel_relaxed(fbi->dbar1, fbi->base + DBAR1);
+	writel_relaxed(fbi->dbar2, fbi->base + DBAR2);
+	writel_relaxed(fbi->reg_lccr0 | LCCR0_LEN, fbi->base + LCCR0);
+
+	if (machine_is_shannon())
+		gpio_set_value(SHANNON_GPIO_DISP_EN, 1);
+
+	dev_dbg(fbi->dev, "DBAR1: 0x%08x\n", readl_relaxed(fbi->base + DBAR1));
+	dev_dbg(fbi->dev, "DBAR2: 0x%08x\n", readl_relaxed(fbi->base + DBAR2));
+	dev_dbg(fbi->dev, "LCCR0: 0x%08x\n", readl_relaxed(fbi->base + LCCR0));
+	dev_dbg(fbi->dev, "LCCR1: 0x%08x\n", readl_relaxed(fbi->base + LCCR1));
+	dev_dbg(fbi->dev, "LCCR2: 0x%08x\n", readl_relaxed(fbi->base + LCCR2));
+	dev_dbg(fbi->dev, "LCCR3: 0x%08x\n", readl_relaxed(fbi->base + LCCR3));
 }
 
 static void sa1100fb_disable_controller(struct sa1100fb_info *fbi)
 {
 	DECLARE_WAITQUEUE(wait, current);
+	u32 lccr0;
 
-	DPRINTK("Disabling LCD controller\n");
+	dev_dbg(fbi->dev, "Disabling LCD controller\n");
 
-	if (machine_is_shannon()) {
-		GPCR |= SHANNON_GPIO_DISP_EN;
-	}	
+	if (machine_is_shannon())
+		gpio_set_value(SHANNON_GPIO_DISP_EN, 0);
 
 	set_current_state(TASK_UNINTERRUPTIBLE);
 	add_wait_queue(&fbi->ctrlr_wait, &wait);
 
-	LCSR = 0xffffffff;	/* Clear LCD Status Register */
-	LCCR0 &= ~LCCR0_LDM;	/* Enable LCD Disable Done Interrupt */
-	LCCR0 &= ~LCCR0_LEN;	/* Disable LCD Controller */
+	/* Clear LCD Status Register */
+	writel_relaxed(~0, fbi->base + LCSR);
+
+	lccr0 = readl_relaxed(fbi->base + LCCR0);
+	lccr0 &= ~LCCR0_LDM;	/* Enable LCD Disable Done Interrupt */
+	writel_relaxed(lccr0, fbi->base + LCCR0);
+	lccr0 &= ~LCCR0_LEN;	/* Disable LCD Controller */
+	writel_relaxed(lccr0, fbi->base + LCCR0);
 
 	schedule_timeout(20 * HZ / 1000);
 	remove_wait_queue(&fbi->ctrlr_wait, &wait);
@@ -1072,14 +843,15 @@ static void sa1100fb_disable_controller(struct sa1100fb_info *fbi)
 static irqreturn_t sa1100fb_handle_irq(int irq, void *dev_id)
 {
 	struct sa1100fb_info *fbi = dev_id;
-	unsigned int lcsr = LCSR;
+	unsigned int lcsr = readl_relaxed(fbi->base + LCSR);
 
 	if (lcsr & LCSR_LDD) {
-		LCCR0 |= LCCR0_LDM;
+		u32 lccr0 = readl_relaxed(fbi->base + LCCR0) | LCCR0_LDM;
+		writel_relaxed(lccr0, fbi->base + LCCR0);
 		wake_up(&fbi->ctrlr_wait);
 	}
 
-	LCSR = lcsr;
+	writel_relaxed(lcsr, fbi->base + LCSR);
 	return IRQ_HANDLED;
 }
 
@@ -1268,7 +1040,7 @@ sa1100fb_freq_policy(struct notifier_block *nb, unsigned long val,
 	switch (val) {
 	case CPUFREQ_ADJUST:
 	case CPUFREQ_INCOMPATIBLE:
-		printk(KERN_DEBUG "min dma period: %d ps, "
+		dev_dbg(fbi->dev, "min dma period: %d ps, "
 			"new clock %d kHz\n", sa1100fb_min_dma_period(fbi),
 			policy->max);
 		/* todo: fill in min/max values */
@@ -1318,7 +1090,7 @@ static int sa1100fb_resume(struct platform_device *dev)
  *      cache.  Once this area is remapped, all virtual memory
  *      access to the video memory should occur at the new region.
  */
-static int __init sa1100fb_map_video_memory(struct sa1100fb_info *fbi)
+static int __devinit sa1100fb_map_video_memory(struct sa1100fb_info *fbi)
 {
 	/*
 	 * We reserve one page for the palette, plus the size
@@ -1344,7 +1116,7 @@ static int __init sa1100fb_map_video_memory(struct sa1100fb_info *fbi)
 }
 
 /* Fake monspecs to fill in fbinfo structure */
-static struct fb_monspecs monspecs __initdata = {
+static struct fb_monspecs monspecs __devinitdata = {
 	.hfmin	= 30000,
 	.hfmax	= 70000,
 	.vfmin	= 50,
@@ -1352,10 +1124,11 @@ static struct fb_monspecs monspecs __initdata = {
 };
 
 
-static struct sa1100fb_info * __init sa1100fb_init_fbinfo(struct device *dev)
+static struct sa1100fb_info * __devinit sa1100fb_init_fbinfo(struct device *dev)
 {
-	struct sa1100fb_mach_info *inf;
+	struct sa1100fb_mach_info *inf = dev->platform_data;
 	struct sa1100fb_info *fbi;
+	unsigned i;
 
 	fbi = kmalloc(sizeof(struct sa1100fb_info) + sizeof(u32) * 16,
 		      GFP_KERNEL);
@@ -1390,8 +1163,6 @@ static struct sa1100fb_info * __init sa1100fb_init_fbinfo(struct device *dev)
 	fbi->rgb[RGB_8]		= &rgb_8;
 	fbi->rgb[RGB_16]	= &def_rgb_16;
 
-	inf = sa1100fb_get_machine_info(fbi);
-
 	/*
 	 * People just don't seem to get this.  We don't support
 	 * anything but correct entries now, so panic if someone
@@ -1402,13 +1173,10 @@ static struct sa1100fb_info * __init sa1100fb_init_fbinfo(struct device *dev)
 		panic("sa1100fb error: invalid LCCR3 fields set or zero "
 			"pixclock.");
 
-	fbi->max_xres			= inf->xres;
 	fbi->fb.var.xres		= inf->xres;
 	fbi->fb.var.xres_virtual	= inf->xres;
-	fbi->max_yres			= inf->yres;
 	fbi->fb.var.yres		= inf->yres;
 	fbi->fb.var.yres_virtual	= inf->yres;
-	fbi->max_bpp			= inf->bpp;
 	fbi->fb.var.bits_per_pixel	= inf->bpp;
 	fbi->fb.var.pixclock		= inf->pixclock;
 	fbi->fb.var.hsync_len		= inf->hsync_len;
@@ -1419,14 +1187,16 @@ static struct sa1100fb_info * __init sa1100fb_init_fbinfo(struct device *dev)
 	fbi->fb.var.lower_margin	= inf->lower_margin;
 	fbi->fb.var.sync		= inf->sync;
 	fbi->fb.var.grayscale		= inf->cmap_greyscale;
-	fbi->cmap_inverse		= inf->cmap_inverse;
-	fbi->cmap_static		= inf->cmap_static;
-	fbi->lccr0			= inf->lccr0;
-	fbi->lccr3			= inf->lccr3;
 	fbi->state			= C_STARTUP;
 	fbi->task_state			= (u_char)-1;
-	fbi->fb.fix.smem_len		= fbi->max_xres * fbi->max_yres *
-					  fbi->max_bpp / 8;
+	fbi->fb.fix.smem_len		= inf->xres * inf->yres *
+					  inf->bpp / 8;
+	fbi->inf			= inf;
+
+	/* Copy the RGB bitfield overrides */
+	for (i = 0; i < NR_RGB; i++)
+		if (inf->rgb[i])
+			fbi->rgb[i] = inf->rgb[i];
 
 	init_waitqueue_head(&fbi->ctrlr_wait);
 	INIT_WORK(&fbi->task, sa1100fb_task);
@@ -1438,13 +1208,20 @@ static struct sa1100fb_info * __init sa1100fb_init_fbinfo(struct device *dev)
 static int __devinit sa1100fb_probe(struct platform_device *pdev)
 {
 	struct sa1100fb_info *fbi;
+	struct resource *res;
 	int ret, irq;
 
+	if (!pdev->dev.platform_data) {
+		dev_err(&pdev->dev, "no platform LCD data\n");
+		return -EINVAL;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
+	if (irq < 0 || !res)
 		return -EINVAL;
 
-	if (!request_mem_region(0xb0100000, 0x10000, "LCD"))
+	if (!request_mem_region(res->start, resource_size(res), "LCD"))
 		return -EBUSY;
 
 	fbi = sa1100fb_init_fbinfo(&pdev->dev);
@@ -1452,6 +1229,10 @@ static int __devinit sa1100fb_probe(struct platform_device *pdev)
 	if (!fbi)
 		goto failed;
 
+	fbi->base = ioremap(res->start, resource_size(res));
+	if (!fbi->base)
+		goto failed;
+
 	/* Initialize video memory */
 	ret = sa1100fb_map_video_memory(fbi);
 	if (ret)
@@ -1459,14 +1240,16 @@ static int __devinit sa1100fb_probe(struct platform_device *pdev)
 
 	ret = request_irq(irq, sa1100fb_handle_irq, 0, "LCD", fbi);
 	if (ret) {
-		printk(KERN_ERR "sa1100fb: request_irq failed: %d\n", ret);
+		dev_err(&pdev->dev, "request_irq failed: %d\n", ret);
 		goto failed;
 	}
 
-#ifdef ASSABET_PAL_VIDEO
-	if (machine_is_assabet())
-		ASSABET_BCR_clear(ASSABET_BCR_LCD_ON);
-#endif
+	if (machine_is_shannon()) {
+		ret = gpio_request_one(SHANNON_GPIO_DISP_EN,
+			GPIOF_OUT_INIT_LOW, "display enable");
+		if (ret)
+			goto err_free_irq;
+	}
 
 	/*
 	 * This makes sure that our colour bitfield
@@ -1478,7 +1261,7 @@ static int __devinit sa1100fb_probe(struct platform_device *pdev)
 
 	ret = register_framebuffer(&fbi->fb);
 	if (ret < 0)
-		goto err_free_irq;
+		goto err_reg_fb;
 
 #ifdef CONFIG_CPU_FREQ
 	fbi->freq_transition.notifier_call = sa1100fb_freq_transition;
@@ -1490,12 +1273,17 @@ static int __devinit sa1100fb_probe(struct platform_device *pdev)
 	/* This driver cannot be unloaded at the moment */
 	return 0;
 
+ err_reg_fb:
+	if (machine_is_shannon())
+		gpio_free(SHANNON_GPIO_DISP_EN);
  err_free_irq:
 	free_irq(irq, fbi);
  failed:
+	if (fbi)
+		iounmap(fbi->base);
 	platform_set_drvdata(pdev, NULL);
 	kfree(fbi);
-	release_mem_region(0xb0100000, 0x10000);
+	release_mem_region(res->start, resource_size(res));
 	return ret;
 }
 
@@ -1505,6 +1293,7 @@ static struct platform_driver sa1100fb_driver = {
 	.resume		= sa1100fb_resume,
 	.driver		= {
 		.name	= "sa11x0-fb",
+		.owner	= THIS_MODULE,
 	},
 };
 
diff --git a/drivers/video/sa1100fb.h b/drivers/video/sa1100fb.h
index 1c3b459865d8..fc5d4292fad6 100644
--- a/drivers/video/sa1100fb.h
+++ b/drivers/video/sa1100fb.h
@@ -10,44 +10,15 @@
  * for more details.
  */
 
-/*
- * These are the bitfields for each
- * display depth that we support.
- */
-struct sa1100fb_rgb {
-	struct fb_bitfield	red;
-	struct fb_bitfield	green;
-	struct fb_bitfield	blue;
-	struct fb_bitfield	transp;
-};
-
-/*
- * This structure describes the machine which we are running on.
- */
-struct sa1100fb_mach_info {
-	u_long		pixclock;
-
-	u_short		xres;
-	u_short		yres;
-
-	u_char		bpp;
-	u_char		hsync_len;
-	u_char		left_margin;
-	u_char		right_margin;
-
-	u_char		vsync_len;
-	u_char		upper_margin;
-	u_char		lower_margin;
-	u_char		sync;
-
-	u_int		cmap_greyscale:1,
-			cmap_inverse:1,
-			cmap_static:1,
-			unused:29;
-
-	u_int		lccr0;
-	u_int		lccr3;
-};
+#define LCCR0           0x0000          /* LCD Control Reg. 0 */
+#define LCSR            0x0004          /* LCD Status Reg. */
+#define DBAR1           0x0010          /* LCD DMA Base Address Reg. channel 1 */
+#define DCAR1           0x0014          /* LCD DMA Current Address Reg. channel 1 */
+#define DBAR2           0x0018          /* LCD DMA Base Address Reg.  channel 2 */
+#define DCAR2           0x001C          /* LCD DMA Current Address Reg. channel 2 */
+#define LCCR1           0x0020          /* LCD Control Reg. 1 */
+#define LCCR2           0x0024          /* LCD Control Reg. 2 */
+#define LCCR3           0x0028          /* LCD Control Reg. 3 */
 
 /* Shadows for LCD controller registers */
 struct sa1100fb_lcd_reg {
@@ -57,19 +28,11 @@ struct sa1100fb_lcd_reg {
 	unsigned long lccr3;
 };
 
-#define RGB_4	(0)
-#define RGB_8	(1)
-#define RGB_16	(2)
-#define NR_RGB	3
-
 struct sa1100fb_info {
 	struct fb_info		fb;
 	struct device		*dev;
-	struct sa1100fb_rgb	*rgb[NR_RGB];
-
-	u_int			max_bpp;
-	u_int			max_xres;
-	u_int			max_yres;
+	const struct sa1100fb_rgb *rgb[NR_RGB];
+	void __iomem		*base;
 
 	/*
 	 * These are the addresses we mapped
@@ -88,12 +51,6 @@ struct sa1100fb_info {
 	dma_addr_t		dbar1;
 	dma_addr_t		dbar2;
 
-	u_int			lccr0;
-	u_int			lccr3;
-	u_int			cmap_inverse:1,
-				cmap_static:1,
-				unused:30;
-
 	u_int			reg_lccr0;
 	u_int			reg_lccr1;
 	u_int			reg_lccr2;
@@ -109,6 +66,8 @@ struct sa1100fb_info {
 	struct notifier_block	freq_transition;
 	struct notifier_block	freq_policy;
 #endif
+
+	const struct sa1100fb_mach_info *inf;
 };
 
 #define TO_INF(ptr,member)	container_of(ptr,struct sa1100fb_info,member)
@@ -130,15 +89,6 @@ struct sa1100fb_info {
 #define SA1100_NAME	"SA1100"
 
 /*
- *  Debug macros 
- */
-#if DEBUG
-#  define DPRINTK(fmt, args...)	printk("%s: " fmt, __func__ , ## args)
-#else
-#  define DPRINTK(fmt, args...)
-#endif
-
-/*
  * Minimum X and Y resolutions
  */
 #define MIN_XRES	64
diff --git a/drivers/video/savage/savagefb_driver.c b/drivers/video/savage/savagefb_driver.c
index beb495044b24..cee7803a0a1c 100644
--- a/drivers/video/savage/savagefb_driver.c
+++ b/drivers/video/savage/savagefb_driver.c
@@ -56,7 +56,6 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_MTRR
 #include <asm/mtrr.h>
diff --git a/drivers/virtio/config.c b/drivers/virtio/config.c
index 983d482fba40..f70bcd2ff98f 100644
--- a/drivers/virtio/config.c
+++ b/drivers/virtio/config.c
@@ -9,5 +9,4 @@
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>
 #include <linux/bug.h>
-#include <asm/system.h>
 
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 958e5129c601..05f0a80818a2 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -398,21 +398,8 @@ static int restore_common(struct virtio_device *vdev)
 	return 0;
 }
 
-static int virtballoon_thaw(struct virtio_device *vdev)
-{
-	return restore_common(vdev);
-}
-
 static int virtballoon_restore(struct virtio_device *vdev)
 {
-	struct virtio_balloon *vb = vdev->priv;
-
-	/*
-	 * If a request wasn't complete at the time of freezing, this
-	 * could have been set.
-	 */
-	vb->need_stats_update = 0;
-
 	return restore_common(vdev);
 }
 #endif
@@ -434,7 +421,6 @@ static struct virtio_driver virtio_balloon_driver = {
 #ifdef CONFIG_PM
 	.freeze	=	virtballoon_freeze,
 	.restore =	virtballoon_restore,
-	.thaw =		virtballoon_thaw,
 #endif
 };
 
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 635e1efb3792..2e03d416b9af 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -720,24 +720,6 @@ static void __devexit virtio_pci_remove(struct pci_dev *pci_dev)
 }
 
 #ifdef CONFIG_PM
-static int virtio_pci_suspend(struct device *dev)
-{
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-
-	pci_save_state(pci_dev);
-	pci_set_power_state(pci_dev, PCI_D3hot);
-	return 0;
-}
-
-static int virtio_pci_resume(struct device *dev)
-{
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-
-	pci_restore_state(pci_dev);
-	pci_set_power_state(pci_dev, PCI_D0);
-	return 0;
-}
-
 static int virtio_pci_freeze(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
@@ -758,59 +740,24 @@ static int virtio_pci_freeze(struct device *dev)
 	return ret;
 }
 
-static int restore_common(struct device *dev)
-{
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-	int ret;
-
-	ret = pci_enable_device(pci_dev);
-	if (ret)
-		return ret;
-	pci_set_master(pci_dev);
-	vp_finalize_features(&vp_dev->vdev);
-
-	return ret;
-}
-
-static int virtio_pci_thaw(struct device *dev)
+static int virtio_pci_restore(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
 	struct virtio_driver *drv;
 	int ret;
 
-	ret = restore_common(dev);
-	if (ret)
-		return ret;
-
 	drv = container_of(vp_dev->vdev.dev.driver,
 			   struct virtio_driver, driver);
 
-	if (drv && drv->thaw)
-		ret = drv->thaw(&vp_dev->vdev);
-	else if (drv && drv->restore)
-		ret = drv->restore(&vp_dev->vdev);
-
-	/* Finally, tell the device we're all set */
-	if (!ret)
-		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
-
-	return ret;
-}
-
-static int virtio_pci_restore(struct device *dev)
-{
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-	struct virtio_driver *drv;
-	int ret;
+	ret = pci_enable_device(pci_dev);
+	if (ret)
+		return ret;
 
-	drv = container_of(vp_dev->vdev.dev.driver,
-			   struct virtio_driver, driver);
+	pci_set_master(pci_dev);
+	vp_finalize_features(&vp_dev->vdev);
 
-	ret = restore_common(dev);
-	if (!ret && drv && drv->restore)
+	if (drv && drv->restore)
 		ret = drv->restore(&vp_dev->vdev);
 
 	/* Finally, tell the device we're all set */
@@ -821,12 +768,7 @@ static int virtio_pci_restore(struct device *dev)
 }
 
 static const struct dev_pm_ops virtio_pci_pm_ops = {
-	.suspend	= virtio_pci_suspend,
-	.resume		= virtio_pci_resume,
-	.freeze		= virtio_pci_freeze,
-	.thaw		= virtio_pci_thaw,
-	.restore	= virtio_pci_restore,
-	.poweroff	= virtio_pci_suspend,
+	SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
 };
 #endif
 
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 0e7366dfc901..37096246c937 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -55,6 +55,7 @@ comment "Watchdog Device Drivers"
 
 config SOFT_WATCHDOG
 	tristate "Software watchdog"
+	select WATCHDOG_CORE
 	help
 	  A software monitoring watchdog. This will fail to reboot your system
 	  from some situations that the hardware watchdog will recover
@@ -74,6 +75,7 @@ config WM831X_WATCHDOG
 config WM8350_WATCHDOG
 	tristate "WM8350 watchdog"
 	depends on MFD_WM8350
+	select WATCHDOG_CORE
 	help
 	  Support for the watchdog in the WM8350 AudioPlus PMIC.  When
 	  the watchdog triggers the system will be reset.
@@ -217,6 +219,7 @@ config MPCORE_WATCHDOG
 config EP93XX_WATCHDOG
 	tristate "EP93xx Watchdog"
 	depends on ARCH_EP93XX
+	select WATCHDOG_CORE
 	help
 	  Say Y here if to include support for the watchdog timer
 	  embedded in the Cirrus Logic EP93xx family of devices.
@@ -234,6 +237,7 @@ config OMAP_WATCHDOG
 config PNX4008_WATCHDOG
 	tristate "PNX4008 and LPC32XX Watchdog"
 	depends on ARCH_PNX4008 || ARCH_LPC32XX
+	select WATCHDOG_CORE
 	help
 	  Say Y here if to include support for the watchdog timer
 	  in the PNX4008 or LPC32XX processor.
@@ -283,6 +287,7 @@ config COH901327_WATCHDOG
 	bool "ST-Ericsson COH 901 327 watchdog"
 	depends on ARCH_U300
 	default y if MACH_U300
+	select WATCHDOG_CORE
 	help
 	  Say Y here to include Watchdog timer support for the
 	  watchdog embedded into the ST-Ericsson U300 series platforms.
@@ -328,6 +333,7 @@ config TS72XX_WATCHDOG
 config MAX63XX_WATCHDOG
 	tristate "Max63xx watchdog"
 	depends on ARM && HAS_IOMEM
+	select WATCHDOG_CORE
 	help
 	  Support for memory mapped max63{69,70,71,72,73,74} watchdog timer.
 
@@ -955,6 +961,7 @@ config INDYDOG
 config JZ4740_WDT
 	tristate "Ingenic jz4740 SoC hardware watchdog"
 	depends on MACH_JZ4740
+	select WATCHDOG_CORE
 	help
 	  Hardware driver for the built-in watchdog timer on Ingenic jz4740 SoCs.
 
@@ -996,6 +1003,7 @@ config AR7_WDT
 config TXX9_WDT
 	tristate "Toshiba TXx9 Watchdog Timer"
 	depends on CPU_TX39XX || CPU_TX49XX
+	select WATCHDOG_CORE
 	help
 	  Hardware driver for the built-in watchdog timer on TXx9 MIPS SoCs.
 
diff --git a/drivers/watchdog/acquirewdt.c b/drivers/watchdog/acquirewdt.c
index b6a2b58cbe64..4397881c83f4 100644
--- a/drivers/watchdog/acquirewdt.c
+++ b/drivers/watchdog/acquirewdt.c
@@ -52,6 +52,8 @@
  *	Includes, defines, variables, module parameters, ...
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 /* Includes */
 #include <linux/module.h>		/* For module specific items */
 #include <linux/moduleparam.h>		/* For new moduleparam's */
@@ -70,7 +72,6 @@
 
 /* Module information */
 #define DRV_NAME "acquirewdt"
-#define PFX DRV_NAME ": "
 #define WATCHDOG_NAME "Acquire WDT"
 /* There is no way to see what the correct time-out period is */
 #define WATCHDOG_HEARTBEAT 0
@@ -92,8 +93,8 @@ static int wdt_start = 0x443;
 module_param(wdt_start, int, 0);
 MODULE_PARM_DESC(wdt_start, "Acquire WDT 'start' io port (default 0x443)");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 	__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -208,8 +209,7 @@ static int acq_close(struct inode *inode, struct file *file)
 	if (expect_close == 42) {
 		acq_stop();
 	} else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		acq_keepalive();
 	}
 	clear_bit(0, &acq_is_open);
@@ -246,27 +246,24 @@ static int __devinit acq_probe(struct platform_device *dev)
 
 	if (wdt_stop != wdt_start) {
 		if (!request_region(wdt_stop, 1, WATCHDOG_NAME)) {
-			printk(KERN_ERR PFX
-			    "I/O address 0x%04x already in use\n", wdt_stop);
+			pr_err("I/O address 0x%04x already in use\n", wdt_stop);
 			ret = -EIO;
 			goto out;
 		}
 	}
 
 	if (!request_region(wdt_start, 1, WATCHDOG_NAME)) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			wdt_start);
+		pr_err("I/O address 0x%04x already in use\n", wdt_start);
 		ret = -EIO;
 		goto unreg_stop;
 	}
 	ret = misc_register(&acq_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto unreg_regions;
 	}
-	printk(KERN_INFO PFX "initialized. (nowayout=%d)\n", nowayout);
+	pr_info("initialized. (nowayout=%d)\n", nowayout);
 
 	return 0;
 unreg_regions:
@@ -308,8 +305,7 @@ static int __init acq_init(void)
 {
 	int err;
 
-	printk(KERN_INFO
-	      "WDT driver for Acquire single board computer initialising.\n");
+	pr_info("WDT driver for Acquire single board computer initialising\n");
 
 	err = platform_driver_register(&acquirewdt_driver);
 	if (err)
@@ -332,7 +328,7 @@ static void __exit acq_exit(void)
 {
 	platform_device_unregister(acq_platform_device);
 	platform_driver_unregister(&acquirewdt_driver);
-	printk(KERN_INFO PFX "Watchdog Module Unloaded.\n");
+	pr_info("Watchdog Module Unloaded\n");
 }
 
 module_init(acq_init);
diff --git a/drivers/watchdog/advantechwdt.c b/drivers/watchdog/advantechwdt.c
index 4d40965d2c9f..64ae9e9fed94 100644
--- a/drivers/watchdog/advantechwdt.c
+++ b/drivers/watchdog/advantechwdt.c
@@ -28,6 +28,8 @@
  *	    add wdt_start and wdt_stop as parameters.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -40,10 +42,8 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 #define DRV_NAME "advantechwdt"
-#define PFX DRV_NAME ": "
 #define WATCHDOG_NAME "Advantech WDT"
 #define WATCHDOG_TIMEOUT 60		/* 60 sec default timeout */
 
@@ -77,8 +77,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. 1<= timeout <=63, default="
 		__MODULE_STRING(WATCHDOG_TIMEOUT) ".");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 		__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -207,8 +207,7 @@ static int advwdt_close(struct inode *inode, struct file *file)
 	if (adv_expect_close == 42) {
 		advwdt_disable();
 	} else {
-		printk(KERN_CRIT PFX
-				"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		advwdt_ping();
 	}
 	clear_bit(0, &advwdt_is_open);
@@ -245,18 +244,15 @@ static int __devinit advwdt_probe(struct platform_device *dev)
 
 	if (wdt_stop != wdt_start) {
 		if (!request_region(wdt_stop, 1, WATCHDOG_NAME)) {
-			printk(KERN_ERR PFX
-				"I/O address 0x%04x already in use\n",
-								wdt_stop);
+			pr_err("I/O address 0x%04x already in use\n",
+			       wdt_stop);
 			ret = -EIO;
 			goto out;
 		}
 	}
 
 	if (!request_region(wdt_start, 1, WATCHDOG_NAME)) {
-		printk(KERN_ERR PFX
-				"I/O address 0x%04x already in use\n",
-								wdt_start);
+		pr_err("I/O address 0x%04x already in use\n", wdt_start);
 		ret = -EIO;
 		goto unreg_stop;
 	}
@@ -265,18 +261,16 @@ static int __devinit advwdt_probe(struct platform_device *dev)
 	 * if not reset to the default */
 	if (advwdt_set_heartbeat(timeout)) {
 		advwdt_set_heartbeat(WATCHDOG_TIMEOUT);
-		printk(KERN_INFO PFX
-			"timeout value must be 1<=x<=63, using %d\n", timeout);
+		pr_info("timeout value must be 1<=x<=63, using %d\n", timeout);
 	}
 
 	ret = misc_register(&advwdt_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto unreg_regions;
 	}
-	printk(KERN_INFO PFX "initialized. timeout=%d sec (nowayout=%d)\n",
+	pr_info("initialized. timeout=%d sec (nowayout=%d)\n",
 		timeout, nowayout);
 out:
 	return ret;
@@ -318,8 +312,7 @@ static int __init advwdt_init(void)
 {
 	int err;
 
-	printk(KERN_INFO
-	     "WDT driver for Advantech single board computer initialising.\n");
+	pr_info("WDT driver for Advantech single board computer initialising\n");
 
 	err = platform_driver_register(&advwdt_driver);
 	if (err)
@@ -343,7 +336,7 @@ static void __exit advwdt_exit(void)
 {
 	platform_device_unregister(advwdt_platform_device);
 	platform_driver_unregister(&advwdt_driver);
-	printk(KERN_INFO PFX "Watchdog Module Unloaded.\n");
+	pr_info("Watchdog Module Unloaded\n");
 }
 
 module_init(advwdt_init);
diff --git a/drivers/watchdog/alim1535_wdt.c b/drivers/watchdog/alim1535_wdt.c
index f16dcbd475fb..41b84936a521 100644
--- a/drivers/watchdog/alim1535_wdt.c
+++ b/drivers/watchdog/alim1535_wdt.c
@@ -7,6 +7,8 @@
  *	2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -22,7 +24,6 @@
 #include <linux/io.h>
 
 #define WATCHDOG_NAME "ALi_M1535"
-#define PFX WATCHDOG_NAME ": "
 #define WATCHDOG_TIMEOUT 60	/* 60 sec default timeout */
 
 /* internal variables */
@@ -39,8 +40,8 @@ MODULE_PARM_DESC(timeout,
 		"Watchdog timeout in seconds. (0 < timeout < 18000, default="
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -268,8 +269,7 @@ static int ali_release(struct inode *inode, struct file *file)
 	if (ali_expect_release == 42)
 		ali_stop();
 	else {
-		printk(KERN_CRIT PFX
-				"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		ali_keepalive();
 	}
 	clear_bit(0, &ali_is_open);
@@ -399,9 +399,8 @@ static int __init watchdog_init(void)
 	   if not reset to the default */
 	if (timeout < 1 || timeout >= 18000) {
 		timeout = WATCHDOG_TIMEOUT;
-		printk(KERN_INFO PFX
-		     "timeout value must be 0 < timeout < 18000, using %d\n",
-							timeout);
+		pr_info("timeout value must be 0 < timeout < 18000, using %d\n",
+			timeout);
 	}
 
 	/* Calculate the watchdog's timeout */
@@ -409,20 +408,18 @@ static int __init watchdog_init(void)
 
 	ret = register_reboot_notifier(&ali_notifier);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto out;
 	}
 
 	ret = misc_register(&ali_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto unreg_reboot;
 	}
 
-	printk(KERN_INFO PFX "initialized. timeout=%d sec (nowayout=%d)\n",
+	pr_info("initialized. timeout=%d sec (nowayout=%d)\n",
 		timeout, nowayout);
 
 out:
diff --git a/drivers/watchdog/alim7101_wdt.c b/drivers/watchdog/alim7101_wdt.c
index 46f4b85b46de..5eee55012e33 100644
--- a/drivers/watchdog/alim7101_wdt.c
+++ b/drivers/watchdog/alim7101_wdt.c
@@ -19,6 +19,8 @@
  *                  -- Mike Waychison <michael.waychison@sun.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -34,10 +36,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
-
-#define OUR_NAME "alim7101_wdt"
-#define PFX OUR_NAME ": "
 
 #define WDT_ENABLE 0x9C
 #define WDT_DISABLE 0x8C
@@ -79,8 +77,8 @@ static unsigned long wdt_is_open;
 static char wdt_expect_close;
 static struct pci_dev *alim7101_pmu;
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -112,8 +110,7 @@ static void wdt_timer_ping(unsigned long data)
 					ALI_7101_GPIO_O, tmp & ~0x20);
 		}
 	} else {
-		printk(KERN_WARNING PFX
-			"Heartbeat lost! Will not ping the watchdog\n");
+		pr_warn("Heartbeat lost! Will not ping the watchdog\n");
 	}
 	/* Re-set the timer interval */
 	mod_timer(&timer, jiffies + WDT_INTERVAL);
@@ -162,7 +159,7 @@ static void wdt_startup(void)
 	/* Start the timer */
 	mod_timer(&timer, jiffies + WDT_INTERVAL);
 
-	printk(KERN_INFO PFX "Watchdog timer is now enabled.\n");
+	pr_info("Watchdog timer is now enabled\n");
 }
 
 static void wdt_turnoff(void)
@@ -170,7 +167,7 @@ static void wdt_turnoff(void)
 	/* Stop the timer */
 	del_timer_sync(&timer);
 	wdt_change(WDT_DISABLE);
-	printk(KERN_INFO PFX "Watchdog timer is now disabled...\n");
+	pr_info("Watchdog timer is now disabled...\n");
 }
 
 static void wdt_keepalive(void)
@@ -226,8 +223,7 @@ static int fop_close(struct inode *inode, struct file *file)
 		wdt_turnoff();
 	else {
 		/* wim: shouldn't there be a: del_timer(&timer); */
-		printk(KERN_CRIT PFX
-		  "device file closed unexpectedly. Will not stop the WDT!\n");
+		pr_crit("device file closed unexpectedly. Will not stop the WDT!\n");
 	}
 	clear_bit(0, &wdt_is_open);
 	wdt_expect_close = 0;
@@ -322,8 +318,7 @@ static int wdt_notify_sys(struct notifier_block *this,
 		 * watchdog on reboot with no heartbeat
 		 */
 		wdt_change(WDT_ENABLE);
-		printk(KERN_INFO PFX "Watchdog timer is now enabled "
-			"with no heartbeat - should reboot in ~1 second.\n");
+		pr_info("Watchdog timer is now enabled with no heartbeat - should reboot in ~1 second\n");
 	}
 	return NOTIFY_DONE;
 }
@@ -352,12 +347,11 @@ static int __init alim7101_wdt_init(void)
 	struct pci_dev *ali1543_south;
 	char tmp;
 
-	printk(KERN_INFO PFX "Steve Hill <steve@navaho.co.uk>.\n");
+	pr_info("Steve Hill <steve@navaho.co.uk>\n");
 	alim7101_pmu = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M7101,
 		NULL);
 	if (!alim7101_pmu) {
-		printk(KERN_INFO PFX
-			"ALi M7101 PMU not present - WDT not set\n");
+		pr_info("ALi M7101 PMU not present - WDT not set\n");
 		return -EBUSY;
 	}
 
@@ -367,56 +361,46 @@ static int __init alim7101_wdt_init(void)
 	ali1543_south = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533,
 		NULL);
 	if (!ali1543_south) {
-		printk(KERN_INFO PFX
-			"ALi 1543 South-Bridge not present - WDT not set\n");
+		pr_info("ALi 1543 South-Bridge not present - WDT not set\n");
 		goto err_out;
 	}
 	pci_read_config_byte(ali1543_south, 0x5e, &tmp);
 	pci_dev_put(ali1543_south);
 	if ((tmp & 0x1e) == 0x00) {
 		if (!use_gpio) {
-			printk(KERN_INFO PFX
-				"Detected old alim7101 revision 'a1d'.  "
-				"If this is a cobalt board, set the 'use_gpio' "
-				"module parameter.\n");
+			pr_info("Detected old alim7101 revision 'a1d'.  If this is a cobalt board, set the 'use_gpio' module parameter.\n");
 			goto err_out;
 		}
 		nowayout = 1;
 	} else if ((tmp & 0x1e) != 0x12 && (tmp & 0x1e) != 0x00) {
-		printk(KERN_INFO PFX
-			"ALi 1543 South-Bridge does not have the correct "
-			"revision number (???1001?) - WDT not set\n");
+		pr_info("ALi 1543 South-Bridge does not have the correct revision number (???1001?) - WDT not set\n");
 		goto err_out;
 	}
 
 	if (timeout < 1 || timeout > 3600) {
 		/* arbitrary upper limit */
 		timeout = WATCHDOG_TIMEOUT;
-		printk(KERN_INFO PFX
-			"timeout value must be 1 <= x <= 3600, using %d\n",
-								timeout);
+		pr_info("timeout value must be 1 <= x <= 3600, using %d\n",
+			timeout);
 	}
 
 	rc = register_reboot_notifier(&wdt_notifier);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", rc);
+		pr_err("cannot register reboot notifier (err=%d)\n", rc);
 		goto err_out;
 	}
 
 	rc = misc_register(&wdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-			wdt_miscdev.minor, rc);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       wdt_miscdev.minor, rc);
 		goto err_out_reboot;
 	}
 
 	if (nowayout)
 		__module_get(THIS_MODULE);
 
-	printk(KERN_INFO PFX "WDT driver for ALi M7101 initialised. "
-					"timeout=%d sec (nowayout=%d)\n",
+	pr_info("WDT driver for ALi M7101 initialised. timeout=%d sec (nowayout=%d)\n",
 		timeout, nowayout);
 	return 0;
 
diff --git a/drivers/watchdog/ar7_wdt.c b/drivers/watchdog/ar7_wdt.c
index 502773ad5acd..639ae9a23fbc 100644
--- a/drivers/watchdog/ar7_wdt.c
+++ b/drivers/watchdog/ar7_wdt.c
@@ -23,6 +23,8 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/errno.h>
@@ -39,7 +41,6 @@
 #include <asm/addrspace.h>
 #include <asm/mach-ar7/ar7.h>
 
-#define DRVNAME "ar7_wdt"
 #define LONGNAME "TI AR7 Watchdog Timer"
 
 MODULE_AUTHOR("Nicolas Thill <nico@openwrt.org>");
@@ -51,8 +52,8 @@ static int margin = 60;
 module_param(margin, int, 0);
 MODULE_PARM_DESC(margin, "Watchdog margin in seconds");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Disable watchdog shutdown on close");
 
 #define READ_REG(x) readl((void __iomem *)&(x))
@@ -93,7 +94,7 @@ static void ar7_wdt_kick(u32 value)
 			return;
 		}
 	}
-	printk(KERN_ERR DRVNAME ": failed to unlock WDT kick reg\n");
+	pr_err("failed to unlock WDT kick reg\n");
 }
 
 static void ar7_wdt_prescale(u32 value)
@@ -106,7 +107,7 @@ static void ar7_wdt_prescale(u32 value)
 			return;
 		}
 	}
-	printk(KERN_ERR DRVNAME ": failed to unlock WDT prescale reg\n");
+	pr_err("failed to unlock WDT prescale reg\n");
 }
 
 static void ar7_wdt_change(u32 value)
@@ -119,7 +120,7 @@ static void ar7_wdt_change(u32 value)
 			return;
 		}
 	}
-	printk(KERN_ERR DRVNAME ": failed to unlock WDT change reg\n");
+	pr_err("failed to unlock WDT change reg\n");
 }
 
 static void ar7_wdt_disable(u32 value)
@@ -135,7 +136,7 @@ static void ar7_wdt_disable(u32 value)
 			}
 		}
 	}
-	printk(KERN_ERR DRVNAME ": failed to unlock WDT disable reg\n");
+	pr_err("failed to unlock WDT disable reg\n");
 }
 
 static void ar7_wdt_update_margin(int new_margin)
@@ -151,21 +152,20 @@ static void ar7_wdt_update_margin(int new_margin)
 		change = 0xffff;
 	ar7_wdt_change(change);
 	margin = change * prescale_value / vbus_rate;
-	printk(KERN_INFO DRVNAME
-	       ": timer margin %d seconds (prescale %d, change %d, freq %d)\n",
-	       margin, prescale_value, change, vbus_rate);
+	pr_info("timer margin %d seconds (prescale %d, change %d, freq %d)\n",
+		margin, prescale_value, change, vbus_rate);
 }
 
 static void ar7_wdt_enable_wdt(void)
 {
-	printk(KERN_DEBUG DRVNAME ": enabling watchdog timer\n");
+	pr_debug("enabling watchdog timer\n");
 	ar7_wdt_disable(1);
 	ar7_wdt_kick(1);
 }
 
 static void ar7_wdt_disable_wdt(void)
 {
-	printk(KERN_DEBUG DRVNAME ": disabling watchdog timer\n");
+	pr_debug("disabling watchdog timer\n");
 	ar7_wdt_disable(0);
 }
 
@@ -183,9 +183,7 @@ static int ar7_wdt_open(struct inode *inode, struct file *file)
 static int ar7_wdt_release(struct inode *inode, struct file *file)
 {
 	if (!expect_close)
-		printk(KERN_WARNING DRVNAME
-		": watchdog device closed unexpectedly,"
-		"will not disable the watchdog timer\n");
+		pr_warn("watchdog device closed unexpectedly, will not disable the watchdog timer\n");
 	else if (!nowayout)
 		ar7_wdt_disable_wdt();
 	clear_bit(0, &wdt_is_open);
@@ -283,28 +281,28 @@ static int __devinit ar7_wdt_probe(struct platform_device *pdev)
 	ar7_regs_wdt =
 		platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
 	if (!ar7_regs_wdt) {
-		printk(KERN_ERR DRVNAME ": could not get registers resource\n");
+		pr_err("could not get registers resource\n");
 		rc = -ENODEV;
 		goto out;
 	}
 
 	if (!request_mem_region(ar7_regs_wdt->start,
 				resource_size(ar7_regs_wdt), LONGNAME)) {
-		printk(KERN_WARNING DRVNAME ": watchdog I/O region busy\n");
+		pr_warn("watchdog I/O region busy\n");
 		rc = -EBUSY;
 		goto out;
 	}
 
 	ar7_wdt = ioremap(ar7_regs_wdt->start, resource_size(ar7_regs_wdt));
 	if (!ar7_wdt) {
-		printk(KERN_ERR DRVNAME ": could not ioremap registers\n");
+		pr_err("could not ioremap registers\n");
 		rc = -ENXIO;
 		goto out_mem_region;
 	}
 
 	vbus_clk = clk_get(NULL, "vbus");
 	if (IS_ERR(vbus_clk)) {
-		printk(KERN_ERR DRVNAME ": could not get vbus clock\n");
+		pr_err("could not get vbus clock\n");
 		rc = PTR_ERR(vbus_clk);
 		goto out_mem_region;
 	}
@@ -315,7 +313,7 @@ static int __devinit ar7_wdt_probe(struct platform_device *pdev)
 
 	rc = misc_register(&ar7_wdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR DRVNAME ": unable to register misc device\n");
+		pr_err("unable to register misc device\n");
 		goto out_alloc;
 	}
 	goto out;
diff --git a/drivers/watchdog/at32ap700x_wdt.c b/drivers/watchdog/at32ap700x_wdt.c
index 4ca5d40304b2..2896430ce42c 100644
--- a/drivers/watchdog/at32ap700x_wdt.c
+++ b/drivers/watchdog/at32ap700x_wdt.c
@@ -45,8 +45,8 @@ MODULE_PARM_DESC(timeout,
 		"Timeout value. Limited to be 1 or 2 seconds. (default="
 		__MODULE_STRING(TIMEOUT_DEFAULT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 		__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
diff --git a/drivers/watchdog/at91rm9200_wdt.c b/drivers/watchdog/at91rm9200_wdt.c
index 7ceefd29ae14..7ef99a169e3b 100644
--- a/drivers/watchdog/at91rm9200_wdt.c
+++ b/drivers/watchdog/at91rm9200_wdt.c
@@ -9,6 +9,8 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -28,14 +30,14 @@
 #define WDT_MAX_TIME		256	/* seconds */
 
 static int wdt_time = WDT_DEFAULT_TIME;
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 module_param(wdt_time, int, 0);
 MODULE_PARM_DESC(wdt_time, "Watchdog time in seconds. (default="
 				__MODULE_STRING(WDT_DEFAULT_TIME) ")");
 
 #ifdef CONFIG_WATCHDOG_NOWAYOUT
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -209,8 +211,8 @@ static int __devinit at91wdt_probe(struct platform_device *pdev)
 	if (res)
 		return res;
 
-	printk(KERN_INFO "AT91 Watchdog Timer enabled (%d seconds%s)\n",
-				wdt_time, nowayout ? ", nowayout" : "");
+	pr_info("AT91 Watchdog Timer enabled (%d seconds%s)\n",
+		wdt_time, nowayout ? ", nowayout" : "");
 	return 0;
 }
 
@@ -268,8 +270,8 @@ static int __init at91_wdt_init(void)
 	   if not reset to the default */
 	if (at91_wdt_settimeout(wdt_time)) {
 		at91_wdt_settimeout(WDT_DEFAULT_TIME);
-		pr_info("at91_wdt: wdt_time value must be 1 <= wdt_time <= 256"
-						", using %d\n", wdt_time);
+		pr_info("wdt_time value must be 1 <= wdt_time <= 256, using %d\n",
+			wdt_time);
 	}
 
 	return platform_driver_register(&at91wdt_driver);
diff --git a/drivers/watchdog/at91sam9_wdt.c b/drivers/watchdog/at91sam9_wdt.c
index 00562566ef5f..05e1be85fdee 100644
--- a/drivers/watchdog/at91sam9_wdt.c
+++ b/drivers/watchdog/at91sam9_wdt.c
@@ -15,6 +15,8 @@
  * bootloader doesn't write to this register.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/init.h>
@@ -60,8 +62,8 @@ module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds. "
 	"(default = " __MODULE_STRING(WDT_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 	"(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -96,7 +98,7 @@ static void at91_ping(unsigned long data)
 		at91_wdt_reset();
 		mod_timer(&at91wdt_private.timer, jiffies + WDT_TIMEOUT);
 	} else
-		printk(KERN_CRIT DRV_NAME": I will reset your machine !\n");
+		pr_crit("I will reset your machine !\n");
 }
 
 /*
@@ -140,7 +142,7 @@ static int at91_wdt_settimeout(unsigned int timeout)
 	/* Check if disabled */
 	mr = wdt_read(AT91_WDT_MR);
 	if (mr & AT91_WDT_WDDIS) {
-		printk(KERN_ERR DRV_NAME": sorry, watchdog is disabled\n");
+		pr_err("sorry, watchdog is disabled\n");
 		return -EIO;
 	}
 
@@ -283,7 +285,7 @@ static int __init at91wdt_probe(struct platform_device *pdev)
 	setup_timer(&at91wdt_private.timer, at91_ping, 0);
 	mod_timer(&at91wdt_private.timer, jiffies + WDT_TIMEOUT);
 
-	printk(KERN_INFO DRV_NAME " enabled (heartbeat=%d sec, nowayout=%d)\n",
+	pr_info("enabled (heartbeat=%d sec, nowayout=%d)\n",
 		heartbeat, nowayout);
 
 	return 0;
diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c
index 9db808349f8b..1f9371f49c40 100644
--- a/drivers/watchdog/ath79_wdt.c
+++ b/drivers/watchdog/ath79_wdt.c
@@ -17,6 +17,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -45,8 +47,8 @@
 #define WDOG_CTRL_ACTION_NMI	2	/* NMI */
 #define WDOG_CTRL_ACTION_FCR	3	/* full chip reset */
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 			   "(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -114,8 +116,7 @@ static int ath79_wdt_release(struct inode *inode, struct file *file)
 	if (test_bit(WDT_FLAGS_EXPECT_CLOSE, &wdt_flags))
 		ath79_wdt_disable();
 	else {
-		pr_crit(DRIVER_NAME ": device closed unexpectedly, "
-			"watchdog timer will not stop!\n");
+		pr_crit("device closed unexpectedly, watchdog timer will not stop!\n");
 		ath79_wdt_keepalive();
 	}
 
diff --git a/drivers/watchdog/bcm47xx_wdt.c b/drivers/watchdog/bcm47xx_wdt.c
index 5c5f4b14fd05..bc0e91e78e86 100644
--- a/drivers/watchdog/bcm47xx_wdt.c
+++ b/drivers/watchdog/bcm47xx_wdt.c
@@ -10,6 +10,8 @@
  *  2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -33,14 +35,14 @@
 #define WDT_MAX_TIME		255	/* seconds */
 
 static int wdt_time = WDT_DEFAULT_TIME;
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 module_param(wdt_time, int, 0);
 MODULE_PARM_DESC(wdt_time, "Watchdog time in seconds. (default="
 				__MODULE_STRING(WDT_DEFAULT_TIME) ")");
 
 #ifdef CONFIG_WATCHDOG_NOWAYOUT
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -91,7 +93,7 @@ static void bcm47xx_timer_tick(unsigned long unused)
 		bcm47xx_wdt_hw_start();
 		mod_timer(&wdt_timer, jiffies + HZ);
 	} else {
-		printk(KERN_CRIT DRV_NAME "Watchdog will fire soon!!!\n");
+		pr_crit("Watchdog will fire soon!!!\n");
 	}
 }
 
@@ -140,8 +142,7 @@ static int bcm47xx_wdt_release(struct inode *inode, struct file *file)
 	if (expect_release == 42) {
 		bcm47xx_wdt_stop();
 	} else {
-		printk(KERN_CRIT DRV_NAME
-			": Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		bcm47xx_wdt_start();
 	}
 
@@ -270,8 +271,7 @@ static int __init bcm47xx_wdt_init(void)
 
 	if (bcm47xx_wdt_settimeout(wdt_time)) {
 		bcm47xx_wdt_settimeout(WDT_DEFAULT_TIME);
-		printk(KERN_INFO DRV_NAME ": "
-			"wdt_time value must be 0 < wdt_time < %d, using %d\n",
+		pr_info("wdt_time value must be 0 < wdt_time < %d, using %d\n",
 			(WDT_MAX_TIME + 1), wdt_time);
 	}
 
@@ -285,8 +285,8 @@ static int __init bcm47xx_wdt_init(void)
 		return ret;
 	}
 
-	printk(KERN_INFO "BCM47xx Watchdog Timer enabled (%d seconds%s)\n",
-				wdt_time, nowayout ? ", nowayout" : "");
+	pr_info("BCM47xx Watchdog Timer enabled (%d seconds%s)\n",
+		wdt_time, nowayout ? ", nowayout" : "");
 	return 0;
 }
 
diff --git a/drivers/watchdog/bcm63xx_wdt.c b/drivers/watchdog/bcm63xx_wdt.c
index 8dc7de641e26..8379dc32fd90 100644
--- a/drivers/watchdog/bcm63xx_wdt.c
+++ b/drivers/watchdog/bcm63xx_wdt.c
@@ -10,6 +10,8 @@
  *  2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -50,8 +52,8 @@ static struct {
 static int expect_close;
 
 static int wdt_time = WDT_DEFAULT_TIME;
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 	__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -82,7 +84,7 @@ static void bcm63xx_timer_tick(unsigned long unused)
 		bcm63xx_wdt_hw_start();
 		mod_timer(&bcm63xx_wdt_device.timer, jiffies + HZ);
 	} else
-		printk(KERN_CRIT PFX ": watchdog will restart system\n");
+		pr_crit("watchdog will restart system\n");
 }
 
 static void bcm63xx_wdt_pet(void)
@@ -126,8 +128,7 @@ static int bcm63xx_wdt_release(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		bcm63xx_wdt_pause();
 	else {
-		printk(KERN_CRIT PFX
-			": Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		bcm63xx_wdt_start();
 	}
 	clear_bit(0, &bcm63xx_wdt_device.inuse);
diff --git a/drivers/watchdog/bfin_wdt.c b/drivers/watchdog/bfin_wdt.c
index b9fa9b71583a..38bc383e0677 100644
--- a/drivers/watchdog/bfin_wdt.c
+++ b/drivers/watchdog/bfin_wdt.c
@@ -11,6 +11,8 @@
  * Licensed under the GPL-2 or later.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -28,15 +30,8 @@
 #define stamp(fmt, args...) \
 	pr_debug("%s:%i: " fmt "\n", __func__, __LINE__, ## args)
 #define stampit() stamp("here i am")
-#define pr_devinit(fmt, args...) \
-	({ static const __devinitconst char __fmt[] = fmt; \
-	printk(__fmt, ## args); })
-#define pr_init(fmt, args...) \
-	({ static const __initconst char __fmt[] = fmt; \
-	printk(__fmt, ## args); })
 
 #define WATCHDOG_NAME "bfin-wdt"
-#define PFX WATCHDOG_NAME ": "
 
 /* The BF561 has two watchdogs (one per core), but since Linux
  * only runs on core A, we'll just work with that one.
@@ -54,7 +49,7 @@
 #define WATCHDOG_TIMEOUT 20
 
 static unsigned int timeout = WATCHDOG_TIMEOUT;
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static const struct watchdog_info bfin_wdt_info;
 static unsigned long open_check;
 static char expect_close;
@@ -126,7 +121,7 @@ static int bfin_wdt_set_timeout(unsigned long t)
 	stamp("maxtimeout=%us newtimeout=%lus (cnt=%#x)", max_t, t, cnt);
 
 	if (t > max_t) {
-		printk(KERN_WARNING PFX "timeout value is too large\n");
+		pr_warn("timeout value is too large\n");
 		return -EINVAL;
 	}
 
@@ -182,8 +177,7 @@ static int bfin_wdt_release(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		bfin_wdt_stop();
 	else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		bfin_wdt_keepalive();
 	}
 	expect_close = 0;
@@ -368,14 +362,13 @@ static int __devinit bfin_wdt_probe(struct platform_device *pdev)
 
 	ret = misc_register(&bfin_wdt_miscdev);
 	if (ret) {
-		pr_devinit(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-				WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		return ret;
 	}
 
-	pr_devinit(KERN_INFO PFX "initialized: timeout=%d sec (nowayout=%d)\n",
-	       timeout, nowayout);
+	pr_info("initialized: timeout=%d sec (nowayout=%d)\n",
+		timeout, nowayout);
 
 	return 0;
 }
@@ -439,14 +432,14 @@ static int __init bfin_wdt_init(void)
 	 */
 	ret = platform_driver_register(&bfin_wdt_driver);
 	if (ret) {
-		pr_init(KERN_ERR PFX "unable to register driver\n");
+		pr_err("unable to register driver\n");
 		return ret;
 	}
 
 	bfin_wdt_device = platform_device_register_simple(WATCHDOG_NAME,
 								-1, NULL, 0);
 	if (IS_ERR(bfin_wdt_device)) {
-		pr_init(KERN_ERR PFX "unable to register device\n");
+		pr_err("unable to register device\n");
 		platform_driver_unregister(&bfin_wdt_driver);
 		return PTR_ERR(bfin_wdt_device);
 	}
@@ -479,7 +472,7 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. (1<=timeout<=((2^32)/SCLK), default="
 		__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 		__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c
index 7c0fdfca2646..ce0ab4415eff 100644
--- a/drivers/watchdog/booke_wdt.c
+++ b/drivers/watchdog/booke_wdt.c
@@ -12,6 +12,8 @@
  * option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/smp.h>
@@ -21,7 +23,6 @@
 #include <linux/uaccess.h>
 
 #include <asm/reg_booke.h>
-#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/div64.h>
 
@@ -225,8 +226,8 @@ static int booke_wdt_open(struct inode *inode, struct file *file)
 	if (booke_wdt_enabled == 0) {
 		booke_wdt_enabled = 1;
 		on_each_cpu(__booke_wdt_enable, NULL, 0);
-		pr_debug("booke_wdt: watchdog enabled (timeout = %llu sec)\n",
-			period_to_sec(booke_wdt_period));
+		pr_debug("watchdog enabled (timeout = %llu sec)\n",
+			 period_to_sec(booke_wdt_period));
 	}
 	spin_unlock(&booke_wdt_lock);
 
@@ -243,7 +244,7 @@ static int booke_wdt_release(struct inode *inode, struct file *file)
 	 */
 	on_each_cpu(__booke_wdt_disable, NULL, 0);
 	booke_wdt_enabled = 0;
-	pr_debug("booke_wdt: watchdog disabled\n");
+	pr_debug("watchdog disabled\n");
 #endif
 
 	clear_bit(0, &wdt_is_active);
@@ -275,19 +276,19 @@ static int __init booke_wdt_init(void)
 {
 	int ret = 0;
 
-	pr_info("booke_wdt: powerpc book-e watchdog driver loaded\n");
+	pr_info("powerpc book-e watchdog driver loaded\n");
 	ident.firmware_version = cur_cpu_spec->pvr_value;
 
 	ret = misc_register(&booke_wdt_miscdev);
 	if (ret) {
-		pr_err("booke_wdt: cannot register device (minor=%u, ret=%i)\n",
+		pr_err("cannot register device (minor=%u, ret=%i)\n",
 		       WATCHDOG_MINOR, ret);
 		return ret;
 	}
 
 	spin_lock(&booke_wdt_lock);
 	if (booke_wdt_enabled == 1) {
-		pr_info("booke_wdt: watchdog enabled (timeout = %llu sec)\n",
+		pr_info("watchdog enabled (timeout = %llu sec)\n",
 			period_to_sec(booke_wdt_period));
 		on_each_cpu(__booke_wdt_enable, NULL, 0);
 	}
diff --git a/drivers/watchdog/coh901327_wdt.c b/drivers/watchdog/coh901327_wdt.c
index 5b89f7d6cd0f..6876430a9f5e 100644
--- a/drivers/watchdog/coh901327_wdt.c
+++ b/drivers/watchdog/coh901327_wdt.c
@@ -8,17 +8,15 @@
  */
 #include <linux/module.h>
 #include <linux/types.h>
-#include <linux/fs.h>
-#include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/interrupt.h>
 #include <linux/pm.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/bitops.h>
-#include <linux/uaccess.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/err.h>
 
 #define DRV_NAME "WDOG COH 901 327"
 
@@ -69,13 +67,11 @@
 #define U300_WDOG_IFR_WILL_BARK_IRQ_FORCE_ENABLE			0x0001U
 
 /* Default timeout in seconds = 1 minute */
-static int margin = 60;
+static unsigned int margin = 60;
 static resource_size_t phybase;
 static resource_size_t physize;
 static int irq;
 static void __iomem *virtbase;
-static unsigned long coh901327_users;
-static unsigned long boot_status;
 static struct device *parent;
 
 /*
@@ -155,34 +151,35 @@ static void coh901327_disable(void)
 			__func__, val);
 }
 
-static void coh901327_start(void)
+static int coh901327_start(struct watchdog_device *wdt_dev)
 {
-	coh901327_enable(margin * 100);
+	coh901327_enable(wdt_dev->timeout * 100);
+	return 0;
+}
+
+static int coh901327_stop(struct watchdog_device *wdt_dev)
+{
+	coh901327_disable();
+	return 0;
 }
 
-static void coh901327_keepalive(void)
+static int coh901327_ping(struct watchdog_device *wdd)
 {
 	clk_enable(clk);
 	/* Feed the watchdog */
 	writew(U300_WDOG_FR_FEED_RESTART_TIMER,
 	       virtbase + U300_WDOG_FR);
 	clk_disable(clk);
+	return 0;
 }
 
-static int coh901327_settimeout(int time)
+static int coh901327_settimeout(struct watchdog_device *wdt_dev,
+				unsigned int time)
 {
-	/*
-	 * Max margin is 327 since the 10ms
-	 * timeout register is max
-	 * 0x7FFF = 327670ms ~= 327s.
-	 */
-	if (time <= 0 || time > 327)
-		return -EINVAL;
-
-	margin = time;
+	wdt_dev->timeout = time;
 	clk_enable(clk);
 	/* Set new timeout value */
-	writew(margin * 100, virtbase + U300_WDOG_TR);
+	writew(time * 100, virtbase + U300_WDOG_TR);
 	/* Feed the dog */
 	writew(U300_WDOG_FR_FEED_RESTART_TIMER,
 	       virtbase + U300_WDOG_FR);
@@ -190,6 +187,23 @@ static int coh901327_settimeout(int time)
 	return 0;
 }
 
+static unsigned int coh901327_gettimeleft(struct watchdog_device *wdt_dev)
+{
+	u16 val;
+
+	clk_enable(clk);
+	/* Read repeatedly until the value is stable! */
+	val = readw(virtbase + U300_WDOG_CR);
+	while (val & U300_WDOG_CR_VALID_IND)
+		val = readw(virtbase + U300_WDOG_CR);
+	val &= U300_WDOG_CR_COUNT_VALUE_MASK;
+	clk_disable(clk);
+	if (val != 0)
+		val /= 100;
+
+	return val;
+}
+
 /*
  * This interrupt occurs 10 ms before the watchdog WILL bark.
  */
@@ -218,130 +232,35 @@ static irqreturn_t coh901327_interrupt(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-/*
- * Allow only one user (daemon) to open the watchdog
- */
-static int coh901327_open(struct inode *inode, struct file *file)
-{
-	if (test_and_set_bit(1, &coh901327_users))
-		return -EBUSY;
-	coh901327_start();
-	return nonseekable_open(inode, file);
-}
-
-static int coh901327_release(struct inode *inode, struct file *file)
-{
-	clear_bit(1, &coh901327_users);
-	coh901327_disable();
-	return 0;
-}
-
-static ssize_t coh901327_write(struct file *file, const char __user *data,
-			       size_t len, loff_t *ppos)
-{
-	if (len)
-		coh901327_keepalive();
-	return len;
-}
-
-static long coh901327_ioctl(struct file *file, unsigned int cmd,
-			    unsigned long arg)
-{
-	int ret = -ENOTTY;
-	u16 val;
-	int time;
-	int new_options;
-	union {
-		struct watchdog_info __user *ident;
-		int __user *i;
-	} uarg;
-	static const struct watchdog_info ident = {
-		.options		= WDIOF_CARDRESET |
-					  WDIOF_SETTIMEOUT |
-					  WDIOF_KEEPALIVEPING,
-		.identity		= "COH 901 327 Watchdog",
-		.firmware_version	= 1,
-	};
-	uarg.i = (int __user *)arg;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		ret = copy_to_user(uarg.ident, &ident,
-				   sizeof(ident)) ? -EFAULT : 0;
-		break;
-
-	case WDIOC_GETSTATUS:
-		ret = put_user(0, uarg.i);
-		break;
-
-	case WDIOC_GETBOOTSTATUS:
-		ret = put_user(boot_status, uarg.i);
-		break;
-
-	case WDIOC_SETOPTIONS:
-		ret = get_user(new_options, uarg.i);
-		if (ret)
-			break;
-		if (new_options & WDIOS_DISABLECARD)
-			coh901327_disable();
-		if (new_options & WDIOS_ENABLECARD)
-			coh901327_start();
-		ret = 0;
-		break;
-
-	case WDIOC_KEEPALIVE:
-		coh901327_keepalive();
-		ret = 0;
-		break;
-
-	case WDIOC_SETTIMEOUT:
-		ret = get_user(time, uarg.i);
-		if (ret)
-			break;
-
-		ret = coh901327_settimeout(time);
-		if (ret)
-			break;
-		/* Then fall through to return set value */
-
-	case WDIOC_GETTIMEOUT:
-		ret = put_user(margin, uarg.i);
-		break;
-
-	case WDIOC_GETTIMELEFT:
-		clk_enable(clk);
-		/* Read repeatedly until the value is stable! */
-		val = readw(virtbase + U300_WDOG_CR);
-		while (val & U300_WDOG_CR_VALID_IND)
-			val = readw(virtbase + U300_WDOG_CR);
-		val &= U300_WDOG_CR_COUNT_VALUE_MASK;
-		clk_disable(clk);
-		if (val != 0)
-			val /= 100;
-		ret = put_user(val, uarg.i);
-		break;
-	}
-	return ret;
-}
+static const struct watchdog_info coh901327_ident = {
+	.options = WDIOF_CARDRESET | WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING,
+	.identity = DRV_NAME,
+};
 
-static const struct file_operations coh901327_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.write		= coh901327_write,
-	.unlocked_ioctl	= coh901327_ioctl,
-	.open		= coh901327_open,
-	.release	= coh901327_release,
+static struct watchdog_ops coh901327_ops = {
+	.owner = THIS_MODULE,
+	.start = coh901327_start,
+	.stop = coh901327_stop,
+	.ping = coh901327_ping,
+	.set_timeout = coh901327_settimeout,
+	.get_timeleft = coh901327_gettimeleft,
 };
 
-static struct miscdevice coh901327_miscdev = {
-	.minor		= WATCHDOG_MINOR,
-	.name		= "watchdog",
-	.fops		= &coh901327_fops,
+static struct watchdog_device coh901327_wdt = {
+	.info = &coh901327_ident,
+	.ops = &coh901327_ops,
+	/*
+	 * Max timeout is 327 since the 10ms
+	 * timeout register is max
+	 * 0x7FFF = 327670ms ~= 327s.
+	 */
+	.min_timeout = 0,
+	.max_timeout = 327,
 };
 
 static int __exit coh901327_remove(struct platform_device *pdev)
 {
-	misc_deregister(&coh901327_miscdev);
+	watchdog_unregister_device(&coh901327_wdt);
 	coh901327_disable();
 	free_irq(irq, pdev);
 	clk_put(clk);
@@ -350,7 +269,6 @@ static int __exit coh901327_remove(struct platform_device *pdev)
 	return 0;
 }
 
-
 static int __init coh901327_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -393,7 +311,7 @@ static int __init coh901327_probe(struct platform_device *pdev)
 	case U300_WDOG_SR_STATUS_TIMED_OUT:
 		dev_info(&pdev->dev,
 			"watchdog timed out since last chip reset!\n");
-		boot_status = WDIOF_CARDRESET;
+		coh901327_wdt.bootstatus |= WDIOF_CARDRESET;
 		/* Status will be cleared below */
 		break;
 	case U300_WDOG_SR_STATUS_NORMAL:
@@ -435,7 +353,11 @@ static int __init coh901327_probe(struct platform_device *pdev)
 
 	clk_disable(clk);
 
-	ret = misc_register(&coh901327_miscdev);
+	if (margin < 1 || margin > 327)
+		margin = 60;
+	coh901327_wdt.timeout = margin;
+
+	ret = watchdog_register_device(&coh901327_wdt);
 	if (ret == 0)
 		dev_info(&pdev->dev,
 			 "initialized. timer margin=%d sec\n", margin);
@@ -543,8 +465,8 @@ module_exit(coh901327_exit);
 MODULE_AUTHOR("Linus Walleij <linus.walleij@stericsson.com>");
 MODULE_DESCRIPTION("COH 901 327 Watchdog");
 
-module_param(margin, int, 0);
+module_param(margin, uint, 0);
 MODULE_PARM_DESC(margin, "Watchdog margin in seconds (default 60s)");
 
 MODULE_LICENSE("GPL");
-MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
+MODULE_ALIAS("platform:coh901327-watchdog");
diff --git a/drivers/watchdog/cpu5wdt.c b/drivers/watchdog/cpu5wdt.c
index 251c863d71dd..7e888393de1f 100644
--- a/drivers/watchdog/cpu5wdt.c
+++ b/drivers/watchdog/cpu5wdt.c
@@ -19,6 +19,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -71,7 +73,7 @@ static struct {
 static void cpu5wdt_trigger(unsigned long unused)
 {
 	if (verbose > 2)
-		printk(KERN_DEBUG PFX "trigger at %i ticks\n", ticks);
+		pr_debug("trigger at %i ticks\n", ticks);
 
 	if (cpu5wdt_device.running)
 		ticks--;
@@ -96,7 +98,7 @@ static void cpu5wdt_reset(void)
 	ticks = cpu5wdt_device.default_ticks;
 
 	if (verbose)
-		printk(KERN_DEBUG PFX "reset (%i ticks)\n", (int) ticks);
+		pr_debug("reset (%i ticks)\n", (int) ticks);
 
 }
 
@@ -129,7 +131,7 @@ static int cpu5wdt_stop(void)
 	ticks = cpu5wdt_device.default_ticks;
 	spin_unlock_irqrestore(&cpu5wdt_lock, flags);
 	if (verbose)
-		printk(KERN_CRIT PFX "stop not possible\n");
+		pr_crit("stop not possible\n");
 	return -EIO;
 }
 
@@ -219,8 +221,7 @@ static int __devinit cpu5wdt_init(void)
 	int err;
 
 	if (verbose)
-		printk(KERN_DEBUG PFX
-				"port=0x%x, verbose=%i\n", port, verbose);
+		pr_debug("port=0x%x, verbose=%i\n", port, verbose);
 
 	init_completion(&cpu5wdt_device.stop);
 	cpu5wdt_device.queue = 0;
@@ -228,7 +229,7 @@ static int __devinit cpu5wdt_init(void)
 	cpu5wdt_device.default_ticks = ticks;
 
 	if (!request_region(port, CPU5WDT_EXTENT, PFX)) {
-		printk(KERN_ERR PFX "request_region failed\n");
+		pr_err("request_region failed\n");
 		err = -EBUSY;
 		goto no_port;
 	}
@@ -237,16 +238,16 @@ static int __devinit cpu5wdt_init(void)
 	val = inb(port + CPU5WDT_STATUS_REG);
 	val = (val >> 2) & 1;
 	if (!val)
-		printk(KERN_INFO PFX "sorry, was my fault\n");
+		pr_info("sorry, was my fault\n");
 
 	err = misc_register(&cpu5wdt_misc);
 	if (err < 0) {
-		printk(KERN_ERR PFX "misc_register failed\n");
+		pr_err("misc_register failed\n");
 		goto no_misc;
 	}
 
 
-	printk(KERN_INFO PFX "init success\n");
+	pr_info("init success\n");
 	return 0;
 
 no_misc:
diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c
index 1b793dfd868f..95b1b954de1b 100644
--- a/drivers/watchdog/cpwd.c
+++ b/drivers/watchdog/cpwd.c
@@ -14,6 +14,8 @@
  * Copyright (C) 2008 David S. Miller <davem@davemloft.net>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/fs.h>
@@ -35,7 +37,6 @@
 #include <asm/watchdog.h>
 
 #define DRIVER_NAME	"cpwd"
-#define PFX		DRIVER_NAME ": "
 
 #define WD_OBPNAME	"watchdog"
 #define WD_BADMODEL	"SUNW,501-5336"
@@ -385,8 +386,7 @@ static int cpwd_open(struct inode *inode, struct file *f)
 	if (!p->initialized) {
 		if (request_irq(p->irq, &cpwd_interrupt,
 				IRQF_SHARED, DRIVER_NAME, p)) {
-			printk(KERN_ERR PFX "Cannot register IRQ %d\n",
-				p->irq);
+			pr_err("Cannot register IRQ %d\n", p->irq);
 			mutex_unlock(&cpwd_mutex);
 			return -EBUSY;
 		}
@@ -542,7 +542,7 @@ static int __devinit cpwd_probe(struct platform_device *op)
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	err = -ENOMEM;
 	if (!p) {
-		printk(KERN_ERR PFX "Unable to allocate struct cpwd.\n");
+		pr_err("Unable to allocate struct cpwd\n");
 		goto out;
 	}
 
@@ -553,14 +553,14 @@ static int __devinit cpwd_probe(struct platform_device *op)
 	p->regs = of_ioremap(&op->resource[0], 0,
 			     4 * WD_TIMER_REGSZ, DRIVER_NAME);
 	if (!p->regs) {
-		printk(KERN_ERR PFX "Unable to map registers.\n");
+		pr_err("Unable to map registers\n");
 		goto out_free;
 	}
 
 	options = of_find_node_by_path("/options");
 	err = -ENODEV;
 	if (!options) {
-		printk(KERN_ERR PFX "Unable to find /options node.\n");
+		pr_err("Unable to find /options node\n");
 		goto out_iounmap;
 	}
 
@@ -605,8 +605,8 @@ static int __devinit cpwd_probe(struct platform_device *op)
 
 		err = misc_register(&p->devs[i].misc);
 		if (err) {
-			printk(KERN_ERR "Could not register misc device for "
-			       "dev %d\n", i);
+			pr_err("Could not register misc device for dev %d\n",
+			       i);
 			goto out_unregister;
 		}
 	}
@@ -617,8 +617,8 @@ static int __devinit cpwd_probe(struct platform_device *op)
 		cpwd_timer.data		= (unsigned long) p;
 		cpwd_timer.expires	= WD_BTIMEOUT;
 
-		printk(KERN_INFO PFX "PLD defect workaround enabled for "
-		       "model " WD_BADMODEL ".\n");
+		pr_info("PLD defect workaround enabled for model %s\n",
+			WD_BADMODEL);
 	}
 
 	dev_set_drvdata(&op->dev, p);
diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index 63d7b58f1c7d..06de1211a444 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -16,7 +16,8 @@
  * If we receive an expected close for the watchdog then we keep the timer
  * running, otherwise the timer is stopped and the watchdog will expire.
  */
-#define pr_fmt(fmt) "dw_wdt: " fmt
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/bitops.h>
 #include <linux/clk.h>
@@ -45,8 +46,8 @@
 /* The maximum TOP (timeout period) value that can be set in the watchdog. */
 #define DW_WDT_MAX_TOP		15
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 		 "(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
diff --git a/drivers/watchdog/ep93xx_wdt.c b/drivers/watchdog/ep93xx_wdt.c
index 09cd888db619..77050037597a 100644
--- a/drivers/watchdog/ep93xx_wdt.c
+++ b/drivers/watchdog/ep93xx_wdt.c
@@ -8,6 +8,9 @@
  * Authors: Ray Lehtiniemi <rayl@mail.com>,
  *	Alessandro Zummo <a.zummo@towertech.it>
  *
+ * Copyright (c) 2012 H Hartley Sweeten <hsweeten@visionengravers.com>
+ *	Convert to a platform device and use the watchdog framework API
+ *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
@@ -25,187 +28,90 @@
 
 #include <linux/platform_device.h>
 #include <linux/module.h>
-#include <linux/fs.h>
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/timer.h>
-#include <linux/uaccess.h>
 #include <linux/io.h>
 
-#define WDT_VERSION	"0.3"
-#define PFX		"ep93xx_wdt: "
+#define WDT_VERSION	"0.4"
 
 /* default timeout (secs) */
 #define WDT_TIMEOUT 30
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-static int timeout = WDT_TIMEOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
+
+static unsigned int timeout = WDT_TIMEOUT;
+module_param(timeout, uint, 0);
+MODULE_PARM_DESC(timeout,
+	"Watchdog timeout in seconds. (1<=timeout<=3600, default="
+				__MODULE_STRING(WDT_TIMEOUT) ")");
 
 static void __iomem *mmio_base;
 static struct timer_list timer;
 static unsigned long next_heartbeat;
-static unsigned long wdt_status;
-static unsigned long boot_status;
-
-#define WDT_IN_USE		0
-#define WDT_OK_TO_CLOSE		1
 
 #define EP93XX_WATCHDOG		0x00
 #define EP93XX_WDSTATUS		0x04
 
-/* reset the wdt every ~200ms */
+/* reset the wdt every ~200ms - the heartbeat of the device is 0.250 seconds*/
 #define WDT_INTERVAL (HZ/5)
 
-static void wdt_enable(void)
+static void ep93xx_wdt_timer_ping(unsigned long data)
 {
-	writel(0xaaaa, mmio_base + EP93XX_WATCHDOG);
-}
-
-static void wdt_disable(void)
-{
-	writel(0xaa55, mmio_base + EP93XX_WATCHDOG);
-}
+	if (time_before(jiffies, next_heartbeat))
+		writel(0x5555, mmio_base + EP93XX_WATCHDOG);
 
-static inline void wdt_ping(void)
-{
-	writel(0x5555, mmio_base + EP93XX_WATCHDOG);
+	/* Re-set the timer interval */
+	mod_timer(&timer, jiffies + WDT_INTERVAL);
 }
 
-static void wdt_startup(void)
+static int ep93xx_wdt_start(struct watchdog_device *wdd)
 {
 	next_heartbeat = jiffies + (timeout * HZ);
 
-	wdt_enable();
+	writel(0xaaaa, mmio_base + EP93XX_WATCHDOG);
 	mod_timer(&timer, jiffies + WDT_INTERVAL);
+
+	return 0;
 }
 
-static void wdt_shutdown(void)
+static int ep93xx_wdt_stop(struct watchdog_device *wdd)
 {
 	del_timer_sync(&timer);
-	wdt_disable();
+	writel(0xaa55, mmio_base + EP93XX_WATCHDOG);
+
+	return 0;
 }
 
-static void wdt_keepalive(void)
+static int ep93xx_wdt_keepalive(struct watchdog_device *wdd)
 {
 	/* user land ping */
 	next_heartbeat = jiffies + (timeout * HZ);
-}
-
-static int ep93xx_wdt_open(struct inode *inode, struct file *file)
-{
-	if (test_and_set_bit(WDT_IN_USE, &wdt_status))
-		return -EBUSY;
-
-	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
-	wdt_startup();
-
-	return nonseekable_open(inode, file);
-}
-
-static ssize_t
-ep93xx_wdt_write(struct file *file, const char __user *data, size_t len,
-		 loff_t *ppos)
-{
-	if (len) {
-		if (!nowayout) {
-			size_t i;
-
-			clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
-			for (i = 0; i != len; i++) {
-				char c;
-
-				if (get_user(c, data + i))
-					return -EFAULT;
-
-				if (c == 'V')
-					set_bit(WDT_OK_TO_CLOSE, &wdt_status);
-				else
-					clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-			}
-		}
-		wdt_keepalive();
-	}
 
-	return len;
+	return 0;
 }
 
-static const struct watchdog_info ident = {
-	.options = WDIOF_CARDRESET | WDIOF_MAGICCLOSE,
-	.identity = "EP93xx Watchdog",
+static const struct watchdog_info ep93xx_wdt_ident = {
+	.options	= WDIOF_CARDRESET |
+			  WDIOF_MAGICCLOSE |
+			  WDIOF_KEEPALIVEPING,
+	.identity	= "EP93xx Watchdog",
 };
 
-static long ep93xx_wdt_ioctl(struct file *file,
-					unsigned int cmd, unsigned long arg)
-{
-	int ret = -ENOTTY;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		ret = copy_to_user((struct watchdog_info __user *)arg, &ident,
-				sizeof(ident)) ? -EFAULT : 0;
-		break;
-
-	case WDIOC_GETSTATUS:
-		ret = put_user(0, (int __user *)arg);
-		break;
-
-	case WDIOC_GETBOOTSTATUS:
-		ret = put_user(boot_status, (int __user *)arg);
-		break;
-
-	case WDIOC_KEEPALIVE:
-		wdt_keepalive();
-		ret = 0;
-		break;
-
-	case WDIOC_GETTIMEOUT:
-		/* actually, it is 0.250 seconds.... */
-		ret = put_user(1, (int __user *)arg);
-		break;
-	}
-	return ret;
-}
-
-static int ep93xx_wdt_release(struct inode *inode, struct file *file)
-{
-	if (test_bit(WDT_OK_TO_CLOSE, &wdt_status))
-		wdt_shutdown();
-	else
-		printk(KERN_CRIT PFX
-			"Device closed unexpectedly - timer will not stop\n");
-
-	clear_bit(WDT_IN_USE, &wdt_status);
-	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
-	return 0;
-}
-
-static const struct file_operations ep93xx_wdt_fops = {
+static struct watchdog_ops ep93xx_wdt_ops = {
 	.owner		= THIS_MODULE,
-	.write		= ep93xx_wdt_write,
-	.unlocked_ioctl	= ep93xx_wdt_ioctl,
-	.open		= ep93xx_wdt_open,
-	.release	= ep93xx_wdt_release,
-	.llseek		= no_llseek,
+	.start		= ep93xx_wdt_start,
+	.stop		= ep93xx_wdt_stop,
+	.ping		= ep93xx_wdt_keepalive,
 };
 
-static struct miscdevice ep93xx_wdt_miscdev = {
-	.minor		= WATCHDOG_MINOR,
-	.name		= "watchdog",
-	.fops		= &ep93xx_wdt_fops,
+static struct watchdog_device ep93xx_wdt_wdd = {
+	.info		= &ep93xx_wdt_ident,
+	.ops		= &ep93xx_wdt_ops,
 };
 
-static void ep93xx_timer_ping(unsigned long data)
-{
-	if (time_before(jiffies, next_heartbeat))
-		wdt_ping();
-
-	/* Re-set the timer interval */
-	mod_timer(&timer, jiffies + WDT_INTERVAL);
-}
-
 static int __devinit ep93xx_wdt_probe(struct platform_device *pdev)
 {
 	struct resource *res;
@@ -224,30 +130,35 @@ static int __devinit ep93xx_wdt_probe(struct platform_device *pdev)
 	if (!mmio_base)
 		return -ENXIO;
 
-	err = misc_register(&ep93xx_wdt_miscdev);
-
-	val = readl(mmio_base + EP93XX_WATCHDOG);
-	boot_status = val & 0x01 ? 1 : 0;
-
-	printk(KERN_INFO PFX "EP93XX watchdog, driver version "
-		WDT_VERSION "%s\n",
-		(val & 0x08) ? " (nCS1 disable detected)" : "");
-
 	if (timeout < 1 || timeout > 3600) {
 		timeout = WDT_TIMEOUT;
-		printk(KERN_INFO PFX
+		dev_warn(&pdev->dev,
 			"timeout value must be 1<=x<=3600, using %d\n",
 			timeout);
 	}
 
-	setup_timer(&timer, ep93xx_timer_ping, 1);
-	return err;
+	val = readl(mmio_base + EP93XX_WATCHDOG);
+	ep93xx_wdt_wdd.bootstatus = (val & 0x01) ? WDIOF_CARDRESET : 0;
+	ep93xx_wdt_wdd.timeout = timeout;
+
+	watchdog_set_nowayout(&ep93xx_wdt_wdd, nowayout);
+
+	setup_timer(&timer, ep93xx_wdt_timer_ping, 1);
+
+	err = watchdog_register_device(&ep93xx_wdt_wdd);
+	if (err)
+		return err;
+
+	dev_info(&pdev->dev,
+		"EP93XX watchdog, driver version " WDT_VERSION "%s\n",
+		(val & 0x08) ? " (nCS1 disable detected)" : "");
+
+	return 0;
 }
 
 static int __devexit ep93xx_wdt_remove(struct platform_device *pdev)
 {
-	wdt_shutdown();
-	misc_deregister(&ep93xx_wdt_miscdev);
+	watchdog_unregister_device(&ep93xx_wdt_wdd);
 	return 0;
 }
 
@@ -262,16 +173,9 @@ static struct platform_driver ep93xx_wdt_driver = {
 
 module_platform_driver(ep93xx_wdt_driver);
 
-module_param(nowayout, int, 0);
-MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
-
-module_param(timeout, int, 0);
-MODULE_PARM_DESC(timeout,
-	"Watchdog timeout in seconds. (1<=timeout<=3600, default="
-				__MODULE_STRING(WDT_TIMEOUT) ")");
-
 MODULE_AUTHOR("Ray Lehtiniemi <rayl@mail.com>,"
-		"Alessandro Zummo <a.zummo@towertech.it>");
+		"Alessandro Zummo <a.zummo@towertech.it>,"
+		"H Hartley Sweeten <hsweeten@visionengravers.com>");
 MODULE_DESCRIPTION("EP93xx Watchdog");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(WDT_VERSION);
diff --git a/drivers/watchdog/eurotechwdt.c b/drivers/watchdog/eurotechwdt.c
index 3946c51099c0..cd31b8a2a729 100644
--- a/drivers/watchdog/eurotechwdt.c
+++ b/drivers/watchdog/eurotechwdt.c
@@ -45,6 +45,8 @@
  *	of the on-board SUPER I/O device SMSC FDC 37B782.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -59,7 +61,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 static unsigned long eurwdt_is_open;
 static int eurwdt_timeout;
@@ -76,8 +77,8 @@ static char *ev = "int";
 
 #define WDT_TIMEOUT		60                /* 1 minute */
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -144,11 +145,11 @@ static void eurwdt_activate_timer(void)
 
 	/* Setting interrupt line */
 	if (irq == 2 || irq > 15 || irq < 0) {
-		printk(KERN_ERR ": invalid irq number\n");
+		pr_err("invalid irq number\n");
 		irq = 0;	/* if invalid we disable interrupt */
 	}
 	if (irq == 0)
-		printk(KERN_INFO ": interrupt disabled\n");
+		pr_info("interrupt disabled\n");
 
 	eurwdt_write_reg(WDT_TIMER_CFG, irq << 4);
 
@@ -163,12 +164,12 @@ static void eurwdt_activate_timer(void)
 
 static irqreturn_t eurwdt_interrupt(int irq, void *dev_id)
 {
-	printk(KERN_CRIT "timeout WDT timeout\n");
+	pr_crit("timeout WDT timeout\n");
 
 #ifdef ONLY_TESTING
-	printk(KERN_CRIT "Would Reboot.\n");
+	pr_crit("Would Reboot\n");
 #else
-	printk(KERN_CRIT "Initiating system reboot.\n");
+	pr_crit("Initiating system reboot\n");
 	emergency_restart();
 #endif
 	return IRQ_HANDLED;
@@ -335,8 +336,7 @@ static int eurwdt_release(struct inode *inode, struct file *file)
 	if (eur_expect_close == 42)
 		eurwdt_disable_timer();
 	else {
-		printk(KERN_CRIT
-			"eurwdt: Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		eurwdt_ping();
 	}
 	clear_bit(0, &eurwdt_is_open);
@@ -429,35 +429,32 @@ static int __init eurwdt_init(void)
 
 	ret = request_irq(irq, eurwdt_interrupt, 0, "eurwdt", NULL);
 	if (ret) {
-		printk(KERN_ERR "eurwdt: IRQ %d is not free.\n", irq);
+		pr_err("IRQ %d is not free\n", irq);
 		goto out;
 	}
 
 	if (!request_region(io, 2, "eurwdt")) {
-		printk(KERN_ERR "eurwdt: IO %X is not free.\n", io);
+		pr_err("IO %X is not free\n", io);
 		ret = -EBUSY;
 		goto outirq;
 	}
 
 	ret = register_reboot_notifier(&eurwdt_notifier);
 	if (ret) {
-		printk(KERN_ERR
-		    "eurwdt: can't register reboot notifier (err=%d)\n", ret);
+		pr_err("can't register reboot notifier (err=%d)\n", ret);
 		goto outreg;
 	}
 
 	ret = misc_register(&eurwdt_miscdev);
 	if (ret) {
-		printk(KERN_ERR "eurwdt: can't misc_register on minor=%d\n",
-		WATCHDOG_MINOR);
+		pr_err("can't misc_register on minor=%d\n", WATCHDOG_MINOR);
 		goto outreboot;
 	}
 
 	eurwdt_unlock_chip();
 
 	ret = 0;
-	printk(KERN_INFO "Eurotech WDT driver 0.01 at %X (Interrupt %d)"
-		" - timeout event: %s\n",
+	pr_info("Eurotech WDT driver 0.01 at %X (Interrupt %d) - timeout event: %s\n",
 		io, irq, (!strcmp("int", ev) ? "int" : "reboot"));
 
 out:
diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index e45ca2b4bfbe..c65b0a5a020c 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -19,6 +19,8 @@
  *   59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.             *
  ***************************************************************************/
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/err.h>
 #include <linux/fs.h>
 #include <linux/init.h>
@@ -189,8 +191,7 @@ static inline int superio_enter(int base)
 {
 	/* Don't step on other drivers' I/O space by accident */
 	if (!request_muxed_region(base, 2, DRVNAME)) {
-		printk(KERN_ERR DRVNAME ": I/O address 0x%04x already in use\n",
-				(int)base);
+		pr_err("I/O address 0x%04x already in use\n", (int)base);
 		return -EBUSY;
 	}
 
@@ -217,7 +218,7 @@ static int watchdog_set_timeout(int timeout)
 {
 	if (timeout <= 0
 	 || timeout >  max_timeout) {
-		printk(KERN_ERR DRVNAME ": watchdog timeout out of range\n");
+		pr_err("watchdog timeout out of range\n");
 		return -EINVAL;
 	}
 
@@ -252,7 +253,7 @@ static int watchdog_set_pulse_width(unsigned int pw)
 	} else if (pw <= 5000) {
 		watchdog.pulse_val = 3;
 	} else {
-		printk(KERN_ERR DRVNAME ": pulse width out of range\n");
+		pr_err("pulse width out of range\n");
 		err = -EINVAL;
 		goto exit_unlock;
 	}
@@ -309,8 +310,7 @@ static int f71862fg_pin_configure(unsigned short ioaddr)
 		if (ioaddr)
 			superio_set_bit(ioaddr, SIO_REG_MFUNCT1, 1);
 	} else {
-		printk(KERN_ERR DRVNAME ": Invalid argument f71862fg_pin=%d\n",
-				f71862fg_pin);
+		pr_err("Invalid argument f71862fg_pin=%d\n", f71862fg_pin);
 		return -EINVAL;
 	}
 	return 0;
@@ -487,8 +487,7 @@ static int watchdog_release(struct inode *inode, struct file *file)
 
 	if (!watchdog.expect_close) {
 		watchdog_keepalive();
-		printk(KERN_CRIT DRVNAME
-			": Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 	} else if (!nowayout) {
 		watchdog_stop();
 	}
@@ -672,25 +671,22 @@ static int __init watchdog_init(int sioaddr)
 
 	err = misc_register(&watchdog_miscdev);
 	if (err) {
-		printk(KERN_ERR DRVNAME
-			": cannot register miscdev on minor=%d\n",
-				watchdog_miscdev.minor);
+		pr_err("cannot register miscdev on minor=%d\n",
+		       watchdog_miscdev.minor);
 		goto exit_reboot;
 	}
 
 	if (start_withtimeout) {
 		if (start_withtimeout <= 0
 		 || start_withtimeout >  max_timeout) {
-			printk(KERN_ERR DRVNAME
-				": starting timeout out of range\n");
+			pr_err("starting timeout out of range\n");
 			err = -EINVAL;
 			goto exit_miscdev;
 		}
 
 		err = watchdog_start();
 		if (err) {
-			printk(KERN_ERR DRVNAME
-				": cannot start watchdog timer\n");
+			pr_err("cannot start watchdog timer\n");
 			goto exit_miscdev;
 		}
 
@@ -720,8 +716,7 @@ static int __init watchdog_init(int sioaddr)
 		if (nowayout)
 			__module_get(THIS_MODULE);
 
-		printk(KERN_INFO DRVNAME
-			": watchdog started with initial timeout of %u sec\n",
+		pr_info("watchdog started with initial timeout of %u sec\n",
 			start_withtimeout);
 	}
 
@@ -746,7 +741,7 @@ static int __init f71808e_find(int sioaddr)
 
 	devid = superio_inw(sioaddr, SIO_REG_MANID);
 	if (devid != SIO_FINTEK_ID) {
-		pr_debug(DRVNAME ": Not a Fintek device\n");
+		pr_debug("Not a Fintek device\n");
 		err = -ENODEV;
 		goto exit;
 	}
@@ -774,13 +769,13 @@ static int __init f71808e_find(int sioaddr)
 		err = -ENODEV;
 		goto exit;
 	default:
-		printk(KERN_INFO DRVNAME ": Unrecognized Fintek device: %04x\n",
-		       (unsigned int)devid);
+		pr_info("Unrecognized Fintek device: %04x\n",
+			(unsigned int)devid);
 		err = -ENODEV;
 		goto exit;
 	}
 
-	printk(KERN_INFO DRVNAME ": Found %s watchdog chip, revision %d\n",
+	pr_info("Found %s watchdog chip, revision %d\n",
 		f71808e_names[watchdog.type],
 		(int)superio_inb(sioaddr, SIO_REG_DEVREV));
 exit:
@@ -808,8 +803,7 @@ static int __init f71808e_init(void)
 static void __exit f71808e_exit(void)
 {
 	if (watchdog_is_running()) {
-		printk(KERN_WARNING DRVNAME
-			": Watchdog timer still running, stopping it\n");
+		pr_warn("Watchdog timer still running, stopping it\n");
 		watchdog_stop();
 	}
 	misc_deregister(&watchdog_miscdev);
diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c
index b146082bd85a..17f4cae770c6 100644
--- a/drivers/watchdog/gef_wdt.c
+++ b/drivers/watchdog/gef_wdt.c
@@ -24,6 +24,8 @@
  * capabilities) a kernel-based watchdog.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/compiler.h>
 #include <linux/init.h>
@@ -68,8 +70,8 @@ static unsigned int bus_clk;
 static char expect_close;
 static DEFINE_SPINLOCK(gef_wdt_spinlock);
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 	__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -110,7 +112,7 @@ static void gef_wdt_handler_enable(void)
 	if (gef_wdt_toggle_wdc(GEF_WDC_ENABLED_FALSE,
 				   GEF_WDC_ENABLE_SHIFT)) {
 		gef_wdt_service();
-		printk(KERN_NOTICE "gef_wdt: watchdog activated\n");
+		pr_notice("watchdog activated\n");
 	}
 }
 
@@ -118,7 +120,7 @@ static void gef_wdt_handler_disable(void)
 {
 	if (gef_wdt_toggle_wdc(GEF_WDC_ENABLED_TRUE,
 				   GEF_WDC_ENABLE_SHIFT))
-		printk(KERN_NOTICE "gef_wdt: watchdog deactivated\n");
+		pr_notice("watchdog deactivated\n");
 }
 
 static void gef_wdt_set_timeout(unsigned int timeout)
@@ -234,8 +236,7 @@ static int gef_wdt_release(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		gef_wdt_handler_disable();
 	else {
-		printk(KERN_CRIT
-		       "gef_wdt: unexpected close, not stopping timer!\n");
+		pr_crit("unexpected close, not stopping timer!\n");
 		gef_wdt_service();
 	}
 	expect_close = 0;
@@ -313,7 +314,7 @@ static struct platform_driver gef_wdt_driver = {
 
 static int __init gef_wdt_init(void)
 {
-	printk(KERN_INFO "GE watchdog driver\n");
+	pr_info("GE watchdog driver\n");
 	return platform_driver_register(&gef_wdt_driver);
 }
 
diff --git a/drivers/watchdog/geodewdt.c b/drivers/watchdog/geodewdt.c
index 9b49b125ad5a..dc563b680abd 100644
--- a/drivers/watchdog/geodewdt.c
+++ b/drivers/watchdog/geodewdt.c
@@ -9,6 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -39,8 +40,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. 1<= timeout <=131, default="
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ".");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -100,7 +101,7 @@ static int geodewdt_release(struct inode *inode, struct file *file)
 		geodewdt_disable();
 		module_put(THIS_MODULE);
 	} else {
-		printk(KERN_CRIT "Unexpected close - watchdog is not stopping.\n");
+		pr_crit("Unexpected close - watchdog is not stopping\n");
 		geodewdt_ping();
 
 		set_bit(WDT_FLAGS_ORPHAN, &wdt_flags);
@@ -220,7 +221,7 @@ static int __devinit geodewdt_probe(struct platform_device *dev)
 
 	wdt_timer = cs5535_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING);
 	if (!wdt_timer) {
-		printk(KERN_ERR "geodewdt:  No timers were available\n");
+		pr_err("No timers were available\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index 3c166d3f4e55..cbc7ceef2786 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -13,6 +13,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/device.h>
 #include <linux/fs.h>
 #include <linux/init.h>
@@ -45,7 +47,7 @@
 
 static unsigned int soft_margin = DEFAULT_MARGIN;	/* in seconds */
 static unsigned int reload;			/* the computed soft_margin */
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static char expect_release;
 static unsigned long hpwdt_is_open;
 
@@ -235,8 +237,7 @@ static int __devinit cru_detect(unsigned long map_entry,
 	asminline_call(&cmn_regs, bios32_entrypoint);
 
 	if (cmn_regs.u1.ral != 0) {
-		printk(KERN_WARNING
-			"hpwdt: Call succeeded but with an error: 0x%x\n",
+		pr_warn("Call succeeded but with an error: 0x%x\n",
 			cmn_regs.u1.ral);
 	} else {
 		physical_bios_base = cmn_regs.u2.rebx;
@@ -256,14 +257,10 @@ static int __devinit cru_detect(unsigned long map_entry,
 			}
 		}
 
-		printk(KERN_DEBUG "hpwdt: CRU Base Address:   0x%lx\n",
-			physical_bios_base);
-		printk(KERN_DEBUG "hpwdt: CRU Offset Address: 0x%lx\n",
-			physical_bios_offset);
-		printk(KERN_DEBUG "hpwdt: CRU Length:         0x%lx\n",
-			cru_length);
-		printk(KERN_DEBUG "hpwdt: CRU Mapped Address: %p\n",
-			&cru_rom_addr);
+		pr_debug("CRU Base Address:   0x%lx\n", physical_bios_base);
+		pr_debug("CRU Offset Address: 0x%lx\n", physical_bios_offset);
+		pr_debug("CRU Length:         0x%lx\n", cru_length);
+		pr_debug("CRU Mapped Address: %p\n", &cru_rom_addr);
 	}
 	iounmap(bios32_map);
 	return retval;
@@ -458,16 +455,13 @@ static void hpwdt_ping(void)
 static int hpwdt_change_timer(int new_margin)
 {
 	if (new_margin < 1 || new_margin > HPWDT_MAX_TIMER) {
-		printk(KERN_WARNING
-			"hpwdt: New value passed in is invalid: %d seconds.\n",
+		pr_warn("New value passed in is invalid: %d seconds\n",
 			new_margin);
 		return -EINVAL;
 	}
 
 	soft_margin = new_margin;
-	printk(KERN_DEBUG
-		"hpwdt: New timer passed in is %d seconds.\n",
-		new_margin);
+	pr_debug("New timer passed in is %d seconds\n", new_margin);
 	reload = SECS_TO_TICKS(soft_margin);
 
 	return 0;
@@ -535,8 +529,7 @@ static int hpwdt_release(struct inode *inode, struct file *file)
 	if (expect_release == 42) {
 		hpwdt_stop();
 	} else {
-		printk(KERN_CRIT
-			"hpwdt: Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		hpwdt_ping();
 	}
 
@@ -881,7 +874,7 @@ MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
 module_param(soft_margin, int, 0);
 MODULE_PARM_DESC(soft_margin, "Watchdog timeout in seconds");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 		__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
diff --git a/drivers/watchdog/i6300esb.c b/drivers/watchdog/i6300esb.c
index db45091ef434..738032a36bcf 100644
--- a/drivers/watchdog/i6300esb.c
+++ b/drivers/watchdog/i6300esb.c
@@ -27,6 +27,8 @@
  *      Includes, defines, variables, module parameters, ...
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -44,7 +46,6 @@
 #define ESB_VERSION "0.05"
 #define ESB_MODULE_NAME "i6300ESB timer"
 #define ESB_DRIVER_NAME ESB_MODULE_NAME ", v" ESB_VERSION
-#define PFX ESB_MODULE_NAME ": "
 
 /* PCI configuration registers */
 #define ESB_CONFIG_REG  0x60            /* Config register                   */
@@ -94,8 +95,8 @@ MODULE_PARM_DESC(heartbeat,
 		"Watchdog heartbeat in seconds. (1<heartbeat<2046, default="
 				__MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -213,8 +214,7 @@ static int esb_release(struct inode *inode, struct file *file)
 	if (esb_expect_close == 42)
 		esb_timer_stop();
 	else {
-		printk(KERN_CRIT PFX
-				"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		esb_timer_keepalive();
 	}
 	clear_bit(0, &timer_alive);
@@ -347,19 +347,19 @@ MODULE_DEVICE_TABLE(pci, esb_pci_tbl);
 static unsigned char __devinit esb_getdevice(struct pci_dev *pdev)
 {
 	if (pci_enable_device(pdev)) {
-		printk(KERN_ERR PFX "failed to enable device\n");
+		pr_err("failed to enable device\n");
 		goto err_devput;
 	}
 
 	if (pci_request_region(pdev, 0, ESB_MODULE_NAME)) {
-		printk(KERN_ERR PFX "failed to request region\n");
+		pr_err("failed to request region\n");
 		goto err_disable;
 	}
 
 	BASEADDR = pci_ioremap_bar(pdev, 0);
 	if (BASEADDR == NULL) {
 		/* Something's wrong here, BASEADDR has to be set */
-		printk(KERN_ERR PFX "failed to get BASEADDR\n");
+		pr_err("failed to get BASEADDR\n");
 		goto err_release;
 	}
 
@@ -397,7 +397,7 @@ static void __devinit esb_initdevice(void)
 	/* Check that the WDT isn't already locked */
 	pci_read_config_byte(esb_pci, ESB_LOCK_REG, &val1);
 	if (val1 & ESB_WDT_LOCK)
-		printk(KERN_WARNING PFX "nowayout already set\n");
+		pr_warn("nowayout already set\n");
 
 	/* Set the timer to watchdog mode and disable it for now */
 	pci_write_config_byte(esb_pci, ESB_LOCK_REG, 0x00);
@@ -423,11 +423,11 @@ static int __devinit esb_probe(struct pci_dev *pdev,
 
 	cards_found++;
 	if (cards_found == 1)
-		printk(KERN_INFO PFX "Intel 6300ESB WatchDog Timer Driver v%s\n",
+		pr_info("Intel 6300ESB WatchDog Timer Driver v%s\n",
 			ESB_VERSION);
 
 	if (cards_found > 1) {
-		printk(KERN_ERR PFX "This driver only supports 1 device\n");
+		pr_err("This driver only supports 1 device\n");
 		return -ENODEV;
 	}
 
@@ -439,9 +439,8 @@ static int __devinit esb_probe(struct pci_dev *pdev,
 	   if not reset to the default */
 	if (heartbeat < 0x1 || heartbeat > 2 * 0x03ff) {
 		heartbeat = WATCHDOG_HEARTBEAT;
-		printk(KERN_INFO PFX
-			"heartbeat value must be 1<heartbeat<2046, using %d\n",
-								heartbeat);
+		pr_info("heartbeat value must be 1<heartbeat<2046, using %d\n",
+			heartbeat);
 	}
 
 	/* Initialize the watchdog and make sure it does not run */
@@ -450,14 +449,12 @@ static int __devinit esb_probe(struct pci_dev *pdev,
 	/* Register the watchdog so that userspace has access to it */
 	ret = misc_register(&esb_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto err_unmap;
 	}
-	printk(KERN_INFO PFX
-		"initialized (0x%p). heartbeat=%d sec (nowayout=%d)\n",
-						BASEADDR, heartbeat, nowayout);
+	pr_info("initialized (0x%p). heartbeat=%d sec (nowayout=%d)\n",
+		BASEADDR, heartbeat, nowayout);
 	return 0;
 
 err_unmap:
@@ -503,7 +500,7 @@ static int __init watchdog_init(void)
 static void __exit watchdog_cleanup(void)
 {
 	pci_unregister_driver(&esb_driver);
-	printk(KERN_INFO PFX "Watchdog Module Unloaded.\n");
+	pr_info("Watchdog Module Unloaded\n");
 }
 
 module_init(watchdog_init);
diff --git a/drivers/watchdog/iTCO_vendor_support.c b/drivers/watchdog/iTCO_vendor_support.c
index 481d1ad43464..2721d29ce243 100644
--- a/drivers/watchdog/iTCO_vendor_support.c
+++ b/drivers/watchdog/iTCO_vendor_support.c
@@ -17,10 +17,11 @@
  *	Includes, defines, variables, module parameters, ...
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 /* Module and version information */
 #define DRV_NAME	"iTCO_vendor_support"
 #define DRV_VERSION	"1.04"
-#define PFX		DRV_NAME ": "
 
 /* Includes */
 #include <linux/module.h>		/* For module specific items */
@@ -355,13 +356,13 @@ EXPORT_SYMBOL(iTCO_vendor_check_noreboot_on);
 
 static int __init iTCO_vendor_init_module(void)
 {
-	printk(KERN_INFO PFX "vendor-support=%d\n", vendorsupport);
+	pr_info("vendor-support=%d\n", vendorsupport);
 	return 0;
 }
 
 static void __exit iTCO_vendor_exit_module(void)
 {
-	printk(KERN_INFO PFX "Module Unloaded\n");
+	pr_info("Module Unloaded\n");
 }
 
 module_init(iTCO_vendor_init_module);
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index bdf401b240b5..9fecb95645a3 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -43,10 +43,11 @@
  *	Includes, defines, variables, module parameters, ...
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 /* Module and version information */
 #define DRV_NAME	"iTCO_wdt"
 #define DRV_VERSION	"1.07"
-#define PFX		DRV_NAME ": "
 
 /* Includes */
 #include <linux/module.h>		/* For module specific items */
@@ -413,8 +414,8 @@ MODULE_PARM_DESC(heartbeat, "Watchdog timeout in seconds. "
 	"5..76 (TCO v1) or 3..614 (TCO v2), default="
 				__MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -489,8 +490,7 @@ static int iTCO_wdt_start(void)
 	/* disable chipset's NO_REBOOT bit */
 	if (iTCO_wdt_unset_NO_REBOOT_bit()) {
 		spin_unlock(&iTCO_wdt_private.io_lock);
-		printk(KERN_ERR PFX "failed to reset NO_REBOOT flag, "
-					"reboot disabled by hardware/BIOS\n");
+		pr_err("failed to reset NO_REBOOT flag, reboot disabled by hardware/BIOS\n");
 		return -EIO;
 	}
 
@@ -661,8 +661,7 @@ static int iTCO_wdt_release(struct inode *inode, struct file *file)
 	if (expect_release == 42) {
 		iTCO_wdt_stop();
 	} else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		iTCO_wdt_keepalive();
 	}
 	clear_bit(0, &is_active);
@@ -804,8 +803,7 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
 	base_address &= 0x0000ff80;
 	if (base_address == 0x00000000) {
 		/* Something's wrong here, ACPIBASE has to be set */
-		printk(KERN_ERR PFX "failed to get TCOBASE address, "
-					"device disabled by hardware/BIOS\n");
+		pr_err("failed to get TCOBASE address, device disabled by hardware/BIOS\n");
 		return -ENODEV;
 	}
 	iTCO_wdt_private.iTCO_version =
@@ -820,8 +818,7 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
 	if (iTCO_wdt_private.iTCO_version == 2) {
 		pci_read_config_dword(pdev, 0xf0, &base_address);
 		if ((base_address & 1) == 0) {
-			printk(KERN_ERR PFX "RCBA is disabled by hardware"
-						"/BIOS, device disabled\n");
+			pr_err("RCBA is disabled by hardware/BIOS, device disabled\n");
 			ret = -ENODEV;
 			goto out;
 		}
@@ -831,8 +828,7 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
 
 	/* Check chipset's NO_REBOOT bit */
 	if (iTCO_wdt_unset_NO_REBOOT_bit() && iTCO_vendor_check_noreboot_on()) {
-		printk(KERN_INFO PFX "unable to reset NO_REBOOT flag, "
-					"device disabled by hardware/BIOS\n");
+		pr_info("unable to reset NO_REBOOT flag, device disabled by hardware/BIOS\n");
 		ret = -ENODEV;	/* Cannot reset NO_REBOOT bit */
 		goto out_unmap;
 	}
@@ -842,9 +838,8 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
 
 	/* The TCO logic uses the TCO_EN bit in the SMI_EN register */
 	if (!request_region(SMI_EN, 4, "iTCO_wdt")) {
-		printk(KERN_ERR PFX
-			"I/O address 0x%04lx already in use, "
-						"device disabled\n", SMI_EN);
+		pr_err("I/O address 0x%04lx already in use, device disabled\n",
+		       SMI_EN);
 		ret = -EIO;
 		goto out_unmap;
 	}
@@ -858,17 +853,16 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
 	/* The TCO I/O registers reside in a 32-byte range pointed to
 	   by the TCOBASE value */
 	if (!request_region(TCOBASE, 0x20, "iTCO_wdt")) {
-		printk(KERN_ERR PFX "I/O address 0x%04lx already in use "
-						"device disabled\n", TCOBASE);
+		pr_err("I/O address 0x%04lx already in use, device disabled\n",
+		       TCOBASE);
 		ret = -EIO;
 		goto unreg_smi_en;
 	}
 
-	printk(KERN_INFO PFX
-		"Found a %s TCO device (Version=%d, TCOBASE=0x%04lx)\n",
-			iTCO_chipset_info[ent->driver_data].name,
-			iTCO_chipset_info[ent->driver_data].iTCO_version,
-			TCOBASE);
+	pr_info("Found a %s TCO device (Version=%d, TCOBASE=0x%04lx)\n",
+		iTCO_chipset_info[ent->driver_data].name,
+		iTCO_chipset_info[ent->driver_data].iTCO_version,
+		TCOBASE);
 
 	/* Clear out the (probably old) status */
 	outw(0x0008, TCO1_STS);	/* Clear the Time Out Status bit */
@@ -882,20 +876,18 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
 	   if not reset to the default */
 	if (iTCO_wdt_set_heartbeat(heartbeat)) {
 		iTCO_wdt_set_heartbeat(WATCHDOG_HEARTBEAT);
-		printk(KERN_INFO PFX
-			"timeout value out of range, using %d\n", heartbeat);
+		pr_info("timeout value out of range, using %d\n", heartbeat);
 	}
 
 	ret = misc_register(&iTCO_wdt_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto unreg_region;
 	}
 
-	printk(KERN_INFO PFX "initialized. heartbeat=%d sec (nowayout=%d)\n",
-							heartbeat, nowayout);
+	pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n",
+		heartbeat, nowayout);
 
 	return 0;
 
@@ -947,7 +939,7 @@ static int __devinit iTCO_wdt_probe(struct platform_device *dev)
 	}
 
 	if (!found)
-		printk(KERN_INFO PFX "No device detected.\n");
+		pr_info("No device detected\n");
 
 	return ret;
 }
@@ -979,8 +971,7 @@ static int __init iTCO_wdt_init_module(void)
 {
 	int err;
 
-	printk(KERN_INFO PFX "Intel TCO WatchDog Timer Driver v%s\n",
-		DRV_VERSION);
+	pr_info("Intel TCO WatchDog Timer Driver v%s\n", DRV_VERSION);
 
 	err = platform_driver_register(&iTCO_wdt_driver);
 	if (err)
@@ -1004,7 +995,7 @@ static void __exit iTCO_wdt_cleanup_module(void)
 {
 	platform_device_unregister(iTCO_wdt_platform_device);
 	platform_driver_unregister(&iTCO_wdt_driver);
-	printk(KERN_INFO PFX "Watchdog Module Unloaded.\n");
+	pr_info("Watchdog Module Unloaded\n");
 }
 
 module_init(iTCO_wdt_init_module);
diff --git a/drivers/watchdog/ib700wdt.c b/drivers/watchdog/ib700wdt.c
index 0149d8dfc81d..184c0bfc87a4 100644
--- a/drivers/watchdog/ib700wdt.c
+++ b/drivers/watchdog/ib700wdt.c
@@ -31,6 +31,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
@@ -44,7 +46,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 static struct platform_device *ibwdt_platform_device;
 static unsigned long ibwdt_is_open;
@@ -53,7 +54,6 @@ static char expect_close;
 
 /* Module information */
 #define DRV_NAME "ib700wdt"
-#define PFX DRV_NAME ": "
 
 /*
  *
@@ -102,8 +102,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. 0<= timeout <=30, default="
 		__MODULE_STRING(WATCHDOG_TIMEOUT) ".");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -246,8 +246,7 @@ static int ibwdt_close(struct inode *inode, struct file *file)
 	if (expect_close == 42) {
 		ibwdt_disable();
 	} else {
-		printk(KERN_CRIT PFX
-		     "WDT device closed unexpectedly.  WDT will not stop!\n");
+		pr_crit("WDT device closed unexpectedly.  WDT will not stop!\n");
 		ibwdt_ping();
 	}
 	clear_bit(0, &ibwdt_is_open);
@@ -284,16 +283,14 @@ static int __devinit ibwdt_probe(struct platform_device *dev)
 
 #if WDT_START != WDT_STOP
 	if (!request_region(WDT_STOP, 1, "IB700 WDT")) {
-		printk(KERN_ERR PFX "STOP method I/O %X is not available.\n",
-								WDT_STOP);
+		pr_err("STOP method I/O %X is not available\n", WDT_STOP);
 		res = -EIO;
 		goto out_nostopreg;
 	}
 #endif
 
 	if (!request_region(WDT_START, 1, "IB700 WDT")) {
-		printk(KERN_ERR PFX "START method I/O %X is not available.\n",
-								WDT_START);
+		pr_err("START method I/O %X is not available\n", WDT_START);
 		res = -EIO;
 		goto out_nostartreg;
 	}
@@ -302,13 +299,12 @@ static int __devinit ibwdt_probe(struct platform_device *dev)
 	 * if not reset to the default */
 	if (ibwdt_set_heartbeat(timeout)) {
 		ibwdt_set_heartbeat(WATCHDOG_TIMEOUT);
-		printk(KERN_INFO PFX
-			"timeout value must be 0<=x<=30, using %d\n", timeout);
+		pr_info("timeout value must be 0<=x<=30, using %d\n", timeout);
 	}
 
 	res = misc_register(&ibwdt_miscdev);
 	if (res) {
-		printk(KERN_ERR PFX "failed to register misc device\n");
+		pr_err("failed to register misc device\n");
 		goto out_nomisc;
 	}
 	return 0;
@@ -353,8 +349,7 @@ static int __init ibwdt_init(void)
 {
 	int err;
 
-	printk(KERN_INFO PFX
-		"WDT driver for IB700 single board computer initialising.\n");
+	pr_info("WDT driver for IB700 single board computer initialising\n");
 
 	err = platform_driver_register(&ibwdt_driver);
 	if (err)
@@ -378,7 +373,7 @@ static void __exit ibwdt_exit(void)
 {
 	platform_device_unregister(ibwdt_platform_device);
 	platform_driver_unregister(&ibwdt_driver);
-	printk(KERN_INFO PFX "Watchdog Module Unloaded.\n");
+	pr_info("Watchdog Module Unloaded\n");
 }
 
 module_init(ibwdt_init);
diff --git a/drivers/watchdog/ibmasr.c b/drivers/watchdog/ibmasr.c
index c7481ad51629..bc3fb8fe89ab 100644
--- a/drivers/watchdog/ibmasr.c
+++ b/drivers/watchdog/ibmasr.c
@@ -10,6 +10,8 @@
  * of the GNU Public License, incorporated herein by reference.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -31,8 +33,6 @@ enum {
 	ASMTYPE_SPRUCE,
 };
 
-#define PFX "ibmasr: "
-
 #define TOPAZ_ASR_REG_OFFSET	4
 #define TOPAZ_ASR_TOGGLE	0x40
 #define TOPAZ_ASR_DISABLE	0x80
@@ -60,7 +60,7 @@ enum {
 #define SPRUCE_ASR_TOGGLE_MASK	0x02	/* bit 0: 0, then 1, then 0 */
 
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 static unsigned long asr_is_open;
 static char asr_expect_close;
@@ -234,12 +234,11 @@ static int __init asr_get_base_address(void)
 	}
 
 	if (!request_region(asr_base, asr_length, "ibmasr")) {
-		printk(KERN_ERR PFX "address %#x already in use\n",
-			asr_base);
+		pr_err("address %#x already in use\n", asr_base);
 		return -EBUSY;
 	}
 
-	printk(KERN_INFO PFX "found %sASR @ addr %#x\n", type, asr_base);
+	pr_info("found %sASR @ addr %#x\n", type, asr_base);
 
 	return 0;
 }
@@ -332,8 +331,7 @@ static int asr_release(struct inode *inode, struct file *file)
 	if (asr_expect_close == 42)
 		asr_disable();
 	else {
-		printk(KERN_CRIT PFX
-				"unexpected close, not stopping watchdog!\n");
+		pr_crit("unexpected close, not stopping watchdog!\n");
 		asr_toggle();
 	}
 	clear_bit(0, &asr_is_open);
@@ -393,7 +391,7 @@ static int __init ibmasr_init(void)
 	rc = misc_register(&asr_miscdev);
 	if (rc < 0) {
 		release_region(asr_base, asr_length);
-		printk(KERN_ERR PFX "failed to register misc device\n");
+		pr_err("failed to register misc device\n");
 		return rc;
 	}
 
@@ -413,7 +411,7 @@ static void __exit ibmasr_exit(void)
 module_init(ibmasr_init);
 module_exit(ibmasr_exit);
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c
index c44c3334003a..7a2b734fcdc7 100644
--- a/drivers/watchdog/imx2_wdt.c
+++ b/drivers/watchdog/imx2_wdt.c
@@ -46,6 +46,9 @@
 #define IMX2_WDT_SEQ1		0x5555		/* -> service sequence 1 */
 #define IMX2_WDT_SEQ2		0xAAAA		/* -> service sequence 2 */
 
+#define IMX2_WDT_WRSR		0x04		/* Reset Status Register */
+#define IMX2_WDT_WRSR_TOUT	(1 << 1)	/* -> Reset due to Timeout */
+
 #define IMX2_WDT_MAX_TIME	128
 #define IMX2_WDT_DEFAULT_TIME	60		/* in seconds */
 
@@ -65,8 +68,8 @@ static struct {
 
 static struct miscdevice imx2_wdt_miscdev;
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -175,6 +178,7 @@ static long imx2_wdt_ioctl(struct file *file, unsigned int cmd,
 	void __user *argp = (void __user *)arg;
 	int __user *p = argp;
 	int new_value;
+	u16 val;
 
 	switch (cmd) {
 	case WDIOC_GETSUPPORT:
@@ -182,9 +186,13 @@ static long imx2_wdt_ioctl(struct file *file, unsigned int cmd,
 			sizeof(struct watchdog_info)) ? -EFAULT : 0;
 
 	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
 		return put_user(0, p);
 
+	case WDIOC_GETBOOTSTATUS:
+		val = __raw_readw(imx2_wdt.base + IMX2_WDT_WRSR);
+		new_value = val & IMX2_WDT_WRSR_TOUT ? WDIOF_CARDRESET : 0;
+		return put_user(new_value, p);
+
 	case WDIOC_KEEPALIVE:
 		imx2_wdt_ping();
 		return 0;
diff --git a/drivers/watchdog/indydog.c b/drivers/watchdog/indydog.c
index 1475e09f9af2..6d90f7a2ce22 100644
--- a/drivers/watchdog/indydog.c
+++ b/drivers/watchdog/indydog.c
@@ -12,6 +12,8 @@
  *	based on softdog.c by Alan Cox <alan@lxorguk.ukuu.org.uk>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -26,14 +28,13 @@
 #include <linux/uaccess.h>
 #include <asm/sgi/mc.h>
 
-#define PFX "indydog: "
 static unsigned long indydog_alive;
 static DEFINE_SPINLOCK(indydog_lock);
 
 #define WATCHDOG_TIMEOUT 30		/* 30 sec default timeout */
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -60,7 +61,7 @@ static void indydog_stop(void)
 	sgimc->cpuctrl0 = mc_ctrl0;
 	spin_unlock(&indydog_lock);
 
-	printk(KERN_INFO PFX "Stopped watchdog timer.\n");
+	pr_info("Stopped watchdog timer\n");
 }
 
 static void indydog_ping(void)
@@ -83,7 +84,7 @@ static int indydog_open(struct inode *inode, struct file *file)
 	indydog_start();
 	indydog_ping();
 
-	printk(KERN_INFO "Started watchdog timer.\n");
+	pr_info("Started watchdog timer\n");
 
 	return nonseekable_open(inode, file);
 }
@@ -178,30 +179,25 @@ static struct notifier_block indydog_notifier = {
 	.notifier_call = indydog_notify_sys,
 };
 
-static char banner[] __initdata =
-	KERN_INFO PFX "Hardware Watchdog Timer for SGI IP22: 0.3\n";
-
 static int __init watchdog_init(void)
 {
 	int ret;
 
 	ret = register_reboot_notifier(&indydog_notifier);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		return ret;
 	}
 
 	ret = misc_register(&indydog_miscdev);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		unregister_reboot_notifier(&indydog_notifier);
 		return ret;
 	}
 
-	printk(banner);
+	pr_info("Hardware Watchdog Timer for SGI IP22: 0.3\n");
 
 	return 0;
 }
diff --git a/drivers/watchdog/intel_scu_watchdog.c b/drivers/watchdog/intel_scu_watchdog.c
index 1abdc0454c54..9dda2d08af91 100644
--- a/drivers/watchdog/intel_scu_watchdog.c
+++ b/drivers/watchdog/intel_scu_watchdog.c
@@ -22,6 +22,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -96,15 +98,14 @@ static struct intel_scu_watchdog_dev watchdog_device;
 static void watchdog_fire(void)
 {
 	if (force_boot) {
-		printk(KERN_CRIT PFX "Initiating system reboot.\n");
+		pr_crit("Initiating system reboot\n");
 		emergency_restart();
-		printk(KERN_CRIT PFX "Reboot didn't ?????\n");
+		pr_crit("Reboot didn't ?????\n");
 	}
 
 	else {
-		printk(KERN_CRIT PFX "Immediate Reboot Disabled\n");
-		printk(KERN_CRIT PFX
-			"System will reset when watchdog timer times out!\n");
+		pr_crit("Immediate Reboot Disabled\n");
+		pr_crit("System will reset when watchdog timer times out!\n");
 	}
 }
 
@@ -112,8 +113,8 @@ static int check_timer_margin(int new_margin)
 {
 	if ((new_margin < MIN_TIME_CYCLE) ||
 	    (new_margin > MAX_TIME - timer_set)) {
-		pr_debug("Watchdog timer: value of new_margin %d is out of the range %d to %d\n",
-			  new_margin, MIN_TIME_CYCLE, MAX_TIME - timer_set);
+		pr_debug("value of new_margin %d is out of the range %d to %d\n",
+			 new_margin, MIN_TIME_CYCLE, MAX_TIME - timer_set);
 		return -EINVAL;
 	}
 	return 0;
@@ -156,14 +157,14 @@ static irqreturn_t watchdog_timer_interrupt(int irq, void *dev_id)
 	int int_status;
 	int_status = ioread32(watchdog_device.timer_interrupt_status_addr);
 
-	pr_debug("Watchdog timer: irq, int_status: %x\n", int_status);
+	pr_debug("irq, int_status: %x\n", int_status);
 
 	if (int_status != 0)
 		return IRQ_NONE;
 
 	/* has the timer been started? If not, then this is spurious */
 	if (watchdog_device.timer_started == 0) {
-		pr_debug("Watchdog timer: spurious interrupt received\n");
+		pr_debug("spurious interrupt received\n");
 		return IRQ_HANDLED;
 	}
 
@@ -220,16 +221,15 @@ static int intel_scu_set_heartbeat(u32 t)
 		(watchdog_device.timer_set - timer_margin)
 		* watchdog_device.timer_tbl_ptr->freq_hz;
 
-	pr_debug("Watchdog timer: set_heartbeat: timer freq is %d\n",
-		watchdog_device.timer_tbl_ptr->freq_hz);
-	pr_debug("Watchdog timer: set_heartbeat: timer_set is %x (hex)\n",
-		watchdog_device.timer_set);
-	pr_debug("Watchdog timer: set_hearbeat: timer_margin is %x (hex)\n",
-		timer_margin);
-	pr_debug("Watchdog timer: set_heartbeat: threshold is %x (hex)\n",
-		watchdog_device.threshold);
-	pr_debug("Watchdog timer: set_heartbeat: soft_threshold is %x (hex)\n",
-		watchdog_device.soft_threshold);
+	pr_debug("set_heartbeat: timer freq is %d\n",
+		 watchdog_device.timer_tbl_ptr->freq_hz);
+	pr_debug("set_heartbeat: timer_set is %x (hex)\n",
+		 watchdog_device.timer_set);
+	pr_debug("set_hearbeat: timer_margin is %x (hex)\n", timer_margin);
+	pr_debug("set_heartbeat: threshold is %x (hex)\n",
+		 watchdog_device.threshold);
+	pr_debug("set_heartbeat: soft_threshold is %x (hex)\n",
+		 watchdog_device.soft_threshold);
 
 	/* Adjust thresholds by FREQ_ADJUSTMENT factor, to make the */
 	/* watchdog timing come out right. */
@@ -264,7 +264,7 @@ static int intel_scu_set_heartbeat(u32 t)
 
 		if (MAX_RETRY < retry_count++) {
 			/* Unable to set timer value */
-			pr_err("Watchdog timer: Unable to set timer\n");
+			pr_err("Unable to set timer\n");
 			return -ENODEV;
 		}
 
@@ -321,18 +321,17 @@ static int intel_scu_release(struct inode *inode, struct file *file)
 	 */
 
 	if (!test_and_clear_bit(0, &watchdog_device.driver_open)) {
-		pr_debug("Watchdog timer: intel_scu_release, without open\n");
+		pr_debug("intel_scu_release, without open\n");
 		return -ENOTTY;
 	}
 
 	if (!watchdog_device.timer_started) {
 		/* Just close, since timer has not been started */
-		pr_debug("Watchdog timer: closed, without starting timer\n");
+		pr_debug("closed, without starting timer\n");
 		return 0;
 	}
 
-	printk(KERN_CRIT PFX
-	       "Unexpected close of /dev/watchdog!\n");
+	pr_crit("Unexpected close of /dev/watchdog!\n");
 
 	/* Since the timer was started, prevent future reopens */
 	watchdog_device.driver_closed = 1;
@@ -454,9 +453,8 @@ static int __init intel_scu_watchdog_init(void)
 	/* Check value of timer_set boot parameter */
 	if ((timer_set < MIN_TIME_CYCLE) ||
 	    (timer_set > MAX_TIME - MIN_TIME_CYCLE)) {
-		pr_err("Watchdog timer: value of timer_set %x (hex) "
-		  "is out of range from %x to %x (hex)\n",
-		  timer_set, MIN_TIME_CYCLE, MAX_TIME - MIN_TIME_CYCLE);
+		pr_err("value of timer_set %x (hex) is out of range from %x to %x (hex)\n",
+		       timer_set, MIN_TIME_CYCLE, MAX_TIME - MIN_TIME_CYCLE);
 		return -EINVAL;
 	}
 
@@ -467,19 +465,18 @@ static int __init intel_scu_watchdog_init(void)
 	watchdog_device.timer_tbl_ptr = sfi_get_mtmr(sfi_mtimer_num-1);
 
 	if (watchdog_device.timer_tbl_ptr == NULL) {
-		pr_debug("Watchdog timer - Intel SCU watchdog: timer is not available\n");
+		pr_debug("timer is not available\n");
 		return -ENODEV;
 	}
 	/* make sure the timer exists */
 	if (watchdog_device.timer_tbl_ptr->phys_addr == 0) {
-		pr_debug("Watchdog timer - Intel SCU watchdog - timer %d does not have valid physical memory\n",
-								sfi_mtimer_num);
+		pr_debug("timer %d does not have valid physical memory\n",
+			 sfi_mtimer_num);
 		return -ENODEV;
 	}
 
 	if (watchdog_device.timer_tbl_ptr->irq == 0) {
-		pr_debug("Watchdog timer: timer %d invalid irq\n",
-							sfi_mtimer_num);
+		pr_debug("timer %d invalid irq\n", sfi_mtimer_num);
 		return -ENODEV;
 	}
 
@@ -487,7 +484,7 @@ static int __init intel_scu_watchdog_init(void)
 			20);
 
 	if (tmp_addr == NULL) {
-		pr_debug("Watchdog timer: timer unable to ioremap\n");
+		pr_debug("timer unable to ioremap\n");
 		return -ENOMEM;
 	}
 
@@ -512,7 +509,7 @@ static int __init intel_scu_watchdog_init(void)
 
 	ret = register_reboot_notifier(&watchdog_device.intel_scu_notifier);
 	if (ret) {
-		pr_err("Watchdog timer: cannot register notifier %d)\n", ret);
+		pr_err("cannot register notifier %d)\n", ret);
 		goto register_reboot_error;
 	}
 
@@ -522,8 +519,8 @@ static int __init intel_scu_watchdog_init(void)
 
 	ret = misc_register(&watchdog_device.miscdev);
 	if (ret) {
-		pr_err("Watchdog timer: cannot register miscdev %d err =%d\n",
-							WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev %d err =%d\n",
+		       WATCHDOG_MINOR, ret);
 		goto misc_register_error;
 	}
 
@@ -532,7 +529,7 @@ static int __init intel_scu_watchdog_init(void)
 		IRQF_SHARED, "watchdog",
 		&watchdog_device.timer_load_count_addr);
 	if (ret) {
-		pr_err("Watchdog timer: error requesting irq %d\n", ret);
+		pr_err("error requesting irq %d\n", ret);
 		goto request_irq_error;
 	}
 	/* Make sure timer is disabled before returning */
diff --git a/drivers/watchdog/intel_scu_watchdog.h b/drivers/watchdog/intel_scu_watchdog.h
index d2b074a82db6..f3ac608deb6a 100644
--- a/drivers/watchdog/intel_scu_watchdog.h
+++ b/drivers/watchdog/intel_scu_watchdog.h
@@ -25,7 +25,6 @@
 #ifndef __INTEL_SCU_WATCHDOG_H
 #define __INTEL_SCU_WATCHDOG_H
 
-#define PFX "Intel_SCU: "
 #define WDT_VER "0.3"
 
 /* minimum time between interrupts */
diff --git a/drivers/watchdog/iop_wdt.c b/drivers/watchdog/iop_wdt.c
index 82fa7a92a8d2..d964faf1a250 100644
--- a/drivers/watchdog/iop_wdt.c
+++ b/drivers/watchdog/iop_wdt.c
@@ -24,6 +24,8 @@
  *	Dan Williams <dan.j.williams@intel.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
@@ -34,7 +36,7 @@
 #include <linux/uaccess.h>
 #include <mach/hardware.h>
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static unsigned long wdt_status;
 static unsigned long boot_status;
 static DEFINE_SPINLOCK(wdt_lock);
@@ -85,7 +87,7 @@ static int wdt_disable(void)
 		write_wdtcr(IOP_WDTCR_DIS);
 		clear_bit(WDT_ENABLED, &wdt_status);
 		spin_unlock(&wdt_lock);
-		printk(KERN_INFO "WATCHDOG: Disabled\n");
+		pr_info("Disabled\n");
 		return 0;
 	} else
 		return 1;
@@ -197,8 +199,8 @@ static int iop_wdt_release(struct inode *inode, struct file *file)
 	 */
 	if (state != 0) {
 		wdt_enable();
-		printk(KERN_CRIT "WATCHDOG: Device closed unexpectedly - "
-		       "reset in %lu seconds\n", iop_watchdog_timeout());
+		pr_crit("Device closed unexpectedly - reset in %lu seconds\n",
+			iop_watchdog_timeout());
 	}
 
 	clear_bit(WDT_IN_USE, &wdt_status);
@@ -238,8 +240,7 @@ static int __init iop_wdt_init(void)
 	   with an open */
 	ret = misc_register(&iop_wdt_miscdev);
 	if (ret == 0)
-		printk(KERN_INFO "iop watchdog timer: timeout %lu sec\n",
-		       iop_watchdog_timeout());
+		pr_info("timeout %lu sec\n", iop_watchdog_timeout());
 
 	return ret;
 }
@@ -252,7 +253,7 @@ static void __exit iop_wdt_exit(void)
 module_init(iop_wdt_init);
 module_exit(iop_wdt_exit);
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
 
 MODULE_AUTHOR("Curt E Bruns <curt.e.bruns@intel.com>");
diff --git a/drivers/watchdog/it8712f_wdt.c b/drivers/watchdog/it8712f_wdt.c
index 8d2d8502d3e8..f4cce6d66a55 100644
--- a/drivers/watchdog/it8712f_wdt.c
+++ b/drivers/watchdog/it8712f_wdt.c
@@ -20,6 +20,8 @@
  *	software is provided AS-IS with no warranties.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
@@ -33,6 +35,7 @@
 #include <linux/io.h>
 #include <linux/ioport.h>
 
+#define DEBUG
 #define NAME "it8712f_wdt"
 
 MODULE_AUTHOR("Jorge Boncompte - DTI2 <jorge@dti2.net>");
@@ -45,8 +48,8 @@ static int margin = 60;		/* in seconds */
 module_param(margin, int, 0);
 MODULE_PARM_DESC(margin, "Watchdog margin in seconds");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Disable watchdog shutdown on close");
 
 static unsigned long wdt_open;
@@ -158,10 +161,10 @@ static void it8712f_wdt_update_margin(void)
 	 */
 	if (units <= max_units) {
 		config |= WDT_UNIT_SEC; /* else UNIT is MINUTES */
-		printk(KERN_INFO NAME ": timer margin %d seconds\n", units);
+		pr_info("timer margin %d seconds\n", units);
 	} else {
 		units /= 60;
-		printk(KERN_INFO NAME ": timer margin %d minutes\n", units);
+		pr_info("timer margin %d minutes\n", units);
 	}
 	superio_outb(config, WDT_CONFIG);
 
@@ -184,7 +187,7 @@ static int it8712f_wdt_enable(void)
 	if (ret)
 		return ret;
 
-	printk(KERN_DEBUG NAME ": enabling watchdog timer\n");
+	pr_debug("enabling watchdog timer\n");
 	superio_select(LDN_GPIO);
 
 	superio_outb(wdt_control_reg, WDT_CONTROL);
@@ -204,7 +207,7 @@ static int it8712f_wdt_disable(void)
 	if (ret)
 		return ret;
 
-	printk(KERN_DEBUG NAME ": disabling watchdog timer\n");
+	pr_debug("disabling watchdog timer\n");
 	superio_select(LDN_GPIO);
 
 	superio_outb(0, WDT_CONFIG);
@@ -331,12 +334,10 @@ static int it8712f_wdt_open(struct inode *inode, struct file *file)
 static int it8712f_wdt_release(struct inode *inode, struct file *file)
 {
 	if (expect_close != 42) {
-		printk(KERN_WARNING NAME
-			": watchdog device closed unexpectedly, will not"
-			" disable the watchdog timer\n");
+		pr_warn("watchdog device closed unexpectedly, will not disable the watchdog timer\n");
 	} else if (!nowayout) {
 		if (it8712f_wdt_disable())
-			printk(KERN_WARNING NAME "Watchdog disable failed\n");
+			pr_warn("Watchdog disable failed\n");
 	}
 	expect_close = 0;
 	clear_bit(0, &wdt_open);
@@ -374,13 +375,13 @@ static int __init it8712f_wdt_find(unsigned short *address)
 	superio_select(LDN_GAME);
 	superio_outb(1, ACT_REG);
 	if (!(superio_inb(ACT_REG) & 0x01)) {
-		printk(KERN_ERR NAME ": Device not activated, skipping\n");
+		pr_err("Device not activated, skipping\n");
 		goto exit;
 	}
 
 	*address = superio_inw(BASE_REG);
 	if (*address == 0) {
-		printk(KERN_ERR NAME ": Base address not set, skipping\n");
+		pr_err("Base address not set, skipping\n");
 		goto exit;
 	}
 
@@ -394,8 +395,7 @@ static int __init it8712f_wdt_find(unsigned short *address)
 	if (margin > (max_units * 60))
 		margin = (max_units * 60);
 
-	printk(KERN_INFO NAME ": Found IT%04xF chip revision %d - "
-		"using DogFood address 0x%x\n",
+	pr_info("Found IT%04xF chip revision %d - using DogFood address 0x%x\n",
 		chip_type, revision, *address);
 
 exit:
@@ -411,27 +411,26 @@ static int __init it8712f_wdt_init(void)
 		return -ENODEV;
 
 	if (!request_region(address, 1, "IT8712F Watchdog")) {
-		printk(KERN_WARNING NAME ": watchdog I/O region busy\n");
+		pr_warn("watchdog I/O region busy\n");
 		return -EBUSY;
 	}
 
 	err = it8712f_wdt_disable();
 	if (err) {
-		printk(KERN_ERR NAME ": unable to disable watchdog timer.\n");
+		pr_err("unable to disable watchdog timer\n");
 		goto out;
 	}
 
 	err = register_reboot_notifier(&it8712f_wdt_notifier);
 	if (err) {
-		printk(KERN_ERR NAME ": unable to register reboot notifier\n");
+		pr_err("unable to register reboot notifier\n");
 		goto out;
 	}
 
 	err = misc_register(&it8712f_wdt_miscdev);
 	if (err) {
-		printk(KERN_ERR NAME
-			": cannot register miscdev on minor=%d (err=%d)\n",
-			WATCHDOG_MINOR, err);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, err);
 		goto reboot_out;
 	}
 
diff --git a/drivers/watchdog/it87_wdt.c b/drivers/watchdog/it87_wdt.c
index a2d9a1266a23..8a741bcb5124 100644
--- a/drivers/watchdog/it87_wdt.c
+++ b/drivers/watchdog/it87_wdt.c
@@ -29,6 +29,8 @@
  *	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -43,11 +45,9 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 
 #define WATCHDOG_VERSION	"1.14"
 #define WATCHDOG_NAME		"IT87 WDT"
-#define PFX			WATCHDOG_NAME ": "
 #define DRIVER_VERSION		WATCHDOG_NAME " driver, v" WATCHDOG_VERSION "\n"
 #define WD_MAGIC		'V'
 
@@ -142,7 +142,7 @@ static	int nogameport = DEFAULT_NOGAMEPORT;
 static	int exclusive  = DEFAULT_EXCLUSIVE;
 static	int timeout    = DEFAULT_TIMEOUT;
 static	int testmode   = DEFAULT_TESTMODE;
-static	int nowayout   = DEFAULT_NOWAYOUT;
+static	bool nowayout   = DEFAULT_NOWAYOUT;
 
 module_param(nogameport, int, 0);
 MODULE_PARM_DESC(nogameport, "Forbid the activation of game port, default="
@@ -156,7 +156,7 @@ MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds, default="
 module_param(testmode, int, 0);
 MODULE_PARM_DESC(testmode, "Watchdog test mode (1 = no reboot), default="
 		__MODULE_STRING(DEFAULT_TESTMODE));
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started, default="
 		__MODULE_STRING(WATCHDOG_NOWAYOUT));
 
@@ -428,8 +428,7 @@ static int wdt_release(struct inode *inode, struct file *file)
 			clear_bit(WDTS_TIMER_RUN, &wdt_status);
 		} else {
 			wdt_keepalive();
-			printk(KERN_CRIT PFX
-			       "unexpected close, not stopping watchdog!\n");
+			pr_crit("unexpected close, not stopping watchdog!\n");
 		}
 	}
 	clear_bit(WDTS_DEV_OPEN, &wdt_status);
@@ -621,16 +620,14 @@ static int __init it87_wdt_init(void)
 		try_gameport = 0;
 		break;
 	case IT8705_ID:
-		printk(KERN_ERR PFX
-		       "Unsupported Chip found, Chip %04x Revision %02x\n",
+		pr_err("Unsupported Chip found, Chip %04x Revision %02x\n",
 		       chip_type, chip_rev);
 		return -ENODEV;
 	case NO_DEV_ID:
-		printk(KERN_ERR PFX "no device\n");
+		pr_err("no device\n");
 		return -ENODEV;
 	default:
-		printk(KERN_ERR PFX
-		       "Unknown Chip found, Chip %04x Revision %04x\n",
+		pr_err("Unknown Chip found, Chip %04x Revision %04x\n",
 		       chip_type, chip_rev);
 		return -ENODEV;
 	}
@@ -663,13 +660,11 @@ static int __init it87_wdt_init(void)
 	if (!test_bit(WDTS_USE_GP, &wdt_status)) {
 		if (!request_region(CIR_BASE, 8, WATCHDOG_NAME)) {
 			if (gp_rreq_fail)
-				printk(KERN_ERR PFX
-					"I/O Address 0x%04x and 0x%04x"
-					" already in use\n", base, CIR_BASE);
+				pr_err("I/O Address 0x%04x and 0x%04x already in use\n",
+				       base, CIR_BASE);
 			else
-				printk(KERN_ERR PFX
-					"I/O Address 0x%04x already in use\n",
-					CIR_BASE);
+				pr_err("I/O Address 0x%04x already in use\n",
+				       CIR_BASE);
 			rc = -EIO;
 			goto err_out;
 		}
@@ -688,9 +683,8 @@ static int __init it87_wdt_init(void)
 
 	if (timeout < 1 || timeout > max_units * 60) {
 		timeout = DEFAULT_TIMEOUT;
-		printk(KERN_WARNING PFX
-		       "Timeout value out of range, use default %d sec\n",
-		       DEFAULT_TIMEOUT);
+		pr_warn("Timeout value out of range, use default %d sec\n",
+			DEFAULT_TIMEOUT);
 	}
 
 	if (timeout > max_units)
@@ -698,16 +692,14 @@ static int __init it87_wdt_init(void)
 
 	rc = register_reboot_notifier(&wdt_notifier);
 	if (rc) {
-		printk(KERN_ERR PFX
-		       "Cannot register reboot notifier (err=%d)\n", rc);
+		pr_err("Cannot register reboot notifier (err=%d)\n", rc);
 		goto err_out_region;
 	}
 
 	rc = misc_register(&wdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR PFX
-		       "Cannot register miscdev on minor=%d (err=%d)\n",
-			wdt_miscdev.minor, rc);
+		pr_err("Cannot register miscdev on minor=%d (err=%d)\n",
+		       wdt_miscdev.minor, rc);
 		goto err_out_reboot;
 	}
 
@@ -722,9 +714,8 @@ static int __init it87_wdt_init(void)
 		outb(0x09, CIR_IER(base));
 	}
 
-	printk(KERN_INFO PFX "Chip IT%04x revision %d initialized. "
-		"timeout=%d sec (nowayout=%d testmode=%d exclusive=%d "
-		"nogameport=%d)\n", chip_type, chip_rev, timeout,
+	pr_info("Chip IT%04x revision %d initialized. timeout=%d sec (nowayout=%d testmode=%d exclusive=%d nogameport=%d)\n",
+		chip_type, chip_rev, timeout,
 		nowayout, testmode, exclusive, nogameport);
 
 	superio_exit();
diff --git a/drivers/watchdog/ixp2000_wdt.c b/drivers/watchdog/ixp2000_wdt.c
index 084f71aa855a..3f047a58d3ae 100644
--- a/drivers/watchdog/ixp2000_wdt.c
+++ b/drivers/watchdog/ixp2000_wdt.c
@@ -16,6 +16,8 @@
  * warranty of any kind, whether express or implied.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -29,7 +31,7 @@
 #include <linux/uaccess.h>
 #include <mach/hardware.h>
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static unsigned int heartbeat = 60;	/* (secs) Default is 1 minute */
 static unsigned long wdt_status;
 static DEFINE_SPINLOCK(wdt_lock);
@@ -158,8 +160,7 @@ static int ixp2000_wdt_release(struct inode *inode, struct file *file)
 	if (test_bit(WDT_OK_TO_CLOSE, &wdt_status))
 		wdt_disable();
 	else
-		printk(KERN_CRIT "WATCHDOG: Device closed unexpectedly - "
-					"timer will not stop\n");
+		pr_crit("Device closed unexpectedly - timer will not stop\n");
 	clear_bit(WDT_IN_USE, &wdt_status);
 	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
 
@@ -185,7 +186,7 @@ static struct miscdevice ixp2000_wdt_miscdev = {
 static int __init ixp2000_wdt_init(void)
 {
 	if ((*IXP2000_PRODUCT_ID & 0x001ffef0) == 0x00000000) {
-		printk(KERN_INFO "Unable to use IXP2000 watchdog due to IXP2800 erratum #25.\n");
+		pr_info("Unable to use IXP2000 watchdog due to IXP2800 erratum #25\n");
 		return -EIO;
 	}
 	wdt_tick_rate = (*IXP2000_T1_CLD * HZ) / 256;
@@ -206,7 +207,7 @@ MODULE_DESCRIPTION("IXP2000 Network Processor Watchdog");
 module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds (default 60s)");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/ixp4xx_wdt.c b/drivers/watchdog/ixp4xx_wdt.c
index 4fc2e9ac26f7..5580b4fff7fe 100644
--- a/drivers/watchdog/ixp4xx_wdt.c
+++ b/drivers/watchdog/ixp4xx_wdt.c
@@ -13,6 +13,8 @@
  * warranty of any kind, whether express or implied.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -25,7 +27,7 @@
 #include <linux/uaccess.h>
 #include <mach/hardware.h>
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static int heartbeat = 60;	/* (secs) Default is 1 minute */
 static unsigned long wdt_status;
 static unsigned long boot_status;
@@ -147,8 +149,7 @@ static int ixp4xx_wdt_release(struct inode *inode, struct file *file)
 	if (test_bit(WDT_OK_TO_CLOSE, &wdt_status))
 		wdt_disable();
 	else
-		printk(KERN_CRIT "WATCHDOG: Device closed unexpectedly - "
-					"timer will not stop\n");
+		pr_crit("Device closed unexpectedly - timer will not stop\n");
 	clear_bit(WDT_IN_USE, &wdt_status);
 	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
 
@@ -176,8 +177,7 @@ static int __init ixp4xx_wdt_init(void)
 	int ret;
 
 	if (!(read_cpuid_id() & 0xf) && !cpu_is_ixp46x()) {
-		printk(KERN_ERR "IXP4XXX Watchdog: Rev. A0 IXP42x CPU detected"
-			" - watchdog disabled\n");
+		pr_err("Rev. A0 IXP42x CPU detected - watchdog disabled\n");
 
 		return -ENODEV;
 	}
@@ -185,8 +185,7 @@ static int __init ixp4xx_wdt_init(void)
 			WDIOF_CARDRESET : 0;
 	ret = misc_register(&ixp4xx_wdt_miscdev);
 	if (ret == 0)
-		printk(KERN_INFO "IXP4xx Watchdog Timer: heartbeat %d sec\n",
-			heartbeat);
+		pr_info("timer heartbeat %d sec\n", heartbeat);
 	return ret;
 }
 
@@ -205,7 +204,7 @@ MODULE_DESCRIPTION("IXP4xx Network Processor Watchdog");
 module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds (default 60s)");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/jz4740_wdt.c b/drivers/watchdog/jz4740_wdt.c
index 17ef300bccc5..978615ef899d 100644
--- a/drivers/watchdog/jz4740_wdt.c
+++ b/drivers/watchdog/jz4740_wdt.c
@@ -17,18 +17,15 @@
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/fs.h>
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/init.h>
-#include <linux/bitops.h>
 #include <linux/platform_device.h>
-#include <linux/spinlock.h>
-#include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/device.h>
 #include <linux/clk.h>
 #include <linux/slab.h>
+#include <linux/err.h>
 
 #include <asm/mach-jz4740/timer.h>
 
@@ -41,9 +38,6 @@
 #define JZ_WDT_CLOCK_RTC  0x2
 #define JZ_WDT_CLOCK_EXT  0x4
 
-#define WDT_IN_USE        0
-#define WDT_OK_TO_CLOSE   1
-
 #define JZ_WDT_CLOCK_DIV_SHIFT   3
 
 #define JZ_WDT_CLOCK_DIV_1    (0 << JZ_WDT_CLOCK_DIV_SHIFT)
@@ -56,32 +50,44 @@
 #define DEFAULT_HEARTBEAT 5
 #define MAX_HEARTBEAT     2048
 
-static struct {
-	void __iomem *base;
-	struct resource	*mem;
-	struct clk *rtc_clk;
-	unsigned long status;
-} jz4740_wdt;
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout,
+		 "Watchdog cannot be stopped once started (default="
+		 __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
-static int heartbeat = DEFAULT_HEARTBEAT;
+static unsigned int heartbeat = DEFAULT_HEARTBEAT;
+module_param(heartbeat, uint, 0);
+MODULE_PARM_DESC(heartbeat,
+		"Watchdog heartbeat period in seconds from 1 to "
+		__MODULE_STRING(MAX_HEARTBEAT) ", default "
+		__MODULE_STRING(DEFAULT_HEARTBEAT));
 
+struct jz4740_wdt_drvdata {
+	struct watchdog_device wdt;
+	void __iomem *base;
+	struct clk *rtc_clk;
+};
 
-static void jz4740_wdt_service(void)
+static int jz4740_wdt_ping(struct watchdog_device *wdt_dev)
 {
-	writew(0x0, jz4740_wdt.base + JZ_REG_WDT_TIMER_COUNTER);
+	struct jz4740_wdt_drvdata *drvdata = watchdog_get_drvdata(wdt_dev);
+
+	writew(0x0, drvdata->base + JZ_REG_WDT_TIMER_COUNTER);
+	return 0;
 }
 
-static void jz4740_wdt_set_heartbeat(int new_heartbeat)
+static int jz4740_wdt_set_timeout(struct watchdog_device *wdt_dev,
+				    unsigned int new_timeout)
 {
+	struct jz4740_wdt_drvdata *drvdata = watchdog_get_drvdata(wdt_dev);
 	unsigned int rtc_clk_rate;
 	unsigned int timeout_value;
 	unsigned short clock_div = JZ_WDT_CLOCK_DIV_1;
 
-	heartbeat = new_heartbeat;
-
-	rtc_clk_rate = clk_get_rate(jz4740_wdt.rtc_clk);
+	rtc_clk_rate = clk_get_rate(drvdata->rtc_clk);
 
-	timeout_value = rtc_clk_rate * heartbeat;
+	timeout_value = rtc_clk_rate * new_timeout;
 	while (timeout_value > 0xffff) {
 		if (clock_div == JZ_WDT_CLOCK_DIV_1024) {
 			/* Requested timeout too high;
@@ -93,199 +99,115 @@ static void jz4740_wdt_set_heartbeat(int new_heartbeat)
 		clock_div += (1 << JZ_WDT_CLOCK_DIV_SHIFT);
 	}
 
-	writeb(0x0, jz4740_wdt.base + JZ_REG_WDT_COUNTER_ENABLE);
-	writew(clock_div, jz4740_wdt.base + JZ_REG_WDT_TIMER_CONTROL);
+	writeb(0x0, drvdata->base + JZ_REG_WDT_COUNTER_ENABLE);
+	writew(clock_div, drvdata->base + JZ_REG_WDT_TIMER_CONTROL);
 
-	writew((u16)timeout_value, jz4740_wdt.base + JZ_REG_WDT_TIMER_DATA);
-	writew(0x0, jz4740_wdt.base + JZ_REG_WDT_TIMER_COUNTER);
+	writew((u16)timeout_value, drvdata->base + JZ_REG_WDT_TIMER_DATA);
+	writew(0x0, drvdata->base + JZ_REG_WDT_TIMER_COUNTER);
 	writew(clock_div | JZ_WDT_CLOCK_RTC,
-		jz4740_wdt.base + JZ_REG_WDT_TIMER_CONTROL);
+		drvdata->base + JZ_REG_WDT_TIMER_CONTROL);
 
-	writeb(0x1, jz4740_wdt.base + JZ_REG_WDT_COUNTER_ENABLE);
-}
+	writeb(0x1, drvdata->base + JZ_REG_WDT_COUNTER_ENABLE);
 
-static void jz4740_wdt_enable(void)
-{
-	jz4740_timer_enable_watchdog();
-	jz4740_wdt_set_heartbeat(heartbeat);
-}
-
-static void jz4740_wdt_disable(void)
-{
-	jz4740_timer_disable_watchdog();
-	writeb(0x0, jz4740_wdt.base + JZ_REG_WDT_COUNTER_ENABLE);
+	wdt_dev->timeout = new_timeout;
+	return 0;
 }
 
-static int jz4740_wdt_open(struct inode *inode, struct file *file)
+static int jz4740_wdt_start(struct watchdog_device *wdt_dev)
 {
-	if (test_and_set_bit(WDT_IN_USE, &jz4740_wdt.status))
-		return -EBUSY;
-
-	jz4740_wdt_enable();
+	jz4740_timer_enable_watchdog();
+	jz4740_wdt_set_timeout(wdt_dev, wdt_dev->timeout);
 
-	return nonseekable_open(inode, file);
+	return 0;
 }
 
-static ssize_t jz4740_wdt_write(struct file *file, const char *data,
-		size_t len, loff_t *ppos)
+static int jz4740_wdt_stop(struct watchdog_device *wdt_dev)
 {
-	if (len) {
-		size_t i;
-
-		clear_bit(WDT_OK_TO_CLOSE, &jz4740_wdt.status);
-		for (i = 0; i != len; i++) {
-			char c;
+	struct jz4740_wdt_drvdata *drvdata = watchdog_get_drvdata(wdt_dev);
 
-			if (get_user(c, data + i))
-				return -EFAULT;
-
-			if (c == 'V')
-				set_bit(WDT_OK_TO_CLOSE, &jz4740_wdt.status);
-		}
-		jz4740_wdt_service();
-	}
+	jz4740_timer_disable_watchdog();
+	writeb(0x0, drvdata->base + JZ_REG_WDT_COUNTER_ENABLE);
 
-	return len;
+	return 0;
 }
 
-static const struct watchdog_info ident = {
-	.options = WDIOF_KEEPALIVEPING,
+static const struct watchdog_info jz4740_wdt_info = {
+	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
 	.identity = "jz4740 Watchdog",
 };
 
-static long jz4740_wdt_ioctl(struct file *file,
-					unsigned int cmd, unsigned long arg)
-{
-	int ret = -ENOTTY;
-	int heartbeat_seconds;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		ret = copy_to_user((struct watchdog_info *)arg, &ident,
-				sizeof(ident)) ? -EFAULT : 0;
-		break;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		ret = put_user(0, (int *)arg);
-		break;
-
-	case WDIOC_KEEPALIVE:
-		jz4740_wdt_service();
-		return 0;
-
-	case WDIOC_SETTIMEOUT:
-		if (get_user(heartbeat_seconds, (int __user *)arg))
-			return -EFAULT;
-
-		jz4740_wdt_set_heartbeat(heartbeat_seconds);
-		return 0;
-
-	case WDIOC_GETTIMEOUT:
-		return put_user(heartbeat, (int *)arg);
-
-	default:
-		break;
-	}
-
-	return ret;
-}
-
-static int jz4740_wdt_release(struct inode *inode, struct file *file)
-{
-	jz4740_wdt_service();
-
-	if (test_and_clear_bit(WDT_OK_TO_CLOSE, &jz4740_wdt.status))
-		jz4740_wdt_disable();
-
-	clear_bit(WDT_IN_USE, &jz4740_wdt.status);
-	return 0;
-}
-
-static const struct file_operations jz4740_wdt_fops = {
+static const struct watchdog_ops jz4740_wdt_ops = {
 	.owner = THIS_MODULE,
-	.llseek = no_llseek,
-	.write = jz4740_wdt_write,
-	.unlocked_ioctl = jz4740_wdt_ioctl,
-	.open = jz4740_wdt_open,
-	.release = jz4740_wdt_release,
-};
-
-static struct miscdevice jz4740_wdt_miscdev = {
-	.minor = WATCHDOG_MINOR,
-	.name = "watchdog",
-	.fops = &jz4740_wdt_fops,
+	.start = jz4740_wdt_start,
+	.stop = jz4740_wdt_stop,
+	.ping = jz4740_wdt_ping,
+	.set_timeout = jz4740_wdt_set_timeout,
 };
 
 static int __devinit jz4740_wdt_probe(struct platform_device *pdev)
 {
-	int ret = 0, size;
-	struct resource *res;
-	struct device *dev = &pdev->dev;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res == NULL) {
-		dev_err(dev, "failed to get memory region resource\n");
-		return -ENXIO;
+	struct jz4740_wdt_drvdata *drvdata;
+	struct watchdog_device *jz4740_wdt;
+	struct resource	*res;
+	int ret;
+
+	drvdata = devm_kzalloc(&pdev->dev, sizeof(struct jz4740_wdt_drvdata),
+			       GFP_KERNEL);
+	if (!drvdata) {
+		dev_err(&pdev->dev, "Unable to alloacate watchdog device\n");
+		return -ENOMEM;
 	}
 
-	size = resource_size(res);
-	jz4740_wdt.mem = request_mem_region(res->start, size, pdev->name);
-	if (jz4740_wdt.mem == NULL) {
-		dev_err(dev, "failed to get memory region\n");
-		return -EBUSY;
-	}
+	if (heartbeat < 1 || heartbeat > MAX_HEARTBEAT)
+		heartbeat = DEFAULT_HEARTBEAT;
 
-	jz4740_wdt.base = ioremap_nocache(res->start, size);
-	if (jz4740_wdt.base == NULL) {
-		dev_err(dev, "failed to map memory region\n");
+	jz4740_wdt = &drvdata->wdt;
+	jz4740_wdt->info = &jz4740_wdt_info;
+	jz4740_wdt->ops = &jz4740_wdt_ops;
+	jz4740_wdt->timeout = heartbeat;
+	jz4740_wdt->min_timeout = 1;
+	jz4740_wdt->max_timeout = MAX_HEARTBEAT;
+	watchdog_set_nowayout(jz4740_wdt, nowayout);
+	watchdog_set_drvdata(jz4740_wdt, drvdata);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	drvdata->base = devm_request_and_ioremap(&pdev->dev, res);
+	if (drvdata->base == NULL) {
 		ret = -EBUSY;
-		goto err_release_region;
+		goto err_out;
 	}
 
-	jz4740_wdt.rtc_clk = clk_get(NULL, "rtc");
-	if (IS_ERR(jz4740_wdt.rtc_clk)) {
-		dev_err(dev, "cannot find RTC clock\n");
-		ret = PTR_ERR(jz4740_wdt.rtc_clk);
-		goto err_iounmap;
+	drvdata->rtc_clk = clk_get(NULL, "rtc");
+	if (IS_ERR(drvdata->rtc_clk)) {
+		dev_err(&pdev->dev, "cannot find RTC clock\n");
+		ret = PTR_ERR(drvdata->rtc_clk);
+		goto err_out;
 	}
 
-	ret = misc_register(&jz4740_wdt_miscdev);
-	if (ret < 0) {
-		dev_err(dev, "cannot register misc device\n");
+	ret = watchdog_register_device(&drvdata->wdt);
+	if (ret < 0)
 		goto err_disable_clk;
-	}
 
+	platform_set_drvdata(pdev, drvdata);
 	return 0;
 
 err_disable_clk:
-	clk_put(jz4740_wdt.rtc_clk);
-err_iounmap:
-	iounmap(jz4740_wdt.base);
-err_release_region:
-	release_mem_region(jz4740_wdt.mem->start,
-			resource_size(jz4740_wdt.mem));
+	clk_put(drvdata->rtc_clk);
+err_out:
 	return ret;
 }
 
-
 static int __devexit jz4740_wdt_remove(struct platform_device *pdev)
 {
-	jz4740_wdt_disable();
-	misc_deregister(&jz4740_wdt_miscdev);
-	clk_put(jz4740_wdt.rtc_clk);
+	struct jz4740_wdt_drvdata *drvdata = platform_get_drvdata(pdev);
 
-	iounmap(jz4740_wdt.base);
-	jz4740_wdt.base = NULL;
-
-	release_mem_region(jz4740_wdt.mem->start,
-				resource_size(jz4740_wdt.mem));
-	jz4740_wdt.mem = NULL;
+	jz4740_wdt_stop(&drvdata->wdt);
+	watchdog_unregister_device(&drvdata->wdt);
+	clk_put(drvdata->rtc_clk);
 
 	return 0;
 }
 
-
 static struct platform_driver jz4740_wdt_driver = {
 	.probe = jz4740_wdt_probe,
 	.remove = __devexit_p(jz4740_wdt_remove),
@@ -299,13 +221,6 @@ module_platform_driver(jz4740_wdt_driver);
 
 MODULE_AUTHOR("Paul Cercueil <paul@crapouillou.net>");
 MODULE_DESCRIPTION("jz4740 Watchdog Driver");
-
-module_param(heartbeat, int, 0);
-MODULE_PARM_DESC(heartbeat,
-		"Watchdog heartbeat period in seconds from 1 to "
-		__MODULE_STRING(MAX_HEARTBEAT) ", default "
-		__MODULE_STRING(DEFAULT_HEARTBEAT));
-
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
 MODULE_ALIAS("platform:jz4740-wdt");
diff --git a/drivers/watchdog/ks8695_wdt.c b/drivers/watchdog/ks8695_wdt.c
index 51757a520e8f..59e75d9a6b7f 100644
--- a/drivers/watchdog/ks8695_wdt.c
+++ b/drivers/watchdog/ks8695_wdt.c
@@ -8,6 +8,8 @@
  * published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -28,14 +30,14 @@
 #define WDT_MAX_TIME		171	/* seconds */
 
 static int wdt_time = WDT_DEFAULT_TIME;
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 module_param(wdt_time, int, 0);
 MODULE_PARM_DESC(wdt_time, "Watchdog time in seconds. (default="
 					__MODULE_STRING(WDT_DEFAULT_TIME) ")");
 
 #ifdef CONFIG_WATCHDOG_NOWAYOUT
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 #endif
@@ -233,8 +235,8 @@ static int __devinit ks8695wdt_probe(struct platform_device *pdev)
 	if (res)
 		return res;
 
-	printk(KERN_INFO "KS8695 Watchdog Timer enabled (%d seconds%s)\n",
-				wdt_time, nowayout ? ", nowayout" : "");
+	pr_info("KS8695 Watchdog Timer enabled (%d seconds%s)\n",
+		wdt_time, nowayout ? ", nowayout" : "");
 	return 0;
 }
 
diff --git a/drivers/watchdog/lantiq_wdt.c b/drivers/watchdog/lantiq_wdt.c
index d3a63be2e28d..a9593a3a32a0 100644
--- a/drivers/watchdog/lantiq_wdt.c
+++ b/drivers/watchdog/lantiq_wdt.c
@@ -7,6 +7,8 @@
  *  Based on EP93xx wdt driver
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/miscdevice.h>
@@ -38,7 +40,7 @@
 #define LTQ_WDT_DIVIDER		0x40000
 #define LTQ_MAX_TIMEOUT		((1 << 16) - 1)	/* the reload field is 16 bit */
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 static void __iomem *ltq_wdt_membase;
 static unsigned long ltq_io_region_clk_rate;
@@ -160,7 +162,7 @@ ltq_wdt_release(struct inode *inode, struct file *file)
 	if (ltq_wdt_ok_to_close)
 		ltq_wdt_disable();
 	else
-		pr_err("ltq_wdt: watchdog closed without warning\n");
+		pr_err("watchdog closed without warning\n");
 	ltq_wdt_ok_to_close = 0;
 	clear_bit(0, &ltq_wdt_in_use);
 
@@ -249,7 +251,7 @@ exit_ltq_wdt(void)
 module_init(init_ltq_wdt);
 module_exit(exit_ltq_wdt);
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
 
 MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
diff --git a/drivers/watchdog/m54xx_wdt.c b/drivers/watchdog/m54xx_wdt.c
index 4d43286074aa..663cad86c633 100644
--- a/drivers/watchdog/m54xx_wdt.c
+++ b/drivers/watchdog/m54xx_wdt.c
@@ -16,6 +16,8 @@
  * warranty of any kind, whether express or implied.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -32,7 +34,7 @@
 #include <asm/m54xxsim.h>
 #include <asm/m54xxgpt.h>
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static unsigned int heartbeat = 30;	/* (secs) Default is 0.5 minute */
 static unsigned long wdt_status;
 
@@ -166,8 +168,7 @@ static int m54xx_wdt_release(struct inode *inode, struct file *file)
 	if (test_bit(WDT_OK_TO_CLOSE, &wdt_status))
 		wdt_disable();
 	else {
-		printk(KERN_CRIT "WATCHDOG: Device closed unexpectedly - "
-					"timer will not stop\n");
+		pr_crit("Device closed unexpectedly - timer will not stop\n");
 		wdt_keepalive();
 	}
 	clear_bit(WDT_IN_USE, &wdt_status);
@@ -196,11 +197,10 @@ static int __init m54xx_wdt_init(void)
 {
 	if (!request_mem_region(MCF_MBAR + MCF_GPT_GCIR0, 4,
 						"Coldfire M54xx Watchdog")) {
-		printk(KERN_WARNING
-				"Coldfire M54xx Watchdog : I/O region busy\n");
+		pr_warn("I/O region busy\n");
 		return -EBUSY;
 	}
-	printk(KERN_INFO "ColdFire watchdog driver is loaded.\n");
+	pr_info("driver is loaded\n");
 
 	return misc_register(&m54xx_wdt_miscdev);
 }
@@ -220,7 +220,7 @@ MODULE_DESCRIPTION("Coldfire M54xx Watchdog");
 module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds (default 30s)");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/machzwd.c b/drivers/watchdog/machzwd.c
index 1332b838cc58..bf84f788e592 100644
--- a/drivers/watchdog/machzwd.c
+++ b/drivers/watchdog/machzwd.c
@@ -28,6 +28,8 @@
  *      Added nowayout module option to override CONFIG_WATCHDOG_NOWAYOUT
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -43,7 +45,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 /* ports */
 #define ZF_IOBASE	0x218
@@ -93,8 +94,8 @@ MODULE_DESCRIPTION("MachZ ZF-Logic Watchdog driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -141,10 +142,10 @@ static unsigned long next_heartbeat;
 #define ZF_CTIMEOUT 0xffff
 
 #ifndef ZF_DEBUG
-#	define dprintk(format, args...)
+#define dprintk(format, args...)
 #else
-#	define dprintk(format, args...) printk(KERN_DEBUG PFX \
-				":%s:%d: " format, __func__, __LINE__ , ## args)
+#define dprintk(format, args...)					\
+	pr_debug(":%s:%d: " format, __func__, __LINE__ , ## args)
 #endif
 
 
@@ -203,7 +204,7 @@ static void zf_timer_off(void)
 	zf_set_control(ctrl_reg);
 	spin_unlock_irqrestore(&zf_port_lock, flags);
 
-	printk(KERN_INFO PFX ": Watchdog timer is now disabled\n");
+	pr_info("Watchdog timer is now disabled\n");
 }
 
 
@@ -233,7 +234,7 @@ static void zf_timer_on(void)
 	zf_set_control(ctrl_reg);
 	spin_unlock_irqrestore(&zf_port_lock, flags);
 
-	printk(KERN_INFO PFX ": Watchdog timer is now enabled\n");
+	pr_info("Watchdog timer is now enabled\n");
 }
 
 
@@ -263,7 +264,7 @@ static void zf_ping(unsigned long data)
 
 		mod_timer(&zf_timer, jiffies + ZF_HW_TIMEO);
 	} else
-		printk(KERN_CRIT PFX ": I will reset your machine\n");
+		pr_crit("I will reset your machine\n");
 }
 
 static ssize_t zf_write(struct file *file, const char __user *buf, size_t count,
@@ -342,8 +343,7 @@ static int zf_close(struct inode *inode, struct file *file)
 		zf_timer_off();
 	else {
 		del_timer(&zf_timer);
-		printk(KERN_ERR PFX ": device file closed unexpectedly. "
-						"Will not stop the WDT!\n");
+		pr_err("device file closed unexpectedly. Will not stop the WDT!\n");
 	}
 	clear_bit(0, &zf_is_open);
 	zf_expect_close = 0;
@@ -390,19 +390,18 @@ static void __init zf_show_action(int act)
 {
 	static const char * const str[] = { "RESET", "SMI", "NMI", "SCI" };
 
-	printk(KERN_INFO PFX ": Watchdog using action = %s\n", str[act]);
+	pr_info("Watchdog using action = %s\n", str[act]);
 }
 
 static int __init zf_init(void)
 {
 	int ret;
 
-	printk(KERN_INFO PFX
-		": MachZ ZF-Logic Watchdog driver initializing.\n");
+	pr_info("MachZ ZF-Logic Watchdog driver initializing\n");
 
 	ret = zf_get_ZFL_version();
 	if (!ret || ret == 0xffff) {
-		printk(KERN_WARNING PFX ": no ZF-Logic found\n");
+		pr_warn("no ZF-Logic found\n");
 		return -ENODEV;
 	}
 
@@ -414,23 +413,20 @@ static int __init zf_init(void)
 	zf_show_action(action);
 
 	if (!request_region(ZF_IOBASE, 3, "MachZ ZFL WDT")) {
-		printk(KERN_ERR "cannot reserve I/O ports at %d\n",
-							ZF_IOBASE);
+		pr_err("cannot reserve I/O ports at %d\n", ZF_IOBASE);
 		ret = -EBUSY;
 		goto no_region;
 	}
 
 	ret = register_reboot_notifier(&zf_notifier);
 	if (ret) {
-		printk(KERN_ERR "can't register reboot notifier (err=%d)\n",
-									ret);
+		pr_err("can't register reboot notifier (err=%d)\n", ret);
 		goto no_reboot;
 	}
 
 	ret = misc_register(&zf_miscdev);
 	if (ret) {
-		printk(KERN_ERR "can't misc_register on minor=%d\n",
-							WATCHDOG_MINOR);
+		pr_err("can't misc_register on minor=%d\n", WATCHDOG_MINOR);
 		goto no_misc;
 	}
 
diff --git a/drivers/watchdog/max63xx_wdt.c b/drivers/watchdog/max63xx_wdt.c
index af63ecfbfa6f..8f4a74e91619 100644
--- a/drivers/watchdog/max63xx_wdt.c
+++ b/drivers/watchdog/max63xx_wdt.c
@@ -18,23 +18,20 @@
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/fs.h>
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
-#include <linux/uaccess.h>
 #include <linux/io.h>
-#include <linux/device.h>
 #include <linux/slab.h>
 
 #define DEFAULT_HEARTBEAT 60
 #define MAX_HEARTBEAT     60
 
-static int heartbeat = DEFAULT_HEARTBEAT;
-static int nowayout  = WATCHDOG_NOWAYOUT;
+static unsigned int heartbeat = DEFAULT_HEARTBEAT;
+static bool nowayout  = WATCHDOG_NOWAYOUT;
 
 /*
  * Memory mapping: a single byte, 3 first lower bits to select bit 3
@@ -45,15 +42,8 @@ static int nowayout  = WATCHDOG_NOWAYOUT;
 
 static DEFINE_SPINLOCK(io_lock);
 
-static unsigned long wdt_status;
-#define WDT_IN_USE	0
-#define WDT_RUNNING	1
-#define WDT_OK_TO_CLOSE 2
-
 static int nodelay;
-static struct resource	*wdt_mem;
 static void __iomem	*wdt_base;
-static struct platform_device *max63xx_pdev;
 
 /*
  * The timeout values used are actually the absolute minimum the chip
@@ -117,7 +107,7 @@ max63xx_select_timeout(struct max63xx_timeout *table, int value)
 	return NULL;
 }
 
-static void max63xx_wdt_ping(void)
+static int max63xx_wdt_ping(struct watchdog_device *wdd)
 {
 	u8 val;
 
@@ -129,15 +119,14 @@ static void max63xx_wdt_ping(void)
 	__raw_writeb(val & ~MAX6369_WDI, wdt_base);
 
 	spin_unlock(&io_lock);
+	return 0;
 }
 
-static void max63xx_wdt_enable(struct max63xx_timeout *entry)
+static int max63xx_wdt_start(struct watchdog_device *wdd)
 {
+	struct max63xx_timeout *entry = watchdog_get_drvdata(wdd);
 	u8 val;
 
-	if (test_and_set_bit(WDT_RUNNING, &wdt_status))
-		return;
-
 	spin_lock(&io_lock);
 
 	val = __raw_readb(wdt_base);
@@ -149,10 +138,11 @@ static void max63xx_wdt_enable(struct max63xx_timeout *entry)
 
 	/* check for a edge triggered startup */
 	if (entry->tdelay == 0)
-		max63xx_wdt_ping();
+		max63xx_wdt_ping(wdd);
+	return 0;
 }
 
-static void max63xx_wdt_disable(void)
+static int max63xx_wdt_stop(struct watchdog_device *wdd)
 {
 	u8 val;
 
@@ -164,113 +154,29 @@ static void max63xx_wdt_disable(void)
 	__raw_writeb(val, wdt_base);
 
 	spin_unlock(&io_lock);
-
-	clear_bit(WDT_RUNNING, &wdt_status);
-}
-
-static int max63xx_wdt_open(struct inode *inode, struct file *file)
-{
-	if (test_and_set_bit(WDT_IN_USE, &wdt_status))
-		return -EBUSY;
-
-	max63xx_wdt_enable(current_timeout);
-	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
-	return nonseekable_open(inode, file);
-}
-
-static ssize_t max63xx_wdt_write(struct file *file, const char *data,
-				 size_t len, loff_t *ppos)
-{
-	if (len) {
-		if (!nowayout) {
-			size_t i;
-
-			clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-			for (i = 0; i != len; i++) {
-				char c;
-
-				if (get_user(c, data + i))
-					return -EFAULT;
-
-				if (c == 'V')
-					set_bit(WDT_OK_TO_CLOSE, &wdt_status);
-			}
-		}
-
-		max63xx_wdt_ping();
-	}
-
-	return len;
+	return 0;
 }
 
-static const struct watchdog_info ident = {
-	.options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING,
+static const struct watchdog_info max63xx_wdt_info = {
+	.options = WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
 	.identity = "max63xx Watchdog",
 };
 
-static long max63xx_wdt_ioctl(struct file *file, unsigned int cmd,
-			      unsigned long arg)
-{
-	int ret = -ENOTTY;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		ret = copy_to_user((struct watchdog_info *)arg, &ident,
-				   sizeof(ident)) ? -EFAULT : 0;
-		break;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		ret = put_user(0, (int *)arg);
-		break;
-
-	case WDIOC_KEEPALIVE:
-		max63xx_wdt_ping();
-		ret = 0;
-		break;
-
-	case WDIOC_GETTIMEOUT:
-		ret = put_user(heartbeat, (int *)arg);
-		break;
-	}
-	return ret;
-}
-
-static int max63xx_wdt_release(struct inode *inode, struct file *file)
-{
-	if (test_bit(WDT_OK_TO_CLOSE, &wdt_status))
-		max63xx_wdt_disable();
-	else
-		dev_crit(&max63xx_pdev->dev,
-			 "device closed unexpectedly - timer will not stop\n");
-
-	clear_bit(WDT_IN_USE, &wdt_status);
-	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
-	return 0;
-}
-
-static const struct file_operations max63xx_wdt_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.write		= max63xx_wdt_write,
-	.unlocked_ioctl	= max63xx_wdt_ioctl,
-	.open		= max63xx_wdt_open,
-	.release	= max63xx_wdt_release,
+static const struct watchdog_ops max63xx_wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = max63xx_wdt_start,
+	.stop = max63xx_wdt_stop,
+	.ping = max63xx_wdt_ping,
 };
 
-static struct miscdevice max63xx_wdt_miscdev = {
-	.minor	= WATCHDOG_MINOR,
-	.name	= "watchdog",
-	.fops	= &max63xx_wdt_fops,
+static struct watchdog_device max63xx_wdt_dev = {
+	.info = &max63xx_wdt_info,
+	.ops = &max63xx_wdt_ops,
 };
 
 static int __devinit max63xx_wdt_probe(struct platform_device *pdev)
 {
-	int ret = 0;
-	int size;
-	struct device *dev = &pdev->dev;
+	struct resource	*wdt_mem;
 	struct max63xx_timeout *table;
 
 	table = (struct max63xx_timeout *)pdev->id_entry->driver_data;
@@ -278,68 +184,34 @@ static int __devinit max63xx_wdt_probe(struct platform_device *pdev)
 	if (heartbeat < 1 || heartbeat > MAX_HEARTBEAT)
 		heartbeat = DEFAULT_HEARTBEAT;
 
-	dev_info(dev, "requesting %ds heartbeat\n", heartbeat);
+	dev_info(&pdev->dev, "requesting %ds heartbeat\n", heartbeat);
 	current_timeout = max63xx_select_timeout(table, heartbeat);
 
 	if (!current_timeout) {
-		dev_err(dev, "unable to satisfy heartbeat request\n");
+		dev_err(&pdev->dev, "unable to satisfy heartbeat request\n");
 		return -EINVAL;
 	}
 
-	dev_info(dev, "using %ds heartbeat with %ds initial delay\n",
+	dev_info(&pdev->dev, "using %ds heartbeat with %ds initial delay\n",
 		 current_timeout->twd, current_timeout->tdelay);
 
 	heartbeat = current_timeout->twd;
 
-	max63xx_pdev = pdev;
-
 	wdt_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (wdt_mem == NULL) {
-		dev_err(dev, "failed to get memory region resource\n");
-		return -ENOENT;
-	}
+	wdt_base = devm_request_and_ioremap(&pdev->dev, wdt_mem);
+	if (!wdt_base)
+		return -ENOMEM;
 
-	size = resource_size(wdt_mem);
-	if (!request_mem_region(wdt_mem->start, size, pdev->name)) {
-		dev_err(dev, "failed to get memory region\n");
-		return -ENOENT;
-	}
-
-	wdt_base = ioremap(wdt_mem->start, size);
-	if (!wdt_base) {
-		dev_err(dev, "failed to map memory region\n");
-		ret = -ENOMEM;
-		goto out_request;
-	}
+	max63xx_wdt_dev.timeout = heartbeat;
+	watchdog_set_nowayout(&max63xx_wdt_dev, nowayout);
+	watchdog_set_drvdata(&max63xx_wdt_dev, current_timeout);
 
-	ret = misc_register(&max63xx_wdt_miscdev);
-	if (ret < 0) {
-		dev_err(dev, "cannot register misc device\n");
-		goto out_unmap;
-	}
-
-	return 0;
-
-out_unmap:
-	iounmap(wdt_base);
-out_request:
-	release_mem_region(wdt_mem->start, size);
-	wdt_mem = NULL;
-
-	return ret;
+	return watchdog_register_device(&max63xx_wdt_dev);
 }
 
 static int __devexit max63xx_wdt_remove(struct platform_device *pdev)
 {
-	misc_deregister(&max63xx_wdt_miscdev);
-	if (wdt_mem) {
-		release_mem_region(wdt_mem->start, resource_size(wdt_mem));
-		wdt_mem = NULL;
-	}
-
-	if (wdt_base)
-		iounmap(wdt_base);
-
+	watchdog_unregister_device(&max63xx_wdt_dev);
 	return 0;
 }
 
@@ -375,7 +247,7 @@ MODULE_PARM_DESC(heartbeat,
 		 __MODULE_STRING(MAX_HEARTBEAT) ", default "
 		 __MODULE_STRING(DEFAULT_HEARTBEAT));
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 		 __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
diff --git a/drivers/watchdog/mixcomwd.c b/drivers/watchdog/mixcomwd.c
index bc820d16699a..37e4b52dbce9 100644
--- a/drivers/watchdog/mixcomwd.c
+++ b/drivers/watchdog/mixcomwd.c
@@ -39,9 +39,10 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #define VERSION "0.6"
 #define WATCHDOG_NAME "mixcomwd"
-#define PFX WATCHDOG_NAME ": "
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -107,8 +108,8 @@ static int mixcomwd_timer_alive;
 static DEFINE_TIMER(mixcomwd_timer, mixcomwd_timerfun, 0, 0);
 static char expect_close;
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -156,15 +157,13 @@ static int mixcomwd_release(struct inode *inode, struct file *file)
 {
 	if (expect_close == 42) {
 		if (mixcomwd_timer_alive) {
-			printk(KERN_ERR PFX
-				"release called while internal timer alive");
+			pr_err("release called while internal timer alive\n");
 			return -EBUSY;
 		}
 		mixcomwd_timer_alive = 1;
 		mod_timer(&mixcomwd_timer, jiffies + 5 * HZ);
 	} else
-		printk(KERN_CRIT PFX
-		    "WDT device closed unexpectedly.  WDT will not stop!\n");
+		pr_crit("WDT device closed unexpectedly.  WDT will not stop!\n");
 
 	clear_bit(0, &mixcomwd_opened);
 	expect_close = 0;
@@ -274,22 +273,19 @@ static int __init mixcomwd_init(void)
 	}
 
 	if (!found) {
-		printk(KERN_ERR PFX
-			"No card detected, or port not available.\n");
+		pr_err("No card detected, or port not available\n");
 		return -ENODEV;
 	}
 
 	ret = misc_register(&mixcomwd_miscdev);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-					WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto error_misc_register_watchdog;
 	}
 
-	printk(KERN_INFO
-		"MixCOM watchdog driver v%s, watchdog port at 0x%3x\n",
-					VERSION, watchdog_port);
+	pr_info("MixCOM watchdog driver v%s, watchdog port at 0x%3x\n",
+		VERSION, watchdog_port);
 
 	return 0;
 
@@ -303,8 +299,7 @@ static void __exit mixcomwd_exit(void)
 {
 	if (!nowayout) {
 		if (mixcomwd_timer_alive) {
-			printk(KERN_WARNING PFX "I quit now, hardware will"
-			       " probably reboot!\n");
+			pr_warn("I quit now, hardware will probably reboot!\n");
 			del_timer_sync(&mixcomwd_timer);
 			mixcomwd_timer_alive = 0;
 		}
diff --git a/drivers/watchdog/mpc8xxx_wdt.c b/drivers/watchdog/mpc8xxx_wdt.c
index 20feb4d3d791..40f7bf1f8654 100644
--- a/drivers/watchdog/mpc8xxx_wdt.c
+++ b/drivers/watchdog/mpc8xxx_wdt.c
@@ -17,6 +17,8 @@
  * option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -60,8 +62,8 @@ module_param(reset, bool, 0);
 MODULE_PARM_DESC(reset,
 	"Watchdog Interrupt/Reset Mode. 0 = interrupt, 1 = reset");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 		 "(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -96,7 +98,7 @@ static void mpc8xxx_wdt_timer_ping(unsigned long arg)
 
 static void mpc8xxx_wdt_pr_warn(const char *msg)
 {
-	pr_crit("mpc8xxx_wdt: %s, expect the %s soon!\n", msg,
+	pr_crit("%s, expect the %s soon!\n", msg,
 		reset ? "reset" : "machine check exception");
 }
 
@@ -209,7 +211,7 @@ static int __devinit mpc8xxx_wdt_probe(struct platform_device *ofdev)
 
 	enabled = in_be32(&wd_base->swcrr) & SWCRR_SWEN;
 	if (!enabled && wdt_type->hw_enabled) {
-		pr_info("mpc8xxx_wdt: could not be enabled in software\n");
+		pr_info("could not be enabled in software\n");
 		ret = -ENOSYS;
 		goto err_unmap;
 	}
@@ -226,9 +228,8 @@ static int __devinit mpc8xxx_wdt_probe(struct platform_device *ofdev)
 		goto err_unmap;
 #endif
 
-	pr_info("WDT driver for MPC8xxx initialized. mode:%s timeout=%d "
-		"(%d seconds)\n", reset ? "reset" : "interrupt", timeout,
-		timeout_sec);
+	pr_info("WDT driver for MPC8xxx initialized. mode:%s timeout=%d (%d seconds)\n",
+		reset ? "reset" : "interrupt", timeout, timeout_sec);
 
 	/*
 	 * If the watchdog was previously enabled or we're running on
@@ -303,7 +304,7 @@ static int mpc8xxx_wdt_init_late(void)
 	ret = misc_register(&mpc8xxx_wdt_miscdev);
 	if (ret) {
 		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
-			WATCHDOG_MINOR, ret);
+		       WATCHDOG_MINOR, ret);
 		return ret;
 	}
 	return 0;
diff --git a/drivers/watchdog/mpcore_wdt.c b/drivers/watchdog/mpcore_wdt.c
index 82ccd36e2c90..7c741dc987bd 100644
--- a/drivers/watchdog/mpcore_wdt.c
+++ b/drivers/watchdog/mpcore_wdt.c
@@ -19,6 +19,9 @@
  *	(c) Copyright 1995    Alan Cox <alan@lxorguk.ukuu.org.uk>
  *
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -44,7 +47,7 @@ struct mpcore_wdt {
 	char		expect_close;
 };
 
-static struct platform_device *mpcore_wdt_dev;
+static struct platform_device *mpcore_wdt_pdev;
 static DEFINE_SPINLOCK(wdt_lock);
 
 #define TIMER_MARGIN	60
@@ -54,8 +57,8 @@ MODULE_PARM_DESC(mpcore_margin,
 	"MPcore timer margin in seconds. (0 < mpcore_margin < 65536, default="
 				__MODULE_STRING(TIMER_MARGIN) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -148,7 +151,7 @@ static int mpcore_wdt_set_heartbeat(int t)
  */
 static int mpcore_wdt_open(struct inode *inode, struct file *file)
 {
-	struct mpcore_wdt *wdt = platform_get_drvdata(mpcore_wdt_dev);
+	struct mpcore_wdt *wdt = platform_get_drvdata(mpcore_wdt_pdev);
 
 	if (test_and_set_bit(0, &wdt->timer_alive))
 		return -EBUSY;
@@ -298,9 +301,9 @@ static long mpcore_wdt_ioctl(struct file *file, unsigned int cmd,
  *	System shutdown handler.  Turn off the watchdog if we're
  *	restarting or halting the system.
  */
-static void mpcore_wdt_shutdown(struct platform_device *dev)
+static void mpcore_wdt_shutdown(struct platform_device *pdev)
 {
-	struct mpcore_wdt *wdt = platform_get_drvdata(dev);
+	struct mpcore_wdt *wdt = platform_get_drvdata(pdev);
 
 	if (system_state == SYSTEM_RESTART || system_state == SYSTEM_HALT)
 		mpcore_wdt_stop(wdt);
@@ -324,99 +327,79 @@ static struct miscdevice mpcore_wdt_miscdev = {
 	.fops		= &mpcore_wdt_fops,
 };
 
-static int __devinit mpcore_wdt_probe(struct platform_device *dev)
+static int __devinit mpcore_wdt_probe(struct platform_device *pdev)
 {
 	struct mpcore_wdt *wdt;
 	struct resource *res;
 	int ret;
 
 	/* We only accept one device, and it must have an id of -1 */
-	if (dev->id != -1)
+	if (pdev->id != -1)
 		return -ENODEV;
 
-	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	if (!res) {
-		ret = -ENODEV;
-		goto err_out;
-	}
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
 
-	wdt = kzalloc(sizeof(struct mpcore_wdt), GFP_KERNEL);
-	if (!wdt) {
-		ret = -ENOMEM;
-		goto err_out;
+	wdt = devm_kzalloc(&pdev->dev, sizeof(struct mpcore_wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
+
+	wdt->dev = &pdev->dev;
+	wdt->irq = platform_get_irq(pdev, 0);
+	if (wdt->irq >= 0) {
+		ret = devm_request_irq(wdt->dev, wdt->irq, mpcore_wdt_fire, 0,
+				"mpcore_wdt", wdt);
+		if (ret) {
+			dev_printk(KERN_ERR, wdt->dev,
+					"cannot register IRQ%d for watchdog\n",
+					wdt->irq);
+			return ret;
+		}
 	}
 
-	wdt->dev = &dev->dev;
-	wdt->irq = platform_get_irq(dev, 0);
-	if (wdt->irq < 0) {
-		ret = -ENXIO;
-		goto err_free;
-	}
-	wdt->base = ioremap(res->start, resource_size(res));
-	if (!wdt->base) {
-		ret = -ENOMEM;
-		goto err_free;
-	}
+	wdt->base = devm_ioremap(wdt->dev, res->start, resource_size(res));
+	if (!wdt->base)
+		return -ENOMEM;
 
-	mpcore_wdt_miscdev.parent = &dev->dev;
+	mpcore_wdt_miscdev.parent = &pdev->dev;
 	ret = misc_register(&mpcore_wdt_miscdev);
 	if (ret) {
 		dev_printk(KERN_ERR, wdt->dev,
 			"cannot register miscdev on minor=%d (err=%d)\n",
 							WATCHDOG_MINOR, ret);
-		goto err_misc;
-	}
-
-	ret = request_irq(wdt->irq, mpcore_wdt_fire, 0, "mpcore_wdt", wdt);
-	if (ret) {
-		dev_printk(KERN_ERR, wdt->dev,
-			"cannot register IRQ%d for watchdog\n", wdt->irq);
-		goto err_irq;
+		return ret;
 	}
 
 	mpcore_wdt_stop(wdt);
-	platform_set_drvdata(dev, wdt);
-	mpcore_wdt_dev = dev;
+	platform_set_drvdata(pdev, wdt);
+	mpcore_wdt_pdev = pdev;
 
 	return 0;
-
-err_irq:
-	misc_deregister(&mpcore_wdt_miscdev);
-err_misc:
-	iounmap(wdt->base);
-err_free:
-	kfree(wdt);
-err_out:
-	return ret;
 }
 
-static int __devexit mpcore_wdt_remove(struct platform_device *dev)
+static int __devexit mpcore_wdt_remove(struct platform_device *pdev)
 {
-	struct mpcore_wdt *wdt = platform_get_drvdata(dev);
-
-	platform_set_drvdata(dev, NULL);
+	platform_set_drvdata(pdev, NULL);
 
 	misc_deregister(&mpcore_wdt_miscdev);
 
-	mpcore_wdt_dev = NULL;
+	mpcore_wdt_pdev = NULL;
 
-	free_irq(wdt->irq, wdt);
-	iounmap(wdt->base);
-	kfree(wdt);
 	return 0;
 }
 
 #ifdef CONFIG_PM
-static int mpcore_wdt_suspend(struct platform_device *dev, pm_message_t msg)
+static int mpcore_wdt_suspend(struct platform_device *pdev, pm_message_t msg)
 {
-	struct mpcore_wdt *wdt = platform_get_drvdata(dev);
+	struct mpcore_wdt *wdt = platform_get_drvdata(pdev);
 	mpcore_wdt_stop(wdt);		/* Turn the WDT off */
 	return 0;
 }
 
-static int mpcore_wdt_resume(struct platform_device *dev)
+static int mpcore_wdt_resume(struct platform_device *pdev)
 {
-	struct mpcore_wdt *wdt = platform_get_drvdata(dev);
+	struct mpcore_wdt *wdt = platform_get_drvdata(pdev);
 	/* re-activate timer */
 	if (test_bit(0, &wdt->timer_alive))
 		mpcore_wdt_start(wdt);
@@ -442,9 +425,6 @@ static struct platform_driver mpcore_wdt_driver = {
 	},
 };
 
-static char banner[] __initdata = KERN_INFO "MPcore Watchdog Timer: 0.1. "
-		"mpcore_noboot=%d mpcore_margin=%d sec (nowayout= %d)\n";
-
 static int __init mpcore_wdt_init(void)
 {
 	/*
@@ -453,11 +433,12 @@ static int __init mpcore_wdt_init(void)
 	 */
 	if (mpcore_wdt_set_heartbeat(mpcore_margin)) {
 		mpcore_wdt_set_heartbeat(TIMER_MARGIN);
-		printk(KERN_INFO "mpcore_margin value must be 0 < mpcore_margin < 65536, using %d\n",
+		pr_info("mpcore_margin value must be 0 < mpcore_margin < 65536, using %d\n",
 			TIMER_MARGIN);
 	}
 
-	printk(banner, mpcore_noboot, mpcore_margin, nowayout);
+	pr_info("MPcore Watchdog Timer: 0.1. mpcore_noboot=%d mpcore_margin=%d sec (nowayout= %d)\n",
+		mpcore_noboot, mpcore_margin, nowayout);
 
 	return platform_driver_register(&mpcore_wdt_driver);
 }
diff --git a/drivers/watchdog/mv64x60_wdt.c b/drivers/watchdog/mv64x60_wdt.c
index 97f8a48d8b78..c53d025e70df 100644
--- a/drivers/watchdog/mv64x60_wdt.c
+++ b/drivers/watchdog/mv64x60_wdt.c
@@ -15,6 +15,8 @@
  * or implied.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -58,8 +60,8 @@ static unsigned int bus_clk;
 static char expect_close;
 static DEFINE_SPINLOCK(mv64x60_wdt_spinlock);
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -100,7 +102,7 @@ static void mv64x60_wdt_handler_enable(void)
 	if (mv64x60_wdt_toggle_wdc(MV64x60_WDC_ENABLED_FALSE,
 				   MV64x60_WDC_ENABLE_SHIFT)) {
 		mv64x60_wdt_service();
-		printk(KERN_NOTICE "mv64x60_wdt: watchdog activated\n");
+		pr_notice("watchdog activated\n");
 	}
 }
 
@@ -108,7 +110,7 @@ static void mv64x60_wdt_handler_disable(void)
 {
 	if (mv64x60_wdt_toggle_wdc(MV64x60_WDC_ENABLED_TRUE,
 				   MV64x60_WDC_ENABLE_SHIFT))
-		printk(KERN_NOTICE "mv64x60_wdt: watchdog deactivated\n");
+		pr_notice("watchdog deactivated\n");
 }
 
 static void mv64x60_wdt_set_timeout(unsigned int timeout)
@@ -139,8 +141,7 @@ static int mv64x60_wdt_release(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		mv64x60_wdt_handler_disable();
 	else {
-		printk(KERN_CRIT
-		       "mv64x60_wdt: unexpected close, not stopping timer!\n");
+		pr_crit("unexpected close, not stopping timer!\n");
 		mv64x60_wdt_service();
 	}
 	expect_close = 0;
@@ -308,7 +309,7 @@ static struct platform_driver mv64x60_wdt_driver = {
 
 static int __init mv64x60_wdt_init(void)
 {
-	printk(KERN_INFO "MV64x60 watchdog driver\n");
+	pr_info("MV64x60 watchdog driver\n");
 
 	return platform_driver_register(&mv64x60_wdt_driver);
 }
diff --git a/drivers/watchdog/nuc900_wdt.c b/drivers/watchdog/nuc900_wdt.c
index 529085b8b8fb..ea4c7448b754 100644
--- a/drivers/watchdog/nuc900_wdt.c
+++ b/drivers/watchdog/nuc900_wdt.c
@@ -55,8 +55,8 @@ module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds. "
 	"(default = " __MODULE_STRING(WDT_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 	"(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
diff --git a/drivers/watchdog/nv_tco.c b/drivers/watchdog/nv_tco.c
index 809f41c30c44..6bbb9efc6125 100644
--- a/drivers/watchdog/nv_tco.c
+++ b/drivers/watchdog/nv_tco.c
@@ -21,6 +21,8 @@
  *	Includes, defines, variables, module parameters, ...
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -41,7 +43,6 @@
 #define TCO_VERSION "0.01"
 #define TCO_MODULE_NAME "NV_TCO"
 #define TCO_DRIVER_NAME   TCO_MODULE_NAME ", v" TCO_VERSION
-#define PFX TCO_MODULE_NAME ": "
 
 /* internal variables */
 static unsigned int tcobase;
@@ -60,8 +61,8 @@ module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds. (2<heartbeat<39, "
 			    "default=" __MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started"
 		" (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -169,8 +170,7 @@ static int nv_tco_release(struct inode *inode, struct file *file)
 	if (tco_expect_close == 42) {
 		tco_timer_stop();
 	} else {
-		printk(KERN_CRIT PFX "Unexpected close, not stopping "
-		       "watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		tco_timer_keepalive();
 	}
 	clear_bit(0, &timer_alive);
@@ -323,15 +323,14 @@ static unsigned char __devinit nv_tco_getdevice(void)
 	val &= 0xffff;
 	if (val == 0x0001 || val == 0x0000) {
 		/* Something is wrong here, bar isn't setup */
-		printk(KERN_ERR PFX "failed to get tcobase address\n");
+		pr_err("failed to get tcobase address\n");
 		return 0;
 	}
 	val &= 0xff00;
 	tcobase = val + 0x40;
 
 	if (!request_region(tcobase, 0x10, "NV TCO")) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-		       tcobase);
+		pr_err("I/O address 0x%04x already in use\n", tcobase);
 		return 0;
 	}
 
@@ -347,7 +346,7 @@ static unsigned char __devinit nv_tco_getdevice(void)
 
 	/* Disable SMI caused by TCO */
 	if (!request_region(MCP51_SMI_EN(tcobase), 4, "NV TCO")) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
+		pr_err("I/O address 0x%04x already in use\n",
 		       MCP51_SMI_EN(tcobase));
 		goto out;
 	}
@@ -357,7 +356,7 @@ static unsigned char __devinit nv_tco_getdevice(void)
 	val = inl(MCP51_SMI_EN(tcobase));
 	release_region(MCP51_SMI_EN(tcobase), 4);
 	if (val & MCP51_SMI_EN_TCO) {
-		printk(KERN_ERR PFX "Could not disable SMI caused by TCO\n");
+		pr_err("Could not disable SMI caused by TCO\n");
 		goto out;
 	}
 
@@ -367,8 +366,7 @@ static unsigned char __devinit nv_tco_getdevice(void)
 	pci_write_config_dword(tco_pci, MCP51_SMBUS_SETUP_B, val);
 	pci_read_config_dword(tco_pci, MCP51_SMBUS_SETUP_B, &val);
 	if (!(val & MCP51_SMBUS_SETUP_B_TCO_REBOOT)) {
-		printk(KERN_ERR PFX "failed to reset NO_REBOOT flag, reboot "
-		       "disabled by hardware\n");
+		pr_err("failed to reset NO_REBOOT flag, reboot disabled by hardware\n");
 		goto out;
 	}
 
@@ -387,8 +385,8 @@ static int __devinit nv_tco_init(struct platform_device *dev)
 		return -ENODEV;
 
 	/* Check to see if last reboot was due to watchdog timeout */
-	printk(KERN_INFO PFX "Watchdog reboot %sdetected.\n",
-	       inl(TCO_STS(tcobase)) & TCO_STS_TCO2TO_STS ? "" : "not ");
+	pr_info("Watchdog reboot %sdetected\n",
+		inl(TCO_STS(tcobase)) & TCO_STS_TCO2TO_STS ? "" : "not ");
 
 	/* Clear out the old status */
 	outl(TCO_STS_RESET, TCO_STS(tcobase));
@@ -400,14 +398,14 @@ static int __devinit nv_tco_init(struct platform_device *dev)
 	if (tco_timer_set_heartbeat(heartbeat)) {
 		heartbeat = WATCHDOG_HEARTBEAT;
 		tco_timer_set_heartbeat(heartbeat);
-		printk(KERN_INFO PFX "heartbeat value must be 2<heartbeat<39, "
-		       "using %d\n", heartbeat);
+		pr_info("heartbeat value must be 2<heartbeat<39, using %d\n",
+			heartbeat);
 	}
 
 	ret = misc_register(&nv_tco_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX "cannot register miscdev on minor=%d "
-		       "(err=%d)\n", WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto unreg_region;
 	}
 
@@ -415,8 +413,8 @@ static int __devinit nv_tco_init(struct platform_device *dev)
 
 	tco_timer_stop();
 
-	printk(KERN_INFO PFX "initialized (0x%04x). heartbeat=%d sec "
-	       "(nowayout=%d)\n", tcobase, heartbeat, nowayout);
+	pr_info("initialized (0x%04x). heartbeat=%d sec (nowayout=%d)\n",
+		tcobase, heartbeat, nowayout);
 
 	return 0;
 
@@ -439,8 +437,7 @@ static void __devexit nv_tco_cleanup(void)
 	pci_write_config_dword(tco_pci, MCP51_SMBUS_SETUP_B, val);
 	pci_read_config_dword(tco_pci, MCP51_SMBUS_SETUP_B, &val);
 	if (val & MCP51_SMBUS_SETUP_B_TCO_REBOOT) {
-		printk(KERN_CRIT PFX "Couldn't unset REBOOT bit.  Machine may "
-		       "soon reset\n");
+		pr_crit("Couldn't unset REBOOT bit.  Machine may soon reset\n");
 	}
 
 	/* Deregister */
@@ -483,8 +480,7 @@ static int __init nv_tco_init_module(void)
 {
 	int err;
 
-	printk(KERN_INFO PFX "NV TCO WatchDog Timer Driver v%s\n",
-	       TCO_VERSION);
+	pr_info("NV TCO WatchDog Timer Driver v%s\n", TCO_VERSION);
 
 	err = platform_driver_register(&nv_tco_driver);
 	if (err)
@@ -508,7 +504,7 @@ static void __exit nv_tco_cleanup_module(void)
 {
 	platform_device_unregister(nv_tco_platform_device);
 	platform_driver_unregister(&nv_tco_driver);
-	printk(KERN_INFO PFX "NV TCO Watchdog Module Unloaded.\n");
+	pr_info("NV TCO Watchdog Module Unloaded\n");
 }
 
 module_init(nv_tco_init_module);
diff --git a/drivers/watchdog/octeon-wdt-main.c b/drivers/watchdog/octeon-wdt-main.c
index 7c0d8630e641..461208831428 100644
--- a/drivers/watchdog/octeon-wdt-main.c
+++ b/drivers/watchdog/octeon-wdt-main.c
@@ -52,6 +52,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/miscdevice.h>
 #include <linux/interrupt.h>
 #include <linux/watchdog.h>
@@ -95,8 +97,8 @@ MODULE_PARM_DESC(heartbeat,
 	"Watchdog heartbeat in seconds. (0 < heartbeat, default="
 				__MODULE_STRING(WD_TIMO) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, S_IRUGO);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, S_IRUGO);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -201,7 +203,7 @@ static void __init octeon_wdt_build_stage1(void)
 	uasm_resolve_relocs(relocs, labels);
 
 	len = (int)(p - nmi_stage1_insns);
-	pr_debug("Synthesized NMI stage 1 handler (%d instructions).\n", len);
+	pr_debug("Synthesized NMI stage 1 handler (%d instructions)\n", len);
 
 	pr_debug("\t.set push\n");
 	pr_debug("\t.set noreorder\n");
@@ -627,7 +629,7 @@ static int octeon_wdt_release(struct inode *inode, struct file *file)
 		do_coundown = 0;
 		octeon_wdt_ping();
 	} else {
-		pr_crit("octeon_wdt: WDT device closed unexpectedly.  WDT will not stop!\n");
+		pr_crit("WDT device closed unexpectedly.  WDT will not stop!\n");
 	}
 	clear_bit(0, &octeon_wdt_is_open);
 	expect_close = 0;
@@ -684,12 +686,12 @@ static int __init octeon_wdt_init(void)
 
 	octeon_wdt_calc_parameters(heartbeat);
 
-	pr_info("octeon_wdt: Initial granularity %d Sec.\n", timeout_sec);
+	pr_info("Initial granularity %d Sec\n", timeout_sec);
 
 	ret = misc_register(&octeon_wdt_miscdev);
 	if (ret) {
-		pr_err("octeon_wdt: cannot register miscdev on minor=%d (err=%d)\n",
-			WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto out;
 	}
 
diff --git a/drivers/watchdog/of_xilinx_wdt.c b/drivers/watchdog/of_xilinx_wdt.c
index f359ab85c3bc..55d2f66dbeae 100644
--- a/drivers/watchdog/of_xilinx_wdt.c
+++ b/drivers/watchdog/of_xilinx_wdt.c
@@ -19,6 +19,8 @@
 *		  know the wdt reset interval
 */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -99,7 +101,7 @@ static void xwdt_stop(void)
 	iowrite32(0, xdev.base + XWT_TWCSR1_OFFSET);
 
 	spin_unlock(&spinlock);
-	printk(KERN_INFO PFX "Stopped!\n");
+	pr_info("Stopped!\n");
 }
 
 static void xwdt_keepalive(void)
@@ -165,7 +167,7 @@ static int xwdt_open(struct inode *inode, struct file *file)
 		__module_get(THIS_MODULE);
 
 	xwdt_start();
-	printk(KERN_INFO PFX "Started...\n");
+	pr_info("Started...\n");
 
 	return nonseekable_open(inode, file);
 }
@@ -175,8 +177,7 @@ static int xwdt_release(struct inode *inode, struct file *file)
 	if (expect_close == 42) {
 		xwdt_stop();
 	} else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		xwdt_keepalive();
 	}
 
@@ -300,22 +301,20 @@ static int __devinit xwdt_probe(struct platform_device *pdev)
 					"clock-frequency", NULL);
 
 	if (pfreq == NULL) {
-		printk(KERN_WARNING PFX
-			"The watchdog clock frequency cannot be obtained!\n");
+		pr_warn("The watchdog clock frequency cannot be obtained!\n");
 		no_timeout = 1;
 	}
 
 	rc = of_address_to_resource(pdev->dev.of_node, 0, &xdev.res);
 	if (rc) {
-		printk(KERN_WARNING PFX "invalid address!\n");
+		pr_warn("invalid address!\n");
 		return rc;
 	}
 
 	tmptr = (u32 *)of_get_property(pdev->dev.of_node,
 					"xlnx,wdt-interval", NULL);
 	if (tmptr == NULL) {
-		printk(KERN_WARNING PFX "Parameter \"xlnx,wdt-interval\""
-					" not found in device tree!\n");
+		pr_warn("Parameter \"xlnx,wdt-interval\" not found in device tree!\n");
 		no_timeout = 1;
 	} else {
 		xdev.wdt_interval = *tmptr;
@@ -324,8 +323,7 @@ static int __devinit xwdt_probe(struct platform_device *pdev)
 	tmptr = (u32 *)of_get_property(pdev->dev.of_node,
 					"xlnx,wdt-enable-once", NULL);
 	if (tmptr == NULL) {
-		printk(KERN_WARNING PFX "Parameter \"xlnx,wdt-enable-once\""
-					" not found in device tree!\n");
+		pr_warn("Parameter \"xlnx,wdt-enable-once\" not found in device tree!\n");
 		xdev.nowayout = WATCHDOG_NOWAYOUT;
 	}
 
@@ -339,20 +337,20 @@ static int __devinit xwdt_probe(struct platform_device *pdev)
 	if (!request_mem_region(xdev.res.start,
 			xdev.res.end - xdev.res.start + 1, WATCHDOG_NAME)) {
 		rc = -ENXIO;
-		printk(KERN_ERR PFX "memory request failure!\n");
+		pr_err("memory request failure!\n");
 		goto err_out;
 	}
 
 	xdev.base = ioremap(xdev.res.start, xdev.res.end - xdev.res.start + 1);
 	if (xdev.base == NULL) {
 		rc = -ENOMEM;
-		printk(KERN_ERR PFX "ioremap failure!\n");
+		pr_err("ioremap failure!\n");
 		goto release_mem;
 	}
 
 	rc = xwdt_selftest();
 	if (rc == XWT_TIMER_FAILED) {
-		printk(KERN_ERR PFX "SelfTest routine error!\n");
+		pr_err("SelfTest routine error!\n");
 		goto unmap_io;
 	}
 
@@ -360,20 +358,17 @@ static int __devinit xwdt_probe(struct platform_device *pdev)
 
 	rc = misc_register(&xwdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						xwdt_miscdev.minor, rc);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       xwdt_miscdev.minor, rc);
 		goto unmap_io;
 	}
 
 	if (no_timeout)
-		printk(KERN_INFO PFX
-			"driver loaded (timeout=? sec, nowayout=%d)\n",
-						    xdev.nowayout);
+		pr_info("driver loaded (timeout=? sec, nowayout=%d)\n",
+			xdev.nowayout);
 	else
-		printk(KERN_INFO PFX
-			"driver loaded (timeout=%d sec, nowayout=%d)\n",
-					timeout, xdev.nowayout);
+		pr_info("driver loaded (timeout=%d sec, nowayout=%d)\n",
+			timeout, xdev.nowayout);
 
 	expect_close = 0;
 	clear_bit(0, &driver_open);
diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c
index d19ff5145e82..8285d65cd207 100644
--- a/drivers/watchdog/omap_wdt.c
+++ b/drivers/watchdog/omap_wdt.c
@@ -26,6 +26,8 @@
  *	Use the driver model and standard identifiers; handle bigger timeouts.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -183,7 +185,7 @@ static int omap_wdt_release(struct inode *inode, struct file *file)
 
 	pm_runtime_put_sync(wdev->dev);
 #else
-	printk(KERN_CRIT "omap_wdt: Unexpected close, not stopping!\n");
+	pr_crit("Unexpected close, not stopping!\n");
 #endif
 	wdev->omap_wdt_users = 0;
 
diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c
index 4ad78f868515..788aa158e78c 100644
--- a/drivers/watchdog/orion_wdt.c
+++ b/drivers/watchdog/orion_wdt.c
@@ -10,6 +10,8 @@
  * warranty of any kind, whether express or implied.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -28,18 +30,19 @@
 /*
  * Watchdog timer block registers.
  */
-#define TIMER_CTRL		(TIMER_VIRT_BASE + 0x0000)
+#define TIMER_CTRL		0x0000
 #define  WDT_EN			0x0010
-#define WDT_VAL			(TIMER_VIRT_BASE + 0x0024)
+#define WDT_VAL			0x0024
 
 #define WDT_MAX_CYCLE_COUNT	0xffffffff
 #define WDT_IN_USE		0
 #define WDT_OK_TO_CLOSE		1
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static int heartbeat = -1;		/* module parameter (seconds) */
 static unsigned int wdt_max_duration;	/* (seconds) */
 static unsigned int wdt_tclk;
+static void __iomem *wdt_reg;
 static unsigned long wdt_status;
 static DEFINE_SPINLOCK(wdt_lock);
 
@@ -48,7 +51,7 @@ static void orion_wdt_ping(void)
 	spin_lock(&wdt_lock);
 
 	/* Reload watchdog duration */
-	writel(wdt_tclk * heartbeat, WDT_VAL);
+	writel(wdt_tclk * heartbeat, wdt_reg + WDT_VAL);
 
 	spin_unlock(&wdt_lock);
 }
@@ -60,7 +63,7 @@ static void orion_wdt_enable(void)
 	spin_lock(&wdt_lock);
 
 	/* Set watchdog duration */
-	writel(wdt_tclk * heartbeat, WDT_VAL);
+	writel(wdt_tclk * heartbeat, wdt_reg + WDT_VAL);
 
 	/* Clear watchdog timer interrupt */
 	reg = readl(BRIDGE_CAUSE);
@@ -68,9 +71,9 @@ static void orion_wdt_enable(void)
 	writel(reg, BRIDGE_CAUSE);
 
 	/* Enable watchdog timer */
-	reg = readl(TIMER_CTRL);
+	reg = readl(wdt_reg + TIMER_CTRL);
 	reg |= WDT_EN;
-	writel(reg, TIMER_CTRL);
+	writel(reg, wdt_reg + TIMER_CTRL);
 
 	/* Enable reset on watchdog */
 	reg = readl(RSTOUTn_MASK);
@@ -92,9 +95,9 @@ static void orion_wdt_disable(void)
 	writel(reg, RSTOUTn_MASK);
 
 	/* Disable watchdog timer */
-	reg = readl(TIMER_CTRL);
+	reg = readl(wdt_reg + TIMER_CTRL);
 	reg &= ~WDT_EN;
-	writel(reg, TIMER_CTRL);
+	writel(reg, wdt_reg + TIMER_CTRL);
 
 	spin_unlock(&wdt_lock);
 }
@@ -102,7 +105,7 @@ static void orion_wdt_disable(void)
 static int orion_wdt_get_timeleft(int *time_left)
 {
 	spin_lock(&wdt_lock);
-	*time_left = readl(WDT_VAL) / wdt_tclk;
+	*time_left = readl(wdt_reg + WDT_VAL) / wdt_tclk;
 	spin_unlock(&wdt_lock);
 	return 0;
 }
@@ -209,8 +212,7 @@ static int orion_wdt_release(struct inode *inode, struct file *file)
 	if (test_bit(WDT_OK_TO_CLOSE, &wdt_status))
 		orion_wdt_disable();
 	else
-		printk(KERN_CRIT "WATCHDOG: Device closed unexpectedly - "
-					"timer will not stop\n");
+		pr_crit("Device closed unexpectedly - timer will not stop\n");
 	clear_bit(WDT_IN_USE, &wdt_status);
 	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
 
@@ -236,15 +238,20 @@ static struct miscdevice orion_wdt_miscdev = {
 static int __devinit orion_wdt_probe(struct platform_device *pdev)
 {
 	struct orion_wdt_platform_data *pdata = pdev->dev.platform_data;
+	struct resource *res;
 	int ret;
 
 	if (pdata) {
 		wdt_tclk = pdata->tclk;
 	} else {
-		printk(KERN_ERR "Orion Watchdog misses platform data\n");
+		pr_err("misses platform data\n");
 		return -ENODEV;
 	}
 
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	wdt_reg = ioremap(res->start, resource_size(res));
+
 	if (orion_wdt_miscdev.parent)
 		return -EBUSY;
 	orion_wdt_miscdev.parent = &pdev->dev;
@@ -257,8 +264,8 @@ static int __devinit orion_wdt_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	printk(KERN_INFO "Orion Watchdog Timer: Initial timeout %d sec%s\n",
-				heartbeat, nowayout ? ", nowayout" : "");
+	pr_info("Initial timeout %d sec%s\n",
+		heartbeat, nowayout ? ", nowayout" : "");
 	return 0;
 }
 
@@ -302,7 +309,7 @@ MODULE_DESCRIPTION("Orion Processor Watchdog");
 module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Initial watchdog heartbeat in seconds");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
diff --git a/drivers/watchdog/pc87413_wdt.c b/drivers/watchdog/pc87413_wdt.c
index e78d89986768..5afb89b48650 100644
--- a/drivers/watchdog/pc87413_wdt.c
+++ b/drivers/watchdog/pc87413_wdt.c
@@ -18,6 +18,8 @@
  *      Release 1.1
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
@@ -33,7 +35,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 /* #define DEBUG 1 */
 
@@ -42,7 +43,6 @@
 
 #define VERSION             "1.1"
 #define MODNAME             "pc87413 WDT"
-#define PFX                 MODNAME ": "
 #define DPFX                MODNAME " - DEBUG: "
 
 #define WDT_INDEX_IO_PORT   (io+0)	/* I/O port base (index register) */
@@ -65,7 +65,7 @@ static char expect_close;		/* is the close expected? */
 
 static DEFINE_SPINLOCK(io_lock);	/* to guard us from io races */
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 /* -- Low level function ----------------------------------------*/
 
@@ -87,7 +87,7 @@ static inline void pc87413_select_wdt_out(void)
 	outb_p(cr_data, WDT_DATA_IO_PORT);
 
 #ifdef DEBUG
-	printk(KERN_INFO DPFX
+	pr_info(DPFX
 		"Select multiple pin,pin55,as WDT output: Bit7 to 1: %d\n",
 								cr_data);
 #endif
@@ -111,7 +111,7 @@ static inline void pc87413_enable_swc(void)
 	outb_p(cr_data, WDT_DATA_IO_PORT);	/* Index0x30_bit0P1 */
 
 #ifdef DEBUG
-	printk(KERN_INFO DPFX "pc87413 - Enable SWC functions\n");
+	pr_info(DPFX "pc87413 - Enable SWC functions\n");
 #endif
 }
 
@@ -132,7 +132,7 @@ static void pc87413_get_swc_base_addr(void)
 
 	swc_base_addr = (addr_h << 8) + addr_l;
 #ifdef DEBUG
-	printk(KERN_INFO DPFX
+	pr_info(DPFX
 		"Read SWC I/O Base Address: low %d, high %d, res %d\n",
 						addr_l, addr_h, swc_base_addr);
 #endif
@@ -145,7 +145,7 @@ static inline void pc87413_swc_bank3(void)
 	/* Step 4: Select Bank3 of SWC */
 	outb_p(inb(swc_base_addr + 0x0f) | 0x03, swc_base_addr + 0x0f);
 #ifdef DEBUG
-	printk(KERN_INFO DPFX "Select Bank3 of SWC\n");
+	pr_info(DPFX "Select Bank3 of SWC\n");
 #endif
 }
 
@@ -156,7 +156,7 @@ static inline void pc87413_programm_wdto(char pc87413_time)
 	/* Step 5: Programm WDTO, Twd. */
 	outb_p(pc87413_time, swc_base_addr + WDTO);
 #ifdef DEBUG
-	printk(KERN_INFO DPFX "Set WDTO to %d minutes\n", pc87413_time);
+	pr_info(DPFX "Set WDTO to %d minutes\n", pc87413_time);
 #endif
 }
 
@@ -167,7 +167,7 @@ static inline void pc87413_enable_wden(void)
 	/* Step 6: Enable WDEN */
 	outb_p(inb(swc_base_addr + WDCTL) | 0x01, swc_base_addr + WDCTL);
 #ifdef DEBUG
-	printk(KERN_INFO DPFX "Enable WDEN\n");
+	pr_info(DPFX "Enable WDEN\n");
 #endif
 }
 
@@ -177,7 +177,7 @@ static inline void pc87413_enable_sw_wd_tren(void)
 	/* Enable SW_WD_TREN */
 	outb_p(inb(swc_base_addr + WDCFG) | 0x80, swc_base_addr + WDCFG);
 #ifdef DEBUG
-	printk(KERN_INFO DPFX "Enable SW_WD_TREN\n");
+	pr_info(DPFX "Enable SW_WD_TREN\n");
 #endif
 }
 
@@ -188,7 +188,7 @@ static inline void pc87413_disable_sw_wd_tren(void)
 	/* Disable SW_WD_TREN */
 	outb_p(inb(swc_base_addr + WDCFG) & 0x7f, swc_base_addr + WDCFG);
 #ifdef DEBUG
-	printk(KERN_INFO DPFX "pc87413 - Disable SW_WD_TREN\n");
+	pr_info(DPFX "pc87413 - Disable SW_WD_TREN\n");
 #endif
 }
 
@@ -199,7 +199,7 @@ static inline void pc87413_enable_sw_wd_trg(void)
 	/* Enable SW_WD_TRG */
 	outb_p(inb(swc_base_addr + WDCTL) | 0x80, swc_base_addr + WDCTL);
 #ifdef DEBUG
-	printk(KERN_INFO DPFX "pc87413 - Enable SW_WD_TRG\n");
+	pr_info(DPFX "pc87413 - Enable SW_WD_TRG\n");
 #endif
 }
 
@@ -210,7 +210,7 @@ static inline void pc87413_disable_sw_wd_trg(void)
 	/* Disable SW_WD_TRG */
 	outb_p(inb(swc_base_addr + WDCTL) & 0x7f, swc_base_addr + WDCTL);
 #ifdef DEBUG
-	printk(KERN_INFO DPFX "Disable SW_WD_TRG\n");
+	pr_info(DPFX "Disable SW_WD_TRG\n");
 #endif
 }
 
@@ -284,8 +284,7 @@ static int pc87413_open(struct inode *inode, struct file *file)
 	/* Reload and activate timer */
 	pc87413_refresh();
 
-	printk(KERN_INFO MODNAME
-		"Watchdog enabled. Timeout set to %d minute(s).\n", timeout);
+	pr_info("Watchdog enabled. Timeout set to %d minute(s).\n", timeout);
 
 	return nonseekable_open(inode, file);
 }
@@ -308,11 +307,9 @@ static int pc87413_release(struct inode *inode, struct file *file)
 
 	if (expect_close == 42) {
 		pc87413_disable();
-		printk(KERN_INFO MODNAME
-				"Watchdog disabled, sleeping again...\n");
+		pr_info("Watchdog disabled, sleeping again...\n");
 	} else {
-		printk(KERN_CRIT MODNAME
-				"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		pc87413_refresh();
 	}
 	clear_bit(0, &timer_enabled);
@@ -428,7 +425,7 @@ static long pc87413_ioctl(struct file *file, unsigned int cmd,
 	case WDIOC_KEEPALIVE:
 		pc87413_refresh();
 #ifdef DEBUG
-		printk(KERN_INFO DPFX "keepalive\n");
+		pr_info(DPFX "keepalive\n");
 #endif
 		return 0;
 	case WDIOC_SETTIMEOUT:
@@ -508,7 +505,7 @@ static int __init pc87413_init(void)
 {
 	int ret;
 
-	printk(KERN_INFO PFX "Version " VERSION " at io 0x%X\n",
+	pr_info("Version " VERSION " at io 0x%X\n",
 							WDT_INDEX_IO_PORT);
 
 	if (!request_muxed_region(io, 2, MODNAME))
@@ -516,26 +513,23 @@ static int __init pc87413_init(void)
 
 	ret = register_reboot_notifier(&pc87413_notifier);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 	}
 
 	ret = misc_register(&pc87413_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-			WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto reboot_unreg;
 	}
-	printk(KERN_INFO PFX "initialized. timeout=%d min \n", timeout);
+	pr_info("initialized. timeout=%d min\n", timeout);
 
 	pc87413_select_wdt_out();
 	pc87413_enable_swc();
 	pc87413_get_swc_base_addr();
 
 	if (!request_region(swc_base_addr, 0x20, MODNAME)) {
-		printk(KERN_ERR PFX
-			"cannot request SWC region at 0x%x\n", swc_base_addr);
+		pr_err("cannot request SWC region at 0x%x\n", swc_base_addr);
 		ret = -EBUSY;
 		goto misc_unreg;
 	}
@@ -568,14 +562,14 @@ static void __exit pc87413_exit(void)
 	/* Stop the timer before we leave */
 	if (!nowayout) {
 		pc87413_disable();
-		printk(KERN_INFO MODNAME "Watchdog disabled.\n");
+		pr_info("Watchdog disabled\n");
 	}
 
 	misc_deregister(&pc87413_miscdev);
 	unregister_reboot_notifier(&pc87413_notifier);
 	release_region(swc_base_addr, 0x20);
 
-	printk(KERN_INFO MODNAME " watchdog component driver removed.\n");
+	pr_info("watchdog component driver removed\n");
 }
 
 module_init(pc87413_init);
@@ -597,7 +591,7 @@ MODULE_PARM_DESC(timeout,
 		"Watchdog timeout in minutes (default="
 				__MODULE_STRING(DEFAULT_TIMEOUT) ").");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
diff --git a/drivers/watchdog/pcwd.c b/drivers/watchdog/pcwd.c
index 06f7922606c0..75694cf24f86 100644
--- a/drivers/watchdog/pcwd.c
+++ b/drivers/watchdog/pcwd.c
@@ -51,6 +51,8 @@
  *	http://www.pcwatchdog.com/
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>	/* For module specific items */
 #include <linux/moduleparam.h>	/* For new moduleparam's */
 #include <linux/types.h>	/* For standard types (like size_t) */
@@ -75,7 +77,6 @@
 #define WATCHDOG_DATE "18 Feb 2007"
 #define WATCHDOG_DRIVER_NAME "ISA-PC Watchdog"
 #define WATCHDOG_NAME "pcwd"
-#define PFX WATCHDOG_NAME ": "
 #define DRIVER_VERSION WATCHDOG_DRIVER_NAME " driver, v" WATCHDOG_VERSION "\n"
 
 /*
@@ -203,8 +204,8 @@ MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds. "
 	"(2 <= heartbeat <= 7200 or 0=delay-time from dip-switches, default="
 				__MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -220,8 +221,7 @@ static int send_isa_command(int cmd)
 	int port0, last_port0;	/* Double read for stabilising */
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "sending following data cmd=0x%02x\n",
-			cmd);
+		pr_debug("sending following data cmd=0x%02x\n", cmd);
 
 	/* The WCMD bit must be 1 and the command is only 4 bits in size */
 	control_status = (cmd & 0x0F) | WD_WCMD;
@@ -240,9 +240,8 @@ static int send_isa_command(int cmd)
 	}
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "received following data for "
-			"cmd=0x%02x: port0=0x%02x last_port0=0x%02x\n",
-			cmd, port0, last_port0);
+		pr_debug("received following data for cmd=0x%02x: port0=0x%02x last_port0=0x%02x\n",
+			 cmd, port0, last_port0);
 
 	return port0;
 }
@@ -271,8 +270,7 @@ static int set_command_mode(void)
 	pcwd_private.command_mode = found;
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "command_mode=%d\n",
-				pcwd_private.command_mode);
+		pr_debug("command_mode=%d\n", pcwd_private.command_mode);
 
 	return found;
 }
@@ -288,8 +286,7 @@ static void unset_command_mode(void)
 	pcwd_private.command_mode = 0;
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "command_mode=%d\n",
-				pcwd_private.command_mode);
+		pr_debug("command_mode=%d\n", pcwd_private.command_mode);
 }
 
 static inline void pcwd_check_temperature_support(void)
@@ -336,17 +333,14 @@ static void pcwd_show_card_info(void)
 
 	/* Get some extra info from the hardware (in command/debug/diag mode) */
 	if (pcwd_private.revision == PCWD_REVISION_A)
-		printk(KERN_INFO PFX
-			"ISA-PC Watchdog (REV.A) detected at port 0x%04x\n",
-							pcwd_private.io_addr);
+		pr_info("ISA-PC Watchdog (REV.A) detected at port 0x%04x\n",
+			pcwd_private.io_addr);
 	else if (pcwd_private.revision == PCWD_REVISION_C) {
 		pcwd_get_firmware();
-		printk(KERN_INFO PFX "ISA-PC Watchdog (REV.C) detected at port "
-			"0x%04x (Firmware version: %s)\n",
+		pr_info("ISA-PC Watchdog (REV.C) detected at port 0x%04x (Firmware version: %s)\n",
 			pcwd_private.io_addr, pcwd_private.fw_ver_str);
 		option_switches = pcwd_get_option_switches();
-		printk(KERN_INFO PFX "Option switches (0x%02x): "
-			"Temperature Reset Enable=%s, Power On Delay=%s\n",
+		pr_info("Option switches (0x%02x): Temperature Reset Enable=%s, Power On Delay=%s\n",
 			option_switches,
 			((option_switches & 0x10) ? "ON" : "OFF"),
 			((option_switches & 0x08) ? "ON" : "OFF"));
@@ -359,22 +353,18 @@ static void pcwd_show_card_info(void)
 	}
 
 	if (pcwd_private.supports_temp)
-		printk(KERN_INFO PFX "Temperature Option Detected\n");
+		pr_info("Temperature Option Detected\n");
 
 	if (pcwd_private.boot_status & WDIOF_CARDRESET)
-		printk(KERN_INFO PFX
-			"Previous reboot was caused by the card\n");
+		pr_info("Previous reboot was caused by the card\n");
 
 	if (pcwd_private.boot_status & WDIOF_OVERHEAT) {
-		printk(KERN_EMERG PFX
-			"Card senses a CPU Overheat. Panicking!\n");
-		printk(KERN_EMERG PFX
-			"CPU Overheat\n");
+		pr_emerg("Card senses a CPU Overheat. Panicking!\n");
+		pr_emerg("CPU Overheat\n");
 	}
 
 	if (pcwd_private.boot_status == 0)
-		printk(KERN_INFO PFX
-			"No previous trip detected - Cold boot or reset\n");
+		pr_info("No previous trip detected - Cold boot or reset\n");
 }
 
 static void pcwd_timer_ping(unsigned long data)
@@ -404,8 +394,7 @@ static void pcwd_timer_ping(unsigned long data)
 
 		spin_unlock(&pcwd_private.io_lock);
 	} else {
-		printk(KERN_WARNING PFX
-			"Heartbeat lost! Will not ping the watchdog\n");
+		pr_warn("Heartbeat lost! Will not ping the watchdog\n");
 	}
 }
 
@@ -426,13 +415,13 @@ static int pcwd_start(void)
 		stat_reg = inb_p(pcwd_private.io_addr + 2);
 		spin_unlock(&pcwd_private.io_lock);
 		if (stat_reg & WD_WDIS) {
-			printk(KERN_INFO PFX "Could not start watchdog\n");
+			pr_info("Could not start watchdog\n");
 			return -EIO;
 		}
 	}
 
 	if (debug >= VERBOSE)
-		printk(KERN_DEBUG PFX "Watchdog started\n");
+		pr_debug("Watchdog started\n");
 
 	return 0;
 }
@@ -454,13 +443,13 @@ static int pcwd_stop(void)
 		stat_reg = inb_p(pcwd_private.io_addr + 2);
 		spin_unlock(&pcwd_private.io_lock);
 		if ((stat_reg & WD_WDIS) == 0) {
-			printk(KERN_INFO PFX "Could not stop watchdog\n");
+			pr_info("Could not stop watchdog\n");
 			return -EIO;
 		}
 	}
 
 	if (debug >= VERBOSE)
-		printk(KERN_DEBUG PFX "Watchdog stopped\n");
+		pr_debug("Watchdog stopped\n");
 
 	return 0;
 }
@@ -471,7 +460,7 @@ static int pcwd_keepalive(void)
 	pcwd_private.next_heartbeat = jiffies + (heartbeat * HZ);
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "Watchdog keepalive signal send\n");
+		pr_debug("Watchdog keepalive signal send\n");
 
 	return 0;
 }
@@ -484,8 +473,7 @@ static int pcwd_set_heartbeat(int t)
 	heartbeat = t;
 
 	if (debug >= VERBOSE)
-		printk(KERN_DEBUG PFX "New heartbeat: %d\n",
-		       heartbeat);
+		pr_debug("New heartbeat: %d\n", heartbeat);
 
 	return 0;
 }
@@ -518,8 +506,7 @@ static int pcwd_get_status(int *status)
 		if (control_status & WD_T110) {
 			*status |= WDIOF_OVERHEAT;
 			if (temp_panic) {
-				printk(KERN_INFO PFX
-					"Temperature overheat trip!\n");
+				pr_info("Temperature overheat trip!\n");
 				kernel_power_off();
 			}
 		}
@@ -530,8 +517,7 @@ static int pcwd_get_status(int *status)
 		if (control_status & WD_REVC_TTRP) {
 			*status |= WDIOF_OVERHEAT;
 			if (temp_panic) {
-				printk(KERN_INFO PFX
-					"Temperature overheat trip!\n");
+				pr_info("Temperature overheat trip!\n");
 				kernel_power_off();
 			}
 		}
@@ -548,16 +534,14 @@ static int pcwd_clear_status(void)
 		spin_lock(&pcwd_private.io_lock);
 
 		if (debug >= VERBOSE)
-			printk(KERN_INFO PFX
-					"clearing watchdog trip status\n");
+			pr_info("clearing watchdog trip status\n");
 
 		control_status = inb_p(pcwd_private.io_addr + 1);
 
 		if (debug >= DEBUG) {
-			printk(KERN_DEBUG PFX "status was: 0x%02x\n",
-				control_status);
-			printk(KERN_DEBUG PFX "sending: 0x%02x\n",
-				(control_status & WD_REVC_R2DS));
+			pr_debug("status was: 0x%02x\n", control_status);
+			pr_debug("sending: 0x%02x\n",
+				 (control_status & WD_REVC_R2DS));
 		}
 
 		/* clear reset status & Keep Relay 2 disable state as it is */
@@ -588,8 +572,7 @@ static int pcwd_get_temperature(int *temperature)
 	spin_unlock(&pcwd_private.io_lock);
 
 	if (debug >= DEBUG) {
-		printk(KERN_DEBUG PFX "temperature is: %d F\n",
-			*temperature);
+		pr_debug("temperature is: %d F\n", *temperature);
 	}
 
 	return 0;
@@ -720,8 +703,7 @@ static int pcwd_close(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		pcwd_stop();
 	else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		pcwd_keepalive();
 	}
 	expect_close = 0;
@@ -828,11 +810,10 @@ static int __devinit pcwd_isa_match(struct device *dev, unsigned int id)
 	int retval;
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "pcwd_isa_match id=%d\n",
-			id);
+		pr_debug("pcwd_isa_match id=%d\n", id);
 
 	if (!request_region(base_addr, 4, "PCWD")) {
-		printk(KERN_INFO PFX "Port 0x%04x unavailable\n", base_addr);
+		pr_info("Port 0x%04x unavailable\n", base_addr);
 		return 0;
 	}
 
@@ -870,21 +851,20 @@ static int __devinit pcwd_isa_probe(struct device *dev, unsigned int id)
 	int ret;
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "pcwd_isa_probe id=%d\n",
-			id);
+		pr_debug("pcwd_isa_probe id=%d\n", id);
 
 	cards_found++;
 	if (cards_found == 1)
-		printk(KERN_INFO PFX "v%s Ken Hollis (kenji@bitgate.com)\n",
+		pr_info("v%s Ken Hollis (kenji@bitgate.com)\n",
 							WATCHDOG_VERSION);
 
 	if (cards_found > 1) {
-		printk(KERN_ERR PFX "This driver only supports 1 device\n");
+		pr_err("This driver only supports 1 device\n");
 		return -ENODEV;
 	}
 
 	if (pcwd_ioports[id] == 0x0000) {
-		printk(KERN_ERR PFX "No I/O-Address for card detected\n");
+		pr_err("No I/O-Address for card detected\n");
 		return -ENODEV;
 	}
 	pcwd_private.io_addr = pcwd_ioports[id];
@@ -896,8 +876,8 @@ static int __devinit pcwd_isa_probe(struct device *dev, unsigned int id)
 
 	if (!request_region(pcwd_private.io_addr,
 		(pcwd_private.revision == PCWD_REVISION_A) ? 2 : 4, "PCWD")) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			pcwd_private.io_addr);
+		pr_err("I/O address 0x%04x already in use\n",
+		       pcwd_private.io_addr);
 		ret = -EIO;
 		goto error_request_region;
 	}
@@ -932,30 +912,27 @@ static int __devinit pcwd_isa_probe(struct device *dev, unsigned int id)
 	   if not reset to the default */
 	if (pcwd_set_heartbeat(heartbeat)) {
 		pcwd_set_heartbeat(WATCHDOG_HEARTBEAT);
-		printk(KERN_INFO PFX
-		  "heartbeat value must be 2 <= heartbeat <= 7200, using %d\n",
-							WATCHDOG_HEARTBEAT);
+		pr_info("heartbeat value must be 2 <= heartbeat <= 7200, using %d\n",
+			WATCHDOG_HEARTBEAT);
 	}
 
 	if (pcwd_private.supports_temp) {
 		ret = misc_register(&temp_miscdev);
 		if (ret) {
-			printk(KERN_ERR PFX
-			    "cannot register miscdev on minor=%d (err=%d)\n",
-							TEMP_MINOR, ret);
+			pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+			       TEMP_MINOR, ret);
 			goto error_misc_register_temp;
 		}
 	}
 
 	ret = misc_register(&pcwd_miscdev);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-					WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto error_misc_register_watchdog;
 	}
 
-	printk(KERN_INFO PFX "initialized. heartbeat=%d sec (nowayout=%d)\n",
+	pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n",
 		heartbeat, nowayout);
 
 	return 0;
@@ -975,8 +952,7 @@ error_request_region:
 static int __devexit pcwd_isa_remove(struct device *dev, unsigned int id)
 {
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "pcwd_isa_remove id=%d\n",
-			id);
+		pr_debug("pcwd_isa_remove id=%d\n", id);
 
 	if (!pcwd_private.io_addr)
 		return 1;
@@ -1000,8 +976,7 @@ static int __devexit pcwd_isa_remove(struct device *dev, unsigned int id)
 static void pcwd_isa_shutdown(struct device *dev, unsigned int id)
 {
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "pcwd_isa_shutdown id=%d\n",
-			id);
+		pr_debug("pcwd_isa_shutdown id=%d\n", id);
 
 	pcwd_stop();
 }
@@ -1025,7 +1000,7 @@ static int __init pcwd_init_module(void)
 static void __exit pcwd_cleanup_module(void)
 {
 	isa_unregister_driver(&pcwd_isa_driver);
-	printk(KERN_INFO PFX "Watchdog Module Unloaded.\n");
+	pr_info("Watchdog Module Unloaded\n");
 }
 
 module_init(pcwd_init_module);
diff --git a/drivers/watchdog/pcwd_pci.c b/drivers/watchdog/pcwd_pci.c
index b8d14f88f0b5..c891399bed6a 100644
--- a/drivers/watchdog/pcwd_pci.c
+++ b/drivers/watchdog/pcwd_pci.c
@@ -32,6 +32,8 @@
  *	Includes, defines, variables, module parameters, ...
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>	/* For module specific items */
 #include <linux/moduleparam.h>	/* For new moduleparam's */
 #include <linux/types.h>	/* For standard types (like size_t) */
@@ -54,8 +56,7 @@
 #define WATCHDOG_VERSION "1.03"
 #define WATCHDOG_DRIVER_NAME "PCI-PC Watchdog"
 #define WATCHDOG_NAME "pcwd_pci"
-#define PFX WATCHDOG_NAME ": "
-#define DRIVER_VERSION WATCHDOG_DRIVER_NAME " driver, v" WATCHDOG_VERSION "\n"
+#define DRIVER_VERSION WATCHDOG_DRIVER_NAME " driver, v" WATCHDOG_VERSION
 
 /* Stuff for the PCI ID's  */
 #ifndef PCI_VENDOR_ID_QUICKLOGIC
@@ -145,8 +146,8 @@ MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds. "
 	"(0<heartbeat<65536 or 0=delay-time from dip-switches, default="
 				__MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 					__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -159,8 +160,8 @@ static int send_command(int cmd, int *msb, int *lsb)
 	int got_response, count;
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "sending following data "
-		"cmd=0x%02x msb=0x%02x lsb=0x%02x\n", cmd, *msb, *lsb);
+		pr_debug("sending following data cmd=0x%02x msb=0x%02x lsb=0x%02x\n",
+			 cmd, *msb, *lsb);
 
 	spin_lock(&pcipcwd_private.io_lock);
 	/* If a command requires data it should be written first.
@@ -185,12 +186,10 @@ static int send_command(int cmd, int *msb, int *lsb)
 
 	if (debug >= DEBUG) {
 		if (got_response) {
-			printk(KERN_DEBUG PFX
-				"time to process command was: %d ms\n",
-				count);
+			pr_debug("time to process command was: %d ms\n",
+				 count);
 		} else {
-			printk(KERN_DEBUG PFX
-				"card did not respond on command!\n");
+			pr_debug("card did not respond on command!\n");
 		}
 	}
 
@@ -203,9 +202,8 @@ static int send_command(int cmd, int *msb, int *lsb)
 		inb_p(pcipcwd_private.io_addr + 6);
 
 		if (debug >= DEBUG)
-			printk(KERN_DEBUG PFX "received following data for "
-				"cmd=0x%02x: msb=0x%02x lsb=0x%02x\n",
-				cmd, *msb, *lsb);
+			pr_debug("received following data for cmd=0x%02x: msb=0x%02x lsb=0x%02x\n",
+				 cmd, *msb, *lsb);
 	}
 
 	spin_unlock(&pcipcwd_private.io_lock);
@@ -243,27 +241,23 @@ static void pcipcwd_show_card_info(void)
 	/* Get switch settings */
 	option_switches = pcipcwd_get_option_switches();
 
-	printk(KERN_INFO PFX "Found card at port "
-		"0x%04x (Firmware: %s) %s temp option\n",
+	pr_info("Found card at port 0x%04x (Firmware: %s) %s temp option\n",
 		(int) pcipcwd_private.io_addr, fw_ver_str,
 		(pcipcwd_private.supports_temp ? "with" : "without"));
 
-	printk(KERN_INFO PFX "Option switches (0x%02x): "
-		"Temperature Reset Enable=%s, Power On Delay=%s\n",
+	pr_info("Option switches (0x%02x): Temperature Reset Enable=%s, Power On Delay=%s\n",
 		option_switches,
 		((option_switches & 0x10) ? "ON" : "OFF"),
 		((option_switches & 0x08) ? "ON" : "OFF"));
 
 	if (pcipcwd_private.boot_status & WDIOF_CARDRESET)
-		printk(KERN_INFO PFX
-			"Previous reset was caused by the Watchdog card\n");
+		pr_info("Previous reset was caused by the Watchdog card\n");
 
 	if (pcipcwd_private.boot_status & WDIOF_OVERHEAT)
-		printk(KERN_INFO PFX "Card sensed a CPU Overheat\n");
+		pr_info("Card sensed a CPU Overheat\n");
 
 	if (pcipcwd_private.boot_status == 0)
-		printk(KERN_INFO PFX
-			"No previous trip detected - Cold boot or reset\n");
+		pr_info("No previous trip detected - Cold boot or reset\n");
 }
 
 static int pcipcwd_start(void)
@@ -278,12 +272,12 @@ static int pcipcwd_start(void)
 	spin_unlock(&pcipcwd_private.io_lock);
 
 	if (stat_reg & WD_PCI_WDIS) {
-		printk(KERN_ERR PFX "Card timer not enabled\n");
+		pr_err("Card timer not enabled\n");
 		return -1;
 	}
 
 	if (debug >= VERBOSE)
-		printk(KERN_DEBUG PFX "Watchdog started\n");
+		pr_debug("Watchdog started\n");
 
 	return 0;
 }
@@ -303,13 +297,12 @@ static int pcipcwd_stop(void)
 	spin_unlock(&pcipcwd_private.io_lock);
 
 	if (!(stat_reg & WD_PCI_WDIS)) {
-		printk(KERN_ERR PFX
-			"Card did not acknowledge disable attempt\n");
+		pr_err("Card did not acknowledge disable attempt\n");
 		return -1;
 	}
 
 	if (debug >= VERBOSE)
-		printk(KERN_DEBUG PFX "Watchdog stopped\n");
+		pr_debug("Watchdog stopped\n");
 
 	return 0;
 }
@@ -322,7 +315,7 @@ static int pcipcwd_keepalive(void)
 	spin_unlock(&pcipcwd_private.io_lock);
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "Watchdog keepalive signal send\n");
+		pr_debug("Watchdog keepalive signal send\n");
 
 	return 0;
 }
@@ -340,8 +333,7 @@ static int pcipcwd_set_heartbeat(int t)
 
 	heartbeat = t;
 	if (debug >= VERBOSE)
-		printk(KERN_DEBUG PFX "New heartbeat: %d\n",
-		       heartbeat);
+		pr_debug("New heartbeat: %d\n", heartbeat);
 
 	return 0;
 }
@@ -357,12 +349,11 @@ static int pcipcwd_get_status(int *status)
 	if (control_status & WD_PCI_TTRP) {
 		*status |= WDIOF_OVERHEAT;
 		if (temp_panic)
-			panic(PFX "Temperature overheat trip!\n");
+			panic(KBUILD_MODNAME ": Temperature overheat trip!\n");
 	}
 
 	if (debug >= DEBUG)
-		printk(KERN_DEBUG PFX "Control Status #1: 0x%02x\n",
-		       control_status);
+		pr_debug("Control Status #1: 0x%02x\n", control_status);
 
 	return 0;
 }
@@ -374,14 +365,14 @@ static int pcipcwd_clear_status(void)
 	int reset_counter;
 
 	if (debug >= VERBOSE)
-		printk(KERN_INFO PFX "clearing watchdog trip status & LED\n");
+		pr_info("clearing watchdog trip status & LED\n");
 
 	control_status = inb_p(pcipcwd_private.io_addr + 1);
 
 	if (debug >= DEBUG) {
-		printk(KERN_DEBUG PFX "status was: 0x%02x\n", control_status);
-		printk(KERN_DEBUG PFX "sending: 0x%02x\n",
-		       (control_status & WD_PCI_R2DS) | WD_PCI_WTRP);
+		pr_debug("status was: 0x%02x\n", control_status);
+		pr_debug("sending: 0x%02x\n",
+			 (control_status & WD_PCI_R2DS) | WD_PCI_WTRP);
 	}
 
 	/* clear trip status & LED and keep mode of relay 2 */
@@ -394,8 +385,7 @@ static int pcipcwd_clear_status(void)
 	send_command(CMD_GET_CLEAR_RESET_COUNT, &msb, &reset_counter);
 
 	if (debug >= DEBUG) {
-		printk(KERN_DEBUG PFX "reset count was: 0x%02x\n",
-		       reset_counter);
+		pr_debug("reset count was: 0x%02x\n", reset_counter);
 	}
 
 	return 0;
@@ -418,8 +408,7 @@ static int pcipcwd_get_temperature(int *temperature)
 	*temperature = (*temperature * 9 / 5) + 32;
 
 	if (debug >= DEBUG) {
-		printk(KERN_DEBUG PFX "temperature is: %d F\n",
-		       *temperature);
+		pr_debug("temperature is: %d F\n", *temperature);
 	}
 
 	return 0;
@@ -437,8 +426,7 @@ static int pcipcwd_get_timeleft(int *time_left)
 	*time_left = (msb << 8) + lsb;
 
 	if (debug >= VERBOSE)
-		printk(KERN_DEBUG PFX "Time left before next reboot: %d\n",
-		       *time_left);
+		pr_debug("Time left before next reboot: %d\n", *time_left);
 
 	return 0;
 }
@@ -583,8 +571,7 @@ static int pcipcwd_open(struct inode *inode, struct file *file)
 	/* /dev/watchdog can only be opened once */
 	if (test_and_set_bit(0, &is_active)) {
 		if (debug >= VERBOSE)
-			printk(KERN_ERR PFX
-				"Attempt to open already opened device.\n");
+			pr_err("Attempt to open already opened device\n");
 		return -EBUSY;
 	}
 
@@ -602,8 +589,7 @@ static int pcipcwd_release(struct inode *inode, struct file *file)
 	if (expect_release == 42) {
 		pcipcwd_stop();
 	} else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		pcipcwd_keepalive();
 	}
 	expect_release = 0;
@@ -703,20 +689,20 @@ static int __devinit pcipcwd_card_init(struct pci_dev *pdev,
 
 	cards_found++;
 	if (cards_found == 1)
-		printk(KERN_INFO PFX DRIVER_VERSION);
+		pr_info("%s\n", DRIVER_VERSION);
 
 	if (cards_found > 1) {
-		printk(KERN_ERR PFX "This driver only supports 1 device\n");
+		pr_err("This driver only supports 1 device\n");
 		return -ENODEV;
 	}
 
 	if (pci_enable_device(pdev)) {
-		printk(KERN_ERR PFX "Not possible to enable PCI Device\n");
+		pr_err("Not possible to enable PCI Device\n");
 		return -ENODEV;
 	}
 
 	if (pci_resource_start(pdev, 0) == 0x0000) {
-		printk(KERN_ERR PFX "No I/O-Address for card detected\n");
+		pr_err("No I/O-Address for card detected\n");
 		ret = -ENODEV;
 		goto err_out_disable_device;
 	}
@@ -725,8 +711,8 @@ static int __devinit pcipcwd_card_init(struct pci_dev *pdev,
 	pcipcwd_private.io_addr = pci_resource_start(pdev, 0);
 
 	if (pci_request_regions(pdev, WATCHDOG_NAME)) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			(int) pcipcwd_private.io_addr);
+		pr_err("I/O address 0x%04x already in use\n",
+		       (int) pcipcwd_private.io_addr);
 		ret = -EIO;
 		goto err_out_disable_device;
 	}
@@ -755,36 +741,33 @@ static int __devinit pcipcwd_card_init(struct pci_dev *pdev,
 	 * if not reset to the default */
 	if (pcipcwd_set_heartbeat(heartbeat)) {
 		pcipcwd_set_heartbeat(WATCHDOG_HEARTBEAT);
-		printk(KERN_INFO PFX
-			"heartbeat value must be 0<heartbeat<65536, using %d\n",
+		pr_info("heartbeat value must be 0<heartbeat<65536, using %d\n",
 			WATCHDOG_HEARTBEAT);
 	}
 
 	ret = register_reboot_notifier(&pcipcwd_notifier);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto err_out_release_region;
 	}
 
 	if (pcipcwd_private.supports_temp) {
 		ret = misc_register(&pcipcwd_temp_miscdev);
 		if (ret != 0) {
-			printk(KERN_ERR PFX "cannot register miscdev on "
-				"minor=%d (err=%d)\n", TEMP_MINOR, ret);
+			pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+			       TEMP_MINOR, ret);
 			goto err_out_unregister_reboot;
 		}
 	}
 
 	ret = misc_register(&pcipcwd_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-			WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto err_out_misc_deregister;
 	}
 
-	printk(KERN_INFO PFX "initialized. heartbeat=%d sec (nowayout=%d)\n",
+	pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n",
 		heartbeat, nowayout);
 
 	return 0;
@@ -842,7 +825,7 @@ static void __exit pcipcwd_cleanup_module(void)
 {
 	pci_unregister_driver(&pcipcwd_driver);
 
-	printk(KERN_INFO PFX "Watchdog Module Unloaded.\n");
+	pr_info("Watchdog Module Unloaded\n");
 }
 
 module_init(pcipcwd_init_module);
diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c
index d8de1ddd176a..7b14d1847927 100644
--- a/drivers/watchdog/pcwd_usb.c
+++ b/drivers/watchdog/pcwd_usb.c
@@ -24,6 +24,8 @@
  *	http://www.berkprod.com/ or http://www.pcwatchdog.com/
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>	/* For module specific items */
 #include <linux/moduleparam.h>	/* For new moduleparam's */
 #include <linux/types.h>	/* For standard types (like size_t) */
@@ -42,17 +44,23 @@
 #include <linux/hid.h>		/* For HID_REQ_SET_REPORT & HID_DT_REPORT */
 #include <linux/uaccess.h>	/* For copy_to_user/put_user/... */
 
-
 #ifdef CONFIG_USB_DEBUG
-	static int debug = 1;
+static int debug = 1;
 #else
-	static int debug;
+static int debug;
 #endif
 
 /* Use our own dbg macro */
+
 #undef dbg
-#define dbg(format, arg...) \
-	do { if (debug) printk(KERN_DEBUG PFX format "\n" , ## arg); } while (0)
+#ifndef DEBUG
+#define DEBUG
+#endif
+#define dbg(format, ...)				\
+do {							\
+	if (debug)					\
+		pr_debug(format "\n", ##__VA_ARGS__);	\
+} while (0)
 
 /* Module and Version Information */
 #define DRIVER_VERSION "1.02"
@@ -60,7 +68,6 @@
 #define DRIVER_DESC "Berkshire USB-PC Watchdog driver"
 #define DRIVER_LICENSE "GPL"
 #define DRIVER_NAME "pcwd_usb"
-#define PFX DRIVER_NAME ": "
 
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
@@ -80,8 +87,8 @@ MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds. "
 	"(0<heartbeat<65536 or 0=delay-time from dip-switches, default="
 				__MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -220,8 +227,8 @@ static void usb_pcwd_intr_done(struct urb *urb)
 resubmit:
 	retval = usb_submit_urb(urb, GFP_ATOMIC);
 	if (retval)
-		printk(KERN_ERR PFX "can't resubmit intr, "
-			"usb_submit_urb failed with result %d\n", retval);
+		pr_err("can't resubmit intr, usb_submit_urb failed with result %d\n",
+		       retval);
 }
 
 static int usb_pcwd_send_command(struct usb_pcwd_private *usb_pcwd,
@@ -284,8 +291,7 @@ static int usb_pcwd_start(struct usb_pcwd_private *usb_pcwd)
 								&msb, &lsb);
 
 	if ((retval == 0) || (lsb == 0)) {
-		printk(KERN_ERR PFX
-				"Card did not acknowledge enable attempt\n");
+		pr_err("Card did not acknowledge enable attempt\n");
 		return -1;
 	}
 
@@ -303,8 +309,7 @@ static int usb_pcwd_stop(struct usb_pcwd_private *usb_pcwd)
 								&msb, &lsb);
 
 	if ((retval == 0) || (lsb != 0)) {
-		printk(KERN_ERR PFX
-			"Card did not acknowledge disable attempt\n");
+		pr_err("Card did not acknowledge disable attempt\n");
 		return -1;
 	}
 
@@ -506,8 +511,7 @@ static int usb_pcwd_release(struct inode *inode, struct file *file)
 	if (expect_release == 42) {
 		usb_pcwd_stop(usb_pcwd_device);
 	} else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		usb_pcwd_keepalive(usb_pcwd_device);
 	}
 	expect_release = 0;
@@ -627,7 +631,7 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 
 	cards_found++;
 	if (cards_found > 1) {
-		printk(KERN_ERR PFX "This driver only supports 1 device\n");
+		pr_err("This driver only supports 1 device\n");
 		return -ENODEV;
 	}
 
@@ -636,8 +640,7 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 
 	/* check out that we have a HID device */
 	if (!(iface_desc->desc.bInterfaceClass == USB_CLASS_HID)) {
-		printk(KERN_ERR PFX
-			"The device isn't a Human Interface Device\n");
+		pr_err("The device isn't a Human Interface Device\n");
 		return -ENODEV;
 	}
 
@@ -646,7 +649,7 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 
 	if (!usb_endpoint_is_int_in(endpoint)) {
 		/* we didn't find a Interrupt endpoint with direction IN */
-		printk(KERN_ERR PFX "Couldn't find an INTR & IN endpoint\n");
+		pr_err("Couldn't find an INTR & IN endpoint\n");
 		return -ENODEV;
 	}
 
@@ -657,7 +660,7 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 	/* allocate memory for our device and initialize it */
 	usb_pcwd = kzalloc(sizeof(struct usb_pcwd_private), GFP_KERNEL);
 	if (usb_pcwd == NULL) {
-		printk(KERN_ERR PFX "Out of memory\n");
+		pr_err("Out of memory\n");
 		goto error;
 	}
 
@@ -674,14 +677,14 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 	usb_pcwd->intr_buffer = usb_alloc_coherent(udev, usb_pcwd->intr_size,
 					GFP_ATOMIC, &usb_pcwd->intr_dma);
 	if (!usb_pcwd->intr_buffer) {
-		printk(KERN_ERR PFX "Out of memory\n");
+		pr_err("Out of memory\n");
 		goto error;
 	}
 
 	/* allocate the urb's */
 	usb_pcwd->intr_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!usb_pcwd->intr_urb) {
-		printk(KERN_ERR PFX "Out of memory\n");
+		pr_err("Out of memory\n");
 		goto error;
 	}
 
@@ -694,7 +697,7 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 
 	/* register our interrupt URB with the USB system */
 	if (usb_submit_urb(usb_pcwd->intr_urb, GFP_KERNEL)) {
-		printk(KERN_ERR PFX "Problem registering interrupt URB\n");
+		pr_err("Problem registering interrupt URB\n");
 		retval = -EIO; /* failure */
 		goto error;
 	}
@@ -713,15 +716,13 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 	else
 		sprintf(fw_ver_str, "<card no answer>");
 
-	printk(KERN_INFO PFX "Found card (Firmware: %s) with temp option\n",
-		fw_ver_str);
+	pr_info("Found card (Firmware: %s) with temp option\n", fw_ver_str);
 
 	/* Get switch settings */
 	usb_pcwd_send_command(usb_pcwd, CMD_GET_DIP_SWITCH_SETTINGS, &dummy,
 							&option_switches);
 
-	printk(KERN_INFO PFX "Option switches (0x%02x): "
-		"Temperature Reset Enable=%s, Power On Delay=%s\n",
+	pr_info("Option switches (0x%02x): Temperature Reset Enable=%s, Power On Delay=%s\n",
 		option_switches,
 		((option_switches & 0x10) ? "ON" : "OFF"),
 		((option_switches & 0x08) ? "ON" : "OFF"));
@@ -734,39 +735,34 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 	 * if not reset to the default */
 	if (usb_pcwd_set_heartbeat(usb_pcwd, heartbeat)) {
 		usb_pcwd_set_heartbeat(usb_pcwd, WATCHDOG_HEARTBEAT);
-		printk(KERN_INFO PFX
-			"heartbeat value must be 0<heartbeat<65536, using %d\n",
+		pr_info("heartbeat value must be 0<heartbeat<65536, using %d\n",
 			WATCHDOG_HEARTBEAT);
 	}
 
 	retval = register_reboot_notifier(&usb_pcwd_notifier);
 	if (retval != 0) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n",
-			retval);
+		pr_err("cannot register reboot notifier (err=%d)\n", retval);
 		goto error;
 	}
 
 	retval = misc_register(&usb_pcwd_temperature_miscdev);
 	if (retval != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-			TEMP_MINOR, retval);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       TEMP_MINOR, retval);
 		goto err_out_unregister_reboot;
 	}
 
 	retval = misc_register(&usb_pcwd_miscdev);
 	if (retval != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-			WATCHDOG_MINOR, retval);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, retval);
 		goto err_out_misc_deregister;
 	}
 
 	/* we can register the device now, as it is ready */
 	usb_set_intfdata(interface, usb_pcwd);
 
-	printk(KERN_INFO PFX "initialized. heartbeat=%d sec (nowayout=%d)\n",
+	pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n",
 		heartbeat, nowayout);
 
 	return 0;
@@ -824,7 +820,7 @@ static void usb_pcwd_disconnect(struct usb_interface *interface)
 
 	mutex_unlock(&disconnect_mutex);
 
-	printk(KERN_INFO PFX "USB PC Watchdog disconnected\n");
+	pr_info("USB PC Watchdog disconnected\n");
 }
 
 module_usb_driver(usb_pcwd_driver);
diff --git a/drivers/watchdog/pika_wdt.c b/drivers/watchdog/pika_wdt.c
index 2d22e996e996..7d3d471f810c 100644
--- a/drivers/watchdog/pika_wdt.c
+++ b/drivers/watchdog/pika_wdt.c
@@ -5,6 +5,8 @@
  *   Sean MacLennan <smaclennan@pikatech.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/module.h>
@@ -23,7 +25,6 @@
 #include <linux/of_platform.h>
 
 #define DRV_NAME "PIKA-WDT"
-#define PFX DRV_NAME ": "
 
 /* Hardware timeout in seconds */
 #define WDT_HW_TIMEOUT 2
@@ -38,8 +39,8 @@ module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds. "
 	"(default = " __MODULE_STRING(WDT_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 	"(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -90,7 +91,7 @@ static void pikawdt_ping(unsigned long data)
 		pikawdt_reset();
 		mod_timer(&pikawdt_private.timer, jiffies + WDT_TIMEOUT);
 	} else
-		printk(KERN_CRIT PFX "I will reset your machine !\n");
+		pr_crit("I will reset your machine !\n");
 }
 
 
@@ -228,14 +229,14 @@ static int __init pikawdt_init(void)
 
 	np = of_find_compatible_node(NULL, NULL, "pika,fpga");
 	if (np == NULL) {
-		printk(KERN_ERR PFX "Unable to find fpga.\n");
+		pr_err("Unable to find fpga\n");
 		return -ENOENT;
 	}
 
 	pikawdt_private.fpga = of_iomap(np, 0);
 	of_node_put(np);
 	if (pikawdt_private.fpga == NULL) {
-		printk(KERN_ERR PFX "Unable to map fpga.\n");
+		pr_err("Unable to map fpga\n");
 		return -ENOMEM;
 	}
 
@@ -244,7 +245,7 @@ static int __init pikawdt_init(void)
 	/* POST information is in the sd area. */
 	np = of_find_compatible_node(NULL, NULL, "pika,fpga-sd");
 	if (np == NULL) {
-		printk(KERN_ERR PFX "Unable to find fpga-sd.\n");
+		pr_err("Unable to find fpga-sd\n");
 		ret = -ENOENT;
 		goto out;
 	}
@@ -252,7 +253,7 @@ static int __init pikawdt_init(void)
 	fpga = of_iomap(np, 0);
 	of_node_put(np);
 	if (fpga == NULL) {
-		printk(KERN_ERR PFX "Unable to map fpga-sd.\n");
+		pr_err("Unable to map fpga-sd\n");
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -271,12 +272,12 @@ static int __init pikawdt_init(void)
 
 	ret = misc_register(&pikawdt_miscdev);
 	if (ret) {
-		printk(KERN_ERR PFX "Unable to register miscdev.\n");
+		pr_err("Unable to register miscdev\n");
 		goto out;
 	}
 
-	printk(KERN_INFO PFX "initialized. heartbeat=%d sec (nowayout=%d)\n",
-							heartbeat, nowayout);
+	pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n",
+		heartbeat, nowayout);
 	return 0;
 
 out:
diff --git a/drivers/watchdog/pnx4008_wdt.c b/drivers/watchdog/pnx4008_wdt.c
index dfae030a7ef2..6b8432f61d05 100644
--- a/drivers/watchdog/pnx4008_wdt.c
+++ b/drivers/watchdog/pnx4008_wdt.c
@@ -8,33 +8,32 @@
  * Based on sa1100 driver,
  * Copyright (C) 2000 Oleg Drokin <green@crimea.edu>
  *
- * 2005-2006 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
+ * 2005-2006 (c) MontaVista Software, Inc.
+ *
+ * (C) 2012 Wolfram Sang, Pengutronix
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/fs.h>
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/init.h>
-#include <linux/bitops.h>
-#include <linux/ioport.h>
-#include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/spinlock.h>
-#include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/err.h>
 #include <mach/hardware.h>
 
-#define MODULE_NAME "PNX4008-WDT: "
-
 /* WatchDog Timer - Chapter 23 Page 207 */
 
 #define DEFAULT_HEARTBEAT 19
@@ -77,251 +76,128 @@
 
 #define WDOG_COUNTER_RATE 13000000	/*the counter clock is 13 MHz fixed */
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-static int heartbeat = DEFAULT_HEARTBEAT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
+static unsigned int heartbeat = DEFAULT_HEARTBEAT;
 
 static DEFINE_SPINLOCK(io_lock);
-static unsigned long wdt_status;
-#define WDT_IN_USE        0
-#define WDT_OK_TO_CLOSE   1
-#define WDT_REGION_INITED 2
-#define WDT_DEVICE_INITED 3
-
-static unsigned long boot_status;
-
-static struct resource	*wdt_mem;
 static void __iomem	*wdt_base;
 struct clk		*wdt_clk;
 
-static void wdt_enable(void)
+static int pnx4008_wdt_start(struct watchdog_device *wdd)
 {
 	spin_lock(&io_lock);
 
 	/* stop counter, initiate counter reset */
-	__raw_writel(RESET_COUNT, WDTIM_CTRL(wdt_base));
+	writel(RESET_COUNT, WDTIM_CTRL(wdt_base));
 	/*wait for reset to complete. 100% guarantee event */
-	while (__raw_readl(WDTIM_COUNTER(wdt_base)))
+	while (readl(WDTIM_COUNTER(wdt_base)))
 		cpu_relax();
 	/* internal and external reset, stop after that */
-	__raw_writel(M_RES2 | STOP_COUNT0 | RESET_COUNT0,
-		WDTIM_MCTRL(wdt_base));
+	writel(M_RES2 | STOP_COUNT0 | RESET_COUNT0, WDTIM_MCTRL(wdt_base));
 	/* configure match output */
-	__raw_writel(MATCH_OUTPUT_HIGH, WDTIM_EMR(wdt_base));
+	writel(MATCH_OUTPUT_HIGH, WDTIM_EMR(wdt_base));
 	/* clear interrupt, just in case */
-	__raw_writel(MATCH_INT, WDTIM_INT(wdt_base));
+	writel(MATCH_INT, WDTIM_INT(wdt_base));
 	/* the longest pulse period 65541/(13*10^6) seconds ~ 5 ms. */
-	__raw_writel(0xFFFF, WDTIM_PULSE(wdt_base));
-	__raw_writel(heartbeat * WDOG_COUNTER_RATE, WDTIM_MATCH0(wdt_base));
+	writel(0xFFFF, WDTIM_PULSE(wdt_base));
+	writel(wdd->timeout * WDOG_COUNTER_RATE, WDTIM_MATCH0(wdt_base));
 	/*enable counter, stop when debugger active */
-	__raw_writel(COUNT_ENAB | DEBUG_EN, WDTIM_CTRL(wdt_base));
+	writel(COUNT_ENAB | DEBUG_EN, WDTIM_CTRL(wdt_base));
 
 	spin_unlock(&io_lock);
+	return 0;
 }
 
-static void wdt_disable(void)
+static int pnx4008_wdt_stop(struct watchdog_device *wdd)
 {
 	spin_lock(&io_lock);
 
-	__raw_writel(0, WDTIM_CTRL(wdt_base));	/*stop counter */
+	writel(0, WDTIM_CTRL(wdt_base));	/*stop counter */
 
 	spin_unlock(&io_lock);
+	return 0;
 }
 
-static int pnx4008_wdt_open(struct inode *inode, struct file *file)
-{
-	int ret;
-
-	if (test_and_set_bit(WDT_IN_USE, &wdt_status))
-		return -EBUSY;
-
-	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
-	ret = clk_enable(wdt_clk);
-	if (ret) {
-		clear_bit(WDT_IN_USE, &wdt_status);
-		return ret;
-	}
-
-	wdt_enable();
-
-	return nonseekable_open(inode, file);
-}
-
-static ssize_t pnx4008_wdt_write(struct file *file, const char *data,
-					size_t len, loff_t *ppos)
+static int pnx4008_wdt_set_timeout(struct watchdog_device *wdd,
+				    unsigned int new_timeout)
 {
-	if (len) {
-		if (!nowayout) {
-			size_t i;
-
-			clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
-			for (i = 0; i != len; i++) {
-				char c;
-
-				if (get_user(c, data + i))
-					return -EFAULT;
-				if (c == 'V')
-					set_bit(WDT_OK_TO_CLOSE, &wdt_status);
-			}
-		}
-		wdt_enable();
-	}
-
-	return len;
+	wdd->timeout = new_timeout;
+	return 0;
 }
 
-static const struct watchdog_info ident = {
+static const struct watchdog_info pnx4008_wdt_ident = {
 	.options = WDIOF_CARDRESET | WDIOF_MAGICCLOSE |
 	    WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING,
 	.identity = "PNX4008 Watchdog",
 };
 
-static long pnx4008_wdt_ioctl(struct file *file, unsigned int cmd,
-				unsigned long arg)
-{
-	int ret = -ENOTTY;
-	int time;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		ret = copy_to_user((struct watchdog_info *)arg, &ident,
-				   sizeof(ident)) ? -EFAULT : 0;
-		break;
-
-	case WDIOC_GETSTATUS:
-		ret = put_user(0, (int *)arg);
-		break;
-
-	case WDIOC_GETBOOTSTATUS:
-		ret = put_user(boot_status, (int *)arg);
-		break;
-
-	case WDIOC_KEEPALIVE:
-		wdt_enable();
-		ret = 0;
-		break;
-
-	case WDIOC_SETTIMEOUT:
-		ret = get_user(time, (int *)arg);
-		if (ret)
-			break;
-
-		if (time <= 0 || time > MAX_HEARTBEAT) {
-			ret = -EINVAL;
-			break;
-		}
-
-		heartbeat = time;
-		wdt_enable();
-		/* Fall through */
-
-	case WDIOC_GETTIMEOUT:
-		ret = put_user(heartbeat, (int *)arg);
-		break;
-	}
-	return ret;
-}
-
-static int pnx4008_wdt_release(struct inode *inode, struct file *file)
-{
-	if (!test_bit(WDT_OK_TO_CLOSE, &wdt_status))
-		printk(KERN_WARNING "WATCHDOG: Device closed unexpectedly\n");
-
-	wdt_disable();
-	clk_disable(wdt_clk);
-	clear_bit(WDT_IN_USE, &wdt_status);
-	clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
-	return 0;
-}
-
-static const struct file_operations pnx4008_wdt_fops = {
+static const struct watchdog_ops pnx4008_wdt_ops = {
 	.owner = THIS_MODULE,
-	.llseek = no_llseek,
-	.write = pnx4008_wdt_write,
-	.unlocked_ioctl = pnx4008_wdt_ioctl,
-	.open = pnx4008_wdt_open,
-	.release = pnx4008_wdt_release,
+	.start = pnx4008_wdt_start,
+	.stop = pnx4008_wdt_stop,
+	.set_timeout = pnx4008_wdt_set_timeout,
 };
 
-static struct miscdevice pnx4008_wdt_miscdev = {
-	.minor = WATCHDOG_MINOR,
-	.name = "watchdog",
-	.fops = &pnx4008_wdt_fops,
+static struct watchdog_device pnx4008_wdd = {
+	.info = &pnx4008_wdt_ident,
+	.ops = &pnx4008_wdt_ops,
+	.min_timeout = 1,
+	.max_timeout = MAX_HEARTBEAT,
 };
 
 static int __devinit pnx4008_wdt_probe(struct platform_device *pdev)
 {
-	int ret = 0, size;
+	struct resource *r;
+	int ret = 0;
 
 	if (heartbeat < 1 || heartbeat > MAX_HEARTBEAT)
 		heartbeat = DEFAULT_HEARTBEAT;
 
-	printk(KERN_INFO MODULE_NAME
-		"PNX4008 Watchdog Timer: heartbeat %d sec\n", heartbeat);
-
-	wdt_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (wdt_mem == NULL) {
-		printk(KERN_INFO MODULE_NAME
-			"failed to get memory region resource\n");
-		return -ENOENT;
-	}
-
-	size = resource_size(wdt_mem);
-
-	if (!request_mem_region(wdt_mem->start, size, pdev->name)) {
-		printk(KERN_INFO MODULE_NAME "failed to get memory region\n");
-		return -ENOENT;
-	}
-	wdt_base = (void __iomem *)IO_ADDRESS(wdt_mem->start);
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	wdt_base = devm_request_and_ioremap(&pdev->dev, r);
+	if (!wdt_base)
+		return -EADDRINUSE;
 
 	wdt_clk = clk_get(&pdev->dev, NULL);
-	if (IS_ERR(wdt_clk)) {
-		ret = PTR_ERR(wdt_clk);
-		release_mem_region(wdt_mem->start, size);
-		wdt_mem = NULL;
-		goto out;
-	}
+	if (IS_ERR(wdt_clk))
+		return PTR_ERR(wdt_clk);
 
 	ret = clk_enable(wdt_clk);
-	if (ret) {
-		release_mem_region(wdt_mem->start, size);
-		wdt_mem = NULL;
-		clk_put(wdt_clk);
+	if (ret)
 		goto out;
-	}
 
-	ret = misc_register(&pnx4008_wdt_miscdev);
+	pnx4008_wdd.timeout = heartbeat;
+	pnx4008_wdd.bootstatus = (readl(WDTIM_RES(wdt_base)) & WDOG_RESET) ?
+			WDIOF_CARDRESET : 0;
+	watchdog_set_nowayout(&pnx4008_wdd, nowayout);
+
+	pnx4008_wdt_stop(&pnx4008_wdd);	/* disable for now */
+
+	ret = watchdog_register_device(&pnx4008_wdd);
 	if (ret < 0) {
-		printk(KERN_ERR MODULE_NAME "cannot register misc device\n");
-		release_mem_region(wdt_mem->start, size);
-		wdt_mem = NULL;
-		clk_disable(wdt_clk);
-		clk_put(wdt_clk);
-	} else {
-		boot_status = (__raw_readl(WDTIM_RES(wdt_base)) & WDOG_RESET) ?
-		    WDIOF_CARDRESET : 0;
-		wdt_disable();		/*disable for now */
-		clk_disable(wdt_clk);
-		set_bit(WDT_DEVICE_INITED, &wdt_status);
+		dev_err(&pdev->dev, "cannot register watchdog device\n");
+		goto disable_clk;
 	}
 
+	dev_info(&pdev->dev, "PNX4008 Watchdog Timer: heartbeat %d sec\n",
+			heartbeat);
+
+	return 0;
+
+disable_clk:
+	clk_disable(wdt_clk);
 out:
+	clk_put(wdt_clk);
 	return ret;
 }
 
 static int __devexit pnx4008_wdt_remove(struct platform_device *pdev)
 {
-	misc_deregister(&pnx4008_wdt_miscdev);
+	watchdog_unregister_device(&pnx4008_wdd);
 
 	clk_disable(wdt_clk);
 	clk_put(wdt_clk);
 
-	if (wdt_mem) {
-		release_mem_region(wdt_mem->start, resource_size(wdt_mem));
-		wdt_mem = NULL;
-	}
 	return 0;
 }
 
@@ -337,15 +213,16 @@ static struct platform_driver platform_wdt_driver = {
 module_platform_driver(platform_wdt_driver);
 
 MODULE_AUTHOR("MontaVista Software, Inc. <source@mvista.com>");
+MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>");
 MODULE_DESCRIPTION("PNX4008 Watchdog Driver");
 
-module_param(heartbeat, int, 0);
+module_param(heartbeat, uint, 0);
 MODULE_PARM_DESC(heartbeat,
 		 "Watchdog heartbeat period in seconds from 1 to "
 		 __MODULE_STRING(MAX_HEARTBEAT) ", default "
 		 __MODULE_STRING(DEFAULT_HEARTBEAT));
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		 "Set to 1 to keep watchdog running after device release");
 
diff --git a/drivers/watchdog/pnx833x_wdt.c b/drivers/watchdog/pnx833x_wdt.c
index a7b5ad2a98bd..1b62a7dfcc95 100644
--- a/drivers/watchdog/pnx833x_wdt.c
+++ b/drivers/watchdog/pnx833x_wdt.c
@@ -17,6 +17,8 @@
  * based on softdog.c by Alan Cox <alan@redhat.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -30,7 +32,6 @@
 #include <linux/init.h>
 #include <asm/mach-pnx833x/pnx833x.h>
 
-#define PFX "pnx833x: "
 #define WATCHDOG_TIMEOUT 30		/* 30 sec Maximum timeout */
 #define WATCHDOG_COUNT_FREQUENCY 68000000U /* Watchdog counts at 68MHZ. */
 #define	PNX_WATCHDOG_TIMEOUT	(WATCHDOG_TIMEOUT * WATCHDOG_COUNT_FREQUENCY)
@@ -54,8 +55,8 @@ module_param(pnx833x_wdt_timeout, int, 0);
 MODULE_PARM_DESC(timeout, "Watchdog timeout in Mhz. (68Mhz clock), default="
 			__MODULE_STRING(PNX_TIMEOUT_VALUE) "(30 seconds).");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 					__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -76,7 +77,7 @@ static void pnx833x_wdt_start(void)
 	PNX833X_REG(PNX833X_CONFIG +
 				PNX833X_CONFIG_CPU_COUNTERS_CONTROL) |= 0x1;
 
-	printk(KERN_INFO PFX "Started watchdog timer.\n");
+	pr_info("Started watchdog timer\n");
 }
 
 static void pnx833x_wdt_stop(void)
@@ -87,7 +88,7 @@ static void pnx833x_wdt_stop(void)
 	PNX833X_REG(PNX833X_CONFIG +
 			PNX833X_CONFIG_CPU_COUNTERS_CONTROL) &= 0xFFFFFFFE;
 
-	printk(KERN_INFO PFX "Stopped watchdog timer.\n");
+	pr_info("Stopped watchdog timer\n");
 }
 
 static void pnx833x_wdt_ping(void)
@@ -113,7 +114,7 @@ static int pnx833x_wdt_open(struct inode *inode, struct file *file)
 
 	pnx833x_wdt_ping();
 
-	printk(KERN_INFO "Started watchdog timer.\n");
+	pr_info("Started watchdog timer\n");
 
 	return nonseekable_open(inode, file);
 }
@@ -232,9 +233,6 @@ static struct notifier_block pnx833x_wdt_notifier = {
 	.notifier_call = pnx833x_wdt_notify_sys,
 };
 
-static char banner[] __initdata =
-	KERN_INFO PFX "Hardware Watchdog Timer for PNX833x: Version 0.1\n";
-
 static int __init watchdog_init(void)
 {
 	int ret, cause;
@@ -243,27 +241,25 @@ static int __init watchdog_init(void)
 	cause = PNX833X_REG(PNX833X_RESET);
 	/*If bit 31 is set then watchdog was cause of reset.*/
 	if (cause & 0x80000000) {
-		printk(KERN_INFO PFX "The system was previously reset due to "
-			"the watchdog firing - please investigate...\n");
+		pr_info("The system was previously reset due to the watchdog firing - please investigate...\n");
 	}
 
 	ret = register_reboot_notifier(&pnx833x_wdt_notifier);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		return ret;
 	}
 
 	ret = misc_register(&pnx833x_wdt_miscdev);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-			WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		unregister_reboot_notifier(&pnx833x_wdt_notifier);
 		return ret;
 	}
 
-	printk(banner);
+	pr_info("Hardware Watchdog Timer for PNX833x: Version 0.1\n");
+
 	if (start_enabled)
 		pnx833x_wdt_start();
 
diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c
index bf7bc8aa1c01..547353a50ebb 100644
--- a/drivers/watchdog/rc32434_wdt.c
+++ b/drivers/watchdog/rc32434_wdt.c
@@ -17,6 +17,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>		/* For module specific items */
 #include <linux/moduleparam.h>		/* For new moduleparam's */
 #include <linux/types.h>		/* For standard types (like size_t) */
@@ -33,8 +35,6 @@
 
 #include <asm/mach-rc32434/integ.h>	/* For the Watchdog registers */
 
-#define PFX KBUILD_MODNAME ": "
-
 #define VERSION "1.0"
 
 static struct {
@@ -64,8 +64,8 @@ module_param(timeout, int, 0);
 MODULE_PARM_DESC(timeout, "Watchdog timeout value, in seconds (default="
 		__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 	__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -78,8 +78,7 @@ static int rc32434_wdt_set(int new_timeout)
 	int max_to = WTCOMP2SEC((u32)-1);
 
 	if (new_timeout < 0 || new_timeout > max_to) {
-		printk(KERN_ERR PFX "timeout value must be between 0 and %d",
-			max_to);
+		pr_err("timeout value must be between 0 and %d\n", max_to);
 		return -EINVAL;
 	}
 	timeout = new_timeout;
@@ -119,7 +118,7 @@ static void rc32434_wdt_start(void)
 	SET_BITS(wdt_reg->wtc, or, nand);
 
 	spin_unlock(&rc32434_wdt_device.io_lock);
-	printk(KERN_INFO PFX "Started watchdog timer.\n");
+	pr_info("Started watchdog timer\n");
 }
 
 static void rc32434_wdt_stop(void)
@@ -130,7 +129,7 @@ static void rc32434_wdt_stop(void)
 	SET_BITS(wdt_reg->wtc, 0, 1 << RC32434_WTC_EN);
 
 	spin_unlock(&rc32434_wdt_device.io_lock);
-	printk(KERN_INFO PFX "Stopped watchdog timer.\n");
+	pr_info("Stopped watchdog timer\n");
 }
 
 static void rc32434_wdt_ping(void)
@@ -160,8 +159,7 @@ static int rc32434_wdt_release(struct inode *inode, struct file *file)
 		rc32434_wdt_stop();
 		module_put(THIS_MODULE);
 	} else {
-		printk(KERN_CRIT PFX
-			"device closed unexpectedly. WDT will not stop!\n");
+		pr_crit("device closed unexpectedly. WDT will not stop!\n");
 		rc32434_wdt_ping();
 	}
 	clear_bit(0, &rc32434_wdt_device.inuse);
@@ -262,9 +260,6 @@ static struct miscdevice rc32434_wdt_miscdev = {
 	.fops	= &rc32434_wdt_fops,
 };
 
-static char banner[] __devinitdata = KERN_INFO PFX
-		"Watchdog Timer version " VERSION ", timer margin: %d sec\n";
-
 static int __devinit rc32434_wdt_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -272,13 +267,13 @@ static int __devinit rc32434_wdt_probe(struct platform_device *pdev)
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rb532_wdt_res");
 	if (!r) {
-		printk(KERN_ERR PFX "failed to retrieve resources\n");
+		pr_err("failed to retrieve resources\n");
 		return -ENODEV;
 	}
 
 	wdt_reg = ioremap_nocache(r->start, resource_size(r));
 	if (!wdt_reg) {
-		printk(KERN_ERR PFX "failed to remap I/O resources\n");
+		pr_err("failed to remap I/O resources\n");
 		return -ENXIO;
 	}
 
@@ -291,18 +286,18 @@ static int __devinit rc32434_wdt_probe(struct platform_device *pdev)
 	 * if not reset to the default */
 	if (rc32434_wdt_set(timeout)) {
 		rc32434_wdt_set(WATCHDOG_TIMEOUT);
-		printk(KERN_INFO PFX
-			"timeout value must be between 0 and %d\n",
+		pr_info("timeout value must be between 0 and %d\n",
 			WTCOMP2SEC((u32)-1));
 	}
 
 	ret = misc_register(&rc32434_wdt_miscdev);
 	if (ret < 0) {
-		printk(KERN_ERR PFX "failed to register watchdog device\n");
+		pr_err("failed to register watchdog device\n");
 		goto unmap;
 	}
 
-	printk(banner, timeout);
+	pr_info("Watchdog Timer version " VERSION ", timer margin: %d sec\n",
+		timeout);
 
 	return 0;
 
diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c
index c7e17ceafa6a..49e1b1c2135c 100644
--- a/drivers/watchdog/riowd.c
+++ b/drivers/watchdog/riowd.c
@@ -3,6 +3,8 @@
  * Copyright (C) 2001, 2008 David S. Miller (davem@davemloft.net)
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -189,7 +191,7 @@ static int __devinit riowd_probe(struct platform_device *op)
 
 	p->regs = of_ioremap(&op->resource[0], 0, 2, DRIVER_NAME);
 	if (!p->regs) {
-		printk(KERN_ERR PFX "Cannot map registers.\n");
+		pr_err("Cannot map registers\n");
 		goto out_free;
 	}
 	/* Make miscdev useable right away */
@@ -197,12 +199,12 @@ static int __devinit riowd_probe(struct platform_device *op)
 
 	err = misc_register(&riowd_miscdev);
 	if (err) {
-		printk(KERN_ERR PFX "Cannot register watchdog misc device.\n");
+		pr_err("Cannot register watchdog misc device\n");
 		goto out_iounmap;
 	}
 
-	printk(KERN_INFO PFX "Hardware watchdog [%i minutes], "
-	       "regs at %p\n", riowd_timeout, p->regs);
+	pr_info("Hardware watchdog [%i minutes], regs at %p\n",
+		riowd_timeout, p->regs);
 
 	dev_set_drvdata(&op->dev, p);
 	return 0;
diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c
index 404172f02c9b..04e5a6de47d7 100644
--- a/drivers/watchdog/s3c2410_wdt.c
+++ b/drivers/watchdog/s3c2410_wdt.c
@@ -23,6 +23,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -46,12 +48,10 @@
 
 #include <plat/regs-watchdog.h>
 
-#define PFX "s3c2410-wdt: "
-
 #define CONFIG_S3C2410_WATCHDOG_ATBOOT		(0)
 #define CONFIG_S3C2410_WATCHDOG_DEFAULT_TIME	(15)
 
-static int nowayout	= WATCHDOG_NOWAYOUT;
+static bool nowayout	= WATCHDOG_NOWAYOUT;
 static int tmr_margin	= CONFIG_S3C2410_WATCHDOG_DEFAULT_TIME;
 static int tmr_atboot	= CONFIG_S3C2410_WATCHDOG_ATBOOT;
 static int soft_noboot;
@@ -59,7 +59,7 @@ static int debug;
 
 module_param(tmr_margin,  int, 0);
 module_param(tmr_atboot,  int, 0);
-module_param(nowayout,    int, 0);
+module_param(nowayout,   bool, 0);
 module_param(soft_noboot, int, 0);
 module_param(debug,	  int, 0);
 
@@ -84,10 +84,11 @@ static DEFINE_SPINLOCK(wdt_lock);
 
 /* watchdog control routines */
 
-#define DBG(msg...) do { \
-	if (debug) \
-		printk(KERN_INFO msg); \
-	} while (0)
+#define DBG(fmt, ...)					\
+do {							\
+	if (debug)					\
+		pr_info(fmt, ##__VA_ARGS__);		\
+} while (0)
 
 /* functions */
 
@@ -200,6 +201,8 @@ static int s3c2410wdt_set_heartbeat(struct watchdog_device *wdd, unsigned timeou
 	writel(count, wdt_base + S3C2410_WTDAT);
 	writel(wtcon, wdt_base + S3C2410_WTCON);
 
+	wdd->timeout = timeout;
+
 	return 0;
 }
 
@@ -354,7 +357,7 @@ static int __devinit s3c2410wdt_probe(struct platform_device *pdev)
 
 	ret = s3c2410wdt_cpufreq_register();
 	if (ret < 0) {
-		printk(KERN_ERR PFX "failed to register cpufreq\n");
+		pr_err("failed to register cpufreq\n");
 		goto err_clk;
 	}
 
@@ -483,8 +486,8 @@ static int s3c2410wdt_resume(struct platform_device *dev)
 	writel(wtdat_save, wdt_base + S3C2410_WTCNT); /* Reset count */
 	writel(wtcon_save, wdt_base + S3C2410_WTCON);
 
-	printk(KERN_INFO PFX "watchdog %sabled\n",
-	       (wtcon_save & S3C2410_WTCON_ENABLE) ? "en" : "dis");
+	pr_info("watchdog %sabled\n",
+		(wtcon_save & S3C2410_WTCON_ENABLE) ? "en" : "dis");
 
 	return 0;
 }
@@ -518,12 +521,10 @@ static struct platform_driver s3c2410wdt_driver = {
 };
 
 
-static char banner[] __initdata =
-	KERN_INFO "S3C2410 Watchdog Timer, (c) 2004 Simtec Electronics\n";
-
 static int __init watchdog_init(void)
 {
-	printk(banner);
+	pr_info("S3C2410 Watchdog Timer, (c) 2004 Simtec Electronics\n");
+
 	return platform_driver_register(&s3c2410wdt_driver);
 }
 
diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c
index 016245419fad..54984deb8561 100644
--- a/drivers/watchdog/sa1100_wdt.c
+++ b/drivers/watchdog/sa1100_wdt.c
@@ -17,6 +17,9 @@
  *
  *	27/11/2000 Initial release
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -25,6 +28,7 @@
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/bitops.h>
 #include <linux/uaccess.h>
 #include <linux/timex.h>
@@ -66,7 +70,7 @@ static int sa1100dog_open(struct inode *inode, struct file *file)
  */
 static int sa1100dog_release(struct inode *inode, struct file *file)
 {
-	printk(KERN_CRIT "WATCHDOG: Device closed - timer will not stop\n");
+	pr_crit("Device closed - timer will not stop\n");
 	clear_bit(1, &sa1100wdt_users);
 	return 0;
 }
@@ -169,9 +173,8 @@ static int __init sa1100dog_init(void)
 
 	ret = misc_register(&sa1100dog_miscdev);
 	if (ret == 0)
-		printk(KERN_INFO
-			"SA1100/PXA2xx Watchdog Timer: timer margin %d sec\n",
-						margin);
+		pr_info("SA1100/PXA2xx Watchdog Timer: timer margin %d sec\n",
+			margin);
 	return ret;
 }
 
diff --git a/drivers/watchdog/sb_wdog.c b/drivers/watchdog/sb_wdog.c
index b01a30e5a663..25c7a3f9652d 100644
--- a/drivers/watchdog/sb_wdog.c
+++ b/drivers/watchdog/sb_wdog.c
@@ -43,6 +43,9 @@
  *	version 1 or 2 as published by the Free Software Foundation.
  *
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
@@ -125,9 +128,8 @@ static int sbwdog_release(struct inode *inode, struct file *file)
 		__raw_writeb(0, user_dog);
 		module_put(THIS_MODULE);
 	} else {
-		printk(KERN_CRIT
-			"%s: Unexpected close, not stopping watchdog!\n",
-						ident.identity);
+		pr_crit("%s: Unexpected close, not stopping watchdog!\n",
+			ident.identity);
 		sbwdog_pet(user_dog);
 	}
 	clear_bit(0, &sbwdog_gate);
@@ -269,7 +271,7 @@ irqreturn_t sbwdog_interrupt(int irq, void *addr)
 	 * if it's the second watchdog timer, it's for those users
 	 */
 	if (wd_cfg_reg == user_dog)
-		printk(KERN_CRIT "%s in danger of initiating system reset "
+		pr_crit("%s in danger of initiating system reset "
 			"in %ld.%01ld seconds\n",
 			ident.identity,
 			wd_init / 1000000, (wd_init / 100000) % 10);
@@ -290,9 +292,8 @@ static int __init sbwdog_init(void)
 	 */
 	ret = register_reboot_notifier(&sbwdog_notifier);
 	if (ret) {
-		printk(KERN_ERR
-			"%s: cannot register reboot notifier (err=%d)\n",
-						ident.identity, ret);
+		pr_err("%s: cannot register reboot notifier (err=%d)\n",
+		       ident.identity, ret);
 		return ret;
 	}
 
@@ -303,16 +304,16 @@ static int __init sbwdog_init(void)
 	ret = request_irq(1, sbwdog_interrupt, IRQF_SHARED,
 		ident.identity, (void *)user_dog);
 	if (ret) {
-		printk(KERN_ERR "%s: failed to request irq 1 - %d\n",
-						ident.identity, ret);
+		pr_err("%s: failed to request irq 1 - %d\n",
+		       ident.identity, ret);
 		goto out;
 	}
 
 	ret = misc_register(&sbwdog_miscdev);
 	if (ret == 0) {
-		printk(KERN_INFO "%s: timeout is %ld.%ld secs\n",
-				ident.identity,
-				timeout / 1000000, (timeout / 100000) % 10);
+		pr_info("%s: timeout is %ld.%ld secs\n",
+			ident.identity,
+			timeout / 1000000, (timeout / 100000) % 10);
 		return 0;
 	}
 	free_irq(1, (void *)user_dog);
@@ -353,8 +354,7 @@ void platform_wd_setup(void)
 	ret = request_irq(1, sbwdog_interrupt, IRQF_SHARED,
 		"Kernel Watchdog", IOADDR(A_SCD_WDOG_CFG_0));
 	if (ret) {
-		printk(KERN_CRIT
-		  "Watchdog IRQ zero(0) failed to be requested - %d\n", ret);
+		pr_crit("Watchdog IRQ zero(0) failed to be requested - %d\n", ret);
 	}
 }
 
diff --git a/drivers/watchdog/sbc60xxwdt.c b/drivers/watchdog/sbc60xxwdt.c
index 626d0e8e56c3..63632ec87c7e 100644
--- a/drivers/watchdog/sbc60xxwdt.c
+++ b/drivers/watchdog/sbc60xxwdt.c
@@ -48,6 +48,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -63,7 +65,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 #define OUR_NAME "sbc60xxwdt"
 #define PFX OUR_NAME ": "
@@ -105,8 +106,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. (1<=timeout<=3600, default="
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -132,8 +133,7 @@ static void wdt_timer_ping(unsigned long data)
 		/* Re-set the timer interval */
 		mod_timer(&timer, jiffies + WDT_INTERVAL);
 	} else
-		printk(KERN_WARNING PFX
-			"Heartbeat lost! Will not ping the watchdog\n");
+		pr_warn("Heartbeat lost! Will not ping the watchdog\n");
 }
 
 /*
@@ -146,7 +146,7 @@ static void wdt_startup(void)
 
 	/* Start the timer */
 	mod_timer(&timer, jiffies + WDT_INTERVAL);
-	printk(KERN_INFO PFX "Watchdog timer is now enabled.\n");
+	pr_info("Watchdog timer is now enabled\n");
 }
 
 static void wdt_turnoff(void)
@@ -154,7 +154,7 @@ static void wdt_turnoff(void)
 	/* Stop the timer */
 	del_timer(&timer);
 	inb_p(wdt_stop);
-	printk(KERN_INFO PFX "Watchdog timer is now disabled...\n");
+	pr_info("Watchdog timer is now disabled...\n");
 }
 
 static void wdt_keepalive(void)
@@ -217,8 +217,7 @@ static int fop_close(struct inode *inode, struct file *file)
 		wdt_turnoff();
 	else {
 		del_timer(&timer);
-		printk(KERN_CRIT PFX
-		  "device file closed unexpectedly. Will not stop the WDT!\n");
+		pr_crit("device file closed unexpectedly. Will not stop the WDT!\n");
 	}
 	clear_bit(0, &wdt_is_open);
 	wdt_expect_close = 0;
@@ -335,14 +334,12 @@ static int __init sbc60xxwdt_init(void)
 
 	if (timeout < 1 || timeout > 3600) { /* arbitrary upper limit */
 		timeout = WATCHDOG_TIMEOUT;
-		printk(KERN_INFO PFX
-			"timeout value must be 1 <= x <= 3600, using %d\n",
-								timeout);
+		pr_info("timeout value must be 1 <= x <= 3600, using %d\n",
+			timeout);
 	}
 
 	if (!request_region(wdt_start, 1, "SBC 60XX WDT")) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			wdt_start);
+		pr_err("I/O address 0x%04x already in use\n", wdt_start);
 		rc = -EIO;
 		goto err_out;
 	}
@@ -350,9 +347,7 @@ static int __init sbc60xxwdt_init(void)
 	/* We cannot reserve 0x45 - the kernel already has! */
 	if (wdt_stop != 0x45 && wdt_stop != wdt_start) {
 		if (!request_region(wdt_stop, 1, "SBC 60XX WDT")) {
-			printk(KERN_ERR PFX
-				"I/O address 0x%04x already in use\n",
-							wdt_stop);
+			pr_err("I/O address 0x%04x already in use\n", wdt_stop);
 			rc = -EIO;
 			goto err_out_region1;
 		}
@@ -360,21 +355,18 @@ static int __init sbc60xxwdt_init(void)
 
 	rc = register_reboot_notifier(&wdt_notifier);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", rc);
+		pr_err("cannot register reboot notifier (err=%d)\n", rc);
 		goto err_out_region2;
 	}
 
 	rc = misc_register(&wdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						wdt_miscdev.minor, rc);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       wdt_miscdev.minor, rc);
 		goto err_out_reboot;
 	}
-	printk(KERN_INFO PFX
-		"WDT driver for 60XX single board computer initialised. "
-		"timeout=%d sec (nowayout=%d)\n", timeout, nowayout);
+	pr_info("WDT driver for 60XX single board computer initialised. timeout=%d sec (nowayout=%d)\n",
+		timeout, nowayout);
 
 	return 0;
 
diff --git a/drivers/watchdog/sbc7240_wdt.c b/drivers/watchdog/sbc7240_wdt.c
index 93ac58953122..719edc8fdeb3 100644
--- a/drivers/watchdog/sbc7240_wdt.c
+++ b/drivers/watchdog/sbc7240_wdt.c
@@ -16,6 +16,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
@@ -30,9 +32,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
-
-#define SBC7240_PREFIX "sbc7240_wdt: "
 
 #define SBC7240_ENABLE_PORT		0x443
 #define SBC7240_DISABLE_PORT		0x043
@@ -47,8 +46,8 @@ MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds. (1<=timeout<="
 		 __MODULE_STRING(SBC7240_MAX_TIMEOUT) ", default="
 		 __MODULE_STRING(SBC7240_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Disable watchdog when closing device file");
 
 #define SBC7240_OPEN_STATUS_BIT		0
@@ -65,8 +64,7 @@ static void wdt_disable(void)
 	/* disable the watchdog */
 	if (test_and_clear_bit(SBC7240_ENABLED_STATUS_BIT, &wdt_status)) {
 		inb_p(SBC7240_DISABLE_PORT);
-		printk(KERN_INFO SBC7240_PREFIX
-		       "Watchdog timer is now disabled.\n");
+		pr_info("Watchdog timer is now disabled\n");
 	}
 }
 
@@ -75,23 +73,20 @@ static void wdt_enable(void)
 	/* enable the watchdog */
 	if (!test_and_set_bit(SBC7240_ENABLED_STATUS_BIT, &wdt_status)) {
 		inb_p(SBC7240_ENABLE_PORT);
-		printk(KERN_INFO SBC7240_PREFIX
-		       "Watchdog timer is now enabled.\n");
+		pr_info("Watchdog timer is now enabled\n");
 	}
 }
 
 static int wdt_set_timeout(int t)
 {
 	if (t < 1 || t > SBC7240_MAX_TIMEOUT) {
-		printk(KERN_ERR SBC7240_PREFIX
-		       "timeout value must be 1<=x<=%d\n",
-		       SBC7240_MAX_TIMEOUT);
+		pr_err("timeout value must be 1<=x<=%d\n", SBC7240_MAX_TIMEOUT);
 		return -1;
 	}
 	/* set the timeout */
 	outb_p((unsigned)t, SBC7240_SET_TIMEOUT_PORT);
 	timeout = t;
-	printk(KERN_INFO SBC7240_PREFIX "timeout set to %d seconds\n", t);
+	pr_info("timeout set to %d seconds\n", t);
 	return 0;
 }
 
@@ -150,8 +145,7 @@ static int fop_close(struct inode *inode, struct file *file)
 	    || !nowayout) {
 		wdt_disable();
 	} else {
-		printk(KERN_CRIT SBC7240_PREFIX
-		       "Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		wdt_keepalive();
 	}
 
@@ -252,7 +246,7 @@ static struct notifier_block wdt_notifier = {
 
 static void __exit sbc7240_wdt_unload(void)
 {
-	printk(KERN_INFO SBC7240_PREFIX "Removing watchdog\n");
+	pr_info("Removing watchdog\n");
 	misc_deregister(&wdt_miscdev);
 
 	unregister_reboot_notifier(&wdt_notifier);
@@ -264,8 +258,7 @@ static int __init sbc7240_wdt_init(void)
 	int rc = -EBUSY;
 
 	if (!request_region(SBC7240_ENABLE_PORT, 1, "SBC7240 WDT")) {
-		printk(KERN_ERR SBC7240_PREFIX
-		       "I/O address 0x%04x already in use\n",
+		pr_err("I/O address 0x%04x already in use\n",
 		       SBC7240_ENABLE_PORT);
 		rc = -EIO;
 		goto err_out;
@@ -277,31 +270,27 @@ static int __init sbc7240_wdt_init(void)
 
 	if (timeout < 1 || timeout > SBC7240_MAX_TIMEOUT) {
 		timeout = SBC7240_TIMEOUT;
-		printk(KERN_INFO SBC7240_PREFIX
-		       "timeout value must be 1<=x<=%d, using %d\n",
-		       SBC7240_MAX_TIMEOUT, timeout);
+		pr_info("timeout value must be 1<=x<=%d, using %d\n",
+			SBC7240_MAX_TIMEOUT, timeout);
 	}
 	wdt_set_timeout(timeout);
 	wdt_disable();
 
 	rc = register_reboot_notifier(&wdt_notifier);
 	if (rc) {
-		printk(KERN_ERR SBC7240_PREFIX
-		       "cannot register reboot notifier (err=%d)\n", rc);
+		pr_err("cannot register reboot notifier (err=%d)\n", rc);
 		goto err_out_region;
 	}
 
 	rc = misc_register(&wdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR SBC7240_PREFIX
-		       "cannot register miscdev on minor=%d (err=%d)\n",
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
 		       wdt_miscdev.minor, rc);
 		goto err_out_reboot_notifier;
 	}
 
-	printk(KERN_INFO SBC7240_PREFIX
-	       "Watchdog driver for SBC7240 initialised (nowayout=%d)\n",
-	       nowayout);
+	pr_info("Watchdog driver for SBC7240 initialised (nowayout=%d)\n",
+		nowayout);
 
 	return 0;
 
diff --git a/drivers/watchdog/sbc8360.c b/drivers/watchdog/sbc8360.c
index 514ec23050f7..d4781e05f017 100644
--- a/drivers/watchdog/sbc8360.c
+++ b/drivers/watchdog/sbc8360.c
@@ -36,6 +36,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
@@ -51,13 +53,10 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 static unsigned long sbc8360_is_open;
 static char expect_close;
 
-#define PFX "sbc8360: "
-
 /*
  *
  * Watchdog Timer Configuration
@@ -197,11 +196,11 @@ static int wd_times[64][2] = {
 static int timeout = 27;
 static int wd_margin = 0xB;
 static int wd_multiplier = 2;
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 module_param(timeout, int, 0);
 MODULE_PARM_DESC(timeout, "Index into timeout table (0-63) (default=27 (60s))");
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		 "Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -280,8 +279,7 @@ static int sbc8360_close(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		sbc8360_stop();
 	else
-		printk(KERN_CRIT PFX "SBC8360 device closed unexpectedly.  "
-						"SBC8360 will not stop!\n");
+		pr_crit("SBC8360 device closed unexpectedly.  SBC8360 will not stop!\n");
 
 	clear_bit(0, &sbc8360_is_open);
 	expect_close = 0;
@@ -334,20 +332,19 @@ static int __init sbc8360_init(void)
 	unsigned long int mseconds = 60000;
 
 	if (timeout < 0 || timeout > 63) {
-		printk(KERN_ERR PFX "Invalid timeout index (must be 0-63).\n");
+		pr_err("Invalid timeout index (must be 0-63)\n");
 		res = -EINVAL;
 		goto out;
 	}
 
 	if (!request_region(SBC8360_ENABLE, 1, "SBC8360")) {
-		printk(KERN_ERR PFX "ENABLE method I/O %X is not available.\n",
+		pr_err("ENABLE method I/O %X is not available\n",
 		       SBC8360_ENABLE);
 		res = -EIO;
 		goto out;
 	}
 	if (!request_region(SBC8360_BASETIME, 1, "SBC8360")) {
-		printk(KERN_ERR PFX
-		       "BASETIME method I/O %X is not available.\n",
+		pr_err("BASETIME method I/O %X is not available\n",
 		       SBC8360_BASETIME);
 		res = -EIO;
 		goto out_nobasetimereg;
@@ -355,13 +352,13 @@ static int __init sbc8360_init(void)
 
 	res = register_reboot_notifier(&sbc8360_notifier);
 	if (res) {
-		printk(KERN_ERR PFX "Failed to register reboot notifier.\n");
+		pr_err("Failed to register reboot notifier\n");
 		goto out_noreboot;
 	}
 
 	res = misc_register(&sbc8360_miscdev);
 	if (res) {
-		printk(KERN_ERR PFX "failed to register misc device\n");
+		pr_err("failed to register misc device\n");
 		goto out_nomisc;
 	}
 
@@ -378,7 +375,7 @@ static int __init sbc8360_init(void)
 		mseconds = (wd_margin + 1) * 100000;
 
 	/* My kingdom for the ability to print "0.5 seconds" in the kernel! */
-	printk(KERN_INFO PFX "Timeout set at %ld ms.\n", mseconds);
+	pr_info("Timeout set at %ld ms\n", mseconds);
 
 	return 0;
 
diff --git a/drivers/watchdog/sbc_epx_c3.c b/drivers/watchdog/sbc_epx_c3.c
index eaca366b7234..0c3e9f66ef77 100644
--- a/drivers/watchdog/sbc_epx_c3.c
+++ b/drivers/watchdog/sbc_epx_c3.c
@@ -13,6 +13,8 @@
  *	based on softdog.c by Alan Cox <alan@lxorguk.ukuu.org.uk>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -28,13 +30,12 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
-#define PFX "epx_c3: "
 static int epx_c3_alive;
 
 #define WATCHDOG_TIMEOUT 1		/* 1 sec default timeout */
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 					__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -51,7 +52,7 @@ static void epx_c3_stop(void)
 
 	outb(0, EPXC3_WATCHDOG_CTL_REG);
 
-	printk(KERN_INFO PFX "Stopped watchdog timer.\n");
+	pr_info("Stopped watchdog timer\n");
 }
 
 static void epx_c3_pet(void)
@@ -75,7 +76,7 @@ static int epx_c3_open(struct inode *inode, struct file *file)
 	epx_c3_pet();
 
 	epx_c3_alive = 1;
-	printk(KERN_INFO "Started watchdog timer.\n");
+	pr_info("Started watchdog timer\n");
 
 	return nonseekable_open(inode, file);
 }
@@ -173,9 +174,6 @@ static struct notifier_block epx_c3_notifier = {
 	.notifier_call = epx_c3_notify_sys,
 };
 
-static const char banner[] __initconst = KERN_INFO PFX
-	"Hardware Watchdog Timer for Winsystems EPX-C3 SBC: 0.1\n";
-
 static int __init watchdog_init(void)
 {
 	int ret;
@@ -185,20 +183,19 @@ static int __init watchdog_init(void)
 
 	ret = register_reboot_notifier(&epx_c3_notifier);
 	if (ret) {
-		printk(KERN_ERR PFX "cannot register reboot notifier "
-			"(err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto out;
 	}
 
 	ret = misc_register(&epx_c3_miscdev);
 	if (ret) {
-		printk(KERN_ERR PFX "cannot register miscdev on minor=%d "
-			"(err=%d)\n", WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		unregister_reboot_notifier(&epx_c3_notifier);
 		goto out;
 	}
 
-	printk(banner);
+	pr_info("Hardware Watchdog Timer for Winsystems EPX-C3 SBC: 0.1\n");
 
 	return 0;
 
diff --git a/drivers/watchdog/sbc_fitpc2_wdt.c b/drivers/watchdog/sbc_fitpc2_wdt.c
index d5d399464599..90d5527ca886 100644
--- a/drivers/watchdog/sbc_fitpc2_wdt.c
+++ b/drivers/watchdog/sbc_fitpc2_wdt.c
@@ -25,9 +25,8 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static unsigned int margin = 60;	/* (secs) Default is 1 minute */
 static unsigned long wdt_status;
 static DEFINE_MUTEX(wdt_lock);
@@ -171,8 +170,7 @@ static int fitpc2_wdt_release(struct inode *inode, struct file *file)
 		wdt_disable();
 		pr_info("Device disabled\n");
 	} else {
-		pr_warning("Device closed unexpectedly -"
-			" timer will not stop\n");
+		pr_warn("Device closed unexpectedly - timer will not stop\n");
 		wdt_enable();
 	}
 
@@ -222,8 +220,8 @@ static int __init fitpc2_wdt_init(void)
 	}
 
 	if (margin < 31 || margin > 255) {
-		pr_err("margin must be in range 31 - 255"
-		       " seconds, you tried to set %d\n", margin);
+		pr_err("margin must be in range 31 - 255 seconds, you tried to set %d\n",
+		       margin);
 		err = -EINVAL;
 		goto err_margin;
 	}
@@ -231,7 +229,7 @@ static int __init fitpc2_wdt_init(void)
 	err = misc_register(&fitpc2_wdt_miscdev);
 	if (err) {
 		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, err);
+		       WATCHDOG_MINOR, err);
 		goto err_margin;
 	}
 
@@ -261,7 +259,7 @@ MODULE_DESCRIPTION("SBC-FITPC2 Watchdog");
 module_param(margin, int, 0);
 MODULE_PARM_DESC(margin, "Watchdog margin in seconds (default 60s)");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/sc1200wdt.c b/drivers/watchdog/sc1200wdt.c
index c01daca8405a..3fb83b0c28c2 100644
--- a/drivers/watchdog/sc1200wdt.c
+++ b/drivers/watchdog/sc1200wdt.c
@@ -31,6 +31,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/miscdevice.h>
@@ -48,7 +50,6 @@
 
 #define SC1200_MODULE_VER	"build 20020303"
 #define SC1200_MODULE_NAME	"sc1200wdt"
-#define PFX			SC1200_MODULE_NAME ": "
 
 #define	MAX_TIMEOUT	255	/* 255 minutes */
 #define PMIR		(io)	/* Power Management Index Register */
@@ -71,7 +72,6 @@
 #define UART2_IRQ	0x04	/* Serial1 */
 /* 5 -7 are reserved */
 
-static char banner[] __initdata = PFX SC1200_MODULE_VER;
 static int timeout = 1;
 static int io = -1;
 static int io_len = 2;		/* for non plug and play */
@@ -93,8 +93,8 @@ MODULE_PARM_DESC(io, "io port");
 module_param(timeout, int, 0);
 MODULE_PARM_DESC(timeout, "range is 0-255 minutes, default is 1");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -176,7 +176,7 @@ static int sc1200wdt_open(struct inode *inode, struct file *file)
 		timeout = MAX_TIMEOUT;
 
 	sc1200wdt_start();
-	printk(KERN_INFO PFX "Watchdog enabled, timeout = %d min(s)", timeout);
+	pr_info("Watchdog enabled, timeout = %d min(s)", timeout);
 
 	return nonseekable_open(inode, file);
 }
@@ -254,11 +254,10 @@ static int sc1200wdt_release(struct inode *inode, struct file *file)
 {
 	if (expect_close == 42) {
 		sc1200wdt_stop();
-		printk(KERN_INFO PFX "Watchdog disabled\n");
+		pr_info("Watchdog disabled\n");
 	} else {
 		sc1200wdt_write_data(WDTO, timeout);
-		printk(KERN_CRIT PFX
-			"Unexpected close!, timeout = %d min(s)\n", timeout);
+		pr_crit("Unexpected close!, timeout = %d min(s)\n", timeout);
 	}
 	clear_bit(0, &open_flag);
 	expect_close = 0;
@@ -361,12 +360,11 @@ static int scl200wdt_pnp_probe(struct pnp_dev *dev,
 	io_len = pnp_port_len(wdt_dev, 0);
 
 	if (!request_region(io, io_len, SC1200_MODULE_NAME)) {
-		printk(KERN_ERR PFX "Unable to register IO port %#x\n", io);
+		pr_err("Unable to register IO port %#x\n", io);
 		return -EBUSY;
 	}
 
-	printk(KERN_INFO "scl200wdt: PnP device found at io port %#x/%d\n",
-								io, io_len);
+	pr_info("PnP device found at io port %#x/%d\n", io, io_len);
 	return 0;
 }
 
@@ -392,7 +390,7 @@ static int __init sc1200wdt_init(void)
 {
 	int ret;
 
-	printk(KERN_INFO "%s\n", banner);
+	pr_info("%s\n", SC1200_MODULE_VER);
 
 #if defined CONFIG_PNP
 	if (isapnp) {
@@ -403,7 +401,7 @@ static int __init sc1200wdt_init(void)
 #endif
 
 	if (io == -1) {
-		printk(KERN_ERR PFX "io parameter must be specified\n");
+		pr_err("io parameter must be specified\n");
 		ret = -EINVAL;
 		goto out_pnp;
 	}
@@ -416,7 +414,7 @@ static int __init sc1200wdt_init(void)
 #endif
 
 	if (!request_region(io, io_len, SC1200_MODULE_NAME)) {
-		printk(KERN_ERR PFX "Unable to register IO port %#x\n", io);
+		pr_err("Unable to register IO port %#x\n", io);
 		ret = -EBUSY;
 		goto out_pnp;
 	}
@@ -427,16 +425,14 @@ static int __init sc1200wdt_init(void)
 
 	ret = register_reboot_notifier(&sc1200wdt_notifier);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"Unable to register reboot notifier err = %d\n", ret);
+		pr_err("Unable to register reboot notifier err = %d\n", ret);
 		goto out_io;
 	}
 
 	ret = misc_register(&sc1200wdt_miscdev);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"Unable to register miscdev on minor %d\n",
-							WATCHDOG_MINOR);
+		pr_err("Unable to register miscdev on minor %d\n",
+		       WATCHDOG_MINOR);
 		goto out_rbt;
 	}
 
diff --git a/drivers/watchdog/sc520_wdt.c b/drivers/watchdog/sc520_wdt.c
index b2840409ebc7..707e027e5002 100644
--- a/drivers/watchdog/sc520_wdt.c
+++ b/drivers/watchdog/sc520_wdt.c
@@ -52,6 +52,8 @@
  *  This driver uses memory mapped IO, and spinlock.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -67,10 +69,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
-
-#define OUR_NAME "sc520_wdt"
-#define PFX OUR_NAME ": "
 
 /*
  * The AMD Elan SC520 timeout value is 492us times a power of 2 (0-7)
@@ -98,8 +96,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. (1 <= timeout <= 3600, default="
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -151,8 +149,7 @@ static void wdt_timer_ping(unsigned long data)
 		/* Re-set the timer interval */
 		mod_timer(&timer, jiffies + WDT_INTERVAL);
 	} else
-		printk(KERN_WARNING PFX
-			"Heartbeat lost! Will not ping the watchdog\n");
+		pr_warn("Heartbeat lost! Will not ping the watchdog\n");
 }
 
 /*
@@ -187,7 +184,7 @@ static int wdt_startup(void)
 	/* Start the watchdog */
 	wdt_config(WDT_ENB | WDT_WRST_ENB | WDT_EXP_SEL_04);
 
-	printk(KERN_INFO PFX "Watchdog timer is now enabled.\n");
+	pr_info("Watchdog timer is now enabled\n");
 	return 0;
 }
 
@@ -199,7 +196,7 @@ static int wdt_turnoff(void)
 	/* Stop the watchdog */
 	wdt_config(0);
 
-	printk(KERN_INFO PFX "Watchdog timer is now disabled...\n");
+	pr_info("Watchdog timer is now disabled...\n");
 	return 0;
 }
 
@@ -270,8 +267,7 @@ static int fop_close(struct inode *inode, struct file *file)
 	if (wdt_expect_close == 42)
 		wdt_turnoff();
 	else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		wdt_keepalive();
 	}
 	clear_bit(0, &wdt_is_open);
@@ -393,36 +389,32 @@ static int __init sc520_wdt_init(void)
 	   if not reset to the default */
 	if (wdt_set_heartbeat(timeout)) {
 		wdt_set_heartbeat(WATCHDOG_TIMEOUT);
-		printk(KERN_INFO PFX
-		    "timeout value must be 1 <= timeout <= 3600, using %d\n",
-							WATCHDOG_TIMEOUT);
+		pr_info("timeout value must be 1 <= timeout <= 3600, using %d\n",
+			WATCHDOG_TIMEOUT);
 	}
 
 	wdtmrctl = ioremap(MMCR_BASE + OFFS_WDTMRCTL, 2);
 	if (!wdtmrctl) {
-		printk(KERN_ERR PFX "Unable to remap memory\n");
+		pr_err("Unable to remap memory\n");
 		rc = -ENOMEM;
 		goto err_out_region2;
 	}
 
 	rc = register_reboot_notifier(&wdt_notifier);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", rc);
+		pr_err("cannot register reboot notifier (err=%d)\n", rc);
 		goto err_out_ioremap;
 	}
 
 	rc = misc_register(&wdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, rc);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, rc);
 		goto err_out_notifier;
 	}
 
-	printk(KERN_INFO PFX
-	   "WDT driver for SC520 initialised. timeout=%d sec (nowayout=%d)\n",
-							timeout, nowayout);
+	pr_info("WDT driver for SC520 initialised. timeout=%d sec (nowayout=%d)\n",
+		timeout, nowayout);
 
 	return 0;
 
diff --git a/drivers/watchdog/sch311x_wdt.c b/drivers/watchdog/sch311x_wdt.c
index 029467e34636..bd86f32d63ab 100644
--- a/drivers/watchdog/sch311x_wdt.c
+++ b/drivers/watchdog/sch311x_wdt.c
@@ -18,6 +18,8 @@
  *	Includes, defines, variables, module parameters, ...
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 /* Includes */
 #include <linux/module.h>		/* For module specific items */
 #include <linux/moduleparam.h>		/* For new moduleparam's */
@@ -37,7 +39,6 @@
 
 /* Module and version information */
 #define DRV_NAME	"sch311x_wdt"
-#define PFX		DRV_NAME ": "
 
 /* Runtime registers */
 #define RESGEN			0x1d
@@ -79,8 +80,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. 1<= timeout <=15300, default="
 		__MODULE_STRING(WATCHDOG_TIMEOUT) ".");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 		__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -323,8 +324,7 @@ static int sch311x_wdt_close(struct inode *inode, struct file *file)
 	if (sch311x_wdt_expect_close == 42) {
 		sch311x_wdt_stop();
 	} else {
-		printk(KERN_CRIT PFX
-				"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		sch311x_wdt_keepalive();
 	}
 	clear_bit(0, &sch311x_wdt_is_open);
@@ -504,20 +504,19 @@ static int __init sch311x_detect(int sio_config_port, unsigned short *addr)
 
 	/* Check if Logical Device Register is currently active */
 	if ((sch311x_sio_inb(sio_config_port, 0x30) & 0x01) == 0)
-		printk(KERN_INFO PFX "Seems that LDN 0x0a is not active...\n");
+		pr_info("Seems that LDN 0x0a is not active...\n");
 
 	/* Get the base address of the runtime registers */
 	base_addr = (sch311x_sio_inb(sio_config_port, 0x60) << 8) |
 			   sch311x_sio_inb(sio_config_port, 0x61);
 	if (!base_addr) {
-		printk(KERN_ERR PFX "Base address not set.\n");
+		pr_err("Base address not set\n");
 		err = -ENODEV;
 		goto exit;
 	}
 	*addr = base_addr;
 
-	printk(KERN_INFO PFX "Found an SMSC SCH311%d chip at 0x%04x\n",
-		dev_id, base_addr);
+	pr_info("Found an SMSC SCH311%d chip at 0x%04x\n", dev_id, base_addr);
 
 exit:
 	sch311x_sio_exit(sio_config_port);
diff --git a/drivers/watchdog/scx200_wdt.c b/drivers/watchdog/scx200_wdt.c
index e67b76c0526c..8ae7c282d465 100644
--- a/drivers/watchdog/scx200_wdt.c
+++ b/drivers/watchdog/scx200_wdt.c
@@ -17,6 +17,8 @@
    of any nature resulting due to the use of this software. This
    software is provided AS-IS with no warranties. */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
@@ -30,7 +32,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
-#define NAME "scx200_wdt"
+#define DEBUG
 
 MODULE_AUTHOR("Christer Weinigel <wingel@nano-system.com>");
 MODULE_DESCRIPTION("NatSemi SCx200 Watchdog Driver");
@@ -41,8 +43,8 @@ static int margin = 60;		/* in seconds */
 module_param(margin, int, 0);
 MODULE_PARM_DESC(margin, "Watchdog margin in seconds");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Disable watchdog shutdown on close");
 
 static u16 wdto_restart;
@@ -66,14 +68,13 @@ static void scx200_wdt_ping(void)
 
 static void scx200_wdt_update_margin(void)
 {
-	printk(KERN_INFO NAME ": timer margin %d seconds\n", margin);
+	pr_info("timer margin %d seconds\n", margin);
 	wdto_restart = margin * W_SCALE;
 }
 
 static void scx200_wdt_enable(void)
 {
-	printk(KERN_DEBUG NAME ": enabling watchdog timer, wdto_restart = %d\n",
-	       wdto_restart);
+	pr_debug("enabling watchdog timer, wdto_restart = %d\n", wdto_restart);
 
 	spin_lock(&scx_lock);
 	outw(0, scx200_cb_base + SCx200_WDT_WDTO);
@@ -86,7 +87,7 @@ static void scx200_wdt_enable(void)
 
 static void scx200_wdt_disable(void)
 {
-	printk(KERN_DEBUG NAME ": disabling watchdog timer\n");
+	pr_debug("disabling watchdog timer\n");
 
 	spin_lock(&scx_lock);
 	outw(0, scx200_cb_base + SCx200_WDT_WDTO);
@@ -108,9 +109,7 @@ static int scx200_wdt_open(struct inode *inode, struct file *file)
 static int scx200_wdt_release(struct inode *inode, struct file *file)
 {
 	if (expect_close != 42)
-		printk(KERN_WARNING NAME
-			": watchdog device closed unexpectedly, "
-			"will not disable the watchdog timer\n");
+		pr_warn("watchdog device closed unexpectedly, will not disable the watchdog timer\n");
 	else if (!nowayout)
 		scx200_wdt_disable();
 	expect_close = 0;
@@ -219,7 +218,7 @@ static int __init scx200_wdt_init(void)
 {
 	int r;
 
-	printk(KERN_DEBUG NAME ": NatSemi SCx200 Watchdog Driver\n");
+	pr_debug("NatSemi SCx200 Watchdog Driver\n");
 
 	/* check that we have found the configuration block */
 	if (!scx200_cb_present())
@@ -228,7 +227,7 @@ static int __init scx200_wdt_init(void)
 	if (!request_region(scx200_cb_base + SCx200_WDT_OFFSET,
 			    SCx200_WDT_SIZE,
 			    "NatSemi SCx200 Watchdog")) {
-		printk(KERN_WARNING NAME ": watchdog I/O region busy\n");
+		pr_warn("watchdog I/O region busy\n");
 		return -EBUSY;
 	}
 
@@ -237,7 +236,7 @@ static int __init scx200_wdt_init(void)
 
 	r = register_reboot_notifier(&scx200_wdt_notifier);
 	if (r) {
-		printk(KERN_ERR NAME ": unable to register reboot notifier");
+		pr_err("unable to register reboot notifier\n");
 		release_region(scx200_cb_base + SCx200_WDT_OFFSET,
 				SCx200_WDT_SIZE);
 		return r;
diff --git a/drivers/watchdog/shwdt.c b/drivers/watchdog/shwdt.c
index a267dc078daf..93958a7763e6 100644
--- a/drivers/watchdog/shwdt.c
+++ b/drivers/watchdog/shwdt.c
@@ -17,6 +17,9 @@
  *     Added expect close support, made emulated timeout runtime changeable
  *     general cleanups, add some ioctls
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/platform_device.h>
@@ -72,7 +75,7 @@ static DEFINE_SPINLOCK(shwdt_lock);
 
 #define WATCHDOG_HEARTBEAT 30			/* 30 sec default heartbeat */
 static int heartbeat = WATCHDOG_HEARTBEAT;	/* in seconds */
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 static unsigned long next_heartbeat;
 
 struct sh_wdt {
@@ -440,20 +443,20 @@ static int __init sh_wdt_init(void)
 		     clock_division_ratio > 0x7)) {
 		clock_division_ratio = WTCSR_CKS_4096;
 
-		pr_info("%s: divisor must be 0x5<=x<=0x7, using %d\n",
-			 DRV_NAME, clock_division_ratio);
+		pr_info("divisor must be 0x5<=x<=0x7, using %d\n",
+			clock_division_ratio);
 	}
 
 	rc = sh_wdt_set_heartbeat(heartbeat);
 	if (unlikely(rc)) {
 		heartbeat = WATCHDOG_HEARTBEAT;
 
-		pr_info("%s: heartbeat value must be 1<=x<=3600, using %d\n",
-			DRV_NAME, heartbeat);
+		pr_info("heartbeat value must be 1<=x<=3600, using %d\n",
+			heartbeat);
 	}
 
-	pr_info("%s: configured with heartbeat=%d sec (nowayout=%d)\n",
-		DRV_NAME, heartbeat, nowayout);
+	pr_info("configured with heartbeat=%d sec (nowayout=%d)\n",
+		heartbeat, nowayout);
 
 	return platform_driver_register(&sh_wdt_driver);
 }
@@ -481,7 +484,7 @@ MODULE_PARM_DESC(heartbeat,
 	"Watchdog heartbeat in seconds. (1 <= heartbeat <= 3600, default="
 				__MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
diff --git a/drivers/watchdog/smsc37b787_wdt.c b/drivers/watchdog/smsc37b787_wdt.c
index 97b8184614ae..6d665f9c1d58 100644
--- a/drivers/watchdog/smsc37b787_wdt.c
+++ b/drivers/watchdog/smsc37b787_wdt.c
@@ -43,6 +43,8 @@
  *   Documentation/watchdog/wdt.txt
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -58,7 +60,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 /* enable support for minutes as units? */
 /* (does not always work correctly, so disabled by default!) */
@@ -70,7 +71,6 @@
 #define UNIT_SECOND     0
 #define UNIT_MINUTE     1
 
-#define MODNAME		"smsc37b787_wdt: "
 #define VERSION		"1.1"
 
 #define IOPORT		0x3F0
@@ -85,7 +85,7 @@ static char expect_close;       /* is the close expected? */
 
 static DEFINE_SPINLOCK(io_lock);/* to guard the watchdog from io races */
 
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 /* -- Low level function ----------------------------------------*/
 
@@ -363,8 +363,7 @@ static int wb_smsc_wdt_open(struct inode *inode, struct file *file)
 	/* Reload and activate timer */
 	wb_smsc_wdt_enable();
 
-	printk(KERN_INFO MODNAME
-		"Watchdog enabled. Timeout set to %d %s.\n",
+	pr_info("Watchdog enabled. Timeout set to %d %s\n",
 		timeout, (unit == UNIT_SECOND) ? "second(s)" : "minute(s)");
 
 	return nonseekable_open(inode, file);
@@ -378,11 +377,9 @@ static int wb_smsc_wdt_release(struct inode *inode, struct file *file)
 
 	if (expect_close == 42) {
 		wb_smsc_wdt_disable();
-		printk(KERN_INFO MODNAME
-				"Watchdog disabled, sleeping again...\n");
+		pr_info("Watchdog disabled, sleeping again...\n");
 	} else {
-		printk(KERN_CRIT MODNAME
-				"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		wb_smsc_wdt_reset_timer();
 	}
 
@@ -534,12 +531,11 @@ static int __init wb_smsc_wdt_init(void)
 {
 	int ret;
 
-	printk(KERN_INFO "SMsC 37B787 watchdog component driver "
-					VERSION " initialising...\n");
+	pr_info("SMsC 37B787 watchdog component driver "
+		VERSION " initialising...\n");
 
 	if (!request_region(IOPORT, IOPORT_SIZE, "SMsC 37B787 watchdog")) {
-		printk(KERN_ERR MODNAME "Unable to register IO port %#x\n",
-								IOPORT);
+		pr_err("Unable to register IO port %#x\n", IOPORT);
 		ret = -EBUSY;
 		goto out_pnp;
 	}
@@ -553,25 +549,22 @@ static int __init wb_smsc_wdt_init(void)
 
 	ret = register_reboot_notifier(&wb_smsc_wdt_notifier);
 	if (ret) {
-		printk(KERN_ERR MODNAME
-			"Unable to register reboot notifier err = %d\n", ret);
+		pr_err("Unable to register reboot notifier err = %d\n", ret);
 		goto out_io;
 	}
 
 	ret = misc_register(&wb_smsc_wdt_miscdev);
 	if (ret) {
-		printk(KERN_ERR MODNAME
-			"Unable to register miscdev on minor %d\n",
-							WATCHDOG_MINOR);
+		pr_err("Unable to register miscdev on minor %d\n",
+		       WATCHDOG_MINOR);
 		goto out_rbt;
 	}
 
 	/* output info */
-	printk(KERN_INFO MODNAME "Timeout set to %d %s.\n",
+	pr_info("Timeout set to %d %s\n",
 		timeout, (unit == UNIT_SECOND) ? "second(s)" : "minute(s)");
-	printk(KERN_INFO MODNAME
-		"Watchdog initialized and sleeping (nowayout=%d)...\n",
-								nowayout);
+	pr_info("Watchdog initialized and sleeping (nowayout=%d)...\n",
+		nowayout);
 out_clean:
 	return ret;
 
@@ -592,14 +585,14 @@ static void __exit wb_smsc_wdt_exit(void)
 	/* Stop the timer before we leave */
 	if (!nowayout) {
 		wb_smsc_wdt_shutdown();
-		printk(KERN_INFO MODNAME "Watchdog disabled.\n");
+		pr_info("Watchdog disabled\n");
 	}
 
 	misc_deregister(&wb_smsc_wdt_miscdev);
 	unregister_reboot_notifier(&wb_smsc_wdt_notifier);
 	release_region(IOPORT, IOPORT_SIZE);
 
-	printk(KERN_INFO "SMsC 37B787 watchdog component driver removed.\n");
+	pr_info("SMsC 37B787 watchdog component driver removed\n");
 }
 
 module_init(wb_smsc_wdt_init);
@@ -621,7 +614,7 @@ MODULE_PARM_DESC(unit,
 module_param(timeout, int, 0);
 MODULE_PARM_DESC(timeout, "range is 1-255 units, default is 60");
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
diff --git a/drivers/watchdog/softdog.c b/drivers/watchdog/softdog.c
index bf16ffb4d21e..fe83beb8f1b7 100644
--- a/drivers/watchdog/softdog.c
+++ b/drivers/watchdog/softdog.c
@@ -1,5 +1,5 @@
 /*
- *	SoftDog	0.07:	A Software Watchdog Device
+ *	SoftDog:	A Software Watchdog Device
  *
  *	(c) Copyright 1996 Alan Cox <alan@lxorguk.ukuu.org.uk>,
  *							All Rights Reserved.
@@ -36,45 +36,37 @@
  *	Added Matt Domsch's nowayout module option.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/timer.h>
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
-#include <linux/fs.h>
 #include <linux/notifier.h>
 #include <linux/reboot.h>
 #include <linux/init.h>
 #include <linux/jiffies.h>
-#include <linux/uaccess.h>
 #include <linux/kernel.h>
 
-#define PFX "SoftDog: "
-
 #define TIMER_MARGIN	60		/* Default is 60 seconds */
-static int soft_margin = TIMER_MARGIN;	/* in seconds */
-module_param(soft_margin, int, 0);
+static unsigned int soft_margin = TIMER_MARGIN;	/* in seconds */
+module_param(soft_margin, uint, 0);
 MODULE_PARM_DESC(soft_margin,
 	"Watchdog soft_margin in seconds. (0 < soft_margin < 65536, default="
 					__MODULE_STRING(TIMER_MARGIN) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
-#ifdef ONLY_TESTING
-static int soft_noboot = 1;
-#else
 static int soft_noboot = 0;
-#endif  /* ONLY_TESTING */
-
 module_param(soft_noboot, int, 0);
 MODULE_PARM_DESC(soft_noboot,
-	"Softdog action, set to 1 to ignore reboots, 0 to reboot "
-					"(default depends on ONLY_TESTING)");
+	"Softdog action, set to 1 to ignore reboots, 0 to reboot (default=0)");
 
 static int soft_panic;
 module_param(soft_panic, int, 0);
@@ -89,9 +81,6 @@ static void watchdog_fire(unsigned long);
 
 static struct timer_list watchdog_ticktock =
 		TIMER_INITIALIZER(watchdog_fire, 0, 0);
-static unsigned long driver_open, orphan_timer;
-static char expect_close;
-
 
 /*
  *	If the timer expires..
@@ -99,18 +88,15 @@ static char expect_close;
 
 static void watchdog_fire(unsigned long data)
 {
-	if (test_and_clear_bit(0, &orphan_timer))
-		module_put(THIS_MODULE);
-
 	if (soft_noboot)
-		printk(KERN_CRIT PFX "Triggered - Reboot ignored.\n");
+		pr_crit("Triggered - Reboot ignored\n");
 	else if (soft_panic) {
-		printk(KERN_CRIT PFX "Initiating panic.\n");
-		panic("Software Watchdog Timer expired.");
+		pr_crit("Initiating panic\n");
+		panic("Software Watchdog Timer expired");
 	} else {
-		printk(KERN_CRIT PFX "Initiating system reboot.\n");
+		pr_crit("Initiating system reboot\n");
 		emergency_restart();
-		printk(KERN_CRIT PFX "Reboot didn't ?????\n");
+		pr_crit("Reboot didn't ?????\n");
 	}
 }
 
@@ -118,127 +104,24 @@ static void watchdog_fire(unsigned long data)
  *	Softdog operations
  */
 
-static int softdog_keepalive(void)
+static int softdog_ping(struct watchdog_device *w)
 {
-	mod_timer(&watchdog_ticktock, jiffies+(soft_margin*HZ));
+	mod_timer(&watchdog_ticktock, jiffies+(w->timeout*HZ));
 	return 0;
 }
 
-static int softdog_stop(void)
+static int softdog_stop(struct watchdog_device *w)
 {
 	del_timer(&watchdog_ticktock);
 	return 0;
 }
 
-static int softdog_set_heartbeat(int t)
-{
-	if ((t < 0x0001) || (t > 0xFFFF))
-		return -EINVAL;
-
-	soft_margin = t;
-	return 0;
-}
-
-/*
- *	/dev/watchdog handling
- */
-
-static int softdog_open(struct inode *inode, struct file *file)
-{
-	if (test_and_set_bit(0, &driver_open))
-		return -EBUSY;
-	if (!test_and_clear_bit(0, &orphan_timer))
-		__module_get(THIS_MODULE);
-	/*
-	 *	Activate timer
-	 */
-	softdog_keepalive();
-	return nonseekable_open(inode, file);
-}
-
-static int softdog_release(struct inode *inode, struct file *file)
+static int softdog_set_timeout(struct watchdog_device *w, unsigned int t)
 {
-	/*
-	 *	Shut off the timer.
-	 *	Lock it in if it's a module and we set nowayout
-	 */
-	if (expect_close == 42) {
-		softdog_stop();
-		module_put(THIS_MODULE);
-	} else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
-		set_bit(0, &orphan_timer);
-		softdog_keepalive();
-	}
-	clear_bit(0, &driver_open);
-	expect_close = 0;
+	w->timeout = t;
 	return 0;
 }
 
-static ssize_t softdog_write(struct file *file, const char __user *data,
-						size_t len, loff_t *ppos)
-{
-	/*
-	 *	Refresh the timer.
-	 */
-	if (len) {
-		if (!nowayout) {
-			size_t i;
-
-			/* In case it was set long ago */
-			expect_close = 0;
-
-			for (i = 0; i != len; i++) {
-				char c;
-
-				if (get_user(c, data + i))
-					return -EFAULT;
-				if (c == 'V')
-					expect_close = 42;
-			}
-		}
-		softdog_keepalive();
-	}
-	return len;
-}
-
-static long softdog_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-	int __user *p = argp;
-	int new_margin;
-	static const struct watchdog_info ident = {
-		.options =		WDIOF_SETTIMEOUT |
-					WDIOF_KEEPALIVEPING |
-					WDIOF_MAGICCLOSE,
-		.firmware_version =	0,
-		.identity =		"Software Watchdog",
-	};
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		return copy_to_user(argp, &ident, sizeof(ident)) ? -EFAULT : 0;
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, p);
-	case WDIOC_KEEPALIVE:
-		softdog_keepalive();
-		return 0;
-	case WDIOC_SETTIMEOUT:
-		if (get_user(new_margin, p))
-			return -EFAULT;
-		if (softdog_set_heartbeat(new_margin))
-			return -EINVAL;
-		softdog_keepalive();
-		/* Fall */
-	case WDIOC_GETTIMEOUT:
-		return put_user(soft_margin, p);
-	default:
-		return -ENOTTY;
-	}
-}
-
 /*
  *	Notifier for system down
  */
@@ -248,7 +131,7 @@ static int softdog_notify_sys(struct notifier_block *this, unsigned long code,
 {
 	if (code == SYS_DOWN || code == SYS_HALT)
 		/* Turn the WDT off */
-		softdog_stop();
+		softdog_stop(NULL);
 	return NOTIFY_DONE;
 }
 
@@ -256,28 +139,29 @@ static int softdog_notify_sys(struct notifier_block *this, unsigned long code,
  *	Kernel Interfaces
  */
 
-static const struct file_operations softdog_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.write		= softdog_write,
-	.unlocked_ioctl	= softdog_ioctl,
-	.open		= softdog_open,
-	.release	= softdog_release,
+static struct notifier_block softdog_notifier = {
+	.notifier_call	= softdog_notify_sys,
 };
 
-static struct miscdevice softdog_miscdev = {
-	.minor		= WATCHDOG_MINOR,
-	.name		= "watchdog",
-	.fops		= &softdog_fops,
+static struct watchdog_info softdog_info = {
+	.identity = "Software Watchdog",
+	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
 };
 
-static struct notifier_block softdog_notifier = {
-	.notifier_call	= softdog_notify_sys,
+static struct watchdog_ops softdog_ops = {
+	.owner = THIS_MODULE,
+	.start = softdog_ping,
+	.stop = softdog_stop,
+	.ping = softdog_ping,
+	.set_timeout = softdog_set_timeout,
 };
 
-static char banner[] __initdata = KERN_INFO "Software Watchdog Timer: 0.07 "
-	"initialized. soft_noboot=%d soft_margin=%d sec soft_panic=%d "
-	"(nowayout= %d)\n";
+static struct watchdog_device softdog_dev = {
+	.info = &softdog_info,
+	.ops = &softdog_ops,
+	.min_timeout = 1,
+	.max_timeout = 0xFFFF
+};
 
 static int __init watchdog_init(void)
 {
@@ -285,37 +169,36 @@ static int __init watchdog_init(void)
 
 	/* Check that the soft_margin value is within it's range;
 	   if not reset to the default */
-	if (softdog_set_heartbeat(soft_margin)) {
-		softdog_set_heartbeat(TIMER_MARGIN);
-		printk(KERN_INFO PFX
-		    "soft_margin must be 0 < soft_margin < 65536, using %d\n",
+	if (soft_margin < 1 || soft_margin > 65535) {
+		pr_info("soft_margin must be 0 < soft_margin < 65536, using %d\n",
 			TIMER_MARGIN);
+		return -EINVAL;
 	}
+	softdog_dev.timeout = soft_margin;
+
+	watchdog_set_nowayout(&softdog_dev, nowayout);
 
 	ret = register_reboot_notifier(&softdog_notifier);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		return ret;
 	}
 
-	ret = misc_register(&softdog_miscdev);
+	ret = watchdog_register_device(&softdog_dev);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						WATCHDOG_MINOR, ret);
 		unregister_reboot_notifier(&softdog_notifier);
 		return ret;
 	}
 
-	printk(banner, soft_noboot, soft_margin, soft_panic, nowayout);
+	pr_info("Software Watchdog Timer: 0.08 initialized. soft_noboot=%d soft_margin=%d sec soft_panic=%d (nowayout=%d)\n",
+		soft_noboot, soft_margin, soft_panic, nowayout);
 
 	return 0;
 }
 
 static void __exit watchdog_exit(void)
 {
-	misc_deregister(&softdog_miscdev);
+	watchdog_unregister_device(&softdog_dev);
 	unregister_reboot_notifier(&softdog_notifier);
 }
 
diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c
index 87e0527669d8..59108e48ada3 100644
--- a/drivers/watchdog/sp5100_tco.c
+++ b/drivers/watchdog/sp5100_tco.c
@@ -20,6 +20,8 @@
  *	Includes, defines, variables, module parameters, ...
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -39,7 +41,6 @@
 #define TCO_VERSION "0.01"
 #define TCO_MODULE_NAME "SP5100 TCO timer"
 #define TCO_DRIVER_NAME   TCO_MODULE_NAME ", v" TCO_VERSION
-#define PFX TCO_MODULE_NAME ": "
 
 /* internal variables */
 static u32 tcobase_phys;
@@ -61,8 +62,8 @@ module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds. (default="
 		 __MODULE_STRING(WATCHDOG_HEARTBEAT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started"
 		" (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -143,8 +144,7 @@ static int sp5100_tco_release(struct inode *inode, struct file *file)
 	if (tco_expect_close == 42) {
 		tco_timer_stop();
 	} else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		tco_timer_keepalive();
 	}
 	clear_bit(0, &timer_alive);
@@ -290,8 +290,7 @@ static unsigned char __devinit sp5100_tco_setupdevice(void)
 	/* Request the IO ports used by this driver */
 	pm_iobase = SP5100_IO_PM_INDEX_REG;
 	if (!request_region(pm_iobase, SP5100_PM_IOPORTS_SIZE, "SP5100 TCO")) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			pm_iobase);
+		pr_err("I/O address 0x%04x already in use\n", pm_iobase);
 		goto exit;
 	}
 
@@ -308,15 +307,14 @@ static unsigned char __devinit sp5100_tco_setupdevice(void)
 
 	if (!request_mem_region_exclusive(val, SP5100_WDT_MEM_MAP_SIZE,
 								"SP5100 TCO")) {
-		printk(KERN_ERR PFX "mmio address 0x%04x already in use\n",
-			val);
+		pr_err("mmio address 0x%04x already in use\n", val);
 		goto unreg_region;
 	}
 	tcobase_phys = val;
 
 	tcobase = ioremap(val, SP5100_WDT_MEM_MAP_SIZE);
 	if (tcobase == 0) {
-		printk(KERN_ERR PFX "failed to get tcobase address\n");
+		pr_err("failed to get tcobase address\n");
 		goto unreg_mem_region;
 	}
 
@@ -375,9 +373,9 @@ static int __devinit sp5100_tco_init(struct platform_device *dev)
 		return -ENODEV;
 
 	/* Check to see if last reboot was due to watchdog timeout */
-	printk(KERN_INFO PFX "Watchdog reboot %sdetected.\n",
-	       readl(SP5100_WDT_CONTROL(tcobase)) & SP5100_PM_WATCHDOG_FIRED ?
-		      "" : "not ");
+	pr_info("Watchdog reboot %sdetected\n",
+		readl(SP5100_WDT_CONTROL(tcobase)) & SP5100_PM_WATCHDOG_FIRED ?
+		"" : "not ");
 
 	/* Clear out the old status */
 	val = readl(SP5100_WDT_CONTROL(tcobase));
@@ -395,16 +393,14 @@ static int __devinit sp5100_tco_init(struct platform_device *dev)
 
 	ret = misc_register(&sp5100_tco_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX "cannot register miscdev on minor="
-		       "%d (err=%d)\n",
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
 		       WATCHDOG_MINOR, ret);
 		goto exit;
 	}
 
 	clear_bit(0, &timer_alive);
 
-	printk(KERN_INFO PFX "initialized (0x%p). heartbeat=%d sec"
-		" (nowayout=%d)\n",
+	pr_info("initialized (0x%p). heartbeat=%d sec (nowayout=%d)\n",
 		tcobase, heartbeat, nowayout);
 
 	return 0;
@@ -455,8 +451,7 @@ static int __init sp5100_tco_init_module(void)
 {
 	int err;
 
-	printk(KERN_INFO PFX "SP5100 TCO WatchDog Timer Driver v%s\n",
-	       TCO_VERSION);
+	pr_info("SP5100 TCO WatchDog Timer Driver v%s\n", TCO_VERSION);
 
 	err = platform_driver_register(&sp5100_tco_driver);
 	if (err)
@@ -480,7 +475,7 @@ static void __exit sp5100_tco_cleanup_module(void)
 {
 	platform_device_unregister(sp5100_tco_platform_device);
 	platform_driver_unregister(&sp5100_tco_driver);
-	printk(KERN_INFO PFX "SP5100 TCO Watchdog Module Unloaded.\n");
+	pr_info("SP5100 TCO Watchdog Module Unloaded\n");
 }
 
 module_init(sp5100_tco_init_module);
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 3ff9e47bd218..bbb170e50055 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -25,6 +25,7 @@
 #include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/pm.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
@@ -55,14 +56,13 @@
 
 /**
  * struct sp805_wdt: sp805 wdt device structure
- *
- * lock: spin lock protecting dev structure and io access
- * base: base address of wdt
- * clk: clock structure of wdt
- * dev: amba device structure of wdt
- * status: current status of wdt
- * load_val: load value to be set for current timeout
- * timeout: current programmed timeout
+ * @lock: spin lock protecting dev structure and io access
+ * @base: base address of wdt
+ * @clk: clock structure of wdt
+ * @adev: amba device structure of wdt
+ * @status: current status of wdt
+ * @load_val: load value to be set for current timeout
+ * @timeout: current programmed timeout
  */
 struct sp805_wdt {
 	spinlock_t			lock;
@@ -78,7 +78,7 @@ struct sp805_wdt {
 
 /* local variables */
 static struct sp805_wdt *wdt;
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
 
 /* This routine finds load value that will reset system in required timout */
 static void wdt_setload(unsigned int timeout)
@@ -113,10 +113,10 @@ static u32 wdt_timeleft(void)
 	rate = clk_get_rate(wdt->clk);
 
 	spin_lock(&wdt->lock);
-	load = readl(wdt->base + WDTVALUE);
+	load = readl_relaxed(wdt->base + WDTVALUE);
 
 	/*If the interrupt is inactive then time left is WDTValue + WDTLoad. */
-	if (!(readl(wdt->base + WDTRIS) & INT_MASK))
+	if (!(readl_relaxed(wdt->base + WDTRIS) & INT_MASK))
 		load += wdt->load_val + 1;
 	spin_unlock(&wdt->lock);
 
@@ -128,14 +128,14 @@ static void wdt_enable(void)
 {
 	spin_lock(&wdt->lock);
 
-	writel(UNLOCK, wdt->base + WDTLOCK);
-	writel(wdt->load_val, wdt->base + WDTLOAD);
-	writel(INT_MASK, wdt->base + WDTINTCLR);
-	writel(INT_ENABLE | RESET_ENABLE, wdt->base + WDTCONTROL);
-	writel(LOCK, wdt->base + WDTLOCK);
+	writel_relaxed(UNLOCK, wdt->base + WDTLOCK);
+	writel_relaxed(wdt->load_val, wdt->base + WDTLOAD);
+	writel_relaxed(INT_MASK, wdt->base + WDTINTCLR);
+	writel_relaxed(INT_ENABLE | RESET_ENABLE, wdt->base + WDTCONTROL);
+	writel_relaxed(LOCK, wdt->base + WDTLOCK);
 
 	/* Flush posted writes. */
-	readl(wdt->base + WDTLOCK);
+	readl_relaxed(wdt->base + WDTLOCK);
 	spin_unlock(&wdt->lock);
 }
 
@@ -144,12 +144,12 @@ static void wdt_disable(void)
 {
 	spin_lock(&wdt->lock);
 
-	writel(UNLOCK, wdt->base + WDTLOCK);
-	writel(0, wdt->base + WDTCONTROL);
-	writel(LOCK, wdt->base + WDTLOCK);
+	writel_relaxed(UNLOCK, wdt->base + WDTLOCK);
+	writel_relaxed(0, wdt->base + WDTCONTROL);
+	writel_relaxed(LOCK, wdt->base + WDTLOCK);
 
 	/* Flush posted writes. */
-	readl(wdt->base + WDTLOCK);
+	readl_relaxed(wdt->base + WDTLOCK);
 	spin_unlock(&wdt->lock);
 }
 
@@ -285,32 +285,33 @@ sp805_wdt_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	int ret = 0;
 
-	if (!request_mem_region(adev->res.start, resource_size(&adev->res),
-				"sp805_wdt")) {
+	if (!devm_request_mem_region(&adev->dev, adev->res.start,
+				resource_size(&adev->res), "sp805_wdt")) {
 		dev_warn(&adev->dev, "Failed to get memory region resource\n");
 		ret = -ENOENT;
 		goto err;
 	}
 
-	wdt = kzalloc(sizeof(*wdt), GFP_KERNEL);
+	wdt = devm_kzalloc(&adev->dev, sizeof(*wdt), GFP_KERNEL);
 	if (!wdt) {
 		dev_warn(&adev->dev, "Kzalloc failed\n");
 		ret = -ENOMEM;
-		goto err_kzalloc;
+		goto err;
+	}
+
+	wdt->base = devm_ioremap(&adev->dev, adev->res.start,
+			resource_size(&adev->res));
+	if (!wdt->base) {
+		ret = -ENOMEM;
+		dev_warn(&adev->dev, "ioremap fail\n");
+		goto err;
 	}
 
 	wdt->clk = clk_get(&adev->dev, NULL);
 	if (IS_ERR(wdt->clk)) {
 		dev_warn(&adev->dev, "Clock not found\n");
 		ret = PTR_ERR(wdt->clk);
-		goto err_clk_get;
-	}
-
-	wdt->base = ioremap(adev->res.start, resource_size(&adev->res));
-	if (!wdt->base) {
-		ret = -ENOMEM;
-		dev_warn(&adev->dev, "ioremap fail\n");
-		goto err_ioremap;
+		goto err;
 	}
 
 	wdt->adev = adev;
@@ -327,14 +328,7 @@ sp805_wdt_probe(struct amba_device *adev, const struct amba_id *id)
 	return 0;
 
 err_misc_register:
-	iounmap(wdt->base);
-err_ioremap:
 	clk_put(wdt->clk);
-err_clk_get:
-	kfree(wdt);
-	wdt = NULL;
-err_kzalloc:
-	release_mem_region(adev->res.start, resource_size(&adev->res));
 err:
 	dev_err(&adev->dev, "Probe Failed!!!\n");
 	return ret;
@@ -343,14 +337,42 @@ err:
 static int __devexit sp805_wdt_remove(struct amba_device *adev)
 {
 	misc_deregister(&sp805_wdt_miscdev);
-	iounmap(wdt->base);
 	clk_put(wdt->clk);
-	kfree(wdt);
-	release_mem_region(adev->res.start, resource_size(&adev->res));
 
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int sp805_wdt_suspend(struct device *dev)
+{
+	if (test_bit(WDT_BUSY, &wdt->status)) {
+		wdt_disable();
+		clk_disable(wdt->clk);
+	}
+
+	return 0;
+}
+
+static int sp805_wdt_resume(struct device *dev)
+{
+	int ret = 0;
+
+	if (test_bit(WDT_BUSY, &wdt->status)) {
+		ret = clk_enable(wdt->clk);
+		if (ret) {
+			dev_err(dev, "clock enable fail");
+			return ret;
+		}
+		wdt_enable();
+	}
+
+	return ret;
+}
+#endif /* CONFIG_PM */
+
+static SIMPLE_DEV_PM_OPS(sp805_wdt_dev_pm_ops, sp805_wdt_suspend,
+		sp805_wdt_resume);
+
 static struct amba_id sp805_wdt_ids[] = {
 	{
 		.id	= 0x00141805,
@@ -364,6 +386,7 @@ MODULE_DEVICE_TABLE(amba, sp805_wdt_ids);
 static struct amba_driver sp805_wdt_driver = {
 	.drv = {
 		.name	= MODULE_NAME,
+		.pm	= &sp805_wdt_dev_pm_ops,
 	},
 	.id_table	= sp805_wdt_ids,
 	.probe		= sp805_wdt_probe,
@@ -372,7 +395,7 @@ static struct amba_driver sp805_wdt_driver = {
 
 module_amba_driver(sp805_wdt_driver);
 
-module_param(nowayout, int, 0);
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Set to 1 to keep watchdog running after device release");
 
diff --git a/drivers/watchdog/stmp3xxx_wdt.c b/drivers/watchdog/stmp3xxx_wdt.c
index e37d81178b9e..21d96b92bfd7 100644
--- a/drivers/watchdog/stmp3xxx_wdt.c
+++ b/drivers/watchdog/stmp3xxx_wdt.c
@@ -6,6 +6,9 @@
  * Copyright 2008 Freescale Semiconductor, Inc. All Rights Reserved.
  * Copyright 2008 Embedded Alley Solutions, Inc All Rights Reserved.
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
@@ -32,7 +35,7 @@
 
 static DEFINE_SPINLOCK(stmp3xxx_wdt_io_lock);
 static unsigned long wdt_status;
-static const int nowayout = WATCHDOG_NOWAYOUT;
+static const bool nowayout = WATCHDOG_NOWAYOUT;
 static int heartbeat = DEFAULT_HEARTBEAT;
 static unsigned long boot_status;
 
@@ -221,8 +224,7 @@ static int __devinit stmp3xxx_wdt_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	printk(KERN_INFO "stmp3xxx watchdog: initialized, heartbeat %d sec\n",
-		heartbeat);
+	pr_info("initialized, heartbeat %d sec\n", heartbeat);
 
 	return ret;
 }
diff --git a/drivers/watchdog/ts72xx_wdt.c b/drivers/watchdog/ts72xx_wdt.c
index 1490293dc7da..8df050d800e6 100644
--- a/drivers/watchdog/ts72xx_wdt.c
+++ b/drivers/watchdog/ts72xx_wdt.c
@@ -34,8 +34,8 @@ MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds. "
 			  __MODULE_STRING(TS72XX_WDT_DEFAULT_TIMEOUT)
 			  ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Disable watchdog shutdown on close");
 
 /**
diff --git a/drivers/watchdog/twl4030_wdt.c b/drivers/watchdog/twl4030_wdt.c
index 0764c6239b98..249f11305d26 100644
--- a/drivers/watchdog/twl4030_wdt.c
+++ b/drivers/watchdog/twl4030_wdt.c
@@ -42,8 +42,8 @@ struct twl4030_wdt {
 	unsigned long		state;
 };
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 	"(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
diff --git a/drivers/watchdog/txx9wdt.c b/drivers/watchdog/txx9wdt.c
index 9e9ed7bfabcb..98e16373e640 100644
--- a/drivers/watchdog/txx9wdt.c
+++ b/drivers/watchdog/txx9wdt.c
@@ -7,177 +7,99 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
-#include <linux/fs.h>
 #include <linux/init.h>
-#include <linux/uaccess.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <asm/txx9tmr.h>
 
+#define WD_TIMER_CCD	7		/* 1/256 */
+#define WD_TIMER_CLK	(clk_get_rate(txx9_imclk) / (2 << WD_TIMER_CCD))
+#define WD_MAX_TIMEOUT	((0xffffffff >> (32 - TXX9_TIMER_BITS)) / WD_TIMER_CLK)
 #define TIMER_MARGIN	60		/* Default is 60 seconds */
 
-static int timeout = TIMER_MARGIN;	/* in seconds */
-module_param(timeout, int, 0);
+static unsigned int timeout = TIMER_MARGIN;	/* in seconds */
+module_param(timeout, uint, 0);
 MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. "
 	"(0<timeout<((2^" __MODULE_STRING(TXX9_TIMER_BITS) ")/(IMCLK/256)), "
 	"default=" __MODULE_STRING(TIMER_MARGIN) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started "
 	"(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
-#define WD_TIMER_CCD	7	/* 1/256 */
-#define WD_TIMER_CLK	(clk_get_rate(txx9_imclk) / (2 << WD_TIMER_CCD))
-#define WD_MAX_TIMEOUT	((0xffffffff >> (32 - TXX9_TIMER_BITS)) / WD_TIMER_CLK)
-
-static unsigned long txx9wdt_alive;
-static int expect_close;
 static struct txx9_tmr_reg __iomem *txx9wdt_reg;
 static struct clk *txx9_imclk;
 static DEFINE_SPINLOCK(txx9_lock);
 
-static void txx9wdt_ping(void)
+static int txx9wdt_ping(struct watchdog_device *wdt_dev)
 {
 	spin_lock(&txx9_lock);
 	__raw_writel(TXx9_TMWTMR_TWIE | TXx9_TMWTMR_TWC, &txx9wdt_reg->wtmr);
 	spin_unlock(&txx9_lock);
+	return 0;
 }
 
-static void txx9wdt_start(void)
+static int txx9wdt_start(struct watchdog_device *wdt_dev)
 {
 	spin_lock(&txx9_lock);
-	__raw_writel(WD_TIMER_CLK * timeout, &txx9wdt_reg->cpra);
+	__raw_writel(WD_TIMER_CLK * wdt_dev->timeout, &txx9wdt_reg->cpra);
 	__raw_writel(WD_TIMER_CCD, &txx9wdt_reg->ccdr);
 	__raw_writel(0, &txx9wdt_reg->tisr);	/* clear pending interrupt */
 	__raw_writel(TXx9_TMTCR_TCE | TXx9_TMTCR_CCDE | TXx9_TMTCR_TMODE_WDOG,
 		     &txx9wdt_reg->tcr);
 	__raw_writel(TXx9_TMWTMR_TWIE | TXx9_TMWTMR_TWC, &txx9wdt_reg->wtmr);
 	spin_unlock(&txx9_lock);
+	return 0;
 }
 
-static void txx9wdt_stop(void)
+static int txx9wdt_stop(struct watchdog_device *wdt_dev)
 {
 	spin_lock(&txx9_lock);
 	__raw_writel(TXx9_TMWTMR_WDIS, &txx9wdt_reg->wtmr);
 	__raw_writel(__raw_readl(&txx9wdt_reg->tcr) & ~TXx9_TMTCR_TCE,
 		     &txx9wdt_reg->tcr);
 	spin_unlock(&txx9_lock);
-}
-
-static int txx9wdt_open(struct inode *inode, struct file *file)
-{
-	if (test_and_set_bit(0, &txx9wdt_alive))
-		return -EBUSY;
-
-	if (__raw_readl(&txx9wdt_reg->tcr) & TXx9_TMTCR_TCE) {
-		clear_bit(0, &txx9wdt_alive);
-		return -EBUSY;
-	}
-
-	if (nowayout)
-		__module_get(THIS_MODULE);
-
-	txx9wdt_start();
-	return nonseekable_open(inode, file);
-}
-
-static int txx9wdt_release(struct inode *inode, struct file *file)
-{
-	if (expect_close)
-		txx9wdt_stop();
-	else {
-		printk(KERN_CRIT "txx9wdt: "
-		       "Unexpected close, not stopping watchdog!\n");
-		txx9wdt_ping();
-	}
-	clear_bit(0, &txx9wdt_alive);
-	expect_close = 0;
 	return 0;
 }
 
-static ssize_t txx9wdt_write(struct file *file, const char __user *data,
-			     size_t len, loff_t *ppos)
+static int txx9wdt_set_timeout(struct watchdog_device *wdt_dev,
+			       unsigned int new_timeout)
 {
-	if (len) {
-		if (!nowayout) {
-			size_t i;
-
-			expect_close = 0;
-			for (i = 0; i != len; i++) {
-				char c;
-				if (get_user(c, data + i))
-					return -EFAULT;
-				if (c == 'V')
-					expect_close = 1;
-			}
-		}
-		txx9wdt_ping();
-	}
-	return len;
+	wdt_dev->timeout = new_timeout;
+	txx9wdt_stop(wdt_dev);
+	txx9wdt_start(wdt_dev);
+	return 0;
 }
 
-static long txx9wdt_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-	int __user *p = argp;
-	int new_timeout;
-	static const struct watchdog_info ident = {
-		.options =		WDIOF_SETTIMEOUT |
-					WDIOF_KEEPALIVEPING |
-					WDIOF_MAGICCLOSE,
-		.firmware_version =	0,
-		.identity =		"Hardware Watchdog for TXx9",
-	};
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		return copy_to_user(argp, &ident, sizeof(ident)) ? -EFAULT : 0;
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, p);
-	case WDIOC_KEEPALIVE:
-		txx9wdt_ping();
-		return 0;
-	case WDIOC_SETTIMEOUT:
-		if (get_user(new_timeout, p))
-			return -EFAULT;
-		if (new_timeout < 1 || new_timeout > WD_MAX_TIMEOUT)
-			return -EINVAL;
-		timeout = new_timeout;
-		txx9wdt_stop();
-		txx9wdt_start();
-		/* Fall */
-	case WDIOC_GETTIMEOUT:
-		return put_user(timeout, p);
-	default:
-		return -ENOTTY;
-	}
-}
+static const struct watchdog_info txx9wdt_info = {
+	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
+	.identity = "Hardware Watchdog for TXx9",
+};
 
-static const struct file_operations txx9wdt_fops = {
-	.owner		=	THIS_MODULE,
-	.llseek		=	no_llseek,
-	.write		=	txx9wdt_write,
-	.unlocked_ioctl =	txx9wdt_ioctl,
-	.open		=	txx9wdt_open,
-	.release	=	txx9wdt_release,
+static const struct watchdog_ops txx9wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = txx9wdt_start,
+	.stop = txx9wdt_stop,
+	.ping = txx9wdt_ping,
+	.set_timeout = txx9wdt_set_timeout,
 };
 
-static struct miscdevice txx9wdt_miscdev = {
-	.minor	=	WATCHDOG_MINOR,
-	.name	=	"watchdog",
-	.fops	=	&txx9wdt_fops,
+static struct watchdog_device txx9wdt = {
+	.info = &txx9wdt_info,
+	.ops = &txx9wdt_ops,
 };
 
 static int __init txx9wdt_probe(struct platform_device *dev)
@@ -199,27 +121,27 @@ static int __init txx9wdt_probe(struct platform_device *dev)
 	}
 
 	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	if (!res)
-		goto exit_busy;
-	if (!devm_request_mem_region(&dev->dev, res->start, resource_size(res),
-				     "txx9wdt"))
-		goto exit_busy;
-	txx9wdt_reg = devm_ioremap(&dev->dev, res->start, resource_size(res));
-	if (!txx9wdt_reg)
-		goto exit_busy;
-
-	ret = misc_register(&txx9wdt_miscdev);
-	if (ret) {
+	txx9wdt_reg = devm_request_and_ioremap(&dev->dev, res);
+	if (!txx9wdt_reg) {
+		ret = -EBUSY;
 		goto exit;
 	}
 
-	printk(KERN_INFO "Hardware Watchdog Timer for TXx9: "
-	       "timeout=%d sec (max %ld) (nowayout= %d)\n",
-	       timeout, WD_MAX_TIMEOUT, nowayout);
+	if (timeout < 1 || timeout > WD_MAX_TIMEOUT)
+		timeout = TIMER_MARGIN;
+	txx9wdt.timeout = timeout;
+	txx9wdt.min_timeout = 1;
+	txx9wdt.max_timeout = WD_MAX_TIMEOUT;
+	watchdog_set_nowayout(&txx9wdt, nowayout);
+
+	ret = watchdog_register_device(&txx9wdt);
+	if (ret)
+		goto exit;
+
+	pr_info("Hardware Watchdog Timer: timeout=%d sec (max %ld) (nowayout= %d)\n",
+		timeout, WD_MAX_TIMEOUT, nowayout);
 
 	return 0;
-exit_busy:
-	ret = -EBUSY;
 exit:
 	if (txx9_imclk) {
 		clk_disable(txx9_imclk);
@@ -230,7 +152,7 @@ exit:
 
 static int __exit txx9wdt_remove(struct platform_device *dev)
 {
-	misc_deregister(&txx9wdt_miscdev);
+	watchdog_unregister_device(&txx9wdt);
 	clk_disable(txx9_imclk);
 	clk_put(txx9_imclk);
 	return 0;
@@ -238,7 +160,7 @@ static int __exit txx9wdt_remove(struct platform_device *dev)
 
 static void txx9wdt_shutdown(struct platform_device *dev)
 {
-	txx9wdt_stop();
+	txx9wdt_stop(&txx9wdt);
 }
 
 static struct platform_driver txx9wdt_driver = {
diff --git a/drivers/watchdog/via_wdt.c b/drivers/watchdog/via_wdt.c
index 8f07dd4bd94a..465e08273c97 100644
--- a/drivers/watchdog/via_wdt.c
+++ b/drivers/watchdog/via_wdt.c
@@ -10,6 +10,9 @@
  * Caveat: PnP must be enabled in BIOS to allow full access to watchdog
  * control registers. If not, the watchdog must be configured in BIOS manually.
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/jiffies.h>
@@ -55,8 +58,8 @@ module_param(timeout, int, 0);
 MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds, between 1 and 1023 "
 	"(default = " __MODULE_STRING(WDT_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 	"(default = " __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
@@ -98,7 +101,7 @@ static void wdt_timer_tick(unsigned long data)
 static int wdt_ping(struct watchdog_device *wdd)
 {
 	/* calculate when the next userspace timeout will be */
-	next_heartbeat = jiffies + timeout * HZ;
+	next_heartbeat = jiffies + wdd->timeout * HZ;
 	return 0;
 }
 
@@ -106,7 +109,7 @@ static int wdt_start(struct watchdog_device *wdd)
 {
 	unsigned int ctl = readl(wdt_mem);
 
-	writel(timeout, wdt_mem + VIA_WDT_COUNT);
+	writel(wdd->timeout, wdt_mem + VIA_WDT_COUNT);
 	writel(ctl | VIA_WDT_RUNNING | VIA_WDT_TRIGGER, wdt_mem);
 	wdt_ping(wdd);
 	mod_timer(&timer, jiffies + WDT_HEARTBEAT);
@@ -125,7 +128,7 @@ static int wdt_set_timeout(struct watchdog_device *wdd,
 			   unsigned int new_timeout)
 {
 	writel(new_timeout, wdt_mem + VIA_WDT_COUNT);
-	timeout = new_timeout;
+	wdd->timeout = new_timeout;
 	return 0;
 }
 
diff --git a/drivers/watchdog/w83627hf_wdt.c b/drivers/watchdog/w83627hf_wdt.c
index 576a388a1164..92f1326f0cfc 100644
--- a/drivers/watchdog/w83627hf_wdt.c
+++ b/drivers/watchdog/w83627hf_wdt.c
@@ -26,6 +26,8 @@
  *	(c) Copyright 1995    Alan Cox <alan@lxorguk.ukuu.org.uk>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -40,10 +42,8 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 #define WATCHDOG_NAME "w83627hf/thf/hg/dhg WDT"
-#define PFX WATCHDOG_NAME ": "
 #define WATCHDOG_TIMEOUT 60		/* 60 sec default timeout */
 
 static unsigned long wdt_is_open;
@@ -61,8 +61,8 @@ MODULE_PARM_DESC(timeout,
 		"Watchdog timeout in seconds. 1 <= timeout <= 255, default="
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ".");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -119,9 +119,8 @@ static void w83627hf_init(void)
 	outb_p(0xF6, WDT_EFER); /* Select CRF6 */
 	t = inb_p(WDT_EFDR);      /* read CRF6 */
 	if (t != 0) {
-		printk(KERN_INFO PFX
-		     "Watchdog already running. Resetting timeout to %d sec\n",
-								timeout);
+		pr_info("Watchdog already running. Resetting timeout to %d sec\n",
+			timeout);
 		outb_p(timeout, WDT_EFDR);    /* Write back to CRF6 */
 	}
 
@@ -290,8 +289,7 @@ static int wdt_close(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		wdt_disable();
 	else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		wdt_ping();
 	}
 	expect_close = 0;
@@ -344,18 +342,16 @@ static int __init wdt_init(void)
 {
 	int ret;
 
-	printk(KERN_INFO "WDT driver for the Winbond(TM) W83627HF/THF/HG/DHG Super I/O chip initialising.\n");
+	pr_info("WDT driver for the Winbond(TM) W83627HF/THF/HG/DHG Super I/O chip initialising\n");
 
 	if (wdt_set_heartbeat(timeout)) {
 		wdt_set_heartbeat(WATCHDOG_TIMEOUT);
-		printk(KERN_INFO PFX
-		     "timeout value must be 1 <= timeout <= 255, using %d\n",
-				WATCHDOG_TIMEOUT);
+		pr_info("timeout value must be 1 <= timeout <= 255, using %d\n",
+			WATCHDOG_TIMEOUT);
 	}
 
 	if (!request_region(wdt_io, 1, WATCHDOG_NAME)) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			wdt_io);
+		pr_err("I/O address 0x%04x already in use\n", wdt_io);
 		ret = -EIO;
 		goto out;
 	}
@@ -364,22 +360,19 @@ static int __init wdt_init(void)
 
 	ret = register_reboot_notifier(&wdt_notifier);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto unreg_regions;
 	}
 
 	ret = misc_register(&wdt_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto unreg_reboot;
 	}
 
-	printk(KERN_INFO PFX
-			"initialized. timeout=%d sec (nowayout=%d)\n",
-							timeout, nowayout);
+	pr_info("initialized. timeout=%d sec (nowayout=%d)\n",
+		timeout, nowayout);
 
 out:
 	return ret;
diff --git a/drivers/watchdog/w83697hf_wdt.c b/drivers/watchdog/w83697hf_wdt.c
index af08972de506..cd9f3c1e1af4 100644
--- a/drivers/watchdog/w83697hf_wdt.c
+++ b/drivers/watchdog/w83697hf_wdt.c
@@ -25,6 +25,8 @@
  *	"AS-IS" and at no charge.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -39,10 +41,8 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 #define WATCHDOG_NAME "w83697hf/hg WDT"
-#define PFX WATCHDOG_NAME ": "
 #define WATCHDOG_TIMEOUT 60		/* 60 sec default timeout */
 #define WATCHDOG_EARLY_DISABLE 1	/* Disable until userland kicks in */
 
@@ -62,8 +62,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. 1<= timeout <=255 (default="
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -309,8 +309,7 @@ static int wdt_close(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		wdt_disable();
 	else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		wdt_ping();
 	}
 	expect_close = 0;
@@ -362,24 +361,21 @@ static struct notifier_block wdt_notifier = {
 static int w83697hf_check_wdt(void)
 {
 	if (!request_region(wdt_io, 2, WATCHDOG_NAME)) {
-		printk(KERN_ERR PFX
-			"I/O address 0x%x already in use\n", wdt_io);
+		pr_err("I/O address 0x%x already in use\n", wdt_io);
 		return -EIO;
 	}
 
-	printk(KERN_DEBUG PFX
-			"Looking for watchdog at address 0x%x\n", wdt_io);
+	pr_debug("Looking for watchdog at address 0x%x\n", wdt_io);
 	w83697hf_unlock();
 	if (w83697hf_get_reg(0x20) == 0x60) {
-		printk(KERN_INFO PFX
-			"watchdog found at address 0x%x\n", wdt_io);
+		pr_info("watchdog found at address 0x%x\n", wdt_io);
 		w83697hf_lock();
 		return 0;
 	}
 	/* Reprotect in case it was a compatible device */
 	w83697hf_lock();
 
-	printk(KERN_INFO PFX "watchdog not found at address 0x%x\n", wdt_io);
+	pr_info("watchdog not found at address 0x%x\n", wdt_io);
 	release_region(wdt_io, 2);
 	return -EIO;
 }
@@ -390,7 +386,7 @@ static int __init wdt_init(void)
 {
 	int ret, i, found = 0;
 
-	printk(KERN_INFO PFX "WDT driver for W83697HF/HG initializing\n");
+	pr_info("WDT driver for W83697HF/HG initializing\n");
 
 	if (wdt_io == 0) {
 		/* we will autodetect the W83697HF/HG watchdog */
@@ -405,7 +401,7 @@ static int __init wdt_init(void)
 	}
 
 	if (!found) {
-		printk(KERN_ERR PFX "No W83697HF/HG could be found\n");
+		pr_err("No W83697HF/HG could be found\n");
 		ret = -EIO;
 		goto out;
 	}
@@ -413,34 +409,30 @@ static int __init wdt_init(void)
 	w83697hf_init();
 	if (early_disable) {
 		if (wdt_running())
-			printk(KERN_WARNING PFX "Stopping previously enabled "
-					"watchdog until userland kicks in\n");
+			pr_warn("Stopping previously enabled watchdog until userland kicks in\n");
 		wdt_disable();
 	}
 
 	if (wdt_set_heartbeat(timeout)) {
 		wdt_set_heartbeat(WATCHDOG_TIMEOUT);
-		printk(KERN_INFO PFX
-		     "timeout value must be 1 <= timeout <= 255, using %d\n",
-							WATCHDOG_TIMEOUT);
+		pr_info("timeout value must be 1 <= timeout <= 255, using %d\n",
+			WATCHDOG_TIMEOUT);
 	}
 
 	ret = register_reboot_notifier(&wdt_notifier);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto unreg_regions;
 	}
 
 	ret = misc_register(&wdt_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto unreg_reboot;
 	}
 
-	printk(KERN_INFO PFX "initialized. timeout=%d sec (nowayout=%d)\n",
+	pr_info("initialized. timeout=%d sec (nowayout=%d)\n",
 		timeout, nowayout);
 
 out:
diff --git a/drivers/watchdog/w83697ug_wdt.c b/drivers/watchdog/w83697ug_wdt.c
index be9c4d839e15..274be0bfaf24 100644
--- a/drivers/watchdog/w83697ug_wdt.c
+++ b/drivers/watchdog/w83697ug_wdt.c
@@ -30,6 +30,8 @@
  *	(c) Copyright 1995    Alan Cox <alan@redhat.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -44,10 +46,8 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 #define WATCHDOG_NAME "w83697ug/uf WDT"
-#define PFX WATCHDOG_NAME ": "
 #define WATCHDOG_TIMEOUT 60		/* 60 sec default timeout */
 
 static unsigned long wdt_is_open;
@@ -64,8 +64,8 @@ MODULE_PARM_DESC(timeout,
 	"Watchdog timeout in seconds. 1<= timeout <=255 (default="
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -91,8 +91,8 @@ static int w83697ug_select_wd_register(void)
 	version = inb(WDT_EFDR);
 
 	if (version == 0x68) {	/* W83697UG		*/
-		printk(KERN_INFO PFX "Watchdog chip version 0x%02x = "
-			"W83697UG/UF found at 0x%04x\n", version, wdt_io);
+		pr_info("Watchdog chip version 0x%02x = W83697UG/UF found at 0x%04x\n",
+			version, wdt_io);
 
 		outb_p(0x2b, WDT_EFER);
 		c = inb_p(WDT_EFDR);    /* select WDT0 */
@@ -101,7 +101,7 @@ static int w83697ug_select_wd_register(void)
 		outb_p(c, WDT_EFDR);	/* set pin118 to WDT0 */
 
 	} else {
-		printk(KERN_ERR PFX "No W83697UG/UF could be found\n");
+		pr_err("No W83697UG/UF could be found\n");
 		return -ENODEV;
 	}
 
@@ -131,8 +131,8 @@ static int w83697ug_init(void)
 	outb_p(0xF6, WDT_EFER); /* Select CRF6 */
 	t = inb_p(WDT_EFDR);    /* read CRF6 */
 	if (t != 0) {
-		printk(KERN_INFO PFX "Watchdog already running."
-			" Resetting timeout to %d sec\n", timeout);
+		pr_info("Watchdog already running. Resetting timeout to %d sec\n",
+			timeout);
 		outb_p(timeout, WDT_EFDR);    /* Write back to CRF6 */
 	}
 	outb_p(0xF5, WDT_EFER); /* Select CRF5 */
@@ -286,8 +286,7 @@ static int wdt_close(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		wdt_disable();
 	else {
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 		wdt_ping();
 	}
 	expect_close = 0;
@@ -340,18 +339,16 @@ static int __init wdt_init(void)
 {
 	int ret;
 
-	printk(KERN_INFO "WDT driver for the Winbond(TM) W83697UG/UF Super I/O chip initialising.\n");
+	pr_info("WDT driver for the Winbond(TM) W83697UG/UF Super I/O chip initialising\n");
 
 	if (wdt_set_heartbeat(timeout)) {
 		wdt_set_heartbeat(WATCHDOG_TIMEOUT);
-		printk(KERN_INFO PFX
-			"timeout value must be 1<=timeout<=255, using %d\n",
+		pr_info("timeout value must be 1<=timeout<=255, using %d\n",
 			WATCHDOG_TIMEOUT);
 	}
 
 	if (!request_region(wdt_io, 1, WATCHDOG_NAME)) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			wdt_io);
+		pr_err("I/O address 0x%04x already in use\n", wdt_io);
 		ret = -EIO;
 		goto out;
 	}
@@ -362,20 +359,18 @@ static int __init wdt_init(void)
 
 	ret = register_reboot_notifier(&wdt_notifier);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto unreg_regions;
 	}
 
 	ret = misc_register(&wdt_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-			WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto unreg_reboot;
 	}
 
-	printk(KERN_INFO PFX "initialized. timeout=%d sec (nowayout=%d)\n",
+	pr_info("initialized. timeout=%d sec (nowayout=%d)\n",
 		timeout, nowayout);
 
 out:
diff --git a/drivers/watchdog/w83877f_wdt.c b/drivers/watchdog/w83877f_wdt.c
index 24587d2060c4..7874ae06232b 100644
--- a/drivers/watchdog/w83877f_wdt.c
+++ b/drivers/watchdog/w83877f_wdt.c
@@ -42,6 +42,8 @@
  *  daemon always getting scheduled within that time frame.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -56,10 +58,8 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
-#include <asm/system.h>
 
 #define OUR_NAME "w83877f_wdt"
-#define PFX OUR_NAME ": "
 
 #define ENABLE_W83877F_PORT 0x3F0
 #define ENABLE_W83877F 0x87
@@ -91,8 +91,8 @@ MODULE_PARM_DESC(timeout,
 				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
 
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -126,8 +126,7 @@ static void wdt_timer_ping(unsigned long data)
 		spin_unlock(&wdt_spinlock);
 
 	} else
-		printk(KERN_WARNING PFX
-			"Heartbeat lost! Will not ping the watchdog\n");
+		pr_warn("Heartbeat lost! Will not ping the watchdog\n");
 }
 
 /*
@@ -165,7 +164,7 @@ static void wdt_startup(void)
 
 	wdt_change(WDT_ENABLE);
 
-	printk(KERN_INFO PFX "Watchdog timer is now enabled.\n");
+	pr_info("Watchdog timer is now enabled\n");
 }
 
 static void wdt_turnoff(void)
@@ -175,7 +174,7 @@ static void wdt_turnoff(void)
 
 	wdt_change(WDT_DISABLE);
 
-	printk(KERN_INFO PFX "Watchdog timer is now disabled...\n");
+	pr_info("Watchdog timer is now disabled...\n");
 }
 
 static void wdt_keepalive(void)
@@ -234,8 +233,7 @@ static int fop_close(struct inode *inode, struct file *file)
 		wdt_turnoff();
 	else {
 		del_timer(&timer);
-		printk(KERN_CRIT PFX
-		  "device file closed unexpectedly. Will not stop the WDT!\n");
+		pr_crit("device file closed unexpectedly. Will not stop the WDT!\n");
 	}
 	clear_bit(0, &wdt_is_open);
 	wdt_expect_close = 0;
@@ -357,42 +355,37 @@ static int __init w83877f_wdt_init(void)
 
 	if (timeout < 1 || timeout > 3600) { /* arbitrary upper limit */
 		timeout = WATCHDOG_TIMEOUT;
-		printk(KERN_INFO PFX
-			"timeout value must be 1 <= x <= 3600, using %d\n",
-							timeout);
+		pr_info("timeout value must be 1 <= x <= 3600, using %d\n",
+			timeout);
 	}
 
 	if (!request_region(ENABLE_W83877F_PORT, 2, "W83877F WDT")) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			ENABLE_W83877F_PORT);
+		pr_err("I/O address 0x%04x already in use\n",
+		       ENABLE_W83877F_PORT);
 		rc = -EIO;
 		goto err_out;
 	}
 
 	if (!request_region(WDT_PING, 1, "W8387FF WDT")) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			WDT_PING);
+		pr_err("I/O address 0x%04x already in use\n", WDT_PING);
 		rc = -EIO;
 		goto err_out_region1;
 	}
 
 	rc = register_reboot_notifier(&wdt_notifier);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", rc);
+		pr_err("cannot register reboot notifier (err=%d)\n", rc);
 		goto err_out_region2;
 	}
 
 	rc = misc_register(&wdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							wdt_miscdev.minor, rc);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       wdt_miscdev.minor, rc);
 		goto err_out_reboot;
 	}
 
-	printk(KERN_INFO PFX
-	  "WDT driver for W83877F initialised. timeout=%d sec (nowayout=%d)\n",
+	pr_info("WDT driver for W83877F initialised. timeout=%d sec (nowayout=%d)\n",
 		timeout, nowayout);
 
 	return 0;
diff --git a/drivers/watchdog/w83977f_wdt.c b/drivers/watchdog/w83977f_wdt.c
index 6e6743d1066f..5d2c902825c2 100644
--- a/drivers/watchdog/w83977f_wdt.c
+++ b/drivers/watchdog/w83977f_wdt.c
@@ -15,6 +15,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -29,12 +31,9 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
-#include <asm/system.h>
 
 #define WATCHDOG_VERSION  "1.00"
 #define WATCHDOG_NAME     "W83977F WDT"
-#define PFX WATCHDOG_NAME ": "
-#define DRIVER_VERSION    WATCHDOG_NAME " driver, v" WATCHDOG_VERSION "\n"
 
 #define IO_INDEX_PORT     0x3F0
 #define IO_DATA_PORT      (IO_INDEX_PORT+1)
@@ -59,8 +58,8 @@ MODULE_PARM_DESC(timeout,
 module_param(testmode, int, 0);
 MODULE_PARM_DESC(testmode, "Watchdog testmode (1 = no reboot), default=0");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -131,7 +130,7 @@ static int wdt_start(void)
 
 	spin_unlock_irqrestore(&spinlock, flags);
 
-	printk(KERN_INFO PFX "activated.\n");
+	pr_info("activated\n");
 
 	return 0;
 }
@@ -185,7 +184,7 @@ static int wdt_stop(void)
 
 	spin_unlock_irqrestore(&spinlock, flags);
 
-	printk(KERN_INFO PFX "shutdown.\n");
+	pr_info("shutdown\n");
 
 	return 0;
 }
@@ -313,8 +312,7 @@ static int wdt_release(struct inode *inode, struct file *file)
 		clear_bit(0, &timer_alive);
 	} else {
 		wdt_keepalive();
-		printk(KERN_CRIT PFX
-			"unexpected close, not stopping watchdog!\n");
+		pr_crit("unexpected close, not stopping watchdog!\n");
 	}
 	expect_close = 0;
 	return 0;
@@ -471,7 +469,7 @@ static int __init w83977f_wdt_init(void)
 {
 	int rc;
 
-	printk(KERN_INFO PFX DRIVER_VERSION);
+	pr_info("driver v%s\n", WATCHDOG_VERSION);
 
 	/*
 	 * Check that the timeout value is within it's range;
@@ -479,36 +477,31 @@ static int __init w83977f_wdt_init(void)
 	 */
 	if (wdt_set_timeout(timeout)) {
 		wdt_set_timeout(DEFAULT_TIMEOUT);
-		printk(KERN_INFO PFX
-		    "timeout value must be 15 <= timeout <= 7635, using %d\n",
-							DEFAULT_TIMEOUT);
+		pr_info("timeout value must be 15 <= timeout <= 7635, using %d\n",
+			DEFAULT_TIMEOUT);
 	}
 
 	if (!request_region(IO_INDEX_PORT, 2, WATCHDOG_NAME)) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			IO_INDEX_PORT);
+		pr_err("I/O address 0x%04x already in use\n", IO_INDEX_PORT);
 		rc = -EIO;
 		goto err_out;
 	}
 
 	rc = register_reboot_notifier(&wdt_notifier);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", rc);
+		pr_err("cannot register reboot notifier (err=%d)\n", rc);
 		goto err_out_region;
 	}
 
 	rc = misc_register(&wdt_miscdev);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						wdt_miscdev.minor, rc);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       wdt_miscdev.minor, rc);
 		goto err_out_reboot;
 	}
 
-	printk(KERN_INFO PFX
-		"initialized. timeout=%d sec (nowayout=%d testmode=%d)\n",
-					timeout, nowayout, testmode);
+	pr_info("initialized. timeout=%d sec (nowayout=%d testmode=%d)\n",
+		timeout, nowayout, testmode);
 
 	return 0;
 
diff --git a/drivers/watchdog/wafer5823wdt.c b/drivers/watchdog/wafer5823wdt.c
index c3c3188c34d7..25aba6e00a23 100644
--- a/drivers/watchdog/wafer5823wdt.c
+++ b/drivers/watchdog/wafer5823wdt.c
@@ -26,6 +26,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/miscdevice.h>
@@ -65,8 +67,8 @@ MODULE_PARM_DESC(timeout,
 		"Watchdog timeout in seconds. 1 <= timeout <= 255, default="
 				__MODULE_STRING(WD_TIMO) ".");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -203,8 +205,7 @@ static int wafwdt_close(struct inode *inode, struct file *file)
 	if (expect_close == 42)
 		wafwdt_stop();
 	else {
-		printk(KERN_CRIT PFX
-		    "WDT device closed unexpectedly.  WDT will not stop!\n");
+		pr_crit("WDT device closed unexpectedly.  WDT will not stop!\n");
 		wafwdt_ping();
 	}
 	clear_bit(0, &wafwdt_is_open);
@@ -256,49 +257,42 @@ static int __init wafwdt_init(void)
 {
 	int ret;
 
-	printk(KERN_INFO
-	  "WDT driver for Wafer 5823 single board computer initialising.\n");
+	pr_info("WDT driver for Wafer 5823 single board computer initialising\n");
 
 	if (timeout < 1 || timeout > 255) {
 		timeout = WD_TIMO;
-		printk(KERN_INFO PFX
-			"timeout value must be 1 <= x <= 255, using %d\n",
-								timeout);
+		pr_info("timeout value must be 1 <= x <= 255, using %d\n",
+			timeout);
 	}
 
 	if (wdt_stop != wdt_start) {
 		if (!request_region(wdt_stop, 1, "Wafer 5823 WDT")) {
-			printk(KERN_ERR PFX
-				"I/O address 0x%04x already in use\n",
-								wdt_stop);
+			pr_err("I/O address 0x%04x already in use\n", wdt_stop);
 			ret = -EIO;
 			goto error;
 		}
 	}
 
 	if (!request_region(wdt_start, 1, "Wafer 5823 WDT")) {
-		printk(KERN_ERR PFX "I/O address 0x%04x already in use\n",
-			wdt_start);
+		pr_err("I/O address 0x%04x already in use\n", wdt_start);
 		ret = -EIO;
 		goto error2;
 	}
 
 	ret = register_reboot_notifier(&wafwdt_notifier);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto error3;
 	}
 
 	ret = misc_register(&wafwdt_miscdev);
 	if (ret != 0) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto error4;
 	}
 
-	printk(KERN_INFO PFX "initialized. timeout=%d sec (nowayout=%d)\n",
+	pr_info("initialized. timeout=%d sec (nowayout=%d)\n",
 		timeout, nowayout);
 
 	return ret;
diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c
index cfa1a1518aad..14d768bfa267 100644
--- a/drivers/watchdog/watchdog_core.c
+++ b/drivers/watchdog/watchdog_core.c
@@ -77,7 +77,7 @@ int watchdog_register_device(struct watchdog_device *wdd)
 	/* We only support 1 watchdog device via the /dev/watchdog interface */
 	ret = watchdog_dev_register(wdd);
 	if (ret) {
-		pr_err("error registering /dev/watchdog (err=%d).\n", ret);
+		pr_err("error registering /dev/watchdog (err=%d)\n", ret);
 		return ret;
 	}
 
@@ -101,7 +101,7 @@ void watchdog_unregister_device(struct watchdog_device *wdd)
 
 	ret = watchdog_dev_unregister(wdd);
 	if (ret)
-		pr_err("error unregistering /dev/watchdog (err=%d).\n", ret);
+		pr_err("error unregistering /dev/watchdog (err=%d)\n", ret);
 }
 EXPORT_SYMBOL_GPL(watchdog_unregister_device);
 
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 1199da0f98cf..8558da912c42 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -226,7 +226,6 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd,
 		err = wdd->ops->set_timeout(wdd, val);
 		if (err < 0)
 			return err;
-		wdd->timeout = val;
 		/* If the watchdog is active then we send a keepalive ping
 		 * to make sure that the watchdog keep's running (and if
 		 * possible that it takes the new timeout) */
@@ -237,6 +236,11 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd,
 		if (wdd->timeout == 0)
 			return -EOPNOTSUPP;
 		return put_user(wdd->timeout, p);
+	case WDIOC_GETTIMELEFT:
+		if (!wdd->ops->get_timeleft)
+			return -EOPNOTSUPP;
+
+		return put_user(wdd->ops->get_timeleft(wdd), p);
 	default:
 		return -ENOTTY;
 	}
@@ -347,7 +351,7 @@ int watchdog_dev_register(struct watchdog_device *watchdog)
 
 	/* Only one device can register for /dev/watchdog */
 	if (test_and_set_bit(0, &watchdog_dev_busy)) {
-		pr_err("only one watchdog can use /dev/watchdog.\n");
+		pr_err("only one watchdog can use /dev/watchdog\n");
 		return -EBUSY;
 	}
 
@@ -355,8 +359,8 @@ int watchdog_dev_register(struct watchdog_device *watchdog)
 
 	err = misc_register(&watchdog_miscdev);
 	if (err != 0) {
-		pr_err("%s: cannot register miscdev on minor=%d (err=%d).\n",
-			watchdog->info->identity, WATCHDOG_MINOR, err);
+		pr_err("%s: cannot register miscdev on minor=%d (err=%d)\n",
+		       watchdog->info->identity, WATCHDOG_MINOR, err);
 		goto out;
 	}
 
@@ -383,8 +387,8 @@ int watchdog_dev_unregister(struct watchdog_device *watchdog)
 
 	/* We can only unregister the watchdog device that was registered */
 	if (watchdog != wdd) {
-		pr_err("%s: watchdog was not registered as /dev/watchdog.\n",
-			watchdog->info->identity);
+		pr_err("%s: watchdog was not registered as /dev/watchdog\n",
+		       watchdog->info->identity);
 		return -ENODEV;
 	}
 
diff --git a/drivers/watchdog/wdrtas.c b/drivers/watchdog/wdrtas.c
index 94ec22b9e66b..0a77655cda60 100644
--- a/drivers/watchdog/wdrtas.c
+++ b/drivers/watchdog/wdrtas.c
@@ -26,6 +26,8 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -49,7 +51,7 @@ MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
 MODULE_ALIAS_MISCDEV(TEMP_MINOR);
 
-static int wdrtas_nowayout = WATCHDOG_NOWAYOUT;
+static bool wdrtas_nowayout = WATCHDOG_NOWAYOUT;
 static atomic_t wdrtas_miscdev_open = ATOMIC_INIT(0);
 static char wdrtas_expect_close;
 
@@ -93,8 +95,8 @@ static int wdrtas_set_interval(int interval)
 	result = rtas_call(wdrtas_token_set_indicator, 3, 1, NULL,
 			   WDRTAS_SURVEILLANCE_IND, 0, interval);
 	if (result < 0 && print_msg) {
-		printk(KERN_ERR "wdrtas: setting the watchdog to %i "
-		       "timeout failed: %li\n", interval, result);
+		pr_err("setting the watchdog to %i timeout failed: %li\n",
+		       interval, result);
 		print_msg--;
 	}
 
@@ -128,8 +130,8 @@ static int wdrtas_get_interval(int fallback_value)
 	spin_unlock(&rtas_data_buf_lock);
 
 	if (value[0] != 0 || value[1] != 2 || value[3] != 0 || result < 0) {
-		printk(KERN_WARNING "wdrtas: could not get sp_spi watchdog "
-		       "timeout (%li). Continuing\n", result);
+		pr_warn("could not get sp_spi watchdog timeout (%li). Continuing\n",
+			result);
 		return fallback_value;
 	}
 
@@ -170,18 +172,18 @@ static void wdrtas_log_scanned_event(void)
 	int i;
 
 	for (i = 0; i < WDRTAS_LOGBUFFER_LEN; i += 16)
-		printk(KERN_INFO "wdrtas: dumping event (line %i/%i), data = "
-		       "%02x %02x %02x %02x  %02x %02x %02x %02x   "
-		       "%02x %02x %02x %02x  %02x %02x %02x %02x\n",
-		       (i / 16) + 1, (WDRTAS_LOGBUFFER_LEN / 16),
-		       wdrtas_logbuffer[i + 0], wdrtas_logbuffer[i + 1],
-		       wdrtas_logbuffer[i + 2], wdrtas_logbuffer[i + 3],
-		       wdrtas_logbuffer[i + 4], wdrtas_logbuffer[i + 5],
-		       wdrtas_logbuffer[i + 6], wdrtas_logbuffer[i + 7],
-		       wdrtas_logbuffer[i + 8], wdrtas_logbuffer[i + 9],
-		       wdrtas_logbuffer[i + 10], wdrtas_logbuffer[i + 11],
-		       wdrtas_logbuffer[i + 12], wdrtas_logbuffer[i + 13],
-		       wdrtas_logbuffer[i + 14], wdrtas_logbuffer[i + 15]);
+		pr_info("dumping event (line %i/%i), data = "
+			"%02x %02x %02x %02x  %02x %02x %02x %02x   "
+			"%02x %02x %02x %02x  %02x %02x %02x %02x\n",
+			(i / 16) + 1, (WDRTAS_LOGBUFFER_LEN / 16),
+			wdrtas_logbuffer[i + 0], wdrtas_logbuffer[i + 1],
+			wdrtas_logbuffer[i + 2], wdrtas_logbuffer[i + 3],
+			wdrtas_logbuffer[i + 4], wdrtas_logbuffer[i + 5],
+			wdrtas_logbuffer[i + 6], wdrtas_logbuffer[i + 7],
+			wdrtas_logbuffer[i + 8], wdrtas_logbuffer[i + 9],
+			wdrtas_logbuffer[i + 10], wdrtas_logbuffer[i + 11],
+			wdrtas_logbuffer[i + 12], wdrtas_logbuffer[i + 13],
+			wdrtas_logbuffer[i + 14], wdrtas_logbuffer[i + 15]);
 }
 
 /**
@@ -201,8 +203,7 @@ static void wdrtas_timer_keepalive(void)
 				   (void *)__pa(wdrtas_logbuffer),
 				   WDRTAS_LOGBUFFER_LEN);
 		if (result < 0)
-			printk(KERN_ERR "wdrtas: event-scan failed: %li\n",
-			       result);
+			pr_err("event-scan failed: %li\n", result);
 		if (result == 0)
 			wdrtas_log_scanned_event();
 	} while (result == 0);
@@ -224,8 +225,7 @@ static int wdrtas_get_temperature(void)
 	result = rtas_get_sensor(WDRTAS_THERMAL_SENSOR, 0, &temperature);
 
 	if (result < 0)
-		printk(KERN_WARNING "wdrtas: reading the thermal sensor "
-		       "failed: %i\n", result);
+		pr_warn("reading the thermal sensor failed: %i\n", result);
 	else
 		temperature = ((temperature * 9) / 5) + 32; /* fahrenheit */
 
@@ -419,8 +419,7 @@ static int wdrtas_close(struct inode *inode, struct file *file)
 	if (wdrtas_expect_close == WDRTAS_MAGIC_CHAR)
 		wdrtas_timer_stop();
 	else {
-		printk(KERN_WARNING "wdrtas: got unexpected close. Watchdog "
-		       "not stopped.\n");
+		pr_warn("got unexpected close. Watchdog not stopped.\n");
 		wdrtas_timer_keepalive();
 	}
 
@@ -552,30 +551,24 @@ static int wdrtas_get_tokens(void)
 {
 	wdrtas_token_get_sensor_state = rtas_token("get-sensor-state");
 	if (wdrtas_token_get_sensor_state == RTAS_UNKNOWN_SERVICE) {
-		printk(KERN_WARNING "wdrtas: couldn't get token for "
-		       "get-sensor-state. Trying to continue without "
-		       "temperature support.\n");
+		pr_warn("couldn't get token for get-sensor-state. Trying to continue without temperature support.\n");
 	}
 
 	wdrtas_token_get_sp = rtas_token("ibm,get-system-parameter");
 	if (wdrtas_token_get_sp == RTAS_UNKNOWN_SERVICE) {
-		printk(KERN_WARNING "wdrtas: couldn't get token for "
-		       "ibm,get-system-parameter. Trying to continue with "
-		       "a default timeout value of %i seconds.\n",
-		       WDRTAS_DEFAULT_INTERVAL);
+		pr_warn("couldn't get token for ibm,get-system-parameter. Trying to continue with a default timeout value of %i seconds.\n",
+			WDRTAS_DEFAULT_INTERVAL);
 	}
 
 	wdrtas_token_set_indicator = rtas_token("set-indicator");
 	if (wdrtas_token_set_indicator == RTAS_UNKNOWN_SERVICE) {
-		printk(KERN_ERR "wdrtas: couldn't get token for "
-		       "set-indicator. Terminating watchdog code.\n");
+		pr_err("couldn't get token for set-indicator. Terminating watchdog code.\n");
 		return -EIO;
 	}
 
 	wdrtas_token_event_scan = rtas_token("event-scan");
 	if (wdrtas_token_event_scan == RTAS_UNKNOWN_SERVICE) {
-		printk(KERN_ERR "wdrtas: couldn't get token for event-scan. "
-		       "Terminating watchdog code.\n");
+		pr_err("couldn't get token for event-scan. Terminating watchdog code.\n");
 		return -EIO;
 	}
 
@@ -609,17 +602,14 @@ static int wdrtas_register_devs(void)
 
 	result = misc_register(&wdrtas_miscdev);
 	if (result) {
-		printk(KERN_ERR "wdrtas: couldn't register watchdog misc "
-		       "device. Terminating watchdog code.\n");
+		pr_err("couldn't register watchdog misc device. Terminating watchdog code.\n");
 		return result;
 	}
 
 	if (wdrtas_token_get_sensor_state != RTAS_UNKNOWN_SERVICE) {
 		result = misc_register(&wdrtas_tempdev);
 		if (result) {
-			printk(KERN_WARNING "wdrtas: couldn't register "
-			       "watchdog temperature misc device. Continuing "
-			       "without temperature support.\n");
+			pr_warn("couldn't register watchdog temperature misc device. Continuing without temperature support.\n");
 			wdrtas_token_get_sensor_state = RTAS_UNKNOWN_SERVICE;
 		}
 	}
@@ -643,8 +633,7 @@ static int __init wdrtas_init(void)
 		return -ENODEV;
 
 	if (register_reboot_notifier(&wdrtas_notifier)) {
-		printk(KERN_ERR "wdrtas: could not register reboot notifier. "
-		       "Terminating watchdog code.\n");
+		pr_err("could not register reboot notifier. Terminating watchdog code.\n");
 		wdrtas_unregister_devs();
 		return -ENODEV;
 	}
diff --git a/drivers/watchdog/wdt.c b/drivers/watchdog/wdt.c
index d2ef002be96b..ee4333c01109 100644
--- a/drivers/watchdog/wdt.c
+++ b/drivers/watchdog/wdt.c
@@ -32,6 +32,8 @@
  *		Matt Domsch	:	Added nowayout module option
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -46,7 +48,6 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 #include "wd501p.h"
 
 static unsigned long wdt_is_open;
@@ -65,8 +66,8 @@ MODULE_PARM_DESC(heartbeat,
 	"Watchdog heartbeat in seconds. (0 < heartbeat < 65536, default="
 				__MODULE_STRING(WD_TIMO) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 	"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -252,11 +253,11 @@ static int wdt_get_temperature(void)
 static void wdt_decode_501(int status)
 {
 	if (!(status & WDC_SR_TGOOD))
-		printk(KERN_CRIT "Overheat alarm.(%d)\n", inb_p(WDT_RT));
+		pr_crit("Overheat alarm (%d)\n", inb_p(WDT_RT));
 	if (!(status & WDC_SR_PSUOVER))
-		printk(KERN_CRIT "PSU over voltage.\n");
+		pr_crit("PSU over voltage\n");
 	if (!(status & WDC_SR_PSUUNDR))
-		printk(KERN_CRIT "PSU under voltage.\n");
+		pr_crit("PSU under voltage\n");
 }
 
 /**
@@ -280,25 +281,25 @@ static irqreturn_t wdt_interrupt(int irq, void *dev_id)
 	spin_lock(&wdt_lock);
 	status = inb_p(WDT_SR);
 
-	printk(KERN_CRIT "WDT status %d\n", status);
+	pr_crit("WDT status %d\n", status);
 
 	if (type == 501) {
 		wdt_decode_501(status);
 		if (tachometer) {
 			if (!(status & WDC_SR_FANGOOD))
-				printk(KERN_CRIT "Possible fan fault.\n");
+				pr_crit("Possible fan fault\n");
 		}
 	}
 	if (!(status & WDC_SR_WCCR)) {
 #ifdef SOFTWARE_REBOOT
 #ifdef ONLY_TESTING
-		printk(KERN_CRIT "Would Reboot.\n");
+		pr_crit("Would Reboot\n");
 #else
-		printk(KERN_CRIT "Initiating system reboot.\n");
+		pr_crit("Initiating system reboot\n");
 		emergency_restart();
 #endif
 #else
-		printk(KERN_CRIT "Reset in 5ms.\n");
+		pr_crit("Reset in 5ms\n");
 #endif
 	}
 	spin_unlock(&wdt_lock);
@@ -441,8 +442,7 @@ static int wdt_release(struct inode *inode, struct file *file)
 		wdt_stop();
 		clear_bit(0, &wdt_is_open);
 	} else {
-		printk(KERN_CRIT
-		 "wdt: WDT device closed unexpectedly.  WDT will not stop!\n");
+		pr_crit("WDT device closed unexpectedly.  WDT will not stop!\n");
 		wdt_ping();
 	}
 	expect_close = 0;
@@ -593,7 +593,7 @@ static int __init wdt_init(void)
 	int ret;
 
 	if (type != 500 && type != 501) {
-		printk(KERN_ERR "wdt: unknown card type '%d'.\n", type);
+		pr_err("unknown card type '%d'\n", type);
 		return -ENODEV;
 	}
 
@@ -601,53 +601,49 @@ static int __init wdt_init(void)
 	   if not reset to the default */
 	if (wdt_set_heartbeat(heartbeat)) {
 		wdt_set_heartbeat(WD_TIMO);
-		printk(KERN_INFO "wdt: heartbeat value must be "
-			"0 < heartbeat < 65536, using %d\n", WD_TIMO);
+		pr_info("heartbeat value must be 0 < heartbeat < 65536, using %d\n",
+			WD_TIMO);
 	}
 
 	if (!request_region(io, 8, "wdt501p")) {
-		printk(KERN_ERR
-			"wdt: I/O address 0x%04x already in use\n", io);
+		pr_err("I/O address 0x%04x already in use\n", io);
 		ret = -EBUSY;
 		goto out;
 	}
 
 	ret = request_irq(irq, wdt_interrupt, 0, "wdt501p", NULL);
 	if (ret) {
-		printk(KERN_ERR "wdt: IRQ %d is not free.\n", irq);
+		pr_err("IRQ %d is not free\n", irq);
 		goto outreg;
 	}
 
 	ret = register_reboot_notifier(&wdt_notifier);
 	if (ret) {
-		printk(KERN_ERR
-		      "wdt: cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto outirq;
 	}
 
 	if (type == 501) {
 		ret = misc_register(&temp_miscdev);
 		if (ret) {
-			printk(KERN_ERR "wdt: cannot register miscdev "
-				"on minor=%d (err=%d)\n", TEMP_MINOR, ret);
+			pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+			       TEMP_MINOR, ret);
 			goto outrbt;
 		}
 	}
 
 	ret = misc_register(&wdt_miscdev);
 	if (ret) {
-		printk(KERN_ERR
-			"wdt: cannot register miscdev on minor=%d (err=%d)\n",
-							WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto outmisc;
 	}
 
-	printk(KERN_INFO "WDT500/501-P driver 0.10 "
-		"at 0x%04x (Interrupt %d). heartbeat=%d sec (nowayout=%d)\n",
+	pr_info("WDT500/501-P driver 0.10 at 0x%04x (Interrupt %d). heartbeat=%d sec (nowayout=%d)\n",
 		io, irq, heartbeat, nowayout);
 	if (type == 501)
-		printk(KERN_INFO "wdt: Fan Tachometer is %s\n",
-				(tachometer ? "Enabled" : "Disabled"));
+		pr_info("Fan Tachometer is %s\n",
+			tachometer ? "Enabled" : "Disabled");
 	return 0;
 
 outmisc:
diff --git a/drivers/watchdog/wdt285.c b/drivers/watchdog/wdt285.c
index f55135662d78..5eec74053882 100644
--- a/drivers/watchdog/wdt285.c
+++ b/drivers/watchdog/wdt285.c
@@ -16,6 +16,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -32,6 +34,7 @@
 #include <mach/hardware.h>
 
 #include <asm/mach-types.h>
+#include <asm/system_info.h>
 #include <asm/hardware/dec21285.h>
 
 /*
@@ -49,7 +52,7 @@ static unsigned long timer_alive;
  */
 static void watchdog_fire(int irq, void *dev_id)
 {
-	printk(KERN_CRIT "Watchdog: Would Reboot.\n");
+	pr_crit("Would Reboot\n");
 	*CSR_TIMER4_CNTL = 0;
 	*CSR_TIMER4_CLR = 0;
 }
@@ -205,13 +208,11 @@ static int __init footbridge_watchdog_init(void)
 	if (retval < 0)
 		return retval;
 
-	printk(KERN_INFO
-		"Footbridge Watchdog Timer: 0.01, timer margin: %d sec\n",
-								soft_margin);
+	pr_info("Footbridge Watchdog Timer: 0.01, timer margin: %d sec\n",
+		soft_margin);
 
 	if (machine_is_cats())
-		printk(KERN_WARNING
-		  "Warning: Watchdog reset may not work on this machine.\n");
+		pr_warn("Warning: Watchdog reset may not work on this machine\n");
 	return 0;
 }
 
diff --git a/drivers/watchdog/wdt977.c b/drivers/watchdog/wdt977.c
index a2f01c9f5c34..65a402344933 100644
--- a/drivers/watchdog/wdt977.c
+++ b/drivers/watchdog/wdt977.c
@@ -23,6 +23,8 @@
  *				    Netwinders only
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
@@ -37,13 +39,10 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 #include <asm/mach-types.h>
 
 #define WATCHDOG_VERSION  "0.04"
 #define WATCHDOG_NAME     "Wdt977"
-#define PFX WATCHDOG_NAME ": "
-#define DRIVER_VERSION    WATCHDOG_NAME " driver, v" WATCHDOG_VERSION "\n"
 
 #define IO_INDEX_PORT	0x370		/* on some systems it can be 0x3F0 */
 #define IO_DATA_PORT	(IO_INDEX_PORT + 1)
@@ -68,8 +67,8 @@ MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (60..15300, default="
 module_param(testmode, int, 0);
 MODULE_PARM_DESC(testmode, "Watchdog testmode (1 = no reboot), default=0");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -119,7 +118,7 @@ static int wdt977_start(void)
 	outb_p(LOCK_DATA, IO_INDEX_PORT);
 
 	spin_unlock_irqrestore(&spinlock, flags);
-	printk(KERN_INFO PFX "activated.\n");
+	pr_info("activated\n");
 
 	return 0;
 }
@@ -164,7 +163,7 @@ static int wdt977_stop(void)
 	outb_p(LOCK_DATA, IO_INDEX_PORT);
 
 	spin_unlock_irqrestore(&spinlock, flags);
-	printk(KERN_INFO PFX "shutdown.\n");
+	pr_info("shutdown\n");
 
 	return 0;
 }
@@ -288,8 +287,7 @@ static int wdt977_release(struct inode *inode, struct file *file)
 		clear_bit(0, &timer_alive);
 	} else {
 		wdt977_keepalive();
-		printk(KERN_CRIT PFX
-			"Unexpected close, not stopping watchdog!\n");
+		pr_crit("Unexpected close, not stopping watchdog!\n");
 	}
 	expect_close = 0;
 	return 0;
@@ -446,15 +444,14 @@ static int __init wd977_init(void)
 {
 	int rc;
 
-	printk(KERN_INFO PFX DRIVER_VERSION);
+	pr_info("driver v%s\n", WATCHDOG_VERSION);
 
 	/* Check that the timeout value is within its range;
 	   if not reset to the default */
 	if (wdt977_set_timeout(timeout)) {
 		wdt977_set_timeout(DEFAULT_TIMEOUT);
-		printk(KERN_INFO PFX
-		      "timeout value must be 60 < timeout < 15300, using %d\n",
-							DEFAULT_TIMEOUT);
+		pr_info("timeout value must be 60 < timeout < 15300, using %d\n",
+			DEFAULT_TIMEOUT);
 	}
 
 	/* on Netwinder the IOports are already reserved by
@@ -462,9 +459,8 @@ static int __init wd977_init(void)
 	 */
 	if (!machine_is_netwinder()) {
 		if (!request_region(IO_INDEX_PORT, 2, WATCHDOG_NAME)) {
-			printk(KERN_ERR PFX
-				"I/O address 0x%04x already in use\n",
-								IO_INDEX_PORT);
+			pr_err("I/O address 0x%04x already in use\n",
+			       IO_INDEX_PORT);
 			rc = -EIO;
 			goto err_out;
 		}
@@ -472,22 +468,19 @@ static int __init wd977_init(void)
 
 	rc = register_reboot_notifier(&wdt977_notifier);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", rc);
+		pr_err("cannot register reboot notifier (err=%d)\n", rc);
 		goto err_out_region;
 	}
 
 	rc = misc_register(&wdt977_miscdev);
 	if (rc) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						wdt977_miscdev.minor, rc);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       wdt977_miscdev.minor, rc);
 		goto err_out_reboot;
 	}
 
-	printk(KERN_INFO PFX
-		"initialized. timeout=%d sec (nowayout=%d, testmode=%i)\n",
-						timeout, nowayout, testmode);
+	pr_info("initialized. timeout=%d sec (nowayout=%d, testmode=%i)\n",
+		timeout, nowayout, testmode);
 
 	return 0;
 
diff --git a/drivers/watchdog/wdt_pci.c b/drivers/watchdog/wdt_pci.c
index e0fc3baa9197..1c888c7d4cce 100644
--- a/drivers/watchdog/wdt_pci.c
+++ b/drivers/watchdog/wdt_pci.c
@@ -37,6 +37,8 @@
  *		Matt Domsch	:	nowayout module option
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -53,13 +55,10 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 
 #define WDT_IS_PCI
 #include "wd501p.h"
 
-#define PFX "wdt_pci: "
-
 /* We can only use 1 card due to the /dev/watchdog restriction */
 static int dev_count;
 
@@ -80,8 +79,8 @@ MODULE_PARM_DESC(heartbeat,
 		"Watchdog heartbeat in seconds. (0<heartbeat<65536, default="
 				__MODULE_STRING(WD_TIMO) ")");
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -312,33 +311,32 @@ static irqreturn_t wdtpci_interrupt(int irq, void *dev_id)
 	status = inb(WDT_SR);
 	udelay(8);
 
-	printk(KERN_CRIT PFX "status %d\n", status);
+	pr_crit("status %d\n", status);
 
 	if (type == 501) {
 		if (!(status & WDC_SR_TGOOD)) {
-			printk(KERN_CRIT PFX "Overheat alarm.(%d)\n",
-								inb(WDT_RT));
+			pr_crit("Overheat alarm (%d)\n", inb(WDT_RT));
 			udelay(8);
 		}
 		if (!(status & WDC_SR_PSUOVER))
-			printk(KERN_CRIT PFX "PSU over voltage.\n");
+			pr_crit("PSU over voltage\n");
 		if (!(status & WDC_SR_PSUUNDR))
-			printk(KERN_CRIT PFX "PSU under voltage.\n");
+			pr_crit("PSU under voltage\n");
 		if (tachometer) {
 			if (!(status & WDC_SR_FANGOOD))
-				printk(KERN_CRIT PFX "Possible fan fault.\n");
+				pr_crit("Possible fan fault\n");
 		}
 	}
 	if (!(status & WDC_SR_WCCR)) {
 #ifdef SOFTWARE_REBOOT
 #ifdef ONLY_TESTING
-		printk(KERN_CRIT PFX "Would Reboot.\n");
+		pr_crit("Would Reboot\n");
 #else
-		printk(KERN_CRIT PFX "Initiating system reboot.\n");
+		pr_crit("Initiating system reboot\n");
 		emergency_restart(NULL);
 #endif
 #else
-		printk(KERN_CRIT PFX "Reset in 5ms.\n");
+		pr_crit("Reset in 5ms\n");
 #endif
 	}
 	spin_unlock(&wdtpci_lock);
@@ -484,7 +482,7 @@ static int wdtpci_release(struct inode *inode, struct file *file)
 	if (expect_close == 42) {
 		wdtpci_stop();
 	} else {
-		printk(KERN_CRIT PFX "Unexpected close, not stopping timer!");
+		pr_crit("Unexpected close, not stopping timer!\n");
 		wdtpci_ping();
 	}
 	expect_close = 0;
@@ -614,29 +612,29 @@ static int __devinit wdtpci_init_one(struct pci_dev *dev,
 
 	dev_count++;
 	if (dev_count > 1) {
-		printk(KERN_ERR PFX "This driver only supports one device\n");
+		pr_err("This driver only supports one device\n");
 		return -ENODEV;
 	}
 
 	if (type != 500 && type != 501) {
-		printk(KERN_ERR PFX "unknown card type '%d'.\n", type);
+		pr_err("unknown card type '%d'\n", type);
 		return -ENODEV;
 	}
 
 	if (pci_enable_device(dev)) {
-		printk(KERN_ERR PFX "Not possible to enable PCI Device\n");
+		pr_err("Not possible to enable PCI Device\n");
 		return -ENODEV;
 	}
 
 	if (pci_resource_start(dev, 2) == 0x0000) {
-		printk(KERN_ERR PFX "No I/O-Address for card detected\n");
+		pr_err("No I/O-Address for card detected\n");
 		ret = -ENODEV;
 		goto out_pci;
 	}
 
 	if (pci_request_region(dev, 2, "wdt_pci")) {
-		printk(KERN_ERR PFX "I/O address 0x%llx already in use\n",
-			(unsigned long long)pci_resource_start(dev, 2));
+		pr_err("I/O address 0x%llx already in use\n",
+		       (unsigned long long)pci_resource_start(dev, 2));
 		goto out_pci;
 	}
 
@@ -645,53 +643,48 @@ static int __devinit wdtpci_init_one(struct pci_dev *dev,
 
 	if (request_irq(irq, wdtpci_interrupt, IRQF_SHARED,
 			 "wdt_pci", &wdtpci_miscdev)) {
-		printk(KERN_ERR PFX "IRQ %d is not free\n", irq);
+		pr_err("IRQ %d is not free\n", irq);
 		goto out_reg;
 	}
 
-	printk(KERN_INFO
-	 "PCI-WDT500/501 (PCI-WDG-CSM) driver 0.10 at 0x%llx (Interrupt %d)\n",
-					(unsigned long long)io, irq);
+	pr_info("PCI-WDT500/501 (PCI-WDG-CSM) driver 0.10 at 0x%llx (Interrupt %d)\n",
+		(unsigned long long)io, irq);
 
 	/* Check that the heartbeat value is within its range;
 	   if not reset to the default */
 	if (wdtpci_set_heartbeat(heartbeat)) {
 		wdtpci_set_heartbeat(WD_TIMO);
-		printk(KERN_INFO PFX
-		  "heartbeat value must be 0 < heartbeat < 65536, using %d\n",
-								WD_TIMO);
+		pr_info("heartbeat value must be 0 < heartbeat < 65536, using %d\n",
+			WD_TIMO);
 	}
 
 	ret = register_reboot_notifier(&wdtpci_notifier);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register reboot notifier (err=%d)\n", ret);
+		pr_err("cannot register reboot notifier (err=%d)\n", ret);
 		goto out_irq;
 	}
 
 	if (type == 501) {
 		ret = misc_register(&temp_miscdev);
 		if (ret) {
-			printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-							TEMP_MINOR, ret);
+			pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+			       TEMP_MINOR, ret);
 			goto out_rbt;
 		}
 	}
 
 	ret = misc_register(&wdtpci_miscdev);
 	if (ret) {
-		printk(KERN_ERR PFX
-			"cannot register miscdev on minor=%d (err=%d)\n",
-						WATCHDOG_MINOR, ret);
+		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
+		       WATCHDOG_MINOR, ret);
 		goto out_misc;
 	}
 
-	printk(KERN_INFO PFX "initialized. heartbeat=%d sec (nowayout=%d)\n",
+	pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n",
 		heartbeat, nowayout);
 	if (type == 501)
-		printk(KERN_INFO "wdt: Fan Tachometer is %s\n",
-				(tachometer ? "Enabled" : "Disabled"));
+		pr_info("Fan Tachometer is %s\n",
+			tachometer ? "Enabled" : "Disabled");
 
 	ret = 0;
 out:
diff --git a/drivers/watchdog/wm831x_wdt.c b/drivers/watchdog/wm831x_wdt.c
index 263c883f0806..b1815c5ed7a7 100644
--- a/drivers/watchdog/wm831x_wdt.c
+++ b/drivers/watchdog/wm831x_wdt.c
@@ -22,8 +22,8 @@
 #include <linux/mfd/wm831x/pdata.h>
 #include <linux/mfd/wm831x/watchdog.h>
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		 "Watchdog cannot be stopped once started (default="
 		 __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
@@ -163,6 +163,8 @@ static int wm831x_wdt_set_timeout(struct watchdog_device *wdt_dev,
 			ret);
 	}
 
+	wdt_dev->timeout = timeout;
+
 	return ret;
 }
 
diff --git a/drivers/watchdog/wm8350_wdt.c b/drivers/watchdog/wm8350_wdt.c
index 5d7113c7e501..3c76693447fd 100644
--- a/drivers/watchdog/wm8350_wdt.c
+++ b/drivers/watchdog/wm8350_wdt.c
@@ -8,63 +8,65 @@
  * as published by the Free Software Foundation
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/miscdevice.h>
 #include <linux/platform_device.h>
 #include <linux/watchdog.h>
 #include <linux/uaccess.h>
 #include <linux/mfd/wm8350/core.h>
 
-static int nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout,
 		 "Watchdog cannot be stopped once started (default="
 		 __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
-static unsigned long wm8350_wdt_users;
-static struct miscdevice wm8350_wdt_miscdev;
-static int wm8350_wdt_expect_close;
 static DEFINE_MUTEX(wdt_mutex);
 
 static struct {
-	int time;  /* Seconds */
-	u16 val;   /* To be set in WM8350_SYSTEM_CONTROL_2 */
+	unsigned int time;  /* Seconds */
+	u16 val;	    /* To be set in WM8350_SYSTEM_CONTROL_2 */
 } wm8350_wdt_cfgs[] = {
 	{ 1, 0x02 },
 	{ 2, 0x04 },
 	{ 4, 0x05 },
 };
 
-static struct wm8350 *get_wm8350(void)
-{
-	return dev_get_drvdata(wm8350_wdt_miscdev.parent);
-}
-
-static int wm8350_wdt_set_timeout(struct wm8350 *wm8350, u16 value)
+static int wm8350_wdt_set_timeout(struct watchdog_device *wdt_dev,
+				  unsigned int timeout)
 {
-	int ret;
+	struct wm8350 *wm8350 = watchdog_get_drvdata(wdt_dev);
+	int ret, i;
 	u16 reg;
 
+	for (i = 0; i < ARRAY_SIZE(wm8350_wdt_cfgs); i++)
+		if (wm8350_wdt_cfgs[i].time == timeout)
+			break;
+	if (i == ARRAY_SIZE(wm8350_wdt_cfgs))
+		return -EINVAL;
+
 	mutex_lock(&wdt_mutex);
 	wm8350_reg_unlock(wm8350);
 
 	reg = wm8350_reg_read(wm8350, WM8350_SYSTEM_CONTROL_2);
 	reg &= ~WM8350_WDOG_TO_MASK;
-	reg |= value;
+	reg |= wm8350_wdt_cfgs[i].val;
 	ret = wm8350_reg_write(wm8350, WM8350_SYSTEM_CONTROL_2, reg);
 
 	wm8350_reg_lock(wm8350);
 	mutex_unlock(&wdt_mutex);
 
+	wdt_dev->timeout = timeout;
 	return ret;
 }
 
-static int wm8350_wdt_start(struct wm8350 *wm8350)
+static int wm8350_wdt_start(struct watchdog_device *wdt_dev)
 {
+	struct wm8350 *wm8350 = watchdog_get_drvdata(wdt_dev);
 	int ret;
 	u16 reg;
 
@@ -82,8 +84,9 @@ static int wm8350_wdt_start(struct wm8350 *wm8350)
 	return ret;
 }
 
-static int wm8350_wdt_stop(struct wm8350 *wm8350)
+static int wm8350_wdt_stop(struct watchdog_device *wdt_dev)
 {
+	struct wm8350 *wm8350 = watchdog_get_drvdata(wdt_dev);
 	int ret;
 	u16 reg;
 
@@ -100,8 +103,9 @@ static int wm8350_wdt_stop(struct wm8350 *wm8350)
 	return ret;
 }
 
-static int wm8350_wdt_kick(struct wm8350 *wm8350)
+static int wm8350_wdt_ping(struct watchdog_device *wdt_dev)
 {
+	struct wm8350 *wm8350 = watchdog_get_drvdata(wdt_dev);
 	int ret;
 	u16 reg;
 
@@ -115,168 +119,25 @@ static int wm8350_wdt_kick(struct wm8350 *wm8350)
 	return ret;
 }
 
-static int wm8350_wdt_open(struct inode *inode, struct file *file)
-{
-	struct wm8350 *wm8350 = get_wm8350();
-	int ret;
-
-	if (!wm8350)
-		return -ENODEV;
-
-	if (test_and_set_bit(0, &wm8350_wdt_users))
-		return -EBUSY;
-
-	ret = wm8350_wdt_start(wm8350);
-	if (ret != 0)
-		return ret;
-
-	return nonseekable_open(inode, file);
-}
-
-static int wm8350_wdt_release(struct inode *inode, struct file *file)
-{
-	struct wm8350 *wm8350 = get_wm8350();
-
-	if (wm8350_wdt_expect_close)
-		wm8350_wdt_stop(wm8350);
-	else {
-		dev_warn(wm8350->dev, "Watchdog device closed uncleanly\n");
-		wm8350_wdt_kick(wm8350);
-	}
-
-	clear_bit(0, &wm8350_wdt_users);
-
-	return 0;
-}
-
-static ssize_t wm8350_wdt_write(struct file *file,
-				const char __user *data, size_t count,
-				loff_t *ppos)
-{
-	struct wm8350 *wm8350 = get_wm8350();
-	size_t i;
-
-	if (count) {
-		wm8350_wdt_kick(wm8350);
-
-		if (!nowayout) {
-			/* In case it was set long ago */
-			wm8350_wdt_expect_close = 0;
-
-			/* scan to see whether or not we got the magic
-			   character */
-			for (i = 0; i != count; i++) {
-				char c;
-				if (get_user(c, data + i))
-					return -EFAULT;
-				if (c == 'V')
-					wm8350_wdt_expect_close = 42;
-			}
-		}
-	}
-	return count;
-}
-
-static const struct watchdog_info ident = {
+static const struct watchdog_info wm8350_wdt_info = {
 	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
 	.identity = "WM8350 Watchdog",
 };
 
-static long wm8350_wdt_ioctl(struct file *file, unsigned int cmd,
-			     unsigned long arg)
-{
-	struct wm8350 *wm8350 = get_wm8350();
-	int ret = -ENOTTY, time, i;
-	void __user *argp = (void __user *)arg;
-	int __user *p = argp;
-	u16 reg;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		ret = copy_to_user(argp, &ident, sizeof(ident)) ? -EFAULT : 0;
-		break;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		ret = put_user(0, p);
-		break;
-
-	case WDIOC_SETOPTIONS:
-	{
-		int options;
-
-		if (get_user(options, p))
-			return -EFAULT;
-
-		ret = -EINVAL;
-
-		/* Setting both simultaneously means at least one must fail */
-		if (options == WDIOS_DISABLECARD)
-			ret = wm8350_wdt_stop(wm8350);
-
-		if (options == WDIOS_ENABLECARD)
-			ret = wm8350_wdt_start(wm8350);
-		break;
-	}
-
-	case WDIOC_KEEPALIVE:
-		ret = wm8350_wdt_kick(wm8350);
-		break;
-
-	case WDIOC_SETTIMEOUT:
-		ret = get_user(time, p);
-		if (ret)
-			break;
-
-		if (time == 0) {
-			if (nowayout)
-				ret = -EINVAL;
-			else
-				wm8350_wdt_stop(wm8350);
-			break;
-		}
-
-		for (i = 0; i < ARRAY_SIZE(wm8350_wdt_cfgs); i++)
-			if (wm8350_wdt_cfgs[i].time == time)
-				break;
-		if (i == ARRAY_SIZE(wm8350_wdt_cfgs))
-			ret = -EINVAL;
-		else
-			ret = wm8350_wdt_set_timeout(wm8350,
-						     wm8350_wdt_cfgs[i].val);
-		break;
-
-	case WDIOC_GETTIMEOUT:
-		reg = wm8350_reg_read(wm8350, WM8350_SYSTEM_CONTROL_2);
-		reg &= WM8350_WDOG_TO_MASK;
-		for (i = 0; i < ARRAY_SIZE(wm8350_wdt_cfgs); i++)
-			if (wm8350_wdt_cfgs[i].val == reg)
-				break;
-		if (i == ARRAY_SIZE(wm8350_wdt_cfgs)) {
-			dev_warn(wm8350->dev,
-				 "Unknown watchdog configuration: %x\n", reg);
-			ret = -EINVAL;
-		} else
-			ret = put_user(wm8350_wdt_cfgs[i].time, p);
-
-	}
-
-	return ret;
-}
-
-static const struct file_operations wm8350_wdt_fops = {
+static const struct watchdog_ops wm8350_wdt_ops = {
 	.owner = THIS_MODULE,
-	.llseek = no_llseek,
-	.write = wm8350_wdt_write,
-	.unlocked_ioctl = wm8350_wdt_ioctl,
-	.open = wm8350_wdt_open,
-	.release = wm8350_wdt_release,
+	.start = wm8350_wdt_start,
+	.stop = wm8350_wdt_stop,
+	.ping = wm8350_wdt_ping,
+	.set_timeout = wm8350_wdt_set_timeout,
 };
 
-static struct miscdevice wm8350_wdt_miscdev = {
-	.minor = WATCHDOG_MINOR,
-	.name = "watchdog",
-	.fops = &wm8350_wdt_fops,
+static struct watchdog_device wm8350_wdt = {
+	.info = &wm8350_wdt_info,
+	.ops = &wm8350_wdt_ops,
+	.timeout = 4,
+	.min_timeout = 1,
+	.max_timeout = 4,
 };
 
 static int __devinit wm8350_wdt_probe(struct platform_device *pdev)
@@ -288,18 +149,18 @@ static int __devinit wm8350_wdt_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	/* Default to 4s timeout */
-	wm8350_wdt_set_timeout(wm8350, 0x05);
+	watchdog_set_nowayout(&wm8350_wdt, nowayout);
+	watchdog_set_drvdata(&wm8350_wdt, wm8350);
 
-	wm8350_wdt_miscdev.parent = &pdev->dev;
+	/* Default to 4s timeout */
+	wm8350_wdt_set_timeout(&wm8350_wdt, 4);
 
-	return misc_register(&wm8350_wdt_miscdev);
+	return watchdog_register_device(&wm8350_wdt);
 }
 
 static int __devexit wm8350_wdt_remove(struct platform_device *pdev)
 {
-	misc_deregister(&wm8350_wdt_miscdev);
-
+	watchdog_unregister_device(&wm8350_wdt);
 	return 0;
 }
 
diff --git a/drivers/watchdog/xen_wdt.c b/drivers/watchdog/xen_wdt.c
index 49bd9d395562..e4a25b51165c 100644
--- a/drivers/watchdog/xen_wdt.c
+++ b/drivers/watchdog/xen_wdt.c
@@ -9,9 +9,10 @@
  *	2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #define DRV_NAME	"wdt"
 #define DRV_VERSION	"0.01"
-#define PFX		DRV_NAME ": "
 
 #include <linux/bug.h>
 #include <linux/errno.h>
@@ -131,16 +132,17 @@ static int xen_wdt_open(struct inode *inode, struct file *file)
 
 static int xen_wdt_release(struct inode *inode, struct file *file)
 {
+	int err = 0;
+
 	if (expect_release)
-		xen_wdt_stop();
+		err = xen_wdt_stop();
 	else {
-		printk(KERN_CRIT PFX
-		       "unexpected close, not stopping watchdog!\n");
+		pr_crit("unexpected close, not stopping watchdog!\n");
 		xen_wdt_kick();
 	}
-	is_active = false;
+	is_active = err;
 	expect_release = false;
-	return 0;
+	return err;
 }
 
 static ssize_t xen_wdt_write(struct file *file, const char __user *data,
@@ -251,30 +253,27 @@ static int __devinit xen_wdt_probe(struct platform_device *dev)
 	case -EINVAL:
 		if (!timeout) {
 			timeout = WATCHDOG_TIMEOUT;
-			printk(KERN_INFO PFX
-			       "timeout value invalid, using %d\n", timeout);
+			pr_info("timeout value invalid, using %d\n", timeout);
 		}
 
 		ret = misc_register(&xen_wdt_miscdev);
 		if (ret) {
-			printk(KERN_ERR PFX
-			       "cannot register miscdev on minor=%d (%d)\n",
+			pr_err("cannot register miscdev on minor=%d (%d)\n",
 			       WATCHDOG_MINOR, ret);
 			break;
 		}
 
-		printk(KERN_INFO PFX
-		       "initialized (timeout=%ds, nowayout=%d)\n",
-		       timeout, nowayout);
+		pr_info("initialized (timeout=%ds, nowayout=%d)\n",
+			timeout, nowayout);
 		break;
 
 	case -ENOSYS:
-		printk(KERN_INFO PFX "not supported\n");
+		pr_info("not supported\n");
 		ret = -ENODEV;
 		break;
 
 	default:
-		printk(KERN_INFO PFX "bogus return value %d\n", ret);
+		pr_info("bogus return value %d\n", ret);
 		break;
 	}
 
@@ -299,11 +298,18 @@ static void xen_wdt_shutdown(struct platform_device *dev)
 
 static int xen_wdt_suspend(struct platform_device *dev, pm_message_t state)
 {
-	return xen_wdt_stop();
+	typeof(wdt.id) id = wdt.id;
+	int rc = xen_wdt_stop();
+
+	wdt.id = id;
+	return rc;
 }
 
 static int xen_wdt_resume(struct platform_device *dev)
 {
+	if (!wdt.id)
+		return 0;
+	wdt.id = 0;
 	return xen_wdt_start();
 }
 
@@ -326,7 +332,7 @@ static int __init xen_wdt_init_module(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	printk(KERN_INFO PFX "Xen WatchDog Timer Driver v%s\n", DRV_VERSION);
+	pr_info("Xen WatchDog Timer Driver v%s\n", DRV_VERSION);
 
 	err = platform_driver_register(&xen_wdt_driver);
 	if (err)
@@ -346,7 +352,7 @@ static void __exit xen_wdt_cleanup_module(void)
 {
 	platform_device_unregister(platform_device);
 	platform_driver_unregister(&xen_wdt_driver);
-	printk(KERN_INFO PFX "module unloaded\n");
+	pr_info("module unloaded\n");
 }
 
 module_init(xen_wdt_init_module);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 19e6a2041371..1afb4fba11b4 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -204,7 +204,8 @@ error:
 
 void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flags)
+			   dma_addr_t *dma_handle, gfp_t flags,
+			   struct dma_attrs *attrs)
 {
 	void *ret;
 	int order = get_order(size);
@@ -253,7 +254,7 @@ EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
 
 void
 xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
-			  dma_addr_t dev_addr)
+			  dma_addr_t dev_addr, struct dma_attrs *attrs)
 {
 	int order = get_order(size);
 	phys_addr_t phys;
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 10b7d3c9dba8..8c92a9ba8330 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -259,7 +259,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	if (v9fs_proto_dotl(v9ses)) {
 		res = p9_client_statfs(fid, &rs);
 		if (res == 0) {
-			buf->f_type = V9FS_MAGIC;
+			buf->f_type = rs.type;
 			buf->f_bsize = rs.bsize;
 			buf->f_blocks = rs.blocks;
 			buf->f_bfree = rs.bfree;
diff --git a/fs/aio.c b/fs/aio.c
index 4f71627264fd..da887604dfc5 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -305,15 +305,18 @@ out_freectx:
 	return ERR_PTR(err);
 }
 
-/* aio_cancel_all
+/* kill_ctx
  *	Cancels all outstanding aio requests on an aio context.  Used 
  *	when the processes owning a context have all exited to encourage 
  *	the rapid destruction of the kioctx.
  */
-static void aio_cancel_all(struct kioctx *ctx)
+static void kill_ctx(struct kioctx *ctx)
 {
 	int (*cancel)(struct kiocb *, struct io_event *);
+	struct task_struct *tsk = current;
+	DECLARE_WAITQUEUE(wait, tsk);
 	struct io_event res;
+
 	spin_lock_irq(&ctx->ctx_lock);
 	ctx->dead = 1;
 	while (!list_empty(&ctx->active_reqs)) {
@@ -329,15 +332,7 @@ static void aio_cancel_all(struct kioctx *ctx)
 			spin_lock_irq(&ctx->ctx_lock);
 		}
 	}
-	spin_unlock_irq(&ctx->ctx_lock);
-}
-
-static void wait_for_all_aios(struct kioctx *ctx)
-{
-	struct task_struct *tsk = current;
-	DECLARE_WAITQUEUE(wait, tsk);
 
-	spin_lock_irq(&ctx->ctx_lock);
 	if (!ctx->reqs_active)
 		goto out;
 
@@ -387,9 +382,7 @@ void exit_aio(struct mm_struct *mm)
 		ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list);
 		hlist_del_rcu(&ctx->list);
 
-		aio_cancel_all(ctx);
-
-		wait_for_all_aios(ctx);
+		kill_ctx(ctx);
 
 		if (1 != atomic_read(&ctx->users))
 			printk(KERN_DEBUG
@@ -1269,8 +1262,7 @@ static void io_destroy(struct kioctx *ioctx)
 	if (likely(!was_dead))
 		put_ioctx(ioctx);	/* twice for the list */
 
-	aio_cancel_all(ioctx);
-	wait_for_all_aios(ioctx);
+	kill_ctx(ioctx);
 
 	/*
 	 * Wake up any waiters.  The setting of ctx->dead must be seen
@@ -1278,7 +1270,6 @@ static void io_destroy(struct kioctx *ioctx)
 	 * locking done by the above calls to ensure this consistency.
 	 */
 	wake_up_all(&ioctx->wait);
-	put_ioctx(ioctx);	/* once for the lookup */
 }
 
 /* sys_io_setup:
@@ -1315,11 +1306,9 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	ret = PTR_ERR(ioctx);
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
-		if (!ret) {
-			put_ioctx(ioctx);
-			return 0;
-		}
-		io_destroy(ioctx);
+		if (ret)
+			io_destroy(ioctx);
+		put_ioctx(ioctx);
 	}
 
 out:
@@ -1337,6 +1326,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	struct kioctx *ioctx = lookup_ioctx(ctx);
 	if (likely(NULL != ioctx)) {
 		io_destroy(ioctx);
+		put_ioctx(ioctx);
 		return 0;
 	}
 	pr_debug("EINVAL: io_destroy: invalid context id\n");
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 85f1fcdb30e7..9dacb8586701 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -230,7 +230,7 @@ static void autofs_dev_ioctl_fd_install(unsigned int fd, struct file *file)
 	fdt = files_fdtable(files);
 	BUG_ON(fdt->fd[fd] != NULL);
 	rcu_assign_pointer(fdt->fd[fd], file);
-	FD_SET(fd, fdt->close_on_exec);
+	__set_close_on_exec(fd, fdt);
 	spin_unlock(&files->file_lock);
 }
 
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 4d5e6d26578c..2eb12f13593d 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -26,7 +26,6 @@
 #include <linux/coredump.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/a.out-core.h>
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 504b6eee50a9..48ffb3dc610a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -35,6 +35,7 @@
 #include <asm/uaccess.h>
 #include <asm/param.h>
 #include <asm/page.h>
+#include <asm/exec.h>
 
 static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs);
 static int load_elf_library(struct file *);
@@ -1414,6 +1415,22 @@ static void do_thread_regset_writeback(struct task_struct *task,
 		regset->writeback(task, regset, 1);
 }
 
+#ifndef PR_REG_SIZE
+#define PR_REG_SIZE(S) sizeof(S)
+#endif
+
+#ifndef PRSTATUS_SIZE
+#define PRSTATUS_SIZE(S) sizeof(S)
+#endif
+
+#ifndef PR_REG_PTR
+#define PR_REG_PTR(S) (&((S)->pr_reg))
+#endif
+
+#ifndef SET_PR_FPVALID
+#define SET_PR_FPVALID(S, V) ((S)->pr_fpvalid = (V))
+#endif
+
 static int fill_thread_core_info(struct elf_thread_core_info *t,
 				 const struct user_regset_view *view,
 				 long signr, size_t *total)
@@ -1428,11 +1445,11 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	 */
 	fill_prstatus(&t->prstatus, t->task, signr);
 	(void) view->regsets[0].get(t->task, &view->regsets[0],
-				    0, sizeof(t->prstatus.pr_reg),
-				    &t->prstatus.pr_reg, NULL);
+				    0, PR_REG_SIZE(t->prstatus.pr_reg),
+				    PR_REG_PTR(&t->prstatus), NULL);
 
 	fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
-		  sizeof(t->prstatus), &t->prstatus);
+		  PRSTATUS_SIZE(t->prstatus), &t->prstatus);
 	*total += notesize(&t->notes[0]);
 
 	do_thread_regset_writeback(t->task, &view->regsets[0]);
@@ -1462,7 +1479,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 						  regset->core_note_type,
 						  size, data);
 				else {
-					t->prstatus.pr_fpvalid = 1;
+					SET_PR_FPVALID(&t->prstatus, 1);
 					fill_note(&t->notes[i], "CORE",
 						  NT_PRFPREG, size, data);
 				}
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index c64bf5ee2df4..9bd5612a8224 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -39,6 +39,7 @@
 #include <asm/uaccess.h>
 #include <asm/param.h>
 #include <asm/pgalloc.h>
+#include <asm/exec.h>
 
 typedef char *elf_caddr_t;
 
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 5979027451b3..024d20ee3ca3 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -37,7 +37,6 @@
 #include <linux/syscalls.h>
 
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <asm/cacheflush.h>
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 0cc20b35c1c4..42704149b723 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -171,11 +171,11 @@ out:
 	spin_unlock_irqrestore(&workers->lock, flags);
 }
 
-static noinline int run_ordered_completions(struct btrfs_workers *workers,
+static noinline void run_ordered_completions(struct btrfs_workers *workers,
 					    struct btrfs_work *work)
 {
 	if (!workers->ordered)
-		return 0;
+		return;
 
 	set_bit(WORK_DONE_BIT, &work->flags);
 
@@ -213,7 +213,6 @@ static noinline int run_ordered_completions(struct btrfs_workers *workers,
 	}
 
 	spin_unlock(&workers->order_lock);
-	return 0;
 }
 
 static void put_worker(struct btrfs_worker_thread *worker)
@@ -399,7 +398,7 @@ again:
 /*
  * this will wait for all the worker threads to shutdown
  */
-int btrfs_stop_workers(struct btrfs_workers *workers)
+void btrfs_stop_workers(struct btrfs_workers *workers)
 {
 	struct list_head *cur;
 	struct btrfs_worker_thread *worker;
@@ -427,7 +426,6 @@ int btrfs_stop_workers(struct btrfs_workers *workers)
 		put_worker(worker);
 	}
 	spin_unlock_irq(&workers->lock);
-	return 0;
 }
 
 /*
@@ -615,14 +613,14 @@ found:
  * it was taken from.  It is intended for use with long running work functions
  * that make some progress and want to give the cpu up for others.
  */
-int btrfs_requeue_work(struct btrfs_work *work)
+void btrfs_requeue_work(struct btrfs_work *work)
 {
 	struct btrfs_worker_thread *worker = work->worker;
 	unsigned long flags;
 	int wake = 0;
 
 	if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
-		goto out;
+		return;
 
 	spin_lock_irqsave(&worker->lock, flags);
 	if (test_bit(WORK_HIGH_PRIO_BIT, &work->flags))
@@ -649,9 +647,6 @@ int btrfs_requeue_work(struct btrfs_work *work)
 	if (wake)
 		wake_up_process(worker->task);
 	spin_unlock_irqrestore(&worker->lock, flags);
-out:
-
-	return 0;
 }
 
 void btrfs_set_work_high_prio(struct btrfs_work *work)
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index f34cc31fa3c9..063698b90ce2 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -111,9 +111,9 @@ struct btrfs_workers {
 
 void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
 int btrfs_start_workers(struct btrfs_workers *workers);
-int btrfs_stop_workers(struct btrfs_workers *workers);
+void btrfs_stop_workers(struct btrfs_workers *workers);
 void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
 			struct btrfs_workers *async_starter);
-int btrfs_requeue_work(struct btrfs_work *work);
+void btrfs_requeue_work(struct btrfs_work *work);
 void btrfs_set_work_high_prio(struct btrfs_work *work);
 #endif
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 0436c12da8c2..f4e90748940a 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -116,6 +116,7 @@ add_parent:
  * to a logical address
  */
 static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
+					int search_commit_root,
 					struct __prelim_ref *ref,
 					struct ulist *parents)
 {
@@ -131,6 +132,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->search_commit_root = !!search_commit_root;
 
 	root_key.objectid = ref->root_id;
 	root_key.type = BTRFS_ROOT_ITEM_KEY;
@@ -188,6 +190,7 @@ out:
  * resolve all indirect backrefs from the list
  */
 static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
+				   int search_commit_root,
 				   struct list_head *head)
 {
 	int err;
@@ -212,7 +215,8 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
 			continue;
 		if (ref->count == 0)
 			continue;
-		err = __resolve_indirect_ref(fs_info, ref, parents);
+		err = __resolve_indirect_ref(fs_info, search_commit_root,
+					     ref, parents);
 		if (err) {
 			if (ret == 0)
 				ret = err;
@@ -586,6 +590,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_head *head;
 	int info_level = 0;
 	int ret;
+	int search_commit_root = (trans == BTRFS_BACKREF_SEARCH_COMMIT_ROOT);
 	struct list_head prefs_delayed;
 	struct list_head prefs;
 	struct __prelim_ref *ref;
@@ -600,6 +605,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->search_commit_root = !!search_commit_root;
 
 	/*
 	 * grab both a lock on the path and a lock on the delayed ref head.
@@ -614,35 +620,39 @@ again:
 		goto out;
 	BUG_ON(ret == 0);
 
-	/*
-	 * look if there are updates for this ref queued and lock the head
-	 */
-	delayed_refs = &trans->transaction->delayed_refs;
-	spin_lock(&delayed_refs->lock);
-	head = btrfs_find_delayed_ref_head(trans, bytenr);
-	if (head) {
-		if (!mutex_trylock(&head->mutex)) {
-			atomic_inc(&head->node.refs);
-			spin_unlock(&delayed_refs->lock);
-
-			btrfs_release_path(path);
-
-			/*
-			 * Mutex was contended, block until it's
-			 * released and try again
-			 */
-			mutex_lock(&head->mutex);
-			mutex_unlock(&head->mutex);
-			btrfs_put_delayed_ref(&head->node);
-			goto again;
-		}
-		ret = __add_delayed_refs(head, seq, &info_key, &prefs_delayed);
-		if (ret) {
-			spin_unlock(&delayed_refs->lock);
-			goto out;
+	if (trans != BTRFS_BACKREF_SEARCH_COMMIT_ROOT) {
+		/*
+		 * look if there are updates for this ref queued and lock the
+		 * head
+		 */
+		delayed_refs = &trans->transaction->delayed_refs;
+		spin_lock(&delayed_refs->lock);
+		head = btrfs_find_delayed_ref_head(trans, bytenr);
+		if (head) {
+			if (!mutex_trylock(&head->mutex)) {
+				atomic_inc(&head->node.refs);
+				spin_unlock(&delayed_refs->lock);
+
+				btrfs_release_path(path);
+
+				/*
+				 * Mutex was contended, block until it's
+				 * released and try again
+				 */
+				mutex_lock(&head->mutex);
+				mutex_unlock(&head->mutex);
+				btrfs_put_delayed_ref(&head->node);
+				goto again;
+			}
+			ret = __add_delayed_refs(head, seq, &info_key,
+						 &prefs_delayed);
+			if (ret) {
+				spin_unlock(&delayed_refs->lock);
+				goto out;
+			}
 		}
+		spin_unlock(&delayed_refs->lock);
 	}
-	spin_unlock(&delayed_refs->lock);
 
 	if (path->slots[0]) {
 		struct extent_buffer *leaf;
@@ -679,7 +689,7 @@ again:
 	if (ret)
 		goto out;
 
-	ret = __resolve_indirect_refs(fs_info, &prefs);
+	ret = __resolve_indirect_refs(fs_info, search_commit_root, &prefs);
 	if (ret)
 		goto out;
 
@@ -1074,8 +1084,7 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 	return 0;
 }
 
-static int iterate_leaf_refs(struct btrfs_fs_info *fs_info,
-				struct btrfs_path *path, u64 logical,
+static int iterate_leaf_refs(struct btrfs_fs_info *fs_info, u64 logical,
 				u64 orig_extent_item_objectid,
 				u64 extent_item_pos, u64 root,
 				iterate_extent_inodes_t *iterate, void *ctx)
@@ -1143,35 +1152,38 @@ static int iterate_leaf_refs(struct btrfs_fs_info *fs_info,
  * calls iterate() for every inode that references the extent identified by
  * the given parameters.
  * when the iterator function returns a non-zero value, iteration stops.
- * path is guaranteed to be in released state when iterate() is called.
  */
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
-				struct btrfs_path *path,
 				u64 extent_item_objectid, u64 extent_item_pos,
+				int search_commit_root,
 				iterate_extent_inodes_t *iterate, void *ctx)
 {
 	int ret;
 	struct list_head data_refs = LIST_HEAD_INIT(data_refs);
 	struct list_head shared_refs = LIST_HEAD_INIT(shared_refs);
 	struct btrfs_trans_handle *trans;
-	struct ulist *refs;
-	struct ulist *roots;
+	struct ulist *refs = NULL;
+	struct ulist *roots = NULL;
 	struct ulist_node *ref_node = NULL;
 	struct ulist_node *root_node = NULL;
 	struct seq_list seq_elem;
-	struct btrfs_delayed_ref_root *delayed_refs;
-
-	trans = btrfs_join_transaction(fs_info->extent_root);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
+	struct btrfs_delayed_ref_root *delayed_refs = NULL;
 
 	pr_debug("resolving all inodes for extent %llu\n",
 			extent_item_objectid);
 
-	delayed_refs = &trans->transaction->delayed_refs;
-	spin_lock(&delayed_refs->lock);
-	btrfs_get_delayed_seq(delayed_refs, &seq_elem);
-	spin_unlock(&delayed_refs->lock);
+	if (search_commit_root) {
+		trans = BTRFS_BACKREF_SEARCH_COMMIT_ROOT;
+	} else {
+		trans = btrfs_join_transaction(fs_info->extent_root);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
+
+		delayed_refs = &trans->transaction->delayed_refs;
+		spin_lock(&delayed_refs->lock);
+		btrfs_get_delayed_seq(delayed_refs, &seq_elem);
+		spin_unlock(&delayed_refs->lock);
+	}
 
 	ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid,
 				   extent_item_pos, seq_elem.seq,
@@ -1188,7 +1200,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 		while (!ret && (root_node = ulist_next(roots, root_node))) {
 			pr_debug("root %llu references leaf %llu\n",
 					root_node->val, ref_node->val);
-			ret = iterate_leaf_refs(fs_info, path, ref_node->val,
+			ret = iterate_leaf_refs(fs_info, ref_node->val,
 						extent_item_objectid,
 						extent_item_pos, root_node->val,
 						iterate, ctx);
@@ -1198,8 +1210,11 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 	ulist_free(refs);
 	ulist_free(roots);
 out:
-	btrfs_put_delayed_seq(delayed_refs, &seq_elem);
-	btrfs_end_transaction(trans, fs_info->extent_root);
+	if (!search_commit_root) {
+		btrfs_put_delayed_seq(delayed_refs, &seq_elem);
+		btrfs_end_transaction(trans, fs_info->extent_root);
+	}
+
 	return ret;
 }
 
@@ -1210,6 +1225,7 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 	int ret;
 	u64 extent_item_pos;
 	struct btrfs_key found_key;
+	int search_commit_root = path->search_commit_root;
 
 	ret = extent_from_logical(fs_info, logical, path,
 					&found_key);
@@ -1220,8 +1236,9 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 		return ret;
 
 	extent_item_pos = logical - found_key.objectid;
-	ret = iterate_extent_inodes(fs_info, path, found_key.objectid,
-					extent_item_pos, iterate, ctx);
+	ret = iterate_extent_inodes(fs_info, found_key.objectid,
+					extent_item_pos, search_commit_root,
+					iterate, ctx);
 
 	return ret;
 }
@@ -1342,12 +1359,6 @@ int paths_from_inode(u64 inum, struct inode_fs_paths *ipath)
 				inode_to_path, ipath);
 }
 
-/*
- * allocates space to return multiple file system paths for an inode.
- * total_bytes to allocate are passed, note that space usable for actual path
- * information will be total_bytes - sizeof(struct inode_fs_paths).
- * the returned pointer must be freed with free_ipath() in the end.
- */
 struct btrfs_data_container *init_data_container(u32 total_bytes)
 {
 	struct btrfs_data_container *data;
@@ -1403,5 +1414,6 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 
 void free_ipath(struct inode_fs_paths *ipath)
 {
+	kfree(ipath->fspath);
 	kfree(ipath);
 }
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index d00dfa9ca934..57ea2e959e4d 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -22,6 +22,8 @@
 #include "ioctl.h"
 #include "ulist.h"
 
+#define BTRFS_BACKREF_SEARCH_COMMIT_ROOT ((struct btrfs_trans_handle *)0)
+
 struct inode_fs_paths {
 	struct btrfs_path		*btrfs_path;
 	struct btrfs_root		*fs_root;
@@ -44,9 +46,8 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 				u64 *out_root, u8 *out_level);
 
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
-				struct btrfs_path *path,
 				u64 extent_item_objectid,
-				u64 extent_offset,
+				u64 extent_offset, int search_commit_root,
 				iterate_extent_inodes_t *iterate, void *ctx);
 
 int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b805afb37fa8..d286b40a5671 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -226,8 +226,8 @@ out:
  * Clear the writeback bits on all of the file
  * pages for a compressed write
  */
-static noinline int end_compressed_writeback(struct inode *inode, u64 start,
-					     unsigned long ram_size)
+static noinline void end_compressed_writeback(struct inode *inode, u64 start,
+					      unsigned long ram_size)
 {
 	unsigned long index = start >> PAGE_CACHE_SHIFT;
 	unsigned long end_index = (start + ram_size - 1) >> PAGE_CACHE_SHIFT;
@@ -253,7 +253,6 @@ static noinline int end_compressed_writeback(struct inode *inode, u64 start,
 		index += ret;
 	}
 	/* the inode may be gone now */
-	return 0;
 }
 
 /*
@@ -392,16 +391,16 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 			 */
 			atomic_inc(&cb->pending_bios);
 			ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 
 			if (!skip_sum) {
 				ret = btrfs_csum_one_bio(root, inode, bio,
 							 start, 1);
-				BUG_ON(ret);
+				BUG_ON(ret); /* -ENOMEM */
 			}
 
 			ret = btrfs_map_bio(root, WRITE, bio, 0, 1);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 
 			bio_put(bio);
 
@@ -421,15 +420,15 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	bio_get(bio);
 
 	ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -ENOMEM */
 
 	if (!skip_sum) {
 		ret = btrfs_csum_one_bio(root, inode, bio, start, 1);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 
 	ret = btrfs_map_bio(root, WRITE, bio, 0, 1);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -ENOMEM */
 
 	bio_put(bio);
 	return 0;
@@ -497,7 +496,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		 * sure they map to this compressed extent on disk.
 		 */
 		set_page_extent_mapped(page);
-		lock_extent(tree, last_offset, end, GFP_NOFS);
+		lock_extent(tree, last_offset, end);
 		read_lock(&em_tree->lock);
 		em = lookup_extent_mapping(em_tree, last_offset,
 					   PAGE_CACHE_SIZE);
@@ -507,7 +506,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		    (last_offset + PAGE_CACHE_SIZE > extent_map_end(em)) ||
 		    (em->block_start >> 9) != cb->orig_bio->bi_sector) {
 			free_extent_map(em);
-			unlock_extent(tree, last_offset, end, GFP_NOFS);
+			unlock_extent(tree, last_offset, end);
 			unlock_page(page);
 			page_cache_release(page);
 			break;
@@ -535,7 +534,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			nr_pages++;
 			page_cache_release(page);
 		} else {
-			unlock_extent(tree, last_offset, end, GFP_NOFS);
+			unlock_extent(tree, last_offset, end);
 			unlock_page(page);
 			page_cache_release(page);
 			break;
@@ -662,7 +661,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			bio_get(comp_bio);
 
 			ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 
 			/*
 			 * inc the count before we submit the bio so
@@ -675,14 +674,14 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
 				ret = btrfs_lookup_bio_sums(root, inode,
 							comp_bio, sums);
-				BUG_ON(ret);
+				BUG_ON(ret); /* -ENOMEM */
 			}
 			sums += (comp_bio->bi_size + root->sectorsize - 1) /
 				root->sectorsize;
 
 			ret = btrfs_map_bio(root, READ, comp_bio,
 					    mirror_num, 0);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 
 			bio_put(comp_bio);
 
@@ -698,15 +697,15 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	bio_get(comp_bio);
 
 	ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -ENOMEM */
 
 	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
 		ret = btrfs_lookup_bio_sums(root, inode, comp_bio, sums);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 
 	ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -ENOMEM */
 
 	bio_put(comp_bio);
 	return 0;
@@ -734,7 +733,7 @@ struct btrfs_compress_op *btrfs_compress_op[] = {
 	&btrfs_lzo_compress,
 };
 
-int __init btrfs_init_compress(void)
+void __init btrfs_init_compress(void)
 {
 	int i;
 
@@ -744,7 +743,6 @@ int __init btrfs_init_compress(void)
 		atomic_set(&comp_alloc_workspace[i], 0);
 		init_waitqueue_head(&comp_workspace_wait[i]);
 	}
-	return 0;
 }
 
 /*
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index a12059f4f0fd..9afb0a62ae82 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -19,7 +19,7 @@
 #ifndef __BTRFS_COMPRESSION_
 #define __BTRFS_COMPRESSION_
 
-int btrfs_init_compress(void);
+void btrfs_init_compress(void);
 void btrfs_exit_compress(void);
 
 int btrfs_compress_pages(int type, struct address_space *mapping,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0639a555e16e..e801f226d7e0 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -36,7 +36,7 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      struct extent_buffer *dst_buf,
 			      struct extent_buffer *src_buf);
-static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+static void del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		   struct btrfs_path *path, int level, int slot);
 
 struct btrfs_path *btrfs_alloc_path(void)
@@ -156,10 +156,23 @@ struct extent_buffer *btrfs_root_node(struct btrfs_root *root)
 {
 	struct extent_buffer *eb;
 
-	rcu_read_lock();
-	eb = rcu_dereference(root->node);
-	extent_buffer_get(eb);
-	rcu_read_unlock();
+	while (1) {
+		rcu_read_lock();
+		eb = rcu_dereference(root->node);
+
+		/*
+		 * RCU really hurts here, we could free up the root node because
+		 * it was cow'ed but we may not get the new root node yet so do
+		 * the inc_not_zero dance and if it doesn't work then
+		 * synchronize_rcu and try again.
+		 */
+		if (atomic_inc_not_zero(&eb->refs)) {
+			rcu_read_unlock();
+			break;
+		}
+		rcu_read_unlock();
+		synchronize_rcu();
+	}
 	return eb;
 }
 
@@ -331,8 +344,13 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 	if (btrfs_block_can_be_shared(root, buf)) {
 		ret = btrfs_lookup_extent_info(trans, root, buf->start,
 					       buf->len, &refs, &flags);
-		BUG_ON(ret);
-		BUG_ON(refs == 0);
+		if (ret)
+			return ret;
+		if (refs == 0) {
+			ret = -EROFS;
+			btrfs_std_error(root->fs_info, ret);
+			return ret;
+		}
 	} else {
 		refs = 1;
 		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
@@ -351,14 +369,14 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 		     root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) &&
 		    !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
 			ret = btrfs_inc_ref(trans, root, buf, 1, 1);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 
 			if (root->root_key.objectid ==
 			    BTRFS_TREE_RELOC_OBJECTID) {
 				ret = btrfs_dec_ref(trans, root, buf, 0, 1);
-				BUG_ON(ret);
+				BUG_ON(ret); /* -ENOMEM */
 				ret = btrfs_inc_ref(trans, root, cow, 1, 1);
-				BUG_ON(ret);
+				BUG_ON(ret); /* -ENOMEM */
 			}
 			new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
 		} else {
@@ -368,14 +386,15 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 				ret = btrfs_inc_ref(trans, root, cow, 1, 1);
 			else
 				ret = btrfs_inc_ref(trans, root, cow, 0, 1);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 		}
 		if (new_flags != 0) {
 			ret = btrfs_set_disk_extent_flags(trans, root,
 							  buf->start,
 							  buf->len,
 							  new_flags, 0);
-			BUG_ON(ret);
+			if (ret)
+				return ret;
 		}
 	} else {
 		if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
@@ -384,9 +403,9 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 				ret = btrfs_inc_ref(trans, root, cow, 1, 1);
 			else
 				ret = btrfs_inc_ref(trans, root, cow, 0, 1);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 			ret = btrfs_dec_ref(trans, root, buf, 1, 1);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 		}
 		clean_tree_block(trans, root, buf);
 		*last_ref = 1;
@@ -415,7 +434,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_disk_key disk_key;
 	struct extent_buffer *cow;
-	int level;
+	int level, ret;
 	int last_ref = 0;
 	int unlock_orig = 0;
 	u64 parent_start;
@@ -467,7 +486,11 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 			    (unsigned long)btrfs_header_fsid(cow),
 			    BTRFS_FSID_SIZE);
 
-	update_ref_for_cow(trans, root, buf, cow, &last_ref);
+	ret = update_ref_for_cow(trans, root, buf, cow, &last_ref);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		return ret;
+	}
 
 	if (root->ref_cows)
 		btrfs_reloc_cow_block(trans, root, buf, cow);
@@ -504,7 +527,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	}
 	if (unlock_orig)
 		btrfs_tree_unlock(buf);
-	free_extent_buffer(buf);
+	free_extent_buffer_stale(buf);
 	btrfs_mark_buffer_dirty(cow);
 	*cow_ret = cow;
 	return 0;
@@ -934,7 +957,12 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 		/* promote the child to a root */
 		child = read_node_slot(root, mid, 0);
-		BUG_ON(!child);
+		if (!child) {
+			ret = -EROFS;
+			btrfs_std_error(root->fs_info, ret);
+			goto enospc;
+		}
+
 		btrfs_tree_lock(child);
 		btrfs_set_lock_blocking(child);
 		ret = btrfs_cow_block(trans, root, child, mid, 0, &child);
@@ -959,7 +987,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		root_sub_used(root, mid->len);
 		btrfs_free_tree_block(trans, root, mid, 0, 1, 0);
 		/* once for the root ptr */
-		free_extent_buffer(mid);
+		free_extent_buffer_stale(mid);
 		return 0;
 	}
 	if (btrfs_header_nritems(mid) >
@@ -1010,13 +1038,10 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		if (btrfs_header_nritems(right) == 0) {
 			clean_tree_block(trans, root, right);
 			btrfs_tree_unlock(right);
-			wret = del_ptr(trans, root, path, level + 1, pslot +
-				       1);
-			if (wret)
-				ret = wret;
+			del_ptr(trans, root, path, level + 1, pslot + 1);
 			root_sub_used(root, right->len);
 			btrfs_free_tree_block(trans, root, right, 0, 1, 0);
-			free_extent_buffer(right);
+			free_extent_buffer_stale(right);
 			right = NULL;
 		} else {
 			struct btrfs_disk_key right_key;
@@ -1035,7 +1060,11 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		 * otherwise we would have pulled some pointers from the
 		 * right
 		 */
-		BUG_ON(!left);
+		if (!left) {
+			ret = -EROFS;
+			btrfs_std_error(root->fs_info, ret);
+			goto enospc;
+		}
 		wret = balance_node_right(trans, root, mid, left);
 		if (wret < 0) {
 			ret = wret;
@@ -1051,12 +1080,10 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 	if (btrfs_header_nritems(mid) == 0) {
 		clean_tree_block(trans, root, mid);
 		btrfs_tree_unlock(mid);
-		wret = del_ptr(trans, root, path, level + 1, pslot);
-		if (wret)
-			ret = wret;
+		del_ptr(trans, root, path, level + 1, pslot);
 		root_sub_used(root, mid->len);
 		btrfs_free_tree_block(trans, root, mid, 0, 1, 0);
-		free_extent_buffer(mid);
+		free_extent_buffer_stale(mid);
 		mid = NULL;
 	} else {
 		/* update the parent key to reflect our changes */
@@ -1382,7 +1409,8 @@ static noinline int reada_for_balance(struct btrfs_root *root,
  * if lowest_unlock is 1, level 0 won't be unlocked
  */
 static noinline void unlock_up(struct btrfs_path *path, int level,
-			       int lowest_unlock)
+			       int lowest_unlock, int min_write_lock_level,
+			       int *write_lock_level)
 {
 	int i;
 	int skip_level = level;
@@ -1414,6 +1442,11 @@ static noinline void unlock_up(struct btrfs_path *path, int level,
 		if (i >= lowest_unlock && i > skip_level && path->locks[i]) {
 			btrfs_tree_unlock_rw(t, path->locks[i]);
 			path->locks[i] = 0;
+			if (write_lock_level &&
+			    i > min_write_lock_level &&
+			    i <= *write_lock_level) {
+				*write_lock_level = i - 1;
+			}
 		}
 	}
 }
@@ -1637,6 +1670,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
 	/* everything at write_lock_level or lower must be write locked */
 	int write_lock_level = 0;
 	u8 lowest_level = 0;
+	int min_write_lock_level;
 
 	lowest_level = p->lowest_level;
 	WARN_ON(lowest_level && ins_len > 0);
@@ -1664,6 +1698,8 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
 	if (cow && (p->keep_locks || p->lowest_level))
 		write_lock_level = BTRFS_MAX_LEVEL;
 
+	min_write_lock_level = write_lock_level;
+
 again:
 	/*
 	 * we try very hard to do read locks on the root
@@ -1795,7 +1831,8 @@ cow_done:
 				goto again;
 			}
 
-			unlock_up(p, level, lowest_unlock);
+			unlock_up(p, level, lowest_unlock,
+				  min_write_lock_level, &write_lock_level);
 
 			if (level == lowest_level) {
 				if (dec)
@@ -1857,7 +1894,8 @@ cow_done:
 				}
 			}
 			if (!p->search_for_split)
-				unlock_up(p, level, lowest_unlock);
+				unlock_up(p, level, lowest_unlock,
+					  min_write_lock_level, &write_lock_level);
 			goto done;
 		}
 	}
@@ -1881,15 +1919,12 @@ done:
  * fixing up pointers when a given leaf/node is not in slot 0 of the
  * higher levels
  *
- * If this fails to write a tree block, it returns -1, but continues
- * fixing up the blocks in ram so the tree is consistent.
  */
-static int fixup_low_keys(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root, struct btrfs_path *path,
-			  struct btrfs_disk_key *key, int level)
+static void fixup_low_keys(struct btrfs_trans_handle *trans,
+			   struct btrfs_root *root, struct btrfs_path *path,
+			   struct btrfs_disk_key *key, int level)
 {
 	int i;
-	int ret = 0;
 	struct extent_buffer *t;
 
 	for (i = level; i < BTRFS_MAX_LEVEL; i++) {
@@ -1902,7 +1937,6 @@ static int fixup_low_keys(struct btrfs_trans_handle *trans,
 		if (tslot != 0)
 			break;
 	}
-	return ret;
 }
 
 /*
@@ -1911,9 +1945,9 @@ static int fixup_low_keys(struct btrfs_trans_handle *trans,
  * This function isn't completely safe. It's the caller's responsibility
  * that the new key won't break the order
  */
-int btrfs_set_item_key_safe(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root, struct btrfs_path *path,
-			    struct btrfs_key *new_key)
+void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root, struct btrfs_path *path,
+			     struct btrfs_key *new_key)
 {
 	struct btrfs_disk_key disk_key;
 	struct extent_buffer *eb;
@@ -1923,13 +1957,11 @@ int btrfs_set_item_key_safe(struct btrfs_trans_handle *trans,
 	slot = path->slots[0];
 	if (slot > 0) {
 		btrfs_item_key(eb, &disk_key, slot - 1);
-		if (comp_keys(&disk_key, new_key) >= 0)
-			return -1;
+		BUG_ON(comp_keys(&disk_key, new_key) >= 0);
 	}
 	if (slot < btrfs_header_nritems(eb) - 1) {
 		btrfs_item_key(eb, &disk_key, slot + 1);
-		if (comp_keys(&disk_key, new_key) <= 0)
-			return -1;
+		BUG_ON(comp_keys(&disk_key, new_key) <= 0);
 	}
 
 	btrfs_cpu_key_to_disk(&disk_key, new_key);
@@ -1937,7 +1969,6 @@ int btrfs_set_item_key_safe(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(eb);
 	if (slot == 0)
 		fixup_low_keys(trans, root, path, &disk_key, 1);
-	return 0;
 }
 
 /*
@@ -2140,12 +2171,11 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
  *
  * slot and level indicate where you want the key to go, and
  * blocknr is the block the key points to.
- *
- * returns zero on success and < 0 on any error
  */
-static int insert_ptr(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_path *path, struct btrfs_disk_key
-		      *key, u64 bytenr, int slot, int level)
+static void insert_ptr(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root, struct btrfs_path *path,
+		       struct btrfs_disk_key *key, u64 bytenr,
+		       int slot, int level)
 {
 	struct extent_buffer *lower;
 	int nritems;
@@ -2155,8 +2185,7 @@ static int insert_ptr(struct btrfs_trans_handle *trans, struct btrfs_root
 	lower = path->nodes[level];
 	nritems = btrfs_header_nritems(lower);
 	BUG_ON(slot > nritems);
-	if (nritems == BTRFS_NODEPTRS_PER_BLOCK(root))
-		BUG();
+	BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(root));
 	if (slot != nritems) {
 		memmove_extent_buffer(lower,
 			      btrfs_node_key_ptr_offset(slot + 1),
@@ -2169,7 +2198,6 @@ static int insert_ptr(struct btrfs_trans_handle *trans, struct btrfs_root
 	btrfs_set_node_ptr_generation(lower, slot, trans->transid);
 	btrfs_set_header_nritems(lower, nritems + 1);
 	btrfs_mark_buffer_dirty(lower);
-	return 0;
 }
 
 /*
@@ -2190,7 +2218,6 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	struct btrfs_disk_key disk_key;
 	int mid;
 	int ret;
-	int wret;
 	u32 c_nritems;
 
 	c = path->nodes[level];
@@ -2247,11 +2274,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(c);
 	btrfs_mark_buffer_dirty(split);
 
-	wret = insert_ptr(trans, root, path, &disk_key, split->start,
-			  path->slots[level + 1] + 1,
-			  level + 1);
-	if (wret)
-		ret = wret;
+	insert_ptr(trans, root, path, &disk_key, split->start,
+		   path->slots[level + 1] + 1, level + 1);
 
 	if (path->slots[level] >= mid) {
 		path->slots[level] -= mid;
@@ -2320,6 +2344,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 {
 	struct extent_buffer *left = path->nodes[0];
 	struct extent_buffer *upper = path->nodes[1];
+	struct btrfs_map_token token;
 	struct btrfs_disk_key disk_key;
 	int slot;
 	u32 i;
@@ -2331,6 +2356,8 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 	u32 data_end;
 	u32 this_item_size;
 
+	btrfs_init_map_token(&token);
+
 	if (empty)
 		nr = 0;
 	else
@@ -2408,8 +2435,8 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 	push_space = BTRFS_LEAF_DATA_SIZE(root);
 	for (i = 0; i < right_nritems; i++) {
 		item = btrfs_item_nr(right, i);
-		push_space -= btrfs_item_size(right, item);
-		btrfs_set_item_offset(right, item, push_space);
+		push_space -= btrfs_token_item_size(right, item, &token);
+		btrfs_set_token_item_offset(right, item, push_space, &token);
 	}
 
 	left_nritems -= push_items;
@@ -2537,9 +2564,11 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 	u32 old_left_nritems;
 	u32 nr;
 	int ret = 0;
-	int wret;
 	u32 this_item_size;
 	u32 old_left_item_size;
+	struct btrfs_map_token token;
+
+	btrfs_init_map_token(&token);
 
 	if (empty)
 		nr = min(right_nritems, max_slot);
@@ -2600,9 +2629,10 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 
 		item = btrfs_item_nr(left, i);
 
-		ioff = btrfs_item_offset(left, item);
-		btrfs_set_item_offset(left, item,
-		      ioff - (BTRFS_LEAF_DATA_SIZE(root) - old_left_item_size));
+		ioff = btrfs_token_item_offset(left, item, &token);
+		btrfs_set_token_item_offset(left, item,
+		      ioff - (BTRFS_LEAF_DATA_SIZE(root) - old_left_item_size),
+		      &token);
 	}
 	btrfs_set_header_nritems(left, old_left_nritems + push_items);
 
@@ -2632,8 +2662,9 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 	for (i = 0; i < right_nritems; i++) {
 		item = btrfs_item_nr(right, i);
 
-		push_space = push_space - btrfs_item_size(right, item);
-		btrfs_set_item_offset(right, item, push_space);
+		push_space = push_space - btrfs_token_item_size(right,
+								item, &token);
+		btrfs_set_token_item_offset(right, item, push_space, &token);
 	}
 
 	btrfs_mark_buffer_dirty(left);
@@ -2643,9 +2674,7 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 		clean_tree_block(trans, root, right);
 
 	btrfs_item_key(right, &disk_key, 0);
-	wret = fixup_low_keys(trans, root, path, &disk_key, 1);
-	if (wret)
-		ret = wret;
+	fixup_low_keys(trans, root, path, &disk_key, 1);
 
 	/* then fixup the leaf pointer in the path */
 	if (path->slots[0] < push_items) {
@@ -2716,7 +2745,8 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 			      path->nodes[1], slot - 1, &left);
 	if (ret) {
 		/* we hit -ENOSPC, but it isn't fatal here */
-		ret = 1;
+		if (ret == -ENOSPC)
+			ret = 1;
 		goto out;
 	}
 
@@ -2738,22 +2768,21 @@ out:
 /*
  * split the path's leaf in two, making sure there is at least data_size
  * available for the resulting leaf level of the path.
- *
- * returns 0 if all went well and < 0 on failure.
  */
-static noinline int copy_for_split(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
-			       struct btrfs_path *path,
-			       struct extent_buffer *l,
-			       struct extent_buffer *right,
-			       int slot, int mid, int nritems)
+static noinline void copy_for_split(struct btrfs_trans_handle *trans,
+				    struct btrfs_root *root,
+				    struct btrfs_path *path,
+				    struct extent_buffer *l,
+				    struct extent_buffer *right,
+				    int slot, int mid, int nritems)
 {
 	int data_copy_size;
 	int rt_data_off;
 	int i;
-	int ret = 0;
-	int wret;
 	struct btrfs_disk_key disk_key;
+	struct btrfs_map_token token;
+
+	btrfs_init_map_token(&token);
 
 	nritems = nritems - mid;
 	btrfs_set_header_nritems(right, nritems);
@@ -2775,17 +2804,15 @@ static noinline int copy_for_split(struct btrfs_trans_handle *trans,
 		struct btrfs_item *item = btrfs_item_nr(right, i);
 		u32 ioff;
 
-		ioff = btrfs_item_offset(right, item);
-		btrfs_set_item_offset(right, item, ioff + rt_data_off);
+		ioff = btrfs_token_item_offset(right, item, &token);
+		btrfs_set_token_item_offset(right, item,
+					    ioff + rt_data_off, &token);
 	}
 
 	btrfs_set_header_nritems(l, mid);
-	ret = 0;
 	btrfs_item_key(right, &disk_key, 0);
-	wret = insert_ptr(trans, root, path, &disk_key, right->start,
-			  path->slots[1] + 1, 1);
-	if (wret)
-		ret = wret;
+	insert_ptr(trans, root, path, &disk_key, right->start,
+		   path->slots[1] + 1, 1);
 
 	btrfs_mark_buffer_dirty(right);
 	btrfs_mark_buffer_dirty(l);
@@ -2803,8 +2830,6 @@ static noinline int copy_for_split(struct btrfs_trans_handle *trans,
 	}
 
 	BUG_ON(path->slots[0] < 0);
-
-	return ret;
 }
 
 /*
@@ -2993,12 +3018,8 @@ again:
 	if (split == 0) {
 		if (mid <= slot) {
 			btrfs_set_header_nritems(right, 0);
-			wret = insert_ptr(trans, root, path,
-					  &disk_key, right->start,
-					  path->slots[1] + 1, 1);
-			if (wret)
-				ret = wret;
-
+			insert_ptr(trans, root, path, &disk_key, right->start,
+				   path->slots[1] + 1, 1);
 			btrfs_tree_unlock(path->nodes[0]);
 			free_extent_buffer(path->nodes[0]);
 			path->nodes[0] = right;
@@ -3006,29 +3027,21 @@ again:
 			path->slots[1] += 1;
 		} else {
 			btrfs_set_header_nritems(right, 0);
-			wret = insert_ptr(trans, root, path,
-					  &disk_key,
-					  right->start,
+			insert_ptr(trans, root, path, &disk_key, right->start,
 					  path->slots[1], 1);
-			if (wret)
-				ret = wret;
 			btrfs_tree_unlock(path->nodes[0]);
 			free_extent_buffer(path->nodes[0]);
 			path->nodes[0] = right;
 			path->slots[0] = 0;
-			if (path->slots[1] == 0) {
-				wret = fixup_low_keys(trans, root,
-						path, &disk_key, 1);
-				if (wret)
-					ret = wret;
-			}
+			if (path->slots[1] == 0)
+				fixup_low_keys(trans, root, path,
+					       &disk_key, 1);
 		}
 		btrfs_mark_buffer_dirty(right);
 		return ret;
 	}
 
-	ret = copy_for_split(trans, root, path, l, right, slot, mid, nritems);
-	BUG_ON(ret);
+	copy_for_split(trans, root, path, l, right, slot, mid, nritems);
 
 	if (split == 2) {
 		BUG_ON(num_doubles != 0);
@@ -3036,7 +3049,7 @@ again:
 		goto again;
 	}
 
-	return ret;
+	return 0;
 
 push_for_double:
 	push_for_double_split(trans, root, path, data_size);
@@ -3238,11 +3251,9 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
 		return ret;
 
 	path->slots[0]++;
-	ret = setup_items_for_insert(trans, root, path, new_key, &item_size,
-				     item_size, item_size +
-				     sizeof(struct btrfs_item), 1);
-	BUG_ON(ret);
-
+	setup_items_for_insert(trans, root, path, new_key, &item_size,
+			       item_size, item_size +
+			       sizeof(struct btrfs_item), 1);
 	leaf = path->nodes[0];
 	memcpy_extent_buffer(leaf,
 			     btrfs_item_ptr_offset(leaf, path->slots[0]),
@@ -3257,10 +3268,10 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
  * off the end of the item or if we shift the item to chop bytes off
  * the front.
  */
-int btrfs_truncate_item(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root,
-			struct btrfs_path *path,
-			u32 new_size, int from_end)
+void btrfs_truncate_item(struct btrfs_trans_handle *trans,
+			 struct btrfs_root *root,
+			 struct btrfs_path *path,
+			 u32 new_size, int from_end)
 {
 	int slot;
 	struct extent_buffer *leaf;
@@ -3271,13 +3282,16 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans,
 	unsigned int old_size;
 	unsigned int size_diff;
 	int i;
+	struct btrfs_map_token token;
+
+	btrfs_init_map_token(&token);
 
 	leaf = path->nodes[0];
 	slot = path->slots[0];
 
 	old_size = btrfs_item_size_nr(leaf, slot);
 	if (old_size == new_size)
-		return 0;
+		return;
 
 	nritems = btrfs_header_nritems(leaf);
 	data_end = leaf_data_end(root, leaf);
@@ -3297,8 +3311,9 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans,
 		u32 ioff;
 		item = btrfs_item_nr(leaf, i);
 
-		ioff = btrfs_item_offset(leaf, item);
-		btrfs_set_item_offset(leaf, item, ioff + size_diff);
+		ioff = btrfs_token_item_offset(leaf, item, &token);
+		btrfs_set_token_item_offset(leaf, item,
+					    ioff + size_diff, &token);
 	}
 
 	/* shift the data */
@@ -3350,15 +3365,14 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans,
 		btrfs_print_leaf(root, leaf);
 		BUG();
 	}
-	return 0;
 }
 
 /*
  * make the item pointed to by the path bigger, data_size is the new size.
  */
-int btrfs_extend_item(struct btrfs_trans_handle *trans,
-		      struct btrfs_root *root, struct btrfs_path *path,
-		      u32 data_size)
+void btrfs_extend_item(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root, struct btrfs_path *path,
+		       u32 data_size)
 {
 	int slot;
 	struct extent_buffer *leaf;
@@ -3368,6 +3382,9 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans,
 	unsigned int old_data;
 	unsigned int old_size;
 	int i;
+	struct btrfs_map_token token;
+
+	btrfs_init_map_token(&token);
 
 	leaf = path->nodes[0];
 
@@ -3397,8 +3414,9 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans,
 		u32 ioff;
 		item = btrfs_item_nr(leaf, i);
 
-		ioff = btrfs_item_offset(leaf, item);
-		btrfs_set_item_offset(leaf, item, ioff - data_size);
+		ioff = btrfs_token_item_offset(leaf, item, &token);
+		btrfs_set_token_item_offset(leaf, item,
+					    ioff - data_size, &token);
 	}
 
 	/* shift the data */
@@ -3416,7 +3434,6 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans,
 		btrfs_print_leaf(root, leaf);
 		BUG();
 	}
-	return 0;
 }
 
 /*
@@ -3441,6 +3458,9 @@ int btrfs_insert_some_items(struct btrfs_trans_handle *trans,
 	unsigned int data_end;
 	struct btrfs_disk_key disk_key;
 	struct btrfs_key found_key;
+	struct btrfs_map_token token;
+
+	btrfs_init_map_token(&token);
 
 	for (i = 0; i < nr; i++) {
 		if (total_size + data_size[i] + sizeof(struct btrfs_item) >
@@ -3506,8 +3526,9 @@ int btrfs_insert_some_items(struct btrfs_trans_handle *trans,
 			u32 ioff;
 
 			item = btrfs_item_nr(leaf, i);
-			ioff = btrfs_item_offset(leaf, item);
-			btrfs_set_item_offset(leaf, item, ioff - total_data);
+			ioff = btrfs_token_item_offset(leaf, item, &token);
+			btrfs_set_token_item_offset(leaf, item,
+						    ioff - total_data, &token);
 		}
 		/* shift the items */
 		memmove_extent_buffer(leaf, btrfs_item_nr_offset(slot + nr),
@@ -3534,9 +3555,10 @@ int btrfs_insert_some_items(struct btrfs_trans_handle *trans,
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key + i);
 		btrfs_set_item_key(leaf, &disk_key, slot + i);
 		item = btrfs_item_nr(leaf, slot + i);
-		btrfs_set_item_offset(leaf, item, data_end - data_size[i]);
+		btrfs_set_token_item_offset(leaf, item,
+					    data_end - data_size[i], &token);
 		data_end -= data_size[i];
-		btrfs_set_item_size(leaf, item, data_size[i]);
+		btrfs_set_token_item_size(leaf, item, data_size[i], &token);
 	}
 	btrfs_set_header_nritems(leaf, nritems + nr);
 	btrfs_mark_buffer_dirty(leaf);
@@ -3544,7 +3566,7 @@ int btrfs_insert_some_items(struct btrfs_trans_handle *trans,
 	ret = 0;
 	if (slot == 0) {
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
-		ret = fixup_low_keys(trans, root, path, &disk_key, 1);
+		fixup_low_keys(trans, root, path, &disk_key, 1);
 	}
 
 	if (btrfs_leaf_free_space(root, leaf) < 0) {
@@ -3562,19 +3584,21 @@ out:
  * to save stack depth by doing the bulk of the work in a function
  * that doesn't call btrfs_search_slot
  */
-int setup_items_for_insert(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root, struct btrfs_path *path,
-			   struct btrfs_key *cpu_key, u32 *data_size,
-			   u32 total_data, u32 total_size, int nr)
+void setup_items_for_insert(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root, struct btrfs_path *path,
+			    struct btrfs_key *cpu_key, u32 *data_size,
+			    u32 total_data, u32 total_size, int nr)
 {
 	struct btrfs_item *item;
 	int i;
 	u32 nritems;
 	unsigned int data_end;
 	struct btrfs_disk_key disk_key;
-	int ret;
 	struct extent_buffer *leaf;
 	int slot;
+	struct btrfs_map_token token;
+
+	btrfs_init_map_token(&token);
 
 	leaf = path->nodes[0];
 	slot = path->slots[0];
@@ -3606,8 +3630,9 @@ int setup_items_for_insert(struct btrfs_trans_handle *trans,
 			u32 ioff;
 
 			item = btrfs_item_nr(leaf, i);
-			ioff = btrfs_item_offset(leaf, item);
-			btrfs_set_item_offset(leaf, item, ioff - total_data);
+			ioff = btrfs_token_item_offset(leaf, item, &token);
+			btrfs_set_token_item_offset(leaf, item,
+						    ioff - total_data, &token);
 		}
 		/* shift the items */
 		memmove_extent_buffer(leaf, btrfs_item_nr_offset(slot + nr),
@@ -3626,17 +3651,17 @@ int setup_items_for_insert(struct btrfs_trans_handle *trans,
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key + i);
 		btrfs_set_item_key(leaf, &disk_key, slot + i);
 		item = btrfs_item_nr(leaf, slot + i);
-		btrfs_set_item_offset(leaf, item, data_end - data_size[i]);
+		btrfs_set_token_item_offset(leaf, item,
+					    data_end - data_size[i], &token);
 		data_end -= data_size[i];
-		btrfs_set_item_size(leaf, item, data_size[i]);
+		btrfs_set_token_item_size(leaf, item, data_size[i], &token);
 	}
 
 	btrfs_set_header_nritems(leaf, nritems + nr);
 
-	ret = 0;
 	if (slot == 0) {
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
-		ret = fixup_low_keys(trans, root, path, &disk_key, 1);
+		fixup_low_keys(trans, root, path, &disk_key, 1);
 	}
 	btrfs_unlock_up_safe(path, 1);
 	btrfs_mark_buffer_dirty(leaf);
@@ -3645,7 +3670,6 @@ int setup_items_for_insert(struct btrfs_trans_handle *trans,
 		btrfs_print_leaf(root, leaf);
 		BUG();
 	}
-	return ret;
 }
 
 /*
@@ -3672,16 +3696,14 @@ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
 	if (ret == 0)
 		return -EEXIST;
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	slot = path->slots[0];
 	BUG_ON(slot < 0);
 
-	ret = setup_items_for_insert(trans, root, path, cpu_key, data_size,
+	setup_items_for_insert(trans, root, path, cpu_key, data_size,
 			       total_data, total_size, nr);
-
-out:
-	return ret;
+	return 0;
 }
 
 /*
@@ -3717,13 +3739,11 @@ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root
  * the tree should have been previously balanced so the deletion does not
  * empty a node.
  */
-static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		   struct btrfs_path *path, int level, int slot)
+static void del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		    struct btrfs_path *path, int level, int slot)
 {
 	struct extent_buffer *parent = path->nodes[level];
 	u32 nritems;
-	int ret = 0;
-	int wret;
 
 	nritems = btrfs_header_nritems(parent);
 	if (slot != nritems - 1) {
@@ -3743,12 +3763,9 @@ static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		struct btrfs_disk_key disk_key;
 
 		btrfs_node_key(parent, &disk_key, 0);
-		wret = fixup_low_keys(trans, root, path, &disk_key, level + 1);
-		if (wret)
-			ret = wret;
+		fixup_low_keys(trans, root, path, &disk_key, level + 1);
 	}
 	btrfs_mark_buffer_dirty(parent);
-	return ret;
 }
 
 /*
@@ -3761,17 +3778,13 @@ static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
  * The path must have already been setup for deleting the leaf, including
  * all the proper balancing.  path->nodes[1] must be locked.
  */
-static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans,
-				   struct btrfs_root *root,
-				   struct btrfs_path *path,
-				   struct extent_buffer *leaf)
+static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans,
+				    struct btrfs_root *root,
+				    struct btrfs_path *path,
+				    struct extent_buffer *leaf)
 {
-	int ret;
-
 	WARN_ON(btrfs_header_generation(leaf) != trans->transid);
-	ret = del_ptr(trans, root, path, 1, path->slots[1]);
-	if (ret)
-		return ret;
+	del_ptr(trans, root, path, 1, path->slots[1]);
 
 	/*
 	 * btrfs_free_extent is expensive, we want to make sure we
@@ -3781,8 +3794,9 @@ static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans,
 
 	root_sub_used(root, leaf->len);
 
+	extent_buffer_get(leaf);
 	btrfs_free_tree_block(trans, root, leaf, 0, 1, 0);
-	return 0;
+	free_extent_buffer_stale(leaf);
 }
 /*
  * delete the item at the leaf level in path.  If that empties
@@ -3799,6 +3813,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	int wret;
 	int i;
 	u32 nritems;
+	struct btrfs_map_token token;
+
+	btrfs_init_map_token(&token);
 
 	leaf = path->nodes[0];
 	last_off = btrfs_item_offset_nr(leaf, slot + nr - 1);
@@ -3820,8 +3837,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			u32 ioff;
 
 			item = btrfs_item_nr(leaf, i);
-			ioff = btrfs_item_offset(leaf, item);
-			btrfs_set_item_offset(leaf, item, ioff + dsize);
+			ioff = btrfs_token_item_offset(leaf, item, &token);
+			btrfs_set_token_item_offset(leaf, item,
+						    ioff + dsize, &token);
 		}
 
 		memmove_extent_buffer(leaf, btrfs_item_nr_offset(slot),
@@ -3839,8 +3857,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		} else {
 			btrfs_set_path_blocking(path);
 			clean_tree_block(trans, root, leaf);
-			ret = btrfs_del_leaf(trans, root, path, leaf);
-			BUG_ON(ret);
+			btrfs_del_leaf(trans, root, path, leaf);
 		}
 	} else {
 		int used = leaf_space_used(leaf, 0, nritems);
@@ -3848,10 +3865,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			struct btrfs_disk_key disk_key;
 
 			btrfs_item_key(leaf, &disk_key, 0);
-			wret = fixup_low_keys(trans, root, path,
-					      &disk_key, 1);
-			if (wret)
-				ret = wret;
+			fixup_low_keys(trans, root, path, &disk_key, 1);
 		}
 
 		/* delete the leaf if it is mostly empty */
@@ -3879,9 +3893,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 			if (btrfs_header_nritems(leaf) == 0) {
 				path->slots[1] = slot;
-				ret = btrfs_del_leaf(trans, root, path, leaf);
-				BUG_ON(ret);
+				btrfs_del_leaf(trans, root, path, leaf);
 				free_extent_buffer(leaf);
+				ret = 0;
 			} else {
 				/* if we're still in the path, make sure
 				 * we're dirty.  Otherwise, one of the
@@ -4059,18 +4073,18 @@ find_next_key:
 		path->slots[level] = slot;
 		if (level == path->lowest_level) {
 			ret = 0;
-			unlock_up(path, level, 1);
+			unlock_up(path, level, 1, 0, NULL);
 			goto out;
 		}
 		btrfs_set_path_blocking(path);
 		cur = read_node_slot(root, cur, slot);
-		BUG_ON(!cur);
+		BUG_ON(!cur); /* -ENOMEM */
 
 		btrfs_tree_read_lock(cur);
 
 		path->locks[level - 1] = BTRFS_READ_LOCK;
 		path->nodes[level - 1] = cur;
-		unlock_up(path, level, 1);
+		unlock_up(path, level, 1, 0, NULL);
 		btrfs_clear_path_blocking(path, NULL, 0);
 	}
 out:
@@ -4306,7 +4320,7 @@ again:
 	}
 	ret = 0;
 done:
-	unlock_up(path, 0, 1);
+	unlock_up(path, 0, 1, 0, NULL);
 	path->leave_spinning = old_spinning;
 	if (!old_spinning)
 		btrfs_set_path_blocking(path);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 80b6486fd5e6..5b8ef8eb3521 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -48,6 +48,8 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_MAGIC "_BHRfS_M"
 
+#define BTRFS_MAX_MIRRORS 2
+
 #define BTRFS_MAX_LEVEL 8
 
 #define BTRFS_COMPAT_EXTENT_TREE_V0
@@ -138,6 +140,12 @@ struct btrfs_ordered_sum;
 #define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2
 
 /*
+ * the max metadata block size.  This limit is somewhat artificial,
+ * but the memmove costs go through the roof for larger blocks.
+ */
+#define BTRFS_MAX_METADATA_BLOCKSIZE 65536
+
+/*
  * we can actually store much bigger names, but lets not confuse the rest
  * of linux
  */
@@ -461,6 +469,19 @@ struct btrfs_super_block {
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
 #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)
 #define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO	(1ULL << 3)
+/*
+ * some patches floated around with a second compression method
+ * lets save that incompat here for when they do get in
+ * Note we don't actually support it, we're just reserving the
+ * number
+ */
+#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2	(1ULL << 4)
+
+/*
+ * older kernels tried to do bigger metadata blocks, but the
+ * code was pretty buggy.  Lets not let them try anymore.
+ */
+#define BTRFS_FEATURE_INCOMPAT_BIG_METADATA	(1ULL << 5)
 
 #define BTRFS_FEATURE_COMPAT_SUPP		0ULL
 #define BTRFS_FEATURE_COMPAT_RO_SUPP		0ULL
@@ -468,6 +489,7 @@ struct btrfs_super_block {
 	(BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF |		\
 	 BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL |	\
 	 BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS |		\
+	 BTRFS_FEATURE_INCOMPAT_BIG_METADATA |		\
 	 BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO)
 
 /*
@@ -829,6 +851,21 @@ struct btrfs_csum_item {
  */
 #define BTRFS_AVAIL_ALLOC_BIT_SINGLE	(1ULL << 48)
 
+#define BTRFS_EXTENDED_PROFILE_MASK	(BTRFS_BLOCK_GROUP_PROFILE_MASK | \
+					 BTRFS_AVAIL_ALLOC_BIT_SINGLE)
+
+static inline u64 chunk_to_extended(u64 flags)
+{
+	if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0)
+		flags |= BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+	return flags;
+}
+static inline u64 extended_to_chunk(u64 flags)
+{
+	return flags & ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+}
+
 struct btrfs_block_group_item {
 	__le64 used;
 	__le64 chunk_objectid;
@@ -1503,6 +1540,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_SKIP_BALANCE	(1 << 19)
 #define BTRFS_MOUNT_CHECK_INTEGRITY	(1 << 20)
 #define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
+#define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR	(1 << 22)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -1526,6 +1564,17 @@ struct btrfs_ioctl_defrag_range_args {
 
 #define BTRFS_INODE_ROOT_ITEM_INIT	(1 << 31)
 
+struct btrfs_map_token {
+	struct extent_buffer *eb;
+	char *kaddr;
+	unsigned long offset;
+};
+
+static inline void btrfs_init_map_token (struct btrfs_map_token *token)
+{
+	memset(token, 0, sizeof(*token));
+}
+
 /* some macros to generate set/get funcs for the struct fields.  This
  * assumes there is a lefoo_to_cpu for every type, so lets make a simple
  * one for u8:
@@ -1549,20 +1598,22 @@ struct btrfs_ioctl_defrag_range_args {
 #ifndef BTRFS_SETGET_FUNCS
 #define BTRFS_SETGET_FUNCS(name, type, member, bits)			\
 u##bits btrfs_##name(struct extent_buffer *eb, type *s);		\
+u##bits btrfs_token_##name(struct extent_buffer *eb, type *s, struct btrfs_map_token *token);		\
+void btrfs_set_token_##name(struct extent_buffer *eb, type *s, u##bits val, struct btrfs_map_token *token);\
 void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val);
 #endif
 
 #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits)		\
 static inline u##bits btrfs_##name(struct extent_buffer *eb)		\
 {									\
-	type *p = page_address(eb->first_page);				\
+	type *p = page_address(eb->pages[0]);				\
 	u##bits res = le##bits##_to_cpu(p->member);			\
 	return res;							\
 }									\
 static inline void btrfs_set_##name(struct extent_buffer *eb,		\
 				    u##bits val)			\
 {									\
-	type *p = page_address(eb->first_page);				\
+	type *p = page_address(eb->pages[0]);				\
 	p->member = cpu_to_le##bits(val);				\
 }
 
@@ -2466,8 +2517,7 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
 				  struct btrfs_root *root,
 				  u64 num_bytes, u64 min_alloc_size,
 				  u64 empty_size, u64 hint_byte,
-				  u64 search_end, struct btrfs_key *ins,
-				  u64 data);
+				  struct btrfs_key *ins, u64 data);
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		  struct extent_buffer *buf, int full_backref, int for_cow);
 int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
@@ -2484,8 +2534,8 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
 				       u64 start, u64 len);
-int btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root);
+void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root);
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root);
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
@@ -2548,8 +2598,8 @@ void btrfs_block_rsv_release(struct btrfs_root *root,
 			     u64 num_bytes);
 int btrfs_set_block_group_ro(struct btrfs_root *root,
 			     struct btrfs_block_group_cache *cache);
-int btrfs_set_block_group_rw(struct btrfs_root *root,
-			     struct btrfs_block_group_cache *cache);
+void btrfs_set_block_group_rw(struct btrfs_root *root,
+			      struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
 int btrfs_error_unpin_extent_range(struct btrfs_root *root,
@@ -2568,9 +2618,9 @@ int btrfs_comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2);
 int btrfs_previous_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid,
 			int type);
-int btrfs_set_item_key_safe(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root, struct btrfs_path *path,
-			    struct btrfs_key *new_key);
+void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root, struct btrfs_path *path,
+			     struct btrfs_key *new_key);
 struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
 struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
 int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
@@ -2590,12 +2640,13 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		      struct extent_buffer **cow_ret, u64 new_root_objectid);
 int btrfs_block_can_be_shared(struct btrfs_root *root,
 			      struct extent_buffer *buf);
-int btrfs_extend_item(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_path *path, u32 data_size);
-int btrfs_truncate_item(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root,
-			struct btrfs_path *path,
-			u32 new_size, int from_end);
+void btrfs_extend_item(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root, struct btrfs_path *path,
+		       u32 data_size);
+void btrfs_truncate_item(struct btrfs_trans_handle *trans,
+			 struct btrfs_root *root,
+			 struct btrfs_path *path,
+			 u32 new_size, int from_end);
 int btrfs_split_item(struct btrfs_trans_handle *trans,
 		     struct btrfs_root *root,
 		     struct btrfs_path *path,
@@ -2629,10 +2680,10 @@ static inline int btrfs_del_item(struct btrfs_trans_handle *trans,
 	return btrfs_del_items(trans, root, path, path->slots[0], 1);
 }
 
-int setup_items_for_insert(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root, struct btrfs_path *path,
-			   struct btrfs_key *cpu_key, u32 *data_size,
-			   u32 total_data, u32 total_size, int nr);
+void setup_items_for_insert(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root, struct btrfs_path *path,
+			    struct btrfs_key *cpu_key, u32 *data_size,
+			    u32 total_data, u32 total_size, int nr);
 int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_key *key, void *data, u32 data_size);
 int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
@@ -2659,9 +2710,9 @@ static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p)
 }
 int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
 int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf);
-void btrfs_drop_snapshot(struct btrfs_root *root,
-			 struct btrfs_block_rsv *block_rsv, int update_ref,
-			 int for_reloc);
+int __must_check btrfs_drop_snapshot(struct btrfs_root *root,
+				     struct btrfs_block_rsv *block_rsv,
+				     int update_ref, int for_reloc);
 int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct extent_buffer *node,
@@ -2687,24 +2738,6 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info)
 	kfree(fs_info->super_for_commit);
 	kfree(fs_info);
 }
-/**
- * profile_is_valid - tests whether a given profile is valid and reduced
- * @flags: profile to validate
- * @extended: if true @flags is treated as an extended profile
- */
-static inline int profile_is_valid(u64 flags, int extended)
-{
-	u64 mask = ~BTRFS_BLOCK_GROUP_PROFILE_MASK;
-
-	flags &= ~BTRFS_BLOCK_GROUP_TYPE_MASK;
-	if (extended)
-		mask &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-
-	if (flags & mask)
-		return 0;
-	/* true if zero or exactly one bit set */
-	return (flags & (~flags + 1)) == flags;
-}
 
 /* root-item.c */
 int btrfs_find_root_ref(struct btrfs_root *tree_root,
@@ -2723,9 +2756,10 @@ int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_key *key, struct btrfs_root_item
 		      *item);
-int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_key *key, struct btrfs_root_item
-		      *item);
+int __must_check btrfs_update_root(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root,
+				   struct btrfs_key *key,
+				   struct btrfs_root_item *item);
 int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, struct
 			 btrfs_root_item *item, struct btrfs_key *key);
 int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid);
@@ -2909,7 +2943,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root);
 void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root);
 int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
-int btrfs_invalidate_inodes(struct btrfs_root *root);
+void btrfs_invalidate_inodes(struct btrfs_root *root);
 void btrfs_add_delayed_iput(struct inode *inode);
 void btrfs_run_delayed_iputs(struct btrfs_root *root);
 int btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -2961,13 +2995,41 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 /* super.c */
 int btrfs_parse_options(struct btrfs_root *root, char *options);
 int btrfs_sync_fs(struct super_block *sb, int wait);
+void btrfs_printk(struct btrfs_fs_info *fs_info, const char *fmt, ...);
 void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
-		     unsigned int line, int errno);
+		     unsigned int line, int errno, const char *fmt, ...);
+
+void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root, const char *function,
+			       unsigned int line, int errno);
+
+#define btrfs_abort_transaction(trans, root, errno)		\
+do {								\
+	__btrfs_abort_transaction(trans, root, __func__,	\
+				  __LINE__, errno);		\
+} while (0)
 
 #define btrfs_std_error(fs_info, errno)				\
 do {								\
 	if ((errno))						\
-		__btrfs_std_error((fs_info), __func__, __LINE__, (errno));\
+		__btrfs_std_error((fs_info), __func__,		\
+				   __LINE__, (errno), NULL);	\
+} while (0)
+
+#define btrfs_error(fs_info, errno, fmt, args...)		\
+do {								\
+	__btrfs_std_error((fs_info), __func__, __LINE__,	\
+			  (errno), fmt, ##args);		\
+} while (0)
+
+void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
+		   unsigned int line, int errno, const char *fmt, ...);
+
+#define btrfs_panic(fs_info, errno, fmt, args...)			\
+do {									\
+	struct btrfs_fs_info *_i = (fs_info);				\
+	__btrfs_panic(_i, __func__, __LINE__, errno, fmt, ##args);	\
+	BUG_ON(!(_i->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR));	\
 } while (0)
 
 /* acl.c */
@@ -3003,16 +3065,17 @@ void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 void btrfs_reloc_pre_snapshot(struct btrfs_trans_handle *trans,
 			      struct btrfs_pending_snapshot *pending,
 			      u64 *bytes_to_reserve);
-void btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
+int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
 			      struct btrfs_pending_snapshot *pending);
 
 /* scrub.c */
 int btrfs_scrub_dev(struct btrfs_root *root, u64 devid, u64 start, u64 end,
 		    struct btrfs_scrub_progress *progress, int readonly);
-int btrfs_scrub_pause(struct btrfs_root *root);
-int btrfs_scrub_pause_super(struct btrfs_root *root);
-int btrfs_scrub_continue(struct btrfs_root *root);
-int btrfs_scrub_continue_super(struct btrfs_root *root);
+void btrfs_scrub_pause(struct btrfs_root *root);
+void btrfs_scrub_pause_super(struct btrfs_root *root);
+void btrfs_scrub_continue(struct btrfs_root *root);
+void btrfs_scrub_continue_super(struct btrfs_root *root);
+int __btrfs_scrub_cancel(struct btrfs_fs_info *info);
 int btrfs_scrub_cancel(struct btrfs_root *root);
 int btrfs_scrub_cancel_dev(struct btrfs_root *root, struct btrfs_device *dev);
 int btrfs_scrub_cancel_devid(struct btrfs_root *root, u64 devid);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index fe4cd0f1cef1..03e3748d84d0 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -115,6 +115,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode)
 	return NULL;
 }
 
+/* Will return either the node or PTR_ERR(-ENOMEM) */
 static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node(
 							struct inode *inode)
 {
@@ -836,10 +837,8 @@ static int btrfs_batch_insert_items(struct btrfs_trans_handle *trans,
 	btrfs_clear_path_blocking(path, NULL, 0);
 
 	/* insert the keys of the items */
-	ret = setup_items_for_insert(trans, root, path, keys, data_size,
-				     total_data_size, total_size, nitems);
-	if (ret)
-		goto error;
+	setup_items_for_insert(trans, root, path, keys, data_size,
+			       total_data_size, total_size, nitems);
 
 	/* insert the dir index items */
 	slot = path->slots[0];
@@ -1108,16 +1107,25 @@ static int btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-/* Called when committing the transaction. */
+/*
+ * Called when committing the transaction.
+ * Returns 0 on success.
+ * Returns < 0 on error and returns with an aborted transaction with any
+ * outstanding delayed items cleaned up.
+ */
 int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root)
 {
+	struct btrfs_root *curr_root = root;
 	struct btrfs_delayed_root *delayed_root;
 	struct btrfs_delayed_node *curr_node, *prev_node;
 	struct btrfs_path *path;
 	struct btrfs_block_rsv *block_rsv;
 	int ret = 0;
 
+	if (trans->aborted)
+		return -EIO;
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -1130,17 +1138,18 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
 
 	curr_node = btrfs_first_delayed_node(delayed_root);
 	while (curr_node) {
-		root = curr_node->root;
-		ret = btrfs_insert_delayed_items(trans, path, root,
+		curr_root = curr_node->root;
+		ret = btrfs_insert_delayed_items(trans, path, curr_root,
 						 curr_node);
 		if (!ret)
-			ret = btrfs_delete_delayed_items(trans, path, root,
-							 curr_node);
+			ret = btrfs_delete_delayed_items(trans, path,
+						curr_root, curr_node);
 		if (!ret)
-			ret = btrfs_update_delayed_inode(trans, root, path,
-							 curr_node);
+			ret = btrfs_update_delayed_inode(trans, curr_root,
+						path, curr_node);
 		if (ret) {
 			btrfs_release_delayed_node(curr_node);
+			btrfs_abort_transaction(trans, root, ret);
 			break;
 		}
 
@@ -1151,6 +1160,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
 
 	btrfs_free_path(path);
 	trans->block_rsv = block_rsv;
+
 	return ret;
 }
 
@@ -1371,6 +1381,7 @@ void btrfs_balance_delayed_items(struct btrfs_root *root)
 	btrfs_wq_run_delayed_node(delayed_root, root, 0);
 }
 
+/* Will return 0 or -ENOMEM */
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root, const char *name,
 				   int name_len, struct inode *dir,
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 66e4f29505a3..69f22e3ab3bc 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -420,7 +420,7 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
  * this does all the dirty work in terms of maintaining the correct
  * overall modification count.
  */
-static noinline int add_delayed_ref_head(struct btrfs_fs_info *fs_info,
+static noinline void add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 					struct btrfs_trans_handle *trans,
 					struct btrfs_delayed_ref_node *ref,
 					u64 bytenr, u64 num_bytes,
@@ -487,20 +487,19 @@ static noinline int add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		 * we've updated the existing ref, free the newly
 		 * allocated ref
 		 */
-		kfree(ref);
+		kfree(head_ref);
 	} else {
 		delayed_refs->num_heads++;
 		delayed_refs->num_heads_ready++;
 		delayed_refs->num_entries++;
 		trans->delayed_ref_updates++;
 	}
-	return 0;
 }
 
 /*
  * helper to insert a delayed tree ref into the rbtree.
  */
-static noinline int add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
+static noinline void add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 					 struct btrfs_trans_handle *trans,
 					 struct btrfs_delayed_ref_node *ref,
 					 u64 bytenr, u64 num_bytes, u64 parent,
@@ -549,18 +548,17 @@ static noinline int add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 		 * we've updated the existing ref, free the newly
 		 * allocated ref
 		 */
-		kfree(ref);
+		kfree(full_ref);
 	} else {
 		delayed_refs->num_entries++;
 		trans->delayed_ref_updates++;
 	}
-	return 0;
 }
 
 /*
  * helper to insert a delayed data ref into the rbtree.
  */
-static noinline int add_delayed_data_ref(struct btrfs_fs_info *fs_info,
+static noinline void add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 					 struct btrfs_trans_handle *trans,
 					 struct btrfs_delayed_ref_node *ref,
 					 u64 bytenr, u64 num_bytes, u64 parent,
@@ -611,12 +609,11 @@ static noinline int add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 		 * we've updated the existing ref, free the newly
 		 * allocated ref
 		 */
-		kfree(ref);
+		kfree(full_ref);
 	} else {
 		delayed_refs->num_entries++;
 		trans->delayed_ref_updates++;
 	}
-	return 0;
 }
 
 /*
@@ -634,7 +631,6 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	struct btrfs_delayed_tree_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
-	int ret;
 
 	BUG_ON(extent_op && extent_op->is_data);
 	ref = kmalloc(sizeof(*ref), GFP_NOFS);
@@ -656,14 +652,12 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	 * insert both the head node and the new ref without dropping
 	 * the spin lock
 	 */
-	ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
+	add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
 				   num_bytes, action, 0);
-	BUG_ON(ret);
 
-	ret = add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr,
+	add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr,
 				   num_bytes, parent, ref_root, level, action,
 				   for_cow);
-	BUG_ON(ret);
 	if (!need_ref_seq(for_cow, ref_root) &&
 	    waitqueue_active(&delayed_refs->seq_wait))
 		wake_up(&delayed_refs->seq_wait);
@@ -685,7 +679,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	struct btrfs_delayed_data_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
-	int ret;
 
 	BUG_ON(extent_op && !extent_op->is_data);
 	ref = kmalloc(sizeof(*ref), GFP_NOFS);
@@ -707,14 +700,12 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	 * insert both the head node and the new ref without dropping
 	 * the spin lock
 	 */
-	ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
+	add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
 				   num_bytes, action, 1);
-	BUG_ON(ret);
 
-	ret = add_delayed_data_ref(fs_info, trans, &ref->node, bytenr,
+	add_delayed_data_ref(fs_info, trans, &ref->node, bytenr,
 				   num_bytes, parent, ref_root, owner, offset,
 				   action, for_cow);
-	BUG_ON(ret);
 	if (!need_ref_seq(for_cow, ref_root) &&
 	    waitqueue_active(&delayed_refs->seq_wait))
 		wake_up(&delayed_refs->seq_wait);
@@ -729,7 +720,6 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
-	int ret;
 
 	head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
 	if (!head_ref)
@@ -740,10 +730,9 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
 	delayed_refs = &trans->transaction->delayed_refs;
 	spin_lock(&delayed_refs->lock);
 
-	ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
+	add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
 				   num_bytes, BTRFS_UPDATE_DELAYED_HEAD,
 				   extent_op->is_data);
-	BUG_ON(ret);
 
 	if (waitqueue_active(&delayed_refs->seq_wait))
 		wake_up(&delayed_refs->seq_wait);
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 31d84e78129b..c1a074d0696f 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -49,9 +49,8 @@ static struct btrfs_dir_item *insert_with_overflow(struct btrfs_trans_handle
 		di = btrfs_match_dir_item_name(root, path, name, name_len);
 		if (di)
 			return ERR_PTR(-EEXIST);
-		ret = btrfs_extend_item(trans, root, path, data_size);
-	}
-	if (ret < 0)
+		btrfs_extend_item(trans, root, path, data_size);
+	} else if (ret < 0)
 		return ERR_PTR(ret);
 	WARN_ON(ret > 0);
 	leaf = path->nodes[0];
@@ -116,6 +115,7 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
  * 'location' is the key to stuff into the directory item, 'type' is the
  * type of the inode we're pointing to, and 'index' is the sequence number
  * to use for the second index (if one is created).
+ * Will return 0 or -ENOMEM
  */
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 			  *root, const char *name, int name_len,
@@ -383,8 +383,8 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans,
 		start = btrfs_item_ptr_offset(leaf, path->slots[0]);
 		memmove_extent_buffer(leaf, ptr, ptr + sub_item_len,
 			item_len - (ptr + sub_item_len - start));
-		ret = btrfs_truncate_item(trans, root, path,
-					  item_len - sub_item_len, 1);
+		btrfs_truncate_item(trans, root, path,
+				    item_len - sub_item_len, 1);
 	}
 	return ret;
 }
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 534266fe505f..20196f411206 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -48,20 +48,19 @@
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
-static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
+static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 				    int read_only);
-static int btrfs_destroy_ordered_operations(struct btrfs_root *root);
-static int btrfs_destroy_ordered_extents(struct btrfs_root *root);
+static void btrfs_destroy_ordered_operations(struct btrfs_root *root);
+static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_root *root);
-static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t);
-static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
+static void btrfs_destroy_pending_snapshots(struct btrfs_transaction *t);
+static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
 static int btrfs_destroy_marked_extents(struct btrfs_root *root,
 					struct extent_io_tree *dirty_pages,
 					int mark);
 static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
 				       struct extent_io_tree *pinned_extents);
-static int btrfs_cleanup_transaction(struct btrfs_root *root);
 
 /*
  * end_io_wq structs are used to do processing in task context when an IO is
@@ -99,6 +98,7 @@ struct async_submit_bio {
 	 */
 	u64 bio_offset;
 	struct btrfs_work work;
+	int error;
 };
 
 /*
@@ -332,8 +332,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 		return 0;
 
 	lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
-			 0, &cached_state, GFP_NOFS);
-	if (extent_buffer_uptodate(io_tree, eb, cached_state) &&
+			 0, &cached_state);
+	if (extent_buffer_uptodate(eb) &&
 	    btrfs_header_generation(eb) == parent_transid) {
 		ret = 0;
 		goto out;
@@ -344,7 +344,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 		       (unsigned long long)parent_transid,
 		       (unsigned long long)btrfs_header_generation(eb));
 	ret = 1;
-	clear_extent_buffer_uptodate(io_tree, eb, &cached_state);
+	clear_extent_buffer_uptodate(eb);
 out:
 	unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
 			     &cached_state, GFP_NOFS);
@@ -360,9 +360,11 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 					  u64 start, u64 parent_transid)
 {
 	struct extent_io_tree *io_tree;
+	int failed = 0;
 	int ret;
 	int num_copies = 0;
 	int mirror_num = 0;
+	int failed_mirror = 0;
 
 	clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 	io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
@@ -370,9 +372,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 		ret = read_extent_buffer_pages(io_tree, eb, start,
 					       WAIT_COMPLETE,
 					       btree_get_extent, mirror_num);
-		if (!ret &&
-		    !verify_parent_transid(io_tree, eb, parent_transid))
-			return ret;
+		if (!ret && !verify_parent_transid(io_tree, eb, parent_transid))
+			break;
 
 		/*
 		 * This buffer's crc is fine, but its contents are corrupted, so
@@ -380,18 +381,31 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 		 * any less wrong.
 		 */
 		if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
-			return ret;
+			break;
+
+		if (!failed_mirror) {
+			failed = 1;
+			printk(KERN_ERR "failed mirror was %d\n", eb->failed_mirror);
+			failed_mirror = eb->failed_mirror;
+		}
 
 		num_copies = btrfs_num_copies(&root->fs_info->mapping_tree,
 					      eb->start, eb->len);
 		if (num_copies == 1)
-			return ret;
+			break;
 
 		mirror_num++;
+		if (mirror_num == failed_mirror)
+			mirror_num++;
+
 		if (mirror_num > num_copies)
-			return ret;
+			break;
 	}
-	return -EIO;
+
+	if (failed && !ret)
+		repair_eb_io_failure(root, eb, failed_mirror);
+
+	return ret;
 }
 
 /*
@@ -404,50 +418,27 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
 	struct extent_io_tree *tree;
 	u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
 	u64 found_start;
-	unsigned long len;
 	struct extent_buffer *eb;
-	int ret;
 
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
 
-	if (page->private == EXTENT_PAGE_PRIVATE) {
-		WARN_ON(1);
-		goto out;
-	}
-	if (!page->private) {
-		WARN_ON(1);
-		goto out;
-	}
-	len = page->private >> 2;
-	WARN_ON(len == 0);
-
-	eb = alloc_extent_buffer(tree, start, len, page);
-	if (eb == NULL) {
-		WARN_ON(1);
-		goto out;
-	}
-	ret = btree_read_extent_buffer_pages(root, eb, start + PAGE_CACHE_SIZE,
-					     btrfs_header_generation(eb));
-	BUG_ON(ret);
-	WARN_ON(!btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN));
-
+	eb = (struct extent_buffer *)page->private;
+	if (page != eb->pages[0])
+		return 0;
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != start) {
 		WARN_ON(1);
-		goto err;
+		return 0;
 	}
-	if (eb->first_page != page) {
+	if (eb->pages[0] != page) {
 		WARN_ON(1);
-		goto err;
+		return 0;
 	}
 	if (!PageUptodate(page)) {
 		WARN_ON(1);
-		goto err;
+		return 0;
 	}
 	csum_tree_block(root, eb, 0);
-err:
-	free_extent_buffer(eb);
-out:
 	return 0;
 }
 
@@ -537,34 +528,74 @@ static noinline int check_leaf(struct btrfs_root *root,
 	return 0;
 }
 
+struct extent_buffer *find_eb_for_page(struct extent_io_tree *tree,
+				       struct page *page, int max_walk)
+{
+	struct extent_buffer *eb;
+	u64 start = page_offset(page);
+	u64 target = start;
+	u64 min_start;
+
+	if (start < max_walk)
+		min_start = 0;
+	else
+		min_start = start - max_walk;
+
+	while (start >= min_start) {
+		eb = find_extent_buffer(tree, start, 0);
+		if (eb) {
+			/*
+			 * we found an extent buffer and it contains our page
+			 * horray!
+			 */
+			if (eb->start <= target &&
+			    eb->start + eb->len > target)
+				return eb;
+
+			/* we found an extent buffer that wasn't for us */
+			free_extent_buffer(eb);
+			return NULL;
+		}
+		if (start == 0)
+			break;
+		start -= PAGE_CACHE_SIZE;
+	}
+	return NULL;
+}
+
 static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 			       struct extent_state *state)
 {
 	struct extent_io_tree *tree;
 	u64 found_start;
 	int found_level;
-	unsigned long len;
 	struct extent_buffer *eb;
 	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
 	int ret = 0;
+	int reads_done;
 
-	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	if (page->private == EXTENT_PAGE_PRIVATE)
-		goto out;
 	if (!page->private)
 		goto out;
 
-	len = page->private >> 2;
-	WARN_ON(len == 0);
+	tree = &BTRFS_I(page->mapping->host)->io_tree;
+	eb = (struct extent_buffer *)page->private;
 
-	eb = alloc_extent_buffer(tree, start, len, page);
-	if (eb == NULL) {
+	/* the pending IO might have been the only thing that kept this buffer
+	 * in memory.  Make sure we have a ref for all this other checks
+	 */
+	extent_buffer_get(eb);
+
+	reads_done = atomic_dec_and_test(&eb->io_pages);
+	if (!reads_done)
+		goto err;
+
+	if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
 		ret = -EIO;
-		goto out;
+		goto err;
 	}
 
 	found_start = btrfs_header_bytenr(eb);
-	if (found_start != start) {
+	if (found_start != eb->start) {
 		printk_ratelimited(KERN_INFO "btrfs bad tree block start "
 			       "%llu %llu\n",
 			       (unsigned long long)found_start,
@@ -572,13 +603,6 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 		ret = -EIO;
 		goto err;
 	}
-	if (eb->first_page != page) {
-		printk(KERN_INFO "btrfs bad first page %lu %lu\n",
-		       eb->first_page->index, page->index);
-		WARN_ON(1);
-		ret = -EIO;
-		goto err;
-	}
 	if (check_tree_block_fsid(root, eb)) {
 		printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n",
 			       (unsigned long long)eb->start);
@@ -606,48 +630,31 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 		ret = -EIO;
 	}
 
-	end = min_t(u64, eb->len, PAGE_CACHE_SIZE);
-	end = eb->start + end - 1;
+	if (!ret)
+		set_extent_buffer_uptodate(eb);
 err:
 	if (test_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) {
 		clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags);
 		btree_readahead_hook(root, eb, eb->start, ret);
 	}
 
+	if (ret)
+		clear_extent_buffer_uptodate(eb);
 	free_extent_buffer(eb);
 out:
 	return ret;
 }
 
-static int btree_io_failed_hook(struct bio *failed_bio,
-			 struct page *page, u64 start, u64 end,
-			 int mirror_num, struct extent_state *state)
+static int btree_io_failed_hook(struct page *page, int failed_mirror)
 {
-	struct extent_io_tree *tree;
-	unsigned long len;
 	struct extent_buffer *eb;
 	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
 
-	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	if (page->private == EXTENT_PAGE_PRIVATE)
-		goto out;
-	if (!page->private)
-		goto out;
-
-	len = page->private >> 2;
-	WARN_ON(len == 0);
-
-	eb = alloc_extent_buffer(tree, start, len, page);
-	if (eb == NULL)
-		goto out;
-
-	if (test_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) {
-		clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags);
+	eb = (struct extent_buffer *)page->private;
+	set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+	eb->failed_mirror = failed_mirror;
+	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
 		btree_readahead_hook(root, eb, eb->start, -EIO);
-	}
-	free_extent_buffer(eb);
-
-out:
 	return -EIO;	/* we fixed nothing */
 }
 
@@ -719,11 +726,14 @@ unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
 static void run_one_async_start(struct btrfs_work *work)
 {
 	struct async_submit_bio *async;
+	int ret;
 
 	async = container_of(work, struct  async_submit_bio, work);
-	async->submit_bio_start(async->inode, async->rw, async->bio,
-			       async->mirror_num, async->bio_flags,
-			       async->bio_offset);
+	ret = async->submit_bio_start(async->inode, async->rw, async->bio,
+				      async->mirror_num, async->bio_flags,
+				      async->bio_offset);
+	if (ret)
+		async->error = ret;
 }
 
 static void run_one_async_done(struct btrfs_work *work)
@@ -744,6 +754,12 @@ static void run_one_async_done(struct btrfs_work *work)
 	    waitqueue_active(&fs_info->async_submit_wait))
 		wake_up(&fs_info->async_submit_wait);
 
+	/* If an error occured we just want to clean up the bio and move on */
+	if (async->error) {
+		bio_endio(async->bio, async->error);
+		return;
+	}
+
 	async->submit_bio_done(async->inode, async->rw, async->bio,
 			       async->mirror_num, async->bio_flags,
 			       async->bio_offset);
@@ -785,6 +801,8 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 	async->bio_flags = bio_flags;
 	async->bio_offset = bio_offset;
 
+	async->error = 0;
+
 	atomic_inc(&fs_info->nr_async_submits);
 
 	if (rw & REQ_SYNC)
@@ -806,15 +824,18 @@ static int btree_csum_one_bio(struct bio *bio)
 	struct bio_vec *bvec = bio->bi_io_vec;
 	int bio_index = 0;
 	struct btrfs_root *root;
+	int ret = 0;
 
 	WARN_ON(bio->bi_vcnt <= 0);
 	while (bio_index < bio->bi_vcnt) {
 		root = BTRFS_I(bvec->bv_page->mapping->host)->root;
-		csum_dirty_buffer(root, bvec->bv_page);
+		ret = csum_dirty_buffer(root, bvec->bv_page);
+		if (ret)
+			break;
 		bio_index++;
 		bvec++;
 	}
-	return 0;
+	return ret;
 }
 
 static int __btree_submit_bio_start(struct inode *inode, int rw,
@@ -826,8 +847,7 @@ static int __btree_submit_bio_start(struct inode *inode, int rw,
 	 * when we're called for a write, we're already in the async
 	 * submission context.  Just jump into btrfs_map_bio
 	 */
-	btree_csum_one_bio(bio);
-	return 0;
+	return btree_csum_one_bio(bio);
 }
 
 static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
@@ -847,15 +867,16 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 {
 	int ret;
 
-	ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info,
-					  bio, 1);
-	BUG_ON(ret);
-
 	if (!(rw & REQ_WRITE)) {
+
 		/*
 		 * called for a read, do the setup so that checksum validation
 		 * can happen in the async kernel threads
 		 */
+		ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info,
+					  bio, 1);
+		if (ret)
+			return ret;
 		return btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
 				     mirror_num, 0);
 	}
@@ -893,34 +914,6 @@ static int btree_migratepage(struct address_space *mapping,
 }
 #endif
 
-static int btree_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct extent_io_tree *tree;
-	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
-	struct extent_buffer *eb;
-	int was_dirty;
-
-	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	if (!(current->flags & PF_MEMALLOC)) {
-		return extent_write_full_page(tree, page,
-					      btree_get_extent, wbc);
-	}
-
-	redirty_page_for_writepage(wbc, page);
-	eb = btrfs_find_tree_block(root, page_offset(page), PAGE_CACHE_SIZE);
-	WARN_ON(!eb);
-
-	was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
-	if (!was_dirty) {
-		spin_lock(&root->fs_info->delalloc_lock);
-		root->fs_info->dirty_metadata_bytes += PAGE_CACHE_SIZE;
-		spin_unlock(&root->fs_info->delalloc_lock);
-	}
-	free_extent_buffer(eb);
-
-	unlock_page(page);
-	return 0;
-}
 
 static int btree_writepages(struct address_space *mapping,
 			    struct writeback_control *wbc)
@@ -940,7 +933,7 @@ static int btree_writepages(struct address_space *mapping,
 		if (num_dirty < thresh)
 			return 0;
 	}
-	return extent_writepages(tree, mapping, btree_get_extent, wbc);
+	return btree_write_cache_pages(mapping, wbc);
 }
 
 static int btree_readpage(struct file *file, struct page *page)
@@ -952,16 +945,8 @@ static int btree_readpage(struct file *file, struct page *page)
 
 static int btree_releasepage(struct page *page, gfp_t gfp_flags)
 {
-	struct extent_io_tree *tree;
-	struct extent_map_tree *map;
-	int ret;
-
 	if (PageWriteback(page) || PageDirty(page))
 		return 0;
-
-	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	map = &BTRFS_I(page->mapping->host)->extent_tree;
-
 	/*
 	 * We need to mask out eg. __GFP_HIGHMEM and __GFP_DMA32 as we're doing
 	 * slab allocation from alloc_extent_state down the callchain where
@@ -969,18 +954,7 @@ static int btree_releasepage(struct page *page, gfp_t gfp_flags)
 	 */
 	gfp_flags &= ~GFP_SLAB_BUG_MASK;
 
-	ret = try_release_extent_state(map, tree, page, gfp_flags);
-	if (!ret)
-		return 0;
-
-	ret = try_release_extent_buffer(tree, page);
-	if (ret == 1) {
-		ClearPagePrivate(page);
-		set_page_private(page, 0);
-		page_cache_release(page);
-	}
-
-	return ret;
+	return try_release_extent_buffer(page, gfp_flags);
 }
 
 static void btree_invalidatepage(struct page *page, unsigned long offset)
@@ -998,15 +972,28 @@ static void btree_invalidatepage(struct page *page, unsigned long offset)
 	}
 }
 
+static int btree_set_page_dirty(struct page *page)
+{
+	struct extent_buffer *eb;
+
+	BUG_ON(!PagePrivate(page));
+	eb = (struct extent_buffer *)page->private;
+	BUG_ON(!eb);
+	BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+	BUG_ON(!atomic_read(&eb->refs));
+	btrfs_assert_tree_locked(eb);
+	return __set_page_dirty_nobuffers(page);
+}
+
 static const struct address_space_operations btree_aops = {
 	.readpage	= btree_readpage,
-	.writepage	= btree_writepage,
 	.writepages	= btree_writepages,
 	.releasepage	= btree_releasepage,
 	.invalidatepage = btree_invalidatepage,
 #ifdef CONFIG_MIGRATION
 	.migratepage	= btree_migratepage,
 #endif
+	.set_page_dirty = btree_set_page_dirty,
 };
 
 int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
@@ -1049,7 +1036,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 	if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) {
 		free_extent_buffer(buf);
 		return -EIO;
-	} else if (extent_buffer_uptodate(io_tree, buf, NULL)) {
+	} else if (extent_buffer_uptodate(buf)) {
 		*eb = buf;
 	} else {
 		free_extent_buffer(buf);
@@ -1074,20 +1061,20 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 	struct extent_buffer *eb;
 
 	eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
-				 bytenr, blocksize, NULL);
+				 bytenr, blocksize);
 	return eb;
 }
 
 
 int btrfs_write_tree_block(struct extent_buffer *buf)
 {
-	return filemap_fdatawrite_range(buf->first_page->mapping, buf->start,
+	return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
 					buf->start + buf->len - 1);
 }
 
 int btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
 {
-	return filemap_fdatawait_range(buf->first_page->mapping,
+	return filemap_fdatawait_range(buf->pages[0]->mapping,
 				       buf->start, buf->start + buf->len - 1);
 }
 
@@ -1102,17 +1089,13 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 		return NULL;
 
 	ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
-
-	if (ret == 0)
-		set_bit(EXTENT_BUFFER_UPTODATE, &buf->bflags);
 	return buf;
 
 }
 
-int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		     struct extent_buffer *buf)
+void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      struct extent_buffer *buf)
 {
-	struct inode *btree_inode = root->fs_info->btree_inode;
 	if (btrfs_header_generation(buf) ==
 	    root->fs_info->running_transaction->transid) {
 		btrfs_assert_tree_locked(buf);
@@ -1121,23 +1104,27 @@ int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			spin_lock(&root->fs_info->delalloc_lock);
 			if (root->fs_info->dirty_metadata_bytes >= buf->len)
 				root->fs_info->dirty_metadata_bytes -= buf->len;
-			else
-				WARN_ON(1);
+			else {
+				spin_unlock(&root->fs_info->delalloc_lock);
+				btrfs_panic(root->fs_info, -EOVERFLOW,
+					  "Can't clear %lu bytes from "
+					  " dirty_mdatadata_bytes (%lu)",
+					  buf->len,
+					  root->fs_info->dirty_metadata_bytes);
+			}
 			spin_unlock(&root->fs_info->delalloc_lock);
 		}
 
 		/* ugh, clear_extent_buffer_dirty needs to lock the page */
 		btrfs_set_lock_blocking(buf);
-		clear_extent_buffer_dirty(&BTRFS_I(btree_inode)->io_tree,
-					  buf);
+		clear_extent_buffer_dirty(buf);
 	}
-	return 0;
 }
 
-static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
-			u32 stripesize, struct btrfs_root *root,
-			struct btrfs_fs_info *fs_info,
-			u64 objectid)
+static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
+			 u32 stripesize, struct btrfs_root *root,
+			 struct btrfs_fs_info *fs_info,
+			 u64 objectid)
 {
 	root->node = NULL;
 	root->commit_root = NULL;
@@ -1189,13 +1176,12 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->defrag_running = 0;
 	root->root_key.objectid = objectid;
 	root->anon_dev = 0;
-	return 0;
 }
 
-static int find_and_setup_root(struct btrfs_root *tree_root,
-			       struct btrfs_fs_info *fs_info,
-			       u64 objectid,
-			       struct btrfs_root *root)
+static int __must_check find_and_setup_root(struct btrfs_root *tree_root,
+					    struct btrfs_fs_info *fs_info,
+					    u64 objectid,
+					    struct btrfs_root *root)
 {
 	int ret;
 	u32 blocksize;
@@ -1208,7 +1194,8 @@ static int find_and_setup_root(struct btrfs_root *tree_root,
 				   &root->root_item, &root->root_key);
 	if (ret > 0)
 		return -ENOENT;
-	BUG_ON(ret);
+	else if (ret < 0)
+		return ret;
 
 	generation = btrfs_root_generation(&root->root_item);
 	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
@@ -1377,7 +1364,7 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
 	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
 				     blocksize, generation);
 	root->commit_root = btrfs_root_node(root);
-	BUG_ON(!root->node);
+	BUG_ON(!root->node); /* -ENOMEM */
 out:
 	if (location->objectid != BTRFS_TREE_LOG_OBJECTID) {
 		root->ref_cows = 1;
@@ -1513,41 +1500,6 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 	return 0;
 }
 
-static int bio_ready_for_csum(struct bio *bio)
-{
-	u64 length = 0;
-	u64 buf_len = 0;
-	u64 start = 0;
-	struct page *page;
-	struct extent_io_tree *io_tree = NULL;
-	struct bio_vec *bvec;
-	int i;
-	int ret;
-
-	bio_for_each_segment(bvec, bio, i) {
-		page = bvec->bv_page;
-		if (page->private == EXTENT_PAGE_PRIVATE) {
-			length += bvec->bv_len;
-			continue;
-		}
-		if (!page->private) {
-			length += bvec->bv_len;
-			continue;
-		}
-		length = bvec->bv_len;
-		buf_len = page->private >> 2;
-		start = page_offset(page) + bvec->bv_offset;
-		io_tree = &BTRFS_I(page->mapping->host)->io_tree;
-	}
-	/* are we fully contained in this bio? */
-	if (buf_len <= length)
-		return 1;
-
-	ret = extent_range_uptodate(io_tree, start + length,
-				    start + buf_len - 1);
-	return ret;
-}
-
 /*
  * called by the kthread helper functions to finally call the bio end_io
  * functions.  This is where read checksum verification actually happens
@@ -1563,17 +1515,6 @@ static void end_workqueue_fn(struct btrfs_work *work)
 	bio = end_io_wq->bio;
 	fs_info = end_io_wq->info;
 
-	/* metadata bio reads are special because the whole tree block must
-	 * be checksummed at once.  This makes sure the entire block is in
-	 * ram and up to date before trying to verify things.  For
-	 * blocksize <= pagesize, it is basically a noop
-	 */
-	if (!(bio->bi_rw & REQ_WRITE) && end_io_wq->metadata &&
-	    !bio_ready_for_csum(bio)) {
-		btrfs_queue_worker(&fs_info->endio_meta_workers,
-				   &end_io_wq->work);
-		return;
-	}
 	error = end_io_wq->error;
 	bio->bi_private = end_io_wq->private;
 	bio->bi_end_io = end_io_wq->end_io;
@@ -1614,9 +1555,10 @@ static int transaction_kthread(void *arg)
 	u64 transid;
 	unsigned long now;
 	unsigned long delay;
-	int ret;
+	bool cannot_commit;
 
 	do {
+		cannot_commit = false;
 		delay = HZ * 30;
 		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
 		mutex_lock(&root->fs_info->transaction_kthread_mutex);
@@ -1638,11 +1580,14 @@ static int transaction_kthread(void *arg)
 		transid = cur->transid;
 		spin_unlock(&root->fs_info->trans_lock);
 
+		/* If the file system is aborted, this will always fail. */
 		trans = btrfs_join_transaction(root);
-		BUG_ON(IS_ERR(trans));
+		if (IS_ERR(trans)) {
+			cannot_commit = true;
+			goto sleep;
+		}
 		if (transid == trans->transid) {
-			ret = btrfs_commit_transaction(trans, root);
-			BUG_ON(ret);
+			btrfs_commit_transaction(trans, root);
 		} else {
 			btrfs_end_transaction(trans, root);
 		}
@@ -1653,7 +1598,8 @@ sleep:
 		if (!try_to_freeze()) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			if (!kthread_should_stop() &&
-			    !btrfs_transaction_blocked(root->fs_info))
+			    (!btrfs_transaction_blocked(root->fs_info) ||
+			     cannot_commit))
 				schedule_timeout(delay);
 			__set_current_state(TASK_RUNNING);
 		}
@@ -2042,6 +1988,7 @@ int open_ctree(struct super_block *sb,
 	RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
 	extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
 			     fs_info->btree_inode->i_mapping);
+	BTRFS_I(fs_info->btree_inode)->io_tree.track_uptodate = 0;
 	extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree);
 
 	BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops;
@@ -2084,6 +2031,7 @@ int open_ctree(struct super_block *sb,
 	__setup_root(4096, 4096, 4096, 4096, tree_root,
 		     fs_info, BTRFS_ROOT_TREE_OBJECTID);
 
+	invalidate_bdev(fs_devices->latest_bdev);
 	bh = btrfs_read_dev_super(fs_devices->latest_bdev);
 	if (!bh) {
 		err = -EINVAL;
@@ -2104,7 +2052,12 @@ int open_ctree(struct super_block *sb,
 	/* check FS state, whether FS is broken. */
 	fs_info->fs_state |= btrfs_super_flags(disk_super);
 
-	btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
+	ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
+	if (ret) {
+		printk(KERN_ERR "btrfs: superblock contains fatal errors\n");
+		err = ret;
+		goto fail_alloc;
+	}
 
 	/*
 	 * run through our array of backup supers and setup
@@ -2135,10 +2088,55 @@ int open_ctree(struct super_block *sb,
 		goto fail_alloc;
 	}
 
+	if (btrfs_super_leafsize(disk_super) !=
+	    btrfs_super_nodesize(disk_super)) {
+		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
+		       "blocksizes don't match.  node %d leaf %d\n",
+		       btrfs_super_nodesize(disk_super),
+		       btrfs_super_leafsize(disk_super));
+		err = -EINVAL;
+		goto fail_alloc;
+	}
+	if (btrfs_super_leafsize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
+		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
+		       "blocksize (%d) was too large\n",
+		       btrfs_super_leafsize(disk_super));
+		err = -EINVAL;
+		goto fail_alloc;
+	}
+
 	features = btrfs_super_incompat_flags(disk_super);
 	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
 	if (tree_root->fs_info->compress_type & BTRFS_COMPRESS_LZO)
 		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+
+	/*
+	 * flag our filesystem as having big metadata blocks if
+	 * they are bigger than the page size
+	 */
+	if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) {
+		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
+			printk(KERN_INFO "btrfs flagging fs with big metadata feature\n");
+		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
+	}
+
+	nodesize = btrfs_super_nodesize(disk_super);
+	leafsize = btrfs_super_leafsize(disk_super);
+	sectorsize = btrfs_super_sectorsize(disk_super);
+	stripesize = btrfs_super_stripesize(disk_super);
+
+	/*
+	 * mixed block groups end up with duplicate but slightly offset
+	 * extent buffers for the same range.  It leads to corruptions
+	 */
+	if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
+	    (sectorsize != leafsize)) {
+		printk(KERN_WARNING "btrfs: unequal leaf/node/sector sizes "
+				"are not allowed for mixed block groups on %s\n",
+				sb->s_id);
+		goto fail_alloc;
+	}
+
 	btrfs_set_super_incompat_flags(disk_super, features);
 
 	features = btrfs_super_compat_ro_flags(disk_super) &
@@ -2242,10 +2240,6 @@ int open_ctree(struct super_block *sb,
 	fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
 				    4 * 1024 * 1024 / PAGE_CACHE_SIZE);
 
-	nodesize = btrfs_super_nodesize(disk_super);
-	leafsize = btrfs_super_leafsize(disk_super);
-	sectorsize = btrfs_super_sectorsize(disk_super);
-	stripesize = btrfs_super_stripesize(disk_super);
 	tree_root->nodesize = nodesize;
 	tree_root->leafsize = leafsize;
 	tree_root->sectorsize = sectorsize;
@@ -2285,7 +2279,7 @@ int open_ctree(struct super_block *sb,
 	chunk_root->node = read_tree_block(chunk_root,
 					   btrfs_super_chunk_root(disk_super),
 					   blocksize, generation);
-	BUG_ON(!chunk_root->node);
+	BUG_ON(!chunk_root->node); /* -ENOMEM */
 	if (!test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
 		printk(KERN_WARNING "btrfs: failed to read chunk root on %s\n",
 		       sb->s_id);
@@ -2425,21 +2419,31 @@ retry_root_backup:
 		log_tree_root->node = read_tree_block(tree_root, bytenr,
 						      blocksize,
 						      generation + 1);
+		/* returns with log_tree_root freed on success */
 		ret = btrfs_recover_log_trees(log_tree_root);
-		BUG_ON(ret);
+		if (ret) {
+			btrfs_error(tree_root->fs_info, ret,
+				    "Failed to recover log tree");
+			free_extent_buffer(log_tree_root->node);
+			kfree(log_tree_root);
+			goto fail_trans_kthread;
+		}
 
 		if (sb->s_flags & MS_RDONLY) {
-			ret =  btrfs_commit_super(tree_root);
-			BUG_ON(ret);
+			ret = btrfs_commit_super(tree_root);
+			if (ret)
+				goto fail_trans_kthread;
 		}
 	}
 
 	ret = btrfs_find_orphan_roots(tree_root);
-	BUG_ON(ret);
+	if (ret)
+		goto fail_trans_kthread;
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		ret = btrfs_cleanup_fs_roots(fs_info);
-		BUG_ON(ret);
+		if (ret) {
+			}
 
 		ret = btrfs_recover_relocation(tree_root);
 		if (ret < 0) {
@@ -2859,6 +2863,8 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
 	if (total_errors > max_errors) {
 		printk(KERN_ERR "btrfs: %d errors while writing supers\n",
 		       total_errors);
+
+		/* This shouldn't happen. FUA is masked off if unsupported */
 		BUG();
 	}
 
@@ -2875,9 +2881,9 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
 	}
 	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 	if (total_errors > max_errors) {
-		printk(KERN_ERR "btrfs: %d errors while writing supers\n",
-		       total_errors);
-		BUG();
+		btrfs_error(root->fs_info, -EIO,
+			    "%d errors while writing supers", total_errors);
+		return -EIO;
 	}
 	return 0;
 }
@@ -2891,7 +2897,20 @@ int write_ctree_super(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
+/* Kill all outstanding I/O */
+void btrfs_abort_devices(struct btrfs_root *root)
+{
+	struct list_head *head;
+	struct btrfs_device *dev;
+	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+	head = &root->fs_info->fs_devices->devices;
+	list_for_each_entry_rcu(dev, head, dev_list) {
+		blk_abort_queue(dev->bdev->bd_disk->queue);
+	}
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+}
+
+void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
 {
 	spin_lock(&fs_info->fs_roots_radix_lock);
 	radix_tree_delete(&fs_info->fs_roots_radix,
@@ -2904,7 +2923,6 @@ int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
 	__btrfs_remove_free_space_cache(root->free_ino_pinned);
 	__btrfs_remove_free_space_cache(root->free_ino_ctl);
 	free_fs_root(root);
-	return 0;
 }
 
 static void free_fs_root(struct btrfs_root *root)
@@ -2921,7 +2939,7 @@ static void free_fs_root(struct btrfs_root *root)
 	kfree(root);
 }
 
-static int del_fs_roots(struct btrfs_fs_info *fs_info)
+static void del_fs_roots(struct btrfs_fs_info *fs_info)
 {
 	int ret;
 	struct btrfs_root *gang[8];
@@ -2950,7 +2968,6 @@ static int del_fs_roots(struct btrfs_fs_info *fs_info)
 		for (i = 0; i < ret; i++)
 			btrfs_free_fs_root(fs_info, gang[i]);
 	}
-	return 0;
 }
 
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
@@ -2999,14 +3016,21 @@ int btrfs_commit_super(struct btrfs_root *root)
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 	ret = btrfs_commit_transaction(trans, root);
-	BUG_ON(ret);
+	if (ret)
+		return ret;
 	/* run commit again to drop the original snapshot */
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
-	btrfs_commit_transaction(trans, root);
+	ret = btrfs_commit_transaction(trans, root);
+	if (ret)
+		return ret;
 	ret = btrfs_write_and_wait_transaction(NULL, root);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_error(root->fs_info, ret,
+			    "Failed to sync btree inode to disk.");
+		return ret;
+	}
 
 	ret = write_ctree_super(NULL, root, 0);
 	return ret;
@@ -3122,10 +3146,9 @@ int close_ctree(struct btrfs_root *root)
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid)
 {
 	int ret;
-	struct inode *btree_inode = buf->first_page->mapping->host;
+	struct inode *btree_inode = buf->pages[0]->mapping->host;
 
-	ret = extent_buffer_uptodate(&BTRFS_I(btree_inode)->io_tree, buf,
-				     NULL);
+	ret = extent_buffer_uptodate(buf);
 	if (!ret)
 		return ret;
 
@@ -3136,16 +3159,13 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid)
 
 int btrfs_set_buffer_uptodate(struct extent_buffer *buf)
 {
-	struct inode *btree_inode = buf->first_page->mapping->host;
-	return set_extent_buffer_uptodate(&BTRFS_I(btree_inode)->io_tree,
-					  buf);
+	return set_extent_buffer_uptodate(buf);
 }
 
 void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 {
-	struct btrfs_root *root = BTRFS_I(buf->first_page->mapping->host)->root;
+	struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
 	u64 transid = btrfs_header_generation(buf);
-	struct inode *btree_inode = root->fs_info->btree_inode;
 	int was_dirty;
 
 	btrfs_assert_tree_locked(buf);
@@ -3157,8 +3177,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 			(unsigned long long)root->fs_info->generation);
 		WARN_ON(1);
 	}
-	was_dirty = set_extent_buffer_dirty(&BTRFS_I(btree_inode)->io_tree,
-					    buf);
+	was_dirty = set_extent_buffer_dirty(buf);
 	if (!was_dirty) {
 		spin_lock(&root->fs_info->delalloc_lock);
 		root->fs_info->dirty_metadata_bytes += buf->len;
@@ -3212,12 +3231,8 @@ void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
 
 int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
 {
-	struct btrfs_root *root = BTRFS_I(buf->first_page->mapping->host)->root;
-	int ret;
-	ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
-	if (ret == 0)
-		set_bit(EXTENT_BUFFER_UPTODATE, &buf->bflags);
-	return ret;
+	struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
+	return btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
 }
 
 static int btree_lock_page_hook(struct page *page, void *data,
@@ -3225,17 +3240,21 @@ static int btree_lock_page_hook(struct page *page, void *data,
 {
 	struct inode *inode = page->mapping->host;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct extent_buffer *eb;
-	unsigned long len;
-	u64 bytenr = page_offset(page);
 
-	if (page->private == EXTENT_PAGE_PRIVATE)
+	/*
+	 * We culled this eb but the page is still hanging out on the mapping,
+	 * carry on.
+	 */
+	if (!PagePrivate(page))
 		goto out;
 
-	len = page->private >> 2;
-	eb = find_extent_buffer(io_tree, bytenr, len);
-	if (!eb)
+	eb = (struct extent_buffer *)page->private;
+	if (!eb) {
+		WARN_ON(1);
+		goto out;
+	}
+	if (page != eb->pages[0])
 		goto out;
 
 	if (!btrfs_try_tree_write_lock(eb)) {
@@ -3254,7 +3273,6 @@ static int btree_lock_page_hook(struct page *page, void *data,
 	}
 
 	btrfs_tree_unlock(eb);
-	free_extent_buffer(eb);
 out:
 	if (!trylock_page(page)) {
 		flush_fn(data);
@@ -3263,15 +3281,23 @@ out:
 	return 0;
 }
 
-static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
+static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 			      int read_only)
 {
+	if (btrfs_super_csum_type(fs_info->super_copy) >= ARRAY_SIZE(btrfs_csum_sizes)) {
+		printk(KERN_ERR "btrfs: unsupported checksum algorithm\n");
+		return -EINVAL;
+	}
+
 	if (read_only)
-		return;
+		return 0;
 
-	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
 		printk(KERN_WARNING "warning: mount fs with errors, "
 		       "running btrfsck is recommended\n");
+	}
+
+	return 0;
 }
 
 int btrfs_error_commit_super(struct btrfs_root *root)
@@ -3293,7 +3319,7 @@ int btrfs_error_commit_super(struct btrfs_root *root)
 	return ret;
 }
 
-static int btrfs_destroy_ordered_operations(struct btrfs_root *root)
+static void btrfs_destroy_ordered_operations(struct btrfs_root *root)
 {
 	struct btrfs_inode *btrfs_inode;
 	struct list_head splice;
@@ -3315,11 +3341,9 @@ static int btrfs_destroy_ordered_operations(struct btrfs_root *root)
 
 	spin_unlock(&root->fs_info->ordered_extent_lock);
 	mutex_unlock(&root->fs_info->ordered_operations_mutex);
-
-	return 0;
 }
 
-static int btrfs_destroy_ordered_extents(struct btrfs_root *root)
+static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
 {
 	struct list_head splice;
 	struct btrfs_ordered_extent *ordered;
@@ -3351,12 +3375,10 @@ static int btrfs_destroy_ordered_extents(struct btrfs_root *root)
 	}
 
 	spin_unlock(&root->fs_info->ordered_extent_lock);
-
-	return 0;
 }
 
-static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
-				      struct btrfs_root *root)
+int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
+			       struct btrfs_root *root)
 {
 	struct rb_node *node;
 	struct btrfs_delayed_ref_root *delayed_refs;
@@ -3365,6 +3387,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 
 	delayed_refs = &trans->delayed_refs;
 
+again:
 	spin_lock(&delayed_refs->lock);
 	if (delayed_refs->num_entries == 0) {
 		spin_unlock(&delayed_refs->lock);
@@ -3386,6 +3409,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 			struct btrfs_delayed_ref_head *head;
 
 			head = btrfs_delayed_node_to_head(ref);
+			spin_unlock(&delayed_refs->lock);
 			mutex_lock(&head->mutex);
 			kfree(head->extent_op);
 			delayed_refs->num_heads--;
@@ -3393,8 +3417,9 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				delayed_refs->num_heads_ready--;
 			list_del_init(&head->cluster);
 			mutex_unlock(&head->mutex);
+			btrfs_put_delayed_ref(ref);
+			goto again;
 		}
-
 		spin_unlock(&delayed_refs->lock);
 		btrfs_put_delayed_ref(ref);
 
@@ -3407,7 +3432,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 	return ret;
 }
 
-static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
+static void btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
 {
 	struct btrfs_pending_snapshot *snapshot;
 	struct list_head splice;
@@ -3425,11 +3450,9 @@ static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
 
 		kfree(snapshot);
 	}
-
-	return 0;
 }
 
-static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
+static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
 {
 	struct btrfs_inode *btrfs_inode;
 	struct list_head splice;
@@ -3449,8 +3472,6 @@ static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
 	}
 
 	spin_unlock(&root->fs_info->delalloc_lock);
-
-	return 0;
 }
 
 static int btrfs_destroy_marked_extents(struct btrfs_root *root,
@@ -3541,13 +3562,43 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
 	return 0;
 }
 
-static int btrfs_cleanup_transaction(struct btrfs_root *root)
+void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
+				   struct btrfs_root *root)
+{
+	btrfs_destroy_delayed_refs(cur_trans, root);
+	btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
+				cur_trans->dirty_pages.dirty_bytes);
+
+	/* FIXME: cleanup wait for commit */
+	cur_trans->in_commit = 1;
+	cur_trans->blocked = 1;
+	if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
+		wake_up(&root->fs_info->transaction_blocked_wait);
+
+	cur_trans->blocked = 0;
+	if (waitqueue_active(&root->fs_info->transaction_wait))
+		wake_up(&root->fs_info->transaction_wait);
+
+	cur_trans->commit_done = 1;
+	if (waitqueue_active(&cur_trans->commit_wait))
+		wake_up(&cur_trans->commit_wait);
+
+	btrfs_destroy_pending_snapshots(cur_trans);
+
+	btrfs_destroy_marked_extents(root, &cur_trans->dirty_pages,
+				     EXTENT_DIRTY);
+
+	/*
+	memset(cur_trans, 0, sizeof(*cur_trans));
+	kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+	*/
+}
+
+int btrfs_cleanup_transaction(struct btrfs_root *root)
 {
 	struct btrfs_transaction *t;
 	LIST_HEAD(list);
 
-	WARN_ON(1);
-
 	mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
 	spin_lock(&root->fs_info->trans_lock);
@@ -3612,6 +3663,17 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 	return 0;
 }
 
+static int btree_writepage_io_failed_hook(struct bio *bio, struct page *page,
+					  u64 start, u64 end,
+					  struct extent_state *state)
+{
+	struct super_block *sb = page->mapping->host->i_sb;
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	btrfs_error(fs_info, -EIO,
+		    "Error occured while writing out btree at %llu", start);
+	return -EIO;
+}
+
 static struct extent_io_ops btree_extent_io_ops = {
 	.write_cache_pages_lock_hook = btree_lock_page_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
@@ -3619,4 +3681,5 @@ static struct extent_io_ops btree_extent_io_ops = {
 	.submit_bio_hook = btree_submit_bio_hook,
 	/* note we're sharing with inode.c for the merge bio hook */
 	.merge_bio_hook = btrfs_merge_bio_hook,
+	.writepage_io_failed_hook = btree_writepage_io_failed_hook,
 };
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index e4bc4741319b..a7ace1a2dd12 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -44,8 +44,8 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 			 int mirror_num, struct extent_buffer **eb);
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						   u64 bytenr, u32 blocksize);
-int clean_tree_block(struct btrfs_trans_handle *trans,
-		     struct btrfs_root *root, struct extent_buffer *buf);
+void clean_tree_block(struct btrfs_trans_handle *trans,
+		      struct btrfs_root *root, struct extent_buffer *buf);
 int open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
@@ -64,7 +64,7 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
 void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
 void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
-int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root);
+void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root);
 void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid);
 int btrfs_set_buffer_uptodate(struct extent_buffer *buf);
@@ -85,6 +85,10 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info);
 int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root);
+int btrfs_cleanup_transaction(struct btrfs_root *root);
+void btrfs_cleanup_one_transaction(struct btrfs_transaction *trans,
+				  struct btrfs_root *root);
+void btrfs_abort_devices(struct btrfs_root *root);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void btrfs_init_lockdep(void);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 5f77166fd01c..e887ee62b6d4 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -193,7 +193,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 	if (ret < 0)
 		goto fail;
 
-	BUG_ON(ret == 0);
+	BUG_ON(ret == 0); /* Key with offset of -1 found */
 	if (path->slots[0] == 0) {
 		ret = -ENOENT;
 		goto fail;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 37e0a800d34e..a84420491c11 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -245,7 +245,7 @@ static int exclude_super_stripes(struct btrfs_root *root,
 		cache->bytes_super += stripe_len;
 		ret = add_excluded_extent(root, cache->key.objectid,
 					  stripe_len);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
@@ -253,13 +253,13 @@ static int exclude_super_stripes(struct btrfs_root *root,
 		ret = btrfs_rmap_block(&root->fs_info->mapping_tree,
 				       cache->key.objectid, bytenr,
 				       0, &logical, &nr, &stripe_len);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 
 		while (nr--) {
 			cache->bytes_super += stripe_len;
 			ret = add_excluded_extent(root, logical[nr],
 						  stripe_len);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 		}
 
 		kfree(logical);
@@ -321,7 +321,7 @@ static u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 			total_added += size;
 			ret = btrfs_add_free_space(block_group, start,
 						   size);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM or logic error */
 			start = extent_end + 1;
 		} else {
 			break;
@@ -332,7 +332,7 @@ static u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 		size = end - start;
 		total_added += size;
 		ret = btrfs_add_free_space(block_group, start, size);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM or logic error */
 	}
 
 	return total_added;
@@ -474,7 +474,8 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	int ret = 0;
 
 	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
-	BUG_ON(!caching_ctl);
+	if (!caching_ctl)
+		return -ENOMEM;
 
 	INIT_LIST_HEAD(&caching_ctl->list);
 	mutex_init(&caching_ctl->mutex);
@@ -982,7 +983,7 @@ static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
 				ret = btrfs_next_leaf(root, path);
 				if (ret < 0)
 					return ret;
-				BUG_ON(ret > 0);
+				BUG_ON(ret > 0); /* Corruption */
 				leaf = path->nodes[0];
 			}
 			btrfs_item_key_to_cpu(leaf, &found_key,
@@ -1008,9 +1009,9 @@ static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
 				new_size + extra_size, 1);
 	if (ret < 0)
 		return ret;
-	BUG_ON(ret);
+	BUG_ON(ret); /* Corruption */
 
-	ret = btrfs_extend_item(trans, root, path, new_size);
+	btrfs_extend_item(trans, root, path, new_size);
 
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
@@ -1478,7 +1479,11 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 		err = ret;
 		goto out;
 	}
-	BUG_ON(ret);
+	if (ret && !insert) {
+		err = -ENOENT;
+		goto out;
+	}
+	BUG_ON(ret); /* Corruption */
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
@@ -1592,13 +1597,13 @@ out:
  * helper to add new inline back ref
  */
 static noinline_for_stack
-int setup_inline_extent_backref(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root,
-				struct btrfs_path *path,
-				struct btrfs_extent_inline_ref *iref,
-				u64 parent, u64 root_objectid,
-				u64 owner, u64 offset, int refs_to_add,
-				struct btrfs_delayed_extent_op *extent_op)
+void setup_inline_extent_backref(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 struct btrfs_extent_inline_ref *iref,
+				 u64 parent, u64 root_objectid,
+				 u64 owner, u64 offset, int refs_to_add,
+				 struct btrfs_delayed_extent_op *extent_op)
 {
 	struct extent_buffer *leaf;
 	struct btrfs_extent_item *ei;
@@ -1608,7 +1613,6 @@ int setup_inline_extent_backref(struct btrfs_trans_handle *trans,
 	u64 refs;
 	int size;
 	int type;
-	int ret;
 
 	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
@@ -1617,7 +1621,7 @@ int setup_inline_extent_backref(struct btrfs_trans_handle *trans,
 	type = extent_ref_type(parent, owner);
 	size = btrfs_extent_inline_ref_size(type);
 
-	ret = btrfs_extend_item(trans, root, path, size);
+	btrfs_extend_item(trans, root, path, size);
 
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	refs = btrfs_extent_refs(leaf, ei);
@@ -1652,7 +1656,6 @@ int setup_inline_extent_backref(struct btrfs_trans_handle *trans,
 		btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
 	}
 	btrfs_mark_buffer_dirty(leaf);
-	return 0;
 }
 
 static int lookup_extent_backref(struct btrfs_trans_handle *trans,
@@ -1687,12 +1690,12 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
  * helper to update/remove inline back ref
  */
 static noinline_for_stack
-int update_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root,
-				 struct btrfs_path *path,
-				 struct btrfs_extent_inline_ref *iref,
-				 int refs_to_mod,
-				 struct btrfs_delayed_extent_op *extent_op)
+void update_inline_extent_backref(struct btrfs_trans_handle *trans,
+				  struct btrfs_root *root,
+				  struct btrfs_path *path,
+				  struct btrfs_extent_inline_ref *iref,
+				  int refs_to_mod,
+				  struct btrfs_delayed_extent_op *extent_op)
 {
 	struct extent_buffer *leaf;
 	struct btrfs_extent_item *ei;
@@ -1703,7 +1706,6 @@ int update_inline_extent_backref(struct btrfs_trans_handle *trans,
 	u32 item_size;
 	int size;
 	int type;
-	int ret;
 	u64 refs;
 
 	leaf = path->nodes[0];
@@ -1745,10 +1747,9 @@ int update_inline_extent_backref(struct btrfs_trans_handle *trans,
 			memmove_extent_buffer(leaf, ptr, ptr + size,
 					      end - ptr - size);
 		item_size -= size;
-		ret = btrfs_truncate_item(trans, root, path, item_size, 1);
+		btrfs_truncate_item(trans, root, path, item_size, 1);
 	}
 	btrfs_mark_buffer_dirty(leaf);
-	return 0;
 }
 
 static noinline_for_stack
@@ -1768,13 +1769,13 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 					   root_objectid, owner, offset, 1);
 	if (ret == 0) {
 		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
-		ret = update_inline_extent_backref(trans, root, path, iref,
-						   refs_to_add, extent_op);
+		update_inline_extent_backref(trans, root, path, iref,
+					     refs_to_add, extent_op);
 	} else if (ret == -ENOENT) {
-		ret = setup_inline_extent_backref(trans, root, path, iref,
-						  parent, root_objectid,
-						  owner, offset, refs_to_add,
-						  extent_op);
+		setup_inline_extent_backref(trans, root, path, iref, parent,
+					    root_objectid, owner, offset,
+					    refs_to_add, extent_op);
+		ret = 0;
 	}
 	return ret;
 }
@@ -1804,12 +1805,12 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 				 struct btrfs_extent_inline_ref *iref,
 				 int refs_to_drop, int is_data)
 {
-	int ret;
+	int ret = 0;
 
 	BUG_ON(!is_data && refs_to_drop != 1);
 	if (iref) {
-		ret = update_inline_extent_backref(trans, root, path, iref,
-						   -refs_to_drop, NULL);
+		update_inline_extent_backref(trans, root, path, iref,
+					     -refs_to_drop, NULL);
 	} else if (is_data) {
 		ret = remove_extent_data_ref(trans, root, path, refs_to_drop);
 	} else {
@@ -1835,6 +1836,7 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 	/* Tell the block device(s) that the sectors can be discarded */
 	ret = btrfs_map_block(&root->fs_info->mapping_tree, REQ_DISCARD,
 			      bytenr, &num_bytes, &bbio, 0);
+	/* Error condition is -ENOMEM */
 	if (!ret) {
 		struct btrfs_bio_stripe *stripe = bbio->stripes;
 		int i;
@@ -1850,7 +1852,7 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 			if (!ret)
 				discarded_bytes += stripe->length;
 			else if (ret != -EOPNOTSUPP)
-				break;
+				break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */
 
 			/*
 			 * Just in case we get back EOPNOTSUPP for some reason,
@@ -1869,6 +1871,7 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 	return ret;
 }
 
+/* Can return -ENOMEM */
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
@@ -1944,7 +1947,8 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	ret = insert_extent_backref(trans, root->fs_info->extent_root,
 				    path, bytenr, parent, root_objectid,
 				    owner, offset, refs_to_add);
-	BUG_ON(ret);
+	if (ret)
+		btrfs_abort_transaction(trans, root, ret);
 out:
 	btrfs_free_path(path);
 	return err;
@@ -2031,6 +2035,9 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
 	int ret;
 	int err = 0;
 
+	if (trans->aborted)
+		return 0;
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -2128,7 +2135,11 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int insert_reserved)
 {
-	int ret;
+	int ret = 0;
+
+	if (trans->aborted)
+		return 0;
+
 	if (btrfs_delayed_ref_is_head(node)) {
 		struct btrfs_delayed_ref_head *head;
 		/*
@@ -2146,11 +2157,10 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 				ret = btrfs_del_csums(trans, root,
 						      node->bytenr,
 						      node->num_bytes);
-				BUG_ON(ret);
 			}
 		}
 		mutex_unlock(&head->mutex);
-		return 0;
+		return ret;
 	}
 
 	if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
@@ -2197,6 +2207,10 @@ again:
 	return NULL;
 }
 
+/*
+ * Returns 0 on success or if called with an already aborted transaction.
+ * Returns -ENOMEM or -EIO on failure and will abort the transaction.
+ */
 static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 				       struct btrfs_root *root,
 				       struct list_head *cluster)
@@ -2285,9 +2299,13 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 
 				ret = run_delayed_extent_op(trans, root,
 							    ref, extent_op);
-				BUG_ON(ret);
 				kfree(extent_op);
 
+				if (ret) {
+					printk(KERN_DEBUG "btrfs: run_delayed_extent_op returned %d\n", ret);
+					return ret;
+				}
+
 				goto next;
 			}
 
@@ -2308,11 +2326,16 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 
 		ret = run_one_delayed_ref(trans, root, ref, extent_op,
 					  must_insert_reserved);
-		BUG_ON(ret);
 
 		btrfs_put_delayed_ref(ref);
 		kfree(extent_op);
 		count++;
+
+		if (ret) {
+			printk(KERN_DEBUG "btrfs: run_one_delayed_ref returned %d\n", ret);
+			return ret;
+		}
+
 next:
 		do_chunk_alloc(trans, root->fs_info->extent_root,
 			       2 * 1024 * 1024,
@@ -2347,6 +2370,9 @@ static void wait_for_more_refs(struct btrfs_delayed_ref_root *delayed_refs,
  * 0, which means to process everything in the tree at the start
  * of the run (but not newly added entries), or it can be some target
  * number you'd like to process.
+ *
+ * Returns 0 on success or if called with an aborted transaction
+ * Returns <0 on error and aborts the transaction
  */
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, unsigned long count)
@@ -2362,6 +2388,10 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 	unsigned long num_refs = 0;
 	int consider_waiting;
 
+	/* We'll clean this up in btrfs_cleanup_transaction */
+	if (trans->aborted)
+		return 0;
+
 	if (root == root->fs_info->extent_root)
 		root = root->fs_info->tree_root;
 
@@ -2419,7 +2449,11 @@ again:
 		}
 
 		ret = run_clustered_refs(trans, root, &cluster);
-		BUG_ON(ret < 0);
+		if (ret < 0) {
+			spin_unlock(&delayed_refs->lock);
+			btrfs_abort_transaction(trans, root, ret);
+			return ret;
+		}
 
 		count -= min_t(unsigned long, ret, count);
 
@@ -2584,7 +2618,7 @@ static noinline int check_committed_ref(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret == 0);
+	BUG_ON(ret == 0); /* Corruption */
 
 	ret = -ENOENT;
 	if (path->slots[0] == 0)
@@ -2738,7 +2772,6 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 	}
 	return 0;
 fail:
-	BUG();
 	return ret;
 }
 
@@ -2767,7 +2800,7 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
 	if (ret < 0)
 		goto fail;
-	BUG_ON(ret);
+	BUG_ON(ret); /* Corruption */
 
 	leaf = path->nodes[0];
 	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
@@ -2775,8 +2808,10 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 fail:
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
 		return ret;
+	}
 	return 0;
 
 }
@@ -2949,7 +2984,8 @@ again:
 		if (last == 0) {
 			err = btrfs_run_delayed_refs(trans, root,
 						     (unsigned long)-1);
-			BUG_ON(err);
+			if (err) /* File system offline */
+				goto out;
 		}
 
 		cache = btrfs_lookup_first_block_group(root->fs_info, last);
@@ -2976,7 +3012,9 @@ again:
 		last = cache->key.objectid + cache->key.offset;
 
 		err = write_one_cache_group(trans, root, path, cache);
-		BUG_ON(err);
+		if (err) /* File system offline */
+			goto out;
+
 		btrfs_put_block_group(cache);
 	}
 
@@ -2989,7 +3027,8 @@ again:
 		if (last == 0) {
 			err = btrfs_run_delayed_refs(trans, root,
 						     (unsigned long)-1);
-			BUG_ON(err);
+			if (err) /* File system offline */
+				goto out;
 		}
 
 		cache = btrfs_lookup_first_block_group(root->fs_info, last);
@@ -3014,20 +3053,21 @@ again:
 			continue;
 		}
 
-		btrfs_write_out_cache(root, trans, cache, path);
+		err = btrfs_write_out_cache(root, trans, cache, path);
 
 		/*
 		 * If we didn't have an error then the cache state is still
 		 * NEED_WRITE, so we can set it to WRITTEN.
 		 */
-		if (cache->disk_cache_state == BTRFS_DC_NEED_WRITE)
+		if (!err && cache->disk_cache_state == BTRFS_DC_NEED_WRITE)
 			cache->disk_cache_state = BTRFS_DC_WRITTEN;
 		last = cache->key.objectid + cache->key.offset;
 		btrfs_put_block_group(cache);
 	}
+out:
 
 	btrfs_free_path(path);
-	return 0;
+	return err;
 }
 
 int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr)
@@ -3098,11 +3138,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 
 static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 {
-	u64 extra_flags = flags & BTRFS_BLOCK_GROUP_PROFILE_MASK;
-
-	/* chunk -> extended profile */
-	if (extra_flags == 0)
-		extra_flags = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+	u64 extra_flags = chunk_to_extended(flags) &
+				BTRFS_EXTENDED_PROFILE_MASK;
 
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
 		fs_info->avail_data_alloc_bits |= extra_flags;
@@ -3113,6 +3150,35 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 }
 
 /*
+ * returns target flags in extended format or 0 if restripe for this
+ * chunk_type is not in progress
+ */
+static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
+{
+	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+	u64 target = 0;
+
+	BUG_ON(!mutex_is_locked(&fs_info->volume_mutex) &&
+	       !spin_is_locked(&fs_info->balance_lock));
+
+	if (!bctl)
+		return 0;
+
+	if (flags & BTRFS_BLOCK_GROUP_DATA &&
+	    bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+		target = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
+	} else if (flags & BTRFS_BLOCK_GROUP_SYSTEM &&
+		   bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+		target = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
+	} else if (flags & BTRFS_BLOCK_GROUP_METADATA &&
+		   bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+		target = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
+	}
+
+	return target;
+}
+
+/*
  * @flags: available profiles in extended format (see ctree.h)
  *
  * Returns reduced profile in chunk format.  If profile changing is in
@@ -3128,31 +3194,19 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
 	 */
 	u64 num_devices = root->fs_info->fs_devices->rw_devices +
 		root->fs_info->fs_devices->missing_devices;
+	u64 target;
 
-	/* pick restriper's target profile if it's available */
+	/*
+	 * see if restripe for this chunk_type is in progress, if so
+	 * try to reduce to the target profile
+	 */
 	spin_lock(&root->fs_info->balance_lock);
-	if (root->fs_info->balance_ctl) {
-		struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
-		u64 tgt = 0;
-
-		if ((flags & BTRFS_BLOCK_GROUP_DATA) &&
-		    (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
-		    (flags & bctl->data.target)) {
-			tgt = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
-		} else if ((flags & BTRFS_BLOCK_GROUP_SYSTEM) &&
-			   (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
-			   (flags & bctl->sys.target)) {
-			tgt = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
-		} else if ((flags & BTRFS_BLOCK_GROUP_METADATA) &&
-			   (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
-			   (flags & bctl->meta.target)) {
-			tgt = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
-		}
-
-		if (tgt) {
+	target = get_restripe_target(root->fs_info, flags);
+	if (target) {
+		/* pick target profile only if it's already available */
+		if ((flags & target) & BTRFS_EXTENDED_PROFILE_MASK) {
 			spin_unlock(&root->fs_info->balance_lock);
-			flags = tgt;
-			goto out;
+			return extended_to_chunk(target);
 		}
 	}
 	spin_unlock(&root->fs_info->balance_lock);
@@ -3180,10 +3234,7 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
 		flags &= ~BTRFS_BLOCK_GROUP_RAID0;
 	}
 
-out:
-	/* extended -> chunk profile */
-	flags &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-	return flags;
+	return extended_to_chunk(flags);
 }
 
 static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
@@ -3312,8 +3363,7 @@ commit_trans:
 	}
 	data_sinfo->bytes_may_use += bytes;
 	trace_btrfs_space_reservation(root->fs_info, "space_info",
-				      (u64)(unsigned long)data_sinfo,
-				      bytes, 1);
+				      data_sinfo->flags, bytes, 1);
 	spin_unlock(&data_sinfo->lock);
 
 	return 0;
@@ -3334,8 +3384,7 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes)
 	spin_lock(&data_sinfo->lock);
 	data_sinfo->bytes_may_use -= bytes;
 	trace_btrfs_space_reservation(root->fs_info, "space_info",
-				      (u64)(unsigned long)data_sinfo,
-				      bytes, 0);
+				      data_sinfo->flags, bytes, 0);
 	spin_unlock(&data_sinfo->lock);
 }
 
@@ -3396,6 +3445,50 @@ static int should_alloc_chunk(struct btrfs_root *root,
 	return 1;
 }
 
+static u64 get_system_chunk_thresh(struct btrfs_root *root, u64 type)
+{
+	u64 num_dev;
+
+	if (type & BTRFS_BLOCK_GROUP_RAID10 ||
+	    type & BTRFS_BLOCK_GROUP_RAID0)
+		num_dev = root->fs_info->fs_devices->rw_devices;
+	else if (type & BTRFS_BLOCK_GROUP_RAID1)
+		num_dev = 2;
+	else
+		num_dev = 1;	/* DUP or single */
+
+	/* metadata for updaing devices and chunk tree */
+	return btrfs_calc_trans_metadata_size(root, num_dev + 1);
+}
+
+static void check_system_chunk(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root, u64 type)
+{
+	struct btrfs_space_info *info;
+	u64 left;
+	u64 thresh;
+
+	info = __find_space_info(root->fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
+	spin_lock(&info->lock);
+	left = info->total_bytes - info->bytes_used - info->bytes_pinned -
+		info->bytes_reserved - info->bytes_readonly;
+	spin_unlock(&info->lock);
+
+	thresh = get_system_chunk_thresh(root, type);
+	if (left < thresh && btrfs_test_opt(root, ENOSPC_DEBUG)) {
+		printk(KERN_INFO "left=%llu, need=%llu, flags=%llu\n",
+		       left, thresh, type);
+		dump_space_info(info, 0, 0);
+	}
+
+	if (left < thresh) {
+		u64 flags;
+
+		flags = btrfs_get_alloc_profile(root->fs_info->chunk_root, 0);
+		btrfs_alloc_chunk(trans, root, flags);
+	}
+}
+
 static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *extent_root, u64 alloc_bytes,
 			  u64 flags, int force)
@@ -3405,15 +3498,13 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 	int wait_for_alloc = 0;
 	int ret = 0;
 
-	BUG_ON(!profile_is_valid(flags, 0));
-
 	space_info = __find_space_info(extent_root->fs_info, flags);
 	if (!space_info) {
 		ret = update_space_info(extent_root->fs_info, flags,
 					0, 0, &space_info);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
-	BUG_ON(!space_info);
+	BUG_ON(!space_info); /* Logic error */
 
 again:
 	spin_lock(&space_info->lock);
@@ -3468,6 +3559,12 @@ again:
 			force_metadata_allocation(fs_info);
 	}
 
+	/*
+	 * Check if we have enough space in SYSTEM chunk because we may need
+	 * to update devices.
+	 */
+	check_system_chunk(trans, extent_root, flags);
+
 	ret = btrfs_alloc_chunk(trans, extent_root, flags);
 	if (ret < 0 && ret != -ENOSPC)
 		goto out;
@@ -3678,8 +3775,10 @@ again:
 		ret = wait_event_interruptible(space_info->wait,
 					       !space_info->flush);
 		/* Must have been interrupted, return */
-		if (ret)
+		if (ret) {
+			printk(KERN_DEBUG "btrfs: %s returning -EINTR\n", __func__);
 			return -EINTR;
+		}
 
 		spin_lock(&space_info->lock);
 	}
@@ -3700,9 +3799,7 @@ again:
 		if (used + orig_bytes <= space_info->total_bytes) {
 			space_info->bytes_may_use += orig_bytes;
 			trace_btrfs_space_reservation(root->fs_info,
-					      "space_info",
-					      (u64)(unsigned long)space_info,
-					      orig_bytes, 1);
+				"space_info", space_info->flags, orig_bytes, 1);
 			ret = 0;
 		} else {
 			/*
@@ -3771,9 +3868,7 @@ again:
 		if (used + num_bytes < space_info->total_bytes + avail) {
 			space_info->bytes_may_use += orig_bytes;
 			trace_btrfs_space_reservation(root->fs_info,
-					      "space_info",
-					      (u64)(unsigned long)space_info,
-					      orig_bytes, 1);
+				"space_info", space_info->flags, orig_bytes, 1);
 			ret = 0;
 		} else {
 			wait_ordered = true;
@@ -3836,8 +3931,9 @@ out:
 	return ret;
 }
 
-static struct btrfs_block_rsv *get_block_rsv(struct btrfs_trans_handle *trans,
-					     struct btrfs_root *root)
+static struct btrfs_block_rsv *get_block_rsv(
+					const struct btrfs_trans_handle *trans,
+					const struct btrfs_root *root)
 {
 	struct btrfs_block_rsv *block_rsv = NULL;
 
@@ -3918,8 +4014,7 @@ static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 			spin_lock(&space_info->lock);
 			space_info->bytes_may_use -= num_bytes;
 			trace_btrfs_space_reservation(fs_info, "space_info",
-					      (u64)(unsigned long)space_info,
-					      num_bytes, 0);
+					space_info->flags, num_bytes, 0);
 			space_info->reservation_progress++;
 			spin_unlock(&space_info->lock);
 		}
@@ -4137,14 +4232,14 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 		block_rsv->reserved += num_bytes;
 		sinfo->bytes_may_use += num_bytes;
 		trace_btrfs_space_reservation(fs_info, "space_info",
-				      (u64)(unsigned long)sinfo, num_bytes, 1);
+				      sinfo->flags, num_bytes, 1);
 	}
 
 	if (block_rsv->reserved >= block_rsv->size) {
 		num_bytes = block_rsv->reserved - block_rsv->size;
 		sinfo->bytes_may_use -= num_bytes;
 		trace_btrfs_space_reservation(fs_info, "space_info",
-				      (u64)(unsigned long)sinfo, num_bytes, 0);
+				      sinfo->flags, num_bytes, 0);
 		sinfo->reservation_progress++;
 		block_rsv->reserved = block_rsv->size;
 		block_rsv->full = 1;
@@ -4198,12 +4293,12 @@ void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 		return;
 
 	trace_btrfs_space_reservation(root->fs_info, "transaction",
-				      (u64)(unsigned long)trans,
-				      trans->bytes_reserved, 0);
+				      trans->transid, trans->bytes_reserved, 0);
 	btrfs_block_rsv_release(root, trans->block_rsv, trans->bytes_reserved);
 	trans->bytes_reserved = 0;
 }
 
+/* Can only return 0 or -ENOSPC */
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 				  struct inode *inode)
 {
@@ -4540,7 +4635,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 	while (total) {
 		cache = btrfs_lookup_block_group(info, bytenr);
 		if (!cache)
-			return -1;
+			return -ENOENT;
 		if (cache->flags & (BTRFS_BLOCK_GROUP_DUP |
 				    BTRFS_BLOCK_GROUP_RAID1 |
 				    BTRFS_BLOCK_GROUP_RAID10))
@@ -4643,7 +4738,7 @@ int btrfs_pin_extent(struct btrfs_root *root,
 	struct btrfs_block_group_cache *cache;
 
 	cache = btrfs_lookup_block_group(root->fs_info, bytenr);
-	BUG_ON(!cache);
+	BUG_ON(!cache); /* Logic error */
 
 	pin_down_extent(root, cache, bytenr, num_bytes, reserved);
 
@@ -4661,7 +4756,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
 	struct btrfs_block_group_cache *cache;
 
 	cache = btrfs_lookup_block_group(root->fs_info, bytenr);
-	BUG_ON(!cache);
+	BUG_ON(!cache); /* Logic error */
 
 	/*
 	 * pull in the free space cache (if any) so that our pin
@@ -4706,6 +4801,7 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
 {
 	struct btrfs_space_info *space_info = cache->space_info;
 	int ret = 0;
+
 	spin_lock(&space_info->lock);
 	spin_lock(&cache->lock);
 	if (reserve != RESERVE_FREE) {
@@ -4716,9 +4812,8 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
 			space_info->bytes_reserved += num_bytes;
 			if (reserve == RESERVE_ALLOC) {
 				trace_btrfs_space_reservation(cache->fs_info,
-					      "space_info",
-					      (u64)(unsigned long)space_info,
-					      num_bytes, 0);
+						"space_info", space_info->flags,
+						num_bytes, 0);
 				space_info->bytes_may_use -= num_bytes;
 			}
 		}
@@ -4734,7 +4829,7 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
 	return ret;
 }
 
-int btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
+void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -4764,7 +4859,6 @@ int btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 	up_write(&fs_info->extent_commit_sem);
 
 	update_global_block_rsv(fs_info);
-	return 0;
 }
 
 static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
@@ -4779,7 +4873,7 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 			if (cache)
 				btrfs_put_block_group(cache);
 			cache = btrfs_lookup_block_group(fs_info, start);
-			BUG_ON(!cache);
+			BUG_ON(!cache); /* Logic error */
 		}
 
 		len = cache->key.objectid + cache->key.offset - start;
@@ -4816,6 +4910,9 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 	u64 end;
 	int ret;
 
+	if (trans->aborted)
+		return 0;
+
 	if (fs_info->pinned_extents == &fs_info->freed_extents[0])
 		unpin = &fs_info->freed_extents[1];
 	else
@@ -4901,7 +4998,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			ret = remove_extent_backref(trans, extent_root, path,
 						    NULL, refs_to_drop,
 						    is_data);
-			BUG_ON(ret);
+			if (ret)
+				goto abort;
 			btrfs_release_path(path);
 			path->leave_spinning = 1;
 
@@ -4919,10 +5017,11 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 					btrfs_print_leaf(extent_root,
 							 path->nodes[0]);
 			}
-			BUG_ON(ret);
+			if (ret < 0)
+				goto abort;
 			extent_slot = path->slots[0];
 		}
-	} else {
+	} else if (ret == -ENOENT) {
 		btrfs_print_leaf(extent_root, path->nodes[0]);
 		WARN_ON(1);
 		printk(KERN_ERR "btrfs unable to find ref byte nr %llu "
@@ -4932,6 +5031,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 		       (unsigned long long)root_objectid,
 		       (unsigned long long)owner_objectid,
 		       (unsigned long long)owner_offset);
+	} else {
+		goto abort;
 	}
 
 	leaf = path->nodes[0];
@@ -4941,7 +5042,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 		BUG_ON(found_extent || extent_slot != path->slots[0]);
 		ret = convert_extent_item_v0(trans, extent_root, path,
 					     owner_objectid, 0);
-		BUG_ON(ret < 0);
+		if (ret < 0)
+			goto abort;
 
 		btrfs_release_path(path);
 		path->leave_spinning = 1;
@@ -4958,7 +5060,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			       (unsigned long long)bytenr);
 			btrfs_print_leaf(extent_root, path->nodes[0]);
 		}
-		BUG_ON(ret);
+		if (ret < 0)
+			goto abort;
 		extent_slot = path->slots[0];
 		leaf = path->nodes[0];
 		item_size = btrfs_item_size_nr(leaf, extent_slot);
@@ -4995,7 +5098,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			ret = remove_extent_backref(trans, extent_root, path,
 						    iref, refs_to_drop,
 						    is_data);
-			BUG_ON(ret);
+			if (ret)
+				goto abort;
 		}
 	} else {
 		if (found_extent) {
@@ -5012,23 +5116,27 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 
 		ret = btrfs_del_items(trans, extent_root, path, path->slots[0],
 				      num_to_del);
-		BUG_ON(ret);
+		if (ret)
+			goto abort;
 		btrfs_release_path(path);
 
 		if (is_data) {
 			ret = btrfs_del_csums(trans, root, bytenr, num_bytes);
-			BUG_ON(ret);
-		} else {
-			invalidate_mapping_pages(info->btree_inode->i_mapping,
-			     bytenr >> PAGE_CACHE_SHIFT,
-			     (bytenr + num_bytes - 1) >> PAGE_CACHE_SHIFT);
+			if (ret)
+				goto abort;
 		}
 
 		ret = update_block_group(trans, root, bytenr, num_bytes, 0);
-		BUG_ON(ret);
+		if (ret)
+			goto abort;
 	}
+out:
 	btrfs_free_path(path);
 	return ret;
+
+abort:
+	btrfs_abort_transaction(trans, extent_root, ret);
+	goto out;
 }
 
 /*
@@ -5124,7 +5232,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 					parent, root->root_key.objectid,
 					btrfs_header_level(buf),
 					BTRFS_DROP_DELAYED_REF, NULL, for_cow);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 
 	if (!last_ref)
@@ -5158,6 +5266,7 @@ out:
 	btrfs_put_block_group(cache);
 }
 
+/* Can return -ENOMEM */
 int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
 		      u64 owner, u64 offset, int for_cow)
@@ -5179,14 +5288,12 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 					num_bytes,
 					parent, root_objectid, (int)owner,
 					BTRFS_DROP_DELAYED_REF, NULL, for_cow);
-		BUG_ON(ret);
 	} else {
 		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
 						num_bytes,
 						parent, root_objectid, owner,
 						offset, BTRFS_DROP_DELAYED_REF,
 						NULL, for_cow);
-		BUG_ON(ret);
 	}
 	return ret;
 }
@@ -5243,28 +5350,34 @@ wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-static int get_block_group_index(struct btrfs_block_group_cache *cache)
+static int __get_block_group_index(u64 flags)
 {
 	int index;
-	if (cache->flags & BTRFS_BLOCK_GROUP_RAID10)
+
+	if (flags & BTRFS_BLOCK_GROUP_RAID10)
 		index = 0;
-	else if (cache->flags & BTRFS_BLOCK_GROUP_RAID1)
+	else if (flags & BTRFS_BLOCK_GROUP_RAID1)
 		index = 1;
-	else if (cache->flags & BTRFS_BLOCK_GROUP_DUP)
+	else if (flags & BTRFS_BLOCK_GROUP_DUP)
 		index = 2;
-	else if (cache->flags & BTRFS_BLOCK_GROUP_RAID0)
+	else if (flags & BTRFS_BLOCK_GROUP_RAID0)
 		index = 3;
 	else
 		index = 4;
+
 	return index;
 }
 
+static int get_block_group_index(struct btrfs_block_group_cache *cache)
+{
+	return __get_block_group_index(cache->flags);
+}
+
 enum btrfs_loop_type {
-	LOOP_FIND_IDEAL = 0,
-	LOOP_CACHING_NOWAIT = 1,
-	LOOP_CACHING_WAIT = 2,
-	LOOP_ALLOC_CHUNK = 3,
-	LOOP_NO_EMPTY_SIZE = 4,
+	LOOP_CACHING_NOWAIT = 0,
+	LOOP_CACHING_WAIT = 1,
+	LOOP_ALLOC_CHUNK = 2,
+	LOOP_NO_EMPTY_SIZE = 3,
 };
 
 /*
@@ -5278,7 +5391,6 @@ enum btrfs_loop_type {
 static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *orig_root,
 				     u64 num_bytes, u64 empty_size,
-				     u64 search_start, u64 search_end,
 				     u64 hint_byte, struct btrfs_key *ins,
 				     u64 data)
 {
@@ -5287,6 +5399,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_free_cluster *last_ptr = NULL;
 	struct btrfs_block_group_cache *block_group = NULL;
 	struct btrfs_block_group_cache *used_block_group;
+	u64 search_start = 0;
 	int empty_cluster = 2 * 1024 * 1024;
 	int allowed_chunk_alloc = 0;
 	int done_chunk_alloc = 0;
@@ -5300,8 +5413,6 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 	bool failed_alloc = false;
 	bool use_cluster = true;
 	bool have_caching_bg = false;
-	u64 ideal_cache_percent = 0;
-	u64 ideal_cache_offset = 0;
 
 	WARN_ON(num_bytes < root->sectorsize);
 	btrfs_set_key_type(ins, BTRFS_EXTENT_ITEM_KEY);
@@ -5351,7 +5462,6 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 		empty_cluster = 0;
 
 	if (search_start == hint_byte) {
-ideal_cache:
 		block_group = btrfs_lookup_block_group(root->fs_info,
 						       search_start);
 		used_block_group = block_group;
@@ -5363,8 +5473,7 @@ ideal_cache:
 		 * picked out then we don't care that the block group is cached.
 		 */
 		if (block_group && block_group_bits(block_group, data) &&
-		    (block_group->cached != BTRFS_CACHE_NO ||
-		     search_start == ideal_cache_offset)) {
+		    block_group->cached != BTRFS_CACHE_NO) {
 			down_read(&space_info->groups_sem);
 			if (list_empty(&block_group->list) ||
 			    block_group->ro) {
@@ -5418,44 +5527,13 @@ search:
 have_block_group:
 		cached = block_group_cache_done(block_group);
 		if (unlikely(!cached)) {
-			u64 free_percent;
-
 			found_uncached_bg = true;
 			ret = cache_block_group(block_group, trans,
-						orig_root, 1);
-			if (block_group->cached == BTRFS_CACHE_FINISHED)
-				goto alloc;
-
-			free_percent = btrfs_block_group_used(&block_group->item);
-			free_percent *= 100;
-			free_percent = div64_u64(free_percent,
-						 block_group->key.offset);
-			free_percent = 100 - free_percent;
-			if (free_percent > ideal_cache_percent &&
-			    likely(!block_group->ro)) {
-				ideal_cache_offset = block_group->key.objectid;
-				ideal_cache_percent = free_percent;
-			}
-
-			/*
-			 * The caching workers are limited to 2 threads, so we
-			 * can queue as much work as we care to.
-			 */
-			if (loop > LOOP_FIND_IDEAL) {
-				ret = cache_block_group(block_group, trans,
-							orig_root, 0);
-				BUG_ON(ret);
-			}
-
-			/*
-			 * If loop is set for cached only, try the next block
-			 * group.
-			 */
-			if (loop == LOOP_FIND_IDEAL)
-				goto loop;
+						orig_root, 0);
+			BUG_ON(ret < 0);
+			ret = 0;
 		}
 
-alloc:
 		if (unlikely(block_group->ro))
 			goto loop;
 
@@ -5606,11 +5684,6 @@ unclustered_alloc:
 		}
 checks:
 		search_start = stripe_align(root, offset);
-		/* move on to the next group */
-		if (search_start + num_bytes >= search_end) {
-			btrfs_add_free_space(used_block_group, offset, num_bytes);
-			goto loop;
-		}
 
 		/* move on to the next group */
 		if (search_start + num_bytes >
@@ -5661,9 +5734,7 @@ loop:
 	if (!ins->objectid && ++index < BTRFS_NR_RAID_TYPES)
 		goto search;
 
-	/* LOOP_FIND_IDEAL, only search caching/cached bg's, and don't wait for
-	 *			for them to make caching progress.  Also
-	 *			determine the best possible bg to cache
+	/*
 	 * LOOP_CACHING_NOWAIT, search partially cached block groups, kicking
 	 *			caching kthreads as we move along
 	 * LOOP_CACHING_WAIT, search everything, and wait if our bg is caching
@@ -5673,50 +5744,17 @@ loop:
 	 */
 	if (!ins->objectid && loop < LOOP_NO_EMPTY_SIZE) {
 		index = 0;
-		if (loop == LOOP_FIND_IDEAL && found_uncached_bg) {
-			found_uncached_bg = false;
-			loop++;
-			if (!ideal_cache_percent)
-				goto search;
-
-			/*
-			 * 1 of the following 2 things have happened so far
-			 *
-			 * 1) We found an ideal block group for caching that
-			 * is mostly full and will cache quickly, so we might
-			 * as well wait for it.
-			 *
-			 * 2) We searched for cached only and we didn't find
-			 * anything, and we didn't start any caching kthreads
-			 * either, so chances are we will loop through and
-			 * start a couple caching kthreads, and then come back
-			 * around and just wait for them.  This will be slower
-			 * because we will have 2 caching kthreads reading at
-			 * the same time when we could have just started one
-			 * and waited for it to get far enough to give us an
-			 * allocation, so go ahead and go to the wait caching
-			 * loop.
-			 */
-			loop = LOOP_CACHING_WAIT;
-			search_start = ideal_cache_offset;
-			ideal_cache_percent = 0;
-			goto ideal_cache;
-		} else if (loop == LOOP_FIND_IDEAL) {
-			/*
-			 * Didn't find a uncached bg, wait on anything we find
-			 * next.
-			 */
-			loop = LOOP_CACHING_WAIT;
-			goto search;
-		}
-
 		loop++;
-
 		if (loop == LOOP_ALLOC_CHUNK) {
 		       if (allowed_chunk_alloc) {
 				ret = do_chunk_alloc(trans, root, num_bytes +
 						     2 * 1024 * 1024, data,
 						     CHUNK_ALLOC_LIMITED);
+				if (ret < 0) {
+					btrfs_abort_transaction(trans,
+								root, ret);
+					goto out;
+				}
 				allowed_chunk_alloc = 0;
 				if (ret == 1)
 					done_chunk_alloc = 1;
@@ -5745,6 +5783,7 @@ loop:
 	} else if (ins->objectid) {
 		ret = 0;
 	}
+out:
 
 	return ret;
 }
@@ -5798,12 +5837,10 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 num_bytes, u64 min_alloc_size,
 			 u64 empty_size, u64 hint_byte,
-			 u64 search_end, struct btrfs_key *ins,
-			 u64 data)
+			 struct btrfs_key *ins, u64 data)
 {
 	bool final_tried = false;
 	int ret;
-	u64 search_start = 0;
 
 	data = btrfs_get_alloc_profile(root, data);
 again:
@@ -5811,23 +5848,31 @@ again:
 	 * the only place that sets empty_size is btrfs_realloc_node, which
 	 * is not called recursively on allocations
 	 */
-	if (empty_size || root->ref_cows)
+	if (empty_size || root->ref_cows) {
 		ret = do_chunk_alloc(trans, root->fs_info->extent_root,
 				     num_bytes + 2 * 1024 * 1024, data,
 				     CHUNK_ALLOC_NO_FORCE);
+		if (ret < 0 && ret != -ENOSPC) {
+			btrfs_abort_transaction(trans, root, ret);
+			return ret;
+		}
+	}
 
 	WARN_ON(num_bytes < root->sectorsize);
 	ret = find_free_extent(trans, root, num_bytes, empty_size,
-			       search_start, search_end, hint_byte,
-			       ins, data);
+			       hint_byte, ins, data);
 
 	if (ret == -ENOSPC) {
 		if (!final_tried) {
 			num_bytes = num_bytes >> 1;
 			num_bytes = num_bytes & ~(root->sectorsize - 1);
 			num_bytes = max(num_bytes, min_alloc_size);
-			do_chunk_alloc(trans, root->fs_info->extent_root,
+			ret = do_chunk_alloc(trans, root->fs_info->extent_root,
 				       num_bytes, data, CHUNK_ALLOC_FORCE);
+			if (ret < 0 && ret != -ENOSPC) {
+				btrfs_abort_transaction(trans, root, ret);
+				return ret;
+			}
 			if (num_bytes == min_alloc_size)
 				final_tried = true;
 			goto again;
@@ -5838,7 +5883,8 @@ again:
 			printk(KERN_ERR "btrfs allocation failed flags %llu, "
 			       "wanted %llu\n", (unsigned long long)data,
 			       (unsigned long long)num_bytes);
-			dump_space_info(sinfo, num_bytes, 1);
+			if (sinfo)
+				dump_space_info(sinfo, num_bytes, 1);
 		}
 	}
 
@@ -5917,7 +5963,10 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
 				      ins, size);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_free_path(path);
+		return ret;
+	}
 
 	leaf = path->nodes[0];
 	extent_item = btrfs_item_ptr(leaf, path->slots[0],
@@ -5947,7 +5996,7 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	btrfs_free_path(path);
 
 	ret = update_block_group(trans, root, ins->objectid, ins->offset, 1);
-	if (ret) {
+	if (ret) { /* -ENOENT, logic error */
 		printk(KERN_ERR "btrfs update block group failed for %llu "
 		       "%llu\n", (unsigned long long)ins->objectid,
 		       (unsigned long long)ins->offset);
@@ -5978,7 +6027,10 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
 				      ins, size);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_free_path(path);
+		return ret;
+	}
 
 	leaf = path->nodes[0];
 	extent_item = btrfs_item_ptr(leaf, path->slots[0],
@@ -6008,7 +6060,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	btrfs_free_path(path);
 
 	ret = update_block_group(trans, root, ins->objectid, ins->offset, 1);
-	if (ret) {
+	if (ret) { /* -ENOENT, logic error */
 		printk(KERN_ERR "btrfs update block group failed for %llu "
 		       "%llu\n", (unsigned long long)ins->objectid,
 		       (unsigned long long)ins->offset);
@@ -6056,28 +6108,28 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 	if (!caching_ctl) {
 		BUG_ON(!block_group_cache_done(block_group));
 		ret = btrfs_remove_free_space(block_group, start, num_bytes);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	} else {
 		mutex_lock(&caching_ctl->mutex);
 
 		if (start >= caching_ctl->progress) {
 			ret = add_excluded_extent(root, start, num_bytes);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 		} else if (start + num_bytes <= caching_ctl->progress) {
 			ret = btrfs_remove_free_space(block_group,
 						      start, num_bytes);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 		} else {
 			num_bytes = caching_ctl->progress - start;
 			ret = btrfs_remove_free_space(block_group,
 						      start, num_bytes);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 
 			start = caching_ctl->progress;
 			num_bytes = ins->objectid + ins->offset -
 				    caching_ctl->progress;
 			ret = add_excluded_extent(root, start, num_bytes);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 		}
 
 		mutex_unlock(&caching_ctl->mutex);
@@ -6086,7 +6138,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_update_reserved_bytes(block_group, ins->offset,
 					  RESERVE_ALLOC_NO_ACCOUNT);
-	BUG_ON(ret);
+	BUG_ON(ret); /* logic error */
 	btrfs_put_block_group(block_group);
 	ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
 					 0, owner, offset, ins, 1);
@@ -6107,6 +6159,7 @@ struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
 	clean_tree_block(trans, root, buf);
+	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
 
 	btrfs_set_lock_blocking(buf);
 	btrfs_set_buffer_uptodate(buf);
@@ -6214,7 +6267,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 		return ERR_CAST(block_rsv);
 
 	ret = btrfs_reserve_extent(trans, root, blocksize, blocksize,
-				   empty_size, hint, (u64)-1, &ins, 0);
+				   empty_size, hint, &ins, 0);
 	if (ret) {
 		unuse_block_rsv(root->fs_info, block_rsv, blocksize);
 		return ERR_PTR(ret);
@@ -6222,7 +6275,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 
 	buf = btrfs_init_new_buffer(trans, root, ins.objectid,
 				    blocksize, level);
-	BUG_ON(IS_ERR(buf));
+	BUG_ON(IS_ERR(buf)); /* -ENOMEM */
 
 	if (root_objectid == BTRFS_TREE_RELOC_OBJECTID) {
 		if (parent == 0)
@@ -6234,7 +6287,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 	if (root_objectid != BTRFS_TREE_LOG_OBJECTID) {
 		struct btrfs_delayed_extent_op *extent_op;
 		extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
-		BUG_ON(!extent_op);
+		BUG_ON(!extent_op); /* -ENOMEM */
 		if (key)
 			memcpy(&extent_op->key, key, sizeof(extent_op->key));
 		else
@@ -6249,7 +6302,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 					ins.offset, parent, root_objectid,
 					level, BTRFS_ADD_DELAYED_EXTENT,
 					extent_op, for_cow);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 	return buf;
 }
@@ -6319,7 +6372,9 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
 		/* We don't lock the tree block, it's OK to be racy here */
 		ret = btrfs_lookup_extent_info(trans, root, bytenr, blocksize,
 					       &refs, &flags);
-		BUG_ON(ret);
+		/* We don't care about errors in readahead. */
+		if (ret < 0)
+			continue;
 		BUG_ON(refs == 0);
 
 		if (wc->stage == DROP_REFERENCE) {
@@ -6386,7 +6441,9 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 					       eb->start, eb->len,
 					       &wc->refs[level],
 					       &wc->flags[level]);
-		BUG_ON(ret);
+		BUG_ON(ret == -ENOMEM);
+		if (ret)
+			return ret;
 		BUG_ON(wc->refs[level] == 0);
 	}
 
@@ -6405,12 +6462,12 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 	if (!(wc->flags[level] & flag)) {
 		BUG_ON(!path->locks[level]);
 		ret = btrfs_inc_ref(trans, root, eb, 1, wc->for_reloc);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 		ret = btrfs_dec_ref(trans, root, eb, 0, wc->for_reloc);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 		ret = btrfs_set_disk_extent_flags(trans, root, eb->start,
 						  eb->len, flag, 0);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 		wc->flags[level] |= flag;
 	}
 
@@ -6482,7 +6539,11 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	ret = btrfs_lookup_extent_info(trans, root, bytenr, blocksize,
 				       &wc->refs[level - 1],
 				       &wc->flags[level - 1]);
-	BUG_ON(ret);
+	if (ret < 0) {
+		btrfs_tree_unlock(next);
+		return ret;
+	}
+
 	BUG_ON(wc->refs[level - 1] == 0);
 	*lookup_info = 0;
 
@@ -6551,7 +6612,7 @@ skip:
 
 		ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent,
 				root->root_key.objectid, level - 1, 0, 0);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 	btrfs_tree_unlock(next);
 	free_extent_buffer(next);
@@ -6609,7 +6670,10 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 						       eb->start, eb->len,
 						       &wc->refs[level],
 						       &wc->flags[level]);
-			BUG_ON(ret);
+			if (ret < 0) {
+				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				return ret;
+			}
 			BUG_ON(wc->refs[level] == 0);
 			if (wc->refs[level] == 1) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
@@ -6629,7 +6693,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			else
 				ret = btrfs_dec_ref(trans, root, eb, 0,
 						    wc->for_reloc);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM */
 		}
 		/* make block locked assertion in clean_tree_block happy */
 		if (!path->locks[level] &&
@@ -6738,7 +6802,7 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
  * also make sure backrefs for the shared block and all lower level
  * blocks are properly updated.
  */
-void btrfs_drop_snapshot(struct btrfs_root *root,
+int btrfs_drop_snapshot(struct btrfs_root *root,
 			 struct btrfs_block_rsv *block_rsv, int update_ref,
 			 int for_reloc)
 {
@@ -6766,7 +6830,10 @@ void btrfs_drop_snapshot(struct btrfs_root *root,
 	}
 
 	trans = btrfs_start_transaction(tree_root, 0);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto out_free;
+	}
 
 	if (block_rsv)
 		trans->block_rsv = block_rsv;
@@ -6791,7 +6858,7 @@ void btrfs_drop_snapshot(struct btrfs_root *root,
 		path->lowest_level = 0;
 		if (ret < 0) {
 			err = ret;
-			goto out_free;
+			goto out_end_trans;
 		}
 		WARN_ON(ret > 0);
 
@@ -6811,7 +6878,10 @@ void btrfs_drop_snapshot(struct btrfs_root *root,
 						path->nodes[level]->len,
 						&wc->refs[level],
 						&wc->flags[level]);
-			BUG_ON(ret);
+			if (ret < 0) {
+				err = ret;
+				goto out_end_trans;
+			}
 			BUG_ON(wc->refs[level] == 0);
 
 			if (level == root_item->drop_level)
@@ -6862,26 +6932,40 @@ void btrfs_drop_snapshot(struct btrfs_root *root,
 			ret = btrfs_update_root(trans, tree_root,
 						&root->root_key,
 						root_item);
-			BUG_ON(ret);
+			if (ret) {
+				btrfs_abort_transaction(trans, tree_root, ret);
+				err = ret;
+				goto out_end_trans;
+			}
 
 			btrfs_end_transaction_throttle(trans, tree_root);
 			trans = btrfs_start_transaction(tree_root, 0);
-			BUG_ON(IS_ERR(trans));
+			if (IS_ERR(trans)) {
+				err = PTR_ERR(trans);
+				goto out_free;
+			}
 			if (block_rsv)
 				trans->block_rsv = block_rsv;
 		}
 	}
 	btrfs_release_path(path);
-	BUG_ON(err);
+	if (err)
+		goto out_end_trans;
 
 	ret = btrfs_del_root(trans, tree_root, &root->root_key);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, tree_root, ret);
+		goto out_end_trans;
+	}
 
 	if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
 		ret = btrfs_find_last_root(tree_root, root->root_key.objectid,
 					   NULL, NULL);
-		BUG_ON(ret < 0);
-		if (ret > 0) {
+		if (ret < 0) {
+			btrfs_abort_transaction(trans, tree_root, ret);
+			err = ret;
+			goto out_end_trans;
+		} else if (ret > 0) {
 			/* if we fail to delete the orphan item this time
 			 * around, it'll get picked up the next time.
 			 *
@@ -6899,14 +6983,15 @@ void btrfs_drop_snapshot(struct btrfs_root *root,
 		free_extent_buffer(root->commit_root);
 		kfree(root);
 	}
-out_free:
+out_end_trans:
 	btrfs_end_transaction_throttle(trans, tree_root);
+out_free:
 	kfree(wc);
 	btrfs_free_path(path);
 out:
 	if (err)
 		btrfs_std_error(root->fs_info, err);
-	return;
+	return err;
 }
 
 /*
@@ -6983,31 +7068,15 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
 {
 	u64 num_devices;
-	u64 stripped = BTRFS_BLOCK_GROUP_RAID0 |
-		BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
+	u64 stripped;
 
-	if (root->fs_info->balance_ctl) {
-		struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
-		u64 tgt = 0;
-
-		/* pick restriper's target profile and return */
-		if (flags & BTRFS_BLOCK_GROUP_DATA &&
-		    bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) {
-			tgt = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
-		} else if (flags & BTRFS_BLOCK_GROUP_SYSTEM &&
-			   bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
-			tgt = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
-		} else if (flags & BTRFS_BLOCK_GROUP_METADATA &&
-			   bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) {
-			tgt = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
-		}
-
-		if (tgt) {
-			/* extended -> chunk profile */
-			tgt &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-			return tgt;
-		}
-	}
+	/*
+	 * if restripe for this chunk_type is on pick target profile and
+	 * return, otherwise do the usual balance
+	 */
+	stripped = get_restripe_target(root->fs_info, flags);
+	if (stripped)
+		return extended_to_chunk(stripped);
 
 	/*
 	 * we add in the count of missing devices because we want
@@ -7017,6 +7086,9 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
 	num_devices = root->fs_info->fs_devices->rw_devices +
 		root->fs_info->fs_devices->missing_devices;
 
+	stripped = BTRFS_BLOCK_GROUP_RAID0 |
+		BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
+
 	if (num_devices == 1) {
 		stripped |= BTRFS_BLOCK_GROUP_DUP;
 		stripped = flags & ~stripped;
@@ -7029,7 +7101,6 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
 		if (flags & (BTRFS_BLOCK_GROUP_RAID1 |
 			     BTRFS_BLOCK_GROUP_RAID10))
 			return stripped | BTRFS_BLOCK_GROUP_DUP;
-		return flags;
 	} else {
 		/* they already had raid on here, just return */
 		if (flags & stripped)
@@ -7042,9 +7113,9 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
 		if (flags & BTRFS_BLOCK_GROUP_DUP)
 			return stripped | BTRFS_BLOCK_GROUP_RAID1;
 
-		/* turn single device chunks into raid0 */
-		return stripped | BTRFS_BLOCK_GROUP_RAID0;
+		/* this is drive concat, leave it alone */
 	}
+
 	return flags;
 }
 
@@ -7103,12 +7174,16 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 	BUG_ON(cache->ro);
 
 	trans = btrfs_join_transaction(root);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 
 	alloc_flags = update_block_group_flags(root, cache->flags);
-	if (alloc_flags != cache->flags)
-		do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
-			       CHUNK_ALLOC_FORCE);
+	if (alloc_flags != cache->flags) {
+		ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+				     CHUNK_ALLOC_FORCE);
+		if (ret < 0)
+			goto out;
+	}
 
 	ret = set_block_group_ro(cache, 0);
 	if (!ret)
@@ -7188,7 +7263,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 	return free_bytes;
 }
 
-int btrfs_set_block_group_rw(struct btrfs_root *root,
+void btrfs_set_block_group_rw(struct btrfs_root *root,
 			      struct btrfs_block_group_cache *cache)
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
@@ -7204,7 +7279,6 @@ int btrfs_set_block_group_rw(struct btrfs_root *root,
 	cache->ro = 0;
 	spin_unlock(&cache->lock);
 	spin_unlock(&sinfo->lock);
-	return 0;
 }
 
 /*
@@ -7222,6 +7296,7 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	u64 min_free;
 	u64 dev_min = 1;
 	u64 dev_nr = 0;
+	u64 target;
 	int index;
 	int full = 0;
 	int ret = 0;
@@ -7262,13 +7337,11 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	/*
 	 * ok we don't have enough space, but maybe we have free space on our
 	 * devices to allocate new chunks for relocation, so loop through our
-	 * alloc devices and guess if we have enough space.  However, if we
-	 * were marked as full, then we know there aren't enough chunks, and we
-	 * can just return.
+	 * alloc devices and guess if we have enough space.  if this block
+	 * group is going to be restriped, run checks against the target
+	 * profile instead of the current one.
 	 */
 	ret = -1;
-	if (full)
-		goto out;
 
 	/*
 	 * index:
@@ -7278,7 +7351,20 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	 *      3: raid0
 	 *      4: single
 	 */
-	index = get_block_group_index(block_group);
+	target = get_restripe_target(root->fs_info, block_group->flags);
+	if (target) {
+		index = __get_block_group_index(extended_to_chunk(target));
+	} else {
+		/*
+		 * this is just a balance, so if we were marked as full
+		 * we know there is no space for a new chunk
+		 */
+		if (full)
+			goto out;
+
+		index = get_block_group_index(block_group);
+	}
+
 	if (index == 0) {
 		dev_min = 4;
 		/* Divide by 2 */
@@ -7572,7 +7658,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		ret = update_space_info(info, cache->flags, found_key.offset,
 					btrfs_block_group_used(&cache->item),
 					&space_info);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 		cache->space_info = space_info;
 		spin_lock(&cache->space_info->lock);
 		cache->space_info->bytes_readonly += cache->bytes_super;
@@ -7581,7 +7667,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		__link_block_group(space_info, cache);
 
 		ret = btrfs_add_block_group_cache(root->fs_info, cache);
-		BUG_ON(ret);
+		BUG_ON(ret); /* Logic error */
 
 		set_avail_alloc_bits(root->fs_info, cache->flags);
 		if (btrfs_chunk_readonly(root, cache->key.objectid))
@@ -7663,7 +7749,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 
 	ret = update_space_info(root->fs_info, cache->flags, size, bytes_used,
 				&cache->space_info);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -ENOMEM */
 	update_global_block_rsv(root->fs_info);
 
 	spin_lock(&cache->space_info->lock);
@@ -7673,11 +7759,14 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	__link_block_group(cache->space_info, cache);
 
 	ret = btrfs_add_block_group_cache(root->fs_info, cache);
-	BUG_ON(ret);
+	BUG_ON(ret); /* Logic error */
 
 	ret = btrfs_insert_item(trans, extent_root, &cache->key, &cache->item,
 				sizeof(cache->item));
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, extent_root, ret);
+		return ret;
+	}
 
 	set_avail_alloc_bits(extent_root->fs_info, type);
 
@@ -7686,11 +7775,8 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 
 static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 {
-	u64 extra_flags = flags & BTRFS_BLOCK_GROUP_PROFILE_MASK;
-
-	/* chunk -> extended profile */
-	if (extra_flags == 0)
-		extra_flags = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+	u64 extra_flags = chunk_to_extended(flags) &
+				BTRFS_EXTENDED_PROFILE_MASK;
 
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
 		fs_info->avail_data_alloc_bits &= ~extra_flags;
@@ -7758,7 +7844,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	inode = lookup_free_space_inode(tree_root, block_group, path);
 	if (!IS_ERR(inode)) {
 		ret = btrfs_orphan_add(trans, inode);
-		BUG_ON(ret);
+		if (ret) {
+			btrfs_add_delayed_iput(inode);
+			goto out;
+		}
 		clear_nlink(inode);
 		/* One for the block groups ref */
 		spin_lock(&block_group->lock);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2862454bcdb3..8d904dd7ea9f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -19,6 +19,7 @@
 #include "btrfs_inode.h"
 #include "volumes.h"
 #include "check-integrity.h"
+#include "locking.h"
 
 static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;
@@ -53,6 +54,13 @@ struct extent_page_data {
 	unsigned int sync_io:1;
 };
 
+static noinline void flush_write_bio(void *data);
+static inline struct btrfs_fs_info *
+tree_fs_info(struct extent_io_tree *tree)
+{
+	return btrfs_sb(tree->mapping->host->i_sb);
+}
+
 int __init extent_io_init(void)
 {
 	extent_state_cache = kmem_cache_create("extent_state",
@@ -136,6 +144,7 @@ static struct extent_state *alloc_extent_state(gfp_t mask)
 #endif
 	atomic_set(&state->refs, 1);
 	init_waitqueue_head(&state->wq);
+	trace_alloc_extent_state(state, mask, _RET_IP_);
 	return state;
 }
 
@@ -153,6 +162,7 @@ void free_extent_state(struct extent_state *state)
 		list_del(&state->leak_list);
 		spin_unlock_irqrestore(&leak_lock, flags);
 #endif
+		trace_free_extent_state(state, _RET_IP_);
 		kmem_cache_free(extent_state_cache, state);
 	}
 }
@@ -439,6 +449,13 @@ alloc_extent_state_atomic(struct extent_state *prealloc)
 	return prealloc;
 }
 
+void extent_io_tree_panic(struct extent_io_tree *tree, int err)
+{
+	btrfs_panic(tree_fs_info(tree), err, "Locking error: "
+		    "Extent tree was modified by another "
+		    "thread while locked.");
+}
+
 /*
  * clear some bits on a range in the tree.  This may require splitting
  * or inserting elements in the tree, so the gfp mask is used to
@@ -449,8 +466,7 @@ alloc_extent_state_atomic(struct extent_state *prealloc)
  *
  * the range [start, end] is inclusive.
  *
- * This takes the tree lock, and returns < 0 on error, > 0 if any of the
- * bits were already set, or zero if none of the bits were already set.
+ * This takes the tree lock, and returns 0 on success and < 0 on error.
  */
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		     int bits, int wake, int delete,
@@ -464,7 +480,6 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	struct rb_node *node;
 	u64 last_end;
 	int err;
-	int set = 0;
 	int clear = 0;
 
 	if (delete)
@@ -542,12 +557,14 @@ hit_next:
 		prealloc = alloc_extent_state_atomic(prealloc);
 		BUG_ON(!prealloc);
 		err = split_state(tree, state, prealloc, start);
-		BUG_ON(err == -EEXIST);
+		if (err)
+			extent_io_tree_panic(tree, err);
+
 		prealloc = NULL;
 		if (err)
 			goto out;
 		if (state->end <= end) {
-			set |= clear_state_bit(tree, state, &bits, wake);
+			clear_state_bit(tree, state, &bits, wake);
 			if (last_end == (u64)-1)
 				goto out;
 			start = last_end + 1;
@@ -564,17 +581,19 @@ hit_next:
 		prealloc = alloc_extent_state_atomic(prealloc);
 		BUG_ON(!prealloc);
 		err = split_state(tree, state, prealloc, end + 1);
-		BUG_ON(err == -EEXIST);
+		if (err)
+			extent_io_tree_panic(tree, err);
+
 		if (wake)
 			wake_up(&state->wq);
 
-		set |= clear_state_bit(tree, prealloc, &bits, wake);
+		clear_state_bit(tree, prealloc, &bits, wake);
 
 		prealloc = NULL;
 		goto out;
 	}
 
-	set |= clear_state_bit(tree, state, &bits, wake);
+	clear_state_bit(tree, state, &bits, wake);
 next:
 	if (last_end == (u64)-1)
 		goto out;
@@ -591,7 +610,7 @@ out:
 	if (prealloc)
 		free_extent_state(prealloc);
 
-	return set;
+	return 0;
 
 search_again:
 	if (start > end)
@@ -602,8 +621,8 @@ search_again:
 	goto again;
 }
 
-static int wait_on_state(struct extent_io_tree *tree,
-			 struct extent_state *state)
+static void wait_on_state(struct extent_io_tree *tree,
+			  struct extent_state *state)
 		__releases(tree->lock)
 		__acquires(tree->lock)
 {
@@ -613,7 +632,6 @@ static int wait_on_state(struct extent_io_tree *tree,
 	schedule();
 	spin_lock(&tree->lock);
 	finish_wait(&state->wq, &wait);
-	return 0;
 }
 
 /*
@@ -621,7 +639,7 @@ static int wait_on_state(struct extent_io_tree *tree,
  * The range [start, end] is inclusive.
  * The tree lock is taken by this function
  */
-int wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int bits)
+void wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int bits)
 {
 	struct extent_state *state;
 	struct rb_node *node;
@@ -658,7 +676,6 @@ again:
 	}
 out:
 	spin_unlock(&tree->lock);
-	return 0;
 }
 
 static void set_state_bits(struct extent_io_tree *tree,
@@ -706,9 +723,10 @@ static void uncache_state(struct extent_state **cached_ptr)
  * [start, end] is inclusive This takes the tree lock.
  */
 
-int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   int bits, int exclusive_bits, u64 *failed_start,
-		   struct extent_state **cached_state, gfp_t mask)
+static int __must_check
+__set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		 int bits, int exclusive_bits, u64 *failed_start,
+		 struct extent_state **cached_state, gfp_t mask)
 {
 	struct extent_state *state;
 	struct extent_state *prealloc = NULL;
@@ -742,8 +760,10 @@ again:
 		prealloc = alloc_extent_state_atomic(prealloc);
 		BUG_ON(!prealloc);
 		err = insert_state(tree, prealloc, start, end, &bits);
+		if (err)
+			extent_io_tree_panic(tree, err);
+
 		prealloc = NULL;
-		BUG_ON(err == -EEXIST);
 		goto out;
 	}
 	state = rb_entry(node, struct extent_state, rb_node);
@@ -809,7 +829,9 @@ hit_next:
 		prealloc = alloc_extent_state_atomic(prealloc);
 		BUG_ON(!prealloc);
 		err = split_state(tree, state, prealloc, start);
-		BUG_ON(err == -EEXIST);
+		if (err)
+			extent_io_tree_panic(tree, err);
+
 		prealloc = NULL;
 		if (err)
 			goto out;
@@ -846,12 +868,9 @@ hit_next:
 		 */
 		err = insert_state(tree, prealloc, start, this_end,
 				   &bits);
-		BUG_ON(err == -EEXIST);
-		if (err) {
-			free_extent_state(prealloc);
-			prealloc = NULL;
-			goto out;
-		}
+		if (err)
+			extent_io_tree_panic(tree, err);
+
 		cache_state(prealloc, cached_state);
 		prealloc = NULL;
 		start = this_end + 1;
@@ -873,7 +892,8 @@ hit_next:
 		prealloc = alloc_extent_state_atomic(prealloc);
 		BUG_ON(!prealloc);
 		err = split_state(tree, state, prealloc, end + 1);
-		BUG_ON(err == -EEXIST);
+		if (err)
+			extent_io_tree_panic(tree, err);
 
 		set_state_bits(tree, prealloc, &bits);
 		cache_state(prealloc, cached_state);
@@ -900,6 +920,15 @@ search_again:
 	goto again;
 }
 
+int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int bits,
+		   u64 *failed_start, struct extent_state **cached_state,
+		   gfp_t mask)
+{
+	return __set_extent_bit(tree, start, end, bits, 0, failed_start,
+				cached_state, mask);
+}
+
+
 /**
  * convert_extent - convert all bits in a given range from one bit to another
  * @tree:	the io tree to search
@@ -946,7 +975,8 @@ again:
 		}
 		err = insert_state(tree, prealloc, start, end, &bits);
 		prealloc = NULL;
-		BUG_ON(err == -EEXIST);
+		if (err)
+			extent_io_tree_panic(tree, err);
 		goto out;
 	}
 	state = rb_entry(node, struct extent_state, rb_node);
@@ -1002,7 +1032,8 @@ hit_next:
 			goto out;
 		}
 		err = split_state(tree, state, prealloc, start);
-		BUG_ON(err == -EEXIST);
+		if (err)
+			extent_io_tree_panic(tree, err);
 		prealloc = NULL;
 		if (err)
 			goto out;
@@ -1041,12 +1072,8 @@ hit_next:
 		 */
 		err = insert_state(tree, prealloc, start, this_end,
 				   &bits);
-		BUG_ON(err == -EEXIST);
-		if (err) {
-			free_extent_state(prealloc);
-			prealloc = NULL;
-			goto out;
-		}
+		if (err)
+			extent_io_tree_panic(tree, err);
 		prealloc = NULL;
 		start = this_end + 1;
 		goto search_again;
@@ -1065,7 +1092,8 @@ hit_next:
 		}
 
 		err = split_state(tree, state, prealloc, end + 1);
-		BUG_ON(err == -EEXIST);
+		if (err)
+			extent_io_tree_panic(tree, err);
 
 		set_state_bits(tree, prealloc, &bits);
 		clear_state_bit(tree, prealloc, &clear_bits, 0);
@@ -1095,14 +1123,14 @@ search_again:
 int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 		     gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, EXTENT_DIRTY, 0, NULL,
+	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
 			      NULL, mask);
 }
 
 int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 		    int bits, gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, bits, 0, NULL,
+	return set_extent_bit(tree, start, end, bits, NULL,
 			      NULL, mask);
 }
 
@@ -1117,7 +1145,7 @@ int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
 {
 	return set_extent_bit(tree, start, end,
 			      EXTENT_DELALLOC | EXTENT_UPTODATE,
-			      0, NULL, cached_state, mask);
+			      NULL, cached_state, mask);
 }
 
 int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1131,7 +1159,7 @@ int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
 		     gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, EXTENT_NEW, 0, NULL,
+	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL,
 			      NULL, mask);
 }
 
@@ -1139,7 +1167,7 @@ int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask)
 {
 	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0,
-			      NULL, cached_state, mask);
+			      cached_state, mask);
 }
 
 static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
@@ -1155,42 +1183,40 @@ static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
  * us if waiting is desired.
  */
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     int bits, struct extent_state **cached_state, gfp_t mask)
+		     int bits, struct extent_state **cached_state)
 {
 	int err;
 	u64 failed_start;
 	while (1) {
-		err = set_extent_bit(tree, start, end, EXTENT_LOCKED | bits,
-				     EXTENT_LOCKED, &failed_start,
-				     cached_state, mask);
-		if (err == -EEXIST && (mask & __GFP_WAIT)) {
+		err = __set_extent_bit(tree, start, end, EXTENT_LOCKED | bits,
+				       EXTENT_LOCKED, &failed_start,
+				       cached_state, GFP_NOFS);
+		if (err == -EEXIST) {
 			wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED);
 			start = failed_start;
-		} else {
+		} else
 			break;
-		}
 		WARN_ON(start > end);
 	}
 	return err;
 }
 
-int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask)
+int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 {
-	return lock_extent_bits(tree, start, end, 0, NULL, mask);
+	return lock_extent_bits(tree, start, end, 0, NULL);
 }
 
-int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
-		    gfp_t mask)
+int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 {
 	int err;
 	u64 failed_start;
 
-	err = set_extent_bit(tree, start, end, EXTENT_LOCKED, EXTENT_LOCKED,
-			     &failed_start, NULL, mask);
+	err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, EXTENT_LOCKED,
+			       &failed_start, NULL, GFP_NOFS);
 	if (err == -EEXIST) {
 		if (failed_start > start)
 			clear_extent_bit(tree, start, failed_start - 1,
-					 EXTENT_LOCKED, 1, 0, NULL, mask);
+					 EXTENT_LOCKED, 1, 0, NULL, GFP_NOFS);
 		return 0;
 	}
 	return 1;
@@ -1203,10 +1229,10 @@ int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
 				mask);
 }
 
-int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask)
+int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 {
 	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL,
-				mask);
+				GFP_NOFS);
 }
 
 /*
@@ -1220,7 +1246,7 @@ static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 
 	while (index <= end_index) {
 		page = find_get_page(tree->mapping, index);
-		BUG_ON(!page);
+		BUG_ON(!page); /* Pages should be in the extent_io_tree */
 		set_page_writeback(page);
 		page_cache_release(page);
 		index++;
@@ -1343,9 +1369,9 @@ out:
 	return found;
 }
 
-static noinline int __unlock_for_delalloc(struct inode *inode,
-					  struct page *locked_page,
-					  u64 start, u64 end)
+static noinline void __unlock_for_delalloc(struct inode *inode,
+					   struct page *locked_page,
+					   u64 start, u64 end)
 {
 	int ret;
 	struct page *pages[16];
@@ -1355,7 +1381,7 @@ static noinline int __unlock_for_delalloc(struct inode *inode,
 	int i;
 
 	if (index == locked_page->index && end_index == index)
-		return 0;
+		return;
 
 	while (nr_pages > 0) {
 		ret = find_get_pages_contig(inode->i_mapping, index,
@@ -1370,7 +1396,6 @@ static noinline int __unlock_for_delalloc(struct inode *inode,
 		index += ret;
 		cond_resched();
 	}
-	return 0;
 }
 
 static noinline int lock_delalloc_pages(struct inode *inode,
@@ -1500,11 +1525,10 @@ again:
 			goto out_failed;
 		}
 	}
-	BUG_ON(ret);
+	BUG_ON(ret); /* Only valid values are 0 and -EAGAIN */
 
 	/* step three, lock the state bits for the whole range */
-	lock_extent_bits(tree, delalloc_start, delalloc_end,
-			 0, &cached_state, GFP_NOFS);
+	lock_extent_bits(tree, delalloc_start, delalloc_end, 0, &cached_state);
 
 	/* then test to make sure it is all still delalloc */
 	ret = test_range_bit(tree, delalloc_start, delalloc_end,
@@ -1761,39 +1785,34 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
  * helper function to set a given page up to date if all the
  * extents in the tree for that page are up to date
  */
-static int check_page_uptodate(struct extent_io_tree *tree,
-			       struct page *page)
+static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
 {
 	u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
 	u64 end = start + PAGE_CACHE_SIZE - 1;
 	if (test_range_bit(tree, start, end, EXTENT_UPTODATE, 1, NULL))
 		SetPageUptodate(page);
-	return 0;
 }
 
 /*
  * helper function to unlock a page if all the extents in the tree
  * for that page are unlocked
  */
-static int check_page_locked(struct extent_io_tree *tree,
-			     struct page *page)
+static void check_page_locked(struct extent_io_tree *tree, struct page *page)
 {
 	u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
 	u64 end = start + PAGE_CACHE_SIZE - 1;
 	if (!test_range_bit(tree, start, end, EXTENT_LOCKED, 0, NULL))
 		unlock_page(page);
-	return 0;
 }
 
 /*
  * helper function to end page writeback if all the extents
  * in the tree for that page are done with writeback
  */
-static int check_page_writeback(struct extent_io_tree *tree,
-			     struct page *page)
+static void check_page_writeback(struct extent_io_tree *tree,
+				 struct page *page)
 {
 	end_page_writeback(page);
-	return 0;
 }
 
 /*
@@ -1912,6 +1931,26 @@ int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start,
 	return 0;
 }
 
+int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
+			 int mirror_num)
+{
+	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
+	u64 start = eb->start;
+	unsigned long i, num_pages = num_extent_pages(eb->start, eb->len);
+	int ret;
+
+	for (i = 0; i < num_pages; i++) {
+		struct page *p = extent_buffer_page(eb, i);
+		ret = repair_io_failure(map_tree, start, PAGE_CACHE_SIZE,
+					start, p, mirror_num);
+		if (ret)
+			break;
+		start += PAGE_CACHE_SIZE;
+	}
+
+	return ret;
+}
+
 /*
  * each time an IO finishes, we do a fast check in the IO failure tree
  * to see if we need to process or clean up an io_failure_record
@@ -2258,6 +2297,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 	u64 start;
 	u64 end;
 	int whole_page;
+	int failed_mirror;
 	int ret;
 
 	if (err)
@@ -2304,9 +2344,16 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 			else
 				clean_io_failure(start, page);
 		}
-		if (!uptodate) {
-			int failed_mirror;
+
+		if (!uptodate)
 			failed_mirror = (int)(unsigned long)bio->bi_bdev;
+
+		if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) {
+			ret = tree->ops->readpage_io_failed_hook(page, failed_mirror);
+			if (!ret && !err &&
+			    test_bit(BIO_UPTODATE, &bio->bi_flags))
+				uptodate = 1;
+		} else if (!uptodate) {
 			/*
 			 * The generic bio_readpage_error handles errors the
 			 * following way: If possible, new read requests are
@@ -2320,7 +2367,6 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 			ret = bio_readpage_error(bio, page, start, end,
 							failed_mirror, NULL);
 			if (ret == 0) {
-error_handled:
 				uptodate =
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
@@ -2328,16 +2374,9 @@ error_handled:
 				uncache_state(&cached);
 				continue;
 			}
-			if (tree->ops && tree->ops->readpage_io_failed_hook) {
-				ret = tree->ops->readpage_io_failed_hook(
-							bio, page, start, end,
-							failed_mirror, state);
-				if (ret == 0)
-					goto error_handled;
-			}
 		}
 
-		if (uptodate) {
+		if (uptodate && tree->track_uptodate) {
 			set_extent_uptodate(tree, start, end, &cached,
 					    GFP_ATOMIC);
 		}
@@ -2386,8 +2425,12 @@ btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
 	return bio;
 }
 
-static int submit_one_bio(int rw, struct bio *bio, int mirror_num,
-			  unsigned long bio_flags)
+/*
+ * Since writes are async, they will only return -ENOMEM.
+ * Reads can return the full range of I/O error conditions.
+ */
+static int __must_check submit_one_bio(int rw, struct bio *bio,
+				       int mirror_num, unsigned long bio_flags)
 {
 	int ret = 0;
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
@@ -2413,6 +2456,19 @@ static int submit_one_bio(int rw, struct bio *bio, int mirror_num,
 	return ret;
 }
 
+static int merge_bio(struct extent_io_tree *tree, struct page *page,
+		     unsigned long offset, size_t size, struct bio *bio,
+		     unsigned long bio_flags)
+{
+	int ret = 0;
+	if (tree->ops && tree->ops->merge_bio_hook)
+		ret = tree->ops->merge_bio_hook(page, offset, size, bio,
+						bio_flags);
+	BUG_ON(ret < 0);
+	return ret;
+
+}
+
 static int submit_extent_page(int rw, struct extent_io_tree *tree,
 			      struct page *page, sector_t sector,
 			      size_t size, unsigned long offset,
@@ -2441,12 +2497,12 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 				sector;
 
 		if (prev_bio_flags != bio_flags || !contig ||
-		    (tree->ops && tree->ops->merge_bio_hook &&
-		     tree->ops->merge_bio_hook(page, offset, page_size, bio,
-					       bio_flags)) ||
+		    merge_bio(tree, page, offset, page_size, bio, bio_flags) ||
 		    bio_add_page(bio, page, page_size, offset) < page_size) {
 			ret = submit_one_bio(rw, bio, mirror_num,
 					     prev_bio_flags);
+			if (ret < 0)
+				return ret;
 			bio = NULL;
 		} else {
 			return 0;
@@ -2473,25 +2529,31 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 	return ret;
 }
 
-void set_page_extent_mapped(struct page *page)
+void attach_extent_buffer_page(struct extent_buffer *eb, struct page *page)
 {
 	if (!PagePrivate(page)) {
 		SetPagePrivate(page);
 		page_cache_get(page);
-		set_page_private(page, EXTENT_PAGE_PRIVATE);
+		set_page_private(page, (unsigned long)eb);
+	} else {
+		WARN_ON(page->private != (unsigned long)eb);
 	}
 }
 
-static void set_page_extent_head(struct page *page, unsigned long len)
+void set_page_extent_mapped(struct page *page)
 {
-	WARN_ON(!PagePrivate(page));
-	set_page_private(page, EXTENT_PAGE_PRIVATE_FIRST_PAGE | len << 2);
+	if (!PagePrivate(page)) {
+		SetPagePrivate(page);
+		page_cache_get(page);
+		set_page_private(page, EXTENT_PAGE_PRIVATE);
+	}
 }
 
 /*
  * basic readpage implementation.  Locked extent state structs are inserted
  * into the tree that are removed when the IO is done (by the end_io
  * handlers)
+ * XXX JDM: This needs looking at to ensure proper page locking
  */
 static int __extent_read_full_page(struct extent_io_tree *tree,
 				   struct page *page,
@@ -2531,11 +2593,11 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 
 	end = page_end;
 	while (1) {
-		lock_extent(tree, start, end, GFP_NOFS);
+		lock_extent(tree, start, end);
 		ordered = btrfs_lookup_ordered_extent(inode, start);
 		if (!ordered)
 			break;
-		unlock_extent(tree, start, end, GFP_NOFS);
+		unlock_extent(tree, start, end);
 		btrfs_start_ordered_extent(inode, ordered, 1);
 		btrfs_put_ordered_extent(ordered);
 	}
@@ -2572,7 +2634,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 				end - cur + 1, 0);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
-			unlock_extent(tree, cur, end, GFP_NOFS);
+			unlock_extent(tree, cur, end);
 			break;
 		}
 		extent_offset = cur - em->start;
@@ -2624,7 +2686,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
 			check_page_uptodate(tree, page);
-			unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -2634,7 +2696,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		 */
 		if (block_start == EXTENT_MAP_INLINE) {
 			SetPageError(page);
-			unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -2654,6 +2716,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
 					 this_bio_flag);
+			BUG_ON(ret == -ENOMEM);
 			nr++;
 			*bio_flags = this_bio_flag;
 		}
@@ -2795,7 +2858,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 						       delalloc_end,
 						       &page_started,
 						       &nr_written);
-			BUG_ON(ret);
+			/* File system has been set read-only */
+			if (ret) {
+				SetPageError(page);
+				goto done;
+			}
 			/*
 			 * delalloc_end is already one less than the total
 			 * length, so we don't subtract one from
@@ -2968,6 +3035,275 @@ done_unlocked:
 	return 0;
 }
 
+static int eb_wait(void *word)
+{
+	io_schedule();
+	return 0;
+}
+
+static void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
+{
+	wait_on_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK, eb_wait,
+		    TASK_UNINTERRUPTIBLE);
+}
+
+static int lock_extent_buffer_for_io(struct extent_buffer *eb,
+				     struct btrfs_fs_info *fs_info,
+				     struct extent_page_data *epd)
+{
+	unsigned long i, num_pages;
+	int flush = 0;
+	int ret = 0;
+
+	if (!btrfs_try_tree_write_lock(eb)) {
+		flush = 1;
+		flush_write_bio(epd);
+		btrfs_tree_lock(eb);
+	}
+
+	if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) {
+		btrfs_tree_unlock(eb);
+		if (!epd->sync_io)
+			return 0;
+		if (!flush) {
+			flush_write_bio(epd);
+			flush = 1;
+		}
+		while (1) {
+			wait_on_extent_buffer_writeback(eb);
+			btrfs_tree_lock(eb);
+			if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags))
+				break;
+			btrfs_tree_unlock(eb);
+		}
+	}
+
+	if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
+		set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
+		btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
+		spin_lock(&fs_info->delalloc_lock);
+		if (fs_info->dirty_metadata_bytes >= eb->len)
+			fs_info->dirty_metadata_bytes -= eb->len;
+		else
+			WARN_ON(1);
+		spin_unlock(&fs_info->delalloc_lock);
+		ret = 1;
+	}
+
+	btrfs_tree_unlock(eb);
+
+	if (!ret)
+		return ret;
+
+	num_pages = num_extent_pages(eb->start, eb->len);
+	for (i = 0; i < num_pages; i++) {
+		struct page *p = extent_buffer_page(eb, i);
+
+		if (!trylock_page(p)) {
+			if (!flush) {
+				flush_write_bio(epd);
+				flush = 1;
+			}
+			lock_page(p);
+		}
+	}
+
+	return ret;
+}
+
+static void end_extent_buffer_writeback(struct extent_buffer *eb)
+{
+	clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
+}
+
+static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
+{
+	int uptodate = err == 0;
+	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+	struct extent_buffer *eb;
+	int done;
+
+	do {
+		struct page *page = bvec->bv_page;
+
+		bvec--;
+		eb = (struct extent_buffer *)page->private;
+		BUG_ON(!eb);
+		done = atomic_dec_and_test(&eb->io_pages);
+
+		if (!uptodate || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+			set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+
+		end_page_writeback(page);
+
+		if (!done)
+			continue;
+
+		end_extent_buffer_writeback(eb);
+	} while (bvec >= bio->bi_io_vec);
+
+	bio_put(bio);
+
+}
+
+static int write_one_eb(struct extent_buffer *eb,
+			struct btrfs_fs_info *fs_info,
+			struct writeback_control *wbc,
+			struct extent_page_data *epd)
+{
+	struct block_device *bdev = fs_info->fs_devices->latest_bdev;
+	u64 offset = eb->start;
+	unsigned long i, num_pages;
+	int rw = (epd->sync_io ? WRITE_SYNC : WRITE);
+	int ret;
+
+	clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+	num_pages = num_extent_pages(eb->start, eb->len);
+	atomic_set(&eb->io_pages, num_pages);
+	for (i = 0; i < num_pages; i++) {
+		struct page *p = extent_buffer_page(eb, i);
+
+		clear_page_dirty_for_io(p);
+		set_page_writeback(p);
+		ret = submit_extent_page(rw, eb->tree, p, offset >> 9,
+					 PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
+					 -1, end_bio_extent_buffer_writepage,
+					 0, 0, 0);
+		if (ret) {
+			set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+			SetPageError(p);
+			if (atomic_sub_and_test(num_pages - i, &eb->io_pages))
+				end_extent_buffer_writeback(eb);
+			ret = -EIO;
+			break;
+		}
+		offset += PAGE_CACHE_SIZE;
+		update_nr_written(p, wbc, 1);
+		unlock_page(p);
+	}
+
+	if (unlikely(ret)) {
+		for (; i < num_pages; i++) {
+			struct page *p = extent_buffer_page(eb, i);
+			unlock_page(p);
+		}
+	}
+
+	return ret;
+}
+
+int btree_write_cache_pages(struct address_space *mapping,
+				   struct writeback_control *wbc)
+{
+	struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
+	struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info;
+	struct extent_buffer *eb, *prev_eb = NULL;
+	struct extent_page_data epd = {
+		.bio = NULL,
+		.tree = tree,
+		.extent_locked = 0,
+		.sync_io = wbc->sync_mode == WB_SYNC_ALL,
+	};
+	int ret = 0;
+	int done = 0;
+	int nr_to_write_done = 0;
+	struct pagevec pvec;
+	int nr_pages;
+	pgoff_t index;
+	pgoff_t end;		/* Inclusive */
+	int scanned = 0;
+	int tag;
+
+	pagevec_init(&pvec, 0);
+	if (wbc->range_cyclic) {
+		index = mapping->writeback_index; /* Start from prev offset */
+		end = -1;
+	} else {
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
+		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		scanned = 1;
+	}
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		tag = PAGECACHE_TAG_TOWRITE;
+	else
+		tag = PAGECACHE_TAG_DIRTY;
+retry:
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		tag_pages_for_writeback(mapping, index, end);
+	while (!done && !nr_to_write_done && (index <= end) &&
+	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+		unsigned i;
+
+		scanned = 1;
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			if (!PagePrivate(page))
+				continue;
+
+			if (!wbc->range_cyclic && page->index > end) {
+				done = 1;
+				break;
+			}
+
+			eb = (struct extent_buffer *)page->private;
+			if (!eb) {
+				WARN_ON(1);
+				continue;
+			}
+
+			if (eb == prev_eb)
+				continue;
+
+			if (!atomic_inc_not_zero(&eb->refs)) {
+				WARN_ON(1);
+				continue;
+			}
+
+			prev_eb = eb;
+			ret = lock_extent_buffer_for_io(eb, fs_info, &epd);
+			if (!ret) {
+				free_extent_buffer(eb);
+				continue;
+			}
+
+			ret = write_one_eb(eb, fs_info, wbc, &epd);
+			if (ret) {
+				done = 1;
+				free_extent_buffer(eb);
+				break;
+			}
+			free_extent_buffer(eb);
+
+			/*
+			 * the filesystem may choose to bump up nr_to_write.
+			 * We have to make sure to honor the new nr_to_write
+			 * at any time
+			 */
+			nr_to_write_done = wbc->nr_to_write <= 0;
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+	if (!scanned && !done) {
+		/*
+		 * We hit the last page and there is more work to be done: wrap
+		 * back to the start of the file
+		 */
+		scanned = 1;
+		index = 0;
+		goto retry;
+	}
+	flush_write_bio(&epd);
+	return ret;
+}
+
 /**
  * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
  * @mapping: address space structure to write
@@ -3099,10 +3435,14 @@ retry:
 static void flush_epd_write_bio(struct extent_page_data *epd)
 {
 	if (epd->bio) {
+		int rw = WRITE;
+		int ret;
+
 		if (epd->sync_io)
-			submit_one_bio(WRITE_SYNC, epd->bio, 0, 0);
-		else
-			submit_one_bio(WRITE, epd->bio, 0, 0);
+			rw = WRITE_SYNC;
+
+		ret = submit_one_bio(rw, epd->bio, 0, 0);
+		BUG_ON(ret < 0); /* -ENOMEM */
 		epd->bio = NULL;
 	}
 }
@@ -3219,7 +3559,7 @@ int extent_readpages(struct extent_io_tree *tree,
 	}
 	BUG_ON(!list_empty(pages));
 	if (bio)
-		submit_one_bio(READ, bio, 0, bio_flags);
+		return submit_one_bio(READ, bio, 0, bio_flags);
 	return 0;
 }
 
@@ -3240,7 +3580,7 @@ int extent_invalidatepage(struct extent_io_tree *tree,
 	if (start > end)
 		return 0;
 
-	lock_extent_bits(tree, start, end, 0, &cached_state, GFP_NOFS);
+	lock_extent_bits(tree, start, end, 0, &cached_state);
 	wait_on_page_writeback(page);
 	clear_extent_bit(tree, start, end,
 			 EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
@@ -3454,7 +3794,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	}
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0,
-			 &cached_state, GFP_NOFS);
+			 &cached_state);
 
 	em = get_extent_skip_holes(inode, start, last_for_get_extent,
 				   get_extent);
@@ -3548,26 +3888,7 @@ out:
 inline struct page *extent_buffer_page(struct extent_buffer *eb,
 					      unsigned long i)
 {
-	struct page *p;
-	struct address_space *mapping;
-
-	if (i == 0)
-		return eb->first_page;
-	i += eb->start >> PAGE_CACHE_SHIFT;
-	mapping = eb->first_page->mapping;
-	if (!mapping)
-		return NULL;
-
-	/*
-	 * extent_buffer_page is only called after pinning the page
-	 * by increasing the reference count.  So we know the page must
-	 * be in the radix tree.
-	 */
-	rcu_read_lock();
-	p = radix_tree_lookup(&mapping->page_tree, i);
-	rcu_read_unlock();
-
-	return p;
+	return eb->pages[i];
 }
 
 inline unsigned long num_extent_pages(u64 start, u64 len)
@@ -3576,6 +3897,19 @@ inline unsigned long num_extent_pages(u64 start, u64 len)
 		(start >> PAGE_CACHE_SHIFT);
 }
 
+static void __free_extent_buffer(struct extent_buffer *eb)
+{
+#if LEAK_DEBUG
+	unsigned long flags;
+	spin_lock_irqsave(&leak_lock, flags);
+	list_del(&eb->leak_list);
+	spin_unlock_irqrestore(&leak_lock, flags);
+#endif
+	if (eb->pages && eb->pages != eb->inline_pages)
+		kfree(eb->pages);
+	kmem_cache_free(extent_buffer_cache, eb);
+}
+
 static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
 						   u64 start,
 						   unsigned long len,
@@ -3591,6 +3925,7 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
 		return NULL;
 	eb->start = start;
 	eb->len = len;
+	eb->tree = tree;
 	rwlock_init(&eb->lock);
 	atomic_set(&eb->write_locks, 0);
 	atomic_set(&eb->read_locks, 0);
@@ -3607,20 +3942,32 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
 	list_add(&eb->leak_list, &buffers);
 	spin_unlock_irqrestore(&leak_lock, flags);
 #endif
+	spin_lock_init(&eb->refs_lock);
 	atomic_set(&eb->refs, 1);
+	atomic_set(&eb->io_pages, 0);
+
+	if (len > MAX_INLINE_EXTENT_BUFFER_SIZE) {
+		struct page **pages;
+		int num_pages = (len + PAGE_CACHE_SIZE - 1) >>
+			PAGE_CACHE_SHIFT;
+		pages = kzalloc(num_pages, mask);
+		if (!pages) {
+			__free_extent_buffer(eb);
+			return NULL;
+		}
+		eb->pages = pages;
+	} else {
+		eb->pages = eb->inline_pages;
+	}
 
 	return eb;
 }
 
-static void __free_extent_buffer(struct extent_buffer *eb)
+static int extent_buffer_under_io(struct extent_buffer *eb)
 {
-#if LEAK_DEBUG
-	unsigned long flags;
-	spin_lock_irqsave(&leak_lock, flags);
-	list_del(&eb->leak_list);
-	spin_unlock_irqrestore(&leak_lock, flags);
-#endif
-	kmem_cache_free(extent_buffer_cache, eb);
+	return (atomic_read(&eb->io_pages) ||
+		test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
+		test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
 }
 
 /*
@@ -3632,8 +3979,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
 	unsigned long index;
 	struct page *page;
 
-	if (!eb->first_page)
-		return;
+	BUG_ON(extent_buffer_under_io(eb));
 
 	index = num_extent_pages(eb->start, eb->len);
 	if (start_idx >= index)
@@ -3642,8 +3988,34 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
 	do {
 		index--;
 		page = extent_buffer_page(eb, index);
-		if (page)
+		if (page) {
+			spin_lock(&page->mapping->private_lock);
+			/*
+			 * We do this since we'll remove the pages after we've
+			 * removed the eb from the radix tree, so we could race
+			 * and have this page now attached to the new eb.  So
+			 * only clear page_private if it's still connected to
+			 * this eb.
+			 */
+			if (PagePrivate(page) &&
+			    page->private == (unsigned long)eb) {
+				BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+				BUG_ON(PageDirty(page));
+				BUG_ON(PageWriteback(page));
+				/*
+				 * We need to make sure we haven't be attached
+				 * to a new eb.
+				 */
+				ClearPagePrivate(page);
+				set_page_private(page, 0);
+				/* One for the page private */
+				page_cache_release(page);
+			}
+			spin_unlock(&page->mapping->private_lock);
+
+			/* One for when we alloced the page */
 			page_cache_release(page);
+		}
 	} while (index != start_idx);
 }
 
@@ -3656,9 +4028,50 @@ static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
 	__free_extent_buffer(eb);
 }
 
+static void check_buffer_tree_ref(struct extent_buffer *eb)
+{
+	/* the ref bit is tricky.  We have to make sure it is set
+	 * if we have the buffer dirty.   Otherwise the
+	 * code to free a buffer can end up dropping a dirty
+	 * page
+	 *
+	 * Once the ref bit is set, it won't go away while the
+	 * buffer is dirty or in writeback, and it also won't
+	 * go away while we have the reference count on the
+	 * eb bumped.
+	 *
+	 * We can't just set the ref bit without bumping the
+	 * ref on the eb because free_extent_buffer might
+	 * see the ref bit and try to clear it.  If this happens
+	 * free_extent_buffer might end up dropping our original
+	 * ref by mistake and freeing the page before we are able
+	 * to add one more ref.
+	 *
+	 * So bump the ref count first, then set the bit.  If someone
+	 * beat us to it, drop the ref we added.
+	 */
+	if (!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
+		atomic_inc(&eb->refs);
+		if (test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
+			atomic_dec(&eb->refs);
+	}
+}
+
+static void mark_extent_buffer_accessed(struct extent_buffer *eb)
+{
+	unsigned long num_pages, i;
+
+	check_buffer_tree_ref(eb);
+
+	num_pages = num_extent_pages(eb->start, eb->len);
+	for (i = 0; i < num_pages; i++) {
+		struct page *p = extent_buffer_page(eb, i);
+		mark_page_accessed(p);
+	}
+}
+
 struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
-					  u64 start, unsigned long len,
-					  struct page *page0)
+					  u64 start, unsigned long len)
 {
 	unsigned long num_pages = num_extent_pages(start, len);
 	unsigned long i;
@@ -3674,7 +4087,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 	eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT);
 	if (eb && atomic_inc_not_zero(&eb->refs)) {
 		rcu_read_unlock();
-		mark_page_accessed(eb->first_page);
+		mark_extent_buffer_accessed(eb);
 		return eb;
 	}
 	rcu_read_unlock();
@@ -3683,32 +4096,43 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 	if (!eb)
 		return NULL;
 
-	if (page0) {
-		eb->first_page = page0;
-		i = 1;
-		index++;
-		page_cache_get(page0);
-		mark_page_accessed(page0);
-		set_page_extent_mapped(page0);
-		set_page_extent_head(page0, len);
-		uptodate = PageUptodate(page0);
-	} else {
-		i = 0;
-	}
-	for (; i < num_pages; i++, index++) {
+	for (i = 0; i < num_pages; i++, index++) {
 		p = find_or_create_page(mapping, index, GFP_NOFS);
 		if (!p) {
 			WARN_ON(1);
 			goto free_eb;
 		}
-		set_page_extent_mapped(p);
-		mark_page_accessed(p);
-		if (i == 0) {
-			eb->first_page = p;
-			set_page_extent_head(p, len);
-		} else {
-			set_page_private(p, EXTENT_PAGE_PRIVATE);
+
+		spin_lock(&mapping->private_lock);
+		if (PagePrivate(p)) {
+			/*
+			 * We could have already allocated an eb for this page
+			 * and attached one so lets see if we can get a ref on
+			 * the existing eb, and if we can we know it's good and
+			 * we can just return that one, else we know we can just
+			 * overwrite page->private.
+			 */
+			exists = (struct extent_buffer *)p->private;
+			if (atomic_inc_not_zero(&exists->refs)) {
+				spin_unlock(&mapping->private_lock);
+				unlock_page(p);
+				mark_extent_buffer_accessed(exists);
+				goto free_eb;
+			}
+
+			/*
+			 * Do this so attach doesn't complain and we need to
+			 * drop the ref the old guy had.
+			 */
+			ClearPagePrivate(p);
+			WARN_ON(PageDirty(p));
+			page_cache_release(p);
 		}
+		attach_extent_buffer_page(eb, p);
+		spin_unlock(&mapping->private_lock);
+		WARN_ON(PageDirty(p));
+		mark_page_accessed(p);
+		eb->pages[i] = p;
 		if (!PageUptodate(p))
 			uptodate = 0;
 
@@ -3716,12 +4140,10 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 		 * see below about how we avoid a nasty race with release page
 		 * and why we unlock later
 		 */
-		if (i != 0)
-			unlock_page(p);
 	}
 	if (uptodate)
 		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-
+again:
 	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
 	if (ret)
 		goto free_eb;
@@ -3731,14 +4153,21 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 	if (ret == -EEXIST) {
 		exists = radix_tree_lookup(&tree->buffer,
 						start >> PAGE_CACHE_SHIFT);
-		/* add one reference for the caller */
-		atomic_inc(&exists->refs);
+		if (!atomic_inc_not_zero(&exists->refs)) {
+			spin_unlock(&tree->buffer_lock);
+			radix_tree_preload_end();
+			exists = NULL;
+			goto again;
+		}
 		spin_unlock(&tree->buffer_lock);
 		radix_tree_preload_end();
+		mark_extent_buffer_accessed(exists);
 		goto free_eb;
 	}
 	/* add one reference for the tree */
-	atomic_inc(&eb->refs);
+	spin_lock(&eb->refs_lock);
+	check_buffer_tree_ref(eb);
+	spin_unlock(&eb->refs_lock);
 	spin_unlock(&tree->buffer_lock);
 	radix_tree_preload_end();
 
@@ -3751,15 +4180,20 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 	 * after the extent buffer is in the radix tree so
 	 * it doesn't get lost
 	 */
-	set_page_extent_mapped(eb->first_page);
-	set_page_extent_head(eb->first_page, eb->len);
-	if (!page0)
-		unlock_page(eb->first_page);
+	SetPageChecked(eb->pages[0]);
+	for (i = 1; i < num_pages; i++) {
+		p = extent_buffer_page(eb, i);
+		ClearPageChecked(p);
+		unlock_page(p);
+	}
+	unlock_page(eb->pages[0]);
 	return eb;
 
 free_eb:
-	if (eb->first_page && !page0)
-		unlock_page(eb->first_page);
+	for (i = 0; i < num_pages; i++) {
+		if (eb->pages[i])
+			unlock_page(eb->pages[i]);
+	}
 
 	if (!atomic_dec_and_test(&eb->refs))
 		return exists;
@@ -3776,7 +4210,7 @@ struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
 	eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT);
 	if (eb && atomic_inc_not_zero(&eb->refs)) {
 		rcu_read_unlock();
-		mark_page_accessed(eb->first_page);
+		mark_extent_buffer_accessed(eb);
 		return eb;
 	}
 	rcu_read_unlock();
@@ -3784,19 +4218,71 @@ struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
 	return NULL;
 }
 
+static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
+{
+	struct extent_buffer *eb =
+			container_of(head, struct extent_buffer, rcu_head);
+
+	__free_extent_buffer(eb);
+}
+
+/* Expects to have eb->eb_lock already held */
+static void release_extent_buffer(struct extent_buffer *eb, gfp_t mask)
+{
+	WARN_ON(atomic_read(&eb->refs) == 0);
+	if (atomic_dec_and_test(&eb->refs)) {
+		struct extent_io_tree *tree = eb->tree;
+
+		spin_unlock(&eb->refs_lock);
+
+		spin_lock(&tree->buffer_lock);
+		radix_tree_delete(&tree->buffer,
+				  eb->start >> PAGE_CACHE_SHIFT);
+		spin_unlock(&tree->buffer_lock);
+
+		/* Should be safe to release our pages at this point */
+		btrfs_release_extent_buffer_page(eb, 0);
+
+		call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
+		return;
+	}
+	spin_unlock(&eb->refs_lock);
+}
+
 void free_extent_buffer(struct extent_buffer *eb)
 {
 	if (!eb)
 		return;
 
-	if (!atomic_dec_and_test(&eb->refs))
+	spin_lock(&eb->refs_lock);
+	if (atomic_read(&eb->refs) == 2 &&
+	    test_bit(EXTENT_BUFFER_STALE, &eb->bflags) &&
+	    !extent_buffer_under_io(eb) &&
+	    test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
+		atomic_dec(&eb->refs);
+
+	/*
+	 * I know this is terrible, but it's temporary until we stop tracking
+	 * the uptodate bits and such for the extent buffers.
+	 */
+	release_extent_buffer(eb, GFP_ATOMIC);
+}
+
+void free_extent_buffer_stale(struct extent_buffer *eb)
+{
+	if (!eb)
 		return;
 
-	WARN_ON(1);
+	spin_lock(&eb->refs_lock);
+	set_bit(EXTENT_BUFFER_STALE, &eb->bflags);
+
+	if (atomic_read(&eb->refs) == 2 && !extent_buffer_under_io(eb) &&
+	    test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
+		atomic_dec(&eb->refs);
+	release_extent_buffer(eb, GFP_NOFS);
 }
 
-int clear_extent_buffer_dirty(struct extent_io_tree *tree,
-			      struct extent_buffer *eb)
+void clear_extent_buffer_dirty(struct extent_buffer *eb)
 {
 	unsigned long i;
 	unsigned long num_pages;
@@ -3812,10 +4298,6 @@ int clear_extent_buffer_dirty(struct extent_io_tree *tree,
 		lock_page(page);
 		WARN_ON(!PagePrivate(page));
 
-		set_page_extent_mapped(page);
-		if (i == 0)
-			set_page_extent_head(page, eb->len);
-
 		clear_page_dirty_for_io(page);
 		spin_lock_irq(&page->mapping->tree_lock);
 		if (!PageDirty(page)) {
@@ -3827,24 +4309,29 @@ int clear_extent_buffer_dirty(struct extent_io_tree *tree,
 		ClearPageError(page);
 		unlock_page(page);
 	}
-	return 0;
+	WARN_ON(atomic_read(&eb->refs) == 0);
 }
 
-int set_extent_buffer_dirty(struct extent_io_tree *tree,
-			     struct extent_buffer *eb)
+int set_extent_buffer_dirty(struct extent_buffer *eb)
 {
 	unsigned long i;
 	unsigned long num_pages;
 	int was_dirty = 0;
 
+	check_buffer_tree_ref(eb);
+
 	was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
+
 	num_pages = num_extent_pages(eb->start, eb->len);
+	WARN_ON(atomic_read(&eb->refs) == 0);
+	WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
+
 	for (i = 0; i < num_pages; i++)
-		__set_page_dirty_nobuffers(extent_buffer_page(eb, i));
+		set_page_dirty(extent_buffer_page(eb, i));
 	return was_dirty;
 }
 
-static int __eb_straddles_pages(u64 start, u64 len)
+static int range_straddles_pages(u64 start, u64 len)
 {
 	if (len < PAGE_CACHE_SIZE)
 		return 1;
@@ -3855,25 +4342,14 @@ static int __eb_straddles_pages(u64 start, u64 len)
 	return 0;
 }
 
-static int eb_straddles_pages(struct extent_buffer *eb)
-{
-	return __eb_straddles_pages(eb->start, eb->len);
-}
-
-int clear_extent_buffer_uptodate(struct extent_io_tree *tree,
-				struct extent_buffer *eb,
-				struct extent_state **cached_state)
+int clear_extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	unsigned long i;
 	struct page *page;
 	unsigned long num_pages;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
 	clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-
-	clear_extent_uptodate(tree, eb->start, eb->start + eb->len - 1,
-			      cached_state, GFP_NOFS);
-
+	num_pages = num_extent_pages(eb->start, eb->len);
 	for (i = 0; i < num_pages; i++) {
 		page = extent_buffer_page(eb, i);
 		if (page)
@@ -3882,27 +4358,16 @@ int clear_extent_buffer_uptodate(struct extent_io_tree *tree,
 	return 0;
 }
 
-int set_extent_buffer_uptodate(struct extent_io_tree *tree,
-				struct extent_buffer *eb)
+int set_extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	unsigned long i;
 	struct page *page;
 	unsigned long num_pages;
 
+	set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 	num_pages = num_extent_pages(eb->start, eb->len);
-
-	if (eb_straddles_pages(eb)) {
-		set_extent_uptodate(tree, eb->start, eb->start + eb->len - 1,
-				    NULL, GFP_NOFS);
-	}
 	for (i = 0; i < num_pages; i++) {
 		page = extent_buffer_page(eb, i);
-		if ((i == 0 && (eb->start & (PAGE_CACHE_SIZE - 1))) ||
-		    ((i == num_pages - 1) &&
-		     ((eb->start + eb->len) & (PAGE_CACHE_SIZE - 1)))) {
-			check_page_uptodate(tree, page);
-			continue;
-		}
 		SetPageUptodate(page);
 	}
 	return 0;
@@ -3917,7 +4382,7 @@ int extent_range_uptodate(struct extent_io_tree *tree,
 	int uptodate;
 	unsigned long index;
 
-	if (__eb_straddles_pages(start, end - start + 1)) {
+	if (range_straddles_pages(start, end - start + 1)) {
 		ret = test_range_bit(tree, start, end,
 				     EXTENT_UPTODATE, 1, NULL);
 		if (ret)
@@ -3939,35 +4404,9 @@ int extent_range_uptodate(struct extent_io_tree *tree,
 	return pg_uptodate;
 }
 
-int extent_buffer_uptodate(struct extent_io_tree *tree,
-			   struct extent_buffer *eb,
-			   struct extent_state *cached_state)
+int extent_buffer_uptodate(struct extent_buffer *eb)
 {
-	int ret = 0;
-	unsigned long num_pages;
-	unsigned long i;
-	struct page *page;
-	int pg_uptodate = 1;
-
-	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
-		return 1;
-
-	if (eb_straddles_pages(eb)) {
-		ret = test_range_bit(tree, eb->start, eb->start + eb->len - 1,
-				   EXTENT_UPTODATE, 1, cached_state);
-		if (ret)
-			return ret;
-	}
-
-	num_pages = num_extent_pages(eb->start, eb->len);
-	for (i = 0; i < num_pages; i++) {
-		page = extent_buffer_page(eb, i);
-		if (!PageUptodate(page)) {
-			pg_uptodate = 0;
-			break;
-		}
-	}
-	return pg_uptodate;
+	return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 }
 
 int read_extent_buffer_pages(struct extent_io_tree *tree,
@@ -3981,21 +4420,14 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	int ret = 0;
 	int locked_pages = 0;
 	int all_uptodate = 1;
-	int inc_all_pages = 0;
 	unsigned long num_pages;
+	unsigned long num_reads = 0;
 	struct bio *bio = NULL;
 	unsigned long bio_flags = 0;
 
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
 
-	if (eb_straddles_pages(eb)) {
-		if (test_range_bit(tree, eb->start, eb->start + eb->len - 1,
-				   EXTENT_UPTODATE, 1, NULL)) {
-			return 0;
-		}
-	}
-
 	if (start) {
 		WARN_ON(start < eb->start);
 		start_i = (start >> PAGE_CACHE_SHIFT) -
@@ -4014,8 +4446,10 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			lock_page(page);
 		}
 		locked_pages++;
-		if (!PageUptodate(page))
+		if (!PageUptodate(page)) {
+			num_reads++;
 			all_uptodate = 0;
+		}
 	}
 	if (all_uptodate) {
 		if (start_i == 0)
@@ -4023,20 +4457,12 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 		goto unlock_exit;
 	}
 
+	clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+	eb->failed_mirror = 0;
+	atomic_set(&eb->io_pages, num_reads);
 	for (i = start_i; i < num_pages; i++) {
 		page = extent_buffer_page(eb, i);
-
-		WARN_ON(!PagePrivate(page));
-
-		set_page_extent_mapped(page);
-		if (i == 0)
-			set_page_extent_head(page, eb->len);
-
-		if (inc_all_pages)
-			page_cache_get(page);
 		if (!PageUptodate(page)) {
-			if (start_i == 0)
-				inc_all_pages = 1;
 			ClearPageError(page);
 			err = __extent_read_full_page(tree, page,
 						      get_extent, &bio,
@@ -4048,8 +4474,11 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 		}
 	}
 
-	if (bio)
-		submit_one_bio(READ, bio, mirror_num, bio_flags);
+	if (bio) {
+		err = submit_one_bio(READ, bio, mirror_num, bio_flags);
+		if (err)
+			return err;
+	}
 
 	if (ret || wait != WAIT_COMPLETE)
 		return ret;
@@ -4061,8 +4490,6 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			ret = -EIO;
 	}
 
-	if (!ret)
-		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 	return ret;
 
 unlock_exit:
@@ -4304,15 +4731,20 @@ static void copy_pages(struct page *dst_page, struct page *src_page,
 {
 	char *dst_kaddr = page_address(dst_page);
 	char *src_kaddr;
+	int must_memmove = 0;
 
 	if (dst_page != src_page) {
 		src_kaddr = page_address(src_page);
 	} else {
 		src_kaddr = dst_kaddr;
-		BUG_ON(areas_overlap(src_off, dst_off, len));
+		if (areas_overlap(src_off, dst_off, len))
+			must_memmove = 1;
 	}
 
-	memcpy(dst_kaddr + dst_off, src_kaddr + src_off, len);
+	if (must_memmove)
+		memmove(dst_kaddr + dst_off, src_kaddr + src_off, len);
+	else
+		memcpy(dst_kaddr + dst_off, src_kaddr + src_off, len);
 }
 
 void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
@@ -4382,7 +4814,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 		       "len %lu len %lu\n", dst_offset, len, dst->len);
 		BUG_ON(1);
 	}
-	if (!areas_overlap(src_offset, dst_offset, len)) {
+	if (dst_offset < src_offset) {
 		memcpy_extent_buffer(dst, dst_offset, src_offset, len);
 		return;
 	}
@@ -4408,47 +4840,48 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 	}
 }
 
-static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
+int try_release_extent_buffer(struct page *page, gfp_t mask)
 {
-	struct extent_buffer *eb =
-			container_of(head, struct extent_buffer, rcu_head);
-
-	btrfs_release_extent_buffer(eb);
-}
-
-int try_release_extent_buffer(struct extent_io_tree *tree, struct page *page)
-{
-	u64 start = page_offset(page);
 	struct extent_buffer *eb;
-	int ret = 1;
 
-	spin_lock(&tree->buffer_lock);
-	eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT);
-	if (!eb) {
-		spin_unlock(&tree->buffer_lock);
-		return ret;
+	/*
+	 * We need to make sure noboody is attaching this page to an eb right
+	 * now.
+	 */
+	spin_lock(&page->mapping->private_lock);
+	if (!PagePrivate(page)) {
+		spin_unlock(&page->mapping->private_lock);
+		return 1;
 	}
 
-	if (test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
-		ret = 0;
-		goto out;
-	}
+	eb = (struct extent_buffer *)page->private;
+	BUG_ON(!eb);
 
 	/*
-	 * set @eb->refs to 0 if it is already 1, and then release the @eb.
-	 * Or go back.
+	 * This is a little awful but should be ok, we need to make sure that
+	 * the eb doesn't disappear out from under us while we're looking at
+	 * this page.
 	 */
-	if (atomic_cmpxchg(&eb->refs, 1, 0) != 1) {
-		ret = 0;
-		goto out;
+	spin_lock(&eb->refs_lock);
+	if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
+		spin_unlock(&eb->refs_lock);
+		spin_unlock(&page->mapping->private_lock);
+		return 0;
 	}
+	spin_unlock(&page->mapping->private_lock);
 
-	radix_tree_delete(&tree->buffer, start >> PAGE_CACHE_SHIFT);
-out:
-	spin_unlock(&tree->buffer_lock);
+	if ((mask & GFP_NOFS) == GFP_NOFS)
+		mask = GFP_NOFS;
 
-	/* at this point we can safely release the extent buffer */
-	if (atomic_read(&eb->refs) == 0)
-		call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
-	return ret;
+	/*
+	 * If tree ref isn't set then we know the ref on this eb is a real ref,
+	 * so just return, this page will likely be freed soon anyway.
+	 */
+	if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
+		spin_unlock(&eb->refs_lock);
+		return 0;
+	}
+	release_extent_buffer(eb, mask);
+
+	return 1;
 }
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index cecc3518c121..faf10eb57f75 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -35,6 +35,10 @@
 #define EXTENT_BUFFER_DIRTY 2
 #define EXTENT_BUFFER_CORRUPT 3
 #define EXTENT_BUFFER_READAHEAD 4	/* this got triggered by readahead */
+#define EXTENT_BUFFER_TREE_REF 5
+#define EXTENT_BUFFER_STALE 6
+#define EXTENT_BUFFER_WRITEBACK 7
+#define EXTENT_BUFFER_IOERR 8
 
 /* these are flags for extent_clear_unlock_delalloc */
 #define EXTENT_CLEAR_UNLOCK_PAGE 0x1
@@ -54,6 +58,7 @@
 #define EXTENT_PAGE_PRIVATE_FIRST_PAGE 3
 
 struct extent_state;
+struct btrfs_root;
 
 typedef	int (extent_submit_bio_hook_t)(struct inode *inode, int rw,
 				       struct bio *bio, int mirror_num,
@@ -69,9 +74,7 @@ struct extent_io_ops {
 			      size_t size, struct bio *bio,
 			      unsigned long bio_flags);
 	int (*readpage_io_hook)(struct page *page, u64 start, u64 end);
-	int (*readpage_io_failed_hook)(struct bio *bio, struct page *page,
-				       u64 start, u64 end, int failed_mirror,
-				       struct extent_state *state);
+	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
 	int (*writepage_io_failed_hook)(struct bio *bio, struct page *page,
 					u64 start, u64 end,
 				       struct extent_state *state);
@@ -97,6 +100,7 @@ struct extent_io_tree {
 	struct radix_tree_root buffer;
 	struct address_space *mapping;
 	u64 dirty_bytes;
+	int track_uptodate;
 	spinlock_t lock;
 	spinlock_t buffer_lock;
 	struct extent_io_ops *ops;
@@ -119,16 +123,21 @@ struct extent_state {
 	struct list_head leak_list;
 };
 
+#define INLINE_EXTENT_BUFFER_PAGES 16
+#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_CACHE_SIZE)
 struct extent_buffer {
 	u64 start;
 	unsigned long len;
 	unsigned long map_start;
 	unsigned long map_len;
-	struct page *first_page;
 	unsigned long bflags;
+	struct extent_io_tree *tree;
+	spinlock_t refs_lock;
+	atomic_t refs;
+	atomic_t io_pages;
+	int failed_mirror;
 	struct list_head leak_list;
 	struct rcu_head rcu_head;
-	atomic_t refs;
 	pid_t lock_owner;
 
 	/* count of read lock holders on the extent buffer */
@@ -152,6 +161,9 @@ struct extent_buffer {
 	 * to unlock
 	 */
 	wait_queue_head_t read_lock_wq;
+	wait_queue_head_t lock_wq;
+	struct page *inline_pages[INLINE_EXTENT_BUFFER_PAGES];
+	struct page **pages;
 };
 
 static inline void extent_set_compress_type(unsigned long *bio_flags,
@@ -178,18 +190,17 @@ void extent_io_tree_init(struct extent_io_tree *tree,
 int try_release_extent_mapping(struct extent_map_tree *map,
 			       struct extent_io_tree *tree, struct page *page,
 			       gfp_t mask);
-int try_release_extent_buffer(struct extent_io_tree *tree, struct page *page);
+int try_release_extent_buffer(struct page *page, gfp_t mask);
 int try_release_extent_state(struct extent_map_tree *map,
 			     struct extent_io_tree *tree, struct page *page,
 			     gfp_t mask);
-int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask);
+int lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     int bits, struct extent_state **cached, gfp_t mask);
-int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask);
+		     int bits, struct extent_state **cached);
+int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
 			 struct extent_state **cached, gfp_t mask);
-int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
-		    gfp_t mask);
+int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
@@ -210,7 +221,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 		    int bits, gfp_t mask);
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   int bits, int exclusive_bits, u64 *failed_start,
+		   int bits, u64 *failed_start,
 		   struct extent_state **cached_state, gfp_t mask);
 int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask);
@@ -240,6 +251,8 @@ int extent_writepages(struct extent_io_tree *tree,
 		      struct address_space *mapping,
 		      get_extent_t *get_extent,
 		      struct writeback_control *wbc);
+int btree_write_cache_pages(struct address_space *mapping,
+			    struct writeback_control *wbc);
 int extent_readpages(struct extent_io_tree *tree,
 		     struct address_space *mapping,
 		     struct list_head *pages, unsigned nr_pages,
@@ -251,11 +264,11 @@ int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private);
 void set_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
-					  u64 start, unsigned long len,
-					  struct page *page0);
+					  u64 start, unsigned long len);
 struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
 					 u64 start, unsigned long len);
 void free_extent_buffer(struct extent_buffer *eb);
+void free_extent_buffer_stale(struct extent_buffer *eb);
 #define WAIT_NONE	0
 #define WAIT_COMPLETE	1
 #define WAIT_PAGE_LOCK	2
@@ -287,19 +300,12 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 			   unsigned long src_offset, unsigned long len);
 void memset_extent_buffer(struct extent_buffer *eb, char c,
 			  unsigned long start, unsigned long len);
-int wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int bits);
-int clear_extent_buffer_dirty(struct extent_io_tree *tree,
-			      struct extent_buffer *eb);
-int set_extent_buffer_dirty(struct extent_io_tree *tree,
-			     struct extent_buffer *eb);
-int set_extent_buffer_uptodate(struct extent_io_tree *tree,
-			       struct extent_buffer *eb);
-int clear_extent_buffer_uptodate(struct extent_io_tree *tree,
-				struct extent_buffer *eb,
-				struct extent_state **cached_state);
-int extent_buffer_uptodate(struct extent_io_tree *tree,
-			   struct extent_buffer *eb,
-			   struct extent_state *cached_state);
+void wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int bits);
+void clear_extent_buffer_dirty(struct extent_buffer *eb);
+int set_extent_buffer_dirty(struct extent_buffer *eb);
+int set_extent_buffer_uptodate(struct extent_buffer *eb);
+int clear_extent_buffer_uptodate(struct extent_buffer *eb);
+int extent_buffer_uptodate(struct extent_buffer *eb);
 int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset,
 		      unsigned long min_len, char **map,
 		      unsigned long *map_start,
@@ -320,4 +326,6 @@ int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start,
 			u64 length, u64 logical, struct page *page,
 			int mirror_num);
 int end_extent_writepage(struct page *page, int err, u64 start, u64 end);
+int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
+			 int mirror_num);
 #endif
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 078b4fd54500..5d158d320233 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -25,10 +25,12 @@
 #include "transaction.h"
 #include "print-tree.h"
 
-#define MAX_CSUM_ITEMS(r, size) ((((BTRFS_LEAF_DATA_SIZE(r) - \
+#define __MAX_CSUM_ITEMS(r, size) ((((BTRFS_LEAF_DATA_SIZE(r) - \
 				   sizeof(struct btrfs_item) * 2) / \
 				  size) - 1))
 
+#define MAX_CSUM_ITEMS(r, size) (min(__MAX_CSUM_ITEMS(r, size), PAGE_CACHE_SIZE))
+
 #define MAX_ORDERED_SUM_BYTES(r) ((PAGE_SIZE - \
 				   sizeof(struct btrfs_ordered_sum)) / \
 				   sizeof(struct btrfs_sector_sum) * \
@@ -59,7 +61,7 @@ int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 				      sizeof(*item));
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret);
+	BUG_ON(ret); /* Can't happen */
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0],
 			      struct btrfs_file_extent_item);
@@ -284,6 +286,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_sector_sum *sector_sum;
 	struct btrfs_csum_item *item;
+	LIST_HEAD(tmplist);
 	unsigned long offset;
 	int ret;
 	size_t size;
@@ -358,7 +361,10 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 					MAX_ORDERED_SUM_BYTES(root));
 			sums = kzalloc(btrfs_ordered_sum_size(root, size),
 					GFP_NOFS);
-			BUG_ON(!sums);
+			if (!sums) {
+				ret = -ENOMEM;
+				goto fail;
+			}
 
 			sector_sum = sums->sums;
 			sums->bytenr = start;
@@ -380,12 +386,19 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 				offset += csum_size;
 				sector_sum++;
 			}
-			list_add_tail(&sums->list, list);
+			list_add_tail(&sums->list, &tmplist);
 		}
 		path->slots[0]++;
 	}
 	ret = 0;
 fail:
+	while (ret < 0 && !list_empty(&tmplist)) {
+		sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+		list_del(&sums->list);
+		kfree(sums);
+	}
+	list_splice_tail(&tmplist, list);
+
 	btrfs_free_path(path);
 	return ret;
 }
@@ -420,7 +433,7 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 
 	ordered = btrfs_lookup_ordered_extent(inode, offset);
-	BUG_ON(!ordered);
+	BUG_ON(!ordered); /* Logic error */
 	sums->bytenr = ordered->start;
 
 	while (bio_index < bio->bi_vcnt) {
@@ -439,11 +452,11 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 
 			sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
 				       GFP_NOFS);
-			BUG_ON(!sums);
+			BUG_ON(!sums); /* -ENOMEM */
 			sector_sum = sums->sums;
 			sums->len = bytes_left;
 			ordered = btrfs_lookup_ordered_extent(inode, offset);
-			BUG_ON(!ordered);
+			BUG_ON(!ordered); /* Logic error */
 			sums->bytenr = ordered->start;
 		}
 
@@ -483,18 +496,17 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
  * This calls btrfs_truncate_item with the correct args based on the
  * overlap, and fixes up the key as required.
  */
-static noinline int truncate_one_csum(struct btrfs_trans_handle *trans,
-				      struct btrfs_root *root,
-				      struct btrfs_path *path,
-				      struct btrfs_key *key,
-				      u64 bytenr, u64 len)
+static noinline void truncate_one_csum(struct btrfs_trans_handle *trans,
+				       struct btrfs_root *root,
+				       struct btrfs_path *path,
+				       struct btrfs_key *key,
+				       u64 bytenr, u64 len)
 {
 	struct extent_buffer *leaf;
 	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 	u64 csum_end;
 	u64 end_byte = bytenr + len;
 	u32 blocksize_bits = root->fs_info->sb->s_blocksize_bits;
-	int ret;
 
 	leaf = path->nodes[0];
 	csum_end = btrfs_item_size_nr(leaf, path->slots[0]) / csum_size;
@@ -510,7 +522,7 @@ static noinline int truncate_one_csum(struct btrfs_trans_handle *trans,
 		 */
 		u32 new_size = (bytenr - key->offset) >> blocksize_bits;
 		new_size *= csum_size;
-		ret = btrfs_truncate_item(trans, root, path, new_size, 1);
+		btrfs_truncate_item(trans, root, path, new_size, 1);
 	} else if (key->offset >= bytenr && csum_end > end_byte &&
 		   end_byte > key->offset) {
 		/*
@@ -522,15 +534,13 @@ static noinline int truncate_one_csum(struct btrfs_trans_handle *trans,
 		u32 new_size = (csum_end - end_byte) >> blocksize_bits;
 		new_size *= csum_size;
 
-		ret = btrfs_truncate_item(trans, root, path, new_size, 0);
+		btrfs_truncate_item(trans, root, path, new_size, 0);
 
 		key->offset = end_byte;
-		ret = btrfs_set_item_key_safe(trans, root, path, key);
-		BUG_ON(ret);
+		btrfs_set_item_key_safe(trans, root, path, key);
 	} else {
 		BUG();
 	}
-	return 0;
 }
 
 /*
@@ -635,13 +645,14 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 			 * item changed size or key
 			 */
 			ret = btrfs_split_item(trans, root, path, &key, offset);
-			BUG_ON(ret && ret != -EAGAIN);
+			if (ret && ret != -EAGAIN) {
+				btrfs_abort_transaction(trans, root, ret);
+				goto out;
+			}
 
 			key.offset = end_byte - 1;
 		} else {
-			ret = truncate_one_csum(trans, root, path,
-						&key, bytenr, len);
-			BUG_ON(ret);
+			truncate_one_csum(trans, root, path, &key, bytenr, len);
 			if (key.offset < bytenr)
 				break;
 		}
@@ -772,7 +783,7 @@ again:
 		if (diff != csum_size)
 			goto insert;
 
-		ret = btrfs_extend_item(trans, root, path, diff);
+		btrfs_extend_item(trans, root, path, diff);
 		goto csum;
 	}
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e8d06b6b9194..d83260d7498f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -452,7 +452,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split = alloc_extent_map();
 		if (!split2)
 			split2 = alloc_extent_map();
-		BUG_ON(!split || !split2);
+		BUG_ON(!split || !split2); /* -ENOMEM */
 
 		write_lock(&em_tree->lock);
 		em = lookup_extent_mapping(em_tree, start, len);
@@ -494,7 +494,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			ret = add_extent_mapping(em_tree, split);
-			BUG_ON(ret);
+			BUG_ON(ret); /* Logic error */
 			free_extent_map(split);
 			split = split2;
 			split2 = NULL;
@@ -520,7 +520,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			}
 
 			ret = add_extent_mapping(em_tree, split);
-			BUG_ON(ret);
+			BUG_ON(ret); /* Logic error */
 			free_extent_map(split);
 			split = NULL;
 		}
@@ -679,7 +679,7 @@ next_slot:
 						root->root_key.objectid,
 						new_key.objectid,
 						start - extent_offset, 0);
-				BUG_ON(ret);
+				BUG_ON(ret); /* -ENOMEM */
 				*hint_byte = disk_bytenr;
 			}
 			key.offset = start;
@@ -754,7 +754,7 @@ next_slot:
 						root->root_key.objectid,
 						key.objectid, key.offset -
 						extent_offset, 0);
-				BUG_ON(ret);
+				BUG_ON(ret); /* -ENOMEM */
 				inode_sub_bytes(inode,
 						extent_end - key.offset);
 				*hint_byte = disk_bytenr;
@@ -770,7 +770,10 @@ next_slot:
 
 			ret = btrfs_del_items(trans, root, path, del_slot,
 					      del_nr);
-			BUG_ON(ret);
+			if (ret) {
+				btrfs_abort_transaction(trans, root, ret);
+				goto out;
+			}
 
 			del_nr = 0;
 			del_slot = 0;
@@ -782,11 +785,13 @@ next_slot:
 		BUG_ON(1);
 	}
 
-	if (del_nr > 0) {
+	if (!ret && del_nr > 0) {
 		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
-		BUG_ON(ret);
+		if (ret)
+			btrfs_abort_transaction(trans, root, ret);
 	}
 
+out:
 	btrfs_free_path(path);
 	return ret;
 }
@@ -944,7 +949,10 @@ again:
 			btrfs_release_path(path);
 			goto again;
 		}
-		BUG_ON(ret < 0);
+		if (ret < 0) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out;
+		}
 
 		leaf = path->nodes[0];
 		fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
@@ -963,7 +971,7 @@ again:
 		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
 					   root->root_key.objectid,
 					   ino, orig_offset, 0);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 
 		if (split == start) {
 			key.offset = start;
@@ -990,7 +998,7 @@ again:
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
 					ino, orig_offset, 0);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 	other_start = 0;
 	other_end = start;
@@ -1007,7 +1015,7 @@ again:
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
 					ino, orig_offset, 0);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 	if (del_nr == 0) {
 		fi = btrfs_item_ptr(leaf, path->slots[0],
@@ -1025,7 +1033,10 @@ again:
 		btrfs_mark_buffer_dirty(leaf);
 
 		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
-		BUG_ON(ret);
+		if (ret < 0) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out;
+		}
 	}
 out:
 	btrfs_free_path(path);
@@ -1105,8 +1116,7 @@ again:
 	if (start_pos < inode->i_size) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent_bits(&BTRFS_I(inode)->io_tree,
-				 start_pos, last_pos - 1, 0, &cached_state,
-				 GFP_NOFS);
+				 start_pos, last_pos - 1, 0, &cached_state);
 		ordered = btrfs_lookup_first_ordered_extent(inode,
 							    last_pos - 1);
 		if (ordered &&
@@ -1638,7 +1648,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		 * transaction
 		 */
 		lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
-				 locked_end, 0, &cached_state, GFP_NOFS);
+				 locked_end, 0, &cached_state);
 		ordered = btrfs_lookup_first_ordered_extent(inode,
 							    alloc_end - 1);
 		if (ordered &&
@@ -1667,7 +1677,13 @@ static long btrfs_fallocate(struct file *file, int mode,
 
 		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
 				      alloc_end - cur_offset, 0);
-		BUG_ON(IS_ERR_OR_NULL(em));
+		if (IS_ERR_OR_NULL(em)) {
+			if (!em)
+				ret = -ENOMEM;
+			else
+				ret = PTR_ERR(em);
+			break;
+		}
 		last_byte = min(extent_map_end(em), alloc_end);
 		actual_end = min_t(u64, extent_map_end(em), offset + len);
 		last_byte = (last_byte + mask) & ~mask;
@@ -1737,7 +1753,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
 		return -ENXIO;
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0,
-			 &cached_state, GFP_NOFS);
+			 &cached_state);
 
 	/*
 	 * Delalloc is such a pain.  If we have a hole and we have pending
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index b02e379b14c7..e88330d3df52 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -230,11 +230,13 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
 
 	if (ret) {
 		trans->block_rsv = rsv;
-		WARN_ON(1);
+		btrfs_abort_transaction(trans, root, ret);
 		return ret;
 	}
 
 	ret = btrfs_update_inode(trans, root, inode);
+	if (ret)
+		btrfs_abort_transaction(trans, root, ret);
 	trans->block_rsv = rsv;
 
 	return ret;
@@ -869,7 +871,7 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	io_ctl_prepare_pages(&io_ctl, inode, 0);
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
-			 0, &cached_state, GFP_NOFS);
+			 0, &cached_state);
 
 	node = rb_first(&ctl->free_space_offset);
 	if (!node && cluster) {
@@ -1948,14 +1950,14 @@ again:
 		 */
 		ret = btrfs_add_free_space(block_group, old_start,
 					   offset - old_start);
-		WARN_ON(ret);
+		WARN_ON(ret); /* -ENOMEM */
 		goto out;
 	}
 
 	ret = remove_from_bitmap(ctl, info, &offset, &bytes);
 	if (ret == -EAGAIN)
 		goto again;
-	BUG_ON(ret);
+	BUG_ON(ret); /* logic error */
 out_lock:
 	spin_unlock(&ctl->tree_lock);
 out:
@@ -2346,7 +2348,7 @@ again:
 	rb_erase(&entry->offset_index, &ctl->free_space_offset);
 	ret = tree_insert_offset(&cluster->root, entry->offset,
 				 &entry->offset_index, 1);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -EEXIST; Logic error */
 
 	trace_btrfs_setup_cluster(block_group, cluster,
 				  total_found * block_group->sectorsize, 1);
@@ -2439,7 +2441,7 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
 		ret = tree_insert_offset(&cluster->root, entry->offset,
 					 &entry->offset_index, 0);
 		total_size += entry->bytes;
-		BUG_ON(ret);
+		BUG_ON(ret); /* -EEXIST; Logic error */
 	} while (node && entry != last);
 
 	cluster->max_size = max_extent;
@@ -2830,6 +2832,7 @@ u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root)
 		int ret;
 
 		ret = search_bitmap(ctl, entry, &offset, &count);
+		/* Logic error; Should be empty if it can't find anything */
 		BUG_ON(ret);
 
 		ino = offset;
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index baa74f3db691..a13cf1a96c73 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -19,6 +19,7 @@
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
+#include "print-tree.h"
 
 static int find_name_in_backref(struct btrfs_path *path, const char *name,
 			 int name_len, struct btrfs_inode_ref **ref_ret)
@@ -128,13 +129,14 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
 	item_start = btrfs_item_ptr_offset(leaf, path->slots[0]);
 	memmove_extent_buffer(leaf, ptr, ptr + sub_item_len,
 			      item_size - (ptr + sub_item_len - item_start));
-	ret = btrfs_truncate_item(trans, root, path,
+	btrfs_truncate_item(trans, root, path,
 				  item_size - sub_item_len, 1);
 out:
 	btrfs_free_path(path);
 	return ret;
 }
 
+/* Will return 0, -ENOMEM, -EMLINK, or -EEXIST or anything from the CoW path */
 int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   const char *name, int name_len,
@@ -165,7 +167,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 			goto out;
 
 		old_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
-		ret = btrfs_extend_item(trans, root, path, ins_len);
+		btrfs_extend_item(trans, root, path, ins_len);
 		ref = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				     struct btrfs_inode_ref);
 		ref = (struct btrfs_inode_ref *)((unsigned long)ref + old_size);
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index ee15d88b33d2..b1a1c929ba80 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -178,7 +178,7 @@ static void start_caching(struct btrfs_root *root)
 
 	tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu\n",
 			  root->root_key.objectid);
-	BUG_ON(IS_ERR(tsk));
+	BUG_ON(IS_ERR(tsk)); /* -ENOMEM */
 }
 
 int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid)
@@ -271,7 +271,7 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 			break;
 
 		info = rb_entry(n, struct btrfs_free_space, offset_index);
-		BUG_ON(info->bitmap);
+		BUG_ON(info->bitmap); /* Logic error */
 
 		if (info->offset > root->cache_progress)
 			goto free;
@@ -439,17 +439,16 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	if (ret)
 		goto out;
 	trace_btrfs_space_reservation(root->fs_info, "ino_cache",
-				      (u64)(unsigned long)trans,
-				      trans->bytes_reserved, 1);
+				      trans->transid, trans->bytes_reserved, 1);
 again:
 	inode = lookup_free_ino_inode(root, path);
-	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
+	if (IS_ERR(inode) && (PTR_ERR(inode) != -ENOENT || retry)) {
 		ret = PTR_ERR(inode);
 		goto out_release;
 	}
 
 	if (IS_ERR(inode)) {
-		BUG_ON(retry);
+		BUG_ON(retry); /* Logic error */
 		retry = true;
 
 		ret = create_free_ino_inode(root, trans, path);
@@ -460,12 +459,17 @@ again:
 
 	BTRFS_I(inode)->generation = 0;
 	ret = btrfs_update_inode(trans, root, inode);
-	WARN_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_put;
+	}
 
 	if (i_size_read(inode) > 0) {
 		ret = btrfs_truncate_free_space_cache(root, trans, path, inode);
-		if (ret)
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
 			goto out_put;
+		}
 	}
 
 	spin_lock(&root->cache_lock);
@@ -502,8 +506,7 @@ out_put:
 	iput(inode);
 out_release:
 	trace_btrfs_space_reservation(root->fs_info, "ino_cache",
-				      (u64)(unsigned long)trans,
-				      trans->bytes_reserved, 0);
+				      trans->transid, trans->bytes_reserved, 0);
 	btrfs_block_rsv_release(root, trans->block_rsv, trans->bytes_reserved);
 out:
 	trans->block_rsv = rsv;
@@ -532,7 +535,7 @@ static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
 	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
 	if (ret < 0)
 		goto error;
-	BUG_ON(ret == 0);
+	BUG_ON(ret == 0); /* Corruption */
 	if (path->slots[0] > 0) {
 		slot = path->slots[0] - 1;
 		l = path->nodes[0];
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3a0b5c1f9d31..115bc05e42b0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -150,7 +150,6 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 	inode_add_bytes(inode, size);
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
 				      datasize);
-	BUG_ON(ret);
 	if (ret) {
 		err = ret;
 		goto fail;
@@ -206,9 +205,9 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 	 * could end up racing with unlink.
 	 */
 	BTRFS_I(inode)->disk_i_size = inode->i_size;
-	btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, inode);
 
-	return 0;
+	return ret;
 fail:
 	btrfs_free_path(path);
 	return err;
@@ -250,14 +249,18 @@ static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_drop_extents(trans, inode, start, aligned_end,
 				 &hint_byte, 1);
-	BUG_ON(ret);
+	if (ret)
+		return ret;
 
 	if (isize > actual_end)
 		inline_len = min_t(u64, isize, actual_end);
 	ret = insert_inline_extent(trans, root, inode, start,
 				   inline_len, compressed_size,
 				   compress_type, compressed_pages);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		return ret;
+	}
 	btrfs_delalloc_release_metadata(inode, end + 1 - start);
 	btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
 	return 0;
@@ -293,7 +296,7 @@ static noinline int add_async_extent(struct async_cow *cow,
 	struct async_extent *async_extent;
 
 	async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
-	BUG_ON(!async_extent);
+	BUG_ON(!async_extent); /* -ENOMEM */
 	async_extent->start = start;
 	async_extent->ram_size = ram_size;
 	async_extent->compressed_size = compressed_size;
@@ -344,8 +347,9 @@ static noinline int compress_file_range(struct inode *inode,
 	int will_compress;
 	int compress_type = root->fs_info->compress_type;
 
-	/* if this is a small write inside eof, kick off a defragbot */
-	if (end <= BTRFS_I(inode)->disk_i_size && (end - start + 1) < 16 * 1024)
+	/* if this is a small write inside eof, kick off a defrag */
+	if ((end - start + 1) < 16 * 1024 &&
+	    (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
 		btrfs_add_inode_defrag(NULL, inode);
 
 	actual_end = min_t(u64, isize, end + 1);
@@ -433,7 +437,11 @@ again:
 cont:
 	if (start == 0) {
 		trans = btrfs_join_transaction(root);
-		BUG_ON(IS_ERR(trans));
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+			trans = NULL;
+			goto cleanup_and_out;
+		}
 		trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 		/* lets try to make an inline extent */
@@ -450,11 +458,11 @@ cont:
 						    total_compressed,
 						    compress_type, pages);
 		}
-		if (ret == 0) {
+		if (ret <= 0) {
 			/*
-			 * inline extent creation worked, we don't need
-			 * to create any more async work items.  Unlock
-			 * and free up our temp pages.
+			 * inline extent creation worked or returned error,
+			 * we don't need to create any more async work items.
+			 * Unlock and free up our temp pages.
 			 */
 			extent_clear_unlock_delalloc(inode,
 			     &BTRFS_I(inode)->io_tree,
@@ -547,7 +555,7 @@ cleanup_and_bail_uncompressed:
 	}
 
 out:
-	return 0;
+	return ret;
 
 free_pages_out:
 	for (i = 0; i < nr_pages_ret; i++) {
@@ -557,6 +565,20 @@ free_pages_out:
 	kfree(pages);
 
 	goto out;
+
+cleanup_and_out:
+	extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
+				     start, end, NULL,
+				     EXTENT_CLEAR_UNLOCK_PAGE |
+				     EXTENT_CLEAR_DIRTY |
+				     EXTENT_CLEAR_DELALLOC |
+				     EXTENT_SET_WRITEBACK |
+				     EXTENT_END_WRITEBACK);
+	if (!trans || IS_ERR(trans))
+		btrfs_error(root->fs_info, ret, "Failed to join transaction");
+	else
+		btrfs_abort_transaction(trans, root, ret);
+	goto free_pages_out;
 }
 
 /*
@@ -597,7 +619,7 @@ retry:
 
 			lock_extent(io_tree, async_extent->start,
 					 async_extent->start +
-					 async_extent->ram_size - 1, GFP_NOFS);
+					 async_extent->ram_size - 1);
 
 			/* allocate blocks */
 			ret = cow_file_range(inode, async_cow->locked_page,
@@ -606,6 +628,8 @@ retry:
 					     async_extent->ram_size - 1,
 					     &page_started, &nr_written, 0);
 
+			/* JDM XXX */
+
 			/*
 			 * if page_started, cow_file_range inserted an
 			 * inline extent and took care of all the unlocking
@@ -625,18 +649,21 @@ retry:
 		}
 
 		lock_extent(io_tree, async_extent->start,
-			    async_extent->start + async_extent->ram_size - 1,
-			    GFP_NOFS);
+			    async_extent->start + async_extent->ram_size - 1);
 
 		trans = btrfs_join_transaction(root);
-		BUG_ON(IS_ERR(trans));
-		trans->block_rsv = &root->fs_info->delalloc_block_rsv;
-		ret = btrfs_reserve_extent(trans, root,
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+		} else {
+			trans->block_rsv = &root->fs_info->delalloc_block_rsv;
+			ret = btrfs_reserve_extent(trans, root,
 					   async_extent->compressed_size,
 					   async_extent->compressed_size,
-					   0, alloc_hint,
-					   (u64)-1, &ins, 1);
-		btrfs_end_transaction(trans, root);
+					   0, alloc_hint, &ins, 1);
+			if (ret)
+				btrfs_abort_transaction(trans, root, ret);
+			btrfs_end_transaction(trans, root);
+		}
 
 		if (ret) {
 			int i;
@@ -649,8 +676,10 @@ retry:
 			async_extent->pages = NULL;
 			unlock_extent(io_tree, async_extent->start,
 				      async_extent->start +
-				      async_extent->ram_size - 1, GFP_NOFS);
-			goto retry;
+				      async_extent->ram_size - 1);
+			if (ret == -ENOSPC)
+				goto retry;
+			goto out_free; /* JDM: Requeue? */
 		}
 
 		/*
@@ -662,7 +691,7 @@ retry:
 					async_extent->ram_size - 1, 0);
 
 		em = alloc_extent_map();
-		BUG_ON(!em);
+		BUG_ON(!em); /* -ENOMEM */
 		em->start = async_extent->start;
 		em->len = async_extent->ram_size;
 		em->orig_start = em->start;
@@ -694,7 +723,7 @@ retry:
 						ins.offset,
 						BTRFS_ORDERED_COMPRESSED,
 						async_extent->compress_type);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 
 		/*
 		 * clear dirty, set writeback and unlock the pages.
@@ -716,13 +745,17 @@ retry:
 				    ins.offset, async_extent->pages,
 				    async_extent->nr_pages);
 
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 		alloc_hint = ins.objectid + ins.offset;
 		kfree(async_extent);
 		cond_resched();
 	}
-
-	return 0;
+	ret = 0;
+out:
+	return ret;
+out_free:
+	kfree(async_extent);
+	goto out;
 }
 
 static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
@@ -791,7 +824,18 @@ static noinline int cow_file_range(struct inode *inode,
 
 	BUG_ON(btrfs_is_free_space_inode(root, inode));
 	trans = btrfs_join_transaction(root);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans)) {
+		extent_clear_unlock_delalloc(inode,
+			     &BTRFS_I(inode)->io_tree,
+			     start, end, NULL,
+			     EXTENT_CLEAR_UNLOCK_PAGE |
+			     EXTENT_CLEAR_UNLOCK |
+			     EXTENT_CLEAR_DELALLOC |
+			     EXTENT_CLEAR_DIRTY |
+			     EXTENT_SET_WRITEBACK |
+			     EXTENT_END_WRITEBACK);
+		return PTR_ERR(trans);
+	}
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	num_bytes = (end - start + blocksize) & ~(blocksize - 1);
@@ -800,7 +844,8 @@ static noinline int cow_file_range(struct inode *inode,
 	ret = 0;
 
 	/* if this is a small write inside eof, kick off defrag */
-	if (end <= BTRFS_I(inode)->disk_i_size && num_bytes < 64 * 1024)
+	if (num_bytes < 64 * 1024 &&
+	    (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
 		btrfs_add_inode_defrag(trans, inode);
 
 	if (start == 0) {
@@ -821,8 +866,10 @@ static noinline int cow_file_range(struct inode *inode,
 			*nr_written = *nr_written +
 			     (end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE;
 			*page_started = 1;
-			ret = 0;
 			goto out;
+		} else if (ret < 0) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out_unlock;
 		}
 	}
 
@@ -838,11 +885,14 @@ static noinline int cow_file_range(struct inode *inode,
 		cur_alloc_size = disk_num_bytes;
 		ret = btrfs_reserve_extent(trans, root, cur_alloc_size,
 					   root->sectorsize, 0, alloc_hint,
-					   (u64)-1, &ins, 1);
-		BUG_ON(ret);
+					   &ins, 1);
+		if (ret < 0) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out_unlock;
+		}
 
 		em = alloc_extent_map();
-		BUG_ON(!em);
+		BUG_ON(!em); /* -ENOMEM */
 		em->start = start;
 		em->orig_start = em->start;
 		ram_size = ins.offset;
@@ -868,13 +918,16 @@ static noinline int cow_file_range(struct inode *inode,
 		cur_alloc_size = ins.offset;
 		ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
 					       ram_size, cur_alloc_size, 0);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 
 		if (root->root_key.objectid ==
 		    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 			ret = btrfs_reloc_clone_csums(inode, start,
 						      cur_alloc_size);
-			BUG_ON(ret);
+			if (ret) {
+				btrfs_abort_transaction(trans, root, ret);
+				goto out_unlock;
+			}
 		}
 
 		if (disk_num_bytes < cur_alloc_size)
@@ -899,11 +952,23 @@ static noinline int cow_file_range(struct inode *inode,
 		alloc_hint = ins.objectid + ins.offset;
 		start += cur_alloc_size;
 	}
-out:
 	ret = 0;
+out:
 	btrfs_end_transaction(trans, root);
 
 	return ret;
+out_unlock:
+	extent_clear_unlock_delalloc(inode,
+		     &BTRFS_I(inode)->io_tree,
+		     start, end, NULL,
+		     EXTENT_CLEAR_UNLOCK_PAGE |
+		     EXTENT_CLEAR_UNLOCK |
+		     EXTENT_CLEAR_DELALLOC |
+		     EXTENT_CLEAR_DIRTY |
+		     EXTENT_SET_WRITEBACK |
+		     EXTENT_END_WRITEBACK);
+
+	goto out;
 }
 
 /*
@@ -969,7 +1034,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 			 1, 0, NULL, GFP_NOFS);
 	while (start < end) {
 		async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS);
-		BUG_ON(!async_cow);
+		BUG_ON(!async_cow); /* -ENOMEM */
 		async_cow->inode = inode;
 		async_cow->root = root;
 		async_cow->locked_page = locked_page;
@@ -1060,7 +1125,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	u64 disk_bytenr;
 	u64 num_bytes;
 	int extent_type;
-	int ret;
+	int ret, err;
 	int type;
 	int nocow;
 	int check_prev = 1;
@@ -1078,7 +1143,11 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	else
 		trans = btrfs_join_transaction(root);
 
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans)) {
+		btrfs_free_path(path);
+		return PTR_ERR(trans);
+	}
+
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	cow_start = (u64)-1;
@@ -1086,7 +1155,10 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	while (1) {
 		ret = btrfs_lookup_file_extent(trans, root, path, ino,
 					       cur_offset, 0);
-		BUG_ON(ret < 0);
+		if (ret < 0) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto error;
+		}
 		if (ret > 0 && path->slots[0] > 0 && check_prev) {
 			leaf = path->nodes[0];
 			btrfs_item_key_to_cpu(leaf, &found_key,
@@ -1100,8 +1172,10 @@ next_slot:
 		leaf = path->nodes[0];
 		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
 			ret = btrfs_next_leaf(root, path);
-			if (ret < 0)
-				BUG_ON(1);
+			if (ret < 0) {
+				btrfs_abort_transaction(trans, root, ret);
+				goto error;
+			}
 			if (ret > 0)
 				break;
 			leaf = path->nodes[0];
@@ -1189,7 +1263,10 @@ out_check:
 			ret = cow_file_range(inode, locked_page, cow_start,
 					found_key.offset - 1, page_started,
 					nr_written, 1);
-			BUG_ON(ret);
+			if (ret) {
+				btrfs_abort_transaction(trans, root, ret);
+				goto error;
+			}
 			cow_start = (u64)-1;
 		}
 
@@ -1198,7 +1275,7 @@ out_check:
 			struct extent_map_tree *em_tree;
 			em_tree = &BTRFS_I(inode)->extent_tree;
 			em = alloc_extent_map();
-			BUG_ON(!em);
+			BUG_ON(!em); /* -ENOMEM */
 			em->start = cur_offset;
 			em->orig_start = em->start;
 			em->len = num_bytes;
@@ -1224,13 +1301,16 @@ out_check:
 
 		ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr,
 					       num_bytes, num_bytes, type);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 
 		if (root->root_key.objectid ==
 		    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 			ret = btrfs_reloc_clone_csums(inode, cur_offset,
 						      num_bytes);
-			BUG_ON(ret);
+			if (ret) {
+				btrfs_abort_transaction(trans, root, ret);
+				goto error;
+			}
 		}
 
 		extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
@@ -1249,18 +1329,23 @@ out_check:
 	if (cow_start != (u64)-1) {
 		ret = cow_file_range(inode, locked_page, cow_start, end,
 				     page_started, nr_written, 1);
-		BUG_ON(ret);
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto error;
+		}
 	}
 
+error:
 	if (nolock) {
-		ret = btrfs_end_transaction_nolock(trans, root);
-		BUG_ON(ret);
+		err = btrfs_end_transaction_nolock(trans, root);
 	} else {
-		ret = btrfs_end_transaction(trans, root);
-		BUG_ON(ret);
+		err = btrfs_end_transaction(trans, root);
 	}
+	if (!ret)
+		ret = err;
+
 	btrfs_free_path(path);
-	return 0;
+	return ret;
 }
 
 /*
@@ -1425,10 +1510,11 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 	map_length = length;
 	ret = btrfs_map_block(map_tree, READ, logical,
 			      &map_length, NULL, 0);
-
+	/* Will always return 0 or 1 with map_multi == NULL */
+	BUG_ON(ret < 0);
 	if (map_length < length + size)
 		return 1;
-	return ret;
+	return 0;
 }
 
 /*
@@ -1448,7 +1534,7 @@ static int __btrfs_submit_bio_start(struct inode *inode, int rw,
 	int ret = 0;
 
 	ret = btrfs_csum_one_bio(root, inode, bio, 0, 0);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -ENOMEM */
 	return 0;
 }
 
@@ -1479,14 +1565,16 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret = 0;
 	int skip_sum;
+	int metadata = 0;
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
 	if (btrfs_is_free_space_inode(root, inode))
-		ret = btrfs_bio_wq_end_io(root->fs_info, bio, 2);
-	else
-		ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
-	BUG_ON(ret);
+		metadata = 2;
+
+	ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata);
+	if (ret)
+		return ret;
 
 	if (!(rw & REQ_WRITE)) {
 		if (bio_flags & EXTENT_BIO_COMPRESSED) {
@@ -1571,7 +1659,7 @@ again:
 	page_end = page_offset(page) + PAGE_CACHE_SIZE - 1;
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, 0,
-			 &cached_state, GFP_NOFS);
+			 &cached_state);
 
 	/* already ordered? We're done */
 	if (PagePrivate2(page))
@@ -1675,13 +1763,15 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	 */
 	ret = btrfs_drop_extents(trans, inode, file_pos, file_pos + num_bytes,
 				 &hint, 0);
-	BUG_ON(ret);
+	if (ret)
+		goto out;
 
 	ins.objectid = btrfs_ino(inode);
 	ins.offset = file_pos;
 	ins.type = BTRFS_EXTENT_DATA_KEY;
 	ret = btrfs_insert_empty_item(trans, root, path, &ins, sizeof(*fi));
-	BUG_ON(ret);
+	if (ret)
+		goto out;
 	leaf = path->nodes[0];
 	fi = btrfs_item_ptr(leaf, path->slots[0],
 			    struct btrfs_file_extent_item);
@@ -1709,10 +1799,10 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	ret = btrfs_alloc_reserved_file_extent(trans, root,
 					root->root_key.objectid,
 					btrfs_ino(inode), file_pos, &ins);
-	BUG_ON(ret);
+out:
 	btrfs_free_path(path);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -1740,35 +1830,41 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 					     end - start + 1);
 	if (!ret)
 		return 0;
-	BUG_ON(!ordered_extent);
+	BUG_ON(!ordered_extent); /* Logic error */
 
 	nolock = btrfs_is_free_space_inode(root, inode);
 
 	if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
-		BUG_ON(!list_empty(&ordered_extent->list));
+		BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */
 		ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
 		if (!ret) {
 			if (nolock)
 				trans = btrfs_join_transaction_nolock(root);
 			else
 				trans = btrfs_join_transaction(root);
-			BUG_ON(IS_ERR(trans));
+			if (IS_ERR(trans))
+				return PTR_ERR(trans);
 			trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 			ret = btrfs_update_inode_fallback(trans, root, inode);
-			BUG_ON(ret);
+			if (ret) /* -ENOMEM or corruption */
+				btrfs_abort_transaction(trans, root, ret);
 		}
 		goto out;
 	}
 
 	lock_extent_bits(io_tree, ordered_extent->file_offset,
 			 ordered_extent->file_offset + ordered_extent->len - 1,
-			 0, &cached_state, GFP_NOFS);
+			 0, &cached_state);
 
 	if (nolock)
 		trans = btrfs_join_transaction_nolock(root);
 	else
 		trans = btrfs_join_transaction(root);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		trans = NULL;
+		goto out_unlock;
+	}
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
@@ -1779,7 +1875,6 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
 						ordered_extent->len);
-		BUG_ON(ret);
 	} else {
 		BUG_ON(root == root->fs_info->tree_root);
 		ret = insert_reserved_file_extent(trans, inode,
@@ -1793,11 +1888,14 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 		unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
 				   ordered_extent->file_offset,
 				   ordered_extent->len);
-		BUG_ON(ret);
 	}
 	unlock_extent_cached(io_tree, ordered_extent->file_offset,
 			     ordered_extent->file_offset +
 			     ordered_extent->len - 1, &cached_state, GFP_NOFS);
+	if (ret < 0) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out;
+	}
 
 	add_pending_csums(trans, inode, ordered_extent->file_offset,
 			  &ordered_extent->list);
@@ -1805,7 +1903,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 	ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
 	if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
 		ret = btrfs_update_inode_fallback(trans, root, inode);
-		BUG_ON(ret);
+		if (ret) { /* -ENOMEM or corruption */
+			btrfs_abort_transaction(trans, root, ret);
+			goto out;
+		}
 	}
 	ret = 0;
 out:
@@ -1824,6 +1925,11 @@ out:
 	btrfs_put_ordered_extent(ordered_extent);
 
 	return 0;
+out_unlock:
+	unlock_extent_cached(io_tree, ordered_extent->file_offset,
+			     ordered_extent->file_offset +
+			     ordered_extent->len - 1, &cached_state, GFP_NOFS);
+	goto out;
 }
 
 static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
@@ -1905,6 +2011,8 @@ struct delayed_iput {
 	struct inode *inode;
 };
 
+/* JDM: If this is fs-wide, why can't we add a pointer to
+ * btrfs_inode instead and avoid the allocation? */
 void btrfs_add_delayed_iput(struct inode *inode)
 {
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
@@ -2051,20 +2159,27 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	/* grab metadata reservation from transaction handle */
 	if (reserve) {
 		ret = btrfs_orphan_reserve_metadata(trans, inode);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOSPC in reservation; Logic error? JDM */
 	}
 
 	/* insert an orphan item to track this unlinked/truncated file */
 	if (insert >= 1) {
 		ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
-		BUG_ON(ret && ret != -EEXIST);
+		if (ret && ret != -EEXIST) {
+			btrfs_abort_transaction(trans, root, ret);
+			return ret;
+		}
+		ret = 0;
 	}
 
 	/* insert an orphan item to track subvolume contains orphan files */
 	if (insert >= 2) {
 		ret = btrfs_insert_orphan_item(trans, root->fs_info->tree_root,
 					       root->root_key.objectid);
-		BUG_ON(ret);
+		if (ret && ret != -EEXIST) {
+			btrfs_abort_transaction(trans, root, ret);
+			return ret;
+		}
 	}
 	return 0;
 }
@@ -2094,7 +2209,7 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode)
 
 	if (trans && delete_item) {
 		ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode));
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM or corruption (JDM: Recheck) */
 	}
 
 	if (release_rsv)
@@ -2228,7 +2343,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 			}
 			ret = btrfs_del_orphan_item(trans, root,
 						    found_key.objectid);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM or corruption (JDM: Recheck) */
 			btrfs_end_transaction(trans, root);
 			continue;
 		}
@@ -2610,16 +2725,22 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		printk(KERN_INFO "btrfs failed to delete reference to %.*s, "
 		       "inode %llu parent %llu\n", name_len, name,
 		       (unsigned long long)ino, (unsigned long long)dir_ino);
+		btrfs_abort_transaction(trans, root, ret);
 		goto err;
 	}
 
 	ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
 		goto err;
+	}
 
 	ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len,
 					 inode, dir_ino);
-	BUG_ON(ret != 0 && ret != -ENOENT);
+	if (ret != 0 && ret != -ENOENT) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto err;
+	}
 
 	ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len,
 					   dir, index);
@@ -2777,7 +2898,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 			err = ret;
 			goto out;
 		}
-		BUG_ON(ret == 0);
+		BUG_ON(ret == 0); /* Corruption */
 		if (check_path_shared(root, path))
 			goto out;
 		btrfs_release_path(path);
@@ -2810,7 +2931,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 		err = PTR_ERR(ref);
 		goto out;
 	}
-	BUG_ON(!ref);
+	BUG_ON(!ref); /* Logic error */
 	if (check_path_shared(root, path))
 		goto out;
 	index = btrfs_inode_ref_index(path->nodes[0], ref);
@@ -2917,23 +3038,42 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 
 	di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
 				   name, name_len, -1);
-	BUG_ON(IS_ERR_OR_NULL(di));
+	if (IS_ERR_OR_NULL(di)) {
+		if (!di)
+			ret = -ENOENT;
+		else
+			ret = PTR_ERR(di);
+		goto out;
+	}
 
 	leaf = path->nodes[0];
 	btrfs_dir_item_key_to_cpu(leaf, di, &key);
 	WARN_ON(key.type != BTRFS_ROOT_ITEM_KEY || key.objectid != objectid);
 	ret = btrfs_delete_one_dir_name(trans, root, path, di);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out;
+	}
 	btrfs_release_path(path);
 
 	ret = btrfs_del_root_ref(trans, root->fs_info->tree_root,
 				 objectid, root->root_key.objectid,
 				 dir_ino, &index, name, name_len);
 	if (ret < 0) {
-		BUG_ON(ret != -ENOENT);
+		if (ret != -ENOENT) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out;
+		}
 		di = btrfs_search_dir_index_item(root, path, dir_ino,
 						 name, name_len);
-		BUG_ON(IS_ERR_OR_NULL(di));
+		if (IS_ERR_OR_NULL(di)) {
+			if (!di)
+				ret = -ENOENT;
+			else
+				ret = PTR_ERR(di);
+			btrfs_abort_transaction(trans, root, ret);
+			goto out;
+		}
 
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
@@ -2943,15 +3083,19 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	btrfs_release_path(path);
 
 	ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out;
+	}
 
 	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 	ret = btrfs_update_inode(trans, root, dir);
-	BUG_ON(ret);
-
+	if (ret)
+		btrfs_abort_transaction(trans, root, ret);
+out:
 	btrfs_free_path(path);
-	return 0;
+	return ret;
 }
 
 static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
@@ -3161,8 +3305,8 @@ search_again:
 				}
 				size =
 				    btrfs_file_extent_calc_inline_size(size);
-				ret = btrfs_truncate_item(trans, root, path,
-							  size, 1);
+				btrfs_truncate_item(trans, root, path,
+						    size, 1);
 			} else if (root->ref_cows) {
 				inode_sub_bytes(inode, item_end + 1 -
 						found_key.offset);
@@ -3210,7 +3354,11 @@ delete:
 				ret = btrfs_del_items(trans, root, path,
 						pending_del_slot,
 						pending_del_nr);
-				BUG_ON(ret);
+				if (ret) {
+					btrfs_abort_transaction(trans,
+								root, ret);
+					goto error;
+				}
 				pending_del_nr = 0;
 			}
 			btrfs_release_path(path);
@@ -3223,8 +3371,10 @@ out:
 	if (pending_del_nr) {
 		ret = btrfs_del_items(trans, root, path, pending_del_slot,
 				      pending_del_nr);
-		BUG_ON(ret);
+		if (ret)
+			btrfs_abort_transaction(trans, root, ret);
 	}
+error:
 	btrfs_free_path(path);
 	return err;
 }
@@ -3282,8 +3432,7 @@ again:
 	}
 	wait_on_page_writeback(page);
 
-	lock_extent_bits(io_tree, page_start, page_end, 0, &cached_state,
-			 GFP_NOFS);
+	lock_extent_bits(io_tree, page_start, page_end, 0, &cached_state);
 	set_page_extent_mapped(page);
 
 	ordered = btrfs_lookup_ordered_extent(inode, page_start);
@@ -3359,7 +3508,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 		btrfs_wait_ordered_range(inode, hole_start,
 					 block_end - hole_start);
 		lock_extent_bits(io_tree, hole_start, block_end - 1, 0,
-				 &cached_state, GFP_NOFS);
+				 &cached_state);
 		ordered = btrfs_lookup_ordered_extent(inode, hole_start);
 		if (!ordered)
 			break;
@@ -3372,7 +3521,10 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 	while (1) {
 		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
 				block_end - cur_offset, 0);
-		BUG_ON(IS_ERR_OR_NULL(em));
+		if (IS_ERR(em)) {
+			err = PTR_ERR(em);
+			break;
+		}
 		last_byte = min(extent_map_end(em), block_end);
 		last_byte = (last_byte + mask) & ~mask;
 		if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
@@ -3389,7 +3541,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 						 cur_offset + hole_size,
 						 &hint_byte, 1);
 			if (err) {
-				btrfs_update_inode(trans, root, inode);
+				btrfs_abort_transaction(trans, root, err);
 				btrfs_end_transaction(trans, root);
 				break;
 			}
@@ -3399,7 +3551,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 					0, hole_size, 0, hole_size,
 					0, 0, 0);
 			if (err) {
-				btrfs_update_inode(trans, root, inode);
+				btrfs_abort_transaction(trans, root, err);
 				btrfs_end_transaction(trans, root);
 				break;
 			}
@@ -3779,7 +3931,7 @@ static void inode_tree_del(struct inode *inode)
 	}
 }
 
-int btrfs_invalidate_inodes(struct btrfs_root *root)
+void btrfs_invalidate_inodes(struct btrfs_root *root)
 {
 	struct rb_node *node;
 	struct rb_node *prev;
@@ -3839,7 +3991,6 @@ again:
 		node = rb_next(node);
 	}
 	spin_unlock(&root->inode_lock);
-	return 0;
 }
 
 static int btrfs_init_locked_inode(struct inode *inode, void *p)
@@ -4581,18 +4732,26 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 					     parent_ino, index);
 	}
 
-	if (ret == 0) {
-		ret = btrfs_insert_dir_item(trans, root, name, name_len,
-					    parent_inode, &key,
-					    btrfs_inode_type(inode), index);
-		if (ret)
-			goto fail_dir_item;
+	/* Nothing to clean up yet */
+	if (ret)
+		return ret;
 
-		btrfs_i_size_write(parent_inode, parent_inode->i_size +
-				   name_len * 2);
-		parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
-		ret = btrfs_update_inode(trans, root, parent_inode);
+	ret = btrfs_insert_dir_item(trans, root, name, name_len,
+				    parent_inode, &key,
+				    btrfs_inode_type(inode), index);
+	if (ret == -EEXIST)
+		goto fail_dir_item;
+	else if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		return ret;
 	}
+
+	btrfs_i_size_write(parent_inode, parent_inode->i_size +
+			   name_len * 2);
+	parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
+	ret = btrfs_update_inode(trans, root, parent_inode);
+	if (ret)
+		btrfs_abort_transaction(trans, root, ret);
 	return ret;
 
 fail_dir_item:
@@ -4806,7 +4965,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	} else {
 		struct dentry *parent = dentry->d_parent;
 		err = btrfs_update_inode(trans, root, inode);
-		BUG_ON(err);
+		if (err)
+			goto fail;
 		d_instantiate(dentry, inode);
 		btrfs_log_new_name(trans, inode, NULL, parent);
 	}
@@ -5137,7 +5297,7 @@ again:
 				ret = uncompress_inline(path, inode, page,
 							pg_offset,
 							extent_offset, item);
-				BUG_ON(ret);
+				BUG_ON(ret); /* -ENOMEM */
 			} else {
 				map = kmap(page);
 				read_extent_buffer(leaf, map + pg_offset, ptr,
@@ -5252,6 +5412,7 @@ out:
 		free_extent_map(em);
 		return ERR_PTR(err);
 	}
+	BUG_ON(!em); /* Error is always set */
 	return em;
 }
 
@@ -5414,7 +5575,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 
 	alloc_hint = get_extent_allocation_hint(inode, start, len);
 	ret = btrfs_reserve_extent(trans, root, len, root->sectorsize, 0,
-				   alloc_hint, (u64)-1, &ins, 1);
+				   alloc_hint, &ins, 1);
 	if (ret) {
 		em = ERR_PTR(ret);
 		goto out;
@@ -5602,7 +5763,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		free_extent_map(em);
 		/* DIO will do one hole at a time, so just unlock a sector */
 		unlock_extent(&BTRFS_I(inode)->io_tree, start,
-			      start + root->sectorsize - 1, GFP_NOFS);
+			      start + root->sectorsize - 1);
 		return 0;
 	}
 
@@ -5743,7 +5904,7 @@ static void btrfs_endio_direct_read(struct bio *bio, int err)
 	} while (bvec <= bvec_end);
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
-		      dip->logical_offset + dip->bytes - 1, GFP_NOFS);
+		      dip->logical_offset + dip->bytes - 1);
 	bio->bi_private = dip->private;
 
 	kfree(dip->csums);
@@ -5794,7 +5955,7 @@ again:
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, ordered->file_offset,
 			 ordered->file_offset + ordered->len - 1, 0,
-			 &cached_state, GFP_NOFS);
+			 &cached_state);
 
 	if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags)) {
 		ret = btrfs_mark_extent_written(trans, inode,
@@ -5868,7 +6029,7 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode, int rw,
 	int ret;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	ret = btrfs_csum_one_bio(root, inode, bio, offset, 1);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -ENOMEM */
 	return 0;
 }
 
@@ -6209,7 +6370,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 
 	while (1) {
 		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				 0, &cached_state, GFP_NOFS);
+				 0, &cached_state);
 		/*
 		 * We're concerned with the entire range that we're going to be
 		 * doing DIO to, so we need to make sure theres no ordered
@@ -6233,7 +6394,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 	if (writing) {
 		write_bits = EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING;
 		ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				     EXTENT_DELALLOC, 0, NULL, &cached_state,
+				     EXTENT_DELALLOC, NULL, &cached_state,
 				     GFP_NOFS);
 		if (ret) {
 			clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
@@ -6363,8 +6524,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset)
 		btrfs_releasepage(page, GFP_NOFS);
 		return;
 	}
-	lock_extent_bits(tree, page_start, page_end, 0, &cached_state,
-			 GFP_NOFS);
+	lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
 	ordered = btrfs_lookup_ordered_extent(page->mapping->host,
 					   page_offset(page));
 	if (ordered) {
@@ -6386,8 +6546,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset)
 		}
 		btrfs_put_ordered_extent(ordered);
 		cached_state = NULL;
-		lock_extent_bits(tree, page_start, page_end, 0, &cached_state,
-				 GFP_NOFS);
+		lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
 	}
 	clear_extent_bit(tree, page_start, page_end,
 		 EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
@@ -6462,8 +6621,7 @@ again:
 	}
 	wait_on_page_writeback(page);
 
-	lock_extent_bits(io_tree, page_start, page_end, 0, &cached_state,
-			 GFP_NOFS);
+	lock_extent_bits(io_tree, page_start, page_end, 0, &cached_state);
 	set_page_extent_mapped(page);
 
 	/*
@@ -6737,10 +6895,9 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 	btrfs_i_size_write(inode, 0);
 
 	err = btrfs_update_inode(trans, new_root, inode);
-	BUG_ON(err);
 
 	iput(inode);
-	return 0;
+	return err;
 }
 
 struct inode *btrfs_alloc_inode(struct super_block *sb)
@@ -6783,6 +6940,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	extent_map_tree_init(&ei->extent_tree);
 	extent_io_tree_init(&ei->io_tree, &inode->i_data);
 	extent_io_tree_init(&ei->io_failure_tree, &inode->i_data);
+	ei->io_tree.track_uptodate = 1;
+	ei->io_failure_tree.track_uptodate = 1;
 	mutex_init(&ei->log_mutex);
 	mutex_init(&ei->delalloc_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
@@ -7072,7 +7231,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (!ret)
 			ret = btrfs_update_inode(trans, root, old_inode);
 	}
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_fail;
+	}
 
 	if (new_inode) {
 		new_inode->i_ctime = CURRENT_TIME;
@@ -7090,11 +7252,14 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 						 new_dentry->d_name.name,
 						 new_dentry->d_name.len);
 		}
-		BUG_ON(ret);
-		if (new_inode->i_nlink == 0) {
+		if (!ret && new_inode->i_nlink == 0) {
 			ret = btrfs_orphan_add(trans, new_dentry->d_inode);
 			BUG_ON(ret);
 		}
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out_fail;
+		}
 	}
 
 	fixup_inode_flags(new_dir, old_inode);
@@ -7102,7 +7267,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	ret = btrfs_add_link(trans, new_dir, old_inode,
 			     new_dentry->d_name.name,
 			     new_dentry->d_name.len, 0, index);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_fail;
+	}
 
 	if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
 		struct dentry *parent = new_dentry->d_parent;
@@ -7315,7 +7483,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		}
 
 		ret = btrfs_reserve_extent(trans, root, num_bytes, min_size,
-					   0, *alloc_hint, (u64)-1, &ins, 1);
+					   0, *alloc_hint, &ins, 1);
 		if (ret) {
 			if (own_trans)
 				btrfs_end_transaction(trans, root);
@@ -7327,7 +7495,12 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 						  ins.offset, ins.offset,
 						  ins.offset, 0, 0, 0,
 						  BTRFS_FILE_EXTENT_PREALLOC);
-		BUG_ON(ret);
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
+			if (own_trans)
+				btrfs_end_transaction(trans, root);
+			break;
+		}
 		btrfs_drop_extent_cache(inode, cur_offset,
 					cur_offset + ins.offset -1, 0);
 
@@ -7349,7 +7522,13 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		}
 
 		ret = btrfs_update_inode(trans, root, inode);
-		BUG_ON(ret);
+
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
+			if (own_trans)
+				btrfs_end_transaction(trans, root);
+			break;
+		}
 
 		if (own_trans)
 			btrfs_end_transaction(trans, root);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d8b54715c2de..18cc23d164a8 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -425,22 +425,37 @@ static noinline int create_subvol(struct btrfs_root *root,
 
 	key.offset = (u64)-1;
 	new_root = btrfs_read_fs_root_no_name(root->fs_info, &key);
-	BUG_ON(IS_ERR(new_root));
+	if (IS_ERR(new_root)) {
+		btrfs_abort_transaction(trans, root, PTR_ERR(new_root));
+		ret = PTR_ERR(new_root);
+		goto fail;
+	}
 
 	btrfs_record_root_in_trans(trans, new_root);
 
 	ret = btrfs_create_subvol_root(trans, new_root, new_dirid);
+	if (ret) {
+		/* We potentially lose an unused inode item here */
+		btrfs_abort_transaction(trans, root, ret);
+		goto fail;
+	}
+
 	/*
 	 * insert the directory item
 	 */
 	ret = btrfs_set_inode_index(dir, &index);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto fail;
+	}
 
 	ret = btrfs_insert_dir_item(trans, root,
 				    name, namelen, dir, &key,
 				    BTRFS_FT_DIR, index);
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
 		goto fail;
+	}
 
 	btrfs_i_size_write(dir, dir->i_size + namelen * 2);
 	ret = btrfs_update_inode(trans, root, dir);
@@ -769,6 +784,31 @@ none:
 	return -ENOENT;
 }
 
+/*
+ * Validaty check of prev em and next em:
+ * 1) no prev/next em
+ * 2) prev/next em is an hole/inline extent
+ */
+static int check_adjacent_extents(struct inode *inode, struct extent_map *em)
+{
+	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map *prev = NULL, *next = NULL;
+	int ret = 0;
+
+	read_lock(&em_tree->lock);
+	prev = lookup_extent_mapping(em_tree, em->start - 1, (u64)-1);
+	next = lookup_extent_mapping(em_tree, em->start + em->len, (u64)-1);
+	read_unlock(&em_tree->lock);
+
+	if ((!prev || prev->block_start >= EXTENT_MAP_LAST_BYTE) &&
+	    (!next || next->block_start >= EXTENT_MAP_LAST_BYTE))
+		ret = 1;
+	free_extent_map(prev);
+	free_extent_map(next);
+
+	return ret;
+}
+
 static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 			       int thresh, u64 *last_len, u64 *skip,
 			       u64 *defrag_end)
@@ -797,17 +837,25 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 
 	if (!em) {
 		/* get the big lock and read metadata off disk */
-		lock_extent(io_tree, start, start + len - 1, GFP_NOFS);
+		lock_extent(io_tree, start, start + len - 1);
 		em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
-		unlock_extent(io_tree, start, start + len - 1, GFP_NOFS);
+		unlock_extent(io_tree, start, start + len - 1);
 
 		if (IS_ERR(em))
 			return 0;
 	}
 
 	/* this will cover holes, and inline extents */
-	if (em->block_start >= EXTENT_MAP_LAST_BYTE)
+	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
 		ret = 0;
+		goto out;
+	}
+
+	/* If we have nothing to merge with us, just skip. */
+	if (check_adjacent_extents(inode, em)) {
+		ret = 0;
+		goto out;
+	}
 
 	/*
 	 * we hit a real extent, if it is big don't bother defragging it again
@@ -815,6 +863,7 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 	if ((*last_len == 0 || *last_len >= thresh) && em->len >= thresh)
 		ret = 0;
 
+out:
 	/*
 	 * last_len ends up being a counter of how many bytes we've defragged.
 	 * every time we choose not to defrag an extent, we reset *last_len
@@ -856,6 +905,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	u64 isize = i_size_read(inode);
 	u64 page_start;
 	u64 page_end;
+	u64 page_cnt;
 	int ret;
 	int i;
 	int i_done;
@@ -864,19 +914,21 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	struct extent_io_tree *tree;
 	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
 
-	if (isize == 0)
-		return 0;
 	file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
+	if (!isize || start_index > file_end)
+		return 0;
+
+	page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
 
 	ret = btrfs_delalloc_reserve_space(inode,
-					   num_pages << PAGE_CACHE_SHIFT);
+					   page_cnt << PAGE_CACHE_SHIFT);
 	if (ret)
 		return ret;
 	i_done = 0;
 	tree = &BTRFS_I(inode)->io_tree;
 
 	/* step one, lock all the pages */
-	for (i = 0; i < num_pages; i++) {
+	for (i = 0; i < page_cnt; i++) {
 		struct page *page;
 again:
 		page = find_or_create_page(inode->i_mapping,
@@ -887,10 +939,10 @@ again:
 		page_start = page_offset(page);
 		page_end = page_start + PAGE_CACHE_SIZE - 1;
 		while (1) {
-			lock_extent(tree, page_start, page_end, GFP_NOFS);
+			lock_extent(tree, page_start, page_end);
 			ordered = btrfs_lookup_ordered_extent(inode,
 							      page_start);
-			unlock_extent(tree, page_start, page_end, GFP_NOFS);
+			unlock_extent(tree, page_start, page_end);
 			if (!ordered)
 				break;
 
@@ -898,6 +950,15 @@ again:
 			btrfs_start_ordered_extent(inode, ordered, 1);
 			btrfs_put_ordered_extent(ordered);
 			lock_page(page);
+			/*
+			 * we unlocked the page above, so we need check if
+			 * it was released or not.
+			 */
+			if (page->mapping != inode->i_mapping) {
+				unlock_page(page);
+				page_cache_release(page);
+				goto again;
+			}
 		}
 
 		if (!PageUptodate(page)) {
@@ -911,15 +972,6 @@ again:
 			}
 		}
 
-		isize = i_size_read(inode);
-		file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
-		if (!isize || page->index > file_end) {
-			/* whoops, we blew past eof, skip this page */
-			unlock_page(page);
-			page_cache_release(page);
-			break;
-		}
-
 		if (page->mapping != inode->i_mapping) {
 			unlock_page(page);
 			page_cache_release(page);
@@ -946,19 +998,18 @@ again:
 	page_end = page_offset(pages[i_done - 1]) + PAGE_CACHE_SIZE;
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree,
-			 page_start, page_end - 1, 0, &cached_state,
-			 GFP_NOFS);
+			 page_start, page_end - 1, 0, &cached_state);
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
 			  page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING, 0, 0, &cached_state,
 			  GFP_NOFS);
 
-	if (i_done != num_pages) {
+	if (i_done != page_cnt) {
 		spin_lock(&BTRFS_I(inode)->lock);
 		BTRFS_I(inode)->outstanding_extents++;
 		spin_unlock(&BTRFS_I(inode)->lock);
 		btrfs_delalloc_release_space(inode,
-				     (num_pages - i_done) << PAGE_CACHE_SHIFT);
+				     (page_cnt - i_done) << PAGE_CACHE_SHIFT);
 	}
 
 
@@ -983,7 +1034,7 @@ out:
 		unlock_page(pages[i]);
 		page_cache_release(pages[i]);
 	}
-	btrfs_delalloc_release_space(inode, num_pages << PAGE_CACHE_SHIFT);
+	btrfs_delalloc_release_space(inode, page_cnt << PAGE_CACHE_SHIFT);
 	return ret;
 
 }
@@ -1089,12 +1140,9 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 		if (!(inode->i_sb->s_flags & MS_ACTIVE))
 			break;
 
-		if (!newer_than &&
-		    !should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
-					PAGE_CACHE_SIZE,
-					extent_thresh,
-					&last_len, &skip,
-					&defrag_end)) {
+		if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
+					 PAGE_CACHE_SIZE, extent_thresh,
+					 &last_len, &skip, &defrag_end)) {
 			unsigned long next;
 			/*
 			 * the should_defrag function tells us how much to skip
@@ -1123,17 +1171,24 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			ra_index += max_cluster;
 		}
 
+		mutex_lock(&inode->i_mutex);
 		ret = cluster_pages_for_defrag(inode, pages, i, cluster);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&inode->i_mutex);
 			goto out_ra;
+		}
 
 		defrag_count += ret;
 		balance_dirty_pages_ratelimited_nr(inode->i_mapping, ret);
+		mutex_unlock(&inode->i_mutex);
 
 		if (newer_than) {
 			if (newer_off == (u64)-1)
 				break;
 
+			if (ret > 0)
+				i += ret;
+
 			newer_off = max(newer_off + 1,
 					(u64)i << PAGE_CACHE_SHIFT);
 
@@ -1966,7 +2021,11 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 				dest->root_key.objectid,
 				dentry->d_name.name,
 				dentry->d_name.len);
-	BUG_ON(ret);
+	if (ret) {
+		err = ret;
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_end_trans;
+	}
 
 	btrfs_record_root_in_trans(trans, dest);
 
@@ -1979,11 +2038,16 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		ret = btrfs_insert_orphan_item(trans,
 					root->fs_info->tree_root,
 					dest->root_key.objectid);
-		BUG_ON(ret);
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
+			err = ret;
+			goto out_end_trans;
+		}
 	}
-
+out_end_trans:
 	ret = btrfs_end_transaction(trans, root);
-	BUG_ON(ret);
+	if (ret && !err)
+		err = ret;
 	inode->i_flags |= S_DEAD;
 out_up_write:
 	up_write(&root->fs_info->subvol_sem);
@@ -2326,13 +2390,13 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	   another, and lock file content */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
-		lock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
+		lock_extent(&BTRFS_I(src)->io_tree, off, off+len);
 		ordered = btrfs_lookup_first_ordered_extent(src, off+len);
 		if (!ordered &&
 		    !test_range_bit(&BTRFS_I(src)->io_tree, off, off+len,
 				   EXTENT_DELALLOC, 0, NULL))
 			break;
-		unlock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
+		unlock_extent(&BTRFS_I(src)->io_tree, off, off+len);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
 		btrfs_wait_ordered_range(src, off, len);
@@ -2447,11 +2511,21 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 							 new_key.offset,
 							 new_key.offset + datal,
 							 &hint_byte, 1);
-				BUG_ON(ret);
+				if (ret) {
+					btrfs_abort_transaction(trans, root,
+								ret);
+					btrfs_end_transaction(trans, root);
+					goto out;
+				}
 
 				ret = btrfs_insert_empty_item(trans, root, path,
 							      &new_key, size);
-				BUG_ON(ret);
+				if (ret) {
+					btrfs_abort_transaction(trans, root,
+								ret);
+					btrfs_end_transaction(trans, root);
+					goto out;
+				}
 
 				leaf = path->nodes[0];
 				slot = path->slots[0];
@@ -2478,7 +2552,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 							btrfs_ino(inode),
 							new_key.offset - datao,
 							0);
-					BUG_ON(ret);
+					if (ret) {
+						btrfs_abort_transaction(trans,
+									root,
+									ret);
+						btrfs_end_transaction(trans,
+								      root);
+						goto out;
+
+					}
 				}
 			} else if (type == BTRFS_FILE_EXTENT_INLINE) {
 				u64 skip = 0;
@@ -2503,11 +2585,21 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 							 new_key.offset,
 							 new_key.offset + datal,
 							 &hint_byte, 1);
-				BUG_ON(ret);
+				if (ret) {
+					btrfs_abort_transaction(trans, root,
+								ret);
+					btrfs_end_transaction(trans, root);
+					goto out;
+				}
 
 				ret = btrfs_insert_empty_item(trans, root, path,
 							      &new_key, size);
-				BUG_ON(ret);
+				if (ret) {
+					btrfs_abort_transaction(trans, root,
+								ret);
+					btrfs_end_transaction(trans, root);
+					goto out;
+				}
 
 				if (skip) {
 					u32 start =
@@ -2541,8 +2633,12 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 				btrfs_i_size_write(inode, endoff);
 
 			ret = btrfs_update_inode(trans, root, inode);
-			BUG_ON(ret);
-			btrfs_end_transaction(trans, root);
+			if (ret) {
+				btrfs_abort_transaction(trans, root, ret);
+				btrfs_end_transaction(trans, root);
+				goto out;
+			}
+			ret = btrfs_end_transaction(trans, root);
 		}
 next:
 		btrfs_release_path(path);
@@ -2551,7 +2647,7 @@ next:
 	ret = 0;
 out:
 	btrfs_release_path(path);
-	unlock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
+	unlock_extent(&BTRFS_I(src)->io_tree, off, off+len);
 out_unlock:
 	mutex_unlock(&src->i_mutex);
 	mutex_unlock(&inode->i_mutex);
@@ -3066,8 +3162,8 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 		goto out;
 
 	extent_item_pos = loi->logical - key.objectid;
-	ret = iterate_extent_inodes(root->fs_info, path, key.objectid,
-					extent_item_pos, build_ino_list,
+	ret = iterate_extent_inodes(root->fs_info, key.objectid,
+					extent_item_pos, 0, build_ino_list,
 					inodes);
 
 	if (ret < 0)
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 5e178d8f7167..272f911203ff 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -208,7 +208,7 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
  * take a spinning write lock.  This will wait for both
  * blocking readers or writers
  */
-int btrfs_tree_lock(struct extent_buffer *eb)
+void btrfs_tree_lock(struct extent_buffer *eb)
 {
 again:
 	wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0);
@@ -230,13 +230,12 @@ again:
 	atomic_inc(&eb->spinning_writers);
 	atomic_inc(&eb->write_locks);
 	eb->lock_owner = current->pid;
-	return 0;
 }
 
 /*
  * drop a spinning or a blocking write lock.
  */
-int btrfs_tree_unlock(struct extent_buffer *eb)
+void btrfs_tree_unlock(struct extent_buffer *eb)
 {
 	int blockers = atomic_read(&eb->blocking_writers);
 
@@ -255,7 +254,6 @@ int btrfs_tree_unlock(struct extent_buffer *eb)
 		atomic_dec(&eb->spinning_writers);
 		write_unlock(&eb->lock);
 	}
-	return 0;
 }
 
 void btrfs_assert_tree_locked(struct extent_buffer *eb)
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 17247ddb81a0..ca52681e5f40 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -24,8 +24,8 @@
 #define BTRFS_WRITE_LOCK_BLOCKING 3
 #define BTRFS_READ_LOCK_BLOCKING 4
 
-int btrfs_tree_lock(struct extent_buffer *eb);
-int btrfs_tree_unlock(struct extent_buffer *eb);
+void btrfs_tree_lock(struct extent_buffer *eb);
+void btrfs_tree_unlock(struct extent_buffer *eb);
 int btrfs_try_spin_lock(struct extent_buffer *eb);
 
 void btrfs_tree_read_lock(struct extent_buffer *eb);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index a1c940425307..bbf6d0d9aebe 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -59,6 +59,14 @@ static struct rb_node *tree_insert(struct rb_root *root, u64 file_offset,
 	return NULL;
 }
 
+static void ordered_data_tree_panic(struct inode *inode, int errno,
+					       u64 offset)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	btrfs_panic(fs_info, errno, "Inconsistency in ordered tree at offset "
+		    "%llu\n", (unsigned long long)offset);
+}
+
 /*
  * look for a given offset in the tree, and if it can't be found return the
  * first lesser offset
@@ -207,7 +215,8 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	spin_lock(&tree->lock);
 	node = tree_insert(&tree->tree, file_offset,
 			   &entry->rb_node);
-	BUG_ON(node);
+	if (node)
+		ordered_data_tree_panic(inode, -EEXIST, file_offset);
 	spin_unlock(&tree->lock);
 
 	spin_lock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
@@ -215,7 +224,6 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 		      &BTRFS_I(inode)->root->fs_info->ordered_extents);
 	spin_unlock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
 
-	BUG_ON(node);
 	return 0;
 }
 
@@ -249,9 +257,9 @@ int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
  * when an ordered extent is finished.  If the list covers more than one
  * ordered extent, it is split across multiples.
  */
-int btrfs_add_ordered_sum(struct inode *inode,
-			  struct btrfs_ordered_extent *entry,
-			  struct btrfs_ordered_sum *sum)
+void btrfs_add_ordered_sum(struct inode *inode,
+			   struct btrfs_ordered_extent *entry,
+			   struct btrfs_ordered_sum *sum)
 {
 	struct btrfs_ordered_inode_tree *tree;
 
@@ -259,7 +267,6 @@ int btrfs_add_ordered_sum(struct inode *inode,
 	spin_lock(&tree->lock);
 	list_add_tail(&sum->list, &entry->list);
 	spin_unlock(&tree->lock);
-	return 0;
 }
 
 /*
@@ -384,7 +391,7 @@ out:
  * used to drop a reference on an ordered extent.  This will free
  * the extent if the last reference is dropped
  */
-int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
+void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 {
 	struct list_head *cur;
 	struct btrfs_ordered_sum *sum;
@@ -400,7 +407,6 @@ int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 		}
 		kfree(entry);
 	}
-	return 0;
 }
 
 /*
@@ -408,8 +414,8 @@ int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
  * and you must wake_up entry->wait.  You must hold the tree lock
  * while you call this function.
  */
-static int __btrfs_remove_ordered_extent(struct inode *inode,
-				struct btrfs_ordered_extent *entry)
+static void __btrfs_remove_ordered_extent(struct inode *inode,
+					  struct btrfs_ordered_extent *entry)
 {
 	struct btrfs_ordered_inode_tree *tree;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -436,35 +442,30 @@ static int __btrfs_remove_ordered_extent(struct inode *inode,
 		list_del_init(&BTRFS_I(inode)->ordered_operations);
 	}
 	spin_unlock(&root->fs_info->ordered_extent_lock);
-
-	return 0;
 }
 
 /*
  * remove an ordered extent from the tree.  No references are dropped
  * but any waiters are woken.
  */
-int btrfs_remove_ordered_extent(struct inode *inode,
-				struct btrfs_ordered_extent *entry)
+void btrfs_remove_ordered_extent(struct inode *inode,
+				 struct btrfs_ordered_extent *entry)
 {
 	struct btrfs_ordered_inode_tree *tree;
-	int ret;
 
 	tree = &BTRFS_I(inode)->ordered_tree;
 	spin_lock(&tree->lock);
-	ret = __btrfs_remove_ordered_extent(inode, entry);
+	__btrfs_remove_ordered_extent(inode, entry);
 	spin_unlock(&tree->lock);
 	wake_up(&entry->wait);
-
-	return ret;
 }
 
 /*
  * wait for all the ordered extents in a root.  This is done when balancing
  * space between drives.
  */
-int btrfs_wait_ordered_extents(struct btrfs_root *root,
-			       int nocow_only, int delay_iput)
+void btrfs_wait_ordered_extents(struct btrfs_root *root,
+				int nocow_only, int delay_iput)
 {
 	struct list_head splice;
 	struct list_head *cur;
@@ -512,7 +513,6 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root,
 		spin_lock(&root->fs_info->ordered_extent_lock);
 	}
 	spin_unlock(&root->fs_info->ordered_extent_lock);
-	return 0;
 }
 
 /*
@@ -525,7 +525,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root,
  * extra check to make sure the ordered operation list really is empty
  * before we return
  */
-int btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
+void btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
 {
 	struct btrfs_inode *btrfs_inode;
 	struct inode *inode;
@@ -573,8 +573,6 @@ again:
 
 	spin_unlock(&root->fs_info->ordered_extent_lock);
 	mutex_unlock(&root->fs_info->ordered_operations_mutex);
-
-	return 0;
 }
 
 /*
@@ -609,7 +607,7 @@ void btrfs_start_ordered_extent(struct inode *inode,
 /*
  * Used to wait on ordered extents across a large range of bytes.
  */
-int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
+void btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 {
 	u64 end;
 	u64 orig_end;
@@ -664,7 +662,6 @@ again:
 		schedule_timeout(1);
 		goto again;
 	}
-	return 0;
 }
 
 /*
@@ -948,9 +945,8 @@ out:
  * If trans is not null, we'll do a friendly check for a transaction that
  * is already flushing things and force the IO down ourselves.
  */
-int btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root,
-				struct inode *inode)
+void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root, struct inode *inode)
 {
 	u64 last_mod;
 
@@ -961,7 +957,7 @@ int btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
 	 * commit, we can safely return without doing anything
 	 */
 	if (last_mod < root->fs_info->last_trans_committed)
-		return 0;
+		return;
 
 	/*
 	 * the transaction is already committing.  Just start the IO and
@@ -969,7 +965,7 @@ int btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
 	 */
 	if (trans && root->fs_info->running_transaction->blocked) {
 		btrfs_wait_ordered_range(inode, 0, (u64)-1);
-		return 0;
+		return;
 	}
 
 	spin_lock(&root->fs_info->ordered_extent_lock);
@@ -978,6 +974,4 @@ int btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
 			      &root->fs_info->ordered_operations);
 	}
 	spin_unlock(&root->fs_info->ordered_extent_lock);
-
-	return 0;
 }
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index ff1f69aa1883..c355ad4dc1a6 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -138,8 +138,8 @@ btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t)
 	t->last = NULL;
 }
 
-int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
-int btrfs_remove_ordered_extent(struct inode *inode,
+void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
+void btrfs_remove_ordered_extent(struct inode *inode,
 				struct btrfs_ordered_extent *entry);
 int btrfs_dec_test_ordered_pending(struct inode *inode,
 				   struct btrfs_ordered_extent **cached,
@@ -154,14 +154,14 @@ int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
 int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
 				      u64 start, u64 len, u64 disk_len,
 				      int type, int compress_type);
-int btrfs_add_ordered_sum(struct inode *inode,
-			  struct btrfs_ordered_extent *entry,
-			  struct btrfs_ordered_sum *sum);
+void btrfs_add_ordered_sum(struct inode *inode,
+			   struct btrfs_ordered_extent *entry,
+			   struct btrfs_ordered_sum *sum);
 struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
 							 u64 file_offset);
 void btrfs_start_ordered_extent(struct inode *inode,
 				struct btrfs_ordered_extent *entry, int wait);
-int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
+void btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
 struct btrfs_ordered_extent *
 btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset);
 struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode,
@@ -170,10 +170,10 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode,
 int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 				struct btrfs_ordered_extent *ordered);
 int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum);
-int btrfs_run_ordered_operations(struct btrfs_root *root, int wait);
-int btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root,
-				struct inode *inode);
-int btrfs_wait_ordered_extents(struct btrfs_root *root,
-			       int nocow_only, int delay_iput);
+void btrfs_run_ordered_operations(struct btrfs_root *root, int wait);
+void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct inode *inode);
+void btrfs_wait_ordered_extents(struct btrfs_root *root,
+				int nocow_only, int delay_iput);
 #endif
diff --git a/fs/btrfs/orphan.c b/fs/btrfs/orphan.c
index f8be250963a0..24cad1695af7 100644
--- a/fs/btrfs/orphan.c
+++ b/fs/btrfs/orphan.c
@@ -58,7 +58,7 @@ int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret < 0)
 		goto out;
-	if (ret) {
+	if (ret) { /* JDM: Really? */
 		ret = -ENOENT;
 		goto out;
 	}
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 22db04550f6a..dc5d33146fdb 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -54,7 +54,6 @@
  * than the 2 started one after another.
  */
 
-#define MAX_MIRRORS 2
 #define MAX_IN_FLIGHT 6
 
 struct reada_extctl {
@@ -71,7 +70,7 @@ struct reada_extent {
 	struct list_head	extctl;
 	struct kref		refcnt;
 	spinlock_t		lock;
-	struct reada_zone	*zones[MAX_MIRRORS];
+	struct reada_zone	*zones[BTRFS_MAX_MIRRORS];
 	int			nzones;
 	struct btrfs_device	*scheduled_for;
 };
@@ -84,7 +83,8 @@ struct reada_zone {
 	spinlock_t		lock;
 	int			locked;
 	struct btrfs_device	*device;
-	struct btrfs_device	*devs[MAX_MIRRORS]; /* full list, incl self */
+	struct btrfs_device	*devs[BTRFS_MAX_MIRRORS]; /* full list, incl
+							   * self */
 	int			ndevs;
 	struct kref		refcnt;
 };
@@ -365,9 +365,9 @@ again:
 	if (ret || !bbio || length < blocksize)
 		goto error;
 
-	if (bbio->num_stripes > MAX_MIRRORS) {
+	if (bbio->num_stripes > BTRFS_MAX_MIRRORS) {
 		printk(KERN_ERR "btrfs readahead: more than %d copies not "
-				"supported", MAX_MIRRORS);
+				"supported", BTRFS_MAX_MIRRORS);
 		goto error;
 	}
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 8c1aae2c845d..017281dbb2a7 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -326,6 +326,19 @@ static struct rb_node *tree_search(struct rb_root *root, u64 bytenr)
 	return NULL;
 }
 
+void backref_tree_panic(struct rb_node *rb_node, int errno,
+					  u64 bytenr)
+{
+
+	struct btrfs_fs_info *fs_info = NULL;
+	struct backref_node *bnode = rb_entry(rb_node, struct backref_node,
+					      rb_node);
+	if (bnode->root)
+		fs_info = bnode->root->fs_info;
+	btrfs_panic(fs_info, errno, "Inconsistency in backref cache "
+		    "found at offset %llu\n", (unsigned long long)bytenr);
+}
+
 /*
  * walk up backref nodes until reach node presents tree root
  */
@@ -452,7 +465,8 @@ static void update_backref_node(struct backref_cache *cache,
 	rb_erase(&node->rb_node, &cache->rb_root);
 	node->bytenr = bytenr;
 	rb_node = tree_insert(&cache->rb_root, node->bytenr, &node->rb_node);
-	BUG_ON(rb_node);
+	if (rb_node)
+		backref_tree_panic(rb_node, -EEXIST, bytenr);
 }
 
 /*
@@ -999,7 +1013,8 @@ next:
 	if (!cowonly) {
 		rb_node = tree_insert(&cache->rb_root, node->bytenr,
 				      &node->rb_node);
-		BUG_ON(rb_node);
+		if (rb_node)
+			backref_tree_panic(rb_node, -EEXIST, node->bytenr);
 		list_add_tail(&node->lower, &cache->leaves);
 	}
 
@@ -1034,7 +1049,9 @@ next:
 		if (!cowonly) {
 			rb_node = tree_insert(&cache->rb_root, upper->bytenr,
 					      &upper->rb_node);
-			BUG_ON(rb_node);
+			if (rb_node)
+				backref_tree_panic(rb_node, -EEXIST,
+						   upper->bytenr);
 		}
 
 		list_add_tail(&edge->list[UPPER], &upper->lower);
@@ -1180,7 +1197,8 @@ static int clone_backref_node(struct btrfs_trans_handle *trans,
 
 	rb_node = tree_insert(&cache->rb_root, new_node->bytenr,
 			      &new_node->rb_node);
-	BUG_ON(rb_node);
+	if (rb_node)
+		backref_tree_panic(rb_node, -EEXIST, new_node->bytenr);
 
 	if (!new_node->lowest) {
 		list_for_each_entry(new_edge, &new_node->lower, list[UPPER]) {
@@ -1203,14 +1221,15 @@ fail:
 /*
  * helper to add 'address of tree root -> reloc tree' mapping
  */
-static int __add_reloc_root(struct btrfs_root *root)
+static int __must_check __add_reloc_root(struct btrfs_root *root)
 {
 	struct rb_node *rb_node;
 	struct mapping_node *node;
 	struct reloc_control *rc = root->fs_info->reloc_ctl;
 
 	node = kmalloc(sizeof(*node), GFP_NOFS);
-	BUG_ON(!node);
+	if (!node)
+		return -ENOMEM;
 
 	node->bytenr = root->node->start;
 	node->data = root;
@@ -1219,7 +1238,12 @@ static int __add_reloc_root(struct btrfs_root *root)
 	rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
 			      node->bytenr, &node->rb_node);
 	spin_unlock(&rc->reloc_root_tree.lock);
-	BUG_ON(rb_node);
+	if (rb_node) {
+		kfree(node);
+		btrfs_panic(root->fs_info, -EEXIST, "Duplicate root found "
+			    "for start=%llu while inserting into relocation "
+			    "tree\n");
+	}
 
 	list_add_tail(&root->root_list, &rc->reloc_roots);
 	return 0;
@@ -1252,7 +1276,8 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
 		rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
 				      node->bytenr, &node->rb_node);
 		spin_unlock(&rc->reloc_root_tree.lock);
-		BUG_ON(rb_node);
+		if (rb_node)
+			backref_tree_panic(rb_node, -EEXIST, node->bytenr);
 	} else {
 		list_del_init(&root->root_list);
 		kfree(node);
@@ -1334,6 +1359,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 	struct btrfs_root *reloc_root;
 	struct reloc_control *rc = root->fs_info->reloc_ctl;
 	int clear_rsv = 0;
+	int ret;
 
 	if (root->reloc_root) {
 		reloc_root = root->reloc_root;
@@ -1353,7 +1379,8 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 	if (clear_rsv)
 		trans->block_rsv = NULL;
 
-	__add_reloc_root(reloc_root);
+	ret = __add_reloc_root(reloc_root);
+	BUG_ON(ret < 0);
 	root->reloc_root = reloc_root;
 	return 0;
 }
@@ -1577,15 +1604,14 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 				WARN_ON(!IS_ALIGNED(end, root->sectorsize));
 				end--;
 				ret = try_lock_extent(&BTRFS_I(inode)->io_tree,
-						      key.offset, end,
-						      GFP_NOFS);
+						      key.offset, end);
 				if (!ret)
 					continue;
 
 				btrfs_drop_extent_cache(inode, key.offset, end,
 							1);
 				unlock_extent(&BTRFS_I(inode)->io_tree,
-					      key.offset, end, GFP_NOFS);
+					      key.offset, end);
 			}
 		}
 
@@ -1956,9 +1982,9 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 		}
 
 		/* the lock_extent waits for readpage to complete */
-		lock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+		lock_extent(&BTRFS_I(inode)->io_tree, start, end);
 		btrfs_drop_extent_cache(inode, start, end, 1);
-		unlock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+		unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 	}
 	return 0;
 }
@@ -2246,7 +2272,8 @@ again:
 		} else {
 			list_del_init(&reloc_root->root_list);
 		}
-		btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0, 1);
+		ret = btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0, 1);
+		BUG_ON(ret < 0);
 	}
 
 	if (found) {
@@ -2862,12 +2889,12 @@ int prealloc_file_extent_cluster(struct inode *inode,
 		else
 			end = cluster->end - offset;
 
-		lock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+		lock_extent(&BTRFS_I(inode)->io_tree, start, end);
 		num_bytes = end + 1 - start;
 		ret = btrfs_prealloc_file_range(inode, 0, start,
 						num_bytes, num_bytes,
 						end + 1, &alloc_hint);
-		unlock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+		unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 		if (ret)
 			break;
 		nr++;
@@ -2899,7 +2926,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 	em->bdev = root->fs_info->fs_devices->latest_bdev;
 	set_bit(EXTENT_FLAG_PINNED, &em->flags);
 
-	lock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+	lock_extent(&BTRFS_I(inode)->io_tree, start, end);
 	while (1) {
 		write_lock(&em_tree->lock);
 		ret = add_extent_mapping(em_tree, em);
@@ -2910,7 +2937,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 		}
 		btrfs_drop_extent_cache(inode, start, end, 0);
 	}
-	unlock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+	unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 	return ret;
 }
 
@@ -2990,8 +3017,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 		page_start = (u64)page->index << PAGE_CACHE_SHIFT;
 		page_end = page_start + PAGE_CACHE_SIZE - 1;
 
-		lock_extent(&BTRFS_I(inode)->io_tree,
-			    page_start, page_end, GFP_NOFS);
+		lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end);
 
 		set_page_extent_mapped(page);
 
@@ -3007,7 +3033,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 		set_page_dirty(page);
 
 		unlock_extent(&BTRFS_I(inode)->io_tree,
-			      page_start, page_end, GFP_NOFS);
+			      page_start, page_end);
 		unlock_page(page);
 		page_cache_release(page);
 
@@ -3154,7 +3180,8 @@ static int add_tree_block(struct reloc_control *rc,
 	block->key_ready = 0;
 
 	rb_node = tree_insert(blocks, block->bytenr, &block->rb_node);
-	BUG_ON(rb_node);
+	if (rb_node)
+		backref_tree_panic(rb_node, -EEXIST, block->bytenr);
 
 	return 0;
 }
@@ -3426,7 +3453,9 @@ static int find_data_references(struct reloc_control *rc,
 			block->key_ready = 1;
 			rb_node = tree_insert(blocks, block->bytenr,
 					      &block->rb_node);
-			BUG_ON(rb_node);
+			if (rb_node)
+				backref_tree_panic(rb_node, -EEXIST,
+						   block->bytenr);
 		}
 		if (counted)
 			added = 1;
@@ -4073,10 +4102,11 @@ out:
 static noinline_for_stack int mark_garbage_root(struct btrfs_root *root)
 {
 	struct btrfs_trans_handle *trans;
-	int ret;
+	int ret, err;
 
 	trans = btrfs_start_transaction(root->fs_info->tree_root, 0);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 
 	memset(&root->root_item.drop_progress, 0,
 		sizeof(root->root_item.drop_progress));
@@ -4084,11 +4114,11 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root)
 	btrfs_set_root_refs(&root->root_item, 0);
 	ret = btrfs_update_root(trans, root->fs_info->tree_root,
 				&root->root_key, &root->root_item);
-	BUG_ON(ret);
 
-	ret = btrfs_end_transaction(trans, root->fs_info->tree_root);
-	BUG_ON(ret);
-	return 0;
+	err = btrfs_end_transaction(trans, root->fs_info->tree_root);
+	if (err)
+		return err;
+	return ret;
 }
 
 /*
@@ -4156,7 +4186,11 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 					err = ret;
 					goto out;
 				}
-				mark_garbage_root(reloc_root);
+				ret = mark_garbage_root(reloc_root);
+				if (ret < 0) {
+					err = ret;
+					goto out;
+				}
 			}
 		}
 
@@ -4202,13 +4236,19 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 
 		fs_root = read_fs_root(root->fs_info,
 				       reloc_root->root_key.offset);
-		BUG_ON(IS_ERR(fs_root));
+		if (IS_ERR(fs_root)) {
+			err = PTR_ERR(fs_root);
+			goto out_free;
+		}
 
-		__add_reloc_root(reloc_root);
+		err = __add_reloc_root(reloc_root);
+		BUG_ON(err < 0); /* -ENOMEM or logic error */
 		fs_root->reloc_root = reloc_root;
 	}
 
-	btrfs_commit_transaction(trans, rc->extent_root);
+	err = btrfs_commit_transaction(trans, rc->extent_root);
+	if (err)
+		goto out_free;
 
 	merge_reloc_roots(rc);
 
@@ -4218,7 +4258,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 	if (IS_ERR(trans))
 		err = PTR_ERR(trans);
 	else
-		btrfs_commit_transaction(trans, rc->extent_root);
+		err = btrfs_commit_transaction(trans, rc->extent_root);
 out_free:
 	kfree(rc);
 out:
@@ -4267,6 +4307,8 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len)
 	disk_bytenr = file_pos + BTRFS_I(inode)->index_cnt;
 	ret = btrfs_lookup_csums_range(root->fs_info->csum_root, disk_bytenr,
 				       disk_bytenr + len - 1, &list, 0);
+	if (ret)
+		goto out;
 
 	while (!list_empty(&list)) {
 		sums = list_entry(list.next, struct btrfs_ordered_sum, list);
@@ -4284,6 +4326,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len)
 
 		btrfs_add_ordered_sum(inode, ordered, sums);
 	}
+out:
 	btrfs_put_ordered_extent(ordered);
 	return ret;
 }
@@ -4380,7 +4423,7 @@ void btrfs_reloc_pre_snapshot(struct btrfs_trans_handle *trans,
  * called after snapshot is created. migrate block reservation
  * and create reloc root for the newly created snapshot
  */
-void btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
+int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
 			       struct btrfs_pending_snapshot *pending)
 {
 	struct btrfs_root *root = pending->root;
@@ -4390,7 +4433,7 @@ void btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
 	int ret;
 
 	if (!root->reloc_root)
-		return;
+		return 0;
 
 	rc = root->fs_info->reloc_ctl;
 	rc->merging_rsv_size += rc->nodes_relocated;
@@ -4399,18 +4442,21 @@ void btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
 		ret = btrfs_block_rsv_migrate(&pending->block_rsv,
 					      rc->block_rsv,
 					      rc->nodes_relocated);
-		BUG_ON(ret);
+		if (ret)
+			return ret;
 	}
 
 	new_root = pending->snap;
 	reloc_root = create_reloc_root(trans, root->reloc_root,
 				       new_root->root_key.objectid);
+	if (IS_ERR(reloc_root))
+		return PTR_ERR(reloc_root);
 
-	__add_reloc_root(reloc_root);
+	ret = __add_reloc_root(reloc_root);
+	BUG_ON(ret < 0);
 	new_root->reloc_root = reloc_root;
 
-	if (rc->create_reloc_tree) {
+	if (rc->create_reloc_tree)
 		ret = clone_backref_node(trans, rc, root, reloc_root);
-		BUG_ON(ret);
-	}
+	return ret;
 }
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index f4099904565a..24fb8ce4e071 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -93,10 +93,14 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
 	unsigned long ptr;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
+
 	ret = btrfs_search_slot(trans, root, key, path, 0, 1);
-	if (ret < 0)
+	if (ret < 0) {
+		btrfs_abort_transaction(trans, root, ret);
 		goto out;
+	}
 
 	if (ret != 0) {
 		btrfs_print_leaf(root, path->nodes[0]);
@@ -116,13 +120,10 @@ out:
 	return ret;
 }
 
-int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_key *key, struct btrfs_root_item
-		      *item)
+int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      struct btrfs_key *key, struct btrfs_root_item *item)
 {
-	int ret;
-	ret = btrfs_insert_item(trans, root, key, item, sizeof(*item));
-	return ret;
+	return btrfs_insert_item(trans, root, key, item, sizeof(*item));
 }
 
 /*
@@ -384,6 +385,8 @@ int btrfs_find_root_ref(struct btrfs_root *tree_root,
  *
  * For a back ref the root_id is the id of the subvol or snapshot and
  * ref_id is the id of the tree referencing it.
+ *
+ * Will return 0, -ENOMEM, or anything from the CoW path
  */
 int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *tree_root,
@@ -407,7 +410,11 @@ int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
 again:
 	ret = btrfs_insert_empty_item(trans, tree_root, path, &key,
 				      sizeof(*ref) + name_len);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, tree_root, ret);
+		btrfs_free_path(path);
+		return ret;
+	}
 
 	leaf = path->nodes[0];
 	ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 390e7102b0ff..90acc82046c3 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -36,37 +36,30 @@
  * Future enhancements:
  *  - In case an unrepairable extent is encountered, track which files are
  *    affected and report them
- *  - In case of a read error on files with nodatasum, map the file and read
- *    the extent to trigger a writeback of the good copy
  *  - track and record media errors, throw out bad devices
  *  - add a mode to also read unallocated space
  */
 
-struct scrub_bio;
-struct scrub_page;
+struct scrub_block;
 struct scrub_dev;
-static void scrub_bio_end_io(struct bio *bio, int err);
-static void scrub_checksum(struct btrfs_work *work);
-static int scrub_checksum_data(struct scrub_dev *sdev,
-			       struct scrub_page *spag, void *buffer);
-static int scrub_checksum_tree_block(struct scrub_dev *sdev,
-				     struct scrub_page *spag, u64 logical,
-				     void *buffer);
-static int scrub_checksum_super(struct scrub_bio *sbio, void *buffer);
-static int scrub_fixup_check(struct scrub_bio *sbio, int ix);
-static void scrub_fixup_end_io(struct bio *bio, int err);
-static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector,
-			  struct page *page);
-static void scrub_fixup(struct scrub_bio *sbio, int ix);
 
 #define SCRUB_PAGES_PER_BIO	16	/* 64k per bio */
 #define SCRUB_BIOS_PER_DEV	16	/* 1 MB per device in flight */
+#define SCRUB_MAX_PAGES_PER_BLOCK	16	/* 64k per node/leaf/sector */
 
 struct scrub_page {
+	struct scrub_block	*sblock;
+	struct page		*page;
+	struct block_device	*bdev;
 	u64			flags;  /* extent flags */
 	u64			generation;
-	int			mirror_num;
-	int			have_csum;
+	u64			logical;
+	u64			physical;
+	struct {
+		unsigned int	mirror_num:8;
+		unsigned int	have_csum:1;
+		unsigned int	io_error:1;
+	};
 	u8			csum[BTRFS_CSUM_SIZE];
 };
 
@@ -77,12 +70,25 @@ struct scrub_bio {
 	int			err;
 	u64			logical;
 	u64			physical;
-	struct scrub_page	spag[SCRUB_PAGES_PER_BIO];
-	u64			count;
+	struct scrub_page	*pagev[SCRUB_PAGES_PER_BIO];
+	int			page_count;
 	int			next_free;
 	struct btrfs_work	work;
 };
 
+struct scrub_block {
+	struct scrub_page	pagev[SCRUB_MAX_PAGES_PER_BLOCK];
+	int			page_count;
+	atomic_t		outstanding_pages;
+	atomic_t		ref_count; /* free mem on transition to zero */
+	struct scrub_dev	*sdev;
+	struct {
+		unsigned int	header_error:1;
+		unsigned int	checksum_error:1;
+		unsigned int	no_io_error_seen:1;
+	};
+};
+
 struct scrub_dev {
 	struct scrub_bio	*bios[SCRUB_BIOS_PER_DEV];
 	struct btrfs_device	*dev;
@@ -96,6 +102,10 @@ struct scrub_dev {
 	struct list_head	csum_list;
 	atomic_t		cancel_req;
 	int			readonly;
+	int			pages_per_bio; /* <= SCRUB_PAGES_PER_BIO */
+	u32			sectorsize;
+	u32			nodesize;
+	u32			leafsize;
 	/*
 	 * statistics
 	 */
@@ -124,6 +134,43 @@ struct scrub_warning {
 	int			scratch_bufsize;
 };
 
+
+static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
+static int scrub_setup_recheck_block(struct scrub_dev *sdev,
+				     struct btrfs_mapping_tree *map_tree,
+				     u64 length, u64 logical,
+				     struct scrub_block *sblock);
+static int scrub_recheck_block(struct btrfs_fs_info *fs_info,
+			       struct scrub_block *sblock, int is_metadata,
+			       int have_csum, u8 *csum, u64 generation,
+			       u16 csum_size);
+static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
+					 struct scrub_block *sblock,
+					 int is_metadata, int have_csum,
+					 const u8 *csum, u64 generation,
+					 u16 csum_size);
+static void scrub_complete_bio_end_io(struct bio *bio, int err);
+static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
+					     struct scrub_block *sblock_good,
+					     int force_write);
+static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
+					    struct scrub_block *sblock_good,
+					    int page_num, int force_write);
+static int scrub_checksum_data(struct scrub_block *sblock);
+static int scrub_checksum_tree_block(struct scrub_block *sblock);
+static int scrub_checksum_super(struct scrub_block *sblock);
+static void scrub_block_get(struct scrub_block *sblock);
+static void scrub_block_put(struct scrub_block *sblock);
+static int scrub_add_page_to_bio(struct scrub_dev *sdev,
+				 struct scrub_page *spage);
+static int scrub_pages(struct scrub_dev *sdev, u64 logical, u64 len,
+		       u64 physical, u64 flags, u64 gen, int mirror_num,
+		       u8 *csum, int force);
+static void scrub_bio_end_io(struct bio *bio, int err);
+static void scrub_bio_end_io_worker(struct btrfs_work *work);
+static void scrub_block_complete(struct scrub_block *sblock);
+
+
 static void scrub_free_csums(struct scrub_dev *sdev)
 {
 	while (!list_empty(&sdev->csum_list)) {
@@ -135,23 +182,6 @@ static void scrub_free_csums(struct scrub_dev *sdev)
 	}
 }
 
-static void scrub_free_bio(struct bio *bio)
-{
-	int i;
-	struct page *last_page = NULL;
-
-	if (!bio)
-		return;
-
-	for (i = 0; i < bio->bi_vcnt; ++i) {
-		if (bio->bi_io_vec[i].bv_page == last_page)
-			continue;
-		last_page = bio->bi_io_vec[i].bv_page;
-		__free_page(last_page);
-	}
-	bio_put(bio);
-}
-
 static noinline_for_stack void scrub_free_dev(struct scrub_dev *sdev)
 {
 	int i;
@@ -159,13 +189,23 @@ static noinline_for_stack void scrub_free_dev(struct scrub_dev *sdev)
 	if (!sdev)
 		return;
 
+	/* this can happen when scrub is cancelled */
+	if (sdev->curr != -1) {
+		struct scrub_bio *sbio = sdev->bios[sdev->curr];
+
+		for (i = 0; i < sbio->page_count; i++) {
+			BUG_ON(!sbio->pagev[i]);
+			BUG_ON(!sbio->pagev[i]->page);
+			scrub_block_put(sbio->pagev[i]->sblock);
+		}
+		bio_put(sbio->bio);
+	}
+
 	for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
 		struct scrub_bio *sbio = sdev->bios[i];
 
 		if (!sbio)
 			break;
-
-		scrub_free_bio(sbio->bio);
 		kfree(sbio);
 	}
 
@@ -179,11 +219,16 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
 	struct scrub_dev *sdev;
 	int		i;
 	struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
+	int pages_per_bio;
 
+	pages_per_bio = min_t(int, SCRUB_PAGES_PER_BIO,
+			      bio_get_nr_vecs(dev->bdev));
 	sdev = kzalloc(sizeof(*sdev), GFP_NOFS);
 	if (!sdev)
 		goto nomem;
 	sdev->dev = dev;
+	sdev->pages_per_bio = pages_per_bio;
+	sdev->curr = -1;
 	for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
 		struct scrub_bio *sbio;
 
@@ -194,8 +239,8 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
 
 		sbio->index = i;
 		sbio->sdev = sdev;
-		sbio->count = 0;
-		sbio->work.func = scrub_checksum;
+		sbio->page_count = 0;
+		sbio->work.func = scrub_bio_end_io_worker;
 
 		if (i != SCRUB_BIOS_PER_DEV-1)
 			sdev->bios[i]->next_free = i + 1;
@@ -203,7 +248,9 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
 			sdev->bios[i]->next_free = -1;
 	}
 	sdev->first_free = 0;
-	sdev->curr = -1;
+	sdev->nodesize = dev->dev_root->nodesize;
+	sdev->leafsize = dev->dev_root->leafsize;
+	sdev->sectorsize = dev->dev_root->sectorsize;
 	atomic_set(&sdev->in_flight, 0);
 	atomic_set(&sdev->fixup_cnt, 0);
 	atomic_set(&sdev->cancel_req, 0);
@@ -294,10 +341,9 @@ err:
 	return 0;
 }
 
-static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
-				int ix)
+static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 {
-	struct btrfs_device *dev = sbio->sdev->dev;
+	struct btrfs_device *dev = sblock->sdev->dev;
 	struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
 	struct btrfs_path *path;
 	struct btrfs_key found_key;
@@ -316,8 +362,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 
 	swarn.scratch_buf = kmalloc(bufsize, GFP_NOFS);
 	swarn.msg_buf = kmalloc(bufsize, GFP_NOFS);
-	swarn.sector = (sbio->physical + ix * PAGE_SIZE) >> 9;
-	swarn.logical = sbio->logical + ix * PAGE_SIZE;
+	BUG_ON(sblock->page_count < 1);
+	swarn.sector = (sblock->pagev[0].physical) >> 9;
+	swarn.logical = sblock->pagev[0].logical;
 	swarn.errstr = errstr;
 	swarn.dev = dev;
 	swarn.msg_bufsize = bufsize;
@@ -342,7 +389,8 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 		do {
 			ret = tree_backref_for_extent(&ptr, eb, ei, item_size,
 							&ref_root, &ref_level);
-			printk(KERN_WARNING "%s at logical %llu on dev %s, "
+			printk(KERN_WARNING
+				"btrfs: %s at logical %llu on dev %s, "
 				"sector %llu: metadata %s (level %d) in tree "
 				"%llu\n", errstr, swarn.logical, dev->name,
 				(unsigned long long)swarn.sector,
@@ -352,8 +400,8 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 		} while (ret != 1);
 	} else {
 		swarn.path = path;
-		iterate_extent_inodes(fs_info, path, found_key.objectid,
-					extent_item_pos,
+		iterate_extent_inodes(fs_info, found_key.objectid,
+					extent_item_pos, 1,
 					scrub_print_warning_inode, &swarn);
 	}
 
@@ -531,9 +579,9 @@ out:
 		spin_lock(&sdev->stat_lock);
 		++sdev->stat.uncorrectable_errors;
 		spin_unlock(&sdev->stat_lock);
-		printk_ratelimited(KERN_ERR "btrfs: unable to fixup "
-					"(nodatasum) error at logical %llu\n",
-					fixup->logical);
+		printk_ratelimited(KERN_ERR
+			"btrfs: unable to fixup (nodatasum) error at logical %llu on dev %s\n",
+			(unsigned long long)fixup->logical, sdev->dev->name);
 	}
 
 	btrfs_free_path(path);
@@ -550,91 +598,168 @@ out:
 }
 
 /*
- * scrub_recheck_error gets called when either verification of the page
- * failed or the bio failed to read, e.g. with EIO. In the latter case,
- * recheck_error gets called for every page in the bio, even though only
- * one may be bad
+ * scrub_handle_errored_block gets called when either verification of the
+ * pages failed or the bio failed to read, e.g. with EIO. In the latter
+ * case, this function handles all pages in the bio, even though only one
+ * may be bad.
+ * The goal of this function is to repair the errored block by using the
+ * contents of one of the mirrors.
  */
-static int scrub_recheck_error(struct scrub_bio *sbio, int ix)
+static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 {
-	struct scrub_dev *sdev = sbio->sdev;
-	u64 sector = (sbio->physical + ix * PAGE_SIZE) >> 9;
+	struct scrub_dev *sdev = sblock_to_check->sdev;
+	struct btrfs_fs_info *fs_info;
+	u64 length;
+	u64 logical;
+	u64 generation;
+	unsigned int failed_mirror_index;
+	unsigned int is_metadata;
+	unsigned int have_csum;
+	u8 *csum;
+	struct scrub_block *sblocks_for_recheck; /* holds one for each mirror */
+	struct scrub_block *sblock_bad;
+	int ret;
+	int mirror_index;
+	int page_num;
+	int success;
 	static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
-					DEFAULT_RATELIMIT_BURST);
+				      DEFAULT_RATELIMIT_BURST);
+
+	BUG_ON(sblock_to_check->page_count < 1);
+	fs_info = sdev->dev->dev_root->fs_info;
+	length = sblock_to_check->page_count * PAGE_SIZE;
+	logical = sblock_to_check->pagev[0].logical;
+	generation = sblock_to_check->pagev[0].generation;
+	BUG_ON(sblock_to_check->pagev[0].mirror_num < 1);
+	failed_mirror_index = sblock_to_check->pagev[0].mirror_num - 1;
+	is_metadata = !(sblock_to_check->pagev[0].flags &
+			BTRFS_EXTENT_FLAG_DATA);
+	have_csum = sblock_to_check->pagev[0].have_csum;
+	csum = sblock_to_check->pagev[0].csum;
 
-	if (sbio->err) {
-		if (scrub_fixup_io(READ, sbio->sdev->dev->bdev, sector,
-				   sbio->bio->bi_io_vec[ix].bv_page) == 0) {
-			if (scrub_fixup_check(sbio, ix) == 0)
-				return 0;
-		}
-		if (__ratelimit(&_rs))
-			scrub_print_warning("i/o error", sbio, ix);
-	} else {
-		if (__ratelimit(&_rs))
-			scrub_print_warning("checksum error", sbio, ix);
+	/*
+	 * read all mirrors one after the other. This includes to
+	 * re-read the extent or metadata block that failed (that was
+	 * the cause that this fixup code is called) another time,
+	 * page by page this time in order to know which pages
+	 * caused I/O errors and which ones are good (for all mirrors).
+	 * It is the goal to handle the situation when more than one
+	 * mirror contains I/O errors, but the errors do not
+	 * overlap, i.e. the data can be repaired by selecting the
+	 * pages from those mirrors without I/O error on the
+	 * particular pages. One example (with blocks >= 2 * PAGE_SIZE)
+	 * would be that mirror #1 has an I/O error on the first page,
+	 * the second page is good, and mirror #2 has an I/O error on
+	 * the second page, but the first page is good.
+	 * Then the first page of the first mirror can be repaired by
+	 * taking the first page of the second mirror, and the
+	 * second page of the second mirror can be repaired by
+	 * copying the contents of the 2nd page of the 1st mirror.
+	 * One more note: if the pages of one mirror contain I/O
+	 * errors, the checksum cannot be verified. In order to get
+	 * the best data for repairing, the first attempt is to find
+	 * a mirror without I/O errors and with a validated checksum.
+	 * Only if this is not possible, the pages are picked from
+	 * mirrors with I/O errors without considering the checksum.
+	 * If the latter is the case, at the end, the checksum of the
+	 * repaired area is verified in order to correctly maintain
+	 * the statistics.
+	 */
+
+	sblocks_for_recheck = kzalloc(BTRFS_MAX_MIRRORS *
+				     sizeof(*sblocks_for_recheck),
+				     GFP_NOFS);
+	if (!sblocks_for_recheck) {
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.malloc_errors++;
+		sdev->stat.read_errors++;
+		sdev->stat.uncorrectable_errors++;
+		spin_unlock(&sdev->stat_lock);
+		goto out;
 	}
 
-	spin_lock(&sdev->stat_lock);
-	++sdev->stat.read_errors;
-	spin_unlock(&sdev->stat_lock);
+	/* setup the context, map the logical blocks and alloc the pages */
+	ret = scrub_setup_recheck_block(sdev, &fs_info->mapping_tree, length,
+					logical, sblocks_for_recheck);
+	if (ret) {
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.read_errors++;
+		sdev->stat.uncorrectable_errors++;
+		spin_unlock(&sdev->stat_lock);
+		goto out;
+	}
+	BUG_ON(failed_mirror_index >= BTRFS_MAX_MIRRORS);
+	sblock_bad = sblocks_for_recheck + failed_mirror_index;
 
-	scrub_fixup(sbio, ix);
-	return 1;
-}
+	/* build and submit the bios for the failed mirror, check checksums */
+	ret = scrub_recheck_block(fs_info, sblock_bad, is_metadata, have_csum,
+				  csum, generation, sdev->csum_size);
+	if (ret) {
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.read_errors++;
+		sdev->stat.uncorrectable_errors++;
+		spin_unlock(&sdev->stat_lock);
+		goto out;
+	}
 
-static int scrub_fixup_check(struct scrub_bio *sbio, int ix)
-{
-	int ret = 1;
-	struct page *page;
-	void *buffer;
-	u64 flags = sbio->spag[ix].flags;
+	if (!sblock_bad->header_error && !sblock_bad->checksum_error &&
+	    sblock_bad->no_io_error_seen) {
+		/*
+		 * the error disappeared after reading page by page, or
+		 * the area was part of a huge bio and other parts of the
+		 * bio caused I/O errors, or the block layer merged several
+		 * read requests into one and the error is caused by a
+		 * different bio (usually one of the two latter cases is
+		 * the cause)
+		 */
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.unverified_errors++;
+		spin_unlock(&sdev->stat_lock);
 
-	page = sbio->bio->bi_io_vec[ix].bv_page;
-	buffer = kmap_atomic(page);
-	if (flags & BTRFS_EXTENT_FLAG_DATA) {
-		ret = scrub_checksum_data(sbio->sdev,
-					  sbio->spag + ix, buffer);
-	} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-		ret = scrub_checksum_tree_block(sbio->sdev,
-						sbio->spag + ix,
-						sbio->logical + ix * PAGE_SIZE,
-						buffer);
-	} else {
-		WARN_ON(1);
+		goto out;
 	}
-	kunmap_atomic(buffer);
 
-	return ret;
-}
+	if (!sblock_bad->no_io_error_seen) {
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.read_errors++;
+		spin_unlock(&sdev->stat_lock);
+		if (__ratelimit(&_rs))
+			scrub_print_warning("i/o error", sblock_to_check);
+	} else if (sblock_bad->checksum_error) {
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.csum_errors++;
+		spin_unlock(&sdev->stat_lock);
+		if (__ratelimit(&_rs))
+			scrub_print_warning("checksum error", sblock_to_check);
+	} else if (sblock_bad->header_error) {
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.verify_errors++;
+		spin_unlock(&sdev->stat_lock);
+		if (__ratelimit(&_rs))
+			scrub_print_warning("checksum/header error",
+					    sblock_to_check);
+	}
 
-static void scrub_fixup_end_io(struct bio *bio, int err)
-{
-	complete((struct completion *)bio->bi_private);
-}
+	if (sdev->readonly)
+		goto did_not_correct_error;
 
-static void scrub_fixup(struct scrub_bio *sbio, int ix)
-{
-	struct scrub_dev *sdev = sbio->sdev;
-	struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
-	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
-	struct btrfs_bio *bbio = NULL;
-	struct scrub_fixup_nodatasum *fixup;
-	u64 logical = sbio->logical + ix * PAGE_SIZE;
-	u64 length;
-	int i;
-	int ret;
-	DECLARE_COMPLETION_ONSTACK(complete);
-
-	if ((sbio->spag[ix].flags & BTRFS_EXTENT_FLAG_DATA) &&
-	    (sbio->spag[ix].have_csum == 0)) {
-		fixup = kzalloc(sizeof(*fixup), GFP_NOFS);
-		if (!fixup)
-			goto uncorrectable;
-		fixup->sdev = sdev;
-		fixup->logical = logical;
-		fixup->root = fs_info->extent_root;
-		fixup->mirror_num = sbio->spag[ix].mirror_num;
+	if (!is_metadata && !have_csum) {
+		struct scrub_fixup_nodatasum *fixup_nodatasum;
+
+		/*
+		 * !is_metadata and !have_csum, this means that the data
+		 * might not be COW'ed, that it might be modified
+		 * concurrently. The general strategy to work on the
+		 * commit root does not help in the case when COW is not
+		 * used.
+		 */
+		fixup_nodatasum = kzalloc(sizeof(*fixup_nodatasum), GFP_NOFS);
+		if (!fixup_nodatasum)
+			goto did_not_correct_error;
+		fixup_nodatasum->sdev = sdev;
+		fixup_nodatasum->logical = logical;
+		fixup_nodatasum->root = fs_info->extent_root;
+		fixup_nodatasum->mirror_num = failed_mirror_index + 1;
 		/*
 		 * increment scrubs_running to prevent cancel requests from
 		 * completing as long as a fixup worker is running. we must also
@@ -649,235 +774,528 @@ static void scrub_fixup(struct scrub_bio *sbio, int ix)
 		atomic_inc(&fs_info->scrubs_paused);
 		mutex_unlock(&fs_info->scrub_lock);
 		atomic_inc(&sdev->fixup_cnt);
-		fixup->work.func = scrub_fixup_nodatasum;
-		btrfs_queue_worker(&fs_info->scrub_workers, &fixup->work);
-		return;
+		fixup_nodatasum->work.func = scrub_fixup_nodatasum;
+		btrfs_queue_worker(&fs_info->scrub_workers,
+				   &fixup_nodatasum->work);
+		goto out;
 	}
 
-	length = PAGE_SIZE;
-	ret = btrfs_map_block(map_tree, REQ_WRITE, logical, &length,
-			      &bbio, 0);
-	if (ret || !bbio || length < PAGE_SIZE) {
-		printk(KERN_ERR
-		       "scrub_fixup: btrfs_map_block failed us for %llu\n",
-		       (unsigned long long)logical);
-		WARN_ON(1);
-		kfree(bbio);
-		return;
+	/*
+	 * now build and submit the bios for the other mirrors, check
+	 * checksums
+	 */
+	for (mirror_index = 0;
+	     mirror_index < BTRFS_MAX_MIRRORS &&
+	     sblocks_for_recheck[mirror_index].page_count > 0;
+	     mirror_index++) {
+		if (mirror_index == failed_mirror_index)
+			continue;
+
+		/* build and submit the bios, check checksums */
+		ret = scrub_recheck_block(fs_info,
+					  sblocks_for_recheck + mirror_index,
+					  is_metadata, have_csum, csum,
+					  generation, sdev->csum_size);
+		if (ret)
+			goto did_not_correct_error;
 	}
 
-	if (bbio->num_stripes == 1)
-		/* there aren't any replicas */
-		goto uncorrectable;
+	/*
+	 * first try to pick the mirror which is completely without I/O
+	 * errors and also does not have a checksum error.
+	 * If one is found, and if a checksum is present, the full block
+	 * that is known to contain an error is rewritten. Afterwards
+	 * the block is known to be corrected.
+	 * If a mirror is found which is completely correct, and no
+	 * checksum is present, only those pages are rewritten that had
+	 * an I/O error in the block to be repaired, since it cannot be
+	 * determined, which copy of the other pages is better (and it
+	 * could happen otherwise that a correct page would be
+	 * overwritten by a bad one).
+	 */
+	for (mirror_index = 0;
+	     mirror_index < BTRFS_MAX_MIRRORS &&
+	     sblocks_for_recheck[mirror_index].page_count > 0;
+	     mirror_index++) {
+		struct scrub_block *sblock_other = sblocks_for_recheck +
+						   mirror_index;
+
+		if (!sblock_other->header_error &&
+		    !sblock_other->checksum_error &&
+		    sblock_other->no_io_error_seen) {
+			int force_write = is_metadata || have_csum;
+
+			ret = scrub_repair_block_from_good_copy(sblock_bad,
+								sblock_other,
+								force_write);
+			if (0 == ret)
+				goto corrected_error;
+		}
+	}
 
 	/*
-	 * first find a good copy
+	 * in case of I/O errors in the area that is supposed to be
+	 * repaired, continue by picking good copies of those pages.
+	 * Select the good pages from mirrors to rewrite bad pages from
+	 * the area to fix. Afterwards verify the checksum of the block
+	 * that is supposed to be repaired. This verification step is
+	 * only done for the purpose of statistic counting and for the
+	 * final scrub report, whether errors remain.
+	 * A perfect algorithm could make use of the checksum and try
+	 * all possible combinations of pages from the different mirrors
+	 * until the checksum verification succeeds. For example, when
+	 * the 2nd page of mirror #1 faces I/O errors, and the 2nd page
+	 * of mirror #2 is readable but the final checksum test fails,
+	 * then the 2nd page of mirror #3 could be tried, whether now
+	 * the final checksum succeedes. But this would be a rare
+	 * exception and is therefore not implemented. At least it is
+	 * avoided that the good copy is overwritten.
+	 * A more useful improvement would be to pick the sectors
+	 * without I/O error based on sector sizes (512 bytes on legacy
+	 * disks) instead of on PAGE_SIZE. Then maybe 512 byte of one
+	 * mirror could be repaired by taking 512 byte of a different
+	 * mirror, even if other 512 byte sectors in the same PAGE_SIZE
+	 * area are unreadable.
 	 */
-	for (i = 0; i < bbio->num_stripes; ++i) {
-		if (i + 1 == sbio->spag[ix].mirror_num)
-			continue;
 
-		if (scrub_fixup_io(READ, bbio->stripes[i].dev->bdev,
-				   bbio->stripes[i].physical >> 9,
-				   sbio->bio->bi_io_vec[ix].bv_page)) {
-			/* I/O-error, this is not a good copy */
+	/* can only fix I/O errors from here on */
+	if (sblock_bad->no_io_error_seen)
+		goto did_not_correct_error;
+
+	success = 1;
+	for (page_num = 0; page_num < sblock_bad->page_count; page_num++) {
+		struct scrub_page *page_bad = sblock_bad->pagev + page_num;
+
+		if (!page_bad->io_error)
 			continue;
+
+		for (mirror_index = 0;
+		     mirror_index < BTRFS_MAX_MIRRORS &&
+		     sblocks_for_recheck[mirror_index].page_count > 0;
+		     mirror_index++) {
+			struct scrub_block *sblock_other = sblocks_for_recheck +
+							   mirror_index;
+			struct scrub_page *page_other = sblock_other->pagev +
+							page_num;
+
+			if (!page_other->io_error) {
+				ret = scrub_repair_page_from_good_copy(
+					sblock_bad, sblock_other, page_num, 0);
+				if (0 == ret) {
+					page_bad->io_error = 0;
+					break; /* succeeded for this page */
+				}
+			}
 		}
 
-		if (scrub_fixup_check(sbio, ix) == 0)
-			break;
+		if (page_bad->io_error) {
+			/* did not find a mirror to copy the page from */
+			success = 0;
+		}
 	}
-	if (i == bbio->num_stripes)
-		goto uncorrectable;
 
-	if (!sdev->readonly) {
-		/*
-		 * bi_io_vec[ix].bv_page now contains good data, write it back
-		 */
-		if (scrub_fixup_io(WRITE, sdev->dev->bdev,
-				   (sbio->physical + ix * PAGE_SIZE) >> 9,
-				   sbio->bio->bi_io_vec[ix].bv_page)) {
-			/* I/O-error, writeback failed, give up */
-			goto uncorrectable;
+	if (success) {
+		if (is_metadata || have_csum) {
+			/*
+			 * need to verify the checksum now that all
+			 * sectors on disk are repaired (the write
+			 * request for data to be repaired is on its way).
+			 * Just be lazy and use scrub_recheck_block()
+			 * which re-reads the data before the checksum
+			 * is verified, but most likely the data comes out
+			 * of the page cache.
+			 */
+			ret = scrub_recheck_block(fs_info, sblock_bad,
+						  is_metadata, have_csum, csum,
+						  generation, sdev->csum_size);
+			if (!ret && !sblock_bad->header_error &&
+			    !sblock_bad->checksum_error &&
+			    sblock_bad->no_io_error_seen)
+				goto corrected_error;
+			else
+				goto did_not_correct_error;
+		} else {
+corrected_error:
+			spin_lock(&sdev->stat_lock);
+			sdev->stat.corrected_errors++;
+			spin_unlock(&sdev->stat_lock);
+			printk_ratelimited(KERN_ERR
+				"btrfs: fixed up error at logical %llu on dev %s\n",
+				(unsigned long long)logical, sdev->dev->name);
 		}
+	} else {
+did_not_correct_error:
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.uncorrectable_errors++;
+		spin_unlock(&sdev->stat_lock);
+		printk_ratelimited(KERN_ERR
+			"btrfs: unable to fixup (regular) error at logical %llu on dev %s\n",
+			(unsigned long long)logical, sdev->dev->name);
 	}
 
-	kfree(bbio);
-	spin_lock(&sdev->stat_lock);
-	++sdev->stat.corrected_errors;
-	spin_unlock(&sdev->stat_lock);
+out:
+	if (sblocks_for_recheck) {
+		for (mirror_index = 0; mirror_index < BTRFS_MAX_MIRRORS;
+		     mirror_index++) {
+			struct scrub_block *sblock = sblocks_for_recheck +
+						     mirror_index;
+			int page_index;
+
+			for (page_index = 0; page_index < SCRUB_PAGES_PER_BIO;
+			     page_index++)
+				if (sblock->pagev[page_index].page)
+					__free_page(
+						sblock->pagev[page_index].page);
+		}
+		kfree(sblocks_for_recheck);
+	}
 
-	printk_ratelimited(KERN_ERR "btrfs: fixed up error at logical %llu\n",
-			       (unsigned long long)logical);
-	return;
+	return 0;
+}
 
-uncorrectable:
-	kfree(bbio);
-	spin_lock(&sdev->stat_lock);
-	++sdev->stat.uncorrectable_errors;
-	spin_unlock(&sdev->stat_lock);
+static int scrub_setup_recheck_block(struct scrub_dev *sdev,
+				     struct btrfs_mapping_tree *map_tree,
+				     u64 length, u64 logical,
+				     struct scrub_block *sblocks_for_recheck)
+{
+	int page_index;
+	int mirror_index;
+	int ret;
+
+	/*
+	 * note: the three members sdev, ref_count and outstanding_pages
+	 * are not used (and not set) in the blocks that are used for
+	 * the recheck procedure
+	 */
+
+	page_index = 0;
+	while (length > 0) {
+		u64 sublen = min_t(u64, length, PAGE_SIZE);
+		u64 mapped_length = sublen;
+		struct btrfs_bio *bbio = NULL;
+
+		/*
+		 * with a length of PAGE_SIZE, each returned stripe
+		 * represents one mirror
+		 */
+		ret = btrfs_map_block(map_tree, WRITE, logical, &mapped_length,
+				      &bbio, 0);
+		if (ret || !bbio || mapped_length < sublen) {
+			kfree(bbio);
+			return -EIO;
+		}
 
-	printk_ratelimited(KERN_ERR "btrfs: unable to fixup (regular) error at "
-				"logical %llu\n", (unsigned long long)logical);
+		BUG_ON(page_index >= SCRUB_PAGES_PER_BIO);
+		for (mirror_index = 0; mirror_index < (int)bbio->num_stripes;
+		     mirror_index++) {
+			struct scrub_block *sblock;
+			struct scrub_page *page;
+
+			if (mirror_index >= BTRFS_MAX_MIRRORS)
+				continue;
+
+			sblock = sblocks_for_recheck + mirror_index;
+			page = sblock->pagev + page_index;
+			page->logical = logical;
+			page->physical = bbio->stripes[mirror_index].physical;
+			page->bdev = bbio->stripes[mirror_index].dev->bdev;
+			page->mirror_num = mirror_index + 1;
+			page->page = alloc_page(GFP_NOFS);
+			if (!page->page) {
+				spin_lock(&sdev->stat_lock);
+				sdev->stat.malloc_errors++;
+				spin_unlock(&sdev->stat_lock);
+				return -ENOMEM;
+			}
+			sblock->page_count++;
+		}
+		kfree(bbio);
+		length -= sublen;
+		logical += sublen;
+		page_index++;
+	}
+
+	return 0;
 }
 
-static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector,
-			 struct page *page)
+/*
+ * this function will check the on disk data for checksum errors, header
+ * errors and read I/O errors. If any I/O errors happen, the exact pages
+ * which are errored are marked as being bad. The goal is to enable scrub
+ * to take those pages that are not errored from all the mirrors so that
+ * the pages that are errored in the just handled mirror can be repaired.
+ */
+static int scrub_recheck_block(struct btrfs_fs_info *fs_info,
+			       struct scrub_block *sblock, int is_metadata,
+			       int have_csum, u8 *csum, u64 generation,
+			       u16 csum_size)
 {
-	struct bio *bio = NULL;
-	int ret;
-	DECLARE_COMPLETION_ONSTACK(complete);
+	int page_num;
+
+	sblock->no_io_error_seen = 1;
+	sblock->header_error = 0;
+	sblock->checksum_error = 0;
+
+	for (page_num = 0; page_num < sblock->page_count; page_num++) {
+		struct bio *bio;
+		int ret;
+		struct scrub_page *page = sblock->pagev + page_num;
+		DECLARE_COMPLETION_ONSTACK(complete);
+
+		BUG_ON(!page->page);
+		bio = bio_alloc(GFP_NOFS, 1);
+		bio->bi_bdev = page->bdev;
+		bio->bi_sector = page->physical >> 9;
+		bio->bi_end_io = scrub_complete_bio_end_io;
+		bio->bi_private = &complete;
+
+		ret = bio_add_page(bio, page->page, PAGE_SIZE, 0);
+		if (PAGE_SIZE != ret) {
+			bio_put(bio);
+			return -EIO;
+		}
+		btrfsic_submit_bio(READ, bio);
 
-	bio = bio_alloc(GFP_NOFS, 1);
-	bio->bi_bdev = bdev;
-	bio->bi_sector = sector;
-	bio_add_page(bio, page, PAGE_SIZE, 0);
-	bio->bi_end_io = scrub_fixup_end_io;
-	bio->bi_private = &complete;
-	btrfsic_submit_bio(rw, bio);
+		/* this will also unplug the queue */
+		wait_for_completion(&complete);
 
-	/* this will also unplug the queue */
-	wait_for_completion(&complete);
+		page->io_error = !test_bit(BIO_UPTODATE, &bio->bi_flags);
+		if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+			sblock->no_io_error_seen = 0;
+		bio_put(bio);
+	}
 
-	ret = !test_bit(BIO_UPTODATE, &bio->bi_flags);
-	bio_put(bio);
-	return ret;
+	if (sblock->no_io_error_seen)
+		scrub_recheck_block_checksum(fs_info, sblock, is_metadata,
+					     have_csum, csum, generation,
+					     csum_size);
+
+	return 0;
 }
 
-static void scrub_bio_end_io(struct bio *bio, int err)
+static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
+					 struct scrub_block *sblock,
+					 int is_metadata, int have_csum,
+					 const u8 *csum, u64 generation,
+					 u16 csum_size)
 {
-	struct scrub_bio *sbio = bio->bi_private;
-	struct scrub_dev *sdev = sbio->sdev;
-	struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
+	int page_num;
+	u8 calculated_csum[BTRFS_CSUM_SIZE];
+	u32 crc = ~(u32)0;
+	struct btrfs_root *root = fs_info->extent_root;
+	void *mapped_buffer;
+
+	BUG_ON(!sblock->pagev[0].page);
+	if (is_metadata) {
+		struct btrfs_header *h;
+
+		mapped_buffer = kmap_atomic(sblock->pagev[0].page);
+		h = (struct btrfs_header *)mapped_buffer;
+
+		if (sblock->pagev[0].logical != le64_to_cpu(h->bytenr) ||
+		    generation != le64_to_cpu(h->generation) ||
+		    memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE) ||
+		    memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
+			   BTRFS_UUID_SIZE))
+			sblock->header_error = 1;
+		csum = h->csum;
+	} else {
+		if (!have_csum)
+			return;
 
-	sbio->err = err;
-	sbio->bio = bio;
+		mapped_buffer = kmap_atomic(sblock->pagev[0].page);
+	}
 
-	btrfs_queue_worker(&fs_info->scrub_workers, &sbio->work);
+	for (page_num = 0;;) {
+		if (page_num == 0 && is_metadata)
+			crc = btrfs_csum_data(root,
+				((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE,
+				crc, PAGE_SIZE - BTRFS_CSUM_SIZE);
+		else
+			crc = btrfs_csum_data(root, mapped_buffer, crc,
+					      PAGE_SIZE);
+
+		kunmap_atomic(mapped_buffer);
+		page_num++;
+		if (page_num >= sblock->page_count)
+			break;
+		BUG_ON(!sblock->pagev[page_num].page);
+
+		mapped_buffer = kmap_atomic(sblock->pagev[page_num].page);
+	}
+
+	btrfs_csum_final(crc, calculated_csum);
+	if (memcmp(calculated_csum, csum, csum_size))
+		sblock->checksum_error = 1;
 }
 
-static void scrub_checksum(struct btrfs_work *work)
+static void scrub_complete_bio_end_io(struct bio *bio, int err)
 {
-	struct scrub_bio *sbio = container_of(work, struct scrub_bio, work);
-	struct scrub_dev *sdev = sbio->sdev;
-	struct page *page;
-	void *buffer;
-	int i;
-	u64 flags;
-	u64 logical;
-	int ret;
+	complete((struct completion *)bio->bi_private);
+}
 
-	if (sbio->err) {
-		ret = 0;
-		for (i = 0; i < sbio->count; ++i)
-			ret |= scrub_recheck_error(sbio, i);
-		if (!ret) {
-			spin_lock(&sdev->stat_lock);
-			++sdev->stat.unverified_errors;
-			spin_unlock(&sdev->stat_lock);
-		}
+static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
+					     struct scrub_block *sblock_good,
+					     int force_write)
+{
+	int page_num;
+	int ret = 0;
 
-		sbio->bio->bi_flags &= ~(BIO_POOL_MASK - 1);
-		sbio->bio->bi_flags |= 1 << BIO_UPTODATE;
-		sbio->bio->bi_phys_segments = 0;
-		sbio->bio->bi_idx = 0;
+	for (page_num = 0; page_num < sblock_bad->page_count; page_num++) {
+		int ret_sub;
 
-		for (i = 0; i < sbio->count; i++) {
-			struct bio_vec *bi;
-			bi = &sbio->bio->bi_io_vec[i];
-			bi->bv_offset = 0;
-			bi->bv_len = PAGE_SIZE;
-		}
-		goto out;
+		ret_sub = scrub_repair_page_from_good_copy(sblock_bad,
+							   sblock_good,
+							   page_num,
+							   force_write);
+		if (ret_sub)
+			ret = ret_sub;
 	}
-	for (i = 0; i < sbio->count; ++i) {
-		page = sbio->bio->bi_io_vec[i].bv_page;
-		buffer = kmap_atomic(page);
-		flags = sbio->spag[i].flags;
-		logical = sbio->logical + i * PAGE_SIZE;
-		ret = 0;
-		if (flags & BTRFS_EXTENT_FLAG_DATA) {
-			ret = scrub_checksum_data(sdev, sbio->spag + i, buffer);
-		} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-			ret = scrub_checksum_tree_block(sdev, sbio->spag + i,
-							logical, buffer);
-		} else if (flags & BTRFS_EXTENT_FLAG_SUPER) {
-			BUG_ON(i);
-			(void)scrub_checksum_super(sbio, buffer);
-		} else {
-			WARN_ON(1);
-		}
-		kunmap_atomic(buffer);
-		if (ret) {
-			ret = scrub_recheck_error(sbio, i);
-			if (!ret) {
-				spin_lock(&sdev->stat_lock);
-				++sdev->stat.unverified_errors;
-				spin_unlock(&sdev->stat_lock);
-			}
+
+	return ret;
+}
+
+static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
+					    struct scrub_block *sblock_good,
+					    int page_num, int force_write)
+{
+	struct scrub_page *page_bad = sblock_bad->pagev + page_num;
+	struct scrub_page *page_good = sblock_good->pagev + page_num;
+
+	BUG_ON(sblock_bad->pagev[page_num].page == NULL);
+	BUG_ON(sblock_good->pagev[page_num].page == NULL);
+	if (force_write || sblock_bad->header_error ||
+	    sblock_bad->checksum_error || page_bad->io_error) {
+		struct bio *bio;
+		int ret;
+		DECLARE_COMPLETION_ONSTACK(complete);
+
+		bio = bio_alloc(GFP_NOFS, 1);
+		bio->bi_bdev = page_bad->bdev;
+		bio->bi_sector = page_bad->physical >> 9;
+		bio->bi_end_io = scrub_complete_bio_end_io;
+		bio->bi_private = &complete;
+
+		ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
+		if (PAGE_SIZE != ret) {
+			bio_put(bio);
+			return -EIO;
 		}
+		btrfsic_submit_bio(WRITE, bio);
+
+		/* this will also unplug the queue */
+		wait_for_completion(&complete);
+		bio_put(bio);
 	}
 
-out:
-	scrub_free_bio(sbio->bio);
-	sbio->bio = NULL;
-	spin_lock(&sdev->list_lock);
-	sbio->next_free = sdev->first_free;
-	sdev->first_free = sbio->index;
-	spin_unlock(&sdev->list_lock);
-	atomic_dec(&sdev->in_flight);
-	wake_up(&sdev->list_wait);
+	return 0;
+}
+
+static void scrub_checksum(struct scrub_block *sblock)
+{
+	u64 flags;
+	int ret;
+
+	BUG_ON(sblock->page_count < 1);
+	flags = sblock->pagev[0].flags;
+	ret = 0;
+	if (flags & BTRFS_EXTENT_FLAG_DATA)
+		ret = scrub_checksum_data(sblock);
+	else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
+		ret = scrub_checksum_tree_block(sblock);
+	else if (flags & BTRFS_EXTENT_FLAG_SUPER)
+		(void)scrub_checksum_super(sblock);
+	else
+		WARN_ON(1);
+	if (ret)
+		scrub_handle_errored_block(sblock);
 }
 
-static int scrub_checksum_data(struct scrub_dev *sdev,
-			       struct scrub_page *spag, void *buffer)
+static int scrub_checksum_data(struct scrub_block *sblock)
 {
+	struct scrub_dev *sdev = sblock->sdev;
 	u8 csum[BTRFS_CSUM_SIZE];
+	u8 *on_disk_csum;
+	struct page *page;
+	void *buffer;
 	u32 crc = ~(u32)0;
 	int fail = 0;
 	struct btrfs_root *root = sdev->dev->dev_root;
+	u64 len;
+	int index;
 
-	if (!spag->have_csum)
+	BUG_ON(sblock->page_count < 1);
+	if (!sblock->pagev[0].have_csum)
 		return 0;
 
-	crc = btrfs_csum_data(root, buffer, crc, PAGE_SIZE);
+	on_disk_csum = sblock->pagev[0].csum;
+	page = sblock->pagev[0].page;
+	buffer = kmap_atomic(page);
+
+	len = sdev->sectorsize;
+	index = 0;
+	for (;;) {
+		u64 l = min_t(u64, len, PAGE_SIZE);
+
+		crc = btrfs_csum_data(root, buffer, crc, l);
+		kunmap_atomic(buffer);
+		len -= l;
+		if (len == 0)
+			break;
+		index++;
+		BUG_ON(index >= sblock->page_count);
+		BUG_ON(!sblock->pagev[index].page);
+		page = sblock->pagev[index].page;
+		buffer = kmap_atomic(page);
+	}
+
 	btrfs_csum_final(crc, csum);
-	if (memcmp(csum, spag->csum, sdev->csum_size))
+	if (memcmp(csum, on_disk_csum, sdev->csum_size))
 		fail = 1;
 
-	spin_lock(&sdev->stat_lock);
-	++sdev->stat.data_extents_scrubbed;
-	sdev->stat.data_bytes_scrubbed += PAGE_SIZE;
-	if (fail)
+	if (fail) {
+		spin_lock(&sdev->stat_lock);
 		++sdev->stat.csum_errors;
-	spin_unlock(&sdev->stat_lock);
+		spin_unlock(&sdev->stat_lock);
+	}
 
 	return fail;
 }
 
-static int scrub_checksum_tree_block(struct scrub_dev *sdev,
-				     struct scrub_page *spag, u64 logical,
-				     void *buffer)
+static int scrub_checksum_tree_block(struct scrub_block *sblock)
 {
+	struct scrub_dev *sdev = sblock->sdev;
 	struct btrfs_header *h;
 	struct btrfs_root *root = sdev->dev->dev_root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	u8 csum[BTRFS_CSUM_SIZE];
+	u8 calculated_csum[BTRFS_CSUM_SIZE];
+	u8 on_disk_csum[BTRFS_CSUM_SIZE];
+	struct page *page;
+	void *mapped_buffer;
+	u64 mapped_size;
+	void *p;
 	u32 crc = ~(u32)0;
 	int fail = 0;
 	int crc_fail = 0;
+	u64 len;
+	int index;
+
+	BUG_ON(sblock->page_count < 1);
+	page = sblock->pagev[0].page;
+	mapped_buffer = kmap_atomic(page);
+	h = (struct btrfs_header *)mapped_buffer;
+	memcpy(on_disk_csum, h->csum, sdev->csum_size);
 
 	/*
 	 * we don't use the getter functions here, as we
 	 * a) don't have an extent buffer and
 	 * b) the page is already kmapped
 	 */
-	h = (struct btrfs_header *)buffer;
 
-	if (logical != le64_to_cpu(h->bytenr))
+	if (sblock->pagev[0].logical != le64_to_cpu(h->bytenr))
 		++fail;
 
-	if (spag->generation != le64_to_cpu(h->generation))
+	if (sblock->pagev[0].generation != le64_to_cpu(h->generation))
 		++fail;
 
 	if (memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE))
@@ -887,51 +1305,99 @@ static int scrub_checksum_tree_block(struct scrub_dev *sdev,
 		   BTRFS_UUID_SIZE))
 		++fail;
 
-	crc = btrfs_csum_data(root, buffer + BTRFS_CSUM_SIZE, crc,
-			      PAGE_SIZE - BTRFS_CSUM_SIZE);
-	btrfs_csum_final(crc, csum);
-	if (memcmp(csum, h->csum, sdev->csum_size))
+	BUG_ON(sdev->nodesize != sdev->leafsize);
+	len = sdev->nodesize - BTRFS_CSUM_SIZE;
+	mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE;
+	p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE;
+	index = 0;
+	for (;;) {
+		u64 l = min_t(u64, len, mapped_size);
+
+		crc = btrfs_csum_data(root, p, crc, l);
+		kunmap_atomic(mapped_buffer);
+		len -= l;
+		if (len == 0)
+			break;
+		index++;
+		BUG_ON(index >= sblock->page_count);
+		BUG_ON(!sblock->pagev[index].page);
+		page = sblock->pagev[index].page;
+		mapped_buffer = kmap_atomic(page);
+		mapped_size = PAGE_SIZE;
+		p = mapped_buffer;
+	}
+
+	btrfs_csum_final(crc, calculated_csum);
+	if (memcmp(calculated_csum, on_disk_csum, sdev->csum_size))
 		++crc_fail;
 
-	spin_lock(&sdev->stat_lock);
-	++sdev->stat.tree_extents_scrubbed;
-	sdev->stat.tree_bytes_scrubbed += PAGE_SIZE;
-	if (crc_fail)
-		++sdev->stat.csum_errors;
-	if (fail)
-		++sdev->stat.verify_errors;
-	spin_unlock(&sdev->stat_lock);
+	if (crc_fail || fail) {
+		spin_lock(&sdev->stat_lock);
+		if (crc_fail)
+			++sdev->stat.csum_errors;
+		if (fail)
+			++sdev->stat.verify_errors;
+		spin_unlock(&sdev->stat_lock);
+	}
 
 	return fail || crc_fail;
 }
 
-static int scrub_checksum_super(struct scrub_bio *sbio, void *buffer)
+static int scrub_checksum_super(struct scrub_block *sblock)
 {
 	struct btrfs_super_block *s;
-	u64 logical;
-	struct scrub_dev *sdev = sbio->sdev;
+	struct scrub_dev *sdev = sblock->sdev;
 	struct btrfs_root *root = sdev->dev->dev_root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	u8 csum[BTRFS_CSUM_SIZE];
+	u8 calculated_csum[BTRFS_CSUM_SIZE];
+	u8 on_disk_csum[BTRFS_CSUM_SIZE];
+	struct page *page;
+	void *mapped_buffer;
+	u64 mapped_size;
+	void *p;
 	u32 crc = ~(u32)0;
 	int fail = 0;
+	u64 len;
+	int index;
 
-	s = (struct btrfs_super_block *)buffer;
-	logical = sbio->logical;
+	BUG_ON(sblock->page_count < 1);
+	page = sblock->pagev[0].page;
+	mapped_buffer = kmap_atomic(page);
+	s = (struct btrfs_super_block *)mapped_buffer;
+	memcpy(on_disk_csum, s->csum, sdev->csum_size);
 
-	if (logical != le64_to_cpu(s->bytenr))
+	if (sblock->pagev[0].logical != le64_to_cpu(s->bytenr))
 		++fail;
 
-	if (sbio->spag[0].generation != le64_to_cpu(s->generation))
+	if (sblock->pagev[0].generation != le64_to_cpu(s->generation))
 		++fail;
 
 	if (memcmp(s->fsid, fs_info->fsid, BTRFS_UUID_SIZE))
 		++fail;
 
-	crc = btrfs_csum_data(root, buffer + BTRFS_CSUM_SIZE, crc,
-			      PAGE_SIZE - BTRFS_CSUM_SIZE);
-	btrfs_csum_final(crc, csum);
-	if (memcmp(csum, s->csum, sbio->sdev->csum_size))
+	len = BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE;
+	mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE;
+	p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE;
+	index = 0;
+	for (;;) {
+		u64 l = min_t(u64, len, mapped_size);
+
+		crc = btrfs_csum_data(root, p, crc, l);
+		kunmap_atomic(mapped_buffer);
+		len -= l;
+		if (len == 0)
+			break;
+		index++;
+		BUG_ON(index >= sblock->page_count);
+		BUG_ON(!sblock->pagev[index].page);
+		page = sblock->pagev[index].page;
+		mapped_buffer = kmap_atomic(page);
+		mapped_size = PAGE_SIZE;
+		p = mapped_buffer;
+	}
+
+	btrfs_csum_final(crc, calculated_csum);
+	if (memcmp(calculated_csum, on_disk_csum, sdev->csum_size))
 		++fail;
 
 	if (fail) {
@@ -948,29 +1414,42 @@ static int scrub_checksum_super(struct scrub_bio *sbio, void *buffer)
 	return fail;
 }
 
-static int scrub_submit(struct scrub_dev *sdev)
+static void scrub_block_get(struct scrub_block *sblock)
+{
+	atomic_inc(&sblock->ref_count);
+}
+
+static void scrub_block_put(struct scrub_block *sblock)
+{
+	if (atomic_dec_and_test(&sblock->ref_count)) {
+		int i;
+
+		for (i = 0; i < sblock->page_count; i++)
+			if (sblock->pagev[i].page)
+				__free_page(sblock->pagev[i].page);
+		kfree(sblock);
+	}
+}
+
+static void scrub_submit(struct scrub_dev *sdev)
 {
 	struct scrub_bio *sbio;
 
 	if (sdev->curr == -1)
-		return 0;
+		return;
 
 	sbio = sdev->bios[sdev->curr];
-	sbio->err = 0;
 	sdev->curr = -1;
 	atomic_inc(&sdev->in_flight);
 
 	btrfsic_submit_bio(READ, sbio->bio);
-
-	return 0;
 }
 
-static int scrub_page(struct scrub_dev *sdev, u64 logical, u64 len,
-		      u64 physical, u64 flags, u64 gen, int mirror_num,
-		      u8 *csum, int force)
+static int scrub_add_page_to_bio(struct scrub_dev *sdev,
+				 struct scrub_page *spage)
 {
+	struct scrub_block *sblock = spage->sblock;
 	struct scrub_bio *sbio;
-	struct page *page;
 	int ret;
 
 again:
@@ -983,7 +1462,7 @@ again:
 		if (sdev->curr != -1) {
 			sdev->first_free = sdev->bios[sdev->curr]->next_free;
 			sdev->bios[sdev->curr]->next_free = -1;
-			sdev->bios[sdev->curr]->count = 0;
+			sdev->bios[sdev->curr]->page_count = 0;
 			spin_unlock(&sdev->list_lock);
 		} else {
 			spin_unlock(&sdev->list_lock);
@@ -991,62 +1470,200 @@ again:
 		}
 	}
 	sbio = sdev->bios[sdev->curr];
-	if (sbio->count == 0) {
+	if (sbio->page_count == 0) {
 		struct bio *bio;
 
-		sbio->physical = physical;
-		sbio->logical = logical;
-		bio = bio_alloc(GFP_NOFS, SCRUB_PAGES_PER_BIO);
-		if (!bio)
-			return -ENOMEM;
+		sbio->physical = spage->physical;
+		sbio->logical = spage->logical;
+		bio = sbio->bio;
+		if (!bio) {
+			bio = bio_alloc(GFP_NOFS, sdev->pages_per_bio);
+			if (!bio)
+				return -ENOMEM;
+			sbio->bio = bio;
+		}
 
 		bio->bi_private = sbio;
 		bio->bi_end_io = scrub_bio_end_io;
 		bio->bi_bdev = sdev->dev->bdev;
-		bio->bi_sector = sbio->physical >> 9;
+		bio->bi_sector = spage->physical >> 9;
 		sbio->err = 0;
-		sbio->bio = bio;
-	} else if (sbio->physical + sbio->count * PAGE_SIZE != physical ||
-		   sbio->logical + sbio->count * PAGE_SIZE != logical) {
-		ret = scrub_submit(sdev);
-		if (ret)
-			return ret;
+	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
+		   spage->physical ||
+		   sbio->logical + sbio->page_count * PAGE_SIZE !=
+		   spage->logical) {
+		scrub_submit(sdev);
 		goto again;
 	}
-	sbio->spag[sbio->count].flags = flags;
-	sbio->spag[sbio->count].generation = gen;
-	sbio->spag[sbio->count].have_csum = 0;
-	sbio->spag[sbio->count].mirror_num = mirror_num;
-
-	page = alloc_page(GFP_NOFS);
-	if (!page)
-		return -ENOMEM;
 
-	ret = bio_add_page(sbio->bio, page, PAGE_SIZE, 0);
-	if (!ret) {
-		__free_page(page);
-		ret = scrub_submit(sdev);
-		if (ret)
-			return ret;
+	sbio->pagev[sbio->page_count] = spage;
+	ret = bio_add_page(sbio->bio, spage->page, PAGE_SIZE, 0);
+	if (ret != PAGE_SIZE) {
+		if (sbio->page_count < 1) {
+			bio_put(sbio->bio);
+			sbio->bio = NULL;
+			return -EIO;
+		}
+		scrub_submit(sdev);
 		goto again;
 	}
 
-	if (csum) {
-		sbio->spag[sbio->count].have_csum = 1;
-		memcpy(sbio->spag[sbio->count].csum, csum, sdev->csum_size);
+	scrub_block_get(sblock); /* one for the added page */
+	atomic_inc(&sblock->outstanding_pages);
+	sbio->page_count++;
+	if (sbio->page_count == sdev->pages_per_bio)
+		scrub_submit(sdev);
+
+	return 0;
+}
+
+static int scrub_pages(struct scrub_dev *sdev, u64 logical, u64 len,
+		       u64 physical, u64 flags, u64 gen, int mirror_num,
+		       u8 *csum, int force)
+{
+	struct scrub_block *sblock;
+	int index;
+
+	sblock = kzalloc(sizeof(*sblock), GFP_NOFS);
+	if (!sblock) {
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.malloc_errors++;
+		spin_unlock(&sdev->stat_lock);
+		return -ENOMEM;
 	}
-	++sbio->count;
-	if (sbio->count == SCRUB_PAGES_PER_BIO || force) {
+
+	/* one ref inside this function, plus one for each page later on */
+	atomic_set(&sblock->ref_count, 1);
+	sblock->sdev = sdev;
+	sblock->no_io_error_seen = 1;
+
+	for (index = 0; len > 0; index++) {
+		struct scrub_page *spage = sblock->pagev + index;
+		u64 l = min_t(u64, len, PAGE_SIZE);
+
+		BUG_ON(index >= SCRUB_MAX_PAGES_PER_BLOCK);
+		spage->page = alloc_page(GFP_NOFS);
+		if (!spage->page) {
+			spin_lock(&sdev->stat_lock);
+			sdev->stat.malloc_errors++;
+			spin_unlock(&sdev->stat_lock);
+			while (index > 0) {
+				index--;
+				__free_page(sblock->pagev[index].page);
+			}
+			kfree(sblock);
+			return -ENOMEM;
+		}
+		spage->sblock = sblock;
+		spage->bdev = sdev->dev->bdev;
+		spage->flags = flags;
+		spage->generation = gen;
+		spage->logical = logical;
+		spage->physical = physical;
+		spage->mirror_num = mirror_num;
+		if (csum) {
+			spage->have_csum = 1;
+			memcpy(spage->csum, csum, sdev->csum_size);
+		} else {
+			spage->have_csum = 0;
+		}
+		sblock->page_count++;
+		len -= l;
+		logical += l;
+		physical += l;
+	}
+
+	BUG_ON(sblock->page_count == 0);
+	for (index = 0; index < sblock->page_count; index++) {
+		struct scrub_page *spage = sblock->pagev + index;
 		int ret;
 
-		ret = scrub_submit(sdev);
-		if (ret)
+		ret = scrub_add_page_to_bio(sdev, spage);
+		if (ret) {
+			scrub_block_put(sblock);
 			return ret;
+		}
 	}
 
+	if (force)
+		scrub_submit(sdev);
+
+	/* last one frees, either here or in bio completion for last page */
+	scrub_block_put(sblock);
 	return 0;
 }
 
+static void scrub_bio_end_io(struct bio *bio, int err)
+{
+	struct scrub_bio *sbio = bio->bi_private;
+	struct scrub_dev *sdev = sbio->sdev;
+	struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
+
+	sbio->err = err;
+	sbio->bio = bio;
+
+	btrfs_queue_worker(&fs_info->scrub_workers, &sbio->work);
+}
+
+static void scrub_bio_end_io_worker(struct btrfs_work *work)
+{
+	struct scrub_bio *sbio = container_of(work, struct scrub_bio, work);
+	struct scrub_dev *sdev = sbio->sdev;
+	int i;
+
+	BUG_ON(sbio->page_count > SCRUB_PAGES_PER_BIO);
+	if (sbio->err) {
+		for (i = 0; i < sbio->page_count; i++) {
+			struct scrub_page *spage = sbio->pagev[i];
+
+			spage->io_error = 1;
+			spage->sblock->no_io_error_seen = 0;
+		}
+	}
+
+	/* now complete the scrub_block items that have all pages completed */
+	for (i = 0; i < sbio->page_count; i++) {
+		struct scrub_page *spage = sbio->pagev[i];
+		struct scrub_block *sblock = spage->sblock;
+
+		if (atomic_dec_and_test(&sblock->outstanding_pages))
+			scrub_block_complete(sblock);
+		scrub_block_put(sblock);
+	}
+
+	if (sbio->err) {
+		/* what is this good for??? */
+		sbio->bio->bi_flags &= ~(BIO_POOL_MASK - 1);
+		sbio->bio->bi_flags |= 1 << BIO_UPTODATE;
+		sbio->bio->bi_phys_segments = 0;
+		sbio->bio->bi_idx = 0;
+
+		for (i = 0; i < sbio->page_count; i++) {
+			struct bio_vec *bi;
+			bi = &sbio->bio->bi_io_vec[i];
+			bi->bv_offset = 0;
+			bi->bv_len = PAGE_SIZE;
+		}
+	}
+
+	bio_put(sbio->bio);
+	sbio->bio = NULL;
+	spin_lock(&sdev->list_lock);
+	sbio->next_free = sdev->first_free;
+	sdev->first_free = sbio->index;
+	spin_unlock(&sdev->list_lock);
+	atomic_dec(&sdev->in_flight);
+	wake_up(&sdev->list_wait);
+}
+
+static void scrub_block_complete(struct scrub_block *sblock)
+{
+	if (!sblock->no_io_error_seen)
+		scrub_handle_errored_block(sblock);
+	else
+		scrub_checksum(sblock);
+}
+
 static int scrub_find_csum(struct scrub_dev *sdev, u64 logical, u64 len,
 			   u8 *csum)
 {
@@ -1054,7 +1671,6 @@ static int scrub_find_csum(struct scrub_dev *sdev, u64 logical, u64 len,
 	int ret = 0;
 	unsigned long i;
 	unsigned long num_sectors;
-	u32 sectorsize = sdev->dev->dev_root->sectorsize;
 
 	while (!list_empty(&sdev->csum_list)) {
 		sum = list_first_entry(&sdev->csum_list,
@@ -1072,7 +1688,7 @@ static int scrub_find_csum(struct scrub_dev *sdev, u64 logical, u64 len,
 	if (!sum)
 		return 0;
 
-	num_sectors = sum->len / sectorsize;
+	num_sectors = sum->len / sdev->sectorsize;
 	for (i = 0; i < num_sectors; ++i) {
 		if (sum->sums[i].bytenr == logical) {
 			memcpy(csum, &sum->sums[i].sum, sdev->csum_size);
@@ -1093,9 +1709,28 @@ static int scrub_extent(struct scrub_dev *sdev, u64 logical, u64 len,
 {
 	int ret;
 	u8 csum[BTRFS_CSUM_SIZE];
+	u32 blocksize;
+
+	if (flags & BTRFS_EXTENT_FLAG_DATA) {
+		blocksize = sdev->sectorsize;
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.data_extents_scrubbed++;
+		sdev->stat.data_bytes_scrubbed += len;
+		spin_unlock(&sdev->stat_lock);
+	} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+		BUG_ON(sdev->nodesize != sdev->leafsize);
+		blocksize = sdev->nodesize;
+		spin_lock(&sdev->stat_lock);
+		sdev->stat.tree_extents_scrubbed++;
+		sdev->stat.tree_bytes_scrubbed += len;
+		spin_unlock(&sdev->stat_lock);
+	} else {
+		blocksize = sdev->sectorsize;
+		BUG_ON(1);
+	}
 
 	while (len) {
-		u64 l = min_t(u64, len, PAGE_SIZE);
+		u64 l = min_t(u64, len, blocksize);
 		int have_csum = 0;
 
 		if (flags & BTRFS_EXTENT_FLAG_DATA) {
@@ -1104,8 +1739,8 @@ static int scrub_extent(struct scrub_dev *sdev, u64 logical, u64 len,
 			if (have_csum == 0)
 				++sdev->stat.no_csum;
 		}
-		ret = scrub_page(sdev, logical, l, physical, flags, gen,
-				 mirror_num, have_csum ? csum : NULL, 0);
+		ret = scrub_pages(sdev, logical, l, physical, flags, gen,
+				  mirror_num, have_csum ? csum : NULL, 0);
 		if (ret)
 			return ret;
 		len -= l;
@@ -1170,6 +1805,11 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
 	if (!path)
 		return -ENOMEM;
 
+	/*
+	 * work on commit root. The related disk blocks are static as
+	 * long as COW is applied. This means, it is save to rewrite
+	 * them to repair disk errors without any race conditions
+	 */
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
@@ -1516,15 +2156,18 @@ static noinline_for_stack int scrub_supers(struct scrub_dev *sdev)
 	struct btrfs_device *device = sdev->dev;
 	struct btrfs_root *root = device->dev_root;
 
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+		return -EIO;
+
 	gen = root->fs_info->last_trans_committed;
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
 		bytenr = btrfs_sb_offset(i);
-		if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes)
+		if (bytenr + BTRFS_SUPER_INFO_SIZE > device->total_bytes)
 			break;
 
-		ret = scrub_page(sdev, bytenr, PAGE_SIZE, bytenr,
-				 BTRFS_EXTENT_FLAG_SUPER, gen, i, NULL, 1);
+		ret = scrub_pages(sdev, bytenr, BTRFS_SUPER_INFO_SIZE, bytenr,
+				     BTRFS_EXTENT_FLAG_SUPER, gen, i, NULL, 1);
 		if (ret)
 			return ret;
 	}
@@ -1583,10 +2226,30 @@ int btrfs_scrub_dev(struct btrfs_root *root, u64 devid, u64 start, u64 end,
 	/*
 	 * check some assumptions
 	 */
-	if (root->sectorsize != PAGE_SIZE ||
-	    root->sectorsize != root->leafsize ||
-	    root->sectorsize != root->nodesize) {
-		printk(KERN_ERR "btrfs_scrub: size assumptions fail\n");
+	if (root->nodesize != root->leafsize) {
+		printk(KERN_ERR
+		       "btrfs_scrub: size assumption nodesize == leafsize (%d == %d) fails\n",
+		       root->nodesize, root->leafsize);
+		return -EINVAL;
+	}
+
+	if (root->nodesize > BTRFS_STRIPE_LEN) {
+		/*
+		 * in this case scrub is unable to calculate the checksum
+		 * the way scrub is implemented. Do not handle this
+		 * situation at all because it won't ever happen.
+		 */
+		printk(KERN_ERR
+		       "btrfs_scrub: size assumption nodesize <= BTRFS_STRIPE_LEN (%d <= %d) fails\n",
+		       root->nodesize, BTRFS_STRIPE_LEN);
+		return -EINVAL;
+	}
+
+	if (root->sectorsize != PAGE_SIZE) {
+		/* not supported for data w/o checksums */
+		printk(KERN_ERR
+		       "btrfs_scrub: size assumption sectorsize != PAGE_SIZE (%d != %lld) fails\n",
+		       root->sectorsize, (unsigned long long)PAGE_SIZE);
 		return -EINVAL;
 	}
 
@@ -1656,7 +2319,7 @@ int btrfs_scrub_dev(struct btrfs_root *root, u64 devid, u64 start, u64 end,
 	return ret;
 }
 
-int btrfs_scrub_pause(struct btrfs_root *root)
+void btrfs_scrub_pause(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
@@ -1671,34 +2334,28 @@ int btrfs_scrub_pause(struct btrfs_root *root)
 		mutex_lock(&fs_info->scrub_lock);
 	}
 	mutex_unlock(&fs_info->scrub_lock);
-
-	return 0;
 }
 
-int btrfs_scrub_continue(struct btrfs_root *root)
+void btrfs_scrub_continue(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	atomic_dec(&fs_info->scrub_pause_req);
 	wake_up(&fs_info->scrub_pause_wait);
-	return 0;
 }
 
-int btrfs_scrub_pause_super(struct btrfs_root *root)
+void btrfs_scrub_pause_super(struct btrfs_root *root)
 {
 	down_write(&root->fs_info->scrub_super_lock);
-	return 0;
 }
 
-int btrfs_scrub_continue_super(struct btrfs_root *root)
+void btrfs_scrub_continue_super(struct btrfs_root *root)
 {
 	up_write(&root->fs_info->scrub_super_lock);
-	return 0;
 }
 
-int btrfs_scrub_cancel(struct btrfs_root *root)
+int __btrfs_scrub_cancel(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	mutex_lock(&fs_info->scrub_lock);
 	if (!atomic_read(&fs_info->scrubs_running)) {
@@ -1719,6 +2376,11 @@ int btrfs_scrub_cancel(struct btrfs_root *root)
 	return 0;
 }
 
+int btrfs_scrub_cancel(struct btrfs_root *root)
+{
+	return __btrfs_scrub_cancel(root->fs_info);
+}
+
 int btrfs_scrub_cancel_dev(struct btrfs_root *root, struct btrfs_device *dev)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -1741,6 +2403,7 @@ int btrfs_scrub_cancel_dev(struct btrfs_root *root, struct btrfs_device *dev)
 
 	return 0;
 }
+
 int btrfs_scrub_cancel_devid(struct btrfs_root *root, u64 devid)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index bc1f6ad18442..c6ffa5812419 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -44,8 +44,9 @@
 #define BTRFS_SETGET_FUNCS(name, type, member, bits)			\
 u##bits btrfs_##name(struct extent_buffer *eb, type *s);		\
 void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val);	\
-u##bits btrfs_##name(struct extent_buffer *eb,				\
-				   type *s)				\
+void btrfs_set_token_##name(struct extent_buffer *eb, type *s, u##bits val, struct btrfs_map_token *token);	\
+u##bits btrfs_token_##name(struct extent_buffer *eb,				\
+			   type *s, struct btrfs_map_token *token)	\
 {									\
 	unsigned long part_offset = (unsigned long)s;			\
 	unsigned long offset = part_offset + offsetof(type, member);	\
@@ -54,9 +55,18 @@ u##bits btrfs_##name(struct extent_buffer *eb,				\
 	char *kaddr;						\
 	unsigned long map_start;				\
 	unsigned long map_len;					\
+	unsigned long mem_len = sizeof(((type *)0)->member);	\
 	u##bits res;						\
+	if (token && token->kaddr && token->offset <= offset &&	\
+	    token->eb == eb &&					\
+	   (token->offset + PAGE_CACHE_SIZE >= offset + mem_len)) { \
+		kaddr = token->kaddr;				\
+		p = (type *)(kaddr + part_offset - token->offset);  \
+		res = le##bits##_to_cpu(p->member);		\
+		return res;					\
+	}							\
 	err = map_private_extent_buffer(eb, offset,		\
-			sizeof(((type *)0)->member),		\
+			mem_len,				\
 			&kaddr, &map_start, &map_len);		\
 	if (err) {						\
 		__le##bits leres;				\
@@ -65,10 +75,15 @@ u##bits btrfs_##name(struct extent_buffer *eb,				\
 	}							\
 	p = (type *)(kaddr + part_offset - map_start);		\
 	res = le##bits##_to_cpu(p->member);			\
+	if (token) {						\
+		token->kaddr = kaddr;				\
+		token->offset = map_start;			\
+		token->eb = eb;					\
+	}							\
 	return res;						\
 }									\
-void btrfs_set_##name(struct extent_buffer *eb,				\
-				    type *s, u##bits val)		\
+void btrfs_set_token_##name(struct extent_buffer *eb,				\
+			    type *s, u##bits val, struct btrfs_map_token *token)		\
 {									\
 	unsigned long part_offset = (unsigned long)s;			\
 	unsigned long offset = part_offset + offsetof(type, member);	\
@@ -77,8 +92,17 @@ void btrfs_set_##name(struct extent_buffer *eb,				\
 	char *kaddr;						\
 	unsigned long map_start;				\
 	unsigned long map_len;					\
+	unsigned long mem_len = sizeof(((type *)0)->member);	\
+	if (token && token->kaddr && token->offset <= offset &&	\
+	    token->eb == eb &&					\
+	   (token->offset + PAGE_CACHE_SIZE >= offset + mem_len)) { \
+		kaddr = token->kaddr;				\
+		p = (type *)(kaddr + part_offset - token->offset);  \
+		p->member = cpu_to_le##bits(val);		\
+		return;						\
+	}							\
 	err = map_private_extent_buffer(eb, offset,		\
-			sizeof(((type *)0)->member),		\
+			mem_len,				\
 			&kaddr, &map_start, &map_len);		\
 	if (err) {						\
 		__le##bits val2;				\
@@ -88,7 +112,22 @@ void btrfs_set_##name(struct extent_buffer *eb,				\
 	}							\
 	p = (type *)(kaddr + part_offset - map_start);		\
 	p->member = cpu_to_le##bits(val);			\
-}
+	if (token) {						\
+		token->kaddr = kaddr;				\
+		token->offset = map_start;			\
+		token->eb = eb;					\
+	}							\
+}								\
+void btrfs_set_##name(struct extent_buffer *eb,			\
+		      type *s, u##bits val)			\
+{								\
+	btrfs_set_token_##name(eb, s, val, NULL);		\
+}								\
+u##bits btrfs_##name(struct extent_buffer *eb,			\
+		      type *s)					\
+{								\
+	return btrfs_token_##name(eb, s, NULL);			\
+}								\
 
 #include "ctree.h"
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 81df3fec6a6d..8d5d380f7bdb 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -76,6 +76,9 @@ static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
 	case -EROFS:
 		errstr = "Readonly filesystem";
 		break;
+	case -EEXIST:
+		errstr = "Object already exists";
+		break;
 	default:
 		if (nbuf) {
 			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
@@ -116,6 +119,8 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
 	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
 		sb->s_flags |= MS_RDONLY;
 		printk(KERN_INFO "btrfs is forced readonly\n");
+		__btrfs_scrub_cancel(fs_info);
+//		WARN_ON(1);
 	}
 }
 
@@ -124,25 +129,132 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
  * invokes the approciate error response.
  */
 void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
-		     unsigned int line, int errno)
+		       unsigned int line, int errno, const char *fmt, ...)
 {
 	struct super_block *sb = fs_info->sb;
 	char nbuf[16];
 	const char *errstr;
+	va_list args;
+	va_start(args, fmt);
 
 	/*
 	 * Special case: if the error is EROFS, and we're already
 	 * under MS_RDONLY, then it is safe here.
 	 */
 	if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
+  		return;
+
+  	errstr = btrfs_decode_error(fs_info, errno, nbuf);
+	if (fmt) {
+		struct va_format vaf = {
+			.fmt = fmt,
+			.va = &args,
+		};
+
+		printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s (%pV)\n",
+			sb->s_id, function, line, errstr, &vaf);
+	} else {
+		printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s\n",
+			sb->s_id, function, line, errstr);
+	}
+
+	/* Don't go through full error handling during mount */
+	if (sb->s_flags & MS_BORN) {
+		save_error_info(fs_info);
+		btrfs_handle_error(fs_info);
+	}
+	va_end(args);
+}
+
+const char *logtypes[] = {
+	"emergency",
+	"alert",
+	"critical",
+	"error",
+	"warning",
+	"notice",
+	"info",
+	"debug",
+};
+
+void btrfs_printk(struct btrfs_fs_info *fs_info, const char *fmt, ...)
+{
+	struct super_block *sb = fs_info->sb;
+	char lvl[4];
+	struct va_format vaf;
+	va_list args;
+	const char *type = logtypes[4];
+
+	va_start(args, fmt);
+
+	if (fmt[0] == '<' && isdigit(fmt[1]) && fmt[2] == '>') {
+		strncpy(lvl, fmt, 3);
+		fmt += 3;
+		type = logtypes[fmt[1] - '0'];
+	} else
+		*lvl = '\0';
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk("%sBTRFS %s (device %s): %pV", lvl, type, sb->s_id, &vaf);
+}
+
+/*
+ * We only mark the transaction aborted and then set the file system read-only.
+ * This will prevent new transactions from starting or trying to join this
+ * one.
+ *
+ * This means that error recovery at the call site is limited to freeing
+ * any local memory allocations and passing the error code up without
+ * further cleanup. The transaction should complete as it normally would
+ * in the call path but will return -EIO.
+ *
+ * We'll complete the cleanup in btrfs_end_transaction and
+ * btrfs_commit_transaction.
+ */
+void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root, const char *function,
+			       unsigned int line, int errno)
+{
+	WARN_ONCE(1, KERN_DEBUG "btrfs: Transaction aborted");
+	trans->aborted = errno;
+	/* Nothing used. The other threads that have joined this
+	 * transaction may be able to continue. */
+	if (!trans->blocks_used) {
+		btrfs_printk(root->fs_info, "Aborting unused transaction.\n");
 		return;
+	}
+	trans->transaction->aborted = errno;
+	__btrfs_std_error(root->fs_info, function, line, errno, NULL);
+}
+/*
+ * __btrfs_panic decodes unexpected, fatal errors from the caller,
+ * issues an alert, and either panics or BUGs, depending on mount options.
+ */
+void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
+		   unsigned int line, int errno, const char *fmt, ...)
+{
+	char nbuf[16];
+	char *s_id = "<unknown>";
+	const char *errstr;
+	struct va_format vaf = { .fmt = fmt };
+	va_list args;
 
-	errstr = btrfs_decode_error(fs_info, errno, nbuf);
-	printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s\n",
-		sb->s_id, function, line, errstr);
-	save_error_info(fs_info);
+	if (fs_info)
+		s_id = fs_info->sb->s_id;
 
-	btrfs_handle_error(fs_info);
+	va_start(args, fmt);
+	vaf.va = &args;
+
+	errstr = btrfs_decode_error(fs_info, errno, nbuf);
+	if (fs_info->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR)
+		panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (%s)\n",
+			s_id, function, line, &vaf, errstr);
+
+	printk(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (%s)\n",
+	       s_id, function, line, &vaf, errstr);
+	va_end(args);
+	/* Caller calls BUG() */
 }
 
 static void btrfs_put_super(struct super_block *sb)
@@ -166,7 +278,7 @@ enum {
 	Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache,
 	Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
 	Opt_check_integrity, Opt_check_integrity_including_extent_data,
-	Opt_check_integrity_print_mask,
+	Opt_check_integrity_print_mask, Opt_fatal_errors,
 	Opt_err,
 };
 
@@ -206,12 +318,14 @@ static match_table_t tokens = {
 	{Opt_check_integrity, "check_int"},
 	{Opt_check_integrity_including_extent_data, "check_int_data"},
 	{Opt_check_integrity_print_mask, "check_int_print_mask=%d"},
+	{Opt_fatal_errors, "fatal_errors=%s"},
 	{Opt_err, NULL},
 };
 
 /*
  * Regular mount options parser.  Everything that is needed only when
  * reading in a new superblock is parsed here.
+ * XXX JDM: This needs to be cleaned up for remount.
  */
 int btrfs_parse_options(struct btrfs_root *root, char *options)
 {
@@ -438,6 +552,18 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			ret = -EINVAL;
 			goto out;
 #endif
+		case Opt_fatal_errors:
+			if (strcmp(args[0].from, "panic") == 0)
+				btrfs_set_opt(info->mount_opt,
+					      PANIC_ON_FATAL_ERROR);
+			else if (strcmp(args[0].from, "bug") == 0)
+				btrfs_clear_opt(info->mount_opt,
+					      PANIC_ON_FATAL_ERROR);
+			else {
+				ret = -EINVAL;
+				goto out;
+			}
+			break;
 		case Opt_err:
 			printk(KERN_INFO "btrfs: unrecognized mount option "
 			       "'%s'\n", p);
@@ -762,6 +888,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",inode_cache");
 	if (btrfs_test_opt(root, SKIP_BALANCE))
 		seq_puts(seq, ",skip_balance");
+	if (btrfs_test_opt(root, PANIC_ON_FATAL_ERROR))
+		seq_puts(seq, ",fatal_errors=panic");
 	return 0;
 }
 
@@ -995,11 +1123,20 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_root *root = fs_info->tree_root;
+	unsigned old_flags = sb->s_flags;
+	unsigned long old_opts = fs_info->mount_opt;
+	unsigned long old_compress_type = fs_info->compress_type;
+	u64 old_max_inline = fs_info->max_inline;
+	u64 old_alloc_start = fs_info->alloc_start;
+	int old_thread_pool_size = fs_info->thread_pool_size;
+	unsigned int old_metadata_ratio = fs_info->metadata_ratio;
 	int ret;
 
 	ret = btrfs_parse_options(root, data);
-	if (ret)
-		return -EINVAL;
+	if (ret) {
+		ret = -EINVAL;
+		goto restore;
+	}
 
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
@@ -1007,26 +1144,44 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	if (*flags & MS_RDONLY) {
 		sb->s_flags |= MS_RDONLY;
 
-		ret =  btrfs_commit_super(root);
-		WARN_ON(ret);
+		ret = btrfs_commit_super(root);
+		if (ret)
+			goto restore;
 	} else {
 		if (fs_info->fs_devices->rw_devices == 0)
-			return -EACCES;
+			ret = -EACCES;
+			goto restore;
 
 		if (btrfs_super_log_root(fs_info->super_copy) != 0)
-			return -EINVAL;
+			ret = -EINVAL;
+			goto restore;
 
 		ret = btrfs_cleanup_fs_roots(fs_info);
-		WARN_ON(ret);
+		if (ret)
+			goto restore;
 
 		/* recover relocation */
 		ret = btrfs_recover_relocation(root);
-		WARN_ON(ret);
+		if (ret)
+			goto restore;
 
 		sb->s_flags &= ~MS_RDONLY;
 	}
 
 	return 0;
+
+restore:
+	/* We've hit an error - don't reset MS_RDONLY */
+	if (sb->s_flags & MS_RDONLY)
+		old_flags |= MS_RDONLY;
+	sb->s_flags = old_flags;
+	fs_info->mount_opt = old_opts;
+	fs_info->compress_type = old_compress_type;
+	fs_info->max_inline = old_max_inline;
+	fs_info->alloc_start = old_alloc_start;
+	fs_info->thread_pool_size = old_thread_pool_size;
+	fs_info->metadata_ratio = old_metadata_ratio;
+	return ret;
 }
 
 /* Used to sort the devices by max_avail(descending sort) */
@@ -1356,9 +1511,7 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		return err;
 
-	err = btrfs_init_compress();
-	if (err)
-		goto free_sysfs;
+	btrfs_init_compress();
 
 	err = btrfs_init_cachep();
 	if (err)
@@ -1384,6 +1537,8 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		goto unregister_ioctl;
 
+	btrfs_init_lockdep();
+
 	printk(KERN_INFO "%s loaded\n", BTRFS_BUILD_VERSION);
 	return 0;
 
@@ -1399,7 +1554,6 @@ free_cachep:
 	btrfs_destroy_cachep();
 free_compress:
 	btrfs_exit_compress();
-free_sysfs:
 	btrfs_exit_sysfs();
 	return err;
 }
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 04b77e3ceb7a..8da29e8e4de1 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -31,7 +31,7 @@
 
 #define BTRFS_ROOT_TRANS_TAG 0
 
-static noinline void put_transaction(struct btrfs_transaction *transaction)
+void put_transaction(struct btrfs_transaction *transaction)
 {
 	WARN_ON(atomic_read(&transaction->use_count) == 0);
 	if (atomic_dec_and_test(&transaction->use_count)) {
@@ -58,6 +58,12 @@ static noinline int join_transaction(struct btrfs_root *root, int nofail)
 
 	spin_lock(&root->fs_info->trans_lock);
 loop:
+	/* The file system has been taken offline. No new transactions. */
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		spin_unlock(&root->fs_info->trans_lock);
+		return -EROFS;
+	}
+
 	if (root->fs_info->trans_no_join) {
 		if (!nofail) {
 			spin_unlock(&root->fs_info->trans_lock);
@@ -67,6 +73,8 @@ loop:
 
 	cur_trans = root->fs_info->running_transaction;
 	if (cur_trans) {
+		if (cur_trans->aborted)
+			return cur_trans->aborted;
 		atomic_inc(&cur_trans->use_count);
 		atomic_inc(&cur_trans->num_writers);
 		cur_trans->num_joined++;
@@ -123,6 +131,7 @@ loop:
 	root->fs_info->generation++;
 	cur_trans->transid = root->fs_info->generation;
 	root->fs_info->running_transaction = cur_trans;
+	cur_trans->aborted = 0;
 	spin_unlock(&root->fs_info->trans_lock);
 
 	return 0;
@@ -318,6 +327,7 @@ again:
 	h->use_count = 1;
 	h->block_rsv = NULL;
 	h->orig_rsv = NULL;
+	h->aborted = 0;
 
 	smp_mb();
 	if (cur_trans->blocked && may_wait_transaction(root, type)) {
@@ -327,8 +337,7 @@ again:
 
 	if (num_bytes) {
 		trace_btrfs_space_reservation(root->fs_info, "transaction",
-					      (u64)(unsigned long)h,
-					      num_bytes, 1);
+					      h->transid, num_bytes, 1);
 		h->block_rsv = &root->fs_info->trans_block_rsv;
 		h->bytes_reserved = num_bytes;
 	}
@@ -440,6 +449,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_block_rsv *rsv = trans->block_rsv;
 	int updates;
+	int err;
 
 	smp_mb();
 	if (cur_trans->blocked || cur_trans->delayed_refs.flushing)
@@ -453,8 +463,11 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
 
 	updates = trans->delayed_ref_updates;
 	trans->delayed_ref_updates = 0;
-	if (updates)
-		btrfs_run_delayed_refs(trans, root, updates);
+	if (updates) {
+		err = btrfs_run_delayed_refs(trans, root, updates);
+		if (err) /* Error code will also eval true */
+			return err;
+	}
 
 	trans->block_rsv = rsv;
 
@@ -525,6 +538,11 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	if (throttle)
 		btrfs_run_delayed_iputs(root);
 
+	if (trans->aborted ||
+	    root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		return -EIO;
+	}
+
 	return 0;
 }
 
@@ -690,11 +708,13 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 		ret = btrfs_update_root(trans, tree_root,
 					&root->root_key,
 					&root->root_item);
-		BUG_ON(ret);
+		if (ret)
+			return ret;
 
 		old_root_used = btrfs_root_used(&root->root_item);
 		ret = btrfs_write_dirty_block_groups(trans, root);
-		BUG_ON(ret);
+		if (ret)
+			return ret;
 	}
 
 	if (root != root->fs_info->extent_root)
@@ -705,6 +725,10 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 
 /*
  * update all the cowonly tree roots on disk
+ *
+ * The error handling in this function may not be obvious. Any of the
+ * failures will cause the file system to go offline. We still need
+ * to clean up the delayed refs.
  */
 static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
 					 struct btrfs_root *root)
@@ -715,22 +739,30 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
 	int ret;
 
 	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
-	BUG_ON(ret);
+	if (ret)
+		return ret;
 
 	eb = btrfs_lock_root_node(fs_info->tree_root);
-	btrfs_cow_block(trans, fs_info->tree_root, eb, NULL, 0, &eb);
+	ret = btrfs_cow_block(trans, fs_info->tree_root, eb, NULL,
+			      0, &eb);
 	btrfs_tree_unlock(eb);
 	free_extent_buffer(eb);
 
+	if (ret)
+		return ret;
+
 	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
-	BUG_ON(ret);
+	if (ret)
+		return ret;
 
 	while (!list_empty(&fs_info->dirty_cowonly_roots)) {
 		next = fs_info->dirty_cowonly_roots.next;
 		list_del_init(next);
 		root = list_entry(next, struct btrfs_root, dirty_list);
 
-		update_cowonly_root(trans, root);
+		ret = update_cowonly_root(trans, root);
+		if (ret)
+			return ret;
 	}
 
 	down_write(&fs_info->extent_commit_sem);
@@ -874,7 +906,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 
 	new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
 	if (!new_root_item) {
-		pending->error = -ENOMEM;
+		ret = pending->error = -ENOMEM;
 		goto fail;
 	}
 
@@ -911,21 +943,24 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	 * insert the directory item
 	 */
 	ret = btrfs_set_inode_index(parent_inode, &index);
-	BUG_ON(ret);
+	BUG_ON(ret); /* -ENOMEM */
 	ret = btrfs_insert_dir_item(trans, parent_root,
 				dentry->d_name.name, dentry->d_name.len,
 				parent_inode, &key,
 				BTRFS_FT_DIR, index);
-	if (ret) {
+	if (ret == -EEXIST) {
 		pending->error = -EEXIST;
 		dput(parent);
 		goto fail;
+	} else if (ret) {
+		goto abort_trans_dput;
 	}
 
 	btrfs_i_size_write(parent_inode, parent_inode->i_size +
 					 dentry->d_name.len * 2);
 	ret = btrfs_update_inode(trans, parent_root, parent_inode);
-	BUG_ON(ret);
+	if (ret)
+		goto abort_trans_dput;
 
 	/*
 	 * pull in the delayed directory update
@@ -934,7 +969,10 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	 * snapshot
 	 */
 	ret = btrfs_run_delayed_items(trans, root);
-	BUG_ON(ret);
+	if (ret) { /* Transaction aborted */
+		dput(parent);
+		goto fail;
+	}
 
 	record_root_in_trans(trans, root);
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
@@ -949,12 +987,21 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_set_root_flags(new_root_item, root_flags);
 
 	old = btrfs_lock_root_node(root);
-	btrfs_cow_block(trans, root, old, NULL, 0, &old);
+	ret = btrfs_cow_block(trans, root, old, NULL, 0, &old);
+	if (ret) {
+		btrfs_tree_unlock(old);
+		free_extent_buffer(old);
+		goto abort_trans_dput;
+	}
+
 	btrfs_set_lock_blocking(old);
 
-	btrfs_copy_root(trans, root, old, &tmp, objectid);
+	ret = btrfs_copy_root(trans, root, old, &tmp, objectid);
+	/* clean up in any case */
 	btrfs_tree_unlock(old);
 	free_extent_buffer(old);
+	if (ret)
+		goto abort_trans_dput;
 
 	/* see comments in should_cow_block() */
 	root->force_cow = 1;
@@ -966,7 +1013,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	ret = btrfs_insert_root(trans, tree_root, &key, new_root_item);
 	btrfs_tree_unlock(tmp);
 	free_extent_buffer(tmp);
-	BUG_ON(ret);
+	if (ret)
+		goto abort_trans_dput;
 
 	/*
 	 * insert root back/forward references
@@ -975,19 +1023,32 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 				 parent_root->root_key.objectid,
 				 btrfs_ino(parent_inode), index,
 				 dentry->d_name.name, dentry->d_name.len);
-	BUG_ON(ret);
 	dput(parent);
+	if (ret)
+		goto fail;
 
 	key.offset = (u64)-1;
 	pending->snap = btrfs_read_fs_root_no_name(root->fs_info, &key);
-	BUG_ON(IS_ERR(pending->snap));
+	if (IS_ERR(pending->snap)) {
+		ret = PTR_ERR(pending->snap);
+		goto abort_trans;
+	}
 
-	btrfs_reloc_post_snapshot(trans, pending);
+	ret = btrfs_reloc_post_snapshot(trans, pending);
+	if (ret)
+		goto abort_trans;
+	ret = 0;
 fail:
 	kfree(new_root_item);
 	trans->block_rsv = rsv;
 	btrfs_block_rsv_release(root, &pending->block_rsv, (u64)-1);
-	return 0;
+	return ret;
+
+abort_trans_dput:
+	dput(parent);
+abort_trans:
+	btrfs_abort_transaction(trans, root, ret);
+	goto fail;
 }
 
 /*
@@ -1124,6 +1185,33 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+
+static void cleanup_transaction(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root)
+{
+	struct btrfs_transaction *cur_trans = trans->transaction;
+
+	WARN_ON(trans->use_count > 1);
+
+	spin_lock(&root->fs_info->trans_lock);
+	list_del_init(&cur_trans->list);
+	spin_unlock(&root->fs_info->trans_lock);
+
+	btrfs_cleanup_one_transaction(trans->transaction, root);
+
+	put_transaction(cur_trans);
+	put_transaction(cur_trans);
+
+	trace_btrfs_transaction_commit(root);
+
+	btrfs_scrub_continue(root);
+
+	if (current->journal_info == trans)
+		current->journal_info = NULL;
+
+	kmem_cache_free(btrfs_trans_handle_cachep, trans);
+}
+
 /*
  * btrfs_transaction state sequence:
  *    in_commit = 0, blocked = 0  (initial)
@@ -1135,10 +1223,10 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root)
 {
 	unsigned long joined = 0;
-	struct btrfs_transaction *cur_trans;
+	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_transaction *prev_trans = NULL;
 	DEFINE_WAIT(wait);
-	int ret;
+	int ret = -EIO;
 	int should_grow = 0;
 	unsigned long now = get_seconds();
 	int flush_on_commit = btrfs_test_opt(root, FLUSHONCOMMIT);
@@ -1148,13 +1236,18 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	btrfs_trans_release_metadata(trans, root);
 	trans->block_rsv = NULL;
 
+	if (cur_trans->aborted)
+		goto cleanup_transaction;
+
 	/* make a pass through all the delayed refs we have so far
 	 * any runnings procs may add more while we are here
 	 */
 	ret = btrfs_run_delayed_refs(trans, root, 0);
-	BUG_ON(ret);
+	if (ret)
+		goto cleanup_transaction;
 
 	cur_trans = trans->transaction;
+
 	/*
 	 * set the flushing flag so procs in this transaction have to
 	 * start sending their work down.
@@ -1162,19 +1255,20 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	cur_trans->delayed_refs.flushing = 1;
 
 	ret = btrfs_run_delayed_refs(trans, root, 0);
-	BUG_ON(ret);
+	if (ret)
+		goto cleanup_transaction;
 
 	spin_lock(&cur_trans->commit_lock);
 	if (cur_trans->in_commit) {
 		spin_unlock(&cur_trans->commit_lock);
 		atomic_inc(&cur_trans->use_count);
-		btrfs_end_transaction(trans, root);
+		ret = btrfs_end_transaction(trans, root);
 
 		wait_for_commit(root, cur_trans);
 
 		put_transaction(cur_trans);
 
-		return 0;
+		return ret;
 	}
 
 	trans->transaction->in_commit = 1;
@@ -1214,12 +1308,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 		if (flush_on_commit || snap_pending) {
 			btrfs_start_delalloc_inodes(root, 1);
-			ret = btrfs_wait_ordered_extents(root, 0, 1);
-			BUG_ON(ret);
+			btrfs_wait_ordered_extents(root, 0, 1);
 		}
 
 		ret = btrfs_run_delayed_items(trans, root);
-		BUG_ON(ret);
+		if (ret)
+			goto cleanup_transaction;
 
 		/*
 		 * rename don't use btrfs_join_transaction, so, once we
@@ -1261,13 +1355,22 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	mutex_lock(&root->fs_info->reloc_mutex);
 
 	ret = btrfs_run_delayed_items(trans, root);
-	BUG_ON(ret);
+	if (ret) {
+		mutex_unlock(&root->fs_info->reloc_mutex);
+		goto cleanup_transaction;
+	}
 
 	ret = create_pending_snapshots(trans, root->fs_info);
-	BUG_ON(ret);
+	if (ret) {
+		mutex_unlock(&root->fs_info->reloc_mutex);
+		goto cleanup_transaction;
+	}
 
 	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
-	BUG_ON(ret);
+	if (ret) {
+		mutex_unlock(&root->fs_info->reloc_mutex);
+		goto cleanup_transaction;
+	}
 
 	/*
 	 * make sure none of the code above managed to slip in a
@@ -1294,7 +1397,10 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	mutex_lock(&root->fs_info->tree_log_mutex);
 
 	ret = commit_fs_roots(trans, root);
-	BUG_ON(ret);
+	if (ret) {
+		mutex_unlock(&root->fs_info->tree_log_mutex);
+		goto cleanup_transaction;
+	}
 
 	/* commit_fs_roots gets rid of all the tree log roots, it is now
 	 * safe to free the root of tree log roots
@@ -1302,7 +1408,10 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	btrfs_free_log_root_tree(trans, root->fs_info);
 
 	ret = commit_cowonly_roots(trans, root);
-	BUG_ON(ret);
+	if (ret) {
+		mutex_unlock(&root->fs_info->tree_log_mutex);
+		goto cleanup_transaction;
+	}
 
 	btrfs_prepare_extent_commit(trans, root);
 
@@ -1336,8 +1445,18 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	wake_up(&root->fs_info->transaction_wait);
 
 	ret = btrfs_write_and_wait_transaction(trans, root);
-	BUG_ON(ret);
-	write_ctree_super(trans, root, 0);
+	if (ret) {
+		btrfs_error(root->fs_info, ret,
+			    "Error while writing out transaction.");
+		mutex_unlock(&root->fs_info->tree_log_mutex);
+		goto cleanup_transaction;
+	}
+
+	ret = write_ctree_super(trans, root, 0);
+	if (ret) {
+		mutex_unlock(&root->fs_info->tree_log_mutex);
+		goto cleanup_transaction;
+	}
 
 	/*
 	 * the super is written, we can safely allow the tree-loggers
@@ -1373,6 +1492,15 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		btrfs_run_delayed_iputs(root);
 
 	return ret;
+
+cleanup_transaction:
+	btrfs_printk(root->fs_info, "Skipping commit of aborted transaction.\n");
+//	WARN_ON(1);
+	if (current->journal_info == trans)
+		current->journal_info = NULL;
+	cleanup_transaction(trans, root);
+
+	return ret;
 }
 
 /*
@@ -1388,6 +1516,8 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root)
 	spin_unlock(&fs_info->trans_lock);
 
 	while (!list_empty(&list)) {
+		int ret;
+
 		root = list_entry(list.next, struct btrfs_root, root_list);
 		list_del(&root->root_list);
 
@@ -1395,9 +1525,10 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root)
 
 		if (btrfs_header_backref_rev(root->node) <
 		    BTRFS_MIXED_BACKREF_REV)
-			btrfs_drop_snapshot(root, NULL, 0, 0);
+			ret = btrfs_drop_snapshot(root, NULL, 0, 0);
 		else
-			btrfs_drop_snapshot(root, NULL, 1, 0);
+			ret =btrfs_drop_snapshot(root, NULL, 1, 0);
+		BUG_ON(ret < 0);
 	}
 	return 0;
 }
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 02564e6230ac..fe27379e368b 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -43,6 +43,7 @@ struct btrfs_transaction {
 	wait_queue_head_t commit_wait;
 	struct list_head pending_snapshots;
 	struct btrfs_delayed_ref_root delayed_refs;
+	int aborted;
 };
 
 struct btrfs_trans_handle {
@@ -55,6 +56,7 @@ struct btrfs_trans_handle {
 	struct btrfs_transaction *transaction;
 	struct btrfs_block_rsv *block_rsv;
 	struct btrfs_block_rsv *orig_rsv;
+	int aborted;
 };
 
 struct btrfs_pending_snapshot {
@@ -114,4 +116,5 @@ int btrfs_wait_marked_extents(struct btrfs_root *root,
 				struct extent_io_tree *dirty_pages, int mark);
 int btrfs_transaction_blocked(struct btrfs_fs_info *info);
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
+void put_transaction(struct btrfs_transaction *transaction);
 #endif
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 966cc74f5d6c..d017283ae6f5 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -212,14 +212,13 @@ int btrfs_pin_log_trans(struct btrfs_root *root)
  * indicate we're done making changes to the log tree
  * and wake up anyone waiting to do a sync
  */
-int btrfs_end_log_trans(struct btrfs_root *root)
+void btrfs_end_log_trans(struct btrfs_root *root)
 {
 	if (atomic_dec_and_test(&root->log_writers)) {
 		smp_mb();
 		if (waitqueue_active(&root->log_writer_wait))
 			wake_up(&root->log_writer_wait);
 	}
-	return 0;
 }
 
 
@@ -378,12 +377,11 @@ insert:
 		u32 found_size;
 		found_size = btrfs_item_size_nr(path->nodes[0],
 						path->slots[0]);
-		if (found_size > item_size) {
+		if (found_size > item_size)
 			btrfs_truncate_item(trans, root, path, item_size, 1);
-		} else if (found_size < item_size) {
-			ret = btrfs_extend_item(trans, root, path,
-						item_size - found_size);
-		}
+		else if (found_size < item_size)
+			btrfs_extend_item(trans, root, path,
+					  item_size - found_size);
 	} else if (ret) {
 		return ret;
 	}
@@ -1763,7 +1761,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 					BTRFS_TREE_LOG_OBJECTID);
 				ret = btrfs_free_and_pin_reserved_extent(root,
 							 bytenr, blocksize);
-				BUG_ON(ret);
+				BUG_ON(ret); /* -ENOMEM or logic errors */
 			}
 			free_extent_buffer(next);
 			continue;
@@ -1871,20 +1869,26 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 		wret = walk_down_log_tree(trans, log, path, &level, wc);
 		if (wret > 0)
 			break;
-		if (wret < 0)
+		if (wret < 0) {
 			ret = wret;
+			goto out;
+		}
 
 		wret = walk_up_log_tree(trans, log, path, &level, wc);
 		if (wret > 0)
 			break;
-		if (wret < 0)
+		if (wret < 0) {
 			ret = wret;
+			goto out;
+		}
 	}
 
 	/* was the root node processed? if not, catch it here */
 	if (path->nodes[orig_level]) {
-		wc->process_func(log, path->nodes[orig_level], wc,
+		ret = wc->process_func(log, path->nodes[orig_level], wc,
 			 btrfs_header_generation(path->nodes[orig_level]));
+		if (ret)
+			goto out;
 		if (wc->free) {
 			struct extent_buffer *next;
 
@@ -1900,10 +1904,11 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 				BTRFS_TREE_LOG_OBJECTID);
 			ret = btrfs_free_and_pin_reserved_extent(log, next->start,
 							 next->len);
-			BUG_ON(ret);
+			BUG_ON(ret); /* -ENOMEM or logic errors */
 		}
 	}
 
+out:
 	for (i = 0; i <= orig_level; i++) {
 		if (path->nodes[i]) {
 			free_extent_buffer(path->nodes[i]);
@@ -1963,8 +1968,8 @@ static int wait_log_commit(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-static int wait_for_writer(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root)
+static void wait_for_writer(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root)
 {
 	DEFINE_WAIT(wait);
 	while (root->fs_info->last_trans_log_full_commit !=
@@ -1978,7 +1983,6 @@ static int wait_for_writer(struct btrfs_trans_handle *trans,
 		mutex_lock(&root->log_mutex);
 		finish_wait(&root->log_writer_wait, &wait);
 	}
-	return 0;
 }
 
 /*
@@ -2046,7 +2050,11 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 * wait for them until later.
 	 */
 	ret = btrfs_write_marked_extents(log, &log->dirty_log_pages, mark);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		mutex_unlock(&root->log_mutex);
+		goto out;
+	}
 
 	btrfs_set_root_node(&log->root_item, log->node);
 
@@ -2077,7 +2085,11 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	}
 
 	if (ret) {
-		BUG_ON(ret != -ENOSPC);
+		if (ret != -ENOSPC) {
+			btrfs_abort_transaction(trans, root, ret);
+			mutex_unlock(&log_root_tree->log_mutex);
+			goto out;
+		}
 		root->fs_info->last_trans_log_full_commit = trans->transid;
 		btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
 		mutex_unlock(&log_root_tree->log_mutex);
@@ -2117,7 +2129,11 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	ret = btrfs_write_and_wait_marked_extents(log_root_tree,
 				&log_root_tree->dirty_log_pages,
 				EXTENT_DIRTY | EXTENT_NEW);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		mutex_unlock(&log_root_tree->log_mutex);
+		goto out_wake_log_root;
+	}
 	btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
 
 	btrfs_set_super_log_root(root->fs_info->super_for_commit,
@@ -2326,7 +2342,9 @@ out_unlock:
 	if (ret == -ENOSPC) {
 		root->fs_info->last_trans_log_full_commit = trans->transid;
 		ret = 0;
-	}
+	} else if (ret < 0)
+		btrfs_abort_transaction(trans, root, ret);
+
 	btrfs_end_log_trans(root);
 
 	return err;
@@ -2357,7 +2375,8 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 	if (ret == -ENOSPC) {
 		root->fs_info->last_trans_log_full_commit = trans->transid;
 		ret = 0;
-	}
+	} else if (ret < 0 && ret != -ENOENT)
+		btrfs_abort_transaction(trans, root, ret);
 	btrfs_end_log_trans(root);
 
 	return ret;
@@ -3169,13 +3188,20 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
 	fs_info->log_root_recovering = 1;
 
 	trans = btrfs_start_transaction(fs_info->tree_root, 0);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto error;
+	}
 
 	wc.trans = trans;
 	wc.pin = 1;
 
 	ret = walk_log_tree(trans, log_root_tree, &wc);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_error(fs_info, ret, "Failed to pin buffers while "
+			    "recovering log root tree.");
+		goto error;
+	}
 
 again:
 	key.objectid = BTRFS_TREE_LOG_OBJECTID;
@@ -3184,8 +3210,12 @@ again:
 
 	while (1) {
 		ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0);
-		if (ret < 0)
-			break;
+
+		if (ret < 0) {
+			btrfs_error(fs_info, ret,
+				    "Couldn't find tree log root.");
+			goto error;
+		}
 		if (ret > 0) {
 			if (path->slots[0] == 0)
 				break;
@@ -3199,14 +3229,24 @@ again:
 
 		log = btrfs_read_fs_root_no_radix(log_root_tree,
 						  &found_key);
-		BUG_ON(IS_ERR(log));
+		if (IS_ERR(log)) {
+			ret = PTR_ERR(log);
+			btrfs_error(fs_info, ret,
+				    "Couldn't read tree log root.");
+			goto error;
+		}
 
 		tmp_key.objectid = found_key.offset;
 		tmp_key.type = BTRFS_ROOT_ITEM_KEY;
 		tmp_key.offset = (u64)-1;
 
 		wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key);
-		BUG_ON(IS_ERR_OR_NULL(wc.replay_dest));
+		if (IS_ERR(wc.replay_dest)) {
+			ret = PTR_ERR(wc.replay_dest);
+			btrfs_error(fs_info, ret, "Couldn't read target root "
+				    "for tree log recovery.");
+			goto error;
+		}
 
 		wc.replay_dest->log_root = log;
 		btrfs_record_root_in_trans(trans, wc.replay_dest);
@@ -3254,6 +3294,10 @@ again:
 
 	kfree(log_root_tree);
 	return 0;
+
+error:
+	btrfs_free_path(path);
+	return ret;
 }
 
 /*
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 2270ac58d746..862ac813f6b8 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -38,7 +38,7 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
 			       const char *name, int name_len,
 			       struct inode *inode, u64 dirid);
-int btrfs_end_log_trans(struct btrfs_root *root);
+void btrfs_end_log_trans(struct btrfs_root *root);
 int btrfs_pin_log_trans(struct btrfs_root *root);
 int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		    struct btrfs_root *root, struct inode *inode,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ef41f285a475..a872b48be0ae 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -67,7 +67,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
 	kfree(fs_devices);
 }
 
-int btrfs_cleanup_fs_uuids(void)
+void btrfs_cleanup_fs_uuids(void)
 {
 	struct btrfs_fs_devices *fs_devices;
 
@@ -77,7 +77,6 @@ int btrfs_cleanup_fs_uuids(void)
 		list_del(&fs_devices->list);
 		free_fs_devices(fs_devices);
 	}
-	return 0;
 }
 
 static noinline struct btrfs_device *__find_device(struct list_head *head,
@@ -130,7 +129,7 @@ static void requeue_list(struct btrfs_pending_bios *pending_bios,
  * the list if the block device is congested.  This way, multiple devices
  * can make progress from a single worker thread.
  */
-static noinline int run_scheduled_bios(struct btrfs_device *device)
+static noinline void run_scheduled_bios(struct btrfs_device *device)
 {
 	struct bio *pending;
 	struct backing_dev_info *bdi;
@@ -316,7 +315,6 @@ loop_lock:
 
 done:
 	blk_finish_plug(&plug);
-	return 0;
 }
 
 static void pending_bios_fn(struct btrfs_work *work)
@@ -455,7 +453,7 @@ error:
 	return ERR_PTR(-ENOMEM);
 }
 
-int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices)
+void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device, *next;
 
@@ -503,7 +501,6 @@ again:
 	fs_devices->latest_trans = latest_transid;
 
 	mutex_unlock(&uuid_mutex);
-	return 0;
 }
 
 static void __free_device(struct work_struct *work)
@@ -552,10 +549,10 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 			fs_devices->num_can_discard--;
 
 		new_device = kmalloc(sizeof(*new_device), GFP_NOFS);
-		BUG_ON(!new_device);
+		BUG_ON(!new_device); /* -ENOMEM */
 		memcpy(new_device, device, sizeof(*new_device));
 		new_device->name = kstrdup(device->name, GFP_NOFS);
-		BUG_ON(device->name && !new_device->name);
+		BUG_ON(device->name && !new_device->name); /* -ENOMEM */
 		new_device->bdev = NULL;
 		new_device->writeable = 0;
 		new_device->in_fs_metadata = 0;
@@ -625,6 +622,8 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 			printk(KERN_INFO "open %s failed\n", device->name);
 			goto error;
 		}
+		filemap_write_and_wait(bdev->bd_inode->i_mapping);
+		invalidate_bdev(bdev);
 		set_blocksize(bdev, 4096);
 
 		bh = btrfs_read_dev_super(bdev);
@@ -1039,8 +1038,10 @@ again:
 		leaf = path->nodes[0];
 		extent = btrfs_item_ptr(leaf, path->slots[0],
 					struct btrfs_dev_extent);
+	} else {
+		btrfs_error(root->fs_info, ret, "Slot search failed");
+		goto out;
 	}
-	BUG_ON(ret);
 
 	if (device->bytes_used > 0) {
 		u64 len = btrfs_dev_extent_length(leaf, extent);
@@ -1050,7 +1051,10 @@ again:
 		spin_unlock(&root->fs_info->free_chunk_lock);
 	}
 	ret = btrfs_del_item(trans, root, path);
-
+	if (ret) {
+		btrfs_error(root->fs_info, ret,
+			    "Failed to remove dev extent item");
+	}
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -1078,7 +1082,8 @@ int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_DEV_EXTENT_KEY;
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
 				      sizeof(*extent));
-	BUG_ON(ret);
+	if (ret)
+		goto out;
 
 	leaf = path->nodes[0];
 	extent = btrfs_item_ptr(leaf, path->slots[0],
@@ -1093,6 +1098,7 @@ int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans,
 
 	btrfs_set_dev_extent_length(leaf, extent, num_bytes);
 	btrfs_mark_buffer_dirty(leaf);
+out:
 	btrfs_free_path(path);
 	return ret;
 }
@@ -1118,7 +1124,7 @@ static noinline int find_next_chunk(struct btrfs_root *root,
 	if (ret < 0)
 		goto error;
 
-	BUG_ON(ret == 0);
+	BUG_ON(ret == 0); /* Corruption */
 
 	ret = btrfs_previous_item(root, path, 0, BTRFS_CHUNK_ITEM_KEY);
 	if (ret) {
@@ -1162,7 +1168,7 @@ static noinline int find_next_devid(struct btrfs_root *root, u64 *objectid)
 	if (ret < 0)
 		goto error;
 
-	BUG_ON(ret == 0);
+	BUG_ON(ret == 0); /* Corruption */
 
 	ret = btrfs_previous_item(root, path, BTRFS_DEV_ITEMS_OBJECTID,
 				  BTRFS_DEV_ITEM_KEY);
@@ -1350,6 +1356,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		}
 
 		set_blocksize(bdev, 4096);
+		invalidate_bdev(bdev);
 		bh = btrfs_read_dev_super(bdev);
 		if (!bh) {
 			ret = -EINVAL;
@@ -1596,7 +1603,7 @@ next_slot:
 				   (unsigned long)btrfs_device_fsid(dev_item),
 				   BTRFS_UUID_SIZE);
 		device = btrfs_find_device(root, devid, dev_uuid, fs_uuid);
-		BUG_ON(!device);
+		BUG_ON(!device); /* Logic error */
 
 		if (device->fs_devices->seeding) {
 			btrfs_set_device_generation(leaf, dev_item,
@@ -1706,7 +1713,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	if (seeding_dev) {
 		sb->s_flags &= ~MS_RDONLY;
 		ret = btrfs_prepare_sprout(root);
-		BUG_ON(ret);
+		BUG_ON(ret); /* -ENOMEM */
 	}
 
 	device->fs_devices = root->fs_info->fs_devices;
@@ -1744,11 +1751,15 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 
 	if (seeding_dev) {
 		ret = init_first_rw_device(trans, root, device);
-		BUG_ON(ret);
+		if (ret)
+			goto error_trans;
 		ret = btrfs_finish_sprout(trans, root);
-		BUG_ON(ret);
+		if (ret)
+			goto error_trans;
 	} else {
 		ret = btrfs_add_device(trans, root, device);
+		if (ret)
+			goto error_trans;
 	}
 
 	/*
@@ -1758,17 +1769,31 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	btrfs_clear_space_info_full(root->fs_info);
 
 	unlock_chunks(root);
-	btrfs_commit_transaction(trans, root);
+	ret = btrfs_commit_transaction(trans, root);
 
 	if (seeding_dev) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
 
+		if (ret) /* transaction commit */
+			return ret;
+
 		ret = btrfs_relocate_sys_chunks(root);
-		BUG_ON(ret);
+		if (ret < 0)
+			btrfs_error(root->fs_info, ret,
+				    "Failed to relocate sys chunks after "
+				    "device initialization. This can be fixed "
+				    "using the \"btrfs balance\" command.");
 	}
 
 	return ret;
+
+error_trans:
+	unlock_chunks(root);
+	btrfs_abort_transaction(trans, root, ret);
+	btrfs_end_transaction(trans, root);
+	kfree(device->name);
+	kfree(device);
 error:
 	blkdev_put(bdev, FMODE_EXCL);
 	if (seeding_dev) {
@@ -1876,10 +1901,20 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_CHUNK_ITEM_KEY;
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-	BUG_ON(ret);
+	if (ret < 0)
+		goto out;
+	else if (ret > 0) { /* Logic error or corruption */
+		btrfs_error(root->fs_info, -ENOENT,
+			    "Failed lookup while freeing chunk.");
+		ret = -ENOENT;
+		goto out;
+	}
 
 	ret = btrfs_del_item(trans, root, path);
-
+	if (ret < 0)
+		btrfs_error(root->fs_info, ret,
+			    "Failed to delete chunk item.");
+out:
 	btrfs_free_path(path);
 	return ret;
 }
@@ -2041,7 +2076,7 @@ again:
 		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
 		if (ret < 0)
 			goto error;
-		BUG_ON(ret == 0);
+		BUG_ON(ret == 0); /* Corruption */
 
 		ret = btrfs_previous_item(chunk_root, path, key.objectid,
 					  key.type);
@@ -2250,15 +2285,13 @@ static void unset_balance_control(struct btrfs_fs_info *fs_info)
  * Balance filters.  Return 1 if chunk should be filtered out
  * (should not be balanced).
  */
-static int chunk_profiles_filter(u64 chunk_profile,
+static int chunk_profiles_filter(u64 chunk_type,
 				 struct btrfs_balance_args *bargs)
 {
-	chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
-
-	if (chunk_profile == 0)
-		chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+	chunk_type = chunk_to_extended(chunk_type) &
+				BTRFS_EXTENDED_PROFILE_MASK;
 
-	if (bargs->profiles & chunk_profile)
+	if (bargs->profiles & chunk_type)
 		return 0;
 
 	return 1;
@@ -2365,18 +2398,16 @@ static int chunk_vrange_filter(struct extent_buffer *leaf,
 	return 1;
 }
 
-static int chunk_soft_convert_filter(u64 chunk_profile,
+static int chunk_soft_convert_filter(u64 chunk_type,
 				     struct btrfs_balance_args *bargs)
 {
 	if (!(bargs->flags & BTRFS_BALANCE_ARGS_CONVERT))
 		return 0;
 
-	chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
+	chunk_type = chunk_to_extended(chunk_type) &
+				BTRFS_EXTENDED_PROFILE_MASK;
 
-	if (chunk_profile == 0)
-		chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-
-	if (bargs->target & chunk_profile)
+	if (bargs->target == chunk_type)
 		return 1;
 
 	return 0;
@@ -2602,6 +2633,30 @@ error:
 	return ret;
 }
 
+/**
+ * alloc_profile_is_valid - see if a given profile is valid and reduced
+ * @flags: profile to validate
+ * @extended: if true @flags is treated as an extended profile
+ */
+static int alloc_profile_is_valid(u64 flags, int extended)
+{
+	u64 mask = (extended ? BTRFS_EXTENDED_PROFILE_MASK :
+			       BTRFS_BLOCK_GROUP_PROFILE_MASK);
+
+	flags &= ~BTRFS_BLOCK_GROUP_TYPE_MASK;
+
+	/* 1) check that all other bits are zeroed */
+	if (flags & ~mask)
+		return 0;
+
+	/* 2) see if profile is reduced */
+	if (flags == 0)
+		return !extended; /* "0" is valid for usual profiles */
+
+	/* true if exactly one bit set */
+	return (flags & (flags - 1)) == 0;
+}
+
 static inline int balance_need_close(struct btrfs_fs_info *fs_info)
 {
 	/* cancel requested || normal exit path */
@@ -2630,6 +2685,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 {
 	struct btrfs_fs_info *fs_info = bctl->fs_info;
 	u64 allowed;
+	int mixed = 0;
 	int ret;
 
 	if (btrfs_fs_closing(fs_info) ||
@@ -2639,13 +2695,16 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		goto out;
 	}
 
+	allowed = btrfs_super_incompat_flags(fs_info->super_copy);
+	if (allowed & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+		mixed = 1;
+
 	/*
 	 * In case of mixed groups both data and meta should be picked,
 	 * and identical options should be given for both of them.
 	 */
-	allowed = btrfs_super_incompat_flags(fs_info->super_copy);
-	if ((allowed & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
-	    (bctl->flags & (BTRFS_BALANCE_DATA | BTRFS_BALANCE_METADATA))) {
+	allowed = BTRFS_BALANCE_DATA | BTRFS_BALANCE_METADATA;
+	if (mixed && (bctl->flags & allowed)) {
 		if (!(bctl->flags & BTRFS_BALANCE_DATA) ||
 		    !(bctl->flags & BTRFS_BALANCE_METADATA) ||
 		    memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) {
@@ -2656,14 +2715,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		}
 	}
 
-	/*
-	 * Profile changing sanity checks.  Skip them if a simple
-	 * balance is requested.
-	 */
-	if (!((bctl->data.flags | bctl->sys.flags | bctl->meta.flags) &
-	      BTRFS_BALANCE_ARGS_CONVERT))
-		goto do_balance;
-
 	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
 	if (fs_info->fs_devices->num_devices == 1)
 		allowed |= BTRFS_BLOCK_GROUP_DUP;
@@ -2673,24 +2724,27 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
 				BTRFS_BLOCK_GROUP_RAID10);
 
-	if (!profile_is_valid(bctl->data.target, 1) ||
-	    bctl->data.target & ~allowed) {
+	if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+	    (!alloc_profile_is_valid(bctl->data.target, 1) ||
+	     (bctl->data.target & ~allowed))) {
 		printk(KERN_ERR "btrfs: unable to start balance with target "
 		       "data profile %llu\n",
 		       (unsigned long long)bctl->data.target);
 		ret = -EINVAL;
 		goto out;
 	}
-	if (!profile_is_valid(bctl->meta.target, 1) ||
-	    bctl->meta.target & ~allowed) {
+	if ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+	    (!alloc_profile_is_valid(bctl->meta.target, 1) ||
+	     (bctl->meta.target & ~allowed))) {
 		printk(KERN_ERR "btrfs: unable to start balance with target "
 		       "metadata profile %llu\n",
 		       (unsigned long long)bctl->meta.target);
 		ret = -EINVAL;
 		goto out;
 	}
-	if (!profile_is_valid(bctl->sys.target, 1) ||
-	    bctl->sys.target & ~allowed) {
+	if ((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+	    (!alloc_profile_is_valid(bctl->sys.target, 1) ||
+	     (bctl->sys.target & ~allowed))) {
 		printk(KERN_ERR "btrfs: unable to start balance with target "
 		       "system profile %llu\n",
 		       (unsigned long long)bctl->sys.target);
@@ -2698,7 +2752,9 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		goto out;
 	}
 
-	if (bctl->data.target & BTRFS_BLOCK_GROUP_DUP) {
+	/* allow dup'ed data chunks only in mixed mode */
+	if (!mixed && (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+	    (bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) {
 		printk(KERN_ERR "btrfs: dup for data is not allowed\n");
 		ret = -EINVAL;
 		goto out;
@@ -2724,7 +2780,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		}
 	}
 
-do_balance:
 	ret = insert_balance_item(fs_info->tree_root, bctl);
 	if (ret && ret != -EEXIST)
 		goto out;
@@ -2967,7 +3022,7 @@ again:
 	key.offset = (u64)-1;
 	key.type = BTRFS_DEV_EXTENT_KEY;
 
-	while (1) {
+	do {
 		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 		if (ret < 0)
 			goto done;
@@ -3009,8 +3064,7 @@ again:
 			goto done;
 		if (ret == -ENOSPC)
 			failed++;
-		key.offset -= 1;
-	}
+	} while (key.offset-- > 0);
 
 	if (failed && !retried) {
 		failed = 0;
@@ -3128,11 +3182,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	int i;
 	int j;
 
-	if ((type & BTRFS_BLOCK_GROUP_RAID1) &&
-	    (type & BTRFS_BLOCK_GROUP_DUP)) {
-		WARN_ON(1);
-		type &= ~BTRFS_BLOCK_GROUP_DUP;
-	}
+	BUG_ON(!alloc_profile_is_valid(type, 0));
 
 	if (list_empty(&fs_devices->alloc_list))
 		return -ENOSPC;
@@ -3328,13 +3378,15 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	write_lock(&em_tree->lock);
 	ret = add_extent_mapping(em_tree, em);
 	write_unlock(&em_tree->lock);
-	BUG_ON(ret);
 	free_extent_map(em);
+	if (ret)
+		goto error;
 
 	ret = btrfs_make_block_group(trans, extent_root, 0, type,
 				     BTRFS_FIRST_CHUNK_TREE_OBJECTID,
 				     start, num_bytes);
-	BUG_ON(ret);
+	if (ret)
+		goto error;
 
 	for (i = 0; i < map->num_stripes; ++i) {
 		struct btrfs_device *device;
@@ -3347,7 +3399,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 				info->chunk_root->root_key.objectid,
 				BTRFS_FIRST_CHUNK_TREE_OBJECTID,
 				start, dev_offset, stripe_size);
-		BUG_ON(ret);
+		if (ret) {
+			btrfs_abort_transaction(trans, extent_root, ret);
+			goto error;
+		}
 	}
 
 	kfree(devices_info);
@@ -3383,7 +3438,8 @@ static int __finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		device = map->stripes[index].dev;
 		device->bytes_used += stripe_size;
 		ret = btrfs_update_device(trans, device);
-		BUG_ON(ret);
+		if (ret)
+			goto out_free;
 		index++;
 	}
 
@@ -3420,16 +3476,19 @@ static int __finish_chunk_alloc(struct btrfs_trans_handle *trans,
 	key.offset = chunk_offset;
 
 	ret = btrfs_insert_item(trans, chunk_root, &key, chunk, item_size);
-	BUG_ON(ret);
 
-	if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
+	if (ret == 0 && map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
+		/*
+		 * TODO: Cleanup of inserted chunk root in case of
+		 * failure.
+		 */
 		ret = btrfs_add_system_chunk(chunk_root, &key, chunk,
 					     item_size);
-		BUG_ON(ret);
 	}
 
+out_free:
 	kfree(chunk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -3461,7 +3520,8 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	ret = __finish_chunk_alloc(trans, extent_root, map, chunk_offset,
 				   chunk_size, stripe_size);
-	BUG_ON(ret);
+	if (ret)
+		return ret;
 	return 0;
 }
 
@@ -3493,7 +3553,8 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
 
 	ret = __btrfs_alloc_chunk(trans, extent_root, &map, &chunk_size,
 				  &stripe_size, chunk_offset, alloc_profile);
-	BUG_ON(ret);
+	if (ret)
+		return ret;
 
 	sys_chunk_offset = chunk_offset + chunk_size;
 
@@ -3504,10 +3565,12 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
 	ret = __btrfs_alloc_chunk(trans, extent_root, &sys_map,
 				  &sys_chunk_size, &sys_stripe_size,
 				  sys_chunk_offset, alloc_profile);
-	BUG_ON(ret);
+	if (ret)
+		goto abort;
 
 	ret = btrfs_add_device(trans, fs_info->chunk_root, device);
-	BUG_ON(ret);
+	if (ret)
+		goto abort;
 
 	/*
 	 * Modifying chunk tree needs allocating new blocks from both
@@ -3517,13 +3580,20 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
 	 */
 	ret = __finish_chunk_alloc(trans, extent_root, map, chunk_offset,
 				   chunk_size, stripe_size);
-	BUG_ON(ret);
+	if (ret)
+		goto abort;
 
 	ret = __finish_chunk_alloc(trans, extent_root, sys_map,
 				   sys_chunk_offset, sys_chunk_size,
 				   sys_stripe_size);
-	BUG_ON(ret);
+	if (ret)
+		goto abort;
+
 	return 0;
+
+abort:
+	btrfs_abort_transaction(trans, root, ret);
+	return ret;
 }
 
 int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
@@ -3874,7 +3944,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 		do_div(length, map->num_stripes);
 
 	buf = kzalloc(sizeof(u64) * map->num_stripes, GFP_NOFS);
-	BUG_ON(!buf);
+	BUG_ON(!buf); /* -ENOMEM */
 
 	for (i = 0; i < map->num_stripes; i++) {
 		if (devid && map->stripes[i].dev->devid != devid)
@@ -3967,7 +4037,7 @@ struct async_sched {
  * This will add one bio to the pending list for a device and make sure
  * the work struct is scheduled.
  */
-static noinline int schedule_bio(struct btrfs_root *root,
+static noinline void schedule_bio(struct btrfs_root *root,
 				 struct btrfs_device *device,
 				 int rw, struct bio *bio)
 {
@@ -3979,7 +4049,7 @@ static noinline int schedule_bio(struct btrfs_root *root,
 		bio_get(bio);
 		btrfsic_submit_bio(rw, bio);
 		bio_put(bio);
-		return 0;
+		return;
 	}
 
 	/*
@@ -4013,7 +4083,6 @@ static noinline int schedule_bio(struct btrfs_root *root,
 	if (should_queue)
 		btrfs_queue_worker(&root->fs_info->submit_workers,
 				   &device->work);
-	return 0;
 }
 
 int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
@@ -4036,7 +4105,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 
 	ret = btrfs_map_block(map_tree, rw, logical, &map_length, &bbio,
 			      mirror_num);
-	BUG_ON(ret);
+	if (ret) /* -ENOMEM */
+		return ret;
 
 	total_devs = bbio->num_stripes;
 	if (map_length < length) {
@@ -4055,7 +4125,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 	while (dev_nr < total_devs) {
 		if (dev_nr < total_devs - 1) {
 			bio = bio_clone(first_bio, GFP_NOFS);
-			BUG_ON(!bio);
+			BUG_ON(!bio); /* -ENOMEM */
 		} else {
 			bio = first_bio;
 		}
@@ -4209,13 +4279,13 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	write_lock(&map_tree->map_tree.lock);
 	ret = add_extent_mapping(&map_tree->map_tree, em);
 	write_unlock(&map_tree->map_tree.lock);
-	BUG_ON(ret);
+	BUG_ON(ret); /* Tree corruption */
 	free_extent_map(em);
 
 	return 0;
 }
 
-static int fill_device_from_item(struct extent_buffer *leaf,
+static void fill_device_from_item(struct extent_buffer *leaf,
 				 struct btrfs_dev_item *dev_item,
 				 struct btrfs_device *device)
 {
@@ -4232,8 +4302,6 @@ static int fill_device_from_item(struct extent_buffer *leaf,
 
 	ptr = (unsigned long)btrfs_device_uuid(dev_item);
 	read_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
-
-	return 0;
 }
 
 static int open_seed_devices(struct btrfs_root *root, u8 *fsid)
@@ -4384,7 +4452,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	 * to silence the warning eg. on PowerPC 64.
 	 */
 	if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE)
-		SetPageUptodate(sb->first_page);
+		SetPageUptodate(sb->pages[0]);
 
 	write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
 	array_size = btrfs_super_sys_array_size(super_copy);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 19ac95048b88..bb6b03f97aaa 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -260,12 +260,12 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 			  struct btrfs_fs_devices **fs_devices_ret);
 int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
-int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices);
+void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices);
 int btrfs_add_device(struct btrfs_trans_handle *trans,
 		     struct btrfs_root *root,
 		     struct btrfs_device *device);
 int btrfs_rm_device(struct btrfs_root *root, char *device_path);
-int btrfs_cleanup_fs_uuids(void);
+void btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_mapping_tree *map_tree, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
 		      struct btrfs_device *device, u64 new_size);
diff --git a/fs/buffer.c b/fs/buffer.c
index 70e2017edd70..36d66653b931 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1384,10 +1384,23 @@ static void invalidate_bh_lru(void *arg)
 	}
 	put_cpu_var(bh_lrus);
 }
+
+static bool has_bh_in_lru(int cpu, void *dummy)
+{
+	struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
+	int i;
 	
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		if (b->bhs[i])
+			return 1;
+	}
+
+	return 0;
+}
+
 void invalidate_bh_lrus(void)
 {
-	on_each_cpu(invalidate_bh_lru, NULL, 1);
+	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2c489378b4cd..9fff9f3b17e4 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -677,18 +677,19 @@ static int fill_inode(struct inode *inode,
 	case S_IFLNK:
 		inode->i_op = &ceph_symlink_iops;
 		if (!ci->i_symlink) {
-			int symlen = iinfo->symlink_len;
+			u32 symlen = iinfo->symlink_len;
 			char *sym;
 
-			BUG_ON(symlen != inode->i_size);
 			spin_unlock(&ci->i_ceph_lock);
 
+			err = -EINVAL;
+			if (WARN_ON(symlen != inode->i_size))
+				goto out;
+
 			err = -ENOMEM;
-			sym = kmalloc(symlen+1, GFP_NOFS);
+			sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
 			if (!sym)
 				goto out;
-			memcpy(sym, iinfo->symlink, symlen);
-			sym[symlen] = 0;
 
 			spin_lock(&ci->i_ceph_lock);
 			if (!ci->i_symlink)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 866e8d7ca37d..89971e137aab 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -402,7 +402,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 
 	spin_lock_init(&s->s_gen_ttl_lock);
 	s->s_cap_gen = 0;
-	s->s_cap_ttl = 0;
+	s->s_cap_ttl = jiffies - 1;
 
 	spin_lock_init(&s->s_cap_lock);
 	s->s_renew_requested = 0;
@@ -1083,8 +1083,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc,
 	int wake = 0;
 
 	spin_lock(&session->s_cap_lock);
-	was_stale = is_renew && (session->s_cap_ttl == 0 ||
-				 time_after_eq(jiffies, session->s_cap_ttl));
+	was_stale = is_renew && time_after_eq(jiffies, session->s_cap_ttl);
 
 	session->s_cap_ttl = session->s_renew_requested +
 		mdsc->mdsmap->m_session_timeout*HZ;
@@ -2332,7 +2331,7 @@ static void handle_session(struct ceph_mds_session *session,
 			session->s_mds);
 		spin_lock(&session->s_gen_ttl_lock);
 		session->s_cap_gen++;
-		session->s_cap_ttl = 0;
+		session->s_cap_ttl = jiffies - 1;
 		spin_unlock(&session->s_gen_ttl_lock);
 		send_renew_caps(mdsc, session);
 		break;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index a559c80f127a..f04c0961f993 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -331,7 +331,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 
 	/* alloc new snap context */
 	err = -ENOMEM;
-	if (num > ULONG_MAX / sizeof(u64) - sizeof(*snapc))
+	if (num > (ULONG_MAX - sizeof(*snapc)) / sizeof(u64))
 		goto fail;
 	snapc = kzalloc(sizeof(*snapc) + num*sizeof(u64), GFP_NOFS);
 	if (!snapc)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 256f85221926..1e67dd7305a4 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -130,10 +130,12 @@ enum {
 	Opt_nodirstat,
 	Opt_rbytes,
 	Opt_norbytes,
+	Opt_asyncreaddir,
 	Opt_noasyncreaddir,
 	Opt_dcache,
 	Opt_nodcache,
 	Opt_ino32,
+	Opt_noino32,
 };
 
 static match_table_t fsopt_tokens = {
@@ -153,10 +155,12 @@ static match_table_t fsopt_tokens = {
 	{Opt_nodirstat, "nodirstat"},
 	{Opt_rbytes, "rbytes"},
 	{Opt_norbytes, "norbytes"},
+	{Opt_asyncreaddir, "asyncreaddir"},
 	{Opt_noasyncreaddir, "noasyncreaddir"},
 	{Opt_dcache, "dcache"},
 	{Opt_nodcache, "nodcache"},
 	{Opt_ino32, "ino32"},
+	{Opt_noino32, "noino32"},
 	{-1, NULL}
 };
 
@@ -232,6 +236,9 @@ static int parse_fsopt_token(char *c, void *private)
 	case Opt_norbytes:
 		fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
 		break;
+	case Opt_asyncreaddir:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR;
+		break;
 	case Opt_noasyncreaddir:
 		fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
 		break;
@@ -244,6 +251,9 @@ static int parse_fsopt_token(char *c, void *private)
 	case Opt_ino32:
 		fsopt->flags |= CEPH_MOUNT_OPT_INO32;
 		break;
+	case Opt_noino32:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
+		break;
 	default:
 		BUG_ON(token);
 	}
@@ -334,10 +344,12 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 	*path += 2;
 	dout("server path '%s'\n", *path);
 
-	err = ceph_parse_options(popt, options, dev_name, dev_name_end,
+	*popt = ceph_parse_options(options, dev_name, dev_name_end,
 				 parse_fsopt_token, (void *)fsopt);
-	if (err)
+	if (IS_ERR(*popt)) {
+		err = PTR_ERR(*popt);
 		goto out;
+	}
 
 	/* success */
 	*pfsopt = fsopt;
@@ -926,6 +938,7 @@ static int __init init_ceph(void)
 	if (ret)
 		goto out;
 
+	ceph_xattr_init();
 	ret = register_filesystem(&ceph_fs_type);
 	if (ret)
 		goto out_icache;
@@ -935,6 +948,7 @@ static int __init init_ceph(void)
 	return 0;
 
 out_icache:
+	ceph_xattr_exit();
 	destroy_caches();
 out:
 	return ret;
@@ -944,6 +958,7 @@ static void __exit exit_ceph(void)
 {
 	dout("exit_ceph\n");
 	unregister_filesystem(&ceph_fs_type);
+	ceph_xattr_exit();
 	destroy_caches();
 }
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1421f3d875a2..fc35036d258d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -367,7 +367,7 @@ static inline u32 ceph_ino_to_ino32(__u64 vino)
 	u32 ino = vino & 0xffffffff;
 	ino ^= vino >> 32;
 	if (!ino)
-		ino = 1;
+		ino = 2;
 	return ino;
 }
 
@@ -733,6 +733,8 @@ extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
 extern int ceph_removexattr(struct dentry *, const char *);
 extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
 extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
+extern void __init ceph_xattr_init(void);
+extern void ceph_xattr_exit(void);
 
 /* caps.c */
 extern const char *ceph_cap_string(int c);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index a76f697303d9..35b86331d8a5 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -8,9 +8,12 @@
 #include <linux/xattr.h>
 #include <linux/slab.h>
 
+#define XATTR_CEPH_PREFIX "ceph."
+#define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
+
 static bool ceph_is_valid_xattr(const char *name)
 {
-	return !strncmp(name, "ceph.", 5) ||
+	return !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) ||
 	       !strncmp(name, XATTR_SECURITY_PREFIX,
 			XATTR_SECURITY_PREFIX_LEN) ||
 	       !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
@@ -21,79 +24,91 @@ static bool ceph_is_valid_xattr(const char *name)
  * These define virtual xattrs exposing the recursive directory
  * statistics and layout metadata.
  */
-struct ceph_vxattr_cb {
-	bool readonly;
+struct ceph_vxattr {
 	char *name;
+	size_t name_size;	/* strlen(name) + 1 (for '\0') */
 	size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
 			      size_t size);
+	bool readonly;
 };
 
 /* directories */
 
-static size_t ceph_vxattrcb_entries(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
 					size_t size)
 {
 	return snprintf(val, size, "%lld", ci->i_files + ci->i_subdirs);
 }
 
-static size_t ceph_vxattrcb_files(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_files(struct ceph_inode_info *ci, char *val,
 				      size_t size)
 {
 	return snprintf(val, size, "%lld", ci->i_files);
 }
 
-static size_t ceph_vxattrcb_subdirs(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_subdirs(struct ceph_inode_info *ci, char *val,
 					size_t size)
 {
 	return snprintf(val, size, "%lld", ci->i_subdirs);
 }
 
-static size_t ceph_vxattrcb_rentries(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rentries(struct ceph_inode_info *ci, char *val,
 					 size_t size)
 {
 	return snprintf(val, size, "%lld", ci->i_rfiles + ci->i_rsubdirs);
 }
 
-static size_t ceph_vxattrcb_rfiles(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rfiles(struct ceph_inode_info *ci, char *val,
 				       size_t size)
 {
 	return snprintf(val, size, "%lld", ci->i_rfiles);
 }
 
-static size_t ceph_vxattrcb_rsubdirs(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rsubdirs(struct ceph_inode_info *ci, char *val,
 					 size_t size)
 {
 	return snprintf(val, size, "%lld", ci->i_rsubdirs);
 }
 
-static size_t ceph_vxattrcb_rbytes(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rbytes(struct ceph_inode_info *ci, char *val,
 				       size_t size)
 {
 	return snprintf(val, size, "%lld", ci->i_rbytes);
 }
 
-static size_t ceph_vxattrcb_rctime(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
 				       size_t size)
 {
-	return snprintf(val, size, "%ld.%ld", (long)ci->i_rctime.tv_sec,
+	return snprintf(val, size, "%ld.09%ld", (long)ci->i_rctime.tv_sec,
 			(long)ci->i_rctime.tv_nsec);
 }
 
-static struct ceph_vxattr_cb ceph_dir_vxattrs[] = {
-	{ true, "ceph.dir.entries", ceph_vxattrcb_entries},
-	{ true, "ceph.dir.files", ceph_vxattrcb_files},
-	{ true, "ceph.dir.subdirs", ceph_vxattrcb_subdirs},
-	{ true, "ceph.dir.rentries", ceph_vxattrcb_rentries},
-	{ true, "ceph.dir.rfiles", ceph_vxattrcb_rfiles},
-	{ true, "ceph.dir.rsubdirs", ceph_vxattrcb_rsubdirs},
-	{ true, "ceph.dir.rbytes", ceph_vxattrcb_rbytes},
-	{ true, "ceph.dir.rctime", ceph_vxattrcb_rctime},
-	{ true, NULL, NULL }
+#define CEPH_XATTR_NAME(_type, _name)	XATTR_CEPH_PREFIX #_type "." #_name
+
+#define XATTR_NAME_CEPH(_type, _name) \
+		{ \
+			.name = CEPH_XATTR_NAME(_type, _name), \
+			.name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
+			.getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
+			.readonly = true, \
+		}
+
+static struct ceph_vxattr ceph_dir_vxattrs[] = {
+	XATTR_NAME_CEPH(dir, entries),
+	XATTR_NAME_CEPH(dir, files),
+	XATTR_NAME_CEPH(dir, subdirs),
+	XATTR_NAME_CEPH(dir, rentries),
+	XATTR_NAME_CEPH(dir, rfiles),
+	XATTR_NAME_CEPH(dir, rsubdirs),
+	XATTR_NAME_CEPH(dir, rbytes),
+	XATTR_NAME_CEPH(dir, rctime),
+	{ 0 }	/* Required table terminator */
 };
+static size_t ceph_dir_vxattrs_name_size;	/* total size of all names */
 
 /* files */
 
-static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val,
 				   size_t size)
 {
 	int ret;
@@ -103,21 +118,32 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 		(unsigned long long)ceph_file_layout_su(ci->i_layout),
 		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
 		(unsigned long long)ceph_file_layout_object_size(ci->i_layout));
-	if (ceph_file_layout_pg_preferred(ci->i_layout))
-		ret += snprintf(val + ret, size, "preferred_osd=%lld\n",
+
+	if (ceph_file_layout_pg_preferred(ci->i_layout) >= 0) {
+		val += ret;
+		size -= ret;
+		ret += snprintf(val, size, "preferred_osd=%lld\n",
 			    (unsigned long long)ceph_file_layout_pg_preferred(
 				    ci->i_layout));
+	}
+
 	return ret;
 }
 
-static struct ceph_vxattr_cb ceph_file_vxattrs[] = {
-	{ true, "ceph.file.layout", ceph_vxattrcb_layout},
+static struct ceph_vxattr ceph_file_vxattrs[] = {
+	XATTR_NAME_CEPH(file, layout),
 	/* The following extended attribute name is deprecated */
-	{ true, "ceph.layout", ceph_vxattrcb_layout},
-	{ true, NULL, NULL }
+	{
+		.name = XATTR_CEPH_PREFIX "layout",
+		.name_size = sizeof (XATTR_CEPH_PREFIX "layout"),
+		.getxattr_cb = ceph_vxattrcb_file_layout,
+		.readonly = true,
+	},
+	{ 0 }	/* Required table terminator */
 };
+static size_t ceph_file_vxattrs_name_size;	/* total size of all names */
 
-static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
+static struct ceph_vxattr *ceph_inode_vxattrs(struct inode *inode)
 {
 	if (S_ISDIR(inode->i_mode))
 		return ceph_dir_vxattrs;
@@ -126,14 +152,59 @@ static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
 	return NULL;
 }
 
-static struct ceph_vxattr_cb *ceph_match_vxattr(struct ceph_vxattr_cb *vxattr,
+static size_t ceph_vxattrs_name_size(struct ceph_vxattr *vxattrs)
+{
+	if (vxattrs == ceph_dir_vxattrs)
+		return ceph_dir_vxattrs_name_size;
+	if (vxattrs == ceph_file_vxattrs)
+		return ceph_file_vxattrs_name_size;
+	BUG();
+
+	return 0;
+}
+
+/*
+ * Compute the aggregate size (including terminating '\0') of all
+ * virtual extended attribute names in the given vxattr table.
+ */
+static size_t __init vxattrs_name_size(struct ceph_vxattr *vxattrs)
+{
+	struct ceph_vxattr *vxattr;
+	size_t size = 0;
+
+	for (vxattr = vxattrs; vxattr->name; vxattr++)
+		size += vxattr->name_size;
+
+	return size;
+}
+
+/* Routines called at initialization and exit time */
+
+void __init ceph_xattr_init(void)
+{
+	ceph_dir_vxattrs_name_size = vxattrs_name_size(ceph_dir_vxattrs);
+	ceph_file_vxattrs_name_size = vxattrs_name_size(ceph_file_vxattrs);
+}
+
+void ceph_xattr_exit(void)
+{
+	ceph_dir_vxattrs_name_size = 0;
+	ceph_file_vxattrs_name_size = 0;
+}
+
+static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode,
 						const char *name)
 {
-	do {
-		if (strcmp(vxattr->name, name) == 0)
-			return vxattr;
-		vxattr++;
-	} while (vxattr->name);
+	struct ceph_vxattr *vxattr = ceph_inode_vxattrs(inode);
+
+	if (vxattr) {
+		while (vxattr->name) {
+			if (!strcmp(vxattr->name, name))
+				return vxattr;
+			vxattr++;
+		}
+	}
+
 	return NULL;
 }
 
@@ -502,17 +573,15 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
 {
 	struct inode *inode = dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
 	int err;
 	struct ceph_inode_xattr *xattr;
-	struct ceph_vxattr_cb *vxattr = NULL;
+	struct ceph_vxattr *vxattr = NULL;
 
 	if (!ceph_is_valid_xattr(name))
 		return -ENODATA;
 
 	/* let's see if a virtual xattr was requested */
-	if (vxattrs)
-		vxattr = ceph_match_vxattr(vxattrs, name);
+	vxattr = ceph_match_vxattr(inode, name);
 
 	spin_lock(&ci->i_ceph_lock);
 	dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
@@ -568,7 +637,7 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
 {
 	struct inode *inode = dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+	struct ceph_vxattr *vxattrs = ceph_inode_vxattrs(inode);
 	u32 vir_namelen = 0;
 	u32 namelen;
 	int err;
@@ -596,11 +665,12 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
 		goto out;
 
 list_xattr:
-	vir_namelen = 0;
-	/* include virtual dir xattrs */
-	if (vxattrs)
-		for (i = 0; vxattrs[i].name; i++)
-			vir_namelen += strlen(vxattrs[i].name) + 1;
+	/*
+	 * Start with virtual dir xattr names (if any) (including
+	 * terminating '\0' characters for each).
+	 */
+	vir_namelen = ceph_vxattrs_name_size(vxattrs);
+
 	/* adding 1 byte per each variable due to the null termination */
 	namelen = vir_namelen + ci->i_xattrs.names_size + ci->i_xattrs.count;
 	err = -ERANGE;
@@ -698,17 +768,17 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
 		  const void *value, size_t size, int flags)
 {
 	struct inode *inode = dentry->d_inode;
+	struct ceph_vxattr *vxattr;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+	int issued;
 	int err;
+	int dirty;
 	int name_len = strlen(name);
 	int val_len = size;
 	char *newname = NULL;
 	char *newval = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
-	int issued;
 	int required_blob_size;
-	int dirty;
 
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
@@ -716,12 +786,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
 	if (!ceph_is_valid_xattr(name))
 		return -EOPNOTSUPP;
 
-	if (vxattrs) {
-		struct ceph_vxattr_cb *vxattr =
-			ceph_match_vxattr(vxattrs, name);
-		if (vxattr && vxattr->readonly)
-			return -EOPNOTSUPP;
-	}
+	vxattr = ceph_match_vxattr(inode, name);
+	if (vxattr && vxattr->readonly)
+		return -EOPNOTSUPP;
 
 	/* preallocate memory for xattr name, value, index node */
 	err = -ENOMEM;
@@ -730,11 +797,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
 		goto out;
 
 	if (val_len) {
-		newval = kmalloc(val_len + 1, GFP_NOFS);
+		newval = kmemdup(value, val_len, GFP_NOFS);
 		if (!newval)
 			goto out;
-		memcpy(newval, value, val_len);
-		newval[val_len] = '\0';
 	}
 
 	xattr = kmalloc(sizeof(struct ceph_inode_xattr), GFP_NOFS);
@@ -744,6 +809,7 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
 	spin_lock(&ci->i_ceph_lock);
 retry:
 	issued = __ceph_caps_issued(ci, NULL);
+	dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
 	if (!(issued & CEPH_CAP_XATTR_EXCL))
 		goto do_sync;
 	__build_xattrs(inode);
@@ -752,7 +818,7 @@ retry:
 
 	if (!ci->i_xattrs.prealloc_blob ||
 	    required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
-		struct ceph_buffer *blob = NULL;
+		struct ceph_buffer *blob;
 
 		spin_unlock(&ci->i_ceph_lock);
 		dout(" preaallocating new blob size=%d\n", required_blob_size);
@@ -766,12 +832,13 @@ retry:
 		goto retry;
 	}
 
-	dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
 	err = __set_xattr(ci, newname, name_len, newval,
 			  val_len, 1, 1, 1, &xattr);
+
 	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
 	ci->i_xattrs.dirty = true;
 	inode->i_ctime = CURRENT_TIME;
+
 	spin_unlock(&ci->i_ceph_lock);
 	if (dirty)
 		__mark_inode_dirty(inode, dirty);
@@ -816,8 +883,8 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name)
 int ceph_removexattr(struct dentry *dentry, const char *name)
 {
 	struct inode *inode = dentry->d_inode;
+	struct ceph_vxattr *vxattr;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
 	int issued;
 	int err;
 	int required_blob_size;
@@ -829,22 +896,19 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
 	if (!ceph_is_valid_xattr(name))
 		return -EOPNOTSUPP;
 
-	if (vxattrs) {
-		struct ceph_vxattr_cb *vxattr =
-			ceph_match_vxattr(vxattrs, name);
-		if (vxattr && vxattr->readonly)
-			return -EOPNOTSUPP;
-	}
+	vxattr = ceph_match_vxattr(inode, name);
+	if (vxattr && vxattr->readonly)
+		return -EOPNOTSUPP;
 
 	err = -ENOMEM;
 	spin_lock(&ci->i_ceph_lock);
-	__build_xattrs(inode);
 retry:
 	issued = __ceph_caps_issued(ci, NULL);
 	dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
 
 	if (!(issued & CEPH_CAP_XATTR_EXCL))
 		goto do_sync;
+	__build_xattrs(inode);
 
 	required_blob_size = __get_required_blob_size(ci, 0, 0);
 
@@ -865,10 +929,10 @@ retry:
 	}
 
 	err = __remove_xattr_by_name(ceph_inode(inode), name);
+
 	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
 	ci->i_xattrs.dirty = true;
 	inode->i_ctime = CURRENT_TIME;
-
 	spin_unlock(&ci->i_ceph_lock);
 	if (dirty)
 		__mark_inode_dirty(inode, dirty);
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 573b899b5a5d..270464629416 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -58,15 +58,16 @@ cifs_dump_mem(char *label, void *data, int length)
 }
 
 #ifdef CONFIG_CIFS_DEBUG2
-void cifs_dump_detail(struct smb_hdr *smb)
+void cifs_dump_detail(void *buf)
 {
+	struct smb_hdr *smb = (struct smb_hdr *)buf;
+
 	cERROR(1, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d",
 		  smb->Command, smb->Status.CifsError,
 		  smb->Flags, smb->Flags2, smb->Mid, smb->Pid);
 	cERROR(1, "smb buf %p len %d", smb, smbCalcSize(smb));
 }
 
-
 void cifs_dump_mids(struct TCP_Server_Info *server)
 {
 	struct list_head *tmp;
@@ -79,15 +80,15 @@ void cifs_dump_mids(struct TCP_Server_Info *server)
 	spin_lock(&GlobalMid_Lock);
 	list_for_each(tmp, &server->pending_mid_q) {
 		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-		cERROR(1, "State: %d Cmd: %d Pid: %d Cbdata: %p Mid %d",
-			mid_entry->midState,
-			(int)mid_entry->command,
+		cERROR(1, "State: %d Cmd: %d Pid: %d Cbdata: %p Mid %llu",
+			mid_entry->mid_state,
+			le16_to_cpu(mid_entry->command),
 			mid_entry->pid,
 			mid_entry->callback_data,
 			mid_entry->mid);
 #ifdef CONFIG_CIFS_STATS2
 		cERROR(1, "IsLarge: %d buf: %p time rcv: %ld now: %ld",
-			mid_entry->largeBuf,
+			mid_entry->large_buf,
 			mid_entry->resp_buf,
 			mid_entry->when_received,
 			jiffies);
@@ -217,12 +218,12 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 				mid_entry = list_entry(tmp3, struct mid_q_entry,
 					qhead);
 				seq_printf(m, "\tState: %d com: %d pid:"
-						" %d cbdata: %p mid %d\n",
-						mid_entry->midState,
-						(int)mid_entry->command,
-						mid_entry->pid,
-						mid_entry->callback_data,
-						mid_entry->mid);
+					      " %d cbdata: %p mid %llu\n",
+					      mid_entry->mid_state,
+					      le16_to_cpu(mid_entry->command),
+					      mid_entry->pid,
+					      mid_entry->callback_data,
+					      mid_entry->mid);
 			}
 			spin_unlock(&GlobalMid_Lock);
 		}
@@ -417,7 +418,6 @@ static const struct file_operations cifs_stats_proc_fops = {
 
 static struct proc_dir_entry *proc_fs_cifs;
 static const struct file_operations cifsFYI_proc_fops;
-static const struct file_operations cifs_oplock_proc_fops;
 static const struct file_operations cifs_lookup_cache_proc_fops;
 static const struct file_operations traceSMB_proc_fops;
 static const struct file_operations cifs_multiuser_mount_proc_fops;
@@ -438,7 +438,6 @@ cifs_proc_init(void)
 #endif /* STATS */
 	proc_create("cifsFYI", 0, proc_fs_cifs, &cifsFYI_proc_fops);
 	proc_create("traceSMB", 0, proc_fs_cifs, &traceSMB_proc_fops);
-	proc_create("OplockEnabled", 0, proc_fs_cifs, &cifs_oplock_proc_fops);
 	proc_create("LinuxExtensionsEnabled", 0, proc_fs_cifs,
 		    &cifs_linux_ext_proc_fops);
 	proc_create("MultiuserMount", 0, proc_fs_cifs,
@@ -462,7 +461,6 @@ cifs_proc_clean(void)
 	remove_proc_entry("Stats", proc_fs_cifs);
 #endif
 	remove_proc_entry("MultiuserMount", proc_fs_cifs);
-	remove_proc_entry("OplockEnabled", proc_fs_cifs);
 	remove_proc_entry("SecurityFlags", proc_fs_cifs);
 	remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
 	remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
@@ -508,46 +506,6 @@ static const struct file_operations cifsFYI_proc_fops = {
 	.write		= cifsFYI_proc_write,
 };
 
-static int cifs_oplock_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%d\n", enable_oplocks);
-	return 0;
-}
-
-static int cifs_oplock_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, cifs_oplock_proc_show, NULL);
-}
-
-static ssize_t cifs_oplock_proc_write(struct file *file,
-		const char __user *buffer, size_t count, loff_t *ppos)
-{
-	char c;
-	int rc;
-
-	printk(KERN_WARNING "CIFS: The /proc/fs/cifs/OplockEnabled interface "
-	       "will be removed in kernel version 3.4. Please migrate to "
-	       "using the 'enable_oplocks' module parameter in cifs.ko.\n");
-	rc = get_user(c, buffer);
-	if (rc)
-		return rc;
-	if (c == '0' || c == 'n' || c == 'N')
-		enable_oplocks = false;
-	else if (c == '1' || c == 'y' || c == 'Y')
-		enable_oplocks = true;
-
-	return count;
-}
-
-static const struct file_operations cifs_oplock_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= cifs_oplock_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= cifs_oplock_proc_write,
-};
-
 static int cifs_linux_ext_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "%d\n", linuxExtEnabled);
diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index 8942b28cf807..566e0ae8dc2c 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -26,13 +26,13 @@
 void cifs_dump_mem(char *label, void *data, int length);
 #ifdef CONFIG_CIFS_DEBUG2
 #define DBG2 2
-void cifs_dump_detail(struct smb_hdr *);
+void cifs_dump_detail(void *);
 void cifs_dump_mids(struct TCP_Server_Info *);
 #else
 #define DBG2 0
 #endif
 extern int traceSMB;		/* flag which enables the function below */
-void dump_smb(struct smb_hdr *, int);
+void dump_smb(void *, int);
 #define CIFS_INFO	0x01
 #define CIFS_RC		0x02
 #define CIFS_TIMER	0x04
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index eee522c56ef0..d34212822444 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -85,6 +85,8 @@ extern mempool_t *cifs_sm_req_poolp;
 extern mempool_t *cifs_req_poolp;
 extern mempool_t *cifs_mid_poolp;
 
+struct workqueue_struct	*cifsiod_wq;
+
 static int
 cifs_read_super(struct super_block *sb)
 {
@@ -1111,9 +1113,15 @@ init_cifs(void)
 		cFYI(1, "cifs_max_pending set to max of %u", CIFS_MAX_REQ);
 	}
 
+	cifsiod_wq = alloc_workqueue("cifsiod", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+	if (!cifsiod_wq) {
+		rc = -ENOMEM;
+		goto out_clean_proc;
+	}
+
 	rc = cifs_fscache_register();
 	if (rc)
-		goto out_clean_proc;
+		goto out_destroy_wq;
 
 	rc = cifs_init_inodecache();
 	if (rc)
@@ -1161,6 +1169,8 @@ out_destroy_inodecache:
 	cifs_destroy_inodecache();
 out_unreg_fscache:
 	cifs_fscache_unregister();
+out_destroy_wq:
+	destroy_workqueue(cifsiod_wq);
 out_clean_proc:
 	cifs_proc_clean();
 	return rc;
@@ -1183,6 +1193,7 @@ exit_cifs(void)
 	cifs_destroy_mids();
 	cifs_destroy_inodecache();
 	cifs_fscache_unregister();
+	destroy_workqueue(cifsiod_wq);
 	cifs_proc_clean();
 }
 
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index fe5ecf1b422a..d1389bb33ceb 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -125,5 +125,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "1.76"
+#define CIFS_VERSION   "1.77"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 339ebe3ebc0d..4ff6313f0a91 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -230,6 +230,12 @@ struct cifs_mnt_data {
 	int flags;
 };
 
+static inline unsigned int
+get_rfc1002_length(void *buf)
+{
+	return be32_to_cpu(*((__be32 *)buf));
+}
+
 struct TCP_Server_Info {
 	struct list_head tcp_ses_list;
 	struct list_head smb_ses_list;
@@ -276,7 +282,7 @@ struct TCP_Server_Info {
 				   vcnumbers */
 	int capabilities; /* allow selective disabling of caps by smb sess */
 	int timeAdj;  /* Adjust for difference in server time zone in sec */
-	__u16 CurrentMid;         /* multiplex id - rotating counter */
+	__u64 CurrentMid;         /* multiplex id - rotating counter */
 	char cryptkey[CIFS_CRYPTO_KEY_SIZE]; /* used by ntlm, ntlmv2 etc */
 	/* 16th byte of RFC1001 workstation name is always null */
 	char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL];
@@ -335,6 +341,18 @@ has_credits(struct TCP_Server_Info *server, int *credits)
 	return num > 0;
 }
 
+static inline size_t
+header_size(void)
+{
+	return sizeof(struct smb_hdr);
+}
+
+static inline size_t
+max_header_size(void)
+{
+	return MAX_CIFS_HDR_SIZE;
+}
+
 /*
  * Macros to allow the TCP_Server_Info->net field and related code to drop out
  * when CONFIG_NET_NS isn't set.
@@ -583,9 +601,11 @@ struct cifs_io_parms {
  * Take a reference on the file private data. Must be called with
  * cifs_file_list_lock held.
  */
-static inline void cifsFileInfo_get(struct cifsFileInfo *cifs_file)
+static inline
+struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file)
 {
 	++cifs_file->count;
+	return cifs_file;
 }
 
 void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
@@ -606,7 +626,7 @@ struct cifsInodeInfo {
 	bool delete_pending;		/* DELETE_ON_CLOSE is set */
 	bool invalid_mapping;		/* pagecache is invalid */
 	unsigned long time;		/* jiffies of last update of inode */
-	u64  server_eof;		/* current file size on server */
+	u64  server_eof;		/* current file size on server -- protected by i_lock */
 	u64  uniqueid;			/* server inode number */
 	u64  createtime;		/* creation time on server */
 #ifdef CONFIG_CIFS_FSCACHE
@@ -713,8 +733,8 @@ typedef void (mid_callback_t)(struct mid_q_entry *mid);
 /* one of these for every pending CIFS request to the server */
 struct mid_q_entry {
 	struct list_head qhead;	/* mids waiting on reply from this server */
-	__u16 mid;		/* multiplex id */
-	__u16 pid;		/* process id */
+	__u64 mid;		/* multiplex id */
+	__u32 pid;		/* process id */
 	__u32 sequence_number;  /* for CIFS signing */
 	unsigned long when_alloc;  /* when mid was created */
 #ifdef CONFIG_CIFS_STATS2
@@ -724,10 +744,10 @@ struct mid_q_entry {
 	mid_receive_t *receive; /* call receive callback */
 	mid_callback_t *callback; /* call completion callback */
 	void *callback_data;	  /* general purpose pointer for callback */
-	struct smb_hdr *resp_buf;	/* pointer to received SMB header */
-	int midState;	/* wish this were enum but can not pass to wait_event */
-	__u8 command;	/* smb command code */
-	bool largeBuf:1;	/* if valid response, is pointer to large buf */
+	void *resp_buf;		/* pointer to received SMB header */
+	int mid_state;	/* wish this were enum but can not pass to wait_event */
+	__le16 command;		/* smb command code */
+	bool large_buf:1;	/* if valid response, is pointer to large buf */
 	bool multiRsp:1;	/* multiple trans2 responses for one request  */
 	bool multiEnd:1;	/* both received */
 };
@@ -1052,5 +1072,6 @@ GLOBAL_EXTERN spinlock_t gidsidlock;
 void cifs_oplock_break(struct work_struct *work);
 
 extern const struct slow_work_ops cifs_oplock_break_ops;
+extern struct workqueue_struct *cifsiod_wq;
 
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 503e73d8bdb7..96192c1e380a 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -77,7 +77,7 @@ extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *,
 			struct smb_hdr * /* out */ ,
 			int * /* bytes returned */ , const int long_op);
 extern int SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses,
-			struct smb_hdr *in_buf, int flags);
+			    char *in_buf, int flags);
 extern int cifs_check_receive(struct mid_q_entry *mid,
 			struct TCP_Server_Info *server, bool log_error);
 extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *,
@@ -91,9 +91,8 @@ extern int SendReceiveBlockingLock(const unsigned int xid,
 extern void cifs_add_credits(struct TCP_Server_Info *server,
 			     const unsigned int add);
 extern void cifs_set_credits(struct TCP_Server_Info *server, const int val);
-extern int checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length);
-extern bool is_valid_oplock_break(struct smb_hdr *smb,
-				  struct TCP_Server_Info *);
+extern int checkSMB(char *buf, unsigned int length);
+extern bool is_valid_oplock_break(char *, struct TCP_Server_Info *);
 extern bool backup_cred(struct cifs_sb_info *);
 extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof);
 extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
@@ -107,7 +106,7 @@ extern int cifs_convert_address(struct sockaddr *dst, const char *src, int len);
 extern int cifs_set_port(struct sockaddr *addr, const unsigned short int port);
 extern int cifs_fill_sockaddr(struct sockaddr *dst, const char *src, int len,
 				const unsigned short int port);
-extern int map_smb_to_linux_error(struct smb_hdr *smb, bool logErr);
+extern int map_smb_to_linux_error(char *buf, bool logErr);
 extern void header_assemble(struct smb_hdr *, char /* command */ ,
 			    const struct cifs_tcon *, int /* length of
 			    fixed section (word count) in two byte units */);
@@ -116,7 +115,7 @@ extern int small_smb_init_no_tc(const int smb_cmd, const int wct,
 				void **request_buf);
 extern int CIFS_SessSetup(unsigned int xid, struct cifs_ses *ses,
 			     const struct nls_table *nls_cp);
-extern __u16 GetNextMid(struct TCP_Server_Info *server);
+extern __u64 GetNextMid(struct TCP_Server_Info *server);
 extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
 extern u64 cifs_UnixTimeToNT(struct timespec);
 extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
@@ -484,18 +483,25 @@ int cifs_async_readv(struct cifs_readdata *rdata);
 /* asynchronous write support */
 struct cifs_writedata {
 	struct kref			refcount;
+	struct list_head		list;
+	struct completion		done;
 	enum writeback_sync_modes	sync_mode;
 	struct work_struct		work;
 	struct cifsFileInfo		*cfile;
 	__u64				offset;
+	pid_t				pid;
 	unsigned int			bytes;
 	int				result;
+	void (*marshal_iov) (struct kvec *iov,
+			     struct cifs_writedata *wdata);
 	unsigned int			nr_pages;
 	struct page			*pages[1];
 };
 
 int cifs_async_writev(struct cifs_writedata *wdata);
-struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages);
+void cifs_writev_complete(struct work_struct *work);
+struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages,
+						work_func_t complete);
 void cifs_writedata_release(struct kref *refcount);
 
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 70aac35c398f..f52c5ab78f9d 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -696,7 +696,7 @@ CIFSSMBTDis(const int xid, struct cifs_tcon *tcon)
 	if (rc)
 		return rc;
 
-	rc = SendReceiveNoRsp(xid, tcon->ses, smb_buffer, 0);
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *)smb_buffer, 0);
 	if (rc)
 		cFYI(1, "Tree disconnect failed %d", rc);
 
@@ -792,7 +792,7 @@ CIFSSMBLogoff(const int xid, struct cifs_ses *ses)
 	pSMB->hdr.Uid = ses->Suid;
 
 	pSMB->AndXCommand = 0xFF;
-	rc = SendReceiveNoRsp(xid, ses, (struct smb_hdr *) pSMB, 0);
+	rc = SendReceiveNoRsp(xid, ses, (char *) pSMB, 0);
 session_already_dead:
 	mutex_unlock(&ses->session_mutex);
 
@@ -1414,8 +1414,7 @@ cifs_readdata_free(struct cifs_readdata *rdata)
 static int
 cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
-	READ_RSP *rsp = (READ_RSP *)server->smallbuf;
-	unsigned int rfclen = be32_to_cpu(rsp->hdr.smb_buf_length);
+	unsigned int rfclen = get_rfc1002_length(server->smallbuf);
 	int remaining = rfclen + 4 - server->total_read;
 	struct cifs_readdata *rdata = mid->callback_data;
 
@@ -1424,7 +1423,7 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 		length = cifs_read_from_socket(server, server->bigbuf,
 				min_t(unsigned int, remaining,
-					CIFSMaxBufSize + MAX_CIFS_HDR_SIZE));
+					CIFSMaxBufSize + max_header_size()));
 		if (length < 0)
 			return length;
 		server->total_read += length;
@@ -1435,19 +1434,40 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	return 0;
 }
 
+static inline size_t
+read_rsp_size(void)
+{
+	return sizeof(READ_RSP);
+}
+
+static inline unsigned int
+read_data_offset(char *buf)
+{
+	READ_RSP *rsp = (READ_RSP *)buf;
+	return le16_to_cpu(rsp->DataOffset);
+}
+
+static inline unsigned int
+read_data_length(char *buf)
+{
+	READ_RSP *rsp = (READ_RSP *)buf;
+	return (le16_to_cpu(rsp->DataLengthHigh) << 16) +
+	       le16_to_cpu(rsp->DataLength);
+}
+
 static int
 cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
 	int length, len;
 	unsigned int data_offset, remaining, data_len;
 	struct cifs_readdata *rdata = mid->callback_data;
-	READ_RSP *rsp = (READ_RSP *)server->smallbuf;
-	unsigned int rfclen = be32_to_cpu(rsp->hdr.smb_buf_length) + 4;
+	char *buf = server->smallbuf;
+	unsigned int buflen = get_rfc1002_length(buf) + 4;
 	u64 eof;
 	pgoff_t eof_index;
 	struct page *page, *tpage;
 
-	cFYI(1, "%s: mid=%u offset=%llu bytes=%u", __func__,
+	cFYI(1, "%s: mid=%llu offset=%llu bytes=%u", __func__,
 		mid->mid, rdata->offset, rdata->bytes);
 
 	/*
@@ -1455,10 +1475,9 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	 * can if there's not enough data. At this point, we've read down to
 	 * the Mid.
 	 */
-	len = min_t(unsigned int, rfclen, sizeof(*rsp)) -
-			sizeof(struct smb_hdr) + 1;
+	len = min_t(unsigned int, buflen, read_rsp_size()) - header_size() + 1;
 
-	rdata->iov[0].iov_base = server->smallbuf + sizeof(struct smb_hdr) - 1;
+	rdata->iov[0].iov_base = buf + header_size() - 1;
 	rdata->iov[0].iov_len = len;
 
 	length = cifs_readv_from_socket(server, rdata->iov, 1, len);
@@ -1467,7 +1486,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	server->total_read += length;
 
 	/* Was the SMB read successful? */
-	rdata->result = map_smb_to_linux_error(&rsp->hdr, false);
+	rdata->result = map_smb_to_linux_error(buf, false);
 	if (rdata->result != 0) {
 		cFYI(1, "%s: server returned error %d", __func__,
 			rdata->result);
@@ -1475,14 +1494,14 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	}
 
 	/* Is there enough to get to the rest of the READ_RSP header? */
-	if (server->total_read < sizeof(READ_RSP)) {
+	if (server->total_read < read_rsp_size()) {
 		cFYI(1, "%s: server returned short header. got=%u expected=%zu",
-			__func__, server->total_read, sizeof(READ_RSP));
+			__func__, server->total_read, read_rsp_size());
 		rdata->result = -EIO;
 		return cifs_readv_discard(server, mid);
 	}
 
-	data_offset = le16_to_cpu(rsp->DataOffset) + 4;
+	data_offset = read_data_offset(buf) + 4;
 	if (data_offset < server->total_read) {
 		/*
 		 * win2k8 sometimes sends an offset of 0 when the read
@@ -1506,7 +1525,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	len = data_offset - server->total_read;
 	if (len > 0) {
 		/* read any junk before data into the rest of smallbuf */
-		rdata->iov[0].iov_base = server->smallbuf + server->total_read;
+		rdata->iov[0].iov_base = buf + server->total_read;
 		rdata->iov[0].iov_len = len;
 		length = cifs_readv_from_socket(server, rdata->iov, 1, len);
 		if (length < 0)
@@ -1515,15 +1534,14 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	}
 
 	/* set up first iov for signature check */
-	rdata->iov[0].iov_base = server->smallbuf;
+	rdata->iov[0].iov_base = buf;
 	rdata->iov[0].iov_len = server->total_read;
 	cFYI(1, "0: iov_base=%p iov_len=%zu",
 		rdata->iov[0].iov_base, rdata->iov[0].iov_len);
 
 	/* how much data is in the response? */
-	data_len = le16_to_cpu(rsp->DataLengthHigh) << 16;
-	data_len += le16_to_cpu(rsp->DataLength);
-	if (data_offset + data_len > rfclen) {
+	data_len = read_data_length(buf);
+	if (data_offset + data_len > buflen) {
 		/* data_len is corrupt -- discard frame */
 		rdata->result = -EIO;
 		return cifs_readv_discard(server, mid);
@@ -1602,11 +1620,11 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	rdata->bytes = length;
 
-	cFYI(1, "total_read=%u rfclen=%u remaining=%u", server->total_read,
-		rfclen, remaining);
+	cFYI(1, "total_read=%u buflen=%u remaining=%u", server->total_read,
+		buflen, remaining);
 
 	/* discard anything left over */
-	if (server->total_read < rfclen)
+	if (server->total_read < buflen)
 		return cifs_readv_discard(server, mid);
 
 	dequeue_mid(mid, false);
@@ -1647,10 +1665,10 @@ cifs_readv_callback(struct mid_q_entry *mid)
 	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
 
-	cFYI(1, "%s: mid=%u state=%d result=%d bytes=%u", __func__,
-		mid->mid, mid->midState, rdata->result, rdata->bytes);
+	cFYI(1, "%s: mid=%llu state=%d result=%d bytes=%u", __func__,
+		mid->mid, mid->mid_state, rdata->result, rdata->bytes);
 
-	switch (mid->midState) {
+	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
 		/* result already set, check signature */
 		if (server->sec_mode &
@@ -1671,7 +1689,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
 		rdata->result = -EIO;
 	}
 
-	queue_work(system_nrt_wq, &rdata->work);
+	queue_work(cifsiod_wq, &rdata->work);
 	DeleteMidQEntry(mid);
 	cifs_add_credits(server, 1);
 }
@@ -2017,7 +2035,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
 	kref_put(&wdata->refcount, cifs_writedata_release);
 }
 
-static void
+void
 cifs_writev_complete(struct work_struct *work)
 {
 	struct cifs_writedata *wdata = container_of(work,
@@ -2026,7 +2044,9 @@ cifs_writev_complete(struct work_struct *work)
 	int i = 0;
 
 	if (wdata->result == 0) {
+		spin_lock(&inode->i_lock);
 		cifs_update_eof(CIFS_I(inode), wdata->offset, wdata->bytes);
+		spin_unlock(&inode->i_lock);
 		cifs_stats_bytes_written(tlink_tcon(wdata->cfile->tlink),
 					 wdata->bytes);
 	} else if (wdata->sync_mode == WB_SYNC_ALL && wdata->result == -EAGAIN)
@@ -2047,7 +2067,7 @@ cifs_writev_complete(struct work_struct *work)
 }
 
 struct cifs_writedata *
-cifs_writedata_alloc(unsigned int nr_pages)
+cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete)
 {
 	struct cifs_writedata *wdata;
 
@@ -2061,14 +2081,16 @@ cifs_writedata_alloc(unsigned int nr_pages)
 	wdata = kzalloc(sizeof(*wdata) +
 			sizeof(struct page *) * (nr_pages - 1), GFP_NOFS);
 	if (wdata != NULL) {
-		INIT_WORK(&wdata->work, cifs_writev_complete);
 		kref_init(&wdata->refcount);
+		INIT_LIST_HEAD(&wdata->list);
+		init_completion(&wdata->done);
+		INIT_WORK(&wdata->work, complete);
 	}
 	return wdata;
 }
 
 /*
- * Check the midState and signature on received buffer (if any), and queue the
+ * Check the mid_state and signature on received buffer (if any), and queue the
  * workqueue completion task.
  */
 static void
@@ -2079,7 +2101,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
 	unsigned int written;
 	WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf;
 
-	switch (mid->midState) {
+	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
 		wdata->result = cifs_check_receive(mid, tcon->ses->server, 0);
 		if (wdata->result != 0)
@@ -2111,7 +2133,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
 		break;
 	}
 
-	queue_work(system_nrt_wq, &wdata->work);
+	queue_work(cifsiod_wq, &wdata->work);
 	DeleteMidQEntry(mid);
 	cifs_add_credits(tcon->ses->server, 1);
 }
@@ -2124,7 +2146,6 @@ cifs_async_writev(struct cifs_writedata *wdata)
 	WRITE_REQ *smb = NULL;
 	int wct;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
-	struct inode *inode = wdata->cfile->dentry->d_inode;
 	struct kvec *iov = NULL;
 
 	if (tcon->ses->capabilities & CAP_LARGE_FILES) {
@@ -2148,8 +2169,8 @@ cifs_async_writev(struct cifs_writedata *wdata)
 		goto async_writev_out;
 	}
 
-	smb->hdr.Pid = cpu_to_le16((__u16)wdata->cfile->pid);
-	smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->cfile->pid >> 16));
+	smb->hdr.Pid = cpu_to_le16((__u16)wdata->pid);
+	smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->pid >> 16));
 
 	smb->AndXCommand = 0xFF;	/* none */
 	smb->Fid = wdata->cfile->netfid;
@@ -2167,15 +2188,13 @@ cifs_async_writev(struct cifs_writedata *wdata)
 	iov[0].iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4 + 1;
 	iov[0].iov_base = smb;
 
-	/* marshal up the pages into iov array */
-	wdata->bytes = 0;
-	for (i = 0; i < wdata->nr_pages; i++) {
-		iov[i + 1].iov_len = min(inode->i_size -
-				      page_offset(wdata->pages[i]),
-					(loff_t)PAGE_CACHE_SIZE);
-		iov[i + 1].iov_base = kmap(wdata->pages[i]);
-		wdata->bytes += iov[i + 1].iov_len;
-	}
+	/*
+	 * This function should marshal up the page array into the kvec
+	 * array, reserving [0] for the header. It should kmap the pages
+	 * and set the iov_len properly for each one. It may also set
+	 * wdata->bytes too.
+	 */
+	wdata->marshal_iov(iov, wdata);
 
 	cFYI(1, "async write at %llu %u bytes", wdata->offset, wdata->bytes);
 
@@ -2420,8 +2439,7 @@ CIFSSMBLock(const int xid, struct cifs_tcon *tcon,
 			(struct smb_hdr *) pSMB, &bytes_returned);
 		cifs_small_buf_release(pSMB);
 	} else {
-		rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *)pSMB,
-				      timeout);
+		rc = SendReceiveNoRsp(xid, tcon->ses, (char *)pSMB, timeout);
 		/* SMB buffer freed by function above */
 	}
 	cifs_stats_inc(&tcon->num_locks);
@@ -2588,7 +2606,7 @@ CIFSSMBClose(const int xid, struct cifs_tcon *tcon, int smb_file_id)
 	pSMB->FileID = (__u16) smb_file_id;
 	pSMB->LastWriteTime = 0xFFFFFFFF;
 	pSMB->ByteCount = 0;
-	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
 	cifs_stats_inc(&tcon->num_closes);
 	if (rc) {
 		if (rc != -EINTR) {
@@ -2617,7 +2635,7 @@ CIFSSMBFlush(const int xid, struct cifs_tcon *tcon, int smb_file_id)
 
 	pSMB->FileID = (__u16) smb_file_id;
 	pSMB->ByteCount = 0;
-	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
 	cifs_stats_inc(&tcon->num_flushes);
 	if (rc)
 		cERROR(1, "Send error in Flush = %d", rc);
@@ -3874,13 +3892,12 @@ CIFSSMBSetCIFSACL(const int xid, struct cifs_tcon *tcon, __u16 fid,
 	int rc = 0;
 	int bytes_returned = 0;
 	SET_SEC_DESC_REQ *pSMB = NULL;
-	NTRANSACT_RSP *pSMBr = NULL;
+	void *pSMBr;
 
 setCifsAclRetry:
-	rc = smb_init(SMB_COM_NT_TRANSACT, 19, tcon, (void **) &pSMB,
-			(void **) &pSMBr);
+	rc = smb_init(SMB_COM_NT_TRANSACT, 19, tcon, (void **) &pSMB, &pSMBr);
 	if (rc)
-			return (rc);
+		return rc;
 
 	pSMB->MaxSetupCount = 0;
 	pSMB->Reserved = 0;
@@ -3908,9 +3925,8 @@ setCifsAclRetry:
 	pSMB->AclFlags = cpu_to_le32(aclflag);
 
 	if (pntsd && acllen) {
-		memcpy((char *) &pSMBr->hdr.Protocol + data_offset,
-			(char *) pntsd,
-			acllen);
+		memcpy((char *)pSMBr + offsetof(struct smb_hdr, Protocol) +
+				data_offset, pntsd, acllen);
 		inc_rfc1001_len(pSMB, byte_count + data_count);
 	} else
 		inc_rfc1001_len(pSMB, byte_count);
@@ -4625,7 +4641,7 @@ CIFSFindClose(const int xid, struct cifs_tcon *tcon,
 
 	pSMB->FileID = searchHandle;
 	pSMB->ByteCount = 0;
-	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
 	if (rc)
 		cERROR(1, "Send error in FindClose = %d", rc);
 
@@ -5646,7 +5662,7 @@ CIFSSMBSetFileSize(const int xid, struct cifs_tcon *tcon, __u64 size,
 	pSMB->Reserved4 = 0;
 	inc_rfc1001_len(pSMB, byte_count);
 	pSMB->ByteCount = cpu_to_le16(byte_count);
-	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
 	if (rc) {
 		cFYI(1, "Send error in SetFileInfo (SetFileSize) = %d", rc);
 	}
@@ -5690,7 +5706,8 @@ CIFSSMBSetFileInfo(const int xid, struct cifs_tcon *tcon,
 	param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4;
 	offset = param_offset + params;
 
-	data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
+	data_offset = (char *)pSMB +
+			offsetof(struct smb_hdr, Protocol) + offset;
 
 	count = sizeof(FILE_BASIC_INFO);
 	pSMB->MaxParameterCount = cpu_to_le16(2);
@@ -5715,7 +5732,7 @@ CIFSSMBSetFileInfo(const int xid, struct cifs_tcon *tcon,
 	inc_rfc1001_len(pSMB, byte_count);
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	memcpy(data_offset, data, sizeof(FILE_BASIC_INFO));
-	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
 	if (rc)
 		cFYI(1, "Send error in Set Time (SetFileInfo) = %d", rc);
 
@@ -5774,7 +5791,7 @@ CIFSSMBSetFileDisposition(const int xid, struct cifs_tcon *tcon,
 	inc_rfc1001_len(pSMB, byte_count);
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	*data_offset = delete_file ? 1 : 0;
-	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
 	if (rc)
 		cFYI(1, "Send error in SetFileDisposition = %d", rc);
 
@@ -5959,7 +5976,7 @@ CIFSSMBUnixSetFileInfo(const int xid, struct cifs_tcon *tcon,
 		       u16 fid, u32 pid_of_opener)
 {
 	struct smb_com_transaction2_sfi_req *pSMB  = NULL;
-	FILE_UNIX_BASIC_INFO *data_offset;
+	char *data_offset;
 	int rc = 0;
 	u16 params, param_offset, offset, byte_count, count;
 
@@ -5981,8 +5998,9 @@ CIFSSMBUnixSetFileInfo(const int xid, struct cifs_tcon *tcon,
 	param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4;
 	offset = param_offset + params;
 
-	data_offset = (FILE_UNIX_BASIC_INFO *)
-				((char *)(&pSMB->hdr.Protocol) + offset);
+	data_offset = (char *)pSMB +
+			offsetof(struct smb_hdr, Protocol) + offset;
+
 	count = sizeof(FILE_UNIX_BASIC_INFO);
 
 	pSMB->MaxParameterCount = cpu_to_le16(2);
@@ -6004,9 +6022,9 @@ CIFSSMBUnixSetFileInfo(const int xid, struct cifs_tcon *tcon,
 	inc_rfc1001_len(pSMB, byte_count);
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 
-	cifs_fill_unix_set_info(data_offset, args);
+	cifs_fill_unix_set_info((FILE_UNIX_BASIC_INFO *)data_offset, args);
 
-	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
 	if (rc)
 		cFYI(1, "Send error in Set Time (SetFileInfo) = %d", rc);
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5560e1d5e54b..d81e933a796b 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -40,6 +40,8 @@
 #include <linux/module.h>
 #include <keys/user-type.h>
 #include <net/ipv6.h>
+#include <linux/parser.h>
+
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifsproto.h"
@@ -63,6 +65,193 @@ extern mempool_t *cifs_req_poolp;
 #define TLINK_ERROR_EXPIRE	(1 * HZ)
 #define TLINK_IDLE_EXPIRE	(600 * HZ)
 
+enum {
+
+	/* Mount options that take no arguments */
+	Opt_user_xattr, Opt_nouser_xattr,
+	Opt_forceuid, Opt_noforceuid,
+	Opt_noblocksend, Opt_noautotune,
+	Opt_hard, Opt_soft, Opt_perm, Opt_noperm,
+	Opt_mapchars, Opt_nomapchars, Opt_sfu,
+	Opt_nosfu, Opt_nodfs, Opt_posixpaths,
+	Opt_noposixpaths, Opt_nounix,
+	Opt_nocase,
+	Opt_brl, Opt_nobrl,
+	Opt_forcemandatorylock, Opt_setuids,
+	Opt_nosetuids, Opt_dynperm, Opt_nodynperm,
+	Opt_nohard, Opt_nosoft,
+	Opt_nointr, Opt_intr,
+	Opt_nostrictsync, Opt_strictsync,
+	Opt_serverino, Opt_noserverino,
+	Opt_rwpidforward, Opt_cifsacl, Opt_nocifsacl,
+	Opt_acl, Opt_noacl, Opt_locallease,
+	Opt_sign, Opt_seal, Opt_direct,
+	Opt_strictcache, Opt_noac,
+	Opt_fsc, Opt_mfsymlinks,
+	Opt_multiuser, Opt_sloppy,
+
+	/* Mount options which take numeric value */
+	Opt_backupuid, Opt_backupgid, Opt_uid,
+	Opt_cruid, Opt_gid, Opt_file_mode,
+	Opt_dirmode, Opt_port,
+	Opt_rsize, Opt_wsize, Opt_actimeo,
+
+	/* Mount options which take string value */
+	Opt_user, Opt_pass, Opt_ip,
+	Opt_unc, Opt_domain,
+	Opt_srcaddr, Opt_prefixpath,
+	Opt_iocharset, Opt_sockopt,
+	Opt_netbiosname, Opt_servern,
+	Opt_ver, Opt_sec,
+
+	/* Mount options to be ignored */
+	Opt_ignore,
+
+	/* Options which could be blank */
+	Opt_blank_pass,
+
+	Opt_err
+};
+
+static const match_table_t cifs_mount_option_tokens = {
+
+	{ Opt_user_xattr, "user_xattr" },
+	{ Opt_nouser_xattr, "nouser_xattr" },
+	{ Opt_forceuid, "forceuid" },
+	{ Opt_noforceuid, "noforceuid" },
+	{ Opt_noblocksend, "noblocksend" },
+	{ Opt_noautotune, "noautotune" },
+	{ Opt_hard, "hard" },
+	{ Opt_soft, "soft" },
+	{ Opt_perm, "perm" },
+	{ Opt_noperm, "noperm" },
+	{ Opt_mapchars, "mapchars" },
+	{ Opt_nomapchars, "nomapchars" },
+	{ Opt_sfu, "sfu" },
+	{ Opt_nosfu, "nosfu" },
+	{ Opt_nodfs, "nodfs" },
+	{ Opt_posixpaths, "posixpaths" },
+	{ Opt_noposixpaths, "noposixpaths" },
+	{ Opt_nounix, "nounix" },
+	{ Opt_nounix, "nolinux" },
+	{ Opt_nocase, "nocase" },
+	{ Opt_nocase, "ignorecase" },
+	{ Opt_brl, "brl" },
+	{ Opt_nobrl, "nobrl" },
+	{ Opt_nobrl, "nolock" },
+	{ Opt_forcemandatorylock, "forcemandatorylock" },
+	{ Opt_forcemandatorylock, "forcemand" },
+	{ Opt_setuids, "setuids" },
+	{ Opt_nosetuids, "nosetuids" },
+	{ Opt_dynperm, "dynperm" },
+	{ Opt_nodynperm, "nodynperm" },
+	{ Opt_nohard, "nohard" },
+	{ Opt_nosoft, "nosoft" },
+	{ Opt_nointr, "nointr" },
+	{ Opt_intr, "intr" },
+	{ Opt_nostrictsync, "nostrictsync" },
+	{ Opt_strictsync, "strictsync" },
+	{ Opt_serverino, "serverino" },
+	{ Opt_noserverino, "noserverino" },
+	{ Opt_rwpidforward, "rwpidforward" },
+	{ Opt_cifsacl, "cifsacl" },
+	{ Opt_nocifsacl, "nocifsacl" },
+	{ Opt_acl, "acl" },
+	{ Opt_noacl, "noacl" },
+	{ Opt_locallease, "locallease" },
+	{ Opt_sign, "sign" },
+	{ Opt_seal, "seal" },
+	{ Opt_direct, "direct" },
+	{ Opt_direct, "forceddirectio" },
+	{ Opt_strictcache, "strictcache" },
+	{ Opt_noac, "noac" },
+	{ Opt_fsc, "fsc" },
+	{ Opt_mfsymlinks, "mfsymlinks" },
+	{ Opt_multiuser, "multiuser" },
+	{ Opt_sloppy, "sloppy" },
+
+	{ Opt_backupuid, "backupuid=%s" },
+	{ Opt_backupgid, "backupgid=%s" },
+	{ Opt_uid, "uid=%s" },
+	{ Opt_cruid, "cruid=%s" },
+	{ Opt_gid, "gid=%s" },
+	{ Opt_file_mode, "file_mode=%s" },
+	{ Opt_dirmode, "dirmode=%s" },
+	{ Opt_dirmode, "dir_mode=%s" },
+	{ Opt_port, "port=%s" },
+	{ Opt_rsize, "rsize=%s" },
+	{ Opt_wsize, "wsize=%s" },
+	{ Opt_actimeo, "actimeo=%s" },
+
+	{ Opt_user, "user=%s" },
+	{ Opt_user, "username=%s" },
+	{ Opt_blank_pass, "pass=" },
+	{ Opt_pass, "pass=%s" },
+	{ Opt_pass, "password=%s" },
+	{ Opt_ip, "ip=%s" },
+	{ Opt_ip, "addr=%s" },
+	{ Opt_unc, "unc=%s" },
+	{ Opt_unc, "target=%s" },
+	{ Opt_unc, "path=%s" },
+	{ Opt_domain, "dom=%s" },
+	{ Opt_domain, "domain=%s" },
+	{ Opt_domain, "workgroup=%s" },
+	{ Opt_srcaddr, "srcaddr=%s" },
+	{ Opt_prefixpath, "prefixpath=%s" },
+	{ Opt_iocharset, "iocharset=%s" },
+	{ Opt_sockopt, "sockopt=%s" },
+	{ Opt_netbiosname, "netbiosname=%s" },
+	{ Opt_servern, "servern=%s" },
+	{ Opt_ver, "ver=%s" },
+	{ Opt_ver, "vers=%s" },
+	{ Opt_ver, "version=%s" },
+	{ Opt_sec, "sec=%s" },
+
+	{ Opt_ignore, "cred" },
+	{ Opt_ignore, "credentials" },
+	{ Opt_ignore, "guest" },
+	{ Opt_ignore, "rw" },
+	{ Opt_ignore, "ro" },
+	{ Opt_ignore, "suid" },
+	{ Opt_ignore, "nosuid" },
+	{ Opt_ignore, "exec" },
+	{ Opt_ignore, "noexec" },
+	{ Opt_ignore, "nodev" },
+	{ Opt_ignore, "noauto" },
+	{ Opt_ignore, "dev" },
+	{ Opt_ignore, "mand" },
+	{ Opt_ignore, "nomand" },
+	{ Opt_ignore, "_netdev" },
+
+	{ Opt_err, NULL }
+};
+
+enum {
+	Opt_sec_krb5, Opt_sec_krb5i, Opt_sec_krb5p,
+	Opt_sec_ntlmsspi, Opt_sec_ntlmssp,
+	Opt_ntlm, Opt_sec_ntlmi, Opt_sec_ntlmv2i,
+	Opt_sec_nontlm, Opt_sec_lanman,
+	Opt_sec_none,
+
+	Opt_sec_err
+};
+
+static const match_table_t cifs_secflavor_tokens = {
+	{ Opt_sec_krb5, "krb5" },
+	{ Opt_sec_krb5i, "krb5i" },
+	{ Opt_sec_krb5p, "krb5p" },
+	{ Opt_sec_ntlmsspi, "ntlmsspi" },
+	{ Opt_sec_ntlmssp, "ntlmssp" },
+	{ Opt_ntlm, "ntlm" },
+	{ Opt_sec_ntlmi, "ntlmi" },
+	{ Opt_sec_ntlmv2i, "ntlmv2i" },
+	{ Opt_sec_nontlm, "nontlm" },
+	{ Opt_sec_lanman, "lanman" },
+	{ Opt_sec_none, "none" },
+
+	{ Opt_sec_err, NULL }
+};
+
 static int ip_connect(struct TCP_Server_Info *server);
 static int generic_ip_connect(struct TCP_Server_Info *server);
 static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink);
@@ -143,8 +332,8 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	spin_lock(&GlobalMid_Lock);
 	list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-		if (mid_entry->midState == MID_REQUEST_SUBMITTED)
-			mid_entry->midState = MID_RETRY_NEEDED;
+		if (mid_entry->mid_state == MID_REQUEST_SUBMITTED)
+			mid_entry->mid_state = MID_RETRY_NEEDED;
 		list_move(&mid_entry->qhead, &retry_list);
 	}
 	spin_unlock(&GlobalMid_Lock);
@@ -183,8 +372,9 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		-EINVAL = invalid transact2
 
  */
-static int check2ndT2(struct smb_hdr *pSMB)
+static int check2ndT2(char *buf)
 {
+	struct smb_hdr *pSMB = (struct smb_hdr *)buf;
 	struct smb_t2_rsp *pSMBt;
 	int remaining;
 	__u16 total_data_size, data_in_this_rsp;
@@ -224,10 +414,10 @@ static int check2ndT2(struct smb_hdr *pSMB)
 	return remaining;
 }
 
-static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB)
+static int coalesce_t2(char *second_buf, struct smb_hdr *target_hdr)
 {
-	struct smb_t2_rsp *pSMBs = (struct smb_t2_rsp *)psecond;
-	struct smb_t2_rsp *pSMBt  = (struct smb_t2_rsp *)pTargetSMB;
+	struct smb_t2_rsp *pSMBs = (struct smb_t2_rsp *)second_buf;
+	struct smb_t2_rsp *pSMBt  = (struct smb_t2_rsp *)target_hdr;
 	char *data_area_of_tgt;
 	char *data_area_of_src;
 	int remaining;
@@ -280,23 +470,23 @@ static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB)
 	put_unaligned_le16(total_in_tgt, &pSMBt->t2_rsp.DataCount);
 
 	/* fix up the BCC */
-	byte_count = get_bcc(pTargetSMB);
+	byte_count = get_bcc(target_hdr);
 	byte_count += total_in_src;
 	/* is the result too big for the field? */
 	if (byte_count > USHRT_MAX) {
 		cFYI(1, "coalesced BCC too large (%u)", byte_count);
 		return -EPROTO;
 	}
-	put_bcc(byte_count, pTargetSMB);
+	put_bcc(byte_count, target_hdr);
 
-	byte_count = be32_to_cpu(pTargetSMB->smb_buf_length);
+	byte_count = be32_to_cpu(target_hdr->smb_buf_length);
 	byte_count += total_in_src;
 	/* don't allow buffer to overflow */
 	if (byte_count > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
 		cFYI(1, "coalesced BCC exceeds buffer size (%u)", byte_count);
 		return -ENOBUFS;
 	}
-	pTargetSMB->smb_buf_length = cpu_to_be32(byte_count);
+	target_hdr->smb_buf_length = cpu_to_be32(byte_count);
 
 	/* copy second buffer into end of first buffer */
 	memcpy(data_area_of_tgt, data_area_of_src, total_in_src);
@@ -334,7 +524,7 @@ cifs_echo_request(struct work_struct *work)
 			server->hostname);
 
 requeue_echo:
-	queue_delayed_work(system_nrt_wq, &server->echo, SMB_ECHO_INTERVAL);
+	queue_delayed_work(cifsiod_wq, &server->echo, SMB_ECHO_INTERVAL);
 }
 
 static bool
@@ -350,7 +540,7 @@ allocate_buffers(struct TCP_Server_Info *server)
 		}
 	} else if (server->large_buf) {
 		/* we are reusing a dirty large buf, clear its start */
-		memset(server->bigbuf, 0, sizeof(struct smb_hdr));
+		memset(server->bigbuf, 0, header_size());
 	}
 
 	if (!server->smallbuf) {
@@ -364,7 +554,7 @@ allocate_buffers(struct TCP_Server_Info *server)
 		/* beginning of smb buffer is cleared in our buf_get */
 	} else {
 		/* if existing small buf clear beginning */
-		memset(server->smallbuf, 0, sizeof(struct smb_hdr));
+		memset(server->smallbuf, 0, header_size());
 	}
 
 	return true;
@@ -566,15 +756,16 @@ is_smb_response(struct TCP_Server_Info *server, unsigned char type)
 }
 
 static struct mid_q_entry *
-find_mid(struct TCP_Server_Info *server, struct smb_hdr *buf)
+find_mid(struct TCP_Server_Info *server, char *buffer)
 {
+	struct smb_hdr *buf = (struct smb_hdr *)buffer;
 	struct mid_q_entry *mid;
 
 	spin_lock(&GlobalMid_Lock);
 	list_for_each_entry(mid, &server->pending_mid_q, qhead) {
 		if (mid->mid == buf->Mid &&
-		    mid->midState == MID_REQUEST_SUBMITTED &&
-		    mid->command == buf->Command) {
+		    mid->mid_state == MID_REQUEST_SUBMITTED &&
+		    le16_to_cpu(mid->command) == buf->Command) {
 			spin_unlock(&GlobalMid_Lock);
 			return mid;
 		}
@@ -591,16 +782,16 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed)
 #endif
 	spin_lock(&GlobalMid_Lock);
 	if (!malformed)
-		mid->midState = MID_RESPONSE_RECEIVED;
+		mid->mid_state = MID_RESPONSE_RECEIVED;
 	else
-		mid->midState = MID_RESPONSE_MALFORMED;
+		mid->mid_state = MID_RESPONSE_MALFORMED;
 	list_del_init(&mid->qhead);
 	spin_unlock(&GlobalMid_Lock);
 }
 
 static void
 handle_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server,
-	   struct smb_hdr *buf, int malformed)
+	   char *buf, int malformed)
 {
 	if (malformed == 0 && check2ndT2(buf) > 0) {
 		mid->multiRsp = true;
@@ -620,13 +811,13 @@ handle_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 		} else {
 			/* Have first buffer */
 			mid->resp_buf = buf;
-			mid->largeBuf = true;
+			mid->large_buf = true;
 			server->bigbuf = NULL;
 		}
 		return;
 	}
 	mid->resp_buf = buf;
-	mid->largeBuf = server->large_buf;
+	mid->large_buf = server->large_buf;
 	/* Was previous buf put in mpx struct for multi-rsp? */
 	if (!mid->multiRsp) {
 		/* smb buffer will be freed by user thread */
@@ -682,8 +873,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 		spin_lock(&GlobalMid_Lock);
 		list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-			cFYI(1, "Clearing mid 0x%x", mid_entry->mid);
-			mid_entry->midState = MID_SHUTDOWN;
+			cFYI(1, "Clearing mid 0x%llx", mid_entry->mid);
+			mid_entry->mid_state = MID_SHUTDOWN;
 			list_move(&mid_entry->qhead, &dispose_list);
 		}
 		spin_unlock(&GlobalMid_Lock);
@@ -691,7 +882,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 		/* now walk dispose list and issue callbacks */
 		list_for_each_safe(tmp, tmp2, &dispose_list) {
 			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-			cFYI(1, "Callback mid 0x%x", mid_entry->mid);
+			cFYI(1, "Callback mid 0x%llx", mid_entry->mid);
 			list_del_init(&mid_entry->qhead);
 			mid_entry->callback(mid_entry);
 		}
@@ -731,11 +922,10 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
 	int length;
 	char *buf = server->smallbuf;
-	struct smb_hdr *smb_buffer = (struct smb_hdr *)buf;
-	unsigned int pdu_length = be32_to_cpu(smb_buffer->smb_buf_length);
+	unsigned int pdu_length = get_rfc1002_length(buf);
 
 	/* make sure this will fit in a large buffer */
-	if (pdu_length > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
+	if (pdu_length > CIFSMaxBufSize + max_header_size() - 4) {
 		cERROR(1, "SMB response too long (%u bytes)",
 			pdu_length);
 		cifs_reconnect(server);
@@ -746,20 +936,18 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	/* switch to large buffer if too big for a small one */
 	if (pdu_length > MAX_CIFS_SMALL_BUFFER_SIZE - 4) {
 		server->large_buf = true;
-		memcpy(server->bigbuf, server->smallbuf, server->total_read);
+		memcpy(server->bigbuf, buf, server->total_read);
 		buf = server->bigbuf;
-		smb_buffer = (struct smb_hdr *)buf;
 	}
 
 	/* now read the rest */
-	length = cifs_read_from_socket(server,
-			  buf + sizeof(struct smb_hdr) - 1,
-			  pdu_length - sizeof(struct smb_hdr) + 1 + 4);
+	length = cifs_read_from_socket(server, buf + header_size() - 1,
+				       pdu_length - header_size() + 1 + 4);
 	if (length < 0)
 		return length;
 	server->total_read += length;
 
-	dump_smb(smb_buffer, server->total_read);
+	dump_smb(buf, server->total_read);
 
 	/*
 	 * We know that we received enough to get to the MID as we
@@ -770,7 +958,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	 * 48 bytes is enough to display the header and a little bit
 	 * into the payload for debugging purposes.
 	 */
-	length = checkSMB(smb_buffer, smb_buffer->Mid, server->total_read);
+	length = checkSMB(buf, server->total_read);
 	if (length != 0)
 		cifs_dump_mem("Bad SMB: ", buf,
 			min_t(unsigned int, server->total_read, 48));
@@ -778,7 +966,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	if (!mid)
 		return length;
 
-	handle_mid(mid, server, smb_buffer, length);
+	handle_mid(mid, server, buf, length);
 	return 0;
 }
 
@@ -789,7 +977,6 @@ cifs_demultiplex_thread(void *p)
 	struct TCP_Server_Info *server = p;
 	unsigned int pdu_length;
 	char *buf = NULL;
-	struct smb_hdr *smb_buffer = NULL;
 	struct task_struct *task_to_wake = NULL;
 	struct mid_q_entry *mid_entry;
 
@@ -810,7 +997,6 @@ cifs_demultiplex_thread(void *p)
 			continue;
 
 		server->large_buf = false;
-		smb_buffer = (struct smb_hdr *)server->smallbuf;
 		buf = server->smallbuf;
 		pdu_length = 4; /* enough to get RFC1001 header */
 
@@ -823,14 +1009,14 @@ cifs_demultiplex_thread(void *p)
 		 * The right amount was read from socket - 4 bytes,
 		 * so we can now interpret the length field.
 		 */
-		pdu_length = be32_to_cpu(smb_buffer->smb_buf_length);
+		pdu_length = get_rfc1002_length(buf);
 
 		cFYI(1, "RFC1002 header 0x%x", pdu_length);
 		if (!is_smb_response(server, buf[0]))
 			continue;
 
 		/* make sure we have enough to get to the MID */
-		if (pdu_length < sizeof(struct smb_hdr) - 1 - 4) {
+		if (pdu_length < header_size() - 1 - 4) {
 			cERROR(1, "SMB response too short (%u bytes)",
 				pdu_length);
 			cifs_reconnect(server);
@@ -840,12 +1026,12 @@ cifs_demultiplex_thread(void *p)
 
 		/* read down to the MID */
 		length = cifs_read_from_socket(server, buf + 4,
-					sizeof(struct smb_hdr) - 1 - 4);
+					       header_size() - 1 - 4);
 		if (length < 0)
 			continue;
 		server->total_read += length;
 
-		mid_entry = find_mid(server, smb_buffer);
+		mid_entry = find_mid(server, buf);
 
 		if (!mid_entry || !mid_entry->receive)
 			length = standard_receive3(server, mid_entry);
@@ -855,22 +1041,19 @@ cifs_demultiplex_thread(void *p)
 		if (length < 0)
 			continue;
 
-		if (server->large_buf) {
+		if (server->large_buf)
 			buf = server->bigbuf;
-			smb_buffer = (struct smb_hdr *)buf;
-		}
 
 		server->lstrp = jiffies;
 		if (mid_entry != NULL) {
 			if (!mid_entry->multiRsp || mid_entry->multiEnd)
 				mid_entry->callback(mid_entry);
-		} else if (!is_valid_oplock_break(smb_buffer, server)) {
+		} else if (!is_valid_oplock_break(buf, server)) {
 			cERROR(1, "No task to wake, unknown frame received! "
 				   "NumMids %d", atomic_read(&midCount));
-			cifs_dump_mem("Received Data is: ", buf,
-				      sizeof(struct smb_hdr));
+			cifs_dump_mem("Received Data is: ", buf, header_size());
 #ifdef CONFIG_CIFS_DEBUG2
-			cifs_dump_detail(smb_buffer);
+			cifs_dump_detail(buf);
 			cifs_dump_mids(server);
 #endif /* CIFS_DEBUG2 */
 
@@ -926,23 +1109,95 @@ extract_hostname(const char *unc)
 	return dst;
 }
 
+static int get_option_ul(substring_t args[], unsigned long *option)
+{
+	int rc;
+	char *string;
+
+	string = match_strdup(args);
+	if (string == NULL)
+		return -ENOMEM;
+	rc = kstrtoul(string, 10, option);
+	kfree(string);
+
+	return rc;
+}
+
+
+static int cifs_parse_security_flavors(char *value,
+				       struct smb_vol *vol)
+{
+
+	substring_t args[MAX_OPT_ARGS];
+
+	switch (match_token(value, cifs_secflavor_tokens, args)) {
+	case Opt_sec_krb5:
+		vol->secFlg |= CIFSSEC_MAY_KRB5;
+		break;
+	case Opt_sec_krb5i:
+		vol->secFlg |= CIFSSEC_MAY_KRB5 | CIFSSEC_MUST_SIGN;
+		break;
+	case Opt_sec_krb5p:
+		/* vol->secFlg |= CIFSSEC_MUST_SEAL | CIFSSEC_MAY_KRB5; */
+		cERROR(1, "Krb5 cifs privacy not supported");
+		break;
+	case Opt_sec_ntlmssp:
+		vol->secFlg |= CIFSSEC_MAY_NTLMSSP;
+		break;
+	case Opt_sec_ntlmsspi:
+		vol->secFlg |= CIFSSEC_MAY_NTLMSSP | CIFSSEC_MUST_SIGN;
+		break;
+	case Opt_ntlm:
+		/* ntlm is default so can be turned off too */
+		vol->secFlg |= CIFSSEC_MAY_NTLM;
+		break;
+	case Opt_sec_ntlmi:
+		vol->secFlg |= CIFSSEC_MAY_NTLM | CIFSSEC_MUST_SIGN;
+		break;
+	case Opt_sec_nontlm:
+		vol->secFlg |= CIFSSEC_MAY_NTLMV2;
+		break;
+	case Opt_sec_ntlmv2i:
+		vol->secFlg |= CIFSSEC_MAY_NTLMV2 | CIFSSEC_MUST_SIGN;
+		break;
+#ifdef CONFIG_CIFS_WEAK_PW_HASH
+	case Opt_sec_lanman:
+		vol->secFlg |= CIFSSEC_MAY_LANMAN;
+		break;
+#endif
+	case Opt_sec_none:
+		vol->nullauth = 1;
+		break;
+	default:
+		cERROR(1, "bad security option: %s", value);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int
 cifs_parse_mount_options(const char *mountdata, const char *devname,
 			 struct smb_vol *vol)
 {
-	char *value, *data, *end;
+	char *data, *end;
 	char *mountdata_copy = NULL, *options;
-	int err;
 	unsigned int  temp_len, i, j;
 	char separator[2];
 	short int override_uid = -1;
 	short int override_gid = -1;
 	bool uid_specified = false;
 	bool gid_specified = false;
+	bool sloppy = false;
+	char *invalid = NULL;
 	char *nodename = utsname()->nodename;
+	char *string = NULL;
+	char *tmp_end, *value;
+	char delim;
 
 	separator[0] = ',';
 	separator[1] = 0;
+	delim = separator[0];
 
 	/*
 	 * does not have to be perfect mapping since field is
@@ -981,6 +1236,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 
 	options = mountdata_copy;
 	end = options + strlen(options);
+
 	if (strncmp(options, "sep=", 4) == 0) {
 		if (options[4] != 0) {
 			separator[0] = options[4];
@@ -993,609 +1249,651 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 	vol->backupgid_specified = false; /* no backup intent for a group */
 
 	while ((data = strsep(&options, separator)) != NULL) {
+		substring_t args[MAX_OPT_ARGS];
+		unsigned long option;
+		int token;
+
 		if (!*data)
 			continue;
-		if ((value = strchr(data, '=')) != NULL)
-			*value++ = '\0';
 
-		/* Have to parse this before we parse for "user" */
-		if (strnicmp(data, "user_xattr", 10) == 0) {
+		token = match_token(data, cifs_mount_option_tokens, args);
+
+		switch (token) {
+
+		/* Ingnore the following */
+		case Opt_ignore:
+			break;
+
+		/* Boolean values */
+		case Opt_user_xattr:
 			vol->no_xattr = 0;
-		} else if (strnicmp(data, "nouser_xattr", 12) == 0) {
+			break;
+		case Opt_nouser_xattr:
 			vol->no_xattr = 1;
-		} else if (strnicmp(data, "user", 4) == 0) {
-			if (!value) {
-				printk(KERN_WARNING
-				       "CIFS: invalid or missing username\n");
-				goto cifs_parse_mount_err;
-			} else if (!*value) {
-				/* null user, ie anonymous, authentication */
-				vol->nullauth = 1;
-			}
-			if (strnlen(value, MAX_USERNAME_SIZE) <
-						MAX_USERNAME_SIZE) {
-				vol->username = kstrdup(value, GFP_KERNEL);
-				if (!vol->username) {
-					printk(KERN_WARNING "CIFS: no memory "
-							    "for username\n");
-					goto cifs_parse_mount_err;
-				}
-			} else {
-				printk(KERN_WARNING "CIFS: username too long\n");
-				goto cifs_parse_mount_err;
-			}
-		} else if (strnicmp(data, "pass", 4) == 0) {
-			if (!value) {
-				vol->password = NULL;
-				continue;
-			} else if (value[0] == 0) {
-				/* check if string begins with double comma
-				   since that would mean the password really
-				   does start with a comma, and would not
-				   indicate an empty string */
-				if (value[1] != separator[0]) {
-					vol->password = NULL;
-					continue;
-				}
-			}
-			temp_len = strlen(value);
-			/* removed password length check, NTLM passwords
-				can be arbitrarily long */
-
-			/* if comma in password, the string will be
-			prematurely null terminated.  Commas in password are
-			specified across the cifs mount interface by a double
-			comma ie ,, and a comma used as in other cases ie ','
-			as a parameter delimiter/separator is single and due
-			to the strsep above is temporarily zeroed. */
-
-			/* NB: password legally can have multiple commas and
-			the only illegal character in a password is null */
-
-			if ((value[temp_len] == 0) &&
-			    (value + temp_len < end) &&
-			    (value[temp_len+1] == separator[0])) {
-				/* reinsert comma */
-				value[temp_len] = separator[0];
-				temp_len += 2;  /* move after second comma */
-				while (value[temp_len] != 0)  {
-					if (value[temp_len] == separator[0]) {
-						if (value[temp_len+1] ==
-						     separator[0]) {
-						/* skip second comma */
-							temp_len++;
-						} else {
-						/* single comma indicating start
-							 of next parm */
-							break;
-						}
-					}
-					temp_len++;
-				}
-				if (value[temp_len] == 0) {
-					options = NULL;
-				} else {
-					value[temp_len] = 0;
-					/* point option to start of next parm */
-					options = value + temp_len + 1;
-				}
-				/* go from value to value + temp_len condensing
-				double commas to singles. Note that this ends up
-				allocating a few bytes too many, which is ok */
-				vol->password = kzalloc(temp_len, GFP_KERNEL);
-				if (vol->password == NULL) {
-					printk(KERN_WARNING "CIFS: no memory "
-							    "for password\n");
-					goto cifs_parse_mount_err;
-				}
-				for (i = 0, j = 0; i < temp_len; i++, j++) {
-					vol->password[j] = value[i];
-					if (value[i] == separator[0]
-						&& value[i+1] == separator[0]) {
-						/* skip second comma */
-						i++;
-					}
-				}
-				vol->password[j] = 0;
-			} else {
-				vol->password = kzalloc(temp_len+1, GFP_KERNEL);
-				if (vol->password == NULL) {
-					printk(KERN_WARNING "CIFS: no memory "
-							    "for password\n");
-					goto cifs_parse_mount_err;
-				}
-				strcpy(vol->password, value);
-			}
-		} else if (!strnicmp(data, "ip", 2) ||
-			   !strnicmp(data, "addr", 4)) {
-			if (!value || !*value) {
-				vol->UNCip = NULL;
-			} else if (strnlen(value, INET6_ADDRSTRLEN) <
-							INET6_ADDRSTRLEN) {
-				vol->UNCip = kstrdup(value, GFP_KERNEL);
-				if (!vol->UNCip) {
-					printk(KERN_WARNING "CIFS: no memory "
-							    "for UNC IP\n");
-					goto cifs_parse_mount_err;
-				}
-			} else {
-				printk(KERN_WARNING "CIFS: ip address "
-						    "too long\n");
-				goto cifs_parse_mount_err;
-			}
-		} else if (strnicmp(data, "sec", 3) == 0) {
-			if (!value || !*value) {
-				cERROR(1, "no security value specified");
-				continue;
-			} else if (strnicmp(value, "krb5i", 5) == 0) {
-				vol->secFlg |= CIFSSEC_MAY_KRB5 |
-					CIFSSEC_MUST_SIGN;
-			} else if (strnicmp(value, "krb5p", 5) == 0) {
-				/* vol->secFlg |= CIFSSEC_MUST_SEAL |
-					CIFSSEC_MAY_KRB5; */
-				cERROR(1, "Krb5 cifs privacy not supported");
-				goto cifs_parse_mount_err;
-			} else if (strnicmp(value, "krb5", 4) == 0) {
-				vol->secFlg |= CIFSSEC_MAY_KRB5;
-			} else if (strnicmp(value, "ntlmsspi", 8) == 0) {
-				vol->secFlg |= CIFSSEC_MAY_NTLMSSP |
-					CIFSSEC_MUST_SIGN;
-			} else if (strnicmp(value, "ntlmssp", 7) == 0) {
-				vol->secFlg |= CIFSSEC_MAY_NTLMSSP;
-			} else if (strnicmp(value, "ntlmv2i", 7) == 0) {
-				vol->secFlg |= CIFSSEC_MAY_NTLMV2 |
-					CIFSSEC_MUST_SIGN;
-			} else if (strnicmp(value, "ntlmv2", 6) == 0) {
-				vol->secFlg |= CIFSSEC_MAY_NTLMV2;
-			} else if (strnicmp(value, "ntlmi", 5) == 0) {
-				vol->secFlg |= CIFSSEC_MAY_NTLM |
-					CIFSSEC_MUST_SIGN;
-			} else if (strnicmp(value, "ntlm", 4) == 0) {
-				/* ntlm is default so can be turned off too */
-				vol->secFlg |= CIFSSEC_MAY_NTLM;
-			} else if (strnicmp(value, "nontlm", 6) == 0) {
-				/* BB is there a better way to do this? */
-				vol->secFlg |= CIFSSEC_MAY_NTLMV2;
-#ifdef CONFIG_CIFS_WEAK_PW_HASH
-			} else if (strnicmp(value, "lanman", 6) == 0) {
-				vol->secFlg |= CIFSSEC_MAY_LANMAN;
-#endif
-			} else if (strnicmp(value, "none", 4) == 0) {
-				vol->nullauth = 1;
-			} else {
-				cERROR(1, "bad security option: %s", value);
-				goto cifs_parse_mount_err;
-			}
-		} else if (strnicmp(data, "vers", 3) == 0) {
-			if (!value || !*value) {
-				cERROR(1, "no protocol version specified"
-					  " after vers= mount option");
-			} else if ((strnicmp(value, "cifs", 4) == 0) ||
-				   (strnicmp(value, "1", 1) == 0)) {
-				/* this is the default */
-				continue;
-			}
-		} else if ((strnicmp(data, "unc", 3) == 0)
-			   || (strnicmp(data, "target", 6) == 0)
-			   || (strnicmp(data, "path", 4) == 0)) {
-			if (!value || !*value) {
-				printk(KERN_WARNING "CIFS: invalid path to "
-						    "network resource\n");
-				goto cifs_parse_mount_err;
-			}
-			if ((temp_len = strnlen(value, 300)) < 300) {
-				vol->UNC = kmalloc(temp_len+1, GFP_KERNEL);
-				if (vol->UNC == NULL)
-					goto cifs_parse_mount_err;
-				strcpy(vol->UNC, value);
-				if (strncmp(vol->UNC, "//", 2) == 0) {
-					vol->UNC[0] = '\\';
-					vol->UNC[1] = '\\';
-				} else if (strncmp(vol->UNC, "\\\\", 2) != 0) {
-					printk(KERN_WARNING
-					       "CIFS: UNC Path does not begin "
-					       "with // or \\\\ \n");
-					goto cifs_parse_mount_err;
-				}
-			} else {
-				printk(KERN_WARNING "CIFS: UNC name too long\n");
-				goto cifs_parse_mount_err;
-			}
-		} else if ((strnicmp(data, "domain", 3) == 0)
-			   || (strnicmp(data, "workgroup", 5) == 0)) {
-			if (!value || !*value) {
-				printk(KERN_WARNING "CIFS: invalid domain name\n");
-				goto cifs_parse_mount_err;
-			}
-			/* BB are there cases in which a comma can be valid in
-			a domain name and need special handling? */
-			if (strnlen(value, 256) < 256) {
-				vol->domainname = kstrdup(value, GFP_KERNEL);
-				if (!vol->domainname) {
-					printk(KERN_WARNING "CIFS: no memory "
-							    "for domainname\n");
-					goto cifs_parse_mount_err;
-				}
-				cFYI(1, "Domain name set");
-			} else {
-				printk(KERN_WARNING "CIFS: domain name too "
-						    "long\n");
-				goto cifs_parse_mount_err;
-			}
-		} else if (strnicmp(data, "srcaddr", 7) == 0) {
-			vol->srcaddr.ss_family = AF_UNSPEC;
-
-			if (!value || !*value) {
-				printk(KERN_WARNING "CIFS: srcaddr value"
-				       " not specified.\n");
-				goto cifs_parse_mount_err;
-			}
-			i = cifs_convert_address((struct sockaddr *)&vol->srcaddr,
-						 value, strlen(value));
-			if (i == 0) {
-				printk(KERN_WARNING "CIFS:  Could not parse"
-				       " srcaddr: %s\n",
-				       value);
-				goto cifs_parse_mount_err;
-			}
-		} else if (strnicmp(data, "prefixpath", 10) == 0) {
-			if (!value || !*value) {
-				printk(KERN_WARNING
-					"CIFS: invalid path prefix\n");
-				goto cifs_parse_mount_err;
-			}
-			if ((temp_len = strnlen(value, 1024)) < 1024) {
-				if (value[0] != '/')
-					temp_len++;  /* missing leading slash */
-				vol->prepath = kmalloc(temp_len+1, GFP_KERNEL);
-				if (vol->prepath == NULL)
-					goto cifs_parse_mount_err;
-				if (value[0] != '/') {
-					vol->prepath[0] = '/';
-					strcpy(vol->prepath+1, value);
-				} else
-					strcpy(vol->prepath, value);
-				cFYI(1, "prefix path %s", vol->prepath);
-			} else {
-				printk(KERN_WARNING "CIFS: prefix too long\n");
-				goto cifs_parse_mount_err;
-			}
-		} else if (strnicmp(data, "iocharset", 9) == 0) {
-			if (!value || !*value) {
-				printk(KERN_WARNING "CIFS: invalid iocharset "
-						    "specified\n");
-				goto cifs_parse_mount_err;
-			}
-			if (strnlen(value, 65) < 65) {
-				if (strnicmp(value, "default", 7)) {
-					vol->iocharset = kstrdup(value,
-								 GFP_KERNEL);
-
-					if (!vol->iocharset) {
-						printk(KERN_WARNING "CIFS: no "
-								   "memory for"
-								   "charset\n");
-						goto cifs_parse_mount_err;
-					}
-				}
-				/* if iocharset not set then load_nls_default
-				   is used by caller */
-				cFYI(1, "iocharset set to %s", value);
-			} else {
-				printk(KERN_WARNING "CIFS: iocharset name "
-						    "too long.\n");
-				goto cifs_parse_mount_err;
-			}
-		} else if (!strnicmp(data, "uid", 3) && value && *value) {
-			vol->linux_uid = simple_strtoul(value, &value, 0);
-			uid_specified = true;
-		} else if (!strnicmp(data, "cruid", 5) && value && *value) {
-			vol->cred_uid = simple_strtoul(value, &value, 0);
-		} else if (!strnicmp(data, "forceuid", 8)) {
+			break;
+		case Opt_forceuid:
 			override_uid = 1;
-		} else if (!strnicmp(data, "noforceuid", 10)) {
+			break;
+		case Opt_noforceuid:
 			override_uid = 0;
-		} else if (!strnicmp(data, "gid", 3) && value && *value) {
-			vol->linux_gid = simple_strtoul(value, &value, 0);
-			gid_specified = true;
-		} else if (!strnicmp(data, "forcegid", 8)) {
-			override_gid = 1;
-		} else if (!strnicmp(data, "noforcegid", 10)) {
-			override_gid = 0;
-		} else if (strnicmp(data, "file_mode", 4) == 0) {
-			if (value && *value) {
-				vol->file_mode =
-					simple_strtoul(value, &value, 0);
-			}
-		} else if (strnicmp(data, "dir_mode", 4) == 0) {
-			if (value && *value) {
-				vol->dir_mode =
-					simple_strtoul(value, &value, 0);
-			}
-		} else if (strnicmp(data, "dirmode", 4) == 0) {
-			if (value && *value) {
-				vol->dir_mode =
-					simple_strtoul(value, &value, 0);
-			}
-		} else if (strnicmp(data, "port", 4) == 0) {
-			if (value && *value) {
-				vol->port =
-					simple_strtoul(value, &value, 0);
-			}
-		} else if (strnicmp(data, "rsize", 5) == 0) {
-			if (value && *value) {
-				vol->rsize =
-					simple_strtoul(value, &value, 0);
-			}
-		} else if (strnicmp(data, "wsize", 5) == 0) {
-			if (value && *value) {
-				vol->wsize =
-					simple_strtoul(value, &value, 0);
-			}
-		} else if (strnicmp(data, "sockopt", 5) == 0) {
-			if (!value || !*value) {
-				cERROR(1, "no socket option specified");
-				continue;
-			} else if (strnicmp(value, "TCP_NODELAY", 11) == 0) {
-				vol->sockopt_tcp_nodelay = 1;
-			}
-		} else if (strnicmp(data, "netbiosname", 4) == 0) {
-			if (!value || !*value || (*value == ' ')) {
-				cFYI(1, "invalid (empty) netbiosname");
-			} else {
-				memset(vol->source_rfc1001_name, 0x20,
-					RFC1001_NAME_LEN);
-				/*
-				 * FIXME: are there cases in which a comma can
-				 * be valid in workstation netbios name (and
-				 * need special handling)?
-				 */
-				for (i = 0; i < RFC1001_NAME_LEN; i++) {
-					/* don't ucase netbiosname for user */
-					if (value[i] == 0)
-						break;
-					vol->source_rfc1001_name[i] = value[i];
-				}
-				/* The string has 16th byte zero still from
-				set at top of the function  */
-				if (i == RFC1001_NAME_LEN && value[i] != 0)
-					printk(KERN_WARNING "CIFS: netbiosname"
-						" longer than 15 truncated.\n");
-			}
-		} else if (strnicmp(data, "servern", 7) == 0) {
-			/* servernetbiosname specified override *SMBSERVER */
-			if (!value || !*value || (*value == ' ')) {
-				cFYI(1, "empty server netbiosname specified");
-			} else {
-				/* last byte, type, is 0x20 for servr type */
-				memset(vol->target_rfc1001_name, 0x20,
-					RFC1001_NAME_LEN_WITH_NULL);
-
-				for (i = 0; i < 15; i++) {
-				/* BB are there cases in which a comma can be
-				   valid in this workstation netbios name
-				   (and need special handling)? */
-
-				/* user or mount helper must uppercase
-				   the netbiosname */
-					if (value[i] == 0)
-						break;
-					else
-						vol->target_rfc1001_name[i] =
-								value[i];
-				}
-				/* The string has 16th byte zero still from
-				   set at top of the function  */
-				if (i == RFC1001_NAME_LEN && value[i] != 0)
-					printk(KERN_WARNING "CIFS: server net"
-					"biosname longer than 15 truncated.\n");
-			}
-		} else if (strnicmp(data, "actimeo", 7) == 0) {
-			if (value && *value) {
-				vol->actimeo = HZ * simple_strtoul(value,
-								   &value, 0);
-				if (vol->actimeo > CIFS_MAX_ACTIMEO) {
-					cERROR(1, "CIFS: attribute cache"
-							"timeout too large");
-					goto cifs_parse_mount_err;
-				}
-			}
-		} else if (strnicmp(data, "credentials", 4) == 0) {
-			/* ignore */
-		} else if (strnicmp(data, "version", 3) == 0) {
-			/* ignore */
-		} else if (strnicmp(data, "guest", 5) == 0) {
-			/* ignore */
-		} else if (strnicmp(data, "rw", 2) == 0 && strlen(data) == 2) {
-			/* ignore */
-		} else if (strnicmp(data, "ro", 2) == 0) {
-			/* ignore */
-		} else if (strnicmp(data, "noblocksend", 11) == 0) {
+			break;
+		case Opt_noblocksend:
 			vol->noblocksnd = 1;
-		} else if (strnicmp(data, "noautotune", 10) == 0) {
+			break;
+		case Opt_noautotune:
 			vol->noautotune = 1;
-		} else if ((strnicmp(data, "suid", 4) == 0) ||
-				   (strnicmp(data, "nosuid", 6) == 0) ||
-				   (strnicmp(data, "exec", 4) == 0) ||
-				   (strnicmp(data, "noexec", 6) == 0) ||
-				   (strnicmp(data, "nodev", 5) == 0) ||
-				   (strnicmp(data, "noauto", 6) == 0) ||
-				   (strnicmp(data, "dev", 3) == 0)) {
-			/*  The mount tool or mount.cifs helper (if present)
-			    uses these opts to set flags, and the flags are read
-			    by the kernel vfs layer before we get here (ie
-			    before read super) so there is no point trying to
-			    parse these options again and set anything and it
-			    is ok to just ignore them */
-			continue;
-		} else if (strnicmp(data, "hard", 4) == 0) {
+			break;
+		case Opt_hard:
 			vol->retry = 1;
-		} else if (strnicmp(data, "soft", 4) == 0) {
+			break;
+		case Opt_soft:
 			vol->retry = 0;
-		} else if (strnicmp(data, "perm", 4) == 0) {
+			break;
+		case Opt_perm:
 			vol->noperm = 0;
-		} else if (strnicmp(data, "noperm", 6) == 0) {
+			break;
+		case Opt_noperm:
 			vol->noperm = 1;
-		} else if (strnicmp(data, "mapchars", 8) == 0) {
+			break;
+		case Opt_mapchars:
 			vol->remap = 1;
-		} else if (strnicmp(data, "nomapchars", 10) == 0) {
+			break;
+		case Opt_nomapchars:
 			vol->remap = 0;
-		} else if (strnicmp(data, "sfu", 3) == 0) {
+			break;
+		case Opt_sfu:
 			vol->sfu_emul = 1;
-		} else if (strnicmp(data, "nosfu", 5) == 0) {
+			break;
+		case Opt_nosfu:
 			vol->sfu_emul = 0;
-		} else if (strnicmp(data, "nodfs", 5) == 0) {
+			break;
+		case Opt_nodfs:
 			vol->nodfs = 1;
-		} else if (strnicmp(data, "posixpaths", 10) == 0) {
+			break;
+		case Opt_posixpaths:
 			vol->posix_paths = 1;
-		} else if (strnicmp(data, "noposixpaths", 12) == 0) {
+			break;
+		case Opt_noposixpaths:
 			vol->posix_paths = 0;
-		} else if (strnicmp(data, "nounix", 6) == 0) {
-			vol->no_linux_ext = 1;
-		} else if (strnicmp(data, "nolinux", 7) == 0) {
+			break;
+		case Opt_nounix:
 			vol->no_linux_ext = 1;
-		} else if ((strnicmp(data, "nocase", 6) == 0) ||
-			   (strnicmp(data, "ignorecase", 10)  == 0)) {
+			break;
+		case Opt_nocase:
 			vol->nocase = 1;
-		} else if (strnicmp(data, "mand", 4) == 0) {
-			/* ignore */
-		} else if (strnicmp(data, "nomand", 6) == 0) {
-			/* ignore */
-		} else if (strnicmp(data, "_netdev", 7) == 0) {
-			/* ignore */
-		} else if (strnicmp(data, "brl", 3) == 0) {
+			break;
+		case Opt_brl:
 			vol->nobrl =  0;
-		} else if ((strnicmp(data, "nobrl", 5) == 0) ||
-			   (strnicmp(data, "nolock", 6) == 0)) {
+			break;
+		case Opt_nobrl:
 			vol->nobrl =  1;
-			/* turn off mandatory locking in mode
-			if remote locking is turned off since the
-			local vfs will do advisory */
+			/*
+			 * turn off mandatory locking in mode
+			 * if remote locking is turned off since the
+			 * local vfs will do advisory
+			 */
 			if (vol->file_mode ==
 				(S_IALLUGO & ~(S_ISUID | S_IXGRP)))
 				vol->file_mode = S_IALLUGO;
-		} else if (strnicmp(data, "forcemandatorylock", 9) == 0) {
-			/* will take the shorter form "forcemand" as well */
-			/* This mount option will force use of mandatory
-			  (DOS/Windows style) byte range locks, instead of
-			  using posix advisory byte range locks, even if the
-			  Unix extensions are available and posix locks would
-			  be supported otherwise. If Unix extensions are not
-			  negotiated this has no effect since mandatory locks
-			  would be used (mandatory locks is all that those
-			  those servers support) */
+			break;
+		case Opt_forcemandatorylock:
 			vol->mand_lock = 1;
-		} else if (strnicmp(data, "setuids", 7) == 0) {
+			break;
+		case Opt_setuids:
 			vol->setuids = 1;
-		} else if (strnicmp(data, "nosetuids", 9) == 0) {
+			break;
+		case Opt_nosetuids:
 			vol->setuids = 0;
-		} else if (strnicmp(data, "dynperm", 7) == 0) {
+			break;
+		case Opt_dynperm:
 			vol->dynperm = true;
-		} else if (strnicmp(data, "nodynperm", 9) == 0) {
+			break;
+		case Opt_nodynperm:
 			vol->dynperm = false;
-		} else if (strnicmp(data, "nohard", 6) == 0) {
+			break;
+		case Opt_nohard:
 			vol->retry = 0;
-		} else if (strnicmp(data, "nosoft", 6) == 0) {
+			break;
+		case Opt_nosoft:
 			vol->retry = 1;
-		} else if (strnicmp(data, "nointr", 6) == 0) {
+			break;
+		case Opt_nointr:
 			vol->intr = 0;
-		} else if (strnicmp(data, "intr", 4) == 0) {
+			break;
+		case Opt_intr:
 			vol->intr = 1;
-		} else if (strnicmp(data, "nostrictsync", 12) == 0) {
+			break;
+		case Opt_nostrictsync:
 			vol->nostrictsync = 1;
-		} else if (strnicmp(data, "strictsync", 10) == 0) {
+			break;
+		case Opt_strictsync:
 			vol->nostrictsync = 0;
-		} else if (strnicmp(data, "serverino", 7) == 0) {
+			break;
+		case Opt_serverino:
 			vol->server_ino = 1;
-		} else if (strnicmp(data, "noserverino", 9) == 0) {
+			break;
+		case Opt_noserverino:
 			vol->server_ino = 0;
-		} else if (strnicmp(data, "rwpidforward", 12) == 0) {
+			break;
+		case Opt_rwpidforward:
 			vol->rwpidforward = 1;
-		} else if (strnicmp(data, "cifsacl", 7) == 0) {
+			break;
+		case Opt_cifsacl:
 			vol->cifs_acl = 1;
-		} else if (strnicmp(data, "nocifsacl", 9) == 0) {
+			break;
+		case Opt_nocifsacl:
 			vol->cifs_acl = 0;
-		} else if (strnicmp(data, "acl", 3) == 0) {
+			break;
+		case Opt_acl:
 			vol->no_psx_acl = 0;
-		} else if (strnicmp(data, "noacl", 5) == 0) {
+			break;
+		case Opt_noacl:
 			vol->no_psx_acl = 1;
-		} else if (strnicmp(data, "locallease", 6) == 0) {
+			break;
+		case Opt_locallease:
 			vol->local_lease = 1;
-		} else if (strnicmp(data, "sign", 4) == 0) {
+			break;
+		case Opt_sign:
 			vol->secFlg |= CIFSSEC_MUST_SIGN;
-		} else if (strnicmp(data, "seal", 4) == 0) {
+			break;
+		case Opt_seal:
 			/* we do not do the following in secFlags because seal
-			   is a per tree connection (mount) not a per socket
-			   or per-smb connection option in the protocol */
-			/* vol->secFlg |= CIFSSEC_MUST_SEAL; */
+			 * is a per tree connection (mount) not a per socket
+			 * or per-smb connection option in the protocol
+			 * vol->secFlg |= CIFSSEC_MUST_SEAL;
+			 */
 			vol->seal = 1;
-		} else if (strnicmp(data, "direct", 6) == 0) {
-			vol->direct_io = 1;
-		} else if (strnicmp(data, "forcedirectio", 13) == 0) {
+			break;
+		case Opt_direct:
 			vol->direct_io = 1;
-		} else if (strnicmp(data, "strictcache", 11) == 0) {
+			break;
+		case Opt_strictcache:
 			vol->strict_io = 1;
-		} else if (strnicmp(data, "noac", 4) == 0) {
+			break;
+		case Opt_noac:
 			printk(KERN_WARNING "CIFS: Mount option noac not "
 				"supported. Instead set "
 				"/proc/fs/cifs/LookupCacheEnabled to 0\n");
-		} else if (strnicmp(data, "fsc", 3) == 0) {
+			break;
+		case Opt_fsc:
 #ifndef CONFIG_CIFS_FSCACHE
 			cERROR(1, "FS-Cache support needs CONFIG_CIFS_FSCACHE "
 				  "kernel config option set");
 			goto cifs_parse_mount_err;
 #endif
 			vol->fsc = true;
-		} else if (strnicmp(data, "mfsymlinks", 10) == 0) {
+			break;
+		case Opt_mfsymlinks:
 			vol->mfsymlinks = true;
-		} else if (strnicmp(data, "multiuser", 8) == 0) {
+			break;
+		case Opt_multiuser:
 			vol->multiuser = true;
-		} else if (!strnicmp(data, "backupuid", 9) && value && *value) {
-			err = kstrtouint(value, 0, &vol->backupuid);
-			if (err < 0) {
+			break;
+		case Opt_sloppy:
+			sloppy = true;
+			break;
+
+		/* Numeric Values */
+		case Opt_backupuid:
+			if (get_option_ul(args, &option)) {
 				cERROR(1, "%s: Invalid backupuid value",
 					__func__);
 				goto cifs_parse_mount_err;
 			}
+			vol->backupuid = option;
 			vol->backupuid_specified = true;
-		} else if (!strnicmp(data, "backupgid", 9) && value && *value) {
-			err = kstrtouint(value, 0, &vol->backupgid);
-			if (err < 0) {
+			break;
+		case Opt_backupgid:
+			if (get_option_ul(args, &option)) {
 				cERROR(1, "%s: Invalid backupgid value",
 					__func__);
 				goto cifs_parse_mount_err;
 			}
+			vol->backupgid = option;
 			vol->backupgid_specified = true;
-		} else
-			printk(KERN_WARNING "CIFS: Unknown mount option %s\n",
-						data);
-	}
-	if (vol->UNC == NULL) {
-		if (devname == NULL) {
-			printk(KERN_WARNING "CIFS: Missing UNC name for mount "
-						"target\n");
-			goto cifs_parse_mount_err;
-		}
-		if ((temp_len = strnlen(devname, 300)) < 300) {
+			break;
+		case Opt_uid:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid uid value",
+					__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->linux_uid = option;
+			uid_specified = true;
+			break;
+		case Opt_cruid:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid cruid value",
+					__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->cred_uid = option;
+			break;
+		case Opt_gid:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid gid value",
+						__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->linux_gid = option;
+			gid_specified = true;
+			break;
+		case Opt_file_mode:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid file_mode value",
+					__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->file_mode = option;
+			break;
+		case Opt_dirmode:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid dir_mode value",
+					__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->dir_mode = option;
+			break;
+		case Opt_port:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid port value",
+					__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->port = option;
+			break;
+		case Opt_rsize:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid rsize value",
+					__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->rsize = option;
+			break;
+		case Opt_wsize:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid wsize value",
+					__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->wsize = option;
+			break;
+		case Opt_actimeo:
+			if (get_option_ul(args, &option)) {
+				cERROR(1, "%s: Invalid actimeo value",
+					__func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->actimeo = HZ * option;
+			if (vol->actimeo > CIFS_MAX_ACTIMEO) {
+				cERROR(1, "CIFS: attribute cache"
+					  "timeout too large");
+				goto cifs_parse_mount_err;
+			}
+			break;
+
+		/* String Arguments */
+
+		case Opt_user:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				/* null user, ie. anonymous authentication */
+				vol->nullauth = 1;
+			} else if (strnlen(string, MAX_USERNAME_SIZE) >
+							MAX_USERNAME_SIZE) {
+				printk(KERN_WARNING "CIFS: username too long\n");
+				goto cifs_parse_mount_err;
+			}
+			vol->username = kstrdup(string, GFP_KERNEL);
+			if (!vol->username) {
+				printk(KERN_WARNING "CIFS: no memory "
+						    "for username\n");
+				goto cifs_parse_mount_err;
+			}
+			break;
+		case Opt_blank_pass:
+			vol->password = NULL;
+			break;
+		case Opt_pass:
+			/* passwords have to be handled differently
+			 * to allow the character used for deliminator
+			 * to be passed within them
+			 */
+
+			/* Obtain the value string */
+			value = strchr(data, '=');
+			value++;
+
+			/* Set tmp_end to end of the string */
+			tmp_end = (char *) value + strlen(value);
+
+			/* Check if following character is the deliminator
+			 * If yes, we have encountered a double deliminator
+			 * reset the NULL character to the deliminator
+			 */
+			if (tmp_end < end && tmp_end[1] == delim)
+				tmp_end[0] = delim;
+
+			/* Keep iterating until we get to a single deliminator
+			 * OR the end
+			 */
+			while ((tmp_end = strchr(tmp_end, delim)) != NULL &&
+			       (tmp_end[1] == delim)) {
+				tmp_end = (char *) &tmp_end[2];
+			}
+
+			/* Reset var options to point to next element */
+			if (tmp_end) {
+				tmp_end[0] = '\0';
+				options = (char *) &tmp_end[1];
+			} else
+				/* Reached the end of the mount option string */
+				options = end;
+
+			/* Now build new password string */
+			temp_len = strlen(value);
+			vol->password = kzalloc(temp_len+1, GFP_KERNEL);
+			if (vol->password == NULL) {
+				printk(KERN_WARNING "CIFS: no memory "
+						    "for password\n");
+				goto cifs_parse_mount_err;
+			}
+
+			for (i = 0, j = 0; i < temp_len; i++, j++) {
+				vol->password[j] = value[i];
+				if ((value[i] == delim) &&
+				     value[i+1] == delim)
+					/* skip the second deliminator */
+					i++;
+			}
+			vol->password[j] = '\0';
+			break;
+		case Opt_ip:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				vol->UNCip = NULL;
+			} else if (strnlen(string, INET6_ADDRSTRLEN) >
+						INET6_ADDRSTRLEN) {
+				printk(KERN_WARNING "CIFS: ip address "
+						    "too long\n");
+				goto cifs_parse_mount_err;
+			}
+			vol->UNCip = kstrdup(string, GFP_KERNEL);
+			if (!vol->UNCip) {
+				printk(KERN_WARNING "CIFS: no memory "
+						    "for UNC IP\n");
+				goto cifs_parse_mount_err;
+			}
+			break;
+		case Opt_unc:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: invalid path to "
+						    "network resource\n");
+				goto cifs_parse_mount_err;
+			}
+
+			temp_len = strnlen(string, 300);
+			if (temp_len  == 300) {
+				printk(KERN_WARNING "CIFS: UNC name too long\n");
+				goto cifs_parse_mount_err;
+			}
+
 			vol->UNC = kmalloc(temp_len+1, GFP_KERNEL);
-			if (vol->UNC == NULL)
+			if (vol->UNC == NULL) {
+				printk(KERN_WARNING "CIFS: no memory for UNC\n");
 				goto cifs_parse_mount_err;
-			strcpy(vol->UNC, devname);
-			if (strncmp(vol->UNC, "//", 2) == 0) {
+			}
+			strcpy(vol->UNC, string);
+
+			if (strncmp(string, "//", 2) == 0) {
 				vol->UNC[0] = '\\';
 				vol->UNC[1] = '\\';
-			} else if (strncmp(vol->UNC, "\\\\", 2) != 0) {
+			} else if (strncmp(string, "\\\\", 2) != 0) {
 				printk(KERN_WARNING "CIFS: UNC Path does not "
-						    "begin with // or \\\\ \n");
+						    "begin with // or \\\\\n");
 				goto cifs_parse_mount_err;
 			}
-			value = strpbrk(vol->UNC+2, "/\\");
-			if (value)
-				*value = '\\';
-		} else {
-			printk(KERN_WARNING "CIFS: UNC name too long\n");
+
+			break;
+		case Opt_domain:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: invalid domain"
+						    " name\n");
+				goto cifs_parse_mount_err;
+			} else if (strnlen(string, 256) == 256) {
+				printk(KERN_WARNING "CIFS: domain name too"
+						    " long\n");
+				goto cifs_parse_mount_err;
+			}
+
+			vol->domainname = kstrdup(string, GFP_KERNEL);
+			if (!vol->domainname) {
+				printk(KERN_WARNING "CIFS: no memory "
+						    "for domainname\n");
+				goto cifs_parse_mount_err;
+			}
+			cFYI(1, "Domain name set");
+			break;
+		case Opt_srcaddr:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: srcaddr value not"
+						    " specified\n");
+				goto cifs_parse_mount_err;
+			} else if (!cifs_convert_address(
+					(struct sockaddr *)&vol->srcaddr,
+					string, strlen(string))) {
+				printk(KERN_WARNING "CIFS:  Could not parse"
+						    " srcaddr: %s\n", string);
+				goto cifs_parse_mount_err;
+			}
+			break;
+		case Opt_prefixpath:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: Invalid path"
+						    " prefix\n");
+				goto cifs_parse_mount_err;
+			}
+			temp_len = strnlen(string, 1024);
+			if (string[0] != '/')
+				temp_len++; /* missing leading slash */
+			if (temp_len > 1024) {
+				printk(KERN_WARNING "CIFS: prefix too long\n");
+				goto cifs_parse_mount_err;
+			}
+
+			vol->prepath = kmalloc(temp_len+1, GFP_KERNEL);
+			if (vol->prepath == NULL) {
+				printk(KERN_WARNING "CIFS: no memory "
+						    "for path prefix\n");
+				goto cifs_parse_mount_err;
+			}
+
+			if (string[0] != '/') {
+				vol->prepath[0] = '/';
+				strcpy(vol->prepath+1, string);
+			} else
+				strcpy(vol->prepath, string);
+
+			break;
+		case Opt_iocharset:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: Invalid iocharset"
+						    " specified\n");
+				goto cifs_parse_mount_err;
+			} else if (strnlen(string, 1024) >= 65) {
+				printk(KERN_WARNING "CIFS: iocharset name "
+						    "too long.\n");
+				goto cifs_parse_mount_err;
+			}
+
+			 if (strnicmp(string, "default", 7) != 0) {
+				vol->iocharset = kstrdup(string,
+							 GFP_KERNEL);
+				if (!vol->iocharset) {
+					printk(KERN_WARNING "CIFS: no memory"
+							    "for charset\n");
+					goto cifs_parse_mount_err;
+				}
+			}
+			/* if iocharset not set then load_nls_default
+			 * is used by caller
+			 */
+			cFYI(1, "iocharset set to %s", string);
+			break;
+		case Opt_sockopt:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: No socket option"
+						    " specified\n");
+				goto cifs_parse_mount_err;
+			}
+			if (strnicmp(string, "TCP_NODELAY", 11) == 0)
+				vol->sockopt_tcp_nodelay = 1;
+			break;
+		case Opt_netbiosname:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: Invalid (empty)"
+						    " netbiosname\n");
+				break;
+			}
+
+			memset(vol->source_rfc1001_name, 0x20,
+				RFC1001_NAME_LEN);
+			/*
+			 * FIXME: are there cases in which a comma can
+			 * be valid in workstation netbios name (and
+			 * need special handling)?
+			 */
+			for (i = 0; i < RFC1001_NAME_LEN; i++) {
+				/* don't ucase netbiosname for user */
+				if (string[i] == 0)
+					break;
+				vol->source_rfc1001_name[i] = string[i];
+			}
+			/* The string has 16th byte zero still from
+			 * set at top of the function
+			 */
+			if (i == RFC1001_NAME_LEN && string[i] != 0)
+				printk(KERN_WARNING "CIFS: netbiosname"
+				       " longer than 15 truncated.\n");
+
+			break;
+		case Opt_servern:
+			/* servernetbiosname specified override *SMBSERVER */
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: Empty server"
+					" netbiosname specified\n");
+				break;
+			}
+			/* last byte, type, is 0x20 for servr type */
+			memset(vol->target_rfc1001_name, 0x20,
+				RFC1001_NAME_LEN_WITH_NULL);
+
+			/* BB are there cases in which a comma can be
+			   valid in this workstation netbios name
+			   (and need special handling)? */
+
+			/* user or mount helper must uppercase the
+			   netbios name */
+			for (i = 0; i < 15; i++) {
+				if (string[i] == 0)
+					break;
+				vol->target_rfc1001_name[i] = string[i];
+			}
+			/* The string has 16th byte zero still from
+			   set at top of the function  */
+			if (i == RFC1001_NAME_LEN && string[i] != 0)
+				printk(KERN_WARNING "CIFS: server net"
+				       "biosname longer than 15 truncated.\n");
+			break;
+		case Opt_ver:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				cERROR(1, "no protocol version specified"
+					  " after vers= mount option");
+				goto cifs_parse_mount_err;
+			}
+
+			if (strnicmp(string, "cifs", 4) == 0 ||
+			    strnicmp(string, "1", 1) == 0) {
+				/* This is the default */
+				break;
+			}
+			/* For all other value, error */
+			printk(KERN_WARNING "CIFS: Invalid version"
+					    " specified\n");
 			goto cifs_parse_mount_err;
+		case Opt_sec:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+
+			if (!*string) {
+				printk(KERN_WARNING "CIFS: no security flavor"
+						    " specified\n");
+				break;
+			}
+
+			if (cifs_parse_security_flavors(string, vol) != 0)
+				goto cifs_parse_mount_err;
+			break;
+		default:
+			/*
+			 * An option we don't recognize. Save it off for later
+			 * if we haven't already found one
+			 */
+			if (!invalid)
+				invalid = data;
+			break;
 		}
+		/* Free up any allocated string */
+		kfree(string);
+		string = NULL;
+	}
+
+	if (!sloppy && invalid) {
+		printk(KERN_ERR "CIFS: Unknown mount option \"%s\"\n", invalid);
+		goto cifs_parse_mount_err;
 	}
 
 #ifndef CONFIG_KEYS
@@ -1625,7 +1923,10 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 	kfree(mountdata_copy);
 	return 0;
 
+out_nomem:
+	printk(KERN_WARNING "Could not allocate temporary buffer\n");
 cifs_parse_mount_err:
+	kfree(string);
 	kfree(mountdata_copy);
 	return 1;
 }
@@ -1977,7 +2278,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	cifs_fscache_get_client_cookie(tcp_ses);
 
 	/* queue echo request delayed work */
-	queue_delayed_work(system_nrt_wq, &tcp_ses->echo, SMB_ECHO_INTERVAL);
+	queue_delayed_work(cifsiod_wq, &tcp_ses->echo, SMB_ECHO_INTERVAL);
 
 	return tcp_ses;
 
@@ -3543,7 +3844,7 @@ remote_path_check:
 	tlink_rb_insert(&cifs_sb->tlink_tree, tlink);
 	spin_unlock(&cifs_sb->tlink_tree_lock);
 
-	queue_delayed_work(system_nrt_wq, &cifs_sb->prune_tlinks,
+	queue_delayed_work(cifsiod_wq, &cifs_sb->prune_tlinks,
 				TLINK_IDLE_EXPIRE);
 
 mount_fail_check:
@@ -4097,6 +4398,6 @@ cifs_prune_tlinks(struct work_struct *work)
 	}
 	spin_unlock(&cifs_sb->tlink_tree_lock);
 
-	queue_delayed_work(system_nrt_wq, &cifs_sb->prune_tlinks,
+	queue_delayed_work(cifsiod_wq, &cifs_sb->prune_tlinks,
 				TLINK_IDLE_EXPIRE);
 }
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 159fcc56dc2d..fae765dac934 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -835,13 +835,21 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 	if ((flock->fl_flags & FL_POSIX) == 0)
 		return rc;
 
+try_again:
 	mutex_lock(&cinode->lock_mutex);
 	if (!cinode->can_cache_brlcks) {
 		mutex_unlock(&cinode->lock_mutex);
 		return rc;
 	}
-	rc = posix_lock_file_wait(file, flock);
+
+	rc = posix_lock_file(file, flock, NULL);
 	mutex_unlock(&cinode->lock_mutex);
+	if (rc == FILE_LOCK_DEFERRED) {
+		rc = wait_event_interruptible(flock->fl_wait, !flock->fl_next);
+		if (!rc)
+			goto try_again;
+		locks_delete_block(flock);
+	}
 	return rc;
 }
 
@@ -1399,7 +1407,10 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 	return rc;
 }
 
-/* update the file size (if needed) after a write */
+/*
+ * update the file size (if needed) after a write. Should be called with
+ * the inode->i_lock held
+ */
 void
 cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
 		      unsigned int bytes_written)
@@ -1471,7 +1482,9 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file, __u32 pid,
 				return rc;
 			}
 		} else {
+			spin_lock(&dentry->d_inode->i_lock);
 			cifs_update_eof(cifsi, *poffset, bytes_written);
+			spin_unlock(&dentry->d_inode->i_lock);
 			*poffset += bytes_written;
 		}
 	}
@@ -1648,6 +1661,27 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
 	return rc;
 }
 
+/*
+ * Marshal up the iov array, reserving the first one for the header. Also,
+ * set wdata->bytes.
+ */
+static void
+cifs_writepages_marshal_iov(struct kvec *iov, struct cifs_writedata *wdata)
+{
+	int i;
+	struct inode *inode = wdata->cfile->dentry->d_inode;
+	loff_t size = i_size_read(inode);
+
+	/* marshal up the pages into iov array */
+	wdata->bytes = 0;
+	for (i = 0; i < wdata->nr_pages; i++) {
+		iov[i + 1].iov_len = min(size - page_offset(wdata->pages[i]),
+					(loff_t)PAGE_CACHE_SIZE);
+		iov[i + 1].iov_base = kmap(wdata->pages[i]);
+		wdata->bytes += iov[i + 1].iov_len;
+	}
+}
+
 static int cifs_writepages(struct address_space *mapping,
 			   struct writeback_control *wbc)
 {
@@ -1684,7 +1718,8 @@ retry:
 		tofind = min((cifs_sb->wsize / PAGE_CACHE_SIZE) - 1,
 				end - index) + 1;
 
-		wdata = cifs_writedata_alloc((unsigned int)tofind);
+		wdata = cifs_writedata_alloc((unsigned int)tofind,
+					     cifs_writev_complete);
 		if (!wdata) {
 			rc = -ENOMEM;
 			break;
@@ -1791,6 +1826,7 @@ retry:
 		wdata->sync_mode = wbc->sync_mode;
 		wdata->nr_pages = nr_pages;
 		wdata->offset = page_offset(wdata->pages[0]);
+		wdata->marshal_iov = cifs_writepages_marshal_iov;
 
 		do {
 			if (wdata->cfile != NULL)
@@ -1802,6 +1838,7 @@ retry:
 				rc = -EBADF;
 				break;
 			}
+			wdata->pid = wdata->cfile->pid;
 			rc = cifs_async_writev(wdata);
 		} while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN);
 
@@ -2043,7 +2080,7 @@ cifs_write_allocate_pages(struct page **pages, unsigned long num_pages)
 	unsigned long i;
 
 	for (i = 0; i < num_pages; i++) {
-		pages[i] = alloc_page(__GFP_HIGHMEM);
+		pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
 		if (!pages[i]) {
 			/*
 			 * save number of pages we have already allocated and
@@ -2051,15 +2088,14 @@ cifs_write_allocate_pages(struct page **pages, unsigned long num_pages)
 			 */
 			num_pages = i;
 			rc = -ENOMEM;
-			goto error;
+			break;
 		}
 	}
 
-	return rc;
-
-error:
-	for (i = 0; i < num_pages; i++)
-		put_page(pages[i]);
+	if (rc) {
+		for (i = 0; i < num_pages; i++)
+			put_page(pages[i]);
+	}
 	return rc;
 }
 
@@ -2070,9 +2106,7 @@ size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len)
 	size_t clen;
 
 	clen = min_t(const size_t, len, wsize);
-	num_pages = clen / PAGE_CACHE_SIZE;
-	if (clen % PAGE_CACHE_SIZE)
-		num_pages++;
+	num_pages = DIV_ROUND_UP(clen, PAGE_SIZE);
 
 	if (cur_len)
 		*cur_len = clen;
@@ -2080,24 +2114,79 @@ size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len)
 	return num_pages;
 }
 
+static void
+cifs_uncached_marshal_iov(struct kvec *iov, struct cifs_writedata *wdata)
+{
+	int i;
+	size_t bytes = wdata->bytes;
+
+	/* marshal up the pages into iov array */
+	for (i = 0; i < wdata->nr_pages; i++) {
+		iov[i + 1].iov_len = min_t(size_t, bytes, PAGE_SIZE);
+		iov[i + 1].iov_base = kmap(wdata->pages[i]);
+		bytes -= iov[i + 1].iov_len;
+	}
+}
+
+static void
+cifs_uncached_writev_complete(struct work_struct *work)
+{
+	int i;
+	struct cifs_writedata *wdata = container_of(work,
+					struct cifs_writedata, work);
+	struct inode *inode = wdata->cfile->dentry->d_inode;
+	struct cifsInodeInfo *cifsi = CIFS_I(inode);
+
+	spin_lock(&inode->i_lock);
+	cifs_update_eof(cifsi, wdata->offset, wdata->bytes);
+	if (cifsi->server_eof > inode->i_size)
+		i_size_write(inode, cifsi->server_eof);
+	spin_unlock(&inode->i_lock);
+
+	complete(&wdata->done);
+
+	if (wdata->result != -EAGAIN) {
+		for (i = 0; i < wdata->nr_pages; i++)
+			put_page(wdata->pages[i]);
+	}
+
+	kref_put(&wdata->refcount, cifs_writedata_release);
+}
+
+/* attempt to send write to server, retry on any -EAGAIN errors */
+static int
+cifs_uncached_retry_writev(struct cifs_writedata *wdata)
+{
+	int rc;
+
+	do {
+		if (wdata->cfile->invalidHandle) {
+			rc = cifs_reopen_file(wdata->cfile, false);
+			if (rc != 0)
+				continue;
+		}
+		rc = cifs_async_writev(wdata);
+	} while (rc == -EAGAIN);
+
+	return rc;
+}
+
 static ssize_t
 cifs_iovec_write(struct file *file, const struct iovec *iov,
 		 unsigned long nr_segs, loff_t *poffset)
 {
-	unsigned int written;
-	unsigned long num_pages, npages, i;
+	unsigned long nr_pages, i;
 	size_t copied, len, cur_len;
 	ssize_t total_written = 0;
-	struct kvec *to_send;
-	struct page **pages;
+	loff_t offset = *poffset;
 	struct iov_iter it;
-	struct inode *inode;
 	struct cifsFileInfo *open_file;
-	struct cifs_tcon *pTcon;
+	struct cifs_tcon *tcon;
 	struct cifs_sb_info *cifs_sb;
-	struct cifs_io_parms io_parms;
-	int xid, rc;
-	__u32 pid;
+	struct cifs_writedata *wdata, *tmp;
+	struct list_head wdata_list;
+	int rc;
+	pid_t pid;
 
 	len = iov_length(iov, nr_segs);
 	if (!len)
@@ -2107,103 +2196,103 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 	if (rc)
 		return rc;
 
+	INIT_LIST_HEAD(&wdata_list);
 	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
-	num_pages = get_numpages(cifs_sb->wsize, len, &cur_len);
-
-	pages = kmalloc(sizeof(struct pages *)*num_pages, GFP_KERNEL);
-	if (!pages)
-		return -ENOMEM;
-
-	to_send = kmalloc(sizeof(struct kvec)*(num_pages + 1), GFP_KERNEL);
-	if (!to_send) {
-		kfree(pages);
-		return -ENOMEM;
-	}
-
-	rc = cifs_write_allocate_pages(pages, num_pages);
-	if (rc) {
-		kfree(pages);
-		kfree(to_send);
-		return rc;
-	}
-
-	xid = GetXid();
 	open_file = file->private_data;
+	tcon = tlink_tcon(open_file->tlink);
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
 		pid = open_file->pid;
 	else
 		pid = current->tgid;
 
-	pTcon = tlink_tcon(open_file->tlink);
-	inode = file->f_path.dentry->d_inode;
-
 	iov_iter_init(&it, iov, nr_segs, len, 0);
-	npages = num_pages;
-
 	do {
-		size_t save_len = cur_len;
-		for (i = 0; i < npages; i++) {
-			copied = min_t(const size_t, cur_len, PAGE_CACHE_SIZE);
-			copied = iov_iter_copy_from_user(pages[i], &it, 0,
-							 copied);
+		size_t save_len;
+
+		nr_pages = get_numpages(cifs_sb->wsize, len, &cur_len);
+		wdata = cifs_writedata_alloc(nr_pages,
+					     cifs_uncached_writev_complete);
+		if (!wdata) {
+			rc = -ENOMEM;
+			break;
+		}
+
+		rc = cifs_write_allocate_pages(wdata->pages, nr_pages);
+		if (rc) {
+			kfree(wdata);
+			break;
+		}
+
+		save_len = cur_len;
+		for (i = 0; i < nr_pages; i++) {
+			copied = min_t(const size_t, cur_len, PAGE_SIZE);
+			copied = iov_iter_copy_from_user(wdata->pages[i], &it,
+							 0, copied);
 			cur_len -= copied;
 			iov_iter_advance(&it, copied);
-			to_send[i+1].iov_base = kmap(pages[i]);
-			to_send[i+1].iov_len = copied;
 		}
-
 		cur_len = save_len - cur_len;
 
-		do {
-			if (open_file->invalidHandle) {
-				rc = cifs_reopen_file(open_file, false);
-				if (rc != 0)
-					break;
-			}
-			io_parms.netfid = open_file->netfid;
-			io_parms.pid = pid;
-			io_parms.tcon = pTcon;
-			io_parms.offset = *poffset;
-			io_parms.length = cur_len;
-			rc = CIFSSMBWrite2(xid, &io_parms, &written, to_send,
-					   npages, 0);
-		} while (rc == -EAGAIN);
-
-		for (i = 0; i < npages; i++)
-			kunmap(pages[i]);
-
-		if (written) {
-			len -= written;
-			total_written += written;
-			cifs_update_eof(CIFS_I(inode), *poffset, written);
-			*poffset += written;
-		} else if (rc < 0) {
-			if (!total_written)
-				total_written = rc;
+		wdata->sync_mode = WB_SYNC_ALL;
+		wdata->nr_pages = nr_pages;
+		wdata->offset = (__u64)offset;
+		wdata->cfile = cifsFileInfo_get(open_file);
+		wdata->pid = pid;
+		wdata->bytes = cur_len;
+		wdata->marshal_iov = cifs_uncached_marshal_iov;
+		rc = cifs_uncached_retry_writev(wdata);
+		if (rc) {
+			kref_put(&wdata->refcount, cifs_writedata_release);
 			break;
 		}
 
-		/* get length and number of kvecs of the next write */
-		npages = get_numpages(cifs_sb->wsize, len, &cur_len);
+		list_add_tail(&wdata->list, &wdata_list);
+		offset += cur_len;
+		len -= cur_len;
 	} while (len > 0);
 
-	if (total_written > 0) {
-		spin_lock(&inode->i_lock);
-		if (*poffset > inode->i_size)
-			i_size_write(inode, *poffset);
-		spin_unlock(&inode->i_lock);
+	/*
+	 * If at least one write was successfully sent, then discard any rc
+	 * value from the later writes. If the other write succeeds, then
+	 * we'll end up returning whatever was written. If it fails, then
+	 * we'll get a new rc value from that.
+	 */
+	if (!list_empty(&wdata_list))
+		rc = 0;
+
+	/*
+	 * Wait for and collect replies for any successful sends in order of
+	 * increasing offset. Once an error is hit or we get a fatal signal
+	 * while waiting, then return without waiting for any more replies.
+	 */
+restart_loop:
+	list_for_each_entry_safe(wdata, tmp, &wdata_list, list) {
+		if (!rc) {
+			/* FIXME: freezable too? */
+			rc = wait_for_completion_killable(&wdata->done);
+			if (rc)
+				rc = -EINTR;
+			else if (wdata->result)
+				rc = wdata->result;
+			else
+				total_written += wdata->bytes;
+
+			/* resend call if it's a retryable error */
+			if (rc == -EAGAIN) {
+				rc = cifs_uncached_retry_writev(wdata);
+				goto restart_loop;
+			}
+		}
+		list_del_init(&wdata->list);
+		kref_put(&wdata->refcount, cifs_writedata_release);
 	}
 
-	cifs_stats_bytes_written(pTcon, total_written);
-	mark_inode_dirty_sync(inode);
+	if (total_written > 0)
+		*poffset += total_written;
 
-	for (i = 0; i < num_pages; i++)
-		put_page(pages[i]);
-	kfree(to_send);
-	kfree(pages);
-	FreeXid(xid);
-	return total_written;
+	cifs_stats_bytes_written(tcon, total_written);
+	return total_written ? total_written : (ssize_t)rc;
 }
 
 ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index c273c12de98e..c29d1aa2c54f 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -213,55 +213,62 @@ cifs_small_buf_release(void *buf_to_free)
 }
 
 /*
-	Find a free multiplex id (SMB mid). Otherwise there could be
-	mid collisions which might cause problems, demultiplexing the
-	wrong response to this request. Multiplex ids could collide if
-	one of a series requests takes much longer than the others, or
-	if a very large number of long lived requests (byte range
-	locks or FindNotify requests) are pending.  No more than
-	64K-1 requests can be outstanding at one time.  If no
-	mids are available, return zero.  A future optimization
-	could make the combination of mids and uid the key we use
-	to demultiplex on (rather than mid alone).
-	In addition to the above check, the cifs demultiplex
-	code already used the command code as a secondary
-	check of the frame and if signing is negotiated the
-	response would be discarded if the mid were the same
-	but the signature was wrong.  Since the mid is not put in the
-	pending queue until later (when it is about to be dispatched)
-	we do have to limit the number of outstanding requests
-	to somewhat less than 64K-1 although it is hard to imagine
-	so many threads being in the vfs at one time.
-*/
-__u16 GetNextMid(struct TCP_Server_Info *server)
+ * Find a free multiplex id (SMB mid). Otherwise there could be
+ * mid collisions which might cause problems, demultiplexing the
+ * wrong response to this request. Multiplex ids could collide if
+ * one of a series requests takes much longer than the others, or
+ * if a very large number of long lived requests (byte range
+ * locks or FindNotify requests) are pending. No more than
+ * 64K-1 requests can be outstanding at one time. If no
+ * mids are available, return zero. A future optimization
+ * could make the combination of mids and uid the key we use
+ * to demultiplex on (rather than mid alone).
+ * In addition to the above check, the cifs demultiplex
+ * code already used the command code as a secondary
+ * check of the frame and if signing is negotiated the
+ * response would be discarded if the mid were the same
+ * but the signature was wrong. Since the mid is not put in the
+ * pending queue until later (when it is about to be dispatched)
+ * we do have to limit the number of outstanding requests
+ * to somewhat less than 64K-1 although it is hard to imagine
+ * so many threads being in the vfs at one time.
+ */
+__u64 GetNextMid(struct TCP_Server_Info *server)
 {
-	__u16 mid = 0;
-	__u16 last_mid;
+	__u64 mid = 0;
+	__u16 last_mid, cur_mid;
 	bool collision;
 
 	spin_lock(&GlobalMid_Lock);
-	last_mid = server->CurrentMid; /* we do not want to loop forever */
-	server->CurrentMid++;
-	/* This nested loop looks more expensive than it is.
-	In practice the list of pending requests is short,
-	fewer than 50, and the mids are likely to be unique
-	on the first pass through the loop unless some request
-	takes longer than the 64 thousand requests before it
-	(and it would also have to have been a request that
-	 did not time out) */
-	while (server->CurrentMid != last_mid) {
+
+	/* mid is 16 bit only for CIFS/SMB */
+	cur_mid = (__u16)((server->CurrentMid) & 0xffff);
+	/* we do not want to loop forever */
+	last_mid = cur_mid;
+	cur_mid++;
+
+	/*
+	 * This nested loop looks more expensive than it is.
+	 * In practice the list of pending requests is short,
+	 * fewer than 50, and the mids are likely to be unique
+	 * on the first pass through the loop unless some request
+	 * takes longer than the 64 thousand requests before it
+	 * (and it would also have to have been a request that
+	 * did not time out).
+	 */
+	while (cur_mid != last_mid) {
 		struct mid_q_entry *mid_entry;
 		unsigned int num_mids;
 
 		collision = false;
-		if (server->CurrentMid == 0)
-			server->CurrentMid++;
+		if (cur_mid == 0)
+			cur_mid++;
 
 		num_mids = 0;
 		list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) {
 			++num_mids;
-			if (mid_entry->mid == server->CurrentMid &&
-			    mid_entry->midState == MID_REQUEST_SUBMITTED) {
+			if (mid_entry->mid == cur_mid &&
+			    mid_entry->mid_state == MID_REQUEST_SUBMITTED) {
 				/* This mid is in use, try a different one */
 				collision = true;
 				break;
@@ -282,10 +289,11 @@ __u16 GetNextMid(struct TCP_Server_Info *server)
 			server->tcpStatus = CifsNeedReconnect;
 
 		if (!collision) {
-			mid = server->CurrentMid;
+			mid = (__u64)cur_mid;
+			server->CurrentMid = mid;
 			break;
 		}
-		server->CurrentMid++;
+		cur_mid++;
 	}
 	spin_unlock(&GlobalMid_Lock);
 	return mid;
@@ -420,8 +428,10 @@ check_smb_hdr(struct smb_hdr *smb, __u16 mid)
 }
 
 int
-checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int total_read)
+checkSMB(char *buf, unsigned int total_read)
 {
+	struct smb_hdr *smb = (struct smb_hdr *)buf;
+	__u16 mid = smb->Mid;
 	__u32 rfclen = be32_to_cpu(smb->smb_buf_length);
 	__u32 clc_len;  /* calculated length */
 	cFYI(0, "checkSMB Length: 0x%x, smb_buf_length: 0x%x",
@@ -502,8 +512,9 @@ checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int total_read)
 }
 
 bool
-is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
+is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
 {
+	struct smb_hdr *buf = (struct smb_hdr *)buffer;
 	struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)buf;
 	struct list_head *tmp, *tmp1, *tmp2;
 	struct cifs_ses *ses;
@@ -584,7 +595,7 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
 
 				cifs_set_oplock_level(pCifsInode,
 					pSMB->OplockLevel ? OPLOCK_READ : 0);
-				queue_work(system_nrt_wq,
+				queue_work(cifsiod_wq,
 					   &netfile->oplock_break);
 				netfile->oplock_break_cancelled = false;
 
@@ -604,16 +615,15 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
 }
 
 void
-dump_smb(struct smb_hdr *smb_buf, int smb_buf_length)
+dump_smb(void *buf, int smb_buf_length)
 {
 	int i, j;
 	char debug_line[17];
-	unsigned char *buffer;
+	unsigned char *buffer = buf;
 
 	if (traceSMB == 0)
 		return;
 
-	buffer = (unsigned char *) smb_buf;
 	for (i = 0, j = 0; i < smb_buf_length; i++, j++) {
 		if (i % 8 == 0) {
 			/* have reached the beginning of line */
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 73e47e84b61a..581c225f7f50 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -197,8 +197,7 @@ cifs_convert_address(struct sockaddr *dst, const char *src, int len)
 		memcpy(scope_id, pct + 1, slen);
 		scope_id[slen] = '\0';
 
-		rc = strict_strtoul(scope_id, 0,
-					(unsigned long *)&s6->sin6_scope_id);
+		rc = kstrtouint(scope_id, 0, &s6->sin6_scope_id);
 		rc = (rc == 0) ? 1 : 0;
 	}
 
@@ -836,8 +835,9 @@ ntstatus_to_dos(__u32 ntstatus, __u8 *eclass, __u16 *ecode)
 }
 
 int
-map_smb_to_linux_error(struct smb_hdr *smb, bool logErr)
+map_smb_to_linux_error(char *buf, bool logErr)
 {
+	struct smb_hdr *smb = (struct smb_hdr *)buf;
 	unsigned int i;
 	int rc = -EIO;	/* if transport error smb error may not be set */
 	__u8 smberrclass;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 310918b6fcb4..0961336513d5 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -60,8 +60,8 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 		memset(temp, 0, sizeof(struct mid_q_entry));
 		temp->mid = smb_buffer->Mid;	/* always LE */
 		temp->pid = current->pid;
-		temp->command = smb_buffer->Command;
-		cFYI(1, "For smb_command %d", temp->command);
+		temp->command = cpu_to_le16(smb_buffer->Command);
+		cFYI(1, "For smb_command %d", smb_buffer->Command);
 	/*	do_gettimeofday(&temp->when_sent);*/ /* easier to use jiffies */
 		/* when mid allocated can be before when sent */
 		temp->when_alloc = jiffies;
@@ -75,7 +75,7 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 	}
 
 	atomic_inc(&midCount);
-	temp->midState = MID_REQUEST_ALLOCATED;
+	temp->mid_state = MID_REQUEST_ALLOCATED;
 	return temp;
 }
 
@@ -85,9 +85,9 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 #ifdef CONFIG_CIFS_STATS2
 	unsigned long now;
 #endif
-	midEntry->midState = MID_FREE;
+	midEntry->mid_state = MID_FREE;
 	atomic_dec(&midCount);
-	if (midEntry->largeBuf)
+	if (midEntry->large_buf)
 		cifs_buf_release(midEntry->resp_buf);
 	else
 		cifs_small_buf_release(midEntry->resp_buf);
@@ -97,8 +97,8 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 	   something is wrong, unless it is quite a slow link or server */
 	if ((now - midEntry->when_alloc) > HZ) {
 		if ((cifsFYI & CIFS_TIMER) &&
-		   (midEntry->command != SMB_COM_LOCKING_ANDX)) {
-			printk(KERN_DEBUG " CIFS slow rsp: cmd %d mid %d",
+		    (midEntry->command != cpu_to_le16(SMB_COM_LOCKING_ANDX))) {
+			printk(KERN_DEBUG " CIFS slow rsp: cmd %d mid %llu",
 			       midEntry->command, midEntry->mid);
 			printk(" A: 0x%lx S: 0x%lx R: 0x%lx\n",
 			       now - midEntry->when_alloc,
@@ -126,11 +126,11 @@ smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
 	int rc = 0;
 	int i = 0;
 	struct msghdr smb_msg;
-	struct smb_hdr *smb_buffer = iov[0].iov_base;
+	__be32 *buf_len = (__be32 *)(iov[0].iov_base);
 	unsigned int len = iov[0].iov_len;
 	unsigned int total_len;
 	int first_vec = 0;
-	unsigned int smb_buf_length = be32_to_cpu(smb_buffer->smb_buf_length);
+	unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base);
 	struct socket *ssocket = server->ssocket;
 
 	if (ssocket == NULL)
@@ -150,7 +150,7 @@ smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
 		total_len += iov[i].iov_len;
 
 	cFYI(1, "Sending smb:  total_len %d", total_len);
-	dump_smb(smb_buffer, len);
+	dump_smb(iov[0].iov_base, len);
 
 	i = 0;
 	while (total_len) {
@@ -158,24 +158,24 @@ smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
 				    n_vec - first_vec, total_len);
 		if ((rc == -ENOSPC) || (rc == -EAGAIN)) {
 			i++;
-			/* if blocking send we try 3 times, since each can block
-			   for 5 seconds. For nonblocking  we have to try more
-			   but wait increasing amounts of time allowing time for
-			   socket to clear.  The overall time we wait in either
-			   case to send on the socket is about 15 seconds.
-			   Similarly we wait for 15 seconds for
-			   a response from the server in SendReceive[2]
-			   for the server to send a response back for
-			   most types of requests (except SMB Write
-			   past end of file which can be slow, and
-			   blocking lock operations). NFS waits slightly longer
-			   than CIFS, but this can make it take longer for
-			   nonresponsive servers to be detected and 15 seconds
-			   is more than enough time for modern networks to
-			   send a packet.  In most cases if we fail to send
-			   after the retries we will kill the socket and
-			   reconnect which may clear the network problem.
-			*/
+			/*
+			 * If blocking send we try 3 times, since each can block
+			 * for 5 seconds. For nonblocking  we have to try more
+			 * but wait increasing amounts of time allowing time for
+			 * socket to clear.  The overall time we wait in either
+			 * case to send on the socket is about 15 seconds.
+			 * Similarly we wait for 15 seconds for a response from
+			 * the server in SendReceive[2] for the server to send
+			 * a response back for most types of requests (except
+			 * SMB Write past end of file which can be slow, and
+			 * blocking lock operations). NFS waits slightly longer
+			 * than CIFS, but this can make it take longer for
+			 * nonresponsive servers to be detected and 15 seconds
+			 * is more than enough time for modern networks to
+			 * send a packet.  In most cases if we fail to send
+			 * after the retries we will kill the socket and
+			 * reconnect which may clear the network problem.
+			 */
 			if ((i >= 14) || (!server->noblocksnd && (i > 2))) {
 				cERROR(1, "sends on sock %p stuck for 15 seconds",
 				    ssocket);
@@ -235,9 +235,8 @@ smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
 	else
 		rc = 0;
 
-	/* Don't want to modify the buffer as a
-	   side effect of this call. */
-	smb_buffer->smb_buf_length = cpu_to_be32(smb_buf_length);
+	/* Don't want to modify the buffer as a side effect of this call. */
+	*buf_len = cpu_to_be32(smb_buf_length);
 
 	return rc;
 }
@@ -342,13 +341,40 @@ wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ)
 	int error;
 
 	error = wait_event_freezekillable(server->response_q,
-				    midQ->midState != MID_REQUEST_SUBMITTED);
+				    midQ->mid_state != MID_REQUEST_SUBMITTED);
 	if (error < 0)
 		return -ERESTARTSYS;
 
 	return 0;
 }
 
+static int
+cifs_setup_async_request(struct TCP_Server_Info *server, struct kvec *iov,
+			 unsigned int nvec, struct mid_q_entry **ret_mid)
+{
+	int rc;
+	struct smb_hdr *hdr = (struct smb_hdr *)iov[0].iov_base;
+	struct mid_q_entry *mid;
+
+	/* enable signing if server requires it */
+	if (server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
+		hdr->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
+
+	mid = AllocMidQEntry(hdr, server);
+	if (mid == NULL)
+		return -ENOMEM;
+
+	/* put it on the pending_mid_q */
+	spin_lock(&GlobalMid_Lock);
+	list_add_tail(&mid->qhead, &server->pending_mid_q);
+	spin_unlock(&GlobalMid_Lock);
+
+	rc = cifs_sign_smb2(iov, nvec, server, &mid->sequence_number);
+	if (rc)
+		delete_mid(mid);
+	*ret_mid = mid;
+	return rc;
+}
 
 /*
  * Send a SMB request and set the callback function in the mid to handle
@@ -361,40 +387,24 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov,
 {
 	int rc;
 	struct mid_q_entry *mid;
-	struct smb_hdr *hdr = (struct smb_hdr *)iov[0].iov_base;
 
 	rc = wait_for_free_request(server, ignore_pend ? CIFS_ASYNC_OP : 0);
 	if (rc)
 		return rc;
 
-	/* enable signing if server requires it */
-	if (server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
-		hdr->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
-
 	mutex_lock(&server->srv_mutex);
-	mid = AllocMidQEntry(hdr, server);
-	if (mid == NULL) {
+	rc = cifs_setup_async_request(server, iov, nvec, &mid);
+	if (rc) {
 		mutex_unlock(&server->srv_mutex);
 		cifs_add_credits(server, 1);
 		wake_up(&server->request_q);
-		return -ENOMEM;
-	}
-
-	/* put it on the pending_mid_q */
-	spin_lock(&GlobalMid_Lock);
-	list_add_tail(&mid->qhead, &server->pending_mid_q);
-	spin_unlock(&GlobalMid_Lock);
-
-	rc = cifs_sign_smb2(iov, nvec, server, &mid->sequence_number);
-	if (rc) {
-		mutex_unlock(&server->srv_mutex);
-		goto out_err;
+		return rc;
 	}
 
 	mid->receive = receive;
 	mid->callback = callback;
 	mid->callback_data = cbdata;
-	mid->midState = MID_REQUEST_SUBMITTED;
+	mid->mid_state = MID_REQUEST_SUBMITTED;
 
 	cifs_in_send_inc(server);
 	rc = smb_sendv(server, iov, nvec);
@@ -424,14 +434,14 @@ out_err:
  */
 int
 SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses,
-		struct smb_hdr *in_buf, int flags)
+		 char *in_buf, int flags)
 {
 	int rc;
 	struct kvec iov[1];
 	int resp_buf_type;
 
-	iov[0].iov_base = (char *)in_buf;
-	iov[0].iov_len = be32_to_cpu(in_buf->smb_buf_length) + 4;
+	iov[0].iov_base = in_buf;
+	iov[0].iov_len = get_rfc1002_length(in_buf) + 4;
 	flags |= CIFS_NO_RESP;
 	rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags);
 	cFYI(DBG2, "SendRcvNoRsp flags %d rc %d", flags, rc);
@@ -444,11 +454,11 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
 {
 	int rc = 0;
 
-	cFYI(1, "%s: cmd=%d mid=%d state=%d", __func__, mid->command,
-		mid->mid, mid->midState);
+	cFYI(1, "%s: cmd=%d mid=%llu state=%d", __func__,
+	     le16_to_cpu(mid->command), mid->mid, mid->mid_state);
 
 	spin_lock(&GlobalMid_Lock);
-	switch (mid->midState) {
+	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
 		spin_unlock(&GlobalMid_Lock);
 		return rc;
@@ -463,8 +473,8 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
 		break;
 	default:
 		list_del_init(&mid->qhead);
-		cERROR(1, "%s: invalid mid state mid=%d state=%d", __func__,
-			mid->mid, mid->midState);
+		cERROR(1, "%s: invalid mid state mid=%llu state=%d", __func__,
+		       mid->mid, mid->mid_state);
 		rc = -EIO;
 	}
 	spin_unlock(&GlobalMid_Lock);
@@ -514,7 +524,7 @@ int
 cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 		   bool log_error)
 {
-	unsigned int len = be32_to_cpu(mid->resp_buf->smb_buf_length) + 4;
+	unsigned int len = get_rfc1002_length(mid->resp_buf) + 4;
 
 	dump_smb(mid->resp_buf, min_t(u32, 92, len));
 
@@ -534,6 +544,24 @@ cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 	return map_smb_to_linux_error(mid->resp_buf, log_error);
 }
 
+static int
+cifs_setup_request(struct cifs_ses *ses, struct kvec *iov,
+		   unsigned int nvec, struct mid_q_entry **ret_mid)
+{
+	int rc;
+	struct smb_hdr *hdr = (struct smb_hdr *)iov[0].iov_base;
+	struct mid_q_entry *mid;
+
+	rc = allocate_mid(ses, hdr, &mid);
+	if (rc)
+		return rc;
+	rc = cifs_sign_smb2(iov, nvec, ses->server, &mid->sequence_number);
+	if (rc)
+		delete_mid(mid);
+	*ret_mid = mid;
+	return rc;
+}
+
 int
 SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	     struct kvec *iov, int n_vec, int *pRespBufType /* ret */,
@@ -542,55 +570,53 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	int rc = 0;
 	int long_op;
 	struct mid_q_entry *midQ;
-	struct smb_hdr *in_buf = iov[0].iov_base;
+	char *buf = iov[0].iov_base;
 
 	long_op = flags & CIFS_TIMEOUT_MASK;
 
 	*pRespBufType = CIFS_NO_BUFFER;  /* no response buf yet */
 
 	if ((ses == NULL) || (ses->server == NULL)) {
-		cifs_small_buf_release(in_buf);
+		cifs_small_buf_release(buf);
 		cERROR(1, "Null session");
 		return -EIO;
 	}
 
 	if (ses->server->tcpStatus == CifsExiting) {
-		cifs_small_buf_release(in_buf);
+		cifs_small_buf_release(buf);
 		return -ENOENT;
 	}
 
-	/* Ensure that we do not send more than 50 overlapping requests
-	   to the same server. We may make this configurable later or
-	   use ses->maxReq */
+	/*
+	 * Ensure that we do not send more than 50 overlapping requests
+	 * to the same server. We may make this configurable later or
+	 * use ses->maxReq.
+	 */
 
 	rc = wait_for_free_request(ses->server, long_op);
 	if (rc) {
-		cifs_small_buf_release(in_buf);
+		cifs_small_buf_release(buf);
 		return rc;
 	}
 
-	/* make sure that we sign in the same order that we send on this socket
-	   and avoid races inside tcp sendmsg code that could cause corruption
-	   of smb data */
+	/*
+	 * Make sure that we sign in the same order that we send on this socket
+	 * and avoid races inside tcp sendmsg code that could cause corruption
+	 * of smb data.
+	 */
 
 	mutex_lock(&ses->server->srv_mutex);
 
-	rc = allocate_mid(ses, in_buf, &midQ);
+	rc = cifs_setup_request(ses, iov, n_vec, &midQ);
 	if (rc) {
 		mutex_unlock(&ses->server->srv_mutex);
-		cifs_small_buf_release(in_buf);
+		cifs_small_buf_release(buf);
 		/* Update # of requests on wire to server */
 		cifs_add_credits(ses->server, 1);
 		return rc;
 	}
-	rc = cifs_sign_smb2(iov, n_vec, ses->server, &midQ->sequence_number);
-	if (rc) {
-		mutex_unlock(&ses->server->srv_mutex);
-		cifs_small_buf_release(in_buf);
-		goto out;
-	}
 
-	midQ->midState = MID_REQUEST_SUBMITTED;
+	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
 	rc = smb_sendv(ses->server, iov, n_vec);
 	cifs_in_send_dec(ses->server);
@@ -599,30 +625,30 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	mutex_unlock(&ses->server->srv_mutex);
 
 	if (rc < 0) {
-		cifs_small_buf_release(in_buf);
+		cifs_small_buf_release(buf);
 		goto out;
 	}
 
 	if (long_op == CIFS_ASYNC_OP) {
-		cifs_small_buf_release(in_buf);
+		cifs_small_buf_release(buf);
 		goto out;
 	}
 
 	rc = wait_for_response(ses->server, midQ);
 	if (rc != 0) {
-		send_nt_cancel(ses->server, in_buf, midQ);
+		send_nt_cancel(ses->server, (struct smb_hdr *)buf, midQ);
 		spin_lock(&GlobalMid_Lock);
-		if (midQ->midState == MID_REQUEST_SUBMITTED) {
+		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
 			midQ->callback = DeleteMidQEntry;
 			spin_unlock(&GlobalMid_Lock);
-			cifs_small_buf_release(in_buf);
+			cifs_small_buf_release(buf);
 			cifs_add_credits(ses->server, 1);
 			return rc;
 		}
 		spin_unlock(&GlobalMid_Lock);
 	}
 
-	cifs_small_buf_release(in_buf);
+	cifs_small_buf_release(buf);
 
 	rc = cifs_sync_mid_result(midQ, ses->server);
 	if (rc != 0) {
@@ -630,15 +656,16 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 		return rc;
 	}
 
-	if (!midQ->resp_buf || midQ->midState != MID_RESPONSE_RECEIVED) {
+	if (!midQ->resp_buf || midQ->mid_state != MID_RESPONSE_RECEIVED) {
 		rc = -EIO;
 		cFYI(1, "Bad MID state?");
 		goto out;
 	}
 
-	iov[0].iov_base = (char *)midQ->resp_buf;
-	iov[0].iov_len = be32_to_cpu(midQ->resp_buf->smb_buf_length) + 4;
-	if (midQ->largeBuf)
+	buf = (char *)midQ->resp_buf;
+	iov[0].iov_base = buf;
+	iov[0].iov_len = get_rfc1002_length(buf) + 4;
+	if (midQ->large_buf)
 		*pRespBufType = CIFS_LARGE_BUFFER;
 	else
 		*pRespBufType = CIFS_SMALL_BUFFER;
@@ -710,7 +737,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 		goto out;
 	}
 
-	midQ->midState = MID_REQUEST_SUBMITTED;
+	midQ->mid_state = MID_REQUEST_SUBMITTED;
 
 	cifs_in_send_inc(ses->server);
 	rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
@@ -728,7 +755,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	if (rc != 0) {
 		send_nt_cancel(ses->server, in_buf, midQ);
 		spin_lock(&GlobalMid_Lock);
-		if (midQ->midState == MID_REQUEST_SUBMITTED) {
+		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
 			/* no longer considered to be "in-flight" */
 			midQ->callback = DeleteMidQEntry;
 			spin_unlock(&GlobalMid_Lock);
@@ -745,13 +772,13 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	}
 
 	if (!midQ->resp_buf || !out_buf ||
-	    midQ->midState != MID_RESPONSE_RECEIVED) {
+	    midQ->mid_state != MID_RESPONSE_RECEIVED) {
 		rc = -EIO;
 		cERROR(1, "Bad MID state?");
 		goto out;
 	}
 
-	*pbytes_returned = be32_to_cpu(midQ->resp_buf->smb_buf_length);
+	*pbytes_returned = get_rfc1002_length(midQ->resp_buf);
 	memcpy(out_buf, midQ->resp_buf, *pbytes_returned + 4);
 	rc = cifs_check_receive(midQ, ses->server, 0);
 out:
@@ -844,7 +871,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 		return rc;
 	}
 
-	midQ->midState = MID_REQUEST_SUBMITTED;
+	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
 	rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
 	cifs_in_send_dec(ses->server);
@@ -858,13 +885,13 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 
 	/* Wait for a reply - allow signals to interrupt. */
 	rc = wait_event_interruptible(ses->server->response_q,
-		(!(midQ->midState == MID_REQUEST_SUBMITTED)) ||
+		(!(midQ->mid_state == MID_REQUEST_SUBMITTED)) ||
 		((ses->server->tcpStatus != CifsGood) &&
 		 (ses->server->tcpStatus != CifsNew)));
 
 	/* Were we interrupted by a signal ? */
 	if ((rc == -ERESTARTSYS) &&
-		(midQ->midState == MID_REQUEST_SUBMITTED) &&
+		(midQ->mid_state == MID_REQUEST_SUBMITTED) &&
 		((ses->server->tcpStatus == CifsGood) ||
 		 (ses->server->tcpStatus == CifsNew))) {
 
@@ -894,7 +921,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 		if (rc) {
 			send_nt_cancel(ses->server, in_buf, midQ);
 			spin_lock(&GlobalMid_Lock);
-			if (midQ->midState == MID_REQUEST_SUBMITTED) {
+			if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
 				/* no longer considered to be "in-flight" */
 				midQ->callback = DeleteMidQEntry;
 				spin_unlock(&GlobalMid_Lock);
@@ -912,13 +939,13 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 		return rc;
 
 	/* rcvd frame is ok */
-	if (out_buf == NULL || midQ->midState != MID_RESPONSE_RECEIVED) {
+	if (out_buf == NULL || midQ->mid_state != MID_RESPONSE_RECEIVED) {
 		rc = -EIO;
 		cERROR(1, "Bad MID state?");
 		goto out;
 	}
 
-	*pbytes_returned = be32_to_cpu(midQ->resp_buf->smb_buf_length);
+	*pbytes_returned = get_rfc1002_length(midQ->resp_buf);
 	memcpy(out_buf, midQ->resp_buf, *pbytes_returned + 4);
 	rc = cifs_check_receive(midQ, ses->server, 0);
 out:
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 05156c17b551..2870597b5c9d 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -21,7 +21,6 @@
 #include <linux/vfs.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include <linux/fs.h>
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 8f616e0e252c..761d5b31b18d 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -38,7 +38,6 @@
 #include <linux/mutex.h>
 #include <linux/device.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/poll.h>
 #include <asm/uaccess.h>
 
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index 9727e0c52579..0c68fd31fbf2 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -14,7 +14,6 @@
  * improvements to the Coda project. Contact Peter Braam <coda@cs.cmu.edu>.
  */
 
-#include <asm/system.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/types.h>
diff --git a/fs/compat.c b/fs/compat.c
index 14483a715bbb..f2944ace7a7b 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1170,10 +1170,9 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec,
 }
 
 asmlinkage ssize_t
-compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
-		  unsigned long vlen, u32 pos_low, u32 pos_high)
+compat_sys_preadv64(unsigned long fd, const struct compat_iovec __user *vec,
+		    unsigned long vlen, loff_t pos)
 {
-	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 	struct file *file;
 	int fput_needed;
 	ssize_t ret;
@@ -1190,6 +1189,14 @@ compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
 	return ret;
 }
 
+asmlinkage ssize_t
+compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
+		  unsigned long vlen, u32 pos_low, u32 pos_high)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	return compat_sys_preadv64(fd, vec, vlen, pos);
+}
+
 static size_t compat_writev(struct file *file,
 			    const struct compat_iovec __user *vec,
 			    unsigned long vlen, loff_t *pos)
@@ -1229,10 +1236,9 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec,
 }
 
 asmlinkage ssize_t
-compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
-		   unsigned long vlen, u32 pos_low, u32 pos_high)
+compat_sys_pwritev64(unsigned long fd, const struct compat_iovec __user *vec,
+		     unsigned long vlen, loff_t pos)
 {
-	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 	struct file *file;
 	int fput_needed;
 	ssize_t ret;
@@ -1249,6 +1255,14 @@ compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
 	return ret;
 }
 
+asmlinkage ssize_t
+compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
+		   unsigned long vlen, u32 pos_low, u32 pos_high)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	return compat_sys_pwritev64(fd, vec, vlen, pos);
+}
+
 asmlinkage long
 compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32,
 		    unsigned int nr_segs, unsigned int flags)
diff --git a/fs/dcache.c b/fs/dcache.c
index e9a07b2a0948..b60ddc41d783 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2404,6 +2404,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 			if (d_ancestor(alias, dentry)) {
 				/* Check for loops */
 				actual = ERR_PTR(-ELOOP);
+				spin_unlock(&inode->i_lock);
 			} else if (IS_ROOT(alias)) {
 				/* Is this an anonymous mountpoint that we
 				 * could splice into our tree? */
@@ -2413,7 +2414,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 				goto found;
 			} else {
 				/* Nope, but we must(!) avoid directory
-				 * aliasing */
+				 * aliasing. This drops inode->i_lock */
 				actual = __d_unalias(inode, dentry, alias);
 			}
 			write_sequnlock(&rename_lock);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 21e93605161c..5dfafdd1dbd3 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -33,18 +33,10 @@ static ssize_t default_write_file(struct file *file, const char __user *buf,
 	return count;
 }
 
-static int default_open(struct inode *inode, struct file *file)
-{
-	if (inode->i_private)
-		file->private_data = inode->i_private;
-
-	return 0;
-}
-
 const struct file_operations debugfs_file_operations = {
 	.read =		default_read_file,
 	.write =	default_write_file,
-	.open =		default_open,
+	.open =		simple_open,
 	.llseek =	noop_llseek,
 };
 
@@ -447,7 +439,7 @@ static ssize_t write_file_bool(struct file *file, const char __user *user_buf,
 static const struct file_operations fops_bool = {
 	.read =		read_file_bool,
 	.write =	write_file_bool,
-	.open =		default_open,
+	.open =		simple_open,
 	.llseek =	default_llseek,
 };
 
@@ -492,7 +484,7 @@ static ssize_t read_file_blob(struct file *file, char __user *user_buf,
 
 static const struct file_operations fops_blob = {
 	.read =		read_file_blob,
-	.open =		default_open,
+	.open =		simple_open,
 	.llseek =	default_llseek,
 };
 
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index 3dca2b39e83f..1c9b08095f98 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -609,13 +609,6 @@ static const struct file_operations format3_fops = {
 /*
  * dump lkb's on the ls_waiters list
  */
-
-static int waiters_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t waiters_read(struct file *file, char __user *userbuf,
 			    size_t count, loff_t *ppos)
 {
@@ -644,7 +637,7 @@ static ssize_t waiters_read(struct file *file, char __user *userbuf,
 
 static const struct file_operations waiters_fops = {
 	.owner   = THIS_MODULE,
-	.open    = waiters_open,
+	.open    = simple_open,
 	.read    = waiters_read,
 	.llseek  = default_llseek,
 };
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 629e9ed99d0f..739b0985b398 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -34,7 +34,6 @@
 #include <linux/mutex.h>
 #include <linux/anon_inodes.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/mman.h>
 #include <linux/atomic.h>
diff --git a/fs/exec.c b/fs/exec.c
index 23559c227d9c..b1fd2025e59a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -59,6 +59,7 @@
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
+#include <asm/exec.h>
 
 #include <trace/events/task.h>
 #include "internal.h"
@@ -1027,10 +1028,10 @@ static void flush_old_files(struct files_struct * files)
 		fdt = files_fdtable(files);
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->close_on_exec->fds_bits[j];
+		set = fdt->close_on_exec[j];
 		if (!set)
 			continue;
-		fdt->close_on_exec->fds_bits[j] = 0;
+		fdt->close_on_exec[j] = 0;
 		spin_unlock(&files->file_lock);
 		for ( ; set ; i++,set >>= 1) {
 			if (set & 1) {
@@ -1370,7 +1371,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	unsigned int depth = bprm->recursion_depth;
 	int try,retval;
 	struct linux_binfmt *fmt;
-	pid_t old_pid;
+	pid_t old_pid, old_vpid;
 
 	retval = security_bprm_check(bprm);
 	if (retval)
@@ -1381,8 +1382,9 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 		return retval;
 
 	/* Need to fetch pid before load_binary changes it */
+	old_pid = current->pid;
 	rcu_read_lock();
-	old_pid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
+	old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
 	rcu_read_unlock();
 
 	retval = -ENOENT;
@@ -1405,7 +1407,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 			if (retval >= 0) {
 				if (depth == 0) {
 					trace_sched_process_exec(current, old_pid, bprm);
-					ptrace_event(PTRACE_EVENT_EXEC, old_pid);
+					ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
 				}
 				put_binfmt(fmt);
 				allow_write_access(bprm->file);
@@ -2066,8 +2068,8 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 	fd_install(0, rp);
 	spin_lock(&cf->file_lock);
 	fdt = files_fdtable(cf);
-	FD_SET(0, fdt->open_fds);
-	FD_CLR(0, fdt->close_on_exec);
+	__set_open_fd(0, fdt);
+	__clear_close_on_exec(0, fdt);
 	spin_unlock(&cf->file_lock);
 
 	/* and disallow core files too */
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 7f2b590a36b7..735ca06430ac 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -389,7 +389,7 @@ static int exofs_sync_fs(struct super_block *sb, int wait)
 	ios->length = offsetof(struct exofs_fscb, s_dev_table_oid);
 	memset(fscb, 0, ios->length);
 	fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
-	fscb->s_numfiles = cpu_to_le32(sbi->s_numfiles);
+	fscb->s_numfiles = cpu_to_le64(sbi->s_numfiles);
 	fscb->s_magic = cpu_to_le16(sb->s_magic);
 	fscb->s_newfs = 0;
 	fscb->s_version = EXOFS_FSCB_VER;
@@ -529,7 +529,8 @@ static int exofs_devs_2_odi(struct exofs_dt_device_info *dt_dev,
 			     struct osd_dev_info *odi)
 {
 	odi->systemid_len = le32_to_cpu(dt_dev->systemid_len);
-	memcpy(odi->systemid, dt_dev->systemid, odi->systemid_len);
+	if (likely(odi->systemid_len))
+		memcpy(odi->systemid, dt_dev->systemid, OSD_SYSTEMID_LEN);
 
 	odi->osdname_len = le32_to_cpu(dt_dev->osdname_len);
 	odi->osdname = dt_dev->osdname;
@@ -565,7 +566,7 @@ int __alloc_dev_table(struct exofs_sb_info *sbi, unsigned numdevs,
 
 	aoded = kzalloc(sizeof(*aoded), GFP_KERNEL);
 	if (unlikely(!aoded)) {
-		EXOFS_ERR("ERROR: faild allocating Device array[%d]\n",
+		EXOFS_ERR("ERROR: failed allocating Device array[%d]\n",
 			  numdevs);
 		return -ENOMEM;
 	}
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 75ad433c6691..0b2b4db5bdcd 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -1,5 +1,636 @@
+/*
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/include/linux/minix_fs.h
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
 #include <linux/fs.h>
 #include <linux/ext2_fs.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
+#include <linux/rbtree.h>
+
+/* XXX Here for now... not interested in restructing headers JUST now */
+
+/* data type for block offset of block group */
+typedef int ext2_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long ext2_fsblk_t;
+
+#define E2FSBLK "%lu"
+
+struct ext2_reserve_window {
+	ext2_fsblk_t		_rsv_start;	/* First byte reserved */
+	ext2_fsblk_t		_rsv_end;	/* Last byte reserved or 0 */
+};
+
+struct ext2_reserve_window_node {
+	struct rb_node	 	rsv_node;
+	__u32			rsv_goal_size;
+	__u32			rsv_alloc_hit;
+	struct ext2_reserve_window	rsv_window;
+};
+
+struct ext2_block_alloc_info {
+	/* information about reservation window */
+	struct ext2_reserve_window_node	rsv_window_node;
+	/*
+	 * was i_next_alloc_block in ext2_inode_info
+	 * is the logical (file-relative) number of the
+	 * most-recently-allocated block in this file.
+	 * We use this for detecting linearly ascending allocation requests.
+	 */
+	__u32			last_alloc_logical_block;
+	/*
+	 * Was i_next_alloc_goal in ext2_inode_info
+	 * is the *physical* companion to i_next_alloc_block.
+	 * it the the physical block number of the block which was most-recentl
+	 * allocated to this file.  This give us the goal (target) for the next
+	 * allocation when we detect linearly ascending requests.
+	 */
+	ext2_fsblk_t		last_alloc_physical_block;
+};
+
+#define rsv_start rsv_window._rsv_start
+#define rsv_end rsv_window._rsv_end
+
+/*
+ * second extended-fs super-block data in memory
+ */
+struct ext2_sb_info {
+	unsigned long s_frag_size;	/* Size of a fragment in bytes */
+	unsigned long s_frags_per_block;/* Number of fragments per block */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	unsigned long s_frags_per_group;/* Number of fragments in a group */
+	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_inodes_per_group;/* Number of inodes in a group */
+	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
+	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
+	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
+	unsigned long s_groups_count;	/* Number of groups in the fs */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext2_super_block * s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head ** s_group_desc;
+	unsigned long  s_mount_opt;
+	unsigned long s_sb_block;
+	uid_t s_resuid;
+	gid_t s_resgid;
+	unsigned short s_mount_state;
+	unsigned short s_pad;
+	int s_addr_per_block_bits;
+	int s_desc_per_block_bits;
+	int s_inode_size;
+	int s_first_ino;
+	spinlock_t s_next_gen_lock;
+	u32 s_next_generation;
+	unsigned long s_dir_count;
+	u8 *s_debts;
+	struct percpu_counter s_freeblocks_counter;
+	struct percpu_counter s_freeinodes_counter;
+	struct percpu_counter s_dirs_counter;
+	struct blockgroup_lock *s_blockgroup_lock;
+	/* root of the per fs reservation window tree */
+	spinlock_t s_rsv_window_lock;
+	struct rb_root s_rsv_window_root;
+	struct ext2_reserve_window_node s_rsv_window_head;
+	/*
+	 * s_lock protects against concurrent modifications of s_mount_state,
+	 * s_blocks_last, s_overhead_last and the content of superblock's
+	 * buffer pointed to by sbi->s_es.
+	 *
+	 * Note: It is used in ext2_show_options() to provide a consistent view
+	 * of the mount options.
+	 */
+	spinlock_t s_lock;
+};
+
+static inline spinlock_t *
+sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group)
+{
+	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
+}
+
+/*
+ * Define EXT2FS_DEBUG to produce debug messages
+ */
+#undef EXT2FS_DEBUG
+
+/*
+ * Define EXT2_RESERVATION to reserve data blocks for expanding files
+ */
+#define EXT2_DEFAULT_RESERVE_BLOCKS     8
+/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
+#define EXT2_MAX_RESERVE_BLOCKS         1027
+#define EXT2_RESERVE_WINDOW_NOT_ALLOCATED 0
+/*
+ * The second extended file system version
+ */
+#define EXT2FS_DATE		"95/08/09"
+#define EXT2FS_VERSION		"0.5b"
+
+/*
+ * Debug code
+ */
+#ifdef EXT2FS_DEBUG
+#	define ext2_debug(f, a...)	{ \
+					printk ("EXT2-fs DEBUG (%s, %d): %s:", \
+						__FILE__, __LINE__, __func__); \
+				  	printk (f, ## a); \
+					}
+#else
+#	define ext2_debug(f, a...)	/**/
+#endif
+
+/*
+ * Special inode numbers
+ */
+#define	EXT2_BAD_INO		 1	/* Bad blocks inode */
+#define EXT2_ROOT_INO		 2	/* Root inode */
+#define EXT2_BOOT_LOADER_INO	 5	/* Boot loader inode */
+#define EXT2_UNDEL_DIR_INO	 6	/* Undelete directory inode */
+
+/* First non-reserved inode for old ext2 filesystems */
+#define EXT2_GOOD_OLD_FIRST_INO	11
+
+static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+/*
+ * Macro-instructions used to manage several block sizes
+ */
+#define EXT2_MIN_BLOCK_SIZE		1024
+#define	EXT2_MAX_BLOCK_SIZE		4096
+#define EXT2_MIN_BLOCK_LOG_SIZE		  10
+#define EXT2_BLOCK_SIZE(s)		((s)->s_blocksize)
+#define	EXT2_ADDR_PER_BLOCK(s)		(EXT2_BLOCK_SIZE(s) / sizeof (__u32))
+#define EXT2_BLOCK_SIZE_BITS(s)		((s)->s_blocksize_bits)
+#define	EXT2_ADDR_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_addr_per_block_bits)
+#define EXT2_INODE_SIZE(s)		(EXT2_SB(s)->s_inode_size)
+#define EXT2_FIRST_INO(s)		(EXT2_SB(s)->s_first_ino)
+
+/*
+ * Macro-instructions used to manage fragments
+ */
+#define EXT2_MIN_FRAG_SIZE		1024
+#define	EXT2_MAX_FRAG_SIZE		4096
+#define EXT2_MIN_FRAG_LOG_SIZE		  10
+#define EXT2_FRAG_SIZE(s)		(EXT2_SB(s)->s_frag_size)
+#define EXT2_FRAGS_PER_BLOCK(s)		(EXT2_SB(s)->s_frags_per_block)
+
+/*
+ * Structure of a blocks group descriptor
+ */
+struct ext2_group_desc
+{
+	__le32	bg_block_bitmap;		/* Blocks bitmap block */
+	__le32	bg_inode_bitmap;		/* Inodes bitmap block */
+	__le32	bg_inode_table;		/* Inodes table block */
+	__le16	bg_free_blocks_count;	/* Free blocks count */
+	__le16	bg_free_inodes_count;	/* Free inodes count */
+	__le16	bg_used_dirs_count;	/* Directories count */
+	__le16	bg_pad;
+	__le32	bg_reserved[3];
+};
+
+/*
+ * Macro-instructions used to manage group descriptors
+ */
+#define EXT2_BLOCKS_PER_GROUP(s)	(EXT2_SB(s)->s_blocks_per_group)
+#define EXT2_DESC_PER_BLOCK(s)		(EXT2_SB(s)->s_desc_per_block)
+#define EXT2_INODES_PER_GROUP(s)	(EXT2_SB(s)->s_inodes_per_group)
+#define EXT2_DESC_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_desc_per_block_bits)
+
+/*
+ * Constants relative to the data blocks
+ */
+#define	EXT2_NDIR_BLOCKS		12
+#define	EXT2_IND_BLOCK			EXT2_NDIR_BLOCKS
+#define	EXT2_DIND_BLOCK			(EXT2_IND_BLOCK + 1)
+#define	EXT2_TIND_BLOCK			(EXT2_DIND_BLOCK + 1)
+#define	EXT2_N_BLOCKS			(EXT2_TIND_BLOCK + 1)
+
+/*
+ * Inode flags (GETFLAGS/SETFLAGS)
+ */
+#define	EXT2_SECRM_FL			FS_SECRM_FL	/* Secure deletion */
+#define	EXT2_UNRM_FL			FS_UNRM_FL	/* Undelete */
+#define	EXT2_COMPR_FL			FS_COMPR_FL	/* Compress file */
+#define EXT2_SYNC_FL			FS_SYNC_FL	/* Synchronous updates */
+#define EXT2_IMMUTABLE_FL		FS_IMMUTABLE_FL	/* Immutable file */
+#define EXT2_APPEND_FL			FS_APPEND_FL	/* writes to file may only append */
+#define EXT2_NODUMP_FL			FS_NODUMP_FL	/* do not dump file */
+#define EXT2_NOATIME_FL			FS_NOATIME_FL	/* do not update atime */
+/* Reserved for compression usage... */
+#define EXT2_DIRTY_FL			FS_DIRTY_FL
+#define EXT2_COMPRBLK_FL		FS_COMPRBLK_FL	/* One or more compressed clusters */
+#define EXT2_NOCOMP_FL			FS_NOCOMP_FL	/* Don't compress */
+#define EXT2_ECOMPR_FL			FS_ECOMPR_FL	/* Compression error */
+/* End compression flags --- maybe not all used */	
+#define EXT2_BTREE_FL			FS_BTREE_FL	/* btree format dir */
+#define EXT2_INDEX_FL			FS_INDEX_FL	/* hash-indexed directory */
+#define EXT2_IMAGIC_FL			FS_IMAGIC_FL	/* AFS directory */
+#define EXT2_JOURNAL_DATA_FL		FS_JOURNAL_DATA_FL /* Reserved for ext3 */
+#define EXT2_NOTAIL_FL			FS_NOTAIL_FL	/* file tail should not be merged */
+#define EXT2_DIRSYNC_FL			FS_DIRSYNC_FL	/* dirsync behaviour (directories only) */
+#define EXT2_TOPDIR_FL			FS_TOPDIR_FL	/* Top of directory hierarchies*/
+#define EXT2_RESERVED_FL		FS_RESERVED_FL	/* reserved for ext2 lib */
+
+#define EXT2_FL_USER_VISIBLE		FS_FL_USER_VISIBLE	/* User visible flags */
+#define EXT2_FL_USER_MODIFIABLE		FS_FL_USER_MODIFIABLE	/* User modifiable flags */
+
+/* Flags that should be inherited by new inodes from their parent. */
+#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
+			   EXT2_SYNC_FL | EXT2_NODUMP_FL |\
+			   EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
+			   EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
+			   EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
+
+/* Flags that are appropriate for regular files (all but dir-specific ones). */
+#define EXT2_REG_FLMASK (~(EXT2_DIRSYNC_FL | EXT2_TOPDIR_FL))
+
+/* Flags that are appropriate for non-directories/regular files. */
+#define EXT2_OTHER_FLMASK (EXT2_NODUMP_FL | EXT2_NOATIME_FL)
+
+/* Mask out flags that are inappropriate for the given type of inode. */
+static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
+{
+	if (S_ISDIR(mode))
+		return flags;
+	else if (S_ISREG(mode))
+		return flags & EXT2_REG_FLMASK;
+	else
+		return flags & EXT2_OTHER_FLMASK;
+}
+
+/*
+ * ioctl commands
+ */
+#define	EXT2_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT2_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define	EXT2_IOC_GETVERSION		FS_IOC_GETVERSION
+#define	EXT2_IOC_SETVERSION		FS_IOC_SETVERSION
+#define	EXT2_IOC_GETRSVSZ		_IOR('f', 5, long)
+#define	EXT2_IOC_SETRSVSZ		_IOW('f', 6, long)
+
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT2_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT2_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define EXT2_IOC32_GETVERSION		FS_IOC32_GETVERSION
+#define EXT2_IOC32_SETVERSION		FS_IOC32_SETVERSION
+
+/*
+ * Structure of an inode on the disk
+ */
+struct ext2_inode {
+	__le16	i_mode;		/* File mode */
+	__le16	i_uid;		/* Low 16 bits of Owner Uid */
+	__le32	i_size;		/* Size in bytes */
+	__le32	i_atime;	/* Access time */
+	__le32	i_ctime;	/* Creation time */
+	__le32	i_mtime;	/* Modification time */
+	__le32	i_dtime;	/* Deletion Time */
+	__le16	i_gid;		/* Low 16 bits of Group Id */
+	__le16	i_links_count;	/* Links count */
+	__le32	i_blocks;	/* Blocks count */
+	__le32	i_flags;	/* File flags */
+	union {
+		struct {
+			__le32  l_i_reserved1;
+		} linux1;
+		struct {
+			__le32  h_i_translator;
+		} hurd1;
+		struct {
+			__le32  m_i_reserved1;
+		} masix1;
+	} osd1;				/* OS dependent 1 */
+	__le32	i_block[EXT2_N_BLOCKS];/* Pointers to blocks */
+	__le32	i_generation;	/* File version (for NFS) */
+	__le32	i_file_acl;	/* File ACL */
+	__le32	i_dir_acl;	/* Directory ACL */
+	__le32	i_faddr;	/* Fragment address */
+	union {
+		struct {
+			__u8	l_i_frag;	/* Fragment number */
+			__u8	l_i_fsize;	/* Fragment size */
+			__u16	i_pad1;
+			__le16	l_i_uid_high;	/* these 2 fields    */
+			__le16	l_i_gid_high;	/* were reserved2[0] */
+			__u32	l_i_reserved2;
+		} linux2;
+		struct {
+			__u8	h_i_frag;	/* Fragment number */
+			__u8	h_i_fsize;	/* Fragment size */
+			__le16	h_i_mode_high;
+			__le16	h_i_uid_high;
+			__le16	h_i_gid_high;
+			__le32	h_i_author;
+		} hurd2;
+		struct {
+			__u8	m_i_frag;	/* Fragment number */
+			__u8	m_i_fsize;	/* Fragment size */
+			__u16	m_pad1;
+			__u32	m_i_reserved2[2];
+		} masix2;
+	} osd2;				/* OS dependent 2 */
+};
+
+#define i_size_high	i_dir_acl
+
+#define i_reserved1	osd1.linux1.l_i_reserved1
+#define i_frag		osd2.linux2.l_i_frag
+#define i_fsize		osd2.linux2.l_i_fsize
+#define i_uid_low	i_uid
+#define i_gid_low	i_gid
+#define i_uid_high	osd2.linux2.l_i_uid_high
+#define i_gid_high	osd2.linux2.l_i_gid_high
+#define i_reserved2	osd2.linux2.l_i_reserved2
+
+/*
+ * File system states
+ */
+#define	EXT2_VALID_FS			0x0001	/* Unmounted cleanly */
+#define	EXT2_ERROR_FS			0x0002	/* Errors detected */
+
+/*
+ * Mount flags
+ */
+#define EXT2_MOUNT_CHECK		0x000001  /* Do mount-time checks */
+#define EXT2_MOUNT_OLDALLOC		0x000002  /* Don't use the new Orlov allocator */
+#define EXT2_MOUNT_GRPID		0x000004  /* Create files with directory's group */
+#define EXT2_MOUNT_DEBUG		0x000008  /* Some debugging messages */
+#define EXT2_MOUNT_ERRORS_CONT		0x000010  /* Continue on errors */
+#define EXT2_MOUNT_ERRORS_RO		0x000020  /* Remount fs ro on errors */
+#define EXT2_MOUNT_ERRORS_PANIC		0x000040  /* Panic on errors */
+#define EXT2_MOUNT_MINIX_DF		0x000080  /* Mimics the Minix statfs */
+#define EXT2_MOUNT_NOBH			0x000100  /* No buffer_heads */
+#define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
+#define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
+#define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
+#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
+#define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
+#define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
+#define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */
+
+
+#define clear_opt(o, opt)		o &= ~EXT2_MOUNT_##opt
+#define set_opt(o, opt)			o |= EXT2_MOUNT_##opt
+#define test_opt(sb, opt)		(EXT2_SB(sb)->s_mount_opt & \
+					 EXT2_MOUNT_##opt)
+/*
+ * Maximal mount counts between two filesystem checks
+ */
+#define EXT2_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
+#define EXT2_DFL_CHECKINTERVAL		0	/* Don't use interval check */
+
+/*
+ * Behaviour when detecting errors
+ */
+#define EXT2_ERRORS_CONTINUE		1	/* Continue execution */
+#define EXT2_ERRORS_RO			2	/* Remount fs read-only */
+#define EXT2_ERRORS_PANIC		3	/* Panic */
+#define EXT2_ERRORS_DEFAULT		EXT2_ERRORS_CONTINUE
+
+/*
+ * Structure of the super block
+ */
+struct ext2_super_block {
+	__le32	s_inodes_count;		/* Inodes count */
+	__le32	s_blocks_count;		/* Blocks count */
+	__le32	s_r_blocks_count;	/* Reserved blocks count */
+	__le32	s_free_blocks_count;	/* Free blocks count */
+	__le32	s_free_inodes_count;	/* Free inodes count */
+	__le32	s_first_data_block;	/* First Data Block */
+	__le32	s_log_block_size;	/* Block size */
+	__le32	s_log_frag_size;	/* Fragment size */
+	__le32	s_blocks_per_group;	/* # Blocks per group */
+	__le32	s_frags_per_group;	/* # Fragments per group */
+	__le32	s_inodes_per_group;	/* # Inodes per group */
+	__le32	s_mtime;		/* Mount time */
+	__le32	s_wtime;		/* Write time */
+	__le16	s_mnt_count;		/* Mount count */
+	__le16	s_max_mnt_count;	/* Maximal mount count */
+	__le16	s_magic;		/* Magic signature */
+	__le16	s_state;		/* File system state */
+	__le16	s_errors;		/* Behaviour when detecting errors */
+	__le16	s_minor_rev_level; 	/* minor revision level */
+	__le32	s_lastcheck;		/* time of last check */
+	__le32	s_checkinterval;	/* max. time between checks */
+	__le32	s_creator_os;		/* OS */
+	__le32	s_rev_level;		/* Revision level */
+	__le16	s_def_resuid;		/* Default uid for reserved blocks */
+	__le16	s_def_resgid;		/* Default gid for reserved blocks */
+	/*
+	 * These fields are for EXT2_DYNAMIC_REV superblocks only.
+	 *
+	 * Note: the difference between the compatible feature set and
+	 * the incompatible feature set is that if there is a bit set
+	 * in the incompatible feature set that the kernel doesn't
+	 * know about, it should refuse to mount the filesystem.
+	 * 
+	 * e2fsck's requirements are more strict; if it doesn't know
+	 * about a feature in either the compatible or incompatible
+	 * feature set, it must abort and not try to meddle with
+	 * things it doesn't understand...
+	 */
+	__le32	s_first_ino; 		/* First non-reserved inode */
+	__le16   s_inode_size; 		/* size of inode structure */
+	__le16	s_block_group_nr; 	/* block group # of this superblock */
+	__le32	s_feature_compat; 	/* compatible feature set */
+	__le32	s_feature_incompat; 	/* incompatible feature set */
+	__le32	s_feature_ro_compat; 	/* readonly-compatible feature set */
+	__u8	s_uuid[16];		/* 128-bit uuid for volume */
+	char	s_volume_name[16]; 	/* volume name */
+	char	s_last_mounted[64]; 	/* directory where last mounted */
+	__le32	s_algorithm_usage_bitmap; /* For compression */
+	/*
+	 * Performance hints.  Directory preallocation should only
+	 * happen if the EXT2_COMPAT_PREALLOC flag is on.
+	 */
+	__u8	s_prealloc_blocks;	/* Nr of blocks to try to preallocate*/
+	__u8	s_prealloc_dir_blocks;	/* Nr to preallocate for dirs */
+	__u16	s_padding1;
+	/*
+	 * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set.
+	 */
+	__u8	s_journal_uuid[16];	/* uuid of journal superblock */
+	__u32	s_journal_inum;		/* inode number of journal file */
+	__u32	s_journal_dev;		/* device number of journal file */
+	__u32	s_last_orphan;		/* start of list of inodes to delete */
+	__u32	s_hash_seed[4];		/* HTREE hash seed */
+	__u8	s_def_hash_version;	/* Default hash version to use */
+	__u8	s_reserved_char_pad;
+	__u16	s_reserved_word_pad;
+	__le32	s_default_mount_opts;
+ 	__le32	s_first_meta_bg; 	/* First metablock block group */
+	__u32	s_reserved[190];	/* Padding to the end of the block */
+};
+
+/*
+ * Codes for operating systems
+ */
+#define EXT2_OS_LINUX		0
+#define EXT2_OS_HURD		1
+#define EXT2_OS_MASIX		2
+#define EXT2_OS_FREEBSD		3
+#define EXT2_OS_LITES		4
+
+/*
+ * Revision levels
+ */
+#define EXT2_GOOD_OLD_REV	0	/* The good old (original) format */
+#define EXT2_DYNAMIC_REV	1 	/* V2 format w/ dynamic inode sizes */
+
+#define EXT2_CURRENT_REV	EXT2_GOOD_OLD_REV
+#define EXT2_MAX_SUPP_REV	EXT2_DYNAMIC_REV
+
+#define EXT2_GOOD_OLD_INODE_SIZE 128
+
+/*
+ * Feature set definitions
+ */
+
+#define EXT2_HAS_COMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
+#define EXT2_HAS_RO_COMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
+#define EXT2_HAS_INCOMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
+#define EXT2_SET_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
+#define EXT2_SET_RO_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
+#define EXT2_SET_INCOMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
+#define EXT2_CLEAR_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
+#define EXT2_CLEAR_RO_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
+#define EXT2_CLEAR_INCOMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
+
+#define EXT2_FEATURE_COMPAT_DIR_PREALLOC	0x0001
+#define EXT2_FEATURE_COMPAT_IMAGIC_INODES	0x0002
+#define EXT3_FEATURE_COMPAT_HAS_JOURNAL		0x0004
+#define EXT2_FEATURE_COMPAT_EXT_ATTR		0x0008
+#define EXT2_FEATURE_COMPAT_RESIZE_INO		0x0010
+#define EXT2_FEATURE_COMPAT_DIR_INDEX		0x0020
+#define EXT2_FEATURE_COMPAT_ANY			0xffffffff
+
+#define EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
+#define EXT2_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
+#define EXT2_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
+#define EXT2_FEATURE_RO_COMPAT_ANY		0xffffffff
+
+#define EXT2_FEATURE_INCOMPAT_COMPRESSION	0x0001
+#define EXT2_FEATURE_INCOMPAT_FILETYPE		0x0002
+#define EXT3_FEATURE_INCOMPAT_RECOVER		0x0004
+#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV	0x0008
+#define EXT2_FEATURE_INCOMPAT_META_BG		0x0010
+#define EXT2_FEATURE_INCOMPAT_ANY		0xffffffff
+
+#define EXT2_FEATURE_COMPAT_SUPP	EXT2_FEATURE_COMPAT_EXT_ATTR
+#define EXT2_FEATURE_INCOMPAT_SUPP	(EXT2_FEATURE_INCOMPAT_FILETYPE| \
+					 EXT2_FEATURE_INCOMPAT_META_BG)
+#define EXT2_FEATURE_RO_COMPAT_SUPP	(EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+					 EXT2_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT2_FEATURE_RO_COMPAT_BTREE_DIR)
+#define EXT2_FEATURE_RO_COMPAT_UNSUPPORTED	~EXT2_FEATURE_RO_COMPAT_SUPP
+#define EXT2_FEATURE_INCOMPAT_UNSUPPORTED	~EXT2_FEATURE_INCOMPAT_SUPP
+
+/*
+ * Default values for user and/or group using reserved blocks
+ */
+#define	EXT2_DEF_RESUID		0
+#define	EXT2_DEF_RESGID		0
+
+/*
+ * Default mount options
+ */
+#define EXT2_DEFM_DEBUG		0x0001
+#define EXT2_DEFM_BSDGROUPS	0x0002
+#define EXT2_DEFM_XATTR_USER	0x0004
+#define EXT2_DEFM_ACL		0x0008
+#define EXT2_DEFM_UID16		0x0010
+    /* Not used by ext2, but reserved for use by ext3 */
+#define EXT3_DEFM_JMODE		0x0060 
+#define EXT3_DEFM_JMODE_DATA	0x0020
+#define EXT3_DEFM_JMODE_ORDERED	0x0040
+#define EXT3_DEFM_JMODE_WBACK	0x0060
+
+/*
+ * Structure of a directory entry
+ */
+
+struct ext2_dir_entry {
+	__le32	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__le16	name_len;		/* Name length */
+	char	name[];			/* File name, up to EXT2_NAME_LEN */
+};
+
+/*
+ * The new version of the directory entry.  Since EXT2 structures are
+ * stored in intel byte order, and the name_len field could never be
+ * bigger than 255 chars, it's safe to reclaim the extra byte for the
+ * file_type field.
+ */
+struct ext2_dir_entry_2 {
+	__le32	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__u8	name_len;		/* Name length */
+	__u8	file_type;
+	char	name[];			/* File name, up to EXT2_NAME_LEN */
+};
+
+/*
+ * Ext2 directory file types.  Only the low 3 bits are used.  The
+ * other bits are reserved for now.
+ */
+enum {
+	EXT2_FT_UNKNOWN		= 0,
+	EXT2_FT_REG_FILE	= 1,
+	EXT2_FT_DIR		= 2,
+	EXT2_FT_CHRDEV		= 3,
+	EXT2_FT_BLKDEV		= 4,
+	EXT2_FT_FIFO		= 5,
+	EXT2_FT_SOCK		= 6,
+	EXT2_FT_SYMLINK		= 7,
+	EXT2_FT_MAX
+};
+
+/*
+ * EXT2_DIR_PAD defines the directory entries boundaries
+ *
+ * NOTE: It must be a multiple of 4
+ */
+#define EXT2_DIR_PAD		 	4
+#define EXT2_DIR_ROUND 			(EXT2_DIR_PAD - 1)
+#define EXT2_DIR_REC_LEN(name_len)	(((name_len) + 8 + EXT2_DIR_ROUND) & \
+					 ~EXT2_DIR_ROUND)
+#define EXT2_MAX_REC_LEN		((1<<16)-1)
+
+static inline void verify_offsets(void)
+{
+#define A(x,y) BUILD_BUG_ON(x != offsetof(struct ext2_super_block, y));
+	A(EXT2_SB_MAGIC_OFFSET, s_magic);
+	A(EXT2_SB_BLOCKS_OFFSET, s_blocks_count);
+	A(EXT2_SB_BSIZE_OFFSET, s_log_block_size);
+#undef A
+}
 
 /*
  * ext2 mount options
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index be7a8d02c9a7..cfedb2cb0d8c 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -3,10 +3,7 @@
  * Handler for storing security labels as extended attributes.
  */
 
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/ext2_fs.h>
+#include "ext2.h"
 #include <linux/security.h>
 #include "xattr.h"
 
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index 2989467d3595..7e192574c001 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -5,10 +5,7 @@
  * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
  */
 
-#include <linux/string.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
-#include <linux/ext2_fs.h>
+#include "ext2.h"
 #include "xattr.h"
 
 static size_t
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
index 322a56b2dfb1..1c3312858fcf 100644
--- a/fs/ext2/xip.c
+++ b/fs/ext2/xip.c
@@ -9,8 +9,6 @@
 #include <linux/fs.h>
 #include <linux/genhd.h>
 #include <linux/buffer_head.h>
-#include <linux/ext2_fs_sb.h>
-#include <linux/ext2_fs.h>
 #include <linux/blkdev.h>
 #include "ext2.h"
 #include "xip.h"
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index 3091f62e55b6..c76832c8d192 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -4,13 +4,7 @@
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
  */
 
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index a2038928f9a3..baac1b129fba 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -11,17 +11,9 @@
  *        David S. Miller (davem@caip.rutgers.edu), 1995
  */
 
-#include <linux/time.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
 #include <linux/quotaops.h>
-#include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <trace/events/ext3.h>
+#include "ext3.h"
 
 /*
  * balloc.c contains the blocks allocation and deallocation routines
@@ -1743,8 +1735,11 @@ allocated:
 
 	*errp = 0;
 	brelse(bitmap_bh);
-	dquot_free_block(inode, *count-num);
-	*count = num;
+
+	if (num < *count) {
+		dquot_free_block(inode, *count-num);
+		*count = num;
+	}
 
 	trace_ext3_allocate_blocks(inode, goal, num,
 				   (unsigned long long)ret_block);
@@ -1970,7 +1965,7 @@ static ext3_grpblk_t ext3_trim_all_free(struct super_block *sb,
 	sbi = EXT3_SB(sb);
 
 	 /* Walk through the whole group */
-	while (start < max) {
+	while (start <= max) {
 		start = bitmap_search_next_usable_block(start, bitmap_bh, max);
 		if (start < 0)
 			break;
@@ -1980,7 +1975,7 @@ static ext3_grpblk_t ext3_trim_all_free(struct super_block *sb,
 		 * Allocate contiguous free extents by setting bits in the
 		 * block bitmap
 		 */
-		while (next < max
+		while (next <= max
 			&& claim_block(sb_bgl_lock(sbi, group),
 					next, bitmap_bh)) {
 			next++;
@@ -2091,73 +2086,74 @@ err_out:
  */
 int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range)
 {
-	ext3_grpblk_t last_block, first_block, free_blocks;
-	unsigned long first_group, last_group;
-	unsigned long group, ngroups;
+	ext3_grpblk_t last_block, first_block;
+	unsigned long group, first_group, last_group;
 	struct ext3_group_desc *gdp;
 	struct ext3_super_block *es = EXT3_SB(sb)->s_es;
-	uint64_t start, len, minlen, trimmed;
+	uint64_t start, minlen, end, trimmed = 0;
+	ext3_fsblk_t first_data_blk =
+			le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block);
 	ext3_fsblk_t max_blks = le32_to_cpu(es->s_blocks_count);
 	int ret = 0;
 
-	start = (range->start >> sb->s_blocksize_bits) +
-		le32_to_cpu(es->s_first_data_block);
-	len = range->len >> sb->s_blocksize_bits;
+	start = range->start >> sb->s_blocksize_bits;
+	end = start + (range->len >> sb->s_blocksize_bits) - 1;
 	minlen = range->minlen >> sb->s_blocksize_bits;
-	trimmed = 0;
 
-	if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)))
+	if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)) ||
+	    unlikely(start >= max_blks))
 		return -EINVAL;
-	if (start >= max_blks)
-		return -EINVAL;
-	if (start + len > max_blks)
-		len = max_blks - start;
+	if (end >= max_blks)
+		end = max_blks - 1;
+	if (end <= first_data_blk)
+		goto out;
+	if (start < first_data_blk)
+		start = first_data_blk;
 
-	ngroups = EXT3_SB(sb)->s_groups_count;
 	smp_rmb();
 
 	/* Determine first and last group to examine based on start and len */
 	ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) start,
 				     &first_group, &first_block);
-	ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) (start + len),
+	ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) end,
 				     &last_group, &last_block);
-	last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
-	last_block = EXT3_BLOCKS_PER_GROUP(sb);
 
-	if (first_group > last_group)
-		return -EINVAL;
+	/* end now represents the last block to discard in this group */
+	end = EXT3_BLOCKS_PER_GROUP(sb) - 1;
 
 	for (group = first_group; group <= last_group; group++) {
 		gdp = ext3_get_group_desc(sb, group, NULL);
 		if (!gdp)
 			break;
 
-		free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
-		if (free_blocks < minlen)
-			continue;
-
 		/*
 		 * For all the groups except the last one, last block will
-		 * always be EXT3_BLOCKS_PER_GROUP(sb), so we only need to
-		 * change it for the last group in which case first_block +
-		 * len < EXT3_BLOCKS_PER_GROUP(sb).
+		 * always be EXT3_BLOCKS_PER_GROUP(sb)-1, so we only need to
+		 * change it for the last group, note that last_block is
+		 * already computed earlier by ext3_get_group_no_and_offset()
 		 */
-		if (first_block + len < EXT3_BLOCKS_PER_GROUP(sb))
-			last_block = first_block + len;
-		len -= last_block - first_block;
+		if (group == last_group)
+			end = last_block;
 
-		ret = ext3_trim_all_free(sb, group, first_block,
-					last_block, minlen);
-		if (ret < 0)
-			break;
+		if (le16_to_cpu(gdp->bg_free_blocks_count) >= minlen) {
+			ret = ext3_trim_all_free(sb, group, first_block,
+						 end, minlen);
+			if (ret < 0)
+				break;
+			trimmed += ret;
+		}
 
-		trimmed += ret;
+		/*
+		 * For every group except the first one, we are sure
+		 * that the first block to discard will be block #0.
+		 */
 		first_block = 0;
 	}
 
-	if (ret >= 0)
+	if (ret > 0)
 		ret = 0;
-	range->len = trimmed * sb->s_blocksize;
 
+out:
+	range->len = trimmed * sb->s_blocksize;
 	return ret;
 }
diff --git a/fs/ext3/bitmap.c b/fs/ext3/bitmap.c
index 6afc39d80253..909d13e26560 100644
--- a/fs/ext3/bitmap.c
+++ b/fs/ext3/bitmap.c
@@ -7,9 +7,7 @@
  * Universite Pierre et Marie Curie (Paris VI)
  */
 
-#include <linux/buffer_head.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 
 #ifdef EXT3FS_DEBUG
 
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 34f0a072b935..cc761ad8fa57 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -21,12 +21,7 @@
  *
  */
 
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/buffer_head.h>
-#include <linux/slab.h>
-#include <linux/rbtree.h>
+#include "ext3.h"
 
 static unsigned char ext3_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
diff --git a/include/linux/ext3_fs.h b/fs/ext3/ext3.h
index f5a84eef6ed2..b6515fd7e56c 100644
--- a/include/linux/ext3_fs.h
+++ b/fs/ext3/ext3.h
@@ -1,5 +1,11 @@
 /*
- *  linux/include/linux/ext3_fs.h
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
+ *
+ * Copyright 1998--1999 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
  *
  * Copyright (C) 1992, 1993, 1994, 1995
  * Remy Card (card@masi.ibp.fr)
@@ -13,12 +19,11 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  */
 
-#ifndef _LINUX_EXT3_FS_H
-#define _LINUX_EXT3_FS_H
-
-#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/jbd.h>
 #include <linux/magic.h>
 #include <linux/bug.h>
+#include <linux/blockgroup_lock.h>
 
 /*
  * The second extended filesystem constants/structures
@@ -75,29 +80,12 @@
 #define EXT3_MIN_BLOCK_SIZE		1024
 #define	EXT3_MAX_BLOCK_SIZE		65536
 #define EXT3_MIN_BLOCK_LOG_SIZE		10
-#ifdef __KERNEL__
-# define EXT3_BLOCK_SIZE(s)		((s)->s_blocksize)
-#else
-# define EXT3_BLOCK_SIZE(s)		(EXT3_MIN_BLOCK_SIZE << (s)->s_log_block_size)
-#endif
+#define EXT3_BLOCK_SIZE(s)		((s)->s_blocksize)
 #define	EXT3_ADDR_PER_BLOCK(s)		(EXT3_BLOCK_SIZE(s) / sizeof (__u32))
-#ifdef __KERNEL__
-# define EXT3_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
-#else
-# define EXT3_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
-#endif
-#ifdef __KERNEL__
+#define EXT3_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
 #define	EXT3_ADDR_PER_BLOCK_BITS(s)	(EXT3_SB(s)->s_addr_per_block_bits)
 #define EXT3_INODE_SIZE(s)		(EXT3_SB(s)->s_inode_size)
 #define EXT3_FIRST_INO(s)		(EXT3_SB(s)->s_first_ino)
-#else
-#define EXT3_INODE_SIZE(s)	(((s)->s_rev_level == EXT3_GOOD_OLD_REV) ? \
-				 EXT3_GOOD_OLD_INODE_SIZE : \
-				 (s)->s_inode_size)
-#define EXT3_FIRST_INO(s)	(((s)->s_rev_level == EXT3_GOOD_OLD_REV) ? \
-				 EXT3_GOOD_OLD_FIRST_INO : \
-				 (s)->s_first_ino)
-#endif
 
 /*
  * Macro-instructions used to manage fragments
@@ -105,13 +93,8 @@
 #define EXT3_MIN_FRAG_SIZE		1024
 #define	EXT3_MAX_FRAG_SIZE		4096
 #define EXT3_MIN_FRAG_LOG_SIZE		  10
-#ifdef __KERNEL__
-# define EXT3_FRAG_SIZE(s)		(EXT3_SB(s)->s_frag_size)
-# define EXT3_FRAGS_PER_BLOCK(s)	(EXT3_SB(s)->s_frags_per_block)
-#else
-# define EXT3_FRAG_SIZE(s)		(EXT3_MIN_FRAG_SIZE << (s)->s_log_frag_size)
-# define EXT3_FRAGS_PER_BLOCK(s)	(EXT3_BLOCK_SIZE(s) / EXT3_FRAG_SIZE(s))
-#endif
+#define EXT3_FRAG_SIZE(s)		(EXT3_SB(s)->s_frag_size)
+#define EXT3_FRAGS_PER_BLOCK(s)		(EXT3_SB(s)->s_frags_per_block)
 
 /*
  * Structure of a blocks group descriptor
@@ -131,16 +114,10 @@ struct ext3_group_desc
 /*
  * Macro-instructions used to manage group descriptors
  */
-#ifdef __KERNEL__
-# define EXT3_BLOCKS_PER_GROUP(s)	(EXT3_SB(s)->s_blocks_per_group)
-# define EXT3_DESC_PER_BLOCK(s)		(EXT3_SB(s)->s_desc_per_block)
-# define EXT3_INODES_PER_GROUP(s)	(EXT3_SB(s)->s_inodes_per_group)
-# define EXT3_DESC_PER_BLOCK_BITS(s)	(EXT3_SB(s)->s_desc_per_block_bits)
-#else
-# define EXT3_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
-# define EXT3_DESC_PER_BLOCK(s)		(EXT3_BLOCK_SIZE(s) / sizeof (struct ext3_group_desc))
-# define EXT3_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
-#endif
+#define EXT3_BLOCKS_PER_GROUP(s)	(EXT3_SB(s)->s_blocks_per_group)
+#define EXT3_DESC_PER_BLOCK(s)		(EXT3_SB(s)->s_desc_per_block)
+#define EXT3_INODES_PER_GROUP(s)	(EXT3_SB(s)->s_inodes_per_group)
+#define EXT3_DESC_PER_BLOCK_BITS(s)	(EXT3_SB(s)->s_desc_per_block_bits)
 
 /*
  * Constants relative to the data blocks
@@ -336,7 +313,6 @@ struct ext3_inode {
 
 #define i_size_high	i_dir_acl
 
-#if defined(__KERNEL__) || defined(__linux__)
 #define i_reserved1	osd1.linux1.l_i_reserved1
 #define i_frag		osd2.linux2.l_i_frag
 #define i_fsize		osd2.linux2.l_i_fsize
@@ -346,24 +322,6 @@ struct ext3_inode {
 #define i_gid_high	osd2.linux2.l_i_gid_high
 #define i_reserved2	osd2.linux2.l_i_reserved2
 
-#elif defined(__GNU__)
-
-#define i_translator	osd1.hurd1.h_i_translator
-#define i_frag		osd2.hurd2.h_i_frag;
-#define i_fsize		osd2.hurd2.h_i_fsize;
-#define i_uid_high	osd2.hurd2.h_i_uid_high
-#define i_gid_high	osd2.hurd2.h_i_gid_high
-#define i_author	osd2.hurd2.h_i_author
-
-#elif defined(__masix__)
-
-#define i_reserved1	osd1.masix1.m_i_reserved1
-#define i_frag		osd2.masix2.m_i_frag
-#define i_fsize		osd2.masix2.m_i_fsize
-#define i_reserved2	osd2.masix2.m_i_reserved2
-
-#endif /* defined(__KERNEL__) || defined(__linux__) */
-
 /*
  * File system states
  */
@@ -531,9 +489,197 @@ struct ext3_super_block {
 	__u32   s_reserved[162];        /* Padding to the end of the block */
 };
 
-#ifdef __KERNEL__
-#include <linux/ext3_fs_i.h>
-#include <linux/ext3_fs_sb.h>
+/* data type for block offset of block group */
+typedef int ext3_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long ext3_fsblk_t;
+
+#define E3FSBLK "%lu"
+
+struct ext3_reserve_window {
+	ext3_fsblk_t	_rsv_start;	/* First byte reserved */
+	ext3_fsblk_t	_rsv_end;	/* Last byte reserved or 0 */
+};
+
+struct ext3_reserve_window_node {
+	struct rb_node		rsv_node;
+	__u32			rsv_goal_size;
+	__u32			rsv_alloc_hit;
+	struct ext3_reserve_window	rsv_window;
+};
+
+struct ext3_block_alloc_info {
+	/* information about reservation window */
+	struct ext3_reserve_window_node	rsv_window_node;
+	/*
+	 * was i_next_alloc_block in ext3_inode_info
+	 * is the logical (file-relative) number of the
+	 * most-recently-allocated block in this file.
+	 * We use this for detecting linearly ascending allocation requests.
+	 */
+	__u32                   last_alloc_logical_block;
+	/*
+	 * Was i_next_alloc_goal in ext3_inode_info
+	 * is the *physical* companion to i_next_alloc_block.
+	 * it the physical block number of the block which was most-recentl
+	 * allocated to this file.  This give us the goal (target) for the next
+	 * allocation when we detect linearly ascending requests.
+	 */
+	ext3_fsblk_t		last_alloc_physical_block;
+};
+
+#define rsv_start rsv_window._rsv_start
+#define rsv_end rsv_window._rsv_end
+
+/*
+ * third extended file system inode data in memory
+ */
+struct ext3_inode_info {
+	__le32	i_data[15];	/* unconverted */
+	__u32	i_flags;
+#ifdef EXT3_FRAGMENTS
+	__u32	i_faddr;
+	__u8	i_frag_no;
+	__u8	i_frag_size;
+#endif
+	ext3_fsblk_t	i_file_acl;
+	__u32	i_dir_acl;
+	__u32	i_dtime;
+
+	/*
+	 * i_block_group is the number of the block group which contains
+	 * this file's inode.  Constant across the lifetime of the inode,
+	 * it is ued for making block allocation decisions - we try to
+	 * place a file's data blocks near its inode block, and new inodes
+	 * near to their parent directory's inode.
+	 */
+	__u32	i_block_group;
+	unsigned long	i_state_flags;	/* Dynamic state flags for ext3 */
+
+	/* block reservation info */
+	struct ext3_block_alloc_info *i_block_alloc_info;
+
+	__u32	i_dir_start_lookup;
+#ifdef CONFIG_EXT3_FS_XATTR
+	/*
+	 * Extended attributes can be read independently of the main file
+	 * data. Taking i_mutex even when reading would cause contention
+	 * between readers of EAs and writers of regular file data, so
+	 * instead we synchronize on xattr_sem when reading or changing
+	 * EAs.
+	 */
+	struct rw_semaphore xattr_sem;
+#endif
+
+	struct list_head i_orphan;	/* unlinked but open inodes */
+
+	/*
+	 * i_disksize keeps track of what the inode size is ON DISK, not
+	 * in memory.  During truncate, i_size is set to the new size by
+	 * the VFS prior to calling ext3_truncate(), but the filesystem won't
+	 * set i_disksize to 0 until the truncate is actually under way.
+	 *
+	 * The intent is that i_disksize always represents the blocks which
+	 * are used by this file.  This allows recovery to restart truncate
+	 * on orphans if we crash during truncate.  We actually write i_disksize
+	 * into the on-disk inode when writing inodes out, instead of i_size.
+	 *
+	 * The only time when i_disksize and i_size may be different is when
+	 * a truncate is in progress.  The only things which change i_disksize
+	 * are ext3_get_block (growth) and ext3_truncate (shrinkth).
+	 */
+	loff_t	i_disksize;
+
+	/* on-disk additional length */
+	__u16 i_extra_isize;
+
+	/*
+	 * truncate_mutex is for serialising ext3_truncate() against
+	 * ext3_getblock().  In the 2.4 ext2 design, great chunks of inode's
+	 * data tree are chopped off during truncate. We can't do that in
+	 * ext3 because whenever we perform intermediate commits during
+	 * truncate, the inode and all the metadata blocks *must* be in a
+	 * consistent state which allows truncation of the orphans to restart
+	 * during recovery.  Hence we must fix the get_block-vs-truncate race
+	 * by other means, so we have truncate_mutex.
+	 */
+	struct mutex truncate_mutex;
+
+	/*
+	 * Transactions that contain inode's metadata needed to complete
+	 * fsync and fdatasync, respectively.
+	 */
+	atomic_t i_sync_tid;
+	atomic_t i_datasync_tid;
+
+	struct inode vfs_inode;
+};
+
+/*
+ * third extended-fs super-block data in memory
+ */
+struct ext3_sb_info {
+	unsigned long s_frag_size;	/* Size of a fragment in bytes */
+	unsigned long s_frags_per_block;/* Number of fragments per block */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	unsigned long s_frags_per_group;/* Number of fragments in a group */
+	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_inodes_per_group;/* Number of inodes in a group */
+	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
+	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
+	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
+	unsigned long s_groups_count;	/* Number of groups in the fs */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext3_super_block * s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head ** s_group_desc;
+	unsigned long  s_mount_opt;
+	ext3_fsblk_t s_sb_block;
+	uid_t s_resuid;
+	gid_t s_resgid;
+	unsigned short s_mount_state;
+	unsigned short s_pad;
+	int s_addr_per_block_bits;
+	int s_desc_per_block_bits;
+	int s_inode_size;
+	int s_first_ino;
+	spinlock_t s_next_gen_lock;
+	u32 s_next_generation;
+	u32 s_hash_seed[4];
+	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
+	struct percpu_counter s_freeblocks_counter;
+	struct percpu_counter s_freeinodes_counter;
+	struct percpu_counter s_dirs_counter;
+	struct blockgroup_lock *s_blockgroup_lock;
+
+	/* root of the per fs reservation window tree */
+	spinlock_t s_rsv_window_lock;
+	struct rb_root s_rsv_window_root;
+	struct ext3_reserve_window_node s_rsv_window_head;
+
+	/* Journaling */
+	struct inode * s_journal_inode;
+	struct journal_s * s_journal;
+	struct list_head s_orphan;
+	struct mutex s_orphan_lock;
+	struct mutex s_resize_lock;
+	unsigned long s_commit_interval;
+	struct block_device *journal_bdev;
+#ifdef CONFIG_QUOTA
+	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
+	int s_jquota_fmt;			/* Format of quota to use */
+#endif
+};
+
+static inline spinlock_t *
+sb_bgl_lock(struct ext3_sb_info *sbi, unsigned int block_group)
+{
+	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
+}
+
 static inline struct ext3_sb_info * EXT3_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
@@ -576,12 +722,6 @@ static inline void ext3_clear_inode_state(struct inode *inode, int bit)
 {
 	clear_bit(bit, &EXT3_I(inode)->i_state_flags);
 }
-#else
-/* Assume that user mode programs are passing in an ext3fs superblock, not
- * a kernel struct super_block.  This will allow us to call the feature-test
- * macros from user land. */
-#define EXT3_SB(sb)	(sb)
-#endif
 
 #define NEXT_ORPHAN(inode) EXT3_I(inode)->i_dtime
 
@@ -771,8 +911,6 @@ static inline __le16 ext3_rec_len_to_disk(unsigned len)
 #define DX_HASH_HALF_MD4_UNSIGNED	4
 #define DX_HASH_TEA_UNSIGNED		5
 
-#ifdef __KERNEL__
-
 /* hash info structure used by the directory hash */
 struct dx_hash_info
 {
@@ -974,7 +1112,211 @@ extern const struct inode_operations ext3_special_inode_operations;
 extern const struct inode_operations ext3_symlink_inode_operations;
 extern const struct inode_operations ext3_fast_symlink_inode_operations;
 
+#define EXT3_JOURNAL(inode)	(EXT3_SB((inode)->i_sb)->s_journal)
+
+/* Define the number of blocks we need to account to a transaction to
+ * modify one block of data.
+ *
+ * We may have to touch one inode, one bitmap buffer, up to three
+ * indirection blocks, the group and superblock summaries, and the data
+ * block to complete the transaction.  */
+
+#define EXT3_SINGLEDATA_TRANS_BLOCKS	8U
+
+/* Extended attribute operations touch at most two data buffers,
+ * two bitmap buffers, and two group summaries, in addition to the inode
+ * and the superblock, which are already accounted for. */
+
+#define EXT3_XATTR_TRANS_BLOCKS		6U
+
+/* Define the minimum size for a transaction which modifies data.  This
+ * needs to take into account the fact that we may end up modifying two
+ * quota files too (one for the group, one for the user quota).  The
+ * superblock only gets updated once, of course, so don't bother
+ * counting that again for the quota updates. */
+
+#define EXT3_DATA_TRANS_BLOCKS(sb)	(EXT3_SINGLEDATA_TRANS_BLOCKS + \
+					 EXT3_XATTR_TRANS_BLOCKS - 2 + \
+					 EXT3_MAXQUOTAS_TRANS_BLOCKS(sb))
+
+/* Delete operations potentially hit one directory's namespace plus an
+ * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
+ * generous.  We can grow the delete transaction later if necessary. */
+
+#define EXT3_DELETE_TRANS_BLOCKS(sb)   (EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) + 64)
+
+/* Define an arbitrary limit for the amount of data we will anticipate
+ * writing to any given transaction.  For unbounded transactions such as
+ * write(2) and truncate(2) we can write more than this, but we always
+ * start off at the maximum transaction size and grow the transaction
+ * optimistically as we go. */
+
+#define EXT3_MAX_TRANS_DATA		64U
+
+/* We break up a large truncate or write transaction once the handle's
+ * buffer credits gets this low, we need either to extend the
+ * transaction or to start a new one.  Reserve enough space here for
+ * inode, bitmap, superblock, group and indirection updates for at least
+ * one block, plus two quota updates.  Quota allocations are not
+ * needed. */
+
+#define EXT3_RESERVE_TRANS_BLOCKS	12U
+
+#define EXT3_INDEX_EXTRA_TRANS_BLOCKS	8
+
+#ifdef CONFIG_QUOTA
+/* Amount of blocks needed for quota update - we know that the structure was
+ * allocated so we need to update only inode+data */
+#define EXT3_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0)
+/* Amount of blocks needed for quota insert/delete - we do some block writes
+ * but inode, sb and group updates are done only once */
+#define EXT3_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
+		(EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0)
+#define EXT3_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
+		(EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0)
+#else
+#define EXT3_QUOTA_TRANS_BLOCKS(sb) 0
+#define EXT3_QUOTA_INIT_BLOCKS(sb) 0
+#define EXT3_QUOTA_DEL_BLOCKS(sb) 0
+#endif
+#define EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_TRANS_BLOCKS(sb))
+#define EXT3_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_INIT_BLOCKS(sb))
+#define EXT3_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_DEL_BLOCKS(sb))
+
+int
+ext3_mark_iloc_dirty(handle_t *handle,
+		     struct inode *inode,
+		     struct ext3_iloc *iloc);
+
+/*
+ * On success, We end up with an outstanding reference count against
+ * iloc->bh.  This _must_ be cleaned up later.
+ */
+
+int ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
+			struct ext3_iloc *iloc);
+
+int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode);
+
+/*
+ * Wrapper functions with which ext3 calls into JBD.  The intent here is
+ * to allow these to be turned into appropriate stubs so ext3 can control
+ * ext2 filesystems, so ext2+ext3 systems only nee one fs.  This work hasn't
+ * been done yet.
+ */
+
+static inline void ext3_journal_release_buffer(handle_t *handle,
+						struct buffer_head *bh)
+{
+	journal_release_buffer(handle, bh);
+}
+
+void ext3_journal_abort_handle(const char *caller, const char *err_fn,
+		struct buffer_head *bh, handle_t *handle, int err);
+
+int __ext3_journal_get_undo_access(const char *where, handle_t *handle,
+				struct buffer_head *bh);
+
+int __ext3_journal_get_write_access(const char *where, handle_t *handle,
+				struct buffer_head *bh);
+
+int __ext3_journal_forget(const char *where, handle_t *handle,
+				struct buffer_head *bh);
 
-#endif	/* __KERNEL__ */
+int __ext3_journal_revoke(const char *where, handle_t *handle,
+				unsigned long blocknr, struct buffer_head *bh);
+
+int __ext3_journal_get_create_access(const char *where,
+				handle_t *handle, struct buffer_head *bh);
+
+int __ext3_journal_dirty_metadata(const char *where,
+				handle_t *handle, struct buffer_head *bh);
+
+#define ext3_journal_get_undo_access(handle, bh) \
+	__ext3_journal_get_undo_access(__func__, (handle), (bh))
+#define ext3_journal_get_write_access(handle, bh) \
+	__ext3_journal_get_write_access(__func__, (handle), (bh))
+#define ext3_journal_revoke(handle, blocknr, bh) \
+	__ext3_journal_revoke(__func__, (handle), (blocknr), (bh))
+#define ext3_journal_get_create_access(handle, bh) \
+	__ext3_journal_get_create_access(__func__, (handle), (bh))
+#define ext3_journal_dirty_metadata(handle, bh) \
+	__ext3_journal_dirty_metadata(__func__, (handle), (bh))
+#define ext3_journal_forget(handle, bh) \
+	__ext3_journal_forget(__func__, (handle), (bh))
+
+int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh);
+
+handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks);
+int __ext3_journal_stop(const char *where, handle_t *handle);
+
+static inline handle_t *ext3_journal_start(struct inode *inode, int nblocks)
+{
+	return ext3_journal_start_sb(inode->i_sb, nblocks);
+}
+
+#define ext3_journal_stop(handle) \
+	__ext3_journal_stop(__func__, (handle))
+
+static inline handle_t *ext3_journal_current_handle(void)
+{
+	return journal_current_handle();
+}
+
+static inline int ext3_journal_extend(handle_t *handle, int nblocks)
+{
+	return journal_extend(handle, nblocks);
+}
+
+static inline int ext3_journal_restart(handle_t *handle, int nblocks)
+{
+	return journal_restart(handle, nblocks);
+}
+
+static inline int ext3_journal_blocks_per_page(struct inode *inode)
+{
+	return journal_blocks_per_page(inode);
+}
+
+static inline int ext3_journal_force_commit(journal_t *journal)
+{
+	return journal_force_commit(journal);
+}
+
+/* super.c */
+int ext3_force_commit(struct super_block *sb);
+
+static inline int ext3_should_journal_data(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 1;
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
+		return 1;
+	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
+		return 1;
+	return 0;
+}
+
+static inline int ext3_should_order_data(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
+		return 0;
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
+		return 1;
+	return 0;
+}
+
+static inline int ext3_should_writeback_data(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
+		return 0;
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
+		return 1;
+	return 0;
+}
 
-#endif	/* _LINUX_EXT3_FS_H */
+#include <trace/events/ext3.h>
diff --git a/fs/ext3/ext3_jbd.c b/fs/ext3/ext3_jbd.c
index d401f148d74d..785a3261a26c 100644
--- a/fs/ext3/ext3_jbd.c
+++ b/fs/ext3/ext3_jbd.c
@@ -2,7 +2,7 @@
  * Interface between ext3 and JBD
  */
 
-#include <linux/ext3_jbd.h>
+#include "ext3.h"
 
 int __ext3_journal_get_undo_access(const char *where, handle_t *handle,
 				struct buffer_head *bh)
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index 724df69847dc..25cb413277e9 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -18,12 +18,8 @@
  *	(jj@sunsite.ms.mff.cuni.cz)
  */
 
-#include <linux/time.h>
-#include <linux/fs.h>
-#include <linux/jbd.h>
 #include <linux/quotaops.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 
diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c
index 1860ed356323..d4dff278cbd8 100644
--- a/fs/ext3/fsync.c
+++ b/fs/ext3/fsync.c
@@ -22,15 +22,9 @@
  * we can depend on generic_block_fdatasync() to sync the data blocks.
  */
 
-#include <linux/time.h>
 #include <linux/blkdev.h>
-#include <linux/fs.h>
-#include <linux/sched.h>
 #include <linux/writeback.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
-#include <trace/events/ext3.h>
+#include "ext3.h"
 
 /*
  * akpm: A new design for ext3_sync_file().
diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c
index 7d215b4d4f2e..d10231ddcf8a 100644
--- a/fs/ext3/hash.c
+++ b/fs/ext3/hash.c
@@ -9,9 +9,7 @@
  * License.
  */
 
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include <linux/cryptohash.h>
 
 #define DELTA 0x9E3779B9
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 1cde28438014..e3c39e4cec19 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -12,21 +12,10 @@
  *        David S. Miller (davem@caip.rutgers.edu), 1995
  */
 
-#include <linux/time.h>
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/stat.h>
-#include <linux/string.h>
 #include <linux/quotaops.h>
-#include <linux/buffer_head.h>
 #include <linux/random.h>
-#include <linux/bitops.h>
-#include <trace/events/ext3.h>
-
-#include <asm/byteorder.h>
 
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2d0afeca0b47..10d7812f6021 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -22,22 +22,12 @@
  *  Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000
  */
 
-#include <linux/fs.h>
-#include <linux/time.h>
-#include <linux/ext3_jbd.h>
-#include <linux/jbd.h>
 #include <linux/highuid.h>
-#include <linux/pagemap.h>
 #include <linux/quotaops.h>
-#include <linux/string.h>
-#include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/mpage.h>
-#include <linux/uio.h>
-#include <linux/bio.h>
-#include <linux/fiemap.h>
 #include <linux/namei.h>
-#include <trace/events/ext3.h>
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 
@@ -756,6 +746,7 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode,
 	struct ext3_block_alloc_info *block_i;
 	ext3_fsblk_t current_block;
 	struct ext3_inode_info *ei = EXT3_I(inode);
+	struct timespec now;
 
 	block_i = ei->i_block_alloc_info;
 	/*
@@ -795,9 +786,11 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode,
 	}
 
 	/* We are done with atomic stuff, now do the rest of housekeeping */
-
-	inode->i_ctime = CURRENT_TIME_SEC;
-	ext3_mark_inode_dirty(handle, inode);
+	now = CURRENT_TIME_SEC;
+	if (!timespec_equal(&inode->i_ctime, &now) || !where->bh) {
+		inode->i_ctime = now;
+		ext3_mark_inode_dirty(handle, inode);
+	}
 	/* ext3_mark_inode_dirty already updated i_sync_tid */
 	atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid);
 
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 4af574ce4a46..677a5c27dc69 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -7,15 +7,10 @@
  * Universite Pierre et Marie Curie (Paris VI)
  */
 
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/capability.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
 #include <linux/mount.h>
-#include <linux/time.h>
 #include <linux/compat.h>
 #include <asm/uaccess.h>
+#include "ext3.h"
 
 long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index e8e211795e9f..d7940b24cf68 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -24,20 +24,8 @@
  *	Theodore Ts'o, 2002
  */
 
-#include <linux/fs.h>
-#include <linux/pagemap.h>
-#include <linux/jbd.h>
-#include <linux/time.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/fcntl.h>
-#include <linux/stat.h>
-#include <linux/string.h>
 #include <linux/quotaops.h>
-#include <linux/buffer_head.h>
-#include <linux/bio.h>
-#include <trace/events/ext3.h>
-
+#include "ext3.h"
 #include "namei.h"
 #include "xattr.h"
 #include "acl.h"
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index 7916e4ce166a..0f814f3450de 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -11,10 +11,7 @@
 
 #define EXT3FS_DEBUG
 
-#include <linux/ext3_jbd.h>
-
-#include <linux/errno.h>
-#include <linux/slab.h>
+#include "ext3.h"
 
 
 #define outside(b, first, last)	((b) < (first) || (b) >= (last))
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index e0b45b93327b..cf0b5921cf0f 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -17,22 +17,12 @@
  */
 
 #include <linux/module.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/time.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/slab.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/parser.h>
-#include <linux/buffer_head.h>
 #include <linux/exportfs.h>
-#include <linux/vfs.h>
+#include <linux/statfs.h>
 #include <linux/random.h>
 #include <linux/mount.h>
-#include <linux/namei.h>
 #include <linux/quotaops.h>
 #include <linux/seq_file.h>
 #include <linux/log2.h>
@@ -40,13 +30,13 @@
 
 #include <asm/uaccess.h>
 
+#define CREATE_TRACE_POINTS
+
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 #include "namei.h"
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/ext3.h>
-
 #ifdef CONFIG_EXT3_DEFAULTS_TO_ORDERED
   #define EXT3_MOUNT_DEFAULT_DATA_MODE EXT3_MOUNT_ORDERED_DATA
 #else
diff --git a/fs/ext3/symlink.c b/fs/ext3/symlink.c
index 7c4898207776..6b01c3eab1f3 100644
--- a/fs/ext3/symlink.c
+++ b/fs/ext3/symlink.c
@@ -17,10 +17,8 @@
  *  ext3 symlink handling code
  */
 
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
 #include <linux/namei.h>
+#include "ext3.h"
 #include "xattr.h"
 
 static void * ext3_follow_link(struct dentry *dentry, struct nameidata *nd)
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index d565759d82ee..d22ebb7a4f55 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -50,14 +50,9 @@
  * by the buffer lock.
  */
 
-#include <linux/init.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include <linux/mbcache.h>
 #include <linux/quotaops.h>
-#include <linux/rwsem.h>
 #include "xattr.h"
 #include "acl.h"
 
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index ea26f2acab94..3387664ad70e 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -3,12 +3,8 @@
  * Handler for storing security labels as extended attributes.
  */
 
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
 #include <linux/security.h>
+#include "ext3.h"
 #include "xattr.h"
 
 static size_t
diff --git a/fs/ext3/xattr_trusted.c b/fs/ext3/xattr_trusted.c
index 2526a8829de8..d75727cc67fa 100644
--- a/fs/ext3/xattr_trusted.c
+++ b/fs/ext3/xattr_trusted.c
@@ -5,11 +5,7 @@
  * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
  */
 
-#include <linux/string.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include "xattr.h"
 
 static size_t
diff --git a/fs/ext3/xattr_user.c b/fs/ext3/xattr_user.c
index b32e473a1e33..5612af3567e0 100644
--- a/fs/ext3/xattr_user.c
+++ b/fs/ext3/xattr_user.c
@@ -5,10 +5,7 @@
  * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
  */
 
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include "xattr.h"
 
 static size_t
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f9e2cd8cf711..4bbd07a6fa18 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -336,10 +336,10 @@ err_out:
  * Return buffer_head on success or NULL in case of failure.
  */
 struct buffer_head *
-ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 {
 	struct ext4_group_desc *desc;
-	struct buffer_head *bh = NULL;
+	struct buffer_head *bh;
 	ext4_fsblk_t bitmap_blk;
 
 	desc = ext4_get_group_desc(sb, block_group, NULL);
@@ -348,9 +348,9 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	bitmap_blk = ext4_block_bitmap(sb, desc);
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, "Cannot read block bitmap - "
-			    "block_group = %u, block_bitmap = %llu",
-			    block_group, bitmap_blk);
+		ext4_error(sb, "Cannot get buffer for block bitmap - "
+			   "block_group = %u, block_bitmap = %llu",
+			   block_group, bitmap_blk);
 		return NULL;
 	}
 
@@ -382,25 +382,50 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 		return bh;
 	}
 	/*
-	 * submit the buffer_head for read. We can
-	 * safely mark the bitmap as uptodate now.
-	 * We do it here so the bitmap uptodate bit
-	 * get set with buffer lock held.
+	 * submit the buffer_head for reading
 	 */
+	set_buffer_new(bh);
 	trace_ext4_read_block_bitmap_load(sb, block_group);
-	set_bitmap_uptodate(bh);
-	if (bh_submit_read(bh) < 0) {
-		put_bh(bh);
+	bh->b_end_io = ext4_end_bitmap_read;
+	get_bh(bh);
+	submit_bh(READ, bh);
+	return bh;
+}
+
+/* Returns 0 on success, 1 on error */
+int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
+			   struct buffer_head *bh)
+{
+	struct ext4_group_desc *desc;
+
+	if (!buffer_new(bh))
+		return 0;
+	desc = ext4_get_group_desc(sb, block_group, NULL);
+	if (!desc)
+		return 1;
+	wait_on_buffer(bh);
+	if (!buffer_uptodate(bh)) {
 		ext4_error(sb, "Cannot read block bitmap - "
-			    "block_group = %u, block_bitmap = %llu",
-			    block_group, bitmap_blk);
-		return NULL;
+			   "block_group = %u, block_bitmap = %llu",
+			   block_group, (unsigned long long) bh->b_blocknr);
+		return 1;
 	}
+	clear_buffer_new(bh);
+	/* Panic or remount fs read-only if block bitmap is invalid */
 	ext4_valid_block_bitmap(sb, desc, block_group, bh);
-	/*
-	 * file system mounted not to panic on error,
-	 * continue with corrupt bitmap
-	 */
+	return 0;
+}
+
+struct buffer_head *
+ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+{
+	struct buffer_head *bh;
+
+	bh = ext4_read_block_bitmap_nowait(sb, block_group);
+	if (ext4_wait_block_bitmap(sb, block_group, bh)) {
+		put_bh(bh);
+		return NULL;
+	}
 	return bh;
 }
 
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 164c56092e58..b86786202643 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -32,24 +32,8 @@ static unsigned char ext4_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
 };
 
-static int ext4_readdir(struct file *, void *, filldir_t);
 static int ext4_dx_readdir(struct file *filp,
 			   void *dirent, filldir_t filldir);
-static int ext4_release_dir(struct inode *inode,
-				struct file *filp);
-
-const struct file_operations ext4_dir_operations = {
-	.llseek		= ext4_llseek,
-	.read		= generic_read_dir,
-	.readdir	= ext4_readdir,		/* we take BKL. needed?*/
-	.unlocked_ioctl = ext4_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= ext4_compat_ioctl,
-#endif
-	.fsync		= ext4_sync_file,
-	.release	= ext4_release_dir,
-};
-
 
 static unsigned char get_dtype(struct super_block *sb, int filetype)
 {
@@ -60,6 +44,26 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
 	return (ext4_filetype_table[filetype]);
 }
 
+/**
+ * Check if the given dir-inode refers to an htree-indexed directory
+ * (or a directory which chould potentially get coverted to use htree
+ * indexing).
+ *
+ * Return 1 if it is a dx dir, 0 if not
+ */
+static int is_dx_dir(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+
+	if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
+		     EXT4_FEATURE_COMPAT_DIR_INDEX) &&
+	    ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
+	     ((inode->i_size >> sb->s_blocksize_bits) == 1)))
+		return 1;
+
+	return 0;
+}
+
 /*
  * Return 0 if the directory entry is OK, and 1 if there is a problem
  *
@@ -91,17 +95,17 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
 		return 0;
 
 	if (filp)
-		ext4_error_file(filp, function, line, bh ? bh->b_blocknr : 0,
+		ext4_error_file(filp, function, line, bh->b_blocknr,
 				"bad entry in directory: %s - offset=%u(%u), "
 				"inode=%u, rec_len=%d, name_len=%d",
-				error_msg, (unsigned) (offset%bh->b_size),
+				error_msg, (unsigned) (offset % bh->b_size),
 				offset, le32_to_cpu(de->inode),
 				rlen, de->name_len);
 	else
-		ext4_error_inode(dir, function, line, bh ? bh->b_blocknr : 0,
+		ext4_error_inode(dir, function, line, bh->b_blocknr,
 				"bad entry in directory: %s - offset=%u(%u), "
 				"inode=%u, rec_len=%d, name_len=%d",
-				error_msg, (unsigned) (offset%bh->b_size),
+				error_msg, (unsigned) (offset % bh->b_size),
 				offset, le32_to_cpu(de->inode),
 				rlen, de->name_len);
 
@@ -115,18 +119,13 @@ static int ext4_readdir(struct file *filp,
 	unsigned int offset;
 	int i, stored;
 	struct ext4_dir_entry_2 *de;
-	struct super_block *sb;
 	int err;
 	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
 	int ret = 0;
 	int dir_has_error = 0;
 
-	sb = inode->i_sb;
-
-	if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
-				    EXT4_FEATURE_COMPAT_DIR_INDEX) &&
-	    ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
-	     ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(filp, dirent, filldir);
 		if (err != ERR_BAD_DX_DIR) {
 			ret = err;
@@ -254,22 +253,134 @@ out:
 	return ret;
 }
 
+static inline int is_32bit_api(void)
+{
+#ifdef CONFIG_COMPAT
+	return is_compat_task();
+#else
+	return (BITS_PER_LONG == 32);
+#endif
+}
+
 /*
  * These functions convert from the major/minor hash to an f_pos
- * value.
+ * value for dx directories
+ *
+ * Upper layer (for example NFS) should specify FMODE_32BITHASH or
+ * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted
+ * directly on both 32-bit and 64-bit nodes, under such case, neither
+ * FMODE_32BITHASH nor FMODE_64BITHASH is specified.
+ */
+static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return major >> 1;
+	else
+		return ((__u64)(major >> 1) << 32) | (__u64)minor;
+}
+
+static inline __u32 pos2maj_hash(struct file *filp, loff_t pos)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return (pos << 1) & 0xffffffff;
+	else
+		return ((pos >> 32) << 1) & 0xffffffff;
+}
+
+static inline __u32 pos2min_hash(struct file *filp, loff_t pos)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return 0;
+	else
+		return pos & 0xffffffff;
+}
+
+/*
+ * Return 32- or 64-bit end-of-file for dx directories
+ */
+static inline loff_t ext4_get_htree_eof(struct file *filp)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return EXT4_HTREE_EOF_32BIT;
+	else
+		return EXT4_HTREE_EOF_64BIT;
+}
+
+
+/*
+ * ext4_dir_llseek() based on generic_file_llseek() to handle both
+ * non-htree and htree directories, where the "offset" is in terms
+ * of the filename hash value instead of the byte offset.
  *
- * Currently we only use major hash numer.  This is unfortunate, but
- * on 32-bit machines, the same VFS interface is used for lseek and
- * llseek, so if we use the 64 bit offset, then the 32-bit versions of
- * lseek/telldir/seekdir will blow out spectacularly, and from within
- * the ext2 low-level routine, we don't know if we're being called by
- * a 64-bit version of the system call or the 32-bit version of the
- * system call.  Worse yet, NFSv2 only allows for a 32-bit readdir
- * cookie.  Sigh.
+ * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX)
+ *       will be invalid once the directory was converted into a dx directory
  */
-#define hash2pos(major, minor)	(major >> 1)
-#define pos2maj_hash(pos)	((pos << 1) & 0xffffffff)
-#define pos2min_hash(pos)	(0)
+loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t ret = -EINVAL;
+	int dx_dir = is_dx_dir(inode);
+
+	mutex_lock(&inode->i_mutex);
+
+	/* NOTE: relative offsets with dx directories might not work
+	 *       as expected, as it is difficult to figure out the
+	 *       correct offset between dx hashes */
+
+	switch (origin) {
+	case SEEK_END:
+		if (unlikely(offset > 0))
+			goto out_err; /* not supported for directories */
+
+		/* so only negative offsets are left, does that have a
+		 * meaning for directories at all? */
+		if (dx_dir)
+			offset += ext4_get_htree_eof(file);
+		else
+			offset += inode->i_size;
+		break;
+	case SEEK_CUR:
+		/*
+		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
+		 * position-querying operation.  Avoid rewriting the "same"
+		 * f_pos value back to the file because a concurrent read(),
+		 * write() or lseek() might have altered it
+		 */
+		if (offset == 0) {
+			offset = file->f_pos;
+			goto out_ok;
+		}
+
+		offset += file->f_pos;
+		break;
+	}
+
+	if (unlikely(offset < 0))
+		goto out_err;
+
+	if (!dx_dir) {
+		if (offset > inode->i_sb->s_maxbytes)
+			goto out_err;
+	} else if (offset > ext4_get_htree_eof(file))
+		goto out_err;
+
+	/* Special lock needed here? */
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+
+out_ok:
+	ret = offset;
+out_err:
+	mutex_unlock(&inode->i_mutex);
+
+	return ret;
+}
 
 /*
  * This structure holds the nodes of the red-black tree used to store
@@ -330,15 +441,16 @@ static void free_rb_tree_fname(struct rb_root *root)
 }
 
 
-static struct dir_private_info *ext4_htree_create_dir_info(loff_t pos)
+static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp,
+							   loff_t pos)
 {
 	struct dir_private_info *p;
 
 	p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
 	if (!p)
 		return NULL;
-	p->curr_hash = pos2maj_hash(pos);
-	p->curr_minor_hash = pos2min_hash(pos);
+	p->curr_hash = pos2maj_hash(filp, pos);
+	p->curr_minor_hash = pos2min_hash(filp, pos);
 	return p;
 }
 
@@ -425,11 +537,12 @@ static int call_filldir(struct file *filp, void *dirent,
 	sb = inode->i_sb;
 
 	if (!fname) {
-		printk(KERN_ERR "EXT4-fs: call_filldir: called with "
-		       "null fname?!?\n");
+		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: "
+			 "called with null fname?!?", __func__, __LINE__,
+			 inode->i_ino, current->comm);
 		return 0;
 	}
-	curr_pos = hash2pos(fname->hash, fname->minor_hash);
+	curr_pos = hash2pos(filp, fname->hash, fname->minor_hash);
 	while (fname) {
 		error = filldir(dirent, fname->name,
 				fname->name_len, curr_pos,
@@ -454,13 +567,13 @@ static int ext4_dx_readdir(struct file *filp,
 	int	ret;
 
 	if (!info) {
-		info = ext4_htree_create_dir_info(filp->f_pos);
+		info = ext4_htree_create_dir_info(filp, filp->f_pos);
 		if (!info)
 			return -ENOMEM;
 		filp->private_data = info;
 	}
 
-	if (filp->f_pos == EXT4_HTREE_EOF)
+	if (filp->f_pos == ext4_get_htree_eof(filp))
 		return 0;	/* EOF */
 
 	/* Some one has messed with f_pos; reset the world */
@@ -468,8 +581,8 @@ static int ext4_dx_readdir(struct file *filp,
 		free_rb_tree_fname(&info->root);
 		info->curr_node = NULL;
 		info->extra_fname = NULL;
-		info->curr_hash = pos2maj_hash(filp->f_pos);
-		info->curr_minor_hash = pos2min_hash(filp->f_pos);
+		info->curr_hash = pos2maj_hash(filp, filp->f_pos);
+		info->curr_minor_hash = pos2min_hash(filp, filp->f_pos);
 	}
 
 	/*
@@ -501,7 +614,7 @@ static int ext4_dx_readdir(struct file *filp,
 			if (ret < 0)
 				return ret;
 			if (ret == 0) {
-				filp->f_pos = EXT4_HTREE_EOF;
+				filp->f_pos = ext4_get_htree_eof(filp);
 				break;
 			}
 			info->curr_node = rb_first(&info->root);
@@ -521,7 +634,7 @@ static int ext4_dx_readdir(struct file *filp,
 			info->curr_minor_hash = fname->minor_hash;
 		} else {
 			if (info->next_hash == ~0) {
-				filp->f_pos = EXT4_HTREE_EOF;
+				filp->f_pos = ext4_get_htree_eof(filp);
 				break;
 			}
 			info->curr_hash = info->next_hash;
@@ -540,3 +653,15 @@ static int ext4_release_dir(struct inode *inode, struct file *filp)
 
 	return 0;
 }
+
+const struct file_operations ext4_dir_operations = {
+	.llseek		= ext4_dir_llseek,
+	.read		= generic_read_dir,
+	.readdir	= ext4_readdir,
+	.unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext4_compat_ioctl,
+#endif
+	.fsync		= ext4_sync_file,
+	.release	= ext4_release_dir,
+};
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 513004fc3d84..ab2594a30f86 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -53,7 +53,7 @@
 		printk(KERN_DEBUG f, ## a);				\
 	} while (0)
 #else
-#define ext4_debug(f, a...)	do {} while (0)
+#define ext4_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 #define EXT4_ERROR_INODE(inode, fmt, a...) \
@@ -184,6 +184,8 @@ struct mpage_da_data {
 #define	EXT4_IO_END_UNWRITTEN	0x0001
 #define EXT4_IO_END_ERROR	0x0002
 #define EXT4_IO_END_QUEUED	0x0004
+#define EXT4_IO_END_DIRECT	0x0008
+#define EXT4_IO_END_IN_FSYNC	0x0010
 
 struct ext4_io_page {
 	struct page	*p_page;
@@ -192,18 +194,25 @@ struct ext4_io_page {
 
 #define MAX_IO_PAGES 128
 
+/*
+ * For converting uninitialized extents on a work queue.
+ *
+ * 'page' is only used from the writepage() path; 'pages' is only used for
+ * buffered writes; they are used to keep page references until conversion
+ * takes place.  For AIO/DIO, neither field is filled in.
+ */
 typedef struct ext4_io_end {
 	struct list_head	list;		/* per-file finished IO list */
 	struct inode		*inode;		/* file being written to */
 	unsigned int		flag;		/* unwritten or not */
-	struct page		*page;		/* page struct for buffer write */
+	struct page		*page;		/* for writepage() path */
 	loff_t			offset;		/* offset in the file */
 	ssize_t			size;		/* size of the extent */
 	struct work_struct	work;		/* data work queue */
 	struct kiocb		*iocb;		/* iocb struct for AIO */
 	int			result;		/* error value for AIO */
-	int			num_io_pages;
-	struct ext4_io_page	*pages[MAX_IO_PAGES];
+	int			num_io_pages;   /* for writepages() */
+	struct ext4_io_page	*pages[MAX_IO_PAGES]; /* for writepages() */
 } ext4_io_end_t;
 
 struct ext4_io_submit {
@@ -923,6 +932,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_ERRORS_CONT		0x00010	/* Continue on errors */
 #define EXT4_MOUNT_ERRORS_RO		0x00020	/* Remount fs ro on errors */
 #define EXT4_MOUNT_ERRORS_PANIC		0x00040	/* Panic on errors */
+#define EXT4_MOUNT_ERRORS_MASK		0x00070
 #define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
 #define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
 #define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
@@ -941,7 +951,6 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
-#define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
 #define EXT4_MOUNT_MBLK_IO_SUBMIT	0x4000000 /* multi-block io submits */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
@@ -1142,6 +1151,7 @@ struct ext4_sb_info {
 	unsigned int s_mount_opt;
 	unsigned int s_mount_opt2;
 	unsigned int s_mount_flags;
+	unsigned int s_def_mount_opt;
 	ext4_fsblk_t s_sb_block;
 	uid_t s_resuid;
 	gid_t s_resgid;
@@ -1420,8 +1430,9 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
 #define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
 #define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
-#define EXT4_FEATURE_INCOMPAT_INLINEDATA	0x2000 /* data in inode */
+#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM	0x2000 /* use crc32c for bg */
 #define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
+#define EXT4_FEATURE_INCOMPAT_INLINEDATA	0x8000 /* data in inode */
 
 #define EXT2_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
 #define EXT2_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1612,7 +1623,11 @@ struct dx_hash_info
 	u32		*seed;
 };
 
-#define EXT4_HTREE_EOF	0x7fffffff
+
+/* 32 and 64 bit signed EOF for dx directories */
+#define EXT4_HTREE_EOF_32BIT   ((1UL  << (32 - 1)) - 1)
+#define EXT4_HTREE_EOF_64BIT   ((1ULL << (64 - 1)) - 1)
+
 
 /*
  * Control parameters used by ext4_htree_next_block
@@ -1794,8 +1809,14 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 						    ext4_group_t block_group,
 						    struct buffer_head ** bh);
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
-struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
-				      ext4_group_t block_group);
+
+extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
+						ext4_group_t block_group);
+extern int ext4_wait_block_bitmap(struct super_block *sb,
+				  ext4_group_t block_group,
+				  struct buffer_head *bh);
+extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
+						  ext4_group_t block_group);
 extern void ext4_init_block_bitmap(struct super_block *sb,
 				   struct buffer_head *bh,
 				   ext4_group_t group,
@@ -1841,6 +1862,7 @@ extern void ext4_check_inodes_bitmap(struct super_block *);
 extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
 extern int ext4_init_inode_table(struct super_block *sb,
 				 ext4_group_t group, int barrier);
+extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index a52db3a69a30..0f58b86e3a02 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -47,9 +47,9 @@
  */
 #define EXT_DEBUG__
 #ifdef EXT_DEBUG
-#define ext_debug(a...)		printk(a)
+#define ext_debug(fmt, ...)	printk(fmt, ##__VA_ARGS__)
 #else
-#define ext_debug(a...)
+#define ext_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 /*
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5802fa1dab18..83b20fcf9400 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -104,6 +104,78 @@
 #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
 #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
 
+/**
+ *   struct ext4_journal_cb_entry - Base structure for callback information.
+ *
+ *   This struct is a 'seed' structure for a using with your own callback
+ *   structs. If you are using callbacks you must allocate one of these
+ *   or another struct of your own definition which has this struct
+ *   as it's first element and pass it to ext4_journal_callback_add().
+ */
+struct ext4_journal_cb_entry {
+	/* list information for other callbacks attached to the same handle */
+	struct list_head jce_list;
+
+	/*  Function to call with this callback structure */
+	void (*jce_func)(struct super_block *sb,
+			 struct ext4_journal_cb_entry *jce, int error);
+
+	/* user data goes here */
+};
+
+/**
+ * ext4_journal_callback_add: add a function to call after transaction commit
+ * @handle: active journal transaction handle to register callback on
+ * @func: callback function to call after the transaction has committed:
+ *        @sb: superblock of current filesystem for transaction
+ *        @jce: returned journal callback data
+ *        @rc: journal state at commit (0 = transaction committed properly)
+ * @jce: journal callback data (internal and function private data struct)
+ *
+ * The registered function will be called in the context of the journal thread
+ * after the transaction for which the handle was created has completed.
+ *
+ * No locks are held when the callback function is called, so it is safe to
+ * call blocking functions from within the callback, but the callback should
+ * not block or run for too long, or the filesystem will be blocked waiting for
+ * the next transaction to commit. No journaling functions can be used, or
+ * there is a risk of deadlock.
+ *
+ * There is no guaranteed calling order of multiple registered callbacks on
+ * the same transaction.
+ */
+static inline void ext4_journal_callback_add(handle_t *handle,
+			void (*func)(struct super_block *sb,
+				     struct ext4_journal_cb_entry *jce,
+				     int rc),
+			struct ext4_journal_cb_entry *jce)
+{
+	struct ext4_sb_info *sbi =
+			EXT4_SB(handle->h_transaction->t_journal->j_private);
+
+	/* Add the jce to transaction's private list */
+	jce->jce_func = func;
+	spin_lock(&sbi->s_md_lock);
+	list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
+	spin_unlock(&sbi->s_md_lock);
+}
+
+/**
+ * ext4_journal_callback_del: delete a registered callback
+ * @handle: active journal transaction handle on which callback was registered
+ * @jce: registered journal callback entry to unregister
+ */
+static inline void ext4_journal_callback_del(handle_t *handle,
+					     struct ext4_journal_cb_entry *jce)
+{
+	struct ext4_sb_info *sbi =
+			EXT4_SB(handle->h_transaction->t_journal->j_private);
+
+	spin_lock(&sbi->s_md_lock);
+	list_del_init(&jce->jce_list);
+	spin_unlock(&sbi->s_md_lock);
+}
+
 int
 ext4_mark_iloc_dirty(handle_t *handle,
 		     struct inode *inode,
@@ -261,43 +333,45 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
 /* super.c */
 int ext4_force_commit(struct super_block *sb);
 
-static inline int ext4_should_journal_data(struct inode *inode)
+/*
+ * Ext4 inode journal modes
+ */
+#define EXT4_INODE_JOURNAL_DATA_MODE	0x01 /* journal data mode */
+#define EXT4_INODE_ORDERED_DATA_MODE	0x02 /* ordered data mode */
+#define EXT4_INODE_WRITEBACK_DATA_MODE	0x04 /* writeback data mode */
+
+static inline int ext4_inode_journal_mode(struct inode *inode)
 {
 	if (EXT4_JOURNAL(inode) == NULL)
-		return 0;
-	if (!S_ISREG(inode->i_mode))
-		return 1;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
-		return 1;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 1;
-	return 0;
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	/* We do not support data journalling with delayed allocation */
+	if (!S_ISREG(inode->i_mode) ||
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	else
+		BUG();
+}
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
 }
 
 static inline int ext4_should_order_data(struct inode *inode)
 {
-	if (EXT4_JOURNAL(inode) == NULL)
-		return 0;
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
-		return 1;
-	return 0;
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
 }
 
 static inline int ext4_should_writeback_data(struct inode *inode)
 {
-	if (EXT4_JOURNAL(inode) == NULL)
-		return 1;
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
-		return 1;
-	return 0;
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
 }
 
 /*
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 74f23c292e1b..1421938e6792 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -44,6 +44,14 @@
 
 #include <trace/events/ext4.h>
 
+/*
+ * used by extent splitting.
+ */
+#define EXT4_EXT_MAY_ZEROOUT	0x1  /* safe to zeroout if split fails \
+					due to ENOSPC */
+#define EXT4_EXT_MARK_UNINIT1	0x2  /* mark first half uninitialized */
+#define EXT4_EXT_MARK_UNINIT2	0x4  /* mark second half uninitialized */
+
 static int ext4_split_extent(handle_t *handle,
 				struct inode *inode,
 				struct ext4_ext_path *path,
@@ -51,6 +59,13 @@ static int ext4_split_extent(handle_t *handle,
 				int split_flag,
 				int flags);
 
+static int ext4_split_extent_at(handle_t *handle,
+			     struct inode *inode,
+			     struct ext4_ext_path *path,
+			     ext4_lblk_t split,
+			     int split_flag,
+			     int flags);
+
 static int ext4_ext_truncate_extend_restart(handle_t *handle,
 					    struct inode *inode,
 					    int needed)
@@ -300,6 +315,8 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 	ext4_fsblk_t block = ext4_ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
 
+	if (len == 0)
+		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
 
@@ -2308,7 +2325,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	struct ext4_extent *ex;
 
 	/* the header must be checked already in ext4_ext_remove_space() */
-	ext_debug("truncate since %u in leaf\n", start);
+	ext_debug("truncate since %u in leaf to %u\n", start, end);
 	if (!path[depth].p_hdr)
 		path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
 	eh = path[depth].p_hdr;
@@ -2343,14 +2360,17 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		ext_debug("  border %u:%u\n", a, b);
 
 		/* If this extent is beyond the end of the hole, skip it */
-		if (end <= ex_ee_block) {
+		if (end < ex_ee_block) {
 			ex--;
 			ex_ee_block = le32_to_cpu(ex->ee_block);
 			ex_ee_len = ext4_ext_get_actual_len(ex);
 			continue;
 		} else if (b != ex_ee_block + ex_ee_len - 1) {
-			EXT4_ERROR_INODE(inode,"  bad truncate %u:%u\n",
-					 start, end);
+			EXT4_ERROR_INODE(inode,
+					 "can not handle truncate %u:%u "
+					 "on extent %u:%u",
+					 start, end, ex_ee_block,
+					 ex_ee_block + ex_ee_len - 1);
 			err = -EIO;
 			goto out;
 		} else if (a != ex_ee_block) {
@@ -2482,7 +2502,8 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path)
 	return 1;
 }
 
-static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
+static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
+				 ext4_lblk_t end)
 {
 	struct super_block *sb = inode->i_sb;
 	int depth = ext_depth(inode);
@@ -2491,7 +2512,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
 	handle_t *handle;
 	int i, err;
 
-	ext_debug("truncate since %u\n", start);
+	ext_debug("truncate since %u to %u\n", start, end);
 
 	/* probably first extent we're gonna free will be last in block */
 	handle = ext4_journal_start(inode, depth + 1);
@@ -2504,6 +2525,61 @@ again:
 	trace_ext4_ext_remove_space(inode, start, depth);
 
 	/*
+	 * Check if we are removing extents inside the extent tree. If that
+	 * is the case, we are going to punch a hole inside the extent tree
+	 * so we have to check whether we need to split the extent covering
+	 * the last block to remove so we can easily remove the part of it
+	 * in ext4_ext_rm_leaf().
+	 */
+	if (end < EXT_MAX_BLOCKS - 1) {
+		struct ext4_extent *ex;
+		ext4_lblk_t ee_block;
+
+		/* find extent for this block */
+		path = ext4_ext_find_extent(inode, end, NULL);
+		if (IS_ERR(path)) {
+			ext4_journal_stop(handle);
+			return PTR_ERR(path);
+		}
+		depth = ext_depth(inode);
+		ex = path[depth].p_ext;
+		if (!ex)
+			goto cont;
+
+		ee_block = le32_to_cpu(ex->ee_block);
+
+		/*
+		 * See if the last block is inside the extent, if so split
+		 * the extent at 'end' block so we can easily remove the
+		 * tail of the first part of the split extent in
+		 * ext4_ext_rm_leaf().
+		 */
+		if (end >= ee_block &&
+		    end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
+			int split_flag = 0;
+
+			if (ext4_ext_is_uninitialized(ex))
+				split_flag = EXT4_EXT_MARK_UNINIT1 |
+					     EXT4_EXT_MARK_UNINIT2;
+
+			/*
+			 * Split the extent in two so that 'end' is the last
+			 * block in the first new extent
+			 */
+			err = ext4_split_extent_at(handle, inode, path,
+						end + 1, split_flag,
+						EXT4_GET_BLOCKS_PRE_IO |
+						EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
+
+			if (err < 0)
+				goto out;
+		}
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+cont:
+
+	/*
 	 * We start scanning from right side, freeing all the blocks
 	 * after i_size and walking into the tree depth-wise.
 	 */
@@ -2515,6 +2591,7 @@ again:
 	}
 	path[0].p_depth = depth;
 	path[0].p_hdr = ext_inode_hdr(inode);
+
 	if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
 		err = -EIO;
 		goto out;
@@ -2526,7 +2603,7 @@ again:
 			/* this is leaf block */
 			err = ext4_ext_rm_leaf(handle, inode, path,
 					       &partial_cluster, start,
-					       EXT_MAX_BLOCKS - 1);
+					       end);
 			/* root level has p_bh == NULL, brelse() eats this */
 			brelse(path[i].p_bh);
 			path[i].p_bh = NULL;
@@ -2651,17 +2728,17 @@ void ext4_ext_init(struct super_block *sb)
 
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
 #if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS)
-		printk(KERN_INFO "EXT4-fs: file extents enabled");
+		printk(KERN_INFO "EXT4-fs: file extents enabled"
 #ifdef AGGRESSIVE_TEST
-		printk(", aggressive tests");
+		       ", aggressive tests"
 #endif
 #ifdef CHECK_BINSEARCH
-		printk(", check binsearch");
+		       ", check binsearch"
 #endif
 #ifdef EXTENTS_STATS
-		printk(", stats");
+		       ", stats"
 #endif
-		printk("\n");
+		       "\n");
 #endif
 #ifdef EXTENTS_STATS
 		spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
@@ -2709,14 +2786,6 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 }
 
 /*
- * used by extent splitting.
- */
-#define EXT4_EXT_MAY_ZEROOUT	0x1  /* safe to zeroout if split fails \
-					due to ENOSPC */
-#define EXT4_EXT_MARK_UNINIT1	0x2  /* mark first half uninitialized */
-#define EXT4_EXT_MARK_UNINIT2	0x4  /* mark second half uninitialized */
-
-/*
  * ext4_split_extent_at() splits an extent at given block.
  *
  * @handle: the journal handle
@@ -3224,11 +3293,13 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 
-	if (unlikely(!eh->eh_entries)) {
-		EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and "
-				 "EOFBLOCKS_FL set");
-		return -EIO;
-	}
+	/*
+	 * We're going to remove EOFBLOCKS_FL entirely in future so we
+	 * do not care for this case anymore. Simply remove the flag
+	 * if there are no extents.
+	 */
+	if (unlikely(!eh->eh_entries))
+		goto out;
 	last_ex = EXT_LAST_EXTENT(eh);
 	/*
 	 * We should clear the EOFBLOCKS_FL flag if we are writing the
@@ -3252,6 +3323,7 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
 	for (i = depth-1; i >= 0; i--)
 		if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
 			return 0;
+out:
 	ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	return ext4_mark_inode_dirty(handle, inode);
 }
@@ -3710,8 +3782,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	int free_on_err = 0, err = 0, depth, ret;
 	unsigned int allocated = 0, offset = 0;
 	unsigned int allocated_clusters = 0;
-	unsigned int punched_out = 0;
-	unsigned int result = 0;
 	struct ext4_allocation_request ar;
 	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
 	ext4_lblk_t cluster_offset;
@@ -3721,8 +3791,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
 
 	/* check in cache */
-	if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
-		ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
+	if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
 		if (!newex.ee_start_lo && !newex.ee_start_hi) {
 			if ((sbi->s_cluster_ratio > 1) &&
 			    ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
@@ -3790,113 +3859,25 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 
 		/* if found extent covers block, simply return it */
 		if (in_range(map->m_lblk, ee_block, ee_len)) {
-			struct ext4_map_blocks punch_map;
-			ext4_fsblk_t partial_cluster = 0;
-
 			newblock = map->m_lblk - ee_block + ee_start;
 			/* number of remaining blocks in the extent */
 			allocated = ee_len - (map->m_lblk - ee_block);
 			ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
 				  ee_block, ee_len, newblock);
 
-			if ((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0) {
-				/*
-				 * Do not put uninitialized extent
-				 * in the cache
-				 */
-				if (!ext4_ext_is_uninitialized(ex)) {
-					ext4_ext_put_in_cache(inode, ee_block,
-						ee_len, ee_start);
-					goto out;
-				}
-				ret = ext4_ext_handle_uninitialized_extents(
-					handle, inode, map, path, flags,
-					allocated, newblock);
-				return ret;
-			}
-
-			/*
-			 * Punch out the map length, but only to the
-			 * end of the extent
-			 */
-			punched_out = allocated < map->m_len ?
-				allocated : map->m_len;
-
 			/*
-			 * Sense extents need to be converted to
-			 * uninitialized, they must fit in an
-			 * uninitialized extent
+			 * Do not put uninitialized extent
+			 * in the cache
 			 */
-			if (punched_out > EXT_UNINIT_MAX_LEN)
-				punched_out = EXT_UNINIT_MAX_LEN;
-
-			punch_map.m_lblk = map->m_lblk;
-			punch_map.m_pblk = newblock;
-			punch_map.m_len = punched_out;
-			punch_map.m_flags = 0;
-
-			/* Check to see if the extent needs to be split */
-			if (punch_map.m_len != ee_len ||
-				punch_map.m_lblk != ee_block) {
-
-				ret = ext4_split_extent(handle, inode,
-				path, &punch_map, 0,
-				EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
-				EXT4_GET_BLOCKS_PRE_IO);
-
-				if (ret < 0) {
-					err = ret;
-					goto out2;
-				}
-				/*
-				 * find extent for the block at
-				 * the start of the hole
-				 */
-				ext4_ext_drop_refs(path);
-				kfree(path);
-
-				path = ext4_ext_find_extent(inode,
-				map->m_lblk, NULL);
-				if (IS_ERR(path)) {
-					err = PTR_ERR(path);
-					path = NULL;
-					goto out2;
-				}
-
-				depth = ext_depth(inode);
-				ex = path[depth].p_ext;
-				ee_len = ext4_ext_get_actual_len(ex);
-				ee_block = le32_to_cpu(ex->ee_block);
-				ee_start = ext4_ext_pblock(ex);
-
-			}
-
-			ext4_ext_mark_uninitialized(ex);
-
-			ext4_ext_invalidate_cache(inode);
-
-			err = ext4_ext_rm_leaf(handle, inode, path,
-					       &partial_cluster, map->m_lblk,
-					       map->m_lblk + punched_out);
-
-			if (!err && path->p_hdr->eh_entries == 0) {
-				/*
-				 * Punch hole freed all of this sub tree,
-				 * so we need to correct eh_depth
-				 */
-				err = ext4_ext_get_access(handle, inode, path);
-				if (err == 0) {
-					ext_inode_hdr(inode)->eh_depth = 0;
-					ext_inode_hdr(inode)->eh_max =
-					cpu_to_le16(ext4_ext_space_root(
-						inode, 0));
-
-					err = ext4_ext_dirty(
-						handle, inode, path);
-				}
+			if (!ext4_ext_is_uninitialized(ex)) {
+				ext4_ext_put_in_cache(inode, ee_block,
+					ee_len, ee_start);
+				goto out;
 			}
-
-			goto out2;
+			ret = ext4_ext_handle_uninitialized_extents(
+				handle, inode, map, path, flags,
+				allocated, newblock);
+			return ret;
 		}
 	}
 
@@ -4165,13 +4146,11 @@ out2:
 		ext4_ext_drop_refs(path);
 		kfree(path);
 	}
-	result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
-			punched_out : allocated;
 
 	trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
-		newblock, map->m_len, err ? err : result);
+		newblock, map->m_len, err ? err : allocated);
 
-	return err ? err : result;
+	return err ? err : allocated;
 }
 
 void ext4_ext_truncate(struct inode *inode)
@@ -4228,7 +4207,7 @@ void ext4_ext_truncate(struct inode *inode)
 
 	last_block = (inode->i_size + sb->s_blocksize - 1)
 			>> EXT4_BLOCK_SIZE_BITS(sb);
-	err = ext4_ext_remove_space(inode, last_block);
+	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
 
 	/* In a multi-transaction truncate, we only make the final
 	 * transaction synchronous.
@@ -4436,10 +4415,11 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
 				      EXT4_GET_BLOCKS_IO_CONVERT_EXT);
 		if (ret <= 0) {
 			WARN_ON(ret <= 0);
-			printk(KERN_ERR "%s: ext4_ext_map_blocks "
-				    "returned error inode#%lu, block=%u, "
-				    "max_blocks=%u", __func__,
-				    inode->i_ino, map.m_lblk, map.m_len);
+			ext4_msg(inode->i_sb, KERN_ERR,
+				 "%s:%d: inode #%lu: block %u: len %u: "
+				 "ext4_ext_map_blocks returned %d",
+				 __func__, __LINE__, inode->i_ino, map.m_lblk,
+				 map.m_len, ret);
 		}
 		ext4_mark_inode_dirty(handle, inode);
 		ret2 = ext4_journal_stop(handle);
@@ -4705,14 +4685,12 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
 {
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct super_block *sb = inode->i_sb;
-	struct ext4_ext_cache cache_ex;
-	ext4_lblk_t first_block, last_block, num_blocks, iblock, max_blocks;
+	ext4_lblk_t first_block, stop_block;
 	struct address_space *mapping = inode->i_mapping;
-	struct ext4_map_blocks map;
 	handle_t *handle;
 	loff_t first_page, last_page, page_len;
 	loff_t first_page_offset, last_page_offset;
-	int ret, credits, blocks_released, err = 0;
+	int credits, err = 0;
 
 	/* No need to punch hole beyond i_size */
 	if (offset >= inode->i_size)
@@ -4728,10 +4706,6 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
 		   offset;
 	}
 
-	first_block = (offset + sb->s_blocksize - 1) >>
-		EXT4_BLOCK_SIZE_BITS(sb);
-	last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
-
 	first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	last_page = (offset + length) >> PAGE_CACHE_SHIFT;
 
@@ -4810,7 +4784,6 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
 		}
 	}
 
-
 	/*
 	 * If i_size is contained in the last page, we need to
 	 * unmap and zero the partial page after i_size
@@ -4830,73 +4803,22 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
 		}
 	}
 
+	first_block = (offset + sb->s_blocksize - 1) >>
+		EXT4_BLOCK_SIZE_BITS(sb);
+	stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
+
 	/* If there are no blocks to remove, return now */
-	if (first_block >= last_block)
+	if (first_block >= stop_block)
 		goto out;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_ext_invalidate_cache(inode);
 	ext4_discard_preallocations(inode);
 
-	/*
-	 * Loop over all the blocks and identify blocks
-	 * that need to be punched out
-	 */
-	iblock = first_block;
-	blocks_released = 0;
-	while (iblock < last_block) {
-		max_blocks = last_block - iblock;
-		num_blocks = 1;
-		memset(&map, 0, sizeof(map));
-		map.m_lblk = iblock;
-		map.m_len = max_blocks;
-		ret = ext4_ext_map_blocks(handle, inode, &map,
-			EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
-
-		if (ret > 0) {
-			blocks_released += ret;
-			num_blocks = ret;
-		} else if (ret == 0) {
-			/*
-			 * If map blocks could not find the block,
-			 * then it is in a hole.  If the hole was
-			 * not already cached, then map blocks should
-			 * put it in the cache.  So we can get the hole
-			 * out of the cache
-			 */
-			memset(&cache_ex, 0, sizeof(cache_ex));
-			if ((ext4_ext_check_cache(inode, iblock, &cache_ex)) &&
-				!cache_ex.ec_start) {
-
-				/* The hole is cached */
-				num_blocks = cache_ex.ec_block +
-				cache_ex.ec_len - iblock;
-
-			} else {
-				/* The block could not be identified */
-				err = -EIO;
-				break;
-			}
-		} else {
-			/* Map blocks error */
-			err = ret;
-			break;
-		}
-
-		if (num_blocks == 0) {
-			/* This condition should never happen */
-			ext_debug("Block lookup failed");
-			err = -EIO;
-			break;
-		}
-
-		iblock += num_blocks;
-	}
+	err = ext4_ext_remove_space(inode, first_block, stop_block - 1);
 
-	if (blocks_released > 0) {
-		ext4_ext_invalidate_cache(inode);
-		ext4_discard_preallocations(inode);
-	}
+	ext4_ext_invalidate_cache(inode);
+	ext4_discard_preallocations(inode);
 
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 00a2cb753efd..bb6c7d811313 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -89,6 +89,7 @@ int ext4_flush_completed_IO(struct inode *inode)
 		io = list_entry(ei->i_completed_io_list.next,
 				ext4_io_end_t, list);
 		list_del_init(&io->list);
+		io->flag |= EXT4_IO_END_IN_FSYNC;
 		/*
 		 * Calling ext4_end_io_nolock() to convert completed
 		 * IO to written.
@@ -108,6 +109,7 @@ int ext4_flush_completed_IO(struct inode *inode)
 		if (ret < 0)
 			ret2 = ret;
 		spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+		io->flag &= ~EXT4_IO_END_IN_FSYNC;
 	}
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 	return (ret2 < 0) ? ret2 : 0;
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index ac8f168c8ab4..fa8e4911d354 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -200,8 +200,8 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		return -1;
 	}
 	hash = hash & ~1;
-	if (hash == (EXT4_HTREE_EOF << 1))
-		hash = (EXT4_HTREE_EOF-1) << 1;
+	if (hash == (EXT4_HTREE_EOF_32BIT << 1))
+		hash = (EXT4_HTREE_EOF_32BIT - 1) << 1;
 	hinfo->hash = hash;
 	hinfo->minor_hash = minor_hash;
 	return 0;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 25d8c9781ad9..409c2ee7750a 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -92,6 +92,16 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
 	return EXT4_INODES_PER_GROUP(sb);
 }
 
+void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate)
+{
+	if (uptodate) {
+		set_buffer_uptodate(bh);
+		set_bitmap_uptodate(bh);
+	}
+	unlock_buffer(bh);
+	put_bh(bh);
+}
+
 /*
  * Read the inode allocation bitmap for a given block_group, reading
  * into the specified slot in the superblock's bitmap cache.
@@ -147,18 +157,18 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		return bh;
 	}
 	/*
-	 * submit the buffer_head for read. We can
-	 * safely mark the bitmap as uptodate now.
-	 * We do it here so the bitmap uptodate bit
-	 * get set with buffer lock held.
+	 * submit the buffer_head for reading
 	 */
 	trace_ext4_load_inode_bitmap(sb, block_group);
-	set_bitmap_uptodate(bh);
-	if (bh_submit_read(bh) < 0) {
+	bh->b_end_io = ext4_end_bitmap_read;
+	get_bh(bh);
+	submit_bh(READ, bh);
+	wait_on_buffer(bh);
+	if (!buffer_uptodate(bh)) {
 		put_bh(bh);
 		ext4_error(sb, "Cannot read inode bitmap - "
-			    "block_group = %u, inode_bitmap = %llu",
-			    block_group, bitmap_blk);
+			   "block_group = %u, inode_bitmap = %llu",
+			   block_group, bitmap_blk);
 		return NULL;
 	}
 	return bh;
@@ -194,19 +204,20 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	struct ext4_sb_info *sbi;
 	int fatal = 0, err, count, cleared;
 
-	if (atomic_read(&inode->i_count) > 1) {
-		printk(KERN_ERR "ext4_free_inode: inode has count=%d\n",
-		       atomic_read(&inode->i_count));
+	if (!sb) {
+		printk(KERN_ERR "EXT4-fs: %s:%d: inode on "
+		       "nonexistent device\n", __func__, __LINE__);
 		return;
 	}
-	if (inode->i_nlink) {
-		printk(KERN_ERR "ext4_free_inode: inode has nlink=%d\n",
-		       inode->i_nlink);
+	if (atomic_read(&inode->i_count) > 1) {
+		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: count=%d",
+			 __func__, __LINE__, inode->i_ino,
+			 atomic_read(&inode->i_count));
 		return;
 	}
-	if (!sb) {
-		printk(KERN_ERR "ext4_free_inode: inode on "
-		       "nonexistent device\n");
+	if (inode->i_nlink) {
+		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: nlink=%d\n",
+			 __func__, __LINE__, inode->i_ino, inode->i_nlink);
 		return;
 	}
 	sbi = EXT4_SB(sb);
@@ -593,94 +604,6 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 }
 
 /*
- * claim the inode from the inode bitmap. If the group
- * is uninit we need to take the groups's ext4_group_lock
- * and clear the uninit flag. The inode bitmap update
- * and group desc uninit flag clear should be done
- * after holding ext4_group_lock so that ext4_read_inode_bitmap
- * doesn't race with the ext4_claim_inode
- */
-static int ext4_claim_inode(struct super_block *sb,
-			struct buffer_head *inode_bitmap_bh,
-			unsigned long ino, ext4_group_t group, umode_t mode)
-{
-	int free = 0, retval = 0, count;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
-	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
-
-	/*
-	 * We have to be sure that new inode allocation does not race with
-	 * inode table initialization, because otherwise we may end up
-	 * allocating and writing new inode right before sb_issue_zeroout
-	 * takes place and overwriting our new inode with zeroes. So we
-	 * take alloc_sem to prevent it.
-	 */
-	down_read(&grp->alloc_sem);
-	ext4_lock_group(sb, group);
-	if (ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data)) {
-		/* not a free inode */
-		retval = 1;
-		goto err_ret;
-	}
-	ino++;
-	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
-			ino > EXT4_INODES_PER_GROUP(sb)) {
-		ext4_unlock_group(sb, group);
-		up_read(&grp->alloc_sem);
-		ext4_error(sb, "reserved inode or inode > inodes count - "
-			   "block_group = %u, inode=%lu", group,
-			   ino + group * EXT4_INODES_PER_GROUP(sb));
-		return 1;
-	}
-	/* If we didn't allocate from within the initialized part of the inode
-	 * table then we need to initialize up to this inode. */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
-
-		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
-			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
-			/* When marking the block group with
-			 * ~EXT4_BG_INODE_UNINIT we don't want to depend
-			 * on the value of bg_itable_unused even though
-			 * mke2fs could have initialized the same for us.
-			 * Instead we calculated the value below
-			 */
-
-			free = 0;
-		} else {
-			free = EXT4_INODES_PER_GROUP(sb) -
-				ext4_itable_unused_count(sb, gdp);
-		}
-
-		/*
-		 * Check the relative inode number against the last used
-		 * relative inode number in this group. if it is greater
-		 * we need to  update the bg_itable_unused count
-		 *
-		 */
-		if (ino > free)
-			ext4_itable_unused_set(sb, gdp,
-					(EXT4_INODES_PER_GROUP(sb) - ino));
-	}
-	count = ext4_free_inodes_count(sb, gdp) - 1;
-	ext4_free_inodes_set(sb, gdp, count);
-	if (S_ISDIR(mode)) {
-		count = ext4_used_dirs_count(sb, gdp) + 1;
-		ext4_used_dirs_set(sb, gdp, count);
-		if (sbi->s_log_groups_per_flex) {
-			ext4_group_t f = ext4_flex_group(sbi, group);
-
-			atomic_inc(&sbi->s_flex_groups[f].used_dirs);
-		}
-	}
-	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
-err_ret:
-	ext4_unlock_group(sb, group);
-	up_read(&grp->alloc_sem);
-	return retval;
-}
-
-/*
  * There are two policies for allocating an inode.  If the new inode is
  * a directory, then a forward search is made for a block group with both
  * free space and a low directory-to-inode ratio; if that fails, then of
@@ -741,6 +664,11 @@ got_group:
 	if (ret2 == -1)
 		goto out;
 
+	/*
+	 * Normally we will only go through one pass of this loop,
+	 * unless we get unlucky and it turns out the group we selected
+	 * had its last inode grabbed by someone else.
+	 */
 	for (i = 0; i < ngroups; i++, ino = 0) {
 		err = -EIO;
 
@@ -757,51 +685,24 @@ repeat_in_this_group:
 		ino = ext4_find_next_zero_bit((unsigned long *)
 					      inode_bitmap_bh->b_data,
 					      EXT4_INODES_PER_GROUP(sb), ino);
-
-		if (ino < EXT4_INODES_PER_GROUP(sb)) {
-
-			BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
-			err = ext4_journal_get_write_access(handle,
-							    inode_bitmap_bh);
-			if (err)
-				goto fail;
-
-			BUFFER_TRACE(group_desc_bh, "get_write_access");
-			err = ext4_journal_get_write_access(handle,
-								group_desc_bh);
-			if (err)
-				goto fail;
-			if (!ext4_claim_inode(sb, inode_bitmap_bh,
-						ino, group, mode)) {
-				/* we won it */
-				BUFFER_TRACE(inode_bitmap_bh,
-					"call ext4_handle_dirty_metadata");
-				err = ext4_handle_dirty_metadata(handle,
-								 NULL,
-							inode_bitmap_bh);
-				if (err)
-					goto fail;
-				/* zero bit is inode number 1*/
-				ino++;
-				goto got;
-			}
-			/* we lost it */
-			ext4_handle_release_buffer(handle, inode_bitmap_bh);
-			ext4_handle_release_buffer(handle, group_desc_bh);
-
-			if (++ino < EXT4_INODES_PER_GROUP(sb))
-				goto repeat_in_this_group;
+		if (ino >= EXT4_INODES_PER_GROUP(sb)) {
+			if (++group == ngroups)
+				group = 0;
+			continue;
 		}
-
-		/*
-		 * This case is possible in concurrent environment.  It is very
-		 * rare.  We cannot repeat the find_group_xxx() call because
-		 * that will simply return the same blockgroup, because the
-		 * group descriptor metadata has not yet been updated.
-		 * So we just go onto the next blockgroup.
-		 */
-		if (++group == ngroups)
-			group = 0;
+		if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
+			ext4_error(sb, "reserved inode found cleared - "
+				   "inode=%lu", ino + 1);
+			continue;
+		}
+		ext4_lock_group(sb, group);
+		ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data);
+		ext4_unlock_group(sb, group);
+		ino++;		/* the inode bitmap is zero-based */
+		if (!ret2)
+			goto got; /* we grabbed the inode! */
+		if (ino < EXT4_INODES_PER_GROUP(sb))
+			goto repeat_in_this_group;
 	}
 	err = -ENOSPC;
 	goto out;
@@ -838,6 +739,59 @@ got:
 		if (err)
 			goto fail;
 	}
+
+	BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
+	if (err)
+		goto fail;
+
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, group_desc_bh);
+	if (err)
+		goto fail;
+
+	/* Update the relevant bg descriptor fields */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+		int free;
+		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+		down_read(&grp->alloc_sem); /* protect vs itable lazyinit */
+		ext4_lock_group(sb, group); /* while we modify the bg desc */
+		free = EXT4_INODES_PER_GROUP(sb) -
+			ext4_itable_unused_count(sb, gdp);
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+			free = 0;
+		}
+		/*
+		 * Check the relative inode number against the last used
+		 * relative inode number in this group. if it is greater
+		 * we need to update the bg_itable_unused count
+		 */
+		if (ino > free)
+			ext4_itable_unused_set(sb, gdp,
+					(EXT4_INODES_PER_GROUP(sb) - ino));
+		up_read(&grp->alloc_sem);
+	}
+	ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
+	if (S_ISDIR(mode)) {
+		ext4_used_dirs_set(sb, gdp, ext4_used_dirs_count(sb, gdp) + 1);
+		if (sbi->s_log_groups_per_flex) {
+			ext4_group_t f = ext4_flex_group(sbi, group);
+
+			atomic_inc(&sbi->s_flex_groups[f].used_dirs);
+		}
+	}
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+		gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+		ext4_unlock_group(sb, group);
+	}
+
+	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
+	if (err)
+		goto fail;
+
 	BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
 	err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
 	if (err)
@@ -1101,7 +1055,7 @@ unsigned long ext4_count_dirs(struct super_block * sb)
  * where it is called from on active part of filesystem is ext4lazyinit
  * thread, so we do not need any special locks, however we have to prevent
  * inode allocation from the current group, so we take alloc_sem lock, to
- * block ext4_claim_inode until we are finished.
+ * block ext4_new_inode() until we are finished.
  */
 int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 				 int barrier)
@@ -1149,9 +1103,9 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 			    sbi->s_inodes_per_block);
 
 	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
-		ext4_error(sb, "Something is wrong with group %u\n"
-			   "Used itable blocks: %d"
-			   "itable unused count: %u\n",
+		ext4_error(sb, "Something is wrong with group %u: "
+			   "used itable blocks: %d; "
+			   "itable unused count: %u",
 			   group, used_blks,
 			   ext4_itable_unused_count(sb, gdp));
 		ret = 1;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index feaa82fe629d..c77b0bd2c711 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -272,7 +272,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 	trace_ext4_da_update_reserve_space(inode, used, quota_claim);
 	if (unlikely(used > ei->i_reserved_data_blocks)) {
 		ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
-			 "with only %d reserved data blocks\n",
+			 "with only %d reserved data blocks",
 			 __func__, inode->i_ino, used,
 			 ei->i_reserved_data_blocks);
 		WARN_ON(1);
@@ -1165,7 +1165,7 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
 		 */
 		ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
 			 "ino %lu, to_free %d with only %d reserved "
-			 "data blocks\n", inode->i_ino, to_free,
+			 "data blocks", inode->i_ino, to_free,
 			 ei->i_reserved_data_blocks);
 		WARN_ON(1);
 		to_free = ei->i_reserved_data_blocks;
@@ -1428,20 +1428,22 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
 static void ext4_print_free_blocks(struct inode *inode)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	printk(KERN_CRIT "Total free blocks count %lld\n",
+	struct super_block *sb = inode->i_sb;
+
+	ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld",
 	       EXT4_C2B(EXT4_SB(inode->i_sb),
 			ext4_count_free_clusters(inode->i_sb)));
-	printk(KERN_CRIT "Free/Dirty block details\n");
-	printk(KERN_CRIT "free_blocks=%lld\n",
+	ext4_msg(sb, KERN_CRIT, "Free/Dirty block details");
+	ext4_msg(sb, KERN_CRIT, "free_blocks=%lld",
 	       (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
 		percpu_counter_sum(&sbi->s_freeclusters_counter)));
-	printk(KERN_CRIT "dirty_blocks=%lld\n",
+	ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld",
 	       (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
 		percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
-	printk(KERN_CRIT "Block reservation details\n");
-	printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
-	       EXT4_I(inode)->i_reserved_data_blocks);
-	printk(KERN_CRIT "i_reserved_meta_blocks=%u\n",
+	ext4_msg(sb, KERN_CRIT, "Block reservation details");
+	ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u",
+		 EXT4_I(inode)->i_reserved_data_blocks);
+	ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u",
 	       EXT4_I(inode)->i_reserved_meta_blocks);
 	return;
 }
@@ -2482,13 +2484,14 @@ static int ext4_da_write_end(struct file *file,
 	int write_mode = (int)(unsigned long)fsdata;
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC) {
-		if (ext4_should_order_data(inode)) {
+		switch (ext4_inode_journal_mode(inode)) {
+		case EXT4_INODE_ORDERED_DATA_MODE:
 			return ext4_ordered_write_end(file, mapping, pos,
 					len, copied, page, fsdata);
-		} else if (ext4_should_writeback_data(inode)) {
+		case EXT4_INODE_WRITEBACK_DATA_MODE:
 			return ext4_writeback_write_end(file, mapping, pos,
 					len, copied, page, fsdata);
-		} else {
+		default:
 			BUG();
 		}
 	}
@@ -2763,7 +2766,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 		goto out;
 
 	ext_debug("ext4_end_io_dio(): io_end 0x%p "
-		  "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
+		  "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
  		  iocb->private, io_end->inode->i_ino, iocb, offset,
 		  size);
 
@@ -2795,9 +2798,6 @@ out:
 
 	/* queue the work to convert unwritten extents to written */
 	queue_work(wq, &io_end->work);
-
-	/* XXX: probably should move into the real I/O completion handler */
-	inode_dio_done(inode);
 }
 
 static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
@@ -2811,8 +2811,9 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
 		goto out;
 
 	if (!(io_end->inode->i_sb->s_flags & MS_ACTIVE)) {
-		printk("sb umounted, discard end_io request for inode %lu\n",
-			io_end->inode->i_ino);
+		ext4_msg(io_end->inode->i_sb, KERN_INFO,
+			 "sb umounted, discard end_io request for inode %lu",
+			 io_end->inode->i_ino);
 		ext4_free_io_end(io_end);
 		goto out;
 	}
@@ -2921,9 +2922,12 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		iocb->private = NULL;
 		EXT4_I(inode)->cur_aio_dio = NULL;
 		if (!is_sync_kiocb(iocb)) {
-			iocb->private = ext4_init_io_end(inode, GFP_NOFS);
-			if (!iocb->private)
+			ext4_io_end_t *io_end =
+				ext4_init_io_end(inode, GFP_NOFS);
+			if (!io_end)
 				return -ENOMEM;
+			io_end->flag |= EXT4_IO_END_DIRECT;
+			iocb->private = io_end;
 			/*
 			 * we save the io structure for current async
 			 * direct IO, so that later ext4_map_blocks()
@@ -2940,7 +2944,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 					 ext4_get_block_write,
 					 ext4_end_io_dio,
 					 NULL,
-					 DIO_LOCKING | DIO_SKIP_HOLES);
+					 DIO_LOCKING);
 		if (iocb->private)
 			EXT4_I(inode)->cur_aio_dio = NULL;
 		/*
@@ -3086,18 +3090,25 @@ static const struct address_space_operations ext4_da_aops = {
 
 void ext4_set_aops(struct inode *inode)
 {
-	if (ext4_should_order_data(inode) &&
-		test_opt(inode->i_sb, DELALLOC))
-		inode->i_mapping->a_ops = &ext4_da_aops;
-	else if (ext4_should_order_data(inode))
-		inode->i_mapping->a_ops = &ext4_ordered_aops;
-	else if (ext4_should_writeback_data(inode) &&
-		 test_opt(inode->i_sb, DELALLOC))
-		inode->i_mapping->a_ops = &ext4_da_aops;
-	else if (ext4_should_writeback_data(inode))
-		inode->i_mapping->a_ops = &ext4_writeback_aops;
-	else
+	switch (ext4_inode_journal_mode(inode)) {
+	case EXT4_INODE_ORDERED_DATA_MODE:
+		if (test_opt(inode->i_sb, DELALLOC))
+			inode->i_mapping->a_ops = &ext4_da_aops;
+		else
+			inode->i_mapping->a_ops = &ext4_ordered_aops;
+		break;
+	case EXT4_INODE_WRITEBACK_DATA_MODE:
+		if (test_opt(inode->i_sb, DELALLOC))
+			inode->i_mapping->a_ops = &ext4_da_aops;
+		else
+			inode->i_mapping->a_ops = &ext4_writeback_aops;
+		break;
+	case EXT4_INODE_JOURNAL_DATA_MODE:
 		inode->i_mapping->a_ops = &ext4_journalled_aops;
+		break;
+	default:
+		BUG();
+	}
 }
 
 
@@ -3329,16 +3340,16 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 {
 	struct inode *inode = file->f_path.dentry->d_inode;
 	if (!S_ISREG(inode->i_mode))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		/* TODO: Add support for non extent hole punching */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
 		/* TODO: Add support for bigalloc file systems */
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	return ext4_ext_punch_hole(file, offset, length);
@@ -3924,10 +3935,8 @@ static int ext4_do_update_inode(handle_t *handle,
 			ext4_update_dynamic_rev(sb);
 			EXT4_SET_RO_COMPAT_FEATURE(sb,
 					EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
-			sb->s_dirt = 1;
 			ext4_handle_sync(handle);
-			err = ext4_handle_dirty_metadata(handle, NULL,
-					EXT4_SB(sb)->s_sbh);
+			err = ext4_handle_dirty_super(handle, sb);
 		}
 	}
 	raw_inode->i_generation = cpu_to_le32(inode->i_generation);
@@ -4152,11 +4161,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		if (attr->ia_size != i_size_read(inode)) {
+		if (attr->ia_size != i_size_read(inode))
 			truncate_setsize(inode, attr->ia_size);
-			ext4_truncate(inode);
-		} else if (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
-			ext4_truncate(inode);
+		ext4_truncate(inode);
 	}
 
 	if (!rc) {
@@ -4314,7 +4321,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 {
 	int err = 0;
 
-	if (test_opt(inode->i_sb, I_VERSION))
+	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
 	/* the do_update_inode consumes one bh->b_count */
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index cb990b21c698..99ab428bcfa0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -21,6 +21,7 @@
  * mballoc.c contains the multiblocks allocation routines
  */
 
+#include "ext4_jbd2.h"
 #include "mballoc.h"
 #include <linux/debugfs.h>
 #include <linux/slab.h>
@@ -339,7 +340,7 @@
  */
 static struct kmem_cache *ext4_pspace_cachep;
 static struct kmem_cache *ext4_ac_cachep;
-static struct kmem_cache *ext4_free_ext_cachep;
+static struct kmem_cache *ext4_free_data_cachep;
 
 /* We create slab caches for groupinfo data structures based on the
  * superblock block size.  There will be one per mounted filesystem for
@@ -357,7 +358,8 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group);
 static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 						ext4_group_t group);
-static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
+static void ext4_free_data_callback(struct super_block *sb,
+				struct ext4_journal_cb_entry *jce, int rc);
 
 static inline void *mb_correct_addr_and_bit(int *bit, void *addr)
 {
@@ -425,7 +427,7 @@ static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
 {
 	char *bb;
 
-	BUG_ON(EXT4_MB_BITMAP(e4b) == EXT4_MB_BUDDY(e4b));
+	BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
 	BUG_ON(max == NULL);
 
 	if (order > e4b->bd_blkbits + 1) {
@@ -436,10 +438,10 @@ static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
 	/* at order 0 we see each particular block */
 	if (order == 0) {
 		*max = 1 << (e4b->bd_blkbits + 3);
-		return EXT4_MB_BITMAP(e4b);
+		return e4b->bd_bitmap;
 	}
 
-	bb = EXT4_MB_BUDDY(e4b) + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order];
+	bb = e4b->bd_buddy + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order];
 	*max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order];
 
 	return bb;
@@ -588,7 +590,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 			for (j = 0; j < (1 << order); j++) {
 				k = (i * (1 << order)) + j;
 				MB_CHECK_ASSERT(
-					!mb_test_bit(k, EXT4_MB_BITMAP(e4b)));
+					!mb_test_bit(k, e4b->bd_bitmap));
 			}
 			count++;
 		}
@@ -782,7 +784,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	int groups_per_page;
 	int err = 0;
 	int i;
-	ext4_group_t first_group;
+	ext4_group_t first_group, group;
 	int first_block;
 	struct super_block *sb;
 	struct buffer_head *bhs;
@@ -806,24 +808,23 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 
 	/* allocate buffer_heads to read bitmaps */
 	if (groups_per_page > 1) {
-		err = -ENOMEM;
 		i = sizeof(struct buffer_head *) * groups_per_page;
 		bh = kzalloc(i, GFP_NOFS);
-		if (bh == NULL)
+		if (bh == NULL) {
+			err = -ENOMEM;
 			goto out;
+		}
 	} else
 		bh = &bhs;
 
 	first_group = page->index * blocks_per_page / 2;
 
 	/* read all groups the page covers into the cache */
-	for (i = 0; i < groups_per_page; i++) {
-		struct ext4_group_desc *desc;
-
-		if (first_group + i >= ngroups)
+	for (i = 0, group = first_group; i < groups_per_page; i++, group++) {
+		if (group >= ngroups)
 			break;
 
-		grinfo = ext4_get_group_info(sb, first_group + i);
+		grinfo = ext4_get_group_info(sb, group);
 		/*
 		 * If page is uptodate then we came here after online resize
 		 * which added some new uninitialized group info structs, so
@@ -834,69 +835,21 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 			bh[i] = NULL;
 			continue;
 		}
-
-		err = -EIO;
-		desc = ext4_get_group_desc(sb, first_group + i, NULL);
-		if (desc == NULL)
-			goto out;
-
-		err = -ENOMEM;
-		bh[i] = sb_getblk(sb, ext4_block_bitmap(sb, desc));
-		if (bh[i] == NULL)
+		if (!(bh[i] = ext4_read_block_bitmap_nowait(sb, group))) {
+			err = -ENOMEM;
 			goto out;
-
-		if (bitmap_uptodate(bh[i]))
-			continue;
-
-		lock_buffer(bh[i]);
-		if (bitmap_uptodate(bh[i])) {
-			unlock_buffer(bh[i]);
-			continue;
-		}
-		ext4_lock_group(sb, first_group + i);
-		if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-			ext4_init_block_bitmap(sb, bh[i],
-						first_group + i, desc);
-			set_bitmap_uptodate(bh[i]);
-			set_buffer_uptodate(bh[i]);
-			ext4_unlock_group(sb, first_group + i);
-			unlock_buffer(bh[i]);
-			continue;
 		}
-		ext4_unlock_group(sb, first_group + i);
-		if (buffer_uptodate(bh[i])) {
-			/*
-			 * if not uninit if bh is uptodate,
-			 * bitmap is also uptodate
-			 */
-			set_bitmap_uptodate(bh[i]);
-			unlock_buffer(bh[i]);
-			continue;
-		}
-		get_bh(bh[i]);
-		/*
-		 * submit the buffer_head for read. We can
-		 * safely mark the bitmap as uptodate now.
-		 * We do it here so the bitmap uptodate bit
-		 * get set with buffer lock held.
-		 */
-		set_bitmap_uptodate(bh[i]);
-		bh[i]->b_end_io = end_buffer_read_sync;
-		submit_bh(READ, bh[i]);
-		mb_debug(1, "read bitmap for group %u\n", first_group + i);
+		mb_debug(1, "read bitmap for group %u\n", group);
 	}
 
 	/* wait for I/O completion */
-	for (i = 0; i < groups_per_page; i++)
-		if (bh[i])
-			wait_on_buffer(bh[i]);
-
-	err = -EIO;
-	for (i = 0; i < groups_per_page; i++)
-		if (bh[i] && !buffer_uptodate(bh[i]))
+	for (i = 0, group = first_group; i < groups_per_page; i++, group++) {
+		if (bh[i] && ext4_wait_block_bitmap(sb, group, bh[i])) {
+			err = -EIO;
 			goto out;
+		}
+	}
 
-	err = 0;
 	first_block = page->index * blocks_per_page;
 	for (i = 0; i < blocks_per_page; i++) {
 		int group;
@@ -1250,10 +1203,10 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
 	int order = 1;
 	void *bb;
 
-	BUG_ON(EXT4_MB_BITMAP(e4b) == EXT4_MB_BUDDY(e4b));
+	BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
 	BUG_ON(block >= (1 << (e4b->bd_blkbits + 3)));
 
-	bb = EXT4_MB_BUDDY(e4b);
+	bb = e4b->bd_buddy;
 	while (order <= e4b->bd_blkbits + 1) {
 		block = block >> 1;
 		if (!mb_test_bit(block, bb)) {
@@ -1323,9 +1276,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 
 	/* let's maintain fragments counter */
 	if (first != 0)
-		block = !mb_test_bit(first - 1, EXT4_MB_BITMAP(e4b));
+		block = !mb_test_bit(first - 1, e4b->bd_bitmap);
 	if (first + count < EXT4_SB(sb)->s_mb_maxs[0])
-		max = !mb_test_bit(first + count, EXT4_MB_BITMAP(e4b));
+		max = !mb_test_bit(first + count, e4b->bd_bitmap);
 	if (block && max)
 		e4b->bd_info->bb_fragments--;
 	else if (!block && !max)
@@ -1336,7 +1289,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 		block = first++;
 		order = 0;
 
-		if (!mb_test_bit(block, EXT4_MB_BITMAP(e4b))) {
+		if (!mb_test_bit(block, e4b->bd_bitmap)) {
 			ext4_fsblk_t blocknr;
 
 			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
@@ -1347,7 +1300,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 					      "freeing already freed block "
 					      "(bit %u)", block);
 		}
-		mb_clear_bit(block, EXT4_MB_BITMAP(e4b));
+		mb_clear_bit(block, e4b->bd_bitmap);
 		e4b->bd_info->bb_counters[order]++;
 
 		/* start of the buddy */
@@ -1429,7 +1382,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
 			break;
 
 		next = (block + 1) * (1 << order);
-		if (mb_test_bit(next, EXT4_MB_BITMAP(e4b)))
+		if (mb_test_bit(next, e4b->bd_bitmap))
 			break;
 
 		order = mb_find_order_for_block(e4b, next);
@@ -1466,9 +1419,9 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 
 	/* let's maintain fragments counter */
 	if (start != 0)
-		mlen = !mb_test_bit(start - 1, EXT4_MB_BITMAP(e4b));
+		mlen = !mb_test_bit(start - 1, e4b->bd_bitmap);
 	if (start + len < EXT4_SB(e4b->bd_sb)->s_mb_maxs[0])
-		max = !mb_test_bit(start + len, EXT4_MB_BITMAP(e4b));
+		max = !mb_test_bit(start + len, e4b->bd_bitmap);
 	if (mlen && max)
 		e4b->bd_info->bb_fragments++;
 	else if (!mlen && !max)
@@ -1511,7 +1464,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 	}
 	mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
 
-	ext4_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
+	ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
 	mb_check_buddy(e4b);
 
 	return ret;
@@ -1810,7 +1763,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 					struct ext4_buddy *e4b)
 {
 	struct super_block *sb = ac->ac_sb;
-	void *bitmap = EXT4_MB_BITMAP(e4b);
+	void *bitmap = e4b->bd_bitmap;
 	struct ext4_free_extent ex;
 	int i;
 	int free;
@@ -1870,7 +1823,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
 {
 	struct super_block *sb = ac->ac_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	void *bitmap = EXT4_MB_BITMAP(e4b);
+	void *bitmap = e4b->bd_bitmap;
 	struct ext4_free_extent ex;
 	ext4_fsblk_t first_group_block;
 	ext4_fsblk_t a;
@@ -2224,7 +2177,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 			EXT4_DESC_PER_BLOCK_BITS(sb);
 		meta_group_info = kmalloc(metalen, GFP_KERNEL);
 		if (meta_group_info == NULL) {
-			ext4_msg(sb, KERN_ERR, "EXT4-fs: can't allocate mem "
+			ext4_msg(sb, KERN_ERR, "can't allocate mem "
 				 "for a buddy group");
 			goto exit_meta_group_info;
 		}
@@ -2238,7 +2191,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 
 	meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL);
 	if (meta_group_info[i] == NULL) {
-		ext4_msg(sb, KERN_ERR, "EXT4-fs: can't allocate buddy mem");
+		ext4_msg(sb, KERN_ERR, "can't allocate buddy mem");
 		goto exit_group_info;
 	}
 	memset(meta_group_info[i], 0, kmem_cache_size(cachep));
@@ -2522,9 +2475,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 		proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
 				 &ext4_mb_seq_groups_fops, sb);
 
-	if (sbi->s_journal)
-		sbi->s_journal->j_commit_callback = release_blocks_on_commit;
-
 	return 0;
 
 out_free_locality_groups:
@@ -2637,58 +2587,55 @@ static inline int ext4_issue_discard(struct super_block *sb,
  * This function is called by the jbd2 layer once the commit has finished,
  * so we know we can free the blocks that were released with that commit.
  */
-static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
+static void ext4_free_data_callback(struct super_block *sb,
+				    struct ext4_journal_cb_entry *jce,
+				    int rc)
 {
-	struct super_block *sb = journal->j_private;
+	struct ext4_free_data *entry = (struct ext4_free_data *)jce;
 	struct ext4_buddy e4b;
 	struct ext4_group_info *db;
 	int err, count = 0, count2 = 0;
-	struct ext4_free_data *entry;
-	struct list_head *l, *ltmp;
 
-	list_for_each_safe(l, ltmp, &txn->t_private_list) {
-		entry = list_entry(l, struct ext4_free_data, list);
+	mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
+		 entry->efd_count, entry->efd_group, entry);
 
-		mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
-			 entry->count, entry->group, entry);
+	if (test_opt(sb, DISCARD))
+		ext4_issue_discard(sb, entry->efd_group,
+				   entry->efd_start_cluster, entry->efd_count);
 
-		if (test_opt(sb, DISCARD))
-			ext4_issue_discard(sb, entry->group,
-					   entry->start_cluster, entry->count);
+	err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b);
+	/* we expect to find existing buddy because it's pinned */
+	BUG_ON(err != 0);
 
-		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
-		/* we expect to find existing buddy because it's pinned */
-		BUG_ON(err != 0);
 
-		db = e4b.bd_info;
-		/* there are blocks to put in buddy to make them really free */
-		count += entry->count;
-		count2++;
-		ext4_lock_group(sb, entry->group);
-		/* Take it out of per group rb tree */
-		rb_erase(&entry->node, &(db->bb_free_root));
-		mb_free_blocks(NULL, &e4b, entry->start_cluster, entry->count);
+	db = e4b.bd_info;
+	/* there are blocks to put in buddy to make them really free */
+	count += entry->efd_count;
+	count2++;
+	ext4_lock_group(sb, entry->efd_group);
+	/* Take it out of per group rb tree */
+	rb_erase(&entry->efd_node, &(db->bb_free_root));
+	mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count);
 
-		/*
-		 * Clear the trimmed flag for the group so that the next
-		 * ext4_trim_fs can trim it.
-		 * If the volume is mounted with -o discard, online discard
-		 * is supported and the free blocks will be trimmed online.
-		 */
-		if (!test_opt(sb, DISCARD))
-			EXT4_MB_GRP_CLEAR_TRIMMED(db);
+	/*
+	 * Clear the trimmed flag for the group so that the next
+	 * ext4_trim_fs can trim it.
+	 * If the volume is mounted with -o discard, online discard
+	 * is supported and the free blocks will be trimmed online.
+	 */
+	if (!test_opt(sb, DISCARD))
+		EXT4_MB_GRP_CLEAR_TRIMMED(db);
 
-		if (!db->bb_free_root.rb_node) {
-			/* No more items in the per group rb tree
-			 * balance refcounts from ext4_mb_free_metadata()
-			 */
-			page_cache_release(e4b.bd_buddy_page);
-			page_cache_release(e4b.bd_bitmap_page);
-		}
-		ext4_unlock_group(sb, entry->group);
-		kmem_cache_free(ext4_free_ext_cachep, entry);
-		ext4_mb_unload_buddy(&e4b);
+	if (!db->bb_free_root.rb_node) {
+		/* No more items in the per group rb tree
+		 * balance refcounts from ext4_mb_free_metadata()
+		 */
+		page_cache_release(e4b.bd_buddy_page);
+		page_cache_release(e4b.bd_bitmap_page);
 	}
+	ext4_unlock_group(sb, entry->efd_group);
+	kmem_cache_free(ext4_free_data_cachep, entry);
+	ext4_mb_unload_buddy(&e4b);
 
 	mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
 }
@@ -2741,9 +2688,9 @@ int __init ext4_init_mballoc(void)
 		return -ENOMEM;
 	}
 
-	ext4_free_ext_cachep = KMEM_CACHE(ext4_free_data,
-					  SLAB_RECLAIM_ACCOUNT);
-	if (ext4_free_ext_cachep == NULL) {
+	ext4_free_data_cachep = KMEM_CACHE(ext4_free_data,
+					   SLAB_RECLAIM_ACCOUNT);
+	if (ext4_free_data_cachep == NULL) {
 		kmem_cache_destroy(ext4_pspace_cachep);
 		kmem_cache_destroy(ext4_ac_cachep);
 		return -ENOMEM;
@@ -2761,7 +2708,7 @@ void ext4_exit_mballoc(void)
 	rcu_barrier();
 	kmem_cache_destroy(ext4_pspace_cachep);
 	kmem_cache_destroy(ext4_ac_cachep);
-	kmem_cache_destroy(ext4_free_ext_cachep);
+	kmem_cache_destroy(ext4_free_data_cachep);
 	ext4_groupinfo_destroy_slabs();
 	ext4_remove_debugfs_entry();
 }
@@ -2815,7 +2762,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
 	if (!ext4_data_block_valid(sbi, block, len)) {
 		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
-			   "fs metadata\n", block, block+len);
+			   "fs metadata", block, block+len);
 		/* File system mounted not to panic on error
 		 * Fix the bitmap and repeat the block allocation
 		 * We leak some of the blocks here.
@@ -2911,7 +2858,8 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	int bsbits, max;
 	ext4_lblk_t end;
-	loff_t size, orig_size, start_off;
+	loff_t size, start_off;
+	loff_t orig_size __maybe_unused;
 	ext4_lblk_t start;
 	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
 	struct ext4_prealloc_space *pa;
@@ -3321,8 +3269,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 	n = rb_first(&(grp->bb_free_root));
 
 	while (n) {
-		entry = rb_entry(n, struct ext4_free_data, node);
-		ext4_set_bits(bitmap, entry->start_cluster, entry->count);
+		entry = rb_entry(n, struct ext4_free_data, efd_node);
+		ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count);
 		n = rb_next(n);
 	}
 	return;
@@ -3916,11 +3864,11 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 	    (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED))
 		return;
 
-	ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: Can't allocate:"
+	ext4_msg(ac->ac_sb, KERN_ERR, "Can't allocate:"
 			" Allocation context details:");
-	ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: status %d flags %d",
+	ext4_msg(ac->ac_sb, KERN_ERR, "status %d flags %d",
 			ac->ac_status, ac->ac_flags);
-	ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: orig %lu/%lu/%lu@%lu, "
+	ext4_msg(ac->ac_sb, KERN_ERR, "orig %lu/%lu/%lu@%lu, "
 		 	"goal %lu/%lu/%lu@%lu, "
 			"best %lu/%lu/%lu@%lu cr %d",
 			(unsigned long)ac->ac_o_ex.fe_group,
@@ -3936,9 +3884,9 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 			(unsigned long)ac->ac_b_ex.fe_len,
 			(unsigned long)ac->ac_b_ex.fe_logical,
 			(int)ac->ac_criteria);
-	ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: %lu scanned, %d found",
+	ext4_msg(ac->ac_sb, KERN_ERR, "%lu scanned, %d found",
 		 ac->ac_ex_scanned, ac->ac_found);
-	ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: groups: ");
+	ext4_msg(ac->ac_sb, KERN_ERR, "groups: ");
 	ngroups = ext4_get_groups_count(sb);
 	for (i = 0; i < ngroups; i++) {
 		struct ext4_group_info *grp = ext4_get_group_info(sb, i);
@@ -4428,9 +4376,9 @@ out:
 static int can_merge(struct ext4_free_data *entry1,
 			struct ext4_free_data *entry2)
 {
-	if ((entry1->t_tid == entry2->t_tid) &&
-	    (entry1->group == entry2->group) &&
-	    ((entry1->start_cluster + entry1->count) == entry2->start_cluster))
+	if ((entry1->efd_tid == entry2->efd_tid) &&
+	    (entry1->efd_group == entry2->efd_group) &&
+	    ((entry1->efd_start_cluster + entry1->efd_count) == entry2->efd_start_cluster))
 		return 1;
 	return 0;
 }
@@ -4452,8 +4400,8 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	BUG_ON(e4b->bd_bitmap_page == NULL);
 	BUG_ON(e4b->bd_buddy_page == NULL);
 
-	new_node = &new_entry->node;
-	cluster = new_entry->start_cluster;
+	new_node = &new_entry->efd_node;
+	cluster = new_entry->efd_start_cluster;
 
 	if (!*n) {
 		/* first free block exent. We need to
@@ -4466,10 +4414,10 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	}
 	while (*n) {
 		parent = *n;
-		entry = rb_entry(parent, struct ext4_free_data, node);
-		if (cluster < entry->start_cluster)
+		entry = rb_entry(parent, struct ext4_free_data, efd_node);
+		if (cluster < entry->efd_start_cluster)
 			n = &(*n)->rb_left;
-		else if (cluster >= (entry->start_cluster + entry->count))
+		else if (cluster >= (entry->efd_start_cluster + entry->efd_count))
 			n = &(*n)->rb_right;
 		else {
 			ext4_grp_locked_error(sb, group, 0,
@@ -4486,34 +4434,29 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	/* Now try to see the extent can be merged to left and right */
 	node = rb_prev(new_node);
 	if (node) {
-		entry = rb_entry(node, struct ext4_free_data, node);
+		entry = rb_entry(node, struct ext4_free_data, efd_node);
 		if (can_merge(entry, new_entry)) {
-			new_entry->start_cluster = entry->start_cluster;
-			new_entry->count += entry->count;
+			new_entry->efd_start_cluster = entry->efd_start_cluster;
+			new_entry->efd_count += entry->efd_count;
 			rb_erase(node, &(db->bb_free_root));
-			spin_lock(&sbi->s_md_lock);
-			list_del(&entry->list);
-			spin_unlock(&sbi->s_md_lock);
-			kmem_cache_free(ext4_free_ext_cachep, entry);
+			ext4_journal_callback_del(handle, &entry->efd_jce);
+			kmem_cache_free(ext4_free_data_cachep, entry);
 		}
 	}
 
 	node = rb_next(new_node);
 	if (node) {
-		entry = rb_entry(node, struct ext4_free_data, node);
+		entry = rb_entry(node, struct ext4_free_data, efd_node);
 		if (can_merge(new_entry, entry)) {
-			new_entry->count += entry->count;
+			new_entry->efd_count += entry->efd_count;
 			rb_erase(node, &(db->bb_free_root));
-			spin_lock(&sbi->s_md_lock);
-			list_del(&entry->list);
-			spin_unlock(&sbi->s_md_lock);
-			kmem_cache_free(ext4_free_ext_cachep, entry);
+			ext4_journal_callback_del(handle, &entry->efd_jce);
+			kmem_cache_free(ext4_free_data_cachep, entry);
 		}
 	}
 	/* Add the extent to transaction's private list */
-	spin_lock(&sbi->s_md_lock);
-	list_add(&new_entry->list, &handle->h_transaction->t_private_list);
-	spin_unlock(&sbi->s_md_lock);
+	ext4_journal_callback_add(handle, ext4_free_data_callback,
+				  &new_entry->efd_jce);
 	return 0;
 }
 
@@ -4691,15 +4634,15 @@ do_more:
 		 * blocks being freed are metadata. these blocks shouldn't
 		 * be used until this transaction is committed
 		 */
-		new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+		new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
 		if (!new_entry) {
 			err = -ENOMEM;
 			goto error_return;
 		}
-		new_entry->start_cluster = bit;
-		new_entry->group  = block_group;
-		new_entry->count = count_clusters;
-		new_entry->t_tid = handle->h_transaction->t_tid;
+		new_entry->efd_start_cluster = bit;
+		new_entry->efd_group = block_group;
+		new_entry->efd_count = count_clusters;
+		new_entry->efd_tid = handle->h_transaction->t_tid;
 
 		ext4_lock_group(sb, block_group);
 		mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
@@ -4971,11 +4914,11 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 	start = (e4b.bd_info->bb_first_free > start) ?
 		e4b.bd_info->bb_first_free : start;
 
-	while (start < max) {
-		start = mb_find_next_zero_bit(bitmap, max, start);
-		if (start >= max)
+	while (start <= max) {
+		start = mb_find_next_zero_bit(bitmap, max + 1, start);
+		if (start > max)
 			break;
-		next = mb_find_next_bit(bitmap, max, start);
+		next = mb_find_next_bit(bitmap, max + 1, start);
 
 		if ((next - start) >= minblocks) {
 			ext4_trim_extent(sb, start,
@@ -5027,37 +4970,36 @@ out:
 int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 {
 	struct ext4_group_info *grp;
-	ext4_group_t first_group, last_group;
-	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
+	ext4_group_t group, first_group, last_group;
 	ext4_grpblk_t cnt = 0, first_cluster, last_cluster;
-	uint64_t start, len, minlen, trimmed = 0;
+	uint64_t start, end, minlen, trimmed = 0;
 	ext4_fsblk_t first_data_blk =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+	ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es);
 	int ret = 0;
 
 	start = range->start >> sb->s_blocksize_bits;
-	len = range->len >> sb->s_blocksize_bits;
+	end = start + (range->len >> sb->s_blocksize_bits) - 1;
 	minlen = range->minlen >> sb->s_blocksize_bits;
 
-	if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)))
+	if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)) ||
+	    unlikely(start >= max_blks))
 		return -EINVAL;
-	if (start + len <= first_data_blk)
+	if (end >= max_blks)
+		end = max_blks - 1;
+	if (end <= first_data_blk)
 		goto out;
-	if (start < first_data_blk) {
-		len -= first_data_blk - start;
+	if (start < first_data_blk)
 		start = first_data_blk;
-	}
 
-	/* Determine first and last group to examine based on start and len */
+	/* Determine first and last group to examine based on start and end */
 	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start,
 				     &first_group, &first_cluster);
-	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len),
+	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) end,
 				     &last_group, &last_cluster);
-	last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
-	last_cluster = EXT4_CLUSTERS_PER_GROUP(sb);
 
-	if (first_group > last_group)
-		return -EINVAL;
+	/* end now represents the last cluster to discard in this group */
+	end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
 
 	for (group = first_group; group <= last_group; group++) {
 		grp = ext4_get_group_info(sb, group);
@@ -5069,31 +5011,35 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		}
 
 		/*
-		 * For all the groups except the last one, last block will
-		 * always be EXT4_BLOCKS_PER_GROUP(sb), so we only need to
-		 * change it for the last group in which case start +
-		 * len < EXT4_BLOCKS_PER_GROUP(sb).
+		 * For all the groups except the last one, last cluster will
+		 * always be EXT4_CLUSTERS_PER_GROUP(sb)-1, so we only need to
+		 * change it for the last group, note that last_cluster is
+		 * already computed earlier by ext4_get_group_no_and_offset()
 		 */
-		if (first_cluster + len < EXT4_CLUSTERS_PER_GROUP(sb))
-			last_cluster = first_cluster + len;
-		len -= last_cluster - first_cluster;
+		if (group == last_group)
+			end = last_cluster;
 
 		if (grp->bb_free >= minlen) {
 			cnt = ext4_trim_all_free(sb, group, first_cluster,
-						last_cluster, minlen);
+						end, minlen);
 			if (cnt < 0) {
 				ret = cnt;
 				break;
 			}
+			trimmed += cnt;
 		}
-		trimmed += cnt;
+
+		/*
+		 * For every group except the first one, we are sure
+		 * that the first cluster to discard will be cluster #0.
+		 */
 		first_cluster = 0;
 	}
-	range->len = trimmed * sb->s_blocksize;
 
 	if (!ret)
 		atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen);
 
 out:
+	range->len = trimmed * sb->s_blocksize;
 	return ret;
 }
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 47705f3285e3..c070618c21ce 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -96,21 +96,23 @@ extern u8 mb_enable_debug;
 
 
 struct ext4_free_data {
-	/* this links the free block information from group_info */
-	struct rb_node node;
+	/* MUST be the first member */
+	struct ext4_journal_cb_entry	efd_jce;
+
+	/* ext4_free_data private data starts from here */
 
-	/* this links the free block information from ext4_sb_info */
-	struct list_head list;
+	/* this links the free block information from group_info */
+	struct rb_node			efd_node;
 
 	/* group which free block extent belongs */
-	ext4_group_t group;
+	ext4_group_t			efd_group;
 
 	/* free block extent */
-	ext4_grpblk_t start_cluster;
-	ext4_grpblk_t count;
+	ext4_grpblk_t			efd_start_cluster;
+	ext4_grpblk_t			efd_count;
 
 	/* transaction which freed this extent */
-	tid_t	t_tid;
+	tid_t				efd_tid;
 };
 
 struct ext4_prealloc_space {
@@ -210,8 +212,6 @@ struct ext4_buddy {
 	__u16 bd_blkbits;
 	ext4_group_t bd_group;
 };
-#define EXT4_MB_BITMAP(e4b)	((e4b)->bd_bitmap)
-#define EXT4_MB_BUDDY(e4b)	((e4b)->bd_buddy)
 
 static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
 					struct ext4_free_extent *fex)
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index e7d6bb0acfa6..f39f80f8f2c5 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -471,7 +471,7 @@ int ext4_ext_migrate(struct inode *inode)
 	tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
 				   S_IFREG, NULL, goal, owner);
 	if (IS_ERR(tmp_inode)) {
-		retval = PTR_ERR(inode);
+		retval = PTR_ERR(tmp_inode);
 		ext4_journal_stop(handle);
 		return retval;
 	}
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 7ea4ba4eff2a..ed6548d89165 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -257,8 +257,8 @@ int ext4_multi_mount_protect(struct super_block *sb,
 	 * If check_interval in MMP block is larger, use that instead of
 	 * update_interval from the superblock.
 	 */
-	if (mmp->mmp_check_interval > mmp_check_interval)
-		mmp_check_interval = mmp->mmp_check_interval;
+	if (le16_to_cpu(mmp->mmp_check_interval) > mmp_check_interval)
+		mmp_check_interval = le16_to_cpu(mmp->mmp_check_interval);
 
 	seq = le32_to_cpu(mmp->mmp_seq);
 	if (seq == EXT4_MMP_SEQ_CLEAN)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2043f482375d..349d7b3671c8 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -468,7 +468,7 @@ fail2:
 fail:
 	if (*err == ERR_BAD_DX_DIR)
 		ext4_warning(dir->i_sb,
-			     "Corrupt dir inode %ld, running e2fsck is "
+			     "Corrupt dir inode %lu, running e2fsck is "
 			     "recommended.", dir->i_ino);
 	return NULL;
 }
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 475851896518..dcdeef169a69 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -110,6 +110,8 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
 	if (io->iocb)
 		aio_complete(io->iocb, io->result, 0);
 
+	if (io->flag & EXT4_IO_END_DIRECT)
+		inode_dio_done(inode);
 	/* Wake up anyone waiting on unwritten extent conversion */
 	if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten))
 		wake_up_all(ext4_ioend_wq(io->inode));
@@ -127,12 +129,18 @@ static void ext4_end_io_work(struct work_struct *work)
 	unsigned long		flags;
 
 	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	if (io->flag & EXT4_IO_END_IN_FSYNC)
+		goto requeue;
 	if (list_empty(&io->list)) {
 		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 		goto free;
 	}
 
 	if (!mutex_trylock(&inode->i_mutex)) {
+		bool was_queued;
+requeue:
+		was_queued = !!(io->flag & EXT4_IO_END_QUEUED);
+		io->flag |= EXT4_IO_END_QUEUED;
 		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 		/*
 		 * Requeue the work instead of waiting so that the work
@@ -145,9 +153,8 @@ static void ext4_end_io_work(struct work_struct *work)
 		 * yield the cpu if it sees an end_io request that has already
 		 * been requeued.
 		 */
-		if (io->flag & EXT4_IO_END_QUEUED)
+		if (was_queued)
 			yield();
-		io->flag |= EXT4_IO_END_QUEUED;
 		return;
 	}
 	list_del_init(&io->list);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index f9d948f0eb86..59fa0be27251 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1163,8 +1163,11 @@ static void ext4_update_super(struct super_block *sb,
 	do_div(reserved_blocks, 100);
 
 	ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
+	ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
 	le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
 		     flex_gd->count);
+	le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) *
+		     flex_gd->count);
 
 	/*
 	 * We need to protect s_groups_count against other CPUs seeing
@@ -1465,6 +1468,7 @@ static int ext4_group_extend_no_check(struct super_block *sb,
 	}
 
 	ext4_blocks_count_set(es, o_blocks_count + add);
+	ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
 	ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
 	/* We add the blocks to the bitmap and set the group need init bit */
@@ -1512,16 +1516,17 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 	o_blocks_count = ext4_blocks_count(es);
 
 	if (test_opt(sb, DEBUG))
-		printk(KERN_DEBUG "EXT4-fs: extending last group from %llu to %llu blocks\n",
-		       o_blocks_count, n_blocks_count);
+		ext4_msg(sb, KERN_DEBUG,
+			 "extending last group from %llu to %llu blocks",
+			 o_blocks_count, n_blocks_count);
 
 	if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
 		return 0;
 
 	if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
-		printk(KERN_ERR "EXT4-fs: filesystem on %s:"
-			" too large to resize to %llu blocks safely\n",
-			sb->s_id, n_blocks_count);
+		ext4_msg(sb, KERN_ERR,
+			 "filesystem too large to resize to %llu blocks safely",
+			 n_blocks_count);
 		if (sizeof(sector_t) < 8)
 			ext4_warning(sb, "CONFIG_LBDAF not enabled");
 		return -EINVAL;
@@ -1582,7 +1587,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 	ext4_fsblk_t o_blocks_count;
 	ext4_group_t o_group;
 	ext4_group_t n_group;
-	ext4_grpblk_t offset;
+	ext4_grpblk_t offset, add;
 	unsigned long n_desc_blocks;
 	unsigned long o_desc_blocks;
 	unsigned long desc_blocks;
@@ -1591,8 +1596,8 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 	o_blocks_count = ext4_blocks_count(es);
 
 	if (test_opt(sb, DEBUG))
-		printk(KERN_DEBUG "EXT4-fs: resizing filesystem from %llu "
-		       "upto %llu blocks\n", o_blocks_count, n_blocks_count);
+		ext4_msg(sb, KERN_DEBUG, "resizing filesystem from %llu "
+		       "to %llu blocks", o_blocks_count, n_blocks_count);
 
 	if (n_blocks_count < o_blocks_count) {
 		/* On-line shrinking not supported */
@@ -1605,7 +1610,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 		return 0;
 
 	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
-	ext4_get_group_no_and_offset(sb, o_blocks_count, &o_group, &offset);
+	ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset);
 
 	n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) /
 			EXT4_DESC_PER_BLOCK(sb);
@@ -1634,10 +1639,12 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 	}
 	brelse(bh);
 
-	if (offset != 0) {
-		/* extend the last group */
-		ext4_grpblk_t add;
-		add = EXT4_BLOCKS_PER_GROUP(sb) - offset;
+	/* extend the last group */
+	if (n_group == o_group)
+		add = n_blocks_count - o_blocks_count;
+	else
+		add = EXT4_BLOCKS_PER_GROUP(sb) - (offset + 1);
+	if (add > 0) {
 		err = ext4_group_extend_no_check(sb, o_blocks_count, add);
 		if (err)
 			goto out;
@@ -1674,7 +1681,7 @@ out:
 
 	iput(resize_inode);
 	if (test_opt(sb, DEBUG))
-		printk(KERN_DEBUG "EXT4-fs: resized filesystem from %llu "
-		       "upto %llu blocks\n", o_blocks_count, n_blocks_count);
+		ext4_msg(sb, KERN_DEBUG, "resized filesystem from %llu "
+		       "upto %llu blocks", o_blocks_count, n_blocks_count);
 	return err;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 933900909ed0..ceebaf853beb 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -62,6 +62,7 @@ static struct ext4_features *ext4_feat;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
+static int ext4_show_options(struct seq_file *seq, struct dentry *root);
 static int ext4_commit_super(struct super_block *sb, int sync);
 static void ext4_mark_recovery_complete(struct super_block *sb,
 					struct ext4_super_block *es);
@@ -375,7 +376,7 @@ void ext4_journal_abort_handle(const char *caller, unsigned int line,
 	if (is_handle_aborted(handle))
 		return;
 
-	printk(KERN_ERR "%s:%d: aborting transaction: %s in %s\n",
+	printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n",
 	       caller, line, errstr, err_fn);
 
 	jbd2_journal_abort_handle(handle);
@@ -431,6 +432,22 @@ static int block_device_ejected(struct super_block *sb)
 	return bdi->dev == NULL;
 }
 
+static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
+{
+	struct super_block		*sb = journal->j_private;
+	struct ext4_sb_info		*sbi = EXT4_SB(sb);
+	int				error = is_journal_aborted(journal);
+	struct ext4_journal_cb_entry	*jce, *tmp;
+
+	spin_lock(&sbi->s_md_lock);
+	list_for_each_entry_safe(jce, tmp, &txn->t_private_list, jce_list) {
+		list_del_init(&jce->jce_list);
+		spin_unlock(&sbi->s_md_lock);
+		jce->jce_func(sb, jce, error);
+		spin_lock(&sbi->s_md_lock);
+	}
+	spin_unlock(&sbi->s_md_lock);
+}
 
 /* Deal with the reporting of failure conditions on a filesystem such as
  * inconsistencies detected or read IO failures.
@@ -498,11 +515,16 @@ void ext4_error_inode(struct inode *inode, const char *function,
 	va_start(args, fmt);
 	vaf.fmt = fmt;
 	vaf.va = &args;
-	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
-	       inode->i_sb->s_id, function, line, inode->i_ino);
 	if (block)
-		printk(KERN_CONT "block %llu: ", block);
-	printk(KERN_CONT "comm %s: %pV\n", current->comm, &vaf);
+		printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+		       "inode #%lu: block %llu: comm %s: %pV\n",
+		       inode->i_sb->s_id, function, line, inode->i_ino,
+		       block, current->comm, &vaf);
+	else
+		printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+		       "inode #%lu: comm %s: %pV\n",
+		       inode->i_sb->s_id, function, line, inode->i_ino,
+		       current->comm, &vaf);
 	va_end(args);
 
 	ext4_handle_error(inode->i_sb);
@@ -524,15 +546,21 @@ void ext4_error_file(struct file *file, const char *function,
 	path = d_path(&(file->f_path), pathname, sizeof(pathname));
 	if (IS_ERR(path))
 		path = "(unknown)";
-	printk(KERN_CRIT
-	       "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
-	       inode->i_sb->s_id, function, line, inode->i_ino);
-	if (block)
-		printk(KERN_CONT "block %llu: ", block);
 	va_start(args, fmt);
 	vaf.fmt = fmt;
 	vaf.va = &args;
-	printk(KERN_CONT "comm %s: path %s: %pV\n", current->comm, path, &vaf);
+	if (block)
+		printk(KERN_CRIT
+		       "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+		       "block %llu: comm %s: path %s: %pV\n",
+		       inode->i_sb->s_id, function, line, inode->i_ino,
+		       block, current->comm, path, &vaf);
+	else
+		printk(KERN_CRIT
+		       "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+		       "comm %s: path %s: %pV\n",
+		       inode->i_sb->s_id, function, line, inode->i_ino,
+		       current->comm, path, &vaf);
 	va_end(args);
 
 	ext4_handle_error(inode->i_sb);
@@ -808,9 +836,6 @@ static void ext4_put_super(struct super_block *sb)
 	destroy_workqueue(sbi->dio_unwritten_wq);
 
 	lock_super(sb);
-	if (sb->s_dirt)
-		ext4_commit_super(sb, 1);
-
 	if (sbi->s_journal) {
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
@@ -827,9 +852,12 @@ static void ext4_put_super(struct super_block *sb)
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
-		ext4_commit_super(sb, 1);
 	}
+	if (sb->s_dirt || !(sb->s_flags & MS_RDONLY))
+		ext4_commit_super(sb, 1);
+
 	if (sbi->s_proc) {
+		remove_proc_entry("options", sbi->s_proc);
 		remove_proc_entry(sb->s_id, ext4_proc_root);
 	}
 	kobject_del(&sbi->s_kobj);
@@ -990,180 +1018,6 @@ void ext4_clear_inode(struct inode *inode)
 	}
 }
 
-static inline void ext4_show_quota_options(struct seq_file *seq,
-					   struct super_block *sb)
-{
-#if defined(CONFIG_QUOTA)
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-
-	if (sbi->s_jquota_fmt) {
-		char *fmtname = "";
-
-		switch (sbi->s_jquota_fmt) {
-		case QFMT_VFS_OLD:
-			fmtname = "vfsold";
-			break;
-		case QFMT_VFS_V0:
-			fmtname = "vfsv0";
-			break;
-		case QFMT_VFS_V1:
-			fmtname = "vfsv1";
-			break;
-		}
-		seq_printf(seq, ",jqfmt=%s", fmtname);
-	}
-
-	if (sbi->s_qf_names[USRQUOTA])
-		seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
-
-	if (sbi->s_qf_names[GRPQUOTA])
-		seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
-
-	if (test_opt(sb, USRQUOTA))
-		seq_puts(seq, ",usrquota");
-
-	if (test_opt(sb, GRPQUOTA))
-		seq_puts(seq, ",grpquota");
-#endif
-}
-
-/*
- * Show an option if
- *  - it's set to a non-default value OR
- *  - if the per-sb default is different from the global default
- */
-static int ext4_show_options(struct seq_file *seq, struct dentry *root)
-{
-	int def_errors;
-	unsigned long def_mount_opts;
-	struct super_block *sb = root->d_sb;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_super_block *es = sbi->s_es;
-
-	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
-	def_errors     = le16_to_cpu(es->s_errors);
-
-	if (sbi->s_sb_block != 1)
-		seq_printf(seq, ",sb=%llu", sbi->s_sb_block);
-	if (test_opt(sb, MINIX_DF))
-		seq_puts(seq, ",minixdf");
-	if (test_opt(sb, GRPID) && !(def_mount_opts & EXT4_DEFM_BSDGROUPS))
-		seq_puts(seq, ",grpid");
-	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT4_DEFM_BSDGROUPS))
-		seq_puts(seq, ",nogrpid");
-	if (sbi->s_resuid != EXT4_DEF_RESUID ||
-	    le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) {
-		seq_printf(seq, ",resuid=%u", sbi->s_resuid);
-	}
-	if (sbi->s_resgid != EXT4_DEF_RESGID ||
-	    le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) {
-		seq_printf(seq, ",resgid=%u", sbi->s_resgid);
-	}
-	if (test_opt(sb, ERRORS_RO)) {
-		if (def_errors == EXT4_ERRORS_PANIC ||
-		    def_errors == EXT4_ERRORS_CONTINUE) {
-			seq_puts(seq, ",errors=remount-ro");
-		}
-	}
-	if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
-		seq_puts(seq, ",errors=continue");
-	if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
-		seq_puts(seq, ",errors=panic");
-	if (test_opt(sb, NO_UID32) && !(def_mount_opts & EXT4_DEFM_UID16))
-		seq_puts(seq, ",nouid32");
-	if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
-		seq_puts(seq, ",debug");
-#ifdef CONFIG_EXT4_FS_XATTR
-	if (test_opt(sb, XATTR_USER))
-		seq_puts(seq, ",user_xattr");
-	if (!test_opt(sb, XATTR_USER))
-		seq_puts(seq, ",nouser_xattr");
-#endif
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
-	if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
-		seq_puts(seq, ",acl");
-	if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL))
-		seq_puts(seq, ",noacl");
-#endif
-	if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
-		seq_printf(seq, ",commit=%u",
-			   (unsigned) (sbi->s_commit_interval / HZ));
-	}
-	if (sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) {
-		seq_printf(seq, ",min_batch_time=%u",
-			   (unsigned) sbi->s_min_batch_time);
-	}
-	if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) {
-		seq_printf(seq, ",max_batch_time=%u",
-			   (unsigned) sbi->s_max_batch_time);
-	}
-
-	/*
-	 * We're changing the default of barrier mount option, so
-	 * let's always display its mount state so it's clear what its
-	 * status is.
-	 */
-	seq_puts(seq, ",barrier=");
-	seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
-	if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
-		seq_puts(seq, ",journal_async_commit");
-	else if (test_opt(sb, JOURNAL_CHECKSUM))
-		seq_puts(seq, ",journal_checksum");
-	if (test_opt(sb, I_VERSION))
-		seq_puts(seq, ",i_version");
-	if (!test_opt(sb, DELALLOC) &&
-	    !(def_mount_opts & EXT4_DEFM_NODELALLOC))
-		seq_puts(seq, ",nodelalloc");
-
-	if (!test_opt(sb, MBLK_IO_SUBMIT))
-		seq_puts(seq, ",nomblk_io_submit");
-	if (sbi->s_stripe)
-		seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
-	/*
-	 * journal mode get enabled in different ways
-	 * So just print the value even if we didn't specify it
-	 */
-	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
-		seq_puts(seq, ",data=journal");
-	else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
-		seq_puts(seq, ",data=ordered");
-	else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
-		seq_puts(seq, ",data=writeback");
-
-	if (sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
-		seq_printf(seq, ",inode_readahead_blks=%u",
-			   sbi->s_inode_readahead_blks);
-
-	if (test_opt(sb, DATA_ERR_ABORT))
-		seq_puts(seq, ",data_err=abort");
-
-	if (test_opt(sb, NO_AUTO_DA_ALLOC))
-		seq_puts(seq, ",noauto_da_alloc");
-
-	if (test_opt(sb, DISCARD) && !(def_mount_opts & EXT4_DEFM_DISCARD))
-		seq_puts(seq, ",discard");
-
-	if (test_opt(sb, NOLOAD))
-		seq_puts(seq, ",norecovery");
-
-	if (test_opt(sb, DIOREAD_NOLOCK))
-		seq_puts(seq, ",dioread_nolock");
-
-	if (test_opt(sb, BLOCK_VALIDITY) &&
-	    !(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY))
-		seq_puts(seq, ",block_validity");
-
-	if (!test_opt(sb, INIT_INODE_TABLE))
-		seq_puts(seq, ",noinit_itable");
-	else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
-		seq_printf(seq, ",init_itable=%u",
-			   (unsigned) sbi->s_li_wait_mult);
-
-	ext4_show_quota_options(seq, sb);
-
-	return 0;
-}
-
 static struct inode *ext4_nfs_get_inode(struct super_block *sb,
 					u64 ino, u32 generation)
 {
@@ -1316,18 +1170,17 @@ static const struct export_operations ext4_export_ops = {
 enum {
 	Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
 	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
-	Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
+	Opt_nouid32, Opt_debug, Opt_removed,
 	Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
-	Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_nobh, Opt_bh,
+	Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
 	Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
-	Opt_journal_update, Opt_journal_dev,
-	Opt_journal_checksum, Opt_journal_async_commit,
+	Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit,
 	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
 	Opt_data_err_abort, Opt_data_err_ignore,
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
-	Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err,
-	Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version,
+	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
+	Opt_usrquota, Opt_grpquota, Opt_i_version,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
@@ -1350,20 +1203,19 @@ static const match_table_t tokens = {
 	{Opt_err_ro, "errors=remount-ro"},
 	{Opt_nouid32, "nouid32"},
 	{Opt_debug, "debug"},
-	{Opt_oldalloc, "oldalloc"},
-	{Opt_orlov, "orlov"},
+	{Opt_removed, "oldalloc"},
+	{Opt_removed, "orlov"},
 	{Opt_user_xattr, "user_xattr"},
 	{Opt_nouser_xattr, "nouser_xattr"},
 	{Opt_acl, "acl"},
 	{Opt_noacl, "noacl"},
-	{Opt_noload, "noload"},
 	{Opt_noload, "norecovery"},
-	{Opt_nobh, "nobh"},
-	{Opt_bh, "bh"},
+	{Opt_noload, "noload"},
+	{Opt_removed, "nobh"},
+	{Opt_removed, "bh"},
 	{Opt_commit, "commit=%u"},
 	{Opt_min_batch_time, "min_batch_time=%u"},
 	{Opt_max_batch_time, "max_batch_time=%u"},
-	{Opt_journal_update, "journal=update"},
 	{Opt_journal_dev, "journal_dev=%u"},
 	{Opt_journal_checksum, "journal_checksum"},
 	{Opt_journal_async_commit, "journal_async_commit"},
@@ -1389,7 +1241,6 @@ static const match_table_t tokens = {
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_i_version, "i_version"},
 	{Opt_stripe, "stripe=%u"},
-	{Opt_resize, "resize"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_nodelalloc, "nodelalloc"},
 	{Opt_mblk_io_submit, "mblk_io_submit"},
@@ -1408,6 +1259,11 @@ static const match_table_t tokens = {
 	{Opt_init_itable, "init_itable=%u"},
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
+	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
+	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
+	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
+	{Opt_removed, "noreservation"}, /* mount option from ext2/3 */
+	{Opt_removed, "journal=%u"},	/* mount option from ext2/3 */
 	{Opt_err, NULL},
 };
 
@@ -1496,420 +1352,273 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 }
 #endif
 
-static int parse_options(char *options, struct super_block *sb,
-			 unsigned long *journal_devnum,
-			 unsigned int *journal_ioprio,
-			 ext4_fsblk_t *n_blocks_count, int is_remount)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	char *p;
-	substring_t args[MAX_OPT_ARGS];
-	int data_opt = 0;
-	int option;
+#define MOPT_SET	0x0001
+#define MOPT_CLEAR	0x0002
+#define MOPT_NOSUPPORT	0x0004
+#define MOPT_EXPLICIT	0x0008
+#define MOPT_CLEAR_ERR	0x0010
+#define MOPT_GTE0	0x0020
 #ifdef CONFIG_QUOTA
-	int qfmt;
+#define MOPT_Q		0
+#define MOPT_QFMT	0x0040
+#else
+#define MOPT_Q		MOPT_NOSUPPORT
+#define MOPT_QFMT	MOPT_NOSUPPORT
 #endif
-
-	if (!options)
-		return 1;
-
-	while ((p = strsep(&options, ",")) != NULL) {
-		int token;
-		if (!*p)
-			continue;
-
-		/*
-		 * Initialize args struct so we know whether arg was
-		 * found; some options take optional arguments.
-		 */
-		args[0].to = args[0].from = NULL;
-		token = match_token(p, tokens, args);
-		switch (token) {
-		case Opt_bsd_df:
-			ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
-			clear_opt(sb, MINIX_DF);
-			break;
-		case Opt_minix_df:
-			ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
-			set_opt(sb, MINIX_DF);
-
-			break;
-		case Opt_grpid:
-			ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
-			set_opt(sb, GRPID);
-
-			break;
-		case Opt_nogrpid:
-			ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
-			clear_opt(sb, GRPID);
-
-			break;
-		case Opt_resuid:
-			if (match_int(&args[0], &option))
-				return 0;
-			sbi->s_resuid = option;
-			break;
-		case Opt_resgid:
-			if (match_int(&args[0], &option))
-				return 0;
-			sbi->s_resgid = option;
-			break;
-		case Opt_sb:
-			/* handled by get_sb_block() instead of here */
-			/* *sb_block = match_int(&args[0]); */
-			break;
-		case Opt_err_panic:
-			clear_opt(sb, ERRORS_CONT);
-			clear_opt(sb, ERRORS_RO);
-			set_opt(sb, ERRORS_PANIC);
-			break;
-		case Opt_err_ro:
-			clear_opt(sb, ERRORS_CONT);
-			clear_opt(sb, ERRORS_PANIC);
-			set_opt(sb, ERRORS_RO);
-			break;
-		case Opt_err_cont:
-			clear_opt(sb, ERRORS_RO);
-			clear_opt(sb, ERRORS_PANIC);
-			set_opt(sb, ERRORS_CONT);
-			break;
-		case Opt_nouid32:
-			set_opt(sb, NO_UID32);
-			break;
-		case Opt_debug:
-			set_opt(sb, DEBUG);
-			break;
-		case Opt_oldalloc:
-			ext4_msg(sb, KERN_WARNING,
-				 "Ignoring deprecated oldalloc option");
-			break;
-		case Opt_orlov:
-			ext4_msg(sb, KERN_WARNING,
-				 "Ignoring deprecated orlov option");
-			break;
+#define MOPT_DATAJ	0x0080
+
+static const struct mount_opts {
+	int	token;
+	int	mount_opt;
+	int	flags;
+} ext4_mount_opts[] = {
+	{Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET},
+	{Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR},
+	{Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET},
+	{Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR},
+	{Opt_mblk_io_submit, EXT4_MOUNT_MBLK_IO_SUBMIT, MOPT_SET},
+	{Opt_nomblk_io_submit, EXT4_MOUNT_MBLK_IO_SUBMIT, MOPT_CLEAR},
+	{Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET},
+	{Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR},
+	{Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_SET},
+	{Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_CLEAR},
+	{Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET},
+	{Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR},
+	{Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_SET | MOPT_EXPLICIT},
+	{Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_CLEAR | MOPT_EXPLICIT},
+	{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_SET},
+	{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
+				    EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_SET},
+	{Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_SET},
+	{Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR},
+	{Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
+	{Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR},
+	{Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_SET},
+	{Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_CLEAR},
+	{Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET},
+	{Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR},
+	{Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET},
+	{Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR},
+	{Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR},
+	{Opt_commit, 0, MOPT_GTE0},
+	{Opt_max_batch_time, 0, MOPT_GTE0},
+	{Opt_min_batch_time, 0, MOPT_GTE0},
+	{Opt_inode_readahead_blks, 0, MOPT_GTE0},
+	{Opt_init_itable, 0, MOPT_GTE0},
+	{Opt_stripe, 0, MOPT_GTE0},
+	{Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_DATAJ},
+	{Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_DATAJ},
+	{Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA, MOPT_DATAJ},
 #ifdef CONFIG_EXT4_FS_XATTR
-		case Opt_user_xattr:
-			set_opt(sb, XATTR_USER);
-			break;
-		case Opt_nouser_xattr:
-			clear_opt(sb, XATTR_USER);
-			break;
+	{Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET},
+	{Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR},
 #else
-		case Opt_user_xattr:
-		case Opt_nouser_xattr:
-			ext4_msg(sb, KERN_ERR, "(no)user_xattr options not supported");
-			break;
+	{Opt_user_xattr, 0, MOPT_NOSUPPORT},
+	{Opt_nouser_xattr, 0, MOPT_NOSUPPORT},
 #endif
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
-		case Opt_acl:
-			set_opt(sb, POSIX_ACL);
-			break;
-		case Opt_noacl:
-			clear_opt(sb, POSIX_ACL);
-			break;
+	{Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET},
+	{Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR},
 #else
-		case Opt_acl:
-		case Opt_noacl:
-			ext4_msg(sb, KERN_ERR, "(no)acl options not supported");
-			break;
+	{Opt_acl, 0, MOPT_NOSUPPORT},
+	{Opt_noacl, 0, MOPT_NOSUPPORT},
 #endif
-		case Opt_journal_update:
-			/* @@@ FIXME */
-			/* Eventually we will want to be able to create
-			   a journal file here.  For now, only allow the
-			   user to specify an existing inode to be the
-			   journal file. */
-			if (is_remount) {
-				ext4_msg(sb, KERN_ERR,
-					 "Cannot specify journal on remount");
-				return 0;
-			}
-			set_opt(sb, UPDATE_JOURNAL);
-			break;
-		case Opt_journal_dev:
-			if (is_remount) {
+	{Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
+	{Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
+	{Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q},
+	{Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA,
+							MOPT_SET | MOPT_Q},
+	{Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA,
+							MOPT_SET | MOPT_Q},
+	{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
+		       EXT4_MOUNT_GRPQUOTA), MOPT_CLEAR | MOPT_Q},
+	{Opt_usrjquota, 0, MOPT_Q},
+	{Opt_grpjquota, 0, MOPT_Q},
+	{Opt_offusrjquota, 0, MOPT_Q},
+	{Opt_offgrpjquota, 0, MOPT_Q},
+	{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
+	{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
+	{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
+	{Opt_err, 0, 0}
+};
+
+static int handle_mount_opt(struct super_block *sb, char *opt, int token,
+			    substring_t *args, unsigned long *journal_devnum,
+			    unsigned int *journal_ioprio, int is_remount)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	const struct mount_opts *m;
+	int arg = 0;
+
+	if (args->from && match_int(args, &arg))
+		return -1;
+	switch (token) {
+	case Opt_noacl:
+	case Opt_nouser_xattr:
+		ext4_msg(sb, KERN_WARNING, deprecated_msg, opt, "3.5");
+		break;
+	case Opt_sb:
+		return 1;	/* handled by get_sb_block() */
+	case Opt_removed:
+		ext4_msg(sb, KERN_WARNING,
+			 "Ignoring removed %s option", opt);
+		return 1;
+	case Opt_resuid:
+		sbi->s_resuid = arg;
+		return 1;
+	case Opt_resgid:
+		sbi->s_resgid = arg;
+		return 1;
+	case Opt_abort:
+		sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		return 1;
+	case Opt_i_version:
+		sb->s_flags |= MS_I_VERSION;
+		return 1;
+	case Opt_journal_dev:
+		if (is_remount) {
+			ext4_msg(sb, KERN_ERR,
+				 "Cannot specify journal on remount");
+			return -1;
+		}
+		*journal_devnum = arg;
+		return 1;
+	case Opt_journal_ioprio:
+		if (arg < 0 || arg > 7)
+			return -1;
+		*journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
+		return 1;
+	}
+
+	for (m = ext4_mount_opts; m->token != Opt_err; m++) {
+		if (token != m->token)
+			continue;
+		if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
+			return -1;
+		if (m->flags & MOPT_EXPLICIT)
+			set_opt2(sb, EXPLICIT_DELALLOC);
+		if (m->flags & MOPT_CLEAR_ERR)
+			clear_opt(sb, ERRORS_MASK);
+		if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
+			ext4_msg(sb, KERN_ERR, "Cannot change quota "
+				 "options when quota turned on");
+			return -1;
+		}
+
+		if (m->flags & MOPT_NOSUPPORT) {
+			ext4_msg(sb, KERN_ERR, "%s option not supported", opt);
+		} else if (token == Opt_commit) {
+			if (arg == 0)
+				arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
+			sbi->s_commit_interval = HZ * arg;
+		} else if (token == Opt_max_batch_time) {
+			if (arg == 0)
+				arg = EXT4_DEF_MAX_BATCH_TIME;
+			sbi->s_max_batch_time = arg;
+		} else if (token == Opt_min_batch_time) {
+			sbi->s_min_batch_time = arg;
+		} else if (token == Opt_inode_readahead_blks) {
+			if (arg > (1 << 30))
+				return -1;
+			if (arg && !is_power_of_2(arg)) {
 				ext4_msg(sb, KERN_ERR,
-					"Cannot specify journal on remount");
-				return 0;
+					 "EXT4-fs: inode_readahead_blks"
+					 " must be a power of 2");
+				return -1;
 			}
-			if (match_int(&args[0], &option))
-				return 0;
-			*journal_devnum = option;
-			break;
-		case Opt_journal_checksum:
-			set_opt(sb, JOURNAL_CHECKSUM);
-			break;
-		case Opt_journal_async_commit:
-			set_opt(sb, JOURNAL_ASYNC_COMMIT);
-			set_opt(sb, JOURNAL_CHECKSUM);
-			break;
-		case Opt_noload:
-			set_opt(sb, NOLOAD);
-			break;
-		case Opt_commit:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < 0)
-				return 0;
-			if (option == 0)
-				option = JBD2_DEFAULT_MAX_COMMIT_AGE;
-			sbi->s_commit_interval = HZ * option;
-			break;
-		case Opt_max_batch_time:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < 0)
-				return 0;
-			if (option == 0)
-				option = EXT4_DEF_MAX_BATCH_TIME;
-			sbi->s_max_batch_time = option;
-			break;
-		case Opt_min_batch_time:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < 0)
-				return 0;
-			sbi->s_min_batch_time = option;
-			break;
-		case Opt_data_journal:
-			data_opt = EXT4_MOUNT_JOURNAL_DATA;
-			goto datacheck;
-		case Opt_data_ordered:
-			data_opt = EXT4_MOUNT_ORDERED_DATA;
-			goto datacheck;
-		case Opt_data_writeback:
-			data_opt = EXT4_MOUNT_WRITEBACK_DATA;
-		datacheck:
+			sbi->s_inode_readahead_blks = arg;
+		} else if (token == Opt_init_itable) {
+			set_opt(sb, INIT_INODE_TABLE);
+			if (!args->from)
+				arg = EXT4_DEF_LI_WAIT_MULT;
+			sbi->s_li_wait_mult = arg;
+		} else if (token == Opt_stripe) {
+			sbi->s_stripe = arg;
+		} else if (m->flags & MOPT_DATAJ) {
 			if (is_remount) {
 				if (!sbi->s_journal)
 					ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
-				else if (test_opt(sb, DATA_FLAGS) != data_opt) {
+				else if (test_opt(sb, DATA_FLAGS) !=
+					 m->mount_opt) {
 					ext4_msg(sb, KERN_ERR,
-						"Cannot change data mode on remount");
-					return 0;
+					 "Cannot change data mode on remount");
+					return -1;
 				}
 			} else {
 				clear_opt(sb, DATA_FLAGS);
-				sbi->s_mount_opt |= data_opt;
+				sbi->s_mount_opt |= m->mount_opt;
 			}
-			break;
-		case Opt_data_err_abort:
-			set_opt(sb, DATA_ERR_ABORT);
-			break;
-		case Opt_data_err_ignore:
-			clear_opt(sb, DATA_ERR_ABORT);
-			break;
 #ifdef CONFIG_QUOTA
-		case Opt_usrjquota:
+		} else if (token == Opt_usrjquota) {
 			if (!set_qf_name(sb, USRQUOTA, &args[0]))
-				return 0;
-			break;
-		case Opt_grpjquota:
+				return -1;
+		} else if (token == Opt_grpjquota) {
 			if (!set_qf_name(sb, GRPQUOTA, &args[0]))
-				return 0;
-			break;
-		case Opt_offusrjquota:
+				return -1;
+		} else if (token == Opt_offusrjquota) {
 			if (!clear_qf_name(sb, USRQUOTA))
-				return 0;
-			break;
-		case Opt_offgrpjquota:
+				return -1;
+		} else if (token == Opt_offgrpjquota) {
 			if (!clear_qf_name(sb, GRPQUOTA))
-				return 0;
-			break;
-
-		case Opt_jqfmt_vfsold:
-			qfmt = QFMT_VFS_OLD;
-			goto set_qf_format;
-		case Opt_jqfmt_vfsv0:
-			qfmt = QFMT_VFS_V0;
-			goto set_qf_format;
-		case Opt_jqfmt_vfsv1:
-			qfmt = QFMT_VFS_V1;
-set_qf_format:
+				return -1;
+		} else if (m->flags & MOPT_QFMT) {
 			if (sb_any_quota_loaded(sb) &&
-			    sbi->s_jquota_fmt != qfmt) {
-				ext4_msg(sb, KERN_ERR, "Cannot change "
-					"journaled quota options when "
-					"quota turned on");
-				return 0;
-			}
-			sbi->s_jquota_fmt = qfmt;
-			break;
-		case Opt_quota:
-		case Opt_usrquota:
-			set_opt(sb, QUOTA);
-			set_opt(sb, USRQUOTA);
-			break;
-		case Opt_grpquota:
-			set_opt(sb, QUOTA);
-			set_opt(sb, GRPQUOTA);
-			break;
-		case Opt_noquota:
-			if (sb_any_quota_loaded(sb)) {
-				ext4_msg(sb, KERN_ERR, "Cannot change quota "
-					"options when quota turned on");
-				return 0;
+			    sbi->s_jquota_fmt != m->mount_opt) {
+				ext4_msg(sb, KERN_ERR, "Cannot "
+					 "change journaled quota options "
+					 "when quota turned on");
+				return -1;
 			}
-			clear_opt(sb, QUOTA);
-			clear_opt(sb, USRQUOTA);
-			clear_opt(sb, GRPQUOTA);
-			break;
-#else
-		case Opt_quota:
-		case Opt_usrquota:
-		case Opt_grpquota:
-			ext4_msg(sb, KERN_ERR,
-				"quota options not supported");
-			break;
-		case Opt_usrjquota:
-		case Opt_grpjquota:
-		case Opt_offusrjquota:
-		case Opt_offgrpjquota:
-		case Opt_jqfmt_vfsold:
-		case Opt_jqfmt_vfsv0:
-		case Opt_jqfmt_vfsv1:
-			ext4_msg(sb, KERN_ERR,
-				"journaled quota options not supported");
-			break;
-		case Opt_noquota:
-			break;
+			sbi->s_jquota_fmt = m->mount_opt;
 #endif
-		case Opt_abort:
-			sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
-			break;
-		case Opt_nobarrier:
-			clear_opt(sb, BARRIER);
-			break;
-		case Opt_barrier:
-			if (args[0].from) {
-				if (match_int(&args[0], &option))
-					return 0;
-			} else
-				option = 1;	/* No argument, default to 1 */
-			if (option)
-				set_opt(sb, BARRIER);
-			else
-				clear_opt(sb, BARRIER);
-			break;
-		case Opt_ignore:
-			break;
-		case Opt_resize:
-			if (!is_remount) {
-				ext4_msg(sb, KERN_ERR,
-					"resize option only available "
-					"for remount");
-				return 0;
-			}
-			if (match_int(&args[0], &option) != 0)
-				return 0;
-			*n_blocks_count = option;
-			break;
-		case Opt_nobh:
-			ext4_msg(sb, KERN_WARNING,
-				 "Ignoring deprecated nobh option");
-			break;
-		case Opt_bh:
-			ext4_msg(sb, KERN_WARNING,
-				 "Ignoring deprecated bh option");
-			break;
-		case Opt_i_version:
-			set_opt(sb, I_VERSION);
-			sb->s_flags |= MS_I_VERSION;
-			break;
-		case Opt_nodelalloc:
-			clear_opt(sb, DELALLOC);
-			clear_opt2(sb, EXPLICIT_DELALLOC);
-			break;
-		case Opt_mblk_io_submit:
-			set_opt(sb, MBLK_IO_SUBMIT);
-			break;
-		case Opt_nomblk_io_submit:
-			clear_opt(sb, MBLK_IO_SUBMIT);
-			break;
-		case Opt_stripe:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < 0)
-				return 0;
-			sbi->s_stripe = option;
-			break;
-		case Opt_delalloc:
-			set_opt(sb, DELALLOC);
-			set_opt2(sb, EXPLICIT_DELALLOC);
-			break;
-		case Opt_block_validity:
-			set_opt(sb, BLOCK_VALIDITY);
-			break;
-		case Opt_noblock_validity:
-			clear_opt(sb, BLOCK_VALIDITY);
-			break;
-		case Opt_inode_readahead_blks:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < 0 || option > (1 << 30))
-				return 0;
-			if (option && !is_power_of_2(option)) {
-				ext4_msg(sb, KERN_ERR,
-					 "EXT4-fs: inode_readahead_blks"
-					 " must be a power of 2");
-				return 0;
+		} else {
+			if (!args->from)
+				arg = 1;
+			if (m->flags & MOPT_CLEAR)
+				arg = !arg;
+			else if (unlikely(!(m->flags & MOPT_SET))) {
+				ext4_msg(sb, KERN_WARNING,
+					 "buggy handling of option %s", opt);
+				WARN_ON(1);
+				return -1;
 			}
-			sbi->s_inode_readahead_blks = option;
-			break;
-		case Opt_journal_ioprio:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < 0 || option > 7)
-				break;
-			*journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE,
-							    option);
-			break;
-		case Opt_noauto_da_alloc:
-			set_opt(sb, NO_AUTO_DA_ALLOC);
-			break;
-		case Opt_auto_da_alloc:
-			if (args[0].from) {
-				if (match_int(&args[0], &option))
-					return 0;
-			} else
-				option = 1;	/* No argument, default to 1 */
-			if (option)
-				clear_opt(sb, NO_AUTO_DA_ALLOC);
+			if (arg != 0)
+				sbi->s_mount_opt |= m->mount_opt;
 			else
-				set_opt(sb,NO_AUTO_DA_ALLOC);
-			break;
-		case Opt_discard:
-			set_opt(sb, DISCARD);
-			break;
-		case Opt_nodiscard:
-			clear_opt(sb, DISCARD);
-			break;
-		case Opt_dioread_nolock:
-			set_opt(sb, DIOREAD_NOLOCK);
-			break;
-		case Opt_dioread_lock:
-			clear_opt(sb, DIOREAD_NOLOCK);
-			break;
-		case Opt_init_itable:
-			set_opt(sb, INIT_INODE_TABLE);
-			if (args[0].from) {
-				if (match_int(&args[0], &option))
-					return 0;
-			} else
-				option = EXT4_DEF_LI_WAIT_MULT;
-			if (option < 0)
-				return 0;
-			sbi->s_li_wait_mult = option;
-			break;
-		case Opt_noinit_itable:
-			clear_opt(sb, INIT_INODE_TABLE);
-			break;
-		default:
-			ext4_msg(sb, KERN_ERR,
-			       "Unrecognized mount option \"%s\" "
-			       "or missing value", p);
-			return 0;
+				sbi->s_mount_opt &= ~m->mount_opt;
 		}
+		return 1;
+	}
+	ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" "
+		 "or missing value", opt);
+	return -1;
+}
+
+static int parse_options(char *options, struct super_block *sb,
+			 unsigned long *journal_devnum,
+			 unsigned int *journal_ioprio,
+			 int is_remount)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int token;
+
+	if (!options)
+		return 1;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		if (!*p)
+			continue;
+		/*
+		 * Initialize args struct so we know whether arg was
+		 * found; some options take optional arguments.
+		 */
+		args[0].to = args[0].from = 0;
+		token = match_token(p, tokens, args);
+		if (handle_mount_opt(sb, p, token, args, journal_devnum,
+				     journal_ioprio, is_remount) < 0)
+			return 0;
 	}
 #ifdef CONFIG_QUOTA
 	if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
@@ -1942,6 +1651,160 @@ set_qf_format:
 	return 1;
 }
 
+static inline void ext4_show_quota_options(struct seq_file *seq,
+					   struct super_block *sb)
+{
+#if defined(CONFIG_QUOTA)
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (sbi->s_jquota_fmt) {
+		char *fmtname = "";
+
+		switch (sbi->s_jquota_fmt) {
+		case QFMT_VFS_OLD:
+			fmtname = "vfsold";
+			break;
+		case QFMT_VFS_V0:
+			fmtname = "vfsv0";
+			break;
+		case QFMT_VFS_V1:
+			fmtname = "vfsv1";
+			break;
+		}
+		seq_printf(seq, ",jqfmt=%s", fmtname);
+	}
+
+	if (sbi->s_qf_names[USRQUOTA])
+		seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
+
+	if (sbi->s_qf_names[GRPQUOTA])
+		seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
+
+	if (test_opt(sb, USRQUOTA))
+		seq_puts(seq, ",usrquota");
+
+	if (test_opt(sb, GRPQUOTA))
+		seq_puts(seq, ",grpquota");
+#endif
+}
+
+static const char *token2str(int token)
+{
+	static const struct match_token *t;
+
+	for (t = tokens; t->token != Opt_err; t++)
+		if (t->token == token && !strchr(t->pattern, '='))
+			break;
+	return t->pattern;
+}
+
+/*
+ * Show an option if
+ *  - it's set to a non-default value OR
+ *  - if the per-sb default is different from the global default
+ */
+static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
+			      int nodefs)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	int def_errors, def_mount_opt = nodefs ? 0 : sbi->s_def_mount_opt;
+	const struct mount_opts *m;
+	char sep = nodefs ? '\n' : ',';
+
+#define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep)
+#define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg)
+
+	if (sbi->s_sb_block != 1)
+		SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block);
+
+	for (m = ext4_mount_opts; m->token != Opt_err; m++) {
+		int want_set = m->flags & MOPT_SET;
+		if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
+		    (m->flags & MOPT_CLEAR_ERR))
+			continue;
+		if (!(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
+			continue; /* skip if same as the default */
+		if ((want_set &&
+		     (sbi->s_mount_opt & m->mount_opt) != m->mount_opt) ||
+		    (!want_set && (sbi->s_mount_opt & m->mount_opt)))
+			continue; /* select Opt_noFoo vs Opt_Foo */
+		SEQ_OPTS_PRINT("%s", token2str(m->token));
+	}
+
+	if (nodefs || sbi->s_resuid != EXT4_DEF_RESUID ||
+	    le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID)
+		SEQ_OPTS_PRINT("resuid=%u", sbi->s_resuid);
+	if (nodefs || sbi->s_resgid != EXT4_DEF_RESGID ||
+	    le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID)
+		SEQ_OPTS_PRINT("resgid=%u", sbi->s_resgid);
+	def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors);
+	if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO)
+		SEQ_OPTS_PUTS("errors=remount-ro");
+	if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
+		SEQ_OPTS_PUTS("errors=continue");
+	if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
+		SEQ_OPTS_PUTS("errors=panic");
+	if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ)
+		SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ);
+	if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME)
+		SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
+	if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
+		SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
+	if (sb->s_flags & MS_I_VERSION)
+		SEQ_OPTS_PUTS("i_version");
+	if (nodefs || sbi->s_stripe)
+		SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
+	if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ def_mount_opt)) {
+		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+			SEQ_OPTS_PUTS("data=journal");
+		else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+			SEQ_OPTS_PUTS("data=ordered");
+		else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+			SEQ_OPTS_PUTS("data=writeback");
+	}
+	if (nodefs ||
+	    sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
+		SEQ_OPTS_PRINT("inode_readahead_blks=%u",
+			       sbi->s_inode_readahead_blks);
+
+	if (nodefs || (test_opt(sb, INIT_INODE_TABLE) &&
+		       (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)))
+		SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
+
+	ext4_show_quota_options(seq, sb);
+	return 0;
+}
+
+static int ext4_show_options(struct seq_file *seq, struct dentry *root)
+{
+	return _ext4_show_options(seq, root->d_sb, 0);
+}
+
+static int options_seq_show(struct seq_file *seq, void *offset)
+{
+	struct super_block *sb = seq->private;
+	int rc;
+
+	seq_puts(seq, (sb->s_flags & MS_RDONLY) ? "ro" : "rw");
+	rc = _ext4_show_options(seq, sb, 1);
+	seq_puts(seq, "\n");
+	return rc;
+}
+
+static int options_open_fs(struct inode *inode, struct file *file)
+{
+	return single_open(file, options_seq_show, PDE(inode)->data);
+}
+
+static const struct file_operations ext4_seq_options_fops = {
+	.owner = THIS_MODULE,
+	.open = options_open_fs,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 			    int read_only)
 {
@@ -2945,7 +2808,7 @@ static int ext4_run_lazyinit_thread(void)
 		ext4_clear_request_list();
 		kfree(ext4_li_info);
 		ext4_li_info = NULL;
-		printk(KERN_CRIT "EXT4: error %d creating inode table "
+		printk(KERN_CRIT "EXT4-fs: error %d creating inode table "
 				 "initialization thread\n",
 				 err);
 		return err;
@@ -3183,11 +3046,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	set_opt(sb, INIT_INODE_TABLE);
 	if (def_mount_opts & EXT4_DEFM_DEBUG)
 		set_opt(sb, DEBUG);
-	if (def_mount_opts & EXT4_DEFM_BSDGROUPS) {
-		ext4_msg(sb, KERN_WARNING, deprecated_msg, "bsdgroups",
-			"2.6.38");
+	if (def_mount_opts & EXT4_DEFM_BSDGROUPS)
 		set_opt(sb, GRPID);
-	}
 	if (def_mount_opts & EXT4_DEFM_UID16)
 		set_opt(sb, NO_UID32);
 	/* xattr user namespace & acls are now defaulted on */
@@ -3240,13 +3100,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
 
 	if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
-			   &journal_devnum, &journal_ioprio, NULL, 0)) {
+			   &journal_devnum, &journal_ioprio, 0)) {
 		ext4_msg(sb, KERN_WARNING,
 			 "failed to parse options in superblock: %s",
 			 sbi->s_es->s_mount_opts);
 	}
+	sbi->s_def_mount_opt = sbi->s_mount_opt;
 	if (!parse_options((char *) data, sb, &journal_devnum,
-			   &journal_ioprio, NULL, 0))
+			   &journal_ioprio, 0))
 		goto failed_mount;
 
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
@@ -3416,7 +3277,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #else
 		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
 #endif
-		sb->s_dirt = 1;
 	}
 
 	/* Handle clustersize */
@@ -3540,6 +3400,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (ext4_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
 
+	if (sbi->s_proc)
+		proc_create_data("options", S_IRUGO, sbi->s_proc,
+				 &ext4_seq_options_fops, sb);
+
 	bgl_lock_init(sbi->s_blockgroup_lock);
 
 	for (i = 0; i < db_count; i++) {
@@ -3694,6 +3558,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
+	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
+
 	/*
 	 * The journal may have updated the bg summary counts, so we
 	 * need to update the global counters.
@@ -3861,6 +3727,7 @@ failed_mount2:
 	ext4_kvfree(sbi->s_group_desc);
 failed_mount:
 	if (sbi->s_proc) {
+		remove_proc_entry("options", sbi->s_proc);
 		remove_proc_entry(sb->s_id, ext4_proc_root);
 	}
 #ifdef CONFIG_QUOTA
@@ -4090,15 +3957,6 @@ static int ext4_load_journal(struct super_block *sb,
 	if (!(journal->j_flags & JBD2_BARRIER))
 		ext4_msg(sb, KERN_INFO, "barriers disabled");
 
-	if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
-		err = jbd2_journal_update_format(journal);
-		if (err)  {
-			ext4_msg(sb, KERN_ERR, "error updating journal");
-			jbd2_journal_destroy(journal);
-			return err;
-		}
-	}
-
 	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER))
 		err = jbd2_journal_wipe(journal, !really_read_only);
 	if (!err) {
@@ -4385,7 +4243,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	ext4_fsblk_t n_blocks_count = 0;
 	unsigned long old_sb_flags;
 	struct ext4_mount_options old_opts;
 	int enable_quota = 0;
@@ -4418,8 +4275,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	/*
 	 * Allow the "check" option to be passed as a remount option.
 	 */
-	if (!parse_options(data, sb, NULL, &journal_ioprio,
-			   &n_blocks_count, 1)) {
+	if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
 		err = -EINVAL;
 		goto restore_opts;
 	}
@@ -4437,8 +4293,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 	}
 
-	if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
-		n_blocks_count > ext4_blocks_count(es)) {
+	if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) {
 		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
 			err = -EROFS;
 			goto restore_opts;
@@ -4513,8 +4368,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			if (sbi->s_journal)
 				ext4_clear_journal_err(sb, es);
 			sbi->s_mount_state = le16_to_cpu(es->s_state);
-			if ((err = ext4_group_extend(sb, es, n_blocks_count)))
-				goto restore_opts;
 			if (!ext4_setup_super(sb, es, 0))
 				sb->s_flags &= ~MS_RDONLY;
 			if (EXT4_HAS_INCOMPAT_FEATURE(sb,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 93a00d89a220..e88748e55c0f 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -82,8 +82,8 @@
 		printk("\n"); \
 	} while (0)
 #else
-# define ea_idebug(f...)
-# define ea_bdebug(f...)
+# define ea_idebug(inode, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
+# define ea_bdebug(bh, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 static void ext4_xattr_cache_insert(struct buffer_head *);
@@ -158,13 +158,10 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
 static inline int
 ext4_xattr_check_block(struct buffer_head *bh)
 {
-	int error;
-
 	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
 	    BHDR(bh)->h_blocks != cpu_to_le32(1))
 		return -EIO;
-	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
-	return error;
+	return ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
 }
 
 static inline int
@@ -220,7 +217,8 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
 	error = -ENODATA;
 	if (!EXT4_I(inode)->i_file_acl)
 		goto cleanup;
-	ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
+	ea_idebug(inode, "reading block %llu",
+		  (unsigned long long)EXT4_I(inode)->i_file_acl);
 	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
 	if (!bh)
 		goto cleanup;
@@ -363,7 +361,8 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	error = 0;
 	if (!EXT4_I(inode)->i_file_acl)
 		goto cleanup;
-	ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
+	ea_idebug(inode, "reading block %llu",
+		  (unsigned long long)EXT4_I(inode)->i_file_acl);
 	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
 	error = -EIO;
 	if (!bh)
@@ -487,18 +486,19 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		ext4_free_blocks(handle, inode, bh, 0, 1,
 				 EXT4_FREE_BLOCKS_METADATA |
 				 EXT4_FREE_BLOCKS_FORGET);
+		unlock_buffer(bh);
 	} else {
 		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
+		if (ce)
+			mb_cache_entry_release(ce);
+		unlock_buffer(bh);
 		error = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 		dquot_free_block(inode, 1);
 		ea_bdebug(bh, "refcount now=%d; releasing",
 			  le32_to_cpu(BHDR(bh)->h_refcount));
-		if (ce)
-			mb_cache_entry_release(ce);
 	}
-	unlock_buffer(bh);
 out:
 	ext4_std_error(inode->i_sb, error);
 	return;
@@ -834,7 +834,8 @@ inserted:
 			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
 
-			ea_idebug(inode, "creating block %d", block);
+			ea_idebug(inode, "creating block %llu",
+				  (unsigned long long)block);
 
 			new_bh = sb_getblk(sb, block);
 			if (!new_bh) {
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 22764c7c8382..75e7c1f3a080 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -32,20 +32,20 @@ void set_close_on_exec(unsigned int fd, int flag)
 	spin_lock(&files->file_lock);
 	fdt = files_fdtable(files);
 	if (flag)
-		FD_SET(fd, fdt->close_on_exec);
+		__set_close_on_exec(fd, fdt);
 	else
-		FD_CLR(fd, fdt->close_on_exec);
+		__clear_close_on_exec(fd, fdt);
 	spin_unlock(&files->file_lock);
 }
 
-static int get_close_on_exec(unsigned int fd)
+static bool get_close_on_exec(unsigned int fd)
 {
 	struct files_struct *files = current->files;
 	struct fdtable *fdt;
-	int res;
+	bool res;
 	rcu_read_lock();
 	fdt = files_fdtable(files);
-	res = FD_ISSET(fd, fdt->close_on_exec);
+	res = close_on_exec(fd, fdt);
 	rcu_read_unlock();
 	return res;
 }
@@ -90,15 +90,15 @@ SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
 	err = -EBUSY;
 	fdt = files_fdtable(files);
 	tofree = fdt->fd[newfd];
-	if (!tofree && FD_ISSET(newfd, fdt->open_fds))
+	if (!tofree && fd_is_open(newfd, fdt))
 		goto out_unlock;
 	get_file(file);
 	rcu_assign_pointer(fdt->fd[newfd], file);
-	FD_SET(newfd, fdt->open_fds);
+	__set_open_fd(newfd, fdt);
 	if (flags & O_CLOEXEC)
-		FD_SET(newfd, fdt->close_on_exec);
+		__set_close_on_exec(newfd, fdt);
 	else
-		FD_CLR(newfd, fdt->close_on_exec);
+		__clear_close_on_exec(newfd, fdt);
 	spin_unlock(&files->file_lock);
 
 	if (tofree)
diff --git a/fs/file.c b/fs/file.c
index 3c426de7203a..ba3f6053025c 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -40,7 +40,7 @@ int sysctl_nr_open_max = 1024 * 1024; /* raised later */
  */
 static DEFINE_PER_CPU(struct fdtable_defer, fdtable_defer_list);
 
-static void *alloc_fdmem(unsigned int size)
+static void *alloc_fdmem(size_t size)
 {
 	/*
 	 * Very large allocations can stress page reclaim, so fall back to
@@ -142,7 +142,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
 static struct fdtable * alloc_fdtable(unsigned int nr)
 {
 	struct fdtable *fdt;
-	char *data;
+	void *data;
 
 	/*
 	 * Figure out how many fds we actually want to support in this fdtable.
@@ -172,14 +172,15 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
 	data = alloc_fdmem(nr * sizeof(struct file *));
 	if (!data)
 		goto out_fdt;
-	fdt->fd = (struct file **)data;
-	data = alloc_fdmem(max_t(unsigned int,
+	fdt->fd = data;
+
+	data = alloc_fdmem(max_t(size_t,
 				 2 * nr / BITS_PER_BYTE, L1_CACHE_BYTES));
 	if (!data)
 		goto out_arr;
-	fdt->open_fds = (fd_set *)data;
+	fdt->open_fds = data;
 	data += nr / BITS_PER_BYTE;
-	fdt->close_on_exec = (fd_set *)data;
+	fdt->close_on_exec = data;
 	fdt->next = NULL;
 
 	return fdt;
@@ -275,11 +276,11 @@ static int count_open_files(struct fdtable *fdt)
 	int i;
 
 	/* Find the last open fd */
-	for (i = size/(8*sizeof(long)); i > 0; ) {
-		if (fdt->open_fds->fds_bits[--i])
+	for (i = size / BITS_PER_LONG; i > 0; ) {
+		if (fdt->open_fds[--i])
 			break;
 	}
-	i = (i+1) * 8 * sizeof(long);
+	i = (i + 1) * BITS_PER_LONG;
 	return i;
 }
 
@@ -306,8 +307,8 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 	newf->next_fd = 0;
 	new_fdt = &newf->fdtab;
 	new_fdt->max_fds = NR_OPEN_DEFAULT;
-	new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
-	new_fdt->open_fds = (fd_set *)&newf->open_fds_init;
+	new_fdt->close_on_exec = newf->close_on_exec_init;
+	new_fdt->open_fds = newf->open_fds_init;
 	new_fdt->fd = &newf->fd_array[0];
 	new_fdt->next = NULL;
 
@@ -350,10 +351,8 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 	old_fds = old_fdt->fd;
 	new_fds = new_fdt->fd;
 
-	memcpy(new_fdt->open_fds->fds_bits,
-		old_fdt->open_fds->fds_bits, open_files/8);
-	memcpy(new_fdt->close_on_exec->fds_bits,
-		old_fdt->close_on_exec->fds_bits, open_files/8);
+	memcpy(new_fdt->open_fds, old_fdt->open_fds, open_files / 8);
+	memcpy(new_fdt->close_on_exec, old_fdt->close_on_exec, open_files / 8);
 
 	for (i = open_files; i != 0; i--) {
 		struct file *f = *old_fds++;
@@ -366,7 +365,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 			 * is partway through open().  So make sure that this
 			 * fd is available to the new process.
 			 */
-			FD_CLR(open_files - i, new_fdt->open_fds);
+			__clear_open_fd(open_files - i, new_fdt);
 		}
 		rcu_assign_pointer(*new_fds++, f);
 	}
@@ -379,11 +378,11 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 	memset(new_fds, 0, size);
 
 	if (new_fdt->max_fds > open_files) {
-		int left = (new_fdt->max_fds-open_files)/8;
-		int start = open_files / (8 * sizeof(unsigned long));
+		int left = (new_fdt->max_fds - open_files) / 8;
+		int start = open_files / BITS_PER_LONG;
 
-		memset(&new_fdt->open_fds->fds_bits[start], 0, left);
-		memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
+		memset(&new_fdt->open_fds[start], 0, left);
+		memset(&new_fdt->close_on_exec[start], 0, left);
 	}
 
 	rcu_assign_pointer(newf->fdt, new_fdt);
@@ -419,8 +418,8 @@ struct files_struct init_files = {
 	.fdtab		= {
 		.max_fds	= NR_OPEN_DEFAULT,
 		.fd		= &init_files.fd_array[0],
-		.close_on_exec	= (fd_set *)&init_files.close_on_exec_init,
-		.open_fds	= (fd_set *)&init_files.open_fds_init,
+		.close_on_exec	= init_files.close_on_exec_init,
+		.open_fds	= init_files.open_fds_init,
 	},
 	.file_lock	= __SPIN_LOCK_UNLOCKED(init_task.file_lock),
 };
@@ -443,8 +442,7 @@ repeat:
 		fd = files->next_fd;
 
 	if (fd < fdt->max_fds)
-		fd = find_next_zero_bit(fdt->open_fds->fds_bits,
-					   fdt->max_fds, fd);
+		fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd);
 
 	error = expand_files(files, fd);
 	if (error < 0)
@@ -460,11 +458,11 @@ repeat:
 	if (start <= files->next_fd)
 		files->next_fd = fd + 1;
 
-	FD_SET(fd, fdt->open_fds);
+	__set_open_fd(fd, fdt);
 	if (flags & O_CLOEXEC)
-		FD_SET(fd, fdt->close_on_exec);
+		__set_close_on_exec(fd, fdt);
 	else
-		FD_CLR(fd, fdt->close_on_exec);
+		__clear_close_on_exec(fd, fdt);
 	error = fd;
 #if 1
 	/* Sanity check */
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 236972b752f5..539f36cf3e4a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -256,7 +256,8 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 }
 
 /*
- * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
+ * Move expired (dirtied after work->older_than_this) dirty inodes from
+ * @delaying_queue to @dispatch_queue.
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
@@ -1148,23 +1149,6 @@ out_unlock_inode:
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
-/*
- * Write out a superblock's list of dirty inodes.  A wait will be performed
- * upon no inodes, all inodes or the final one, depending upon sync_mode.
- *
- * If older_than_this is non-NULL, then only write out inodes which
- * had their first dirtying at a time earlier than *older_than_this.
- *
- * If `bdi' is non-zero then we're being asked to writeback a specific queue.
- * This function assumes that the blockdev superblock's inodes are backed by
- * a variety of queues, so all inodes are searched.  For other superblocks,
- * assume that all inodes are backed by the same queue.
- *
- * The inodes to be written are parked on bdi->b_io.  They are moved back onto
- * bdi->b_dirty as they are selected for writing.  This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
- */
 static void wait_sb_inodes(struct super_block *sb)
 {
 	struct inode *inode, *old_inode = NULL;
@@ -1364,8 +1348,6 @@ int write_inode_now(struct inode *inode, int sync)
 	ret = writeback_single_inode(inode, wb, &wbc);
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&wb->list_lock);
-	if (sync)
-		inode_sync_wait(inode);
 	return ret;
 }
 EXPORT_SYMBOL(write_inode_now);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 76834587a8a4..a3d2c9ee8d66 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -18,7 +18,6 @@
 #include <linux/mount.h>
 #include <linux/fs.h>
 #include <linux/gfs2_ondisk.h>
-#include <linux/ext2_fs.h>
 #include <linux/falloc.h>
 #include <linux/swap.h>
 #include <linux/crc32.h>
diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
index 3cbfa93cd782..1fe731337f07 100644
--- a/fs/hostfs/hostfs.h
+++ b/fs/hostfs/hostfs.h
@@ -67,7 +67,8 @@ extern int access_file(char *path, int r, int w, int x);
 extern int open_file(char *path, int r, int w, int append);
 extern void *open_dir(char *path, int *err_out);
 extern char *read_dir(void *stream, unsigned long long *pos,
-		      unsigned long long *ino_out, int *len_out);
+		      unsigned long long *ino_out, int *len_out,
+		      unsigned int *type_out);
 extern void close_file(void *stream);
 extern int replace_file(int oldfd, int fd);
 extern void close_dir(void *stream);
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 588d45885a6f..07c516bfea76 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -283,6 +283,7 @@ int hostfs_readdir(struct file *file, void *ent, filldir_t filldir)
 	char *name;
 	unsigned long long next, ino;
 	int error, len;
+	unsigned int type;
 
 	name = dentry_name(file->f_path.dentry);
 	if (name == NULL)
@@ -292,9 +293,9 @@ int hostfs_readdir(struct file *file, void *ent, filldir_t filldir)
 	if (dir == NULL)
 		return -error;
 	next = file->f_pos;
-	while ((name = read_dir(dir, &next, &ino, &len)) != NULL) {
+	while ((name = read_dir(dir, &next, &ino, &len, &type)) != NULL) {
 		error = (*filldir)(ent, name, len, file->f_pos,
-				   ino, DT_UNKNOWN);
+				   ino, type);
 		if (error) break;
 		file->f_pos = next;
 	}
diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
index dd7bc38a3825..a74ad0d371c2 100644
--- a/fs/hostfs/hostfs_user.c
+++ b/fs/hostfs/hostfs_user.c
@@ -98,7 +98,8 @@ void *open_dir(char *path, int *err_out)
 }
 
 char *read_dir(void *stream, unsigned long long *pos,
-	       unsigned long long *ino_out, int *len_out)
+	       unsigned long long *ino_out, int *len_out,
+	       unsigned int *type_out)
 {
 	DIR *dir = stream;
 	struct dirent *ent;
@@ -109,6 +110,7 @@ char *read_dir(void *stream, unsigned long long *pos,
 		return NULL;
 	*len_out = strlen(ent->d_name);
 	*ino_out = ent->d_ino;
+	*type_out = ent->d_type;
 	*pos = telldir(dir);
 	return ent->d_name;
 }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ea251749d9d5..28cf06e4ec84 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1031,7 +1031,6 @@ static int __init init_hugetlbfs_fs(void)
 	}
 
 	error = PTR_ERR(vfsmount);
-	unregister_filesystem(&hugetlbfs_fs_type);
 
  out:
 	kmem_cache_destroy(hugetlbfs_inode_cachep);
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index d49d202903fb..c78841ee81cf 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -88,14 +88,13 @@ static inline void __buffer_relink_io(struct journal_head *jh)
  * whole transaction.
  *
  * Requires j_list_lock
- * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
  */
 static int __try_to_free_cp_buf(struct journal_head *jh)
 {
 	int ret = 0;
 	struct buffer_head *bh = jh2bh(jh);
 
-	if (jh->b_jlist == BJ_None && !buffer_locked(bh) &&
+	if (jh->b_transaction == NULL && !buffer_locked(bh) &&
 	    !buffer_dirty(bh) && !buffer_write_io_error(bh)) {
 		/*
 		 * Get our reference so that bh cannot be freed before
@@ -104,11 +103,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 		get_bh(bh);
 		JBUFFER_TRACE(jh, "remove from checkpoint list");
 		ret = __jbd2_journal_remove_checkpoint(jh) + 1;
-		jbd_unlock_bh_state(bh);
 		BUFFER_TRACE(bh, "release");
 		__brelse(bh);
-	} else {
-		jbd_unlock_bh_state(bh);
 	}
 	return ret;
 }
@@ -180,21 +176,6 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 }
 
 /*
- * We were unable to perform jbd_trylock_bh_state() inside j_list_lock.
- * The caller must restart a list walk.  Wait for someone else to run
- * jbd_unlock_bh_state().
- */
-static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
-	__releases(journal->j_list_lock)
-{
-	get_bh(bh);
-	spin_unlock(&journal->j_list_lock);
-	jbd_lock_bh_state(bh);
-	jbd_unlock_bh_state(bh);
-	put_bh(bh);
-}
-
-/*
  * Clean up transaction's list of buffers submitted for io.
  * We wait for any pending IO to complete and remove any clean
  * buffers. Note that we take the buffers in the opposite ordering
@@ -222,15 +203,9 @@ restart:
 	while (!released && transaction->t_checkpoint_io_list) {
 		jh = transaction->t_checkpoint_io_list;
 		bh = jh2bh(jh);
-		if (!jbd_trylock_bh_state(bh)) {
-			jbd_sync_bh(journal, bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart;
-		}
 		get_bh(bh);
 		if (buffer_locked(bh)) {
 			spin_unlock(&journal->j_list_lock);
-			jbd_unlock_bh_state(bh);
 			wait_on_buffer(bh);
 			/* the journal_head may have gone by now */
 			BUFFER_TRACE(bh, "brelse");
@@ -246,7 +221,6 @@ restart:
 		 * it has been written out and so we can drop it from the list
 		 */
 		released = __jbd2_journal_remove_checkpoint(jh);
-		jbd_unlock_bh_state(bh);
 		__brelse(bh);
 	}
 
@@ -266,7 +240,6 @@ __flush_batch(journal_t *journal, int *batch_count)
 
 	for (i = 0; i < *batch_count; i++) {
 		struct buffer_head *bh = journal->j_chkpt_bhs[i];
-		clear_buffer_jwrite(bh);
 		BUFFER_TRACE(bh, "brelse");
 		__brelse(bh);
 	}
@@ -281,7 +254,6 @@ __flush_batch(journal_t *journal, int *batch_count)
  * be written out.
  *
  * Called with j_list_lock held and drops it if 1 is returned
- * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
  */
 static int __process_buffer(journal_t *journal, struct journal_head *jh,
 			    int *batch_count, transaction_t *transaction)
@@ -292,7 +264,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 	if (buffer_locked(bh)) {
 		get_bh(bh);
 		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
 		wait_on_buffer(bh);
 		/* the journal_head may have gone by now */
 		BUFFER_TRACE(bh, "brelse");
@@ -304,7 +275,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 
 		transaction->t_chp_stats.cs_forced_to_close++;
 		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
 		if (unlikely(journal->j_flags & JBD2_UNMOUNT))
 			/*
 			 * The journal thread is dead; so starting and
@@ -323,11 +293,9 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		if (unlikely(buffer_write_io_error(bh)))
 			ret = -EIO;
 		get_bh(bh);
-		J_ASSERT_JH(jh, !buffer_jbddirty(bh));
 		BUFFER_TRACE(bh, "remove from checkpoint");
 		__jbd2_journal_remove_checkpoint(jh);
 		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
 		__brelse(bh);
 	} else {
 		/*
@@ -340,10 +308,8 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		BUFFER_TRACE(bh, "queue");
 		get_bh(bh);
 		J_ASSERT_BH(bh, !buffer_jwrite(bh));
-		set_buffer_jwrite(bh);
 		journal->j_chkpt_bhs[*batch_count] = bh;
 		__buffer_relink_io(jh);
-		jbd_unlock_bh_state(bh);
 		transaction->t_chp_stats.cs_written++;
 		(*batch_count)++;
 		if (*batch_count == JBD2_NR_BATCH) {
@@ -407,15 +373,7 @@ restart:
 		int retry = 0, err;
 
 		while (!retry && transaction->t_checkpoint_list) {
-			struct buffer_head *bh;
-
 			jh = transaction->t_checkpoint_list;
-			bh = jh2bh(jh);
-			if (!jbd_trylock_bh_state(bh)) {
-				jbd_sync_bh(journal, bh);
-				retry = 1;
-				break;
-			}
 			retry = __process_buffer(journal, jh, &batch_count,
 						 transaction);
 			if (retry < 0 && !result)
@@ -478,79 +436,28 @@ out:
 
 int jbd2_cleanup_journal_tail(journal_t *journal)
 {
-	transaction_t * transaction;
 	tid_t		first_tid;
-	unsigned long	blocknr, freed;
+	unsigned long	blocknr;
 
 	if (is_journal_aborted(journal))
 		return 1;
 
-	/* OK, work out the oldest transaction remaining in the log, and
-	 * the log block it starts at.
-	 *
-	 * If the log is now empty, we need to work out which is the
-	 * next transaction ID we will write, and where it will
-	 * start. */
-
-	write_lock(&journal->j_state_lock);
-	spin_lock(&journal->j_list_lock);
-	transaction = journal->j_checkpoint_transactions;
-	if (transaction) {
-		first_tid = transaction->t_tid;
-		blocknr = transaction->t_log_start;
-	} else if ((transaction = journal->j_committing_transaction) != NULL) {
-		first_tid = transaction->t_tid;
-		blocknr = transaction->t_log_start;
-	} else if ((transaction = journal->j_running_transaction) != NULL) {
-		first_tid = transaction->t_tid;
-		blocknr = journal->j_head;
-	} else {
-		first_tid = journal->j_transaction_sequence;
-		blocknr = journal->j_head;
-	}
-	spin_unlock(&journal->j_list_lock);
-	J_ASSERT(blocknr != 0);
-
-	/* If the oldest pinned transaction is at the tail of the log
-           already then there's not much we can do right now. */
-	if (journal->j_tail_sequence == first_tid) {
-		write_unlock(&journal->j_state_lock);
+	if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr))
 		return 1;
-	}
-
-	/* OK, update the superblock to recover the freed space.
-	 * Physical blocks come first: have we wrapped beyond the end of
-	 * the log?  */
-	freed = blocknr - journal->j_tail;
-	if (blocknr < journal->j_tail)
-		freed = freed + journal->j_last - journal->j_first;
-
-	trace_jbd2_cleanup_journal_tail(journal, first_tid, blocknr, freed);
-	jbd_debug(1,
-		  "Cleaning journal tail from %d to %d (offset %lu), "
-		  "freeing %lu\n",
-		  journal->j_tail_sequence, first_tid, blocknr, freed);
-
-	journal->j_free += freed;
-	journal->j_tail_sequence = first_tid;
-	journal->j_tail = blocknr;
-	write_unlock(&journal->j_state_lock);
+	J_ASSERT(blocknr != 0);
 
 	/*
-	 * If there is an external journal, we need to make sure that
-	 * any data blocks that were recently written out --- perhaps
-	 * by jbd2_log_do_checkpoint() --- are flushed out before we
-	 * drop the transactions from the external journal.  It's
-	 * unlikely this will be necessary, especially with a
-	 * appropriately sized journal, but we need this to guarantee
-	 * correctness.  Fortunately jbd2_cleanup_journal_tail()
-	 * doesn't get called all that often.
+	 * We need to make sure that any blocks that were recently written out
+	 * --- perhaps by jbd2_log_do_checkpoint() --- are flushed out before
+	 * we drop the transactions from the journal. It's unlikely this will
+	 * be necessary, especially with an appropriately sized journal, but we
+	 * need this to guarantee correctness.  Fortunately
+	 * jbd2_cleanup_journal_tail() doesn't get called all that often.
 	 */
-	if ((journal->j_fs_dev != journal->j_dev) &&
-	    (journal->j_flags & JBD2_BARRIER))
+	if (journal->j_flags & JBD2_BARRIER)
 		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
-	if (!(journal->j_flags & JBD2_ABORT))
-		jbd2_journal_update_superblock(journal, 1);
+
+	__jbd2_update_log_tail(journal, first_tid, blocknr);
 	return 0;
 }
 
@@ -582,15 +489,12 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
 	do {
 		jh = next_jh;
 		next_jh = jh->b_cpnext;
-		/* Use trylock because of the ranking */
-		if (jbd_trylock_bh_state(jh2bh(jh))) {
-			ret = __try_to_free_cp_buf(jh);
-			if (ret) {
-				freed++;
-				if (ret == 2) {
-					*released = 1;
-					return freed;
-				}
+		ret = __try_to_free_cp_buf(jh);
+		if (ret) {
+			freed++;
+			if (ret == 2) {
+				*released = 1;
+				return freed;
 			}
 		}
 		/*
@@ -673,9 +577,7 @@ out:
  * The function can free jh and bh.
  *
  * This function is called with j_list_lock held.
- * This function is called with jbd_lock_bh_state(jh2bh(jh))
  */
-
 int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 {
 	struct transaction_chp_stats_s *stats;
@@ -722,7 +624,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 				    transaction->t_tid, stats);
 
 	__jbd2_journal_drop_transaction(journal, transaction);
-	kfree(transaction);
+	jbd2_journal_free_transaction(transaction);
 
 	/* Just in case anybody was waiting for more transactions to be
            checkpointed... */
@@ -797,5 +699,7 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact
 	J_ASSERT(journal->j_committing_transaction != transaction);
 	J_ASSERT(journal->j_running_transaction != transaction);
 
+	trace_jbd2_drop_transaction(journal, transaction);
+
 	jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid);
 }
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index c067a8cae63b..806525a7269c 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -28,7 +28,6 @@
 #include <linux/blkdev.h>
 #include <linux/bitops.h>
 #include <trace/events/jbd2.h>
-#include <asm/system.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.
@@ -331,6 +330,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	struct buffer_head *cbh = NULL; /* For transactional checksums */
 	__u32 crc32_sum = ~0;
 	struct blk_plug plug;
+	/* Tail of the journal */
+	unsigned long first_block;
+	tid_t first_tid;
+	int update_tail;
 
 	/*
 	 * First job: lock down the current transaction and wait for
@@ -340,7 +343,18 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	/* Do we need to erase the effects of a prior jbd2_journal_flush? */
 	if (journal->j_flags & JBD2_FLUSHED) {
 		jbd_debug(3, "super block updated\n");
-		jbd2_journal_update_superblock(journal, 1);
+		mutex_lock(&journal->j_checkpoint_mutex);
+		/*
+		 * We hold j_checkpoint_mutex so tail cannot change under us.
+		 * We don't need any special data guarantees for writing sb
+		 * since journal is empty and it is ok for write to be
+		 * flushed only with transaction commit.
+		 */
+		jbd2_journal_update_sb_log_tail(journal,
+						journal->j_tail_sequence,
+						journal->j_tail,
+						WRITE_SYNC);
+		mutex_unlock(&journal->j_checkpoint_mutex);
 	} else {
 		jbd_debug(3, "superblock not updated\n");
 	}
@@ -677,10 +691,30 @@ start_journal_io:
 		err = 0;
 	}
 
+	/*
+	 * Get current oldest transaction in the log before we issue flush
+	 * to the filesystem device. After the flush we can be sure that
+	 * blocks of all older transactions are checkpointed to persistent
+	 * storage and we will be safe to update journal start in the
+	 * superblock with the numbers we get here.
+	 */
+	update_tail =
+		jbd2_journal_get_log_tail(journal, &first_tid, &first_block);
+
 	write_lock(&journal->j_state_lock);
+	if (update_tail) {
+		long freed = first_block - journal->j_tail;
+
+		if (first_block < journal->j_tail)
+			freed += journal->j_last - journal->j_first;
+		/* Update tail only if we free significant amount of space */
+		if (freed < journal->j_maxlen / 4)
+			update_tail = 0;
+	}
 	J_ASSERT(commit_transaction->t_state == T_COMMIT);
 	commit_transaction->t_state = T_COMMIT_DFLUSH;
 	write_unlock(&journal->j_state_lock);
+
 	/* 
 	 * If the journal is not located on the file system device,
 	 * then we must flush the file system device before we issue
@@ -831,6 +865,14 @@ wait_for_iobuf:
 	if (err)
 		jbd2_journal_abort(journal, err);
 
+	/*
+	 * Now disk caches for filesystem device are flushed so we are safe to
+	 * erase checkpointed transactions from the log by updating journal
+	 * superblock.
+	 */
+	if (update_tail)
+		jbd2_update_log_tail(journal, first_tid, first_block);
+
 	/* End of a transaction!  Finally, we can do checkpoint
            processing: any buffers committed as a result of this
            transaction can be removed from any checkpoint list it was on
@@ -1048,7 +1090,7 @@ restart_loop:
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 	if (to_free)
-		kfree(commit_transaction);
+		jbd2_journal_free_transaction(commit_transaction);
 
 	wake_up(&journal->j_wait_done_commit);
 }
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 839377e3d624..1afb701622b0 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -50,7 +50,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
-#include <asm/system.h>
 
 EXPORT_SYMBOL(jbd2_journal_extend);
 EXPORT_SYMBOL(jbd2_journal_stop);
@@ -71,7 +70,6 @@ EXPORT_SYMBOL(jbd2_journal_revoke);
 
 EXPORT_SYMBOL(jbd2_journal_init_dev);
 EXPORT_SYMBOL(jbd2_journal_init_inode);
-EXPORT_SYMBOL(jbd2_journal_update_format);
 EXPORT_SYMBOL(jbd2_journal_check_used_features);
 EXPORT_SYMBOL(jbd2_journal_check_available_features);
 EXPORT_SYMBOL(jbd2_journal_set_features);
@@ -96,7 +94,6 @@ EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
 EXPORT_SYMBOL(jbd2_inode_cache);
 
-static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
 static void __journal_abort_soft (journal_t *journal, int errno);
 static int jbd2_journal_create_slab(size_t slab_size);
 
@@ -746,6 +743,98 @@ struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
 	return jbd2_journal_add_journal_head(bh);
 }
 
+/*
+ * Return tid of the oldest transaction in the journal and block in the journal
+ * where the transaction starts.
+ *
+ * If the journal is now empty, return which will be the next transaction ID
+ * we will write and where will that transaction start.
+ *
+ * The return value is 0 if journal tail cannot be pushed any further, 1 if
+ * it can.
+ */
+int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
+			      unsigned long *block)
+{
+	transaction_t *transaction;
+	int ret;
+
+	read_lock(&journal->j_state_lock);
+	spin_lock(&journal->j_list_lock);
+	transaction = journal->j_checkpoint_transactions;
+	if (transaction) {
+		*tid = transaction->t_tid;
+		*block = transaction->t_log_start;
+	} else if ((transaction = journal->j_committing_transaction) != NULL) {
+		*tid = transaction->t_tid;
+		*block = transaction->t_log_start;
+	} else if ((transaction = journal->j_running_transaction) != NULL) {
+		*tid = transaction->t_tid;
+		*block = journal->j_head;
+	} else {
+		*tid = journal->j_transaction_sequence;
+		*block = journal->j_head;
+	}
+	ret = tid_gt(*tid, journal->j_tail_sequence);
+	spin_unlock(&journal->j_list_lock);
+	read_unlock(&journal->j_state_lock);
+
+	return ret;
+}
+
+/*
+ * Update information in journal structure and in on disk journal superblock
+ * about log tail. This function does not check whether information passed in
+ * really pushes log tail further. It's responsibility of the caller to make
+ * sure provided log tail information is valid (e.g. by holding
+ * j_checkpoint_mutex all the time between computing log tail and calling this
+ * function as is the case with jbd2_cleanup_journal_tail()).
+ *
+ * Requires j_checkpoint_mutex
+ */
+void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
+{
+	unsigned long freed;
+
+	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
+
+	/*
+	 * We cannot afford for write to remain in drive's caches since as
+	 * soon as we update j_tail, next transaction can start reusing journal
+	 * space and if we lose sb update during power failure we'd replay
+	 * old transaction with possibly newly overwritten data.
+	 */
+	jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA);
+	write_lock(&journal->j_state_lock);
+	freed = block - journal->j_tail;
+	if (block < journal->j_tail)
+		freed += journal->j_last - journal->j_first;
+
+	trace_jbd2_update_log_tail(journal, tid, block, freed);
+	jbd_debug(1,
+		  "Cleaning journal tail from %d to %d (offset %lu), "
+		  "freeing %lu\n",
+		  journal->j_tail_sequence, tid, block, freed);
+
+	journal->j_free += freed;
+	journal->j_tail_sequence = tid;
+	journal->j_tail = block;
+	write_unlock(&journal->j_state_lock);
+}
+
+/*
+ * This is a variaon of __jbd2_update_log_tail which checks for validity of
+ * provided log tail and locks j_checkpoint_mutex. So it is safe against races
+ * with other threads updating log tail.
+ */
+void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
+{
+	mutex_lock(&journal->j_checkpoint_mutex);
+	if (tid_gt(tid, journal->j_tail_sequence))
+		__jbd2_update_log_tail(journal, tid, block);
+	mutex_unlock(&journal->j_checkpoint_mutex);
+}
+
 struct jbd2_stats_proc_session {
 	journal_t *journal;
 	struct transaction_stats_s *stats;
@@ -1114,40 +1203,45 @@ static int journal_reset(journal_t *journal)
 
 	journal->j_max_transaction_buffers = journal->j_maxlen / 4;
 
-	/* Add the dynamic fields and write it to disk. */
-	jbd2_journal_update_superblock(journal, 1);
-	return jbd2_journal_start_thread(journal);
-}
-
-/**
- * void jbd2_journal_update_superblock() - Update journal sb on disk.
- * @journal: The journal to update.
- * @wait: Set to '0' if you don't want to wait for IO completion.
- *
- * Update a journal's dynamic superblock fields and write it to disk,
- * optionally waiting for the IO to complete.
- */
-void jbd2_journal_update_superblock(journal_t *journal, int wait)
-{
-	journal_superblock_t *sb = journal->j_superblock;
-	struct buffer_head *bh = journal->j_sb_buffer;
-
 	/*
 	 * As a special case, if the on-disk copy is already marked as needing
-	 * no recovery (s_start == 0) and there are no outstanding transactions
-	 * in the filesystem, then we can safely defer the superblock update
-	 * until the next commit by setting JBD2_FLUSHED.  This avoids
+	 * no recovery (s_start == 0), then we can safely defer the superblock
+	 * update until the next commit by setting JBD2_FLUSHED.  This avoids
 	 * attempting a write to a potential-readonly device.
 	 */
-	if (sb->s_start == 0 && journal->j_tail_sequence ==
-				journal->j_transaction_sequence) {
+	if (sb->s_start == 0) {
 		jbd_debug(1, "JBD2: Skipping superblock update on recovered sb "
 			"(start %ld, seq %d, errno %d)\n",
 			journal->j_tail, journal->j_tail_sequence,
 			journal->j_errno);
-		goto out;
+		journal->j_flags |= JBD2_FLUSHED;
+	} else {
+		/* Lock here to make assertions happy... */
+		mutex_lock(&journal->j_checkpoint_mutex);
+		/*
+		 * Update log tail information. We use WRITE_FUA since new
+		 * transaction will start reusing journal space and so we
+		 * must make sure information about current log tail is on
+		 * disk before that.
+		 */
+		jbd2_journal_update_sb_log_tail(journal,
+						journal->j_tail_sequence,
+						journal->j_tail,
+						WRITE_FUA);
+		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
+	return jbd2_journal_start_thread(journal);
+}
 
+static void jbd2_write_superblock(journal_t *journal, int write_op)
+{
+	struct buffer_head *bh = journal->j_sb_buffer;
+	int ret;
+
+	trace_jbd2_write_superblock(journal, write_op);
+	if (!(journal->j_flags & JBD2_BARRIER))
+		write_op &= ~(REQ_FUA | REQ_FLUSH);
+	lock_buffer(bh);
 	if (buffer_write_io_error(bh)) {
 		/*
 		 * Oh, dear.  A previous attempt to write the journal
@@ -1163,48 +1257,106 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
 		clear_buffer_write_io_error(bh);
 		set_buffer_uptodate(bh);
 	}
+	get_bh(bh);
+	bh->b_end_io = end_buffer_write_sync;
+	ret = submit_bh(write_op, bh);
+	wait_on_buffer(bh);
+	if (buffer_write_io_error(bh)) {
+		clear_buffer_write_io_error(bh);
+		set_buffer_uptodate(bh);
+		ret = -EIO;
+	}
+	if (ret) {
+		printk(KERN_ERR "JBD2: Error %d detected when updating "
+		       "journal superblock for %s.\n", ret,
+		       journal->j_devname);
+	}
+}
+
+/**
+ * jbd2_journal_update_sb_log_tail() - Update log tail in journal sb on disk.
+ * @journal: The journal to update.
+ * @tail_tid: TID of the new transaction at the tail of the log
+ * @tail_block: The first block of the transaction at the tail of the log
+ * @write_op: With which operation should we write the journal sb
+ *
+ * Update a journal's superblock information about log tail and write it to
+ * disk, waiting for the IO to complete.
+ */
+void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
+				     unsigned long tail_block, int write_op)
+{
+	journal_superblock_t *sb = journal->j_superblock;
+
+	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
+	jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
+		  tail_block, tail_tid);
+
+	sb->s_sequence = cpu_to_be32(tail_tid);
+	sb->s_start    = cpu_to_be32(tail_block);
+
+	jbd2_write_superblock(journal, write_op);
+
+	/* Log is no longer empty */
+	write_lock(&journal->j_state_lock);
+	WARN_ON(!sb->s_sequence);
+	journal->j_flags &= ~JBD2_FLUSHED;
+	write_unlock(&journal->j_state_lock);
+}
+
+/**
+ * jbd2_mark_journal_empty() - Mark on disk journal as empty.
+ * @journal: The journal to update.
+ *
+ * Update a journal's dynamic superblock fields to show that journal is empty.
+ * Write updated superblock to disk waiting for IO to complete.
+ */
+static void jbd2_mark_journal_empty(journal_t *journal)
+{
+	journal_superblock_t *sb = journal->j_superblock;
 
+	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	read_lock(&journal->j_state_lock);
-	jbd_debug(1, "JBD2: updating superblock (start %ld, seq %d, errno %d)\n",
-		  journal->j_tail, journal->j_tail_sequence, journal->j_errno);
+	jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n",
+		  journal->j_tail_sequence);
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
-	sb->s_start    = cpu_to_be32(journal->j_tail);
-	sb->s_errno    = cpu_to_be32(journal->j_errno);
+	sb->s_start    = cpu_to_be32(0);
 	read_unlock(&journal->j_state_lock);
 
-	BUFFER_TRACE(bh, "marking dirty");
-	mark_buffer_dirty(bh);
-	if (wait) {
-		sync_dirty_buffer(bh);
-		if (buffer_write_io_error(bh)) {
-			printk(KERN_ERR "JBD2: I/O error detected "
-			       "when updating journal superblock for %s.\n",
-			       journal->j_devname);
-			clear_buffer_write_io_error(bh);
-			set_buffer_uptodate(bh);
-		}
-	} else
-		write_dirty_buffer(bh, WRITE);
-
-out:
-	/* If we have just flushed the log (by marking s_start==0), then
-	 * any future commit will have to be careful to update the
-	 * superblock again to re-record the true start of the log. */
+	jbd2_write_superblock(journal, WRITE_FUA);
 
+	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
-	if (sb->s_start)
-		journal->j_flags &= ~JBD2_FLUSHED;
-	else
-		journal->j_flags |= JBD2_FLUSHED;
+	journal->j_flags |= JBD2_FLUSHED;
 	write_unlock(&journal->j_state_lock);
 }
 
+
+/**
+ * jbd2_journal_update_sb_errno() - Update error in the journal.
+ * @journal: The journal to update.
+ *
+ * Update a journal's errno.  Write updated superblock to disk waiting for IO
+ * to complete.
+ */
+static void jbd2_journal_update_sb_errno(journal_t *journal)
+{
+	journal_superblock_t *sb = journal->j_superblock;
+
+	read_lock(&journal->j_state_lock);
+	jbd_debug(1, "JBD2: updating superblock error (errno %d)\n",
+		  journal->j_errno);
+	sb->s_errno    = cpu_to_be32(journal->j_errno);
+	read_unlock(&journal->j_state_lock);
+
+	jbd2_write_superblock(journal, WRITE_SYNC);
+}
+
 /*
  * Read the superblock for a given journal, performing initial
  * validation of the format.
  */
-
 static int journal_get_superblock(journal_t *journal)
 {
 	struct buffer_head *bh;
@@ -1398,14 +1550,11 @@ int jbd2_journal_destroy(journal_t *journal)
 
 	if (journal->j_sb_buffer) {
 		if (!is_journal_aborted(journal)) {
-			/* We can now mark the journal as empty. */
-			journal->j_tail = 0;
-			journal->j_tail_sequence =
-				++journal->j_transaction_sequence;
-			jbd2_journal_update_superblock(journal, 1);
-		} else {
+			mutex_lock(&journal->j_checkpoint_mutex);
+			jbd2_mark_journal_empty(journal);
+			mutex_unlock(&journal->j_checkpoint_mutex);
+		} else
 			err = -EIO;
-		}
 		brelse(journal->j_sb_buffer);
 	}
 
@@ -1552,61 +1701,6 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
 EXPORT_SYMBOL(jbd2_journal_clear_features);
 
 /**
- * int jbd2_journal_update_format () - Update on-disk journal structure.
- * @journal: Journal to act on.
- *
- * Given an initialised but unloaded journal struct, poke about in the
- * on-disk structure to update it to the most recent supported version.
- */
-int jbd2_journal_update_format (journal_t *journal)
-{
-	journal_superblock_t *sb;
-	int err;
-
-	err = journal_get_superblock(journal);
-	if (err)
-		return err;
-
-	sb = journal->j_superblock;
-
-	switch (be32_to_cpu(sb->s_header.h_blocktype)) {
-	case JBD2_SUPERBLOCK_V2:
-		return 0;
-	case JBD2_SUPERBLOCK_V1:
-		return journal_convert_superblock_v1(journal, sb);
-	default:
-		break;
-	}
-	return -EINVAL;
-}
-
-static int journal_convert_superblock_v1(journal_t *journal,
-					 journal_superblock_t *sb)
-{
-	int offset, blocksize;
-	struct buffer_head *bh;
-
-	printk(KERN_WARNING
-		"JBD2: Converting superblock from version 1 to 2.\n");
-
-	/* Pre-initialise new fields to zero */
-	offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb);
-	blocksize = be32_to_cpu(sb->s_blocksize);
-	memset(&sb->s_feature_compat, 0, blocksize-offset);
-
-	sb->s_nr_users = cpu_to_be32(1);
-	sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
-	journal->j_format_version = 2;
-
-	bh = journal->j_sb_buffer;
-	BUFFER_TRACE(bh, "marking dirty");
-	mark_buffer_dirty(bh);
-	sync_dirty_buffer(bh);
-	return 0;
-}
-
-
-/**
  * int jbd2_journal_flush () - Flush journal
  * @journal: Journal to act on.
  *
@@ -1619,7 +1713,6 @@ int jbd2_journal_flush(journal_t *journal)
 {
 	int err = 0;
 	transaction_t *transaction = NULL;
-	unsigned long old_tail;
 
 	write_lock(&journal->j_state_lock);
 
@@ -1654,6 +1747,7 @@ int jbd2_journal_flush(journal_t *journal)
 	if (is_journal_aborted(journal))
 		return -EIO;
 
+	mutex_lock(&journal->j_checkpoint_mutex);
 	jbd2_cleanup_journal_tail(journal);
 
 	/* Finally, mark the journal as really needing no recovery.
@@ -1661,14 +1755,9 @@ int jbd2_journal_flush(journal_t *journal)
 	 * the magic code for a fully-recovered superblock.  Any future
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
+	jbd2_mark_journal_empty(journal);
+	mutex_unlock(&journal->j_checkpoint_mutex);
 	write_lock(&journal->j_state_lock);
-	old_tail = journal->j_tail;
-	journal->j_tail = 0;
-	write_unlock(&journal->j_state_lock);
-	jbd2_journal_update_superblock(journal, 1);
-	write_lock(&journal->j_state_lock);
-	journal->j_tail = old_tail;
-
 	J_ASSERT(!journal->j_running_transaction);
 	J_ASSERT(!journal->j_committing_transaction);
 	J_ASSERT(!journal->j_checkpoint_transactions);
@@ -1708,8 +1797,12 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 		write ? "Clearing" : "Ignoring");
 
 	err = jbd2_journal_skip_recovery(journal);
-	if (write)
-		jbd2_journal_update_superblock(journal, 1);
+	if (write) {
+		/* Lock to make assertions happy... */
+		mutex_lock(&journal->j_checkpoint_mutex);
+		jbd2_mark_journal_empty(journal);
+		mutex_unlock(&journal->j_checkpoint_mutex);
+	}
 
  no_recovery:
 	return err;
@@ -1759,7 +1852,7 @@ static void __journal_abort_soft (journal_t *journal, int errno)
 	__jbd2_journal_abort_hard(journal);
 
 	if (errno)
-		jbd2_journal_update_superblock(journal, 1);
+		jbd2_journal_update_sb_errno(journal);
 }
 
 /**
@@ -2017,7 +2110,7 @@ static struct kmem_cache *jbd2_journal_head_cache;
 static atomic_t nr_journal_heads = ATOMIC_INIT(0);
 #endif
 
-static int journal_init_jbd2_journal_head_cache(void)
+static int jbd2_journal_init_journal_head_cache(void)
 {
 	int retval;
 
@@ -2035,7 +2128,7 @@ static int journal_init_jbd2_journal_head_cache(void)
 	return retval;
 }
 
-static void jbd2_journal_destroy_jbd2_journal_head_cache(void)
+static void jbd2_journal_destroy_journal_head_cache(void)
 {
 	if (jbd2_journal_head_cache) {
 		kmem_cache_destroy(jbd2_journal_head_cache);
@@ -2323,7 +2416,7 @@ static void __exit jbd2_remove_jbd_stats_proc_entry(void)
 
 struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache;
 
-static int __init journal_init_handle_cache(void)
+static int __init jbd2_journal_init_handle_cache(void)
 {
 	jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY);
 	if (jbd2_handle_cache == NULL) {
@@ -2358,17 +2451,20 @@ static int __init journal_init_caches(void)
 
 	ret = jbd2_journal_init_revoke_caches();
 	if (ret == 0)
-		ret = journal_init_jbd2_journal_head_cache();
+		ret = jbd2_journal_init_journal_head_cache();
+	if (ret == 0)
+		ret = jbd2_journal_init_handle_cache();
 	if (ret == 0)
-		ret = journal_init_handle_cache();
+		ret = jbd2_journal_init_transaction_cache();
 	return ret;
 }
 
 static void jbd2_journal_destroy_caches(void)
 {
 	jbd2_journal_destroy_revoke_caches();
-	jbd2_journal_destroy_jbd2_journal_head_cache();
+	jbd2_journal_destroy_journal_head_cache();
 	jbd2_journal_destroy_handle_cache();
+	jbd2_journal_destroy_transaction_cache();
 	jbd2_journal_destroy_slabs();
 }
 
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index da6d7baf1390..c1a03354a22f 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -21,6 +21,7 @@
 #include <linux/jbd2.h>
 #include <linux/errno.h>
 #include <linux/crc32.h>
+#include <linux/blkdev.h>
 #endif
 
 /*
@@ -265,7 +266,9 @@ int jbd2_journal_recover(journal_t *journal)
 	err2 = sync_blockdev(journal->j_fs_dev);
 	if (!err)
 		err = err2;
-
+	/* Make sure all replayed data is on permanent storage */
+	if (journal->j_flags & JBD2_BARRIER)
+		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
 	return err;
 }
 
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 30b2867d6cc9..6973705d6a3d 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -208,17 +208,13 @@ int __init jbd2_journal_init_revoke_caches(void)
 	J_ASSERT(!jbd2_revoke_record_cache);
 	J_ASSERT(!jbd2_revoke_table_cache);
 
-	jbd2_revoke_record_cache = kmem_cache_create("jbd2_revoke_record",
-					   sizeof(struct jbd2_revoke_record_s),
-					   0,
-					   SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
-					   NULL);
+	jbd2_revoke_record_cache = KMEM_CACHE(jbd2_revoke_record_s,
+					SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY);
 	if (!jbd2_revoke_record_cache)
 		goto record_cache_failure;
 
-	jbd2_revoke_table_cache = kmem_cache_create("jbd2_revoke_table",
-					   sizeof(struct jbd2_revoke_table_s),
-					   0, SLAB_TEMPORARY, NULL);
+	jbd2_revoke_table_cache = KMEM_CACHE(jbd2_revoke_table_s,
+					     SLAB_TEMPORARY);
 	if (!jbd2_revoke_table_cache)
 		goto table_cache_failure;
 	return 0;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e5aba56e1fd5..ddcd3549c6c2 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -33,6 +33,35 @@
 static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
 static void __jbd2_journal_unfile_buffer(struct journal_head *jh);
 
+static struct kmem_cache *transaction_cache;
+int __init jbd2_journal_init_transaction_cache(void)
+{
+	J_ASSERT(!transaction_cache);
+	transaction_cache = kmem_cache_create("jbd2_transaction_s",
+					sizeof(transaction_t),
+					0,
+					SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
+					NULL);
+	if (transaction_cache)
+		return 0;
+	return -ENOMEM;
+}
+
+void jbd2_journal_destroy_transaction_cache(void)
+{
+	if (transaction_cache) {
+		kmem_cache_destroy(transaction_cache);
+		transaction_cache = NULL;
+	}
+}
+
+void jbd2_journal_free_transaction(transaction_t *transaction)
+{
+	if (unlikely(ZERO_OR_NULL_PTR(transaction)))
+		return;
+	kmem_cache_free(transaction_cache, transaction);
+}
+
 /*
  * jbd2_get_transaction: obtain a new transaction_t object.
  *
@@ -133,7 +162,8 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
 
 alloc_transaction:
 	if (!journal->j_running_transaction) {
-		new_transaction = kzalloc(sizeof(*new_transaction), gfp_mask);
+		new_transaction = kmem_cache_alloc(transaction_cache,
+						   gfp_mask | __GFP_ZERO);
 		if (!new_transaction) {
 			/*
 			 * If __GFP_FS is not present, then we may be
@@ -162,7 +192,7 @@ repeat:
 	if (is_journal_aborted(journal) ||
 	    (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) {
 		read_unlock(&journal->j_state_lock);
-		kfree(new_transaction);
+		jbd2_journal_free_transaction(new_transaction);
 		return -EROFS;
 	}
 
@@ -284,7 +314,7 @@ repeat:
 	read_unlock(&journal->j_state_lock);
 
 	lock_map_acquire(&handle->h_lockdep_map);
-	kfree(new_transaction);
+	jbd2_journal_free_transaction(new_transaction);
 	return 0;
 }
 
@@ -1549,9 +1579,9 @@ __blist_del_buffer(struct journal_head **list, struct journal_head *jh)
  * of these pointers, it could go bad.  Generally the caller needs to re-read
  * the pointer from the transaction_t.
  *
- * Called under j_list_lock.  The journal may not be locked.
+ * Called under j_list_lock.
  */
-void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
+static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 {
 	struct journal_head **list = NULL;
 	transaction_t *transaction;
@@ -1646,10 +1676,8 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
 	spin_lock(&journal->j_list_lock);
 	if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
 		/* written-back checkpointed metadata buffer */
-		if (jh->b_jlist == BJ_None) {
-			JBUFFER_TRACE(jh, "remove from checkpoint list");
-			__jbd2_journal_remove_checkpoint(jh);
-		}
+		JBUFFER_TRACE(jh, "remove from checkpoint list");
+		__jbd2_journal_remove_checkpoint(jh);
 	}
 	spin_unlock(&journal->j_list_lock);
 out:
@@ -1949,6 +1977,8 @@ zap_buffer_unlocked:
 	clear_buffer_mapped(bh);
 	clear_buffer_req(bh);
 	clear_buffer_new(bh);
+	clear_buffer_delay(bh);
+	clear_buffer_unwritten(bh);
 	bh->b_bdev = NULL;
 	return may_free;
 }
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index 926d02068a14..922f146e4235 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c
index 404111b016c9..2b60ce1996aa 100644
--- a/fs/jffs2/background.c
+++ b/fs/jffs2/background.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/jffs2.h>
 #include <linux/mtd/mtd.h>
@@ -42,12 +44,13 @@ int jffs2_start_garbage_collect_thread(struct jffs2_sb_info *c)
 
 	tsk = kthread_run(jffs2_garbage_collect_thread, c, "jffs2_gcd_mtd%d", c->mtd->index);
 	if (IS_ERR(tsk)) {
-		printk(KERN_WARNING "fork failed for JFFS2 garbage collect thread: %ld\n", -PTR_ERR(tsk));
+		pr_warn("fork failed for JFFS2 garbage collect thread: %ld\n",
+			-PTR_ERR(tsk));
 		complete(&c->gc_thread_exit);
 		ret = PTR_ERR(tsk);
 	} else {
 		/* Wait for it... */
-		D1(printk(KERN_DEBUG "JFFS2: Garbage collect thread is pid %d\n", tsk->pid));
+		jffs2_dbg(1, "Garbage collect thread is pid %d\n", tsk->pid);
 		wait_for_completion(&c->gc_thread_start);
 		ret = tsk->pid;
 	}
@@ -60,7 +63,7 @@ void jffs2_stop_garbage_collect_thread(struct jffs2_sb_info *c)
 	int wait = 0;
 	spin_lock(&c->erase_completion_lock);
 	if (c->gc_task) {
-		D1(printk(KERN_DEBUG "jffs2: Killing GC task %d\n", c->gc_task->pid));
+		jffs2_dbg(1, "Killing GC task %d\n", c->gc_task->pid);
 		send_sig(SIGKILL, c->gc_task, 1);
 		wait = 1;
 	}
@@ -90,7 +93,7 @@ static int jffs2_garbage_collect_thread(void *_c)
 		if (!jffs2_thread_should_wake(c)) {
 			set_current_state (TASK_INTERRUPTIBLE);
 			spin_unlock(&c->erase_completion_lock);
-			D1(printk(KERN_DEBUG "jffs2_garbage_collect_thread sleeping...\n"));
+			jffs2_dbg(1, "%s(): sleeping...\n", __func__);
 			schedule();
 		} else
 			spin_unlock(&c->erase_completion_lock);
@@ -109,7 +112,7 @@ static int jffs2_garbage_collect_thread(void *_c)
 		schedule_timeout_interruptible(msecs_to_jiffies(50));
 
 		if (kthread_should_stop()) {
-			D1(printk(KERN_DEBUG "jffs2_garbage_collect_thread():  kthread_stop() called.\n"));
+			jffs2_dbg(1, "%s(): kthread_stop() called\n", __func__);
 			goto die;
 		}
 
@@ -126,28 +129,32 @@ static int jffs2_garbage_collect_thread(void *_c)
 
 			switch(signr) {
 			case SIGSTOP:
-				D1(printk(KERN_DEBUG "jffs2_garbage_collect_thread(): SIGSTOP received.\n"));
+				jffs2_dbg(1, "%s(): SIGSTOP received\n",
+					  __func__);
 				set_current_state(TASK_STOPPED);
 				schedule();
 				break;
 
 			case SIGKILL:
-				D1(printk(KERN_DEBUG "jffs2_garbage_collect_thread(): SIGKILL received.\n"));
+				jffs2_dbg(1, "%s(): SIGKILL received\n",
+					  __func__);
 				goto die;
 
 			case SIGHUP:
-				D1(printk(KERN_DEBUG "jffs2_garbage_collect_thread(): SIGHUP received.\n"));
+				jffs2_dbg(1, "%s(): SIGHUP received\n",
+					  __func__);
 				break;
 			default:
-				D1(printk(KERN_DEBUG "jffs2_garbage_collect_thread(): signal %ld received\n", signr));
+				jffs2_dbg(1, "%s(): signal %ld received\n",
+					  __func__, signr);
 			}
 		}
 		/* We don't want SIGHUP to interrupt us. STOP and KILL are OK though. */
 		disallow_signal(SIGHUP);
 
-		D1(printk(KERN_DEBUG "jffs2_garbage_collect_thread(): pass\n"));
+		jffs2_dbg(1, "%s(): pass\n", __func__);
 		if (jffs2_garbage_collect_pass(c) == -ENOSPC) {
-			printk(KERN_NOTICE "No space for garbage collection. Aborting GC thread\n");
+			pr_notice("No space for garbage collection. Aborting GC thread\n");
 			goto die;
 		}
 	}
diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index 3005ec4520ad..a3750f902adc 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -307,8 +309,8 @@ static void jffs2_calc_trigger_levels(struct jffs2_sb_info *c)
 	   trying to GC to make more space. It'll be a fruitless task */
 	c->nospc_dirty_size = c->sector_size + (c->flash_size / 100);
 
-	dbg_fsbuild("JFFS2 trigger levels (size %d KiB, block size %d KiB, %d blocks)\n",
-		  c->flash_size / 1024, c->sector_size / 1024, c->nr_blocks);
+	dbg_fsbuild("trigger levels (size %d KiB, block size %d KiB, %d blocks)\n",
+		    c->flash_size / 1024, c->sector_size / 1024, c->nr_blocks);
 	dbg_fsbuild("Blocks required to allow deletion:    %d (%d KiB)\n",
 		  c->resv_blocks_deletion, c->resv_blocks_deletion*c->sector_size/1024);
 	dbg_fsbuild("Blocks required to allow writes:      %d (%d KiB)\n",
diff --git a/fs/jffs2/compr.c b/fs/jffs2/compr.c
index 96ed3c9ec3fc..4849a4c9a0e2 100644
--- a/fs/jffs2/compr.c
+++ b/fs/jffs2/compr.c
@@ -12,6 +12,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include "compr.h"
 
 static DEFINE_SPINLOCK(jffs2_compressor_list_lock);
@@ -79,7 +81,7 @@ static int jffs2_selected_compress(u8 compr, unsigned char *data_in,
 
 	output_buf = kmalloc(*cdatalen, GFP_KERNEL);
 	if (!output_buf) {
-		printk(KERN_WARNING "JFFS2: No memory for compressor allocation. Compression failed.\n");
+		pr_warn("No memory for compressor allocation. Compression failed.\n");
 		return ret;
 	}
 	orig_slen = *datalen;
@@ -188,7 +190,8 @@ uint16_t jffs2_compress(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 				tmp_buf = kmalloc(orig_slen, GFP_KERNEL);
 				spin_lock(&jffs2_compressor_list_lock);
 				if (!tmp_buf) {
-					printk(KERN_WARNING "JFFS2: No memory for compressor allocation. (%d bytes)\n", orig_slen);
+					pr_warn("No memory for compressor allocation. (%d bytes)\n",
+						orig_slen);
 					continue;
 				}
 				else {
@@ -235,7 +238,7 @@ uint16_t jffs2_compress(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 				cpage_out, datalen, cdatalen);
 		break;
 	default:
-		printk(KERN_ERR "JFFS2: unknown compression mode.\n");
+		pr_err("unknown compression mode\n");
 	}
 
 	if (ret == JFFS2_COMPR_NONE) {
@@ -277,7 +280,8 @@ int jffs2_decompress(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 				ret = this->decompress(cdata_in, data_out, cdatalen, datalen);
 				spin_lock(&jffs2_compressor_list_lock);
 				if (ret) {
-					printk(KERN_WARNING "Decompressor \"%s\" returned %d\n", this->name, ret);
+					pr_warn("Decompressor \"%s\" returned %d\n",
+						this->name, ret);
 				}
 				else {
 					this->stat_decompr_blocks++;
@@ -287,7 +291,7 @@ int jffs2_decompress(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 				return ret;
 			}
 		}
-		printk(KERN_WARNING "JFFS2 compression type 0x%02x not available.\n", comprtype);
+		pr_warn("compression type 0x%02x not available\n", comprtype);
 		spin_unlock(&jffs2_compressor_list_lock);
 		return -EIO;
 	}
@@ -299,7 +303,7 @@ int jffs2_register_compressor(struct jffs2_compressor *comp)
 	struct jffs2_compressor *this;
 
 	if (!comp->name) {
-		printk(KERN_WARNING "NULL compressor name at registering JFFS2 compressor. Failed.\n");
+		pr_warn("NULL compressor name at registering JFFS2 compressor. Failed.\n");
 		return -1;
 	}
 	comp->compr_buf_size=0;
@@ -309,7 +313,7 @@ int jffs2_register_compressor(struct jffs2_compressor *comp)
 	comp->stat_compr_new_size=0;
 	comp->stat_compr_blocks=0;
 	comp->stat_decompr_blocks=0;
-	D1(printk(KERN_DEBUG "Registering JFFS2 compressor \"%s\"\n", comp->name));
+	jffs2_dbg(1, "Registering JFFS2 compressor \"%s\"\n", comp->name);
 
 	spin_lock(&jffs2_compressor_list_lock);
 
@@ -332,15 +336,15 @@ out:
 
 int jffs2_unregister_compressor(struct jffs2_compressor *comp)
 {
-	D2(struct jffs2_compressor *this;)
+	D2(struct jffs2_compressor *this);
 
-	D1(printk(KERN_DEBUG "Unregistering JFFS2 compressor \"%s\"\n", comp->name));
+	jffs2_dbg(1, "Unregistering JFFS2 compressor \"%s\"\n", comp->name);
 
 	spin_lock(&jffs2_compressor_list_lock);
 
 	if (comp->usecount) {
 		spin_unlock(&jffs2_compressor_list_lock);
-		printk(KERN_WARNING "JFFS2: Compressor module is in use. Unregister failed.\n");
+		pr_warn("Compressor module is in use. Unregister failed.\n");
 		return -1;
 	}
 	list_del(&comp->list);
@@ -377,17 +381,17 @@ int __init jffs2_compressors_init(void)
 /* Setting default compression mode */
 #ifdef CONFIG_JFFS2_CMODE_NONE
 	jffs2_compression_mode = JFFS2_COMPR_MODE_NONE;
-	D1(printk(KERN_INFO "JFFS2: default compression mode: none\n");)
+	jffs2_dbg(1, "default compression mode: none\n");
 #else
 #ifdef CONFIG_JFFS2_CMODE_SIZE
 	jffs2_compression_mode = JFFS2_COMPR_MODE_SIZE;
-	D1(printk(KERN_INFO "JFFS2: default compression mode: size\n");)
+	jffs2_dbg(1, "default compression mode: size\n");
 #else
 #ifdef CONFIG_JFFS2_CMODE_FAVOURLZO
 	jffs2_compression_mode = JFFS2_COMPR_MODE_FAVOURLZO;
-	D1(printk(KERN_INFO "JFFS2: default compression mode: favourlzo\n");)
+	jffs2_dbg(1, "default compression mode: favourlzo\n");
 #else
-	D1(printk(KERN_INFO "JFFS2: default compression mode: priority\n");)
+	jffs2_dbg(1, "default compression mode: priority\n");
 #endif
 #endif
 #endif
diff --git a/fs/jffs2/compr_lzo.c b/fs/jffs2/compr_lzo.c
index af186ee674d8..c553bd6506da 100644
--- a/fs/jffs2/compr_lzo.c
+++ b/fs/jffs2/compr_lzo.c
@@ -33,7 +33,6 @@ static int __init alloc_workspace(void)
 	lzo_compress_buf = vmalloc(lzo1x_worst_compress(PAGE_SIZE));
 
 	if (!lzo_mem || !lzo_compress_buf) {
-		printk(KERN_WARNING "Failed to allocate lzo deflate workspace\n");
 		free_workspace();
 		return -ENOMEM;
 	}
diff --git a/fs/jffs2/compr_rubin.c b/fs/jffs2/compr_rubin.c
index 9e7cec808c4c..92e0644bf867 100644
--- a/fs/jffs2/compr_rubin.c
+++ b/fs/jffs2/compr_rubin.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/jffs2.h>
diff --git a/fs/jffs2/compr_zlib.c b/fs/jffs2/compr_zlib.c
index 5a001020c542..0b9a1e44e833 100644
--- a/fs/jffs2/compr_zlib.c
+++ b/fs/jffs2/compr_zlib.c
@@ -14,6 +14,8 @@
 #error "The userspace support got too messy and was removed. Update your mkfs.jffs2"
 #endif
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/zlib.h>
 #include <linux/zutil.h>
@@ -42,18 +44,18 @@ static int __init alloc_workspaces(void)
 {
 	def_strm.workspace = vmalloc(zlib_deflate_workspacesize(MAX_WBITS,
 							MAX_MEM_LEVEL));
-	if (!def_strm.workspace) {
-		printk(KERN_WARNING "Failed to allocate %d bytes for deflate workspace\n", zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL));
+	if (!def_strm.workspace)
 		return -ENOMEM;
-	}
-	D1(printk(KERN_DEBUG "Allocated %d bytes for deflate workspace\n", zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL)));
+
+	jffs2_dbg(1, "Allocated %d bytes for deflate workspace\n",
+		  zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL));
 	inf_strm.workspace = vmalloc(zlib_inflate_workspacesize());
 	if (!inf_strm.workspace) {
-		printk(KERN_WARNING "Failed to allocate %d bytes for inflate workspace\n", zlib_inflate_workspacesize());
 		vfree(def_strm.workspace);
 		return -ENOMEM;
 	}
-	D1(printk(KERN_DEBUG "Allocated %d bytes for inflate workspace\n", zlib_inflate_workspacesize()));
+	jffs2_dbg(1, "Allocated %d bytes for inflate workspace\n",
+		  zlib_inflate_workspacesize());
 	return 0;
 }
 
@@ -79,7 +81,7 @@ static int jffs2_zlib_compress(unsigned char *data_in,
 	mutex_lock(&deflate_mutex);
 
 	if (Z_OK != zlib_deflateInit(&def_strm, 3)) {
-		printk(KERN_WARNING "deflateInit failed\n");
+		pr_warn("deflateInit failed\n");
 		mutex_unlock(&deflate_mutex);
 		return -1;
 	}
@@ -93,13 +95,14 @@ static int jffs2_zlib_compress(unsigned char *data_in,
 	while (def_strm.total_out < *dstlen - STREAM_END_SPACE && def_strm.total_in < *sourcelen) {
 		def_strm.avail_out = *dstlen - (def_strm.total_out + STREAM_END_SPACE);
 		def_strm.avail_in = min((unsigned)(*sourcelen-def_strm.total_in), def_strm.avail_out);
-		D1(printk(KERN_DEBUG "calling deflate with avail_in %d, avail_out %d\n",
-			  def_strm.avail_in, def_strm.avail_out));
+		jffs2_dbg(1, "calling deflate with avail_in %d, avail_out %d\n",
+			  def_strm.avail_in, def_strm.avail_out);
 		ret = zlib_deflate(&def_strm, Z_PARTIAL_FLUSH);
-		D1(printk(KERN_DEBUG "deflate returned with avail_in %d, avail_out %d, total_in %ld, total_out %ld\n",
-			  def_strm.avail_in, def_strm.avail_out, def_strm.total_in, def_strm.total_out));
+		jffs2_dbg(1, "deflate returned with avail_in %d, avail_out %d, total_in %ld, total_out %ld\n",
+			  def_strm.avail_in, def_strm.avail_out,
+			  def_strm.total_in, def_strm.total_out);
 		if (ret != Z_OK) {
-			D1(printk(KERN_DEBUG "deflate in loop returned %d\n", ret));
+			jffs2_dbg(1, "deflate in loop returned %d\n", ret);
 			zlib_deflateEnd(&def_strm);
 			mutex_unlock(&deflate_mutex);
 			return -1;
@@ -111,20 +114,20 @@ static int jffs2_zlib_compress(unsigned char *data_in,
 	zlib_deflateEnd(&def_strm);
 
 	if (ret != Z_STREAM_END) {
-		D1(printk(KERN_DEBUG "final deflate returned %d\n", ret));
+		jffs2_dbg(1, "final deflate returned %d\n", ret);
 		ret = -1;
 		goto out;
 	}
 
 	if (def_strm.total_out >= def_strm.total_in) {
-		D1(printk(KERN_DEBUG "zlib compressed %ld bytes into %ld; failing\n",
-			  def_strm.total_in, def_strm.total_out));
+		jffs2_dbg(1, "zlib compressed %ld bytes into %ld; failing\n",
+			  def_strm.total_in, def_strm.total_out);
 		ret = -1;
 		goto out;
 	}
 
-	D1(printk(KERN_DEBUG "zlib compressed %ld bytes into %ld\n",
-		  def_strm.total_in, def_strm.total_out));
+	jffs2_dbg(1, "zlib compressed %ld bytes into %ld\n",
+		  def_strm.total_in, def_strm.total_out);
 
 	*dstlen = def_strm.total_out;
 	*sourcelen = def_strm.total_in;
@@ -157,18 +160,18 @@ static int jffs2_zlib_decompress(unsigned char *data_in,
 	    ((data_in[0] & 0x0f) == Z_DEFLATED) &&
 	    !(((data_in[0]<<8) + data_in[1]) % 31)) {
 
-		D2(printk(KERN_DEBUG "inflate skipping adler32\n"));
+		jffs2_dbg(2, "inflate skipping adler32\n");
 		wbits = -((data_in[0] >> 4) + 8);
 		inf_strm.next_in += 2;
 		inf_strm.avail_in -= 2;
 	} else {
 		/* Let this remain D1 for now -- it should never happen */
-		D1(printk(KERN_DEBUG "inflate not skipping adler32\n"));
+		jffs2_dbg(1, "inflate not skipping adler32\n");
 	}
 
 
 	if (Z_OK != zlib_inflateInit2(&inf_strm, wbits)) {
-		printk(KERN_WARNING "inflateInit failed\n");
+		pr_warn("inflateInit failed\n");
 		mutex_unlock(&inflate_mutex);
 		return 1;
 	}
@@ -176,7 +179,7 @@ static int jffs2_zlib_decompress(unsigned char *data_in,
 	while((ret = zlib_inflate(&inf_strm, Z_FINISH)) == Z_OK)
 		;
 	if (ret != Z_STREAM_END) {
-		printk(KERN_NOTICE "inflate returned %d\n", ret);
+		pr_notice("inflate returned %d\n", ret);
 	}
 	zlib_inflateEnd(&inf_strm);
 	mutex_unlock(&inflate_mutex);
diff --git a/fs/jffs2/debug.c b/fs/jffs2/debug.c
index e0b76c87a91a..1090eb64b90d 100644
--- a/fs/jffs2/debug.c
+++ b/fs/jffs2/debug.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/pagemap.h>
@@ -261,12 +263,15 @@ void __jffs2_dbg_superblock_counts(struct jffs2_sb_info *c)
 		bad += c->sector_size;
 	}
 
-#define check(sz) \
-	if (sz != c->sz##_size) {			\
-		printk(KERN_WARNING #sz "_size mismatch counted 0x%x, c->" #sz "_size 0x%x\n", \
-		       sz, c->sz##_size);		\
-		dump = 1;				\
-	}
+#define check(sz)							\
+do {									\
+	if (sz != c->sz##_size) {					\
+		pr_warn("%s_size mismatch counted 0x%x, c->%s_size 0x%x\n", \
+			#sz, sz, #sz, c->sz##_size);			\
+		dump = 1;						\
+	}								\
+} while (0)
+
 	check(free);
 	check(dirty);
 	check(used);
@@ -274,11 +279,12 @@ void __jffs2_dbg_superblock_counts(struct jffs2_sb_info *c)
 	check(unchecked);
 	check(bad);
 	check(erasing);
+
 #undef check
 
 	if (nr_counted != c->nr_blocks) {
-		printk(KERN_WARNING "%s counted only 0x%x blocks of 0x%x. Where are the others?\n",
-		       __func__, nr_counted, c->nr_blocks);
+		pr_warn("%s counted only 0x%x blocks of 0x%x. Where are the others?\n",
+			__func__, nr_counted, c->nr_blocks);
 		dump = 1;
 	}
 
diff --git a/fs/jffs2/debug.h b/fs/jffs2/debug.h
index c4f8eef5ca68..4fd9be4cbc98 100644
--- a/fs/jffs2/debug.h
+++ b/fs/jffs2/debug.h
@@ -51,6 +51,7 @@
  * superseded by nicer dbg_xxx() macros...
  */
 #if CONFIG_JFFS2_FS_DEBUG > 0
+#define DEBUG
 #define D1(x) x
 #else
 #define D1(x)
@@ -62,50 +63,33 @@
 #define D2(x)
 #endif
 
+#define jffs2_dbg(level, fmt, ...)		\
+do {						\
+	if (CONFIG_JFFS2_FS_DEBUG >= level)	\
+		pr_debug(fmt, ##__VA_ARGS__);	\
+} while (0)
+
 /* The prefixes of JFFS2 messages */
+#define JFFS2_DBG		KERN_DEBUG
 #define JFFS2_DBG_PREFIX	"[JFFS2 DBG]"
-#define JFFS2_ERR_PREFIX	"JFFS2 error:"
-#define JFFS2_WARN_PREFIX	"JFFS2 warning:"
-#define JFFS2_NOTICE_PREFIX	"JFFS2 notice:"
-
-#define JFFS2_ERR	KERN_ERR
-#define JFFS2_WARN	KERN_WARNING
-#define JFFS2_NOT	KERN_NOTICE
-#define JFFS2_DBG	KERN_DEBUG
-
 #define JFFS2_DBG_MSG_PREFIX	JFFS2_DBG JFFS2_DBG_PREFIX
-#define JFFS2_ERR_MSG_PREFIX	JFFS2_ERR JFFS2_ERR_PREFIX
-#define JFFS2_WARN_MSG_PREFIX	JFFS2_WARN JFFS2_WARN_PREFIX
-#define JFFS2_NOTICE_MSG_PREFIX	JFFS2_NOT JFFS2_NOTICE_PREFIX
 
 /* JFFS2 message macros */
-#define JFFS2_ERROR(fmt, ...)						\
-	do {								\
-		printk(JFFS2_ERR_MSG_PREFIX				\
-			" (%d) %s: " fmt, task_pid_nr(current),		\
-			__func__ , ##__VA_ARGS__);			\
-	} while(0)
+#define JFFS2_ERROR(fmt, ...)					\
+	pr_err("error: (%d) %s: " fmt,				\
+	       task_pid_nr(current), __func__, ##__VA_ARGS__)
 
 #define JFFS2_WARNING(fmt, ...)						\
-	do {								\
-		printk(JFFS2_WARN_MSG_PREFIX				\
-			" (%d) %s: " fmt, task_pid_nr(current),		\
-			__func__ , ##__VA_ARGS__);			\
-	} while(0)
+	pr_warn("warning: (%d) %s: " fmt,				\
+		task_pid_nr(current), __func__, ##__VA_ARGS__)
 
 #define JFFS2_NOTICE(fmt, ...)						\
-	do {								\
-		printk(JFFS2_NOTICE_MSG_PREFIX				\
-			" (%d) %s: " fmt, task_pid_nr(current),		\
-			__func__ , ##__VA_ARGS__);			\
-	} while(0)
+	pr_notice("notice: (%d) %s: " fmt,				\
+		  task_pid_nr(current), __func__, ##__VA_ARGS__)
 
 #define JFFS2_DEBUG(fmt, ...)						\
-	do {								\
-		printk(JFFS2_DBG_MSG_PREFIX				\
-			" (%d) %s: " fmt, task_pid_nr(current),		\
-			__func__ , ##__VA_ARGS__);			\
-	} while(0)
+	printk(KERN_DEBUG "[JFFS2 DBG] (%d) %s: " fmt,			\
+	       task_pid_nr(current), __func__, ##__VA_ARGS__)
 
 /*
  * We split our debugging messages on several parts, depending on the JFFS2
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 973ac5822bd7..b56018896d5e 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
@@ -79,7 +81,7 @@ static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target,
 	uint32_t ino = 0;
 	struct inode *inode = NULL;
 
-	D1(printk(KERN_DEBUG "jffs2_lookup()\n"));
+	jffs2_dbg(1, "jffs2_lookup()\n");
 
 	if (target->d_name.len > JFFS2_MAX_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -103,7 +105,7 @@ static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target,
 	if (ino) {
 		inode = jffs2_iget(dir_i->i_sb, ino);
 		if (IS_ERR(inode))
-			printk(KERN_WARNING "iget() failed for ino #%u\n", ino);
+			pr_warn("iget() failed for ino #%u\n", ino);
 	}
 
 	return d_splice_alias(inode, target);
@@ -119,21 +121,22 @@ static int jffs2_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	struct jffs2_full_dirent *fd;
 	unsigned long offset, curofs;
 
-	D1(printk(KERN_DEBUG "jffs2_readdir() for dir_i #%lu\n", filp->f_path.dentry->d_inode->i_ino));
+	jffs2_dbg(1, "jffs2_readdir() for dir_i #%lu\n",
+		  filp->f_path.dentry->d_inode->i_ino);
 
 	f = JFFS2_INODE_INFO(inode);
 
 	offset = filp->f_pos;
 
 	if (offset == 0) {
-		D1(printk(KERN_DEBUG "Dirent 0: \".\", ino #%lu\n", inode->i_ino));
+		jffs2_dbg(1, "Dirent 0: \".\", ino #%lu\n", inode->i_ino);
 		if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
 			goto out;
 		offset++;
 	}
 	if (offset == 1) {
 		unsigned long pino = parent_ino(filp->f_path.dentry);
-		D1(printk(KERN_DEBUG "Dirent 1: \"..\", ino #%lu\n", pino));
+		jffs2_dbg(1, "Dirent 1: \"..\", ino #%lu\n", pino);
 		if (filldir(dirent, "..", 2, 1, pino, DT_DIR) < 0)
 			goto out;
 		offset++;
@@ -146,16 +149,18 @@ static int jffs2_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		curofs++;
 		/* First loop: curofs = 2; offset = 2 */
 		if (curofs < offset) {
-			D2(printk(KERN_DEBUG "Skipping dirent: \"%s\", ino #%u, type %d, because curofs %ld < offset %ld\n",
-				  fd->name, fd->ino, fd->type, curofs, offset));
+			jffs2_dbg(2, "Skipping dirent: \"%s\", ino #%u, type %d, because curofs %ld < offset %ld\n",
+				  fd->name, fd->ino, fd->type, curofs, offset);
 			continue;
 		}
 		if (!fd->ino) {
-			D2(printk(KERN_DEBUG "Skipping deletion dirent \"%s\"\n", fd->name));
+			jffs2_dbg(2, "Skipping deletion dirent \"%s\"\n",
+				  fd->name);
 			offset++;
 			continue;
 		}
-		D2(printk(KERN_DEBUG "Dirent %ld: \"%s\", ino #%u, type %d\n", offset, fd->name, fd->ino, fd->type));
+		jffs2_dbg(2, "Dirent %ld: \"%s\", ino #%u, type %d\n",
+			  offset, fd->name, fd->ino, fd->type);
 		if (filldir(dirent, fd->name, strlen(fd->name), offset, fd->ino, fd->type) < 0)
 			break;
 		offset++;
@@ -184,12 +189,12 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
 
 	c = JFFS2_SB_INFO(dir_i->i_sb);
 
-	D1(printk(KERN_DEBUG "jffs2_create()\n"));
+	jffs2_dbg(1, "%s()\n", __func__);
 
 	inode = jffs2_new_inode(dir_i, mode, ri);
 
 	if (IS_ERR(inode)) {
-		D1(printk(KERN_DEBUG "jffs2_new_inode() failed\n"));
+		jffs2_dbg(1, "jffs2_new_inode() failed\n");
 		jffs2_free_raw_inode(ri);
 		return PTR_ERR(inode);
 	}
@@ -217,9 +222,9 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
 
 	jffs2_free_raw_inode(ri);
 
-	D1(printk(KERN_DEBUG "jffs2_create: Created ino #%lu with mode %o, nlink %d(%d). nrpages %ld\n",
-		  inode->i_ino, inode->i_mode, inode->i_nlink,
-		  f->inocache->pino_nlink, inode->i_mapping->nrpages));
+	jffs2_dbg(1, "%s(): Created ino #%lu with mode %o, nlink %d(%d). nrpages %ld\n",
+		  __func__, inode->i_ino, inode->i_mode, inode->i_nlink,
+		  f->inocache->pino_nlink, inode->i_mapping->nrpages);
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
@@ -362,14 +367,15 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 	/* We use f->target field to store the target path. */
 	f->target = kmemdup(target, targetlen + 1, GFP_KERNEL);
 	if (!f->target) {
-		printk(KERN_WARNING "Can't allocate %d bytes of memory\n", targetlen + 1);
+		pr_warn("Can't allocate %d bytes of memory\n", targetlen + 1);
 		mutex_unlock(&f->sem);
 		jffs2_complete_reservation(c);
 		ret = -ENOMEM;
 		goto fail;
 	}
 
-	D1(printk(KERN_DEBUG "jffs2_symlink: symlink's target '%s' cached\n", (char *)f->target));
+	jffs2_dbg(1, "%s(): symlink's target '%s' cached\n",
+		  __func__, (char *)f->target);
 
 	/* No data here. Only a metadata node, which will be
 	   obsoleted by the first data write
@@ -856,7 +862,8 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 			f->inocache->pino_nlink++;
 		mutex_unlock(&f->sem);
 
-		printk(KERN_NOTICE "jffs2_rename(): Link succeeded, unlink failed (err %d). You now have a hard link\n", ret);
+		pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n",
+			  __func__, ret);
 		/* Might as well let the VFS know */
 		d_instantiate(new_dentry, old_dentry->d_inode);
 		ihold(old_dentry->d_inode);
diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c
index eafb8d37a6fb..4a6cf289be24 100644
--- a/fs/jffs2/erase.c
+++ b/fs/jffs2/erase.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mtd/mtd.h>
@@ -46,11 +48,12 @@ static void jffs2_erase_block(struct jffs2_sb_info *c,
 #else /* Linux */
 	struct erase_info *instr;
 
-	D1(printk(KERN_DEBUG "jffs2_erase_block(): erase block %#08x (range %#08x-%#08x)\n",
-				jeb->offset, jeb->offset, jeb->offset + c->sector_size));
+	jffs2_dbg(1, "%s(): erase block %#08x (range %#08x-%#08x)\n",
+		  __func__,
+		  jeb->offset, jeb->offset, jeb->offset + c->sector_size);
 	instr = kmalloc(sizeof(struct erase_info) + sizeof(struct erase_priv_struct), GFP_KERNEL);
 	if (!instr) {
-		printk(KERN_WARNING "kmalloc for struct erase_info in jffs2_erase_block failed. Refiling block for later\n");
+		pr_warn("kmalloc for struct erase_info in jffs2_erase_block failed. Refiling block for later\n");
 		mutex_lock(&c->erase_free_sem);
 		spin_lock(&c->erase_completion_lock);
 		list_move(&jeb->list, &c->erase_pending_list);
@@ -69,7 +72,6 @@ static void jffs2_erase_block(struct jffs2_sb_info *c,
 	instr->len = c->sector_size;
 	instr->callback = jffs2_erase_callback;
 	instr->priv = (unsigned long)(&instr[1]);
-	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
 
 	((struct erase_priv_struct *)instr->priv)->jeb = jeb;
 	((struct erase_priv_struct *)instr->priv)->c = c;
@@ -84,7 +86,8 @@ static void jffs2_erase_block(struct jffs2_sb_info *c,
 
 	if (ret == -ENOMEM || ret == -EAGAIN) {
 		/* Erase failed immediately. Refile it on the list */
-		D1(printk(KERN_DEBUG "Erase at 0x%08x failed: %d. Refiling on erase_pending_list\n", jeb->offset, ret));
+		jffs2_dbg(1, "Erase at 0x%08x failed: %d. Refiling on erase_pending_list\n",
+			  jeb->offset, ret);
 		mutex_lock(&c->erase_free_sem);
 		spin_lock(&c->erase_completion_lock);
 		list_move(&jeb->list, &c->erase_pending_list);
@@ -97,9 +100,11 @@ static void jffs2_erase_block(struct jffs2_sb_info *c,
 	}
 
 	if (ret == -EROFS)
-		printk(KERN_WARNING "Erase at 0x%08x failed immediately: -EROFS. Is the sector locked?\n", jeb->offset);
+		pr_warn("Erase at 0x%08x failed immediately: -EROFS. Is the sector locked?\n",
+			jeb->offset);
 	else
-		printk(KERN_WARNING "Erase at 0x%08x failed immediately: errno %d\n", jeb->offset, ret);
+		pr_warn("Erase at 0x%08x failed immediately: errno %d\n",
+			jeb->offset, ret);
 
 	jffs2_erase_failed(c, jeb, bad_offset);
 }
@@ -125,13 +130,14 @@ int jffs2_erase_pending_blocks(struct jffs2_sb_info *c, int count)
 
 			work_done++;
 			if (!--count) {
-				D1(printk(KERN_DEBUG "Count reached. jffs2_erase_pending_blocks leaving\n"));
+				jffs2_dbg(1, "Count reached. jffs2_erase_pending_blocks leaving\n");
 				goto done;
 			}
 
 		} else if (!list_empty(&c->erase_pending_list)) {
 			jeb = list_entry(c->erase_pending_list.next, struct jffs2_eraseblock, list);
-			D1(printk(KERN_DEBUG "Starting erase of pending block 0x%08x\n", jeb->offset));
+			jffs2_dbg(1, "Starting erase of pending block 0x%08x\n",
+				  jeb->offset);
 			list_del(&jeb->list);
 			c->erasing_size += c->sector_size;
 			c->wasted_size -= jeb->wasted_size;
@@ -159,13 +165,13 @@ int jffs2_erase_pending_blocks(struct jffs2_sb_info *c, int count)
 	spin_unlock(&c->erase_completion_lock);
 	mutex_unlock(&c->erase_free_sem);
  done:
-	D1(printk(KERN_DEBUG "jffs2_erase_pending_blocks completed\n"));
+	jffs2_dbg(1, "jffs2_erase_pending_blocks completed\n");
 	return work_done;
 }
 
 static void jffs2_erase_succeeded(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb)
 {
-	D1(printk(KERN_DEBUG "Erase completed successfully at 0x%08x\n", jeb->offset));
+	jffs2_dbg(1, "Erase completed successfully at 0x%08x\n", jeb->offset);
 	mutex_lock(&c->erase_free_sem);
 	spin_lock(&c->erase_completion_lock);
 	list_move_tail(&jeb->list, &c->erase_complete_list);
@@ -214,7 +220,7 @@ static void jffs2_erase_callback(struct erase_info *instr)
 	struct erase_priv_struct *priv = (void *)instr->priv;
 
 	if(instr->state != MTD_ERASE_DONE) {
-		printk(KERN_WARNING "Erase at 0x%08llx finished, but state != MTD_ERASE_DONE. State is 0x%x instead.\n",
+		pr_warn("Erase at 0x%08llx finished, but state != MTD_ERASE_DONE. State is 0x%x instead.\n",
 			(unsigned long long)instr->addr, instr->state);
 		jffs2_erase_failed(priv->c, priv->jeb, instr->fail_addr);
 	} else {
@@ -269,8 +275,8 @@ static inline void jffs2_remove_node_refs_from_ino_list(struct jffs2_sb_info *c,
 		return;
 	}
 
-	D1(printk(KERN_DEBUG "Removed nodes in range 0x%08x-0x%08x from ino #%u\n",
-		  jeb->offset, jeb->offset + c->sector_size, ic->ino));
+	jffs2_dbg(1, "Removed nodes in range 0x%08x-0x%08x from ino #%u\n",
+		  jeb->offset, jeb->offset + c->sector_size, ic->ino);
 
 	D2({
 		int i=0;
@@ -281,7 +287,7 @@ static inline void jffs2_remove_node_refs_from_ino_list(struct jffs2_sb_info *c,
 
 		printk(KERN_DEBUG);
 		while(this) {
-			printk(KERN_CONT "0x%08x(%d)->",
+			pr_cont("0x%08x(%d)->",
 			       ref_offset(this), ref_flags(this));
 			if (++i == 5) {
 				printk(KERN_DEBUG);
@@ -289,7 +295,7 @@ static inline void jffs2_remove_node_refs_from_ino_list(struct jffs2_sb_info *c,
 			}
 			this = this->next_in_ino;
 		}
-		printk(KERN_CONT "\n");
+		pr_cont("\n");
 	});
 
 	switch (ic->class) {
@@ -310,7 +316,8 @@ static inline void jffs2_remove_node_refs_from_ino_list(struct jffs2_sb_info *c,
 void jffs2_free_jeb_node_refs(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb)
 {
 	struct jffs2_raw_node_ref *block, *ref;
-	D1(printk(KERN_DEBUG "Freeing all node refs for eraseblock offset 0x%08x\n", jeb->offset));
+	jffs2_dbg(1, "Freeing all node refs for eraseblock offset 0x%08x\n",
+		  jeb->offset);
 
 	block = ref = jeb->first_node;
 
@@ -342,12 +349,13 @@ static int jffs2_block_check_erase(struct jffs2_sb_info *c, struct jffs2_erasebl
 			&ebuf, NULL);
 	if (ret != -EOPNOTSUPP) {
 		if (ret) {
-			D1(printk(KERN_DEBUG "MTD point failed %d\n", ret));
+			jffs2_dbg(1, "MTD point failed %d\n", ret);
 			goto do_flash_read;
 		}
 		if (retlen < c->sector_size) {
 			/* Don't muck about if it won't let us point to the whole erase sector */
-			D1(printk(KERN_DEBUG "MTD point returned len too short: 0x%zx\n", retlen));
+			jffs2_dbg(1, "MTD point returned len too short: 0x%zx\n",
+				  retlen);
 			mtd_unpoint(c->mtd, jeb->offset, retlen);
 			goto do_flash_read;
 		}
@@ -359,8 +367,10 @@ static int jffs2_block_check_erase(struct jffs2_sb_info *c, struct jffs2_erasebl
 		} while(--retlen);
 		mtd_unpoint(c->mtd, jeb->offset, c->sector_size);
 		if (retlen) {
-			printk(KERN_WARNING "Newly-erased block contained word 0x%lx at offset 0x%08tx\n",
-			       *wordebuf, jeb->offset + c->sector_size-retlen*sizeof(*wordebuf));
+			pr_warn("Newly-erased block contained word 0x%lx at offset 0x%08tx\n",
+				*wordebuf,
+				jeb->offset +
+				c->sector_size-retlen * sizeof(*wordebuf));
 			return -EIO;
 		}
 		return 0;
@@ -368,11 +378,12 @@ static int jffs2_block_check_erase(struct jffs2_sb_info *c, struct jffs2_erasebl
  do_flash_read:
 	ebuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!ebuf) {
-		printk(KERN_WARNING "Failed to allocate page buffer for verifying erase at 0x%08x. Refiling\n", jeb->offset);
+		pr_warn("Failed to allocate page buffer for verifying erase at 0x%08x. Refiling\n",
+			jeb->offset);
 		return -EAGAIN;
 	}
 
-	D1(printk(KERN_DEBUG "Verifying erase at 0x%08x\n", jeb->offset));
+	jffs2_dbg(1, "Verifying erase at 0x%08x\n", jeb->offset);
 
 	for (ofs = jeb->offset; ofs < jeb->offset + c->sector_size; ) {
 		uint32_t readlen = min((uint32_t)PAGE_SIZE, jeb->offset + c->sector_size - ofs);
@@ -382,12 +393,14 @@ static int jffs2_block_check_erase(struct jffs2_sb_info *c, struct jffs2_erasebl
 
 		ret = mtd_read(c->mtd, ofs, readlen, &retlen, ebuf);
 		if (ret) {
-			printk(KERN_WARNING "Read of newly-erased block at 0x%08x failed: %d. Putting on bad_list\n", ofs, ret);
+			pr_warn("Read of newly-erased block at 0x%08x failed: %d. Putting on bad_list\n",
+				ofs, ret);
 			ret = -EIO;
 			goto fail;
 		}
 		if (retlen != readlen) {
-			printk(KERN_WARNING "Short read from newly-erased block at 0x%08x. Wanted %d, got %zd\n", ofs, readlen, retlen);
+			pr_warn("Short read from newly-erased block at 0x%08x. Wanted %d, got %zd\n",
+				ofs, readlen, retlen);
 			ret = -EIO;
 			goto fail;
 		}
@@ -396,7 +409,8 @@ static int jffs2_block_check_erase(struct jffs2_sb_info *c, struct jffs2_erasebl
 			unsigned long *datum = ebuf + i;
 			if (*datum + 1) {
 				*bad_offset += i;
-				printk(KERN_WARNING "Newly-erased block contained word 0x%lx at offset 0x%08x\n", *datum, *bad_offset);
+				pr_warn("Newly-erased block contained word 0x%lx at offset 0x%08x\n",
+					*datum, *bad_offset);
 				ret = -EIO;
 				goto fail;
 			}
@@ -422,7 +436,7 @@ static void jffs2_mark_erased_block(struct jffs2_sb_info *c, struct jffs2_eraseb
 	}
 
 	/* Write the erase complete marker */
-	D1(printk(KERN_DEBUG "Writing erased marker to block at 0x%08x\n", jeb->offset));
+	jffs2_dbg(1, "Writing erased marker to block at 0x%08x\n", jeb->offset);
 	bad_offset = jeb->offset;
 
 	/* Cleanmarker in oob area or no cleanmarker at all ? */
@@ -451,10 +465,10 @@ static void jffs2_mark_erased_block(struct jffs2_sb_info *c, struct jffs2_eraseb
 
 		if (ret || retlen != sizeof(marker)) {
 			if (ret)
-				printk(KERN_WARNING "Write clean marker to block at 0x%08x failed: %d\n",
+				pr_warn("Write clean marker to block at 0x%08x failed: %d\n",
 				       jeb->offset, ret);
 			else
-				printk(KERN_WARNING "Short write to newly-erased block at 0x%08x: Wanted %zd, got %zd\n",
+				pr_warn("Short write to newly-erased block at 0x%08x: Wanted %zd, got %zd\n",
 				       jeb->offset, sizeof(marker), retlen);
 
 			goto filebad;
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 61e6723535b9..db3889ba8818 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/time.h>
@@ -85,7 +87,8 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
 	unsigned char *pg_buf;
 	int ret;
 
-	D2(printk(KERN_DEBUG "jffs2_do_readpage_nolock(): ino #%lu, page at offset 0x%lx\n", inode->i_ino, pg->index << PAGE_CACHE_SHIFT));
+	jffs2_dbg(2, "%s(): ino #%lu, page at offset 0x%lx\n",
+		  __func__, inode->i_ino, pg->index << PAGE_CACHE_SHIFT);
 
 	BUG_ON(!PageLocked(pg));
 
@@ -105,7 +108,7 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
 	flush_dcache_page(pg);
 	kunmap(pg);
 
-	D2(printk(KERN_DEBUG "readpage finished\n"));
+	jffs2_dbg(2, "readpage finished\n");
 	return ret;
 }
 
@@ -144,7 +147,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		return -ENOMEM;
 	*pagep = pg;
 
-	D1(printk(KERN_DEBUG "jffs2_write_begin()\n"));
+	jffs2_dbg(1, "%s()\n", __func__);
 
 	if (pageofs > inode->i_size) {
 		/* Make new hole frag from old EOF to new page */
@@ -153,8 +156,8 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		struct jffs2_full_dnode *fn;
 		uint32_t alloc_len;
 
-		D1(printk(KERN_DEBUG "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
-			  (unsigned int)inode->i_size, pageofs));
+		jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
+			  (unsigned int)inode->i_size, pageofs);
 
 		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
 					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
@@ -198,7 +201,8 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 			f->metadata = NULL;
 		}
 		if (ret) {
-			D1(printk(KERN_DEBUG "Eep. add_full_dnode_to_inode() failed in write_begin, returned %d\n", ret));
+			jffs2_dbg(1, "Eep. add_full_dnode_to_inode() failed in write_begin, returned %d\n",
+				  ret);
 			jffs2_mark_node_obsolete(c, fn->raw);
 			jffs2_free_full_dnode(fn);
 			jffs2_complete_reservation(c);
@@ -222,7 +226,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		if (ret)
 			goto out_page;
 	}
-	D1(printk(KERN_DEBUG "end write_begin(). pg->flags %lx\n", pg->flags));
+	jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
 	return ret;
 
 out_page:
@@ -248,8 +252,9 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	int ret = 0;
 	uint32_t writtenlen = 0;
 
-	D1(printk(KERN_DEBUG "jffs2_write_end(): ino #%lu, page at 0x%lx, range %d-%d, flags %lx\n",
-		  inode->i_ino, pg->index << PAGE_CACHE_SHIFT, start, end, pg->flags));
+	jffs2_dbg(1, "%s(): ino #%lu, page at 0x%lx, range %d-%d, flags %lx\n",
+		  __func__, inode->i_ino, pg->index << PAGE_CACHE_SHIFT,
+		  start, end, pg->flags);
 
 	/* We need to avoid deadlock with page_cache_read() in
 	   jffs2_garbage_collect_pass(). So the page must be
@@ -268,7 +273,8 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	ri = jffs2_alloc_raw_inode();
 
 	if (!ri) {
-		D1(printk(KERN_DEBUG "jffs2_write_end(): Allocation of raw inode failed\n"));
+		jffs2_dbg(1, "%s(): Allocation of raw inode failed\n",
+			  __func__);
 		unlock_page(pg);
 		page_cache_release(pg);
 		return -ENOMEM;
@@ -315,13 +321,14 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 		/* generic_file_write has written more to the page cache than we've
 		   actually written to the medium. Mark the page !Uptodate so that
 		   it gets reread */
-		D1(printk(KERN_DEBUG "jffs2_write_end(): Not all bytes written. Marking page !uptodate\n"));
+		jffs2_dbg(1, "%s(): Not all bytes written. Marking page !uptodate\n",
+			__func__);
 		SetPageError(pg);
 		ClearPageUptodate(pg);
 	}
 
-	D1(printk(KERN_DEBUG "jffs2_write_end() returning %d\n",
-					writtenlen > 0 ? writtenlen : ret));
+	jffs2_dbg(1, "%s() returning %d\n",
+		  __func__, writtenlen > 0 ? writtenlen : ret);
 	unlock_page(pg);
 	page_cache_release(pg);
 	return writtenlen > 0 ? writtenlen : ret;
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index c0d5c9d770da..bb6f993ebca9 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -39,7 +41,7 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr)
 	int ret;
 	int alloc_type = ALLOC_NORMAL;
 
-	D1(printk(KERN_DEBUG "jffs2_setattr(): ino #%lu\n", inode->i_ino));
+	jffs2_dbg(1, "%s(): ino #%lu\n", __func__, inode->i_ino);
 
 	/* Special cases - we don't want more than one data node
 	   for these types on the medium at any time. So setattr
@@ -50,7 +52,8 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr)
 		/* For these, we don't actually need to read the old node */
 		mdatalen = jffs2_encode_dev(&dev, inode->i_rdev);
 		mdata = (char *)&dev;
-		D1(printk(KERN_DEBUG "jffs2_setattr(): Writing %d bytes of kdev_t\n", mdatalen));
+		jffs2_dbg(1, "%s(): Writing %d bytes of kdev_t\n",
+			  __func__, mdatalen);
 	} else if (S_ISLNK(inode->i_mode)) {
 		mutex_lock(&f->sem);
 		mdatalen = f->metadata->size;
@@ -66,7 +69,8 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr)
 			return ret;
 		}
 		mutex_unlock(&f->sem);
-		D1(printk(KERN_DEBUG "jffs2_setattr(): Writing %d bytes of symlink target\n", mdatalen));
+		jffs2_dbg(1, "%s(): Writing %d bytes of symlink target\n",
+			  __func__, mdatalen);
 	}
 
 	ri = jffs2_alloc_raw_inode();
@@ -233,7 +237,8 @@ void jffs2_evict_inode (struct inode *inode)
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
 
-	D1(printk(KERN_DEBUG "jffs2_evict_inode(): ino #%lu mode %o\n", inode->i_ino, inode->i_mode));
+	jffs2_dbg(1, "%s(): ino #%lu mode %o\n",
+		  __func__, inode->i_ino, inode->i_mode);
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
 	jffs2_do_clear_inode(c, f);
@@ -249,7 +254,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 	dev_t rdev = 0;
 	int ret;
 
-	D1(printk(KERN_DEBUG "jffs2_iget(): ino == %lu\n", ino));
+	jffs2_dbg(1, "%s(): ino == %lu\n", __func__, ino);
 
 	inode = iget_locked(sb, ino);
 	if (!inode)
@@ -317,14 +322,16 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 		/* Read the device numbers from the media */
 		if (f->metadata->size != sizeof(jdev.old_id) &&
 		    f->metadata->size != sizeof(jdev.new_id)) {
-			printk(KERN_NOTICE "Device node has strange size %d\n", f->metadata->size);
+			pr_notice("Device node has strange size %d\n",
+				  f->metadata->size);
 			goto error_io;
 		}
-		D1(printk(KERN_DEBUG "Reading device numbers from flash\n"));
+		jffs2_dbg(1, "Reading device numbers from flash\n");
 		ret = jffs2_read_dnode(c, f, f->metadata, (char *)&jdev, 0, f->metadata->size);
 		if (ret < 0) {
 			/* Eep */
-			printk(KERN_NOTICE "Read device numbers for inode %lu failed\n", (unsigned long)inode->i_ino);
+			pr_notice("Read device numbers for inode %lu failed\n",
+				  (unsigned long)inode->i_ino);
 			goto error;
 		}
 		if (f->metadata->size == sizeof(jdev.old_id))
@@ -339,12 +346,13 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 		break;
 
 	default:
-		printk(KERN_WARNING "jffs2_read_inode(): Bogus imode %o for ino %lu\n", inode->i_mode, (unsigned long)inode->i_ino);
+		pr_warn("%s(): Bogus i_mode %o for ino %lu\n",
+			__func__, inode->i_mode, (unsigned long)inode->i_ino);
 	}
 
 	mutex_unlock(&f->sem);
 
-	D1(printk(KERN_DEBUG "jffs2_read_inode() returning\n"));
+	jffs2_dbg(1, "jffs2_read_inode() returning\n");
 	unlock_new_inode(inode);
 	return inode;
 
@@ -362,11 +370,13 @@ void jffs2_dirty_inode(struct inode *inode, int flags)
 	struct iattr iattr;
 
 	if (!(inode->i_state & I_DIRTY_DATASYNC)) {
-		D2(printk(KERN_DEBUG "jffs2_dirty_inode() not calling setattr() for ino #%lu\n", inode->i_ino));
+		jffs2_dbg(2, "%s(): not calling setattr() for ino #%lu\n",
+			  __func__, inode->i_ino);
 		return;
 	}
 
-	D1(printk(KERN_DEBUG "jffs2_dirty_inode() calling setattr() for ino #%lu\n", inode->i_ino));
+	jffs2_dbg(1, "%s(): calling setattr() for ino #%lu\n",
+		  __func__, inode->i_ino);
 
 	iattr.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_MTIME|ATTR_CTIME;
 	iattr.ia_mode = inode->i_mode;
@@ -414,7 +424,8 @@ struct inode *jffs2_new_inode (struct inode *dir_i, umode_t mode, struct jffs2_r
 	struct jffs2_inode_info *f;
 	int ret;
 
-	D1(printk(KERN_DEBUG "jffs2_new_inode(): dir_i %ld, mode 0x%x\n", dir_i->i_ino, mode));
+	jffs2_dbg(1, "%s(): dir_i %ld, mode 0x%x\n",
+		  __func__, dir_i->i_ino, mode);
 
 	c = JFFS2_SB_INFO(sb);
 
@@ -504,11 +515,11 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent)
 
 #ifndef CONFIG_JFFS2_FS_WRITEBUFFER
 	if (c->mtd->type == MTD_NANDFLASH) {
-		printk(KERN_ERR "jffs2: Cannot operate on NAND flash unless jffs2 NAND support is compiled in.\n");
+		pr_err("Cannot operate on NAND flash unless jffs2 NAND support is compiled in\n");
 		return -EINVAL;
 	}
 	if (c->mtd->type == MTD_DATAFLASH) {
-		printk(KERN_ERR "jffs2: Cannot operate on DataFlash unless jffs2 DataFlash support is compiled in.\n");
+		pr_err("Cannot operate on DataFlash unless jffs2 DataFlash support is compiled in\n");
 		return -EINVAL;
 	}
 #endif
@@ -522,12 +533,13 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	if ((c->sector_size * blocks) != c->flash_size) {
 		c->flash_size = c->sector_size * blocks;
-		printk(KERN_INFO "jffs2: Flash size not aligned to erasesize, reducing to %dKiB\n",
+		pr_info("Flash size not aligned to erasesize, reducing to %dKiB\n",
 			c->flash_size / 1024);
 	}
 
 	if (c->flash_size < 5*c->sector_size) {
-		printk(KERN_ERR "jffs2: Too few erase blocks (%d)\n", c->flash_size / c->sector_size);
+		pr_err("Too few erase blocks (%d)\n",
+		       c->flash_size / c->sector_size);
 		return -EINVAL;
 	}
 
@@ -550,17 +562,17 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent)
 	if ((ret = jffs2_do_mount_fs(c)))
 		goto out_inohash;
 
-	D1(printk(KERN_DEBUG "jffs2_do_fill_super(): Getting root inode\n"));
+	jffs2_dbg(1, "%s(): Getting root inode\n", __func__);
 	root_i = jffs2_iget(sb, 1);
 	if (IS_ERR(root_i)) {
-		D1(printk(KERN_WARNING "get root inode failed\n"));
+		jffs2_dbg(1, "get root inode failed\n");
 		ret = PTR_ERR(root_i);
 		goto out_root;
 	}
 
 	ret = -ENOMEM;
 
-	D1(printk(KERN_DEBUG "jffs2_do_fill_super(): d_alloc_root()\n"));
+	jffs2_dbg(1, "%s(): d_make_root()\n", __func__);
 	sb->s_root = d_make_root(root_i);
 	if (!sb->s_root)
 		goto out_root;
@@ -618,20 +630,21 @@ struct jffs2_inode_info *jffs2_gc_fetch_inode(struct jffs2_sb_info *c,
 		*/
 		inode = ilookup(OFNI_BS_2SFFJ(c), inum);
 		if (!inode) {
-			D1(printk(KERN_DEBUG "ilookup() failed for ino #%u; inode is probably deleted.\n",
-				  inum));
+			jffs2_dbg(1, "ilookup() failed for ino #%u; inode is probably deleted.\n",
+				  inum);
 
 			spin_lock(&c->inocache_lock);
 			ic = jffs2_get_ino_cache(c, inum);
 			if (!ic) {
-				D1(printk(KERN_DEBUG "Inode cache for ino #%u is gone.\n", inum));
+				jffs2_dbg(1, "Inode cache for ino #%u is gone\n",
+					  inum);
 				spin_unlock(&c->inocache_lock);
 				return NULL;
 			}
 			if (ic->state != INO_STATE_CHECKEDABSENT) {
 				/* Wait for progress. Don't just loop */
-				D1(printk(KERN_DEBUG "Waiting for ino #%u in state %d\n",
-					  ic->ino, ic->state));
+				jffs2_dbg(1, "Waiting for ino #%u in state %d\n",
+					  ic->ino, ic->state);
 				sleep_on_spinunlock(&c->inocache_wq, &c->inocache_lock);
 			} else {
 				spin_unlock(&c->inocache_lock);
@@ -649,8 +662,8 @@ struct jffs2_inode_info *jffs2_gc_fetch_inode(struct jffs2_sb_info *c,
 			return ERR_CAST(inode);
 	}
 	if (is_bad_inode(inode)) {
-		printk(KERN_NOTICE "Eep. read_inode() failed for ino #%u. unlinked %d\n",
-		       inum, unlinked);
+		pr_notice("Eep. read_inode() failed for ino #%u. unlinked %d\n",
+			  inum, unlinked);
 		/* NB. This will happen again. We need to do something appropriate here. */
 		iput(inode);
 		return ERR_PTR(-EIO);
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 31dce611337c..ad271c70aa25 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/mtd/mtd.h>
 #include <linux/slab.h>
@@ -51,44 +53,44 @@ static struct jffs2_eraseblock *jffs2_find_gc_block(struct jffs2_sb_info *c)
 	   number of free blocks is low. */
 again:
 	if (!list_empty(&c->bad_used_list) && c->nr_free_blocks > c->resv_blocks_gcbad) {
-		D1(printk(KERN_DEBUG "Picking block from bad_used_list to GC next\n"));
+		jffs2_dbg(1, "Picking block from bad_used_list to GC next\n");
 		nextlist = &c->bad_used_list;
 	} else if (n < 50 && !list_empty(&c->erasable_list)) {
 		/* Note that most of them will have gone directly to be erased.
 		   So don't favour the erasable_list _too_ much. */
-		D1(printk(KERN_DEBUG "Picking block from erasable_list to GC next\n"));
+		jffs2_dbg(1, "Picking block from erasable_list to GC next\n");
 		nextlist = &c->erasable_list;
 	} else if (n < 110 && !list_empty(&c->very_dirty_list)) {
 		/* Most of the time, pick one off the very_dirty list */
-		D1(printk(KERN_DEBUG "Picking block from very_dirty_list to GC next\n"));
+		jffs2_dbg(1, "Picking block from very_dirty_list to GC next\n");
 		nextlist = &c->very_dirty_list;
 	} else if (n < 126 && !list_empty(&c->dirty_list)) {
-		D1(printk(KERN_DEBUG "Picking block from dirty_list to GC next\n"));
+		jffs2_dbg(1, "Picking block from dirty_list to GC next\n");
 		nextlist = &c->dirty_list;
 	} else if (!list_empty(&c->clean_list)) {
-		D1(printk(KERN_DEBUG "Picking block from clean_list to GC next\n"));
+		jffs2_dbg(1, "Picking block from clean_list to GC next\n");
 		nextlist = &c->clean_list;
 	} else if (!list_empty(&c->dirty_list)) {
-		D1(printk(KERN_DEBUG "Picking block from dirty_list to GC next (clean_list was empty)\n"));
+		jffs2_dbg(1, "Picking block from dirty_list to GC next (clean_list was empty)\n");
 
 		nextlist = &c->dirty_list;
 	} else if (!list_empty(&c->very_dirty_list)) {
-		D1(printk(KERN_DEBUG "Picking block from very_dirty_list to GC next (clean_list and dirty_list were empty)\n"));
+		jffs2_dbg(1, "Picking block from very_dirty_list to GC next (clean_list and dirty_list were empty)\n");
 		nextlist = &c->very_dirty_list;
 	} else if (!list_empty(&c->erasable_list)) {
-		D1(printk(KERN_DEBUG "Picking block from erasable_list to GC next (clean_list and {very_,}dirty_list were empty)\n"));
+		jffs2_dbg(1, "Picking block from erasable_list to GC next (clean_list and {very_,}dirty_list were empty)\n");
 
 		nextlist = &c->erasable_list;
 	} else if (!list_empty(&c->erasable_pending_wbuf_list)) {
 		/* There are blocks are wating for the wbuf sync */
-		D1(printk(KERN_DEBUG "Synching wbuf in order to reuse erasable_pending_wbuf_list blocks\n"));
+		jffs2_dbg(1, "Synching wbuf in order to reuse erasable_pending_wbuf_list blocks\n");
 		spin_unlock(&c->erase_completion_lock);
 		jffs2_flush_wbuf_pad(c);
 		spin_lock(&c->erase_completion_lock);
 		goto again;
 	} else {
 		/* Eep. All were empty */
-		D1(printk(KERN_NOTICE "jffs2: No clean, dirty _or_ erasable blocks to GC from! Where are they all?\n"));
+		jffs2_dbg(1, "No clean, dirty _or_ erasable blocks to GC from! Where are they all?\n");
 		return NULL;
 	}
 
@@ -97,13 +99,15 @@ again:
 	c->gcblock = ret;
 	ret->gc_node = ret->first_node;
 	if (!ret->gc_node) {
-		printk(KERN_WARNING "Eep. ret->gc_node for block at 0x%08x is NULL\n", ret->offset);
+		pr_warn("Eep. ret->gc_node for block at 0x%08x is NULL\n",
+			ret->offset);
 		BUG();
 	}
 
 	/* Have we accidentally picked a clean block with wasted space ? */
 	if (ret->wasted_size) {
-		D1(printk(KERN_DEBUG "Converting wasted_size %08x to dirty_size\n", ret->wasted_size));
+		jffs2_dbg(1, "Converting wasted_size %08x to dirty_size\n",
+			  ret->wasted_size);
 		ret->dirty_size += ret->wasted_size;
 		c->wasted_size -= ret->wasted_size;
 		c->dirty_size += ret->wasted_size;
@@ -140,8 +144,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 
 		/* checked_ino is protected by the alloc_sem */
 		if (c->checked_ino > c->highest_ino && xattr) {
-			printk(KERN_CRIT "Checked all inodes but still 0x%x bytes of unchecked space?\n",
-			       c->unchecked_size);
+			pr_crit("Checked all inodes but still 0x%x bytes of unchecked space?\n",
+				c->unchecked_size);
 			jffs2_dbg_dump_block_lists_nolock(c);
 			spin_unlock(&c->erase_completion_lock);
 			mutex_unlock(&c->alloc_sem);
@@ -163,8 +167,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 		}
 
 		if (!ic->pino_nlink) {
-			D1(printk(KERN_DEBUG "Skipping check of ino #%d with nlink/pino zero\n",
-				  ic->ino));
+			jffs2_dbg(1, "Skipping check of ino #%d with nlink/pino zero\n",
+				  ic->ino);
 			spin_unlock(&c->inocache_lock);
 			jffs2_xattr_delete_inode(c, ic);
 			continue;
@@ -172,13 +176,15 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 		switch(ic->state) {
 		case INO_STATE_CHECKEDABSENT:
 		case INO_STATE_PRESENT:
-			D1(printk(KERN_DEBUG "Skipping ino #%u already checked\n", ic->ino));
+			jffs2_dbg(1, "Skipping ino #%u already checked\n",
+				  ic->ino);
 			spin_unlock(&c->inocache_lock);
 			continue;
 
 		case INO_STATE_GC:
 		case INO_STATE_CHECKING:
-			printk(KERN_WARNING "Inode #%u is in state %d during CRC check phase!\n", ic->ino, ic->state);
+			pr_warn("Inode #%u is in state %d during CRC check phase!\n",
+				ic->ino, ic->state);
 			spin_unlock(&c->inocache_lock);
 			BUG();
 
@@ -186,7 +192,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 			/* We need to wait for it to finish, lest we move on
 			   and trigger the BUG() above while we haven't yet
 			   finished checking all its nodes */
-			D1(printk(KERN_DEBUG "Waiting for ino #%u to finish reading\n", ic->ino));
+			jffs2_dbg(1, "Waiting for ino #%u to finish reading\n",
+				  ic->ino);
 			/* We need to come back again for the _same_ inode. We've
 			 made no progress in this case, but that should be OK */
 			c->checked_ino--;
@@ -204,11 +211,13 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 		ic->state = INO_STATE_CHECKING;
 		spin_unlock(&c->inocache_lock);
 
-		D1(printk(KERN_DEBUG "jffs2_garbage_collect_pass() triggering inode scan of ino#%u\n", ic->ino));
+		jffs2_dbg(1, "%s(): triggering inode scan of ino#%u\n",
+			  __func__, ic->ino);
 
 		ret = jffs2_do_crccheck_inode(c, ic);
 		if (ret)
-			printk(KERN_WARNING "Returned error for crccheck of ino #%u. Expect badness...\n", ic->ino);
+			pr_warn("Returned error for crccheck of ino #%u. Expect badness...\n",
+				ic->ino);
 
 		jffs2_set_inocache_state(c, ic, INO_STATE_CHECKEDABSENT);
 		mutex_unlock(&c->alloc_sem);
@@ -220,11 +229,11 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 	    !list_empty(&c->erase_pending_list)) {
 		spin_unlock(&c->erase_completion_lock);
 		mutex_unlock(&c->alloc_sem);
-		D1(printk(KERN_DEBUG "jffs2_garbage_collect_pass() erasing pending blocks\n"));
+		jffs2_dbg(1, "%s(): erasing pending blocks\n", __func__);
 		if (jffs2_erase_pending_blocks(c, 1))
 			return 0;
 
-		D1(printk(KERN_DEBUG "No progress from erasing blocks; doing GC anyway\n"));
+		jffs2_dbg(1, "No progress from erasing block; doing GC anyway\n");
 		spin_lock(&c->erase_completion_lock);
 		mutex_lock(&c->alloc_sem);
 	}
@@ -242,13 +251,14 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 			mutex_unlock(&c->alloc_sem);
 			return -EAGAIN;
 		}
-		D1(printk(KERN_NOTICE "jffs2: Couldn't find erase block to garbage collect!\n"));
+		jffs2_dbg(1, "Couldn't find erase block to garbage collect!\n");
 		spin_unlock(&c->erase_completion_lock);
 		mutex_unlock(&c->alloc_sem);
 		return -EIO;
 	}
 
-	D1(printk(KERN_DEBUG "GC from block %08x, used_size %08x, dirty_size %08x, free_size %08x\n", jeb->offset, jeb->used_size, jeb->dirty_size, jeb->free_size));
+	jffs2_dbg(1, "GC from block %08x, used_size %08x, dirty_size %08x, free_size %08x\n",
+		  jeb->offset, jeb->used_size, jeb->dirty_size, jeb->free_size);
 	D1(if (c->nextblock)
 	   printk(KERN_DEBUG "Nextblock at  %08x, used_size %08x, dirty_size %08x, wasted_size %08x, free_size %08x\n", c->nextblock->offset, c->nextblock->used_size, c->nextblock->dirty_size, c->nextblock->wasted_size, c->nextblock->free_size));
 
@@ -261,12 +271,14 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 	gcblock_dirty = jeb->dirty_size;
 
 	while(ref_obsolete(raw)) {
-		D1(printk(KERN_DEBUG "Node at 0x%08x is obsolete... skipping\n", ref_offset(raw)));
+		jffs2_dbg(1, "Node at 0x%08x is obsolete... skipping\n",
+			  ref_offset(raw));
 		raw = ref_next(raw);
 		if (unlikely(!raw)) {
-			printk(KERN_WARNING "eep. End of raw list while still supposedly nodes to GC\n");
-			printk(KERN_WARNING "erase block at 0x%08x. free_size 0x%08x, dirty_size 0x%08x, used_size 0x%08x\n",
-			       jeb->offset, jeb->free_size, jeb->dirty_size, jeb->used_size);
+			pr_warn("eep. End of raw list while still supposedly nodes to GC\n");
+			pr_warn("erase block at 0x%08x. free_size 0x%08x, dirty_size 0x%08x, used_size 0x%08x\n",
+				jeb->offset, jeb->free_size,
+				jeb->dirty_size, jeb->used_size);
 			jeb->gc_node = raw;
 			spin_unlock(&c->erase_completion_lock);
 			mutex_unlock(&c->alloc_sem);
@@ -275,7 +287,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 	}
 	jeb->gc_node = raw;
 
-	D1(printk(KERN_DEBUG "Going to garbage collect node at 0x%08x\n", ref_offset(raw)));
+	jffs2_dbg(1, "Going to garbage collect node at 0x%08x\n",
+		  ref_offset(raw));
 
 	if (!raw->next_in_ino) {
 		/* Inode-less node. Clean marker, snapshot or something like that */
@@ -316,7 +329,9 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 
 	spin_unlock(&c->erase_completion_lock);
 
-	D1(printk(KERN_DEBUG "jffs2_garbage_collect_pass collecting from block @0x%08x. Node @0x%08x(%d), ino #%u\n", jeb->offset, ref_offset(raw), ref_flags(raw), ic->ino));
+	jffs2_dbg(1, "%s(): collecting from block @0x%08x. Node @0x%08x(%d), ino #%u\n",
+		  __func__, jeb->offset, ref_offset(raw), ref_flags(raw),
+		  ic->ino);
 
 	/* Three possibilities:
 	   1. Inode is already in-core. We must iget it and do proper
@@ -336,8 +351,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 		if (ref_flags(raw) == REF_PRISTINE)
 			ic->state = INO_STATE_GC;
 		else {
-			D1(printk(KERN_DEBUG "Ino #%u is absent but node not REF_PRISTINE. Reading.\n",
-				  ic->ino));
+			jffs2_dbg(1, "Ino #%u is absent but node not REF_PRISTINE. Reading.\n",
+				  ic->ino);
 		}
 		break;
 
@@ -353,8 +368,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 		   we're holding the alloc_sem, no other garbage collection
 		   can happen.
 		*/
-		printk(KERN_CRIT "Inode #%u already in state %d in jffs2_garbage_collect_pass()!\n",
-		       ic->ino, ic->state);
+		pr_crit("Inode #%u already in state %d in jffs2_garbage_collect_pass()!\n",
+			ic->ino, ic->state);
 		mutex_unlock(&c->alloc_sem);
 		spin_unlock(&c->inocache_lock);
 		BUG();
@@ -367,8 +382,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 		   drop the alloc_sem before sleeping. */
 
 		mutex_unlock(&c->alloc_sem);
-		D1(printk(KERN_DEBUG "jffs2_garbage_collect_pass() waiting for ino #%u in state %d\n",
-			  ic->ino, ic->state));
+		jffs2_dbg(1, "%s(): waiting for ino #%u in state %d\n",
+			  __func__, ic->ino, ic->state);
 		sleep_on_spinunlock(&c->inocache_wq, &c->inocache_lock);
 		/* And because we dropped the alloc_sem we must start again from the
 		   beginning. Ponder chance of livelock here -- we're returning success
@@ -433,7 +448,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
  test_gcnode:
 	if (jeb->dirty_size == gcblock_dirty && !ref_obsolete(jeb->gc_node)) {
 		/* Eep. This really should never happen. GC is broken */
-		printk(KERN_ERR "Error garbage collecting node at %08x!\n", ref_offset(jeb->gc_node));
+		pr_err("Error garbage collecting node at %08x!\n",
+		       ref_offset(jeb->gc_node));
 		ret = -ENOSPC;
 	}
  release_sem:
@@ -445,7 +461,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 
  eraseit:
 	if (c->gcblock && !c->gcblock->used_size) {
-		D1(printk(KERN_DEBUG "Block at 0x%08x completely obsoleted by GC. Moving to erase_pending_list\n", c->gcblock->offset));
+		jffs2_dbg(1, "Block at 0x%08x completely obsoleted by GC. Moving to erase_pending_list\n",
+			  c->gcblock->offset);
 		/* We're GC'ing an empty block? */
 		list_add_tail(&c->gcblock->list, &c->erase_pending_list);
 		c->gcblock = NULL;
@@ -475,12 +492,12 @@ static int jffs2_garbage_collect_live(struct jffs2_sb_info *c,  struct jffs2_era
 
 	if (c->gcblock != jeb) {
 		spin_unlock(&c->erase_completion_lock);
-		D1(printk(KERN_DEBUG "GC block is no longer gcblock. Restart\n"));
+		jffs2_dbg(1, "GC block is no longer gcblock. Restart\n");
 		goto upnout;
 	}
 	if (ref_obsolete(raw)) {
 		spin_unlock(&c->erase_completion_lock);
-		D1(printk(KERN_DEBUG "node to be GC'd was obsoleted in the meantime.\n"));
+		jffs2_dbg(1, "node to be GC'd was obsoleted in the meantime.\n");
 		/* They'll call again */
 		goto upnout;
 	}
@@ -536,10 +553,10 @@ static int jffs2_garbage_collect_live(struct jffs2_sb_info *c,  struct jffs2_era
 	} else if (fd) {
 		ret = jffs2_garbage_collect_deletion_dirent(c, jeb, f, fd);
 	} else {
-		printk(KERN_WARNING "Raw node at 0x%08x wasn't in node lists for ino #%u\n",
-		       ref_offset(raw), f->inocache->ino);
+		pr_warn("Raw node at 0x%08x wasn't in node lists for ino #%u\n",
+			ref_offset(raw), f->inocache->ino);
 		if (ref_obsolete(raw)) {
-			printk(KERN_WARNING "But it's obsolete so we don't mind too much\n");
+			pr_warn("But it's obsolete so we don't mind too much\n");
 		} else {
 			jffs2_dbg_dump_node(c, ref_offset(raw));
 			BUG();
@@ -562,7 +579,8 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 	uint32_t crc, rawlen;
 	int retried = 0;
 
-	D1(printk(KERN_DEBUG "Going to GC REF_PRISTINE node at 0x%08x\n", ref_offset(raw)));
+	jffs2_dbg(1, "Going to GC REF_PRISTINE node at 0x%08x\n",
+		  ref_offset(raw));
 
 	alloclen = rawlen = ref_totlen(c, c->gcblock, raw);
 
@@ -595,8 +613,8 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 
 	crc = crc32(0, node, sizeof(struct jffs2_unknown_node)-4);
 	if (je32_to_cpu(node->u.hdr_crc) != crc) {
-		printk(KERN_WARNING "Header CRC failed on REF_PRISTINE node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
-		       ref_offset(raw), je32_to_cpu(node->u.hdr_crc), crc);
+		pr_warn("Header CRC failed on REF_PRISTINE node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
+			ref_offset(raw), je32_to_cpu(node->u.hdr_crc), crc);
 		goto bail;
 	}
 
@@ -604,16 +622,18 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 	case JFFS2_NODETYPE_INODE:
 		crc = crc32(0, node, sizeof(node->i)-8);
 		if (je32_to_cpu(node->i.node_crc) != crc) {
-			printk(KERN_WARNING "Node CRC failed on REF_PRISTINE data node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
-			       ref_offset(raw), je32_to_cpu(node->i.node_crc), crc);
+			pr_warn("Node CRC failed on REF_PRISTINE data node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
+				ref_offset(raw), je32_to_cpu(node->i.node_crc),
+				crc);
 			goto bail;
 		}
 
 		if (je32_to_cpu(node->i.dsize)) {
 			crc = crc32(0, node->i.data, je32_to_cpu(node->i.csize));
 			if (je32_to_cpu(node->i.data_crc) != crc) {
-				printk(KERN_WARNING "Data CRC failed on REF_PRISTINE data node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
-				       ref_offset(raw), je32_to_cpu(node->i.data_crc), crc);
+				pr_warn("Data CRC failed on REF_PRISTINE data node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
+					ref_offset(raw),
+					je32_to_cpu(node->i.data_crc), crc);
 				goto bail;
 			}
 		}
@@ -622,21 +642,24 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 	case JFFS2_NODETYPE_DIRENT:
 		crc = crc32(0, node, sizeof(node->d)-8);
 		if (je32_to_cpu(node->d.node_crc) != crc) {
-			printk(KERN_WARNING "Node CRC failed on REF_PRISTINE dirent node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
-			       ref_offset(raw), je32_to_cpu(node->d.node_crc), crc);
+			pr_warn("Node CRC failed on REF_PRISTINE dirent node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
+				ref_offset(raw),
+				je32_to_cpu(node->d.node_crc), crc);
 			goto bail;
 		}
 
 		if (strnlen(node->d.name, node->d.nsize) != node->d.nsize) {
-			printk(KERN_WARNING "Name in dirent node at 0x%08x contains zeroes\n", ref_offset(raw));
+			pr_warn("Name in dirent node at 0x%08x contains zeroes\n",
+				ref_offset(raw));
 			goto bail;
 		}
 
 		if (node->d.nsize) {
 			crc = crc32(0, node->d.name, node->d.nsize);
 			if (je32_to_cpu(node->d.name_crc) != crc) {
-				printk(KERN_WARNING "Name CRC failed on REF_PRISTINE dirent node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
-				       ref_offset(raw), je32_to_cpu(node->d.name_crc), crc);
+				pr_warn("Name CRC failed on REF_PRISTINE dirent node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
+					ref_offset(raw),
+					je32_to_cpu(node->d.name_crc), crc);
 				goto bail;
 			}
 		}
@@ -644,8 +667,8 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 	default:
 		/* If it's inode-less, we don't _know_ what it is. Just copy it intact */
 		if (ic) {
-			printk(KERN_WARNING "Unknown node type for REF_PRISTINE node at 0x%08x: 0x%04x\n",
-			       ref_offset(raw), je16_to_cpu(node->u.nodetype));
+			pr_warn("Unknown node type for REF_PRISTINE node at 0x%08x: 0x%04x\n",
+				ref_offset(raw), je16_to_cpu(node->u.nodetype));
 			goto bail;
 		}
 	}
@@ -657,12 +680,13 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 	ret = jffs2_flash_write(c, phys_ofs, rawlen, &retlen, (char *)node);
 
 	if (ret || (retlen != rawlen)) {
-		printk(KERN_NOTICE "Write of %d bytes at 0x%08x failed. returned %d, retlen %zd\n",
-		       rawlen, phys_ofs, ret, retlen);
+		pr_notice("Write of %d bytes at 0x%08x failed. returned %d, retlen %zd\n",
+			  rawlen, phys_ofs, ret, retlen);
 		if (retlen) {
 			jffs2_add_physical_node_ref(c, phys_ofs | REF_OBSOLETE, rawlen, NULL);
 		} else {
-			printk(KERN_NOTICE "Not marking the space at 0x%08x as dirty because the flash driver returned retlen zero\n", phys_ofs);
+			pr_notice("Not marking the space at 0x%08x as dirty because the flash driver returned retlen zero\n",
+				  phys_ofs);
 		}
 		if (!retried) {
 			/* Try to reallocate space and retry */
@@ -671,7 +695,7 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 
 			retried = 1;
 
-			D1(printk(KERN_DEBUG "Retrying failed write of REF_PRISTINE node.\n"));
+			jffs2_dbg(1, "Retrying failed write of REF_PRISTINE node.\n");
 
 			jffs2_dbg_acct_sanity_check(c,jeb);
 			jffs2_dbg_acct_paranoia_check(c, jeb);
@@ -681,14 +705,16 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 							it is only an upper estimation */
 
 			if (!ret) {
-				D1(printk(KERN_DEBUG "Allocated space at 0x%08x to retry failed write.\n", phys_ofs));
+				jffs2_dbg(1, "Allocated space at 0x%08x to retry failed write.\n",
+					  phys_ofs);
 
 				jffs2_dbg_acct_sanity_check(c,jeb);
 				jffs2_dbg_acct_paranoia_check(c, jeb);
 
 				goto retry;
 			}
-			D1(printk(KERN_DEBUG "Failed to allocate space to retry failed write: %d!\n", ret));
+			jffs2_dbg(1, "Failed to allocate space to retry failed write: %d!\n",
+				  ret);
 		}
 
 		if (!ret)
@@ -698,7 +724,8 @@ static int jffs2_garbage_collect_pristine(struct jffs2_sb_info *c,
 	jffs2_add_physical_node_ref(c, phys_ofs | REF_PRISTINE, rawlen, ic);
 
 	jffs2_mark_node_obsolete(c, raw);
-	D1(printk(KERN_DEBUG "WHEEE! GC REF_PRISTINE node at 0x%08x succeeded\n", ref_offset(raw)));
+	jffs2_dbg(1, "WHEEE! GC REF_PRISTINE node at 0x%08x succeeded\n",
+		  ref_offset(raw));
 
  out_node:
 	kfree(node);
@@ -725,29 +752,32 @@ static int jffs2_garbage_collect_metadata(struct jffs2_sb_info *c, struct jffs2_
 		/* For these, we don't actually need to read the old node */
 		mdatalen = jffs2_encode_dev(&dev, JFFS2_F_I_RDEV(f));
 		mdata = (char *)&dev;
-		D1(printk(KERN_DEBUG "jffs2_garbage_collect_metadata(): Writing %d bytes of kdev_t\n", mdatalen));
+		jffs2_dbg(1, "%s(): Writing %d bytes of kdev_t\n",
+			  __func__, mdatalen);
 	} else if (S_ISLNK(JFFS2_F_I_MODE(f))) {
 		mdatalen = fn->size;
 		mdata = kmalloc(fn->size, GFP_KERNEL);
 		if (!mdata) {
-			printk(KERN_WARNING "kmalloc of mdata failed in jffs2_garbage_collect_metadata()\n");
+			pr_warn("kmalloc of mdata failed in jffs2_garbage_collect_metadata()\n");
 			return -ENOMEM;
 		}
 		ret = jffs2_read_dnode(c, f, fn, mdata, 0, mdatalen);
 		if (ret) {
-			printk(KERN_WARNING "read of old metadata failed in jffs2_garbage_collect_metadata(): %d\n", ret);
+			pr_warn("read of old metadata failed in jffs2_garbage_collect_metadata(): %d\n",
+				ret);
 			kfree(mdata);
 			return ret;
 		}
-		D1(printk(KERN_DEBUG "jffs2_garbage_collect_metadata(): Writing %d bites of symlink target\n", mdatalen));
+		jffs2_dbg(1, "%s(): Writing %d bites of symlink target\n",
+			  __func__, mdatalen);
 
 	}
 
 	ret = jffs2_reserve_space_gc(c, sizeof(ri) + mdatalen, &alloclen,
 				JFFS2_SUMMARY_INODE_SIZE);
 	if (ret) {
-		printk(KERN_WARNING "jffs2_reserve_space_gc of %zd bytes for garbage_collect_metadata failed: %d\n",
-		       sizeof(ri)+ mdatalen, ret);
+		pr_warn("jffs2_reserve_space_gc of %zd bytes for garbage_collect_metadata failed: %d\n",
+			sizeof(ri) + mdatalen, ret);
 		goto out;
 	}
 
@@ -784,7 +814,7 @@ static int jffs2_garbage_collect_metadata(struct jffs2_sb_info *c, struct jffs2_
 	new_fn = jffs2_write_dnode(c, f, &ri, mdata, mdatalen, ALLOC_GC);
 
 	if (IS_ERR(new_fn)) {
-		printk(KERN_WARNING "Error writing new dnode: %ld\n", PTR_ERR(new_fn));
+		pr_warn("Error writing new dnode: %ld\n", PTR_ERR(new_fn));
 		ret = PTR_ERR(new_fn);
 		goto out;
 	}
@@ -827,14 +857,15 @@ static int jffs2_garbage_collect_dirent(struct jffs2_sb_info *c, struct jffs2_er
 	ret = jffs2_reserve_space_gc(c, sizeof(rd)+rd.nsize, &alloclen,
 				JFFS2_SUMMARY_DIRENT_SIZE(rd.nsize));
 	if (ret) {
-		printk(KERN_WARNING "jffs2_reserve_space_gc of %zd bytes for garbage_collect_dirent failed: %d\n",
-		       sizeof(rd)+rd.nsize, ret);
+		pr_warn("jffs2_reserve_space_gc of %zd bytes for garbage_collect_dirent failed: %d\n",
+			sizeof(rd)+rd.nsize, ret);
 		return ret;
 	}
 	new_fd = jffs2_write_dirent(c, f, &rd, fd->name, rd.nsize, ALLOC_GC);
 
 	if (IS_ERR(new_fd)) {
-		printk(KERN_WARNING "jffs2_write_dirent in garbage_collect_dirent failed: %ld\n", PTR_ERR(new_fd));
+		pr_warn("jffs2_write_dirent in garbage_collect_dirent failed: %ld\n",
+			PTR_ERR(new_fd));
 		return PTR_ERR(new_fd);
 	}
 	jffs2_add_fd_to_list(c, new_fd, &f->dents);
@@ -887,19 +918,22 @@ static int jffs2_garbage_collect_deletion_dirent(struct jffs2_sb_info *c, struct
 			if (SECTOR_ADDR(raw->flash_offset) == SECTOR_ADDR(fd->raw->flash_offset))
 				continue;
 
-			D1(printk(KERN_DEBUG "Check potential deletion dirent at %08x\n", ref_offset(raw)));
+			jffs2_dbg(1, "Check potential deletion dirent at %08x\n",
+				  ref_offset(raw));
 
 			/* This is an obsolete node belonging to the same directory, and it's of the right
 			   length. We need to take a closer look...*/
 			ret = jffs2_flash_read(c, ref_offset(raw), rawlen, &retlen, (char *)rd);
 			if (ret) {
-				printk(KERN_WARNING "jffs2_g_c_deletion_dirent(): Read error (%d) reading obsolete node at %08x\n", ret, ref_offset(raw));
+				pr_warn("%s(): Read error (%d) reading obsolete node at %08x\n",
+					__func__, ret, ref_offset(raw));
 				/* If we can't read it, we don't need to continue to obsolete it. Continue */
 				continue;
 			}
 			if (retlen != rawlen) {
-				printk(KERN_WARNING "jffs2_g_c_deletion_dirent(): Short read (%zd not %u) reading header from obsolete node at %08x\n",
-				       retlen, rawlen, ref_offset(raw));
+				pr_warn("%s(): Short read (%zd not %u) reading header from obsolete node at %08x\n",
+					__func__, retlen, rawlen,
+					ref_offset(raw));
 				continue;
 			}
 
@@ -923,8 +957,9 @@ static int jffs2_garbage_collect_deletion_dirent(struct jffs2_sb_info *c, struct
 			   a new deletion dirent to replace it */
 			mutex_unlock(&c->erase_free_sem);
 
-			D1(printk(KERN_DEBUG "Deletion dirent at %08x still obsoletes real dirent \"%s\" at %08x for ino #%u\n",
-				  ref_offset(fd->raw), fd->name, ref_offset(raw), je32_to_cpu(rd->ino)));
+			jffs2_dbg(1, "Deletion dirent at %08x still obsoletes real dirent \"%s\" at %08x for ino #%u\n",
+				  ref_offset(fd->raw), fd->name,
+				  ref_offset(raw), je32_to_cpu(rd->ino));
 			kfree(rd);
 
 			return jffs2_garbage_collect_dirent(c, jeb, f, fd);
@@ -947,7 +982,8 @@ static int jffs2_garbage_collect_deletion_dirent(struct jffs2_sb_info *c, struct
 		fdp = &(*fdp)->next;
 	}
 	if (!found) {
-		printk(KERN_WARNING "Deletion dirent \"%s\" not found in list for ino #%u\n", fd->name, f->inocache->ino);
+		pr_warn("Deletion dirent \"%s\" not found in list for ino #%u\n",
+			fd->name, f->inocache->ino);
 	}
 	jffs2_mark_node_obsolete(c, fd->raw);
 	jffs2_free_full_dirent(fd);
@@ -964,8 +1000,8 @@ static int jffs2_garbage_collect_hole(struct jffs2_sb_info *c, struct jffs2_eras
 	uint32_t alloclen, ilen;
 	int ret;
 
-	D1(printk(KERN_DEBUG "Writing replacement hole node for ino #%u from offset 0x%x to 0x%x\n",
-		  f->inocache->ino, start, end));
+	jffs2_dbg(1, "Writing replacement hole node for ino #%u from offset 0x%x to 0x%x\n",
+		  f->inocache->ino, start, end);
 
 	memset(&ri, 0, sizeof(ri));
 
@@ -976,35 +1012,37 @@ static int jffs2_garbage_collect_hole(struct jffs2_sb_info *c, struct jffs2_eras
 		   write it out again with the _same_ version as before */
 		ret = jffs2_flash_read(c, ref_offset(fn->raw), sizeof(ri), &readlen, (char *)&ri);
 		if (readlen != sizeof(ri) || ret) {
-			printk(KERN_WARNING "Node read failed in jffs2_garbage_collect_hole. Ret %d, retlen %zd. Data will be lost by writing new hole node\n", ret, readlen);
+			pr_warn("Node read failed in jffs2_garbage_collect_hole. Ret %d, retlen %zd. Data will be lost by writing new hole node\n",
+				ret, readlen);
 			goto fill;
 		}
 		if (je16_to_cpu(ri.nodetype) != JFFS2_NODETYPE_INODE) {
-			printk(KERN_WARNING "jffs2_garbage_collect_hole: Node at 0x%08x had node type 0x%04x instead of JFFS2_NODETYPE_INODE(0x%04x)\n",
-			       ref_offset(fn->raw),
-			       je16_to_cpu(ri.nodetype), JFFS2_NODETYPE_INODE);
+			pr_warn("%s(): Node at 0x%08x had node type 0x%04x instead of JFFS2_NODETYPE_INODE(0x%04x)\n",
+				__func__, ref_offset(fn->raw),
+				je16_to_cpu(ri.nodetype), JFFS2_NODETYPE_INODE);
 			return -EIO;
 		}
 		if (je32_to_cpu(ri.totlen) != sizeof(ri)) {
-			printk(KERN_WARNING "jffs2_garbage_collect_hole: Node at 0x%08x had totlen 0x%x instead of expected 0x%zx\n",
-			       ref_offset(fn->raw),
-			       je32_to_cpu(ri.totlen), sizeof(ri));
+			pr_warn("%s(): Node at 0x%08x had totlen 0x%x instead of expected 0x%zx\n",
+				__func__, ref_offset(fn->raw),
+				je32_to_cpu(ri.totlen), sizeof(ri));
 			return -EIO;
 		}
 		crc = crc32(0, &ri, sizeof(ri)-8);
 		if (crc != je32_to_cpu(ri.node_crc)) {
-			printk(KERN_WARNING "jffs2_garbage_collect_hole: Node at 0x%08x had CRC 0x%08x which doesn't match calculated CRC 0x%08x\n",
-			       ref_offset(fn->raw),
-			       je32_to_cpu(ri.node_crc), crc);
+			pr_warn("%s: Node at 0x%08x had CRC 0x%08x which doesn't match calculated CRC 0x%08x\n",
+				__func__, ref_offset(fn->raw),
+				je32_to_cpu(ri.node_crc), crc);
 			/* FIXME: We could possibly deal with this by writing new holes for each frag */
-			printk(KERN_WARNING "Data in the range 0x%08x to 0x%08x of inode #%u will be lost\n",
-			       start, end, f->inocache->ino);
+			pr_warn("Data in the range 0x%08x to 0x%08x of inode #%u will be lost\n",
+				start, end, f->inocache->ino);
 			goto fill;
 		}
 		if (ri.compr != JFFS2_COMPR_ZERO) {
-			printk(KERN_WARNING "jffs2_garbage_collect_hole: Node 0x%08x wasn't a hole node!\n", ref_offset(fn->raw));
-			printk(KERN_WARNING "Data in the range 0x%08x to 0x%08x of inode #%u will be lost\n",
-			       start, end, f->inocache->ino);
+			pr_warn("%s(): Node 0x%08x wasn't a hole node!\n",
+				__func__, ref_offset(fn->raw));
+			pr_warn("Data in the range 0x%08x to 0x%08x of inode #%u will be lost\n",
+				start, end, f->inocache->ino);
 			goto fill;
 		}
 	} else {
@@ -1043,14 +1081,14 @@ static int jffs2_garbage_collect_hole(struct jffs2_sb_info *c, struct jffs2_eras
 	ret = jffs2_reserve_space_gc(c, sizeof(ri), &alloclen,
 				     JFFS2_SUMMARY_INODE_SIZE);
 	if (ret) {
-		printk(KERN_WARNING "jffs2_reserve_space_gc of %zd bytes for garbage_collect_hole failed: %d\n",
-		       sizeof(ri), ret);
+		pr_warn("jffs2_reserve_space_gc of %zd bytes for garbage_collect_hole failed: %d\n",
+			sizeof(ri), ret);
 		return ret;
 	}
 	new_fn = jffs2_write_dnode(c, f, &ri, NULL, 0, ALLOC_GC);
 
 	if (IS_ERR(new_fn)) {
-		printk(KERN_WARNING "Error writing new hole node: %ld\n", PTR_ERR(new_fn));
+		pr_warn("Error writing new hole node: %ld\n", PTR_ERR(new_fn));
 		return PTR_ERR(new_fn);
 	}
 	if (je32_to_cpu(ri.version) == f->highest_version) {
@@ -1070,9 +1108,9 @@ static int jffs2_garbage_collect_hole(struct jffs2_sb_info *c, struct jffs2_eras
 	 * above.)
 	 */
 	D1(if(unlikely(fn->frags <= 1)) {
-		printk(KERN_WARNING "jffs2_garbage_collect_hole: Replacing fn with %d frag(s) but new ver %d != highest_version %d of ino #%d\n",
-		       fn->frags, je32_to_cpu(ri.version), f->highest_version,
-		       je32_to_cpu(ri.ino));
+			pr_warn("%s(): Replacing fn with %d frag(s) but new ver %d != highest_version %d of ino #%d\n",
+				__func__, fn->frags, je32_to_cpu(ri.version),
+				f->highest_version, je32_to_cpu(ri.ino));
 	});
 
 	/* This is a partially-overlapped hole node. Mark it REF_NORMAL not REF_PRISTINE */
@@ -1089,11 +1127,11 @@ static int jffs2_garbage_collect_hole(struct jffs2_sb_info *c, struct jffs2_eras
 		}
 	}
 	if (fn->frags) {
-		printk(KERN_WARNING "jffs2_garbage_collect_hole: Old node still has frags!\n");
+		pr_warn("%s(): Old node still has frags!\n", __func__);
 		BUG();
 	}
 	if (!new_fn->frags) {
-		printk(KERN_WARNING "jffs2_garbage_collect_hole: New node has no frags!\n");
+		pr_warn("%s(): New node has no frags!\n", __func__);
 		BUG();
 	}
 
@@ -1117,8 +1155,8 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 
 	memset(&ri, 0, sizeof(ri));
 
-	D1(printk(KERN_DEBUG "Writing replacement dnode for ino #%u from offset 0x%x to 0x%x\n",
-		  f->inocache->ino, start, end));
+	jffs2_dbg(1, "Writing replacement dnode for ino #%u from offset 0x%x to 0x%x\n",
+		  f->inocache->ino, start, end);
 
 	orig_end = end;
 	orig_start = start;
@@ -1149,15 +1187,15 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 			/* If the previous frag doesn't even reach the beginning, there's
 			   excessive fragmentation. Just merge. */
 			if (frag->ofs > min) {
-				D1(printk(KERN_DEBUG "Expanding down to cover partial frag (0x%x-0x%x)\n",
-					  frag->ofs, frag->ofs+frag->size));
+				jffs2_dbg(1, "Expanding down to cover partial frag (0x%x-0x%x)\n",
+					  frag->ofs, frag->ofs+frag->size);
 				start = frag->ofs;
 				continue;
 			}
 			/* OK. This frag holds the first byte of the page. */
 			if (!frag->node || !frag->node->raw) {
-				D1(printk(KERN_DEBUG "First frag in page is hole (0x%x-0x%x). Not expanding down.\n",
-					  frag->ofs, frag->ofs+frag->size));
+				jffs2_dbg(1, "First frag in page is hole (0x%x-0x%x). Not expanding down.\n",
+					  frag->ofs, frag->ofs+frag->size);
 				break;
 			} else {
 
@@ -1171,19 +1209,25 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 				jeb = &c->blocks[raw->flash_offset / c->sector_size];
 
 				if (jeb == c->gcblock) {
-					D1(printk(KERN_DEBUG "Expanding down to cover frag (0x%x-0x%x) in gcblock at %08x\n",
-						  frag->ofs, frag->ofs+frag->size, ref_offset(raw)));
+					jffs2_dbg(1, "Expanding down to cover frag (0x%x-0x%x) in gcblock at %08x\n",
+						  frag->ofs,
+						  frag->ofs + frag->size,
+						  ref_offset(raw));
 					start = frag->ofs;
 					break;
 				}
 				if (!ISDIRTY(jeb->dirty_size + jeb->wasted_size)) {
-					D1(printk(KERN_DEBUG "Not expanding down to cover frag (0x%x-0x%x) in clean block %08x\n",
-						  frag->ofs, frag->ofs+frag->size, jeb->offset));
+					jffs2_dbg(1, "Not expanding down to cover frag (0x%x-0x%x) in clean block %08x\n",
+						  frag->ofs,
+						  frag->ofs + frag->size,
+						  jeb->offset);
 					break;
 				}
 
-				D1(printk(KERN_DEBUG "Expanding down to cover frag (0x%x-0x%x) in dirty block %08x\n",
-						  frag->ofs, frag->ofs+frag->size, jeb->offset));
+				jffs2_dbg(1, "Expanding down to cover frag (0x%x-0x%x) in dirty block %08x\n",
+					  frag->ofs,
+					  frag->ofs + frag->size,
+					  jeb->offset);
 				start = frag->ofs;
 				break;
 			}
@@ -1199,15 +1243,15 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 			/* If the previous frag doesn't even reach the beginning, there's lots
 			   of fragmentation. Just merge. */
 			if (frag->ofs+frag->size < max) {
-				D1(printk(KERN_DEBUG "Expanding up to cover partial frag (0x%x-0x%x)\n",
-					  frag->ofs, frag->ofs+frag->size));
+				jffs2_dbg(1, "Expanding up to cover partial frag (0x%x-0x%x)\n",
+					  frag->ofs, frag->ofs+frag->size);
 				end = frag->ofs + frag->size;
 				continue;
 			}
 
 			if (!frag->node || !frag->node->raw) {
-				D1(printk(KERN_DEBUG "Last frag in page is hole (0x%x-0x%x). Not expanding up.\n",
-					  frag->ofs, frag->ofs+frag->size));
+				jffs2_dbg(1, "Last frag in page is hole (0x%x-0x%x). Not expanding up.\n",
+					  frag->ofs, frag->ofs+frag->size);
 				break;
 			} else {
 
@@ -1221,25 +1265,31 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 				jeb = &c->blocks[raw->flash_offset / c->sector_size];
 
 				if (jeb == c->gcblock) {
-					D1(printk(KERN_DEBUG "Expanding up to cover frag (0x%x-0x%x) in gcblock at %08x\n",
-						  frag->ofs, frag->ofs+frag->size, ref_offset(raw)));
+					jffs2_dbg(1, "Expanding up to cover frag (0x%x-0x%x) in gcblock at %08x\n",
+						  frag->ofs,
+						  frag->ofs + frag->size,
+						  ref_offset(raw));
 					end = frag->ofs + frag->size;
 					break;
 				}
 				if (!ISDIRTY(jeb->dirty_size + jeb->wasted_size)) {
-					D1(printk(KERN_DEBUG "Not expanding up to cover frag (0x%x-0x%x) in clean block %08x\n",
-						  frag->ofs, frag->ofs+frag->size, jeb->offset));
+					jffs2_dbg(1, "Not expanding up to cover frag (0x%x-0x%x) in clean block %08x\n",
+						  frag->ofs,
+						  frag->ofs + frag->size,
+						  jeb->offset);
 					break;
 				}
 
-				D1(printk(KERN_DEBUG "Expanding up to cover frag (0x%x-0x%x) in dirty block %08x\n",
-						  frag->ofs, frag->ofs+frag->size, jeb->offset));
+				jffs2_dbg(1, "Expanding up to cover frag (0x%x-0x%x) in dirty block %08x\n",
+					  frag->ofs,
+					  frag->ofs + frag->size,
+					  jeb->offset);
 				end = frag->ofs + frag->size;
 				break;
 			}
 		}
-		D1(printk(KERN_DEBUG "Expanded dnode to write from (0x%x-0x%x) to (0x%x-0x%x)\n",
-			  orig_start, orig_end, start, end));
+		jffs2_dbg(1, "Expanded dnode to write from (0x%x-0x%x) to (0x%x-0x%x)\n",
+			  orig_start, orig_end, start, end);
 
 		D1(BUG_ON(end > frag_last(&f->fragtree)->ofs + frag_last(&f->fragtree)->size));
 		BUG_ON(end < orig_end);
@@ -1256,7 +1306,8 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 	pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg);
 
 	if (IS_ERR(pg_ptr)) {
-		printk(KERN_WARNING "read_cache_page() returned error: %ld\n", PTR_ERR(pg_ptr));
+		pr_warn("read_cache_page() returned error: %ld\n",
+			PTR_ERR(pg_ptr));
 		return PTR_ERR(pg_ptr);
 	}
 
@@ -1270,8 +1321,8 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 					&alloclen, JFFS2_SUMMARY_INODE_SIZE);
 
 		if (ret) {
-			printk(KERN_WARNING "jffs2_reserve_space_gc of %zd bytes for garbage_collect_dnode failed: %d\n",
-			       sizeof(ri)+ JFFS2_MIN_DATA_LEN, ret);
+			pr_warn("jffs2_reserve_space_gc of %zd bytes for garbage_collect_dnode failed: %d\n",
+				sizeof(ri) + JFFS2_MIN_DATA_LEN, ret);
 			break;
 		}
 		cdatalen = min_t(uint32_t, alloclen - sizeof(ri), end - offset);
@@ -1308,7 +1359,8 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		jffs2_free_comprbuf(comprbuf, writebuf);
 
 		if (IS_ERR(new_fn)) {
-			printk(KERN_WARNING "Error writing new dnode: %ld\n", PTR_ERR(new_fn));
+			pr_warn("Error writing new dnode: %ld\n",
+				PTR_ERR(new_fn));
 			ret = PTR_ERR(new_fn);
 			break;
 		}
diff --git a/fs/jffs2/malloc.c b/fs/jffs2/malloc.c
index c082868910f2..4f47aa24b556 100644
--- a/fs/jffs2/malloc.c
+++ b/fs/jffs2/malloc.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/init.h>
diff --git a/fs/jffs2/nodelist.c b/fs/jffs2/nodelist.c
index 5e03233c2363..975a1f562c10 100644
--- a/fs/jffs2/nodelist.c
+++ b/fs/jffs2/nodelist.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
@@ -687,8 +689,8 @@ int jffs2_scan_dirty_space(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb
 	if (!size)
 		return 0;
 	if (unlikely(size > jeb->free_size)) {
-		printk(KERN_CRIT "Dirty space 0x%x larger then free_size 0x%x (wasted 0x%x)\n",
-		       size, jeb->free_size, jeb->wasted_size);
+		pr_crit("Dirty space 0x%x larger then free_size 0x%x (wasted 0x%x)\n",
+			size, jeb->free_size, jeb->wasted_size);
 		BUG();
 	}
 	/* REF_EMPTY_NODE is !obsolete, so that works OK */
@@ -726,8 +728,10 @@ static inline uint32_t __ref_totlen(struct jffs2_sb_info *c,
 
 		/* Last node in block. Use free_space */
 		if (unlikely(ref != jeb->last_node)) {
-			printk(KERN_CRIT "ref %p @0x%08x is not jeb->last_node (%p @0x%08x)\n",
-			       ref, ref_offset(ref), jeb->last_node, jeb->last_node?ref_offset(jeb->last_node):0);
+			pr_crit("ref %p @0x%08x is not jeb->last_node (%p @0x%08x)\n",
+				ref, ref_offset(ref), jeb->last_node,
+				jeb->last_node ?
+				ref_offset(jeb->last_node) : 0);
 			BUG();
 		}
 		ref_end = jeb->offset + c->sector_size - jeb->free_size;
@@ -747,16 +751,20 @@ uint32_t __jffs2_ref_totlen(struct jffs2_sb_info *c, struct jffs2_eraseblock *je
 		if (!jeb)
 			jeb = &c->blocks[ref->flash_offset / c->sector_size];
 
-		printk(KERN_CRIT "Totlen for ref at %p (0x%08x-0x%08x) miscalculated as 0x%x instead of %x\n",
-		       ref, ref_offset(ref), ref_offset(ref)+ref->__totlen,
-		       ret, ref->__totlen);
+		pr_crit("Totlen for ref at %p (0x%08x-0x%08x) miscalculated as 0x%x instead of %x\n",
+			ref, ref_offset(ref), ref_offset(ref) + ref->__totlen,
+			ret, ref->__totlen);
 		if (ref_next(ref)) {
-			printk(KERN_CRIT "next %p (0x%08x-0x%08x)\n", ref_next(ref), ref_offset(ref_next(ref)),
-			       ref_offset(ref_next(ref))+ref->__totlen);
+			pr_crit("next %p (0x%08x-0x%08x)\n",
+				ref_next(ref), ref_offset(ref_next(ref)),
+				ref_offset(ref_next(ref)) + ref->__totlen);
 		} else 
-			printk(KERN_CRIT "No next ref. jeb->last_node is %p\n", jeb->last_node);
+			pr_crit("No next ref. jeb->last_node is %p\n",
+				jeb->last_node);
 
-		printk(KERN_CRIT "jeb->wasted_size %x, dirty_size %x, used_size %x, free_size %x\n", jeb->wasted_size, jeb->dirty_size, jeb->used_size, jeb->free_size);
+		pr_crit("jeb->wasted_size %x, dirty_size %x, used_size %x, free_size %x\n",
+			jeb->wasted_size, jeb->dirty_size, jeb->used_size,
+			jeb->free_size);
 
 #if defined(JFFS2_DBG_DUMPS) || defined(JFFS2_DBG_PARANOIA_CHECKS)
 		__jffs2_dbg_dump_node_refs_nolock(c, jeb);
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index 694aa5b03505..6784d1e7a7eb 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/mtd/mtd.h>
 #include <linux/compiler.h>
@@ -46,10 +48,10 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 	/* align it */
 	minsize = PAD(minsize);
 
-	D1(printk(KERN_DEBUG "jffs2_reserve_space(): Requested 0x%x bytes\n", minsize));
+	jffs2_dbg(1, "%s(): Requested 0x%x bytes\n", __func__, minsize);
 	mutex_lock(&c->alloc_sem);
 
-	D1(printk(KERN_DEBUG "jffs2_reserve_space(): alloc sem got\n"));
+	jffs2_dbg(1, "%s(): alloc sem got\n", __func__);
 
 	spin_lock(&c->erase_completion_lock);
 
@@ -73,11 +75,13 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 			dirty = c->dirty_size + c->erasing_size - c->nr_erasing_blocks * c->sector_size + c->unchecked_size;
 			if (dirty < c->nospc_dirty_size) {
 				if (prio == ALLOC_DELETION && c->nr_free_blocks + c->nr_erasing_blocks >= c->resv_blocks_deletion) {
-					D1(printk(KERN_NOTICE "jffs2_reserve_space(): Low on dirty space to GC, but it's a deletion. Allowing...\n"));
+					jffs2_dbg(1, "%s(): Low on dirty space to GC, but it's a deletion. Allowing...\n",
+						  __func__);
 					break;
 				}
-				D1(printk(KERN_DEBUG "dirty size 0x%08x + unchecked_size 0x%08x < nospc_dirty_size 0x%08x, returning -ENOSPC\n",
-					  dirty, c->unchecked_size, c->sector_size));
+				jffs2_dbg(1, "dirty size 0x%08x + unchecked_size 0x%08x < nospc_dirty_size 0x%08x, returning -ENOSPC\n",
+					  dirty, c->unchecked_size,
+					  c->sector_size);
 
 				spin_unlock(&c->erase_completion_lock);
 				mutex_unlock(&c->alloc_sem);
@@ -96,12 +100,13 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 			avail = c->free_size + c->dirty_size + c->erasing_size + c->unchecked_size;
 			if ( (avail / c->sector_size) <= blocksneeded) {
 				if (prio == ALLOC_DELETION && c->nr_free_blocks + c->nr_erasing_blocks >= c->resv_blocks_deletion) {
-					D1(printk(KERN_NOTICE "jffs2_reserve_space(): Low on possibly available space, but it's a deletion. Allowing...\n"));
+					jffs2_dbg(1, "%s(): Low on possibly available space, but it's a deletion. Allowing...\n",
+						  __func__);
 					break;
 				}
 
-				D1(printk(KERN_DEBUG "max. available size 0x%08x  < blocksneeded * sector_size 0x%08x, returning -ENOSPC\n",
-					  avail, blocksneeded * c->sector_size));
+				jffs2_dbg(1, "max. available size 0x%08x  < blocksneeded * sector_size 0x%08x, returning -ENOSPC\n",
+					  avail, blocksneeded * c->sector_size);
 				spin_unlock(&c->erase_completion_lock);
 				mutex_unlock(&c->alloc_sem);
 				return -ENOSPC;
@@ -109,9 +114,14 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 
 			mutex_unlock(&c->alloc_sem);
 
-			D1(printk(KERN_DEBUG "Triggering GC pass. nr_free_blocks %d, nr_erasing_blocks %d, free_size 0x%08x, dirty_size 0x%08x, wasted_size 0x%08x, used_size 0x%08x, erasing_size 0x%08x, bad_size 0x%08x (total 0x%08x of 0x%08x)\n",
-				  c->nr_free_blocks, c->nr_erasing_blocks, c->free_size, c->dirty_size, c->wasted_size, c->used_size, c->erasing_size, c->bad_size,
-				  c->free_size + c->dirty_size + c->wasted_size + c->used_size + c->erasing_size + c->bad_size, c->flash_size));
+			jffs2_dbg(1, "Triggering GC pass. nr_free_blocks %d, nr_erasing_blocks %d, free_size 0x%08x, dirty_size 0x%08x, wasted_size 0x%08x, used_size 0x%08x, erasing_size 0x%08x, bad_size 0x%08x (total 0x%08x of 0x%08x)\n",
+				  c->nr_free_blocks, c->nr_erasing_blocks,
+				  c->free_size, c->dirty_size, c->wasted_size,
+				  c->used_size, c->erasing_size, c->bad_size,
+				  c->free_size + c->dirty_size +
+				  c->wasted_size + c->used_size +
+				  c->erasing_size + c->bad_size,
+				  c->flash_size);
 			spin_unlock(&c->erase_completion_lock);
 
 			ret = jffs2_garbage_collect_pass(c);
@@ -124,7 +134,8 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 					DECLARE_WAITQUEUE(wait, current);
 					set_current_state(TASK_UNINTERRUPTIBLE);
 					add_wait_queue(&c->erase_wait, &wait);
-					D1(printk(KERN_DEBUG "%s waiting for erase to complete\n", __func__));
+					jffs2_dbg(1, "%s waiting for erase to complete\n",
+						  __func__);
 					spin_unlock(&c->erase_completion_lock);
 
 					schedule();
@@ -144,7 +155,7 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 
 		ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
 		if (ret) {
-			D1(printk(KERN_DEBUG "jffs2_reserve_space: ret is %d\n", ret));
+			jffs2_dbg(1, "%s(): ret is %d\n", __func__, ret);
 		}
 	}
 	spin_unlock(&c->erase_completion_lock);
@@ -161,13 +172,14 @@ int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize,
 	int ret = -EAGAIN;
 	minsize = PAD(minsize);
 
-	D1(printk(KERN_DEBUG "jffs2_reserve_space_gc(): Requested 0x%x bytes\n", minsize));
+	jffs2_dbg(1, "%s(): Requested 0x%x bytes\n", __func__, minsize);
 
 	spin_lock(&c->erase_completion_lock);
 	while(ret == -EAGAIN) {
 		ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
 		if (ret) {
-			D1(printk(KERN_DEBUG "jffs2_reserve_space_gc: looping, ret is %d\n", ret));
+			jffs2_dbg(1, "%s(): looping, ret is %d\n",
+				  __func__, ret);
 		}
 	}
 	spin_unlock(&c->erase_completion_lock);
@@ -184,8 +196,8 @@ static void jffs2_close_nextblock(struct jffs2_sb_info *c, struct jffs2_eraseblo
 {
 
 	if (c->nextblock == NULL) {
-		D1(printk(KERN_DEBUG "jffs2_close_nextblock: Erase block at 0x%08x has already been placed in a list\n",
-		  jeb->offset));
+		jffs2_dbg(1, "%s(): Erase block at 0x%08x has already been placed in a list\n",
+			  __func__, jeb->offset);
 		return;
 	}
 	/* Check, if we have a dirty block now, or if it was dirty already */
@@ -195,17 +207,20 @@ static void jffs2_close_nextblock(struct jffs2_sb_info *c, struct jffs2_eraseblo
 		jeb->dirty_size += jeb->wasted_size;
 		jeb->wasted_size = 0;
 		if (VERYDIRTY(c, jeb->dirty_size)) {
-			D1(printk(KERN_DEBUG "Adding full erase block at 0x%08x to very_dirty_list (free 0x%08x, dirty 0x%08x, used 0x%08x\n",
-			  jeb->offset, jeb->free_size, jeb->dirty_size, jeb->used_size));
+			jffs2_dbg(1, "Adding full erase block at 0x%08x to very_dirty_list (free 0x%08x, dirty 0x%08x, used 0x%08x\n",
+				  jeb->offset, jeb->free_size, jeb->dirty_size,
+				  jeb->used_size);
 			list_add_tail(&jeb->list, &c->very_dirty_list);
 		} else {
-			D1(printk(KERN_DEBUG "Adding full erase block at 0x%08x to dirty_list (free 0x%08x, dirty 0x%08x, used 0x%08x\n",
-			  jeb->offset, jeb->free_size, jeb->dirty_size, jeb->used_size));
+			jffs2_dbg(1, "Adding full erase block at 0x%08x to dirty_list (free 0x%08x, dirty 0x%08x, used 0x%08x\n",
+				  jeb->offset, jeb->free_size, jeb->dirty_size,
+				  jeb->used_size);
 			list_add_tail(&jeb->list, &c->dirty_list);
 		}
 	} else {
-		D1(printk(KERN_DEBUG "Adding full erase block at 0x%08x to clean_list (free 0x%08x, dirty 0x%08x, used 0x%08x\n",
-		  jeb->offset, jeb->free_size, jeb->dirty_size, jeb->used_size));
+		jffs2_dbg(1, "Adding full erase block at 0x%08x to clean_list (free 0x%08x, dirty 0x%08x, used 0x%08x\n",
+			  jeb->offset, jeb->free_size, jeb->dirty_size,
+			  jeb->used_size);
 		list_add_tail(&jeb->list, &c->clean_list);
 	}
 	c->nextblock = NULL;
@@ -230,13 +245,14 @@ static int jffs2_find_nextblock(struct jffs2_sb_info *c)
 			list_move_tail(&ejeb->list, &c->erase_pending_list);
 			c->nr_erasing_blocks++;
 			jffs2_garbage_collect_trigger(c);
-			D1(printk(KERN_DEBUG "jffs2_find_nextblock: Triggering erase of erasable block at 0x%08x\n",
-				  ejeb->offset));
+			jffs2_dbg(1, "%s(): Triggering erase of erasable block at 0x%08x\n",
+				  __func__, ejeb->offset);
 		}
 
 		if (!c->nr_erasing_blocks &&
 			!list_empty(&c->erasable_pending_wbuf_list)) {
-			D1(printk(KERN_DEBUG "jffs2_find_nextblock: Flushing write buffer\n"));
+			jffs2_dbg(1, "%s(): Flushing write buffer\n",
+				  __func__);
 			/* c->nextblock is NULL, no update to c->nextblock allowed */
 			spin_unlock(&c->erase_completion_lock);
 			jffs2_flush_wbuf_pad(c);
@@ -248,9 +264,11 @@ static int jffs2_find_nextblock(struct jffs2_sb_info *c)
 		if (!c->nr_erasing_blocks) {
 			/* Ouch. We're in GC, or we wouldn't have got here.
 			   And there's no space left. At all. */
-			printk(KERN_CRIT "Argh. No free space left for GC. nr_erasing_blocks is %d. nr_free_blocks is %d. (erasableempty: %s, erasingempty: %s, erasependingempty: %s)\n",
-				   c->nr_erasing_blocks, c->nr_free_blocks, list_empty(&c->erasable_list)?"yes":"no",
-				   list_empty(&c->erasing_list)?"yes":"no", list_empty(&c->erase_pending_list)?"yes":"no");
+			pr_crit("Argh. No free space left for GC. nr_erasing_blocks is %d. nr_free_blocks is %d. (erasableempty: %s, erasingempty: %s, erasependingempty: %s)\n",
+				c->nr_erasing_blocks, c->nr_free_blocks,
+				list_empty(&c->erasable_list) ? "yes" : "no",
+				list_empty(&c->erasing_list) ? "yes" : "no",
+				list_empty(&c->erase_pending_list) ? "yes" : "no");
 			return -ENOSPC;
 		}
 
@@ -278,7 +296,8 @@ static int jffs2_find_nextblock(struct jffs2_sb_info *c)
 		c->wbuf_ofs = 0xffffffff;
 #endif
 
-	D1(printk(KERN_DEBUG "jffs2_find_nextblock(): new nextblock = 0x%08x\n", c->nextblock->offset));
+	jffs2_dbg(1, "%s(): new nextblock = 0x%08x\n",
+		  __func__, c->nextblock->offset);
 
 	return 0;
 }
@@ -345,7 +364,8 @@ static int jffs2_do_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 
 			if (jffs2_wbuf_dirty(c)) {
 				spin_unlock(&c->erase_completion_lock);
-				D1(printk(KERN_DEBUG "jffs2_do_reserve_space: Flushing write buffer\n"));
+				jffs2_dbg(1, "%s(): Flushing write buffer\n",
+					  __func__);
 				jffs2_flush_wbuf_pad(c);
 				spin_lock(&c->erase_completion_lock);
 				jeb = c->nextblock;
@@ -387,7 +407,8 @@ static int jffs2_do_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 		jeb = c->nextblock;
 
 		if (jeb->free_size != c->sector_size - c->cleanmarker_size) {
-			printk(KERN_WARNING "Eep. Block 0x%08x taken from free_list had free_size of 0x%08x!!\n", jeb->offset, jeb->free_size);
+			pr_warn("Eep. Block 0x%08x taken from free_list had free_size of 0x%08x!!\n",
+				jeb->offset, jeb->free_size);
 			goto restart;
 		}
 	}
@@ -408,8 +429,9 @@ static int jffs2_do_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 		spin_lock(&c->erase_completion_lock);
 	}
 
-	D1(printk(KERN_DEBUG "jffs2_do_reserve_space(): Giving 0x%x bytes at 0x%x\n",
-		  *len, jeb->offset + (c->sector_size - jeb->free_size)));
+	jffs2_dbg(1, "%s(): Giving 0x%x bytes at 0x%x\n",
+		  __func__,
+		  *len, jeb->offset + (c->sector_size - jeb->free_size));
 	return 0;
 }
 
@@ -434,20 +456,22 @@ struct jffs2_raw_node_ref *jffs2_add_physical_node_ref(struct jffs2_sb_info *c,
 
 	jeb = &c->blocks[ofs / c->sector_size];
 
-	D1(printk(KERN_DEBUG "jffs2_add_physical_node_ref(): Node at 0x%x(%d), size 0x%x\n",
-		  ofs & ~3, ofs & 3, len));
+	jffs2_dbg(1, "%s(): Node at 0x%x(%d), size 0x%x\n",
+		  __func__, ofs & ~3, ofs & 3, len);
 #if 1
 	/* Allow non-obsolete nodes only to be added at the end of c->nextblock, 
 	   if c->nextblock is set. Note that wbuf.c will file obsolete nodes
 	   even after refiling c->nextblock */
 	if ((c->nextblock || ((ofs & 3) != REF_OBSOLETE))
 	    && (jeb != c->nextblock || (ofs & ~3) != jeb->offset + (c->sector_size - jeb->free_size))) {
-		printk(KERN_WARNING "argh. node added in wrong place at 0x%08x(%d)\n", ofs & ~3, ofs & 3);
+		pr_warn("argh. node added in wrong place at 0x%08x(%d)\n",
+			ofs & ~3, ofs & 3);
 		if (c->nextblock)
-			printk(KERN_WARNING "nextblock 0x%08x", c->nextblock->offset);
+			pr_warn("nextblock 0x%08x", c->nextblock->offset);
 		else
-			printk(KERN_WARNING "No nextblock");
-		printk(", expected at %08x\n", jeb->offset + (c->sector_size - jeb->free_size));
+			pr_warn("No nextblock");
+		pr_cont(", expected at %08x\n",
+			jeb->offset + (c->sector_size - jeb->free_size));
 		return ERR_PTR(-EINVAL);
 	}
 #endif
@@ -457,8 +481,9 @@ struct jffs2_raw_node_ref *jffs2_add_physical_node_ref(struct jffs2_sb_info *c,
 
 	if (!jeb->free_size && !jeb->dirty_size && !ISDIRTY(jeb->wasted_size)) {
 		/* If it lives on the dirty_list, jffs2_reserve_space will put it there */
-		D1(printk(KERN_DEBUG "Adding full erase block at 0x%08x to clean_list (free 0x%08x, dirty 0x%08x, used 0x%08x\n",
-			  jeb->offset, jeb->free_size, jeb->dirty_size, jeb->used_size));
+		jffs2_dbg(1, "Adding full erase block at 0x%08x to clean_list (free 0x%08x, dirty 0x%08x, used 0x%08x\n",
+			  jeb->offset, jeb->free_size, jeb->dirty_size,
+			  jeb->used_size);
 		if (jffs2_wbuf_dirty(c)) {
 			/* Flush the last write in the block if it's outstanding */
 			spin_unlock(&c->erase_completion_lock);
@@ -480,7 +505,7 @@ struct jffs2_raw_node_ref *jffs2_add_physical_node_ref(struct jffs2_sb_info *c,
 
 void jffs2_complete_reservation(struct jffs2_sb_info *c)
 {
-	D1(printk(KERN_DEBUG "jffs2_complete_reservation()\n"));
+	jffs2_dbg(1, "jffs2_complete_reservation()\n");
 	spin_lock(&c->erase_completion_lock);
 	jffs2_garbage_collect_trigger(c);
 	spin_unlock(&c->erase_completion_lock);
@@ -493,7 +518,7 @@ static inline int on_list(struct list_head *obj, struct list_head *head)
 
 	list_for_each(this, head) {
 		if (this == obj) {
-			D1(printk("%p is on list at %p\n", obj, head));
+			jffs2_dbg(1, "%p is on list at %p\n", obj, head);
 			return 1;
 
 		}
@@ -511,16 +536,18 @@ void jffs2_mark_node_obsolete(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
 	uint32_t freed_len;
 
 	if(unlikely(!ref)) {
-		printk(KERN_NOTICE "EEEEEK. jffs2_mark_node_obsolete called with NULL node\n");
+		pr_notice("EEEEEK. jffs2_mark_node_obsolete called with NULL node\n");
 		return;
 	}
 	if (ref_obsolete(ref)) {
-		D1(printk(KERN_DEBUG "jffs2_mark_node_obsolete called with already obsolete node at 0x%08x\n", ref_offset(ref)));
+		jffs2_dbg(1, "%s(): called with already obsolete node at 0x%08x\n",
+			  __func__, ref_offset(ref));
 		return;
 	}
 	blocknr = ref->flash_offset / c->sector_size;
 	if (blocknr >= c->nr_blocks) {
-		printk(KERN_NOTICE "raw node at 0x%08x is off the end of device!\n", ref->flash_offset);
+		pr_notice("raw node at 0x%08x is off the end of device!\n",
+			  ref->flash_offset);
 		BUG();
 	}
 	jeb = &c->blocks[blocknr];
@@ -542,27 +569,31 @@ void jffs2_mark_node_obsolete(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
 
 	if (ref_flags(ref) == REF_UNCHECKED) {
 		D1(if (unlikely(jeb->unchecked_size < freed_len)) {
-			printk(KERN_NOTICE "raw unchecked node of size 0x%08x freed from erase block %d at 0x%08x, but unchecked_size was already 0x%08x\n",
-			       freed_len, blocknr, ref->flash_offset, jeb->used_size);
+				pr_notice("raw unchecked node of size 0x%08x freed from erase block %d at 0x%08x, but unchecked_size was already 0x%08x\n",
+					  freed_len, blocknr,
+					  ref->flash_offset, jeb->used_size);
 			BUG();
 		})
-		D1(printk(KERN_DEBUG "Obsoleting previously unchecked node at 0x%08x of len %x: ", ref_offset(ref), freed_len));
+			jffs2_dbg(1, "Obsoleting previously unchecked node at 0x%08x of len %x\n",
+				  ref_offset(ref), freed_len);
 		jeb->unchecked_size -= freed_len;
 		c->unchecked_size -= freed_len;
 	} else {
 		D1(if (unlikely(jeb->used_size < freed_len)) {
-			printk(KERN_NOTICE "raw node of size 0x%08x freed from erase block %d at 0x%08x, but used_size was already 0x%08x\n",
-			       freed_len, blocknr, ref->flash_offset, jeb->used_size);
+				pr_notice("raw node of size 0x%08x freed from erase block %d at 0x%08x, but used_size was already 0x%08x\n",
+					  freed_len, blocknr,
+					  ref->flash_offset, jeb->used_size);
 			BUG();
 		})
-		D1(printk(KERN_DEBUG "Obsoleting node at 0x%08x of len %#x: ", ref_offset(ref), freed_len));
+			jffs2_dbg(1, "Obsoleting node at 0x%08x of len %#x: ",
+				  ref_offset(ref), freed_len);
 		jeb->used_size -= freed_len;
 		c->used_size -= freed_len;
 	}
 
 	// Take care, that wasted size is taken into concern
 	if ((jeb->dirty_size || ISDIRTY(jeb->wasted_size + freed_len)) && jeb != c->nextblock) {
-		D1(printk("Dirtying\n"));
+		jffs2_dbg(1, "Dirtying\n");
 		addedsize = freed_len;
 		jeb->dirty_size += freed_len;
 		c->dirty_size += freed_len;
@@ -570,12 +601,12 @@ void jffs2_mark_node_obsolete(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
 		/* Convert wasted space to dirty, if not a bad block */
 		if (jeb->wasted_size) {
 			if (on_list(&jeb->list, &c->bad_used_list)) {
-				D1(printk(KERN_DEBUG "Leaving block at %08x on the bad_used_list\n",
-					  jeb->offset));
+				jffs2_dbg(1, "Leaving block at %08x on the bad_used_list\n",
+					  jeb->offset);
 				addedsize = 0; /* To fool the refiling code later */
 			} else {
-				D1(printk(KERN_DEBUG "Converting %d bytes of wasted space to dirty in block at %08x\n",
-					  jeb->wasted_size, jeb->offset));
+				jffs2_dbg(1, "Converting %d bytes of wasted space to dirty in block at %08x\n",
+					  jeb->wasted_size, jeb->offset);
 				addedsize += jeb->wasted_size;
 				jeb->dirty_size += jeb->wasted_size;
 				c->dirty_size += jeb->wasted_size;
@@ -584,7 +615,7 @@ void jffs2_mark_node_obsolete(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
 			}
 		}
 	} else {
-		D1(printk("Wasting\n"));
+		jffs2_dbg(1, "Wasting\n");
 		addedsize = 0;
 		jeb->wasted_size += freed_len;
 		c->wasted_size += freed_len;
@@ -606,50 +637,57 @@ void jffs2_mark_node_obsolete(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
 	}
 
 	if (jeb == c->nextblock) {
-		D2(printk(KERN_DEBUG "Not moving nextblock 0x%08x to dirty/erase_pending list\n", jeb->offset));
+		jffs2_dbg(2, "Not moving nextblock 0x%08x to dirty/erase_pending list\n",
+			  jeb->offset);
 	} else if (!jeb->used_size && !jeb->unchecked_size) {
 		if (jeb == c->gcblock) {
-			D1(printk(KERN_DEBUG "gcblock at 0x%08x completely dirtied. Clearing gcblock...\n", jeb->offset));
+			jffs2_dbg(1, "gcblock at 0x%08x completely dirtied. Clearing gcblock...\n",
+				  jeb->offset);
 			c->gcblock = NULL;
 		} else {
-			D1(printk(KERN_DEBUG "Eraseblock at 0x%08x completely dirtied. Removing from (dirty?) list...\n", jeb->offset));
+			jffs2_dbg(1, "Eraseblock at 0x%08x completely dirtied. Removing from (dirty?) list...\n",
+				  jeb->offset);
 			list_del(&jeb->list);
 		}
 		if (jffs2_wbuf_dirty(c)) {
-			D1(printk(KERN_DEBUG "...and adding to erasable_pending_wbuf_list\n"));
+			jffs2_dbg(1, "...and adding to erasable_pending_wbuf_list\n");
 			list_add_tail(&jeb->list, &c->erasable_pending_wbuf_list);
 		} else {
 			if (jiffies & 127) {
 				/* Most of the time, we just erase it immediately. Otherwise we
 				   spend ages scanning it on mount, etc. */
-				D1(printk(KERN_DEBUG "...and adding to erase_pending_list\n"));
+				jffs2_dbg(1, "...and adding to erase_pending_list\n");
 				list_add_tail(&jeb->list, &c->erase_pending_list);
 				c->nr_erasing_blocks++;
 				jffs2_garbage_collect_trigger(c);
 			} else {
 				/* Sometimes, however, we leave it elsewhere so it doesn't get
 				   immediately reused, and we spread the load a bit. */
-				D1(printk(KERN_DEBUG "...and adding to erasable_list\n"));
+				jffs2_dbg(1, "...and adding to erasable_list\n");
 				list_add_tail(&jeb->list, &c->erasable_list);
 			}
 		}
-		D1(printk(KERN_DEBUG "Done OK\n"));
+		jffs2_dbg(1, "Done OK\n");
 	} else if (jeb == c->gcblock) {
-		D2(printk(KERN_DEBUG "Not moving gcblock 0x%08x to dirty_list\n", jeb->offset));
+		jffs2_dbg(2, "Not moving gcblock 0x%08x to dirty_list\n",
+			  jeb->offset);
 	} else if (ISDIRTY(jeb->dirty_size) && !ISDIRTY(jeb->dirty_size - addedsize)) {
-		D1(printk(KERN_DEBUG "Eraseblock at 0x%08x is freshly dirtied. Removing from clean list...\n", jeb->offset));
+		jffs2_dbg(1, "Eraseblock at 0x%08x is freshly dirtied. Removing from clean list...\n",
+			  jeb->offset);
 		list_del(&jeb->list);
-		D1(printk(KERN_DEBUG "...and adding to dirty_list\n"));
+		jffs2_dbg(1, "...and adding to dirty_list\n");
 		list_add_tail(&jeb->list, &c->dirty_list);
 	} else if (VERYDIRTY(c, jeb->dirty_size) &&
 		   !VERYDIRTY(c, jeb->dirty_size - addedsize)) {
-		D1(printk(KERN_DEBUG "Eraseblock at 0x%08x is now very dirty. Removing from dirty list...\n", jeb->offset));
+		jffs2_dbg(1, "Eraseblock at 0x%08x is now very dirty. Removing from dirty list...\n",
+			  jeb->offset);
 		list_del(&jeb->list);
-		D1(printk(KERN_DEBUG "...and adding to very_dirty_list\n"));
+		jffs2_dbg(1, "...and adding to very_dirty_list\n");
 		list_add_tail(&jeb->list, &c->very_dirty_list);
 	} else {
-		D1(printk(KERN_DEBUG "Eraseblock at 0x%08x not moved anywhere. (free 0x%08x, dirty 0x%08x, used 0x%08x)\n",
-			  jeb->offset, jeb->free_size, jeb->dirty_size, jeb->used_size));
+		jffs2_dbg(1, "Eraseblock at 0x%08x not moved anywhere. (free 0x%08x, dirty 0x%08x, used 0x%08x)\n",
+			  jeb->offset, jeb->free_size, jeb->dirty_size,
+			  jeb->used_size);
 	}
 
 	spin_unlock(&c->erase_completion_lock);
@@ -665,33 +703,40 @@ void jffs2_mark_node_obsolete(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
 	   the block hasn't _already_ been erased, and that 'ref' itself hasn't been freed yet
 	   by jffs2_free_jeb_node_refs() in erase.c. Which is nice. */
 
-	D1(printk(KERN_DEBUG "obliterating obsoleted node at 0x%08x\n", ref_offset(ref)));
+	jffs2_dbg(1, "obliterating obsoleted node at 0x%08x\n",
+		  ref_offset(ref));
 	ret = jffs2_flash_read(c, ref_offset(ref), sizeof(n), &retlen, (char *)&n);
 	if (ret) {
-		printk(KERN_WARNING "Read error reading from obsoleted node at 0x%08x: %d\n", ref_offset(ref), ret);
+		pr_warn("Read error reading from obsoleted node at 0x%08x: %d\n",
+			ref_offset(ref), ret);
 		goto out_erase_sem;
 	}
 	if (retlen != sizeof(n)) {
-		printk(KERN_WARNING "Short read from obsoleted node at 0x%08x: %zd\n", ref_offset(ref), retlen);
+		pr_warn("Short read from obsoleted node at 0x%08x: %zd\n",
+			ref_offset(ref), retlen);
 		goto out_erase_sem;
 	}
 	if (PAD(je32_to_cpu(n.totlen)) != PAD(freed_len)) {
-		printk(KERN_WARNING "Node totlen on flash (0x%08x) != totlen from node ref (0x%08x)\n", je32_to_cpu(n.totlen), freed_len);
+		pr_warn("Node totlen on flash (0x%08x) != totlen from node ref (0x%08x)\n",
+			je32_to_cpu(n.totlen), freed_len);
 		goto out_erase_sem;
 	}
 	if (!(je16_to_cpu(n.nodetype) & JFFS2_NODE_ACCURATE)) {
-		D1(printk(KERN_DEBUG "Node at 0x%08x was already marked obsolete (nodetype 0x%04x)\n", ref_offset(ref), je16_to_cpu(n.nodetype)));
+		jffs2_dbg(1, "Node at 0x%08x was already marked obsolete (nodetype 0x%04x)\n",
+			  ref_offset(ref), je16_to_cpu(n.nodetype));
 		goto out_erase_sem;
 	}
 	/* XXX FIXME: This is ugly now */
 	n.nodetype = cpu_to_je16(je16_to_cpu(n.nodetype) & ~JFFS2_NODE_ACCURATE);
 	ret = jffs2_flash_write(c, ref_offset(ref), sizeof(n), &retlen, (char *)&n);
 	if (ret) {
-		printk(KERN_WARNING "Write error in obliterating obsoleted node at 0x%08x: %d\n", ref_offset(ref), ret);
+		pr_warn("Write error in obliterating obsoleted node at 0x%08x: %d\n",
+			ref_offset(ref), ret);
 		goto out_erase_sem;
 	}
 	if (retlen != sizeof(n)) {
-		printk(KERN_WARNING "Short write in obliterating obsoleted node at 0x%08x: %zd\n", ref_offset(ref), retlen);
+		pr_warn("Short write in obliterating obsoleted node at 0x%08x: %zd\n",
+			ref_offset(ref), retlen);
 		goto out_erase_sem;
 	}
 
@@ -751,8 +796,8 @@ int jffs2_thread_should_wake(struct jffs2_sb_info *c)
 		return 1;
 
 	if (c->unchecked_size) {
-		D1(printk(KERN_DEBUG "jffs2_thread_should_wake(): unchecked_size %d, checked_ino #%d\n",
-			  c->unchecked_size, c->checked_ino));
+		jffs2_dbg(1, "jffs2_thread_should_wake(): unchecked_size %d, checked_ino #%d\n",
+			  c->unchecked_size, c->checked_ino);
 		return 1;
 	}
 
@@ -780,8 +825,9 @@ int jffs2_thread_should_wake(struct jffs2_sb_info *c)
 		}
 	}
 
-	D1(printk(KERN_DEBUG "jffs2_thread_should_wake(): nr_free_blocks %d, nr_erasing_blocks %d, dirty_size 0x%x, vdirty_blocks %d: %s\n",
-		  c->nr_free_blocks, c->nr_erasing_blocks, c->dirty_size, nr_very_dirty, ret?"yes":"no"));
+	jffs2_dbg(1, "%s(): nr_free_blocks %d, nr_erasing_blocks %d, dirty_size 0x%x, vdirty_blocks %d: %s\n",
+		  __func__, c->nr_free_blocks, c->nr_erasing_blocks,
+		  c->dirty_size, nr_very_dirty, ret ? "yes" : "no");
 
 	return ret;
 }
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index ab65ee3ec858..1cd3aec9d9ae 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -76,7 +76,7 @@ static inline void jffs2_init_inode_info(struct jffs2_inode_info *f)
 #define jffs2_write_nand_cleanmarker(c,jeb) (-EIO)
 
 #define jffs2_flash_write(c, ofs, len, retlen, buf) jffs2_flash_direct_write(c, ofs, len, retlen, buf)
-#define jffs2_flash_read(c, ofs, len, retlen, buf) ((c)->mtd->read((c)->mtd, ofs, len, retlen, buf))
+#define jffs2_flash_read(c, ofs, len, retlen, buf) (mtd_read((c)->mtd, ofs, len, retlen, buf))
 #define jffs2_flush_wbuf_pad(c) ({ do{} while(0); (void)(c), 0; })
 #define jffs2_flush_wbuf_gc(c, i) ({ do{} while(0); (void)(c), (void) i, 0; })
 #define jffs2_write_nand_badblock(c,jeb,bad_offset) (1)
@@ -108,8 +108,6 @@ static inline void jffs2_init_inode_info(struct jffs2_inode_info *f)
 
 #define jffs2_cleanmarker_oob(c) (c->mtd->type == MTD_NANDFLASH)
 
-#define jffs2_flash_write_oob(c, ofs, len, retlen, buf) ((c)->mtd->write_oob((c)->mtd, ofs, len, retlen, buf))
-#define jffs2_flash_read_oob(c, ofs, len, retlen, buf) ((c)->mtd->read_oob((c)->mtd, ofs, len, retlen, buf))
 #define jffs2_wbuf_dirty(c) (!!(c)->wbuf_len)
 
 /* wbuf.c */
diff --git a/fs/jffs2/read.c b/fs/jffs2/read.c
index 3f39be1b0455..0b042b1fc82f 100644
--- a/fs/jffs2/read.c
+++ b/fs/jffs2/read.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/crc32.h>
@@ -36,24 +38,25 @@ int jffs2_read_dnode(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 	ret = jffs2_flash_read(c, ref_offset(fd->raw), sizeof(*ri), &readlen, (char *)ri);
 	if (ret) {
 		jffs2_free_raw_inode(ri);
-		printk(KERN_WARNING "Error reading node from 0x%08x: %d\n", ref_offset(fd->raw), ret);
+		pr_warn("Error reading node from 0x%08x: %d\n",
+			ref_offset(fd->raw), ret);
 		return ret;
 	}
 	if (readlen != sizeof(*ri)) {
 		jffs2_free_raw_inode(ri);
-		printk(KERN_WARNING "Short read from 0x%08x: wanted 0x%zx bytes, got 0x%zx\n",
-		       ref_offset(fd->raw), sizeof(*ri), readlen);
+		pr_warn("Short read from 0x%08x: wanted 0x%zx bytes, got 0x%zx\n",
+			ref_offset(fd->raw), sizeof(*ri), readlen);
 		return -EIO;
 	}
 	crc = crc32(0, ri, sizeof(*ri)-8);
 
-	D1(printk(KERN_DEBUG "Node read from %08x: node_crc %08x, calculated CRC %08x. dsize %x, csize %x, offset %x, buf %p\n",
+	jffs2_dbg(1, "Node read from %08x: node_crc %08x, calculated CRC %08x. dsize %x, csize %x, offset %x, buf %p\n",
 		  ref_offset(fd->raw), je32_to_cpu(ri->node_crc),
 		  crc, je32_to_cpu(ri->dsize), je32_to_cpu(ri->csize),
-		  je32_to_cpu(ri->offset), buf));
+		  je32_to_cpu(ri->offset), buf);
 	if (crc != je32_to_cpu(ri->node_crc)) {
-		printk(KERN_WARNING "Node CRC %08x != calculated CRC %08x for node at %08x\n",
-		       je32_to_cpu(ri->node_crc), crc, ref_offset(fd->raw));
+		pr_warn("Node CRC %08x != calculated CRC %08x for node at %08x\n",
+			je32_to_cpu(ri->node_crc), crc, ref_offset(fd->raw));
 		ret = -EIO;
 		goto out_ri;
 	}
@@ -66,8 +69,8 @@ int jffs2_read_dnode(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 	}
 
 	D1(if(ofs + len > je32_to_cpu(ri->dsize)) {
-		printk(KERN_WARNING "jffs2_read_dnode() asked for %d bytes at %d from %d-byte node\n",
-		       len, ofs, je32_to_cpu(ri->dsize));
+			pr_warn("jffs2_read_dnode() asked for %d bytes at %d from %d-byte node\n",
+				len, ofs, je32_to_cpu(ri->dsize));
 		ret = -EINVAL;
 		goto out_ri;
 	});
@@ -107,8 +110,8 @@ int jffs2_read_dnode(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 		decomprbuf = readbuf;
 	}
 
-	D2(printk(KERN_DEBUG "Read %d bytes to %p\n", je32_to_cpu(ri->csize),
-		  readbuf));
+	jffs2_dbg(2, "Read %d bytes to %p\n", je32_to_cpu(ri->csize),
+		  readbuf);
 	ret = jffs2_flash_read(c, (ref_offset(fd->raw)) + sizeof(*ri),
 			       je32_to_cpu(ri->csize), &readlen, readbuf);
 
@@ -119,18 +122,19 @@ int jffs2_read_dnode(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 
 	crc = crc32(0, readbuf, je32_to_cpu(ri->csize));
 	if (crc != je32_to_cpu(ri->data_crc)) {
-		printk(KERN_WARNING "Data CRC %08x != calculated CRC %08x for node at %08x\n",
-		       je32_to_cpu(ri->data_crc), crc, ref_offset(fd->raw));
+		pr_warn("Data CRC %08x != calculated CRC %08x for node at %08x\n",
+			je32_to_cpu(ri->data_crc), crc, ref_offset(fd->raw));
 		ret = -EIO;
 		goto out_decomprbuf;
 	}
-	D2(printk(KERN_DEBUG "Data CRC matches calculated CRC %08x\n", crc));
+	jffs2_dbg(2, "Data CRC matches calculated CRC %08x\n", crc);
 	if (ri->compr != JFFS2_COMPR_NONE) {
-		D2(printk(KERN_DEBUG "Decompress %d bytes from %p to %d bytes at %p\n",
-			  je32_to_cpu(ri->csize), readbuf, je32_to_cpu(ri->dsize), decomprbuf));
+		jffs2_dbg(2, "Decompress %d bytes from %p to %d bytes at %p\n",
+			  je32_to_cpu(ri->csize), readbuf,
+			  je32_to_cpu(ri->dsize), decomprbuf);
 		ret = jffs2_decompress(c, f, ri->compr | (ri->usercompr << 8), readbuf, decomprbuf, je32_to_cpu(ri->csize), je32_to_cpu(ri->dsize));
 		if (ret) {
-			printk(KERN_WARNING "Error: jffs2_decompress returned %d\n", ret);
+			pr_warn("Error: jffs2_decompress returned %d\n", ret);
 			goto out_decomprbuf;
 		}
 	}
@@ -157,8 +161,8 @@ int jffs2_read_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 	struct jffs2_node_frag *frag;
 	int ret;
 
-	D1(printk(KERN_DEBUG "jffs2_read_inode_range: ino #%u, range 0x%08x-0x%08x\n",
-		  f->inocache->ino, offset, offset+len));
+	jffs2_dbg(1, "%s(): ino #%u, range 0x%08x-0x%08x\n",
+		  __func__, f->inocache->ino, offset, offset + len);
 
 	frag = jffs2_lookup_node_frag(&f->fragtree, offset);
 
@@ -168,22 +172,27 @@ int jffs2_read_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 	 * (or perhaps is before it, if we've been asked to read off the
 	 * end of the file). */
 	while(offset < end) {
-		D2(printk(KERN_DEBUG "jffs2_read_inode_range: offset %d, end %d\n", offset, end));
+		jffs2_dbg(2, "%s(): offset %d, end %d\n",
+			  __func__, offset, end);
 		if (unlikely(!frag || frag->ofs > offset ||
 			     frag->ofs + frag->size <= offset)) {
 			uint32_t holesize = end - offset;
 			if (frag && frag->ofs > offset) {
-				D1(printk(KERN_NOTICE "Eep. Hole in ino #%u fraglist. frag->ofs = 0x%08x, offset = 0x%08x\n", f->inocache->ino, frag->ofs, offset));
+				jffs2_dbg(1, "Eep. Hole in ino #%u fraglist. frag->ofs = 0x%08x, offset = 0x%08x\n",
+					  f->inocache->ino, frag->ofs, offset);
 				holesize = min(holesize, frag->ofs - offset);
 			}
-			D1(printk(KERN_DEBUG "Filling non-frag hole from %d-%d\n", offset, offset+holesize));
+			jffs2_dbg(1, "Filling non-frag hole from %d-%d\n",
+				  offset, offset + holesize);
 			memset(buf, 0, holesize);
 			buf += holesize;
 			offset += holesize;
 			continue;
 		} else if (unlikely(!frag->node)) {
 			uint32_t holeend = min(end, frag->ofs + frag->size);
-			D1(printk(KERN_DEBUG "Filling frag hole from %d-%d (frag 0x%x 0x%x)\n", offset, holeend, frag->ofs, frag->ofs + frag->size));
+			jffs2_dbg(1, "Filling frag hole from %d-%d (frag 0x%x 0x%x)\n",
+				  offset, holeend, frag->ofs,
+				  frag->ofs + frag->size);
 			memset(buf, 0, holeend - offset);
 			buf += holeend - offset;
 			offset = holeend;
@@ -195,20 +204,23 @@ int jffs2_read_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 
 			fragofs = offset - frag->ofs;
 			readlen = min(frag->size - fragofs, end - offset);
-			D1(printk(KERN_DEBUG "Reading %d-%d from node at 0x%08x (%d)\n",
-				  frag->ofs+fragofs, frag->ofs+fragofs+readlen,
-				  ref_offset(frag->node->raw), ref_flags(frag->node->raw)));
+			jffs2_dbg(1, "Reading %d-%d from node at 0x%08x (%d)\n",
+				  frag->ofs+fragofs,
+				  frag->ofs + fragofs+readlen,
+				  ref_offset(frag->node->raw),
+				  ref_flags(frag->node->raw));
 			ret = jffs2_read_dnode(c, f, frag->node, buf, fragofs + frag->ofs - frag->node->ofs, readlen);
-			D2(printk(KERN_DEBUG "node read done\n"));
+			jffs2_dbg(2, "node read done\n");
 			if (ret) {
-				D1(printk(KERN_DEBUG"jffs2_read_inode_range error %d\n",ret));
+				jffs2_dbg(1, "%s(): error %d\n",
+					  __func__, ret);
 				memset(buf, 0, readlen);
 				return ret;
 			}
 			buf += readlen;
 			offset += readlen;
 			frag = frag_next(frag);
-			D2(printk(KERN_DEBUG "node read was OK. Looping\n"));
+			jffs2_dbg(2, "node read was OK. Looping\n");
 		}
 	}
 	return 0;
diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c
index 3093ac4fb24c..dc0437e84763 100644
--- a/fs/jffs2/readinode.c
+++ b/fs/jffs2/readinode.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c
index f99464833bb2..7654e87b0428 100644
--- a/fs/jffs2/scan.c
+++ b/fs/jffs2/scan.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -22,15 +24,15 @@
 
 #define DEFAULT_EMPTY_SCAN_SIZE 256
 
-#define noisy_printk(noise, args...) do { \
-	if (*(noise)) { \
-		printk(KERN_NOTICE args); \
-		 (*(noise))--; \
-		 if (!(*(noise))) { \
-			 printk(KERN_NOTICE "Further such events for this erase block will not be printed\n"); \
-		 } \
-	} \
-} while(0)
+#define noisy_printk(noise, fmt, ...)					\
+do {									\
+	if (*(noise)) {							\
+		pr_notice(fmt, ##__VA_ARGS__);				\
+		(*(noise))--;						\
+		if (!(*(noise)))					\
+			pr_notice("Further such events for this erase block will not be printed\n"); \
+	}								\
+} while (0)
 
 static uint32_t pseudo_random;
 
@@ -96,18 +98,17 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
 #ifndef __ECOS
 	size_t pointlen, try_size;
 
-	if (c->mtd->point) {
-		ret = mtd_point(c->mtd, 0, c->mtd->size, &pointlen,
-				(void **)&flashbuf, NULL);
-		if (!ret && pointlen < c->mtd->size) {
-			/* Don't muck about if it won't let us point to the whole flash */
-			D1(printk(KERN_DEBUG "MTD point returned len too short: 0x%zx\n", pointlen));
-			mtd_unpoint(c->mtd, 0, pointlen);
-			flashbuf = NULL;
-		}
-		if (ret && ret != -EOPNOTSUPP)
-			D1(printk(KERN_DEBUG "MTD point failed %d\n", ret));
+	ret = mtd_point(c->mtd, 0, c->mtd->size, &pointlen,
+			(void **)&flashbuf, NULL);
+	if (!ret && pointlen < c->mtd->size) {
+		/* Don't muck about if it won't let us point to the whole flash */
+		jffs2_dbg(1, "MTD point returned len too short: 0x%zx\n",
+			  pointlen);
+		mtd_unpoint(c->mtd, 0, pointlen);
+		flashbuf = NULL;
 	}
+	if (ret && ret != -EOPNOTSUPP)
+		jffs2_dbg(1, "MTD point failed %d\n", ret);
 #endif
 	if (!flashbuf) {
 		/* For NAND it's quicker to read a whole eraseblock at a time,
@@ -117,15 +118,15 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
 		else
 			try_size = PAGE_SIZE;
 
-		D1(printk(KERN_DEBUG "Trying to allocate readbuf of %zu "
-			"bytes\n", try_size));
+		jffs2_dbg(1, "Trying to allocate readbuf of %zu "
+			  "bytes\n", try_size);
 
 		flashbuf = mtd_kmalloc_up_to(c->mtd, &try_size);
 		if (!flashbuf)
 			return -ENOMEM;
 
-		D1(printk(KERN_DEBUG "Allocated readbuf of %zu bytes\n",
-			try_size));
+		jffs2_dbg(1, "Allocated readbuf of %zu bytes\n",
+			  try_size);
 
 		buf_size = (uint32_t)try_size;
 	}
@@ -178,7 +179,8 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
 				c->nr_free_blocks++;
 			} else {
 				/* Dirt */
-				D1(printk(KERN_DEBUG "Adding all-dirty block at 0x%08x to erase_pending_list\n", jeb->offset));
+				jffs2_dbg(1, "Adding all-dirty block at 0x%08x to erase_pending_list\n",
+					  jeb->offset);
 				list_add(&jeb->list, &c->erase_pending_list);
 				c->nr_erasing_blocks++;
 			}
@@ -205,7 +207,8 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
 				}
 				/* update collected summary information for the current nextblock */
 				jffs2_sum_move_collected(c, s);
-				D1(printk(KERN_DEBUG "jffs2_scan_medium(): new nextblock = 0x%08x\n", jeb->offset));
+				jffs2_dbg(1, "%s(): new nextblock = 0x%08x\n",
+					  __func__, jeb->offset);
 				c->nextblock = jeb;
 			} else {
 				ret = file_dirty(c, jeb);
@@ -217,20 +220,21 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
 		case BLK_STATE_ALLDIRTY:
 			/* Nothing valid - not even a clean marker. Needs erasing. */
 			/* For now we just put it on the erasing list. We'll start the erases later */
-			D1(printk(KERN_NOTICE "JFFS2: Erase block at 0x%08x is not formatted. It will be erased\n", jeb->offset));
+			jffs2_dbg(1, "Erase block at 0x%08x is not formatted. It will be erased\n",
+				  jeb->offset);
 			list_add(&jeb->list, &c->erase_pending_list);
 			c->nr_erasing_blocks++;
 			break;
 
 		case BLK_STATE_BADBLOCK:
-			D1(printk(KERN_NOTICE "JFFS2: Block at 0x%08x is bad\n", jeb->offset));
+			jffs2_dbg(1, "Block at 0x%08x is bad\n", jeb->offset);
 			list_add(&jeb->list, &c->bad_list);
 			c->bad_size += c->sector_size;
 			c->free_size -= c->sector_size;
 			bad_blocks++;
 			break;
 		default:
-			printk(KERN_WARNING "jffs2_scan_medium(): unknown block state\n");
+			pr_warn("%s(): unknown block state\n", __func__);
 			BUG();
 		}
 	}
@@ -250,16 +254,17 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
 
 		uint32_t skip = c->nextblock->free_size % c->wbuf_pagesize;
 
-		D1(printk(KERN_DEBUG "jffs2_scan_medium(): Skipping %d bytes in nextblock to ensure page alignment\n",
-			  skip));
+		jffs2_dbg(1, "%s(): Skipping %d bytes in nextblock to ensure page alignment\n",
+			  __func__, skip);
 		jffs2_prealloc_raw_node_refs(c, c->nextblock, 1);
 		jffs2_scan_dirty_space(c, c->nextblock, skip);
 	}
 #endif
 	if (c->nr_erasing_blocks) {
 		if ( !c->used_size && ((c->nr_free_blocks+empty_blocks+bad_blocks)!= c->nr_blocks || bad_blocks == c->nr_blocks) ) {
-			printk(KERN_NOTICE "Cowardly refusing to erase blocks on filesystem with no valid JFFS2 nodes\n");
-			printk(KERN_NOTICE "empty_blocks %d, bad_blocks %d, c->nr_blocks %d\n",empty_blocks,bad_blocks,c->nr_blocks);
+			pr_notice("Cowardly refusing to erase blocks on filesystem with no valid JFFS2 nodes\n");
+			pr_notice("empty_blocks %d, bad_blocks %d, c->nr_blocks %d\n",
+				  empty_blocks, bad_blocks, c->nr_blocks);
 			ret = -EIO;
 			goto out;
 		}
@@ -287,11 +292,13 @@ static int jffs2_fill_scan_buf(struct jffs2_sb_info *c, void *buf,
 
 	ret = jffs2_flash_read(c, ofs, len, &retlen, buf);
 	if (ret) {
-		D1(printk(KERN_WARNING "mtd->read(0x%x bytes from 0x%x) returned %d\n", len, ofs, ret));
+		jffs2_dbg(1, "mtd->read(0x%x bytes from 0x%x) returned %d\n",
+			  len, ofs, ret);
 		return ret;
 	}
 	if (retlen < len) {
-		D1(printk(KERN_WARNING "Read at 0x%x gave only 0x%zx bytes\n", ofs, retlen));
+		jffs2_dbg(1, "Read at 0x%x gave only 0x%zx bytes\n",
+			  ofs, retlen);
 		return -EIO;
 	}
 	return 0;
@@ -368,7 +375,7 @@ static int jffs2_scan_xattr_node(struct jffs2_sb_info *c, struct jffs2_erasebloc
 
 	if (jffs2_sum_active())
 		jffs2_sum_add_xattr_mem(s, rx, ofs - jeb->offset);
-	dbg_xattr("scaning xdatum at %#08x (xid=%u, version=%u)\n",
+	dbg_xattr("scanning xdatum at %#08x (xid=%u, version=%u)\n",
 		  ofs, xd->xid, xd->version);
 	return 0;
 }
@@ -449,7 +456,7 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo
 	ofs = jeb->offset;
 	prevofs = jeb->offset - 1;
 
-	D1(printk(KERN_DEBUG "jffs2_scan_eraseblock(): Scanning block at 0x%x\n", ofs));
+	jffs2_dbg(1, "%s(): Scanning block at 0x%x\n", __func__, ofs);
 
 #ifdef CONFIG_JFFS2_FS_WRITEBUFFER
 	if (jffs2_cleanmarker_oob(c)) {
@@ -459,7 +466,7 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo
 			return BLK_STATE_BADBLOCK;
 
 		ret = jffs2_check_nand_cleanmarker(c, jeb);
-		D2(printk(KERN_NOTICE "jffs_check_nand_cleanmarker returned %d\n",ret));
+		jffs2_dbg(2, "jffs_check_nand_cleanmarker returned %d\n", ret);
 
 		/* Even if it's not found, we still scan to see
 		   if the block is empty. We use this information
@@ -561,7 +568,8 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo
 		if (jffs2_cleanmarker_oob(c)) {
 			/* scan oob, take care of cleanmarker */
 			int ret = jffs2_check_oob_empty(c, jeb, cleanmarkerfound);
-			D2(printk(KERN_NOTICE "jffs2_check_oob_empty returned %d\n",ret));
+			jffs2_dbg(2, "jffs2_check_oob_empty returned %d\n",
+				  ret);
 			switch (ret) {
 			case 0:		return cleanmarkerfound ? BLK_STATE_CLEANMARKER : BLK_STATE_ALLFF;
 			case 1: 	return BLK_STATE_ALLDIRTY;
@@ -569,15 +577,16 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo
 			}
 		}
 #endif
-		D1(printk(KERN_DEBUG "Block at 0x%08x is empty (erased)\n", jeb->offset));
+		jffs2_dbg(1, "Block at 0x%08x is empty (erased)\n",
+			  jeb->offset);
 		if (c->cleanmarker_size == 0)
 			return BLK_STATE_CLEANMARKER;	/* don't bother with re-erase */
 		else
 			return BLK_STATE_ALLFF;	/* OK to erase if all blocks are like this */
 	}
 	if (ofs) {
-		D1(printk(KERN_DEBUG "Free space at %08x ends at %08x\n", jeb->offset,
-			  jeb->offset + ofs));
+		jffs2_dbg(1, "Free space at %08x ends at %08x\n", jeb->offset,
+			  jeb->offset + ofs);
 		if ((err = jffs2_prealloc_raw_node_refs(c, jeb, 1)))
 			return err;
 		if ((err = jffs2_scan_dirty_space(c, jeb, ofs)))
@@ -604,12 +613,13 @@ scan_more:
 		cond_resched();
 
 		if (ofs & 3) {
-			printk(KERN_WARNING "Eep. ofs 0x%08x not word-aligned!\n", ofs);
+			pr_warn("Eep. ofs 0x%08x not word-aligned!\n", ofs);
 			ofs = PAD(ofs);
 			continue;
 		}
 		if (ofs == prevofs) {
-			printk(KERN_WARNING "ofs 0x%08x has already been seen. Skipping\n", ofs);
+			pr_warn("ofs 0x%08x has already been seen. Skipping\n",
+				ofs);
 			if ((err = jffs2_scan_dirty_space(c, jeb, 4)))
 				return err;
 			ofs += 4;
@@ -618,8 +628,10 @@ scan_more:
 		prevofs = ofs;
 
 		if (jeb->offset + c->sector_size < ofs + sizeof(*node)) {
-			D1(printk(KERN_DEBUG "Fewer than %zd bytes left to end of block. (%x+%x<%x+%zx) Not reading\n", sizeof(struct jffs2_unknown_node),
-				  jeb->offset, c->sector_size, ofs, sizeof(*node)));
+			jffs2_dbg(1, "Fewer than %zd bytes left to end of block. (%x+%x<%x+%zx) Not reading\n",
+				  sizeof(struct jffs2_unknown_node),
+				  jeb->offset, c->sector_size, ofs,
+				  sizeof(*node));
 			if ((err = jffs2_scan_dirty_space(c, jeb, (jeb->offset + c->sector_size)-ofs)))
 				return err;
 			break;
@@ -627,8 +639,9 @@ scan_more:
 
 		if (buf_ofs + buf_len < ofs + sizeof(*node)) {
 			buf_len = min_t(uint32_t, buf_size, jeb->offset + c->sector_size - ofs);
-			D1(printk(KERN_DEBUG "Fewer than %zd bytes (node header) left to end of buf. Reading 0x%x at 0x%08x\n",
-				  sizeof(struct jffs2_unknown_node), buf_len, ofs));
+			jffs2_dbg(1, "Fewer than %zd bytes (node header) left to end of buf. Reading 0x%x at 0x%08x\n",
+				  sizeof(struct jffs2_unknown_node),
+				  buf_len, ofs);
 			err = jffs2_fill_scan_buf(c, buf, ofs, buf_len);
 			if (err)
 				return err;
@@ -645,13 +658,13 @@ scan_more:
 			ofs += 4;
 			scan_end = min_t(uint32_t, EMPTY_SCAN_SIZE(c->sector_size)/8, buf_len);
 
-			D1(printk(KERN_DEBUG "Found empty flash at 0x%08x\n", ofs));
+			jffs2_dbg(1, "Found empty flash at 0x%08x\n", ofs);
 		more_empty:
 			inbuf_ofs = ofs - buf_ofs;
 			while (inbuf_ofs < scan_end) {
 				if (unlikely(*(uint32_t *)(&buf[inbuf_ofs]) != 0xffffffff)) {
-					printk(KERN_WARNING "Empty flash at 0x%08x ends at 0x%08x\n",
-					       empty_start, ofs);
+					pr_warn("Empty flash at 0x%08x ends at 0x%08x\n",
+						empty_start, ofs);
 					if ((err = jffs2_scan_dirty_space(c, jeb, ofs-empty_start)))
 						return err;
 					goto scan_more;
@@ -661,13 +674,15 @@ scan_more:
 				ofs += 4;
 			}
 			/* Ran off end. */
-			D1(printk(KERN_DEBUG "Empty flash to end of buffer at 0x%08x\n", ofs));
+			jffs2_dbg(1, "Empty flash to end of buffer at 0x%08x\n",
+				  ofs);
 
 			/* If we're only checking the beginning of a block with a cleanmarker,
 			   bail now */
 			if (buf_ofs == jeb->offset && jeb->used_size == PAD(c->cleanmarker_size) &&
 			    c->cleanmarker_size && !jeb->dirty_size && !ref_next(jeb->first_node)) {
-				D1(printk(KERN_DEBUG "%d bytes at start of block seems clean... assuming all clean\n", EMPTY_SCAN_SIZE(c->sector_size)));
+				jffs2_dbg(1, "%d bytes at start of block seems clean... assuming all clean\n",
+					  EMPTY_SCAN_SIZE(c->sector_size));
 				return BLK_STATE_CLEANMARKER;
 			}
 			if (!buf_size && (scan_end != buf_len)) {/* XIP/point case */
@@ -680,13 +695,14 @@ scan_more:
 			if (!buf_len) {
 				/* No more to read. Break out of main loop without marking
 				   this range of empty space as dirty (because it's not) */
-				D1(printk(KERN_DEBUG "Empty flash at %08x runs to end of block. Treating as free_space\n",
-					  empty_start));
+				jffs2_dbg(1, "Empty flash at %08x runs to end of block. Treating as free_space\n",
+					  empty_start);
 				break;
 			}
 			/* point never reaches here */
 			scan_end = buf_len;
-			D1(printk(KERN_DEBUG "Reading another 0x%x at 0x%08x\n", buf_len, ofs));
+			jffs2_dbg(1, "Reading another 0x%x at 0x%08x\n",
+				  buf_len, ofs);
 			err = jffs2_fill_scan_buf(c, buf, ofs, buf_len);
 			if (err)
 				return err;
@@ -695,22 +711,23 @@ scan_more:
 		}
 
 		if (ofs == jeb->offset && je16_to_cpu(node->magic) == KSAMTIB_CIGAM_2SFFJ) {
-			printk(KERN_WARNING "Magic bitmask is backwards at offset 0x%08x. Wrong endian filesystem?\n", ofs);
+			pr_warn("Magic bitmask is backwards at offset 0x%08x. Wrong endian filesystem?\n",
+				ofs);
 			if ((err = jffs2_scan_dirty_space(c, jeb, 4)))
 				return err;
 			ofs += 4;
 			continue;
 		}
 		if (je16_to_cpu(node->magic) == JFFS2_DIRTY_BITMASK) {
-			D1(printk(KERN_DEBUG "Dirty bitmask at 0x%08x\n", ofs));
+			jffs2_dbg(1, "Dirty bitmask at 0x%08x\n", ofs);
 			if ((err = jffs2_scan_dirty_space(c, jeb, 4)))
 				return err;
 			ofs += 4;
 			continue;
 		}
 		if (je16_to_cpu(node->magic) == JFFS2_OLD_MAGIC_BITMASK) {
-			printk(KERN_WARNING "Old JFFS2 bitmask found at 0x%08x\n", ofs);
-			printk(KERN_WARNING "You cannot use older JFFS2 filesystems with newer kernels\n");
+			pr_warn("Old JFFS2 bitmask found at 0x%08x\n", ofs);
+			pr_warn("You cannot use older JFFS2 filesystems with newer kernels\n");
 			if ((err = jffs2_scan_dirty_space(c, jeb, 4)))
 				return err;
 			ofs += 4;
@@ -718,7 +735,8 @@ scan_more:
 		}
 		if (je16_to_cpu(node->magic) != JFFS2_MAGIC_BITMASK) {
 			/* OK. We're out of possibilities. Whinge and move on */
-			noisy_printk(&noise, "jffs2_scan_eraseblock(): Magic bitmask 0x%04x not found at 0x%08x: 0x%04x instead\n",
+			noisy_printk(&noise, "%s(): Magic bitmask 0x%04x not found at 0x%08x: 0x%04x instead\n",
+				     __func__,
 				     JFFS2_MAGIC_BITMASK, ofs,
 				     je16_to_cpu(node->magic));
 			if ((err = jffs2_scan_dirty_space(c, jeb, 4)))
@@ -733,7 +751,8 @@ scan_more:
 		hdr_crc = crc32(0, &crcnode, sizeof(crcnode)-4);
 
 		if (hdr_crc != je32_to_cpu(node->hdr_crc)) {
-			noisy_printk(&noise, "jffs2_scan_eraseblock(): Node at 0x%08x {0x%04x, 0x%04x, 0x%08x) has invalid CRC 0x%08x (calculated 0x%08x)\n",
+			noisy_printk(&noise, "%s(): Node at 0x%08x {0x%04x, 0x%04x, 0x%08x) has invalid CRC 0x%08x (calculated 0x%08x)\n",
+				     __func__,
 				     ofs, je16_to_cpu(node->magic),
 				     je16_to_cpu(node->nodetype),
 				     je32_to_cpu(node->totlen),
@@ -747,9 +766,9 @@ scan_more:
 
 		if (ofs + je32_to_cpu(node->totlen) > jeb->offset + c->sector_size) {
 			/* Eep. Node goes over the end of the erase block. */
-			printk(KERN_WARNING "Node at 0x%08x with length 0x%08x would run over the end of the erase block\n",
-			       ofs, je32_to_cpu(node->totlen));
-			printk(KERN_WARNING "Perhaps the file system was created with the wrong erase size?\n");
+			pr_warn("Node at 0x%08x with length 0x%08x would run over the end of the erase block\n",
+				ofs, je32_to_cpu(node->totlen));
+			pr_warn("Perhaps the file system was created with the wrong erase size?\n");
 			if ((err = jffs2_scan_dirty_space(c, jeb, 4)))
 				return err;
 			ofs += 4;
@@ -758,7 +777,8 @@ scan_more:
 
 		if (!(je16_to_cpu(node->nodetype) & JFFS2_NODE_ACCURATE)) {
 			/* Wheee. This is an obsoleted node */
-			D2(printk(KERN_DEBUG "Node at 0x%08x is obsolete. Skipping\n", ofs));
+			jffs2_dbg(2, "Node at 0x%08x is obsolete. Skipping\n",
+				  ofs);
 			if ((err = jffs2_scan_dirty_space(c, jeb, PAD(je32_to_cpu(node->totlen)))))
 				return err;
 			ofs += PAD(je32_to_cpu(node->totlen));
@@ -769,8 +789,9 @@ scan_more:
 		case JFFS2_NODETYPE_INODE:
 			if (buf_ofs + buf_len < ofs + sizeof(struct jffs2_raw_inode)) {
 				buf_len = min_t(uint32_t, buf_size, jeb->offset + c->sector_size - ofs);
-				D1(printk(KERN_DEBUG "Fewer than %zd bytes (inode node) left to end of buf. Reading 0x%x at 0x%08x\n",
-					  sizeof(struct jffs2_raw_inode), buf_len, ofs));
+				jffs2_dbg(1, "Fewer than %zd bytes (inode node) left to end of buf. Reading 0x%x at 0x%08x\n",
+					  sizeof(struct jffs2_raw_inode),
+					  buf_len, ofs);
 				err = jffs2_fill_scan_buf(c, buf, ofs, buf_len);
 				if (err)
 					return err;
@@ -785,8 +806,9 @@ scan_more:
 		case JFFS2_NODETYPE_DIRENT:
 			if (buf_ofs + buf_len < ofs + je32_to_cpu(node->totlen)) {
 				buf_len = min_t(uint32_t, buf_size, jeb->offset + c->sector_size - ofs);
-				D1(printk(KERN_DEBUG "Fewer than %d bytes (dirent node) left to end of buf. Reading 0x%x at 0x%08x\n",
-					  je32_to_cpu(node->totlen), buf_len, ofs));
+				jffs2_dbg(1, "Fewer than %d bytes (dirent node) left to end of buf. Reading 0x%x at 0x%08x\n",
+					  je32_to_cpu(node->totlen), buf_len,
+					  ofs);
 				err = jffs2_fill_scan_buf(c, buf, ofs, buf_len);
 				if (err)
 					return err;
@@ -802,9 +824,9 @@ scan_more:
 		case JFFS2_NODETYPE_XATTR:
 			if (buf_ofs + buf_len < ofs + je32_to_cpu(node->totlen)) {
 				buf_len = min_t(uint32_t, buf_size, jeb->offset + c->sector_size - ofs);
-				D1(printk(KERN_DEBUG "Fewer than %d bytes (xattr node)"
-					  " left to end of buf. Reading 0x%x at 0x%08x\n",
-					  je32_to_cpu(node->totlen), buf_len, ofs));
+				jffs2_dbg(1, "Fewer than %d bytes (xattr node) left to end of buf. Reading 0x%x at 0x%08x\n",
+					  je32_to_cpu(node->totlen), buf_len,
+					  ofs);
 				err = jffs2_fill_scan_buf(c, buf, ofs, buf_len);
 				if (err)
 					return err;
@@ -819,9 +841,9 @@ scan_more:
 		case JFFS2_NODETYPE_XREF:
 			if (buf_ofs + buf_len < ofs + je32_to_cpu(node->totlen)) {
 				buf_len = min_t(uint32_t, buf_size, jeb->offset + c->sector_size - ofs);
-				D1(printk(KERN_DEBUG "Fewer than %d bytes (xref node)"
-					  " left to end of buf. Reading 0x%x at 0x%08x\n",
-					  je32_to_cpu(node->totlen), buf_len, ofs));
+				jffs2_dbg(1, "Fewer than %d bytes (xref node) left to end of buf. Reading 0x%x at 0x%08x\n",
+					  je32_to_cpu(node->totlen), buf_len,
+					  ofs);
 				err = jffs2_fill_scan_buf(c, buf, ofs, buf_len);
 				if (err)
 					return err;
@@ -836,15 +858,17 @@ scan_more:
 #endif	/* CONFIG_JFFS2_FS_XATTR */
 
 		case JFFS2_NODETYPE_CLEANMARKER:
-			D1(printk(KERN_DEBUG "CLEANMARKER node found at 0x%08x\n", ofs));
+			jffs2_dbg(1, "CLEANMARKER node found at 0x%08x\n", ofs);
 			if (je32_to_cpu(node->totlen) != c->cleanmarker_size) {
-				printk(KERN_NOTICE "CLEANMARKER node found at 0x%08x has totlen 0x%x != normal 0x%x\n",
-				       ofs, je32_to_cpu(node->totlen), c->cleanmarker_size);
+				pr_notice("CLEANMARKER node found at 0x%08x has totlen 0x%x != normal 0x%x\n",
+					  ofs, je32_to_cpu(node->totlen),
+					  c->cleanmarker_size);
 				if ((err = jffs2_scan_dirty_space(c, jeb, PAD(sizeof(struct jffs2_unknown_node)))))
 					return err;
 				ofs += PAD(sizeof(struct jffs2_unknown_node));
 			} else if (jeb->first_node) {
-				printk(KERN_NOTICE "CLEANMARKER node found at 0x%08x, not first node in block (0x%08x)\n", ofs, jeb->offset);
+				pr_notice("CLEANMARKER node found at 0x%08x, not first node in block (0x%08x)\n",
+					  ofs, jeb->offset);
 				if ((err = jffs2_scan_dirty_space(c, jeb, PAD(sizeof(struct jffs2_unknown_node)))))
 					return err;
 				ofs += PAD(sizeof(struct jffs2_unknown_node));
@@ -866,7 +890,8 @@ scan_more:
 		default:
 			switch (je16_to_cpu(node->nodetype) & JFFS2_COMPAT_MASK) {
 			case JFFS2_FEATURE_ROCOMPAT:
-				printk(KERN_NOTICE "Read-only compatible feature node (0x%04x) found at offset 0x%08x\n", je16_to_cpu(node->nodetype), ofs);
+				pr_notice("Read-only compatible feature node (0x%04x) found at offset 0x%08x\n",
+					  je16_to_cpu(node->nodetype), ofs);
 				c->flags |= JFFS2_SB_FLAG_RO;
 				if (!(jffs2_is_readonly(c)))
 					return -EROFS;
@@ -876,18 +901,21 @@ scan_more:
 				break;
 
 			case JFFS2_FEATURE_INCOMPAT:
-				printk(KERN_NOTICE "Incompatible feature node (0x%04x) found at offset 0x%08x\n", je16_to_cpu(node->nodetype), ofs);
+				pr_notice("Incompatible feature node (0x%04x) found at offset 0x%08x\n",
+					  je16_to_cpu(node->nodetype), ofs);
 				return -EINVAL;
 
 			case JFFS2_FEATURE_RWCOMPAT_DELETE:
-				D1(printk(KERN_NOTICE "Unknown but compatible feature node (0x%04x) found at offset 0x%08x\n", je16_to_cpu(node->nodetype), ofs));
+				jffs2_dbg(1, "Unknown but compatible feature node (0x%04x) found at offset 0x%08x\n",
+					  je16_to_cpu(node->nodetype), ofs);
 				if ((err = jffs2_scan_dirty_space(c, jeb, PAD(je32_to_cpu(node->totlen)))))
 					return err;
 				ofs += PAD(je32_to_cpu(node->totlen));
 				break;
 
 			case JFFS2_FEATURE_RWCOMPAT_COPY: {
-				D1(printk(KERN_NOTICE "Unknown but compatible feature node (0x%04x) found at offset 0x%08x\n", je16_to_cpu(node->nodetype), ofs));
+				jffs2_dbg(1, "Unknown but compatible feature node (0x%04x) found at offset 0x%08x\n",
+					  je16_to_cpu(node->nodetype), ofs);
 
 				jffs2_link_node_ref(c, jeb, ofs | REF_PRISTINE, PAD(je32_to_cpu(node->totlen)), NULL);
 
@@ -908,8 +936,9 @@ scan_more:
 		}
 	}
 
-	D1(printk(KERN_DEBUG "Block at 0x%08x: free 0x%08x, dirty 0x%08x, unchecked 0x%08x, used 0x%08x, wasted 0x%08x\n",
-		  jeb->offset,jeb->free_size, jeb->dirty_size, jeb->unchecked_size, jeb->used_size, jeb->wasted_size));
+	jffs2_dbg(1, "Block at 0x%08x: free 0x%08x, dirty 0x%08x, unchecked 0x%08x, used 0x%08x, wasted 0x%08x\n",
+		  jeb->offset, jeb->free_size, jeb->dirty_size,
+		  jeb->unchecked_size, jeb->used_size, jeb->wasted_size);
 	
 	/* mark_node_obsolete can add to wasted !! */
 	if (jeb->wasted_size) {
@@ -935,7 +964,7 @@ struct jffs2_inode_cache *jffs2_scan_make_ino_cache(struct jffs2_sb_info *c, uin
 
 	ic = jffs2_alloc_inode_cache();
 	if (!ic) {
-		printk(KERN_NOTICE "jffs2_scan_make_inode_cache(): allocation of inode cache failed\n");
+		pr_notice("%s(): allocation of inode cache failed\n", __func__);
 		return NULL;
 	}
 	memset(ic, 0, sizeof(*ic));
@@ -954,7 +983,7 @@ static int jffs2_scan_inode_node(struct jffs2_sb_info *c, struct jffs2_erasebloc
 	struct jffs2_inode_cache *ic;
 	uint32_t crc, ino = je32_to_cpu(ri->ino);
 
-	D1(printk(KERN_DEBUG "jffs2_scan_inode_node(): Node at 0x%08x\n", ofs));
+	jffs2_dbg(1, "%s(): Node at 0x%08x\n", __func__, ofs);
 
 	/* We do very little here now. Just check the ino# to which we should attribute
 	   this node; we can do all the CRC checking etc. later. There's a tradeoff here --
@@ -968,9 +997,8 @@ static int jffs2_scan_inode_node(struct jffs2_sb_info *c, struct jffs2_erasebloc
 	/* Check the node CRC in any case. */
 	crc = crc32(0, ri, sizeof(*ri)-8);
 	if (crc != je32_to_cpu(ri->node_crc)) {
-		printk(KERN_NOTICE "jffs2_scan_inode_node(): CRC failed on "
-		       "node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
-		       ofs, je32_to_cpu(ri->node_crc), crc);
+		pr_notice("%s(): CRC failed on node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
+			  __func__, ofs, je32_to_cpu(ri->node_crc), crc);
 		/*
 		 * We believe totlen because the CRC on the node
 		 * _header_ was OK, just the node itself failed.
@@ -989,10 +1017,10 @@ static int jffs2_scan_inode_node(struct jffs2_sb_info *c, struct jffs2_erasebloc
 	/* Wheee. It worked */
 	jffs2_link_node_ref(c, jeb, ofs | REF_UNCHECKED, PAD(je32_to_cpu(ri->totlen)), ic);
 
-	D1(printk(KERN_DEBUG "Node is ino #%u, version %d. Range 0x%x-0x%x\n",
+	jffs2_dbg(1, "Node is ino #%u, version %d. Range 0x%x-0x%x\n",
 		  je32_to_cpu(ri->ino), je32_to_cpu(ri->version),
 		  je32_to_cpu(ri->offset),
-		  je32_to_cpu(ri->offset)+je32_to_cpu(ri->dsize)));
+		  je32_to_cpu(ri->offset)+je32_to_cpu(ri->dsize));
 
 	pseudo_random += je32_to_cpu(ri->version);
 
@@ -1012,15 +1040,15 @@ static int jffs2_scan_dirent_node(struct jffs2_sb_info *c, struct jffs2_eraseblo
 	uint32_t crc;
 	int err;
 
-	D1(printk(KERN_DEBUG "jffs2_scan_dirent_node(): Node at 0x%08x\n", ofs));
+	jffs2_dbg(1, "%s(): Node at 0x%08x\n", __func__, ofs);
 
 	/* We don't get here unless the node is still valid, so we don't have to
 	   mask in the ACCURATE bit any more. */
 	crc = crc32(0, rd, sizeof(*rd)-8);
 
 	if (crc != je32_to_cpu(rd->node_crc)) {
-		printk(KERN_NOTICE "jffs2_scan_dirent_node(): Node CRC failed on node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
-		       ofs, je32_to_cpu(rd->node_crc), crc);
+		pr_notice("%s(): Node CRC failed on node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
+			  __func__, ofs, je32_to_cpu(rd->node_crc), crc);
 		/* We believe totlen because the CRC on the node _header_ was OK, just the node itself failed. */
 		if ((err = jffs2_scan_dirty_space(c, jeb, PAD(je32_to_cpu(rd->totlen)))))
 			return err;
@@ -1032,7 +1060,7 @@ static int jffs2_scan_dirent_node(struct jffs2_sb_info *c, struct jffs2_eraseblo
 	/* Should never happen. Did. (OLPC trac #4184)*/
 	checkedlen = strnlen(rd->name, rd->nsize);
 	if (checkedlen < rd->nsize) {
-		printk(KERN_ERR "Dirent at %08x has zeroes in name. Truncating to %d chars\n",
+		pr_err("Dirent at %08x has zeroes in name. Truncating to %d chars\n",
 		       ofs, checkedlen);
 	}
 	fd = jffs2_alloc_full_dirent(checkedlen+1);
@@ -1044,9 +1072,10 @@ static int jffs2_scan_dirent_node(struct jffs2_sb_info *c, struct jffs2_eraseblo
 
 	crc = crc32(0, fd->name, rd->nsize);
 	if (crc != je32_to_cpu(rd->name_crc)) {
-		printk(KERN_NOTICE "jffs2_scan_dirent_node(): Name CRC failed on node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
-		       ofs, je32_to_cpu(rd->name_crc), crc);
-		D1(printk(KERN_NOTICE "Name for which CRC failed is (now) '%s', ino #%d\n", fd->name, je32_to_cpu(rd->ino)));
+		pr_notice("%s(): Name CRC failed on node at 0x%08x: Read 0x%08x, calculated 0x%08x\n",
+			  __func__, ofs, je32_to_cpu(rd->name_crc), crc);
+		jffs2_dbg(1, "Name for which CRC failed is (now) '%s', ino #%d\n",
+			  fd->name, je32_to_cpu(rd->ino));
 		jffs2_free_full_dirent(fd);
 		/* FIXME: Why do we believe totlen? */
 		/* We believe totlen because the CRC on the node _header_ was OK, just the name failed. */
diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c
index 0f20208df602..aca97f35b292 100644
--- a/fs/jffs2/security.c
+++ b/fs/jffs2/security.c
@@ -23,8 +23,8 @@
 #include "nodelist.h"
 
 /* ---- Initial Security Label(s) Attachment callback --- */
-int jffs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
-		     void *fs_info)
+static int jffs2_initxattrs(struct inode *inode,
+			    const struct xattr *xattr_array, void *fs_info)
 {
 	const struct xattr *xattr;
 	int err = 0;
diff --git a/fs/jffs2/summary.c b/fs/jffs2/summary.c
index e537fb0e0184..c522d098bb4f 100644
--- a/fs/jffs2/summary.c
+++ b/fs/jffs2/summary.c
@@ -11,6 +11,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mtd/mtd.h>
@@ -442,13 +444,16 @@ static int jffs2_sum_process_sum_data(struct jffs2_sb_info *c, struct jffs2_eras
 				/* This should never happen, but https://dev.laptop.org/ticket/4184 */
 				checkedlen = strnlen(spd->name, spd->nsize);
 				if (!checkedlen) {
-					printk(KERN_ERR "Dirent at %08x has zero at start of name. Aborting mount.\n",
-					       jeb->offset + je32_to_cpu(spd->offset));
+					pr_err("Dirent at %08x has zero at start of name. Aborting mount.\n",
+					       jeb->offset +
+					       je32_to_cpu(spd->offset));
 					return -EIO;
 				}
 				if (checkedlen < spd->nsize) {
-					printk(KERN_ERR "Dirent at %08x has zeroes in name. Truncating to %d chars\n",
-					       jeb->offset + je32_to_cpu(spd->offset), checkedlen);
+					pr_err("Dirent at %08x has zeroes in name. Truncating to %d chars\n",
+					       jeb->offset +
+					       je32_to_cpu(spd->offset),
+					       checkedlen);
 				}
 
 
@@ -808,8 +813,7 @@ static int jffs2_sum_write_data(struct jffs2_sb_info *c, struct jffs2_eraseblock
 
 	sum_ofs = jeb->offset + c->sector_size - jeb->free_size;
 
-	dbg_summary("JFFS2: writing out data to flash to pos : 0x%08x\n",
-		    sum_ofs);
+	dbg_summary("writing out data to flash to pos : 0x%08x\n", sum_ofs);
 
 	ret = jffs2_flash_writev(c, vecs, 2, sum_ofs, &retlen, 0);
 
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index f2d96b5e64f6..f9916f312bd8 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -69,7 +71,7 @@ static void jffs2_write_super(struct super_block *sb)
 	sb->s_dirt = 0;
 
 	if (!(sb->s_flags & MS_RDONLY)) {
-		D1(printk(KERN_DEBUG "jffs2_write_super()\n"));
+		jffs2_dbg(1, "%s()\n", __func__);
 		jffs2_flush_wbuf_gc(c, 0);
 	}
 
@@ -214,8 +216,8 @@ static int jffs2_parse_options(struct jffs2_sb_info *c, char *data)
 						JFFS2_COMPR_MODE_FORCEZLIB;
 #endif
 			else {
-				printk(KERN_ERR "JFFS2 Error: unknown compressor \"%s\"",
-						name);
+				pr_err("Error: unknown compressor \"%s\"\n",
+				       name);
 				kfree(name);
 				return -EINVAL;
 			}
@@ -223,8 +225,8 @@ static int jffs2_parse_options(struct jffs2_sb_info *c, char *data)
 			c->mount_opts.override_compr = true;
 			break;
 		default:
-			printk(KERN_ERR "JFFS2 Error: unrecognized mount option '%s' or missing value\n",
-					p);
+			pr_err("Error: unrecognized mount option '%s' or missing value\n",
+			       p);
 			return -EINVAL;
 		}
 	}
@@ -266,9 +268,9 @@ static int jffs2_fill_super(struct super_block *sb, void *data, int silent)
 	struct jffs2_sb_info *c;
 	int ret;
 
-	D1(printk(KERN_DEBUG "jffs2_get_sb_mtd():"
+	jffs2_dbg(1, "jffs2_get_sb_mtd():"
 		  " New superblock for device %d (\"%s\")\n",
-		  sb->s_mtd->index, sb->s_mtd->name));
+		  sb->s_mtd->index, sb->s_mtd->name);
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
@@ -315,7 +317,7 @@ static void jffs2_put_super (struct super_block *sb)
 {
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
 
-	D2(printk(KERN_DEBUG "jffs2: jffs2_put_super()\n"));
+	jffs2_dbg(2, "%s()\n", __func__);
 
 	if (sb->s_dirt)
 		jffs2_write_super(sb);
@@ -336,7 +338,7 @@ static void jffs2_put_super (struct super_block *sb)
 	kfree(c->inocache_list);
 	jffs2_clear_xattr_subsystem(c);
 	mtd_sync(c->mtd);
-	D1(printk(KERN_DEBUG "jffs2_put_super returning\n"));
+	jffs2_dbg(1, "%s(): returning\n", __func__);
 }
 
 static void jffs2_kill_sb(struct super_block *sb)
@@ -371,7 +373,7 @@ static int __init init_jffs2_fs(void)
 	BUILD_BUG_ON(sizeof(struct jffs2_raw_inode) != 68);
 	BUILD_BUG_ON(sizeof(struct jffs2_raw_summary) != 32);
 
-	printk(KERN_INFO "JFFS2 version 2.2."
+	pr_info("version 2.2."
 #ifdef CONFIG_JFFS2_FS_WRITEBUFFER
 	       " (NAND)"
 #endif
@@ -386,22 +388,22 @@ static int __init init_jffs2_fs(void)
 						SLAB_MEM_SPREAD),
 					     jffs2_i_init_once);
 	if (!jffs2_inode_cachep) {
-		printk(KERN_ERR "JFFS2 error: Failed to initialise inode cache\n");
+		pr_err("error: Failed to initialise inode cache\n");
 		return -ENOMEM;
 	}
 	ret = jffs2_compressors_init();
 	if (ret) {
-		printk(KERN_ERR "JFFS2 error: Failed to initialise compressors\n");
+		pr_err("error: Failed to initialise compressors\n");
 		goto out;
 	}
 	ret = jffs2_create_slab_caches();
 	if (ret) {
-		printk(KERN_ERR "JFFS2 error: Failed to initialise slab caches\n");
+		pr_err("error: Failed to initialise slab caches\n");
 		goto out_compressors;
 	}
 	ret = register_filesystem(&jffs2_fs_type);
 	if (ret) {
-		printk(KERN_ERR "JFFS2 error: Failed to register filesystem\n");
+		pr_err("error: Failed to register filesystem\n");
 		goto out_slab;
 	}
 	return 0;
diff --git a/fs/jffs2/symlink.c b/fs/jffs2/symlink.c
index e3035afb1814..6e563332bb24 100644
--- a/fs/jffs2/symlink.c
+++ b/fs/jffs2/symlink.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
@@ -47,10 +49,11 @@ static void *jffs2_follow_link(struct dentry *dentry, struct nameidata *nd)
 	 */
 
 	if (!p) {
-		printk(KERN_ERR "jffs2_follow_link(): can't find symlink target\n");
+		pr_err("%s(): can't find symlink target\n", __func__);
 		p = ERR_PTR(-EIO);
 	}
-	D1(printk(KERN_DEBUG "jffs2_follow_link(): target path is '%s'\n", (char *) f->target));
+	jffs2_dbg(1, "%s(): target path is '%s'\n",
+		  __func__, (char *)f->target);
 
 	nd_set_link(nd, p);
 
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index 30e8f47e8a23..74d9be19df3f 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -11,6 +11,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mtd/mtd.h>
@@ -91,7 +93,7 @@ static void jffs2_wbuf_dirties_inode(struct jffs2_sb_info *c, uint32_t ino)
 
 	new = kmalloc(sizeof(*new), GFP_KERNEL);
 	if (!new) {
-		D1(printk(KERN_DEBUG "No memory to allocate inodirty. Fallback to all considered dirty\n"));
+		jffs2_dbg(1, "No memory to allocate inodirty. Fallback to all considered dirty\n");
 		jffs2_clear_wbuf_ino_list(c);
 		c->wbuf_inodes = &inodirty_nomem;
 		return;
@@ -113,19 +115,20 @@ static inline void jffs2_refile_wbuf_blocks(struct jffs2_sb_info *c)
 	list_for_each_safe(this, next, &c->erasable_pending_wbuf_list) {
 		struct jffs2_eraseblock *jeb = list_entry(this, struct jffs2_eraseblock, list);
 
-		D1(printk(KERN_DEBUG "Removing eraseblock at 0x%08x from erasable_pending_wbuf_list...\n", jeb->offset));
+		jffs2_dbg(1, "Removing eraseblock at 0x%08x from erasable_pending_wbuf_list...\n",
+			  jeb->offset);
 		list_del(this);
 		if ((jiffies + (n++)) & 127) {
 			/* Most of the time, we just erase it immediately. Otherwise we
 			   spend ages scanning it on mount, etc. */
-			D1(printk(KERN_DEBUG "...and adding to erase_pending_list\n"));
+			jffs2_dbg(1, "...and adding to erase_pending_list\n");
 			list_add_tail(&jeb->list, &c->erase_pending_list);
 			c->nr_erasing_blocks++;
 			jffs2_garbage_collect_trigger(c);
 		} else {
 			/* Sometimes, however, we leave it elsewhere so it doesn't get
 			   immediately reused, and we spread the load a bit. */
-			D1(printk(KERN_DEBUG "...and adding to erasable_list\n"));
+			jffs2_dbg(1, "...and adding to erasable_list\n");
 			list_add_tail(&jeb->list, &c->erasable_list);
 		}
 	}
@@ -136,7 +139,7 @@ static inline void jffs2_refile_wbuf_blocks(struct jffs2_sb_info *c)
 
 static void jffs2_block_refile(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb, int allow_empty)
 {
-	D1(printk("About to refile bad block at %08x\n", jeb->offset));
+	jffs2_dbg(1, "About to refile bad block at %08x\n", jeb->offset);
 
 	/* File the existing block on the bad_used_list.... */
 	if (c->nextblock == jeb)
@@ -144,12 +147,14 @@ static void jffs2_block_refile(struct jffs2_sb_info *c, struct jffs2_eraseblock
 	else /* Not sure this should ever happen... need more coffee */
 		list_del(&jeb->list);
 	if (jeb->first_node) {
-		D1(printk("Refiling block at %08x to bad_used_list\n", jeb->offset));
+		jffs2_dbg(1, "Refiling block at %08x to bad_used_list\n",
+			  jeb->offset);
 		list_add(&jeb->list, &c->bad_used_list);
 	} else {
 		BUG_ON(allow_empty == REFILE_NOTEMPTY);
 		/* It has to have had some nodes or we couldn't be here */
-		D1(printk("Refiling block at %08x to erase_pending_list\n", jeb->offset));
+		jffs2_dbg(1, "Refiling block at %08x to erase_pending_list\n",
+			  jeb->offset);
 		list_add(&jeb->list, &c->erase_pending_list);
 		c->nr_erasing_blocks++;
 		jffs2_garbage_collect_trigger(c);
@@ -230,10 +235,12 @@ static int jffs2_verify_write(struct jffs2_sb_info *c, unsigned char *buf,
 
 	ret = mtd_read(c->mtd, ofs, c->wbuf_pagesize, &retlen, c->wbuf_verify);
 	if (ret && ret != -EUCLEAN && ret != -EBADMSG) {
-		printk(KERN_WARNING "jffs2_verify_write(): Read back of page at %08x failed: %d\n", c->wbuf_ofs, ret);
+		pr_warn("%s(): Read back of page at %08x failed: %d\n",
+			__func__, c->wbuf_ofs, ret);
 		return ret;
 	} else if (retlen != c->wbuf_pagesize) {
-		printk(KERN_WARNING "jffs2_verify_write(): Read back of page at %08x gave short read: %zd not %d.\n", ofs, retlen, c->wbuf_pagesize);
+		pr_warn("%s(): Read back of page at %08x gave short read: %zd not %d\n",
+			__func__, ofs, retlen, c->wbuf_pagesize);
 		return -EIO;
 	}
 	if (!memcmp(buf, c->wbuf_verify, c->wbuf_pagesize))
@@ -246,12 +253,12 @@ static int jffs2_verify_write(struct jffs2_sb_info *c, unsigned char *buf,
 	else
 		eccstr = "OK or unused";
 
-	printk(KERN_WARNING "Write verify error (ECC %s) at %08x. Wrote:\n",
-	       eccstr, c->wbuf_ofs);
+	pr_warn("Write verify error (ECC %s) at %08x. Wrote:\n",
+		eccstr, c->wbuf_ofs);
 	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1,
 		       c->wbuf, c->wbuf_pagesize, 0);
 
-	printk(KERN_WARNING "Read back:\n");
+	pr_warn("Read back:\n");
 	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1,
 		       c->wbuf_verify, c->wbuf_pagesize, 0);
 
@@ -308,7 +315,7 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 
 	if (!first_raw) {
 		/* All nodes were obsolete. Nothing to recover. */
-		D1(printk(KERN_DEBUG "No non-obsolete nodes to be recovered. Just filing block bad\n"));
+		jffs2_dbg(1, "No non-obsolete nodes to be recovered. Just filing block bad\n");
 		c->wbuf_len = 0;
 		return;
 	}
@@ -331,7 +338,7 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 
 		buf = kmalloc(end - start, GFP_KERNEL);
 		if (!buf) {
-			printk(KERN_CRIT "Malloc failure in wbuf recovery. Data loss ensues.\n");
+			pr_crit("Malloc failure in wbuf recovery. Data loss ensues.\n");
 
 			goto read_failed;
 		}
@@ -346,7 +353,7 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 			ret = 0;
 
 		if (ret || retlen != c->wbuf_ofs - start) {
-			printk(KERN_CRIT "Old data are already lost in wbuf recovery. Data loss ensues.\n");
+			pr_crit("Old data are already lost in wbuf recovery. Data loss ensues.\n");
 
 			kfree(buf);
 			buf = NULL;
@@ -380,7 +387,7 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 	/* ... and get an allocation of space from a shiny new block instead */
 	ret = jffs2_reserve_space_gc(c, end-start, &len, JFFS2_SUMMARY_NOSUM_SIZE);
 	if (ret) {
-		printk(KERN_WARNING "Failed to allocate space for wbuf recovery. Data loss ensues.\n");
+		pr_warn("Failed to allocate space for wbuf recovery. Data loss ensues.\n");
 		kfree(buf);
 		return;
 	}
@@ -390,7 +397,7 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 
 	ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, nr_refile);
 	if (ret) {
-		printk(KERN_WARNING "Failed to allocate node refs for wbuf recovery. Data loss ensues.\n");
+		pr_warn("Failed to allocate node refs for wbuf recovery. Data loss ensues.\n");
 		kfree(buf);
 		return;
 	}
@@ -406,13 +413,13 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 		unsigned char *rewrite_buf = buf?:c->wbuf;
 		uint32_t towrite = (end-start) - ((end-start)%c->wbuf_pagesize);
 
-		D1(printk(KERN_DEBUG "Write 0x%x bytes at 0x%08x in wbuf recover\n",
-			  towrite, ofs));
+		jffs2_dbg(1, "Write 0x%x bytes at 0x%08x in wbuf recover\n",
+			  towrite, ofs);
 
 #ifdef BREAKMEHEADER
 		static int breakme;
 		if (breakme++ == 20) {
-			printk(KERN_NOTICE "Faking write error at 0x%08x\n", ofs);
+			pr_notice("Faking write error at 0x%08x\n", ofs);
 			breakme = 0;
 			mtd_write(c->mtd, ofs, towrite, &retlen, brokenbuf);
 			ret = -EIO;
@@ -423,7 +430,7 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 
 		if (ret || retlen != towrite || jffs2_verify_write(c, rewrite_buf, ofs)) {
 			/* Argh. We tried. Really we did. */
-			printk(KERN_CRIT "Recovery of wbuf failed due to a second write error\n");
+			pr_crit("Recovery of wbuf failed due to a second write error\n");
 			kfree(buf);
 
 			if (retlen)
@@ -431,7 +438,7 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 
 			return;
 		}
-		printk(KERN_NOTICE "Recovery of wbuf succeeded to %08x\n", ofs);
+		pr_notice("Recovery of wbuf succeeded to %08x\n", ofs);
 
 		c->wbuf_len = (end - start) - towrite;
 		c->wbuf_ofs = ofs + towrite;
@@ -459,8 +466,8 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 		struct jffs2_raw_node_ref **adjust_ref = NULL;
 		struct jffs2_inode_info *f = NULL;
 
-		D1(printk(KERN_DEBUG "Refiling block of %08x at %08x(%d) to %08x\n",
-			  rawlen, ref_offset(raw), ref_flags(raw), ofs));
+		jffs2_dbg(1, "Refiling block of %08x at %08x(%d) to %08x\n",
+			  rawlen, ref_offset(raw), ref_flags(raw), ofs);
 
 		ic = jffs2_raw_ref_to_ic(raw);
 
@@ -540,7 +547,8 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 
 	/* Fix up the original jeb now it's on the bad_list */
 	if (first_raw == jeb->first_node) {
-		D1(printk(KERN_DEBUG "Failing block at %08x is now empty. Moving to erase_pending_list\n", jeb->offset));
+		jffs2_dbg(1, "Failing block at %08x is now empty. Moving to erase_pending_list\n",
+			  jeb->offset);
 		list_move(&jeb->list, &c->erase_pending_list);
 		c->nr_erasing_blocks++;
 		jffs2_garbage_collect_trigger(c);
@@ -554,7 +562,8 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c)
 
 	spin_unlock(&c->erase_completion_lock);
 
-	D1(printk(KERN_DEBUG "wbuf recovery completed OK. wbuf_ofs 0x%08x, len 0x%x\n", c->wbuf_ofs, c->wbuf_len));
+	jffs2_dbg(1, "wbuf recovery completed OK. wbuf_ofs 0x%08x, len 0x%x\n",
+		  c->wbuf_ofs, c->wbuf_len);
 
 }
 
@@ -579,7 +588,7 @@ static int __jffs2_flush_wbuf(struct jffs2_sb_info *c, int pad)
 		return 0;
 
 	if (!mutex_is_locked(&c->alloc_sem)) {
-		printk(KERN_CRIT "jffs2_flush_wbuf() called with alloc_sem not locked!\n");
+		pr_crit("jffs2_flush_wbuf() called with alloc_sem not locked!\n");
 		BUG();
 	}
 
@@ -617,7 +626,7 @@ static int __jffs2_flush_wbuf(struct jffs2_sb_info *c, int pad)
 #ifdef BREAKME
 	static int breakme;
 	if (breakme++ == 20) {
-		printk(KERN_NOTICE "Faking write error at 0x%08x\n", c->wbuf_ofs);
+		pr_notice("Faking write error at 0x%08x\n", c->wbuf_ofs);
 		breakme = 0;
 		mtd_write(c->mtd, c->wbuf_ofs, c->wbuf_pagesize, &retlen,
 			  brokenbuf);
@@ -629,11 +638,11 @@ static int __jffs2_flush_wbuf(struct jffs2_sb_info *c, int pad)
 				&retlen, c->wbuf);
 
 	if (ret) {
-		printk(KERN_WARNING "jffs2_flush_wbuf(): Write failed with %d\n", ret);
+		pr_warn("jffs2_flush_wbuf(): Write failed with %d\n", ret);
 		goto wfail;
 	} else if (retlen != c->wbuf_pagesize) {
-		printk(KERN_WARNING "jffs2_flush_wbuf(): Write was short: %zd instead of %d\n",
-		       retlen, c->wbuf_pagesize);
+		pr_warn("jffs2_flush_wbuf(): Write was short: %zd instead of %d\n",
+			retlen, c->wbuf_pagesize);
 		ret = -EIO;
 		goto wfail;
 	} else if ((ret = jffs2_verify_write(c, c->wbuf, c->wbuf_ofs))) {
@@ -647,17 +656,18 @@ static int __jffs2_flush_wbuf(struct jffs2_sb_info *c, int pad)
 	if (pad) {
 		uint32_t waste = c->wbuf_pagesize - c->wbuf_len;
 
-		D1(printk(KERN_DEBUG "jffs2_flush_wbuf() adjusting free_size of %sblock at %08x\n",
-			  (wbuf_jeb==c->nextblock)?"next":"", wbuf_jeb->offset));
+		jffs2_dbg(1, "jffs2_flush_wbuf() adjusting free_size of %sblock at %08x\n",
+			  (wbuf_jeb == c->nextblock) ? "next" : "",
+			  wbuf_jeb->offset);
 
 		/* wbuf_pagesize - wbuf_len is the amount of space that's to be
 		   padded. If there is less free space in the block than that,
 		   something screwed up */
 		if (wbuf_jeb->free_size < waste) {
-			printk(KERN_CRIT "jffs2_flush_wbuf(): Accounting error. wbuf at 0x%08x has 0x%03x bytes, 0x%03x left.\n",
-			       c->wbuf_ofs, c->wbuf_len, waste);
-			printk(KERN_CRIT "jffs2_flush_wbuf(): But free_size for block at 0x%08x is only 0x%08x\n",
-			       wbuf_jeb->offset, wbuf_jeb->free_size);
+			pr_crit("jffs2_flush_wbuf(): Accounting error. wbuf at 0x%08x has 0x%03x bytes, 0x%03x left.\n",
+				c->wbuf_ofs, c->wbuf_len, waste);
+			pr_crit("jffs2_flush_wbuf(): But free_size for block at 0x%08x is only 0x%08x\n",
+				wbuf_jeb->offset, wbuf_jeb->free_size);
 			BUG();
 		}
 
@@ -694,14 +704,14 @@ int jffs2_flush_wbuf_gc(struct jffs2_sb_info *c, uint32_t ino)
 	uint32_t old_wbuf_len;
 	int ret = 0;
 
-	D1(printk(KERN_DEBUG "jffs2_flush_wbuf_gc() called for ino #%u...\n", ino));
+	jffs2_dbg(1, "jffs2_flush_wbuf_gc() called for ino #%u...\n", ino);
 
 	if (!c->wbuf)
 		return 0;
 
 	mutex_lock(&c->alloc_sem);
 	if (!jffs2_wbuf_pending_for_ino(c, ino)) {
-		D1(printk(KERN_DEBUG "Ino #%d not pending in wbuf. Returning\n", ino));
+		jffs2_dbg(1, "Ino #%d not pending in wbuf. Returning\n", ino);
 		mutex_unlock(&c->alloc_sem);
 		return 0;
 	}
@@ -711,7 +721,8 @@ int jffs2_flush_wbuf_gc(struct jffs2_sb_info *c, uint32_t ino)
 
 	if (c->unchecked_size) {
 		/* GC won't make any progress for a while */
-		D1(printk(KERN_DEBUG "jffs2_flush_wbuf_gc() padding. Not finished checking\n"));
+		jffs2_dbg(1, "%s(): padding. Not finished checking\n",
+			  __func__);
 		down_write(&c->wbuf_sem);
 		ret = __jffs2_flush_wbuf(c, PAD_ACCOUNTING);
 		/* retry flushing wbuf in case jffs2_wbuf_recover
@@ -724,7 +735,7 @@ int jffs2_flush_wbuf_gc(struct jffs2_sb_info *c, uint32_t ino)
 
 		mutex_unlock(&c->alloc_sem);
 
-		D1(printk(KERN_DEBUG "jffs2_flush_wbuf_gc() calls gc pass\n"));
+		jffs2_dbg(1, "%s(): calls gc pass\n", __func__);
 
 		ret = jffs2_garbage_collect_pass(c);
 		if (ret) {
@@ -742,7 +753,7 @@ int jffs2_flush_wbuf_gc(struct jffs2_sb_info *c, uint32_t ino)
 		mutex_lock(&c->alloc_sem);
 	}
 
-	D1(printk(KERN_DEBUG "jffs2_flush_wbuf_gc() ends...\n"));
+	jffs2_dbg(1, "%s(): ends...\n", __func__);
 
 	mutex_unlock(&c->alloc_sem);
 	return ret;
@@ -811,9 +822,8 @@ int jffs2_flash_writev(struct jffs2_sb_info *c, const struct kvec *invecs,
 	if (SECTOR_ADDR(to) != SECTOR_ADDR(c->wbuf_ofs)) {
 		/* It's a write to a new block */
 		if (c->wbuf_len) {
-			D1(printk(KERN_DEBUG "jffs2_flash_writev() to 0x%lx "
-				  "causes flush of wbuf at 0x%08x\n",
-				  (unsigned long)to, c->wbuf_ofs));
+			jffs2_dbg(1, "%s(): to 0x%lx causes flush of wbuf at 0x%08x\n",
+				  __func__, (unsigned long)to, c->wbuf_ofs);
 			ret = __jffs2_flush_wbuf(c, PAD_NOACCOUNT);
 			if (ret)
 				goto outerr;
@@ -825,11 +835,11 @@ int jffs2_flash_writev(struct jffs2_sb_info *c, const struct kvec *invecs,
 
 	if (to != PAD(c->wbuf_ofs + c->wbuf_len)) {
 		/* We're not writing immediately after the writebuffer. Bad. */
-		printk(KERN_CRIT "jffs2_flash_writev(): Non-contiguous write "
-		       "to %08lx\n", (unsigned long)to);
+		pr_crit("%s(): Non-contiguous write to %08lx\n",
+			__func__, (unsigned long)to);
 		if (c->wbuf_len)
-			printk(KERN_CRIT "wbuf was previously %08x-%08x\n",
-			       c->wbuf_ofs, c->wbuf_ofs+c->wbuf_len);
+			pr_crit("wbuf was previously %08x-%08x\n",
+				c->wbuf_ofs, c->wbuf_ofs + c->wbuf_len);
 		BUG();
 	}
 
@@ -957,8 +967,8 @@ int jffs2_flash_read(struct jffs2_sb_info *c, loff_t ofs, size_t len, size_t *re
 
 	if ( (ret == -EBADMSG || ret == -EUCLEAN) && (*retlen == len) ) {
 		if (ret == -EBADMSG)
-			printk(KERN_WARNING "mtd->read(0x%zx bytes from 0x%llx)"
-			       " returned ECC error\n", len, ofs);
+			pr_warn("mtd->read(0x%zx bytes from 0x%llx) returned ECC error\n",
+				len, ofs);
 		/*
 		 * We have the raw data without ECC correction in the buffer,
 		 * maybe we are lucky and all data or parts are correct. We
@@ -1034,9 +1044,8 @@ int jffs2_check_oob_empty(struct jffs2_sb_info *c,
 
 	ret = mtd_read_oob(c->mtd, jeb->offset, &ops);
 	if (ret || ops.oobretlen != ops.ooblen) {
-		printk(KERN_ERR "cannot read OOB for EB at %08x, requested %zd"
-				" bytes, read %zd bytes, error %d\n",
-				jeb->offset, ops.ooblen, ops.oobretlen, ret);
+		pr_err("cannot read OOB for EB at %08x, requested %zd bytes, read %zd bytes, error %d\n",
+		       jeb->offset, ops.ooblen, ops.oobretlen, ret);
 		if (!ret)
 			ret = -EIO;
 		return ret;
@@ -1048,8 +1057,8 @@ int jffs2_check_oob_empty(struct jffs2_sb_info *c,
 			continue;
 
 		if (ops.oobbuf[i] != 0xFF) {
-			D2(printk(KERN_DEBUG "Found %02x at %x in OOB for "
-				  "%08x\n", ops.oobbuf[i], i, jeb->offset));
+			jffs2_dbg(2, "Found %02x at %x in OOB for "
+				  "%08x\n", ops.oobbuf[i], i, jeb->offset);
 			return 1;
 		}
 	}
@@ -1077,9 +1086,8 @@ int jffs2_check_nand_cleanmarker(struct jffs2_sb_info *c,
 
 	ret = mtd_read_oob(c->mtd, jeb->offset, &ops);
 	if (ret || ops.oobretlen != ops.ooblen) {
-		printk(KERN_ERR "cannot read OOB for EB at %08x, requested %zd"
-				" bytes, read %zd bytes, error %d\n",
-				jeb->offset, ops.ooblen, ops.oobretlen, ret);
+		pr_err("cannot read OOB for EB at %08x, requested %zd bytes, read %zd bytes, error %d\n",
+		       jeb->offset, ops.ooblen, ops.oobretlen, ret);
 		if (!ret)
 			ret = -EIO;
 		return ret;
@@ -1103,9 +1111,8 @@ int jffs2_write_nand_cleanmarker(struct jffs2_sb_info *c,
 
 	ret = mtd_write_oob(c->mtd, jeb->offset, &ops);
 	if (ret || ops.oobretlen != ops.ooblen) {
-		printk(KERN_ERR "cannot write OOB for EB at %08x, requested %zd"
-				" bytes, read %zd bytes, error %d\n",
-				jeb->offset, ops.ooblen, ops.oobretlen, ret);
+		pr_err("cannot write OOB for EB at %08x, requested %zd bytes, read %zd bytes, error %d\n",
+		       jeb->offset, ops.ooblen, ops.oobretlen, ret);
 		if (!ret)
 			ret = -EIO;
 		return ret;
@@ -1130,11 +1137,12 @@ int jffs2_write_nand_badblock(struct jffs2_sb_info *c, struct jffs2_eraseblock *
 	if( ++jeb->bad_count < MAX_ERASE_FAILURES)
 		return 0;
 
-	printk(KERN_WARNING "JFFS2: marking eraseblock at %08x\n as bad", bad_offset);
+	pr_warn("marking eraseblock at %08x as bad\n", bad_offset);
 	ret = mtd_block_markbad(c->mtd, bad_offset);
 
 	if (ret) {
-		D1(printk(KERN_WARNING "jffs2_write_nand_badblock(): Write failed for block at %08x: error %d\n", jeb->offset, ret));
+		jffs2_dbg(1, "%s(): Write failed for block at %08x: error %d\n",
+			  __func__, jeb->offset, ret);
 		return ret;
 	}
 	return 1;
@@ -1151,11 +1159,11 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
 	c->cleanmarker_size = 0;
 
 	if (!oinfo || oinfo->oobavail == 0) {
-		printk(KERN_ERR "inconsistent device description\n");
+		pr_err("inconsistent device description\n");
 		return -EINVAL;
 	}
 
-	D1(printk(KERN_DEBUG "JFFS2 using OOB on NAND\n"));
+	jffs2_dbg(1, "using OOB on NAND\n");
 
 	c->oobavail = oinfo->oobavail;
 
@@ -1222,7 +1230,7 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) {
 
 	if ((c->flash_size % c->sector_size) != 0) {
 		c->flash_size = (c->flash_size / c->sector_size) * c->sector_size;
-		printk(KERN_WARNING "JFFS2 flash size adjusted to %dKiB\n", c->flash_size);
+		pr_warn("flash size adjusted to %dKiB\n", c->flash_size);
 	};
 
 	c->wbuf_ofs = 0xFFFFFFFF;
@@ -1239,7 +1247,8 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) {
 	}
 #endif
 
-	printk(KERN_INFO "JFFS2 write-buffering enabled buffer (%d) erasesize (%d)\n", c->wbuf_pagesize, c->sector_size);
+	pr_info("write-buffering enabled buffer (%d) erasesize (%d)\n",
+		c->wbuf_pagesize, c->sector_size);
 
 	return 0;
 }
@@ -1297,7 +1306,8 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) {
 	if (!c->wbuf)
 		return -ENOMEM;
 
-	printk(KERN_INFO "JFFS2 write-buffering enabled buffer (%d) erasesize (%d)\n", c->wbuf_pagesize, c->sector_size);
+	pr_info("write-buffering enabled buffer (%d) erasesize (%d)\n",
+		c->wbuf_pagesize, c->sector_size);
 
 	return 0;
 }
diff --git a/fs/jffs2/write.c b/fs/jffs2/write.c
index 30d175b6d290..b634de4c8101 100644
--- a/fs/jffs2/write.c
+++ b/fs/jffs2/write.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/crc32.h>
@@ -36,7 +38,7 @@ int jffs2_do_new_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 	f->inocache->state = INO_STATE_PRESENT;
 
 	jffs2_add_ino_cache(c, f->inocache);
-	D1(printk(KERN_DEBUG "jffs2_do_new_inode(): Assigned ino# %d\n", f->inocache->ino));
+	jffs2_dbg(1, "%s(): Assigned ino# %d\n", __func__, f->inocache->ino);
 	ri->ino = cpu_to_je32(f->inocache->ino);
 
 	ri->magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -68,7 +70,7 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 	unsigned long cnt = 2;
 
 	D1(if(je32_to_cpu(ri->hdr_crc) != crc32(0, ri, sizeof(struct jffs2_unknown_node)-4)) {
-		printk(KERN_CRIT "Eep. CRC not correct in jffs2_write_dnode()\n");
+		pr_crit("Eep. CRC not correct in jffs2_write_dnode()\n");
 		BUG();
 	}
 	   );
@@ -78,7 +80,9 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 	vecs[1].iov_len = datalen;
 
 	if (je32_to_cpu(ri->totlen) != sizeof(*ri) + datalen) {
-		printk(KERN_WARNING "jffs2_write_dnode: ri->totlen (0x%08x) != sizeof(*ri) (0x%08zx) + datalen (0x%08x)\n", je32_to_cpu(ri->totlen), sizeof(*ri), datalen);
+		pr_warn("%s(): ri->totlen (0x%08x) != sizeof(*ri) (0x%08zx) + datalen (0x%08x)\n",
+			__func__, je32_to_cpu(ri->totlen),
+			sizeof(*ri), datalen);
 	}
 
 	fn = jffs2_alloc_full_dnode();
@@ -95,9 +99,9 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 
 	if ((alloc_mode!=ALLOC_GC) && (je32_to_cpu(ri->version) < f->highest_version)) {
 		BUG_ON(!retried);
-		D1(printk(KERN_DEBUG "jffs2_write_dnode : dnode_version %d, "
-				"highest version %d -> updating dnode\n",
-				je32_to_cpu(ri->version), f->highest_version));
+		jffs2_dbg(1, "%s(): dnode_version %d, highest version %d -> updating dnode\n",
+			  __func__,
+			  je32_to_cpu(ri->version), f->highest_version);
 		ri->version = cpu_to_je32(++f->highest_version);
 		ri->node_crc = cpu_to_je32(crc32(0, ri, sizeof(*ri)-8));
 	}
@@ -106,8 +110,8 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 				 (alloc_mode==ALLOC_GC)?0:f->inocache->ino);
 
 	if (ret || (retlen != sizeof(*ri) + datalen)) {
-		printk(KERN_NOTICE "Write of %zd bytes at 0x%08x failed. returned %d, retlen %zd\n",
-		       sizeof(*ri)+datalen, flash_ofs, ret, retlen);
+		pr_notice("Write of %zd bytes at 0x%08x failed. returned %d, retlen %zd\n",
+			  sizeof(*ri) + datalen, flash_ofs, ret, retlen);
 
 		/* Mark the space as dirtied */
 		if (retlen) {
@@ -118,7 +122,8 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 			   this node */
 			jffs2_add_physical_node_ref(c, flash_ofs | REF_OBSOLETE, PAD(sizeof(*ri)+datalen), NULL);
 		} else {
-			printk(KERN_NOTICE "Not marking the space at 0x%08x as dirty because the flash driver returned retlen zero\n", flash_ofs);
+			pr_notice("Not marking the space at 0x%08x as dirty because the flash driver returned retlen zero\n",
+				  flash_ofs);
 		}
 		if (!retried && alloc_mode != ALLOC_NORETRY) {
 			/* Try to reallocate space and retry */
@@ -127,7 +132,7 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 
 			retried = 1;
 
-			D1(printk(KERN_DEBUG "Retrying failed write.\n"));
+			jffs2_dbg(1, "Retrying failed write.\n");
 
 			jffs2_dbg_acct_sanity_check(c,jeb);
 			jffs2_dbg_acct_paranoia_check(c, jeb);
@@ -147,14 +152,16 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 
 			if (!ret) {
 				flash_ofs = write_ofs(c);
-				D1(printk(KERN_DEBUG "Allocated space at 0x%08x to retry failed write.\n", flash_ofs));
+				jffs2_dbg(1, "Allocated space at 0x%08x to retry failed write.\n",
+					  flash_ofs);
 
 				jffs2_dbg_acct_sanity_check(c,jeb);
 				jffs2_dbg_acct_paranoia_check(c, jeb);
 
 				goto retry;
 			}
-			D1(printk(KERN_DEBUG "Failed to allocate space to retry failed write: %d!\n", ret));
+			jffs2_dbg(1, "Failed to allocate space to retry failed write: %d!\n",
+				  ret);
 		}
 		/* Release the full_dnode which is now useless, and return */
 		jffs2_free_full_dnode(fn);
@@ -183,10 +190,10 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 	fn->size = je32_to_cpu(ri->dsize);
 	fn->frags = 0;
 
-	D1(printk(KERN_DEBUG "jffs2_write_dnode wrote node at 0x%08x(%d) with dsize 0x%x, csize 0x%x, node_crc 0x%08x, data_crc 0x%08x, totlen 0x%08x\n",
+	jffs2_dbg(1, "jffs2_write_dnode wrote node at 0x%08x(%d) with dsize 0x%x, csize 0x%x, node_crc 0x%08x, data_crc 0x%08x, totlen 0x%08x\n",
 		  flash_ofs & ~3, flash_ofs & 3, je32_to_cpu(ri->dsize),
 		  je32_to_cpu(ri->csize), je32_to_cpu(ri->node_crc),
-		  je32_to_cpu(ri->data_crc), je32_to_cpu(ri->totlen)));
+		  je32_to_cpu(ri->data_crc), je32_to_cpu(ri->totlen));
 
 	if (retried) {
 		jffs2_dbg_acct_sanity_check(c,NULL);
@@ -206,22 +213,23 @@ struct jffs2_full_dirent *jffs2_write_dirent(struct jffs2_sb_info *c, struct jff
 	int retried = 0;
 	int ret;
 
-	D1(printk(KERN_DEBUG "jffs2_write_dirent(ino #%u, name at *0x%p \"%s\"->ino #%u, name_crc 0x%08x)\n",
+	jffs2_dbg(1, "%s(ino #%u, name at *0x%p \"%s\"->ino #%u, name_crc 0x%08x)\n",
+		  __func__,
 		  je32_to_cpu(rd->pino), name, name, je32_to_cpu(rd->ino),
-		  je32_to_cpu(rd->name_crc)));
+		  je32_to_cpu(rd->name_crc));
 
 	D1(if(je32_to_cpu(rd->hdr_crc) != crc32(0, rd, sizeof(struct jffs2_unknown_node)-4)) {
-		printk(KERN_CRIT "Eep. CRC not correct in jffs2_write_dirent()\n");
+		pr_crit("Eep. CRC not correct in jffs2_write_dirent()\n");
 		BUG();
 	   });
 
 	if (strnlen(name, namelen) != namelen) {
 		/* This should never happen, but seems to have done on at least one
 		   occasion: https://dev.laptop.org/ticket/4184 */
-		printk(KERN_CRIT "Error in jffs2_write_dirent() -- name contains zero bytes!\n");
-		printk(KERN_CRIT "Directory inode #%u, name at *0x%p \"%s\"->ino #%u, name_crc 0x%08x\n",
-		       je32_to_cpu(rd->pino), name, name, je32_to_cpu(rd->ino),
-		       je32_to_cpu(rd->name_crc));
+		pr_crit("Error in jffs2_write_dirent() -- name contains zero bytes!\n");
+		pr_crit("Directory inode #%u, name at *0x%p \"%s\"->ino #%u, name_crc 0x%08x\n",
+			je32_to_cpu(rd->pino), name, name, je32_to_cpu(rd->ino),
+			je32_to_cpu(rd->name_crc));
 		WARN_ON(1);
 		return ERR_PTR(-EIO);
 	}
@@ -249,9 +257,9 @@ struct jffs2_full_dirent *jffs2_write_dirent(struct jffs2_sb_info *c, struct jff
 
 	if ((alloc_mode!=ALLOC_GC) && (je32_to_cpu(rd->version) < f->highest_version)) {
 		BUG_ON(!retried);
-		D1(printk(KERN_DEBUG "jffs2_write_dirent : dirent_version %d, "
-				     "highest version %d -> updating dirent\n",
-				     je32_to_cpu(rd->version), f->highest_version));
+		jffs2_dbg(1, "%s(): dirent_version %d, highest version %d -> updating dirent\n",
+			  __func__,
+			  je32_to_cpu(rd->version), f->highest_version);
 		rd->version = cpu_to_je32(++f->highest_version);
 		fd->version = je32_to_cpu(rd->version);
 		rd->node_crc = cpu_to_je32(crc32(0, rd, sizeof(*rd)-8));
@@ -260,13 +268,14 @@ struct jffs2_full_dirent *jffs2_write_dirent(struct jffs2_sb_info *c, struct jff
 	ret = jffs2_flash_writev(c, vecs, 2, flash_ofs, &retlen,
 				 (alloc_mode==ALLOC_GC)?0:je32_to_cpu(rd->pino));
 	if (ret || (retlen != sizeof(*rd) + namelen)) {
-		printk(KERN_NOTICE "Write of %zd bytes at 0x%08x failed. returned %d, retlen %zd\n",
-			       sizeof(*rd)+namelen, flash_ofs, ret, retlen);
+		pr_notice("Write of %zd bytes at 0x%08x failed. returned %d, retlen %zd\n",
+			  sizeof(*rd) + namelen, flash_ofs, ret, retlen);
 		/* Mark the space as dirtied */
 		if (retlen) {
 			jffs2_add_physical_node_ref(c, flash_ofs | REF_OBSOLETE, PAD(sizeof(*rd)+namelen), NULL);
 		} else {
-			printk(KERN_NOTICE "Not marking the space at 0x%08x as dirty because the flash driver returned retlen zero\n", flash_ofs);
+			pr_notice("Not marking the space at 0x%08x as dirty because the flash driver returned retlen zero\n",
+				  flash_ofs);
 		}
 		if (!retried) {
 			/* Try to reallocate space and retry */
@@ -275,7 +284,7 @@ struct jffs2_full_dirent *jffs2_write_dirent(struct jffs2_sb_info *c, struct jff
 
 			retried = 1;
 
-			D1(printk(KERN_DEBUG "Retrying failed write.\n"));
+			jffs2_dbg(1, "Retrying failed write.\n");
 
 			jffs2_dbg_acct_sanity_check(c,jeb);
 			jffs2_dbg_acct_paranoia_check(c, jeb);
@@ -295,12 +304,14 @@ struct jffs2_full_dirent *jffs2_write_dirent(struct jffs2_sb_info *c, struct jff
 
 			if (!ret) {
 				flash_ofs = write_ofs(c);
-				D1(printk(KERN_DEBUG "Allocated space at 0x%08x to retry failed write.\n", flash_ofs));
+				jffs2_dbg(1, "Allocated space at 0x%08x to retry failed write\n",
+					  flash_ofs);
 				jffs2_dbg_acct_sanity_check(c,jeb);
 				jffs2_dbg_acct_paranoia_check(c, jeb);
 				goto retry;
 			}
-			D1(printk(KERN_DEBUG "Failed to allocate space to retry failed write: %d!\n", ret));
+			jffs2_dbg(1, "Failed to allocate space to retry failed write: %d!\n",
+				  ret);
 		}
 		/* Release the full_dnode which is now useless, and return */
 		jffs2_free_full_dirent(fd);
@@ -333,8 +344,8 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 	int ret = 0;
 	uint32_t writtenlen = 0;
 
-       	D1(printk(KERN_DEBUG "jffs2_write_inode_range(): Ino #%u, ofs 0x%x, len 0x%x\n",
-		  f->inocache->ino, offset, writelen));
+	jffs2_dbg(1, "%s(): Ino #%u, ofs 0x%x, len 0x%x\n",
+		  __func__, f->inocache->ino, offset, writelen);
 
 	while(writelen) {
 		struct jffs2_full_dnode *fn;
@@ -345,12 +356,13 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 		int retried = 0;
 
 	retry:
-		D2(printk(KERN_DEBUG "jffs2_commit_write() loop: 0x%x to write to 0x%x\n", writelen, offset));
+		jffs2_dbg(2, "jffs2_commit_write() loop: 0x%x to write to 0x%x\n",
+			  writelen, offset);
 
 		ret = jffs2_reserve_space(c, sizeof(*ri) + JFFS2_MIN_DATA_LEN,
 					&alloclen, ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
 		if (ret) {
-			D1(printk(KERN_DEBUG "jffs2_reserve_space returned %d\n", ret));
+			jffs2_dbg(1, "jffs2_reserve_space returned %d\n", ret);
 			break;
 		}
 		mutex_lock(&f->sem);
@@ -386,7 +398,7 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 			if (!retried) {
 				/* Write error to be retried */
 				retried = 1;
-				D1(printk(KERN_DEBUG "Retrying node write in jffs2_write_inode_range()\n"));
+				jffs2_dbg(1, "Retrying node write in jffs2_write_inode_range()\n");
 				goto retry;
 			}
 			break;
@@ -399,7 +411,8 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 		}
 		if (ret) {
 			/* Eep */
-			D1(printk(KERN_DEBUG "Eep. add_full_dnode_to_inode() failed in commit_write, returned %d\n", ret));
+			jffs2_dbg(1, "Eep. add_full_dnode_to_inode() failed in commit_write, returned %d\n",
+				  ret);
 			jffs2_mark_node_obsolete(c, fn->raw);
 			jffs2_free_full_dnode(fn);
 
@@ -410,11 +423,11 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 		mutex_unlock(&f->sem);
 		jffs2_complete_reservation(c);
 		if (!datalen) {
-			printk(KERN_WARNING "Eep. We didn't actually write any data in jffs2_write_inode_range()\n");
+			pr_warn("Eep. We didn't actually write any data in jffs2_write_inode_range()\n");
 			ret = -EIO;
 			break;
 		}
-		D1(printk(KERN_DEBUG "increasing writtenlen by %d\n", datalen));
+		jffs2_dbg(1, "increasing writtenlen by %d\n", datalen);
 		writtenlen += datalen;
 		offset += datalen;
 		writelen -= datalen;
@@ -439,7 +452,7 @@ int jffs2_do_create(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f,
 	 */
 	ret = jffs2_reserve_space(c, sizeof(*ri), &alloclen, ALLOC_NORMAL,
 				JFFS2_SUMMARY_INODE_SIZE);
-	D1(printk(KERN_DEBUG "jffs2_do_create(): reserved 0x%x bytes\n", alloclen));
+	jffs2_dbg(1, "%s(): reserved 0x%x bytes\n", __func__, alloclen);
 	if (ret)
 		return ret;
 
@@ -450,11 +463,11 @@ int jffs2_do_create(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f,
 
 	fn = jffs2_write_dnode(c, f, ri, NULL, 0, ALLOC_NORMAL);
 
-	D1(printk(KERN_DEBUG "jffs2_do_create created file with mode 0x%x\n",
-		  jemode_to_cpu(ri->mode)));
+	jffs2_dbg(1, "jffs2_do_create created file with mode 0x%x\n",
+		  jemode_to_cpu(ri->mode));
 
 	if (IS_ERR(fn)) {
-		D1(printk(KERN_DEBUG "jffs2_write_dnode() failed\n"));
+		jffs2_dbg(1, "jffs2_write_dnode() failed\n");
 		/* Eeek. Wave bye bye */
 		mutex_unlock(&f->sem);
 		jffs2_complete_reservation(c);
@@ -480,7 +493,7 @@ int jffs2_do_create(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f,
 
 	if (ret) {
 		/* Eep. */
-		D1(printk(KERN_DEBUG "jffs2_reserve_space() for dirent failed\n"));
+		jffs2_dbg(1, "jffs2_reserve_space() for dirent failed\n");
 		return ret;
 	}
 
@@ -597,8 +610,8 @@ int jffs2_do_unlink(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f,
 			    !memcmp(fd->name, name, namelen) &&
 			    !fd->name[namelen]) {
 
-				D1(printk(KERN_DEBUG "Marking old dirent node (ino #%u) @%08x obsolete\n",
-					  fd->ino, ref_offset(fd->raw)));
+				jffs2_dbg(1, "Marking old dirent node (ino #%u) @%08x obsolete\n",
+					  fd->ino, ref_offset(fd->raw));
 				jffs2_mark_node_obsolete(c, fd->raw);
 				/* We don't want to remove it from the list immediately,
 				   because that screws up getdents()/seek() semantics even
@@ -627,11 +640,13 @@ int jffs2_do_unlink(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f,
 				dead_f->dents = fd->next;
 
 				if (fd->ino) {
-					printk(KERN_WARNING "Deleting inode #%u with active dentry \"%s\"->ino #%u\n",
-					       dead_f->inocache->ino, fd->name, fd->ino);
+					pr_warn("Deleting inode #%u with active dentry \"%s\"->ino #%u\n",
+						dead_f->inocache->ino,
+						fd->name, fd->ino);
 				} else {
-					D1(printk(KERN_DEBUG "Removing deletion dirent for \"%s\" from dir ino #%u\n",
-						fd->name, dead_f->inocache->ino));
+					jffs2_dbg(1, "Removing deletion dirent for \"%s\" from dir ino #%u\n",
+						  fd->name,
+						  dead_f->inocache->ino);
 				}
 				if (fd->raw)
 					jffs2_mark_node_obsolete(c, fd->raw);
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index 3e93cdd19005..b55b803eddcb 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
diff --git a/fs/libfs.c b/fs/libfs.c
index 4a0d1f06da57..358094f0433d 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -264,6 +264,13 @@ Enomem:
 	return ERR_PTR(-ENOMEM);
 }
 
+int simple_open(struct inode *inode, struct file *file)
+{
+	if (inode->i_private)
+		file->private_data = inode->i_private;
+	return 0;
+}
+
 int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = old_dentry->d_inode;
@@ -984,6 +991,7 @@ EXPORT_SYMBOL(simple_dir_operations);
 EXPORT_SYMBOL(simple_empty);
 EXPORT_SYMBOL(simple_fill_super);
 EXPORT_SYMBOL(simple_getattr);
+EXPORT_SYMBOL(simple_open);
 EXPORT_SYMBOL(simple_link);
 EXPORT_SYMBOL(simple_lookup);
 EXPORT_SYMBOL(simple_pin_fs);
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 2774e1013b34..f49b9afc4436 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -496,7 +496,7 @@ static int param_set_##name(const char *val, struct kernel_param *kp)	\
 	__typeof__(type) num = which_strtol(val, &endp, 0);		\
 	if (endp == val || *endp || num < (min) || num > (max))		\
 		return -EINVAL;						\
-	*((int *) kp->arg) = num;					\
+	*((type *) kp->arg) = num;					\
 	return 0;							\
 }
 
diff --git a/fs/locks.c b/fs/locks.c
index 637694bf3a03..0d68f1f81799 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -510,12 +510,13 @@ static void __locks_delete_block(struct file_lock *waiter)
 
 /*
  */
-static void locks_delete_block(struct file_lock *waiter)
+void locks_delete_block(struct file_lock *waiter)
 {
 	lock_flocks();
 	__locks_delete_block(waiter);
 	unlock_flocks();
 }
+EXPORT_SYMBOL(locks_delete_block);
 
 /* Insert waiter into blocker's block list.
  * We use a circular list so that processes can be easily woken up in
diff --git a/fs/namei.c b/fs/namei.c
index e615ff37e27d..0062dd17eb55 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1054,53 +1054,65 @@ static void follow_dotdot(struct nameidata *nd)
 }
 
 /*
- * Allocate a dentry with name and parent, and perform a parent
- * directory ->lookup on it. Returns the new dentry, or ERR_PTR
- * on error. parent->d_inode->i_mutex must be held. d_lookup must
- * have verified that no child exists while under i_mutex.
+ * This looks up the name in dcache, possibly revalidates the old dentry and
+ * allocates a new one if not found or not valid.  In the need_lookup argument
+ * returns whether i_op->lookup is necessary.
+ *
+ * dir->d_inode->i_mutex must be held
  */
-static struct dentry *d_alloc_and_lookup(struct dentry *parent,
-				struct qstr *name, struct nameidata *nd)
+static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
+				    struct nameidata *nd, bool *need_lookup)
 {
-	struct inode *inode = parent->d_inode;
 	struct dentry *dentry;
-	struct dentry *old;
+	int error;
 
-	/* Don't create child dentry for a dead directory. */
-	if (unlikely(IS_DEADDIR(inode)))
-		return ERR_PTR(-ENOENT);
+	*need_lookup = false;
+	dentry = d_lookup(dir, name);
+	if (dentry) {
+		if (d_need_lookup(dentry)) {
+			*need_lookup = true;
+		} else if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
+			error = d_revalidate(dentry, nd);
+			if (unlikely(error <= 0)) {
+				if (error < 0) {
+					dput(dentry);
+					return ERR_PTR(error);
+				} else if (!d_invalidate(dentry)) {
+					dput(dentry);
+					dentry = NULL;
+				}
+			}
+		}
+	}
 
-	dentry = d_alloc(parent, name);
-	if (unlikely(!dentry))
-		return ERR_PTR(-ENOMEM);
+	if (!dentry) {
+		dentry = d_alloc(dir, name);
+		if (unlikely(!dentry))
+			return ERR_PTR(-ENOMEM);
 
-	old = inode->i_op->lookup(inode, dentry, nd);
-	if (unlikely(old)) {
-		dput(dentry);
-		dentry = old;
+		*need_lookup = true;
 	}
 	return dentry;
 }
 
 /*
- * We already have a dentry, but require a lookup to be performed on the parent
- * directory to fill in d_inode. Returns the new dentry, or ERR_PTR on error.
- * parent->d_inode->i_mutex must be held. d_lookup must have verified that no
- * child exists while under i_mutex.
+ * Call i_op->lookup on the dentry.  The dentry must be negative but may be
+ * hashed if it was pouplated with DCACHE_NEED_LOOKUP.
+ *
+ * dir->d_inode->i_mutex must be held
  */
-static struct dentry *d_inode_lookup(struct dentry *parent, struct dentry *dentry,
-				     struct nameidata *nd)
+static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
+				  struct nameidata *nd)
 {
-	struct inode *inode = parent->d_inode;
 	struct dentry *old;
 
 	/* Don't create child dentry for a dead directory. */
-	if (unlikely(IS_DEADDIR(inode))) {
+	if (unlikely(IS_DEADDIR(dir))) {
 		dput(dentry);
 		return ERR_PTR(-ENOENT);
 	}
 
-	old = inode->i_op->lookup(inode, dentry, nd);
+	old = dir->i_op->lookup(dir, dentry, nd);
 	if (unlikely(old)) {
 		dput(dentry);
 		dentry = old;
@@ -1108,6 +1120,19 @@ static struct dentry *d_inode_lookup(struct dentry *parent, struct dentry *dentr
 	return dentry;
 }
 
+static struct dentry *__lookup_hash(struct qstr *name,
+		struct dentry *base, struct nameidata *nd)
+{
+	bool need_lookup;
+	struct dentry *dentry;
+
+	dentry = lookup_dcache(name, base, nd, &need_lookup);
+	if (!need_lookup)
+		return dentry;
+
+	return lookup_real(base->d_inode, dentry, nd);
+}
+
 /*
  *  It's more convoluted than I'd like it to be, but... it's still fairly
  *  small and for now I'd prefer to have fast path as straight as possible.
@@ -1139,6 +1164,8 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 			return -ECHILD;
 		nd->seq = seq;
 
+		if (unlikely(d_need_lookup(dentry)))
+			goto unlazy;
 		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
 			status = d_revalidate(dentry, nd);
 			if (unlikely(status <= 0)) {
@@ -1147,8 +1174,6 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 				goto unlazy;
 			}
 		}
-		if (unlikely(d_need_lookup(dentry)))
-			goto unlazy;
 		path->mnt = mnt;
 		path->dentry = dentry;
 		if (unlikely(!__follow_mount_rcu(nd, path, inode)))
@@ -1163,38 +1188,14 @@ unlazy:
 		dentry = __d_lookup(parent, name);
 	}
 
-	if (dentry && unlikely(d_need_lookup(dentry))) {
+	if (unlikely(!dentry))
+		goto need_lookup;
+
+	if (unlikely(d_need_lookup(dentry))) {
 		dput(dentry);
-		dentry = NULL;
-	}
-retry:
-	if (unlikely(!dentry)) {
-		struct inode *dir = parent->d_inode;
-		BUG_ON(nd->inode != dir);
-
-		mutex_lock(&dir->i_mutex);
-		dentry = d_lookup(parent, name);
-		if (likely(!dentry)) {
-			dentry = d_alloc_and_lookup(parent, name, nd);
-			if (IS_ERR(dentry)) {
-				mutex_unlock(&dir->i_mutex);
-				return PTR_ERR(dentry);
-			}
-			/* known good */
-			need_reval = 0;
-			status = 1;
-		} else if (unlikely(d_need_lookup(dentry))) {
-			dentry = d_inode_lookup(parent, dentry, nd);
-			if (IS_ERR(dentry)) {
-				mutex_unlock(&dir->i_mutex);
-				return PTR_ERR(dentry);
-			}
-			/* known good */
-			need_reval = 0;
-			status = 1;
-		}
-		mutex_unlock(&dir->i_mutex);
+		goto need_lookup;
 	}
+
 	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
 		status = d_revalidate(dentry, nd);
 	if (unlikely(status <= 0)) {
@@ -1204,12 +1205,10 @@ retry:
 		}
 		if (!d_invalidate(dentry)) {
 			dput(dentry);
-			dentry = NULL;
-			need_reval = 1;
-			goto retry;
+			goto need_lookup;
 		}
 	}
-
+done:
 	path->mnt = mnt;
 	path->dentry = dentry;
 	err = follow_managed(path, nd->flags);
@@ -1221,6 +1220,16 @@ retry:
 		nd->flags |= LOOKUP_JUMPED;
 	*inode = path->dentry->d_inode;
 	return 0;
+
+need_lookup:
+	BUG_ON(nd->inode != parent->d_inode);
+
+	mutex_lock(&parent->d_inode->i_mutex);
+	dentry = __lookup_hash(name, parent, nd);
+	mutex_unlock(&parent->d_inode->i_mutex);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	goto done;
 }
 
 static inline int may_lookup(struct nameidata *nd)
@@ -1398,18 +1407,9 @@ static inline int can_lookup(struct inode *inode)
  */
 #ifdef CONFIG_DCACHE_WORD_ACCESS
 
-#ifdef CONFIG_64BIT
+#include <asm/word-at-a-time.h>
 
-/*
- * Jan Achrenius on G+: microoptimized version of
- * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
- * that works for the bytemasks without having to
- * mask them first.
- */
-static inline long count_masked_bytes(unsigned long mask)
-{
-	return mask*0x0001020304050608ul >> 56;
-}
+#ifdef CONFIG_64BIT
 
 static inline unsigned int fold_hash(unsigned long hash)
 {
@@ -1419,15 +1419,6 @@ static inline unsigned int fold_hash(unsigned long hash)
 
 #else	/* 32-bit case */
 
-/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
-static inline long count_masked_bytes(long mask)
-{
-	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
-	long a = (0x0ff0001+mask) >> 23;
-	/* Fix the 1 for 00 case */
-	return a & mask;
-}
-
 #define fold_hash(x) (x)
 
 #endif
@@ -1455,17 +1446,6 @@ done:
 }
 EXPORT_SYMBOL(full_name_hash);
 
-#define REPEAT_BYTE(x)	((~0ul / 0xff) * (x))
-#define ONEBYTES	REPEAT_BYTE(0x01)
-#define SLASHBYTES	REPEAT_BYTE('/')
-#define HIGHBITS	REPEAT_BYTE(0x80)
-
-/* Return the high bit set in the first byte that is a zero */
-static inline unsigned long has_zero(unsigned long a)
-{
-	return ((a - ONEBYTES) & ~a) & HIGHBITS;
-}
-
 /*
  * Calculate the length and hash of the path component, and
  * return the length of the component;
@@ -1481,7 +1461,7 @@ static inline unsigned long hash_name(const char *name, unsigned int *hashp)
 		len += sizeof(unsigned long);
 		a = *(unsigned long *)(name+len);
 		/* Do we have any NUL or '/' bytes in this word? */
-		mask = has_zero(a) | has_zero(a ^ SLASHBYTES);
+		mask = has_zero(a) | has_zero(a ^ REPEAT_BYTE('/'));
 	} while (!mask);
 
 	/* The mask *below* the first high bit set */
@@ -1846,59 +1826,6 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 	return err;
 }
 
-static struct dentry *__lookup_hash(struct qstr *name,
-		struct dentry *base, struct nameidata *nd)
-{
-	struct inode *inode = base->d_inode;
-	struct dentry *dentry;
-	int err;
-
-	err = inode_permission(inode, MAY_EXEC);
-	if (err)
-		return ERR_PTR(err);
-
-	/*
-	 * Don't bother with __d_lookup: callers are for creat as
-	 * well as unlink, so a lot of the time it would cost
-	 * a double lookup.
-	 */
-	dentry = d_lookup(base, name);
-
-	if (dentry && d_need_lookup(dentry)) {
-		/*
-		 * __lookup_hash is called with the parent dir's i_mutex already
-		 * held, so we are good to go here.
-		 */
-		dentry = d_inode_lookup(base, dentry, nd);
-		if (IS_ERR(dentry))
-			return dentry;
-	}
-
-	if (dentry && (dentry->d_flags & DCACHE_OP_REVALIDATE)) {
-		int status = d_revalidate(dentry, nd);
-		if (unlikely(status <= 0)) {
-			/*
-			 * The dentry failed validation.
-			 * If d_revalidate returned 0 attempt to invalidate
-			 * the dentry otherwise d_revalidate is asking us
-			 * to return a fail status.
-			 */
-			if (status < 0) {
-				dput(dentry);
-				return ERR_PTR(status);
-			} else if (!d_invalidate(dentry)) {
-				dput(dentry);
-				dentry = NULL;
-			}
-		}
-	}
-
-	if (!dentry)
-		dentry = d_alloc_and_lookup(base, name, nd);
-
-	return dentry;
-}
-
 /*
  * Restricted form of lookup. Doesn't follow links, single-component only,
  * needs parent already locked. Doesn't follow mounts.
@@ -1924,6 +1851,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 {
 	struct qstr this;
 	unsigned int c;
+	int err;
 
 	WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
 
@@ -1948,6 +1876,10 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 			return ERR_PTR(err);
 	}
 
+	err = inode_permission(base->d_inode, MAY_EXEC);
+	if (err)
+		return ERR_PTR(err);
+
 	return __lookup_hash(&this, base, NULL);
 }
 
@@ -2749,7 +2681,7 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
 
 /*
  * The dentry_unhash() helper will try to drop the dentry early: we
- * should have a usage count of 2 if we're the only user of this
+ * should have a usage count of 1 if we're the only user of this
  * dentry, and if that is true (possibly after pruning the dcache),
  * then we drop the dentry now.
  *
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 64a326418aa2..3ff5fcc1528f 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -7,7 +7,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include <linux/time.h>
 #include <linux/kernel.h>
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 49df0e7f8379..87484fb8d177 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -11,7 +11,6 @@
 
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>
 
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index e5d71b27a5b0..be20a7e171a0 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -19,7 +19,6 @@
 #include <linux/memcontrol.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include "ncp_fs.h"
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 4a108a0a2a60..da7b5e4ff9ec 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -43,7 +43,6 @@
 #include <linux/nsproxy.h>
 #include <linux/pid_namespace.h>
 
-#include <asm/system.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 9c7f66ac6cc2..481be7f7bdd3 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -51,7 +51,6 @@
 #include <linux/nfs_page.h>
 #include <linux/sunrpc/clnt.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/atomic.h>
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 4fdaaa63cf1c..aa9b709fd328 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -30,7 +30,6 @@
 #include <linux/swap.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include "delegation.h"
 #include "internal.h"
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 801d6d830787..4ca6f5c8038e 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -32,7 +32,6 @@
 #include <linux/namei.h>
 #include <linux/security.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "nfs4_fs.h"
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 7bb4d13c1cd5..e8bbfa5b3500 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -41,7 +41,6 @@
 #include <linux/freezer.h>
 #include <linux/crc32.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "nfs4_fs.h"
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 634c0bcb4fd6..5acfd9ea8a31 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -793,7 +793,6 @@ filelayout_clear_request_commit(struct nfs_page *req)
 	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
 		goto out;
 	if (list_is_singular(&req->wb_list)) {
-		struct inode *inode = req->wb_context->dentry->d_inode;
 		struct pnfs_layout_segment *lseg;
 
 		/* From here we can find the bucket, but for the moment,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e809d2305ebf..f82bde005a82 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -270,7 +270,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 		case 0:
 			return 0;
 		case -NFS4ERR_OPENMODE:
-			if (nfs_have_delegation(inode, FMODE_READ)) {
+			if (inode && nfs_have_delegation(inode, FMODE_READ)) {
 				nfs_inode_return_delegation(inode);
 				exception->retry = 1;
 				return 0;
@@ -282,10 +282,9 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (state != NULL)
-				nfs_remove_bad_delegation(state->inode);
 			if (state == NULL)
 				break;
+			nfs_remove_bad_delegation(state->inode);
 			nfs4_schedule_stateid_recovery(server, state);
 			goto wait_on_recovery;
 		case -NFS4ERR_EXPIRED:
@@ -2290,11 +2289,12 @@ static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
 		switch (err) {
 		case 0:
 		case -NFS4ERR_WRONGSEC:
-			break;
+			goto out;
 		default:
 			err = nfs4_handle_exception(server, err, &exception);
 		}
 	} while (exception.retry);
+out:
 	return err;
 }
 
@@ -3712,7 +3712,7 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		if (acl_len > buflen)
 			goto out_free;
 		_copy_from_pages(buf, pages, res.acl_data_offset,
-				res.acl_len);
+				acl_len);
 	}
 	ret = acl_len;
 out_free:
@@ -3824,8 +3824,9 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (state != NULL)
-				nfs_remove_bad_delegation(state->inode);
+			if (state == NULL)
+				break;
+			nfs_remove_bad_delegation(state->inode);
 		case -NFS4ERR_OPENMODE:
 			if (state == NULL)
 				break;
@@ -6111,21 +6112,22 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 		return;
 
 	switch (task->tk_status) { /* Just ignore these failures */
-	case NFS4ERR_DELEG_REVOKED: /* layout was recalled */
-	case NFS4ERR_BADIOMODE:     /* no IOMODE_RW layout for range */
-	case NFS4ERR_BADLAYOUT:     /* no layout */
-	case NFS4ERR_GRACE:	    /* loca_recalim always false */
+	case -NFS4ERR_DELEG_REVOKED: /* layout was recalled */
+	case -NFS4ERR_BADIOMODE:     /* no IOMODE_RW layout for range */
+	case -NFS4ERR_BADLAYOUT:     /* no layout */
+	case -NFS4ERR_GRACE:	    /* loca_recalim always false */
 		task->tk_status = 0;
-	}
-
-	if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
-		rpc_restart_call_prepare(task);
-		return;
-	}
-
-	if (task->tk_status == 0)
+		break;
+	case 0:
 		nfs_post_op_update_inode_force_wcc(data->args.inode,
 						   data->res.fattr);
+		break;
+	default:
+		if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+			rpc_restart_call_prepare(task);
+			return;
+		}
+	}
 }
 
 static void nfs4_layoutcommit_release(void *calldata)
@@ -6229,11 +6231,12 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 		case 0:
 		case -NFS4ERR_WRONGSEC:
 		case -NFS4ERR_NOTSUPP:
-			break;
+			goto out;
 		default:
 			err = nfs4_handle_exception(server, err, &exception);
 		}
 	} while (exception.retry);
+out:
 	return err;
 }
 
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index cc1f758a7ee1..9a0e8ef4a409 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -20,7 +20,6 @@
 #include <linux/nfs_page.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include "pnfs.h"
 
 #include "nfs4_fs.h"
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ccc4cdb1efe9..37412f706b32 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -55,7 +55,6 @@
 #include <linux/nsproxy.h>
 #include <linux/rcupdate.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "nfs4_fs.h"
diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h
new file mode 100644
index 000000000000..4123551208d8
--- /dev/null
+++ b/fs/nfsd/current_stateid.h
@@ -0,0 +1,28 @@
+#ifndef _NFSD4_CURRENT_STATE_H
+#define _NFSD4_CURRENT_STATE_H
+
+#include "state.h"
+#include "xdr4.h"
+
+extern void clear_current_stateid(struct nfsd4_compound_state *cstate);
+/*
+ * functions to set current state id
+ */
+extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
+extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, struct nfsd4_open *);
+extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, struct nfsd4_lock *);
+extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+
+/*
+ * functions to consume current state id
+ */
+extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
+extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, struct nfsd4_delegreturn *);
+extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, struct nfsd4_free_stateid *);
+extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, struct nfsd4_setattr *);
+extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, struct nfsd4_locku *);
+extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, struct nfsd4_read *);
+extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, struct nfsd4_write *);
+
+#endif   /* _NFSD4_CURRENT_STATE_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index cf8a6bd062fa..8e9689abbc0c 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -87,7 +87,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
 	struct svc_expkey key;
 	struct svc_expkey *ek = NULL;
 
-	if (mlen < 1 || mesg[mlen-1] != '\n')
+	if (mesg[mlen - 1] != '\n')
 		return -EINVAL;
 	mesg[mlen-1] = 0;
 
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
new file mode 100644
index 000000000000..12e0cff435b4
--- /dev/null
+++ b/fs/nfsd/netns.h
@@ -0,0 +1,34 @@
+/*
+ * per net namespace data structures for nfsd
+ *
+ * Copyright (C) 2012, Jeff Layton <jlayton@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 51
+ * Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+
+#ifndef __NFSD_NETNS_H__
+#define __NFSD_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+struct cld_net;
+
+struct nfsd_net {
+	struct cld_net *cld_net;
+};
+
+extern int nfsd_net_id;
+#endif /* __NFSD_NETNS_H__ */
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 0e262f32ac41..c8e9f637153a 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -645,7 +645,6 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		.timeout	= &timeparms,
 		.program	= &cb_program,
 		.version	= 0,
-		.authflavor	= clp->cl_flavor,
 		.flags		= (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
 	};
 	struct rpc_clnt *client;
@@ -656,6 +655,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		args.client_name = clp->cl_principal;
 		args.prognumber	= conn->cb_prog,
 		args.protocol = XPRT_TRANSPORT_TCP;
+		args.authflavor = clp->cl_flavor;
 		clp->cl_cb_ident = conn->cb_ident;
 	} else {
 		if (!conn->cb_xprt)
@@ -665,6 +665,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		args.bc_xprt = conn->cb_xprt;
 		args.prognumber = clp->cl_cb_session->se_cb_prog;
 		args.protocol = XPRT_TRANSPORT_BC_TCP;
+		args.authflavor = RPC_AUTH_UNIX;
 	}
 	/* Create RPC client */
 	client = rpc_create(&args);
@@ -754,9 +755,9 @@ static void do_probe_callback(struct nfs4_client *clp)
  */
 void nfsd4_probe_callback(struct nfs4_client *clp)
 {
-	/* XXX: atomicity?  Also, should we be using cl_cb_flags? */
+	/* XXX: atomicity?  Also, should we be using cl_flags? */
 	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
-	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags);
+	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
 	do_probe_callback(clp);
 }
 
@@ -915,7 +916,7 @@ void nfsd4_destroy_callback_queue(void)
 /* must be called under the state lock */
 void nfsd4_shutdown_callback(struct nfs4_client *clp)
 {
-	set_bit(NFSD4_CLIENT_KILL, &clp->cl_cb_flags);
+	set_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags);
 	/*
 	 * Note this won't actually result in a null callback;
 	 * instead, nfsd4_do_callback_rpc() will detect the killed
@@ -966,15 +967,15 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
 		clp->cl_cb_conn.cb_xprt = NULL;
 	}
-	if (test_bit(NFSD4_CLIENT_KILL, &clp->cl_cb_flags))
+	if (test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags))
 		return;
 	spin_lock(&clp->cl_lock);
 	/*
 	 * Only serialized callback code is allowed to clear these
 	 * flags; main nfsd code can only set them:
 	 */
-	BUG_ON(!clp->cl_cb_flags);
-	clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags);
+	BUG_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK));
+	clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
 	memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn));
 	c = __nfsd4_find_backchannel(clp);
 	if (c) {
@@ -986,7 +987,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 
 	err = setup_callback_client(clp, &conn, ses);
 	if (err) {
-		warn_no_callback_path(clp, err);
+		nfsd4_mark_cb_down(clp, err);
 		return;
 	}
 	/* Yay, the callback channel's back! Restart any callbacks: */
@@ -1000,7 +1001,7 @@ void nfsd4_do_callback_rpc(struct work_struct *w)
 	struct nfs4_client *clp = cb->cb_clp;
 	struct rpc_clnt *clnt;
 
-	if (clp->cl_cb_flags)
+	if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)
 		nfsd4_process_cb_update(cb);
 
 	clnt = clp->cl_cb_client;
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index 94096273cd6c..322d11ce06a4 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -41,6 +41,14 @@
 #include "nfsd.h"
 
 /*
+ * Turn off idmapping when using AUTH_SYS.
+ */
+static bool nfs4_disable_idmapping = true;
+module_param(nfs4_disable_idmapping, bool, 0644);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off server's NFSv4 idmapping when using 'sec=sys'");
+
+/*
  * Cache entry
  */
 
@@ -561,28 +569,65 @@ idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
 	return ret;
 }
 
+static bool
+numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id)
+{
+	int ret;
+	char buf[11];
+
+	if (namelen + 1 > sizeof(buf))
+		/* too long to represent a 32-bit id: */
+		return false;
+	/* Just to make sure it's null-terminated: */
+	memcpy(buf, name, namelen);
+	buf[namelen] = '\0';
+	ret = kstrtouint(name, 10, id);
+	return ret == 0;
+}
+
+static __be32
+do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_flavor < RPC_AUTH_GSS)
+		if (numeric_name_to_id(rqstp, type, name, namelen, id))
+			return 0;
+		/*
+		 * otherwise, fall through and try idmapping, for
+		 * backwards compatibility with clients sending names:
+		 */
+	return idmap_name_to_id(rqstp, type, name, namelen, id);
+}
+
+static int
+do_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_flavor < RPC_AUTH_GSS)
+		return sprintf(name, "%u", id);
+	return idmap_id_to_name(rqstp, type, id, name);
+}
+
 __be32
 nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 		__u32 *id)
 {
-	return idmap_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, id);
+	return do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, id);
 }
 
 __be32
 nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 		__u32 *id)
 {
-	return idmap_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, id);
+	return do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, id);
 }
 
 int
 nfsd_map_uid_to_name(struct svc_rqst *rqstp, __u32 id, char *name)
 {
-	return idmap_id_to_name(rqstp, IDMAP_TYPE_USER, id, name);
+	return do_id_to_name(rqstp, IDMAP_TYPE_USER, id, name);
 }
 
 int
 nfsd_map_gid_to_name(struct svc_rqst *rqstp, __u32 id, char *name)
 {
-	return idmap_id_to_name(rqstp, IDMAP_TYPE_GROUP, id, name);
+	return do_id_to_name(rqstp, IDMAP_TYPE_GROUP, id, name);
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 896da74ec563..2ed14dfd00a2 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -39,6 +39,7 @@
 #include "cache.h"
 #include "xdr4.h"
 #include "vfs.h"
+#include "current_stateid.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_PROC
 
@@ -192,10 +193,13 @@ static __be32 nfsd_check_obj_isreg(struct svc_fh *fh)
 static __be32
 do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
 {
-	struct svc_fh resfh;
+	struct svc_fh *resfh;
 	__be32 status;
 
-	fh_init(&resfh, NFS4_FHSIZE);
+	resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
+	if (!resfh)
+		return nfserr_jukebox;
+	fh_init(resfh, NFS4_FHSIZE);
 	open->op_truncate = 0;
 
 	if (open->op_create) {
@@ -220,7 +224,7 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 		 */
 		status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
 					open->op_fname.len, &open->op_iattr,
-					&resfh, open->op_createmode,
+					resfh, open->op_createmode,
 					(u32 *)open->op_verf.data,
 					&open->op_truncate, &open->op_created);
 
@@ -234,30 +238,29 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 						FATTR4_WORD1_TIME_MODIFY);
 	} else {
 		status = nfsd_lookup(rqstp, current_fh,
-				     open->op_fname.data, open->op_fname.len, &resfh);
+				     open->op_fname.data, open->op_fname.len, resfh);
 		fh_unlock(current_fh);
 		if (status)
 			goto out;
-		status = nfsd_check_obj_isreg(&resfh);
+		status = nfsd_check_obj_isreg(resfh);
 	}
 	if (status)
 		goto out;
 
 	if (is_create_with_attrs(open) && open->op_acl != NULL)
-		do_set_nfs4_acl(rqstp, &resfh, open->op_acl, open->op_bmval);
-
-	set_change_info(&open->op_cinfo, current_fh);
-	fh_dup2(current_fh, &resfh);
+		do_set_nfs4_acl(rqstp, resfh, open->op_acl, open->op_bmval);
 
 	/* set reply cache */
 	fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh,
-			&resfh.fh_handle);
+			&resfh->fh_handle);
 	if (!open->op_created)
-		status = do_open_permission(rqstp, current_fh, open,
+		status = do_open_permission(rqstp, resfh, open,
 					    NFSD_MAY_NOP);
-
+	set_change_info(&open->op_cinfo, current_fh);
+	fh_dup2(current_fh, resfh);
 out:
-	fh_put(&resfh);
+	fh_put(resfh);
+	kfree(resfh);
 	return status;
 }
 
@@ -310,16 +313,14 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
 		return nfserr_inval;
 
-	/* We don't yet support WANT bits: */
-	open->op_share_access &= NFS4_SHARE_ACCESS_MASK;
-
 	open->op_created = 0;
 	/*
 	 * RFC5661 18.51.3
 	 * Before RECLAIM_COMPLETE done, server should deny new lock
 	 */
 	if (nfsd4_has_session(cstate) &&
-	    !cstate->session->se_client->cl_firststate &&
+	    !test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE,
+		      &cstate->session->se_client->cl_flags) &&
 	    open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
 		return nfserr_grace;
 
@@ -452,6 +453,10 @@ nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_restorefh;
 
 	fh_dup2(&cstate->current_fh, &cstate->save_fh);
+	if (HAS_STATE_ID(cstate, SAVED_STATE_ID_FLAG)) {
+		memcpy(&cstate->current_stateid, &cstate->save_stateid, sizeof(stateid_t));
+		SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+	}
 	return nfs_ok;
 }
 
@@ -463,6 +468,10 @@ nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_nofilehandle;
 
 	fh_dup2(&cstate->save_fh, &cstate->current_fh);
+	if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG)) {
+		memcpy(&cstate->save_stateid, &cstate->current_stateid, sizeof(stateid_t));
+		SET_STATE_ID(cstate, SAVED_STATE_ID_FLAG);
+	}
 	return nfs_ok;
 }
 
@@ -481,14 +490,20 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			   &access->ac_supported);
 }
 
+static void gen_boot_verifier(nfs4_verifier *verifier)
+{
+	__be32 verf[2];
+
+	verf[0] = (__be32)nfssvc_boot.tv_sec;
+	verf[1] = (__be32)nfssvc_boot.tv_usec;
+	memcpy(verifier->data, verf, sizeof(verifier->data));
+}
+
 static __be32
 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	     struct nfsd4_commit *commit)
 {
-	u32 *p = (u32 *)commit->co_verf.data;
-	*p++ = nfssvc_boot.tv_sec;
-	*p++ = nfssvc_boot.tv_usec;
-
+	gen_boot_verifier(&commit->co_verf);
 	return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
 			     commit->co_count);
 }
@@ -865,7 +880,6 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	stateid_t *stateid = &write->wr_stateid;
 	struct file *filp = NULL;
-	u32 *p;
 	__be32 status = nfs_ok;
 	unsigned long cnt;
 
@@ -887,9 +901,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	cnt = write->wr_buflen;
 	write->wr_how_written = write->wr_stable_how;
-	p = (u32 *)write->wr_verifier.data;
-	*p++ = nfssvc_boot.tv_sec;
-	*p++ = nfssvc_boot.tv_usec;
+	gen_boot_verifier(&write->wr_verifier);
 
 	status =  nfsd_write(rqstp, &cstate->current_fh, filp,
 			     write->wr_offset, rqstp->rq_vec, write->wr_vlen,
@@ -1000,6 +1012,8 @@ static inline void nfsd4_increment_op_stats(u32 opnum)
 typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
 			      void *);
 typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op);
+typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *);
+typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *);
 
 enum nfsd4_op_flags {
 	ALLOWED_WITHOUT_FH = 1 << 0,	/* No current filehandle required */
@@ -1025,6 +1039,10 @@ enum nfsd4_op_flags {
 	 * the v4.0 case).
 	 */
 	OP_CACHEME = 1 << 6,
+	/*
+	 * These are ops which clear current state id.
+	 */
+	OP_CLEAR_STATEID = 1 << 7,
 };
 
 struct nfsd4_operation {
@@ -1033,11 +1051,15 @@ struct nfsd4_operation {
 	char *op_name;
 	/* Try to get response size before operation */
 	nfsd4op_rsize op_rsize_bop;
+	stateid_setter op_get_currentstateid;
+	stateid_getter op_set_currentstateid;
 };
 
 static struct nfsd4_operation nfsd4_ops[];
 
+#ifdef NFSD_DEBUG
 static const char *nfsd4_op_name(unsigned opnum);
+#endif
 
 /*
  * Enforce NFSv4.1 COMPOUND ordering rules:
@@ -1215,13 +1237,23 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 		if (op->status)
 			goto encode_op;
 
-		if (opdesc->op_func)
+		if (opdesc->op_func) {
+			if (opdesc->op_get_currentstateid)
+				opdesc->op_get_currentstateid(cstate, &op->u);
 			op->status = opdesc->op_func(rqstp, cstate, &op->u);
-		else
+		} else
 			BUG_ON(op->status == nfs_ok);
 
-		if (!op->status && need_wrongsec_check(rqstp))
-			op->status = check_nfsd_access(cstate->current_fh.fh_export, rqstp);
+		if (!op->status) {
+			if (opdesc->op_set_currentstateid)
+				opdesc->op_set_currentstateid(cstate, &op->u);
+
+			if (opdesc->op_flags & OP_CLEAR_STATEID)
+				clear_current_stateid(cstate);
+
+			if (need_wrongsec_check(rqstp))
+				op->status = check_nfsd_access(cstate->current_fh.fh_export, rqstp);
+		}
 
 encode_op:
 		/* Only from SEQUENCE */
@@ -1413,6 +1445,8 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_CLOSE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid,
+		.op_set_currentstateid = (stateid_setter)nfsd4_set_closestateid,
 	},
 	[OP_COMMIT] = {
 		.op_func = (nfsd4op_func)nfsd4_commit,
@@ -1422,7 +1456,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 	[OP_CREATE] = {
 		.op_func = (nfsd4op_func)nfsd4_create,
-		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID,
 		.op_name = "OP_CREATE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_create_rsize,
 	},
@@ -1431,6 +1465,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_DELEGRETURN",
 		.op_rsize_bop = nfsd4_only_status_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_delegreturnstateid,
 	},
 	[OP_GETATTR] = {
 		.op_func = (nfsd4op_func)nfsd4_getattr,
@@ -1453,6 +1488,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LOCK",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize,
+		.op_set_currentstateid = (stateid_setter)nfsd4_set_lockstateid,
 	},
 	[OP_LOCKT] = {
 		.op_func = (nfsd4op_func)nfsd4_lockt,
@@ -1463,15 +1499,16 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LOCKU",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_lockustateid,
 	},
 	[OP_LOOKUP] = {
 		.op_func = (nfsd4op_func)nfsd4_lookup,
-		.op_flags = OP_HANDLES_WRONGSEC,
+		.op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
 		.op_name = "OP_LOOKUP",
 	},
 	[OP_LOOKUPP] = {
 		.op_func = (nfsd4op_func)nfsd4_lookupp,
-		.op_flags = OP_HANDLES_WRONGSEC,
+		.op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
 		.op_name = "OP_LOOKUPP",
 	},
 	[OP_NVERIFY] = {
@@ -1483,6 +1520,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING,
 		.op_name = "OP_OPEN",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize,
+		.op_set_currentstateid = (stateid_setter)nfsd4_set_openstateid,
 	},
 	[OP_OPEN_CONFIRM] = {
 		.op_func = (nfsd4op_func)nfsd4_open_confirm,
@@ -1495,25 +1533,30 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_OPEN_DOWNGRADE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid,
+		.op_set_currentstateid = (stateid_setter)nfsd4_set_opendowngradestateid,
 	},
 	[OP_PUTFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+				| OP_CLEAR_STATEID,
 		.op_name = "OP_PUTFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
 	[OP_PUTPUBFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+				| OP_CLEAR_STATEID,
 		.op_name = "OP_PUTPUBFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
 	[OP_PUTROOTFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+				| OP_CLEAR_STATEID,
 		.op_name = "OP_PUTROOTFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
@@ -1522,6 +1565,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_READ",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid,
 	},
 	[OP_READDIR] = {
 		.op_func = (nfsd4op_func)nfsd4_readdir,
@@ -1576,6 +1620,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_name = "OP_SETATTR",
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_setattrstateid,
 	},
 	[OP_SETCLIENTID] = {
 		.op_func = (nfsd4op_func)nfsd4_setclientid,
@@ -1600,6 +1645,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_WRITE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize,
+		.op_get_currentstateid = (stateid_getter)nfsd4_get_writestateid,
 	},
 	[OP_RELEASE_LOCKOWNER] = {
 		.op_func = (nfsd4op_func)nfsd4_release_lockowner,
@@ -1674,12 +1720,14 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 };
 
+#ifdef NFSD_DEBUG
 static const char *nfsd4_op_name(unsigned opnum)
 {
 	if (opnum < ARRAY_SIZE(nfsd4_ops))
 		return nfsd4_ops[opnum].op_name;
 	return "unknown_operation";
 }
+#endif
 
 #define nfsd4_voidres			nfsd4_voidargs
 struct nfsd4_voidargs { int dummy; };
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 0b3e875d1abd..4767429264a2 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -1,5 +1,6 @@
 /*
 *  Copyright (c) 2004 The Regents of the University of Michigan.
+*  Copyright (c) 2012 Jeff Layton <jlayton@redhat.com>
 *  All rights reserved.
 *
 *  Andy Adamson <andros@citi.umich.edu>
@@ -36,16 +37,34 @@
 #include <linux/namei.h>
 #include <linux/crypto.h>
 #include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <net/net_namespace.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/nfsd/cld.h>
 
 #include "nfsd.h"
 #include "state.h"
 #include "vfs.h"
+#include "netns.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
+/* Declarations */
+struct nfsd4_client_tracking_ops {
+	int (*init)(struct net *);
+	void (*exit)(struct net *);
+	void (*create)(struct nfs4_client *);
+	void (*remove)(struct nfs4_client *);
+	int (*check)(struct nfs4_client *);
+	void (*grace_done)(struct net *, time_t);
+};
+
 /* Globals */
 static struct file *rec_file;
 static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
+static struct nfsd4_client_tracking_ops *client_tracking_ops;
 
 static int
 nfs4_save_creds(const struct cred **original_creds)
@@ -117,7 +136,8 @@ out_no_tfm:
 	return status;
 }
 
-void nfsd4_create_clid_dir(struct nfs4_client *clp)
+static void
+nfsd4_create_clid_dir(struct nfs4_client *clp)
 {
 	const struct cred *original_cred;
 	char *dname = clp->cl_recdir;
@@ -126,9 +146,8 @@ void nfsd4_create_clid_dir(struct nfs4_client *clp)
 
 	dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname);
 
-	if (clp->cl_firststate)
+	if (test_and_set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
 		return;
-	clp->cl_firststate = 1;
 	if (!rec_file)
 		return;
 	status = nfs4_save_creds(&original_cred);
@@ -265,19 +284,19 @@ out_unlock:
 	return status;
 }
 
-void
+static void
 nfsd4_remove_clid_dir(struct nfs4_client *clp)
 {
 	const struct cred *original_cred;
 	int status;
 
-	if (!rec_file || !clp->cl_firststate)
+	if (!rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
 		return;
 
 	status = mnt_want_write_file(rec_file);
 	if (status)
 		goto out;
-	clp->cl_firststate = 0;
+	clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
 
 	status = nfs4_save_creds(&original_cred);
 	if (status < 0)
@@ -292,7 +311,6 @@ out:
 	if (status)
 		printk("NFSD: Failed to remove expired client state directory"
 				" %.*s\n", HEXDIR_LEN, clp->cl_recdir);
-	return;
 }
 
 static int
@@ -311,8 +329,9 @@ purge_old(struct dentry *parent, struct dentry *child)
 	return 0;
 }
 
-void
-nfsd4_recdir_purge_old(void) {
+static void
+nfsd4_recdir_purge_old(struct net *net, time_t boot_time)
+{
 	int status;
 
 	if (!rec_file)
@@ -343,7 +362,7 @@ load_recdir(struct dentry *parent, struct dentry *child)
 	return 0;
 }
 
-int
+static int
 nfsd4_recdir_load(void) {
 	int status;
 
@@ -361,8 +380,8 @@ nfsd4_recdir_load(void) {
  * Hold reference to the recovery directory.
  */
 
-void
-nfsd4_init_recdir()
+static int
+nfsd4_init_recdir(void)
 {
 	const struct cred *original_cred;
 	int status;
@@ -377,20 +396,44 @@ nfsd4_init_recdir()
 		printk("NFSD: Unable to change credentials to find recovery"
 		       " directory: error %d\n",
 		       status);
-		return;
+		return status;
 	}
 
 	rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0);
 	if (IS_ERR(rec_file)) {
 		printk("NFSD: unable to find recovery directory %s\n",
 				user_recovery_dirname);
+		status = PTR_ERR(rec_file);
 		rec_file = NULL;
 	}
 
 	nfs4_reset_creds(original_cred);
+	return status;
 }
 
-void
+static int
+nfsd4_load_reboot_recovery_data(struct net *net)
+{
+	int status;
+
+	/* XXX: The legacy code won't work in a container */
+	if (net != &init_net) {
+		WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client "
+			"tracking in a container!\n");
+		return -EINVAL;
+	}
+
+	nfs4_lock_state();
+	status = nfsd4_init_recdir();
+	if (!status)
+		status = nfsd4_recdir_load();
+	nfs4_unlock_state();
+	if (status)
+		printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
+	return status;
+}
+
+static void
 nfsd4_shutdown_recdir(void)
 {
 	if (!rec_file)
@@ -399,6 +442,13 @@ nfsd4_shutdown_recdir(void)
 	rec_file = NULL;
 }
 
+static void
+nfsd4_legacy_tracking_exit(struct net *net)
+{
+	nfs4_release_reclaim();
+	nfsd4_shutdown_recdir();
+}
+
 /*
  * Change the NFSv4 recovery directory to recdir.
  */
@@ -425,3 +475,572 @@ nfs4_recoverydir(void)
 {
 	return user_recovery_dirname;
 }
+
+static int
+nfsd4_check_legacy_client(struct nfs4_client *clp)
+{
+	/* did we already find that this client is stable? */
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return 0;
+
+	/* look for it in the reclaim hashtable otherwise */
+	if (nfsd4_find_reclaim_client(clp)) {
+		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
+	.init		= nfsd4_load_reboot_recovery_data,
+	.exit		= nfsd4_legacy_tracking_exit,
+	.create		= nfsd4_create_clid_dir,
+	.remove		= nfsd4_remove_clid_dir,
+	.check		= nfsd4_check_legacy_client,
+	.grace_done	= nfsd4_recdir_purge_old,
+};
+
+/* Globals */
+#define NFSD_PIPE_DIR		"nfsd"
+#define NFSD_CLD_PIPE		"cld"
+
+/* per-net-ns structure for holding cld upcall info */
+struct cld_net {
+	struct rpc_pipe		*cn_pipe;
+	spinlock_t		 cn_lock;
+	struct list_head	 cn_list;
+	unsigned int		 cn_xid;
+};
+
+struct cld_upcall {
+	struct list_head	 cu_list;
+	struct cld_net		*cu_net;
+	struct task_struct	*cu_task;
+	struct cld_msg		 cu_msg;
+};
+
+static int
+__cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg)
+{
+	int ret;
+	struct rpc_pipe_msg msg;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.data = cmsg;
+	msg.len = sizeof(*cmsg);
+
+	/*
+	 * Set task state before we queue the upcall. That prevents
+	 * wake_up_process in the downcall from racing with schedule.
+	 */
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	ret = rpc_queue_upcall(pipe, &msg);
+	if (ret < 0) {
+		set_current_state(TASK_RUNNING);
+		goto out;
+	}
+
+	schedule();
+	set_current_state(TASK_RUNNING);
+
+	if (msg.errno < 0)
+		ret = msg.errno;
+out:
+	return ret;
+}
+
+static int
+cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg)
+{
+	int ret;
+
+	/*
+	 * -EAGAIN occurs when pipe is closed and reopened while there are
+	 *  upcalls queued.
+	 */
+	do {
+		ret = __cld_pipe_upcall(pipe, cmsg);
+	} while (ret == -EAGAIN);
+
+	return ret;
+}
+
+static ssize_t
+cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
+{
+	struct cld_upcall *tmp, *cup;
+	struct cld_msg *cmsg = (struct cld_msg *)src;
+	uint32_t xid;
+	struct nfsd_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
+						nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	if (mlen != sizeof(*cmsg)) {
+		dprintk("%s: got %lu bytes, expected %lu\n", __func__, mlen,
+			sizeof(*cmsg));
+		return -EINVAL;
+	}
+
+	/* copy just the xid so we can try to find that */
+	if (copy_from_user(&xid, &cmsg->cm_xid, sizeof(xid)) != 0) {
+		dprintk("%s: error when copying xid from userspace", __func__);
+		return -EFAULT;
+	}
+
+	/* walk the list and find corresponding xid */
+	cup = NULL;
+	spin_lock(&cn->cn_lock);
+	list_for_each_entry(tmp, &cn->cn_list, cu_list) {
+		if (get_unaligned(&tmp->cu_msg.cm_xid) == xid) {
+			cup = tmp;
+			list_del_init(&cup->cu_list);
+			break;
+		}
+	}
+	spin_unlock(&cn->cn_lock);
+
+	/* couldn't find upcall? */
+	if (!cup) {
+		dprintk("%s: couldn't find upcall -- xid=%u\n", __func__, xid);
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&cup->cu_msg, src, mlen) != 0)
+		return -EFAULT;
+
+	wake_up_process(cup->cu_task);
+	return mlen;
+}
+
+static void
+cld_pipe_destroy_msg(struct rpc_pipe_msg *msg)
+{
+	struct cld_msg *cmsg = msg->data;
+	struct cld_upcall *cup = container_of(cmsg, struct cld_upcall,
+						 cu_msg);
+
+	/* errno >= 0 means we got a downcall */
+	if (msg->errno >= 0)
+		return;
+
+	wake_up_process(cup->cu_task);
+}
+
+static const struct rpc_pipe_ops cld_upcall_ops = {
+	.upcall		= rpc_pipe_generic_upcall,
+	.downcall	= cld_pipe_downcall,
+	.destroy_msg	= cld_pipe_destroy_msg,
+};
+
+static struct dentry *
+nfsd4_cld_register_sb(struct super_block *sb, struct rpc_pipe *pipe)
+{
+	struct dentry *dir, *dentry;
+
+	dir = rpc_d_lookup_sb(sb, NFSD_PIPE_DIR);
+	if (dir == NULL)
+		return ERR_PTR(-ENOENT);
+	dentry = rpc_mkpipe_dentry(dir, NFSD_CLD_PIPE, NULL, pipe);
+	dput(dir);
+	return dentry;
+}
+
+static void
+nfsd4_cld_unregister_sb(struct rpc_pipe *pipe)
+{
+	if (pipe->dentry)
+		rpc_unlink(pipe->dentry);
+}
+
+static struct dentry *
+nfsd4_cld_register_net(struct net *net, struct rpc_pipe *pipe)
+{
+	struct super_block *sb;
+	struct dentry *dentry;
+
+	sb = rpc_get_sb_net(net);
+	if (!sb)
+		return NULL;
+	dentry = nfsd4_cld_register_sb(sb, pipe);
+	rpc_put_sb_net(net);
+	return dentry;
+}
+
+static void
+nfsd4_cld_unregister_net(struct net *net, struct rpc_pipe *pipe)
+{
+	struct super_block *sb;
+
+	sb = rpc_get_sb_net(net);
+	if (sb) {
+		nfsd4_cld_unregister_sb(pipe);
+		rpc_put_sb_net(net);
+	}
+}
+
+/* Initialize rpc_pipefs pipe for communication with client tracking daemon */
+static int
+nfsd4_init_cld_pipe(struct net *net)
+{
+	int ret;
+	struct dentry *dentry;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct cld_net *cn;
+
+	if (nn->cld_net)
+		return 0;
+
+	cn = kzalloc(sizeof(*cn), GFP_KERNEL);
+	if (!cn) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	cn->cn_pipe = rpc_mkpipe_data(&cld_upcall_ops, RPC_PIPE_WAIT_FOR_OPEN);
+	if (IS_ERR(cn->cn_pipe)) {
+		ret = PTR_ERR(cn->cn_pipe);
+		goto err;
+	}
+	spin_lock_init(&cn->cn_lock);
+	INIT_LIST_HEAD(&cn->cn_list);
+
+	dentry = nfsd4_cld_register_net(net, cn->cn_pipe);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto err_destroy_data;
+	}
+
+	cn->cn_pipe->dentry = dentry;
+	nn->cld_net = cn;
+	return 0;
+
+err_destroy_data:
+	rpc_destroy_pipe_data(cn->cn_pipe);
+err:
+	kfree(cn);
+	printk(KERN_ERR "NFSD: unable to create nfsdcld upcall pipe (%d)\n",
+			ret);
+	return ret;
+}
+
+static void
+nfsd4_remove_cld_pipe(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	nfsd4_cld_unregister_net(net, cn->cn_pipe);
+	rpc_destroy_pipe_data(cn->cn_pipe);
+	kfree(nn->cld_net);
+	nn->cld_net = NULL;
+}
+
+static struct cld_upcall *
+alloc_cld_upcall(struct cld_net *cn)
+{
+	struct cld_upcall *new, *tmp;
+
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return new;
+
+	/* FIXME: hard cap on number in flight? */
+restart_search:
+	spin_lock(&cn->cn_lock);
+	list_for_each_entry(tmp, &cn->cn_list, cu_list) {
+		if (tmp->cu_msg.cm_xid == cn->cn_xid) {
+			cn->cn_xid++;
+			spin_unlock(&cn->cn_lock);
+			goto restart_search;
+		}
+	}
+	new->cu_task = current;
+	new->cu_msg.cm_vers = CLD_UPCALL_VERSION;
+	put_unaligned(cn->cn_xid++, &new->cu_msg.cm_xid);
+	new->cu_net = cn;
+	list_add(&new->cu_list, &cn->cn_list);
+	spin_unlock(&cn->cn_lock);
+
+	dprintk("%s: allocated xid %u\n", __func__, new->cu_msg.cm_xid);
+
+	return new;
+}
+
+static void
+free_cld_upcall(struct cld_upcall *victim)
+{
+	struct cld_net *cn = victim->cu_net;
+
+	spin_lock(&cn->cn_lock);
+	list_del(&victim->cu_list);
+	spin_unlock(&cn->cn_lock);
+	kfree(victim);
+}
+
+/* Ask daemon to create a new record */
+static void
+nfsd4_cld_create(struct nfs4_client *clp)
+{
+	int ret;
+	struct cld_upcall *cup;
+	/* FIXME: determine net from clp */
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	/* Don't upcall if it's already stored */
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return;
+
+	cup = alloc_cld_upcall(cn);
+	if (!cup) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	cup->cu_msg.cm_cmd = Cld_Create;
+	cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
+	memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
+			clp->cl_name.len);
+
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
+	if (!ret) {
+		ret = cup->cu_msg.cm_status;
+		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	}
+
+	free_cld_upcall(cup);
+out_err:
+	if (ret)
+		printk(KERN_ERR "NFSD: Unable to create client "
+				"record on stable storage: %d\n", ret);
+}
+
+/* Ask daemon to create a new record */
+static void
+nfsd4_cld_remove(struct nfs4_client *clp)
+{
+	int ret;
+	struct cld_upcall *cup;
+	/* FIXME: determine net from clp */
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	/* Don't upcall if it's already removed */
+	if (!test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return;
+
+	cup = alloc_cld_upcall(cn);
+	if (!cup) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	cup->cu_msg.cm_cmd = Cld_Remove;
+	cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
+	memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
+			clp->cl_name.len);
+
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
+	if (!ret) {
+		ret = cup->cu_msg.cm_status;
+		clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	}
+
+	free_cld_upcall(cup);
+out_err:
+	if (ret)
+		printk(KERN_ERR "NFSD: Unable to remove client "
+				"record from stable storage: %d\n", ret);
+}
+
+/* Check for presence of a record, and update its timestamp */
+static int
+nfsd4_cld_check(struct nfs4_client *clp)
+{
+	int ret;
+	struct cld_upcall *cup;
+	/* FIXME: determine net from clp */
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	/* Don't upcall if one was already stored during this grace pd */
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return 0;
+
+	cup = alloc_cld_upcall(cn);
+	if (!cup) {
+		printk(KERN_ERR "NFSD: Unable to check client record on "
+				"stable storage: %d\n", -ENOMEM);
+		return -ENOMEM;
+	}
+
+	cup->cu_msg.cm_cmd = Cld_Check;
+	cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
+	memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
+			clp->cl_name.len);
+
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
+	if (!ret) {
+		ret = cup->cu_msg.cm_status;
+		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	}
+
+	free_cld_upcall(cup);
+	return ret;
+}
+
+static void
+nfsd4_cld_grace_done(struct net *net, time_t boot_time)
+{
+	int ret;
+	struct cld_upcall *cup;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+
+	cup = alloc_cld_upcall(cn);
+	if (!cup) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	cup->cu_msg.cm_cmd = Cld_GraceDone;
+	cup->cu_msg.cm_u.cm_gracetime = (int64_t)boot_time;
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
+	if (!ret)
+		ret = cup->cu_msg.cm_status;
+
+	free_cld_upcall(cup);
+out_err:
+	if (ret)
+		printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret);
+}
+
+static struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = {
+	.init		= nfsd4_init_cld_pipe,
+	.exit		= nfsd4_remove_cld_pipe,
+	.create		= nfsd4_cld_create,
+	.remove		= nfsd4_cld_remove,
+	.check		= nfsd4_cld_check,
+	.grace_done	= nfsd4_cld_grace_done,
+};
+
+int
+nfsd4_client_tracking_init(struct net *net)
+{
+	int status;
+	struct path path;
+
+	if (!client_tracking_ops) {
+		client_tracking_ops = &nfsd4_cld_tracking_ops;
+		status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
+		if (!status) {
+			if (S_ISDIR(path.dentry->d_inode->i_mode))
+				client_tracking_ops =
+						&nfsd4_legacy_tracking_ops;
+			path_put(&path);
+		}
+	}
+
+	status = client_tracking_ops->init(net);
+	if (status) {
+		printk(KERN_WARNING "NFSD: Unable to initialize client "
+				    "recovery tracking! (%d)\n", status);
+		client_tracking_ops = NULL;
+	}
+	return status;
+}
+
+void
+nfsd4_client_tracking_exit(struct net *net)
+{
+	if (client_tracking_ops) {
+		client_tracking_ops->exit(net);
+		client_tracking_ops = NULL;
+	}
+}
+
+void
+nfsd4_client_record_create(struct nfs4_client *clp)
+{
+	if (client_tracking_ops)
+		client_tracking_ops->create(clp);
+}
+
+void
+nfsd4_client_record_remove(struct nfs4_client *clp)
+{
+	if (client_tracking_ops)
+		client_tracking_ops->remove(clp);
+}
+
+int
+nfsd4_client_record_check(struct nfs4_client *clp)
+{
+	if (client_tracking_ops)
+		return client_tracking_ops->check(clp);
+
+	return -EOPNOTSUPP;
+}
+
+void
+nfsd4_record_grace_done(struct net *net, time_t boot_time)
+{
+	if (client_tracking_ops)
+		client_tracking_ops->grace_done(net, boot_time);
+}
+
+static int
+rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr)
+{
+	struct super_block *sb = ptr;
+	struct net *net = sb->s_fs_info;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct cld_net *cn = nn->cld_net;
+	struct dentry *dentry;
+	int ret = 0;
+
+	if (!try_module_get(THIS_MODULE))
+		return 0;
+
+	if (!cn) {
+		module_put(THIS_MODULE);
+		return 0;
+	}
+
+	switch (event) {
+	case RPC_PIPEFS_MOUNT:
+		dentry = nfsd4_cld_register_sb(sb, cn->cn_pipe);
+		if (IS_ERR(dentry)) {
+			ret = PTR_ERR(dentry);
+			break;
+		}
+		cn->cn_pipe->dentry = dentry;
+		break;
+	case RPC_PIPEFS_UMOUNT:
+		if (cn->cn_pipe->dentry)
+			nfsd4_cld_unregister_sb(cn->cn_pipe);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+struct notifier_block nfsd4_cld_block = {
+	.notifier_call = rpc_pipefs_event,
+};
+
+int
+register_cld_notifier(void)
+{
+	return rpc_pipefs_notifier_register(&nfsd4_cld_block);
+}
+
+void
+unregister_cld_notifier(void)
+{
+	rpc_pipefs_notifier_unregister(&nfsd4_cld_block);
+}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c5cddd659429..1841f8bf845e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -58,11 +58,15 @@ static const stateid_t one_stateid = {
 static const stateid_t zero_stateid = {
 	/* all fields zero */
 };
+static const stateid_t currentstateid = {
+	.si_generation = 1,
+};
 
 static u64 current_sessionid = 1;
 
 #define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t)))
 #define ONE_STATEID(stateid)  (!memcmp((stateid), &one_stateid, sizeof(stateid_t)))
+#define CURRENT_STATEID(stateid) (!memcmp((stateid), &currentstateid, sizeof(stateid_t)))
 
 /* forward declarations */
 static int check_for_locks(struct nfs4_file *filp, struct nfs4_lockowner *lowner);
@@ -91,6 +95,19 @@ nfs4_lock_state(void)
 	mutex_lock(&client_mutex);
 }
 
+static void free_session(struct kref *);
+
+/* Must be called under the client_lock */
+static void nfsd4_put_session_locked(struct nfsd4_session *ses)
+{
+	kref_put(&ses->se_ref, free_session);
+}
+
+static void nfsd4_get_session(struct nfsd4_session *ses)
+{
+	kref_get(&ses->se_ref);
+}
+
 void
 nfs4_unlock_state(void)
 {
@@ -605,12 +622,20 @@ hash_sessionid(struct nfs4_sessionid *sessionid)
 	return sid->sequence % SESSION_HASH_SIZE;
 }
 
+#ifdef NFSD_DEBUG
 static inline void
 dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
 {
 	u32 *ptr = (u32 *)(&sessionid->data[0]);
 	dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]);
 }
+#else
+static inline void
+dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
+{
+}
+#endif
+
 
 static void
 gen_sessionid(struct nfsd4_session *ses)
@@ -832,11 +857,12 @@ static void nfsd4_del_conns(struct nfsd4_session *s)
 	spin_unlock(&clp->cl_lock);
 }
 
-void free_session(struct kref *kref)
+static void free_session(struct kref *kref)
 {
 	struct nfsd4_session *ses;
 	int mem;
 
+	BUG_ON(!spin_is_locked(&client_lock));
 	ses = container_of(kref, struct nfsd4_session, se_ref);
 	nfsd4_del_conns(ses);
 	spin_lock(&nfsd_drc_lock);
@@ -847,6 +873,13 @@ void free_session(struct kref *kref)
 	kfree(ses);
 }
 
+void nfsd4_put_session(struct nfsd4_session *ses)
+{
+	spin_lock(&client_lock);
+	nfsd4_put_session_locked(ses);
+	spin_unlock(&client_lock);
+}
+
 static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, struct nfsd4_create_session *cses)
 {
 	struct nfsd4_session *new;
@@ -894,7 +927,9 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n
 	status = nfsd4_new_conn_from_crses(rqstp, new);
 	/* whoops: benny points out, status is ignored! (err, or bogus) */
 	if (status) {
+		spin_lock(&client_lock);
 		free_session(&new->se_ref);
+		spin_unlock(&client_lock);
 		return NULL;
 	}
 	if (cses->flags & SESSION4_BACK_CHAN) {
@@ -1006,12 +1041,13 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 static inline void
 free_client(struct nfs4_client *clp)
 {
+	BUG_ON(!spin_is_locked(&client_lock));
 	while (!list_empty(&clp->cl_sessions)) {
 		struct nfsd4_session *ses;
 		ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
 				se_perclnt);
 		list_del(&ses->se_perclnt);
-		nfsd4_put_session(ses);
+		nfsd4_put_session_locked(ses);
 	}
 	if (clp->cl_cred.cr_group_info)
 		put_group_info(clp->cl_cred.cr_group_info);
@@ -1138,12 +1174,12 @@ static void gen_clid(struct nfs4_client *clp)
 
 static void gen_confirm(struct nfs4_client *clp)
 {
+	__be32 verf[2];
 	static u32 i;
-	u32 *p;
 
-	p = (u32 *)clp->cl_confirm.data;
-	*p++ = get_seconds();
-	*p++ = i++;
+	verf[0] = (__be32)get_seconds();
+	verf[1] = (__be32)i++;
+	memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data));
 }
 
 static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
@@ -1180,7 +1216,9 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir,
 	if (princ) {
 		clp->cl_principal = kstrdup(princ, GFP_KERNEL);
 		if (clp->cl_principal == NULL) {
+			spin_lock(&client_lock);
 			free_client(clp);
+			spin_unlock(&client_lock);
 			return NULL;
 		}
 	}
@@ -1347,6 +1385,7 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
 	slot->sl_opcnt = resp->opcnt;
 	slot->sl_status = resp->cstate.status;
 
+	slot->sl_flags |= NFSD4_SLOT_INITIALIZED;
 	if (nfsd4_not_cached(resp)) {
 		slot->sl_datalen = 0;
 		return;
@@ -1374,15 +1413,12 @@ nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args,
 	struct nfsd4_op *op;
 	struct nfsd4_slot *slot = resp->cstate.slot;
 
-	dprintk("--> %s resp->opcnt %d cachethis %u \n", __func__,
-		resp->opcnt, resp->cstate.slot->sl_cachethis);
-
 	/* Encode the replayed sequence operation */
 	op = &args->ops[resp->opcnt - 1];
 	nfsd4_encode_operation(resp, op);
 
 	/* Return nfserr_retry_uncached_rep in next operation. */
-	if (args->opcnt > 1 && slot->sl_cachethis == 0) {
+	if (args->opcnt > 1 && !(slot->sl_flags & NFSD4_SLOT_CACHETHIS)) {
 		op = &args->ops[resp->opcnt++];
 		op->status = nfserr_retry_uncached_rep;
 		nfsd4_encode_operation(resp, op);
@@ -1575,16 +1611,11 @@ check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse)
 		else
 			return nfserr_seq_misordered;
 	}
-	/* Normal */
+	/* Note unsigned 32-bit arithmetic handles wraparound: */
 	if (likely(seqid == slot_seqid + 1))
 		return nfs_ok;
-	/* Replay */
 	if (seqid == slot_seqid)
 		return nfserr_replay_cache;
-	/* Wraparound */
-	if (seqid == 1 && (slot_seqid + 1) == 0)
-		return nfs_ok;
-	/* Misordered replay or misordered new request */
 	return nfserr_seq_misordered;
 }
 
@@ -1815,9 +1846,10 @@ nfsd4_destroy_session(struct svc_rqst *r,
 	nfsd4_probe_callback_sync(ses->se_client);
 	nfs4_unlock_state();
 
+	spin_lock(&client_lock);
 	nfsd4_del_conns(ses);
-
-	nfsd4_put_session(ses);
+	nfsd4_put_session_locked(ses);
+	spin_unlock(&client_lock);
 	status = nfs_ok;
 out:
 	dprintk("%s returns %d\n", __func__, ntohl(status));
@@ -1921,8 +1953,12 @@ nfsd4_sequence(struct svc_rqst *rqstp,
 	 * sr_highest_slotid and the sr_target_slot id to maxslots */
 	seq->maxslots = session->se_fchannel.maxreqs;
 
-	status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_inuse);
+	status = check_slot_seqid(seq->seqid, slot->sl_seqid,
+					slot->sl_flags & NFSD4_SLOT_INUSE);
 	if (status == nfserr_replay_cache) {
+		status = nfserr_seq_misordered;
+		if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED))
+			goto out;
 		cstate->slot = slot;
 		cstate->session = session;
 		/* Return the cached reply status and set cstate->status
@@ -1938,9 +1974,12 @@ nfsd4_sequence(struct svc_rqst *rqstp,
 	conn = NULL;
 
 	/* Success! bump slot seqid */
-	slot->sl_inuse = true;
 	slot->sl_seqid = seq->seqid;
-	slot->sl_cachethis = seq->cachethis;
+	slot->sl_flags |= NFSD4_SLOT_INUSE;
+	if (seq->cachethis)
+		slot->sl_flags |= NFSD4_SLOT_CACHETHIS;
+	else
+		slot->sl_flags &= ~NFSD4_SLOT_CACHETHIS;
 
 	cstate->slot = slot;
 	cstate->session = session;
@@ -2030,7 +2069,8 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 
 	nfs4_lock_state();
 	status = nfserr_complete_already;
-	if (cstate->session->se_client->cl_firststate)
+	if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE,
+			     &cstate->session->se_client->cl_flags))
 		goto out;
 
 	status = nfserr_stale_clientid;
@@ -2045,7 +2085,7 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 		goto out;
 
 	status = nfs_ok;
-	nfsd4_create_clid_dir(cstate->session->se_client);
+	nfsd4_client_record_create(cstate->session->se_client);
 out:
 	nfs4_unlock_state();
 	return status;
@@ -2240,7 +2280,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 			conf = find_confirmed_client_by_str(unconf->cl_recdir,
 							    hash);
 			if (conf) {
-				nfsd4_remove_clid_dir(conf);
+				nfsd4_client_record_remove(conf);
 				expire_client(conf);
 			}
 			move_to_confirmed(unconf);
@@ -2633,8 +2673,6 @@ nfs4_check_delegmode(struct nfs4_delegation *dp, int flags)
 
 static int share_access_to_flags(u32 share_access)
 {
-	share_access &= ~NFS4_SHARE_WANT_MASK;
-
 	return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE;
 }
 
@@ -2776,10 +2814,9 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *c
 
 
 static void
-nfs4_set_claim_prev(struct nfsd4_open *open)
+nfs4_set_claim_prev(struct nfsd4_open *open, bool has_session)
 {
 	open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
-	open->op_openowner->oo_owner.so_client->cl_firststate = 1;
 }
 
 /* Should we give out recallable state?: */
@@ -2855,6 +2892,27 @@ static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag)
 	return 0;
 }
 
+static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
+{
+	open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+	if (status == -EAGAIN)
+		open->op_why_no_deleg = WND4_CONTENTION;
+	else {
+		open->op_why_no_deleg = WND4_RESOURCE;
+		switch (open->op_deleg_want) {
+		case NFS4_SHARE_WANT_READ_DELEG:
+		case NFS4_SHARE_WANT_WRITE_DELEG:
+		case NFS4_SHARE_WANT_ANY_DELEG:
+			break;
+		case NFS4_SHARE_WANT_CANCEL:
+			open->op_why_no_deleg = WND4_CANCELLED;
+			break;
+		case NFS4_SHARE_WANT_NO_DELEG:
+			BUG();	/* not supposed to get here */
+		}
+	}
+}
+
 /*
  * Attempt to hand out a delegation.
  */
@@ -2864,7 +2922,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_ol_
 	struct nfs4_delegation *dp;
 	struct nfs4_openowner *oo = container_of(stp->st_stateowner, struct nfs4_openowner, oo_owner);
 	int cb_up;
-	int status, flag = 0;
+	int status = 0, flag = 0;
 
 	cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
 	flag = NFS4_OPEN_DELEGATE_NONE;
@@ -2905,11 +2963,16 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_ol_
 	dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
 		STATEID_VAL(&dp->dl_stid.sc_stateid));
 out:
-	if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS
-			&& flag == NFS4_OPEN_DELEGATE_NONE
-			&& open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
-		dprintk("NFSD: WARNING: refusing delegation reclaim\n");
 	open->op_delegate_type = flag;
+	if (flag == NFS4_OPEN_DELEGATE_NONE) {
+		if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
+		    open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
+			dprintk("NFSD: WARNING: refusing delegation reclaim\n");
+
+		/* 4.1 client asking for a delegation? */
+		if (open->op_deleg_want)
+			nfsd4_open_deleg_none_ext(open, status);
+	}
 	return;
 out_free:
 	nfs4_put_delegation(dp);
@@ -2918,6 +2981,24 @@ out_no_deleg:
 	goto out;
 }
 
+static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open,
+					struct nfs4_delegation *dp)
+{
+	if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG &&
+	    dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
+		open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+		open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE;
+	} else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG &&
+		   dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
+		open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+		open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE;
+	}
+	/* Otherwise the client must be confused wanting a delegation
+	 * it already has, therefore we don't return
+	 * NFS4_OPEN_DELEGATE_NONE_EXT and reason.
+	 */
+}
+
 /*
  * called with nfs4_lock_state() held.
  */
@@ -2979,24 +3060,36 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 
-	if (nfsd4_has_session(&resp->cstate))
+	if (nfsd4_has_session(&resp->cstate)) {
 		open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
 
+		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
+			open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+			open->op_why_no_deleg = WND4_NOT_WANTED;
+			goto nodeleg;
+		}
+	}
+
 	/*
 	* Attempt to hand out a delegation. No error return, because the
 	* OPEN succeeds even if we fail.
 	*/
 	nfs4_open_delegation(current_fh, open, stp);
-
+nodeleg:
 	status = nfs_ok;
 
 	dprintk("%s: stateid=" STATEID_FMT "\n", __func__,
 		STATEID_VAL(&stp->st_stid.sc_stateid));
 out:
+	/* 4.1 client trying to upgrade/downgrade delegation? */
+	if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp &&
+	    open->op_deleg_want)
+		nfsd4_deleg_xgrade_none_ext(open, dp);
+
 	if (fp)
 		put_nfs4_file(fp);
 	if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
-		nfs4_set_claim_prev(open);
+		nfs4_set_claim_prev(open, nfsd4_has_session(&resp->cstate));
 	/*
 	* To finish the open response, we just need to set the rflags.
 	*/
@@ -3066,7 +3159,7 @@ static void
 nfsd4_end_grace(void)
 {
 	dprintk("NFSD: end of grace period\n");
-	nfsd4_recdir_purge_old();
+	nfsd4_record_grace_done(&init_net, boot_time);
 	locks_end_grace(&nfsd4_manager);
 	/*
 	 * Now that every NFSv4 client has had the chance to recover and
@@ -3115,7 +3208,7 @@ nfs4_laundromat(void)
 		clp = list_entry(pos, struct nfs4_client, cl_lru);
 		dprintk("NFSD: purging unused client (clientid %08x)\n",
 			clp->cl_clientid.cl_id);
-		nfsd4_remove_clid_dir(clp);
+		nfsd4_client_record_remove(clp);
 		expire_client(clp);
 	}
 	spin_lock(&recall_lock);
@@ -3400,7 +3493,14 @@ __be32
 nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		   struct nfsd4_test_stateid *test_stateid)
 {
-	/* real work is done during encoding */
+	struct nfsd4_test_stateid_id *stateid;
+	struct nfs4_client *cl = cstate->session->se_client;
+
+	nfs4_lock_state();
+	list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list)
+		stateid->ts_id_status = nfs4_validate_stateid(cl, &stateid->ts_id_stateid);
+	nfs4_unlock_state();
+
 	return nfs_ok;
 }
 
@@ -3539,7 +3639,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
 		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
 
-	nfsd4_create_clid_dir(oo->oo_owner.so_client);
+	nfsd4_client_record_create(oo->oo_owner.so_client);
 	status = nfs_ok;
 out:
 	if (!cstate->replay_owner)
@@ -3596,7 +3696,9 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 			cstate->current_fh.fh_dentry->d_name.name);
 
 	/* We don't yet support WANT bits: */
-	od->od_share_access &= NFS4_SHARE_ACCESS_MASK;
+	if (od->od_deleg_want)
+		dprintk("NFSD: %s: od_deleg_want=0x%x ignored\n", __func__,
+			od->od_deleg_want);
 
 	nfs4_lock_state();
 	status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid,
@@ -4353,7 +4455,9 @@ nfs4_has_reclaimed_state(const char *name, bool use_exchange_id)
 	struct nfs4_client *clp;
 
 	clp = find_confirmed_client_by_str(name, strhashval);
-	return clp ? 1 : 0;
+	if (!clp)
+		return 0;
+	return test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
 }
 
 /*
@@ -4377,7 +4481,7 @@ nfs4_client_to_reclaim(const char *name)
 	return 1;
 }
 
-static void
+void
 nfs4_release_reclaim(void)
 {
 	struct nfs4_client_reclaim *crp = NULL;
@@ -4397,19 +4501,12 @@ nfs4_release_reclaim(void)
 
 /*
  * called from OPEN, CLAIM_PREVIOUS with a new clientid. */
-static struct nfs4_client_reclaim *
-nfs4_find_reclaim_client(clientid_t *clid)
+struct nfs4_client_reclaim *
+nfsd4_find_reclaim_client(struct nfs4_client *clp)
 {
 	unsigned int strhashval;
-	struct nfs4_client *clp;
 	struct nfs4_client_reclaim *crp = NULL;
 
-
-	/* find clientid in conf_id_hashtbl */
-	clp = find_confirmed_client(clid);
-	if (clp == NULL)
-		return NULL;
-
 	dprintk("NFSD: nfs4_find_reclaim_client for %.*s with recdir %s\n",
 		            clp->cl_name.len, clp->cl_name.data,
 			    clp->cl_recdir);
@@ -4430,7 +4527,14 @@ nfs4_find_reclaim_client(clientid_t *clid)
 __be32
 nfs4_check_open_reclaim(clientid_t *clid)
 {
-	return nfs4_find_reclaim_client(clid) ? nfs_ok : nfserr_reclaim_bad;
+	struct nfs4_client *clp;
+
+	/* find clientid in conf_id_hashtbl */
+	clp = find_confirmed_client(clid);
+	if (clp == NULL)
+		return nfserr_reclaim_bad;
+
+	return nfsd4_client_record_check(clp) ? nfserr_reclaim_bad : nfs_ok;
 }
 
 #ifdef CONFIG_NFSD_FAULT_INJECTION
@@ -4442,7 +4546,7 @@ void nfsd_forget_clients(u64 num)
 
 	nfs4_lock_state();
 	list_for_each_entry_safe(clp, next, &client_lru, cl_lru) {
-		nfsd4_remove_clid_dir(clp);
+		nfsd4_client_record_remove(clp);
 		expire_client(clp);
 		if (++count == num)
 			break;
@@ -4577,19 +4681,6 @@ nfs4_state_init(void)
 	reclaim_str_hashtbl_size = 0;
 }
 
-static void
-nfsd4_load_reboot_recovery_data(void)
-{
-	int status;
-
-	nfs4_lock_state();
-	nfsd4_init_recdir();
-	status = nfsd4_recdir_load();
-	nfs4_unlock_state();
-	if (status)
-		printk("NFSD: Failure reading reboot recovery data\n");
-}
-
 /*
  * Since the lifetime of a delegation isn't limited to that of an open, a
  * client may quite reasonably hang on to a delegation as long as it has
@@ -4613,21 +4704,34 @@ set_max_delegations(void)
 
 /* initialization to perform when the nfsd service is started: */
 
-static int
-__nfs4_state_start(void)
+int
+nfs4_state_start(void)
 {
 	int ret;
 
+	/*
+	 * FIXME: For now, we hang most of the pernet global stuff off of
+	 * init_net until nfsd is fully containerized. Eventually, we'll
+	 * need to pass a net pointer into this function, take a reference
+	 * to that instead and then do most of the rest of this on a per-net
+	 * basis.
+	 */
+	get_net(&init_net);
+	nfsd4_client_tracking_init(&init_net);
 	boot_time = get_seconds();
 	locks_start_grace(&nfsd4_manager);
 	printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
 	       nfsd4_grace);
 	ret = set_callback_cred();
-	if (ret)
-		return -ENOMEM;
+	if (ret) {
+		ret = -ENOMEM;
+		goto out_recovery;
+	}
 	laundry_wq = create_singlethread_workqueue("nfsd4");
-	if (laundry_wq == NULL)
-		return -ENOMEM;
+	if (laundry_wq == NULL) {
+		ret = -ENOMEM;
+		goto out_recovery;
+	}
 	ret = nfsd4_create_callback_queue();
 	if (ret)
 		goto out_free_laundry;
@@ -4636,16 +4740,12 @@ __nfs4_state_start(void)
 	return 0;
 out_free_laundry:
 	destroy_workqueue(laundry_wq);
+out_recovery:
+	nfsd4_client_tracking_exit(&init_net);
+	put_net(&init_net);
 	return ret;
 }
 
-int
-nfs4_state_start(void)
-{
-	nfsd4_load_reboot_recovery_data();
-	return __nfs4_state_start();
-}
-
 static void
 __nfs4_state_shutdown(void)
 {
@@ -4676,7 +4776,8 @@ __nfs4_state_shutdown(void)
 		unhash_delegation(dp);
 	}
 
-	nfsd4_shutdown_recdir();
+	nfsd4_client_tracking_exit(&init_net);
+	put_net(&init_net);
 }
 
 void
@@ -4686,8 +4787,108 @@ nfs4_state_shutdown(void)
 	destroy_workqueue(laundry_wq);
 	locks_end_grace(&nfsd4_manager);
 	nfs4_lock_state();
-	nfs4_release_reclaim();
 	__nfs4_state_shutdown();
 	nfs4_unlock_state();
 	nfsd4_destroy_callback_queue();
 }
+
+static void
+get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
+{
+	if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid))
+		memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t));
+}
+
+static void
+put_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
+{
+	if (cstate->minorversion) {
+		memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t));
+		SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+	}
+}
+
+void
+clear_current_stateid(struct nfsd4_compound_state *cstate)
+{
+	CLEAR_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+}
+
+/*
+ * functions to set current state id
+ */
+void
+nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp)
+{
+	put_stateid(cstate, &odp->od_stateid);
+}
+
+void
+nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
+{
+	put_stateid(cstate, &open->op_stateid);
+}
+
+void
+nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close)
+{
+	put_stateid(cstate, &close->cl_stateid);
+}
+
+void
+nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lock)
+{
+	put_stateid(cstate, &lock->lk_resp_stateid);
+}
+
+/*
+ * functions to consume current state id
+ */
+
+void
+nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp)
+{
+	get_stateid(cstate, &odp->od_stateid);
+}
+
+void
+nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *drp)
+{
+	get_stateid(cstate, &drp->dr_stateid);
+}
+
+void
+nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *fsp)
+{
+	get_stateid(cstate, &fsp->fr_stateid);
+}
+
+void
+nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, struct nfsd4_setattr *setattr)
+{
+	get_stateid(cstate, &setattr->sa_stateid);
+}
+
+void
+nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close)
+{
+	get_stateid(cstate, &close->cl_stateid);
+}
+
+void
+nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, struct nfsd4_locku *locku)
+{
+	get_stateid(cstate, &locku->lu_stateid);
+}
+
+void
+nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, struct nfsd4_read *read)
+{
+	get_stateid(cstate, &read->rd_stateid);
+}
+
+void
+nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, struct nfsd4_write *write)
+{
+	get_stateid(cstate, &write->wr_stateid);
+}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0ec5a1b9700e..bcd8904ab1e3 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -133,22 +133,6 @@ xdr_error:					\
 	}					\
 } while (0)
 
-static void save_buf(struct nfsd4_compoundargs *argp, struct nfsd4_saved_compoundargs *savep)
-{
-	savep->p        = argp->p;
-	savep->end      = argp->end;
-	savep->pagelen  = argp->pagelen;
-	savep->pagelist = argp->pagelist;
-}
-
-static void restore_buf(struct nfsd4_compoundargs *argp, struct nfsd4_saved_compoundargs *savep)
-{
-	argp->p        = savep->p;
-	argp->end      = savep->end;
-	argp->pagelen  = savep->pagelen;
-	argp->pagelist = savep->pagelist;
-}
-
 static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
 {
 	/* We want more bytes than seem to be available.
@@ -638,14 +622,18 @@ nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup
 	DECODE_TAIL;
 }
 
-static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *x)
+static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *share_access, u32 *deleg_want, u32 *deleg_when)
 {
 	__be32 *p;
 	u32 w;
 
 	READ_BUF(4);
 	READ32(w);
-	*x = w;
+	*share_access = w & NFS4_SHARE_ACCESS_MASK;
+	*deleg_want = w & NFS4_SHARE_WANT_MASK;
+	if (deleg_when)
+		*deleg_when = w & NFS4_SHARE_WHEN_MASK;
+
 	switch (w & NFS4_SHARE_ACCESS_MASK) {
 	case NFS4_SHARE_ACCESS_READ:
 	case NFS4_SHARE_ACCESS_WRITE:
@@ -673,6 +661,9 @@ static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *x)
 	w &= ~NFS4_SHARE_WANT_MASK;
 	if (!w)
 		return nfs_ok;
+
+	if (!deleg_when)	/* open_downgrade */
+		return nfserr_inval;
 	switch (w) {
 	case NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL:
 	case NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED:
@@ -719,6 +710,7 @@ static __be32
 nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 {
 	DECODE_HEAD;
+	u32 dummy;
 
 	memset(open->op_bmval, 0, sizeof(open->op_bmval));
 	open->op_iattr.ia_valid = 0;
@@ -727,7 +719,9 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 	/* seqid, share_access, share_deny, clientid, ownerlen */
 	READ_BUF(4);
 	READ32(open->op_seqid);
-	status = nfsd4_decode_share_access(argp, &open->op_share_access);
+	/* decode, yet ignore deleg_when until supported */
+	status = nfsd4_decode_share_access(argp, &open->op_share_access,
+					   &open->op_deleg_want, &dummy);
 	if (status)
 		goto xdr_error;
 	status = nfsd4_decode_share_deny(argp, &open->op_share_deny);
@@ -755,14 +749,14 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 				goto out;
 			break;
 		case NFS4_CREATE_EXCLUSIVE:
-			READ_BUF(8);
-			COPYMEM(open->op_verf.data, 8);
+			READ_BUF(NFS4_VERIFIER_SIZE);
+			COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
 			break;
 		case NFS4_CREATE_EXCLUSIVE4_1:
 			if (argp->minorversion < 1)
 				goto xdr_error;
-			READ_BUF(8);
-			COPYMEM(open->op_verf.data, 8);
+			READ_BUF(NFS4_VERIFIER_SIZE);
+			COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
 			status = nfsd4_decode_fattr(argp, open->op_bmval,
 				&open->op_iattr, &open->op_acl);
 			if (status)
@@ -848,7 +842,8 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d
 		return status;
 	READ_BUF(4);
 	READ32(open_down->od_seqid);
-	status = nfsd4_decode_share_access(argp, &open_down->od_share_access);
+	status = nfsd4_decode_share_access(argp, &open_down->od_share_access,
+					   &open_down->od_deleg_want, NULL);
 	if (status)
 		return status;
 	status = nfsd4_decode_share_deny(argp, &open_down->od_share_deny);
@@ -994,8 +989,8 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
 {
 	DECODE_HEAD;
 
-	READ_BUF(8);
-	COPYMEM(setclientid->se_verf.data, 8);
+	READ_BUF(NFS4_VERIFIER_SIZE);
+	COPYMEM(setclientid->se_verf.data, NFS4_VERIFIER_SIZE);
 
 	status = nfsd4_decode_opaque(argp, &setclientid->se_name);
 	if (status)
@@ -1020,9 +1015,9 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s
 {
 	DECODE_HEAD;
 
-	READ_BUF(8 + sizeof(nfs4_verifier));
+	READ_BUF(8 + NFS4_VERIFIER_SIZE);
 	COPYMEM(&scd_c->sc_clientid, 8);
-	COPYMEM(&scd_c->sc_confirm, sizeof(nfs4_verifier));
+	COPYMEM(&scd_c->sc_confirm, NFS4_VERIFIER_SIZE);
 
 	DECODE_TAIL;
 }
@@ -1385,26 +1380,29 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp,
 static __be32
 nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_stateid *test_stateid)
 {
-	unsigned int nbytes;
-	stateid_t si;
 	int i;
-	__be32 *p;
-	__be32 status;
+	__be32 *p, status;
+	struct nfsd4_test_stateid_id *stateid;
 
 	READ_BUF(4);
 	test_stateid->ts_num_ids = ntohl(*p++);
 
-	nbytes = test_stateid->ts_num_ids * sizeof(stateid_t);
-	if (nbytes > (u32)((char *)argp->end - (char *)argp->p))
-		goto xdr_error;
-
-	test_stateid->ts_saved_args = argp;
-	save_buf(argp, &test_stateid->ts_savedp);
+	INIT_LIST_HEAD(&test_stateid->ts_stateid_list);
 
 	for (i = 0; i < test_stateid->ts_num_ids; i++) {
-		status = nfsd4_decode_stateid(argp, &si);
+		stateid = kmalloc(sizeof(struct nfsd4_test_stateid_id), GFP_KERNEL);
+		if (!stateid) {
+			status = PTR_ERR(stateid);
+			goto out;
+		}
+
+		defer_free(argp, kfree, stateid);
+		INIT_LIST_HEAD(&stateid->ts_id_list);
+		list_add_tail(&stateid->ts_id_list, &test_stateid->ts_stateid_list);
+
+		status = nfsd4_decode_stateid(argp, &stateid->ts_id_stateid);
 		if (status)
-			return status;
+			goto out;
 	}
 
 	status = 0;
@@ -2661,8 +2659,8 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(8);
-		WRITEMEM(commit->co_verf.data, 8);
+		RESERVE_SPACE(NFS4_VERIFIER_SIZE);
+		WRITEMEM(commit->co_verf.data, NFS4_VERIFIER_SIZE);
 		ADJUST_ARGS();
 	}
 	return nfserr;
@@ -2851,6 +2849,20 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op
 		WRITE32(0);   /* XXX: is NULL principal ok? */
 		ADJUST_ARGS();
 		break;
+	case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */
+		switch (open->op_why_no_deleg) {
+		case WND4_CONTENTION:
+		case WND4_RESOURCE:
+			RESERVE_SPACE(8);
+			WRITE32(open->op_why_no_deleg);
+			WRITE32(0);	/* deleg signaling not supported yet */
+			break;
+		default:
+			RESERVE_SPACE(4);
+			WRITE32(open->op_why_no_deleg);
+		}
+		ADJUST_ARGS();
+		break;
 	default:
 		BUG();
 	}
@@ -3008,7 +3020,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
 	if (resp->xbuf->page_len)
 		return nfserr_resource;
 
-	RESERVE_SPACE(8);  /* verifier */
+	RESERVE_SPACE(NFS4_VERIFIER_SIZE);
 	savep = p;
 
 	/* XXX: Following NFSv3, we ignore the READDIR verifier for now. */
@@ -3209,9 +3221,9 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(8 + sizeof(nfs4_verifier));
+		RESERVE_SPACE(8 + NFS4_VERIFIER_SIZE);
 		WRITEMEM(&scd->se_clientid, 8);
-		WRITEMEM(&scd->se_confirm, sizeof(nfs4_verifier));
+		WRITEMEM(&scd->se_confirm, NFS4_VERIFIER_SIZE);
 		ADJUST_ARGS();
 	}
 	else if (nfserr == nfserr_clid_inuse) {
@@ -3232,7 +3244,7 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w
 		RESERVE_SPACE(16);
 		WRITE32(write->wr_bytes_written);
 		WRITE32(write->wr_how_written);
-		WRITEMEM(write->wr_verifier.data, 8);
+		WRITEMEM(write->wr_verifier.data, NFS4_VERIFIER_SIZE);
 		ADJUST_ARGS();
 	}
 	return nfserr;
@@ -3391,30 +3403,17 @@ __be32
 nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, int nfserr,
 			  struct nfsd4_test_stateid *test_stateid)
 {
-	struct nfsd4_compoundargs *argp;
-	struct nfs4_client *cl = resp->cstate.session->se_client;
-	stateid_t si;
+	struct nfsd4_test_stateid_id *stateid, *next;
 	__be32 *p;
-	int i;
-	int valid;
-
-	restore_buf(test_stateid->ts_saved_args, &test_stateid->ts_savedp);
-	argp = test_stateid->ts_saved_args;
 
-	RESERVE_SPACE(4);
+	RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids));
 	*p++ = htonl(test_stateid->ts_num_ids);
-	resp->p = p;
 
-	nfs4_lock_state();
-	for (i = 0; i < test_stateid->ts_num_ids; i++) {
-		nfsd4_decode_stateid(argp, &si);
-		valid = nfs4_validate_stateid(cl, &si);
-		RESERVE_SPACE(4);
-		*p++ = htonl(valid);
-		resp->p = p;
+	list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) {
+		*p++ = htonl(stateid->ts_id_status);
 	}
-	nfs4_unlock_state();
 
+	ADJUST_ARGS();
 	return nfserr;
 }
 
@@ -3532,7 +3531,7 @@ int nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 pad)
 	if (length > session->se_fchannel.maxresp_sz)
 		return nfserr_rep_too_big;
 
-	if (slot->sl_cachethis == 1 &&
+	if ((slot->sl_flags & NFSD4_SLOT_CACHETHIS) &&
 	    length > session->se_fchannel.maxresp_cached)
 		return nfserr_rep_too_big_to_cache;
 
@@ -3656,8 +3655,7 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
 	if (nfsd4_has_session(cs)) {
 		if (cs->status != nfserr_replay_cache) {
 			nfsd4_store_cache_entry(resp);
-			dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
-			cs->slot->sl_inuse = false;
+			cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE;
 		}
 		/* Renew the clientid on success and on replay */
 		release_session_client(cs->session);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 64c24af8d7ea..2c53be6d3579 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -13,12 +13,14 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/gss_api.h>
 #include <linux/sunrpc/gss_krb5_enctypes.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/module.h>
 
 #include "idmap.h"
 #include "nfsd.h"
 #include "cache.h"
 #include "fault_inject.h"
+#include "netns.h"
 
 /*
  *	We have a single directory with several nodes in it.
@@ -1124,14 +1126,26 @@ static int create_proc_exports_entry(void)
 }
 #endif
 
+int nfsd_net_id;
+static struct pernet_operations nfsd_net_ops = {
+	.id   = &nfsd_net_id,
+	.size = sizeof(struct nfsd_net),
+};
+
 static int __init init_nfsd(void)
 {
 	int retval;
 	printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n");
 
-	retval = nfsd4_init_slabs();
+	retval = register_cld_notifier();
 	if (retval)
 		return retval;
+	retval = register_pernet_subsys(&nfsd_net_ops);
+	if (retval < 0)
+		goto out_unregister_notifier;
+	retval = nfsd4_init_slabs();
+	if (retval)
+		goto out_unregister_pernet;
 	nfs4_state_init();
 	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
 	if (retval)
@@ -1169,6 +1183,10 @@ out_free_stat:
 	nfsd_fault_inject_cleanup();
 out_free_slabs:
 	nfsd4_free_slabs();
+out_unregister_pernet:
+	unregister_pernet_subsys(&nfsd_net_ops);
+out_unregister_notifier:
+	unregister_cld_notifier();
 	return retval;
 }
 
@@ -1184,6 +1202,8 @@ static void __exit exit_nfsd(void)
 	nfsd4_free_slabs();
 	nfsd_fault_inject_cleanup();
 	unregister_filesystem(&nfsd_fs_type);
+	unregister_pernet_subsys(&nfsd_net_ops);
+	unregister_cld_notifier();
 }
 
 MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 1d1e8589b4ce..1671429ffa66 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -364,12 +364,17 @@ static inline u32 nfsd_suppattrs2(u32 minorversion)
 	NFSD_WRITEABLE_ATTRS_WORD2
 
 extern int nfsd4_is_junction(struct dentry *dentry);
-#else
+extern int register_cld_notifier(void);
+extern void unregister_cld_notifier(void);
+#else /* CONFIG_NFSD_V4 */
 static inline int nfsd4_is_junction(struct dentry *dentry)
 {
 	return 0;
 }
 
+#define register_cld_notifier() 0
+#define unregister_cld_notifier() do { } while(0)
+
 #endif /* CONFIG_NFSD_V4 */
 
 #endif /* LINUX_NFSD_NFSD_H */
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index fce472f5f39e..28dfad39f0c5 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -307,33 +307,37 @@ static void set_max_drc(void)
 	dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
 }
 
-int nfsd_create_serv(void)
+static int nfsd_get_default_max_blksize(void)
 {
-	int err = 0;
+	struct sysinfo i;
+	unsigned long long target;
+	unsigned long ret;
+
+	si_meminfo(&i);
+	target = (i.totalram - i.totalhigh) << PAGE_SHIFT;
+	/*
+	 * Aim for 1/4096 of memory per thread This gives 1MB on 4Gig
+	 * machines, but only uses 32K on 128M machines.  Bottom out at
+	 * 8K on 32M and smaller.  Of course, this is only a default.
+	 */
+	target >>= 12;
+
+	ret = NFSSVC_MAXBLKSIZE;
+	while (ret > target && ret >= 8*1024*2)
+		ret /= 2;
+	return ret;
+}
 
+int nfsd_create_serv(void)
+{
 	WARN_ON(!mutex_is_locked(&nfsd_mutex));
 	if (nfsd_serv) {
 		svc_get(nfsd_serv);
 		return 0;
 	}
-	if (nfsd_max_blksize == 0) {
-		/* choose a suitable default */
-		struct sysinfo i;
-		si_meminfo(&i);
-		/* Aim for 1/4096 of memory per thread
-		 * This gives 1MB on 4Gig machines
-		 * But only uses 32K on 128M machines.
-		 * Bottom out at 8K on 32M and smaller.
-		 * Of course, this is only a default.
-		 */
-		nfsd_max_blksize = NFSSVC_MAXBLKSIZE;
-		i.totalram <<= PAGE_SHIFT - 12;
-		while (nfsd_max_blksize > i.totalram &&
-		       nfsd_max_blksize >= 8*1024*2)
-			nfsd_max_blksize /= 2;
-	}
+	if (nfsd_max_blksize == 0)
+		nfsd_max_blksize = nfsd_get_default_max_blksize();
 	nfsd_reset_versions();
-
 	nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
 				      nfsd_last_thread, nfsd, THIS_MODULE);
 	if (nfsd_serv == NULL)
@@ -341,7 +345,7 @@ int nfsd_create_serv(void)
 
 	set_max_drc();
 	do_gettimeofday(&nfssvc_boot);		/* record boot time */
-	return err;
+	return 0;
 }
 
 int nfsd_nrpools(void)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index ffb5df1db94f..89ab137d379a 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -128,12 +128,14 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s)
 		(NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)
 
 struct nfsd4_slot {
-	bool	sl_inuse;
-	bool	sl_cachethis;
-	u16	sl_opcnt;
 	u32	sl_seqid;
 	__be32	sl_status;
 	u32	sl_datalen;
+	u16	sl_opcnt;
+#define NFSD4_SLOT_INUSE	(1 << 0)
+#define NFSD4_SLOT_CACHETHIS	(1 << 1)
+#define NFSD4_SLOT_INITIALIZED	(1 << 2)
+	u8	sl_flags;
 	char	sl_data[];
 };
 
@@ -196,18 +198,7 @@ struct nfsd4_session {
 	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
 };
 
-static inline void
-nfsd4_put_session(struct nfsd4_session *ses)
-{
-	extern void free_session(struct kref *kref);
-	kref_put(&ses->se_ref, free_session);
-}
-
-static inline void
-nfsd4_get_session(struct nfsd4_session *ses)
-{
-	kref_get(&ses->se_ref);
-}
+extern void nfsd4_put_session(struct nfsd4_session *ses);
 
 /* formatted contents of nfs4_sessionid */
 struct nfsd4_sessionid {
@@ -245,14 +236,17 @@ struct nfs4_client {
 	struct svc_cred		cl_cred; 	/* setclientid principal */
 	clientid_t		cl_clientid;	/* generated by server */
 	nfs4_verifier		cl_confirm;	/* generated by server */
-	u32			cl_firststate;	/* recovery dir creation */
 	u32			cl_minorversion;
 
 	/* for v4.0 and v4.1 callbacks: */
 	struct nfs4_cb_conn	cl_cb_conn;
-#define NFSD4_CLIENT_CB_UPDATE	1
-#define NFSD4_CLIENT_KILL	2
-	unsigned long		cl_cb_flags;
+#define NFSD4_CLIENT_CB_UPDATE		(0)
+#define NFSD4_CLIENT_CB_KILL		(1)
+#define NFSD4_CLIENT_STABLE		(2)	/* client on stable storage */
+#define NFSD4_CLIENT_RECLAIM_COMPLETE	(3)	/* reclaim_complete done */
+#define NFSD4_CLIENT_CB_FLAG_MASK	(1 << NFSD4_CLIENT_CB_UPDATE | \
+					 1 << NFSD4_CLIENT_CB_KILL)
+	unsigned long		cl_flags;
 	struct rpc_clnt		*cl_cb_client;
 	u32			cl_cb_ident;
 #define NFSD4_CB_UP		0
@@ -463,6 +457,8 @@ extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
 extern void nfs4_lock_state(void);
 extern void nfs4_unlock_state(void);
 extern int nfs4_in_grace(void);
+extern void nfs4_release_reclaim(void);
+extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct nfs4_client *crp);
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
 extern void nfs4_free_openowner(struct nfs4_openowner *);
 extern void nfs4_free_lockowner(struct nfs4_lockowner *);
@@ -477,16 +473,17 @@ extern void nfsd4_destroy_callback_queue(void);
 extern void nfsd4_shutdown_callback(struct nfs4_client *);
 extern void nfs4_put_delegation(struct nfs4_delegation *dp);
 extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
-extern void nfsd4_init_recdir(void);
-extern int nfsd4_recdir_load(void);
-extern void nfsd4_shutdown_recdir(void);
 extern int nfs4_client_to_reclaim(const char *name);
 extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
-extern void nfsd4_recdir_purge_old(void);
-extern void nfsd4_create_clid_dir(struct nfs4_client *clp);
-extern void nfsd4_remove_clid_dir(struct nfs4_client *clp);
 extern void release_session_client(struct nfsd4_session *);
 extern __be32 nfs4_validate_stateid(struct nfs4_client *, stateid_t *);
 extern void nfsd4_purge_closed_stateid(struct nfs4_stateowner *);
 
+/* nfs4recover operations */
+extern int nfsd4_client_tracking_init(struct net *net);
+extern void nfsd4_client_tracking_exit(struct net *net);
+extern void nfsd4_client_record_create(struct nfs4_client *clp);
+extern void nfsd4_client_record_remove(struct nfs4_client *clp);
+extern int nfsd4_client_record_check(struct nfs4_client *clp);
+extern void nfsd4_record_grace_done(struct net *net, time_t boot_time);
 #endif   /* NFSD4_STATE_H */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index e59f71d0cf73..296d671654d6 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -737,12 +737,13 @@ static int nfsd_open_break_lease(struct inode *inode, int access)
 
 /*
  * Open an existing file or directory.
- * The access argument indicates the type of open (read/write/lock)
+ * The may_flags argument indicates the type of open (read/write/lock)
+ * and additional flags.
  * N.B. After this call fhp needs an fh_put
  */
 __be32
 nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
-			int access, struct file **filp)
+			int may_flags, struct file **filp)
 {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -757,7 +758,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 	 * and (hopefully) checked permission - so allow OWNER_OVERRIDE
 	 * in case a chmod has now revoked permission.
 	 */
-	err = fh_verify(rqstp, fhp, type, access | NFSD_MAY_OWNER_OVERRIDE);
+	err = fh_verify(rqstp, fhp, type, may_flags | NFSD_MAY_OWNER_OVERRIDE);
 	if (err)
 		goto out;
 
@@ -768,7 +769,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 	 * or any access when mandatory locking enabled
 	 */
 	err = nfserr_perm;
-	if (IS_APPEND(inode) && (access & NFSD_MAY_WRITE))
+	if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE))
 		goto out;
 	/*
 	 * We must ignore files (but only files) which might have mandatory
@@ -781,12 +782,12 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 	if (!inode->i_fop)
 		goto out;
 
-	host_err = nfsd_open_break_lease(inode, access);
+	host_err = nfsd_open_break_lease(inode, may_flags);
 	if (host_err) /* NOMEM or WOULDBLOCK */
 		goto out_nfserr;
 
-	if (access & NFSD_MAY_WRITE) {
-		if (access & NFSD_MAY_READ)
+	if (may_flags & NFSD_MAY_WRITE) {
+		if (may_flags & NFSD_MAY_READ)
 			flags = O_RDWR|O_LARGEFILE;
 		else
 			flags = O_WRONLY|O_LARGEFILE;
@@ -795,8 +796,15 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 			    flags, current_cred());
 	if (IS_ERR(*filp))
 		host_err = PTR_ERR(*filp);
-	else
-		host_err = ima_file_check(*filp, access);
+	else {
+		host_err = ima_file_check(*filp, may_flags);
+
+		if (may_flags & NFSD_MAY_64BIT_COOKIE)
+			(*filp)->f_mode |= FMODE_64BITHASH;
+		else
+			(*filp)->f_mode |= FMODE_32BITHASH;
+	}
+
 out_nfserr:
 	err = nfserrno(host_err);
 out:
@@ -2021,8 +2029,13 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
 	__be32		err;
 	struct file	*file;
 	loff_t		offset = *offsetp;
+	int             may_flags = NFSD_MAY_READ;
+
+	/* NFSv2 only supports 32 bit cookies */
+	if (rqstp->rq_vers > 2)
+		may_flags |= NFSD_MAY_64BIT_COOKIE;
 
-	err = nfsd_open(rqstp, fhp, S_IFDIR, NFSD_MAY_READ, &file);
+	err = nfsd_open(rqstp, fhp, S_IFDIR, may_flags, &file);
 	if (err)
 		goto out;
 
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 1dcd238e11a0..ec0611b2b738 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -27,6 +27,8 @@
 #define NFSD_MAY_BYPASS_GSS		0x400
 #define NFSD_MAY_READ_IF_EXEC		0x800
 
+#define NFSD_MAY_64BIT_COOKIE		0x1000 /* 64 bit readdir cookies for >= NFSv3 */
+
 #define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
 #define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
 
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 2364747ee97d..1b3501598ab5 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -43,6 +43,13 @@
 #define NFSD4_MAX_TAGLEN	128
 #define XDR_LEN(n)                     (((n) + 3) & ~3)
 
+#define CURRENT_STATE_ID_FLAG (1<<0)
+#define SAVED_STATE_ID_FLAG (1<<1)
+
+#define SET_STATE_ID(c, f) ((c)->sid_flags |= (f))
+#define HAS_STATE_ID(c, f) ((c)->sid_flags & (f))
+#define CLEAR_STATE_ID(c, f) ((c)->sid_flags &= ~(f))
+
 struct nfsd4_compound_state {
 	struct svc_fh		current_fh;
 	struct svc_fh		save_fh;
@@ -54,6 +61,10 @@ struct nfsd4_compound_state {
 	size_t			iovlen;
 	u32			minorversion;
 	u32			status;
+	stateid_t	current_stateid;
+	stateid_t	save_stateid;
+	/* to indicate current and saved state id presents */
+	u32		sid_flags;
 };
 
 static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
@@ -212,16 +223,19 @@ struct nfsd4_open {
 	struct xdr_netobj op_fname;	    /* request - everything but CLAIM_PREV */
 	u32		op_delegate_type;   /* request - CLAIM_PREV only */
 	stateid_t       op_delegate_stateid; /* request - response */
+	u32		op_why_no_deleg;    /* response - DELEG_NONE_EXT only */
 	u32		op_create;     	    /* request */
 	u32		op_createmode;      /* request */
 	u32		op_bmval[3];        /* request */
 	struct iattr	iattr;              /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
-	nfs4_verifier	verf;               /* EXCLUSIVE4 */
+	nfs4_verifier	op_verf __attribute__((aligned(32)));
+					    /* EXCLUSIVE4 */
 	clientid_t	op_clientid;        /* request */
 	struct xdr_netobj op_owner;           /* request */
 	u32		op_seqid;           /* request */
 	u32		op_share_access;    /* request */
 	u32		op_share_deny;      /* request */
+	u32		op_deleg_want;      /* request */
 	stateid_t	op_stateid;         /* response */
 	u32		op_recall;          /* recall */
 	struct nfsd4_change_info  op_cinfo; /* response */
@@ -234,7 +248,6 @@ struct nfsd4_open {
 	struct nfs4_acl *op_acl;
 };
 #define op_iattr	iattr
-#define op_verf		verf
 
 struct nfsd4_open_confirm {
 	stateid_t	oc_req_stateid		/* request */;
@@ -245,8 +258,9 @@ struct nfsd4_open_confirm {
 struct nfsd4_open_downgrade {
 	stateid_t       od_stateid;
 	u32             od_seqid;
-	u32             od_share_access;
-	u32             od_share_deny;
+	u32             od_share_access;	/* request */
+	u32		od_deleg_want;		/* request */
+	u32             od_share_deny;		/* request */
 };
 
 
@@ -343,10 +357,15 @@ struct nfsd4_saved_compoundargs {
 	struct page **pagelist;
 };
 
+struct nfsd4_test_stateid_id {
+	__be32			ts_id_status;
+	stateid_t		ts_id_stateid;
+	struct list_head	ts_id_list;
+};
+
 struct nfsd4_test_stateid {
 	__be32		ts_num_ids;
-	struct nfsd4_compoundargs *ts_saved_args;
-	struct nfsd4_saved_compoundargs ts_savedp;
+	struct list_head ts_stateid_list;
 };
 
 struct nfsd4_free_stateid {
@@ -503,7 +522,8 @@ static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp)
 
 static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
 {
-	return !resp->cstate.slot->sl_cachethis || nfsd4_is_solo_sequence(resp);
+	return !(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS)
+		|| nfsd4_is_solo_sequence(resp);
 }
 
 #define NFS4_SVC_XDRSIZE		sizeof(struct nfsd4_compoundargs)
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index a6fda3c188aa..a1a1bfd652c9 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -28,8 +28,6 @@
 #include "suballoc.h"
 #include "move_extents.h"
 
-#include <linux/ext2_fs.h>
-
 #define o2info_from_user(a, b)	\
 		copy_from_user(&(a), (b), sizeof(a))
 #define o2info_to_user(a, b)	\
diff --git a/fs/open.c b/fs/open.c
index 77becc041149..5720854156db 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -836,7 +836,7 @@ EXPORT_SYMBOL(dentry_open);
 static void __put_unused_fd(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = files_fdtable(files);
-	__FD_CLR(fd, fdt->open_fds);
+	__clear_open_fd(fd, fdt);
 	if (fd < files->next_fd)
 		files->next_fd = fd;
 }
@@ -1080,7 +1080,7 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 	if (!filp)
 		goto out_unlock;
 	rcu_assign_pointer(fdt->fd[fd], NULL);
-	FD_CLR(fd, fdt->close_on_exec);
+	__clear_close_on_exec(fd, fdt);
 	__put_unused_fd(files, fd);
 	spin_unlock(&files->file_lock);
 	retval = filp_close(filp, files);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index fbb53c249086..f9bd395b3473 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -550,7 +550,7 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, ' ', shared);
 	seq_put_decimal_ull(m, ' ', text);
 	seq_put_decimal_ull(m, ' ', 0);
-	seq_put_decimal_ull(m, ' ', text);
+	seq_put_decimal_ull(m, ' ', data);
 	seq_put_decimal_ull(m, ' ', 0);
 	seq_putc(m, '\n');
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 3b42c1418f31..1c8b280146d7 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1753,7 +1753,7 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info)
 
 			fdt = files_fdtable(files);
 			f_flags = file->f_flags & ~O_CLOEXEC;
-			if (FD_ISSET(fd, fdt->close_on_exec))
+			if (close_on_exec(fd, fdt))
 				f_flags |= O_CLOEXEC;
 
 			if (path) {
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 8461a7b82fdb..205c92280838 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -22,7 +22,6 @@
 #include <linux/slab.h>
 #include <linux/mount.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 3551f1f839eb..0d9e23a39e49 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -156,15 +156,15 @@ static struct dentry *proc_ns_dir_lookup(struct inode *dir,
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto out;
 
-	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
-	for (entry = ns_entries; entry <= last; entry++) {
+	last = &ns_entries[ARRAY_SIZE(ns_entries)];
+	for (entry = ns_entries; entry < last; entry++) {
 		if (strlen((*entry)->name) != len)
 			continue;
 		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
 			break;
 	}
 	error = ERR_PTR(-ENOENT);
-	if (entry > last)
+	if (entry == last)
 		goto out;
 
 	error = proc_ns_instantiate(dir, dentry, task, *entry);
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 46a15d8a29ca..eed44bfc85db 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -115,12 +115,13 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
 
+	if (!proc_parse_options(options, ns)) {
+		deactivate_locked_super(sb);
+		return ERR_PTR(-EINVAL);
+	}
+
 	if (!sb->s_root) {
 		sb->s_flags = flags;
-		if (!proc_parse_options(options, ns)) {
-			deactivate_locked_super(sb);
-			return ERR_PTR(-EINVAL);
-		}
 		err = proc_fill_super(sb);
 		if (err) {
 			deactivate_locked_super(sb);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 9694cc283511..2b9a7607cbd5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -781,12 +781,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	int err = 0;
 	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
 
-	if (pmd_trans_unstable(pmd))
-		return 0;
-
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
-	spin_lock(&walk->mm->page_table_lock);
 	if (pmd_trans_huge_lock(pmd, vma) == 1) {
 		for (; addr != end; addr += PAGE_SIZE) {
 			unsigned long offset;
@@ -802,6 +798,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		return err;
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	for (; addr != end; addr += PAGE_SIZE) {
 
 		/* check to see if we've left 'vma' behind
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index f37c32b94525..19507889bb7f 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -52,12 +52,6 @@ struct pstore_private {
 	char	data[];
 };
 
-static int pstore_file_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t pstore_file_read(struct file *file, char __user *userbuf,
 						size_t count, loff_t *ppos)
 {
@@ -67,7 +61,7 @@ static ssize_t pstore_file_read(struct file *file, char __user *userbuf,
 }
 
 static const struct file_operations pstore_file_operations = {
-	.open	= pstore_file_open,
+	.open	= simple_open,
 	.read	= pstore_file_read,
 	.llseek	= default_llseek,
 };
@@ -105,26 +99,12 @@ static const struct inode_operations pstore_dir_inode_operations = {
 	.unlink		= pstore_unlink,
 };
 
-static struct inode *pstore_get_inode(struct super_block *sb,
-					const struct inode *dir, int mode, dev_t dev)
+static struct inode *pstore_get_inode(struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
-
 	if (inode) {
 		inode->i_ino = get_next_ino();
-		inode->i_uid = inode->i_gid = 0;
-		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		switch (mode & S_IFMT) {
-		case S_IFREG:
-			inode->i_fop = &pstore_file_operations;
-			break;
-		case S_IFDIR:
-			inode->i_op = &pstore_dir_inode_operations;
-			inode->i_fop = &simple_dir_operations;
-			inc_nlink(inode);
-			break;
-		}
 	}
 	return inode;
 }
@@ -216,9 +196,11 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id,
 		return rc;
 
 	rc = -ENOMEM;
-	inode = pstore_get_inode(pstore_sb, root->d_inode, S_IFREG | 0444, 0);
+	inode = pstore_get_inode(pstore_sb);
 	if (!inode)
 		goto fail;
+	inode->i_mode = S_IFREG | 0444;
+	inode->i_fop = &pstore_file_operations;
 	private = kmalloc(sizeof *private + size, GFP_KERNEL);
 	if (!private)
 		goto fail_alloc;
@@ -293,10 +275,12 @@ int pstore_fill_super(struct super_block *sb, void *data, int silent)
 
 	parse_options(data);
 
-	inode = pstore_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	inode = pstore_get_inode(sb);
 	if (inode) {
-		/* override ramfs "dir" options so we catch unlink(2) */
+		inode->i_mode = S_IFDIR | 0755;
 		inode->i_op = &pstore_dir_inode_operations;
+		inode->i_fop = &simple_dir_operations;
+		inc_nlink(inode);
 	}
 	sb->s_root = d_make_root(inode);
 	if (!sb->s_root)
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 8b4f12b33f57..d69a1d1d7e15 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1110,6 +1110,13 @@ static void dquot_decr_space(struct dquot *dquot, qsize_t number)
 	clear_bit(DQ_BLKS_B, &dquot->dq_flags);
 }
 
+struct dquot_warn {
+	struct super_block *w_sb;
+	qid_t w_dq_id;
+	short w_dq_type;
+	short w_type;
+};
+
 static int warning_issued(struct dquot *dquot, const int warntype)
 {
 	int flag = (warntype == QUOTA_NL_BHARDWARN ||
@@ -1125,41 +1132,42 @@ static int warning_issued(struct dquot *dquot, const int warntype)
 #ifdef CONFIG_PRINT_QUOTA_WARNING
 static int flag_print_warnings = 1;
 
-static int need_print_warning(struct dquot *dquot)
+static int need_print_warning(struct dquot_warn *warn)
 {
 	if (!flag_print_warnings)
 		return 0;
 
-	switch (dquot->dq_type) {
+	switch (warn->w_dq_type) {
 		case USRQUOTA:
-			return current_fsuid() == dquot->dq_id;
+			return current_fsuid() == warn->w_dq_id;
 		case GRPQUOTA:
-			return in_group_p(dquot->dq_id);
+			return in_group_p(warn->w_dq_id);
 	}
 	return 0;
 }
 
 /* Print warning to user which exceeded quota */
-static void print_warning(struct dquot *dquot, const int warntype)
+static void print_warning(struct dquot_warn *warn)
 {
 	char *msg = NULL;
 	struct tty_struct *tty;
+	int warntype = warn->w_type;
 
 	if (warntype == QUOTA_NL_IHARDBELOW ||
 	    warntype == QUOTA_NL_ISOFTBELOW ||
 	    warntype == QUOTA_NL_BHARDBELOW ||
-	    warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(dquot))
+	    warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(warn))
 		return;
 
 	tty = get_current_tty();
 	if (!tty)
 		return;
-	tty_write_message(tty, dquot->dq_sb->s_id);
+	tty_write_message(tty, warn->w_sb->s_id);
 	if (warntype == QUOTA_NL_ISOFTWARN || warntype == QUOTA_NL_BSOFTWARN)
 		tty_write_message(tty, ": warning, ");
 	else
 		tty_write_message(tty, ": write failed, ");
-	tty_write_message(tty, quotatypes[dquot->dq_type]);
+	tty_write_message(tty, quotatypes[warn->w_dq_type]);
 	switch (warntype) {
 		case QUOTA_NL_IHARDWARN:
 			msg = " file limit reached.\r\n";
@@ -1185,26 +1193,34 @@ static void print_warning(struct dquot *dquot, const int warntype)
 }
 #endif
 
+static void prepare_warning(struct dquot_warn *warn, struct dquot *dquot,
+			    int warntype)
+{
+	if (warning_issued(dquot, warntype))
+		return;
+	warn->w_type = warntype;
+	warn->w_sb = dquot->dq_sb;
+	warn->w_dq_id = dquot->dq_id;
+	warn->w_dq_type = dquot->dq_type;
+}
+
 /*
  * Write warnings to the console and send warning messages over netlink.
  *
- * Note that this function can sleep.
+ * Note that this function can call into tty and networking code.
  */
-static void flush_warnings(struct dquot *const *dquots, char *warntype)
+static void flush_warnings(struct dquot_warn *warn)
 {
-	struct dquot *dq;
 	int i;
 
 	for (i = 0; i < MAXQUOTAS; i++) {
-		dq = dquots[i];
-		if (dq && warntype[i] != QUOTA_NL_NOWARN &&
-		    !warning_issued(dq, warntype[i])) {
+		if (warn[i].w_type == QUOTA_NL_NOWARN)
+			continue;
 #ifdef CONFIG_PRINT_QUOTA_WARNING
-			print_warning(dq, warntype[i]);
+		print_warning(&warn[i]);
 #endif
-			quota_send_warning(dq->dq_type, dq->dq_id,
-					   dq->dq_sb->s_dev, warntype[i]);
-		}
+		quota_send_warning(warn[i].w_dq_type, warn[i].w_dq_id,
+				   warn[i].w_sb->s_dev, warn[i].w_type);
 	}
 }
 
@@ -1218,11 +1234,11 @@ static int ignore_hardlimit(struct dquot *dquot)
 }
 
 /* needs dq_data_lock */
-static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
+static int check_idq(struct dquot *dquot, qsize_t inodes,
+		     struct dquot_warn *warn)
 {
 	qsize_t newinodes = dquot->dq_dqb.dqb_curinodes + inodes;
 
-	*warntype = QUOTA_NL_NOWARN;
 	if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_type) ||
 	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
 		return 0;
@@ -1230,7 +1246,7 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
 	if (dquot->dq_dqb.dqb_ihardlimit &&
 	    newinodes > dquot->dq_dqb.dqb_ihardlimit &&
             !ignore_hardlimit(dquot)) {
-		*warntype = QUOTA_NL_IHARDWARN;
+		prepare_warning(warn, dquot, QUOTA_NL_IHARDWARN);
 		return -EDQUOT;
 	}
 
@@ -1239,14 +1255,14 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
 	    dquot->dq_dqb.dqb_itime &&
 	    get_seconds() >= dquot->dq_dqb.dqb_itime &&
             !ignore_hardlimit(dquot)) {
-		*warntype = QUOTA_NL_ISOFTLONGWARN;
+		prepare_warning(warn, dquot, QUOTA_NL_ISOFTLONGWARN);
 		return -EDQUOT;
 	}
 
 	if (dquot->dq_dqb.dqb_isoftlimit &&
 	    newinodes > dquot->dq_dqb.dqb_isoftlimit &&
 	    dquot->dq_dqb.dqb_itime == 0) {
-		*warntype = QUOTA_NL_ISOFTWARN;
+		prepare_warning(warn, dquot, QUOTA_NL_ISOFTWARN);
 		dquot->dq_dqb.dqb_itime = get_seconds() +
 		    sb_dqopt(dquot->dq_sb)->info[dquot->dq_type].dqi_igrace;
 	}
@@ -1255,12 +1271,12 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
 }
 
 /* needs dq_data_lock */
-static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *warntype)
+static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc,
+		     struct dquot_warn *warn)
 {
 	qsize_t tspace;
 	struct super_block *sb = dquot->dq_sb;
 
-	*warntype = QUOTA_NL_NOWARN;
 	if (!sb_has_quota_limits_enabled(sb, dquot->dq_type) ||
 	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
 		return 0;
@@ -1272,7 +1288,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
 	    tspace > dquot->dq_dqb.dqb_bhardlimit &&
             !ignore_hardlimit(dquot)) {
 		if (!prealloc)
-			*warntype = QUOTA_NL_BHARDWARN;
+			prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN);
 		return -EDQUOT;
 	}
 
@@ -1282,7 +1298,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
 	    get_seconds() >= dquot->dq_dqb.dqb_btime &&
             !ignore_hardlimit(dquot)) {
 		if (!prealloc)
-			*warntype = QUOTA_NL_BSOFTLONGWARN;
+			prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN);
 		return -EDQUOT;
 	}
 
@@ -1290,7 +1306,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
 	    tspace > dquot->dq_dqb.dqb_bsoftlimit &&
 	    dquot->dq_dqb.dqb_btime == 0) {
 		if (!prealloc) {
-			*warntype = QUOTA_NL_BSOFTWARN;
+			prepare_warning(warn, dquot, QUOTA_NL_BSOFTWARN);
 			dquot->dq_dqb.dqb_btime = get_seconds() +
 			    sb_dqopt(sb)->info[dquot->dq_type].dqi_bgrace;
 		}
@@ -1543,10 +1559,9 @@ static void inode_decr_space(struct inode *inode, qsize_t number, int reserve)
 int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
 {
 	int cnt, ret = 0;
-	char warntype[MAXQUOTAS];
-	int warn = flags & DQUOT_SPACE_WARN;
+	struct dquot_warn warn[MAXQUOTAS];
+	struct dquot **dquots = inode->i_dquot;
 	int reserve = flags & DQUOT_SPACE_RESERVE;
-	int nofail = flags & DQUOT_SPACE_NOFAIL;
 
 	/*
 	 * First test before acquiring mutex - solves deadlocks when we
@@ -1559,36 +1574,36 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
 
 	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		warntype[cnt] = QUOTA_NL_NOWARN;
+		warn[cnt].w_type = QUOTA_NL_NOWARN;
 
 	spin_lock(&dq_data_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (!inode->i_dquot[cnt])
+		if (!dquots[cnt])
 			continue;
-		ret = check_bdq(inode->i_dquot[cnt], number, !warn,
-				warntype+cnt);
-		if (ret && !nofail) {
+		ret = check_bdq(dquots[cnt], number,
+				!(flags & DQUOT_SPACE_WARN), &warn[cnt]);
+		if (ret && !(flags & DQUOT_SPACE_NOFAIL)) {
 			spin_unlock(&dq_data_lock);
 			goto out_flush_warn;
 		}
 	}
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (!inode->i_dquot[cnt])
+		if (!dquots[cnt])
 			continue;
 		if (reserve)
-			dquot_resv_space(inode->i_dquot[cnt], number);
+			dquot_resv_space(dquots[cnt], number);
 		else
-			dquot_incr_space(inode->i_dquot[cnt], number);
+			dquot_incr_space(dquots[cnt], number);
 	}
 	inode_incr_space(inode, number, reserve);
 	spin_unlock(&dq_data_lock);
 
 	if (reserve)
 		goto out_flush_warn;
-	mark_all_dquot_dirty(inode->i_dquot);
+	mark_all_dquot_dirty(dquots);
 out_flush_warn:
-	flush_warnings(inode->i_dquot, warntype);
 	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+	flush_warnings(warn);
 out:
 	return ret;
 }
@@ -1600,36 +1615,37 @@ EXPORT_SYMBOL(__dquot_alloc_space);
 int dquot_alloc_inode(const struct inode *inode)
 {
 	int cnt, ret = 0;
-	char warntype[MAXQUOTAS];
+	struct dquot_warn warn[MAXQUOTAS];
+	struct dquot * const *dquots = inode->i_dquot;
 
 	/* First test before acquiring mutex - solves deadlocks when we
          * re-enter the quota code and are already holding the mutex */
 	if (!dquot_active(inode))
 		return 0;
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		warntype[cnt] = QUOTA_NL_NOWARN;
+		warn[cnt].w_type = QUOTA_NL_NOWARN;
 	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	spin_lock(&dq_data_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (!inode->i_dquot[cnt])
+		if (!dquots[cnt])
 			continue;
-		ret = check_idq(inode->i_dquot[cnt], 1, warntype + cnt);
+		ret = check_idq(dquots[cnt], 1, &warn[cnt]);
 		if (ret)
 			goto warn_put_all;
 	}
 
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (!inode->i_dquot[cnt])
+		if (!dquots[cnt])
 			continue;
-		dquot_incr_inodes(inode->i_dquot[cnt], 1);
+		dquot_incr_inodes(dquots[cnt], 1);
 	}
 
 warn_put_all:
 	spin_unlock(&dq_data_lock);
 	if (ret == 0)
-		mark_all_dquot_dirty(inode->i_dquot);
-	flush_warnings(inode->i_dquot, warntype);
+		mark_all_dquot_dirty(dquots);
 	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+	flush_warnings(warn);
 	return ret;
 }
 EXPORT_SYMBOL(dquot_alloc_inode);
@@ -1669,7 +1685,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty);
 void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
 {
 	unsigned int cnt;
-	char warntype[MAXQUOTAS];
+	struct dquot_warn warn[MAXQUOTAS];
+	struct dquot **dquots = inode->i_dquot;
 	int reserve = flags & DQUOT_SPACE_RESERVE;
 
 	/* First test before acquiring mutex - solves deadlocks when we
@@ -1682,23 +1699,28 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
 	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	spin_lock(&dq_data_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (!inode->i_dquot[cnt])
+		int wtype;
+
+		warn[cnt].w_type = QUOTA_NL_NOWARN;
+		if (!dquots[cnt])
 			continue;
-		warntype[cnt] = info_bdq_free(inode->i_dquot[cnt], number);
+		wtype = info_bdq_free(dquots[cnt], number);
+		if (wtype != QUOTA_NL_NOWARN)
+			prepare_warning(&warn[cnt], dquots[cnt], wtype);
 		if (reserve)
-			dquot_free_reserved_space(inode->i_dquot[cnt], number);
+			dquot_free_reserved_space(dquots[cnt], number);
 		else
-			dquot_decr_space(inode->i_dquot[cnt], number);
+			dquot_decr_space(dquots[cnt], number);
 	}
 	inode_decr_space(inode, number, reserve);
 	spin_unlock(&dq_data_lock);
 
 	if (reserve)
 		goto out_unlock;
-	mark_all_dquot_dirty(inode->i_dquot);
+	mark_all_dquot_dirty(dquots);
 out_unlock:
-	flush_warnings(inode->i_dquot, warntype);
 	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+	flush_warnings(warn);
 }
 EXPORT_SYMBOL(__dquot_free_space);
 
@@ -1708,7 +1730,8 @@ EXPORT_SYMBOL(__dquot_free_space);
 void dquot_free_inode(const struct inode *inode)
 {
 	unsigned int cnt;
-	char warntype[MAXQUOTAS];
+	struct dquot_warn warn[MAXQUOTAS];
+	struct dquot * const *dquots = inode->i_dquot;
 
 	/* First test before acquiring mutex - solves deadlocks when we
          * re-enter the quota code and are already holding the mutex */
@@ -1718,15 +1741,20 @@ void dquot_free_inode(const struct inode *inode)
 	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	spin_lock(&dq_data_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (!inode->i_dquot[cnt])
+		int wtype;
+
+		warn[cnt].w_type = QUOTA_NL_NOWARN;
+		if (!dquots[cnt])
 			continue;
-		warntype[cnt] = info_idq_free(inode->i_dquot[cnt], 1);
-		dquot_decr_inodes(inode->i_dquot[cnt], 1);
+		wtype = info_idq_free(dquots[cnt], 1);
+		if (wtype != QUOTA_NL_NOWARN)
+			prepare_warning(&warn[cnt], dquots[cnt], wtype);
+		dquot_decr_inodes(dquots[cnt], 1);
 	}
 	spin_unlock(&dq_data_lock);
-	mark_all_dquot_dirty(inode->i_dquot);
-	flush_warnings(inode->i_dquot, warntype);
+	mark_all_dquot_dirty(dquots);
 	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+	flush_warnings(warn);
 }
 EXPORT_SYMBOL(dquot_free_inode);
 
@@ -1747,16 +1775,20 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 	struct dquot *transfer_from[MAXQUOTAS] = {};
 	int cnt, ret = 0;
 	char is_valid[MAXQUOTAS] = {};
-	char warntype_to[MAXQUOTAS];
-	char warntype_from_inodes[MAXQUOTAS], warntype_from_space[MAXQUOTAS];
+	struct dquot_warn warn_to[MAXQUOTAS];
+	struct dquot_warn warn_from_inodes[MAXQUOTAS];
+	struct dquot_warn warn_from_space[MAXQUOTAS];
 
 	/* First test before acquiring mutex - solves deadlocks when we
          * re-enter the quota code and are already holding the mutex */
 	if (IS_NOQUOTA(inode))
 		return 0;
 	/* Initialize the arrays */
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		warntype_to[cnt] = QUOTA_NL_NOWARN;
+	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+		warn_to[cnt].w_type = QUOTA_NL_NOWARN;
+		warn_from_inodes[cnt].w_type = QUOTA_NL_NOWARN;
+		warn_from_space[cnt].w_type = QUOTA_NL_NOWARN;
+	}
 	down_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	if (IS_NOQUOTA(inode)) {	/* File without quota accounting? */
 		up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
@@ -1778,10 +1810,10 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 			continue;
 		is_valid[cnt] = 1;
 		transfer_from[cnt] = inode->i_dquot[cnt];
-		ret = check_idq(transfer_to[cnt], 1, warntype_to + cnt);
+		ret = check_idq(transfer_to[cnt], 1, &warn_to[cnt]);
 		if (ret)
 			goto over_quota;
-		ret = check_bdq(transfer_to[cnt], space, 0, warntype_to + cnt);
+		ret = check_bdq(transfer_to[cnt], space, 0, &warn_to[cnt]);
 		if (ret)
 			goto over_quota;
 	}
@@ -1794,10 +1826,15 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 			continue;
 		/* Due to IO error we might not have transfer_from[] structure */
 		if (transfer_from[cnt]) {
-			warntype_from_inodes[cnt] =
-				info_idq_free(transfer_from[cnt], 1);
-			warntype_from_space[cnt] =
-				info_bdq_free(transfer_from[cnt], space);
+			int wtype;
+			wtype = info_idq_free(transfer_from[cnt], 1);
+			if (wtype != QUOTA_NL_NOWARN)
+				prepare_warning(&warn_from_inodes[cnt],
+						transfer_from[cnt], wtype);
+			wtype = info_bdq_free(transfer_from[cnt], space);
+			if (wtype != QUOTA_NL_NOWARN)
+				prepare_warning(&warn_from_space[cnt],
+						transfer_from[cnt], wtype);
 			dquot_decr_inodes(transfer_from[cnt], 1);
 			dquot_decr_space(transfer_from[cnt], cur_space);
 			dquot_free_reserved_space(transfer_from[cnt],
@@ -1815,9 +1852,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 
 	mark_all_dquot_dirty(transfer_from);
 	mark_all_dquot_dirty(transfer_to);
-	flush_warnings(transfer_to, warntype_to);
-	flush_warnings(transfer_from, warntype_from_inodes);
-	flush_warnings(transfer_from, warntype_from_space);
+	flush_warnings(warn_to);
+	flush_warnings(warn_from_inodes);
+	flush_warnings(warn_from_space);
 	/* Pass back references to put */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
 		if (is_valid[cnt])
@@ -1826,7 +1863,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 over_quota:
 	spin_unlock(&dq_data_lock);
 	up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
-	flush_warnings(transfer_to, warntype_to);
+	flush_warnings(warn_to);
 	return ret;
 }
 EXPORT_SYMBOL(__dquot_transfer);
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index cf9f4de00a95..b1a08573fe14 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -51,7 +51,6 @@
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 
 /* gets a struct reiserfs_journal_list * from a list head */
 #define JOURNAL_LIST_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c
index 71e2b4d50a0a..f86f51f99ace 100644
--- a/fs/romfs/storage.c
+++ b/fs/romfs/storage.c
@@ -19,7 +19,7 @@
 #endif
 
 #ifdef CONFIG_ROMFS_ON_MTD
-#define ROMFS_MTD_READ(sb, ...) ((sb)->s_mtd->read((sb)->s_mtd, ##__VA_ARGS__))
+#define ROMFS_MTD_READ(sb, ...) mtd_read((sb)->s_mtd, ##__VA_ARGS__)
 
 /*
  * read data from an romfs image on an MTD device
diff --git a/fs/select.c b/fs/select.c
index 6fb8943d580b..17d33d09fc16 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -348,7 +348,7 @@ static int max_select_fd(unsigned long n, fd_set_bits *fds)
 	set = ~(~0UL << (n & (__NFDBITS-1)));
 	n /= __NFDBITS;
 	fdt = files_fdtable(current->files);
-	open_fds = fdt->open_fds->fds_bits+n;
+	open_fds = fdt->open_fds + n;
 	max = 0;
 	if (set) {
 		set &= BITS(fds, n);
diff --git a/fs/splice.c b/fs/splice.c
index 5f883de7ef3a..f8476841eb04 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -30,6 +30,7 @@
 #include <linux/uio.h>
 #include <linux/security.h>
 #include <linux/gfp.h>
+#include <linux/socket.h>
 
 /*
  * Attempt to steal a page from a pipe buffer. This should perhaps go into
@@ -690,7 +691,9 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
 	if (!likely(file->f_op && file->f_op->sendpage))
 		return -EINVAL;
 
-	more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
+	more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0;
+	if (sd->len < sd->total_len)
+		more |= MSG_SENDPAGE_NOTLAST;
 	return file->f_op->sendpage(file, buf->page, buf->offset,
 				    sd->len, &pos, more);
 }
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index ed0eb2a921f4..fb50652e4e11 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -83,7 +83,8 @@ static struct buffer_head *get_block_length(struct super_block *sb,
  * filesystem), otherwise the length is obtained from the first two bytes of
  * the metadata block.  A bit in the length field indicates if the block
  * is stored uncompressed in the filesystem (usually because compression
- * generated a larger block - this does occasionally happen with zlib).
+ * generated a larger block - this does occasionally happen with compression
+ * algorithms).
  */
 int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 			int length, u64 *next_index, int srclength, int pages)
diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c
index 9dfe2ce0fb70..b381305c9a47 100644
--- a/fs/squashfs/dir.c
+++ b/fs/squashfs/dir.c
@@ -64,7 +64,7 @@ static int get_dir_index_using_offset(struct super_block *sb,
 	 * is offset by 3 because we invent "." and ".." entries which are
 	 * not actually stored in the directory.
 	 */
-	if (f_pos < 3)
+	if (f_pos <= 3)
 		return f_pos;
 	f_pos -= 3;
 
@@ -105,7 +105,7 @@ static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir)
 	struct inode *inode = file->f_dentry->d_inode;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 	u64 block = squashfs_i(inode)->start + msblk->directory_table;
-	int offset = squashfs_i(inode)->offset, length = 0, dir_count, size,
+	int offset = squashfs_i(inode)->offset, length, dir_count, size,
 				type, err;
 	unsigned int inode_number;
 	struct squashfs_dir_header dirh;
@@ -173,8 +173,7 @@ static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir)
 
 		dir_count = le32_to_cpu(dirh.count) + 1;
 
-		/* dir_count should never be larger than 256 */
-		if (dir_count > 256)
+		if (dir_count > SQUASHFS_DIR_COUNT)
 			goto failed_read;
 
 		while (dir_count--) {
diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c
index 0682b38d7e31..abcc58f3c152 100644
--- a/fs/squashfs/namei.c
+++ b/fs/squashfs/namei.c
@@ -144,7 +144,7 @@ static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct squashfs_dir_entry *dire;
 	u64 block = squashfs_i(dir)->start + msblk->directory_table;
 	int offset = squashfs_i(dir)->offset;
-	int err, length = 0, dir_count, size;
+	int err, length, dir_count, size;
 
 	TRACE("Entered squashfs_lookup [%llx:%x]\n", block, offset);
 
@@ -177,8 +177,7 @@ static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
 
 		dir_count = le32_to_cpu(dirh.count) + 1;
 
-		/* dir_count should never be larger than 256 */
-		if (dir_count > 256)
+		if (dir_count > SQUASHFS_DIR_COUNT)
 			goto data_error;
 
 		while (dir_count--) {
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index e8e14645de9a..9e2349d07cb1 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -30,11 +30,6 @@
 
 /* size of metadata (inode and directory) blocks */
 #define SQUASHFS_METADATA_SIZE		8192
-#define SQUASHFS_METADATA_LOG		13
-
-/* default size of data blocks */
-#define SQUASHFS_FILE_SIZE		131072
-#define SQUASHFS_FILE_LOG		17
 
 /* default size of block device I/O */
 #ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE
@@ -46,12 +41,12 @@
 #define SQUASHFS_FILE_MAX_SIZE		1048576
 #define SQUASHFS_FILE_MAX_LOG		20
 
-/* Max number of uids and gids */
-#define SQUASHFS_IDS			65536
-
 /* Max length of filename (not 255) */
 #define SQUASHFS_NAME_LEN		256
 
+/* Max value for directory header count*/
+#define SQUASHFS_DIR_COUNT		256
+
 #define SQUASHFS_INVALID_FRAG		(0xffffffffU)
 #define SQUASHFS_INVALID_XATTR		(0xffffffffU)
 #define SQUASHFS_INVALID_BLK		(-1LL)
@@ -142,9 +137,6 @@
 #define SQUASHFS_MKINODE(A, B)		((long long)(((long long) (A)\
 					<< 16) + (B)))
 
-/* Translate between VFS mode and squashfs mode */
-#define SQUASHFS_MODE(A)		((A) & 0xfff)
-
 /* fragment and fragment table defines */
 #define SQUASHFS_FRAGMENT_BYTES(A)	\
 				((A) * sizeof(struct squashfs_fragment_entry))
@@ -215,11 +207,6 @@
 /* cached data constants for filesystem */
 #define SQUASHFS_CACHED_BLKS		8
 
-#define SQUASHFS_MAX_FILE_SIZE_LOG	64
-
-#define SQUASHFS_MAX_FILE_SIZE		(1LL << \
-					(SQUASHFS_MAX_FILE_SIZE_LOG - 2))
-
 /* meta index cache */
 #define SQUASHFS_META_INDEXES	(SQUASHFS_METADATA_SIZE / sizeof(unsigned int))
 #define SQUASHFS_META_ENTRIES	127
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 970b1167e7cb..29cd014ed3a1 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -158,10 +158,15 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+	/* Check block log for sanity */
 	msblk->block_log = le16_to_cpu(sblk->block_log);
 	if (msblk->block_log > SQUASHFS_FILE_MAX_LOG)
 		goto failed_mount;
 
+	/* Check that block_size and block_log match */
+	if (msblk->block_size != (1 << msblk->block_log))
+		goto failed_mount;
+
 	/* Check the root inode for sanity */
 	root_inode = le64_to_cpu(sblk->root_inode);
 	if (SQUASHFS_INODE_OFFSET(root_inode) > SQUASHFS_METADATA_SIZE)
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 987585bb0a1d..1ba2baaf4367 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -105,7 +105,6 @@ static void udf_add_free_space(struct super_block *sb, u16 partition, u32 cnt)
 }
 
 static void udf_bitmap_free_blocks(struct super_block *sb,
-				   struct inode *inode,
 				   struct udf_bitmap *bitmap,
 				   struct kernel_lb_addr *bloc,
 				   uint32_t offset,
@@ -172,7 +171,6 @@ error_return:
 }
 
 static int udf_bitmap_prealloc_blocks(struct super_block *sb,
-				      struct inode *inode,
 				      struct udf_bitmap *bitmap,
 				      uint16_t partition, uint32_t first_block,
 				      uint32_t block_count)
@@ -223,7 +221,6 @@ out:
 }
 
 static int udf_bitmap_new_block(struct super_block *sb,
-				struct inode *inode,
 				struct udf_bitmap *bitmap, uint16_t partition,
 				uint32_t goal, int *err)
 {
@@ -349,7 +346,6 @@ error_return:
 }
 
 static void udf_table_free_blocks(struct super_block *sb,
-				  struct inode *inode,
 				  struct inode *table,
 				  struct kernel_lb_addr *bloc,
 				  uint32_t offset,
@@ -581,7 +577,6 @@ error_return:
 }
 
 static int udf_table_prealloc_blocks(struct super_block *sb,
-				     struct inode *inode,
 				     struct inode *table, uint16_t partition,
 				     uint32_t first_block, uint32_t block_count)
 {
@@ -643,7 +638,6 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
 }
 
 static int udf_table_new_block(struct super_block *sb,
-			       struct inode *inode,
 			       struct inode *table, uint16_t partition,
 			       uint32_t goal, int *err)
 {
@@ -743,18 +737,23 @@ void udf_free_blocks(struct super_block *sb, struct inode *inode,
 	struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition];
 
 	if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) {
-		udf_bitmap_free_blocks(sb, inode, map->s_uspace.s_bitmap,
+		udf_bitmap_free_blocks(sb, map->s_uspace.s_bitmap,
 				       bloc, offset, count);
 	} else if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE) {
-		udf_table_free_blocks(sb, inode, map->s_uspace.s_table,
+		udf_table_free_blocks(sb, map->s_uspace.s_table,
 				      bloc, offset, count);
 	} else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP) {
-		udf_bitmap_free_blocks(sb, inode, map->s_fspace.s_bitmap,
+		udf_bitmap_free_blocks(sb, map->s_fspace.s_bitmap,
 				       bloc, offset, count);
 	} else if (map->s_partition_flags & UDF_PART_FLAG_FREED_TABLE) {
-		udf_table_free_blocks(sb, inode, map->s_fspace.s_table,
+		udf_table_free_blocks(sb, map->s_fspace.s_table,
 				      bloc, offset, count);
 	}
+
+	if (inode) {
+		inode_sub_bytes(inode,
+				((sector_t)count) << sb->s_blocksize_bits);
+	}
 }
 
 inline int udf_prealloc_blocks(struct super_block *sb,
@@ -763,29 +762,34 @@ inline int udf_prealloc_blocks(struct super_block *sb,
 			       uint32_t block_count)
 {
 	struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition];
+	sector_t allocated;
 
 	if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP)
-		return udf_bitmap_prealloc_blocks(sb, inode,
-						  map->s_uspace.s_bitmap,
-						  partition, first_block,
-						  block_count);
+		allocated = udf_bitmap_prealloc_blocks(sb,
+						       map->s_uspace.s_bitmap,
+						       partition, first_block,
+						       block_count);
 	else if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE)
-		return udf_table_prealloc_blocks(sb, inode,
-						 map->s_uspace.s_table,
-						 partition, first_block,
-						 block_count);
+		allocated = udf_table_prealloc_blocks(sb,
+						      map->s_uspace.s_table,
+						      partition, first_block,
+						      block_count);
 	else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP)
-		return udf_bitmap_prealloc_blocks(sb, inode,
-						  map->s_fspace.s_bitmap,
-						  partition, first_block,
-						  block_count);
+		allocated = udf_bitmap_prealloc_blocks(sb,
+						       map->s_fspace.s_bitmap,
+						       partition, first_block,
+						       block_count);
 	else if (map->s_partition_flags & UDF_PART_FLAG_FREED_TABLE)
-		return udf_table_prealloc_blocks(sb, inode,
-						 map->s_fspace.s_table,
-						 partition, first_block,
-						 block_count);
+		allocated = udf_table_prealloc_blocks(sb,
+						      map->s_fspace.s_table,
+						      partition, first_block,
+						      block_count);
 	else
 		return 0;
+
+	if (inode && allocated > 0)
+		inode_add_bytes(inode, allocated << sb->s_blocksize_bits);
+	return allocated;
 }
 
 inline int udf_new_block(struct super_block *sb,
@@ -793,25 +797,29 @@ inline int udf_new_block(struct super_block *sb,
 			 uint16_t partition, uint32_t goal, int *err)
 {
 	struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition];
+	int block;
 
 	if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP)
-		return udf_bitmap_new_block(sb, inode,
-					   map->s_uspace.s_bitmap,
-					   partition, goal, err);
+		block = udf_bitmap_new_block(sb,
+					     map->s_uspace.s_bitmap,
+					     partition, goal, err);
 	else if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE)
-		return udf_table_new_block(sb, inode,
-					   map->s_uspace.s_table,
-					   partition, goal, err);
-	else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP)
-		return udf_bitmap_new_block(sb, inode,
-					    map->s_fspace.s_bitmap,
+		block = udf_table_new_block(sb,
+					    map->s_uspace.s_table,
 					    partition, goal, err);
+	else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP)
+		block = udf_bitmap_new_block(sb,
+					     map->s_fspace.s_bitmap,
+					     partition, goal, err);
 	else if (map->s_partition_flags & UDF_PART_FLAG_FREED_TABLE)
-		return udf_table_new_block(sb, inode,
-					   map->s_fspace.s_table,
-					   partition, goal, err);
+		block = udf_table_new_block(sb,
+					    map->s_fspace.s_table,
+					    partition, goal, err);
 	else {
 		*err = -EIO;
 		return 0;
 	}
+	if (inode && block)
+		inode_add_bytes(inode, sb->s_blocksize);
+	return block;
 }
diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c
index 05ab48195be9..7e5aae4bf46f 100644
--- a/fs/udf/ialloc.c
+++ b/fs/udf/ialloc.c
@@ -116,6 +116,7 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err)
 	iinfo->i_lenEAttr = 0;
 	iinfo->i_lenAlloc = 0;
 	iinfo->i_use = 0;
+	iinfo->i_checkpoint = 1;
 	if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_AD_IN_ICB))
 		iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB;
 	else if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 7699df7b3198..7d7528008359 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1358,6 +1358,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh)
 		iinfo->i_unique = le64_to_cpu(fe->uniqueID);
 		iinfo->i_lenEAttr = le32_to_cpu(fe->lengthExtendedAttr);
 		iinfo->i_lenAlloc = le32_to_cpu(fe->lengthAllocDescs);
+		iinfo->i_checkpoint = le32_to_cpu(fe->checkpoint);
 		offset = sizeof(struct fileEntry) + iinfo->i_lenEAttr;
 	} else {
 		inode->i_blocks = le64_to_cpu(efe->logicalBlocksRecorded) <<
@@ -1379,6 +1380,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh)
 		iinfo->i_unique = le64_to_cpu(efe->uniqueID);
 		iinfo->i_lenEAttr = le32_to_cpu(efe->lengthExtendedAttr);
 		iinfo->i_lenAlloc = le32_to_cpu(efe->lengthAllocDescs);
+		iinfo->i_checkpoint = le32_to_cpu(efe->checkpoint);
 		offset = sizeof(struct extendedFileEntry) +
 							iinfo->i_lenEAttr;
 	}
@@ -1495,6 +1497,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 	struct buffer_head *bh = NULL;
 	struct fileEntry *fe;
 	struct extendedFileEntry *efe;
+	uint64_t lb_recorded;
 	uint32_t udfperms;
 	uint16_t icbflags;
 	uint16_t crclen;
@@ -1589,13 +1592,18 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		dsea->minorDeviceIdent = cpu_to_le32(iminor(inode));
 	}
 
+	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)
+		lb_recorded = 0; /* No extents => no blocks! */
+	else
+		lb_recorded =
+			(inode->i_blocks + (1 << (blocksize_bits - 9)) - 1) >>
+			(blocksize_bits - 9);
+
 	if (iinfo->i_efe == 0) {
 		memcpy(bh->b_data + sizeof(struct fileEntry),
 		       iinfo->i_ext.i_data,
 		       inode->i_sb->s_blocksize - sizeof(struct fileEntry));
-		fe->logicalBlocksRecorded = cpu_to_le64(
-			(inode->i_blocks + (1 << (blocksize_bits - 9)) - 1) >>
-			(blocksize_bits - 9));
+		fe->logicalBlocksRecorded = cpu_to_le64(lb_recorded);
 
 		udf_time_to_disk_stamp(&fe->accessTime, inode->i_atime);
 		udf_time_to_disk_stamp(&fe->modificationTime, inode->i_mtime);
@@ -1607,6 +1615,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		fe->uniqueID = cpu_to_le64(iinfo->i_unique);
 		fe->lengthExtendedAttr = cpu_to_le32(iinfo->i_lenEAttr);
 		fe->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc);
+		fe->checkpoint = cpu_to_le32(iinfo->i_checkpoint);
 		fe->descTag.tagIdent = cpu_to_le16(TAG_IDENT_FE);
 		crclen = sizeof(struct fileEntry);
 	} else {
@@ -1615,9 +1624,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		       inode->i_sb->s_blocksize -
 					sizeof(struct extendedFileEntry));
 		efe->objectSize = cpu_to_le64(inode->i_size);
-		efe->logicalBlocksRecorded = cpu_to_le64(
-			(inode->i_blocks + (1 << (blocksize_bits - 9)) - 1) >>
-			(blocksize_bits - 9));
+		efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded);
 
 		if (iinfo->i_crtime.tv_sec > inode->i_atime.tv_sec ||
 		    (iinfo->i_crtime.tv_sec == inode->i_atime.tv_sec &&
@@ -1646,6 +1653,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		efe->uniqueID = cpu_to_le64(iinfo->i_unique);
 		efe->lengthExtendedAttr = cpu_to_le32(iinfo->i_lenEAttr);
 		efe->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc);
+		efe->checkpoint = cpu_to_le32(iinfo->i_checkpoint);
 		efe->descTag.tagIdent = cpu_to_le16(TAG_IDENT_EFE);
 		crclen = sizeof(struct extendedFileEntry);
 	}
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 85067b4c7e14..ac8a348dcb69 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -950,11 +950,8 @@ static struct udf_bitmap *udf_sb_alloc_bitmap(struct super_block *sb, u32 index)
 	else
 		bitmap = vzalloc(size); /* TODO: get rid of vzalloc */
 
-	if (bitmap == NULL) {
-		udf_err(sb, "Unable to allocate space for bitmap and %d buffer_head pointers\n",
-			nr_groups);
+	if (bitmap == NULL)
 		return NULL;
-	}
 
 	bitmap->s_block_bitmap = (struct buffer_head **)(bitmap + 1);
 	bitmap->s_nr_groups = nr_groups;
diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h
index d1bd31ea724e..bb8309dcd5c1 100644
--- a/fs/udf/udf_i.h
+++ b/fs/udf/udf_i.h
@@ -23,6 +23,7 @@ struct udf_inode_info {
 	__u64			i_lenExtents;
 	__u32			i_next_alloc_block;
 	__u32			i_next_alloc_goal;
+	__u32			i_checkpoint;
 	unsigned		i_alloc_type : 3;
 	unsigned		i_efe : 1;	/* extendedFileEntry */
 	unsigned		i_use : 1;	/* unallocSpaceEntry */
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 9094e1d917be..7cdd3953d67e 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -26,7 +26,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include <linux/errno.h>
 #include <linux/fs.h>
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index f636f6b460d0..ac8e279eccc6 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -73,7 +73,6 @@
 #include <stdarg.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include <linux/errno.h>
 #include <linux/fs.h>
diff --git a/fs/xattr.c b/fs/xattr.c
index d6dfd247bb2f..3c8c1cc333c7 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -19,8 +19,9 @@
 #include <linux/export.h>
 #include <linux/fsnotify.h>
 #include <linux/audit.h>
-#include <asm/uaccess.h>
+#include <linux/vmalloc.h>
 
+#include <asm/uaccess.h>
 
 /*
  * Check permissions for extended attribute access.  This is a bit complicated
@@ -320,6 +321,7 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 {
 	int error;
 	void *kvalue = NULL;
+	void *vvalue = NULL;	/* If non-NULL, we used vmalloc() */
 	char kname[XATTR_NAME_MAX + 1];
 
 	if (flags & ~(XATTR_CREATE|XATTR_REPLACE))
@@ -334,13 +336,25 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 	if (size) {
 		if (size > XATTR_SIZE_MAX)
 			return -E2BIG;
-		kvalue = memdup_user(value, size);
-		if (IS_ERR(kvalue))
-			return PTR_ERR(kvalue);
+		kvalue = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
+		if (!kvalue) {
+			vvalue = vmalloc(size);
+			if (!vvalue)
+				return -ENOMEM;
+			kvalue = vvalue;
+		}
+		if (copy_from_user(kvalue, value, size)) {
+			error = -EFAULT;
+			goto out;
+		}
 	}
 
 	error = vfs_setxattr(d, kname, kvalue, size, flags);
-	kfree(kvalue);
+out:
+	if (vvalue)
+		vfree(vvalue);
+	else
+		kfree(kvalue);
 	return error;
 }
 
@@ -492,13 +506,18 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 {
 	ssize_t error;
 	char *klist = NULL;
+	char *vlist = NULL;	/* If non-NULL, we used vmalloc() */
 
 	if (size) {
 		if (size > XATTR_LIST_MAX)
 			size = XATTR_LIST_MAX;
-		klist = kmalloc(size, GFP_KERNEL);
-		if (!klist)
-			return -ENOMEM;
+		klist = kmalloc(size, __GFP_NOWARN | GFP_KERNEL);
+		if (!klist) {
+			vlist = vmalloc(size);
+			if (!vlist)
+				return -ENOMEM;
+			klist = vlist;
+		}
 	}
 
 	error = vfs_listxattr(d, klist, size);
@@ -510,7 +529,10 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 		   than XATTR_LIST_MAX bytes. Not possible. */
 		error = -E2BIG;
 	}
-	kfree(klist);
+	if (vlist)
+		vfree(vlist);
+	else
+		kfree(klist);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index ce84ffd0264c..0f0df2759b09 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -35,6 +35,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 
+struct workqueue_struct *xfs_alloc_wq;
 
 #define XFS_ABSDIFF(a,b)	(((a) <= (b)) ? ((b) - (a)) : ((a) - (b)))
 
@@ -68,7 +69,7 @@ xfs_alloc_lookup_eq(
  * Lookup the first record greater than or equal to [bno, len]
  * in the btree given by cur.
  */
-STATIC int				/* error */
+int				/* error */
 xfs_alloc_lookup_ge(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_agblock_t		bno,	/* starting block of extent */
@@ -2207,7 +2208,7 @@ xfs_alloc_read_agf(
  * group or loop over the allocation groups to find the result.
  */
 int				/* error */
-xfs_alloc_vextent(
+__xfs_alloc_vextent(
 	xfs_alloc_arg_t	*args)	/* allocation argument structure */
 {
 	xfs_agblock_t	agsize;	/* allocation group size */
@@ -2417,6 +2418,37 @@ error0:
 	return error;
 }
 
+static void
+xfs_alloc_vextent_worker(
+	struct work_struct	*work)
+{
+	struct xfs_alloc_arg	*args = container_of(work,
+						struct xfs_alloc_arg, work);
+	unsigned long		pflags;
+
+	/* we are in a transaction context here */
+	current_set_flags_nested(&pflags, PF_FSTRANS);
+
+	args->result = __xfs_alloc_vextent(args);
+	complete(args->done);
+
+	current_restore_flags_nested(&pflags, PF_FSTRANS);
+}
+
+
+int				/* error */
+xfs_alloc_vextent(
+	xfs_alloc_arg_t	*args)	/* allocation argument structure */
+{
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	args->done = &done;
+	INIT_WORK(&args->work, xfs_alloc_vextent_worker);
+	queue_work(xfs_alloc_wq, &args->work);
+	wait_for_completion(&done);
+	return args->result;
+}
+
 /*
  * Free an extent.
  * Just break up the extent address and hand off to xfs_free_ag_extent
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 2f52b924be79..3a7e7d8f8ded 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -25,6 +25,8 @@ struct xfs_perag;
 struct xfs_trans;
 struct xfs_busy_extent;
 
+extern struct workqueue_struct *xfs_alloc_wq;
+
 /*
  * Freespace allocation types.  Argument to xfs_alloc_[v]extent.
  */
@@ -119,6 +121,9 @@ typedef struct xfs_alloc_arg {
 	char		isfl;		/* set if is freelist blocks - !acctg */
 	char		userdata;	/* set if this is user data */
 	xfs_fsblock_t	firstblock;	/* io first block allocated */
+	struct completion *done;
+	struct work_struct work;
+	int		result;
 } xfs_alloc_arg_t;
 
 /*
@@ -243,6 +248,13 @@ xfs_alloc_lookup_le(
 	xfs_extlen_t		len,	/* length of extent */
 	int			*stat);	/* success/failure */
 
+int				/* error */
+xfs_alloc_lookup_ge(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len,	/* length of extent */
+	int			*stat);	/* success/failure */
+
 int					/* error */
 xfs_alloc_get_rec(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index 08b9ac644c31..65d61b948ead 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -853,6 +853,8 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
 {
 	int newsize, forkoff, retval;
 
+	trace_xfs_attr_sf_addname(args);
+
 	retval = xfs_attr_shortform_lookup(args);
 	if ((args->flags & ATTR_REPLACE) && (retval == ENOATTR)) {
 		return(retval);
@@ -896,6 +898,8 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	int retval, error, committed, forkoff;
 
+	trace_xfs_attr_leaf_addname(args);
+
 	/*
 	 * Read the (only) block in the attribute list in.
 	 */
@@ -920,6 +924,9 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 			xfs_da_brelse(args->trans, bp);
 			return(retval);
 		}
+
+		trace_xfs_attr_leaf_replace(args);
+
 		args->op_flags |= XFS_DA_OP_RENAME;	/* an atomic rename */
 		args->blkno2 = args->blkno;		/* set 2nd entry info*/
 		args->index2 = args->index;
@@ -1090,6 +1097,8 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	int error, committed, forkoff;
 
+	trace_xfs_attr_leaf_removename(args);
+
 	/*
 	 * Remove the attribute.
 	 */
@@ -1223,6 +1232,8 @@ xfs_attr_node_addname(xfs_da_args_t *args)
 	xfs_mount_t *mp;
 	int committed, retval, error;
 
+	trace_xfs_attr_node_addname(args);
+
 	/*
 	 * Fill in bucket of arguments/results/context to carry around.
 	 */
@@ -1249,6 +1260,9 @@ restart:
 	} else if (retval == EEXIST) {
 		if (args->flags & ATTR_CREATE)
 			goto out;
+
+		trace_xfs_attr_node_replace(args);
+
 		args->op_flags |= XFS_DA_OP_RENAME;	/* atomic rename op */
 		args->blkno2 = args->blkno;		/* set 2nd entry info*/
 		args->index2 = args->index;
@@ -1480,6 +1494,8 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	int retval, error, committed, forkoff;
 
+	trace_xfs_attr_node_removename(args);
+
 	/*
 	 * Tie a string around our finger to remind us where we are.
 	 */
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index d25eafd4d28d..76d93dc953e1 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -235,6 +235,8 @@ xfs_attr_shortform_create(xfs_da_args_t *args)
 	xfs_inode_t *dp;
 	xfs_ifork_t *ifp;
 
+	trace_xfs_attr_sf_create(args);
+
 	dp = args->dp;
 	ASSERT(dp != NULL);
 	ifp = dp->i_afp;
@@ -268,6 +270,8 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
 	xfs_inode_t *dp;
 	xfs_ifork_t *ifp;
 
+	trace_xfs_attr_sf_add(args);
+
 	dp = args->dp;
 	mp = dp->i_mount;
 	dp->i_d.di_forkoff = forkoff;
@@ -337,6 +341,8 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
 	xfs_mount_t *mp;
 	xfs_inode_t *dp;
 
+	trace_xfs_attr_sf_remove(args);
+
 	dp = args->dp;
 	mp = dp->i_mount;
 	base = sizeof(xfs_attr_sf_hdr_t);
@@ -405,6 +411,8 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
 	int i;
 	xfs_ifork_t *ifp;
 
+	trace_xfs_attr_sf_lookup(args);
+
 	ifp = args->dp->i_afp;
 	ASSERT(ifp->if_flags & XFS_IFINLINE);
 	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
@@ -476,6 +484,8 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	xfs_ifork_t *ifp;
 
+	trace_xfs_attr_sf_to_leaf(args);
+
 	dp = args->dp;
 	ifp = dp->i_afp;
 	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
@@ -775,6 +785,8 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
 	char *tmpbuffer;
 	int error, i;
 
+	trace_xfs_attr_leaf_to_sf(args);
+
 	dp = args->dp;
 	tmpbuffer = kmem_alloc(XFS_LBSIZE(dp->i_mount), KM_SLEEP);
 	ASSERT(tmpbuffer != NULL);
@@ -848,6 +860,8 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	xfs_dablk_t blkno;
 	int error;
 
+	trace_xfs_attr_leaf_to_node(args);
+
 	dp = args->dp;
 	bp1 = bp2 = NULL;
 	error = xfs_da_grow_inode(args, &blkno);
@@ -911,6 +925,8 @@ xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
 	xfs_dabuf_t *bp;
 	int error;
 
+	trace_xfs_attr_leaf_create(args);
+
 	dp = args->dp;
 	ASSERT(dp != NULL);
 	error = xfs_da_get_buf(args->trans, args->dp, blkno, -1, &bp,
@@ -948,6 +964,8 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	xfs_dablk_t blkno;
 	int error;
 
+	trace_xfs_attr_leaf_split(state->args);
+
 	/*
 	 * Allocate space for a new leaf node.
 	 */
@@ -977,10 +995,13 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	 *
 	 * Insert the "new" entry in the correct block.
 	 */
-	if (state->inleaf)
+	if (state->inleaf) {
+		trace_xfs_attr_leaf_add_old(state->args);
 		error = xfs_attr_leaf_add(oldblk->bp, state->args);
-	else
+	} else {
+		trace_xfs_attr_leaf_add_new(state->args);
 		error = xfs_attr_leaf_add(newblk->bp, state->args);
+	}
 
 	/*
 	 * Update last hashval in each block since we added the name.
@@ -1001,6 +1022,8 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	xfs_attr_leaf_map_t *map;
 	int tablesize, entsize, sum, tmp, i;
 
+	trace_xfs_attr_leaf_add(args);
+
 	leaf = bp->data;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT((args->index >= 0)
@@ -1128,8 +1151,6 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 	       (be32_to_cpu(entry->hashval) <= be32_to_cpu((entry+1)->hashval)));
 
 	/*
-	 * Copy the attribute name and value into the new space.
-	 *
 	 * For "remote" attribute values, simply note that we need to
 	 * allocate space for the "remote" value.  We can't actually
 	 * allocate the extents in this transaction, and we can't decide
@@ -1265,6 +1286,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	args = state->args;
 
+	trace_xfs_attr_leaf_rebalance(args);
+
 	/*
 	 * Check ordering of blocks, reverse if it makes things simpler.
 	 *
@@ -1810,6 +1833,8 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	xfs_mount_t *mp;
 	char *tmpbuffer;
 
+	trace_xfs_attr_leaf_unbalance(state->args);
+
 	/*
 	 * Set up environment.
 	 */
@@ -1919,6 +1944,8 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	int probe, span;
 	xfs_dahash_t hashval;
 
+	trace_xfs_attr_leaf_lookup(args);
+
 	leaf = bp->data;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count)
@@ -2445,6 +2472,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 	char *name;
 #endif /* DEBUG */
 
+	trace_xfs_attr_leaf_clearflag(args);
 	/*
 	 * Set up the operation.
 	 */
@@ -2509,6 +2537,8 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	int error;
 
+	trace_xfs_attr_leaf_setflag(args);
+
 	/*
 	 * Set up the operation.
 	 */
@@ -2565,6 +2595,8 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 	char *name1, *name2;
 #endif /* DEBUG */
 
+	trace_xfs_attr_leaf_flipflags(args);
+
 	/*
 	 * Read the block containing the "old" attr
 	 */
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 3548c6f75593..85e7e327bcd8 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -5124,6 +5124,15 @@ xfs_bunmapi(
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
+
+	if (isrt) {
+		/*
+		 * Synchronize by locking the bitmap inode.
+		 */
+		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+	}
+
 	extno = 0;
 	while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 &&
 	       (nexts == 0 || extno < nexts)) {
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index df7ffb0affe7..5bf3be45f543 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -21,7 +21,6 @@
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/spinlock.h>
-#include <asm/system.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 77c74257c2a3..7f1a6f5b05a6 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -108,6 +108,8 @@ xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
 	int error;
 	xfs_trans_t *tp;
 
+	trace_xfs_da_node_create(args);
+
 	tp = args->trans;
 	error = xfs_da_get_buf(tp, args->dp, blkno, -1, &bp, whichfork);
 	if (error)
@@ -140,6 +142,8 @@ xfs_da_split(xfs_da_state_t *state)
 	xfs_dabuf_t *bp;
 	int max, action, error, i;
 
+	trace_xfs_da_split(state->args);
+
 	/*
 	 * Walk back up the tree splitting/inserting/adjusting as necessary.
 	 * If we need to insert and there isn't room, split the node, then
@@ -178,10 +182,12 @@ xfs_da_split(xfs_da_state_t *state)
 			state->extravalid = 1;
 			if (state->inleaf) {
 				state->extraafter = 0;	/* before newblk */
+				trace_xfs_attr_leaf_split_before(state->args);
 				error = xfs_attr_leaf_split(state, oldblk,
 							    &state->extrablk);
 			} else {
 				state->extraafter = 1;	/* after newblk */
+				trace_xfs_attr_leaf_split_after(state->args);
 				error = xfs_attr_leaf_split(state, newblk,
 							    &state->extrablk);
 			}
@@ -300,6 +306,8 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	xfs_mount_t *mp;
 	xfs_dir2_leaf_t *leaf;
 
+	trace_xfs_da_root_split(state->args);
+
 	/*
 	 * Copy the existing (incorrect) block from the root node position
 	 * to a free space somewhere.
@@ -380,6 +388,8 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	int newcount, error;
 	int useextra;
 
+	trace_xfs_da_node_split(state->args);
+
 	node = oldblk->bp->data;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 
@@ -466,6 +476,8 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	int count, tmp;
 	xfs_trans_t *tp;
 
+	trace_xfs_da_node_rebalance(state->args);
+
 	node1 = blk1->bp->data;
 	node2 = blk2->bp->data;
 	/*
@@ -574,6 +586,8 @@ xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	xfs_da_node_entry_t *btree;
 	int tmp;
 
+	trace_xfs_da_node_add(state->args);
+
 	node = oldblk->bp->data;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	ASSERT((oldblk->index >= 0) && (oldblk->index <= be16_to_cpu(node->hdr.count)));
@@ -619,6 +633,8 @@ xfs_da_join(xfs_da_state_t *state)
 	xfs_da_state_blk_t *drop_blk, *save_blk;
 	int action, error;
 
+	trace_xfs_da_join(state->args);
+
 	action = 0;
 	drop_blk = &state->path.blk[ state->path.active-1 ];
 	save_blk = &state->altpath.blk[ state->path.active-1 ];
@@ -723,6 +739,8 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
 	xfs_dabuf_t *bp;
 	int error;
 
+	trace_xfs_da_root_join(state->args);
+
 	args = state->args;
 	ASSERT(args != NULL);
 	ASSERT(root_blk->magic == XFS_DA_NODE_MAGIC);
@@ -941,6 +959,8 @@ xfs_da_node_remove(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk)
 	xfs_da_node_entry_t *btree;
 	int tmp;
 
+	trace_xfs_da_node_remove(state->args);
+
 	node = drop_blk->bp->data;
 	ASSERT(drop_blk->index < be16_to_cpu(node->hdr.count));
 	ASSERT(drop_blk->index >= 0);
@@ -984,6 +1004,8 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	int tmp;
 	xfs_trans_t *tp;
 
+	trace_xfs_da_node_unbalance(state->args);
+
 	drop_node = drop_blk->bp->data;
 	save_node = save_blk->bp->data;
 	ASSERT(drop_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
@@ -1230,6 +1252,7 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 		/*
 		 * Link new block in before existing block.
 		 */
+		trace_xfs_da_link_before(args);
 		new_info->forw = cpu_to_be32(old_blk->blkno);
 		new_info->back = old_info->back;
 		if (old_info->back) {
@@ -1251,6 +1274,7 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 		/*
 		 * Link new block in after existing block.
 		 */
+		trace_xfs_da_link_after(args);
 		new_info->forw = old_info->forw;
 		new_info->back = cpu_to_be32(old_blk->blkno);
 		if (old_info->forw) {
@@ -1348,6 +1372,7 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	 * Unlink the leaf block from the doubly linked chain of leaves.
 	 */
 	if (be32_to_cpu(save_info->back) == drop_blk->blkno) {
+		trace_xfs_da_unlink_back(args);
 		save_info->back = drop_info->back;
 		if (drop_info->back) {
 			error = xfs_da_read_buf(args->trans, args->dp,
@@ -1365,6 +1390,7 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 			xfs_da_buf_done(bp);
 		}
 	} else {
+		trace_xfs_da_unlink_forward(args);
 		save_info->forw = drop_info->forw;
 		if (drop_info->forw) {
 			error = xfs_da_read_buf(args->trans, args->dp,
@@ -1652,6 +1678,8 @@ xfs_da_grow_inode(
 	int			count;
 	int			error;
 
+	trace_xfs_da_grow_inode(args);
+
 	if (args->whichfork == XFS_DATA_FORK) {
 		bno = args->dp->i_mount->m_dirleafblk;
 		count = args->dp->i_mount->m_dirblkfsbs;
@@ -1690,6 +1718,8 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	xfs_dir2_leaf_t *dead_leaf2;
 	xfs_dahash_t dead_hash;
 
+	trace_xfs_da_swap_lastblock(args);
+
 	dead_buf = *dead_bufp;
 	dead_blkno = *dead_blknop;
 	tp = args->trans;
@@ -1878,6 +1908,8 @@ xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 	xfs_trans_t *tp;
 	xfs_mount_t *mp;
 
+	trace_xfs_da_shrink_inode(args);
+
 	dp = args->dp;
 	w = args->whichfork;
 	tp = args->trans;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 286a051f12cf..1ad3a4b8ca40 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -37,9 +37,9 @@ STATIC int
 xfs_trim_extents(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
-	xfs_fsblock_t		start,
-	xfs_fsblock_t		end,
-	xfs_fsblock_t		minlen,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_daddr_t		minlen,
 	__uint64_t		*blocks_trimmed)
 {
 	struct block_device	*bdev = mp->m_ddev_targp->bt_bdev;
@@ -67,7 +67,7 @@ xfs_trim_extents(
 	/*
 	 * Look up the longest btree in the AGF and start with it.
 	 */
-	error = xfs_alloc_lookup_le(cur, 0,
+	error = xfs_alloc_lookup_ge(cur, 0,
 			    be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest), &i);
 	if (error)
 		goto out_del_cursor;
@@ -77,8 +77,10 @@ xfs_trim_extents(
 	 * enough to be worth discarding.
 	 */
 	while (i) {
-		xfs_agblock_t fbno;
-		xfs_extlen_t flen;
+		xfs_agblock_t	fbno;
+		xfs_extlen_t	flen;
+		xfs_daddr_t	dbno;
+		xfs_extlen_t	dlen;
 
 		error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
 		if (error)
@@ -87,9 +89,17 @@ xfs_trim_extents(
 		ASSERT(flen <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest));
 
 		/*
+		 * use daddr format for all range/len calculations as that is
+		 * the format the range/len variables are supplied in by
+		 * userspace.
+		 */
+		dbno = XFS_AGB_TO_DADDR(mp, agno, fbno);
+		dlen = XFS_FSB_TO_BB(mp, flen);
+
+		/*
 		 * Too small?  Give up.
 		 */
-		if (flen < minlen) {
+		if (dlen < minlen) {
 			trace_xfs_discard_toosmall(mp, agno, fbno, flen);
 			goto out_del_cursor;
 		}
@@ -99,8 +109,7 @@ xfs_trim_extents(
 		 * supposed to discard skip it.  Do not bother to trim
 		 * down partially overlapping ranges for now.
 		 */
-		if (XFS_AGB_TO_FSB(mp, agno, fbno) + flen < start ||
-		    XFS_AGB_TO_FSB(mp, agno, fbno) > end) {
+		if (dbno + dlen < start || dbno > end) {
 			trace_xfs_discard_exclude(mp, agno, fbno, flen);
 			goto next_extent;
 		}
@@ -115,10 +124,7 @@ xfs_trim_extents(
 		}
 
 		trace_xfs_discard_extent(mp, agno, fbno, flen);
-		error = -blkdev_issue_discard(bdev,
-				XFS_AGB_TO_DADDR(mp, agno, fbno),
-				XFS_FSB_TO_BB(mp, flen),
-				GFP_NOFS, 0);
+		error = -blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS, 0);
 		if (error)
 			goto out_del_cursor;
 		*blocks_trimmed += flen;
@@ -137,6 +143,15 @@ out_put_perag:
 	return error;
 }
 
+/*
+ * trim a range of the filesystem.
+ *
+ * Note: the parameters passed from userspace are byte ranges into the
+ * filesystem which does not match to the format we use for filesystem block
+ * addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
+ * is a linear address range. Hence we need to use DADDR based conversions and
+ * comparisons for determining the correct offset and regions to trim.
+ */
 int
 xfs_ioc_trim(
 	struct xfs_mount		*mp,
@@ -145,7 +160,7 @@ xfs_ioc_trim(
 	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
 	unsigned int		granularity = q->limits.discard_granularity;
 	struct fstrim_range	range;
-	xfs_fsblock_t		start, end, minlen;
+	xfs_daddr_t		start, end, minlen;
 	xfs_agnumber_t		start_agno, end_agno, agno;
 	__uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;
@@ -159,22 +174,22 @@ xfs_ioc_trim(
 
 	/*
 	 * Truncating down the len isn't actually quite correct, but using
-	 * XFS_B_TO_FSB would mean we trivially get overflows for values
+	 * BBTOB would mean we trivially get overflows for values
 	 * of ULLONG_MAX or slightly lower.  And ULLONG_MAX is the default
 	 * used by the fstrim application.  In the end it really doesn't
 	 * matter as trimming blocks is an advisory interface.
 	 */
-	start = XFS_B_TO_FSBT(mp, range.start);
-	end = start + XFS_B_TO_FSBT(mp, range.len) - 1;
-	minlen = XFS_B_TO_FSB(mp, max_t(u64, granularity, range.minlen));
+	start = BTOBB(range.start);
+	end = start + BTOBBT(range.len) - 1;
+	minlen = BTOBB(max_t(u64, granularity, range.minlen));
 
-	if (start >= mp->m_sb.sb_dblocks)
+	if (XFS_BB_TO_FSB(mp, start) >= mp->m_sb.sb_dblocks)
 		return -XFS_ERROR(EINVAL);
-	if (end > mp->m_sb.sb_dblocks - 1)
-		end = mp->m_sb.sb_dblocks - 1;
+	if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
+		end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1;
 
-	start_agno = XFS_FSB_TO_AGNO(mp, start);
-	end_agno = XFS_FSB_TO_AGNO(mp, end);
+	start_agno = xfs_daddr_to_agno(mp, start);
+	end_agno = xfs_daddr_to_agno(mp, end);
 
 	for (agno = start_agno; agno <= end_agno; agno++) {
 		error = -xfs_trim_extents(mp, agno, start, end, minlen,
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 4be16a0cbe5a..1155208fa830 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1065,7 +1065,7 @@ out:
 	return -ENOMEM;
 }
 
-void __exit
+void
 xfs_qm_exit(void)
 {
 	kmem_zone_destroy(xfs_qm_dqtrxzone);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index a98cb4524e6c..bcc6c249b2c7 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -289,7 +289,7 @@ xfs_iget_cache_hit(
 	if (lock_flags != 0)
 		xfs_ilock(ip, lock_flags);
 
-	xfs_iflags_clear(ip, XFS_ISTALE);
+	xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
 	XFS_STATS_INC(xs_ig_found);
 
 	return 0;
@@ -314,6 +314,7 @@ xfs_iget_cache_miss(
 	struct xfs_inode	*ip;
 	int			error;
 	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);
+	int			iflags;
 
 	ip = xfs_inode_alloc(mp, ino);
 	if (!ip)
@@ -358,8 +359,11 @@ xfs_iget_cache_miss(
 	 * memory barrier that ensures this detection works correctly at lookup
 	 * time.
 	 */
+	iflags = XFS_INEW;
+	if (flags & XFS_IGET_DONTCACHE)
+		iflags |= XFS_IDONTCACHE;
 	ip->i_udquot = ip->i_gdquot = NULL;
-	xfs_iflags_set(ip, XFS_INEW);
+	xfs_iflags_set(ip, iflags);
 
 	/* insert the new inode */
 	spin_lock(&pag->pag_ici_lock);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index f123dbe6d42a..7fee3387e1c8 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -387,10 +387,11 @@ xfs_set_projid(struct xfs_inode *ip,
 #define XFS_IFLOCK		(1 << __XFS_IFLOCK_BIT)
 #define __XFS_IPINNED_BIT	8	 /* wakeup key for zero pin count */
 #define XFS_IPINNED		(1 << __XFS_IPINNED_BIT)
+#define XFS_IDONTCACHE		(1 << 9) /* don't cache the inode long term */
 
 /*
  * Per-lifetime flags need to be reset when re-using a reclaimable inode during
- * inode lookup. Thi prevents unintended behaviour on the new inode from
+ * inode lookup. This prevents unintended behaviour on the new inode from
  * ocurring.
  */
 #define XFS_IRECLAIM_RESET_FLAGS	\
@@ -553,6 +554,7 @@ do { \
  */
 #define XFS_IGET_CREATE		0x1
 #define XFS_IGET_UNTRUSTED	0x2
+#define XFS_IGET_DONTCACHE	0x4
 
 int		xfs_inotobp(struct xfs_mount *, struct xfs_trans *,
 			    xfs_ino_t, struct xfs_dinode **,
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index f588320dc4b9..91f8ff547ab3 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -209,6 +209,7 @@ xfs_open_by_handle(
 	struct file		*filp;
 	struct inode		*inode;
 	struct dentry		*dentry;
+	fmode_t			fmode;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -XFS_ERROR(EPERM);
@@ -228,26 +229,21 @@ xfs_open_by_handle(
 	hreq->oflags |= O_LARGEFILE;
 #endif
 
-	/* Put open permission in namei format. */
 	permflag = hreq->oflags;
-	if ((permflag+1) & O_ACCMODE)
-		permflag++;
-	if (permflag & O_TRUNC)
-		permflag |= 2;
-
+	fmode = OPEN_FMODE(permflag);
 	if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
-	    (permflag & FMODE_WRITE) && IS_APPEND(inode)) {
+	    (fmode & FMODE_WRITE) && IS_APPEND(inode)) {
 		error = -XFS_ERROR(EPERM);
 		goto out_dput;
 	}
 
-	if ((permflag & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
+	if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
 		error = -XFS_ERROR(EACCES);
 		goto out_dput;
 	}
 
 	/* Can't write directories. */
-	if (S_ISDIR(inode->i_mode) && (permflag & FMODE_WRITE)) {
+	if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) {
 		error = -XFS_ERROR(EISDIR);
 		goto out_dput;
 	}
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 9720c54bbed0..acc2bf264dab 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -75,7 +75,8 @@ xfs_bulkstat_one_int(
 		return XFS_ERROR(ENOMEM);
 
 	error = xfs_iget(mp, NULL, ino,
-			 XFS_IGET_UNTRUSTED, XFS_ILOCK_SHARED, &ip);
+			 (XFS_IGET_DONTCACHE | XFS_IGET_UNTRUSTED),
+			 XFS_ILOCK_SHARED, &ip);
 	if (error) {
 		*stat = BULKSTAT_RV_NOTHING;
 		goto out_free;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 98a9cb5ffd17..6db1fef38bff 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -726,8 +726,9 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 				.lv_iovecp = &reg,
 			};
 
-			/* remove inited flag */
+			/* remove inited flag, and account for space used */
 			tic->t_flags = 0;
+			tic->t_curr_res -= sizeof(magic);
 			error = xlog_write(log, &vec, tic, &lsn,
 					   NULL, XLOG_UNMOUNT_TRANS);
 			/*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 7c75c7374d5a..8ecad5bad66c 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3161,37 +3161,26 @@ xlog_recover_process_iunlinks(
 			 */
 			continue;
 		}
+		/*
+		 * Unlock the buffer so that it can be acquired in the normal
+		 * course of the transaction to truncate and free each inode.
+		 * Because we are not racing with anyone else here for the AGI
+		 * buffer, we don't even need to hold it locked to read the
+		 * initial unlinked bucket entries out of the buffer. We keep
+		 * buffer reference though, so that it stays pinned in memory
+		 * while we need the buffer.
+		 */
 		agi = XFS_BUF_TO_AGI(agibp);
+		xfs_buf_unlock(agibp);
 
 		for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) {
 			agino = be32_to_cpu(agi->agi_unlinked[bucket]);
 			while (agino != NULLAGINO) {
-				/*
-				 * Release the agi buffer so that it can
-				 * be acquired in the normal course of the
-				 * transaction to truncate and free the inode.
-				 */
-				xfs_buf_relse(agibp);
-
 				agino = xlog_recover_process_one_iunlink(mp,
 							agno, agino, bucket);
-
-				/*
-				 * Reacquire the agibuffer and continue around
-				 * the loop. This should never fail as we know
-				 * the buffer was good earlier on.
-				 */
-				error = xfs_read_agi(mp, NULL, agno, &agibp);
-				ASSERT(error == 0);
-				agi = XFS_BUF_TO_AGI(agibp);
 			}
 		}
-
-		/*
-		 * Release the buffer for the current agi so we can
-		 * go on to the next one.
-		 */
-		xfs_buf_relse(agibp);
+		xfs_buf_rele(agibp);
 	}
 
 	mp->m_dmevmask = mp_dmevmask;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 87323f1ded64..ca4f31534a0a 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -183,6 +183,7 @@ error_cancel:
 		oblocks = map.br_startoff + map.br_blockcount;
 	}
 	return 0;
+
 error:
 	return error;
 }
@@ -2139,11 +2140,9 @@ xfs_rtfree_extent(
 	xfs_buf_t	*sumbp;		/* summary file block buffer */
 
 	mp = tp->t_mountp;
-	/*
-	 * Synchronize by locking the bitmap inode.
-	 */
-	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+
+	ASSERT(mp->m_rbmip->i_itemp != NULL);
+	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
 
 #if defined(__KERNEL__) && defined(DEBUG)
 	/*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 912442cf0f82..dab9a5f6dfd6 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -950,6 +950,22 @@ xfs_fs_evict_inode(
 	xfs_inactive(ip);
 }
 
+/*
+ * We do an unlocked check for XFS_IDONTCACHE here because we are already
+ * serialised against cache hits here via the inode->i_lock and igrab() in
+ * xfs_iget_cache_hit(). Hence a lookup that might clear this flag will not be
+ * racing with us, and it avoids needing to grab a spinlock here for every inode
+ * we drop the final reference on.
+ */
+STATIC int
+xfs_fs_drop_inode(
+	struct inode		*inode)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+
+	return generic_drop_inode(inode) || (ip->i_flags & XFS_IDONTCACHE);
+}
+
 STATIC void
 xfs_free_fsname(
 	struct xfs_mount	*mp)
@@ -1433,6 +1449,7 @@ static const struct super_operations xfs_super_operations = {
 	.destroy_inode		= xfs_fs_destroy_inode,
 	.dirty_inode		= xfs_fs_dirty_inode,
 	.evict_inode		= xfs_fs_evict_inode,
+	.drop_inode		= xfs_fs_drop_inode,
 	.put_super		= xfs_fs_put_super,
 	.sync_fs		= xfs_fs_sync_fs,
 	.freeze_fs		= xfs_fs_freeze,
@@ -1606,12 +1623,28 @@ xfs_init_workqueues(void)
 	xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_NON_REENTRANT, 0);
 	if (!xfs_syncd_wq)
 		return -ENOMEM;
+
+	/*
+	 * The allocation workqueue can be used in memory reclaim situations
+	 * (writepage path), and parallelism is only limited by the number of
+	 * AGs in all the filesystems mounted. Hence use the default large
+	 * max_active value for this workqueue.
+	 */
+	xfs_alloc_wq = alloc_workqueue("xfsalloc", WQ_MEM_RECLAIM, 0);
+	if (!xfs_alloc_wq)
+		goto out_destroy_syncd;
+
 	return 0;
+
+out_destroy_syncd:
+	destroy_workqueue(xfs_syncd_wq);
+	return -ENOMEM;
 }
 
 STATIC void
 xfs_destroy_workqueues(void)
 {
+	destroy_workqueue(xfs_alloc_wq);
 	destroy_workqueue(xfs_syncd_wq);
 }
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 75eb54af4d58..06838c42b2a0 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -627,16 +627,19 @@ DECLARE_EVENT_CLASS(xfs_namespace_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_ino_t, dp_ino)
+		__field(int, namelen)
 		__dynamic_array(char, name, name->len)
 	),
 	TP_fast_assign(
 		__entry->dev = VFS_I(dp)->i_sb->s_dev;
 		__entry->dp_ino = dp->i_ino;
+		__entry->namelen = name->len;
 		memcpy(__get_str(name), name->name, name->len);
 	),
-	TP_printk("dev %d:%d dp ino 0x%llx name %s",
+	TP_printk("dev %d:%d dp ino 0x%llx name %.*s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dp_ino,
+		  __entry->namelen,
 		  __get_str(name))
 )
 
@@ -658,6 +661,8 @@ TRACE_EVENT(xfs_rename,
 		__field(dev_t, dev)
 		__field(xfs_ino_t, src_dp_ino)
 		__field(xfs_ino_t, target_dp_ino)
+		__field(int, src_namelen)
+		__field(int, target_namelen)
 		__dynamic_array(char, src_name, src_name->len)
 		__dynamic_array(char, target_name, target_name->len)
 	),
@@ -665,15 +670,20 @@ TRACE_EVENT(xfs_rename,
 		__entry->dev = VFS_I(src_dp)->i_sb->s_dev;
 		__entry->src_dp_ino = src_dp->i_ino;
 		__entry->target_dp_ino = target_dp->i_ino;
+		__entry->src_namelen = src_name->len;
+		__entry->target_namelen = target_name->len;
 		memcpy(__get_str(src_name), src_name->name, src_name->len);
-		memcpy(__get_str(target_name), target_name->name, target_name->len);
+		memcpy(__get_str(target_name), target_name->name,
+			target_name->len);
 	),
 	TP_printk("dev %d:%d src dp ino 0x%llx target dp ino 0x%llx"
-		  " src name %s target name %s",
+		  " src name %.*s target name %.*s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->src_dp_ino,
 		  __entry->target_dp_ino,
+		  __entry->src_namelen,
 		  __get_str(src_name),
+		  __entry->target_namelen,
 		  __get_str(target_name))
 )
 
@@ -1408,7 +1418,7 @@ DEFINE_ALLOC_EVENT(xfs_alloc_vextent_noagbp);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_loopfailed);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_allfailed);
 
-DECLARE_EVENT_CLASS(xfs_dir2_class,
+DECLARE_EVENT_CLASS(xfs_da_class,
 	TP_PROTO(struct xfs_da_args *args),
 	TP_ARGS(args),
 	TP_STRUCT__entry(
@@ -1443,7 +1453,7 @@ DECLARE_EVENT_CLASS(xfs_dir2_class,
 )
 
 #define DEFINE_DIR2_EVENT(name) \
-DEFINE_EVENT(xfs_dir2_class, name, \
+DEFINE_EVENT(xfs_da_class, name, \
 	TP_PROTO(struct xfs_da_args *args), \
 	TP_ARGS(args))
 DEFINE_DIR2_EVENT(xfs_dir2_sf_addname);
@@ -1472,6 +1482,64 @@ DEFINE_DIR2_EVENT(xfs_dir2_node_replace);
 DEFINE_DIR2_EVENT(xfs_dir2_node_removename);
 DEFINE_DIR2_EVENT(xfs_dir2_node_to_leaf);
 
+#define DEFINE_ATTR_EVENT(name) \
+DEFINE_EVENT(xfs_da_class, name, \
+	TP_PROTO(struct xfs_da_args *args), \
+	TP_ARGS(args))
+DEFINE_ATTR_EVENT(xfs_attr_sf_add);
+DEFINE_ATTR_EVENT(xfs_attr_sf_addname);
+DEFINE_ATTR_EVENT(xfs_attr_sf_create);
+DEFINE_ATTR_EVENT(xfs_attr_sf_lookup);
+DEFINE_ATTR_EVENT(xfs_attr_sf_remove);
+DEFINE_ATTR_EVENT(xfs_attr_sf_removename);
+DEFINE_ATTR_EVENT(xfs_attr_sf_to_leaf);
+
+DEFINE_ATTR_EVENT(xfs_attr_leaf_add);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_add_old);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_add_new);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_addname);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_create);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_lookup);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_replace);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_removename);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_split);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_split_before);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_split_after);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_clearflag);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_setflag);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_flipflags);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_to_sf);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_to_node);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_rebalance);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_unbalance);
+
+DEFINE_ATTR_EVENT(xfs_attr_node_addname);
+DEFINE_ATTR_EVENT(xfs_attr_node_lookup);
+DEFINE_ATTR_EVENT(xfs_attr_node_replace);
+DEFINE_ATTR_EVENT(xfs_attr_node_removename);
+
+#define DEFINE_DA_EVENT(name) \
+DEFINE_EVENT(xfs_da_class, name, \
+	TP_PROTO(struct xfs_da_args *args), \
+	TP_ARGS(args))
+DEFINE_DA_EVENT(xfs_da_split);
+DEFINE_DA_EVENT(xfs_da_join);
+DEFINE_DA_EVENT(xfs_da_link_before);
+DEFINE_DA_EVENT(xfs_da_link_after);
+DEFINE_DA_EVENT(xfs_da_unlink_back);
+DEFINE_DA_EVENT(xfs_da_unlink_forward);
+DEFINE_DA_EVENT(xfs_da_root_split);
+DEFINE_DA_EVENT(xfs_da_root_join);
+DEFINE_DA_EVENT(xfs_da_node_add);
+DEFINE_DA_EVENT(xfs_da_node_create);
+DEFINE_DA_EVENT(xfs_da_node_split);
+DEFINE_DA_EVENT(xfs_da_node_remove);
+DEFINE_DA_EVENT(xfs_da_node_rebalance);
+DEFINE_DA_EVENT(xfs_da_node_unbalance);
+DEFINE_DA_EVENT(xfs_da_swap_lastblock);
+DEFINE_DA_EVENT(xfs_da_grow_inode);
+DEFINE_DA_EVENT(xfs_da_shrink_inode);
+
 DECLARE_EVENT_CLASS(xfs_dir2_space_class,
 	TP_PROTO(struct xfs_da_args *args, int idx),
 	TP_ARGS(args, idx),
diff --git a/drivers/acpi/acpica/acconfig.h b/include/acpi/acconfig.h
index 1f30af613e87..03f14856bd09 100644
--- a/drivers/acpi/acpica/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -85,6 +85,23 @@
  */
 #define ACPI_CHECKSUM_ABORT             FALSE
 
+/*
+ * Generate a version of ACPICA that only supports "reduced hardware"
+ * platforms (as defined in ACPI 5.0). Set to TRUE to generate a specialized
+ * version of ACPICA that ONLY supports the ACPI 5.0 "reduced hardware"
+ * model. In other words, no ACPI hardware is supported.
+ *
+ * If TRUE, this means no support for the following:
+ *      PM Event and Control registers
+ *      SCI interrupt (and handler)
+ *      Fixed Events
+ *      General Purpose Events (GPEs)
+ *      Global Lock
+ *      ACPI PM timer
+ *      FACS table (Waking vectors and Global Lock)
+ */
+#define ACPI_REDUCED_HARDWARE           FALSE
+
 /******************************************************************************
  *
  * Subsystem Constants
@@ -93,7 +110,7 @@
 
 /* Version of ACPI supported */
 
-#define ACPI_CA_SUPPORT_LEVEL           3
+#define ACPI_CA_SUPPORT_LEVEL           5
 
 /* Maximum count for a semaphore object */
 
diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index 5b6c391efc8e..92d6e1d701ff 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -57,6 +57,7 @@
 #define ACPI_SUCCESS(a)                 (!(a))
 #define ACPI_FAILURE(a)                 (a)
 
+#define ACPI_SKIP(a)                    (a == AE_CTRL_SKIP)
 #define AE_OK                           (acpi_status) 0x0000
 
 /*
@@ -89,8 +90,9 @@
 #define AE_SAME_HANDLER                 (acpi_status) (0x0019 | AE_CODE_ENVIRONMENTAL)
 #define AE_NO_HANDLER                   (acpi_status) (0x001A | AE_CODE_ENVIRONMENTAL)
 #define AE_OWNER_ID_LIMIT               (acpi_status) (0x001B | AE_CODE_ENVIRONMENTAL)
+#define AE_NOT_CONFIGURED               (acpi_status) (0x001C | AE_CODE_ENVIRONMENTAL)
 
-#define AE_CODE_ENV_MAX                 0x001B
+#define AE_CODE_ENV_MAX                 0x001C
 
 /*
  * Programmer exceptions
@@ -213,7 +215,8 @@ char const *acpi_gbl_exception_names_env[] = {
 	"AE_ABORT_METHOD",
 	"AE_SAME_HANDLER",
 	"AE_NO_HANDLER",
-	"AE_OWNER_ID_LIMIT"
+	"AE_OWNER_ID_LIMIT",
+	"AE_NOT_CONFIGURED"
 };
 
 char const *acpi_gbl_exception_names_pgm[] = {
diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index 5b5af0d30a97..38f508816e4a 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -46,6 +46,7 @@
 
 /* Method names - these methods can appear anywhere in the namespace */
 
+#define METHOD_NAME__SB_        "_SB_"
 #define METHOD_NAME__HID        "_HID"
 #define METHOD_NAME__CID        "_CID"
 #define METHOD_NAME__UID        "_UID"
@@ -64,11 +65,11 @@
 
 /* Method names - these methods must appear at the namespace root */
 
-#define METHOD_NAME__BFS        "\\_BFS"
-#define METHOD_NAME__GTS        "\\_GTS"
-#define METHOD_NAME__PTS        "\\_PTS"
-#define METHOD_NAME__SST        "\\_SI._SST"
-#define METHOD_NAME__WAK        "\\_WAK"
+#define METHOD_PATHNAME__BFS    "\\_BFS"
+#define METHOD_PATHNAME__GTS    "\\_GTS"
+#define METHOD_PATHNAME__PTS    "\\_PTS"
+#define METHOD_PATHNAME__SST    "\\_SI._SST"
+#define METHOD_PATHNAME__WAK    "\\_WAK"
 
 /* Definitions of the predefined namespace names  */
 
@@ -79,6 +80,5 @@
 #define ACPI_PREFIX_LOWER       (u32) 0x69706361	/* "acpi" */
 
 #define ACPI_NS_ROOT_PATH       "\\"
-#define ACPI_NS_SYSTEM_BUS      "_SB_"
 
 #endif				/* __ACNAMES_H__  */
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 6cd5b6403a7b..f1c8ca60e824 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -323,6 +323,8 @@ int acpi_bus_set_power(acpi_handle handle, int state);
 int acpi_bus_update_power(acpi_handle handle, int *state_p);
 bool acpi_bus_power_manageable(acpi_handle handle);
 bool acpi_bus_can_wakeup(acpi_handle handle);
+int acpi_power_resource_register_device(struct device *dev, acpi_handle handle);
+void acpi_power_resource_unregister_device(struct device *dev, acpi_handle handle);
 #ifdef CONFIG_ACPI_PROC_EVENT
 int acpi_bus_generate_proc_event(struct acpi_device *device, u8 type, int data);
 int acpi_bus_generate_proc_event4(const char *class, const char *bid, u8 type, int data);
@@ -392,8 +394,13 @@ static inline int acpi_pm_device_sleep_state(struct device *d, int *p)
 #endif
 
 #ifdef CONFIG_PM_SLEEP
+int acpi_pm_device_run_wake(struct device *, bool);
 int acpi_pm_device_sleep_wake(struct device *, bool);
 #else
+static inline int acpi_pm_device_run_wake(struct device *dev, bool enable)
+{
+	return -ENODEV;
+}
 static inline int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 {
 	return -ENODEV;
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 7c9aebe8a7aa..21a5548c6686 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -95,6 +95,11 @@ acpi_status
 acpi_os_table_override(struct acpi_table_header *existing_table,
 		       struct acpi_table_header **new_table);
 
+acpi_status
+acpi_os_physical_table_override(struct acpi_table_header *existing_table,
+				acpi_physical_address * new_address,
+				u32 *new_table_length);
+
 /*
  * Spinlock primitives
  */
@@ -217,14 +222,10 @@ acpi_status acpi_os_write_port(acpi_io_address address, u32 value, u32 width);
  * Platform and hardware-independent physical memory interfaces
  */
 acpi_status
-acpi_os_read_memory(acpi_physical_address address, u32 * value, u32 width);
-acpi_status
-acpi_os_read_memory64(acpi_physical_address address, u64 *value, u32 width);
+acpi_os_read_memory(acpi_physical_address address, u64 *value, u32 width);
 
 acpi_status
-acpi_os_write_memory(acpi_physical_address address, u32 value, u32 width);
-acpi_status
-acpi_os_write_memory64(acpi_physical_address address, u64 value, u32 width);
+acpi_os_write_memory(acpi_physical_address address, u64 value, u32 width);
 
 /*
  * Platform and hardware-independent PCI configuration space access
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index a28da35ba45e..982110134672 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -47,8 +47,9 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20120111
+#define ACPI_CA_VERSION                 0x20120320
 
+#include "acconfig.h"
 #include "actypes.h"
 #include "actbl.h"
 
@@ -71,6 +72,33 @@ extern u8 acpi_gbl_copy_dsdt_locally;
 extern u8 acpi_gbl_truncate_io_addresses;
 extern u8 acpi_gbl_disable_auto_repair;
 
+/*
+ * Hardware-reduced prototypes. All interfaces that use these macros will
+ * be configured out of the ACPICA build if the ACPI_REDUCED_HARDWARE flag
+ * is set to TRUE.
+ */
+#if (!ACPI_REDUCED_HARDWARE)
+#define ACPI_HW_DEPENDENT_RETURN_STATUS(prototype) \
+	prototype;
+
+#define ACPI_HW_DEPENDENT_RETURN_OK(prototype) \
+	prototype;
+
+#define ACPI_HW_DEPENDENT_RETURN_VOID(prototype) \
+	prototype;
+
+#else
+#define ACPI_HW_DEPENDENT_RETURN_STATUS(prototype) \
+	static ACPI_INLINE prototype {return(AE_NOT_CONFIGURED);}
+
+#define ACPI_HW_DEPENDENT_RETURN_OK(prototype) \
+	static ACPI_INLINE prototype {return(AE_OK);}
+
+#define ACPI_HW_DEPENDENT_RETURN_VOID(prototype) \
+	static ACPI_INLINE prototype {}
+
+#endif				/* !ACPI_REDUCED_HARDWARE */
+
 extern u32 acpi_current_gpe_count;
 extern struct acpi_table_fadt acpi_gbl_FADT;
 extern u8 acpi_gbl_system_awake_and_running;
@@ -96,9 +124,8 @@ acpi_status acpi_terminate(void);
 acpi_status acpi_subsystem_status(void);
 #endif
 
-acpi_status acpi_enable(void);
-
-acpi_status acpi_disable(void);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable(void))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable(void))
 
 #ifdef ACPI_FUTURE_USAGE
 acpi_status acpi_get_system_info(struct acpi_buffer *ret_buffer);
@@ -235,17 +262,34 @@ acpi_status acpi_get_parent(acpi_handle object, acpi_handle * out_handle);
 acpi_status
 acpi_install_initialization_handler(acpi_init_handler handler, u32 function);
 
-acpi_status
-acpi_install_global_event_handler(ACPI_GBL_EVENT_HANDLER handler,
-				 void *context);
-
-acpi_status
-acpi_install_fixed_event_handler(u32 acpi_event,
-				 acpi_event_handler handler, void *context);
-
-acpi_status
-acpi_remove_fixed_event_handler(u32 acpi_event, acpi_event_handler handler);
-
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_install_global_event_handler
+				(ACPI_GBL_EVENT_HANDLER handler, void *context))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_install_fixed_event_handler(u32
+								  acpi_event,
+								  acpi_event_handler
+								  handler,
+								  void
+								  *context))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_remove_fixed_event_handler(u32 acpi_event,
+								 acpi_event_handler
+								 handler))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_install_gpe_handler(acpi_handle
+							  gpe_device,
+							  u32 gpe_number,
+							  u32 type,
+							  acpi_gpe_handler
+							  address,
+							  void *context))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_remove_gpe_handler(acpi_handle gpe_device,
+							 u32 gpe_number,
+							 acpi_gpe_handler
+							 address))
 acpi_status
 acpi_install_notify_handler(acpi_handle device,
 			    u32 handler_type,
@@ -266,15 +310,6 @@ acpi_remove_address_space_handler(acpi_handle device,
 				  acpi_adr_space_type space_id,
 				  acpi_adr_space_handler handler);
 
-acpi_status
-acpi_install_gpe_handler(acpi_handle gpe_device,
-			 u32 gpe_number,
-			 u32 type, acpi_gpe_handler address, void *context);
-
-acpi_status
-acpi_remove_gpe_handler(acpi_handle gpe_device,
-			u32 gpe_number, acpi_gpe_handler address);
-
 #ifdef ACPI_FUTURE_USAGE
 acpi_status acpi_install_exception_handler(acpi_exception_handler handler);
 #endif
@@ -284,9 +319,11 @@ acpi_status acpi_install_interface_handler(acpi_interface_handler handler);
 /*
  * Global Lock interfaces
  */
-acpi_status acpi_acquire_global_lock(u16 timeout, u32 * handle);
-
-acpi_status acpi_release_global_lock(u32 handle);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_acquire_global_lock(u16 timeout,
+							 u32 *handle))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_release_global_lock(u32 handle))
 
 /*
  * Interfaces to AML mutex objects
@@ -299,47 +336,75 @@ acpi_status acpi_release_mutex(acpi_handle handle, acpi_string pathname);
 /*
  * Fixed Event interfaces
  */
-acpi_status acpi_enable_event(u32 event, u32 flags);
-
-acpi_status acpi_disable_event(u32 event, u32 flags);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_enable_event(u32 event, u32 flags))
 
-acpi_status acpi_clear_event(u32 event);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_disable_event(u32 event, u32 flags))
 
-acpi_status acpi_get_event_status(u32 event, acpi_event_status * event_status);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_clear_event(u32 event))
 
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_get_event_status(u32 event,
+						      acpi_event_status
+						      *event_status))
 /*
  * General Purpose Event (GPE) Interfaces
  */
-acpi_status acpi_enable_gpe(acpi_handle gpe_device, u32 gpe_number);
-
-acpi_status acpi_disable_gpe(acpi_handle gpe_device, u32 gpe_number);
-
-acpi_status acpi_clear_gpe(acpi_handle gpe_device, u32 gpe_number);
-
-acpi_status
-acpi_setup_gpe_for_wake(acpi_handle parent_device,
-			acpi_handle gpe_device, u32 gpe_number);
-
-acpi_status acpi_set_gpe_wake_mask(acpi_handle gpe_device, u32 gpe_number, u8 action);
-
-acpi_status
-acpi_get_gpe_status(acpi_handle gpe_device,
-		    u32 gpe_number, acpi_event_status *event_status);
-
-acpi_status acpi_disable_all_gpes(void);
-
-acpi_status acpi_enable_all_runtime_gpes(void);
-
-acpi_status acpi_get_gpe_device(u32 gpe_index, acpi_handle *gpe_device);
-
-acpi_status
-acpi_install_gpe_block(acpi_handle gpe_device,
-		       struct acpi_generic_address *gpe_block_address,
-		       u32 register_count, u32 interrupt_number);
-
-acpi_status acpi_remove_gpe_block(acpi_handle gpe_device);
-
-acpi_status acpi_update_all_gpes(void);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_update_all_gpes(void))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_enable_gpe(acpi_handle gpe_device,
+						u32 gpe_number))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_disable_gpe(acpi_handle gpe_device,
+						 u32 gpe_number))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_clear_gpe(acpi_handle gpe_device,
+					       u32 gpe_number))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_set_gpe(acpi_handle gpe_device,
+					     u32 gpe_number, u8 action))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_finish_gpe(acpi_handle gpe_device,
+						u32 gpe_number))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_setup_gpe_for_wake(acpi_handle
+							parent_device,
+							acpi_handle gpe_device,
+							u32 gpe_number))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_set_gpe_wake_mask(acpi_handle gpe_device,
+							u32 gpe_number,
+							u8 action))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_get_gpe_status(acpi_handle gpe_device,
+						     u32 gpe_number,
+						     acpi_event_status
+						     *event_status))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_get_gpe_device(u32 gpe_index,
+						    acpi_handle * gpe_device))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_install_gpe_block(acpi_handle gpe_device,
+						       struct
+						       acpi_generic_address
+						       *gpe_block_address,
+						       u32 register_count,
+						       u32 interrupt_number))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_remove_gpe_block(acpi_handle gpe_device))
 
 /*
  * Resource interfaces
@@ -391,34 +456,60 @@ acpi_buffer_to_resource(u8 *aml_buffer,
  */
 acpi_status acpi_reset(void);
 
-acpi_status acpi_read_bit_register(u32 register_id, u32 *return_value);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_read_bit_register(u32 register_id,
+						       u32 *return_value))
 
-acpi_status acpi_write_bit_register(u32 register_id, u32 value);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_write_bit_register(u32 register_id,
+							u32 value))
 
-acpi_status acpi_set_firmware_waking_vector(u32 physical_address);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_set_firmware_waking_vector(u32
+								physical_address))
 
 #if ACPI_MACHINE_WIDTH == 64
-acpi_status acpi_set_firmware_waking_vector64(u64 physical_address);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_set_firmware_waking_vector64(u64
+								  physical_address))
 #endif
 
 acpi_status acpi_read(u64 *value, struct acpi_generic_address *reg);
 
 acpi_status acpi_write(u64 value, struct acpi_generic_address *reg);
 
+/*
+ * Sleep/Wake interfaces
+ */
 acpi_status
 acpi_get_sleep_type_data(u8 sleep_state, u8 * slp_typ_a, u8 * slp_typ_b);
 
 acpi_status acpi_enter_sleep_state_prep(u8 sleep_state);
 
-acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state);
+acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state, u8 flags);
 
-acpi_status asmlinkage acpi_enter_sleep_state_s4bios(void);
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status asmlinkage acpi_enter_sleep_state_s4bios(void))
 
-acpi_status acpi_leave_sleep_state_prep(u8 sleep_state);
+acpi_status acpi_leave_sleep_state_prep(u8 sleep_state, u8 flags);
 
 acpi_status acpi_leave_sleep_state(u8 sleep_state);
 
 /*
+ * ACPI Timer interfaces
+ */
+#ifdef ACPI_FUTURE_USAGE
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_get_timer_resolution(u32 *resolution))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_get_timer(u32 *ticks))
+
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				acpi_get_timer_duration(u32 start_ticks,
+							u32 end_ticks,
+							u32 *time_elapsed))
+#endif				/* ACPI_FUTURE_USAGE */
+
+/*
  * Error/Warning output
  */
 void ACPI_INTERNAL_VAR_XFACE
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index 8e1b92f6f650..8dea54665dcf 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -309,6 +309,13 @@ enum acpi_prefered_pm_profiles {
 	PM_TABLET = 8
 };
 
+/* Values for sleep_status and sleep_control registers (V5 FADT) */
+
+#define ACPI_X_WAKE_STATUS          0x80
+#define ACPI_X_SLEEP_TYPE_MASK      0x1C
+#define ACPI_X_SLEEP_TYPE_POSITION  0x02
+#define ACPI_X_SLEEP_ENABLE         0x20
+
 /* Reset to default packing */
 
 #pragma pack()
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index d5dee7ce9474..eba66043cf1b 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -518,6 +518,13 @@ typedef u64 acpi_integer;
 #define ACPI_SLEEP_TYPE_INVALID         0xFF
 
 /*
+ * Sleep/Wake flags
+ */
+#define ACPI_NO_OPTIONAL_METHODS        0x00	/* Do not execute any optional methods */
+#define ACPI_EXECUTE_GTS                0x01	/* For enter sleep interface */
+#define ACPI_EXECUTE_BFS                0x02	/* For leave sleep prep interface */
+
+/*
  * Standard notify values
  */
 #define ACPI_NOTIFY_BUS_CHECK           (u8) 0x00
@@ -532,8 +539,9 @@ typedef u64 acpi_integer;
 #define ACPI_NOTIFY_DEVICE_PLD_CHECK    (u8) 0x09
 #define ACPI_NOTIFY_RESERVED            (u8) 0x0A
 #define ACPI_NOTIFY_LOCALITY_UPDATE     (u8) 0x0B
+#define ACPI_NOTIFY_SHUTDOWN_REQUEST    (u8) 0x0C
 
-#define ACPI_NOTIFY_MAX                 0x0B
+#define ACPI_NOTIFY_MAX                 0x0C
 
 /*
  * Types associated with ACPI names and objects. The first group of
@@ -698,7 +706,8 @@ typedef u32 acpi_event_status;
 #define ACPI_ALL_NOTIFY                 (ACPI_SYSTEM_NOTIFY | ACPI_DEVICE_NOTIFY)
 #define ACPI_MAX_NOTIFY_HANDLER_TYPE    0x3
 
-#define ACPI_MAX_SYS_NOTIFY             0x7f
+#define ACPI_MAX_SYS_NOTIFY             0x7F
+#define ACPI_MAX_DEVICE_SPECIFIC_NOTIFY 0xBF
 
 /* Address Space (Operation Region) Types */
 
@@ -786,6 +795,15 @@ typedef u8 acpi_adr_space_type;
 #define ACPI_ENABLE_EVENT                       1
 #define ACPI_DISABLE_EVENT                      0
 
+/* Sleep function dispatch */
+
+typedef acpi_status(*ACPI_SLEEP_FUNCTION) (u8 sleep_state, u8 flags);
+
+struct acpi_sleep_functions {
+	ACPI_SLEEP_FUNCTION legacy_function;
+	ACPI_SLEEP_FUNCTION extended_function;
+};
+
 /*
  * External ACPI object definition
  */
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index f4b2effe0333..6fbc4cab5834 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -57,7 +57,6 @@
 #include <linux/kernel.h>
 #include <linux/ctype.h>
 #include <linux/sched.h>
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/div64.h>
 #include <asm/acpi.h>
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index e37963c1df4d..1ced6413ea03 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -15,6 +15,8 @@
 #ifndef __ASM_GENERIC_ATOMIC_H
 #define __ASM_GENERIC_ATOMIC_H
 
+#include <asm/cmpxchg.h>
+
 #ifdef CONFIG_SMP
 /* Force people to define core atomics */
 # if !defined(atomic_add_return) || !defined(atomic_sub_return) || \
@@ -52,7 +54,6 @@
 #define atomic_set(v, i) (((v)->counter) = (i))
 
 #include <linux/irqflags.h>
-#include <asm/system.h>
 
 /**
  * atomic_add_return - add integer to atomic variable
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
new file mode 100644
index 000000000000..639d7a4d033b
--- /dev/null
+++ b/include/asm-generic/barrier.h
@@ -0,0 +1,50 @@
+/* Generic barrier definitions, based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_BARRIER_H
+#define __ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#define nop() asm volatile ("nop")
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * This implementation only contains a compiler barrier.
+ */
+
+#define mb()	asm volatile ("": : :"memory")
+#define rmb()	mb()
+#define wmb()	asm volatile ("": : :"memory")
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#endif
+
+#define set_mb(var, value)  do { var = value;  mb(); } while (0)
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+
+#define read_barrier_depends()		do {} while (0)
+#define smp_read_barrier_depends()	do {} while (0)
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index ecc44a8e2b44..9ae6c34dc191 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -2,7 +2,7 @@
 #define _ASM_GENERIC_BITOPS_ATOMIC_H_
 
 #include <asm/types.h>
-#include <asm/system.h>
+#include <linux/irqflags.h>
 
 #ifdef CONFIG_SMP
 #include <asm/spinlock.h>
diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h
index 213ac6e8fe39..14883026015d 100644
--- a/include/asm-generic/cmpxchg.h
+++ b/include/asm-generic/cmpxchg.h
@@ -1,22 +1,98 @@
+/*
+ * Generic UP xchg and cmpxchg using interrupt disablement.  Does not
+ * support SMP.
+ */
+
 #ifndef __ASM_GENERIC_CMPXCHG_H
 #define __ASM_GENERIC_CMPXCHG_H
 
-/*
- * Generic cmpxchg
- *
- * Uses the local cmpxchg. Does not support SMP.
- */
 #ifdef CONFIG_SMP
 #error "Cannot use generic cmpxchg on SMP"
 #endif
 
+#include <linux/types.h>
+#include <linux/irqflags.h>
+
+#ifndef xchg
+
+/*
+ * This function doesn't exist, so you'll get a linker error if
+ * something tries to do an invalidly-sized xchg().
+ */
+extern void __xchg_called_with_bad_pointer(void);
+
+static inline
+unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
+{
+	unsigned long ret, flags;
+
+	switch (size) {
+	case 1:
+#ifdef __xchg_u8
+		return __xchg_u8(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u8 *)ptr;
+		*(volatile u8 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u8 */
+
+	case 2:
+#ifdef __xchg_u16
+		return __xchg_u16(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u16 *)ptr;
+		*(volatile u16 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u16 */
+
+	case 4:
+#ifdef __xchg_u32
+		return __xchg_u32(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u32 *)ptr;
+		*(volatile u32 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u32 */
+
+#ifdef CONFIG_64BIT
+	case 8:
+#ifdef __xchg_u64
+		return __xchg_u64(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u64 *)ptr;
+		*(volatile u64 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u64 */
+#endif /* CONFIG_64BIT */
+
+	default:
+		__xchg_called_with_bad_pointer();
+		return x;
+	}
+}
+
+#define xchg(ptr, x) \
+	((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+
+#endif /* xchg */
+
 /*
  * Atomic compare and exchange.
  *
  * Do not define __HAVE_ARCH_CMPXCHG because we want to use it to check whether
  * a cmpxchg primitive faster than repeated local irq save/restore exists.
  */
+#include <asm-generic/cmpxchg-local.h>
+
 #define cmpxchg(ptr, o, n)	cmpxchg_local((ptr), (o), (n))
 #define cmpxchg64(ptr, o, n)	cmpxchg64_local((ptr), (o), (n))
 
-#endif
+#endif /* __ASM_GENERIC_CMPXCHG_H */
diff --git a/include/asm-generic/exec.h b/include/asm-generic/exec.h
new file mode 100644
index 000000000000..567766b0074a
--- /dev/null
+++ b/include/asm-generic/exec.h
@@ -0,0 +1,19 @@
+/* Generic process execution definitions, based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_EXEC_H
+#define __ASM_GENERIC_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __ASM_GENERIC_EXEC_H */
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index 1ff4e221cb4d..5f52690c3c8f 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -142,9 +142,9 @@ extern int __must_check gpiochip_reserve(int start, int ngpio);
 /* add/remove chips */
 extern int gpiochip_add(struct gpio_chip *chip);
 extern int __must_check gpiochip_remove(struct gpio_chip *chip);
-extern struct gpio_chip *gpiochip_find(void *data,
+extern struct gpio_chip *gpiochip_find(const void *data,
 					int (*match)(struct gpio_chip *chip,
-						     void *data));
+						     const void *data));
 
 
 /* Always use the library code for GPIO management calls,
diff --git a/include/asm-generic/posix_types.h b/include/asm-generic/posix_types.h
index 3dab00860e71..91d44bd4dde3 100644
--- a/include/asm-generic/posix_types.h
+++ b/include/asm-generic/posix_types.h
@@ -10,8 +10,13 @@
  * architectures, so that you can override them.
  */
 
+#ifndef __kernel_long_t
+typedef long		__kernel_long_t;
+typedef unsigned long	__kernel_ulong_t;
+#endif
+
 #ifndef __kernel_ino_t
-typedef unsigned long	__kernel_ino_t;
+typedef __kernel_ulong_t __kernel_ino_t;
 #endif
 
 #ifndef __kernel_mode_t
@@ -19,7 +24,7 @@ typedef unsigned int	__kernel_mode_t;
 #endif
 
 #ifndef __kernel_nlink_t
-typedef unsigned long	__kernel_nlink_t;
+typedef __kernel_ulong_t __kernel_nlink_t;
 #endif
 
 #ifndef __kernel_pid_t
@@ -36,7 +41,7 @@ typedef unsigned int	__kernel_gid_t;
 #endif
 
 #ifndef __kernel_suseconds_t
-typedef long		__kernel_suseconds_t;
+typedef __kernel_long_t		__kernel_suseconds_t;
 #endif
 
 #ifndef __kernel_daddr_t
@@ -44,8 +49,8 @@ typedef int		__kernel_daddr_t;
 #endif
 
 #ifndef __kernel_uid32_t
-typedef __kernel_uid_t	__kernel_uid32_t;
-typedef __kernel_gid_t	__kernel_gid32_t;
+typedef unsigned int	__kernel_uid32_t;
+typedef unsigned int	__kernel_gid32_t;
 #endif
 
 #ifndef __kernel_old_uid_t
@@ -67,99 +72,29 @@ typedef unsigned int	__kernel_size_t;
 typedef int		__kernel_ssize_t;
 typedef int		__kernel_ptrdiff_t;
 #else
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
+typedef __kernel_ulong_t __kernel_size_t;
+typedef __kernel_long_t	__kernel_ssize_t;
+typedef __kernel_long_t	__kernel_ptrdiff_t;
 #endif
 #endif
 
+#ifndef __kernel_fsid_t
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+#endif
+
 /*
  * anything below here should be completely generic
  */
-typedef long		__kernel_off_t;
+typedef __kernel_long_t	__kernel_off_t;
 typedef long long	__kernel_loff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_clock_t;
+typedef __kernel_long_t	__kernel_time_t;
+typedef __kernel_long_t	__kernel_clock_t;
 typedef int		__kernel_timer_t;
 typedef int		__kernel_clockid_t;
 typedef char *		__kernel_caddr_t;
 typedef unsigned short	__kernel_uid16_t;
 typedef unsigned short	__kernel_gid16_t;
 
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* __KERNEL__ */
-
 #endif /* __ASM_GENERIC_POSIX_TYPES_H */
diff --git a/include/asm-generic/switch_to.h b/include/asm-generic/switch_to.h
new file mode 100644
index 000000000000..052c4ac04fd5
--- /dev/null
+++ b/include/asm-generic/switch_to.h
@@ -0,0 +1,30 @@
+/* Generic task switch macro wrapper, based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_SWITCH_TO_H
+#define __ASM_GENERIC_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+
+/*
+ * Context switching is now performed out-of-line in switch_to.S
+ */
+extern struct task_struct *__switch_to(struct task_struct *,
+				       struct task_struct *);
+
+#define switch_to(prev, next, last)					\
+	do {								\
+		((last) = __switch_to((prev), (next)));			\
+	} while (0)
+
+#endif /* __ASM_GENERIC_SWITCH_TO_H */
diff --git a/include/asm-generic/system.h b/include/asm-generic/system.h
deleted file mode 100644
index 215efa74f5a2..000000000000
--- a/include/asm-generic/system.h
+++ /dev/null
@@ -1,141 +0,0 @@
-/* Generic system definitions, based on MN10300 definitions.
- *
- * It should be possible to use these on really simple architectures,
- * but it serves more as a starting point for new ports.
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-#ifndef __ASM_GENERIC_SYSTEM_H
-#define __ASM_GENERIC_SYSTEM_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-#include <linux/irqflags.h>
-
-#include <asm/cmpxchg-local.h>
-#include <asm/cmpxchg.h>
-
-struct task_struct;
-
-/* context switching is now performed out-of-line in switch_to.S */
-extern struct task_struct *__switch_to(struct task_struct *,
-		struct task_struct *);
-#define switch_to(prev, next, last)					\
-	do {								\
-		((last) = __switch_to((prev), (next)));			\
-	} while (0)
-
-#define arch_align_stack(x) (x)
-
-#define nop() asm volatile ("nop")
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- *
- * This implementation only contains a compiler barrier.
- */
-
-#define mb()	asm volatile ("": : :"memory")
-#define rmb()	mb()
-#define wmb()	asm volatile ("": : :"memory")
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#endif
-
-#define set_mb(var, value)  do { var = value;  mb(); } while (0)
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-/*
- * we make sure local_irq_enable() doesn't cause priority inversion
- */
-#ifndef __ASSEMBLY__
-
-/* This function doesn't exist, so you'll get a linker error
- *    if something tries to do an invalid xchg().  */
-extern void __xchg_called_with_bad_pointer(void);
-
-static inline
-unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
-{
-	unsigned long ret, flags;
-
-	switch (size) {
-	case 1:
-#ifdef __xchg_u8
-		return __xchg_u8(x, ptr);
-#else
-		local_irq_save(flags);
-		ret = *(volatile u8 *)ptr;
-		*(volatile u8 *)ptr = x;
-		local_irq_restore(flags);
-		return ret;
-#endif /* __xchg_u8 */
-
-	case 2:
-#ifdef __xchg_u16
-		return __xchg_u16(x, ptr);
-#else
-		local_irq_save(flags);
-		ret = *(volatile u16 *)ptr;
-		*(volatile u16 *)ptr = x;
-		local_irq_restore(flags);
-		return ret;
-#endif /* __xchg_u16 */
-
-	case 4:
-#ifdef __xchg_u32
-		return __xchg_u32(x, ptr);
-#else
-		local_irq_save(flags);
-		ret = *(volatile u32 *)ptr;
-		*(volatile u32 *)ptr = x;
-		local_irq_restore(flags);
-		return ret;
-#endif /* __xchg_u32 */
-
-#ifdef CONFIG_64BIT
-	case 8:
-#ifdef __xchg_u64
-		return __xchg_u64(x, ptr);
-#else
-		local_irq_save(flags);
-		ret = *(volatile u64 *)ptr;
-		*(volatile u64 *)ptr = x;
-		local_irq_restore(flags);
-		return ret;
-#endif /* __xchg_u64 */
-#endif /* CONFIG_64BIT */
-
-	default:
-		__xchg_called_with_bad_pointer();
-		return x;
-	}
-}
-
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_GENERIC_SYSTEM_H */
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index 2292d1af9d70..991ef01cd77e 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -218,7 +218,7 @@ __SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
 
 /* fs/sendfile.c */
 #define __NR3264_sendfile 71
-__SC_3264(__NR3264_sendfile, sys_sendfile64, sys_sendfile)
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
 
 /* fs/select.c */
 #define __NR_pselect6 72
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 798603e8ec38..8aeadf6b553a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -616,30 +616,23 @@
 		*(.init.setup)						\
 		VMLINUX_SYMBOL(__setup_end) = .;
 
-#define INITCALLS							\
-	*(.initcallearly.init)						\
-	VMLINUX_SYMBOL(__early_initcall_end) = .;			\
-  	*(.initcall0.init)						\
-  	*(.initcall0s.init)						\
-  	*(.initcall1.init)						\
-  	*(.initcall1s.init)						\
-  	*(.initcall2.init)						\
-  	*(.initcall2s.init)						\
-  	*(.initcall3.init)						\
-  	*(.initcall3s.init)						\
-  	*(.initcall4.init)						\
-  	*(.initcall4s.init)						\
-  	*(.initcall5.init)						\
-  	*(.initcall5s.init)						\
-	*(.initcallrootfs.init)						\
-  	*(.initcall6.init)						\
-  	*(.initcall6s.init)						\
-  	*(.initcall7.init)						\
-  	*(.initcall7s.init)
+#define INIT_CALLS_LEVEL(level)						\
+		VMLINUX_SYMBOL(__initcall##level##_start) = .;		\
+		*(.initcall##level##.init)				\
+		*(.initcall##level##s.init)				\
 
 #define INIT_CALLS							\
 		VMLINUX_SYMBOL(__initcall_start) = .;			\
-		INITCALLS						\
+		*(.initcallearly.init)					\
+		INIT_CALLS_LEVEL(0)					\
+		INIT_CALLS_LEVEL(1)					\
+		INIT_CALLS_LEVEL(2)					\
+		INIT_CALLS_LEVEL(3)					\
+		INIT_CALLS_LEVEL(4)					\
+		INIT_CALLS_LEVEL(5)					\
+		INIT_CALLS_LEVEL(rootfs)				\
+		INIT_CALLS_LEVEL(6)					\
+		INIT_CALLS_LEVEL(7)					\
 		VMLINUX_SYMBOL(__initcall_end) = .;
 
 #define CON_INITCALL							\
diff --git a/include/crypto/internal/aead.h b/include/crypto/internal/aead.h
index d838c945575a..2eba340230a7 100644
--- a/include/crypto/internal/aead.h
+++ b/include/crypto/internal/aead.h
@@ -31,6 +31,8 @@ static inline void crypto_set_aead_spawn(
 	crypto_set_spawn(&spawn->base, inst);
 }
 
+struct crypto_alg *crypto_lookup_aead(const char *name, u32 type, u32 mask);
+
 int crypto_grab_aead(struct crypto_aead_spawn *spawn, const char *name,
 		     u32 type, u32 mask);
 
diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h
index 3a748a6bf772..06e8b32d541c 100644
--- a/include/crypto/internal/skcipher.h
+++ b/include/crypto/internal/skcipher.h
@@ -34,6 +34,8 @@ static inline void crypto_set_skcipher_spawn(
 int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name,
 			 u32 type, u32 mask);
 
+struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask);
+
 static inline void crypto_drop_skcipher(struct crypto_skcipher_spawn *spawn)
 {
 	crypto_drop_spawn(&spawn->base);
diff --git a/include/drm/drm.h b/include/drm/drm.h
index 34a7b89fd006..64ff02d5b730 100644
--- a/include/drm/drm.h
+++ b/include/drm/drm.h
@@ -617,6 +617,17 @@ struct drm_get_cap {
 	__u64 value;
 };
 
+#define DRM_CLOEXEC O_CLOEXEC
+struct drm_prime_handle {
+	__u32 handle;
+
+	/** Flags.. only applicable for handle->fd */
+	__u32 flags;
+
+	/** Returned dmabuf file descriptor */
+	__s32 fd;
+};
+
 #include "drm_mode.h"
 
 #define DRM_IOCTL_BASE			'd'
@@ -673,7 +684,8 @@ struct drm_get_cap {
 #define DRM_IOCTL_UNLOCK		DRM_IOW( 0x2b, struct drm_lock)
 #define DRM_IOCTL_FINISH		DRM_IOW( 0x2c, struct drm_lock)
 
-#define DRM_IOCTL_GEM_PRIME_OPEN        DRM_IOWR(0x2e, struct drm_gem_open)
+#define DRM_IOCTL_PRIME_HANDLE_TO_FD    DRM_IOWR(0x2d, struct drm_prime_handle)
+#define DRM_IOCTL_PRIME_FD_TO_HANDLE    DRM_IOWR(0x2e, struct drm_prime_handle)
 
 #define DRM_IOCTL_AGP_ACQUIRE		DRM_IO(  0x30)
 #define DRM_IOCTL_AGP_RELEASE		DRM_IO(  0x31)
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 574bd1c81ebd..dd731043fecd 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -91,6 +91,7 @@ struct drm_device;
 #define DRM_UT_CORE 		0x01
 #define DRM_UT_DRIVER		0x02
 #define DRM_UT_KMS		0x04
+#define DRM_UT_PRIME		0x08
 /*
  * Three debug levels are defined.
  * drm_core, drm_driver, drm_kms
@@ -150,6 +151,7 @@ int drm_err(const char *func, const char *format, ...);
 #define DRIVER_IRQ_VBL2    0x800
 #define DRIVER_GEM         0x1000
 #define DRIVER_MODESET     0x2000
+#define DRIVER_PRIME       0x4000
 
 #define DRIVER_BUS_PCI 0x1
 #define DRIVER_BUS_PLATFORM 0x2
@@ -215,6 +217,11 @@ int drm_err(const char *func, const char *format, ...);
 		drm_ut_debug_printk(DRM_UT_KMS, DRM_NAME, 		\
 					 __func__, fmt, ##args);	\
 	} while (0)
+#define DRM_DEBUG_PRIME(fmt, args...)					\
+	do {								\
+		drm_ut_debug_printk(DRM_UT_PRIME, DRM_NAME,		\
+					__func__, fmt, ##args);		\
+	} while (0)
 #define DRM_LOG(fmt, args...)						\
 	do {								\
 		drm_ut_debug_printk(DRM_UT_CORE, NULL,			\
@@ -238,6 +245,7 @@ int drm_err(const char *func, const char *format, ...);
 #else
 #define DRM_DEBUG_DRIVER(fmt, args...) do { } while (0)
 #define DRM_DEBUG_KMS(fmt, args...)	do { } while (0)
+#define DRM_DEBUG_PRIME(fmt, args...)	do { } while (0)
 #define DRM_DEBUG(fmt, arg...)		 do { } while (0)
 #define DRM_LOG(fmt, arg...)		do { } while (0)
 #define DRM_LOG_KMS(fmt, args...) do { } while (0)
@@ -410,6 +418,12 @@ struct drm_pending_event {
 	void (*destroy)(struct drm_pending_event *event);
 };
 
+/* initial implementaton using a linked list - todo hashtab */
+struct drm_prime_file_private {
+	struct list_head head;
+	struct mutex lock;
+};
+
 /** File private data */
 struct drm_file {
 	int authenticated;
@@ -437,6 +451,8 @@ struct drm_file {
 	wait_queue_head_t event_wait;
 	struct list_head event_list;
 	int event_space;
+
+	struct drm_prime_file_private prime;
 };
 
 /** Wait queue */
@@ -652,6 +668,12 @@ struct drm_gem_object {
 	uint32_t pending_write_domain;
 
 	void *driver_private;
+
+	/* dma buf exported from this GEM object */
+	struct dma_buf *export_dma_buf;
+
+	/* dma buf attachment backing this object */
+	struct dma_buf_attachment *import_attach;
 };
 
 #include "drm_crtc.h"
@@ -890,6 +912,20 @@ struct drm_driver {
 	int (*gem_open_object) (struct drm_gem_object *, struct drm_file *);
 	void (*gem_close_object) (struct drm_gem_object *, struct drm_file *);
 
+	/* prime: */
+	/* export handle -> fd (see drm_gem_prime_handle_to_fd() helper) */
+	int (*prime_handle_to_fd)(struct drm_device *dev, struct drm_file *file_priv,
+				uint32_t handle, uint32_t flags, int *prime_fd);
+	/* import fd -> handle (see drm_gem_prime_fd_to_handle() helper) */
+	int (*prime_fd_to_handle)(struct drm_device *dev, struct drm_file *file_priv,
+				int prime_fd, uint32_t *handle);
+	/* export GEM -> dmabuf */
+	struct dma_buf * (*gem_prime_export)(struct drm_device *dev,
+				struct drm_gem_object *obj, int flags);
+	/* import dmabuf -> GEM */
+	struct drm_gem_object * (*gem_prime_import)(struct drm_device *dev,
+				struct dma_buf *dma_buf);
+
 	/* vga arb irq handler */
 	void (*vgaarb_irq)(struct drm_device *dev, bool state);
 
@@ -1509,6 +1545,32 @@ extern int drm_vblank_info(struct seq_file *m, void *data);
 extern int drm_clients_info(struct seq_file *m, void* data);
 extern int drm_gem_name_info(struct seq_file *m, void *data);
 
+
+extern int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+		struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+		int *prime_fd);
+extern int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+		struct drm_file *file_priv, int prime_fd, uint32_t *handle);
+
+extern int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
+					struct drm_file *file_priv);
+extern int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
+					struct drm_file *file_priv);
+
+extern struct sg_table *drm_prime_pages_to_sg(struct page **pages, int nr_pages);
+extern void drm_prime_gem_destroy(struct drm_gem_object *obj, struct sg_table *sg);
+
+
+void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
+void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
+int drm_prime_add_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf, uint32_t handle);
+int drm_prime_lookup_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf, uint32_t *handle);
+void drm_prime_remove_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf);
+
+int drm_prime_add_dma_buf(struct drm_device *dev, struct drm_gem_object *obj);
+int drm_prime_lookup_obj(struct drm_device *dev, struct dma_buf *buf,
+			 struct drm_gem_object **obj);
+
 #if DRM_DEBUG_CODE
 extern int drm_vma_info(struct seq_file *m, void *data);
 #endif
diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h
index 0a0001b9dc78..923afb5dcf0c 100644
--- a/include/drm/intel-gtt.h
+++ b/include/drm/intel-gtt.h
@@ -44,4 +44,8 @@ void intel_gtt_insert_pages(unsigned int first_entry, unsigned int num_entries,
 /* flag for GFDT type */
 #define AGP_USER_CACHED_MEMORY_GFDT (1 << 3)
 
+#ifdef CONFIG_INTEL_IOMMU
+extern int intel_iommu_gfx_mapped;
+#endif
+
 #endif
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index a25555381097..3c9b616c834a 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -3,6 +3,7 @@ header-y += can/
 header-y += caif/
 header-y += dvb/
 header-y += hdlc/
+header-y += hsi/
 header-y += isdn/
 header-y += mmc/
 header-y += nfsd/
@@ -120,7 +121,6 @@ header-y += errno.h
 header-y += errqueue.h
 header-y += ethtool.h
 header-y += eventpoll.h
-header-y += ext2_fs.h
 header-y += fadvise.h
 header-y += falloc.h
 header-y += fanotify.h
@@ -357,6 +357,7 @@ header-y += suspend_ioctls.h
 header-y += swab.h
 header-y += synclink.h
 header-y += sysctl.h
+header-y += sysinfo.h
 header-y += taskstats.h
 header-y += tcp.h
 header-y += telephony.h
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 3f968665899b..f421dd84f29d 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -151,6 +151,7 @@ extern int ec_write(u8 addr, u8 val);
 extern int ec_transaction(u8 command,
                           const u8 *wdata, unsigned wdata_len,
                           u8 *rdata, unsigned rdata_len);
+extern acpi_handle ec_get_handle(void);
 
 #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE)
 
@@ -371,4 +372,14 @@ static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *),
 
 #endif	/* !CONFIG_ACPI */
 
+#ifdef CONFIG_ACPI
+void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
+			       u32 pm1a_ctrl,  u32 pm1b_ctrl));
+
+acpi_status acpi_os_prepare_sleep(u8 sleep_state,
+				  u32 pm1a_control, u32 pm1b_control);
+#else
+#define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0)
+#endif
+
 #endif	/*_LINUX_ACPI_H*/
diff --git a/include/linux/aio_abi.h b/include/linux/aio_abi.h
index 2c8731664180..86fa7a71336a 100644
--- a/include/linux/aio_abi.h
+++ b/include/linux/aio_abi.h
@@ -30,7 +30,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 
-typedef unsigned long	aio_context_t;
+typedef __kernel_ulong_t aio_context_t;
 
 enum {
 	IOCB_CMD_PREAD = 0,
diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h
index 033f6aa670de..e64ce2cfee99 100644
--- a/include/linux/amba/pl08x.h
+++ b/include/linux/amba/pl08x.h
@@ -47,9 +47,6 @@ enum {
  * @muxval: a number usually used to poke into some mux regiser to
  * mux in the signal to this channel
  * @cctl_opt: default options for the channel control register
- * @device_fc: Flow Controller Settings for ccfg register. Only valid for slave
- * channels. Fill with 'true' if peripheral should be flow controller. Direction
- * will be selected at Runtime.
  * @addr: source/target address in physical memory for this DMA channel,
  * can be the address of a FIFO register for burst requests for example.
  * This can be left undefined if the PrimeCell API is used for configuring
@@ -68,7 +65,6 @@ struct pl08x_channel_data {
 	int max_signal;
 	u32 muxval;
 	u32 cctl;
-	bool device_fc;
 	dma_addr_t addr;
 	bool circular_buffer;
 	bool single;
@@ -176,13 +172,15 @@ enum pl08x_dma_chan_state {
  * @runtime_addr: address for RX/TX according to the runtime config
  * @runtime_direction: current direction of this channel according to
  * runtime config
- * @lc: last completed transaction on this channel
  * @pend_list: queued transactions pending on this channel
  * @at: active transaction on this channel
  * @lock: a lock for this channel data
  * @host: a pointer to the host (internal use)
  * @state: whether the channel is idle, paused, running etc
  * @slave: whether this channel is a device (slave) or for memcpy
+ * @device_fc: Flow Controller Settings for ccfg register. Only valid for slave
+ * channels. Fill with 'true' if peripheral should be flow controller. Direction
+ * will be selected at Runtime.
  * @waiting: a TX descriptor on this channel which is waiting for a physical
  * channel to become available
  */
@@ -198,13 +196,13 @@ struct pl08x_dma_chan {
 	u32 src_cctl;
 	u32 dst_cctl;
 	enum dma_transfer_direction runtime_direction;
-	dma_cookie_t lc;
 	struct list_head pend_list;
 	struct pl08x_txd *at;
 	spinlock_t lock;
 	struct pl08x_driver_data *host;
 	enum pl08x_dma_chan_state state;
 	bool slave;
+	bool device_fc;
 	struct pl08x_txd *waiting;
 };
 
diff --git a/include/linux/amba/pl330.h b/include/linux/amba/pl330.h
index 12e023c19ac1..fe93758e8403 100644
--- a/include/linux/amba/pl330.h
+++ b/include/linux/amba/pl330.h
@@ -13,7 +13,6 @@
 #define	__AMBA_PL330_H_
 
 #include <linux/dmaengine.h>
-#include <asm/hardware/pl330.h>
 
 struct dma_pl330_platdata {
 	/*
diff --git a/include/linux/apple_bl.h b/include/linux/apple_bl.h
new file mode 100644
index 000000000000..47bedc0eee69
--- /dev/null
+++ b/include/linux/apple_bl.h
@@ -0,0 +1,26 @@
+/*
+ * apple_bl exported symbols
+ */
+
+#ifndef _LINUX_APPLE_BL_H
+#define _LINUX_APPLE_BL_H
+
+#ifdef CONFIG_BACKLIGHT_APPLE
+
+extern int apple_bl_register(void);
+extern void apple_bl_unregister(void);
+
+#else /* !CONFIG_BACKLIGHT_APPLE */
+
+static inline int apple_bl_register(void)
+{
+	return 0;
+}
+
+static inline void apple_bl_unregister(void)
+{
+}
+
+#endif /* !CONFIG_BACKLIGHT_APPLE */
+
+#endif /* _LINUX_APPLE_BL_H */
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index e8cf0ccd1a8d..e71d683982a6 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -208,7 +208,7 @@ extern struct kmem_cache *ceph_cap_cachep;
 extern struct kmem_cache *ceph_dentry_cachep;
 extern struct kmem_cache *ceph_file_cachep;
 
-extern int ceph_parse_options(struct ceph_options **popt, char *options,
+extern struct ceph_options *ceph_parse_options(char *options,
 			      const char *dev_name, const char *dev_name_end,
 			      int (*parse_extra_token)(char *c, void *private),
 			      void *private);
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index ffbeb2c217b4..3bff047f6b0f 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -14,8 +14,6 @@
 struct ceph_msg;
 struct ceph_connection;
 
-extern struct workqueue_struct *ceph_msgr_wq;       /* receive work queue */
-
 /*
  * Ceph defines these callbacks for handling connection events.
  */
@@ -54,7 +52,6 @@ struct ceph_connection_operations {
 struct ceph_messenger {
 	struct ceph_entity_inst inst;    /* my name+address */
 	struct ceph_entity_addr my_enc_addr;
-	struct page *zero_page;          /* used in certain error cases */
 
 	bool nocrc;
 
@@ -101,7 +98,7 @@ struct ceph_msg {
 struct ceph_msg_pos {
 	int page, page_pos;  /* which page; offset in page */
 	int data_pos;        /* offset in data payload */
-	int did_page_crc;    /* true if we've calculated crc for current page */
+	bool did_page_crc;   /* true if we've calculated crc for current page */
 };
 
 /* ceph connection fault delay defaults, for exponential backoff */
diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h
new file mode 100644
index 000000000000..5e4312b6f5cc
--- /dev/null
+++ b/include/linux/clk-private.h
@@ -0,0 +1,196 @@
+/*
+ *  linux/include/linux/clk-private.h
+ *
+ *  Copyright (c) 2010-2011 Jeremy Kerr <jeremy.kerr@canonical.com>
+ *  Copyright (C) 2011-2012 Linaro Ltd <mturquette@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_CLK_PRIVATE_H
+#define __LINUX_CLK_PRIVATE_H
+
+#include <linux/clk-provider.h>
+#include <linux/list.h>
+
+/*
+ * WARNING: Do not include clk-private.h from any file that implements struct
+ * clk_ops.  Doing so is a layering violation!
+ *
+ * This header exists only to allow for statically initialized clock data.  Any
+ * static clock data must be defined in a separate file from the logic that
+ * implements the clock operations for that same data.
+ */
+
+#ifdef CONFIG_COMMON_CLK
+
+struct clk {
+	const char		*name;
+	const struct clk_ops	*ops;
+	struct clk_hw		*hw;
+	struct clk		*parent;
+	char			**parent_names;
+	struct clk		**parents;
+	u8			num_parents;
+	unsigned long		rate;
+	unsigned long		new_rate;
+	unsigned long		flags;
+	unsigned int		enable_count;
+	unsigned int		prepare_count;
+	struct hlist_head	children;
+	struct hlist_node	child_node;
+	unsigned int		notifier_count;
+#ifdef CONFIG_COMMON_CLK_DEBUG
+	struct dentry		*dentry;
+#endif
+};
+
+/*
+ * DOC: Basic clock implementations common to many platforms
+ *
+ * Each basic clock hardware type is comprised of a structure describing the
+ * clock hardware, implementations of the relevant callbacks in struct clk_ops,
+ * unique flags for that hardware type, a registration function and an
+ * alternative macro for static initialization
+ */
+
+extern struct clk_ops clk_fixed_rate_ops;
+
+#define DEFINE_CLK_FIXED_RATE(_name, _flags, _rate,		\
+				_fixed_rate_flags)		\
+	static struct clk _name;				\
+	static char *_name##_parent_names[] = {};		\
+	static struct clk_fixed_rate _name##_hw = {		\
+		.hw = {						\
+			.clk = &_name,				\
+		},						\
+		.fixed_rate = _rate,				\
+		.flags = _fixed_rate_flags,			\
+	};							\
+	static struct clk _name = {				\
+		.name = #_name,					\
+		.ops = &clk_fixed_rate_ops,			\
+		.hw = &_name##_hw.hw,				\
+		.parent_names = _name##_parent_names,		\
+		.num_parents =					\
+			ARRAY_SIZE(_name##_parent_names),	\
+		.flags = _flags,				\
+	};
+
+extern struct clk_ops clk_gate_ops;
+
+#define DEFINE_CLK_GATE(_name, _parent_name, _parent_ptr,	\
+				_flags, _reg, _bit_idx,		\
+				_gate_flags, _lock)		\
+	static struct clk _name;				\
+	static char *_name##_parent_names[] = {			\
+		_parent_name,					\
+	};							\
+	static struct clk *_name##_parents[] = {		\
+		_parent_ptr,					\
+	};							\
+	static struct clk_gate _name##_hw = {			\
+		.hw = {						\
+			.clk = &_name,				\
+		},						\
+		.reg = _reg,					\
+		.bit_idx = _bit_idx,				\
+		.flags = _gate_flags,				\
+		.lock = _lock,					\
+	};							\
+	static struct clk _name = {				\
+		.name = #_name,					\
+		.ops = &clk_gate_ops,				\
+		.hw = &_name##_hw.hw,				\
+		.parent_names = _name##_parent_names,		\
+		.num_parents =					\
+			ARRAY_SIZE(_name##_parent_names),	\
+		.parents = _name##_parents,			\
+		.flags = _flags,				\
+	};
+
+extern struct clk_ops clk_divider_ops;
+
+#define DEFINE_CLK_DIVIDER(_name, _parent_name, _parent_ptr,	\
+				_flags, _reg, _shift, _width,	\
+				_divider_flags, _lock)		\
+	static struct clk _name;				\
+	static char *_name##_parent_names[] = {			\
+		_parent_name,					\
+	};							\
+	static struct clk *_name##_parents[] = {		\
+		_parent_ptr,					\
+	};							\
+	static struct clk_divider _name##_hw = {		\
+		.hw = {						\
+			.clk = &_name,				\
+		},						\
+		.reg = _reg,					\
+		.shift = _shift,				\
+		.width = _width,				\
+		.flags = _divider_flags,			\
+		.lock = _lock,					\
+	};							\
+	static struct clk _name = {				\
+		.name = #_name,					\
+		.ops = &clk_divider_ops,			\
+		.hw = &_name##_hw.hw,				\
+		.parent_names = _name##_parent_names,		\
+		.num_parents =					\
+			ARRAY_SIZE(_name##_parent_names),	\
+		.parents = _name##_parents,			\
+		.flags = _flags,				\
+	};
+
+extern struct clk_ops clk_mux_ops;
+
+#define DEFINE_CLK_MUX(_name, _parent_names, _parents, _flags,	\
+				_reg, _shift, _width,		\
+				_mux_flags, _lock)		\
+	static struct clk _name;				\
+	static struct clk_mux _name##_hw = {			\
+		.hw = {						\
+			.clk = &_name,				\
+		},						\
+		.reg = _reg,					\
+		.shift = _shift,				\
+		.width = _width,				\
+		.flags = _mux_flags,				\
+		.lock = _lock,					\
+	};							\
+	static struct clk _name = {				\
+		.name = #_name,					\
+		.ops = &clk_mux_ops,				\
+		.hw = &_name##_hw.hw,				\
+		.parent_names = _parent_names,			\
+		.num_parents =					\
+			ARRAY_SIZE(_parent_names),		\
+		.parents = _parents,				\
+		.flags = _flags,				\
+	};
+
+/**
+ * __clk_init - initialize the data structures in a struct clk
+ * @dev:	device initializing this clk, placeholder for now
+ * @clk:	clk being initialized
+ *
+ * Initializes the lists in struct clk, queries the hardware for the
+ * parent and rate and sets them both.
+ *
+ * Any struct clk passed into __clk_init must have the following members
+ * populated:
+ * 	.name
+ * 	.ops
+ * 	.hw
+ * 	.parent_names
+ * 	.num_parents
+ * 	.flags
+ *
+ * It is not necessary to call clk_register if __clk_init is used directly with
+ * statically initialized clock data.
+ */
+void __clk_init(struct device *dev, struct clk *clk);
+
+#endif /* CONFIG_COMMON_CLK */
+#endif /* CLK_PRIVATE_H */
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
new file mode 100644
index 000000000000..5508897ad376
--- /dev/null
+++ b/include/linux/clk-provider.h
@@ -0,0 +1,300 @@
+/*
+ *  linux/include/linux/clk-provider.h
+ *
+ *  Copyright (c) 2010-2011 Jeremy Kerr <jeremy.kerr@canonical.com>
+ *  Copyright (C) 2011-2012 Linaro Ltd <mturquette@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_CLK_PROVIDER_H
+#define __LINUX_CLK_PROVIDER_H
+
+#include <linux/clk.h>
+
+#ifdef CONFIG_COMMON_CLK
+
+/**
+ * struct clk_hw - handle for traversing from a struct clk to its corresponding
+ * hardware-specific structure.  struct clk_hw should be declared within struct
+ * clk_foo and then referenced by the struct clk instance that uses struct
+ * clk_foo's clk_ops
+ *
+ * clk: pointer to the struct clk instance that points back to this struct
+ * clk_hw instance
+ */
+struct clk_hw {
+	struct clk *clk;
+};
+
+/*
+ * flags used across common struct clk.  these flags should only affect the
+ * top-level framework.  custom flags for dealing with hardware specifics
+ * belong in struct clk_foo
+ */
+#define CLK_SET_RATE_GATE	BIT(0) /* must be gated across rate change */
+#define CLK_SET_PARENT_GATE	BIT(1) /* must be gated across re-parent */
+#define CLK_SET_RATE_PARENT	BIT(2) /* propagate rate change up one level */
+#define CLK_IGNORE_UNUSED	BIT(3) /* do not gate even if unused */
+#define CLK_IS_ROOT		BIT(4) /* root clk, has no parent */
+
+/**
+ * struct clk_ops -  Callback operations for hardware clocks; these are to
+ * be provided by the clock implementation, and will be called by drivers
+ * through the clk_* api.
+ *
+ * @prepare:	Prepare the clock for enabling. This must not return until
+ * 		the clock is fully prepared, and it's safe to call clk_enable.
+ * 		This callback is intended to allow clock implementations to
+ * 		do any initialisation that may sleep. Called with
+ * 		prepare_lock held.
+ *
+ * @unprepare:	Release the clock from its prepared state. This will typically
+ * 		undo any work done in the @prepare callback. Called with
+ * 		prepare_lock held.
+ *
+ * @enable:	Enable the clock atomically. This must not return until the
+ * 		clock is generating a valid clock signal, usable by consumer
+ * 		devices. Called with enable_lock held. This function must not
+ * 		sleep.
+ *
+ * @disable:	Disable the clock atomically. Called with enable_lock held.
+ * 		This function must not sleep.
+ *
+ * @recalc_rate	Recalculate the rate of this clock, by quering hardware.  The
+ * 		parent rate is an input parameter.  It is up to the caller to
+ * 		insure that the prepare_mutex is held across this call.
+ * 		Returns the calculated rate.  Optional, but recommended - if
+ * 		this op is not set then clock rate will be initialized to 0.
+ *
+ * @round_rate:	Given a target rate as input, returns the closest rate actually
+ * 		supported by the clock.
+ *
+ * @get_parent:	Queries the hardware to determine the parent of a clock.  The
+ * 		return value is a u8 which specifies the index corresponding to
+ * 		the parent clock.  This index can be applied to either the
+ * 		.parent_names or .parents arrays.  In short, this function
+ * 		translates the parent value read from hardware into an array
+ * 		index.  Currently only called when the clock is initialized by
+ * 		__clk_init.  This callback is mandatory for clocks with
+ * 		multiple parents.  It is optional (and unnecessary) for clocks
+ * 		with 0 or 1 parents.
+ *
+ * @set_parent:	Change the input source of this clock; for clocks with multiple
+ * 		possible parents specify a new parent by passing in the index
+ * 		as a u8 corresponding to the parent in either the .parent_names
+ * 		or .parents arrays.  This function in affect translates an
+ * 		array index into the value programmed into the hardware.
+ * 		Returns 0 on success, -EERROR otherwise.
+ *
+ * @set_rate:	Change the rate of this clock. If this callback returns
+ * 		CLK_SET_RATE_PARENT, the rate change will be propagated to the
+ * 		parent clock (which may propagate again if the parent clock
+ * 		also sets this flag). The requested rate of the parent is
+ * 		passed back from the callback in the second 'unsigned long *'
+ * 		argument.  Note that it is up to the hardware clock's set_rate
+ * 		implementation to insure that clocks do not run out of spec
+ * 		when propgating the call to set_rate up to the parent.  One way
+ * 		to do this is to gate the clock (via clk_disable and/or
+ * 		clk_unprepare) before calling clk_set_rate, then ungating it
+ * 		afterward.  If your clock also has the CLK_GATE_SET_RATE flag
+ * 		set then this will insure safety.  Returns 0 on success,
+ * 		-EERROR otherwise.
+ *
+ * The clk_enable/clk_disable and clk_prepare/clk_unprepare pairs allow
+ * implementations to split any work between atomic (enable) and sleepable
+ * (prepare) contexts.  If enabling a clock requires code that might sleep,
+ * this must be done in clk_prepare.  Clock enable code that will never be
+ * called in a sleepable context may be implement in clk_enable.
+ *
+ * Typically, drivers will call clk_prepare when a clock may be needed later
+ * (eg. when a device is opened), and clk_enable when the clock is actually
+ * required (eg. from an interrupt). Note that clk_prepare MUST have been
+ * called before clk_enable.
+ */
+struct clk_ops {
+	int		(*prepare)(struct clk_hw *hw);
+	void		(*unprepare)(struct clk_hw *hw);
+	int		(*enable)(struct clk_hw *hw);
+	void		(*disable)(struct clk_hw *hw);
+	int		(*is_enabled)(struct clk_hw *hw);
+	unsigned long	(*recalc_rate)(struct clk_hw *hw,
+					unsigned long parent_rate);
+	long		(*round_rate)(struct clk_hw *hw, unsigned long,
+					unsigned long *);
+	int		(*set_parent)(struct clk_hw *hw, u8 index);
+	u8		(*get_parent)(struct clk_hw *hw);
+	int		(*set_rate)(struct clk_hw *hw, unsigned long);
+	void		(*init)(struct clk_hw *hw);
+};
+
+/*
+ * DOC: Basic clock implementations common to many platforms
+ *
+ * Each basic clock hardware type is comprised of a structure describing the
+ * clock hardware, implementations of the relevant callbacks in struct clk_ops,
+ * unique flags for that hardware type, a registration function and an
+ * alternative macro for static initialization
+ */
+
+/**
+ * struct clk_fixed_rate - fixed-rate clock
+ * @hw:		handle between common and hardware-specific interfaces
+ * @fixed_rate:	constant frequency of clock
+ */
+struct clk_fixed_rate {
+	struct		clk_hw hw;
+	unsigned long	fixed_rate;
+	u8		flags;
+};
+
+struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
+		const char *parent_name, unsigned long flags,
+		unsigned long fixed_rate);
+
+/**
+ * struct clk_gate - gating clock
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @reg:	register controlling gate
+ * @bit_idx:	single bit controlling gate
+ * @flags:	hardware-specific flags
+ * @lock:	register lock
+ *
+ * Clock which can gate its output.  Implements .enable & .disable
+ *
+ * Flags:
+ * CLK_GATE_SET_DISABLE - by default this clock sets the bit at bit_idx to
+ * 	enable the clock.  Setting this flag does the opposite: setting the bit
+ * 	disable the clock and clearing it enables the clock
+ */
+struct clk_gate {
+	struct clk_hw hw;
+	void __iomem	*reg;
+	u8		bit_idx;
+	u8		flags;
+	spinlock_t	*lock;
+	char		*parent[1];
+};
+
+#define CLK_GATE_SET_TO_DISABLE		BIT(0)
+
+struct clk *clk_register_gate(struct device *dev, const char *name,
+		const char *parent_name, unsigned long flags,
+		void __iomem *reg, u8 bit_idx,
+		u8 clk_gate_flags, spinlock_t *lock);
+
+/**
+ * struct clk_divider - adjustable divider clock
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @reg:	register containing the divider
+ * @shift:	shift to the divider bit field
+ * @width:	width of the divider bit field
+ * @lock:	register lock
+ *
+ * Clock with an adjustable divider affecting its output frequency.  Implements
+ * .recalc_rate, .set_rate and .round_rate
+ *
+ * Flags:
+ * CLK_DIVIDER_ONE_BASED - by default the divisor is the value read from the
+ * 	register plus one.  If CLK_DIVIDER_ONE_BASED is set then the divider is
+ * 	the raw value read from the register, with the value of zero considered
+ * 	invalid
+ * CLK_DIVIDER_POWER_OF_TWO - clock divisor is 2 raised to the value read from
+ * 	the hardware register
+ */
+struct clk_divider {
+	struct clk_hw	hw;
+	void __iomem	*reg;
+	u8		shift;
+	u8		width;
+	u8		flags;
+	spinlock_t	*lock;
+	char		*parent[1];
+};
+
+#define CLK_DIVIDER_ONE_BASED		BIT(0)
+#define CLK_DIVIDER_POWER_OF_TWO	BIT(1)
+
+struct clk *clk_register_divider(struct device *dev, const char *name,
+		const char *parent_name, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width,
+		u8 clk_divider_flags, spinlock_t *lock);
+
+/**
+ * struct clk_mux - multiplexer clock
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @reg:	register controlling multiplexer
+ * @shift:	shift to multiplexer bit field
+ * @width:	width of mutliplexer bit field
+ * @num_clks:	number of parent clocks
+ * @lock:	register lock
+ *
+ * Clock with multiple selectable parents.  Implements .get_parent, .set_parent
+ * and .recalc_rate
+ *
+ * Flags:
+ * CLK_MUX_INDEX_ONE - register index starts at 1, not 0
+ * CLK_MUX_INDEX_BITWISE - register index is a single bit (power of two)
+ */
+struct clk_mux {
+	struct clk_hw	hw;
+	void __iomem	*reg;
+	u8		shift;
+	u8		width;
+	u8		flags;
+	spinlock_t	*lock;
+};
+
+#define CLK_MUX_INDEX_ONE		BIT(0)
+#define CLK_MUX_INDEX_BIT		BIT(1)
+
+struct clk *clk_register_mux(struct device *dev, const char *name,
+		char **parent_names, u8 num_parents, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width,
+		u8 clk_mux_flags, spinlock_t *lock);
+
+/**
+ * clk_register - allocate a new clock, register it and return an opaque cookie
+ * @dev: device that is registering this clock
+ * @name: clock name
+ * @ops: operations this clock supports
+ * @hw: link to hardware-specific clock data
+ * @parent_names: array of string names for all possible parents
+ * @num_parents: number of possible parents
+ * @flags: framework-level hints and quirks
+ *
+ * clk_register is the primary interface for populating the clock tree with new
+ * clock nodes.  It returns a pointer to the newly allocated struct clk which
+ * cannot be dereferenced by driver code but may be used in conjuction with the
+ * rest of the clock API.
+ */
+struct clk *clk_register(struct device *dev, const char *name,
+		const struct clk_ops *ops, struct clk_hw *hw,
+		char **parent_names, u8 num_parents, unsigned long flags);
+
+/* helper functions */
+const char *__clk_get_name(struct clk *clk);
+struct clk_hw *__clk_get_hw(struct clk *clk);
+u8 __clk_get_num_parents(struct clk *clk);
+struct clk *__clk_get_parent(struct clk *clk);
+inline int __clk_get_enable_count(struct clk *clk);
+inline int __clk_get_prepare_count(struct clk *clk);
+unsigned long __clk_get_rate(struct clk *clk);
+unsigned long __clk_get_flags(struct clk *clk);
+int __clk_is_enabled(struct clk *clk);
+struct clk *__clk_lookup(const char *name);
+
+/*
+ * FIXME clock api without lock protection
+ */
+int __clk_prepare(struct clk *clk);
+void __clk_unprepare(struct clk *clk);
+void __clk_reparent(struct clk *clk, struct clk *new_parent);
+unsigned long __clk_round_rate(struct clk *clk, unsigned long rate);
+
+#endif /* CONFIG_COMMON_CLK */
+#endif /* CLK_PROVIDER_H */
diff --git a/include/linux/clk.h b/include/linux/clk.h
index b9d46fa154b4..b0252726df61 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -3,6 +3,7 @@
  *
  *  Copyright (C) 2004 ARM Limited.
  *  Written by Deep Blue Solutions Limited.
+ *  Copyright (C) 2011-2012 Linaro Ltd <mturquette@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -12,18 +13,75 @@
 #define __LINUX_CLK_H
 
 #include <linux/kernel.h>
+#include <linux/notifier.h>
 
 struct device;
 
-/*
- * The base API.
+struct clk;
+
+#ifdef CONFIG_COMMON_CLK
+
+/**
+ * DOC: clk notifier callback types
+ *
+ * PRE_RATE_CHANGE - called immediately before the clk rate is changed,
+ *     to indicate that the rate change will proceed.  Drivers must
+ *     immediately terminate any operations that will be affected by the
+ *     rate change.  Callbacks may either return NOTIFY_DONE or
+ *     NOTIFY_STOP.
+ *
+ * ABORT_RATE_CHANGE: called if the rate change failed for some reason
+ *     after PRE_RATE_CHANGE.  In this case, all registered notifiers on
+ *     the clk will be called with ABORT_RATE_CHANGE. Callbacks must
+ *     always return NOTIFY_DONE.
+ *
+ * POST_RATE_CHANGE - called after the clk rate change has successfully
+ *     completed.  Callbacks must always return NOTIFY_DONE.
+ *
  */
+#define PRE_RATE_CHANGE			BIT(0)
+#define POST_RATE_CHANGE		BIT(1)
+#define ABORT_RATE_CHANGE		BIT(2)
 
+/**
+ * struct clk_notifier - associate a clk with a notifier
+ * @clk: struct clk * to associate the notifier with
+ * @notifier_head: a blocking_notifier_head for this clk
+ * @node: linked list pointers
+ *
+ * A list of struct clk_notifier is maintained by the notifier code.
+ * An entry is created whenever code registers the first notifier on a
+ * particular @clk.  Future notifiers on that @clk are added to the
+ * @notifier_head.
+ */
+struct clk_notifier {
+	struct clk			*clk;
+	struct srcu_notifier_head	notifier_head;
+	struct list_head		node;
+};
 
-/*
- * struct clk - an machine class defined object / cookie.
+/**
+ * struct clk_notifier_data - rate data to pass to the notifier callback
+ * @clk: struct clk * being changed
+ * @old_rate: previous rate of this clk
+ * @new_rate: new rate of this clk
+ *
+ * For a pre-notifier, old_rate is the clk's rate before this rate
+ * change, and new_rate is what the rate will be in the future.  For a
+ * post-notifier, old_rate and new_rate are both set to the clk's
+ * current rate (this was done to optimize the implementation).
  */
-struct clk;
+struct clk_notifier_data {
+	struct clk		*clk;
+	unsigned long		old_rate;
+	unsigned long		new_rate;
+};
+
+int clk_notifier_register(struct clk *clk, struct notifier_block *nb);
+
+int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb);
+
+#endif /* !CONFIG_COMMON_CLK */
 
 /**
  * clk_get - lookup and obtain a reference to a clock producer.
diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h
index e3d8bf26e5eb..aa629bce9033 100644
--- a/include/linux/cnt32_to_63.h
+++ b/include/linux/cnt32_to_63.h
@@ -16,7 +16,6 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/byteorder.h>
-#include <asm/system.h>
 
 /* this is used only to give gcc a clue about good code generation */
 union cnt32_to_63 {
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 7e05fcee75a1..5d46217f84ad 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -19,6 +19,10 @@
 #include <asm/siginfo.h>
 #include <asm/signal.h>
 
+#ifndef COMPAT_USE_64BIT_TIME
+#define COMPAT_USE_64BIT_TIME 0
+#endif
+
 #define compat_jiffies_to_clock_t(x)	\
 		(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)
 
@@ -83,10 +87,26 @@ typedef struct {
 	compat_sigset_word	sig[_COMPAT_NSIG_WORDS];
 } compat_sigset_t;
 
+/*
+ * These functions operate strictly on struct compat_time*
+ */
 extern int get_compat_timespec(struct timespec *,
 			       const struct compat_timespec __user *);
 extern int put_compat_timespec(const struct timespec *,
 			       struct compat_timespec __user *);
+extern int get_compat_timeval(struct timeval *,
+			      const struct compat_timeval __user *);
+extern int put_compat_timeval(const struct timeval *,
+			      struct compat_timeval __user *);
+/*
+ * These functions operate on 32- or 64-bit specs depending on
+ * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments and the
+ * naming as compat_get/put_ rather than get/put_compat_.
+ */
+extern int compat_get_timespec(struct timespec *, const void __user *);
+extern int compat_put_timespec(const struct timespec *, void __user *);
+extern int compat_get_timeval(struct timeval *, const void __user *);
+extern int compat_put_timeval(const struct timeval *, void __user *);
 
 struct compat_iovec {
 	compat_uptr_t	iov_base;
@@ -224,6 +244,7 @@ struct compat_sysinfo;
 struct compat_sysctl_args;
 struct compat_kexec_segment;
 struct compat_mq_attr;
+struct compat_msgbuf;
 
 extern void compat_exit_robust_list(struct task_struct *curr);
 
@@ -234,13 +255,22 @@ asmlinkage long
 compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 			   compat_size_t __user *len_ptr);
 
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
 long compat_sys_semctl(int first, int second, int third, void __user *uptr);
 long compat_sys_msgsnd(int first, int second, int third, void __user *uptr);
 long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
 		int version, void __user *uptr);
-long compat_sys_msgctl(int first, int second, void __user *uptr);
 long compat_sys_shmat(int first, int second, compat_uptr_t third, int version,
 		void __user *uptr);
+#else
+long compat_sys_semctl(int semid, int semnum, int cmd, int arg);
+long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp,
+		size_t msgsz, int msgflg);
+long compat_sys_msgrcv(int msqid, struct compat_msgbuf __user *msgp,
+		size_t msgsz, long msgtyp, int msgflg);
+long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg);
+#endif
+long compat_sys_msgctl(int first, int second, void __user *uptr);
 long compat_sys_shmctl(int first, int second, void __user *uptr);
 long compat_sys_semtimedop(int semid, struct sembuf __user *tsems,
 		unsigned nsems, const struct compat_timespec __user *timeout);
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 712abcc205ae..6c26a3da0e03 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/kobject.h>
 #include <linux/completion.h>
+#include <linux/hrtimer.h>
 
 #define CPUIDLE_STATE_MAX	8
 #define CPUIDLE_NAME_LEN	16
@@ -43,12 +44,15 @@ struct cpuidle_state {
 
 	unsigned int	flags;
 	unsigned int	exit_latency; /* in US */
-	unsigned int	power_usage; /* in mW */
+	int		power_usage; /* in mW */
 	unsigned int	target_residency; /* in US */
+	unsigned int    disable;
 
 	int (*enter)	(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index);
+
+	int (*enter_dead) (struct cpuidle_device *dev, int index);
 };
 
 /* Idle State Flags */
@@ -96,7 +100,6 @@ struct cpuidle_device {
 	struct list_head 	device_list;
 	struct kobject		kobj;
 	struct completion	kobj_unregister;
-	void			*governor_data;
 };
 
 DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
@@ -118,10 +121,12 @@ static inline int cpuidle_get_last_residency(struct cpuidle_device *dev)
  ****************************/
 
 struct cpuidle_driver {
-	char			name[CPUIDLE_NAME_LEN];
+	const char		*name;
 	struct module 		*owner;
 
 	unsigned int		power_specified:1;
+	/* set to 1 to use the core cpuidle time keeping (for all states). */
+	unsigned int		en_core_tk_irqen:1;
 	struct cpuidle_state	states[CPUIDLE_STATE_MAX];
 	int			state_count;
 	int			safe_state_index;
@@ -140,6 +145,11 @@ extern void cpuidle_pause_and_lock(void);
 extern void cpuidle_resume_and_unlock(void);
 extern int cpuidle_enable_device(struct cpuidle_device *dev);
 extern void cpuidle_disable_device(struct cpuidle_device *dev);
+extern int cpuidle_wrap_enter(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int index,
+				int (*enter)(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index));
+extern int cpuidle_play_dead(void);
 
 #else
 static inline void disable_cpuidle(void) { }
@@ -157,6 +167,12 @@ static inline void cpuidle_resume_and_unlock(void) { }
 static inline int cpuidle_enable_device(struct cpuidle_device *dev)
 {return -ENODEV; }
 static inline void cpuidle_disable_device(struct cpuidle_device *dev) { }
+static inline int cpuidle_wrap_enter(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int index,
+				int (*enter)(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index))
+{ return -ENODEV; }
+static inline int cpuidle_play_dead(void) {return -ENODEV; }
 
 #endif
 
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 7b9b75a529be..a2c819d3c96e 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -764,12 +764,6 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
  *
  */
 #ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
-/* These strip const, as traditionally they weren't const. */
-#define cpu_possible_map	(*(cpumask_t *)cpu_possible_mask)
-#define cpu_online_map		(*(cpumask_t *)cpu_online_mask)
-#define cpu_present_map		(*(cpumask_t *)cpu_present_mask)
-#define cpu_active_map		(*(cpumask_t *)cpu_active_mask)
-
 #define cpumask_of_cpu(cpu) (*get_cpu_mask(cpu))
 
 #define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS)
@@ -810,11 +804,10 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 #else /* NR_CPUS > 1 */
 int __first_cpu(const cpumask_t *srcp);
 int __next_cpu(int n, const cpumask_t *srcp);
-int __any_online_cpu(const cpumask_t *mask);
 
 #define first_cpu(src)		__first_cpu(&(src))
 #define next_cpu(n, src)	__next_cpu((n), &(src))
-#define any_online_cpu(mask) __any_online_cpu(&(mask))
+#define any_online_cpu(mask) cpumask_any_and(&mask, cpu_online_mask)
 #define for_each_cpu_mask(cpu, mask)			\
 	for ((cpu) = -1;				\
 		(cpu) = next_cpu((cpu), (mask)),	\
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 7a7e5fd2a277..668f66baac7b 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -22,7 +22,7 @@ extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
 extern void cpuset_update_active_cpus(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
-extern int cpuset_cpus_allowed_fallback(struct task_struct *p);
+extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -135,10 +135,8 @@ static inline void cpuset_cpus_allowed(struct task_struct *p,
 	cpumask_copy(mask, cpu_possible_mask);
 }
 
-static inline int cpuset_cpus_allowed_fallback(struct task_struct *p)
+static inline void cpuset_cpus_allowed_fallback(struct task_struct *p)
 {
-	do_set_cpus_allowed(p, cpu_possible_mask);
-	return cpumask_any(cpu_active_mask);
 }
 
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
diff --git a/include/linux/cryptouser.h b/include/linux/cryptouser.h
index 532fb58f16bf..4abf2ea6a887 100644
--- a/include/linux/cryptouser.h
+++ b/include/linux/cryptouser.h
@@ -100,3 +100,6 @@ struct crypto_report_rng {
 	char type[CRYPTO_MAX_NAME];
 	unsigned int seedsize;
 };
+
+#define CRYPTO_REPORT_MAXSIZE (sizeof(struct crypto_user_alg) + \
+			       sizeof(struct crypto_report_blkcipher))
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 94f20c1488a1..3bd46f766751 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -4,7 +4,6 @@
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/bug.h>
-#include <asm/system.h>
 
 struct task_struct;
 
diff --git a/include/linux/dma-attrs.h b/include/linux/dma-attrs.h
index 71ad34eca6e3..547ab568d3ae 100644
--- a/include/linux/dma-attrs.h
+++ b/include/linux/dma-attrs.h
@@ -13,6 +13,8 @@
 enum dma_attr {
 	DMA_ATTR_WRITE_BARRIER,
 	DMA_ATTR_WEAK_ORDERING,
+	DMA_ATTR_WRITE_COMBINE,
+	DMA_ATTR_NON_CONSISTENT,
 	DMA_ATTR_MAX,
 };
 
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 887dcd487062..3efbfc2145c3 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -29,6 +29,7 @@
 #include <linux/scatterlist.h>
 #include <linux/list.h>
 #include <linux/dma-mapping.h>
+#include <linux/fs.h>
 
 struct device;
 struct dma_buf;
@@ -49,6 +50,17 @@ struct dma_buf_attachment;
  * @unmap_dma_buf: decreases usecount of buffer, might deallocate scatter
  *		   pages.
  * @release: release this buffer; to be called after the last dma_buf_put.
+ * @begin_cpu_access: [optional] called before cpu access to invalidate cpu
+ * 		      caches and allocate backing storage (if not yet done)
+ * 		      respectively pin the objet into memory.
+ * @end_cpu_access: [optional] called after cpu access to flush cashes.
+ * @kmap_atomic: maps a page from the buffer into kernel address
+ * 		 space, users may not block until the subsequent unmap call.
+ * 		 This callback must not sleep.
+ * @kunmap_atomic: [optional] unmaps a atomically mapped page from the buffer.
+ * 		   This Callback must not sleep.
+ * @kmap: maps a page from the buffer into kernel address space.
+ * @kunmap: [optional] unmaps a page from the buffer.
  */
 struct dma_buf_ops {
 	int (*attach)(struct dma_buf *, struct device *,
@@ -63,7 +75,8 @@ struct dma_buf_ops {
 	struct sg_table * (*map_dma_buf)(struct dma_buf_attachment *,
 						enum dma_data_direction);
 	void (*unmap_dma_buf)(struct dma_buf_attachment *,
-						struct sg_table *);
+						struct sg_table *,
+						enum dma_data_direction);
 	/* TODO: Add try_map_dma_buf version, to return immed with -EBUSY
 	 * if the call would block.
 	 */
@@ -71,6 +84,14 @@ struct dma_buf_ops {
 	/* after final dma_buf_put() */
 	void (*release)(struct dma_buf *);
 
+	int (*begin_cpu_access)(struct dma_buf *, size_t, size_t,
+				enum dma_data_direction);
+	void (*end_cpu_access)(struct dma_buf *, size_t, size_t,
+			       enum dma_data_direction);
+	void *(*kmap_atomic)(struct dma_buf *, unsigned long);
+	void (*kunmap_atomic)(struct dma_buf *, unsigned long, void *);
+	void *(*kmap)(struct dma_buf *, unsigned long);
+	void (*kunmap)(struct dma_buf *, unsigned long, void *);
 };
 
 /**
@@ -86,7 +107,7 @@ struct dma_buf {
 	struct file *file;
 	struct list_head attachments;
 	const struct dma_buf_ops *ops;
-	/* mutex to serialize list manipulation and other ops */
+	/* mutex to serialize list manipulation and attach/detach */
 	struct mutex lock;
 	void *priv;
 };
@@ -109,20 +130,43 @@ struct dma_buf_attachment {
 	void *priv;
 };
 
+/**
+ * get_dma_buf - convenience wrapper for get_file.
+ * @dmabuf:	[in]	pointer to dma_buf
+ *
+ * Increments the reference count on the dma-buf, needed in case of drivers
+ * that either need to create additional references to the dmabuf on the
+ * kernel side.  For example, an exporter that needs to keep a dmabuf ptr
+ * so that subsequent exports don't create a new dmabuf.
+ */
+static inline void get_dma_buf(struct dma_buf *dmabuf)
+{
+	get_file(dmabuf->file);
+}
+
 #ifdef CONFIG_DMA_SHARED_BUFFER
 struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 							struct device *dev);
 void dma_buf_detach(struct dma_buf *dmabuf,
 				struct dma_buf_attachment *dmabuf_attach);
-struct dma_buf *dma_buf_export(void *priv, struct dma_buf_ops *ops,
-			size_t size, int flags);
-int dma_buf_fd(struct dma_buf *dmabuf);
+struct dma_buf *dma_buf_export(void *priv, const struct dma_buf_ops *ops,
+			       size_t size, int flags);
+int dma_buf_fd(struct dma_buf *dmabuf, int flags);
 struct dma_buf *dma_buf_get(int fd);
 void dma_buf_put(struct dma_buf *dmabuf);
 
 struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *,
 					enum dma_data_direction);
-void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *);
+void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *,
+				enum dma_data_direction);
+int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size_t len,
+			     enum dma_data_direction dir);
+void dma_buf_end_cpu_access(struct dma_buf *dma_buf, size_t start, size_t len,
+			    enum dma_data_direction dir);
+void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long);
+void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *);
+void *dma_buf_kmap(struct dma_buf *, unsigned long);
+void dma_buf_kunmap(struct dma_buf *, unsigned long, void *);
 #else
 
 static inline struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
@@ -138,13 +182,13 @@ static inline void dma_buf_detach(struct dma_buf *dmabuf,
 }
 
 static inline struct dma_buf *dma_buf_export(void *priv,
-						struct dma_buf_ops *ops,
-						size_t size, int flags)
+					     const struct dma_buf_ops *ops,
+					     size_t size, int flags)
 {
 	return ERR_PTR(-ENODEV);
 }
 
-static inline int dma_buf_fd(struct dma_buf *dmabuf)
+static inline int dma_buf_fd(struct dma_buf *dmabuf, int flags)
 {
 	return -ENODEV;
 }
@@ -166,11 +210,44 @@ static inline struct sg_table *dma_buf_map_attachment(
 }
 
 static inline void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
-						struct sg_table *sg)
+			struct sg_table *sg, enum dma_data_direction dir)
 {
 	return;
 }
 
+static inline int dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
+					   size_t start, size_t len,
+					   enum dma_data_direction dir)
+{
+	return -ENODEV;
+}
+
+static inline void dma_buf_end_cpu_access(struct dma_buf *dmabuf,
+					  size_t start, size_t len,
+					  enum dma_data_direction dir)
+{
+}
+
+static inline void *dma_buf_kmap_atomic(struct dma_buf *dmabuf,
+					unsigned long pnum)
+{
+	return NULL;
+}
+
+static inline void dma_buf_kunmap_atomic(struct dma_buf *dmabuf,
+					 unsigned long pnum, void *vaddr)
+{
+}
+
+static inline void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long pnum)
+{
+	return NULL;
+}
+
+static inline void dma_buf_kunmap(struct dma_buf *dmabuf,
+				  unsigned long pnum, void *vaddr)
+{
+}
 #endif /* CONFIG_DMA_SHARED_BUFFER */
 
 #endif /* __DMA_BUF_H__ */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index e13117cbd2f7..dfc099e56a66 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -9,10 +9,15 @@
 #include <linux/scatterlist.h>
 
 struct dma_map_ops {
-	void* (*alloc_coherent)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t gfp);
-	void (*free_coherent)(struct device *dev, size_t size,
-			      void *vaddr, dma_addr_t dma_handle);
+	void* (*alloc)(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t gfp,
+				struct dma_attrs *attrs);
+	void (*free)(struct device *dev, size_t size,
+			      void *vaddr, dma_addr_t dma_handle,
+			      struct dma_attrs *attrs);
+	int (*mmap)(struct device *, struct vm_area_struct *,
+			  void *, dma_addr_t, size_t, struct dma_attrs *attrs);
+
 	dma_addr_t (*map_page)(struct device *dev, struct page *page,
 			       unsigned long offset, size_t size,
 			       enum dma_data_direction dir,
@@ -77,7 +82,7 @@ static inline u64 dma_get_mask(struct device *dev)
 	return DMA_BIT_MASK(32);
 }
 
-#ifdef ARCH_HAS_DMA_SET_COHERENT_MASK
+#ifdef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 #else
 static inline int dma_set_coherent_mask(struct device *dev, u64 mask)
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index a5966f691ef8..676f967390ae 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -18,14 +18,15 @@
  * The full GNU General Public License is included in this distribution in the
  * file called COPYING.
  */
-#ifndef DMAENGINE_H
-#define DMAENGINE_H
+#ifndef LINUX_DMAENGINE_H
+#define LINUX_DMAENGINE_H
 
 #include <linux/device.h>
 #include <linux/uio.h>
 #include <linux/bug.h>
 #include <linux/scatterlist.h>
 #include <linux/bitmap.h>
+#include <linux/types.h>
 #include <asm/page.h>
 
 /**
@@ -258,6 +259,7 @@ struct dma_chan_percpu {
  * struct dma_chan - devices supply DMA channels, clients use them
  * @device: ptr to the dma device who supplies this channel, always !%NULL
  * @cookie: last cookie value returned to client
+ * @completed_cookie: last completed cookie for this channel
  * @chan_id: channel ID for sysfs
  * @dev: class device for sysfs
  * @device_node: used to add this to the device chan list
@@ -269,6 +271,7 @@ struct dma_chan_percpu {
 struct dma_chan {
 	struct dma_device *device;
 	dma_cookie_t cookie;
+	dma_cookie_t completed_cookie;
 
 	/* sysfs */
 	int chan_id;
@@ -332,6 +335,9 @@ enum dma_slave_buswidth {
  * may or may not be applicable on memory sources.
  * @dst_maxburst: same as src_maxburst but for destination target
  * mutatis mutandis.
+ * @device_fc: Flow Controller Settings. Only valid for slave channels. Fill
+ * with 'true' if peripheral should be flow controller. Direction will be
+ * selected at Runtime.
  *
  * This struct is passed in as configuration data to a DMA engine
  * in order to set up a certain channel for DMA transport at runtime.
@@ -358,6 +364,7 @@ struct dma_slave_config {
 	enum dma_slave_buswidth dst_addr_width;
 	u32 src_maxburst;
 	u32 dst_maxburst;
+	bool device_fc;
 };
 
 static inline const char *dma_chan_name(struct dma_chan *chan)
@@ -576,10 +583,11 @@ struct dma_device {
 	struct dma_async_tx_descriptor *(*device_prep_slave_sg)(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags);
+		unsigned long flags, void *context);
 	struct dma_async_tx_descriptor *(*device_prep_dma_cyclic)(
 		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction);
+		size_t period_len, enum dma_transfer_direction direction,
+		void *context);
 	struct dma_async_tx_descriptor *(*device_prep_interleaved_dma)(
 		struct dma_chan *chan, struct dma_interleaved_template *xt,
 		unsigned long flags);
@@ -613,7 +621,24 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
 	struct scatterlist sg;
 	sg_init_one(&sg, buf, len);
 
-	return chan->device->device_prep_slave_sg(chan, &sg, 1, dir, flags);
+	return chan->device->device_prep_slave_sg(chan, &sg, 1,
+						  dir, flags, NULL);
+}
+
+static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl,	unsigned int sg_len,
+	enum dma_transfer_direction dir, unsigned long flags)
+{
+	return chan->device->device_prep_slave_sg(chan, sgl, sg_len,
+						  dir, flags, NULL);
+}
+
+static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+		size_t period_len, enum dma_transfer_direction dir)
+{
+	return chan->device->device_prep_dma_cyclic(chan, buf_addr, buf_len,
+						period_len, dir, NULL);
 }
 
 static inline int dmaengine_terminate_all(struct dma_chan *chan)
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index f2c64f92c4a0..2412e02d7c0f 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -31,18 +31,6 @@ struct dw_dma_platform_data {
 	unsigned char	chan_priority;
 };
 
-/**
- * enum dw_dma_slave_width - DMA slave register access width.
- * @DMA_SLAVE_WIDTH_8BIT: Do 8-bit slave register accesses
- * @DMA_SLAVE_WIDTH_16BIT: Do 16-bit slave register accesses
- * @DMA_SLAVE_WIDTH_32BIT: Do 32-bit slave register accesses
- */
-enum dw_dma_slave_width {
-	DW_DMA_SLAVE_WIDTH_8BIT,
-	DW_DMA_SLAVE_WIDTH_16BIT,
-	DW_DMA_SLAVE_WIDTH_32BIT,
-};
-
 /* bursts size */
 enum dw_dma_msize {
 	DW_DMA_MSIZE_1,
@@ -55,47 +43,21 @@ enum dw_dma_msize {
 	DW_DMA_MSIZE_256,
 };
 
-/* flow controller */
-enum dw_dma_fc {
-	DW_DMA_FC_D_M2M,
-	DW_DMA_FC_D_M2P,
-	DW_DMA_FC_D_P2M,
-	DW_DMA_FC_D_P2P,
-	DW_DMA_FC_P_P2M,
-	DW_DMA_FC_SP_P2P,
-	DW_DMA_FC_P_M2P,
-	DW_DMA_FC_DP_P2P,
-};
-
 /**
  * struct dw_dma_slave - Controller-specific information about a slave
  *
  * @dma_dev: required DMA master device
- * @tx_reg: physical address of data register used for
- *	memory-to-peripheral transfers
- * @rx_reg: physical address of data register used for
- *	peripheral-to-memory transfers
- * @reg_width: peripheral register width
  * @cfg_hi: Platform-specific initializer for the CFG_HI register
  * @cfg_lo: Platform-specific initializer for the CFG_LO register
  * @src_master: src master for transfers on allocated channel.
  * @dst_master: dest master for transfers on allocated channel.
- * @src_msize: src burst size.
- * @dst_msize: dest burst size.
- * @fc: flow controller for DMA transfer
  */
 struct dw_dma_slave {
 	struct device		*dma_dev;
-	dma_addr_t		tx_reg;
-	dma_addr_t		rx_reg;
-	enum dw_dma_slave_width	reg_width;
 	u32			cfg_hi;
 	u32			cfg_lo;
 	u8			src_master;
 	u8			dst_master;
-	u8			src_msize;
-	u8			dst_msize;
-	u8			fc;
 };
 
 /* Platform-configurable bits in CFG_HI */
diff --git a/include/linux/edac.h b/include/linux/edac.h
index ba317e2930a1..c621d762bb2c 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -70,25 +70,64 @@ enum dev_type {
 #define DEV_FLAG_X32		BIT(DEV_X32)
 #define DEV_FLAG_X64		BIT(DEV_X64)
 
-/* memory types */
+/**
+ * enum mem_type - memory types. For a more detailed reference, please see
+ *			http://en.wikipedia.org/wiki/DRAM
+ *
+ * @MEM_EMPTY		Empty csrow
+ * @MEM_RESERVED:	Reserved csrow type
+ * @MEM_UNKNOWN:	Unknown csrow type
+ * @MEM_FPM:		FPM - Fast Page Mode, used on systems up to 1995.
+ * @MEM_EDO:		EDO - Extended data out, used on systems up to 1998.
+ * @MEM_BEDO:		BEDO - Burst Extended data out, an EDO variant.
+ * @MEM_SDR:		SDR - Single data rate SDRAM
+ *			http://en.wikipedia.org/wiki/Synchronous_dynamic_random-access_memory
+ *			They use 3 pins for chip select: Pins 0 and 2 are
+ *			for rank 0; pins 1 and 3 are for rank 1, if the memory
+ *			is dual-rank.
+ * @MEM_RDR:		Registered SDR SDRAM
+ * @MEM_DDR:		Double data rate SDRAM
+ *			http://en.wikipedia.org/wiki/DDR_SDRAM
+ * @MEM_RDDR:		Registered Double data rate SDRAM
+ *			This is a variant of the DDR memories.
+ *			A registered memory has a buffer inside it, hiding
+ *			part of the memory details to the memory controller.
+ * @MEM_RMBS:		Rambus DRAM, used on a few Pentium III/IV controllers.
+ * @MEM_DDR2:		DDR2 RAM, as described at JEDEC JESD79-2F.
+ *			Those memories are labed as "PC2-" instead of "PC" to
+ *			differenciate from DDR.
+ * @MEM_FB_DDR2:	Fully-Buffered DDR2, as described at JEDEC Std No. 205
+ *			and JESD206.
+ *			Those memories are accessed per DIMM slot, and not by
+ *			a chip select signal.
+ * @MEM_RDDR2:		Registered DDR2 RAM
+ *			This is a variant of the DDR2 memories.
+ * @MEM_XDR:		Rambus XDR
+ *			It is an evolution of the original RAMBUS memories,
+ *			created to compete with DDR2. Weren't used on any
+ *			x86 arch, but cell_edac PPC memory controller uses it.
+ * @MEM_DDR3:		DDR3 RAM
+ * @MEM_RDDR3:		Registered DDR3 RAM
+ *			This is a variant of the DDR3 memories.
+ */
 enum mem_type {
-	MEM_EMPTY = 0,		/* Empty csrow */
-	MEM_RESERVED,		/* Reserved csrow type */
-	MEM_UNKNOWN,		/* Unknown csrow type */
-	MEM_FPM,		/* Fast page mode */
-	MEM_EDO,		/* Extended data out */
-	MEM_BEDO,		/* Burst Extended data out */
-	MEM_SDR,		/* Single data rate SDRAM */
-	MEM_RDR,		/* Registered single data rate SDRAM */
-	MEM_DDR,		/* Double data rate SDRAM */
-	MEM_RDDR,		/* Registered Double data rate SDRAM */
-	MEM_RMBS,		/* Rambus DRAM */
-	MEM_DDR2,		/* DDR2 RAM */
-	MEM_FB_DDR2,		/* fully buffered DDR2 */
-	MEM_RDDR2,		/* Registered DDR2 RAM */
-	MEM_XDR,		/* Rambus XDR */
-	MEM_DDR3,		/* DDR3 RAM */
-	MEM_RDDR3,		/* Registered DDR3 RAM */
+	MEM_EMPTY = 0,
+	MEM_RESERVED,
+	MEM_UNKNOWN,
+	MEM_FPM,
+	MEM_EDO,
+	MEM_BEDO,
+	MEM_SDR,
+	MEM_RDR,
+	MEM_DDR,
+	MEM_RDDR,
+	MEM_RMBS,
+	MEM_DDR2,
+	MEM_FB_DDR2,
+	MEM_RDDR2,
+	MEM_XDR,
+	MEM_DDR3,
+	MEM_RDDR3,
 };
 
 #define MEM_FLAG_EMPTY		BIT(MEM_EMPTY)
@@ -166,8 +205,9 @@ enum scrub_type {
 #define OP_OFFLINE		0x300
 
 /*
- * There are several things to be aware of that aren't at all obvious:
+ * Concepts used at the EDAC subsystem
  *
+ * There are several things to be aware of that aren't at all obvious:
  *
  * SOCKETS, SOCKET SETS, BANKS, ROWS, CHIP-SELECT ROWS, CHANNELS, etc..
  *
@@ -176,36 +216,61 @@ enum scrub_type {
  * creating a common ground for discussion, terms and their definitions
  * will be established.
  *
- * Memory devices:	The individual chip on a memory stick.  These devices
- *			commonly output 4 and 8 bits each.  Grouping several
- *			of these in parallel provides 64 bits which is common
- *			for a memory stick.
+ * Memory devices:	The individual DRAM chips on a memory stick.  These
+ *			devices commonly output 4 and 8 bits each (x4, x8).
+ *			Grouping several of these in parallel provides the
+ *			number of bits that the memory controller expects:
+ *			typically 72 bits, in order to provide 64 bits +
+ *			8 bits of ECC data.
  *
  * Memory Stick:	A printed circuit board that aggregates multiple
- *			memory devices in parallel.  This is the atomic
- *			memory component that is purchaseable by Joe consumer
- *			and loaded into a memory socket.
+ *			memory devices in parallel.  In general, this is the
+ *			Field Replaceable Unit (FRU) which gets replaced, in
+ *			the case of excessive errors. Most often it is also
+ *			called DIMM (Dual Inline Memory Module).
+ *
+ * Memory Socket:	A physical connector on the motherboard that accepts
+ *			a single memory stick. Also called as "slot" on several
+ *			datasheets.
  *
- * Socket:		A physical connector on the motherboard that accepts
- *			a single memory stick.
+ * Channel:		A memory controller channel, responsible to communicate
+ *			with a group of DIMMs. Each channel has its own
+ *			independent control (command) and data bus, and can
+ *			be used independently or grouped with other channels.
  *
- * Channel:		Set of memory devices on a memory stick that must be
- *			grouped in parallel with one or more additional
- *			channels from other memory sticks.  This parallel
- *			grouping of the output from multiple channels are
- *			necessary for the smallest granularity of memory access.
- *			Some memory controllers are capable of single channel -
- *			which means that memory sticks can be loaded
- *			individually.  Other memory controllers are only
- *			capable of dual channel - which means that memory
- *			sticks must be loaded as pairs (see "socket set").
+ * Branch:		It is typically the highest hierarchy on a
+ *			Fully-Buffered DIMM memory controller.
+ *			Typically, it contains two channels.
+ *			Two channels at the same branch can be used in single
+ *			mode or in lockstep mode.
+ *			When lockstep is enabled, the cacheline is doubled,
+ *			but it generally brings some performance penalty.
+ *			Also, it is generally not possible to point to just one
+ *			memory stick when an error occurs, as the error
+ *			correction code is calculated using two DIMMs instead
+ *			of one. Due to that, it is capable of correcting more
+ *			errors than on single mode.
  *
- * Chip-select row:	All of the memory devices that are selected together.
- *			for a single, minimum grain of memory access.
- *			This selects all of the parallel memory devices across
- *			all of the parallel channels.  Common chip-select rows
- *			for single channel are 64 bits, for dual channel 128
- *			bits.
+ * Single-channel:	The data accessed by the memory controller is contained
+ *			into one dimm only. E. g. if the data is 64 bits-wide,
+ *			the data flows to the CPU using one 64 bits parallel
+ *			access.
+ *			Typically used with SDR, DDR, DDR2 and DDR3 memories.
+ *			FB-DIMM and RAMBUS use a different concept for channel,
+ *			so this concept doesn't apply there.
+ *
+ * Double-channel:	The data size accessed by the memory controller is
+ *			interlaced into two dimms, accessed at the same time.
+ *			E. g. if the DIMM is 64 bits-wide (72 bits with ECC),
+ *			the data flows to the CPU using a 128 bits parallel
+ *			access.
+ *
+ * Chip-select row:	This is the name of the DRAM signal used to select the
+ *			DRAM ranks to be accessed. Common chip-select rows for
+ *			single channel are 64 bits, for dual channel 128 bits.
+ *			It may not be visible by the memory controller, as some
+ *			DIMM types have a memory buffer that can hide direct
+ *			access to it from the Memory Controller.
  *
  * Single-Ranked stick:	A Single-ranked stick has 1 chip-select row of memory.
  *			Motherboards commonly drive two chip-select pins to
@@ -218,8 +283,8 @@ enum scrub_type {
  *
  * Double-sided stick:	DEPRECATED TERM, see Double-Ranked stick.
  *			A double-sided stick has two chip-select rows which
- *			access different sets of memory devices.  The two
- *			rows cannot be accessed concurrently.  "Double-sided"
+ *			access different sets of memory devices. The two
+ *			rows cannot be accessed concurrently. "Double-sided"
  *			is irrespective of the memory devices being mounted
  *			on both sides of the memory stick.
  *
@@ -247,10 +312,22 @@ enum scrub_type {
  * PS - I enjoyed writing all that about as much as you enjoyed reading it.
  */
 
-struct channel_info {
-	int chan_idx;		/* channel index */
-	u32 ce_count;		/* Correctable Errors for this CHANNEL */
-	char label[EDAC_MC_LABEL_LEN + 1];	/* DIMM label on motherboard */
+/**
+ * struct rank_info - contains the information for one DIMM rank
+ *
+ * @chan_idx:	channel number where the rank is (typically, 0 or 1)
+ * @ce_count:	number of correctable errors for this rank
+ * @label:	DIMM label. Different ranks for the same DIMM should be
+ *		filled, on userspace, with the same label.
+ *		FIXME: The core currently won't enforce it.
+ * @csrow:	A pointer to the chip select row structure (the parent
+ *		structure). The location of the rank is given by
+ *		the (csrow->csrow_idx, chan_idx) vector.
+ */
+struct rank_info {
+	int chan_idx;
+	u32 ce_count;
+	char label[EDAC_MC_LABEL_LEN + 1];
 	struct csrow_info *csrow;	/* the parent */
 };
 
@@ -274,7 +351,7 @@ struct csrow_info {
 
 	/* channel information for this csrow */
 	u32 nr_channels;
-	struct channel_info *channels;
+	struct rank_info *channels;
 };
 
 struct mcidev_sysfs_group {
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 47fbf6b3dc77..88ec80670d5f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -22,7 +22,6 @@
 #include <linux/pstore.h>
 
 #include <asm/page.h>
-#include <asm/system.h>
 
 #define EFI_SUCCESS		0
 #define EFI_LOAD_ERROR          ( 1 | (1UL << (BITS_PER_LONG-1)))
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 560a247bde2a..89d68d837b6e 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -923,8 +923,7 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
  *
  * All operations are optional (i.e. the function pointer may be set
  * to %NULL) and callers must take this into account.  Callers must
- * hold the RTNL, except that for @get_drvinfo the caller may or may
- * not hold the RTNL.
+ * hold the RTNL lock.
  *
  * See the structures used by these operations for further documentation.
  *
diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h
index ce1b719e8bd4..2723e715f67a 100644
--- a/include/linux/ext2_fs.h
+++ b/include/linux/ext2_fs.h
@@ -18,574 +18,25 @@
 
 #include <linux/types.h>
 #include <linux/magic.h>
-#include <linux/fs.h>
 
-/*
- * The second extended filesystem constants/structures
- */
-
-/*
- * Define EXT2FS_DEBUG to produce debug messages
- */
-#undef EXT2FS_DEBUG
-
-/*
- * Define EXT2_RESERVATION to reserve data blocks for expanding files
- */
-#define EXT2_DEFAULT_RESERVE_BLOCKS     8
-/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
-#define EXT2_MAX_RESERVE_BLOCKS         1027
-#define EXT2_RESERVE_WINDOW_NOT_ALLOCATED 0
-/*
- * The second extended file system version
- */
-#define EXT2FS_DATE		"95/08/09"
-#define EXT2FS_VERSION		"0.5b"
-
-/*
- * Debug code
- */
-#ifdef EXT2FS_DEBUG
-#	define ext2_debug(f, a...)	{ \
-					printk ("EXT2-fs DEBUG (%s, %d): %s:", \
-						__FILE__, __LINE__, __func__); \
-				  	printk (f, ## a); \
-					}
-#else
-#	define ext2_debug(f, a...)	/**/
-#endif
-
-/*
- * Special inode numbers
- */
-#define	EXT2_BAD_INO		 1	/* Bad blocks inode */
-#define EXT2_ROOT_INO		 2	/* Root inode */
-#define EXT2_BOOT_LOADER_INO	 5	/* Boot loader inode */
-#define EXT2_UNDEL_DIR_INO	 6	/* Undelete directory inode */
-
-/* First non-reserved inode for old ext2 filesystems */
-#define EXT2_GOOD_OLD_FIRST_INO	11
-
-#ifdef __KERNEL__
-#include <linux/ext2_fs_sb.h>
-static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
-{
-	return sb->s_fs_info;
-}
-#else
-/* Assume that user mode programs are passing in an ext2fs superblock, not
- * a kernel struct super_block.  This will allow us to call the feature-test
- * macros from user land. */
-#define EXT2_SB(sb)	(sb)
-#endif
+#define EXT2_NAME_LEN 255
 
 /*
  * Maximal count of links to a file
  */
 #define EXT2_LINK_MAX		32000
 
-/*
- * Macro-instructions used to manage several block sizes
- */
-#define EXT2_MIN_BLOCK_SIZE		1024
-#define	EXT2_MAX_BLOCK_SIZE		4096
-#define EXT2_MIN_BLOCK_LOG_SIZE		  10
-#ifdef __KERNEL__
-# define EXT2_BLOCK_SIZE(s)		((s)->s_blocksize)
-#else
-# define EXT2_BLOCK_SIZE(s)		(EXT2_MIN_BLOCK_SIZE << (s)->s_log_block_size)
-#endif
-#define	EXT2_ADDR_PER_BLOCK(s)		(EXT2_BLOCK_SIZE(s) / sizeof (__u32))
-#ifdef __KERNEL__
-# define EXT2_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
-#else
-# define EXT2_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
-#endif
-#ifdef __KERNEL__
-#define	EXT2_ADDR_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_addr_per_block_bits)
-#define EXT2_INODE_SIZE(s)		(EXT2_SB(s)->s_inode_size)
-#define EXT2_FIRST_INO(s)		(EXT2_SB(s)->s_first_ino)
-#else
-#define EXT2_INODE_SIZE(s)	(((s)->s_rev_level == EXT2_GOOD_OLD_REV) ? \
-				 EXT2_GOOD_OLD_INODE_SIZE : \
-				 (s)->s_inode_size)
-#define EXT2_FIRST_INO(s)	(((s)->s_rev_level == EXT2_GOOD_OLD_REV) ? \
-				 EXT2_GOOD_OLD_FIRST_INO : \
-				 (s)->s_first_ino)
-#endif
+#define EXT2_SB_MAGIC_OFFSET	0x38
+#define EXT2_SB_BLOCKS_OFFSET	0x04
+#define EXT2_SB_BSIZE_OFFSET	0x18
 
-/*
- * Macro-instructions used to manage fragments
- */
-#define EXT2_MIN_FRAG_SIZE		1024
-#define	EXT2_MAX_FRAG_SIZE		4096
-#define EXT2_MIN_FRAG_LOG_SIZE		  10
-#ifdef __KERNEL__
-# define EXT2_FRAG_SIZE(s)		(EXT2_SB(s)->s_frag_size)
-# define EXT2_FRAGS_PER_BLOCK(s)	(EXT2_SB(s)->s_frags_per_block)
-#else
-# define EXT2_FRAG_SIZE(s)		(EXT2_MIN_FRAG_SIZE << (s)->s_log_frag_size)
-# define EXT2_FRAGS_PER_BLOCK(s)	(EXT2_BLOCK_SIZE(s) / EXT2_FRAG_SIZE(s))
-#endif
-
-/*
- * Structure of a blocks group descriptor
- */
-struct ext2_group_desc
+static inline u64 ext2_image_size(void *ext2_sb)
 {
-	__le32	bg_block_bitmap;		/* Blocks bitmap block */
-	__le32	bg_inode_bitmap;		/* Inodes bitmap block */
-	__le32	bg_inode_table;		/* Inodes table block */
-	__le16	bg_free_blocks_count;	/* Free blocks count */
-	__le16	bg_free_inodes_count;	/* Free inodes count */
-	__le16	bg_used_dirs_count;	/* Directories count */
-	__le16	bg_pad;
-	__le32	bg_reserved[3];
-};
-
-/*
- * Macro-instructions used to manage group descriptors
- */
-#ifdef __KERNEL__
-# define EXT2_BLOCKS_PER_GROUP(s)	(EXT2_SB(s)->s_blocks_per_group)
-# define EXT2_DESC_PER_BLOCK(s)		(EXT2_SB(s)->s_desc_per_block)
-# define EXT2_INODES_PER_GROUP(s)	(EXT2_SB(s)->s_inodes_per_group)
-# define EXT2_DESC_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_desc_per_block_bits)
-#else
-# define EXT2_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
-# define EXT2_DESC_PER_BLOCK(s)		(EXT2_BLOCK_SIZE(s) / sizeof (struct ext2_group_desc))
-# define EXT2_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
-#endif
-
-/*
- * Constants relative to the data blocks
- */
-#define	EXT2_NDIR_BLOCKS		12
-#define	EXT2_IND_BLOCK			EXT2_NDIR_BLOCKS
-#define	EXT2_DIND_BLOCK			(EXT2_IND_BLOCK + 1)
-#define	EXT2_TIND_BLOCK			(EXT2_DIND_BLOCK + 1)
-#define	EXT2_N_BLOCKS			(EXT2_TIND_BLOCK + 1)
-
-/*
- * Inode flags (GETFLAGS/SETFLAGS)
- */
-#define	EXT2_SECRM_FL			FS_SECRM_FL	/* Secure deletion */
-#define	EXT2_UNRM_FL			FS_UNRM_FL	/* Undelete */
-#define	EXT2_COMPR_FL			FS_COMPR_FL	/* Compress file */
-#define EXT2_SYNC_FL			FS_SYNC_FL	/* Synchronous updates */
-#define EXT2_IMMUTABLE_FL		FS_IMMUTABLE_FL	/* Immutable file */
-#define EXT2_APPEND_FL			FS_APPEND_FL	/* writes to file may only append */
-#define EXT2_NODUMP_FL			FS_NODUMP_FL	/* do not dump file */
-#define EXT2_NOATIME_FL			FS_NOATIME_FL	/* do not update atime */
-/* Reserved for compression usage... */
-#define EXT2_DIRTY_FL			FS_DIRTY_FL
-#define EXT2_COMPRBLK_FL		FS_COMPRBLK_FL	/* One or more compressed clusters */
-#define EXT2_NOCOMP_FL			FS_NOCOMP_FL	/* Don't compress */
-#define EXT2_ECOMPR_FL			FS_ECOMPR_FL	/* Compression error */
-/* End compression flags --- maybe not all used */	
-#define EXT2_BTREE_FL			FS_BTREE_FL	/* btree format dir */
-#define EXT2_INDEX_FL			FS_INDEX_FL	/* hash-indexed directory */
-#define EXT2_IMAGIC_FL			FS_IMAGIC_FL	/* AFS directory */
-#define EXT2_JOURNAL_DATA_FL		FS_JOURNAL_DATA_FL /* Reserved for ext3 */
-#define EXT2_NOTAIL_FL			FS_NOTAIL_FL	/* file tail should not be merged */
-#define EXT2_DIRSYNC_FL			FS_DIRSYNC_FL	/* dirsync behaviour (directories only) */
-#define EXT2_TOPDIR_FL			FS_TOPDIR_FL	/* Top of directory hierarchies*/
-#define EXT2_RESERVED_FL		FS_RESERVED_FL	/* reserved for ext2 lib */
-
-#define EXT2_FL_USER_VISIBLE		FS_FL_USER_VISIBLE	/* User visible flags */
-#define EXT2_FL_USER_MODIFIABLE		FS_FL_USER_MODIFIABLE	/* User modifiable flags */
-
-/* Flags that should be inherited by new inodes from their parent. */
-#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
-			   EXT2_SYNC_FL | EXT2_NODUMP_FL |\
-			   EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
-			   EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
-			   EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
-
-/* Flags that are appropriate for regular files (all but dir-specific ones). */
-#define EXT2_REG_FLMASK (~(EXT2_DIRSYNC_FL | EXT2_TOPDIR_FL))
-
-/* Flags that are appropriate for non-directories/regular files. */
-#define EXT2_OTHER_FLMASK (EXT2_NODUMP_FL | EXT2_NOATIME_FL)
-
-/* Mask out flags that are inappropriate for the given type of inode. */
-static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
-{
-	if (S_ISDIR(mode))
-		return flags;
-	else if (S_ISREG(mode))
-		return flags & EXT2_REG_FLMASK;
-	else
-		return flags & EXT2_OTHER_FLMASK;
+	__u8 *p = ext2_sb;
+	if (*(__le16 *)(p + EXT2_SB_MAGIC_OFFSET) != cpu_to_le16(EXT2_SUPER_MAGIC))
+		return 0;
+	return (u64)le32_to_cpup((__le32 *)(p + EXT2_SB_BLOCKS_OFFSET)) <<
+		le32_to_cpup((__le32 *)(p + EXT2_SB_BSIZE_OFFSET));
 }
 
-/*
- * ioctl commands
- */
-#define	EXT2_IOC_GETFLAGS		FS_IOC_GETFLAGS
-#define	EXT2_IOC_SETFLAGS		FS_IOC_SETFLAGS
-#define	EXT2_IOC_GETVERSION		FS_IOC_GETVERSION
-#define	EXT2_IOC_SETVERSION		FS_IOC_SETVERSION
-#define	EXT2_IOC_GETRSVSZ		_IOR('f', 5, long)
-#define	EXT2_IOC_SETRSVSZ		_IOW('f', 6, long)
-
-/*
- * ioctl commands in 32 bit emulation
- */
-#define EXT2_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
-#define EXT2_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
-#define EXT2_IOC32_GETVERSION		FS_IOC32_GETVERSION
-#define EXT2_IOC32_SETVERSION		FS_IOC32_SETVERSION
-
-/*
- * Structure of an inode on the disk
- */
-struct ext2_inode {
-	__le16	i_mode;		/* File mode */
-	__le16	i_uid;		/* Low 16 bits of Owner Uid */
-	__le32	i_size;		/* Size in bytes */
-	__le32	i_atime;	/* Access time */
-	__le32	i_ctime;	/* Creation time */
-	__le32	i_mtime;	/* Modification time */
-	__le32	i_dtime;	/* Deletion Time */
-	__le16	i_gid;		/* Low 16 bits of Group Id */
-	__le16	i_links_count;	/* Links count */
-	__le32	i_blocks;	/* Blocks count */
-	__le32	i_flags;	/* File flags */
-	union {
-		struct {
-			__le32  l_i_reserved1;
-		} linux1;
-		struct {
-			__le32  h_i_translator;
-		} hurd1;
-		struct {
-			__le32  m_i_reserved1;
-		} masix1;
-	} osd1;				/* OS dependent 1 */
-	__le32	i_block[EXT2_N_BLOCKS];/* Pointers to blocks */
-	__le32	i_generation;	/* File version (for NFS) */
-	__le32	i_file_acl;	/* File ACL */
-	__le32	i_dir_acl;	/* Directory ACL */
-	__le32	i_faddr;	/* Fragment address */
-	union {
-		struct {
-			__u8	l_i_frag;	/* Fragment number */
-			__u8	l_i_fsize;	/* Fragment size */
-			__u16	i_pad1;
-			__le16	l_i_uid_high;	/* these 2 fields    */
-			__le16	l_i_gid_high;	/* were reserved2[0] */
-			__u32	l_i_reserved2;
-		} linux2;
-		struct {
-			__u8	h_i_frag;	/* Fragment number */
-			__u8	h_i_fsize;	/* Fragment size */
-			__le16	h_i_mode_high;
-			__le16	h_i_uid_high;
-			__le16	h_i_gid_high;
-			__le32	h_i_author;
-		} hurd2;
-		struct {
-			__u8	m_i_frag;	/* Fragment number */
-			__u8	m_i_fsize;	/* Fragment size */
-			__u16	m_pad1;
-			__u32	m_i_reserved2[2];
-		} masix2;
-	} osd2;				/* OS dependent 2 */
-};
-
-#define i_size_high	i_dir_acl
-
-#if defined(__KERNEL__) || defined(__linux__)
-#define i_reserved1	osd1.linux1.l_i_reserved1
-#define i_frag		osd2.linux2.l_i_frag
-#define i_fsize		osd2.linux2.l_i_fsize
-#define i_uid_low	i_uid
-#define i_gid_low	i_gid
-#define i_uid_high	osd2.linux2.l_i_uid_high
-#define i_gid_high	osd2.linux2.l_i_gid_high
-#define i_reserved2	osd2.linux2.l_i_reserved2
-#endif
-
-#ifdef	__hurd__
-#define i_translator	osd1.hurd1.h_i_translator
-#define i_frag		osd2.hurd2.h_i_frag
-#define i_fsize		osd2.hurd2.h_i_fsize
-#define i_uid_high	osd2.hurd2.h_i_uid_high
-#define i_gid_high	osd2.hurd2.h_i_gid_high
-#define i_author	osd2.hurd2.h_i_author
-#endif
-
-#ifdef	__masix__
-#define i_reserved1	osd1.masix1.m_i_reserved1
-#define i_frag		osd2.masix2.m_i_frag
-#define i_fsize		osd2.masix2.m_i_fsize
-#define i_reserved2	osd2.masix2.m_i_reserved2
-#endif
-
-/*
- * File system states
- */
-#define	EXT2_VALID_FS			0x0001	/* Unmounted cleanly */
-#define	EXT2_ERROR_FS			0x0002	/* Errors detected */
-
-/*
- * Mount flags
- */
-#define EXT2_MOUNT_CHECK		0x000001  /* Do mount-time checks */
-#define EXT2_MOUNT_OLDALLOC		0x000002  /* Don't use the new Orlov allocator */
-#define EXT2_MOUNT_GRPID		0x000004  /* Create files with directory's group */
-#define EXT2_MOUNT_DEBUG		0x000008  /* Some debugging messages */
-#define EXT2_MOUNT_ERRORS_CONT		0x000010  /* Continue on errors */
-#define EXT2_MOUNT_ERRORS_RO		0x000020  /* Remount fs ro on errors */
-#define EXT2_MOUNT_ERRORS_PANIC		0x000040  /* Panic on errors */
-#define EXT2_MOUNT_MINIX_DF		0x000080  /* Mimics the Minix statfs */
-#define EXT2_MOUNT_NOBH			0x000100  /* No buffer_heads */
-#define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
-#define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
-#define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
-#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
-#define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
-#define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
-#define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */
-
-
-#define clear_opt(o, opt)		o &= ~EXT2_MOUNT_##opt
-#define set_opt(o, opt)			o |= EXT2_MOUNT_##opt
-#define test_opt(sb, opt)		(EXT2_SB(sb)->s_mount_opt & \
-					 EXT2_MOUNT_##opt)
-/*
- * Maximal mount counts between two filesystem checks
- */
-#define EXT2_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
-#define EXT2_DFL_CHECKINTERVAL		0	/* Don't use interval check */
-
-/*
- * Behaviour when detecting errors
- */
-#define EXT2_ERRORS_CONTINUE		1	/* Continue execution */
-#define EXT2_ERRORS_RO			2	/* Remount fs read-only */
-#define EXT2_ERRORS_PANIC		3	/* Panic */
-#define EXT2_ERRORS_DEFAULT		EXT2_ERRORS_CONTINUE
-
-/*
- * Structure of the super block
- */
-struct ext2_super_block {
-	__le32	s_inodes_count;		/* Inodes count */
-	__le32	s_blocks_count;		/* Blocks count */
-	__le32	s_r_blocks_count;	/* Reserved blocks count */
-	__le32	s_free_blocks_count;	/* Free blocks count */
-	__le32	s_free_inodes_count;	/* Free inodes count */
-	__le32	s_first_data_block;	/* First Data Block */
-	__le32	s_log_block_size;	/* Block size */
-	__le32	s_log_frag_size;	/* Fragment size */
-	__le32	s_blocks_per_group;	/* # Blocks per group */
-	__le32	s_frags_per_group;	/* # Fragments per group */
-	__le32	s_inodes_per_group;	/* # Inodes per group */
-	__le32	s_mtime;		/* Mount time */
-	__le32	s_wtime;		/* Write time */
-	__le16	s_mnt_count;		/* Mount count */
-	__le16	s_max_mnt_count;	/* Maximal mount count */
-	__le16	s_magic;		/* Magic signature */
-	__le16	s_state;		/* File system state */
-	__le16	s_errors;		/* Behaviour when detecting errors */
-	__le16	s_minor_rev_level; 	/* minor revision level */
-	__le32	s_lastcheck;		/* time of last check */
-	__le32	s_checkinterval;	/* max. time between checks */
-	__le32	s_creator_os;		/* OS */
-	__le32	s_rev_level;		/* Revision level */
-	__le16	s_def_resuid;		/* Default uid for reserved blocks */
-	__le16	s_def_resgid;		/* Default gid for reserved blocks */
-	/*
-	 * These fields are for EXT2_DYNAMIC_REV superblocks only.
-	 *
-	 * Note: the difference between the compatible feature set and
-	 * the incompatible feature set is that if there is a bit set
-	 * in the incompatible feature set that the kernel doesn't
-	 * know about, it should refuse to mount the filesystem.
-	 * 
-	 * e2fsck's requirements are more strict; if it doesn't know
-	 * about a feature in either the compatible or incompatible
-	 * feature set, it must abort and not try to meddle with
-	 * things it doesn't understand...
-	 */
-	__le32	s_first_ino; 		/* First non-reserved inode */
-	__le16   s_inode_size; 		/* size of inode structure */
-	__le16	s_block_group_nr; 	/* block group # of this superblock */
-	__le32	s_feature_compat; 	/* compatible feature set */
-	__le32	s_feature_incompat; 	/* incompatible feature set */
-	__le32	s_feature_ro_compat; 	/* readonly-compatible feature set */
-	__u8	s_uuid[16];		/* 128-bit uuid for volume */
-	char	s_volume_name[16]; 	/* volume name */
-	char	s_last_mounted[64]; 	/* directory where last mounted */
-	__le32	s_algorithm_usage_bitmap; /* For compression */
-	/*
-	 * Performance hints.  Directory preallocation should only
-	 * happen if the EXT2_COMPAT_PREALLOC flag is on.
-	 */
-	__u8	s_prealloc_blocks;	/* Nr of blocks to try to preallocate*/
-	__u8	s_prealloc_dir_blocks;	/* Nr to preallocate for dirs */
-	__u16	s_padding1;
-	/*
-	 * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set.
-	 */
-	__u8	s_journal_uuid[16];	/* uuid of journal superblock */
-	__u32	s_journal_inum;		/* inode number of journal file */
-	__u32	s_journal_dev;		/* device number of journal file */
-	__u32	s_last_orphan;		/* start of list of inodes to delete */
-	__u32	s_hash_seed[4];		/* HTREE hash seed */
-	__u8	s_def_hash_version;	/* Default hash version to use */
-	__u8	s_reserved_char_pad;
-	__u16	s_reserved_word_pad;
-	__le32	s_default_mount_opts;
- 	__le32	s_first_meta_bg; 	/* First metablock block group */
-	__u32	s_reserved[190];	/* Padding to the end of the block */
-};
-
-/*
- * Codes for operating systems
- */
-#define EXT2_OS_LINUX		0
-#define EXT2_OS_HURD		1
-#define EXT2_OS_MASIX		2
-#define EXT2_OS_FREEBSD		3
-#define EXT2_OS_LITES		4
-
-/*
- * Revision levels
- */
-#define EXT2_GOOD_OLD_REV	0	/* The good old (original) format */
-#define EXT2_DYNAMIC_REV	1 	/* V2 format w/ dynamic inode sizes */
-
-#define EXT2_CURRENT_REV	EXT2_GOOD_OLD_REV
-#define EXT2_MAX_SUPP_REV	EXT2_DYNAMIC_REV
-
-#define EXT2_GOOD_OLD_INODE_SIZE 128
-
-/*
- * Feature set definitions
- */
-
-#define EXT2_HAS_COMPAT_FEATURE(sb,mask)			\
-	( EXT2_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
-#define EXT2_HAS_RO_COMPAT_FEATURE(sb,mask)			\
-	( EXT2_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
-#define EXT2_HAS_INCOMPAT_FEATURE(sb,mask)			\
-	( EXT2_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
-#define EXT2_SET_COMPAT_FEATURE(sb,mask)			\
-	EXT2_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
-#define EXT2_SET_RO_COMPAT_FEATURE(sb,mask)			\
-	EXT2_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
-#define EXT2_SET_INCOMPAT_FEATURE(sb,mask)			\
-	EXT2_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
-#define EXT2_CLEAR_COMPAT_FEATURE(sb,mask)			\
-	EXT2_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
-#define EXT2_CLEAR_RO_COMPAT_FEATURE(sb,mask)			\
-	EXT2_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
-#define EXT2_CLEAR_INCOMPAT_FEATURE(sb,mask)			\
-	EXT2_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
-
-#define EXT2_FEATURE_COMPAT_DIR_PREALLOC	0x0001
-#define EXT2_FEATURE_COMPAT_IMAGIC_INODES	0x0002
-#define EXT3_FEATURE_COMPAT_HAS_JOURNAL		0x0004
-#define EXT2_FEATURE_COMPAT_EXT_ATTR		0x0008
-#define EXT2_FEATURE_COMPAT_RESIZE_INO		0x0010
-#define EXT2_FEATURE_COMPAT_DIR_INDEX		0x0020
-#define EXT2_FEATURE_COMPAT_ANY			0xffffffff
-
-#define EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
-#define EXT2_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
-#define EXT2_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
-#define EXT2_FEATURE_RO_COMPAT_ANY		0xffffffff
-
-#define EXT2_FEATURE_INCOMPAT_COMPRESSION	0x0001
-#define EXT2_FEATURE_INCOMPAT_FILETYPE		0x0002
-#define EXT3_FEATURE_INCOMPAT_RECOVER		0x0004
-#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV	0x0008
-#define EXT2_FEATURE_INCOMPAT_META_BG		0x0010
-#define EXT2_FEATURE_INCOMPAT_ANY		0xffffffff
-
-#define EXT2_FEATURE_COMPAT_SUPP	EXT2_FEATURE_COMPAT_EXT_ATTR
-#define EXT2_FEATURE_INCOMPAT_SUPP	(EXT2_FEATURE_INCOMPAT_FILETYPE| \
-					 EXT2_FEATURE_INCOMPAT_META_BG)
-#define EXT2_FEATURE_RO_COMPAT_SUPP	(EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER| \
-					 EXT2_FEATURE_RO_COMPAT_LARGE_FILE| \
-					 EXT2_FEATURE_RO_COMPAT_BTREE_DIR)
-#define EXT2_FEATURE_RO_COMPAT_UNSUPPORTED	~EXT2_FEATURE_RO_COMPAT_SUPP
-#define EXT2_FEATURE_INCOMPAT_UNSUPPORTED	~EXT2_FEATURE_INCOMPAT_SUPP
-
-/*
- * Default values for user and/or group using reserved blocks
- */
-#define	EXT2_DEF_RESUID		0
-#define	EXT2_DEF_RESGID		0
-
-/*
- * Default mount options
- */
-#define EXT2_DEFM_DEBUG		0x0001
-#define EXT2_DEFM_BSDGROUPS	0x0002
-#define EXT2_DEFM_XATTR_USER	0x0004
-#define EXT2_DEFM_ACL		0x0008
-#define EXT2_DEFM_UID16		0x0010
-    /* Not used by ext2, but reserved for use by ext3 */
-#define EXT3_DEFM_JMODE		0x0060 
-#define EXT3_DEFM_JMODE_DATA	0x0020
-#define EXT3_DEFM_JMODE_ORDERED	0x0040
-#define EXT3_DEFM_JMODE_WBACK	0x0060
-
-/*
- * Structure of a directory entry
- */
-#define EXT2_NAME_LEN 255
-
-struct ext2_dir_entry {
-	__le32	inode;			/* Inode number */
-	__le16	rec_len;		/* Directory entry length */
-	__le16	name_len;		/* Name length */
-	char	name[EXT2_NAME_LEN];	/* File name */
-};
-
-/*
- * The new version of the directory entry.  Since EXT2 structures are
- * stored in intel byte order, and the name_len field could never be
- * bigger than 255 chars, it's safe to reclaim the extra byte for the
- * file_type field.
- */
-struct ext2_dir_entry_2 {
-	__le32	inode;			/* Inode number */
-	__le16	rec_len;		/* Directory entry length */
-	__u8	name_len;		/* Name length */
-	__u8	file_type;
-	char	name[EXT2_NAME_LEN];	/* File name */
-};
-
-/*
- * Ext2 directory file types.  Only the low 3 bits are used.  The
- * other bits are reserved for now.
- */
-enum {
-	EXT2_FT_UNKNOWN		= 0,
-	EXT2_FT_REG_FILE	= 1,
-	EXT2_FT_DIR		= 2,
-	EXT2_FT_CHRDEV		= 3,
-	EXT2_FT_BLKDEV		= 4,
-	EXT2_FT_FIFO		= 5,
-	EXT2_FT_SOCK		= 6,
-	EXT2_FT_SYMLINK		= 7,
-	EXT2_FT_MAX
-};
-
-/*
- * EXT2_DIR_PAD defines the directory entries boundaries
- *
- * NOTE: It must be a multiple of 4
- */
-#define EXT2_DIR_PAD		 	4
-#define EXT2_DIR_ROUND 			(EXT2_DIR_PAD - 1)
-#define EXT2_DIR_REC_LEN(name_len)	(((name_len) + 8 + EXT2_DIR_ROUND) & \
-					 ~EXT2_DIR_ROUND)
-#define EXT2_MAX_REC_LEN		((1<<16)-1)
-
 #endif	/* _LINUX_EXT2_FS_H */
diff --git a/include/linux/ext2_fs_sb.h b/include/linux/ext2_fs_sb.h
deleted file mode 100644
index db4d9f586bb6..000000000000
--- a/include/linux/ext2_fs_sb.h
+++ /dev/null
@@ -1,126 +0,0 @@
-/*
- *  linux/include/linux/ext2_fs_sb.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/include/linux/minix_fs_sb.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _LINUX_EXT2_FS_SB
-#define _LINUX_EXT2_FS_SB
-
-#include <linux/blockgroup_lock.h>
-#include <linux/percpu_counter.h>
-#include <linux/rbtree.h>
-
-/* XXX Here for now... not interested in restructing headers JUST now */
-
-/* data type for block offset of block group */
-typedef int ext2_grpblk_t;
-
-/* data type for filesystem-wide blocks number */
-typedef unsigned long ext2_fsblk_t;
-
-#define E2FSBLK "%lu"
-
-struct ext2_reserve_window {
-	ext2_fsblk_t		_rsv_start;	/* First byte reserved */
-	ext2_fsblk_t		_rsv_end;	/* Last byte reserved or 0 */
-};
-
-struct ext2_reserve_window_node {
-	struct rb_node	 	rsv_node;
-	__u32			rsv_goal_size;
-	__u32			rsv_alloc_hit;
-	struct ext2_reserve_window	rsv_window;
-};
-
-struct ext2_block_alloc_info {
-	/* information about reservation window */
-	struct ext2_reserve_window_node	rsv_window_node;
-	/*
-	 * was i_next_alloc_block in ext2_inode_info
-	 * is the logical (file-relative) number of the
-	 * most-recently-allocated block in this file.
-	 * We use this for detecting linearly ascending allocation requests.
-	 */
-	__u32			last_alloc_logical_block;
-	/*
-	 * Was i_next_alloc_goal in ext2_inode_info
-	 * is the *physical* companion to i_next_alloc_block.
-	 * it the the physical block number of the block which was most-recentl
-	 * allocated to this file.  This give us the goal (target) for the next
-	 * allocation when we detect linearly ascending requests.
-	 */
-	ext2_fsblk_t		last_alloc_physical_block;
-};
-
-#define rsv_start rsv_window._rsv_start
-#define rsv_end rsv_window._rsv_end
-
-/*
- * second extended-fs super-block data in memory
- */
-struct ext2_sb_info {
-	unsigned long s_frag_size;	/* Size of a fragment in bytes */
-	unsigned long s_frags_per_block;/* Number of fragments per block */
-	unsigned long s_inodes_per_block;/* Number of inodes per block */
-	unsigned long s_frags_per_group;/* Number of fragments in a group */
-	unsigned long s_blocks_per_group;/* Number of blocks in a group */
-	unsigned long s_inodes_per_group;/* Number of inodes in a group */
-	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
-	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
-	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
-	unsigned long s_groups_count;	/* Number of groups in the fs */
-	unsigned long s_overhead_last;  /* Last calculated overhead */
-	unsigned long s_blocks_last;    /* Last seen block count */
-	struct buffer_head * s_sbh;	/* Buffer containing the super block */
-	struct ext2_super_block * s_es;	/* Pointer to the super block in the buffer */
-	struct buffer_head ** s_group_desc;
-	unsigned long  s_mount_opt;
-	unsigned long s_sb_block;
-	uid_t s_resuid;
-	gid_t s_resgid;
-	unsigned short s_mount_state;
-	unsigned short s_pad;
-	int s_addr_per_block_bits;
-	int s_desc_per_block_bits;
-	int s_inode_size;
-	int s_first_ino;
-	spinlock_t s_next_gen_lock;
-	u32 s_next_generation;
-	unsigned long s_dir_count;
-	u8 *s_debts;
-	struct percpu_counter s_freeblocks_counter;
-	struct percpu_counter s_freeinodes_counter;
-	struct percpu_counter s_dirs_counter;
-	struct blockgroup_lock *s_blockgroup_lock;
-	/* root of the per fs reservation window tree */
-	spinlock_t s_rsv_window_lock;
-	struct rb_root s_rsv_window_root;
-	struct ext2_reserve_window_node s_rsv_window_head;
-	/*
-	 * s_lock protects against concurrent modifications of s_mount_state,
-	 * s_blocks_last, s_overhead_last and the content of superblock's
-	 * buffer pointed to by sbi->s_es.
-	 *
-	 * Note: It is used in ext2_show_options() to provide a consistent view
-	 * of the mount options.
-	 */
-	spinlock_t s_lock;
-};
-
-static inline spinlock_t *
-sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group)
-{
-	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
-}
-
-#endif	/* _LINUX_EXT2_FS_SB */
diff --git a/include/linux/ext3_fs_i.h b/include/linux/ext3_fs_i.h
deleted file mode 100644
index f42c098aed8d..000000000000
--- a/include/linux/ext3_fs_i.h
+++ /dev/null
@@ -1,151 +0,0 @@
-/*
- *  linux/include/linux/ext3_fs_i.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/include/linux/minix_fs_i.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _LINUX_EXT3_FS_I
-#define _LINUX_EXT3_FS_I
-
-#include <linux/rwsem.h>
-#include <linux/rbtree.h>
-#include <linux/seqlock.h>
-#include <linux/mutex.h>
-
-/* data type for block offset of block group */
-typedef int ext3_grpblk_t;
-
-/* data type for filesystem-wide blocks number */
-typedef unsigned long ext3_fsblk_t;
-
-#define E3FSBLK "%lu"
-
-struct ext3_reserve_window {
-	ext3_fsblk_t	_rsv_start;	/* First byte reserved */
-	ext3_fsblk_t	_rsv_end;	/* Last byte reserved or 0 */
-};
-
-struct ext3_reserve_window_node {
-	struct rb_node		rsv_node;
-	__u32			rsv_goal_size;
-	__u32			rsv_alloc_hit;
-	struct ext3_reserve_window	rsv_window;
-};
-
-struct ext3_block_alloc_info {
-	/* information about reservation window */
-	struct ext3_reserve_window_node	rsv_window_node;
-	/*
-	 * was i_next_alloc_block in ext3_inode_info
-	 * is the logical (file-relative) number of the
-	 * most-recently-allocated block in this file.
-	 * We use this for detecting linearly ascending allocation requests.
-	 */
-	__u32                   last_alloc_logical_block;
-	/*
-	 * Was i_next_alloc_goal in ext3_inode_info
-	 * is the *physical* companion to i_next_alloc_block.
-	 * it the physical block number of the block which was most-recentl
-	 * allocated to this file.  This give us the goal (target) for the next
-	 * allocation when we detect linearly ascending requests.
-	 */
-	ext3_fsblk_t		last_alloc_physical_block;
-};
-
-#define rsv_start rsv_window._rsv_start
-#define rsv_end rsv_window._rsv_end
-
-/*
- * third extended file system inode data in memory
- */
-struct ext3_inode_info {
-	__le32	i_data[15];	/* unconverted */
-	__u32	i_flags;
-#ifdef EXT3_FRAGMENTS
-	__u32	i_faddr;
-	__u8	i_frag_no;
-	__u8	i_frag_size;
-#endif
-	ext3_fsblk_t	i_file_acl;
-	__u32	i_dir_acl;
-	__u32	i_dtime;
-
-	/*
-	 * i_block_group is the number of the block group which contains
-	 * this file's inode.  Constant across the lifetime of the inode,
-	 * it is ued for making block allocation decisions - we try to
-	 * place a file's data blocks near its inode block, and new inodes
-	 * near to their parent directory's inode.
-	 */
-	__u32	i_block_group;
-	unsigned long	i_state_flags;	/* Dynamic state flags for ext3 */
-
-	/* block reservation info */
-	struct ext3_block_alloc_info *i_block_alloc_info;
-
-	__u32	i_dir_start_lookup;
-#ifdef CONFIG_EXT3_FS_XATTR
-	/*
-	 * Extended attributes can be read independently of the main file
-	 * data. Taking i_mutex even when reading would cause contention
-	 * between readers of EAs and writers of regular file data, so
-	 * instead we synchronize on xattr_sem when reading or changing
-	 * EAs.
-	 */
-	struct rw_semaphore xattr_sem;
-#endif
-
-	struct list_head i_orphan;	/* unlinked but open inodes */
-
-	/*
-	 * i_disksize keeps track of what the inode size is ON DISK, not
-	 * in memory.  During truncate, i_size is set to the new size by
-	 * the VFS prior to calling ext3_truncate(), but the filesystem won't
-	 * set i_disksize to 0 until the truncate is actually under way.
-	 *
-	 * The intent is that i_disksize always represents the blocks which
-	 * are used by this file.  This allows recovery to restart truncate
-	 * on orphans if we crash during truncate.  We actually write i_disksize
-	 * into the on-disk inode when writing inodes out, instead of i_size.
-	 *
-	 * The only time when i_disksize and i_size may be different is when
-	 * a truncate is in progress.  The only things which change i_disksize
-	 * are ext3_get_block (growth) and ext3_truncate (shrinkth).
-	 */
-	loff_t	i_disksize;
-
-	/* on-disk additional length */
-	__u16 i_extra_isize;
-
-	/*
-	 * truncate_mutex is for serialising ext3_truncate() against
-	 * ext3_getblock().  In the 2.4 ext2 design, great chunks of inode's
-	 * data tree are chopped off during truncate. We can't do that in
-	 * ext3 because whenever we perform intermediate commits during
-	 * truncate, the inode and all the metadata blocks *must* be in a
-	 * consistent state which allows truncation of the orphans to restart
-	 * during recovery.  Hence we must fix the get_block-vs-truncate race
-	 * by other means, so we have truncate_mutex.
-	 */
-	struct mutex truncate_mutex;
-
-	/*
-	 * Transactions that contain inode's metadata needed to complete
-	 * fsync and fdatasync, respectively.
-	 */
-	atomic_t i_sync_tid;
-	atomic_t i_datasync_tid;
-
-	struct inode vfs_inode;
-};
-
-#endif	/* _LINUX_EXT3_FS_I */
diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h
deleted file mode 100644
index 64365252f1b0..000000000000
--- a/include/linux/ext3_fs_sb.h
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- *  linux/include/linux/ext3_fs_sb.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/include/linux/minix_fs_sb.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _LINUX_EXT3_FS_SB
-#define _LINUX_EXT3_FS_SB
-
-#ifdef __KERNEL__
-#include <linux/timer.h>
-#include <linux/wait.h>
-#include <linux/blockgroup_lock.h>
-#include <linux/percpu_counter.h>
-#endif
-#include <linux/rbtree.h>
-
-/*
- * third extended-fs super-block data in memory
- */
-struct ext3_sb_info {
-	unsigned long s_frag_size;	/* Size of a fragment in bytes */
-	unsigned long s_frags_per_block;/* Number of fragments per block */
-	unsigned long s_inodes_per_block;/* Number of inodes per block */
-	unsigned long s_frags_per_group;/* Number of fragments in a group */
-	unsigned long s_blocks_per_group;/* Number of blocks in a group */
-	unsigned long s_inodes_per_group;/* Number of inodes in a group */
-	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
-	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
-	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
-	unsigned long s_groups_count;	/* Number of groups in the fs */
-	unsigned long s_overhead_last;  /* Last calculated overhead */
-	unsigned long s_blocks_last;    /* Last seen block count */
-	struct buffer_head * s_sbh;	/* Buffer containing the super block */
-	struct ext3_super_block * s_es;	/* Pointer to the super block in the buffer */
-	struct buffer_head ** s_group_desc;
-	unsigned long  s_mount_opt;
-	ext3_fsblk_t s_sb_block;
-	uid_t s_resuid;
-	gid_t s_resgid;
-	unsigned short s_mount_state;
-	unsigned short s_pad;
-	int s_addr_per_block_bits;
-	int s_desc_per_block_bits;
-	int s_inode_size;
-	int s_first_ino;
-	spinlock_t s_next_gen_lock;
-	u32 s_next_generation;
-	u32 s_hash_seed[4];
-	int s_def_hash_version;
-	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
-	struct percpu_counter s_freeblocks_counter;
-	struct percpu_counter s_freeinodes_counter;
-	struct percpu_counter s_dirs_counter;
-	struct blockgroup_lock *s_blockgroup_lock;
-
-	/* root of the per fs reservation window tree */
-	spinlock_t s_rsv_window_lock;
-	struct rb_root s_rsv_window_root;
-	struct ext3_reserve_window_node s_rsv_window_head;
-
-	/* Journaling */
-	struct inode * s_journal_inode;
-	struct journal_s * s_journal;
-	struct list_head s_orphan;
-	struct mutex s_orphan_lock;
-	struct mutex s_resize_lock;
-	unsigned long s_commit_interval;
-	struct block_device *journal_bdev;
-#ifdef CONFIG_QUOTA
-	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
-	int s_jquota_fmt;			/* Format of quota to use */
-#endif
-};
-
-static inline spinlock_t *
-sb_bgl_lock(struct ext3_sb_info *sbi, unsigned int block_group)
-{
-	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
-}
-
-#endif	/* _LINUX_EXT3_FS_SB */
diff --git a/include/linux/ext3_jbd.h b/include/linux/ext3_jbd.h
deleted file mode 100644
index d7b5ddca99c2..000000000000
--- a/include/linux/ext3_jbd.h
+++ /dev/null
@@ -1,229 +0,0 @@
-/*
- * linux/include/linux/ext3_jbd.h
- *
- * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
- *
- * Copyright 1998--1999 Red Hat corp --- All Rights Reserved
- *
- * This file is part of the Linux kernel and is made available under
- * the terms of the GNU General Public License, version 2, or at your
- * option, any later version, incorporated herein by reference.
- *
- * Ext3-specific journaling extensions.
- */
-
-#ifndef _LINUX_EXT3_JBD_H
-#define _LINUX_EXT3_JBD_H
-
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-
-#define EXT3_JOURNAL(inode)	(EXT3_SB((inode)->i_sb)->s_journal)
-
-/* Define the number of blocks we need to account to a transaction to
- * modify one block of data.
- *
- * We may have to touch one inode, one bitmap buffer, up to three
- * indirection blocks, the group and superblock summaries, and the data
- * block to complete the transaction.  */
-
-#define EXT3_SINGLEDATA_TRANS_BLOCKS	8U
-
-/* Extended attribute operations touch at most two data buffers,
- * two bitmap buffers, and two group summaries, in addition to the inode
- * and the superblock, which are already accounted for. */
-
-#define EXT3_XATTR_TRANS_BLOCKS		6U
-
-/* Define the minimum size for a transaction which modifies data.  This
- * needs to take into account the fact that we may end up modifying two
- * quota files too (one for the group, one for the user quota).  The
- * superblock only gets updated once, of course, so don't bother
- * counting that again for the quota updates. */
-
-#define EXT3_DATA_TRANS_BLOCKS(sb)	(EXT3_SINGLEDATA_TRANS_BLOCKS + \
-					 EXT3_XATTR_TRANS_BLOCKS - 2 + \
-					 EXT3_MAXQUOTAS_TRANS_BLOCKS(sb))
-
-/* Delete operations potentially hit one directory's namespace plus an
- * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
- * generous.  We can grow the delete transaction later if necessary. */
-
-#define EXT3_DELETE_TRANS_BLOCKS(sb)   (EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) + 64)
-
-/* Define an arbitrary limit for the amount of data we will anticipate
- * writing to any given transaction.  For unbounded transactions such as
- * write(2) and truncate(2) we can write more than this, but we always
- * start off at the maximum transaction size and grow the transaction
- * optimistically as we go. */
-
-#define EXT3_MAX_TRANS_DATA		64U
-
-/* We break up a large truncate or write transaction once the handle's
- * buffer credits gets this low, we need either to extend the
- * transaction or to start a new one.  Reserve enough space here for
- * inode, bitmap, superblock, group and indirection updates for at least
- * one block, plus two quota updates.  Quota allocations are not
- * needed. */
-
-#define EXT3_RESERVE_TRANS_BLOCKS	12U
-
-#define EXT3_INDEX_EXTRA_TRANS_BLOCKS	8
-
-#ifdef CONFIG_QUOTA
-/* Amount of blocks needed for quota update - we know that the structure was
- * allocated so we need to update only inode+data */
-#define EXT3_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0)
-/* Amount of blocks needed for quota insert/delete - we do some block writes
- * but inode, sb and group updates are done only once */
-#define EXT3_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
-		(EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0)
-#define EXT3_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
-		(EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0)
-#else
-#define EXT3_QUOTA_TRANS_BLOCKS(sb) 0
-#define EXT3_QUOTA_INIT_BLOCKS(sb) 0
-#define EXT3_QUOTA_DEL_BLOCKS(sb) 0
-#endif
-#define EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_TRANS_BLOCKS(sb))
-#define EXT3_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_INIT_BLOCKS(sb))
-#define EXT3_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_DEL_BLOCKS(sb))
-
-int
-ext3_mark_iloc_dirty(handle_t *handle,
-		     struct inode *inode,
-		     struct ext3_iloc *iloc);
-
-/*
- * On success, We end up with an outstanding reference count against
- * iloc->bh.  This _must_ be cleaned up later.
- */
-
-int ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
-			struct ext3_iloc *iloc);
-
-int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode);
-
-/*
- * Wrapper functions with which ext3 calls into JBD.  The intent here is
- * to allow these to be turned into appropriate stubs so ext3 can control
- * ext2 filesystems, so ext2+ext3 systems only nee one fs.  This work hasn't
- * been done yet.
- */
-
-static inline void ext3_journal_release_buffer(handle_t *handle,
-						struct buffer_head *bh)
-{
-	journal_release_buffer(handle, bh);
-}
-
-void ext3_journal_abort_handle(const char *caller, const char *err_fn,
-		struct buffer_head *bh, handle_t *handle, int err);
-
-int __ext3_journal_get_undo_access(const char *where, handle_t *handle,
-				struct buffer_head *bh);
-
-int __ext3_journal_get_write_access(const char *where, handle_t *handle,
-				struct buffer_head *bh);
-
-int __ext3_journal_forget(const char *where, handle_t *handle,
-				struct buffer_head *bh);
-
-int __ext3_journal_revoke(const char *where, handle_t *handle,
-				unsigned long blocknr, struct buffer_head *bh);
-
-int __ext3_journal_get_create_access(const char *where,
-				handle_t *handle, struct buffer_head *bh);
-
-int __ext3_journal_dirty_metadata(const char *where,
-				handle_t *handle, struct buffer_head *bh);
-
-#define ext3_journal_get_undo_access(handle, bh) \
-	__ext3_journal_get_undo_access(__func__, (handle), (bh))
-#define ext3_journal_get_write_access(handle, bh) \
-	__ext3_journal_get_write_access(__func__, (handle), (bh))
-#define ext3_journal_revoke(handle, blocknr, bh) \
-	__ext3_journal_revoke(__func__, (handle), (blocknr), (bh))
-#define ext3_journal_get_create_access(handle, bh) \
-	__ext3_journal_get_create_access(__func__, (handle), (bh))
-#define ext3_journal_dirty_metadata(handle, bh) \
-	__ext3_journal_dirty_metadata(__func__, (handle), (bh))
-#define ext3_journal_forget(handle, bh) \
-	__ext3_journal_forget(__func__, (handle), (bh))
-
-int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh);
-
-handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks);
-int __ext3_journal_stop(const char *where, handle_t *handle);
-
-static inline handle_t *ext3_journal_start(struct inode *inode, int nblocks)
-{
-	return ext3_journal_start_sb(inode->i_sb, nblocks);
-}
-
-#define ext3_journal_stop(handle) \
-	__ext3_journal_stop(__func__, (handle))
-
-static inline handle_t *ext3_journal_current_handle(void)
-{
-	return journal_current_handle();
-}
-
-static inline int ext3_journal_extend(handle_t *handle, int nblocks)
-{
-	return journal_extend(handle, nblocks);
-}
-
-static inline int ext3_journal_restart(handle_t *handle, int nblocks)
-{
-	return journal_restart(handle, nblocks);
-}
-
-static inline int ext3_journal_blocks_per_page(struct inode *inode)
-{
-	return journal_blocks_per_page(inode);
-}
-
-static inline int ext3_journal_force_commit(journal_t *journal)
-{
-	return journal_force_commit(journal);
-}
-
-/* super.c */
-int ext3_force_commit(struct super_block *sb);
-
-static inline int ext3_should_journal_data(struct inode *inode)
-{
-	if (!S_ISREG(inode->i_mode))
-		return 1;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
-		return 1;
-	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
-		return 1;
-	return 0;
-}
-
-static inline int ext3_should_order_data(struct inode *inode)
-{
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
-		return 1;
-	return 0;
-}
-
-static inline int ext3_should_writeback_data(struct inode *inode)
-{
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
-		return 1;
-	return 0;
-}
-
-#endif	/* _LINUX_EXT3_JBD_H */
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 82163c4b32c9..158a41eed314 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -21,23 +21,45 @@
  */
 #define NR_OPEN_DEFAULT BITS_PER_LONG
 
-/*
- * The embedded_fd_set is a small fd_set,
- * suitable for most tasks (which open <= BITS_PER_LONG files)
- */
-struct embedded_fd_set {
-	unsigned long fds_bits[1];
-};
-
 struct fdtable {
 	unsigned int max_fds;
 	struct file __rcu **fd;      /* current fd array */
-	fd_set *close_on_exec;
-	fd_set *open_fds;
+	unsigned long *close_on_exec;
+	unsigned long *open_fds;
 	struct rcu_head rcu;
 	struct fdtable *next;
 };
 
+static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
+{
+	__set_bit(fd, fdt->close_on_exec);
+}
+
+static inline void __clear_close_on_exec(int fd, struct fdtable *fdt)
+{
+	__clear_bit(fd, fdt->close_on_exec);
+}
+
+static inline bool close_on_exec(int fd, const struct fdtable *fdt)
+{
+	return test_bit(fd, fdt->close_on_exec);
+}
+
+static inline void __set_open_fd(int fd, struct fdtable *fdt)
+{
+	__set_bit(fd, fdt->open_fds);
+}
+
+static inline void __clear_open_fd(int fd, struct fdtable *fdt)
+{
+	__clear_bit(fd, fdt->open_fds);
+}
+
+static inline bool fd_is_open(int fd, const struct fdtable *fdt)
+{
+	return test_bit(fd, fdt->open_fds);
+}
+
 /*
  * Open file table structure
  */
@@ -53,8 +75,8 @@ struct files_struct {
    */
 	spinlock_t file_lock ____cacheline_aligned_in_smp;
 	int next_fd;
-	struct embedded_fd_set close_on_exec_init;
-	struct embedded_fd_set open_fds_init;
+	unsigned long close_on_exec_init[1];
+	unsigned long open_fds_init[1];
 	struct file __rcu * fd_array[NR_OPEN_DEFAULT];
 };
 
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 4db7b68f0582..cdc9b719e9c7 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -2,6 +2,7 @@
 #define _LINUX_FIREWIRE_H
 
 #include <linux/completion.h>
+#include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
@@ -64,8 +65,6 @@
 #define CSR_MODEL		0x17
 #define CSR_DIRECTORY_ID	0x20
 
-struct device;
-
 struct fw_csr_iterator {
 	const u32 *p;
 	const u32 *end;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fa63f1b46103..8de675523e46 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -92,6 +92,10 @@ struct inodes_stat_t {
 /* File is opened using open(.., 3, ..) and is writeable only for ioctls
    (specialy hack for floppy.c) */
 #define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
+/* 32bit hashes as llseek() offset (for directories) */
+#define FMODE_32BITHASH         ((__force fmode_t)0x200)
+/* 64bit hashes as llseek() offset (for directories) */
+#define FMODE_64BITHASH         ((__force fmode_t)0x400)
 
 /*
  * Don't update ctime and mtime.
@@ -1211,6 +1215,7 @@ extern int vfs_setlease(struct file *, long, struct file_lock **);
 extern int lease_modify(struct file_lock **, int);
 extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
 extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
+extern void locks_delete_block(struct file_lock *waiter);
 extern void lock_flocks(void);
 extern void unlock_flocks(void);
 #else /* !CONFIG_FILE_LOCKING */
@@ -1355,6 +1360,10 @@ static inline int lock_may_write(struct inode *inode, loff_t start,
 	return 1;
 }
 
+static inline void locks_delete_block(struct file_lock *waiter)
+{
+}
+
 static inline void lock_flocks(void)
 {
 }
@@ -1872,19 +1881,6 @@ extern struct dentry *mount_pseudo(struct file_system_type *, char *,
 	const struct dentry_operations *dops,
 	unsigned long);
 
-static inline void sb_mark_dirty(struct super_block *sb)
-{
-	sb->s_dirt = 1;
-}
-static inline void sb_mark_clean(struct super_block *sb)
-{
-	sb->s_dirt = 0;
-}
-static inline int sb_is_dirty(struct super_block *sb)
-{
-	return sb->s_dirt;
-}
-
 /* Alas, no aliases. Too much hassle with bringing module.h everywhere */
 #define fops_get(fops) \
 	(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
@@ -2515,6 +2511,7 @@ extern int dcache_readdir(struct file *, void *, filldir_t);
 extern int simple_setattr(struct dentry *, struct iattr *);
 extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int simple_statfs(struct dentry *, struct kstatfs *);
+extern int simple_open(struct inode *inode, struct file *file);
 extern int simple_link(struct dentry *, struct inode *, struct dentry *);
 extern int simple_unlink(struct inode *, struct dentry *);
 extern int simple_rmdir(struct inode *, struct dentry *);
diff --git a/arch/arm/mach-mxs/include/mach/dma.h b/include/linux/fsl/mxs-dma.h
index 203d7c4a3e11..203d7c4a3e11 100644
--- a/arch/arm/mach-mxs/include/mach/dma.h
+++ b/include/linux/fsl/mxs-dma.h
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index dd478fc8f9f5..5f3f3be5af09 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -144,12 +144,14 @@ struct event_filter;
 enum trace_reg {
 	TRACE_REG_REGISTER,
 	TRACE_REG_UNREGISTER,
+#ifdef CONFIG_PERF_EVENTS
 	TRACE_REG_PERF_REGISTER,
 	TRACE_REG_PERF_UNREGISTER,
 	TRACE_REG_PERF_OPEN,
 	TRACE_REG_PERF_CLOSE,
 	TRACE_REG_PERF_ADD,
 	TRACE_REG_PERF_DEL,
+#endif
 };
 
 struct ftrace_event_call;
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index ed5a46707ad0..6155ecf192b0 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -14,6 +14,12 @@
 #define GPIOF_OUT_INIT_LOW	(GPIOF_DIR_OUT | GPIOF_INIT_LOW)
 #define GPIOF_OUT_INIT_HIGH	(GPIOF_DIR_OUT | GPIOF_INIT_HIGH)
 
+/* Gpio pin is open drain */
+#define GPIOF_OPEN_DRAIN	(1 << 2)
+
+/* Gpio pin is open source */
+#define GPIOF_OPEN_SOURCE	(1 << 3)
+
 /**
  * struct gpio - a structure describing a GPIO with configuration
  * @gpio:	the GPIO number
diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h
index 004ff33ab38e..a7e977ff4abf 100644
--- a/include/linux/gpio_keys.h
+++ b/include/linux/gpio_keys.h
@@ -6,7 +6,7 @@ struct device;
 struct gpio_keys_button {
 	/* Configuration parameters */
 	unsigned int code;	/* input event code (KEY_*, SW_*) */
-	int gpio;
+	int gpio;		/* -1 if this key does not support gpio */
 	int active_low;
 	const char *desc;
 	unsigned int type;	/* input event type (EV_KEY, EV_SW, EV_ABS) */
@@ -14,6 +14,7 @@ struct gpio_keys_button {
 	int debounce_interval;	/* debounce ticks interval in msecs */
 	bool can_disable;
 	int value;		/* axis value for EV_ABS */
+	unsigned int irq;	/* Irq number in case of interrupt keys */
 };
 
 struct gpio_keys_platform_data {
diff --git a/include/linux/hsi/Kbuild b/include/linux/hsi/Kbuild
new file mode 100644
index 000000000000..271a770b4784
--- /dev/null
+++ b/include/linux/hsi/Kbuild
@@ -0,0 +1 @@
+header-y += hsi_char.h
diff --git a/include/linux/hsi/hsi.h b/include/linux/hsi/hsi.h
new file mode 100644
index 000000000000..4b178067f405
--- /dev/null
+++ b/include/linux/hsi/hsi.h
@@ -0,0 +1,410 @@
+/*
+ * HSI core header file.
+ *
+ * Copyright (C) 2010 Nokia Corporation. All rights reserved.
+ *
+ * Contact: Carlos Chinea <carlos.chinea@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ */
+
+#ifndef __LINUX_HSI_H__
+#define __LINUX_HSI_H__
+
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/module.h>
+
+/* HSI message ttype */
+#define HSI_MSG_READ	0
+#define HSI_MSG_WRITE	1
+
+/* HSI configuration values */
+enum {
+	HSI_MODE_STREAM	= 1,
+	HSI_MODE_FRAME,
+};
+
+enum {
+	HSI_FLOW_SYNC,	/* Synchronized flow */
+	HSI_FLOW_PIPE,	/* Pipelined flow */
+};
+
+enum {
+	HSI_ARB_RR,	/* Round-robin arbitration */
+	HSI_ARB_PRIO,	/* Channel priority arbitration */
+};
+
+#define HSI_MAX_CHANNELS	16
+
+/* HSI message status codes */
+enum {
+	HSI_STATUS_COMPLETED,	/* Message transfer is completed */
+	HSI_STATUS_PENDING,	/* Message pending to be read/write (POLL) */
+	HSI_STATUS_PROCEEDING,	/* Message transfer is ongoing */
+	HSI_STATUS_QUEUED,	/* Message waiting to be served */
+	HSI_STATUS_ERROR,	/* Error when message transfer was ongoing */
+};
+
+/* HSI port event codes */
+enum {
+	HSI_EVENT_START_RX,
+	HSI_EVENT_STOP_RX,
+};
+
+/**
+ * struct hsi_config - Configuration for RX/TX HSI modules
+ * @mode: Bit transmission mode (STREAM or FRAME)
+ * @channels: Number of channels to use [1..16]
+ * @speed: Max bit transmission speed (Kbit/s)
+ * @flow: RX flow type (SYNCHRONIZED or PIPELINE)
+ * @arb_mode: Arbitration mode for TX frame (Round robin, priority)
+ */
+struct hsi_config {
+	unsigned int	mode;
+	unsigned int	channels;
+	unsigned int	speed;
+	union {
+		unsigned int	flow;		/* RX only */
+		unsigned int	arb_mode;	/* TX only */
+	};
+};
+
+/**
+ * struct hsi_board_info - HSI client board info
+ * @name: Name for the HSI device
+ * @hsi_id: HSI controller id where the client sits
+ * @port: Port number in the controller where the client sits
+ * @tx_cfg: HSI TX configuration
+ * @rx_cfg: HSI RX configuration
+ * @platform_data: Platform related data
+ * @archdata: Architecture-dependent device data
+ */
+struct hsi_board_info {
+	const char		*name;
+	unsigned int		hsi_id;
+	unsigned int		port;
+	struct hsi_config	tx_cfg;
+	struct hsi_config	rx_cfg;
+	void			*platform_data;
+	struct dev_archdata	*archdata;
+};
+
+#ifdef CONFIG_HSI_BOARDINFO
+extern int hsi_register_board_info(struct hsi_board_info const *info,
+							unsigned int len);
+#else
+static inline int hsi_register_board_info(struct hsi_board_info const *info,
+							unsigned int len)
+{
+	return 0;
+}
+#endif /* CONFIG_HSI_BOARDINFO */
+
+/**
+ * struct hsi_client - HSI client attached to an HSI port
+ * @device: Driver model representation of the device
+ * @tx_cfg: HSI TX configuration
+ * @rx_cfg: HSI RX configuration
+ * @hsi_start_rx: Called after incoming wake line goes high
+ * @hsi_stop_rx: Called after incoming wake line goes low
+ */
+struct hsi_client {
+	struct device		device;
+	struct hsi_config	tx_cfg;
+	struct hsi_config	rx_cfg;
+	void			(*hsi_start_rx)(struct hsi_client *cl);
+	void			(*hsi_stop_rx)(struct hsi_client *cl);
+	/* private: */
+	unsigned int		pclaimed:1;
+	struct list_head	link;
+};
+
+#define to_hsi_client(dev) container_of(dev, struct hsi_client, device)
+
+static inline void hsi_client_set_drvdata(struct hsi_client *cl, void *data)
+{
+	dev_set_drvdata(&cl->device, data);
+}
+
+static inline void *hsi_client_drvdata(struct hsi_client *cl)
+{
+	return dev_get_drvdata(&cl->device);
+}
+
+/**
+ * struct hsi_client_driver - Driver associated to an HSI client
+ * @driver: Driver model representation of the driver
+ */
+struct hsi_client_driver {
+	struct device_driver	driver;
+};
+
+#define to_hsi_client_driver(drv) container_of(drv, struct hsi_client_driver,\
+									driver)
+
+int hsi_register_client_driver(struct hsi_client_driver *drv);
+
+static inline void hsi_unregister_client_driver(struct hsi_client_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+
+/**
+ * struct hsi_msg - HSI message descriptor
+ * @link: Free to use by the current descriptor owner
+ * @cl: HSI device client that issues the transfer
+ * @sgt: Head of the scatterlist array
+ * @context: Client context data associated to the transfer
+ * @complete: Transfer completion callback
+ * @destructor: Destructor to free resources when flushing
+ * @status: Status of the transfer when completed
+ * @actual_len: Actual length of data transfered on completion
+ * @channel: Channel were to TX/RX the message
+ * @ttype: Transfer type (TX if set, RX otherwise)
+ * @break_frame: if true HSI will send/receive a break frame. Data buffers are
+ *		ignored in the request.
+ */
+struct hsi_msg {
+	struct list_head	link;
+	struct hsi_client	*cl;
+	struct sg_table		sgt;
+	void			*context;
+
+	void			(*complete)(struct hsi_msg *msg);
+	void			(*destructor)(struct hsi_msg *msg);
+
+	int			status;
+	unsigned int		actual_len;
+	unsigned int		channel;
+	unsigned int		ttype:1;
+	unsigned int		break_frame:1;
+};
+
+struct hsi_msg *hsi_alloc_msg(unsigned int n_frag, gfp_t flags);
+void hsi_free_msg(struct hsi_msg *msg);
+
+/**
+ * struct hsi_port - HSI port device
+ * @device: Driver model representation of the device
+ * @tx_cfg: Current TX path configuration
+ * @rx_cfg: Current RX path configuration
+ * @num: Port number
+ * @shared: Set when port can be shared by different clients
+ * @claimed: Reference count of clients which claimed the port
+ * @lock: Serialize port claim
+ * @async: Asynchronous transfer callback
+ * @setup: Callback to set the HSI client configuration
+ * @flush: Callback to clean the HW state and destroy all pending transfers
+ * @start_tx: Callback to inform that a client wants to TX data
+ * @stop_tx: Callback to inform that a client no longer wishes to TX data
+ * @release: Callback to inform that a client no longer uses the port
+ * @clients: List of hsi_clients using the port.
+ * @clock: Lock to serialize access to the clients list.
+ */
+struct hsi_port {
+	struct device			device;
+	struct hsi_config		tx_cfg;
+	struct hsi_config		rx_cfg;
+	unsigned int			num;
+	unsigned int			shared:1;
+	int				claimed;
+	struct mutex			lock;
+	int				(*async)(struct hsi_msg *msg);
+	int				(*setup)(struct hsi_client *cl);
+	int				(*flush)(struct hsi_client *cl);
+	int				(*start_tx)(struct hsi_client *cl);
+	int				(*stop_tx)(struct hsi_client *cl);
+	int				(*release)(struct hsi_client *cl);
+	struct list_head		clients;
+	spinlock_t			clock;
+};
+
+#define to_hsi_port(dev) container_of(dev, struct hsi_port, device)
+#define hsi_get_port(cl) to_hsi_port((cl)->device.parent)
+
+void hsi_event(struct hsi_port *port, unsigned int event);
+int hsi_claim_port(struct hsi_client *cl, unsigned int share);
+void hsi_release_port(struct hsi_client *cl);
+
+static inline int hsi_port_claimed(struct hsi_client *cl)
+{
+	return cl->pclaimed;
+}
+
+static inline void hsi_port_set_drvdata(struct hsi_port *port, void *data)
+{
+	dev_set_drvdata(&port->device, data);
+}
+
+static inline void *hsi_port_drvdata(struct hsi_port *port)
+{
+	return dev_get_drvdata(&port->device);
+}
+
+/**
+ * struct hsi_controller - HSI controller device
+ * @device: Driver model representation of the device
+ * @owner: Pointer to the module owning the controller
+ * @id: HSI controller ID
+ * @num_ports: Number of ports in the HSI controller
+ * @port: Array of HSI ports
+ */
+struct hsi_controller {
+	struct device		device;
+	struct module		*owner;
+	unsigned int		id;
+	unsigned int		num_ports;
+	struct hsi_port		*port;
+};
+
+#define to_hsi_controller(dev) container_of(dev, struct hsi_controller, device)
+
+struct hsi_controller *hsi_alloc_controller(unsigned int n_ports, gfp_t flags);
+void hsi_free_controller(struct hsi_controller *hsi);
+int hsi_register_controller(struct hsi_controller *hsi);
+void hsi_unregister_controller(struct hsi_controller *hsi);
+
+static inline void hsi_controller_set_drvdata(struct hsi_controller *hsi,
+								void *data)
+{
+	dev_set_drvdata(&hsi->device, data);
+}
+
+static inline void *hsi_controller_drvdata(struct hsi_controller *hsi)
+{
+	return dev_get_drvdata(&hsi->device);
+}
+
+static inline struct hsi_port *hsi_find_port_num(struct hsi_controller *hsi,
+							unsigned int num)
+{
+	return (num < hsi->num_ports) ? &hsi->port[num] : NULL;
+}
+
+/*
+ * API for HSI clients
+ */
+int hsi_async(struct hsi_client *cl, struct hsi_msg *msg);
+
+/**
+ * hsi_id - Get HSI controller ID associated to a client
+ * @cl: Pointer to a HSI client
+ *
+ * Return the controller id where the client is attached to
+ */
+static inline unsigned int hsi_id(struct hsi_client *cl)
+{
+	return	to_hsi_controller(cl->device.parent->parent)->id;
+}
+
+/**
+ * hsi_port_id - Gets the port number a client is attached to
+ * @cl: Pointer to HSI client
+ *
+ * Return the port number associated to the client
+ */
+static inline unsigned int hsi_port_id(struct hsi_client *cl)
+{
+	return	to_hsi_port(cl->device.parent)->num;
+}
+
+/**
+ * hsi_setup - Configure the client's port
+ * @cl: Pointer to the HSI client
+ *
+ * When sharing ports, clients should either relay on a single
+ * client setup or have the same setup for all of them.
+ *
+ * Return -errno on failure, 0 on success
+ */
+static inline int hsi_setup(struct hsi_client *cl)
+{
+	if (!hsi_port_claimed(cl))
+		return -EACCES;
+	return	hsi_get_port(cl)->setup(cl);
+}
+
+/**
+ * hsi_flush - Flush all pending transactions on the client's port
+ * @cl: Pointer to the HSI client
+ *
+ * This function will destroy all pending hsi_msg in the port and reset
+ * the HW port so it is ready to receive and transmit from a clean state.
+ *
+ * Return -errno on failure, 0 on success
+ */
+static inline int hsi_flush(struct hsi_client *cl)
+{
+	if (!hsi_port_claimed(cl))
+		return -EACCES;
+	return hsi_get_port(cl)->flush(cl);
+}
+
+/**
+ * hsi_async_read - Submit a read transfer
+ * @cl: Pointer to the HSI client
+ * @msg: HSI message descriptor of the transfer
+ *
+ * Return -errno on failure, 0 on success
+ */
+static inline int hsi_async_read(struct hsi_client *cl, struct hsi_msg *msg)
+{
+	msg->ttype = HSI_MSG_READ;
+	return hsi_async(cl, msg);
+}
+
+/**
+ * hsi_async_write - Submit a write transfer
+ * @cl: Pointer to the HSI client
+ * @msg: HSI message descriptor of the transfer
+ *
+ * Return -errno on failure, 0 on success
+ */
+static inline int hsi_async_write(struct hsi_client *cl, struct hsi_msg *msg)
+{
+	msg->ttype = HSI_MSG_WRITE;
+	return hsi_async(cl, msg);
+}
+
+/**
+ * hsi_start_tx - Signal the port that the client wants to start a TX
+ * @cl: Pointer to the HSI client
+ *
+ * Return -errno on failure, 0 on success
+ */
+static inline int hsi_start_tx(struct hsi_client *cl)
+{
+	if (!hsi_port_claimed(cl))
+		return -EACCES;
+	return hsi_get_port(cl)->start_tx(cl);
+}
+
+/**
+ * hsi_stop_tx - Signal the port that the client no longer wants to transmit
+ * @cl: Pointer to the HSI client
+ *
+ * Return -errno on failure, 0 on success
+ */
+static inline int hsi_stop_tx(struct hsi_client *cl)
+{
+	if (!hsi_port_claimed(cl))
+		return -EACCES;
+	return hsi_get_port(cl)->stop_tx(cl);
+}
+#endif /* __LINUX_HSI_H__ */
diff --git a/include/linux/hsi/hsi_char.h b/include/linux/hsi/hsi_char.h
new file mode 100644
index 000000000000..76160b4f455d
--- /dev/null
+++ b/include/linux/hsi/hsi_char.h
@@ -0,0 +1,63 @@
+/*
+ * Part of the HSI character device driver.
+ *
+ * Copyright (C) 2010 Nokia Corporation. All rights reserved.
+ *
+ * Contact: Andras Domokos <andras.domokos at nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ */
+
+
+#ifndef __HSI_CHAR_H
+#define __HSI_CHAR_H
+
+#define HSI_CHAR_MAGIC		'k'
+#define HSC_IOW(num, dtype)	_IOW(HSI_CHAR_MAGIC, num, dtype)
+#define HSC_IOR(num, dtype)	_IOR(HSI_CHAR_MAGIC, num, dtype)
+#define HSC_IOWR(num, dtype)	_IOWR(HSI_CHAR_MAGIC, num, dtype)
+#define HSC_IO(num)		_IO(HSI_CHAR_MAGIC, num)
+
+#define HSC_RESET		HSC_IO(16)
+#define HSC_SET_PM		HSC_IO(17)
+#define HSC_SEND_BREAK		HSC_IO(18)
+#define HSC_SET_RX		HSC_IOW(19, struct hsc_rx_config)
+#define HSC_GET_RX		HSC_IOW(20, struct hsc_rx_config)
+#define HSC_SET_TX		HSC_IOW(21, struct hsc_tx_config)
+#define HSC_GET_TX		HSC_IOW(22, struct hsc_tx_config)
+
+#define HSC_PM_DISABLE		0
+#define HSC_PM_ENABLE		1
+
+#define HSC_MODE_STREAM		1
+#define HSC_MODE_FRAME		2
+#define HSC_FLOW_SYNC		0
+#define HSC_ARB_RR		0
+#define HSC_ARB_PRIO		1
+
+struct hsc_rx_config {
+	uint32_t mode;
+	uint32_t flow;
+	uint32_t channels;
+};
+
+struct hsc_tx_config {
+	uint32_t mode;
+	uint32_t channels;
+	uint32_t speed;
+	uint32_t arb_mode;
+};
+
+#endif /* __HSI_CHAR_H */
diff --git a/include/linux/i2c-algo-bit.h b/include/linux/i2c-algo-bit.h
index 584ffa0f3282..63904ba6887e 100644
--- a/include/linux/i2c-algo-bit.h
+++ b/include/linux/i2c-algo-bit.h
@@ -15,7 +15,8 @@
 
     You should have received a copy of the GNU General Public License
     along with this program; if not, write to the Free Software
-    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.                */
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.							     */
 /* ------------------------------------------------------------------------- */
 
 /* With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi> and even
diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h
index 0f91a957a690..538e8f41a319 100644
--- a/include/linux/i2c-algo-pcf.h
+++ b/include/linux/i2c-algo-pcf.h
@@ -16,7 +16,8 @@
 
     You should have received a copy of the GNU General Public License
     along with this program; if not, write to the Free Software
-    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.                */
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.							     */
 /* ------------------------------------------------------------------------- */
 
 /* With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi> and even
diff --git a/include/linux/i2c-dev.h b/include/linux/i2c-dev.h
index fd53bfd26470..8a7406b2114d 100644
--- a/include/linux/i2c-dev.h
+++ b/include/linux/i2c-dev.h
@@ -16,7 +16,8 @@
 
     You should have received a copy of the GNU General Public License
     along with this program; if not, write to the Free Software
-    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
 */
 
 #ifndef _LINUX_I2C_DEV_H
diff --git a/include/linux/i2c-mux.h b/include/linux/i2c-mux.h
index 34536effd652..747f0cde4164 100644
--- a/include/linux/i2c-mux.h
+++ b/include/linux/i2c-mux.h
@@ -18,7 +18,8 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301 USA.
  */
 
 #ifndef _LINUX_I2C_MUX_H
diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h
index 63f57a8c8b31..017fb40f702a 100644
--- a/include/linux/i2c-smbus.h
+++ b/include/linux/i2c-smbus.h
@@ -15,7 +15,8 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301 USA.
  */
 
 #ifndef _LINUX_I2C_SMBUS_H
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 8e25a9167f13..195d8b3d9cfb 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -17,7 +17,8 @@
 
     You should have received a copy of the GNU General Public License
     along with this program; if not, write to the Free Software
-    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.		     */
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.							     */
 /* ------------------------------------------------------------------------- */
 
 /* With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi> and
diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index 7fcab23c59ce..2463b6100333 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -761,7 +761,7 @@ struct twl_regulator_driver_data {
 
 /*----------------------------------------------------------------------*/
 
-int twl4030_sih_setup(int module);
+int twl4030_sih_setup(struct device *dev, int module, int irq_base);
 
 /* Offsets to Power Registers */
 #define TWL4030_VDAC_DEV_GRP		0x3B
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 7afe15f916da..b17974917dbf 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -22,7 +22,6 @@
 #include <acpi/acpi.h>
 #endif
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 /* for request_sense */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 3f830e005118..2aea5d22db07 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -19,7 +19,6 @@
 
 #include <linux/atomic.h>
 #include <asm/ptrace.h>
-#include <asm/system.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 5557baefed60..912c30a8ddb1 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -971,6 +971,10 @@ extern void __journal_clean_data_list(transaction_t *transaction);
 /* Log buffer allocation */
 extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *);
 int jbd2_journal_next_log_block(journal_t *, unsigned long long *);
+int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
+			      unsigned long *block);
+void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);
+void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);
 
 /* Commit management */
 extern void jbd2_journal_commit_transaction(journal_t *);
@@ -1020,6 +1024,11 @@ jbd2_journal_write_metadata_buffer(transaction_t	  *transaction,
 /* Transaction locking */
 extern void		__wait_on_journal (journal_t *);
 
+/* Transaction cache support */
+extern void jbd2_journal_destroy_transaction_cache(void);
+extern int  jbd2_journal_init_transaction_cache(void);
+extern void jbd2_journal_free_transaction(transaction_t *);
+
 /*
  * Journal locking.
  *
@@ -1082,7 +1091,8 @@ extern int	   jbd2_journal_destroy    (journal_t *);
 extern int	   jbd2_journal_recover    (journal_t *journal);
 extern int	   jbd2_journal_wipe       (journal_t *, int);
 extern int	   jbd2_journal_skip_recovery	(journal_t *);
-extern void	   jbd2_journal_update_superblock	(journal_t *, int);
+extern void	   jbd2_journal_update_sb_log_tail	(journal_t *, tid_t,
+				unsigned long, int);
 extern void	   __jbd2_journal_abort_hard	(journal_t *);
 extern void	   jbd2_journal_abort      (journal_t *, int);
 extern int	   jbd2_journal_errno      (journal_t *);
diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h
index 423cb6d78ee0..c18b46f8aeeb 100644
--- a/include/linux/journal-head.h
+++ b/include/linux/journal-head.h
@@ -66,6 +66,8 @@ struct journal_head {
 	 * transaction (if there is one).  Only applies to buffers on a
 	 * transaction's data or metadata journaling list.
 	 * [j_list_lock] [jbd_lock_bh_state()]
+	 * Either of these locks is enough for reading, both are needed for
+	 * changes.
 	 */
 	transaction_t *b_transaction;
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5db52d0ff1d4..645231c373c8 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_KERNEL_H
 #define _LINUX_KERNEL_H
 
+#include <linux/sysinfo.h>
+
 /*
  * 'kernel.h' contains some often-used function prototypes etc
  */
@@ -428,16 +430,10 @@ extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
  * Most likely, you want to use tracing_on/tracing_off.
  */
 #ifdef CONFIG_RING_BUFFER
-void tracing_on(void);
-void tracing_off(void);
 /* trace_off_permanent stops recording with no way to bring it back */
 void tracing_off_permanent(void);
-int tracing_is_on(void);
 #else
-static inline void tracing_on(void) { }
-static inline void tracing_off(void) { }
 static inline void tracing_off_permanent(void) { }
-static inline int tracing_is_on(void) { return 0; }
 #endif
 
 enum ftrace_dump_mode {
@@ -447,6 +443,10 @@ enum ftrace_dump_mode {
 };
 
 #ifdef CONFIG_TRACING
+void tracing_on(void);
+void tracing_off(void);
+int tracing_is_on(void);
+
 extern void tracing_start(void);
 extern void tracing_stop(void);
 extern void ftrace_off_permanent(void);
@@ -531,6 +531,11 @@ static inline void tracing_start(void) { }
 static inline void tracing_stop(void) { }
 static inline void ftrace_off_permanent(void) { }
 static inline void trace_dump_stack(void) { }
+
+static inline void tracing_on(void) { }
+static inline void tracing_off(void) { }
+static inline int tracing_is_on(void) { return 0; }
+
 static inline int
 trace_printk(const char *fmt, ...)
 {
@@ -698,27 +703,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
 #endif
 
-struct sysinfo;
 extern int do_sysinfo(struct sysinfo *info);
 
 #endif /* __KERNEL__ */
 
-#define SI_LOAD_SHIFT	16
-struct sysinfo {
-	long uptime;			/* Seconds since boot */
-	unsigned long loads[3];		/* 1, 5, and 15 minute load averages */
-	unsigned long totalram;		/* Total usable main memory size */
-	unsigned long freeram;		/* Available memory size */
-	unsigned long sharedram;	/* Amount of shared memory */
-	unsigned long bufferram;	/* Memory used by buffers */
-	unsigned long totalswap;	/* Total swap space size */
-	unsigned long freeswap;		/* swap space still available */
-	unsigned short procs;		/* Number of current processes */
-	unsigned short pad;		/* explicit padding for m68k */
-	unsigned long totalhigh;	/* Total high memory size */
-	unsigned long freehigh;		/* Available high memory size */
-	unsigned int mem_unit;		/* Memory unit size in bytes */
-	char _f[20-2*sizeof(long)-sizeof(int)];	/* Padding: libc5 uses this.. */
-};
-
 #endif
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index fa391835508d..c4d2fc194ede 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -63,7 +63,8 @@ enum kgdb_bptype {
 	BP_HARDWARE_BREAKPOINT,
 	BP_WRITE_WATCHPOINT,
 	BP_READ_WATCHPOINT,
-	BP_ACCESS_WATCHPOINT
+	BP_ACCESS_WATCHPOINT,
+	BP_POKE_BREAKPOINT,
 };
 
 enum kgdb_bpstate {
@@ -207,8 +208,8 @@ extern void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc);
 
 /* Optional functions. */
 extern int kgdb_validate_break_address(unsigned long addr);
-extern int kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr);
-extern int kgdb_arch_remove_breakpoint(unsigned long addr, char *bundle);
+extern int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt);
+extern int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt);
 
 /**
  *	kgdb_arch_late - Perform any architecture specific initalization.
diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index 9efeae679106..dd99c329e161 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -110,12 +110,29 @@ call_usermodehelper(char *path, char **argv, char **envp, int wait)
 
 extern struct ctl_table usermodehelper_table[];
 
+enum umh_disable_depth {
+	UMH_ENABLED = 0,
+	UMH_FREEZING,
+	UMH_DISABLED,
+};
+
 extern void usermodehelper_init(void);
 
-extern int usermodehelper_disable(void);
-extern void usermodehelper_enable(void);
-extern bool usermodehelper_is_disabled(void);
-extern void read_lock_usermodehelper(void);
-extern void read_unlock_usermodehelper(void);
+extern int __usermodehelper_disable(enum umh_disable_depth depth);
+extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth);
+
+static inline int usermodehelper_disable(void)
+{
+	return __usermodehelper_disable(UMH_DISABLED);
+}
+
+static inline void usermodehelper_enable(void)
+{
+	__usermodehelper_set_disable_depth(UMH_ENABLED);
+}
+
+extern int usermodehelper_read_trylock(void);
+extern long usermodehelper_read_lock_wait(long timeout);
+extern void usermodehelper_read_unlock(void);
 
 #endif /* __LINUX_KMOD_H__ */
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 68e67e50d028..6c322a90b92f 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -162,6 +162,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_INTERNAL_ERROR   17
 #define KVM_EXIT_OSI              18
 #define KVM_EXIT_PAPR_HCALL	  19
+#define KVM_EXIT_S390_UCONTROL	  20
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -249,6 +250,11 @@ struct kvm_run {
 #define KVM_S390_RESET_CPU_INIT  8
 #define KVM_S390_RESET_IPL       16
 		__u64 s390_reset_flags;
+		/* KVM_EXIT_S390_UCONTROL */
+		struct {
+			__u64 trans_exc_code;
+			__u32 pgm_code;
+		} s390_ucontrol;
 		/* KVM_EXIT_DCR */
 		struct {
 			__u32 dcrn;
@@ -273,6 +279,20 @@ struct kvm_run {
 		/* Fix the size of the union. */
 		char padding[256];
 	};
+
+	/*
+	 * shared registers between kvm and userspace.
+	 * kvm_valid_regs specifies the register classes set by the host
+	 * kvm_dirty_regs specified the register classes dirtied by userspace
+	 * struct kvm_sync_regs is architecture specific, as well as the
+	 * bits for kvm_valid_regs and kvm_dirty_regs
+	 */
+	__u64 kvm_valid_regs;
+	__u64 kvm_dirty_regs;
+	union {
+		struct kvm_sync_regs regs;
+		char padding[1024];
+	} s;
 };
 
 /* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
@@ -431,6 +451,11 @@ struct kvm_ppc_pvinfo {
 
 #define KVMIO 0xAE
 
+/* machine type bits, to be used as argument to KVM_CREATE_VM */
+#define KVM_VM_S390_UCONTROL	1
+
+#define KVM_S390_SIE_PAGE_OFFSET 1
+
 /*
  * ioctls for /dev/kvm fds:
  */
@@ -555,9 +580,15 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_SMT 64
 #define KVM_CAP_PPC_RMA	65
 #define KVM_CAP_MAX_VCPUS 66       /* returns max vcpus per vm */
+#define KVM_CAP_PPC_HIOR 67
 #define KVM_CAP_PPC_PAPR 68
+#define KVM_CAP_SW_TLB 69
+#define KVM_CAP_ONE_REG 70
 #define KVM_CAP_S390_GMAP 71
 #define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_S390_UCONTROL 73
+#define KVM_CAP_SYNC_REGS 74
+#define KVM_CAP_PCI_2_3 75
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -637,6 +668,52 @@ struct kvm_clock_data {
 	__u32 pad[9];
 };
 
+#define KVM_MMU_FSL_BOOKE_NOHV		0
+#define KVM_MMU_FSL_BOOKE_HV		1
+
+struct kvm_config_tlb {
+	__u64 params;
+	__u64 array;
+	__u32 mmu_type;
+	__u32 array_len;
+};
+
+struct kvm_dirty_tlb {
+	__u64 bitmap;
+	__u32 num_dirty;
+};
+
+/* Available with KVM_CAP_ONE_REG */
+
+#define KVM_REG_ARCH_MASK	0xff00000000000000ULL
+#define KVM_REG_GENERIC		0x0000000000000000ULL
+
+/*
+ * Architecture specific registers are to be defined in arch headers and
+ * ORed with the arch identifier.
+ */
+#define KVM_REG_PPC		0x1000000000000000ULL
+#define KVM_REG_X86		0x2000000000000000ULL
+#define KVM_REG_IA64		0x3000000000000000ULL
+#define KVM_REG_ARM		0x4000000000000000ULL
+#define KVM_REG_S390		0x5000000000000000ULL
+
+#define KVM_REG_SIZE_SHIFT	52
+#define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
+#define KVM_REG_SIZE_U8		0x0000000000000000ULL
+#define KVM_REG_SIZE_U16	0x0010000000000000ULL
+#define KVM_REG_SIZE_U32	0x0020000000000000ULL
+#define KVM_REG_SIZE_U64	0x0030000000000000ULL
+#define KVM_REG_SIZE_U128	0x0040000000000000ULL
+#define KVM_REG_SIZE_U256	0x0050000000000000ULL
+#define KVM_REG_SIZE_U512	0x0060000000000000ULL
+#define KVM_REG_SIZE_U1024	0x0070000000000000ULL
+
+struct kvm_one_reg {
+	__u64 id;
+	__u64 addr;
+};
+
 /*
  * ioctls for VM fds
  */
@@ -655,6 +732,17 @@ struct kvm_clock_data {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+
+/* enable ucontrol for s390 */
+struct kvm_s390_ucas_mapping {
+	__u64 user_addr;
+	__u64 vcpu_addr;
+	__u64 length;
+};
+#define KVM_S390_UCAS_MAP        _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
+#define KVM_S390_UCAS_UNMAP      _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
+#define KVM_S390_VCPU_FAULT	 _IOW(KVMIO, 0x52, unsigned long)
+
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP        _IO(KVMIO,   0x60)
 #define KVM_IRQ_LINE              _IOW(KVMIO,  0x61, struct kvm_irq_level)
@@ -697,6 +785,9 @@ struct kvm_clock_data {
 /* Available with KVM_CAP_TSC_CONTROL */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
+/* Available with KVM_CAP_PCI_2_3 */
+#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
+				       struct kvm_assigned_pci_dev)
 
 /*
  * ioctls for vcpu fds
@@ -763,8 +854,15 @@ struct kvm_clock_data {
 #define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
 /* Available with KVM_CAP_RMA */
 #define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_SW_TLB */
+#define KVM_DIRTY_TLB		  _IOW(KVMIO,  0xaa, struct kvm_dirty_tlb)
+/* Available with KVM_CAP_ONE_REG */
+#define KVM_GET_ONE_REG		  _IOW(KVMIO,  0xab, struct kvm_one_reg)
+#define KVM_SET_ONE_REG		  _IOW(KVMIO,  0xac, struct kvm_one_reg)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
+#define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
+#define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)
 
 struct kvm_assigned_pci_dev {
 	__u32 assigned_dev_id;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ca1b153585d3..665a260c7e09 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -172,11 +172,6 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
  */
 #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
 
-struct kvm_lpage_info {
-	unsigned long rmap_pde;
-	int write_count;
-};
-
 struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
@@ -185,7 +180,7 @@ struct kvm_memory_slot {
 	unsigned long *dirty_bitmap;
 	unsigned long *dirty_bitmap_head;
 	unsigned long nr_dirty_pages;
-	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
+	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
 	int user_alloc;
 	int id;
@@ -377,6 +372,9 @@ int kvm_set_memory_region(struct kvm *kvm,
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem,
 			    int user_alloc);
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont);
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_memory_slot old,
@@ -386,6 +384,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
 				int user_alloc);
+bool kvm_largepages_enabled(void);
 void kvm_disable_largepages(void);
 void kvm_arch_flush_shadow(struct kvm *kvm);
 
@@ -451,6 +450,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg);
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
 
 int kvm_dev_ioctl_check_extension(long ext);
 
@@ -521,7 +521,7 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
-int kvm_arch_init_vm(struct kvm *kvm);
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
 void kvm_arch_destroy_vm(struct kvm *kvm);
 void kvm_free_all_assigned_devices(struct kvm *kvm);
 void kvm_arch_sync_events(struct kvm *kvm);
@@ -547,6 +547,7 @@ struct kvm_assigned_dev_kernel {
 	unsigned int entries_nr;
 	int host_irq;
 	bool host_irq_disabled;
+	bool pci_2_3;
 	struct msix_entry *host_msix_entries;
 	int guest_irq;
 	struct msix_entry *guest_msix_entries;
@@ -556,6 +557,7 @@ struct kvm_assigned_dev_kernel {
 	struct pci_dev *dev;
 	struct kvm *kvm;
 	spinlock_t intx_lock;
+	spinlock_t intx_mask_lock;
 	char irq_name[32];
 	struct pci_saved_state *pci_saved_state;
 };
@@ -651,11 +653,43 @@ static inline void kvm_guest_exit(void)
 	current->flags &= ~PF_VCPU;
 }
 
+/*
+ * search_memslots() and __gfn_to_memslot() are here because they are
+ * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c.
+ * gfn_to_memslot() itself isn't here as an inline because that would
+ * bloat other code too much.
+ */
+static inline struct kvm_memory_slot *
+search_memslots(struct kvm_memslots *slots, gfn_t gfn)
+{
+	struct kvm_memory_slot *memslot;
+
+	kvm_for_each_memslot(memslot, slots)
+		if (gfn >= memslot->base_gfn &&
+		      gfn < memslot->base_gfn + memslot->npages)
+			return memslot;
+
+	return NULL;
+}
+
+static inline struct kvm_memory_slot *
+__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
+{
+	return search_memslots(slots, gfn);
+}
+
 static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn_to_memslot(kvm, gfn)->id;
 }
 
+static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
+{
+	/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
+	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
+		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
+}
+
 static inline unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
 					       gfn_t gfn)
 {
@@ -702,12 +736,16 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se
 	if (unlikely(vcpu->kvm->mmu_notifier_count))
 		return 1;
 	/*
-	 * Both reads happen under the mmu_lock and both values are
-	 * modified under mmu_lock, so there's no need of smb_rmb()
-	 * here in between, otherwise mmu_notifier_count should be
-	 * read before mmu_notifier_seq, see
-	 * mmu_notifier_invalidate_range_end write side.
+	 * Ensure the read of mmu_notifier_count happens before the read
+	 * of mmu_notifier_seq.  This interacts with the smp_wmb() in
+	 * mmu_notifier_invalidate_range_end to make sure that the caller
+	 * either sees the old (non-zero) value of mmu_notifier_count or
+	 * the new (incremented) value of mmu_notifier_seq.
+	 * PowerPC Book3s HV KVM calls this under a per-page lock
+	 * rather than under kvm->mmu_lock, for scalability, so
+	 * can't rely on kvm->mmu_lock to keep things ordered.
 	 */
+	smp_rmb();
 	if (vcpu->kvm->mmu_notifier_seq != mmu_seq)
 		return 1;
 	return 0;
@@ -770,6 +808,13 @@ static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id;
 }
+
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu);
+
+#else
+
+static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
+
 #endif
 
 #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 801b44b07aac..a5199f6d0e82 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -56,8 +56,7 @@
  */
 
 #include <linux/kernel.h>
-#include <asm/system.h>
-#include <asm/processor.h>
+#include <asm/cmpxchg.h>
 
 struct llist_head {
 	struct llist_node *first;
diff --git a/include/linux/lp8727.h b/include/linux/lp8727.h
index d21fa2865bf4..ea98c6133d32 100644
--- a/include/linux/lp8727.h
+++ b/include/linux/lp8727.h
@@ -1,4 +1,7 @@
 /*
+ * LP8727 Micro/Mini USB IC with integrated charger
+ *
+ *			Copyright (C) 2011 Texas Instruments
  *			Copyright (C) 2011 National Semiconductor
  *
  * This program is free software; you can redistribute it and/or modify
@@ -32,13 +35,24 @@ enum lp8727_ichg {
 	ICHG_1000mA,
 };
 
+/**
+ * struct lp8727_chg_param
+ * @eoc_level : end of charge level setting
+ * @ichg : charging current
+ */
 struct lp8727_chg_param {
-	/* end of charge level setting */
 	enum lp8727_eoc_level eoc_level;
-	/* charging current */
 	enum lp8727_ichg ichg;
 };
 
+/**
+ * struct lp8727_platform_data
+ * @get_batt_present : check battery status - exists or not
+ * @get_batt_level : get battery voltage (mV)
+ * @get_batt_capacity : get battery capacity (%)
+ * @get_batt_temp : get battery temperature
+ * @ac, @usb : charging parameters each charger type
+ */
 struct lp8727_platform_data {
 	u8 (*get_batt_present)(void);
 	u16 (*get_batt_level)(void);
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 88e78dedc2e8..fad48aab893b 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -21,8 +21,24 @@
 #include <linux/path.h>
 #include <linux/key.h>
 #include <linux/skbuff.h>
-#include <asm/system.h>
 
+struct lsm_network_audit {
+	int netif;
+	struct sock *sk;
+	u16 family;
+	__be16 dport;
+	__be16 sport;
+	union {
+		struct {
+			__be32 daddr;
+			__be32 saddr;
+		} v4;
+		struct {
+			struct in6_addr daddr;
+			struct in6_addr saddr;
+		} v6;
+	} fam;
+};
 
 /* Auxiliary data to use in generating the audit record. */
 struct common_audit_data {
@@ -42,23 +58,7 @@ struct common_audit_data {
 		struct path path;
 		struct dentry *dentry;
 		struct inode *inode;
-		struct {
-			int netif;
-			struct sock *sk;
-			u16 family;
-			__be16 dport;
-			__be16 sport;
-			union {
-				struct {
-					__be32 daddr;
-					__be32 saddr;
-				} v4;
-				struct {
-					struct in6_addr daddr;
-					struct in6_addr saddr;
-				} v6;
-			} fam;
-		} net;
+		struct lsm_network_audit *net;
 		int cap;
 		int ipc_id;
 		struct task_struct *tsk;
@@ -73,64 +73,15 @@ struct common_audit_data {
 	/* this union contains LSM specific data */
 	union {
 #ifdef CONFIG_SECURITY_SMACK
-		/* SMACK data */
-		struct smack_audit_data {
-			const char *function;
-			char *subject;
-			char *object;
-			char *request;
-			int result;
-		} smack_audit_data;
+		struct smack_audit_data *smack_audit_data;
 #endif
 #ifdef CONFIG_SECURITY_SELINUX
-		/* SELinux data */
-		struct {
-			u32 ssid;
-			u32 tsid;
-			u16 tclass;
-			u32 requested;
-			u32 audited;
-			u32 denied;
-			/*
-			 * auditdeny is a bit tricky and unintuitive.  See the
-			 * comments in avc.c for it's meaning and usage.
-			 */
-			u32 auditdeny;
-			struct av_decision *avd;
-			int result;
-		} selinux_audit_data;
+		struct selinux_audit_data *selinux_audit_data;
 #endif
 #ifdef CONFIG_SECURITY_APPARMOR
-		struct {
-			int error;
-			int op;
-			int type;
-			void *profile;
-			const char *name;
-			const char *info;
-			union {
-				void *target;
-				struct {
-					long pos;
-					void *target;
-				} iface;
-				struct {
-					int rlim;
-					unsigned long max;
-				} rlim;
-				struct {
-					const char *target;
-					u32 request;
-					u32 denied;
-					uid_t ouid;
-				} fs;
-			};
-		} apparmor_audit_data;
+		struct apparmor_audit_data *apparmor_audit_data;
 #endif
-	};
-	/* these callback will be implemented by a specific LSM */
-	void (*lsm_pre_audit)(struct audit_buffer *, void *);
-	void (*lsm_post_audit)(struct audit_buffer *, void *);
+	}; /* per LSM data pointer union */
 };
 
 #define v4info fam.v4
@@ -147,6 +98,8 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 	{ memset((_d), 0, sizeof(struct common_audit_data)); \
 	 (_d)->type = LSM_AUDIT_DATA_##_t; }
 
-void common_lsm_audit(struct common_audit_data *a);
+void common_lsm_audit(struct common_audit_data *a,
+	void (*pre_audit)(struct audit_buffer *, void *),
+	void (*post_audit)(struct audit_buffer *, void *));
 
 #endif
diff --git a/include/linux/mfd/88pm860x.h b/include/linux/mfd/88pm860x.h
index 92be3476c9f5..84d071ade1d8 100644
--- a/include/linux/mfd/88pm860x.h
+++ b/include/linux/mfd/88pm860x.h
@@ -263,6 +263,22 @@ enum {
 #define PM8607_PD_PREBIAS_MASK		(0x1F << 0)
 #define PM8607_PD_PRECHG_MASK		(7 << 5)
 
+#define PM8606_REF_GP_OSC_OFF         0
+#define PM8606_REF_GP_OSC_ON          1
+#define PM8606_REF_GP_OSC_UNKNOWN     2
+
+/* Clients of reference group and 8MHz oscillator in 88PM8606 */
+enum pm8606_ref_gp_and_osc_clients {
+	REF_GP_NO_CLIENTS       = 0,
+	WLED1_DUTY              = (1<<0), /*PF 0x02.7:0*/
+	WLED2_DUTY              = (1<<1), /*PF 0x04.7:0*/
+	WLED3_DUTY              = (1<<2), /*PF 0x06.7:0*/
+	RGB1_ENABLE             = (1<<3), /*PF 0x07.1*/
+	RGB2_ENABLE             = (1<<4), /*PF 0x07.2*/
+	LDO_VBR_EN              = (1<<5), /*PF 0x12.0*/
+	REF_GP_MAX_CLIENT       = 0xFFFF
+};
+
 /* Interrupt Number in 88PM8607 */
 enum {
 	PM8607_IRQ_ONKEY,
@@ -298,6 +314,7 @@ enum {
 struct pm860x_chip {
 	struct device		*dev;
 	struct mutex		irq_lock;
+	struct mutex		osc_lock;
 	struct i2c_client	*client;
 	struct i2c_client	*companion;	/* companion chip client */
 	struct regmap           *regmap;
@@ -305,12 +322,15 @@ struct pm860x_chip {
 
 	int			buck3_double;	/* DVC ramp slope double */
 	unsigned short		companion_addr;
+	unsigned short		osc_vote;
 	int			id;
 	int			irq_mode;
 	int			irq_base;
 	int			core_irq;
 	unsigned char		chip_version;
+	unsigned char		osc_status;
 
+	unsigned int            wakeup_flag;
 };
 
 enum {
@@ -369,6 +389,9 @@ struct pm860x_platform_data {
 	int		num_regulators;
 };
 
+extern int pm8606_osc_enable(struct pm860x_chip *, unsigned short);
+extern int pm8606_osc_disable(struct pm860x_chip *, unsigned short);
+
 extern int pm860x_reg_read(struct i2c_client *, int);
 extern int pm860x_reg_write(struct i2c_client *, int, unsigned char);
 extern int pm860x_bulk_read(struct i2c_client *, int, int, unsigned char *);
diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h
index e20dd6ead1d0..ee96cd51d8b2 100644
--- a/include/linux/mfd/abx500.h
+++ b/include/linux/mfd/abx500.h
@@ -34,13 +34,6 @@ struct device;
 #define AB5500_1_1	0x21
 #define AB5500_2_0	0x24
 
-/* AB8500 CIDs*/
-#define AB8500_CUT1P0	0x10
-#define AB8500_CUT1P1	0x11
-#define AB8500_CUT2P0	0x20
-#define AB8500_CUT3P0	0x30
-#define AB8500_CUT3P3	0x33
-
 /*
  * AB3100, EVENTA1, A2 and A3 event register flags
  * these are catenated into a single 32-bit flag in the code
@@ -153,6 +146,279 @@ struct abx500_init_settings {
 	u8 setting;
 };
 
+/* Battery driver related data */
+/*
+ * ADC for the battery thermistor.
+ * When using the ABx500_ADC_THERM_BATCTRL the battery ID resistor is combined
+ * with a NTC resistor to both identify the battery and to measure its
+ * temperature. Different phone manufactures uses different techniques to both
+ * identify the battery and to read its temperature.
+ */
+enum abx500_adc_therm {
+	ABx500_ADC_THERM_BATCTRL,
+	ABx500_ADC_THERM_BATTEMP,
+};
+
+/**
+ * struct abx500_res_to_temp - defines one point in a temp to res curve. To
+ * be used in battery packs that combines the identification resistor with a
+ * NTC resistor.
+ * @temp:			battery pack temperature in Celcius
+ * @resist:			NTC resistor net total resistance
+ */
+struct abx500_res_to_temp {
+	int temp;
+	int resist;
+};
+
+/**
+ * struct abx500_v_to_cap - Table for translating voltage to capacity
+ * @voltage:		Voltage in mV
+ * @capacity:		Capacity in percent
+ */
+struct abx500_v_to_cap {
+	int voltage;
+	int capacity;
+};
+
+/* Forward declaration */
+struct abx500_fg;
+
+/**
+ * struct abx500_fg_parameters - Fuel gauge algorithm parameters, in seconds
+ * if not specified
+ * @recovery_sleep_timer:	Time between measurements while recovering
+ * @recovery_total_time:	Total recovery time
+ * @init_timer:			Measurement interval during startup
+ * @init_discard_time:		Time we discard voltage measurement at startup
+ * @init_total_time:		Total init time during startup
+ * @high_curr_time:		Time current has to be high to go to recovery
+ * @accu_charging:		FG accumulation time while charging
+ * @accu_high_curr:		FG accumulation time in high current mode
+ * @high_curr_threshold:	High current threshold, in mA
+ * @lowbat_threshold:		Low battery threshold, in mV
+ * @overbat_threshold:		Over battery threshold, in mV
+ * @battok_falling_th_sel0	Threshold in mV for battOk signal sel0
+ *				Resolution in 50 mV step.
+ * @battok_raising_th_sel1	Threshold in mV for battOk signal sel1
+ *				Resolution in 50 mV step.
+ * @user_cap_limit		Capacity reported from user must be within this
+ *				limit to be considered as sane, in percentage
+ *				points.
+ * @maint_thres			This is the threshold where we stop reporting
+ *				battery full while in maintenance, in per cent
+ */
+struct abx500_fg_parameters {
+	int recovery_sleep_timer;
+	int recovery_total_time;
+	int init_timer;
+	int init_discard_time;
+	int init_total_time;
+	int high_curr_time;
+	int accu_charging;
+	int accu_high_curr;
+	int high_curr_threshold;
+	int lowbat_threshold;
+	int overbat_threshold;
+	int battok_falling_th_sel0;
+	int battok_raising_th_sel1;
+	int user_cap_limit;
+	int maint_thres;
+};
+
+/**
+ * struct abx500_charger_maximization - struct used by the board config.
+ * @use_maxi:		Enable maximization for this battery type
+ * @maxi_chg_curr:	Maximum charger current allowed
+ * @maxi_wait_cycles:	cycles to wait before setting charger current
+ * @charger_curr_step	delta between two charger current settings (mA)
+ */
+struct abx500_maxim_parameters {
+	bool ena_maxi;
+	int chg_curr;
+	int wait_cycles;
+	int charger_curr_step;
+};
+
+/**
+ * struct abx500_battery_type - different batteries supported
+ * @name:			battery technology
+ * @resis_high:			battery upper resistance limit
+ * @resis_low:			battery lower resistance limit
+ * @charge_full_design:		Maximum battery capacity in mAh
+ * @nominal_voltage:		Nominal voltage of the battery in mV
+ * @termination_vol:		max voltage upto which battery can be charged
+ * @termination_curr		battery charging termination current in mA
+ * @recharge_vol		battery voltage limit that will trigger a new
+ *				full charging cycle in the case where maintenan-
+ *				-ce charging has been disabled
+ * @normal_cur_lvl:		charger current in normal state in mA
+ * @normal_vol_lvl:		charger voltage in normal state in mV
+ * @maint_a_cur_lvl:		charger current in maintenance A state in mA
+ * @maint_a_vol_lvl:		charger voltage in maintenance A state in mV
+ * @maint_a_chg_timer_h:	charge time in maintenance A state
+ * @maint_b_cur_lvl:		charger current in maintenance B state in mA
+ * @maint_b_vol_lvl:		charger voltage in maintenance B state in mV
+ * @maint_b_chg_timer_h:	charge time in maintenance B state
+ * @low_high_cur_lvl:		charger current in temp low/high state in mA
+ * @low_high_vol_lvl:		charger voltage in temp low/high state in mV'
+ * @battery_resistance:		battery inner resistance in mOhm.
+ * @n_r_t_tbl_elements:		number of elements in r_to_t_tbl
+ * @r_to_t_tbl:			table containing resistance to temp points
+ * @n_v_cap_tbl_elements:	number of elements in v_to_cap_tbl
+ * @v_to_cap_tbl:		Voltage to capacity (in %) table
+ * @n_batres_tbl_elements	number of elements in the batres_tbl
+ * @batres_tbl			battery internal resistance vs temperature table
+ */
+struct abx500_battery_type {
+	int name;
+	int resis_high;
+	int resis_low;
+	int charge_full_design;
+	int nominal_voltage;
+	int termination_vol;
+	int termination_curr;
+	int recharge_vol;
+	int normal_cur_lvl;
+	int normal_vol_lvl;
+	int maint_a_cur_lvl;
+	int maint_a_vol_lvl;
+	int maint_a_chg_timer_h;
+	int maint_b_cur_lvl;
+	int maint_b_vol_lvl;
+	int maint_b_chg_timer_h;
+	int low_high_cur_lvl;
+	int low_high_vol_lvl;
+	int battery_resistance;
+	int n_temp_tbl_elements;
+	struct abx500_res_to_temp *r_to_t_tbl;
+	int n_v_cap_tbl_elements;
+	struct abx500_v_to_cap *v_to_cap_tbl;
+	int n_batres_tbl_elements;
+	struct batres_vs_temp *batres_tbl;
+};
+
+/**
+ * struct abx500_bm_capacity_levels - abx500 capacity level data
+ * @critical:		critical capacity level in percent
+ * @low:		low capacity level in percent
+ * @normal:		normal capacity level in percent
+ * @high:		high capacity level in percent
+ * @full:		full capacity level in percent
+ */
+struct abx500_bm_capacity_levels {
+	int critical;
+	int low;
+	int normal;
+	int high;
+	int full;
+};
+
+/**
+ * struct abx500_bm_charger_parameters - Charger specific parameters
+ * @usb_volt_max:	maximum allowed USB charger voltage in mV
+ * @usb_curr_max:	maximum allowed USB charger current in mA
+ * @ac_volt_max:	maximum allowed AC charger voltage in mV
+ * @ac_curr_max:	maximum allowed AC charger current in mA
+ */
+struct abx500_bm_charger_parameters {
+	int usb_volt_max;
+	int usb_curr_max;
+	int ac_volt_max;
+	int ac_curr_max;
+};
+
+/**
+ * struct abx500_bm_data - abx500 battery management data
+ * @temp_under		under this temp, charging is stopped
+ * @temp_low		between this temp and temp_under charging is reduced
+ * @temp_high		between this temp and temp_over charging is reduced
+ * @temp_over		over this temp, charging is stopped
+ * @temp_now		present battery temperature
+ * @temp_interval_chg	temperature measurement interval in s when charging
+ * @temp_interval_nochg	temperature measurement interval in s when not charging
+ * @main_safety_tmr_h	safety timer for main charger
+ * @usb_safety_tmr_h	safety timer for usb charger
+ * @bkup_bat_v		voltage which we charge the backup battery with
+ * @bkup_bat_i		current which we charge the backup battery with
+ * @no_maintenance	indicates that maintenance charging is disabled
+ * @abx500_adc_therm	placement of thermistor, batctrl or battemp adc
+ * @chg_unknown_bat	flag to enable charging of unknown batteries
+ * @enable_overshoot	flag to enable VBAT overshoot control
+ * @auto_trig		flag to enable auto adc trigger
+ * @fg_res		resistance of FG resistor in 0.1mOhm
+ * @n_btypes		number of elements in array bat_type
+ * @batt_id		index of the identified battery in array bat_type
+ * @interval_charging	charge alg cycle period time when charging (sec)
+ * @interval_not_charging charge alg cycle period time when not charging (sec)
+ * @temp_hysteresis	temperature hysteresis
+ * @gnd_lift_resistance	Battery ground to phone ground resistance (mOhm)
+ * @maxi:		maximization parameters
+ * @cap_levels		capacity in percent for the different capacity levels
+ * @bat_type		table of supported battery types
+ * @chg_params		charger parameters
+ * @fg_params		fuel gauge parameters
+ */
+struct abx500_bm_data {
+	int temp_under;
+	int temp_low;
+	int temp_high;
+	int temp_over;
+	int temp_now;
+	int temp_interval_chg;
+	int temp_interval_nochg;
+	int main_safety_tmr_h;
+	int usb_safety_tmr_h;
+	int bkup_bat_v;
+	int bkup_bat_i;
+	bool no_maintenance;
+	bool chg_unknown_bat;
+	bool enable_overshoot;
+	bool auto_trig;
+	enum abx500_adc_therm adc_therm;
+	int fg_res;
+	int n_btypes;
+	int batt_id;
+	int interval_charging;
+	int interval_not_charging;
+	int temp_hysteresis;
+	int gnd_lift_resistance;
+	const struct abx500_maxim_parameters *maxi;
+	const struct abx500_bm_capacity_levels *cap_levels;
+	const struct abx500_battery_type *bat_type;
+	const struct abx500_bm_charger_parameters *chg_params;
+	const struct abx500_fg_parameters *fg_params;
+};
+
+struct abx500_chargalg_platform_data {
+	char **supplied_to;
+	size_t num_supplicants;
+};
+
+struct abx500_charger_platform_data {
+	char **supplied_to;
+	size_t num_supplicants;
+	bool autopower_cfg;
+};
+
+struct abx500_btemp_platform_data {
+	char **supplied_to;
+	size_t num_supplicants;
+};
+
+struct abx500_fg_platform_data {
+	char **supplied_to;
+	size_t num_supplicants;
+};
+
+struct abx500_bm_plat_data {
+	struct abx500_bm_data *battery;
+	struct abx500_charger_platform_data *charger;
+	struct abx500_btemp_platform_data *btemp;
+	struct abx500_fg_platform_data *fg;
+	struct abx500_chargalg_platform_data *chargalg;
+};
+
 int abx500_set_register_interruptible(struct device *dev, u8 bank, u8 reg,
 	u8 value);
 int abx500_get_register_interruptible(struct device *dev, u8 bank, u8 reg,
diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h
new file mode 100644
index 000000000000..44310c98ee6e
--- /dev/null
+++ b/include/linux/mfd/abx500/ab8500-bm.h
@@ -0,0 +1,474 @@
+/*
+ * Copyright ST-Ericsson 2012.
+ *
+ * Author: Arun Murthy <arun.murthy@stericsson.com>
+ * Licensed under GPLv2.
+ */
+
+#ifndef _AB8500_BM_H
+#define _AB8500_BM_H
+
+#include <linux/kernel.h>
+#include <linux/mfd/abx500.h>
+
+/*
+ * System control 2 register offsets.
+ * bank = 0x02
+ */
+#define AB8500_MAIN_WDOG_CTRL_REG	0x01
+#define AB8500_LOW_BAT_REG		0x03
+#define AB8500_BATT_OK_REG		0x04
+/*
+ * USB/ULPI register offsets
+ * Bank : 0x5
+ */
+#define AB8500_USB_LINE_STAT_REG	0x80
+
+/*
+ * Charger / status register offfsets
+ * Bank : 0x0B
+ */
+#define AB8500_CH_STATUS1_REG		0x00
+#define AB8500_CH_STATUS2_REG		0x01
+#define AB8500_CH_USBCH_STAT1_REG	0x02
+#define AB8500_CH_USBCH_STAT2_REG	0x03
+#define AB8500_CH_FSM_STAT_REG		0x04
+#define AB8500_CH_STAT_REG		0x05
+
+/*
+ * Charger / control register offfsets
+ * Bank : 0x0B
+ */
+#define AB8500_CH_VOLT_LVL_REG		0x40
+#define AB8500_CH_VOLT_LVL_MAX_REG	0x41  /*Only in Cut2.0*/
+#define AB8500_CH_OPT_CRNTLVL_REG	0x42
+#define AB8500_CH_OPT_CRNTLVL_MAX_REG	0x43  /*Only in Cut2.0*/
+#define AB8500_CH_WD_TIMER_REG		0x50
+#define AB8500_CHARG_WD_CTRL		0x51
+#define AB8500_BTEMP_HIGH_TH		0x52
+#define AB8500_LED_INDICATOR_PWM_CTRL	0x53
+#define AB8500_LED_INDICATOR_PWM_DUTY	0x54
+#define AB8500_BATT_OVV			0x55
+#define AB8500_CHARGER_CTRL		0x56
+#define AB8500_BAT_CTRL_CURRENT_SOURCE	0x60  /*Only in Cut2.0*/
+
+/*
+ * Charger / main control register offsets
+ * Bank : 0x0B
+ */
+#define AB8500_MCH_CTRL1		0x80
+#define AB8500_MCH_CTRL2		0x81
+#define AB8500_MCH_IPT_CURLVL_REG	0x82
+#define AB8500_CH_WD_REG		0x83
+
+/*
+ * Charger / USB control register offsets
+ * Bank : 0x0B
+ */
+#define AB8500_USBCH_CTRL1_REG		0xC0
+#define AB8500_USBCH_CTRL2_REG		0xC1
+#define AB8500_USBCH_IPT_CRNTLVL_REG	0xC2
+
+/*
+ * Gas Gauge register offsets
+ * Bank : 0x0C
+ */
+#define AB8500_GASG_CC_CTRL_REG		0x00
+#define AB8500_GASG_CC_ACCU1_REG	0x01
+#define AB8500_GASG_CC_ACCU2_REG	0x02
+#define AB8500_GASG_CC_ACCU3_REG	0x03
+#define AB8500_GASG_CC_ACCU4_REG	0x04
+#define AB8500_GASG_CC_SMPL_CNTRL_REG	0x05
+#define AB8500_GASG_CC_SMPL_CNTRH_REG	0x06
+#define AB8500_GASG_CC_SMPL_CNVL_REG	0x07
+#define AB8500_GASG_CC_SMPL_CNVH_REG	0x08
+#define AB8500_GASG_CC_CNTR_AVGOFF_REG	0x09
+#define AB8500_GASG_CC_OFFSET_REG	0x0A
+#define AB8500_GASG_CC_NCOV_ACCU	0x10
+#define AB8500_GASG_CC_NCOV_ACCU_CTRL	0x11
+#define AB8500_GASG_CC_NCOV_ACCU_LOW	0x12
+#define AB8500_GASG_CC_NCOV_ACCU_MED	0x13
+#define AB8500_GASG_CC_NCOV_ACCU_HIGH	0x14
+
+/*
+ * Interrupt register offsets
+ * Bank : 0x0E
+ */
+#define AB8500_IT_SOURCE2_REG		0x01
+#define AB8500_IT_SOURCE21_REG		0x14
+
+/*
+ * RTC register offsets
+ * Bank: 0x0F
+ */
+#define AB8500_RTC_BACKUP_CHG_REG	0x0C
+#define AB8500_RTC_CC_CONF_REG		0x01
+#define AB8500_RTC_CTRL_REG		0x0B
+
+/*
+ * OTP register offsets
+ * Bank : 0x15
+ */
+#define AB8500_OTP_CONF_15		0x0E
+
+/* GPADC constants from AB8500 spec, UM0836 */
+#define ADC_RESOLUTION			1024
+#define ADC_CH_MAIN_MIN			0
+#define ADC_CH_MAIN_MAX			20030
+#define ADC_CH_VBUS_MIN			0
+#define ADC_CH_VBUS_MAX			20030
+#define ADC_CH_VBAT_MIN			2300
+#define ADC_CH_VBAT_MAX			4800
+#define ADC_CH_BKBAT_MIN		0
+#define ADC_CH_BKBAT_MAX		3200
+
+/* Main charge i/p current */
+#define MAIN_CH_IP_CUR_0P9A		0x80
+#define MAIN_CH_IP_CUR_1P0A		0x90
+#define MAIN_CH_IP_CUR_1P1A		0xA0
+#define MAIN_CH_IP_CUR_1P2A		0xB0
+#define MAIN_CH_IP_CUR_1P3A		0xC0
+#define MAIN_CH_IP_CUR_1P4A		0xD0
+#define MAIN_CH_IP_CUR_1P5A		0xE0
+
+/* ChVoltLevel */
+#define CH_VOL_LVL_3P5			0x00
+#define CH_VOL_LVL_4P0			0x14
+#define CH_VOL_LVL_4P05			0x16
+#define CH_VOL_LVL_4P1			0x1B
+#define CH_VOL_LVL_4P15			0x20
+#define CH_VOL_LVL_4P2			0x25
+#define CH_VOL_LVL_4P6			0x4D
+
+/* ChOutputCurrentLevel */
+#define CH_OP_CUR_LVL_0P1		0x00
+#define CH_OP_CUR_LVL_0P2		0x01
+#define CH_OP_CUR_LVL_0P3		0x02
+#define CH_OP_CUR_LVL_0P4		0x03
+#define CH_OP_CUR_LVL_0P5		0x04
+#define CH_OP_CUR_LVL_0P6		0x05
+#define CH_OP_CUR_LVL_0P7		0x06
+#define CH_OP_CUR_LVL_0P8		0x07
+#define CH_OP_CUR_LVL_0P9		0x08
+#define CH_OP_CUR_LVL_1P4		0x0D
+#define CH_OP_CUR_LVL_1P5		0x0E
+#define CH_OP_CUR_LVL_1P6		0x0F
+
+/* BTEMP High thermal limits */
+#define BTEMP_HIGH_TH_57_0		0x00
+#define BTEMP_HIGH_TH_52		0x01
+#define BTEMP_HIGH_TH_57_1		0x02
+#define BTEMP_HIGH_TH_62		0x03
+
+/* current is mA */
+#define USB_0P1A			100
+#define USB_0P2A			200
+#define USB_0P3A			300
+#define USB_0P4A			400
+#define USB_0P5A			500
+
+#define LOW_BAT_3P1V			0x20
+#define LOW_BAT_2P3V			0x00
+#define LOW_BAT_RESET			0x01
+#define LOW_BAT_ENABLE			0x01
+
+/* Backup battery constants */
+#define BUP_ICH_SEL_50UA		0x00
+#define BUP_ICH_SEL_150UA		0x04
+#define BUP_ICH_SEL_300UA		0x08
+#define BUP_ICH_SEL_700UA		0x0C
+
+#define BUP_VCH_SEL_2P5V		0x00
+#define BUP_VCH_SEL_2P6V		0x01
+#define BUP_VCH_SEL_2P8V		0x02
+#define BUP_VCH_SEL_3P1V		0x03
+
+/* Battery OVV constants */
+#define BATT_OVV_ENA			0x02
+#define BATT_OVV_TH_3P7			0x00
+#define BATT_OVV_TH_4P75		0x01
+
+/* A value to indicate over voltage */
+#define BATT_OVV_VALUE			4750
+
+/* VBUS OVV constants */
+#define VBUS_OVV_SELECT_MASK		0x78
+#define VBUS_OVV_SELECT_5P6V		0x00
+#define VBUS_OVV_SELECT_5P7V		0x08
+#define VBUS_OVV_SELECT_5P8V		0x10
+#define VBUS_OVV_SELECT_5P9V		0x18
+#define VBUS_OVV_SELECT_6P0V		0x20
+#define VBUS_OVV_SELECT_6P1V		0x28
+#define VBUS_OVV_SELECT_6P2V		0x30
+#define VBUS_OVV_SELECT_6P3V		0x38
+
+#define VBUS_AUTO_IN_CURR_LIM_ENA	0x04
+
+/* Fuel Gauge constants */
+#define RESET_ACCU			0x02
+#define READ_REQ			0x01
+#define CC_DEEP_SLEEP_ENA		0x02
+#define CC_PWR_UP_ENA			0x01
+#define CC_SAMPLES_40			0x28
+#define RD_NCONV_ACCU_REQ		0x01
+#define CC_CALIB			0x08
+#define CC_INTAVGOFFSET_ENA		0x10
+#define CC_MUXOFFSET			0x80
+#define CC_INT_CAL_N_AVG_MASK		0x60
+#define CC_INT_CAL_SAMPLES_16		0x40
+#define CC_INT_CAL_SAMPLES_8		0x20
+#define CC_INT_CAL_SAMPLES_4		0x00
+
+/* RTC constants */
+#define RTC_BUP_CH_ENA			0x10
+
+/* BatCtrl Current Source Constants */
+#define BAT_CTRL_7U_ENA			0x01
+#define BAT_CTRL_20U_ENA		0x02
+#define BAT_CTRL_CMP_ENA		0x04
+#define FORCE_BAT_CTRL_CMP_HIGH		0x08
+#define BAT_CTRL_PULL_UP_ENA		0x10
+
+/* Battery type */
+#define BATTERY_UNKNOWN			00
+
+/**
+ * struct res_to_temp - defines one point in a temp to res curve. To
+ * be used in battery packs that combines the identification resistor with a
+ * NTC resistor.
+ * @temp:			battery pack temperature in Celcius
+ * @resist:			NTC resistor net total resistance
+ */
+struct res_to_temp {
+	int temp;
+	int resist;
+};
+
+/**
+ * struct batres_vs_temp - defines one point in a temp vs battery internal
+ * resistance curve.
+ * @temp:			battery pack temperature in Celcius
+ * @resist:			battery internal reistance in mOhm
+ */
+struct batres_vs_temp {
+	int temp;
+	int resist;
+};
+
+/* Forward declaration */
+struct ab8500_fg;
+
+/**
+ * struct ab8500_fg_parameters - Fuel gauge algorithm parameters, in seconds
+ * if not specified
+ * @recovery_sleep_timer:	Time between measurements while recovering
+ * @recovery_total_time:	Total recovery time
+ * @init_timer:			Measurement interval during startup
+ * @init_discard_time:		Time we discard voltage measurement at startup
+ * @init_total_time:		Total init time during startup
+ * @high_curr_time:		Time current has to be high to go to recovery
+ * @accu_charging:		FG accumulation time while charging
+ * @accu_high_curr:		FG accumulation time in high current mode
+ * @high_curr_threshold:	High current threshold, in mA
+ * @lowbat_threshold:		Low battery threshold, in mV
+ * @battok_falling_th_sel0	Threshold in mV for battOk signal sel0
+ *				Resolution in 50 mV step.
+ * @battok_raising_th_sel1	Threshold in mV for battOk signal sel1
+ *				Resolution in 50 mV step.
+ * @user_cap_limit		Capacity reported from user must be within this
+ *				limit to be considered as sane, in percentage
+ *				points.
+ * @maint_thres			This is the threshold where we stop reporting
+ *				battery full while in maintenance, in per cent
+ */
+struct ab8500_fg_parameters {
+	int recovery_sleep_timer;
+	int recovery_total_time;
+	int init_timer;
+	int init_discard_time;
+	int init_total_time;
+	int high_curr_time;
+	int accu_charging;
+	int accu_high_curr;
+	int high_curr_threshold;
+	int lowbat_threshold;
+	int battok_falling_th_sel0;
+	int battok_raising_th_sel1;
+	int user_cap_limit;
+	int maint_thres;
+};
+
+/**
+ * struct ab8500_charger_maximization - struct used by the board config.
+ * @use_maxi:		Enable maximization for this battery type
+ * @maxi_chg_curr:	Maximum charger current allowed
+ * @maxi_wait_cycles:	cycles to wait before setting charger current
+ * @charger_curr_step	delta between two charger current settings (mA)
+ */
+struct ab8500_maxim_parameters {
+	bool ena_maxi;
+	int chg_curr;
+	int wait_cycles;
+	int charger_curr_step;
+};
+
+/**
+ * struct ab8500_bm_capacity_levels - ab8500 capacity level data
+ * @critical:		critical capacity level in percent
+ * @low:		low capacity level in percent
+ * @normal:		normal capacity level in percent
+ * @high:		high capacity level in percent
+ * @full:		full capacity level in percent
+ */
+struct ab8500_bm_capacity_levels {
+	int critical;
+	int low;
+	int normal;
+	int high;
+	int full;
+};
+
+/**
+ * struct ab8500_bm_charger_parameters - Charger specific parameters
+ * @usb_volt_max:	maximum allowed USB charger voltage in mV
+ * @usb_curr_max:	maximum allowed USB charger current in mA
+ * @ac_volt_max:	maximum allowed AC charger voltage in mV
+ * @ac_curr_max:	maximum allowed AC charger current in mA
+ */
+struct ab8500_bm_charger_parameters {
+	int usb_volt_max;
+	int usb_curr_max;
+	int ac_volt_max;
+	int ac_curr_max;
+};
+
+/**
+ * struct ab8500_bm_data - ab8500 battery management data
+ * @temp_under		under this temp, charging is stopped
+ * @temp_low		between this temp and temp_under charging is reduced
+ * @temp_high		between this temp and temp_over charging is reduced
+ * @temp_over		over this temp, charging is stopped
+ * @temp_interval_chg	temperature measurement interval in s when charging
+ * @temp_interval_nochg	temperature measurement interval in s when not charging
+ * @main_safety_tmr_h	safety timer for main charger
+ * @usb_safety_tmr_h	safety timer for usb charger
+ * @bkup_bat_v		voltage which we charge the backup battery with
+ * @bkup_bat_i		current which we charge the backup battery with
+ * @no_maintenance	indicates that maintenance charging is disabled
+ * @adc_therm		placement of thermistor, batctrl or battemp adc
+ * @chg_unknown_bat	flag to enable charging of unknown batteries
+ * @enable_overshoot	flag to enable VBAT overshoot control
+ * @fg_res		resistance of FG resistor in 0.1mOhm
+ * @n_btypes		number of elements in array bat_type
+ * @batt_id		index of the identified battery in array bat_type
+ * @interval_charging	charge alg cycle period time when charging (sec)
+ * @interval_not_charging charge alg cycle period time when not charging (sec)
+ * @temp_hysteresis	temperature hysteresis
+ * @gnd_lift_resistance	Battery ground to phone ground resistance (mOhm)
+ * @maxi:		maximization parameters
+ * @cap_levels		capacity in percent for the different capacity levels
+ * @bat_type		table of supported battery types
+ * @chg_params		charger parameters
+ * @fg_params		fuel gauge parameters
+ */
+struct ab8500_bm_data {
+	int temp_under;
+	int temp_low;
+	int temp_high;
+	int temp_over;
+	int temp_interval_chg;
+	int temp_interval_nochg;
+	int main_safety_tmr_h;
+	int usb_safety_tmr_h;
+	int bkup_bat_v;
+	int bkup_bat_i;
+	bool no_maintenance;
+	bool chg_unknown_bat;
+	bool enable_overshoot;
+	enum abx500_adc_therm adc_therm;
+	int fg_res;
+	int n_btypes;
+	int batt_id;
+	int interval_charging;
+	int interval_not_charging;
+	int temp_hysteresis;
+	int gnd_lift_resistance;
+	const struct ab8500_maxim_parameters *maxi;
+	const struct ab8500_bm_capacity_levels *cap_levels;
+	const struct ab8500_bm_charger_parameters *chg_params;
+	const struct ab8500_fg_parameters *fg_params;
+};
+
+struct ab8500_charger_platform_data {
+	char **supplied_to;
+	size_t num_supplicants;
+	bool autopower_cfg;
+};
+
+struct ab8500_btemp_platform_data {
+	char **supplied_to;
+	size_t num_supplicants;
+};
+
+struct ab8500_fg_platform_data {
+	char **supplied_to;
+	size_t num_supplicants;
+};
+
+struct ab8500_chargalg_platform_data {
+	char **supplied_to;
+	size_t num_supplicants;
+};
+struct ab8500_btemp;
+struct ab8500_gpadc;
+struct ab8500_fg;
+#ifdef CONFIG_AB8500_BM
+void ab8500_fg_reinit(void);
+void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA);
+struct ab8500_btemp *ab8500_btemp_get(void);
+int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp);
+struct ab8500_fg *ab8500_fg_get(void);
+int ab8500_fg_inst_curr_blocking(struct ab8500_fg *dev);
+int ab8500_fg_inst_curr_start(struct ab8500_fg *di);
+int ab8500_fg_inst_curr_finalize(struct ab8500_fg *di, int *res);
+int ab8500_fg_inst_curr_done(struct ab8500_fg *di);
+
+#else
+int ab8500_fg_inst_curr_done(struct ab8500_fg *di)
+{
+}
+static void ab8500_fg_reinit(void)
+{
+}
+static void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA)
+{
+}
+static struct ab8500_btemp *ab8500_btemp_get(void)
+{
+	return NULL;
+}
+static int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp)
+{
+	return 0;
+}
+struct ab8500_fg *ab8500_fg_get(void)
+{
+	return NULL;
+}
+static int ab8500_fg_inst_curr_blocking(struct ab8500_fg *dev)
+{
+	return -ENODEV;
+}
+
+static inline int ab8500_fg_inst_curr_start(struct ab8500_fg *di)
+{
+	return -ENODEV;
+}
+
+static inline int ab8500_fg_inst_curr_finalize(struct ab8500_fg *di, int *res)
+{
+	return -ENODEV;
+}
+
+#endif
+#endif /* _AB8500_BM_H */
diff --git a/include/linux/mfd/abx500/ab8500-gpio.h b/include/linux/mfd/abx500/ab8500-gpio.h
index 488a8c920a29..2387c207ea86 100644
--- a/include/linux/mfd/abx500/ab8500-gpio.h
+++ b/include/linux/mfd/abx500/ab8500-gpio.h
@@ -10,12 +10,14 @@
 
 /*
  * Platform data to register a block: only the initial gpio/irq number.
+ * Array sizes are large enough to contain all AB8500 and AB9540 GPIO
+ * registers.
  */
 
 struct ab8500_gpio_platform_data {
 	int gpio_base;
 	u32 irq_base;
-	u8  config_reg[7];
+	u8  config_reg[8];
 };
 
 #endif /* _AB8500_GPIO_H */
diff --git a/include/linux/mfd/abx500/ab8500-sysctrl.h b/include/linux/mfd/abx500/ab8500-sysctrl.h
index 10da0291f8f8..10eb50973c39 100644
--- a/include/linux/mfd/abx500/ab8500-sysctrl.h
+++ b/include/linux/mfd/abx500/ab8500-sysctrl.h
@@ -71,6 +71,13 @@ static inline int ab8500_sysctrl_clear(u16 reg, u8 bits)
 #define AB8500_SWATCTRL			0x230
 #define AB8500_HIQCLKCTRL		0x232
 #define AB8500_VSIMSYSCLKCTRL		0x233
+#define AB9540_SYSCLK12BUFCTRL		0x234
+#define AB9540_SYSCLK12CONFCTRL		0x235
+#define AB9540_SYSCLK12BUFCTRL2		0x236
+#define AB9540_SYSCLK12BUF1VALID	0x237
+#define AB9540_SYSCLK12BUF2VALID	0x238
+#define AB9540_SYSCLK12BUF3VALID	0x239
+#define AB9540_SYSCLK12BUF4VALID	0x23A
 
 /* Bits */
 #define AB8500_TURNONSTATUS_PORNVBAT BIT(0)
@@ -251,4 +258,40 @@ static inline int ab8500_sysctrl_clear(u16 reg, u8 bits)
 #define AB8500_VSIMSYSCLKCTRL_VSIMSYSCLKREQ7VALID BIT(6)
 #define AB8500_VSIMSYSCLKCTRL_VSIMSYSCLKREQ8VALID BIT(7)
 
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUF1ENA BIT(0)
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUF2ENA BIT(1)
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUF3ENA BIT(2)
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUF4ENA BIT(3)
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUFENA_MASK 0x0F
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUF1STRE BIT(4)
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUF2STRE BIT(5)
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUF3STRE BIT(6)
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUF4STRE BIT(7)
+#define AB9540_SYSCLK12BUFCTRL_SYSCLK12BUFSTRE_MASK 0xF0
+
+#define AB9540_SYSCLK12CONFCTRL_PLL26TO38ENA BIT(0)
+#define AB9540_SYSCLK12CONFCTRL_SYSCLK12USBMUXSEL BIT(1)
+#define AB9540_SYSCLK12CONFCTRL_INT384MHZMUXSEL_MASK 0x0C
+#define AB9540_SYSCLK12CONFCTRL_INT384MHZMUXSEL_SHIFT 2
+#define AB9540_SYSCLK12CONFCTRL_SYSCLK12BUFMUX BIT(4)
+#define AB9540_SYSCLK12CONFCTRL_SYSCLK12PLLMUX BIT(5)
+#define AB9540_SYSCLK12CONFCTRL_SYSCLK2MUXVALID BIT(6)
+
+#define AB9540_SYSCLK12BUFCTRL2_SYSCLK12BUF1PDENA BIT(0)
+#define AB9540_SYSCLK12BUFCTRL2_SYSCLK12BUF2PDENA BIT(1)
+#define AB9540_SYSCLK12BUFCTRL2_SYSCLK12BUF3PDENA BIT(2)
+#define AB9540_SYSCLK12BUFCTRL2_SYSCLK12BUF4PDENA BIT(3)
+
+#define AB9540_SYSCLK12BUF1VALID_SYSCLK12BUF1VALID_MASK 0xFF
+#define AB9540_SYSCLK12BUF1VALID_SYSCLK12BUF1VALID_SHIFT 0
+
+#define AB9540_SYSCLK12BUF2VALID_SYSCLK12BUF2VALID_MASK 0xFF
+#define AB9540_SYSCLK12BUF2VALID_SYSCLK12BUF2VALID_SHIFT 0
+
+#define AB9540_SYSCLK12BUF3VALID_SYSCLK12BUF3VALID_MASK 0xFF
+#define AB9540_SYSCLK12BUF3VALID_SYSCLK12BUF3VALID_SHIFT 0
+
+#define AB9540_SYSCLK12BUF4VALID_SYSCLK12BUF4VALID_MASK 0xFF
+#define AB9540_SYSCLK12BUF4VALID_SYSCLK12BUF4VALID_SHIFT 0
+
 #endif /* __AB8500_SYSCTRL_H */
diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h
index dca94396190d..fccc3002f271 100644
--- a/include/linux/mfd/abx500/ab8500.h
+++ b/include/linux/mfd/abx500/ab8500.h
@@ -12,6 +12,29 @@
 struct device;
 
 /*
+ * AB IC versions
+ *
+ * AB8500_VERSION_AB8500 should be 0xFF but will never be read as need a
+ * non-supported multi-byte I2C access via PRCMU. Set to 0x00 to ease the
+ * print of version string.
+ */
+enum ab8500_version {
+	AB8500_VERSION_AB8500 = 0x0,
+	AB8500_VERSION_AB8505 = 0x1,
+	AB8500_VERSION_AB9540 = 0x2,
+	AB8500_VERSION_AB8540 = 0x3,
+	AB8500_VERSION_UNDEFINED,
+};
+
+/* AB8500 CIDs*/
+#define AB8500_CUTEARLY	0x00
+#define AB8500_CUT1P0	0x10
+#define AB8500_CUT1P1	0x11
+#define AB8500_CUT2P0	0x20
+#define AB8500_CUT3P0	0x30
+#define AB8500_CUT3P3	0x33
+
+/*
  * AB8500 bank addresses
  */
 #define AB8500_SYS_CTRL1_BLOCK	0x1
@@ -37,30 +60,34 @@ struct device;
 
 /*
  * Interrupts
+ * Values used to index into array ab8500_irq_regoffset[] defined in
+ * drivers/mdf/ab8500-core.c
  */
-
-#define AB8500_INT_MAIN_EXT_CH_NOT_OK	0
-#define AB8500_INT_UN_PLUG_TV_DET	1
-#define AB8500_INT_PLUG_TV_DET		2
+/* Definitions for AB8500 and AB9540 */
+/* ab8500_irq_regoffset[0] -> IT[Source|Latch|Mask]1 */
+#define AB8500_INT_MAIN_EXT_CH_NOT_OK	0 /* not 8505/9540 */
+#define AB8500_INT_UN_PLUG_TV_DET	1 /* not 8505/9540 */
+#define AB8500_INT_PLUG_TV_DET		2 /* not 8505/9540 */
 #define AB8500_INT_TEMP_WARM		3
 #define AB8500_INT_PON_KEY2DB_F		4
 #define AB8500_INT_PON_KEY2DB_R		5
 #define AB8500_INT_PON_KEY1DB_F		6
 #define AB8500_INT_PON_KEY1DB_R		7
+/* ab8500_irq_regoffset[1] -> IT[Source|Latch|Mask]2 */
 #define AB8500_INT_BATT_OVV		8
-#define AB8500_INT_MAIN_CH_UNPLUG_DET	10
-#define AB8500_INT_MAIN_CH_PLUG_DET	11
-#define AB8500_INT_USB_ID_DET_F		12
-#define AB8500_INT_USB_ID_DET_R		13
+#define AB8500_INT_MAIN_CH_UNPLUG_DET	10 /* not 8505 */
+#define AB8500_INT_MAIN_CH_PLUG_DET	11 /* not 8505 */
 #define AB8500_INT_VBUS_DET_F		14
 #define AB8500_INT_VBUS_DET_R		15
+/* ab8500_irq_regoffset[2] -> IT[Source|Latch|Mask]3 */
 #define AB8500_INT_VBUS_CH_DROP_END	16
 #define AB8500_INT_RTC_60S		17
 #define AB8500_INT_RTC_ALARM		18
 #define AB8500_INT_BAT_CTRL_INDB	20
 #define AB8500_INT_CH_WD_EXP		21
 #define AB8500_INT_VBUS_OVV		22
-#define AB8500_INT_MAIN_CH_DROP_END	23
+#define AB8500_INT_MAIN_CH_DROP_END	23 /* not 8505/9540 */
+/* ab8500_irq_regoffset[3] -> IT[Source|Latch|Mask]4 */
 #define AB8500_INT_CCN_CONV_ACC		24
 #define AB8500_INT_INT_AUD		25
 #define AB8500_INT_CCEOC		26
@@ -69,7 +96,8 @@ struct device;
 #define AB8500_INT_LOW_BAT_R		29
 #define AB8500_INT_BUP_CHG_NOT_OK	30
 #define AB8500_INT_BUP_CHG_OK		31
-#define AB8500_INT_GP_HW_ADC_CONV_END	32
+/* ab8500_irq_regoffset[4] -> IT[Source|Latch|Mask]5 */
+#define AB8500_INT_GP_HW_ADC_CONV_END	32 /* not 8505 */
 #define AB8500_INT_ACC_DETECT_1DB_F	33
 #define AB8500_INT_ACC_DETECT_1DB_R	34
 #define AB8500_INT_ACC_DETECT_22DB_F	35
@@ -77,38 +105,43 @@ struct device;
 #define AB8500_INT_ACC_DETECT_21DB_F	37
 #define AB8500_INT_ACC_DETECT_21DB_R	38
 #define AB8500_INT_GP_SW_ADC_CONV_END	39
-#define AB8500_INT_GPIO6R		40
-#define AB8500_INT_GPIO7R		41
-#define AB8500_INT_GPIO8R		42
-#define AB8500_INT_GPIO9R		43
+/* ab8500_irq_regoffset[5] -> IT[Source|Latch|Mask]7 */
+#define AB8500_INT_GPIO6R		40 /* not 8505/9540 */
+#define AB8500_INT_GPIO7R		41 /* not 8505/9540 */
+#define AB8500_INT_GPIO8R		42 /* not 8505/9540 */
+#define AB8500_INT_GPIO9R		43 /* not 8505/9540 */
 #define AB8500_INT_GPIO10R		44
 #define AB8500_INT_GPIO11R		45
-#define AB8500_INT_GPIO12R		46
+#define AB8500_INT_GPIO12R		46 /* not 8505 */
 #define AB8500_INT_GPIO13R		47
-#define AB8500_INT_GPIO24R		48
-#define AB8500_INT_GPIO25R		49
-#define AB8500_INT_GPIO36R		50
-#define AB8500_INT_GPIO37R		51
-#define AB8500_INT_GPIO38R		52
-#define AB8500_INT_GPIO39R		53
+/* ab8500_irq_regoffset[6] -> IT[Source|Latch|Mask]8 */
+#define AB8500_INT_GPIO24R		48 /* not 8505 */
+#define AB8500_INT_GPIO25R		49 /* not 8505 */
+#define AB8500_INT_GPIO36R		50 /* not 8505/9540 */
+#define AB8500_INT_GPIO37R		51 /* not 8505/9540 */
+#define AB8500_INT_GPIO38R		52 /* not 8505/9540 */
+#define AB8500_INT_GPIO39R		53 /* not 8505/9540 */
 #define AB8500_INT_GPIO40R		54
 #define AB8500_INT_GPIO41R		55
-#define AB8500_INT_GPIO6F		56
-#define AB8500_INT_GPIO7F		57
-#define AB8500_INT_GPIO8F		58
-#define AB8500_INT_GPIO9F		59
+/* ab8500_irq_regoffset[7] -> IT[Source|Latch|Mask]9 */
+#define AB8500_INT_GPIO6F		56 /* not 8505/9540 */
+#define AB8500_INT_GPIO7F		57 /* not 8505/9540 */
+#define AB8500_INT_GPIO8F		58 /* not 8505/9540 */
+#define AB8500_INT_GPIO9F		59 /* not 8505/9540 */
 #define AB8500_INT_GPIO10F		60
 #define AB8500_INT_GPIO11F		61
-#define AB8500_INT_GPIO12F		62
+#define AB8500_INT_GPIO12F		62 /* not 8505 */
 #define AB8500_INT_GPIO13F		63
-#define AB8500_INT_GPIO24F		64
-#define AB8500_INT_GPIO25F		65
-#define AB8500_INT_GPIO36F		66
-#define AB8500_INT_GPIO37F		67
-#define AB8500_INT_GPIO38F		68
-#define AB8500_INT_GPIO39F		69
+/* ab8500_irq_regoffset[8] -> IT[Source|Latch|Mask]10 */
+#define AB8500_INT_GPIO24F		64 /* not 8505 */
+#define AB8500_INT_GPIO25F		65 /* not 8505 */
+#define AB8500_INT_GPIO36F		66 /* not 8505/9540 */
+#define AB8500_INT_GPIO37F		67 /* not 8505/9540 */
+#define AB8500_INT_GPIO38F		68 /* not 8505/9540 */
+#define AB8500_INT_GPIO39F		69 /* not 8505/9540 */
 #define AB8500_INT_GPIO40F		70
 #define AB8500_INT_GPIO41F		71
+/* ab8500_irq_regoffset[9] -> IT[Source|Latch|Mask]12 */
 #define AB8500_INT_ADP_SOURCE_ERROR	72
 #define AB8500_INT_ADP_SINK_ERROR	73
 #define AB8500_INT_ADP_PROBE_PLUG	74
@@ -116,30 +149,67 @@ struct device;
 #define AB8500_INT_ADP_SENSE_OFF	76
 #define AB8500_INT_USB_PHY_POWER_ERR	78
 #define AB8500_INT_USB_LINK_STATUS	79
+/* ab8500_irq_regoffset[10] -> IT[Source|Latch|Mask]19 */
 #define AB8500_INT_BTEMP_LOW		80
 #define AB8500_INT_BTEMP_LOW_MEDIUM	81
 #define AB8500_INT_BTEMP_MEDIUM_HIGH	82
 #define AB8500_INT_BTEMP_HIGH		83
-#define AB8500_INT_USB_CHARGER_NOT_OK	89
+/* ab8500_irq_regoffset[11] -> IT[Source|Latch|Mask]20 */
+#define AB8500_INT_SRP_DETECT		88
+#define AB8500_INT_USB_CHARGER_NOT_OKR	89
 #define AB8500_INT_ID_WAKEUP_R		90
 #define AB8500_INT_ID_DET_R1R		92
 #define AB8500_INT_ID_DET_R2R		93
 #define AB8500_INT_ID_DET_R3R		94
 #define AB8500_INT_ID_DET_R4R		95
+/* ab8500_irq_regoffset[12] -> IT[Source|Latch|Mask]21 */
 #define AB8500_INT_ID_WAKEUP_F		96
 #define AB8500_INT_ID_DET_R1F		98
 #define AB8500_INT_ID_DET_R2F		99
 #define AB8500_INT_ID_DET_R3F		100
 #define AB8500_INT_ID_DET_R4F		101
-#define AB8500_INT_USB_CHG_DET_DONE	102
+#define AB8500_INT_CHAUTORESTARTAFTSEC  102
+#define AB8500_INT_CHSTOPBYSEC		103
+/* ab8500_irq_regoffset[13] -> IT[Source|Latch|Mask]22 */
 #define AB8500_INT_USB_CH_TH_PROT_F	104
 #define AB8500_INT_USB_CH_TH_PROT_R    105
-#define AB8500_INT_MAIN_CH_TH_PROT_F   106
-#define AB8500_INT_MAIN_CH_TH_PROT_R	107
-#define AB8500_INT_USB_CHARGER_NOT_OKF	111
+#define AB8500_INT_MAIN_CH_TH_PROT_F	106 /* not 8505/9540 */
+#define AB8500_INT_MAIN_CH_TH_PROT_R	107 /* not 8505/9540 */
+#define AB8500_INT_CHCURLIMNOHSCHIRP	109
+#define AB8500_INT_CHCURLIMHSCHIRP	110
+#define AB8500_INT_XTAL32K_KO		111
+
+/* Definitions for AB9540 */
+/* ab8500_irq_regoffset[14] -> IT[Source|Latch|Mask]13 */
+#define AB9540_INT_GPIO50R		113
+#define AB9540_INT_GPIO51R		114 /* not 8505 */
+#define AB9540_INT_GPIO52R		115
+#define AB9540_INT_GPIO53R		116
+#define AB9540_INT_GPIO54R		117 /* not 8505 */
+#define AB9540_INT_IEXT_CH_RF_BFN_R	118
+#define AB9540_INT_IEXT_CH_RF_BFN_F	119
+/* ab8500_irq_regoffset[15] -> IT[Source|Latch|Mask]14 */
+#define AB9540_INT_GPIO50F		121
+#define AB9540_INT_GPIO51F		122 /* not 8505 */
+#define AB9540_INT_GPIO52F		123
+#define AB9540_INT_GPIO53F		124
+#define AB9540_INT_GPIO54F		125 /* not 8505 */
 
+/*
+ * AB8500_AB9540_NR_IRQS is used when configuring the IRQ numbers for the
+ * entire platform. This is a "compile time" constant so this must be set to
+ * the largest possible value that may be encountered with different AB SOCs.
+ * Of the currently supported AB devices, AB8500 and AB9540, it is the AB9540
+ * which is larger.
+ */
 #define AB8500_NR_IRQS			112
+#define AB8505_NR_IRQS			128
+#define AB9540_NR_IRQS			128
+/* This is set to the roof of any AB8500 chip variant IRQ counts */
+#define AB8500_MAX_NR_IRQS		AB9540_NR_IRQS
+
 #define AB8500_NUM_IRQ_REGS		14
+#define AB9540_NUM_IRQ_REGS		17
 
 /**
  * struct ab8500 - ab8500 internal structure
@@ -147,13 +217,18 @@ struct device;
  * @lock: read/write operations lock
  * @irq_lock: genirq bus lock
  * @irq: irq line
+ * @version: chip version id (e.g. ab8500 or ab9540)
  * @chip_id: chip revision id
  * @write: register write
+ * @write_masked: masked register write
  * @read: register read
  * @rx_buf: rx buf for SPI
  * @tx_buf: tx buf for SPI
  * @mask: cache of IRQ regs for bus lock
  * @oldmask: cache of previous IRQ regs for bus lock
+ * @mask_size: Actual number of valid entries in mask[], oldmask[] and
+ * irq_reg_offset
+ * @irq_reg_offset: Array of offsets into IRQ registers
  */
 struct ab8500 {
 	struct device	*dev;
@@ -162,16 +237,20 @@ struct ab8500 {
 
 	int		irq_base;
 	int		irq;
+	enum ab8500_version version;
 	u8		chip_id;
 
-	int (*write) (struct ab8500 *a8500, u16 addr, u8 data);
-	int (*read) (struct ab8500 *a8500, u16 addr);
+	int (*write)(struct ab8500 *ab8500, u16 addr, u8 data);
+	int (*write_masked)(struct ab8500 *ab8500, u16 addr, u8 mask, u8 data);
+	int (*read)(struct ab8500 *ab8500, u16 addr);
 
 	unsigned long	tx_buf[4];
 	unsigned long	rx_buf[4];
 
-	u8 mask[AB8500_NUM_IRQ_REGS];
-	u8 oldmask[AB8500_NUM_IRQ_REGS];
+	u8 *mask;
+	u8 *oldmask;
+	int mask_size;
+	const int *irq_reg_offset;
 };
 
 struct regulator_reg_init;
@@ -197,7 +276,52 @@ struct ab8500_platform_data {
 	struct ab8500_gpio_platform_data *gpio;
 };
 
-extern int __devinit ab8500_init(struct ab8500 *ab8500);
+extern int __devinit ab8500_init(struct ab8500 *ab8500,
+				 enum ab8500_version version);
 extern int __devexit ab8500_exit(struct ab8500 *ab8500);
 
+static inline int is_ab8500(struct ab8500 *ab)
+{
+	return ab->version == AB8500_VERSION_AB8500;
+}
+
+static inline int is_ab8505(struct ab8500 *ab)
+{
+	return ab->version == AB8500_VERSION_AB8505;
+}
+
+static inline int is_ab9540(struct ab8500 *ab)
+{
+	return ab->version == AB8500_VERSION_AB9540;
+}
+
+static inline int is_ab8540(struct ab8500 *ab)
+{
+	return ab->version == AB8500_VERSION_AB8540;
+}
+
+/* exclude also ab8505, ab9540... */
+static inline int is_ab8500_1p0_or_earlier(struct ab8500 *ab)
+{
+	return (is_ab8500(ab) && (ab->chip_id <= AB8500_CUT1P0));
+}
+
+/* exclude also ab8505, ab9540... */
+static inline int is_ab8500_1p1_or_earlier(struct ab8500 *ab)
+{
+	return (is_ab8500(ab) && (ab->chip_id <= AB8500_CUT1P1));
+}
+
+/* exclude also ab8505, ab9540... */
+static inline int is_ab8500_2p0_or_earlier(struct ab8500 *ab)
+{
+	return (is_ab8500(ab) && (ab->chip_id <= AB8500_CUT2P0));
+}
+
+/* exclude also ab8505, ab9540... */
+static inline int is_ab8500_2p0(struct ab8500 *ab)
+{
+	return (is_ab8500(ab) && (ab->chip_id == AB8500_CUT2P0));
+}
+
 #endif /* MFD_AB8500_H */
diff --git a/include/linux/mfd/abx500/ux500_chargalg.h b/include/linux/mfd/abx500/ux500_chargalg.h
new file mode 100644
index 000000000000..9b07725750c9
--- /dev/null
+++ b/include/linux/mfd/abx500/ux500_chargalg.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2012
+ * Author: Johan Gardsmark <johan.gardsmark@stericsson.com> for ST-Ericsson.
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#ifndef _UX500_CHARGALG_H
+#define _UX500_CHARGALG_H
+
+#include <linux/power_supply.h>
+
+#define psy_to_ux500_charger(x) container_of((x), \
+		struct ux500_charger, psy)
+
+/* Forward declaration */
+struct ux500_charger;
+
+struct ux500_charger_ops {
+	int (*enable) (struct ux500_charger *, int, int, int);
+	int (*kick_wd) (struct ux500_charger *);
+	int (*update_curr) (struct ux500_charger *, int);
+};
+
+/**
+ * struct ux500_charger - power supply ux500 charger sub class
+ * @psy			power supply base class
+ * @ops			ux500 charger operations
+ * @max_out_volt	maximum output charger voltage in mV
+ * @max_out_curr	maximum output charger current in mA
+ */
+struct ux500_charger {
+	struct power_supply psy;
+	struct ux500_charger_ops ops;
+	int max_out_volt;
+	int max_out_curr;
+};
+
+#endif
diff --git a/arch/arm/mach-bcmring/include/mach/io.h b/include/linux/mfd/anatop.h
index dae5e9b166ea..22c1007d3ec5 100644
--- a/arch/arm/mach-bcmring/include/mach/io.h
+++ b/include/linux/mfd/anatop.h
@@ -1,6 +1,8 @@
 /*
+ * anatop.h - Anatop MFD driver
  *
- *  Copyright (C) 1999 ARM Limited
+ *  Copyright (C) 2012 Ying-Chun Liu (PaulLiu) <paul.liu@linaro.org>
+ *  Copyright (C) 2012 Linaro
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -16,18 +18,23 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
+#ifndef __LINUX_MFD_ANATOP_H
+#define __LINUX_MFD_ANATOP_H
 
-#define IO_SPACE_LIMIT 0xffffffff
+#include <linux/spinlock.h>
 
-/*
- * We don't actually have real ISA nor PCI buses, but there is so many
- * drivers out there that might just work if we fake them...
+/**
+ * anatop - MFD data
+ * @ioreg: ioremap register
+ * @reglock: spinlock for register read/write
  */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
+struct anatop {
+	void *ioreg;
+	spinlock_t reglock;
+};
+
+extern u32 anatop_get_bits(struct anatop *, u32, int, int);
+extern void anatop_set_bits(struct anatop *, u32, int, int, u32);
 
-#endif
+#endif /*  __LINUX_MFD_ANATOP_H */
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index 5702d1be13b4..7ffbd6e9e7fc 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -76,8 +76,6 @@ enum da9052_chip_id {
 struct da9052_pdata;
 
 struct da9052 {
-	struct mutex io_lock;
-
 	struct device *dev;
 	struct regmap *regmap;
 
diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h
index 60d27f7bfc1f..b3a43b1263fe 100644
--- a/include/linux/mfd/db8500-prcmu.h
+++ b/include/linux/mfd/db8500-prcmu.h
@@ -11,6 +11,24 @@
 #define __MFD_DB8500_PRCMU_H
 
 #include <linux/interrupt.h>
+#include <linux/bitops.h>
+
+/*
+ * Registers
+ */
+#define DB8500_PRCM_GPIOCR 0x138
+#define DB8500_PRCM_GPIOCR_DBG_UARTMOD_CMD0	BIT(0)
+#define DB8500_PRCM_GPIOCR_DBG_STM_APE_CMD	BIT(9)
+#define DB8500_PRCM_GPIOCR_DBG_STM_MOD_CMD1	BIT(11)
+#define DB8500_PRCM_GPIOCR_SPI2_SELECT		BIT(23)
+
+#define DB8500_PRCM_LINE_VALUE 0x170
+#define DB8500_PRCM_LINE_VALUE_HSI_CAWAKE0	BIT(3)
+
+#define DB8500_PRCM_DSI_SW_RESET 0x324
+#define DB8500_PRCM_DSI_SW_RESET_DSI0_SW_RESETN BIT(0)
+#define DB8500_PRCM_DSI_SW_RESET_DSI1_SW_RESETN BIT(1)
+#define DB8500_PRCM_DSI_SW_RESET_DSI2_SW_RESETN BIT(2)
 
 /* This portion previously known as <mach/prcmu-fw-defs_v1.h> */
 
@@ -421,40 +439,22 @@ enum auto_enable {
 /* End of file previously known as prcmu-fw-defs_v1.h */
 
 /**
- * enum hw_acc_dev - enum for hw accelerators
- * @HW_ACC_SVAMMDSP: for SVAMMDSP
- * @HW_ACC_SVAPIPE:  for SVAPIPE
- * @HW_ACC_SIAMMDSP: for SIAMMDSP
- * @HW_ACC_SIAPIPE: for SIAPIPE
- * @HW_ACC_SGA: for SGA
- * @HW_ACC_B2R2: for B2R2
- * @HW_ACC_MCDE: for MCDE
- * @HW_ACC_ESRAM1: for ESRAM1
- * @HW_ACC_ESRAM2: for ESRAM2
- * @HW_ACC_ESRAM3: for ESRAM3
- * @HW_ACC_ESRAM4: for ESRAM4
- * @NUM_HW_ACC: number of hardware accelerators
- *
- * Different hw accelerators which can be turned ON/
- * OFF or put into retention (MMDSPs and ESRAMs).
- * Used with EPOD API.
+ * enum prcmu_power_status - results from set_power_state
+ * @PRCMU_SLEEP_OK: Sleep went ok
+ * @PRCMU_DEEP_SLEEP_OK: DeepSleep went ok
+ * @PRCMU_IDLE_OK: Idle went ok
+ * @PRCMU_DEEPIDLE_OK: DeepIdle went ok
+ * @PRCMU_PRCMU2ARMPENDINGIT_ER: Pending interrupt detected
+ * @PRCMU_ARMPENDINGIT_ER: Pending interrupt detected
  *
- * NOTE! Deprecated, to be removed when all users switched over to use the
- * regulator API.
  */
-enum hw_acc_dev {
-	HW_ACC_SVAMMDSP,
-	HW_ACC_SVAPIPE,
-	HW_ACC_SIAMMDSP,
-	HW_ACC_SIAPIPE,
-	HW_ACC_SGA,
-	HW_ACC_B2R2,
-	HW_ACC_MCDE,
-	HW_ACC_ESRAM1,
-	HW_ACC_ESRAM2,
-	HW_ACC_ESRAM3,
-	HW_ACC_ESRAM4,
-	NUM_HW_ACC
+enum prcmu_power_status {
+	PRCMU_SLEEP_OK			= 0xf3,
+	PRCMU_DEEP_SLEEP_OK		= 0xf6,
+	PRCMU_IDLE_OK			= 0xf0,
+	PRCMU_DEEPIDLE_OK		= 0xe3,
+	PRCMU_PRCMU2ARMPENDINGIT_ER	= 0x91,
+	PRCMU_ARMPENDINGIT_ER		= 0x93,
 };
 
 /*
@@ -493,6 +493,20 @@ struct prcmu_auto_pm_config {
 	u8 sva_policy;
 };
 
+#define PRCMU_FW_PROJECT_U8500		2
+#define PRCMU_FW_PROJECT_U9500		4
+#define PRCMU_FW_PROJECT_U8500_C2	7
+#define PRCMU_FW_PROJECT_U9500_C2	11
+#define PRCMU_FW_PROJECT_U8520		13
+#define PRCMU_FW_PROJECT_U8420		14
+
+struct prcmu_fw_version {
+	u8 project;
+	u8 api_version;
+	u8 func_version;
+	u8 errata;
+};
+
 #ifdef CONFIG_MFD_DB8500_PRCMU
 
 void db8500_prcmu_early_init(void);
@@ -500,42 +514,41 @@ int prcmu_set_rc_a2p(enum romcode_write);
 enum romcode_read prcmu_get_rc_p2a(void);
 enum ap_pwrst prcmu_get_xp70_current_state(void);
 bool prcmu_has_arm_maxopp(void);
-bool prcmu_is_u8400(void);
-int prcmu_set_ape_opp(u8 opp);
-int prcmu_get_ape_opp(void);
+struct prcmu_fw_version *prcmu_get_fw_version(void);
 int prcmu_request_ape_opp_100_voltage(bool enable);
 int prcmu_release_usb_wakeup_state(void);
-int prcmu_set_ddr_opp(u8 opp);
-int prcmu_get_ddr_opp(void);
-/* NOTE! Use regulator framework instead */
-int prcmu_set_hwacc(u16 hw_acc_dev, u8 state);
 void prcmu_configure_auto_pm(struct prcmu_auto_pm_config *sleep,
 	struct prcmu_auto_pm_config *idle);
 bool prcmu_is_auto_pm_enabled(void);
 
 int prcmu_config_clkout(u8 clkout, u8 source, u8 div);
 int prcmu_set_clock_divider(u8 clock, u8 divider);
-int prcmu_config_hotdog(u8 threshold);
-int prcmu_config_hotmon(u8 low, u8 high);
-int prcmu_start_temp_sense(u16 cycles32k);
-int prcmu_stop_temp_sense(void);
+int db8500_prcmu_config_hotdog(u8 threshold);
+int db8500_prcmu_config_hotmon(u8 low, u8 high);
+int db8500_prcmu_start_temp_sense(u16 cycles32k);
+int db8500_prcmu_stop_temp_sense(void);
 int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
 int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size);
 
 void prcmu_ac_wake_req(void);
 void prcmu_ac_sleep_req(void);
-void prcmu_modem_reset(void);
-void prcmu_enable_spi2(void);
-void prcmu_disable_spi2(void);
+void db8500_prcmu_modem_reset(void);
 
-int prcmu_config_a9wdog(u8 num, bool sleep_auto_off);
-int prcmu_enable_a9wdog(u8 id);
-int prcmu_disable_a9wdog(u8 id);
-int prcmu_kick_a9wdog(u8 id);
-int prcmu_load_a9wdog(u8 id, u32 val);
+int db8500_prcmu_config_a9wdog(u8 num, bool sleep_auto_off);
+int db8500_prcmu_enable_a9wdog(u8 id);
+int db8500_prcmu_disable_a9wdog(u8 id);
+int db8500_prcmu_kick_a9wdog(u8 id);
+int db8500_prcmu_load_a9wdog(u8 id, u32 val);
 
 void db8500_prcmu_system_reset(u16 reset_code);
 int db8500_prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll);
+u8 db8500_prcmu_get_power_state_result(void);
+int db8500_prcmu_gic_decouple(void);
+int db8500_prcmu_gic_recouple(void);
+int db8500_prcmu_copy_gic_settings(void);
+bool db8500_prcmu_gic_pending_irq(void);
+bool db8500_prcmu_pending_irq(void);
+bool db8500_prcmu_is_cpu_in_wfi(int cpu);
 void db8500_prcmu_enable_wakeups(u32 wakeups);
 int db8500_prcmu_set_epod(u16 epod_id, u8 epod_state);
 int db8500_prcmu_request_clock(u8 clock, bool enable);
@@ -549,6 +562,14 @@ u16 db8500_prcmu_get_reset_code(void);
 bool db8500_prcmu_is_ac_wake_requested(void);
 int db8500_prcmu_set_arm_opp(u8 opp);
 int db8500_prcmu_get_arm_opp(void);
+int db8500_prcmu_set_ape_opp(u8 opp);
+int db8500_prcmu_get_ape_opp(void);
+int db8500_prcmu_set_ddr_opp(u8 opp);
+int db8500_prcmu_get_ddr_opp(void);
+
+u32 db8500_prcmu_read(unsigned int reg);
+void db8500_prcmu_write(unsigned int reg, u32 value);
+void db8500_prcmu_write_masked(unsigned int reg, u32 mask, u32 value);
 
 #else /* !CONFIG_MFD_DB8500_PRCMU */
 
@@ -574,17 +595,17 @@ static inline bool prcmu_has_arm_maxopp(void)
 	return false;
 }
 
-static inline bool prcmu_is_u8400(void)
+static inline struct prcmu_fw_version *prcmu_get_fw_version(void)
 {
-	return false;
+	return NULL;
 }
 
-static inline int prcmu_set_ape_opp(u8 opp)
+static inline int db8500_prcmu_set_ape_opp(u8 opp)
 {
 	return 0;
 }
 
-static inline int prcmu_get_ape_opp(void)
+static inline int db8500_prcmu_get_ape_opp(void)
 {
 	return APE_100_OPP;
 }
@@ -599,21 +620,16 @@ static inline int prcmu_release_usb_wakeup_state(void)
 	return 0;
 }
 
-static inline int prcmu_set_ddr_opp(u8 opp)
+static inline int db8500_prcmu_set_ddr_opp(u8 opp)
 {
 	return 0;
 }
 
-static inline int prcmu_get_ddr_opp(void)
+static inline int db8500_prcmu_get_ddr_opp(void)
 {
 	return DDR_100_OPP;
 }
 
-static inline int prcmu_set_hwacc(u16 hw_acc_dev, u8 state)
-{
-	return 0;
-}
-
 static inline void prcmu_configure_auto_pm(struct prcmu_auto_pm_config *sleep,
 	struct prcmu_auto_pm_config *idle)
 {
@@ -634,22 +650,22 @@ static inline int prcmu_set_clock_divider(u8 clock, u8 divider)
 	return 0;
 }
 
-static inline int prcmu_config_hotdog(u8 threshold)
+static inline int db8500_prcmu_config_hotdog(u8 threshold)
 {
 	return 0;
 }
 
-static inline int prcmu_config_hotmon(u8 low, u8 high)
+static inline int db8500_prcmu_config_hotmon(u8 low, u8 high)
 {
 	return 0;
 }
 
-static inline int prcmu_start_temp_sense(u16 cycles32k)
+static inline int db8500_prcmu_start_temp_sense(u16 cycles32k)
 {
 	return 0;
 }
 
-static inline int prcmu_stop_temp_sense(void)
+static inline int db8500_prcmu_stop_temp_sense(void)
 {
 	return 0;
 }
@@ -668,22 +684,17 @@ static inline void prcmu_ac_wake_req(void) {}
 
 static inline void prcmu_ac_sleep_req(void) {}
 
-static inline void prcmu_modem_reset(void) {}
+static inline void db8500_prcmu_modem_reset(void) {}
 
-static inline int prcmu_enable_spi2(void)
-{
-	return 0;
-}
+static inline void db8500_prcmu_system_reset(u16 reset_code) {}
 
-static inline int prcmu_disable_spi2(void)
+static inline int db8500_prcmu_set_power_state(u8 state, bool keep_ulp_clk,
+	bool keep_ap_pll)
 {
 	return 0;
 }
 
-static inline void db8500_prcmu_system_reset(u16 reset_code) {}
-
-static inline int db8500_prcmu_set_power_state(u8 state, bool keep_ulp_clk,
-	bool keep_ap_pll)
+static inline u8 db8500_prcmu_get_power_state_result(void)
 {
 	return 0;
 }
@@ -729,27 +740,27 @@ static inline u16 db8500_prcmu_get_reset_code(void)
 	return 0;
 }
 
-static inline int prcmu_config_a9wdog(u8 num, bool sleep_auto_off)
+static inline int db8500_prcmu_config_a9wdog(u8 num, bool sleep_auto_off)
 {
 	return 0;
 }
 
-static inline int prcmu_enable_a9wdog(u8 id)
+static inline int db8500_prcmu_enable_a9wdog(u8 id)
 {
 	return 0;
 }
 
-static inline int prcmu_disable_a9wdog(u8 id)
+static inline int db8500_prcmu_disable_a9wdog(u8 id)
 {
 	return 0;
 }
 
-static inline int prcmu_kick_a9wdog(u8 id)
+static inline int db8500_prcmu_kick_a9wdog(u8 id)
 {
 	return 0;
 }
 
-static inline int prcmu_load_a9wdog(u8 id, u32 val)
+static inline int db8500_prcmu_load_a9wdog(u8 id, u32 val)
 {
 	return 0;
 }
@@ -769,6 +780,16 @@ static inline int db8500_prcmu_get_arm_opp(void)
 	return 0;
 }
 
+static inline u32 db8500_prcmu_read(unsigned int reg)
+{
+	return 0;
+}
+
+static inline void db8500_prcmu_write(unsigned int reg, u32 value) {}
+
+static inline void db8500_prcmu_write_masked(unsigned int reg, u32 mask,
+	u32 value) {}
+
 #endif /* !CONFIG_MFD_DB8500_PRCMU */
 
 #endif /* __MFD_DB8500_PRCMU_H */
diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
index bac942f959c1..d7674eb7305f 100644
--- a/include/linux/mfd/dbx500-prcmu.h
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -10,7 +10,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
-#include <asm/mach-types.h>
+#include <linux/err.h>
 
 /* PRCMU Wakeup defines */
 enum prcmu_wakeup_index {
@@ -80,6 +80,29 @@ enum prcmu_wakeup_index {
 #define EPOD_STATE_ON_CLK_OFF	0x03
 #define EPOD_STATE_ON		0x04
 
+/* DB5500 CLKOUT IDs */
+enum {
+	DB5500_CLKOUT0 = 0,
+	DB5500_CLKOUT1,
+};
+
+/* DB5500 CLKOUTx sources */
+enum {
+	DB5500_CLKOUT_REF_CLK_SEL0,
+	DB5500_CLKOUT_RTC_CLK0_SEL0,
+	DB5500_CLKOUT_ULP_CLK_SEL0,
+	DB5500_CLKOUT_STATIC0,
+	DB5500_CLKOUT_REFCLK,
+	DB5500_CLKOUT_ULPCLK,
+	DB5500_CLKOUT_ARMCLK,
+	DB5500_CLKOUT_SYSACC0CLK,
+	DB5500_CLKOUT_SOC0PLLCLK,
+	DB5500_CLKOUT_SOC1PLLCLK,
+	DB5500_CLKOUT_DDRPLLCLK,
+	DB5500_CLKOUT_TVCLK,
+	DB5500_CLKOUT_IRDACLK,
+};
+
 /*
  * CLKOUT sources
  */
@@ -111,6 +134,7 @@ enum prcmu_clock {
 	PRCMU_MSP1CLK,
 	PRCMU_I2CCLK,
 	PRCMU_SDMMCCLK,
+	PRCMU_SPARE1CLK,
 	PRCMU_SLIMCLK,
 	PRCMU_PER1CLK,
 	PRCMU_PER2CLK,
@@ -139,12 +163,20 @@ enum prcmu_clock {
 	PRCMU_IRRCCLK,
 	PRCMU_SIACLK,
 	PRCMU_SVACLK,
+	PRCMU_ACLK,
 	PRCMU_NUM_REG_CLOCKS,
 	PRCMU_SYSCLK = PRCMU_NUM_REG_CLOCKS,
+	PRCMU_CDCLK,
 	PRCMU_TIMCLK,
 	PRCMU_PLLSOC0,
 	PRCMU_PLLSOC1,
 	PRCMU_PLLDDR,
+	PRCMU_PLLDSI,
+	PRCMU_DSI0CLK,
+	PRCMU_DSI1CLK,
+	PRCMU_DSI0ESCCLK,
+	PRCMU_DSI1ESCCLK,
+	PRCMU_DSI2ESCCLK,
 };
 
 /**
@@ -153,12 +185,14 @@ enum prcmu_clock {
  * @APE_NO_CHANGE: The APE operating point is unchanged
  * @APE_100_OPP: The new APE operating point is ape100opp
  * @APE_50_OPP: 50%
+ * @APE_50_PARTLY_25_OPP: 50%, except some clocks at 25%.
  */
 enum ape_opp {
 	APE_OPP_INIT = 0x00,
 	APE_NO_CHANGE = 0x01,
 	APE_100_OPP = 0x02,
-	APE_50_OPP = 0x03
+	APE_50_OPP = 0x03,
+	APE_50_PARTLY_25_OPP = 0xFF,
 };
 
 /**
@@ -218,9 +252,11 @@ enum ddr_pwrst {
 
 #if defined(CONFIG_UX500_SOC_DB8500) || defined(CONFIG_UX500_SOC_DB5500)
 
+#include <mach/id.h>
+
 static inline void __init prcmu_early_init(void)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_early_init();
 	else
 		return db8500_prcmu_early_init();
@@ -229,7 +265,7 @@ static inline void __init prcmu_early_init(void)
 static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk,
 		bool keep_ap_pll)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_set_power_state(state, keep_ulp_clk,
 			keep_ap_pll);
 	else
@@ -237,9 +273,65 @@ static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk,
 			keep_ap_pll);
 }
 
+static inline u8 prcmu_get_power_state_result(void)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_get_power_state_result();
+}
+
+static inline int prcmu_gic_decouple(void)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_gic_decouple();
+}
+
+static inline int prcmu_gic_recouple(void)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_gic_recouple();
+}
+
+static inline bool prcmu_gic_pending_irq(void)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_gic_pending_irq();
+}
+
+static inline bool prcmu_is_cpu_in_wfi(int cpu)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_is_cpu_in_wfi(cpu);
+}
+
+static inline int prcmu_copy_gic_settings(void)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_copy_gic_settings();
+}
+
+static inline bool prcmu_pending_irq(void)
+{
+        if (cpu_is_u5500())
+                return -EINVAL;
+        else
+                return db8500_prcmu_pending_irq();
+}
+
 static inline int prcmu_set_epod(u16 epod_id, u8 epod_state)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return -EINVAL;
 	else
 		return db8500_prcmu_set_epod(epod_id, epod_state);
@@ -247,7 +339,7 @@ static inline int prcmu_set_epod(u16 epod_id, u8 epod_state)
 
 static inline void prcmu_enable_wakeups(u32 wakeups)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		db5500_prcmu_enable_wakeups(wakeups);
 	else
 		db8500_prcmu_enable_wakeups(wakeups);
@@ -260,7 +352,7 @@ static inline void prcmu_disable_wakeups(void)
 
 static inline void prcmu_config_abb_event_readout(u32 abb_events)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		db5500_prcmu_config_abb_event_readout(abb_events);
 	else
 		db8500_prcmu_config_abb_event_readout(abb_events);
@@ -268,7 +360,7 @@ static inline void prcmu_config_abb_event_readout(u32 abb_events)
 
 static inline void prcmu_get_abb_event_buffer(void __iomem **buf)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		db5500_prcmu_get_abb_event_buffer(buf);
 	else
 		db8500_prcmu_get_abb_event_buffer(buf);
@@ -276,25 +368,40 @@ static inline void prcmu_get_abb_event_buffer(void __iomem **buf)
 
 int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
 int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size);
+int prcmu_abb_write_masked(u8 slave, u8 reg, u8 *value, u8 *mask, u8 size);
 
 int prcmu_config_clkout(u8 clkout, u8 source, u8 div);
 
 static inline int prcmu_request_clock(u8 clock, bool enable)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_request_clock(clock, enable);
 	else
 		return db8500_prcmu_request_clock(clock, enable);
 }
 
-int prcmu_set_ape_opp(u8 opp);
-int prcmu_get_ape_opp(void);
-int prcmu_set_ddr_opp(u8 opp);
-int prcmu_get_ddr_opp(void);
+unsigned long prcmu_clock_rate(u8 clock);
+long prcmu_round_clock_rate(u8 clock, unsigned long rate);
+int prcmu_set_clock_rate(u8 clock, unsigned long rate);
+
+static inline int prcmu_set_ddr_opp(u8 opp)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_set_ddr_opp(opp);
+}
+static inline int prcmu_get_ddr_opp(void)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_get_ddr_opp();
+}
 
 static inline int prcmu_set_arm_opp(u8 opp)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return -EINVAL;
 	else
 		return db8500_prcmu_set_arm_opp(opp);
@@ -302,15 +409,31 @@ static inline int prcmu_set_arm_opp(u8 opp)
 
 static inline int prcmu_get_arm_opp(void)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return -EINVAL;
 	else
 		return db8500_prcmu_get_arm_opp();
 }
 
+static inline int prcmu_set_ape_opp(u8 opp)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_set_ape_opp(opp);
+}
+
+static inline int prcmu_get_ape_opp(void)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_get_ape_opp();
+}
+
 static inline void prcmu_system_reset(u16 reset_code)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_system_reset(reset_code);
 	else
 		return db8500_prcmu_system_reset(reset_code);
@@ -318,7 +441,7 @@ static inline void prcmu_system_reset(u16 reset_code)
 
 static inline u16 prcmu_get_reset_code(void)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_get_reset_code();
 	else
 		return db8500_prcmu_get_reset_code();
@@ -326,10 +449,17 @@ static inline u16 prcmu_get_reset_code(void)
 
 void prcmu_ac_wake_req(void);
 void prcmu_ac_sleep_req(void);
-void prcmu_modem_reset(void);
+static inline void prcmu_modem_reset(void)
+{
+	if (cpu_is_u5500())
+		return;
+	else
+		return db8500_prcmu_modem_reset();
+}
+
 static inline bool prcmu_is_ac_wake_requested(void)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_is_ac_wake_requested();
 	else
 		return db8500_prcmu_is_ac_wake_requested();
@@ -337,7 +467,7 @@ static inline bool prcmu_is_ac_wake_requested(void)
 
 static inline int prcmu_set_display_clocks(void)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_set_display_clocks();
 	else
 		return db8500_prcmu_set_display_clocks();
@@ -345,7 +475,7 @@ static inline int prcmu_set_display_clocks(void)
 
 static inline int prcmu_disable_dsipll(void)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_disable_dsipll();
 	else
 		return db8500_prcmu_disable_dsipll();
@@ -353,7 +483,7 @@ static inline int prcmu_disable_dsipll(void)
 
 static inline int prcmu_enable_dsipll(void)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return db5500_prcmu_enable_dsipll();
 	else
 		return db8500_prcmu_enable_dsipll();
@@ -361,11 +491,107 @@ static inline int prcmu_enable_dsipll(void)
 
 static inline int prcmu_config_esram0_deep_sleep(u8 state)
 {
-	if (machine_is_u5500())
+	if (cpu_is_u5500())
 		return -EINVAL;
 	else
 		return db8500_prcmu_config_esram0_deep_sleep(state);
 }
+
+static inline int prcmu_config_hotdog(u8 threshold)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_config_hotdog(threshold);
+}
+
+static inline int prcmu_config_hotmon(u8 low, u8 high)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_config_hotmon(low, high);
+}
+
+static inline int prcmu_start_temp_sense(u16 cycles32k)
+{
+	if (cpu_is_u5500())
+		return  -EINVAL;
+	else
+		return  db8500_prcmu_start_temp_sense(cycles32k);
+}
+
+static inline int prcmu_stop_temp_sense(void)
+{
+	if (cpu_is_u5500())
+		return  -EINVAL;
+	else
+		return  db8500_prcmu_stop_temp_sense();
+}
+
+static inline u32 prcmu_read(unsigned int reg)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_read(reg);
+}
+
+static inline void prcmu_write(unsigned int reg, u32 value)
+{
+	if (cpu_is_u5500())
+		return;
+	else
+		db8500_prcmu_write(reg, value);
+}
+
+static inline void prcmu_write_masked(unsigned int reg, u32 mask, u32 value)
+{
+	if (cpu_is_u5500())
+		return;
+	else
+		db8500_prcmu_write_masked(reg, mask, value);
+}
+
+static inline int prcmu_enable_a9wdog(u8 id)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_enable_a9wdog(id);
+}
+
+static inline int prcmu_disable_a9wdog(u8 id)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_disable_a9wdog(id);
+}
+
+static inline int prcmu_kick_a9wdog(u8 id)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_kick_a9wdog(id);
+}
+
+static inline int prcmu_load_a9wdog(u8 id, u32 timeout)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_load_a9wdog(id, timeout);
+}
+
+static inline int prcmu_config_a9wdog(u8 num, bool sleep_auto_off)
+{
+	if (cpu_is_u5500())
+		return -EINVAL;
+	else
+		return db8500_prcmu_config_a9wdog(num, sleep_auto_off);
+}
 #else
 
 static inline void __init prcmu_early_init(void) {}
@@ -395,6 +621,12 @@ static inline int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
 	return -ENOSYS;
 }
 
+static inline int prcmu_abb_write_masked(u8 slave, u8 reg, u8 *value, u8 *mask,
+	u8 size)
+{
+	return -ENOSYS;
+}
+
 static inline int prcmu_config_clkout(u8 clkout, u8 source, u8 div)
 {
 	return 0;
@@ -405,6 +637,21 @@ static inline int prcmu_request_clock(u8 clock, bool enable)
 	return 0;
 }
 
+static inline long prcmu_round_clock_rate(u8 clock, unsigned long rate)
+{
+	return 0;
+}
+
+static inline int prcmu_set_clock_rate(u8 clock, unsigned long rate)
+{
+	return 0;
+}
+
+static inline unsigned long prcmu_clock_rate(u8 clock)
+{
+	return 0;
+}
+
 static inline int prcmu_set_ape_opp(u8 opp)
 {
 	return 0;
@@ -480,14 +727,133 @@ static inline void prcmu_get_abb_event_buffer(void __iomem **buf)
 	*buf = NULL;
 }
 
+static inline int prcmu_config_hotdog(u8 threshold)
+{
+	return 0;
+}
+
+static inline int prcmu_config_hotmon(u8 low, u8 high)
+{
+	return 0;
+}
+
+static inline int prcmu_start_temp_sense(u16 cycles32k)
+{
+	return 0;
+}
+
+static inline int prcmu_stop_temp_sense(void)
+{
+	return 0;
+}
+
+static inline u32 prcmu_read(unsigned int reg)
+{
+	return 0;
+}
+
+static inline void prcmu_write(unsigned int reg, u32 value) {}
+
+static inline void prcmu_write_masked(unsigned int reg, u32 mask, u32 value) {}
+
+#endif
+
+static inline void prcmu_set(unsigned int reg, u32 bits)
+{
+	prcmu_write_masked(reg, bits, bits);
+}
+
+static inline void prcmu_clear(unsigned int reg, u32 bits)
+{
+	prcmu_write_masked(reg, bits, 0);
+}
+
+#if defined(CONFIG_UX500_SOC_DB8500) || defined(CONFIG_UX500_SOC_DB5500)
+
+/**
+ * prcmu_enable_spi2 - Enables pin muxing for SPI2 on OtherAlternateC1.
+ */
+static inline void prcmu_enable_spi2(void)
+{
+	if (cpu_is_u8500())
+		prcmu_set(DB8500_PRCM_GPIOCR, DB8500_PRCM_GPIOCR_SPI2_SELECT);
+}
+
+/**
+ * prcmu_disable_spi2 - Disables pin muxing for SPI2 on OtherAlternateC1.
+ */
+static inline void prcmu_disable_spi2(void)
+{
+	if (cpu_is_u8500())
+		prcmu_clear(DB8500_PRCM_GPIOCR, DB8500_PRCM_GPIOCR_SPI2_SELECT);
+}
+
+/**
+ * prcmu_enable_stm_mod_uart - Enables pin muxing for STMMOD
+ * and UARTMOD on OtherAlternateC3.
+ */
+static inline void prcmu_enable_stm_mod_uart(void)
+{
+	if (cpu_is_u8500()) {
+		prcmu_set(DB8500_PRCM_GPIOCR,
+			(DB8500_PRCM_GPIOCR_DBG_STM_MOD_CMD1 |
+			 DB8500_PRCM_GPIOCR_DBG_UARTMOD_CMD0));
+	}
+}
+
+/**
+ * prcmu_disable_stm_mod_uart - Disables pin muxing for STMMOD
+ * and UARTMOD on OtherAlternateC3.
+ */
+static inline void prcmu_disable_stm_mod_uart(void)
+{
+	if (cpu_is_u8500()) {
+		prcmu_clear(DB8500_PRCM_GPIOCR,
+			(DB8500_PRCM_GPIOCR_DBG_STM_MOD_CMD1 |
+			 DB8500_PRCM_GPIOCR_DBG_UARTMOD_CMD0));
+	}
+}
+
+/**
+ * prcmu_enable_stm_ape - Enables pin muxing for STM APE on OtherAlternateC1.
+ */
+static inline void prcmu_enable_stm_ape(void)
+{
+	if (cpu_is_u8500()) {
+		prcmu_set(DB8500_PRCM_GPIOCR,
+			DB8500_PRCM_GPIOCR_DBG_STM_APE_CMD);
+	}
+}
+
+/**
+ * prcmu_disable_stm_ape - Disables pin muxing for STM APE on OtherAlternateC1.
+ */
+static inline void prcmu_disable_stm_ape(void)
+{
+	if (cpu_is_u8500()) {
+		prcmu_clear(DB8500_PRCM_GPIOCR,
+			DB8500_PRCM_GPIOCR_DBG_STM_APE_CMD);
+	}
+}
+
+#else
+
+static inline void prcmu_enable_spi2(void) {}
+static inline void prcmu_disable_spi2(void) {}
+static inline void prcmu_enable_stm_mod_uart(void) {}
+static inline void prcmu_disable_stm_mod_uart(void) {}
+static inline void prcmu_enable_stm_ape(void) {}
+static inline void prcmu_disable_stm_ape(void) {}
+
 #endif
 
 /* PRCMU QoS APE OPP class */
 #define PRCMU_QOS_APE_OPP 1
 #define PRCMU_QOS_DDR_OPP 2
+#define PRCMU_QOS_ARM_OPP 3
 #define PRCMU_QOS_DEFAULT_VALUE -1
 
-#ifdef CONFIG_UX500_PRCMU_QOS_POWER
+#ifdef CONFIG_DBX500_PRCMU_QOS_POWER
 
 unsigned long prcmu_qos_get_cpufreq_opp_delay(void);
 void prcmu_qos_set_cpufreq_opp_delay(unsigned long);
diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h
index b86ee45c8b03..10e038bac8dd 100644
--- a/include/linux/mfd/mc13xxx.h
+++ b/include/linux/mfd/mc13xxx.h
@@ -38,7 +38,8 @@ int mc13xxx_irq_ack(struct mc13xxx *mc13xxx, int irq);
 int mc13xxx_get_flags(struct mc13xxx *mc13xxx);
 
 int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx,
-		unsigned int mode, unsigned int channel, unsigned int *sample);
+		unsigned int mode, unsigned int channel,
+		u8 ato, bool atox, unsigned int *sample);
 
 #define MC13XXX_IRQ_ADCDONE	0
 #define MC13XXX_IRQ_ADCBISDONE	1
@@ -157,6 +158,18 @@ struct mc13xxx_buttons_platform_data {
 	unsigned short b3on_key;
 };
 
+struct mc13xxx_ts_platform_data {
+	/* Delay between Touchscreen polarization and ADC Conversion.
+	 * Given in clock ticks of a 32 kHz clock which gives a granularity of
+	 * about 30.5ms */
+	u8 ato;
+
+#define MC13783_TS_ATO_FIRST false
+#define MC13783_TS_ATO_EACH  true
+	/* Use the ATO delay only for the first conversion or for each one */
+	bool atox;
+};
+
 struct mc13xxx_platform_data {
 #define MC13XXX_USE_TOUCHSCREEN (1 << 0)
 #define MC13XXX_USE_CODEC	(1 << 1)
@@ -167,6 +180,7 @@ struct mc13xxx_platform_data {
 	struct mc13xxx_regulator_platform_data regulators;
 	struct mc13xxx_leds_platform_data *leds;
 	struct mc13xxx_buttons_platform_data *buttons;
+	struct mc13xxx_ts_platform_data touch;
 };
 
 #define MC13XXX_ADC_MODE_TS		1
diff --git a/include/linux/mfd/mcp.h b/include/linux/mfd/mcp.h
index f88c1cc0cb0f..a9e8bd157673 100644
--- a/include/linux/mfd/mcp.h
+++ b/include/linux/mfd/mcp.h
@@ -10,8 +10,6 @@
 #ifndef MCP_H
 #define MCP_H
 
-#include <mach/dma.h>
-
 struct mcp_ops;
 
 struct mcp {
@@ -21,12 +19,7 @@ struct mcp {
 	int		use_count;
 	unsigned int	sclk_rate;
 	unsigned int	rw_timeout;
-	dma_device_t	dma_audio_rd;
-	dma_device_t	dma_audio_wr;
-	dma_device_t	dma_telco_rd;
-	dma_device_t	dma_telco_wr;
 	struct device	attached_device;
-	int		gpio_base;
 };
 
 struct mcp_ops {
@@ -47,15 +40,14 @@ void mcp_disable(struct mcp *);
 #define mcp_get_sclk_rate(mcp)	((mcp)->sclk_rate)
 
 struct mcp *mcp_host_alloc(struct device *, size_t);
-int mcp_host_register(struct mcp *);
-void mcp_host_unregister(struct mcp *);
+int mcp_host_add(struct mcp *, void *);
+void mcp_host_del(struct mcp *);
+void mcp_host_free(struct mcp *);
 
 struct mcp_driver {
 	struct device_driver drv;
 	int (*probe)(struct mcp *);
 	void (*remove)(struct mcp *);
-	int (*suspend)(struct mcp *, pm_message_t);
-	int (*resume)(struct mcp *);
 };
 
 int mcp_driver_register(struct mcp_driver *);
diff --git a/include/linux/mfd/rc5t583.h b/include/linux/mfd/rc5t583.h
new file mode 100644
index 000000000000..a2c61609d21d
--- /dev/null
+++ b/include/linux/mfd/rc5t583.h
@@ -0,0 +1,295 @@
+/*
+ * Core driver interface to access RICOH_RC5T583 power management chip.
+ *
+ * Copyright (c) 2011-2012, NVIDIA CORPORATION.  All rights reserved.
+ * Author: Laxman dewangan <ldewangan@nvidia.com>
+ *
+ * Based on code
+ *      Copyright (C) 2011 RICOH COMPANY,LTD
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#ifndef __LINUX_MFD_RC5T583_H
+#define __LINUX_MFD_RC5T583_H
+
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+#define RC5T583_MAX_REGS		0xF8
+
+/* Maximum number of main interrupts */
+#define MAX_MAIN_INTERRUPT		5
+#define RC5T583_MAX_GPEDGE_REG		2
+#define RC5T583_MAX_INTERRUPT_MASK_REGS	9
+
+/* Interrupt enable register */
+#define RC5T583_INT_EN_SYS1	0x19
+#define RC5T583_INT_EN_SYS2	0x1D
+#define RC5T583_INT_EN_DCDC	0x41
+#define RC5T583_INT_EN_RTC	0xED
+#define RC5T583_INT_EN_ADC1	0x90
+#define RC5T583_INT_EN_ADC2	0x91
+#define RC5T583_INT_EN_ADC3	0x92
+
+/* Interrupt status registers (monitor regs in Ricoh)*/
+#define RC5T583_INTC_INTPOL	0xAD
+#define RC5T583_INTC_INTEN	0xAE
+#define RC5T583_INTC_INTMON	0xAF
+
+#define RC5T583_INT_MON_GRP	0xAF
+#define RC5T583_INT_MON_SYS1	0x1B
+#define RC5T583_INT_MON_SYS2	0x1F
+#define RC5T583_INT_MON_DCDC	0x43
+#define RC5T583_INT_MON_RTC	0xEE
+
+/* Interrupt clearing registers */
+#define RC5T583_INT_IR_SYS1	0x1A
+#define RC5T583_INT_IR_SYS2	0x1E
+#define RC5T583_INT_IR_DCDC	0x42
+#define RC5T583_INT_IR_RTC	0xEE
+#define RC5T583_INT_IR_ADCL	0x94
+#define RC5T583_INT_IR_ADCH	0x95
+#define RC5T583_INT_IR_ADCEND	0x96
+#define RC5T583_INT_IR_GPIOR	0xA9
+#define RC5T583_INT_IR_GPIOF	0xAA
+
+/* Sleep sequence registers */
+#define RC5T583_SLPSEQ1		0x21
+#define RC5T583_SLPSEQ2		0x22
+#define RC5T583_SLPSEQ3		0x23
+#define RC5T583_SLPSEQ4		0x24
+#define RC5T583_SLPSEQ5		0x25
+#define RC5T583_SLPSEQ6		0x26
+#define RC5T583_SLPSEQ7		0x27
+#define RC5T583_SLPSEQ8		0x28
+#define RC5T583_SLPSEQ9		0x29
+#define RC5T583_SLPSEQ10	0x2A
+#define RC5T583_SLPSEQ11	0x2B
+
+/* Regulator registers */
+#define RC5T583_REG_DC0CTL	0x30
+#define RC5T583_REG_DC0DAC	0x31
+#define RC5T583_REG_DC0LATCTL	0x32
+#define RC5T583_REG_SR0CTL	0x33
+
+#define RC5T583_REG_DC1CTL	0x34
+#define RC5T583_REG_DC1DAC	0x35
+#define RC5T583_REG_DC1LATCTL	0x36
+#define RC5T583_REG_SR1CTL	0x37
+
+#define RC5T583_REG_DC2CTL	0x38
+#define RC5T583_REG_DC2DAC	0x39
+#define RC5T583_REG_DC2LATCTL	0x3A
+#define RC5T583_REG_SR2CTL	0x3B
+
+#define RC5T583_REG_DC3CTL	0x3C
+#define RC5T583_REG_DC3DAC	0x3D
+#define RC5T583_REG_DC3LATCTL	0x3E
+#define RC5T583_REG_SR3CTL	0x3F
+
+
+#define RC5T583_REG_LDOEN1	0x50
+#define RC5T583_REG_LDOEN2	0x51
+#define RC5T583_REG_LDODIS1	0x52
+#define RC5T583_REG_LDODIS2	0x53
+
+#define RC5T583_REG_LDO0DAC	0x54
+#define RC5T583_REG_LDO1DAC	0x55
+#define RC5T583_REG_LDO2DAC	0x56
+#define RC5T583_REG_LDO3DAC	0x57
+#define RC5T583_REG_LDO4DAC	0x58
+#define RC5T583_REG_LDO5DAC	0x59
+#define RC5T583_REG_LDO6DAC	0x5A
+#define RC5T583_REG_LDO7DAC	0x5B
+#define RC5T583_REG_LDO8DAC	0x5C
+#define RC5T583_REG_LDO9DAC	0x5D
+
+#define RC5T583_REG_DC0DAC_DS	0x60
+#define RC5T583_REG_DC1DAC_DS	0x61
+#define RC5T583_REG_DC2DAC_DS	0x62
+#define RC5T583_REG_DC3DAC_DS	0x63
+
+#define RC5T583_REG_LDO0DAC_DS	0x64
+#define RC5T583_REG_LDO1DAC_DS	0x65
+#define RC5T583_REG_LDO2DAC_DS	0x66
+#define RC5T583_REG_LDO3DAC_DS	0x67
+#define RC5T583_REG_LDO4DAC_DS	0x68
+#define RC5T583_REG_LDO5DAC_DS	0x69
+#define RC5T583_REG_LDO6DAC_DS	0x6A
+#define RC5T583_REG_LDO7DAC_DS	0x6B
+#define RC5T583_REG_LDO8DAC_DS	0x6C
+#define RC5T583_REG_LDO9DAC_DS	0x6D
+
+/* GPIO register base address */
+#define RC5T583_GPIO_IOSEL	0xA0
+#define RC5T583_GPIO_PDEN	0xA1
+#define RC5T583_GPIO_IOOUT	0xA2
+#define RC5T583_GPIO_PGSEL	0xA3
+#define RC5T583_GPIO_GPINV	0xA4
+#define RC5T583_GPIO_GPDEB	0xA5
+#define RC5T583_GPIO_GPEDGE1	0xA6
+#define RC5T583_GPIO_GPEDGE2	0xA7
+#define RC5T583_GPIO_EN_INT	0xA8
+#define RC5T583_GPIO_MON_IOIN	0xAB
+#define RC5T583_GPIO_GPOFUNC	0xAC
+
+/* RICOH_RC5T583 IRQ definitions */
+enum {
+	RC5T583_IRQ_ONKEY,
+	RC5T583_IRQ_ACOK,
+	RC5T583_IRQ_LIDOPEN,
+	RC5T583_IRQ_PREOT,
+	RC5T583_IRQ_CLKSTP,
+	RC5T583_IRQ_ONKEY_OFF,
+	RC5T583_IRQ_WD,
+	RC5T583_IRQ_EN_PWRREQ1,
+	RC5T583_IRQ_EN_PWRREQ2,
+	RC5T583_IRQ_PRE_VINDET,
+
+	RC5T583_IRQ_DC0LIM,
+	RC5T583_IRQ_DC1LIM,
+	RC5T583_IRQ_DC2LIM,
+	RC5T583_IRQ_DC3LIM,
+
+	RC5T583_IRQ_CTC,
+	RC5T583_IRQ_YALE,
+	RC5T583_IRQ_DALE,
+	RC5T583_IRQ_WALE,
+
+	RC5T583_IRQ_AIN1L,
+	RC5T583_IRQ_AIN2L,
+	RC5T583_IRQ_AIN3L,
+	RC5T583_IRQ_VBATL,
+	RC5T583_IRQ_VIN3L,
+	RC5T583_IRQ_VIN8L,
+	RC5T583_IRQ_AIN1H,
+	RC5T583_IRQ_AIN2H,
+	RC5T583_IRQ_AIN3H,
+	RC5T583_IRQ_VBATH,
+	RC5T583_IRQ_VIN3H,
+	RC5T583_IRQ_VIN8H,
+	RC5T583_IRQ_ADCEND,
+
+	RC5T583_IRQ_GPIO0,
+	RC5T583_IRQ_GPIO1,
+	RC5T583_IRQ_GPIO2,
+	RC5T583_IRQ_GPIO3,
+	RC5T583_IRQ_GPIO4,
+	RC5T583_IRQ_GPIO5,
+	RC5T583_IRQ_GPIO6,
+	RC5T583_IRQ_GPIO7,
+
+	/* Should be last entry */
+	RC5T583_MAX_IRQS,
+};
+
+/* Ricoh583 gpio definitions */
+enum {
+	RC5T583_GPIO0,
+	RC5T583_GPIO1,
+	RC5T583_GPIO2,
+	RC5T583_GPIO3,
+	RC5T583_GPIO4,
+	RC5T583_GPIO5,
+	RC5T583_GPIO6,
+	RC5T583_GPIO7,
+
+	/* Should be last entry */
+	RC5T583_MAX_GPIO,
+};
+
+enum {
+	RC5T583_DS_NONE,
+	RC5T583_DS_DC0,
+	RC5T583_DS_DC1,
+	RC5T583_DS_DC2,
+	RC5T583_DS_DC3,
+	RC5T583_DS_LDO0,
+	RC5T583_DS_LDO1,
+	RC5T583_DS_LDO2,
+	RC5T583_DS_LDO3,
+	RC5T583_DS_LDO4,
+	RC5T583_DS_LDO5,
+	RC5T583_DS_LDO6,
+	RC5T583_DS_LDO7,
+	RC5T583_DS_LDO8,
+	RC5T583_DS_LDO9,
+	RC5T583_DS_PSO0,
+	RC5T583_DS_PSO1,
+	RC5T583_DS_PSO2,
+	RC5T583_DS_PSO3,
+	RC5T583_DS_PSO4,
+	RC5T583_DS_PSO5,
+	RC5T583_DS_PSO6,
+	RC5T583_DS_PSO7,
+
+	/* Should be last entry */
+	RC5T583_DS_MAX,
+};
+
+/*
+ * Ricoh pmic RC5T583 supports sleep through two external controls.
+ * The output of gpios and regulator can be enable/disable through
+ * this external signals.
+ */
+enum {
+	RC5T583_EXT_PWRREQ1_CONTROL = 0x1,
+	RC5T583_EXT_PWRREQ2_CONTROL = 0x2,
+};
+
+struct rc5t583 {
+	struct device	*dev;
+	struct regmap	*regmap;
+	int		chip_irq;
+	int		irq_base;
+	struct mutex	irq_lock;
+	unsigned long	group_irq_en[MAX_MAIN_INTERRUPT];
+
+	/* For main interrupt bits in INTC */
+	uint8_t		intc_inten_reg;
+
+	/* For group interrupt bits and address */
+	uint8_t		irq_en_reg[RC5T583_MAX_INTERRUPT_MASK_REGS];
+
+	/* For gpio edge */
+	uint8_t		gpedge_reg[RC5T583_MAX_GPEDGE_REG];
+};
+
+/*
+ * rc5t583_platform_data: Platform data for ricoh rc5t583 pmu.
+ * The board specific data is provided through this structure.
+ * @irq_base: Irq base number on which this device registers their interrupts.
+ * @enable_shutdown: Enable shutdown through the input pin "shutdown".
+ */
+
+struct rc5t583_platform_data {
+	int		irq_base;
+	bool		enable_shutdown;
+};
+
+int rc5t583_write(struct device *dev, u8 reg, uint8_t val);
+int rc5t583_read(struct device *dev, uint8_t reg, uint8_t *val);
+int rc5t583_set_bits(struct device *dev, unsigned int reg,
+		unsigned int bit_mask);
+int rc5t583_clear_bits(struct device *dev, unsigned int reg,
+		unsigned int bit_mask);
+int rc5t583_update(struct device *dev, unsigned int reg,
+		unsigned int val, unsigned int mask);
+int rc5t583_ext_power_req_config(struct device *dev, int deepsleep_id,
+	int ext_pwr_req, int deepsleep_slot_nr);
+int rc5t583_irq_init(struct rc5t583 *rc5t583, int irq, int irq_base);
+int rc5t583_irq_exit(struct rc5t583 *rc5t583);
+
+#endif
diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h
index 8c54de674b4b..8516fd1eaabc 100644
--- a/include/linux/mfd/stmpe.h
+++ b/include/linux/mfd/stmpe.h
@@ -28,6 +28,7 @@ enum stmpe_partnum {
 	STMPE1601,
 	STMPE2401,
 	STMPE2403,
+	STMPE_NBR_PARTS
 };
 
 /*
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 0dc98044d8b7..f5171dbf8850 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -1,8 +1,10 @@
 #ifndef MFD_TMIO_H
 #define MFD_TMIO_H
 
+#include <linux/device.h>
 #include <linux/fb.h>
 #include <linux/io.h>
+#include <linux/jiffies.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 
@@ -64,8 +66,8 @@
 #define TMIO_MMC_SDIO_IRQ		(1 << 2)
 /*
  * Some platforms can detect card insertion events with controller powered
- * down, in which case they have to call tmio_mmc_cd_wakeup() to power up the
- * controller and report the event to the driver.
+ * down, using a GPIO IRQ, in which case they have to fill in cd_irq, cd_gpio,
+ * and cd_flags fields of struct tmio_mmc_data.
  */
 #define TMIO_MMC_HAS_COLD_CD		(1 << 3)
 /*
@@ -73,6 +75,12 @@
  * idle before writing to some registers.
  */
 #define TMIO_MMC_HAS_IDLE_WAIT		(1 << 4)
+/*
+ * A GPIO is used for card hotplug detection. We need an extra flag for this,
+ * because 0 is a valid GPIO number too, and requiring users to specify
+ * cd_gpio < 0 to disable GPIO hotplug would break backwards compatibility.
+ */
+#define TMIO_MMC_USE_GPIO_CD		(1 << 5)
 
 int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base);
 int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base);
@@ -97,19 +105,23 @@ struct tmio_mmc_data {
 	u32				ocr_mask;	/* available voltages */
 	struct tmio_mmc_dma		*dma;
 	struct device			*dev;
-	bool				power;
+	unsigned int			cd_gpio;
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
 	int (*get_cd)(struct platform_device *host);
 	int (*write16_hook)(struct tmio_mmc_host *host, int addr);
 };
 
+/*
+ * This function is deprecated and will be removed soon. Please, convert your
+ * platform to use drivers/mmc/core/cd-gpio.c
+ */
+#include <linux/mmc/host.h>
 static inline void tmio_mmc_cd_wakeup(struct tmio_mmc_data *pdata)
 {
-	if (pdata && !pdata->power) {
-		pdata->power = true;
-		pm_runtime_get(pdata->dev);
-	}
+	if (pdata)
+		mmc_detect_change(dev_get_drvdata(pdata->dev),
+				  msecs_to_jiffies(100));
 }
 
 /*
diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h
new file mode 100644
index 000000000000..38e31c55adbb
--- /dev/null
+++ b/include/linux/mfd/tps65090.h
@@ -0,0 +1,46 @@
+/*
+ * Core driver interface for TI TPS65090 PMIC family
+ *
+ * Copyright (C) 2012 NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ */
+
+#ifndef __LINUX_MFD_TPS65090_H
+#define __LINUX_MFD_TPS65090_H
+
+struct tps65090_subdev_info {
+	int		id;
+	const char	*name;
+	void		*platform_data;
+};
+
+struct tps65090_platform_data {
+	int irq_base;
+	int num_subdevs;
+	struct tps65090_subdev_info *subdevs;
+};
+
+/*
+ * NOTE: the functions below are not intended for use outside
+ * of the TPS65090 sub-device drivers
+ */
+extern int tps65090_write(struct device *dev, int reg, uint8_t val);
+extern int tps65090_read(struct device *dev, int reg, uint8_t *val);
+extern int tps65090_set_bits(struct device *dev, int reg, uint8_t bit_num);
+extern int tps65090_clr_bits(struct device *dev, int reg, uint8_t bit_num);
+
+#endif /*__LINUX_MFD_TPS65090_H */
diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h
new file mode 100644
index 000000000000..e030ef9a64ee
--- /dev/null
+++ b/include/linux/mfd/tps65217.h
@@ -0,0 +1,283 @@
+/*
+ * linux/mfd/tps65217.h
+ *
+ * Functions to access TPS65217 power management chip.
+ *
+ * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_MFD_TPS65217_H
+#define __LINUX_MFD_TPS65217_H
+
+#include <linux/i2c.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+
+/* I2C ID for TPS65217 part */
+#define TPS65217_I2C_ID			0x24
+
+/* All register addresses */
+#define TPS65217_REG_CHIPID		0X00
+#define TPS65217_REG_PPATH		0X01
+#define TPS65217_REG_INT		0X02
+#define TPS65217_REG_CHGCONFIG0		0X03
+#define TPS65217_REG_CHGCONFIG1		0X04
+#define TPS65217_REG_CHGCONFIG2		0X05
+#define TPS65217_REG_CHGCONFIG3		0X06
+#define TPS65217_REG_WLEDCTRL1		0X07
+#define TPS65217_REG_WLEDCTRL2		0X08
+#define TPS65217_REG_MUXCTRL		0X09
+#define TPS65217_REG_STATUS		0X0A
+#define TPS65217_REG_PASSWORD		0X0B
+#define TPS65217_REG_PGOOD		0X0C
+#define TPS65217_REG_DEFPG		0X0D
+#define TPS65217_REG_DEFDCDC1		0X0E
+#define TPS65217_REG_DEFDCDC2		0X0F
+#define TPS65217_REG_DEFDCDC3		0X10
+#define TPS65217_REG_DEFSLEW		0X11
+#define TPS65217_REG_DEFLDO1		0X12
+#define TPS65217_REG_DEFLDO2		0X13
+#define TPS65217_REG_DEFLS1		0X14
+#define TPS65217_REG_DEFLS2		0X15
+#define TPS65217_REG_ENABLE		0X16
+#define TPS65217_REG_DEFUVLO		0X18
+#define TPS65217_REG_SEQ1		0X19
+#define TPS65217_REG_SEQ2		0X1A
+#define TPS65217_REG_SEQ3		0X1B
+#define TPS65217_REG_SEQ4		0X1C
+#define TPS65217_REG_SEQ5		0X1D
+#define TPS65217_REG_SEQ6		0X1E
+
+/* Register field definitions */
+#define TPS65217_CHIPID_CHIP_MASK	0xF0
+#define TPS65217_CHIPID_REV_MASK	0x0F
+
+#define TPS65217_PPATH_ACSINK_ENABLE	BIT(7)
+#define TPS65217_PPATH_USBSINK_ENABLE	BIT(6)
+#define TPS65217_PPATH_AC_PW_ENABLE	BIT(5)
+#define TPS65217_PPATH_USB_PW_ENABLE	BIT(4)
+#define TPS65217_PPATH_AC_CURRENT_MASK	0x0C
+#define TPS65217_PPATH_USB_CURRENT_MASK	0x03
+
+#define TPS65217_INT_PBM		BIT(6)
+#define TPS65217_INT_ACM		BIT(5)
+#define TPS65217_INT_USBM		BIT(4)
+#define TPS65217_INT_PBI		BIT(2)
+#define TPS65217_INT_ACI		BIT(1)
+#define TPS65217_INT_USBI		BIT(0)
+
+#define TPS65217_CHGCONFIG0_TREG	BIT(7)
+#define TPS65217_CHGCONFIG0_DPPM	BIT(6)
+#define TPS65217_CHGCONFIG0_TSUSP	BIT(5)
+#define TPS65217_CHGCONFIG0_TERMI	BIT(4)
+#define TPS65217_CHGCONFIG0_ACTIVE	BIT(3)
+#define TPS65217_CHGCONFIG0_CHGTOUT	BIT(2)
+#define TPS65217_CHGCONFIG0_PCHGTOUT	BIT(1)
+#define TPS65217_CHGCONFIG0_BATTEMP	BIT(0)
+
+#define TPS65217_CHGCONFIG1_TMR_MASK	0xC0
+#define TPS65217_CHGCONFIG1_TMR_ENABLE	BIT(5)
+#define TPS65217_CHGCONFIG1_NTC_TYPE	BIT(4)
+#define TPS65217_CHGCONFIG1_RESET	BIT(3)
+#define TPS65217_CHGCONFIG1_TERM	BIT(2)
+#define TPS65217_CHGCONFIG1_SUSP	BIT(1)
+#define TPS65217_CHGCONFIG1_CHG_EN	BIT(0)
+
+#define TPS65217_CHGCONFIG2_DYNTMR	BIT(7)
+#define TPS65217_CHGCONFIG2_VPREGHG	BIT(6)
+#define TPS65217_CHGCONFIG2_VOREG_MASK	0x30
+
+#define TPS65217_CHGCONFIG3_ICHRG_MASK	0xC0
+#define TPS65217_CHGCONFIG3_DPPMTH_MASK	0x30
+#define TPS65217_CHGCONFIG2_PCHRGT	BIT(3)
+#define TPS65217_CHGCONFIG2_TERMIF	0x06
+#define TPS65217_CHGCONFIG2_TRANGE	BIT(0)
+
+#define TPS65217_WLEDCTRL1_ISINK_ENABLE	BIT(3)
+#define TPS65217_WLEDCTRL1_ISEL		BIT(2)
+#define TPS65217_WLEDCTRL1_FDIM_MASK	0x03
+
+#define TPS65217_WLEDCTRL2_DUTY_MASK	0x7F
+
+#define TPS65217_MUXCTRL_MUX_MASK	0x07
+
+#define TPS65217_STATUS_OFF		BIT(7)
+#define TPS65217_STATUS_ACPWR		BIT(3)
+#define TPS65217_STATUS_USBPWR		BIT(2)
+#define TPS65217_STATUS_PB		BIT(0)
+
+#define TPS65217_PASSWORD_REGS_UNLOCK	0x7D
+
+#define TPS65217_PGOOD_LDO3_PG		BIT(6)
+#define TPS65217_PGOOD_LDO4_PG		BIT(5)
+#define TPS65217_PGOOD_DC1_PG		BIT(4)
+#define TPS65217_PGOOD_DC2_PG		BIT(3)
+#define TPS65217_PGOOD_DC3_PG		BIT(2)
+#define TPS65217_PGOOD_LDO1_PG		BIT(1)
+#define TPS65217_PGOOD_LDO2_PG		BIT(0)
+
+#define TPS65217_DEFPG_LDO1PGM		BIT(3)
+#define TPS65217_DEFPG_LDO2PGM		BIT(2)
+#define TPS65217_DEFPG_PGDLY_MASK	0x03
+
+#define TPS65217_DEFDCDCX_XADJX		BIT(7)
+#define TPS65217_DEFDCDCX_DCDC_MASK	0x3F
+
+#define TPS65217_DEFSLEW_GO		BIT(7)
+#define TPS65217_DEFSLEW_GODSBL		BIT(6)
+#define TPS65217_DEFSLEW_PFM_EN1	BIT(5)
+#define TPS65217_DEFSLEW_PFM_EN2	BIT(4)
+#define TPS65217_DEFSLEW_PFM_EN3	BIT(3)
+#define TPS65217_DEFSLEW_SLEW_MASK	0x07
+
+#define TPS65217_DEFLDO1_LDO1_MASK	0x0F
+
+#define TPS65217_DEFLDO2_TRACK		BIT(6)
+#define TPS65217_DEFLDO2_LDO2_MASK	0x3F
+
+#define TPS65217_DEFLDO3_LDO3_EN	BIT(5)
+#define TPS65217_DEFLDO3_LDO3_MASK	0x1F
+
+#define TPS65217_DEFLDO4_LDO4_EN	BIT(5)
+#define TPS65217_DEFLDO4_LDO4_MASK	0x1F
+
+#define TPS65217_ENABLE_LS1_EN		BIT(6)
+#define TPS65217_ENABLE_LS2_EN		BIT(5)
+#define TPS65217_ENABLE_DC1_EN		BIT(4)
+#define TPS65217_ENABLE_DC2_EN		BIT(3)
+#define TPS65217_ENABLE_DC3_EN		BIT(2)
+#define TPS65217_ENABLE_LDO1_EN		BIT(1)
+#define TPS65217_ENABLE_LDO2_EN		BIT(0)
+
+#define TPS65217_DEFUVLO_UVLOHYS	BIT(2)
+#define TPS65217_DEFUVLO_UVLO_MASK	0x03
+
+#define TPS65217_SEQ1_DC1_SEQ_MASK	0xF0
+#define TPS65217_SEQ1_DC2_SEQ_MASK	0x0F
+
+#define TPS65217_SEQ2_DC3_SEQ_MASK	0xF0
+#define TPS65217_SEQ2_LDO1_SEQ_MASK	0x0F
+
+#define TPS65217_SEQ3_LDO2_SEQ_MASK	0xF0
+#define TPS65217_SEQ3_LDO3_SEQ_MASK	0x0F
+
+#define TPS65217_SEQ4_LDO4_SEQ_MASK	0xF0
+
+#define TPS65217_SEQ5_DLY1_MASK		0xC0
+#define TPS65217_SEQ5_DLY2_MASK		0x30
+#define TPS65217_SEQ5_DLY3_MASK		0x0C
+#define TPS65217_SEQ5_DLY4_MASK		0x03
+
+#define TPS65217_SEQ6_DLY5_MASK		0xC0
+#define TPS65217_SEQ6_DLY6_MASK		0x30
+#define TPS65217_SEQ6_SEQUP		BIT(2)
+#define TPS65217_SEQ6_SEQDWN		BIT(1)
+#define TPS65217_SEQ6_INSTDWN		BIT(0)
+
+#define TPS65217_MAX_REGISTER		0x1E
+#define TPS65217_PROTECT_NONE		0
+#define TPS65217_PROTECT_L1		1
+#define TPS65217_PROTECT_L2		2
+
+
+enum tps65217_regulator_id {
+	/* DCDC's */
+	TPS65217_DCDC_1,
+	TPS65217_DCDC_2,
+	TPS65217_DCDC_3,
+	/* LDOs */
+	TPS65217_LDO_1,
+	TPS65217_LDO_2,
+	TPS65217_LDO_3,
+	TPS65217_LDO_4,
+};
+
+#define TPS65217_MAX_REG_ID		TPS65217_LDO_4
+
+/* Number of step-down converters available */
+#define TPS65217_NUM_DCDC		3
+/* Number of LDO voltage regulators available */
+#define TPS65217_NUM_LDO		4
+/* Number of total regulators available */
+#define TPS65217_NUM_REGULATOR		(TPS65217_NUM_DCDC + TPS65217_NUM_LDO)
+
+/**
+ * struct tps65217_board - packages regulator init data
+ * @tps65217_regulator_data: regulator initialization values
+ *
+ * Board data may be used to initialize regulator.
+ */
+struct tps65217_board {
+	struct regulator_init_data *tps65217_init_data;
+};
+
+/**
+ * struct tps_info - packages regulator constraints
+ * @name:		Voltage regulator name
+ * @min_uV:		minimum micro volts
+ * @max_uV:		minimum micro volts
+ * @vsel_to_uv:		Function pointer to get voltage from selector
+ * @uv_to_vsel:		Function pointer to get selector from voltage
+ * @table:		Table for non-uniform voltage step-size
+ * @table_len:		Length of the voltage table
+ * @enable_mask:	Regulator enable mask bits
+ * @set_vout_reg:	Regulator output voltage set register
+ * @set_vout_mask:	Regulator output voltage set mask
+ *
+ * This data is used to check the regualtor voltage limits while setting.
+ */
+struct tps_info {
+	const char *name;
+	int min_uV;
+	int max_uV;
+	int (*vsel_to_uv)(unsigned int vsel);
+	int (*uv_to_vsel)(int uV, unsigned int *vsel);
+	const int *table;
+	unsigned int table_len;
+	unsigned int enable_mask;
+	unsigned int set_vout_reg;
+	unsigned int set_vout_mask;
+};
+
+/**
+ * struct tps65217 - tps65217 sub-driver chip access routines
+ *
+ * Device data may be used to access the TPS65217 chip
+ */
+
+struct tps65217 {
+	struct device *dev;
+	struct tps65217_board *pdata;
+	struct regulator_desc desc[TPS65217_NUM_REGULATOR];
+	struct regulator_dev *rdev[TPS65217_NUM_REGULATOR];
+	struct tps_info *info[TPS65217_NUM_REGULATOR];
+	struct regmap *regmap;
+
+	/* Client devices */
+	struct platform_device *regulator_pdev[TPS65217_NUM_REGULATOR];
+};
+
+static inline struct tps65217 *dev_to_tps65217(struct device *dev)
+{
+	return dev_get_drvdata(dev);
+}
+
+int tps65217_reg_read(struct tps65217 *tps, unsigned int reg,
+					unsigned int *val);
+int tps65217_reg_write(struct tps65217 *tps, unsigned int reg,
+			unsigned int val, unsigned int level);
+int tps65217_set_bits(struct tps65217 *tps, unsigned int reg,
+		unsigned int mask, unsigned int val, unsigned int level);
+int tps65217_clear_bits(struct tps65217 *tps, unsigned int reg,
+		unsigned int mask, unsigned int level);
+
+#endif /*  __LINUX_MFD_TPS65217_H */
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 76700b5eee92..1c6c2860d1a6 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -17,6 +17,8 @@
 #ifndef __LINUX_MFD_TPS65910_H
 #define __LINUX_MFD_TPS65910_H
 
+#include <linux/gpio.h>
+
 /* TPS chip id list */
 #define TPS65910			0
 #define TPS65911			1
@@ -657,6 +659,8 @@
 
 
 /*Register GPIO  (0x80) register.RegisterDescription */
+#define GPIO_SLEEP_MASK                         0x80
+#define GPIO_SLEEP_SHIFT                        7
 #define GPIO_DEB_MASK                           0x10
 #define GPIO_DEB_SHIFT                          4
 #define GPIO_PUEN_MASK                          0x08
@@ -740,6 +744,11 @@
 #define TPS65910_GPIO_STS				BIT(1)
 #define TPS65910_GPIO_SET				BIT(0)
 
+/* Max number of TPS65910/11 GPIOs */
+#define TPS65910_NUM_GPIO				6
+#define TPS65911_NUM_GPIO				9
+#define TPS6591X_MAX_NUM_GPIO				9
+
 /* Regulator Index Definitions */
 #define TPS65910_REG_VRTC				0
 #define TPS65910_REG_VIO				1
@@ -785,6 +794,7 @@ struct tps65910_board {
 	int irq_base;
 	int vmbch_threshold;
 	int vmbch2_threshold;
+	bool en_gpio_sleep[TPS6591X_MAX_NUM_GPIO];
 	unsigned long regulator_ext_sleep_control[TPS65910_NUM_REGS];
 	struct regulator_init_data *tps65910_pmic_init_data[TPS65910_NUM_REGS];
 };
@@ -796,6 +806,7 @@ struct tps65910_board {
 struct tps65910 {
 	struct device *dev;
 	struct i2c_client *i2c_client;
+	struct regmap *regmap;
 	struct mutex io_mutex;
 	unsigned int id;
 	int (*read)(struct tps65910 *tps65910, u8 reg, int size, void *dest);
diff --git a/include/linux/mfd/ucb1x00.h b/include/linux/mfd/ucb1x00.h
index 4321f044d1e4..28af41756360 100644
--- a/include/linux/mfd/ucb1x00.h
+++ b/include/linux/mfd/ucb1x00.h
@@ -12,7 +12,7 @@
 
 #include <linux/mfd/mcp.h>
 #include <linux/gpio.h>
-#include <linux/semaphore.h>
+#include <linux/mutex.h>
 
 #define UCB_IO_DATA	0x00
 #define UCB_IO_DIR	0x01
@@ -104,17 +104,27 @@
 #define UCB_MODE_DYN_VFLAG_ENA	(1 << 12)
 #define UCB_MODE_AUD_OFF_CAN	(1 << 13)
 
+enum ucb1x00_reset {
+	UCB_RST_PROBE,
+	UCB_RST_RESUME,
+	UCB_RST_SUSPEND,
+	UCB_RST_REMOVE,
+	UCB_RST_PROBE_FAIL,
+};
 
-struct ucb1x00_irq {
-	void *devid;
-	void (*fn)(int, void *);
+struct ucb1x00_plat_data {
+	void			(*reset)(enum ucb1x00_reset);
+	unsigned		irq_base;
+	int			gpio_base;
+	unsigned		can_wakeup;
 };
 
 struct ucb1x00 {
-	spinlock_t		lock;
+	raw_spinlock_t		irq_lock;
 	struct mcp		*mcp;
 	unsigned int		irq;
-	struct semaphore	adc_sem;
+	int			irq_base;
+	struct mutex		adc_mutex;
 	spinlock_t		io_lock;
 	u16			id;
 	u16			io_dir;
@@ -122,7 +132,8 @@ struct ucb1x00 {
 	u16			adc_cr;
 	u16			irq_fal_enbl;
 	u16			irq_ris_enbl;
-	struct ucb1x00_irq	irq_handler[16];
+	u16			irq_mask;
+	u16			irq_wake;
 	struct device		dev;
 	struct list_head	node;
 	struct list_head	devs;
@@ -144,7 +155,7 @@ struct ucb1x00_driver {
 	struct list_head	devs;
 	int	(*add)(struct ucb1x00_dev *dev);
 	void	(*remove)(struct ucb1x00_dev *dev);
-	int	(*suspend)(struct ucb1x00_dev *dev, pm_message_t state);
+	int	(*suspend)(struct ucb1x00_dev *dev);
 	int	(*resume)(struct ucb1x00_dev *dev);
 };
 
@@ -245,15 +256,4 @@ unsigned int ucb1x00_adc_read(struct ucb1x00 *ucb, int adc_channel, int sync);
 void ucb1x00_adc_enable(struct ucb1x00 *ucb);
 void ucb1x00_adc_disable(struct ucb1x00 *ucb);
 
-/*
- * Which edges of the IRQ do you want to control today?
- */
-#define UCB_RISING	(1 << 0)
-#define UCB_FALLING	(1 << 1)
-
-int ucb1x00_hook_irq(struct ucb1x00 *ucb, unsigned int idx, void (*fn)(int, void *), void *devid);
-void ucb1x00_enable_irq(struct ucb1x00 *ucb, unsigned int idx, int edges);
-void ucb1x00_disable_irq(struct ucb1x00 *ucb, unsigned int idx, int edges);
-int ucb1x00_free_irq(struct ucb1x00 *ucb, unsigned int idx, void *devid);
-
 #endif
diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h
index dc3e05011689..893267bb6229 100644
--- a/include/linux/mfd/wm8994/pdata.h
+++ b/include/linux/mfd/wm8994/pdata.h
@@ -22,7 +22,6 @@ struct wm8994_ldo_pdata {
 	/** GPIOs to enable regulator, 0 or less if not available */
 	int enable;
 
-	const char *supply;
 	const struct regulator_init_data *init_data;
 };
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cf7982336103..d8738a464b94 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -954,7 +954,7 @@ extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 extern int vmtruncate(struct inode *inode, loff_t offset);
 extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end);
-
+void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
 int truncate_inode_page(struct address_space *mapping, struct page *page);
 int generic_error_remove_page(struct address_space *mapping, struct page *page);
 
@@ -1258,6 +1258,8 @@ static inline void pgtable_page_dtor(struct page *page)
 extern void free_area_init(unsigned long * zones_size);
 extern void free_area_init_node(int nid, unsigned long * zones_size,
 		unsigned long zone_start_pfn, unsigned long *zholes_size);
+extern void free_initmem(void);
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 /*
  * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 6faa145c81e3..01beae78f079 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -72,6 +72,8 @@ struct mmc_ext_csd {
 	bool			hpi_en;			/* HPI enablebit */
 	bool			hpi;			/* HPI support bit */
 	unsigned int		hpi_cmd;		/* cmd used as HPI */
+	unsigned int            data_sector_size;       /* 512 bytes or 4KB */
+	unsigned int            data_tag_unit_size;     /* DATA TAG UNIT size */
 	unsigned int		boot_ro_lock;		/* ro lock support */
 	bool			boot_ro_lockable;
 	u8			raw_partition_support;	/* 160 */
diff --git a/include/linux/mmc/cd-gpio.h b/include/linux/mmc/cd-gpio.h
index a8e469783318..cefaba038ccb 100644
--- a/include/linux/mmc/cd-gpio.h
+++ b/include/linux/mmc/cd-gpio.h
@@ -12,8 +12,7 @@
 #define MMC_CD_GPIO_H
 
 struct mmc_host;
-int mmc_cd_gpio_request(struct mmc_host *host, unsigned int gpio,
-			unsigned int irq, unsigned long flags);
+int mmc_cd_gpio_request(struct mmc_host *host, unsigned int gpio);
 void mmc_cd_gpio_free(struct mmc_host *host);
 
 #endif
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 2e6a681fceb2..1b431c728b9a 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -175,7 +175,6 @@ extern unsigned int mmc_align_data_size(struct mmc_card *, unsigned int);
 
 extern int __mmc_claim_host(struct mmc_host *host, atomic_t *abort);
 extern void mmc_release_host(struct mmc_host *host);
-extern void mmc_do_release_host(struct mmc_host *host);
 extern int mmc_try_claim_host(struct mmc_host *host);
 
 extern int mmc_flush_cache(struct mmc_card *);
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index aae5d1f1bb39..8f66e28f5a0f 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -76,7 +76,7 @@ struct mmc_data;
  * @num_slots: Number of slots available.
  * @verid: Denote Version ID.
  * @data_offset: Set the offset of DATA register according to VERID.
- * @pdev: Platform device associated with the MMC controller.
+ * @dev: Device associated with the MMC controller.
  * @pdata: Platform data associated with the MMC controller.
  * @slot: Slots sharing this MMC controller.
  * @fifo_depth: depth of FIFO.
@@ -87,6 +87,8 @@ struct mmc_data;
  * @push_data: Pointer to FIFO push function.
  * @pull_data: Pointer to FIFO pull function.
  * @quirks: Set of quirks that apply to specific versions of the IP.
+ * @irq_flags: The flags to be passed to request_irq.
+ * @irq: The irq value to be passed to request_irq.
  *
  * Locking
  * =======
@@ -153,7 +155,7 @@ struct dw_mci {
 	u32			fifoth_val;
 	u16			verid;
 	u16			data_offset;
-	struct platform_device	*pdev;
+	struct device		dev;
 	struct dw_mci_board	*pdata;
 	struct dw_mci_slot	*slot[MAX_MCI_SLOTS];
 
@@ -174,6 +176,8 @@ struct dw_mci {
 	u32			quirks;
 
 	struct regulator	*vmmc;	/* Power regulator */
+	unsigned long		irq_flags; /* IRQ flags */
+	unsigned int		irq;
 };
 
 /* DMA ops for Internal/External DMAC interface */
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 91924e8c642b..cbde4b7e675e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -81,34 +81,11 @@ struct mmc_ios {
 
 struct mmc_host_ops {
 	/*
-	 * Hosts that support power saving can use the 'enable' and 'disable'
-	 * methods to exit and enter power saving states. 'enable' is called
-	 * when the host is claimed and 'disable' is called (or scheduled with
-	 * a delay) when the host is released. The 'disable' is scheduled if
-	 * the disable delay set by 'mmc_set_disable_delay()' is non-zero,
-	 * otherwise 'disable' is called immediately. 'disable' may be
-	 * scheduled repeatedly, to permit ever greater power saving at the
-	 * expense of ever greater latency to re-enable. Rescheduling is
-	 * determined by the return value of the 'disable' method. A positive
-	 * value gives the delay in milliseconds.
-	 *
-	 * In the case where a host function (like set_ios) may be called
-	 * with or without the host claimed, enabling and disabling can be
-	 * done directly and will nest correctly. Call 'mmc_host_enable()' and
-	 * 'mmc_host_lazy_disable()' for this purpose, but note that these
-	 * functions must be paired.
-	 *
-	 * Alternatively, 'mmc_host_enable()' may be paired with
-	 * 'mmc_host_disable()' which calls 'disable' immediately.  In this
-	 * case the 'disable' method will be called with 'lazy' set to 0.
-	 * This is mainly useful for error paths.
-	 *
-	 * Because lazy disable may be called from a work queue, the 'disable'
-	 * method must claim the host when 'lazy' != 0, which will work
-	 * correctly because recursion is detected and handled.
+	 * 'enable' is called when the host is claimed and 'disable' is called
+	 * when the host is released. 'enable' and 'disable' are deprecated.
 	 */
 	int (*enable)(struct mmc_host *host);
-	int (*disable)(struct mmc_host *host, int lazy);
+	int (*disable)(struct mmc_host *host);
 	/*
 	 * It is optional for the host to implement pre_req and post_req in
 	 * order to support double buffering of requests (prepare one
@@ -219,7 +196,7 @@ struct mmc_host {
 #define MMC_CAP_SPI		(1 << 4)	/* Talks only SPI protocols */
 #define MMC_CAP_NEEDS_POLL	(1 << 5)	/* Needs polling for card-detection */
 #define MMC_CAP_8_BIT_DATA	(1 << 6)	/* Can the host do 8 bit transfers */
-#define MMC_CAP_DISABLE		(1 << 7)	/* Can the host be disabled */
+
 #define MMC_CAP_NONREMOVABLE	(1 << 8)	/* Nonremovable e.g. eMMC */
 #define MMC_CAP_WAIT_WHILE_BUSY	(1 << 9)	/* Waits while card is busy */
 #define MMC_CAP_ERASE		(1 << 10)	/* Allow erase/trim commands */
@@ -259,6 +236,8 @@ struct mmc_host {
 #define MMC_CAP2_HS200		(MMC_CAP2_HS200_1_8V_SDR | \
 				 MMC_CAP2_HS200_1_2V_SDR)
 #define MMC_CAP2_BROKEN_VOLTAGE	(1 << 7)	/* Use the broken voltage */
+#define MMC_CAP2_DETECT_ON_ERR	(1 << 8)	/* On I/O err check card removal */
+#define MMC_CAP2_HC_ERASE_SZ	(1 << 9)	/* High-capacity erase size */
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 	unsigned int        power_notify_type;
@@ -301,13 +280,7 @@ struct mmc_host {
 	unsigned int		removed:1;	/* host is being removed */
 #endif
 
-	/* Only used with MMC_CAP_DISABLE */
-	int			enabled;	/* host is enabled */
 	int			rescan_disable;	/* disable card detection */
-	int			nesting_cnt;	/* "enable" nesting count */
-	int			en_dis_recurs;	/* detect recursion */
-	unsigned int		disable_delay;	/* disable delay in msecs */
-	struct delayed_work	disable;	/* disabling work */
 
 	struct mmc_card		*card;		/* device attached to this host */
 
@@ -407,17 +380,8 @@ int mmc_card_awake(struct mmc_host *host);
 int mmc_card_sleep(struct mmc_host *host);
 int mmc_card_can_sleep(struct mmc_host *host);
 
-int mmc_host_enable(struct mmc_host *host);
-int mmc_host_disable(struct mmc_host *host);
-int mmc_host_lazy_disable(struct mmc_host *host);
 int mmc_pm_notify(struct notifier_block *notify_block, unsigned long, void *);
 
-static inline void mmc_set_disable_delay(struct mmc_host *host,
-					 unsigned int disable_delay)
-{
-	host->disable_delay = disable_delay;
-}
-
 /* Module parameter */
 extern bool mmc_assume_removable;
 
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index fb9f6e116e1c..b822a2cb6008 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -274,6 +274,7 @@ struct _mmc_csd {
 #define EXT_CSD_FLUSH_CACHE		32      /* W */
 #define EXT_CSD_CACHE_CTRL		33      /* R/W */
 #define EXT_CSD_POWER_OFF_NOTIFICATION	34	/* R/W */
+#define EXT_CSD_DATA_SECTOR_SIZE	61	/* R */
 #define EXT_CSD_GP_SIZE_MULT		143	/* R/W */
 #define EXT_CSD_PARTITION_ATTRIBUTE	156	/* R/W */
 #define EXT_CSD_PARTITION_SUPPORT	160	/* RO */
@@ -315,6 +316,8 @@ struct _mmc_csd {
 #define EXT_CSD_POWER_OFF_LONG_TIME	247	/* RO */
 #define EXT_CSD_GENERIC_CMD6_TIME	248	/* RO */
 #define EXT_CSD_CACHE_SIZE		249	/* RO, 4 bytes */
+#define EXT_CSD_TAG_UNIT_SIZE		498	/* RO */
+#define EXT_CSD_DATA_TAG_SUPPORT	499	/* RO */
 #define EXT_CSD_HPI_FEATURES		503	/* RO */
 
 /*
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index c750f85177d9..e9051e1cb1ce 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -90,6 +90,8 @@ struct sdhci_host {
 
 	unsigned int quirks2;	/* More deviations from spec. */
 
+#define SDHCI_QUIRK2_HOST_OFF_CARD_ON			(1<<0)
+
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
 
diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h
index 04ff452bf5c3..05f0e3db1c12 100644
--- a/include/linux/mmc/sh_mmcif.h
+++ b/include/linux/mmc/sh_mmcif.h
@@ -77,18 +77,15 @@ struct sh_mmcif_plat_data {
 
 /* CE_CLK_CTRL */
 #define CLK_ENABLE		(1 << 24) /* 1: output mmc clock */
-#define CLK_CLEAR		((1 << 19) | (1 << 18) | (1 << 17) | (1 << 16))
-#define CLK_SUP_PCLK		((1 << 19) | (1 << 18) | (1 << 17) | (1 << 16))
-#define CLKDIV_4		(1<<16) /* mmc clock frequency.
-					 * n: bus clock/(2^(n+1)) */
-#define CLKDIV_256		(7<<16) /* mmc clock frequency. (see above) */
-#define SRSPTO_256		((1 << 13) | (0 << 12)) /* resp timeout */
-#define SRBSYTO_29		((1 << 11) | (1 << 10) |	\
-				 (1 << 9) | (1 << 8)) /* resp busy timeout */
-#define SRWDTO_29		((1 << 7) | (1 << 6) |		\
-				 (1 << 5) | (1 << 4)) /* read/write timeout */
-#define SCCSTO_29		((1 << 3) | (1 << 2) |		\
-				 (1 << 1) | (1 << 0)) /* ccs timeout */
+#define CLK_CLEAR		(0xf << 16)
+#define CLK_SUP_PCLK		(0xf << 16)
+#define CLKDIV_4		(1 << 16) /* mmc clock frequency.
+					   * n: bus clock/(2^(n+1)) */
+#define CLKDIV_256		(7 << 16) /* mmc clock frequency. (see above) */
+#define SRSPTO_256		(2 << 12) /* resp timeout */
+#define SRBSYTO_29		(0xf << 8) /* resp busy timeout */
+#define SRWDTO_29		(0xf << 4) /* read/write timeout */
+#define SCCSTO_29		(0xf << 0) /* ccs timeout */
 
 /* CE_VERSION */
 #define SOFT_RST_ON		(1 << 31)
diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h
index 71b805451bd8..e94e620aeddc 100644
--- a/include/linux/mmc/sh_mobile_sdhi.h
+++ b/include/linux/mmc/sh_mobile_sdhi.h
@@ -10,15 +10,29 @@ struct tmio_mmc_data;
 #define SH_MOBILE_SDHI_IRQ_SDCARD	"sdcard"
 #define SH_MOBILE_SDHI_IRQ_SDIO		"sdio"
 
+/**
+ * struct sh_mobile_sdhi_ops - SDHI driver callbacks
+ * @cd_wakeup:		trigger a card-detection run
+ */
+struct sh_mobile_sdhi_ops {
+	void (*cd_wakeup)(const struct platform_device *pdev);
+};
+
 struct sh_mobile_sdhi_info {
 	int dma_slave_tx;
 	int dma_slave_rx;
 	unsigned long tmio_flags;
 	unsigned long tmio_caps;
 	u32 tmio_ocr_mask;	/* available MMC voltages */
+	unsigned int cd_gpio;
 	struct tmio_mmc_data *pdata;
 	void (*set_pwr)(struct platform_device *pdev, int state);
 	int (*get_cd)(struct platform_device *pdev);
+
+	/* callbacks for board specific setup code */
+	int (*init)(struct platform_device *pdev,
+		    const struct sh_mobile_sdhi_ops *ops);
+	void (*cleanup)(struct platform_device *pdev);
 };
 
 #endif /* LINUX_MMC_SH_MOBILE_SDHI_H */
diff --git a/include/linux/module.h b/include/linux/module.h
index 4598bf03e98b..fbcafe2ee13e 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -21,8 +21,6 @@
 #include <linux/percpu.h>
 #include <asm/module.h>
 
-#include <trace/events/module.h>
-
 /* Not Yet Implemented */
 #define MODULE_SUPPORTED_DEVICE(name)
 
@@ -452,33 +450,11 @@ void symbol_put_addr(void *addr);
 
 /* Sometimes we know we already have a refcount, and it's easier not
    to handle the error case (which only happens with rmmod --wait). */
-static inline void __module_get(struct module *module)
-{
-	if (module) {
-		preempt_disable();
-		__this_cpu_inc(module->refptr->incs);
-		trace_module_get(module, _THIS_IP_);
-		preempt_enable();
-	}
-}
-
-static inline int try_module_get(struct module *module)
-{
-	int ret = 1;
-
-	if (module) {
-		preempt_disable();
+extern void __module_get(struct module *module);
 
-		if (likely(module_is_live(module))) {
-			__this_cpu_inc(module->refptr->incs);
-			trace_module_get(module, _THIS_IP_);
-		} else
-			ret = 0;
-
-		preempt_enable();
-	}
-	return ret;
-}
+/* This is the Right Way to get a module: if it fails, it's being removed,
+ * so pretend it's not there. */
+extern bool try_module_get(struct module *module);
 
 extern void module_put(struct module *module);
 
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index c47f4d60db0b..ea36486378d8 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -47,14 +47,11 @@ struct kernel_param_ops {
 	void (*free)(void *arg);
 };
 
-/* Flag bits for kernel_param.flags */
-#define KPARAM_ISBOOL		2
-
 struct kernel_param {
 	const char *name;
 	const struct kernel_param_ops *ops;
 	u16 perm;
-	u16 flags;
+	s16 level;
 	union {
 		void *arg;
 		const struct kparam_string *str;
@@ -131,8 +128,40 @@ struct kparam_array
  * The ops can have NULL set or get functions.
  */
 #define module_param_cb(name, ops, arg, perm)				      \
-	__module_param_call(MODULE_PARAM_PREFIX,			      \
-			    name, ops, arg, __same_type((arg), bool *), perm)
+	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, 0)
+
+/**
+ * <level>_param_cb - general callback for a module/cmdline parameter
+ *                    to be evaluated before certain initcall level
+ * @name: a valid C identifier which is the parameter name.
+ * @ops: the set & get operations for this parameter.
+ * @perm: visibility in sysfs.
+ *
+ * The ops can have NULL set or get functions.
+ */
+#define __level_param_cb(name, ops, arg, perm, level)			\
+	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, level)
+
+#define core_param_cb(name, ops, arg, perm)		\
+	__level_param_cb(name, ops, arg, perm, 1)
+
+#define postcore_param_cb(name, ops, arg, perm)		\
+	__level_param_cb(name, ops, arg, perm, 2)
+
+#define arch_param_cb(name, ops, arg, perm)		\
+	__level_param_cb(name, ops, arg, perm, 3)
+
+#define subsys_param_cb(name, ops, arg, perm)		\
+	__level_param_cb(name, ops, arg, perm, 4)
+
+#define fs_param_cb(name, ops, arg, perm)		\
+	__level_param_cb(name, ops, arg, perm, 5)
+
+#define device_param_cb(name, ops, arg, perm)		\
+	__level_param_cb(name, ops, arg, perm, 6)
+
+#define late_param_cb(name, ops, arg, perm)		\
+	__level_param_cb(name, ops, arg, perm, 7)
 
 /* On alpha, ia64 and ppc64 relocations to global data cannot go into
    read-only sections (which is part of respective UNIX ABI on these
@@ -146,7 +175,7 @@ struct kparam_array
 
 /* This is the fundamental function for registering boot/module
    parameters. */
-#define __module_param_call(prefix, name, ops, arg, isbool, perm)	\
+#define __module_param_call(prefix, name, ops, arg, perm, level)	\
 	/* Default value instead of permissions? */			\
 	static int __param_perm_check_##name __attribute__((unused)) =	\
 	BUILD_BUG_ON_ZERO((perm) < 0 || (perm) > 0777 || ((perm) & 2))	\
@@ -155,8 +184,7 @@ struct kparam_array
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
     __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \
-	= { __param_str_##name, ops, perm, isbool ? KPARAM_ISBOOL : 0,	\
-	    { arg } }
+	= { __param_str_##name, ops, perm, level, { arg } }
 
 /* Obsolete - use module_param_cb() */
 #define module_param_call(name, set, get, arg, perm)			\
@@ -164,8 +192,7 @@ struct kparam_array
 		 { (void *)set, (void *)get };				\
 	__module_param_call(MODULE_PARAM_PREFIX,			\
 			    name, &__param_ops_##name, arg,		\
-			    __same_type(arg, bool *),			\
-			    (perm) + sizeof(__check_old_set_param(set))*0)
+			    (perm) + sizeof(__check_old_set_param(set))*0, 0)
 
 /* We don't get oldget: it's often a new-style param_get_uint, etc. */
 static inline int
@@ -245,8 +272,7 @@ static inline void __kernel_param_unlock(void)
  */
 #define core_param(name, var, type, perm)				\
 	param_check_##type(name, &(var));				\
-	__module_param_call("", name, &param_ops_##type,		\
-			    &var, __same_type(var, bool), perm)
+	__module_param_call("", name, &param_ops_##type, &var, perm, 0)
 #endif /* !MODULE */
 
 /**
@@ -264,7 +290,7 @@ static inline void __kernel_param_unlock(void)
 		= { len, string };					\
 	__module_param_call(MODULE_PARAM_PREFIX, name,			\
 			    &param_ops_string,				\
-			    .str = &__param_string_##name, 0, perm);	\
+			    .str = &__param_string_##name, perm, 0);	\
 	__MODULE_PARM_TYPE(name, "string")
 
 /**
@@ -292,6 +318,8 @@ extern int parse_args(const char *name,
 		      char *args,
 		      const struct kernel_param *params,
 		      unsigned num,
+		      s16 level_min,
+		      s16 level_max,
 		      int (*unknown)(char *param, char *val));
 
 /* Called by module remove. */
@@ -403,7 +431,7 @@ extern int param_set_bint(const char *val, const struct kernel_param *kp);
 	__module_param_call(MODULE_PARAM_PREFIX, name,			\
 			    &param_array_ops,				\
 			    .arr = &__param_arr_##name,			\
-			    __same_type(array[0], bool), perm);		\
+			    perm, 0);					\
 	__MODULE_PARM_TYPE(name, "array of " #type)
 
 extern struct kernel_param_ops param_array_ops;
diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h
index c4eec228eef9..650ef352f045 100644
--- a/include/linux/mtd/bbm.h
+++ b/include/linux/mtd/bbm.h
@@ -112,6 +112,11 @@ struct nand_bbt_descr {
 #define NAND_BBT_USE_FLASH	0x00020000
 /* Do not store flash based bad block table in OOB area; store it in-band */
 #define NAND_BBT_NO_OOB		0x00040000
+/*
+ * Do not write new bad block markers to OOB; useful, e.g., when ECC covers
+ * entire spare area. Must be used with NAND_BBT_USE_FLASH.
+ */
+#define NAND_BBT_NO_OOB_BBM	0x00080000
 
 /*
  * Flag set by nand_create_default_bbt_descr(), marking that the nand_bbt_descr
diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h
index 1bbd9f289245..ed270bd2e4df 100644
--- a/include/linux/mtd/blktrans.h
+++ b/include/linux/mtd/blktrans.h
@@ -47,6 +47,7 @@ struct mtd_blktrans_dev {
 	struct request_queue *rq;
 	spinlock_t queue_lock;
 	void *priv;
+	fmode_t file_mode;
 };
 
 struct mtd_blktrans_ops {
diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h
index 6987995ad3cf..b20029221fb1 100644
--- a/include/linux/mtd/fsmc.h
+++ b/include/linux/mtd/fsmc.h
@@ -26,95 +26,83 @@
 #define FSMC_NAND_BW8		1
 #define FSMC_NAND_BW16		2
 
-/*
- * The placement of the Command Latch Enable (CLE) and
- * Address Latch Enable (ALE) is twisted around in the
- * SPEAR310 implementation.
- */
-#if defined(CONFIG_MACH_SPEAR310)
-#define PLAT_NAND_CLE		(1 << 17)
-#define PLAT_NAND_ALE		(1 << 16)
-#else
-#define PLAT_NAND_CLE		(1 << 16)
-#define PLAT_NAND_ALE		(1 << 17)
-#endif
-
 #define FSMC_MAX_NOR_BANKS	4
 #define FSMC_MAX_NAND_BANKS	4
 
 #define FSMC_FLASH_WIDTH8	1
 #define FSMC_FLASH_WIDTH16	2
 
-struct fsmc_nor_bank_regs {
-	uint32_t ctrl;
-	uint32_t ctrl_tim;
-};
-
-/* ctrl register definitions */
-#define BANK_ENABLE		(1 << 0)
-#define MUXED			(1 << 1)
-#define NOR_DEV			(2 << 2)
-#define WIDTH_8			(0 << 4)
-#define WIDTH_16		(1 << 4)
-#define RSTPWRDWN		(1 << 6)
-#define WPROT			(1 << 7)
-#define WRT_ENABLE		(1 << 12)
-#define WAIT_ENB		(1 << 13)
-
-/* ctrl_tim register definitions */
-
-struct fsmc_nand_bank_regs {
-	uint32_t pc;
-	uint32_t sts;
-	uint32_t comm;
-	uint32_t attrib;
-	uint32_t ioata;
-	uint32_t ecc1;
-	uint32_t ecc2;
-	uint32_t ecc3;
-};
-
+/* fsmc controller registers for NOR flash */
+#define CTRL			0x0
+	/* ctrl register definitions */
+	#define BANK_ENABLE		(1 << 0)
+	#define MUXED			(1 << 1)
+	#define NOR_DEV			(2 << 2)
+	#define WIDTH_8			(0 << 4)
+	#define WIDTH_16		(1 << 4)
+	#define RSTPWRDWN		(1 << 6)
+	#define WPROT			(1 << 7)
+	#define WRT_ENABLE		(1 << 12)
+	#define WAIT_ENB		(1 << 13)
+
+#define CTRL_TIM		0x4
+	/* ctrl_tim register definitions */
+
+#define FSMC_NOR_BANK_SZ	0x8
 #define FSMC_NOR_REG_SIZE	0x40
 
-struct fsmc_regs {
-	struct fsmc_nor_bank_regs nor_bank_regs[FSMC_MAX_NOR_BANKS];
-	uint8_t reserved_1[0x40 - 0x20];
-	struct fsmc_nand_bank_regs bank_regs[FSMC_MAX_NAND_BANKS];
-	uint8_t reserved_2[0xfe0 - 0xc0];
-	uint32_t peripid0;			/* 0xfe0 */
-	uint32_t peripid1;			/* 0xfe4 */
-	uint32_t peripid2;			/* 0xfe8 */
-	uint32_t peripid3;			/* 0xfec */
-	uint32_t pcellid0;			/* 0xff0 */
-	uint32_t pcellid1;			/* 0xff4 */
-	uint32_t pcellid2;			/* 0xff8 */
-	uint32_t pcellid3;			/* 0xffc */
-};
+#define FSMC_NOR_REG(base, bank, reg)		(base + \
+						FSMC_NOR_BANK_SZ * (bank) + \
+						reg)
+
+/* fsmc controller registers for NAND flash */
+#define PC			0x00
+	/* pc register definitions */
+	#define FSMC_RESET		(1 << 0)
+	#define FSMC_WAITON		(1 << 1)
+	#define FSMC_ENABLE		(1 << 2)
+	#define FSMC_DEVTYPE_NAND	(1 << 3)
+	#define FSMC_DEVWID_8		(0 << 4)
+	#define FSMC_DEVWID_16		(1 << 4)
+	#define FSMC_ECCEN		(1 << 6)
+	#define FSMC_ECCPLEN_512	(0 << 7)
+	#define FSMC_ECCPLEN_256	(1 << 7)
+	#define FSMC_TCLR_1		(1)
+	#define FSMC_TCLR_SHIFT		(9)
+	#define FSMC_TCLR_MASK		(0xF)
+	#define FSMC_TAR_1		(1)
+	#define FSMC_TAR_SHIFT		(13)
+	#define FSMC_TAR_MASK		(0xF)
+#define STS			0x04
+	/* sts register definitions */
+	#define FSMC_CODE_RDY		(1 << 15)
+#define COMM			0x08
+	/* comm register definitions */
+	#define FSMC_TSET_0		0
+	#define FSMC_TSET_SHIFT		0
+	#define FSMC_TSET_MASK		0xFF
+	#define FSMC_TWAIT_6		6
+	#define FSMC_TWAIT_SHIFT	8
+	#define FSMC_TWAIT_MASK		0xFF
+	#define FSMC_THOLD_4		4
+	#define FSMC_THOLD_SHIFT	16
+	#define FSMC_THOLD_MASK		0xFF
+	#define FSMC_THIZ_1		1
+	#define FSMC_THIZ_SHIFT		24
+	#define FSMC_THIZ_MASK		0xFF
+#define ATTRIB			0x0C
+#define IOATA			0x10
+#define ECC1			0x14
+#define ECC2			0x18
+#define ECC3			0x1C
+#define FSMC_NAND_BANK_SZ	0x20
+
+#define FSMC_NAND_REG(base, bank, reg)		(base + FSMC_NOR_REG_SIZE + \
+						(FSMC_NAND_BANK_SZ * (bank)) + \
+						reg)
 
 #define FSMC_BUSY_WAIT_TIMEOUT	(1 * HZ)
 
-/* pc register definitions */
-#define FSMC_RESET		(1 << 0)
-#define FSMC_WAITON		(1 << 1)
-#define FSMC_ENABLE		(1 << 2)
-#define FSMC_DEVTYPE_NAND	(1 << 3)
-#define FSMC_DEVWID_8		(0 << 4)
-#define FSMC_DEVWID_16		(1 << 4)
-#define FSMC_ECCEN		(1 << 6)
-#define FSMC_ECCPLEN_512	(0 << 7)
-#define FSMC_ECCPLEN_256	(1 << 7)
-#define FSMC_TCLR_1		(1 << 9)
-#define FSMC_TAR_1		(1 << 13)
-
-/* sts register definitions */
-#define FSMC_CODE_RDY		(1 << 15)
-
-/* comm register definitions */
-#define FSMC_TSET_0		(0 << 0)
-#define FSMC_TWAIT_6		(6 << 8)
-#define FSMC_THOLD_4		(4 << 16)
-#define FSMC_THIZ_1		(1 << 24)
-
 /*
  * There are 13 bytes of ecc for every 512 byte block in FSMC version 8
  * and it has to be read consecutively and immediately after the 512
@@ -133,6 +121,20 @@ struct fsmc_eccplace {
 	struct fsmc_nand_eccplace eccplace[MAX_ECCPLACE_ENTRIES];
 };
 
+struct fsmc_nand_timings {
+	uint8_t tclr;
+	uint8_t tar;
+	uint8_t thiz;
+	uint8_t thold;
+	uint8_t twait;
+	uint8_t tset;
+};
+
+enum access_mode {
+	USE_DMA_ACCESS = 1,
+	USE_WORD_ACCESS,
+};
+
 /**
  * fsmc_nand_platform_data - platform specific NAND controller config
  * @partitions: partition table for the platform, use a default fallback
@@ -146,12 +148,23 @@ struct fsmc_eccplace {
  * this may be set to NULL
  */
 struct fsmc_nand_platform_data {
+	struct fsmc_nand_timings *nand_timings;
 	struct mtd_partition	*partitions;
 	unsigned int		nr_partitions;
 	unsigned int		options;
 	unsigned int		width;
 	unsigned int		bank;
+
+	/* CLE, ALE offsets */
+	unsigned int		cle_off;
+	unsigned int		ale_off;
+	enum access_mode	mode;
+
 	void			(*select_bank)(uint32_t bank, uint32_t busw);
+
+	/* priv structures for dma accesses */
+	void			*read_dma_priv;
+	void			*write_dma_priv;
 };
 
 extern int __init fsmc_nor_init(struct platform_device *pdev,
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 94e924e2ecd5..3595a0236b0f 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -29,8 +29,8 @@
 #include <linux/kernel.h>
 
 #include <asm/unaligned.h>
-#include <asm/system.h>
 #include <asm/io.h>
+#include <asm/barrier.h>
 
 #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1
 #define map_bankwidth(map) 1
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index d43dc25af82e..cf5ea8cdcf8e 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -164,6 +164,9 @@ struct mtd_info {
 	/* ECC layout structure pointer - read only! */
 	struct nand_ecclayout *ecclayout;
 
+	/* max number of correctible bit errors per writesize */
+	unsigned int ecc_strength;
+
 	/* Data for variable erase regions. If numeraseregions is zero,
 	 * it means that the whole device has erasesize as given above.
 	 */
@@ -174,52 +177,52 @@ struct mtd_info {
 	 * Do not call via these pointers, use corresponding mtd_*()
 	 * wrappers instead.
 	 */
-	int (*erase) (struct mtd_info *mtd, struct erase_info *instr);
-	int (*point) (struct mtd_info *mtd, loff_t from, size_t len,
-		      size_t *retlen, void **virt, resource_size_t *phys);
-	void (*unpoint) (struct mtd_info *mtd, loff_t from, size_t len);
-	unsigned long (*get_unmapped_area) (struct mtd_info *mtd,
-					    unsigned long len,
-					    unsigned long offset,
-					    unsigned long flags);
-	int (*read) (struct mtd_info *mtd, loff_t from, size_t len,
-		     size_t *retlen, u_char *buf);
-	int (*write) (struct mtd_info *mtd, loff_t to, size_t len,
-		      size_t *retlen, const u_char *buf);
-	int (*panic_write) (struct mtd_info *mtd, loff_t to, size_t len,
-			    size_t *retlen, const u_char *buf);
-	int (*read_oob) (struct mtd_info *mtd, loff_t from,
-			 struct mtd_oob_ops *ops);
-	int (*write_oob) (struct mtd_info *mtd, loff_t to,
+	int (*_erase) (struct mtd_info *mtd, struct erase_info *instr);
+	int (*_point) (struct mtd_info *mtd, loff_t from, size_t len,
+		       size_t *retlen, void **virt, resource_size_t *phys);
+	int (*_unpoint) (struct mtd_info *mtd, loff_t from, size_t len);
+	unsigned long (*_get_unmapped_area) (struct mtd_info *mtd,
+					     unsigned long len,
+					     unsigned long offset,
+					     unsigned long flags);
+	int (*_read) (struct mtd_info *mtd, loff_t from, size_t len,
+		      size_t *retlen, u_char *buf);
+	int (*_write) (struct mtd_info *mtd, loff_t to, size_t len,
+		       size_t *retlen, const u_char *buf);
+	int (*_panic_write) (struct mtd_info *mtd, loff_t to, size_t len,
+			     size_t *retlen, const u_char *buf);
+	int (*_read_oob) (struct mtd_info *mtd, loff_t from,
 			  struct mtd_oob_ops *ops);
-	int (*get_fact_prot_info) (struct mtd_info *mtd, struct otp_info *buf,
-				   size_t len);
-	int (*read_fact_prot_reg) (struct mtd_info *mtd, loff_t from,
-				   size_t len, size_t *retlen, u_char *buf);
-	int (*get_user_prot_info) (struct mtd_info *mtd, struct otp_info *buf,
-				   size_t len);
-	int (*read_user_prot_reg) (struct mtd_info *mtd, loff_t from,
-				   size_t len, size_t *retlen, u_char *buf);
-	int (*write_user_prot_reg) (struct mtd_info *mtd, loff_t to, size_t len,
-				    size_t *retlen, u_char *buf);
-	int (*lock_user_prot_reg) (struct mtd_info *mtd, loff_t from,
-				   size_t len);
-	int (*writev) (struct mtd_info *mtd, const struct kvec *vecs,
+	int (*_write_oob) (struct mtd_info *mtd, loff_t to,
+			   struct mtd_oob_ops *ops);
+	int (*_get_fact_prot_info) (struct mtd_info *mtd, struct otp_info *buf,
+				    size_t len);
+	int (*_read_fact_prot_reg) (struct mtd_info *mtd, loff_t from,
+				    size_t len, size_t *retlen, u_char *buf);
+	int (*_get_user_prot_info) (struct mtd_info *mtd, struct otp_info *buf,
+				    size_t len);
+	int (*_read_user_prot_reg) (struct mtd_info *mtd, loff_t from,
+				    size_t len, size_t *retlen, u_char *buf);
+	int (*_write_user_prot_reg) (struct mtd_info *mtd, loff_t to,
+				     size_t len, size_t *retlen, u_char *buf);
+	int (*_lock_user_prot_reg) (struct mtd_info *mtd, loff_t from,
+				    size_t len);
+	int (*_writev) (struct mtd_info *mtd, const struct kvec *vecs,
 			unsigned long count, loff_t to, size_t *retlen);
-	void (*sync) (struct mtd_info *mtd);
-	int (*lock) (struct mtd_info *mtd, loff_t ofs, uint64_t len);
-	int (*unlock) (struct mtd_info *mtd, loff_t ofs, uint64_t len);
-	int (*is_locked) (struct mtd_info *mtd, loff_t ofs, uint64_t len);
-	int (*block_isbad) (struct mtd_info *mtd, loff_t ofs);
-	int (*block_markbad) (struct mtd_info *mtd, loff_t ofs);
-	int (*suspend) (struct mtd_info *mtd);
-	void (*resume) (struct mtd_info *mtd);
+	void (*_sync) (struct mtd_info *mtd);
+	int (*_lock) (struct mtd_info *mtd, loff_t ofs, uint64_t len);
+	int (*_unlock) (struct mtd_info *mtd, loff_t ofs, uint64_t len);
+	int (*_is_locked) (struct mtd_info *mtd, loff_t ofs, uint64_t len);
+	int (*_block_isbad) (struct mtd_info *mtd, loff_t ofs);
+	int (*_block_markbad) (struct mtd_info *mtd, loff_t ofs);
+	int (*_suspend) (struct mtd_info *mtd);
+	void (*_resume) (struct mtd_info *mtd);
 	/*
 	 * If the driver is something smart, like UBI, it may need to maintain
 	 * its own reference counting. The below functions are only for driver.
 	 */
-	int (*get_device) (struct mtd_info *mtd);
-	void (*put_device) (struct mtd_info *mtd);
+	int (*_get_device) (struct mtd_info *mtd);
+	void (*_put_device) (struct mtd_info *mtd);
 
 	/* Backing device capabilities for this device
 	 * - provides mmap capabilities
@@ -240,214 +243,75 @@ struct mtd_info {
 	int usecount;
 };
 
-/*
- * Erase is an asynchronous operation.  Device drivers are supposed
- * to call instr->callback() whenever the operation completes, even
- * if it completes with a failure.
- * Callers are supposed to pass a callback function and wait for it
- * to be called before writing to the block.
- */
-static inline int mtd_erase(struct mtd_info *mtd, struct erase_info *instr)
-{
-	return mtd->erase(mtd, instr);
-}
-
-/*
- * This stuff for eXecute-In-Place. phys is optional and may be set to NULL.
- */
-static inline int mtd_point(struct mtd_info *mtd, loff_t from, size_t len,
-			    size_t *retlen, void **virt, resource_size_t *phys)
-{
-	*retlen = 0;
-	if (!mtd->point)
-		return -EOPNOTSUPP;
-	return mtd->point(mtd, from, len, retlen, virt, phys);
-}
-
-/* We probably shouldn't allow XIP if the unpoint isn't a NULL */
-static inline void mtd_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
-{
-	return mtd->unpoint(mtd, from, len);
-}
-
-/*
- * Allow NOMMU mmap() to directly map the device (if not NULL)
- * - return the address to which the offset maps
- * - return -ENOSYS to indicate refusal to do the mapping
- */
-static inline unsigned long mtd_get_unmapped_area(struct mtd_info *mtd,
-						  unsigned long len,
-						  unsigned long offset,
-						  unsigned long flags)
-{
-	if (!mtd->get_unmapped_area)
-		return -EOPNOTSUPP;
-	return mtd->get_unmapped_area(mtd, len, offset, flags);
-}
-
-static inline int mtd_read(struct mtd_info *mtd, loff_t from, size_t len,
-			   size_t *retlen, u_char *buf)
-{
-	return mtd->read(mtd, from, len, retlen, buf);
-}
-
-static inline int mtd_write(struct mtd_info *mtd, loff_t to, size_t len,
-			    size_t *retlen, const u_char *buf)
-{
-	*retlen = 0;
-	if (!mtd->write)
-		return -EROFS;
-	return mtd->write(mtd, to, len, retlen, buf);
-}
-
-/*
- * In blackbox flight recorder like scenarios we want to make successful writes
- * in interrupt context. panic_write() is only intended to be called when its
- * known the kernel is about to panic and we need the write to succeed. Since
- * the kernel is not going to be running for much longer, this function can
- * break locks and delay to ensure the write succeeds (but not sleep).
- */
-static inline int mtd_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
-				  size_t *retlen, const u_char *buf)
-{
-	*retlen = 0;
-	if (!mtd->panic_write)
-		return -EOPNOTSUPP;
-	return mtd->panic_write(mtd, to, len, retlen, buf);
-}
+int mtd_erase(struct mtd_info *mtd, struct erase_info *instr);
+int mtd_point(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
+	      void **virt, resource_size_t *phys);
+int mtd_unpoint(struct mtd_info *mtd, loff_t from, size_t len);
+unsigned long mtd_get_unmapped_area(struct mtd_info *mtd, unsigned long len,
+				    unsigned long offset, unsigned long flags);
+int mtd_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
+	     u_char *buf);
+int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
+	      const u_char *buf);
+int mtd_panic_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
+		    const u_char *buf);
 
 static inline int mtd_read_oob(struct mtd_info *mtd, loff_t from,
 			       struct mtd_oob_ops *ops)
 {
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->read_oob)
+	if (!mtd->_read_oob)
 		return -EOPNOTSUPP;
-	return mtd->read_oob(mtd, from, ops);
+	return mtd->_read_oob(mtd, from, ops);
 }
 
 static inline int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 				struct mtd_oob_ops *ops)
 {
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->write_oob)
-		return -EOPNOTSUPP;
-	return mtd->write_oob(mtd, to, ops);
-}
-
-/*
- * Method to access the protection register area, present in some flash
- * devices. The user data is one time programmable but the factory data is read
- * only.
- */
-static inline int mtd_get_fact_prot_info(struct mtd_info *mtd,
-					 struct otp_info *buf, size_t len)
-{
-	if (!mtd->get_fact_prot_info)
+	if (!mtd->_write_oob)
 		return -EOPNOTSUPP;
-	return mtd->get_fact_prot_info(mtd, buf, len);
-}
-
-static inline int mtd_read_fact_prot_reg(struct mtd_info *mtd, loff_t from,
-					 size_t len, size_t *retlen,
-					 u_char *buf)
-{
-	*retlen = 0;
-	if (!mtd->read_fact_prot_reg)
-		return -EOPNOTSUPP;
-	return mtd->read_fact_prot_reg(mtd, from, len, retlen, buf);
-}
-
-static inline int mtd_get_user_prot_info(struct mtd_info *mtd,
-					 struct otp_info *buf,
-					 size_t len)
-{
-	if (!mtd->get_user_prot_info)
-		return -EOPNOTSUPP;
-	return mtd->get_user_prot_info(mtd, buf, len);
-}
-
-static inline int mtd_read_user_prot_reg(struct mtd_info *mtd, loff_t from,
-					 size_t len, size_t *retlen,
-					 u_char *buf)
-{
-	*retlen = 0;
-	if (!mtd->read_user_prot_reg)
-		return -EOPNOTSUPP;
-	return mtd->read_user_prot_reg(mtd, from, len, retlen, buf);
-}
-
-static inline int mtd_write_user_prot_reg(struct mtd_info *mtd, loff_t to,
-					  size_t len, size_t *retlen,
-					  u_char *buf)
-{
-	*retlen = 0;
-	if (!mtd->write_user_prot_reg)
-		return -EOPNOTSUPP;
-	return mtd->write_user_prot_reg(mtd, to, len, retlen, buf);
+	if (!(mtd->flags & MTD_WRITEABLE))
+		return -EROFS;
+	return mtd->_write_oob(mtd, to, ops);
 }
 
-static inline int mtd_lock_user_prot_reg(struct mtd_info *mtd, loff_t from,
-					 size_t len)
-{
-	if (!mtd->lock_user_prot_reg)
-		return -EOPNOTSUPP;
-	return mtd->lock_user_prot_reg(mtd, from, len);
-}
+int mtd_get_fact_prot_info(struct mtd_info *mtd, struct otp_info *buf,
+			   size_t len);
+int mtd_read_fact_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
+			   size_t *retlen, u_char *buf);
+int mtd_get_user_prot_info(struct mtd_info *mtd, struct otp_info *buf,
+			   size_t len);
+int mtd_read_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
+			   size_t *retlen, u_char *buf);
+int mtd_write_user_prot_reg(struct mtd_info *mtd, loff_t to, size_t len,
+			    size_t *retlen, u_char *buf);
+int mtd_lock_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len);
 
 int mtd_writev(struct mtd_info *mtd, const struct kvec *vecs,
 	       unsigned long count, loff_t to, size_t *retlen);
 
 static inline void mtd_sync(struct mtd_info *mtd)
 {
-	if (mtd->sync)
-		mtd->sync(mtd);
-}
-
-/* Chip-supported device locking */
-static inline int mtd_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
-{
-	if (!mtd->lock)
-		return -EOPNOTSUPP;
-	return mtd->lock(mtd, ofs, len);
+	if (mtd->_sync)
+		mtd->_sync(mtd);
 }
 
-static inline int mtd_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
-{
-	if (!mtd->unlock)
-		return -EOPNOTSUPP;
-	return mtd->unlock(mtd, ofs, len);
-}
-
-static inline int mtd_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
-{
-	if (!mtd->is_locked)
-		return -EOPNOTSUPP;
-	return mtd->is_locked(mtd, ofs, len);
-}
+int mtd_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len);
+int mtd_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len);
+int mtd_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len);
+int mtd_block_isbad(struct mtd_info *mtd, loff_t ofs);
+int mtd_block_markbad(struct mtd_info *mtd, loff_t ofs);
 
 static inline int mtd_suspend(struct mtd_info *mtd)
 {
-	return mtd->suspend ? mtd->suspend(mtd) : 0;
+	return mtd->_suspend ? mtd->_suspend(mtd) : 0;
 }
 
 static inline void mtd_resume(struct mtd_info *mtd)
 {
-	if (mtd->resume)
-		mtd->resume(mtd);
-}
-
-static inline int mtd_block_isbad(struct mtd_info *mtd, loff_t ofs)
-{
-	if (!mtd->block_isbad)
-		return 0;
-	return mtd->block_isbad(mtd, ofs);
-}
-
-static inline int mtd_block_markbad(struct mtd_info *mtd, loff_t ofs)
-{
-	if (!mtd->block_markbad)
-		return -EOPNOTSUPP;
-	return mtd->block_markbad(mtd, ofs);
+	if (mtd->_resume)
+		mtd->_resume(mtd);
 }
 
 static inline uint32_t mtd_div_by_eb(uint64_t sz, struct mtd_info *mtd)
@@ -482,12 +346,12 @@ static inline uint32_t mtd_mod_by_ws(uint64_t sz, struct mtd_info *mtd)
 
 static inline int mtd_has_oob(const struct mtd_info *mtd)
 {
-	return mtd->read_oob && mtd->write_oob;
+	return mtd->_read_oob && mtd->_write_oob;
 }
 
 static inline int mtd_can_have_bb(const struct mtd_info *mtd)
 {
-	return !!mtd->block_isbad;
+	return !!mtd->_block_isbad;
 }
 
 	/* Kernel-side ioctl definitions */
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 63b5a8b6dfbd..1482340d3d9f 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -324,6 +324,7 @@ struct nand_hw_control {
  * @steps:	number of ECC steps per page
  * @size:	data bytes per ECC step
  * @bytes:	ECC bytes per step
+ * @strength:	max number of correctible bits per ECC step
  * @total:	total number of ECC bytes per page
  * @prepad:	padding information for syndrome based ECC generators
  * @postpad:	padding information for syndrome based ECC generators
@@ -351,6 +352,7 @@ struct nand_ecc_ctrl {
 	int size;
 	int bytes;
 	int total;
+	int strength;
 	int prepad;
 	int postpad;
 	struct nand_ecclayout	*layout;
@@ -448,8 +450,9 @@ struct nand_buffers {
  *			will be copied to the appropriate nand_bbt_descr's.
  * @badblockpos:	[INTERN] position of the bad block marker in the oob
  *			area.
- * @badblockbits:	[INTERN] number of bits to left-shift the bad block
- *			number
+ * @badblockbits:	[INTERN] minimum number of set bits in a good block's
+ *			bad block marker position; i.e., BBM == 11110111b is
+ *			not bad when badblockbits == 7
  * @cellinfo:		[INTERN] MLC/multichip data from chip ident
  * @numchips:		[INTERN] number of physical chips
  * @chipsize:		[INTERN] the size of one chip for multichip arrays
diff --git a/include/linux/mtd/pmc551.h b/include/linux/mtd/pmc551.h
deleted file mode 100644
index 27ad40aed19f..000000000000
--- a/include/linux/mtd/pmc551.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * PMC551 PCI Mezzanine Ram Device
- *
- * Author:
- *       Mark Ferrell
- *       Copyright 1999,2000 Nortel Networks
- *
- * License:
- *	 As part of this driver was derrived from the slram.c driver it falls
- *	 under the same license, which is GNU General Public License v2
- */
-
-#ifndef __MTD_PMC551_H__
-#define __MTD_PMC551_H__
-
-#include <linux/mtd/mtd.h>
-
-#define PMC551_VERSION \
-       "Ramix PMC551 PCI Mezzanine Ram Driver. (C) 1999,2000 Nortel Networks.\n"
-
-/*
- * Our personal and private information
- */
-struct mypriv {
-        struct pci_dev *dev;
-        u_char *start;
-        u32    base_map0;
-        u32    curr_map0;
-        u32    asize;
-	struct mtd_info *nextpmc551;
-};
-
-/*
- * Function Prototypes
- */
-static int pmc551_erase(struct mtd_info *, struct erase_info *);
-static void pmc551_unpoint(struct mtd_info *, loff_t, size_t);
-static int pmc551_point(struct mtd_info *mtd, loff_t from, size_t len,
-		size_t *retlen, void **virt, resource_size_t *phys);
-static int pmc551_read(struct mtd_info *, loff_t, size_t, size_t *, u_char *);
-static int pmc551_write(struct mtd_info *, loff_t, size_t, size_t *, const u_char *);
-
-
-/*
- * Define the PCI ID's if the kernel doesn't define them for us
- */
-#ifndef PCI_VENDOR_ID_V3_SEMI
-#define PCI_VENDOR_ID_V3_SEMI             0x11b0
-#endif
-
-#ifndef PCI_DEVICE_ID_V3_SEMI_V370PDC
-#define PCI_DEVICE_ID_V3_SEMI_V370PDC     0x0200
-#endif
-
-
-#define PMC551_PCI_MEM_MAP0	0x50
-#define PMC551_PCI_MEM_MAP1	0x54
-#define PMC551_PCI_MEM_MAP_MAP_ADDR_MASK	0x3ff00000
-#define PMC551_PCI_MEM_MAP_APERTURE_MASK	0x000000f0
-#define PMC551_PCI_MEM_MAP_REG_EN		0x00000002
-#define PMC551_PCI_MEM_MAP_ENABLE		0x00000001
-
-#define PMC551_SDRAM_MA		0x60
-#define PMC551_SDRAM_CMD	0x62
-#define PMC551_DRAM_CFG		0x64
-#define PMC551_SYS_CTRL_REG	0x78
-
-#define PMC551_DRAM_BLK0	0x68
-#define PMC551_DRAM_BLK1	0x6c
-#define PMC551_DRAM_BLK2	0x70
-#define PMC551_DRAM_BLK3	0x74
-#define PMC551_DRAM_BLK_GET_SIZE(x) (524288<<((x>>4)&0x0f))
-#define PMC551_DRAM_BLK_SET_COL_MUX(x,v) (((x) & ~0x00007000) | (((v) & 0x7) << 12))
-#define PMC551_DRAM_BLK_SET_ROW_MUX(x,v) (((x) & ~0x00000f00) | (((v) & 0xf) << 8))
-
-
-#endif /* __MTD_PMC551_H__ */
-
diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h
index 9cf4c4c79555..a38e1fa8af01 100644
--- a/include/linux/mtd/sh_flctl.h
+++ b/include/linux/mtd/sh_flctl.h
@@ -23,6 +23,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
+#include <linux/pm_qos.h>
 
 /* FLCTL registers */
 #define FLCMNCR(f)		(f->reg + 0x0)
@@ -38,6 +39,7 @@
 #define FLDTFIFO(f)		(f->reg + 0x24)
 #define FLECFIFO(f)		(f->reg + 0x28)
 #define FLTRCR(f)		(f->reg + 0x2C)
+#define FLHOLDCR(f)		(f->reg + 0x38)
 #define	FL4ECCRESULT0(f)	(f->reg + 0x80)
 #define	FL4ECCRESULT1(f)	(f->reg + 0x84)
 #define	FL4ECCRESULT2(f)	(f->reg + 0x88)
@@ -67,6 +69,30 @@
 #define	CE0_ENABLE	(0x1 << 3)	/* Chip Enable 0 */
 #define	TYPESEL_SET	(0x1 << 0)
 
+/*
+ * Clock settings using the PULSEx registers from FLCMNCR
+ *
+ * Some hardware uses bits called PULSEx instead of FCKSEL_E and QTSEL_E
+ * to control the clock divider used between the High-Speed Peripheral Clock
+ * and the FLCTL internal clock. If so, use CLK_8_BIT_xxx for connecting 8 bit
+ * and CLK_16_BIT_xxx for connecting 16 bit bus bandwith NAND chips. For the 16
+ * bit version the divider is seperate for the pulse width of high and low
+ * signals.
+ */
+#define PULSE3	(0x1 << 27)
+#define PULSE2	(0x1 << 17)
+#define PULSE1	(0x1 << 15)
+#define PULSE0	(0x1 << 9)
+#define CLK_8B_0_5			PULSE1
+#define CLK_8B_1			0x0
+#define CLK_8B_1_5			(PULSE1 | PULSE2)
+#define CLK_8B_2			PULSE0
+#define CLK_8B_3			(PULSE0 | PULSE1 | PULSE2)
+#define CLK_8B_4			(PULSE0 | PULSE2)
+#define CLK_16B_6L_2H			PULSE0
+#define CLK_16B_9L_3H			(PULSE0 | PULSE1 | PULSE2)
+#define CLK_16B_12L_4H			(PULSE0 | PULSE2)
+
 /* FLCMDCR control bits */
 #define ADRCNT2_E	(0x1 << 31)	/* 5byte address enable */
 #define ADRMD_E		(0x1 << 26)	/* Sector address access */
@@ -85,6 +111,15 @@
 #define TRSTRT		(0x1 << 0)	/* translation start */
 #define TREND		(0x1 << 1)	/* translation end */
 
+/*
+ * FLHOLDCR control bits
+ *
+ * HOLDEN: Bus Occupancy Enable (inverted)
+ * Enable this bit when the external bus might be used in between transfers.
+ * If not set and the bus gets used by other modules, a deadlock occurs.
+ */
+#define HOLDEN		(0x1 << 0)
+
 /* FL4ECCCR control bits */
 #define	_4ECCFA		(0x1 << 2)	/* 4 symbols correct fault */
 #define	_4ECCEND	(0x1 << 1)	/* 4 symbols end */
@@ -97,6 +132,7 @@ struct sh_flctl {
 	struct mtd_info		mtd;
 	struct nand_chip	chip;
 	struct platform_device	*pdev;
+	struct dev_pm_qos_request pm_qos;
 	void __iomem		*reg;
 
 	uint8_t	done_buff[2048 + 64];	/* max size 2048 + 64 */
@@ -108,11 +144,14 @@ struct sh_flctl {
 	int	erase1_page_addr;	/* page_addr in ERASE1 cmd */
 	uint32_t erase_ADRCNT;		/* bits of FLCMDCR in ERASE1 cmd */
 	uint32_t rw_ADRCNT;	/* bits of FLCMDCR in READ WRITE cmd */
+	uint32_t flcmncr_base;	/* base value of FLCMNCR */
 
 	int	hwecc_cant_correct[4];
 
 	unsigned page_size:1;	/* NAND page size (0 = 512, 1 = 2048) */
 	unsigned hwecc:1;	/* Hardware ECC (0 = disabled, 1 = enabled) */
+	unsigned holden:1;	/* Hardware has FLHOLDCR and HOLDEN is set */
+	unsigned qos_request:1;	/* QoS request to prevent deep power shutdown */
 };
 
 struct sh_flctl_platform_data {
@@ -121,6 +160,7 @@ struct sh_flctl_platform_data {
 	unsigned long		flcmncr_val;
 
 	unsigned has_hwecc:1;
+	unsigned use_holden:1;
 };
 
 static inline struct sh_flctl *mtd_to_flctl(struct mtd_info *mtdinfo)
diff --git a/include/linux/mtd/spear_smi.h b/include/linux/mtd/spear_smi.h
new file mode 100644
index 000000000000..8ae1726044c3
--- /dev/null
+++ b/include/linux/mtd/spear_smi.h
@@ -0,0 +1,65 @@
+/*
+ * Copyright © 2010 ST Microelectronics
+ * Shiraz Hashim <shiraz.hashim@st.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MTD_SPEAR_SMI_H
+#define __MTD_SPEAR_SMI_H
+
+#include <linux/types.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+
+/* max possible slots for serial-nor flash chip in the SMI controller */
+#define MAX_NUM_FLASH_CHIP	4
+
+/* macro to define partitions for flash devices */
+#define DEFINE_PARTS(n, of, s)		\
+{					\
+	.name = n,			\
+	.offset = of,			\
+	.size = s,			\
+}
+
+/**
+ * struct spear_smi_flash_info - platform structure for passing flash
+ * information
+ *
+ * name: name of the serial nor flash for identification
+ * mem_base: the memory base on which the flash is mapped
+ * size: size of the flash in bytes
+ * partitions: parition details
+ * nr_partitions: number of partitions
+ * fast_mode: whether flash supports fast mode
+ */
+
+struct spear_smi_flash_info {
+	char *name;
+	unsigned long mem_base;
+	unsigned long size;
+	struct mtd_partition *partitions;
+	int nr_partitions;
+	u8 fast_mode;
+};
+
+/**
+ * struct spear_smi_plat_data - platform structure for configuring smi
+ *
+ * clk_rate: clk rate at which SMI must operate
+ * num_flashes: number of flashes present on board
+ * board_flash_info: specific details of each flash present on board
+ */
+struct spear_smi_plat_data {
+	unsigned long clk_rate;
+	int num_flashes;
+	struct spear_smi_flash_info *board_flash_info;
+	struct device_node *np[MAX_NUM_FLASH_CHIP];
+};
+
+#endif /* __MTD_SPEAR_SMI_H */
diff --git a/include/linux/mtio.h b/include/linux/mtio.h
index 8f825756c459..18543e2db06f 100644
--- a/include/linux/mtio.h
+++ b/include/linux/mtio.h
@@ -194,6 +194,7 @@ struct	mtpos {
 #define MT_ST_SYSV              0x1000
 #define MT_ST_NOWAIT            0x2000
 #define MT_ST_SILI		0x4000
+#define MT_ST_NOWAIT_EOF	0x8000
 
 /* The mode parameters to be controlled. Parameter chosen with bits 20-28 */
 #define MT_ST_CLEAR_DEFAULT	0xfffff
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1f77540bdc95..5cbaa20f1659 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2604,8 +2604,6 @@ extern void		net_disable_timestamp(void);
 extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
 extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
 extern void dev_seq_stop(struct seq_file *seq, void *v);
-extern int dev_seq_open_ops(struct inode *inode, struct file *file,
-			    const struct seq_operations *ops);
 #endif
 
 extern int netdev_class_create_file(struct class_attribute *class_attr);
diff --git a/include/linux/netfilter/xt_set.h b/include/linux/netfilter/xt_set.h
index c0405ac92870..e3a9978f259f 100644
--- a/include/linux/netfilter/xt_set.h
+++ b/include/linux/netfilter/xt_set.h
@@ -58,8 +58,8 @@ struct xt_set_info_target_v1 {
 struct xt_set_info_target_v2 {
 	struct xt_set_info add_set;
 	struct xt_set_info del_set;
-	u32 flags;
-	u32 timeout;
+	__u32 flags;
+	__u32 timeout;
 };
 
 #endif /*_XT_SET_H*/
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 834df8bf08b6..0987146b0637 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -438,7 +438,20 @@ enum limit_by4 {
 enum open_delegation_type4 {
 	NFS4_OPEN_DELEGATE_NONE = 0,
 	NFS4_OPEN_DELEGATE_READ = 1,
-	NFS4_OPEN_DELEGATE_WRITE = 2
+	NFS4_OPEN_DELEGATE_WRITE = 2,
+	NFS4_OPEN_DELEGATE_NONE_EXT = 3, /* 4.1 */
+};
+
+enum why_no_delegation4 { /* new to v4.1 */
+	WND4_NOT_WANTED = 0,
+	WND4_CONTENTION = 1,
+	WND4_RESOURCE = 2,
+	WND4_NOT_SUPP_FTYPE = 3,
+	WND4_WRITE_DELEG_NOT_SUPP_FTYPE = 4,
+	WND4_NOT_SUPP_UPGRADE = 5,
+	WND4_NOT_SUPP_DOWNGRADE = 6,
+	WND4_CANCELLED = 7,
+	WND4_IS_DIR = 8,
 };
 
 enum lock_type4 {
diff --git a/include/linux/nfsd/cld.h b/include/linux/nfsd/cld.h
new file mode 100644
index 000000000000..f14a9ab06f1f
--- /dev/null
+++ b/include/linux/nfsd/cld.h
@@ -0,0 +1,56 @@
+/*
+ * Upcall description for nfsdcld communication
+ *
+ * Copyright (c) 2012 Red Hat, Inc.
+ * Author(s): Jeff Layton <jlayton@redhat.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _NFSD_CLD_H
+#define _NFSD_CLD_H
+
+/* latest upcall version available */
+#define CLD_UPCALL_VERSION 1
+
+/* defined by RFC3530 */
+#define NFS4_OPAQUE_LIMIT 1024
+
+enum cld_command {
+	Cld_Create,		/* create a record for this cm_id */
+	Cld_Remove,		/* remove record of this cm_id */
+	Cld_Check,		/* is this cm_id allowed? */
+	Cld_GraceDone,		/* grace period is complete */
+};
+
+/* representation of long-form NFSv4 client ID */
+struct cld_name {
+	uint16_t	cn_len;				/* length of cm_id */
+	unsigned char	cn_id[NFS4_OPAQUE_LIMIT];	/* client-provided */
+} __attribute__((packed));
+
+/* message struct for communication with userspace */
+struct cld_msg {
+	uint8_t		cm_vers;		/* upcall version */
+	uint8_t		cm_cmd;			/* upcall command */
+	int16_t		cm_status;		/* return code */
+	uint32_t	cm_xid;			/* transaction id */
+	union {
+		int64_t		cm_gracetime;	/* grace period start time */
+		struct cld_name	cm_name;
+	} __attribute__((packed)) cm_u;
+} __attribute__((packed));
+
+#endif /* !_NFSD_CLD_H */
diff --git a/include/linux/of.h b/include/linux/of.h
index d46a18ffbebb..fa7fb1d97458 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -58,9 +58,6 @@ struct device_node {
 	struct	kref kref;
 	unsigned long _flags;
 	void	*data;
-#if defined(CONFIG_EEH)
-	struct eeh_dev *edev;
-#endif
 #if defined(CONFIG_SPARC)
 	char	*path_component_name;
 	unsigned int unique_id;
@@ -75,13 +72,6 @@ struct of_phandle_args {
 	uint32_t args[MAX_PHANDLE_ARGS];
 };
 
-#if defined(CONFIG_EEH)
-static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn)
-{
-	return dn->edev;
-}
-#endif
-
 #ifdef CONFIG_OF_DYNAMIC
 extern struct device_node *of_node_get(struct device_node *node);
 extern void of_node_put(struct device_node *node);
@@ -361,6 +351,22 @@ static inline int of_machine_is_compatible(const char *compat)
 #define of_match_node(_matches, _node)	NULL
 #endif /* CONFIG_OF */
 
+/**
+ * of_property_read_bool - Findfrom a property
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node.
+ * Returns true if the property exist false otherwise.
+ */
+static inline bool of_property_read_bool(const struct device_node *np,
+					 const char *propname)
+{
+	struct property *prop = of_find_property(np, propname, NULL);
+
+	return prop ? true : false;
+}
+
 static inline int of_property_read_u32(const struct device_node *np,
 				       const char *propname,
 				       u32 *out_value)
diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h
index b254052a49d7..81733d12cbea 100644
--- a/include/linux/of_gpio.h
+++ b/include/linux/of_gpio.h
@@ -50,7 +50,8 @@ static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc)
 extern int of_get_named_gpio_flags(struct device_node *np,
 		const char *list_name, int index, enum of_gpio_flags *flags);
 
-extern unsigned int of_gpio_count(struct device_node *np);
+extern unsigned int of_gpio_named_count(struct device_node *np,
+					const char* propname);
 
 extern int of_mm_gpiochip_add(struct device_node *np,
 			      struct of_mm_gpio_chip *mm_gc);
@@ -71,7 +72,8 @@ static inline int of_get_named_gpio_flags(struct device_node *np,
 	return -ENOSYS;
 }
 
-static inline unsigned int of_gpio_count(struct device_node *np)
+static inline unsigned int of_gpio_named_count(struct device_node *np,
+					const char* propname)
 {
 	return 0;
 }
@@ -89,6 +91,27 @@ static inline void of_gpiochip_remove(struct gpio_chip *gc) { }
 #endif /* CONFIG_OF_GPIO */
 
 /**
+ * of_gpio_count - Count GPIOs for a device
+ * @np:		device node to count GPIOs for
+ *
+ * The function returns the count of GPIOs specified for a node.
+ *
+ * Note that the empty GPIO specifiers counts too. For example,
+ *
+ * gpios = <0
+ *          &pio1 1 2
+ *          0
+ *          &pio2 3 4>;
+ *
+ * defines four GPIOs (so this function will return 4), two of which
+ * are not specified.
+ */
+static inline unsigned int of_gpio_count(struct device_node *np)
+{
+	return of_gpio_named_count(np, "gpios");
+}
+
+/**
  * of_get_gpio_flags() - Get a GPIO number and flags to use with GPIO API
  * @np:		device node to get GPIO from
  * @index:	index of the GPIO
diff --git a/include/linux/of_mtd.h b/include/linux/of_mtd.h
new file mode 100644
index 000000000000..bae1b6094c63
--- /dev/null
+++ b/include/linux/of_mtd.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
+ *
+ * OF helpers for mtd.
+ *
+ * This file is released under the GPLv2
+ */
+
+#ifndef __LINUX_OF_MTD_H
+#define __LINUX_OF_NET_H
+
+#ifdef CONFIG_OF_MTD
+#include <linux/of.h>
+extern const int of_get_nand_ecc_mode(struct device_node *np);
+int of_get_nand_bus_width(struct device_node *np);
+bool of_get_nand_on_flash_bbt(struct device_node *np);
+#endif
+
+#endif /* __LINUX_OF_MTD_H */
diff --git a/include/linux/parport.h b/include/linux/parport.h
index 38a423ed3c01..106c2ca9440b 100644
--- a/include/linux/parport.h
+++ b/include/linux/parport.h
@@ -100,7 +100,6 @@ typedef enum {
 #include <linux/wait.h>
 #include <linux/irqreturn.h>
 #include <linux/semaphore.h>
-#include <asm/system.h>
 #include <asm/ptrace.h>
 
 /* Define this later. */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index bd9f55a5958d..ddbb6a901f65 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -299,18 +299,31 @@ struct perf_event_mmap_page {
 	/*
 	 * Bits needed to read the hw events in user-space.
 	 *
-	 *   u32 seq;
-	 *   s64 count;
+	 *   u32 seq, time_mult, time_shift, idx, width;
+	 *   u64 count, enabled, running;
+	 *   u64 cyc, time_offset;
+	 *   s64 pmc = 0;
 	 *
 	 *   do {
 	 *     seq = pc->lock;
-	 *
 	 *     barrier()
-	 *     if (pc->index) {
-	 *       count = pmc_read(pc->index - 1);
-	 *       count += pc->offset;
-	 *     } else
-	 *       goto regular_read;
+	 *
+	 *     enabled = pc->time_enabled;
+	 *     running = pc->time_running;
+	 *
+	 *     if (pc->cap_usr_time && enabled != running) {
+	 *       cyc = rdtsc();
+	 *       time_offset = pc->time_offset;
+	 *       time_mult   = pc->time_mult;
+	 *       time_shift  = pc->time_shift;
+	 *     }
+	 *
+	 *     idx = pc->index;
+	 *     count = pc->offset;
+	 *     if (pc->cap_usr_rdpmc && idx) {
+	 *       width = pc->pmc_width;
+	 *       pmc = rdpmc(idx - 1);
+	 *     }
 	 *
 	 *     barrier();
 	 *   } while (pc->lock != seq);
@@ -323,14 +336,57 @@ struct perf_event_mmap_page {
 	__s64	offset;			/* add to hardware event value */
 	__u64	time_enabled;		/* time event active */
 	__u64	time_running;		/* time event on cpu */
-	__u32	time_mult, time_shift;
+	union {
+		__u64	capabilities;
+		__u64	cap_usr_time  : 1,
+			cap_usr_rdpmc : 1,
+			cap_____res   : 62;
+	};
+
+	/*
+	 * If cap_usr_rdpmc this field provides the bit-width of the value
+	 * read using the rdpmc() or equivalent instruction. This can be used
+	 * to sign extend the result like:
+	 *
+	 *   pmc <<= 64 - width;
+	 *   pmc >>= 64 - width; // signed shift right
+	 *   count += pmc;
+	 */
+	__u16	pmc_width;
+
+	/*
+	 * If cap_usr_time the below fields can be used to compute the time
+	 * delta since time_enabled (in ns) using rdtsc or similar.
+	 *
+	 *   u64 quot, rem;
+	 *   u64 delta;
+	 *
+	 *   quot = (cyc >> time_shift);
+	 *   rem = cyc & ((1 << time_shift) - 1);
+	 *   delta = time_offset + quot * time_mult +
+	 *              ((rem * time_mult) >> time_shift);
+	 *
+	 * Where time_offset,time_mult,time_shift and cyc are read in the
+	 * seqcount loop described above. This delta can then be added to
+	 * enabled and possible running (if idx), improving the scaling:
+	 *
+	 *   enabled += delta;
+	 *   if (idx)
+	 *     running += delta;
+	 *
+	 *   quot = count / running;
+	 *   rem  = count % running;
+	 *   count = quot * enabled + (rem * enabled) / running;
+	 */
+	__u16	time_shift;
+	__u32	time_mult;
 	__u64	time_offset;
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u64	__reserved[121];	/* align to 1k */
+	__u64	__reserved[120];	/* align to 1k */
 
 	/*
 	 * Control data for the mmap() data buffer.
@@ -550,6 +606,7 @@ struct perf_guest_info_callbacks {
 #include <linux/irq_work.h>
 #include <linux/static_key.h>
 #include <linux/atomic.h>
+#include <linux/sysfs.h>
 #include <asm/local.h>
 
 #define PERF_MAX_STACK_DEPTH		255
@@ -1291,5 +1348,18 @@ do {									\
 	register_cpu_notifier(&fn##_nb);				\
 } while (0)
 
+
+#define PMU_FORMAT_ATTR(_name, _format)					\
+static ssize_t								\
+_name##_show(struct device *dev,					\
+			       struct device_attribute *attr,		\
+			       char *page)				\
+{									\
+	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);			\
+	return sprintf(page, _format "\n");				\
+}									\
+									\
+static struct device_attribute format_attr_##_name = __ATTR_RO(_name)
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index f5bd679be46b..b067bd8c49d0 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -33,6 +33,7 @@ struct pid_namespace {
 #endif
 	gid_t pid_gid;
 	int hide_pid;
+	int reboot;	/* group exit code if this pidns was rebooted */
 };
 
 extern struct pid_namespace init_pid_ns;
@@ -48,6 +49,7 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns);
 extern void free_pid_ns(struct kref *kref);
 extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
+extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd);
 
 static inline void put_pid_ns(struct pid_namespace *ns)
 {
@@ -75,11 +77,15 @@ static inline void put_pid_ns(struct pid_namespace *ns)
 {
 }
 
-
 static inline void zap_pid_ns_processes(struct pid_namespace *ns)
 {
 	BUG();
 }
+
+static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
+{
+	return 0;
+}
 #endif /* CONFIG_PID_NS */
 
 extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h
new file mode 100644
index 000000000000..b0f2c56a8ea2
--- /dev/null
+++ b/include/linux/platform_data/atmel.h
@@ -0,0 +1,27 @@
+/*
+ * atmel platform data
+ *
+ * GPL v2 Only
+ */
+
+#ifndef __ATMEL_H__
+#define __ATMEL_H__
+
+#include <linux/mtd/nand.h>
+
+ /* NAND / SmartMedia */
+struct atmel_nand_data {
+	int		enable_pin;		/* chip enable */
+	int		det_pin;		/* card detect */
+	int		rdy_pin;		/* ready/busy */
+	u8		rdy_pin_active_low;	/* rdy_pin value is inverted */
+	u8		ale;			/* address line number connected to ALE */
+	u8		cle;			/* address line number connected to CLE */
+	u8		bus_width_16;		/* buswidth is 16 bit */
+	u8		ecc_mode;		/* ecc mode */
+	u8		on_flash_bbt;		/* bbt on flash */
+	struct mtd_partition *parts;
+	unsigned int	num_parts;
+};
+
+#endif /* __ATMEL_H__ */
diff --git a/arch/arm/mach-zynq/include/mach/io.h b/include/linux/platform_data/spear_thermal.h
index 39d9885e0e9a..724f2e1cbbcb 100644
--- a/arch/arm/mach-zynq/include/mach/io.h
+++ b/include/linux/platform_data/spear_thermal.h
@@ -1,6 +1,8 @@
-/* arch/arm/mach-zynq/include/mach/io.h
+/*
+ * SPEAr thermal driver platform data.
  *
- *  Copyright (C) 2011 Xilinx
+ * Copyright (C) 2011-2012 ST Microelectronics
+ * Author: Vincenzo Frascino <vincenzo.frascino@st.com>
  *
  * This software is licensed under the terms of the GNU General Public
  * License version 2, as published by the Free Software Foundation, and
@@ -10,24 +12,15 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
+ *
  */
+#ifndef SPEAR_THERMAL_H
+#define SPEAR_THERMAL_H
 
-#ifndef __MACH_IO_H__
-#define __MACH_IO_H__
-
-/* Allow IO space to be anywhere in the memory */
-
-#define IO_SPACE_LIMIT 0xffff
-
-/* IO address mapping macros, nothing special at this time but required */
-
-#ifdef __ASSEMBLER__
-#define IOMEM(x)		(x)
-#else
-#define IOMEM(x)		((void __force __iomem *)(x))
-#endif
-
-#define __io(a)			__typesafe_io(a)
-#define __mem_pci(a)		(a)
+/* SPEAr Thermal Sensor Platform Data */
+struct spear_thermal_pdata {
+	/* flags used to enable thermal sensor */
+	unsigned int thermal_flags;
+};
 
-#endif
+#endif /* SPEAR_THERMAL_H */
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 2e9191a712f3..233149cb19f4 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -8,6 +8,7 @@
 #include <linux/notifier.h>
 #include <linux/miscdevice.h>
 #include <linux/device.h>
+#include <linux/workqueue.h>
 
 enum {
 	PM_QOS_RESERVED = 0,
@@ -29,6 +30,7 @@ enum {
 struct pm_qos_request {
 	struct plist_node node;
 	int pm_qos_class;
+	struct delayed_work work; /* for pm_qos_update_request_timeout */
 };
 
 struct dev_pm_qos_request {
@@ -73,6 +75,8 @@ void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class,
 			s32 value);
 void pm_qos_update_request(struct pm_qos_request *req,
 			   s32 new_value);
+void pm_qos_update_request_timeout(struct pm_qos_request *req,
+				   s32 new_value, unsigned long timeout_us);
 void pm_qos_remove_request(struct pm_qos_request *req);
 
 int pm_qos_request(int pm_qos_class);
diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h
index fe99211fb2b8..e01b167e66f0 100644
--- a/include/linux/power/max17042_battery.h
+++ b/include/linux/power/max17042_battery.h
@@ -27,6 +27,8 @@
 #define MAX17042_BATTERY_FULL	(100)
 #define MAX17042_DEFAULT_SNS_RESISTOR	(10000)
 
+#define MAX17042_CHARACTERIZATION_DATA_SIZE 48
+
 enum max17042_register {
 	MAX17042_STATUS		= 0x00,
 	MAX17042_VALRT_Th	= 0x01,
@@ -40,11 +42,11 @@ enum max17042_register {
 	MAX17042_VCELL		= 0x09,
 	MAX17042_Current	= 0x0A,
 	MAX17042_AvgCurrent	= 0x0B,
-	MAX17042_Qresidual	= 0x0C,
+
 	MAX17042_SOC		= 0x0D,
 	MAX17042_AvSOC		= 0x0E,
 	MAX17042_RemCap		= 0x0F,
-	MAX17402_FullCAP	= 0x10,
+	MAX17042_FullCAP	= 0x10,
 	MAX17042_TTE		= 0x11,
 	MAX17042_V_empty	= 0x12,
 
@@ -62,14 +64,14 @@ enum max17042_register {
 	MAX17042_AvCap		= 0x1F,
 	MAX17042_ManName	= 0x20,
 	MAX17042_DevName	= 0x21,
-	MAX17042_DevChem	= 0x22,
 
+	MAX17042_FullCAPNom	= 0x23,
 	MAX17042_TempNom	= 0x24,
-	MAX17042_TempCold	= 0x25,
+	MAX17042_TempLim	= 0x25,
 	MAX17042_TempHot	= 0x26,
 	MAX17042_AIN		= 0x27,
 	MAX17042_LearnCFG	= 0x28,
-	MAX17042_SHFTCFG	= 0x29,
+	MAX17042_FilterCFG	= 0x29,
 	MAX17042_RelaxCFG	= 0x2A,
 	MAX17042_MiscCFG	= 0x2B,
 	MAX17042_TGAIN		= 0x2C,
@@ -77,22 +79,41 @@ enum max17042_register {
 	MAX17042_CGAIN		= 0x2E,
 	MAX17042_COFF		= 0x2F,
 
-	MAX17042_Q_empty	= 0x33,
+	MAX17042_MaskSOC	= 0x32,
+	MAX17042_SOC_empty	= 0x33,
 	MAX17042_T_empty	= 0x34,
 
+	MAX17042_FullCAP0       = 0x35,
+	MAX17042_LAvg_empty	= 0x36,
+	MAX17042_FCTC		= 0x37,
 	MAX17042_RCOMP0		= 0x38,
 	MAX17042_TempCo		= 0x39,
-	MAX17042_Rx		= 0x3A,
-	MAX17042_T_empty0	= 0x3B,
+	MAX17042_EmptyTempCo	= 0x3A,
+	MAX17042_K_empty0	= 0x3B,
 	MAX17042_TaskPeriod	= 0x3C,
 	MAX17042_FSTAT		= 0x3D,
 
 	MAX17042_SHDNTIMER	= 0x3F,
 
-	MAX17042_VFRemCap	= 0x4A,
+	MAX17042_dQacc		= 0x45,
+	MAX17042_dPacc		= 0x46,
+
+	MAX17042_VFSOC0		= 0x48,
 
 	MAX17042_QH		= 0x4D,
 	MAX17042_QL		= 0x4E,
+
+	MAX17042_VFSOC0Enable	= 0x60,
+	MAX17042_MLOCKReg1	= 0x62,
+	MAX17042_MLOCKReg2	= 0x63,
+
+	MAX17042_MODELChrTbl	= 0x80,
+
+	MAX17042_OCV		= 0xEE,
+
+	MAX17042_OCVInternal	= 0xFB,
+
+	MAX17042_VFSOC		= 0xFF,
 };
 
 /*
@@ -105,10 +126,64 @@ struct max17042_reg_data {
 	u16 data;
 };
 
+struct max17042_config_data {
+	/* External current sense resistor value in milli-ohms */
+	u32	cur_sense_val;
+
+	/* A/D measurement */
+	u16	tgain;		/* 0x2C */
+	u16	toff;		/* 0x2D */
+	u16	cgain;		/* 0x2E */
+	u16	coff;		/* 0x2F */
+
+	/* Alert / Status */
+	u16	valrt_thresh;	/* 0x01 */
+	u16	talrt_thresh;	/* 0x02 */
+	u16	soc_alrt_thresh;	/* 0x03 */
+	u16	config;		/* 0x01D */
+	u16	shdntimer;	/* 0x03F */
+
+	/* App data */
+	u16	design_cap;	/* 0x18 */
+	u16	ichgt_term;	/* 0x1E */
+
+	/* MG3 config */
+	u16	at_rate;	/* 0x04 */
+	u16	learn_cfg;	/* 0x28 */
+	u16	filter_cfg;	/* 0x29 */
+	u16	relax_cfg;	/* 0x2A */
+	u16	misc_cfg;	/* 0x2B */
+	u16	masksoc;	/* 0x32 */
+
+	/* MG3 save and restore */
+	u16	fullcap;	/* 0x10 */
+	u16	fullcapnom;	/* 0x23 */
+	u16	socempty;	/* 0x33 */
+	u16	lavg_empty;	/* 0x36 */
+	u16	dqacc;		/* 0x45 */
+	u16	dpacc;		/* 0x46 */
+
+	/* Cell technology from power_supply.h */
+	u16	cell_technology;
+
+	/* Cell Data */
+	u16	vempty;		/* 0x12 */
+	u16	temp_nom;	/* 0x24 */
+	u16	temp_lim;	/* 0x25 */
+	u16	fctc;		/* 0x37 */
+	u16	rcomp0;		/* 0x38 */
+	u16	tcompc0;	/* 0x39 */
+	u16	empty_tempco;	/* 0x3A */
+	u16	kempty0;	/* 0x3B */
+	u16	cell_char_tbl[MAX17042_CHARACTERIZATION_DATA_SIZE];
+} __packed;
+
 struct max17042_platform_data {
 	struct max17042_reg_data *init_data;
+	struct max17042_config_data *config_data;
 	int num_init_data; /* Number of enties in init_data array */
 	bool enable_current_sense;
+	bool enable_por_init; /* Use POR init from Maxim appnote */
 
 	/*
 	 * R_sns in micro-ohms.
diff --git a/include/linux/power/smb347-charger.h b/include/linux/power/smb347-charger.h
new file mode 100644
index 000000000000..b3cb20dab55f
--- /dev/null
+++ b/include/linux/power/smb347-charger.h
@@ -0,0 +1,117 @@
+/*
+ * Summit Microelectronics SMB347 Battery Charger Driver
+ *
+ * Copyright (C) 2011, Intel Corporation
+ *
+ * Authors: Bruce E. Robertson <bruce.e.robertson@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SMB347_CHARGER_H
+#define SMB347_CHARGER_H
+
+#include <linux/types.h>
+#include <linux/power_supply.h>
+
+enum {
+	/* use the default compensation method */
+	SMB347_SOFT_TEMP_COMPENSATE_DEFAULT = -1,
+
+	SMB347_SOFT_TEMP_COMPENSATE_NONE,
+	SMB347_SOFT_TEMP_COMPENSATE_CURRENT,
+	SMB347_SOFT_TEMP_COMPENSATE_VOLTAGE,
+};
+
+/* Use default factory programmed value for hard/soft temperature limit */
+#define SMB347_TEMP_USE_DEFAULT		-273
+
+/*
+ * Charging enable can be controlled by software (via i2c) by
+ * smb347-charger driver or by EN pin (active low/high).
+ */
+enum smb347_chg_enable {
+	SMB347_CHG_ENABLE_SW,
+	SMB347_CHG_ENABLE_PIN_ACTIVE_LOW,
+	SMB347_CHG_ENABLE_PIN_ACTIVE_HIGH,
+};
+
+/**
+ * struct smb347_charger_platform_data - platform data for SMB347 charger
+ * @battery_info: Information about the battery
+ * @max_charge_current: maximum current (in uA) the battery can be charged
+ * @max_charge_voltage: maximum voltage (in uV) the battery can be charged
+ * @pre_charge_current: current (in uA) to use in pre-charging phase
+ * @termination_current: current (in uA) used to determine when the
+ *			 charging cycle terminates
+ * @pre_to_fast_voltage: voltage (in uV) treshold used for transitioning to
+ *			 pre-charge to fast charge mode
+ * @mains_current_limit: maximum input current drawn from AC/DC input (in uA)
+ * @usb_hc_current_limit: maximum input high current (in uA) drawn from USB
+ *			  input
+ * @chip_temp_threshold: die temperature where device starts limiting charge
+ *			 current [%100 - %130] (in degree C)
+ * @soft_cold_temp_limit: soft cold temperature limit [%0 - %15] (in degree C),
+ *			  granularity is 5 deg C.
+ * @soft_hot_temp_limit: soft hot temperature limit [%40 - %55] (in degree  C),
+ *			 granularity is 5 deg C.
+ * @hard_cold_temp_limit: hard cold temperature limit [%-5 - %10] (in degree C),
+ *			  granularity is 5 deg C.
+ * @hard_hot_temp_limit: hard hot temperature limit [%50 - %65] (in degree C),
+ *			 granularity is 5 deg C.
+ * @suspend_on_hard_temp_limit: suspend charging when hard limit is hit
+ * @soft_temp_limit_compensation: compensation method when soft temperature
+ *				  limit is hit
+ * @charge_current_compensation: current (in uA) for charging compensation
+ *				 current when temperature hits soft limits
+ * @use_mains: AC/DC input can be used
+ * @use_usb: USB input can be used
+ * @use_usb_otg: USB OTG output can be used (not implemented yet)
+ * @irq_gpio: GPIO number used for interrupts (%-1 if not used)
+ * @enable_control: how charging enable/disable is controlled
+ *		    (driver/pin controls)
+ *
+ * @use_main, @use_usb, and @use_usb_otg are means to enable/disable
+ * hardware support for these. This is useful when we want to have for
+ * example OTG charging controlled via OTG transceiver driver and not by
+ * the SMB347 hardware.
+ *
+ * Hard and soft temperature limit values are given as described in the
+ * device data sheet and assuming NTC beta value is %3750. Even if this is
+ * not the case, these values should be used. They can be mapped to the
+ * corresponding NTC beta values with the help of table %2 in the data
+ * sheet. So for example if NTC beta is %3375 and we want to program hard
+ * hot limit to be %53 deg C, @hard_hot_temp_limit should be set to %50.
+ *
+ * If zero value is given in any of the current and voltage values, the
+ * factory programmed default will be used. For soft/hard temperature
+ * values, pass in %SMB347_TEMP_USE_DEFAULT instead.
+ */
+struct smb347_charger_platform_data {
+	struct power_supply_info battery_info;
+	unsigned int	max_charge_current;
+	unsigned int	max_charge_voltage;
+	unsigned int	pre_charge_current;
+	unsigned int	termination_current;
+	unsigned int	pre_to_fast_voltage;
+	unsigned int	mains_current_limit;
+	unsigned int	usb_hc_current_limit;
+	unsigned int	chip_temp_threshold;
+	int		soft_cold_temp_limit;
+	int		soft_hot_temp_limit;
+	int		hard_cold_temp_limit;
+	int		hard_hot_temp_limit;
+	bool		suspend_on_hard_temp_limit;
+	unsigned int	soft_temp_limit_compensation;
+	unsigned int	charge_current_compensation;
+	bool		use_mains;
+	bool		use_usb;
+	bool		use_usb_otg;
+	int		irq_gpio;
+	enum smb347_chg_enable enable_control;
+};
+
+#endif /* SMB347_CHARGER_H */
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index e9a48234e693..0d04cd69ab9b 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -2,6 +2,7 @@
  * Copyright (C) 2001 Momchil Velikov
  * Portions Copyright (C) 2001 Christoph Hellwig
  * Copyright (C) 2006 Nick Piggin
+ * Copyright (C) 2012 Konstantin Khlebnikov
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -257,4 +258,199 @@ static inline void radix_tree_preload_end(void)
 	preempt_enable();
 }
 
+/**
+ * struct radix_tree_iter - radix tree iterator state
+ *
+ * @index:	index of current slot
+ * @next_index:	next-to-last index for this chunk
+ * @tags:	bit-mask for tag-iterating
+ *
+ * This radix tree iterator works in terms of "chunks" of slots.  A chunk is a
+ * subinterval of slots contained within one radix tree leaf node.  It is
+ * described by a pointer to its first slot and a struct radix_tree_iter
+ * which holds the chunk's position in the tree and its size.  For tagged
+ * iteration radix_tree_iter also holds the slots' bit-mask for one chosen
+ * radix tree tag.
+ */
+struct radix_tree_iter {
+	unsigned long	index;
+	unsigned long	next_index;
+	unsigned long	tags;
+};
+
+#define RADIX_TREE_ITER_TAG_MASK	0x00FF	/* tag index in lower byte */
+#define RADIX_TREE_ITER_TAGGED		0x0100	/* lookup tagged slots */
+#define RADIX_TREE_ITER_CONTIG		0x0200	/* stop at first hole */
+
+/**
+ * radix_tree_iter_init - initialize radix tree iterator
+ *
+ * @iter:	pointer to iterator state
+ * @start:	iteration starting index
+ * Returns:	NULL
+ */
+static __always_inline void **
+radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start)
+{
+	/*
+	 * Leave iter->tags uninitialized. radix_tree_next_chunk() will fill it
+	 * in the case of a successful tagged chunk lookup.  If the lookup was
+	 * unsuccessful or non-tagged then nobody cares about ->tags.
+	 *
+	 * Set index to zero to bypass next_index overflow protection.
+	 * See the comment in radix_tree_next_chunk() for details.
+	 */
+	iter->index = 0;
+	iter->next_index = start;
+	return NULL;
+}
+
+/**
+ * radix_tree_next_chunk - find next chunk of slots for iteration
+ *
+ * @root:	radix tree root
+ * @iter:	iterator state
+ * @flags:	RADIX_TREE_ITER_* flags and tag index
+ * Returns:	pointer to chunk first slot, or NULL if there no more left
+ *
+ * This function looks up the next chunk in the radix tree starting from
+ * @iter->next_index.  It returns a pointer to the chunk's first slot.
+ * Also it fills @iter with data about chunk: position in the tree (index),
+ * its end (next_index), and constructs a bit mask for tagged iterating (tags).
+ */
+void **radix_tree_next_chunk(struct radix_tree_root *root,
+			     struct radix_tree_iter *iter, unsigned flags);
+
+/**
+ * radix_tree_chunk_size - get current chunk size
+ *
+ * @iter:	pointer to radix tree iterator
+ * Returns:	current chunk size
+ */
+static __always_inline unsigned
+radix_tree_chunk_size(struct radix_tree_iter *iter)
+{
+	return iter->next_index - iter->index;
+}
+
+/**
+ * radix_tree_next_slot - find next slot in chunk
+ *
+ * @slot:	pointer to current slot
+ * @iter:	pointer to interator state
+ * @flags:	RADIX_TREE_ITER_*, should be constant
+ * Returns:	pointer to next slot, or NULL if there no more left
+ *
+ * This function updates @iter->index in the case of a successful lookup.
+ * For tagged lookup it also eats @iter->tags.
+ */
+static __always_inline void **
+radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags)
+{
+	if (flags & RADIX_TREE_ITER_TAGGED) {
+		iter->tags >>= 1;
+		if (likely(iter->tags & 1ul)) {
+			iter->index++;
+			return slot + 1;
+		}
+		if (!(flags & RADIX_TREE_ITER_CONTIG) && likely(iter->tags)) {
+			unsigned offset = __ffs(iter->tags);
+
+			iter->tags >>= offset;
+			iter->index += offset + 1;
+			return slot + offset + 1;
+		}
+	} else {
+		unsigned size = radix_tree_chunk_size(iter) - 1;
+
+		while (size--) {
+			slot++;
+			iter->index++;
+			if (likely(*slot))
+				return slot;
+			if (flags & RADIX_TREE_ITER_CONTIG)
+				break;
+		}
+	}
+	return NULL;
+}
+
+/**
+ * radix_tree_for_each_chunk - iterate over chunks
+ *
+ * @slot:	the void** variable for pointer to chunk first slot
+ * @root:	the struct radix_tree_root pointer
+ * @iter:	the struct radix_tree_iter pointer
+ * @start:	iteration starting index
+ * @flags:	RADIX_TREE_ITER_* and tag index
+ *
+ * Locks can be released and reacquired between iterations.
+ */
+#define radix_tree_for_each_chunk(slot, root, iter, start, flags)	\
+	for (slot = radix_tree_iter_init(iter, start) ;			\
+	      (slot = radix_tree_next_chunk(root, iter, flags)) ;)
+
+/**
+ * radix_tree_for_each_chunk_slot - iterate over slots in one chunk
+ *
+ * @slot:	the void** variable, at the beginning points to chunk first slot
+ * @iter:	the struct radix_tree_iter pointer
+ * @flags:	RADIX_TREE_ITER_*, should be constant
+ *
+ * This macro is designed to be nested inside radix_tree_for_each_chunk().
+ * @slot points to the radix tree slot, @iter->index contains its index.
+ */
+#define radix_tree_for_each_chunk_slot(slot, iter, flags)		\
+	for (; slot ; slot = radix_tree_next_slot(slot, iter, flags))
+
+/**
+ * radix_tree_for_each_slot - iterate over non-empty slots
+ *
+ * @slot:	the void** variable for pointer to slot
+ * @root:	the struct radix_tree_root pointer
+ * @iter:	the struct radix_tree_iter pointer
+ * @start:	iteration starting index
+ *
+ * @slot points to radix tree slot, @iter->index contains its index.
+ */
+#define radix_tree_for_each_slot(slot, root, iter, start)		\
+	for (slot = radix_tree_iter_init(iter, start) ;			\
+	     slot || (slot = radix_tree_next_chunk(root, iter, 0)) ;	\
+	     slot = radix_tree_next_slot(slot, iter, 0))
+
+/**
+ * radix_tree_for_each_contig - iterate over contiguous slots
+ *
+ * @slot:	the void** variable for pointer to slot
+ * @root:	the struct radix_tree_root pointer
+ * @iter:	the struct radix_tree_iter pointer
+ * @start:	iteration starting index
+ *
+ * @slot points to radix tree slot, @iter->index contains its index.
+ */
+#define radix_tree_for_each_contig(slot, root, iter, start)		\
+	for (slot = radix_tree_iter_init(iter, start) ;			\
+	     slot || (slot = radix_tree_next_chunk(root, iter,		\
+				RADIX_TREE_ITER_CONTIG)) ;		\
+	     slot = radix_tree_next_slot(slot, iter,			\
+				RADIX_TREE_ITER_CONTIG))
+
+/**
+ * radix_tree_for_each_tagged - iterate over tagged slots
+ *
+ * @slot:	the void** variable for pointer to slot
+ * @root:	the struct radix_tree_root pointer
+ * @iter:	the struct radix_tree_iter pointer
+ * @start:	iteration starting index
+ * @tag:	tag index
+ *
+ * @slot points to radix tree slot, @iter->index contains its index.
+ */
+#define radix_tree_for_each_tagged(slot, root, iter, start, tag)	\
+	for (slot = radix_tree_iter_init(iter, start) ;			\
+	     slot || (slot = radix_tree_next_chunk(root, iter,		\
+			      RADIX_TREE_ITER_TAGGED | tag)) ;		\
+	     slot = radix_tree_next_slot(slot, iter,			\
+				RADIX_TREE_ITER_TAGGED))
+
 #endif /* _LINUX_RADIX_TREE_H */
diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h
index 76579f964a29..7bd73bbdfd1b 100644
--- a/include/linux/regulator/ab8500.h
+++ b/include/linux/regulator/ab8500.h
@@ -26,7 +26,26 @@ enum ab8500_regulator_id {
 	AB8500_NUM_REGULATORS,
 };
 
-/* AB8500 register initialization */
+/* AB9450 regulators */
+enum ab9540_regulator_id {
+	AB9540_LDO_AUX1,
+	AB9540_LDO_AUX2,
+	AB9540_LDO_AUX3,
+	AB9540_LDO_AUX4,
+	AB9540_LDO_INTCORE,
+	AB9540_LDO_TVOUT,
+	AB9540_LDO_USB,
+	AB9540_LDO_AUDIO,
+	AB9540_LDO_ANAMIC1,
+	AB9540_LDO_ANAMIC2,
+	AB9540_LDO_DMIC,
+	AB9540_LDO_ANA,
+	AB9540_SYSCLKREQ_2,
+	AB9540_SYSCLKREQ_4,
+	AB9540_NUM_REGULATORS,
+};
+
+/* AB8500 and AB9540 register initialization */
 struct ab8500_regulator_reg_init {
 	int id;
 	u8 value;
@@ -71,4 +90,53 @@ enum ab8500_regulator_reg {
 	AB8500_NUM_REGULATOR_REGISTERS,
 };
 
+
+/* AB9540 registers */
+enum ab9540_regulator_reg {
+	AB9540_REGUREQUESTCTRL1,
+	AB9540_REGUREQUESTCTRL2,
+	AB9540_REGUREQUESTCTRL3,
+	AB9540_REGUREQUESTCTRL4,
+	AB9540_REGUSYSCLKREQ1HPVALID1,
+	AB9540_REGUSYSCLKREQ1HPVALID2,
+	AB9540_REGUHWHPREQ1VALID1,
+	AB9540_REGUHWHPREQ1VALID2,
+	AB9540_REGUHWHPREQ2VALID1,
+	AB9540_REGUHWHPREQ2VALID2,
+	AB9540_REGUSWHPREQVALID1,
+	AB9540_REGUSWHPREQVALID2,
+	AB9540_REGUSYSCLKREQVALID1,
+	AB9540_REGUSYSCLKREQVALID2,
+	AB9540_REGUVAUX4REQVALID,
+	AB9540_REGUMISC1,
+	AB9540_VAUDIOSUPPLY,
+	AB9540_REGUCTRL1VAMIC,
+	AB9540_VSMPS1REGU,
+	AB9540_VSMPS2REGU,
+	AB9540_VSMPS3REGU, /* NOTE! PRCMU register */
+	AB9540_VPLLVANAREGU,
+	AB9540_EXTSUPPLYREGU,
+	AB9540_VAUX12REGU,
+	AB9540_VRF1VAUX3REGU,
+	AB9540_VSMPS1SEL1,
+	AB9540_VSMPS1SEL2,
+	AB9540_VSMPS1SEL3,
+	AB9540_VSMPS2SEL1,
+	AB9540_VSMPS2SEL2,
+	AB9540_VSMPS2SEL3,
+	AB9540_VSMPS3SEL1, /* NOTE! PRCMU register */
+	AB9540_VSMPS3SEL2, /* NOTE! PRCMU register */
+	AB9540_VAUX1SEL,
+	AB9540_VAUX2SEL,
+	AB9540_VRF1VAUX3SEL,
+	AB9540_REGUCTRL2SPARE,
+	AB9540_VAUX4REQCTRL,
+	AB9540_VAUX4REGU,
+	AB9540_VAUX4SEL,
+	AB9540_REGUCTRLDISCH,
+	AB9540_REGUCTRLDISCH2,
+	AB9540_REGUCTRLDISCH3,
+	AB9540_NUM_REGULATOR_REGISTERS,
+};
+
 #endif
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 7abb16093312..b02108446be7 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -71,7 +71,7 @@ struct regulator_state {
  * @uV_offset: Offset applied to voltages from consumer to compensate for
  *             voltage drops.
  *
- * @min_uA: Smallest consumers consumers may set.
+ * @min_uA: Smallest current consumers may set.
  * @max_uA: Largest current consumers may set.
  *
  * @valid_modes_mask: Mask of modes which may be configured by consumers.
@@ -134,10 +134,8 @@ struct regulation_constraints {
 /**
  * struct regulator_consumer_supply - supply -> device mapping
  *
- * This maps a supply name to a device.  Only one of dev or dev_name
- * can be specified.  Use of dev_name allows support for buses which
- * make struct device available late such as I2C and is the preferred
- * form.
+ * This maps a supply name to a device. Use of dev_name allows support for
+ * buses which make struct device available late such as I2C.
  *
  * @dev_name: Result of dev_name() for the consumer.
  * @supply: Name for the supply.
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 67be0376d8e3..7be2e88f23fd 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -151,6 +151,9 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
 
 void ring_buffer_record_disable(struct ring_buffer *buffer);
 void ring_buffer_record_enable(struct ring_buffer *buffer);
+void ring_buffer_record_off(struct ring_buffer *buffer);
+void ring_buffer_record_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_on(struct ring_buffer *buffer);
 void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
 
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 93f4d035076b..fcabfb4873c8 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -202,7 +202,8 @@ struct rtc_device
 	struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */
 	int pie_enabled;
 	struct work_struct irqwork;
-
+	/* Some hardware can't support UIE mode */
+	int uie_unsupported;
 
 #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
 	struct work_struct uie_task;
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 63d406554391..54bd7cd7ecbd 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -14,7 +14,6 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 
 struct rw_semaphore;
diff --git a/include/linux/sa11x0-dma.h b/include/linux/sa11x0-dma.h
new file mode 100644
index 000000000000..65839a58b8e5
--- /dev/null
+++ b/include/linux/sa11x0-dma.h
@@ -0,0 +1,24 @@
+/*
+ * SA11x0 DMA Engine support
+ *
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_SA11X0_DMA_H
+#define __LINUX_SA11X0_DMA_H
+
+struct dma_chan;
+
+#if defined(CONFIG_DMA_SA11X0) || defined(CONFIG_DMA_SA11X0_MODULE)
+bool sa11x0_dma_filter_fn(struct dma_chan *, void *);
+#else
+static inline bool sa11x0_dma_filter_fn(struct dma_chan *c, void *d)
+{
+	return false;
+}
+#endif
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0c3854b0d4b1..81a173c0897d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -63,7 +63,6 @@ struct sched_param {
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include <asm/cputime.h>
diff --git a/include/linux/sh_intc.h b/include/linux/sh_intc.h
index b160645f5599..6aed0805927f 100644
--- a/include/linux/sh_intc.h
+++ b/include/linux/sh_intc.h
@@ -3,6 +3,23 @@
 
 #include <linux/ioport.h>
 
+#ifdef CONFIG_SUPERH
+#define INTC_NR_IRQS	512
+#else
+#define INTC_NR_IRQS	1024
+#endif
+
+/*
+ * Convert back and forth between INTEVT and IRQ values.
+ */
+#ifdef CONFIG_CPU_HAS_INTEVT
+#define evt2irq(evt)		(((evt) >> 5) - 16)
+#define irq2evt(irq)		(((irq) + 16) << 5)
+#else
+#define evt2irq(evt)		(evt)
+#define irq2evt(irq)		(irq)
+#endif
+
 typedef unsigned char intc_enum;
 
 struct intc_vect {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 192250bd49f5..33370271b8b2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -501,7 +501,6 @@ struct sk_buff {
  */
 #include <linux/slab.h>
 
-#include <asm/system.h>
 
 /*
  * skb might have a dst pointer attached, refcounted or not.
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 573c809c33d9..a595dce6b0c7 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -190,7 +190,7 @@ size_t ksize(const void *);
 #endif
 
 /**
- * kcalloc - allocate memory for an array. The memory is set to zero.
+ * kmalloc_array - allocate memory for an array.
  * @n: number of elements.
  * @size: element size.
  * @flags: the type of memory to allocate.
@@ -240,11 +240,22 @@ size_t ksize(const void *);
  * for general use, and so are not documented here. For a full list of
  * potential flags, always refer to linux/gfp.h.
  */
-static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
+static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
 {
 	if (size != 0 && n > ULONG_MAX / size)
 		return NULL;
-	return __kmalloc(n * size, flags | __GFP_ZERO);
+	return __kmalloc(n * size, flags);
+}
+
+/**
+ * kcalloc - allocate memory for an array. The memory is set to zero.
+ * @n: number of elements.
+ * @size: element size.
+ * @flags: the type of memory to allocate (see kmalloc).
+ */
+static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
+{
+	return kmalloc_array(n, size, flags | __GFP_ZERO);
 }
 
 #if !defined(CONFIG_NUMA) && !defined(CONFIG_SLOB)
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index ca122b36aec1..c2f8c8bc56ed 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -22,7 +22,7 @@ enum stat_item {
 	FREE_FROZEN,		/* Freeing to frozen slab */
 	FREE_ADD_PARTIAL,	/* Freeing moves slab to partial list */
 	FREE_REMOVE_PARTIAL,	/* Freeing removes last object */
-	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from partial list */
+	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from node partial list */
 	ALLOC_SLAB,		/* Cpu slab acquired from page allocator */
 	ALLOC_REFILL,		/* Refill cpu slab from slab freelist */
 	ALLOC_NODE_MISMATCH,	/* Switching cpu slab */
@@ -38,7 +38,9 @@ enum stat_item {
 	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
 	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
 	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
-	CPU_PARTIAL_FREE,	/* USed cpu partial on free */
+	CPU_PARTIAL_FREE,	/* Refill cpu partial on free */
+	CPU_PARTIAL_NODE,	/* Refill cpu partial from node partial */
+	CPU_PARTIAL_DRAIN,	/* Drain cpu partial to node partial */
 	NR_SLUB_STAT_ITEMS };
 
 struct kmem_cache_cpu {
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 8cc38d3bab0c..10530d92c04b 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -102,6 +102,22 @@ static inline void call_function_init(void) { }
 int on_each_cpu(smp_call_func_t func, void *info, int wait);
 
 /*
+ * Call a function on processors specified by mask, which might include
+ * the local one.
+ */
+void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
+		void *info, bool wait);
+
+/*
+ * Call a function on each processor for which the supplied function
+ * cond_func returns a positive value. This may include the local
+ * processor.
+ */
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+		smp_call_func_t func, void *info, bool wait,
+		gfp_t gfp_flags);
+
+/*
  * Mark the boot cpu "online" so that it can call console drivers in
  * printk() and can access its per-cpu storage.
  */
@@ -132,6 +148,36 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info)
 		local_irq_enable();		\
 		0;				\
 	})
+/*
+ * Note we still need to test the mask even for UP
+ * because we actually can get an empty mask from
+ * code that on SMP might call us without the local
+ * CPU in the mask.
+ */
+#define on_each_cpu_mask(mask, func, info, wait) \
+	do {						\
+		if (cpumask_test_cpu(0, (mask))) {	\
+			local_irq_disable();		\
+			(func)(info);			\
+			local_irq_enable();		\
+		}					\
+	} while (0)
+/*
+ * Preemption is disabled here to make sure the cond_func is called under the
+ * same condtions in UP and SMP.
+ */
+#define on_each_cpu_cond(cond_func, func, info, wait, gfp_flags)\
+	do {							\
+		void *__info = (info);				\
+		preempt_disable();				\
+		if ((cond_func)(0, __info)) {			\
+			local_irq_disable();			\
+			(func)(__info);				\
+			local_irq_enable();			\
+		}						\
+		preempt_enable();				\
+	} while (0)
+
 static inline void smp_send_reschedule(int cpu) { }
 #define num_booting_cpus()			1
 #define smp_prepare_boot_cpu()			do {} while (0)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index da2d3e2543f3..b84bbd48b874 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -265,7 +265,7 @@ struct ucred {
 #define MSG_NOSIGNAL	0x4000	/* Do not generate SIGPIPE */
 #define MSG_MORE	0x8000	/* Sender will send more */
 #define MSG_WAITFORONE	0x10000	/* recvmmsg(): block until 1+ packets avail */
-
+#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
 #define MSG_EOF         MSG_FIN
 
 #define MSG_CMSG_CLOEXEC 0x40000000	/* Set close_on_exit for file
diff --git a/include/linux/spi/orion_spi.h b/include/linux/spi/orion_spi.h
index decf6d8c77b7..b4d9fa6f797c 100644
--- a/include/linux/spi/orion_spi.h
+++ b/include/linux/spi/orion_spi.h
@@ -11,7 +11,6 @@
 
 struct orion_spi_info {
 	u32	tclk;		/* no <linux/clk.h> support yet */
-	u32	enable_clock_fix;
 };
 
 
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 363239087263..7d537ced949a 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -55,8 +55,8 @@
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/bottom_half.h>
+#include <asm/barrier.h>
 
-#include <asm/system.h>
 
 /*
  * Must define these before including other files, inline functions need them
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index e253ccd7a604..51df117abe46 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -67,7 +67,7 @@ _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
 #define _raw_spin_trylock_bh(lock) __raw_spin_trylock_bh(lock)
 #endif
 
-#ifdef CONFIG_INLINE_SPIN_UNLOCK
+#ifndef CONFIG_UNINLINE_SPIN_UNLOCK
 #define _raw_spin_unlock(lock) __raw_spin_unlock(lock)
 #endif
 
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index c170edc3bf5f..3b5e910d14ca 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -5,7 +5,6 @@
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 #include <linux/list.h>
-#include <asm/system.h>
 
 /*
  * stop_cpu[s]() is simplistic per-cpu maximum priority cpu
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index c14fe86dac59..0b8e3e6bdacf 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -190,7 +190,7 @@ extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
 extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int);
 extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int);
 extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int,
-					    u32, u64, u32);
+					    __be32, __be64, u32);
 extern void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *,
 					     struct rpcrdma_msg *,
 					     struct rpcrdma_msg *,
@@ -292,7 +292,7 @@ svc_rdma_get_reply_array(struct rpcrdma_msg *rmsgp)
 	if (wr_ary) {
 		rp_ary = (struct rpcrdma_write_array *)
 			&wr_ary->
-			wc_array[wr_ary->wc_nchunks].wc_target.rs_length;
+			wc_array[ntohl(wr_ary->wc_nchunks)].wc_target.rs_length;
 
 		goto found_it;
 	}
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b86b5c20617d..b1fd5c7925fe 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -21,6 +21,9 @@ struct bio;
 #define SWAP_FLAG_PRIO_SHIFT	0
 #define SWAP_FLAG_DISCARD	0x10000 /* discard swap cluster after use */
 
+#define SWAP_FLAGS_VALID	(SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \
+				 SWAP_FLAG_DISCARD)
+
 static inline int current_is_kswapd(void)
 {
 	return current->flags & PF_KSWAPD;
@@ -302,6 +305,13 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 	return vm_swappiness;
 }
 #endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
+#else
+static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
+{
+}
+#endif
 #ifdef CONFIG_SWAP
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct page *);
@@ -372,13 +382,6 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 {
 }
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
-extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
-#else
-static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
-{
-}
-#endif
 
 #else /* CONFIG_SWAP */
 
diff --git a/include/linux/sysinfo.h b/include/linux/sysinfo.h
new file mode 100644
index 000000000000..934335a22522
--- /dev/null
+++ b/include/linux/sysinfo.h
@@ -0,0 +1,24 @@
+#ifndef _LINUX_SYSINFO_H
+#define _LINUX_SYSINFO_H
+
+#include <linux/types.h>
+
+#define SI_LOAD_SHIFT	16
+struct sysinfo {
+	__kernel_long_t uptime;		/* Seconds since boot */
+	__kernel_ulong_t loads[3];	/* 1, 5, and 15 minute load averages */
+	__kernel_ulong_t totalram;	/* Total usable main memory size */
+	__kernel_ulong_t freeram;	/* Available memory size */
+	__kernel_ulong_t sharedram;	/* Amount of shared memory */
+	__kernel_ulong_t bufferram;	/* Memory used by buffers */
+	__kernel_ulong_t totalswap;	/* Total swap space size */
+	__kernel_ulong_t freeswap;	/* swap space still available */
+	__u16 procs;		   	/* Number of current processes */
+	__u16 pad;		   	/* Explicit padding for m68k */
+	__kernel_ulong_t totalhigh;	/* Total high memory size */
+	__kernel_ulong_t freehigh;	/* Available high memory size */
+	__u32 mem_unit;			/* Memory unit size in bytes */
+	char _f[20-2*sizeof(__kernel_ulong_t)-sizeof(__u32)];	/* Padding: libc5 uses this.. */
+};
+
+#endif /* _LINUX_SYSINFO_H */
diff --git a/include/linux/tboot.h b/include/linux/tboot.h
index 1dba6ee55203..c75128bed5fa 100644
--- a/include/linux/tboot.h
+++ b/include/linux/tboot.h
@@ -143,7 +143,6 @@ static inline int tboot_enabled(void)
 
 extern void tboot_probe(void);
 extern void tboot_shutdown(u32 shutdown_type);
-extern void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control);
 extern struct acpi_table_header *tboot_get_dmar_table(
 				      struct acpi_table_header *dmar_tbl);
 extern int tboot_force_iommu(void);
diff --git a/include/linux/time.h b/include/linux/time.h
index b3061782dec3..33a92ead4d88 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -116,7 +116,6 @@ static inline struct timespec timespec_sub(struct timespec lhs,
 extern void read_persistent_clock(struct timespec *ts);
 extern void read_boot_clock(struct timespec *ts);
 extern int update_persistent_clock(struct timespec now);
-extern int no_sync_cmos_clock __read_mostly;
 void timekeeping_init(void);
 extern int timekeeping_suspended;
 
@@ -256,6 +255,7 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns)
 	a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns);
 	a->tv_nsec = ns;
 }
+
 #endif /* __KERNEL__ */
 
 #define NFDBITS			__NFDBITS
diff --git a/include/linux/timex.h b/include/linux/timex.h
index b75e1864ed19..99bc88b1fc02 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -252,7 +252,7 @@ extern void ntp_clear(void);
 /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
 extern u64 ntp_tick_length(void);
 
-extern void second_overflow(void);
+extern int second_overflow(unsigned long secs);
 extern int do_adjtimex(struct timex *);
 extern void hardpps(const struct timespec *, const struct timespec *);
 
diff --git a/include/linux/tty.h b/include/linux/tty.h
index a91ff403b3bf..9f47ab540f65 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -44,7 +44,6 @@
 #include <linux/tty_ldisc.h>
 #include <linux/mutex.h>
 
-#include <asm/system.h>
 
 
 /*
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index d0018d27c281..8efd28ae5597 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -96,7 +96,6 @@ struct virtio_driver {
 	void (*config_changed)(struct virtio_device *dev);
 #ifdef CONFIG_PM
 	int (*freeze)(struct virtio_device *dev);
-	int (*thaw)(struct virtio_device *dev);
 	int (*restore)(struct virtio_device *dev);
 #endif
 };
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 7d9a9e990ce6..1dee81c41ff1 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -22,7 +22,6 @@
 #include <linux/list.h>
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
-#include <asm/system.h>
 #include <asm/current.h>
 
 typedef struct __wait_queue wait_queue_t;
diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h
index 43ba5b3ce2a3..ac40716b44e9 100644
--- a/include/linux/watchdog.h
+++ b/include/linux/watchdog.h
@@ -66,6 +66,7 @@ struct watchdog_device;
  * @ping:	The routine that sends a keepalive ping to the watchdog device.
  * @status:	The routine that shows the status of the watchdog device.
  * @set_timeout:The routine for setting the watchdog devices timeout value.
+ * @get_timeleft:The routine that get's the time that's left before a reset.
  * @ioctl:	The routines that handles extra ioctl calls.
  *
  * The watchdog_ops structure contains a list of low-level operations
@@ -82,6 +83,7 @@ struct watchdog_ops {
 	int (*ping)(struct watchdog_device *);
 	unsigned int (*status)(struct watchdog_device *);
 	int (*set_timeout)(struct watchdog_device *, unsigned int);
+	unsigned int (*get_timeleft)(struct watchdog_device *);
 	long (*ioctl)(struct watchdog_device *, unsigned int, unsigned long);
 };
 
@@ -127,7 +129,7 @@ struct watchdog_device {
 #endif
 
 /* Use the following function to set the nowayout feature */
-static inline void watchdog_set_nowayout(struct watchdog_device *wdd, int nowayout)
+static inline void watchdog_set_nowayout(struct watchdog_device *wdd, bool nowayout)
 {
 	if (nowayout)
 		set_bit(WDOG_NO_WAY_OUT, &wdd->status);
diff --git a/include/net/netfilter/xt_log.h b/include/net/netfilter/xt_log.h
index 7e1544e8f70d..9d9756cca013 100644
--- a/include/net/netfilter/xt_log.h
+++ b/include/net/netfilter/xt_log.h
@@ -47,7 +47,7 @@ static void sb_close(struct sbuff *m)
 	if (likely(m != &emergency))
 		kfree(m);
 	else {
-		xchg(&emergency_ptr, m);
+		emergency_ptr = m;
 		local_bh_enable();
 	}
 }
diff --git a/include/scsi/iscsi_if.h b/include/scsi/iscsi_if.h
index 9c23ee8fd2d3..917741bb8e11 100644
--- a/include/scsi/iscsi_if.h
+++ b/include/scsi/iscsi_if.h
@@ -261,7 +261,8 @@ struct iscsi_uevent {
 		} host_event;
 		struct msg_ping_comp {
 			uint32_t        host_no;
-			uint32_t        status;
+			uint32_t        status; /* enum
+						 * iscsi_ping_status_code */
 			uint32_t	pid;	/* unique ping id associated
 						   with each ping request */
 			uint32_t        data_size;
@@ -483,6 +484,20 @@ enum iscsi_port_state {
 	ISCSI_PORT_STATE_UP		= 0x2,
 };
 
+/* iSCSI PING status/error code */
+enum iscsi_ping_status_code {
+	ISCSI_PING_SUCCESS			= 0,
+	ISCSI_PING_FW_DISABLED			= 0x1,
+	ISCSI_PING_IPADDR_INVALID		= 0x2,
+	ISCSI_PING_LINKLOCAL_IPV6_ADDR_INVALID	= 0x3,
+	ISCSI_PING_TIMEOUT			= 0x4,
+	ISCSI_PING_INVALID_DEST_ADDR		= 0x5,
+	ISCSI_PING_OVERSIZE_PACKET		= 0x6,
+	ISCSI_PING_ICMP_ERROR			= 0x7,
+	ISCSI_PING_MAX_REQ_EXCEEDED		= 0x8,
+	ISCSI_PING_NO_ARP_RECEIVED		= 0x9,
+};
+
 #define iscsi_ptr(_handle) ((void*)(unsigned long)_handle)
 #define iscsi_handle(_ptr) ((uint64_t)(unsigned long)_ptr)
 
@@ -578,6 +593,6 @@ struct iscsi_chap_rec {
 	char username[ISCSI_CHAP_AUTH_NAME_MAX_LEN];
 	uint8_t password[ISCSI_CHAP_AUTH_SECRET_MAX_LEN];
 	uint8_t password_length;
-} __packed;
+};
 
 #endif
diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h
index 5a35a2a2d3c5..cfdb55f0937e 100644
--- a/include/scsi/libfcoe.h
+++ b/include/scsi/libfcoe.h
@@ -165,7 +165,8 @@ struct fcoe_ctlr {
  * @switch_name: WWN of switch from advertisement
  * @fabric_name: WWN of fabric from advertisement
  * @fc_map:	 FC_MAP value from advertisement
- * @fcf_mac:	 Ethernet address of the FCF
+ * @fcf_mac:	 Ethernet address of the FCF for FIP traffic
+ * @fcoe_mac:	 Ethernet address of the FCF for FCoE traffic
  * @vfid:	 virtual fabric ID
  * @pri:	 selection priority, smaller values are better
  * @flogi_sent:	 current FLOGI sent to this FCF
@@ -188,6 +189,7 @@ struct fcoe_fcf {
 	u32 fc_map;
 	u16 vfid;
 	u8 fcf_mac[ETH_ALEN];
+	u8 fcoe_mac[ETH_ALEN];
 
 	u8 pri;
 	u8 flogi_sent;
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 84f3001a568d..91b91e805673 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -6,6 +6,7 @@
 
 #include <linux/writeback.h>
 #include <linux/tracepoint.h>
+#include <trace/events/gfpflags.h>
 
 struct btrfs_root;
 struct btrfs_fs_info;
@@ -862,6 +863,49 @@ TRACE_EVENT(btrfs_setup_cluster,
 		  __entry->size, __entry->max_size, __entry->bitmap)
 );
 
+struct extent_state;
+TRACE_EVENT(alloc_extent_state,
+
+	TP_PROTO(struct extent_state *state, gfp_t mask, unsigned long IP),
+
+	TP_ARGS(state, mask, IP),
+
+	TP_STRUCT__entry(
+		__field(struct extent_state *, state)
+		__field(gfp_t, mask)
+		__field(unsigned long, ip)
+	),
+
+	TP_fast_assign(
+		__entry->state	= state,
+		__entry->mask	= mask,
+		__entry->ip	= IP
+	),
+
+	TP_printk("state=%p; mask = %s; caller = %pF", __entry->state,
+		  show_gfp_flags(__entry->mask), (void *)__entry->ip)
+);
+
+TRACE_EVENT(free_extent_state,
+
+	TP_PROTO(struct extent_state *state, unsigned long IP),
+
+	TP_ARGS(state, IP),
+
+	TP_STRUCT__entry(
+		__field(struct extent_state *, state)
+		__field(unsigned long, ip)
+	),
+
+	TP_fast_assign(
+		__entry->state	= state,
+		__entry->ip = IP
+	),
+
+	TP_printk(" state=%p; caller = %pF", __entry->state,
+		  (void *)__entry->ip)
+);
+
 #endif /* _TRACE_BTRFS_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index 75964412ddbb..127993dbf322 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -81,6 +81,13 @@ DEFINE_EVENT(jbd2_commit, jbd2_commit_logging,
 	TP_ARGS(journal, commit_transaction)
 );
 
+DEFINE_EVENT(jbd2_commit, jbd2_drop_transaction,
+
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction)
+);
+
 TRACE_EVENT(jbd2_end_commit,
 	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
 
@@ -200,7 +207,7 @@ TRACE_EVENT(jbd2_checkpoint_stats,
 		  __entry->forced_to_close, __entry->written, __entry->dropped)
 );
 
-TRACE_EVENT(jbd2_cleanup_journal_tail,
+TRACE_EVENT(jbd2_update_log_tail,
 
 	TP_PROTO(journal_t *journal, tid_t first_tid,
 		 unsigned long block_nr, unsigned long freed),
@@ -229,6 +236,26 @@ TRACE_EVENT(jbd2_cleanup_journal_tail,
 		  __entry->block_nr, __entry->freed)
 );
 
+TRACE_EVENT(jbd2_write_superblock,
+
+	TP_PROTO(journal_t *journal, int write_op),
+
+	TP_ARGS(journal, write_op),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,  dev			)
+		__field(	  int,  write_op		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->write_op	= write_op;
+	),
+
+	TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev),
+		  MINOR(__entry->dev), __entry->write_op)
+);
+
 #endif /* _TRACE_JBD2_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index fbc7b1ad929b..ea7a2035456d 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -295,7 +295,7 @@ TRACE_EVENT(sched_process_exec,
 	TP_fast_assign(
 		__assign_str(filename, bprm->filename);
 		__entry->pid		= p->pid;
-		__entry->old_pid	= p->pid;
+		__entry->old_pid	= old_pid;
 	),
 
 	TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename),
diff --git a/include/video/sa1100fb.h b/include/video/sa1100fb.h
new file mode 100644
index 000000000000..4ab409653785
--- /dev/null
+++ b/include/video/sa1100fb.h
@@ -0,0 +1,63 @@
+/*
+ * StrongARM 1100 LCD Controller Frame Buffer Device
+ *
+ * Copyright (C) 1999 Eric A. Thomas
+ *  Based on acornfb.c Copyright (C) Russell King.
+ *  
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+#ifndef _VIDEO_SA1100FB_H
+#define _VIDEO_SA1100FB_H
+
+#include <linux/fb.h>
+#include <linux/types.h>
+
+#define RGB_4	0
+#define RGB_8	1
+#define RGB_16	2
+#define NR_RGB	3
+
+/* These are the bitfields for each display depth that we support. */
+struct sa1100fb_rgb {
+	struct fb_bitfield	red;
+	struct fb_bitfield	green;
+	struct fb_bitfield	blue;
+	struct fb_bitfield	transp;
+};
+
+/* This structure describes the machine which we are running on. */
+struct sa1100fb_mach_info {
+	u_long		pixclock;
+
+	u_short		xres;
+	u_short		yres;
+
+	u_char		bpp;
+	u_char		hsync_len;
+	u_char		left_margin;
+	u_char		right_margin;
+
+	u_char		vsync_len;
+	u_char		upper_margin;
+	u_char		lower_margin;
+	u_char		sync;
+
+	u_int		cmap_greyscale:1,
+			cmap_inverse:1,
+			cmap_static:1,
+			unused:29;
+
+	u_int		lccr0;
+	u_int		lccr3;
+
+	/* Overrides for the default RGB maps */
+	const struct sa1100fb_rgb *rgb[NR_RGB];
+
+	void (*backlight_power)(int);
+	void (*lcd_power)(int);
+	void (*set_visual)(u32);
+};
+
+#endif
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index 2ea2fdc79c16..4f4d449f00f6 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -7,11 +7,13 @@ extern void xen_swiotlb_init(int verbose);
 
 extern void
 *xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t flags);
+			    dma_addr_t *dma_handle, gfp_t flags,
+			    struct dma_attrs *attrs);
 
 extern void
 xen_swiotlb_free_coherent(struct device *hwdev, size_t size,
-			  void *vaddr, dma_addr_t dma_handle);
+			  void *vaddr, dma_addr_t dma_handle,
+			  struct dma_attrs *attrs);
 
 extern dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 				       unsigned long offset, size_t size,
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 03c85d7387fb..6a198e46ab6e 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -23,6 +23,7 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
 
 void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order);
 
+struct vm_area_struct;
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 			       unsigned long addr,
 			       unsigned long mfn, int nr,
diff --git a/init/Kconfig b/init/Kconfig
index 72f33faca44f..6cfd71d06463 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1414,8 +1414,8 @@ endif # MODULES
 config INIT_ALL_POSSIBLE
 	bool
 	help
-	  Back when each arch used to define their own cpu_online_map and
-	  cpu_possible_map, some of them chose to initialize cpu_possible_map
+	  Back when each arch used to define their own cpu_online_mask and
+	  cpu_possible_mask, some of them chose to initialize cpu_possible_mask
 	  with all 1s, and others with all 0s.  When they were centralised,
 	  it was better to provide this option than to break all the archs
 	  and have several arch maintainers pursuing me down dark alleys.
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 3098a38f3ae1..9047330c73e9 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -2,7 +2,6 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/minix_fs.h>
-#include <linux/ext2_fs.h>
 #include <linux/romfs_fs.h>
 #include <linux/initrd.h>
 #include <linux/sched.h>
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 01f1306aa26e..6212586df29a 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -54,20 +54,19 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 {
 	const int size = 512;
 	struct minix_super_block *minixsb;
-	struct ext2_super_block *ext2sb;
 	struct romfs_super_block *romfsb;
 	struct cramfs_super *cramfsb;
 	struct squashfs_super_block *squashfsb;
 	int nblocks = -1;
 	unsigned char *buf;
 	const char *compress_name;
+	unsigned long n;
 
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	minixsb = (struct minix_super_block *) buf;
-	ext2sb = (struct ext2_super_block *) buf;
 	romfsb = (struct romfs_super_block *) buf;
 	cramfsb = (struct cramfs_super *) buf;
 	squashfsb = (struct squashfs_super_block *) buf;
@@ -150,12 +149,12 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 	}
 
 	/* Try ext2 */
-	if (ext2sb->s_magic == cpu_to_le16(EXT2_SUPER_MAGIC)) {
+	n = ext2_image_size(buf);
+	if (n) {
 		printk(KERN_NOTICE
 		       "RAMDISK: ext2 filesystem found at block %d\n",
 		       start_block);
-		nblocks = le32_to_cpu(ext2sb->s_blocks_count) <<
-			le32_to_cpu(ext2sb->s_log_block_size);
+		nblocks = n;
 		goto done;
 	}
 
diff --git a/init/main.c b/init/main.c
index c24805c824b9..9d454f09f3b1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -87,7 +87,6 @@ extern void mca_init(void);
 extern void sbus_init(void);
 extern void prio_tree_init(void);
 extern void radix_tree_init(void);
-extern void free_initmem(void);
 #ifndef CONFIG_DEBUG_RODATA
 static inline void mark_rodata_ro(void) { }
 #endif
@@ -400,7 +399,7 @@ static int __init do_early_param(char *param, char *val)
 
 void __init parse_early_options(char *cmdline)
 {
-	parse_args("early options", cmdline, NULL, 0, do_early_param);
+	parse_args("early options", cmdline, NULL, 0, 0, 0, do_early_param);
 }
 
 /* Arch code calls this early on, or if not, just before other parsing. */
@@ -503,7 +502,7 @@ asmlinkage void __init start_kernel(void)
 	parse_early_param();
 	parse_args("Booting kernel", static_command_line, __start___param,
 		   __stop___param - __start___param,
-		   &unknown_bootoption);
+		   0, 0, &unknown_bootoption);
 
 	jump_label_init();
 
@@ -699,16 +698,69 @@ int __init_or_module do_one_initcall(initcall_t fn)
 }
 
 
-extern initcall_t __initcall_start[], __initcall_end[], __early_initcall_end[];
+extern initcall_t __initcall_start[];
+extern initcall_t __initcall0_start[];
+extern initcall_t __initcall1_start[];
+extern initcall_t __initcall2_start[];
+extern initcall_t __initcall3_start[];
+extern initcall_t __initcall4_start[];
+extern initcall_t __initcall5_start[];
+extern initcall_t __initcall6_start[];
+extern initcall_t __initcall7_start[];
+extern initcall_t __initcall_end[];
+
+static initcall_t *initcall_levels[] __initdata = {
+	__initcall0_start,
+	__initcall1_start,
+	__initcall2_start,
+	__initcall3_start,
+	__initcall4_start,
+	__initcall5_start,
+	__initcall6_start,
+	__initcall7_start,
+	__initcall_end,
+};
+
+static char *initcall_level_names[] __initdata = {
+	"early parameters",
+	"core parameters",
+	"postcore parameters",
+	"arch parameters",
+	"subsys parameters",
+	"fs parameters",
+	"device parameters",
+	"late parameters",
+};
+
+static int __init ignore_unknown_bootoption(char *param, char *val)
+{
+	return 0;
+}
 
-static void __init do_initcalls(void)
+static void __init do_initcall_level(int level)
 {
+	extern const struct kernel_param __start___param[], __stop___param[];
 	initcall_t *fn;
 
-	for (fn = __early_initcall_end; fn < __initcall_end; fn++)
+	strcpy(static_command_line, saved_command_line);
+	parse_args(initcall_level_names[level],
+		   static_command_line, __start___param,
+		   __stop___param - __start___param,
+		   level, level,
+		   ignore_unknown_bootoption);
+
+	for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
 		do_one_initcall(*fn);
 }
 
+static void __init do_initcalls(void)
+{
+	int level;
+
+	for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++)
+		do_initcall_level(level);
+}
+
 /*
  * Ok, the machine is now initialized. None of the devices
  * have been touched yet, but the CPU subsystem is up and
@@ -732,7 +784,7 @@ static void __init do_pre_smp_initcalls(void)
 {
 	initcall_t *fn;
 
-	for (fn = __initcall_start; fn < __early_initcall_end; fn++)
+	for (fn = __initcall_start; fn < __initcall0_start; fn++)
 		do_one_initcall(*fn);
 }
 
diff --git a/ipc/compat.c b/ipc/compat.c
index 845a28738d3a..a6df704f521e 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -27,6 +27,7 @@
 #include <linux/msg.h>
 #include <linux/shm.h>
 #include <linux/syscalls.h>
+#include <linux/ptrace.h>
 
 #include <linux/mutex.h>
 #include <asm/uaccess.h>
@@ -117,6 +118,7 @@ extern int sem_ctls[];
 
 static inline int compat_ipc_parse_version(int *cmd)
 {
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
 	int version = *cmd & IPC_64;
 
 	/* this is tricky: architectures that have support for the old
@@ -128,6 +130,10 @@ static inline int compat_ipc_parse_version(int *cmd)
 	*cmd &= ~IPC_64;
 #endif
 	return version;
+#else
+	/* With the asm-generic APIs, we always use the 64-bit versions. */
+	return IPC_64;
+#endif
 }
 
 static inline int __get_compat_ipc64_perm(struct ipc64_perm *p64,
@@ -232,10 +238,9 @@ static inline int put_compat_semid_ds(struct semid64_ds *s,
 	return err;
 }
 
-long compat_sys_semctl(int first, int second, int third, void __user *uptr)
+static long do_compat_semctl(int first, int second, int third, u32 pad)
 {
 	union semun fourth;
-	u32 pad;
 	int err, err2;
 	struct semid64_ds s64;
 	struct semid64_ds __user *up64;
@@ -243,10 +248,6 @@ long compat_sys_semctl(int first, int second, int third, void __user *uptr)
 
 	memset(&s64, 0, sizeof(s64));
 
-	if (!uptr)
-		return -EINVAL;
-	if (get_user(pad, (u32 __user *) uptr))
-		return -EFAULT;
 	if ((third & (~IPC_64)) == SETVAL)
 		fourth.val = (int) pad;
 	else
@@ -305,6 +306,18 @@ long compat_sys_semctl(int first, int second, int third, void __user *uptr)
 	return err;
 }
 
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
+long compat_sys_semctl(int first, int second, int third, void __user *uptr)
+{
+	u32 pad;
+
+	if (!uptr)
+		return -EINVAL;
+	if (get_user(pad, (u32 __user *) uptr))
+		return -EFAULT;
+	return do_compat_semctl(first, second, third, pad);
+}
+
 long compat_sys_msgsnd(int first, int second, int third, void __user *uptr)
 {
 	struct compat_msgbuf __user *up = uptr;
@@ -353,6 +366,37 @@ long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
 out:
 	return err;
 }
+#else
+long compat_sys_semctl(int semid, int semnum, int cmd, int arg)
+{
+	return do_compat_semctl(semid, semnum, cmd, arg);
+}
+
+long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp,
+		       size_t msgsz, int msgflg)
+{
+	compat_long_t mtype;
+
+	if (get_user(mtype, &msgp->mtype))
+		return -EFAULT;
+	return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg);
+}
+
+long compat_sys_msgrcv(int msqid, struct compat_msgbuf __user *msgp,
+		       size_t msgsz, long msgtyp, int msgflg)
+{
+	long err, mtype;
+
+	err =  do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg);
+	if (err < 0)
+		goto out;
+
+	if (put_user(mtype, &msgp->mtype))
+		err = -EFAULT;
+ out:
+	return err;
+}
+#endif
 
 static inline int get_compat_msqid64(struct msqid64_ds *m64,
 				     struct compat_msqid64_ds __user *up64)
@@ -470,6 +514,7 @@ long compat_sys_msgctl(int first, int second, void __user *uptr)
 	return err;
 }
 
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
 long compat_sys_shmat(int first, int second, compat_uptr_t third, int version,
 			void __user *uptr)
 {
@@ -485,6 +530,19 @@ long compat_sys_shmat(int first, int second, compat_uptr_t third, int version,
 	uaddr = compat_ptr(third);
 	return put_user(raddr, uaddr);
 }
+#else
+long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg)
+{
+	unsigned long ret;
+	long err;
+
+	err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret);
+	if (err)
+		return err;
+	force_successful_syscall_return();
+	return (long)ret;
+}
+#endif
 
 static inline int get_compat_shmid64_ds(struct shmid64_ds *s64,
 					struct compat_shmid64_ds __user *up64)
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 5068e2a4e75f..2251882daf53 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -124,8 +124,8 @@ config INLINE_SPIN_LOCK_IRQSAVE
 	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
 		 ARCH_INLINE_SPIN_LOCK_IRQSAVE
 
-config INLINE_SPIN_UNLOCK
-	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK)
+config UNINLINE_SPIN_UNLOCK
+	bool
 
 config INLINE_SPIN_UNLOCK_BH
 	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 24e7cb0ba26a..3f9c97419f02 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -36,6 +36,7 @@ config PREEMPT_VOLUNTARY
 config PREEMPT
 	bool "Preemptible Kernel (Low-Latency Desktop)"
 	select PREEMPT_COUNT
+	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
 	help
 	  This option reduces the latency of the kernel by making
 	  all kernel code (that is not executing in a critical section)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f4ea4b6f3cf1..ed64ccac67c9 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1883,7 +1883,7 @@ static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
  */
 int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
-	int retval;
+	int retval = 0;
 	struct cgroup_subsys *ss, *failed_ss = NULL;
 	struct cgroup *oldcgrp;
 	struct cgroupfs_root *root = cgrp->root;
diff --git a/kernel/compat.c b/kernel/compat.c
index f346cedfe24d..74ff8498809a 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -31,11 +31,10 @@
 #include <asm/uaccess.h>
 
 /*
- * Note that the native side is already converted to a timespec, because
- * that's what we want anyway.
+ * Get/set struct timeval with struct timespec on the native side
  */
-static int compat_get_timeval(struct timespec *o,
-		struct compat_timeval __user *i)
+static int compat_get_timeval_convert(struct timespec *o,
+				      struct compat_timeval __user *i)
 {
 	long usec;
 
@@ -46,8 +45,8 @@ static int compat_get_timeval(struct timespec *o,
 	return 0;
 }
 
-static int compat_put_timeval(struct compat_timeval __user *o,
-		struct timeval *i)
+static int compat_put_timeval_convert(struct compat_timeval __user *o,
+				      struct timeval *i)
 {
 	return (put_user(i->tv_sec, &o->tv_sec) ||
 		put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
@@ -117,7 +116,7 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
 	if (tv) {
 		struct timeval ktv;
 		do_gettimeofday(&ktv);
-		if (compat_put_timeval(tv, &ktv))
+		if (compat_put_timeval_convert(tv, &ktv))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -135,7 +134,7 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
 	struct timezone ktz;
 
 	if (tv) {
-		if (compat_get_timeval(&kts, tv))
+		if (compat_get_timeval_convert(&kts, tv))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -146,12 +145,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
 	return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
 }
 
+int get_compat_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
+{
+	return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) ||
+			__get_user(tv->tv_sec, &ctv->tv_sec) ||
+			__get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
+}
+EXPORT_SYMBOL_GPL(get_compat_timeval);
+
+int put_compat_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
+{
+	return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) ||
+			__put_user(tv->tv_sec, &ctv->tv_sec) ||
+			__put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
+}
+EXPORT_SYMBOL_GPL(put_compat_timeval);
+
 int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
 			__get_user(ts->tv_sec, &cts->tv_sec) ||
 			__get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
+EXPORT_SYMBOL_GPL(get_compat_timespec);
 
 int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
 {
@@ -161,6 +177,42 @@ int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user
 }
 EXPORT_SYMBOL_GPL(put_compat_timespec);
 
+int compat_get_timeval(struct timeval *tv, const void __user *utv)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_from_user(tv, utv, sizeof *tv) ? -EFAULT : 0;
+	else
+		return get_compat_timeval(tv, utv);
+}
+EXPORT_SYMBOL_GPL(compat_get_timeval);
+
+int compat_put_timeval(const struct timeval *tv, void __user *utv)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_to_user(utv, tv, sizeof *tv) ? -EFAULT : 0;
+	else
+		return put_compat_timeval(tv, utv);
+}
+EXPORT_SYMBOL_GPL(compat_put_timeval);
+
+int compat_get_timespec(struct timespec *ts, const void __user *uts)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_from_user(ts, uts, sizeof *ts) ? -EFAULT : 0;
+	else
+		return get_compat_timespec(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_get_timespec);
+
+int compat_put_timespec(const struct timespec *ts, void __user *uts)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_to_user(uts, ts, sizeof *ts) ? -EFAULT : 0;
+	else
+		return put_compat_timespec(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_put_timespec);
+
 static long compat_nanosleep_restart(struct restart_block *restart)
 {
 	struct compat_timespec __user *rmtp;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1010cc61931f..14f7070b4ba2 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -270,11 +270,11 @@ static struct file_system_type cpuset_fs_type = {
  * are online.  If none are online, walk up the cpuset hierarchy
  * until we find one that does have some online cpus.  If we get
  * all the way to the top and still haven't found any online cpus,
- * return cpu_online_map.  Or if passed a NULL cs from an exit'ing
- * task, return cpu_online_map.
+ * return cpu_online_mask.  Or if passed a NULL cs from an exit'ing
+ * task, return cpu_online_mask.
  *
  * One way or another, we guarantee to return some non-empty subset
- * of cpu_online_map.
+ * of cpu_online_mask.
  *
  * Call with callback_mutex held.
  */
@@ -867,7 +867,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	int retval;
 	int is_load_balanced;
 
-	/* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
+	/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
 	if (cs == &top_cpuset)
 		return -EACCES;
 
@@ -2149,7 +2149,7 @@ void __init cpuset_init_smp(void)
  *
  * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
- * subset of cpu_online_map, even if this means going outside the
+ * subset of cpu_online_mask, even if this means going outside the
  * tasks cpuset.
  **/
 
@@ -2162,10 +2162,9 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 	mutex_unlock(&callback_mutex);
 }
 
-int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
+void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
 	const struct cpuset *cs;
-	int cpu;
 
 	rcu_read_lock();
 	cs = task_cs(tsk);
@@ -2186,22 +2185,10 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 	 * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary
 	 * set any mask even if it is not right from task_cs() pov,
 	 * the pending set_cpus_allowed_ptr() will fix things.
+	 *
+	 * select_fallback_rq() will fix things ups and set cpu_possible_mask
+	 * if required.
 	 */
-
-	cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask);
-	if (cpu >= nr_cpu_ids) {
-		/*
-		 * Either tsk->cpus_allowed is wrong (see above) or it
-		 * is actually empty. The latter case is only possible
-		 * if we are racing with remove_tasks_in_empty_cpuset().
-		 * Like above we can temporary set any mask and rely on
-		 * set_cpus_allowed_ptr() as synchronization point.
-		 */
-		do_set_cpus_allowed(tsk, cpu_possible_mask);
-		cpu = cpumask_any(cpu_active_mask);
-	}
-
-	return cpu;
 }
 
 void cpuset_init_current_mems_allowed(void)
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 3f88a45e6f0a..0557f24c6bca 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -53,7 +53,6 @@
 #include <asm/cacheflush.h>
 #include <asm/byteorder.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 
 #include "debug_core.h"
 
@@ -161,37 +160,39 @@ early_param("nokgdbroundup", opt_nokgdbroundup);
  * Weak aliases for breakpoint management,
  * can be overriden by architectures when needed:
  */
-int __weak kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr)
+int __weak kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
 	int err;
 
-	err = probe_kernel_read(saved_instr, (char *)addr, BREAK_INSTR_SIZE);
+	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
-
-	return probe_kernel_write((char *)addr, arch_kgdb_ops.gdb_bpt_instr,
-				  BREAK_INSTR_SIZE);
+	err = probe_kernel_write((char *)bpt->bpt_addr,
+				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
+	return err;
 }
 
-int __weak kgdb_arch_remove_breakpoint(unsigned long addr, char *bundle)
+int __weak kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-	return probe_kernel_write((char *)addr,
-				  (char *)bundle, BREAK_INSTR_SIZE);
+	return probe_kernel_write((char *)bpt->bpt_addr,
+				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
 
 int __weak kgdb_validate_break_address(unsigned long addr)
 {
-	char tmp_variable[BREAK_INSTR_SIZE];
+	struct kgdb_bkpt tmp;
 	int err;
-	/* Validate setting the breakpoint and then removing it.  In the
+	/* Validate setting the breakpoint and then removing it.  If the
 	 * remove fails, the kernel needs to emit a bad message because we
 	 * are deep trouble not being able to put things back the way we
 	 * found them.
 	 */
-	err = kgdb_arch_set_breakpoint(addr, tmp_variable);
+	tmp.bpt_addr = addr;
+	err = kgdb_arch_set_breakpoint(&tmp);
 	if (err)
 		return err;
-	err = kgdb_arch_remove_breakpoint(addr, tmp_variable);
+	err = kgdb_arch_remove_breakpoint(&tmp);
 	if (err)
 		printk(KERN_ERR "KGDB: Critical breakpoint error, kernel "
 		   "memory destroyed at: %lx", addr);
@@ -235,7 +236,6 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
  */
 int dbg_activate_sw_breakpoints(void)
 {
-	unsigned long addr;
 	int error;
 	int ret = 0;
 	int i;
@@ -244,16 +244,15 @@ int dbg_activate_sw_breakpoints(void)
 		if (kgdb_break[i].state != BP_SET)
 			continue;
 
-		addr = kgdb_break[i].bpt_addr;
-		error = kgdb_arch_set_breakpoint(addr,
-				kgdb_break[i].saved_instr);
+		error = kgdb_arch_set_breakpoint(&kgdb_break[i]);
 		if (error) {
 			ret = error;
-			printk(KERN_INFO "KGDB: BP install failed: %lx", addr);
+			printk(KERN_INFO "KGDB: BP install failed: %lx",
+			       kgdb_break[i].bpt_addr);
 			continue;
 		}
 
-		kgdb_flush_swbreak_addr(addr);
+		kgdb_flush_swbreak_addr(kgdb_break[i].bpt_addr);
 		kgdb_break[i].state = BP_ACTIVE;
 	}
 	return ret;
@@ -302,7 +301,6 @@ int dbg_set_sw_break(unsigned long addr)
 
 int dbg_deactivate_sw_breakpoints(void)
 {
-	unsigned long addr;
 	int error;
 	int ret = 0;
 	int i;
@@ -310,15 +308,14 @@ int dbg_deactivate_sw_breakpoints(void)
 	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
 		if (kgdb_break[i].state != BP_ACTIVE)
 			continue;
-		addr = kgdb_break[i].bpt_addr;
-		error = kgdb_arch_remove_breakpoint(addr,
-					kgdb_break[i].saved_instr);
+		error = kgdb_arch_remove_breakpoint(&kgdb_break[i]);
 		if (error) {
-			printk(KERN_INFO "KGDB: BP remove failed: %lx\n", addr);
+			printk(KERN_INFO "KGDB: BP remove failed: %lx\n",
+			       kgdb_break[i].bpt_addr);
 			ret = error;
 		}
 
-		kgdb_flush_swbreak_addr(addr);
+		kgdb_flush_swbreak_addr(kgdb_break[i].bpt_addr);
 		kgdb_break[i].state = BP_SET;
 	}
 	return ret;
@@ -352,7 +349,6 @@ int kgdb_isremovedbreak(unsigned long addr)
 
 int dbg_remove_all_break(void)
 {
-	unsigned long addr;
 	int error;
 	int i;
 
@@ -360,12 +356,10 @@ int dbg_remove_all_break(void)
 	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
 		if (kgdb_break[i].state != BP_ACTIVE)
 			goto setundefined;
-		addr = kgdb_break[i].bpt_addr;
-		error = kgdb_arch_remove_breakpoint(addr,
-				kgdb_break[i].saved_instr);
+		error = kgdb_arch_remove_breakpoint(&kgdb_break[i]);
 		if (error)
 			printk(KERN_ERR "KGDB: breakpoint remove failed: %lx\n",
-			   addr);
+			       kgdb_break[i].bpt_addr);
 setundefined:
 		kgdb_break[i].state = BP_UNDEFINED;
 	}
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index 7179eac7b41c..07c9bbb94a0b 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -15,7 +15,6 @@
 #include <linux/sched.h>
 #include <linux/kdb.h>
 #include <linux/nmi.h>
-#include <asm/system.h>
 #include "kdb_private.h"
 
 
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 9b5f17da1c56..bb9520f0f6ff 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -743,7 +743,7 @@ kdb_printit:
 		kdb_input_flush();
 		c = console_drivers;
 
-		if (!dbg_io_ops->is_console) {
+		if (dbg_io_ops && !dbg_io_ops->is_console) {
 			len = strlen(moreprompt);
 			cp = moreprompt;
 			while (len--) {
diff --git a/kernel/dma.c b/kernel/dma.c
index 68a2306522c8..6c6262f86c17 100644
--- a/kernel/dma.c
+++ b/kernel/dma.c
@@ -18,7 +18,6 @@
 #include <linux/proc_fs.h>
 #include <linux/init.h>
 #include <asm/dma.h>
-#include <asm/system.h>
 
 
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4b50357914fb..a6a9ec4cd8f5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3348,7 +3348,7 @@ static void calc_timer_values(struct perf_event *event,
 	*running = ctx_time - event->tstamp_running;
 }
 
-void __weak perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
 }
 
@@ -3398,7 +3398,7 @@ void perf_event_update_userpage(struct perf_event *event)
 	userpg->time_running = running +
 			atomic64_read(&event->child_total_time_running);
 
-	perf_update_user_clock(userpg, now);
+	arch_perf_update_userpage(userpg, now);
 
 	barrier();
 	++userpg->lock;
@@ -7116,6 +7116,13 @@ void __init perf_event_init(void)
 
 	/* do not patch jump label more than once per second */
 	jump_label_rate_limit(&perf_sched_events, HZ);
+
+	/*
+	 * Build time assertion that we keep the data_head at the intended
+	 * location.  IOW, validation we got the __reserved[] size right.
+	 */
+	BUILD_BUG_ON((offsetof(struct perf_event_mmap_page, data_head))
+		     != 1024);
 }
 
 static int __init perf_event_sysfs_init(void)
diff --git a/kernel/exit.c b/kernel/exit.c
index 3db1909faed9..d8bd3b425fa7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -474,7 +474,7 @@ static void close_files(struct files_struct * files)
 		i = j * __NFDBITS;
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->open_fds->fds_bits[j++];
+		set = fdt->open_fds[j++];
 		while (set) {
 			if (set & 1) {
 				struct file * file = xchg(&fdt->fd[i], NULL);
diff --git a/kernel/futex.c b/kernel/futex.c
index 72efa1e4359a..e2b0fb9a0b3b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -59,6 +59,7 @@
 #include <linux/magic.h>
 #include <linux/pid.h>
 #include <linux/nsproxy.h>
+#include <linux/ptrace.h>
 
 #include <asm/futex.h>
 
@@ -2443,40 +2444,31 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
 {
 	struct robust_list_head __user *head;
 	unsigned long ret;
-	const struct cred *cred = current_cred(), *pcred;
+	struct task_struct *p;
 
 	if (!futex_cmpxchg_enabled)
 		return -ENOSYS;
 
+	WARN_ONCE(1, "deprecated: get_robust_list will be deleted in 2013.\n");
+
+	rcu_read_lock();
+
+	ret = -ESRCH;
 	if (!pid)
-		head = current->robust_list;
+		p = current;
 	else {
-		struct task_struct *p;
-
-		ret = -ESRCH;
-		rcu_read_lock();
 		p = find_task_by_vpid(pid);
 		if (!p)
 			goto err_unlock;
-		ret = -EPERM;
-		pcred = __task_cred(p);
-		/* If victim is in different user_ns, then uids are not
-		   comparable, so we must have CAP_SYS_PTRACE */
-		if (cred->user->user_ns != pcred->user->user_ns) {
-			if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
-				goto err_unlock;
-			goto ok;
-		}
-		/* If victim is in same user_ns, then uids are comparable */
-		if (cred->euid != pcred->euid &&
-		    cred->euid != pcred->uid &&
-		    !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
-			goto err_unlock;
-ok:
-		head = p->robust_list;
-		rcu_read_unlock();
 	}
 
+	ret = -EPERM;
+	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+		goto err_unlock;
+
+	head = p->robust_list;
+	rcu_read_unlock();
+
 	if (put_user(sizeof(*head), len_ptr))
 		return -EFAULT;
 	return put_user(head, head_ptr);
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 5f9e689dc8f0..83e368b005fc 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -10,6 +10,7 @@
 #include <linux/compat.h>
 #include <linux/nsproxy.h>
 #include <linux/futex.h>
+#include <linux/ptrace.h>
 
 #include <asm/uaccess.h>
 
@@ -136,40 +137,31 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 {
 	struct compat_robust_list_head __user *head;
 	unsigned long ret;
-	const struct cred *cred = current_cred(), *pcred;
+	struct task_struct *p;
 
 	if (!futex_cmpxchg_enabled)
 		return -ENOSYS;
 
+	WARN_ONCE(1, "deprecated: get_robust_list will be deleted in 2013.\n");
+
+	rcu_read_lock();
+
+	ret = -ESRCH;
 	if (!pid)
-		head = current->compat_robust_list;
+		p = current;
 	else {
-		struct task_struct *p;
-
-		ret = -ESRCH;
-		rcu_read_lock();
 		p = find_task_by_vpid(pid);
 		if (!p)
 			goto err_unlock;
-		ret = -EPERM;
-		pcred = __task_cred(p);
-		/* If victim is in different user_ns, then uids are not
-		   comparable, so we must have CAP_SYS_PTRACE */
-		if (cred->user->user_ns != pcred->user->user_ns) {
-			if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
-				goto err_unlock;
-			goto ok;
-		}
-		/* If victim is in same user_ns, then uids are comparable */
-		if (cred->euid != pcred->euid &&
-		    cred->euid != pcred->uid &&
-		    !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
-			goto err_unlock;
-ok:
-		head = p->compat_robust_list;
-		rcu_read_unlock();
 	}
 
+	ret = -EPERM;
+	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+		goto err_unlock;
+
+	head = p->compat_robust_list;
+	rcu_read_unlock();
+
 	if (put_user(sizeof(*head), len_ptr))
 		return -EFAULT;
 	return put_user(ptr_to_compat(head), head_ptr);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 5a38bf4de641..cf1a4a68ce44 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -13,7 +13,7 @@ config GENERIC_HARDIRQS
 # Options selectable by the architecture code
 
 # Make sparse irq Kconfig switch below available
-config HAVE_SPARSE_IRQ
+config MAY_HAVE_SPARSE_IRQ
        bool
 
 # Enable the generic irq autoprobe mechanism
@@ -56,13 +56,22 @@ config GENERIC_IRQ_CHIP
 config IRQ_DOMAIN
 	bool
 
+config IRQ_DOMAIN_DEBUG
+	bool "Expose hardware/virtual IRQ mapping via debugfs"
+	depends on IRQ_DOMAIN && DEBUG_FS
+	help
+	  This option will show the mapping relationship between hardware irq
+	  numbers and Linux irq numbers. The mapping is exposed via debugfs
+	  in the file "virq_mapping".
+
+	  If you don't know what this means you don't need it.
+
 # Support forced irq threading
 config IRQ_FORCED_THREADING
        bool
 
 config SPARSE_IRQ
-	bool "Support sparse irq numbering"
-	depends on HAVE_SPARSE_IRQ
+	bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ
 	---help---
 
 	  Sparse irq numbering is useful for distro kernels that want
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 6ff84e6a954c..bdb180325551 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -54,14 +54,18 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
 static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
 {
 	/*
-	 * Wake up the handler thread for this action. In case the
-	 * thread crashed and was killed we just pretend that we
-	 * handled the interrupt. The hardirq handler has disabled the
-	 * device interrupt, so no irq storm is lurking. If the
+	 * In case the thread crashed and was killed we just pretend that
+	 * we handled the interrupt. The hardirq handler has disabled the
+	 * device interrupt, so no irq storm is lurking.
+	 */
+	if (action->thread->flags & PF_EXITING)
+		return;
+
+	/*
+	 * Wake up the handler thread for this action. If the
 	 * RUNTHREAD bit is already set, nothing to do.
 	 */
-	if ((action->thread->flags & PF_EXITING) ||
-	    test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+	if (test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
 		return;
 
 	/*
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index af48e59bc2ff..3601f3fbf67c 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -632,7 +632,7 @@ unsigned int irq_linear_revmap(struct irq_domain *domain,
 	return revmap[hwirq];
 }
 
-#ifdef CONFIG_VIRQ_DEBUG
+#ifdef CONFIG_IRQ_DOMAIN_DEBUG
 static int virq_debug_show(struct seq_file *m, void *private)
 {
 	unsigned long flags;
@@ -668,7 +668,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
 			data = irq_desc_get_chip_data(desc);
 			seq_printf(m, "0x%16p  ", data);
 
-			if (desc->irq_data.domain->of_node)
+			if (desc->irq_data.domain && desc->irq_data.domain->of_node)
 				p = desc->irq_data.domain->of_node->full_name;
 			else
 				p = none;
@@ -695,14 +695,14 @@ static const struct file_operations virq_debug_fops = {
 
 static int __init irq_debugfs_init(void)
 {
-	if (debugfs_create_file("virq_mapping", S_IRUGO, powerpc_debugfs_root,
+	if (debugfs_create_file("irq_domain_mapping", S_IRUGO, NULL,
 				 NULL, &virq_debug_fops) == NULL)
 		return -ENOMEM;
 
 	return 0;
 }
 __initcall(irq_debugfs_init);
-#endif /* CONFIG_VIRQ_DEBUG */
+#endif /* CONFIG_IRQ_DOMAIN_DEBUG */
 
 int irq_domain_simple_map(struct irq_domain *d, unsigned int irq,
 			  irq_hw_number_t hwirq)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index b0ccd1ac2d6a..89a3ea82569b 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -282,7 +282,7 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct cpumask *set = irq_default_affinity;
-	int ret;
+	int ret, node = desc->irq_data.node;
 
 	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
@@ -301,6 +301,13 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 	}
 
 	cpumask_and(mask, cpu_online_mask, set);
+	if (node != NUMA_NO_NODE) {
+		const struct cpumask *nodemask = cpumask_of_node(node);
+
+		/* make sure at least one of the cpus in nodemask is online */
+		if (cpumask_intersects(mask, nodemask))
+			cpumask_and(mask, mask, nodemask);
+	}
 	ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
@@ -645,7 +652,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  * is marked MASKED.
  */
 static void irq_finalize_oneshot(struct irq_desc *desc,
-				 struct irqaction *action, bool force)
+				 struct irqaction *action)
 {
 	if (!(desc->istate & IRQS_ONESHOT))
 		return;
@@ -679,7 +686,7 @@ again:
 	 * we would clear the threads_oneshot bit of this thread which
 	 * was just set.
 	 */
-	if (!force && test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+	if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
 		goto out_unlock;
 
 	desc->threads_oneshot &= ~action->thread_mask;
@@ -739,7 +746,7 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 
 	local_bh_disable();
 	ret = action->thread_fn(action->irq, action->dev_id);
-	irq_finalize_oneshot(desc, action, false);
+	irq_finalize_oneshot(desc, action);
 	local_bh_enable();
 	return ret;
 }
@@ -755,7 +762,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
 	irqreturn_t ret;
 
 	ret = action->thread_fn(action->irq, action->dev_id);
-	irq_finalize_oneshot(desc, action, false);
+	irq_finalize_oneshot(desc, action);
 	return ret;
 }
 
@@ -844,7 +851,7 @@ void exit_irq_thread(void)
 		wake_threads_waitq(desc);
 
 	/* Prevent a stale desc->threads_oneshot */
-	irq_finalize_oneshot(desc, action, true);
+	irq_finalize_oneshot(desc, action);
 }
 
 static void irq_setup_forced_threading(struct irqaction *new)
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 47420908fba0..c3c89751b327 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -43,12 +43,16 @@ void irq_move_masked_irq(struct irq_data *idata)
 	 * masking the irqs.
 	 */
 	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
-		   < nr_cpu_ids))
-		if (!chip->irq_set_affinity(&desc->irq_data,
-					    desc->pending_mask, false)) {
+		   < nr_cpu_ids)) {
+		int ret = chip->irq_set_affinity(&desc->irq_data,
+						 desc->pending_mask, false);
+		switch (ret) {
+		case IRQ_SET_MASK_OK:
 			cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
+		case IRQ_SET_MASK_OK_NOCOPY:
 			irq_set_thread_affinity(desc);
 		}
+	}
 
 	cpumask_clear(desc->pending_mask);
 }
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index c3c46c72046e..0c56d44b9fd5 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -5,6 +5,7 @@
  * context. The enqueueing is NMI-safe.
  */
 
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/irq_work.h>
diff --git a/kernel/kexec.c b/kernel/kexec.c
index a6a675cb9818..4e2e472f6aeb 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -37,7 +37,6 @@
 #include <asm/page.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/sections.h>
 
 /* Per cpu memory for storing cpu states in case of system crash. */
@@ -1359,6 +1358,10 @@ static int __init parse_crashkernel_simple(char 		*cmdline,
 
 	if (*cur == '@')
 		*crash_base = memparse(cur+1, &cur);
+	else if (*cur != ' ' && *cur != '\0') {
+		pr_warning("crashkernel: unrecognized char\n");
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -1462,7 +1465,9 @@ static int __init crash_save_vmcoreinfo_init(void)
 
 	VMCOREINFO_SYMBOL(init_uts_ns);
 	VMCOREINFO_SYMBOL(node_online_map);
+#ifdef CONFIG_MMU
 	VMCOREINFO_SYMBOL(swapper_pg_dir);
+#endif
 	VMCOREINFO_SYMBOL(_stext);
 	VMCOREINFO_SYMBOL(vmlist);
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 957a7aab8ebc..05698a7415fe 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -322,7 +322,7 @@ static void __call_usermodehelper(struct work_struct *work)
  * land has been frozen during a system-wide hibernation or suspend operation).
  * Should always be manipulated under umhelper_sem acquired for write.
  */
-static int usermodehelper_disabled = 1;
+static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED;
 
 /* Number of helpers running */
 static atomic_t running_helpers = ATOMIC_INIT(0);
@@ -334,32 +334,110 @@ static atomic_t running_helpers = ATOMIC_INIT(0);
 static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq);
 
 /*
+ * Used by usermodehelper_read_lock_wait() to wait for usermodehelper_disabled
+ * to become 'false'.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq);
+
+/*
  * Time to wait for running_helpers to become zero before the setting of
  * usermodehelper_disabled in usermodehelper_disable() fails
  */
 #define RUNNING_HELPERS_TIMEOUT	(5 * HZ)
 
-void read_lock_usermodehelper(void)
+int usermodehelper_read_trylock(void)
 {
+	DEFINE_WAIT(wait);
+	int ret = 0;
+
 	down_read(&umhelper_sem);
+	for (;;) {
+		prepare_to_wait(&usermodehelper_disabled_waitq, &wait,
+				TASK_INTERRUPTIBLE);
+		if (!usermodehelper_disabled)
+			break;
+
+		if (usermodehelper_disabled == UMH_DISABLED)
+			ret = -EAGAIN;
+
+		up_read(&umhelper_sem);
+
+		if (ret)
+			break;
+
+		schedule();
+		try_to_freeze();
+
+		down_read(&umhelper_sem);
+	}
+	finish_wait(&usermodehelper_disabled_waitq, &wait);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(usermodehelper_read_trylock);
+
+long usermodehelper_read_lock_wait(long timeout)
+{
+	DEFINE_WAIT(wait);
+
+	if (timeout < 0)
+		return -EINVAL;
+
+	down_read(&umhelper_sem);
+	for (;;) {
+		prepare_to_wait(&usermodehelper_disabled_waitq, &wait,
+				TASK_UNINTERRUPTIBLE);
+		if (!usermodehelper_disabled)
+			break;
+
+		up_read(&umhelper_sem);
+
+		timeout = schedule_timeout(timeout);
+		if (!timeout)
+			break;
+
+		down_read(&umhelper_sem);
+	}
+	finish_wait(&usermodehelper_disabled_waitq, &wait);
+	return timeout;
 }
-EXPORT_SYMBOL_GPL(read_lock_usermodehelper);
+EXPORT_SYMBOL_GPL(usermodehelper_read_lock_wait);
 
-void read_unlock_usermodehelper(void)
+void usermodehelper_read_unlock(void)
 {
 	up_read(&umhelper_sem);
 }
-EXPORT_SYMBOL_GPL(read_unlock_usermodehelper);
+EXPORT_SYMBOL_GPL(usermodehelper_read_unlock);
 
 /**
- * usermodehelper_disable - prevent new helpers from being started
+ * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled.
+ * depth: New value to assign to usermodehelper_disabled.
+ *
+ * Change the value of usermodehelper_disabled (under umhelper_sem locked for
+ * writing) and wakeup tasks waiting for it to change.
  */
-int usermodehelper_disable(void)
+void __usermodehelper_set_disable_depth(enum umh_disable_depth depth)
+{
+	down_write(&umhelper_sem);
+	usermodehelper_disabled = depth;
+	wake_up(&usermodehelper_disabled_waitq);
+	up_write(&umhelper_sem);
+}
+
+/**
+ * __usermodehelper_disable - Prevent new helpers from being started.
+ * @depth: New value to assign to usermodehelper_disabled.
+ *
+ * Set usermodehelper_disabled to @depth and wait for running helpers to exit.
+ */
+int __usermodehelper_disable(enum umh_disable_depth depth)
 {
 	long retval;
 
+	if (!depth)
+		return -EINVAL;
+
 	down_write(&umhelper_sem);
-	usermodehelper_disabled = 1;
+	usermodehelper_disabled = depth;
 	up_write(&umhelper_sem);
 
 	/*
@@ -374,31 +452,10 @@ int usermodehelper_disable(void)
 	if (retval)
 		return 0;
 
-	down_write(&umhelper_sem);
-	usermodehelper_disabled = 0;
-	up_write(&umhelper_sem);
+	__usermodehelper_set_disable_depth(UMH_ENABLED);
 	return -EAGAIN;
 }
 
-/**
- * usermodehelper_enable - allow new helpers to be started again
- */
-void usermodehelper_enable(void)
-{
-	down_write(&umhelper_sem);
-	usermodehelper_disabled = 0;
-	up_write(&umhelper_sem);
-}
-
-/**
- * usermodehelper_is_disabled - check if new helpers are allowed to be started
- */
-bool usermodehelper_is_disabled(void)
-{
-	return usermodehelper_disabled;
-}
-EXPORT_SYMBOL_GPL(usermodehelper_is_disabled);
-
 static void helper_lock(void)
 {
 	atomic_inc(&running_helpers);
diff --git a/kernel/module.c b/kernel/module.c
index 2c932760fd33..78ac6ec1e425 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -105,6 +105,7 @@ struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */
 
 /* Block module loading/unloading? */
 int modules_disabled = 0;
+core_param(nomodule, modules_disabled, bint, 0);
 
 /* Waiting for a module to finish initializing? */
 static DECLARE_WAIT_QUEUE_HEAD(module_wq);
@@ -903,6 +904,36 @@ static ssize_t show_refcnt(struct module_attribute *mattr,
 static struct module_attribute modinfo_refcnt =
 	__ATTR(refcnt, 0444, show_refcnt, NULL);
 
+void __module_get(struct module *module)
+{
+	if (module) {
+		preempt_disable();
+		__this_cpu_inc(module->refptr->incs);
+		trace_module_get(module, _RET_IP_);
+		preempt_enable();
+	}
+}
+EXPORT_SYMBOL(__module_get);
+
+bool try_module_get(struct module *module)
+{
+	bool ret = true;
+
+	if (module) {
+		preempt_disable();
+
+		if (likely(module_is_live(module))) {
+			__this_cpu_inc(module->refptr->incs);
+			trace_module_get(module, _RET_IP_);
+		} else
+			ret = false;
+
+		preempt_enable();
+	}
+	return ret;
+}
+EXPORT_SYMBOL(try_module_get);
+
 void module_put(struct module *module)
 {
 	if (module) {
@@ -2380,8 +2411,7 @@ static int copy_and_check(struct load_info *info,
 		return -ENOEXEC;
 
 	/* Suck in entire file: we'll want most of it. */
-	/* vmalloc barfs on "unusual" numbers.  Check here */
-	if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL)
+	if ((hdr = vmalloc(len)) == NULL)
 		return -ENOMEM;
 
 	if (copy_from_user(hdr, umod, len) != 0) {
@@ -2922,7 +2952,8 @@ static struct module *load_module(void __user *umod,
 	mutex_unlock(&module_mutex);
 
 	/* Module is ready to execute: parsing args may do that. */
-	err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL);
+	err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp,
+			 -32768, 32767, NULL);
 	if (err < 0)
 		goto unlink;
 
diff --git a/kernel/padata.c b/kernel/padata.c
index 6f10eb285ece..89fe3d1b9efb 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -1,6 +1,8 @@
 /*
  * padata.c - generic interface to process data streams in parallel
  *
+ * See Documentation/padata.txt for an api documentation.
+ *
  * Copyright (C) 2008, 2009 secunet Security Networks AG
  * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
  *
@@ -354,13 +356,13 @@ static int padata_setup_cpumasks(struct parallel_data *pd,
 	if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL))
 		return -ENOMEM;
 
-	cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_active_mask);
+	cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask);
 	if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) {
 		free_cpumask_var(pd->cpumask.cbcpu);
 		return -ENOMEM;
 	}
 
-	cpumask_and(pd->cpumask.cbcpu, cbcpumask, cpu_active_mask);
+	cpumask_and(pd->cpumask.cbcpu, cbcpumask, cpu_online_mask);
 	return 0;
 }
 
@@ -564,7 +566,7 @@ EXPORT_SYMBOL(padata_unregister_cpumask_notifier);
 static bool padata_validate_cpumask(struct padata_instance *pinst,
 				    const struct cpumask *cpumask)
 {
-	if (!cpumask_intersects(cpumask, cpu_active_mask)) {
+	if (!cpumask_intersects(cpumask, cpu_online_mask)) {
 		pinst->flags |= PADATA_INVALID;
 		return false;
 	}
@@ -678,7 +680,7 @@ static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
 {
 	struct parallel_data *pd;
 
-	if (cpumask_test_cpu(cpu, cpu_active_mask)) {
+	if (cpumask_test_cpu(cpu, cpu_online_mask)) {
 		pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu,
 				     pinst->cpumask.cbcpu);
 		if (!pd)
@@ -746,6 +748,9 @@ static int __padata_remove_cpu(struct padata_instance *pinst, int cpu)
 			return -ENOMEM;
 
 		padata_replace(pinst, pd);
+
+		cpumask_clear_cpu(cpu, pd->cpumask.cbcpu);
+		cpumask_clear_cpu(cpu, pd->cpumask.pcpu);
 	}
 
 	return 0;
diff --git a/kernel/params.c b/kernel/params.c
index 47f5bf12434a..f37d82631347 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -87,6 +87,8 @@ static int parse_one(char *param,
 		     char *val,
 		     const struct kernel_param *params,
 		     unsigned num_params,
+		     s16 min_level,
+		     s16 max_level,
 		     int (*handle_unknown)(char *param, char *val))
 {
 	unsigned int i;
@@ -95,6 +97,9 @@ static int parse_one(char *param,
 	/* Find parameter */
 	for (i = 0; i < num_params; i++) {
 		if (parameq(param, params[i].name)) {
+			if (params[i].level < min_level
+			    || params[i].level > max_level)
+				return 0;
 			/* No one handled NULL, so do it here. */
 			if (!val && params[i].ops->set != param_set_bool
 			    && params[i].ops->set != param_set_bint)
@@ -174,6 +179,8 @@ int parse_args(const char *name,
 	       char *args,
 	       const struct kernel_param *params,
 	       unsigned num,
+	       s16 min_level,
+	       s16 max_level,
 	       int (*unknown)(char *param, char *val))
 {
 	char *param, *val;
@@ -189,7 +196,8 @@ int parse_args(const char *name,
 
 		args = next_arg(args, &param, &val);
 		irq_was_disabled = irqs_disabled();
-		ret = parse_one(param, val, params, num, unknown);
+		ret = parse_one(param, val, params, num,
+				min_level, max_level, unknown);
 		if (irq_was_disabled && !irqs_disabled()) {
 			printk(KERN_WARNING "parse_args(): option '%s' enabled "
 					"irq's!\n", param);
@@ -297,35 +305,18 @@ EXPORT_SYMBOL(param_ops_charp);
 /* Actually could be a bool or an int, for historical reasons. */
 int param_set_bool(const char *val, const struct kernel_param *kp)
 {
-	bool v;
-	int ret;
-
 	/* No equals means "set"... */
 	if (!val) val = "1";
 
 	/* One of =[yYnN01] */
-	ret = strtobool(val, &v);
-	if (ret)
-		return ret;
-
-	if (kp->flags & KPARAM_ISBOOL)
-		*(bool *)kp->arg = v;
-	else
-		*(int *)kp->arg = v;
-	return 0;
+	return strtobool(val, kp->arg);
 }
 EXPORT_SYMBOL(param_set_bool);
 
 int param_get_bool(char *buffer, const struct kernel_param *kp)
 {
-	bool val;
-	if (kp->flags & KPARAM_ISBOOL)
-		val = *(bool *)kp->arg;
-	else
-		val = *(int *)kp->arg;
-
 	/* Y and N chosen as being relatively non-coder friendly */
-	return sprintf(buffer, "%c", val ? 'Y' : 'N');
+	return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N');
 }
 EXPORT_SYMBOL(param_get_bool);
 
@@ -343,7 +334,6 @@ int param_set_invbool(const char *val, const struct kernel_param *kp)
 	struct kernel_param dummy;
 
 	dummy.arg = &boolval;
-	dummy.flags = KPARAM_ISBOOL;
 	ret = param_set_bool(val, &dummy);
 	if (ret == 0)
 		*(bool *)kp->arg = !boolval;
@@ -372,7 +362,6 @@ int param_set_bint(const char *val, const struct kernel_param *kp)
 	/* Match bool exactly, by re-using it. */
 	boolkp = *kp;
 	boolkp.arg = &v;
-	boolkp.flags |= KPARAM_ISBOOL;
 
 	ret = param_set_bool(val, &boolkp);
 	if (ret == 0)
@@ -393,7 +382,7 @@ static int param_array(const char *name,
 		       unsigned int min, unsigned int max,
 		       void *elem, int elemsize,
 		       int (*set)(const char *, const struct kernel_param *kp),
-		       u16 flags,
+		       s16 level,
 		       unsigned int *num)
 {
 	int ret;
@@ -403,7 +392,7 @@ static int param_array(const char *name,
 	/* Get the name right for errors. */
 	kp.name = name;
 	kp.arg = elem;
-	kp.flags = flags;
+	kp.level = level;
 
 	*num = 0;
 	/* We expect a comma-separated list of values. */
@@ -444,7 +433,7 @@ static int param_array_set(const char *val, const struct kernel_param *kp)
 	unsigned int temp_num;
 
 	return param_array(kp->name, val, 1, arr->max, arr->elem,
-			   arr->elemsize, arr->ops->set, kp->flags,
+			   arr->elemsize, arr->ops->set, kp->level,
 			   arr->num ?: &temp_num);
 }
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 17b232869a04..57bc1fd35b3c 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -15,6 +15,7 @@
 #include <linux/acct.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
+#include <linux/reboot.h>
 
 #define BITS_PER_PAGE		(PAGE_SIZE*8)
 
@@ -183,6 +184,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 		rc = sys_wait4(-1, NULL, __WALL, NULL);
 	} while (rc != -ECHILD);
 
+	if (pid_ns->reboot)
+		current->signal->group_exit_code = pid_ns->reboot;
+
 	acct_exit_ns(pid_ns);
 	return;
 }
@@ -217,6 +221,35 @@ static struct ctl_table pid_ns_ctl_table[] = {
 
 static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
 
+int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
+{
+	if (pid_ns == &init_pid_ns)
+		return 0;
+
+	switch (cmd) {
+	case LINUX_REBOOT_CMD_RESTART2:
+	case LINUX_REBOOT_CMD_RESTART:
+		pid_ns->reboot = SIGHUP;
+		break;
+
+	case LINUX_REBOOT_CMD_POWER_OFF:
+	case LINUX_REBOOT_CMD_HALT:
+		pid_ns->reboot = SIGINT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	read_lock(&tasklist_lock);
+	force_sig(SIGKILL, pid_ns->child_reaper);
+	read_unlock(&tasklist_lock);
+
+	do_exit(0);
+
+	/* Not reached */
+	return 0;
+}
+
 static __init int pid_namespaces_init(void)
 {
 	pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 0a186cfde788..e09dfbfeecee 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -16,7 +16,6 @@
 #include <linux/string.h>
 #include <linux/device.h>
 #include <linux/async.h>
-#include <linux/kmod.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -611,14 +610,10 @@ int hibernate(void)
 	if (error)
 		goto Exit;
 
-	error = usermodehelper_disable();
-	if (error)
-		goto Exit;
-
 	/* Allocate memory management structures */
 	error = create_basic_memory_bitmaps();
 	if (error)
-		goto Enable_umh;
+		goto Exit;
 
 	printk(KERN_INFO "PM: Syncing filesystems ... ");
 	sys_sync();
@@ -661,8 +656,6 @@ int hibernate(void)
 
  Free_bitmaps:
 	free_basic_memory_bitmaps();
- Enable_umh:
-	usermodehelper_enable();
  Exit:
 	pm_notifier_call_chain(PM_POST_HIBERNATION);
 	pm_restore_console();
@@ -777,15 +770,9 @@ static int software_resume(void)
 	if (error)
 		goto close_finish;
 
-	error = usermodehelper_disable();
-	if (error)
-		goto close_finish;
-
 	error = create_basic_memory_bitmaps();
-	if (error) {
-		usermodehelper_enable();
+	if (error)
 		goto close_finish;
-	}
 
 	pr_debug("PM: Preparing processes for restore.\n");
 	error = freeze_processes();
@@ -806,7 +793,6 @@ static int software_resume(void)
 	thaw_processes();
  Done:
 	free_basic_memory_bitmaps();
-	usermodehelper_enable();
  Finish:
 	pm_notifier_call_chain(PM_POST_RESTORE);
 	pm_restore_console();
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 0d2aeb226108..19db29f67558 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -16,6 +16,7 @@
 #include <linux/freezer.h>
 #include <linux/delay.h>
 #include <linux/workqueue.h>
+#include <linux/kmod.h>
 
 /* 
  * Timeout for stopping processes
@@ -122,6 +123,10 @@ int freeze_processes(void)
 {
 	int error;
 
+	error = __usermodehelper_disable(UMH_FREEZING);
+	if (error)
+		return error;
+
 	if (!pm_freezing)
 		atomic_inc(&system_freezing_cnt);
 
@@ -130,6 +135,7 @@ int freeze_processes(void)
 	error = try_to_freeze_tasks(true);
 	if (!error) {
 		printk("done.");
+		__usermodehelper_set_disable_depth(UMH_DISABLED);
 		oom_killer_disable();
 	}
 	printk("\n");
@@ -187,6 +193,8 @@ void thaw_processes(void)
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 
+	usermodehelper_enable();
+
 	schedule();
 	printk("done.\n");
 }
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index d6d6dbd1ecc0..6a031e684026 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -230,6 +230,21 @@ int pm_qos_request_active(struct pm_qos_request *req)
 EXPORT_SYMBOL_GPL(pm_qos_request_active);
 
 /**
+ * pm_qos_work_fn - the timeout handler of pm_qos_update_request_timeout
+ * @work: work struct for the delayed work (timeout)
+ *
+ * This cancels the timeout request by falling back to the default at timeout.
+ */
+static void pm_qos_work_fn(struct work_struct *work)
+{
+	struct pm_qos_request *req = container_of(to_delayed_work(work),
+						  struct pm_qos_request,
+						  work);
+
+	pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
+}
+
+/**
  * pm_qos_add_request - inserts new qos request into the list
  * @req: pointer to a preallocated handle
  * @pm_qos_class: identifies which list of qos request to use
@@ -253,6 +268,7 @@ void pm_qos_add_request(struct pm_qos_request *req,
 		return;
 	}
 	req->pm_qos_class = pm_qos_class;
+	INIT_DELAYED_WORK(&req->work, pm_qos_work_fn);
 	pm_qos_update_target(pm_qos_array[pm_qos_class]->constraints,
 			     &req->node, PM_QOS_ADD_REQ, value);
 }
@@ -279,6 +295,9 @@ void pm_qos_update_request(struct pm_qos_request *req,
 		return;
 	}
 
+	if (delayed_work_pending(&req->work))
+		cancel_delayed_work_sync(&req->work);
+
 	if (new_value != req->node.prio)
 		pm_qos_update_target(
 			pm_qos_array[req->pm_qos_class]->constraints,
@@ -287,6 +306,34 @@ void pm_qos_update_request(struct pm_qos_request *req,
 EXPORT_SYMBOL_GPL(pm_qos_update_request);
 
 /**
+ * pm_qos_update_request_timeout - modifies an existing qos request temporarily.
+ * @req : handle to list element holding a pm_qos request to use
+ * @new_value: defines the temporal qos request
+ * @timeout_us: the effective duration of this qos request in usecs.
+ *
+ * After timeout_us, this qos request is cancelled automatically.
+ */
+void pm_qos_update_request_timeout(struct pm_qos_request *req, s32 new_value,
+				   unsigned long timeout_us)
+{
+	if (!req)
+		return;
+	if (WARN(!pm_qos_request_active(req),
+		 "%s called for unknown object.", __func__))
+		return;
+
+	if (delayed_work_pending(&req->work))
+		cancel_delayed_work_sync(&req->work);
+
+	if (new_value != req->node.prio)
+		pm_qos_update_target(
+			pm_qos_array[req->pm_qos_class]->constraints,
+			&req->node, PM_QOS_UPDATE_REQ, new_value);
+
+	schedule_delayed_work(&req->work, usecs_to_jiffies(timeout_us));
+}
+
+/**
  * pm_qos_remove_request - modifies an existing qos request
  * @req: handle to request list element
  *
@@ -305,6 +352,9 @@ void pm_qos_remove_request(struct pm_qos_request *req)
 		return;
 	}
 
+	if (delayed_work_pending(&req->work))
+		cancel_delayed_work_sync(&req->work);
+
 	pm_qos_update_target(pm_qos_array[req->pm_qos_class]->constraints,
 			     &req->node, PM_QOS_REMOVE_REQ,
 			     PM_QOS_DEFAULT_VALUE);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 88e5c967370d..396d262b8fd0 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -12,7 +12,6 @@
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/init.h>
-#include <linux/kmod.h>
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
@@ -102,17 +101,12 @@ static int suspend_prepare(void)
 	if (error)
 		goto Finish;
 
-	error = usermodehelper_disable();
-	if (error)
-		goto Finish;
-
 	error = suspend_freeze_processes();
 	if (!error)
 		return 0;
 
 	suspend_stats.failed_freeze++;
 	dpm_save_failed_step(SUSPEND_FREEZE);
-	usermodehelper_enable();
  Finish:
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
@@ -259,7 +253,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 static void suspend_finish(void)
 {
 	suspend_thaw_processes();
-	usermodehelper_enable();
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
 }
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 33c4329205af..91b0fd021a95 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -12,7 +12,6 @@
 #include <linux/suspend.h>
 #include <linux/syscalls.h>
 #include <linux/reboot.h>
-#include <linux/kmod.h>
 #include <linux/string.h>
 #include <linux/device.h>
 #include <linux/miscdevice.h>
@@ -222,14 +221,8 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		sys_sync();
 		printk("done.\n");
 
-		error = usermodehelper_disable();
-		if (error)
-			break;
-
 		error = freeze_processes();
-		if (error)
-			usermodehelper_enable();
-		else
+		if (!error)
 			data->frozen = 1;
 		break;
 
@@ -238,7 +231,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 			break;
 		pm_restore_gfp_mask();
 		thaw_processes();
-		usermodehelper_enable();
 		data->frozen = 0;
 		break;
 
diff --git a/kernel/rwsem.c b/kernel/rwsem.c
index b152f74f02de..6850f53e02d8 100644
--- a/kernel/rwsem.c
+++ b/kernel/rwsem.c
@@ -10,7 +10,6 @@
 #include <linux/export.h>
 #include <linux/rwsem.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 503d6426126d..4603b9d8f30a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -73,6 +73,7 @@
 #include <linux/init_task.h>
 #include <linux/binfmts.h>
 
+#include <asm/switch_to.h>
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
 #include <asm/mutex.h>
@@ -1264,29 +1265,59 @@ EXPORT_SYMBOL_GPL(kick_process);
  */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
-	int dest_cpu;
 	const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
+	enum { cpuset, possible, fail } state = cpuset;
+	int dest_cpu;
 
 	/* Look for allowed, online CPU in same node. */
-	for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
+	for_each_cpu(dest_cpu, nodemask) {
+		if (!cpu_online(dest_cpu))
+			continue;
+		if (!cpu_active(dest_cpu))
+			continue;
 		if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
 			return dest_cpu;
+	}
+
+	for (;;) {
+		/* Any allowed, online CPU? */
+		for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
+			if (!cpu_online(dest_cpu))
+				continue;
+			if (!cpu_active(dest_cpu))
+				continue;
+			goto out;
+		}
 
-	/* Any allowed, online CPU? */
-	dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask);
-	if (dest_cpu < nr_cpu_ids)
-		return dest_cpu;
+		switch (state) {
+		case cpuset:
+			/* No more Mr. Nice Guy. */
+			cpuset_cpus_allowed_fallback(p);
+			state = possible;
+			break;
 
-	/* No more Mr. Nice Guy. */
-	dest_cpu = cpuset_cpus_allowed_fallback(p);
-	/*
-	 * Don't tell them about moving exiting tasks or
-	 * kernel threads (both mm NULL), since they never
-	 * leave kernel.
-	 */
-	if (p->mm && printk_ratelimit()) {
-		printk_sched("process %d (%s) no longer affine to cpu%d\n",
-				task_pid_nr(p), p->comm, cpu);
+		case possible:
+			do_set_cpus_allowed(p, cpu_possible_mask);
+			state = fail;
+			break;
+
+		case fail:
+			BUG();
+			break;
+		}
+	}
+
+out:
+	if (state != cpuset) {
+		/*
+		 * Don't tell them about moving exiting tasks or
+		 * kernel threads (both mm NULL), since they never
+		 * leave kernel.
+		 */
+		if (p->mm && printk_ratelimit()) {
+			printk_sched("process %d (%s) no longer affine to cpu%d\n",
+					task_pid_nr(p), p->comm, cpu);
+		}
 	}
 
 	return dest_cpu;
@@ -1933,6 +1964,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	local_irq_enable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
 	finish_lock_switch(rq, prev);
+	finish_arch_post_lock_switch();
 
 	fire_sched_in_preempt_notifiers(current);
 	if (mm)
@@ -3070,8 +3102,6 @@ EXPORT_SYMBOL(sub_preempt_count);
  */
 static noinline void __schedule_bug(struct task_struct *prev)
 {
-	struct pt_regs *regs = get_irq_regs();
-
 	if (oops_in_progress)
 		return;
 
@@ -3082,11 +3112,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 	print_modules();
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
-
-	if (regs)
-		show_regs(regs);
-	else
-		dump_stack();
+	dump_stack();
 }
 
 /*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 94340c7544a9..0d97ebdc58f0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -416,8 +416,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-				   unsigned long delta_exec);
+static __always_inline
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec);
 
 /**************************************************************
  * Scheduling class tree data structure manipulation methods:
@@ -1162,7 +1162,7 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		__clear_buddies_skip(se);
 }
 
-static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
+static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
@@ -1546,8 +1546,8 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
 		resched_task(rq_of(cfs_rq)->curr);
 }
 
-static __always_inline void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-						   unsigned long delta_exec)
+static __always_inline
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec)
 {
 	if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
 		return;
@@ -2073,11 +2073,11 @@ void unthrottle_offline_cfs_rqs(struct rq *rq)
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-				     unsigned long delta_exec) {}
+static __always_inline
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec) {}
 static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
-static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
 {
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index b60dad720173..44af55e6d5d0 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1428,7 +1428,7 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 next_idx:
 		if (idx >= MAX_RT_PRIO)
 			continue;
-		if (next && next->prio < idx)
+		if (next && next->prio <= idx)
 			continue;
 		list_for_each_entry(rt_se, array->queue + idx, run_list) {
 			struct task_struct *p;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 42b1f304b044..fb3acba4d52e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -681,6 +681,9 @@ static inline int task_running(struct rq *rq, struct task_struct *p)
 #ifndef finish_arch_switch
 # define finish_arch_switch(prev)	do { } while (0)
 #endif
+#ifndef finish_arch_post_lock_switch
+# define finish_arch_post_lock_switch()	do { } while (0)
+#endif
 
 #ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
diff --git a/kernel/signal.c b/kernel/signal.c
index d523da02dd14..17afcaf582d0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -36,6 +36,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/siginfo.h>
+#include <asm/cacheflush.h>
 #include "audit.h"	/* audit_signal_info() */
 
 /*
diff --git a/kernel/smp.c b/kernel/smp.c
index db197d60489b..2f8b10ecf759 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -701,3 +701,93 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait)
 	return ret;
 }
 EXPORT_SYMBOL(on_each_cpu);
+
+/**
+ * on_each_cpu_mask(): Run a function on processors specified by
+ * cpumask, which may include the local processor.
+ * @mask: The set of cpus to run on (only runs on online subset).
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
+ *
+ * If @wait is true, then returns once @func has returned.
+ *
+ * You must not call this function with disabled interrupts or
+ * from a hardware interrupt handler or from a bottom half handler.
+ */
+void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
+			void *info, bool wait)
+{
+	int cpu = get_cpu();
+
+	smp_call_function_many(mask, func, info, wait);
+	if (cpumask_test_cpu(cpu, mask)) {
+		local_irq_disable();
+		func(info);
+		local_irq_enable();
+	}
+	put_cpu();
+}
+EXPORT_SYMBOL(on_each_cpu_mask);
+
+/*
+ * on_each_cpu_cond(): Call a function on each processor for which
+ * the supplied function cond_func returns true, optionally waiting
+ * for all the required CPUs to finish. This may include the local
+ * processor.
+ * @cond_func:	A callback function that is passed a cpu id and
+ *		the the info parameter. The function is called
+ *		with preemption disabled. The function should
+ *		return a blooean value indicating whether to IPI
+ *		the specified CPU.
+ * @func:	The function to run on all applicable CPUs.
+ *		This must be fast and non-blocking.
+ * @info:	An arbitrary pointer to pass to both functions.
+ * @wait:	If true, wait (atomically) until function has
+ *		completed on other CPUs.
+ * @gfp_flags:	GFP flags to use when allocating the cpumask
+ *		used internally by the function.
+ *
+ * The function might sleep if the GFP flags indicates a non
+ * atomic allocation is allowed.
+ *
+ * Preemption is disabled to protect against CPUs going offline but not online.
+ * CPUs going online during the call will not be seen or sent an IPI.
+ *
+ * You must not call this function with disabled interrupts or
+ * from a hardware interrupt handler or from a bottom half handler.
+ */
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+			smp_call_func_t func, void *info, bool wait,
+			gfp_t gfp_flags)
+{
+	cpumask_var_t cpus;
+	int cpu, ret;
+
+	might_sleep_if(gfp_flags & __GFP_WAIT);
+
+	if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
+		preempt_disable();
+		for_each_online_cpu(cpu)
+			if (cond_func(cpu, info))
+				cpumask_set_cpu(cpu, cpus);
+		on_each_cpu_mask(cpus, func, info, wait);
+		preempt_enable();
+		free_cpumask_var(cpus);
+	} else {
+		/*
+		 * No free cpumask, bother. No matter, we'll
+		 * just have to IPI them one by one.
+		 */
+		preempt_disable();
+		for_each_online_cpu(cpu)
+			if (cond_func(cpu, info)) {
+				ret = smp_call_function_single(cpu, func,
+								info, wait);
+				WARN_ON_ONCE(!ret);
+			}
+		preempt_enable();
+	}
+}
+EXPORT_SYMBOL(on_each_cpu_cond);
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 84c7d96918bf..5cdd8065a3ce 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -163,7 +163,7 @@ void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)
 EXPORT_SYMBOL(_raw_spin_lock_bh);
 #endif
 
-#ifndef CONFIG_INLINE_SPIN_UNLOCK
+#ifdef CONFIG_UNINLINE_SPIN_UNLOCK
 void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)
 {
 	__raw_spin_unlock(lock);
diff --git a/kernel/sys.c b/kernel/sys.c
index 9eb7fcab8df6..e7006eb6c1e4 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -444,6 +444,15 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	                magic2 != LINUX_REBOOT_MAGIC2C))
 		return -EINVAL;
 
+	/*
+	 * If pid namespaces are enabled and the current task is in a child
+	 * pid_namespace, the command is handled by reboot_pid_ns() which will
+	 * call do_exit().
+	 */
+	ret = reboot_pid_ns(task_active_pid_ns(current), cmd);
+	if (ret)
+		return ret;
+
 	/* Instead of trying to make the power_off code look like
 	 * halt when pm_power_off is not set do it the easy way.
 	 */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d48ff4fd44c3..52b3a06a02f8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -23,6 +23,7 @@
 #include <linux/swap.h>
 #include <linux/slab.h>
 #include <linux/sysctl.h>
+#include <linux/bitmap.h>
 #include <linux/signal.h>
 #include <linux/printk.h>
 #include <linux/proc_fs.h>
@@ -68,6 +69,9 @@
 #include <asm/stacktrace.h>
 #include <asm/io.h>
 #endif
+#ifdef CONFIG_SPARC
+#include <asm/setup.h>
+#endif
 #ifdef CONFIG_BSD_PROCESS_ACCT
 #include <linux/acct.h>
 #endif
@@ -142,7 +146,6 @@ static const int cap_last_cap = CAP_LAST_CAP;
 #include <linux/inotify.h>
 #endif
 #ifdef CONFIG_SPARC
-#include <asm/system.h>
 #endif
 
 #ifdef CONFIG_SPARC64
@@ -2393,9 +2396,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write,
 				}
 			}
 
-			while (val_a <= val_b)
-				set_bit(val_a++, tmp_bitmap);
-
+			bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1);
 			first = 0;
 			proc_skip_char(&kbuf, &left, '\n');
 		}
@@ -2438,8 +2439,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write,
 			if (*ppos)
 				bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len);
 			else
-				memcpy(bitmap, tmp_bitmap,
-					BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long));
+				bitmap_copy(bitmap, tmp_bitmap, bitmap_len);
 		}
 		kfree(tmp_bitmap);
 		*lenp -= left;
diff --git a/kernel/time.c b/kernel/time.c
index 73e416db0a1e..ba744cf80696 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -163,7 +163,6 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 		return error;
 
 	if (tz) {
-		/* SMP safe, global irq locking makes it work. */
 		sys_tz = *tz;
 		update_vsyscall_tz();
 		if (firsttime) {
@@ -173,12 +172,7 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 		}
 	}
 	if (tv)
-	{
-		/* SMP safe, again the code in arch/foo/time.c should
-		 * globally block out interrupts when it runs.
-		 */
 		return do_settimeofday(tv);
-	}
 	return 0;
 }
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 8a46f5d64504..8a538c55fc7b 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -96,6 +96,11 @@ static int alarmtimer_rtc_add_device(struct device *dev,
 	return 0;
 }
 
+static inline void alarmtimer_rtc_timer_init(void)
+{
+	rtc_timer_init(&rtctimer, NULL, NULL);
+}
+
 static struct class_interface alarmtimer_rtc_interface = {
 	.add_dev = &alarmtimer_rtc_add_device,
 };
@@ -117,6 +122,7 @@ static inline struct rtc_device *alarmtimer_get_rtcdev(void)
 #define rtcdev (NULL)
 static inline int alarmtimer_rtc_interface_setup(void) { return 0; }
 static inline void alarmtimer_rtc_interface_remove(void) { }
+static inline void alarmtimer_rtc_timer_init(void) { }
 #endif
 
 /**
@@ -783,6 +789,8 @@ static int __init alarmtimer_init(void)
 		.nsleep		= alarm_timer_nsleep,
 	};
 
+	alarmtimer_rtc_timer_init();
+
 	posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock);
 	posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock);
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index a45ca167ab24..c9583382141a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -500,7 +500,7 @@ static u32 clocksource_max_adjustment(struct clocksource *cs)
 {
 	u64 ret;
 	/*
-	 * We won't try to correct for more then 11% adjustments (110,000 ppm),
+	 * We won't try to correct for more than 11% adjustments (110,000 ppm),
 	 */
 	ret = (u64)cs->mult * 11;
 	do_div(ret,100);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 6e039b144daf..f03fd83b170b 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -34,8 +34,6 @@ unsigned long			tick_nsec;
 static u64			tick_length;
 static u64			tick_length_base;
 
-static struct hrtimer		leap_timer;
-
 #define MAX_TICKADJ		500LL		/* usecs */
 #define MAX_TICKADJ_SCALED \
 	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
@@ -381,70 +379,63 @@ u64 ntp_tick_length(void)
 
 
 /*
- * Leap second processing. If in leap-insert state at the end of the
- * day, the system clock is set back one second; if in leap-delete
- * state, the system clock is set ahead one second.
+ * this routine handles the overflow of the microsecond field
+ *
+ * The tricky bits of code to handle the accurate clock support
+ * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
+ * They were originally developed for SUN and DEC kernels.
+ * All the kudos should go to Dave for this stuff.
+ *
+ * Also handles leap second processing, and returns leap offset
  */
-static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
+int second_overflow(unsigned long secs)
 {
-	enum hrtimer_restart res = HRTIMER_NORESTART;
-	unsigned long flags;
+	s64 delta;
 	int leap = 0;
+	unsigned long flags;
 
 	spin_lock_irqsave(&ntp_lock, flags);
+
+	/*
+	 * Leap second processing. If in leap-insert state at the end of the
+	 * day, the system clock is set back one second; if in leap-delete
+	 * state, the system clock is set ahead one second.
+	 */
 	switch (time_state) {
 	case TIME_OK:
+		if (time_status & STA_INS)
+			time_state = TIME_INS;
+		else if (time_status & STA_DEL)
+			time_state = TIME_DEL;
 		break;
 	case TIME_INS:
-		leap = -1;
-		time_state = TIME_OOP;
-		printk(KERN_NOTICE
-			"Clock: inserting leap second 23:59:60 UTC\n");
-		hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
-		res = HRTIMER_RESTART;
+		if (secs % 86400 == 0) {
+			leap = -1;
+			time_state = TIME_OOP;
+			printk(KERN_NOTICE
+				"Clock: inserting leap second 23:59:60 UTC\n");
+		}
 		break;
 	case TIME_DEL:
-		leap = 1;
-		time_tai--;
-		time_state = TIME_WAIT;
-		printk(KERN_NOTICE
-			"Clock: deleting leap second 23:59:59 UTC\n");
+		if ((secs + 1) % 86400 == 0) {
+			leap = 1;
+			time_tai--;
+			time_state = TIME_WAIT;
+			printk(KERN_NOTICE
+				"Clock: deleting leap second 23:59:59 UTC\n");
+		}
 		break;
 	case TIME_OOP:
 		time_tai++;
 		time_state = TIME_WAIT;
-		/* fall through */
+		break;
+
 	case TIME_WAIT:
 		if (!(time_status & (STA_INS | STA_DEL)))
 			time_state = TIME_OK;
 		break;
 	}
-	spin_unlock_irqrestore(&ntp_lock, flags);
 
-	/*
-	 * We have to call this outside of the ntp_lock to keep
-	 * the proper locking hierarchy
-	 */
-	if (leap)
-		timekeeping_leap_insert(leap);
-
-	return res;
-}
-
-/*
- * this routine handles the overflow of the microsecond field
- *
- * The tricky bits of code to handle the accurate clock support
- * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
- * They were originally developed for SUN and DEC kernels.
- * All the kudos should go to Dave for this stuff.
- */
-void second_overflow(void)
-{
-	s64 delta;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ntp_lock, flags);
 
 	/* Bump the maxerror field */
 	time_maxerror += MAXFREQ / NSEC_PER_USEC;
@@ -481,15 +472,17 @@ void second_overflow(void)
 	tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
 							 << NTP_SCALE_SHIFT;
 	time_adjust = 0;
+
+
+
 out:
 	spin_unlock_irqrestore(&ntp_lock, flags);
+
+	return leap;
 }
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
 
-/* Disable the cmos update - used by virtualization and embedded */
-int no_sync_cmos_clock  __read_mostly;
-
 static void sync_cmos_clock(struct work_struct *work);
 
 static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
@@ -536,35 +529,13 @@ static void sync_cmos_clock(struct work_struct *work)
 
 static void notify_cmos_timer(void)
 {
-	if (!no_sync_cmos_clock)
-		schedule_delayed_work(&sync_cmos_work, 0);
+	schedule_delayed_work(&sync_cmos_work, 0);
 }
 
 #else
 static inline void notify_cmos_timer(void) { }
 #endif
 
-/*
- * Start the leap seconds timer:
- */
-static inline void ntp_start_leap_timer(struct timespec *ts)
-{
-	long now = ts->tv_sec;
-
-	if (time_status & STA_INS) {
-		time_state = TIME_INS;
-		now += 86400 - now % 86400;
-		hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
-
-		return;
-	}
-
-	if (time_status & STA_DEL) {
-		time_state = TIME_DEL;
-		now += 86400 - (now + 1) % 86400;
-		hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
-	}
-}
 
 /*
  * Propagate a new txc->status value into the NTP state:
@@ -589,22 +560,6 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts)
 	time_status &= STA_RONLY;
 	time_status |= txc->status & ~STA_RONLY;
 
-	switch (time_state) {
-	case TIME_OK:
-		ntp_start_leap_timer(ts);
-		break;
-	case TIME_INS:
-	case TIME_DEL:
-		time_state = TIME_OK;
-		ntp_start_leap_timer(ts);
-	case TIME_WAIT:
-		if (!(time_status & (STA_INS | STA_DEL)))
-			time_state = TIME_OK;
-		break;
-	case TIME_OOP:
-		hrtimer_restart(&leap_timer);
-		break;
-	}
 }
 /*
  * Called with the xtime lock held, so we can access and modify
@@ -686,9 +641,6 @@ int do_adjtimex(struct timex *txc)
 		    (txc->tick <  900000/USER_HZ ||
 		     txc->tick > 1100000/USER_HZ))
 			return -EINVAL;
-
-		if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
-			hrtimer_cancel(&leap_timer);
 	}
 
 	if (txc->modes & ADJ_SETOFFSET) {
@@ -1010,6 +962,4 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup);
 void __init ntp_init(void)
 {
 	ntp_clear();
-	hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	leap_timer.function = ntp_leap_second;
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 15be32e19c6e..d66b21308f7c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -184,18 +184,6 @@ static void timekeeping_update(bool clearntp)
 }
 
 
-void timekeeping_leap_insert(int leapsecond)
-{
-	unsigned long flags;
-
-	write_seqlock_irqsave(&timekeeper.lock, flags);
-	timekeeper.xtime.tv_sec += leapsecond;
-	timekeeper.wall_to_monotonic.tv_sec -= leapsecond;
-	timekeeping_update(false);
-	write_sequnlock_irqrestore(&timekeeper.lock, flags);
-
-}
-
 /**
  * timekeeping_forward_now - update clock to the current time
  *
@@ -448,9 +436,12 @@ EXPORT_SYMBOL(timekeeping_inject_offset);
 static int change_clocksource(void *data)
 {
 	struct clocksource *new, *old;
+	unsigned long flags;
 
 	new = (struct clocksource *) data;
 
+	write_seqlock_irqsave(&timekeeper.lock, flags);
+
 	timekeeping_forward_now();
 	if (!new->enable || new->enable(new) == 0) {
 		old = timekeeper.clock;
@@ -458,6 +449,10 @@ static int change_clocksource(void *data)
 		if (old->disable)
 			old->disable(old);
 	}
+	timekeeping_update(true);
+
+	write_sequnlock_irqrestore(&timekeeper.lock, flags);
+
 	return 0;
 }
 
@@ -827,7 +822,7 @@ static void timekeeping_adjust(s64 offset)
 	int adj;
 
 	/*
-	 * The point of this is to check if the error is greater then half
+	 * The point of this is to check if the error is greater than half
 	 * an interval.
 	 *
 	 * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
@@ -835,7 +830,7 @@ static void timekeeping_adjust(s64 offset)
 	 * Note we subtract one in the shift, so that error is really error*2.
 	 * This "saves" dividing(shifting) interval twice, but keeps the
 	 * (error > interval) comparison as still measuring if error is
-	 * larger then half an interval.
+	 * larger than half an interval.
 	 *
 	 * Note: It does not "save" on aggravation when reading the code.
 	 */
@@ -843,7 +838,7 @@ static void timekeeping_adjust(s64 offset)
 	if (error > interval) {
 		/*
 		 * We now divide error by 4(via shift), which checks if
-		 * the error is greater then twice the interval.
+		 * the error is greater than twice the interval.
 		 * If it is greater, we need a bigadjust, if its smaller,
 		 * we can adjust by 1.
 		 */
@@ -874,13 +869,15 @@ static void timekeeping_adjust(s64 offset)
 	} else /* No adjustment needed */
 		return;
 
-	WARN_ONCE(timekeeper.clock->maxadj &&
-			(timekeeper.mult + adj > timekeeper.clock->mult +
-						timekeeper.clock->maxadj),
-			"Adjusting %s more then 11%% (%ld vs %ld)\n",
+	if (unlikely(timekeeper.clock->maxadj &&
+			(timekeeper.mult + adj >
+			timekeeper.clock->mult + timekeeper.clock->maxadj))) {
+		printk_once(KERN_WARNING
+			"Adjusting %s more than 11%% (%ld vs %ld)\n",
 			timekeeper.clock->name, (long)timekeeper.mult + adj,
 			(long)timekeeper.clock->mult +
 				timekeeper.clock->maxadj);
+	}
 	/*
 	 * So the following can be confusing.
 	 *
@@ -952,7 +949,7 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 	u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
 	u64 raw_nsecs;
 
-	/* If the offset is smaller then a shifted interval, do nothing */
+	/* If the offset is smaller than a shifted interval, do nothing */
 	if (offset < timekeeper.cycle_interval<<shift)
 		return offset;
 
@@ -962,9 +959,11 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 
 	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
 	while (timekeeper.xtime_nsec >= nsecps) {
+		int leap;
 		timekeeper.xtime_nsec -= nsecps;
 		timekeeper.xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(timekeeper.xtime.tv_sec);
+		timekeeper.xtime.tv_sec += leap;
 	}
 
 	/* Accumulate raw time */
@@ -1018,13 +1017,13 @@ static void update_wall_time(void)
 	 * With NO_HZ we may have to accumulate many cycle_intervals
 	 * (think "ticks") worth of time at once. To do this efficiently,
 	 * we calculate the largest doubling multiple of cycle_intervals
-	 * that is smaller then the offset. We then accumulate that
+	 * that is smaller than the offset.  We then accumulate that
 	 * chunk in one go, and then try to consume the next smaller
 	 * doubled multiple.
 	 */
 	shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
 	shift = max(0, shift);
-	/* Bound shift to one less then what overflows tick_length */
+	/* Bound shift to one less than what overflows tick_length */
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= timekeeper.cycle_interval) {
@@ -1072,12 +1071,14 @@ static void update_wall_time(void)
 
 	/*
 	 * Finally, make sure that after the rounding
-	 * xtime.tv_nsec isn't larger then NSEC_PER_SEC
+	 * xtime.tv_nsec isn't larger than NSEC_PER_SEC
 	 */
 	if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) {
+		int leap;
 		timekeeper.xtime.tv_nsec -= NSEC_PER_SEC;
 		timekeeper.xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(timekeeper.xtime.tv_sec);
+		timekeeper.xtime.tv_sec += leap;
 	}
 
 	timekeeping_update(false);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index cd3134510f3d..a1d2849f2473 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -141,7 +141,7 @@ if FTRACE
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE
+	select FRAME_POINTER if !ARM_UNWIND && !PPC && !S390 && !MICROBLAZE
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index cdea7b56b0c9..c0bd0308741c 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -311,13 +311,6 @@ int blk_trace_remove(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_trace_remove);
 
-static int blk_dropped_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-
-	return 0;
-}
-
 static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
 				size_t count, loff_t *ppos)
 {
@@ -331,18 +324,11 @@ static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
 
 static const struct file_operations blk_dropped_fops = {
 	.owner =	THIS_MODULE,
-	.open =		blk_dropped_open,
+	.open =		simple_open,
 	.read =		blk_dropped_read,
 	.llseek =	default_llseek,
 };
 
-static int blk_msg_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-
-	return 0;
-}
-
 static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
 				size_t count, loff_t *ppos)
 {
@@ -371,7 +357,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
 
 static const struct file_operations blk_msg_fops = {
 	.owner =	THIS_MODULE,
-	.open =		blk_msg_open,
+	.open =		simple_open,
 	.write =	blk_msg_write,
 	.llseek =	noop_llseek,
 };
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 867bd1dd2dd0..0fa92f677c92 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -249,7 +249,8 @@ static void update_ftrace_function(void)
 #else
 	__ftrace_trace_function = func;
 #endif
-	ftrace_trace_function = ftrace_test_stop_func;
+	ftrace_trace_function =
+		(func == ftrace_stub) ? func : ftrace_test_stop_func;
 #endif
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f5b7b5c1195b..cf8d11e91efd 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -154,33 +154,10 @@ enum {
 
 static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
 
-#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
-
-/**
- * tracing_on - enable all tracing buffers
- *
- * This function enables all tracing buffers that may have been
- * disabled with tracing_off.
- */
-void tracing_on(void)
-{
-	set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
-}
-EXPORT_SYMBOL_GPL(tracing_on);
+/* Used for individual buffers (after the counter) */
+#define RB_BUFFER_OFF		(1 << 20)
 
-/**
- * tracing_off - turn off all tracing buffers
- *
- * This function stops all tracing buffers from recording data.
- * It does not disable any overhead the tracers themselves may
- * be causing. This function simply causes all recording to
- * the ring buffers to fail.
- */
-void tracing_off(void)
-{
-	clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
-}
-EXPORT_SYMBOL_GPL(tracing_off);
+#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
 
 /**
  * tracing_off_permanent - permanently disable ring buffers
@@ -193,15 +170,6 @@ void tracing_off_permanent(void)
 	set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
 }
 
-/**
- * tracing_is_on - show state of ring buffers enabled
- */
-int tracing_is_on(void)
-{
-	return ring_buffer_flags == RB_BUFFERS_ON;
-}
-EXPORT_SYMBOL_GPL(tracing_is_on);
-
 #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
 #define RB_ALIGNMENT		4U
 #define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
@@ -2619,6 +2587,63 @@ void ring_buffer_record_enable(struct ring_buffer *buffer)
 EXPORT_SYMBOL_GPL(ring_buffer_record_enable);
 
 /**
+ * ring_buffer_record_off - stop all writes into the buffer
+ * @buffer: The ring buffer to stop writes to.
+ *
+ * This prevents all writes to the buffer. Any attempt to write
+ * to the buffer after this will fail and return NULL.
+ *
+ * This is different than ring_buffer_record_disable() as
+ * it works like an on/off switch, where as the disable() verison
+ * must be paired with a enable().
+ */
+void ring_buffer_record_off(struct ring_buffer *buffer)
+{
+	unsigned int rd;
+	unsigned int new_rd;
+
+	do {
+		rd = atomic_read(&buffer->record_disabled);
+		new_rd = rd | RB_BUFFER_OFF;
+	} while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_record_off);
+
+/**
+ * ring_buffer_record_on - restart writes into the buffer
+ * @buffer: The ring buffer to start writes to.
+ *
+ * This enables all writes to the buffer that was disabled by
+ * ring_buffer_record_off().
+ *
+ * This is different than ring_buffer_record_enable() as
+ * it works like an on/off switch, where as the enable() verison
+ * must be paired with a disable().
+ */
+void ring_buffer_record_on(struct ring_buffer *buffer)
+{
+	unsigned int rd;
+	unsigned int new_rd;
+
+	do {
+		rd = atomic_read(&buffer->record_disabled);
+		new_rd = rd & ~RB_BUFFER_OFF;
+	} while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_record_on);
+
+/**
+ * ring_buffer_record_is_on - return true if the ring buffer can write
+ * @buffer: The ring buffer to see if write is enabled
+ *
+ * Returns true if the ring buffer is in a state that it accepts writes.
+ */
+int ring_buffer_record_is_on(struct ring_buffer *buffer)
+{
+	return !atomic_read(&buffer->record_disabled);
+}
+
+/**
  * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
  * @buffer: The ring buffer to stop writes to.
  * @cpu: The CPU buffer to stop
@@ -4039,68 +4064,6 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
-#ifdef CONFIG_TRACING
-static ssize_t
-rb_simple_read(struct file *filp, char __user *ubuf,
-	       size_t cnt, loff_t *ppos)
-{
-	unsigned long *p = filp->private_data;
-	char buf[64];
-	int r;
-
-	if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
-		r = sprintf(buf, "permanently disabled\n");
-	else
-		r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
-
-	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
-static ssize_t
-rb_simple_write(struct file *filp, const char __user *ubuf,
-		size_t cnt, loff_t *ppos)
-{
-	unsigned long *p = filp->private_data;
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
-	if (ret)
-		return ret;
-
-	if (val)
-		set_bit(RB_BUFFERS_ON_BIT, p);
-	else
-		clear_bit(RB_BUFFERS_ON_BIT, p);
-
-	(*ppos)++;
-
-	return cnt;
-}
-
-static const struct file_operations rb_simple_fops = {
-	.open		= tracing_open_generic,
-	.read		= rb_simple_read,
-	.write		= rb_simple_write,
-	.llseek		= default_llseek,
-};
-
-
-static __init int rb_init_debugfs(void)
-{
-	struct dentry *d_tracer;
-
-	d_tracer = tracing_init_dentry();
-
-	trace_create_file("tracing_on", 0644, d_tracer,
-			    &ring_buffer_flags, &rb_simple_fops);
-
-	return 0;
-}
-
-fs_initcall(rb_init_debugfs);
-#endif
-
 #ifdef CONFIG_HOTPLUG_CPU
 static int rb_cpu_notify(struct notifier_block *self,
 			 unsigned long action, void *hcpu)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 10d5503f0d04..ed7b5d1e12f4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -36,6 +36,7 @@
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
+#include <linux/nmi.h>
 #include <linux/fs.h>
 
 #include "trace.h"
@@ -352,6 +353,59 @@ static void wakeup_work_handler(struct work_struct *work)
 static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler);
 
 /**
+ * tracing_on - enable tracing buffers
+ *
+ * This function enables tracing buffers that may have been
+ * disabled with tracing_off.
+ */
+void tracing_on(void)
+{
+	if (global_trace.buffer)
+		ring_buffer_record_on(global_trace.buffer);
+	/*
+	 * This flag is only looked at when buffers haven't been
+	 * allocated yet. We don't really care about the race
+	 * between setting this flag and actually turning
+	 * on the buffer.
+	 */
+	global_trace.buffer_disabled = 0;
+}
+EXPORT_SYMBOL_GPL(tracing_on);
+
+/**
+ * tracing_off - turn off tracing buffers
+ *
+ * This function stops the tracing buffers from recording data.
+ * It does not disable any overhead the tracers themselves may
+ * be causing. This function simply causes all recording to
+ * the ring buffers to fail.
+ */
+void tracing_off(void)
+{
+	if (global_trace.buffer)
+		ring_buffer_record_on(global_trace.buffer);
+	/*
+	 * This flag is only looked at when buffers haven't been
+	 * allocated yet. We don't really care about the race
+	 * between setting this flag and actually turning
+	 * on the buffer.
+	 */
+	global_trace.buffer_disabled = 1;
+}
+EXPORT_SYMBOL_GPL(tracing_off);
+
+/**
+ * tracing_is_on - show state of ring buffers enabled
+ */
+int tracing_is_on(void)
+{
+	if (global_trace.buffer)
+		return ring_buffer_record_is_on(global_trace.buffer);
+	return !global_trace.buffer_disabled;
+}
+EXPORT_SYMBOL_GPL(tracing_is_on);
+
+/**
  * trace_wake_up - wake up tasks waiting for trace input
  *
  * Schedules a delayed work to wake up any task that is blocked on the
@@ -1644,6 +1698,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 	int cpu_file = iter->cpu_file;
 	u64 next_ts = 0, ts;
 	int next_cpu = -1;
+	int next_size = 0;
 	int cpu;
 
 	/*
@@ -1675,9 +1730,12 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 			next_cpu = cpu;
 			next_ts = ts;
 			next_lost = lost_events;
+			next_size = iter->ent_size;
 		}
 	}
 
+	iter->ent_size = next_size;
+
 	if (ent_cpu)
 		*ent_cpu = next_cpu;
 
@@ -4567,6 +4625,55 @@ static __init void create_trace_options_dir(void)
 		create_trace_option_core_file(trace_options[i], i);
 }
 
+static ssize_t
+rb_simple_read(struct file *filp, char __user *ubuf,
+	       size_t cnt, loff_t *ppos)
+{
+	struct ring_buffer *buffer = filp->private_data;
+	char buf[64];
+	int r;
+
+	if (buffer)
+		r = ring_buffer_record_is_on(buffer);
+	else
+		r = 0;
+
+	r = sprintf(buf, "%d\n", r);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+rb_simple_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos)
+{
+	struct ring_buffer *buffer = filp->private_data;
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	if (buffer) {
+		if (val)
+			ring_buffer_record_on(buffer);
+		else
+			ring_buffer_record_off(buffer);
+	}
+
+	(*ppos)++;
+
+	return cnt;
+}
+
+static const struct file_operations rb_simple_fops = {
+	.open		= tracing_open_generic,
+	.read		= rb_simple_read,
+	.write		= rb_simple_write,
+	.llseek		= default_llseek,
+};
+
 static __init int tracer_init_debugfs(void)
 {
 	struct dentry *d_tracer;
@@ -4626,6 +4733,9 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("trace_clock", 0644, d_tracer, NULL,
 			  &trace_clock_fops);
 
+	trace_create_file("tracing_on", 0644, d_tracer,
+			    global_trace.buffer, &rb_simple_fops);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
@@ -4798,6 +4908,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 			if (ret != TRACE_TYPE_NO_CONSUME)
 				trace_consume(&iter);
 		}
+		touch_nmi_watchdog();
 
 		trace_printk_seq(&iter.seq);
 	}
@@ -4863,6 +4974,8 @@ __init static int tracer_alloc_buffers(void)
 		goto out_free_cpumask;
 	}
 	global_trace.entries = ring_buffer_size(global_trace.buffer);
+	if (global_trace.buffer_disabled)
+		tracing_off();
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 54faec790bc1..95059f091a24 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -154,6 +154,7 @@ struct trace_array {
 	struct ring_buffer	*buffer;
 	unsigned long		entries;
 	int			cpu;
+	int			buffer_disabled;
 	cycle_t			time_start;
 	struct task_struct	*waiter;
 	struct trace_array_cpu	*data[NR_CPUS];
@@ -835,13 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[];
 		     filter)
 #include "trace_entries.h"
 
-#ifdef CONFIG_PERF_EVENTS
 #ifdef CONFIG_FUNCTION_TRACER
 int perf_ftrace_event_register(struct ftrace_event_call *call,
 			       enum trace_reg type, void *data);
 #else
 #define perf_ftrace_event_register NULL
 #endif /* CONFIG_FUNCTION_TRACER */
-#endif /* CONFIG_PERF_EVENTS */
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index d91eb0541b3a..4108e1250ca2 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -166,6 +166,12 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
 
 #define FTRACE_STACK_ENTRIES	8
 
+#ifndef CONFIG_64BIT
+# define IP_FMT "%08lx"
+#else
+# define IP_FMT "%016lx"
+#endif
+
 FTRACE_ENTRY(kernel_stack, stack_entry,
 
 	TRACE_STACK,
@@ -175,8 +181,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 		__dynamic_array(unsigned long,	caller	)
 	),
 
-	F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
-		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+	F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+		 "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+		 "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n",
 		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
 		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
 		 __entry->caller[6], __entry->caller[7]),
@@ -193,8 +200,9 @@ FTRACE_ENTRY(user_stack, userstack_entry,
 		__array(	unsigned long,	caller, FTRACE_STACK_ENTRIES	)
 	),
 
-	F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
-		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+	F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+		 "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+		 "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n",
 		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
 		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
 		 __entry->caller[6], __entry->caller[7]),
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7b46c9bd22ae..3dd15e8bc856 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -162,7 +162,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 #define __dynamic_array(type, item)
 
 #undef F_printk
-#define F_printk(fmt, args...) #fmt ", "  __stringify(args)
+#define F_printk(fmt, args...) __stringify(fmt) ", "  __stringify(args)
 
 #undef FTRACE_ENTRY_REG
 #define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
diff --git a/lib/Kconfig b/lib/Kconfig
index 43359bb1ca90..4a8aba2e5cc0 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -29,6 +29,10 @@ config GENERIC_IOMAP
 	bool
 	select GENERIC_PCI_IOMAP
 
+config GENERIC_IO
+	boolean
+	default n
+
 config CRC_CCITT
 	tristate "CRC-CCITT functions"
 	help
@@ -84,6 +88,10 @@ choice
 	prompt "CRC32 implementation"
 	depends on CRC32
 	default CRC32_SLICEBY8
+	help
+	  This option allows a kernel builder to override the default choice
+	  of CRC32 algorithm.  Choose the default ("slice by 8") unless you
+	  know that you need one of the others.
 
 config CRC32_SLICEBY8
 	bool "Slice by 8 bytes"
@@ -277,6 +285,7 @@ config BTREE
 config HAS_IOMEM
 	boolean
 	depends on !NO_IOMEM
+	select GENERIC_IO
 	default y
 
 config HAS_IOPORT
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index f7af95d304c5..6777153f18f3 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -499,6 +499,7 @@ config RT_MUTEX_TESTER
 config DEBUG_SPINLOCK
 	bool "Spinlock and rw-lock debugging: basic checks"
 	depends on DEBUG_KERNEL
+	select UNINLINE_SPIN_UNLOCK
 	help
 	  Say Y here and build SMP to catch missing spinlock initialization
 	  and certain other kinds of spinlock errors commonly made.  This is
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 0b660118ed91..402a54ac35cb 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -26,18 +26,6 @@ int __next_cpu_nr(int n, const cpumask_t *srcp)
 EXPORT_SYMBOL(__next_cpu_nr);
 #endif
 
-int __any_online_cpu(const cpumask_t *mask)
-{
-	int cpu;
-
-	for_each_cpu(cpu, mask) {
-		if (cpu_online(cpu))
-			break;
-	}
-	return cpu;
-}
-EXPORT_SYMBOL(__any_online_cpu);
-
 /**
  * cpumask_next_and - get the next cpu in *src1p & *src2p
  * @n: the cpu prior to the place to search (ie. return will be > @n)
diff --git a/lib/llist.c b/lib/llist.c
index 8221b3d2fbf0..4a15115e90f8 100644
--- a/lib/llist.c
+++ b/lib/llist.c
@@ -27,7 +27,6 @@
 #include <linux/interrupt.h>
 #include <linux/llist.h>
 
-#include <asm/system.h>
 
 /**
  * llist_add_batch - add several linked entries in batch
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 3e69c2b66c94..86516f5588e3 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -3,6 +3,7 @@
  * Portions Copyright (C) 2001 Christoph Hellwig
  * Copyright (C) 2005 SGI, Christoph Lameter
  * Copyright (C) 2006 Nick Piggin
+ * Copyright (C) 2012 Konstantin Khlebnikov
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -146,6 +147,43 @@ static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag)
 	}
 	return 0;
 }
+
+/**
+ * radix_tree_find_next_bit - find the next set bit in a memory region
+ *
+ * @addr: The address to base the search on
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Unrollable variant of find_next_bit() for constant size arrays.
+ * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero.
+ * Returns next bit offset, or size if nothing found.
+ */
+static __always_inline unsigned long
+radix_tree_find_next_bit(const unsigned long *addr,
+			 unsigned long size, unsigned long offset)
+{
+	if (!__builtin_constant_p(size))
+		return find_next_bit(addr, size, offset);
+
+	if (offset < size) {
+		unsigned long tmp;
+
+		addr += offset / BITS_PER_LONG;
+		tmp = *addr >> (offset % BITS_PER_LONG);
+		if (tmp)
+			return __ffs(tmp) + offset;
+		offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1);
+		while (offset < size) {
+			tmp = *++addr;
+			if (tmp)
+				return __ffs(tmp) + offset;
+			offset += BITS_PER_LONG;
+		}
+	}
+	return size;
+}
+
 /*
  * This assumes that the caller has performed appropriate preallocation, and
  * that the caller has pinned this thread of control to the current CPU.
@@ -613,6 +651,119 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 EXPORT_SYMBOL(radix_tree_tag_get);
 
 /**
+ * radix_tree_next_chunk - find next chunk of slots for iteration
+ *
+ * @root:	radix tree root
+ * @iter:	iterator state
+ * @flags:	RADIX_TREE_ITER_* flags and tag index
+ * Returns:	pointer to chunk first slot, or NULL if iteration is over
+ */
+void **radix_tree_next_chunk(struct radix_tree_root *root,
+			     struct radix_tree_iter *iter, unsigned flags)
+{
+	unsigned shift, tag = flags & RADIX_TREE_ITER_TAG_MASK;
+	struct radix_tree_node *rnode, *node;
+	unsigned long index, offset;
+
+	if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag))
+		return NULL;
+
+	/*
+	 * Catch next_index overflow after ~0UL. iter->index never overflows
+	 * during iterating; it can be zero only at the beginning.
+	 * And we cannot overflow iter->next_index in a single step,
+	 * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG.
+	 */
+	index = iter->next_index;
+	if (!index && iter->index)
+		return NULL;
+
+	rnode = rcu_dereference_raw(root->rnode);
+	if (radix_tree_is_indirect_ptr(rnode)) {
+		rnode = indirect_to_ptr(rnode);
+	} else if (rnode && !index) {
+		/* Single-slot tree */
+		iter->index = 0;
+		iter->next_index = 1;
+		iter->tags = 1;
+		return (void **)&root->rnode;
+	} else
+		return NULL;
+
+restart:
+	shift = (rnode->height - 1) * RADIX_TREE_MAP_SHIFT;
+	offset = index >> shift;
+
+	/* Index outside of the tree */
+	if (offset >= RADIX_TREE_MAP_SIZE)
+		return NULL;
+
+	node = rnode;
+	while (1) {
+		if ((flags & RADIX_TREE_ITER_TAGGED) ?
+				!test_bit(offset, node->tags[tag]) :
+				!node->slots[offset]) {
+			/* Hole detected */
+			if (flags & RADIX_TREE_ITER_CONTIG)
+				return NULL;
+
+			if (flags & RADIX_TREE_ITER_TAGGED)
+				offset = radix_tree_find_next_bit(
+						node->tags[tag],
+						RADIX_TREE_MAP_SIZE,
+						offset + 1);
+			else
+				while (++offset	< RADIX_TREE_MAP_SIZE) {
+					if (node->slots[offset])
+						break;
+				}
+			index &= ~((RADIX_TREE_MAP_SIZE << shift) - 1);
+			index += offset << shift;
+			/* Overflow after ~0UL */
+			if (!index)
+				return NULL;
+			if (offset == RADIX_TREE_MAP_SIZE)
+				goto restart;
+		}
+
+		/* This is leaf-node */
+		if (!shift)
+			break;
+
+		node = rcu_dereference_raw(node->slots[offset]);
+		if (node == NULL)
+			goto restart;
+		shift -= RADIX_TREE_MAP_SHIFT;
+		offset = (index >> shift) & RADIX_TREE_MAP_MASK;
+	}
+
+	/* Update the iterator state */
+	iter->index = index;
+	iter->next_index = (index | RADIX_TREE_MAP_MASK) + 1;
+
+	/* Construct iter->tags bit-mask from node->tags[tag] array */
+	if (flags & RADIX_TREE_ITER_TAGGED) {
+		unsigned tag_long, tag_bit;
+
+		tag_long = offset / BITS_PER_LONG;
+		tag_bit  = offset % BITS_PER_LONG;
+		iter->tags = node->tags[tag][tag_long] >> tag_bit;
+		/* This never happens if RADIX_TREE_TAG_LONGS == 1 */
+		if (tag_long < RADIX_TREE_TAG_LONGS - 1) {
+			/* Pick tags from next element */
+			if (tag_bit)
+				iter->tags |= node->tags[tag][tag_long + 1] <<
+						(BITS_PER_LONG - tag_bit);
+			/* Clip chunk size, here only BITS_PER_LONG tags */
+			iter->next_index = index + BITS_PER_LONG;
+		}
+	}
+
+	return node->slots + offset;
+}
+EXPORT_SYMBOL(radix_tree_next_chunk);
+
+/**
  * radix_tree_range_tag_if_tagged - for each item in given range set given
  *				   tag if item has another tag set
  * @root:		radix tree root
@@ -817,57 +968,6 @@ unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_prev_hole);
 
-static unsigned int
-__lookup(struct radix_tree_node *slot, void ***results, unsigned long *indices,
-	unsigned long index, unsigned int max_items, unsigned long *next_index)
-{
-	unsigned int nr_found = 0;
-	unsigned int shift, height;
-	unsigned long i;
-
-	height = slot->height;
-	if (height == 0)
-		goto out;
-	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
-
-	for ( ; height > 1; height--) {
-		i = (index >> shift) & RADIX_TREE_MAP_MASK;
-		for (;;) {
-			if (slot->slots[i] != NULL)
-				break;
-			index &= ~((1UL << shift) - 1);
-			index += 1UL << shift;
-			if (index == 0)
-				goto out;	/* 32-bit wraparound */
-			i++;
-			if (i == RADIX_TREE_MAP_SIZE)
-				goto out;
-		}
-
-		shift -= RADIX_TREE_MAP_SHIFT;
-		slot = rcu_dereference_raw(slot->slots[i]);
-		if (slot == NULL)
-			goto out;
-	}
-
-	/* Bottom level: grab some items */
-	for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) {
-		if (slot->slots[i]) {
-			results[nr_found] = &(slot->slots[i]);
-			if (indices)
-				indices[nr_found] = index;
-			if (++nr_found == max_items) {
-				index++;
-				goto out;
-			}
-		}
-		index++;
-	}
-out:
-	*next_index = index;
-	return nr_found;
-}
-
 /**
  *	radix_tree_gang_lookup - perform multiple lookup on a radix tree
  *	@root:		radix tree root
@@ -891,48 +991,19 @@ unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 			unsigned long first_index, unsigned int max_items)
 {
-	unsigned long max_index;
-	struct radix_tree_node *node;
-	unsigned long cur_index = first_index;
-	unsigned int ret;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
 
-	node = rcu_dereference_raw(root->rnode);
-	if (!node)
+	if (unlikely(!max_items))
 		return 0;
 
-	if (!radix_tree_is_indirect_ptr(node)) {
-		if (first_index > 0)
-			return 0;
-		results[0] = node;
-		return 1;
-	}
-	node = indirect_to_ptr(node);
-
-	max_index = radix_tree_maxindex(node->height);
-
-	ret = 0;
-	while (ret < max_items) {
-		unsigned int nr_found, slots_found, i;
-		unsigned long next_index;	/* Index of next search */
-
-		if (cur_index > max_index)
-			break;
-		slots_found = __lookup(node, (void ***)results + ret, NULL,
-				cur_index, max_items - ret, &next_index);
-		nr_found = 0;
-		for (i = 0; i < slots_found; i++) {
-			struct radix_tree_node *slot;
-			slot = *(((void ***)results)[ret + i]);
-			if (!slot)
-				continue;
-			results[ret + nr_found] =
-				indirect_to_ptr(rcu_dereference_raw(slot));
-			nr_found++;
-		}
-		ret += nr_found;
-		if (next_index == 0)
+	radix_tree_for_each_slot(slot, root, &iter, first_index) {
+		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		if (!results[ret])
+			continue;
+		if (++ret == max_items)
 			break;
-		cur_index = next_index;
 	}
 
 	return ret;
@@ -962,112 +1033,25 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root,
 			void ***results, unsigned long *indices,
 			unsigned long first_index, unsigned int max_items)
 {
-	unsigned long max_index;
-	struct radix_tree_node *node;
-	unsigned long cur_index = first_index;
-	unsigned int ret;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
 
-	node = rcu_dereference_raw(root->rnode);
-	if (!node)
+	if (unlikely(!max_items))
 		return 0;
 
-	if (!radix_tree_is_indirect_ptr(node)) {
-		if (first_index > 0)
-			return 0;
-		results[0] = (void **)&root->rnode;
+	radix_tree_for_each_slot(slot, root, &iter, first_index) {
+		results[ret] = slot;
 		if (indices)
-			indices[0] = 0;
-		return 1;
-	}
-	node = indirect_to_ptr(node);
-
-	max_index = radix_tree_maxindex(node->height);
-
-	ret = 0;
-	while (ret < max_items) {
-		unsigned int slots_found;
-		unsigned long next_index;	/* Index of next search */
-
-		if (cur_index > max_index)
+			indices[ret] = iter.index;
+		if (++ret == max_items)
 			break;
-		slots_found = __lookup(node, results + ret,
-				indices ? indices + ret : NULL,
-				cur_index, max_items - ret, &next_index);
-		ret += slots_found;
-		if (next_index == 0)
-			break;
-		cur_index = next_index;
 	}
 
 	return ret;
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup_slot);
 
-/*
- * FIXME: the two tag_get()s here should use find_next_bit() instead of
- * open-coding the search.
- */
-static unsigned int
-__lookup_tag(struct radix_tree_node *slot, void ***results, unsigned long index,
-	unsigned int max_items, unsigned long *next_index, unsigned int tag)
-{
-	unsigned int nr_found = 0;
-	unsigned int shift, height;
-
-	height = slot->height;
-	if (height == 0)
-		goto out;
-	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
-
-	while (height > 0) {
-		unsigned long i = (index >> shift) & RADIX_TREE_MAP_MASK ;
-
-		for (;;) {
-			if (tag_get(slot, tag, i))
-				break;
-			index &= ~((1UL << shift) - 1);
-			index += 1UL << shift;
-			if (index == 0)
-				goto out;	/* 32-bit wraparound */
-			i++;
-			if (i == RADIX_TREE_MAP_SIZE)
-				goto out;
-		}
-		height--;
-		if (height == 0) {	/* Bottom level: grab some items */
-			unsigned long j = index & RADIX_TREE_MAP_MASK;
-
-			for ( ; j < RADIX_TREE_MAP_SIZE; j++) {
-				index++;
-				if (!tag_get(slot, tag, j))
-					continue;
-				/*
-				 * Even though the tag was found set, we need to
-				 * recheck that we have a non-NULL node, because
-				 * if this lookup is lockless, it may have been
-				 * subsequently deleted.
-				 *
-				 * Similar care must be taken in any place that
-				 * lookup ->slots[x] without a lock (ie. can't
-				 * rely on its value remaining the same).
-				 */
-				if (slot->slots[j]) {
-					results[nr_found++] = &(slot->slots[j]);
-					if (nr_found == max_items)
-						goto out;
-				}
-			}
-		}
-		shift -= RADIX_TREE_MAP_SHIFT;
-		slot = rcu_dereference_raw(slot->slots[i]);
-		if (slot == NULL)
-			break;
-	}
-out:
-	*next_index = index;
-	return nr_found;
-}
-
 /**
  *	radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree
  *	                             based on a tag
@@ -1086,52 +1070,19 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
 		unsigned long first_index, unsigned int max_items,
 		unsigned int tag)
 {
-	struct radix_tree_node *node;
-	unsigned long max_index;
-	unsigned long cur_index = first_index;
-	unsigned int ret;
-
-	/* check the root's tag bit */
-	if (!root_tag_get(root, tag))
-		return 0;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
 
-	node = rcu_dereference_raw(root->rnode);
-	if (!node)
+	if (unlikely(!max_items))
 		return 0;
 
-	if (!radix_tree_is_indirect_ptr(node)) {
-		if (first_index > 0)
-			return 0;
-		results[0] = node;
-		return 1;
-	}
-	node = indirect_to_ptr(node);
-
-	max_index = radix_tree_maxindex(node->height);
-
-	ret = 0;
-	while (ret < max_items) {
-		unsigned int nr_found, slots_found, i;
-		unsigned long next_index;	/* Index of next search */
-
-		if (cur_index > max_index)
-			break;
-		slots_found = __lookup_tag(node, (void ***)results + ret,
-				cur_index, max_items - ret, &next_index, tag);
-		nr_found = 0;
-		for (i = 0; i < slots_found; i++) {
-			struct radix_tree_node *slot;
-			slot = *(((void ***)results)[ret + i]);
-			if (!slot)
-				continue;
-			results[ret + nr_found] =
-				indirect_to_ptr(rcu_dereference_raw(slot));
-			nr_found++;
-		}
-		ret += nr_found;
-		if (next_index == 0)
+	radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
+		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		if (!results[ret])
+			continue;
+		if (++ret == max_items)
 			break;
-		cur_index = next_index;
 	}
 
 	return ret;
@@ -1156,42 +1107,17 @@ radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results,
 		unsigned long first_index, unsigned int max_items,
 		unsigned int tag)
 {
-	struct radix_tree_node *node;
-	unsigned long max_index;
-	unsigned long cur_index = first_index;
-	unsigned int ret;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
 
-	/* check the root's tag bit */
-	if (!root_tag_get(root, tag))
-		return 0;
-
-	node = rcu_dereference_raw(root->rnode);
-	if (!node)
+	if (unlikely(!max_items))
 		return 0;
 
-	if (!radix_tree_is_indirect_ptr(node)) {
-		if (first_index > 0)
-			return 0;
-		results[0] = (void **)&root->rnode;
-		return 1;
-	}
-	node = indirect_to_ptr(node);
-
-	max_index = radix_tree_maxindex(node->height);
-
-	ret = 0;
-	while (ret < max_items) {
-		unsigned int slots_found;
-		unsigned long next_index;	/* Index of next search */
-
-		if (cur_index > max_index)
-			break;
-		slots_found = __lookup_tag(node, results + ret,
-				cur_index, max_items - ret, &next_index, tag);
-		ret += slots_found;
-		if (next_index == 0)
+	radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
+		results[ret] = slot;
+		if (++ret == max_items)
 			break;
-		cur_index = next_index;
 	}
 
 	return ret;
diff --git a/lib/raid6/altivec.uc b/lib/raid6/altivec.uc
index 2654d5c854be..b71012b756f4 100644
--- a/lib/raid6/altivec.uc
+++ b/lib/raid6/altivec.uc
@@ -28,8 +28,8 @@
 
 #include <altivec.h>
 #ifdef __KERNEL__
-# include <asm/system.h>
 # include <asm/cputable.h>
+# include <asm/switch_to.h>
 #endif
 
 /*
diff --git a/mm/filemap.c b/mm/filemap.c
index c3811bc6b9e3..79c4b2b0b14e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -813,20 +813,19 @@ EXPORT_SYMBOL(find_or_create_page);
 unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 			    unsigned int nr_pages, struct page **pages)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found, nr_skip;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
 
 	rcu_read_lock();
 restart:
-	nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
-				(void ***)pages, NULL, start, nr_pages);
-	ret = 0;
-	nr_skip = 0;
-	for (i = 0; i < nr_found; i++) {
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
 		struct page *page;
 repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
+		page = radix_tree_deref_slot(slot);
 		if (unlikely(!page))
 			continue;
 
@@ -837,7 +836,7 @@ repeat:
 				 * when entry at index 0 moves out of or back
 				 * to root: none yet gotten, safe to restart.
 				 */
-				WARN_ON(start | i);
+				WARN_ON(iter.index);
 				goto restart;
 			}
 			/*
@@ -845,7 +844,6 @@ repeat:
 			 * here as an exceptional entry: so skip over it -
 			 * we only reach this from invalidate_mapping_pages().
 			 */
-			nr_skip++;
 			continue;
 		}
 
@@ -853,21 +851,16 @@ repeat:
 			goto repeat;
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
+		if (unlikely(page != *slot)) {
 			page_cache_release(page);
 			goto repeat;
 		}
 
 		pages[ret] = page;
-		ret++;
+		if (++ret == nr_pages)
+			break;
 	}
 
-	/*
-	 * If all entries were removed before we could secure them,
-	 * try again, because callers stop trying once 0 is returned.
-	 */
-	if (unlikely(!ret && nr_found > nr_skip))
-		goto restart;
 	rcu_read_unlock();
 	return ret;
 }
@@ -887,21 +880,22 @@ repeat:
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 			       unsigned int nr_pages, struct page **pages)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
 
 	rcu_read_lock();
 restart:
-	nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
-				(void ***)pages, NULL, index, nr_pages);
-	ret = 0;
-	for (i = 0; i < nr_found; i++) {
+	radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) {
 		struct page *page;
 repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
+		page = radix_tree_deref_slot(slot);
+		/* The hole, there no reason to continue */
 		if (unlikely(!page))
-			continue;
+			break;
 
 		if (radix_tree_exception(page)) {
 			if (radix_tree_deref_retry(page)) {
@@ -924,7 +918,7 @@ repeat:
 			goto repeat;
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
+		if (unlikely(page != *slot)) {
 			page_cache_release(page);
 			goto repeat;
 		}
@@ -934,14 +928,14 @@ repeat:
 		 * otherwise we can get both false positives and false
 		 * negatives, which is just confusing to the caller.
 		 */
-		if (page->mapping == NULL || page->index != index) {
+		if (page->mapping == NULL || page->index != iter.index) {
 			page_cache_release(page);
 			break;
 		}
 
 		pages[ret] = page;
-		ret++;
-		index++;
+		if (++ret == nr_pages)
+			break;
 	}
 	rcu_read_unlock();
 	return ret;
@@ -962,19 +956,20 @@ EXPORT_SYMBOL(find_get_pages_contig);
 unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
 			int tag, unsigned int nr_pages, struct page **pages)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
 
 	rcu_read_lock();
 restart:
-	nr_found = radix_tree_gang_lookup_tag_slot(&mapping->page_tree,
-				(void ***)pages, *index, nr_pages, tag);
-	ret = 0;
-	for (i = 0; i < nr_found; i++) {
+	radix_tree_for_each_tagged(slot, &mapping->page_tree,
+				   &iter, *index, tag) {
 		struct page *page;
 repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
+		page = radix_tree_deref_slot(slot);
 		if (unlikely(!page))
 			continue;
 
@@ -998,21 +993,16 @@ repeat:
 			goto repeat;
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
+		if (unlikely(page != *slot)) {
 			page_cache_release(page);
 			goto repeat;
 		}
 
 		pages[ret] = page;
-		ret++;
+		if (++ret == nr_pages)
+			break;
 	}
 
-	/*
-	 * If all entries were removed before we could secure them,
-	 * try again, because callers stop trying once 0 is returned.
-	 */
-	if (unlikely(!ret && nr_found))
-		goto restart;
 	rcu_read_unlock();
 
 	if (ret)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b2ee6df0e9bb..7d698df4a067 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5306,6 +5306,8 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 		return 0;
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE)
 		if (get_mctgt_type(vma, addr, *pte, NULL))
@@ -5502,6 +5504,8 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 		return 0;
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 retry:
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; addr += PAGE_SIZE) {
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3fc261705b1e..26adea8ca2e7 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -95,6 +95,8 @@ unsigned long vm_dirty_bytes;
  */
 unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */
 
+EXPORT_SYMBOL_GPL(dirty_writeback_interval);
+
 /*
  * The longest time for which data is allowed to remain dirty
  */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index caea788628e4..a712fb9e04ce 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1161,11 +1161,47 @@ void drain_local_pages(void *arg)
 }
 
 /*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
+ *
+ * Note that this code is protected against sending an IPI to an offline
+ * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
+ * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
+ * nothing keeps CPUs from showing up after we populated the cpumask and
+ * before the call to on_each_cpu_mask().
  */
 void drain_all_pages(void)
 {
-	on_each_cpu(drain_local_pages, NULL, 1);
+	int cpu;
+	struct per_cpu_pageset *pcp;
+	struct zone *zone;
+
+	/*
+	 * Allocate in the BSS so we wont require allocation in
+	 * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
+	 */
+	static cpumask_t cpus_with_pcps;
+
+	/*
+	 * We don't care about racing with CPU hotplug event
+	 * as offline notification will cause the notified
+	 * cpu to drain that CPU pcps and on_each_cpu_mask
+	 * disables preemption as part of its processing
+	 */
+	for_each_online_cpu(cpu) {
+		bool has_pcps = false;
+		for_each_populated_zone(zone) {
+			pcp = per_cpu_ptr(zone->pageset, cpu);
+			if (pcp->pcp.count) {
+				has_pcps = true;
+				break;
+			}
+		}
+		if (has_pcps)
+			cpumask_set_cpu(cpu, &cpus_with_pcps);
+		else
+			cpumask_clear_cpu(cpu, &cpus_with_pcps);
+	}
+	on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -2308,6 +2344,10 @@ rebalance:
 		if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
 			if (oom_killer_disabled)
 				goto nopage;
+			/* Coredumps can quickly deplete all memory reserves */
+			if ((current->flags & PF_DUMPCORE) &&
+			    !(gfp_mask & __GFP_NOFAIL))
+				goto nopage;
 			page = __alloc_pages_may_oom(gfp_mask, order,
 					zonelist, high_zoneidx,
 					nodemask, preferred_zone,
diff --git a/mm/slab.c b/mm/slab.c
index 29c8716eb7a9..e901a36e2520 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1731,6 +1731,52 @@ static int __init cpucache_init(void)
 }
 __initcall(cpucache_init);
 
+static noinline void
+slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
+{
+	struct kmem_list3 *l3;
+	struct slab *slabp;
+	unsigned long flags;
+	int node;
+
+	printk(KERN_WARNING
+		"SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n",
+		nodeid, gfpflags);
+	printk(KERN_WARNING "  cache: %s, object size: %d, order: %d\n",
+		cachep->name, cachep->buffer_size, cachep->gfporder);
+
+	for_each_online_node(node) {
+		unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
+		unsigned long active_slabs = 0, num_slabs = 0;
+
+		l3 = cachep->nodelists[node];
+		if (!l3)
+			continue;
+
+		spin_lock_irqsave(&l3->list_lock, flags);
+		list_for_each_entry(slabp, &l3->slabs_full, list) {
+			active_objs += cachep->num;
+			active_slabs++;
+		}
+		list_for_each_entry(slabp, &l3->slabs_partial, list) {
+			active_objs += slabp->inuse;
+			active_slabs++;
+		}
+		list_for_each_entry(slabp, &l3->slabs_free, list)
+			num_slabs++;
+
+		free_objects += l3->free_objects;
+		spin_unlock_irqrestore(&l3->list_lock, flags);
+
+		num_slabs += active_slabs;
+		num_objs = num_slabs * cachep->num;
+		printk(KERN_WARNING
+			"  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
+			node, active_slabs, num_slabs, active_objs, num_objs,
+			free_objects);
+	}
+}
+
 /*
  * Interface to system's page allocator. No need to hold the cache-lock.
  *
@@ -1757,8 +1803,11 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		flags |= __GFP_RECLAIMABLE;
 
 	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
-	if (!page)
+	if (!page) {
+		if (!(flags & __GFP_NOWARN) && printk_ratelimit())
+			slab_out_of_memory(cachep, flags, nodeid);
 		return NULL;
+	}
 
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
@@ -3696,13 +3745,12 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp,
 
 	if (likely(ac->avail < ac->limit)) {
 		STATS_INC_FREEHIT(cachep);
-		ac->entry[ac->avail++] = objp;
-		return;
 	} else {
 		STATS_INC_FREEMISS(cachep);
 		cache_flusharray(cachep, ac);
-		ac->entry[ac->avail++] = objp;
 	}
+
+	ac->entry[ac->avail++] = objp;
 }
 
 /**
diff --git a/mm/slub.c b/mm/slub.c
index f4a6229848fd..ffe13fdf8144 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -29,6 +29,7 @@
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
 #include <linux/stacktrace.h>
+#include <linux/prefetch.h>
 
 #include <trace/events/kmem.h>
 
@@ -269,6 +270,11 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object)
 	return *(void **)(object + s->offset);
 }
 
+static void prefetch_freepointer(const struct kmem_cache *s, void *object)
+{
+	prefetch(object + s->offset);
+}
+
 static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
 {
 	void *p;
@@ -1560,6 +1566,7 @@ static void *get_partial_node(struct kmem_cache *s,
 		} else {
 			page->freelist = t;
 			available = put_cpu_partial(s, page, 0);
+			stat(s, CPU_PARTIAL_NODE);
 		}
 		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
 			break;
@@ -1983,6 +1990,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 				local_irq_restore(flags);
 				pobjects = 0;
 				pages = 0;
+				stat(s, CPU_PARTIAL_DRAIN);
 			}
 		}
 
@@ -1994,7 +2002,6 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 		page->next = oldpage;
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
-	stat(s, CPU_PARTIAL_FREE);
 	return pobjects;
 }
 
@@ -2028,9 +2035,17 @@ static void flush_cpu_slab(void *d)
 	__flush_cpu_slab(s, smp_processor_id());
 }
 
+static bool has_cpu_slab(int cpu, void *info)
+{
+	struct kmem_cache *s = info;
+	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+
+	return !!(c->page);
+}
+
 static void flush_all(struct kmem_cache *s)
 {
-	on_each_cpu(flush_cpu_slab, s, 1);
+	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC);
 }
 
 /*
@@ -2319,6 +2334,8 @@ redo:
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
 	else {
+		void *next_object = get_freepointer_safe(s, object);
+
 		/*
 		 * The cmpxchg will only match if there was no additional
 		 * operation and if we are on the right processor.
@@ -2334,11 +2351,12 @@ redo:
 		if (unlikely(!this_cpu_cmpxchg_double(
 				s->cpu_slab->freelist, s->cpu_slab->tid,
 				object, tid,
-				get_freepointer_safe(s, object), next_tid(tid)))) {
+				next_object, next_tid(tid)))) {
 
 			note_cmpxchg_failure("slab_alloc", s, tid);
 			goto redo;
 		}
+		prefetch_freepointer(s, next_object);
 		stat(s, ALLOC_FASTPATH);
 	}
 
@@ -2475,9 +2493,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		 * If we just froze the page then put it onto the
 		 * per cpu partial list.
 		 */
-		if (new.frozen && !was_frozen)
+		if (new.frozen && !was_frozen) {
 			put_cpu_partial(s, page, 1);
-
+			stat(s, CPU_PARTIAL_FREE);
+		}
 		/*
 		 * The list lock was not taken therefore no list
 		 * activity can be necessary.
@@ -3939,13 +3958,14 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		if (kmem_cache_open(s, n,
 				size, align, flags, ctor)) {
 			list_add(&s->list, &slab_caches);
+			up_write(&slub_lock);
 			if (sysfs_slab_add(s)) {
+				down_write(&slub_lock);
 				list_del(&s->list);
 				kfree(n);
 				kfree(s);
 				goto err;
 			}
-			up_write(&slub_lock);
 			return s;
 		}
 		kfree(n);
@@ -5069,6 +5089,8 @@ STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail);
 STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail);
 STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc);
 STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free);
+STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node);
+STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -5134,6 +5156,8 @@ static struct attribute *slab_attrs[] = {
 	&cmpxchg_double_cpu_fail_attr.attr,
 	&cpu_partial_alloc_attr.attr,
 	&cpu_partial_free_attr.attr,
+	&cpu_partial_node_attr.attr,
+	&cpu_partial_drain_attr.attr,
 #endif
 #ifdef CONFIG_FAILSLAB
 	&failslab_attr.attr,
diff --git a/mm/swapfile.c b/mm/swapfile.c
index dae42f380d6e..fafc26d1b1dc 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2022,6 +2022,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	struct page *page = NULL;
 	struct inode *inode = NULL;
 
+	if (swap_flags & ~SWAP_FLAGS_VALID)
+		return -EINVAL;
+
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
diff --git a/mm/truncate.c b/mm/truncate.c
index 18aded3a89fc..61a183b89df6 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -626,3 +626,43 @@ int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 
 	return 0;
 }
+
+/**
+ * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
+ * @inode: inode
+ * @lstart: offset of beginning of hole
+ * @lend: offset of last byte of hole
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * situations such as writepage being called for a page that has already
+ * had its underlying blocks deallocated.
+ */
+void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
+{
+	struct address_space *mapping = inode->i_mapping;
+	loff_t unmap_start = round_up(lstart, PAGE_SIZE);
+	loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
+	/*
+	 * This rounding is currently just for example: unmap_mapping_range
+	 * expands its hole outwards, whereas we want it to contract the hole
+	 * inwards.  However, existing callers of truncate_pagecache_range are
+	 * doing their own page rounding first; and truncate_inode_pages_range
+	 * currently BUGs if lend is not pagealigned-1 (it handles partial
+	 * page at start of hole, but not partial page at end of hole).  Note
+	 * unmap_mapping_range allows holelen 0 for all, and we allow lend -1.
+	 */
+
+	/*
+	 * Unlike in truncate_pagecache, unmap_mapping_range is called only
+	 * once (before truncating pagecache), and without "even_cows" flag:
+	 * hole-punching should not remove private COWed pages from the hole.
+	 */
+	if ((u64)unmap_end > (u64)unmap_start)
+		unmap_mapping_range(mapping, unmap_start,
+				    1 + unmap_end - unmap_start, 0);
+	truncate_inode_pages_range(mapping, lstart, lend);
+}
+EXPORT_SYMBOL(truncate_pagecache_range);
diff --git a/net/802/fc.c b/net/802/fc.c
index bd345f3d29f8..b324e31401a9 100644
--- a/net/802/fc.c
+++ b/net/802/fc.c
@@ -11,7 +11,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/net/802/fddi.c b/net/802/fddi.c
index 94b3ad08f39a..5ab25cd4314b 100644
--- a/net/802/fddi.c
+++ b/net/802/fddi.c
@@ -27,7 +27,6 @@
  */
 
 #include <linux/module.h>
-#include <asm/system.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/net/802/hippi.c b/net/802/hippi.c
index 91aca8780fd0..056794e66375 100644
--- a/net/802/hippi.c
+++ b/net/802/hippi.c
@@ -35,7 +35,6 @@
 #include <net/arp.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 /*
  * Create the HIPPI MAC header for an arbitrary protocol layer
diff --git a/net/802/tr.c b/net/802/tr.c
index 5e20cf8a074b..b9a3a145e348 100644
--- a/net/802/tr.c
+++ b/net/802/tr.c
@@ -16,7 +16,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/9p/client.c b/net/9p/client.c
index 776618cd2be5..b23a17c431c8 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -740,10 +740,18 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 			c->status = Disconnected;
 		goto reterr;
 	}
+again:
 	/* Wait for the response */
 	err = wait_event_interruptible(*req->wq,
 				       req->status >= REQ_STATUS_RCVD);
 
+	if ((err == -ERESTARTSYS) && (c->status == Connected)
+				  && (type == P9_TFLUSH)) {
+		sigpending = 1;
+		clear_thread_flag(TIF_SIGPENDING);
+		goto again;
+	}
+
 	if (req->status == REQ_STATUS_ERROR) {
 		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
 		err = req->t_err;
@@ -1420,6 +1428,7 @@ int p9_client_clunk(struct p9_fid *fid)
 	int err;
 	struct p9_client *clnt;
 	struct p9_req_t *req;
+	int retries = 0;
 
 	if (!fid) {
 		pr_warn("%s (%d): Trying to clunk with NULL fid\n",
@@ -1428,7 +1437,9 @@ int p9_client_clunk(struct p9_fid *fid)
 		return 0;
 	}
 
-	p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d\n", fid->fid);
+again:
+	p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid,
+								retries);
 	err = 0;
 	clnt = fid->clnt;
 
@@ -1444,8 +1455,14 @@ int p9_client_clunk(struct p9_fid *fid)
 error:
 	/*
 	 * Fid is not valid even after a failed clunk
+	 * If interrupted, retry once then give up and
+	 * leak fid until umount.
 	 */
-	p9_fid_destroy(fid);
+	if (err == -ERESTARTSYS) {
+		if (retries++ == 0)
+			goto again;
+	} else
+		p9_fid_destroy(fid);
 	return err;
 }
 EXPORT_SYMBOL(p9_client_clunk);
@@ -1470,7 +1487,10 @@ int p9_client_remove(struct p9_fid *fid)
 
 	p9_free_req(clnt, req);
 error:
-	p9_fid_destroy(fid);
+	if (err == -ERESTARTSYS)
+		p9_client_clunk(fid);
+	else
+		p9_fid_destroy(fid);
 	return err;
 }
 EXPORT_SYMBOL(p9_client_remove);
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 5de42ea309bc..8ae3a7879335 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -37,7 +37,6 @@
 #include <linux/param.h> /* for HZ */
 #include <linux/uaccess.h>
 #include <asm/byteorder.h> /* for htons etc. */
-#include <asm/system.h> /* save/restore_flags */
 #include <linux/atomic.h>
 
 #include "common.h"
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 3cd0a0dc91cb..0906c194a413 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -33,7 +33,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>
diff --git a/net/ax25/ax25_addr.c b/net/ax25/ax25_addr.c
index 7e7964dd987b..9162409559cf 100644
--- a/net/ax25/ax25_addr.c
+++ b/net/ax25/ax25_addr.c
@@ -22,7 +22,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index c1cb982f6e86..d0de30e89591 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -24,7 +24,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_ds_in.c b/net/ax25/ax25_ds_in.c
index 8273b1200eee..9bd31e88aeca 100644
--- a/net/ax25/ax25_ds_in.c
+++ b/net/ax25/ax25_ds_in.c
@@ -23,7 +23,6 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_ds_subr.c b/net/ax25/ax25_ds_subr.c
index 85816e612dc0..5ea7fd3e2af9 100644
--- a/net/ax25/ax25_ds_subr.c
+++ b/net/ax25/ax25_ds_subr.c
@@ -24,7 +24,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index c7d81436213d..993c439b4f71 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -25,7 +25,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_iface.c b/net/ax25/ax25_iface.c
index 60b545e2822a..7d5f24b82cc8 100644
--- a/net/ax25/ax25_iface.c
+++ b/net/ax25/ax25_iface.c
@@ -24,7 +24,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c
index 9bb776541203..96f4cab3a2f9 100644
--- a/net/ax25/ax25_in.c
+++ b/net/ax25/ax25_in.c
@@ -27,7 +27,6 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index cf0c47a26530..846ae4e2b115 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -24,7 +24,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>
diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c
index 37507d806f65..be8a25e0db65 100644
--- a/net/ax25/ax25_out.c
+++ b/net/ax25/ax25_out.c
@@ -27,7 +27,6 @@
 #include <linux/netfilter.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index 87fddab22e0f..a65588040b9e 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -32,7 +32,6 @@
 #include <linux/spinlock.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_std_in.c b/net/ax25/ax25_std_in.c
index a8eef88d8652..3fbf8f7b2cf4 100644
--- a/net/ax25/ax25_std_in.c
+++ b/net/ax25/ax25_std_in.c
@@ -30,7 +30,6 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_std_subr.c b/net/ax25/ax25_std_subr.c
index 277f81bb979a..8b66a41e538f 100644
--- a/net/ax25/ax25_std_subr.c
+++ b/net/ax25/ax25_std_subr.c
@@ -21,7 +21,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_std_timer.c b/net/ax25/ax25_std_timer.c
index 96e4b9273250..004467c9e6e1 100644
--- a/net/ax25/ax25_std_timer.c
+++ b/net/ax25/ax25_std_timer.c
@@ -25,7 +25,6 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index c6715ee4ab8f..1997538a5d23 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -26,7 +26,6 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_timer.c b/net/ax25/ax25_timer.c
index db29ea71e80a..c3cffa79bafb 100644
--- a/net/ax25/ax25_timer.c
+++ b/net/ax25/ax25_timer.c
@@ -29,7 +29,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c
index 4c83137b5954..e3c579ba6325 100644
--- a/net/ax25/ax25_uid.c
+++ b/net/ax25/ax25_uid.c
@@ -26,7 +26,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index 9f9c8dcd8af0..180bfc45810d 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/net/bluetooth/bnep/sock.c
@@ -42,7 +42,6 @@
 #include <linux/uaccess.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 
 #include "bnep.h"
 
diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c
index 1230faaac29b..311668d14571 100644
--- a/net/bluetooth/cmtp/sock.c
+++ b/net/bluetooth/cmtp/sock.c
@@ -39,7 +39,6 @@
 
 #include <linux/isdn/capilli.h>
 
-#include <asm/system.h>
 
 #include "cmtp.h"
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 947172bf1621..5238b6b3ea6a 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -37,7 +37,6 @@
 #include <linux/interrupt.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 59ec99eb739b..e33af63a884a 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -45,7 +45,6 @@
 #include <linux/crypto.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index badb7851d116..b37531094c49 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -37,7 +37,6 @@
 #include <linux/interrupt.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 63afd234283e..5914623f426a 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -42,7 +42,6 @@
 #include <linux/ioctl.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
@@ -734,7 +733,8 @@ static inline void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_
 		data = &tv;
 		len = sizeof(tv);
 #ifdef CONFIG_COMPAT
-		if (msg->msg_flags & MSG_CMSG_COMPAT) {
+		if (!COMPAT_USE_64BIT_TIME &&
+		    (msg->msg_flags & MSG_CMSG_COMPAT)) {
 			ctv.tv_sec = tv.tv_sec;
 			ctv.tv_usec = tv.tv_usec;
 			data = &ctv;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 3e450f4a3125..b8e17e4dac8b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -49,7 +49,6 @@
 #include <linux/crc16.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include <net/bluetooth/bluetooth.h>
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 22169c3f1482..a55a43e9f70e 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -45,7 +45,6 @@
 #include <linux/security.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 
 #include <net/bluetooth/bluetooth.h>
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 8bf26d1bc5c1..f6ab12907963 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -44,7 +44,6 @@
 #include <linux/security.h>
 #include <net/sock.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 
 #include <net/bluetooth/bluetooth.h>
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 761ad9d6cc3b..cc913193d992 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -201,7 +201,9 @@ enum {
 	Opt_ip,
 	Opt_last_string,
 	/* string args above */
+	Opt_share,
 	Opt_noshare,
+	Opt_crc,
 	Opt_nocrc,
 };
 
@@ -217,7 +219,9 @@ static match_table_t opt_tokens = {
 	{Opt_key, "key=%s"},
 	{Opt_ip, "ip=%s"},
 	/* string args above */
+	{Opt_share, "share"},
 	{Opt_noshare, "noshare"},
+	{Opt_crc, "crc"},
 	{Opt_nocrc, "nocrc"},
 	{-1, NULL}
 };
@@ -277,10 +281,11 @@ out:
 	return err;
 }
 
-int ceph_parse_options(struct ceph_options **popt, char *options,
-		       const char *dev_name, const char *dev_name_end,
-		       int (*parse_extra_token)(char *c, void *private),
-		       void *private)
+struct ceph_options *
+ceph_parse_options(char *options, const char *dev_name,
+			const char *dev_name_end,
+			int (*parse_extra_token)(char *c, void *private),
+			void *private)
 {
 	struct ceph_options *opt;
 	const char *c;
@@ -289,7 +294,7 @@ int ceph_parse_options(struct ceph_options **popt, char *options,
 
 	opt = kzalloc(sizeof(*opt), GFP_KERNEL);
 	if (!opt)
-		return err;
+		return ERR_PTR(-ENOMEM);
 	opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr),
 				GFP_KERNEL);
 	if (!opt->mon_addr)
@@ -398,10 +403,16 @@ int ceph_parse_options(struct ceph_options **popt, char *options,
 			opt->mount_timeout = intval;
 			break;
 
+		case Opt_share:
+			opt->flags &= ~CEPH_OPT_NOSHARE;
+			break;
 		case Opt_noshare:
 			opt->flags |= CEPH_OPT_NOSHARE;
 			break;
 
+		case Opt_crc:
+			opt->flags &= ~CEPH_OPT_NOCRC;
+			break;
 		case Opt_nocrc:
 			opt->flags |= CEPH_OPT_NOCRC;
 			break;
@@ -412,12 +423,11 @@ int ceph_parse_options(struct ceph_options **popt, char *options,
 	}
 
 	/* success */
-	*popt = opt;
-	return 0;
+	return opt;
 
 out:
 	ceph_destroy_options(opt);
-	return err;
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(ceph_parse_options);
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index ad5b70801f37..f0993af2ae4d 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -38,48 +38,54 @@ static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
 static struct lock_class_key socket_class;
 #endif
 
+/*
+ * When skipping (ignoring) a block of input we read it into a "skip
+ * buffer," which is this many bytes in size.
+ */
+#define SKIP_BUF_SIZE	1024
 
 static void queue_con(struct ceph_connection *con);
 static void con_work(struct work_struct *);
 static void ceph_fault(struct ceph_connection *con);
 
 /*
- * nicely render a sockaddr as a string.
+ * Nicely render a sockaddr as a string.  An array of formatted
+ * strings is used, to approximate reentrancy.
  */
-#define MAX_ADDR_STR 20
-#define MAX_ADDR_STR_LEN 60
-static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN];
-static DEFINE_SPINLOCK(addr_str_lock);
-static int last_addr_str;
+#define ADDR_STR_COUNT_LOG	5	/* log2(# address strings in array) */
+#define ADDR_STR_COUNT		(1 << ADDR_STR_COUNT_LOG)
+#define ADDR_STR_COUNT_MASK	(ADDR_STR_COUNT - 1)
+#define MAX_ADDR_STR_LEN	64	/* 54 is enough */
+
+static char addr_str[ADDR_STR_COUNT][MAX_ADDR_STR_LEN];
+static atomic_t addr_str_seq = ATOMIC_INIT(0);
+
+static struct page *zero_page;		/* used in certain error cases */
 
 const char *ceph_pr_addr(const struct sockaddr_storage *ss)
 {
 	int i;
 	char *s;
-	struct sockaddr_in *in4 = (void *)ss;
-	struct sockaddr_in6 *in6 = (void *)ss;
-
-	spin_lock(&addr_str_lock);
-	i = last_addr_str++;
-	if (last_addr_str == MAX_ADDR_STR)
-		last_addr_str = 0;
-	spin_unlock(&addr_str_lock);
+	struct sockaddr_in *in4 = (struct sockaddr_in *) ss;
+	struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) ss;
+
+	i = atomic_inc_return(&addr_str_seq) & ADDR_STR_COUNT_MASK;
 	s = addr_str[i];
 
 	switch (ss->ss_family) {
 	case AF_INET:
-		snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%u", &in4->sin_addr,
-			 (unsigned int)ntohs(in4->sin_port));
+		snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%hu", &in4->sin_addr,
+			 ntohs(in4->sin_port));
 		break;
 
 	case AF_INET6:
-		snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%u", &in6->sin6_addr,
-			 (unsigned int)ntohs(in6->sin6_port));
+		snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%hu", &in6->sin6_addr,
+			 ntohs(in6->sin6_port));
 		break;
 
 	default:
-		snprintf(s, MAX_ADDR_STR_LEN, "(unknown sockaddr family %d)",
-			 (int)ss->ss_family);
+		snprintf(s, MAX_ADDR_STR_LEN, "(unknown sockaddr family %hu)",
+			 ss->ss_family);
 	}
 
 	return s;
@@ -95,22 +101,43 @@ static void encode_my_addr(struct ceph_messenger *msgr)
 /*
  * work queue for all reading and writing to/from the socket.
  */
-struct workqueue_struct *ceph_msgr_wq;
+static struct workqueue_struct *ceph_msgr_wq;
+
+void _ceph_msgr_exit(void)
+{
+	if (ceph_msgr_wq) {
+		destroy_workqueue(ceph_msgr_wq);
+		ceph_msgr_wq = NULL;
+	}
+
+	BUG_ON(zero_page == NULL);
+	kunmap(zero_page);
+	page_cache_release(zero_page);
+	zero_page = NULL;
+}
 
 int ceph_msgr_init(void)
 {
+	BUG_ON(zero_page != NULL);
+	zero_page = ZERO_PAGE(0);
+	page_cache_get(zero_page);
+
 	ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0);
-	if (!ceph_msgr_wq) {
-		pr_err("msgr_init failed to create workqueue\n");
-		return -ENOMEM;
-	}
-	return 0;
+	if (ceph_msgr_wq)
+		return 0;
+
+	pr_err("msgr_init failed to create workqueue\n");
+	_ceph_msgr_exit();
+
+	return -ENOMEM;
 }
 EXPORT_SYMBOL(ceph_msgr_init);
 
 void ceph_msgr_exit(void)
 {
-	destroy_workqueue(ceph_msgr_wq);
+	BUG_ON(ceph_msgr_wq == NULL);
+
+	_ceph_msgr_exit();
 }
 EXPORT_SYMBOL(ceph_msgr_exit);
 
@@ -128,8 +155,8 @@ EXPORT_SYMBOL(ceph_msgr_flush);
 /* data available on socket, or listen socket received a connect */
 static void ceph_data_ready(struct sock *sk, int count_unused)
 {
-	struct ceph_connection *con =
-		(struct ceph_connection *)sk->sk_user_data;
+	struct ceph_connection *con = sk->sk_user_data;
+
 	if (sk->sk_state != TCP_CLOSE_WAIT) {
 		dout("ceph_data_ready on %p state = %lu, queueing work\n",
 		     con, con->state);
@@ -140,26 +167,30 @@ static void ceph_data_ready(struct sock *sk, int count_unused)
 /* socket has buffer space for writing */
 static void ceph_write_space(struct sock *sk)
 {
-	struct ceph_connection *con =
-		(struct ceph_connection *)sk->sk_user_data;
+	struct ceph_connection *con = sk->sk_user_data;
 
-	/* only queue to workqueue if there is data we want to write. */
+	/* only queue to workqueue if there is data we want to write,
+	 * and there is sufficient space in the socket buffer to accept
+	 * more data.  clear SOCK_NOSPACE so that ceph_write_space()
+	 * doesn't get called again until try_write() fills the socket
+	 * buffer. See net/ipv4/tcp_input.c:tcp_check_space()
+	 * and net/core/stream.c:sk_stream_write_space().
+	 */
 	if (test_bit(WRITE_PENDING, &con->state)) {
-		dout("ceph_write_space %p queueing write work\n", con);
-		queue_con(con);
+		if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
+			dout("ceph_write_space %p queueing write work\n", con);
+			clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+			queue_con(con);
+		}
 	} else {
 		dout("ceph_write_space %p nothing to write\n", con);
 	}
-
-	/* since we have our own write_space, clear the SOCK_NOSPACE flag */
-	clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 }
 
 /* socket's state has changed */
 static void ceph_state_change(struct sock *sk)
 {
-	struct ceph_connection *con =
-		(struct ceph_connection *)sk->sk_user_data;
+	struct ceph_connection *con = sk->sk_user_data;
 
 	dout("ceph_state_change %p state = %lu sk_state = %u\n",
 	     con, con->state, sk->sk_state);
@@ -184,6 +215,8 @@ static void ceph_state_change(struct sock *sk)
 		dout("ceph_state_change TCP_ESTABLISHED\n");
 		queue_con(con);
 		break;
+	default:	/* Everything else is uninteresting */
+		break;
 	}
 }
 
@@ -194,7 +227,7 @@ static void set_sock_callbacks(struct socket *sock,
 			       struct ceph_connection *con)
 {
 	struct sock *sk = sock->sk;
-	sk->sk_user_data = (void *)con;
+	sk->sk_user_data = con;
 	sk->sk_data_ready = ceph_data_ready;
 	sk->sk_write_space = ceph_write_space;
 	sk->sk_state_change = ceph_state_change;
@@ -208,7 +241,7 @@ static void set_sock_callbacks(struct socket *sock,
 /*
  * initiate connection to a remote socket.
  */
-static struct socket *ceph_tcp_connect(struct ceph_connection *con)
+static int ceph_tcp_connect(struct ceph_connection *con)
 {
 	struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
 	struct socket *sock;
@@ -218,8 +251,7 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con)
 	ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM,
 			       IPPROTO_TCP, &sock);
 	if (ret)
-		return ERR_PTR(ret);
-	con->sock = sock;
+		return ret;
 	sock->sk->sk_allocation = GFP_NOFS;
 
 #ifdef CONFIG_LOCKDEP
@@ -236,19 +268,17 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con)
 		dout("connect %s EINPROGRESS sk_state = %u\n",
 		     ceph_pr_addr(&con->peer_addr.in_addr),
 		     sock->sk->sk_state);
-		ret = 0;
-	}
-	if (ret < 0) {
+	} else if (ret < 0) {
 		pr_err("connect %s error %d\n",
 		       ceph_pr_addr(&con->peer_addr.in_addr), ret);
 		sock_release(sock);
-		con->sock = NULL;
 		con->error_msg = "connect error";
+
+		return ret;
 	}
+	con->sock = sock;
 
-	if (ret < 0)
-		return ERR_PTR(ret);
-	return sock;
+	return 0;
 }
 
 static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
@@ -284,6 +314,19 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
 	return r;
 }
 
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+		     int offset, size_t size, int more)
+{
+	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR);
+	int ret;
+
+	ret = kernel_sendpage(sock, page, offset, size, flags);
+	if (ret == -EAGAIN)
+		ret = 0;
+
+	return ret;
+}
+
 
 /*
  * Shutdown/close the socket for the given connection.
@@ -391,22 +434,23 @@ bool ceph_con_opened(struct ceph_connection *con)
  */
 struct ceph_connection *ceph_con_get(struct ceph_connection *con)
 {
-	dout("con_get %p nref = %d -> %d\n", con,
-	     atomic_read(&con->nref), atomic_read(&con->nref) + 1);
-	if (atomic_inc_not_zero(&con->nref))
-		return con;
-	return NULL;
+	int nref = __atomic_add_unless(&con->nref, 1, 0);
+
+	dout("con_get %p nref = %d -> %d\n", con, nref, nref + 1);
+
+	return nref ? con : NULL;
 }
 
 void ceph_con_put(struct ceph_connection *con)
 {
-	dout("con_put %p nref = %d -> %d\n", con,
-	     atomic_read(&con->nref), atomic_read(&con->nref) - 1);
-	BUG_ON(atomic_read(&con->nref) == 0);
-	if (atomic_dec_and_test(&con->nref)) {
+	int nref = atomic_dec_return(&con->nref);
+
+	BUG_ON(nref < 0);
+	if (nref == 0) {
 		BUG_ON(con->sock);
 		kfree(con);
 	}
+	dout("con_put %p nref = %d -> %d\n", con, nref + 1, nref);
 }
 
 /*
@@ -442,14 +486,35 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
 	return ret;
 }
 
+static void ceph_con_out_kvec_reset(struct ceph_connection *con)
+{
+	con->out_kvec_left = 0;
+	con->out_kvec_bytes = 0;
+	con->out_kvec_cur = &con->out_kvec[0];
+}
+
+static void ceph_con_out_kvec_add(struct ceph_connection *con,
+				size_t size, void *data)
+{
+	int index;
+
+	index = con->out_kvec_left;
+	BUG_ON(index >= ARRAY_SIZE(con->out_kvec));
+
+	con->out_kvec[index].iov_len = size;
+	con->out_kvec[index].iov_base = data;
+	con->out_kvec_left++;
+	con->out_kvec_bytes += size;
+}
 
 /*
  * Prepare footer for currently outgoing message, and finish things
  * off.  Assumes out_kvec* are already valid.. we just add on to the end.
  */
-static void prepare_write_message_footer(struct ceph_connection *con, int v)
+static void prepare_write_message_footer(struct ceph_connection *con)
 {
 	struct ceph_msg *m = con->out_msg;
+	int v = con->out_kvec_left;
 
 	dout("prepare_write_message_footer %p\n", con);
 	con->out_kvec_is_msg = true;
@@ -467,9 +532,9 @@ static void prepare_write_message_footer(struct ceph_connection *con, int v)
 static void prepare_write_message(struct ceph_connection *con)
 {
 	struct ceph_msg *m;
-	int v = 0;
+	u32 crc;
 
-	con->out_kvec_bytes = 0;
+	ceph_con_out_kvec_reset(con);
 	con->out_kvec_is_msg = true;
 	con->out_msg_done = false;
 
@@ -477,16 +542,13 @@ static void prepare_write_message(struct ceph_connection *con)
 	 * TCP packet that's a good thing. */
 	if (con->in_seq > con->in_seq_acked) {
 		con->in_seq_acked = con->in_seq;
-		con->out_kvec[v].iov_base = &tag_ack;
-		con->out_kvec[v++].iov_len = 1;
+		ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
 		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-		con->out_kvec[v].iov_base = &con->out_temp_ack;
-		con->out_kvec[v++].iov_len = sizeof(con->out_temp_ack);
-		con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack);
+		ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack),
+			&con->out_temp_ack);
 	}
 
-	m = list_first_entry(&con->out_queue,
-		       struct ceph_msg, list_head);
+	m = list_first_entry(&con->out_queue, struct ceph_msg, list_head);
 	con->out_msg = m;
 
 	/* put message on sent list */
@@ -510,30 +572,26 @@ static void prepare_write_message(struct ceph_connection *con)
 	BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len);
 
 	/* tag + hdr + front + middle */
-	con->out_kvec[v].iov_base = &tag_msg;
-	con->out_kvec[v++].iov_len = 1;
-	con->out_kvec[v].iov_base = &m->hdr;
-	con->out_kvec[v++].iov_len = sizeof(m->hdr);
-	con->out_kvec[v++] = m->front;
+	ceph_con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
+	ceph_con_out_kvec_add(con, sizeof (m->hdr), &m->hdr);
+	ceph_con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
+
 	if (m->middle)
-		con->out_kvec[v++] = m->middle->vec;
-	con->out_kvec_left = v;
-	con->out_kvec_bytes += 1 + sizeof(m->hdr) + m->front.iov_len +
-		(m->middle ? m->middle->vec.iov_len : 0);
-	con->out_kvec_cur = con->out_kvec;
+		ceph_con_out_kvec_add(con, m->middle->vec.iov_len,
+			m->middle->vec.iov_base);
 
 	/* fill in crc (except data pages), footer */
-	con->out_msg->hdr.crc =
-		cpu_to_le32(crc32c(0, (void *)&m->hdr,
-				      sizeof(m->hdr) - sizeof(m->hdr.crc)));
+	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
+	con->out_msg->hdr.crc = cpu_to_le32(crc);
 	con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE;
-	con->out_msg->footer.front_crc =
-		cpu_to_le32(crc32c(0, m->front.iov_base, m->front.iov_len));
-	if (m->middle)
-		con->out_msg->footer.middle_crc =
-			cpu_to_le32(crc32c(0, m->middle->vec.iov_base,
-					   m->middle->vec.iov_len));
-	else
+
+	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
+	con->out_msg->footer.front_crc = cpu_to_le32(crc);
+	if (m->middle) {
+		crc = crc32c(0, m->middle->vec.iov_base,
+				m->middle->vec.iov_len);
+		con->out_msg->footer.middle_crc = cpu_to_le32(crc);
+	} else
 		con->out_msg->footer.middle_crc = 0;
 	con->out_msg->footer.data_crc = 0;
 	dout("prepare_write_message front_crc %u data_crc %u\n",
@@ -549,11 +607,11 @@ static void prepare_write_message(struct ceph_connection *con)
 		else
 			con->out_msg_pos.page_pos = 0;
 		con->out_msg_pos.data_pos = 0;
-		con->out_msg_pos.did_page_crc = 0;
+		con->out_msg_pos.did_page_crc = false;
 		con->out_more = 1;  /* data + footer will follow */
 	} else {
 		/* no, queue up footer too and be done */
-		prepare_write_message_footer(con, v);
+		prepare_write_message_footer(con);
 	}
 
 	set_bit(WRITE_PENDING, &con->state);
@@ -568,14 +626,14 @@ static void prepare_write_ack(struct ceph_connection *con)
 	     con->in_seq_acked, con->in_seq);
 	con->in_seq_acked = con->in_seq;
 
-	con->out_kvec[0].iov_base = &tag_ack;
-	con->out_kvec[0].iov_len = 1;
+	ceph_con_out_kvec_reset(con);
+
+	ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+
 	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	con->out_kvec[1].iov_base = &con->out_temp_ack;
-	con->out_kvec[1].iov_len = sizeof(con->out_temp_ack);
-	con->out_kvec_left = 2;
-	con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack);
-	con->out_kvec_cur = con->out_kvec;
+	ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack),
+				&con->out_temp_ack);
+
 	con->out_more = 1;  /* more will follow.. eventually.. */
 	set_bit(WRITE_PENDING, &con->state);
 }
@@ -586,11 +644,8 @@ static void prepare_write_ack(struct ceph_connection *con)
 static void prepare_write_keepalive(struct ceph_connection *con)
 {
 	dout("prepare_write_keepalive %p\n", con);
-	con->out_kvec[0].iov_base = &tag_keepalive;
-	con->out_kvec[0].iov_len = 1;
-	con->out_kvec_left = 1;
-	con->out_kvec_bytes = 1;
-	con->out_kvec_cur = con->out_kvec;
+	ceph_con_out_kvec_reset(con);
+	ceph_con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive);
 	set_bit(WRITE_PENDING, &con->state);
 }
 
@@ -619,12 +674,9 @@ static int prepare_connect_authorizer(struct ceph_connection *con)
 	con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol);
 	con->out_connect.authorizer_len = cpu_to_le32(auth_len);
 
-	if (auth_len) {
-		con->out_kvec[con->out_kvec_left].iov_base = auth_buf;
-		con->out_kvec[con->out_kvec_left].iov_len = auth_len;
-		con->out_kvec_left++;
-		con->out_kvec_bytes += auth_len;
-	}
+	if (auth_len)
+		ceph_con_out_kvec_add(con, auth_len, auth_buf);
+
 	return 0;
 }
 
@@ -634,22 +686,18 @@ static int prepare_connect_authorizer(struct ceph_connection *con)
 static void prepare_write_banner(struct ceph_messenger *msgr,
 				 struct ceph_connection *con)
 {
-	int len = strlen(CEPH_BANNER);
+	ceph_con_out_kvec_reset(con);
+	ceph_con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
+	ceph_con_out_kvec_add(con, sizeof (msgr->my_enc_addr),
+					&msgr->my_enc_addr);
 
-	con->out_kvec[0].iov_base = CEPH_BANNER;
-	con->out_kvec[0].iov_len = len;
-	con->out_kvec[1].iov_base = &msgr->my_enc_addr;
-	con->out_kvec[1].iov_len = sizeof(msgr->my_enc_addr);
-	con->out_kvec_left = 2;
-	con->out_kvec_bytes = len + sizeof(msgr->my_enc_addr);
-	con->out_kvec_cur = con->out_kvec;
 	con->out_more = 0;
 	set_bit(WRITE_PENDING, &con->state);
 }
 
 static int prepare_write_connect(struct ceph_messenger *msgr,
 				 struct ceph_connection *con,
-				 int after_banner)
+				 int include_banner)
 {
 	unsigned global_seq = get_global_seq(con->msgr, 0);
 	int proto;
@@ -678,22 +726,18 @@ static int prepare_write_connect(struct ceph_messenger *msgr,
 	con->out_connect.protocol_version = cpu_to_le32(proto);
 	con->out_connect.flags = 0;
 
-	if (!after_banner) {
-		con->out_kvec_left = 0;
-		con->out_kvec_bytes = 0;
-	}
-	con->out_kvec[con->out_kvec_left].iov_base = &con->out_connect;
-	con->out_kvec[con->out_kvec_left].iov_len = sizeof(con->out_connect);
-	con->out_kvec_left++;
-	con->out_kvec_bytes += sizeof(con->out_connect);
-	con->out_kvec_cur = con->out_kvec;
+	if (include_banner)
+		prepare_write_banner(msgr, con);
+	else
+		ceph_con_out_kvec_reset(con);
+	ceph_con_out_kvec_add(con, sizeof (con->out_connect), &con->out_connect);
+
 	con->out_more = 0;
 	set_bit(WRITE_PENDING, &con->state);
 
 	return prepare_connect_authorizer(con);
 }
 
-
 /*
  * write as much of pending kvecs to the socket as we can.
  *  1 -> done
@@ -714,17 +758,18 @@ static int write_partial_kvec(struct ceph_connection *con)
 		con->out_kvec_bytes -= ret;
 		if (con->out_kvec_bytes == 0)
 			break;            /* done */
-		while (ret > 0) {
-			if (ret >= con->out_kvec_cur->iov_len) {
-				ret -= con->out_kvec_cur->iov_len;
-				con->out_kvec_cur++;
-				con->out_kvec_left--;
-			} else {
-				con->out_kvec_cur->iov_len -= ret;
-				con->out_kvec_cur->iov_base += ret;
-				ret = 0;
-				break;
-			}
+
+		/* account for full iov entries consumed */
+		while (ret >= con->out_kvec_cur->iov_len) {
+			BUG_ON(!con->out_kvec_left);
+			ret -= con->out_kvec_cur->iov_len;
+			con->out_kvec_cur++;
+			con->out_kvec_left--;
+		}
+		/* and for a partially-consumed entry */
+		if (ret) {
+			con->out_kvec_cur->iov_len -= ret;
+			con->out_kvec_cur->iov_base += ret;
 		}
 	}
 	con->out_kvec_left = 0;
@@ -773,7 +818,7 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 	struct ceph_msg *msg = con->out_msg;
 	unsigned data_len = le32_to_cpu(msg->hdr.data_len);
 	size_t len;
-	int crc = con->msgr->nocrc;
+	bool do_datacrc = !con->msgr->nocrc;
 	int ret;
 	int total_max_write;
 	int in_trail = 0;
@@ -790,9 +835,8 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 
 	while (data_len > con->out_msg_pos.data_pos) {
 		struct page *page = NULL;
-		void *kaddr = NULL;
 		int max_write = PAGE_SIZE;
-		int page_shift = 0;
+		int bio_offset = 0;
 
 		total_max_write = data_len - trail_len -
 			con->out_msg_pos.data_pos;
@@ -811,58 +855,47 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 
 			page = list_first_entry(&msg->trail->head,
 						struct page, lru);
-			if (crc)
-				kaddr = kmap(page);
 			max_write = PAGE_SIZE;
 		} else if (msg->pages) {
 			page = msg->pages[con->out_msg_pos.page];
-			if (crc)
-				kaddr = kmap(page);
 		} else if (msg->pagelist) {
 			page = list_first_entry(&msg->pagelist->head,
 						struct page, lru);
-			if (crc)
-				kaddr = kmap(page);
 #ifdef CONFIG_BLOCK
 		} else if (msg->bio) {
 			struct bio_vec *bv;
 
 			bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg);
 			page = bv->bv_page;
-			page_shift = bv->bv_offset;
-			if (crc)
-				kaddr = kmap(page) + page_shift;
+			bio_offset = bv->bv_offset;
 			max_write = bv->bv_len;
 #endif
 		} else {
-			page = con->msgr->zero_page;
-			if (crc)
-				kaddr = page_address(con->msgr->zero_page);
+			page = zero_page;
 		}
 		len = min_t(int, max_write - con->out_msg_pos.page_pos,
 			    total_max_write);
 
-		if (crc && !con->out_msg_pos.did_page_crc) {
-			void *base = kaddr + con->out_msg_pos.page_pos;
+		if (do_datacrc && !con->out_msg_pos.did_page_crc) {
+			void *base;
+			u32 crc;
 			u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
+			char *kaddr;
 
+			kaddr = kmap(page);
 			BUG_ON(kaddr == NULL);
-			con->out_msg->footer.data_crc =
-				cpu_to_le32(crc32c(tmpcrc, base, len));
-			con->out_msg_pos.did_page_crc = 1;
+			base = kaddr + con->out_msg_pos.page_pos + bio_offset;
+			crc = crc32c(tmpcrc, base, len);
+			con->out_msg->footer.data_crc = cpu_to_le32(crc);
+			con->out_msg_pos.did_page_crc = true;
 		}
-		ret = kernel_sendpage(con->sock, page,
-				      con->out_msg_pos.page_pos + page_shift,
-				      len,
-				      MSG_DONTWAIT | MSG_NOSIGNAL |
-				      MSG_MORE);
-
-		if (crc &&
-		    (msg->pages || msg->pagelist || msg->bio || in_trail))
+		ret = ceph_tcp_sendpage(con->sock, page,
+				      con->out_msg_pos.page_pos + bio_offset,
+				      len, 1);
+
+		if (do_datacrc)
 			kunmap(page);
 
-		if (ret == -EAGAIN)
-			ret = 0;
 		if (ret <= 0)
 			goto out;
 
@@ -871,7 +904,7 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 		if (ret == len) {
 			con->out_msg_pos.page_pos = 0;
 			con->out_msg_pos.page++;
-			con->out_msg_pos.did_page_crc = 0;
+			con->out_msg_pos.did_page_crc = false;
 			if (in_trail)
 				list_move_tail(&page->lru,
 					       &msg->trail->head);
@@ -888,12 +921,10 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 	dout("write_partial_msg_pages %p msg %p done\n", con, msg);
 
 	/* prepare and queue up footer, too */
-	if (!crc)
+	if (!do_datacrc)
 		con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
-	con->out_kvec_bytes = 0;
-	con->out_kvec_left = 0;
-	con->out_kvec_cur = con->out_kvec;
-	prepare_write_message_footer(con, 0);
+	ceph_con_out_kvec_reset(con);
+	prepare_write_message_footer(con);
 	ret = 1;
 out:
 	return ret;
@@ -907,12 +938,9 @@ static int write_partial_skip(struct ceph_connection *con)
 	int ret;
 
 	while (con->out_skip > 0) {
-		struct kvec iov = {
-			.iov_base = page_address(con->msgr->zero_page),
-			.iov_len = min(con->out_skip, (int)PAGE_CACHE_SIZE)
-		};
+		size_t size = min(con->out_skip, (int) PAGE_CACHE_SIZE);
 
-		ret = ceph_tcp_sendmsg(con->sock, &iov, 1, iov.iov_len, 1);
+		ret = ceph_tcp_sendpage(con->sock, zero_page, 0, size, 1);
 		if (ret <= 0)
 			goto out;
 		con->out_skip -= ret;
@@ -1085,8 +1113,8 @@ static void addr_set_port(struct sockaddr_storage *ss, int p)
 static int ceph_pton(const char *str, size_t len, struct sockaddr_storage *ss,
 		char delim, const char **ipend)
 {
-	struct sockaddr_in *in4 = (void *)ss;
-	struct sockaddr_in6 *in6 = (void *)ss;
+	struct sockaddr_in *in4 = (struct sockaddr_in *) ss;
+	struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) ss;
 
 	memset(ss, 0, sizeof(*ss));
 
@@ -1512,10 +1540,9 @@ static int read_partial_message_section(struct ceph_connection *con,
 		if (ret <= 0)
 			return ret;
 		section->iov_len += ret;
-		if (section->iov_len == sec_len)
-			*crc = crc32c(0, section->iov_base,
-				      section->iov_len);
 	}
+	if (section->iov_len == sec_len)
+		*crc = crc32c(0, section->iov_base, section->iov_len);
 
 	return 1;
 }
@@ -1527,7 +1554,7 @@ static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
 
 static int read_partial_message_pages(struct ceph_connection *con,
 				      struct page **pages,
-				      unsigned data_len, int datacrc)
+				      unsigned data_len, bool do_datacrc)
 {
 	void *p;
 	int ret;
@@ -1540,7 +1567,7 @@ static int read_partial_message_pages(struct ceph_connection *con,
 	p = kmap(pages[con->in_msg_pos.page]);
 	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
 			       left);
-	if (ret > 0 && datacrc)
+	if (ret > 0 && do_datacrc)
 		con->in_data_crc =
 			crc32c(con->in_data_crc,
 				  p + con->in_msg_pos.page_pos, ret);
@@ -1560,7 +1587,7 @@ static int read_partial_message_pages(struct ceph_connection *con,
 #ifdef CONFIG_BLOCK
 static int read_partial_message_bio(struct ceph_connection *con,
 				    struct bio **bio_iter, int *bio_seg,
-				    unsigned data_len, int datacrc)
+				    unsigned data_len, bool do_datacrc)
 {
 	struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg);
 	void *p;
@@ -1576,7 +1603,7 @@ static int read_partial_message_bio(struct ceph_connection *con,
 
 	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
 			       left);
-	if (ret > 0 && datacrc)
+	if (ret > 0 && do_datacrc)
 		con->in_data_crc =
 			crc32c(con->in_data_crc,
 				  p + con->in_msg_pos.page_pos, ret);
@@ -1603,9 +1630,10 @@ static int read_partial_message(struct ceph_connection *con)
 	int ret;
 	int to, left;
 	unsigned front_len, middle_len, data_len;
-	int datacrc = con->msgr->nocrc;
+	bool do_datacrc = !con->msgr->nocrc;
 	int skip;
 	u64 seq;
+	u32 crc;
 
 	dout("read_partial_message con %p msg %p\n", con, m);
 
@@ -1618,17 +1646,16 @@ static int read_partial_message(struct ceph_connection *con)
 		if (ret <= 0)
 			return ret;
 		con->in_base_pos += ret;
-		if (con->in_base_pos == sizeof(con->in_hdr)) {
-			u32 crc = crc32c(0, (void *)&con->in_hdr,
-				 sizeof(con->in_hdr) - sizeof(con->in_hdr.crc));
-			if (crc != le32_to_cpu(con->in_hdr.crc)) {
-				pr_err("read_partial_message bad hdr "
-				       " crc %u != expected %u\n",
-				       crc, con->in_hdr.crc);
-				return -EBADMSG;
-			}
-		}
 	}
+
+	crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc));
+	if (cpu_to_le32(crc) != con->in_hdr.crc) {
+		pr_err("read_partial_message bad hdr "
+		       " crc %u != expected %u\n",
+		       crc, con->in_hdr.crc);
+		return -EBADMSG;
+	}
+
 	front_len = le32_to_cpu(con->in_hdr.front_len);
 	if (front_len > CEPH_MSG_MAX_FRONT_LEN)
 		return -EIO;
@@ -1714,7 +1741,7 @@ static int read_partial_message(struct ceph_connection *con)
 	while (con->in_msg_pos.data_pos < data_len) {
 		if (m->pages) {
 			ret = read_partial_message_pages(con, m->pages,
-						 data_len, datacrc);
+						 data_len, do_datacrc);
 			if (ret <= 0)
 				return ret;
 #ifdef CONFIG_BLOCK
@@ -1722,7 +1749,7 @@ static int read_partial_message(struct ceph_connection *con)
 
 			ret = read_partial_message_bio(con,
 						 &m->bio_iter, &m->bio_seg,
-						 data_len, datacrc);
+						 data_len, do_datacrc);
 			if (ret <= 0)
 				return ret;
 #endif
@@ -1757,7 +1784,7 @@ static int read_partial_message(struct ceph_connection *con)
 		       m, con->in_middle_crc, m->footer.middle_crc);
 		return -EBADMSG;
 	}
-	if (datacrc &&
+	if (do_datacrc &&
 	    (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 &&
 	    con->in_data_crc != le32_to_cpu(m->footer.data_crc)) {
 		pr_err("read_partial_message %p data crc %u != exp. %u\n", m,
@@ -1819,7 +1846,6 @@ more:
 
 	/* open the socket first? */
 	if (con->sock == NULL) {
-		prepare_write_banner(msgr, con);
 		prepare_write_connect(msgr, con, 1);
 		prepare_read_banner(con);
 		set_bit(CONNECTING, &con->state);
@@ -1829,11 +1855,9 @@ more:
 		con->in_tag = CEPH_MSGR_TAG_READY;
 		dout("try_write initiating connect on %p new state %lu\n",
 		     con, con->state);
-		con->sock = ceph_tcp_connect(con);
-		if (IS_ERR(con->sock)) {
-			con->sock = NULL;
+		ret = ceph_tcp_connect(con);
+		if (ret < 0) {
 			con->error_msg = "connect error";
-			ret = -1;
 			goto out;
 		}
 	}
@@ -1953,8 +1977,9 @@ more:
 		 *
 		 * FIXME: there must be a better way to do this!
 		 */
-		static char buf[1024];
-		int skip = min(1024, -con->in_base_pos);
+		static char buf[SKIP_BUF_SIZE];
+		int skip = min((int) sizeof (buf), -con->in_base_pos);
+
 		dout("skipping %d / %d bytes\n", skip, -con->in_base_pos);
 		ret = ceph_tcp_recvmsg(con->sock, buf, skip);
 		if (ret <= 0)
@@ -2216,15 +2241,6 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
 
 	spin_lock_init(&msgr->global_seq_lock);
 
-	/* the zero page is needed if a request is "canceled" while the message
-	 * is being written over the socket */
-	msgr->zero_page = __page_cache_alloc(GFP_KERNEL | __GFP_ZERO);
-	if (!msgr->zero_page) {
-		kfree(msgr);
-		return ERR_PTR(-ENOMEM);
-	}
-	kmap(msgr->zero_page);
-
 	if (myaddr)
 		msgr->inst.addr = *myaddr;
 
@@ -2241,8 +2257,6 @@ EXPORT_SYMBOL(ceph_messenger_create);
 void ceph_messenger_destroy(struct ceph_messenger *msgr)
 {
 	dout("destroy %p\n", msgr);
-	kunmap(msgr->zero_page);
-	__free_page(msgr->zero_page);
 	kfree(msgr);
 	dout("destroyed messenger %p\n", msgr);
 }
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index fd863fe76934..29ad46ec9dcf 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -283,7 +283,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 		ceph_decode_32_safe(p, end, yes, bad);
 #if BITS_PER_LONG == 32
 		err = -EINVAL;
-		if (yes > ULONG_MAX / sizeof(struct crush_rule_step))
+		if (yes > (ULONG_MAX - sizeof(*r))
+			  / sizeof(struct crush_rule_step))
 			goto bad;
 #endif
 		r = c->rules[i] = kmalloc(sizeof(*r) +
diff --git a/net/compat.c b/net/compat.c
index 64b4515a64e6..e055708b8ec9 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -219,8 +219,6 @@ Efault:
 
 int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data)
 {
-	struct compat_timeval ctv;
-	struct compat_timespec cts[3];
 	struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control;
 	struct compat_cmsghdr cmhdr;
 	int cmlen;
@@ -230,24 +228,28 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat
 		return 0; /* XXX: return error? check spec. */
 	}
 
-	if (level == SOL_SOCKET && type == SCM_TIMESTAMP) {
-		struct timeval *tv = (struct timeval *)data;
-		ctv.tv_sec = tv->tv_sec;
-		ctv.tv_usec = tv->tv_usec;
-		data = &ctv;
-		len = sizeof(ctv);
-	}
-	if (level == SOL_SOCKET &&
-	    (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) {
-		int count = type == SCM_TIMESTAMPNS ? 1 : 3;
-		int i;
-		struct timespec *ts = (struct timespec *)data;
-		for (i = 0; i < count; i++) {
-			cts[i].tv_sec = ts[i].tv_sec;
-			cts[i].tv_nsec = ts[i].tv_nsec;
+	if (!COMPAT_USE_64BIT_TIME) {
+		struct compat_timeval ctv;
+		struct compat_timespec cts[3];
+		if (level == SOL_SOCKET && type == SCM_TIMESTAMP) {
+			struct timeval *tv = (struct timeval *)data;
+			ctv.tv_sec = tv->tv_sec;
+			ctv.tv_usec = tv->tv_usec;
+			data = &ctv;
+			len = sizeof(ctv);
+		}
+		if (level == SOL_SOCKET &&
+		    (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) {
+			int count = type == SCM_TIMESTAMPNS ? 1 : 3;
+			int i;
+			struct timespec *ts = (struct timespec *)data;
+			for (i = 0; i < count; i++) {
+				cts[i].tv_sec = ts[i].tv_sec;
+				cts[i].tv_nsec = ts[i].tv_nsec;
+			}
+			data = &cts;
+			len = sizeof(cts[0]) * count;
 		}
-		data = &cts;
-		len = sizeof(cts[0]) * count;
 	}
 
 	cmlen = CMSG_COMPAT_LEN(len);
@@ -454,11 +456,15 @@ static int compat_sock_getsockopt(struct socket *sock, int level, int optname,
 
 int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 {
-	struct compat_timeval __user *ctv =
-			(struct compat_timeval __user *) userstamp;
-	int err = -ENOENT;
+	struct compat_timeval __user *ctv;
+	int err;
 	struct timeval tv;
 
+	if (COMPAT_USE_64BIT_TIME)
+		return sock_get_timestamp(sk, userstamp);
+
+	ctv = (struct compat_timeval __user *) userstamp;
+	err = -ENOENT;
 	if (!sock_flag(sk, SOCK_TIMESTAMP))
 		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
 	tv = ktime_to_timeval(sk->sk_stamp);
@@ -478,11 +484,15 @@ EXPORT_SYMBOL(compat_sock_get_timestamp);
 
 int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
 {
-	struct compat_timespec __user *ctv =
-			(struct compat_timespec __user *) userstamp;
-	int err = -ENOENT;
+	struct compat_timespec __user *ctv;
+	int err;
 	struct timespec ts;
 
+	if (COMPAT_USE_64BIT_TIME)
+		return sock_get_timestampns (sk, userstamp);
+
+	ctv = (struct compat_timespec __user *) userstamp;
+	err = -ENOENT;
 	if (!sock_flag(sk, SOCK_TIMESTAMP))
 		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
 	ts = ktime_to_timespec(sk->sk_stamp);
@@ -767,6 +777,11 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
 	int datagrams;
 	struct timespec ktspec;
 
+	if (COMPAT_USE_64BIT_TIME)
+		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+				      flags | MSG_CMSG_COMPAT,
+				      (struct timespec *) timeout);
+
 	if (timeout == NULL)
 		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 				      flags | MSG_CMSG_COMPAT, NULL);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index d3cf12f62c8f..e4fbfd6e2bd4 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -37,7 +37,6 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/errno.h>
diff --git a/net/core/dev.c b/net/core/dev.c
index 723a4065a00e..c25d453b2803 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -73,7 +73,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -4029,54 +4028,41 @@ static int dev_ifconf(struct net *net, char __user *arg)
 
 #ifdef CONFIG_PROC_FS
 
-#define BUCKET_SPACE (32 - NETDEV_HASHBITS)
-
-struct dev_iter_state {
-	struct seq_net_private p;
-	unsigned int pos; /* bucket << BUCKET_SPACE + offset */
-};
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
 
 #define get_bucket(x) ((x) >> BUCKET_SPACE)
 #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
 #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
 
-static inline struct net_device *dev_from_same_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
 {
-	struct dev_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct net_device *dev;
 	struct hlist_node *p;
 	struct hlist_head *h;
-	unsigned int count, bucket, offset;
+	unsigned int count = 0, offset = get_offset(*pos);
 
-	bucket = get_bucket(state->pos);
-	offset = get_offset(state->pos);
-	h = &net->dev_name_head[bucket];
-	count = 0;
+	h = &net->dev_name_head[get_bucket(*pos)];
 	hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
-		if (count++ == offset) {
-			state->pos = set_bucket_offset(bucket, count);
+		if (++count == offset)
 			return dev;
-		}
 	}
 
 	return NULL;
 }
 
-static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
 {
-	struct dev_iter_state *state = seq->private;
 	struct net_device *dev;
 	unsigned int bucket;
 
-	bucket = get_bucket(state->pos);
 	do {
-		dev = dev_from_same_bucket(seq);
+		dev = dev_from_same_bucket(seq, pos);
 		if (dev)
 			return dev;
 
-		bucket++;
-		state->pos = set_bucket_offset(bucket, 0);
+		bucket = get_bucket(*pos) + 1;
+		*pos = set_bucket_offset(bucket, 1);
 	} while (bucket < NETDEV_HASHENTRIES);
 
 	return NULL;
@@ -4089,33 +4075,20 @@ static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
 void *dev_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
-	struct dev_iter_state *state = seq->private;
-
 	rcu_read_lock();
 	if (!*pos)
 		return SEQ_START_TOKEN;
 
-	/* check for end of the hash */
-	if (state->pos == 0 && *pos > 1)
+	if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
 		return NULL;
 
-	return dev_from_new_bucket(seq);
+	return dev_from_bucket(seq, pos);
 }
 
 void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct net_device *dev;
-
 	++*pos;
-
-	if (v == SEQ_START_TOKEN)
-		return dev_from_new_bucket(seq);
-
-	dev = dev_from_same_bucket(seq);
-	if (dev)
-		return dev;
-
-	return dev_from_new_bucket(seq);
+	return dev_from_bucket(seq, pos);
 }
 
 void dev_seq_stop(struct seq_file *seq, void *v)
@@ -4214,13 +4187,7 @@ static const struct seq_operations dev_seq_ops = {
 static int dev_seq_open(struct inode *inode, struct file *file)
 {
 	return seq_open_net(inode, file, &dev_seq_ops,
-			    sizeof(struct dev_iter_state));
-}
-
-int dev_seq_open_ops(struct inode *inode, struct file *file,
-		     const struct seq_operations *ops)
-{
-	return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations dev_seq_fops = {
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 29c07fef9228..626698f0db8b 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -696,7 +696,8 @@ static const struct seq_operations dev_mc_seq_ops = {
 
 static int dev_mc_seq_open(struct inode *inode, struct file *file)
 {
-	return dev_seq_open_ops(inode, file, &dev_mc_seq_ops);
+	return seq_open_net(inode, file, &dev_mc_seq_ops,
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations dev_mc_seq_fops = {
diff --git a/net/core/filter.c b/net/core/filter.c
index 5099c4b4a53f..95d05a6012d1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -33,15 +33,17 @@
 #include <net/sock.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/filter.h>
 #include <linux/reciprocal_div.h>
 #include <linux/ratelimit.h>
 
-/* No hurry in this branch */
-static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
+/* No hurry in this branch
+ *
+ * Exported for the bpf jit load helper.
+ */
+void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
 {
 	u8 *ptr = NULL;
 
@@ -60,7 +62,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k,
 {
 	if (k >= 0)
 		return skb_header_pointer(skb, k, size, buffer);
-	return __load_pointer(skb, k, size);
+	return bpf_internal_load_pointer_neg_helper(skb, k, size);
 }
 
 /**
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 43b03dd71e85..d9d198aa9fed 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -14,7 +14,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/types.h>
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b76f8fa3fc64..545a969672ab 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -38,7 +38,6 @@
 #include <linux/pci.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include <linux/inet.h>
 #include <linux/netdevice.h>
diff --git a/net/core/scm.c b/net/core/scm.c
index ff52ad0a5150..611c5efd4cb0 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -28,7 +28,6 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include <net/protocol.h>
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b2595adb605f..a396a6926238 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -66,7 +66,6 @@
 #include <net/xfrm.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <trace/events/skb.h>
 #include <linux/highmem.h>
 
@@ -3162,6 +3161,8 @@ static void sock_rmem_free(struct sk_buff *skb)
  */
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 {
+	int len = skb->len;
+
 	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
 	    (unsigned)sk->sk_rcvbuf)
 		return -ENOMEM;
@@ -3176,7 +3177,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 
 	skb_queue_tail(&sk->sk_error_queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk, len);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index 9be6d0d6c533..b2e14c07d920 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -115,7 +115,6 @@
 #include <linux/memcontrol.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include <linux/netdevice.h>
 #include <net/protocol.h>
diff --git a/net/core/utils.c b/net/core/utils.c
index 386e263f6066..dc3c3faff2f4 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -30,7 +30,6 @@
 #include <net/net_ratelimit.h>
 
 #include <asm/byteorder.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 int net_msg_warn __read_mostly = 1;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 19acd00a6382..4136987d94da 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -119,7 +119,6 @@ Version 0.0.6    2.1.110   07-aug-98   Eduardo Marcelo Serrat
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <net/flow.h>
-#include <asm/system.h>
 #include <asm/ioctls.h>
 #include <linux/capability.h>
 #include <linux/mm.h>
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 16efcda2f060..a4aecb09d12a 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -42,7 +42,6 @@
 #include <linux/notifier.h>
 #include <linux/slab.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <net/net_namespace.h>
 #include <net/neighbour.h>
 #include <net/dst.h>
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index 73fa268fe2e8..f6544b2c91b0 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -60,7 +60,6 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/termios.h>
diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c
index bd78836a81eb..e446e85e64a6 100644
--- a/net/decnet/dn_nsp_out.c
+++ b/net/decnet/dn_nsp_out.c
@@ -52,7 +52,6 @@
 #include <linux/route.h>
 #include <linux/slab.h>
 #include <net/sock.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/termios.h>
diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c
index 7e717cb35ad1..71b5edcee401 100644
--- a/net/econet/af_econet.c
+++ b/net/econet/af_econet.c
@@ -47,7 +47,6 @@
 #include <linux/mutex.h>
 
 #include <linux/uaccess.h>
-#include <asm/system.h>
 
 static const struct proto_ops econet_ops;
 static struct hlist_head econet_sklist;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index a93af86b8474..bf10a311cf1c 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -59,7 +59,6 @@
 #include <net/ip.h>
 #include <net/dsa.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 __setup("ether=", netdev_boot_setup);
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index fdf49fd44bb4..10e3751466b5 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -91,7 +91,6 @@
 #include <linux/slab.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 #include <linux/inet.h>
 #include <linux/igmp.h>
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 73f46d691abc..18d9b81ecb1a 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -113,7 +113,6 @@
 #include <net/ax25.h>
 #include <net/netrom.h>
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 
 #include <linux/netfilter_arp.h>
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 3ffaad0ef98f..7ba2196e4377 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -27,7 +27,6 @@
 
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/capability.h>
 #include <linux/module.h>
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 76e72bacc217..cbe3a68507cf 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -15,7 +15,6 @@
 
 #include <linux/module.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/capability.h>
 #include <linux/types.h>
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 63aa48acc98a..a8bdf7405433 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -14,7 +14,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index da9b9cb2282d..bce36f1a37b4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -51,7 +51,6 @@
 #define VERSION "0.409"
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 9664d353ccd8..2cb2bf845641 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -91,7 +91,6 @@
 #include <linux/errno.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index e9b90a8ca55a..ceaac24ecdca 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -73,7 +73,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/jiffies.h>
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index f3f1108940f5..26eccc5bab1c 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -115,7 +115,6 @@
 
 #define pr_fmt(fmt) "IPv4: " fmt
 
-#include <asm/system.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ff302bde8890..4910176d24ed 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -43,7 +43,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index dcf4d7fe3917..5bef604ac0fa 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -26,7 +26,6 @@
  *
  */
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/types.h>
 #include <linux/capability.h>
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index ab6b36e6da15..50009c787bcd 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -20,7 +20,6 @@
  *
  */
 
-#include <asm/system.h>
 #include <linux/uaccess.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 634aa824b17e..e4d18f2a305d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -66,7 +66,6 @@
 
 #include <linux/module.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cfd7edda0a8e..5d54ed30e821 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -860,7 +860,7 @@ wait_for_memory:
 	}
 
 out:
-	if (copied)
+	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
 		tcp_push(sk, flags, mss_now, tp->nonagle);
 	return copied;
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d6f5feeb3eaf..fe141052a1be 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -79,7 +79,6 @@
 
 #define pr_fmt(fmt) "UDP: " fmt
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
 #include <linux/bootmem.h>
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 5605f9dca87e..8ed1b930e75f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -60,7 +60,6 @@
 #endif
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/mroute6.h>
 
 MODULE_AUTHOR("Cast of dozens");
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 6dd59f160da4..cc079d8d4681 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -66,7 +66,6 @@
 #include <net/inet_common.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 
 /*
  *	The ICMP socket(s). This is the most convenient way to flow control
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index ff6ddf93f269..efc0098b59dd 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -16,7 +16,6 @@
  *
  */
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/types.h>
 #include <linux/sched.h>
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 6264d8fd2a2d..7dfb89f2bae5 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2044,7 +2044,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 		if (!delta)
 			pmc->mca_sfcount[sfmode]--;
 		for (j=0; j<i; j++)
-			(void) ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]);
+			ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]);
 	} else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) {
 		struct ip6_sf_list *psf;
 
diff --git a/net/irda/irlan/irlan_client.c b/net/irda/irlan/irlan_client.c
index ba1a3fc39b5c..42cf1390ce9c 100644
--- a/net/irda/irlan/irlan_client.c
+++ b/net/irda/irlan/irlan_client.c
@@ -37,7 +37,6 @@
 #include <linux/bitops.h>
 #include <net/arp.h>
 
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 #include <net/irda/irda.h>
diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c
index 579617cca125..7ac4d1becbfc 100644
--- a/net/irda/irlan/irlan_common.c
+++ b/net/irda/irlan/irlan_common.c
@@ -40,7 +40,6 @@
 #include <linux/moduleparam.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 #include <net/irda/irda.h>
diff --git a/net/irda/irlan/irlan_provider.c b/net/irda/irlan/irlan_provider.c
index 8b61cf0d8a69..32dcaac70b0c 100644
--- a/net/irda/irlan/irlan_provider.c
+++ b/net/irda/irlan/irlan_provider.c
@@ -36,7 +36,6 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/byteorder.h>
 
 #include <net/irda/irda.h>
diff --git a/net/irda/timer.c b/net/irda/timer.c
index f418cb2ad49c..1d552b3946fc 100644
--- a/net/irda/timer.c
+++ b/net/irda/timer.c
@@ -24,7 +24,6 @@
  *
  ********************************************************************/
 
-#include <asm/system.h>
 #include <linux/delay.h>
 
 #include <net/irda/timer.h>
diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index 8d0324bac01c..ab3d35f23257 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -32,7 +32,6 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/lapb/lapb_in.c b/net/lapb/lapb_in.c
index 2ec1af5c36cc..f4e3c1accab7 100644
--- a/net/lapb/lapb_in.c
+++ b/net/lapb/lapb_in.c
@@ -30,7 +30,6 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c
index c75a79540f9f..baab2760f651 100644
--- a/net/lapb/lapb_out.c
+++ b/net/lapb/lapb_out.c
@@ -28,7 +28,6 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/lapb/lapb_subr.c b/net/lapb/lapb_subr.c
index 43a2a7fb327b..066225b4e824 100644
--- a/net/lapb/lapb_subr.c
+++ b/net/lapb/lapb_subr.c
@@ -27,7 +27,6 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c
index af6d14b44e2e..f8cd641dfc82 100644
--- a/net/lapb/lapb_timer.c
+++ b/net/lapb/lapb_timer.c
@@ -28,7 +28,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index cc5b7a6e7e0b..778e5916d7c3 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -15,12 +15,6 @@
 #include "rate.h"
 #include "debugfs.h"
 
-int mac80211_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 #define DEBUGFS_FORMAT_BUFFER_SIZE 100
 
 int mac80211_format_buffer(char __user *userbuf, size_t count,
@@ -50,7 +44,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf,	\
 #define DEBUGFS_READONLY_FILE_OPS(name)			\
 static const struct file_operations name## _ops = {			\
 	.read = name## _read,						\
-	.open = mac80211_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
@@ -93,7 +87,7 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf,
 
 static const struct file_operations reset_ops = {
 	.write = reset_write,
-	.open = mac80211_open_file_generic,
+	.open = simple_open,
 	.llseek = noop_llseek,
 };
 
@@ -254,7 +248,7 @@ static ssize_t stats_ ##name## _read(struct file *file,			\
 									\
 static const struct file_operations stats_ ##name## _ops = {		\
 	.read = stats_ ##name## _read,					\
-	.open = mac80211_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
diff --git a/net/mac80211/debugfs.h b/net/mac80211/debugfs.h
index 7c87529630f5..9be4e6d71d00 100644
--- a/net/mac80211/debugfs.h
+++ b/net/mac80211/debugfs.h
@@ -3,7 +3,6 @@
 
 #ifdef CONFIG_MAC80211_DEBUGFS
 extern void debugfs_hw_add(struct ieee80211_local *local);
-extern int mac80211_open_file_generic(struct inode *inode, struct file *file);
 extern int mac80211_format_buffer(char __user *userbuf, size_t count,
 				  loff_t *ppos, char *fmt, ...);
 #else
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 59edcd95a58d..7932767bb482 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -30,7 +30,7 @@ static ssize_t key_##name##_read(struct file *file,			\
 #define KEY_OPS(name)							\
 static const struct file_operations key_ ##name## _ops = {		\
 	.read = key_##name##_read,					\
-	.open = mac80211_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 }
 
@@ -45,7 +45,7 @@ static const struct file_operations key_ ##name## _ops = {		\
 #define KEY_CONF_OPS(name)						\
 static const struct file_operations key_ ##name## _ops = {		\
 	.read = key_conf_##name##_read,					\
-	.open = mac80211_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 }
 
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index a32eeda04aa3..30f99c344847 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -135,7 +135,7 @@ static ssize_t ieee80211_if_read_##name(struct file *file,		\
 static const struct file_operations name##_ops = {			\
 	.read = ieee80211_if_read_##name,				\
 	.write = (_write),						\
-	.open = mac80211_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 }
 
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 6d45804d09bc..832b2da5e4cd 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -33,7 +33,7 @@ static ssize_t sta_ ##name## _read(struct file *file,			\
 #define STA_OPS(name)							\
 static const struct file_operations sta_ ##name## _ops = {		\
 	.read = sta_##name##_read,					\
-	.open = mac80211_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 }
 
@@ -41,7 +41,7 @@ static const struct file_operations sta_ ##name## _ops = {		\
 static const struct file_operations sta_ ##name## _ops = {		\
 	.read = sta_##name##_read,					\
 	.write = sta_##name##_write,					\
-	.open = mac80211_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 }
 
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index b4f7600a3e36..3313c117b322 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -145,7 +145,7 @@ static ssize_t rcname_read(struct file *file, char __user *userbuf,
 
 static const struct file_operations rcname_ops = {
 	.read = rcname_read,
-	.open = mac80211_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 #endif
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index fe6cb4304d72..52856178c9d7 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -31,7 +31,6 @@
 #include <net/net_namespace.h>
 #include <net/protocol.h>
 #include <net/tcp.h>
-#include <asm/system.h>
 #include <linux/stat.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 85312939695f..f843a8833250 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -25,7 +25,6 @@
 #include <net/protocol.h>
 #include <net/tcp.h>
 #include <net/udp.h>
-#include <asm/system.h>
 #include <linux/stat.h>
 #include <linux/proc_fs.h>
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index b0ab8c43abe7..6cd8e32e281c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -735,6 +735,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 out_free:
+	atomic_dec(&net->ct.count);
 	kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
 	return ERR_PTR(-ENOMEM);
 #endif
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4d70785b953d..e6ddde165612 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -23,7 +23,6 @@
 #include <linux/net.h>
 #include <linux/skbuff.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <net/sock.h>
 #include <net/netlink.h>
 #include <linux/init.h>
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 0c8e43810ce3..59530e93fa58 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -150,6 +150,17 @@ err1:
 	return ret;
 }
 
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+static void __xt_ct_tg_timeout_put(struct ctnl_timeout *timeout)
+{
+	typeof(nf_ct_timeout_put_hook) timeout_put;
+
+	timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
+	if (timeout_put)
+		timeout_put(timeout);
+}
+#endif
+
 static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 {
 	struct xt_ct_target_info_v1 *info = par->targinfo;
@@ -158,7 +169,9 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 	struct nf_conn *ct;
 	int ret = 0;
 	u8 proto;
-
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+	struct ctnl_timeout *timeout;
+#endif
 	if (info->flags & ~XT_CT_NOTRACK)
 		return -EINVAL;
 
@@ -216,7 +229,6 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 	if (info->timeout) {
 		typeof(nf_ct_timeout_find_get_hook) timeout_find_get;
-		struct ctnl_timeout *timeout;
 		struct nf_conn_timeout *timeout_ext;
 
 		rcu_read_lock();
@@ -245,7 +257,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 				pr_info("Timeout policy `%s' can only be "
 					"used by L3 protocol number %d\n",
 					info->timeout, timeout->l3num);
-				goto err4;
+				goto err5;
 			}
 			/* Make sure the timeout policy matches any existing
 			 * protocol tracker, otherwise default to generic.
@@ -258,13 +270,13 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 					"used by L4 protocol number %d\n",
 					info->timeout,
 					timeout->l4proto->l4proto);
-				goto err4;
+				goto err5;
 			}
 			timeout_ext = nf_ct_timeout_ext_add(ct, timeout,
-							    GFP_KERNEL);
+							    GFP_ATOMIC);
 			if (timeout_ext == NULL) {
 				ret = -ENOMEM;
-				goto err4;
+				goto err5;
 			}
 		} else {
 			ret = -ENOENT;
@@ -281,8 +293,12 @@ out:
 	info->ct = ct;
 	return 0;
 
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+err5:
+	__xt_ct_tg_timeout_put(timeout);
 err4:
 	rcu_read_unlock();
+#endif
 err3:
 	nf_conntrack_free(ct);
 err2:
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 32bb75324e76..faa48f70b7c9 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -829,12 +829,19 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 	return 0;
 }
 
-int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
+static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 {
 	int len = skb->len;
 
 	skb_queue_tail(&sk->sk_receive_queue, skb);
 	sk->sk_data_ready(sk, len);
+	return len;
+}
+
+int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
+{
+	int len = __netlink_sendskb(sk, skb);
+
 	sock_put(sk);
 	return len;
 }
@@ -957,8 +964,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
 	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
 	    !test_bit(0, &nlk->state)) {
 		skb_set_owner_r(skb, sk);
-		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
+		__netlink_sendskb(sk, skb);
 		return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
 	}
 	return -1;
@@ -1698,10 +1704,8 @@ static int netlink_dump(struct sock *sk)
 
 		if (sk_filter(sk, skb))
 			kfree_skb(skb);
-		else {
-			skb_queue_tail(&sk->sk_receive_queue, skb);
-			sk->sk_data_ready(sk, skb->len);
-		}
+		else
+			__netlink_sendskb(sk, skb);
 		return 0;
 	}
 
@@ -1715,10 +1719,8 @@ static int netlink_dump(struct sock *sk)
 
 	if (sk_filter(sk, skb))
 		kfree_skb(skb);
-	else {
-		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
-	}
+	else
+		__netlink_sendskb(sk, skb);
 
 	if (cb->done)
 		cb->done(cb);
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 7dab229bfbcc..06592d8b4a2b 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -31,7 +31,6 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>
diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c
index 64e6dde9749d..1c51d7a58f0b 100644
--- a/net/netrom/nr_dev.c
+++ b/net/netrom/nr_dev.c
@@ -21,7 +21,6 @@
 #include <linux/if_ether.h>	/* For the statistics structure. */
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 
diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c
index 6d4ef6d65b3d..c3073a2ef634 100644
--- a/net/netrom/nr_in.c
+++ b/net/netrom/nr_in.c
@@ -24,7 +24,6 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c
index 607fddb4fdbb..0b4bcb2bf38f 100644
--- a/net/netrom/nr_out.c
+++ b/net/netrom/nr_out.c
@@ -23,7 +23,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 2cf330162d7e..70ffff76a967 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -26,7 +26,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>
diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c
index 6a947ae50dbd..ca40e2298f5a 100644
--- a/net/netrom/nr_subr.c
+++ b/net/netrom/nr_subr.c
@@ -23,7 +23,6 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index 1cb98e88f5e1..ff2c1b142f57 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -24,7 +24,6 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index f5ca1257debf..f86de29979ef 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -38,7 +38,6 @@
 #include <linux/udp.h>
 #include <linux/ethtool.h>
 #include <linux/wait.h>
-#include <asm/system.h>
 #include <asm/div64.h>
 #include <linux/highmem.h>
 #include <linux/netfilter_bridge.h>
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ae2d484416dd..4f2c0df79563 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -73,7 +73,6 @@
 #include <net/sock.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
 #include <asm/page.h>
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 9f60008740e3..9726fe684ab8 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -1130,6 +1130,9 @@ static int pep_sendmsg(struct kiocb *iocb, struct sock *sk,
 	int flags = msg->msg_flags;
 	int err, done;
 
+	if (len > USHRT_MAX)
+		return -EMSGSIZE;
+
 	if ((msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL|
 				MSG_CMSG_COMPAT)) ||
 			!(msg->msg_flags & MSG_EOR))
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index f9ea925ad9cb..c4719ce604c2 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -34,7 +34,6 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>
diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c
index 2679507ad333..906cc05bba63 100644
--- a/net/rose/rose_dev.c
+++ b/net/rose/rose_dev.c
@@ -21,7 +21,6 @@
 #include <linux/if_ether.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 
 #include <linux/inet.h>
diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c
index 7f7fcb46b4fa..79c4abcfa6b4 100644
--- a/net/rose/rose_in.c
+++ b/net/rose/rose_in.c
@@ -26,7 +26,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c
index 7a02bd1cc5a0..bc5514211b0c 100644
--- a/net/rose/rose_link.c
+++ b/net/rose/rose_link.c
@@ -22,7 +22,6 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/rose/rose_out.c b/net/rose/rose_out.c
index 4ebf33afbe47..9ad98b524646 100644
--- a/net/rose/rose_out.c
+++ b/net/rose/rose_out.c
@@ -21,7 +21,6 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index cd9b7ee60f3e..40148932c8a4 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -25,7 +25,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
diff --git a/net/rose/rose_subr.c b/net/rose/rose_subr.c
index f6c71caa94b9..47f1fdb346b0 100644
--- a/net/rose/rose_subr.c
+++ b/net/rose/rose_subr.c
@@ -22,7 +22,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index b6c8f38cc26c..bc5469d6d9cb 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -23,7 +23,6 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/system.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 06b42b7f5a02..92ba71dfe080 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4133,9 +4133,10 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len,
 static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval,
 				  int __user *optlen)
 {
-	if (len < sizeof(struct sctp_event_subscribe))
+	if (len <= 0)
 		return -EINVAL;
-	len = sizeof(struct sctp_event_subscribe);
+	if (len > sizeof(struct sctp_event_subscribe))
+		len = sizeof(struct sctp_event_subscribe);
 	if (put_user(len, optlen))
 		return -EFAULT;
 	if (copy_to_user(optval, &sctp_sk(sk)->subscribe, len))
diff --git a/net/socket.c b/net/socket.c
index 12a48d846223..851edcd6b098 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -811,9 +811,9 @@ static ssize_t sock_sendpage(struct file *file, struct page *page,
 
 	sock = file->private_data;
 
-	flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT;
-	if (more)
-		flags |= MSG_MORE;
+	flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
+	/* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */
+	flags |= more;
 
 	return kernel_sendpage(sock, page, offset, size, flags);
 }
@@ -2592,7 +2592,7 @@ void socket_seq_show(struct seq_file *seq)
 
 #ifdef CONFIG_COMPAT
 static int do_siocgstamp(struct net *net, struct socket *sock,
-			 unsigned int cmd, struct compat_timeval __user *up)
+			 unsigned int cmd, void __user *up)
 {
 	mm_segment_t old_fs = get_fs();
 	struct timeval ktv;
@@ -2601,15 +2601,14 @@ static int do_siocgstamp(struct net *net, struct socket *sock,
 	set_fs(KERNEL_DS);
 	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
 	set_fs(old_fs);
-	if (!err) {
-		err = put_user(ktv.tv_sec, &up->tv_sec);
-		err |= __put_user(ktv.tv_usec, &up->tv_usec);
-	}
+	if (!err)
+		err = compat_put_timeval(up, &ktv);
+
 	return err;
 }
 
 static int do_siocgstampns(struct net *net, struct socket *sock,
-			 unsigned int cmd, struct compat_timespec __user *up)
+			   unsigned int cmd, void __user *up)
 {
 	mm_segment_t old_fs = get_fs();
 	struct timespec kts;
@@ -2618,10 +2617,9 @@ static int do_siocgstampns(struct net *net, struct socket *sock,
 	set_fs(KERNEL_DS);
 	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
 	set_fs(old_fs);
-	if (!err) {
-		err = put_user(kts.tv_sec, &up->tv_sec);
-		err |= __put_user(kts.tv_nsec, &up->tv_nsec);
-	}
+	if (!err)
+		err = compat_put_timespec(up, &kts);
+
 	return err;
 }
 
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index f21ece088764..de0b0f39d9d8 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -830,6 +830,8 @@ static ssize_t cache_do_downcall(char *kaddr, const char __user *buf,
 {
 	ssize_t ret;
 
+	if (count == 0)
+		return -EINVAL;
 	if (copy_from_user(kaddr, buf, count))
 		return -EFAULT;
 	kaddr[count] = '\0';
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 7a4cb5fdc212..67972462a543 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -17,7 +17,6 @@
  *  Copyright (C) 1995,1996 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <asm/system.h>
 
 #include <linux/module.h>
 #include <linux/types.h>
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index c84c0e0c41cb..0af37fc46818 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1014,6 +1014,7 @@ enum {
 	RPCAUTH_statd,
 	RPCAUTH_nfsd4_cb,
 	RPCAUTH_cache,
+	RPCAUTH_nfsd,
 	RPCAUTH_RootEOF
 };
 
@@ -1046,6 +1047,10 @@ static const struct rpc_filelist files[] = {
 		.name = "cache",
 		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
 	},
+	[RPCAUTH_nfsd] = {
+		.name = "nfsd",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
 };
 
 /*
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 207a74696c9f..78ac39fd9fe7 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -734,7 +734,7 @@ void rpcb_getport_async(struct rpc_task *task)
 	map->r_vers = clnt->cl_vers;
 	map->r_prot = xprt->prot;
 	map->r_port = 0;
-	map->r_xprt = xprt_get(xprt);
+	map->r_xprt = xprt;
 	map->r_status = -EIO;
 
 	switch (bind_version) {
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index bcd574f2ac56..521d8f7dc833 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -507,7 +507,7 @@ static int unix_gid_parse(struct cache_detail *cd,
 	time_t expiry;
 	struct unix_gid ug, *ugp;
 
-	if (mlen <= 0 || mesg[mlen-1] != '\n')
+	if (mesg[mlen - 1] != '\n')
 		return -EINVAL;
 	mesg[mlen-1] = 0;
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 40ae884db865..824d32fb3121 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1381,8 +1381,6 @@ void svc_sock_update_bufs(struct svc_serv *serv)
 	spin_lock_bh(&serv->sv_lock);
 	list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list)
 		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
-	list_for_each_entry(svsk, &serv->sv_tempsocks, sk_xprt.xpt_list)
-		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
 	spin_unlock_bh(&serv->sv_lock);
 }
 EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index 09af4fab1a45..8343737e85f4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -47,6 +47,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/svc_rdma.h>
+#include "xprt_rdma.h"
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 9530ef2d40dc..8d2edddf48cf 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -60,21 +60,11 @@ static u32 *decode_read_list(u32 *va, u32 *vaend)
 	struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va;
 
 	while (ch->rc_discrim != xdr_zero) {
-		u64 ch_offset;
-
 		if (((unsigned long)ch + sizeof(struct rpcrdma_read_chunk)) >
 		    (unsigned long)vaend) {
 			dprintk("svcrdma: vaend=%p, ch=%p\n", vaend, ch);
 			return NULL;
 		}
-
-		ch->rc_discrim = ntohl(ch->rc_discrim);
-		ch->rc_position = ntohl(ch->rc_position);
-		ch->rc_target.rs_handle = ntohl(ch->rc_target.rs_handle);
-		ch->rc_target.rs_length = ntohl(ch->rc_target.rs_length);
-		va = (u32 *)&ch->rc_target.rs_offset;
-		xdr_decode_hyper(va, &ch_offset);
-		put_unaligned(ch_offset, (u64 *)va);
 		ch++;
 	}
 	return (u32 *)&ch->rc_position;
@@ -91,7 +81,7 @@ void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch,
 	*byte_count = 0;
 	*ch_count = 0;
 	for (; ch->rc_discrim != 0; ch++) {
-		*byte_count = *byte_count + ch->rc_target.rs_length;
+		*byte_count = *byte_count + ntohl(ch->rc_target.rs_length);
 		*ch_count = *ch_count + 1;
 	}
 }
@@ -108,7 +98,8 @@ void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch,
  */
 static u32 *decode_write_list(u32 *va, u32 *vaend)
 {
-	int ch_no;
+	int nchunks;
+
 	struct rpcrdma_write_array *ary =
 		(struct rpcrdma_write_array *)va;
 
@@ -121,37 +112,24 @@ static u32 *decode_write_list(u32 *va, u32 *vaend)
 		dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
 		return NULL;
 	}
-	ary->wc_discrim = ntohl(ary->wc_discrim);
-	ary->wc_nchunks = ntohl(ary->wc_nchunks);
+	nchunks = ntohl(ary->wc_nchunks);
 	if (((unsigned long)&ary->wc_array[0] +
-	     (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) >
+	     (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
 	    (unsigned long)vaend) {
 		dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
-			ary, ary->wc_nchunks, vaend);
+			ary, nchunks, vaend);
 		return NULL;
 	}
-	for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) {
-		u64 ch_offset;
-
-		ary->wc_array[ch_no].wc_target.rs_handle =
-			ntohl(ary->wc_array[ch_no].wc_target.rs_handle);
-		ary->wc_array[ch_no].wc_target.rs_length =
-			ntohl(ary->wc_array[ch_no].wc_target.rs_length);
-		va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset;
-		xdr_decode_hyper(va, &ch_offset);
-		put_unaligned(ch_offset, (u64 *)va);
-	}
-
 	/*
 	 * rs_length is the 2nd 4B field in wc_target and taking its
 	 * address skips the list terminator
 	 */
-	return (u32 *)&ary->wc_array[ch_no].wc_target.rs_length;
+	return (u32 *)&ary->wc_array[nchunks].wc_target.rs_length;
 }
 
 static u32 *decode_reply_array(u32 *va, u32 *vaend)
 {
-	int ch_no;
+	int nchunks;
 	struct rpcrdma_write_array *ary =
 		(struct rpcrdma_write_array *)va;
 
@@ -164,28 +142,15 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend)
 		dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
 		return NULL;
 	}
-	ary->wc_discrim = ntohl(ary->wc_discrim);
-	ary->wc_nchunks = ntohl(ary->wc_nchunks);
+	nchunks = ntohl(ary->wc_nchunks);
 	if (((unsigned long)&ary->wc_array[0] +
-	     (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) >
+	     (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
 	    (unsigned long)vaend) {
 		dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
-			ary, ary->wc_nchunks, vaend);
+			ary, nchunks, vaend);
 		return NULL;
 	}
-	for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) {
-		u64 ch_offset;
-
-		ary->wc_array[ch_no].wc_target.rs_handle =
-			ntohl(ary->wc_array[ch_no].wc_target.rs_handle);
-		ary->wc_array[ch_no].wc_target.rs_length =
-			ntohl(ary->wc_array[ch_no].wc_target.rs_length);
-		va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset;
-		xdr_decode_hyper(va, &ch_offset);
-		put_unaligned(ch_offset, (u64 *)va);
-	}
-
-	return (u32 *)&ary->wc_array[ch_no];
+	return (u32 *)&ary->wc_array[nchunks];
 }
 
 int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req,
@@ -386,13 +351,14 @@ void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *ary,
 
 void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary,
 				     int chunk_no,
-				     u32 rs_handle, u64 rs_offset,
+				     __be32 rs_handle,
+				     __be64 rs_offset,
 				     u32 write_len)
 {
 	struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target;
-	seg->rs_handle = htonl(rs_handle);
+	seg->rs_handle = rs_handle;
+	seg->rs_offset = rs_offset;
 	seg->rs_length = htonl(write_len);
-	xdr_encode_hyper((u32 *) &seg->rs_offset, rs_offset);
 }
 
 void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index df67211c4baf..41cb63b623df 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -147,7 +147,7 @@ static int map_read_chunks(struct svcxprt_rdma *xprt,
 	page_off = 0;
 	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
 	ch_no = 0;
-	ch_bytes = ch->rc_target.rs_length;
+	ch_bytes = ntohl(ch->rc_target.rs_length);
 	head->arg.head[0] = rqstp->rq_arg.head[0];
 	head->arg.tail[0] = rqstp->rq_arg.tail[0];
 	head->arg.pages = &head->pages[head->count];
@@ -183,7 +183,7 @@ static int map_read_chunks(struct svcxprt_rdma *xprt,
 			ch_no++;
 			ch++;
 			chl_map->ch[ch_no].start = sge_no;
-			ch_bytes = ch->rc_target.rs_length;
+			ch_bytes = ntohl(ch->rc_target.rs_length);
 			/* If bytes remaining account for next chunk */
 			if (byte_count) {
 				head->arg.page_len += ch_bytes;
@@ -281,11 +281,12 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
 	offset = 0;
 	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
 	for (ch_no = 0; ch_no < ch_count; ch_no++) {
+		int len = ntohl(ch->rc_target.rs_length);
 		rpl_map->sge[ch_no].iov_base = frmr->kva + offset;
-		rpl_map->sge[ch_no].iov_len = ch->rc_target.rs_length;
+		rpl_map->sge[ch_no].iov_len = len;
 		chl_map->ch[ch_no].count = 1;
 		chl_map->ch[ch_no].start = ch_no;
-		offset += ch->rc_target.rs_length;
+		offset += len;
 		ch++;
 	}
 
@@ -316,7 +317,7 @@ static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt,
 	for (i = 0; i < count; i++) {
 		ctxt->sge[i].length = 0; /* in case map fails */
 		if (!frmr) {
-			BUG_ON(0 == virt_to_page(vec[i].iov_base));
+			BUG_ON(!virt_to_page(vec[i].iov_base));
 			off = (unsigned long)vec[i].iov_base & ~PAGE_MASK;
 			ctxt->sge[i].addr =
 				ib_dma_map_page(xprt->sc_cm_id->device,
@@ -426,6 +427,7 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt,
 
 	for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
 	     ch->rc_discrim != 0; ch++, ch_no++) {
+		u64 rs_offset;
 next_sge:
 		ctxt = svc_rdma_get_context(xprt);
 		ctxt->direction = DMA_FROM_DEVICE;
@@ -440,10 +442,10 @@ next_sge:
 		read_wr.opcode = IB_WR_RDMA_READ;
 		ctxt->wr_op = read_wr.opcode;
 		read_wr.send_flags = IB_SEND_SIGNALED;
-		read_wr.wr.rdma.rkey = ch->rc_target.rs_handle;
-		read_wr.wr.rdma.remote_addr =
-			get_unaligned(&(ch->rc_target.rs_offset)) +
-			sgl_offset;
+		read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle);
+		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
+				 &rs_offset);
+		read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset;
 		read_wr.sg_list = ctxt->sge;
 		read_wr.num_sge =
 			rdma_read_max_sge(xprt, chl_map->ch[ch_no].count);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 249a835b703f..42eb7ba0b903 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -409,21 +409,21 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
 		u64 rs_offset;
 
 		arg_ch = &arg_ary->wc_array[chunk_no].wc_target;
-		write_len = min(xfer_len, arg_ch->rs_length);
+		write_len = min(xfer_len, ntohl(arg_ch->rs_length));
 
 		/* Prepare the response chunk given the length actually
 		 * written */
-		rs_offset = get_unaligned(&(arg_ch->rs_offset));
+		xdr_decode_hyper((__be32 *)&arg_ch->rs_offset, &rs_offset);
 		svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
-					    arg_ch->rs_handle,
-					    rs_offset,
-					    write_len);
+						arg_ch->rs_handle,
+						arg_ch->rs_offset,
+						write_len);
 		chunk_off = 0;
 		while (write_len) {
 			int this_write;
 			this_write = min(write_len, max_write);
 			ret = send_write(xprt, rqstp,
-					 arg_ch->rs_handle,
+					 ntohl(arg_ch->rs_handle),
 					 rs_offset + chunk_off,
 					 xdr_off,
 					 this_write,
@@ -457,6 +457,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt,
 	u32 xdr_off;
 	int chunk_no;
 	int chunk_off;
+	int nchunks;
 	struct rpcrdma_segment *ch;
 	struct rpcrdma_write_array *arg_ary;
 	struct rpcrdma_write_array *res_ary;
@@ -476,26 +477,27 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt,
 		max_write = xprt->sc_max_sge * PAGE_SIZE;
 
 	/* xdr offset starts at RPC message */
+	nchunks = ntohl(arg_ary->wc_nchunks);
 	for (xdr_off = 0, chunk_no = 0;
-	     xfer_len && chunk_no < arg_ary->wc_nchunks;
+	     xfer_len && chunk_no < nchunks;
 	     chunk_no++) {
 		u64 rs_offset;
 		ch = &arg_ary->wc_array[chunk_no].wc_target;
-		write_len = min(xfer_len, ch->rs_length);
+		write_len = min(xfer_len, htonl(ch->rs_length));
 
 		/* Prepare the reply chunk given the length actually
 		 * written */
-		rs_offset = get_unaligned(&(ch->rs_offset));
+		xdr_decode_hyper((__be32 *)&ch->rs_offset, &rs_offset);
 		svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
-					    ch->rs_handle, rs_offset,
-					    write_len);
+						ch->rs_handle, ch->rs_offset,
+						write_len);
 		chunk_off = 0;
 		while (write_len) {
 			int this_write;
 
 			this_write = min(write_len, max_write);
 			ret = send_write(xprt, rqstp,
-					 ch->rs_handle,
+					 ntohl(ch->rs_handle),
 					 rs_offset + chunk_off,
 					 xdr_off,
 					 this_write,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 894cb42db91d..73b428bef598 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -51,6 +51,7 @@
 #include <rdma/rdma_cm.h>
 #include <linux/sunrpc/svc_rdma.h>
 #include <linux/export.h>
+#include "xprt_rdma.h"
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
@@ -90,12 +91,6 @@ struct svc_xprt_class svc_rdma_class = {
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
 };
 
-/* WR context cache. Created in svc_rdma.c  */
-extern struct kmem_cache *svc_rdma_ctxt_cachep;
-
-/* Workqueue created in svc_rdma.c */
-extern struct workqueue_struct *svc_rdma_wq;
-
 struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
 {
 	struct svc_rdma_op_ctxt *ctxt;
@@ -150,9 +145,6 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
 	atomic_dec(&xprt->sc_ctxt_used);
 }
 
-/* Temporary NFS request map cache. Created in svc_rdma.c  */
-extern struct kmem_cache *svc_rdma_map_cachep;
-
 /*
  * Temporary NFS req mappings are shared across all transport
  * instances. These are short lived and should be bounded by the number
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 08c5d5a128fc..9a66c95b5837 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -343,4 +343,11 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *);
  */
 int rpcrdma_marshal_req(struct rpc_rqst *);
 
+/* Temporary NFS request map cache. Created in svc_rdma.c  */
+extern struct kmem_cache *svc_rdma_map_cachep;
+/* WR context cache. Created in svc_rdma.c  */
+extern struct kmem_cache *svc_rdma_ctxt_cachep;
+/* Workqueue created in svc_rdma.c */
+extern struct workqueue_struct *svc_rdma_wq;
+
 #endif				/* _LINUX_SUNRPC_XPRT_RDMA_H */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 92bc5181dbeb..890b03f8d877 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2475,6 +2475,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 static struct rpc_xprt_ops bc_tcp_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xprt_release_xprt,
+	.rpcbind		= xs_local_rpcbind,
 	.buf_alloc		= bc_malloc,
 	.buf_free		= bc_free,
 	.send_request		= bc_send_request,
diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
index 39765bcfb472..920cabe0461b 100644
--- a/net/wireless/debugfs.c
+++ b/net/wireless/debugfs.c
@@ -13,12 +13,6 @@
 #include "core.h"
 #include "debugfs.h"
 
-static int cfg80211_open_file_generic(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 #define DEBUGFS_READONLY_FILE(name, buflen, fmt, value...)		\
 static ssize_t name## _read(struct file *file, char __user *userbuf,	\
 			    size_t count, loff_t *ppos)			\
@@ -33,7 +27,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf,	\
 									\
 static const struct file_operations name## _ops = {			\
 	.read = name## _read,						\
-	.open = cfg80211_open_file_generic,				\
+	.open = simple_open,						\
 	.llseek = generic_file_llseek,					\
 };
 
@@ -102,7 +96,7 @@ static ssize_t ht40allow_map_read(struct file *file,
 
 static const struct file_operations ht40allow_map_ops = {
 	.read = ht40allow_map_read,
-	.open = cfg80211_open_file_generic,
+	.open = simple_open,
 	.llseek = default_llseek,
 };
 
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index d897278b1f97..6a3ee981931d 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -104,7 +104,7 @@ as-option = $(call try-run,\
 # Usage: cflags-y += $(call as-instr,instr,option1,option2)
 
 as-instr = $(call try-run,\
-	/bin/echo -e "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" -,$(2),$(3))
+	printf "%b\n" "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" -,$(2),$(3))
 
 # cc-option
 # Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index d2b366c16b64..ff1720d28d0c 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -69,6 +69,7 @@ warning-1 += -Wmissing-prototypes
 warning-1 += -Wold-style-definition
 warning-1 += $(call cc-option, -Wmissing-include-dirs)
 warning-1 += $(call cc-option, -Wunused-but-set-variable)
+warning-1 += $(call cc-disable-warning, missing-field-initializers)
 
 warning-2 := -Waggregate-return
 warning-2 += -Wcast-align
@@ -76,6 +77,7 @@ warning-2 += -Wdisabled-optimization
 warning-2 += -Wnested-externs
 warning-2 += -Wshadow
 warning-2 += $(call cc-option, -Wlogical-op)
+warning-2 += $(call cc-option, -Wmissing-field-initializers)
 
 warning-3 := -Wbad-function-cast
 warning-3 += -Wcast-qual
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 00c368c6e996..0be6f110cce7 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -304,6 +304,30 @@ cmd_lzo = (cat $(filter-out FORCE,$^) | \
 	lzop -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
 	(rm -f $@ ; false)
 
+# U-Boot mkimage
+# ---------------------------------------------------------------------------
+
+MKIMAGE := $(srctree)/scripts/mkuboot.sh
+
+# SRCARCH just happens to match slightly more than ARCH (on sparc), so reduces
+# the number of overrides in arch makefiles
+UIMAGE_ARCH ?= $(SRCARCH)
+UIMAGE_COMPRESSION ?= $(if $(2),$(2),none)
+UIMAGE_OPTS-y ?=
+UIMAGE_TYPE ?= kernel
+UIMAGE_LOADADDR ?= arch_must_set_this
+UIMAGE_ENTRYADDR ?= $(UIMAGE_LOADADDR)
+UIMAGE_NAME ?= 'Linux-$(KERNELRELEASE)'
+UIMAGE_IN ?= $<
+UIMAGE_OUT ?= $@
+
+quiet_cmd_uimage = UIMAGE  $(UIMAGE_OUT)
+      cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A $(UIMAGE_ARCH) -O linux \
+			-C $(UIMAGE_COMPRESSION) $(UIMAGE_OPTS-y) \
+			-T $(UIMAGE_TYPE) \
+			-a $(UIMAGE_LOADADDR) -e $(UIMAGE_ENTRYADDR) \
+			-n $(UIMAGE_NAME) -d $(UIMAGE_IN) $(UIMAGE_OUT)
+
 # XZ
 # ---------------------------------------------------------------------------
 # Use xzkern to compress the kernel image and xzmisc to compress other things.
diff --git a/scripts/coccinelle/api/ptr_ret.cocci b/scripts/coccinelle/api/ptr_ret.cocci
new file mode 100644
index 000000000000..cbfd08c7d8c7
--- /dev/null
+++ b/scripts/coccinelle/api/ptr_ret.cocci
@@ -0,0 +1,70 @@
+///
+/// Use PTR_RET rather than if(IS_ERR(...)) + PTR_ERR
+///
+// Confidence: High
+// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6.  GPLv2.
+// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Options: -no_includes -include_headers
+//
+// Keywords: ERR_PTR, PTR_ERR, PTR_RET
+// Version min: 2.6.39
+//
+
+virtual context
+virtual patch
+virtual org
+virtual report
+
+@depends on patch@
+expression ptr;
+@@
+
+- if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0;
++ return PTR_RET(ptr);
+
+@depends on patch@
+expression ptr;
+@@
+
+- if (IS_ERR(ptr)) return PTR_ERR(ptr); return 0;
++ return PTR_RET(ptr);
+
+@r1 depends on !patch@
+expression ptr;
+position p1;
+@@
+
+* if@p1 (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0;
+
+@r2 depends on !patch@
+expression ptr;
+position p2;
+@@
+
+* if@p2 (IS_ERR(ptr)) return PTR_ERR(ptr); return 0;
+
+@script:python depends on org@
+p << r1.p1;
+@@
+
+coccilib.org.print_todo(p[0], "WARNING: PTR_RET can be used")
+
+
+@script:python depends on org@
+p << r2.p2;
+@@
+
+coccilib.org.print_todo(p[0], "WARNING: PTR_RET can be used")
+
+@script:python depends on report@
+p << r1.p1;
+@@
+
+coccilib.report.print_report(p[0], "WARNING: PTR_RET can be used")
+
+@script:python depends on report@
+p << r2.p2;
+@@
+
+coccilib.report.print_report(p[0], "WARNING: PTR_RET can be used")
diff --git a/scripts/coccinelle/api/simple_open.cocci b/scripts/coccinelle/api/simple_open.cocci
new file mode 100644
index 000000000000..05962f7be155
--- /dev/null
+++ b/scripts/coccinelle/api/simple_open.cocci
@@ -0,0 +1,70 @@
+/// This removes an open coded simple_open() function
+/// and replaces file operations references to the function
+/// with simple_open() instead.
+///
+// Confidence: High
+// Comments:
+// Options: -no_includes -include_headers
+
+virtual patch
+virtual report
+
+@ open depends on patch @
+identifier open_f != simple_open;
+identifier i, f;
+@@
+-int open_f(struct inode *i, struct file *f)
+-{
+(
+-if (i->i_private)
+-f->private_data = i->i_private;
+|
+-f->private_data = i->i_private;
+)
+-return 0;
+-}
+
+@ has_open depends on open @
+identifier fops;
+identifier open.open_f;
+@@
+struct file_operations fops = {
+...,
+-.open = open_f,
++.open = simple_open,
+...
+};
+
+@ openr depends on report @
+identifier open_f != simple_open;
+identifier i, f;
+position p;
+@@
+int open_f@p(struct inode *i, struct file *f)
+{
+(
+if (i->i_private)
+f->private_data = i->i_private;
+|
+f->private_data = i->i_private;
+)
+return 0;
+}
+
+@ has_openr depends on openr @
+identifier fops;
+identifier openr.open_f;
+position p;
+@@
+struct file_operations fops = {
+...,
+.open = open_f@p,
+...
+};
+
+@script:python@
+pf << openr.p;
+ps << has_openr.p;
+@@
+
+coccilib.report.print_report(pf[0],"WARNING opportunity for simple_open, see also structure on line %s"%(ps[0].line))
diff --git a/scripts/coccinelle/free/clk_put.cocci b/scripts/coccinelle/free/clk_put.cocci
new file mode 100644
index 000000000000..46747adfd20a
--- /dev/null
+++ b/scripts/coccinelle/free/clk_put.cocci
@@ -0,0 +1,67 @@
+/// Find missing clk_puts.
+///
+//# This only signals a missing clk_put when there is a clk_put later
+//# in the same function.
+//# False positives can be due to loops.
+//
+// Confidence: Moderate
+// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6.  GPLv2.
+// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Comments:
+// Options:
+
+virtual context
+virtual org
+virtual report
+
+@clk@
+expression e;
+statement S,S1;
+int ret;
+position p1,p2,p3;
+@@
+
+e = clk_get@p1(...)
+... when != clk_put(e)
+if (<+...e...+>) S
+... when any
+    when != clk_put(e)
+    when != if (...) { ... clk_put(e); ... }
+(
+ if (ret == 0) S1
+|
+if (...)
+   { ...
+     return 0; }
+|
+if (...)
+   { ...
+     return <+...e...+>; }
+|
+*if@p2 (...)
+   { ... when != clk_put(e)
+         when forall
+     return@p3 ...; }
+)
+... when any
+clk_put(e);
+
+@script:python depends on org@
+p1 << clk.p1;
+p2 << clk.p2;
+p3 << clk.p3;
+@@
+
+cocci.print_main("clk_get",p1)
+cocci.print_secs("if",p2)
+cocci.print_secs("needed clk_put",p3)
+
+@script:python depends on report@
+p1 << clk.p1;
+p2 << clk.p2;
+p3 << clk.p3;
+@@
+
+msg = "ERROR: missing clk_put; clk_get on line %s and execution via conditional on line %s" % (p1[0].line,p2[0].line)
+coccilib.report.print_report(p3[0],msg)
diff --git a/scripts/coccinelle/free/iounmap.cocci b/scripts/coccinelle/free/iounmap.cocci
new file mode 100644
index 000000000000..5384f4ba1192
--- /dev/null
+++ b/scripts/coccinelle/free/iounmap.cocci
@@ -0,0 +1,67 @@
+/// Find missing iounmaps.
+///
+//# This only signals a missing iounmap when there is an iounmap later
+//# in the same function.
+//# False positives can be due to loops.
+//
+// Confidence: Moderate
+// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6.  GPLv2.
+// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Comments:
+// Options:
+
+virtual context
+virtual org
+virtual report
+
+@iom@
+expression e;
+statement S,S1;
+int ret;
+position p1,p2,p3;
+@@
+
+e = \(ioremap@p1\|ioremap_nocache@p1\)(...)
+... when != iounmap(e)
+if (<+...e...+>) S
+... when any
+    when != iounmap(e)
+    when != if (...) { ... iounmap(e); ... }
+(
+ if (ret == 0) S1
+|
+if (...)
+   { ...
+     return 0; }
+|
+if (...)
+   { ...
+     return <+...e...+>; }
+|
+*if@p2 (...)
+   { ... when != iounmap(e)
+         when forall
+     return@p3 ...; }
+)
+... when any
+iounmap(e);
+
+@script:python depends on org@
+p1 << iom.p1;
+p2 << iom.p2;
+p3 << iom.p3;
+@@
+
+cocci.print_main("ioremap",p1)
+cocci.print_secs("if",p2)
+cocci.print_secs("needed iounmap",p3)
+
+@script:python depends on report@
+p1 << iom.p1;
+p2 << iom.p2;
+p3 << iom.p3;
+@@
+
+msg = "ERROR: missing iounmap; ioremap on line %s and execution via conditional on line %s" % (p1[0].line,p2[0].line)
+coccilib.report.print_report(p3[0],msg)
diff --git a/scripts/coccinelle/misc/boolinit.cocci b/scripts/coccinelle/misc/boolinit.cocci
new file mode 100644
index 000000000000..97ce41ce8135
--- /dev/null
+++ b/scripts/coccinelle/misc/boolinit.cocci
@@ -0,0 +1,178 @@
+/// Bool initializations should use true and false.  Bool tests don't need
+/// comparisons.  Based on contributions from Joe Perches, Rusty Russell
+/// and Bruce W Allan.
+///
+// Confidence: High
+// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6.  GPLv2.
+// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Options: -include_headers
+
+virtual patch
+virtual context
+virtual org
+virtual report
+
+@depends on patch@
+bool t;
+symbol true;
+symbol false;
+@@
+
+(
+- t == true
++ t
+|
+- true == t
++ t
+|
+- t != true
++ !t
+|
+- true != t
++ !t
+|
+- t == false
++ !t
+|
+- false == t
++ !t
+|
+- t != false
++ t
+|
+- false != t
++ t
+)
+
+@depends on patch disable is_zero, isnt_zero@
+bool t;
+@@
+
+(
+- t == 1
++ t
+|
+- t != 1
++ !t
+|
+- t == 0
++ !t
+|
+- t != 0
++ t
+)
+
+@depends on patch@
+bool b;
+@@
+(
+ b =
+- 0
++ false
+|
+ b =
+- 1
++ true
+)
+
+// ---------------------------------------------------------------------
+
+@r1 depends on !patch@
+bool t;
+position p;
+@@
+
+(
+* t@p == true
+|
+* true == t@p
+|
+* t@p != true
+|
+* true != t@p
+|
+* t@p == false
+|
+* false == t@p
+|
+* t@p != false
+|
+* false != t@p
+)
+
+@r2 depends on !patch disable is_zero, isnt_zero@
+bool t;
+position p;
+@@
+
+(
+* t@p == 1
+|
+* t@p != 1
+|
+* t@p == 0
+|
+* t@p != 0
+)
+
+@r3 depends on !patch@
+bool b;
+position p1,p2;
+constant c;
+@@
+(
+*b@p1 = 0
+|
+*b@p1 = 1
+|
+*b@p2 = c
+)
+
+@script:python depends on org@
+p << r1.p;
+@@
+
+cocci.print_main("WARNING: Comparison to bool",p)
+
+@script:python depends on org@
+p << r2.p;
+@@
+
+cocci.print_main("WARNING: Comparison of bool to 0/1",p)
+
+@script:python depends on org@
+p1 << r3.p1;
+@@
+
+cocci.print_main("WARNING: Assignment of bool to 0/1",p1)
+
+@script:python depends on org@
+p2 << r3.p2;
+@@
+
+cocci.print_main("ERROR: Assignment of bool to non-0/1 constant",p2)
+
+@script:python depends on report@
+p << r1.p;
+@@
+
+coccilib.report.print_report(p[0],"WARNING: Comparison to bool")
+
+@script:python depends on report@
+p << r2.p;
+@@
+
+coccilib.report.print_report(p[0],"WARNING: Comparison of bool to 0/1")
+
+@script:python depends on report@
+p1 << r3.p1;
+@@
+
+coccilib.report.print_report(p1[0],"WARNING: Assignment of bool to 0/1")
+
+@script:python depends on report@
+p2 << r3.p2;
+@@
+
+coccilib.report.print_report(p2[0],"ERROR: Assignment of bool to non-0/1 constant")
diff --git a/scripts/coccinelle/misc/cstptr.cocci b/scripts/coccinelle/misc/cstptr.cocci
new file mode 100644
index 000000000000..d42564484528
--- /dev/null
+++ b/scripts/coccinelle/misc/cstptr.cocci
@@ -0,0 +1,41 @@
+/// PTR_ERR should be applied before its argument is reassigned, typically
+/// to NULL
+///
+// Confidence: High
+// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6.  GPLv2.
+// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Comments:
+// Options: -no_includes -include_headers
+
+virtual org
+virtual report
+virtual context
+
+@r exists@
+expression e,e1;
+constant c;
+position p1,p2;
+@@
+
+*e@p1 = c
+... when != e = e1
+    when != &e
+    when != true IS_ERR(e)
+*PTR_ERR@p2(e)
+
+@script:python depends on org@
+p1 << r.p1;
+p2 << r.p2;
+@@
+
+cocci.print_main("PTR_ERR",p2)
+cocci.print_secs("assignment",p1)
+
+@script:python depends on report@
+p1 << r.p1;
+p2 << r.p2;
+@@
+
+msg = "ERROR: PTR_ERR applied after initialization to constant on line %s" % (p1[0].line)
+coccilib.report.print_report(p2[0],msg)
diff --git a/scripts/coccinelle/null/badzero.cocci b/scripts/coccinelle/null/badzero.cocci
new file mode 100644
index 000000000000..d79baf7220e7
--- /dev/null
+++ b/scripts/coccinelle/null/badzero.cocci
@@ -0,0 +1,237 @@
+/// Compare pointer-typed values to NULL rather than 0
+///
+//# This makes an effort to choose between !x and x == NULL.  !x is used
+//# if it has previously been used with the function used to initialize x.
+//# This relies on type information.  More type information can be obtained
+//# using the option -all_includes and the option -I to specify an
+//# include path.
+//
+// Confidence: High
+// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6.  GPLv2.
+// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Comments:
+// Options:
+
+virtual patch
+virtual context
+virtual org
+virtual report
+
+@initialize:ocaml@
+let negtable = Hashtbl.create 101
+
+@depends on patch@
+expression *E;
+identifier f;
+@@
+
+(
+  (E = f(...)) ==
+- 0
++ NULL
+|
+  (E = f(...)) !=
+- 0
++ NULL
+|
+- 0
++ NULL
+  == (E = f(...))
+|
+- 0
++ NULL
+  != (E = f(...))
+)
+
+
+@t1 depends on !patch@
+expression *E;
+identifier f;
+position p;
+@@
+
+(
+  (E = f(...)) ==
+* 0@p
+|
+  (E = f(...)) !=
+* 0@p
+|
+* 0@p
+  == (E = f(...))
+|
+* 0@p
+  != (E = f(...))
+)
+
+@script:python depends on org@
+p << t1.p;
+@@
+
+coccilib.org.print_todo(p[0], "WARNING comparing pointer to 0")
+
+@script:python depends on report@
+p << t1.p;
+@@
+
+coccilib.report.print_report(p[0], "WARNING comparing pointer to 0")
+
+// Tests of returned values
+
+@s@
+identifier f;
+expression E,E1;
+@@
+
+ E = f(...)
+ ... when != E = E1
+ !E
+
+@script:ocaml depends on s@
+f << s.f;
+@@
+
+try let _ = Hashtbl.find negtable f in ()
+with Not_found -> Hashtbl.add negtable f ()
+
+@ r disable is_zero,isnt_zero exists @
+expression *E;
+identifier f;
+@@
+
+E = f(...)
+...
+(E == 0
+|E != 0
+|0 == E
+|0 != E
+)
+
+@script:ocaml@
+f << r.f;
+@@
+
+try let _ = Hashtbl.find negtable f in ()
+with Not_found -> include_match false
+
+// This rule may lead to inconsistent path problems, if E is defined in two
+// places
+@ depends on patch disable is_zero,isnt_zero @
+expression *E;
+expression E1;
+identifier r.f;
+@@
+
+E = f(...)
+<...
+(
+- E == 0
++ !E
+|
+- E != 0
++ E
+|
+- 0 == E
++ !E
+|
+- 0 != E
++ E
+)
+...>
+?E = E1
+
+@t2 depends on !patch disable is_zero,isnt_zero @
+expression *E;
+expression E1;
+identifier r.f;
+position p1;
+position p2;
+@@
+
+E = f(...)
+<...
+(
+* E == 0@p1
+|
+* E != 0@p2
+|
+* 0@p1 == E
+|
+* 0@p1 != E
+)
+...>
+?E = E1
+
+@script:python depends on org@
+p << t2.p1;
+@@
+
+coccilib.org.print_todo(p[0], "WARNING comparing pointer to 0, suggest !E")
+
+@script:python depends on org@
+p << t2.p2;
+@@
+
+coccilib.org.print_todo(p[0], "WARNING comparing pointer to 0")
+
+@script:python depends on report@
+p << t2.p1;
+@@
+
+coccilib.report.print_report(p[0], "WARNING comparing pointer to 0, suggest !E")
+
+@script:python depends on report@
+p << t2.p2;
+@@
+
+coccilib.report.print_report(p[0], "WARNING comparing pointer to 0")
+
+@ depends on patch disable is_zero,isnt_zero @
+expression *E;
+@@
+
+(
+  E ==
+- 0
++ NULL
+|
+  E !=
+- 0
++ NULL
+|
+- 0
++ NULL
+  == E
+|
+- 0
++ NULL
+  != E
+)
+
+@ t3 depends on !patch disable is_zero,isnt_zero @
+expression *E;
+position p;
+@@
+
+(
+* E == 0@p
+|
+* E != 0@p
+|
+* 0@p == E
+|
+* 0@p != E
+)
+
+@script:python depends on org@
+p << t3.p;
+@@
+
+coccilib.org.print_todo(p[0], "WARNING comparing pointer to 0")
+
+@script:python depends on report@
+p << t3.p;
+@@
+
+coccilib.report.print_report(p[0], "WARNING comparing pointer to 0")
diff --git a/scripts/dtc/dtc.c b/scripts/dtc/dtc.c
index 451c92d31b19..2ef5e2e3dd38 100644
--- a/scripts/dtc/dtc.c
+++ b/scripts/dtc/dtc.c
@@ -101,7 +101,7 @@ int main(int argc, char *argv[])
 	const char *outform = "dts";
 	const char *outname = "-";
 	const char *depname = NULL;
-	int force = 0, check = 0, sort = 0;
+	int force = 0, sort = 0;
 	const char *arg;
 	int opt;
 	FILE *outf = NULL;
@@ -143,9 +143,6 @@ int main(int argc, char *argv[])
 		case 'f':
 			force = 1;
 			break;
-		case 'c':
-			check = 1;
-			break;
 		case 'q':
 			quiet++;
 			break;
diff --git a/scripts/dtc/flattree.c b/scripts/dtc/flattree.c
index ead0332c87e1..28d0b2381df6 100644
--- a/scripts/dtc/flattree.c
+++ b/scripts/dtc/flattree.c
@@ -697,7 +697,6 @@ static struct reserve_info *flat_read_mem_reserve(struct inbuf *inb)
 {
 	struct reserve_info *reservelist = NULL;
 	struct reserve_info *new;
-	const char *p;
 	struct fdt_reserve_entry re;
 
 	/*
@@ -706,7 +705,6 @@ static struct reserve_info *flat_read_mem_reserve(struct inbuf *inb)
 	 *
 	 * First pass, count entries.
 	 */
-	p = inb->ptr;
 	while (1) {
 		flat_read_chunk(inb, &re, sizeof(re));
 		re.address  = fdt64_to_cpu(re.address);
diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh
index 98cffcb941ea..a2af2e88daf3 100644
--- a/scripts/gcc-goto.sh
+++ b/scripts/gcc-goto.sh
@@ -2,4 +2,20 @@
 # Test for gcc 'asm goto' support
 # Copyright (C) 2010, Jason Baron <jbaron@redhat.com>
 
-echo "int main(void) { entry: asm goto (\"\"::::entry); return 0; }" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
+cat << "END" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
+int main(void)
+{
+#ifdef __arm__
+	/*
+	 * Not related to asm goto, but used by jump label
+	 * and broken on some ARM GCC versions (see GCC Bug 48637).
+	 */
+	static struct { int dummy; int state; } tp;
+	asm (".long %c0" :: "i" (&tp.state));
+#endif
+
+entry:
+	asm goto ("" :::: entry);
+	return 0;
+}
+END
diff --git a/scripts/headers_check.pl b/scripts/headers_check.pl
index 7957e7a5166a..64ac2380e4d5 100644
--- a/scripts/headers_check.pl
+++ b/scripts/headers_check.pl
@@ -19,6 +19,7 @@
 # 3) Check for leaked CONFIG_ symbols
 
 use strict;
+use File::Basename;
 
 my ($dir, $arch, @files) = @ARGV;
 
@@ -99,6 +100,39 @@ sub check_asm_types
 }
 
 my $linux_types;
+my %import_stack = ();
+sub check_include_typesh
+{
+	my $path = $_[0];
+	my $import_path;
+
+	my $fh;
+	my @file_paths = ($path, $dir . "/" .  $path, dirname($filename) . "/" . $path);
+	for my $possible ( @file_paths ) {
+	    if (not $import_stack{$possible} and open($fh, '<', $possible)) {
+		$import_path = $possible;
+		$import_stack{$import_path} = 1;
+		last;
+	    }
+	}
+	if (eof $fh) {
+	    return;
+	}
+
+	my $line;
+	while ($line = <$fh>) {
+		if ($line =~ m/^\s*#\s*include\s+<linux\/types.h>/) {
+			$linux_types = 1;
+			last;
+		}
+		if (my $included = ($line =~ /^\s*#\s*include\s+[<"](\S+)[>"]/)[0]) {
+			check_include_typesh($included);
+		}
+	}
+	close $fh;
+	delete $import_stack{$import_path};
+}
+
 sub check_sizetypes
 {
 	if ($filename =~ /types.h|int-l64.h|int-ll64.h/o) {
@@ -113,6 +147,9 @@ sub check_sizetypes
 		$linux_types = 1;
 		return;
 	}
+	if (my $included = ($line =~ /^\s*#\s*include\s+[<"](\S+)[>"]/)[0]) {
+		check_include_typesh($included);
+	}
 	if ($line =~ m/__[us](8|16|32|64)\b/) {
 		printf STDERR "$filename:$lineno: " .
 		              "found __[us]{8,16,32,64} type " .
@@ -122,4 +159,3 @@ sub check_sizetypes
 		#$ret = 1;
 	}
 }
-
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 7c7a5a6cc3f5..0586085136d1 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -344,10 +344,8 @@ setsym:
 
 int conf_read(const char *name)
 {
-	struct symbol *sym, *choice_sym;
-	struct property *prop;
-	struct expr *e;
-	int i, flags;
+	struct symbol *sym;
+	int i;
 
 	sym_set_change_count(0);
 
@@ -357,7 +355,7 @@ int conf_read(const char *name)
 	for_all_symbols(i, sym) {
 		sym_calc_value(sym);
 		if (sym_is_choice(sym) || (sym->flags & SYMBOL_AUTO))
-			goto sym_ok;
+			continue;
 		if (sym_has_value(sym) && (sym->flags & SYMBOL_WRITE)) {
 			/* check that calculated value agrees with saved value */
 			switch (sym->type) {
@@ -366,30 +364,18 @@ int conf_read(const char *name)
 				if (sym->def[S_DEF_USER].tri != sym_get_tristate_value(sym))
 					break;
 				if (!sym_is_choice(sym))
-					goto sym_ok;
+					continue;
 				/* fall through */
 			default:
 				if (!strcmp(sym->curr.val, sym->def[S_DEF_USER].val))
-					goto sym_ok;
+					continue;
 				break;
 			}
 		} else if (!sym_has_value(sym) && !(sym->flags & SYMBOL_WRITE))
 			/* no previous value and not saved */
-			goto sym_ok;
+			continue;
 		conf_unsaved++;
 		/* maybe print value in verbose mode... */
-	sym_ok:
-		if (!sym_is_choice(sym))
-			continue;
-		/* The choice symbol only has a set value (and thus is not new)
-		 * if all its visible childs have values.
-		 */
-		prop = sym_get_choice_prop(sym);
-		flags = sym->flags;
-		expr_list_for_each_sym(prop->expr, e, choice_sym)
-			if (choice_sym->visible != no)
-				flags &= choice_sym->flags;
-		sym->flags &= flags | ~SYMBOL_DEF_USER;
 	}
 
 	for_all_symbols(i, sym) {
diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh
index ceadf0e150cf..974d5cb7e30a 100644..100755
--- a/scripts/kconfig/merge_config.sh
+++ b/scripts/kconfig/merge_config.sh
@@ -31,10 +31,12 @@ usage() {
 	echo "  -h    display this help text"
 	echo "  -m    only merge the fragments, do not execute the make command"
 	echo "  -n    use allnoconfig instead of alldefconfig"
+	echo "  -r    list redundant entries when merging fragments"
 }
 
 MAKE=true
 ALLTARGET=alldefconfig
+WARNREDUN=false
 
 while true; do
 	case $1 in
@@ -52,18 +54,27 @@ while true; do
 		usage
 		exit
 		;;
+	"-r")
+		WARNREDUN=true
+		shift
+		continue
+		;;
 	*)
 		break
 		;;
 	esac
 done
 
-
+INITFILE=$1
+shift;
 
 MERGE_LIST=$*
 SED_CONFIG_EXP="s/^\(# \)\{0,1\}\(CONFIG_[a-zA-Z0-9_]*\)[= ].*/\2/p"
 TMP_FILE=$(mktemp ./.tmp.config.XXXXXXXXXX)
 
+echo "Using $INITFILE as base"
+cat $INITFILE > $TMP_FILE
+
 # Merge files, printing warnings on overrided values
 for MERGE_FILE in $MERGE_LIST ; do
 	echo "Merging $MERGE_FILE"
@@ -79,6 +90,8 @@ for MERGE_FILE in $MERGE_LIST ; do
 			echo Previous  value: $PREV_VAL
 			echo New value:       $NEW_VAL
 			echo
+			elif [ "$WARNREDUN" = "true" ]; then
+			echo Value of $CFG is redundant by fragment $MERGE_FILE:
 			fi
 			sed -i "/$CFG[ =]/d" $TMP_FILE
 		fi
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 071f00c3046e..22a3c400fc41 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -262,11 +262,18 @@ static struct symbol *sym_calc_choice(struct symbol *sym)
 	struct symbol *def_sym;
 	struct property *prop;
 	struct expr *e;
+	int flags;
 
 	/* first calculate all choice values' visibilities */
+	flags = sym->flags;
 	prop = sym_get_choice_prop(sym);
-	expr_list_for_each_sym(prop->expr, e, def_sym)
+	expr_list_for_each_sym(prop->expr, e, def_sym) {
 		sym_calc_visibility(def_sym);
+		if (def_sym->visible != no)
+			flags &= def_sym->flags;
+	}
+
+	sym->flags &= flags | ~SYMBOL_DEF_USER;
 
 	/* is the user choice visible? */
 	def_sym = sym->def[S_DEF_USER].val;
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 9adb667dd31a..3f01fd908730 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -849,7 +849,7 @@ static void check_section(const char *modname, struct elf_info *elf,
 
 #define ALL_INIT_DATA_SECTIONS \
 	".init.setup$", ".init.rodata$", \
-	".devinit.rodata$", ".cpuinit.rodata$", ".meminit.rodata$" \
+	".devinit.rodata$", ".cpuinit.rodata$", ".meminit.rodata$", \
 	".init.data$", ".devinit.data$", ".cpuinit.data$", ".meminit.data$"
 #define ALL_EXIT_DATA_SECTIONS \
 	".exit.data$", ".devexit.data$", ".cpuexit.data$", ".memexit.data$"
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 3c6c0b14c807..eee5f8ed2493 100644
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -97,6 +97,7 @@ mkdir -m 755 -p "$libc_headers_dir/DEBIAN"
 mkdir -p "$libc_headers_dir/usr/share/doc/$libc_headers_packagename"
 mkdir -m 755 -p "$kernel_headers_dir/DEBIAN"
 mkdir -p "$kernel_headers_dir/usr/share/doc/$kernel_headers_packagename"
+mkdir -p "$kernel_headers_dir/lib/modules/$version/"
 if [ "$ARCH" = "um" ] ; then
 	mkdir -p "$tmpdir/usr/lib/uml/modules/$version" "$tmpdir/usr/bin"
 fi
@@ -120,15 +121,19 @@ else
 fi
 
 if grep -q '^CONFIG_MODULES=y' .config ; then
-	INSTALL_MOD_PATH="$tmpdir" make KBUILD_SRC= modules_install
+	INSTALL_MOD_PATH="$tmpdir" $MAKE KBUILD_SRC= modules_install
+	rm -f "$tmpdir/lib/modules/$version/build"
+	rm -f "$tmpdir/lib/modules/$version/source"
 	if [ "$ARCH" = "um" ] ; then
 		mv "$tmpdir/lib/modules/$version"/* "$tmpdir/usr/lib/uml/modules/$version/"
 		rmdir "$tmpdir/lib/modules/$version"
 	fi
 fi
 
-make headers_check
-make headers_install INSTALL_HDR_PATH="$libc_headers_dir/usr"
+if [ "$ARCH" != "um" ]; then
+	$MAKE headers_check KBUILD_SRC=
+	$MAKE headers_install KBUILD_SRC= INSTALL_HDR_PATH="$libc_headers_dir/usr"
+fi
 
 # Install the maintainer scripts
 # Note: hook scripts under /etc/kernel are also executed by official Debian
@@ -245,6 +250,7 @@ destdir=$kernel_headers_dir/usr/src/linux-headers-$version
 mkdir -p "$destdir"
 (cd $srctree; tar -c -f - -T "$objtree/debian/hdrsrcfiles") | (cd $destdir; tar -xf -)
 (cd $objtree; tar -c -f - -T "$objtree/debian/hdrobjfiles") | (cd $destdir; tar -xf -)
+ln -sf "/usr/src/linux-headers-$version" "$kernel_headers_dir/lib/modules/$version/build"
 rm -f "$objtree/debian/hdrsrcfiles" "$objtree/debian/hdrobjfiles"
 arch=$(dpkg --print-architecture)
 
@@ -259,8 +265,6 @@ Description: Linux kernel headers for $KERNELRELEASE on $arch
  This is useful for people who need to build external modules
 EOF
 
-create_package "$kernel_headers_packagename" "$kernel_headers_dir"
-
 # Do we have firmware? Move it out of the way and build it into a package.
 if [ -e "$tmpdir/lib/firmware" ]; then
 	mv "$tmpdir/lib/firmware" "$fwdir/lib/"
@@ -287,7 +291,11 @@ Description: Linux support headers for userspace development
  are used by the installed headers for GNU glibc and other system libraries.
 EOF
 
-create_package "$libc_headers_packagename" "$libc_headers_dir"
+if [ "$ARCH" != "um" ]; then
+	create_package "$kernel_headers_packagename" "$kernel_headers_dir"
+	create_package "$libc_headers_packagename" "$libc_headers_dir"
+fi
+
 create_package "$packagename" "$tmpdir"
 
 exit 0
diff --git a/scripts/patch-kernel b/scripts/patch-kernel
index 20fb25c23382..d000ea3a41fd 100755
--- a/scripts/patch-kernel
+++ b/scripts/patch-kernel
@@ -116,6 +116,10 @@ findFile () {
 		ext=".bz2"
 		name="bzip2"
 		uncomp="bunzip2 -dc"
+  elif [ -r ${filebase}.xz ]; then
+                ext=".xz"
+                name="xz"
+                uncomp="xz -dc"
   elif [ -r ${filebase}.zip ]; then
 		ext=".zip"
 		name="zip"
diff --git a/scripts/setlocalversion b/scripts/setlocalversion
index 4d403844e137..bd6dca8a0ab2 100755
--- a/scripts/setlocalversion
+++ b/scripts/setlocalversion
@@ -75,8 +75,7 @@ scm_version()
 		[ -w . ] && git update-index --refresh --unmerged > /dev/null
 
 		# Check for uncommitted changes
-		if git diff-index --name-only HEAD | grep -v "^scripts/package" \
-		    | read dummy; then
+		if git diff-index --name-only HEAD | grep -qv "^scripts/package"; then
 			printf '%s' -dirty
 		fi
 
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 833813a99e7c..cf7b12fee573 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -116,7 +116,7 @@ docscope()
 
 dogtags()
 {
-	all_sources | gtags -f -
+	all_sources | gtags -i -f -
 }
 
 exuberant()
@@ -166,9 +166,6 @@ exuberant()
 	all_defconfigs | xargs -r $1 -a                         \
 	--langdef=dotconfig --language-force=dotconfig          \
 	--regex-dotconfig='/^#?[[:blank:]]*(CONFIG_[[:alnum:]_]+)/\1/'
-
-	# Remove structure forward declarations.
-	LANG=C sed -i -e '/^\([a-zA-Z_][a-zA-Z0-9_]*\)\t.*\t\/\^struct \1;.*\$\/;"\tx$/d' tags
 }
 
 emacs()
@@ -233,6 +230,7 @@ if [ "${ARCH}" = "um" ]; then
 	fi
 fi
 
+remove_structs=
 case "$1" in
 	"cscope")
 		docscope
@@ -245,10 +243,17 @@ case "$1" in
 	"tags")
 		rm -f tags
 		xtags ctags
+		remove_structs=y
 		;;
 
 	"TAGS")
 		rm -f TAGS
 		xtags etags
+		remove_structs=y
 		;;
 esac
+
+# Remove structure forward declarations.
+if [ -n "$remove_structs" ]; then
+    LANG=C sed -i -e '/^\([a-zA-Z_][a-zA-Z0-9_]*\)\t.*\t\/\^struct \1;.*\$\/;"\tx$/d' $1
+fi
diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c
index 5ff67776a5ad..cc3520d39a78 100644
--- a/security/apparmor/audit.c
+++ b/security/apparmor/audit.c
@@ -115,23 +115,23 @@ static void audit_pre(struct audit_buffer *ab, void *ca)
 
 	if (aa_g_audit_header) {
 		audit_log_format(ab, "apparmor=");
-		audit_log_string(ab, aa_audit_type[sa->aad.type]);
+		audit_log_string(ab, aa_audit_type[sa->aad->type]);
 	}
 
-	if (sa->aad.op) {
+	if (sa->aad->op) {
 		audit_log_format(ab, " operation=");
-		audit_log_string(ab, op_table[sa->aad.op]);
+		audit_log_string(ab, op_table[sa->aad->op]);
 	}
 
-	if (sa->aad.info) {
+	if (sa->aad->info) {
 		audit_log_format(ab, " info=");
-		audit_log_string(ab, sa->aad.info);
-		if (sa->aad.error)
-			audit_log_format(ab, " error=%d", sa->aad.error);
+		audit_log_string(ab, sa->aad->info);
+		if (sa->aad->error)
+			audit_log_format(ab, " error=%d", sa->aad->error);
 	}
 
-	if (sa->aad.profile) {
-		struct aa_profile *profile = sa->aad.profile;
+	if (sa->aad->profile) {
+		struct aa_profile *profile = sa->aad->profile;
 		pid_t pid;
 		rcu_read_lock();
 		pid = rcu_dereference(tsk->real_parent)->pid;
@@ -145,9 +145,9 @@ static void audit_pre(struct audit_buffer *ab, void *ca)
 		audit_log_untrustedstring(ab, profile->base.hname);
 	}
 
-	if (sa->aad.name) {
+	if (sa->aad->name) {
 		audit_log_format(ab, " name=");
-		audit_log_untrustedstring(ab, sa->aad.name);
+		audit_log_untrustedstring(ab, sa->aad->name);
 	}
 }
 
@@ -159,10 +159,8 @@ static void audit_pre(struct audit_buffer *ab, void *ca)
 void aa_audit_msg(int type, struct common_audit_data *sa,
 		  void (*cb) (struct audit_buffer *, void *))
 {
-	sa->aad.type = type;
-	sa->lsm_pre_audit = audit_pre;
-	sa->lsm_post_audit = cb;
-	common_lsm_audit(sa);
+	sa->aad->type = type;
+	common_lsm_audit(sa, audit_pre, cb);
 }
 
 /**
@@ -184,7 +182,7 @@ int aa_audit(int type, struct aa_profile *profile, gfp_t gfp,
 	BUG_ON(!profile);
 
 	if (type == AUDIT_APPARMOR_AUTO) {
-		if (likely(!sa->aad.error)) {
+		if (likely(!sa->aad->error)) {
 			if (AUDIT_MODE(profile) != AUDIT_ALL)
 				return 0;
 			type = AUDIT_APPARMOR_AUDIT;
@@ -196,21 +194,21 @@ int aa_audit(int type, struct aa_profile *profile, gfp_t gfp,
 	if (AUDIT_MODE(profile) == AUDIT_QUIET ||
 	    (type == AUDIT_APPARMOR_DENIED &&
 	     AUDIT_MODE(profile) == AUDIT_QUIET))
-		return sa->aad.error;
+		return sa->aad->error;
 
 	if (KILL_MODE(profile) && type == AUDIT_APPARMOR_DENIED)
 		type = AUDIT_APPARMOR_KILL;
 
 	if (!unconfined(profile))
-		sa->aad.profile = profile;
+		sa->aad->profile = profile;
 
 	aa_audit_msg(type, sa, cb);
 
-	if (sa->aad.type == AUDIT_APPARMOR_KILL)
+	if (sa->aad->type == AUDIT_APPARMOR_KILL)
 		(void)send_sig_info(SIGKILL, NULL, sa->tsk ? sa->tsk : current);
 
-	if (sa->aad.type == AUDIT_APPARMOR_ALLOWED)
-		return complain_error(sa->aad.error);
+	if (sa->aad->type == AUDIT_APPARMOR_ALLOWED)
+		return complain_error(sa->aad->error);
 
-	return sa->aad.error;
+	return sa->aad->error;
 }
diff --git a/security/apparmor/capability.c b/security/apparmor/capability.c
index 9982c48def4e..088dba3bf7dc 100644
--- a/security/apparmor/capability.c
+++ b/security/apparmor/capability.c
@@ -64,11 +64,13 @@ static int audit_caps(struct aa_profile *profile, struct task_struct *task,
 	struct audit_cache *ent;
 	int type = AUDIT_APPARMOR_AUTO;
 	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
 	COMMON_AUDIT_DATA_INIT(&sa, CAP);
+	sa.aad = &aad;
 	sa.tsk = task;
 	sa.u.cap = cap;
-	sa.aad.op = OP_CAPABLE;
-	sa.aad.error = error;
+	sa.aad->op = OP_CAPABLE;
+	sa.aad->error = error;
 
 	if (likely(!error)) {
 		/* test if auditing is being forced */
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 7c69599a69e1..6327685c101e 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -410,7 +410,8 @@ int apparmor_bprm_set_creds(struct linux_binprm *bprm)
 		 * exec\0change_profile
 		 */
 		state = aa_dfa_null_transition(profile->file.dfa, state);
-		cp = change_profile_perms(profile, cxt->onexec->ns, name,
+		cp = change_profile_perms(profile, cxt->onexec->ns,
+					  cxt->onexec->base.name,
 					  AA_MAY_ONEXEC, state);
 
 		if (!(cp.allow & AA_MAY_ONEXEC))
diff --git a/security/apparmor/file.c b/security/apparmor/file.c
index 3022c0f4f0db..2f8fcba9ce4b 100644
--- a/security/apparmor/file.c
+++ b/security/apparmor/file.c
@@ -67,22 +67,22 @@ static void file_audit_cb(struct audit_buffer *ab, void *va)
 	struct common_audit_data *sa = va;
 	uid_t fsuid = current_fsuid();
 
-	if (sa->aad.fs.request & AA_AUDIT_FILE_MASK) {
+	if (sa->aad->fs.request & AA_AUDIT_FILE_MASK) {
 		audit_log_format(ab, " requested_mask=");
-		audit_file_mask(ab, sa->aad.fs.request);
+		audit_file_mask(ab, sa->aad->fs.request);
 	}
-	if (sa->aad.fs.denied & AA_AUDIT_FILE_MASK) {
+	if (sa->aad->fs.denied & AA_AUDIT_FILE_MASK) {
 		audit_log_format(ab, " denied_mask=");
-		audit_file_mask(ab, sa->aad.fs.denied);
+		audit_file_mask(ab, sa->aad->fs.denied);
 	}
-	if (sa->aad.fs.request & AA_AUDIT_FILE_MASK) {
+	if (sa->aad->fs.request & AA_AUDIT_FILE_MASK) {
 		audit_log_format(ab, " fsuid=%d", fsuid);
-		audit_log_format(ab, " ouid=%d", sa->aad.fs.ouid);
+		audit_log_format(ab, " ouid=%d", sa->aad->fs.ouid);
 	}
 
-	if (sa->aad.fs.target) {
+	if (sa->aad->fs.target) {
 		audit_log_format(ab, " target=");
-		audit_log_untrustedstring(ab, sa->aad.fs.target);
+		audit_log_untrustedstring(ab, sa->aad->fs.target);
 	}
 }
 
@@ -107,45 +107,47 @@ int aa_audit_file(struct aa_profile *profile, struct file_perms *perms,
 {
 	int type = AUDIT_APPARMOR_AUTO;
 	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
 	COMMON_AUDIT_DATA_INIT(&sa, NONE);
-	sa.aad.op = op,
-	sa.aad.fs.request = request;
-	sa.aad.name = name;
-	sa.aad.fs.target = target;
-	sa.aad.fs.ouid = ouid;
-	sa.aad.info = info;
-	sa.aad.error = error;
-
-	if (likely(!sa.aad.error)) {
+	sa.aad = &aad;
+	aad.op = op,
+	aad.fs.request = request;
+	aad.name = name;
+	aad.fs.target = target;
+	aad.fs.ouid = ouid;
+	aad.info = info;
+	aad.error = error;
+
+	if (likely(!sa.aad->error)) {
 		u32 mask = perms->audit;
 
 		if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL))
 			mask = 0xffff;
 
 		/* mask off perms that are not being force audited */
-		sa.aad.fs.request &= mask;
+		sa.aad->fs.request &= mask;
 
-		if (likely(!sa.aad.fs.request))
+		if (likely(!sa.aad->fs.request))
 			return 0;
 		type = AUDIT_APPARMOR_AUDIT;
 	} else {
 		/* only report permissions that were denied */
-		sa.aad.fs.request = sa.aad.fs.request & ~perms->allow;
+		sa.aad->fs.request = sa.aad->fs.request & ~perms->allow;
 
-		if (sa.aad.fs.request & perms->kill)
+		if (sa.aad->fs.request & perms->kill)
 			type = AUDIT_APPARMOR_KILL;
 
 		/* quiet known rejects, assumes quiet and kill do not overlap */
-		if ((sa.aad.fs.request & perms->quiet) &&
+		if ((sa.aad->fs.request & perms->quiet) &&
 		    AUDIT_MODE(profile) != AUDIT_NOQUIET &&
 		    AUDIT_MODE(profile) != AUDIT_ALL)
-			sa.aad.fs.request &= ~perms->quiet;
+			sa.aad->fs.request &= ~perms->quiet;
 
-		if (!sa.aad.fs.request)
-			return COMPLAIN_MODE(profile) ? 0 : sa.aad.error;
+		if (!sa.aad->fs.request)
+			return COMPLAIN_MODE(profile) ? 0 : sa.aad->error;
 	}
 
-	sa.aad.fs.denied = sa.aad.fs.request & ~perms->allow;
+	sa.aad->fs.denied = sa.aad->fs.request & ~perms->allow;
 	return aa_audit(type, profile, gfp, &sa, file_audit_cb);
 }
 
@@ -215,6 +217,8 @@ static struct file_perms compute_perms(struct aa_dfa *dfa, unsigned int state,
 	/* change_profile wasn't determined by ownership in old mapping */
 	if (ACCEPT_TABLE(dfa)[state] & 0x80000000)
 		perms.allow |= AA_MAY_CHANGE_PROFILE;
+	if (ACCEPT_TABLE(dfa)[state] & 0x40000000)
+		perms.allow |= AA_MAY_ONEXEC;
 
 	return perms;
 }
diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h
index 4ba78c203af1..3868b1e5d5ba 100644
--- a/security/apparmor/include/audit.h
+++ b/security/apparmor/include/audit.h
@@ -103,7 +103,33 @@ enum aa_ops {
 };
 
 
-/* define a short hand for apparmor_audit_data portion of common_audit_data */
+struct apparmor_audit_data {
+	int error;
+	int op;
+	int type;
+	void *profile;
+	const char *name;
+	const char *info;
+	union {
+		void *target;
+		struct {
+			long pos;
+			void *target;
+		} iface;
+		struct {
+			int rlim;
+			unsigned long max;
+		} rlim;
+		struct {
+			const char *target;
+			u32 request;
+			u32 denied;
+			uid_t ouid;
+		} fs;
+	};
+};
+
+/* define a short hand for apparmor_audit_data structure */
 #define aad apparmor_audit_data
 
 void aa_audit_msg(int type, struct common_audit_data *sa,
diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c
index 7ee05c6f3c64..c3da93a5150d 100644
--- a/security/apparmor/ipc.c
+++ b/security/apparmor/ipc.c
@@ -26,7 +26,7 @@ static void audit_cb(struct audit_buffer *ab, void *va)
 {
 	struct common_audit_data *sa = va;
 	audit_log_format(ab, " target=");
-	audit_log_untrustedstring(ab, sa->aad.target);
+	audit_log_untrustedstring(ab, sa->aad->target);
 }
 
 /**
@@ -41,10 +41,12 @@ static int aa_audit_ptrace(struct aa_profile *profile,
 			   struct aa_profile *target, int error)
 {
 	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
 	COMMON_AUDIT_DATA_INIT(&sa, NONE);
-	sa.aad.op = OP_PTRACE;
-	sa.aad.target = target;
-	sa.aad.error = error;
+	sa.aad = &aad;
+	aad.op = OP_PTRACE;
+	aad.target = target;
+	aad.error = error;
 
 	return aa_audit(AUDIT_APPARMOR_AUTO, profile, GFP_ATOMIC, &sa,
 			audit_cb);
diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c
index 9516948041ad..e75829ba0ff9 100644
--- a/security/apparmor/lib.c
+++ b/security/apparmor/lib.c
@@ -65,8 +65,10 @@ void aa_info_message(const char *str)
 {
 	if (audit_enabled) {
 		struct common_audit_data sa;
+		struct apparmor_audit_data aad = {0,};
 		COMMON_AUDIT_DATA_INIT(&sa, NONE);
-		sa.aad.info = str;
+		sa.aad = &aad;
+		aad.info = str;
 		aa_audit_msg(AUDIT_APPARMOR_STATUS, &sa, NULL);
 	}
 	printk(KERN_INFO "AppArmor: %s\n", str);
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 97ce8fae49b3..ad05d391974d 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -588,10 +588,12 @@ static int apparmor_setprocattr(struct task_struct *task, char *name,
 			error = aa_setprocattr_permipc(args);
 		} else {
 			struct common_audit_data sa;
+			struct apparmor_audit_data aad = {0,};
 			COMMON_AUDIT_DATA_INIT(&sa, NONE);
-			sa.aad.op = OP_SETPROCATTR;
-			sa.aad.info = name;
-			sa.aad.error = -EINVAL;
+			sa.aad = &aad;
+			aad.op = OP_SETPROCATTR;
+			aad.info = name;
+			aad.error = -EINVAL;
 			return aa_audit(AUDIT_APPARMOR_DENIED,
 					__aa_current_profile(), GFP_KERNEL,
 					&sa, NULL);
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 906414383022..f1f7506a464d 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -964,11 +964,13 @@ static int audit_policy(int op, gfp_t gfp, const char *name, const char *info,
 			int error)
 {
 	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
 	COMMON_AUDIT_DATA_INIT(&sa, NONE);
-	sa.aad.op = op;
-	sa.aad.name = name;
-	sa.aad.info = info;
-	sa.aad.error = error;
+	sa.aad = &aad;
+	aad.op = op;
+	aad.name = name;
+	aad.info = info;
+	aad.error = error;
 
 	return aa_audit(AUDIT_APPARMOR_STATUS, __aa_current_profile(), gfp,
 			&sa, NULL);
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 25fd51edc8da..deab7c7e8dc0 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -70,13 +70,13 @@ struct aa_ext {
 static void audit_cb(struct audit_buffer *ab, void *va)
 {
 	struct common_audit_data *sa = va;
-	if (sa->aad.iface.target) {
-		struct aa_profile *name = sa->aad.iface.target;
+	if (sa->aad->iface.target) {
+		struct aa_profile *name = sa->aad->iface.target;
 		audit_log_format(ab, " name=");
 		audit_log_untrustedstring(ab, name->base.hname);
 	}
-	if (sa->aad.iface.pos)
-		audit_log_format(ab, " offset=%ld", sa->aad.iface.pos);
+	if (sa->aad->iface.pos)
+		audit_log_format(ab, " offset=%ld", sa->aad->iface.pos);
 }
 
 /**
@@ -94,13 +94,15 @@ static int audit_iface(struct aa_profile *new, const char *name,
 {
 	struct aa_profile *profile = __aa_current_profile();
 	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
 	COMMON_AUDIT_DATA_INIT(&sa, NONE);
+	sa.aad = &aad;
 	if (e)
-		sa.aad.iface.pos = e->pos - e->start;
-	sa.aad.iface.target = new;
-	sa.aad.name = name;
-	sa.aad.info = info;
-	sa.aad.error = error;
+		aad.iface.pos = e->pos - e->start;
+	aad.iface.target = new;
+	aad.name = name;
+	aad.info = info;
+	aad.error = error;
 
 	return aa_audit(AUDIT_APPARMOR_STATUS, profile, GFP_KERNEL, &sa,
 			audit_cb);
diff --git a/security/apparmor/resource.c b/security/apparmor/resource.c
index 72c25a4f2cfd..2fe8613efe33 100644
--- a/security/apparmor/resource.c
+++ b/security/apparmor/resource.c
@@ -34,7 +34,7 @@ static void audit_cb(struct audit_buffer *ab, void *va)
 	struct common_audit_data *sa = va;
 
 	audit_log_format(ab, " rlimit=%s value=%lu",
-			 rlim_names[sa->aad.rlim.rlim], sa->aad.rlim.max);
+			 rlim_names[sa->aad->rlim.rlim], sa->aad->rlim.max);
 }
 
 /**
@@ -50,12 +50,14 @@ static int audit_resource(struct aa_profile *profile, unsigned int resource,
 			  unsigned long value, int error)
 {
 	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
 
 	COMMON_AUDIT_DATA_INIT(&sa, NONE);
-	sa.aad.op = OP_SETRLIMIT,
-	sa.aad.rlim.rlim = resource;
-	sa.aad.rlim.max = value;
-	sa.aad.error = error;
+	sa.aad = &aad;
+	aad.op = OP_SETRLIMIT,
+	aad.rlim.rlim = resource;
+	aad.rlim.max = value;
+	aad.error = error;
 	return aa_audit(AUDIT_APPARMOR_AUTO, profile, GFP_KERNEL, &sa,
 			audit_cb);
 }
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 8b8f0902f6e5..90c129b0102f 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -49,8 +49,8 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 	if (ih == NULL)
 		return -EINVAL;
 
-	ad->u.net.v4info.saddr = ih->saddr;
-	ad->u.net.v4info.daddr = ih->daddr;
+	ad->u.net->v4info.saddr = ih->saddr;
+	ad->u.net->v4info.daddr = ih->daddr;
 
 	if (proto)
 		*proto = ih->protocol;
@@ -64,8 +64,8 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 		if (th == NULL)
 			break;
 
-		ad->u.net.sport = th->source;
-		ad->u.net.dport = th->dest;
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
 		break;
 	}
 	case IPPROTO_UDP: {
@@ -73,8 +73,8 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 		if (uh == NULL)
 			break;
 
-		ad->u.net.sport = uh->source;
-		ad->u.net.dport = uh->dest;
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
 		break;
 	}
 	case IPPROTO_DCCP: {
@@ -82,16 +82,16 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 		if (dh == NULL)
 			break;
 
-		ad->u.net.sport = dh->dccph_sport;
-		ad->u.net.dport = dh->dccph_dport;
+		ad->u.net->sport = dh->dccph_sport;
+		ad->u.net->dport = dh->dccph_dport;
 		break;
 	}
 	case IPPROTO_SCTP: {
 		struct sctphdr *sh = sctp_hdr(skb);
 		if (sh == NULL)
 			break;
-		ad->u.net.sport = sh->source;
-		ad->u.net.dport = sh->dest;
+		ad->u.net->sport = sh->source;
+		ad->u.net->dport = sh->dest;
 		break;
 	}
 	default:
@@ -119,8 +119,8 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 	ip6 = ipv6_hdr(skb);
 	if (ip6 == NULL)
 		return -EINVAL;
-	ad->u.net.v6info.saddr = ip6->saddr;
-	ad->u.net.v6info.daddr = ip6->daddr;
+	ad->u.net->v6info.saddr = ip6->saddr;
+	ad->u.net->v6info.daddr = ip6->daddr;
 	ret = 0;
 	/* IPv6 can have several extension header before the Transport header
 	 * skip them */
@@ -140,8 +140,8 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 		if (th == NULL)
 			break;
 
-		ad->u.net.sport = th->source;
-		ad->u.net.dport = th->dest;
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
 		break;
 	}
 	case IPPROTO_UDP: {
@@ -151,8 +151,8 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 		if (uh == NULL)
 			break;
 
-		ad->u.net.sport = uh->source;
-		ad->u.net.dport = uh->dest;
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
 		break;
 	}
 	case IPPROTO_DCCP: {
@@ -162,8 +162,8 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 		if (dh == NULL)
 			break;
 
-		ad->u.net.sport = dh->dccph_sport;
-		ad->u.net.dport = dh->dccph_dport;
+		ad->u.net->sport = dh->dccph_sport;
+		ad->u.net->dport = dh->dccph_dport;
 		break;
 	}
 	case IPPROTO_SCTP: {
@@ -172,8 +172,8 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 		sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
 		if (sh == NULL)
 			break;
-		ad->u.net.sport = sh->source;
-		ad->u.net.dport = sh->dest;
+		ad->u.net->sport = sh->source;
+		ad->u.net->dport = sh->dest;
 		break;
 	}
 	default:
@@ -281,8 +281,8 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		}
 		break;
 	case LSM_AUDIT_DATA_NET:
-		if (a->u.net.sk) {
-			struct sock *sk = a->u.net.sk;
+		if (a->u.net->sk) {
+			struct sock *sk = a->u.net->sk;
 			struct unix_sock *u;
 			int len = 0;
 			char *p = NULL;
@@ -330,29 +330,29 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			}
 		}
 
-		switch (a->u.net.family) {
+		switch (a->u.net->family) {
 		case AF_INET:
-			print_ipv4_addr(ab, a->u.net.v4info.saddr,
-					a->u.net.sport,
+			print_ipv4_addr(ab, a->u.net->v4info.saddr,
+					a->u.net->sport,
 					"saddr", "src");
-			print_ipv4_addr(ab, a->u.net.v4info.daddr,
-					a->u.net.dport,
+			print_ipv4_addr(ab, a->u.net->v4info.daddr,
+					a->u.net->dport,
 					"daddr", "dest");
 			break;
 		case AF_INET6:
-			print_ipv6_addr(ab, &a->u.net.v6info.saddr,
-					a->u.net.sport,
+			print_ipv6_addr(ab, &a->u.net->v6info.saddr,
+					a->u.net->sport,
 					"saddr", "src");
-			print_ipv6_addr(ab, &a->u.net.v6info.daddr,
-					a->u.net.dport,
+			print_ipv6_addr(ab, &a->u.net->v6info.daddr,
+					a->u.net->dport,
 					"daddr", "dest");
 			break;
 		}
-		if (a->u.net.netif > 0) {
+		if (a->u.net->netif > 0) {
 			struct net_device *dev;
 
 			/* NOTE: we always use init's namespace */
-			dev = dev_get_by_index(&init_net, a->u.net.netif);
+			dev = dev_get_by_index(&init_net, a->u.net->netif);
 			if (dev) {
 				audit_log_format(ab, " netif=%s", dev->name);
 				dev_put(dev);
@@ -378,11 +378,15 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 /**
  * common_lsm_audit - generic LSM auditing function
  * @a:  auxiliary audit data
+ * @pre_audit: lsm-specific pre-audit callback
+ * @post_audit: lsm-specific post-audit callback
  *
  * setup the audit buffer for common security information
  * uses callback to print LSM specific information
  */
-void common_lsm_audit(struct common_audit_data *a)
+void common_lsm_audit(struct common_audit_data *a,
+	void (*pre_audit)(struct audit_buffer *, void *),
+	void (*post_audit)(struct audit_buffer *, void *))
 {
 	struct audit_buffer *ab;
 
@@ -394,13 +398,13 @@ void common_lsm_audit(struct common_audit_data *a)
 	if (ab == NULL)
 		return;
 
-	if (a->lsm_pre_audit)
-		a->lsm_pre_audit(ab, a);
+	if (pre_audit)
+		pre_audit(ab, a);
 
 	dump_common_audit_data(ab, a);
 
-	if (a->lsm_post_audit)
-		a->lsm_post_audit(ab, a);
+	if (post_audit)
+		post_audit(ab, a);
 
 	audit_log_end(ab);
 }
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 6989472d0957..8ee42b2a5f19 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -436,9 +436,9 @@ static void avc_audit_pre_callback(struct audit_buffer *ab, void *a)
 {
 	struct common_audit_data *ad = a;
 	audit_log_format(ab, "avc:  %s ",
-			 ad->selinux_audit_data.denied ? "denied" : "granted");
-	avc_dump_av(ab, ad->selinux_audit_data.tclass,
-			ad->selinux_audit_data.audited);
+			 ad->selinux_audit_data->slad->denied ? "denied" : "granted");
+	avc_dump_av(ab, ad->selinux_audit_data->slad->tclass,
+			ad->selinux_audit_data->slad->audited);
 	audit_log_format(ab, " for ");
 }
 
@@ -452,22 +452,25 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
 {
 	struct common_audit_data *ad = a;
 	audit_log_format(ab, " ");
-	avc_dump_query(ab, ad->selinux_audit_data.ssid,
-			   ad->selinux_audit_data.tsid,
-			   ad->selinux_audit_data.tclass);
+	avc_dump_query(ab, ad->selinux_audit_data->slad->ssid,
+			   ad->selinux_audit_data->slad->tsid,
+			   ad->selinux_audit_data->slad->tclass);
 }
 
 /* This is the slow part of avc audit with big stack footprint */
 static noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
 		u32 requested, u32 audited, u32 denied,
-		struct av_decision *avd, struct common_audit_data *a,
+		struct common_audit_data *a,
 		unsigned flags)
 {
 	struct common_audit_data stack_data;
+	struct selinux_audit_data sad = {0,};
+	struct selinux_late_audit_data slad;
 
 	if (!a) {
 		a = &stack_data;
 		COMMON_AUDIT_DATA_INIT(a, NONE);
+		a->selinux_audit_data = &sad;
 	}
 
 	/*
@@ -481,15 +484,15 @@ static noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
 	    (flags & MAY_NOT_BLOCK))
 		return -ECHILD;
 
-	a->selinux_audit_data.tclass = tclass;
-	a->selinux_audit_data.requested = requested;
-	a->selinux_audit_data.ssid = ssid;
-	a->selinux_audit_data.tsid = tsid;
-	a->selinux_audit_data.audited = audited;
-	a->selinux_audit_data.denied = denied;
-	a->lsm_pre_audit = avc_audit_pre_callback;
-	a->lsm_post_audit = avc_audit_post_callback;
-	common_lsm_audit(a);
+	slad.tclass = tclass;
+	slad.requested = requested;
+	slad.ssid = ssid;
+	slad.tsid = tsid;
+	slad.audited = audited;
+	slad.denied = denied;
+
+	a->selinux_audit_data->slad = &slad;
+	common_lsm_audit(a, avc_audit_pre_callback, avc_audit_post_callback);
 	return 0;
 }
 
@@ -513,7 +516,7 @@ static noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
  * be performed under a lock, to allow the lock to be released
  * before calling the auditing code.
  */
-int avc_audit(u32 ssid, u32 tsid,
+inline int avc_audit(u32 ssid, u32 tsid,
 	       u16 tclass, u32 requested,
 	       struct av_decision *avd, int result, struct common_audit_data *a,
 	       unsigned flags)
@@ -523,7 +526,7 @@ int avc_audit(u32 ssid, u32 tsid,
 	if (unlikely(denied)) {
 		audited = denied & avd->auditdeny;
 		/*
-		 * a->selinux_audit_data.auditdeny is TRICKY!  Setting a bit in
+		 * a->selinux_audit_data->auditdeny is TRICKY!  Setting a bit in
 		 * this field means that ANY denials should NOT be audited if
 		 * the policy contains an explicit dontaudit rule for that
 		 * permission.  Take notice that this is unrelated to the
@@ -532,15 +535,15 @@ int avc_audit(u32 ssid, u32 tsid,
 		 *
 		 * denied == READ
 		 * avd.auditdeny & ACCESS == 0 (not set means explicit rule)
-		 * selinux_audit_data.auditdeny & ACCESS == 1
+		 * selinux_audit_data->auditdeny & ACCESS == 1
 		 *
 		 * We will NOT audit the denial even though the denied
 		 * permission was READ and the auditdeny checks were for
 		 * ACCESS
 		 */
 		if (a &&
-		    a->selinux_audit_data.auditdeny &&
-		    !(a->selinux_audit_data.auditdeny & avd->auditdeny))
+		    a->selinux_audit_data->auditdeny &&
+		    !(a->selinux_audit_data->auditdeny & avd->auditdeny))
 			audited = 0;
 	} else if (result)
 		audited = denied = requested;
@@ -551,7 +554,7 @@ int avc_audit(u32 ssid, u32 tsid,
 
 	return slow_avc_audit(ssid, tsid, tclass,
 		requested, audited, denied,
-		avd, a, flags);
+		a, flags);
 }
 
 /**
@@ -741,6 +744,41 @@ int avc_ss_reset(u32 seqno)
 	return rc;
 }
 
+/*
+ * Slow-path helper function for avc_has_perm_noaudit,
+ * when the avc_node lookup fails. We get called with
+ * the RCU read lock held, and need to return with it
+ * still held, but drop if for the security compute.
+ *
+ * Don't inline this, since it's the slow-path and just
+ * results in a bigger stack frame.
+ */
+static noinline struct avc_node *avc_compute_av(u32 ssid, u32 tsid,
+			 u16 tclass, struct av_decision *avd)
+{
+	rcu_read_unlock();
+	security_compute_av(ssid, tsid, tclass, avd);
+	rcu_read_lock();
+	return avc_insert(ssid, tsid, tclass, avd);
+}
+
+static noinline int avc_denied(u32 ssid, u32 tsid,
+			 u16 tclass, u32 requested,
+			 unsigned flags,
+			 struct av_decision *avd)
+{
+	if (flags & AVC_STRICT)
+		return -EACCES;
+
+	if (selinux_enforcing && !(avd->flags & AVD_FLAGS_PERMISSIVE))
+		return -EACCES;
+
+	avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
+				tsid, tclass, avd->seqno);
+	return 0;
+}
+
+
 /**
  * avc_has_perm_noaudit - Check permissions but perform no auditing.
  * @ssid: source security identifier
@@ -761,7 +799,7 @@ int avc_ss_reset(u32 seqno)
  * auditing, e.g. in cases where a lock must be held for the check but
  * should be released for the auditing.
  */
-int avc_has_perm_noaudit(u32 ssid, u32 tsid,
+inline int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 			 u16 tclass, u32 requested,
 			 unsigned flags,
 			 struct av_decision *avd)
@@ -776,26 +814,15 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 
 	node = avc_lookup(ssid, tsid, tclass);
 	if (unlikely(!node)) {
-		rcu_read_unlock();
-		security_compute_av(ssid, tsid, tclass, avd);
-		rcu_read_lock();
-		node = avc_insert(ssid, tsid, tclass, avd);
+		node = avc_compute_av(ssid, tsid, tclass, avd);
 	} else {
 		memcpy(avd, &node->ae.avd, sizeof(*avd));
 		avd = &node->ae.avd;
 	}
 
 	denied = requested & ~(avd->allowed);
-
-	if (denied) {
-		if (flags & AVC_STRICT)
-			rc = -EACCES;
-		else if (!selinux_enforcing || (avd->flags & AVD_FLAGS_PERMISSIVE))
-			avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
-					tsid, tclass, avd->seqno);
-		else
-			rc = -EACCES;
-	}
+	if (unlikely(denied))
+		rc = avc_denied(ssid, tsid, tclass, requested, flags, avd);
 
 	rcu_read_unlock();
 	return rc;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 304929909375..d85b793c9321 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -28,7 +28,6 @@
 #include <linux/kernel.h>
 #include <linux/tracehook.h>
 #include <linux/errno.h>
-#include <linux/ext2_fs.h>
 #include <linux/sched.h>
 #include <linux/security.h>
 #include <linux/xattr.h>
@@ -1421,6 +1420,7 @@ static int cred_has_capability(const struct cred *cred,
 			       int cap, int audit)
 {
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	struct av_decision avd;
 	u16 sclass;
 	u32 sid = cred_sid(cred);
@@ -1428,6 +1428,7 @@ static int cred_has_capability(const struct cred *cred,
 	int rc;
 
 	COMMON_AUDIT_DATA_INIT(&ad, CAP);
+	ad.selinux_audit_data = &sad;
 	ad.tsk = current;
 	ad.u.cap = cap;
 
@@ -1493,9 +1494,11 @@ static int inode_has_perm_noadp(const struct cred *cred,
 				unsigned flags)
 {
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 
 	COMMON_AUDIT_DATA_INIT(&ad, INODE);
 	ad.u.inode = inode;
+	ad.selinux_audit_data = &sad;
 	return inode_has_perm(cred, inode, perms, &ad, flags);
 }
 
@@ -1508,9 +1511,11 @@ static inline int dentry_has_perm(const struct cred *cred,
 {
 	struct inode *inode = dentry->d_inode;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 
 	COMMON_AUDIT_DATA_INIT(&ad, DENTRY);
 	ad.u.dentry = dentry;
+	ad.selinux_audit_data = &sad;
 	return inode_has_perm(cred, inode, av, &ad, 0);
 }
 
@@ -1523,9 +1528,11 @@ static inline int path_has_perm(const struct cred *cred,
 {
 	struct inode *inode = path->dentry->d_inode;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 
 	COMMON_AUDIT_DATA_INIT(&ad, PATH);
 	ad.u.path = *path;
+	ad.selinux_audit_data = &sad;
 	return inode_has_perm(cred, inode, av, &ad, 0);
 }
 
@@ -1544,11 +1551,13 @@ static int file_has_perm(const struct cred *cred,
 	struct file_security_struct *fsec = file->f_security;
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = cred_sid(cred);
 	int rc;
 
 	COMMON_AUDIT_DATA_INIT(&ad, PATH);
 	ad.u.path = file->f_path;
+	ad.selinux_audit_data = &sad;
 
 	if (sid != fsec->sid) {
 		rc = avc_has_perm(sid, fsec->sid,
@@ -1578,6 +1587,7 @@ static int may_create(struct inode *dir,
 	struct superblock_security_struct *sbsec;
 	u32 sid, newsid;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	int rc;
 
 	dsec = dir->i_security;
@@ -1588,6 +1598,7 @@ static int may_create(struct inode *dir,
 
 	COMMON_AUDIT_DATA_INIT(&ad, DENTRY);
 	ad.u.dentry = dentry;
+	ad.selinux_audit_data = &sad;
 
 	rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR,
 			  DIR__ADD_NAME | DIR__SEARCH,
@@ -1632,6 +1643,7 @@ static int may_link(struct inode *dir,
 {
 	struct inode_security_struct *dsec, *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 	u32 av;
 	int rc;
@@ -1641,6 +1653,7 @@ static int may_link(struct inode *dir,
 
 	COMMON_AUDIT_DATA_INIT(&ad, DENTRY);
 	ad.u.dentry = dentry;
+	ad.selinux_audit_data = &sad;
 
 	av = DIR__SEARCH;
 	av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME);
@@ -1675,6 +1688,7 @@ static inline int may_rename(struct inode *old_dir,
 {
 	struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 	u32 av;
 	int old_is_dir, new_is_dir;
@@ -1686,6 +1700,7 @@ static inline int may_rename(struct inode *old_dir,
 	new_dsec = new_dir->i_security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, DENTRY);
+	ad.selinux_audit_data = &sad;
 
 	ad.u.dentry = old_dentry;
 	rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR,
@@ -1971,6 +1986,7 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 	struct task_security_struct *new_tsec;
 	struct inode_security_struct *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	struct inode *inode = bprm->file->f_path.dentry->d_inode;
 	int rc;
 
@@ -2010,6 +2026,7 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 	}
 
 	COMMON_AUDIT_DATA_INIT(&ad, PATH);
+	ad.selinux_audit_data = &sad;
 	ad.u.path = bprm->file->f_path;
 
 	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
@@ -2099,6 +2116,7 @@ static inline void flush_unauthorized_files(const struct cred *cred,
 					    struct files_struct *files)
 {
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	struct file *file, *devnull = NULL;
 	struct tty_struct *tty;
 	struct fdtable *fdt;
@@ -2136,6 +2154,7 @@ static inline void flush_unauthorized_files(const struct cred *cred,
 	/* Revalidate access to inherited open files. */
 
 	COMMON_AUDIT_DATA_INIT(&ad, INODE);
+	ad.selinux_audit_data = &sad;
 
 	spin_lock(&files->file_lock);
 	for (;;) {
@@ -2147,7 +2166,7 @@ static inline void flush_unauthorized_files(const struct cred *cred,
 		fdt = files_fdtable(files);
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->open_fds->fds_bits[j];
+		set = fdt->open_fds[j];
 		if (!set)
 			continue;
 		spin_unlock(&files->file_lock);
@@ -2473,6 +2492,7 @@ static int selinux_sb_kern_mount(struct super_block *sb, int flags, void *data)
 {
 	const struct cred *cred = current_cred();
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	int rc;
 
 	rc = superblock_doinit(sb, data);
@@ -2484,6 +2504,7 @@ static int selinux_sb_kern_mount(struct super_block *sb, int flags, void *data)
 		return 0;
 
 	COMMON_AUDIT_DATA_INIT(&ad, DENTRY);
+	ad.selinux_audit_data = &sad;
 	ad.u.dentry = sb->s_root;
 	return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad);
 }
@@ -2492,8 +2513,10 @@ static int selinux_sb_statfs(struct dentry *dentry)
 {
 	const struct cred *cred = current_cred();
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 
 	COMMON_AUDIT_DATA_INIT(&ad, DENTRY);
+	ad.selinux_audit_data = &sad;
 	ad.u.dentry = dentry->d_sb->s_root;
 	return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad);
 }
@@ -2657,6 +2680,7 @@ static int selinux_inode_permission(struct inode *inode, int mask)
 {
 	const struct cred *cred = current_cred();
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 perms;
 	bool from_access;
 	unsigned flags = mask & MAY_NOT_BLOCK;
@@ -2669,10 +2693,11 @@ static int selinux_inode_permission(struct inode *inode, int mask)
 		return 0;
 
 	COMMON_AUDIT_DATA_INIT(&ad, INODE);
+	ad.selinux_audit_data = &sad;
 	ad.u.inode = inode;
 
 	if (from_access)
-		ad.selinux_audit_data.auditdeny |= FILE__AUDIT_ACCESS;
+		ad.selinux_audit_data->auditdeny |= FILE__AUDIT_ACCESS;
 
 	perms = file_mask_to_av(inode->i_mode, mask);
 
@@ -2738,6 +2763,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
 	struct inode_security_struct *isec = inode->i_security;
 	struct superblock_security_struct *sbsec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 newsid, sid = current_sid();
 	int rc = 0;
 
@@ -2752,6 +2778,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
 		return -EPERM;
 
 	COMMON_AUDIT_DATA_INIT(&ad, DENTRY);
+	ad.selinux_audit_data = &sad;
 	ad.u.dentry = dentry;
 
 	rc = avc_has_perm(sid, isec->sid, isec->sclass,
@@ -2971,15 +2998,15 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 	/* fall through */
 	case FIGETBSZ:
 	/* fall through */
-	case EXT2_IOC_GETFLAGS:
+	case FS_IOC_GETFLAGS:
 	/* fall through */
-	case EXT2_IOC_GETVERSION:
+	case FS_IOC_GETVERSION:
 		error = file_has_perm(cred, file, FILE__GETATTR);
 		break;
 
-	case EXT2_IOC_SETFLAGS:
+	case FS_IOC_SETFLAGS:
 	/* fall through */
-	case EXT2_IOC_SETVERSION:
+	case FS_IOC_SETVERSION:
 		error = file_has_perm(cred, file, FILE__SETATTR);
 		break;
 
@@ -3346,10 +3373,12 @@ static int selinux_kernel_module_request(char *kmod_name)
 {
 	u32 sid;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 
 	sid = task_sid(current);
 
 	COMMON_AUDIT_DATA_INIT(&ad, KMOD);
+	ad.selinux_audit_data = &sad;
 	ad.u.kmod_name = kmod_name;
 
 	return avc_has_perm(sid, SECINITSID_KERNEL, SECCLASS_SYSTEM,
@@ -3488,8 +3517,8 @@ static int selinux_parse_skb_ipv4(struct sk_buff *skb,
 	if (ihlen < sizeof(_iph))
 		goto out;
 
-	ad->u.net.v4info.saddr = ih->saddr;
-	ad->u.net.v4info.daddr = ih->daddr;
+	ad->u.net->v4info.saddr = ih->saddr;
+	ad->u.net->v4info.daddr = ih->daddr;
 	ret = 0;
 
 	if (proto)
@@ -3507,8 +3536,8 @@ static int selinux_parse_skb_ipv4(struct sk_buff *skb,
 		if (th == NULL)
 			break;
 
-		ad->u.net.sport = th->source;
-		ad->u.net.dport = th->dest;
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
 		break;
 	}
 
@@ -3523,8 +3552,8 @@ static int selinux_parse_skb_ipv4(struct sk_buff *skb,
 		if (uh == NULL)
 			break;
 
-		ad->u.net.sport = uh->source;
-		ad->u.net.dport = uh->dest;
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
 		break;
 	}
 
@@ -3539,8 +3568,8 @@ static int selinux_parse_skb_ipv4(struct sk_buff *skb,
 		if (dh == NULL)
 			break;
 
-		ad->u.net.sport = dh->dccph_sport;
-		ad->u.net.dport = dh->dccph_dport;
+		ad->u.net->sport = dh->dccph_sport;
+		ad->u.net->dport = dh->dccph_dport;
 		break;
 	}
 
@@ -3567,8 +3596,8 @@ static int selinux_parse_skb_ipv6(struct sk_buff *skb,
 	if (ip6 == NULL)
 		goto out;
 
-	ad->u.net.v6info.saddr = ip6->saddr;
-	ad->u.net.v6info.daddr = ip6->daddr;
+	ad->u.net->v6info.saddr = ip6->saddr;
+	ad->u.net->v6info.daddr = ip6->daddr;
 	ret = 0;
 
 	nexthdr = ip6->nexthdr;
@@ -3588,8 +3617,8 @@ static int selinux_parse_skb_ipv6(struct sk_buff *skb,
 		if (th == NULL)
 			break;
 
-		ad->u.net.sport = th->source;
-		ad->u.net.dport = th->dest;
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
 		break;
 	}
 
@@ -3600,8 +3629,8 @@ static int selinux_parse_skb_ipv6(struct sk_buff *skb,
 		if (uh == NULL)
 			break;
 
-		ad->u.net.sport = uh->source;
-		ad->u.net.dport = uh->dest;
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
 		break;
 	}
 
@@ -3612,8 +3641,8 @@ static int selinux_parse_skb_ipv6(struct sk_buff *skb,
 		if (dh == NULL)
 			break;
 
-		ad->u.net.sport = dh->dccph_sport;
-		ad->u.net.dport = dh->dccph_dport;
+		ad->u.net->sport = dh->dccph_sport;
+		ad->u.net->dport = dh->dccph_dport;
 		break;
 	}
 
@@ -3633,13 +3662,13 @@ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad,
 	char *addrp;
 	int ret;
 
-	switch (ad->u.net.family) {
+	switch (ad->u.net->family) {
 	case PF_INET:
 		ret = selinux_parse_skb_ipv4(skb, ad, proto);
 		if (ret)
 			goto parse_error;
-		addrp = (char *)(src ? &ad->u.net.v4info.saddr :
-				       &ad->u.net.v4info.daddr);
+		addrp = (char *)(src ? &ad->u.net->v4info.saddr :
+				       &ad->u.net->v4info.daddr);
 		goto okay;
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
@@ -3647,8 +3676,8 @@ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad,
 		ret = selinux_parse_skb_ipv6(skb, ad, proto);
 		if (ret)
 			goto parse_error;
-		addrp = (char *)(src ? &ad->u.net.v6info.saddr :
-				       &ad->u.net.v6info.daddr);
+		addrp = (char *)(src ? &ad->u.net->v6info.saddr :
+				       &ad->u.net->v6info.daddr);
 		goto okay;
 #endif	/* IPV6 */
 	default:
@@ -3722,13 +3751,17 @@ static int sock_has_perm(struct task_struct *task, struct sock *sk, u32 perms)
 {
 	struct sk_security_struct *sksec = sk->sk_security;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
+	struct lsm_network_audit net = {0,};
 	u32 tsid = task_sid(task);
 
 	if (sksec->sid == SECINITSID_KERNEL)
 		return 0;
 
 	COMMON_AUDIT_DATA_INIT(&ad, NET);
-	ad.u.net.sk = sk;
+	ad.selinux_audit_data = &sad;
+	ad.u.net = &net;
+	ad.u.net->sk = sk;
 
 	return avc_has_perm(tsid, sksec->sid, sksec->sclass, perms, &ad);
 }
@@ -3806,6 +3839,8 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 		char *addrp;
 		struct sk_security_struct *sksec = sk->sk_security;
 		struct common_audit_data ad;
+		struct selinux_audit_data sad = {0,};
+		struct lsm_network_audit net = {0,};
 		struct sockaddr_in *addr4 = NULL;
 		struct sockaddr_in6 *addr6 = NULL;
 		unsigned short snum;
@@ -3832,8 +3867,10 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 				if (err)
 					goto out;
 				COMMON_AUDIT_DATA_INIT(&ad, NET);
-				ad.u.net.sport = htons(snum);
-				ad.u.net.family = family;
+				ad.selinux_audit_data = &sad;
+				ad.u.net = &net;
+				ad.u.net->sport = htons(snum);
+				ad.u.net->family = family;
 				err = avc_has_perm(sksec->sid, sid,
 						   sksec->sclass,
 						   SOCKET__NAME_BIND, &ad);
@@ -3865,13 +3902,15 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 			goto out;
 
 		COMMON_AUDIT_DATA_INIT(&ad, NET);
-		ad.u.net.sport = htons(snum);
-		ad.u.net.family = family;
+		ad.selinux_audit_data = &sad;
+		ad.u.net = &net;
+		ad.u.net->sport = htons(snum);
+		ad.u.net->family = family;
 
 		if (family == PF_INET)
-			ad.u.net.v4info.saddr = addr4->sin_addr.s_addr;
+			ad.u.net->v4info.saddr = addr4->sin_addr.s_addr;
 		else
-			ad.u.net.v6info.saddr = addr6->sin6_addr;
+			ad.u.net->v6info.saddr = addr6->sin6_addr;
 
 		err = avc_has_perm(sksec->sid, sid,
 				   sksec->sclass, node_perm, &ad);
@@ -3898,6 +3937,8 @@ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address,
 	if (sksec->sclass == SECCLASS_TCP_SOCKET ||
 	    sksec->sclass == SECCLASS_DCCP_SOCKET) {
 		struct common_audit_data ad;
+		struct selinux_audit_data sad = {0,};
+		struct lsm_network_audit net = {0,};
 		struct sockaddr_in *addr4 = NULL;
 		struct sockaddr_in6 *addr6 = NULL;
 		unsigned short snum;
@@ -3923,8 +3964,10 @@ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address,
 		       TCP_SOCKET__NAME_CONNECT : DCCP_SOCKET__NAME_CONNECT;
 
 		COMMON_AUDIT_DATA_INIT(&ad, NET);
-		ad.u.net.dport = htons(snum);
-		ad.u.net.family = sk->sk_family;
+		ad.selinux_audit_data = &sad;
+		ad.u.net = &net;
+		ad.u.net->dport = htons(snum);
+		ad.u.net->family = sk->sk_family;
 		err = avc_has_perm(sksec->sid, sid, sksec->sclass, perm, &ad);
 		if (err)
 			goto out;
@@ -4013,10 +4056,14 @@ static int selinux_socket_unix_stream_connect(struct sock *sock,
 	struct sk_security_struct *sksec_other = other->sk_security;
 	struct sk_security_struct *sksec_new = newsk->sk_security;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
+	struct lsm_network_audit net = {0,};
 	int err;
 
 	COMMON_AUDIT_DATA_INIT(&ad, NET);
-	ad.u.net.sk = other;
+	ad.selinux_audit_data = &sad;
+	ad.u.net = &net;
+	ad.u.net->sk = other;
 
 	err = avc_has_perm(sksec_sock->sid, sksec_other->sid,
 			   sksec_other->sclass,
@@ -4043,9 +4090,13 @@ static int selinux_socket_unix_may_send(struct socket *sock,
 	struct sk_security_struct *ssec = sock->sk->sk_security;
 	struct sk_security_struct *osec = other->sk->sk_security;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
+	struct lsm_network_audit net = {0,};
 
 	COMMON_AUDIT_DATA_INIT(&ad, NET);
-	ad.u.net.sk = other->sk;
+	ad.selinux_audit_data = &sad;
+	ad.u.net = &net;
+	ad.u.net->sk = other->sk;
 
 	return avc_has_perm(ssec->sid, osec->sid, osec->sclass, SOCKET__SENDTO,
 			    &ad);
@@ -4081,11 +4132,15 @@ static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb,
 	struct sk_security_struct *sksec = sk->sk_security;
 	u32 sk_sid = sksec->sid;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
+	struct lsm_network_audit net = {0,};
 	char *addrp;
 
 	COMMON_AUDIT_DATA_INIT(&ad, NET);
-	ad.u.net.netif = skb->skb_iif;
-	ad.u.net.family = family;
+	ad.selinux_audit_data = &sad;
+	ad.u.net = &net;
+	ad.u.net->netif = skb->skb_iif;
+	ad.u.net->family = family;
 	err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL);
 	if (err)
 		return err;
@@ -4112,6 +4167,8 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	u16 family = sk->sk_family;
 	u32 sk_sid = sksec->sid;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
+	struct lsm_network_audit net = {0,};
 	char *addrp;
 	u8 secmark_active;
 	u8 peerlbl_active;
@@ -4136,8 +4193,10 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		return 0;
 
 	COMMON_AUDIT_DATA_INIT(&ad, NET);
-	ad.u.net.netif = skb->skb_iif;
-	ad.u.net.family = family;
+	ad.selinux_audit_data = &sad;
+	ad.u.net = &net;
+	ad.u.net->netif = skb->skb_iif;
+	ad.u.net->family = family;
 	err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL);
 	if (err)
 		return err;
@@ -4472,6 +4531,8 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
 	char *addrp;
 	u32 peer_sid;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
+	struct lsm_network_audit net = {0,};
 	u8 secmark_active;
 	u8 netlbl_active;
 	u8 peerlbl_active;
@@ -4489,8 +4550,10 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
 		return NF_DROP;
 
 	COMMON_AUDIT_DATA_INIT(&ad, NET);
-	ad.u.net.netif = ifindex;
-	ad.u.net.family = family;
+	ad.selinux_audit_data = &sad;
+	ad.u.net = &net;
+	ad.u.net->netif = ifindex;
+	ad.u.net->family = family;
 	if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0)
 		return NF_DROP;
 
@@ -4577,6 +4640,8 @@ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb,
 	struct sock *sk = skb->sk;
 	struct sk_security_struct *sksec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
+	struct lsm_network_audit net = {0,};
 	char *addrp;
 	u8 proto;
 
@@ -4585,8 +4650,10 @@ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb,
 	sksec = sk->sk_security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, NET);
-	ad.u.net.netif = ifindex;
-	ad.u.net.family = family;
+	ad.selinux_audit_data = &sad;
+	ad.u.net = &net;
+	ad.u.net->netif = ifindex;
+	ad.u.net->family = family;
 	if (selinux_parse_skb(skb, &ad, &addrp, 0, &proto))
 		return NF_DROP;
 
@@ -4608,6 +4675,8 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 	u32 peer_sid;
 	struct sock *sk;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
+	struct lsm_network_audit net = {0,};
 	char *addrp;
 	u8 secmark_active;
 	u8 peerlbl_active;
@@ -4654,8 +4723,10 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 	}
 
 	COMMON_AUDIT_DATA_INIT(&ad, NET);
-	ad.u.net.netif = ifindex;
-	ad.u.net.family = family;
+	ad.selinux_audit_data = &sad;
+	ad.u.net = &net;
+	ad.u.net->netif = ifindex;
+	ad.u.net->family = family;
 	if (selinux_parse_skb(skb, &ad, &addrp, 0, NULL))
 		return NF_DROP;
 
@@ -4770,11 +4841,13 @@ static int ipc_has_perm(struct kern_ipc_perm *ipc_perms,
 {
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 
 	isec = ipc_perms->security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = ipc_perms->key;
 
 	return avc_has_perm(sid, isec->sid, isec->sclass, perms, &ad);
@@ -4795,6 +4868,7 @@ static int selinux_msg_queue_alloc_security(struct msg_queue *msq)
 {
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 	int rc;
 
@@ -4805,6 +4879,7 @@ static int selinux_msg_queue_alloc_security(struct msg_queue *msq)
 	isec = msq->q_perm.security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = msq->q_perm.key;
 
 	rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ,
@@ -4825,11 +4900,13 @@ static int selinux_msg_queue_associate(struct msg_queue *msq, int msqflg)
 {
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 
 	isec = msq->q_perm.security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = msq->q_perm.key;
 
 	return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ,
@@ -4869,6 +4946,7 @@ static int selinux_msg_queue_msgsnd(struct msg_queue *msq, struct msg_msg *msg,
 	struct ipc_security_struct *isec;
 	struct msg_security_struct *msec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 	int rc;
 
@@ -4890,6 +4968,7 @@ static int selinux_msg_queue_msgsnd(struct msg_queue *msq, struct msg_msg *msg,
 	}
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = msq->q_perm.key;
 
 	/* Can this process write to the queue? */
@@ -4914,6 +4993,7 @@ static int selinux_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg,
 	struct ipc_security_struct *isec;
 	struct msg_security_struct *msec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = task_sid(target);
 	int rc;
 
@@ -4921,6 +5001,7 @@ static int selinux_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg,
 	msec = msg->security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = msq->q_perm.key;
 
 	rc = avc_has_perm(sid, isec->sid,
@@ -4936,6 +5017,7 @@ static int selinux_shm_alloc_security(struct shmid_kernel *shp)
 {
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 	int rc;
 
@@ -4946,6 +5028,7 @@ static int selinux_shm_alloc_security(struct shmid_kernel *shp)
 	isec = shp->shm_perm.security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = shp->shm_perm.key;
 
 	rc = avc_has_perm(sid, isec->sid, SECCLASS_SHM,
@@ -4966,11 +5049,13 @@ static int selinux_shm_associate(struct shmid_kernel *shp, int shmflg)
 {
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 
 	isec = shp->shm_perm.security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = shp->shm_perm.key;
 
 	return avc_has_perm(sid, isec->sid, SECCLASS_SHM,
@@ -5028,6 +5113,7 @@ static int selinux_sem_alloc_security(struct sem_array *sma)
 {
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 	int rc;
 
@@ -5038,6 +5124,7 @@ static int selinux_sem_alloc_security(struct sem_array *sma)
 	isec = sma->sem_perm.security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = sma->sem_perm.key;
 
 	rc = avc_has_perm(sid, isec->sid, SECCLASS_SEM,
@@ -5058,11 +5145,13 @@ static int selinux_sem_associate(struct sem_array *sma, int semflg)
 {
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
+	struct selinux_audit_data sad = {0,};
 	u32 sid = current_sid();
 
 	isec = sma->sem_perm.security;
 
 	COMMON_AUDIT_DATA_INIT(&ad, IPC);
+	ad.selinux_audit_data = &sad;
 	ad.u.ipc_id = sma->sem_perm.key;
 
 	return avc_has_perm(sid, isec->sid, SECCLASS_SEM,
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index 47fda963495d..1931370233d7 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -15,7 +15,6 @@
 #include <linux/audit.h>
 #include <linux/lsm_audit.h>
 #include <linux/in6.h>
-#include <asm/system.h>
 #include "flask.h"
 #include "av_permissions.h"
 #include "security.h"
@@ -48,6 +47,31 @@ struct avc_cache_stats {
 };
 
 /*
+ * We only need this data after we have decided to send an audit message.
+ */
+struct selinux_late_audit_data {
+	u32 ssid;
+	u32 tsid;
+	u16 tclass;
+	u32 requested;
+	u32 audited;
+	u32 denied;
+	int result;
+};
+
+/*
+ * We collect this at the beginning or during an selinux security operation
+ */
+struct selinux_audit_data {
+	/*
+	 * auditdeny is a bit tricky and unintuitive.  See the
+	 * comments in avc.c for it's meaning and usage.
+	 */
+	u32 auditdeny;
+	struct selinux_late_audit_data *slad;
+};
+
+/*
  * AVC operations
  */
 
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index b43813c9e049..c220f314709c 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -7,6 +7,8 @@
 #ifndef _SELINUX_XFRM_H_
 #define _SELINUX_XFRM_H_
 
+#include <net/flow.h>
+
 int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
 			      struct xfrm_user_sec_ctx *sec_ctx);
 int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 48a7d0014b4f..d7018bfa1f00 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -344,7 +344,7 @@ static int sel_make_classes(void);
 static int sel_make_policycap(void);
 
 /* declaration for sel_make_class_dirs */
-static int sel_make_dir(struct inode *dir, struct dentry *dentry,
+static struct dentry *sel_make_dir(struct dentry *dir, const char *name,
 			unsigned long *ino);
 
 static ssize_t sel_read_mls(struct file *filp, char __user *buf,
@@ -1678,13 +1678,9 @@ static int sel_make_class_dir_entries(char *classname, int index,
 	inode->i_ino = sel_class_to_ino(index);
 	d_add(dentry, inode);
 
-	dentry = d_alloc_name(dir, "perms");
-	if (!dentry)
-		return -ENOMEM;
-
-	rc = sel_make_dir(dir->d_inode, dentry, &last_class_ino);
-	if (rc)
-		return rc;
+	dentry = sel_make_dir(dir, "perms", &last_class_ino);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
 
 	rc = sel_make_perm_files(classname, index, dentry);
 
@@ -1733,15 +1729,12 @@ static int sel_make_classes(void)
 	for (i = 0; i < nclasses; i++) {
 		struct dentry *class_name_dir;
 
-		rc = -ENOMEM;
-		class_name_dir = d_alloc_name(class_dir, classes[i]);
-		if (!class_name_dir)
-			goto out;
-
-		rc = sel_make_dir(class_dir->d_inode, class_name_dir,
+		class_name_dir = sel_make_dir(class_dir, classes[i],
 				&last_class_ino);
-		if (rc)
+		if (IS_ERR(class_name_dir)) {
+			rc = PTR_ERR(class_name_dir);
 			goto out;
+		}
 
 		/* i+1 since class values are 1-indexed */
 		rc = sel_make_class_dir_entries(classes[i], i + 1,
@@ -1787,14 +1780,20 @@ static int sel_make_policycap(void)
 	return 0;
 }
 
-static int sel_make_dir(struct inode *dir, struct dentry *dentry,
+static struct dentry *sel_make_dir(struct dentry *dir, const char *name,
 			unsigned long *ino)
 {
+	struct dentry *dentry = d_alloc_name(dir, name);
 	struct inode *inode;
 
-	inode = sel_make_inode(dir->i_sb, S_IFDIR | S_IRUGO | S_IXUGO);
-	if (!inode)
-		return -ENOMEM;
+	if (!dentry)
+		return ERR_PTR(-ENOMEM);
+
+	inode = sel_make_inode(dir->d_sb, S_IFDIR | S_IRUGO | S_IXUGO);
+	if (!inode) {
+		dput(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
@@ -1803,16 +1802,16 @@ static int sel_make_dir(struct inode *dir, struct dentry *dentry,
 	inc_nlink(inode);
 	d_add(dentry, inode);
 	/* bump link count on parent directory, too */
-	inc_nlink(dir);
+	inc_nlink(dir->d_inode);
 
-	return 0;
+	return dentry;
 }
 
 static int sel_fill_super(struct super_block *sb, void *data, int silent)
 {
 	int ret;
 	struct dentry *dentry;
-	struct inode *inode, *root_inode;
+	struct inode *inode;
 	struct inode_security_struct *isec;
 
 	static struct tree_descr selinux_files[] = {
@@ -1839,18 +1838,12 @@ static int sel_fill_super(struct super_block *sb, void *data, int silent)
 	if (ret)
 		goto err;
 
-	root_inode = sb->s_root->d_inode;
-
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, BOOL_DIR_NAME);
-	if (!dentry)
+	bool_dir = sel_make_dir(sb->s_root, BOOL_DIR_NAME, &sel_last_ino);
+	if (IS_ERR(bool_dir)) {
+		ret = PTR_ERR(bool_dir);
+		bool_dir = NULL;
 		goto err;
-
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
-		goto err;
-
-	bool_dir = dentry;
+	}
 
 	ret = -ENOMEM;
 	dentry = d_alloc_name(sb->s_root, NULL_FILE_NAME);
@@ -1872,54 +1865,39 @@ static int sel_fill_super(struct super_block *sb, void *data, int silent)
 	d_add(dentry, inode);
 	selinux_null = dentry;
 
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, "avc");
-	if (!dentry)
-		goto err;
-
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
+	dentry = sel_make_dir(sb->s_root, "avc", &sel_last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
 		goto err;
+	}
 
 	ret = sel_make_avc_files(dentry);
 	if (ret)
 		goto err;
 
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, "initial_contexts");
-	if (!dentry)
-		goto err;
-
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
+	dentry = sel_make_dir(sb->s_root, "initial_contexts", &sel_last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
 		goto err;
+	}
 
 	ret = sel_make_initcon_files(dentry);
 	if (ret)
 		goto err;
 
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, "class");
-	if (!dentry)
-		goto err;
-
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
-		goto err;
-
-	class_dir = dentry;
-
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, "policy_capabilities");
-	if (!dentry)
+	class_dir = sel_make_dir(sb->s_root, "class", &sel_last_ino);
+	if (IS_ERR(class_dir)) {
+		ret = PTR_ERR(class_dir);
+		class_dir = NULL;
 		goto err;
+	}
 
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
+	policycap_dir = sel_make_dir(sb->s_root, "policy_capabilities", &sel_last_ino);
+	if (IS_ERR(policycap_dir)) {
+		ret = PTR_ERR(policycap_dir);
+		policycap_dir = NULL;
 		goto err;
-
-	policycap_dir = dentry;
-
+	}
 	return 0;
 err:
 	printk(KERN_ERR "SELinux: %s:  failed while creating inodes\n",
diff --git a/security/smack/smack.h b/security/smack/smack.h
index 2ad00657b801..4ede719922ed 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -185,6 +185,15 @@ struct smack_known {
  */
 #define SMK_NUM_ACCESS_TYPE 5
 
+/* SMACK data */
+struct smack_audit_data {
+	const char *function;
+	char *subject;
+	char *object;
+	char *request;
+	int result;
+};
+
 /*
  * Smack audit data; is empty if CONFIG_AUDIT not set
  * to save some stack
@@ -192,6 +201,7 @@ struct smack_known {
 struct smk_audit_info {
 #ifdef CONFIG_AUDIT
 	struct common_audit_data a;
+	struct smack_audit_data sad;
 #endif
 };
 /*
@@ -311,7 +321,16 @@ static inline void smk_ad_init(struct smk_audit_info *a, const char *func,
 {
 	memset(a, 0, sizeof(*a));
 	a->a.type = type;
-	a->a.smack_audit_data.function = func;
+	a->a.smack_audit_data = &a->sad;
+	a->a.smack_audit_data->function = func;
+}
+
+static inline void smk_ad_init_net(struct smk_audit_info *a, const char *func,
+				   char type, struct lsm_network_audit *net)
+{
+	smk_ad_init(a, func, type);
+	memset(net, 0, sizeof(*net));
+	a->a.u.net = net;
 }
 
 static inline void smk_ad_setfield_u_tsk(struct smk_audit_info *a,
@@ -337,7 +356,7 @@ static inline void smk_ad_setfield_u_fs_path(struct smk_audit_info *a,
 static inline void smk_ad_setfield_u_net_sk(struct smk_audit_info *a,
 					    struct sock *sk)
 {
-	a->a.u.net.sk = sk;
+	a->a.u.net->sk = sk;
 }
 
 #else /* no AUDIT */
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
index cc7cb6edba08..c8115f7308f8 100644
--- a/security/smack/smack_access.c
+++ b/security/smack/smack_access.c
@@ -275,9 +275,9 @@ static inline void smack_str_from_perm(char *string, int access)
 static void smack_log_callback(struct audit_buffer *ab, void *a)
 {
 	struct common_audit_data *ad = a;
-	struct smack_audit_data *sad = &ad->smack_audit_data;
+	struct smack_audit_data *sad = ad->smack_audit_data;
 	audit_log_format(ab, "lsm=SMACK fn=%s action=%s",
-			 ad->smack_audit_data.function,
+			 ad->smack_audit_data->function,
 			 sad->result ? "denied" : "granted");
 	audit_log_format(ab, " subject=");
 	audit_log_untrustedstring(ab, sad->subject);
@@ -310,19 +310,19 @@ void smack_log(char *subject_label, char *object_label, int request,
 	if (result == 0 && (log_policy & SMACK_AUDIT_ACCEPT) == 0)
 		return;
 
-	if (a->smack_audit_data.function == NULL)
-		a->smack_audit_data.function = "unknown";
+	sad = a->smack_audit_data;
+
+	if (sad->function == NULL)
+		sad->function = "unknown";
 
 	/* end preparing the audit data */
-	sad = &a->smack_audit_data;
 	smack_str_from_perm(request_buffer, request);
 	sad->subject = subject_label;
 	sad->object  = object_label;
 	sad->request = request_buffer;
 	sad->result  = result;
-	a->lsm_pre_audit = smack_log_callback;
 
-	common_lsm_audit(a);
+	common_lsm_audit(a, smack_log_callback, NULL);
 }
 #else /* #ifdef CONFIG_AUDIT */
 void smack_log(char *subject_label, char *object_label, int request,
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index cd667b4089a5..81c03a597112 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1939,16 +1939,17 @@ static int smack_netlabel_send(struct sock *sk, struct sockaddr_in *sap)
 	char *hostsp;
 	struct socket_smack *ssp = sk->sk_security;
 	struct smk_audit_info ad;
+	struct lsm_network_audit net;
 
 	rcu_read_lock();
 	hostsp = smack_host_label(sap);
 	if (hostsp != NULL) {
 		sk_lbl = SMACK_UNLABELED_SOCKET;
 #ifdef CONFIG_AUDIT
-		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
-		ad.a.u.net.family = sap->sin_family;
-		ad.a.u.net.dport = sap->sin_port;
-		ad.a.u.net.v4info.daddr = sap->sin_addr.s_addr;
+		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+		ad.a.u.net->family = sap->sin_family;
+		ad.a.u.net->dport = sap->sin_port;
+		ad.a.u.net->v4info.daddr = sap->sin_addr.s_addr;
 #endif
 		rc = smk_access(ssp->smk_out, hostsp, MAY_WRITE, &ad);
 	} else {
@@ -2808,9 +2809,10 @@ static int smack_unix_stream_connect(struct sock *sock,
 	struct socket_smack *osp = other->sk_security;
 	struct socket_smack *nsp = newsk->sk_security;
 	struct smk_audit_info ad;
+	struct lsm_network_audit net;
 	int rc = 0;
 
-	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+	smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
 	smk_ad_setfield_u_net_sk(&ad, other);
 
 	if (!capable(CAP_MAC_OVERRIDE))
@@ -2840,9 +2842,10 @@ static int smack_unix_may_send(struct socket *sock, struct socket *other)
 	struct socket_smack *ssp = sock->sk->sk_security;
 	struct socket_smack *osp = other->sk->sk_security;
 	struct smk_audit_info ad;
+	struct lsm_network_audit net;
 	int rc = 0;
 
-	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+	smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
 	smk_ad_setfield_u_net_sk(&ad, other->sk);
 
 	if (!capable(CAP_MAC_OVERRIDE))
@@ -2990,6 +2993,7 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	char *csp;
 	int rc;
 	struct smk_audit_info ad;
+	struct lsm_network_audit net;
 	if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
 		return 0;
 
@@ -3007,9 +3011,9 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	netlbl_secattr_destroy(&secattr);
 
 #ifdef CONFIG_AUDIT
-	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
-	ad.a.u.net.family = sk->sk_family;
-	ad.a.u.net.netif = skb->skb_iif;
+	smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+	ad.a.u.net->family = sk->sk_family;
+	ad.a.u.net->netif = skb->skb_iif;
 	ipv4_skb_to_auditdata(skb, &ad.a, NULL);
 #endif
 	/*
@@ -3152,6 +3156,7 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	char *sp;
 	int rc;
 	struct smk_audit_info ad;
+	struct lsm_network_audit net;
 
 	/* handle mapped IPv4 packets arriving via IPv6 sockets */
 	if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
@@ -3166,9 +3171,9 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	netlbl_secattr_destroy(&secattr);
 
 #ifdef CONFIG_AUDIT
-	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
-	ad.a.u.net.family = family;
-	ad.a.u.net.netif = skb->skb_iif;
+	smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+	ad.a.u.net->family = family;
+	ad.a.u.net->netif = skb->skb_iif;
 	ipv4_skb_to_auditdata(skb, &ad.a, NULL);
 #endif
 	/*
diff --git a/sound/arm/pxa2xx-ac97-lib.c b/sound/arm/pxa2xx-ac97-lib.c
index d1aa4218f129..48d7c0aa5073 100644
--- a/sound/arm/pxa2xx-ac97-lib.c
+++ b/sound/arm/pxa2xx-ac97-lib.c
@@ -17,11 +17,12 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/io.h>
 
 #include <sound/ac97_codec.h>
 #include <sound/pxa2xx-lib.h>
 
-#include <asm/irq.h>
+#include <mach/irqs.h>
 #include <mach/regs-ac97.h>
 #include <mach/audio.h>
 
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index 3a39626a82d6..afef72c4f0d3 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 
diff --git a/sound/atmel/abdac.c b/sound/atmel/abdac.c
index 4fa1dbd8ee83..f7c2bb08055d 100644
--- a/sound/atmel/abdac.c
+++ b/sound/atmel/abdac.c
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/types.h>
 #include <linux/io.h>
 
 #include <sound/core.h>
@@ -467,15 +468,24 @@ static int __devinit atmel_abdac_probe(struct platform_device *pdev)
 	snd_card_set_dev(card, &pdev->dev);
 
 	if (pdata->dws.dma_dev) {
-		struct dw_dma_slave *dws = &pdata->dws;
 		dma_cap_mask_t mask;
 
-		dws->tx_reg = regs->start + DAC_DATA;
-
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
 
-		dac->dma.chan = dma_request_channel(mask, filter, dws);
+		dac->dma.chan = dma_request_channel(mask, filter, &pdata->dws);
+		if (dac->dma.chan) {
+			struct dma_slave_config dma_conf = {
+				.dst_addr = regs->start + DAC_DATA,
+				.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+				.src_maxburst = 1,
+				.dst_maxburst = 1,
+				.direction = DMA_MEM_TO_DEV,
+				.device_fc = false,
+			};
+
+			dmaengine_slave_config(dac->dma.chan, &dma_conf);
+		}
 	}
 	if (!pdata->dws.dma_dev || !dac->dma.chan) {
 		dev_dbg(&pdev->dev, "DMA not available\n");
diff --git a/sound/atmel/ac97c.c b/sound/atmel/ac97c.c
index 61dade698358..115313ef54d6 100644
--- a/sound/atmel/ac97c.c
+++ b/sound/atmel/ac97c.c
@@ -20,6 +20,7 @@
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/gpio.h>
+#include <linux/types.h>
 #include <linux/io.h>
 
 #include <sound/core.h>
@@ -1014,16 +1015,28 @@ static int __devinit atmel_ac97c_probe(struct platform_device *pdev)
 
 	if (cpu_is_at32ap7000()) {
 		if (pdata->rx_dws.dma_dev) {
-			struct dw_dma_slave *dws = &pdata->rx_dws;
 			dma_cap_mask_t mask;
 
-			dws->rx_reg = regs->start + AC97C_CARHR + 2;
-
 			dma_cap_zero(mask);
 			dma_cap_set(DMA_SLAVE, mask);
 
 			chip->dma.rx_chan = dma_request_channel(mask, filter,
-								dws);
+								&pdata->rx_dws);
+			if (chip->dma.rx_chan) {
+				struct dma_slave_config dma_conf = {
+					.src_addr = regs->start + AC97C_CARHR +
+						2,
+					.src_addr_width =
+						DMA_SLAVE_BUSWIDTH_2_BYTES,
+					.src_maxburst = 1,
+					.dst_maxburst = 1,
+					.direction = DMA_DEV_TO_MEM,
+					.device_fc = false,
+				};
+
+				dmaengine_slave_config(chip->dma.rx_chan,
+						&dma_conf);
+			}
 
 			dev_info(&chip->pdev->dev, "using %s for DMA RX\n",
 				dev_name(&chip->dma.rx_chan->dev->device));
@@ -1031,16 +1044,28 @@ static int __devinit atmel_ac97c_probe(struct platform_device *pdev)
 		}
 
 		if (pdata->tx_dws.dma_dev) {
-			struct dw_dma_slave *dws = &pdata->tx_dws;
 			dma_cap_mask_t mask;
 
-			dws->tx_reg = regs->start + AC97C_CATHR + 2;
-
 			dma_cap_zero(mask);
 			dma_cap_set(DMA_SLAVE, mask);
 
 			chip->dma.tx_chan = dma_request_channel(mask, filter,
-								dws);
+								&pdata->tx_dws);
+			if (chip->dma.tx_chan) {
+				struct dma_slave_config dma_conf = {
+					.dst_addr = regs->start + AC97C_CATHR +
+						2,
+					.dst_addr_width =
+						DMA_SLAVE_BUSWIDTH_2_BYTES,
+					.src_maxburst = 1,
+					.dst_maxburst = 1,
+					.direction = DMA_MEM_TO_DEV,
+					.device_fc = false,
+				};
+
+				dmaengine_slave_config(chip->dma.tx_chan,
+						&dma_conf);
+			}
 
 			dev_info(&chip->pdev->dev, "using %s for DMA TX\n",
 				dev_name(&chip->dma.tx_chan->dev->device));
diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c
index bbe32d2177d9..dbc550716790 100644
--- a/sound/core/seq/seq_dummy.c
+++ b/sound/core/seq/seq_dummy.c
@@ -46,7 +46,7 @@
 
   The number of ports to be created can be specified via the module
   parameter "ports".  For example, to create four ports, add the
-  following option in /etc/modprobe.conf:
+  following option in a configuration file under /etc/modprobe.d/:
 
 	option snd-seq-dummy ports=4
 
diff --git a/sound/drivers/Kconfig b/sound/drivers/Kconfig
index c8961165277c..fe5ae09ffccb 100644
--- a/sound/drivers/Kconfig
+++ b/sound/drivers/Kconfig
@@ -50,7 +50,8 @@ config SND_PCSP
 	  before the other sound driver of yours, making the
 	  pc-speaker a default sound device. Which is likely not
 	  what you want. To make this driver play nicely with other
-	  sound driver, you can add this into your /etc/modprobe.conf:
+	  sound driver, you can add this in a configuration file under
+	  /etc/modprobe.d/ directory:
 	  options snd-pcsp index=2
 
 	  You don't need this driver if you only want your pc-speaker to beep.
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index babaedd242f7..d7ccf28bd66a 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -65,7 +65,7 @@ static int index = SNDRV_DEFAULT_IDX1;	/* Index 0-MAX */
 static char *id = SNDRV_DEFAULT_STR1;		/* ID for this card */
 //static bool enable = SNDRV_DEFAULT_ENABLE1;	/* Enable this card */
 #ifdef CONFIG_PNP
-static int isapnp = 1;			/* Enable ISA PnP detection */
+static bool isapnp = true;			/* Enable ISA PnP detection */
 #endif
 static long port = SNDRV_DEFAULT_PORT1; 	/* 0x530,0xe80,0xf40,0x604 */
 static long mpu_port = SNDRV_DEFAULT_PORT1;	/* 0x300,0x310,0x320,0x330 */
diff --git a/sound/oss/msnd_pinnacle.c b/sound/oss/msnd_pinnacle.c
index eba734560f6f..2c79d60a725f 100644
--- a/sound/oss/msnd_pinnacle.c
+++ b/sound/oss/msnd_pinnacle.c
@@ -1631,7 +1631,7 @@ static int ide_irq __initdata = 0;
 static int joystick_io __initdata = 0;
 
 /* If we have the digital daugherboard... */
-static int digital __initdata = 0;
+static bool digital __initdata = false;
 #endif
 
 static int fifosize __initdata =	DEFFIFOSIZE;
diff --git a/sound/oss/os.h b/sound/oss/os.h
index a1a962d7f67d..75ad0cd0c0ab 100644
--- a/sound/oss/os.h
+++ b/sound/oss/os.h
@@ -16,7 +16,6 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <asm/page.h>
-#include <asm/system.h>
 #include <linux/vmalloc.h>
 #include <asm/uaccess.h>
 #include <linux/poll.h>
diff --git a/sound/oss/vidc.c b/sound/oss/vidc.c
index 12ba28e7b933..92ca5bee1860 100644
--- a/sound/oss/vidc.c
+++ b/sound/oss/vidc.c
@@ -28,7 +28,6 @@
 #include <asm/io.h>
 #include <asm/hardware/iomd.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 
 #include "sound_config.h"
 #include "vidc.h"
diff --git a/sound/oss/waveartist.c b/sound/oss/waveartist.c
index 52468742d9f2..24c430f721d4 100644
--- a/sound/oss/waveartist.c
+++ b/sound/oss/waveartist.c
@@ -42,7 +42,6 @@
 #include <linux/spinlock.h>
 #include <linux/bitops.h>
 
-#include <asm/system.h>
 
 #include "sound_config.h"
 #include "waveartist.h"
diff --git a/sound/pci/asihpi/hpi_internal.h b/sound/pci/asihpi/hpi_internal.h
index 4cc315daeda0..8c63200cf339 100644
--- a/sound/pci/asihpi/hpi_internal.h
+++ b/sound/pci/asihpi/hpi_internal.h
@@ -42,7 +42,7 @@ On error *pLockedMemHandle marked invalid, non-zero returned.
 If this function succeeds, then HpiOs_LockedMem_GetVirtAddr() and
 HpiOs_LockedMem_GetPyhsAddr() will always succed on the returned handle.
 */
-u16 hpios_locked_mem_alloc(struct consistent_dma_area *p_locked_mem_handle,
+int hpios_locked_mem_alloc(struct consistent_dma_area *p_locked_mem_handle,
 							   /**< memory handle */
 	u32 size, /**< Size in bytes to allocate */
 	struct pci_dev *p_os_reference
diff --git a/sound/pci/asihpi/hpios.c b/sound/pci/asihpi/hpios.c
index 2d7d1c2e1d0d..87f4385fe8c7 100644
--- a/sound/pci/asihpi/hpios.c
+++ b/sound/pci/asihpi/hpios.c
@@ -43,7 +43,7 @@ void hpios_delay_micro_seconds(u32 num_micro_sec)
 
 On error, return -ENOMEM, and *pMemArea.size = 0
 */
-u16 hpios_locked_mem_alloc(struct consistent_dma_area *p_mem_area, u32 size,
+int hpios_locked_mem_alloc(struct consistent_dma_area *p_mem_area, u32 size,
 	struct pci_dev *pdev)
 {
 	/*?? any benefit in using managed dmam_alloc_coherent? */
diff --git a/sound/pci/asihpi/hpios.h b/sound/pci/asihpi/hpios.h
index c5cef113c209..d3fbd0d76c37 100644
--- a/sound/pci/asihpi/hpios.h
+++ b/sound/pci/asihpi/hpios.h
@@ -30,7 +30,6 @@ HPI Operating System Specific macros for Linux Kernel driver
 #define HPI_BUILD_KERNEL_MODE
 
 #include <linux/io.h>
-#include <asm/system.h>
 #include <linux/ioctl.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/sound/pci/aw2/aw2-saa7146.c b/sound/pci/aw2/aw2-saa7146.c
index 8afd8b5d1ac7..4439636971eb 100644
--- a/sound/pci/aw2/aw2-saa7146.c
+++ b/sound/pci/aw2/aw2-saa7146.c
@@ -27,7 +27,6 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <sound/core.h>
 #include <sound/initval.h>
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 8ea2fd654327..9917e55d6f11 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2717,9 +2717,6 @@ static int alc_auto_fill_adc_caps(struct hda_codec *codec)
 	int max_nums = ARRAY_SIZE(spec->private_adc_nids);
 	int i, nums = 0;
 
-	if (spec->shared_mic_hp)
-		max_nums = 1; /* no multi streams with the shared HP/mic */
-
 	nid = codec->start_nid;
 	for (i = 0; i < codec->num_nodes; i++, nid++) {
 		hda_nid_t src;
@@ -4076,6 +4073,7 @@ static void alc_remove_invalid_adc_nids(struct hda_codec *codec)
 	if (spec->dyn_adc_switch)
 		return;
 
+ again:
 	nums = 0;
 	for (n = 0; n < spec->num_adc_nids; n++) {
 		hda_nid_t cap = spec->private_capsrc_nids[n];
@@ -4096,6 +4094,11 @@ static void alc_remove_invalid_adc_nids(struct hda_codec *codec)
 	if (!nums) {
 		/* check whether ADC-switch is possible */
 		if (!alc_check_dyn_adc_switch(codec)) {
+			if (spec->shared_mic_hp) {
+				spec->shared_mic_hp = 0;
+				spec->private_imux[0].num_items = 1;
+				goto again;
+			}
 			printk(KERN_WARNING "hda_codec: %s: no valid ADC found;"
 			       " using fallback 0x%x\n",
 			       codec->chip_name, spec->private_adc_nids[0]);
@@ -4113,7 +4116,7 @@ static void alc_remove_invalid_adc_nids(struct hda_codec *codec)
 
 	if (spec->auto_mic)
 		alc_auto_mic_check_imux(codec); /* check auto-mic setups */
-	else if (spec->input_mux->num_items == 1)
+	else if (spec->input_mux->num_items == 1 || spec->shared_mic_hp)
 		spec->num_adc_nids = 1; /* reduce to a single ADC */
 }
 
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index fe7fbaeb7146..7c49642af052 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -3629,7 +3629,7 @@ static int wm8994_codec_probe(struct snd_soc_codec *codec)
 		case 2:
 		case 3:
 			wm8994->hubs.dcs_codes_l = -9;
-			wm8994->hubs.dcs_codes_r = -5;
+			wm8994->hubs.dcs_codes_r = -7;
 			break;
 		default:
 			break;
diff --git a/sound/soc/fsl/mpc8610_hpcd.c b/sound/soc/fsl/mpc8610_hpcd.c
index afbabf427f27..3fea5a15ffe8 100644
--- a/sound/soc/fsl/mpc8610_hpcd.c
+++ b/sound/soc/fsl/mpc8610_hpcd.c
@@ -58,9 +58,9 @@ static int mpc8610_hpcd_machine_probe(struct snd_soc_card *card)
 {
 	struct mpc8610_hpcd_data *machine_data =
 		container_of(card, struct mpc8610_hpcd_data, card);
-	struct ccsr_guts_86xx __iomem *guts;
+	struct ccsr_guts __iomem *guts;
 
-	guts = ioremap(guts_phys, sizeof(struct ccsr_guts_86xx));
+	guts = ioremap(guts_phys, sizeof(struct ccsr_guts));
 	if (!guts) {
 		dev_err(card->dev, "could not map global utilities\n");
 		return -ENOMEM;
@@ -142,9 +142,9 @@ static int mpc8610_hpcd_machine_remove(struct snd_soc_card *card)
 {
 	struct mpc8610_hpcd_data *machine_data =
 		container_of(card, struct mpc8610_hpcd_data, card);
-	struct ccsr_guts_86xx __iomem *guts;
+	struct ccsr_guts __iomem *guts;
 
-	guts = ioremap(guts_phys, sizeof(struct ccsr_guts_86xx));
+	guts = ioremap(guts_phys, sizeof(struct ccsr_guts));
 	if (!guts) {
 		dev_err(card->dev, "could not map global utilities\n");
 		return -ENOMEM;
diff --git a/sound/soc/fsl/p1022_ds.c b/sound/soc/fsl/p1022_ds.c
index 46623405a2ce..982a1c944983 100644
--- a/sound/soc/fsl/p1022_ds.c
+++ b/sound/soc/fsl/p1022_ds.c
@@ -46,7 +46,7 @@
  * ch: The channel on the DMA controller (0, 1, 2, or 3)
  * device: The device to set as the target (CCSR_GUTS_DMUXCR_xxx)
  */
-static inline void guts_set_dmuxcr(struct ccsr_guts_85xx __iomem *guts,
+static inline void guts_set_dmuxcr(struct ccsr_guts __iomem *guts,
 	unsigned int co, unsigned int ch, unsigned int device)
 {
 	unsigned int shift = 16 + (8 * (1 - co) + 2 * (3 - ch));
@@ -90,9 +90,9 @@ static int p1022_ds_machine_probe(struct snd_soc_card *card)
 {
 	struct machine_data *mdata =
 		container_of(card, struct machine_data, card);
-	struct ccsr_guts_85xx __iomem *guts;
+	struct ccsr_guts __iomem *guts;
 
-	guts = ioremap(guts_phys, sizeof(struct ccsr_guts_85xx));
+	guts = ioremap(guts_phys, sizeof(struct ccsr_guts));
 	if (!guts) {
 		dev_err(card->dev, "could not map global utilities\n");
 		return -ENOMEM;
@@ -164,9 +164,9 @@ static int p1022_ds_machine_remove(struct snd_soc_card *card)
 {
 	struct machine_data *mdata =
 		container_of(card, struct machine_data, card);
-	struct ccsr_guts_85xx __iomem *guts;
+	struct ccsr_guts __iomem *guts;
 
-	guts = ioremap(guts_phys, sizeof(struct ccsr_guts_85xx));
+	guts = ioremap(guts_phys, sizeof(struct ccsr_guts));
 	if (!guts) {
 		dev_err(card->dev, "could not map global utilities\n");
 		return -ENOMEM;
diff --git a/sound/soc/imx/imx-audmux.c b/sound/soc/imx/imx-audmux.c
index 601df809a26a..1765a197acb0 100644
--- a/sound/soc/imx/imx-audmux.c
+++ b/sound/soc/imx/imx-audmux.c
@@ -40,12 +40,6 @@ static void __iomem *audmux_base;
 #ifdef CONFIG_DEBUG_FS
 static struct dentry *audmux_debugfs_root;
 
-static int audmux_open_file(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 /* There is an annoying discontinuity in the SSI numbering with regard
  * to the Linux number of the devices */
 static const char *audmux_port_string(int port)
@@ -142,7 +136,7 @@ static ssize_t audmux_read_file(struct file *file, char __user *user_buf,
 }
 
 static const struct file_operations audmux_debugfs_fops = {
-	.open = audmux_open_file,
+	.open = simple_open,
 	.read = audmux_read_file,
 	.llseek = default_llseek,
 };
diff --git a/sound/soc/imx/imx-pcm-dma-mx2.c b/sound/soc/imx/imx-pcm-dma-mx2.c
index e43c8fa2788b..6b818de2fc03 100644
--- a/sound/soc/imx/imx-pcm-dma-mx2.c
+++ b/sound/soc/imx/imx-pcm-dma-mx2.c
@@ -21,6 +21,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/dmaengine.h>
+#include <linux/types.h>
 
 #include <sound/core.h>
 #include <sound/initval.h>
@@ -58,6 +59,8 @@ static int snd_imx_pcm_hw_params(struct snd_pcm_substream *substream,
 	if (ret)
 		return ret;
 
+	slave_config.device_fc = false;
+
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		slave_config.dst_addr = dma_params->dma_addr;
 		slave_config.dst_maxburst = dma_params->burstsize;
diff --git a/sound/soc/mxs/mxs-pcm.c b/sound/soc/mxs/mxs-pcm.c
index 6ca1f46d84a4..e373fbbc97a0 100644
--- a/sound/soc/mxs/mxs-pcm.c
+++ b/sound/soc/mxs/mxs-pcm.c
@@ -28,6 +28,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/dmaengine.h>
+#include <linux/fsl/mxs-dma.h>
 
 #include <sound/core.h>
 #include <sound/initval.h>
@@ -36,7 +37,6 @@
 #include <sound/soc.h>
 #include <sound/dmaengine_pcm.h>
 
-#include <mach/dma.h>
 #include "mxs-pcm.h"
 
 struct mxs_pcm_dma_data {
diff --git a/sound/soc/mxs/mxs-saif.c b/sound/soc/mxs/mxs-saif.c
index 12be05b16880..53f4fd8feced 100644
--- a/sound/soc/mxs/mxs-saif.c
+++ b/sound/soc/mxs/mxs-saif.c
@@ -24,12 +24,12 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/time.h>
+#include <linux/fsl/mxs-dma.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
 #include <sound/saif.h>
-#include <mach/dma.h>
 #include <asm/mach-types.h>
 #include <mach/hardware.h>
 #include <mach/mxs.h>
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 4800d5fe568d..06ea2744cc88 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 
diff --git a/sound/soc/sh/siu_pcm.c b/sound/soc/sh/siu_pcm.c
index 0193e595d415..5cfcc655e95f 100644
--- a/sound/soc/sh/siu_pcm.c
+++ b/sound/soc/sh/siu_pcm.c
@@ -130,7 +130,7 @@ static int siu_pcm_wr_set(struct siu_port *port_info,
 	sg_dma_len(&sg) = size;
 	sg_dma_address(&sg) = buff;
 
-	desc = siu_stream->chan->device->device_prep_slave_sg(siu_stream->chan,
+	desc = dmaengine_prep_slave_sg(siu_stream->chan,
 		&sg, 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		dev_err(dev, "Failed to allocate a dma descriptor\n");
@@ -180,7 +180,7 @@ static int siu_pcm_rd_set(struct siu_port *port_info,
 	sg_dma_len(&sg) = size;
 	sg_dma_address(&sg) = buff;
 
-	desc = siu_stream->chan->device->device_prep_slave_sg(siu_stream->chan,
+	desc = dmaengine_prep_slave_sg(siu_stream->chan,
 		&sg, 1, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		dev_err(dev, "Failed to allocate dma descriptor\n");
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index a4deebc0801a..e19c24ade414 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -201,12 +201,6 @@ static ssize_t pmdown_time_set(struct device *dev,
 static DEVICE_ATTR(pmdown_time, 0644, pmdown_time_show, pmdown_time_set);
 
 #ifdef CONFIG_DEBUG_FS
-static int codec_reg_open_file(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t codec_reg_read_file(struct file *file, char __user *user_buf,
 				   size_t count, loff_t *ppos)
 {
@@ -264,7 +258,7 @@ static ssize_t codec_reg_write_file(struct file *file,
 }
 
 static const struct file_operations codec_reg_fops = {
-	.open = codec_reg_open_file,
+	.open = simple_open,
 	.read = codec_reg_read_file,
 	.write = codec_reg_write_file,
 	.llseek = default_llseek,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 6241490fff30..5cbd2d7623b8 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1544,12 +1544,6 @@ static int dapm_power_widgets(struct snd_soc_dapm_context *dapm, int event)
 }
 
 #ifdef CONFIG_DEBUG_FS
-static int dapm_widget_power_open_file(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t dapm_widget_power_read_file(struct file *file,
 					   char __user *user_buf,
 					   size_t count, loff_t *ppos)
@@ -1613,17 +1607,11 @@ static ssize_t dapm_widget_power_read_file(struct file *file,
 }
 
 static const struct file_operations dapm_widget_power_fops = {
-	.open = dapm_widget_power_open_file,
+	.open = simple_open,
 	.read = dapm_widget_power_read_file,
 	.llseek = default_llseek,
 };
 
-static int dapm_bias_open_file(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t dapm_bias_read_file(struct file *file, char __user *user_buf,
 				   size_t count, loff_t *ppos)
 {
@@ -1654,7 +1642,7 @@ static ssize_t dapm_bias_read_file(struct file *file, char __user *user_buf,
 }
 
 static const struct file_operations dapm_bias_fops = {
-	.open = dapm_bias_open_file,
+	.open = simple_open,
 	.read = dapm_bias_read_file,
 	.llseek = default_llseek,
 };
diff --git a/sound/soc/soc-dmaengine-pcm.c b/sound/soc/soc-dmaengine-pcm.c
index 4420b7030c83..475695234b3d 100644
--- a/sound/soc/soc-dmaengine-pcm.c
+++ b/sound/soc/soc-dmaengine-pcm.c
@@ -143,7 +143,7 @@ static int dmaengine_pcm_prepare_and_submit(struct snd_pcm_substream *substream)
 	direction = snd_pcm_substream_to_dma_direction(substream);
 
 	prtd->pos = 0;
-	desc = chan->device->device_prep_dma_cyclic(chan,
+	desc = dmaengine_prep_dma_cyclic(chan,
 		substream->runtime->dma_addr,
 		snd_pcm_lib_buffer_bytes(substream),
 		snd_pcm_lib_period_bytes(substream), direction);
diff --git a/sound/soc/txx9/txx9aclc.c b/sound/soc/txx9/txx9aclc.c
index 21554611557c..b609d2c64c55 100644
--- a/sound/soc/txx9/txx9aclc.c
+++ b/sound/soc/txx9/txx9aclc.c
@@ -132,7 +132,7 @@ txx9aclc_dma_submit(struct txx9aclc_dmadata *dmadata, dma_addr_t buf_dma_addr)
 	sg_set_page(&sg, pfn_to_page(PFN_DOWN(buf_dma_addr)),
 		    dmadata->frag_bytes, buf_dma_addr & (PAGE_SIZE - 1));
 	sg_dma_address(&sg) = buf_dma_addr;
-	desc = chan->device->device_prep_slave_sg(chan, &sg, 1,
+	desc = dmaengine_prep_slave_sg(chan, &sg, 1,
 		dmadata->substream->stream == SNDRV_PCM_STREAM_PLAYBACK ?
 		DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
 		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 87feeee8b90c..2d89f02719b5 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -48,6 +48,9 @@ OPTIONS
 	Only consider these symbols. CSV that understands
 	file://filename entries.
 
+--symbol-filter=::
+	Only show symbols that match (partially) with this filter.
+
 -U::
 --hide-unresolved::
         Only display entries resolved to a symbol.
@@ -110,6 +113,8 @@ OPTIONS
 	requires a tty, if one is not present, as when piping to other
 	commands, the stdio interface is used.
 
+--gtk:: Use the GTK2 interface.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 74fd7f89208a..820371f10d1b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -182,7 +182,7 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)/util -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
@@ -234,6 +234,25 @@ endif
 
 export PERL_PATH
 
+FLEX = $(CROSS_COMPILE)flex
+BISON= $(CROSS_COMPILE)bison
+
+event-parser:
+	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d -o $(OUTPUT)util/parse-events-bison.c
+	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
+
+$(OUTPUT)util/parse-events-flex.c: event-parser
+$(OUTPUT)util/parse-events-bison.c: event-parser
+
+pmu-parser:
+	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c
+	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
+
+$(OUTPUT)util/pmu-flex.c: pmu-parser
+$(OUTPUT)util/pmu-bison.c: pmu-parser
+
+$(OUTPUT)util/parse-events.o: event-parser pmu-parser
+
 LIB_FILE=$(OUTPUT)libperf.a
 
 LIB_H += ../../include/linux/perf_event.h
@@ -249,7 +268,7 @@ LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
-LIB_H += util/include/linux/module.h
+LIB_H += util/include/linux/export.h
 LIB_H += util/include/linux/poison.h
 LIB_H += util/include/linux/prefetch.h
 LIB_H += util/include/linux/rbtree.h
@@ -276,6 +295,7 @@ LIB_H += util/build-id.h
 LIB_H += util/debug.h
 LIB_H += util/debugfs.h
 LIB_H += util/sysfs.h
+LIB_H += util/pmu.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
 LIB_H += util/evlist.h
@@ -323,6 +343,7 @@ LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
 LIB_OBJS += $(OUTPUT)util/debugfs.o
 LIB_OBJS += $(OUTPUT)util/sysfs.o
+LIB_OBJS += $(OUTPUT)util/pmu.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
 LIB_OBJS += $(OUTPUT)util/evlist.o
@@ -359,6 +380,10 @@ LIB_OBJS += $(OUTPUT)util/session.o
 LIB_OBJS += $(OUTPUT)util/thread.o
 LIB_OBJS += $(OUTPUT)util/thread_map.o
 LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
+LIB_OBJS += $(OUTPUT)util/parse-events-flex.o
+LIB_OBJS += $(OUTPUT)util/parse-events-bison.o
+LIB_OBJS += $(OUTPUT)util/pmu-flex.o
+LIB_OBJS += $(OUTPUT)util/pmu-bison.o
 LIB_OBJS += $(OUTPUT)util/trace-event-read.o
 LIB_OBJS += $(OUTPUT)util/trace-event-info.o
 LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
@@ -501,6 +526,20 @@ else
 	endif
 endif
 
+ifdef NO_GTK2
+	BASIC_CFLAGS += -DNO_GTK2
+else
+	FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0)
+	ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2)),y)
+		msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
+		BASIC_CFLAGS += -DNO_GTK2_SUPPORT
+	else
+		BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0)
+		EXTLIBS += $(shell pkg-config --libs gtk+-2.0)
+		LIB_OBJS += $(OUTPUT)util/gtk/browser.o
+	endif
+endif
+
 ifdef NO_LIBPERL
 	BASIC_CFLAGS += -DNO_LIBPERL
 else
@@ -647,6 +686,8 @@ ifndef V
 	QUIET_LINK     = @echo '   ' LINK $@;
 	QUIET_MKDIR    = @echo '   ' MKDIR $@;
 	QUIET_GEN      = @echo '   ' GEN $@;
+	QUIET_FLEX     = @echo '   ' FLEX $@;
+	QUIET_BISON    = @echo '   ' BISON $@;
 endif
 endif
 
@@ -727,12 +768,28 @@ $(OUTPUT)perf.o perf.spec \
 	$(SCRIPTS) \
 	: $(OUTPUT)PERF-VERSION-FILE
 
+.SUFFIXES:
+.SUFFIXES: .o .c .S .s
+
+# These two need to be here so that when O= is not used they take precedence
+# over the general rule for .o
+
+$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Iutil/ -Wno-redundant-decls -Wno-switch-default -Wno-unused-function $<
+
+$(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -Iutil/ -Wno-redundant-decls -Wno-switch-default -Wno-unused-function $<
+
 $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
 $(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
+	$(QUIET_CC)$(CC) -o $@ -S $(ALL_CFLAGS) $<
 $(OUTPUT)%.o: %.S
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.s: %.S
+	$(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
 
 $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
@@ -795,6 +852,8 @@ help:
 	@echo '  html		- make html documentation'
 	@echo '  info		- make GNU info documentation (access with info <foo>)'
 	@echo '  pdf		- make pdf documentation'
+	@echo '  event-parser	- make event parser code'
+	@echo '  pmu-parser	- make pmu format parser code'
 	@echo '  TAGS		- use etags to make tag information for source browsing'
 	@echo '  tags		- use ctags to make tag information for source browsing'
 	@echo '  cscope	- use cscope to make interactive browsing database'
@@ -931,6 +990,7 @@ clean:
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
+	$(RM) $(OUTPUT)util/*-{bison,flex}*
 	$(python-clean)
 
 .PHONY: all install clean strip
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 4f19513d7dda..d29d350fb2b7 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -24,6 +24,11 @@ static char	  diff__default_sort_order[] = "dso,symbol";
 static bool  force;
 static bool show_displacement;
 
+struct perf_diff {
+	struct perf_tool tool;
+	struct perf_session *session;
+};
+
 static int hists__add_entry(struct hists *self,
 			    struct addr_location *al, u64 period)
 {
@@ -32,12 +37,14 @@ static int hists__add_entry(struct hists *self,
 	return -ENOMEM;
 }
 
-static int diff__process_sample_event(struct perf_tool *tool __used,
+static int diff__process_sample_event(struct perf_tool *tool,
 				      union perf_event *event,
 				      struct perf_sample *sample,
 				      struct perf_evsel *evsel __used,
 				      struct machine *machine)
 {
+	struct perf_diff *_diff = container_of(tool, struct perf_diff, tool);
+	struct perf_session *session = _diff->session;
 	struct addr_location al;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) {
@@ -49,24 +56,26 @@ static int diff__process_sample_event(struct perf_tool *tool __used,
 	if (al.filtered || al.sym == NULL)
 		return 0;
 
-	if (hists__add_entry(&evsel->hists, &al, sample->period)) {
+	if (hists__add_entry(&session->hists, &al, sample->period)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
 
-	evsel->hists.stats.total_period += sample->period;
+	session->hists.stats.total_period += sample->period;
 	return 0;
 }
 
-static struct perf_tool perf_diff = {
-	.sample	= diff__process_sample_event,
-	.mmap	= perf_event__process_mmap,
-	.comm	= perf_event__process_comm,
-	.exit	= perf_event__process_task,
-	.fork	= perf_event__process_task,
-	.lost	= perf_event__process_lost,
-	.ordered_samples = true,
-	.ordering_requires_timestamps = true,
+static struct perf_diff diff = {
+	.tool = {
+		.sample	= diff__process_sample_event,
+		.mmap	= perf_event__process_mmap,
+		.comm	= perf_event__process_comm,
+		.exit	= perf_event__process_task,
+		.fork	= perf_event__process_task,
+		.lost	= perf_event__process_lost,
+		.ordered_samples = true,
+		.ordering_requires_timestamps = true,
+	},
 };
 
 static void perf_session__insert_hist_entry_by_name(struct rb_root *root,
@@ -107,12 +116,6 @@ static void hists__resort_entries(struct hists *self)
 	self->entries = tmp;
 }
 
-static void hists__set_positions(struct hists *self)
-{
-	hists__output_resort(self);
-	hists__resort_entries(self);
-}
-
 static struct hist_entry *hists__find_entry(struct hists *self,
 					    struct hist_entry *he)
 {
@@ -146,30 +149,37 @@ static void hists__match(struct hists *older, struct hists *newer)
 static int __cmd_diff(void)
 {
 	int ret, i;
+#define older (session[0])
+#define newer (session[1])
 	struct perf_session *session[2];
 
-	session[0] = perf_session__new(input_old, O_RDONLY, force, false, &perf_diff);
-	session[1] = perf_session__new(input_new, O_RDONLY, force, false, &perf_diff);
+	older = perf_session__new(input_old, O_RDONLY, force, false,
+				  &diff.tool);
+	newer = perf_session__new(input_new, O_RDONLY, force, false,
+				  &diff.tool);
 	if (session[0] == NULL || session[1] == NULL)
 		return -ENOMEM;
 
 	for (i = 0; i < 2; ++i) {
-		ret = perf_session__process_events(session[i], &perf_diff);
+		diff.session = session[i];
+		ret = perf_session__process_events(session[i], &diff.tool);
 		if (ret)
 			goto out_delete;
+		hists__output_resort(&session[i]->hists);
 	}
 
-	hists__output_resort(&session[1]->hists);
 	if (show_displacement)
-		hists__set_positions(&session[0]->hists);
+		hists__resort_entries(&older->hists);
 
-	hists__match(&session[0]->hists, &session[1]->hists);
-	hists__fprintf(&session[1]->hists, &session[0]->hists,
+	hists__match(&older->hists, &newer->hists);
+	hists__fprintf(&newer->hists, &older->hists,
 		       show_displacement, true, 0, 0, stdout);
 out_delete:
 	for (i = 0; i < 2; ++i)
 		perf_session__delete(session[i]);
 	return ret;
+#undef older
+#undef newer
 }
 
 static const char * const diff_usage[] = {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8e91c6eba18a..2e317438980b 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -40,7 +40,7 @@ struct perf_report {
 	struct perf_tool	tool;
 	struct perf_session	*session;
 	char const		*input_name;
-	bool			force, use_tui, use_stdio;
+	bool			force, use_tui, use_gtk, use_stdio;
 	bool			hide_unresolved;
 	bool			dont_use_callchains;
 	bool			show_full_info;
@@ -50,6 +50,7 @@ struct perf_report {
 	const char		*pretty_printing_style;
 	symbol_filter_t		annotate_init;
 	const char		*cpu_list;
+	const char		*symbol_filter_str;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
@@ -400,6 +401,9 @@ static int __cmd_report(struct perf_report *rep)
 	list_for_each_entry(pos, &session->evlist->entries, node) {
 		struct hists *hists = &pos->hists;
 
+		if (pos->idx == 0)
+			hists->symbol_filter_str = rep->symbol_filter_str;
+
 		hists__collapse_resort(hists);
 		hists__output_resort(hists);
 		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
@@ -411,8 +415,13 @@ static int __cmd_report(struct perf_report *rep)
 	}
 
 	if (use_browser > 0) {
-		perf_evlist__tui_browse_hists(session->evlist, help,
-					      NULL, NULL, 0);
+		if (use_browser == 1) {
+			perf_evlist__tui_browse_hists(session->evlist, help,
+						      NULL, NULL, 0);
+		} else if (use_browser == 2) {
+			perf_evlist__gtk_browse_hists(session->evlist, help,
+						      NULL, NULL, 0);
+		}
 	} else
 		perf_evlist__tty_browse_hists(session->evlist, rep, help);
 
@@ -569,6 +578,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	OPT_STRING(0, "pretty", &report.pretty_printing_style, "key",
 		   "pretty printing style key: normal raw"),
 	OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
 	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
@@ -591,6 +601,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		   "only consider symbols in these comms"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_STRING(0, "symbol-filter", &report.symbol_filter_str, "filter",
+		   "only show symbols that (partially) match with this filter"),
 	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
 		   "width[,width...]",
 		   "don't try to adjust column width, use these fixed values"),
@@ -624,6 +636,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		use_browser = 0;
 	else if (report.use_tui)
 		use_browser = 1;
+	else if (report.use_gtk)
+		use_browser = 2;
 
 	if (report.inverted_callchain)
 		callchain_param.order = ORDER_CALLER;
@@ -660,7 +674,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	}
 
 	if (strcmp(report.input_name, "-") != 0) {
-		setup_browser(true);
+		if (report.use_gtk)
+			perf_gtk_setup_browser(argc, argv, true);
+		else
+			setup_browser(true);
 	} else {
 		use_browser = 0;
 	}
@@ -709,11 +726,16 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	} else
 		symbol_conf.exclude_other = false;
 
-	/*
-	 * Any (unrecognized) arguments left?
-	 */
-	if (argc)
-		usage_with_options(report_usage, options);
+	if (argc) {
+		/*
+		 * Special case: if there's an argument left then assume that
+		 * it's a symbol filter:
+		 */
+		if (argc > 1)
+			usage_with_options(report_usage, options);
+
+		report.symbol_filter_str = argv[0];
+	}
 
 	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ea40e4e8b227..c941bb640f49 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,7 +296,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 	if (system_wide)
 		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
 						group, group_fd);
-	if (!target_pid && !target_tid) {
+	if (!target_pid && !target_tid && (!group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 3e087ce8daa6..1c5b9801ac61 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -13,6 +13,7 @@
 #include "util/parse-events.h"
 #include "util/symbol.h"
 #include "util/thread_map.h"
+#include "util/pmu.h"
 #include "../../include/linux/hw_breakpoint.h"
 
 #include <sys/mman.h>
@@ -650,7 +651,7 @@ static int test__checkevent_raw(struct perf_evlist *evlist)
 
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
-	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config", 0x1a == evsel->attr.config);
 	return 0;
 }
 
@@ -677,6 +678,24 @@ static int test__checkevent_symbolic_name(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong period",
+			100000 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong config1",
+			0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",
+			1 == evsel->attr.config2);
+	return 0;
+}
+
 static int test__checkevent_symbolic_alias(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -858,6 +877,115 @@ static int test__checkevent_genhw_modifier(struct perf_evlist *evlist)
 	return test__checkevent_genhw(evlist);
 }
 
+static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint(evlist);
+}
+
+static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_x(evlist);
+}
+
+static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_r(evlist);
+}
+
+static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_w(evlist);
+}
+
+static int test__checkevent_pmu(struct perf_evlist *evlist)
+{
+
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",    10 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1",    1 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",    3 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong period",  1000 == evsel->attr.sample_period);
+
+	return 0;
+}
+
+static int test__checkevent_list(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+	/* r1 */
+	evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2", 0 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	/* syscalls:sys_enter_open:k */
+	evsel = list_entry(evsel->node.next, struct perf_evsel, node);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong sample_type",
+		(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU) ==
+		evsel->attr.sample_type);
+	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	/* 1:1:hp */
+	evsel = list_entry(evsel->node.next, struct perf_evsel, node);
+	TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return 0;
+}
+
 static struct test__event_st {
 	const char *name;
 	__u32 type;
@@ -872,7 +1000,7 @@ static struct test__event_st {
 		.check = test__checkevent_tracepoint_multi,
 	},
 	{
-		.name  = "r1",
+		.name  = "r1a",
 		.check = test__checkevent_raw,
 	},
 	{
@@ -884,6 +1012,10 @@ static struct test__event_st {
 		.check = test__checkevent_symbolic_name,
 	},
 	{
+		.name  = "cycles/period=100000,config2/",
+		.check = test__checkevent_symbolic_name_config,
+	},
+	{
 		.name  = "faults",
 		.check = test__checkevent_symbolic_alias,
 	},
@@ -916,7 +1048,7 @@ static struct test__event_st {
 		.check = test__checkevent_tracepoint_multi_modifier,
 	},
 	{
-		.name  = "r1:kp",
+		.name  = "r1a:kp",
 		.check = test__checkevent_raw_modifier,
 	},
 	{
@@ -935,6 +1067,30 @@ static struct test__event_st {
 		.name  = "L1-dcache-load-miss:kp",
 		.check = test__checkevent_genhw_modifier,
 	},
+	{
+		.name  = "mem:0:u",
+		.check = test__checkevent_breakpoint_modifier,
+	},
+	{
+		.name  = "mem:0:x:k",
+		.check = test__checkevent_breakpoint_x_modifier,
+	},
+	{
+		.name  = "mem:0:r:hp",
+		.check = test__checkevent_breakpoint_r_modifier,
+	},
+	{
+		.name  = "mem:0:w:up",
+		.check = test__checkevent_breakpoint_w_modifier,
+	},
+	{
+		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
+		.check = test__checkevent_pmu,
+	},
+	{
+		.name  = "r1,syscalls:sys_enter_open:k,1:1:hp",
+		.check = test__checkevent_list,
+	},
 };
 
 #define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st))
@@ -960,10 +1116,9 @@ static int test__parse_events(void)
 		}
 
 		ret = e->check(evlist);
+		perf_evlist__delete(evlist);
 		if (ret)
 			break;
-
-		perf_evlist__delete(evlist);
 	}
 
 	return ret;
@@ -1462,6 +1617,11 @@ static int test__rdpmc(void)
 
 #endif
 
+static int test__perf_pmu(void)
+{
+	return perf_pmu__test();
+}
+
 static struct test {
 	const char *desc;
 	int (*func)(void);
@@ -1497,6 +1657,10 @@ static struct test {
 		.func = test__PERF_RECORD,
 	},
 	{
+		.desc = "Test perf pmu format parsing",
+		.func = test__perf_pmu,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 6170fd2531b5..d9084e03ce56 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -65,6 +65,21 @@ int main(void)
 endef
 endif
 
+ifndef NO_GTK2
+define SOURCE_GTK2
+#pragma GCC diagnostic ignored \"-Wstrict-prototypes\"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error \"-Wstrict-prototypes\"
+
+int main(int argc, char *argv[])
+{
+        gtk_init(&argc, &argv);
+
+        return 0;
+}
+endef
+endif
+
 ifndef NO_LIBPERL
 define SOURCE_PERL_EMBED
 #include <EXTERN.h>
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e5a462f1d07c..199f69ec656f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -28,8 +28,8 @@ int symbol__annotate_init(struct map *map __used, struct symbol *sym)
 int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	size_t sizeof_sym_hist = (sizeof(struct sym_hist) +
-				  (sym->end - sym->start) * sizeof(u64));
+	const size_t size = sym->end - sym->start + 1;
+	size_t sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
 
 	notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist);
 	if (notes->src == NULL)
@@ -64,7 +64,7 @@ int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-	if (addr >= sym->end)
+	if (addr > sym->end)
 		return 0;
 
 	offset = addr - sym->start;
@@ -408,7 +408,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 	if (!notes->src->lines)
 		return -1;
 
-	start = map->unmap_ip(map, sym->start);
+	start = map__rip_2objdump(map, sym->start);
 
 	for (i = 0; i < len; i++) {
 		char *path = NULL;
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index fc5e5a09d5b9..8dd224df3e54 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -45,6 +45,18 @@ void setup_browser(bool fallback_to_pager);
 void exit_browser(bool wait_for_ok);
 #endif
 
+#ifdef NO_GTK2_SUPPORT
+static inline void perf_gtk_setup_browser(int argc __used, const char *argv[] __used, bool fallback_to_pager)
+{
+	if (fallback_to_pager)
+		setup_pager();
+}
+static inline void perf_gtk_exit_browser(bool wait_for_ok __used) {}
+#else
+void perf_gtk_setup_browser(int argc, const char *argv[], bool fallback_to_pager);
+void perf_gtk_exit_browser(bool wait_for_ok);
+#endif
+
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 159263d17c2d..1986d8051bd1 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -51,13 +51,15 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
 void perf_evlist__config_attrs(struct perf_evlist *evlist,
 			       struct perf_record_opts *opts)
 {
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel, *first;
 
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(evsel, &evlist->entries, node) {
-		perf_evsel__config(evsel, opts);
+		perf_evsel__config(evsel, opts, first);
 
 		if (evlist->nr_entries > 1)
 			evsel->attr.sample_type |= PERF_SAMPLE_ID;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f421f7cbc0d3..8c13dbcb84b9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -34,7 +34,7 @@ int __perf_evsel__sample_size(u64 sample_type)
 	return size;
 }
 
-static void hists__init(struct hists *hists)
+void hists__init(struct hists *hists)
 {
 	memset(hists, 0, sizeof(*hists));
 	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
@@ -63,7 +63,8 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
-void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
+			struct perf_evsel *first)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
@@ -134,7 +135,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
 	attr->mmap = track;
 	attr->comm = track;
 
-	if (!opts->target_pid && !opts->target_tid && !opts->system_wide) {
+	if (!opts->target_pid && !opts->target_tid && !opts->system_wide &&
+	    (!opts->group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
@@ -578,6 +580,8 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 			return -EFAULT;
 
 		data->raw_data = (void *) pdata;
+
+		array = (void *)array + data->raw_size + sizeof(u32);
 	}
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 326b8e4d5035..3d6b3e4cb66b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -80,7 +80,8 @@ void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts);
+			struct perf_record_opts *opts,
+			struct perf_evsel *first);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
@@ -169,4 +170,6 @@ static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
 	return __perf_evsel__sample_size(evsel->attr.sample_type);
 }
 
+void hists__init(struct hists *hists);
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/gtk/browser.c b/tools/perf/util/gtk/browser.c
new file mode 100644
index 000000000000..258352a2356c
--- /dev/null
+++ b/tools/perf/util/gtk/browser.c
@@ -0,0 +1,189 @@
+#include "../evlist.h"
+#include "../cache.h"
+#include "../evsel.h"
+#include "../sort.h"
+#include "../hist.h"
+#include "gtk.h"
+
+#include <signal.h>
+
+#define MAX_COLUMNS			32
+
+void perf_gtk_setup_browser(int argc, const char *argv[],
+			    bool fallback_to_pager __used)
+{
+	gtk_init(&argc, (char ***)&argv);
+}
+
+void perf_gtk_exit_browser(bool wait_for_ok __used)
+{
+	gtk_main_quit();
+}
+
+static void perf_gtk_signal(int sig)
+{
+	psignal(sig, "perf");
+	gtk_main_quit();
+}
+
+static void perf_gtk_resize_window(GtkWidget *window)
+{
+	GdkRectangle rect;
+	GdkScreen *screen;
+	int monitor;
+	int height;
+	int width;
+
+	screen = gtk_widget_get_screen(window);
+
+	monitor = gdk_screen_get_monitor_at_window(screen, window->window);
+
+	gdk_screen_get_monitor_geometry(screen, monitor, &rect);
+
+	width	= rect.width * 3 / 4;
+	height	= rect.height * 3 / 4;
+
+	gtk_window_resize(GTK_WINDOW(window), width, height);
+}
+
+static void perf_gtk_show_hists(GtkWidget *window, struct hists *hists)
+{
+	GType col_types[MAX_COLUMNS];
+	GtkCellRenderer *renderer;
+	struct sort_entry *se;
+	GtkListStore *store;
+	struct rb_node *nd;
+	u64 total_period;
+	GtkWidget *view;
+	int col_idx;
+	int nr_cols;
+
+	nr_cols = 0;
+
+	/* The percentage column */
+	col_types[nr_cols++] = G_TYPE_STRING;
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (se->elide)
+			continue;
+
+		col_types[nr_cols++] = G_TYPE_STRING;
+	}
+
+	store = gtk_list_store_newv(nr_cols, col_types);
+
+	view = gtk_tree_view_new();
+
+	renderer = gtk_cell_renderer_text_new();
+
+	col_idx = 0;
+
+	/* The percentage column */
+	gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+						    -1, "Overhead (%)",
+						    renderer, "text",
+						    col_idx++, NULL);
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (se->elide)
+			continue;
+
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, se->se_header,
+							    renderer, "text",
+							    col_idx++, NULL);
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	total_period = hists->stats.total_period;
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		GtkTreeIter iter;
+		double percent;
+		char s[512];
+
+		if (h->filtered)
+			continue;
+
+		gtk_list_store_append(store, &iter);
+
+		col_idx = 0;
+
+		percent = (h->period * 100.0) / total_period;
+
+		snprintf(s, ARRAY_SIZE(s), "%.2f", percent);
+
+		gtk_list_store_set(store, &iter, col_idx++, s, -1);
+
+		list_for_each_entry(se, &hist_entry__sort_list, list) {
+			if (se->elide)
+				continue;
+
+			se->se_snprintf(h, s, ARRAY_SIZE(s),
+					hists__col_len(hists, se->se_width_idx));
+
+			gtk_list_store_set(store, &iter, col_idx++, s, -1);
+		}
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), view);
+}
+
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
+				  const char *help __used,
+				  void (*timer) (void *arg)__used,
+				  void *arg __used, int delay_secs __used)
+{
+	struct perf_evsel *pos;
+	GtkWidget *notebook;
+	GtkWidget *window;
+
+	signal(SIGSEGV, perf_gtk_signal);
+	signal(SIGFPE,  perf_gtk_signal);
+	signal(SIGINT,  perf_gtk_signal);
+	signal(SIGQUIT, perf_gtk_signal);
+	signal(SIGTERM, perf_gtk_signal);
+
+	window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+
+	gtk_window_set_title(GTK_WINDOW(window), "perf report");
+
+	g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
+
+	notebook = gtk_notebook_new();
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		struct hists *hists = &pos->hists;
+		const char *evname = event_name(pos);
+		GtkWidget *scrolled_window;
+		GtkWidget *tab_label;
+
+		scrolled_window = gtk_scrolled_window_new(NULL, NULL);
+
+		gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window),
+							GTK_POLICY_AUTOMATIC,
+							GTK_POLICY_AUTOMATIC);
+
+		perf_gtk_show_hists(scrolled_window, hists);
+
+		tab_label = gtk_label_new(evname);
+
+		gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label);
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), notebook);
+
+	gtk_widget_show_all(window);
+
+	perf_gtk_resize_window(window);
+
+	gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
+
+	gtk_main();
+
+	return 0;
+}
diff --git a/tools/perf/util/gtk/gtk.h b/tools/perf/util/gtk/gtk.h
new file mode 100644
index 000000000000..75177ee04032
--- /dev/null
+++ b/tools/perf/util/gtk/gtk.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_GTK_H_
+#define _PERF_GTK_H_ 1
+
+#pragma GCC diagnostic ignored "-Wstrict-prototypes"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+#endif /* _PERF_GTK_H_ */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fcd9cf3ea63e..4c7c2d73251f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1177,7 +1177,7 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 		goto error;
 
 	msz = sizeof(attr);
-	if (sz < (ssize_t)msz)
+	if (sz < msz)
 		msz = sz;
 
 	for (i = 0 ; i < nre; i++) {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 3dc99a9b71f5..2ec4b60aff6c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -10,11 +10,14 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
 				       struct hist_entry *he);
 static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he);
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he);
 
 enum hist_filter {
 	HIST_FILTER__DSO,
 	HIST_FILTER__THREAD,
 	HIST_FILTER__PARENT,
+	HIST_FILTER__SYMBOL,
 };
 
 struct callchain_param	callchain_param = {
@@ -420,6 +423,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 {
 	hists__filter_entry_by_dso(hists, he);
 	hists__filter_entry_by_thread(hists, he);
+	hists__filter_entry_by_symbol(hists, he);
 }
 
 static void __hists__collapse_resort(struct hists *hists, bool threaded)
@@ -603,7 +607,7 @@ static void init_rem_hits(void)
 	rem_hits.ms.sym = rem_sq_bracket;
 }
 
-static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
+static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 					 u64 total_samples, int depth,
 					 int depth_mask, int left_margin)
 {
@@ -611,21 +615,16 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	struct callchain_node *child;
 	struct callchain_list *chain;
 	int new_depth_mask = depth_mask;
-	u64 new_total;
 	u64 remaining;
 	size_t ret = 0;
 	int i;
 	uint entries_printed = 0;
 
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = self->children_hit;
-	else
-		new_total = total_samples;
-
-	remaining = new_total;
+	remaining = total_samples;
 
-	node = rb_first(&self->rb_root);
+	node = rb_first(root);
 	while (node) {
+		u64 new_total;
 		u64 cumul;
 
 		child = rb_entry(node, struct callchain_node, rb_node);
@@ -653,11 +652,17 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		list_for_each_entry(chain, &child->val, list) {
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
-						      new_total,
+						      total_samples,
 						      cumul,
 						      left_margin);
 		}
-		ret += __callchain__fprintf_graph(fp, child, new_total,
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL)
+			new_total = child->children_hit;
+		else
+			new_total = total_samples;
+
+		ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total,
 						  depth + 1,
 						  new_depth_mask | (1 << depth),
 						  left_margin);
@@ -667,61 +672,75 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	}
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL &&
-		remaining && remaining != new_total) {
+		remaining && remaining != total_samples) {
 
 		if (!rem_sq_bracket)
 			return ret;
 
 		new_depth_mask &= ~(1 << (depth - 1));
-
 		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
-					      new_depth_mask, 0, new_total,
+					      new_depth_mask, 0, total_samples,
 					      remaining, left_margin);
 	}
 
 	return ret;
 }
 
-static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
+static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 				       u64 total_samples, int left_margin)
 {
+	struct callchain_node *cnode;
 	struct callchain_list *chain;
+	u32 entries_printed = 0;
 	bool printed = false;
+	struct rb_node *node;
 	int i = 0;
-	int ret = 0;
-	u32 entries_printed = 0;
-
-	list_for_each_entry(chain, &self->val, list) {
-		if (!i++ && sort__first_dimension == SORT_SYM)
-			continue;
-
-		if (!printed) {
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-			ret += fprintf(fp, "|\n");
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-			ret += fprintf(fp, "---");
-
-			left_margin += 3;
-			printed = true;
-		} else
-			ret += callchain__fprintf_left_margin(fp, left_margin);
+	int ret;
 
-		if (chain->ms.sym)
-			ret += fprintf(fp, " %s\n", chain->ms.sym->name);
-		else
-			ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+	/*
+	 * If have one single callchain root, don't bother printing
+	 * its percentage (100 % in fractal mode and the same percentage
+	 * than the hist in graph mode). This also avoid one level of column.
+	 */
+	node = rb_first(root);
+	if (node && !rb_next(node)) {
+		cnode = rb_entry(node, struct callchain_node, rb_node);
+		list_for_each_entry(chain, &cnode->val, list) {
+			/*
+			 * If we sort by symbol, the first entry is the same than
+			 * the symbol. No need to print it otherwise it appears as
+			 * displayed twice.
+			 */
+			if (!i++ && sort__first_dimension == SORT_SYM)
+				continue;
+			if (!printed) {
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+				ret += fprintf(fp, "|\n");
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+				ret += fprintf(fp, "---");
+				left_margin += 3;
+				printed = true;
+			} else
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+
+			if (chain->ms.sym)
+				ret += fprintf(fp, " %s\n", chain->ms.sym->name);
+			else
+				ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
 
-		if (++entries_printed == callchain_param.print_limit)
-			break;
+			if (++entries_printed == callchain_param.print_limit)
+				break;
+		}
+		root = &cnode->rb_root;
 	}
 
-	ret += __callchain__fprintf_graph(fp, self, total_samples, 1, 1, left_margin);
-
-	return ret;
+	return __callchain__fprintf_graph(fp, root, total_samples,
+					  1, 1, left_margin);
 }
 
-static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
-				      u64 total_samples)
+static size_t __callchain__fprintf_flat(FILE *fp,
+					struct callchain_node *self,
+					u64 total_samples)
 {
 	struct callchain_list *chain;
 	size_t ret = 0;
@@ -729,7 +748,7 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	if (!self)
 		return 0;
 
-	ret += callchain__fprintf_flat(fp, self->parent, total_samples);
+	ret += __callchain__fprintf_flat(fp, self->parent, total_samples);
 
 
 	list_for_each_entry(chain, &self->val, list) {
@@ -745,44 +764,58 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	return ret;
 }
 
-static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
-					    u64 total_samples, int left_margin,
-					    FILE *fp)
+static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *self,
+				      u64 total_samples)
 {
-	struct rb_node *rb_node;
-	struct callchain_node *chain;
 	size_t ret = 0;
 	u32 entries_printed = 0;
+	struct rb_node *rb_node;
+	struct callchain_node *chain;
 
-	rb_node = rb_first(&he->sorted_chain);
+	rb_node = rb_first(self);
 	while (rb_node) {
 		double percent;
 
 		chain = rb_entry(rb_node, struct callchain_node, rb_node);
 		percent = chain->hit * 100.0 / total_samples;
-		switch (callchain_param.mode) {
-		case CHAIN_FLAT:
-			ret += percent_color_fprintf(fp, "           %6.2f%%\n",
-						     percent);
-			ret += callchain__fprintf_flat(fp, chain, total_samples);
-			break;
-		case CHAIN_GRAPH_ABS: /* Falldown */
-		case CHAIN_GRAPH_REL:
-			ret += callchain__fprintf_graph(fp, chain, total_samples,
-							left_margin);
-		case CHAIN_NONE:
-		default:
-			break;
-		}
+
+		ret = percent_color_fprintf(fp, "           %6.2f%%\n", percent);
+		ret += __callchain__fprintf_flat(fp, chain, total_samples);
 		ret += fprintf(fp, "\n");
 		if (++entries_printed == callchain_param.print_limit)
 			break;
+
 		rb_node = rb_next(rb_node);
 	}
 
 	return ret;
 }
 
+static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
+					    u64 total_samples, int left_margin,
+					    FILE *fp)
+{
+	switch (callchain_param.mode) {
+	case CHAIN_GRAPH_REL:
+		return callchain__fprintf_graph(fp, &he->sorted_chain, he->period,
+						left_margin);
+		break;
+	case CHAIN_GRAPH_ABS:
+		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+						left_margin);
+		break;
+	case CHAIN_FLAT:
+		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
+		break;
+	case CHAIN_NONE:
+		break;
+	default:
+		pr_err("Bad callchain mode\n");
+	}
+
+	return 0;
+}
+
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
 {
 	struct rb_node *next = rb_first(&hists->entries);
@@ -887,9 +920,9 @@ static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s,
 		diff = new_percent - old_percent;
 
 		if (fabs(diff) >= 0.01)
-			ret += scnprintf(bf, sizeof(bf), "%+4.2F%%", diff);
+			scnprintf(bf, sizeof(bf), "%+4.2F%%", diff);
 		else
-			ret += scnprintf(bf, sizeof(bf), " ");
+			scnprintf(bf, sizeof(bf), " ");
 
 		if (sep)
 			ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
@@ -898,9 +931,9 @@ static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s,
 
 		if (show_displacement) {
 			if (displacement)
-				ret += scnprintf(bf, sizeof(bf), "%+4ld", displacement);
+				scnprintf(bf, sizeof(bf), "%+4ld", displacement);
 			else
-				ret += scnprintf(bf, sizeof(bf), " ");
+				scnprintf(bf, sizeof(bf), " ");
 
 			if (sep)
 				ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
@@ -1247,6 +1280,37 @@ void hists__filter_by_thread(struct hists *hists)
 	}
 }
 
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if (hists->symbol_filter_str != NULL &&
+	    (!he->ms.sym || strstr(he->ms.sym->name,
+				   hists->symbol_filter_str) == NULL)) {
+		he->filtered |= (1 << HIST_FILTER__SYMBOL);
+		return true;
+	}
+
+	return false;
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+	struct rb_node *nd;
+
+	hists->nr_entries = hists->stats.total_period = 0;
+	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	hists__reset_col_len(hists);
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (hists__filter_entry_by_symbol(hists, h))
+			continue;
+
+		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
+	}
+}
+
 int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
 {
 	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 9413f3e31fea..2cae9df40e04 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -62,6 +62,7 @@ struct hists {
 	const struct thread	*thread_filter;
 	const struct dso	*dso_filter;
 	const char		*uid_filter_str;
+	const char		*symbol_filter_str;
 	pthread_mutex_t		lock;
 	struct events_stats	stats;
 	u64			event_stream;
@@ -107,6 +108,7 @@ int hist_entry__annotate(struct hist_entry *self, size_t privsize);
 
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
+void hists__filter_by_symbol(struct hists *hists);
 
 u16 hists__col_len(struct hists *self, enum hist_column col);
 void hists__set_col_len(struct hists *self, enum hist_column col, u16 len);
@@ -145,6 +147,23 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  int refresh);
 #endif
 
+#ifdef NO_GTK2_SUPPORT
+static inline
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __used,
+				  const char *help __used,
+				  void(*timer)(void *arg) __used,
+				  void *arg __used,
+				  int refresh __used)
+{
+	return 0;
+}
+
+#else
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
+				  void(*timer)(void *arg), void *arg,
+				  int refresh);
+#endif
+
 unsigned int hists__sort_list_width(struct hists *self);
 
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/include/linux/module.h b/tools/perf/util/include/linux/export.h
index b43e2dc21e04..b43e2dc21e04 100644
--- a/tools/perf/util/include/linux/module.h
+++ b/tools/perf/util/include/linux/export.h
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c7a6f6faf91e..5b3a0ef4e232 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -11,6 +11,10 @@
 #include "cache.h"
 #include "header.h"
 #include "debugfs.h"
+#include "parse-events-flex.h"
+#include "pmu.h"
+
+#define MAX_NAME_LEN 100
 
 struct event_symbol {
 	u8		type;
@@ -19,11 +23,8 @@ struct event_symbol {
 	const char	*alias;
 };
 
-enum event_result {
-	EVT_FAILED,
-	EVT_HANDLED,
-	EVT_HANDLED_ALL
-};
+int parse_events_parse(struct list_head *list, struct list_head *list_tmp,
+		       int *idx);
 
 #define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x
 #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
@@ -354,7 +355,24 @@ const char *__event_name(int type, u64 config)
 	return "unknown";
 }
 
-static int parse_aliases(const char **str, const char *names[][MAX_ALIASES], int size)
+static int add_event(struct list_head *list, int *idx,
+		     struct perf_event_attr *attr, char *name)
+{
+	struct perf_evsel *evsel;
+
+	event_attr_init(attr);
+
+	evsel = perf_evsel__new(attr, (*idx)++);
+	if (!evsel)
+		return -ENOMEM;
+
+	list_add_tail(&evsel->node, list);
+
+	evsel->name = strdup(name);
+	return 0;
+}
+
+static int parse_aliases(char *str, const char *names[][MAX_ALIASES], int size)
 {
 	int i, j;
 	int n, longest = -1;
@@ -362,58 +380,57 @@ static int parse_aliases(const char **str, const char *names[][MAX_ALIASES], int
 	for (i = 0; i < size; i++) {
 		for (j = 0; j < MAX_ALIASES && names[i][j]; j++) {
 			n = strlen(names[i][j]);
-			if (n > longest && !strncasecmp(*str, names[i][j], n))
+			if (n > longest && !strncasecmp(str, names[i][j], n))
 				longest = n;
 		}
-		if (longest > 0) {
-			*str += longest;
+		if (longest > 0)
 			return i;
-		}
 	}
 
 	return -1;
 }
 
-static enum event_result
-parse_generic_hw_event(const char **str, struct perf_event_attr *attr)
+int parse_events_add_cache(struct list_head *list, int *idx,
+			   char *type, char *op_result1, char *op_result2)
 {
-	const char *s = *str;
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 	int cache_type = -1, cache_op = -1, cache_result = -1;
+	char *op_result[2] = { op_result1, op_result2 };
+	int i, n;
 
-	cache_type = parse_aliases(&s, hw_cache, PERF_COUNT_HW_CACHE_MAX);
 	/*
 	 * No fallback - if we cannot get a clear cache type
 	 * then bail out:
 	 */
+	cache_type = parse_aliases(type, hw_cache,
+				   PERF_COUNT_HW_CACHE_MAX);
 	if (cache_type == -1)
-		return EVT_FAILED;
+		return -EINVAL;
 
-	while ((cache_op == -1 || cache_result == -1) && *s == '-') {
-		++s;
+	n = snprintf(name, MAX_NAME_LEN, "%s", type);
+
+	for (i = 0; (i < 2) && (op_result[i]); i++) {
+		char *str = op_result[i];
+
+		snprintf(name + n, MAX_NAME_LEN - n, "-%s\n", str);
 
 		if (cache_op == -1) {
-			cache_op = parse_aliases(&s, hw_cache_op,
-						PERF_COUNT_HW_CACHE_OP_MAX);
+			cache_op = parse_aliases(str, hw_cache_op,
+						 PERF_COUNT_HW_CACHE_OP_MAX);
 			if (cache_op >= 0) {
 				if (!is_cache_op_valid(cache_type, cache_op))
-					return EVT_FAILED;
+					return -EINVAL;
 				continue;
 			}
 		}
 
 		if (cache_result == -1) {
-			cache_result = parse_aliases(&s, hw_cache_result,
+			cache_result = parse_aliases(str, hw_cache_result,
 						PERF_COUNT_HW_CACHE_RESULT_MAX);
 			if (cache_result >= 0)
 				continue;
 		}
-
-		/*
-		 * Can't parse this as a cache op or result, so back up
-		 * to the '-'.
-		 */
-		--s;
-		break;
 	}
 
 	/*
@@ -428,20 +445,17 @@ parse_generic_hw_event(const char **str, struct perf_event_attr *attr)
 	if (cache_result == -1)
 		cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS;
 
-	attr->config = cache_type | (cache_op << 8) | (cache_result << 16);
-	attr->type = PERF_TYPE_HW_CACHE;
-
-	*str = s;
-	return EVT_HANDLED;
+	memset(&attr, 0, sizeof(attr));
+	attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
+	attr.type = PERF_TYPE_HW_CACHE;
+	return add_event(list, idx, &attr, name);
 }
 
-static enum event_result
-parse_single_tracepoint_event(char *sys_name,
-			      const char *evt_name,
-			      unsigned int evt_length,
-			      struct perf_event_attr *attr,
-			      const char **strp)
+static int add_tracepoint(struct list_head *list, int *idx,
+			  char *sys_name, char *evt_name)
 {
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 	char evt_path[MAXPATHLEN];
 	char id_buf[4];
 	u64 id;
@@ -452,130 +466,80 @@ parse_single_tracepoint_event(char *sys_name,
 
 	fd = open(evt_path, O_RDONLY);
 	if (fd < 0)
-		return EVT_FAILED;
+		return -1;
 
 	if (read(fd, id_buf, sizeof(id_buf)) < 0) {
 		close(fd);
-		return EVT_FAILED;
+		return -1;
 	}
 
 	close(fd);
 	id = atoll(id_buf);
-	attr->config = id;
-	attr->type = PERF_TYPE_TRACEPOINT;
-	*strp += strlen(sys_name) + evt_length + 1; /* + 1 for the ':' */
-
-	attr->sample_type |= PERF_SAMPLE_RAW;
-	attr->sample_type |= PERF_SAMPLE_TIME;
-	attr->sample_type |= PERF_SAMPLE_CPU;
-
-	attr->sample_period = 1;
 
+	memset(&attr, 0, sizeof(attr));
+	attr.config = id;
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.sample_type |= PERF_SAMPLE_RAW;
+	attr.sample_type |= PERF_SAMPLE_TIME;
+	attr.sample_type |= PERF_SAMPLE_CPU;
+	attr.sample_period = 1;
 
-	return EVT_HANDLED;
+	snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name);
+	return add_event(list, idx, &attr, name);
 }
 
-/* sys + ':' + event + ':' + flags*/
-#define MAX_EVOPT_LEN	(MAX_EVENT_LENGTH * 2 + 2 + 128)
-static enum event_result
-parse_multiple_tracepoint_event(struct perf_evlist *evlist, char *sys_name,
-				const char *evt_exp, char *flags)
+static int add_tracepoint_multi(struct list_head *list, int *idx,
+				char *sys_name, char *evt_name)
 {
 	char evt_path[MAXPATHLEN];
 	struct dirent *evt_ent;
 	DIR *evt_dir;
+	int ret = 0;
 
 	snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
 	evt_dir = opendir(evt_path);
-
 	if (!evt_dir) {
 		perror("Can't open event dir");
-		return EVT_FAILED;
+		return -1;
 	}
 
-	while ((evt_ent = readdir(evt_dir))) {
-		char event_opt[MAX_EVOPT_LEN + 1];
-		int len;
-
+	while (!ret && (evt_ent = readdir(evt_dir))) {
 		if (!strcmp(evt_ent->d_name, ".")
 		    || !strcmp(evt_ent->d_name, "..")
 		    || !strcmp(evt_ent->d_name, "enable")
 		    || !strcmp(evt_ent->d_name, "filter"))
 			continue;
 
-		if (!strglobmatch(evt_ent->d_name, evt_exp))
+		if (!strglobmatch(evt_ent->d_name, evt_name))
 			continue;
 
-		len = snprintf(event_opt, MAX_EVOPT_LEN, "%s:%s%s%s", sys_name,
-			       evt_ent->d_name, flags ? ":" : "",
-			       flags ?: "");
-		if (len < 0)
-			return EVT_FAILED;
-
-		if (parse_events(evlist, event_opt, 0))
-			return EVT_FAILED;
+		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name);
 	}
 
-	return EVT_HANDLED_ALL;
+	return ret;
 }
 
-static enum event_result
-parse_tracepoint_event(struct perf_evlist *evlist, const char **strp,
-		       struct perf_event_attr *attr)
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event)
 {
-	const char *evt_name;
-	char *flags = NULL, *comma_loc;
-	char sys_name[MAX_EVENT_LENGTH];
-	unsigned int sys_length, evt_length;
-
-	if (debugfs_valid_mountpoint(tracing_events_path))
-		return 0;
-
-	evt_name = strchr(*strp, ':');
-	if (!evt_name)
-		return EVT_FAILED;
-
-	sys_length = evt_name - *strp;
-	if (sys_length >= MAX_EVENT_LENGTH)
-		return 0;
+	int ret;
 
-	strncpy(sys_name, *strp, sys_length);
-	sys_name[sys_length] = '\0';
-	evt_name = evt_name + 1;
+	ret = debugfs_valid_mountpoint(tracing_events_path);
+	if (ret)
+		return ret;
 
-	comma_loc = strchr(evt_name, ',');
-	if (comma_loc) {
-		/* take the event name up to the comma */
-		evt_name = strndup(evt_name, comma_loc - evt_name);
-	}
-	flags = strchr(evt_name, ':');
-	if (flags) {
-		/* split it out: */
-		evt_name = strndup(evt_name, flags - evt_name);
-		flags++;
-	}
-
-	evt_length = strlen(evt_name);
-	if (evt_length >= MAX_EVENT_LENGTH)
-		return EVT_FAILED;
-	if (strpbrk(evt_name, "*?")) {
-		*strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */
-		return parse_multiple_tracepoint_event(evlist, sys_name,
-						       evt_name, flags);
-	} else {
-		return parse_single_tracepoint_event(sys_name, evt_name,
-						     evt_length, attr, strp);
-	}
+	return strpbrk(event, "*?") ?
+	       add_tracepoint_multi(list, idx, sys, event) :
+	       add_tracepoint(list, idx, sys, event);
 }
 
-static enum event_result
-parse_breakpoint_type(const char *type, const char **strp,
-		      struct perf_event_attr *attr)
+static int
+parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 {
 	int i;
 
 	for (i = 0; i < 3; i++) {
-		if (!type[i])
+		if (!type || !type[i])
 			break;
 
 		switch (type[i]) {
@@ -589,164 +553,146 @@ parse_breakpoint_type(const char *type, const char **strp,
 			attr->bp_type |= HW_BREAKPOINT_X;
 			break;
 		default:
-			return EVT_FAILED;
+			return -EINVAL;
 		}
 	}
+
 	if (!attr->bp_type) /* Default */
 		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
 
-	*strp = type + i;
-
-	return EVT_HANDLED;
+	return 0;
 }
 
-static enum event_result
-parse_breakpoint_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
+				void *ptr, char *type)
 {
-	const char *target;
-	const char *type;
-	char *endaddr;
-	u64 addr;
-	enum event_result err;
-
-	target = strchr(*strp, ':');
-	if (!target)
-		return EVT_FAILED;
-
-	if (strncmp(*strp, "mem", target - *strp) != 0)
-		return EVT_FAILED;
-
-	target++;
-
-	addr = strtoull(target, &endaddr, 0);
-	if (target == endaddr)
-		return EVT_FAILED;
-
-	attr->bp_addr = addr;
-	*strp = endaddr;
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 
-	type = strchr(target, ':');
+	memset(&attr, 0, sizeof(attr));
+	attr.bp_addr = (unsigned long) ptr;
 
-	/* If no type is defined, just rw as default */
-	if (!type) {
-		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
-	} else {
-		err = parse_breakpoint_type(++type, strp, attr);
-		if (err == EVT_FAILED)
-			return EVT_FAILED;
-	}
+	if (parse_breakpoint_type(type, &attr))
+		return -EINVAL;
 
 	/*
 	 * We should find a nice way to override the access length
 	 * Provide some defaults for now
 	 */
-	if (attr->bp_type == HW_BREAKPOINT_X)
-		attr->bp_len = sizeof(long);
+	if (attr.bp_type == HW_BREAKPOINT_X)
+		attr.bp_len = sizeof(long);
 	else
-		attr->bp_len = HW_BREAKPOINT_LEN_4;
+		attr.bp_len = HW_BREAKPOINT_LEN_4;
 
-	attr->type = PERF_TYPE_BREAKPOINT;
+	attr.type = PERF_TYPE_BREAKPOINT;
 
-	return EVT_HANDLED;
+	snprintf(name, MAX_NAME_LEN, "mem:%p:%s", ptr, type ? type : "rw");
+	return add_event(list, idx, &attr, name);
 }
 
-static int check_events(const char *str, unsigned int i)
+static int config_term(struct perf_event_attr *attr,
+		       struct parse_events__term *term)
 {
-	int n;
+	switch (term->type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+		attr->config = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+		attr->config1 = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+		attr->config2 = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+		attr->sample_period = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+		/*
+		 * TODO uncomment when the field is available
+		 * attr->branch_sample_type = term->val.num;
+		 */
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
 
-	n = strlen(event_symbols[i].symbol);
-	if (!strncasecmp(str, event_symbols[i].symbol, n))
-		return n;
+static int config_attr(struct perf_event_attr *attr,
+		       struct list_head *head, int fail)
+{
+	struct parse_events__term *term;
 
-	n = strlen(event_symbols[i].alias);
-	if (n) {
-		if (!strncasecmp(str, event_symbols[i].alias, n))
-			return n;
-	}
+	list_for_each_entry(term, head, list)
+		if (config_term(attr, term) && fail)
+			return -EINVAL;
 
 	return 0;
 }
 
-static enum event_result
-parse_symbolic_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_numeric(struct list_head *list, int *idx,
+			     unsigned long type, unsigned long config,
+			     struct list_head *head_config)
 {
-	const char *str = *strp;
-	unsigned int i;
-	int n;
-
-	for (i = 0; i < ARRAY_SIZE(event_symbols); i++) {
-		n = check_events(str, i);
-		if (n > 0) {
-			attr->type = event_symbols[i].type;
-			attr->config = event_symbols[i].config;
-			*strp = str + n;
-			return EVT_HANDLED;
-		}
-	}
-	return EVT_FAILED;
+	struct perf_event_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.type = type;
+	attr.config = config;
+
+	if (head_config &&
+	    config_attr(&attr, head_config, 1))
+		return -EINVAL;
+
+	return add_event(list, idx, &attr,
+			 (char *) __event_name(type, config));
 }
 
-static enum event_result
-parse_raw_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_pmu(struct list_head *list, int *idx,
+			 char *name, struct list_head *head_config)
 {
-	const char *str = *strp;
-	u64 config;
-	int n;
-
-	if (*str != 'r')
-		return EVT_FAILED;
-	n = hex2u64(str + 1, &config);
-	if (n > 0) {
-		const char *end = str + n + 1;
-		if (*end != '\0' && *end != ',' && *end != ':')
-			return EVT_FAILED;
-
-		*strp = end;
-		attr->type = PERF_TYPE_RAW;
-		attr->config = config;
-		return EVT_HANDLED;
-	}
-	return EVT_FAILED;
+	struct perf_event_attr attr;
+	struct perf_pmu *pmu;
+
+	pmu = perf_pmu__find(name);
+	if (!pmu)
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+
+	/*
+	 * Configure hardcoded terms first, no need to check
+	 * return value when called with fail == 0 ;)
+	 */
+	config_attr(&attr, head_config, 0);
+
+	if (perf_pmu__config(pmu, &attr, head_config))
+		return -EINVAL;
+
+	return add_event(list, idx, &attr, (char *) "pmu");
 }
 
-static enum event_result
-parse_numeric_event(const char **strp, struct perf_event_attr *attr)
+void parse_events_update_lists(struct list_head *list_event,
+			       struct list_head *list_all)
 {
-	const char *str = *strp;
-	char *endp;
-	unsigned long type;
-	u64 config;
-
-	type = strtoul(str, &endp, 0);
-	if (endp > str && type < PERF_TYPE_MAX && *endp == ':') {
-		str = endp + 1;
-		config = strtoul(str, &endp, 0);
-		if (endp > str) {
-			attr->type = type;
-			attr->config = config;
-			*strp = endp;
-			return EVT_HANDLED;
-		}
-	}
-	return EVT_FAILED;
+	/*
+	 * Called for single event definition. Update the
+	 * 'all event' list, and reinit the 'signle event'
+	 * list, for next event definition.
+	 */
+	list_splice_tail(list_event, list_all);
+	INIT_LIST_HEAD(list_event);
 }
 
-static int
-parse_event_modifier(const char **strp, struct perf_event_attr *attr)
+int parse_events_modifier(struct list_head *list, char *str)
 {
-	const char *str = *strp;
+	struct perf_evsel *evsel;
 	int exclude = 0, exclude_GH = 0;
 	int eu = 0, ek = 0, eh = 0, eH = 0, eG = 0, precise = 0;
 
-	if (!*str)
+	if (str == NULL)
 		return 0;
 
-	if (*str == ',')
-		return 0;
-
-	if (*str++ != ':')
-		return -1;
-
 	while (*str) {
 		if (*str == 'u') {
 			if (!exclude)
@@ -775,111 +721,62 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 
 		++str;
 	}
-	if (str < *strp + 2)
-		return -1;
 
-	*strp = str;
+	/*
+	 * precise ip:
+	 *
+	 *  0 - SAMPLE_IP can have arbitrary skid
+	 *  1 - SAMPLE_IP must have constant skid
+	 *  2 - SAMPLE_IP requested to have 0 skid
+	 *  3 - SAMPLE_IP must have 0 skid
+	 *
+	 *  See also PERF_RECORD_MISC_EXACT_IP
+	 */
+	if (precise > 3)
+		return -EINVAL;
 
-	attr->exclude_user   = eu;
-	attr->exclude_kernel = ek;
-	attr->exclude_hv     = eh;
-	attr->precise_ip     = precise;
-	attr->exclude_host   = eH;
-	attr->exclude_guest  = eG;
+	list_for_each_entry(evsel, list, node) {
+		evsel->attr.exclude_user   = eu;
+		evsel->attr.exclude_kernel = ek;
+		evsel->attr.exclude_hv     = eh;
+		evsel->attr.precise_ip     = precise;
+		evsel->attr.exclude_host   = eH;
+		evsel->attr.exclude_guest  = eG;
+	}
 
 	return 0;
 }
 
-/*
- * Each event can have multiple symbolic names.
- * Symbolic names are (almost) exactly matched.
- */
-static enum event_result
-parse_event_symbols(struct perf_evlist *evlist, const char **str,
-		    struct perf_event_attr *attr)
+int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
 {
-	enum event_result ret;
-
-	ret = parse_tracepoint_event(evlist, str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
-
-	ret = parse_raw_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	LIST_HEAD(list);
+	LIST_HEAD(list_tmp);
+	YY_BUFFER_STATE buffer;
+	int ret, idx = evlist->nr_entries;
 
-	ret = parse_numeric_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	buffer = parse_events__scan_string(str);
 
-	ret = parse_symbolic_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	ret = parse_events_parse(&list, &list_tmp, &idx);
 
-	ret = parse_generic_hw_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	parse_events__flush_buffer(buffer);
+	parse_events__delete_buffer(buffer);
 
-	ret = parse_breakpoint_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
-
-	fprintf(stderr, "invalid or unsupported event: '%s'\n", *str);
-	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
-	return EVT_FAILED;
-
-modifier:
-	if (parse_event_modifier(str, attr) < 0) {
-		fprintf(stderr, "invalid event modifier: '%s'\n", *str);
-		fprintf(stderr, "Run 'perf list' for a list of valid events and modifiers\n");
-
-		return EVT_FAILED;
+	if (!ret) {
+		int entries = idx - evlist->nr_entries;
+		perf_evlist__splice_list_tail(evlist, &list, entries);
+		return 0;
 	}
 
+	/*
+	 * There are 2 users - builtin-record and builtin-test objects.
+	 * Both call perf_evlist__delete in case of error, so we dont
+	 * need to bother.
+	 */
+	fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
+	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist , const char *str, int unset __used)
-{
-	struct perf_event_attr attr;
-	enum event_result ret;
-	const char *ostr;
-
-	for (;;) {
-		ostr = str;
-		memset(&attr, 0, sizeof(attr));
-		event_attr_init(&attr);
-		ret = parse_event_symbols(evlist, &str, &attr);
-		if (ret == EVT_FAILED)
-			return -1;
-
-		if (!(*str == 0 || *str == ',' || isspace(*str)))
-			return -1;
-
-		if (ret != EVT_HANDLED_ALL) {
-			struct perf_evsel *evsel;
-			evsel = perf_evsel__new(&attr, evlist->nr_entries);
-			if (evsel == NULL)
-				return -1;
-			perf_evlist__add(evlist, evsel);
-
-			evsel->name = calloc(str - ostr + 1, 1);
-			if (!evsel->name)
-				return -1;
-			strncpy(evsel->name, ostr, str - ostr);
-		}
-
-		if (*str == 0)
-			break;
-		if (*str == ',')
-			++str;
-		while (isspace(*str))
-			++str;
-	}
-
-	return 0;
-}
-
 int parse_events_option(const struct option *opt, const char *str,
 			int unset __used)
 {
@@ -1052,8 +949,6 @@ int print_hwcache_events(const char *event_glob)
 	return printed;
 }
 
-#define MAX_NAME_LEN 100
-
 /*
  * Print the help text for the event symbols:
  */
@@ -1102,8 +997,12 @@ void print_events(const char *event_glob)
 
 	printf("\n");
 	printf("  %-50s [%s]\n",
-		"rNNN (see 'perf list --help' on how to encode it)",
+	       "rNNN",
 	       event_type_descriptors[PERF_TYPE_RAW]);
+	printf("  %-50s [%s]\n",
+	       "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
+	       event_type_descriptors[PERF_TYPE_RAW]);
+	printf("   (see 'perf list --help' on how to encode it)\n");
 	printf("\n");
 
 	printf("  %-50s [%s]\n",
@@ -1113,3 +1012,51 @@ void print_events(const char *event_glob)
 
 	print_tracepoint_events(NULL, NULL);
 }
+
+int parse_events__is_hardcoded_term(struct parse_events__term *term)
+{
+	return term->type <= PARSE_EVENTS__TERM_TYPE_HARDCODED_MAX;
+}
+
+int parse_events__new_term(struct parse_events__term **_term, int type,
+			   char *config, char *str, long num)
+{
+	struct parse_events__term *term;
+
+	term = zalloc(sizeof(*term));
+	if (!term)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&term->list);
+	term->type = type;
+	term->config = config;
+
+	switch (type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+	case PARSE_EVENTS__TERM_TYPE_NUM:
+		term->val.num = num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_STR:
+		term->val.str = str;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*_term = term;
+	return 0;
+}
+
+void parse_events__free_terms(struct list_head *terms)
+{
+	struct parse_events__term *term, *h;
+
+	list_for_each_entry_safe(term, h, terms, list)
+		free(term);
+
+	free(terms);
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 7e0cbe75d5f1..ca069f893381 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -33,6 +33,55 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
+enum {
+	PARSE_EVENTS__TERM_TYPE_CONFIG,
+	PARSE_EVENTS__TERM_TYPE_CONFIG1,
+	PARSE_EVENTS__TERM_TYPE_CONFIG2,
+	PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD,
+	PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+	PARSE_EVENTS__TERM_TYPE_NUM,
+	PARSE_EVENTS__TERM_TYPE_STR,
+
+	PARSE_EVENTS__TERM_TYPE_HARDCODED_MAX =
+		PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+};
+
+struct parse_events__term {
+	char *config;
+	union {
+		char *str;
+		long  num;
+	} val;
+	int type;
+
+	struct list_head list;
+};
+
+int parse_events__is_hardcoded_term(struct parse_events__term *term);
+int parse_events__new_term(struct parse_events__term **term, int type,
+			   char *config, char *str, long num);
+void parse_events__free_terms(struct list_head *terms);
+int parse_events_modifier(struct list_head *list __used, char *str __used);
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event);
+int parse_events_add_raw(struct perf_evlist *evlist, unsigned long config,
+			 unsigned long config1, unsigned long config2,
+			 char *mod);
+int parse_events_add_numeric(struct list_head *list, int *idx,
+			     unsigned long type, unsigned long config,
+			     struct list_head *head_config);
+int parse_events_add_cache(struct list_head *list, int *idx,
+			   char *type, char *op_result1, char *op_result2);
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
+				void *ptr, char *type);
+int parse_events_add_pmu(struct list_head *list, int *idx,
+			 char *pmu , struct list_head *head_config);
+void parse_events_update_lists(struct list_head *list_event,
+			       struct list_head *list_all);
+void parse_events_error(struct list_head *list_all,
+			struct list_head *list_event,
+			int *idx, char const *msg);
+
 void print_events(const char *event_glob);
 void print_events_type(u8 type);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
new file mode 100644
index 000000000000..05d766e3ecb5
--- /dev/null
+++ b/tools/perf/util/parse-events.l
@@ -0,0 +1,127 @@
+
+%option prefix="parse_events_"
+
+%{
+#include <errno.h>
+#include "../perf.h"
+#include "parse-events-bison.h"
+#include "parse-events.h"
+
+static int __value(char *str, int base, int token)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(str, NULL, base);
+	if (errno)
+		return PE_ERROR;
+
+	parse_events_lval.num = num;
+	return token;
+}
+
+static int value(int base)
+{
+	return __value(parse_events_text, base, PE_VALUE);
+}
+
+static int raw(void)
+{
+	return __value(parse_events_text + 1, 16, PE_RAW);
+}
+
+static int str(int token)
+{
+	parse_events_lval.str = strdup(parse_events_text);
+	return token;
+}
+
+static int sym(int type, int config)
+{
+	parse_events_lval.num = (type << 16) + config;
+	return PE_VALUE_SYM;
+}
+
+static int term(int type)
+{
+	parse_events_lval.num = type;
+	return PE_TERM;
+}
+
+%}
+
+num_dec		[0-9]+
+num_hex		0x[a-fA-F0-9]+
+num_raw_hex	[a-fA-F0-9]+
+name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
+modifier_event	[ukhp]{1,5}
+modifier_bp	[rwx]
+
+%%
+cpu-cycles|cycles				{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-clock					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations			{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
+
+L1-dcache|l1-d|l1d|L1-data		|
+L1-icache|l1-i|l1i|L1-instruction	|
+LLC|L2					|
+dTLB|d-tlb|Data-TLB			|
+iTLB|i-tlb|Instruction-TLB		|
+branch|branches|bpu|btb|bpc		|
+node					{ return str(PE_NAME_CACHE_TYPE); }
+
+load|loads|read				|
+store|stores|write			|
+prefetch|prefetches			|
+speculative-read|speculative-load	|
+refs|Reference|ops|access		|
+misses|miss				{ return str(PE_NAME_CACHE_OP_RESULT); }
+
+	/*
+	 * These are event config hardcoded term names to be specified
+	 * within xxx/.../ syntax. So far we dont clash with other names,
+	 * so we can put them here directly. In case the we have a conflict
+	 * in future, this needs to go into '//' condition block.
+	 */
+config			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG); }
+config1			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+config2			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+period			{ return term(PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+branch_type		{ return term(PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+
+mem:			{ return PE_PREFIX_MEM; }
+r{num_raw_hex}		{ return raw(); }
+{num_dec}		{ return value(10); }
+{num_hex}		{ return value(16); }
+
+{modifier_event}	{ return str(PE_MODIFIER_EVENT); }
+{modifier_bp}		{ return str(PE_MODIFIER_BP); }
+{name}			{ return str(PE_NAME); }
+"/"			{ return '/'; }
+-			{ return '-'; }
+,			{ return ','; }
+:			{ return ':'; }
+=			{ return '='; }
+
+%%
+
+int parse_events_wrap(void)
+{
+	return 1;
+}
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
new file mode 100644
index 000000000000..d9637da7333c
--- /dev/null
+++ b/tools/perf/util/parse-events.y
@@ -0,0 +1,229 @@
+
+%name-prefix "parse_events_"
+%parse-param {struct list_head *list_all}
+%parse-param {struct list_head *list_event}
+%parse-param {int *idx}
+
+%{
+
+#define YYDEBUG 1
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include "types.h"
+#include "util.h"
+#include "parse-events.h"
+
+extern int parse_events_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+	if (val) \
+		YYABORT; \
+} while (0)
+
+%}
+
+%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM
+%token PE_NAME
+%token PE_MODIFIER_EVENT PE_MODIFIER_BP
+%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
+%token PE_PREFIX_MEM PE_PREFIX_RAW
+%token PE_ERROR
+%type <num> PE_VALUE
+%type <num> PE_VALUE_SYM
+%type <num> PE_RAW
+%type <num> PE_TERM
+%type <str> PE_NAME
+%type <str> PE_NAME_CACHE_TYPE
+%type <str> PE_NAME_CACHE_OP_RESULT
+%type <str> PE_MODIFIER_EVENT
+%type <str> PE_MODIFIER_BP
+%type <head> event_config
+%type <term> event_term
+
+%union
+{
+	char *str;
+	unsigned long num;
+	struct list_head *head;
+	struct parse_events__term *term;
+}
+%%
+
+events:
+events ',' event | event
+
+event:
+event_def PE_MODIFIER_EVENT
+{
+	/*
+	 * Apply modifier on all events added by single event definition
+	 * (there could be more events added for multiple tracepoint
+	 * definitions via '*?'.
+	 */
+	ABORT_ON(parse_events_modifier(list_event, $2));
+	parse_events_update_lists(list_event, list_all);
+}
+|
+event_def
+{
+	parse_events_update_lists(list_event, list_all);
+}
+
+event_def: event_pmu |
+	   event_legacy_symbol |
+	   event_legacy_cache sep_dc |
+	   event_legacy_mem |
+	   event_legacy_tracepoint sep_dc |
+	   event_legacy_numeric sep_dc |
+	   event_legacy_raw sep_dc
+
+event_pmu:
+PE_NAME '/' event_config '/'
+{
+	ABORT_ON(parse_events_add_pmu(list_event, idx, $1, $3));
+	parse_events__free_terms($3);
+}
+
+event_legacy_symbol:
+PE_VALUE_SYM '/' event_config '/'
+{
+	int type = $1 >> 16;
+	int config = $1 & 255;
+
+	ABORT_ON(parse_events_add_numeric(list_event, idx, type, config, $3));
+	parse_events__free_terms($3);
+}
+|
+PE_VALUE_SYM sep_slash_dc
+{
+	int type = $1 >> 16;
+	int config = $1 & 255;
+
+	ABORT_ON(parse_events_add_numeric(list_event, idx, type, config, NULL));
+}
+
+event_legacy_cache:
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+{
+	ABORT_ON(parse_events_add_cache(list_event, idx, $1, $3, $5));
+}
+|
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+{
+	ABORT_ON(parse_events_add_cache(list_event, idx, $1, $3, NULL));
+}
+|
+PE_NAME_CACHE_TYPE
+{
+	ABORT_ON(parse_events_add_cache(list_event, idx, $1, NULL, NULL));
+}
+
+event_legacy_mem:
+PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
+{
+	ABORT_ON(parse_events_add_breakpoint(list_event, idx, (void *) $2, $4));
+}
+|
+PE_PREFIX_MEM PE_VALUE sep_dc
+{
+	ABORT_ON(parse_events_add_breakpoint(list_event, idx, (void *) $2, NULL));
+}
+
+event_legacy_tracepoint:
+PE_NAME ':' PE_NAME
+{
+	ABORT_ON(parse_events_add_tracepoint(list_event, idx, $1, $3));
+}
+
+event_legacy_numeric:
+PE_VALUE ':' PE_VALUE
+{
+	ABORT_ON(parse_events_add_numeric(list_event, idx, $1, $3, NULL));
+}
+
+event_legacy_raw:
+PE_RAW
+{
+	ABORT_ON(parse_events_add_numeric(list_event, idx, PERF_TYPE_RAW, $1, NULL));
+}
+
+event_config:
+event_config ',' event_term
+{
+	struct list_head *head = $1;
+	struct parse_events__term *term = $3;
+
+	ABORT_ON(!head);
+	list_add_tail(&term->list, head);
+	$$ = $1;
+}
+|
+event_term
+{
+	struct list_head *head = malloc(sizeof(*head));
+	struct parse_events__term *term = $1;
+
+	ABORT_ON(!head);
+	INIT_LIST_HEAD(head);
+	list_add_tail(&term->list, head);
+	$$ = head;
+}
+
+event_term:
+PE_NAME '=' PE_NAME
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_STR,
+		 $1, $3, 0));
+	$$ = term;
+}
+|
+PE_NAME '=' PE_VALUE
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM,
+		 $1, NULL, $3));
+	$$ = term;
+}
+|
+PE_NAME
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM,
+		 $1, NULL, 1));
+	$$ = term;
+}
+|
+PE_TERM '=' PE_VALUE
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, $1, NULL, NULL, $3));
+	$$ = term;
+}
+|
+PE_TERM
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, $1, NULL, NULL, 1));
+	$$ = term;
+}
+
+sep_dc: ':' |
+
+sep_slash_dc: '/' | ':' |
+
+%%
+
+void parse_events_error(struct list_head *list_all __used,
+			struct list_head *list_event __used,
+			int *idx __used,
+			char const *msg __used)
+{
+}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
new file mode 100644
index 000000000000..cb08a118e811
--- /dev/null
+++ b/tools/perf/util/pmu.c
@@ -0,0 +1,469 @@
+
+#include <linux/list.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <dirent.h>
+#include "sysfs.h"
+#include "util.h"
+#include "pmu.h"
+#include "parse-events.h"
+
+int perf_pmu_parse(struct list_head *list, char *name);
+extern FILE *perf_pmu_in;
+
+static LIST_HEAD(pmus);
+
+/*
+ * Parse & process all the sysfs attributes located under
+ * the directory specified in 'dir' parameter.
+ */
+static int pmu_format_parse(char *dir, struct list_head *head)
+{
+	struct dirent *evt_ent;
+	DIR *format_dir;
+	int ret = 0;
+
+	format_dir = opendir(dir);
+	if (!format_dir)
+		return -EINVAL;
+
+	while (!ret && (evt_ent = readdir(format_dir))) {
+		char path[PATH_MAX];
+		char *name = evt_ent->d_name;
+		FILE *file;
+
+		if (!strcmp(name, ".") || !strcmp(name, ".."))
+			continue;
+
+		snprintf(path, PATH_MAX, "%s/%s", dir, name);
+
+		ret = -EINVAL;
+		file = fopen(path, "r");
+		if (!file)
+			break;
+
+		perf_pmu_in = file;
+		ret = perf_pmu_parse(head, name);
+		fclose(file);
+	}
+
+	closedir(format_dir);
+	return ret;
+}
+
+/*
+ * Reading/parsing the default pmu format definition, which should be
+ * located at:
+ * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
+ */
+static int pmu_format(char *name, struct list_head *format)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs_find_mountpoint();
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/format", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return -1;
+
+	if (pmu_format_parse(path, format))
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Reading/parsing the default pmu type value, which should be
+ * located at:
+ * /sys/bus/event_source/devices/<dev>/type as sysfs attribute.
+ */
+static int pmu_type(char *name, __u32 *type)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+	FILE *file;
+	int ret = 0;
+
+	sysfs = sysfs_find_mountpoint();
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/type", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return -1;
+
+	file = fopen(path, "r");
+	if (!file)
+		return -EINVAL;
+
+	if (1 != fscanf(file, "%u", type))
+		ret = -1;
+
+	fclose(file);
+	return ret;
+}
+
+static struct perf_pmu *pmu_lookup(char *name)
+{
+	struct perf_pmu *pmu;
+	LIST_HEAD(format);
+	__u32 type;
+
+	/*
+	 * The pmu data we store & need consists of the pmu
+	 * type value and format definitions. Load both right
+	 * now.
+	 */
+	if (pmu_format(name, &format))
+		return NULL;
+
+	if (pmu_type(name, &type))
+		return NULL;
+
+	pmu = zalloc(sizeof(*pmu));
+	if (!pmu)
+		return NULL;
+
+	INIT_LIST_HEAD(&pmu->format);
+	list_splice(&format, &pmu->format);
+	pmu->name = strdup(name);
+	pmu->type = type;
+	return pmu;
+}
+
+static struct perf_pmu *pmu_find(char *name)
+{
+	struct perf_pmu *pmu;
+
+	list_for_each_entry(pmu, &pmus, list)
+		if (!strcmp(pmu->name, name))
+			return pmu;
+
+	return NULL;
+}
+
+struct perf_pmu *perf_pmu__find(char *name)
+{
+	struct perf_pmu *pmu;
+
+	/*
+	 * Once PMU is loaded it stays in the list,
+	 * so we keep us from multiple reading/parsing
+	 * the pmu format definitions.
+	 */
+	pmu = pmu_find(name);
+	if (pmu)
+		return pmu;
+
+	return pmu_lookup(name);
+}
+
+static struct perf_pmu__format*
+pmu_find_format(struct list_head *formats, char *name)
+{
+	struct perf_pmu__format *format;
+
+	list_for_each_entry(format, formats, list)
+		if (!strcmp(format->name, name))
+			return format;
+
+	return NULL;
+}
+
+/*
+ * Returns value based on the format definition (format parameter)
+ * and unformated value (value parameter).
+ *
+ * TODO maybe optimize a little ;)
+ */
+static __u64 pmu_format_value(unsigned long *format, __u64 value)
+{
+	unsigned long fbit, vbit;
+	__u64 v = 0;
+
+	for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
+
+		if (!test_bit(fbit, format))
+			continue;
+
+		if (!(value & (1llu << vbit++)))
+			continue;
+
+		v |= (1llu << fbit);
+	}
+
+	return v;
+}
+
+/*
+ * Setup one of config[12] attr members based on the
+ * user input data - temr parameter.
+ */
+static int pmu_config_term(struct list_head *formats,
+			   struct perf_event_attr *attr,
+			   struct parse_events__term *term)
+{
+	struct perf_pmu__format *format;
+	__u64 *vp;
+
+	/*
+	 * Support only for hardcoded and numnerial terms.
+	 * Hardcoded terms should be already in, so nothing
+	 * to be done for them.
+	 */
+	if (parse_events__is_hardcoded_term(term))
+		return 0;
+
+	if (term->type != PARSE_EVENTS__TERM_TYPE_NUM)
+		return -EINVAL;
+
+	format = pmu_find_format(formats, term->config);
+	if (!format)
+		return -EINVAL;
+
+	switch (format->value) {
+	case PERF_PMU_FORMAT_VALUE_CONFIG:
+		vp = &attr->config;
+		break;
+	case PERF_PMU_FORMAT_VALUE_CONFIG1:
+		vp = &attr->config1;
+		break;
+	case PERF_PMU_FORMAT_VALUE_CONFIG2:
+		vp = &attr->config2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*vp |= pmu_format_value(format->bits, term->val.num);
+	return 0;
+}
+
+static int pmu_config(struct list_head *formats, struct perf_event_attr *attr,
+		      struct list_head *head_terms)
+{
+	struct parse_events__term *term, *h;
+
+	list_for_each_entry_safe(term, h, head_terms, list)
+		if (pmu_config_term(formats, attr, term))
+			return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Configures event's 'attr' parameter based on the:
+ * 1) users input - specified in terms parameter
+ * 2) pmu format definitions - specified by pmu parameter
+ */
+int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
+		     struct list_head *head_terms)
+{
+	attr->type = pmu->type;
+	return pmu_config(&pmu->format, attr, head_terms);
+}
+
+int perf_pmu__new_format(struct list_head *list, char *name,
+			 int config, unsigned long *bits)
+{
+	struct perf_pmu__format *format;
+
+	format = zalloc(sizeof(*format));
+	if (!format)
+		return -ENOMEM;
+
+	format->name = strdup(name);
+	format->value = config;
+	memcpy(format->bits, bits, sizeof(format->bits));
+
+	list_add_tail(&format->list, list);
+	return 0;
+}
+
+void perf_pmu__set_format(unsigned long *bits, long from, long to)
+{
+	long b;
+
+	if (!to)
+		to = from;
+
+	memset(bits, 0, BITS_TO_LONGS(PERF_PMU_FORMAT_BITS));
+	for (b = from; b <= to; b++)
+		set_bit(b, bits);
+}
+
+/* Simulated format definitions. */
+static struct test_format {
+	const char *name;
+	const char *value;
+} test_formats[] = {
+	{ "krava01", "config:0-1,62-63\n", },
+	{ "krava02", "config:10-17\n", },
+	{ "krava03", "config:5\n", },
+	{ "krava11", "config1:0,2,4,6,8,20-28\n", },
+	{ "krava12", "config1:63\n", },
+	{ "krava13", "config1:45-47\n", },
+	{ "krava21", "config2:0-3,10-13,20-23,30-33,40-43,50-53,60-63\n", },
+	{ "krava22", "config2:8,18,48,58\n", },
+	{ "krava23", "config2:28-29,38\n", },
+};
+
+#define TEST_FORMATS_CNT (sizeof(test_formats) / sizeof(struct test_format))
+
+/* Simulated users input. */
+static struct parse_events__term test_terms[] = {
+	{
+		.config  = (char *) "krava01",
+		.val.num = 15,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava02",
+		.val.num = 170,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava03",
+		.val.num = 1,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava11",
+		.val.num = 27,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava12",
+		.val.num = 1,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava13",
+		.val.num = 2,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava21",
+		.val.num = 119,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava22",
+		.val.num = 11,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava23",
+		.val.num = 2,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+};
+#define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term))
+
+/*
+ * Prepare format directory data, exported by kernel
+ * at /sys/bus/event_source/devices/<dev>/format.
+ */
+static char *test_format_dir_get(void)
+{
+	static char dir[PATH_MAX];
+	unsigned int i;
+
+	snprintf(dir, PATH_MAX, "/tmp/perf-pmu-test-format-XXXXXX");
+	if (!mkdtemp(dir))
+		return NULL;
+
+	for (i = 0; i < TEST_FORMATS_CNT; i++) {
+		static char name[PATH_MAX];
+		struct test_format *format = &test_formats[i];
+		FILE *file;
+
+		snprintf(name, PATH_MAX, "%s/%s", dir, format->name);
+
+		file = fopen(name, "w");
+		if (!file)
+			return NULL;
+
+		if (1 != fwrite(format->value, strlen(format->value), 1, file))
+			break;
+
+		fclose(file);
+	}
+
+	return dir;
+}
+
+/* Cleanup format directory. */
+static int test_format_dir_put(char *dir)
+{
+	char buf[PATH_MAX];
+	snprintf(buf, PATH_MAX, "rm -f %s/*\n", dir);
+	if (system(buf))
+		return -1;
+
+	snprintf(buf, PATH_MAX, "rmdir %s\n", dir);
+	return system(buf);
+}
+
+static struct list_head *test_terms_list(void)
+{
+	static LIST_HEAD(terms);
+	unsigned int i;
+
+	for (i = 0; i < TERMS_CNT; i++)
+		list_add_tail(&test_terms[i].list, &terms);
+
+	return &terms;
+}
+
+#undef TERMS_CNT
+
+int perf_pmu__test(void)
+{
+	char *format = test_format_dir_get();
+	LIST_HEAD(formats);
+	struct list_head *terms = test_terms_list();
+	int ret;
+
+	if (!format)
+		return -EINVAL;
+
+	do {
+		struct perf_event_attr attr;
+
+		memset(&attr, 0, sizeof(attr));
+
+		ret = pmu_format_parse(format, &formats);
+		if (ret)
+			break;
+
+		ret = pmu_config(&formats, &attr, terms);
+		if (ret)
+			break;
+
+		ret = -EINVAL;
+
+		if (attr.config  != 0xc00000000002a823)
+			break;
+		if (attr.config1 != 0x8000400000000145)
+			break;
+		if (attr.config2 != 0x0400000020041d07)
+			break;
+
+		ret = 0;
+	} while (0);
+
+	test_format_dir_put(format);
+	return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
new file mode 100644
index 000000000000..68c0db965e1f
--- /dev/null
+++ b/tools/perf/util/pmu.h
@@ -0,0 +1,41 @@
+#ifndef __PMU_H
+#define __PMU_H
+
+#include <linux/bitops.h>
+#include "../../../include/linux/perf_event.h"
+
+enum {
+	PERF_PMU_FORMAT_VALUE_CONFIG,
+	PERF_PMU_FORMAT_VALUE_CONFIG1,
+	PERF_PMU_FORMAT_VALUE_CONFIG2,
+};
+
+#define PERF_PMU_FORMAT_BITS 64
+
+struct perf_pmu__format {
+	char *name;
+	int value;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+	struct list_head list;
+};
+
+struct perf_pmu {
+	char *name;
+	__u32 type;
+	struct list_head format;
+	struct list_head list;
+};
+
+struct perf_pmu *perf_pmu__find(char *name);
+int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
+		     struct list_head *head_terms);
+
+int perf_pmu_wrap(void);
+void perf_pmu_error(struct list_head *list, char *name, char const *msg);
+
+int perf_pmu__new_format(struct list_head *list, char *name,
+			 int config, unsigned long *bits);
+void perf_pmu__set_format(unsigned long *bits, long from, long to);
+
+int perf_pmu__test(void);
+#endif /* __PMU_H */
diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l
new file mode 100644
index 000000000000..a15d9fbd7c0e
--- /dev/null
+++ b/tools/perf/util/pmu.l
@@ -0,0 +1,43 @@
+%option prefix="perf_pmu_"
+
+%{
+#include <stdlib.h>
+#include <linux/bitops.h>
+#include "pmu.h"
+#include "pmu-bison.h"
+
+static int value(int base)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(perf_pmu_text, NULL, base);
+	if (errno)
+		return PP_ERROR;
+
+	perf_pmu_lval.num = num;
+	return PP_VALUE;
+}
+
+%}
+
+num_dec         [0-9]+
+
+%%
+
+{num_dec}	{ return value(10); }
+config		{ return PP_CONFIG; }
+config1		{ return PP_CONFIG1; }
+config2		{ return PP_CONFIG2; }
+-		{ return '-'; }
+:		{ return ':'; }
+,		{ return ','; }
+.		{ ; }
+\n		{ ; }
+
+%%
+
+int perf_pmu_wrap(void)
+{
+	return 1;
+}
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
new file mode 100644
index 000000000000..20ea77e93169
--- /dev/null
+++ b/tools/perf/util/pmu.y
@@ -0,0 +1,93 @@
+
+%name-prefix "perf_pmu_"
+%parse-param {struct list_head *format}
+%parse-param {char *name}
+
+%{
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/bitmap.h>
+#include <string.h>
+#include "pmu.h"
+
+extern int perf_pmu_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+        if (val) \
+                YYABORT; \
+} while (0)
+
+%}
+
+%token PP_CONFIG PP_CONFIG1 PP_CONFIG2
+%token PP_VALUE PP_ERROR
+%type <num> PP_VALUE
+%type <bits> bit_term
+%type <bits> bits
+
+%union
+{
+	unsigned long num;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+}
+
+%%
+
+format:
+format format_term
+|
+format_term
+
+format_term:
+PP_CONFIG ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG,
+				      $3));
+}
+|
+PP_CONFIG1 ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG1,
+				      $3));
+}
+|
+PP_CONFIG2 ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG2,
+				      $3));
+}
+
+bits:
+bits ',' bit_term
+{
+	bitmap_or($$, $1, $3, 64);
+}
+|
+bit_term
+{
+	memcpy($$, $1, sizeof($1));
+}
+
+bit_term:
+PP_VALUE '-' PP_VALUE
+{
+	perf_pmu__set_format($$, $1, $3);
+}
+|
+PP_VALUE
+{
+	perf_pmu__set_format($$, $1, 0);
+}
+
+%%
+
+void perf_pmu_error(struct list_head *list __used,
+		    char *name __used,
+		    char const *msg __used)
+{
+}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2cc162d3b78c..d448984ed789 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -972,10 +972,12 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	struct dwarf_callback_param *param = data;
 	struct probe_finder *pf = param->data;
 	struct perf_probe_point *pp = &pf->pev->point;
+	Dwarf_Attribute attr;
 
 	/* Check tag and diename */
 	if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
-	    !die_compare_name(sp_die, pp->function))
+	    !die_compare_name(sp_die, pp->function) ||
+	    dwarf_attr(sp_die, DW_AT_declaration, &attr))
 		return DWARF_CB_OK;
 
 	/* Check declared file */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 002ebbf59f48..9412e3b05f68 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -140,6 +140,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
 	INIT_LIST_HEAD(&self->ordered_samples.to_free);
 	machine__init(&self->host_machine, "", HOST_KERNEL_ID);
+	hists__init(&self->hists);
 
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 5dd83c3e2c0c..c0a028c3ebaf 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,6 +1,5 @@
 #include <dirent.h>
 #include <errno.h>
-#include <libgen.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
@@ -51,6 +50,8 @@ struct symbol_conf symbol_conf = {
 
 int dso__name_len(const struct dso *dso)
 {
+	if (!dso)
+		return strlen("[unknown]");
 	if (verbose)
 		return dso->long_name_len;
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index a4088ced1e64..dfd1bd8371a4 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -722,7 +722,7 @@ static char *event_read_name(void)
 static int event_read_id(void)
 {
 	char *token;
-	int id;
+	int id = -1;
 
 	if (read_expected_item(EVENT_ITEM, "ID") < 0)
 		return -1;
@@ -731,15 +731,13 @@ static int event_read_id(void)
 		return -1;
 
 	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
+		goto free;
 
 	id = strtoul(token, NULL, 0);
-	free_token(token);
-	return id;
 
- fail:
+ free:
 	free_token(token);
-	return -1;
+	return id;
 }
 
 static int field_is_string(struct format_field *field)
diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h
index 84d761b730c1..6ee82f60feaf 100644
--- a/tools/perf/util/ui/browser.h
+++ b/tools/perf/util/ui/browser.h
@@ -49,6 +49,8 @@ int ui_browser__warning(struct ui_browser *browser, int timeout,
 			const char *format, ...);
 int ui_browser__help_window(struct ui_browser *browser, const char *text);
 bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text);
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_sec);
 
 void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence);
 unsigned int ui_browser__argv_refresh(struct ui_browser *browser);
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index fa530fcc764a..d7a1c4afe28b 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -879,6 +879,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	char *options[16];
 	int nr_options = 0;
 	int key = -1;
+	char buf[64];
 
 	if (browser == NULL)
 		return -1;
@@ -933,6 +934,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			goto zoom_dso;
 		case 't':
 			goto zoom_thread;
+		case 's':
+			if (ui_browser__input_window("Symbol to show",
+					"Please enter the name of symbol you want to see",
+					buf, "ENTER: OK, ESC: Cancel",
+					delay_secs * 2) == K_ENTER) {
+				self->symbol_filter_str = *buf ? buf : NULL;
+				hists__filter_by_symbol(self);
+				hist_browser__reset(browser);
+			}
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
@@ -950,7 +961,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					"C             Collapse all callchains\n"
 					"E             Expand all callchains\n"
 					"d             Zoom into current DSO\n"
-					"t             Zoom into current Thread");
+					"t             Zoom into current Thread\n"
+					"s             Filter symbol by name");
 			continue;
 		case K_ENTER:
 		case K_RIGHT:
diff --git a/tools/perf/util/ui/keysyms.h b/tools/perf/util/ui/keysyms.h
index 3458b1985761..809eca5707fa 100644
--- a/tools/perf/util/ui/keysyms.h
+++ b/tools/perf/util/ui/keysyms.h
@@ -16,6 +16,8 @@
 #define K_TAB	'\t'
 #define K_UNTAB	SL_KEY_UNTAB
 #define K_UP	SL_KEY_UP
+#define K_BKSPC 0x7f
+#define K_DEL	SL_KEY_DELETE
 
 /* Not really keys */
 #define K_TIMER	 -1
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 45daa7c41dad..ad4374a16bb0 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -69,6 +69,88 @@ int ui__popup_menu(int argc, char * const argv[])
 	return popup_menu__run(&menu);
 }
 
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_secs)
+{
+	int x, y, len, key;
+	int max_len = 60, nr_lines = 0;
+	static char buf[50];
+	const char *t;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	max_len += 2;
+	nr_lines += 8;
+	y = SLtt_Screen_Rows / 2 - nr_lines / 2;
+	x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, x++, nr_lines, max_len);
+	if (title) {
+		SLsmg_gotorc(y, x + 1);
+		SLsmg_write_string((char *)title);
+	}
+	SLsmg_gotorc(++y, x);
+	nr_lines -= 7;
+	max_len -= 2;
+	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+				   nr_lines, max_len, 1);
+	y += nr_lines;
+	len = 5;
+	while (len--) {
+		SLsmg_gotorc(y + len - 1, x);
+		SLsmg_write_nstring((char *)" ", max_len);
+	}
+	SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
+
+	SLsmg_gotorc(y + 3, x);
+	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_refresh();
+
+	x += 2;
+	len = 0;
+	key = ui__getch(delay_secs);
+	while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
+		if (key == K_BKSPC) {
+			if (len == 0)
+				goto next_key;
+			SLsmg_gotorc(y, x + --len);
+			SLsmg_write_char(' ');
+		} else {
+			buf[len] = key;
+			SLsmg_gotorc(y, x + len++);
+			SLsmg_write_char(key);
+		}
+		SLsmg_refresh();
+
+		/* XXX more graceful overflow handling needed */
+		if (len == sizeof(buf) - 1) {
+			ui_helpline__push("maximum size of symbol name reached!");
+			key = K_ENTER;
+			break;
+		}
+next_key:
+		key = ui__getch(delay_secs);
+	}
+
+	buf[len] = '\0';
+	strncpy(input, buf, len+1);
+	return key;
+}
+
 int ui__question_window(const char *title, const char *text,
 			const char *exit_msg, int delay_secs)
 {
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index e8a03aceceb1..a93e06cfcc2a 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -19,6 +19,16 @@
 # along with this program; if not, write to the Free Software
 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 #
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+ifneq ($(OUTPUT),)
+# check that the output directory actually exists
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
+endif
 
 # --- CONFIGURATION BEGIN ---
 
@@ -87,6 +97,7 @@ AR = $(CROSS)ar
 STRIP = $(CROSS)strip
 RANLIB = $(CROSS)ranlib
 HOSTCC = gcc
+MKDIR = mkdir
 
 
 # Now we set up the build system
@@ -95,7 +106,7 @@ HOSTCC = gcc
 # set up PWD so that older versions of make will work with our build.
 PWD = $(shell pwd)
 
-GMO_FILES = ${shell for HLANG in ${LANGUAGES}; do echo po/$$HLANG.gmo; done;}
+GMO_FILES = ${shell for HLANG in ${LANGUAGES}; do echo $(OUTPUT)po/$$HLANG.gmo; done;}
 
 export CROSS CC AR STRIP RANLIB CFLAGS LDFLAGS LIB_OBJS
 
@@ -122,15 +133,18 @@ UTIL_OBJS =  utils/helpers/amd.o utils/helpers/topology.o utils/helpers/msr.o \
 	utils/cpupower.o utils/cpufreq-info.o utils/cpufreq-set.o \
 	utils/cpupower-set.o utils/cpupower-info.o utils/cpuidle-info.o
 
+UTIL_SRC := $(UTIL_OBJS:.o=.c)
+
+UTIL_OBJS := $(addprefix $(OUTPUT),$(UTIL_OBJS))
+
 UTIL_HEADERS = utils/helpers/helpers.h utils/idle_monitor/cpupower-monitor.h \
 	utils/helpers/bitmask.h \
 	utils/idle_monitor/idle_monitors.h utils/idle_monitor/idle_monitors.def
 
-UTIL_SRC := $(UTIL_OBJS:.o=.c)
-
 LIB_HEADERS = 	lib/cpufreq.h lib/sysfs.h
 LIB_SRC = 	lib/cpufreq.c lib/sysfs.c
 LIB_OBJS = 	lib/cpufreq.o lib/sysfs.o
+LIB_OBJS :=	$(addprefix $(OUTPUT),$(LIB_OBJS))
 
 CFLAGS +=	-pipe
 
@@ -168,83 +182,90 @@ endif
 
 # the actual make rules
 
-all: libcpupower cpupower $(COMPILE_NLS) $(COMPILE_BENCH)
+all: libcpupower $(OUTPUT)cpupower $(COMPILE_NLS) $(COMPILE_BENCH)
 
-lib/%.o: $(LIB_SRC) $(LIB_HEADERS)
+$(OUTPUT)lib/%.o: $(LIB_SRC) $(LIB_HEADERS)
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) $(CFLAGS) -fPIC -o $@ -c lib/$*.c
 
-libcpupower.so.$(LIB_MAJ): $(LIB_OBJS)
+$(OUTPUT)libcpupower.so.$(LIB_MAJ): $(LIB_OBJS)
 	$(ECHO) "  LD      " $@
 	$(QUIET) $(CC) -shared $(CFLAGS) $(LDFLAGS) -o $@ \
 		-Wl,-soname,libcpupower.so.$(LIB_MIN) $(LIB_OBJS)
-	@ln -sf $@ libcpupower.so
-	@ln -sf $@ libcpupower.so.$(LIB_MIN)
+	@ln -sf $(@F) $(OUTPUT)libcpupower.so
+	@ln -sf $(@F) $(OUTPUT)libcpupower.so.$(LIB_MIN)
 
-libcpupower: libcpupower.so.$(LIB_MAJ)
+libcpupower: $(OUTPUT)libcpupower.so.$(LIB_MAJ)
 
 # Let all .o files depend on its .c file and all headers
 # Might be worth to put this into utils/Makefile at some point of time
 $(UTIL_OBJS): $(UTIL_HEADERS)
 
-.c.o:
+$(OUTPUT)%.o: %.c
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) $(CFLAGS) -I./lib -I ./utils -o $@ -c $*.c
 
-cpupower: $(UTIL_OBJS) libcpupower.so.$(LIB_MAJ)
+$(OUTPUT)cpupower: $(UTIL_OBJS) $(OUTPUT)libcpupower.so.$(LIB_MAJ)
 	$(ECHO) "  CC      " $@
-	$(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) -lcpupower -lrt -lpci -L. -o $@ $(UTIL_OBJS)
+	$(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -lrt -lpci -L$(OUTPUT) -o $@
 	$(QUIET) $(STRIPCMD) $@
 
-po/$(PACKAGE).pot: $(UTIL_SRC)
+$(OUTPUT)po/$(PACKAGE).pot: $(UTIL_SRC)
 	$(ECHO) "  GETTEXT " $@
 	$(QUIET) xgettext --default-domain=$(PACKAGE) --add-comments \
-		--keyword=_ --keyword=N_ $(UTIL_SRC) && \
-	test -f $(PACKAGE).po && \
-	mv -f $(PACKAGE).po po/$(PACKAGE).pot
+		--keyword=_ --keyword=N_ $(UTIL_SRC) -p $(@D) -o $(@F)
 
-po/%.gmo: po/%.po
+$(OUTPUT)po/%.gmo: po/%.po
 	$(ECHO) "  MSGFMT  " $@
 	$(QUIET) msgfmt -o $@ po/$*.po
 
 create-gmo: ${GMO_FILES}
 
-update-po: po/$(PACKAGE).pot
+update-po: $(OUTPUT)po/$(PACKAGE).pot
 	$(ECHO) "  MSGMRG  " $@
 	$(QUIET) @for HLANG in $(LANGUAGES); do \
 		echo -n "Updating $$HLANG "; \
-		if msgmerge po/$$HLANG.po po/$(PACKAGE).pot -o \
-		   po/$$HLANG.new.po; then \
-			mv -f po/$$HLANG.new.po po/$$HLANG.po; \
+		if msgmerge po/$$HLANG.po $< -o \
+		   $(OUTPUT)po/$$HLANG.new.po; then \
+			mv -f $(OUTPUT)po/$$HLANG.new.po $(OUTPUT)po/$$HLANG.po; \
 		else \
 			echo "msgmerge for $$HLANG failed!"; \
-			rm -f po/$$HLANG.new.po; \
+			rm -f $(OUTPUT)po/$$HLANG.new.po; \
 		fi; \
 	done;
 
-compile-bench: libcpupower.so.$(LIB_MAJ)
-	@V=$(V) confdir=$(confdir) $(MAKE) -C bench
+compile-bench: $(OUTPUT)libcpupower.so.$(LIB_MAJ)
+	@V=$(V) confdir=$(confdir) $(MAKE) -C bench O=$(OUTPUT)
+
+# we compile into subdirectories. if the target directory is not the
+# source directory, they might not exists. So we depend the various
+# files onto their directories.
+DIRECTORY_DEPS = $(LIB_OBJS) $(UTIL_OBJS) $(GMO_FILES)
+$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS)))
+
+# In the second step, we make a rule to actually create these directories
+$(sort $(dir $(DIRECTORY_DEPS))):
+	$(ECHO) "  MKDIR      " $@
+	$(QUIET) $(MKDIR) -p $@ 2>/dev/null
 
 clean:
-	-find . \( -not -type d \) -and \( -name '*~' -o -name '*.[oas]' \) -type f -print \
+	-find $(OUTPUT) \( -not -type d \) -and \( -name '*~' -o -name '*.[oas]' \) -type f -print \
 	 | xargs rm -f
-	-rm -f $(UTIL_BINS)
-	-rm -f $(IDLE_OBJS)
-	-rm -f cpupower
-	-rm -f libcpupower.so*
-	-rm -rf po/*.gmo po/*.pot
-	$(MAKE) -C bench clean
+	-rm -f $(OUTPUT)cpupower
+	-rm -f $(OUTPUT)libcpupower.so*
+	-rm -rf $(OUTPUT)po/*.{gmo,pot}
+	$(MAKE) -C bench O=$(OUTPUT) clean
 
 
 install-lib:
 	$(INSTALL) -d $(DESTDIR)${libdir}
-	$(CP) libcpupower.so* $(DESTDIR)${libdir}/
+	$(CP) $(OUTPUT)libcpupower.so* $(DESTDIR)${libdir}/
 	$(INSTALL) -d $(DESTDIR)${includedir}
 	$(INSTALL_DATA) lib/cpufreq.h $(DESTDIR)${includedir}/cpufreq.h
 
 install-tools:
 	$(INSTALL) -d $(DESTDIR)${bindir}
-	$(INSTALL_PROGRAM) cpupower $(DESTDIR)${bindir}
+	$(INSTALL_PROGRAM) $(OUTPUT)cpupower $(DESTDIR)${bindir}
 
 install-man:
 	$(INSTALL_DATA) -D man/cpupower.1 $(DESTDIR)${mandir}/man1/cpupower.1
@@ -257,13 +278,13 @@ install-man:
 install-gmo:
 	$(INSTALL) -d $(DESTDIR)${localedir}
 	for HLANG in $(LANGUAGES); do \
-		echo '$(INSTALL_DATA) -D po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo'; \
-		$(INSTALL_DATA) -D po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo; \
+		echo '$(INSTALL_DATA) -D $(OUTPUT)po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo'; \
+		$(INSTALL_DATA) -D $(OUTPUT)po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo; \
 	done;
 
 install-bench:
 	@#DESTDIR must be set from outside to survive
-	@sbindir=$(sbindir) bindir=$(bindir) docdir=$(docdir) confdir=$(confdir) $(MAKE) -C bench install
+	@sbindir=$(sbindir) bindir=$(bindir) docdir=$(docdir) confdir=$(confdir) $(MAKE) -C bench O=$(OUTPUT) install
 
 install: all install-lib install-tools install-man $(INSTALL_NLS) $(INSTALL_BENCH)
 
diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile
index 2b67606fc3e3..7ec7021a29cd 100644
--- a/tools/power/cpupower/bench/Makefile
+++ b/tools/power/cpupower/bench/Makefile
@@ -1,29 +1,36 @@
-LIBS = -L../ -lm -lcpupower
+OUTPUT := ./
+ifeq ("$(origin O)", "command line")
+ifneq ($(O),)
+	OUTPUT := $(O)/
+endif
+endif
 
-OBJS = main.o parse.o system.o benchmark.o
+LIBS = -L../ -L$(OUTPUT) -lm -lcpupower
+
+OBJS = $(OUTPUT)main.o $(OUTPUT)parse.o $(OUTPUT)system.o $(OUTPUT)benchmark.o
 CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\"
 
-%.o : %.c
+$(OUTPUT)%.o : %.c
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) -c $(CFLAGS) $< -o $@
 
-cpufreq-bench: $(OBJS)
+$(OUTPUT)cpufreq-bench: $(OBJS)
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) -o $@ $(CFLAGS) $(OBJS) $(LIBS)
 
-all: cpufreq-bench
+all: $(OUTPUT)cpufreq-bench
 
 install:
 	mkdir -p $(DESTDIR)/$(sbindir)
 	mkdir -p $(DESTDIR)/$(bindir)
 	mkdir -p $(DESTDIR)/$(docdir)
 	mkdir -p $(DESTDIR)/$(confdir)
-	install -m 755 cpufreq-bench $(DESTDIR)/$(sbindir)/cpufreq-bench
+	install -m 755 $(OUTPUT)cpufreq-bench $(DESTDIR)/$(sbindir)/cpufreq-bench
 	install -m 755 cpufreq-bench_plot.sh $(DESTDIR)/$(bindir)/cpufreq-bench_plot.sh
 	install -m 644 README-BENCH $(DESTDIR)/$(docdir)/README-BENCH
 	install -m 755 cpufreq-bench_script.sh $(DESTDIR)/$(docdir)/cpufreq-bench_script.sh
 	install -m 644 example.cfg $(DESTDIR)/$(confdir)/cpufreq-bench.conf
 
 clean:
-	rm -f *.o
-	rm -f cpufreq-bench
+	rm -f $(OUTPUT)*.o
+	rm -f $(OUTPUT)cpufreq-bench
diff --git a/tools/power/cpupower/debug/i386/Makefile b/tools/power/cpupower/debug/i386/Makefile
index d08cc1ead9bc..3ba158f0e287 100644
--- a/tools/power/cpupower/debug/i386/Makefile
+++ b/tools/power/cpupower/debug/i386/Makefile
@@ -1,20 +1,38 @@
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+DESTDIR =
+bindir  = /usr/bin
+
+INSTALL = /usr/bin/install
+
+
 default: all
 
-centrino-decode: centrino-decode.c
-	$(CC) $(CFLAGS) -o centrino-decode centrino-decode.c
+$(OUTPUT)centrino-decode: centrino-decode.c
+	$(CC) $(CFLAGS) -o $@ centrino-decode.c
 
-dump_psb: dump_psb.c
-	$(CC) $(CFLAGS) -o dump_psb dump_psb.c
+$(OUTPUT)dump_psb: dump_psb.c
+	$(CC) $(CFLAGS) -o $@ dump_psb.c
 
-intel_gsic: intel_gsic.c
-	$(CC) $(CFLAGS) -o intel_gsic -llrmi intel_gsic.c
+$(OUTPUT)intel_gsic: intel_gsic.c
+	$(CC) $(CFLAGS) -o $@ -llrmi intel_gsic.c
 
-powernow-k8-decode: powernow-k8-decode.c
-	$(CC) $(CFLAGS) -o powernow-k8-decode powernow-k8-decode.c
+$(OUTPUT)powernow-k8-decode: powernow-k8-decode.c
+	$(CC) $(CFLAGS) -o $@ powernow-k8-decode.c
 
-all: centrino-decode dump_psb intel_gsic powernow-k8-decode
+all: $(OUTPUT)centrino-decode $(OUTPUT)dump_psb $(OUTPUT)intel_gsic $(OUTPUT)powernow-k8-decode
 
 clean:
-	rm -rf centrino-decode dump_psb intel_gsic powernow-k8-decode
+	rm -rf $(OUTPUT){centrino-decode,dump_psb,intel_gsic,powernow-k8-decode}
+
+install:
+	$(INSTALL) -d $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)centrino-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)powernow-k8-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)dump_psb $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)intel_gsic $(DESTDIR)${bindir}
 
-.PHONY: all default clean
+.PHONY: all default clean install
diff --git a/tools/power/cpupower/debug/x86_64/Makefile b/tools/power/cpupower/debug/x86_64/Makefile
index 3326217dd311..1c5214526716 100644
--- a/tools/power/cpupower/debug/x86_64/Makefile
+++ b/tools/power/cpupower/debug/x86_64/Makefile
@@ -1,14 +1,30 @@
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+DESTDIR =
+bindir  = /usr/bin
+
+INSTALL = /usr/bin/install
+
+
 default: all
 
-centrino-decode: ../i386/centrino-decode.c
+$(OUTPUT)centrino-decode: ../i386/centrino-decode.c
 	$(CC) $(CFLAGS) -o $@ $<
 
-powernow-k8-decode: ../i386/powernow-k8-decode.c
+$(OUTPUT)powernow-k8-decode: ../i386/powernow-k8-decode.c
 	$(CC) $(CFLAGS) -o $@ $<
 
-all: centrino-decode powernow-k8-decode
+all: $(OUTPUT)centrino-decode $(OUTPUT)powernow-k8-decode
 
 clean:
-	rm -rf centrino-decode powernow-k8-decode
+	rm -rf $(OUTPUT)centrino-decode $(OUTPUT)powernow-k8-decode
+
+install:
+	$(INSTALL) -d $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)centrino-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)powernow-k8-decode $(DESTDIR)${bindir}
 
-.PHONY: all default clean
+.PHONY: all default clean install
diff --git a/tools/power/cpupower/man/cpupower-frequency-info.1 b/tools/power/cpupower/man/cpupower-frequency-info.1
index bb60a8d1e45a..4a1918ea8f9c 100644
--- a/tools/power/cpupower/man/cpupower-frequency-info.1
+++ b/tools/power/cpupower/man/cpupower-frequency-info.1
@@ -1,4 +1,4 @@
-.TH "cpupower-frequency-info" "1" "0.1" "Mattia Dongili" ""
+.TH "CPUPOWER\-FREQUENCY\-INFO" "1" "0.1" "" "cpupower Manual"
 .SH "NAME"
 .LP 
 cpupower frequency\-info \- Utility to retrieve cpufreq kernel information
@@ -50,8 +50,6 @@ Prints out information like provided by the /proc/cpufreq interface in 2.4. and
 \fB\-m\fR \fB\-\-human\fR
 human\-readable output for the \-f, \-w, \-s and \-y parameters.
 .TP  
-\fB\-h\fR \fB\-\-help\fR
-Prints out the help screen.
 .SH "REMARKS"
 .LP 
 By default only values of core zero are displayed. How to display settings of
diff --git a/tools/power/cpupower/man/cpupower-frequency-set.1 b/tools/power/cpupower/man/cpupower-frequency-set.1
index 685f469093ad..3eacc8d03d1a 100644
--- a/tools/power/cpupower/man/cpupower-frequency-set.1
+++ b/tools/power/cpupower/man/cpupower-frequency-set.1
@@ -1,4 +1,4 @@
-.TH "cpupower-freqency-set" "1" "0.1" "Mattia Dongili" ""
+.TH "CPUPOWER\-FREQUENCY\-SET" "1" "0.1" "" "cpupower Manual"
 .SH "NAME"
 .LP 
 cpupower frequency\-set \- A small tool which allows to modify cpufreq settings.
@@ -26,8 +26,6 @@ specific frequency to be set. Requires userspace governor to be available and lo
 \fB\-r\fR \fB\-\-related\fR
 modify all hardware-related CPUs at the same time
 .TP 
-\fB\-h\fR \fB\-\-help\fR
-Prints out the help screen.
 .SH "REMARKS"
 .LP 
 By default values are applied on all cores. How to modify single core
diff --git a/tools/power/cpupower/man/cpupower-idle-info.1 b/tools/power/cpupower/man/cpupower-idle-info.1
new file mode 100644
index 000000000000..4178effd9e99
--- /dev/null
+++ b/tools/power/cpupower/man/cpupower-idle-info.1
@@ -0,0 +1,90 @@
+.TH "CPUPOWER-IDLE-INFO" "1" "0.1" "" "cpupower Manual"
+.SH "NAME"
+.LP
+cpupower idle\-info \- Utility to retrieve cpu idle kernel information
+.SH "SYNTAX"
+.LP
+cpupower [ \-c cpulist ] idle\-info [\fIoptions\fP]
+.SH "DESCRIPTION"
+.LP
+A tool which prints out per cpu idle information helpful to developers and interested users.
+.SH "OPTIONS"
+.LP
+.TP
+\fB\-f\fR \fB\-\-silent\fR
+Only print a summary of all available C-states in the system.
+.TP
+\fB\-e\fR \fB\-\-proc\fR
+deprecated.
+Prints out idle information in old /proc/acpi/processor/*/power format. This
+interface has been removed from the kernel for quite some time, do not let
+further code depend on this option, best do not use it.
+
+.SH IDLE\-INFO DESCRIPTIONS
+CPU sleep state statistics and descriptions are retrieved from sysfs files,
+exported by the cpuidle kernel subsystem. The kernel only updates these
+statistics when it enters or leaves an idle state, therefore on a very idle or
+a very busy system, these statistics may not be accurate. They still provide a
+good overview about the usage and availability of processor sleep states on
+the platform.
+
+Be aware that the sleep states as exported by the hardware or BIOS and used by
+the Linux kernel may not exactly reflect the capabilities of the
+processor. This often is the case on the X86 architecture when the acpi_idle
+driver is used. It is also possible that the hardware overrules the kernel
+requests, due to internal activity monitors or other reasons.
+On recent X86 platforms it is often possible to read out hardware registers
+which monitor the duration of sleep states the processor resided in. The
+cpupower monitor tool (cpupower\-monitor(1)) can be used to show real sleep
+state residencies. Please refer to the architecture specific description
+section below.
+
+.SH IDLE\-INFO ARCHITECTURE SPECIFIC DESCRIPTIONS
+.SS "X86"
+POLL idle state
+
+If cpuidle is active, X86 platforms have one special idle state.
+The POLL idle state is not a real idle state, it does not save any
+power. Instead, a busy\-loop is executed doing nothing for a short period of
+time. This state is used if the kernel knows that work has to be processed
+very soon and entering any real hardware idle state may result in a slight
+performance penalty.
+
+There exist two different cpuidle drivers on the X86 architecture platform:
+
+"acpi_idle" cpuidle driver
+
+The acpi_idle cpuidle driver retrieves available sleep states (C\-states) from
+the ACPI BIOS tables (from the _CST ACPI function on recent platforms or from
+the FADT BIOS table on older ones).
+The C1 state is not retrieved from ACPI tables. If the C1 state is entered,
+the kernel will call the hlt instruction (or mwait on Intel).
+
+"intel_idle" cpuidle driver
+
+In kernel 2.6.36 the intel_idle driver was introduced.
+It only serves recent Intel CPUs (Nehalem, Westmere, Sandybridge, Atoms or
+newer). On older Intel CPUs the acpi_idle driver is still used (if the BIOS
+provides C\-state ACPI tables).
+The intel_idle driver knows the sleep state capabilities of the processor and
+ignores ACPI BIOS exported processor sleep states tables.
+
+.SH "REMARKS"
+.LP
+By default only values of core zero are displayed. How to display settings of
+other cores is described in the cpupower(1) manpage in the \-\-cpu option
+section.
+.SH REFERENCES
+http://www.acpi.info/spec.htm
+.SH "FILES"
+.nf
+\fI/sys/devices/system/cpu/cpu*/cpuidle/state*\fP
+\fI/sys/devices/system/cpu/cpuidle/*\fP
+.fi
+.SH "AUTHORS"
+.nf
+Thomas Renninger <trenn@suse.de>
+.fi
+.SH "SEE ALSO"
+.LP
+cpupower(1), cpupower\-monitor(1), cpupower\-info(1), cpupower\-set(1)
diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1
index d5cfa265c3d3..1141c2073719 100644
--- a/tools/power/cpupower/man/cpupower-monitor.1
+++ b/tools/power/cpupower/man/cpupower-monitor.1
@@ -107,7 +107,7 @@ Deepest package sleep states may in reality show up as machine/platform wide
 sleep states and can only be entered if all cores are idle. Look up Intel
 manuals (some are provided in the References section) for further details.
 
-.SS "Ontario" "Liano"
+.SS "Fam_12h" "Fam_14h"
 AMD laptop and desktop processor (family 12h and 14h) sleep state counters.
 The registers are accessed via PCI and therefore can still be read out while
 cores have been offlined.
diff --git a/tools/power/cpupower/utils/cpuidle-info.c b/tools/power/cpupower/utils/cpuidle-info.c
index b028267c1376..8145af5f93a6 100644
--- a/tools/power/cpupower/utils/cpuidle-info.c
+++ b/tools/power/cpupower/utils/cpuidle-info.c
@@ -35,17 +35,9 @@ static void cpuidle_cpu_output(unsigned int cpu, int verbose)
 		printf(_("CPU %u: Can't read idle state info\n"), cpu);
 		return;
 	}
-	tmp = sysfs_get_idlestate_name(cpu, idlestates - 1);
-	if (!tmp) {
-		printf(_("Could not determine max idle state %u\n"),
-		       idlestates - 1);
-		return;
-	}
-
 	printf(_("Number of idle states: %d\n"), idlestates);
-
 	printf(_("Available idle states:"));
-	for (idlestate = 1; idlestate < idlestates; idlestate++) {
+	for (idlestate = 0; idlestate < idlestates; idlestate++) {
 		tmp = sysfs_get_idlestate_name(cpu, idlestate);
 		if (!tmp)
 			continue;
@@ -57,7 +49,7 @@ static void cpuidle_cpu_output(unsigned int cpu, int verbose)
 	if (!verbose)
 		return;
 
-	for (idlestate = 1; idlestate < idlestates; idlestate++) {
+	for (idlestate = 0; idlestate < idlestates; idlestate++) {
 		tmp = sysfs_get_idlestate_name(cpu, idlestate);
 		if (!tmp)
 			continue;
diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index 87d5605bdda8..6437ef39aeea 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -112,14 +112,12 @@ int decode_pstates(unsigned int cpu, unsigned int cpu_family,
 int amd_pci_get_num_boost_states(int *active, int *states)
 {
 	struct pci_access *pci_acc;
-	int vendor_id = 0x1022;
-	int boost_dev_ids[4] = {0x1204, 0x1604, 0x1704, 0};
 	struct pci_dev *device;
 	uint8_t val = 0;
 
 	*active = *states = 0;
 
-	device = pci_acc_init(&pci_acc, vendor_id, boost_dev_ids);
+	device = pci_slot_func_init(&pci_acc, 0x18, 4);
 
 	if (device == NULL)
 		return -ENODEV;
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 2747e738efb0..2eb584cf2f55 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -66,8 +66,8 @@ enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL,
 #define CPUPOWER_CAP_AMD_CBP		0x00000004
 #define CPUPOWER_CAP_PERF_BIAS		0x00000008
 #define CPUPOWER_CAP_HAS_TURBO_RATIO	0x00000010
-#define CPUPOWER_CAP_IS_SNB		0x00000011
-#define CPUPOWER_CAP_INTEL_IDA		0x00000012
+#define CPUPOWER_CAP_IS_SNB		0x00000020
+#define CPUPOWER_CAP_INTEL_IDA		0x00000040
 
 #define MAX_HW_PSTATES 10
 
@@ -132,8 +132,11 @@ extern unsigned long long msr_intel_get_turbo_ratio(unsigned int cpu);
 
 /* PCI stuff ****************************/
 extern int amd_pci_get_num_boost_states(int *active, int *states);
-extern struct pci_dev *pci_acc_init(struct pci_access **pacc, int vendor_id,
-				    int *dev_ids);
+extern struct pci_dev *pci_acc_init(struct pci_access **pacc, int domain,
+				    int bus, int slot, int func, int vendor,
+				    int dev);
+extern struct pci_dev *pci_slot_func_init(struct pci_access **pacc,
+					      int slot, int func);
 
 /* PCI stuff ****************************/
 
diff --git a/tools/power/cpupower/utils/helpers/pci.c b/tools/power/cpupower/utils/helpers/pci.c
index cd2eb6fe41c4..9690798e6446 100644
--- a/tools/power/cpupower/utils/helpers/pci.c
+++ b/tools/power/cpupower/utils/helpers/pci.c
@@ -10,19 +10,24 @@
  * **pacc : if a valid pci_dev is returned
  *         *pacc must be passed to pci_acc_cleanup to free it
  *
- * vendor_id : the pci vendor id matching the pci device to access
- * dev_ids :   device ids matching the pci device to access
+ * domain: domain
+ * bus:    bus
+ * slot:   slot
+ * func:   func
+ * vendor: vendor
+ * device: device
+ * Pass -1 for one of the six above to match any
  *
  * Returns :
  * struct pci_dev which can be used with pci_{read,write}_* functions
  *                to access the PCI config space of matching pci devices
  */
-struct pci_dev *pci_acc_init(struct pci_access **pacc, int vendor_id,
-				    int *dev_ids)
+struct pci_dev *pci_acc_init(struct pci_access **pacc, int domain, int bus,
+			     int slot, int func, int vendor, int dev)
 {
-	struct pci_filter filter_nb_link = { -1, -1, -1, -1, vendor_id, 0};
+	struct pci_filter filter_nb_link = { domain, bus, slot, func,
+					     vendor, dev };
 	struct pci_dev *device;
-	unsigned int i;
 
 	*pacc = pci_alloc();
 	if (*pacc == NULL)
@@ -31,14 +36,20 @@ struct pci_dev *pci_acc_init(struct pci_access **pacc, int vendor_id,
 	pci_init(*pacc);
 	pci_scan_bus(*pacc);
 
-	for (i = 0; dev_ids[i] != 0; i++) {
-		filter_nb_link.device = dev_ids[i];
-		for (device = (*pacc)->devices; device; device = device->next) {
-			if (pci_filter_match(&filter_nb_link, device))
-				return device;
-		}
+	for (device = (*pacc)->devices; device; device = device->next) {
+		if (pci_filter_match(&filter_nb_link, device))
+			return device;
 	}
 	pci_cleanup(*pacc);
 	return NULL;
 }
+
+/* Typically one wants to get a specific slot(device)/func of the root domain
+   and bus */
+struct pci_dev *pci_slot_func_init(struct pci_access **pacc, int slot,
+				       int func)
+{
+	return pci_acc_init(pacc, 0, 0, slot, func, -1, -1);
+}
+
 #endif /* defined(__i386__) || defined(__x86_64__) */
diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
index 202e555988be..2116df9ad832 100644
--- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
@@ -20,8 +20,6 @@
 #include "idle_monitor/cpupower-monitor.h"
 #include "helpers/helpers.h"
 
-/******** PCI parts could go into own file and get shared ***************/
-
 #define PCI_NON_PC0_OFFSET	0xb0
 #define PCI_PC1_OFFSET		0xb4
 #define PCI_PC6_OFFSET		0xb8
@@ -82,10 +80,7 @@ static cstate_t amd_fam14h_cstates[AMD_FAM14H_STATE_NUM] = {
 };
 
 static struct pci_access *pci_acc;
-static int pci_vendor_id = 0x1022;
-static int pci_dev_ids[2] = {0x1716, 0};
 static struct pci_dev *amd_fam14h_pci_dev;
-
 static int nbp1_entered;
 
 struct timespec start_time;
@@ -286,13 +281,13 @@ struct cpuidle_monitor *amd_fam14h_register(void)
 	if (cpupower_cpu_info.vendor != X86_VENDOR_AMD)
 		return NULL;
 
-	if (cpupower_cpu_info.family == 0x14) {
-		if (cpu_count <= 0 || cpu_count > 2) {
-			fprintf(stderr, "AMD fam14h: Invalid cpu count: %d\n",
-				cpu_count);
-			return NULL;
-		}
-	} else
+	if (cpupower_cpu_info.family == 0x14)
+		strncpy(amd_fam14h_monitor.name, "Fam_14h",
+			MONITOR_NAME_LEN - 1);
+	else if (cpupower_cpu_info.family == 0x12)
+		strncpy(amd_fam14h_monitor.name, "Fam_12h",
+			MONITOR_NAME_LEN - 1);
+	else
 		return NULL;
 
 	/* We do not alloc for nbp1 machine wide counter */
@@ -303,7 +298,9 @@ struct cpuidle_monitor *amd_fam14h_register(void)
 					      sizeof(unsigned long long));
 	}
 
-	amd_fam14h_pci_dev = pci_acc_init(&pci_acc, pci_vendor_id, pci_dev_ids);
+	/* We need PCI device: Slot 18, Func 6, compare with BKDG
+	   for fam 12h/14h */
+	amd_fam14h_pci_dev = pci_slot_func_init(&pci_acc, 0x18, 6);
 	if (amd_fam14h_pci_dev == NULL || pci_acc == NULL)
 		return NULL;
 
@@ -325,7 +322,7 @@ static void amd_fam14h_unregister(void)
 }
 
 struct cpuidle_monitor amd_fam14h_monitor = {
-	.name			= "Ontario",
+	.name			= "",
 	.hw_states		= amd_fam14h_cstates,
 	.hw_states_num		= AMD_FAM14H_STATE_NUM,
 	.start			= amd_fam14h_start,
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 555c69a5592a..adf175f61496 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -4,11 +4,13 @@ turbostat \- Report processor frequency and idle statistics
 .SH SYNOPSIS
 .ft B
 .B turbostat
+.RB [ "\-s" ]
 .RB [ "\-v" ]
 .RB [ "\-M MSR#" ]
 .RB command
 .br
 .B turbostat
+.RB [ "\-s" ]
 .RB [ "\-v" ]
 .RB [ "\-M MSR#" ]
 .RB [ "\-i interval_sec" ]
@@ -25,6 +27,8 @@ supports an "invariant" TSC, plus the APERF and MPERF MSRs.
 on processors that additionally support C-state residency counters.
 
 .SS Options
+The \fB-s\fP option prints only a 1-line summary for each sample interval.
+.PP
 The \fB-v\fP option increases verbosity.
 .PP
 The \fB-M MSR#\fP option dumps the specified MSR,
@@ -39,13 +43,14 @@ displays the statistics gathered since it was forked.
 .SH FIELD DESCRIPTIONS
 .nf
 \fBpk\fP processor package number.
-\fBcr\fP processor core number.
+\fBcor\fP processor core number.
 \fBCPU\fP Linux CPU (logical processor) number.
+Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology.
 \fB%c0\fP percent of the interval that the CPU retired instructions.
 \fBGHz\fP average clock rate while the CPU was in c0 state.
 \fBTSC\fP average GHz that the TSC ran during the entire interval.
-\fB%c1, %c3, %c6\fP show the percentage residency in hardware core idle states.
-\fB%pc3, %pc6\fP percentage residency in hardware package idle states.
+\fB%c1, %c3, %c6, %c7\fP show the percentage residency in hardware core idle states.
+\fB%pc2, %pc3, %pc6, %pc7\fP percentage residency in hardware package idle states.
 .fi
 .PP
 .SH EXAMPLE
@@ -53,25 +58,37 @@ Without any parameters, turbostat prints out counters ever 5 seconds.
 (override interval with "-i sec" option, or specify a command
 for turbostat to fork).
 
-The first row of statistics reflect the average for the entire system.
+The first row of statistics is a summary for the entire system.
+Note that the summary is a weighted average.
 Subsequent rows show per-CPU statistics.
 
 .nf
 [root@x980]# ./turbostat
-cr   CPU   %c0   GHz  TSC   %c1    %c3    %c6   %pc3   %pc6
-          0.04 1.62 3.38   0.11   0.00  99.85   0.00  95.07
-  0   0   0.04 1.62 3.38   0.06   0.00  99.90   0.00  95.07
-  0   6   0.02 1.62 3.38   0.08   0.00  99.90   0.00  95.07
-  1   2   0.10 1.62 3.38   0.29   0.00  99.61   0.00  95.07
-  1   8   0.11 1.62 3.38   0.28   0.00  99.61   0.00  95.07
-  2   4   0.01 1.62 3.38   0.01   0.00  99.98   0.00  95.07
-  2  10   0.01 1.61 3.38   0.02   0.00  99.98   0.00  95.07
-  8   1   0.07 1.62 3.38   0.15   0.00  99.78   0.00  95.07
-  8   7   0.03 1.62 3.38   0.19   0.00  99.78   0.00  95.07
-  9   3   0.01 1.62 3.38   0.02   0.00  99.98   0.00  95.07
-  9   9   0.01 1.62 3.38   0.02   0.00  99.98   0.00  95.07
- 10   5   0.01 1.62 3.38   0.13   0.00  99.86   0.00  95.07
- 10  11   0.08 1.62 3.38   0.05   0.00  99.86   0.00  95.07
+cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+          0.60 1.63 3.38   2.91   0.00  96.49   0.00  76.64
+  0   0   0.59 1.62 3.38   4.51   0.00  94.90   0.00  76.64
+  0   6   1.13 1.64 3.38   3.97   0.00  94.90   0.00  76.64
+  1   2   0.08 1.62 3.38   0.07   0.00  99.85   0.00  76.64
+  1   8   0.03 1.62 3.38   0.12   0.00  99.85   0.00  76.64
+  2   4   0.01 1.62 3.38   0.06   0.00  99.93   0.00  76.64
+  2  10   0.04 1.62 3.38   0.02   0.00  99.93   0.00  76.64
+  8   1   2.85 1.62 3.38  11.71   0.00  85.44   0.00  76.64
+  8   7   1.98 1.62 3.38  12.58   0.00  85.44   0.00  76.64
+  9   3   0.36 1.62 3.38   0.71   0.00  98.93   0.00  76.64
+  9   9   0.09 1.62 3.38   0.98   0.00  98.93   0.00  76.64
+ 10   5   0.03 1.62 3.38   0.09   0.00  99.87   0.00  76.64
+ 10  11   0.07 1.62 3.38   0.06   0.00  99.87   0.00  76.64
+.fi
+.SH SUMMARY EXAMPLE
+The "-s" option prints the column headers just once,
+and then the one line system summary for each sample interval.
+
+.nf
+[root@x980]# ./turbostat -s
+   %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+  0.61 1.89 3.38   5.95   0.00  93.44   0.00  66.33
+  0.52 1.62 3.38   6.83   0.00  92.65   0.00  61.11
+  0.62 1.92 3.38   5.47   0.00  93.91   0.00  67.31
 .fi
 .SH VERBOSE EXAMPLE
 The "-v" option adds verbosity to the output:
@@ -101,33 +118,33 @@ until ^C while the other CPUs are mostly idle:
 
 .nf
 [root@x980 lenb]# ./turbostat cat /dev/zero > /dev/null
-
-^Ccr   CPU   %c0   GHz  TSC   %c1    %c3    %c6   %pc3   %pc6
-           8.49 3.63 3.38  16.23   0.66  74.63   0.00   0.00
-   0   0   1.22 3.62 3.38  32.18   0.00  66.60   0.00   0.00
-   0   6   0.40 3.61 3.38  33.00   0.00  66.60   0.00   0.00
-   1   2   0.11 3.14 3.38   0.19   3.95  95.75   0.00   0.00
-   1   8   0.05 2.88 3.38   0.25   3.95  95.75   0.00   0.00
-   2   4   0.00 3.13 3.38   0.02   0.00  99.98   0.00   0.00
-   2  10   0.00 3.09 3.38   0.02   0.00  99.98   0.00   0.00
-   8   1   0.04 3.50 3.38  14.43   0.00  85.54   0.00   0.00
-   8   7   0.03 2.98 3.38  14.43   0.00  85.54   0.00   0.00
-   9   3   0.00 3.16 3.38 100.00   0.00   0.00   0.00   0.00
-   9   9  99.93 3.63 3.38   0.06   0.00   0.00   0.00   0.00
-  10   5   0.01 2.82 3.38   0.08   0.00  99.91   0.00   0.00
-  10  11   0.02 3.36 3.38   0.06   0.00  99.91   0.00   0.00
-6.950866 sec
+^C
+cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+          8.63 3.64 3.38  14.46   0.49  76.42   0.00   0.00
+  0   0   0.34 3.36 3.38  99.66   0.00   0.00   0.00   0.00
+  0   6  99.96 3.64 3.38   0.04   0.00   0.00   0.00   0.00
+  1   2   0.14 3.50 3.38   1.75   2.04  96.07   0.00   0.00
+  1   8   0.38 3.57 3.38   1.51   2.04  96.07   0.00   0.00
+  2   4   0.01 2.65 3.38   0.06   0.00  99.93   0.00   0.00
+  2  10   0.03 2.12 3.38   0.04   0.00  99.93   0.00   0.00
+  8   1   0.91 3.59 3.38  35.27   0.92  62.90   0.00   0.00
+  8   7   1.61 3.63 3.38  34.57   0.92  62.90   0.00   0.00
+  9   3   0.04 3.38 3.38   0.20   0.00  99.76   0.00   0.00
+  9   9   0.04 3.29 3.38   0.20   0.00  99.76   0.00   0.00
+ 10   5   0.03 3.08 3.38   0.12   0.00  99.85   0.00   0.00
+ 10  11   0.05 3.07 3.38   0.10   0.00  99.85   0.00   0.00
+4.907015 sec
 
 .fi
-Above the cycle soaker drives cpu9 up 3.6 Ghz turbo limit
+Above the cycle soaker drives cpu6 up 3.6 Ghz turbo limit
 while the other processors are generally in various states of idle.
 
-Note that cpu3 is an HT sibling sharing core9
-with cpu9, and thus it is unable to get to an idle state
-deeper than c1 while cpu9 is busy.
+Note that cpu0 is an HT sibling sharing core0
+with cpu6, and thus it is unable to get to an idle state
+deeper than c1 while cpu6 is busy.
 
-Note that turbostat reports average GHz of 3.61, while
-the arithmetic average of the GHz column above is 3.24.
+Note that turbostat reports average GHz of 3.64, while
+the arithmetic average of the GHz column above is lower.
 This is a weighted average, where the weight is %c0.  ie. it is the total number of
 un-halted cycles elapsed per time divided by the number of CPUs.
 .SH NOTES
@@ -167,6 +184,6 @@ http://www.intel.com/products/processor/manuals/
 .SH "SEE ALSO"
 msr(4), vmstat(8)
 .PP
-.SH AUTHORS
+.SH AUTHOR
 .nf
 Written by Len Brown <len.brown@intel.com>
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 310d3dd5e547..ab2f682fd44c 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2,7 +2,7 @@
  * turbostat -- show CPU frequency and C-state residency
  * on modern Intel turbo-capable processors.
  *
- * Copyright (c) 2010, Intel Corporation.
+ * Copyright (c) 2012 Intel Corporation.
  * Len Brown <len.brown@intel.com>
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -19,6 +19,7 @@
  * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
+#define _GNU_SOURCE
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
@@ -32,6 +33,7 @@
 #include <dirent.h>
 #include <string.h>
 #include <ctype.h>
+#include <sched.h>
 
 #define MSR_TSC	0x10
 #define MSR_NEHALEM_PLATFORM_INFO	0xCE
@@ -49,6 +51,7 @@
 char *proc_stat = "/proc/stat";
 unsigned int interval_sec = 5;	/* set with -i interval_sec */
 unsigned int verbose;		/* set with -v */
+unsigned int summary_only;	/* set with -s */
 unsigned int skip_c0;
 unsigned int skip_c1;
 unsigned int do_nhm_cstates;
@@ -68,9 +71,10 @@ unsigned int show_cpu;
 int aperf_mperf_unstable;
 int backwards_count;
 char *progname;
-int need_reinitialize;
 
 int num_cpus;
+cpu_set_t *cpu_mask;
+size_t cpu_mask_size;
 
 struct counters {
 	unsigned long long tsc;		/* per thread */
@@ -99,44 +103,76 @@ struct timeval tv_even;
 struct timeval tv_odd;
 struct timeval tv_delta;
 
-unsigned long long get_msr(int cpu, off_t offset)
+/*
+ * cpu_mask_init(ncpus)
+ *
+ * allocate and clear cpu_mask
+ * set cpu_mask_size
+ */
+void cpu_mask_init(int ncpus)
+{
+	cpu_mask = CPU_ALLOC(ncpus);
+	if (cpu_mask == NULL) {
+		perror("CPU_ALLOC");
+		exit(3);
+	}
+	cpu_mask_size = CPU_ALLOC_SIZE(ncpus);
+	CPU_ZERO_S(cpu_mask_size, cpu_mask);
+}
+
+void cpu_mask_uninit()
+{
+	CPU_FREE(cpu_mask);
+	cpu_mask = NULL;
+	cpu_mask_size = 0;
+}
+
+int cpu_migrate(int cpu)
+{
+	CPU_ZERO_S(cpu_mask_size, cpu_mask);
+	CPU_SET_S(cpu, cpu_mask_size, cpu_mask);
+	if (sched_setaffinity(0, cpu_mask_size, cpu_mask) == -1)
+		return -1;
+	else
+		return 0;
+}
+
+int get_msr(int cpu, off_t offset, unsigned long long *msr)
 {
 	ssize_t retval;
-	unsigned long long msr;
 	char pathname[32];
 	int fd;
 
 	sprintf(pathname, "/dev/cpu/%d/msr", cpu);
 	fd = open(pathname, O_RDONLY);
-	if (fd < 0) {
-		perror(pathname);
-		need_reinitialize = 1;
-		return 0;
-	}
-
-	retval = pread(fd, &msr, sizeof msr, offset);
-	if (retval != sizeof msr) {
-		fprintf(stderr, "cpu%d pread(..., 0x%zx) = %jd\n",
-			cpu, offset, retval);
-		exit(-2);
-	}
+	if (fd < 0)
+		return -1;
 
+	retval = pread(fd, msr, sizeof *msr, offset);
 	close(fd);
-	return msr;
+
+	if (retval != sizeof *msr)
+		return -1;
+
+	return 0;
 }
 
 void print_header(void)
 {
 	if (show_pkg)
 		fprintf(stderr, "pk");
+	if (show_pkg)
+		fprintf(stderr, " ");
 	if (show_core)
-		fprintf(stderr, " cr");
+		fprintf(stderr, "cor");
 	if (show_cpu)
 		fprintf(stderr, " CPU");
+	if (show_pkg || show_core || show_cpu)
+		fprintf(stderr, " ");
 	if (do_nhm_cstates)
-		fprintf(stderr, "    %%c0 ");
+		fprintf(stderr, "   %%c0");
 	if (has_aperf)
-		fprintf(stderr, " GHz");
+		fprintf(stderr, "  GHz");
 	fprintf(stderr, "  TSC");
 	if (do_nhm_cstates)
 		fprintf(stderr, "    %%c1");
@@ -147,13 +183,13 @@ void print_header(void)
 	if (do_snb_cstates)
 		fprintf(stderr, "    %%c7");
 	if (do_snb_cstates)
-		fprintf(stderr, "  %%pc2");
+		fprintf(stderr, "   %%pc2");
 	if (do_nhm_cstates)
-		fprintf(stderr, "  %%pc3");
+		fprintf(stderr, "   %%pc3");
 	if (do_nhm_cstates)
-		fprintf(stderr, "  %%pc6");
+		fprintf(stderr, "   %%pc6");
 	if (do_snb_cstates)
-		fprintf(stderr, "  %%pc7");
+		fprintf(stderr, "   %%pc7");
 	if (extra_msr_offset)
 		fprintf(stderr, "        MSR 0x%x ", extra_msr_offset);
 
@@ -187,6 +223,15 @@ void dump_list(struct counters *cnt)
 		dump_cnt(cnt);
 }
 
+/*
+ * column formatting convention & formats
+ * package: "pk" 2 columns %2d
+ * core: "cor" 3 columns %3d
+ * CPU: "CPU" 3 columns %3d
+ * GHz: "GHz" 3 columns %3.2
+ * TSC: "TSC" 3 columns %3.2
+ * percentage " %pc3" %6.2
+ */
 void print_cnt(struct counters *p)
 {
 	double interval_float;
@@ -196,39 +241,45 @@ void print_cnt(struct counters *p)
 	/* topology columns, print blanks on 1st (average) line */
 	if (p == cnt_average) {
 		if (show_pkg)
+			fprintf(stderr, "  ");
+		if (show_pkg && show_core)
 			fprintf(stderr, " ");
 		if (show_core)
-			fprintf(stderr, "    ");
+			fprintf(stderr, "   ");
 		if (show_cpu)
-			fprintf(stderr, "    ");
+			fprintf(stderr, " " "   ");
 	} else {
 		if (show_pkg)
-			fprintf(stderr, "%d", p->pkg);
+			fprintf(stderr, "%2d", p->pkg);
+		if (show_pkg && show_core)
+			fprintf(stderr, " ");
 		if (show_core)
-			fprintf(stderr, "%4d", p->core);
+			fprintf(stderr, "%3d", p->core);
 		if (show_cpu)
-			fprintf(stderr, "%4d", p->cpu);
+			fprintf(stderr, " %3d", p->cpu);
 	}
 
 	/* %c0 */
 	if (do_nhm_cstates) {
+		if (show_pkg || show_core || show_cpu)
+			fprintf(stderr, " ");
 		if (!skip_c0)
-			fprintf(stderr, "%7.2f", 100.0 * p->mperf/p->tsc);
+			fprintf(stderr, "%6.2f", 100.0 * p->mperf/p->tsc);
 		else
-			fprintf(stderr, "   ****");
+			fprintf(stderr, "  ****");
 	}
 
 	/* GHz */
 	if (has_aperf) {
 		if (!aperf_mperf_unstable) {
-			fprintf(stderr, "%5.2f",
+			fprintf(stderr, " %3.2f",
 				1.0 * p->tsc / units * p->aperf /
 				p->mperf / interval_float);
 		} else {
 			if (p->aperf > p->tsc || p->mperf > p->tsc) {
-				fprintf(stderr, " ****");
+				fprintf(stderr, " ***");
 			} else {
-				fprintf(stderr, "%4.1f*",
+				fprintf(stderr, "%3.1f*",
 					1.0 * p->tsc /
 					units * p->aperf /
 					p->mperf / interval_float);
@@ -241,7 +292,7 @@ void print_cnt(struct counters *p)
 
 	if (do_nhm_cstates) {
 		if (!skip_c1)
-			fprintf(stderr, "%7.2f", 100.0 * p->c1/p->tsc);
+			fprintf(stderr, " %6.2f", 100.0 * p->c1/p->tsc);
 		else
 			fprintf(stderr, "  ****");
 	}
@@ -252,13 +303,13 @@ void print_cnt(struct counters *p)
 	if (do_snb_cstates)
 		fprintf(stderr, " %6.2f", 100.0 * p->c7/p->tsc);
 	if (do_snb_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc2/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc2/p->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc3/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc3/p->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc6/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc6/p->tsc);
 	if (do_snb_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc7/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc7/p->tsc);
 	if (extra_msr_offset)
 		fprintf(stderr, "  0x%016llx", p->extra_msr);
 	putc('\n', stderr);
@@ -267,12 +318,20 @@ void print_cnt(struct counters *p)
 void print_counters(struct counters *counters)
 {
 	struct counters *cnt;
+	static int printed;
+
 
-	print_header();
+	if (!printed || !summary_only)
+		print_header();
 
 	if (num_cpus > 1)
 		print_cnt(cnt_average);
 
+	printed = 1;
+
+	if (summary_only)
+		return;
+
 	for (cnt = counters; cnt != NULL; cnt = cnt->next)
 		print_cnt(cnt);
 
@@ -440,31 +499,51 @@ void compute_average(struct counters *delta, struct counters *avg)
 	free(sum);
 }
 
-void get_counters(struct counters *cnt)
+int get_counters(struct counters *cnt)
 {
 	for ( ; cnt; cnt = cnt->next) {
-		cnt->tsc = get_msr(cnt->cpu, MSR_TSC);
-		if (do_nhm_cstates)
-			cnt->c3 = get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->c6 = get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY);
-		if (do_snb_cstates)
-			cnt->c7 = get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY);
-		if (has_aperf)
-			cnt->aperf = get_msr(cnt->cpu, MSR_APERF);
-		if (has_aperf)
-			cnt->mperf = get_msr(cnt->cpu, MSR_MPERF);
-		if (do_snb_cstates)
-			cnt->pc2 = get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->pc3 = get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->pc6 = get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY);
+
+		if (cpu_migrate(cnt->cpu))
+			return -1;
+
+		if (get_msr(cnt->cpu, MSR_TSC, &cnt->tsc))
+			return -1;
+
+		if (has_aperf) {
+			if (get_msr(cnt->cpu, MSR_APERF, &cnt->aperf))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_MPERF, &cnt->mperf))
+				return -1;
+		}
+
+		if (do_nhm_cstates) {
+			if (get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY, &cnt->c3))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY, &cnt->c6))
+				return -1;
+		}
+
 		if (do_snb_cstates)
-			cnt->pc7 = get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY);
+			if (get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY, &cnt->c7))
+				return -1;
+
+		if (do_nhm_cstates) {
+			if (get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY, &cnt->pc3))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY, &cnt->pc6))
+				return -1;
+		}
+		if (do_snb_cstates) {
+			if (get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY, &cnt->pc2))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY, &cnt->pc7))
+				return -1;
+		}
 		if (extra_msr_offset)
-			cnt->extra_msr = get_msr(cnt->cpu, extra_msr_offset);
+			if (get_msr(cnt->cpu, extra_msr_offset, &cnt->extra_msr))
+				return -1;
 	}
+	return 0;
 }
 
 void print_nehalem_info(void)
@@ -475,7 +554,7 @@ void print_nehalem_info(void)
 	if (!do_nehalem_platform_info)
 		return;
 
-	msr = get_msr(0, MSR_NEHALEM_PLATFORM_INFO);
+	get_msr(0, MSR_NEHALEM_PLATFORM_INFO, &msr);
 
 	ratio = (msr >> 40) & 0xFF;
 	fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency\n",
@@ -491,7 +570,7 @@ void print_nehalem_info(void)
 	if (!do_nehalem_turbo_ratio_limit)
 		return;
 
-	msr = get_msr(0, MSR_NEHALEM_TURBO_RATIO_LIMIT);
+	get_msr(0, MSR_NEHALEM_TURBO_RATIO_LIMIT, &msr);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
@@ -557,7 +636,8 @@ void insert_counters(struct counters **list,
 		return;
 	}
 
-	show_cpu = 1;	/* there is more than one CPU */
+	if (!summary_only)
+		show_cpu = 1;	/* there is more than one CPU */
 
 	/*
 	 * insert on front of list.
@@ -575,13 +655,15 @@ void insert_counters(struct counters **list,
 
 	while (prev->next && (prev->next->pkg < new->pkg)) {
 		prev = prev->next;
-		show_pkg = 1;	/* there is more than 1 package */
+		if (!summary_only)
+			show_pkg = 1;	/* there is more than 1 package */
 	}
 
 	while (prev->next && (prev->next->pkg == new->pkg)
 		&& (prev->next->core < new->core)) {
 		prev = prev->next;
-		show_core = 1;	/* there is more than 1 core */
+		if (!summary_only)
+			show_core = 1;	/* there is more than 1 core */
 	}
 
 	while (prev->next && (prev->next->pkg == new->pkg)
@@ -681,7 +763,7 @@ int get_core_id(int cpu)
 }
 
 /*
- * run func(index, cpu) on every cpu in /proc/stat
+ * run func(pkg, core, cpu) on every cpu in /proc/stat
  */
 
 int for_all_cpus(void (func)(int, int, int))
@@ -717,18 +799,18 @@ int for_all_cpus(void (func)(int, int, int))
 
 void re_initialize(void)
 {
-	printf("turbostat: topology changed, re-initializing.\n");
 	free_all_counters();
 	num_cpus = for_all_cpus(alloc_new_counters);
-	need_reinitialize = 0;
-	printf("num_cpus is now %d\n", num_cpus);
+	cpu_mask_uninit();
+	cpu_mask_init(num_cpus);
+	printf("turbostat: re-initialized with num_cpus %d\n", num_cpus);
 }
 
 void dummy(int pkg, int core, int cpu) { return; }
 /*
  * check to see if a cpu came on-line
  */
-void verify_num_cpus(void)
+int verify_num_cpus(void)
 {
 	int new_num_cpus;
 
@@ -738,8 +820,9 @@ void verify_num_cpus(void)
 		if (verbose)
 			printf("num_cpus was %d, is now  %d\n",
 				num_cpus, new_num_cpus);
-		need_reinitialize = 1;
+		return -1;
 	}
+	return 0;
 }
 
 void turbostat_loop()
@@ -749,25 +832,25 @@ restart:
 	gettimeofday(&tv_even, (struct timezone *)NULL);
 
 	while (1) {
-		verify_num_cpus();
-		if (need_reinitialize) {
+		if (verify_num_cpus()) {
 			re_initialize();
 			goto restart;
 		}
 		sleep(interval_sec);
-		get_counters(cnt_odd);
+		if (get_counters(cnt_odd)) {
+			re_initialize();
+			goto restart;
+		}
 		gettimeofday(&tv_odd, (struct timezone *)NULL);
-
 		compute_delta(cnt_odd, cnt_even, cnt_delta);
 		timersub(&tv_odd, &tv_even, &tv_delta);
 		compute_average(cnt_delta, cnt_average);
 		print_counters(cnt_delta);
-		if (need_reinitialize) {
+		sleep(interval_sec);
+		if (get_counters(cnt_even)) {
 			re_initialize();
 			goto restart;
 		}
-		sleep(interval_sec);
-		get_counters(cnt_even);
 		gettimeofday(&tv_even, (struct timezone *)NULL);
 		compute_delta(cnt_even, cnt_odd, cnt_delta);
 		timersub(&tv_even, &tv_odd, &tv_delta);
@@ -953,6 +1036,7 @@ void turbostat_init()
 	check_super_user();
 
 	num_cpus = for_all_cpus(alloc_new_counters);
+	cpu_mask_init(num_cpus);
 
 	if (verbose)
 		print_nehalem_info();
@@ -1005,8 +1089,11 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt(argc, argv, "+vi:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "+svi:M:")) != -1) {
 		switch (opt) {
+		case 's':
+			summary_only++;
+			break;
 		case 'v':
 			verbose++;
 			break;
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 4ec84018cc13..28bc57ee757c 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,10 +1,15 @@
-TARGETS = breakpoints
+TARGETS = breakpoints vm
 
 all:
 	for TARGET in $(TARGETS); do \
 		make -C $$TARGET; \
 	done;
 
+run_tests: all
+	for TARGET in $(TARGETS); do \
+		make -C $$TARGET run_tests; \
+	done;
+
 clean:
 	for TARGET in $(TARGETS); do \
 		make -C $$TARGET clean; \
diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile
index f362722cdce7..931278035f5c 100644
--- a/tools/testing/selftests/breakpoints/Makefile
+++ b/tools/testing/selftests/breakpoints/Makefile
@@ -11,10 +11,13 @@ endif
 
 all:
 ifeq ($(ARCH),x86)
-	gcc breakpoint_test.c -o run_test
+	gcc breakpoint_test.c -o breakpoint_test
 else
 	echo "Not an x86 target, can't build breakpoints selftests"
 endif
 
+run_tests:
+	./breakpoint_test
+
 clean:
-	rm -fr run_test
+	rm -fr breakpoint_test
diff --git a/tools/testing/selftests/run_tests b/tools/testing/selftests/run_tests
deleted file mode 100644
index 320718a4e6bf..000000000000
--- a/tools/testing/selftests/run_tests
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/bash
-
-TARGETS=breakpoints
-
-for TARGET in $TARGETS
-do
-	$TARGET/run_test
-done
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
new file mode 100644
index 000000000000..b336b24aa6c0
--- /dev/null
+++ b/tools/testing/selftests/vm/Makefile
@@ -0,0 +1,14 @@
+# Makefile for vm selftests
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra
+
+all: hugepage-mmap hugepage-shm  map_hugetlb
+%: %.c
+	$(CC) $(CFLAGS) -o $@ $^
+
+run_tests: all
+	/bin/sh ./run_vmtests
+
+clean:
+	$(RM) hugepage-mmap hugepage-shm  map_hugetlb
diff --git a/Documentation/vm/hugepage-mmap.c b/tools/testing/selftests/vm/hugepage-mmap.c
index db0dd9a33d54..a10f310d2362 100644
--- a/Documentation/vm/hugepage-mmap.c
+++ b/tools/testing/selftests/vm/hugepage-mmap.c
@@ -22,7 +22,7 @@
 #include <sys/mman.h>
 #include <fcntl.h>
 
-#define FILE_NAME "/mnt/hugepagefile"
+#define FILE_NAME "huge/hugepagefile"
 #define LENGTH (256UL*1024*1024)
 #define PROTECTION (PROT_READ | PROT_WRITE)
 
@@ -48,7 +48,7 @@ static void write_bytes(char *addr)
 		*(addr + i) = (char)i;
 }
 
-static void read_bytes(char *addr)
+static int read_bytes(char *addr)
 {
 	unsigned long i;
 
@@ -56,14 +56,15 @@ static void read_bytes(char *addr)
 	for (i = 0; i < LENGTH; i++)
 		if (*(addr + i) != (char)i) {
 			printf("Mismatch at %lu\n", i);
-			break;
+			return 1;
 		}
+	return 0;
 }
 
 int main(void)
 {
 	void *addr;
-	int fd;
+	int fd, ret;
 
 	fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
 	if (fd < 0) {
@@ -81,11 +82,11 @@ int main(void)
 	printf("Returned address is %p\n", addr);
 	check_bytes(addr);
 	write_bytes(addr);
-	read_bytes(addr);
+	ret = read_bytes(addr);
 
 	munmap(addr, LENGTH);
 	close(fd);
 	unlink(FILE_NAME);
 
-	return 0;
+	return ret;
 }
diff --git a/Documentation/vm/hugepage-shm.c b/tools/testing/selftests/vm/hugepage-shm.c
index 07956d8592c9..0d0ef4fc0c04 100644
--- a/Documentation/vm/hugepage-shm.c
+++ b/tools/testing/selftests/vm/hugepage-shm.c
@@ -57,8 +57,8 @@ int main(void)
 	unsigned long i;
 	char *shmaddr;
 
-	if ((shmid = shmget(2, LENGTH,
-			    SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
+	shmid = shmget(2, LENGTH, SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W);
+	if (shmid < 0) {
 		perror("shmget");
 		exit(1);
 	}
@@ -82,14 +82,16 @@ int main(void)
 
 	dprintf("Starting the Check...");
 	for (i = 0; i < LENGTH; i++)
-		if (shmaddr[i] != (char)i)
+		if (shmaddr[i] != (char)i) {
 			printf("\nIndex %lu mismatched\n", i);
+			exit(3);
+		}
 	dprintf("Done.\n");
 
 	if (shmdt((const void *)shmaddr) != 0) {
 		perror("Detach failure");
 		shmctl(shmid, IPC_RMID, NULL);
-		exit(3);
+		exit(4);
 	}
 
 	shmctl(shmid, IPC_RMID, NULL);
diff --git a/Documentation/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c
index eda1a6d3578a..ac56639dd4a9 100644
--- a/Documentation/vm/map_hugetlb.c
+++ b/tools/testing/selftests/vm/map_hugetlb.c
@@ -44,7 +44,7 @@ static void write_bytes(char *addr)
 		*(addr + i) = (char)i;
 }
 
-static void read_bytes(char *addr)
+static int read_bytes(char *addr)
 {
 	unsigned long i;
 
@@ -52,13 +52,15 @@ static void read_bytes(char *addr)
 	for (i = 0; i < LENGTH; i++)
 		if (*(addr + i) != (char)i) {
 			printf("Mismatch at %lu\n", i);
-			break;
+			return 1;
 		}
+	return 0;
 }
 
 int main(void)
 {
 	void *addr;
+	int ret;
 
 	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, 0, 0);
 	if (addr == MAP_FAILED) {
@@ -69,9 +71,9 @@ int main(void)
 	printf("Returned address is %p\n", addr);
 	check_bytes(addr);
 	write_bytes(addr);
-	read_bytes(addr);
+	ret = read_bytes(addr);
 
 	munmap(addr, LENGTH);
 
-	return 0;
+	return ret;
 }
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
new file mode 100644
index 000000000000..8b40bd5e5cc2
--- /dev/null
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -0,0 +1,77 @@
+#!/bin/bash
+#please run as root
+
+#we need 256M, below is the size in kB
+needmem=262144
+mnt=./huge
+
+#get pagesize and freepages from /proc/meminfo
+while read name size unit; do
+	if [ "$name" = "HugePages_Free:" ]; then
+		freepgs=$size
+	fi
+	if [ "$name" = "Hugepagesize:" ]; then
+		pgsize=$size
+	fi
+done < /proc/meminfo
+
+#set proper nr_hugepages
+if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
+	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
+	needpgs=`expr $needmem / $pgsize`
+	if [ $freepgs -lt $needpgs ]; then
+		lackpgs=$(( $needpgs - $freepgs ))
+		echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
+		if [ $? -ne 0 ]; then
+			echo "Please run this test as root"
+			exit 1
+		fi
+	fi
+else
+	echo "no hugetlbfs support in kernel?"
+	exit 1
+fi
+
+mkdir $mnt
+mount -t hugetlbfs none $mnt
+
+echo "--------------------"
+echo "runing hugepage-mmap"
+echo "--------------------"
+./hugepage-mmap
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+else
+	echo "[PASS]"
+fi
+
+shmmax=`cat /proc/sys/kernel/shmmax`
+shmall=`cat /proc/sys/kernel/shmall`
+echo 268435456 > /proc/sys/kernel/shmmax
+echo 4194304 > /proc/sys/kernel/shmall
+echo "--------------------"
+echo "runing hugepage-shm"
+echo "--------------------"
+./hugepage-shm
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+else
+	echo "[PASS]"
+fi
+echo $shmmax > /proc/sys/kernel/shmmax
+echo $shmall > /proc/sys/kernel/shmall
+
+echo "--------------------"
+echo "runing map_hugetlb"
+echo "--------------------"
+./map_hugetlb
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+else
+	echo "[PASS]"
+fi
+
+#cleanup
+umount $mnt
+rm -rf $mnt
+echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
new file mode 100644
index 000000000000..8e30e5c40f8a
--- /dev/null
+++ b/tools/vm/Makefile
@@ -0,0 +1,11 @@
+# Makefile for vm tools
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra
+
+all: page-types slabinfo
+%: %.c
+	$(CC) $(CFLAGS) -o $@ $^
+
+clean:
+	$(RM) page-types slabinfo
diff --git a/Documentation/vm/page-types.c b/tools/vm/page-types.c
index 0b13f02d4059..7dab7b25b5c6 100644
--- a/Documentation/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -124,7 +124,7 @@
 #define BIT(name)		(1ULL << KPF_##name)
 #define BITS_COMPOUND		(BIT(COMPOUND_HEAD) | BIT(COMPOUND_TAIL))
 
-static const char *page_flag_names[] = {
+static const char * const page_flag_names[] = {
 	[KPF_LOCKED]		= "L:locked",
 	[KPF_ERROR]		= "E:error",
 	[KPF_REFERENCED]	= "R:referenced",
@@ -166,7 +166,7 @@ static const char *page_flag_names[] = {
 };
 
 
-static const char *debugfs_known_mountpoints[] = {
+static const char * const debugfs_known_mountpoints[] = {
 	"/sys/kernel/debug",
 	"/debug",
 	0,
@@ -215,7 +215,7 @@ static int		hwpoison_forget_fd;
 
 static unsigned long	total_pages;
 static unsigned long	nr_pages[HASH_SIZE];
-static uint64_t 	page_flags[HASH_SIZE];
+static uint64_t		page_flags[HASH_SIZE];
 
 
 /*
diff --git a/tools/slub/slabinfo.c b/tools/vm/slabinfo.c
index 164cbcf61106..164cbcf61106 100644
--- a/tools/slub/slabinfo.c
+++ b/tools/vm/slabinfo.c
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 758e3b36d4cf..01f572c10c71 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -49,31 +49,73 @@ static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
 			index = i;
 			break;
 		}
-	if (index < 0) {
+	if (index < 0)
 		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
-		return 0;
-	}
 
 	return index;
 }
 
-static irqreturn_t kvm_assigned_dev_thread(int irq, void *dev_id)
+static irqreturn_t kvm_assigned_dev_intx(int irq, void *dev_id)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	int ret;
+
+	spin_lock(&assigned_dev->intx_lock);
+	if (pci_check_and_mask_intx(assigned_dev->dev)) {
+		assigned_dev->host_irq_disabled = true;
+		ret = IRQ_WAKE_THREAD;
+	} else
+		ret = IRQ_NONE;
+	spin_unlock(&assigned_dev->intx_lock);
+
+	return ret;
+}
 
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_INTX) {
-		spin_lock(&assigned_dev->intx_lock);
+static void
+kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev,
+				 int vector)
+{
+	if (unlikely(assigned_dev->irq_requested_type &
+		     KVM_DEV_IRQ_GUEST_INTX)) {
+		spin_lock(&assigned_dev->intx_mask_lock);
+		if (!(assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX))
+			kvm_set_irq(assigned_dev->kvm,
+				    assigned_dev->irq_source_id, vector, 1);
+		spin_unlock(&assigned_dev->intx_mask_lock);
+	} else
+		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+			    vector, 1);
+}
+
+static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+
+	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+		spin_lock_irq(&assigned_dev->intx_lock);
 		disable_irq_nosync(irq);
 		assigned_dev->host_irq_disabled = true;
-		spin_unlock(&assigned_dev->intx_lock);
+		spin_unlock_irq(&assigned_dev->intx_lock);
 	}
 
-	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-		    assigned_dev->guest_irq, 1);
+	kvm_assigned_dev_raise_guest_irq(assigned_dev,
+					 assigned_dev->guest_irq);
 
 	return IRQ_HANDLED;
 }
 
+#ifdef __KVM_HAVE_MSI
+static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+
+	kvm_assigned_dev_raise_guest_irq(assigned_dev,
+					 assigned_dev->guest_irq);
+
+	return IRQ_HANDLED;
+}
+#endif
+
 #ifdef __KVM_HAVE_MSIX
 static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
 {
@@ -83,8 +125,7 @@ static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
 
 	if (index >= 0) {
 		vector = assigned_dev->guest_msix_entries[index].vector;
-		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-			    vector, 1);
+		kvm_assigned_dev_raise_guest_irq(assigned_dev, vector);
 	}
 
 	return IRQ_HANDLED;
@@ -100,15 +141,31 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 
 	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
 
-	/* The guest irq may be shared so this ack may be
-	 * from another device.
-	 */
-	spin_lock(&dev->intx_lock);
-	if (dev->host_irq_disabled) {
-		enable_irq(dev->host_irq);
-		dev->host_irq_disabled = false;
+	spin_lock(&dev->intx_mask_lock);
+
+	if (!(dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) {
+		bool reassert = false;
+
+		spin_lock_irq(&dev->intx_lock);
+		/*
+		 * The guest IRQ may be shared so this ack can come from an
+		 * IRQ for another guest device.
+		 */
+		if (dev->host_irq_disabled) {
+			if (!(dev->flags & KVM_DEV_ASSIGN_PCI_2_3))
+				enable_irq(dev->host_irq);
+			else if (!pci_check_and_unmask_intx(dev->dev))
+				reassert = true;
+			dev->host_irq_disabled = reassert;
+		}
+		spin_unlock_irq(&dev->intx_lock);
+
+		if (reassert)
+			kvm_set_irq(dev->kvm, dev->irq_source_id,
+				    dev->guest_irq, 1);
 	}
-	spin_unlock(&dev->intx_lock);
+
+	spin_unlock(&dev->intx_mask_lock);
 }
 
 static void deassign_guest_irq(struct kvm *kvm,
@@ -156,7 +213,15 @@ static void deassign_host_irq(struct kvm *kvm,
 		pci_disable_msix(assigned_dev->dev);
 	} else {
 		/* Deal with MSI and INTx */
-		disable_irq(assigned_dev->host_irq);
+		if ((assigned_dev->irq_requested_type &
+		     KVM_DEV_IRQ_HOST_INTX) &&
+		    (assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+			spin_lock_irq(&assigned_dev->intx_lock);
+			pci_intx(assigned_dev->dev, false);
+			spin_unlock_irq(&assigned_dev->intx_lock);
+			synchronize_irq(assigned_dev->host_irq);
+		} else
+			disable_irq(assigned_dev->host_irq);
 
 		free_irq(assigned_dev->host_irq, assigned_dev);
 
@@ -237,15 +302,34 @@ void kvm_free_all_assigned_devices(struct kvm *kvm)
 static int assigned_device_enable_host_intx(struct kvm *kvm,
 					    struct kvm_assigned_dev_kernel *dev)
 {
+	irq_handler_t irq_handler;
+	unsigned long flags;
+
 	dev->host_irq = dev->dev->irq;
-	/* Even though this is PCI, we don't want to use shared
-	 * interrupts. Sharing host devices with guest-assigned devices
-	 * on the same interrupt line is not a happy situation: there
-	 * are going to be long delays in accepting, acking, etc.
+
+	/*
+	 * We can only share the IRQ line with other host devices if we are
+	 * able to disable the IRQ source at device-level - independently of
+	 * the guest driver. Otherwise host devices may suffer from unbounded
+	 * IRQ latencies when the guest keeps the line asserted.
 	 */
-	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
-				 IRQF_ONESHOT, dev->irq_name, dev))
+	if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
+		irq_handler = kvm_assigned_dev_intx;
+		flags = IRQF_SHARED;
+	} else {
+		irq_handler = NULL;
+		flags = IRQF_ONESHOT;
+	}
+	if (request_threaded_irq(dev->host_irq, irq_handler,
+				 kvm_assigned_dev_thread_intx, flags,
+				 dev->irq_name, dev))
 		return -EIO;
+
+	if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
+		spin_lock_irq(&dev->intx_lock);
+		pci_intx(dev->dev, true);
+		spin_unlock_irq(&dev->intx_lock);
+	}
 	return 0;
 }
 
@@ -262,8 +346,9 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
 	}
 
 	dev->host_irq = dev->dev->irq;
-	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
-				 0, dev->irq_name, dev)) {
+	if (request_threaded_irq(dev->host_irq, NULL,
+				 kvm_assigned_dev_thread_msi, 0,
+				 dev->irq_name, dev)) {
 		pci_disable_msi(dev->dev);
 		return -EIO;
 	}
@@ -321,7 +406,6 @@ static int assigned_device_enable_guest_msi(struct kvm *kvm,
 {
 	dev->guest_irq = irq->guest_irq;
 	dev->ack_notifier.gsi = -1;
-	dev->host_irq_disabled = false;
 	return 0;
 }
 #endif
@@ -333,7 +417,6 @@ static int assigned_device_enable_guest_msix(struct kvm *kvm,
 {
 	dev->guest_irq = irq->guest_irq;
 	dev->ack_notifier.gsi = -1;
-	dev->host_irq_disabled = false;
 	return 0;
 }
 #endif
@@ -367,6 +450,7 @@ static int assign_host_irq(struct kvm *kvm,
 	default:
 		r = -EINVAL;
 	}
+	dev->host_irq_disabled = false;
 
 	if (!r)
 		dev->irq_requested_type |= host_irq_type;
@@ -468,6 +552,7 @@ static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
 {
 	int r = -ENODEV;
 	struct kvm_assigned_dev_kernel *match;
+	unsigned long irq_type;
 
 	mutex_lock(&kvm->lock);
 
@@ -476,7 +561,9 @@ static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
 	if (!match)
 		goto out;
 
-	r = kvm_deassign_irq(kvm, match, assigned_irq->flags);
+	irq_type = assigned_irq->flags & (KVM_DEV_IRQ_HOST_MASK |
+					  KVM_DEV_IRQ_GUEST_MASK);
+	r = kvm_deassign_irq(kvm, match, irq_type);
 out:
 	mutex_unlock(&kvm->lock);
 	return r;
@@ -609,6 +696,10 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	if (!match->pci_saved_state)
 		printk(KERN_DEBUG "%s: Couldn't store %s saved state\n",
 		       __func__, dev_name(&dev->dev));
+
+	if (!pci_intx_mask_supported(dev))
+		assigned_dev->flags &= ~KVM_DEV_ASSIGN_PCI_2_3;
+
 	match->assigned_dev_id = assigned_dev->assigned_dev_id;
 	match->host_segnr = assigned_dev->segnr;
 	match->host_busnr = assigned_dev->busnr;
@@ -616,6 +707,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	match->flags = assigned_dev->flags;
 	match->dev = dev;
 	spin_lock_init(&match->intx_lock);
+	spin_lock_init(&match->intx_mask_lock);
 	match->irq_source_id = -1;
 	match->kvm = kvm;
 	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
@@ -761,6 +853,55 @@ msix_entry_out:
 }
 #endif
 
+static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm,
+		struct kvm_assigned_pci_dev *assigned_dev)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *match;
+
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_dev->assigned_dev_id);
+	if (!match) {
+		r = -ENODEV;
+		goto out;
+	}
+
+	spin_lock(&match->intx_mask_lock);
+
+	match->flags &= ~KVM_DEV_ASSIGN_MASK_INTX;
+	match->flags |= assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX;
+
+	if (match->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
+		if (assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX) {
+			kvm_set_irq(match->kvm, match->irq_source_id,
+				    match->guest_irq, 0);
+			/*
+			 * Masking at hardware-level is performed on demand,
+			 * i.e. when an IRQ actually arrives at the host.
+			 */
+		} else if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+			/*
+			 * Unmask the IRQ line if required. Unmasking at
+			 * device level will be performed by user space.
+			 */
+			spin_lock_irq(&match->intx_lock);
+			if (match->host_irq_disabled) {
+				enable_irq(match->host_irq);
+				match->host_irq_disabled = false;
+			}
+			spin_unlock_irq(&match->intx_lock);
+		}
+	}
+
+	spin_unlock(&match->intx_mask_lock);
+
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
 long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 				  unsigned long arg)
 {
@@ -868,6 +1009,15 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 		break;
 	}
 #endif
+	case KVM_ASSIGN_SET_INTX_MASK: {
+		struct kvm_assigned_pci_dev assigned_dev;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+			goto out;
+		r = kvm_vm_ioctl_set_pci_irq_mask(kvm, &assigned_dev);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 		break;
@@ -875,4 +1025,3 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 out:
 	return r;
 }
-
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a91f980077d8..42b73930a6de 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -203,7 +203,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	int dirty_count = kvm->tlbs_dirty;
+	long dirty_count = kvm->tlbs_dirty;
 
 	smp_mb();
 	if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
@@ -289,15 +289,15 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
 	 */
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
+
 	kvm->mmu_notifier_seq++;
 	need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty;
-	spin_unlock(&kvm->mmu_lock);
-	srcu_read_unlock(&kvm->srcu, idx);
-
 	/* we've to flush the tlb before the pages can be freed */
 	if (need_tlb_flush)
 		kvm_flush_remote_tlbs(kvm);
 
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
 }
 
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
@@ -335,12 +335,12 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	for (; start < end; start += PAGE_SIZE)
 		need_tlb_flush |= kvm_unmap_hva(kvm, start);
 	need_tlb_flush |= kvm->tlbs_dirty;
-	spin_unlock(&kvm->mmu_lock);
-	srcu_read_unlock(&kvm->srcu, idx);
-
 	/* we've to flush the tlb before the pages can be freed */
 	if (need_tlb_flush)
 		kvm_flush_remote_tlbs(kvm);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
@@ -357,11 +357,11 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	 * been freed.
 	 */
 	kvm->mmu_notifier_seq++;
+	smp_wmb();
 	/*
 	 * The above sequence increase must be visible before the
-	 * below count decrease but both values are read by the kvm
-	 * page fault under mmu_lock spinlock so we don't need to add
-	 * a smb_wmb() here in between the two.
+	 * below count decrease, which is ensured by the smp_wmb above
+	 * in conjunction with the smp_rmb in mmu_notifier_retry().
 	 */
 	kvm->mmu_notifier_count--;
 	spin_unlock(&kvm->mmu_lock);
@@ -378,13 +378,14 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
-	young = kvm_age_hva(kvm, address);
-	spin_unlock(&kvm->mmu_lock);
-	srcu_read_unlock(&kvm->srcu, idx);
 
+	young = kvm_age_hva(kvm, address);
 	if (young)
 		kvm_flush_remote_tlbs(kvm);
 
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+
 	return young;
 }
 
@@ -449,7 +450,7 @@ static void kvm_init_memslots_id(struct kvm *kvm)
 		slots->id_to_index[i] = slots->memslots[i].id = i;
 }
 
-static struct kvm *kvm_create_vm(void)
+static struct kvm *kvm_create_vm(unsigned long type)
 {
 	int r, i;
 	struct kvm *kvm = kvm_arch_alloc_vm();
@@ -457,7 +458,7 @@ static struct kvm *kvm_create_vm(void)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
-	r = kvm_arch_init_vm(kvm);
+	r = kvm_arch_init_vm(kvm, type);
 	if (r)
 		goto out_err_nodisable;
 
@@ -535,21 +536,13 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
-	int i;
-
 	if (!dont || free->rmap != dont->rmap)
 		vfree(free->rmap);
 
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		kvm_destroy_dirty_bitmap(free);
 
-
-	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
-		if (!dont || free->lpage_info[i] != dont->lpage_info[i]) {
-			vfree(free->lpage_info[i]);
-			free->lpage_info[i] = NULL;
-		}
-	}
+	kvm_arch_free_memslot(free, dont);
 
 	free->npages = 0;
 	free->rmap = NULL;
@@ -616,7 +609,6 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-#ifndef CONFIG_S390
 /*
  * Allocation size is twice as large as the actual dirty bitmap size.
  * This makes it possible to do double buffering: see x86's
@@ -624,6 +616,7 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
  */
 static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
+#ifndef CONFIG_S390
 	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
 	if (dirty_bytes > PAGE_SIZE)
@@ -636,21 +629,8 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 
 	memslot->dirty_bitmap_head = memslot->dirty_bitmap;
 	memslot->nr_dirty_pages = 0;
-	return 0;
-}
 #endif /* !CONFIG_S390 */
-
-static struct kvm_memory_slot *
-search_memslots(struct kvm_memslots *slots, gfn_t gfn)
-{
-	struct kvm_memory_slot *memslot;
-
-	kvm_for_each_memslot(memslot, slots)
-		if (gfn >= memslot->base_gfn &&
-		      gfn < memslot->base_gfn + memslot->npages)
-			return memslot;
-
-	return NULL;
+	return 0;
 }
 
 static int cmp_memslot(const void *slot1, const void *slot2)
@@ -778,69 +758,24 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	r = -ENOMEM;
 
 	/* Allocate if a slot is being created */
+	if (npages && !old.npages) {
+		new.user_alloc = user_alloc;
+		new.userspace_addr = mem->userspace_addr;
 #ifndef CONFIG_S390
-	if (npages && !new.rmap) {
 		new.rmap = vzalloc(npages * sizeof(*new.rmap));
-
 		if (!new.rmap)
 			goto out_free;
-
-		new.user_alloc = user_alloc;
-		new.userspace_addr = mem->userspace_addr;
-	}
-	if (!npages)
-		goto skip_lpage;
-
-	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
-		unsigned long ugfn;
-		unsigned long j;
-		int lpages;
-		int level = i + 2;
-
-		/* Avoid unused variable warning if no large pages */
-		(void)level;
-
-		if (new.lpage_info[i])
-			continue;
-
-		lpages = 1 + ((base_gfn + npages - 1)
-			     >> KVM_HPAGE_GFN_SHIFT(level));
-		lpages -= base_gfn >> KVM_HPAGE_GFN_SHIFT(level);
-
-		new.lpage_info[i] = vzalloc(lpages * sizeof(*new.lpage_info[i]));
-
-		if (!new.lpage_info[i])
+#endif /* not defined CONFIG_S390 */
+		if (kvm_arch_create_memslot(&new, npages))
 			goto out_free;
-
-		if (base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
-			new.lpage_info[i][0].write_count = 1;
-		if ((base_gfn+npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
-			new.lpage_info[i][lpages - 1].write_count = 1;
-		ugfn = new.userspace_addr >> PAGE_SHIFT;
-		/*
-		 * If the gfn and userspace address are not aligned wrt each
-		 * other, or if explicitly asked to, disable large page
-		 * support for this slot
-		 */
-		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) ||
-		    !largepages_enabled)
-			for (j = 0; j < lpages; ++j)
-				new.lpage_info[i][j].write_count = 1;
 	}
 
-skip_lpage:
-
 	/* Allocate page dirty bitmap if needed */
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
 		if (kvm_create_dirty_bitmap(&new) < 0)
 			goto out_free;
 		/* destroy any largepage mappings for dirty tracking */
 	}
-#else  /* not defined CONFIG_S390 */
-	new.user_alloc = user_alloc;
-	if (user_alloc)
-		new.userspace_addr = mem->userspace_addr;
-#endif /* not defined CONFIG_S390 */
 
 	if (!npages) {
 		struct kvm_memory_slot *slot;
@@ -890,8 +825,7 @@ skip_lpage:
 	if (!npages) {
 		new.rmap = NULL;
 		new.dirty_bitmap = NULL;
-		for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i)
-			new.lpage_info[i] = NULL;
+		memset(&new.arch, 0, sizeof(new.arch));
 	}
 
 	update_memslots(slots, &new);
@@ -978,6 +912,11 @@ out:
 	return r;
 }
 
+bool kvm_largepages_enabled(void)
+{
+	return largepages_enabled;
+}
+
 void kvm_disable_largepages(void)
 {
 	largepages_enabled = false;
@@ -1031,12 +970,6 @@ int kvm_is_error_hva(unsigned long addr)
 }
 EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 
-static struct kvm_memory_slot *__gfn_to_memslot(struct kvm_memslots *slots,
-						gfn_t gfn)
-{
-	return search_memslots(slots, gfn);
-}
-
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
@@ -1459,7 +1392,7 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 
 	ghc->gpa = gpa;
 	ghc->generation = slots->generation;
-	ghc->memslot = __gfn_to_memslot(slots, gfn);
+	ghc->memslot = gfn_to_memslot(kvm, gfn);
 	ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL);
 	if (!kvm_is_error_hva(ghc->hva))
 		ghc->hva += offset;
@@ -1657,7 +1590,7 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
 	else
-		return VM_FAULT_SIGBUS;
+		return kvm_arch_vcpu_fault(vcpu, vmf);
 	get_page(page);
 	vmf->page = page;
 	return 0;
@@ -1718,6 +1651,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 		goto vcpu_destroy;
 
 	mutex_lock(&kvm->lock);
+	if (!kvm_vcpu_compatible(vcpu)) {
+		r = -EINVAL;
+		goto unlock_vcpu_destroy;
+	}
 	if (atomic_read(&kvm->online_vcpus) == KVM_MAX_VCPUS) {
 		r = -EINVAL;
 		goto unlock_vcpu_destroy;
@@ -2198,12 +2135,12 @@ static struct file_operations kvm_vm_fops = {
 	.llseek		= noop_llseek,
 };
 
-static int kvm_dev_ioctl_create_vm(void)
+static int kvm_dev_ioctl_create_vm(unsigned long type)
 {
 	int r;
 	struct kvm *kvm;
 
-	kvm = kvm_create_vm();
+	kvm = kvm_create_vm(type);
 	if (IS_ERR(kvm))
 		return PTR_ERR(kvm);
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
@@ -2254,10 +2191,7 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = KVM_API_VERSION;
 		break;
 	case KVM_CREATE_VM:
-		r = -EINVAL;
-		if (arg)
-			goto out;
-		r = kvm_dev_ioctl_create_vm();
+		r = kvm_dev_ioctl_create_vm(arg);
 		break;
 	case KVM_CHECK_EXTENSION:
 		r = kvm_dev_ioctl_check_extension_generic(arg);